diff --git a/Documentation/ABI/testing/sysfs-class-firmware-attributes b/Documentation/ABI/testing/sysfs-class-firmware-attributes index 8ea59fea4709..3348bf80a37c 100644 --- a/Documentation/ABI/testing/sysfs-class-firmware-attributes +++ b/Documentation/ABI/testing/sysfs-class-firmware-attributes @@ -197,8 +197,24 @@ Description: Drivers may emit a CHANGE uevent when a password is set or unset userspace may check it again. - On Dell systems, if Admin password is set, then all BIOS attributes + On Dell and Lenovo systems, if Admin password is set, then all BIOS attributes require password validation. + On Lenovo systems if you change the Admin password the new password is not active until + the next boot. + + Lenovo specific class extensions + ------------------------------ + + On Lenovo systems the following additional settings are available: + + lenovo_encoding: + The encoding method that is used. This can be either "ascii" + or "scancode". Default is set to "ascii" + + lenovo_kbdlang: + The keyboard language method that is used. This is generally a + two char code (e.g. "us", "fr", "gr") and may vary per platform. + Default is set to "us" What: /sys/class/firmware-attributes/*/attributes/pending_reboot Date: February 2021 diff --git a/Documentation/ABI/testing/sysfs-devices-platform-soc-ipa b/Documentation/ABI/testing/sysfs-devices-platform-soc-ipa new file mode 100644 index 000000000000..c56dcf15bf29 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-platform-soc-ipa @@ -0,0 +1,78 @@ +What: /sys/devices/platform/soc@X/XXXXXXX.ipa/ +Date: June 2021 +KernelVersion: v5.14 +Contact: Alex Elder +Description: + The /sys/devices/platform/soc@X/XXXXXXX.ipa/ directory + contains read-only attributes exposing information about + an IPA device. The X values could vary, but are typically + "soc@0/1e40000.ipa". + +What: .../XXXXXXX.ipa/version +Date: June 2021 +KernelVersion: v5.14 +Contact: Alex Elder +Description: + The .../XXXXXXX.ipa/version file contains the IPA hardware + version, as a period-separated set of two or three integers + (e.g., "3.5.1" or "4.2"). + +What: .../XXXXXXX.ipa/feature/ +Date: June 2021 +KernelVersion: v5.14 +Contact: Alex Elder +Description: + The .../XXXXXXX.ipa/feature/ directory contains a set of + attributes describing features implemented by the IPA + hardware. + +What: .../XXXXXXX.ipa/feature/rx_offload +Date: June 2021 +KernelVersion: v5.14 +Contact: Alex Elder +Description: + The .../XXXXXXX.ipa/feature/rx_offload file contains a + string indicating the type of receive checksum offload + that is supported by the hardware. The possible values + are "MAPv4" or "MAPv5". + +What: .../XXXXXXX.ipa/feature/tx_offload +Date: June 2021 +KernelVersion: v5.14 +Contact: Alex Elder +Description: + The .../XXXXXXX.ipa/feature/tx_offload file contains a + string indicating the type of transmit checksum offload + that is supported by the hardware. The possible values + are "MAPv4" or "MAPv5". + +What: .../XXXXXXX.ipa/modem/ +Date: June 2021 +KernelVersion: v5.14 +Contact: Alex Elder +Description: + The .../XXXXXXX.ipa/modem/ directory contains a set of + attributes describing properties of the modem execution + environment reachable by the IPA hardware. + +What: .../XXXXXXX.ipa/modem/rx_endpoint_id +Date: June 2021 +KernelVersion: v5.14 +Contact: Alex Elder +Description: + The .../XXXXXXX.ipa/feature/rx_endpoint_id file contains + the AP endpoint ID that receives packets originating from + the modem execution environment. The "rx" is from the + perspective of the AP; this endpoint is considered an "IPA + producer". An endpoint ID is a small unsigned integer. + +What: .../XXXXXXX.ipa/modem/tx_endpoint_id +Date: June 2021 +KernelVersion: v5.14 +Contact: Alex Elder +Description: + The .../XXXXXXX.ipa/feature/tx_endpoint_id file contains + the AP endpoint ID used to transmit packets destined for + the modem execution environment. The "tx" is from the + perspective of the AP; this endpoint is considered an "IPA + consumer". An endpoint ID is a small unsigned integer. diff --git a/Documentation/ABI/testing/sysfs-platform-dell-privacy-wmi b/Documentation/ABI/testing/sysfs-platform-dell-privacy-wmi new file mode 100644 index 000000000000..7f9e18705861 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-platform-dell-privacy-wmi @@ -0,0 +1,55 @@ +What: /sys/bus/wmi/devices/6932965F-1671-4CEB-B988-D3AB0A901919/dell_privacy_supported_type +Date: Apr 2021 +KernelVersion: 5.13 +Contact: "perry.yuan@dell.com>" +Description: + Display which dell hardware level privacy devices are supported + “Dell Privacy” is a set of HW, FW, and SW features to enhance + Dell’s commitment to platform privacy for MIC, Camera, and + ePrivacy screens. + The supported hardware privacy devices are: +Attributes: + Microphone Mute: + Identifies the local microphone can be muted by hardware, no applications + is available to capture system mic sound + + Camera Shutter: + Identifies camera shutter controlled by hardware, which is a micromechanical + shutter assembly that is built onto the camera module to block capturing images + from outside the laptop + + supported: + The privacy device is supported by this system + + unsupported: + The privacy device is not supported on this system + + For example to check which privacy devices are supported: + + # cat /sys/bus/wmi/drivers/dell-privacy/6932965F-1671-4CEB-B988-D3AB0A901919/dell_privacy_supported_type + [Microphone Mute] [supported] + [Camera Shutter] [supported] + [ePrivacy Screen] [unsupported] + +What: /sys/bus/wmi/devices/6932965F-1671-4CEB-B988-D3AB0A901919/dell_privacy_current_state +Date: Apr 2021 +KernelVersion: 5.13 +Contact: "perry.yuan@dell.com>" +Description: + Allow user space to check current dell privacy device state. + Describes the Device State class exposed by BIOS which can be + consumed by various applications interested in knowing the Privacy + feature capabilities +Attributes: + muted: + Identifies the privacy device is turned off and cannot send stream to OS applications + + unmuted: + Identifies the privacy device is turned on ,audio or camera driver can get + stream from mic and camera module to OS applications + + For example to check all supported current privacy device states: + + # cat /sys/bus/wmi/drivers/dell-privacy/6932965F-1671-4CEB-B988-D3AB0A901919/dell_privacy_current_state + [Microphone] [unmuted] + [Camera Shutter] [unmuted] diff --git a/Documentation/RCU/checklist.rst b/Documentation/RCU/checklist.rst index 1030119294d0..01cc21f17f7b 100644 --- a/Documentation/RCU/checklist.rst +++ b/Documentation/RCU/checklist.rst @@ -211,27 +211,40 @@ over a rather long period of time, but improvements are always welcome! of the system, especially to real-time workloads running on the rest of the system. -7. As of v4.20, a given kernel implements only one RCU flavor, - which is RCU-sched for PREEMPTION=n and RCU-preempt for PREEMPTION=y. - If the updater uses call_rcu() or synchronize_rcu(), - then the corresponding readers may use rcu_read_lock() and - rcu_read_unlock(), rcu_read_lock_bh() and rcu_read_unlock_bh(), - or any pair of primitives that disables and re-enables preemption, - for example, rcu_read_lock_sched() and rcu_read_unlock_sched(). - If the updater uses synchronize_srcu() or call_srcu(), - then the corresponding readers must use srcu_read_lock() and - srcu_read_unlock(), and with the same srcu_struct. The rules for - the expedited primitives are the same as for their non-expedited - counterparts. Mixing things up will result in confusion and - broken kernels, and has even resulted in an exploitable security - issue. +7. As of v4.20, a given kernel implements only one RCU flavor, which + is RCU-sched for PREEMPTION=n and RCU-preempt for PREEMPTION=y. + If the updater uses call_rcu() or synchronize_rcu(), then + the corresponding readers may use: (1) rcu_read_lock() and + rcu_read_unlock(), (2) any pair of primitives that disables + and re-enables softirq, for example, rcu_read_lock_bh() and + rcu_read_unlock_bh(), or (3) any pair of primitives that disables + and re-enables preemption, for example, rcu_read_lock_sched() and + rcu_read_unlock_sched(). If the updater uses synchronize_srcu() + or call_srcu(), then the corresponding readers must use + srcu_read_lock() and srcu_read_unlock(), and with the same + srcu_struct. The rules for the expedited RCU grace-period-wait + primitives are the same as for their non-expedited counterparts. - One exception to this rule: rcu_read_lock() and rcu_read_unlock() - may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh() - in cases where local bottom halves are already known to be - disabled, for example, in irq or softirq context. Commenting - such cases is a must, of course! And the jury is still out on - whether the increased speed is worth it. + If the updater uses call_rcu_tasks() or synchronize_rcu_tasks(), + then the readers must refrain from executing voluntary + context switches, that is, from blocking. If the updater uses + call_rcu_tasks_trace() or synchronize_rcu_tasks_trace(), then + the corresponding readers must use rcu_read_lock_trace() and + rcu_read_unlock_trace(). If an updater uses call_rcu_tasks_rude() + or synchronize_rcu_tasks_rude(), then the corresponding readers + must use anything that disables interrupts. + + Mixing things up will result in confusion and broken kernels, and + has even resulted in an exploitable security issue. Therefore, + when using non-obvious pairs of primitives, commenting is + of course a must. One example of non-obvious pairing is + the XDP feature in networking, which calls BPF programs from + network-driver NAPI (softirq) context. BPF relies heavily on RCU + protection for its data structures, but because the BPF program + invocation happens entirely within a single local_bh_disable() + section in a NAPI poll cycle, this usage is safe. The reason + that this usage is safe is that readers can use anything that + disables BH when updaters use call_rcu() or synchronize_rcu(). 8. Although synchronize_rcu() is slower than is call_rcu(), it usually results in simpler code. So, unless update performance is diff --git a/Documentation/admin-guide/cgroup-v1/blkio-controller.rst b/Documentation/admin-guide/cgroup-v1/blkio-controller.rst index 36d43ae7dc13..16253eda192e 100644 --- a/Documentation/admin-guide/cgroup-v1/blkio-controller.rst +++ b/Documentation/admin-guide/cgroup-v1/blkio-controller.rst @@ -17,36 +17,37 @@ level logical devices like device mapper. HOWTO ===== + Throttling/Upper Limit policy ----------------------------- -- Enable Block IO controller:: +Enable Block IO controller:: CONFIG_BLK_CGROUP=y -- Enable throttling in block layer:: +Enable throttling in block layer:: CONFIG_BLK_DEV_THROTTLING=y -- Mount blkio controller (see cgroups.txt, Why are cgroups needed?):: +Mount blkio controller (see cgroups.txt, Why are cgroups needed?):: mount -t cgroup -o blkio none /sys/fs/cgroup/blkio -- Specify a bandwidth rate on particular device for root group. The format - for policy is ": ":: +Specify a bandwidth rate on particular device for root group. The format +for policy is ": ":: echo "8:16 1048576" > /sys/fs/cgroup/blkio/blkio.throttle.read_bps_device - Above will put a limit of 1MB/second on reads happening for root group - on device having major/minor number 8:16. +This will put a limit of 1MB/second on reads happening for root group +on device having major/minor number 8:16. -- Run dd to read a file and see if rate is throttled to 1MB/s or not:: +Run dd to read a file and see if rate is throttled to 1MB/s or not:: # dd iflag=direct if=/mnt/common/zerofile of=/dev/null bs=4K count=1024 1024+0 records in 1024+0 records out 4194304 bytes (4.2 MB) copied, 4.0001 s, 1.0 MB/s - Limits for writes can be put using blkio.throttle.write_bps_device file. +Limits for writes can be put using blkio.throttle.write_bps_device file. Hierarchical Cgroups ==================== @@ -79,85 +80,89 @@ following:: Various user visible config options =================================== -CONFIG_BLK_CGROUP - - Block IO controller. -CONFIG_BFQ_CGROUP_DEBUG - - Debug help. Right now some additional stats file show up in cgroup + CONFIG_BLK_CGROUP + Block IO controller. + + CONFIG_BFQ_CGROUP_DEBUG + Debug help. Right now some additional stats file show up in cgroup if this option is enabled. -CONFIG_BLK_DEV_THROTTLING - - Enable block device throttling support in block layer. + CONFIG_BLK_DEV_THROTTLING + Enable block device throttling support in block layer. Details of cgroup files ======================= + Proportional weight policy files -------------------------------- -- blkio.weight - - Specifies per cgroup weight. This is default weight of the group - on all the devices until and unless overridden by per device rule. - (See blkio.weight_device). - Currently allowed range of weights is from 10 to 1000. -- blkio.weight_device - - One can specify per cgroup per device rules using this interface. - These rules override the default value of group weight as specified - by blkio.weight. + blkio.bfq.weight + Specifies per cgroup weight. This is default weight of the group + on all the devices until and unless overridden by per device rule + (see `blkio.bfq.weight_device` below). + + Currently allowed range of weights is from 1 to 1000. For more details, + see Documentation/block/bfq-iosched.rst. + + blkio.bfq.weight_device + Specifes per cgroup per device weights, overriding the default group + weight. For more details, see Documentation/block/bfq-iosched.rst. Following is the format:: - # echo dev_maj:dev_minor weight > blkio.weight_device + # echo dev_maj:dev_minor weight > blkio.bfq.weight_device Configure weight=300 on /dev/sdb (8:16) in this cgroup:: - # echo 8:16 300 > blkio.weight_device - # cat blkio.weight_device + # echo 8:16 300 > blkio.bfq.weight_device + # cat blkio.bfq.weight_device dev weight 8:16 300 Configure weight=500 on /dev/sda (8:0) in this cgroup:: - # echo 8:0 500 > blkio.weight_device - # cat blkio.weight_device + # echo 8:0 500 > blkio.bfq.weight_device + # cat blkio.bfq.weight_device dev weight 8:0 500 8:16 300 Remove specific weight for /dev/sda in this cgroup:: - # echo 8:0 0 > blkio.weight_device - # cat blkio.weight_device + # echo 8:0 0 > blkio.bfq.weight_device + # cat blkio.bfq.weight_device dev weight 8:16 300 -- blkio.time - - disk time allocated to cgroup per device in milliseconds. First + blkio.time + Disk time allocated to cgroup per device in milliseconds. First two fields specify the major and minor number of the device and third field specifies the disk time allocated to group in milliseconds. -- blkio.sectors - - number of sectors transferred to/from disk by the group. First + blkio.sectors + Number of sectors transferred to/from disk by the group. First two fields specify the major and minor number of the device and third field specifies the number of sectors transferred by the group to/from the device. -- blkio.io_service_bytes - - Number of bytes transferred to/from the disk by the group. These + blkio.io_service_bytes + Number of bytes transferred to/from the disk by the group. These are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field specifies the number of bytes. -- blkio.io_serviced - - Number of IOs (bio) issued to the disk by the group. These + blkio.io_serviced + Number of IOs (bio) issued to the disk by the group. These are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field specifies the number of IOs. -- blkio.io_service_time - - Total amount of time between request dispatch and request completion + blkio.io_service_time + Total amount of time between request dispatch and request completion for the IOs done by this cgroup. This is in nanoseconds to make it meaningful for flash devices too. For devices with queue depth of 1, this time represents the actual service time. When queue_depth > 1, @@ -170,8 +175,8 @@ Proportional weight policy files specifies the operation type and the fourth field specifies the io_service_time in ns. -- blkio.io_wait_time - - Total amount of time the IOs for this cgroup spent waiting in the + blkio.io_wait_time + Total amount of time the IOs for this cgroup spent waiting in the scheduler queues for service. This can be greater than the total time elapsed since it is cumulative io_wait_time for all IOs. It is not a measure of total time the cgroup spent waiting but rather a measure of @@ -185,24 +190,24 @@ Proportional weight policy files minor number of the device, third field specifies the operation type and the fourth field specifies the io_wait_time in ns. -- blkio.io_merged - - Total number of bios/requests merged into requests belonging to this + blkio.io_merged + Total number of bios/requests merged into requests belonging to this cgroup. This is further divided by the type of operation - read or write, sync or async. -- blkio.io_queued - - Total number of requests queued up at any given instant for this + blkio.io_queued + Total number of requests queued up at any given instant for this cgroup. This is further divided by the type of operation - read or write, sync or async. -- blkio.avg_queue_size - - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. + blkio.avg_queue_size + Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. The average queue size for this cgroup over the entire time of this cgroup's existence. Queue size samples are taken each time one of the queues of this cgroup gets a timeslice. -- blkio.group_wait_time - - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. + blkio.group_wait_time + Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. This is the amount of time the cgroup had to wait since it became busy (i.e., went from 0 to 1 request queued) to get a timeslice for one of its queues. This is different from the io_wait_time which is the @@ -212,8 +217,8 @@ Proportional weight policy files will only report the group_wait_time accumulated till the last time it got a timeslice and will not include the current delta. -- blkio.empty_time - - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. + blkio.empty_time + Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. This is the amount of time a cgroup spends without any pending requests when not being served, i.e., it does not include any time spent idling for one of the queues of the cgroup. This is in @@ -221,8 +226,8 @@ Proportional weight policy files the stat will only report the empty_time accumulated till the last time it had a pending request and will not include the current delta. -- blkio.idle_time - - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. + blkio.idle_time + Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. This is the amount of time spent by the IO scheduler idling for a given cgroup in anticipation of a better request than the existing ones from other queues/cgroups. This is in nanoseconds. If this is read @@ -230,60 +235,60 @@ Proportional weight policy files idle_time accumulated till the last idle period and will not include the current delta. -- blkio.dequeue - - Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. This + blkio.dequeue + Debugging aid only enabled if CONFIG_BFQ_CGROUP_DEBUG=y. This gives the statistics about how many a times a group was dequeued from service tree of the device. First two fields specify the major and minor number of the device and third field specifies the number of times a group was dequeued from a particular device. -- blkio.*_recursive - - Recursive version of various stats. These files show the + blkio.*_recursive + Recursive version of various stats. These files show the same information as their non-recursive counterparts but include stats from all the descendant cgroups. Throttling/Upper limit policy files ----------------------------------- -- blkio.throttle.read_bps_device - - Specifies upper limit on READ rate from the device. IO rate is + blkio.throttle.read_bps_device + Specifies upper limit on READ rate from the device. IO rate is specified in bytes per second. Rules are per device. Following is the format:: echo ": " > /cgrp/blkio.throttle.read_bps_device -- blkio.throttle.write_bps_device - - Specifies upper limit on WRITE rate to the device. IO rate is + blkio.throttle.write_bps_device + Specifies upper limit on WRITE rate to the device. IO rate is specified in bytes per second. Rules are per device. Following is the format:: echo ": " > /cgrp/blkio.throttle.write_bps_device -- blkio.throttle.read_iops_device - - Specifies upper limit on READ rate from the device. IO rate is + blkio.throttle.read_iops_device + Specifies upper limit on READ rate from the device. IO rate is specified in IO per second. Rules are per device. Following is the format:: echo ": " > /cgrp/blkio.throttle.read_iops_device -- blkio.throttle.write_iops_device - - Specifies upper limit on WRITE rate to the device. IO rate is + blkio.throttle.write_iops_device + Specifies upper limit on WRITE rate to the device. IO rate is specified in io per second. Rules are per device. Following is the format:: echo ": " > /cgrp/blkio.throttle.write_iops_device -Note: If both BW and IOPS rules are specified for a device, then IO is - subjected to both the constraints. + Note: If both BW and IOPS rules are specified for a device, then IO is + subjected to both the constraints. -- blkio.throttle.io_serviced - - Number of IOs (bio) issued to the disk by the group. These + blkio.throttle.io_serviced + Number of IOs (bio) issued to the disk by the group. These are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field specifies the number of IOs. -- blkio.throttle.io_service_bytes - - Number of bytes transferred to/from the disk by the group. These + blkio.throttle.io_service_bytes + Number of bytes transferred to/from the disk by the group. These are further divided by the type of operation - read or write, sync or async. First two fields specify the major and minor number of the device, third field specifies the operation type and the fourth field @@ -291,6 +296,6 @@ Note: If both BW and IOPS rules are specified for a device, then IO is Common files among various policies ----------------------------------- -- blkio.reset_stats - - Writing an int to this file will result in resetting all the stats + blkio.reset_stats + Writing an int to this file will result in resetting all the stats for that cgroup. diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index b1e81aa8598a..4e59925e6583 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -56,6 +56,7 @@ v1 is available under :ref:`Documentation/admin-guide/cgroup-v1/index.rst + Format: or acpi_no_auto_serialize [HW,ACPI] Disable auto-serialization of AML methods @@ -586,6 +586,28 @@ loops can be debugged more effectively on production systems. + clocksource.max_cswd_read_retries= [KNL] + Number of clocksource_watchdog() retries due to + external delays before the clock will be marked + unstable. Defaults to three retries, that is, + four attempts to read the clock under test. + + clocksource.verify_n_cpus= [KNL] + Limit the number of CPUs checked for clocksources + marked with CLOCK_SOURCE_VERIFY_PERCPU that + are marked unstable due to excessive skew. + A negative value says to check all CPUs, while + zero says not to check any. Values larger than + nr_cpu_ids are silently truncated to nr_cpu_ids. + The actual CPUs are chosen randomly, with + no replacement if the same CPU is chosen twice. + + clocksource-wdtest.holdoff= [KNL] + Set the time in seconds that the clocksource + watchdog test waits before commencing its tests. + Defaults to zero when built as a module and to + 10 seconds when built into the kernel. + clearcpuid=BITNUM[,BITNUM...] [X86] Disable CPUID feature X for the kernel. See arch/x86/include/asm/cpufeatures.h for the valid bit @@ -3578,6 +3600,12 @@ off: turn off poisoning (default) on: turn on poisoning + page_reporting.page_reporting_order= + [KNL] Minimal page reporting order + Format: + Adjust the minimal page reporting order. The page + reporting is disabled when it exceeds (MAX_ORDER-1). + panic= [KNL] Kernel behaviour on panic: delay timeout > 0: seconds before rebooting timeout = 0: wait forever diff --git a/Documentation/admin-guide/laptops/laptop-mode.rst b/Documentation/admin-guide/laptops/laptop-mode.rst index c984c4262f2e..b61cc601d298 100644 --- a/Documentation/admin-guide/laptops/laptop-mode.rst +++ b/Documentation/admin-guide/laptops/laptop-mode.rst @@ -101,17 +101,6 @@ this results in concentration of disk activity in a small time interval which occurs only once every 10 minutes, or whenever the disk is forced to spin up by a cache miss. The disk can then be spun down in the periods of inactivity. -If you want to find out which process caused the disk to spin up, you can -gather information by setting the flag /proc/sys/vm/block_dump. When this flag -is set, Linux reports all disk read and write operations that take place, and -all block dirtyings done to files. This makes it possible to debug why a disk -needs to spin up, and to increase battery life even more. The output of -block_dump is written to the kernel output, and it can be retrieved using -"dmesg". When you use block_dump and your kernel logging level also includes -kernel debugging messages, you probably want to turn off klogd, otherwise -the output of block_dump will be logged, causing disk activity that is not -normally there. - Configuration ------------- diff --git a/Documentation/admin-guide/lockup-watchdogs.rst b/Documentation/admin-guide/lockup-watchdogs.rst index 290840c160af..3e09284a8b9b 100644 --- a/Documentation/admin-guide/lockup-watchdogs.rst +++ b/Documentation/admin-guide/lockup-watchdogs.rst @@ -39,7 +39,7 @@ in principle, they should work in any architecture where these subsystems are present. A periodic hrtimer runs to generate interrupts and kick the watchdog -task. An NMI perf event is generated every "watchdog_thresh" +job. An NMI perf event is generated every "watchdog_thresh" (compile-time initialized to 10 and configurable through sysctl of the same name) seconds to check for hardlockups. If any CPU in the system does not receive any hrtimer interrupt during that time the @@ -47,7 +47,7 @@ does not receive any hrtimer interrupt during that time the generate a kernel warning or call panic, depending on the configuration. -The watchdog task is a high priority kernel thread that updates a +The watchdog job runs in a stop scheduling thread that updates a timestamp every time it is scheduled. If that timestamp is not updated for 2*watchdog_thresh seconds (the softlockup threshold) the 'softlockup detector' (coded inside the hrtimer callback function) diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst index 10fde58d0869..aec2cd2aaea7 100644 --- a/Documentation/admin-guide/pm/cpuidle.rst +++ b/Documentation/admin-guide/pm/cpuidle.rst @@ -347,81 +347,8 @@ for tickless systems. It follows the same basic strategy as the ``menu`` `one `_: it always tries to find the deepest idle state suitable for the given conditions. However, it applies a different approach to that problem. -First, it does not use sleep length correction factors, but instead it attempts -to correlate the observed idle duration values with the available idle states -and use that information to pick up the idle state that is most likely to -"match" the upcoming CPU idle interval. Second, it does not take the tasks -that were running on the given CPU in the past and are waiting on some I/O -operations to complete now at all (there is no guarantee that they will run on -the same CPU when they become runnable again) and the pattern detection code in -it avoids taking timer wakeups into account. It also only uses idle duration -values less than the current time till the closest timer (with the scheduler -tick excluded) for that purpose. - -Like in the ``menu`` governor `case `_, the first step is to obtain -the *sleep length*, which is the time until the closest timer event with the -assumption that the scheduler tick will be stopped (that also is the upper bound -on the time until the next CPU wakeup). That value is then used to preselect an -idle state on the basis of three metrics maintained for each idle state provided -by the ``CPUIdle`` driver: ``hits``, ``misses`` and ``early_hits``. - -The ``hits`` and ``misses`` metrics measure the likelihood that a given idle -state will "match" the observed (post-wakeup) idle duration if it "matches" the -sleep length. They both are subject to decay (after a CPU wakeup) every time -the target residency of the idle state corresponding to them is less than or -equal to the sleep length and the target residency of the next idle state is -greater than the sleep length (that is, when the idle state corresponding to -them "matches" the sleep length). The ``hits`` metric is increased if the -former condition is satisfied and the target residency of the given idle state -is less than or equal to the observed idle duration and the target residency of -the next idle state is greater than the observed idle duration at the same time -(that is, it is increased when the given idle state "matches" both the sleep -length and the observed idle duration). In turn, the ``misses`` metric is -increased when the given idle state "matches" the sleep length only and the -observed idle duration is too short for its target residency. - -The ``early_hits`` metric measures the likelihood that a given idle state will -"match" the observed (post-wakeup) idle duration if it does not "match" the -sleep length. It is subject to decay on every CPU wakeup and it is increased -when the idle state corresponding to it "matches" the observed (post-wakeup) -idle duration and the target residency of the next idle state is less than or -equal to the sleep length (i.e. the idle state "matching" the sleep length is -deeper than the given one). - -The governor walks the list of idle states provided by the ``CPUIdle`` driver -and finds the last (deepest) one with the target residency less than or equal -to the sleep length. Then, the ``hits`` and ``misses`` metrics of that idle -state are compared with each other and it is preselected if the ``hits`` one is -greater (which means that that idle state is likely to "match" the observed idle -duration after CPU wakeup). If the ``misses`` one is greater, the governor -preselects the shallower idle state with the maximum ``early_hits`` metric -(or if there are multiple shallower idle states with equal ``early_hits`` -metric which also is the maximum, the shallowest of them will be preselected). -[If there is a wakeup latency constraint coming from the `PM QoS framework -`_ which is hit before reaching the deepest idle state with the -target residency within the sleep length, the deepest idle state with the exit -latency within the constraint is preselected without consulting the ``hits``, -``misses`` and ``early_hits`` metrics.] - -Next, the governor takes several idle duration values observed most recently -into consideration and if at least a half of them are greater than or equal to -the target residency of the preselected idle state, that idle state becomes the -final candidate to ask for. Otherwise, the average of the most recent idle -duration values below the target residency of the preselected idle state is -computed and the governor walks the idle states shallower than the preselected -one and finds the deepest of them with the target residency within that average. -That idle state is then taken as the final candidate to ask for. - -Still, at this point the governor may need to refine the idle state selection if -it has not decided to `stop the scheduler tick `_. That -generally happens if the target residency of the idle state selected so far is -less than the tick period and the tick has not been stopped already (in a -previous iteration of the idle loop). Then, like in the ``menu`` governor -`case `_, the sleep length used in the previous computations may not -reflect the real time until the closest timer event and if it really is greater -than that time, a shallower state with a suitable target residency may need to -be selected. - +.. kernel-doc:: drivers/cpuidle/governors/teo.c + :doc: teo-description .. _idle-states-representation: diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst index 7a7d4b041eac..d5043cd8d2f5 100644 --- a/Documentation/admin-guide/pm/intel_pstate.rst +++ b/Documentation/admin-guide/pm/intel_pstate.rst @@ -365,6 +365,9 @@ argument is passed to the kernel in the command line. inclusive) including both turbo and non-turbo P-states (see `Turbo P-states Support`_). + This attribute is present only if the value exposed by it is the same + for all of the CPUs in the system. + The value of this attribute is not affected by the ``no_turbo`` setting described `below `_. @@ -374,6 +377,9 @@ argument is passed to the kernel in the command line. Ratio of the `turbo range `_ size to the size of the entire range of supported P-states, in percent. + This attribute is present only if the value exposed by it is the same + for all of the CPUs in the system. + This attribute is read-only. .. _no_turbo_attr: diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 10dd4b111e5c..426162009ce9 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -1297,11 +1297,11 @@ This parameter can be used to control the soft lockup detector. = ================================= The soft lockup detector monitors CPUs for threads that are hogging the CPUs -without rescheduling voluntarily, and thus prevent the 'watchdog/N' threads -from running. The mechanism depends on the CPUs ability to respond to timer -interrupts which are needed for the 'watchdog/N' threads to be woken up by -the watchdog timer function, otherwise the NMI watchdog — if enabled — can -detect a hard lockup condition. +without rescheduling voluntarily, and thus prevent the 'migration/N' threads +from running, causing the watchdog work fail to execute. The mechanism depends +on the CPUs ability to respond to timer interrupts which are needed for the +watchdog work to be queued by the watchdog timer function, otherwise the NMI +watchdog — if enabled — can detect a hard lockup condition. stack_erasing diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index a8b7573b43f5..4ece86447a3e 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -25,7 +25,6 @@ files can be found in mm/swap.c. Currently, these files are in /proc/sys/vm: - admin_reserve_kbytes -- block_dump - compact_memory - compaction_proactiveness - compact_unevictable_allowed @@ -65,7 +64,7 @@ Currently, these files are in /proc/sys/vm: - overcommit_ratio - page-cluster - panic_on_oom -- percpu_pagelist_fraction +- percpu_pagelist_high_fraction - stat_interval - stat_refresh - numa_stat @@ -107,13 +106,6 @@ On x86_64 this is about 128MB. Changing this takes effect whenever an application requests memory. -block_dump -========== - -block_dump enables block I/O debugging when set to a nonzero value. More -information on block I/O debugging is in Documentation/admin-guide/laptops/laptop-mode.rst. - - compact_memory ============== @@ -806,22 +798,24 @@ panic_on_oom=2+kdump gives you very strong tool to investigate why oom happens. You can get snapshot. -percpu_pagelist_fraction -======================== +percpu_pagelist_high_fraction +============================= -This is the fraction of pages at most (high mark pcp->high) in each zone that -are allocated for each per cpu page list. The min value for this is 8. It -means that we don't allow more than 1/8th of pages in each zone to be -allocated in any single per_cpu_pagelist. This entry only changes the value -of hot per cpu pagelists. User can specify a number like 100 to allocate -1/100th of each zone to each per cpu page list. +This is the fraction of pages in each zone that are can be stored to +per-cpu page lists. It is an upper boundary that is divided depending +on the number of online CPUs. The min value for this is 8 which means +that we do not allow more than 1/8th of pages in each zone to be stored +on per-cpu page lists. This entry only changes the value of hot per-cpu +page lists. A user can specify a number like 100 to allocate 1/100th of +each zone between per-cpu lists. -The batch value of each per cpu pagelist is also updated as a result. It is -set to pcp->high/4. The upper limit of batch is (PAGE_SHIFT * 8) +The batch value of each per-cpu page list remains the same regardless of +the value of the high fraction so allocation latencies are unaffected. -The initial value is zero. Kernel does not use this value at boot time to set -the high water marks for each per cpu page list. If the user writes '0' to this -sysctl, it will revert to this default behavior. +The initial value is zero. Kernel uses this value to set the high pcp->high +mark based on the low watermark for the zone and the number of local +online CPUs. If the user writes '0' to this sysctl, it will revert to +this default behavior. stat_interval @@ -952,12 +946,12 @@ allocations, THP and hugetlbfs pages. To make it sensible with respect to the watermark_scale_factor parameter, the unit is in fractions of 10,000. The default value of -15,000 on !DISCONTIGMEM configurations means that up to 150% of the high -watermark will be reclaimed in the event of a pageblock being mixed due -to fragmentation. The level of reclaim is determined by the number of -fragmentation events that occurred in the recent past. If this value is -smaller than a pageblock then a pageblocks worth of pages will be reclaimed -(e.g. 2MB on 64-bit x86). A boost factor of 0 will disable the feature. +15,000 means that up to 150% of the high watermark will be reclaimed in the +event of a pageblock being mixed due to fragmentation. The level of reclaim +is determined by the number of fragmentation events that occurred in the +recent past. If this value is smaller than a pageblock then a pageblocks +worth of pages will be reclaimed (e.g. 2MB on 64-bit x86). A boost factor +of 0 will disable the feature. watermark_scale_factor diff --git a/Documentation/block/bfq-iosched.rst b/Documentation/block/bfq-iosched.rst index 66c5a4e54130..df3a8a47f58c 100644 --- a/Documentation/block/bfq-iosched.rst +++ b/Documentation/block/bfq-iosched.rst @@ -553,20 +553,36 @@ throughput sustainable with bfq, because updating the blkio.bfq.* stats is rather costly, especially for some of the stats enabled by CONFIG_BFQ_CGROUP_DEBUG. -Parameters to set ------------------ +Parameters +---------- -For each group, there is only the following parameter to set. +For each group, the following parameters can be set: -weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the -group inside its parent. Available values: 1..1000 (default 100). The -linear mapping between ioprio and weights, described at the beginning -of the tunable section, is still valid, but all weights higher than -IOPRIO_BE_NR*10 are mapped to ioprio 0. + weight + This specifies the default weight for the cgroup inside its parent. + Available values: 1..1000 (default: 100). -Recall that, if low-latency is set, then BFQ automatically raises the -weight of the queues associated with interactive and soft real-time -applications. Unset this tunable if you need/want to control weights. + For cgroup v1, it is set by writing the value to `blkio.bfq.weight`. + + For cgroup v2, it is set by writing the value to `io.bfq.weight`. + (with an optional prefix of `default` and a space). + + The linear mapping between ioprio and weights, described at the beginning + of the tunable section, is still valid, but all weights higher than + IOPRIO_BE_NR*10 are mapped to ioprio 0. + + Recall that, if low-latency is set, then BFQ automatically raises the + weight of the queues associated with interactive and soft real-time + applications. Unset this tunable if you need/want to control weights. + + weight_device + This specifies a per-device weight for the cgroup. The syntax is + `minor:major weight`. A weight of `0` may be used to reset to the default + weight. + + For cgroup v1, it is set by writing the value to `blkio.bfq.weight_device`. + + For cgroup v2, the file name is `io.bfq.weight`. [1] diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst index a702f67dd45f..baea6c2abba5 100644 --- a/Documentation/bpf/index.rst +++ b/Documentation/bpf/index.rst @@ -12,6 +12,19 @@ BPF instruction-set. The Cilium project also maintains a `BPF and XDP Reference Guide`_ that goes into great technical depth about the BPF Architecture. +libbpf +====== + +Libbpf is a userspace library for loading and interacting with bpf programs. + +.. toctree:: + :maxdepth: 1 + + libbpf/libbpf + libbpf/libbpf_api + libbpf/libbpf_build + libbpf/libbpf_naming_convention + BPF Type Format (BTF) ===================== @@ -84,6 +97,7 @@ Other :maxdepth: 1 ringbuf + llvm_reloc .. Links: .. _networking-filter: ../networking/filter.rst diff --git a/Documentation/bpf/libbpf/libbpf.rst b/Documentation/bpf/libbpf/libbpf.rst new file mode 100644 index 000000000000..1b1e61d5ead1 --- /dev/null +++ b/Documentation/bpf/libbpf/libbpf.rst @@ -0,0 +1,14 @@ +.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +libbpf +====== + +This is documentation for libbpf, a userspace library for loading and +interacting with bpf programs. + +All general BPF questions, including kernel functionality, libbpf APIs and +their application, should be sent to bpf@vger.kernel.org mailing list. +You can `subscribe `_ to the +mailing list search its `archive `_. +Please search the archive before asking new questions. It very well might +be that this was already addressed or answered before. diff --git a/Documentation/bpf/libbpf/libbpf_api.rst b/Documentation/bpf/libbpf/libbpf_api.rst new file mode 100644 index 000000000000..f07eecd054da --- /dev/null +++ b/Documentation/bpf/libbpf/libbpf_api.rst @@ -0,0 +1,27 @@ +.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +API +=== + +This documentation is autogenerated from header files in libbpf, tools/lib/bpf + +.. kernel-doc:: tools/lib/bpf/libbpf.h + :internal: + +.. kernel-doc:: tools/lib/bpf/bpf.h + :internal: + +.. kernel-doc:: tools/lib/bpf/btf.h + :internal: + +.. kernel-doc:: tools/lib/bpf/xsk.h + :internal: + +.. kernel-doc:: tools/lib/bpf/bpf_tracing.h + :internal: + +.. kernel-doc:: tools/lib/bpf/bpf_core_read.h + :internal: + +.. kernel-doc:: tools/lib/bpf/bpf_endian.h + :internal: \ No newline at end of file diff --git a/Documentation/bpf/libbpf/libbpf_build.rst b/Documentation/bpf/libbpf/libbpf_build.rst new file mode 100644 index 000000000000..8e8c23e8093d --- /dev/null +++ b/Documentation/bpf/libbpf/libbpf_build.rst @@ -0,0 +1,37 @@ +.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +Building libbpf +=============== + +libelf and zlib are internal dependencies of libbpf and thus are required to link +against and must be installed on the system for applications to work. +pkg-config is used by default to find libelf, and the program called +can be overridden with PKG_CONFIG. + +If using pkg-config at build time is not desired, it can be disabled by +setting NO_PKG_CONFIG=1 when calling make. + +To build both static libbpf.a and shared libbpf.so: + +.. code-block:: bash + + $ cd src + $ make + +To build only static libbpf.a library in directory build/ and install them +together with libbpf headers in a staging directory root/: + +.. code-block:: bash + + $ cd src + $ mkdir build root + $ BUILD_STATIC_ONLY=y OBJDIR=build DESTDIR=root make install + +To build both static libbpf.a and shared libbpf.so against a custom libelf +dependency installed in /build/root/ and install them together with libbpf +headers in a build directory /build/root/: + +.. code-block:: bash + + $ cd src + $ PKG_CONFIG_PATH=/build/root/lib64/pkgconfig DESTDIR=/build/root make \ No newline at end of file diff --git a/tools/lib/bpf/README.rst b/Documentation/bpf/libbpf/libbpf_naming_convention.rst similarity index 90% rename from tools/lib/bpf/README.rst rename to Documentation/bpf/libbpf/libbpf_naming_convention.rst index 8928f7787f2d..3de1d51e41da 100644 --- a/tools/lib/bpf/README.rst +++ b/Documentation/bpf/libbpf/libbpf_naming_convention.rst @@ -1,7 +1,7 @@ .. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) -libbpf API naming convention -============================ +API naming convention +===================== libbpf API provides access to a few logically separated groups of functions and types. Every group has its own naming convention @@ -10,14 +10,14 @@ new function or type is added to keep libbpf API clean and consistent. All types and functions provided by libbpf API should have one of the following prefixes: ``bpf_``, ``btf_``, ``libbpf_``, ``xsk_``, -``perf_buffer_``. +``btf_dump_``, ``ring_buffer_``, ``perf_buffer_``. System call wrappers -------------------- System call wrappers are simple wrappers for commands supported by sys_bpf system call. These wrappers should go to ``bpf.h`` header file -and map one-on-one to corresponding commands. +and map one to one to corresponding commands. For example ``bpf_map_lookup_elem`` wraps ``BPF_MAP_LOOKUP_ELEM`` command of sys_bpf, ``bpf_prog_attach`` wraps ``BPF_PROG_ATTACH``, etc. @@ -49,10 +49,6 @@ object, ``bpf_object``, double underscore and ``open`` that defines the purpose of the function to open ELF file and create ``bpf_object`` from it. -Another example: ``bpf_program__load`` is named for corresponding -object, ``bpf_program``, that is separated from other part of the name -by double underscore. - All objects and corresponding functions other than BTF related should go to ``libbpf.h``. BTF types and functions should go to ``btf.h``. @@ -72,11 +68,7 @@ of both low-level ring access functions and high-level configuration functions. These can be mixed and matched. Note that these functions are not reentrant for performance reasons. -Please take a look at Documentation/networking/af_xdp.rst in the Linux -kernel source tree on how to use XDP sockets and for some common -mistakes in case you do not get any traffic up to user space. - -libbpf ABI +ABI ========== libbpf can be both linked statically or used as DSO. To avoid possible @@ -116,7 +108,8 @@ This bump in ABI version is at most once per kernel development cycle. For example, if current state of ``libbpf.map`` is: -.. code-block:: +.. code-block:: c + LIBBPF_0.0.1 { global: bpf_func_a; @@ -128,7 +121,8 @@ For example, if current state of ``libbpf.map`` is: , and a new symbol ``bpf_func_c`` is being introduced, then ``libbpf.map`` should be changed like this: -.. code-block:: +.. code-block:: c + LIBBPF_0.0.1 { global: bpf_func_a; @@ -148,7 +142,7 @@ Format of version script and ways to handle ABI changes, including incompatible ones, described in details in [1]. Stand-alone build -================= +------------------- Under https://github.com/libbpf/libbpf there is a (semi-)automated mirror of the mainline's version of libbpf for a stand-alone build. @@ -157,12 +151,12 @@ However, all changes to libbpf's code base must be upstreamed through the mainline kernel tree. License -======= +------------------- libbpf is dual-licensed under LGPL 2.1 and BSD 2-Clause. Links -===== +------------------- [1] https://www.akkadia.org/drepper/dsohowto.pdf (Chapter 3. Maintaining APIs and ABIs). diff --git a/Documentation/bpf/llvm_reloc.rst b/Documentation/bpf/llvm_reloc.rst new file mode 100644 index 000000000000..ca8957d5b671 --- /dev/null +++ b/Documentation/bpf/llvm_reloc.rst @@ -0,0 +1,240 @@ +.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) + +==================== +BPF LLVM Relocations +==================== + +This document describes LLVM BPF backend relocation types. + +Relocation Record +================= + +LLVM BPF backend records each relocation with the following 16-byte +ELF structure:: + + typedef struct + { + Elf64_Addr r_offset; // Offset from the beginning of section. + Elf64_Xword r_info; // Relocation type and symbol index. + } Elf64_Rel; + +For example, for the following code:: + + int g1 __attribute__((section("sec"))); + int g2 __attribute__((section("sec"))); + static volatile int l1 __attribute__((section("sec"))); + static volatile int l2 __attribute__((section("sec"))); + int test() { + return g1 + g2 + l1 + l2; + } + +Compiled with ``clang -target bpf -O2 -c test.c``, the following is +the code with ``llvm-objdump -dr test.o``:: + + 0: 18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0 ll + 0000000000000000: R_BPF_64_64 g1 + 2: 61 11 00 00 00 00 00 00 r1 = *(u32 *)(r1 + 0) + 3: 18 02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r2 = 0 ll + 0000000000000018: R_BPF_64_64 g2 + 5: 61 20 00 00 00 00 00 00 r0 = *(u32 *)(r2 + 0) + 6: 0f 10 00 00 00 00 00 00 r0 += r1 + 7: 18 01 00 00 08 00 00 00 00 00 00 00 00 00 00 00 r1 = 8 ll + 0000000000000038: R_BPF_64_64 sec + 9: 61 11 00 00 00 00 00 00 r1 = *(u32 *)(r1 + 0) + 10: 0f 10 00 00 00 00 00 00 r0 += r1 + 11: 18 01 00 00 0c 00 00 00 00 00 00 00 00 00 00 00 r1 = 12 ll + 0000000000000058: R_BPF_64_64 sec + 13: 61 11 00 00 00 00 00 00 r1 = *(u32 *)(r1 + 0) + 14: 0f 10 00 00 00 00 00 00 r0 += r1 + 15: 95 00 00 00 00 00 00 00 exit + +There are four relations in the above for four ``LD_imm64`` instructions. +The following ``llvm-readelf -r test.o`` shows the binary values of the four +relocations:: + + Relocation section '.rel.text' at offset 0x190 contains 4 entries: + Offset Info Type Symbol's Value Symbol's Name + 0000000000000000 0000000600000001 R_BPF_64_64 0000000000000000 g1 + 0000000000000018 0000000700000001 R_BPF_64_64 0000000000000004 g2 + 0000000000000038 0000000400000001 R_BPF_64_64 0000000000000000 sec + 0000000000000058 0000000400000001 R_BPF_64_64 0000000000000000 sec + +Each relocation is represented by ``Offset`` (8 bytes) and ``Info`` (8 bytes). +For example, the first relocation corresponds to the first instruction +(Offset 0x0) and the corresponding ``Info`` indicates the relocation type +of ``R_BPF_64_64`` (type 1) and the entry in the symbol table (entry 6). +The following is the symbol table with ``llvm-readelf -s test.o``:: + + Symbol table '.symtab' contains 8 entries: + Num: Value Size Type Bind Vis Ndx Name + 0: 0000000000000000 0 NOTYPE LOCAL DEFAULT UND + 1: 0000000000000000 0 FILE LOCAL DEFAULT ABS test.c + 2: 0000000000000008 4 OBJECT LOCAL DEFAULT 4 l1 + 3: 000000000000000c 4 OBJECT LOCAL DEFAULT 4 l2 + 4: 0000000000000000 0 SECTION LOCAL DEFAULT 4 sec + 5: 0000000000000000 128 FUNC GLOBAL DEFAULT 2 test + 6: 0000000000000000 4 OBJECT GLOBAL DEFAULT 4 g1 + 7: 0000000000000004 4 OBJECT GLOBAL DEFAULT 4 g2 + +The 6th entry is global variable ``g1`` with value 0. + +Similarly, the second relocation is at ``.text`` offset ``0x18``, instruction 3, +for global variable ``g2`` which has a symbol value 4, the offset +from the start of ``.data`` section. + +The third and fourth relocations refers to static variables ``l1`` +and ``l2``. From ``.rel.text`` section above, it is not clear +which symbols they really refers to as they both refers to +symbol table entry 4, symbol ``sec``, which has ``STT_SECTION`` type +and represents a section. So for static variable or function, +the section offset is written to the original insn +buffer, which is called ``A`` (addend). Looking at +above insn ``7`` and ``11``, they have section offset ``8`` and ``12``. +From symbol table, we can find that they correspond to entries ``2`` +and ``3`` for ``l1`` and ``l2``. + +In general, the ``A`` is 0 for global variables and functions, +and is the section offset or some computation result based on +section offset for static variables/functions. The non-section-offset +case refers to function calls. See below for more details. + +Different Relocation Types +========================== + +Six relocation types are supported. The following is an overview and +``S`` represents the value of the symbol in the symbol table:: + + Enum ELF Reloc Type Description BitSize Offset Calculation + 0 R_BPF_NONE None + 1 R_BPF_64_64 ld_imm64 insn 32 r_offset + 4 S + A + 2 R_BPF_64_ABS64 normal data 64 r_offset S + A + 3 R_BPF_64_ABS32 normal data 32 r_offset S + A + 4 R_BPF_64_NODYLD32 .BTF[.ext] data 32 r_offset S + A + 10 R_BPF_64_32 call insn 32 r_offset + 4 (S + A) / 8 - 1 + +For example, ``R_BPF_64_64`` relocation type is used for ``ld_imm64`` instruction. +The actual to-be-relocated data (0 or section offset) +is stored at ``r_offset + 4`` and the read/write +data bitsize is 32 (4 bytes). The relocation can be resolved with +the symbol value plus implicit addend. Note that the ``BitSize`` is 32 which +means the section offset must be less than or equal to ``UINT32_MAX`` and this +is enforced by LLVM BPF backend. + +In another case, ``R_BPF_64_ABS64`` relocation type is used for normal 64-bit data. +The actual to-be-relocated data is stored at ``r_offset`` and the read/write data +bitsize is 64 (8 bytes). The relocation can be resolved with +the symbol value plus implicit addend. + +Both ``R_BPF_64_ABS32`` and ``R_BPF_64_NODYLD32`` types are for 32-bit data. +But ``R_BPF_64_NODYLD32`` specifically refers to relocations in ``.BTF`` and +``.BTF.ext`` sections. For cases like bcc where llvm ``ExecutionEngine RuntimeDyld`` +is involved, ``R_BPF_64_NODYLD32`` types of relocations should not be resolved +to actual function/variable address. Otherwise, ``.BTF`` and ``.BTF.ext`` +become unusable by bcc and kernel. + +Type ``R_BPF_64_32`` is used for call instruction. The call target section +offset is stored at ``r_offset + 4`` (32bit) and calculated as +``(S + A) / 8 - 1``. + +Examples +======== + +Types ``R_BPF_64_64`` and ``R_BPF_64_32`` are used to resolve ``ld_imm64`` +and ``call`` instructions. For example:: + + __attribute__((noinline)) __attribute__((section("sec1"))) + int gfunc(int a, int b) { + return a * b; + } + static __attribute__((noinline)) __attribute__((section("sec1"))) + int lfunc(int a, int b) { + return a + b; + } + int global __attribute__((section("sec2"))); + int test(int a, int b) { + return gfunc(a, b) + lfunc(a, b) + global; + } + +Compiled with ``clang -target bpf -O2 -c test.c``, we will have +following code with `llvm-objdump -dr test.o``:: + + Disassembly of section .text: + + 0000000000000000 : + 0: bf 26 00 00 00 00 00 00 r6 = r2 + 1: bf 17 00 00 00 00 00 00 r7 = r1 + 2: 85 10 00 00 ff ff ff ff call -1 + 0000000000000010: R_BPF_64_32 gfunc + 3: bf 08 00 00 00 00 00 00 r8 = r0 + 4: bf 71 00 00 00 00 00 00 r1 = r7 + 5: bf 62 00 00 00 00 00 00 r2 = r6 + 6: 85 10 00 00 02 00 00 00 call 2 + 0000000000000030: R_BPF_64_32 sec1 + 7: 0f 80 00 00 00 00 00 00 r0 += r8 + 8: 18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0 ll + 0000000000000040: R_BPF_64_64 global + 10: 61 11 00 00 00 00 00 00 r1 = *(u32 *)(r1 + 0) + 11: 0f 10 00 00 00 00 00 00 r0 += r1 + 12: 95 00 00 00 00 00 00 00 exit + + Disassembly of section sec1: + + 0000000000000000 : + 0: bf 20 00 00 00 00 00 00 r0 = r2 + 1: 2f 10 00 00 00 00 00 00 r0 *= r1 + 2: 95 00 00 00 00 00 00 00 exit + + 0000000000000018 : + 3: bf 20 00 00 00 00 00 00 r0 = r2 + 4: 0f 10 00 00 00 00 00 00 r0 += r1 + 5: 95 00 00 00 00 00 00 00 exit + +The first relocation corresponds to ``gfunc(a, b)`` where ``gfunc`` has a value of 0, +so the ``call`` instruction offset is ``(0 + 0)/8 - 1 = -1``. +The second relocation corresponds to ``lfunc(a, b)`` where ``lfunc`` has a section +offset ``0x18``, so the ``call`` instruction offset is ``(0 + 0x18)/8 - 1 = 2``. +The third relocation corresponds to ld_imm64 of ``global``, which has a section +offset ``0``. + +The following is an example to show how R_BPF_64_ABS64 could be generated:: + + int global() { return 0; } + struct t { void *g; } gbl = { global }; + +Compiled with ``clang -target bpf -O2 -g -c test.c``, we will see a +relocation below in ``.data`` section with command +``llvm-readelf -r test.o``:: + + Relocation section '.rel.data' at offset 0x458 contains 1 entries: + Offset Info Type Symbol's Value Symbol's Name + 0000000000000000 0000000700000002 R_BPF_64_ABS64 0000000000000000 global + +The relocation says the first 8-byte of ``.data`` section should be +filled with address of ``global`` variable. + +With ``llvm-readelf`` output, we can see that dwarf sections have a bunch of +``R_BPF_64_ABS32`` and ``R_BPF_64_ABS64`` relocations:: + + Relocation section '.rel.debug_info' at offset 0x468 contains 13 entries: + Offset Info Type Symbol's Value Symbol's Name + 0000000000000006 0000000300000003 R_BPF_64_ABS32 0000000000000000 .debug_abbrev + 000000000000000c 0000000400000003 R_BPF_64_ABS32 0000000000000000 .debug_str + 0000000000000012 0000000400000003 R_BPF_64_ABS32 0000000000000000 .debug_str + 0000000000000016 0000000600000003 R_BPF_64_ABS32 0000000000000000 .debug_line + 000000000000001a 0000000400000003 R_BPF_64_ABS32 0000000000000000 .debug_str + 000000000000001e 0000000200000002 R_BPF_64_ABS64 0000000000000000 .text + 000000000000002b 0000000400000003 R_BPF_64_ABS32 0000000000000000 .debug_str + 0000000000000037 0000000800000002 R_BPF_64_ABS64 0000000000000000 gbl + 0000000000000040 0000000400000003 R_BPF_64_ABS32 0000000000000000 .debug_str + ...... + +The .BTF/.BTF.ext sections has R_BPF_64_NODYLD32 relocations:: + + Relocation section '.rel.BTF' at offset 0x538 contains 1 entries: + Offset Info Type Symbol's Value Symbol's Name + 0000000000000084 0000000800000004 R_BPF_64_NODYLD32 0000000000000000 gbl + + Relocation section '.rel.BTF.ext' at offset 0x548 contains 2 entries: + Offset Info Type Symbol's Value Symbol's Name + 000000000000002c 0000000200000004 R_BPF_64_NODYLD32 0000000000000000 .text + 0000000000000040 0000000200000004 R_BPF_64_NODYLD32 0000000000000000 .text diff --git a/Documentation/core-api/irq/irq-domain.rst b/Documentation/core-api/irq/irq-domain.rst index 8214e215a8bf..53283b3729a1 100644 --- a/Documentation/core-api/irq/irq-domain.rst +++ b/Documentation/core-api/irq/irq-domain.rst @@ -146,7 +146,6 @@ Legacy irq_domain_add_simple() irq_domain_add_legacy() - irq_domain_add_legacy_isa() irq_domain_create_simple() irq_domain_create_legacy() diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst index 385c0cc52f1f..4346ae17a72c 100644 --- a/Documentation/core-api/printk-formats.rst +++ b/Documentation/core-api/printk-formats.rst @@ -513,9 +513,10 @@ Time and date :: %pt[RT] YYYY-mm-ddTHH:MM:SS + %pt[RT]s YYYY-mm-dd HH:MM:SS %pt[RT]d YYYY-mm-dd %pt[RT]t HH:MM:SS - %pt[RT][dt][r] + %pt[RT][dt][r][s] For printing date and time as represented by:: @@ -527,6 +528,10 @@ in human readable format. By default year will be incremented by 1900 and month by 1. Use %pt[RT]r (raw) to suppress this behaviour. +The %pt[RT]s (space) will override ISO 8601 separator by using ' ' (space) +instead of 'T' (Capital T) between date and time. It won't have any effect +when date or time is omitted. + Passed by reference. struct clk diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst index 3a6ae13c663b..5cc404b62d9c 100644 --- a/Documentation/dev-tools/kasan.rst +++ b/Documentation/dev-tools/kasan.rst @@ -447,11 +447,10 @@ When a test fails due to a failed ``kmalloc``:: When a test fails due to a missing KASAN report:: - # kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:629 - Expected kasan_data->report_expected == kasan_data->report_found, but - kasan_data->report_expected == 1 - kasan_data->report_found == 0 - not ok 28 - kmalloc_double_kzfree + # kmalloc_double_kzfree: EXPECTATION FAILED at lib/test_kasan.c:974 + KASAN failure expected in "kfree_sensitive(ptr)", but none occurred + not ok 44 - kmalloc_double_kzfree + At the end the cumulative status of all KASAN tests is printed. On success:: diff --git a/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra30-actmon.txt b/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra30-actmon.txt deleted file mode 100644 index 897eedfa2bc8..000000000000 --- a/Documentation/devicetree/bindings/arm/tegra/nvidia,tegra30-actmon.txt +++ /dev/null @@ -1,57 +0,0 @@ -NVIDIA Tegra Activity Monitor - -The activity monitor block collects statistics about the behaviour of other -components in the system. This information can be used to derive the rate at -which the external memory needs to be clocked in order to serve all requests -from the monitored clients. - -Required properties: -- compatible: should be "nvidia,tegra-actmon" -- reg: offset and length of the register set for the device -- interrupts: standard interrupt property -- clocks: Must contain a phandle and clock specifier pair for each entry in -clock-names. See ../../clock/clock-bindings.txt for details. -- clock-names: Must include the following entries: - - actmon - - emc -- resets: Must contain an entry for each entry in reset-names. See -../../reset/reset.txt for details. -- reset-names: Must include the following entries: - - actmon -- operating-points-v2: See ../bindings/opp/opp.txt for details. -- interconnects: Should contain entries for memory clients sitting on - MC->EMC memory interconnect path. -- interconnect-names: Should include name of the interconnect path for each - interconnect entry. Consult TRM documentation for - information about available memory clients, see MEMORY - CONTROLLER section. - -For each opp entry in 'operating-points-v2' table: -- opp-supported-hw: bitfield indicating SoC speedo ID mask -- opp-peak-kBps: peak bandwidth of the memory channel - -Example: - dfs_opp_table: opp-table { - compatible = "operating-points-v2"; - - opp@12750000 { - opp-hz = /bits/ 64 <12750000>; - opp-supported-hw = <0x000F>; - opp-peak-kBps = <51000>; - }; - ... - }; - - actmon@6000c800 { - compatible = "nvidia,tegra124-actmon"; - reg = <0x0 0x6000c800 0x0 0x400>; - interrupts = ; - clocks = <&tegra_car TEGRA124_CLK_ACTMON>, - <&tegra_car TEGRA124_CLK_EMC>; - clock-names = "actmon", "emc"; - resets = <&tegra_car 119>; - reset-names = "actmon"; - operating-points-v2 = <&dfs_opp_table>; - interconnects = <&mc TEGRA124_MC_MPCORER &emc>; - interconnect-names = "cpu"; - }; diff --git a/Documentation/devicetree/bindings/devfreq/nvidia,tegra30-actmon.yaml b/Documentation/devicetree/bindings/devfreq/nvidia,tegra30-actmon.yaml new file mode 100644 index 000000000000..e3379d106728 --- /dev/null +++ b/Documentation/devicetree/bindings/devfreq/nvidia,tegra30-actmon.yaml @@ -0,0 +1,126 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/devfreq/nvidia,tegra30-actmon.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NVIDIA Tegra30 Activity Monitor + +maintainers: + - Dmitry Osipenko + - Jon Hunter + - Thierry Reding + +description: | + The activity monitor block collects statistics about the behaviour of other + components in the system. This information can be used to derive the rate at + which the external memory needs to be clocked in order to serve all requests + from the monitored clients. + +properties: + compatible: + enum: + - nvidia,tegra30-actmon + - nvidia,tegra114-actmon + - nvidia,tegra124-actmon + - nvidia,tegra210-actmon + + reg: + maxItems: 1 + + clocks: + maxItems: 2 + + clock-names: + items: + - const: actmon + - const: emc + + resets: + maxItems: 1 + + reset-names: + items: + - const: actmon + + interrupts: + maxItems: 1 + + interconnects: + minItems: 1 + maxItems: 12 + + interconnect-names: + minItems: 1 + maxItems: 12 + description: + Should include name of the interconnect path for each interconnect + entry. Consult TRM documentation for information about available + memory clients, see MEMORY CONTROLLER and ACTIVITY MONITOR sections. + + operating-points-v2: + description: + Should contain freqs and voltages and opp-supported-hw property, which + is a bitfield indicating SoC speedo ID mask. + + "#cooling-cells": + const: 2 + +required: + - compatible + - reg + - clocks + - clock-names + - resets + - reset-names + - interrupts + - interconnects + - interconnect-names + - operating-points-v2 + - "#cooling-cells" + +additionalProperties: false + +examples: + - | + #include + + mc: memory-controller@7000f000 { + compatible = "nvidia,tegra30-mc"; + reg = <0x7000f000 0x400>; + clocks = <&clk 32>; + clock-names = "mc"; + + interrupts = <0 77 4>; + + #iommu-cells = <1>; + #reset-cells = <1>; + #interconnect-cells = <1>; + }; + + emc: external-memory-controller@7000f400 { + compatible = "nvidia,tegra30-emc"; + reg = <0x7000f400 0x400>; + interrupts = <0 78 4>; + clocks = <&clk 57>; + + nvidia,memory-controller = <&mc>; + operating-points-v2 = <&dvfs_opp_table>; + power-domains = <&domain>; + + #interconnect-cells = <0>; + }; + + actmon@6000c800 { + compatible = "nvidia,tegra30-actmon"; + reg = <0x6000c800 0x400>; + interrupts = <0 45 4>; + clocks = <&clk 119>, <&clk 57>; + clock-names = "actmon", "emc"; + resets = <&rst 119>; + reset-names = "actmon"; + operating-points-v2 = <&dvfs_opp_table>; + interconnects = <&mc TEGRA30_MC_MPCORER &emc>; + interconnect-names = "cpu-read"; + #cooling-cells = <2>; + }; diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml index 1ecd1831cf02..c84f9fe7f254 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml @@ -145,6 +145,19 @@ properties: required: - affinity + clocks: + maxItems: 1 + + clock-names: + items: + - const: aclk + + power-domains: + maxItems: 1 + + resets: + maxItems: 1 + dependencies: mbi-ranges: [ msi-controller ] msi-controller: [ mbi-ranges ] diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.yaml b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.yaml index b67b8cbd33fc..abb22db3bb28 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.yaml @@ -29,6 +29,7 @@ properties: - renesas,intc-ex-r8a774c0 # RZ/G2E - renesas,intc-ex-r8a7795 # R-Car H3 - renesas,intc-ex-r8a7796 # R-Car M3-W + - renesas,intc-ex-r8a77961 # R-Car M3-W+ - renesas,intc-ex-r8a77965 # R-Car M3-N - renesas,intc-ex-r8a77970 # R-Car V3M - renesas,intc-ex-r8a77980 # R-Car V3H diff --git a/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-kcs-bmc.yaml b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-kcs-bmc.yaml new file mode 100644 index 000000000000..4ff6fabfcb30 --- /dev/null +++ b/Documentation/devicetree/bindings/ipmi/aspeed,ast2400-kcs-bmc.yaml @@ -0,0 +1,106 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/ipmi/aspeed,ast2400-kcs-bmc.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: ASPEED BMC KCS Devices + +maintainers: + - Andrew Jeffery + +description: | + The Aspeed BMC SoCs typically use the Keyboard-Controller-Style (KCS) + interfaces on the LPC bus for in-band IPMI communication with their host. + +properties: + compatible: + oneOf: + - description: Channel ID derived from reg + items: + enum: + - aspeed,ast2400-kcs-bmc-v2 + - aspeed,ast2500-kcs-bmc-v2 + - aspeed,ast2600-kcs-bmc + + - description: Old-style with explicit channel ID, no reg + deprecated: true + items: + enum: + - aspeed,ast2400-kcs-bmc + - aspeed,ast2500-kcs-bmc + + interrupts: + maxItems: 1 + + reg: + # maxItems: 3 + items: + - description: IDR register + - description: ODR register + - description: STR register + + aspeed,lpc-io-reg: + $ref: '/schemas/types.yaml#/definitions/uint32-array' + minItems: 1 + maxItems: 2 + description: | + The host CPU LPC IO data and status addresses for the device. For most + channels the status address is derived from the data address, but the + status address may be optionally provided. + + aspeed,lpc-interrupts: + $ref: "/schemas/types.yaml#/definitions/uint32-array" + minItems: 2 + maxItems: 2 + description: | + A 2-cell property expressing the LPC SerIRQ number and the interrupt + level/sense encoding (specified in the standard fashion). + + Note that the generated interrupt is issued from the BMC to the host, and + thus the target interrupt controller is not captured by the BMC's + devicetree. + + kcs_chan: + deprecated: true + $ref: '/schemas/types.yaml#/definitions/uint32' + description: The LPC channel number in the controller + + kcs_addr: + deprecated: true + $ref: '/schemas/types.yaml#/definitions/uint32' + description: The host CPU IO map address + +required: + - compatible + - interrupts + +additionalProperties: false + +allOf: + - if: + properties: + compatible: + contains: + enum: + - aspeed,ast2400-kcs-bmc + - aspeed,ast2500-kcs-bmc + then: + required: + - kcs_chan + - kcs_addr + else: + required: + - reg + - aspeed,lpc-io-reg + +examples: + - | + #include + kcs3: kcs@24 { + compatible = "aspeed,ast2600-kcs-bmc"; + reg = <0x24 0x1>, <0x30 0x1>, <0x3c 0x1>; + aspeed,lpc-io-reg = <0xca2>; + aspeed,lpc-interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + interrupts = <8>; + }; diff --git a/Documentation/devicetree/bindings/ipmi/aspeed-kcs-bmc.txt b/Documentation/devicetree/bindings/ipmi/aspeed-kcs-bmc.txt deleted file mode 100644 index 193e71ca96b0..000000000000 --- a/Documentation/devicetree/bindings/ipmi/aspeed-kcs-bmc.txt +++ /dev/null @@ -1,33 +0,0 @@ -# Aspeed KCS (Keyboard Controller Style) IPMI interface - -The Aspeed SOCs (AST2400 and AST2500) are commonly used as BMCs -(Baseboard Management Controllers) and the KCS interface can be -used to perform in-band IPMI communication with their host. - -## v1 -Required properties: -- compatible : should be one of - "aspeed,ast2400-kcs-bmc" - "aspeed,ast2500-kcs-bmc" -- interrupts : interrupt generated by the controller -- kcs_chan : The LPC channel number in the controller -- kcs_addr : The host CPU IO map address - -## v2 -Required properties: -- compatible : should be one of - "aspeed,ast2400-kcs-bmc-v2" - "aspeed,ast2500-kcs-bmc-v2" -- reg : The address and size of the IDR, ODR and STR registers -- interrupts : interrupt generated by the controller -- aspeed,lpc-io-reg : The host CPU LPC IO address for the device - -Example: - - kcs3: kcs@24 { - compatible = "aspeed,ast2500-kcs-bmc-v2"; - reg = <0x24 0x1>, <0x30 0x1>, <0x3c 0x1>; - aspeed,lpc-reg = <0xca2>; - interrupts = <8>; - status = "okay"; - }; diff --git a/Documentation/devicetree/bindings/mailbox/fsl,mu.yaml b/Documentation/devicetree/bindings/mailbox/fsl,mu.yaml index 1a3dff277e2b..675ad9de15bb 100644 --- a/Documentation/devicetree/bindings/mailbox/fsl,mu.yaml +++ b/Documentation/devicetree/bindings/mailbox/fsl,mu.yaml @@ -26,6 +26,7 @@ properties: oneOf: - const: fsl,imx6sx-mu - const: fsl,imx7ulp-mu + - const: fsl,imx8ulp-mu - const: fsl,imx8-mu-scu - items: - enum: diff --git a/Documentation/devicetree/bindings/mailbox/microchip,polarfire-soc-mailbox.yaml b/Documentation/devicetree/bindings/mailbox/microchip,polarfire-soc-mailbox.yaml new file mode 100644 index 000000000000..bbb173ea483c --- /dev/null +++ b/Documentation/devicetree/bindings/mailbox/microchip,polarfire-soc-mailbox.yaml @@ -0,0 +1,47 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: "http://devicetree.org/schemas/mailbox/microchip,polarfire-soc-mailbox.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: Microchip PolarFire SoC (MPFS) MSS (microprocessor subsystem) mailbox controller + +maintainers: + - Conor Dooley + +properties: + compatible: + const: microchip,polarfire-soc-mailbox + + reg: + items: + - description: mailbox data registers + - description: mailbox interrupt registers + + interrupts: + maxItems: 1 + + "#mbox-cells": + const: 1 + +required: + - compatible + - reg + - interrupts + - "#mbox-cells" + +additionalProperties: false + +examples: + - | + soc { + #address-cells = <2>; + #size-cells = <2>; + mbox: mailbox@37020000 { + compatible = "microchip,polarfire-soc-mailbox"; + reg = <0x0 0x37020000 0x0 0x1000>, <0x0 0x2000318c 0x0 0x40>; + interrupt-parent = <&L1>; + interrupts = <96>; + #mbox-cells = <1>; + }; + }; diff --git a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml index 5dc1173d03fd..8878ec00820e 100644 --- a/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml +++ b/Documentation/devicetree/bindings/mailbox/qcom,apcs-kpss-global.yaml @@ -19,6 +19,7 @@ properties: - qcom,ipq6018-apcs-apps-global - qcom,ipq8074-apcs-apps-global - qcom,msm8916-apcs-kpss-global + - qcom,msm8939-apcs-kpss-global - qcom,msm8994-apcs-kpss-global - qcom,msm8996-apcs-hmss-global - qcom,msm8998-apcs-hmss-global @@ -27,6 +28,7 @@ properties: - qcom,sc8180x-apss-shared - qcom,sdm660-apcs-hmss-global - qcom,sdm845-apss-shared + - qcom,sm6125-apcs-hmss-global - qcom,sm8150-apss-shared reg: @@ -75,6 +77,7 @@ allOf: - qcom,sc7180-apss-shared - qcom,sdm660-apcs-hmss-global - qcom,sdm845-apss-shared + - qcom,sm6125-apcs-hmss-global - qcom,sm8150-apss-shared then: properties: diff --git a/Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt b/Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt deleted file mode 100644 index 8ba9ed11d716..000000000000 --- a/Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt +++ /dev/null @@ -1,23 +0,0 @@ -* Broadcom iProc MDIO bus controller - -Required properties: -- compatible: should be "brcm,iproc-mdio" -- reg: address and length of the register set for the MDIO interface -- #size-cells: must be 1 -- #address-cells: must be 0 - -Child nodes of this MDIO bus controller node are standard Ethernet PHY device -nodes as described in Documentation/devicetree/bindings/net/phy.txt - -Example: - -mdio@18002000 { - compatible = "brcm,iproc-mdio"; - reg = <0x18002000 0x8>; - #size-cells = <1>; - #address-cells = <0>; - - enet-gphy@0 { - reg = <0>; - }; -}; diff --git a/Documentation/devicetree/bindings/net/brcm,iproc-mdio.yaml b/Documentation/devicetree/bindings/net/brcm,iproc-mdio.yaml new file mode 100644 index 000000000000..3031395f7e6e --- /dev/null +++ b/Documentation/devicetree/bindings/net/brcm,iproc-mdio.yaml @@ -0,0 +1,38 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/brcm,iproc-mdio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Broadcom iProc MDIO bus controller + +maintainers: + - Rafał Miłecki + +allOf: + - $ref: mdio.yaml# + +properties: + compatible: + const: brcm,iproc-mdio + + reg: + maxItems: 1 + +unevaluatedProperties: false + +required: + - reg + +examples: + - | + mdio@18002000 { + compatible = "brcm,iproc-mdio"; + reg = <0x18002000 0x8>; + #address-cells = <1>; + #size-cells = <0>; + + ethernet-phy@0 { + reg = <0>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/can/rcar_can.txt b/Documentation/devicetree/bindings/net/can/rcar_can.txt deleted file mode 100644 index 90ac4fef23f5..000000000000 --- a/Documentation/devicetree/bindings/net/can/rcar_can.txt +++ /dev/null @@ -1,80 +0,0 @@ -Renesas R-Car CAN controller Device Tree Bindings -------------------------------------------------- - -Required properties: -- compatible: "renesas,can-r8a7742" if CAN controller is a part of R8A7742 SoC. - "renesas,can-r8a7743" if CAN controller is a part of R8A7743 SoC. - "renesas,can-r8a7744" if CAN controller is a part of R8A7744 SoC. - "renesas,can-r8a7745" if CAN controller is a part of R8A7745 SoC. - "renesas,can-r8a77470" if CAN controller is a part of R8A77470 SoC. - "renesas,can-r8a774a1" if CAN controller is a part of R8A774A1 SoC. - "renesas,can-r8a774b1" if CAN controller is a part of R8A774B1 SoC. - "renesas,can-r8a774c0" if CAN controller is a part of R8A774C0 SoC. - "renesas,can-r8a774e1" if CAN controller is a part of R8A774E1 SoC. - "renesas,can-r8a7778" if CAN controller is a part of R8A7778 SoC. - "renesas,can-r8a7779" if CAN controller is a part of R8A7779 SoC. - "renesas,can-r8a7790" if CAN controller is a part of R8A7790 SoC. - "renesas,can-r8a7791" if CAN controller is a part of R8A7791 SoC. - "renesas,can-r8a7792" if CAN controller is a part of R8A7792 SoC. - "renesas,can-r8a7793" if CAN controller is a part of R8A7793 SoC. - "renesas,can-r8a7794" if CAN controller is a part of R8A7794 SoC. - "renesas,can-r8a7795" if CAN controller is a part of R8A7795 SoC. - "renesas,can-r8a7796" if CAN controller is a part of R8A77960 SoC. - "renesas,can-r8a77961" if CAN controller is a part of R8A77961 SoC. - "renesas,can-r8a77965" if CAN controller is a part of R8A77965 SoC. - "renesas,can-r8a77990" if CAN controller is a part of R8A77990 SoC. - "renesas,can-r8a77995" if CAN controller is a part of R8A77995 SoC. - "renesas,rcar-gen1-can" for a generic R-Car Gen1 compatible device. - "renesas,rcar-gen2-can" for a generic R-Car Gen2 or RZ/G1 - compatible device. - "renesas,rcar-gen3-can" for a generic R-Car Gen3 or RZ/G2 - compatible device. - When compatible with the generic version, nodes must list the - SoC-specific version corresponding to the platform first - followed by the generic version. - -- reg: physical base address and size of the R-Car CAN register map. -- interrupts: interrupt specifier for the sole interrupt. -- clocks: phandles and clock specifiers for 3 CAN clock inputs. -- clock-names: 3 clock input name strings: "clkp1", "clkp2", and "can_clk". -- pinctrl-0: pin control group to be used for this controller. -- pinctrl-names: must be "default". - -Required properties for R8A774A1, R8A774B1, R8A774C0, R8A774E1, R8A7795, -R8A77960, R8A77961, R8A77965, R8A77990, and R8A77995: -For the denoted SoCs, "clkp2" can be CANFD clock. This is a div6 clock and can -be used by both CAN and CAN FD controller at the same time. It needs to be -scaled to maximum frequency if any of these controllers use it. This is done -using the below properties: - -- assigned-clocks: phandle of clkp2(CANFD) clock. -- assigned-clock-rates: maximum frequency of this clock. - -Optional properties: -- renesas,can-clock-select: R-Car CAN Clock Source Select. Valid values are: - <0x0> (default) : Peripheral clock (clkp1) - <0x1> : Peripheral clock (clkp2) - <0x3> : External input clock - -Example -------- - -SoC common .dtsi file: - - can0: can@e6e80000 { - compatible = "renesas,can-r8a7791", "renesas,rcar-gen2-can"; - reg = <0 0xe6e80000 0 0x1000>; - interrupts = <0 186 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&mstp9_clks R8A7791_CLK_RCAN0>, - <&cpg_clocks R8A7791_CLK_RCAN>, <&can_clk>; - clock-names = "clkp1", "clkp2", "can_clk"; - status = "disabled"; - }; - -Board specific .dts file: - -&can0 { - pinctrl-0 = <&can0_pins>; - pinctrl-names = "default"; - status = "okay"; -}; diff --git a/Documentation/devicetree/bindings/net/can/rcar_canfd.txt b/Documentation/devicetree/bindings/net/can/rcar_canfd.txt deleted file mode 100644 index 248c4ed97a0a..000000000000 --- a/Documentation/devicetree/bindings/net/can/rcar_canfd.txt +++ /dev/null @@ -1,107 +0,0 @@ -Renesas R-Car CAN FD controller Device Tree Bindings ----------------------------------------------------- - -Required properties: -- compatible: Must contain one or more of the following: - - "renesas,rcar-gen3-canfd" for R-Car Gen3 and RZ/G2 compatible controllers. - - "renesas,r8a774a1-canfd" for R8A774A1 (RZ/G2M) compatible controller. - - "renesas,r8a774b1-canfd" for R8A774B1 (RZ/G2N) compatible controller. - - "renesas,r8a774c0-canfd" for R8A774C0 (RZ/G2E) compatible controller. - - "renesas,r8a774e1-canfd" for R8A774E1 (RZ/G2H) compatible controller. - - "renesas,r8a7795-canfd" for R8A7795 (R-Car H3) compatible controller. - - "renesas,r8a7796-canfd" for R8A7796 (R-Car M3-W) compatible controller. - - "renesas,r8a77965-canfd" for R8A77965 (R-Car M3-N) compatible controller. - - "renesas,r8a77970-canfd" for R8A77970 (R-Car V3M) compatible controller. - - "renesas,r8a77980-canfd" for R8A77980 (R-Car V3H) compatible controller. - - "renesas,r8a77990-canfd" for R8A77990 (R-Car E3) compatible controller. - - "renesas,r8a77995-canfd" for R8A77995 (R-Car D3) compatible controller. - - When compatible with the generic version, nodes must list the - SoC-specific version corresponding to the platform first, followed by the - family-specific and/or generic versions. - -- reg: physical base address and size of the R-Car CAN FD register map. -- interrupts: interrupt specifiers for the Channel & Global interrupts -- clocks: phandles and clock specifiers for 3 clock inputs. -- clock-names: 3 clock input name strings: "fck", "canfd", "can_clk". -- pinctrl-0: pin control group to be used for this controller. -- pinctrl-names: must be "default". - -Required child nodes: -The controller supports two channels and each is represented as a child node. -The name of the child nodes are "channel0" and "channel1" respectively. Each -child node supports the "status" property only, which is used to -enable/disable the respective channel. - -Required properties for R8A774A1, R8A774B1, R8A774C0, R8A774E1, R8A7795, -R8A7796, R8A77965, R8A77990, and R8A77995: -In the denoted SoCs, canfd clock is a div6 clock and can be used by both CAN -and CAN FD controller at the same time. It needs to be scaled to maximum -frequency if any of these controllers use it. This is done using the below -properties: - -- assigned-clocks: phandle of canfd clock. -- assigned-clock-rates: maximum frequency of this clock. - -Optional property: -The controller can operate in either CAN FD only mode (default) or -Classical CAN only mode. The mode is global to both the channels. In order to -enable the later, define the following optional property. - - renesas,no-can-fd: puts the controller in Classical CAN only mode. - -Example -------- - -SoC common .dtsi file: - - canfd: can@e66c0000 { - compatible = "renesas,r8a7795-canfd", - "renesas,rcar-gen3-canfd"; - reg = <0 0xe66c0000 0 0x8000>; - interrupts = , - ; - clocks = <&cpg CPG_MOD 914>, - <&cpg CPG_CORE R8A7795_CLK_CANFD>, - <&can_clk>; - clock-names = "fck", "canfd", "can_clk"; - assigned-clocks = <&cpg CPG_CORE R8A7795_CLK_CANFD>; - assigned-clock-rates = <40000000>; - power-domains = <&cpg>; - status = "disabled"; - - channel0 { - status = "disabled"; - }; - - channel1 { - status = "disabled"; - }; - }; - -Board specific .dts file: - -E.g. below enables Channel 1 alone in the board in Classical CAN only mode. - -&canfd { - pinctrl-0 = <&canfd1_pins>; - pinctrl-names = "default"; - renesas,no-can-fd; - status = "okay"; - - channel1 { - status = "okay"; - }; -}; - -E.g. below enables Channel 0 alone in the board using External clock -as fCAN clock. - -&canfd { - pinctrl-0 = <&canfd0_pins>, <&can_clk_pins>; - pinctrl-names = "default"; - status = "okay"; - - channel0 { - status = "okay"; - }; -}; diff --git a/Documentation/devicetree/bindings/net/can/renesas,rcar-can.yaml b/Documentation/devicetree/bindings/net/can/renesas,rcar-can.yaml new file mode 100644 index 000000000000..fadc871fd6b0 --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/renesas,rcar-can.yaml @@ -0,0 +1,139 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/can/renesas,rcar-can.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Renesas R-Car CAN Controller + +maintainers: + - Sergei Shtylyov + +properties: + compatible: + oneOf: + - items: + - enum: + - renesas,can-r8a7778 # R-Car M1-A + - renesas,can-r8a7779 # R-Car H1 + - const: renesas,rcar-gen1-can # R-Car Gen1 + + - items: + - enum: + - renesas,can-r8a7742 # RZ/G1H + - renesas,can-r8a7743 # RZ/G1M + - renesas,can-r8a7744 # RZ/G1N + - renesas,can-r8a7745 # RZ/G1E + - renesas,can-r8a77470 # RZ/G1C + - renesas,can-r8a7790 # R-Car H2 + - renesas,can-r8a7791 # R-Car M2-W + - renesas,can-r8a7792 # R-Car V2H + - renesas,can-r8a7793 # R-Car M2-N + - renesas,can-r8a7794 # R-Car E2 + - const: renesas,rcar-gen2-can # R-Car Gen2 and RZ/G1 + + - items: + - enum: + - renesas,can-r8a774a1 # RZ/G2M + - renesas,can-r8a774b1 # RZ/G2N + - renesas,can-r8a774c0 # RZ/G2E + - renesas,can-r8a774e1 # RZ/G2H + - renesas,can-r8a7795 # R-Car H3 + - renesas,can-r8a7796 # R-Car M3-W + - renesas,can-r8a77961 # R-Car M3-W+ + - renesas,can-r8a77965 # R-Car M3-N + - renesas,can-r8a77990 # R-Car E3 + - renesas,can-r8a77995 # R-Car D3 + - const: renesas,rcar-gen3-can # R-Car Gen3 and RZ/G2 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 3 + + clock-names: + items: + - const: clkp1 + - const: clkp2 + - const: can_clk + + power-domains: + maxItems: 1 + + resets: + maxItems: 1 + + renesas,can-clock-select: + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [ 0, 1, 3 ] + default: 0 + description: | + R-Car CAN Clock Source Select. Valid values are: + <0x0> (default) : Peripheral clock (clkp1) + <0x1> : Peripheral clock (clkp2) + <0x3> : External input clock + + assigned-clocks: + description: + Reference to the clkp2 (CANFD) clock. + On R-Car Gen3 and RZ/G2 SoCs, "clkp2" is the CANFD clock. This is a div6 + clock and can be used by both CAN and CAN FD controllers at the same + time. It needs to be scaled to maximum frequency if any of these + controllers use it. + + assigned-clock-rates: + description: Maximum frequency of the CANFD clock. + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + - power-domains + +allOf: + - $ref: can-controller.yaml# + + - if: + not: + properties: + compatible: + contains: + const: renesas,rcar-gen1-can + then: + required: + - resets + + - if: + properties: + compatible: + contains: + const: renesas,rcar-gen3-can + then: + required: + - assigned-clocks + - assigned-clock-rates + +unevaluatedProperties: false + +examples: + - | + #include + #include + #include + + can0: can@e6e80000 { + compatible = "renesas,can-r8a7791", "renesas,rcar-gen2-can"; + reg = <0xe6e80000 0x1000>; + interrupts = ; + clocks = <&cpg CPG_MOD 916>, + <&cpg CPG_CORE R8A7791_CLK_RCAN>, <&can_clk>; + clock-names = "clkp1", "clkp2", "can_clk"; + power-domains = <&sysc R8A7791_PD_ALWAYS_ON>; + resets = <&cpg 916>; + }; diff --git a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml new file mode 100644 index 000000000000..0b33ba9ccb47 --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml @@ -0,0 +1,122 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/can/renesas,rcar-canfd.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Renesas R-Car CAN FD Controller + +maintainers: + - Fabrizio Castro + +allOf: + - $ref: can-controller.yaml# + +properties: + compatible: + oneOf: + - items: + - enum: + - renesas,r8a774a1-canfd # RZ/G2M + - renesas,r8a774b1-canfd # RZ/G2N + - renesas,r8a774c0-canfd # RZ/G2E + - renesas,r8a774e1-canfd # RZ/G2H + - renesas,r8a7795-canfd # R-Car H3 + - renesas,r8a7796-canfd # R-Car M3-W + - renesas,r8a77965-canfd # R-Car M3-N + - renesas,r8a77970-canfd # R-Car V3M + - renesas,r8a77980-canfd # R-Car V3H + - renesas,r8a77990-canfd # R-Car E3 + - renesas,r8a77995-canfd # R-Car D3 + - const: renesas,rcar-gen3-canfd # R-Car Gen3 and RZ/G2 + + reg: + maxItems: 1 + + interrupts: + items: + - description: Channel interrupt + - description: Global interrupt + + clocks: + maxItems: 3 + + clock-names: + items: + - const: fck + - const: canfd + - const: can_clk + + power-domains: + maxItems: 1 + + resets: + maxItems: 1 + + renesas,no-can-fd: + $ref: /schemas/types.yaml#/definitions/flag + description: + The controller can operate in either CAN FD only mode (default) or + Classical CAN only mode. The mode is global to both the channels. + Specify this property to put the controller in Classical CAN only mode. + + assigned-clocks: + description: + Reference to the CANFD clock. The CANFD clock is a div6 clock and can be + used by both CAN (if present) and CAN FD controllers at the same time. + It needs to be scaled to maximum frequency if any of these controllers + use it. + + assigned-clock-rates: + description: Maximum frequency of the CANFD clock. + +patternProperties: + "^channel[01]$": + type: object + description: + The controller supports two channels and each is represented as a child + node. Each child node supports the "status" property only, which + is used to enable/disable the respective channel. + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + - power-domains + - resets + - assigned-clocks + - assigned-clock-rates + - channel0 + - channel1 + +unevaluatedProperties: false + +examples: + - | + #include + #include + #include + + canfd: can@e66c0000 { + compatible = "renesas,r8a7795-canfd", + "renesas,rcar-gen3-canfd"; + reg = <0xe66c0000 0x8000>; + interrupts = , + ; + clocks = <&cpg CPG_MOD 914>, + <&cpg CPG_CORE R8A7795_CLK_CANFD>, + <&can_clk>; + clock-names = "fck", "canfd", "can_clk"; + assigned-clocks = <&cpg CPG_CORE R8A7795_CLK_CANFD>; + assigned-clock-rates = <40000000>; + power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; + resets = <&cpg 914>; + + channel0 { + }; + + channel1 { + }; + }; diff --git a/Documentation/devicetree/bindings/net/dsa/mt7530.txt b/Documentation/devicetree/bindings/net/dsa/mt7530.txt index de04626a8e9d..18247ebfc487 100644 --- a/Documentation/devicetree/bindings/net/dsa/mt7530.txt +++ b/Documentation/devicetree/bindings/net/dsa/mt7530.txt @@ -81,6 +81,12 @@ Optional properties: - gpio-controller: Boolean; if defined, MT7530's LED controller will run on GPIO mode. - #gpio-cells: Must be 2 if gpio-controller is defined. +- interrupt-controller: Boolean; Enables the internal interrupt controller. + +If interrupt-controller is defined, the following properties are required. + +- #interrupt-cells: Must be 1. +- interrupts: Parent interrupt for the interrupt controller. See Documentation/devicetree/bindings/net/dsa/dsa.txt for a list of additional required, optional properties and how the integrated switch subnodes must diff --git a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml new file mode 100644 index 000000000000..0b8a05dd52e6 --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml @@ -0,0 +1,132 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/dsa/nxp,sja1105.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: NXP SJA1105 Automotive Ethernet Switch Family Device Tree Bindings + +description: + The SJA1105 SPI interface requires a CS-to-CLK time (t2 in UM10944.pdf) of at + least one half of t_CLK. At an SPI frequency of 1MHz, this means a minimum + cs_sck_delay of 500ns. Ensuring that this SPI timing requirement is observed + depends on the SPI bus master driver. + +allOf: + - $ref: "dsa.yaml#" + +maintainers: + - Vladimir Oltean + +properties: + compatible: + enum: + - nxp,sja1105e + - nxp,sja1105t + - nxp,sja1105p + - nxp,sja1105q + - nxp,sja1105r + - nxp,sja1105s + - nxp,sja1110a + - nxp,sja1110b + - nxp,sja1110c + - nxp,sja1110d + + reg: + maxItems: 1 + + # Optional container node for the 2 internal MDIO buses of the SJA1110 + # (one for the internal 100base-T1 PHYs and the other for the single + # 100base-TX PHY). The "reg" property does not have physical significance. + # The PHY addresses to port correspondence is as follows: for 100base-T1, + # port 5 has PHY 1, port 6 has PHY 2 etc, while for 100base-TX, port 1 has + # PHY 1. + mdios: + type: object + + properties: + '#address-cells': + const: 1 + '#size-cells': + const: 0 + + patternProperties: + "^mdio@[0-1]$": + type: object + + allOf: + - $ref: "http://devicetree.org/schemas/net/mdio.yaml#" + + properties: + compatible: + oneOf: + - enum: + - nxp,sja1110-base-t1-mdio + - nxp,sja1110-base-tx-mdio + + reg: + oneOf: + - enum: + - 0 + - 1 + + required: + - compatible + - reg + +required: + - compatible + - reg + +unevaluatedProperties: false + +examples: + - | + spi { + #address-cells = <1>; + #size-cells = <0>; + + ethernet-switch@1 { + reg = <0x1>; + compatible = "nxp,sja1105t"; + + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + phy-handle = <&rgmii_phy6>; + phy-mode = "rgmii-id"; + reg = <0>; + }; + + port@1 { + phy-handle = <&rgmii_phy3>; + phy-mode = "rgmii-id"; + reg = <1>; + }; + + port@2 { + phy-handle = <&rgmii_phy4>; + phy-mode = "rgmii-id"; + reg = <2>; + }; + + port@3 { + phy-mode = "rgmii-id"; + reg = <3>; + }; + + port@4 { + ethernet = <&enet2>; + phy-mode = "rgmii"; + reg = <4>; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/dsa/qca8k.txt b/Documentation/devicetree/bindings/net/dsa/qca8k.txt index ccbc6d89325d..8c73f67c43ca 100644 --- a/Documentation/devicetree/bindings/net/dsa/qca8k.txt +++ b/Documentation/devicetree/bindings/net/dsa/qca8k.txt @@ -3,6 +3,7 @@ Required properties: - compatible: should be one of: + "qca,qca8327" "qca,qca8334" "qca,qca8337" @@ -20,6 +21,10 @@ described in dsa/dsa.txt. If the QCA8K switch is connect to a SoC's external mdio-bus each subnode describing a port needs to have a valid phandle referencing the internal PHY it is connected to. This is because there's no N:N mapping of port and PHY id. +To declare the internal mdio-bus configuration, declare a mdio node in the +switch node and declare the phandle for the port referencing the internal +PHY is connected to. In this config a internal mdio-bus is registered and +the mdio MASTER is used as communication. Don't use mixed external and internal mdio-bus configurations, as this is not supported by the hardware. @@ -149,26 +154,61 @@ for the internal master mdio-bus configuration: port@1 { reg = <1>; label = "lan1"; + phy-mode = "internal"; + phy-handle = <&phy_port1>; }; port@2 { reg = <2>; label = "lan2"; + phy-mode = "internal"; + phy-handle = <&phy_port2>; }; port@3 { reg = <3>; label = "lan3"; + phy-mode = "internal"; + phy-handle = <&phy_port3>; }; port@4 { reg = <4>; label = "lan4"; + phy-mode = "internal"; + phy-handle = <&phy_port4>; }; port@5 { reg = <5>; label = "wan"; + phy-mode = "internal"; + phy-handle = <&phy_port5>; + }; + }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + phy_port1: phy@0 { + reg = <0>; + }; + + phy_port2: phy@1 { + reg = <1>; + }; + + phy_port3: phy@2 { + reg = <2>; + }; + + phy_port4: phy@3 { + reg = <3>; + }; + + phy_port5: phy@4 { + reg = <4>; }; }; }; diff --git a/Documentation/devicetree/bindings/net/dsa/sja1105.txt b/Documentation/devicetree/bindings/net/dsa/sja1105.txt deleted file mode 100644 index 13fd21074d48..000000000000 --- a/Documentation/devicetree/bindings/net/dsa/sja1105.txt +++ /dev/null @@ -1,156 +0,0 @@ -NXP SJA1105 switch driver -========================= - -Required properties: - -- compatible: - Must be one of: - - "nxp,sja1105e" - - "nxp,sja1105t" - - "nxp,sja1105p" - - "nxp,sja1105q" - - "nxp,sja1105r" - - "nxp,sja1105s" - - Although the device ID could be detected at runtime, explicit bindings - are required in order to be able to statically check their validity. - For example, SGMII can only be specified on port 4 of R and S devices, - and the non-SGMII devices, while pin-compatible, are not equal in terms - of support for RGMII internal delays (supported on P/Q/R/S, but not on - E/T). - -Optional properties: - -- sja1105,role-mac: -- sja1105,role-phy: - Boolean properties that can be assigned under each port node. By - default (unless otherwise specified) a port is configured as MAC if it - is driving a PHY (phy-handle is present) or as PHY if it is PHY-less - (fixed-link specified, presumably because it is connected to a MAC). - The effect of this property (in either its implicit or explicit form) - is: - - In the case of MII or RMII it specifies whether the SJA1105 port is a - clock source or sink for this interface (not applicable for RGMII - where there is a Tx and an Rx clock). - - In the case of RGMII it affects the behavior regarding internal - delays: - 1. If sja1105,role-mac is specified, and the phy-mode property is one - of "rgmii-id", "rgmii-txid" or "rgmii-rxid", then the entity - designated to apply the delay/clock skew necessary for RGMII - is the PHY. The SJA1105 MAC does not apply any internal delays. - 2. If sja1105,role-phy is specified, and the phy-mode property is one - of the above, the designated entity to apply the internal delays - is the SJA1105 MAC (if hardware-supported). This is only supported - by the second-generation (P/Q/R/S) hardware. On a first-generation - E or T device, it is an error to specify an RGMII phy-mode other - than "rgmii" for a port that is in fixed-link mode. In that case, - the clock skew must either be added by the MAC at the other end of - the fixed-link, or by PCB serpentine traces on the board. - These properties are required, for example, in the case where SJA1105 - ports are at both ends of a MII/RMII PHY-less setup. One end would need - to have sja1105,role-mac, while the other sja1105,role-phy. - -See Documentation/devicetree/bindings/net/dsa/dsa.txt for the list of standard -DSA required and optional properties. - -Other observations ------------------- - -The SJA1105 SPI interface requires a CS-to-CLK time (t2 in UM10944) of at least -one half of t_CLK. At an SPI frequency of 1MHz, this means a minimum -cs_sck_delay of 500ns. Ensuring that this SPI timing requirement is observed -depends on the SPI bus master driver. - -Example -------- - -Ethernet switch connected via SPI to the host, CPU port wired to enet2: - -arch/arm/boot/dts/ls1021a-tsn.dts: - -/* SPI controller of the LS1021 */ -&dspi0 { - sja1105@1 { - reg = <0x1>; - #address-cells = <1>; - #size-cells = <0>; - compatible = "nxp,sja1105t"; - spi-max-frequency = <4000000>; - fsl,spi-cs-sck-delay = <1000>; - fsl,spi-sck-cs-delay = <1000>; - ports { - #address-cells = <1>; - #size-cells = <0>; - port@0 { - /* ETH5 written on chassis */ - label = "swp5"; - phy-handle = <&rgmii_phy6>; - phy-mode = "rgmii-id"; - reg = <0>; - /* Implicit "sja1105,role-mac;" */ - }; - port@1 { - /* ETH2 written on chassis */ - label = "swp2"; - phy-handle = <&rgmii_phy3>; - phy-mode = "rgmii-id"; - reg = <1>; - /* Implicit "sja1105,role-mac;" */ - }; - port@2 { - /* ETH3 written on chassis */ - label = "swp3"; - phy-handle = <&rgmii_phy4>; - phy-mode = "rgmii-id"; - reg = <2>; - /* Implicit "sja1105,role-mac;" */ - }; - port@3 { - /* ETH4 written on chassis */ - phy-handle = <&rgmii_phy5>; - label = "swp4"; - phy-mode = "rgmii-id"; - reg = <3>; - /* Implicit "sja1105,role-mac;" */ - }; - port@4 { - /* Internal port connected to eth2 */ - ethernet = <&enet2>; - phy-mode = "rgmii"; - reg = <4>; - /* Implicit "sja1105,role-phy;" */ - fixed-link { - speed = <1000>; - full-duplex; - }; - }; - }; - }; -}; - -/* MDIO controller of the LS1021 */ -&mdio0 { - /* BCM5464 */ - rgmii_phy3: ethernet-phy@3 { - reg = <0x3>; - }; - rgmii_phy4: ethernet-phy@4 { - reg = <0x4>; - }; - rgmii_phy5: ethernet-phy@5 { - reg = <0x5>; - }; - rgmii_phy6: ethernet-phy@6 { - reg = <0x6>; - }; -}; - -/* Ethernet master port of the LS1021 */ -&enet2 { - phy-connection-type = "rgmii"; - status = "ok"; - fixed-link { - speed = <1000>; - full-duplex; - }; -}; diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index e8f04687a3e0..b0933a8c295a 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -68,6 +68,7 @@ properties: - tbi - rev-mii - rmii + - rev-rmii # RX and TX delays are added by the MAC when required - rgmii @@ -97,6 +98,7 @@ properties: - 10gbase-kr - usxgmii - 10gbase-r + - 25gbase-r phy-mode: $ref: "#/properties/phy-connection-type" diff --git a/Documentation/devicetree/bindings/net/ingenic,mac.yaml b/Documentation/devicetree/bindings/net/ingenic,mac.yaml new file mode 100644 index 000000000000..d08a88125a5c --- /dev/null +++ b/Documentation/devicetree/bindings/net/ingenic,mac.yaml @@ -0,0 +1,76 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/ingenic,mac.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Bindings for MAC in Ingenic SoCs + +maintainers: + - 周琰杰 (Zhou Yanjie) + +description: + The Ethernet Media Access Controller in Ingenic SoCs. + +properties: + compatible: + enum: + - ingenic,jz4775-mac + - ingenic,x1000-mac + - ingenic,x1600-mac + - ingenic,x1830-mac + - ingenic,x2000-mac + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + interrupt-names: + const: macirq + + clocks: + maxItems: 1 + + clock-names: + const: stmmaceth + + mode-reg: + description: An extra syscon register that control ethernet interface and timing delay + + rx-clk-delay-ps: + description: RGMII receive clock delay defined in pico seconds + + tx-clk-delay-ps: + description: RGMII transmit clock delay defined in pico seconds + +required: + - compatible + - reg + - interrupts + - interrupt-names + - clocks + - clock-names + - mode-reg + +additionalProperties: false + +examples: + - | + #include + + mac: ethernet@134b0000 { + compatible = "ingenic,x1000-mac"; + reg = <0x134b0000 0x2000>; + + interrupt-parent = <&intc>; + interrupts = <55>; + interrupt-names = "macirq"; + + clocks = <&cgu X1000_CLK_MAC>; + clock-names = "stmmaceth"; + + mode-reg = <&mac_phy_ctrl>; + }; +... diff --git a/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml b/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml new file mode 100644 index 000000000000..347b912a46bb --- /dev/null +++ b/Documentation/devicetree/bindings/net/microchip,sparx5-switch.yaml @@ -0,0 +1,226 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/microchip,sparx5-switch.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microchip Sparx5 Ethernet switch controller + +maintainers: + - Steen Hegelund + - Lars Povlsen + +description: | + The SparX-5 Enterprise Ethernet switch family provides a rich set of + Enterprise switching features such as advanced TCAM-based VLAN and + QoS processing enabling delivery of differentiated services, and + security through TCAM-based frame processing using versatile content + aware processor (VCAP). + + IPv4/IPv6 Layer 3 (L3) unicast and multicast routing is supported + with up to 18K IPv4/9K IPv6 unicast LPM entries and up to 9K IPv4/3K + IPv6 (S,G) multicast groups. + + L3 security features include source guard and reverse path + forwarding (uRPF) tasks. Additional L3 features include VRF-Lite and + IP tunnels (IP over GRE/IP). + + The SparX-5 switch family targets managed Layer 2 and Layer 3 + equipment in SMB, SME, and Enterprise where high port count + 1G/2.5G/5G/10G switching with 10G/25G aggregation links is required. + +properties: + $nodename: + pattern: "^switch@[0-9a-f]+$" + + compatible: + const: microchip,sparx5-switch + + reg: + items: + - description: cpu target + - description: devices target + - description: general control block target + + reg-names: + items: + - const: cpu + - const: devices + - const: gcb + + interrupts: + minItems: 1 + items: + - description: register based extraction + - description: frame dma based extraction + + interrupt-names: + minItems: 1 + items: + - const: xtr + - const: fdma + + resets: + items: + - description: Reset controller used for switch core reset (soft reset) + + reset-names: + items: + - const: switch + + mac-address: true + + ethernet-ports: + type: object + patternProperties: + "^port@[0-9a-f]+$": + type: object + + properties: + '#address-cells': + const: 1 + '#size-cells': + const: 0 + + reg: + description: Switch port number + + phys: + maxItems: 1 + description: + phandle of a Ethernet SerDes PHY. This defines which SerDes + instance will handle the Ethernet traffic. + + phy-mode: + description: + This specifies the interface used by the Ethernet SerDes towards + the PHY or SFP. + + microchip,bandwidth: + description: Specifies bandwidth in Mbit/s allocated to the port. + $ref: "/schemas/types.yaml#/definitions/uint32" + maximum: 25000 + + phy-handle: + description: + phandle of a Ethernet PHY. This is optional and if provided it + points to the cuPHY used by the Ethernet SerDes. + + sfp: + description: + phandle of an SFP. This is optional and used when not specifying + a cuPHY. It points to the SFP node that describes the SFP used by + the Ethernet SerDes. + + managed: true + + microchip,sd-sgpio: + description: + Index of the ports Signal Detect SGPIO in the set of 384 SGPIOs + This is optional, and only needed if the default used index is + is not correct. + $ref: "/schemas/types.yaml#/definitions/uint32" + minimum: 0 + maximum: 383 + + required: + - reg + - phys + - phy-mode + - microchip,bandwidth + + oneOf: + - required: + - phy-handle + - required: + - sfp + - managed + +required: + - compatible + - reg + - reg-names + - interrupts + - interrupt-names + - resets + - reset-names + - ethernet-ports + +additionalProperties: false + +examples: + - | + #include + switch: switch@600000000 { + compatible = "microchip,sparx5-switch"; + reg = <0 0x401000>, + <0x10004000 0x7fc000>, + <0x11010000 0xaf0000>; + reg-names = "cpu", "devices", "gcb"; + interrupts = ; + interrupt-names = "xtr"; + resets = <&reset 0>; + reset-names = "switch"; + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + port0: port@0 { + reg = <0>; + microchip,bandwidth = <1000>; + phys = <&serdes 13>; + phy-handle = <&phy0>; + phy-mode = "qsgmii"; + }; + /* ... */ + /* Then the 25G interfaces */ + port60: port@60 { + reg = <60>; + microchip,bandwidth = <25000>; + phys = <&serdes 29>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth60>; + managed = "in-band-status"; + microchip,sd-sgpio = <365>; + }; + port61: port@61 { + reg = <61>; + microchip,bandwidth = <25000>; + phys = <&serdes 30>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth61>; + managed = "in-band-status"; + microchip,sd-sgpio = <369>; + }; + port62: port@62 { + reg = <62>; + microchip,bandwidth = <25000>; + phys = <&serdes 31>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth62>; + managed = "in-band-status"; + microchip,sd-sgpio = <373>; + }; + port63: port@63 { + reg = <63>; + microchip,bandwidth = <25000>; + phys = <&serdes 32>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth63>; + managed = "in-band-status"; + microchip,sd-sgpio = <377>; + }; + /* Finally the Management interface */ + port64: port@64 { + reg = <64>; + microchip,bandwidth = <1000>; + phys = <&serdes 0>; + phy-handle = <&phy64>; + phy-mode = "sgmii"; + mac-address = [ 00 00 00 01 02 03 ]; + }; + }; + }; + +... +# vim: set ts=2 sw=2 sts=2 tw=80 et cc=80 ft=yaml : diff --git a/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml b/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml index 477066e2b821..081742c2b726 100644 --- a/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml +++ b/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml @@ -27,6 +27,9 @@ properties: reg: maxItems: 1 + clocks: + maxItems: 1 + wake-gpios: maxItems: 1 description: @@ -80,6 +83,8 @@ examples: en-gpios = <&gpf1 4 GPIO_ACTIVE_HIGH>; wake-gpios = <&gpj0 2 GPIO_ACTIVE_HIGH>; + + clocks = <&rpmcc 20>; }; }; # UART example on Raspberry Pi diff --git a/Documentation/devicetree/bindings/net/qcom,ipa.yaml b/Documentation/devicetree/bindings/net/qcom,ipa.yaml index 5fe6d3dceb08..ed88ba4b94df 100644 --- a/Documentation/devicetree/bindings/net/qcom,ipa.yaml +++ b/Documentation/devicetree/bindings/net/qcom,ipa.yaml @@ -44,6 +44,7 @@ description: properties: compatible: enum: + - qcom,msm8998-ipa - qcom,sc7180-ipa - qcom,sc7280-ipa - qcom,sdm845-ipa diff --git a/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt b/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt deleted file mode 100644 index 709ca6d51650..000000000000 --- a/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt +++ /dev/null @@ -1,69 +0,0 @@ -Qualcomm Bluetooth Chips ---------------------- - -This documents the binding structure and common properties for serial -attached Qualcomm devices. - -Serial attached Qualcomm devices shall be a child node of the host UART -device the slave device is attached to. - -Required properties: - - compatible: should contain one of the following: - * "qcom,qca6174-bt" - * "qcom,qca9377-bt" - * "qcom,wcn3990-bt" - * "qcom,wcn3991-bt" - * "qcom,wcn3998-bt" - * "qcom,qca6390-bt" - -Optional properties for compatible string qcom,qca6174-bt: - - - enable-gpios: gpio specifier used to enable chip - - clocks: clock provided to the controller (SUSCLK_32KHZ) - - firmware-name: specify the name of nvm firmware to load - -Optional properties for compatible string qcom,qca9377-bt: - - - max-speed: see Documentation/devicetree/bindings/serial/serial.yaml - -Required properties for compatible string qcom,wcn399x-bt: - - - vddio-supply: VDD_IO supply regulator handle. - - vddxo-supply: VDD_XO supply regulator handle. - - vddrf-supply: VDD_RF supply regulator handle. - - vddch0-supply: VDD_CH0 supply regulator handle. - -Optional properties for compatible string qcom,wcn399x-bt: - - - max-speed: see Documentation/devicetree/bindings/serial/serial.yaml - - firmware-name: specify the name of nvm firmware to load - - clocks: clock provided to the controller - -Examples: - -serial@7570000 { - label = "BT-UART"; - status = "okay"; - - bluetooth { - compatible = "qcom,qca6174-bt"; - - enable-gpios = <&pm8994_gpios 19 GPIO_ACTIVE_HIGH>; - clocks = <&divclk4>; - firmware-name = "nvm_00440302.bin"; - }; -}; - -serial@898000 { - bluetooth { - compatible = "qcom,wcn3990-bt"; - - vddio-supply = <&vreg_s4a_1p8>; - vddxo-supply = <&vreg_l7a_1p8>; - vddrf-supply = <&vreg_l17a_1p3>; - vddch0-supply = <&vreg_l25a_3p3>; - max-speed = <3200000>; - firmware-name = "crnv21.bin"; - clocks = <&rpmhcc RPMH_RF_CLK2>; - }; -}; diff --git a/Documentation/devicetree/bindings/net/qualcomm-bluetooth.yaml b/Documentation/devicetree/bindings/net/qualcomm-bluetooth.yaml new file mode 100644 index 000000000000..f93c6e7a1b59 --- /dev/null +++ b/Documentation/devicetree/bindings/net/qualcomm-bluetooth.yaml @@ -0,0 +1,183 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/qualcomm-bluetooth.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Qualcomm Bluetooth Chips + +maintainers: + - Balakrishna Godavarthi + - Rocky Liao + +description: + This binding describes Qualcomm UART-attached bluetooth chips. + +properties: + compatible: + enum: + - qcom,qca6174-bt + - qcom,qca9377-bt + - qcom,wcn3990-bt + - qcom,wcn3991-bt + - qcom,wcn3998-bt + - qcom,qca6390-bt + - qcom,wcn6750-bt + + enable-gpios: + maxItems: 1 + description: gpio specifier used to enable chip + + swctrl-gpios: + maxItems: 1 + description: gpio specifier is used to find status + of clock supply to SoC + + clocks: + maxItems: 1 + description: clock provided to the controller (SUSCLK_32KHZ) + + vddio-supply: + description: VDD_IO supply regulator handle + + vddxo-supply: + description: VDD_XO supply regulator handle + + vddrf-supply: + description: VDD_RF supply regulator handle + + vddch0-supply: + description: VDD_CH0 supply regulator handle + + vddaon-supply: + description: VDD_AON supply regulator handle + + vddbtcxmx-supply: + description: VDD_BT_CXMX supply regulator handle + + vddrfacmn-supply: + description: VDD_RFA_CMN supply regulator handle + + vddrfa0p8-supply: + description: VDD_RFA_0P8 suppply regulator handle + + vddrfa1p7-supply: + description: VDD_RFA_1P7 supply regulator handle + + vddrfa1p2-supply: + description: VDD_RFA_1P2 supply regulator handle + + vddrfa2p2-supply: + description: VDD_RFA_2P2 supply regulator handle + + vddasd-supply: + description: VDD_ASD supply regulator handle + + max-speed: + description: see Documentation/devicetree/bindings/serial/serial.yaml + + firmware-name: + description: specify the name of nvm firmware to load + + local-bd-address: + description: see Documentation/devicetree/bindings/net/bluetooth.txt + + +required: + - compatible + +additionalProperties: false + +allOf: + - if: + properties: + compatible: + contains: + enum: + - qcom,qca6174-bt + then: + required: + - enable-gpios + - clocks + + - if: + properties: + compatible: + contains: + enum: + - qcom,wcn3990-bt + - qcom,wcn3991-bt + - qcom,wcn3998-bt + then: + required: + - vddio-supply + - vddxo-supply + - vddrf-supply + - vddch0-supply + + - if: + properties: + compatible: + contains: + enum: + - qcom,wcn6750-bt + then: + required: + - enable-gpios + - swctrl-gpios + - vddio-supply + - vddaon-supply + - vddbtcxmx-supply + - vddrfacmn-supply + - vddrfa0p8-supply + - vddrfa1p7-supply + - vddrfa1p2-supply + - vddasd-supply + +examples: + - | + #include + serial { + + bluetooth { + compatible = "qcom,qca6174-bt"; + enable-gpios = <&pm8994_gpios 19 GPIO_ACTIVE_HIGH>; + clocks = <&divclk4>; + firmware-name = "nvm_00440302.bin"; + }; + }; + - | + serial { + + bluetooth { + compatible = "qcom,wcn3990-bt"; + vddio-supply = <&vreg_s4a_1p8>; + vddxo-supply = <&vreg_l7a_1p8>; + vddrf-supply = <&vreg_l17a_1p3>; + vddch0-supply = <&vreg_l25a_3p3>; + max-speed = <3200000>; + firmware-name = "crnv21.bin"; + }; + }; + - | + serial { + + bluetooth { + compatible = "qcom,wcn6750-bt"; + pinctrl-names = "default"; + pinctrl-0 = <&bt_en_default>; + enable-gpios = <&tlmm 85 GPIO_ACTIVE_HIGH>; + swctrl-gpios = <&tlmm 86 GPIO_ACTIVE_HIGH>; + vddio-supply = <&vreg_l19b_1p8>; + vddaon-supply = <&vreg_s7b_0p9>; + vddbtcxmx-supply = <&vreg_s7b_0p9>; + vddrfacmn-supply = <&vreg_s7b_0p9>; + vddrfa0p8-supply = <&vreg_s7b_0p9>; + vddrfa1p7-supply = <&vreg_s1b_1p8>; + vddrfa1p2-supply = <&vreg_s8b_1p2>; + vddrfa2p2-supply = <&vreg_s1c_2p2>; + vddasd-supply = <&vreg_l11c_2p8>; + max-speed = <3200000>; + firmware-name = "msnv11.bin"; + }; + }; diff --git a/Documentation/devicetree/bindings/net/realtek,rtl82xx.yaml b/Documentation/devicetree/bindings/net/realtek,rtl82xx.yaml new file mode 100644 index 000000000000..bb94a2388520 --- /dev/null +++ b/Documentation/devicetree/bindings/net/realtek,rtl82xx.yaml @@ -0,0 +1,45 @@ +# SPDX-License-Identifier: GPL-2.0+ +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/realtek,rtl82xx.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Realtek RTL82xx PHY + +maintainers: + - Andrew Lunn + - Florian Fainelli + - Heiner Kallweit + +description: + Bindings for Realtek RTL82xx PHYs + +allOf: + - $ref: ethernet-phy.yaml# + +properties: + realtek,clkout-disable: + type: boolean + description: + Disable CLKOUT clock, CLKOUT clock default is enabled after hardware reset. + + + realtek,aldps-enable: + type: boolean + description: + Enable ALDPS mode, ALDPS mode default is disabled after hardware reset. + +unevaluatedProperties: false + +examples: + - | + mdio { + #address-cells = <1>; + #size-cells = <0>; + + ethphy1: ethernet-phy@1 { + reg = <1>; + realtek,clkout-disable; + realtek,aldps-enable; + }; + }; diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml index 5acddb6171bf..083623c8d718 100644 --- a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml +++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml @@ -19,10 +19,12 @@ select: - rockchip,rk3128-gmac - rockchip,rk3228-gmac - rockchip,rk3288-gmac + - rockchip,rk3308-gmac - rockchip,rk3328-gmac - rockchip,rk3366-gmac - rockchip,rk3368-gmac - rockchip,rk3399-gmac + - rockchip,rk3568-gmac - rockchip,rv1108-gmac required: - compatible @@ -32,17 +34,23 @@ allOf: properties: compatible: - items: - - enum: - - rockchip,px30-gmac - - rockchip,rk3128-gmac - - rockchip,rk3228-gmac - - rockchip,rk3288-gmac - - rockchip,rk3328-gmac - - rockchip,rk3366-gmac - - rockchip,rk3368-gmac - - rockchip,rk3399-gmac - - rockchip,rv1108-gmac + oneOf: + - items: + - enum: + - rockchip,px30-gmac + - rockchip,rk3128-gmac + - rockchip,rk3228-gmac + - rockchip,rk3288-gmac + - rockchip,rk3308-gmac + - rockchip,rk3328-gmac + - rockchip,rk3366-gmac + - rockchip,rk3368-gmac + - rockchip,rk3399-gmac + - rockchip,rv1108-gmac + - items: + - enum: + - rockchip,rk3568-gmac + - const: snps,dwmac-4.20a clocks: minItems: 5 diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index 2edd8bea993e..56f2235f5fb5 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -51,11 +51,20 @@ properties: - allwinner,sun8i-r40-emac - allwinner,sun8i-v3s-emac - allwinner,sun50i-a64-emac + - loongson,ls2k-dwmac + - loongson,ls7a-dwmac - amlogic,meson6-dwmac - amlogic,meson8b-dwmac - amlogic,meson8m2-dwmac - amlogic,meson-gxbb-dwmac - amlogic,meson-axg-dwmac + - loongson,ls2k-dwmac + - loongson,ls7a-dwmac + - ingenic,jz4775-mac + - ingenic,x1000-mac + - ingenic,x1600-mac + - ingenic,x1830-mac + - ingenic,x2000-mac - rockchip,px30-gmac - rockchip,rk3128-gmac - rockchip,rk3228-gmac @@ -310,6 +319,11 @@ allOf: - allwinner,sun8i-r40-emac - allwinner,sun8i-v3s-emac - allwinner,sun50i-a64-emac + - ingenic,jz4775-mac + - ingenic,x1000-mac + - ingenic,x1600-mac + - ingenic,x1830-mac + - ingenic,x2000-mac - snps,dwxgmac - snps,dwxgmac-2.10 - st,spear600-gmac @@ -353,6 +367,13 @@ allOf: - allwinner,sun8i-r40-emac - allwinner,sun8i-v3s-emac - allwinner,sun50i-a64-emac + - loongson,ls2k-dwmac + - loongson,ls7a-dwmac + - ingenic,jz4775-mac + - ingenic,x1000-mac + - ingenic,x1600-mac + - ingenic,x1830-mac + - ingenic,x2000-mac - snps,dwmac-4.00 - snps,dwmac-4.10a - snps,dwmac-4.20a diff --git a/Documentation/devicetree/bindings/soc/microchip/microchip,polarfire-soc-sys-controller.yaml b/Documentation/devicetree/bindings/soc/microchip/microchip,polarfire-soc-sys-controller.yaml new file mode 100644 index 000000000000..2cd3bc6bd8d6 --- /dev/null +++ b/Documentation/devicetree/bindings/soc/microchip/microchip,polarfire-soc-sys-controller.yaml @@ -0,0 +1,35 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: "http://devicetree.org/schemas/soc/microchip/microchip,polarfire-soc-sys-controller.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: Microchip PolarFire SoC (MPFS) MSS (microprocessor subsystem) system controller + +maintainers: + - Conor Dooley + +description: | + The PolarFire SoC system controller is communicated with via a mailbox. + This document describes the bindings for the client portion of that mailbox. + + +properties: + mboxes: + maxItems: 1 + + compatible: + const: microchip,polarfire-soc-sys-controller + +required: + - compatible + - mboxes + +additionalProperties: false + +examples: + - | + syscontroller: syscontroller { + compatible = "microchip,polarfire-soc-sys-controller"; + mboxes = <&mbox 0>; + }; diff --git a/Documentation/driver-api/surface_aggregator/clients/cdev.rst b/Documentation/driver-api/surface_aggregator/clients/cdev.rst index 248c1372d879..0134a841a079 100644 --- a/Documentation/driver-api/surface_aggregator/clients/cdev.rst +++ b/Documentation/driver-api/surface_aggregator/clients/cdev.rst @@ -1,9 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0+ -.. |u8| replace:: :c:type:`u8 ` -.. |u16| replace:: :c:type:`u16 ` .. |ssam_cdev_request| replace:: :c:type:`struct ssam_cdev_request ` .. |ssam_cdev_request_flags| replace:: :c:type:`enum ssam_cdev_request_flags ` +.. |ssam_cdev_event| replace:: :c:type:`struct ssam_cdev_event ` ============================== User-Space EC Interface (cdev) @@ -23,6 +22,40 @@ These IOCTLs and their respective input/output parameter structs are defined in A small python library and scripts for accessing this interface can be found at https://github.com/linux-surface/surface-aggregator-module/tree/master/scripts/ssam. +.. contents:: + + +Receiving Events +================ + +Events can be received by reading from the device-file. The are represented by +the |ssam_cdev_event| datatype. + +Before events are available to be read, however, the desired notifiers must be +registered via the ``SSAM_CDEV_NOTIF_REGISTER`` IOCTL. Notifiers are, in +essence, callbacks, called when the EC sends an event. They are, in this +interface, associated with a specific target category and device-file-instance. +They forward any event of this category to the buffer of the corresponding +instance, from which it can then be read. + +Notifiers themselves do not enable events on the EC. Thus, it may additionally +be necessary to enable events via the ``SSAM_CDEV_EVENT_ENABLE`` IOCTL. While +notifiers work per-client (i.e. per-device-file-instance), events are enabled +globally, for the EC and all of its clients (regardless of userspace or +non-userspace). The ``SSAM_CDEV_EVENT_ENABLE`` and ``SSAM_CDEV_EVENT_DISABLE`` +IOCTLs take care of reference counting the events, such that an event is +enabled as long as there is a client that has requested it. + +Note that enabled events are not automatically disabled once the client +instance is closed. Therefore any client process (or group of processes) should +balance their event enable calls with the corresponding event disable calls. It +is, however, perfectly valid to enable and disable events on different client +instances. For example, it is valid to set up notifiers and read events on +client instance ``A``, enable those events on instance ``B`` (note that these +will also be received by A since events are enabled/disabled globally), and +after no more events are desired, disable the previously enabled events via +instance ``C``. + Controller IOCTLs ================= @@ -45,9 +78,33 @@ The following IOCTLs are provided: - ``REQUEST`` - Perform synchronous SAM request. + * - ``0xA5`` + - ``2`` + - ``W`` + - ``NOTIF_REGISTER`` + - Register event notifier. -``REQUEST`` ------------ + * - ``0xA5`` + - ``3`` + - ``W`` + - ``NOTIF_UNREGISTER`` + - Unregister event notifier. + + * - ``0xA5`` + - ``4`` + - ``W`` + - ``EVENT_ENABLE`` + - Enable event source. + + * - ``0xA5`` + - ``5`` + - ``W`` + - ``EVENT_DISABLE`` + - Disable event source. + + +``SSAM_CDEV_REQUEST`` +--------------------- Defined as ``_IOWR(0xA5, 1, struct ssam_cdev_request)``. @@ -82,6 +139,66 @@ submitted, and completed (i.e. handed back to user-space) successfully from inside the IOCTL, but the request ``status`` member may still be negative in case the actual execution of the request failed after it has been submitted. -A full definition of the argument struct is provided below: +A full definition of the argument struct is provided below. + +``SSAM_CDEV_NOTIF_REGISTER`` +---------------------------- + +Defined as ``_IOW(0xA5, 2, struct ssam_cdev_notifier_desc)``. + +Register a notifier for the event target category specified in the given +notifier description with the specified priority. Notifiers registration is +required to receive events, but does not enable events themselves. After a +notifier for a specific target category has been registered, all events of that +category will be forwarded to the userspace client and can then be read from +the device file instance. Note that events may have to be enabled, e.g. via the +``SSAM_CDEV_EVENT_ENABLE`` IOCTL, before the EC will send them. + +Only one notifier can be registered per target category and client instance. If +a notifier has already been registered, this IOCTL will fail with ``-EEXIST``. + +Notifiers will automatically be removed when the device file instance is +closed. + +``SSAM_CDEV_NOTIF_UNREGISTER`` +------------------------------ + +Defined as ``_IOW(0xA5, 3, struct ssam_cdev_notifier_desc)``. + +Unregisters the notifier associated with the specified target category. The +priority field will be ignored by this IOCTL. If no notifier has been +registered for this client instance and the given category, this IOCTL will +fail with ``-ENOENT``. + +``SSAM_CDEV_EVENT_ENABLE`` +-------------------------- + +Defined as ``_IOW(0xA5, 4, struct ssam_cdev_event_desc)``. + +Enable the event associated with the given event descriptor. + +Note that this call will not register a notifier itself, it will only enable +events on the controller. If you want to receive events by reading from the +device file, you will need to register the corresponding notifier(s) on that +instance. + +Events are not automatically disabled when the device file is closed. This must +be done manually, via a call to the ``SSAM_CDEV_EVENT_DISABLE`` IOCTL. + +``SSAM_CDEV_EVENT_DISABLE`` +--------------------------- + +Defined as ``_IOW(0xA5, 5, struct ssam_cdev_event_desc)``. + +Disable the event associated with the given event descriptor. + +Note that this will not unregister any notifiers. Events may still be received +and forwarded to user-space after this call. The only safe way of stopping +events from being received is unregistering all previously registered +notifiers. + + +Structures and Enums +==================== .. kernel-doc:: include/uapi/linux/surface_aggregator/cdev.h diff --git a/Documentation/filesystems/ext4/journal.rst b/Documentation/filesystems/ext4/journal.rst index cdbfec473167..5fad38860f17 100644 --- a/Documentation/filesystems/ext4/journal.rst +++ b/Documentation/filesystems/ext4/journal.rst @@ -4,14 +4,14 @@ Journal (jbd2) -------------- Introduced in ext3, the ext4 filesystem employs a journal to protect the -filesystem against corruption in the case of a system crash. A small -continuous region of disk (default 128MiB) is reserved inside the -filesystem as a place to land “important” data writes on-disk as quickly -as possible. Once the important data transaction is fully written to the -disk and flushed from the disk write cache, a record of the data being -committed is also written to the journal. At some later point in time, -the journal code writes the transactions to their final locations on -disk (this could involve a lot of seeking or a lot of small +filesystem against metadata inconsistencies in the case of a system crash. Up +to 10,240,000 file system blocks (see man mke2fs(8) for more details on journal +size limits) can be reserved inside the filesystem as a place to land +“important” data writes on-disk as quickly as possible. Once the important +data transaction is fully written to the disk and flushed from the disk write +cache, a record of the data being committed is also written to the journal. At +some later point in time, the journal code writes the transactions to their +final locations on disk (this could involve a lot of seeking or a lot of small read-write-erases) before erasing the commit record. Should the system crash during the second slow write, the journal can be replayed all the way to the latest commit record, guaranteeing the atomicity of whatever @@ -731,3 +731,26 @@ point, the refcount for inode 11 is not reliable, but that gets fixed by the replay of last inode 11 tag. Thus, by converting a non-idempotent procedure into a series of idempotent outcomes, fast commits ensured idempotence during the replay. + +Journal Checkpoint +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Checkpointing the journal ensures all transactions and their associated buffers +are submitted to the disk. In-progress transactions are waited upon and included +in the checkpoint. Checkpointing is used internally during critical updates to +the filesystem including journal recovery, filesystem resizing, and freeing of +the journal_t structure. + +A journal checkpoint can be triggered from userspace via the ioctl +EXT4_IOC_CHECKPOINT. This ioctl takes a single, u64 argument for flags. +Currently, three flags are supported. First, EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN +can be used to verify input to the ioctl. It returns error if there is any +invalid input, otherwise it returns success without performing +any checkpointing. This can be used to check whether the ioctl exists on a +system and to verify there are no issues with arguments or flags. The +other two flags are EXT4_IOC_CHECKPOINT_FLAG_DISCARD and +EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT. These flags cause the journal blocks to be +discarded or zero-filled, respectively, after the journal checkpoint is +complete. EXT4_IOC_CHECKPOINT_FLAG_DISCARD and EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT +cannot both be set. The ioctl may be useful when snapshotting a system or for +complying with content deletion SLOs. diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index 1e894480115b..2183fd8cc350 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -480,7 +480,7 @@ prototypes:: locking rules: ======================= =================== -ops bd_mutex +ops open_mutex ======================= =================== open: yes release: yes diff --git a/Documentation/firmware-guide/acpi/dsd/phy.rst b/Documentation/firmware-guide/acpi/dsd/phy.rst new file mode 100644 index 000000000000..680ad179e5f9 --- /dev/null +++ b/Documentation/firmware-guide/acpi/dsd/phy.rst @@ -0,0 +1,199 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================= +MDIO bus and PHYs in ACPI +========================= + +The PHYs on an MDIO bus [1] are probed and registered using +fwnode_mdiobus_register_phy(). + +Later, for connecting these PHYs to their respective MACs, the PHYs registered +on the MDIO bus have to be referenced. + +This document introduces two _DSD properties that are to be used +for connecting PHYs on the MDIO bus [3] to the MAC layer. + +These properties are defined in accordance with the "Device +Properties UUID For _DSD" [2] document and the +daffd814-6eba-4d8c-8a91-bc9bbf4aa301 UUID must be used in the Device +Data Descriptors containing them. + +phy-handle +---------- +For each MAC node, a device property "phy-handle" is used to reference +the PHY that is registered on an MDIO bus. This is mandatory for +network interfaces that have PHYs connected to MAC via MDIO bus. + +During the MDIO bus driver initialization, PHYs on this bus are probed +using the _ADR object as shown below and are registered on the MDIO bus. + +.. code-block:: none + + Scope(\_SB.MDI0) + { + Device(PHY1) { + Name (_ADR, 0x1) + } // end of PHY1 + + Device(PHY2) { + Name (_ADR, 0x2) + } // end of PHY2 + } + +Later, during the MAC driver initialization, the registered PHY devices +have to be retrieved from the MDIO bus. For this, the MAC driver needs +references to the previously registered PHYs which are provided +as device object references (e.g. \_SB.MDI0.PHY1). + +phy-mode +-------- +The "phy-mode" _DSD property is used to describe the connection to +the PHY. The valid values for "phy-mode" are defined in [4]. + +managed +------- +Optional property, which specifies the PHY management type. +The valid values for "managed" are defined in [4]. + +fixed-link +---------- +The "fixed-link" is described by a data-only subnode of the +MAC port, which is linked in the _DSD package via +hierarchical data extension (UUID dbb8e3e6-5886-4ba6-8795-1319f52a966b +in accordance with [5] "_DSD Implementation Guide" document). +The subnode should comprise a required property ("speed") and +possibly the optional ones - complete list of parameters and +their values are specified in [4]. + +The following ASL example illustrates the usage of these properties. + +DSDT entry for MDIO node +------------------------ + +The MDIO bus has an SoC component (MDIO controller) and a platform +component (PHYs on the MDIO bus). + +a) Silicon Component +This node describes the MDIO controller, MDI0 +--------------------------------------------- + +.. code-block:: none + + Scope(_SB) + { + Device(MDI0) { + Name(_HID, "NXP0006") + Name(_CCA, 1) + Name(_UID, 0) + Name(_CRS, ResourceTemplate() { + Memory32Fixed(ReadWrite, MDI0_BASE, MDI_LEN) + Interrupt(ResourceConsumer, Level, ActiveHigh, Shared) + { + MDI0_IT + } + }) // end of _CRS for MDI0 + } // end of MDI0 + } + +b) Platform Component +The PHY1 and PHY2 nodes represent the PHYs connected to MDIO bus MDI0 +--------------------------------------------------------------------- + +.. code-block:: none + + Scope(\_SB.MDI0) + { + Device(PHY1) { + Name (_ADR, 0x1) + } // end of PHY1 + + Device(PHY2) { + Name (_ADR, 0x2) + } // end of PHY2 + } + +DSDT entries representing MAC nodes +----------------------------------- + +Below are the MAC nodes where PHY nodes are referenced. +phy-mode and phy-handle are used as explained earlier. +------------------------------------------------------ + +.. code-block:: none + + Scope(\_SB.MCE0.PR17) + { + Name (_DSD, Package () { + ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"), + Package () { + Package (2) {"phy-mode", "rgmii-id"}, + Package (2) {"phy-handle", \_SB.MDI0.PHY1} + } + }) + } + + Scope(\_SB.MCE0.PR18) + { + Name (_DSD, Package () { + ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"), + Package () { + Package (2) {"phy-mode", "rgmii-id"}, + Package (2) {"phy-handle", \_SB.MDI0.PHY2}} + } + }) + } + +MAC node example where "managed" property is specified. +------------------------------------------------------- + +.. code-block:: none + + Scope(\_SB.PP21.ETH0) + { + Name (_DSD, Package () { + ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"), + Package () { + Package () {"phy-mode", "sgmii"}, + Package () {"managed", "in-band-status"} + } + }) + } + +MAC node example with a "fixed-link" subnode. +--------------------------------------------- + +.. code-block:: none + + Scope(\_SB.PP21.ETH1) + { + Name (_DSD, Package () { + ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"), + Package () { + Package () {"phy-mode", "sgmii"}, + }, + ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"), + Package () { + Package () {"fixed-link", "LNK0"} + } + }) + Name (LNK0, Package(){ // Data-only subnode of port + ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"), + Package () { + Package () {"speed", 1000}, + Package () {"full-duplex", 1} + } + }) + } + +References +========== + +[1] Documentation/networking/phy.rst + +[2] https://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf + +[3] Documentation/firmware-guide/acpi/DSD-properties-rules.rst + +[4] Documentation/devicetree/bindings/net/ethernet-controller.yaml + +[5] https://github.com/UEFI/DSD-Guide/blob/main/dsd-guide.pdf diff --git a/Documentation/firmware-guide/acpi/index.rst b/Documentation/firmware-guide/acpi/index.rst index f72b5f1769fb..a99ee402b212 100644 --- a/Documentation/firmware-guide/acpi/index.rst +++ b/Documentation/firmware-guide/acpi/index.rst @@ -11,6 +11,7 @@ ACPI Support dsd/graph dsd/data-node-references dsd/leds + dsd/phy enumeration osi method-customizing diff --git a/Documentation/networking/af_xdp.rst b/Documentation/networking/af_xdp.rst index 2ccc5644cc98..42576880aa4a 100644 --- a/Documentation/networking/af_xdp.rst +++ b/Documentation/networking/af_xdp.rst @@ -290,19 +290,19 @@ round-robin example of distributing packets is shown below: #define MAX_SOCKS 16 struct { - __uint(type, BPF_MAP_TYPE_XSKMAP); - __uint(max_entries, MAX_SOCKS); - __uint(key_size, sizeof(int)); - __uint(value_size, sizeof(int)); + __uint(type, BPF_MAP_TYPE_XSKMAP); + __uint(max_entries, MAX_SOCKS); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); } xsks_map SEC(".maps"); static unsigned int rr; SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx) { - rr = (rr + 1) & (MAX_SOCKS - 1); + rr = (rr + 1) & (MAX_SOCKS - 1); - return bpf_redirect_map(&xsks_map, rr, XDP_DROP); + return bpf_redirect_map(&xsks_map, rr, XDP_DROP); } Note, that since there is only a single set of FILL and COMPLETION @@ -379,7 +379,7 @@ would look like this for the TX path: .. code-block:: c if (xsk_ring_prod__needs_wakeup(&my_tx_ring)) - sendto(xsk_socket__fd(xsk_handle), NULL, 0, MSG_DONTWAIT, NULL, 0); + sendto(xsk_socket__fd(xsk_handle), NULL, 0, MSG_DONTWAIT, NULL, 0); I.e., only use the syscall if the flag is set. @@ -442,9 +442,9 @@ purposes. The supported statistics are shown below: .. code-block:: c struct xdp_statistics { - __u64 rx_dropped; /* Dropped for reasons other than invalid desc */ - __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */ - __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ + __u64 rx_dropped; /* Dropped for reasons other than invalid desc */ + __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */ + __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ }; XDP_OPTIONS getsockopt @@ -483,15 +483,15 @@ like this: .. code-block:: c // struct xdp_rxtx_ring { - // __u32 *producer; - // __u32 *consumer; - // struct xdp_desc *desc; + // __u32 *producer; + // __u32 *consumer; + // struct xdp_desc *desc; // }; // struct xdp_umem_ring { - // __u32 *producer; - // __u32 *consumer; - // __u64 *desc; + // __u32 *producer; + // __u32 *consumer; + // __u64 *desc; // }; // typedef struct xdp_rxtx_ring RING; diff --git a/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst b/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst index 70643b58de05..4118384cf8eb 100644 --- a/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst +++ b/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst @@ -27,34 +27,136 @@ these MAP frames and send them to appropriate PDN's. 2. Packet format ================ -a. MAP packet (data / control) +a. MAP packet v1 (data / control) -MAP header has the same endianness of the IP packet. +MAP header fields are in big endian format. Packet format:: - Bit 0 1 2-7 8 - 15 16 - 31 + Bit 0 1 2-7 8-15 16-31 Function Command / Data Reserved Pad Multiplexer ID Payload length - Bit 32 - x - Function Raw Bytes + + Bit 32-x + Function Raw bytes Command (1)/ Data (0) bit value is to indicate if the packet is a MAP command -or data packet. Control packet is used for transport level flow control. Data +or data packet. Command packet is used for transport level flow control. Data packets are standard IP packets. -Reserved bits are usually zeroed out and to be ignored by receiver. +Reserved bits must be zero when sent and ignored when received. -Padding is number of bytes to be added for 4 byte alignment if required by -hardware. +Padding is the number of bytes to be appended to the payload to +ensure 4 byte alignment. Multiplexer ID is to indicate the PDN on which data has to be sent. Payload length includes the padding length but does not include MAP header length. -b. MAP packet (command specific):: +b. Map packet v4 (data / control) - Bit 0 1 2-7 8 - 15 16 - 31 +MAP header fields are in big endian format. + +Packet format:: + + Bit 0 1 2-7 8-15 16-31 + Function Command / Data Reserved Pad Multiplexer ID Payload length + + Bit 32-(x-33) (x-32)-x + Function Raw bytes Checksum offload header + +Command (1)/ Data (0) bit value is to indicate if the packet is a MAP command +or data packet. Command packet is used for transport level flow control. Data +packets are standard IP packets. + +Reserved bits must be zero when sent and ignored when received. + +Padding is the number of bytes to be appended to the payload to +ensure 4 byte alignment. + +Multiplexer ID is to indicate the PDN on which data has to be sent. + +Payload length includes the padding length but does not include MAP header +length. + +Checksum offload header, has the information about the checksum processing done +by the hardware.Checksum offload header fields are in big endian format. + +Packet format:: + + Bit 0-14 15 16-31 + Function Reserved Valid Checksum start offset + + Bit 31-47 48-64 + Function Checksum length Checksum value + +Reserved bits must be zero when sent and ignored when received. + +Valid bit indicates whether the partial checksum is calculated and is valid. +Set to 1, if its is valid. Set to 0 otherwise. + +Padding is the number of bytes to be appended to the payload to +ensure 4 byte alignment. + +Checksum start offset, Indicates the offset in bytes from the beginning of the +IP header, from which modem computed checksum. + +Checksum length is the Length in bytes starting from CKSUM_START_OFFSET, +over which checksum is computed. + +Checksum value, indicates the checksum computed. + +c. MAP packet v5 (data / control) + +MAP header fields are in big endian format. + +Packet format:: + + Bit 0 1 2-7 8-15 16-31 + Function Command / Data Next header Pad Multiplexer ID Payload length + + Bit 32-x + Function Raw bytes + +Command (1)/ Data (0) bit value is to indicate if the packet is a MAP command +or data packet. Command packet is used for transport level flow control. Data +packets are standard IP packets. + +Next header is used to indicate the presence of another header, currently is +limited to checksum header. + +Padding is the number of bytes to be appended to the payload to +ensure 4 byte alignment. + +Multiplexer ID is to indicate the PDN on which data has to be sent. + +Payload length includes the padding length but does not include MAP header +length. + +d. Checksum offload header v5 + +Checksum offload header fields are in big endian format. + + Bit 0 - 6 7 8-15 16-31 + Function Header Type Next Header Checksum Valid Reserved + +Header Type is to indicate the type of header, this usually is set to CHECKSUM + +Header types += ========================================== +0 Reserved +1 Reserved +2 checksum header + +Checksum Valid is to indicate whether the header checksum is valid. Value of 1 +implies that checksum is calculated on this packet and is valid, value of 0 +indicates that the calculated packet checksum is invalid. + +Reserved bits must be zero when sent and ignored when received. + +e. MAP packet v1/v5 (command specific):: + + Bit 0 1 2-7 8 - 15 16 - 31 Function Command Reserved Pad Multiplexer ID Payload length Bit 32 - 39 40 - 45 46 - 47 48 - 63 Function Command name Reserved Command Type Reserved @@ -74,7 +176,7 @@ Command types 3 is for error during processing of commands = ========================================== -c. Aggregation +f. Aggregation Aggregation is multiple MAP packets (can be data or command) delivered to rmnet in a single linear skb. rmnet will process the individual diff --git a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst index f8c6469f2bd2..01b2a69b0cb0 100644 --- a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst +++ b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst @@ -11,12 +11,12 @@ ENA is a networking interface designed to make good use of modern CPU features and system architectures. The ENA device exposes a lightweight management interface with a -minimal set of memory mapped registers and extendable command set +minimal set of memory mapped registers and extendible command set through an Admin Queue. The driver supports a range of ENA devices, is link-speed independent -(i.e., the same driver is used for 10GbE, 25GbE, 40GbE, etc.), and has -a negotiated and extendable feature set. +(i.e., the same driver is used for 10GbE, 25GbE, 40GbE, etc), and has +a negotiated and extendible feature set. Some ENA devices support SR-IOV. This driver is used for both the SR-IOV Physical Function (PF) and Virtual Function (VF) devices. @@ -27,9 +27,9 @@ is advertised by the device via the Admin Queue), a dedicated MSI-X interrupt vector per Tx/Rx queue pair, adaptive interrupt moderation, and CPU cacheline optimized data placement. -The ENA driver supports industry standard TCP/IP offload features such -as checksum offload and TCP transmit segmentation offload (TSO). -Receive-side scaling (RSS) is supported for multi-core scaling. +The ENA driver supports industry standard TCP/IP offload features such as +checksum offload. Receive-side scaling (RSS) is supported for multi-core +scaling. The ENA driver and its corresponding devices implement health monitoring mechanisms such as watchdog, enabling the device and driver @@ -38,22 +38,20 @@ debug logs. Some of the ENA devices support a working mode called Low-latency Queue (LLQ), which saves several more microseconds. - ENA Source Code Directory Structure =================================== ================= ====================================================== ena_com.[ch] Management communication layer. This layer is - responsible for the handling all the management - (admin) communication between the device and the - driver. + responsible for the handling all the management + (admin) communication between the device and the + driver. ena_eth_com.[ch] Tx/Rx data path. ena_admin_defs.h Definition of ENA management interface. ena_eth_io_defs.h Definition of ENA data path interface. ena_common_defs.h Common definitions for ena_com layer. ena_regs_defs.h Definition of ENA PCI memory-mapped (MMIO) registers. ena_netdev.[ch] Main Linux kernel driver. -ena_syfsfs.[ch] Sysfs files. ena_ethtool.c ethtool callbacks. ena_pci_id_tbl.h Supported device IDs. ================= ====================================================== @@ -69,7 +67,7 @@ ENA management interface is exposed by means of: - Asynchronous Event Notification Queue (AENQ) ENA device MMIO Registers are accessed only during driver -initialization and are not involved in further normal device +initialization and are not used during further normal device operation. AQ is used for submitting management commands, and the @@ -100,28 +98,27 @@ group may have multiple syndromes, as shown below The events are: - ==================== =============== - Group Syndrome - ==================== =============== - Link state change **X** - Fatal error **X** - Notification Suspend traffic - Notification Resume traffic - Keep-Alive **X** - ==================== =============== +==================== =============== +Group Syndrome +==================== =============== +Link state change **X** +Fatal error **X** +Notification Suspend traffic +Notification Resume traffic +Keep-Alive **X** +==================== =============== ACQ and AENQ share the same MSI-X vector. -Keep-Alive is a special mechanism that allows monitoring of the -device's health. The driver maintains a watchdog (WD) handler which, -if fired, logs the current state and statistics then resets and -restarts the ENA device and driver. A Keep-Alive event is delivered by -the device every second. The driver re-arms the WD upon reception of a -Keep-Alive event. A missed Keep-Alive event causes the WD handler to -fire. +Keep-Alive is a special mechanism that allows monitoring the device's health. +A Keep-Alive event is delivered by the device every second. +The driver maintains a watchdog (WD) handler which logs the current state and +statistics. If the keep-alive events aren't delivered as expected the WD resets +the device and the driver. Data Path Interface =================== + I/O operations are based on Tx and Rx Submission Queues (Tx SQ and Rx SQ correspondingly). Each SQ has a completion queue (CQ) associated with it. @@ -131,26 +128,24 @@ physical memory. The ENA driver supports two Queue Operation modes for Tx SQs: -- Regular mode +- **Regular mode:** + In this mode the Tx SQs reside in the host's memory. The ENA + device fetches the ENA Tx descriptors and packet data from host + memory. - * In this mode the Tx SQs reside in the host's memory. The ENA - device fetches the ENA Tx descriptors and packet data from host - memory. +- **Low Latency Queue (LLQ) mode or "push-mode":** + In this mode the driver pushes the transmit descriptors and the + first 128 bytes of the packet directly to the ENA device memory + space. The rest of the packet payload is fetched by the + device. For this operation mode, the driver uses a dedicated PCI + device memory BAR, which is mapped with write-combine capability. -- Low Latency Queue (LLQ) mode or "push-mode". - - * In this mode the driver pushes the transmit descriptors and the - first 128 bytes of the packet directly to the ENA device memory - space. The rest of the packet payload is fetched by the - device. For this operation mode, the driver uses a dedicated PCI - device memory BAR, which is mapped with write-combine capability. + **Note that** not all ENA devices support LLQ, and this feature is negotiated + with the device upon initialization. If the ENA device does not + support LLQ mode, the driver falls back to the regular mode. The Rx SQs support only the regular mode. -Note: Not all ENA devices support LLQ, and this feature is negotiated - with the device upon initialization. If the ENA device does not - support LLQ mode, the driver falls back to the regular mode. - The driver supports multi-queue for both Tx and Rx. This has various benefits: @@ -165,6 +160,7 @@ benefits: Interrupt Modes =============== + The driver assigns a single MSI-X vector per queue pair (for both Tx and Rx directions). The driver assigns an additional dedicated MSI-X vector for management (for ACQ and AENQ). @@ -190,20 +186,21 @@ unmasked by the driver after NAPI processing is complete. Interrupt Moderation ==================== + ENA driver and device can operate in conventional or adaptive interrupt moderation mode. -In conventional mode the driver instructs device to postpone interrupt +**In conventional mode** the driver instructs device to postpone interrupt posting according to static interrupt delay value. The interrupt delay -value can be configured through ethtool(8). The following ethtool -parameters are supported by the driver: tx-usecs, rx-usecs +value can be configured through `ethtool(8)`. The following `ethtool` +parameters are supported by the driver: ``tx-usecs``, ``rx-usecs`` -In adaptive interrupt moderation mode the interrupt delay value is +**In adaptive interrupt** moderation mode the interrupt delay value is updated by the driver dynamically and adjusted every NAPI cycle according to the traffic nature. -Adaptive coalescing can be switched on/off through ethtool(8) -adaptive_rx on|off parameter. +Adaptive coalescing can be switched on/off through `ethtool(8)`'s +:code:`adaptive_rx on|off` parameter. More information about Adaptive Interrupt Moderation (DIM) can be found in Documentation/networking/net_dim.rst @@ -214,17 +211,10 @@ The rx_copybreak is initialized by default to ENA_DEFAULT_RX_COPYBREAK and can be configured by the ETHTOOL_STUNABLE command of the SIOCETHTOOL ioctl. -SKB -=== -The driver-allocated SKB for frames received from Rx handling using -NAPI context. The allocation method depends on the size of the packet. -If the frame length is larger than rx_copybreak, napi_get_frags() -is used, otherwise netdev_alloc_skb_ip_align() is used, the buffer -content is copied (by CPU) to the SKB, and the buffer is recycled. - Statistics ========== -The user can obtain ENA device and driver statistics using ethtool. + +The user can obtain ENA device and driver statistics using `ethtool`. The driver can collect regular or extended statistics (including per-queue stats) from the device. @@ -232,22 +222,23 @@ In addition the driver logs the stats to syslog upon device reset. MTU === + The driver supports an arbitrarily large MTU with a maximum that is negotiated with the device. The driver configures MTU using the SetFeature command (ENA_ADMIN_MTU property). The user can change MTU -via ip(8) and similar legacy tools. +via `ip(8)` and similar legacy tools. Stateless Offloads ================== + The ENA driver supports: -- TSO over IPv4/IPv6 -- TSO with ECN - IPv4 header checksum offload - TCP/UDP over IPv4/IPv6 checksum offloads RSS === + - The ENA device supports RSS that allows flexible Rx traffic steering. - Toeplitz and CRC32 hash functions are supported. @@ -260,41 +251,42 @@ RSS function delivered in the Rx CQ descriptor is set in the received SKB. - The user can provide a hash key, hash function, and configure the - indirection table through ethtool(8). + indirection table through `ethtool(8)`. DATA PATH ========= + Tx -- -ena_start_xmit() is called by the stack. This function does the following: +:code:`ena_start_xmit()` is called by the stack. This function does the following: -- Maps data buffers (skb->data and frags). -- Populates ena_buf for the push buffer (if the driver and device are - in push mode.) +- Maps data buffers (``skb->data`` and frags). +- Populates ``ena_buf`` for the push buffer (if the driver and device are + in push mode). - Prepares ENA bufs for the remaining frags. -- Allocates a new request ID from the empty req_id ring. The request +- Allocates a new request ID from the empty ``req_id`` ring. The request ID is the index of the packet in the Tx info. This is used for - out-of-order TX completions. + out-of-order Tx completions. - Adds the packet to the proper place in the Tx ring. -- Calls ena_com_prepare_tx(), an ENA communication layer that converts - the ena_bufs to ENA descriptors (and adds meta ENA descriptors as - needed.) +- Calls :code:`ena_com_prepare_tx()`, an ENA communication layer that converts + the ``ena_bufs`` to ENA descriptors (and adds meta ENA descriptors as + needed). * This function also copies the ENA descriptors and the push buffer - to the Device memory space (if in push mode.) + to the Device memory space (if in push mode). -- Writes doorbell to the ENA device. +- Writes a doorbell to the ENA device. - When the ENA device finishes sending the packet, a completion interrupt is raised. - The interrupt handler schedules NAPI. -- The ena_clean_tx_irq() function is called. This function handles the +- The :code:`ena_clean_tx_irq()` function is called. This function handles the completion descriptors generated by the ENA, with a single completion descriptor per completed packet. - * req_id is retrieved from the completion descriptor. The tx_info of - the packet is retrieved via the req_id. The data buffers are - unmapped and req_id is returned to the empty req_id ring. + * ``req_id`` is retrieved from the completion descriptor. The ``tx_info`` of + the packet is retrieved via the ``req_id``. The data buffers are + unmapped and ``req_id`` is returned to the empty ``req_id`` ring. * The function stops when the completion descriptors are completed or the budget is reached. @@ -303,12 +295,11 @@ Rx - When a packet is received from the ENA device. - The interrupt handler schedules NAPI. -- The ena_clean_rx_irq() function is called. This function calls - ena_rx_pkt(), an ENA communication layer function, which returns the - number of descriptors used for a new unhandled packet, and zero if +- The :code:`ena_clean_rx_irq()` function is called. This function calls + :code:`ena_com_rx_pkt()`, an ENA communication layer function, which returns the + number of descriptors used for a new packet, and zero if no new packet is found. -- Then it calls the ena_clean_rx_irq() function. -- ena_eth_rx_skb() checks packet length: +- :code:`ena_rx_skb()` checks packet length: * If the packet is small (len < rx_copybreak), the driver allocates a SKB for the new packet, and copies the packet payload into the @@ -317,9 +308,10 @@ Rx - In this way the original data buffer is not passed to the stack and is reused for future Rx packets. - * Otherwise the function unmaps the Rx buffer, then allocates the - new SKB structure and hooks the Rx buffer to the SKB frags. + * Otherwise the function unmaps the Rx buffer, sets the first + descriptor as `skb`'s linear part and the other descriptors as the + `skb`'s frags. - The new SKB is updated with the necessary information (protocol, - checksum hw verify result, etc.), and then passed to the network - stack, using the NAPI interface function napi_gro_receive(). + checksum hw verify result, etc), and then passed to the network + stack, using the NAPI interface function :code:`napi_gro_receive()`. diff --git a/Documentation/networking/device_drivers/ethernet/google/gve.rst b/Documentation/networking/device_drivers/ethernet/google/gve.rst index 793693cef6e3..6d73ee78f3d7 100644 --- a/Documentation/networking/device_drivers/ethernet/google/gve.rst +++ b/Documentation/networking/device_drivers/ethernet/google/gve.rst @@ -47,13 +47,24 @@ The driver interacts with the device in the following ways: - Transmit and Receive Queues - See description below +Descriptor Formats +------------------ +GVE supports two descriptor formats: GQI and DQO. These two formats have +entirely different descriptors, which will be described below. + Registers --------- -All registers are MMIO and big endian. +All registers are MMIO. The registers are used for initializing and configuring the device as well as querying device status in response to management interrupts. +Endianness +---------- +- Admin Queue messages and registers are all Big Endian. +- GQI descriptors and datapath registers are Big Endian. +- DQO descriptors and datapath registers are Little Endian. + Admin Queue (AQ) ---------------- The Admin Queue is a PAGE_SIZE memory block, treated as an array of AQ @@ -97,10 +108,10 @@ the queues associated with that interrupt. The handler for these irqs schedule the napi for that block to run and poll the queues. -Traffic Queues --------------- -gVNIC's queues are composed of a descriptor ring and a buffer and are -assigned to a notification block. +GQI Traffic Queues +------------------ +GQI queues are composed of a descriptor ring and a buffer and are assigned to a +notification block. The descriptor rings are power-of-two-sized ring buffers consisting of fixed-size descriptors. They advance their head pointer using a __be32 @@ -121,3 +132,35 @@ Receive The buffers for receive rings are put into a data ring that is the same length as the descriptor ring and the head and tail pointers advance over the rings together. + +DQO Traffic Queues +------------------ +- Every TX and RX queue is assigned a notification block. + +- TX and RX buffers queues, which send descriptors to the device, use MMIO + doorbells to notify the device of new descriptors. + +- RX and TX completion queues, which receive descriptors from the device, use a + "generation bit" to know when a descriptor was populated by the device. The + driver initializes all bits with the "current generation". The device will + populate received descriptors with the "next generation" which is inverted + from the current generation. When the ring wraps, the current/next generation + are swapped. + +- It's the driver's responsibility to ensure that the RX and TX completion + queues are not overrun. This can be accomplished by limiting the number of + descriptors posted to HW. + +- TX packets have a 16 bit completion_tag and RX buffers have a 16 bit + buffer_id. These will be returned on the TX completion and RX queues + respectively to let the driver know which packet/buffer was completed. + +Transmit +~~~~~~~~ +A packet's buffers are DMA mapped for the device to access before transmission. +After the packet was successfully transmitted, the buffers are unmapped. + +Receive +~~~~~~~ +The driver posts fixed sized buffers to HW on the RX buffer queue. The packet +received on the associated RX queue may span multiple descriptors. diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst index 936a10f1942c..ef8cb62e82a1 100644 --- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst @@ -12,6 +12,7 @@ Contents - `Enabling the driver and kconfig options`_ - `Devlink info`_ - `Devlink parameters`_ +- `Bridge offload`_ - `mlx5 subfunction`_ - `mlx5 function attributes`_ - `Devlink health reporters`_ @@ -217,6 +218,37 @@ users try to enable them. $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev +Bridge offload +============== +The mlx5 driver implements support for offloading bridge rules when in switchdev +mode. Linux bridge FDBs are automatically offloaded when mlx5 switchdev +representor is attached to bridge. + +- Change device to switchdev mode:: + + $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev + +- Attach mlx5 switchdev representor 'enp8s0f0' to bridge netdev 'bridge1':: + + $ ip link set enp8s0f0 master bridge1 + +VLANs +----- +Following bridge VLAN functions are supported by mlx5: + +- VLAN filtering (including multiple VLANs per port):: + + $ ip link set bridge1 type bridge vlan_filtering 1 + $ bridge vlan add dev enp8s0f0 vid 2-3 + +- VLAN push on bridge ingress:: + + $ bridge vlan add dev enp8s0f0 vid 3 pvid + +- VLAN pop on bridge egress:: + + $ bridge vlan add dev enp8s0f0 vid 3 untagged + mlx5 subfunction ================ mlx5 supports subfunction management using devlink port (see :ref:`Documentation/networking/devlink/devlink-port.rst `) interface. @@ -568,3 +600,59 @@ tc and eswitch offloads tracepoints: $ cat /sys/kernel/debug/tracing/trace ... kworker/u48:7-2221 [009] ...1 1475.387435: mlx5e_rep_neigh_update: netdev: ens1f0 MAC: 24:8a:07:9a:17:9a IPv4: 1.1.1.10 IPv6: ::ffff:1.1.1.10 neigh_connected=1 + +Bridge offloads tracepoints: + +- mlx5_esw_bridge_fdb_entry_init: trace bridge FDB entry offloaded to mlx5:: + + $ echo mlx5:mlx5_esw_bridge_fdb_entry_init >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u20:9-2217 [003] ...1 318.582243: mlx5_esw_bridge_fdb_entry_init: net_device=enp8s0f0_0 addr=e4:fd:05:08:00:02 vid=0 flags=0 used=0 + +- mlx5_esw_bridge_fdb_entry_cleanup: trace bridge FDB entry deleted from mlx5:: + + $ echo mlx5:mlx5_esw_bridge_fdb_entry_cleanup >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + ip-2581 [005] ...1 318.629871: mlx5_esw_bridge_fdb_entry_cleanup: net_device=enp8s0f0_1 addr=e4:fd:05:08:00:03 vid=0 flags=0 used=16 + +- mlx5_esw_bridge_fdb_entry_refresh: trace bridge FDB entry offload refreshed in + mlx5:: + + $ echo mlx5:mlx5_esw_bridge_fdb_entry_refresh >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u20:8-3849 [003] ...1 466716: mlx5_esw_bridge_fdb_entry_refresh: net_device=enp8s0f0_0 addr=e4:fd:05:08:00:02 vid=3 flags=0 used=0 + +- mlx5_esw_bridge_vlan_create: trace bridge VLAN object add on mlx5 + representor:: + + $ echo mlx5:mlx5_esw_bridge_vlan_create >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + ip-2560 [007] ...1 318.460258: mlx5_esw_bridge_vlan_create: vid=1 flags=6 + +- mlx5_esw_bridge_vlan_cleanup: trace bridge VLAN object delete from mlx5 + representor:: + + $ echo mlx5:mlx5_esw_bridge_vlan_cleanup >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + bridge-2582 [007] ...1 318.653496: mlx5_esw_bridge_vlan_cleanup: vid=2 flags=8 + +- mlx5_esw_bridge_vport_init: trace mlx5 vport assigned with bridge upper + device:: + + $ echo mlx5:mlx5_esw_bridge_vport_init >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + ip-2560 [007] ...1 318.458915: mlx5_esw_bridge_vport_init: vport_num=1 + +- mlx5_esw_bridge_vport_cleanup: trace mlx5 vport removed from bridge upper + device:: + + $ echo mlx5:mlx5_esw_bridge_vport_cleanup >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + ip-5387 [000] ...1 573713: mlx5_esw_bridge_vport_cleanup: vport_num=1 diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst index d8279de7bf25..3a5a1d46e77e 100644 --- a/Documentation/networking/device_drivers/index.rst +++ b/Documentation/networking/device_drivers/index.rst @@ -18,6 +18,7 @@ Contents: qlogic/index wan/index wifi/index + wwan/index .. only:: subproject and html diff --git a/Documentation/networking/device_drivers/wwan/index.rst b/Documentation/networking/device_drivers/wwan/index.rst new file mode 100644 index 000000000000..1cb8c7371401 --- /dev/null +++ b/Documentation/networking/device_drivers/wwan/index.rst @@ -0,0 +1,18 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +WWAN Device Drivers +=================== + +Contents: + +.. toctree:: + :maxdepth: 2 + + iosm + +.. only:: subproject and html + + Indices + ======= + + * :ref:`genindex` diff --git a/Documentation/networking/device_drivers/wwan/iosm.rst b/Documentation/networking/device_drivers/wwan/iosm.rst new file mode 100644 index 000000000000..aceb0223eb46 --- /dev/null +++ b/Documentation/networking/device_drivers/wwan/iosm.rst @@ -0,0 +1,96 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +.. Copyright (C) 2020-21 Intel Corporation + +.. _iosm_driver_doc: + +=========================================== +IOSM Driver for Intel M.2 PCIe based Modems +=========================================== +The IOSM (IPC over Shared Memory) driver is a WWAN PCIe host driver developed +for linux or chrome platform for data exchange over PCIe interface between +Host platform & Intel M.2 Modem. The driver exposes interface conforming to the +MBIM protocol [1]. Any front end application ( eg: Modem Manager) could easily +manage the MBIM interface to enable data communication towards WWAN. + +Basic usage +=========== +MBIM functions are inactive when unmanaged. The IOSM driver only provides a +userspace interface MBIM "WWAN PORT" representing MBIM control channel and does +not play any role in managing the functionality. It is the job of a userspace +application to detect port enumeration and enable MBIM functionality. + +Examples of few such userspace application are: +- mbimcli (included with the libmbim [2] library), and +- Modem Manager [3] + +Management Applications to carry out below required actions for establishing +MBIM IP session: +- open the MBIM control channel +- configure network connection settings +- connect to network +- configure IP network interface + +Management application development +================================== +The driver and userspace interfaces are described below. The MBIM protocol is +described in [1] Mobile Broadband Interface Model v1.0 Errata-1. + +MBIM control channel userspace ABI +---------------------------------- + +/dev/wwan0mbim0 character device +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +The driver exposes an MBIM interface to the MBIM function by implementing +MBIM WWAN Port. The userspace end of the control channel pipe is a +/dev/wwan0mbim0 character device. Application shall use this interface for +MBIM protocol communication. + +Fragmentation +~~~~~~~~~~~~~ +The userspace application is responsible for all control message fragmentation +and defragmentation as per MBIM specification. + +/dev/wwan0mbim0 write() +~~~~~~~~~~~~~~~~~~~~~~~ +The MBIM control messages from the management application must not exceed the +negotiated control message size. + +/dev/wwan0mbim0 read() +~~~~~~~~~~~~~~~~~~~~~~ +The management application must accept control messages of up the negotiated +control message size. + +MBIM data channel userspace ABI +------------------------------- + +wwan0-X network device +~~~~~~~~~~~~~~~~~~~~~~ +The IOSM driver exposes IP link interface "wwan0-X" of type "wwan" for IP +traffic. Iproute network utility is used for creating "wwan0-X" network +interface and for associating it with MBIM IP session. The Driver supports +upto 8 IP sessions for simultaneous IP communication. + +The userspace management application is responsible for creating new IP link +prior to establishing MBIM IP session where the SessionId is greater than 0. + +For example, creating new IP link for a MBIM IP session with SessionId 1: + + ip link add dev wwan0-1 parentdev-name wwan0 type wwan linkid 1 + +The driver will automatically map the "wwan0-1" network device to MBIM IP +session 1. + +References +========== +[1] "MBIM (Mobile Broadband Interface Model) Errata-1" + - https://www.usb.org/document-library/ + +[2] libmbim - "a glib-based library for talking to WWAN modems and + devices which speak the Mobile Interface Broadband Model (MBIM) + protocol" + - http://www.freedesktop.org/wiki/Software/libmbim/ + +[3] Modem Manager - "a DBus-activated daemon which controls mobile + broadband (2G/3G/4G) devices and connections" + - http://www.freedesktop.org/wiki/Software/ModemManager/ diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index ab790e7980b8..7627b1da01f2 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -164,6 +164,41 @@ device to instantiate the subfunction device on particular PCI function. A subfunction device is created on the :ref:`Documentation/driver-api/auxiliary_bus.rst `. At this point a matching subfunction driver binds to the subfunction's auxiliary device. +Rate object management +====================== + +Devlink provides API to manage tx rates of single devlink port or a group. +This is done through rate objects, which can be one of the two types: + +``leaf`` + Represents a single devlink port; created/destroyed by the driver. Since leaf + have 1to1 mapping to its devlink port, in user space it is referred as + ``pci//``; + +``node`` + Represents a group of rate objects (leafs and/or nodes); created/deleted by + request from the userspace; initially empty (no rate objects added). In + userspace it is referred as ``pci//``, where + ``node_name`` can be any identifier, except decimal number, to avoid + collisions with leafs. + +API allows to configure following rate object's parameters: + +``tx_share`` + Minimum TX rate value shared among all other rate objects, or rate objects + that parts of the parent group, if it is a part of the same group. + +``tx_max`` + Maximum TX rate value. + +``parent`` + Parent node name. Parent node rate limits are considered as additional limits + to all node children limits. ``tx_max`` is an upper limit for children. + ``tx_share`` is a total bandwidth distributed among children. + +Driver implementations are allowed to support both or either rate object types +and setting methods of their parameters. + Terms and Definitions ===================== diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst index efa5f7f42c88..90d1381b88de 100644 --- a/Documentation/networking/devlink/devlink-trap.rst +++ b/Documentation/networking/devlink/devlink-trap.rst @@ -497,6 +497,7 @@ drivers: * Documentation/networking/devlink/netdevsim.rst * Documentation/networking/devlink/mlxsw.rst + * Documentation/networking/devlink/prestera.rst .. _Generic-Packet-Trap-Groups: diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst index 8428a1220723..b3b9e0692088 100644 --- a/Documentation/networking/devlink/index.rst +++ b/Documentation/networking/devlink/index.rst @@ -46,3 +46,4 @@ parameters, info versions, and other features it supports. qed ti-cpsw-switch am65-nuss-cpsw-switch + prestera diff --git a/Documentation/networking/devlink/netdevsim.rst b/Documentation/networking/devlink/netdevsim.rst index 02c2d20dc673..8a292fb5aaea 100644 --- a/Documentation/networking/devlink/netdevsim.rst +++ b/Documentation/networking/devlink/netdevsim.rst @@ -57,6 +57,32 @@ entries, FIB rule entries and nexthops that the driver will allow. $ devlink resource set netdevsim/netdevsim0 path /nexthops size 16 $ devlink dev reload netdevsim/netdevsim0 +Rate objects +============ + +The ``netdevsim`` driver supports rate objects management, which includes: + +- registerging/unregistering leaf rate objects per VF devlink port; +- creation/deletion node rate objects; +- setting tx_share and tx_max rate values for any rate object type; +- setting parent node for any rate object type. + +Rate nodes and it's parameters are exposed in ``netdevsim`` debugfs in RO mode. +For example created rate node with name ``some_group``: + +.. code:: shell + + $ ls /sys/kernel/debug/netdevsim/netdevsim0/rate_groups/some_group + rate_parent tx_max tx_share + +Same parameters are exposed for leaf objects in corresponding ports directories. +For ex.: + +.. code:: shell + + $ ls /sys/kernel/debug/netdevsim/netdevsim0/ports/1 + dev ethtool rate_parent tx_max tx_share + Driver-specific Traps ===================== diff --git a/Documentation/networking/devlink/prestera.rst b/Documentation/networking/devlink/prestera.rst new file mode 100644 index 000000000000..49409d1d3081 --- /dev/null +++ b/Documentation/networking/devlink/prestera.rst @@ -0,0 +1,141 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================== +prestera devlink support +======================== + +This document describes the devlink features implemented by the ``prestera`` +device driver. + +Driver-specific Traps +===================== + +.. list-table:: List of Driver-specific Traps Registered by ``prestera`` + :widths: 5 5 90 + + * - Name + - Type + - Description +.. list-table:: List of Driver-specific Traps Registered by ``prestera`` + :widths: 5 5 90 + + * - Name + - Type + - Description + * - ``arp_bc`` + - ``trap`` + - Traps ARP broadcast packets (both requests/responses) + * - ``is_is`` + - ``trap`` + - Traps IS-IS packets + * - ``ospf`` + - ``trap`` + - Traps OSPF packets + * - ``ip_bc_mac`` + - ``trap`` + - Traps IPv4 packets with broadcast DA Mac address + * - ``stp`` + - ``trap`` + - Traps STP BPDU + * - ``lacp`` + - ``trap`` + - Traps LACP packets + * - ``lldp`` + - ``trap`` + - Traps LLDP packets + * - ``router_mc`` + - ``trap`` + - Traps multicast packets + * - ``vrrp`` + - ``trap`` + - Traps VRRP packets + * - ``dhcp`` + - ``trap`` + - Traps DHCP packets + * - ``mtu_error`` + - ``trap`` + - Traps (exception) packets that exceeded port's MTU + * - ``mac_to_me`` + - ``trap`` + - Traps packets with switch-port's DA Mac address + * - ``ttl_error`` + - ``trap`` + - Traps (exception) IPv4 packets whose TTL exceeded + * - ``ipv4_options`` + - ``trap`` + - Traps (exception) packets due to the malformed IPV4 header options + * - ``ip_default_route`` + - ``trap`` + - Traps packets that have no specific IP interface (IP to me) and no forwarding prefix + * - ``local_route`` + - ``trap`` + - Traps packets that have been send to one of switch IP interfaces addresses + * - ``ipv4_icmp_redirect`` + - ``trap`` + - Traps (exception) IPV4 ICMP redirect packets + * - ``arp_response`` + - ``trap`` + - Traps ARP replies packets that have switch-port's DA Mac address + * - ``acl_code_0`` + - ``trap`` + - Traps packets that have ACL priority set to 0 (tc pref 0) + * - ``acl_code_1`` + - ``trap`` + - Traps packets that have ACL priority set to 1 (tc pref 1) + * - ``acl_code_2`` + - ``trap`` + - Traps packets that have ACL priority set to 2 (tc pref 2) + * - ``acl_code_3`` + - ``trap`` + - Traps packets that have ACL priority set to 3 (tc pref 3) + * - ``acl_code_4`` + - ``trap`` + - Traps packets that have ACL priority set to 4 (tc pref 4) + * - ``acl_code_5`` + - ``trap`` + - Traps packets that have ACL priority set to 5 (tc pref 5) + * - ``acl_code_6`` + - ``trap`` + - Traps packets that have ACL priority set to 6 (tc pref 6) + * - ``acl_code_7`` + - ``trap`` + - Traps packets that have ACL priority set to 7 (tc pref 7) + * - ``ipv4_bgp`` + - ``trap`` + - Traps IPv4 BGP packets + * - ``ssh`` + - ``trap`` + - Traps SSH packets + * - ``telnet`` + - ``trap`` + - Traps Telnet packets + * - ``icmp`` + - ``trap`` + - Traps ICMP packets + * - ``rxdma_drop`` + - ``drop`` + - Drops packets (RxDMA) due to the lack of ingress buffers etc. + * - ``port_no_vlan`` + - ``drop`` + - Drops packets due to faulty-configured network or due to internal bug (config issue). + * - ``local_port`` + - ``drop`` + - Drops packets whose decision (FDB entry) is to bridge packet back to the incoming port/trunk. + * - ``invalid_sa`` + - ``drop`` + - Drops packets with multicast source MAC address. + * - ``illegal_ip_addr`` + - ``drop`` + - Drops packets with illegal SIP/DIP multicast/unicast addresses. + * - ``illegal_ipv4_hdr`` + - ``drop`` + - Drops packets with illegal IPV4 header. + * - ``ip_uc_dip_da_mismatch`` + - ``drop`` + - Drops packets with destination MAC being unicast, but destination IP address being multicast. + * - ``ip_sip_is_zero`` + - ``drop`` + - Drops packets with zero (0) IPV4 source address. + * - ``met_red`` + - ``drop`` + - Drops non-conforming packets (dropped by Ingress policer, metering drop), e.g. packet rate exceeded configured bandwith. diff --git a/Documentation/networking/dsa/configuration.rst b/Documentation/networking/dsa/configuration.rst index 774f0e76c746..2b08f1a772d3 100644 --- a/Documentation/networking/dsa/configuration.rst +++ b/Documentation/networking/dsa/configuration.rst @@ -292,3 +292,71 @@ configuration. # bring up the bridge devices ip link set br0 up + +Forwarding database (FDB) management +------------------------------------ + +The existing DSA switches do not have the necessary hardware support to keep +the software FDB of the bridge in sync with the hardware tables, so the two +tables are managed separately (``bridge fdb show`` queries both, and depending +on whether the ``self`` or ``master`` flags are being used, a ``bridge fdb +add`` or ``bridge fdb del`` command acts upon entries from one or both tables). + +Up until kernel v4.14, DSA only supported user space management of bridge FDB +entries using the bridge bypass operations (which do not update the software +FDB, just the hardware one) using the ``self`` flag (which is optional and can +be omitted). + + .. code-block:: sh + + bridge fdb add dev swp0 00:01:02:03:04:05 self static + # or shorthand + bridge fdb add dev swp0 00:01:02:03:04:05 static + +Due to a bug, the bridge bypass FDB implementation provided by DSA did not +distinguish between ``static`` and ``local`` FDB entries (``static`` are meant +to be forwarded, while ``local`` are meant to be locally terminated, i.e. sent +to the host port). Instead, all FDB entries with the ``self`` flag (implicit or +explicit) are treated by DSA as ``static`` even if they are ``local``. + + .. code-block:: sh + + # This command: + bridge fdb add dev swp0 00:01:02:03:04:05 static + # behaves the same for DSA as this command: + bridge fdb add dev swp0 00:01:02:03:04:05 local + # or shorthand, because the 'local' flag is implicit if 'static' is not + # specified, it also behaves the same as: + bridge fdb add dev swp0 00:01:02:03:04:05 + +The last command is an incorrect way of adding a static bridge FDB entry to a +DSA switch using the bridge bypass operations, and works by mistake. Other +drivers will treat an FDB entry added by the same command as ``local`` and as +such, will not forward it, as opposed to DSA. + +Between kernel v4.14 and v5.14, DSA has supported in parallel two modes of +adding a bridge FDB entry to the switch: the bridge bypass discussed above, as +well as a new mode using the ``master`` flag which installs FDB entries in the +software bridge too. + + .. code-block:: sh + + bridge fdb add dev swp0 00:01:02:03:04:05 master static + +Since kernel v5.14, DSA has gained stronger integration with the bridge's +software FDB, and the support for its bridge bypass FDB implementation (using +the ``self`` flag) has been removed. This results in the following changes: + + .. code-block:: sh + + # This is the only valid way of adding an FDB entry that is supported, + # compatible with v4.14 kernels and later: + bridge fdb add dev swp0 00:01:02:03:04:05 master static + # This command is no longer buggy and the entry is properly treated as + # 'local' instead of being forwarded: + bridge fdb add dev swp0 00:01:02:03:04:05 + # This command no longer installs a static FDB entry to hardware: + bridge fdb add dev swp0 00:01:02:03:04:05 static + +Script writers are therefore encouraged to use the ``master static`` set of +flags when working with bridge FDB entries on DSA switch interfaces. diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst index 8688009514cc..20baacf2bc5c 100644 --- a/Documentation/networking/dsa/dsa.rst +++ b/Documentation/networking/dsa/dsa.rst @@ -93,14 +93,15 @@ A tagging protocol may tag all packets with switch tags of the same length, or the tag length might vary (for example packets with PTP timestamps might require an extended switch tag, or there might be one tag length on TX and a different one on RX). Either way, the tagging protocol driver must populate the -``struct dsa_device_ops::overhead`` with the length in octets of the longest -switch frame header. The DSA framework will automatically adjust the MTU of the -master interface to accomodate for this extra size in order for DSA user ports -to support the standard MTU (L2 payload length) of 1500 octets. The ``overhead`` -is also used to request from the network stack, on a best-effort basis, the -allocation of packets with a ``needed_headroom`` or ``needed_tailroom`` -sufficient such that the act of pushing the switch tag on transmission of a -packet does not cause it to reallocate due to lack of memory. +``struct dsa_device_ops::needed_headroom`` and/or ``struct dsa_device_ops::needed_tailroom`` +with the length in octets of the longest switch frame header/trailer. The DSA +framework will automatically adjust the MTU of the master interface to +accommodate for this extra size in order for DSA user ports to support the +standard MTU (L2 payload length) of 1500 octets. The ``needed_headroom`` and +``needed_tailroom`` properties are also used to request from the network stack, +on a best-effort basis, the allocation of packets with enough extra space such +that the act of pushing the switch tag on transmission of a packet does not +cause it to reallocate due to lack of memory. Even though applications are not expected to parse DSA-specific frame headers, the format on the wire of the tagging protocol represents an Application Binary @@ -169,8 +170,8 @@ The job of this method is to prepare the skb in a way that the switch will understand what egress port the packet is for (and not deliver it towards other ports). Typically this is fulfilled by pushing a frame header. Checking for insufficient size in the skb headroom or tailroom is unnecessary provided that -the ``overhead`` and ``tail_tag`` properties were filled out properly, because -DSA ensures there is enough space before calling this method. +the ``needed_headroom`` and ``needed_tailroom`` properties were filled out +properly, because DSA ensures there is enough space before calling this method. The reception of a packet goes through the tagger's ``rcv`` function. The passed ``struct sk_buff *skb`` has ``skb->data`` pointing at diff --git a/Documentation/networking/dsa/sja1105.rst b/Documentation/networking/dsa/sja1105.rst index 7395a33baaf9..da4057ba37f1 100644 --- a/Documentation/networking/dsa/sja1105.rst +++ b/Documentation/networking/dsa/sja1105.rst @@ -5,7 +5,7 @@ NXP SJA1105 switch driver Overview ======== -The NXP SJA1105 is a family of 6 devices: +The NXP SJA1105 is a family of 10 SPI-managed automotive switches: - SJA1105E: First generation, no TTEthernet - SJA1105T: First generation, TTEthernet @@ -13,9 +13,11 @@ The NXP SJA1105 is a family of 6 devices: - SJA1105Q: Second generation, TTEthernet, no SGMII - SJA1105R: Second generation, no TTEthernet, SGMII - SJA1105S: Second generation, TTEthernet, SGMII - -These are SPI-managed automotive switches, with all ports being gigabit -capable, and supporting MII/RMII/RGMII and optionally SGMII on one port. +- SJA1110A: Third generation, TTEthernet, SGMII, integrated 100base-T1 and + 100base-TX PHYs +- SJA1110B: Third generation, TTEthernet, SGMII, 100base-T1, 100base-TX +- SJA1110C: Third generation, TTEthernet, SGMII, 100base-T1, 100base-TX +- SJA1110D: Third generation, TTEthernet, SGMII, 100base-T1 Being automotive parts, their configuration interface is geared towards set-and-forget use, with minimal dynamic interaction at runtime. They @@ -579,3 +581,54 @@ A board would need to hook up the PHYs connected to the switch to any other MDIO bus available to Linux within the system (e.g. to the DSA master's MDIO bus). Link state management then works by the driver manually keeping in sync (over SPI commands) the MAC link speed with the settings negotiated by the PHY. + +By comparison, the SJA1110 supports an MDIO slave access point over which its +internal 100base-T1 PHYs can be accessed from the host. This is, however, not +used by the driver, instead the internal 100base-T1 and 100base-TX PHYs are +accessed through SPI commands, modeled in Linux as virtual MDIO buses. + +The microcontroller attached to the SJA1110 port 0 also has an MDIO controller +operating in master mode, however the driver does not support this either, +since the microcontroller gets disabled when the Linux driver operates. +Discrete PHYs connected to the switch ports should have their MDIO interface +attached to an MDIO controller from the host system and not to the switch, +similar to SJA1105. + +Port compatibility matrix +------------------------- + +The SJA1105 port compatibility matrix is: + +===== ============== ============== ============== +Port SJA1105E/T SJA1105P/Q SJA1105R/S +===== ============== ============== ============== +0 xMII xMII xMII +1 xMII xMII xMII +2 xMII xMII xMII +3 xMII xMII xMII +4 xMII xMII SGMII +===== ============== ============== ============== + + +The SJA1110 port compatibility matrix is: + +===== ============== ============== ============== ============== +Port SJA1110A SJA1110B SJA1110C SJA1110D +===== ============== ============== ============== ============== +0 RevMII (uC) RevMII (uC) RevMII (uC) RevMII (uC) +1 100base-TX 100base-TX 100base-TX + or SGMII SGMII +2 xMII xMII xMII xMII + or SGMII or SGMII +3 xMII xMII xMII + or SGMII or SGMII SGMII + or 2500base-X or 2500base-X or 2500base-X +4 SGMII SGMII SGMII SGMII + or 2500base-X or 2500base-X or 2500base-X or 2500base-X +5 100base-T1 100base-T1 100base-T1 100base-T1 +6 100base-T1 100base-T1 100base-T1 100base-T1 +7 100base-T1 100base-T1 100base-T1 100base-T1 +8 100base-T1 100base-T1 n/a n/a +9 100base-T1 100base-T1 n/a n/a +10 100base-T1 n/a n/a n/a +===== ============== ============== ============== ============== diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 25131df3c2bd..6ea91e41593f 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1363,8 +1363,8 @@ in an implementation specific way. ``ETHTOOL_A_FEC_AUTO`` requests the driver to choose FEC mode based on SFP module parameters. This does not mean autonegotiation. -MODULE_EEPROM -============= +MODULE_EEPROM_GET +================= Fetch module EEPROM data dump. This interface is designed to allow dumps of at most 1/2 page at once. This @@ -1383,12 +1383,14 @@ Request contents: ``ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS`` u8 page I2C address ======================================= ====== ========================== +If ``ETHTOOL_A_MODULE_EEPROM_BANK`` is not specified, bank 0 is assumed. + Kernel response contents: +---------------------------------------------+--------+---------------------+ | ``ETHTOOL_A_MODULE_EEPROM_HEADER`` | nested | reply header | +---------------------------------------------+--------+---------------------+ - | ``ETHTOOL_A_MODULE_EEPROM_DATA`` | nested | array of bytes from | + | ``ETHTOOL_A_MODULE_EEPROM_DATA`` | binary | array of bytes from | | | | module EEPROM | +---------------------------------------------+--------+---------------------+ diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index c2ecc9894fd0..b3fa522e4cd9 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -99,6 +99,35 @@ fib_multipath_hash_policy - INTEGER - 0 - Layer 3 - 1 - Layer 4 - 2 - Layer 3 or inner Layer 3 if present + - 3 - Custom multipath hash. Fields used for multipath hash calculation + are determined by fib_multipath_hash_fields sysctl + +fib_multipath_hash_fields - UNSIGNED INTEGER + When fib_multipath_hash_policy is set to 3 (custom multipath hash), the + fields used for multipath hash calculation are determined by this + sysctl. + + This value is a bitmask which enables various fields for multipath hash + calculation. + + Possible fields are: + + ====== ============================ + 0x0001 Source IP address + 0x0002 Destination IP address + 0x0004 IP protocol + 0x0008 Unused (Flow Label) + 0x0010 Source port + 0x0020 Destination port + 0x0040 Inner source IP address + 0x0080 Inner destination IP address + 0x0100 Inner IP protocol + 0x0200 Inner Flow Label + 0x0400 Inner source port + 0x0800 Inner destination port + ====== ============================ + + Default: 0x0007 (source IP, destination IP and IP protocol) fib_sync_mem - UNSIGNED INTEGER Amount of dirty memory from fib entries that can be backlogged before @@ -732,6 +761,31 @@ tcp_syncookies - INTEGER network connections you can set this knob to 2 to enable unconditionally generation of syncookies. +tcp_migrate_req - BOOLEAN + The incoming connection is tied to a specific listening socket when + the initial SYN packet is received during the three-way handshake. + When a listener is closed, in-flight request sockets during the + handshake and established sockets in the accept queue are aborted. + + If the listener has SO_REUSEPORT enabled, other listeners on the + same port should have been able to accept such connections. This + option makes it possible to migrate such child sockets to another + listener after close() or shutdown(). + + The BPF_SK_REUSEPORT_SELECT_OR_MIGRATE type of eBPF program should + usually be used to define the policy to pick an alive listener. + Otherwise, the kernel will randomly pick an alive listener only if + this option is enabled. + + Note that migration between listeners with different settings may + crash applications. Let's say migration happens from listener A to + B, and only B has TCP_SAVE_SYN enabled. B cannot read SYN data from + the requests migrated from A. To avoid such a situation, cancel + migration by returning SK_DROP in the type of eBPF program, or + disable this option. + + Default: 0 + tcp_fastopen - INTEGER Enable TCP Fast Open (RFC7413) to send and accept data in the opening SYN packet. @@ -1743,6 +1797,35 @@ fib_multipath_hash_policy - INTEGER - 0 - Layer 3 (source and destination addresses plus flow label) - 1 - Layer 4 (standard 5-tuple) - 2 - Layer 3 or inner Layer 3 if present + - 3 - Custom multipath hash. Fields used for multipath hash calculation + are determined by fib_multipath_hash_fields sysctl + +fib_multipath_hash_fields - UNSIGNED INTEGER + When fib_multipath_hash_policy is set to 3 (custom multipath hash), the + fields used for multipath hash calculation are determined by this + sysctl. + + This value is a bitmask which enables various fields for multipath hash + calculation. + + Possible fields are: + + ====== ============================ + 0x0001 Source IP address + 0x0002 Destination IP address + 0x0004 IP protocol + 0x0008 Flow Label + 0x0010 Source port + 0x0020 Destination port + 0x0040 Inner source IP address + 0x0080 Inner destination IP address + 0x0100 Inner IP protocol + 0x0200 Inner Flow Label + 0x0400 Inner source port + 0x0800 Inner destination port + ====== ============================ + + Default: 0x0007 (source IP, destination IP and IP protocol) anycast_src_echo_reply - BOOLEAN Controls the use of anycast addresses as source addresses for ICMPv6 @@ -2751,6 +2834,18 @@ encap_port - INTEGER Default: 0 +plpmtud_probe_interval - INTEGER + The time interval (in milliseconds) for the PLPMTUD probe timer, + which is configured to expire after this period to receive an + acknowledgment to a probe packet. This is also the time interval + between the probes for the current pmtu when the probe search + is done. + + PLPMTUD will be disabled when 0 is set, and other values for it + must be >= 5000. + + Default: 0 + ``/proc/sys/net/core/*`` ======================== diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst index 6af0196c4297..76d939e688b8 100644 --- a/Documentation/networking/mptcp-sysctl.rst +++ b/Documentation/networking/mptcp-sysctl.rst @@ -7,13 +7,13 @@ MPTCP Sysfs variables /proc/sys/net/mptcp/* Variables =============================== -enabled - INTEGER +enabled - BOOLEAN Control whether MPTCP sockets can be created. - MPTCP sockets can be created if the value is nonzero. This is - a per-namespace sysctl. + MPTCP sockets can be created if the value is 1. This is a + per-namespace sysctl. - Default: 1 + Default: 1 (enabled) add_addr_timeout - INTEGER (seconds) Set the timeout after which an ADD_ADDR control message will be @@ -24,3 +24,24 @@ add_addr_timeout - INTEGER (seconds) sysctl. Default: 120 + +checksum_enabled - BOOLEAN + Control whether DSS checksum can be enabled. + + DSS checksum can be enabled if the value is nonzero. This is a + per-namespace sysctl. + + Default: 0 + +allow_join_initial_addr_port - BOOLEAN + Allow peers to send join requests to the IP address and port number used + by the initial subflow if the value is 1. This controls a flag that is + sent to the peer at connection time, and whether such join requests are + accepted or denied. + + Joins to addresses advertised with ADD_ADDR are not affected by this + value. + + This is a per-namespace sysctl. + + Default: 1 diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst index 11a9b76786cb..0467b30e4abe 100644 --- a/Documentation/networking/nf_conntrack-sysctl.rst +++ b/Documentation/networking/nf_conntrack-sysctl.rst @@ -177,3 +177,27 @@ nf_conntrack_gre_timeout_stream - INTEGER (seconds) This extended timeout will be used in case there is an GRE stream detected. + +nf_flowtable_tcp_timeout - INTEGER (seconds) + default 30 + + Control offload timeout for tcp connections. + TCP connections may be offloaded from nf conntrack to nf flow table. + Once aged, the connection is returned to nf conntrack with tcp pickup timeout. + +nf_flowtable_tcp_pickup - INTEGER (seconds) + default 120 + + TCP connection timeout after being aged from nf flow table offload. + +nf_flowtable_udp_timeout - INTEGER (seconds) + default 30 + + Control offload timeout for udp connections. + UDP connections may be offloaded from nf conntrack to nf flow table. + Once aged, the connection is returned to nf conntrack with udp pickup timeout. + +nf_flowtable_udp_pickup - INTEGER (seconds) + default 30 + + UDP connection timeout after being aged from nf flow table offload. diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index 3f05d50ecd6e..571ba08386e7 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -292,6 +292,12 @@ Some of the interface modes are described below: Note: due to legacy usage, some 10GBASE-R usage incorrectly makes use of this definition. +``PHY_INTERFACE_MODE_25GBASER`` + This is the IEEE 802.3 PCS Clause 107 defined 25GBASE-R protocol. + The PCS is identical to 10GBASE-R, i.e. 64B/66B encoded + running 2.5 as fast, giving a fixed bit rate of 25.78125 Gbaud. + Please refer to the IEEE standard for further information. + ``PHY_INTERFACE_MODE_100BASEX`` This defines IEEE 802.3 Clause 24. The link operates at a fixed data rate of 125Mpbs using a 4B/5B encoding scheme, resulting in an underlying diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst index 18ae21bf7f92..d6bf84f061f4 100644 --- a/Documentation/power/runtime_pm.rst +++ b/Documentation/power/runtime_pm.rst @@ -378,7 +378,11 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: `int pm_runtime_get_sync(struct device *dev);` - increment the device's usage counter, run pm_runtime_resume(dev) and - return its result + return its result; + note that it does not drop the device's usage counter on errors, so + consider using pm_runtime_resume_and_get() instead of it, especially + if its return value is checked by the caller, as this is likely to + result in cleaner code. `int pm_runtime_get_if_in_use(struct device *dev);` - return -EINVAL if 'power.disable_depth' is nonzero; otherwise, if the @@ -827,6 +831,15 @@ or driver about runtime power changes. Instead, the driver for the device's parent must take responsibility for telling the device's driver when the parent's power state changes. +Note that, in some cases it may not be desirable for subsystems/drivers to call +pm_runtime_no_callbacks() for their devices. This could be because a subset of +the runtime PM callbacks needs to be implemented, a platform dependent PM +domain could get attached to the device or that the device is power managed +through a supplier device link. For these reasons and to avoid boilerplate code +in subsystems/drivers, the PM core allows runtime PM callbacks to be +unassigned. More precisely, if a callback pointer is NULL, the PM core will act +as though there was a callback and it returned 0. + 9. Autosuspend, or automatically-delayed suspends ================================================= diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 9bfc2b510c64..1409e40e6345 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -325,7 +325,7 @@ Code Seq# Include File Comments 0xA3 90-9F linux/dtlk.h 0xA4 00-1F uapi/linux/tee.h Generic TEE subsystem 0xA4 00-1F uapi/asm/sgx.h -0xA5 01 linux/surface_aggregator/cdev.h Microsoft Surface Platform System Aggregator +0xA5 01-05 linux/surface_aggregator/cdev.h Microsoft Surface Platform System Aggregator 0xA5 20-2F linux/surface_aggregator/dtx.h Microsoft Surface DTX driver diff --git a/Documentation/vm/memory-model.rst b/Documentation/vm/memory-model.rst index ce398a7dc6cd..30e8fbed6914 100644 --- a/Documentation/vm/memory-model.rst +++ b/Documentation/vm/memory-model.rst @@ -14,15 +14,11 @@ for the CPU. Then there could be several contiguous ranges at completely distinct addresses. And, don't forget about NUMA, where different memory banks are attached to different CPUs. -Linux abstracts this diversity using one of the three memory models: -FLATMEM, DISCONTIGMEM and SPARSEMEM. Each architecture defines what +Linux abstracts this diversity using one of the two memory models: +FLATMEM and SPARSEMEM. Each architecture defines what memory models it supports, what the default memory model is and whether it is possible to manually override that default. -.. note:: - At time of this writing, DISCONTIGMEM is considered deprecated, - although it is still in use by several architectures. - All the memory models track the status of physical page frames using struct page arranged in one or more arrays. @@ -63,43 +59,6 @@ straightforward: `PFN - ARCH_PFN_OFFSET` is an index to the The `ARCH_PFN_OFFSET` defines the first page frame number for systems with physical memory starting at address different from 0. -DISCONTIGMEM -============ - -The DISCONTIGMEM model treats the physical memory as a collection of -`nodes` similarly to how Linux NUMA support does. For each node Linux -constructs an independent memory management subsystem represented by -`struct pglist_data` (or `pg_data_t` for short). Among other -things, `pg_data_t` holds the `node_mem_map` array that maps -physical pages belonging to that node. The `node_start_pfn` field of -`pg_data_t` is the number of the first page frame belonging to that -node. - -The architecture setup code should call :c:func:`free_area_init_node` for -each node in the system to initialize the `pg_data_t` object and its -`node_mem_map`. - -Every `node_mem_map` behaves exactly as FLATMEM's `mem_map` - -every physical page frame in a node has a `struct page` entry in the -`node_mem_map` array. When DISCONTIGMEM is enabled, a portion of the -`flags` field of the `struct page` encodes the node number of the -node hosting that page. - -The conversion between a PFN and the `struct page` in the -DISCONTIGMEM model became slightly more complex as it has to determine -which node hosts the physical page and which `pg_data_t` object -holds the `struct page`. - -Architectures that support DISCONTIGMEM provide :c:func:`pfn_to_nid` -to convert PFN to the node number. The opposite conversion helper -:c:func:`page_to_nid` is generic as it uses the node number encoded in -page->flags. - -Once the node number is known, the PFN can be used to index -appropriate `node_mem_map` array to access the `struct page` and -the offset of the `struct page` from the `node_mem_map` plus -`node_start_pfn` is the PFN of that page. - SPARSEMEM ========= diff --git a/MAINTAINERS b/MAINTAINERS index bbd4c729dd7e..d810891fd644 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -973,7 +973,7 @@ F: drivers/net/ethernet/amd/xgbe/ AMD SENSOR FUSION HUB DRIVER M: Nehal Shah -M: Sandeep Singh +M: Basavaraj Natikar L: linux-input@vger.kernel.org S: Maintained F: Documentation/hid/amd-sfh* @@ -4447,6 +4447,18 @@ F: include/linux/compiler-clang.h F: scripts/clang-tools/ K: \b(?i:clang|llvm)\b +CLANG CONTROL FLOW INTEGRITY SUPPORT +M: Sami Tolvanen +M: Kees Cook +R: Nathan Chancellor +R: Nick Desaulniers +L: clang-built-linux@googlegroups.com +S: Supported +B: https://github.com/ClangBuiltLinux/linux/issues +T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/clang/features +F: include/linux/cfi.h +F: kernel/cfi.c + CLEANCACHE API M: Konrad Rzeszutek Wilk L: linux-kernel@vger.kernel.org @@ -5187,7 +5199,14 @@ DELL WMI NOTIFICATIONS DRIVER M: Matthew Garrett M: Pali Rohár S: Maintained -F: drivers/platform/x86/dell/dell-wmi.c +F: drivers/platform/x86/dell/dell-wmi-base.c + +DELL WMI HARDWARE PRIVACY SUPPORT +M: Perry Yuan +L: Dell.Client.Kernel@dell.com +L: platform-driver-x86@vger.kernel.org +S: Maintained +F: drivers/platform/x86/dell/dell-wmi-privacy.c DELTA ST MEDIA DRIVER M: Hugues Fruchet @@ -6460,10 +6479,11 @@ F: Documentation/filesystems/ecryptfs.rst F: fs/ecryptfs/ EDAC-AMD64 -M: Borislav Petkov +M: Yazen Ghannam L: linux-edac@vger.kernel.org -S: Maintained +S: Supported F: drivers/edac/amd64_edac* +F: drivers/edac/mce_amd* EDAC-ARMADA M: Jan Luebbe @@ -6827,6 +6847,8 @@ F: Documentation/devicetree/bindings/net/mdio* F: Documentation/devicetree/bindings/net/qca,ar803x.yaml F: Documentation/networking/phy.rst F: drivers/net/mdio/ +F: drivers/net/mdio/acpi_mdio.c +F: drivers/net/mdio/fwnode_mdio.c F: drivers/net/mdio/of_mdio.c F: drivers/net/pcs/ F: drivers/net/phy/ @@ -9150,6 +9172,7 @@ F: Documentation/networking/device_drivers/ethernet/intel/ F: drivers/net/ethernet/intel/ F: drivers/net/ethernet/intel/*/ F: include/linux/avf/virtchnl.h +F: include/linux/net/intel/iidc.h INTEL FRAMEBUFFER DRIVER (excluding 810 and 815) M: Maik Broemme @@ -9404,6 +9427,11 @@ S: Maintained F: arch/x86/include/asm/intel_scu_ipc.h F: drivers/platform/x86/intel_scu_* +INTEL SKYLAKE INT3472 ACPI DEVICE DRIVER +M: Daniel Scally +S: Maintained +F: drivers/platform/x86/intel/int3472/ + INTEL SPEED SELECT TECHNOLOGY M: Srinivas Pandruvada L: platform-driver-x86@vger.kernel.org @@ -9424,7 +9452,7 @@ F: include/linux/firmware/intel/stratix10-smc.h F: include/linux/firmware/intel/stratix10-svc-client.h INTEL TELEMETRY DRIVER -M: Rajneesh Bhardwaj +M: Rajneesh Bhardwaj M: "David E. Box" L: platform-driver-x86@vger.kernel.org S: Maintained @@ -9469,6 +9497,13 @@ L: Dell.Client.Kernel@dell.com S: Maintained F: drivers/platform/x86/intel-wmi-thunderbolt.c +INTEL WWAN IOSM DRIVER +M: M Chetan Kumar +M: Intel Corporation +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/wwan/iosm/ + INTEL(R) TRACE HUB M: Alexander Shishkin S: Supported @@ -10879,6 +10914,7 @@ S: Maintained F: drivers/mailbox/ F: include/linux/mailbox_client.h F: include/linux/mailbox_controller.h +F: include/dt-bindings/mailbox/ F: Documentation/devicetree/bindings/mailbox/ MAILBOX ARM MHUv2 @@ -12215,7 +12251,7 @@ M: Maximilian Luz L: platform-driver-x86@vger.kernel.org S: Maintained W: https://github.com/linux-surface/surface-aggregator-module -C: irc://chat.freenode.net/##linux-surface +C: irc://irc.libera.chat/linux-surface F: Documentation/driver-api/surface_aggregator/ F: drivers/platform/surface/aggregator/ F: drivers/platform/surface/surface_acpi_notify.c @@ -12411,6 +12447,12 @@ F: Documentation/userspace-api/media/drivers/meye* F: drivers/media/pci/meye/ F: include/uapi/linux/meye.h +MOTORCOMM PHY DRIVER +M: Peter Geis +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/phy/motorcomm.c + MOXA SMARTIO/INDUSTIO/INTELLIO SERIAL CARD S: Orphan F: Documentation/driver-api/serial/moxa-smartio.rst @@ -12682,6 +12724,7 @@ W: http://www.netfilter.org/ W: http://www.iptables.org/ W: http://www.nftables.org/ Q: http://patchwork.ozlabs.org/project/netfilter-devel/list/ +C: irc://irc.libera.chat/netfilter T: git git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next.git F: include/linux/netfilter* @@ -13225,6 +13268,7 @@ M: Vladimir Oltean L: linux-kernel@vger.kernel.org S: Maintained F: drivers/net/dsa/sja1105 +F: drivers/net/pcs/pcs-xpcs-nxp.c NXP TDA998X DRM DRIVER M: Russell King @@ -15612,6 +15656,13 @@ F: include/linux/rpmsg/ F: include/uapi/linux/rpmsg.h F: samples/rpmsg/ +REMOTE PROCESSOR MESSAGING (RPMSG) WWAN CONTROL DRIVER +M: Stephan Gerhold +L: netdev@vger.kernel.org +L: linux-remoteproc@vger.kernel.org +S: Maintained +F: drivers/net/wwan/rpmsg_wwan_ctrl.c + RENESAS CLOCK DRIVERS M: Geert Uytterhoeven L: linux-renesas-soc@vger.kernel.org @@ -15741,6 +15792,14 @@ F: arch/riscv/ N: riscv K: riscv +RISC-V/MICROCHIP POLARFIRE SOC SUPPORT +M: Lewis Hanly +L: linux-riscv@lists.infradead.org +S: Supported +F: drivers/mailbox/mailbox-mpfs.c +F: drivers/soc/microchip/ +F: include/soc/microchip/mpfs.h + RNBD BLOCK DRIVERS M: Md. Haris Iqbal M: Jack Wang @@ -17717,6 +17776,7 @@ M: Jose Abreu L: netdev@vger.kernel.org S: Supported F: drivers/net/pcs/pcs-xpcs.c +F: drivers/net/pcs/pcs-xpcs.h F: include/linux/pcs/pcs-xpcs.h SYNOPSYS DESIGNWARE I2C DRIVER @@ -18219,6 +18279,13 @@ W: http://thinkwiki.org/wiki/Ibm-acpi T: git git://repo.or.cz/linux-2.6/linux-acpi-2.6/ibm-acpi-2.6.git F: drivers/platform/x86/thinkpad_acpi.c +THINKPAD LMI DRIVER +M: Mark Pearson +L: platform-driver-x86@vger.kernel.org +S: Maintained +F: Documentation/ABI/testing/sysfs-class-firmware-attributes +F: drivers/platform/x86/think-lmi.? + THUNDERBOLT DMA TRAFFIC TEST DRIVER M: Isaac Hazan L: linux-usb@vger.kernel.org @@ -19642,6 +19709,7 @@ S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/pmladek/printk.git F: Documentation/core-api/printk-formats.rst F: lib/test_printf.c +F: lib/test_scanf.c F: lib/vsprintf.c VT1211 HARDWARE MONITOR DRIVER @@ -19825,6 +19893,16 @@ F: Documentation/core-api/workqueue.rst F: include/linux/workqueue.h F: kernel/workqueue.c +WWAN DRIVERS +M: Loic Poulain +M: Sergey Ryazanov +R: Johannes Berg +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/wwan/ +F: include/linux/wwan.h +F: include/uapi/linux/wwan.h + X-POWERS AXP288 PMIC DRIVERS M: Hans de Goede S: Maintained diff --git a/arch/Kconfig b/arch/Kconfig index c45b770d3579..129df498a8e1 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -285,6 +285,13 @@ config ARCH_THREAD_STACK_ALLOCATOR config ARCH_WANTS_DYNAMIC_TASK_STRUCT bool +config ARCH_WANTS_NO_INSTR + bool + help + An architecture should select this if the noinstr macro is being used on + functions to denote that the toolchain should avoid instrumenting such + functions and is required for correctness. + config ARCH_32BIT_OFF_T bool depends on !64BIT diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 5998106faa60..8954216b9956 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -549,29 +549,12 @@ config NR_CPUS MARVEL support can handle a maximum of 32 CPUs, all the others with working support have a maximum of 4 CPUs. -config ARCH_DISCONTIGMEM_ENABLE - bool "Discontiguous Memory Support" - depends on BROKEN - help - Say Y to support efficient handling of discontiguous physical memory, - for architectures which are either NUMA (Non-Uniform Memory Access) - or have huge holes in the physical address space for other reasons. - See for more. - config ARCH_SPARSEMEM_ENABLE bool "Sparse Memory Support" help Say Y to support efficient handling of discontiguous physical memory, for systems that have huge holes in the physical address space. -config NUMA - bool "NUMA Support (EXPERIMENTAL)" - depends on DISCONTIGMEM && BROKEN - help - Say Y to compile the kernel to support NUMA (Non-Uniform Memory - Access). This option is for configuring high-end multiprocessor - server machines. If in doubt, say N. - config ALPHA_WTINT bool "Use WTINT" if ALPHA_SRM || ALPHA_GENERIC default y if ALPHA_QEMU @@ -596,11 +579,6 @@ config ALPHA_WTINT If unsure, say N. -config NODES_SHIFT - int - default "7" - depends on NEED_MULTIPLE_NODES - # LARGE_VMALLOC is racy, if you *really* need it then fix it first config ALPHA_LARGE_VMALLOC bool diff --git a/arch/alpha/include/asm/machvec.h b/arch/alpha/include/asm/machvec.h index a4e96e2bec74..e49fabce7b33 100644 --- a/arch/alpha/include/asm/machvec.h +++ b/arch/alpha/include/asm/machvec.h @@ -99,12 +99,6 @@ struct alpha_machine_vector const char *vector_name; - /* NUMA information */ - int (*pa_to_nid)(unsigned long); - int (*cpuid_to_nid)(int); - unsigned long (*node_mem_start)(int); - unsigned long (*node_mem_size)(int); - /* System specific parameters. */ union { struct { diff --git a/arch/alpha/include/asm/mmzone.h b/arch/alpha/include/asm/mmzone.h deleted file mode 100644 index 86644604d977..000000000000 --- a/arch/alpha/include/asm/mmzone.h +++ /dev/null @@ -1,100 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Written by Kanoj Sarcar (kanoj@sgi.com) Aug 99 - * Adapted for the alpha wildfire architecture Jan 2001. - */ -#ifndef _ASM_MMZONE_H_ -#define _ASM_MMZONE_H_ - -#ifdef CONFIG_DISCONTIGMEM - -#include - -/* - * Following are macros that are specific to this numa platform. - */ - -extern pg_data_t node_data[]; - -#define alpha_pa_to_nid(pa) \ - (alpha_mv.pa_to_nid \ - ? alpha_mv.pa_to_nid(pa) \ - : (0)) -#define node_mem_start(nid) \ - (alpha_mv.node_mem_start \ - ? alpha_mv.node_mem_start(nid) \ - : (0UL)) -#define node_mem_size(nid) \ - (alpha_mv.node_mem_size \ - ? alpha_mv.node_mem_size(nid) \ - : ((nid) ? (0UL) : (~0UL))) - -#define pa_to_nid(pa) alpha_pa_to_nid(pa) -#define NODE_DATA(nid) (&node_data[(nid)]) - -#define node_localnr(pfn, nid) ((pfn) - NODE_DATA(nid)->node_start_pfn) - -#if 1 -#define PLAT_NODE_DATA_LOCALNR(p, n) \ - (((p) >> PAGE_SHIFT) - PLAT_NODE_DATA(n)->gendata.node_start_pfn) -#else -static inline unsigned long -PLAT_NODE_DATA_LOCALNR(unsigned long p, int n) -{ - unsigned long temp; - temp = p >> PAGE_SHIFT; - return temp - PLAT_NODE_DATA(n)->gendata.node_start_pfn; -} -#endif - -/* - * Following are macros that each numa implementation must define. - */ - -/* - * Given a kernel address, find the home node of the underlying memory. - */ -#define kvaddr_to_nid(kaddr) pa_to_nid(__pa(kaddr)) - -/* - * Given a kaddr, LOCAL_BASE_ADDR finds the owning node of the memory - * and returns the kaddr corresponding to first physical page in the - * node's mem_map. - */ -#define LOCAL_BASE_ADDR(kaddr) \ - ((unsigned long)__va(NODE_DATA(kvaddr_to_nid(kaddr))->node_start_pfn \ - << PAGE_SHIFT)) - -/* XXX: FIXME -- nyc */ -#define kern_addr_valid(kaddr) (0) - -#define mk_pte(page, pgprot) \ -({ \ - pte_t pte; \ - unsigned long pfn; \ - \ - pfn = page_to_pfn(page) << 32; \ - pte_val(pte) = pfn | pgprot_val(pgprot); \ - \ - pte; \ -}) - -#define pte_page(x) \ -({ \ - unsigned long kvirt; \ - struct page * __xx; \ - \ - kvirt = (unsigned long)__va(pte_val(x) >> (32-PAGE_SHIFT)); \ - __xx = virt_to_page(kvirt); \ - \ - __xx; \ -}) - -#define pfn_to_nid(pfn) pa_to_nid(((u64)(pfn) << PAGE_SHIFT)) -#define pfn_valid(pfn) \ - (((pfn) - node_start_pfn(pfn_to_nid(pfn))) < \ - node_spanned_pages(pfn_to_nid(pfn))) \ - -#endif /* CONFIG_DISCONTIGMEM */ - -#endif /* _ASM_MMZONE_H_ */ diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h index 8d856c62e22a..e1757b7cfe3d 100644 --- a/arch/alpha/include/asm/pgtable.h +++ b/arch/alpha/include/asm/pgtable.h @@ -206,7 +206,6 @@ extern unsigned long __zero_page(void); #define page_to_pa(page) (page_to_pfn(page) << PAGE_SHIFT) #define pte_pfn(pte) (pte_val(pte) >> 32) -#ifndef CONFIG_DISCONTIGMEM #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define mk_pte(page, pgprot) \ ({ \ @@ -215,7 +214,6 @@ extern unsigned long __zero_page(void); pte_val(pte) = (page_to_pfn(page) << 32) | pgprot_val(pgprot); \ pte; \ }) -#endif extern inline pte_t pfn_pte(unsigned long physpfn, pgprot_t pgprot) { pte_t pte; pte_val(pte) = (PHYS_TWIDDLE(physpfn) << 32) | pgprot_val(pgprot); return pte; } @@ -330,9 +328,7 @@ extern inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#ifndef CONFIG_DISCONTIGMEM #define kern_addr_valid(addr) (1) -#endif #define pte_ERROR(e) \ printk("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e)) diff --git a/arch/alpha/include/asm/topology.h b/arch/alpha/include/asm/topology.h index 5a77a40567fa..7d393036aa8f 100644 --- a/arch/alpha/include/asm/topology.h +++ b/arch/alpha/include/asm/topology.h @@ -7,45 +7,6 @@ #include #include -#ifdef CONFIG_NUMA -static inline int cpu_to_node(int cpu) -{ - int node; - - if (!alpha_mv.cpuid_to_nid) - return 0; - - node = alpha_mv.cpuid_to_nid(cpu); - -#ifdef DEBUG_NUMA - BUG_ON(node < 0); -#endif - - return node; -} - -extern struct cpumask node_to_cpumask_map[]; -/* FIXME: This is dumb, recalculating every time. But simple. */ -static const struct cpumask *cpumask_of_node(int node) -{ - int cpu; - - if (node == NUMA_NO_NODE) - return cpu_all_mask; - - cpumask_clear(&node_to_cpumask_map[node]); - - for_each_online_cpu(cpu) { - if (cpu_to_node(cpu) == node) - cpumask_set_cpu(cpu, node_to_cpumask_map[node]); - } - - return &node_to_cpumask_map[node]; -} - -#define cpumask_of_pcibus(bus) (cpu_online_mask) - -#endif /* !CONFIG_NUMA */ # include #endif /* _ASM_ALPHA_TOPOLOGY_H */ diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 57420356ce4c..6b3daba60987 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -127,6 +127,8 @@ #define SO_PREFER_BUSY_POLL 69 #define SO_BUSY_POLL_BUDGET 70 +#define SO_NETNS_COOKIE 71 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index 4485b77f8658..1efca79ac83c 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -287,8 +287,7 @@ io7_init_hose(struct io7 *io7, int port) /* * Set up window 0 for scatter-gather 8MB at 8MB. */ - hose->sg_isa = iommu_arena_new_node(marvel_cpuid_to_nid(io7->pe), - hose, 0x00800000, 0x00800000, 0); + hose->sg_isa = iommu_arena_new_node(0, hose, 0x00800000, 0x00800000, 0); hose->sg_isa->align_entry = 8; /* cache line boundary */ csrs->POx_WBASE[0].csr = hose->sg_isa->dma_base | wbase_m_ena | wbase_m_sg; @@ -305,8 +304,7 @@ io7_init_hose(struct io7 *io7, int port) /* * Set up window 2 for scatter-gather (up-to) 1GB at 3GB. */ - hose->sg_pci = iommu_arena_new_node(marvel_cpuid_to_nid(io7->pe), - hose, 0xc0000000, 0x40000000, 0); + hose->sg_pci = iommu_arena_new_node(0, hose, 0xc0000000, 0x40000000, 0); hose->sg_pci->align_entry = 8; /* cache line boundary */ csrs->POx_WBASE[2].csr = hose->sg_pci->dma_base | wbase_m_ena | wbase_m_sg; @@ -843,53 +841,8 @@ EXPORT_SYMBOL(marvel_ioportmap); EXPORT_SYMBOL(marvel_ioread8); EXPORT_SYMBOL(marvel_iowrite8); #endif - + /* - * NUMA Support - */ -/********** - * FIXME - for now each cpu is a node by itself - * -- no real support for striped mode - ********** - */ -int -marvel_pa_to_nid(unsigned long pa) -{ - int cpuid; - - if ((pa >> 43) & 1) /* I/O */ - cpuid = (~(pa >> 35) & 0xff); - else /* mem */ - cpuid = ((pa >> 34) & 0x3) | ((pa >> (37 - 2)) & (0x1f << 2)); - - return marvel_cpuid_to_nid(cpuid); -} - -int -marvel_cpuid_to_nid(int cpuid) -{ - return cpuid; -} - -unsigned long -marvel_node_mem_start(int nid) -{ - unsigned long pa; - - pa = (nid & 0x3) | ((nid & (0x1f << 2)) << 1); - pa <<= 34; - - return pa; -} - -unsigned long -marvel_node_mem_size(int nid) -{ - return 16UL * 1024 * 1024 * 1024; /* 16GB */ -} - - -/* * AGP GART Support. */ #include diff --git a/arch/alpha/kernel/core_wildfire.c b/arch/alpha/kernel/core_wildfire.c index e8d3b033018d..3a804b67f9da 100644 --- a/arch/alpha/kernel/core_wildfire.c +++ b/arch/alpha/kernel/core_wildfire.c @@ -434,39 +434,12 @@ wildfire_write_config(struct pci_bus *bus, unsigned int devfn, int where, return PCIBIOS_SUCCESSFUL; } -struct pci_ops wildfire_pci_ops = +struct pci_ops wildfire_pci_ops = { .read = wildfire_read_config, .write = wildfire_write_config, }; - -/* - * NUMA Support - */ -int wildfire_pa_to_nid(unsigned long pa) -{ - return pa >> 36; -} - -int wildfire_cpuid_to_nid(int cpuid) -{ - /* assume 4 CPUs per node */ - return cpuid >> 2; -} - -unsigned long wildfire_node_mem_start(int nid) -{ - /* 64GB per node */ - return (unsigned long)nid * (64UL * 1024 * 1024 * 1024); -} - -unsigned long wildfire_node_mem_size(int nid) -{ - /* 64GB per node */ - return 64UL * 1024 * 1024 * 1024; -} - #if DEBUG_DUMP_REGS static void __init diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index d84b19aa8e9d..35d7b3096d6e 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -71,33 +71,6 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base, if (align < mem_size) align = mem_size; - -#ifdef CONFIG_DISCONTIGMEM - - arena = memblock_alloc_node(sizeof(*arena), align, nid); - if (!NODE_DATA(nid) || !arena) { - printk("%s: couldn't allocate arena from node %d\n" - " falling back to system-wide allocation\n", - __func__, nid); - arena = memblock_alloc(sizeof(*arena), SMP_CACHE_BYTES); - if (!arena) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(*arena)); - } - - arena->ptes = memblock_alloc_node(sizeof(*arena), align, nid); - if (!NODE_DATA(nid) || !arena->ptes) { - printk("%s: couldn't allocate arena ptes from node %d\n" - " falling back to system-wide allocation\n", - __func__, nid); - arena->ptes = memblock_alloc(mem_size, align); - if (!arena->ptes) - panic("%s: Failed to allocate %lu bytes align=0x%lx\n", - __func__, mem_size, align); - } - -#else /* CONFIG_DISCONTIGMEM */ - arena = memblock_alloc(sizeof(*arena), SMP_CACHE_BYTES); if (!arena) panic("%s: Failed to allocate %zu bytes\n", __func__, @@ -107,8 +80,6 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base, panic("%s: Failed to allocate %lu bytes align=0x%lx\n", __func__, mem_size, align); -#endif /* CONFIG_DISCONTIGMEM */ - spin_lock_init(&arena->lock); arena->hose = hose; arena->dma_base = base; diff --git a/arch/alpha/kernel/proto.h b/arch/alpha/kernel/proto.h index 701a05090141..5816a31c1b38 100644 --- a/arch/alpha/kernel/proto.h +++ b/arch/alpha/kernel/proto.h @@ -49,10 +49,6 @@ extern void marvel_init_arch(void); extern void marvel_kill_arch(int); extern void marvel_machine_check(unsigned long, unsigned long); extern void marvel_pci_tbi(struct pci_controller *, dma_addr_t, dma_addr_t); -extern int marvel_pa_to_nid(unsigned long); -extern int marvel_cpuid_to_nid(int); -extern unsigned long marvel_node_mem_start(int); -extern unsigned long marvel_node_mem_size(int); extern struct _alpha_agp_info *marvel_agp_info(void); struct io7 *marvel_find_io7(int pe); struct io7 *marvel_next_io7(struct io7 *prev); @@ -101,10 +97,6 @@ extern void wildfire_init_arch(void); extern void wildfire_kill_arch(int); extern void wildfire_machine_check(unsigned long vector, unsigned long la_ptr); extern void wildfire_pci_tbi(struct pci_controller *, dma_addr_t, dma_addr_t); -extern int wildfire_pa_to_nid(unsigned long); -extern int wildfire_cpuid_to_nid(int); -extern unsigned long wildfire_node_mem_start(int); -extern unsigned long wildfire_node_mem_size(int); /* console.c */ #ifdef CONFIG_VGA_HOSE diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 03dda3beb3bd..5f6858e9dc28 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -79,11 +79,6 @@ int alpha_l3_cacheshape; unsigned long alpha_verbose_mcheck = CONFIG_VERBOSE_MCHECK_ON; #endif -#ifdef CONFIG_NUMA -struct cpumask node_to_cpumask_map[MAX_NUMNODES] __read_mostly; -EXPORT_SYMBOL(node_to_cpumask_map); -#endif - /* Which processor we booted from. */ int boot_cpuid; @@ -305,7 +300,6 @@ move_initrd(unsigned long mem_limit) } #endif -#ifndef CONFIG_DISCONTIGMEM static void __init setup_memory(void *kernel_end) { @@ -389,9 +383,6 @@ setup_memory(void *kernel_end) } #endif /* CONFIG_BLK_DEV_INITRD */ } -#else -extern void setup_memory(void *); -#endif /* !CONFIG_DISCONTIGMEM */ int __init page_is_ram(unsigned long pfn) @@ -618,13 +609,6 @@ setup_arch(char **cmdline_p) "VERBOSE_MCHECK " #endif -#ifdef CONFIG_DISCONTIGMEM - "DISCONTIGMEM " -#ifdef CONFIG_NUMA - "NUMA " -#endif -#endif - #ifdef CONFIG_DEBUG_SPINLOCK "DEBUG_SPINLOCK " #endif diff --git a/arch/alpha/kernel/sys_marvel.c b/arch/alpha/kernel/sys_marvel.c index 83d6c53d6d4d..1f99b03effc2 100644 --- a/arch/alpha/kernel/sys_marvel.c +++ b/arch/alpha/kernel/sys_marvel.c @@ -461,10 +461,5 @@ struct alpha_machine_vector marvel_ev7_mv __initmv = { .kill_arch = marvel_kill_arch, .pci_map_irq = marvel_map_irq, .pci_swizzle = common_swizzle, - - .pa_to_nid = marvel_pa_to_nid, - .cpuid_to_nid = marvel_cpuid_to_nid, - .node_mem_start = marvel_node_mem_start, - .node_mem_size = marvel_node_mem_size, }; ALIAS_MV(marvel_ev7) diff --git a/arch/alpha/kernel/sys_wildfire.c b/arch/alpha/kernel/sys_wildfire.c index 2c54d707142a..3cee05443f07 100644 --- a/arch/alpha/kernel/sys_wildfire.c +++ b/arch/alpha/kernel/sys_wildfire.c @@ -337,10 +337,5 @@ struct alpha_machine_vector wildfire_mv __initmv = { .kill_arch = wildfire_kill_arch, .pci_map_irq = wildfire_map_irq, .pci_swizzle = common_swizzle, - - .pa_to_nid = wildfire_pa_to_nid, - .cpuid_to_nid = wildfire_cpuid_to_nid, - .node_mem_start = wildfire_node_mem_start, - .node_mem_size = wildfire_node_mem_size, }; ALIAS_MV(wildfire) diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index 3000a2e8ee21..a17687ed4b51 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -482,7 +482,7 @@ 550 common process_madvise sys_process_madvise 551 common epoll_pwait2 sys_epoll_pwait2 552 common mount_setattr sys_mount_setattr -# 553 reserved for quotactl_path +553 common quotactl_fd sys_quotactl_fd 554 common landlock_create_ruleset sys_landlock_create_ruleset 555 common landlock_add_rule sys_landlock_add_rule 556 common landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/alpha/mm/Makefile b/arch/alpha/mm/Makefile index 08ac6612edad..bd770302eb82 100644 --- a/arch/alpha/mm/Makefile +++ b/arch/alpha/mm/Makefile @@ -6,5 +6,3 @@ ccflags-y := -Werror obj-y := init.o fault.o - -obj-$(CONFIG_DISCONTIGMEM) += numa.o diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index a97650a618f1..f6114d03357c 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -235,8 +235,6 @@ callback_init(void * kernel_end) return kernel_end; } - -#ifndef CONFIG_DISCONTIGMEM /* * paging_init() sets up the memory map. */ @@ -257,7 +255,6 @@ void __init paging_init(void) /* Initialize the kernel's ZERO_PGE. */ memset((void *)ZERO_PGE, 0, PAGE_SIZE); } -#endif /* CONFIG_DISCONTIGMEM */ #if defined(CONFIG_ALPHA_GENERIC) || defined(CONFIG_ALPHA_SRM) void diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c deleted file mode 100644 index 0636e254a22f..000000000000 --- a/arch/alpha/mm/numa.c +++ /dev/null @@ -1,223 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * linux/arch/alpha/mm/numa.c - * - * DISCONTIGMEM NUMA alpha support. - * - * Copyright (C) 2001 Andrea Arcangeli SuSE - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include - -pg_data_t node_data[MAX_NUMNODES]; -EXPORT_SYMBOL(node_data); - -#undef DEBUG_DISCONTIG -#ifdef DEBUG_DISCONTIG -#define DBGDCONT(args...) printk(args) -#else -#define DBGDCONT(args...) -#endif - -#define for_each_mem_cluster(memdesc, _cluster, i) \ - for ((_cluster) = (memdesc)->cluster, (i) = 0; \ - (i) < (memdesc)->numclusters; (i)++, (_cluster)++) - -static void __init show_mem_layout(void) -{ - struct memclust_struct * cluster; - struct memdesc_struct * memdesc; - int i; - - /* Find free clusters, and init and free the bootmem accordingly. */ - memdesc = (struct memdesc_struct *) - (hwrpb->mddt_offset + (unsigned long) hwrpb); - - printk("Raw memory layout:\n"); - for_each_mem_cluster(memdesc, cluster, i) { - printk(" memcluster %2d, usage %1lx, start %8lu, end %8lu\n", - i, cluster->usage, cluster->start_pfn, - cluster->start_pfn + cluster->numpages); - } -} - -static void __init -setup_memory_node(int nid, void *kernel_end) -{ - extern unsigned long mem_size_limit; - struct memclust_struct * cluster; - struct memdesc_struct * memdesc; - unsigned long start_kernel_pfn, end_kernel_pfn; - unsigned long start, end; - unsigned long node_pfn_start, node_pfn_end; - unsigned long node_min_pfn, node_max_pfn; - int i; - int show_init = 0; - - /* Find the bounds of current node */ - node_pfn_start = (node_mem_start(nid)) >> PAGE_SHIFT; - node_pfn_end = node_pfn_start + (node_mem_size(nid) >> PAGE_SHIFT); - - /* Find free clusters, and init and free the bootmem accordingly. */ - memdesc = (struct memdesc_struct *) - (hwrpb->mddt_offset + (unsigned long) hwrpb); - - /* find the bounds of this node (node_min_pfn/node_max_pfn) */ - node_min_pfn = ~0UL; - node_max_pfn = 0UL; - for_each_mem_cluster(memdesc, cluster, i) { - /* Bit 0 is console/PALcode reserved. Bit 1 is - non-volatile memory -- we might want to mark - this for later. */ - if (cluster->usage & 3) - continue; - - start = cluster->start_pfn; - end = start + cluster->numpages; - - if (start >= node_pfn_end || end <= node_pfn_start) - continue; - - if (!show_init) { - show_init = 1; - printk("Initializing bootmem allocator on Node ID %d\n", nid); - } - printk(" memcluster %2d, usage %1lx, start %8lu, end %8lu\n", - i, cluster->usage, cluster->start_pfn, - cluster->start_pfn + cluster->numpages); - - if (start < node_pfn_start) - start = node_pfn_start; - if (end > node_pfn_end) - end = node_pfn_end; - - if (start < node_min_pfn) - node_min_pfn = start; - if (end > node_max_pfn) - node_max_pfn = end; - } - - if (mem_size_limit && node_max_pfn > mem_size_limit) { - static int msg_shown = 0; - if (!msg_shown) { - msg_shown = 1; - printk("setup: forcing memory size to %ldK (from %ldK).\n", - mem_size_limit << (PAGE_SHIFT - 10), - node_max_pfn << (PAGE_SHIFT - 10)); - } - node_max_pfn = mem_size_limit; - } - - if (node_min_pfn >= node_max_pfn) - return; - - /* Update global {min,max}_low_pfn from node information. */ - if (node_min_pfn < min_low_pfn) - min_low_pfn = node_min_pfn; - if (node_max_pfn > max_low_pfn) - max_pfn = max_low_pfn = node_max_pfn; - -#if 0 /* we'll try this one again in a little while */ - /* Cute trick to make sure our local node data is on local memory */ - node_data[nid] = (pg_data_t *)(__va(node_min_pfn << PAGE_SHIFT)); -#endif - printk(" Detected node memory: start %8lu, end %8lu\n", - node_min_pfn, node_max_pfn); - - DBGDCONT(" DISCONTIG: node_data[%d] is at 0x%p\n", nid, NODE_DATA(nid)); - - /* Find the bounds of kernel memory. */ - start_kernel_pfn = PFN_DOWN(KERNEL_START_PHYS); - end_kernel_pfn = PFN_UP(virt_to_phys(kernel_end)); - - if (!nid && (node_max_pfn < end_kernel_pfn || node_min_pfn > start_kernel_pfn)) - panic("kernel loaded out of ram"); - - memblock_add_node(PFN_PHYS(node_min_pfn), - (node_max_pfn - node_min_pfn) << PAGE_SHIFT, nid); - - /* Zone start phys-addr must be 2^(MAX_ORDER-1) aligned. - Note that we round this down, not up - node memory - has much larger alignment than 8Mb, so it's safe. */ - node_min_pfn &= ~((1UL << (MAX_ORDER-1))-1); - - NODE_DATA(nid)->node_start_pfn = node_min_pfn; - NODE_DATA(nid)->node_present_pages = node_max_pfn - node_min_pfn; - - node_set_online(nid); -} - -void __init -setup_memory(void *kernel_end) -{ - unsigned long kernel_size; - int nid; - - show_mem_layout(); - - nodes_clear(node_online_map); - - min_low_pfn = ~0UL; - max_low_pfn = 0UL; - for (nid = 0; nid < MAX_NUMNODES; nid++) - setup_memory_node(nid, kernel_end); - - kernel_size = virt_to_phys(kernel_end) - KERNEL_START_PHYS; - memblock_reserve(KERNEL_START_PHYS, kernel_size); - -#ifdef CONFIG_BLK_DEV_INITRD - initrd_start = INITRD_START; - if (initrd_start) { - extern void *move_initrd(unsigned long); - - initrd_end = initrd_start+INITRD_SIZE; - printk("Initial ramdisk at: 0x%p (%lu bytes)\n", - (void *) initrd_start, INITRD_SIZE); - - if ((void *)initrd_end > phys_to_virt(PFN_PHYS(max_low_pfn))) { - if (!move_initrd(PFN_PHYS(max_low_pfn))) - printk("initrd extends beyond end of memory " - "(0x%08lx > 0x%p)\ndisabling initrd\n", - initrd_end, - phys_to_virt(PFN_PHYS(max_low_pfn))); - } else { - nid = kvaddr_to_nid(initrd_start); - memblock_reserve(virt_to_phys((void *)initrd_start), - INITRD_SIZE); - } - } -#endif /* CONFIG_BLK_DEV_INITRD */ -} - -void __init paging_init(void) -{ - unsigned long max_zone_pfn[MAX_NR_ZONES] = {0, }; - unsigned long dma_local_pfn; - - /* - * The old global MAX_DMA_ADDRESS per-arch API doesn't fit - * in the NUMA model, for now we convert it to a pfn and - * we interpret this pfn as a local per-node information. - * This issue isn't very important since none of these machines - * have legacy ISA slots anyways. - */ - dma_local_pfn = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; - - max_zone_pfn[ZONE_DMA] = dma_local_pfn; - max_zone_pfn[ZONE_NORMAL] = max_pfn; - - free_area_init(max_zone_pfn); - - /* Initialize the kernel's ZERO_PGE. */ - memset((void *)ZERO_PGE, 0, PAGE_SIZE); -} diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 2d98501c0897..d8f51eb8963b 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -62,10 +62,6 @@ config SCHED_OMIT_FRAME_POINTER config GENERIC_CSUM def_bool y -config ARCH_DISCONTIGMEM_ENABLE - def_bool n - depends on BROKEN - config ARCH_FLATMEM_ENABLE def_bool y @@ -344,15 +340,6 @@ config ARC_HUGEPAGE_16M endchoice -config NODES_SHIFT - int "Maximum NUMA Nodes (as a power of 2)" - default "0" if !DISCONTIGMEM - default "1" if DISCONTIGMEM - depends on NEED_MULTIPLE_NODES - help - Accessing memory beyond 1GB (with or w/o PAE) requires 2 memory - zones. - config ARC_COMPACT_IRQ_LEVELS depends on ISA_ARCOMPACT bool "Setup Timer IRQ as high Priority" diff --git a/arch/arc/include/asm/mmzone.h b/arch/arc/include/asm/mmzone.h deleted file mode 100644 index b86b9d1e54dc..000000000000 --- a/arch/arc/include/asm/mmzone.h +++ /dev/null @@ -1,40 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2016 Synopsys, Inc. (www.synopsys.com) - */ - -#ifndef _ASM_ARC_MMZONE_H -#define _ASM_ARC_MMZONE_H - -#ifdef CONFIG_DISCONTIGMEM - -extern struct pglist_data node_data[]; -#define NODE_DATA(nid) (&node_data[nid]) - -static inline int pfn_to_nid(unsigned long pfn) -{ - int is_end_low = 1; - - if (IS_ENABLED(CONFIG_ARC_HAS_PAE40)) - is_end_low = pfn <= virt_to_pfn(0xFFFFFFFFUL); - - /* - * node 0: lowmem: 0x8000_0000 to 0xFFFF_FFFF - * node 1: HIGHMEM w/o PAE40: 0x0 to 0x7FFF_FFFF - * HIGHMEM with PAE40: 0x1_0000_0000 to ... - */ - if (pfn >= ARCH_PFN_OFFSET && is_end_low) - return 0; - - return 1; -} - -static inline int pfn_valid(unsigned long pfn) -{ - int nid = pfn_to_nid(pfn); - - return (pfn <= node_end_pfn(nid)); -} -#endif /* CONFIG_DISCONTIGMEM */ - -#endif diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index a331bb5d8319..7654c2e42dc0 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -83,12 +83,12 @@ static void show_faulting_vma(unsigned long address) * non-inclusive vma */ mmap_read_lock(active_mm); - vma = find_vma(active_mm, address); + vma = vma_lookup(active_mm, address); - /* check against the find_vma( ) behaviour which returns the next VMA - * if the container VMA is not found + /* Lookup the vma at the address and report if the container VMA is not + * found */ - if (vma && (vma->vm_start <= address)) { + if (vma) { char buf[ARC_PATH_MAX]; char *nm = "?"; diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index e2ed355438c9..abfeef7bf6f8 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -32,11 +32,6 @@ unsigned long arch_pfn_offset; EXPORT_SYMBOL(arch_pfn_offset); #endif -#ifdef CONFIG_DISCONTIGMEM -struct pglist_data node_data[MAX_NUMNODES] __read_mostly; -EXPORT_SYMBOL(node_data); -#endif - long __init arc_get_mem_sz(void) { return low_mem_sz; @@ -139,20 +134,14 @@ void __init setup_arch_memory(void) #ifdef CONFIG_HIGHMEM /* - * Populate a new node with highmem - * * On ARC (w/o PAE) HIGHMEM addresses are actually smaller (0 based) - * than addresses in normal ala low memory (0x8000_0000 based). + * than addresses in normal aka low memory (0x8000_0000 based). * Even with PAE, the huge peripheral space hole would waste a lot of - * mem with single mem_map[]. This warrants a mem_map per region design. - * Thus HIGHMEM on ARC is imlemented with DISCONTIGMEM. - * - * DISCONTIGMEM in turns requires multiple nodes. node 0 above is - * populated with normal memory zone while node 1 only has highmem + * mem with single contiguous mem_map[]. + * Thus when HIGHMEM on ARC is enabled the memory map corresponding + * to the hole is freed and ARC specific version of pfn_valid() + * handles the hole in the memory map. */ -#ifdef CONFIG_DISCONTIGMEM - node_set_online(1); -#endif min_high_pfn = PFN_DOWN(high_mem_start); max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz); diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h index 24cbfc112dfa..0ccc985b90af 100644 --- a/arch/arm/include/asm/tlbflush.h +++ b/arch/arm/include/asm/tlbflush.h @@ -253,7 +253,7 @@ extern struct cpu_tlb_fns cpu_tlb; * space. * - mm - mm_struct describing address space * - * flush_tlb_range(mm,start,end) + * flush_tlb_range(vma,start,end) * * Invalidate a range of TLB entries in the specified * address space. @@ -261,18 +261,11 @@ extern struct cpu_tlb_fns cpu_tlb; * - start - start address (may not be aligned) * - end - end address (exclusive, may not be aligned) * - * flush_tlb_page(vaddr,vma) + * flush_tlb_page(vma, uaddr) * * Invalidate the specified page in the specified address range. + * - vma - vm_area_struct describing address range * - vaddr - virtual address (may not be aligned) - * - vma - vma_struct describing address range - * - * flush_kern_tlb_page(kaddr) - * - * Invalidate the TLB entry for the specified page. The address - * will be in the kernels virtual memory space. Current uses - * only require the D-TLB to be invalidated. - * - kaddr - Kernel virtual memory address */ /* diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 698b6f636156..20ab1e607522 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -63,7 +63,27 @@ int arch_show_interrupts(struct seq_file *p, int prec) */ void handle_IRQ(unsigned int irq, struct pt_regs *regs) { - __handle_domain_irq(NULL, irq, false, regs); + struct pt_regs *old_regs = set_irq_regs(regs); + struct irq_desc *desc; + + irq_enter(); + + /* + * Some hardware gives randomly wrong interrupts. Rather + * than crashing, do something sensible. + */ + if (unlikely(!irq || irq >= nr_irqs)) + desc = NULL; + else + desc = irq_to_desc(irq); + + if (likely(desc)) + handle_irq_desc(desc); + else + ack_bad_irq(irq); + + irq_exit(); + set_irq_regs(old_regs); } /* diff --git a/arch/arm/mach-zynq/Kconfig b/arch/arm/mach-zynq/Kconfig index 43fb941dcd07..a56748d671c4 100644 --- a/arch/arm/mach-zynq/Kconfig +++ b/arch/arm/mach-zynq/Kconfig @@ -6,7 +6,7 @@ config ARCH_ZYNQ select ARCH_SUPPORTS_BIG_ENDIAN select ARM_AMBA select ARM_GIC - select ARM_GLOBAL_TIMER if !CPU_FREQ + select ARM_GLOBAL_TIMER select CADENCE_TTC_TIMER select HAVE_ARM_SCU if SMP select HAVE_ARM_TWD if SMP diff --git a/arch/arm/mm/tlb-v6.S b/arch/arm/mm/tlb-v6.S index 5335b9687297..74f4b383afe3 100644 --- a/arch/arm/mm/tlb-v6.S +++ b/arch/arm/mm/tlb-v6.S @@ -24,7 +24,7 @@ * * - start - start address (may not be aligned) * - end - end address (exclusive, may not be aligned) - * - vma - vma_struct describing address range + * - vma - vm_area_struct describing address range * * It is assumed that: * - the "Invalidate single entry" instruction will invalidate diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S index 1bb28d7db567..87bf4ab17721 100644 --- a/arch/arm/mm/tlb-v7.S +++ b/arch/arm/mm/tlb-v7.S @@ -23,7 +23,7 @@ * * - start - start address (may not be aligned) * - end - end address (exclusive, may not be aligned) - * - vma - vma_struct describing address range + * - vma - vm_area_struct describing address range * * It is assumed that: * - the "Invalidate single entry" instruction will invalidate diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 28e03b5fec00..c5df1179fc5d 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -456,7 +456,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 common quotactl_fd sys_quotactl_fd 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index dabe9b81012f..be9083882f97 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -93,6 +93,7 @@ config ARM64 select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) select ARCH_WANT_LD_ORPHAN_WARN + select ARCH_WANTS_NO_INSTR select ARCH_HAS_UBSAN_SANITIZE_ALL select ARM_AMBA select ARM_ARCH_TIMER @@ -1035,7 +1036,7 @@ config NODES_SHIFT int "Maximum NUMA Nodes (as a power of 2)" range 1 10 default "4" - depends on NEED_MULTIPLE_NODES + depends on NUMA help Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accommodate various tables. diff --git a/arch/arm64/boot/dts/microchip/sparx5.dtsi b/arch/arm64/boot/dts/microchip/sparx5.dtsi index d64621d1213b..ad07fff40544 100644 --- a/arch/arm64/boot/dts/microchip/sparx5.dtsi +++ b/arch/arm64/boot/dts/microchip/sparx5.dtsi @@ -135,9 +135,12 @@ }; }; - reset@611010008 { - compatible = "microchip,sparx5-chip-reset"; + reset: reset-controller@611010008 { + compatible = "microchip,sparx5-switch-reset"; reg = <0x6 0x11010008 0x4>; + reg-names = "gcb"; + #reset-cells = <1>; + cpu-syscon = <&cpu_ctrl>; }; uart0: serial@600100000 { @@ -275,6 +278,21 @@ "GPIO_46", "GPIO_47"; function = "emmc"; }; + + miim1_pins: miim1-pins { + pins = "GPIO_56", "GPIO_57"; + function = "miim"; + }; + + miim2_pins: miim2-pins { + pins = "GPIO_58", "GPIO_59"; + function = "miim"; + }; + + miim3_pins: miim3-pins { + pins = "GPIO_52", "GPIO_53"; + function = "miim"; + }; }; sgpio0: gpio@61101036c { @@ -285,6 +303,8 @@ clocks = <&sys_clk>; pinctrl-0 = <&sgpio0_pins>; pinctrl-names = "default"; + resets = <&reset 0>; + reset-names = "switch"; reg = <0x6 0x1101036c 0x100>; sgpio_in0: gpio@0 { compatible = "microchip,sparx5-sgpio-bank"; @@ -292,6 +312,9 @@ gpio-controller; #gpio-cells = <3>; ngpios = <96>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <3>; }; sgpio_out0: gpio@1 { compatible = "microchip,sparx5-sgpio-bank"; @@ -310,6 +333,8 @@ clocks = <&sys_clk>; pinctrl-0 = <&sgpio1_pins>; pinctrl-names = "default"; + resets = <&reset 0>; + reset-names = "switch"; reg = <0x6 0x11010484 0x100>; sgpio_in1: gpio@0 { compatible = "microchip,sparx5-sgpio-bank"; @@ -317,6 +342,9 @@ gpio-controller; #gpio-cells = <3>; ngpios = <96>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <3>; }; sgpio_out1: gpio@1 { compatible = "microchip,sparx5-sgpio-bank"; @@ -335,6 +363,8 @@ clocks = <&sys_clk>; pinctrl-0 = <&sgpio2_pins>; pinctrl-names = "default"; + resets = <&reset 0>; + reset-names = "switch"; reg = <0x6 0x1101059c 0x100>; sgpio_in2: gpio@0 { reg = <0>; @@ -342,6 +372,9 @@ gpio-controller; #gpio-cells = <3>; ngpios = <96>; + interrupts = ; + interrupt-controller; + #interrupt-cells = <3>; }; sgpio_out2: gpio@1 { compatible = "microchip,sparx5-sgpio-bank"; @@ -386,5 +419,62 @@ #thermal-sensor-cells = <0>; clocks = <&ahb_clk>; }; + + mdio0: mdio@6110102b0 { + compatible = "mscc,ocelot-miim"; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x6 0x110102b0 0x24>; + }; + + mdio1: mdio@6110102d4 { + compatible = "mscc,ocelot-miim"; + status = "disabled"; + pinctrl-0 = <&miim1_pins>; + pinctrl-names = "default"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x6 0x110102d4 0x24>; + }; + + mdio2: mdio@6110102f8 { + compatible = "mscc,ocelot-miim"; + status = "disabled"; + pinctrl-0 = <&miim2_pins>; + pinctrl-names = "default"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x6 0x110102d4 0x24>; + }; + + mdio3: mdio@61101031c { + compatible = "mscc,ocelot-miim"; + status = "disabled"; + pinctrl-0 = <&miim3_pins>; + pinctrl-names = "default"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x6 0x1101031c 0x24>; + }; + + serdes: serdes@10808000 { + compatible = "microchip,sparx5-serdes"; + #phy-cells = <1>; + clocks = <&sys_clk>; + reg = <0x6 0x10808000 0x5d0000>; + }; + + switch: switch@0x600000000 { + compatible = "microchip,sparx5-switch"; + reg = <0x6 0 0x401000>, + <0x6 0x10004000 0x7fc000>, + <0x6 0x11010000 0xaf0000>; + reg-names = "cpu", "dev", "gcb"; + interrupt-names = "xtr"; + interrupts = ; + resets = <&reset 0>; + reset-names = "switch"; + }; }; }; diff --git a/arch/arm64/boot/dts/microchip/sparx5_pcb134_board.dtsi b/arch/arm64/boot/dts/microchip/sparx5_pcb134_board.dtsi index f0c915160990..33faf1f3264f 100644 --- a/arch/arm64/boot/dts/microchip/sparx5_pcb134_board.dtsi +++ b/arch/arm64/boot/dts/microchip/sparx5_pcb134_board.dtsi @@ -7,30 +7,6 @@ #include "sparx5_pcb_common.dtsi" /{ - aliases { - i2c0 = &i2c0; - i2c100 = &i2c100; - i2c101 = &i2c101; - i2c102 = &i2c102; - i2c103 = &i2c103; - i2c104 = &i2c104; - i2c105 = &i2c105; - i2c106 = &i2c106; - i2c107 = &i2c107; - i2c108 = &i2c108; - i2c109 = &i2c109; - i2c110 = &i2c110; - i2c111 = &i2c111; - i2c112 = &i2c112; - i2c113 = &i2c113; - i2c114 = &i2c114; - i2c115 = &i2c115; - i2c116 = &i2c116; - i2c117 = &i2c117; - i2c118 = &i2c118; - i2c119 = &i2c119; - }; - gpio-restart { compatible = "gpio-restart"; gpios = <&gpio 37 GPIO_ACTIVE_LOW>; @@ -298,17 +274,10 @@ &spi0 { status = "okay"; - spi@0 { - compatible = "spi-mux"; - mux-controls = <&mux>; - #address-cells = <1>; - #size-cells = <0>; - reg = <0>; /* CS0 */ - spi-flash@9 { - compatible = "jedec,spi-nor"; - spi-max-frequency = <8000000>; - reg = <0x9>; /* SPI */ - }; + spi-flash@0 { + compatible = "jedec,spi-nor"; + spi-max-frequency = <8000000>; + reg = <0>; }; }; @@ -328,6 +297,33 @@ }; }; +&sgpio0 { + status = "okay"; + microchip,sgpio-port-ranges = <8 15>; + gpio@0 { + ngpios = <64>; + }; + gpio@1 { + ngpios = <64>; + }; +}; + +&sgpio1 { + status = "okay"; + microchip,sgpio-port-ranges = <24 31>; + gpio@0 { + ngpios = <64>; + }; + gpio@1 { + ngpios = <64>; + }; +}; + +&sgpio2 { + status = "okay"; + microchip,sgpio-port-ranges = <0 0>, <11 31>; +}; + &gpio { i2cmux_pins_i: i2cmux-pins-i { pins = "GPIO_16", "GPIO_17", "GPIO_18", "GPIO_19", @@ -415,9 +411,9 @@ &i2c0_imux { pinctrl-names = - "i2c100", "i2c101", "i2c102", "i2c103", - "i2c104", "i2c105", "i2c106", "i2c107", - "i2c108", "i2c109", "i2c110", "i2c111", "idle"; + "i2c_sfp1", "i2c_sfp2", "i2c_sfp3", "i2c_sfp4", + "i2c_sfp5", "i2c_sfp6", "i2c_sfp7", "i2c_sfp8", + "i2c_sfp9", "i2c_sfp10", "i2c_sfp11", "i2c_sfp12", "idle"; pinctrl-0 = <&i2cmux_0>; pinctrl-1 = <&i2cmux_1>; pinctrl-2 = <&i2cmux_2>; @@ -431,62 +427,62 @@ pinctrl-10 = <&i2cmux_10>; pinctrl-11 = <&i2cmux_11>; pinctrl-12 = <&i2cmux_pins_i>; - i2c100: i2c_sfp1 { + i2c_sfp1: i2c_sfp1 { reg = <0x0>; #address-cells = <1>; #size-cells = <0>; }; - i2c101: i2c_sfp2 { + i2c_sfp2: i2c_sfp2 { reg = <0x1>; #address-cells = <1>; #size-cells = <0>; }; - i2c102: i2c_sfp3 { + i2c_sfp3: i2c_sfp3 { reg = <0x2>; #address-cells = <1>; #size-cells = <0>; }; - i2c103: i2c_sfp4 { + i2c_sfp4: i2c_sfp4 { reg = <0x3>; #address-cells = <1>; #size-cells = <0>; }; - i2c104: i2c_sfp5 { + i2c_sfp5: i2c_sfp5 { reg = <0x4>; #address-cells = <1>; #size-cells = <0>; }; - i2c105: i2c_sfp6 { + i2c_sfp6: i2c_sfp6 { reg = <0x5>; #address-cells = <1>; #size-cells = <0>; }; - i2c106: i2c_sfp7 { + i2c_sfp7: i2c_sfp7 { reg = <0x6>; #address-cells = <1>; #size-cells = <0>; }; - i2c107: i2c_sfp8 { + i2c_sfp8: i2c_sfp8 { reg = <0x7>; #address-cells = <1>; #size-cells = <0>; }; - i2c108: i2c_sfp9 { + i2c_sfp9: i2c_sfp9 { reg = <0x8>; #address-cells = <1>; #size-cells = <0>; }; - i2c109: i2c_sfp10 { + i2c_sfp10: i2c_sfp10 { reg = <0x9>; #address-cells = <1>; #size-cells = <0>; }; - i2c110: i2c_sfp11 { + i2c_sfp11: i2c_sfp11 { reg = <0xa>; #address-cells = <1>; #size-cells = <0>; }; - i2c111: i2c_sfp12 { + i2c_sfp12: i2c_sfp12 { reg = <0xb>; #address-cells = <1>; #size-cells = <0>; @@ -499,44 +495,413 @@ &gpio 61 GPIO_ACTIVE_HIGH &gpio 54 GPIO_ACTIVE_HIGH>; idle-state = <0x8>; - i2c112: i2c_sfp13 { + i2c_sfp13: i2c_sfp13 { reg = <0x0>; #address-cells = <1>; #size-cells = <0>; }; - i2c113: i2c_sfp14 { + i2c_sfp14: i2c_sfp14 { reg = <0x1>; #address-cells = <1>; #size-cells = <0>; }; - i2c114: i2c_sfp15 { + i2c_sfp15: i2c_sfp15 { reg = <0x2>; #address-cells = <1>; #size-cells = <0>; }; - i2c115: i2c_sfp16 { + i2c_sfp16: i2c_sfp16 { reg = <0x3>; #address-cells = <1>; #size-cells = <0>; }; - i2c116: i2c_sfp17 { + i2c_sfp17: i2c_sfp17 { reg = <0x4>; #address-cells = <1>; #size-cells = <0>; }; - i2c117: i2c_sfp18 { + i2c_sfp18: i2c_sfp18 { reg = <0x5>; #address-cells = <1>; #size-cells = <0>; }; - i2c118: i2c_sfp19 { + i2c_sfp19: i2c_sfp19 { reg = <0x6>; #address-cells = <1>; #size-cells = <0>; }; - i2c119: i2c_sfp20 { + i2c_sfp20: i2c_sfp20 { reg = <0x7>; #address-cells = <1>; #size-cells = <0>; }; }; + +&mdio3 { + status = "ok"; + phy64: ethernet-phy@64 { + reg = <28>; + }; +}; + +&axi { + sfp_eth12: sfp-eth12 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp1>; + tx-disable-gpios = <&sgpio_out2 11 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 11 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 11 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 12 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth13: sfp-eth13 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp2>; + tx-disable-gpios = <&sgpio_out2 12 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 12 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 12 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 13 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth14: sfp-eth14 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp3>; + tx-disable-gpios = <&sgpio_out2 13 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 13 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 13 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 14 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth15: sfp-eth15 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp4>; + tx-disable-gpios = <&sgpio_out2 14 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 14 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 14 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 15 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth48: sfp-eth48 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp5>; + tx-disable-gpios = <&sgpio_out2 15 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 15 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 15 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 16 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth49: sfp-eth49 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp6>; + tx-disable-gpios = <&sgpio_out2 16 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 16 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 16 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 17 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth50: sfp-eth50 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp7>; + tx-disable-gpios = <&sgpio_out2 17 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 17 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 17 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 18 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth51: sfp-eth51 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp8>; + tx-disable-gpios = <&sgpio_out2 18 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 18 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 18 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 19 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth52: sfp-eth52 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp9>; + tx-disable-gpios = <&sgpio_out2 19 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 19 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 19 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 20 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth53: sfp-eth53 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp10>; + tx-disable-gpios = <&sgpio_out2 20 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 20 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 20 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 21 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth54: sfp-eth54 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp11>; + tx-disable-gpios = <&sgpio_out2 21 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 21 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 21 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 22 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth55: sfp-eth55 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp12>; + tx-disable-gpios = <&sgpio_out2 22 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 22 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 22 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 23 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth56: sfp-eth56 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp13>; + tx-disable-gpios = <&sgpio_out2 23 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 23 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 23 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 24 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth57: sfp-eth57 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp14>; + tx-disable-gpios = <&sgpio_out2 24 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 24 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 24 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 25 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth58: sfp-eth58 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp15>; + tx-disable-gpios = <&sgpio_out2 25 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 25 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 25 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 26 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth59: sfp-eth59 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp16>; + tx-disable-gpios = <&sgpio_out2 26 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 26 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 26 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 27 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth60: sfp-eth60 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp17>; + tx-disable-gpios = <&sgpio_out2 27 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 27 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 27 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 28 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth61: sfp-eth61 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp18>; + tx-disable-gpios = <&sgpio_out2 28 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 28 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 28 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 29 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth62: sfp-eth62 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp19>; + tx-disable-gpios = <&sgpio_out2 29 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 29 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 29 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 30 0 GPIO_ACTIVE_HIGH>; + }; + sfp_eth63: sfp-eth63 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp20>; + tx-disable-gpios = <&sgpio_out2 30 1 GPIO_ACTIVE_LOW>; + los-gpios = <&sgpio_in2 30 1 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 30 2 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 31 0 GPIO_ACTIVE_HIGH>; + }; +}; + +&switch { + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + /* 10G SFPs */ + port12: port@12 { + reg = <12>; + microchip,bandwidth = <10000>; + phys = <&serdes 13>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth12>; + microchip,sd-sgpio = <301>; + managed = "in-band-status"; + }; + port13: port@13 { + reg = <13>; + /* Example: CU SFP, 1G speed */ + microchip,bandwidth = <10000>; + phys = <&serdes 14>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth13>; + microchip,sd-sgpio = <305>; + managed = "in-band-status"; + }; + port14: port@14 { + reg = <14>; + microchip,bandwidth = <10000>; + phys = <&serdes 15>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth14>; + microchip,sd-sgpio = <309>; + managed = "in-band-status"; + }; + port15: port@15 { + reg = <15>; + microchip,bandwidth = <10000>; + phys = <&serdes 16>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth15>; + microchip,sd-sgpio = <313>; + managed = "in-band-status"; + }; + port48: port@48 { + reg = <48>; + microchip,bandwidth = <10000>; + phys = <&serdes 17>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth48>; + microchip,sd-sgpio = <317>; + managed = "in-band-status"; + }; + port49: port@49 { + reg = <49>; + microchip,bandwidth = <10000>; + phys = <&serdes 18>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth49>; + microchip,sd-sgpio = <321>; + managed = "in-band-status"; + }; + port50: port@50 { + reg = <50>; + microchip,bandwidth = <10000>; + phys = <&serdes 19>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth50>; + microchip,sd-sgpio = <325>; + managed = "in-band-status"; + }; + port51: port@51 { + reg = <51>; + microchip,bandwidth = <10000>; + phys = <&serdes 20>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth51>; + microchip,sd-sgpio = <329>; + managed = "in-band-status"; + }; + port52: port@52 { + reg = <52>; + microchip,bandwidth = <10000>; + phys = <&serdes 21>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth52>; + microchip,sd-sgpio = <333>; + managed = "in-band-status"; + }; + port53: port@53 { + reg = <53>; + microchip,bandwidth = <10000>; + phys = <&serdes 22>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth53>; + microchip,sd-sgpio = <337>; + managed = "in-band-status"; + }; + port54: port@54 { + reg = <54>; + microchip,bandwidth = <10000>; + phys = <&serdes 23>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth54>; + microchip,sd-sgpio = <341>; + managed = "in-band-status"; + }; + port55: port@55 { + reg = <55>; + microchip,bandwidth = <10000>; + phys = <&serdes 24>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth55>; + microchip,sd-sgpio = <345>; + managed = "in-band-status"; + }; + /* 25G SFPs */ + port56: port@56 { + reg = <56>; + microchip,bandwidth = <10000>; + phys = <&serdes 25>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth56>; + microchip,sd-sgpio = <349>; + managed = "in-band-status"; + }; + port57: port@57 { + reg = <57>; + microchip,bandwidth = <10000>; + phys = <&serdes 26>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth57>; + microchip,sd-sgpio = <353>; + managed = "in-band-status"; + }; + port58: port@58 { + reg = <58>; + microchip,bandwidth = <10000>; + phys = <&serdes 27>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth58>; + microchip,sd-sgpio = <357>; + managed = "in-band-status"; + }; + port59: port@59 { + reg = <59>; + microchip,bandwidth = <10000>; + phys = <&serdes 28>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth59>; + microchip,sd-sgpio = <361>; + managed = "in-band-status"; + }; + port60: port@60 { + reg = <60>; + microchip,bandwidth = <10000>; + phys = <&serdes 29>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth60>; + microchip,sd-sgpio = <365>; + managed = "in-band-status"; + }; + port61: port@61 { + reg = <61>; + microchip,bandwidth = <10000>; + phys = <&serdes 30>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth61>; + microchip,sd-sgpio = <369>; + managed = "in-band-status"; + }; + port62: port@62 { + reg = <62>; + microchip,bandwidth = <10000>; + phys = <&serdes 31>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth62>; + microchip,sd-sgpio = <373>; + managed = "in-band-status"; + }; + port63: port@63 { + reg = <63>; + microchip,bandwidth = <10000>; + phys = <&serdes 32>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth63>; + microchip,sd-sgpio = <377>; + managed = "in-band-status"; + }; + /* Finally the Management interface */ + port64: port@64 { + reg = <64>; + microchip,bandwidth = <1000>; + phys = <&serdes 0>; + phy-handle = <&phy64>; + phy-mode = "sgmii"; + }; + }; +}; diff --git a/arch/arm64/boot/dts/microchip/sparx5_pcb135_board.dtsi b/arch/arm64/boot/dts/microchip/sparx5_pcb135_board.dtsi index e28c6dd16377..ef96e6d8c6b3 100644 --- a/arch/arm64/boot/dts/microchip/sparx5_pcb135_board.dtsi +++ b/arch/arm64/boot/dts/microchip/sparx5_pcb135_board.dtsi @@ -7,14 +7,6 @@ #include "sparx5_pcb_common.dtsi" /{ - aliases { - i2c0 = &i2c0; - i2c152 = &i2c152; - i2c153 = &i2c153; - i2c154 = &i2c154; - i2c155 = &i2c155; - }; - gpio-restart { compatible = "gpio-restart"; gpios = <&gpio 37 GPIO_ACTIVE_LOW>; @@ -97,17 +89,10 @@ &spi0 { status = "okay"; - spi@0 { - compatible = "spi-mux"; - mux-controls = <&mux>; - #address-cells = <1>; - #size-cells = <0>; - reg = <0>; /* CS0 */ - spi-flash@9 { - compatible = "jedec,spi-nor"; - spi-max-frequency = <8000000>; - reg = <0x9>; /* SPI */ - }; + spi-flash@0 { + compatible = "jedec,spi-nor"; + spi-max-frequency = <8000000>; + reg = <0>; }; }; @@ -138,6 +123,11 @@ }; }; +&sgpio2 { + status = "okay"; + microchip,sgpio-port-ranges = <0 0>, <16 18>, <28 31>; +}; + &axi { i2c0_imux: i2c0-imux@0 { compatible = "i2c-mux-pinctrl"; @@ -149,31 +139,614 @@ &i2c0_imux { pinctrl-names = - "i2c152", "i2c153", "i2c154", "i2c155", + "i2c_sfp1", "i2c_sfp2", "i2c_sfp3", "i2c_sfp4", "idle"; pinctrl-0 = <&i2cmux_s29>; pinctrl-1 = <&i2cmux_s30>; pinctrl-2 = <&i2cmux_s31>; pinctrl-3 = <&i2cmux_s32>; pinctrl-4 = <&i2cmux_pins_i>; - i2c152: i2c_sfp1 { + i2c_sfp1: i2c_sfp1 { reg = <0x0>; #address-cells = <1>; #size-cells = <0>; }; - i2c153: i2c_sfp2 { + i2c_sfp2: i2c_sfp2 { reg = <0x1>; #address-cells = <1>; #size-cells = <0>; }; - i2c154: i2c_sfp3 { + i2c_sfp3: i2c_sfp3 { reg = <0x2>; #address-cells = <1>; #size-cells = <0>; }; - i2c155: i2c_sfp4 { + i2c_sfp4: i2c_sfp4 { reg = <0x3>; #address-cells = <1>; #size-cells = <0>; }; }; + +&axi { + sfp_eth60: sfp-eth60 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp1>; + tx-disable-gpios = <&sgpio_out2 28 0 GPIO_ACTIVE_LOW>; + rate-select0-gpios = <&sgpio_out2 28 1 GPIO_ACTIVE_HIGH>; + los-gpios = <&sgpio_in2 28 0 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 28 1 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 28 2 GPIO_ACTIVE_HIGH>; + }; + sfp_eth61: sfp-eth61 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp2>; + tx-disable-gpios = <&sgpio_out2 29 0 GPIO_ACTIVE_LOW>; + rate-select0-gpios = <&sgpio_out2 29 1 GPIO_ACTIVE_HIGH>; + los-gpios = <&sgpio_in2 29 0 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 29 1 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 29 2 GPIO_ACTIVE_HIGH>; + }; + sfp_eth62: sfp-eth62 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp3>; + tx-disable-gpios = <&sgpio_out2 30 0 GPIO_ACTIVE_LOW>; + rate-select0-gpios = <&sgpio_out2 30 1 GPIO_ACTIVE_HIGH>; + los-gpios = <&sgpio_in2 30 0 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 30 1 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 30 2 GPIO_ACTIVE_HIGH>; + }; + sfp_eth63: sfp-eth63 { + compatible = "sff,sfp"; + i2c-bus = <&i2c_sfp4>; + tx-disable-gpios = <&sgpio_out2 31 0 GPIO_ACTIVE_LOW>; + rate-select0-gpios = <&sgpio_out2 31 1 GPIO_ACTIVE_HIGH>; + los-gpios = <&sgpio_in2 31 0 GPIO_ACTIVE_HIGH>; + mod-def0-gpios = <&sgpio_in2 31 1 GPIO_ACTIVE_LOW>; + tx-fault-gpios = <&sgpio_in2 31 2 GPIO_ACTIVE_HIGH>; + }; +}; + +&mdio0 { + status = "ok"; + phy0: ethernet-phy@0 { + reg = <0>; + }; + phy1: ethernet-phy@1 { + reg = <1>; + }; + phy2: ethernet-phy@2 { + reg = <2>; + }; + phy3: ethernet-phy@3 { + reg = <3>; + }; + phy4: ethernet-phy@4 { + reg = <4>; + }; + phy5: ethernet-phy@5 { + reg = <5>; + }; + phy6: ethernet-phy@6 { + reg = <6>; + }; + phy7: ethernet-phy@7 { + reg = <7>; + }; + phy8: ethernet-phy@8 { + reg = <8>; + }; + phy9: ethernet-phy@9 { + reg = <9>; + }; + phy10: ethernet-phy@10 { + reg = <10>; + }; + phy11: ethernet-phy@11 { + reg = <11>; + }; + phy12: ethernet-phy@12 { + reg = <12>; + }; + phy13: ethernet-phy@13 { + reg = <13>; + }; + phy14: ethernet-phy@14 { + reg = <14>; + }; + phy15: ethernet-phy@15 { + reg = <15>; + }; + phy16: ethernet-phy@16 { + reg = <16>; + }; + phy17: ethernet-phy@17 { + reg = <17>; + }; + phy18: ethernet-phy@18 { + reg = <18>; + }; + phy19: ethernet-phy@19 { + reg = <19>; + }; + phy20: ethernet-phy@20 { + reg = <20>; + }; + phy21: ethernet-phy@21 { + reg = <21>; + }; + phy22: ethernet-phy@22 { + reg = <22>; + }; + phy23: ethernet-phy@23 { + reg = <23>; + }; +}; + +&mdio1 { + status = "ok"; + phy24: ethernet-phy@24 { + reg = <0>; + }; + phy25: ethernet-phy@25 { + reg = <1>; + }; + phy26: ethernet-phy@26 { + reg = <2>; + }; + phy27: ethernet-phy@27 { + reg = <3>; + }; + phy28: ethernet-phy@28 { + reg = <4>; + }; + phy29: ethernet-phy@29 { + reg = <5>; + }; + phy30: ethernet-phy@30 { + reg = <6>; + }; + phy31: ethernet-phy@31 { + reg = <7>; + }; + phy32: ethernet-phy@32 { + reg = <8>; + }; + phy33: ethernet-phy@33 { + reg = <9>; + }; + phy34: ethernet-phy@34 { + reg = <10>; + }; + phy35: ethernet-phy@35 { + reg = <11>; + }; + phy36: ethernet-phy@36 { + reg = <12>; + }; + phy37: ethernet-phy@37 { + reg = <13>; + }; + phy38: ethernet-phy@38 { + reg = <14>; + }; + phy39: ethernet-phy@39 { + reg = <15>; + }; + phy40: ethernet-phy@40 { + reg = <16>; + }; + phy41: ethernet-phy@41 { + reg = <17>; + }; + phy42: ethernet-phy@42 { + reg = <18>; + }; + phy43: ethernet-phy@43 { + reg = <19>; + }; + phy44: ethernet-phy@44 { + reg = <20>; + }; + phy45: ethernet-phy@45 { + reg = <21>; + }; + phy46: ethernet-phy@46 { + reg = <22>; + }; + phy47: ethernet-phy@47 { + reg = <23>; + }; +}; + +&mdio3 { + status = "ok"; + phy64: ethernet-phy@64 { + reg = <28>; + }; +}; + +&switch { + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + port0: port@0 { + reg = <0>; + microchip,bandwidth = <1000>; + phys = <&serdes 13>; + phy-handle = <&phy0>; + phy-mode = "qsgmii"; + }; + port1: port@1 { + reg = <1>; + microchip,bandwidth = <1000>; + phys = <&serdes 13>; + phy-handle = <&phy1>; + phy-mode = "qsgmii"; + }; + port2: port@2 { + reg = <2>; + microchip,bandwidth = <1000>; + phys = <&serdes 13>; + phy-handle = <&phy2>; + phy-mode = "qsgmii"; + }; + port3: port@3 { + reg = <3>; + microchip,bandwidth = <1000>; + phys = <&serdes 13>; + phy-handle = <&phy3>; + phy-mode = "qsgmii"; + }; + port4: port@4 { + reg = <4>; + microchip,bandwidth = <1000>; + phys = <&serdes 14>; + phy-handle = <&phy4>; + phy-mode = "qsgmii"; + }; + port5: port@5 { + reg = <5>; + microchip,bandwidth = <1000>; + phys = <&serdes 14>; + phy-handle = <&phy5>; + phy-mode = "qsgmii"; + }; + port6: port@6 { + reg = <6>; + microchip,bandwidth = <1000>; + phys = <&serdes 14>; + phy-handle = <&phy6>; + phy-mode = "qsgmii"; + }; + port7: port@7 { + reg = <7>; + microchip,bandwidth = <1000>; + phys = <&serdes 14>; + phy-handle = <&phy7>; + phy-mode = "qsgmii"; + }; + port8: port@8 { + reg = <8>; + microchip,bandwidth = <1000>; + phys = <&serdes 15>; + phy-handle = <&phy8>; + phy-mode = "qsgmii"; + }; + port9: port@9 { + reg = <9>; + microchip,bandwidth = <1000>; + phys = <&serdes 15>; + phy-handle = <&phy9>; + phy-mode = "qsgmii"; + }; + port10: port@10 { + reg = <10>; + microchip,bandwidth = <1000>; + phys = <&serdes 15>; + phy-handle = <&phy10>; + phy-mode = "qsgmii"; + }; + port11: port@11 { + reg = <11>; + microchip,bandwidth = <1000>; + phys = <&serdes 15>; + phy-handle = <&phy11>; + phy-mode = "qsgmii"; + }; + port12: port@12 { + reg = <12>; + microchip,bandwidth = <1000>; + phys = <&serdes 16>; + phy-handle = <&phy12>; + phy-mode = "qsgmii"; + }; + port13: port@13 { + reg = <13>; + microchip,bandwidth = <1000>; + phys = <&serdes 16>; + phy-handle = <&phy13>; + phy-mode = "qsgmii"; + }; + port14: port@14 { + reg = <14>; + microchip,bandwidth = <1000>; + phys = <&serdes 16>; + phy-handle = <&phy14>; + phy-mode = "qsgmii"; + }; + port15: port@15 { + reg = <15>; + microchip,bandwidth = <1000>; + phys = <&serdes 16>; + phy-handle = <&phy15>; + phy-mode = "qsgmii"; + }; + port16: port@16 { + reg = <16>; + microchip,bandwidth = <1000>; + phys = <&serdes 17>; + phy-handle = <&phy16>; + phy-mode = "qsgmii"; + }; + port17: port@17 { + reg = <17>; + microchip,bandwidth = <1000>; + phys = <&serdes 17>; + phy-handle = <&phy17>; + phy-mode = "qsgmii"; + }; + port18: port@18 { + reg = <18>; + microchip,bandwidth = <1000>; + phys = <&serdes 17>; + phy-handle = <&phy18>; + phy-mode = "qsgmii"; + }; + port19: port@19 { + reg = <19>; + microchip,bandwidth = <1000>; + phys = <&serdes 17>; + phy-handle = <&phy19>; + phy-mode = "qsgmii"; + }; + port20: port@20 { + reg = <20>; + microchip,bandwidth = <1000>; + phys = <&serdes 18>; + phy-handle = <&phy20>; + phy-mode = "qsgmii"; + }; + port21: port@21 { + reg = <21>; + microchip,bandwidth = <1000>; + phys = <&serdes 18>; + phy-handle = <&phy21>; + phy-mode = "qsgmii"; + }; + port22: port@22 { + reg = <22>; + microchip,bandwidth = <1000>; + phys = <&serdes 18>; + phy-handle = <&phy22>; + phy-mode = "qsgmii"; + }; + port23: port@23 { + reg = <23>; + microchip,bandwidth = <1000>; + phys = <&serdes 18>; + phy-handle = <&phy23>; + phy-mode = "qsgmii"; + }; + port24: port@24 { + reg = <24>; + microchip,bandwidth = <1000>; + phys = <&serdes 19>; + phy-handle = <&phy24>; + phy-mode = "qsgmii"; + }; + port25: port@25 { + reg = <25>; + microchip,bandwidth = <1000>; + phys = <&serdes 19>; + phy-handle = <&phy25>; + phy-mode = "qsgmii"; + }; + port26: port@26 { + reg = <26>; + microchip,bandwidth = <1000>; + phys = <&serdes 19>; + phy-handle = <&phy26>; + phy-mode = "qsgmii"; + }; + port27: port@27 { + reg = <27>; + microchip,bandwidth = <1000>; + phys = <&serdes 19>; + phy-handle = <&phy27>; + phy-mode = "qsgmii"; + }; + port28: port@28 { + reg = <28>; + microchip,bandwidth = <1000>; + phys = <&serdes 20>; + phy-handle = <&phy28>; + phy-mode = "qsgmii"; + }; + port29: port@29 { + reg = <29>; + microchip,bandwidth = <1000>; + phys = <&serdes 20>; + phy-handle = <&phy29>; + phy-mode = "qsgmii"; + }; + port30: port@30 { + reg = <30>; + microchip,bandwidth = <1000>; + phys = <&serdes 20>; + phy-handle = <&phy30>; + phy-mode = "qsgmii"; + }; + port31: port@31 { + reg = <31>; + microchip,bandwidth = <1000>; + phys = <&serdes 20>; + phy-handle = <&phy31>; + phy-mode = "qsgmii"; + }; + port32: port@32 { + reg = <32>; + microchip,bandwidth = <1000>; + phys = <&serdes 21>; + phy-handle = <&phy32>; + phy-mode = "qsgmii"; + }; + port33: port@33 { + reg = <33>; + microchip,bandwidth = <1000>; + phys = <&serdes 21>; + phy-handle = <&phy33>; + phy-mode = "qsgmii"; + }; + port34: port@34 { + reg = <34>; + microchip,bandwidth = <1000>; + phys = <&serdes 21>; + phy-handle = <&phy34>; + phy-mode = "qsgmii"; + }; + port35: port@35 { + reg = <35>; + microchip,bandwidth = <1000>; + phys = <&serdes 21>; + phy-handle = <&phy35>; + phy-mode = "qsgmii"; + }; + port36: port@36 { + reg = <36>; + microchip,bandwidth = <1000>; + phys = <&serdes 22>; + phy-handle = <&phy36>; + phy-mode = "qsgmii"; + }; + port37: port@37 { + reg = <37>; + microchip,bandwidth = <1000>; + phys = <&serdes 22>; + phy-handle = <&phy37>; + phy-mode = "qsgmii"; + }; + port38: port@38 { + reg = <38>; + microchip,bandwidth = <1000>; + phys = <&serdes 22>; + phy-handle = <&phy38>; + phy-mode = "qsgmii"; + }; + port39: port@39 { + reg = <39>; + microchip,bandwidth = <1000>; + phys = <&serdes 22>; + phy-handle = <&phy39>; + phy-mode = "qsgmii"; + }; + port40: port@40 { + reg = <40>; + microchip,bandwidth = <1000>; + phys = <&serdes 23>; + phy-handle = <&phy40>; + phy-mode = "qsgmii"; + }; + port41: port@41 { + reg = <41>; + microchip,bandwidth = <1000>; + phys = <&serdes 23>; + phy-handle = <&phy41>; + phy-mode = "qsgmii"; + }; + port42: port@42 { + reg = <42>; + microchip,bandwidth = <1000>; + phys = <&serdes 23>; + phy-handle = <&phy42>; + phy-mode = "qsgmii"; + }; + port43: port@43 { + reg = <43>; + microchip,bandwidth = <1000>; + phys = <&serdes 23>; + phy-handle = <&phy43>; + phy-mode = "qsgmii"; + }; + port44: port@44 { + reg = <44>; + microchip,bandwidth = <1000>; + phys = <&serdes 24>; + phy-handle = <&phy44>; + phy-mode = "qsgmii"; + }; + port45: port@45 { + reg = <45>; + microchip,bandwidth = <1000>; + phys = <&serdes 24>; + phy-handle = <&phy45>; + phy-mode = "qsgmii"; + }; + port46: port@46 { + reg = <46>; + microchip,bandwidth = <1000>; + phys = <&serdes 24>; + phy-handle = <&phy46>; + phy-mode = "qsgmii"; + }; + port47: port@47 { + reg = <47>; + microchip,bandwidth = <1000>; + phys = <&serdes 24>; + phy-handle = <&phy47>; + phy-mode = "qsgmii"; + }; + /* Then the 25G interfaces */ + port60: port@60 { + reg = <60>; + microchip,bandwidth = <25000>; + phys = <&serdes 29>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth60>; + managed = "in-band-status"; + }; + port61: port@61 { + reg = <61>; + microchip,bandwidth = <25000>; + phys = <&serdes 30>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth61>; + managed = "in-band-status"; + }; + port62: port@62 { + reg = <62>; + microchip,bandwidth = <25000>; + phys = <&serdes 31>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth62>; + managed = "in-band-status"; + }; + port63: port@63 { + reg = <63>; + microchip,bandwidth = <25000>; + phys = <&serdes 32>; + phy-mode = "10gbase-r"; + sfp = <&sfp_eth63>; + managed = "in-band-status"; + }; + /* Finally the Management interface */ + port64: port@64 { + reg = <64>; + microchip,bandwidth = <1000>; + phys = <&serdes 0>; + phy-handle = <&phy64>; + phy-mode = "sgmii"; + }; + }; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3308.dtsi b/arch/arm64/boot/dts/rockchip/rk3308.dtsi index 0c5fa9801e6f..b815ce73e5c6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3308.dtsi @@ -637,6 +637,28 @@ status = "disabled"; }; + gmac: ethernet@ff4e0000 { + compatible = "rockchip,rk3308-gmac"; + reg = <0x0 0xff4e0000 0x0 0x10000>; + interrupts = ; + interrupt-names = "macirq"; + clocks = <&cru SCLK_MAC>, <&cru SCLK_MAC_RX_TX>, + <&cru SCLK_MAC_RX_TX>, <&cru SCLK_MAC_REF>, + <&cru SCLK_MAC>, <&cru ACLK_MAC>, + <&cru PCLK_MAC>, <&cru SCLK_MAC_RMII>; + clock-names = "stmmaceth", "mac_clk_rx", + "mac_clk_tx", "clk_mac_ref", + "clk_mac_refout", "aclk_mac", + "pclk_mac", "clk_mac_speed"; + phy-mode = "rmii"; + pinctrl-names = "default"; + pinctrl-0 = <&rmii_pins &mac_refclk_12ma>; + resets = <&cru SRST_MAC_A>; + reset-names = "stmmaceth"; + rockchip,grf = <&grf>; + status = "disabled"; + }; + cru: clock-controller@ff500000 { compatible = "rockchip,rk3308-cru"; reg = <0x0 0xff500000 0x0 0x1000>; diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h index 6fb2e6bcc392..dc3ea4080e2e 100644 --- a/arch/arm64/include/asm/compiler.h +++ b/arch/arm64/include/asm/compiler.h @@ -23,4 +23,20 @@ #define __builtin_return_address(val) \ (void *)(ptrauth_clear_pac((unsigned long)__builtin_return_address(val))) +#ifdef CONFIG_CFI_CLANG +/* + * With CONFIG_CFI_CLANG, the compiler replaces function address + * references with the address of the function's CFI jump table + * entry. The function_nocfi macro always returns the address of the + * actual function instead. + */ +#define function_nocfi(x) ({ \ + void *addr; \ + asm("adrp %0, " __stringify(x) "\n\t" \ + "add %0, %0, :lo12:" __stringify(x) \ + : "=r" (addr)); \ + addr; \ +}) +#endif + #endif /* __ASM_COMPILER_H */ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 7b360960cc35..1a35a4473598 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -321,22 +321,6 @@ static inline void *phys_to_virt(phys_addr_t x) #define virt_to_pfn(x) __phys_to_pfn(__virt_to_phys((unsigned long)(x))) #define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) -#ifdef CONFIG_CFI_CLANG -/* - * With CONFIG_CFI_CLANG, the compiler replaces function address - * references with the address of the function's CFI jump table - * entry. The function_nocfi macro always returns the address of the - * actual function instead. - */ -#define function_nocfi(x) ({ \ - void *addr; \ - asm("adrp %0, " __stringify(x) "\n\t" \ - "add %0, %0, :lo12:" __stringify(x) \ - : "=r" (addr)); \ - addr; \ -}) -#endif - /* * virt_to_page(x) convert a _valid_ virtual address to struct page * * virt_addr_valid(x) indicates whether a virtual address is valid diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 5dab69d2c22b..99ffcafc736c 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -893,7 +893,8 @@ __SYSCALL(__NR_process_madvise, sys_process_madvise) __SYSCALL(__NR_epoll_pwait2, compat_sys_epoll_pwait2) #define __NR_mount_setattr 442 __SYSCALL(__NR_mount_setattr, sys_mount_setattr) -/* 443 is reserved for quotactl_path */ +#define __NR_quotactl_fd 443 +__SYSCALL(__NR_quotactl_fd, sys_quotactl_fd) #define __NR_landlock_create_ruleset 444 __SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset) #define __NR_landlock_add_rule 445 diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 57292dc5ce35..f23dfa06433b 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -929,7 +929,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * get block mapping for device MMIO region. */ mmap_read_lock(current->mm); - vma = find_vma_intersection(current->mm, hva, hva + 1); + vma = vma_lookup(current->mm, hva); if (unlikely(!vma)) { kvm_err("Failed to find VMA for hva 0x%lx\n", hva); mmap_read_unlock(current->mm); diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index dd5000da18b8..dccf98a37283 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -179,9 +179,6 @@ static bool is_addsub_imm(u32 imm) return !(imm & ~0xfff) || !(imm & ~0xfff000); } -/* Stack must be multiples of 16B */ -#define STACK_ALIGN(sz) (((sz) + 15) & ~15) - /* Tail call offset to jump into */ #if IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) #define PROLOGUE_OFFSET 8 @@ -256,7 +253,8 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf) emit(A64_BTI_J, ctx); } - ctx->stack_size = STACK_ALIGN(prog->aux->stack_depth); + /* Stack must be multiples of 16B */ + ctx->stack_size = round_up(prog->aux->stack_depth, 16); /* Set up function call stack */ emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx); @@ -488,17 +486,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, break; case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU64 | BPF_DIV | BPF_X: + emit(A64_UDIV(is64, dst, dst, src), ctx); + break; case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU64 | BPF_MOD | BPF_X: - switch (BPF_OP(code)) { - case BPF_DIV: - emit(A64_UDIV(is64, dst, dst, src), ctx); - break; - case BPF_MOD: - emit(A64_UDIV(is64, tmp, dst, src), ctx); - emit(A64_MSUB(is64, dst, dst, tmp, src), ctx); - break; - } + emit(A64_UDIV(is64, tmp, dst, src), ctx); + emit(A64_MSUB(is64, dst, dst, tmp, src), ctx); break; case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU64 | BPF_LSH | BPF_X: diff --git a/arch/h8300/kernel/setup.c b/arch/h8300/kernel/setup.c index 0281f92eea3d..c3590b2e9592 100644 --- a/arch/h8300/kernel/setup.c +++ b/arch/h8300/kernel/setup.c @@ -69,8 +69,6 @@ void __init h8300_fdt_init(void *fdt, char *bootargs) static void __init bootmem_init(void) { - struct memblock_region *region; - memory_end = memory_start = 0; /* Find main memory where is the kernel */ diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 279252e3e0f7..da22a35e6f03 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -302,7 +302,7 @@ config NODES_SHIFT int "Max num nodes shift(3-10)" range 3 10 default "10" - depends on NEED_MULTIPLE_NODES + depends on NUMA help This option specifies the maximum number of nodes in your SSI system. MAX_NUMNODES will be 2^(This value). diff --git a/arch/ia64/include/asm/pal.h b/arch/ia64/include/asm/pal.h index b1d87955e8cc..5c51fceedaf9 100644 --- a/arch/ia64/include/asm/pal.h +++ b/arch/ia64/include/asm/pal.h @@ -1086,7 +1086,7 @@ static inline long ia64_pal_freq_base(unsigned long *platform_base_freq) /* * Get the ratios for processor frequency, bus frequency and interval timer to - * to base frequency of the platform + * the base frequency of the platform */ static inline s64 ia64_pal_freq_ratios (struct pal_freq_ratio *proc_ratio, struct pal_freq_ratio *bus_ratio, diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h index 5f620e66384e..864775970c50 100644 --- a/arch/ia64/include/asm/spinlock.h +++ b/arch/ia64/include/asm/spinlock.h @@ -26,7 +26,7 @@ * the queue, and the other indicating the current tail. The lock is acquired * by atomically noting the tail and incrementing it by one (thus adding * ourself to the queue and noting our position), then waiting until the head - * becomes equal to the the initial value of the tail. + * becomes equal to the initial value of the tail. * The pad bits in the middle are used to prevent the next_ticket number * overflowing into the now_serving number. * diff --git a/arch/ia64/include/asm/uv/uv_hub.h b/arch/ia64/include/asm/uv/uv_hub.h index 2a88c7204e52..809ddb6896db 100644 --- a/arch/ia64/include/asm/uv/uv_hub.h +++ b/arch/ia64/include/asm/uv/uv_hub.h @@ -257,7 +257,7 @@ static inline int uv_numa_blade_id(void) return 0; } -/* Convert a cpu number to the the UV blade number */ +/* Convert a cpu number to the UV blade number */ static inline int uv_cpu_to_blade_id(int cpu) { return 0; diff --git a/arch/ia64/kernel/efi_stub.S b/arch/ia64/kernel/efi_stub.S index 58233bb7976d..1fd61b78fb29 100644 --- a/arch/ia64/kernel/efi_stub.S +++ b/arch/ia64/kernel/efi_stub.S @@ -7,7 +7,7 @@ * * This stub allows us to make EFI calls in physical mode with interrupts * turned off. We need this because we can't call SetVirtualMap() until - * the kernel has booted far enough to allow allocation of struct vma_struct + * the kernel has booted far enough to allow allocation of struct vm_area_struct * entries (which we would need to map stuff with memory attributes other * than uncached or writeback...). Since the GetTime() service gets called * earlier than that, we need to be able to make physical mode EFI calls from diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index 36a69b4e6169..5bfc79be4cef 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -343,7 +343,7 @@ init_record_index_pools(void) /* - 2 - */ sect_min_size = sal_log_sect_min_sizes[0]; - for (i = 1; i < sizeof sal_log_sect_min_sizes/sizeof(size_t); i++) + for (i = 1; i < ARRAY_SIZE(sal_log_sect_min_sizes); i++) if (sect_min_size > sal_log_sect_min_sizes[i]) sect_min_size = sal_log_sect_min_sizes[i]; diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index bb11fe4c875a..6d07742c57b8 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -363,7 +363,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 common quotactl_fd sys_quotactl_fd 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index 09fc385c2acd..3639e0a7cb3b 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -3,9 +3,8 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * This file contains NUMA specific variables and functions which can - * be split away from DISCONTIGMEM and are used on NUMA machines with - * contiguous memory. + * This file contains NUMA specific variables and functions which are used on + * NUMA machines with contiguous memory. * 2002/08/07 Erich Focht * Populate cpu entries in sysfs for non-numa systems as well * Intel Corporation - Ashok Raj diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index 46b6e5f3a40f..d6579ec3ea32 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -3,9 +3,8 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * This file contains NUMA specific variables and functions which can - * be split away from DISCONTIGMEM and are used on NUMA machines with - * contiguous memory. + * This file contains NUMA specific variables and functions which are used on + * NUMA machines with contiguous memory. * * 2002/08/07 Erich Focht */ diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu index f4d23977d2a5..29e946394fdb 100644 --- a/arch/m68k/Kconfig.cpu +++ b/arch/m68k/Kconfig.cpu @@ -408,10 +408,6 @@ config SINGLE_MEMORY_CHUNK order" to save memory that could be wasted for unused memory map. Say N if not sure. -config ARCH_DISCONTIGMEM_ENABLE - depends on BROKEN - def_bool MMU && !SINGLE_MEMORY_CHUNK - config FORCE_MAX_ZONEORDER int "Maximum zone order" if ADVANCED depends on !SINGLE_MEMORY_CHUNK @@ -451,11 +447,6 @@ config M68K_L2_CACHE depends on MAC default y -config NODES_SHIFT - int - default "3" - depends on DISCONTIGMEM - config CPU_HAS_NO_BITFIELDS bool @@ -553,4 +544,3 @@ config CACHE_COPYBACK The ColdFire CPU cache is set into Copy-back mode. endchoice endif - diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c index ba808543161a..9a8394e96388 100644 --- a/arch/m68k/emu/nfblock.c +++ b/arch/m68k/emu/nfblock.c @@ -55,7 +55,6 @@ struct nfhd_device { int id; u32 blocks, bsize; int bshift; - struct request_queue *queue; struct gendisk *disk; }; @@ -119,32 +118,24 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize) dev->bsize = bsize; dev->bshift = ffs(bsize) - 10; - dev->queue = blk_alloc_queue(NUMA_NO_NODE); - if (dev->queue == NULL) - goto free_dev; - - blk_queue_logical_block_size(dev->queue, bsize); - - dev->disk = alloc_disk(16); + dev->disk = blk_alloc_disk(NUMA_NO_NODE); if (!dev->disk) - goto free_queue; + goto free_dev; dev->disk->major = major_num; dev->disk->first_minor = dev_id * 16; + dev->disk->minors = 16; dev->disk->fops = &nfhd_ops; dev->disk->private_data = dev; sprintf(dev->disk->disk_name, "nfhd%u", dev_id); set_capacity(dev->disk, (sector_t)blocks * (bsize / 512)); - dev->disk->queue = dev->queue; - + blk_queue_logical_block_size(dev->disk->queue, bsize); add_disk(dev->disk); list_add_tail(&dev->list, &nfhd_list); return 0; -free_queue: - blk_cleanup_queue(dev->queue); free_dev: kfree(dev); out: @@ -186,8 +177,7 @@ static void __exit nfhd_exit(void) list_for_each_entry_safe(dev, next, &nfhd_list, list) { list_del(&dev->list); del_gendisk(dev->disk); - put_disk(dev->disk); - blk_cleanup_queue(dev->queue); + blk_cleanup_disk(dev->disk); kfree(dev); } unregister_blkdev(major_num, "nfhd"); diff --git a/arch/m68k/include/asm/mmzone.h b/arch/m68k/include/asm/mmzone.h deleted file mode 100644 index 64573fe8e60d..000000000000 --- a/arch/m68k/include/asm/mmzone.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_M68K_MMZONE_H_ -#define _ASM_M68K_MMZONE_H_ - -extern pg_data_t pg_data_map[]; - -#define NODE_DATA(nid) (&pg_data_map[nid]) -#define NODE_MEM_MAP(nid) (NODE_DATA(nid)->node_mem_map) - -#endif /* _ASM_M68K_MMZONE_H_ */ diff --git a/arch/m68k/include/asm/page.h b/arch/m68k/include/asm/page.h index 97087dd3ca6d..2f1c54e4725d 100644 --- a/arch/m68k/include/asm/page.h +++ b/arch/m68k/include/asm/page.h @@ -62,7 +62,7 @@ extern unsigned long _ramend; #include #endif -#if !defined(CONFIG_MMU) || defined(CONFIG_DISCONTIGMEM) +#ifndef CONFIG_MMU #define __phys_to_pfn(paddr) ((unsigned long)((paddr) >> PAGE_SHIFT)) #define __pfn_to_phys(pfn) PFN_PHYS(pfn) #endif diff --git a/arch/m68k/include/asm/page_mm.h b/arch/m68k/include/asm/page_mm.h index 2411ea9ef578..a5b459bcb7d8 100644 --- a/arch/m68k/include/asm/page_mm.h +++ b/arch/m68k/include/asm/page_mm.h @@ -126,26 +126,6 @@ static inline void *__va(unsigned long x) extern int m68k_virt_to_node_shift; -#ifndef CONFIG_DISCONTIGMEM -#define __virt_to_node(addr) (&pg_data_map[0]) -#else -extern struct pglist_data *pg_data_table[]; - -static inline __attribute_const__ int __virt_to_node_shift(void) -{ - int shift; - - asm ( - "1: moveq #0,%0\n" - m68k_fixup(%c1, 1b) - : "=d" (shift) - : "i" (m68k_fixup_vnode_shift)); - return shift; -} - -#define __virt_to_node(addr) (pg_data_table[(unsigned long)(addr) >> __virt_to_node_shift()]) -#endif - #define virt_to_page(addr) ({ \ pfn_to_page(virt_to_pfn(addr)); \ }) @@ -153,23 +133,8 @@ static inline __attribute_const__ int __virt_to_node_shift(void) pfn_to_virt(page_to_pfn(page)); \ }) -#ifdef CONFIG_DISCONTIGMEM -#define pfn_to_page(pfn) ({ \ - unsigned long __pfn = (pfn); \ - struct pglist_data *pgdat; \ - pgdat = __virt_to_node((unsigned long)pfn_to_virt(__pfn)); \ - pgdat->node_mem_map + (__pfn - pgdat->node_start_pfn); \ -}) -#define page_to_pfn(_page) ({ \ - const struct page *__p = (_page); \ - struct pglist_data *pgdat; \ - pgdat = &pg_data_map[page_to_nid(__p)]; \ - ((__p) - pgdat->node_mem_map) + pgdat->node_start_pfn; \ -}) -#else #define ARCH_PFN_OFFSET (m68k_memory[0].addr >> PAGE_SHIFT) #include -#endif #define virt_addr_valid(kaddr) ((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory) #define pfn_valid(pfn) virt_addr_valid(pfn_to_virt(pfn)) diff --git a/arch/m68k/include/asm/tlbflush.h b/arch/m68k/include/asm/tlbflush.h index 5337bc2c262f..a6318ccd308f 100644 --- a/arch/m68k/include/asm/tlbflush.h +++ b/arch/m68k/include/asm/tlbflush.h @@ -263,7 +263,7 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr BUG(); } -static inline void flush_tlb_range(struct mm_struct *mm, +static inline void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { BUG(); diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c index f55bdcb8e4f1..bd0274c7592e 100644 --- a/arch/m68k/kernel/sys_m68k.c +++ b/arch/m68k/kernel/sys_m68k.c @@ -402,8 +402,8 @@ sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len) * to this process. */ mmap_read_lock(current->mm); - vma = find_vma(current->mm, addr); - if (!vma || addr < vma->vm_start || addr + len > vma->vm_end) + vma = vma_lookup(current->mm, addr); + if (!vma || addr + len > vma->vm_end) goto out_unlock; } diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 79c2d24c89dd..541bc1b3a8f9 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -442,7 +442,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 common quotactl_fd sys_quotactl_fd 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 1759ab875d47..5d749e188246 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -44,28 +44,8 @@ EXPORT_SYMBOL(empty_zero_page); int m68k_virt_to_node_shift; -#ifdef CONFIG_DISCONTIGMEM -pg_data_t pg_data_map[MAX_NUMNODES]; -EXPORT_SYMBOL(pg_data_map); - -pg_data_t *pg_data_table[65]; -EXPORT_SYMBOL(pg_data_table); -#endif - void __init m68k_setup_node(int node) { -#ifdef CONFIG_DISCONTIGMEM - struct m68k_mem_info *info = m68k_memory + node; - int i, end; - - i = (unsigned long)phys_to_virt(info->addr) >> __virt_to_node_shift(); - end = (unsigned long)phys_to_virt(info->addr + info->size - 1) >> __virt_to_node_shift(); - for (; i <= end; i++) { - if (pg_data_table[i]) - pr_warn("overlap at %u for chunk %u\n", i, node); - pg_data_table[i] = pg_data_map + node; - } -#endif node_set_online(node); } diff --git a/arch/microblaze/Makefile b/arch/microblaze/Makefile index b41f323e1fde..6d4af39e3890 100644 --- a/arch/microblaze/Makefile +++ b/arch/microblaze/Makefile @@ -3,7 +3,7 @@ KBUILD_DEFCONFIG := mmu_defconfig UTS_SYSNAME = -DUTS_SYSNAME=\"Linux\" -# What CPU vesion are we building for, and crack it open +# What CPU version are we building for, and crack it open # as major.minor.rev CPU_VER := $(shell echo $(CONFIG_XILINX_MICROBLAZE0_HW_VER)) CPU_MAJOR := $(shell echo $(CPU_VER) | cut -d '.' -f 1) diff --git a/arch/microblaze/include/asm/page.h b/arch/microblaze/include/asm/page.h index bf681f272f72..ce550978f4fc 100644 --- a/arch/microblaze/include/asm/page.h +++ b/arch/microblaze/include/asm/page.h @@ -35,9 +35,6 @@ #define ARCH_SLAB_MINALIGN L1_CACHE_BYTES -#define PAGE_UP(addr) (((addr)+((PAGE_SIZE)-1))&(~((PAGE_SIZE)-1))) -#define PAGE_DOWN(addr) ((addr)&(~((PAGE_SIZE)-1))) - /* * PAGE_OFFSET -- the first address of the first page of memory. With MMU * it is set to the kernel start address (aligned on a page boundary). diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index b11395a20c20..a176faca2927 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -448,7 +448,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 common quotactl_fd sys_quotactl_fd 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index ed51970c08e7..4704a16c2e44 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2867,7 +2867,7 @@ config RANDOMIZE_BASE_MAX_OFFSET config NODES_SHIFT int default "6" - depends on NEED_MULTIPLE_NODES + depends on NUMA config HW_PERF_EVENTS bool "Enable hardware performance counter support for perf events" diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi index 569e814def83..5747f171de29 100644 --- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi +++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi @@ -114,6 +114,52 @@ ranges = <0x01000000 0x0 0x00000000 0x0 0x18000000 0x0 0x00010000>, <0x02000000 0x0 0x40000000 0x0 0x40000000 0x0 0x40000000>; + gmac@3,0 { + compatible = "pci0014,7a03.0", + "pci0014,7a03", + "pciclass0c0320", + "pciclass0c03", + "loongson, pci-gmac"; + + reg = <0x1800 0x0 0x0 0x0 0x0>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>, + <13 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "macirq", "eth_lpi"; + interrupt-parent = <&liointc0>; + phy-mode = "rgmii"; + mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + phy0: ethernet-phy@0 { + reg = <0>; + }; + }; + }; + + gmac@3,1 { + compatible = "pci0014,7a03.0", + "pci0014,7a03", + "pciclass0c0320", + "pciclass0c03", + "loongson, pci-gmac"; + + reg = <0x1900 0x0 0x0 0x0 0x0>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>, + <15 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "macirq", "eth_lpi"; + interrupt-parent = <&liointc0>; + phy-mode = "rgmii"; + mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + phy1: ethernet-phy@1 { + reg = <0>; + }; + }; + }; + ehci@4,1 { compatible = "pci0014,7a14.0", "pci0014,7a14", diff --git a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi index f99a7a11fded..58b9bb47c58a 100644 --- a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi +++ b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi @@ -186,7 +186,8 @@ compatible = "pci0014,7a03.0", "pci0014,7a03", "pciclass020000", - "pciclass0200"; + "pciclass0200", + "loongson, pci-gmac"; reg = <0x1800 0x0 0x0 0x0 0x0>; interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, @@ -208,7 +209,8 @@ compatible = "pci0014,7a03.0", "pci0014,7a03", "pciclass020000", - "pciclass0200"; + "pciclass0200", + "loongson, pci-gmac"; reg = <0x1900 0x0 0x0 0x0 0x0>; interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index f021de661c3a..d1477ecb1af9 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -11,7 +11,6 @@ #include #include -#include #include diff --git a/arch/mips/include/asm/mmzone.h b/arch/mips/include/asm/mmzone.h index b826b8473e95..602a21aee9d4 100644 --- a/arch/mips/include/asm/mmzone.h +++ b/arch/mips/include/asm/mmzone.h @@ -8,7 +8,7 @@ #include -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA # include #endif @@ -20,10 +20,4 @@ #define nid_to_addrbase(nid) 0 #endif -#ifdef CONFIG_DISCONTIGMEM - -#define pfn_to_nid(pfn) pa_to_nid((pfn) << PAGE_SHIFT) - -#endif /* CONFIG_DISCONTIGMEM */ - #endif /* _ASM_MMZONE_H_ */ diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index 195ff4e9771f..96bc798c1ec1 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -239,7 +239,7 @@ static inline int pfn_valid(unsigned long pfn) /* pfn_valid is defined in linux/mmzone.h */ -#elif defined(CONFIG_NEED_MULTIPLE_NODES) +#elif defined(CONFIG_NUMA) #define pfn_valid(pfn) \ ({ \ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 2d949969313b..cdf404a831b2 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -138,6 +138,8 @@ #define SO_PREFER_BUSY_POLL 69 #define SO_BUSY_POLL_BUDGET 70 +#define SO_NETNS_COOKIE 71 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 9220909526f9..c2d2e19abea8 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -381,7 +381,7 @@ 440 n32 process_madvise sys_process_madvise 441 n32 epoll_pwait2 compat_sys_epoll_pwait2 442 n32 mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 n32 quotactl_fd sys_quotactl_fd 444 n32 landlock_create_ruleset sys_landlock_create_ruleset 445 n32 landlock_add_rule sys_landlock_add_rule 446 n32 landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 9cd1c34f31b5..ac653d08b1ea 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -357,7 +357,7 @@ 440 n64 process_madvise sys_process_madvise 441 n64 epoll_pwait2 sys_epoll_pwait2 442 n64 mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 n64 quotactl_fd sys_quotactl_fd 444 n64 landlock_create_ruleset sys_landlock_create_ruleset 445 n64 landlock_add_rule sys_landlock_add_rule 446 n64 landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index d560c467a8c6..253f2cd70b6b 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -430,7 +430,7 @@ 440 o32 process_madvise sys_process_madvise 441 o32 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 o32 mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 o32 quotactl_fd sys_quotactl_fd 444 o32 landlock_create_ruleset sys_landlock_create_ruleset 445 o32 landlock_add_rule sys_landlock_add_rule 446 o32 landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 0b4e06303c55..6f07362de5ce 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -784,7 +784,6 @@ void force_fcr31_sig(unsigned long fcr31, void __user *fault_addr, int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31) { int si_code; - struct vm_area_struct *vma; switch (sig) { case 0: @@ -800,8 +799,7 @@ int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcr31) case SIGSEGV: mmap_read_lock(current->mm); - vma = find_vma(current->mm, (unsigned long)fault_addr); - if (vma && (vma->vm_start <= (unsigned long)fault_addr)) + if (vma_lookup(current->mm, (unsigned long)fault_addr)) si_code = SEGV_ACCERR; else si_code = SEGV_MAPERR; diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c index aeb1b989cd4e..63dccb2ed08b 100644 --- a/arch/mips/lantiq/xway/dma.c +++ b/arch/mips/lantiq/xway/dma.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index c36358758969..19347dc6bbf8 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -394,7 +394,7 @@ void maar_init(void) } } -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA void __init paging_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; @@ -454,9 +454,6 @@ void __init mem_init(void) BUILD_BUG_ON(IS_ENABLED(CONFIG_32BIT) && (_PFN_SHIFT > PAGE_SHIFT)); #ifdef CONFIG_HIGHMEM -#ifdef CONFIG_DISCONTIGMEM -#error "CONFIG_HIGHMEM and CONFIG_DISCONTIGMEM dont work together yet" -#endif max_mapnr = highend_pfn ? highend_pfn : max_low_pfn; #else max_mapnr = max_low_pfn; @@ -476,7 +473,7 @@ void __init mem_init(void) 0x80000000 - 4, KCORE_TEXT); #endif } -#endif /* !CONFIG_NEED_MULTIPLE_NODES */ +#endif /* !CONFIG_NUMA */ void free_init_pages(const char *what, unsigned long begin, unsigned long end) { diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c index aebd4964ea34..c48e23cf5b5e 100644 --- a/arch/mips/pci/pci-rt3883.c +++ b/arch/mips/pci/pci-rt3883.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c index d2216942af18..ab9bedb82b28 100644 --- a/arch/mips/pci/pci-xtalk-bridge.c +++ b/arch/mips/pci/pci-xtalk-bridge.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c index 42df9fafa943..95c1bff1ab9f 100644 --- a/arch/mips/sgi-ip27/ip27-irq.c +++ b/arch/mips/sgi-ip27/ip27-irq.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include diff --git a/arch/mips/sgi-ip30/ip30-irq.c b/arch/mips/sgi-ip30/ip30-irq.c index e8374e4c705b..ba87704073c8 100644 --- a/arch/mips/sgi-ip30/ip30-irq.c +++ b/arch/mips/sgi-ip30/ip30-irq.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/nds32/include/asm/memory.h b/arch/nds32/include/asm/memory.h index 940d32842793..62faafbc28e4 100644 --- a/arch/nds32/include/asm/memory.h +++ b/arch/nds32/include/asm/memory.h @@ -76,18 +76,12 @@ * virt_to_page(k) convert a _valid_ virtual address to struct page * * virt_addr_valid(k) indicates whether a virtual address is valid */ -#ifndef CONFIG_DISCONTIGMEM - #define ARCH_PFN_OFFSET PHYS_PFN_OFFSET #define pfn_valid(pfn) ((pfn) >= PHYS_PFN_OFFSET && (pfn) < (PHYS_PFN_OFFSET + max_mapnr)) #define virt_to_page(kaddr) (pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)) #define virt_addr_valid(kaddr) ((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory) -#else /* CONFIG_DISCONTIGMEM */ -#error CONFIG_DISCONTIGMEM is not supported yet. -#endif /* !CONFIG_DISCONTIGMEM */ - #define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) #endif diff --git a/arch/nios2/include/asm/irq.h b/arch/nios2/include/asm/irq.h index 13ce37272279..c52c94884e93 100644 --- a/arch/nios2/include/asm/irq.h +++ b/arch/nios2/include/asm/irq.h @@ -10,6 +10,5 @@ #define NIOS2_CPU_NR_IRQS 32 #include -#include #endif diff --git a/arch/nios2/kernel/irq.c b/arch/nios2/kernel/irq.c index 5f3555ce4865..c6a1a9f6ac42 100644 --- a/arch/nios2/kernel/irq.c +++ b/arch/nios2/kernel/irq.c @@ -11,6 +11,7 @@ #include #include +#include #include static u32 ienable; diff --git a/arch/openrisc/include/asm/tlbflush.h b/arch/openrisc/include/asm/tlbflush.h index 185dcd3731ed..dbf030365ab4 100644 --- a/arch/openrisc/include/asm/tlbflush.h +++ b/arch/openrisc/include/asm/tlbflush.h @@ -25,7 +25,7 @@ * - flush_tlb_all() flushes all processes TLBs * - flush_tlb_mm(mm) flushes the specified mm context TLB's * - flush_tlb_page(vma, vmaddr) flushes one page - * - flush_tlb_range(mm, start, end) flushes a range of pages + * - flush_tlb_range(vma, start, end) flushes a range of pages */ extern void local_flush_tlb_all(void); extern void local_flush_tlb_mm(struct mm_struct *mm); diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index f60904329bbc..5b5351cdcb33 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -119,6 +119,8 @@ #define SO_PREFER_BUSY_POLL 0x4043 #define SO_BUSY_POLL_BUDGET 0x4044 +#define SO_NETNS_COOKIE 0x4045 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index aabc37f8cae3..e26187b9ab87 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -440,7 +440,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 common quotactl_fd sys_quotactl_fd 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 088dd2afcfe4..14b132cf95e2 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -671,7 +671,7 @@ config NODES_SHIFT int default "8" if PPC64 default "4" - depends on NEED_MULTIPLE_NODES + depends on NUMA config USE_PERCPU_NUMA_NODE_ID def_bool y diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index b2bd58830430..4982f3711fc3 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -6,7 +6,6 @@ /* */ -#include #include #include #include @@ -23,8 +22,8 @@ extern atomic_t ppc_n_lost_interrupts; /* Total number of virq in the platform */ #define NR_IRQS CONFIG_NR_IRQS -/* Same thing, used by the generic IRQ code */ -#define NR_IRQS_LEGACY NUM_ISA_INTERRUPTS +/* Number of irqs reserved for a legacy isa controller */ +#define NR_IRQS_LEGACY 16 extern irq_hw_number_t virq_to_hw(unsigned int virq); diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 6cda76b57c5d..4c6c6dbd182f 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -18,7 +18,7 @@ * flags field of the struct page */ -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA extern struct pglist_data *node_data[]; /* @@ -41,7 +41,7 @@ u64 memory_hotplug_max(void); #else #define memory_hotplug_max() memblock_end_of_DRAM() -#endif /* CONFIG_NEED_MULTIPLE_NODES */ +#endif /* CONFIG_NUMA */ #ifdef CONFIG_FA_DUMP #define __HAVE_ARCH_RESERVED_KERNEL_PAGES #endif diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 9a3c2a84a2ac..15e7b4900689 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index e42b85e4f1aa..a35fbf4d0bce 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -788,7 +788,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, size_t align) { const unsigned long goal = __pa(MAX_DMA_ADDRESS); -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA int node = early_cpu_to_node(cpu); void *ptr; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 6c6e4d934d86..7ddc2d32c39e 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1047,7 +1047,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) zalloc_cpumask_var_node(&per_cpu(cpu_coregroup_map, cpu), GFP_KERNEL, cpu_to_node(cpu)); -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA /* * numa_node_id() works after this. */ diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 8f052ff4058c..aef2a290e71a 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -522,7 +522,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 common quotactl_fd sys_quotactl_fd 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c index 56da5eb2b923..48525e8b5730 100644 --- a/arch/powerpc/kexec/core.c +++ b/arch/powerpc/kexec/core.c @@ -68,11 +68,11 @@ void machine_kexec_cleanup(struct kimage *image) void arch_crash_save_vmcoreinfo(void) { -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA VMCOREINFO_SYMBOL(node_data); VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); #endif -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA VMCOREINFO_SYMBOL(contig_page_data); #endif #if defined(CONFIG_PPC64) && defined(CONFIG_SPARSEMEM_VMEMMAP) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index cd544a46183e..260e860d53a2 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4924,8 +4924,8 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) /* Look up the VMA for the start of this memory slot */ hva = memslot->userspace_addr; mmap_read_lock(kvm->mm); - vma = find_vma(kvm->mm, hva); - if (!vma || vma->vm_start > hva || (vma->vm_flags & VM_IO)) + vma = vma_lookup(kvm->mm, hva); + if (!vma || (vma->vm_flags & VM_IO)) goto up_out; psize = vma_kernel_pagesize(vma); diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 84e5a2dc8be5..a7061ee3b157 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -90,6 +90,7 @@ #include #include #include +#include #include #include #include @@ -614,7 +615,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot, /* Fetch the VMA if addr is not in the latest fetched one */ if (!vma || addr >= vma->vm_end) { - vma = find_vma_intersection(kvm->mm, addr, addr+1); + vma = vma_lookup(kvm->mm, addr); if (!vma) { pr_err("Can't find VMA for gfn:0x%lx\n", gfn); break; diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 9268d386b128..8cfab3547494 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 1253666dd4d8..573ecaab3597 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index c3df3a8501d4..2ffcf540f08b 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -13,7 +13,7 @@ obj-y := fault.o mem.o pgtable.o mmap.o maccess.o \ obj-$(CONFIG_PPC_MMU_NOHASH) += nohash/ obj-$(CONFIG_PPC_BOOK3S_32) += book3s32/ obj-$(CONFIG_PPC_BOOK3S_64) += book3s64/ -obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o +obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_PPC_MM_SLICES) += slice.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 6e3495221ab7..2176a5f70746 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index a6b36a40897a..c5e520c6f13b 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -127,7 +127,7 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, } #endif -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA void __init mem_topology_setup(void) { max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT; @@ -162,7 +162,7 @@ static int __init mark_nonram_nosave(void) return 0; } -#else /* CONFIG_NEED_MULTIPLE_NODES */ +#else /* CONFIG_NUMA */ static int __init mark_nonram_nosave(void) { return 0; diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index e7c976bcadff..cb70c5f25bc6 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -35,6 +35,7 @@ config PPC_IBM_CELL_BLADE config AXON_MSI bool depends on PPC_IBM_CELL_BLADE && PCI_MSI + select IRQ_DOMAIN_NOMAP default y menu "Cell Broadband Engine options" diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c index 35bbd15582af..b207a7f99be5 100644 --- a/arch/powerpc/platforms/cell/pmu.c +++ b/arch/powerpc/platforms/cell/pmu.c @@ -10,6 +10,7 @@ */ #include +#include #include #include #include diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c index d39a9213a3e6..609bda2ad5dd 100644 --- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c +++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/powerpc/platforms/powermac/Kconfig b/arch/powerpc/platforms/powermac/Kconfig index c02d8c503b29..b97bf12801eb 100644 --- a/arch/powerpc/platforms/powermac/Kconfig +++ b/arch/powerpc/platforms/powermac/Kconfig @@ -24,6 +24,7 @@ config PPC_PMAC32_PSURGE bool "Support for powersurge upgrade cards" if EXPERT depends on SMP && PPC32 && PPC_PMAC select PPC_SMP_MUXED_IPI + select IRQ_DOMAIN_NOMAP default y help The powersurge cpu boards can be used in the generation diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig index e32406e918d0..4d0535cc7946 100644 --- a/arch/powerpc/platforms/ps3/Kconfig +++ b/arch/powerpc/platforms/ps3/Kconfig @@ -7,6 +7,7 @@ config PPC_PS3 select USB_OHCI_BIG_ENDIAN_MMIO select USB_EHCI_BIG_ENDIAN_MMIO select HAVE_PCI + select IRQ_DOMAIN_NOMAP help This option enables support for the Sony PS3 game console and other platforms using the PS3 hypervisor. Enabling this diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c index 78f2339ed5cb..49871427f599 100644 --- a/arch/powerpc/platforms/ps3/interrupt.c +++ b/arch/powerpc/platforms/ps3/interrupt.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -45,7 +46,7 @@ * implementation equates HV plug value to Linux virq value, constrains each * interrupt to have a system wide unique plug number, and limits the range * of the plug values to map into the first dword of the bitmaps. This - * gives a usable range of plug values of {NUM_ISA_INTERRUPTS..63}. Note + * gives a usable range of plug values of {NR_IRQS_LEGACY..63}. Note * that there is no constraint on how many in this set an individual thread * can acquire. * @@ -721,7 +722,7 @@ static unsigned int ps3_get_irq(void) } #if defined(DEBUG) - if (unlikely(plug < NUM_ISA_INTERRUPTS || plug > PS3_PLUG_MAX)) { + if (unlikely(plug < NR_IRQS_LEGACY || plug > PS3_PLUG_MAX)) { dump_bmp(&per_cpu(ps3_private, 0)); dump_bmp(&per_cpu(ps3_private, 1)); BUG(); diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c index a15ab33646b3..c6c79ef55e13 100644 --- a/arch/powerpc/platforms/pseries/ibmebus.c +++ b/arch/powerpc/platforms/pseries/ibmebus.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c index 48866e6c1efb..00705258ecf9 100644 --- a/arch/powerpc/sysdev/ehv_pic.c +++ b/arch/powerpc/sysdev/ehv_pic.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/powerpc/sysdev/fsl_mpic_err.c b/arch/powerpc/sysdev/fsl_mpic_err.c index 13583bbc3e8e..5fa5fa215541 100644 --- a/arch/powerpc/sysdev/fsl_mpic_err.c +++ b/arch/powerpc/sysdev/fsl_mpic_err.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c index c1d76c344351..dc1a151c63d7 100644 --- a/arch/powerpc/sysdev/i8259.c +++ b/arch/powerpc/sysdev/i8259.c @@ -260,7 +260,8 @@ void i8259_init(struct device_node *node, unsigned long intack_addr) raw_spin_unlock_irqrestore(&i8259_lock, flags); /* create a legacy host */ - i8259_host = irq_domain_add_legacy_isa(node, &i8259_host_ops, NULL); + i8259_host = irq_domain_add_legacy(node, NR_IRQS_LEGACY, 0, 0, + &i8259_host_ops, NULL); if (i8259_host == NULL) { printk(KERN_ERR "i8259: failed to allocate irq host !\n"); return; diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index b0426f28946a..995fb2ada507 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -602,7 +602,7 @@ static void __init mpic_scan_ht_pics(struct mpic *mpic) /* Find an mpic associated with a given linux interrupt */ static struct mpic *mpic_find(unsigned int irq) { - if (irq < NUM_ISA_INTERRUPTS) + if (irq < NR_IRQS_LEGACY) return NULL; return irq_get_chip_data(irq); diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c index 49f9541954f8..042bb38fa5c2 100644 --- a/arch/powerpc/sysdev/tsi108_pci.c +++ b/arch/powerpc/sysdev/tsi108_pci.c @@ -404,7 +404,8 @@ void __init tsi108_pci_int_init(struct device_node *node) { DBG("Tsi108_pci_int_init: initializing PCI interrupts\n"); - pci_irq_host = irq_domain_add_legacy_isa(node, &pci_irq_domain_ops, NULL); + pci_irq_host = irq_domain_add_legacy(node, NR_IRQS_LEGACY, 0, 0, + &pci_irq_domain_ops, NULL); if (pci_irq_host == NULL) { printk(KERN_ERR "pci_irq_host: failed to allocate irq domain!\n"); return; diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c index 21b9d1bf39ff..6765d9e264a3 100644 --- a/arch/powerpc/sysdev/xics/icp-hv.c +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c index 68fd2540b093..675d708863d5 100644 --- a/arch/powerpc/sysdev/xics/icp-opal.c +++ b/arch/powerpc/sysdev/xics/icp-opal.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index 7e4305c01bac..fdf8db4444b6 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -201,7 +201,7 @@ void xics_migrate_irqs_away(void) struct ics *ics; /* We can't set affinity on ISA interrupts */ - if (virq < NUM_ISA_INTERRUPTS) + if (virq < NR_IRQS_LEGACY) continue; /* We only need to migrate enabled IRQS */ if (!desc->action) diff --git a/arch/powerpc/sysdev/xive/Kconfig b/arch/powerpc/sysdev/xive/Kconfig index 785c292d104b..97796c6b63f0 100644 --- a/arch/powerpc/sysdev/xive/Kconfig +++ b/arch/powerpc/sysdev/xive/Kconfig @@ -3,6 +3,7 @@ config PPC_XIVE bool select PPC_SMP_MUXED_IPI select HARDIRQS_SW_RESEND + select IRQ_DOMAIN_NOMAP config PPC_XIVE_NATIVE bool diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 18ec0f9bb8d5..15f9490a7aad 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -332,7 +332,7 @@ config NODES_SHIFT int "Maximum NUMA Nodes (as a power of 2)" range 1 10 default "2" - depends on NEED_MULTIPLE_NODES + depends on NUMA help Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accommodate various tables. diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index b4c7c34069f8..a49971647f81 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -117,6 +117,7 @@ config S390 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF select ARCH_WANTS_DYNAMIC_TASK_STRUCT + select ARCH_WANTS_NO_INSTR select ARCH_WANT_DEFAULT_BPF_JIT select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_TABLE_SORT @@ -475,7 +476,7 @@ config NUMA config NODES_SHIFT int - depends on NEED_MULTIPLE_NODES + depends on NUMA default "1" config SCHED_SMT diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 29c7ecd5ad1d..b38f7b781564 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -344,8 +344,6 @@ static inline int is_module_addr(void *addr) #define PTRS_PER_P4D _CRST_ENTRIES #define PTRS_PER_PGD _CRST_ENTRIES -#define MAX_PTRS_PER_P4D PTRS_PER_P4D - /* * Segment table and region3 table entry encoding * (R = read-only, I = invalid, y = young bit): diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 8fc52679543d..cb4f73c7228d 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -137,7 +137,6 @@ struct slibe { * @user0: user defineable value * @res4: reserved paramater * @user1: user defineable value - * @user2: user defineable value */ struct qaob { u64 res0[6]; @@ -152,8 +151,7 @@ struct qaob { u16 dcount[QDIO_MAX_ELEMENTS_PER_BUFFER]; u64 user0; u64 res4[2]; - u64 user1; - u64 user2; + u8 user1[16]; } __attribute__ ((packed, aligned(256))); /** diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index 0690263df1dd..64d51ab5a8b4 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -445,7 +445,7 @@ 440 common process_madvise sys_process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 common quotactl_fd sys_quotactl_fd sys_quotactl_fd 444 common landlock_create_ruleset sys_landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/sh/include/asm/mmzone.h b/arch/sh/include/asm/mmzone.h index 6552a088dc97..7b8dead2723d 100644 --- a/arch/sh/include/asm/mmzone.h +++ b/arch/sh/include/asm/mmzone.h @@ -2,7 +2,7 @@ #ifndef __ASM_SH_MMZONE_H #define __ASM_SH_MMZONE_H -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA #include extern struct pglist_data *node_data[]; @@ -31,7 +31,7 @@ static inline void setup_bootmem_node(int nid, unsigned long start, unsigned long end) { } -#endif /* CONFIG_NEED_MULTIPLE_NODES */ +#endif /* CONFIG_NUMA */ /* Platform specific mem init */ void __init plat_mem_setup(void); diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 0b91499ebdcf..e0a70be77d84 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -445,7 +445,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 common quotactl_fd sys_quotactl_fd 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/sh/kernel/topology.c b/arch/sh/kernel/topology.c index 7a989eed3b18..76af6db9daa2 100644 --- a/arch/sh/kernel/topology.c +++ b/arch/sh/kernel/topology.c @@ -46,7 +46,7 @@ static int __init topology_init(void) { int i, ret; -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA for_each_online_node(i) register_one_node(i); #endif diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index d551a9cac41e..ba569cfb4368 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -120,7 +120,7 @@ config NODES_SHIFT int default "3" if CPU_SUBTYPE_SHX3 default "1" - depends on NEED_MULTIPLE_NODES + depends on NUMA config ARCH_FLATMEM_ENABLE def_bool y diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 168d7d4dd735..ce26c7f8950a 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -211,7 +211,7 @@ void __init allocate_pgdat(unsigned int nid) get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA NODE_DATA(nid) = memblock_alloc_try_nid( sizeof(struct pglist_data), SMP_CACHE_BYTES, MEMBLOCK_LOW_LIMIT, diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 164a5254c91c..c72f52c704cd 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -265,7 +265,7 @@ config NODES_SHIFT int "Maximum NUMA Nodes (as a power of 2)" range 4 5 if SPARC64 default "5" - depends on NEED_MULTIPLE_NODES + depends on NUMA help Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accommodate various tables. diff --git a/arch/sparc/include/asm/mmzone.h b/arch/sparc/include/asm/mmzone.h index 6543fb97a849..a236d8aa893a 100644 --- a/arch/sparc/include/asm/mmzone.h +++ b/arch/sparc/include/asm/mmzone.h @@ -2,7 +2,7 @@ #ifndef _SPARC64_MMZONE_H #define _SPARC64_MMZONE_H -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA #include @@ -13,6 +13,6 @@ extern struct pglist_data *node_data[]; extern int numa_cpu_lookup_table[]; extern cpumask_t numa_cpumask_lookup_table[]; -#endif /* CONFIG_NEED_MULTIPLE_NODES */ +#endif /* CONFIG_NUMA */ #endif /* _SPARC64_MMZONE_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 848a22fbac20..92675dc380fa 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -120,6 +120,8 @@ #define SO_PREFER_BUSY_POLL 0x0048 #define SO_BUSY_POLL_BUDGET 0x0049 +#define SO_NETNS_COOKIE 0x0050 + #if !defined(__KERNEL__) diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index ae5faa1d989d..0224d8f19ed6 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1543,7 +1543,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, size_t align) { const unsigned long goal = __pa(MAX_DMA_ADDRESS); -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA int node = cpu_to_node(cpu); void *ptr; diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index e34cc30ef22c..603f5a821502 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -488,7 +488,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 common quotactl_fd sys_quotactl_fd 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index e454f179cf5d..06e938d03f3b 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -903,7 +903,7 @@ struct node_mem_mask { static struct node_mem_mask node_masks[MAX_NUMNODES]; static int num_node_masks; -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA struct mdesc_mlgroup { u64 node; @@ -1059,7 +1059,7 @@ static void __init allocate_node_data(int nid) { struct pglist_data *p; unsigned long start_pfn, end_pfn; -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA NODE_DATA(nid) = memblock_alloc_node(sizeof(struct pglist_data), SMP_CACHE_BYTES, nid); @@ -1080,7 +1080,7 @@ static void __init allocate_node_data(int nid) static void init_node_masks_nonnuma(void) { -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA int i; #endif @@ -1090,7 +1090,7 @@ static void init_node_masks_nonnuma(void) node_masks[0].match = 0; num_node_masks = 1; -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA for (i = 0; i < NR_CPUS; i++) numa_cpu_lookup_table[i] = 0; @@ -1098,7 +1098,7 @@ static void init_node_masks_nonnuma(void) #endif } -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA struct pglist_data *node_data[MAX_NUMNODES]; EXPORT_SYMBOL(numa_cpu_lookup_table); @@ -2487,7 +2487,7 @@ int page_in_phys_avail(unsigned long paddr) static void __init register_page_bootmem_info(void) { -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA int i; for_each_online_node(i) diff --git a/arch/um/kernel/skas/syscall.c b/arch/um/kernel/skas/syscall.c index 3d91f89fd852..9ee19e566da3 100644 --- a/arch/um/kernel/skas/syscall.c +++ b/arch/um/kernel/skas/syscall.c @@ -41,7 +41,7 @@ void handle_syscall(struct uml_pt_regs *r) goto out; syscall = UPT_SYSCALL_NR(r); - if (syscall >= 0 && syscall <= __NR_syscall_max) + if (syscall >= 0 && syscall < __NR_syscalls) PT_REGS_SET_SYSCALL_RETURN(regs, EXECUTE_SYSCALL(syscall, regs)); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 86dae426798b..867e7936dbc5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -103,8 +103,8 @@ config X86 select ARCH_SUPPORTS_DEBUG_PAGEALLOC select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP if NR_CPUS <= 4096 - select ARCH_SUPPORTS_LTO_CLANG if X86_64 - select ARCH_SUPPORTS_LTO_CLANG_THIN if X86_64 + select ARCH_SUPPORTS_LTO_CLANG + select ARCH_SUPPORTS_LTO_CLANG_THIN select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS @@ -113,6 +113,7 @@ config X86 select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH select ARCH_WANT_DEFAULT_BPF_JIT if X86_64 select ARCH_WANTS_DYNAMIC_TASK_STRUCT + select ARCH_WANTS_NO_INSTR select ARCH_WANT_HUGE_PMD_SHARE select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANTS_THP_SWAP if X86_64 @@ -1597,7 +1598,7 @@ config NODES_SHIFT default "10" if MAXSMP default "6" if X86_64 default "3" - depends on NEED_MULTIPLE_NODES + depends on NUMA help Specify the maximum number of NUMA Nodes available on the target system. Increases memory reserved to accommodate various tables. diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index 08bf95dbc911..7fec5dcf6438 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -8,18 +8,8 @@ UBSAN_SANITIZE := n KCOV_INSTRUMENT := n CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_syscall_64.o = $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_syscall_32.o = $(CC_FLAGS_FTRACE) -CFLAGS_REMOVE_syscall_x32.o = $(CC_FLAGS_FTRACE) CFLAGS_common.o += -fno-stack-protector -CFLAGS_syscall_64.o += -fno-stack-protector -CFLAGS_syscall_32.o += -fno-stack-protector -CFLAGS_syscall_x32.o += -fno-stack-protector - -CFLAGS_syscall_64.o += $(call cc-option,-Wno-override-init,) -CFLAGS_syscall_32.o += $(call cc-option,-Wno-override-init,) -CFLAGS_syscall_x32.o += $(call cc-option,-Wno-override-init,) obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o obj-y += common.o diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index f79688648db1..6c2826417b33 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -36,61 +36,97 @@ #include #ifdef CONFIG_X86_64 -__visible noinstr void do_syscall_64(struct pt_regs *regs, unsigned long nr) + +static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr) +{ + /* + * Convert negative numbers to very high and thus out of range + * numbers for comparisons. + */ + unsigned int unr = nr; + + if (likely(unr < NR_syscalls)) { + unr = array_index_nospec(unr, NR_syscalls); + regs->ax = sys_call_table[unr](regs); + return true; + } + return false; +} + +static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr) +{ + /* + * Adjust the starting offset of the table, and convert numbers + * < __X32_SYSCALL_BIT to very high and thus out of range + * numbers for comparisons. + */ + unsigned int xnr = nr - __X32_SYSCALL_BIT; + + if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) { + xnr = array_index_nospec(xnr, X32_NR_syscalls); + regs->ax = x32_sys_call_table[xnr](regs); + return true; + } + return false; +} + +__visible noinstr void do_syscall_64(struct pt_regs *regs, int nr) { add_random_kstack_offset(); nr = syscall_enter_from_user_mode(regs, nr); instrumentation_begin(); - if (likely(nr < NR_syscalls)) { - nr = array_index_nospec(nr, NR_syscalls); - regs->ax = sys_call_table[nr](regs); -#ifdef CONFIG_X86_X32_ABI - } else if (likely((nr & __X32_SYSCALL_BIT) && - (nr & ~__X32_SYSCALL_BIT) < X32_NR_syscalls)) { - nr = array_index_nospec(nr & ~__X32_SYSCALL_BIT, - X32_NR_syscalls); - regs->ax = x32_sys_call_table[nr](regs); -#endif + + if (!do_syscall_x64(regs, nr) && !do_syscall_x32(regs, nr) && nr != -1) { + /* Invalid system call, but still a system call. */ + regs->ax = __x64_sys_ni_syscall(regs); } + instrumentation_end(); syscall_exit_to_user_mode(regs); } #endif #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) -static __always_inline unsigned int syscall_32_enter(struct pt_regs *regs) +static __always_inline int syscall_32_enter(struct pt_regs *regs) { if (IS_ENABLED(CONFIG_IA32_EMULATION)) current_thread_info()->status |= TS_COMPAT; - return (unsigned int)regs->orig_ax; + return (int)regs->orig_ax; } /* * Invoke a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. */ -static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, - unsigned int nr) +static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) { - if (likely(nr < IA32_NR_syscalls)) { - nr = array_index_nospec(nr, IA32_NR_syscalls); - regs->ax = ia32_sys_call_table[nr](regs); + /* + * Convert negative numbers to very high and thus out of range + * numbers for comparisons. + */ + unsigned int unr = nr; + + if (likely(unr < IA32_NR_syscalls)) { + unr = array_index_nospec(unr, IA32_NR_syscalls); + regs->ax = ia32_sys_call_table[unr](regs); + } else if (nr != -1) { + regs->ax = __ia32_sys_ni_syscall(regs); } } /* Handles int $0x80 */ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) { - unsigned int nr = syscall_32_enter(regs); + int nr = syscall_32_enter(regs); add_random_kstack_offset(); /* - * Subtlety here: if ptrace pokes something larger than 2^32-1 into - * orig_ax, the unsigned int return value truncates it. This may - * or may not be necessary, but it matches the old asm behavior. + * Subtlety here: if ptrace pokes something larger than 2^31-1 into + * orig_ax, the int return value truncates it. This matches + * the semantics of syscall_get_nr(). */ - nr = (unsigned int)syscall_enter_from_user_mode(regs, nr); + nr = syscall_enter_from_user_mode(regs, nr); instrumentation_begin(); do_syscall_32_irqs_on(regs, nr); @@ -101,7 +137,7 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) { - unsigned int nr = syscall_32_enter(regs); + int nr = syscall_32_enter(regs); int res; add_random_kstack_offset(); @@ -136,8 +172,7 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) return false; } - /* The case truncates any ptrace induced syscall nr > 2^32 -1 */ - nr = (unsigned int)syscall_enter_from_user_mode_work(regs, nr); + nr = syscall_enter_from_user_mode_work(regs, nr); /* Now this is just like a normal syscall. */ do_syscall_32_irqs_on(regs, nr); diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 237da6ced61b..e38a4cf795d9 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -108,7 +108,8 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) /* IRQs are off. */ movq %rsp, %rdi - movq %rax, %rsi + /* Sign extend the lower 32bit as syscall numbers are treated as int */ + movslq %eax, %rsi call do_syscall_64 /* returns with IRQs disabled */ /* diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 86eb0d89d46f..8cfc9bc73e7f 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -5,21 +5,21 @@ #include #include #include -#include #include -#define __SYSCALL_I386(nr, sym) extern long __ia32_##sym(const struct pt_regs *); +#ifdef CONFIG_IA32_EMULATION +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, compat) +#else +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) +#endif + +#define __SYSCALL(nr, sym) extern long __ia32_##sym(const struct pt_regs *); #include -#undef __SYSCALL_I386 +#undef __SYSCALL -#define __SYSCALL_I386(nr, sym) [nr] = __ia32_##sym, +#define __SYSCALL(nr, sym) __ia32_##sym, -__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = { - /* - * Smells like a compiler bug -- it doesn't work - * when the & below is removed. - */ - [0 ... __NR_ia32_syscall_max] = &__ia32_sys_ni_syscall, +__visible const sys_call_ptr_t ia32_sys_call_table[] = { #include }; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index 1594ec72bcbb..be120eec1fc9 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -5,23 +5,14 @@ #include #include #include -#include #include -#define __SYSCALL_X32(nr, sym) -#define __SYSCALL_COMMON(nr, sym) __SYSCALL_64(nr, sym) - -#define __SYSCALL_64(nr, sym) extern long __x64_##sym(const struct pt_regs *); +#define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *); #include -#undef __SYSCALL_64 +#undef __SYSCALL -#define __SYSCALL_64(nr, sym) [nr] = __x64_##sym, +#define __SYSCALL(nr, sym) __x64_##sym, -asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { - /* - * Smells like a compiler bug -- it doesn't work - * when the & below is removed. - */ - [0 ... __NR_syscall_max] = &__x64_sys_ni_syscall, +asmlinkage const sys_call_ptr_t sys_call_table[] = { #include }; diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c index f2fe0a33bcfd..bdd0e03a1265 100644 --- a/arch/x86/entry/syscall_x32.c +++ b/arch/x86/entry/syscall_x32.c @@ -5,37 +5,14 @@ #include #include #include -#include #include -/* - * Reuse the 64-bit entry points for the x32 versions that occupy different - * slots in the syscall table. - */ -#define __x32_sys_readv __x64_sys_readv -#define __x32_sys_writev __x64_sys_writev -#define __x32_sys_getsockopt __x64_sys_getsockopt -#define __x32_sys_setsockopt __x64_sys_setsockopt -#define __x32_sys_vmsplice __x64_sys_vmsplice -#define __x32_sys_process_vm_readv __x64_sys_process_vm_readv -#define __x32_sys_process_vm_writev __x64_sys_process_vm_writev +#define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *); +#include +#undef __SYSCALL -#define __SYSCALL_64(nr, sym) +#define __SYSCALL(nr, sym) __x64_##sym, -#define __SYSCALL_X32(nr, sym) extern long __x32_##sym(const struct pt_regs *); -#define __SYSCALL_COMMON(nr, sym) extern long __x64_##sym(const struct pt_regs *); -#include -#undef __SYSCALL_X32 -#undef __SYSCALL_COMMON - -#define __SYSCALL_X32(nr, sym) [nr] = __x32_##sym, -#define __SYSCALL_COMMON(nr, sym) [nr] = __x64_##sym, - -asmlinkage const sys_call_ptr_t x32_sys_call_table[__NR_x32_syscall_max+1] = { - /* - * Smells like a compiler bug -- it doesn't work - * when the & below is removed. - */ - [0 ... __NR_x32_syscall_max] = &__x64_sys_ni_syscall, -#include +asmlinkage const sys_call_ptr_t x32_sys_call_table[] = { +#include }; diff --git a/arch/x86/entry/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile index d8c4f6c9eadc..5b3efed0e4e8 100644 --- a/arch/x86/entry/syscalls/Makefile +++ b/arch/x86/entry/syscalls/Makefile @@ -9,47 +9,54 @@ _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \ syscall32 := $(src)/syscall_32.tbl syscall64 := $(src)/syscall_64.tbl -syshdr := $(srctree)/$(src)/syscallhdr.sh -systbl := $(srctree)/$(src)/syscalltbl.sh +syshdr := $(srctree)/scripts/syscallhdr.sh +systbl := $(srctree)/scripts/syscalltbl.sh +offset := +prefix := quiet_cmd_syshdr = SYSHDR $@ - cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' '$<' '$@' \ - '$(syshdr_abi_$(basetarget))' \ - '$(syshdr_pfx_$(basetarget))' \ - '$(syshdr_offset_$(basetarget))' + cmd_syshdr = $(CONFIG_SHELL) $(syshdr) --abis $(abis) --emit-nr \ + $(if $(offset),--offset $(offset)) \ + $(if $(prefix),--prefix $(prefix)) \ + $< $@ quiet_cmd_systbl = SYSTBL $@ - cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@ + cmd_systbl = $(CONFIG_SHELL) $(systbl) --abis $(abis) $< $@ quiet_cmd_hypercalls = HYPERCALLS $@ cmd_hypercalls = $(CONFIG_SHELL) '$<' $@ $(filter-out $<, $(real-prereqs)) -syshdr_abi_unistd_32 := i386 +$(uapi)/unistd_32.h: abis := i386 $(uapi)/unistd_32.h: $(syscall32) $(syshdr) FORCE $(call if_changed,syshdr) -syshdr_abi_unistd_32_ia32 := i386 -syshdr_pfx_unistd_32_ia32 := ia32_ +$(out)/unistd_32_ia32.h: abis := i386 +$(out)/unistd_32_ia32.h: prefix := ia32_ $(out)/unistd_32_ia32.h: $(syscall32) $(syshdr) FORCE $(call if_changed,syshdr) -syshdr_abi_unistd_x32 := common,x32 -syshdr_offset_unistd_x32 := __X32_SYSCALL_BIT +$(uapi)/unistd_x32.h: abis := common,x32 +$(uapi)/unistd_x32.h: offset := __X32_SYSCALL_BIT $(uapi)/unistd_x32.h: $(syscall64) $(syshdr) FORCE $(call if_changed,syshdr) -syshdr_abi_unistd_64 := common,64 +$(uapi)/unistd_64.h: abis := common,64 $(uapi)/unistd_64.h: $(syscall64) $(syshdr) FORCE $(call if_changed,syshdr) -syshdr_abi_unistd_64_x32 := x32 -syshdr_pfx_unistd_64_x32 := x32_ +$(out)/unistd_64_x32.h: abis := x32 +$(out)/unistd_64_x32.h: prefix := x32_ $(out)/unistd_64_x32.h: $(syscall64) $(syshdr) FORCE $(call if_changed,syshdr) +$(out)/syscalls_32.h: abis := i386 $(out)/syscalls_32.h: $(syscall32) $(systbl) FORCE $(call if_changed,systbl) +$(out)/syscalls_64.h: abis := common,64 $(out)/syscalls_64.h: $(syscall64) $(systbl) FORCE $(call if_changed,systbl) +$(out)/syscalls_x32.h: abis := common,x32 +$(out)/syscalls_x32.h: $(syscall64) $(systbl) FORCE + $(call if_changed,systbl) $(out)/xen-hypercalls.h: $(srctree)/scripts/xen-hypercalls.sh FORCE $(call if_changed,hypercalls) @@ -60,6 +67,7 @@ uapisyshdr-y += unistd_32.h unistd_64.h unistd_x32.h syshdr-y += syscalls_32.h syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h unistd_64_x32.h syshdr-$(CONFIG_X86_64) += syscalls_64.h +syshdr-$(CONFIG_X86_X32) += syscalls_x32.h syshdr-$(CONFIG_XEN) += xen-hypercalls.h uapisyshdr-y := $(addprefix $(uapi)/, $(uapisyshdr-y)) diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 4bbc267fb36b..fba2f615119a 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -447,7 +447,7 @@ 440 i386 process_madvise sys_process_madvise 441 i386 epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2 442 i386 mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 i386 quotactl_fd sys_quotactl_fd 444 i386 landlock_create_ruleset sys_landlock_create_ruleset 445 i386 landlock_add_rule sys_landlock_add_rule 446 i386 landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index ce18119ea0d0..af973e400053 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -364,7 +364,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 common quotactl_fd sys_quotactl_fd 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/x86/entry/syscalls/syscallhdr.sh b/arch/x86/entry/syscalls/syscallhdr.sh deleted file mode 100644 index cc1e63857427..000000000000 --- a/arch/x86/entry/syscalls/syscallhdr.sh +++ /dev/null @@ -1,35 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 - -in="$1" -out="$2" -my_abis=`echo "($3)" | tr ',' '|'` -prefix="$4" -offset="$5" - -fileguard=_ASM_X86_`basename "$out" | sed \ - -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \ - -e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'` -grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | ( - echo "#ifndef ${fileguard}" - echo "#define ${fileguard} 1" - echo "" - - max=0 - while read nr abi name entry ; do - if [ -z "$offset" ]; then - echo "#define __NR_${prefix}${name} $nr" - else - echo "#define __NR_${prefix}${name} ($offset + $nr)" - fi - - max=$nr - done - - echo "" - echo "#ifdef __KERNEL__" - echo "#define __NR_${prefix}syscall_max $max" - echo "#endif" - echo "" - echo "#endif /* ${fileguard} */" -) > "$out" diff --git a/arch/x86/entry/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh deleted file mode 100644 index 929bde120d6b..000000000000 --- a/arch/x86/entry/syscalls/syscalltbl.sh +++ /dev/null @@ -1,46 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -in="$1" -out="$2" - -syscall_macro() { - local abi="$1" - local nr="$2" - local entry="$3" - - echo "__SYSCALL_${abi}($nr, $entry)" -} - -emit() { - local abi="$1" - local nr="$2" - local entry="$3" - local compat="$4" - - if [ "$abi" != "I386" -a -n "$compat" ]; then - echo "a compat entry ($abi: $compat) for a 64-bit syscall makes no sense" >&2 - exit 1 - fi - - if [ -z "$compat" ]; then - if [ -n "$entry" ]; then - syscall_macro "$abi" "$nr" "$entry" - fi - else - echo "#ifdef CONFIG_X86_32" - if [ -n "$entry" ]; then - syscall_macro "$abi" "$nr" "$entry" - fi - echo "#else" - syscall_macro "$abi" "$nr" "$compat" - echo "#endif" - fi -} - -grep '^[0-9]' "$in" | sort -n | ( - while read nr abi name entry compat; do - abi=`echo "$abi" | tr '[a-z]' '[A-Z]'` - emit "$abi" "$nr" "$entry" "$compat" - done -) > "$out" diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 256ad0e34dd2..6952e219cba3 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -614,50 +614,3 @@ bool hv_is_isolation_supported(void) return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE; } EXPORT_SYMBOL_GPL(hv_is_isolation_supported); - -/* Bit mask of the extended capability to query: see HV_EXT_CAPABILITY_xxx */ -bool hv_query_ext_cap(u64 cap_query) -{ - /* - * The address of the 'hv_extended_cap' variable will be used as an - * output parameter to the hypercall below and so it should be - * compatible with 'virt_to_phys'. Which means, it's address should be - * directly mapped. Use 'static' to keep it compatible; stack variables - * can be virtually mapped, making them incompatible with - * 'virt_to_phys'. - * Hypercall input/output addresses should also be 8-byte aligned. - */ - static u64 hv_extended_cap __aligned(8); - static bool hv_extended_cap_queried; - u64 status; - - /* - * Querying extended capabilities is an extended hypercall. Check if the - * partition supports extended hypercall, first. - */ - if (!(ms_hyperv.priv_high & HV_ENABLE_EXTENDED_HYPERCALLS)) - return false; - - /* Extended capabilities do not change at runtime. */ - if (hv_extended_cap_queried) - return hv_extended_cap & cap_query; - - status = hv_do_hypercall(HV_EXT_CALL_QUERY_CAPABILITIES, NULL, - &hv_extended_cap); - - /* - * The query extended capabilities hypercall should not fail under - * any normal circumstances. Avoid repeatedly making the hypercall, on - * error. - */ - hv_extended_cap_queried = true; - status &= HV_HYPERCALL_RESULT_MASK; - if (status != HV_STATUS_SUCCESS) { - pr_err("Hyper-V: Extended query capabilities hypercall failed 0x%llx\n", - status); - return false; - } - - return hv_extended_cap & cap_query; -} -EXPORT_SYMBOL_GPL(hv_query_ext_cap); diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index a09fc37ead9d..5e5b9fc2747f 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -203,7 +203,7 @@ static int load_aout_binary(struct linux_binprm *bprm) error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, PROT_READ | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | - MAP_EXECUTABLE | MAP_32BIT, + MAP_32BIT, fd_offset); if (error != N_TXTADDR(ex)) @@ -212,7 +212,7 @@ static int load_aout_binary(struct linux_binprm *bprm) error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data, PROT_READ | PROT_WRITE | PROT_EXEC, MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | - MAP_EXECUTABLE | MAP_32BIT, + MAP_32BIT, fd_offset + ex.a_text); if (error != N_DATADDR(ex)) return error; diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index b19ec8282d50..1e51650b79d7 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -3,6 +3,7 @@ generated-y += syscalls_32.h generated-y += syscalls_64.h +generated-y += syscalls_x32.h generated-y += unistd_32_ia32.h generated-y += unistd_64_x32.h generated-y += xen-hypercalls.h diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 96021e9bd202..e63cf582201f 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -224,6 +224,26 @@ static inline void store_idt(struct desc_ptr *dtr) asm volatile("sidt %0":"=m" (*dtr)); } +static inline void native_gdt_invalidate(void) +{ + const struct desc_ptr invalid_gdt = { + .address = 0, + .size = 0 + }; + + native_load_gdt(&invalid_gdt); +} + +static inline void native_idt_invalidate(void) +{ + const struct desc_ptr invalid_idt = { + .address = 0, + .size = 0 + }; + + native_load_idt(&invalid_idt); +} + /* * The LTR instruction marks the TSS GDT entry as busy. On 64-bit, the GDT is * a read-only remapping. To prevent a page fault, the GDT is switched to the @@ -425,6 +445,6 @@ extern void idt_setup_early_pf(void); static inline void idt_setup_early_pf(void) { } #endif -extern void idt_invalidate(void *addr); +extern void idt_invalidate(void); #endif /* _ASM_X86_DESC_H */ diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index cd9f3e304944..1345088e9902 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -495,7 +495,7 @@ __visible noinstr void func(struct pt_regs *regs, \ .align 8 SYM_CODE_START(irq_entries_start) vector=FIRST_EXTERNAL_VECTOR - .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) + .rept NR_EXTERNAL_VECTORS UNWIND_HINT_IRET_REGS 0 : .byte 0x6a, vector @@ -511,7 +511,7 @@ SYM_CODE_END(irq_entries_start) .align 8 SYM_CODE_START(spurious_entries_start) vector=FIRST_SYSTEM_VECTOR - .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR) + .rept NR_SYSTEM_VECTORS UNWIND_HINT_IRET_REGS 0 : .byte 0x6a, vector diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 889f8b1b5b7f..43dcb9284208 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -26,8 +26,8 @@ * This file enumerates the exact layout of them: */ +/* This is used as an interrupt vector when programming the APIC. */ #define NMI_VECTOR 0x02 -#define MCE_VECTOR 0x12 /* * IDT vectors usable for external interrupt sources start at 0x20. @@ -84,7 +84,7 @@ */ #define IRQ_WORK_VECTOR 0xf6 -#define UV_BAU_MESSAGE 0xf5 +/* 0xf5 - unused, was UV_BAU_MESSAGE */ #define DEFERRED_ERROR_VECTOR 0xf4 /* Vector on which hypervisor callbacks will be delivered */ @@ -114,6 +114,9 @@ #define FIRST_SYSTEM_VECTOR NR_VECTORS #endif +#define NR_EXTERNAL_VECTORS (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) +#define NR_SYSTEM_VECTORS (NR_VECTORS - FIRST_SYSTEM_VECTOR) + /* * Size the maximum number of interrupts. * diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index f6593cafdbd9..f7e2d82d24fb 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -159,7 +159,7 @@ static inline int syscall_get_arch(struct task_struct *task) ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; } -void do_syscall_64(struct pt_regs *regs, unsigned long nr); +void do_syscall_64(struct pt_regs *regs, int nr); void do_int80_syscall_32(struct pt_regs *regs); long do_fast_syscall_32(struct pt_regs *regs); diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index 80c08c7d5e72..6a2827d0681f 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -17,7 +17,7 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); * __x64_sys_*() - 64-bit native syscall * __ia32_sys_*() - 32-bit native syscall or common compat syscall * __ia32_compat_sys_*() - 32-bit compat syscall - * __x32_compat_sys_*() - 64-bit X32 compat syscall + * __x64_compat_sys_*() - 64-bit X32 compat syscall * * The registers are decoded according to the ABI: * 64-bit: RDI, RSI, RDX, R10, R8, R9 @@ -166,17 +166,17 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); * with x86_64 obviously do not need such care. */ #define __X32_COMPAT_SYS_STUB0(name) \ - __SYS_STUB0(x32, compat_sys_##name) + __SYS_STUB0(x64, compat_sys_##name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) \ - __SYS_STUBx(x32, compat_sys##name, \ + __SYS_STUBx(x64, compat_sys##name, \ SC_X86_64_REGS_TO_ARGS(x, __VA_ARGS__)) #define __X32_COMPAT_COND_SYSCALL(name) \ - __COND_SYSCALL(x32, compat_sys_##name) + __COND_SYSCALL(x64, compat_sys_##name) #define __X32_COMPAT_SYS_NI(name) \ - __SYS_NI(x32, compat_sys_##name) + __SYS_NI(x64, compat_sys_##name) #else /* CONFIG_X86_X32 */ #define __X32_COMPAT_SYS_STUB0(name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index c1c3d31b15c0..80e9d5206a71 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -13,7 +13,7 @@ # define __ARCH_WANT_SYS_OLD_MMAP # define __ARCH_WANT_SYS_OLD_SELECT -# define __NR_ia32_syscall_max __NR_syscall_max +# define IA32_NR_syscalls (__NR_syscalls) # else @@ -26,12 +26,12 @@ # define __ARCH_WANT_COMPAT_SYS_PWRITEV64 # define __ARCH_WANT_COMPAT_SYS_PREADV64V2 # define __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 +# define X32_NR_syscalls (__NR_x32_syscalls) +# define IA32_NR_syscalls (__NR_ia32_syscalls) # endif -# define NR_syscalls (__NR_syscall_max + 1) -# define X32_NR_syscalls (__NR_x32_syscall_max + 1) -# define IA32_NR_syscalls (__NR_ia32_syscall_max + 1) +# define NR_syscalls (__NR_syscalls) # define __ARCH_WANT_NEW_STAT # define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index e90310cbe73a..e55e0c1fad8c 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -5,6 +5,7 @@ * Copyright (C) 2001, 2002 Paul Diefenbaugh * Copyright (C) 2001 Jun Nakajima */ +#define pr_fmt(fmt) "ACPI: " fmt #include #include @@ -42,8 +43,6 @@ EXPORT_SYMBOL(acpi_disabled); # include #endif /* X86 */ -#define PREFIX "ACPI: " - int acpi_noirq; /* skip ACPI IRQ initialization */ static int acpi_nobgrt; /* skip ACPI BGRT */ int acpi_pci_disabled; /* skip ACPI PCI scan and IRQ initialization */ @@ -130,15 +129,14 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) madt = (struct acpi_table_madt *)table; if (!madt) { - printk(KERN_WARNING PREFIX "Unable to map MADT\n"); + pr_warn("Unable to map MADT\n"); return -ENODEV; } if (madt->address) { acpi_lapic_addr = (u64) madt->address; - printk(KERN_DEBUG PREFIX "Local APIC address 0x%08x\n", - madt->address); + pr_debug("Local APIC address 0x%08x\n", madt->address); } default_acpi_madt_oem_check(madt->header.oem_id, @@ -161,7 +159,7 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled) int cpu; if (id >= MAX_LOCAL_APIC) { - printk(KERN_INFO PREFIX "skipped apicid that is too big\n"); + pr_info("skipped apicid that is too big\n"); return -EINVAL; } @@ -213,13 +211,13 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end) */ if (!apic->apic_id_valid(apic_id)) { if (enabled) - pr_warn(PREFIX "x2apic entry ignored\n"); + pr_warn("x2apic entry ignored\n"); return 0; } acpi_register_lapic(apic_id, processor->uid, enabled); #else - printk(KERN_WARNING PREFIX "x2apic entry ignored\n"); + pr_warn("x2apic entry ignored\n"); #endif return 0; @@ -306,7 +304,7 @@ acpi_parse_x2apic_nmi(union acpi_subtable_headers *header, acpi_table_print_madt_entry(&header->common); if (x2apic_nmi->lint != 1) - printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n"); + pr_warn("NMI not connected to LINT 1!\n"); return 0; } @@ -324,7 +322,7 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e acpi_table_print_madt_entry(&header->common); if (lapic_nmi->lint != 1) - printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n"); + pr_warn("NMI not connected to LINT 1!\n"); return 0; } @@ -514,14 +512,14 @@ acpi_parse_int_src_ovr(union acpi_subtable_headers * header, if (intsrc->source_irq == 0) { if (acpi_skip_timer_override) { - printk(PREFIX "BIOS IRQ0 override ignored.\n"); + pr_warn("BIOS IRQ0 override ignored.\n"); return 0; } if ((intsrc->global_irq == 2) && acpi_fix_pin2_polarity && (intsrc->inti_flags & ACPI_MADT_POLARITY_MASK)) { intsrc->inti_flags &= ~ACPI_MADT_POLARITY_MASK; - printk(PREFIX "BIOS IRQ0 pin2 override: forcing polarity to high active.\n"); + pr_warn("BIOS IRQ0 pin2 override: forcing polarity to high active.\n"); } } @@ -597,7 +595,7 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) if (old == new) return; - printk(PREFIX "setting ELCR to %04x (from %04x)\n", new, old); + pr_warn("setting ELCR to %04x (from %04x)\n", new, old); outb(new, 0x4d0); outb(new >> 8, 0x4d1); } @@ -754,7 +752,7 @@ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, cpu = acpi_register_lapic(physid, acpi_id, ACPI_MADT_ENABLED); if (cpu < 0) { - pr_info(PREFIX "Unable to map lapic to logical cpu number\n"); + pr_info("Unable to map lapic to logical cpu number\n"); return cpu; } @@ -870,8 +868,7 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) struct acpi_table_hpet *hpet_tbl = (struct acpi_table_hpet *)table; if (hpet_tbl->address.space_id != ACPI_SPACE_MEM) { - printk(KERN_WARNING PREFIX "HPET timers must be located in " - "memory.\n"); + pr_warn("HPET timers must be located in memory.\n"); return -1; } @@ -883,9 +880,7 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) * want to allocate a resource there. */ if (!hpet_address) { - printk(KERN_WARNING PREFIX - "HPET id: %#x base: %#lx is invalid\n", - hpet_tbl->id, hpet_address); + pr_warn("HPET id: %#x base: %#lx is invalid\n", hpet_tbl->id, hpet_address); return 0; } #ifdef CONFIG_X86_64 @@ -896,21 +891,17 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) */ if (hpet_address == 0xfed0000000000000UL) { if (!hpet_force_user) { - printk(KERN_WARNING PREFIX "HPET id: %#x " - "base: 0xfed0000000000000 is bogus\n " - "try hpet=force on the kernel command line to " - "fix it up to 0xfed00000.\n", hpet_tbl->id); + pr_warn("HPET id: %#x base: 0xfed0000000000000 is bogus, try hpet=force on the kernel command line to fix it up to 0xfed00000.\n", + hpet_tbl->id); hpet_address = 0; return 0; } - printk(KERN_WARNING PREFIX - "HPET id: %#x base: 0xfed0000000000000 fixed up " - "to 0xfed00000.\n", hpet_tbl->id); + pr_warn("HPET id: %#x base: 0xfed0000000000000 fixed up to 0xfed00000.\n", + hpet_tbl->id); hpet_address >>= 32; } #endif - printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n", - hpet_tbl->id, hpet_address); + pr_info("HPET id: %#x base: %#lx\n", hpet_tbl->id, hpet_address); /* * Allocate and initialize the HPET firmware resource for adding into @@ -955,24 +946,24 @@ late_initcall(hpet_insert_resource); static int __init acpi_parse_fadt(struct acpi_table_header *table) { if (!(acpi_gbl_FADT.boot_flags & ACPI_FADT_LEGACY_DEVICES)) { - pr_debug("ACPI: no legacy devices present\n"); + pr_debug("no legacy devices present\n"); x86_platform.legacy.devices.pnpbios = 0; } if (acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID && !(acpi_gbl_FADT.boot_flags & ACPI_FADT_8042) && x86_platform.legacy.i8042 != X86_LEGACY_I8042_PLATFORM_ABSENT) { - pr_debug("ACPI: i8042 controller is absent\n"); + pr_debug("i8042 controller is absent\n"); x86_platform.legacy.i8042 = X86_LEGACY_I8042_FIRMWARE_ABSENT; } if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) { - pr_debug("ACPI: not registering RTC platform device\n"); + pr_debug("not registering RTC platform device\n"); x86_platform.legacy.rtc = 0; } if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_VGA) { - pr_debug("ACPI: probing for VGA not safe\n"); + pr_debug("probing for VGA not safe\n"); x86_platform.legacy.no_vga = 1; } @@ -997,8 +988,7 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table) pmtmr_ioport = acpi_gbl_FADT.pm_timer_block; } if (pmtmr_ioport) - printk(KERN_INFO PREFIX "PM-Timer IO Port: %#x\n", - pmtmr_ioport); + pr_info("PM-Timer IO Port: %#x\n", pmtmr_ioport); #endif return 0; } @@ -1024,8 +1014,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_OVERRIDE, acpi_parse_lapic_addr_ovr, 0); if (count < 0) { - printk(KERN_ERR PREFIX - "Error parsing LAPIC address override entry\n"); + pr_err("Error parsing LAPIC address override entry\n"); return count; } @@ -1057,8 +1046,7 @@ static int __init acpi_parse_madt_lapic_entries(void) sizeof(struct acpi_table_madt), madt_proc, ARRAY_SIZE(madt_proc), MAX_LOCAL_APIC); if (ret < 0) { - printk(KERN_ERR PREFIX - "Error parsing LAPIC/X2APIC entries\n"); + pr_err("Error parsing LAPIC/X2APIC entries\n"); return ret; } @@ -1066,11 +1054,11 @@ static int __init acpi_parse_madt_lapic_entries(void) x2count = madt_proc[1].count; } if (!count && !x2count) { - printk(KERN_ERR PREFIX "No LAPIC entries present\n"); + pr_err("No LAPIC entries present\n"); /* TBD: Cleanup to allow fallback to MPS */ return -ENODEV; } else if (count < 0 || x2count < 0) { - printk(KERN_ERR PREFIX "Error parsing LAPIC entry\n"); + pr_err("Error parsing LAPIC entry\n"); /* TBD: Cleanup to allow fallback to MPS */ return count; } @@ -1080,7 +1068,7 @@ static int __init acpi_parse_madt_lapic_entries(void) count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_NMI, acpi_parse_lapic_nmi, 0); if (count < 0 || x2count < 0) { - printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n"); + pr_err("Error parsing LAPIC NMI entry\n"); /* TBD: Cleanup to allow fallback to MPS */ return count; } @@ -1139,7 +1127,7 @@ static void __init mp_config_acpi_legacy_irqs(void) } if (idx != mp_irq_entries) { - printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i); + pr_debug("ACPI: IRQ%d used by override.\n", i); continue; /* IRQ already used */ } @@ -1179,26 +1167,24 @@ static int __init acpi_parse_madt_ioapic_entries(void) * if "noapic" boot option, don't look for IO-APICs */ if (skip_ioapic_setup) { - printk(KERN_INFO PREFIX "Skipping IOAPIC probe " - "due to 'noapic' option.\n"); + pr_info("Skipping IOAPIC probe due to 'noapic' option.\n"); return -ENODEV; } count = acpi_table_parse_madt(ACPI_MADT_TYPE_IO_APIC, acpi_parse_ioapic, MAX_IO_APICS); if (!count) { - printk(KERN_ERR PREFIX "No IOAPIC entries present\n"); + pr_err("No IOAPIC entries present\n"); return -ENODEV; } else if (count < 0) { - printk(KERN_ERR PREFIX "Error parsing IOAPIC entry\n"); + pr_err("Error parsing IOAPIC entry\n"); return count; } count = acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, acpi_parse_int_src_ovr, nr_irqs); if (count < 0) { - printk(KERN_ERR PREFIX - "Error parsing interrupt source overrides entry\n"); + pr_err("Error parsing interrupt source overrides entry\n"); /* TBD: Cleanup to allow fallback to MPS */ return count; } @@ -1218,7 +1204,7 @@ static int __init acpi_parse_madt_ioapic_entries(void) count = acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE, acpi_parse_nmi_src, nr_irqs); if (count < 0) { - printk(KERN_ERR PREFIX "Error parsing NMI SRC entry\n"); + pr_err("Error parsing NMI SRC entry\n"); /* TBD: Cleanup to allow fallback to MPS */ return count; } @@ -1251,8 +1237,7 @@ static void __init early_acpi_process_madt(void) /* * Dell Precision Workstation 410, 610 come here. */ - printk(KERN_ERR PREFIX - "Invalid BIOS MADT, disabling ACPI\n"); + pr_err("Invalid BIOS MADT, disabling ACPI\n"); disable_acpi(); } } @@ -1289,8 +1274,7 @@ static void __init acpi_process_madt(void) /* * Dell Precision Workstation 410, 610 come here. */ - printk(KERN_ERR PREFIX - "Invalid BIOS MADT, disabling ACPI\n"); + pr_err("Invalid BIOS MADT, disabling ACPI\n"); disable_acpi(); } } else { @@ -1300,8 +1284,7 @@ static void __init acpi_process_madt(void) * Boot with "acpi=off" to use MPS on such a system. */ if (smp_found_config) { - printk(KERN_WARNING PREFIX - "No APIC-table, disabling MPS\n"); + pr_warn("No APIC-table, disabling MPS\n"); smp_found_config = 0; } } @@ -1311,11 +1294,9 @@ static void __init acpi_process_madt(void) * processors, where MPS only supports physical. */ if (acpi_lapic && acpi_ioapic) - printk(KERN_INFO "Using ACPI (MADT) for SMP configuration " - "information\n"); + pr_info("Using ACPI (MADT) for SMP configuration information\n"); else if (acpi_lapic) - printk(KERN_INFO "Using ACPI for processor (LAPIC) " - "configuration information\n"); + pr_info("Using ACPI for processor (LAPIC) configuration information\n"); #endif return; } @@ -1323,8 +1304,7 @@ static void __init acpi_process_madt(void) static int __init disable_acpi_irq(const struct dmi_system_id *d) { if (!acpi_force) { - printk(KERN_NOTICE "%s detected: force use of acpi=noirq\n", - d->ident); + pr_notice("%s detected: force use of acpi=noirq\n", d->ident); acpi_noirq_set(); } return 0; @@ -1333,8 +1313,7 @@ static int __init disable_acpi_irq(const struct dmi_system_id *d) static int __init disable_acpi_pci(const struct dmi_system_id *d) { if (!acpi_force) { - printk(KERN_NOTICE "%s detected: force use of pci=noacpi\n", - d->ident); + pr_notice("%s detected: force use of pci=noacpi\n", d->ident); acpi_disable_pci(); } return 0; @@ -1343,11 +1322,10 @@ static int __init disable_acpi_pci(const struct dmi_system_id *d) static int __init dmi_disable_acpi(const struct dmi_system_id *d) { if (!acpi_force) { - printk(KERN_NOTICE "%s detected: acpi off\n", d->ident); + pr_notice("%s detected: acpi off\n", d->ident); disable_acpi(); } else { - printk(KERN_NOTICE - "Warning: DMI blacklist says broken, but acpi forced\n"); + pr_notice("Warning: DMI blacklist says broken, but acpi forced\n"); } return 0; } @@ -1574,9 +1552,9 @@ int __init early_acpi_boot_init(void) */ if (acpi_blacklisted()) { if (acpi_force) { - printk(KERN_WARNING PREFIX "acpi=force override\n"); + pr_warn("acpi=force override\n"); } else { - printk(KERN_WARNING PREFIX "Disabling ACPI support\n"); + pr_warn("Disabling ACPI support\n"); disable_acpi(); return 1; } @@ -1692,9 +1670,7 @@ int __init acpi_mps_check(void) #if defined(CONFIG_X86_LOCAL_APIC) && !defined(CONFIG_X86_MPPARSE) /* mptable code is not built-in*/ if (acpi_disabled || acpi_noirq) { - printk(KERN_WARNING "MPS support code is not built-in.\n" - "Using acpi=off or acpi=noirq or pci=noacpi " - "may have problem\n"); + pr_warn("MPS support code is not built-in, using acpi=off or acpi=noirq or pci=noacpi may have problem\n"); return 1; } #endif diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index bf7fe87a7e88..22791aadc085 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1257,19 +1257,28 @@ static void kill_me_maybe(struct callback_head *cb) { struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me); int flags = MF_ACTION_REQUIRED; + int ret; pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr); if (!p->mce_ripv) flags |= MF_MUST_KILL; - if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags) && - !(p->mce_kflags & MCE_IN_KERNEL_COPYIN)) { + ret = memory_failure(p->mce_addr >> PAGE_SHIFT, flags); + if (!ret && !(p->mce_kflags & MCE_IN_KERNEL_COPYIN)) { set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page); sync_core(); return; } + /* + * -EHWPOISON from memory_failure() means that it already sent SIGBUS + * to the current process with the proper error info, so no need to + * send SIGBUS here again. + */ + if (ret == -EHWPOISON) + return; + if (p->mce_vaddr != (void __user *)-1l) { force_sig_mceerr(BUS_MCEERR_AR, p->mce_vaddr, PAGE_SHIFT); } else { diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index c268c2730048..01ca94f42e4e 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -236,7 +236,7 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus) for_each_present_cpu(i) { if (i == 0) continue; - ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i)); + ret = hv_call_add_logical_proc(numa_cpu_node(i), i, i); BUG_ON(ret); } diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index 6e74f85b6264..fec43ca65065 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -91,8 +91,8 @@ static inline int sgx_encl_find(struct mm_struct *mm, unsigned long addr, { struct vm_area_struct *result; - result = find_vma(mm, addr); - if (!result || result->vm_ops != &sgx_vm_ops || addr < result->vm_start) + result = vma_lookup(mm, addr); + if (!result || result->vm_ops != &sgx_vm_ops) return -EINVAL; *vma = result; diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 6cce6047fa12..df0fa695bb09 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -315,11 +315,10 @@ void __init idt_setup_early_handler(void) /** * idt_invalidate - Invalidate interrupt descriptor table - * @addr: The virtual address of the 'invalid' IDT */ -void idt_invalidate(void *addr) +void idt_invalidate(void) { - struct desc_ptr idt = { .address = (unsigned long) addr, .size = 0 }; + static const struct desc_ptr idt = { .address = 0, .size = 0 }; load_idt(&idt); } diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 64b00b0d7fe8..1b373d79cedc 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -23,17 +23,6 @@ #include #include -static void set_gdt(void *newgdt, __u16 limit) -{ - struct desc_ptr curgdt; - - /* ia32 supports unaligned loads & stores */ - curgdt.size = limit; - curgdt.address = (unsigned long)newgdt; - - load_gdt(&curgdt); -} - static void load_segments(void) { #define __STR(X) #X @@ -232,8 +221,8 @@ void machine_kexec(struct kimage *image) * The gdt & idt are now invalid. * If you want to load them you must set up your own idt & gdt. */ - idt_invalidate(phys_to_virt(0)); - set_gdt(phys_to_virt(0), 0); + native_idt_invalidate(); + native_gdt_invalidate(); /* now call it */ image->start = relocate_kernel_ptr((unsigned long)image->head, diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index c078b0d3ab0e..131f30fdcfbd 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -256,35 +256,6 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) return init_transition_pgtable(image, level4p); } -static void set_idt(void *newidt, u16 limit) -{ - struct desc_ptr curidt; - - /* x86-64 supports unaligned loads & stores */ - curidt.size = limit; - curidt.address = (unsigned long)newidt; - - __asm__ __volatile__ ( - "lidtq %0\n" - : : "m" (curidt) - ); -}; - - -static void set_gdt(void *newgdt, u16 limit) -{ - struct desc_ptr curgdt; - - /* x86-64 supports unaligned loads & stores */ - curgdt.size = limit; - curgdt.address = (unsigned long)newgdt; - - __asm__ __volatile__ ( - "lgdtq %0\n" - : : "m" (curgdt) - ); -}; - static void load_segments(void) { __asm__ __volatile__ ( @@ -379,8 +350,8 @@ void machine_kexec(struct kimage *image) * The gdt & idt are now invalid. * If you want to load them you must set up your own idt & gdt. */ - set_gdt(phys_to_virt(0), 0); - set_idt(phys_to_virt(0), 0); + native_idt_invalidate(); + native_gdt_invalidate(); /* now call it */ image->start = relocate_kernel((unsigned long)image->head, diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index b29657b76e3f..ebfb91108232 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -669,7 +669,7 @@ static void native_machine_emergency_restart(void) break; case BOOT_TRIPLE: - idt_invalidate(NULL); + idt_invalidate(); __asm__ __volatile__("int3"); /* We're probably dead after this, but... */ diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 0941d2f44f2a..78a32b956e81 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -66,7 +66,7 @@ EXPORT_SYMBOL(__per_cpu_offset); */ static bool __init pcpu_need_numa(void) { -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA pg_data_t *last = NULL; unsigned int cpu; @@ -101,7 +101,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, unsigned long align) { const unsigned long goal = __pa(MAX_DMA_ADDRESS); -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA int node = early_cpu_to_node(cpu); void *ptr; @@ -140,7 +140,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size) static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) { -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA if (early_cpu_to_node(from) == early_cpu_to_node(to)) return LOCAL_DISTANCE; else diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 57ec01192180..2e076a459a0c 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1128,6 +1128,7 @@ static int tsc_cs_enable(struct clocksource *cs) static struct clocksource clocksource_tsc_early = { .name = "tsc-early", .rating = 299, + .uncertainty_margin = 32 * NSEC_PER_MSEC, .read = read_tsc, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | @@ -1152,7 +1153,8 @@ static struct clocksource clocksource_tsc = { .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_VALID_FOR_HRES | - CLOCK_SOURCE_MUST_VERIFY, + CLOCK_SOURCE_MUST_VERIFY | + CLOCK_SOURCE_VERIFY_PERCPU, .vdso_clock_mode = VDSO_CLOCKMODE_TSC, .enable = tsc_cs_enable, .resume = tsc_resume, diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 21ffb03f6c72..74b78840182d 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -651,7 +651,7 @@ void __init find_low_pfn_range(void) highmem_pfn_init(); } -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA void __init initmem_init(void) { #ifdef CONFIG_HIGHMEM @@ -677,7 +677,7 @@ void __init initmem_init(void) setup_bootmem_allocator(); } -#endif /* !CONFIG_NEED_MULTIPLE_NODES */ +#endif /* !CONFIG_NUMA */ void __init setup_bootmem_allocator(void) { diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 2a2e290fa5d8..e835164189f1 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -31,7 +31,7 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) } #define EMIT(bytes, len) \ - do { prog = emit_code(prog, bytes, len); cnt += len; } while (0) + do { prog = emit_code(prog, bytes, len); } while (0) #define EMIT1(b1) EMIT(b1, 1) #define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2) @@ -239,7 +239,6 @@ struct jit_context { static void push_callee_regs(u8 **pprog, bool *callee_regs_used) { u8 *prog = *pprog; - int cnt = 0; if (callee_regs_used[0]) EMIT1(0x53); /* push rbx */ @@ -255,7 +254,6 @@ static void push_callee_regs(u8 **pprog, bool *callee_regs_used) static void pop_callee_regs(u8 **pprog, bool *callee_regs_used) { u8 *prog = *pprog; - int cnt = 0; if (callee_regs_used[3]) EMIT2(0x41, 0x5F); /* pop r15 */ @@ -277,13 +275,12 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, bool tail_call_reachable, bool is_subprog) { u8 *prog = *pprog; - int cnt = X86_PATCH_SIZE; /* BPF trampoline can be made to work without these nops, * but let's waste 5 bytes for now and optimize later */ - memcpy(prog, x86_nops[5], cnt); - prog += cnt; + memcpy(prog, x86_nops[5], X86_PATCH_SIZE); + prog += X86_PATCH_SIZE; if (!ebpf_from_cbpf) { if (tail_call_reachable && !is_subprog) EMIT2(0x31, 0xC0); /* xor eax, eax */ @@ -303,7 +300,6 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, static int emit_patch(u8 **pprog, void *func, void *ip, u8 opcode) { u8 *prog = *pprog; - int cnt = 0; s64 offset; offset = func - (ip + X86_PATCH_SIZE); @@ -423,7 +419,6 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, int off1 = 42; int off2 = 31; int off3 = 9; - int cnt = 0; /* count the additional bytes used for popping callee regs from stack * that need to be taken into account for each of the offsets that @@ -513,7 +508,6 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, int pop_bytes = 0; int off1 = 20; int poke_off; - int cnt = 0; /* count the additional bytes used for popping callee regs to stack * that need to be taken into account for jump offset that is used for @@ -615,7 +609,6 @@ static void emit_mov_imm32(u8 **pprog, bool sign_propagate, { u8 *prog = *pprog; u8 b1, b2, b3; - int cnt = 0; /* * Optimization: if imm32 is positive, use 'mov %eax, imm32' @@ -655,7 +648,6 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg, const u32 imm32_hi, const u32 imm32_lo) { u8 *prog = *pprog; - int cnt = 0; if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) { /* @@ -678,7 +670,6 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg, static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg) { u8 *prog = *pprog; - int cnt = 0; if (is64) { /* mov dst, src */ @@ -697,7 +688,6 @@ static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg) static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off) { u8 *prog = *pprog; - int cnt = 0; if (is_imm8(off)) { /* 1-byte signed displacement. @@ -720,7 +710,6 @@ static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off) static void maybe_emit_mod(u8 **pprog, u32 dst_reg, u32 src_reg, bool is64) { u8 *prog = *pprog; - int cnt = 0; if (is64) EMIT1(add_2mod(0x48, dst_reg, src_reg)); @@ -733,7 +722,6 @@ static void maybe_emit_mod(u8 **pprog, u32 dst_reg, u32 src_reg, bool is64) static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { u8 *prog = *pprog; - int cnt = 0; switch (size) { case BPF_B: @@ -764,7 +752,6 @@ static void emit_ldx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { u8 *prog = *pprog; - int cnt = 0; switch (size) { case BPF_B: @@ -799,7 +786,6 @@ static int emit_atomic(u8 **pprog, u8 atomic_op, u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size) { u8 *prog = *pprog; - int cnt = 0; EMIT1(0xF0); /* lock prefix */ @@ -869,10 +855,10 @@ static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt, } } -static int emit_nops(u8 **pprog, int len) +static void emit_nops(u8 **pprog, int len) { u8 *prog = *pprog; - int i, noplen, cnt = 0; + int i, noplen; while (len > 0) { noplen = len; @@ -886,8 +872,6 @@ static int emit_nops(u8 **pprog, int len) } *pprog = prog; - - return cnt; } #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp))) @@ -902,7 +886,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, bool tail_call_seen = false; bool seen_exit = false; u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; - int i, cnt = 0, excnt = 0; + int i, excnt = 0; int ilen, proglen = 0; u8 *prog = temp; int err; @@ -1297,7 +1281,7 @@ st: if (is_imm8(insn->off)) emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { struct exception_table_entry *ex; - u8 *_insn = image + proglen; + u8 *_insn = image + proglen + (start_of_ldx - temp); s64 delta; /* populate jmp_offset for JMP above */ @@ -1576,7 +1560,7 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ nops); return -EFAULT; } - cnt += emit_nops(&prog, nops); + emit_nops(&prog, nops); } EMIT2(jmp_cond, jmp_offset); } else if (is_simm32(jmp_offset)) { @@ -1622,7 +1606,7 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ nops); return -EFAULT; } - cnt += emit_nops(&prog, nops); + emit_nops(&prog, nops); } break; } @@ -1647,7 +1631,7 @@ emit_jmp: nops); return -EFAULT; } - cnt += emit_nops(&prog, INSN_SZ_DIFF - 2); + emit_nops(&prog, INSN_SZ_DIFF - 2); } EMIT2(0xEB, jmp_offset); } else if (is_simm32(jmp_offset)) { @@ -1754,7 +1738,6 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, { u8 *prog = *pprog; u8 *jmp_insn; - int cnt = 0; /* arg1: mov rdi, progs[i] */ emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p); @@ -1822,7 +1805,6 @@ static void emit_align(u8 **pprog, u32 align) static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) { u8 *prog = *pprog; - int cnt = 0; s64 offset; offset = func - (ip + 2 + 4); @@ -1854,7 +1836,7 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, u8 **branches) { u8 *prog = *pprog; - int i, cnt = 0; + int i; /* The first fmod_ret program will receive a garbage return value. * Set this to 0 to avoid confusing the program. @@ -1950,7 +1932,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i struct bpf_tramp_progs *tprogs, void *orig_call) { - int ret, i, cnt = 0, nr_args = m->nr_args; + int ret, i, nr_args = m->nr_args; int stack_size = nr_args * 8; struct bpf_tramp_progs *fentry = &tprogs[BPF_TRAMP_FENTRY]; struct bpf_tramp_progs *fexit = &tprogs[BPF_TRAMP_FEXIT]; @@ -2095,8 +2077,6 @@ static int emit_fallback_jump(u8 **pprog) */ err = emit_jump(&prog, __x86_indirect_thunk_rdx, prog); #else - int cnt = 0; - EMIT2(0xFF, 0xE2); /* jmp rdx */ #endif *pprog = prog; @@ -2106,7 +2086,7 @@ static int emit_fallback_jump(u8 **pprog) static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) { u8 *jg_reloc, *prog = *pprog; - int pivot, err, jg_bytes = 1, cnt = 0; + int pivot, err, jg_bytes = 1; s64 jg_offset; if (a == b) { diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 2ed81e581755..0575decb5e54 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -7,7 +7,6 @@ #include #include #include -#include #include #define __NO_STUBS @@ -26,20 +25,17 @@ #define old_mmap sys_old_mmap -#define __SYSCALL_I386(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) + +#define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include -#undef __SYSCALL_I386 -#define __SYSCALL_I386(nr, sym) [ nr ] = sym, +#undef __SYSCALL +#define __SYSCALL(nr, sym) sym, extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { - /* - * Smells like a compiler bug -- it doesn't work - * when the & below is removed. - */ - [0 ... __NR_syscall_max] = &sys_ni_syscall, #include }; diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index 2e8544dafbb0..95725b5a41ac 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -7,7 +7,6 @@ #include #include #include -#include #include #define __NO_STUBS @@ -36,23 +35,15 @@ #define stub_execveat sys_execveat #define stub_rt_sigreturn sys_rt_sigreturn -#define __SYSCALL_X32(nr, sym) -#define __SYSCALL_COMMON(nr, sym) __SYSCALL_64(nr, sym) - -#define __SYSCALL_64(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; +#define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #include -#undef __SYSCALL_64 -#define __SYSCALL_64(nr, sym) [ nr ] = sym, +#undef __SYSCALL +#define __SYSCALL(nr, sym) sym, extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { - /* - * Smells like a compiler bug -- it doesn't work - * when the & below is removed. - */ - [0 ... __NR_syscall_max] = &sys_ni_syscall, #include }; diff --git a/arch/xtensa/include/asm/page.h b/arch/xtensa/include/asm/page.h index 37ce25ef92d6..493eb7083b1a 100644 --- a/arch/xtensa/include/asm/page.h +++ b/arch/xtensa/include/asm/page.h @@ -192,10 +192,6 @@ static inline unsigned long ___pa(unsigned long va) #define pfn_valid(pfn) \ ((pfn) >= ARCH_PFN_OFFSET && ((pfn) - ARCH_PFN_OFFSET) < max_mapnr) -#ifdef CONFIG_DISCONTIGMEM -# error CONFIG_DISCONTIGMEM not supported -#endif - #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) #define page_to_virt(page) __va(page_to_pfn(page) << PAGE_SHIFT) #define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) diff --git a/arch/xtensa/include/asm/tlbflush.h b/arch/xtensa/include/asm/tlbflush.h index 856e2da2e397..573df8cea200 100644 --- a/arch/xtensa/include/asm/tlbflush.h +++ b/arch/xtensa/include/asm/tlbflush.h @@ -26,8 +26,8 @@ * * - flush_tlb_all() flushes all processes TLB entries * - flush_tlb_mm(mm) flushes the specified mm context TLB entries - * - flush_tlb_page(mm, vmaddr) flushes a single page - * - flush_tlb_range(mm, start, end) flushes a range of pages + * - flush_tlb_page(vma, page) flushes a single page + * - flush_tlb_range(vma, vmaddr, end) flushes a range of pages */ void local_flush_tlb_all(void); diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index fd2f30227d96..235d67d6ceb4 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -413,7 +413,7 @@ 440 common process_madvise sys_process_madvise 441 common epoll_pwait2 sys_epoll_pwait2 442 common mount_setattr sys_mount_setattr -# 443 reserved for quotactl_path +443 common quotactl_fd sys_quotactl_fd 444 common landlock_create_ruleset sys_landlock_create_ruleset 445 common landlock_add_rule sys_landlock_add_rule 446 common landlock_restrict_self sys_landlock_restrict_self diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index fc09be7b1347..3cdfa00738e0 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -27,7 +27,6 @@ struct simdisk { const char *filename; spinlock_t lock; - struct request_queue *queue; struct gendisk *gd; struct proc_dir_entry *procfile; int users; @@ -266,21 +265,13 @@ static int __init simdisk_setup(struct simdisk *dev, int which, spin_lock_init(&dev->lock); dev->users = 0; - dev->queue = blk_alloc_queue(NUMA_NO_NODE); - if (dev->queue == NULL) { - pr_err("blk_alloc_queue failed\n"); - goto out_alloc_queue; - } - - dev->gd = alloc_disk(SIMDISK_MINORS); - if (dev->gd == NULL) { - pr_err("alloc_disk failed\n"); - goto out_alloc_disk; - } + dev->gd = blk_alloc_disk(NUMA_NO_NODE); + if (!dev->gd) + return -ENOMEM; dev->gd->major = simdisk_major; dev->gd->first_minor = which; + dev->gd->minors = SIMDISK_MINORS; dev->gd->fops = &simdisk_ops; - dev->gd->queue = dev->queue; dev->gd->private_data = dev; snprintf(dev->gd->disk_name, 32, "simdisk%d", which); set_capacity(dev->gd, 0); @@ -288,12 +279,6 @@ static int __init simdisk_setup(struct simdisk *dev, int which, dev->procfile = proc_create_data(tmp, 0644, procdir, &simdisk_proc_ops, dev); return 0; - -out_alloc_disk: - blk_cleanup_queue(dev->queue); - dev->queue = NULL; -out_alloc_queue: - return -ENOMEM; } static int __init simdisk_init(void) @@ -343,10 +328,10 @@ static void simdisk_teardown(struct simdisk *dev, int which, char tmp[2] = { '0' + which, 0 }; simdisk_detach(dev); - if (dev->gd) + if (dev->gd) { del_gendisk(dev->gd); - if (dev->queue) - blk_cleanup_queue(dev->queue); + blk_cleanup_disk(dev->gd); + } remove_proc_entry(tmp, procdir); } diff --git a/block/Kconfig b/block/Kconfig index e657e2bd8059..aabfb8588e9d 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -133,6 +133,13 @@ config BLK_WBT dynamically on an algorithm loosely based on CoDel, factoring in the realtime performance of the disk. +config BLK_WBT_MQ + bool "Enable writeback throttling by default" + default y + depends on BLK_WBT + help + Enable writeback throttling by default for request-based block devices. + config BLK_CGROUP_IOLATENCY bool "Enable support for latency based cgroup IO protection" depends on BLK_CGROUP=y @@ -155,12 +162,14 @@ config BLK_CGROUP_IOCOST distributes IO capacity between different groups based on their share of the overall weight distribution. -config BLK_WBT_MQ - bool "Multiqueue writeback throttling" - default y - depends on BLK_WBT +config BLK_CGROUP_IOPRIO + bool "Cgroup I/O controller for assigning an I/O priority class" + depends on BLK_CGROUP help - Enable writeback throttling by default on multiqueue devices. + Enable the .prio interface for assigning an I/O priority class to + requests. The I/O priority class affects the order in which an I/O + scheduler and block devices process requests. Only some I/O schedulers + and some block devices support I/O priorities. config BLK_DEBUG_FS bool "Block layer debugging information in debugfs" diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index 2f2158e05a91..64053d67a97b 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -9,6 +9,12 @@ config MQ_IOSCHED_DEADLINE help MQ version of the deadline IO scheduler. +config MQ_IOSCHED_DEADLINE_CGROUP + tristate + default y + depends on MQ_IOSCHED_DEADLINE + depends on BLK_CGROUP + config MQ_IOSCHED_KYBER tristate "Kyber I/O scheduler" default y diff --git a/block/Makefile b/block/Makefile index 8d841f5f986f..bfbe4e13ca1e 100644 --- a/block/Makefile +++ b/block/Makefile @@ -8,7 +8,8 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \ blk-exec.o blk-merge.o blk-timeout.o \ blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \ blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \ - genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o + genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \ + disk-events.o obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_BLK_SCSI_REQUEST) += scsi_ioctl.o @@ -17,9 +18,12 @@ obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o obj-$(CONFIG_BLK_CGROUP_RWSTAT) += blk-cgroup-rwstat.o obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o +obj-$(CONFIG_BLK_CGROUP_IOPRIO) += blk-ioprio.o obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o obj-$(CONFIG_BLK_CGROUP_IOCOST) += blk-iocost.o obj-$(CONFIG_MQ_IOSCHED_DEADLINE) += mq-deadline.o +mq-deadline-y += mq-deadline-main.o +mq-deadline-$(CONFIG_MQ_IOSCHED_DEADLINE_CGROUP)+= mq-deadline-cgroup.o obj-$(CONFIG_MQ_IOSCHED_KYBER) += kyber-iosched.o bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o obj-$(CONFIG_IOSCHED_BFQ) += bfq.o diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index acd1f881273e..727955918563 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -364,6 +364,16 @@ static int ref_wr_duration[2]; */ static const unsigned long max_service_from_wr = 120000; +/* + * Maximum time between the creation of two queues, for stable merge + * to be activated (in ms) + */ +static const unsigned long bfq_activation_stable_merging = 600; +/* + * Minimum time to be waited before evaluating delayed stable merge (in ms) + */ +static const unsigned long bfq_late_stable_merging = 600; + #define RQ_BIC(rq) icq_to_bic((rq)->elv.priv[0]) #define RQ_BFQQ(rq) ((rq)->elv.priv[1]) @@ -1729,10 +1739,23 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, bfqq->entity.new_weight == 40; *interactive = !in_burst && idle_for_long_time && bfqq->entity.new_weight == 40; + /* + * Merged bfq_queues are kept out of weight-raising + * (low-latency) mechanisms. The reason is that these queues + * are usually created for non-interactive and + * non-soft-real-time tasks. Yet this is not the case for + * stably-merged queues. These queues are merged just because + * they are created shortly after each other. So they may + * easily serve the I/O of an interactive or soft-real time + * application, if the application happens to spawn multiple + * processes. So let also stably-merged queued enjoy weight + * raising. + */ wr_or_deserves_wr = bfqd->low_latency && (bfqq->wr_coeff > 1 || (bfq_bfqq_sync(bfqq) && - bfqq->bic && (*interactive || soft_rt))); + (bfqq->bic || RQ_BIC(rq)->stably_merged) && + (*interactive || soft_rt))); /* * Using the last flag, update budget and check whether bfqq @@ -1962,14 +1985,18 @@ static void bfq_update_io_intensity(struct bfq_queue *bfqq, u64 now_ns) * Turning back to the detection of a waker queue, a queue Q is deemed * as a waker queue for bfqq if, for three consecutive times, bfqq * happens to become non empty right after a request of Q has been - * completed. In particular, on the first time, Q is tentatively set - * as a candidate waker queue, while on the third consecutive time - * that Q is detected, the field waker_bfqq is set to Q, to confirm - * that Q is a waker queue for bfqq. These detection steps are - * performed only if bfqq has a long think time, so as to make it more - * likely that bfqq's I/O is actually being blocked by a - * synchronization. This last filter, plus the above three-times - * requirement, make false positives less likely. + * completed. In this respect, even if bfqq is empty, we do not check + * for a waker if it still has some in-flight I/O. In fact, in this + * case bfqq is actually still being served by the drive, and may + * receive new I/O on the completion of some of the in-flight + * requests. In particular, on the first time, Q is tentatively set as + * a candidate waker queue, while on the third consecutive time that Q + * is detected, the field waker_bfqq is set to Q, to confirm that Q is + * a waker queue for bfqq. These detection steps are performed only if + * bfqq has a long think time, so as to make it more likely that + * bfqq's I/O is actually being blocked by a synchronization. This + * last filter, plus the above three-times requirement, make false + * positives less likely. * * NOTE * @@ -1995,6 +2022,7 @@ static void bfq_check_waker(struct bfq_data *bfqd, struct bfq_queue *bfqq, if (!bfqd->last_completed_rq_bfqq || bfqd->last_completed_rq_bfqq == bfqq || bfq_bfqq_has_short_ttime(bfqq) || + bfqq->dispatched > 0 || now_ns - bfqd->last_completion >= 4 * NSEC_PER_MSEC || bfqd->last_completed_rq_bfqq == bfqq->waker_bfqq) return; @@ -2317,9 +2345,9 @@ static bool bfq_bio_merge(struct request_queue *q, struct bio *bio, ret = blk_mq_sched_try_merge(q, bio, nr_segs, &free); + spin_unlock_irq(&bfqd->lock); if (free) blk_mq_free_request(free); - spin_unlock_irq(&bfqd->lock); return ret; } @@ -2405,7 +2433,7 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq, *next_bfqq = bfq_init_rq(next); if (!bfqq) - return; + goto remove; /* * If next and rq belong to the same bfq_queue and next is older @@ -2428,6 +2456,14 @@ static void bfq_requests_merged(struct request_queue *q, struct request *rq, bfqq->next_rq = rq; bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags); +remove: + /* Merged request may be in the IO scheduler. Remove it. */ + if (!RB_EMPTY_NODE(&next->rb_node)) { + bfq_remove_request(next->q, next); + if (next_bfqq) + bfqg_stats_update_io_remove(bfqq_group(next_bfqq), + next->cmd_flags); + } } /* Must be called with bfqq != NULL */ @@ -2695,10 +2731,18 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, * costly and complicated. */ if (unlikely(!bfqd->nonrot_with_queueing)) { - if (bic->stable_merge_bfqq && + /* + * Make sure also that bfqq is sync, because + * bic->stable_merge_bfqq may point to some queue (for + * stable merging) also if bic is associated with a + * sync queue, but this bfqq is async + */ + if (bfq_bfqq_sync(bfqq) && bic->stable_merge_bfqq && !bfq_bfqq_just_created(bfqq) && - time_is_after_jiffies(bfqq->split_time + - msecs_to_jiffies(200))) { + time_is_before_jiffies(bfqq->split_time + + msecs_to_jiffies(bfq_late_stable_merging)) && + time_is_before_jiffies(bfqq->creation_time + + msecs_to_jiffies(bfq_late_stable_merging))) { struct bfq_queue *stable_merge_bfqq = bic->stable_merge_bfqq; int proc_ref = min(bfqq_process_refs(bfqq), @@ -5479,7 +5523,7 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd, */ if (!last_bfqq_created || time_before(last_bfqq_created->creation_time + - bfqd->bfq_burst_interval, + msecs_to_jiffies(bfq_activation_stable_merging), bfqq->creation_time) || bfqq->entity.parent != last_bfqq_created->entity.parent || bfqq->ioprio != last_bfqq_created->ioprio || @@ -5925,14 +5969,16 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, struct bfq_queue *bfqq; bool idle_timer_disabled = false; unsigned int cmd_flags; + LIST_HEAD(free); #ifdef CONFIG_BFQ_GROUP_IOSCHED if (!cgroup_subsys_on_dfl(io_cgrp_subsys) && rq->bio) bfqg_stats_update_legacy_io(q, rq); #endif spin_lock_irq(&bfqd->lock); - if (blk_mq_sched_try_insert_merge(q, rq)) { + if (blk_mq_sched_try_insert_merge(q, rq, &free)) { spin_unlock_irq(&bfqd->lock); + blk_mq_free_requests(&free); return; } @@ -6129,11 +6175,13 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd) * of other queues. But a false waker will unjustly steal * bandwidth to its supposedly woken queue. So considering * also shared queues in the waking mechanism may cause more - * control troubles than throughput benefits. Then do not set - * last_completed_rq_bfqq to bfqq if bfqq is a shared queue. + * control troubles than throughput benefits. Then reset + * last_completed_rq_bfqq if bfqq is a shared queue. */ if (!bfq_bfqq_coop(bfqq)) bfqd->last_completed_rq_bfqq = bfqq; + else + bfqd->last_completed_rq_bfqq = NULL; /* * If we are waiting to discover whether the request pattern @@ -6376,6 +6424,7 @@ static void bfq_finish_requeue_request(struct request *rq) { struct bfq_queue *bfqq = RQ_BFQQ(rq); struct bfq_data *bfqd; + unsigned long flags; /* * rq either is not associated with any icq, or is an already @@ -6393,39 +6442,15 @@ static void bfq_finish_requeue_request(struct request *rq) rq->io_start_time_ns, rq->cmd_flags); + spin_lock_irqsave(&bfqd->lock, flags); if (likely(rq->rq_flags & RQF_STARTED)) { - unsigned long flags; - - spin_lock_irqsave(&bfqd->lock, flags); - if (rq == bfqd->waited_rq) bfq_update_inject_limit(bfqd, bfqq); bfq_completed_request(bfqq, bfqd); - bfq_finish_requeue_request_body(bfqq); - - spin_unlock_irqrestore(&bfqd->lock, flags); - } else { - /* - * Request rq may be still/already in the scheduler, - * in which case we need to remove it (this should - * never happen in case of requeue). And we cannot - * defer such a check and removal, to avoid - * inconsistencies in the time interval from the end - * of this function to the start of the deferred work. - * This situation seems to occur only in process - * context, as a consequence of a merge. In the - * current version of the code, this implies that the - * lock is held. - */ - - if (!RB_EMPTY_NODE(&rq->rb_node)) { - bfq_remove_request(rq->q, rq); - bfqg_stats_update_io_remove(bfqq_group(bfqq), - rq->cmd_flags); - } - bfq_finish_requeue_request_body(bfqq); } + bfq_finish_requeue_request_body(bfqq); + spin_unlock_irqrestore(&bfqd->lock, flags); /* * Reset private fields. In case of a requeue, this allows diff --git a/block/bio.c b/block/bio.c index 44205dfb6b60..1fab762e079b 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1375,8 +1375,7 @@ static inline bool bio_remaining_done(struct bio *bio) * * bio_endio() can be called several times on a bio that has been chained * using bio_chain(). The ->bi_end_io() function will only be called the - * last time. At this point the BLK_TA_COMPLETE tracing event will be - * generated if BIO_TRACE_COMPLETION is set. + * last time. **/ void bio_endio(struct bio *bio) { @@ -1389,6 +1388,11 @@ again: if (bio->bi_bdev) rq_qos_done_bio(bio->bi_bdev->bd_disk->queue, bio); + if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) { + trace_block_bio_complete(bio->bi_bdev->bd_disk->queue, bio); + bio_clear_flag(bio, BIO_TRACE_COMPLETION); + } + /* * Need to have a real endio function for chained bios, otherwise * various corner cases will break (like stacking block devices that @@ -1402,11 +1406,6 @@ again: goto again; } - if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) { - trace_block_bio_complete(bio->bi_bdev->bd_disk->queue, bio); - bio_clear_flag(bio, BIO_TRACE_COMPLETION); - } - blk_throtl_bio_endio(bio); /* release cgroup info */ bio_uninit(bio); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 582d2f18717e..7b06a5fa3cac 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -31,6 +31,7 @@ #include #include #include "blk.h" +#include "blk-ioprio.h" /* * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation. @@ -1183,15 +1184,18 @@ int blkcg_init_queue(struct request_queue *q) if (preloaded) radix_tree_preload_end(); + ret = blk_iolatency_init(q); + if (ret) + goto err_destroy_all; + + ret = blk_ioprio_init(q); + if (ret) + goto err_destroy_all; + ret = blk_throtl_init(q); if (ret) goto err_destroy_all; - ret = blk_iolatency_init(q); - if (ret) { - blk_throtl_exit(q); - goto err_destroy_all; - } return 0; err_destroy_all: @@ -1217,32 +1221,6 @@ void blkcg_exit_queue(struct request_queue *q) blk_throtl_exit(q); } -/* - * We cannot support shared io contexts, as we have no mean to support - * two tasks with the same ioc in two different groups without major rework - * of the main cic data structures. For now we allow a task to change - * its cgroup only if it's the only owner of its ioc. - */ -static int blkcg_can_attach(struct cgroup_taskset *tset) -{ - struct task_struct *task; - struct cgroup_subsys_state *dst_css; - struct io_context *ioc; - int ret = 0; - - /* task_lock() is needed to avoid races with exit_io_context() */ - cgroup_taskset_for_each(task, dst_css, tset) { - task_lock(task); - ioc = task->io_context; - if (ioc && atomic_read(&ioc->nr_tasks) > 1) - ret = -EINVAL; - task_unlock(task); - if (ret) - break; - } - return ret; -} - static void blkcg_bind(struct cgroup_subsys_state *root_css) { int i; @@ -1275,7 +1253,6 @@ struct cgroup_subsys io_cgrp_subsys = { .css_online = blkcg_css_online, .css_offline = blkcg_css_offline, .css_free = blkcg_css_free, - .can_attach = blkcg_can_attach, .css_rstat_flush = blkcg_rstat_flush, .bind = blkcg_bind, .dfl_cftypes = blkcg_files, diff --git a/block/blk-core.c b/block/blk-core.c index 9bcdae93f6d4..514838ccab2d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -599,7 +599,6 @@ fail_q: kmem_cache_free(blk_requestq_cachep, q); return NULL; } -EXPORT_SYMBOL(blk_alloc_queue); /** * blk_get_queue - increment the request_queue refcount @@ -1086,15 +1085,6 @@ blk_qc_t submit_bio(struct bio *bio) task_io_account_read(bio->bi_iter.bi_size); count_vm_events(PGPGIN, count); } - - if (unlikely(block_dump)) { - char b[BDEVNAME_SIZE]; - printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n", - current->comm, task_pid_nr(current), - op_is_write(bio_op(bio)) ? "WRITE" : "READ", - (unsigned long long)bio->bi_iter.bi_sector, - bio_devname(bio, b), count); - } } /* @@ -1394,26 +1384,22 @@ void blk_steal_bios(struct bio_list *list, struct request *rq) EXPORT_SYMBOL_GPL(blk_steal_bios); /** - * blk_update_request - Special helper function for request stacking drivers + * blk_update_request - Complete multiple bytes without completing the request * @req: the request being processed * @error: block status code - * @nr_bytes: number of bytes to complete @req + * @nr_bytes: number of bytes to complete for @req * * Description: * Ends I/O on a number of bytes attached to @req, but doesn't complete * the request structure even if @req doesn't have leftover. * If @req has leftover, sets it up for the next range of segments. * - * This special helper function is only for request stacking drivers - * (e.g. request-based dm) so that they can handle partial completion. - * Actual device drivers should use blk_mq_end_request instead. - * * Passing the result of blk_rq_bytes() as @nr_bytes guarantees * %false return from this function. * * Note: - * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in both - * blk_rq_bytes() and in blk_update_request(). + * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in this function + * except in the consistency check at the end of this function. * * Return: * %false - this request doesn't have any more data diff --git a/block/blk-flush.c b/block/blk-flush.c index 7942ca6ed321..1002f6c58181 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -219,8 +219,6 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) unsigned long flags = 0; struct blk_flush_queue *fq = blk_get_flush_queue(q, flush_rq->mq_ctx); - blk_account_io_flush(flush_rq); - /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); @@ -230,6 +228,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) return; } + blk_account_io_flush(flush_rq); /* * Flush request has to be marked as IDLE when it is really ended * because its .end_io() is called from timeout code path too for diff --git a/block/blk-ioprio.c b/block/blk-ioprio.c new file mode 100644 index 000000000000..332a07761bf8 --- /dev/null +++ b/block/blk-ioprio.c @@ -0,0 +1,262 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Block rq-qos policy for assigning an I/O priority class to requests. + * + * Using an rq-qos policy for assigning I/O priority class has two advantages + * over using the ioprio_set() system call: + * + * - This policy is cgroup based so it has all the advantages of cgroups. + * - While ioprio_set() does not affect page cache writeback I/O, this rq-qos + * controller affects page cache writeback I/O for filesystems that support + * assiociating a cgroup with writeback I/O. See also + * Documentation/admin-guide/cgroup-v2.rst. + */ + +#include +#include +#include +#include +#include +#include "blk-ioprio.h" +#include "blk-rq-qos.h" + +/** + * enum prio_policy - I/O priority class policy. + * @POLICY_NO_CHANGE: (default) do not modify the I/O priority class. + * @POLICY_NONE_TO_RT: modify IOPRIO_CLASS_NONE into IOPRIO_CLASS_RT. + * @POLICY_RESTRICT_TO_BE: modify IOPRIO_CLASS_NONE and IOPRIO_CLASS_RT into + * IOPRIO_CLASS_BE. + * @POLICY_ALL_TO_IDLE: change the I/O priority class into IOPRIO_CLASS_IDLE. + * + * See also . + */ +enum prio_policy { + POLICY_NO_CHANGE = 0, + POLICY_NONE_TO_RT = 1, + POLICY_RESTRICT_TO_BE = 2, + POLICY_ALL_TO_IDLE = 3, +}; + +static const char *policy_name[] = { + [POLICY_NO_CHANGE] = "no-change", + [POLICY_NONE_TO_RT] = "none-to-rt", + [POLICY_RESTRICT_TO_BE] = "restrict-to-be", + [POLICY_ALL_TO_IDLE] = "idle", +}; + +static struct blkcg_policy ioprio_policy; + +/** + * struct ioprio_blkg - Per (cgroup, request queue) data. + * @pd: blkg_policy_data structure. + */ +struct ioprio_blkg { + struct blkg_policy_data pd; +}; + +/** + * struct ioprio_blkcg - Per cgroup data. + * @cpd: blkcg_policy_data structure. + * @prio_policy: One of the IOPRIO_CLASS_* values. See also . + */ +struct ioprio_blkcg { + struct blkcg_policy_data cpd; + enum prio_policy prio_policy; +}; + +static inline struct ioprio_blkg *pd_to_ioprio(struct blkg_policy_data *pd) +{ + return pd ? container_of(pd, struct ioprio_blkg, pd) : NULL; +} + +static struct ioprio_blkcg *blkcg_to_ioprio_blkcg(struct blkcg *blkcg) +{ + return container_of(blkcg_to_cpd(blkcg, &ioprio_policy), + struct ioprio_blkcg, cpd); +} + +static struct ioprio_blkcg * +ioprio_blkcg_from_css(struct cgroup_subsys_state *css) +{ + return blkcg_to_ioprio_blkcg(css_to_blkcg(css)); +} + +static struct ioprio_blkcg *ioprio_blkcg_from_bio(struct bio *bio) +{ + struct blkg_policy_data *pd = blkg_to_pd(bio->bi_blkg, &ioprio_policy); + + if (!pd) + return NULL; + + return blkcg_to_ioprio_blkcg(pd->blkg->blkcg); +} + +static int ioprio_show_prio_policy(struct seq_file *sf, void *v) +{ + struct ioprio_blkcg *blkcg = ioprio_blkcg_from_css(seq_css(sf)); + + seq_printf(sf, "%s\n", policy_name[blkcg->prio_policy]); + return 0; +} + +static ssize_t ioprio_set_prio_policy(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct ioprio_blkcg *blkcg = ioprio_blkcg_from_css(of_css(of)); + int ret; + + if (off != 0) + return -EIO; + /* kernfs_fop_write_iter() terminates 'buf' with '\0'. */ + ret = sysfs_match_string(policy_name, buf); + if (ret < 0) + return ret; + blkcg->prio_policy = ret; + + return nbytes; +} + +static struct blkg_policy_data * +ioprio_alloc_pd(gfp_t gfp, struct request_queue *q, struct blkcg *blkcg) +{ + struct ioprio_blkg *ioprio_blkg; + + ioprio_blkg = kzalloc(sizeof(*ioprio_blkg), gfp); + if (!ioprio_blkg) + return NULL; + + return &ioprio_blkg->pd; +} + +static void ioprio_free_pd(struct blkg_policy_data *pd) +{ + struct ioprio_blkg *ioprio_blkg = pd_to_ioprio(pd); + + kfree(ioprio_blkg); +} + +static struct blkcg_policy_data *ioprio_alloc_cpd(gfp_t gfp) +{ + struct ioprio_blkcg *blkcg; + + blkcg = kzalloc(sizeof(*blkcg), gfp); + if (!blkcg) + return NULL; + blkcg->prio_policy = POLICY_NO_CHANGE; + return &blkcg->cpd; +} + +static void ioprio_free_cpd(struct blkcg_policy_data *cpd) +{ + struct ioprio_blkcg *blkcg = container_of(cpd, typeof(*blkcg), cpd); + + kfree(blkcg); +} + +#define IOPRIO_ATTRS \ + { \ + .name = "prio.class", \ + .seq_show = ioprio_show_prio_policy, \ + .write = ioprio_set_prio_policy, \ + }, \ + { } /* sentinel */ + +/* cgroup v2 attributes */ +static struct cftype ioprio_files[] = { + IOPRIO_ATTRS +}; + +/* cgroup v1 attributes */ +static struct cftype ioprio_legacy_files[] = { + IOPRIO_ATTRS +}; + +static struct blkcg_policy ioprio_policy = { + .dfl_cftypes = ioprio_files, + .legacy_cftypes = ioprio_legacy_files, + + .cpd_alloc_fn = ioprio_alloc_cpd, + .cpd_free_fn = ioprio_free_cpd, + + .pd_alloc_fn = ioprio_alloc_pd, + .pd_free_fn = ioprio_free_pd, +}; + +struct blk_ioprio { + struct rq_qos rqos; +}; + +static void blkcg_ioprio_track(struct rq_qos *rqos, struct request *rq, + struct bio *bio) +{ + struct ioprio_blkcg *blkcg = ioprio_blkcg_from_bio(bio); + + /* + * Except for IOPRIO_CLASS_NONE, higher I/O priority numbers + * correspond to a lower priority. Hence, the max_t() below selects + * the lower priority of bi_ioprio and the cgroup I/O priority class. + * If the cgroup policy has been set to POLICY_NO_CHANGE == 0, the + * bio I/O priority is not modified. If the bio I/O priority equals + * IOPRIO_CLASS_NONE, the cgroup I/O priority is assigned to the bio. + */ + bio->bi_ioprio = max_t(u16, bio->bi_ioprio, + IOPRIO_PRIO_VALUE(blkcg->prio_policy, 0)); +} + +static void blkcg_ioprio_exit(struct rq_qos *rqos) +{ + struct blk_ioprio *blkioprio_blkg = + container_of(rqos, typeof(*blkioprio_blkg), rqos); + + blkcg_deactivate_policy(rqos->q, &ioprio_policy); + kfree(blkioprio_blkg); +} + +static struct rq_qos_ops blkcg_ioprio_ops = { + .track = blkcg_ioprio_track, + .exit = blkcg_ioprio_exit, +}; + +int blk_ioprio_init(struct request_queue *q) +{ + struct blk_ioprio *blkioprio_blkg; + struct rq_qos *rqos; + int ret; + + blkioprio_blkg = kzalloc(sizeof(*blkioprio_blkg), GFP_KERNEL); + if (!blkioprio_blkg) + return -ENOMEM; + + ret = blkcg_activate_policy(q, &ioprio_policy); + if (ret) { + kfree(blkioprio_blkg); + return ret; + } + + rqos = &blkioprio_blkg->rqos; + rqos->id = RQ_QOS_IOPRIO; + rqos->ops = &blkcg_ioprio_ops; + rqos->q = q; + + /* + * Registering the rq-qos policy after activating the blk-cgroup + * policy guarantees that ioprio_blkcg_from_bio(bio) != NULL in the + * rq-qos callbacks. + */ + rq_qos_add(q, rqos); + + return 0; +} + +static int __init ioprio_init(void) +{ + return blkcg_policy_register(&ioprio_policy); +} + +static void __exit ioprio_exit(void) +{ + blkcg_policy_unregister(&ioprio_policy); +} + +module_init(ioprio_init); +module_exit(ioprio_exit); diff --git a/block/blk-ioprio.h b/block/blk-ioprio.h new file mode 100644 index 000000000000..a7785c2f1aea --- /dev/null +++ b/block/blk-ioprio.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _BLK_IOPRIO_H_ +#define _BLK_IOPRIO_H_ + +#include + +struct request_queue; + +#ifdef CONFIG_BLK_CGROUP_IOPRIO +int blk_ioprio_init(struct request_queue *q); +#else +static inline int blk_ioprio_init(struct request_queue *q) +{ + return 0; +} +#endif + +#endif /* _BLK_IOPRIO_H_ */ diff --git a/block/blk-lib.c b/block/blk-lib.c index 7b256131b20b..9f09beadcbe3 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -21,6 +21,7 @@ struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp) return new; } +EXPORT_SYMBOL_GPL(blk_next_bio); int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, int flags, diff --git a/block/blk-merge.c b/block/blk-merge.c index 4d97fb6dd226..a11b3b53717e 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -559,10 +559,14 @@ static inline unsigned int blk_rq_get_max_segments(struct request *rq) static inline int ll_new_hw_segment(struct request *req, struct bio *bio, unsigned int nr_phys_segs) { - if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req)) + if (blk_integrity_merge_bio(req->q, req, bio) == false) goto no_merge; - if (blk_integrity_merge_bio(req->q, req, bio) == false) + /* discard request merge won't add new segment */ + if (req_op(req) == REQ_OP_DISCARD) + return 1; + + if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req)) goto no_merge; /* @@ -846,18 +850,15 @@ static struct request *attempt_front_merge(struct request_queue *q, return NULL; } -int blk_attempt_req_merge(struct request_queue *q, struct request *rq, - struct request *next) +/* + * Try to merge 'next' into 'rq'. Return true if the merge happened, false + * otherwise. The caller is responsible for freeing 'next' if the merge + * happened. + */ +bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, + struct request *next) { - struct request *free; - - free = attempt_merge(q, rq, next); - if (free) { - blk_put_request(free); - return 1; - } - - return 0; + return attempt_merge(q, rq, next); } bool blk_rq_merge_ok(struct request *rq, struct bio *bio) diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 2a75bc7401df..4b66d2776eda 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -937,6 +937,21 @@ void blk_mq_debugfs_unregister_sched(struct request_queue *q) q->sched_debugfs_dir = NULL; } +static const char *rq_qos_id_to_name(enum rq_qos_id id) +{ + switch (id) { + case RQ_QOS_WBT: + return "wbt"; + case RQ_QOS_LATENCY: + return "latency"; + case RQ_QOS_COST: + return "cost"; + case RQ_QOS_IOPRIO: + return "ioprio"; + } + return "unknown"; +} + void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos) { debugfs_remove_recursive(rqos->debugfs_dir); diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 996a4b2f73aa..c838d81ac058 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -168,9 +168,19 @@ static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) * in blk_mq_dispatch_rq_list(). */ list_add_tail(&rq->queuelist, &rq_list); + count++; if (rq->mq_hctx != hctx) multi_hctxs = true; - } while (++count < max_dispatch); + + /* + * If we cannot get tag for the request, stop dequeueing + * requests from the IO scheduler. We are unlikely to be able + * to submit them anyway and it creates false impression for + * scheduling heuristics that the device can take more IO. + */ + if (!blk_mq_get_driver_tag(rq)) + break; + } while (count < max_dispatch); if (!count) { if (run_queue) @@ -284,8 +294,7 @@ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; - struct elevator_queue *e = q->elevator; - const bool has_sched_dispatch = e && e->type->ops.dispatch_request; + const bool has_sched = q->elevator; int ret = 0; LIST_HEAD(rq_list); @@ -316,12 +325,12 @@ static int __blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) if (!list_empty(&rq_list)) { blk_mq_sched_mark_restart_hctx(hctx); if (blk_mq_dispatch_rq_list(hctx, &rq_list, 0)) { - if (has_sched_dispatch) + if (has_sched) ret = blk_mq_do_dispatch_sched(hctx); else ret = blk_mq_do_dispatch_ctx(hctx); } - } else if (has_sched_dispatch) { + } else if (has_sched) { ret = blk_mq_do_dispatch_sched(hctx); } else if (hctx->dispatch_busy) { /* dequeue request one by one from sw queue if queue is busy */ @@ -390,9 +399,10 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, return ret; } -bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq) +bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq, + struct list_head *free) { - return rq_mergeable(rq) && elv_attempt_insert_merge(q, rq); + return rq_mergeable(rq) && elv_attempt_insert_merge(q, rq, free); } EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge); @@ -453,7 +463,7 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head, goto run; } - if (e && e->type->ops.insert_requests) { + if (e) { LIST_HEAD(list); list_add(&rq->queuelist, &list); @@ -484,9 +494,9 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx, percpu_ref_get(&q->q_usage_counter); e = hctx->queue->elevator; - if (e && e->type->ops.insert_requests) + if (e) { e->type->ops.insert_requests(hctx, list, false); - else { + } else { /* * try to issue requests directly if the hw queue isn't * busy in case of 'none' scheduler, and this way may save @@ -509,11 +519,9 @@ static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { - unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; - if (hctx->sched_tags) { blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx); - blk_mq_free_rq_map(hctx->sched_tags, flags); + blk_mq_free_rq_map(hctx->sched_tags, set->flags); hctx->sched_tags = NULL; } } @@ -523,12 +531,10 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q, unsigned int hctx_idx) { struct blk_mq_tag_set *set = q->tag_set; - /* Clear HCTX_SHARED so tags are init'ed */ - unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; int ret; hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests, - set->reserved_tags, flags); + set->reserved_tags, set->flags); if (!hctx->sched_tags) return -ENOMEM; @@ -546,16 +552,50 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q) int i; queue_for_each_hw_ctx(q, hctx, i) { - /* Clear HCTX_SHARED so tags are freed */ - unsigned int flags = hctx->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; - if (hctx->sched_tags) { - blk_mq_free_rq_map(hctx->sched_tags, flags); + blk_mq_free_rq_map(hctx->sched_tags, hctx->flags); hctx->sched_tags = NULL; } } } +static int blk_mq_init_sched_shared_sbitmap(struct request_queue *queue) +{ + struct blk_mq_tag_set *set = queue->tag_set; + int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags); + struct blk_mq_hw_ctx *hctx; + int ret, i; + + /* + * Set initial depth at max so that we don't need to reallocate for + * updating nr_requests. + */ + ret = blk_mq_init_bitmaps(&queue->sched_bitmap_tags, + &queue->sched_breserved_tags, + MAX_SCHED_RQ, set->reserved_tags, + set->numa_node, alloc_policy); + if (ret) + return ret; + + queue_for_each_hw_ctx(queue, hctx, i) { + hctx->sched_tags->bitmap_tags = + &queue->sched_bitmap_tags; + hctx->sched_tags->breserved_tags = + &queue->sched_breserved_tags; + } + + sbitmap_queue_resize(&queue->sched_bitmap_tags, + queue->nr_requests - set->reserved_tags); + + return 0; +} + +static void blk_mq_exit_sched_shared_sbitmap(struct request_queue *queue) +{ + sbitmap_queue_free(&queue->sched_bitmap_tags); + sbitmap_queue_free(&queue->sched_breserved_tags); +} + int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) { struct blk_mq_hw_ctx *hctx; @@ -580,12 +620,18 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_sched_alloc_tags(q, hctx, i); if (ret) - goto err; + goto err_free_tags; + } + + if (blk_mq_is_sbitmap_shared(q->tag_set->flags)) { + ret = blk_mq_init_sched_shared_sbitmap(q); + if (ret) + goto err_free_tags; } ret = e->ops.init_sched(q, e); if (ret) - goto err; + goto err_free_sbitmap; blk_mq_debugfs_register_sched(q); @@ -605,7 +651,10 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) return 0; -err: +err_free_sbitmap: + if (blk_mq_is_sbitmap_shared(q->tag_set->flags)) + blk_mq_exit_sched_shared_sbitmap(q); +err_free_tags: blk_mq_sched_free_requests(q); blk_mq_sched_tags_teardown(q); q->elevator = NULL; @@ -631,6 +680,7 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) { struct blk_mq_hw_ctx *hctx; unsigned int i; + unsigned int flags = 0; queue_for_each_hw_ctx(q, hctx, i) { blk_mq_debugfs_unregister_sched_hctx(hctx); @@ -638,10 +688,13 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) e->type->ops.exit_hctx(hctx, i); hctx->sched_data = NULL; } + flags = hctx->flags; } blk_mq_debugfs_unregister_sched(q); if (e->type->ops.exit_sched) e->type->ops.exit_sched(e); blk_mq_sched_tags_teardown(q); + if (blk_mq_is_sbitmap_shared(flags)) + blk_mq_exit_sched_shared_sbitmap(q); q->elevator = NULL; } diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 5b18ab915c65..5246ae040704 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -5,13 +5,16 @@ #include "blk-mq.h" #include "blk-mq-tag.h" +#define MAX_SCHED_RQ (16 * BLKDEV_MAX_RQ) + void blk_mq_sched_assign_ioc(struct request *rq); bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs, struct request **merged_request); bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs); -bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq); +bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq, + struct list_head *free); void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx); void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 2a37731e8244..86f87346232a 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -13,6 +13,7 @@ #include #include "blk.h" #include "blk-mq.h" +#include "blk-mq-sched.h" #include "blk-mq-tag.h" /* @@ -199,6 +200,20 @@ struct bt_iter_data { bool reserved; }; +static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags, + unsigned int bitnr) +{ + struct request *rq; + unsigned long flags; + + spin_lock_irqsave(&tags->lock, flags); + rq = tags->rqs[bitnr]; + if (!rq || !refcount_inc_not_zero(&rq->ref)) + rq = NULL; + spin_unlock_irqrestore(&tags->lock, flags); + return rq; +} + static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_iter_data *iter_data = data; @@ -206,18 +221,22 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) struct blk_mq_tags *tags = hctx->tags; bool reserved = iter_data->reserved; struct request *rq; + bool ret = true; if (!reserved) bitnr += tags->nr_reserved_tags; - rq = tags->rqs[bitnr]; - /* * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ - if (rq && rq->q == hctx->queue && rq->mq_hctx == hctx) - return iter_data->fn(hctx, rq, iter_data->data, reserved); - return true; + rq = blk_mq_find_and_get_req(tags, bitnr); + if (!rq) + return true; + + if (rq->q == hctx->queue && rq->mq_hctx == hctx) + ret = iter_data->fn(hctx, rq, iter_data->data, reserved); + blk_mq_put_rq_ref(rq); + return ret; } /** @@ -264,6 +283,8 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) struct blk_mq_tags *tags = iter_data->tags; bool reserved = iter_data->flags & BT_TAG_ITER_RESERVED; struct request *rq; + bool ret = true; + bool iter_static_rqs = !!(iter_data->flags & BT_TAG_ITER_STATIC_RQS); if (!reserved) bitnr += tags->nr_reserved_tags; @@ -272,16 +293,19 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ - if (iter_data->flags & BT_TAG_ITER_STATIC_RQS) + if (iter_static_rqs) rq = tags->static_rqs[bitnr]; else - rq = tags->rqs[bitnr]; + rq = blk_mq_find_and_get_req(tags, bitnr); if (!rq) return true; - if ((iter_data->flags & BT_TAG_ITER_STARTED) && - !blk_mq_request_started(rq)) - return true; - return iter_data->fn(rq, iter_data->data, reserved); + + if (!(iter_data->flags & BT_TAG_ITER_STARTED) || + blk_mq_request_started(rq)) + ret = iter_data->fn(rq, iter_data->data, reserved); + if (!iter_static_rqs) + blk_mq_put_rq_ref(rq); + return ret; } /** @@ -348,6 +372,9 @@ void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, * indicates whether or not @rq is a reserved request. Return * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. + * + * We grab one request reference before calling @fn and release it after + * @fn returns. */ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv) @@ -445,39 +472,54 @@ static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth, node); } +int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, + struct sbitmap_queue *breserved_tags, + unsigned int queue_depth, unsigned int reserved, + int node, int alloc_policy) +{ + unsigned int depth = queue_depth - reserved; + bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; + + if (bt_alloc(bitmap_tags, depth, round_robin, node)) + return -ENOMEM; + if (bt_alloc(breserved_tags, reserved, round_robin, node)) + goto free_bitmap_tags; + + return 0; + +free_bitmap_tags: + sbitmap_queue_free(bitmap_tags); + return -ENOMEM; +} + static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags, int node, int alloc_policy) { - unsigned int depth = tags->nr_tags - tags->nr_reserved_tags; - bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; + int ret; - if (bt_alloc(&tags->__bitmap_tags, depth, round_robin, node)) - return -ENOMEM; - if (bt_alloc(&tags->__breserved_tags, tags->nr_reserved_tags, - round_robin, node)) - goto free_bitmap_tags; + ret = blk_mq_init_bitmaps(&tags->__bitmap_tags, + &tags->__breserved_tags, + tags->nr_tags, tags->nr_reserved_tags, + node, alloc_policy); + if (ret) + return ret; tags->bitmap_tags = &tags->__bitmap_tags; tags->breserved_tags = &tags->__breserved_tags; return 0; -free_bitmap_tags: - sbitmap_queue_free(&tags->__bitmap_tags); - return -ENOMEM; } -int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags) +int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set) { - unsigned int depth = set->queue_depth - set->reserved_tags; int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags); - bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; - int i, node = set->numa_node; + int i, ret; - if (bt_alloc(&set->__bitmap_tags, depth, round_robin, node)) - return -ENOMEM; - if (bt_alloc(&set->__breserved_tags, set->reserved_tags, - round_robin, node)) - goto free_bitmap_tags; + ret = blk_mq_init_bitmaps(&set->__bitmap_tags, &set->__breserved_tags, + set->queue_depth, set->reserved_tags, + set->numa_node, alloc_policy); + if (ret) + return ret; for (i = 0; i < set->nr_hw_queues; i++) { struct blk_mq_tags *tags = set->tags[i]; @@ -487,9 +529,6 @@ int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags) } return 0; -free_bitmap_tags: - sbitmap_queue_free(&set->__bitmap_tags); - return -ENOMEM; } void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set) @@ -516,6 +555,7 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; + spin_lock_init(&tags->lock); if (blk_mq_is_sbitmap_shared(flags)) return tags; @@ -551,8 +591,6 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, */ if (tdepth > tags->nr_tags) { struct blk_mq_tag_set *set = hctx->queue->tag_set; - /* Only sched tags can grow, so clear HCTX_SHARED flag */ - unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; struct blk_mq_tags *new; bool ret; @@ -563,21 +601,21 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, * We need some sort of upper limit, set it high enough that * no valid use cases should require more. */ - if (tdepth > 16 * BLKDEV_MAX_RQ) + if (tdepth > MAX_SCHED_RQ) return -EINVAL; new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth, - tags->nr_reserved_tags, flags); + tags->nr_reserved_tags, set->flags); if (!new) return -ENOMEM; ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth); if (ret) { - blk_mq_free_rq_map(new, flags); + blk_mq_free_rq_map(new, set->flags); return -ENOMEM; } blk_mq_free_rqs(set, *tagsptr, hctx->queue_num); - blk_mq_free_rq_map(*tagsptr, flags); + blk_mq_free_rq_map(*tagsptr, set->flags); *tagsptr = new; } else { /* diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 7d3e6b333a4a..8ed55af08427 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -20,17 +20,26 @@ struct blk_mq_tags { struct request **rqs; struct request **static_rqs; struct list_head page_list; + + /* + * used to clear request reference in rqs[] before freeing one + * request pool + */ + spinlock_t lock; }; extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, unsigned int flags); extern void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags); +extern int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, + struct sbitmap_queue *breserved_tags, + unsigned int queue_depth, + unsigned int reserved, + int node, int alloc_policy); -extern int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, - unsigned int flags); +extern int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set); extern void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set); - extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); diff --git a/block/blk-mq.c b/block/blk-mq.c index e41edae97487..2e9fd0ec63d7 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -909,6 +909,14 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next) return false; } +void blk_mq_put_rq_ref(struct request *rq) +{ + if (is_flush_rq(rq, rq->mq_hctx)) + rq->end_io(rq, 0); + else if (refcount_dec_and_test(&rq->ref)) + __blk_mq_free_request(rq); +} + static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { @@ -942,11 +950,7 @@ static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, if (blk_mq_req_expired(rq, next)) blk_mq_rq_timed_out(rq, reserved); - if (is_flush_rq(rq, hctx)) - rq->end_io(rq, 0); - else if (refcount_dec_and_test(&rq->ref)) - __blk_mq_free_request(rq); - + blk_mq_put_rq_ref(rq); return true; } @@ -1100,7 +1104,7 @@ static bool __blk_mq_get_driver_tag(struct request *rq) return true; } -static bool blk_mq_get_driver_tag(struct request *rq) +bool blk_mq_get_driver_tag(struct request *rq) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; @@ -1220,9 +1224,6 @@ static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy) { unsigned int ewma; - if (hctx->queue->elevator) - return; - ewma = hctx->dispatch_busy; if (!ewma && !busy) @@ -2303,6 +2304,45 @@ queue_exit: return BLK_QC_T_NONE; } +static size_t order_to_size(unsigned int order) +{ + return (size_t)PAGE_SIZE << order; +} + +/* called before freeing request pool in @tags */ +static void blk_mq_clear_rq_mapping(struct blk_mq_tag_set *set, + struct blk_mq_tags *tags, unsigned int hctx_idx) +{ + struct blk_mq_tags *drv_tags = set->tags[hctx_idx]; + struct page *page; + unsigned long flags; + + list_for_each_entry(page, &tags->page_list, lru) { + unsigned long start = (unsigned long)page_address(page); + unsigned long end = start + order_to_size(page->private); + int i; + + for (i = 0; i < set->queue_depth; i++) { + struct request *rq = drv_tags->rqs[i]; + unsigned long rq_addr = (unsigned long)rq; + + if (rq_addr >= start && rq_addr < end) { + WARN_ON_ONCE(refcount_read(&rq->ref) != 0); + cmpxchg(&drv_tags->rqs[i], rq, NULL); + } + } + } + + /* + * Wait until all pending iteration is done. + * + * Request reference is cleared and it is guaranteed to be observed + * after the ->lock is released. + */ + spin_lock_irqsave(&drv_tags->lock, flags); + spin_unlock_irqrestore(&drv_tags->lock, flags); +} + void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { @@ -2321,6 +2361,8 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, } } + blk_mq_clear_rq_mapping(set, tags, hctx_idx); + while (!list_empty(&tags->page_list)) { page = list_first_entry(&tags->page_list, struct page, lru); list_del_init(&page->lru); @@ -2380,11 +2422,6 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, return tags; } -static size_t order_to_size(unsigned int order) -{ - return (size_t)PAGE_SIZE << order; -} - static int blk_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, unsigned int hctx_idx, int node) { @@ -2603,16 +2640,49 @@ static void blk_mq_remove_cpuhp(struct blk_mq_hw_ctx *hctx) &hctx->cpuhp_dead); } +/* + * Before freeing hw queue, clearing the flush request reference in + * tags->rqs[] for avoiding potential UAF. + */ +static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags, + unsigned int queue_depth, struct request *flush_rq) +{ + int i; + unsigned long flags; + + /* The hw queue may not be mapped yet */ + if (!tags) + return; + + WARN_ON_ONCE(refcount_read(&flush_rq->ref) != 0); + + for (i = 0; i < queue_depth; i++) + cmpxchg(&tags->rqs[i], flush_rq, NULL); + + /* + * Wait until all pending iteration is done. + * + * Request reference is cleared and it is guaranteed to be observed + * after the ->lock is released. + */ + spin_lock_irqsave(&tags->lock, flags); + spin_unlock_irqrestore(&tags->lock, flags); +} + /* hctx->ctxs will be freed in queue's release handler */ static void blk_mq_exit_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { + struct request *flush_rq = hctx->fq->flush_rq; + if (blk_mq_hw_queue_mapped(hctx)) blk_mq_tag_idle(hctx); + blk_mq_clear_flush_rq_mapping(set->tags[hctx_idx], + set->queue_depth, flush_rq); if (set->ops->exit_request) - set->ops->exit_request(set, hctx->fq->flush_rq, hctx_idx); + set->ops->exit_request(set, flush_rq, hctx_idx); if (set->ops->exit_hctx) set->ops->exit_hctx(hctx, hctx_idx); @@ -3042,21 +3112,18 @@ void blk_mq_release(struct request_queue *q) struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, void *queuedata) { - struct request_queue *uninit_q, *q; + struct request_queue *q; + int ret; - uninit_q = blk_alloc_queue(set->numa_node); - if (!uninit_q) + q = blk_alloc_queue(set->numa_node); + if (!q) return ERR_PTR(-ENOMEM); - uninit_q->queuedata = queuedata; - - /* - * Initialize the queue without an elevator. device_add_disk() will do - * the initialization. - */ - q = blk_mq_init_allocated_queue(set, uninit_q, false); - if (IS_ERR(q)) - blk_cleanup_queue(uninit_q); - + q->queuedata = queuedata; + ret = blk_mq_init_allocated_queue(set, q); + if (ret) { + blk_cleanup_queue(q); + return ERR_PTR(ret); + } return q; } EXPORT_SYMBOL_GPL(blk_mq_init_queue_data); @@ -3067,39 +3134,24 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) } EXPORT_SYMBOL(blk_mq_init_queue); -/* - * Helper for setting up a queue with mq ops, given queue depth, and - * the passed in mq ops flags. - */ -struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, - const struct blk_mq_ops *ops, - unsigned int queue_depth, - unsigned int set_flags) +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata) { struct request_queue *q; - int ret; + struct gendisk *disk; - memset(set, 0, sizeof(*set)); - set->ops = ops; - set->nr_hw_queues = 1; - set->nr_maps = 1; - set->queue_depth = queue_depth; - set->numa_node = NUMA_NO_NODE; - set->flags = set_flags; + q = blk_mq_init_queue_data(set, queuedata); + if (IS_ERR(q)) + return ERR_CAST(q); - ret = blk_mq_alloc_tag_set(set); - if (ret) - return ERR_PTR(ret); - - q = blk_mq_init_queue(set); - if (IS_ERR(q)) { - blk_mq_free_tag_set(set); - return q; + disk = __alloc_disk_node(0, set->numa_node); + if (!disk) { + blk_cleanup_queue(q); + return ERR_PTR(-ENOMEM); } - - return q; + disk->queue = q; + return disk; } -EXPORT_SYMBOL(blk_mq_init_sq_queue); +EXPORT_SYMBOL(__blk_mq_alloc_disk); static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( struct blk_mq_tag_set *set, struct request_queue *q, @@ -3212,9 +3264,8 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, mutex_unlock(&q->sysfs_lock); } -struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, - struct request_queue *q, - bool elevator_init) +int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, + struct request_queue *q) { /* mark the queue as mq asap */ q->mq_ops = set->ops; @@ -3264,11 +3315,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, blk_mq_init_cpu_queues(q, set->nr_hw_queues); blk_mq_add_queue_tag_set(set, q); blk_mq_map_swqueue(q); - - if (elevator_init) - elevator_init_mq(q); - - return q; + return 0; err_hctxs: kfree(q->queue_hw_ctx); @@ -3279,7 +3326,7 @@ err_poll: q->poll_cb = NULL; err_exit: q->mq_ops = NULL; - return ERR_PTR(-ENOMEM); + return -ENOMEM; } EXPORT_SYMBOL(blk_mq_init_allocated_queue); @@ -3491,7 +3538,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) if (blk_mq_is_sbitmap_shared(set->flags)) { atomic_set(&set->active_queues_shared_sbitmap, 0); - if (blk_mq_init_shared_sbitmap(set, set->flags)) { + if (blk_mq_init_shared_sbitmap(set)) { ret = -ENOMEM; goto out_free_mq_rq_maps; } @@ -3516,6 +3563,22 @@ out_free_mq_map: } EXPORT_SYMBOL(blk_mq_alloc_tag_set); +/* allocate and initialize a tagset for a simple single-queue device */ +int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, unsigned int queue_depth, + unsigned int set_flags) +{ + memset(set, 0, sizeof(*set)); + set->ops = ops; + set->nr_hw_queues = 1; + set->nr_maps = 1; + set->queue_depth = queue_depth; + set->numa_node = NUMA_NO_NODE; + set->flags = set_flags; + return blk_mq_alloc_tag_set(set); +} +EXPORT_SYMBOL_GPL(blk_mq_alloc_sq_tag_set); + void blk_mq_free_tag_set(struct blk_mq_tag_set *set) { int i, j; @@ -3567,15 +3630,24 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) } else { ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags, nr, true); + if (blk_mq_is_sbitmap_shared(set->flags)) { + hctx->sched_tags->bitmap_tags = + &q->sched_bitmap_tags; + hctx->sched_tags->breserved_tags = + &q->sched_breserved_tags; + } } if (ret) break; if (q->elevator && q->elevator->type->ops.depth_updated) q->elevator->type->ops.depth_updated(hctx); } - - if (!ret) + if (!ret) { q->nr_requests = nr; + if (q->elevator && blk_mq_is_sbitmap_shared(set->flags)) + sbitmap_queue_resize(&q->sched_bitmap_tags, + nr - set->reserved_tags); + } blk_mq_unquiesce_queue(q); blk_mq_unfreeze_queue(q); diff --git a/block/blk-mq.h b/block/blk-mq.h index 9ce64bc4a6c8..d08779f77a26 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -47,6 +47,7 @@ void blk_mq_add_to_requeue_list(struct request *rq, bool at_head, void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *start); +void blk_mq_put_rq_ref(struct request *rq); /* * Internal helpers for allocating/freeing the request map @@ -259,6 +260,8 @@ static inline void blk_mq_put_driver_tag(struct request *rq) __blk_mq_put_driver_tag(rq->mq_hctx, rq); } +bool blk_mq_get_driver_tag(struct request *rq); + static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) { int cpu; @@ -299,6 +302,17 @@ static inline struct blk_plug *blk_mq_plug(struct request_queue *q, return NULL; } +/* Free all requests on the list */ +static inline void blk_mq_free_requests(struct list_head *list) +{ + while (!list_empty(list)) { + struct request *rq = list_entry_rq(list->next); + + list_del_init(&rq->queuelist); + blk_mq_free_request(rq); + } +} + /* * For shared tag users, we track the number of currently active users * and attempt to provide a fair share of the tag depth for each of them. diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 656460636ad3..e83af7bc7591 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -266,8 +266,8 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) return; - prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE); - has_sleeper = !wq_has_single_sleeper(&rqw->wait); + has_sleeper = !prepare_to_wait_exclusive(&rqw->wait, &data.wq, + TASK_UNINTERRUPTIBLE); do { /* The memory barrier in set_task_state saves us here. */ if (data.got_token) diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 2bc43e94f4c4..f000f83e0621 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -7,6 +7,7 @@ #include #include #include +#include #include "blk-mq-debugfs.h" @@ -16,6 +17,7 @@ enum rq_qos_id { RQ_QOS_WBT, RQ_QOS_LATENCY, RQ_QOS_COST, + RQ_QOS_IOPRIO, }; struct rq_wait { @@ -78,19 +80,6 @@ static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q) return rq_qos_id(q, RQ_QOS_LATENCY); } -static inline const char *rq_qos_id_to_name(enum rq_qos_id id) -{ - switch (id) { - case RQ_QOS_WBT: - return "wbt"; - case RQ_QOS_LATENCY: - return "latency"; - case RQ_QOS_COST: - return "cost"; - } - return "unknown"; -} - static inline void rq_wait_init(struct rq_wait *rq_wait) { atomic_set(&rq_wait->inflight, 0); @@ -99,8 +88,21 @@ static inline void rq_wait_init(struct rq_wait *rq_wait) static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) { + /* + * No IO can be in-flight when adding rqos, so freeze queue, which + * is fine since we only support rq_qos for blk-mq queue. + * + * Reuse ->queue_lock for protecting against other concurrent + * rq_qos adding/deleting + */ + blk_mq_freeze_queue(q); + + spin_lock_irq(&q->queue_lock); rqos->next = q->rq_qos; q->rq_qos = rqos; + spin_unlock_irq(&q->queue_lock); + + blk_mq_unfreeze_queue(q); if (rqos->ops->debugfs_attrs) blk_mq_debugfs_register_rqos(rqos); @@ -110,12 +112,22 @@ static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) { struct rq_qos **cur; + /* + * See comment in rq_qos_add() about freezing queue & using + * ->queue_lock. + */ + blk_mq_freeze_queue(q); + + spin_lock_irq(&q->queue_lock); for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; break; } } + spin_unlock_irq(&q->queue_lock); + + blk_mq_unfreeze_queue(q); blk_mq_debugfs_unregister_rqos(rqos); } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index e03bedf180ab..370d83c18057 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -91,7 +91,7 @@ static ssize_t queue_ra_show(struct request_queue *q, char *page) unsigned long ra_kb = q->backing_dev_info->ra_pages << (PAGE_SHIFT - 10); - return queue_var_show(ra_kb, (page)); + return queue_var_show(ra_kb, page); } static ssize_t @@ -112,28 +112,28 @@ static ssize_t queue_max_sectors_show(struct request_queue *q, char *page) { int max_sectors_kb = queue_max_sectors(q) >> 1; - return queue_var_show(max_sectors_kb, (page)); + return queue_var_show(max_sectors_kb, page); } static ssize_t queue_max_segments_show(struct request_queue *q, char *page) { - return queue_var_show(queue_max_segments(q), (page)); + return queue_var_show(queue_max_segments(q), page); } static ssize_t queue_max_discard_segments_show(struct request_queue *q, char *page) { - return queue_var_show(queue_max_discard_segments(q), (page)); + return queue_var_show(queue_max_discard_segments(q), page); } static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page) { - return queue_var_show(q->limits.max_integrity_segments, (page)); + return queue_var_show(q->limits.max_integrity_segments, page); } static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page) { - return queue_var_show(queue_max_segment_size(q), (page)); + return queue_var_show(queue_max_segment_size(q), page); } static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page) @@ -261,12 +261,12 @@ static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page) { int max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1; - return queue_var_show(max_hw_sectors_kb, (page)); + return queue_var_show(max_hw_sectors_kb, page); } static ssize_t queue_virt_boundary_mask_show(struct request_queue *q, char *page) { - return queue_var_show(q->limits.virt_boundary_mask, (page)); + return queue_var_show(q->limits.virt_boundary_mask, page); } #define QUEUE_SYSFS_BIT_FNS(name, flag, neg) \ @@ -866,20 +866,6 @@ int blk_register_queue(struct gendisk *disk) "%s is registering an already registered queue\n", kobject_name(&dev->kobj)); - /* - * SCSI probing may synchronously create and destroy a lot of - * request_queues for non-existent devices. Shutting down a fully - * functional queue takes measureable wallclock time as RCU grace - * periods are involved. To avoid excessive latency in these - * cases, a request_queue starts out in a degraded mode which is - * faster to shut down and is made fully functional here as - * request_queues for non-existent devices never get registered. - */ - if (!blk_queue_init_done(q)) { - blk_queue_flag_set(QUEUE_FLAG_INIT_DONE, q); - percpu_ref_switch_to_percpu(&q->q_usage_counter); - } - blk_queue_update_readahead(q); ret = blk_trace_init_sysfs(dev); @@ -938,6 +924,21 @@ int blk_register_queue(struct gendisk *disk) ret = 0; unlock: mutex_unlock(&q->sysfs_dir_lock); + + /* + * SCSI probing may synchronously create and destroy a lot of + * request_queues for non-existent devices. Shutting down a fully + * functional queue takes measureable wallclock time as RCU grace + * periods are involved. To avoid excessive latency in these + * cases, a request_queue starts out in a degraded mode which is + * faster to shut down and is made fully functional here as + * request_queues for non-existent devices never get registered. + */ + if (!blk_queue_init_done(q)) { + blk_queue_flag_set(QUEUE_FLAG_INIT_DONE, q); + percpu_ref_switch_to_percpu(&q->q_usage_counter); + } + return ret; } EXPORT_SYMBOL_GPL(blk_register_queue); diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 42aed0160f86..3ed71b8da887 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -77,7 +77,8 @@ enum { static inline bool rwb_enabled(struct rq_wb *rwb) { - return rwb && rwb->wb_normal != 0; + return rwb && rwb->enable_state != WBT_STATE_OFF_DEFAULT && + rwb->wb_normal != 0; } static void wb_timestamp(struct rq_wb *rwb, unsigned long *var) @@ -563,7 +564,6 @@ static void wbt_cleanup(struct rq_qos *rqos, struct bio *bio) } /* - * Returns true if the IO request should be accounted, false if not. * May sleep, if we have exceeded the writeback limits. Caller can pass * in an irq held spinlock, if it holds one when calling this function. * If we do sleep, we'll release and re-grab it. @@ -636,9 +636,13 @@ void wbt_set_write_cache(struct request_queue *q, bool write_cache_on) void wbt_enable_default(struct request_queue *q) { struct rq_qos *rqos = wbt_rq_qos(q); + /* Throttling already enabled? */ - if (rqos) + if (rqos) { + if (RQWB(rqos)->enable_state == WBT_STATE_OFF_DEFAULT) + RQWB(rqos)->enable_state = WBT_STATE_ON_DEFAULT; return; + } /* Queue not registered? Maybe shutting down... */ if (!blk_queue_registered(q)) @@ -702,7 +706,7 @@ void wbt_disable_default(struct request_queue *q) rwb = RQWB(rqos); if (rwb->enable_state == WBT_STATE_ON_DEFAULT) { blk_stat_deactivate(rwb->cb); - rwb->wb_normal = 0; + rwb->enable_state = WBT_STATE_OFF_DEFAULT; } } EXPORT_SYMBOL_GPL(wbt_disable_default); diff --git a/block/blk-wbt.h b/block/blk-wbt.h index 16bdc85b8df9..2eb01becde8c 100644 --- a/block/blk-wbt.h +++ b/block/blk-wbt.h @@ -34,6 +34,7 @@ enum { enum { WBT_STATE_ON_DEFAULT = 1, WBT_STATE_ON_MANUAL = 2, + WBT_STATE_OFF_DEFAULT }; struct rq_wb { diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 250cb76ee615..86fce751bb17 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -161,18 +161,89 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector, } EXPORT_SYMBOL_GPL(blkdev_report_zones); -static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev, - sector_t sector, - sector_t nr_sectors) +static inline unsigned long *blk_alloc_zone_bitmap(int node, + unsigned int nr_zones) { - if (!blk_queue_zone_resetall(bdev_get_queue(bdev))) - return false; + return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long), + GFP_NOIO, node); +} +static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ /* - * REQ_OP_ZONE_RESET_ALL can be executed only if the number of sectors - * of the applicable zone range is the entire disk. + * For an all-zones reset, ignore conventional, empty, read-only + * and offline zones. */ - return !sector && nr_sectors == get_capacity(bdev->bd_disk); + switch (zone->cond) { + case BLK_ZONE_COND_NOT_WP: + case BLK_ZONE_COND_EMPTY: + case BLK_ZONE_COND_READONLY: + case BLK_ZONE_COND_OFFLINE: + return 0; + default: + set_bit(idx, (unsigned long *)data); + return 0; + } +} + +static int blkdev_zone_reset_all_emulated(struct block_device *bdev, + gfp_t gfp_mask) +{ + struct request_queue *q = bdev_get_queue(bdev); + sector_t capacity = get_capacity(bdev->bd_disk); + sector_t zone_sectors = blk_queue_zone_sectors(q); + unsigned long *need_reset; + struct bio *bio = NULL; + sector_t sector = 0; + int ret; + + need_reset = blk_alloc_zone_bitmap(q->node, q->nr_zones); + if (!need_reset) + return -ENOMEM; + + ret = bdev->bd_disk->fops->report_zones(bdev->bd_disk, 0, + q->nr_zones, blk_zone_need_reset_cb, + need_reset); + if (ret < 0) + goto out_free_need_reset; + + ret = 0; + while (sector < capacity) { + if (!test_bit(blk_queue_zone_no(q, sector), need_reset)) { + sector += zone_sectors; + continue; + } + + bio = blk_next_bio(bio, 0, gfp_mask); + bio_set_dev(bio, bdev); + bio->bi_opf = REQ_OP_ZONE_RESET | REQ_SYNC; + bio->bi_iter.bi_sector = sector; + sector += zone_sectors; + + /* This may take a while, so be nice to others */ + cond_resched(); + } + + if (bio) { + ret = submit_bio_wait(bio); + bio_put(bio); + } + +out_free_need_reset: + kfree(need_reset); + return ret; +} + +static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask) +{ + struct bio bio; + + bio_init(&bio, NULL, 0); + bio_set_dev(&bio, bdev); + bio.bi_opf = REQ_OP_ZONE_RESET_ALL | REQ_SYNC; + + return submit_bio_wait(&bio); } /** @@ -200,7 +271,7 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, sector_t capacity = get_capacity(bdev->bd_disk); sector_t end_sector = sector + nr_sectors; struct bio *bio = NULL; - int ret; + int ret = 0; if (!blk_queue_is_zoned(q)) return -EOPNOTSUPP; @@ -222,20 +293,21 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity) return -EINVAL; + /* + * In the case of a zone reset operation over all zones, + * REQ_OP_ZONE_RESET_ALL can be used with devices supporting this + * command. For other devices, we emulate this command behavior by + * identifying the zones needing a reset. + */ + if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) { + if (!blk_queue_zone_resetall(q)) + return blkdev_zone_reset_all_emulated(bdev, gfp_mask); + return blkdev_zone_reset_all(bdev, gfp_mask); + } + while (sector < end_sector) { bio = blk_next_bio(bio, 0, gfp_mask); bio_set_dev(bio, bdev); - - /* - * Special case for the zone reset operation that reset all - * zones, this is useful for applications like mkfs. - */ - if (op == REQ_OP_ZONE_RESET && - blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) { - bio->bi_opf = REQ_OP_ZONE_RESET_ALL | REQ_SYNC; - break; - } - bio->bi_opf = op | REQ_SYNC; bio->bi_iter.bi_sector = sector; sector += zone_sectors; @@ -396,13 +468,6 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, return ret; } -static inline unsigned long *blk_alloc_zone_bitmap(int node, - unsigned int nr_zones) -{ - return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long), - GFP_NOIO, node); -} - void blk_queue_free_zone_bitmaps(struct request_queue *q) { kfree(q->conv_zones_bitmap); diff --git a/block/blk.h b/block/blk.h index 8b3591aee0a5..4b885c0f6708 100644 --- a/block/blk.h +++ b/block/blk.h @@ -192,7 +192,6 @@ void blk_account_io_done(struct request *req, u64 now); void blk_insert_flush(struct request *rq); -void elevator_init_mq(struct request_queue *q); int elevator_switch_mq(struct request_queue *q, struct elevator_type *new_e); void __elevator_exit(struct request_queue *, struct elevator_queue *); @@ -225,7 +224,7 @@ ssize_t part_timeout_store(struct device *, struct device_attribute *, void __blk_queue_split(struct bio **bio, unsigned int *nr_segs); int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs); -int blk_attempt_req_merge(struct request_queue *q, struct request *rq, +bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next); unsigned int blk_recalc_rq_segments(struct request *rq); void blk_rq_set_mixed_merge(struct request *rq); @@ -343,8 +342,8 @@ static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {} static inline void blk_queue_clear_zone_settings(struct request_queue *q) {} #endif -int blk_alloc_devt(struct block_device *part, dev_t *devt); -void blk_free_devt(dev_t devt); +int blk_alloc_ext_minor(void); +void blk_free_ext_minor(unsigned int minor); char *disk_name(struct gendisk *hd, int partno, char *buf); #define ADDPART_FLAG_NONE 0 #define ADDPART_FLAG_RAID 1 @@ -359,4 +358,14 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, unsigned int max_sectors, bool *same_page); +struct request_queue *blk_alloc_queue(int node_id); + +void disk_alloc_events(struct gendisk *disk); +void disk_add_events(struct gendisk *disk); +void disk_del_events(struct gendisk *disk); +void disk_release_events(struct gendisk *disk); +extern struct device_attribute dev_attr_events; +extern struct device_attribute dev_attr_events_async; +extern struct device_attribute dev_attr_events_poll_msecs; + #endif /* BLK_INTERNAL_H */ diff --git a/block/disk-events.c b/block/disk-events.c new file mode 100644 index 000000000000..a75931ff5da4 --- /dev/null +++ b/block/disk-events.c @@ -0,0 +1,469 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Disk events - monitor disk events like media change and eject request. + */ +#include +#include +#include +#include "blk.h" + +struct disk_events { + struct list_head node; /* all disk_event's */ + struct gendisk *disk; /* the associated disk */ + spinlock_t lock; + + struct mutex block_mutex; /* protects blocking */ + int block; /* event blocking depth */ + unsigned int pending; /* events already sent out */ + unsigned int clearing; /* events being cleared */ + + long poll_msecs; /* interval, -1 for default */ + struct delayed_work dwork; +}; + +static const char *disk_events_strs[] = { + [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "media_change", + [ilog2(DISK_EVENT_EJECT_REQUEST)] = "eject_request", +}; + +static char *disk_uevents[] = { + [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "DISK_MEDIA_CHANGE=1", + [ilog2(DISK_EVENT_EJECT_REQUEST)] = "DISK_EJECT_REQUEST=1", +}; + +/* list of all disk_events */ +static DEFINE_MUTEX(disk_events_mutex); +static LIST_HEAD(disk_events); + +/* disable in-kernel polling by default */ +static unsigned long disk_events_dfl_poll_msecs; + +static unsigned long disk_events_poll_jiffies(struct gendisk *disk) +{ + struct disk_events *ev = disk->ev; + long intv_msecs = 0; + + /* + * If device-specific poll interval is set, always use it. If + * the default is being used, poll if the POLL flag is set. + */ + if (ev->poll_msecs >= 0) + intv_msecs = ev->poll_msecs; + else if (disk->event_flags & DISK_EVENT_FLAG_POLL) + intv_msecs = disk_events_dfl_poll_msecs; + + return msecs_to_jiffies(intv_msecs); +} + +/** + * disk_block_events - block and flush disk event checking + * @disk: disk to block events for + * + * On return from this function, it is guaranteed that event checking + * isn't in progress and won't happen until unblocked by + * disk_unblock_events(). Events blocking is counted and the actual + * unblocking happens after the matching number of unblocks are done. + * + * Note that this intentionally does not block event checking from + * disk_clear_events(). + * + * CONTEXT: + * Might sleep. + */ +void disk_block_events(struct gendisk *disk) +{ + struct disk_events *ev = disk->ev; + unsigned long flags; + bool cancel; + + if (!ev) + return; + + /* + * Outer mutex ensures that the first blocker completes canceling + * the event work before further blockers are allowed to finish. + */ + mutex_lock(&ev->block_mutex); + + spin_lock_irqsave(&ev->lock, flags); + cancel = !ev->block++; + spin_unlock_irqrestore(&ev->lock, flags); + + if (cancel) + cancel_delayed_work_sync(&disk->ev->dwork); + + mutex_unlock(&ev->block_mutex); +} + +static void __disk_unblock_events(struct gendisk *disk, bool check_now) +{ + struct disk_events *ev = disk->ev; + unsigned long intv; + unsigned long flags; + + spin_lock_irqsave(&ev->lock, flags); + + if (WARN_ON_ONCE(ev->block <= 0)) + goto out_unlock; + + if (--ev->block) + goto out_unlock; + + intv = disk_events_poll_jiffies(disk); + if (check_now) + queue_delayed_work(system_freezable_power_efficient_wq, + &ev->dwork, 0); + else if (intv) + queue_delayed_work(system_freezable_power_efficient_wq, + &ev->dwork, intv); +out_unlock: + spin_unlock_irqrestore(&ev->lock, flags); +} + +/** + * disk_unblock_events - unblock disk event checking + * @disk: disk to unblock events for + * + * Undo disk_block_events(). When the block count reaches zero, it + * starts events polling if configured. + * + * CONTEXT: + * Don't care. Safe to call from irq context. + */ +void disk_unblock_events(struct gendisk *disk) +{ + if (disk->ev) + __disk_unblock_events(disk, false); +} + +/** + * disk_flush_events - schedule immediate event checking and flushing + * @disk: disk to check and flush events for + * @mask: events to flush + * + * Schedule immediate event checking on @disk if not blocked. Events in + * @mask are scheduled to be cleared from the driver. Note that this + * doesn't clear the events from @disk->ev. + * + * CONTEXT: + * If @mask is non-zero must be called with disk->open_mutex held. + */ +void disk_flush_events(struct gendisk *disk, unsigned int mask) +{ + struct disk_events *ev = disk->ev; + + if (!ev) + return; + + spin_lock_irq(&ev->lock); + ev->clearing |= mask; + if (!ev->block) + mod_delayed_work(system_freezable_power_efficient_wq, + &ev->dwork, 0); + spin_unlock_irq(&ev->lock); +} + +static void disk_check_events(struct disk_events *ev, + unsigned int *clearing_ptr) +{ + struct gendisk *disk = ev->disk; + char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; + unsigned int clearing = *clearing_ptr; + unsigned int events; + unsigned long intv; + int nr_events = 0, i; + + /* check events */ + events = disk->fops->check_events(disk, clearing); + + /* accumulate pending events and schedule next poll if necessary */ + spin_lock_irq(&ev->lock); + + events &= ~ev->pending; + ev->pending |= events; + *clearing_ptr &= ~clearing; + + intv = disk_events_poll_jiffies(disk); + if (!ev->block && intv) + queue_delayed_work(system_freezable_power_efficient_wq, + &ev->dwork, intv); + + spin_unlock_irq(&ev->lock); + + /* + * Tell userland about new events. Only the events listed in + * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT + * is set. Otherwise, events are processed internally but never + * get reported to userland. + */ + for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) + if ((events & disk->events & (1 << i)) && + (disk->event_flags & DISK_EVENT_FLAG_UEVENT)) + envp[nr_events++] = disk_uevents[i]; + + if (nr_events) + kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); +} + +/** + * disk_clear_events - synchronously check, clear and return pending events + * @disk: disk to fetch and clear events from + * @mask: mask of events to be fetched and cleared + * + * Disk events are synchronously checked and pending events in @mask + * are cleared and returned. This ignores the block count. + * + * CONTEXT: + * Might sleep. + */ +static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) +{ + struct disk_events *ev = disk->ev; + unsigned int pending; + unsigned int clearing = mask; + + if (!ev) + return 0; + + disk_block_events(disk); + + /* + * store the union of mask and ev->clearing on the stack so that the + * race with disk_flush_events does not cause ambiguity (ev->clearing + * can still be modified even if events are blocked). + */ + spin_lock_irq(&ev->lock); + clearing |= ev->clearing; + ev->clearing = 0; + spin_unlock_irq(&ev->lock); + + disk_check_events(ev, &clearing); + /* + * if ev->clearing is not 0, the disk_flush_events got called in the + * middle of this function, so we want to run the workfn without delay. + */ + __disk_unblock_events(disk, ev->clearing ? true : false); + + /* then, fetch and clear pending events */ + spin_lock_irq(&ev->lock); + pending = ev->pending & mask; + ev->pending &= ~mask; + spin_unlock_irq(&ev->lock); + WARN_ON_ONCE(clearing & mask); + + return pending; +} + +/** + * bdev_check_media_change - check if a removable media has been changed + * @bdev: block device to check + * + * Check whether a removable media has been changed, and attempt to free all + * dentries and inodes and invalidates all block device page cache entries in + * that case. + * + * Returns %true if the block device changed, or %false if not. + */ +bool bdev_check_media_change(struct block_device *bdev) +{ + unsigned int events; + + events = disk_clear_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE | + DISK_EVENT_EJECT_REQUEST); + if (!(events & DISK_EVENT_MEDIA_CHANGE)) + return false; + + if (__invalidate_device(bdev, true)) + pr_warn("VFS: busy inodes on changed media %s\n", + bdev->bd_disk->disk_name); + set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); + return true; +} +EXPORT_SYMBOL(bdev_check_media_change); + +/* + * Separate this part out so that a different pointer for clearing_ptr can be + * passed in for disk_clear_events. + */ +static void disk_events_workfn(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct disk_events *ev = container_of(dwork, struct disk_events, dwork); + + disk_check_events(ev, &ev->clearing); +} + +/* + * A disk events enabled device has the following sysfs nodes under + * its /sys/block/X/ directory. + * + * events : list of all supported events + * events_async : list of events which can be detected w/o polling + * (always empty, only for backwards compatibility) + * events_poll_msecs : polling interval, 0: disable, -1: system default + */ +static ssize_t __disk_events_show(unsigned int events, char *buf) +{ + const char *delim = ""; + ssize_t pos = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(disk_events_strs); i++) + if (events & (1 << i)) { + pos += sprintf(buf + pos, "%s%s", + delim, disk_events_strs[i]); + delim = " "; + } + if (pos) + pos += sprintf(buf + pos, "\n"); + return pos; +} + +static ssize_t disk_events_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (!(disk->event_flags & DISK_EVENT_FLAG_UEVENT)) + return 0; + return __disk_events_show(disk->events, buf); +} + +static ssize_t disk_events_async_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return 0; +} + +static ssize_t disk_events_poll_msecs_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (!disk->ev) + return sprintf(buf, "-1\n"); + return sprintf(buf, "%ld\n", disk->ev->poll_msecs); +} + +static ssize_t disk_events_poll_msecs_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct gendisk *disk = dev_to_disk(dev); + long intv; + + if (!count || !sscanf(buf, "%ld", &intv)) + return -EINVAL; + + if (intv < 0 && intv != -1) + return -EINVAL; + + if (!disk->ev) + return -ENODEV; + + disk_block_events(disk); + disk->ev->poll_msecs = intv; + __disk_unblock_events(disk, true); + return count; +} + +DEVICE_ATTR(events, 0444, disk_events_show, NULL); +DEVICE_ATTR(events_async, 0444, disk_events_async_show, NULL); +DEVICE_ATTR(events_poll_msecs, 0644, disk_events_poll_msecs_show, + disk_events_poll_msecs_store); + +/* + * The default polling interval can be specified by the kernel + * parameter block.events_dfl_poll_msecs which defaults to 0 + * (disable). This can also be modified runtime by writing to + * /sys/module/block/parameters/events_dfl_poll_msecs. + */ +static int disk_events_set_dfl_poll_msecs(const char *val, + const struct kernel_param *kp) +{ + struct disk_events *ev; + int ret; + + ret = param_set_ulong(val, kp); + if (ret < 0) + return ret; + + mutex_lock(&disk_events_mutex); + list_for_each_entry(ev, &disk_events, node) + disk_flush_events(ev->disk, 0); + mutex_unlock(&disk_events_mutex); + return 0; +} + +static const struct kernel_param_ops disk_events_dfl_poll_msecs_param_ops = { + .set = disk_events_set_dfl_poll_msecs, + .get = param_get_ulong, +}; + +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "block." + +module_param_cb(events_dfl_poll_msecs, &disk_events_dfl_poll_msecs_param_ops, + &disk_events_dfl_poll_msecs, 0644); + +/* + * disk_{alloc|add|del|release}_events - initialize and destroy disk_events. + */ +void disk_alloc_events(struct gendisk *disk) +{ + struct disk_events *ev; + + if (!disk->fops->check_events || !disk->events) + return; + + ev = kzalloc(sizeof(*ev), GFP_KERNEL); + if (!ev) { + pr_warn("%s: failed to initialize events\n", disk->disk_name); + return; + } + + INIT_LIST_HEAD(&ev->node); + ev->disk = disk; + spin_lock_init(&ev->lock); + mutex_init(&ev->block_mutex); + ev->block = 1; + ev->poll_msecs = -1; + INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); + + disk->ev = ev; +} + +void disk_add_events(struct gendisk *disk) +{ + if (!disk->ev) + return; + + mutex_lock(&disk_events_mutex); + list_add_tail(&disk->ev->node, &disk_events); + mutex_unlock(&disk_events_mutex); + + /* + * Block count is initialized to 1 and the following initial + * unblock kicks it into action. + */ + __disk_unblock_events(disk, true); +} + +void disk_del_events(struct gendisk *disk) +{ + if (disk->ev) { + disk_block_events(disk); + + mutex_lock(&disk_events_mutex); + list_del_init(&disk->ev->node); + mutex_unlock(&disk_events_mutex); + } +} + +void disk_release_events(struct gendisk *disk) +{ + /* the block count should be 1 from disk_del_events() */ + WARN_ON_ONCE(disk->ev && disk->ev->block != 1); + kfree(disk->ev); +} diff --git a/block/elevator.c b/block/elevator.c index 440699c28119..52ada14cfe45 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -350,9 +350,11 @@ enum elv_merge elv_merge(struct request_queue *q, struct request **req, * we can append 'rq' to an existing request, so we can throw 'rq' away * afterwards. * - * Returns true if we merged, false otherwise + * Returns true if we merged, false otherwise. 'free' will contain all + * requests that need to be freed. */ -bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq) +bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq, + struct list_head *free) { struct request *__rq; bool ret; @@ -363,8 +365,10 @@ bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq) /* * First try one-hit cache. */ - if (q->last_merge && blk_attempt_req_merge(q, q->last_merge, rq)) + if (q->last_merge && blk_attempt_req_merge(q, q->last_merge, rq)) { + list_add(&rq->queuelist, free); return true; + } if (blk_queue_noxmerges(q)) return false; @@ -378,6 +382,7 @@ bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq) if (!__rq || !blk_attempt_req_merge(q, __rq, rq)) break; + list_add(&rq->queuelist, free); /* The merged request could be merged with others, try again */ ret = true; rq = __rq; @@ -522,6 +527,10 @@ void elv_unregister_queue(struct request_queue *q) int elv_register(struct elevator_type *e) { + /* insert_requests and dispatch_request are mandatory */ + if (WARN_ON_ONCE(!e->ops.insert_requests || !e->ops.dispatch_request)) + return -EINVAL; + /* create icq_cache if requested */ if (e->icq_size) { if (WARN_ON(e->icq_size < sizeof(struct io_cq)) || @@ -693,7 +702,7 @@ void elevator_init_mq(struct request_queue *q) elevator_put(e); } } - +EXPORT_SYMBOL_GPL(elevator_init_mq); /* only for dm-rq */ /* * switch to new_e io scheduler. be careful not to introduce deadlocks - diff --git a/block/genhd.c b/block/genhd.c index 9f8cb7beaad1..79aa40b4c39c 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -33,13 +33,6 @@ static struct kobject *block_depr; #define NR_EXT_DEVT (1 << MINORBITS) static DEFINE_IDA(ext_devt_ida); -static void disk_check_events(struct disk_events *ev, - unsigned int *clearing_ptr); -static void disk_alloc_events(struct gendisk *disk); -static void disk_add_events(struct gendisk *disk); -static void disk_del_events(struct gendisk *disk); -static void disk_release_events(struct gendisk *disk); - void set_capacity(struct gendisk *disk, sector_t sectors) { struct block_device *bdev = disk->part0; @@ -333,52 +326,22 @@ static int blk_mangle_minor(int minor) return minor; } -/** - * blk_alloc_devt - allocate a dev_t for a block device - * @bdev: block device to allocate dev_t for - * @devt: out parameter for resulting dev_t - * - * Allocate a dev_t for block device. - * - * RETURNS: - * 0 on success, allocated dev_t is returned in *@devt. -errno on - * failure. - * - * CONTEXT: - * Might sleep. - */ -int blk_alloc_devt(struct block_device *bdev, dev_t *devt) +int blk_alloc_ext_minor(void) { - struct gendisk *disk = bdev->bd_disk; int idx; - /* in consecutive minor range? */ - if (bdev->bd_partno < disk->minors) { - *devt = MKDEV(disk->major, disk->first_minor + bdev->bd_partno); - return 0; - } - idx = ida_alloc_range(&ext_devt_ida, 0, NR_EXT_DEVT, GFP_KERNEL); - if (idx < 0) - return idx == -ENOSPC ? -EBUSY : idx; - - *devt = MKDEV(BLOCK_EXT_MAJOR, blk_mangle_minor(idx)); - return 0; + if (idx < 0) { + if (idx == -ENOSPC) + return -EBUSY; + return idx; + } + return blk_mangle_minor(idx); } -/** - * blk_free_devt - free a dev_t - * @devt: dev_t to free - * - * Free @devt which was allocated using blk_alloc_devt(). - * - * CONTEXT: - * Might sleep. - */ -void blk_free_devt(dev_t devt) +void blk_free_ext_minor(unsigned int minor) { - if (MAJOR(devt) == BLOCK_EXT_MAJOR) - ida_free(&ext_devt_ida, blk_mangle_minor(MINOR(devt))); + ida_free(&ext_devt_ida, blk_mangle_minor(minor)); } static char *bdevt_str(dev_t devt, char *buf) @@ -499,8 +462,7 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups, bool register_queue) { - dev_t devt; - int retval; + int ret; /* * The disk queue should now be all set with enough information about @@ -511,24 +473,36 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, if (register_queue) elevator_init_mq(disk->queue); - /* minors == 0 indicates to use ext devt from part0 and should - * be accompanied with EXT_DEVT flag. Make sure all - * parameters make sense. + /* + * If the driver provides an explicit major number it also must provide + * the number of minors numbers supported, and those will be used to + * setup the gendisk. + * Otherwise just allocate the device numbers for both the whole device + * and all partitions from the extended dev_t space. */ - WARN_ON(disk->minors && !(disk->major || disk->first_minor)); - WARN_ON(!disk->minors && - !(disk->flags & (GENHD_FL_EXT_DEVT | GENHD_FL_HIDDEN))); + if (disk->major) { + WARN_ON(!disk->minors); + + if (disk->minors > DISK_MAX_PARTS) { + pr_err("block: can't allocate more than %d partitions\n", + DISK_MAX_PARTS); + disk->minors = DISK_MAX_PARTS; + } + } else { + WARN_ON(disk->minors); + + ret = blk_alloc_ext_minor(); + if (ret < 0) { + WARN_ON(1); + return; + } + disk->major = BLOCK_EXT_MAJOR; + disk->first_minor = MINOR(ret); + disk->flags |= GENHD_FL_EXT_DEVT; + } disk->flags |= GENHD_FL_UP; - retval = blk_alloc_devt(disk->part0, &devt); - if (retval) { - WARN_ON(1); - return; - } - disk->major = MAJOR(devt); - disk->first_minor = MINOR(devt); - disk_alloc_events(disk); if (disk->flags & GENHD_FL_HIDDEN) { @@ -541,14 +515,14 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, } else { struct backing_dev_info *bdi = disk->queue->backing_dev_info; struct device *dev = disk_to_dev(disk); - int ret; /* Register BDI before referencing it from bdev */ - dev->devt = devt; - ret = bdi_register(bdi, "%u:%u", MAJOR(devt), MINOR(devt)); + dev->devt = MKDEV(disk->major, disk->first_minor); + ret = bdi_register(bdi, "%u:%u", + disk->major, disk->first_minor); WARN_ON(ret); bdi_set_owner(bdi, dev); - bdev_add(disk->part0, devt); + bdev_add(disk->part0, dev->devt); } register_disk(parent, disk, groups); if (register_queue) @@ -558,7 +532,10 @@ static void __device_add_disk(struct device *parent, struct gendisk *disk, * Take an extra ref on queue which will be put on disk_release() * so that it sticks around as long as @disk is there. */ - WARN_ON_ONCE(!blk_get_queue(disk->queue)); + if (blk_get_queue(disk->queue)) + set_bit(GD_QUEUE_REF, &disk->state); + else + WARN_ON_ONCE(1); disk_add_events(disk); blk_integrity_add(disk); @@ -607,10 +584,10 @@ void del_gendisk(struct gendisk *disk) blk_integrity_del(disk); disk_del_events(disk); - mutex_lock(&disk->part0->bd_mutex); + mutex_lock(&disk->open_mutex); disk->flags &= ~GENHD_FL_UP; blk_drop_partitions(disk); - mutex_unlock(&disk->part0->bd_mutex); + mutex_unlock(&disk->open_mutex); fsync_bdev(disk->part0); __invalidate_device(disk->part0, true); @@ -692,32 +669,6 @@ void blk_request_module(dev_t devt) request_module("block-major-%d", MAJOR(devt)); } -/** - * bdget_disk - do bdget() by gendisk and partition number - * @disk: gendisk of interest - * @partno: partition number - * - * Find partition @partno from @disk, do bdget() on it. - * - * CONTEXT: - * Don't care. - * - * RETURNS: - * Resulting block_device on success, NULL on failure. - */ -struct block_device *bdget_disk(struct gendisk *disk, int partno) -{ - struct block_device *bdev = NULL; - - rcu_read_lock(); - bdev = xa_load(&disk->part_tbl, partno); - if (bdev && !bdgrab(bdev)) - bdev = NULL; - rcu_read_unlock(); - - return bdev; -} - /* * print a full list of all partitions - intended for places where the root * filesystem can't be mounted and thus to give the victim some idea of what @@ -1071,6 +1022,9 @@ static struct attribute *disk_attrs[] = { &dev_attr_stat.attr, &dev_attr_inflight.attr, &dev_attr_badblocks.attr, + &dev_attr_events.attr, + &dev_attr_events_async.attr, + &dev_attr_events_poll_msecs.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif @@ -1120,12 +1074,13 @@ static void disk_release(struct device *dev) might_sleep(); - blk_free_devt(dev->devt); + if (MAJOR(dev->devt) == BLOCK_EXT_MAJOR) + blk_free_ext_minor(MINOR(dev->devt)); disk_release_events(disk); kfree(disk->random); xa_destroy(&disk->part_tbl); bdput(disk->part0); - if (disk->queue) + if (test_bit(GD_QUEUE_REF, &disk->state) && disk->queue) blk_put_queue(disk->queue); kfree(disk); } @@ -1242,6 +1197,20 @@ static int __init proc_genhd_init(void) module_init(proc_genhd_init); #endif /* CONFIG_PROC_FS */ +dev_t part_devt(struct gendisk *disk, u8 partno) +{ + struct block_device *part; + dev_t devt = 0; + + rcu_read_lock(); + part = xa_load(&disk->part_tbl, partno); + if (part) + devt = part->bd_dev; + rcu_read_unlock(); + + return devt; +} + dev_t blk_lookup_devt(const char *name, int partno) { dev_t devt = MKDEV(0, 0); @@ -1251,7 +1220,6 @@ dev_t blk_lookup_devt(const char *name, int partno) class_dev_iter_init(&iter, &block_class, NULL, &disk_type); while ((dev = class_dev_iter_next(&iter))) { struct gendisk *disk = dev_to_disk(dev); - struct block_device *part; if (strcmp(dev_name(dev), name)) continue; @@ -1262,13 +1230,10 @@ dev_t blk_lookup_devt(const char *name, int partno) */ devt = MKDEV(MAJOR(dev->devt), MINOR(dev->devt) + partno); - break; - } - part = bdget_disk(disk, partno); - if (part) { - devt = part->bd_dev; - bdput(part); - break; + } else { + devt = part_devt(disk, partno); + if (devt) + break; } } class_dev_iter_exit(&iter); @@ -1279,13 +1244,6 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) { struct gendisk *disk; - if (minors > DISK_MAX_PARTS) { - printk(KERN_ERR - "block: can't allocate more than %d partitions\n", - DISK_MAX_PARTS); - minors = DISK_MAX_PARTS; - } - disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id); if (!disk) return NULL; @@ -1295,6 +1253,7 @@ struct gendisk *__alloc_disk_node(int minors, int node_id) goto out_free_disk; disk->node_id = node_id; + mutex_init(&disk->open_mutex); xa_init(&disk->part_tbl); if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL)) goto out_destroy_part_tbl; @@ -1315,6 +1274,25 @@ out_free_disk: } EXPORT_SYMBOL(__alloc_disk_node); +struct gendisk *__blk_alloc_disk(int node) +{ + struct request_queue *q; + struct gendisk *disk; + + q = blk_alloc_queue(node); + if (!q) + return NULL; + + disk = __alloc_disk_node(0, node); + if (!disk) { + blk_cleanup_queue(q); + return NULL; + } + disk->queue = q; + return disk; +} +EXPORT_SYMBOL(__blk_alloc_disk); + /** * put_disk - decrements the gendisk refcount * @disk: the struct gendisk to decrement the refcount for @@ -1332,6 +1310,22 @@ void put_disk(struct gendisk *disk) } EXPORT_SYMBOL(put_disk); +/** + * blk_cleanup_disk - shutdown a gendisk allocated by blk_alloc_disk + * @disk: gendisk to shutdown + * + * Mark the queue hanging off @disk DYING, drain all pending requests, then mark + * the queue DEAD, destroy and put it and the gendisk structure. + * + * Context: can sleep + */ +void blk_cleanup_disk(struct gendisk *disk) +{ + blk_cleanup_queue(disk->queue); + put_disk(disk); +} +EXPORT_SYMBOL(blk_cleanup_disk); + static void set_disk_ro_uevent(struct gendisk *gd, int ro) { char event[] = "DISK_RO=1"; @@ -1369,488 +1363,3 @@ int bdev_read_only(struct block_device *bdev) return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); } EXPORT_SYMBOL(bdev_read_only); - -/* - * Disk events - monitor disk events like media change and eject request. - */ -struct disk_events { - struct list_head node; /* all disk_event's */ - struct gendisk *disk; /* the associated disk */ - spinlock_t lock; - - struct mutex block_mutex; /* protects blocking */ - int block; /* event blocking depth */ - unsigned int pending; /* events already sent out */ - unsigned int clearing; /* events being cleared */ - - long poll_msecs; /* interval, -1 for default */ - struct delayed_work dwork; -}; - -static const char *disk_events_strs[] = { - [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "media_change", - [ilog2(DISK_EVENT_EJECT_REQUEST)] = "eject_request", -}; - -static char *disk_uevents[] = { - [ilog2(DISK_EVENT_MEDIA_CHANGE)] = "DISK_MEDIA_CHANGE=1", - [ilog2(DISK_EVENT_EJECT_REQUEST)] = "DISK_EJECT_REQUEST=1", -}; - -/* list of all disk_events */ -static DEFINE_MUTEX(disk_events_mutex); -static LIST_HEAD(disk_events); - -/* disable in-kernel polling by default */ -static unsigned long disk_events_dfl_poll_msecs; - -static unsigned long disk_events_poll_jiffies(struct gendisk *disk) -{ - struct disk_events *ev = disk->ev; - long intv_msecs = 0; - - /* - * If device-specific poll interval is set, always use it. If - * the default is being used, poll if the POLL flag is set. - */ - if (ev->poll_msecs >= 0) - intv_msecs = ev->poll_msecs; - else if (disk->event_flags & DISK_EVENT_FLAG_POLL) - intv_msecs = disk_events_dfl_poll_msecs; - - return msecs_to_jiffies(intv_msecs); -} - -/** - * disk_block_events - block and flush disk event checking - * @disk: disk to block events for - * - * On return from this function, it is guaranteed that event checking - * isn't in progress and won't happen until unblocked by - * disk_unblock_events(). Events blocking is counted and the actual - * unblocking happens after the matching number of unblocks are done. - * - * Note that this intentionally does not block event checking from - * disk_clear_events(). - * - * CONTEXT: - * Might sleep. - */ -void disk_block_events(struct gendisk *disk) -{ - struct disk_events *ev = disk->ev; - unsigned long flags; - bool cancel; - - if (!ev) - return; - - /* - * Outer mutex ensures that the first blocker completes canceling - * the event work before further blockers are allowed to finish. - */ - mutex_lock(&ev->block_mutex); - - spin_lock_irqsave(&ev->lock, flags); - cancel = !ev->block++; - spin_unlock_irqrestore(&ev->lock, flags); - - if (cancel) - cancel_delayed_work_sync(&disk->ev->dwork); - - mutex_unlock(&ev->block_mutex); -} - -static void __disk_unblock_events(struct gendisk *disk, bool check_now) -{ - struct disk_events *ev = disk->ev; - unsigned long intv; - unsigned long flags; - - spin_lock_irqsave(&ev->lock, flags); - - if (WARN_ON_ONCE(ev->block <= 0)) - goto out_unlock; - - if (--ev->block) - goto out_unlock; - - intv = disk_events_poll_jiffies(disk); - if (check_now) - queue_delayed_work(system_freezable_power_efficient_wq, - &ev->dwork, 0); - else if (intv) - queue_delayed_work(system_freezable_power_efficient_wq, - &ev->dwork, intv); -out_unlock: - spin_unlock_irqrestore(&ev->lock, flags); -} - -/** - * disk_unblock_events - unblock disk event checking - * @disk: disk to unblock events for - * - * Undo disk_block_events(). When the block count reaches zero, it - * starts events polling if configured. - * - * CONTEXT: - * Don't care. Safe to call from irq context. - */ -void disk_unblock_events(struct gendisk *disk) -{ - if (disk->ev) - __disk_unblock_events(disk, false); -} - -/** - * disk_flush_events - schedule immediate event checking and flushing - * @disk: disk to check and flush events for - * @mask: events to flush - * - * Schedule immediate event checking on @disk if not blocked. Events in - * @mask are scheduled to be cleared from the driver. Note that this - * doesn't clear the events from @disk->ev. - * - * CONTEXT: - * If @mask is non-zero must be called with bdev->bd_mutex held. - */ -void disk_flush_events(struct gendisk *disk, unsigned int mask) -{ - struct disk_events *ev = disk->ev; - - if (!ev) - return; - - spin_lock_irq(&ev->lock); - ev->clearing |= mask; - if (!ev->block) - mod_delayed_work(system_freezable_power_efficient_wq, - &ev->dwork, 0); - spin_unlock_irq(&ev->lock); -} - -/** - * disk_clear_events - synchronously check, clear and return pending events - * @disk: disk to fetch and clear events from - * @mask: mask of events to be fetched and cleared - * - * Disk events are synchronously checked and pending events in @mask - * are cleared and returned. This ignores the block count. - * - * CONTEXT: - * Might sleep. - */ -static unsigned int disk_clear_events(struct gendisk *disk, unsigned int mask) -{ - struct disk_events *ev = disk->ev; - unsigned int pending; - unsigned int clearing = mask; - - if (!ev) - return 0; - - disk_block_events(disk); - - /* - * store the union of mask and ev->clearing on the stack so that the - * race with disk_flush_events does not cause ambiguity (ev->clearing - * can still be modified even if events are blocked). - */ - spin_lock_irq(&ev->lock); - clearing |= ev->clearing; - ev->clearing = 0; - spin_unlock_irq(&ev->lock); - - disk_check_events(ev, &clearing); - /* - * if ev->clearing is not 0, the disk_flush_events got called in the - * middle of this function, so we want to run the workfn without delay. - */ - __disk_unblock_events(disk, ev->clearing ? true : false); - - /* then, fetch and clear pending events */ - spin_lock_irq(&ev->lock); - pending = ev->pending & mask; - ev->pending &= ~mask; - spin_unlock_irq(&ev->lock); - WARN_ON_ONCE(clearing & mask); - - return pending; -} - -/** - * bdev_check_media_change - check if a removable media has been changed - * @bdev: block device to check - * - * Check whether a removable media has been changed, and attempt to free all - * dentries and inodes and invalidates all block device page cache entries in - * that case. - * - * Returns %true if the block device changed, or %false if not. - */ -bool bdev_check_media_change(struct block_device *bdev) -{ - unsigned int events; - - events = disk_clear_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE | - DISK_EVENT_EJECT_REQUEST); - if (!(events & DISK_EVENT_MEDIA_CHANGE)) - return false; - - if (__invalidate_device(bdev, true)) - pr_warn("VFS: busy inodes on changed media %s\n", - bdev->bd_disk->disk_name); - set_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); - return true; -} -EXPORT_SYMBOL(bdev_check_media_change); - -/* - * Separate this part out so that a different pointer for clearing_ptr can be - * passed in for disk_clear_events. - */ -static void disk_events_workfn(struct work_struct *work) -{ - struct delayed_work *dwork = to_delayed_work(work); - struct disk_events *ev = container_of(dwork, struct disk_events, dwork); - - disk_check_events(ev, &ev->clearing); -} - -static void disk_check_events(struct disk_events *ev, - unsigned int *clearing_ptr) -{ - struct gendisk *disk = ev->disk; - char *envp[ARRAY_SIZE(disk_uevents) + 1] = { }; - unsigned int clearing = *clearing_ptr; - unsigned int events; - unsigned long intv; - int nr_events = 0, i; - - /* check events */ - events = disk->fops->check_events(disk, clearing); - - /* accumulate pending events and schedule next poll if necessary */ - spin_lock_irq(&ev->lock); - - events &= ~ev->pending; - ev->pending |= events; - *clearing_ptr &= ~clearing; - - intv = disk_events_poll_jiffies(disk); - if (!ev->block && intv) - queue_delayed_work(system_freezable_power_efficient_wq, - &ev->dwork, intv); - - spin_unlock_irq(&ev->lock); - - /* - * Tell userland about new events. Only the events listed in - * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT - * is set. Otherwise, events are processed internally but never - * get reported to userland. - */ - for (i = 0; i < ARRAY_SIZE(disk_uevents); i++) - if ((events & disk->events & (1 << i)) && - (disk->event_flags & DISK_EVENT_FLAG_UEVENT)) - envp[nr_events++] = disk_uevents[i]; - - if (nr_events) - kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); -} - -/* - * A disk events enabled device has the following sysfs nodes under - * its /sys/block/X/ directory. - * - * events : list of all supported events - * events_async : list of events which can be detected w/o polling - * (always empty, only for backwards compatibility) - * events_poll_msecs : polling interval, 0: disable, -1: system default - */ -static ssize_t __disk_events_show(unsigned int events, char *buf) -{ - const char *delim = ""; - ssize_t pos = 0; - int i; - - for (i = 0; i < ARRAY_SIZE(disk_events_strs); i++) - if (events & (1 << i)) { - pos += sprintf(buf + pos, "%s%s", - delim, disk_events_strs[i]); - delim = " "; - } - if (pos) - pos += sprintf(buf + pos, "\n"); - return pos; -} - -static ssize_t disk_events_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct gendisk *disk = dev_to_disk(dev); - - if (!(disk->event_flags & DISK_EVENT_FLAG_UEVENT)) - return 0; - - return __disk_events_show(disk->events, buf); -} - -static ssize_t disk_events_async_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return 0; -} - -static ssize_t disk_events_poll_msecs_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct gendisk *disk = dev_to_disk(dev); - - if (!disk->ev) - return sprintf(buf, "-1\n"); - - return sprintf(buf, "%ld\n", disk->ev->poll_msecs); -} - -static ssize_t disk_events_poll_msecs_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct gendisk *disk = dev_to_disk(dev); - long intv; - - if (!count || !sscanf(buf, "%ld", &intv)) - return -EINVAL; - - if (intv < 0 && intv != -1) - return -EINVAL; - - if (!disk->ev) - return -ENODEV; - - disk_block_events(disk); - disk->ev->poll_msecs = intv; - __disk_unblock_events(disk, true); - - return count; -} - -static const DEVICE_ATTR(events, 0444, disk_events_show, NULL); -static const DEVICE_ATTR(events_async, 0444, disk_events_async_show, NULL); -static const DEVICE_ATTR(events_poll_msecs, 0644, - disk_events_poll_msecs_show, - disk_events_poll_msecs_store); - -static const struct attribute *disk_events_attrs[] = { - &dev_attr_events.attr, - &dev_attr_events_async.attr, - &dev_attr_events_poll_msecs.attr, - NULL, -}; - -/* - * The default polling interval can be specified by the kernel - * parameter block.events_dfl_poll_msecs which defaults to 0 - * (disable). This can also be modified runtime by writing to - * /sys/module/block/parameters/events_dfl_poll_msecs. - */ -static int disk_events_set_dfl_poll_msecs(const char *val, - const struct kernel_param *kp) -{ - struct disk_events *ev; - int ret; - - ret = param_set_ulong(val, kp); - if (ret < 0) - return ret; - - mutex_lock(&disk_events_mutex); - - list_for_each_entry(ev, &disk_events, node) - disk_flush_events(ev->disk, 0); - - mutex_unlock(&disk_events_mutex); - - return 0; -} - -static const struct kernel_param_ops disk_events_dfl_poll_msecs_param_ops = { - .set = disk_events_set_dfl_poll_msecs, - .get = param_get_ulong, -}; - -#undef MODULE_PARAM_PREFIX -#define MODULE_PARAM_PREFIX "block." - -module_param_cb(events_dfl_poll_msecs, &disk_events_dfl_poll_msecs_param_ops, - &disk_events_dfl_poll_msecs, 0644); - -/* - * disk_{alloc|add|del|release}_events - initialize and destroy disk_events. - */ -static void disk_alloc_events(struct gendisk *disk) -{ - struct disk_events *ev; - - if (!disk->fops->check_events || !disk->events) - return; - - ev = kzalloc(sizeof(*ev), GFP_KERNEL); - if (!ev) { - pr_warn("%s: failed to initialize events\n", disk->disk_name); - return; - } - - INIT_LIST_HEAD(&ev->node); - ev->disk = disk; - spin_lock_init(&ev->lock); - mutex_init(&ev->block_mutex); - ev->block = 1; - ev->poll_msecs = -1; - INIT_DELAYED_WORK(&ev->dwork, disk_events_workfn); - - disk->ev = ev; -} - -static void disk_add_events(struct gendisk *disk) -{ - /* FIXME: error handling */ - if (sysfs_create_files(&disk_to_dev(disk)->kobj, disk_events_attrs) < 0) - pr_warn("%s: failed to create sysfs files for events\n", - disk->disk_name); - - if (!disk->ev) - return; - - mutex_lock(&disk_events_mutex); - list_add_tail(&disk->ev->node, &disk_events); - mutex_unlock(&disk_events_mutex); - - /* - * Block count is initialized to 1 and the following initial - * unblock kicks it into action. - */ - __disk_unblock_events(disk, true); -} - -static void disk_del_events(struct gendisk *disk) -{ - if (disk->ev) { - disk_block_events(disk); - - mutex_lock(&disk_events_mutex); - list_del_init(&disk->ev->node); - mutex_unlock(&disk_events_mutex); - } - - sysfs_remove_files(&disk_to_dev(disk)->kobj, disk_events_attrs); -} - -static void disk_release_events(struct gendisk *disk) -{ - /* the block count should be 1 from disk_del_events() */ - WARN_ON_ONCE(disk->ev && disk->ev->block != 1); - kfree(disk->ev); -} diff --git a/block/ioctl.c b/block/ioctl.c index 8ba1ed8defd0..24beec9ca9c9 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -89,7 +89,7 @@ static int blkdev_reread_part(struct block_device *bdev, fmode_t mode) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; - if (bdev->bd_part_count) + if (bdev->bd_disk->open_partitions) return -EBUSY; /* diff --git a/block/mq-deadline-cgroup.c b/block/mq-deadline-cgroup.c new file mode 100644 index 000000000000..3b4bfddec39f --- /dev/null +++ b/block/mq-deadline-cgroup.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +#include "mq-deadline-cgroup.h" + +static struct blkcg_policy dd_blkcg_policy; + +static struct blkcg_policy_data *dd_cpd_alloc(gfp_t gfp) +{ + struct dd_blkcg *pd; + + pd = kzalloc(sizeof(*pd), gfp); + if (!pd) + return NULL; + pd->stats = alloc_percpu_gfp(typeof(*pd->stats), + GFP_KERNEL | __GFP_ZERO); + if (!pd->stats) { + kfree(pd); + return NULL; + } + return &pd->cpd; +} + +static void dd_cpd_free(struct blkcg_policy_data *cpd) +{ + struct dd_blkcg *dd_blkcg = container_of(cpd, typeof(*dd_blkcg), cpd); + + free_percpu(dd_blkcg->stats); + kfree(dd_blkcg); +} + +static struct dd_blkcg *dd_blkcg_from_pd(struct blkg_policy_data *pd) +{ + return container_of(blkcg_to_cpd(pd->blkg->blkcg, &dd_blkcg_policy), + struct dd_blkcg, cpd); +} + +/* + * Convert an association between a block cgroup and a request queue into a + * pointer to the mq-deadline information associated with a (blkcg, queue) pair. + */ +struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio) +{ + struct blkg_policy_data *pd; + + pd = blkg_to_pd(bio->bi_blkg, &dd_blkcg_policy); + if (!pd) + return NULL; + + return dd_blkcg_from_pd(pd); +} + +static size_t dd_pd_stat(struct blkg_policy_data *pd, char *buf, size_t size) +{ + static const char *const prio_class_name[] = { + [IOPRIO_CLASS_NONE] = "NONE", + [IOPRIO_CLASS_RT] = "RT", + [IOPRIO_CLASS_BE] = "BE", + [IOPRIO_CLASS_IDLE] = "IDLE", + }; + struct dd_blkcg *blkcg = dd_blkcg_from_pd(pd); + int res = 0; + u8 prio; + + for (prio = 0; prio < ARRAY_SIZE(blkcg->stats->stats); prio++) + res += scnprintf(buf + res, size - res, + " [%s] dispatched=%u inserted=%u merged=%u", + prio_class_name[prio], + ddcg_sum(blkcg, dispatched, prio) + + ddcg_sum(blkcg, merged, prio) - + ddcg_sum(blkcg, completed, prio), + ddcg_sum(blkcg, inserted, prio) - + ddcg_sum(blkcg, completed, prio), + ddcg_sum(blkcg, merged, prio)); + + return res; +} + +static struct blkg_policy_data *dd_pd_alloc(gfp_t gfp, struct request_queue *q, + struct blkcg *blkcg) +{ + struct dd_blkg *pd; + + pd = kzalloc(sizeof(*pd), gfp); + if (!pd) + return NULL; + return &pd->pd; +} + +static void dd_pd_free(struct blkg_policy_data *pd) +{ + struct dd_blkg *dd_blkg = container_of(pd, typeof(*dd_blkg), pd); + + kfree(dd_blkg); +} + +static struct blkcg_policy dd_blkcg_policy = { + .cpd_alloc_fn = dd_cpd_alloc, + .cpd_free_fn = dd_cpd_free, + + .pd_alloc_fn = dd_pd_alloc, + .pd_free_fn = dd_pd_free, + .pd_stat_fn = dd_pd_stat, +}; + +int dd_activate_policy(struct request_queue *q) +{ + return blkcg_activate_policy(q, &dd_blkcg_policy); +} + +void dd_deactivate_policy(struct request_queue *q) +{ + blkcg_deactivate_policy(q, &dd_blkcg_policy); +} + +int __init dd_blkcg_init(void) +{ + return blkcg_policy_register(&dd_blkcg_policy); +} + +void __exit dd_blkcg_exit(void) +{ + blkcg_policy_unregister(&dd_blkcg_policy); +} diff --git a/block/mq-deadline-cgroup.h b/block/mq-deadline-cgroup.h new file mode 100644 index 000000000000..0143fd74f3ce --- /dev/null +++ b/block/mq-deadline-cgroup.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#if !defined(_MQ_DEADLINE_CGROUP_H_) +#define _MQ_DEADLINE_CGROUP_H_ + +#include + +struct request_queue; + +/** + * struct io_stats_per_prio - I/O statistics per I/O priority class. + * @inserted: Number of inserted requests. + * @merged: Number of merged requests. + * @dispatched: Number of dispatched requests. + * @completed: Number of I/O completions. + */ +struct io_stats_per_prio { + local_t inserted; + local_t merged; + local_t dispatched; + local_t completed; +}; + +/* I/O statistics per I/O cgroup per I/O priority class (IOPRIO_CLASS_*). */ +struct blkcg_io_stats { + struct io_stats_per_prio stats[4]; +}; + +/** + * struct dd_blkcg - Per cgroup data. + * @cpd: blkcg_policy_data structure. + * @stats: I/O statistics. + */ +struct dd_blkcg { + struct blkcg_policy_data cpd; /* must be the first member */ + struct blkcg_io_stats __percpu *stats; +}; + +/* + * Count one event of type 'event_type' and with I/O priority class + * 'prio_class'. + */ +#define ddcg_count(ddcg, event_type, prio_class) do { \ +if (ddcg) { \ + struct blkcg_io_stats *io_stats = get_cpu_ptr((ddcg)->stats); \ + \ + BUILD_BUG_ON(!__same_type((ddcg), struct dd_blkcg *)); \ + BUILD_BUG_ON(!__same_type((prio_class), u8)); \ + local_inc(&io_stats->stats[(prio_class)].event_type); \ + put_cpu_ptr(io_stats); \ +} \ +} while (0) + +/* + * Returns the total number of ddcg_count(ddcg, event_type, prio_class) calls + * across all CPUs. No locking or barriers since it is fine if the returned + * sum is slightly outdated. + */ +#define ddcg_sum(ddcg, event_type, prio) ({ \ + unsigned int cpu; \ + u32 sum = 0; \ + \ + BUILD_BUG_ON(!__same_type((ddcg), struct dd_blkcg *)); \ + BUILD_BUG_ON(!__same_type((prio), u8)); \ + for_each_present_cpu(cpu) \ + sum += local_read(&per_cpu_ptr((ddcg)->stats, cpu)-> \ + stats[(prio)].event_type); \ + sum; \ +}) + +#ifdef CONFIG_BLK_CGROUP + +/** + * struct dd_blkg - Per (cgroup, request queue) data. + * @pd: blkg_policy_data structure. + */ +struct dd_blkg { + struct blkg_policy_data pd; /* must be the first member */ +}; + +struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio); +int dd_activate_policy(struct request_queue *q); +void dd_deactivate_policy(struct request_queue *q); +int __init dd_blkcg_init(void); +void __exit dd_blkcg_exit(void); + +#else /* CONFIG_BLK_CGROUP */ + +static inline struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio) +{ + return NULL; +} + +static inline int dd_activate_policy(struct request_queue *q) +{ + return 0; +} + +static inline void dd_deactivate_policy(struct request_queue *q) +{ +} + +static inline int dd_blkcg_init(void) +{ + return 0; +} + +static inline void dd_blkcg_exit(void) +{ +} + +#endif /* CONFIG_BLK_CGROUP */ + +#endif /* _MQ_DEADLINE_CGROUP_H_ */ diff --git a/block/mq-deadline-main.c b/block/mq-deadline-main.c new file mode 100644 index 000000000000..6f612e6dc82b --- /dev/null +++ b/block/mq-deadline-main.c @@ -0,0 +1,1175 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * MQ Deadline i/o scheduler - adaptation of the legacy deadline scheduler, + * for the blk-mq scheduling framework + * + * Copyright (C) 2016 Jens Axboe + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "blk.h" +#include "blk-mq.h" +#include "blk-mq-debugfs.h" +#include "blk-mq-tag.h" +#include "blk-mq-sched.h" +#include "mq-deadline-cgroup.h" + +/* + * See Documentation/block/deadline-iosched.rst + */ +static const int read_expire = HZ / 2; /* max time before a read is submitted. */ +static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */ +/* + * Time after which to dispatch lower priority requests even if higher + * priority requests are pending. + */ +static const int aging_expire = 10 * HZ; +static const int writes_starved = 2; /* max times reads can starve a write */ +static const int fifo_batch = 16; /* # of sequential requests treated as one + by the above parameters. For throughput. */ + +enum dd_data_dir { + DD_READ = READ, + DD_WRITE = WRITE, +}; + +enum { DD_DIR_COUNT = 2 }; + +enum dd_prio { + DD_RT_PRIO = 0, + DD_BE_PRIO = 1, + DD_IDLE_PRIO = 2, + DD_PRIO_MAX = 2, +}; + +enum { DD_PRIO_COUNT = 3 }; + +/* I/O statistics for all I/O priorities (enum dd_prio). */ +struct io_stats { + struct io_stats_per_prio stats[DD_PRIO_COUNT]; +}; + +/* + * Deadline scheduler data per I/O priority (enum dd_prio). Requests are + * present on both sort_list[] and fifo_list[]. + */ +struct dd_per_prio { + struct list_head dispatch; + struct rb_root sort_list[DD_DIR_COUNT]; + struct list_head fifo_list[DD_DIR_COUNT]; + /* Next request in FIFO order. Read, write or both are NULL. */ + struct request *next_rq[DD_DIR_COUNT]; +}; + +struct deadline_data { + /* + * run time data + */ + + /* Request queue that owns this data structure. */ + struct request_queue *queue; + + struct dd_per_prio per_prio[DD_PRIO_COUNT]; + + /* Data direction of latest dispatched request. */ + enum dd_data_dir last_dir; + unsigned int batching; /* number of sequential requests made */ + unsigned int starved; /* times reads have starved writes */ + + struct io_stats __percpu *stats; + + /* + * settings that change how the i/o scheduler behaves + */ + int fifo_expire[DD_DIR_COUNT]; + int fifo_batch; + int writes_starved; + int front_merges; + u32 async_depth; + int aging_expire; + + spinlock_t lock; + spinlock_t zone_lock; +}; + +/* Count one event of type 'event_type' and with I/O priority 'prio' */ +#define dd_count(dd, event_type, prio) do { \ + struct io_stats *io_stats = get_cpu_ptr((dd)->stats); \ + \ + BUILD_BUG_ON(!__same_type((dd), struct deadline_data *)); \ + BUILD_BUG_ON(!__same_type((prio), enum dd_prio)); \ + local_inc(&io_stats->stats[(prio)].event_type); \ + put_cpu_ptr(io_stats); \ +} while (0) + +/* + * Returns the total number of dd_count(dd, event_type, prio) calls across all + * CPUs. No locking or barriers since it is fine if the returned sum is slightly + * outdated. + */ +#define dd_sum(dd, event_type, prio) ({ \ + unsigned int cpu; \ + u32 sum = 0; \ + \ + BUILD_BUG_ON(!__same_type((dd), struct deadline_data *)); \ + BUILD_BUG_ON(!__same_type((prio), enum dd_prio)); \ + for_each_present_cpu(cpu) \ + sum += local_read(&per_cpu_ptr((dd)->stats, cpu)-> \ + stats[(prio)].event_type); \ + sum; \ +}) + +/* Maps an I/O priority class to a deadline scheduler priority. */ +static const enum dd_prio ioprio_class_to_prio[] = { + [IOPRIO_CLASS_NONE] = DD_BE_PRIO, + [IOPRIO_CLASS_RT] = DD_RT_PRIO, + [IOPRIO_CLASS_BE] = DD_BE_PRIO, + [IOPRIO_CLASS_IDLE] = DD_IDLE_PRIO, +}; + +static inline struct rb_root * +deadline_rb_root(struct dd_per_prio *per_prio, struct request *rq) +{ + return &per_prio->sort_list[rq_data_dir(rq)]; +} + +/* + * Returns the I/O priority class (IOPRIO_CLASS_*) that has been assigned to a + * request. + */ +static u8 dd_rq_ioclass(struct request *rq) +{ + return IOPRIO_PRIO_CLASS(req_get_ioprio(rq)); +} + +/* + * get the request after `rq' in sector-sorted order + */ +static inline struct request * +deadline_latter_request(struct request *rq) +{ + struct rb_node *node = rb_next(&rq->rb_node); + + if (node) + return rb_entry_rq(node); + + return NULL; +} + +static void +deadline_add_rq_rb(struct dd_per_prio *per_prio, struct request *rq) +{ + struct rb_root *root = deadline_rb_root(per_prio, rq); + + elv_rb_add(root, rq); +} + +static inline void +deadline_del_rq_rb(struct dd_per_prio *per_prio, struct request *rq) +{ + const enum dd_data_dir data_dir = rq_data_dir(rq); + + if (per_prio->next_rq[data_dir] == rq) + per_prio->next_rq[data_dir] = deadline_latter_request(rq); + + elv_rb_del(deadline_rb_root(per_prio, rq), rq); +} + +/* + * remove rq from rbtree and fifo. + */ +static void deadline_remove_request(struct request_queue *q, + struct dd_per_prio *per_prio, + struct request *rq) +{ + list_del_init(&rq->queuelist); + + /* + * We might not be on the rbtree, if we are doing an insert merge + */ + if (!RB_EMPTY_NODE(&rq->rb_node)) + deadline_del_rq_rb(per_prio, rq); + + elv_rqhash_del(q, rq); + if (q->last_merge == rq) + q->last_merge = NULL; +} + +static void dd_request_merged(struct request_queue *q, struct request *req, + enum elv_merge type) +{ + struct deadline_data *dd = q->elevator->elevator_data; + const u8 ioprio_class = dd_rq_ioclass(req); + const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + + /* + * if the merge was a front merge, we need to reposition request + */ + if (type == ELEVATOR_FRONT_MERGE) { + elv_rb_del(deadline_rb_root(per_prio, req), req); + deadline_add_rq_rb(per_prio, req); + } +} + +/* + * Callback function that is invoked after @next has been merged into @req. + */ +static void dd_merged_requests(struct request_queue *q, struct request *req, + struct request *next) +{ + struct deadline_data *dd = q->elevator->elevator_data; + const u8 ioprio_class = dd_rq_ioclass(next); + const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + struct dd_blkcg *blkcg = next->elv.priv[0]; + + dd_count(dd, merged, prio); + ddcg_count(blkcg, merged, ioprio_class); + + /* + * if next expires before rq, assign its expire time to rq + * and move into next position (next will be deleted) in fifo + */ + if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) { + if (time_before((unsigned long)next->fifo_time, + (unsigned long)req->fifo_time)) { + list_move(&req->queuelist, &next->queuelist); + req->fifo_time = next->fifo_time; + } + } + + /* + * kill knowledge of next, this one is a goner + */ + deadline_remove_request(q, &dd->per_prio[prio], next); +} + +/* + * move an entry to dispatch queue + */ +static void +deadline_move_request(struct deadline_data *dd, struct dd_per_prio *per_prio, + struct request *rq) +{ + const enum dd_data_dir data_dir = rq_data_dir(rq); + + per_prio->next_rq[data_dir] = deadline_latter_request(rq); + + /* + * take it off the sort and fifo list + */ + deadline_remove_request(rq->q, per_prio, rq); +} + +/* Number of requests queued for a given priority level. */ +static u32 dd_queued(struct deadline_data *dd, enum dd_prio prio) +{ + return dd_sum(dd, inserted, prio) - dd_sum(dd, completed, prio); +} + +/* + * deadline_check_fifo returns 0 if there are no expired requests on the fifo, + * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir]) + */ +static inline int deadline_check_fifo(struct dd_per_prio *per_prio, + enum dd_data_dir data_dir) +{ + struct request *rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next); + + /* + * rq is expired! + */ + if (time_after_eq(jiffies, (unsigned long)rq->fifo_time)) + return 1; + + return 0; +} + +/* + * For the specified data direction, return the next request to + * dispatch using arrival ordered lists. + */ +static struct request * +deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio, + enum dd_data_dir data_dir) +{ + struct request *rq; + unsigned long flags; + + if (list_empty(&per_prio->fifo_list[data_dir])) + return NULL; + + rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next); + if (data_dir == DD_READ || !blk_queue_is_zoned(rq->q)) + return rq; + + /* + * Look for a write request that can be dispatched, that is one with + * an unlocked target zone. + */ + spin_lock_irqsave(&dd->zone_lock, flags); + list_for_each_entry(rq, &per_prio->fifo_list[DD_WRITE], queuelist) { + if (blk_req_can_dispatch_to_zone(rq)) + goto out; + } + rq = NULL; +out: + spin_unlock_irqrestore(&dd->zone_lock, flags); + + return rq; +} + +/* + * For the specified data direction, return the next request to + * dispatch using sector position sorted lists. + */ +static struct request * +deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio, + enum dd_data_dir data_dir) +{ + struct request *rq; + unsigned long flags; + + rq = per_prio->next_rq[data_dir]; + if (!rq) + return NULL; + + if (data_dir == DD_READ || !blk_queue_is_zoned(rq->q)) + return rq; + + /* + * Look for a write request that can be dispatched, that is one with + * an unlocked target zone. + */ + spin_lock_irqsave(&dd->zone_lock, flags); + while (rq) { + if (blk_req_can_dispatch_to_zone(rq)) + break; + rq = deadline_latter_request(rq); + } + spin_unlock_irqrestore(&dd->zone_lock, flags); + + return rq; +} + +/* + * deadline_dispatch_requests selects the best request according to + * read/write expire, fifo_batch, etc and with a start time <= @latest. + */ +static struct request *__dd_dispatch_request(struct deadline_data *dd, + struct dd_per_prio *per_prio, + u64 latest_start_ns) +{ + struct request *rq, *next_rq; + enum dd_data_dir data_dir; + struct dd_blkcg *blkcg; + enum dd_prio prio; + u8 ioprio_class; + + lockdep_assert_held(&dd->lock); + + if (!list_empty(&per_prio->dispatch)) { + rq = list_first_entry(&per_prio->dispatch, struct request, + queuelist); + if (rq->start_time_ns > latest_start_ns) + return NULL; + list_del_init(&rq->queuelist); + goto done; + } + + /* + * batches are currently reads XOR writes + */ + rq = deadline_next_request(dd, per_prio, dd->last_dir); + if (rq && dd->batching < dd->fifo_batch) + /* we have a next request are still entitled to batch */ + goto dispatch_request; + + /* + * at this point we are not running a batch. select the appropriate + * data direction (read / write) + */ + + if (!list_empty(&per_prio->fifo_list[DD_READ])) { + BUG_ON(RB_EMPTY_ROOT(&per_prio->sort_list[DD_READ])); + + if (deadline_fifo_request(dd, per_prio, DD_WRITE) && + (dd->starved++ >= dd->writes_starved)) + goto dispatch_writes; + + data_dir = DD_READ; + + goto dispatch_find_request; + } + + /* + * there are either no reads or writes have been starved + */ + + if (!list_empty(&per_prio->fifo_list[DD_WRITE])) { +dispatch_writes: + BUG_ON(RB_EMPTY_ROOT(&per_prio->sort_list[DD_WRITE])); + + dd->starved = 0; + + data_dir = DD_WRITE; + + goto dispatch_find_request; + } + + return NULL; + +dispatch_find_request: + /* + * we are not running a batch, find best request for selected data_dir + */ + next_rq = deadline_next_request(dd, per_prio, data_dir); + if (deadline_check_fifo(per_prio, data_dir) || !next_rq) { + /* + * A deadline has expired, the last request was in the other + * direction, or we have run out of higher-sectored requests. + * Start again from the request with the earliest expiry time. + */ + rq = deadline_fifo_request(dd, per_prio, data_dir); + } else { + /* + * The last req was the same dir and we have a next request in + * sort order. No expired requests so continue on from here. + */ + rq = next_rq; + } + + /* + * For a zoned block device, if we only have writes queued and none of + * them can be dispatched, rq will be NULL. + */ + if (!rq) + return NULL; + + dd->last_dir = data_dir; + dd->batching = 0; + +dispatch_request: + if (rq->start_time_ns > latest_start_ns) + return NULL; + /* + * rq is the selected appropriate request. + */ + dd->batching++; + deadline_move_request(dd, per_prio, rq); +done: + ioprio_class = dd_rq_ioclass(rq); + prio = ioprio_class_to_prio[ioprio_class]; + dd_count(dd, dispatched, prio); + blkcg = rq->elv.priv[0]; + ddcg_count(blkcg, dispatched, ioprio_class); + /* + * If the request needs its target zone locked, do it. + */ + blk_req_zone_write_lock(rq); + rq->rq_flags |= RQF_STARTED; + return rq; +} + +/* + * Called from blk_mq_run_hw_queue() -> __blk_mq_sched_dispatch_requests(). + * + * One confusing aspect here is that we get called for a specific + * hardware queue, but we may return a request that is for a + * different hardware queue. This is because mq-deadline has shared + * state for all hardware queues, in terms of sorting, FIFOs, etc. + */ +static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx) +{ + struct deadline_data *dd = hctx->queue->elevator->elevator_data; + const u64 now_ns = ktime_get_ns(); + struct request *rq = NULL; + enum dd_prio prio; + + spin_lock(&dd->lock); + /* + * Start with dispatching requests whose deadline expired more than + * aging_expire jiffies ago. + */ + for (prio = DD_BE_PRIO; prio <= DD_PRIO_MAX; prio++) { + rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now_ns - + jiffies_to_nsecs(dd->aging_expire)); + if (rq) + goto unlock; + } + /* + * Next, dispatch requests in priority order. Ignore lower priority + * requests if any higher priority requests are pending. + */ + for (prio = 0; prio <= DD_PRIO_MAX; prio++) { + rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now_ns); + if (rq || dd_queued(dd, prio)) + break; + } + +unlock: + spin_unlock(&dd->lock); + + return rq; +} + +/* + * Called by __blk_mq_alloc_request(). The shallow_depth value set by this + * function is used by __blk_mq_get_tag(). + */ +static void dd_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) +{ + struct deadline_data *dd = data->q->elevator->elevator_data; + + /* Do not throttle synchronous reads. */ + if (op_is_sync(op) && !op_is_write(op)) + return; + + /* + * Throttle asynchronous requests and writes such that these requests + * do not block the allocation of synchronous requests. + */ + data->shallow_depth = dd->async_depth; +} + +/* Called by blk_mq_update_nr_requests(). */ +static void dd_depth_updated(struct blk_mq_hw_ctx *hctx) +{ + struct request_queue *q = hctx->queue; + struct deadline_data *dd = q->elevator->elevator_data; + struct blk_mq_tags *tags = hctx->sched_tags; + + dd->async_depth = max(1UL, 3 * q->nr_requests / 4); + + sbitmap_queue_min_shallow_depth(tags->bitmap_tags, dd->async_depth); +} + +/* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */ +static int dd_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) +{ + dd_depth_updated(hctx); + return 0; +} + +static void dd_exit_sched(struct elevator_queue *e) +{ + struct deadline_data *dd = e->elevator_data; + enum dd_prio prio; + + dd_deactivate_policy(dd->queue); + + for (prio = 0; prio <= DD_PRIO_MAX; prio++) { + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + + WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_READ])); + WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_WRITE])); + } + + free_percpu(dd->stats); + + kfree(dd); +} + +/* + * Initialize elevator private data (deadline_data) and associate with blkcg. + */ +static int dd_init_sched(struct request_queue *q, struct elevator_type *e) +{ + struct deadline_data *dd; + struct elevator_queue *eq; + enum dd_prio prio; + int ret = -ENOMEM; + + /* + * Initialization would be very tricky if the queue is not frozen, + * hence the warning statement below. + */ + WARN_ON_ONCE(!percpu_ref_is_zero(&q->q_usage_counter)); + + eq = elevator_alloc(q, e); + if (!eq) + return ret; + + dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node); + if (!dd) + goto put_eq; + + eq->elevator_data = dd; + + dd->stats = alloc_percpu_gfp(typeof(*dd->stats), + GFP_KERNEL | __GFP_ZERO); + if (!dd->stats) + goto free_dd; + + dd->queue = q; + + for (prio = 0; prio <= DD_PRIO_MAX; prio++) { + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + + INIT_LIST_HEAD(&per_prio->dispatch); + INIT_LIST_HEAD(&per_prio->fifo_list[DD_READ]); + INIT_LIST_HEAD(&per_prio->fifo_list[DD_WRITE]); + per_prio->sort_list[DD_READ] = RB_ROOT; + per_prio->sort_list[DD_WRITE] = RB_ROOT; + } + dd->fifo_expire[DD_READ] = read_expire; + dd->fifo_expire[DD_WRITE] = write_expire; + dd->writes_starved = writes_starved; + dd->front_merges = 1; + dd->last_dir = DD_WRITE; + dd->fifo_batch = fifo_batch; + dd->aging_expire = aging_expire; + spin_lock_init(&dd->lock); + spin_lock_init(&dd->zone_lock); + + ret = dd_activate_policy(q); + if (ret) + goto free_stats; + + ret = 0; + q->elevator = eq; + return 0; + +free_stats: + free_percpu(dd->stats); + +free_dd: + kfree(dd); + +put_eq: + kobject_put(&eq->kobj); + return ret; +} + +/* + * Try to merge @bio into an existing request. If @bio has been merged into + * an existing request, store the pointer to that request into *@rq. + */ +static int dd_request_merge(struct request_queue *q, struct request **rq, + struct bio *bio) +{ + struct deadline_data *dd = q->elevator->elevator_data; + const u8 ioprio_class = IOPRIO_PRIO_CLASS(bio->bi_ioprio); + const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + sector_t sector = bio_end_sector(bio); + struct request *__rq; + + if (!dd->front_merges) + return ELEVATOR_NO_MERGE; + + __rq = elv_rb_find(&per_prio->sort_list[bio_data_dir(bio)], sector); + if (__rq) { + BUG_ON(sector != blk_rq_pos(__rq)); + + if (elv_bio_merge_ok(__rq, bio)) { + *rq = __rq; + return ELEVATOR_FRONT_MERGE; + } + } + + return ELEVATOR_NO_MERGE; +} + +/* + * Attempt to merge a bio into an existing request. This function is called + * before @bio is associated with a request. + */ +static bool dd_bio_merge(struct request_queue *q, struct bio *bio, + unsigned int nr_segs) +{ + struct deadline_data *dd = q->elevator->elevator_data; + struct request *free = NULL; + bool ret; + + spin_lock(&dd->lock); + ret = blk_mq_sched_try_merge(q, bio, nr_segs, &free); + spin_unlock(&dd->lock); + + if (free) + blk_mq_free_request(free); + + return ret; +} + +/* + * add rq to rbtree and fifo + */ +static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, + bool at_head) +{ + struct request_queue *q = hctx->queue; + struct deadline_data *dd = q->elevator->elevator_data; + const enum dd_data_dir data_dir = rq_data_dir(rq); + u16 ioprio = req_get_ioprio(rq); + u8 ioprio_class = IOPRIO_PRIO_CLASS(ioprio); + struct dd_per_prio *per_prio; + enum dd_prio prio; + struct dd_blkcg *blkcg; + LIST_HEAD(free); + + lockdep_assert_held(&dd->lock); + + /* + * This may be a requeue of a write request that has locked its + * target zone. If it is the case, this releases the zone lock. + */ + blk_req_zone_write_unlock(rq); + + /* + * If a block cgroup has been associated with the submitter and if an + * I/O priority has been set in the associated block cgroup, use the + * lowest of the cgroup priority and the request priority for the + * request. If no priority has been set in the request, use the cgroup + * priority. + */ + prio = ioprio_class_to_prio[ioprio_class]; + dd_count(dd, inserted, prio); + blkcg = dd_blkcg_from_bio(rq->bio); + ddcg_count(blkcg, inserted, ioprio_class); + rq->elv.priv[0] = blkcg; + + if (blk_mq_sched_try_insert_merge(q, rq, &free)) { + blk_mq_free_requests(&free); + return; + } + + trace_block_rq_insert(rq); + + per_prio = &dd->per_prio[prio]; + if (at_head) { + list_add(&rq->queuelist, &per_prio->dispatch); + } else { + deadline_add_rq_rb(per_prio, rq); + + if (rq_mergeable(rq)) { + elv_rqhash_add(q, rq); + if (!q->last_merge) + q->last_merge = rq; + } + + /* + * set expire time and add to fifo list + */ + rq->fifo_time = jiffies + dd->fifo_expire[data_dir]; + list_add_tail(&rq->queuelist, &per_prio->fifo_list[data_dir]); + } +} + +/* + * Called from blk_mq_sched_insert_request() or blk_mq_sched_insert_requests(). + */ +static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, + struct list_head *list, bool at_head) +{ + struct request_queue *q = hctx->queue; + struct deadline_data *dd = q->elevator->elevator_data; + + spin_lock(&dd->lock); + while (!list_empty(list)) { + struct request *rq; + + rq = list_first_entry(list, struct request, queuelist); + list_del_init(&rq->queuelist); + dd_insert_request(hctx, rq, at_head); + } + spin_unlock(&dd->lock); +} + +/* Callback from inside blk_mq_rq_ctx_init(). */ +static void dd_prepare_request(struct request *rq) +{ + rq->elv.priv[0] = NULL; +} + +/* + * Callback from inside blk_mq_free_request(). + * + * For zoned block devices, write unlock the target zone of + * completed write requests. Do this while holding the zone lock + * spinlock so that the zone is never unlocked while deadline_fifo_request() + * or deadline_next_request() are executing. This function is called for + * all requests, whether or not these requests complete successfully. + * + * For a zoned block device, __dd_dispatch_request() may have stopped + * dispatching requests if all the queued requests are write requests directed + * at zones that are already locked due to on-going write requests. To ensure + * write request dispatch progress in this case, mark the queue as needing a + * restart to ensure that the queue is run again after completion of the + * request and zones being unlocked. + */ +static void dd_finish_request(struct request *rq) +{ + struct request_queue *q = rq->q; + struct deadline_data *dd = q->elevator->elevator_data; + struct dd_blkcg *blkcg = rq->elv.priv[0]; + const u8 ioprio_class = dd_rq_ioclass(rq); + const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; + struct dd_per_prio *per_prio = &dd->per_prio[prio]; + + dd_count(dd, completed, prio); + ddcg_count(blkcg, completed, ioprio_class); + + if (blk_queue_is_zoned(q)) { + unsigned long flags; + + spin_lock_irqsave(&dd->zone_lock, flags); + blk_req_zone_write_unlock(rq); + if (!list_empty(&per_prio->fifo_list[DD_WRITE])) + blk_mq_sched_mark_restart_hctx(rq->mq_hctx); + spin_unlock_irqrestore(&dd->zone_lock, flags); + } +} + +static bool dd_has_work_for_prio(struct dd_per_prio *per_prio) +{ + return !list_empty_careful(&per_prio->dispatch) || + !list_empty_careful(&per_prio->fifo_list[DD_READ]) || + !list_empty_careful(&per_prio->fifo_list[DD_WRITE]); +} + +static bool dd_has_work(struct blk_mq_hw_ctx *hctx) +{ + struct deadline_data *dd = hctx->queue->elevator->elevator_data; + enum dd_prio prio; + + for (prio = 0; prio <= DD_PRIO_MAX; prio++) + if (dd_has_work_for_prio(&dd->per_prio[prio])) + return true; + + return false; +} + +/* + * sysfs parts below + */ +#define SHOW_INT(__FUNC, __VAR) \ +static ssize_t __FUNC(struct elevator_queue *e, char *page) \ +{ \ + struct deadline_data *dd = e->elevator_data; \ + \ + return sysfs_emit(page, "%d\n", __VAR); \ +} +#define SHOW_JIFFIES(__FUNC, __VAR) SHOW_INT(__FUNC, jiffies_to_msecs(__VAR)) +SHOW_JIFFIES(deadline_read_expire_show, dd->fifo_expire[DD_READ]); +SHOW_JIFFIES(deadline_write_expire_show, dd->fifo_expire[DD_WRITE]); +SHOW_JIFFIES(deadline_aging_expire_show, dd->aging_expire); +SHOW_INT(deadline_writes_starved_show, dd->writes_starved); +SHOW_INT(deadline_front_merges_show, dd->front_merges); +SHOW_INT(deadline_async_depth_show, dd->front_merges); +SHOW_INT(deadline_fifo_batch_show, dd->fifo_batch); +#undef SHOW_INT +#undef SHOW_JIFFIES + +#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ +static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count) \ +{ \ + struct deadline_data *dd = e->elevator_data; \ + int __data, __ret; \ + \ + __ret = kstrtoint(page, 0, &__data); \ + if (__ret < 0) \ + return __ret; \ + if (__data < (MIN)) \ + __data = (MIN); \ + else if (__data > (MAX)) \ + __data = (MAX); \ + *(__PTR) = __CONV(__data); \ + return count; \ +} +#define STORE_INT(__FUNC, __PTR, MIN, MAX) \ + STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, ) +#define STORE_JIFFIES(__FUNC, __PTR, MIN, MAX) \ + STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, msecs_to_jiffies) +STORE_JIFFIES(deadline_read_expire_store, &dd->fifo_expire[DD_READ], 0, INT_MAX); +STORE_JIFFIES(deadline_write_expire_store, &dd->fifo_expire[DD_WRITE], 0, INT_MAX); +STORE_JIFFIES(deadline_aging_expire_store, &dd->aging_expire, 0, INT_MAX); +STORE_INT(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX); +STORE_INT(deadline_front_merges_store, &dd->front_merges, 0, 1); +STORE_INT(deadline_async_depth_store, &dd->front_merges, 1, INT_MAX); +STORE_INT(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX); +#undef STORE_FUNCTION +#undef STORE_INT +#undef STORE_JIFFIES + +#define DD_ATTR(name) \ + __ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store) + +static struct elv_fs_entry deadline_attrs[] = { + DD_ATTR(read_expire), + DD_ATTR(write_expire), + DD_ATTR(writes_starved), + DD_ATTR(front_merges), + DD_ATTR(async_depth), + DD_ATTR(fifo_batch), + DD_ATTR(aging_expire), + __ATTR_NULL +}; + +#ifdef CONFIG_BLK_DEBUG_FS +#define DEADLINE_DEBUGFS_DDIR_ATTRS(prio, data_dir, name) \ +static void *deadline_##name##_fifo_start(struct seq_file *m, \ + loff_t *pos) \ + __acquires(&dd->lock) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + \ + spin_lock(&dd->lock); \ + return seq_list_start(&per_prio->fifo_list[data_dir], *pos); \ +} \ + \ +static void *deadline_##name##_fifo_next(struct seq_file *m, void *v, \ + loff_t *pos) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + \ + return seq_list_next(v, &per_prio->fifo_list[data_dir], pos); \ +} \ + \ +static void deadline_##name##_fifo_stop(struct seq_file *m, void *v) \ + __releases(&dd->lock) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + \ + spin_unlock(&dd->lock); \ +} \ + \ +static const struct seq_operations deadline_##name##_fifo_seq_ops = { \ + .start = deadline_##name##_fifo_start, \ + .next = deadline_##name##_fifo_next, \ + .stop = deadline_##name##_fifo_stop, \ + .show = blk_mq_debugfs_rq_show, \ +}; \ + \ +static int deadline_##name##_next_rq_show(void *data, \ + struct seq_file *m) \ +{ \ + struct request_queue *q = data; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + struct request *rq = per_prio->next_rq[data_dir]; \ + \ + if (rq) \ + __blk_mq_debugfs_rq_show(m, rq); \ + return 0; \ +} + +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_RT_PRIO, DD_READ, read0); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_RT_PRIO, DD_WRITE, write0); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_BE_PRIO, DD_READ, read1); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_BE_PRIO, DD_WRITE, write1); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_IDLE_PRIO, DD_READ, read2); +DEADLINE_DEBUGFS_DDIR_ATTRS(DD_IDLE_PRIO, DD_WRITE, write2); +#undef DEADLINE_DEBUGFS_DDIR_ATTRS + +static int deadline_batching_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; + struct deadline_data *dd = q->elevator->elevator_data; + + seq_printf(m, "%u\n", dd->batching); + return 0; +} + +static int deadline_starved_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; + struct deadline_data *dd = q->elevator->elevator_data; + + seq_printf(m, "%u\n", dd->starved); + return 0; +} + +static int dd_async_depth_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; + struct deadline_data *dd = q->elevator->elevator_data; + + seq_printf(m, "%u\n", dd->async_depth); + return 0; +} + +static int dd_queued_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; + struct deadline_data *dd = q->elevator->elevator_data; + + seq_printf(m, "%u %u %u\n", dd_queued(dd, DD_RT_PRIO), + dd_queued(dd, DD_BE_PRIO), + dd_queued(dd, DD_IDLE_PRIO)); + return 0; +} + +/* Number of requests owned by the block driver for a given priority. */ +static u32 dd_owned_by_driver(struct deadline_data *dd, enum dd_prio prio) +{ + return dd_sum(dd, dispatched, prio) + dd_sum(dd, merged, prio) + - dd_sum(dd, completed, prio); +} + +static int dd_owned_by_driver_show(void *data, struct seq_file *m) +{ + struct request_queue *q = data; + struct deadline_data *dd = q->elevator->elevator_data; + + seq_printf(m, "%u %u %u\n", dd_owned_by_driver(dd, DD_RT_PRIO), + dd_owned_by_driver(dd, DD_BE_PRIO), + dd_owned_by_driver(dd, DD_IDLE_PRIO)); + return 0; +} + +#define DEADLINE_DISPATCH_ATTR(prio) \ +static void *deadline_dispatch##prio##_start(struct seq_file *m, \ + loff_t *pos) \ + __acquires(&dd->lock) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + \ + spin_lock(&dd->lock); \ + return seq_list_start(&per_prio->dispatch, *pos); \ +} \ + \ +static void *deadline_dispatch##prio##_next(struct seq_file *m, \ + void *v, loff_t *pos) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ + \ + return seq_list_next(v, &per_prio->dispatch, pos); \ +} \ + \ +static void deadline_dispatch##prio##_stop(struct seq_file *m, void *v) \ + __releases(&dd->lock) \ +{ \ + struct request_queue *q = m->private; \ + struct deadline_data *dd = q->elevator->elevator_data; \ + \ + spin_unlock(&dd->lock); \ +} \ + \ +static const struct seq_operations deadline_dispatch##prio##_seq_ops = { \ + .start = deadline_dispatch##prio##_start, \ + .next = deadline_dispatch##prio##_next, \ + .stop = deadline_dispatch##prio##_stop, \ + .show = blk_mq_debugfs_rq_show, \ +} + +DEADLINE_DISPATCH_ATTR(0); +DEADLINE_DISPATCH_ATTR(1); +DEADLINE_DISPATCH_ATTR(2); +#undef DEADLINE_DISPATCH_ATTR + +#define DEADLINE_QUEUE_DDIR_ATTRS(name) \ + {#name "_fifo_list", 0400, \ + .seq_ops = &deadline_##name##_fifo_seq_ops} +#define DEADLINE_NEXT_RQ_ATTR(name) \ + {#name "_next_rq", 0400, deadline_##name##_next_rq_show} +static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = { + DEADLINE_QUEUE_DDIR_ATTRS(read0), + DEADLINE_QUEUE_DDIR_ATTRS(write0), + DEADLINE_QUEUE_DDIR_ATTRS(read1), + DEADLINE_QUEUE_DDIR_ATTRS(write1), + DEADLINE_QUEUE_DDIR_ATTRS(read2), + DEADLINE_QUEUE_DDIR_ATTRS(write2), + DEADLINE_NEXT_RQ_ATTR(read0), + DEADLINE_NEXT_RQ_ATTR(write0), + DEADLINE_NEXT_RQ_ATTR(read1), + DEADLINE_NEXT_RQ_ATTR(write1), + DEADLINE_NEXT_RQ_ATTR(read2), + DEADLINE_NEXT_RQ_ATTR(write2), + {"batching", 0400, deadline_batching_show}, + {"starved", 0400, deadline_starved_show}, + {"async_depth", 0400, dd_async_depth_show}, + {"dispatch0", 0400, .seq_ops = &deadline_dispatch0_seq_ops}, + {"dispatch1", 0400, .seq_ops = &deadline_dispatch1_seq_ops}, + {"dispatch2", 0400, .seq_ops = &deadline_dispatch2_seq_ops}, + {"owned_by_driver", 0400, dd_owned_by_driver_show}, + {"queued", 0400, dd_queued_show}, + {}, +}; +#undef DEADLINE_QUEUE_DDIR_ATTRS +#endif + +static struct elevator_type mq_deadline = { + .ops = { + .depth_updated = dd_depth_updated, + .limit_depth = dd_limit_depth, + .insert_requests = dd_insert_requests, + .dispatch_request = dd_dispatch_request, + .prepare_request = dd_prepare_request, + .finish_request = dd_finish_request, + .next_request = elv_rb_latter_request, + .former_request = elv_rb_former_request, + .bio_merge = dd_bio_merge, + .request_merge = dd_request_merge, + .requests_merged = dd_merged_requests, + .request_merged = dd_request_merged, + .has_work = dd_has_work, + .init_sched = dd_init_sched, + .exit_sched = dd_exit_sched, + .init_hctx = dd_init_hctx, + }, + +#ifdef CONFIG_BLK_DEBUG_FS + .queue_debugfs_attrs = deadline_queue_debugfs_attrs, +#endif + .elevator_attrs = deadline_attrs, + .elevator_name = "mq-deadline", + .elevator_alias = "deadline", + .elevator_features = ELEVATOR_F_ZBD_SEQ_WRITE, + .elevator_owner = THIS_MODULE, +}; +MODULE_ALIAS("mq-deadline-iosched"); + +static int __init deadline_init(void) +{ + int ret; + + ret = elv_register(&mq_deadline); + if (ret) + goto out; + ret = dd_blkcg_init(); + if (ret) + goto unreg; + +out: + return ret; + +unreg: + elv_unregister(&mq_deadline); + goto out; +} + +static void __exit deadline_exit(void) +{ + dd_blkcg_exit(); + elv_unregister(&mq_deadline); +} + +module_init(deadline_init); +module_exit(deadline_exit); + +MODULE_AUTHOR("Jens Axboe, Damien Le Moal and Bart Van Assche"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("MQ deadline IO scheduler"); diff --git a/block/mq-deadline.c b/block/mq-deadline.c deleted file mode 100644 index 8eea2cbf2bf4..000000000000 --- a/block/mq-deadline.c +++ /dev/null @@ -1,815 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * MQ Deadline i/o scheduler - adaptation of the legacy deadline scheduler, - * for the blk-mq scheduling framework - * - * Copyright (C) 2016 Jens Axboe - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -#include "blk.h" -#include "blk-mq.h" -#include "blk-mq-debugfs.h" -#include "blk-mq-tag.h" -#include "blk-mq-sched.h" - -/* - * See Documentation/block/deadline-iosched.rst - */ -static const int read_expire = HZ / 2; /* max time before a read is submitted. */ -static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */ -static const int writes_starved = 2; /* max times reads can starve a write */ -static const int fifo_batch = 16; /* # of sequential requests treated as one - by the above parameters. For throughput. */ - -struct deadline_data { - /* - * run time data - */ - - /* - * requests (deadline_rq s) are present on both sort_list and fifo_list - */ - struct rb_root sort_list[2]; - struct list_head fifo_list[2]; - - /* - * next in sort order. read, write or both are NULL - */ - struct request *next_rq[2]; - unsigned int batching; /* number of sequential requests made */ - unsigned int starved; /* times reads have starved writes */ - - /* - * settings that change how the i/o scheduler behaves - */ - int fifo_expire[2]; - int fifo_batch; - int writes_starved; - int front_merges; - - spinlock_t lock; - spinlock_t zone_lock; - struct list_head dispatch; -}; - -static inline struct rb_root * -deadline_rb_root(struct deadline_data *dd, struct request *rq) -{ - return &dd->sort_list[rq_data_dir(rq)]; -} - -/* - * get the request after `rq' in sector-sorted order - */ -static inline struct request * -deadline_latter_request(struct request *rq) -{ - struct rb_node *node = rb_next(&rq->rb_node); - - if (node) - return rb_entry_rq(node); - - return NULL; -} - -static void -deadline_add_rq_rb(struct deadline_data *dd, struct request *rq) -{ - struct rb_root *root = deadline_rb_root(dd, rq); - - elv_rb_add(root, rq); -} - -static inline void -deadline_del_rq_rb(struct deadline_data *dd, struct request *rq) -{ - const int data_dir = rq_data_dir(rq); - - if (dd->next_rq[data_dir] == rq) - dd->next_rq[data_dir] = deadline_latter_request(rq); - - elv_rb_del(deadline_rb_root(dd, rq), rq); -} - -/* - * remove rq from rbtree and fifo. - */ -static void deadline_remove_request(struct request_queue *q, struct request *rq) -{ - struct deadline_data *dd = q->elevator->elevator_data; - - list_del_init(&rq->queuelist); - - /* - * We might not be on the rbtree, if we are doing an insert merge - */ - if (!RB_EMPTY_NODE(&rq->rb_node)) - deadline_del_rq_rb(dd, rq); - - elv_rqhash_del(q, rq); - if (q->last_merge == rq) - q->last_merge = NULL; -} - -static void dd_request_merged(struct request_queue *q, struct request *req, - enum elv_merge type) -{ - struct deadline_data *dd = q->elevator->elevator_data; - - /* - * if the merge was a front merge, we need to reposition request - */ - if (type == ELEVATOR_FRONT_MERGE) { - elv_rb_del(deadline_rb_root(dd, req), req); - deadline_add_rq_rb(dd, req); - } -} - -static void dd_merged_requests(struct request_queue *q, struct request *req, - struct request *next) -{ - /* - * if next expires before rq, assign its expire time to rq - * and move into next position (next will be deleted) in fifo - */ - if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) { - if (time_before((unsigned long)next->fifo_time, - (unsigned long)req->fifo_time)) { - list_move(&req->queuelist, &next->queuelist); - req->fifo_time = next->fifo_time; - } - } - - /* - * kill knowledge of next, this one is a goner - */ - deadline_remove_request(q, next); -} - -/* - * move an entry to dispatch queue - */ -static void -deadline_move_request(struct deadline_data *dd, struct request *rq) -{ - const int data_dir = rq_data_dir(rq); - - dd->next_rq[READ] = NULL; - dd->next_rq[WRITE] = NULL; - dd->next_rq[data_dir] = deadline_latter_request(rq); - - /* - * take it off the sort and fifo list - */ - deadline_remove_request(rq->q, rq); -} - -/* - * deadline_check_fifo returns 0 if there are no expired requests on the fifo, - * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir]) - */ -static inline int deadline_check_fifo(struct deadline_data *dd, int ddir) -{ - struct request *rq = rq_entry_fifo(dd->fifo_list[ddir].next); - - /* - * rq is expired! - */ - if (time_after_eq(jiffies, (unsigned long)rq->fifo_time)) - return 1; - - return 0; -} - -/* - * For the specified data direction, return the next request to - * dispatch using arrival ordered lists. - */ -static struct request * -deadline_fifo_request(struct deadline_data *dd, int data_dir) -{ - struct request *rq; - unsigned long flags; - - if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE)) - return NULL; - - if (list_empty(&dd->fifo_list[data_dir])) - return NULL; - - rq = rq_entry_fifo(dd->fifo_list[data_dir].next); - if (data_dir == READ || !blk_queue_is_zoned(rq->q)) - return rq; - - /* - * Look for a write request that can be dispatched, that is one with - * an unlocked target zone. - */ - spin_lock_irqsave(&dd->zone_lock, flags); - list_for_each_entry(rq, &dd->fifo_list[WRITE], queuelist) { - if (blk_req_can_dispatch_to_zone(rq)) - goto out; - } - rq = NULL; -out: - spin_unlock_irqrestore(&dd->zone_lock, flags); - - return rq; -} - -/* - * For the specified data direction, return the next request to - * dispatch using sector position sorted lists. - */ -static struct request * -deadline_next_request(struct deadline_data *dd, int data_dir) -{ - struct request *rq; - unsigned long flags; - - if (WARN_ON_ONCE(data_dir != READ && data_dir != WRITE)) - return NULL; - - rq = dd->next_rq[data_dir]; - if (!rq) - return NULL; - - if (data_dir == READ || !blk_queue_is_zoned(rq->q)) - return rq; - - /* - * Look for a write request that can be dispatched, that is one with - * an unlocked target zone. - */ - spin_lock_irqsave(&dd->zone_lock, flags); - while (rq) { - if (blk_req_can_dispatch_to_zone(rq)) - break; - rq = deadline_latter_request(rq); - } - spin_unlock_irqrestore(&dd->zone_lock, flags); - - return rq; -} - -/* - * deadline_dispatch_requests selects the best request according to - * read/write expire, fifo_batch, etc - */ -static struct request *__dd_dispatch_request(struct deadline_data *dd) -{ - struct request *rq, *next_rq; - bool reads, writes; - int data_dir; - - if (!list_empty(&dd->dispatch)) { - rq = list_first_entry(&dd->dispatch, struct request, queuelist); - list_del_init(&rq->queuelist); - goto done; - } - - reads = !list_empty(&dd->fifo_list[READ]); - writes = !list_empty(&dd->fifo_list[WRITE]); - - /* - * batches are currently reads XOR writes - */ - rq = deadline_next_request(dd, WRITE); - if (!rq) - rq = deadline_next_request(dd, READ); - - if (rq && dd->batching < dd->fifo_batch) - /* we have a next request are still entitled to batch */ - goto dispatch_request; - - /* - * at this point we are not running a batch. select the appropriate - * data direction (read / write) - */ - - if (reads) { - BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ])); - - if (deadline_fifo_request(dd, WRITE) && - (dd->starved++ >= dd->writes_starved)) - goto dispatch_writes; - - data_dir = READ; - - goto dispatch_find_request; - } - - /* - * there are either no reads or writes have been starved - */ - - if (writes) { -dispatch_writes: - BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[WRITE])); - - dd->starved = 0; - - data_dir = WRITE; - - goto dispatch_find_request; - } - - return NULL; - -dispatch_find_request: - /* - * we are not running a batch, find best request for selected data_dir - */ - next_rq = deadline_next_request(dd, data_dir); - if (deadline_check_fifo(dd, data_dir) || !next_rq) { - /* - * A deadline has expired, the last request was in the other - * direction, or we have run out of higher-sectored requests. - * Start again from the request with the earliest expiry time. - */ - rq = deadline_fifo_request(dd, data_dir); - } else { - /* - * The last req was the same dir and we have a next request in - * sort order. No expired requests so continue on from here. - */ - rq = next_rq; - } - - /* - * For a zoned block device, if we only have writes queued and none of - * them can be dispatched, rq will be NULL. - */ - if (!rq) - return NULL; - - dd->batching = 0; - -dispatch_request: - /* - * rq is the selected appropriate request. - */ - dd->batching++; - deadline_move_request(dd, rq); -done: - /* - * If the request needs its target zone locked, do it. - */ - blk_req_zone_write_lock(rq); - rq->rq_flags |= RQF_STARTED; - return rq; -} - -/* - * One confusing aspect here is that we get called for a specific - * hardware queue, but we may return a request that is for a - * different hardware queue. This is because mq-deadline has shared - * state for all hardware queues, in terms of sorting, FIFOs, etc. - */ -static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx) -{ - struct deadline_data *dd = hctx->queue->elevator->elevator_data; - struct request *rq; - - spin_lock(&dd->lock); - rq = __dd_dispatch_request(dd); - spin_unlock(&dd->lock); - - return rq; -} - -static void dd_exit_queue(struct elevator_queue *e) -{ - struct deadline_data *dd = e->elevator_data; - - BUG_ON(!list_empty(&dd->fifo_list[READ])); - BUG_ON(!list_empty(&dd->fifo_list[WRITE])); - - kfree(dd); -} - -/* - * initialize elevator private data (deadline_data). - */ -static int dd_init_queue(struct request_queue *q, struct elevator_type *e) -{ - struct deadline_data *dd; - struct elevator_queue *eq; - - eq = elevator_alloc(q, e); - if (!eq) - return -ENOMEM; - - dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node); - if (!dd) { - kobject_put(&eq->kobj); - return -ENOMEM; - } - eq->elevator_data = dd; - - INIT_LIST_HEAD(&dd->fifo_list[READ]); - INIT_LIST_HEAD(&dd->fifo_list[WRITE]); - dd->sort_list[READ] = RB_ROOT; - dd->sort_list[WRITE] = RB_ROOT; - dd->fifo_expire[READ] = read_expire; - dd->fifo_expire[WRITE] = write_expire; - dd->writes_starved = writes_starved; - dd->front_merges = 1; - dd->fifo_batch = fifo_batch; - spin_lock_init(&dd->lock); - spin_lock_init(&dd->zone_lock); - INIT_LIST_HEAD(&dd->dispatch); - - q->elevator = eq; - return 0; -} - -static int dd_request_merge(struct request_queue *q, struct request **rq, - struct bio *bio) -{ - struct deadline_data *dd = q->elevator->elevator_data; - sector_t sector = bio_end_sector(bio); - struct request *__rq; - - if (!dd->front_merges) - return ELEVATOR_NO_MERGE; - - __rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector); - if (__rq) { - BUG_ON(sector != blk_rq_pos(__rq)); - - if (elv_bio_merge_ok(__rq, bio)) { - *rq = __rq; - return ELEVATOR_FRONT_MERGE; - } - } - - return ELEVATOR_NO_MERGE; -} - -static bool dd_bio_merge(struct request_queue *q, struct bio *bio, - unsigned int nr_segs) -{ - struct deadline_data *dd = q->elevator->elevator_data; - struct request *free = NULL; - bool ret; - - spin_lock(&dd->lock); - ret = blk_mq_sched_try_merge(q, bio, nr_segs, &free); - spin_unlock(&dd->lock); - - if (free) - blk_mq_free_request(free); - - return ret; -} - -/* - * add rq to rbtree and fifo - */ -static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, - bool at_head) -{ - struct request_queue *q = hctx->queue; - struct deadline_data *dd = q->elevator->elevator_data; - const int data_dir = rq_data_dir(rq); - - /* - * This may be a requeue of a write request that has locked its - * target zone. If it is the case, this releases the zone lock. - */ - blk_req_zone_write_unlock(rq); - - if (blk_mq_sched_try_insert_merge(q, rq)) - return; - - trace_block_rq_insert(rq); - - if (at_head) { - list_add(&rq->queuelist, &dd->dispatch); - } else { - deadline_add_rq_rb(dd, rq); - - if (rq_mergeable(rq)) { - elv_rqhash_add(q, rq); - if (!q->last_merge) - q->last_merge = rq; - } - - /* - * set expire time and add to fifo list - */ - rq->fifo_time = jiffies + dd->fifo_expire[data_dir]; - list_add_tail(&rq->queuelist, &dd->fifo_list[data_dir]); - } -} - -static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, - struct list_head *list, bool at_head) -{ - struct request_queue *q = hctx->queue; - struct deadline_data *dd = q->elevator->elevator_data; - - spin_lock(&dd->lock); - while (!list_empty(list)) { - struct request *rq; - - rq = list_first_entry(list, struct request, queuelist); - list_del_init(&rq->queuelist); - dd_insert_request(hctx, rq, at_head); - } - spin_unlock(&dd->lock); -} - -/* - * Nothing to do here. This is defined only to ensure that .finish_request - * method is called upon request completion. - */ -static void dd_prepare_request(struct request *rq) -{ -} - -/* - * For zoned block devices, write unlock the target zone of - * completed write requests. Do this while holding the zone lock - * spinlock so that the zone is never unlocked while deadline_fifo_request() - * or deadline_next_request() are executing. This function is called for - * all requests, whether or not these requests complete successfully. - * - * For a zoned block device, __dd_dispatch_request() may have stopped - * dispatching requests if all the queued requests are write requests directed - * at zones that are already locked due to on-going write requests. To ensure - * write request dispatch progress in this case, mark the queue as needing a - * restart to ensure that the queue is run again after completion of the - * request and zones being unlocked. - */ -static void dd_finish_request(struct request *rq) -{ - struct request_queue *q = rq->q; - - if (blk_queue_is_zoned(q)) { - struct deadline_data *dd = q->elevator->elevator_data; - unsigned long flags; - - spin_lock_irqsave(&dd->zone_lock, flags); - blk_req_zone_write_unlock(rq); - if (!list_empty(&dd->fifo_list[WRITE])) - blk_mq_sched_mark_restart_hctx(rq->mq_hctx); - spin_unlock_irqrestore(&dd->zone_lock, flags); - } -} - -static bool dd_has_work(struct blk_mq_hw_ctx *hctx) -{ - struct deadline_data *dd = hctx->queue->elevator->elevator_data; - - return !list_empty_careful(&dd->dispatch) || - !list_empty_careful(&dd->fifo_list[0]) || - !list_empty_careful(&dd->fifo_list[1]); -} - -/* - * sysfs parts below - */ -static ssize_t -deadline_var_show(int var, char *page) -{ - return sprintf(page, "%d\n", var); -} - -static void -deadline_var_store(int *var, const char *page) -{ - char *p = (char *) page; - - *var = simple_strtol(p, &p, 10); -} - -#define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \ -static ssize_t __FUNC(struct elevator_queue *e, char *page) \ -{ \ - struct deadline_data *dd = e->elevator_data; \ - int __data = __VAR; \ - if (__CONV) \ - __data = jiffies_to_msecs(__data); \ - return deadline_var_show(__data, (page)); \ -} -SHOW_FUNCTION(deadline_read_expire_show, dd->fifo_expire[READ], 1); -SHOW_FUNCTION(deadline_write_expire_show, dd->fifo_expire[WRITE], 1); -SHOW_FUNCTION(deadline_writes_starved_show, dd->writes_starved, 0); -SHOW_FUNCTION(deadline_front_merges_show, dd->front_merges, 0); -SHOW_FUNCTION(deadline_fifo_batch_show, dd->fifo_batch, 0); -#undef SHOW_FUNCTION - -#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ -static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count) \ -{ \ - struct deadline_data *dd = e->elevator_data; \ - int __data; \ - deadline_var_store(&__data, (page)); \ - if (__data < (MIN)) \ - __data = (MIN); \ - else if (__data > (MAX)) \ - __data = (MAX); \ - if (__CONV) \ - *(__PTR) = msecs_to_jiffies(__data); \ - else \ - *(__PTR) = __data; \ - return count; \ -} -STORE_FUNCTION(deadline_read_expire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1); -STORE_FUNCTION(deadline_write_expire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1); -STORE_FUNCTION(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0); -STORE_FUNCTION(deadline_front_merges_store, &dd->front_merges, 0, 1, 0); -STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0); -#undef STORE_FUNCTION - -#define DD_ATTR(name) \ - __ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store) - -static struct elv_fs_entry deadline_attrs[] = { - DD_ATTR(read_expire), - DD_ATTR(write_expire), - DD_ATTR(writes_starved), - DD_ATTR(front_merges), - DD_ATTR(fifo_batch), - __ATTR_NULL -}; - -#ifdef CONFIG_BLK_DEBUG_FS -#define DEADLINE_DEBUGFS_DDIR_ATTRS(ddir, name) \ -static void *deadline_##name##_fifo_start(struct seq_file *m, \ - loff_t *pos) \ - __acquires(&dd->lock) \ -{ \ - struct request_queue *q = m->private; \ - struct deadline_data *dd = q->elevator->elevator_data; \ - \ - spin_lock(&dd->lock); \ - return seq_list_start(&dd->fifo_list[ddir], *pos); \ -} \ - \ -static void *deadline_##name##_fifo_next(struct seq_file *m, void *v, \ - loff_t *pos) \ -{ \ - struct request_queue *q = m->private; \ - struct deadline_data *dd = q->elevator->elevator_data; \ - \ - return seq_list_next(v, &dd->fifo_list[ddir], pos); \ -} \ - \ -static void deadline_##name##_fifo_stop(struct seq_file *m, void *v) \ - __releases(&dd->lock) \ -{ \ - struct request_queue *q = m->private; \ - struct deadline_data *dd = q->elevator->elevator_data; \ - \ - spin_unlock(&dd->lock); \ -} \ - \ -static const struct seq_operations deadline_##name##_fifo_seq_ops = { \ - .start = deadline_##name##_fifo_start, \ - .next = deadline_##name##_fifo_next, \ - .stop = deadline_##name##_fifo_stop, \ - .show = blk_mq_debugfs_rq_show, \ -}; \ - \ -static int deadline_##name##_next_rq_show(void *data, \ - struct seq_file *m) \ -{ \ - struct request_queue *q = data; \ - struct deadline_data *dd = q->elevator->elevator_data; \ - struct request *rq = dd->next_rq[ddir]; \ - \ - if (rq) \ - __blk_mq_debugfs_rq_show(m, rq); \ - return 0; \ -} -DEADLINE_DEBUGFS_DDIR_ATTRS(READ, read) -DEADLINE_DEBUGFS_DDIR_ATTRS(WRITE, write) -#undef DEADLINE_DEBUGFS_DDIR_ATTRS - -static int deadline_batching_show(void *data, struct seq_file *m) -{ - struct request_queue *q = data; - struct deadline_data *dd = q->elevator->elevator_data; - - seq_printf(m, "%u\n", dd->batching); - return 0; -} - -static int deadline_starved_show(void *data, struct seq_file *m) -{ - struct request_queue *q = data; - struct deadline_data *dd = q->elevator->elevator_data; - - seq_printf(m, "%u\n", dd->starved); - return 0; -} - -static void *deadline_dispatch_start(struct seq_file *m, loff_t *pos) - __acquires(&dd->lock) -{ - struct request_queue *q = m->private; - struct deadline_data *dd = q->elevator->elevator_data; - - spin_lock(&dd->lock); - return seq_list_start(&dd->dispatch, *pos); -} - -static void *deadline_dispatch_next(struct seq_file *m, void *v, loff_t *pos) -{ - struct request_queue *q = m->private; - struct deadline_data *dd = q->elevator->elevator_data; - - return seq_list_next(v, &dd->dispatch, pos); -} - -static void deadline_dispatch_stop(struct seq_file *m, void *v) - __releases(&dd->lock) -{ - struct request_queue *q = m->private; - struct deadline_data *dd = q->elevator->elevator_data; - - spin_unlock(&dd->lock); -} - -static const struct seq_operations deadline_dispatch_seq_ops = { - .start = deadline_dispatch_start, - .next = deadline_dispatch_next, - .stop = deadline_dispatch_stop, - .show = blk_mq_debugfs_rq_show, -}; - -#define DEADLINE_QUEUE_DDIR_ATTRS(name) \ - {#name "_fifo_list", 0400, .seq_ops = &deadline_##name##_fifo_seq_ops}, \ - {#name "_next_rq", 0400, deadline_##name##_next_rq_show} -static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = { - DEADLINE_QUEUE_DDIR_ATTRS(read), - DEADLINE_QUEUE_DDIR_ATTRS(write), - {"batching", 0400, deadline_batching_show}, - {"starved", 0400, deadline_starved_show}, - {"dispatch", 0400, .seq_ops = &deadline_dispatch_seq_ops}, - {}, -}; -#undef DEADLINE_QUEUE_DDIR_ATTRS -#endif - -static struct elevator_type mq_deadline = { - .ops = { - .insert_requests = dd_insert_requests, - .dispatch_request = dd_dispatch_request, - .prepare_request = dd_prepare_request, - .finish_request = dd_finish_request, - .next_request = elv_rb_latter_request, - .former_request = elv_rb_former_request, - .bio_merge = dd_bio_merge, - .request_merge = dd_request_merge, - .requests_merged = dd_merged_requests, - .request_merged = dd_request_merged, - .has_work = dd_has_work, - .init_sched = dd_init_queue, - .exit_sched = dd_exit_queue, - }, - -#ifdef CONFIG_BLK_DEBUG_FS - .queue_debugfs_attrs = deadline_queue_debugfs_attrs, -#endif - .elevator_attrs = deadline_attrs, - .elevator_name = "mq-deadline", - .elevator_alias = "deadline", - .elevator_features = ELEVATOR_F_ZBD_SEQ_WRITE, - .elevator_owner = THIS_MODULE, -}; -MODULE_ALIAS("mq-deadline-iosched"); - -static int __init deadline_init(void) -{ - return elv_register(&mq_deadline); -} - -static void __exit deadline_exit(void) -{ - elv_unregister(&mq_deadline); -} - -module_init(deadline_init); -module_exit(deadline_exit); - -MODULE_AUTHOR("Jens Axboe"); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("MQ deadline IO scheduler"); diff --git a/block/partitions/core.c b/block/partitions/core.c index dc60ecf46fe6..347c56a51d87 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -120,8 +120,7 @@ static void free_partitions(struct parsed_partitions *state) kfree(state); } -static struct parsed_partitions *check_partition(struct gendisk *hd, - struct block_device *bdev) +static struct parsed_partitions *check_partition(struct gendisk *hd) { struct parsed_partitions *state; int i, res, err; @@ -136,7 +135,7 @@ static struct parsed_partitions *check_partition(struct gendisk *hd, } state->pp_buf[0] = '\0'; - state->bdev = bdev; + state->bdev = hd->part0; disk_name(hd, 0, state->name); snprintf(state->pp_buf, PAGE_SIZE, " %s:", state->name); if (isdigit(state->name[strlen(state->name)-1])) @@ -260,7 +259,8 @@ static const struct attribute_group *part_attr_groups[] = { static void part_release(struct device *dev) { - blk_free_devt(dev->devt); + if (MAJOR(dev->devt) == BLOCK_EXT_MAJOR) + blk_free_ext_minor(MINOR(dev->devt)); bdput(dev_to_bdev(dev)); } @@ -282,7 +282,7 @@ struct device_type part_type = { }; /* - * Must be called either with bd_mutex held, before a disk can be opened or + * Must be called either with open_mutex held, before a disk can be opened or * after all disk users are gone. */ static void delete_partition(struct block_device *part) @@ -311,7 +311,7 @@ static ssize_t whole_disk_show(struct device *dev, static DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL); /* - * Must be called either with bd_mutex held, before a disk can be opened or + * Must be called either with open_mutex held, before a disk can be opened or * after all disk users are gone. */ static struct block_device *add_partition(struct gendisk *disk, int partno, @@ -325,10 +325,8 @@ static struct block_device *add_partition(struct gendisk *disk, int partno, const char *dname; int err; - /* - * disk_max_parts() won't be zero, either GENHD_FL_EXT_DEVT is set - * or 'minors' is passed to alloc_disk(). - */ + lockdep_assert_held(&disk->open_mutex); + if (partno >= disk_max_parts(disk)) return ERR_PTR(-EINVAL); @@ -379,9 +377,15 @@ static struct block_device *add_partition(struct gendisk *disk, int partno, pdev->type = &part_type; pdev->parent = ddev; - err = blk_alloc_devt(bdev, &devt); - if (err) - goto out_put; + /* in consecutive minor range? */ + if (bdev->bd_partno < disk->minors) { + devt = MKDEV(disk->major, disk->first_minor + bdev->bd_partno); + } else { + err = blk_alloc_ext_minor(); + if (err < 0) + goto out_put; + devt = MKDEV(BLOCK_EXT_MAJOR, err); + } pdev->devt = devt; /* delay uevent until 'holders' subdir is created */ @@ -450,29 +454,27 @@ int bdev_add_partition(struct block_device *bdev, int partno, { struct block_device *part; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); if (partition_overlaps(bdev->bd_disk, start, length, -1)) { - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); return -EBUSY; } part = add_partition(bdev->bd_disk, partno, start, length, ADDPART_FLAG_NONE, NULL); - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); return PTR_ERR_OR_ZERO(part); } int bdev_del_partition(struct block_device *bdev, int partno) { - struct block_device *part; - int ret; + struct block_device *part = NULL; + int ret = -ENXIO; - part = bdget_disk(bdev->bd_disk, partno); + mutex_lock(&bdev->bd_disk->open_mutex); + part = xa_load(&bdev->bd_disk->part_tbl, partno); if (!part) - return -ENXIO; - - mutex_lock(&part->bd_mutex); - mutex_lock_nested(&bdev->bd_mutex, 1); + goto out_unlock; ret = -EBUSY; if (part->bd_openers) @@ -481,24 +483,21 @@ int bdev_del_partition(struct block_device *bdev, int partno) delete_partition(part); ret = 0; out_unlock: - mutex_unlock(&bdev->bd_mutex); - mutex_unlock(&part->bd_mutex); - bdput(part); + mutex_unlock(&bdev->bd_disk->open_mutex); return ret; } int bdev_resize_partition(struct block_device *bdev, int partno, sector_t start, sector_t length) { - struct block_device *part; - int ret = 0; + struct block_device *part = NULL; + int ret = -ENXIO; - part = bdget_disk(bdev->bd_disk, partno); + mutex_lock(&bdev->bd_disk->open_mutex); + part = xa_load(&bdev->bd_disk->part_tbl, partno); if (!part) - return -ENXIO; + goto out_unlock; - mutex_lock(&part->bd_mutex); - mutex_lock_nested(&bdev->bd_mutex, 1); ret = -EINVAL; if (start != part->bd_start_sect) goto out_unlock; @@ -511,9 +510,7 @@ int bdev_resize_partition(struct block_device *bdev, int partno, ret = 0; out_unlock: - mutex_unlock(&part->bd_mutex); - mutex_unlock(&bdev->bd_mutex); - bdput(part); + mutex_unlock(&bdev->bd_disk->open_mutex); return ret; } @@ -538,7 +535,7 @@ void blk_drop_partitions(struct gendisk *disk) struct block_device *part; unsigned long idx; - lockdep_assert_held(&disk->part0->bd_mutex); + lockdep_assert_held(&disk->open_mutex); xa_for_each_start(&disk->part_tbl, idx, part, 1) { if (!bdgrab(part)) @@ -548,7 +545,7 @@ void blk_drop_partitions(struct gendisk *disk) } } -static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev, +static bool blk_add_partition(struct gendisk *disk, struct parsed_partitions *state, int p) { sector_t size = state->parts[p].size; @@ -598,7 +595,7 @@ static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev, return true; } -int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) +static int blk_add_partitions(struct gendisk *disk) { struct parsed_partitions *state; int ret = -EAGAIN, p; @@ -606,7 +603,7 @@ int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) if (!disk_part_scan_enabled(disk)) return 0; - state = check_partition(disk, bdev); + state = check_partition(disk); if (!state) return 0; if (IS_ERR(state)) { @@ -650,7 +647,7 @@ int blk_add_partitions(struct gendisk *disk, struct block_device *bdev) kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); for (p = 1; p < state->limit; p++) - if (!blk_add_partition(disk, bdev, state, p)) + if (!blk_add_partition(disk, state, p)) goto out_free_state; ret = 0; @@ -659,6 +656,58 @@ out_free_state: return ret; } +int bdev_disk_changed(struct gendisk *disk, bool invalidate) +{ + int ret = 0; + + lockdep_assert_held(&disk->open_mutex); + + if (!(disk->flags & GENHD_FL_UP)) + return -ENXIO; + +rescan: + if (disk->open_partitions) + return -EBUSY; + sync_blockdev(disk->part0); + invalidate_bdev(disk->part0); + blk_drop_partitions(disk); + + clear_bit(GD_NEED_PART_SCAN, &disk->state); + + /* + * Historically we only set the capacity to zero for devices that + * support partitions (independ of actually having partitions created). + * Doing that is rather inconsistent, but changing it broke legacy + * udisks polling for legacy ide-cdrom devices. Use the crude check + * below to get the sane behavior for most device while not breaking + * userspace for this particular setup. + */ + if (invalidate) { + if (disk_part_scan_enabled(disk) || + !(disk->flags & GENHD_FL_REMOVABLE)) + set_capacity(disk, 0); + } + + if (get_capacity(disk)) { + ret = blk_add_partitions(disk); + if (ret == -EAGAIN) + goto rescan; + } else if (invalidate) { + /* + * Tell userspace that the media / partition table may have + * changed. + */ + kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); + } + + return ret; +} +/* + * Only exported for loop and dasd for historic reasons. Don't use in new + * code! + */ +EXPORT_SYMBOL_GPL(bdev_disk_changed); + void *read_part_sector(struct parsed_partitions *state, sector_t n, Sector *p) { struct address_space *mapping = state->bdev->bd_inode->i_mapping; diff --git a/block/partitions/msdos.c b/block/partitions/msdos.c index 8f2fcc080264..63e4f6f8b6e9 100644 --- a/block/partitions/msdos.c +++ b/block/partitions/msdos.c @@ -622,7 +622,7 @@ int msdos_partition(struct parsed_partitions *state) for (slot = 1; slot <= 4; slot++, p++) { if (p->boot_ind != 0 && p->boot_ind != 0x80) { /* - * Even without a valid boot inidicator value + * Even without a valid boot indicator value * its still possible this is valid FAT filesystem * without a partition table. */ diff --git a/drivers/Makefile b/drivers/Makefile index f85185f9139e..27c018bdf4de 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -160,7 +160,7 @@ obj-$(CONFIG_SOUNDWIRE) += soundwire/ # Virtualization drivers obj-$(CONFIG_VIRT_DRIVERS) += virt/ -obj-$(CONFIG_HYPERV) += hv/ +obj-$(subst m,y,$(CONFIG_HYPERV)) += hv/ obj-$(CONFIG_PM_DEVFREQ) += devfreq/ obj-$(CONFIG_EXTCON) += extcon/ diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index eedec61e3476..3972de7b7565 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -543,3 +543,8 @@ config X86_PM_TIMER You should nearly always say Y here because many modern systems require this timer. + +config ACPI_PRMT + bool "Platform Runtime Mechanism Support" + depends on EFI && X86_64 + default y diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 700b41adf2db..ceb1aed4b1fc 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -8,6 +8,11 @@ ccflags-$(CONFIG_ACPI_DEBUG) += -DACPI_DEBUG_OUTPUT # # ACPI Boot-Time Table Parsing # +ifeq ($(CONFIG_ACPI_CUSTOM_DSDT),y) +tables.o: $(src)/../../include/$(subst $\",,$(CONFIG_ACPI_CUSTOM_DSDT_FILE)) ; + +endif + obj-$(CONFIG_ACPI) += tables.o obj-$(CONFIG_X86) += blacklist.o @@ -61,6 +66,7 @@ acpi-$(CONFIG_ACPI_FPDT) += acpi_fpdt.o acpi-$(CONFIG_ACPI_LPIT) += acpi_lpit.o acpi-$(CONFIG_ACPI_GENERIC_GSI) += irq.o acpi-$(CONFIG_ACPI_WATCHDOG) += acpi_watchdog.o +acpi-$(CONFIG_ACPI_PRMT) += prmt.o # Address translation acpi-$(CONFIG_ACPI_ADXL) += acpi_adxl.o diff --git a/drivers/acpi/acpi_cmos_rtc.c b/drivers/acpi/acpi_cmos_rtc.c index 67f1d33d15c4..4cf4aef7ce0c 100644 --- a/drivers/acpi/acpi_cmos_rtc.c +++ b/drivers/acpi/acpi_cmos_rtc.c @@ -6,6 +6,8 @@ * Authors: Lan Tianyu */ +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include @@ -59,7 +61,7 @@ static int acpi_install_cmos_rtc_space_handler(struct acpi_device *adev, &acpi_cmos_rtc_space_handler, NULL, NULL); if (ACPI_FAILURE(status)) { - pr_err(PREFIX "Error installing CMOS-RTC region handler\n"); + pr_err("Error installing CMOS-RTC region handler\n"); return -ENODEV; } @@ -70,7 +72,7 @@ static void acpi_remove_cmos_rtc_space_handler(struct acpi_device *adev) { if (ACPI_FAILURE(acpi_remove_address_space_handler(adev->handle, ACPI_ADR_SPACE_CMOS, &acpi_cmos_rtc_space_handler))) - pr_err(PREFIX "Error removing CMOS-RTC region handler\n"); + pr_err("Error removing CMOS-RTC region handler\n"); } static struct acpi_scan_handler cmos_rtc_handler = { diff --git a/drivers/acpi/acpi_configfs.c b/drivers/acpi/acpi_configfs.c index 3a14859dbb75..76b83b181356 100644 --- a/drivers/acpi/acpi_configfs.c +++ b/drivers/acpi/acpi_configfs.c @@ -13,9 +13,6 @@ #include #include -#include "acpica/accommon.h" -#include "acpica/actables.h" - static struct config_group *acpi_table_group; struct acpi_table { @@ -226,7 +223,7 @@ static void acpi_table_drop_item(struct config_group *group, { struct acpi_table *table = container_of(cfg, struct acpi_table, cfg); - ACPI_INFO(("Host-directed Dynamic ACPI Table Unload")); + pr_debug("Host-directed Dynamic ACPI Table Unload\n"); acpi_unload_table(table->index); config_item_put(cfg); } diff --git a/drivers/acpi/acpi_fpdt.c b/drivers/acpi/acpi_fpdt.c index a89a806a7a2a..4ee2ad234e3d 100644 --- a/drivers/acpi/acpi_fpdt.c +++ b/drivers/acpi/acpi_fpdt.c @@ -240,8 +240,10 @@ static int __init acpi_init_fpdt(void) return 0; fpdt_kobj = kobject_create_and_add("fpdt", acpi_kobj); - if (!fpdt_kobj) + if (!fpdt_kobj) { + acpi_put_table(header); return -ENOMEM; + } while (offset < header->length) { subtable = (void *)header + offset; diff --git a/drivers/acpi/acpi_ipmi.c b/drivers/acpi/acpi_ipmi.c index bbd00d96b7a8..a5fe2926bf50 100644 --- a/drivers/acpi/acpi_ipmi.c +++ b/drivers/acpi/acpi_ipmi.c @@ -597,9 +597,14 @@ static int __init acpi_ipmi_init(void) pr_warn("Can't register IPMI opregion space handle\n"); return -EINVAL; } + result = ipmi_smi_watcher_register(&driver_data.bmc_events); - if (result) + if (result) { + acpi_remove_address_space_handler(ACPI_ROOT_OBJECT, + ACPI_ADR_SPACE_IPMI, + &acpi_ipmi_space_handler); pr_err("Can't register IPMI system interface watcher\n"); + } return result; } diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index ca742f16a507..894b7e6ae144 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -186,13 +186,12 @@ static void byt_i2c_setup(struct lpss_private_data *pdata) long uid = 0; /* Expected to always be true, but better safe then sorry */ - if (uid_str) - uid = simple_strtol(uid_str, NULL, 10); - - /* Detect I2C bus shared with PUNIT and ignore its d3 status */ - status = acpi_evaluate_integer(handle, "_SEM", NULL, &shared_host); - if (ACPI_SUCCESS(status) && shared_host && uid) - pmc_atom_d3_mask &= ~(BIT_LPSS2_F1_I2C1 << (uid - 1)); + if (uid_str && !kstrtol(uid_str, 10, &uid) && uid) { + /* Detect I2C bus shared with PUNIT and ignore its d3 status */ + status = acpi_evaluate_integer(handle, "_SEM", NULL, &shared_host); + if (ACPI_SUCCESS(status) && shared_host) + pmc_atom_d3_mask &= ~(BIT_LPSS2_F1_I2C1 << (uid - 1)); + } lpss_deassert_reset(pdata); diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 0c884020f74b..ffb4afc5aad9 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -1619,8 +1619,6 @@ static void acpi_video_bus_notify(struct acpi_device *device, u32 event) input_report_key(input, keycode, 0); input_sync(input); } - - return; } static void brightness_switch_event(struct acpi_video_device *video_device, @@ -1690,8 +1688,6 @@ static void acpi_video_device_notify(acpi_handle handle, u32 event, void *data) input_report_key(input, keycode, 0); input_sync(input); } - - return; } static int acpi_video_resume(struct notifier_block *nb, @@ -2308,8 +2304,6 @@ static void __exit acpi_video_exit(void) { acpi_video_detect_exit(); acpi_video_unregister(); - - return; } module_init(acpi_video_init); diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h index bccae0d3db75..59d6ded01614 100644 --- a/drivers/acpi/acpica/acutils.h +++ b/drivers/acpi/acpica/acutils.h @@ -737,6 +737,8 @@ const char *acpi_ah_match_uuid(u8 *data); */ #if (defined ACPI_ASL_COMPILER || defined ACPI_EXEC_APP || defined ACPI_HELP_APP) void acpi_ut_convert_string_to_uuid(char *in_string, u8 *uuid_buffer); + +acpi_status acpi_ut_convert_uuid_to_string(char *uuid_buffer, char *out_string); #endif #endif /* _ACUTILS_H */ diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c index 32f03ee81785..06f3c9df1e22 100644 --- a/drivers/acpi/acpica/exfield.c +++ b/drivers/acpi/acpica/exfield.c @@ -139,7 +139,9 @@ acpi_ex_read_data_from_field(struct acpi_walk_state *walk_state, || obj_desc->field.region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS || obj_desc->field.region_obj->region.space_id == - ACPI_ADR_SPACE_IPMI)) { + ACPI_ADR_SPACE_IPMI + || obj_desc->field.region_obj->region.space_id == + ACPI_ADR_SPACE_PLATFORM_RT)) { /* SMBus, GSBus, IPMI serial */ @@ -301,7 +303,9 @@ acpi_ex_write_data_to_field(union acpi_operand_object *source_desc, || obj_desc->field.region_obj->region.space_id == ACPI_ADR_SPACE_GSBUS || obj_desc->field.region_obj->region.space_id == - ACPI_ADR_SPACE_IPMI)) { + ACPI_ADR_SPACE_IPMI + || obj_desc->field.region_obj->region.space_id == + ACPI_ADR_SPACE_PLATFORM_RT)) { /* SMBus, GSBus, IPMI serial */ diff --git a/drivers/acpi/acpica/exserial.c b/drivers/acpi/acpica/exserial.c index 8e8d95f7947b..10d68a5f76a3 100644 --- a/drivers/acpi/acpica/exserial.c +++ b/drivers/acpi/acpica/exserial.c @@ -195,6 +195,12 @@ acpi_ex_read_serial_bus(union acpi_operand_object *obj_desc, function = ACPI_READ | (accessor_type << 16); break; + case ACPI_ADR_SPACE_PLATFORM_RT: + + buffer_length = ACPI_PRM_INPUT_BUFFER_SIZE; + function = ACPI_READ; + break; + default: return_ACPI_STATUS(AE_AML_INVALID_SPACE_ID); } @@ -311,6 +317,12 @@ acpi_ex_write_serial_bus(union acpi_operand_object *source_desc, function = ACPI_WRITE | (accessor_type << 16); break; + case ACPI_ADR_SPACE_PLATFORM_RT: + + buffer_length = ACPI_PRM_INPUT_BUFFER_SIZE; + function = ACPI_WRITE; + break; + default: return_ACPI_STATUS(AE_AML_INVALID_SPACE_ID); } diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c index 14b71b41e845..38e10ab976e6 100644 --- a/drivers/acpi/acpica/nsrepair2.c +++ b/drivers/acpi/acpica/nsrepair2.c @@ -379,6 +379,13 @@ acpi_ns_repair_CID(struct acpi_evaluate_info *info, (*element_ptr)->common.reference_count = original_ref_count; + + /* + * The original_element holds a reference from the package object + * that represents _HID. Since a new element was created by _HID, + * remove the reference from the _CID package. + */ + acpi_ut_remove_reference(original_element); } element_ptr++; diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c index e37d612e8db5..05426596d1f4 100644 --- a/drivers/acpi/acpica/utprint.c +++ b/drivers/acpi/acpica/utprint.c @@ -475,7 +475,7 @@ int vsnprintf(char *string, acpi_size size, const char *format, va_list args) case 'X': type |= ACPI_FORMAT_UPPER; - /* FALLTHROUGH */ + ACPI_FALLTHROUGH; case 'x': diff --git a/drivers/acpi/acpica/utuuid.c b/drivers/acpi/acpica/utuuid.c index 090e44b6b6c7..dca9061518ab 100644 --- a/drivers/acpi/acpica/utuuid.c +++ b/drivers/acpi/acpica/utuuid.c @@ -61,4 +61,45 @@ void acpi_ut_convert_string_to_uuid(char *in_string, u8 *uuid_buffer) 1]); } } + +/******************************************************************************* + * + * FUNCTION: acpi_ut_convert_uuid_to_string + * + * PARAMETERS: uuid_buffer - 16-byte UUID buffer + * out_string - 36-byte formatted UUID string + * + * RETURN: Status + * + * DESCRIPTION: Convert 16-byte UUID buffer to 36-byte formatted UUID string + * out_string must be 37 bytes to include null terminator. + * + ******************************************************************************/ + +acpi_status acpi_ut_convert_uuid_to_string(char *uuid_buffer, char *out_string) +{ + u32 i; + + if (!uuid_buffer || !out_string) { + return (AE_BAD_PARAMETER); + } + + for (i = 0; i < UUID_BUFFER_LENGTH; i++) { + out_string[acpi_gbl_map_to_uuid_offset[i]] = + acpi_ut_hex_to_ascii_char(uuid_buffer[i], 4); + + out_string[acpi_gbl_map_to_uuid_offset[i] + 1] = + acpi_ut_hex_to_ascii_char(uuid_buffer[i], 0); + } + + /* Insert required hyphens (dashes) */ + + out_string[UUID_HYPHEN1_OFFSET] = + out_string[UUID_HYPHEN2_OFFSET] = + out_string[UUID_HYPHEN3_OFFSET] = + out_string[UUID_HYPHEN4_OFFSET] = '-'; + + out_string[UUID_STRING_LENGTH] = 0; /* Null terminate */ + return (AE_OK); +} #endif diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c index 328e8aeece6c..2882450c443e 100644 --- a/drivers/acpi/apei/einj.c +++ b/drivers/acpi/apei/einj.c @@ -673,7 +673,7 @@ static int __init einj_init(void) struct apei_exec_context ctx; if (acpi_disabled) { - pr_warn("ACPI disabled.\n"); + pr_info("ACPI disabled.\n"); return -ENODEV; } diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index fce7ade2aba9..0c8330ed1ffd 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -441,28 +441,35 @@ static void ghes_kick_task_work(struct callback_head *head) gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len); } -static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, - int sev) +static bool ghes_do_memory_failure(u64 physical_addr, int flags) { unsigned long pfn; - int flags = -1; - int sec_sev = ghes_severity(gdata->error_severity); - struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata); if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE)) return false; - if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) - return false; - - pfn = mem_err->physical_addr >> PAGE_SHIFT; + pfn = PHYS_PFN(physical_addr); if (!pfn_valid(pfn)) { pr_warn_ratelimited(FW_WARN GHES_PFX "Invalid address in generic error data: %#llx\n", - mem_err->physical_addr); + physical_addr); return false; } + memory_failure_queue(pfn, flags); + return true; +} + +static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, + int sev) +{ + int flags = -1; + int sec_sev = ghes_severity(gdata->error_severity); + struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata); + + if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) + return false; + /* iff following two events can be handled properly by now */ if (sec_sev == GHES_SEV_CORRECTED && (gdata->flags & CPER_SEC_ERROR_THRESHOLD_EXCEEDED)) @@ -470,14 +477,56 @@ static bool ghes_handle_memory_failure(struct acpi_hest_generic_data *gdata, if (sev == GHES_SEV_RECOVERABLE && sec_sev == GHES_SEV_RECOVERABLE) flags = 0; - if (flags != -1) { - memory_failure_queue(pfn, flags); - return true; - } + if (flags != -1) + return ghes_do_memory_failure(mem_err->physical_addr, flags); return false; } +static bool ghes_handle_arm_hw_error(struct acpi_hest_generic_data *gdata, int sev) +{ + struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata); + bool queued = false; + int sec_sev, i; + char *p; + + log_arm_hw_error(err); + + sec_sev = ghes_severity(gdata->error_severity); + if (sev != GHES_SEV_RECOVERABLE || sec_sev != GHES_SEV_RECOVERABLE) + return false; + + p = (char *)(err + 1); + for (i = 0; i < err->err_info_num; i++) { + struct cper_arm_err_info *err_info = (struct cper_arm_err_info *)p; + bool is_cache = (err_info->type == CPER_ARM_CACHE_ERROR); + bool has_pa = (err_info->validation_bits & CPER_ARM_INFO_VALID_PHYSICAL_ADDR); + const char *error_type = "unknown error"; + + /* + * The field (err_info->error_info & BIT(26)) is fixed to set to + * 1 in some old firmware of HiSilicon Kunpeng920. We assume that + * firmware won't mix corrected errors in an uncorrected section, + * and don't filter out 'corrected' error here. + */ + if (is_cache && has_pa) { + queued = ghes_do_memory_failure(err_info->physical_fault_addr, 0); + p += err_info->length; + continue; + } + + if (err_info->type < ARRAY_SIZE(cper_proc_error_type_strs)) + error_type = cper_proc_error_type_strs[err_info->type]; + + pr_warn_ratelimited(FW_WARN GHES_PFX + "Unhandled processor error type: %s\n", + error_type); + p += err_info->length; + } + + return queued; +} + /* * PCIe AER errors need to be sent to the AER driver for reporting and * recovery. The GHES severities map to the following AER severities and @@ -605,9 +654,7 @@ static bool ghes_do_proc(struct ghes *ghes, ghes_handle_aer(gdata); } else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) { - struct cper_sec_proc_arm *err = acpi_hest_get_payload(gdata); - - log_arm_hw_error(err); + queued = ghes_handle_arm_hw_error(gdata, sev); } else { void *err = acpi_hest_get_payload(gdata); diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 3912a1f6058e..e34937e11186 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -976,7 +976,7 @@ static void iort_named_component_init(struct device *dev, FIELD_GET(ACPI_IORT_NC_PASID_BITS, nc->node_flags)); - if (device_add_properties(dev, props)) + if (device_create_managed_software_node(dev, props, NULL)) dev_warn(dev, "Could not add device properties\n"); } diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c index 19bb7f870204..02d208732f9a 100644 --- a/drivers/acpi/bgrt.c +++ b/drivers/acpi/bgrt.c @@ -15,40 +15,19 @@ static void *bgrt_image; static struct kobject *bgrt_kobj; -static ssize_t version_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.version); -} -static DEVICE_ATTR_RO(version); +#define BGRT_SHOW(_name, _member) \ + static ssize_t _name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf) \ + { \ + return sysfs_emit(buf, "%d\n", bgrt_tab._member); \ + } \ + struct kobj_attribute bgrt_attr_##_name = __ATTR_RO(_name) -static ssize_t status_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.status); -} -static DEVICE_ATTR_RO(status); - -static ssize_t type_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_type); -} -static DEVICE_ATTR_RO(type); - -static ssize_t xoffset_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_offset_x); -} -static DEVICE_ATTR_RO(xoffset); - -static ssize_t yoffset_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_offset_y); -} -static DEVICE_ATTR_RO(yoffset); +BGRT_SHOW(version, version); +BGRT_SHOW(status, status); +BGRT_SHOW(type, image_type); +BGRT_SHOW(xoffset, image_offset_x); +BGRT_SHOW(yoffset, image_offset_y); static ssize_t image_read(struct file *file, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) @@ -60,11 +39,11 @@ static ssize_t image_read(struct file *file, struct kobject *kobj, static BIN_ATTR_RO(image, 0); /* size gets filled in later */ static struct attribute *bgrt_attributes[] = { - &dev_attr_version.attr, - &dev_attr_status.attr, - &dev_attr_type.attr, - &dev_attr_xoffset.attr, - &dev_attr_yoffset.attr, + &bgrt_attr_version.attr, + &bgrt_attr_status.attr, + &bgrt_attr_type.attr, + &bgrt_attr_xoffset.attr, + &bgrt_attr_yoffset.attr, NULL, }; diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c index a86a770c9b79..a558d24fb788 100644 --- a/drivers/acpi/blacklist.c +++ b/drivers/acpi/blacklist.c @@ -10,6 +10,8 @@ * Copyright (C) 2002 Andy Grover */ +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include @@ -49,12 +51,12 @@ int __init acpi_blacklisted(void) i = acpi_match_platform_list(acpi_blacklist); if (i >= 0) { - pr_err(PREFIX "Vendor \"%6.6s\" System \"%8.8s\" Revision 0x%x has a known ACPI BIOS problem.\n", + pr_err("Vendor \"%6.6s\" System \"%8.8s\" Revision 0x%x has a known ACPI BIOS problem.\n", acpi_blacklist[i].oem_id, acpi_blacklist[i].oem_table_id, acpi_blacklist[i].oem_revision); - pr_err(PREFIX "Reason: %s. This is a %s error\n", + pr_err("Reason: %s. This is a %s error\n", acpi_blacklist[i].reason, (acpi_blacklist[i].data ? "non-recoverable" : "recoverable")); @@ -73,8 +75,7 @@ int __init acpi_blacklisted(void) #ifdef CONFIG_ACPI_REV_OVERRIDE_POSSIBLE static int __init dmi_enable_rev_override(const struct dmi_system_id *d) { - printk(KERN_NOTICE PREFIX "DMI detected: %s (force ACPI _REV to 5)\n", - d->ident); + pr_notice("DMI detected: %s (force ACPI _REV to 5)\n", d->ident); acpi_rev_override_setup(NULL); return 0; } diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index a4bd673934c0..60fb6a843853 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -30,6 +30,7 @@ #include #include #include +#include #include "internal.h" @@ -262,8 +263,6 @@ out_success: out_kfree: kfree(output.pointer); - if (status != AE_OK) - context->ret.pointer = NULL; return status; } EXPORT_SYMBOL(acpi_run_osc); @@ -304,6 +303,7 @@ static void acpi_bus_osc_negotiate_platform_control(void) capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_HOTPLUG_OST_SUPPORT; capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PCLPI_SUPPORT; + capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PRM_SUPPORT; #ifdef CONFIG_ARM64 capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_GENERIC_INITIATOR_SUPPORT; @@ -359,7 +359,7 @@ EXPORT_SYMBOL_GPL(osc_sb_native_usb4_control); static void acpi_bus_decode_usb_osc(const char *msg, u32 bits) { - printk(KERN_INFO PREFIX "%s USB3%c DisplayPort%c PCIe%c XDomain%c\n", msg, + pr_info("%s USB3%c DisplayPort%c PCIe%c XDomain%c\n", msg, (bits & OSC_USB_USB3_TUNNELING) ? '+' : '-', (bits & OSC_USB_DP_TUNNELING) ? '+' : '-', (bits & OSC_USB_PCIE_TUNNELING) ? '+' : '-', @@ -398,7 +398,7 @@ static void acpi_bus_osc_negotiate_usb_control(void) return; if (context.ret.length != sizeof(capbuf)) { - printk(KERN_INFO PREFIX "USB4 _OSC: returned invalid length buffer\n"); + pr_info("USB4 _OSC: returned invalid length buffer\n"); goto out_free; } @@ -1195,7 +1195,8 @@ void __init acpi_subsystem_init(void) static acpi_status acpi_bus_table_handler(u32 event, void *table, void *context) { - acpi_scan_table_handler(event, table, context); + if (event == ACPI_TABLE_EVENT_LOAD) + acpi_scan_table_notify(); return acpi_sysfs_table_handler(event, table, context); } @@ -1314,13 +1315,13 @@ static int __init acpi_init(void) } acpi_kobj = kobject_create_and_add("acpi", firmware_kobj); - if (!acpi_kobj) { + if (!acpi_kobj) pr_debug("%s: kset create error\n", __func__); - acpi_kobj = NULL; - } + init_prmt(); result = acpi_bus_init(); if (result) { + kobject_put(acpi_kobj); disable_acpi(); return result; } diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index d260bc1f3e6e..0028b6b51c87 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -20,6 +20,7 @@ #include #include +#include "fan.h" #include "internal.h" /** @@ -1133,19 +1134,48 @@ static int acpi_subsys_resume_noirq(struct device *dev) * * Use ACPI to put the given device into the full-power state and carry out the * generic early resume procedure for it during system transition into the - * working state. + * working state, but only do that if device either defines early resume + * handler, or does not define power operations at all. Otherwise powering up + * of the device is postponed to the normal resume phase. */ static int acpi_subsys_resume_early(struct device *dev) { + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; int ret; if (dev_pm_skip_resume(dev)) return 0; + if (pm && !pm->resume_early) { + dev_dbg(dev, "postponing D0 transition to normal resume stage\n"); + return 0; + } + ret = acpi_dev_resume(dev); return ret ? ret : pm_generic_resume_early(dev); } +/** + * acpi_subsys_resume - Resume device using ACPI. + * @dev: Device to Resume. + * + * Use ACPI to put the given device into the full-power state if it has not been + * powered up during early resume phase, and carry out the generic resume + * procedure for it during system transition into the working state. + */ +static int acpi_subsys_resume(struct device *dev) +{ + const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + int ret = 0; + + if (!dev_pm_skip_resume(dev) && pm && !pm->resume_early) { + dev_dbg(dev, "executing postponed D0 transition\n"); + ret = acpi_dev_resume(dev); + } + + return ret ? ret : pm_generic_resume(dev); +} + /** * acpi_subsys_freeze - Run the device driver's freeze callback. * @dev: Device to handle. @@ -1239,6 +1269,7 @@ static struct dev_pm_domain acpi_general_pm_domain = { .prepare = acpi_subsys_prepare, .complete = acpi_subsys_complete, .suspend = acpi_subsys_suspend, + .resume = acpi_subsys_resume, .suspend_late = acpi_subsys_suspend_late, .suspend_noirq = acpi_subsys_suspend_noirq, .resume_noirq = acpi_subsys_resume_noirq, @@ -1310,10 +1341,7 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on) * with the generic ACPI PM domain. */ static const struct acpi_device_id special_pm_ids[] = { - {"PNP0C0B", }, /* Generic ACPI fan */ - {"INT3404", }, /* Fan */ - {"INTC1044", }, /* Fan for Tiger Lake generation */ - {"INTC1048", }, /* Fan for Alder Lake generation */ + ACPI_FAN_DEVICE_IDS, {} }; struct acpi_device *adev = ACPI_COMPANION(dev); @@ -1340,4 +1368,36 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on) return 1; } EXPORT_SYMBOL_GPL(acpi_dev_pm_attach); + +/** + * acpi_storage_d3 - Check if D3 should be used in the suspend path + * @dev: Device to check + * + * Return %true if the platform firmware wants @dev to be programmed + * into D3hot or D3cold (if supported) in the suspend path, or %false + * when there is no specific preference. On some platforms, if this + * hint is ignored, @dev may remain unresponsive after suspending the + * platform as a whole. + * + * Although the property has storage in the name it actually is + * applied to the PCIe slot and plugging in a non-storage device the + * same platform restrictions will likely apply. + */ +bool acpi_storage_d3(struct device *dev) +{ + struct acpi_device *adev = ACPI_COMPANION(dev); + u8 val; + + if (force_storage_d3()) + return true; + + if (!adev) + return false; + if (fwnode_property_read_u8(acpi_fwnode_handle(adev), "StorageD3Enable", + &val)) + return false; + return val == 1; +} +EXPORT_SYMBOL_GPL(acpi_storage_d3); + #endif /* CONFIG_PM */ diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c index fa2c1c93072c..61271e61c307 100644 --- a/drivers/acpi/device_sysfs.c +++ b/drivers/acpi/device_sysfs.c @@ -268,6 +268,8 @@ int __acpi_device_uevent_modalias(struct acpi_device *adev, /** * acpi_device_uevent_modalias - uevent modalias for ACPI-enumerated devices. + * @dev: Struct device to get ACPI device node. + * @env: Environment variables of the kobject uevent. * * Create the uevent modalias field for ACPI-enumerated devices. * @@ -313,6 +315,9 @@ static int __acpi_device_modalias(struct acpi_device *adev, char *buf, int size) /** * acpi_device_modalias - modalias sysfs attribute for ACPI-enumerated devices. + * @dev: Struct device to get ACPI device node. + * @buf: The buffer to save pnp_modalias and of_modalias. + * @size: Size of buffer. * * Create the modalias sysfs attribute for ACPI-enumerated devices. * @@ -448,7 +453,7 @@ static ssize_t description_show(struct device *dev, (wchar_t *)acpi_dev->pnp.str_obj->buffer.pointer, acpi_dev->pnp.str_obj->buffer.length, UTF16_LITTLE_ENDIAN, buf, - PAGE_SIZE); + PAGE_SIZE - 1); buf[result++] = '\n'; diff --git a/drivers/acpi/dptf/int340x_thermal.c b/drivers/acpi/dptf/int340x_thermal.c index d14025a85ce8..da5d5f0be2f2 100644 --- a/drivers/acpi/dptf/int340x_thermal.c +++ b/drivers/acpi/dptf/int340x_thermal.c @@ -24,6 +24,7 @@ static const struct acpi_device_id int340x_thermal_device_ids[] = { {"INT3409"}, {"INT340A"}, {"INT340B"}, + {"INT3532"}, {"INTC1040"}, {"INTC1041"}, {"INTC1043"}, @@ -33,6 +34,7 @@ static const struct acpi_device_id int340x_thermal_device_ids[] = { {"INTC1047"}, {"INTC1048"}, {"INTC1049"}, + {"INTC1050"}, {"INTC1060"}, {"INTC1061"}, {""}, diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 13565629ce0a..e629e891d1bb 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -183,6 +183,7 @@ static struct workqueue_struct *ec_query_wq; static int EC_FLAGS_CORRECT_ECDT; /* Needs ECDT port address correction */ static int EC_FLAGS_IGNORE_DSDT_GPE; /* Needs ECDT GPE as correction setting */ +static int EC_FLAGS_TRUST_DSDT_GPE; /* Needs DSDT GPE as correction setting */ static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */ /* -------------------------------------------------------------------------- @@ -1593,7 +1594,8 @@ static int acpi_ec_add(struct acpi_device *device) } if (boot_ec && ec->command_addr == boot_ec->command_addr && - ec->data_addr == boot_ec->data_addr) { + ec->data_addr == boot_ec->data_addr && + !EC_FLAGS_TRUST_DSDT_GPE) { /* * Trust PNP0C09 namespace location rather than * ECDT ID. But trust ECDT GPE rather than _GPE @@ -1627,7 +1629,7 @@ static int acpi_ec_add(struct acpi_device *device) WARN(!ret, "Could not request EC cmd io port 0x%lx", ec->command_addr); /* Reprobe devices depending on the EC */ - acpi_walk_dep_device_list(ec->handle); + acpi_dev_clear_dependencies(device); acpi_handle_debug(ec->handle, "enumerated.\n"); return 0; @@ -1816,6 +1818,18 @@ static int ec_correct_ecdt(const struct dmi_system_id *id) return 0; } +/* + * Some ECDTs contain wrong GPE setting, but they share the same port addresses + * with DSDT EC, don't duplicate the DSDT EC with ECDT EC in this case. + * https://bugzilla.kernel.org/show_bug.cgi?id=209989 + */ +static int ec_honor_dsdt_gpe(const struct dmi_system_id *id) +{ + pr_debug("Detected system needing DSDT GPE setting.\n"); + EC_FLAGS_TRUST_DSDT_GPE = 1; + return 0; +} + /* * Some DSDTs contain wrong GPE setting. * Asus FX502VD/VE, GL702VMK, X550VXK, X580VD @@ -1846,6 +1860,22 @@ static const struct dmi_system_id ec_dmi_table[] __initconst = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "GL702VMK"),}, NULL}, { + ec_honor_ecdt_gpe, "ASUSTeK COMPUTER INC. X505BA", { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X505BA"),}, NULL}, + { + ec_honor_ecdt_gpe, "ASUSTeK COMPUTER INC. X505BP", { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X505BP"),}, NULL}, + { + ec_honor_ecdt_gpe, "ASUSTeK COMPUTER INC. X542BA", { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X542BA"),}, NULL}, + { + ec_honor_ecdt_gpe, "ASUSTeK COMPUTER INC. X542BP", { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "X542BP"),}, NULL}, + { ec_honor_ecdt_gpe, "ASUS X550VXK", { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "X550VXK"),}, NULL}, @@ -1854,6 +1884,11 @@ static const struct dmi_system_id ec_dmi_table[] __initconst = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "X580VD"),}, NULL}, { + /* https://bugzilla.kernel.org/show_bug.cgi?id=209989 */ + ec_honor_dsdt_gpe, "HP Pavilion Gaming Laptop 15-cx0xxx", { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Gaming Laptop 15-cx0xxx"),}, NULL}, + { ec_clear_on_resume, "Samsung hardware", { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD.")}, NULL}, {}, diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c index 92e59f45329b..d199a19bb292 100644 --- a/drivers/acpi/event.c +++ b/drivers/acpi/event.c @@ -7,6 +7,8 @@ * */ +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include @@ -165,7 +167,7 @@ static int acpi_event_genetlink_init(void) static int __init acpi_event_init(void) { - int error = 0; + int error; if (acpi_disabled) return 0; @@ -173,8 +175,8 @@ static int __init acpi_event_init(void) /* create genetlink for acpi event */ error = acpi_event_genetlink_init(); if (error) - printk(KERN_WARNING PREFIX - "Failed to create genetlink family for ACPI event\n"); + pr_warn("Failed to create genetlink family for ACPI event\n"); + return 0; } diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c index 66c3983f0ccc..5cd0ceb50bc8 100644 --- a/drivers/acpi/fan.c +++ b/drivers/acpi/fan.c @@ -16,6 +16,8 @@ #include #include +#include "fan.h" + MODULE_AUTHOR("Paul Diefenbaugh"); MODULE_DESCRIPTION("ACPI Fan Driver"); MODULE_LICENSE("GPL"); @@ -24,10 +26,7 @@ static int acpi_fan_probe(struct platform_device *pdev); static int acpi_fan_remove(struct platform_device *pdev); static const struct acpi_device_id fan_device_ids[] = { - {"PNP0C0B", 0}, - {"INT3404", 0}, - {"INTC1044", 0}, - {"INTC1048", 0}, + ACPI_FAN_DEVICE_IDS, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, fan_device_ids); diff --git a/drivers/acpi/fan.h b/drivers/acpi/fan.h new file mode 100644 index 000000000000..dc9a6efa514b --- /dev/null +++ b/drivers/acpi/fan.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +/* + * ACPI fan device IDs are shared between the fan driver and the device power + * management code. + * + * Add new device IDs before the generic ACPI fan one. + */ +#define ACPI_FAN_DEVICE_IDS \ + {"INT3404", }, /* Fan */ \ + {"INTC1044", }, /* Fan for Tiger Lake generation */ \ + {"INTC1048", }, /* Fan for Alder Lake generation */ \ + {"PNP0C0B", } /* Generic ACPI fan */ diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c index 0715e3be99a0..fce3f3bba714 100644 --- a/drivers/acpi/glue.c +++ b/drivers/acpi/glue.c @@ -6,6 +6,8 @@ * Copyright (c) 2005 Intel Corp. */ +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include @@ -19,17 +21,6 @@ #include "internal.h" -#define ACPI_GLUE_DEBUG 0 -#if ACPI_GLUE_DEBUG -#define DBG(fmt, ...) \ - printk(KERN_DEBUG PREFIX fmt, ##__VA_ARGS__) -#else -#define DBG(fmt, ...) \ -do { \ - if (0) \ - printk(KERN_DEBUG PREFIX fmt, ##__VA_ARGS__); \ -} while (0) -#endif static LIST_HEAD(bus_type_list); static DECLARE_RWSEM(bus_type_sem); @@ -44,7 +35,7 @@ int register_acpi_bus_type(struct acpi_bus_type *type) down_write(&bus_type_sem); list_add_tail(&type->list, &bus_type_list); up_write(&bus_type_sem); - printk(KERN_INFO PREFIX "bus type %s registered\n", type->name); + pr_info("bus type %s registered\n", type->name); return 0; } return -ENODEV; @@ -59,8 +50,7 @@ int unregister_acpi_bus_type(struct acpi_bus_type *type) down_write(&bus_type_sem); list_del_init(&type->list); up_write(&bus_type_sem); - printk(KERN_INFO PREFIX "bus type %s unregistered\n", - type->name); + pr_info("bus type %s unregistered\n", type->name); return 0; } return -ENODEV; @@ -307,7 +297,7 @@ static int acpi_device_notify(struct device *dev) adev = type->find_companion(dev); if (!adev) { - DBG("Unable to get handle for %s\n", dev_name(dev)); + pr_debug("Unable to get handle for %s\n", dev_name(dev)); ret = -ENODEV; goto out; } @@ -328,16 +318,15 @@ static int acpi_device_notify(struct device *dev) adev->handler->bind(dev); out: -#if ACPI_GLUE_DEBUG if (!ret) { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; acpi_get_name(ACPI_HANDLE(dev), ACPI_FULL_PATHNAME, &buffer); - DBG("Device %s -> %s\n", dev_name(dev), (char *)buffer.pointer); + pr_debug("Device %s -> %s\n", dev_name(dev), (char *)buffer.pointer); kfree(buffer.pointer); - } else - DBG("Device %s -> No ACPI support\n", dev_name(dev)); -#endif + } else { + pr_debug("Device %s -> No ACPI support\n", dev_name(dev)); + } return ret; } diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index e21611c9a170..d91b560e8867 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -11,8 +11,6 @@ #include -#define PREFIX "ACPI: " - int early_acpi_osi_init(void); int acpi_osi_init(void); acpi_status acpi_os_initialize1(void); @@ -88,7 +86,7 @@ void acpi_device_hotplug(struct acpi_device *adev, u32 src); bool acpi_scan_is_offline(struct acpi_device *adev, bool uevent); acpi_status acpi_sysfs_table_handler(u32 event, void *table, void *context); -void acpi_scan_table_handler(u32 event, void *table, void *context); +void acpi_scan_table_notify(void); /* -------------------------------------------------------------------------- Device Node Initialization / Removal @@ -142,7 +140,7 @@ int acpi_device_sleep_wake(struct acpi_device *dev, int acpi_power_get_inferred_state(struct acpi_device *device, int *state); int acpi_power_on_resources(struct acpi_device *device, int state); int acpi_power_transition(struct acpi_device *device, int state); -void acpi_turn_off_unused_power_resources(bool init); +void acpi_turn_off_unused_power_resources(void); /* -------------------------------------------------------------------------- Device Power Management @@ -236,6 +234,15 @@ static inline int suspend_nvs_save(void) { return 0; } static inline void suspend_nvs_restore(void) {} #endif +#ifdef CONFIG_X86 +bool force_storage_d3(void); +#else +static inline bool force_storage_d3(void) +{ + return false; +} +#endif + /*-------------------------------------------------------------------------- Device properties -------------------------------------------------------------------------- */ diff --git a/drivers/acpi/nvs.c b/drivers/acpi/nvs.c index 9f8712a557b3..a2b11069e792 100644 --- a/drivers/acpi/nvs.c +++ b/drivers/acpi/nvs.c @@ -5,6 +5,8 @@ * Copyright (C) 2008-2011 Rafael J. Wysocki , Novell Inc. */ +#define pr_fmt(fmt) "ACPI: PM: " fmt + #include #include #include @@ -82,19 +84,19 @@ struct nvs_page { static LIST_HEAD(nvs_list); /** - * suspend_nvs_register - register platform NVS memory region to save - * @start - physical address of the region - * @size - size of the region + * suspend_nvs_register - register platform NVS memory region to save + * @start: Physical address of the region. + * @size: Size of the region. * - * The NVS region need not be page-aligned (both ends) and we arrange - * things so that the data from page-aligned addresses in this region will - * be copied into separate RAM pages. + * The NVS region need not be page-aligned (both ends) and we arrange + * things so that the data from page-aligned addresses in this region will + * be copied into separate RAM pages. */ static int suspend_nvs_register(unsigned long start, unsigned long size) { struct nvs_page *entry, *next; - pr_info("PM: Registering ACPI NVS region [mem %#010lx-%#010lx] (%ld bytes)\n", + pr_info("Registering ACPI NVS region [mem %#010lx-%#010lx] (%ld bytes)\n", start, start + size - 1, size); while (size > 0) { @@ -123,7 +125,7 @@ static int suspend_nvs_register(unsigned long start, unsigned long size) } /** - * suspend_nvs_free - free data pages allocated for saving NVS regions + * suspend_nvs_free - free data pages allocated for saving NVS regions */ void suspend_nvs_free(void) { @@ -147,7 +149,7 @@ void suspend_nvs_free(void) } /** - * suspend_nvs_alloc - allocate memory necessary for saving NVS regions + * suspend_nvs_alloc - allocate memory necessary for saving NVS regions */ int suspend_nvs_alloc(void) { @@ -164,13 +166,13 @@ int suspend_nvs_alloc(void) } /** - * suspend_nvs_save - save NVS memory regions + * suspend_nvs_save - save NVS memory regions */ int suspend_nvs_save(void) { struct nvs_page *entry; - printk(KERN_INFO "PM: Saving platform NVS memory\n"); + pr_info("Saving platform NVS memory\n"); list_for_each_entry(entry, &nvs_list, node) if (entry->data) { @@ -193,16 +195,16 @@ int suspend_nvs_save(void) } /** - * suspend_nvs_restore - restore NVS memory regions + * suspend_nvs_restore - restore NVS memory regions * - * This function is going to be called with interrupts disabled, so it - * cannot iounmap the virtual addresses used to access the NVS region. + * This function is going to be called with interrupts disabled, so it + * cannot iounmap the virtual addresses used to access the NVS region. */ void suspend_nvs_restore(void) { struct nvs_page *entry; - printk(KERN_INFO "PM: Restoring platform NVS memory\n"); + pr_info("Restoring platform NVS memory\n"); list_for_each_entry(entry, &nvs_list, node) if (entry->data) diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 327e1b4eb6b0..45c5c0e45e33 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -212,7 +212,7 @@ acpi_physical_address __init acpi_os_get_root_pointer(void) return efi.acpi20; if (efi.acpi != EFI_INVALID_TABLE_ADDR) return efi.acpi; - pr_err(PREFIX "System description tables not found\n"); + pr_err("System description tables not found\n"); } else if (IS_ENABLED(CONFIG_ACPI_LEGACY_TABLES_LOOKUP)) { acpi_find_root_pointer(&pa); } @@ -430,7 +430,7 @@ void __ref acpi_os_unmap_iomem(void __iomem *virt, acpi_size size) map = acpi_map_lookup_virt(virt, size); if (!map) { mutex_unlock(&acpi_ioremap_lock); - WARN(true, PREFIX "%s: bad address %p\n", __func__, virt); + WARN(true, "ACPI: %s: bad address %p\n", __func__, virt); return; } acpi_os_drop_map_ref(map); @@ -1487,12 +1487,7 @@ EXPORT_SYMBOL(acpi_check_resource_conflict); int acpi_check_region(resource_size_t start, resource_size_t n, const char *name) { - struct resource res = { - .start = start, - .end = start + n - 1, - .name = name, - .flags = IORESOURCE_IO, - }; + struct resource res = DEFINE_RES_IO_NAMED(start, n, name); return acpi_check_resource_conflict(&res); } diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index dcd593766a64..d7deedf3548e 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -6,6 +6,8 @@ * Copyright (C) 2001, 2002 Paul Diefenbaugh */ +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include @@ -574,7 +576,7 @@ static int acpi_pci_root_add(struct acpi_device *device, goto end; } - pr_info(PREFIX "%s [%s] (domain %04x %pR)\n", + pr_info("%s [%s] (domain %04x %pR)\n", acpi_device_name(device), acpi_device_bid(device), root->segment, &root->secondary); diff --git a/drivers/acpi/pmic/Kconfig b/drivers/acpi/pmic/Kconfig index 56bbcb2ce61b..f84b8f6038dc 100644 --- a/drivers/acpi/pmic/Kconfig +++ b/drivers/acpi/pmic/Kconfig @@ -52,7 +52,7 @@ endif # PMIC_OPREGION config TPS68470_PMIC_OPREGION bool "ACPI operation region support for TPS68470 PMIC" - depends on MFD_TPS68470 + depends on INTEL_SKL_INT3472 help This config adds ACPI operation region support for TI TPS68470 PMIC. TPS68470 device is an advanced power management unit that powers diff --git a/drivers/acpi/pmic/intel_pmic_chtdc_ti.c b/drivers/acpi/pmic/intel_pmic_chtdc_ti.c index a5101b07611a..fef7831d0d63 100644 --- a/drivers/acpi/pmic/intel_pmic_chtdc_ti.c +++ b/drivers/acpi/pmic/intel_pmic_chtdc_ti.c @@ -117,7 +117,7 @@ static int chtdc_ti_pmic_opregion_probe(struct platform_device *pdev) return err; /* Re-enumerate devices depending on PMIC */ - acpi_walk_dep_device_list(ACPI_HANDLE(pdev->dev.parent)); + acpi_dev_clear_dependencies(ACPI_COMPANION(pdev->dev.parent)); return 0; } diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 97c9a94a1a30..eba7785047ca 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -52,7 +52,7 @@ struct acpi_power_resource { u32 system_level; u32 order; unsigned int ref_count; - unsigned int users; + u8 state; bool wakeup_enabled; struct mutex resource_lock; struct list_head dependents; @@ -173,8 +173,6 @@ int acpi_extract_power_resources(union acpi_object *package, unsigned int start, err = acpi_power_resources_list_add(rhandle, list); if (err) break; - - to_power_resource(rdev)->users++; } if (err) acpi_power_resources_list_free(list); @@ -182,44 +180,54 @@ int acpi_extract_power_resources(union acpi_object *package, unsigned int start, return err; } -static int acpi_power_get_state(acpi_handle handle, int *state) +static int __get_state(acpi_handle handle, u8 *state) { acpi_status status = AE_OK; unsigned long long sta = 0; - - if (!handle || !state) - return -EINVAL; + u8 cur_state; status = acpi_evaluate_integer(handle, "_STA", NULL, &sta); if (ACPI_FAILURE(status)) return -ENODEV; - *state = (sta & 0x01)?ACPI_POWER_RESOURCE_STATE_ON: - ACPI_POWER_RESOURCE_STATE_OFF; + cur_state = sta & ACPI_POWER_RESOURCE_STATE_ON; acpi_handle_debug(handle, "Power resource is %s\n", - *state ? "on" : "off"); + cur_state ? "on" : "off"); + *state = cur_state; return 0; } -static int acpi_power_get_list_state(struct list_head *list, int *state) +static int acpi_power_get_state(struct acpi_power_resource *resource, u8 *state) +{ + if (resource->state == ACPI_POWER_RESOURCE_STATE_UNKNOWN) { + int ret; + + ret = __get_state(resource->device.handle, &resource->state); + if (ret) + return ret; + } + + *state = resource->state; + return 0; +} + +static int acpi_power_get_list_state(struct list_head *list, u8 *state) { struct acpi_power_resource_entry *entry; - int cur_state; + u8 cur_state = ACPI_POWER_RESOURCE_STATE_OFF; if (!list || !state) return -EINVAL; /* The state of the list is 'on' IFF all resources are 'on'. */ - cur_state = 0; list_for_each_entry(entry, list, node) { struct acpi_power_resource *resource = entry->resource; - acpi_handle handle = resource->device.handle; int result; mutex_lock(&resource->resource_lock); - result = acpi_power_get_state(handle, &cur_state); + result = acpi_power_get_state(resource, &cur_state); mutex_unlock(&resource->resource_lock); if (result) return result; @@ -352,8 +360,12 @@ static int __acpi_power_on(struct acpi_power_resource *resource) acpi_status status = AE_OK; status = acpi_evaluate_object(resource->device.handle, "_ON", NULL, NULL); - if (ACPI_FAILURE(status)) + if (ACPI_FAILURE(status)) { + resource->state = ACPI_POWER_RESOURCE_STATE_UNKNOWN; return -ENODEV; + } + + resource->state = ACPI_POWER_RESOURCE_STATE_ON; pr_debug("Power resource [%s] turned on\n", resource->name); @@ -405,8 +417,12 @@ static int __acpi_power_off(struct acpi_power_resource *resource) status = acpi_evaluate_object(resource->device.handle, "_OFF", NULL, NULL); - if (ACPI_FAILURE(status)) + if (ACPI_FAILURE(status)) { + resource->state = ACPI_POWER_RESOURCE_STATE_UNKNOWN; return -ENODEV; + } + + resource->state = ACPI_POWER_RESOURCE_STATE_OFF; pr_debug("Power resource [%s] turned off\n", resource->name); @@ -590,13 +606,12 @@ int acpi_power_wakeup_list_init(struct list_head *list, int *system_level_p) list_for_each_entry(entry, list, node) { struct acpi_power_resource *resource = entry->resource; - acpi_handle handle = resource->device.handle; int result; - int state; + u8 state; mutex_lock(&resource->resource_lock); - result = acpi_power_get_state(handle, &state); + result = acpi_power_get_state(resource, &state); if (result) { mutex_unlock(&resource->resource_lock); return result; @@ -789,8 +804,8 @@ int acpi_disable_wakeup_device_power(struct acpi_device *dev) int acpi_power_get_inferred_state(struct acpi_device *device, int *state) { + u8 list_state = ACPI_POWER_RESOURCE_STATE_OFF; int result = 0; - int list_state = 0; int i = 0; if (!device || !state) @@ -919,7 +934,7 @@ struct acpi_device *acpi_add_power_resource(acpi_handle handle) union acpi_object acpi_object; struct acpi_buffer buffer = { sizeof(acpi_object), &acpi_object }; acpi_status status; - int state, result = -ENODEV; + int result; acpi_bus_get_device(handle, &device); if (device) @@ -946,13 +961,9 @@ struct acpi_device *acpi_add_power_resource(acpi_handle handle) resource->system_level = acpi_object.power_resource.system_level; resource->order = acpi_object.power_resource.resource_order; + resource->state = ACPI_POWER_RESOURCE_STATE_UNKNOWN; - result = acpi_power_get_state(handle, &state); - if (result) - goto err; - - pr_info("%s [%s] (%s)\n", acpi_device_name(device), - acpi_device_bid(device), state ? "on" : "off"); + pr_info("%s [%s]\n", acpi_device_name(device), acpi_device_bid(device)); device->flags.match_driver = true; result = acpi_device_add(device, acpi_release_power_resource); @@ -979,11 +990,13 @@ void acpi_resume_power_resources(void) mutex_lock(&power_resource_list_lock); list_for_each_entry(resource, &acpi_power_resource_list, list_node) { - int result, state; + int result; + u8 state; mutex_lock(&resource->resource_lock); - result = acpi_power_get_state(resource->device.handle, &state); + resource->state = ACPI_POWER_RESOURCE_STATE_UNKNOWN; + result = acpi_power_get_state(resource, &state); if (result) { mutex_unlock(&resource->resource_lock); continue; @@ -991,7 +1004,7 @@ void acpi_resume_power_resources(void) if (state == ACPI_POWER_RESOURCE_STATE_OFF && resource->ref_count) { - dev_info(&resource->device.dev, "Turning ON\n"); + dev_dbg(&resource->device.dev, "Turning ON\n"); __acpi_power_on(resource); } @@ -1002,38 +1015,10 @@ void acpi_resume_power_resources(void) } #endif -static void acpi_power_turn_off_if_unused(struct acpi_power_resource *resource, - bool init) -{ - if (resource->ref_count > 0) - return; - - if (init) { - if (resource->users > 0) - return; - } else { - int result, state; - - result = acpi_power_get_state(resource->device.handle, &state); - if (result || state == ACPI_POWER_RESOURCE_STATE_OFF) - return; - } - - dev_info(&resource->device.dev, "Turning OFF\n"); - __acpi_power_off(resource); -} - /** * acpi_turn_off_unused_power_resources - Turn off power resources not in use. - * @init: Control switch. - * - * If @ainit is set, unconditionally turn off all of the ACPI power resources - * without any users. - * - * Otherwise, turn off all ACPI power resources without active references (that - * is, the ones that should be "off" at the moment) that are "on". */ -void acpi_turn_off_unused_power_resources(bool init) +void acpi_turn_off_unused_power_resources(void) { struct acpi_power_resource *resource; @@ -1042,7 +1027,16 @@ void acpi_turn_off_unused_power_resources(bool init) list_for_each_entry_reverse(resource, &acpi_power_resource_list, list_node) { mutex_lock(&resource->resource_lock); - acpi_power_turn_off_if_unused(resource, init); + /* + * Turn off power resources in an unknown state too, because the + * platform firmware on some system expects the OS to turn off + * power resources without any users unconditionally. + */ + if (!resource->ref_count && + resource->state != ACPI_POWER_RESOURCE_STATE_OFF) { + dev_dbg(&resource->device.dev, "Turning OFF\n"); + __acpi_power_off(resource); + } mutex_unlock(&resource->resource_lock); } diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c index 4ae93350b70d..fe69dc518f31 100644 --- a/drivers/acpi/pptt.c +++ b/drivers/acpi/pptt.c @@ -347,6 +347,7 @@ static struct acpi_pptt_cache *acpi_find_cache_node(struct acpi_table_header *ta * @this_leaf: Kernel cache info structure being updated * @found_cache: The PPTT node describing this cache instance * @cpu_node: A unique reference to describe this cache instance + * @revision: The revision of the PPTT table * * The ACPI spec implies that the fields in the cache structures are used to * extend and correct the information probed from the hardware. Lets only @@ -356,8 +357,11 @@ static struct acpi_pptt_cache *acpi_find_cache_node(struct acpi_table_header *ta */ static void update_cache_properties(struct cacheinfo *this_leaf, struct acpi_pptt_cache *found_cache, - struct acpi_pptt_processor *cpu_node) + struct acpi_pptt_processor *cpu_node, + u8 revision) { + struct acpi_pptt_cache_v1* found_cache_v1; + this_leaf->fw_token = cpu_node; if (found_cache->flags & ACPI_PPTT_SIZE_PROPERTY_VALID) this_leaf->size = found_cache->size; @@ -405,6 +409,13 @@ static void update_cache_properties(struct cacheinfo *this_leaf, if (this_leaf->type == CACHE_TYPE_NOCACHE && found_cache->flags & ACPI_PPTT_CACHE_TYPE_VALID) this_leaf->type = CACHE_TYPE_UNIFIED; + + if (revision >= 3 && (found_cache->flags & ACPI_PPTT_CACHE_ID_VALID)) { + found_cache_v1 = ACPI_ADD_PTR(struct acpi_pptt_cache_v1, + found_cache, sizeof(struct acpi_pptt_cache)); + this_leaf->id = found_cache_v1->cache_id; + this_leaf->attributes |= CACHE_ID; + } } static void cache_setup_acpi_cpu(struct acpi_table_header *table, @@ -425,9 +436,8 @@ static void cache_setup_acpi_cpu(struct acpi_table_header *table, &cpu_node); pr_debug("found = %p %p\n", found_cache, cpu_node); if (found_cache) - update_cache_properties(this_leaf, - found_cache, - cpu_node); + update_cache_properties(this_leaf, found_cache, + cpu_node, table->revision); index++; } diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c new file mode 100644 index 000000000000..31cf9aee5edd --- /dev/null +++ b/drivers/acpi/prmt.c @@ -0,0 +1,303 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Author: Erik Kaneda + * Copyright 2020 Intel Corporation + * + * prmt.c + * + * Each PRM service is an executable that is run in a restricted environment + * that is invoked by writing to the PlatformRtMechanism OperationRegion from + * AML bytecode. + * + * init_prmt initializes the Platform Runtime Mechanism (PRM) services by + * processing data in the PRMT as well as registering an ACPI OperationRegion + * handler for the PlatformRtMechanism subtype. + * + */ +#include +#include +#include +#include +#include + +#pragma pack(1) +struct prm_mmio_addr_range { + u64 phys_addr; + u64 virt_addr; + u32 length; +}; + +struct prm_mmio_info { + u64 mmio_count; + struct prm_mmio_addr_range addr_ranges[]; +}; + +struct prm_buffer { + u8 prm_status; + u64 efi_status; + u8 prm_cmd; + guid_t handler_guid; +}; + +struct prm_context_buffer { + char signature[ACPI_NAMESEG_SIZE]; + u16 revision; + u16 reserved; + guid_t identifier; + u64 static_data_buffer; + struct prm_mmio_info *mmio_ranges; +}; +#pragma pack() + + +static LIST_HEAD(prm_module_list); + +struct prm_handler_info { + guid_t guid; + u64 handler_addr; + u64 static_data_buffer_addr; + u64 acpi_param_buffer_addr; + + struct list_head handler_list; +}; + +struct prm_module_info { + guid_t guid; + u16 major_rev; + u16 minor_rev; + u16 handler_count; + struct prm_mmio_info *mmio_info; + bool updatable; + + struct list_head module_list; + struct prm_handler_info handlers[]; +}; + + +static u64 efi_pa_va_lookup(u64 pa) +{ + efi_memory_desc_t *md; + u64 pa_offset = pa & ~PAGE_MASK; + u64 page = pa & PAGE_MASK; + + for_each_efi_memory_desc(md) { + if (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages) + return pa_offset + md->virt_addr + page - md->phys_addr; + } + + return 0; +} + + +#define get_first_handler(a) ((struct acpi_prmt_handler_info *) ((char *) (a) + a->handler_info_offset)) +#define get_next_handler(a) ((struct acpi_prmt_handler_info *) (sizeof(struct acpi_prmt_handler_info) + (char *) a)) + +static int __init +acpi_parse_prmt(union acpi_subtable_headers *header, const unsigned long end) +{ + struct acpi_prmt_module_info *module_info; + struct acpi_prmt_handler_info *handler_info; + struct prm_handler_info *th; + struct prm_module_info *tm; + u64 mmio_count = 0; + u64 cur_handler = 0; + u32 module_info_size = 0; + u64 mmio_range_size = 0; + void *temp_mmio; + + module_info = (struct acpi_prmt_module_info *) header; + module_info_size = struct_size(tm, handlers, module_info->handler_info_count); + tm = kmalloc(module_info_size, GFP_KERNEL); + + guid_copy(&tm->guid, (guid_t *) module_info->module_guid); + tm->major_rev = module_info->major_rev; + tm->minor_rev = module_info->minor_rev; + tm->handler_count = module_info->handler_info_count; + tm->updatable = true; + + if (module_info->mmio_list_pointer) { + /* + * Each module is associated with a list of addr + * ranges that it can use during the service + */ + mmio_count = *(u64 *) memremap(module_info->mmio_list_pointer, 8, MEMREMAP_WB); + mmio_range_size = struct_size(tm->mmio_info, addr_ranges, mmio_count); + tm->mmio_info = kmalloc(mmio_range_size, GFP_KERNEL); + temp_mmio = memremap(module_info->mmio_list_pointer, mmio_range_size, MEMREMAP_WB); + memmove(tm->mmio_info, temp_mmio, mmio_range_size); + } else { + mmio_range_size = struct_size(tm->mmio_info, addr_ranges, mmio_count); + tm->mmio_info = kmalloc(mmio_range_size, GFP_KERNEL); + tm->mmio_info->mmio_count = 0; + } + + INIT_LIST_HEAD(&tm->module_list); + list_add(&tm->module_list, &prm_module_list); + + handler_info = get_first_handler(module_info); + do { + th = &tm->handlers[cur_handler]; + + guid_copy(&th->guid, (guid_t *)handler_info->handler_guid); + th->handler_addr = efi_pa_va_lookup(handler_info->handler_address); + th->static_data_buffer_addr = efi_pa_va_lookup(handler_info->static_data_buffer_address); + th->acpi_param_buffer_addr = efi_pa_va_lookup(handler_info->acpi_param_buffer_address); + } while (++cur_handler < tm->handler_count && (handler_info = get_next_handler(handler_info))); + + return 0; +} + +#define GET_MODULE 0 +#define GET_HANDLER 1 + +static void *find_guid_info(const guid_t *guid, u8 mode) +{ + struct prm_handler_info *cur_handler; + struct prm_module_info *cur_module; + int i = 0; + + list_for_each_entry(cur_module, &prm_module_list, module_list) { + for (i = 0; i < cur_module->handler_count; ++i) { + cur_handler = &cur_module->handlers[i]; + if (guid_equal(guid, &cur_handler->guid)) { + if (mode == GET_MODULE) + return (void *)cur_module; + else + return (void *)cur_handler; + } + } + } + + return NULL; +} + + +static struct prm_module_info *find_prm_module(const guid_t *guid) +{ + return (struct prm_module_info *)find_guid_info(guid, GET_MODULE); +} + +static struct prm_handler_info *find_prm_handler(const guid_t *guid) +{ + return (struct prm_handler_info *) find_guid_info(guid, GET_HANDLER); +} + +/* In-coming PRM commands */ + +#define PRM_CMD_RUN_SERVICE 0 +#define PRM_CMD_START_TRANSACTION 1 +#define PRM_CMD_END_TRANSACTION 2 + +/* statuses that can be passed back to ASL */ + +#define PRM_HANDLER_SUCCESS 0 +#define PRM_HANDLER_ERROR 1 +#define INVALID_PRM_COMMAND 2 +#define PRM_HANDLER_GUID_NOT_FOUND 3 +#define UPDATE_LOCK_ALREADY_HELD 4 +#define UPDATE_UNLOCK_WITHOUT_LOCK 5 + +/* + * This is the PlatformRtMechanism opregion space handler. + * @function: indicates the read/write. In fact as the PlatformRtMechanism + * message is driven by command, only write is meaningful. + * + * @addr : not used + * @bits : not used. + * @value : it is an in/out parameter. It points to the PRM message buffer. + * @handler_context: not used + */ +static acpi_status acpi_platformrt_space_handler(u32 function, + acpi_physical_address addr, + u32 bits, acpi_integer *value, + void *handler_context, + void *region_context) +{ + struct prm_buffer *buffer = ACPI_CAST_PTR(struct prm_buffer, value); + struct prm_handler_info *handler; + struct prm_module_info *module; + efi_status_t status; + struct prm_context_buffer context; + + /* + * The returned acpi_status will always be AE_OK. Error values will be + * saved in the first byte of the PRM message buffer to be used by ASL. + */ + switch (buffer->prm_cmd) { + case PRM_CMD_RUN_SERVICE: + + handler = find_prm_handler(&buffer->handler_guid); + module = find_prm_module(&buffer->handler_guid); + if (!handler || !module) + goto invalid_guid; + + ACPI_COPY_NAMESEG(context.signature, "PRMC"); + context.revision = 0x0; + context.reserved = 0x0; + context.identifier = handler->guid; + context.static_data_buffer = handler->static_data_buffer_addr; + context.mmio_ranges = module->mmio_info; + + status = efi_call_virt_pointer(handler, handler_addr, + handler->acpi_param_buffer_addr, + &context); + if (status == EFI_SUCCESS) { + buffer->prm_status = PRM_HANDLER_SUCCESS; + } else { + buffer->prm_status = PRM_HANDLER_ERROR; + buffer->efi_status = status; + } + break; + + case PRM_CMD_START_TRANSACTION: + + module = find_prm_module(&buffer->handler_guid); + if (!module) + goto invalid_guid; + + if (module->updatable) + module->updatable = false; + else + buffer->prm_status = UPDATE_LOCK_ALREADY_HELD; + break; + + case PRM_CMD_END_TRANSACTION: + + module = find_prm_module(&buffer->handler_guid); + if (!module) + goto invalid_guid; + + if (module->updatable) + buffer->prm_status = UPDATE_UNLOCK_WITHOUT_LOCK; + else + module->updatable = true; + break; + + default: + + buffer->prm_status = INVALID_PRM_COMMAND; + break; + } + + return AE_OK; + +invalid_guid: + buffer->prm_status = PRM_HANDLER_GUID_NOT_FOUND; + return AE_OK; +} + +void __init init_prmt(void) +{ + acpi_status status; + int mc = acpi_table_parse_entries(ACPI_SIG_PRMT, sizeof(struct acpi_table_prmt) + + sizeof (struct acpi_table_prmt_header), + 0, acpi_parse_prmt, 0); + pr_info("PRM: found %u modules\n", mc); + + status = acpi_install_address_space_handler(ACPI_ROOT_OBJECT, + ACPI_ADR_SPACE_PLATFORM_RT, + &acpi_platformrt_space_handler, + NULL, NULL); + if (ACPI_FAILURE(status)) + pr_alert("PRM: OperationRegion handler could not be installed\n"); +} diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 45a019619e4a..095c8aca141e 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -16,6 +16,7 @@ #include #include #include /* need_resched() */ +#include #include #include #include @@ -384,10 +385,37 @@ static void acpi_processor_power_verify_c3(struct acpi_processor *pr, return; } +static int acpi_cst_latency_cmp(const void *a, const void *b) +{ + const struct acpi_processor_cx *x = a, *y = b; + + if (!(x->valid && y->valid)) + return 0; + if (x->latency > y->latency) + return 1; + if (x->latency < y->latency) + return -1; + return 0; +} +static void acpi_cst_latency_swap(void *a, void *b, int n) +{ + struct acpi_processor_cx *x = a, *y = b; + u32 tmp; + + if (!(x->valid && y->valid)) + return; + tmp = x->latency; + x->latency = y->latency; + y->latency = tmp; +} + static int acpi_processor_power_verify(struct acpi_processor *pr) { unsigned int i; unsigned int working = 0; + unsigned int last_latency = 0; + unsigned int last_type = 0; + bool buggy_latency = false; pr->power.timer_broadcast_on_state = INT_MAX; @@ -411,12 +439,24 @@ static int acpi_processor_power_verify(struct acpi_processor *pr) } if (!cx->valid) continue; + if (cx->type >= last_type && cx->latency < last_latency) + buggy_latency = true; + last_latency = cx->latency; + last_type = cx->type; lapic_timer_check_state(i, pr, cx); tsc_check_state(cx->type); working++; } + if (buggy_latency) { + pr_notice("FW issue: working around C-state latencies out of order\n"); + sort(&pr->power.states[1], max_cstate, + sizeof(struct acpi_processor_cx), + acpi_cst_latency_cmp, + acpi_cst_latency_swap); + } + lapic_timer_propagate_broadcast(pr); return (working); diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index d088a0089ee9..757a98f6d7a2 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -9,6 +9,8 @@ * - Added processor hotplug support */ +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include @@ -20,8 +22,6 @@ #include #endif -#define PREFIX "ACPI: " - #define ACPI_PROCESSOR_FILE_PERFORMANCE "performance" static DEFINE_MUTEX(performance_mutex); @@ -194,7 +194,6 @@ static int acpi_processor_get_performance_control(struct acpi_processor *pr) union acpi_object *pct = NULL; union acpi_object obj = { 0 }; - status = acpi_evaluate_object(pr->handle, "_PCT", NULL, &buffer); if (ACPI_FAILURE(status)) { acpi_evaluation_failure_warn(pr->handle, "_PCT", status); @@ -204,7 +203,7 @@ static int acpi_processor_get_performance_control(struct acpi_processor *pr) pct = (union acpi_object *)buffer.pointer; if (!pct || (pct->type != ACPI_TYPE_PACKAGE) || (pct->package.count != 2)) { - printk(KERN_ERR PREFIX "Invalid _PCT data\n"); + pr_err("Invalid _PCT data\n"); result = -EFAULT; goto end; } @@ -218,7 +217,7 @@ static int acpi_processor_get_performance_control(struct acpi_processor *pr) if ((obj.type != ACPI_TYPE_BUFFER) || (obj.buffer.length < sizeof(struct acpi_pct_register)) || (obj.buffer.pointer == NULL)) { - printk(KERN_ERR PREFIX "Invalid _PCT data (control_register)\n"); + pr_err("Invalid _PCT data (control_register)\n"); result = -EFAULT; goto end; } @@ -234,7 +233,7 @@ static int acpi_processor_get_performance_control(struct acpi_processor *pr) if ((obj.type != ACPI_TYPE_BUFFER) || (obj.buffer.length < sizeof(struct acpi_pct_register)) || (obj.buffer.pointer == NULL)) { - printk(KERN_ERR PREFIX "Invalid _PCT data (status_register)\n"); + pr_err("Invalid _PCT data (status_register)\n"); result = -EFAULT; goto end; } @@ -242,7 +241,7 @@ static int acpi_processor_get_performance_control(struct acpi_processor *pr) memcpy(&pr->performance->status_register, obj.buffer.pointer, sizeof(struct acpi_pct_register)); - end: +end: kfree(buffer.pointer); return result; @@ -294,7 +293,6 @@ static int acpi_processor_get_performance_states(struct acpi_processor *pr) int i; int last_invalid = -1; - status = acpi_evaluate_object(pr->handle, "_PSS", NULL, &buffer); if (ACPI_FAILURE(status)) { acpi_evaluation_failure_warn(pr->handle, "_PSS", status); @@ -303,7 +301,7 @@ static int acpi_processor_get_performance_states(struct acpi_processor *pr) pss = buffer.pointer; if (!pss || (pss->type != ACPI_TYPE_PACKAGE)) { - printk(KERN_ERR PREFIX "Invalid _PSS data\n"); + pr_err("Invalid _PSS data\n"); result = -EFAULT; goto end; } @@ -357,7 +355,7 @@ static int acpi_processor_get_performance_states(struct acpi_processor *pr) if (!px->core_frequency || ((u32)(px->core_frequency * 1000) != (px->core_frequency * 1000))) { - printk(KERN_ERR FW_BUG PREFIX + pr_err(FW_BUG "Invalid BIOS _PSS frequency found for processor %d: 0x%llx MHz\n", pr->id, px->core_frequency); if (last_invalid == -1) @@ -375,8 +373,8 @@ static int acpi_processor_get_performance_states(struct acpi_processor *pr) } if (last_invalid == 0) { - printk(KERN_ERR FW_BUG PREFIX - "No valid BIOS _PSS frequency found for processor %d\n", pr->id); + pr_err(FW_BUG + "No valid BIOS _PSS frequency found for processor %d\n", pr->id); result = -EFAULT; kfree(pr->performance->states); pr->performance->states = NULL; @@ -385,7 +383,7 @@ static int acpi_processor_get_performance_states(struct acpi_processor *pr) if (last_invalid > 0) pr->performance->state_count = last_invalid; - end: +end: kfree(buffer.pointer); return result; @@ -426,7 +424,7 @@ int acpi_processor_get_performance_info(struct acpi_processor *pr) #ifdef CONFIG_X86 if (acpi_has_method(pr->handle, "_PPC")) { if(boot_cpu_has(X86_FEATURE_EST)) - printk(KERN_WARNING FW_BUG "BIOS needs update for CPU " + pr_warn(FW_BUG "BIOS needs update for CPU " "frequency support\n"); } #endif @@ -520,13 +518,13 @@ int acpi_processor_get_psd(acpi_handle handle, struct acpi_psd_package *pdomain) psd = buffer.pointer; if (!psd || (psd->type != ACPI_TYPE_PACKAGE)) { - printk(KERN_ERR PREFIX "Invalid _PSD data\n"); + pr_err("Invalid _PSD data\n"); result = -EFAULT; goto end; } if (psd->package.count != 1) { - printk(KERN_ERR PREFIX "Invalid _PSD data\n"); + pr_err("Invalid _PSD data\n"); result = -EFAULT; goto end; } @@ -537,19 +535,19 @@ int acpi_processor_get_psd(acpi_handle handle, struct acpi_psd_package *pdomain) status = acpi_extract_package(&(psd->package.elements[0]), &format, &state); if (ACPI_FAILURE(status)) { - printk(KERN_ERR PREFIX "Invalid _PSD data\n"); + pr_err("Invalid _PSD data\n"); result = -EFAULT; goto end; } if (pdomain->num_entries != ACPI_PSD_REV0_ENTRIES) { - printk(KERN_ERR PREFIX "Unknown _PSD:num_entries\n"); + pr_err("Unknown _PSD:num_entries\n"); result = -EFAULT; goto end; } if (pdomain->revision != ACPI_PSD_REV0_REVISION) { - printk(KERN_ERR PREFIX "Unknown _PSD:revision\n"); + pr_err("Unknown _PSD:revision\n"); result = -EFAULT; goto end; } @@ -557,7 +555,7 @@ int acpi_processor_get_psd(acpi_handle handle, struct acpi_psd_package *pdomain) if (pdomain->coord_type != DOMAIN_COORD_TYPE_SW_ALL && pdomain->coord_type != DOMAIN_COORD_TYPE_SW_ANY && pdomain->coord_type != DOMAIN_COORD_TYPE_HW_ALL) { - printk(KERN_ERR PREFIX "Invalid _PSD:coord_type\n"); + pr_err("Invalid _PSD:coord_type\n"); result = -EFAULT; goto end; } diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c index 677a132be242..a3d34e3f9f94 100644 --- a/drivers/acpi/processor_thermal.c +++ b/drivers/acpi/processor_thermal.c @@ -17,8 +17,6 @@ #include #include -#define PREFIX "ACPI: " - #ifdef CONFIG_CPU_FREQ /* If a passive cooling situation is detected, primarily CPUfreq is used, as it diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c index e61b8f038364..a822fe410dda 100644 --- a/drivers/acpi/processor_throttling.c +++ b/drivers/acpi/processor_throttling.c @@ -6,9 +6,11 @@ * Copyright (C) 2001, 2002 Paul Diefenbaugh * Copyright (C) 2004 Dominik Brodowski * Copyright (C) 2004 Anil S Keshavamurthy - * - Added processor hotplug support + * - Added processor hotplug support */ +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include @@ -20,8 +22,6 @@ #include #include -#define PREFIX "ACPI: " - /* ignore_tpc: * 0 -> acpi processor driver doesn't ignore _TPC values * 1 -> acpi processor driver ignores _TPC values @@ -195,15 +195,13 @@ void acpi_processor_throttling_init(void) { if (acpi_processor_update_tsd_coord()) pr_debug("Assume no T-state coordination\n"); - - return; } static int acpi_processor_throttling_notifier(unsigned long event, void *data) { struct throttling_tstate *p_tstate = data; struct acpi_processor *pr; - unsigned int cpu ; + unsigned int cpu; int target_state; struct acpi_processor_limit *p_limit; struct acpi_processor_throttling *p_throttling; @@ -236,8 +234,7 @@ static int acpi_processor_throttling_notifier(unsigned long event, void *data) if (pr->throttling_platform_limit > target_state) target_state = pr->throttling_platform_limit; if (target_state >= p_throttling->state_count) { - printk(KERN_WARNING - "Exceed the limit of T-state \n"); + pr_warn("Exceed the limit of T-state \n"); target_state = p_throttling->state_count - 1; } p_tstate->target_state = target_state; @@ -256,8 +253,7 @@ static int acpi_processor_throttling_notifier(unsigned long event, void *data) cpu, target_state); break; default: - printk(KERN_WARNING - "Unsupported Throttling notifier event\n"); + pr_warn("Unsupported Throttling notifier event\n"); break; } @@ -408,7 +404,7 @@ static int acpi_processor_get_throttling_control(struct acpi_processor *pr) acpi_status status = 0; struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; union acpi_object *ptc = NULL; - union acpi_object obj = { 0 }; + union acpi_object obj; struct acpi_processor_throttling *throttling; status = acpi_evaluate_object(pr->handle, "_PTC", NULL, &buffer); @@ -422,7 +418,7 @@ static int acpi_processor_get_throttling_control(struct acpi_processor *pr) ptc = (union acpi_object *)buffer.pointer; if (!ptc || (ptc->type != ACPI_TYPE_PACKAGE) || (ptc->package.count != 2)) { - printk(KERN_ERR PREFIX "Invalid _PTC data\n"); + pr_err("Invalid _PTC data\n"); result = -EFAULT; goto end; } @@ -436,8 +432,7 @@ static int acpi_processor_get_throttling_control(struct acpi_processor *pr) if ((obj.type != ACPI_TYPE_BUFFER) || (obj.buffer.length < sizeof(struct acpi_ptc_register)) || (obj.buffer.pointer == NULL)) { - printk(KERN_ERR PREFIX - "Invalid _PTC data (control_register)\n"); + pr_err("Invalid _PTC data (control_register)\n"); result = -EFAULT; goto end; } @@ -453,7 +448,7 @@ static int acpi_processor_get_throttling_control(struct acpi_processor *pr) if ((obj.type != ACPI_TYPE_BUFFER) || (obj.buffer.length < sizeof(struct acpi_ptc_register)) || (obj.buffer.pointer == NULL)) { - printk(KERN_ERR PREFIX "Invalid _PTC data (status_register)\n"); + pr_err("Invalid _PTC data (status_register)\n"); result = -EFAULT; goto end; } @@ -465,19 +460,19 @@ static int acpi_processor_get_throttling_control(struct acpi_processor *pr) if ((throttling->control_register.bit_width + throttling->control_register.bit_offset) > 32) { - printk(KERN_ERR PREFIX "Invalid _PTC control register\n"); + pr_err("Invalid _PTC control register\n"); result = -EFAULT; goto end; } if ((throttling->status_register.bit_width + throttling->status_register.bit_offset) > 32) { - printk(KERN_ERR PREFIX "Invalid _PTC status register\n"); + pr_err("Invalid _PTC status register\n"); result = -EFAULT; goto end; } - end: +end: kfree(buffer.pointer); return result; @@ -506,7 +501,7 @@ static int acpi_processor_get_throttling_states(struct acpi_processor *pr) tss = buffer.pointer; if (!tss || (tss->type != ACPI_TYPE_PACKAGE)) { - printk(KERN_ERR PREFIX "Invalid _TSS data\n"); + pr_err("Invalid _TSS data\n"); result = -EFAULT; goto end; } @@ -546,15 +541,14 @@ static int acpi_processor_get_throttling_states(struct acpi_processor *pr) } if (!tx->freqpercentage) { - printk(KERN_ERR PREFIX - "Invalid _TSS data: freq is zero\n"); + pr_err("Invalid _TSS data: freq is zero\n"); result = -EFAULT; kfree(pr->throttling.states_tss); goto end; } } - end: +end: kfree(buffer.pointer); return result; @@ -587,13 +581,13 @@ static int acpi_processor_get_tsd(struct acpi_processor *pr) tsd = buffer.pointer; if (!tsd || (tsd->type != ACPI_TYPE_PACKAGE)) { - printk(KERN_ERR PREFIX "Invalid _TSD data\n"); + pr_err("Invalid _TSD data\n"); result = -EFAULT; goto end; } if (tsd->package.count != 1) { - printk(KERN_ERR PREFIX "Invalid _TSD data\n"); + pr_err("Invalid _TSD data\n"); result = -EFAULT; goto end; } @@ -606,19 +600,19 @@ static int acpi_processor_get_tsd(struct acpi_processor *pr) status = acpi_extract_package(&(tsd->package.elements[0]), &format, &state); if (ACPI_FAILURE(status)) { - printk(KERN_ERR PREFIX "Invalid _TSD data\n"); + pr_err("Invalid _TSD data\n"); result = -EFAULT; goto end; } if (pdomain->num_entries != ACPI_TSD_REV0_ENTRIES) { - printk(KERN_ERR PREFIX "Unknown _TSD:num_entries\n"); + pr_err("Unknown _TSD:num_entries\n"); result = -EFAULT; goto end; } if (pdomain->revision != ACPI_TSD_REV0_REVISION) { - printk(KERN_ERR PREFIX "Unknown _TSD:revision\n"); + pr_err("Unknown _TSD:revision\n"); result = -EFAULT; goto end; } @@ -639,7 +633,7 @@ static int acpi_processor_get_tsd(struct acpi_processor *pr) pthrottling->shared_type = DOMAIN_COORD_TYPE_SW_ALL; } - end: +end: kfree(buffer.pointer); return result; } @@ -711,13 +705,12 @@ static int acpi_throttling_rdmsr(u64 *value) if ((this_cpu_read(cpu_info.x86_vendor) != X86_VENDOR_INTEL) || !this_cpu_has(X86_FEATURE_ACPI)) { - printk(KERN_ERR PREFIX - "HARDWARE addr space,NOT supported yet\n"); + pr_err("HARDWARE addr space,NOT supported yet\n"); } else { msr_low = 0; msr_high = 0; rdmsr_safe(MSR_IA32_THERM_CONTROL, - (u32 *)&msr_low , (u32 *) &msr_high); + (u32 *)&msr_low, (u32 *) &msr_high); msr = (msr_high << 32) | msr_low; *value = (u64) msr; ret = 0; @@ -732,8 +725,7 @@ static int acpi_throttling_wrmsr(u64 value) if ((this_cpu_read(cpu_info.x86_vendor) != X86_VENDOR_INTEL) || !this_cpu_has(X86_FEATURE_ACPI)) { - printk(KERN_ERR PREFIX - "HARDWARE addr space,NOT supported yet\n"); + pr_err("HARDWARE addr space,NOT supported yet\n"); } else { msr = value; wrmsr_safe(MSR_IA32_THERM_CONTROL, @@ -745,15 +737,13 @@ static int acpi_throttling_wrmsr(u64 value) #else static int acpi_throttling_rdmsr(u64 *value) { - printk(KERN_ERR PREFIX - "HARDWARE addr space,NOT supported yet\n"); + pr_err("HARDWARE addr space,NOT supported yet\n"); return -1; } static int acpi_throttling_wrmsr(u64 value) { - printk(KERN_ERR PREFIX - "HARDWARE addr space,NOT supported yet\n"); + pr_err("HARDWARE addr space,NOT supported yet\n"); return -1; } #endif @@ -784,7 +774,7 @@ static int acpi_read_throttling_status(struct acpi_processor *pr, ret = acpi_throttling_rdmsr(value); break; default: - printk(KERN_ERR PREFIX "Unknown addr space %d\n", + pr_err("Unknown addr space %d\n", (u32) (throttling->status_register.space_id)); } return ret; @@ -817,7 +807,7 @@ static int acpi_write_throttling_state(struct acpi_processor *pr, ret = acpi_throttling_wrmsr(value); break; default: - printk(KERN_ERR PREFIX "Unknown addr space %d\n", + pr_err("Unknown addr space %d\n", (u32) (throttling->control_register.space_id)); } return ret; @@ -926,7 +916,7 @@ static int acpi_processor_get_fadt_info(struct acpi_processor *pr) } /* TBD: Support duty_cycle values that span bit 4. */ else if ((pr->throttling.duty_offset + pr->throttling.duty_width) > 4) { - printk(KERN_WARNING PREFIX "duty_cycle spans bit 4\n"); + pr_warn("duty_cycle spans bit 4\n"); return -EINVAL; } @@ -1185,8 +1175,7 @@ int acpi_processor_get_throttling_info(struct acpi_processor *pr) */ if (acpi_processor_get_throttling_control(pr) || acpi_processor_get_throttling_states(pr) || - acpi_processor_get_platform_limit(pr)) - { + acpi_processor_get_platform_limit(pr)) { pr->throttling.acpi_processor_get_throttling = &acpi_processor_get_throttling_fadt; pr->throttling.acpi_processor_set_throttling = @@ -1246,7 +1235,7 @@ int acpi_processor_get_throttling_info(struct acpi_processor *pr) goto end; } - end: +end: if (result) pr->flags.throttling = 0; diff --git a/drivers/acpi/reboot.c b/drivers/acpi/reboot.c index 2a61f884e222..b79b7c99c237 100644 --- a/drivers/acpi/reboot.c +++ b/drivers/acpi/reboot.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include @@ -63,7 +65,7 @@ void acpi_reboot(void) case ACPI_ADR_SPACE_SYSTEM_MEMORY: case ACPI_ADR_SPACE_SYSTEM_IO: - printk(KERN_DEBUG "ACPI MEMORY or I/O RESET_REG.\n"); + pr_debug("ACPI MEMORY or I/O RESET_REG.\n"); acpi_reset(); break; } diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index ee78a210c606..dc01fb550b28 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -423,6 +423,13 @@ static void acpi_dev_get_irqresource(struct resource *res, u32 gsi, } } +static bool irq_is_legacy(struct acpi_resource_irq *irq) +{ + return irq->triggering == ACPI_EDGE_SENSITIVE && + irq->polarity == ACPI_ACTIVE_HIGH && + irq->shareable == ACPI_EXCLUSIVE; +} + /** * acpi_dev_resource_interrupt - Extract ACPI interrupt resource information. * @ares: Input ACPI resource object. @@ -461,7 +468,7 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, } acpi_dev_get_irqresource(res, irq->interrupts[index], irq->triggering, irq->polarity, - irq->shareable, true); + irq->shareable, irq_is_legacy(irq)); break; case ACPI_RESOURCE_TYPE_EXTENDED_IRQ: ext_irq = &ares->data.extended_irq; diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index 3b0b6dd34914..4938010fcac7 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -7,6 +7,8 @@ * Copyright (c) 2005 Rich Townsend */ +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include @@ -23,8 +25,6 @@ #include "sbshc.h" -#define PREFIX "ACPI: " - #define ACPI_SBS_CLASS "sbs" #define ACPI_AC_CLASS "ac_adapter" #define ACPI_SBS_DEVICE_NAME "Smart Battery System" @@ -544,7 +544,7 @@ static int acpi_battery_add(struct acpi_sbs *sbs, int id) goto end; battery->have_sysfs_alarm = 1; end: - printk(KERN_INFO PREFIX "%s [%s]: Battery Slot [%s] (battery %s)\n", + pr_info("%s [%s]: Battery Slot [%s] (battery %s)\n", ACPI_SBS_DEVICE_NAME, acpi_device_bid(sbs->device), battery->name, battery->present ? "present" : "absent"); return result; @@ -577,10 +577,10 @@ static int acpi_charger_add(struct acpi_sbs *sbs) result = PTR_ERR(sbs->charger); sbs->charger = NULL; } - printk(KERN_INFO PREFIX "%s [%s]: AC Adapter [%s] (%s)\n", + pr_info("%s [%s]: AC Adapter [%s] (%s)\n", ACPI_SBS_DEVICE_NAME, acpi_device_bid(sbs->device), ACPI_AC_DIR_NAME, sbs->charger_present ? "on-line" : "off-line"); - end: +end: return result; } @@ -658,7 +658,7 @@ static int acpi_sbs_add(struct acpi_device *device) acpi_battery_add(sbs, 0); acpi_smbus_register_callback(sbs->hc, acpi_sbs_callback, sbs); - end: +end: if (result) acpi_sbs_remove(device); return result; diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c index 53c2862c4c75..7c62e149a7a1 100644 --- a/drivers/acpi/sbshc.c +++ b/drivers/acpi/sbshc.c @@ -5,6 +5,8 @@ * Copyright (c) 2007 Alexey Starikovskiy */ +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include @@ -13,8 +15,6 @@ #include #include "sbshc.h" -#define PREFIX "ACPI: " - #define ACPI_SMB_HC_CLASS "smbus_host_ctl" #define ACPI_SMB_HC_DEVICE_NAME "ACPI SMBus HC" @@ -109,7 +109,7 @@ static int acpi_smbus_transaction(struct acpi_smb_hc *hc, u8 protocol, u8 temp, sz = 0; if (!hc) { - printk(KERN_ERR PREFIX "host controller is not configured\n"); + pr_err("host controller is not configured\n"); return ret; } @@ -231,7 +231,6 @@ static int smbus_alarm(void *context) case ACPI_SBS_BATTERY: acpi_os_execute(OSL_NOTIFY_HANDLER, acpi_smbus_callback, hc); - default:; } mutex_unlock(&hc->lock); return 0; @@ -254,7 +253,7 @@ static int acpi_smbus_hc_add(struct acpi_device *device) status = acpi_evaluate_integer(device->handle, "_EC", NULL, &val); if (ACPI_FAILURE(status)) { - printk(KERN_ERR PREFIX "error obtaining _EC.\n"); + pr_err("error obtaining _EC.\n"); return -EIO; } diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index e10d38ac7cf2..0641bc20b097 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -3,6 +3,8 @@ * scan.c - support for transforming the ACPI namespace into individual objects */ +#define pr_fmt(fmt) "ACPI: " fmt + #include #include #include @@ -47,12 +49,6 @@ static DEFINE_MUTEX(acpi_hp_context_lock); */ static u64 spcr_uart_addr; -struct acpi_dep_data { - struct list_head node; - acpi_handle supplier; - acpi_handle consumer; -}; - void acpi_scan_lock_acquire(void) { mutex_lock(&acpi_scan_lock); @@ -612,11 +608,6 @@ struct acpi_device *acpi_bus_get_acpi_device(acpi_handle handle) return handle_to_device(handle, get_acpi_device); } -void acpi_bus_put_acpi_device(struct acpi_device *adev) -{ - acpi_dev_put(adev); -} - static struct acpi_device_bus_id *acpi_device_bus_id_match(const char *dev_id) { struct acpi_device_bus_id *acpi_device_bus_id; @@ -644,24 +635,29 @@ static int acpi_device_set_name(struct acpi_device *device, return 0; } -int acpi_device_add(struct acpi_device *device, - void (*release)(struct device *)) +static int acpi_tie_acpi_dev(struct acpi_device *adev) +{ + acpi_handle handle = adev->handle; + acpi_status status; + + if (!handle) + return 0; + + status = acpi_attach_data(handle, acpi_scan_drop_device, adev); + if (ACPI_FAILURE(status)) { + acpi_handle_err(handle, "Unable to attach device data\n"); + return -ENODEV; + } + + return 0; +} + +static int __acpi_device_add(struct acpi_device *device, + void (*release)(struct device *)) { struct acpi_device_bus_id *acpi_device_bus_id; int result; - if (device->handle) { - acpi_status status; - - status = acpi_attach_data(device->handle, acpi_scan_drop_device, - device); - if (ACPI_FAILURE(status)) { - acpi_handle_err(device->handle, - "Unable to attach device data\n"); - return -ENODEV; - } - } - /* * Linkage * ------- @@ -729,7 +725,7 @@ int acpi_device_add(struct acpi_device *device, result = acpi_device_setup_files(device); if (result) - printk(KERN_ERR PREFIX "Error creating sysfs interface for device %s\n", + pr_err("Error creating sysfs interface for device %s\n", dev_name(&device->dev)); return 0; @@ -750,6 +746,17 @@ err_unlock: return result; } +int acpi_device_add(struct acpi_device *adev, void (*release)(struct device *)) +{ + int ret; + + ret = acpi_tie_acpi_dev(adev); + if (ret) + return ret; + + return __acpi_device_add(adev, release); +} + /* -------------------------------------------------------------------------- Device Enumeration -------------------------------------------------------------------------- */ @@ -1320,8 +1327,7 @@ static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp, acpi_get_object_info(handle, &info); if (!info) { - pr_err(PREFIX "%s: Error reading device info\n", - __func__); + pr_err("%s: Error reading device info\n", __func__); return; } @@ -1405,7 +1411,7 @@ void acpi_free_pnp_ids(struct acpi_device_pnp *pnp) * * Return false if DMA is not supported. Otherwise, return true */ -bool acpi_dma_supported(struct acpi_device *adev) +bool acpi_dma_supported(const struct acpi_device *adev) { if (!adev) return false; @@ -1671,8 +1677,16 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle, device_initialize(&device->dev); dev_set_uevent_suppress(&device->dev, true); acpi_init_coherency(device); - /* Assume there are unmet deps to start with. */ - device->dep_unmet = 1; +} + +static void acpi_scan_dep_init(struct acpi_device *adev) +{ + struct acpi_dep_data *dep; + + list_for_each_entry(dep, &acpi_dep_list, node) { + if (dep->consumer == adev->handle) + adev->dep_unmet++; + } } void acpi_device_add_finalize(struct acpi_device *device) @@ -1688,9 +1702,10 @@ static void acpi_scan_init_status(struct acpi_device *adev) } static int acpi_add_single_object(struct acpi_device **child, - acpi_handle handle, int type) + acpi_handle handle, int type, bool dep_init) { struct acpi_device *device; + bool release_dep_lock = false; int result; device = kzalloc(sizeof(struct acpi_device), GFP_KERNEL); @@ -1703,13 +1718,32 @@ static int acpi_add_single_object(struct acpi_device **child, * acpi_bus_get_status() and use its quirk handling. Note that * this must be done before the get power-/wakeup_dev-flags calls. */ - if (type == ACPI_BUS_TYPE_DEVICE || type == ACPI_BUS_TYPE_PROCESSOR) + if (type == ACPI_BUS_TYPE_DEVICE || type == ACPI_BUS_TYPE_PROCESSOR) { + if (dep_init) { + mutex_lock(&acpi_dep_list_lock); + /* + * Hold the lock until the acpi_tie_acpi_dev() call + * below to prevent concurrent acpi_scan_clear_dep() + * from deleting a dependency list entry without + * updating dep_unmet for the device. + */ + release_dep_lock = true; + acpi_scan_dep_init(device); + } acpi_scan_init_status(device); + } acpi_bus_get_power_flags(device); acpi_bus_get_wakeup_device_flags(device); - result = acpi_device_add(device, acpi_device_release); + result = acpi_tie_acpi_dev(device); + + if (release_dep_lock) + mutex_unlock(&acpi_dep_list_lock); + + if (!result) + result = __acpi_device_add(device, acpi_device_release); + if (result) { acpi_device_release(&device->dev); return result; @@ -1886,22 +1920,6 @@ static u32 acpi_scan_check_dep(acpi_handle handle, bool check_dep) return count; } -static void acpi_scan_dep_init(struct acpi_device *adev) -{ - struct acpi_dep_data *dep; - - adev->dep_unmet = 0; - - mutex_lock(&acpi_dep_list_lock); - - list_for_each_entry(dep, &acpi_dep_list, node) { - if (dep->consumer == adev->handle) - adev->dep_unmet++; - } - - mutex_unlock(&acpi_dep_list_lock); -} - static bool acpi_bus_scan_second_pass; static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep, @@ -1949,19 +1967,15 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep, return AE_OK; } - acpi_add_single_object(&device, handle, type); - if (!device) - return AE_CTRL_DEPTH; - - acpi_scan_init_hotplug(device); /* * If check_dep is true at this point, the device has no dependencies, * or the creation of the device object would have been postponed above. */ - if (check_dep) - device->dep_unmet = 0; - else - acpi_scan_dep_init(device); + acpi_add_single_object(&device, handle, type, !check_dep); + if (!device) + return AE_CTRL_DEPTH; + + acpi_scan_init_hotplug(device); out: if (!*adev_p) @@ -2111,29 +2125,141 @@ static void acpi_bus_attach(struct acpi_device *device, bool first_pass) device->handler->hotplug.notify_online(device); } -void acpi_walk_dep_device_list(acpi_handle handle) +static int acpi_dev_get_first_consumer_dev_cb(struct acpi_dep_data *dep, void *data) +{ + struct acpi_device *adev; + + adev = acpi_bus_get_acpi_device(dep->consumer); + if (adev) { + *(struct acpi_device **)data = adev; + return 1; + } + /* Continue parsing if the device object is not present. */ + return 0; +} + +struct acpi_scan_clear_dep_work { + struct work_struct work; + struct acpi_device *adev; +}; + +static void acpi_scan_clear_dep_fn(struct work_struct *work) +{ + struct acpi_scan_clear_dep_work *cdw; + + cdw = container_of(work, struct acpi_scan_clear_dep_work, work); + + acpi_scan_lock_acquire(); + acpi_bus_attach(cdw->adev, true); + acpi_scan_lock_release(); + + acpi_dev_put(cdw->adev); + kfree(cdw); +} + +static bool acpi_scan_clear_dep_queue(struct acpi_device *adev) +{ + struct acpi_scan_clear_dep_work *cdw; + + if (adev->dep_unmet) + return false; + + cdw = kmalloc(sizeof(*cdw), GFP_KERNEL); + if (!cdw) + return false; + + cdw->adev = adev; + INIT_WORK(&cdw->work, acpi_scan_clear_dep_fn); + /* + * Since the work function may block on the lock until the entire + * initial enumeration of devices is complete, put it into the unbound + * workqueue. + */ + queue_work(system_unbound_wq, &cdw->work); + + return true; +} + +static int acpi_scan_clear_dep(struct acpi_dep_data *dep, void *data) +{ + struct acpi_device *adev = acpi_bus_get_acpi_device(dep->consumer); + + if (adev) { + adev->dep_unmet--; + if (!acpi_scan_clear_dep_queue(adev)) + acpi_dev_put(adev); + } + + list_del(&dep->node); + kfree(dep); + + return 0; +} + +/** + * acpi_walk_dep_device_list - Apply a callback to every entry in acpi_dep_list + * @handle: The ACPI handle of the supplier device + * @callback: Pointer to the callback function to apply + * @data: Pointer to some data to pass to the callback + * + * The return value of the callback determines this function's behaviour. If 0 + * is returned we continue to iterate over acpi_dep_list. If a positive value + * is returned then the loop is broken but this function returns 0. If a + * negative value is returned by the callback then the loop is broken and that + * value is returned as the final error. + */ +static int acpi_walk_dep_device_list(acpi_handle handle, + int (*callback)(struct acpi_dep_data *, void *), + void *data) { struct acpi_dep_data *dep, *tmp; - struct acpi_device *adev; + int ret = 0; mutex_lock(&acpi_dep_list_lock); list_for_each_entry_safe(dep, tmp, &acpi_dep_list, node) { if (dep->supplier == handle) { - acpi_bus_get_device(dep->consumer, &adev); - - if (adev) { - adev->dep_unmet--; - if (!adev->dep_unmet) - acpi_bus_attach(adev, true); - } - - list_del(&dep->node); - kfree(dep); + ret = callback(dep, data); + if (ret) + break; } } mutex_unlock(&acpi_dep_list_lock); + + return ret > 0 ? 0 : ret; } -EXPORT_SYMBOL_GPL(acpi_walk_dep_device_list); + +/** + * acpi_dev_clear_dependencies - Inform consumers that the device is now active + * @supplier: Pointer to the supplier &struct acpi_device + * + * Clear dependencies on the given device. + */ +void acpi_dev_clear_dependencies(struct acpi_device *supplier) +{ + acpi_walk_dep_device_list(supplier->handle, acpi_scan_clear_dep, NULL); +} +EXPORT_SYMBOL_GPL(acpi_dev_clear_dependencies); + +/** + * acpi_dev_get_first_consumer_dev - Return ACPI device dependent on @supplier + * @supplier: Pointer to the dependee device + * + * Returns the first &struct acpi_device which declares itself dependent on + * @supplier via the _DEP buffer, parsed from the acpi_dep_list. + * + * The caller is responsible for putting the reference to adev when it is no + * longer needed. + */ +struct acpi_device *acpi_dev_get_first_consumer_dev(struct acpi_device *supplier) +{ + struct acpi_device *adev = NULL; + + acpi_walk_dep_device_list(supplier->handle, + acpi_dev_get_first_consumer_dev_cb, &adev); + + return adev; +} +EXPORT_SYMBOL_GPL(acpi_dev_get_first_consumer_dev); /** * acpi_bus_scan - Add ACPI device node objects in a given namespace scope. @@ -2223,7 +2349,7 @@ int acpi_bus_register_early_device(int type) struct acpi_device *device = NULL; int result; - result = acpi_add_single_object(&device, NULL, type); + result = acpi_add_single_object(&device, NULL, type, false); if (result) return result; @@ -2243,7 +2369,7 @@ static int acpi_bus_scan_fixed(void) struct acpi_device *device = NULL; result = acpi_add_single_object(&device, NULL, - ACPI_BUS_TYPE_POWER_BUTTON); + ACPI_BUS_TYPE_POWER_BUTTON, false); if (result) return result; @@ -2259,7 +2385,7 @@ static int acpi_bus_scan_fixed(void) struct acpi_device *device = NULL; result = acpi_add_single_object(&device, NULL, - ACPI_BUS_TYPE_SLEEP_BUTTON); + ACPI_BUS_TYPE_SLEEP_BUTTON, false); if (result) return result; @@ -2278,7 +2404,7 @@ static void __init acpi_get_spcr_uart_addr(void) status = acpi_get_table(ACPI_SIG_SPCR, 0, (struct acpi_table_header **)&spcr_ptr); if (ACPI_FAILURE(status)) { - pr_warn(PREFIX "STAO table present, but SPCR is missing\n"); + pr_warn("STAO table present, but SPCR is missing\n"); return; } @@ -2319,7 +2445,7 @@ int __init acpi_scan_init(void) (struct acpi_table_header **)&stao_ptr); if (ACPI_SUCCESS(status)) { if (stao_ptr->header.length > sizeof(struct acpi_table_stao)) - pr_info(PREFIX "STAO Name List not yet supported.\n"); + pr_info("STAO Name List not yet supported.\n"); if (stao_ptr->ignore_uart) acpi_get_spcr_uart_addr(); @@ -2360,7 +2486,7 @@ int __init acpi_scan_init(void) } } - acpi_turn_off_unused_power_resources(true); + acpi_turn_off_unused_power_resources(); acpi_scan_initialized = true; @@ -2408,46 +2534,28 @@ int __init __acpi_probe_device_table(struct acpi_probe_entry *ap_head, int nr) return count; } -struct acpi_table_events_work { - struct work_struct work; - void *table; - u32 event; -}; - static void acpi_table_events_fn(struct work_struct *work) { - struct acpi_table_events_work *tew; + acpi_scan_lock_acquire(); + acpi_bus_scan(ACPI_ROOT_OBJECT); + acpi_scan_lock_release(); - tew = container_of(work, struct acpi_table_events_work, work); - - if (tew->event == ACPI_TABLE_EVENT_LOAD) { - acpi_scan_lock_acquire(); - acpi_bus_scan(ACPI_ROOT_OBJECT); - acpi_scan_lock_release(); - } - - kfree(tew); + kfree(work); } -void acpi_scan_table_handler(u32 event, void *table, void *context) +void acpi_scan_table_notify(void) { - struct acpi_table_events_work *tew; + struct work_struct *work; if (!acpi_scan_initialized) return; - if (event != ACPI_TABLE_EVENT_LOAD) + work = kmalloc(sizeof(*work), GFP_KERNEL); + if (!work) return; - tew = kmalloc(sizeof(*tew), GFP_KERNEL); - if (!tew) - return; - - INIT_WORK(&tew->work, acpi_table_events_fn); - tew->table = table; - tew->event = event; - - schedule_work(&tew->work); + INIT_WORK(work, acpi_table_events_fn); + schedule_work(work); } int acpi_reconfig_notifier_register(struct notifier_block *nb) diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 3bb2adef8490..3023224515ab 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -8,6 +8,8 @@ * Copyright (c) 2003 Open Source Development Lab */ +#define pr_fmt(fmt) "ACPI: PM: " fmt + #include #include #include @@ -41,7 +43,7 @@ static void acpi_sleep_tts_switch(u32 acpi_state) * OS can't evaluate the _TTS object correctly. Some warning * message will be printed. But it won't break anything. */ - printk(KERN_NOTICE "Failure in evaluating _TTS object\n"); + pr_notice("Failure in evaluating _TTS object\n"); } } @@ -73,8 +75,7 @@ static int acpi_sleep_prepare(u32 acpi_state) } ACPI_FLUSH_CPU_CACHE(); #endif - printk(KERN_INFO PREFIX "Preparing to enter system sleep state S%d\n", - acpi_state); + pr_info("Preparing to enter system sleep state S%d\n", acpi_state); acpi_enable_wakeup_devices(acpi_state); acpi_enter_sleep_state_prep(acpi_state); return 0; @@ -406,7 +407,7 @@ static int acpi_pm_freeze(void) } /** - * acpi_pre_suspend - Enable wakeup devices, "freeze" EC and save NVS. + * acpi_pm_pre_suspend - Enable wakeup devices, "freeze" EC and save NVS. */ static int acpi_pm_pre_suspend(void) { @@ -459,8 +460,7 @@ static void acpi_pm_finish(void) if (acpi_state == ACPI_STATE_S0) return; - printk(KERN_INFO PREFIX "Waking up from system sleep state S%d\n", - acpi_state); + pr_info("Waking up from system sleep state S%d\n", acpi_state); acpi_disable_wakeup_devices(acpi_state); acpi_leave_sleep_state(acpi_state); @@ -504,7 +504,7 @@ static void acpi_pm_start(u32 acpi_state) */ static void acpi_pm_end(void) { - acpi_turn_off_unused_power_resources(false); + acpi_turn_off_unused_power_resources(); acpi_scan_lock_release(); /* * This is necessary in case acpi_pm_finish() is not called during a @@ -581,7 +581,7 @@ static int acpi_suspend_enter(suspend_state_t pm_state) error = acpi_suspend_lowlevel(); if (error) return error; - pr_info(PREFIX "Low-level resume complete\n"); + pr_info("Low-level resume complete\n"); pm_set_resume_via_firmware(); break; } @@ -921,7 +921,7 @@ static void acpi_hibernation_leave(void) acpi_leave_sleep_state_prep(ACPI_STATE_S4); /* Check the hardware signature */ if (facs && s4_hardware_signature != facs->hardware_signature) - pr_crit("ACPI: Hardware changed while hibernated, success doubtful!\n"); + pr_crit("Hardware changed while hibernated, success doubtful!\n"); /* Restore the NVS memory area */ suspend_nvs_restore(); /* Allow EC transactions to happen. */ @@ -1027,7 +1027,7 @@ static void acpi_power_off_prepare(void) static void acpi_power_off(void) { /* acpi_sleep_prepare(ACPI_STATE_S5) should have already been called */ - printk(KERN_DEBUG "%s called\n", __func__); + pr_debug("%s called\n", __func__); local_irq_disable(); acpi_enter_sleep_state(ACPI_STATE_S5); } @@ -1059,7 +1059,7 @@ int __init acpi_sleep_init(void) if (sleep_states[i]) pos += sprintf(pos, " S%d", i); } - pr_info(PREFIX "(supports%s)\n", supported); + pr_info("(supports%s)\n", supported); /* * Register the tts_notifier to reboot notifier list so that the _TTS diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c index d25927195d6d..00c0ebaab29f 100644 --- a/drivers/acpi/sysfs.c +++ b/drivers/acpi/sysfs.c @@ -5,10 +5,11 @@ #define pr_fmt(fmt) "ACPI: " fmt +#include +#include #include #include #include -#include #include "internal.h" @@ -254,16 +255,12 @@ static int param_get_trace_state(char *buffer, const struct kernel_param *kp) { if (!(acpi_gbl_trace_flags & ACPI_TRACE_ENABLED)) return sprintf(buffer, "disable\n"); - else { - if (acpi_gbl_trace_method_name) { - if (acpi_gbl_trace_flags & ACPI_TRACE_ONESHOT) - return sprintf(buffer, "method-once\n"); - else - return sprintf(buffer, "method\n"); - } else - return sprintf(buffer, "enable\n"); - } - return 0; + if (!acpi_gbl_trace_method_name) + return sprintf(buffer, "enable\n"); + if (acpi_gbl_trace_flags & ACPI_TRACE_ONESHOT) + return sprintf(buffer, "method-once\n"); + else + return sprintf(buffer, "method\n"); } module_param_call(trace_state, param_set_trace_state, param_get_trace_state, @@ -359,8 +356,7 @@ static int acpi_table_attr_init(struct kobject *tables_obj, } table_attr->instance++; if (table_attr->instance > ACPI_MAX_TABLE_INSTANCES) { - pr_warn("%4.4s: too many table instances\n", - table_attr->name); + pr_warn("%4.4s: too many table instances\n", table_attr->name); return -ERANGE; } @@ -388,8 +384,7 @@ acpi_status acpi_sysfs_table_handler(u32 event, void *table, void *context) switch (event) { case ACPI_TABLE_EVENT_INSTALL: - table_attr = - kzalloc(sizeof(struct acpi_table_attr), GFP_KERNEL); + table_attr = kzalloc(sizeof(*table_attr), GFP_KERNEL); if (!table_attr) return AE_NO_MEMORY; @@ -420,7 +415,7 @@ static ssize_t acpi_data_show(struct file *filp, struct kobject *kobj, loff_t offset, size_t count) { struct acpi_data_attr *data_attr; - void __iomem *base; + void *base; ssize_t rc; data_attr = container_of(bin_attr, struct acpi_data_attr, attr); @@ -582,8 +577,6 @@ static void delete_gpe_attr_array(void) kfree(counter_attrs); } kfree(all_attrs); - - return; } static void gpe_count(u32 gpe_number) @@ -598,8 +591,6 @@ static void gpe_count(u32 gpe_number) else all_counters[num_gpes + ACPI_NUM_FIXED_EVENTS + COUNT_ERROR].count++; - - return; } static void fixed_event_count(u32 event_number) @@ -612,8 +603,6 @@ static void fixed_event_count(u32 event_number) else all_counters[num_gpes + ACPI_NUM_FIXED_EVENTS + COUNT_ERROR].count++; - - return; } static void acpi_global_event_handler(u32 event_type, acpi_handle device, @@ -737,8 +726,7 @@ static ssize_t counter_set(struct kobject *kobj, goto end; if (!(status & ACPI_EVENT_FLAG_HAS_HANDLER)) { - printk(KERN_WARNING PREFIX - "Can not change Invalid GPE/Fixed Event status\n"); + pr_warn("Can not change Invalid GPE/Fixed Event status\n"); return -EINVAL; } @@ -796,6 +784,7 @@ end: * the GPE flooding for GPE 00, they need to specify the following boot * parameter: * acpi_mask_gpe=0x00 + * Note, the parameter can be a list (see bitmap_parselist() for the details). * The masking status can be modified by the following runtime controlling * interface: * echo unmask > /sys/firmware/acpi/interrupts/gpe00 @@ -805,11 +794,16 @@ static DECLARE_BITMAP(acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX) __initdata; static int __init acpi_gpe_set_masked_gpes(char *val) { + int ret; u8 gpe; - if (kstrtou8(val, 0, &gpe)) - return -EINVAL; - set_bit(gpe, acpi_masked_gpes_map); + ret = kstrtou8(val, 0, &gpe); + if (ret) { + ret = bitmap_parselist(val, acpi_masked_gpes_map, ACPI_MASKABLE_GPE_MAX); + if (ret) + return ret; + } else + set_bit(gpe, acpi_masked_gpes_map); return 1; } @@ -841,13 +835,11 @@ void acpi_irq_stats_init(void) num_gpes = acpi_current_gpe_count; num_counters = num_gpes + ACPI_NUM_FIXED_EVENTS + NUM_COUNTERS_EXTRA; - all_attrs = kcalloc(num_counters + 1, sizeof(struct attribute *), - GFP_KERNEL); + all_attrs = kcalloc(num_counters + 1, sizeof(*all_attrs), GFP_KERNEL); if (all_attrs == NULL) return; - all_counters = kcalloc(num_counters, sizeof(struct event_counter), - GFP_KERNEL); + all_counters = kcalloc(num_counters, sizeof(*all_counters), GFP_KERNEL); if (all_counters == NULL) goto fail; @@ -855,8 +847,7 @@ void acpi_irq_stats_init(void) if (ACPI_FAILURE(status)) goto fail; - counter_attrs = kcalloc(num_counters, sizeof(struct kobj_attribute), - GFP_KERNEL); + counter_attrs = kcalloc(num_counters, sizeof(*counter_attrs), GFP_KERNEL); if (counter_attrs == NULL) goto fail; @@ -906,7 +897,6 @@ void acpi_irq_stats_init(void) fail: delete_gpe_attr_array(); - return; } static void __exit interrupt_stats_exit(void) @@ -914,31 +904,24 @@ static void __exit interrupt_stats_exit(void) sysfs_remove_group(acpi_kobj, &interrupt_stats_attr_group); delete_gpe_attr_array(); - - return; } -static ssize_t -acpi_show_profile(struct kobject *kobj, struct kobj_attribute *attr, - char *buf) +static ssize_t pm_profile_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sprintf(buf, "%d\n", acpi_gbl_FADT.preferred_profile); } -static const struct kobj_attribute pm_profile_attr = - __ATTR(pm_profile, S_IRUGO, acpi_show_profile, NULL); +static const struct kobj_attribute pm_profile_attr = __ATTR_RO(pm_profile); -static ssize_t hotplug_enabled_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) +static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct acpi_hotplug_profile *hotplug = to_acpi_hotplug_profile(kobj); return sprintf(buf, "%d\n", hotplug->enabled); } -static ssize_t hotplug_enabled_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t size) +static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t size) { struct acpi_hotplug_profile *hotplug = to_acpi_hotplug_profile(kobj); unsigned int val; @@ -950,9 +933,7 @@ static ssize_t hotplug_enabled_store(struct kobject *kobj, return size; } -static struct kobj_attribute hotplug_enabled_attr = - __ATTR(enabled, S_IRUGO | S_IWUSR, hotplug_enabled_show, - hotplug_enabled_store); +static struct kobj_attribute hotplug_enabled_attr = __ATTR_RW(enabled); static struct attribute *hotplug_profile_attrs[] = { &hotplug_enabled_attr.attr, @@ -983,7 +964,7 @@ void acpi_sysfs_add_hotplug_profile(struct acpi_hotplug_profile *hotplug, return; err_out: - pr_err(PREFIX "Unable to add hotplug profile '%s'\n", name); + pr_err("Unable to add hotplug profile '%s'\n", name); } static ssize_t force_remove_show(struct kobject *kobj, @@ -1010,9 +991,7 @@ static ssize_t force_remove_store(struct kobject *kobj, return size; } -static const struct kobj_attribute force_remove_attr = - __ATTR(force_remove, S_IRUGO | S_IWUSR, force_remove_show, - force_remove_store); +static const struct kobj_attribute force_remove_attr = __ATTR_RW(force_remove); int __init acpi_sysfs_init(void) { diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index 9d581045acff..a37a1532a575 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -39,6 +39,7 @@ static int acpi_apic_instance __initdata; enum acpi_subtable_type { ACPI_SUBTABLE_COMMON, ACPI_SUBTABLE_HMAT, + ACPI_SUBTABLE_PRMT, }; struct acpi_subtable_entry { @@ -222,6 +223,8 @@ acpi_get_entry_type(struct acpi_subtable_entry *entry) return entry->hdr->common.type; case ACPI_SUBTABLE_HMAT: return entry->hdr->hmat.type; + case ACPI_SUBTABLE_PRMT: + return 0; } return 0; } @@ -234,6 +237,8 @@ acpi_get_entry_length(struct acpi_subtable_entry *entry) return entry->hdr->common.length; case ACPI_SUBTABLE_HMAT: return entry->hdr->hmat.length; + case ACPI_SUBTABLE_PRMT: + return entry->hdr->prmt.length; } return 0; } @@ -246,6 +251,8 @@ acpi_get_subtable_header_length(struct acpi_subtable_entry *entry) return sizeof(entry->hdr->common); case ACPI_SUBTABLE_HMAT: return sizeof(entry->hdr->hmat); + case ACPI_SUBTABLE_PRMT: + return sizeof(entry->hdr->prmt); } return 0; } @@ -255,6 +262,8 @@ acpi_get_subtable_type(char *id) { if (strncmp(id, ACPI_SIG_HMAT, 4) == 0) return ACPI_SUBTABLE_HMAT; + if (strncmp(id, ACPI_SIG_PRMT, 4) == 0) + return ACPI_SUBTABLE_PRMT; return ACPI_SUBTABLE_COMMON; } diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index 3b54b8fd7396..e7ddd281afff 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -277,6 +277,20 @@ acpi_evaluate_integer(acpi_handle handle, EXPORT_SYMBOL(acpi_evaluate_integer); +int acpi_get_local_address(acpi_handle handle, u32 *addr) +{ + unsigned long long adr; + acpi_status status; + + status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &adr); + if (ACPI_FAILURE(status)) + return -ENODATA; + + *addr = (u32)adr; + return 0; +} +EXPORT_SYMBOL(acpi_get_local_address); + acpi_status acpi_evaluate_reference(acpi_handle handle, acpi_string pathname, diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c index 2b69536cdccb..816bf2c34b7a 100644 --- a/drivers/acpi/x86/s2idle.c +++ b/drivers/acpi/x86/s2idle.c @@ -32,6 +32,9 @@ static const struct acpi_device_id lps0_device_ids[] = { {"", }, }; +/* Microsoft platform agnostic UUID */ +#define ACPI_LPS0_DSM_UUID_MICROSOFT "11e00d56-ce64-47ce-837b-1f898f9aa461" + #define ACPI_LPS0_DSM_UUID "c4eb40a0-6cd2-11e2-bcfd-0800200c9a66" #define ACPI_LPS0_GET_DEVICE_CONSTRAINTS 1 @@ -39,15 +42,22 @@ static const struct acpi_device_id lps0_device_ids[] = { #define ACPI_LPS0_SCREEN_ON 4 #define ACPI_LPS0_ENTRY 5 #define ACPI_LPS0_EXIT 6 +#define ACPI_LPS0_MS_ENTRY 7 +#define ACPI_LPS0_MS_EXIT 8 /* AMD */ #define ACPI_LPS0_DSM_UUID_AMD "e3f32452-febc-43ce-9039-932122d37721" +#define ACPI_LPS0_ENTRY_AMD 2 +#define ACPI_LPS0_EXIT_AMD 3 #define ACPI_LPS0_SCREEN_OFF_AMD 4 #define ACPI_LPS0_SCREEN_ON_AMD 5 static acpi_handle lps0_device_handle; static guid_t lps0_dsm_guid; -static char lps0_dsm_func_mask; +static int lps0_dsm_func_mask; + +static guid_t lps0_dsm_guid_microsoft; +static int lps0_dsm_func_mask_microsoft; /* Device constraint entry structure */ struct lpi_device_info { @@ -68,15 +78,7 @@ struct lpi_constraints { int min_dstate; }; -/* AMD */ -/* Device constraint entry structure */ -struct lpi_device_info_amd { - int revision; - int count; - union acpi_object *package; -}; - -/* Constraint package structure */ +/* AMD Constraint package structure */ struct lpi_device_constraint_amd { char *name; int enabled; @@ -94,15 +96,15 @@ static void lpi_device_get_constraints_amd(void) int i, j, k; out_obj = acpi_evaluate_dsm_typed(lps0_device_handle, &lps0_dsm_guid, - 1, ACPI_LPS0_GET_DEVICE_CONSTRAINTS, + rev_id, ACPI_LPS0_GET_DEVICE_CONSTRAINTS, NULL, ACPI_TYPE_PACKAGE); - if (!out_obj) - return; - acpi_handle_debug(lps0_device_handle, "_DSM function 1 eval %s\n", out_obj ? "successful" : "failed"); + if (!out_obj) + return; + for (i = 0; i < out_obj->package.count; i++) { union acpi_object *package = &out_obj->package.elements[i]; @@ -315,14 +317,15 @@ static void lpi_check_constraints(void) } } -static void acpi_sleep_run_lps0_dsm(unsigned int func) +static void acpi_sleep_run_lps0_dsm(unsigned int func, unsigned int func_mask, guid_t dsm_guid) { union acpi_object *out_obj; - if (!(lps0_dsm_func_mask & (1 << func))) + if (!(func_mask & (1 << func))) return; - out_obj = acpi_evaluate_dsm(lps0_device_handle, &lps0_dsm_guid, rev_id, func, NULL); + out_obj = acpi_evaluate_dsm(lps0_device_handle, &dsm_guid, + rev_id, func, NULL); ACPI_FREE(out_obj); acpi_handle_debug(lps0_device_handle, "_DSM function %u evaluation %s\n", @@ -334,11 +337,33 @@ static bool acpi_s2idle_vendor_amd(void) return boot_cpu_data.x86_vendor == X86_VENDOR_AMD; } +static int validate_dsm(acpi_handle handle, const char *uuid, int rev, guid_t *dsm_guid) +{ + union acpi_object *obj; + int ret = -EINVAL; + + guid_parse(uuid, dsm_guid); + obj = acpi_evaluate_dsm(handle, dsm_guid, rev, 0, NULL); + + /* Check if the _DSM is present and as expected. */ + if (!obj || obj->type != ACPI_TYPE_BUFFER || obj->buffer.length == 0 || + obj->buffer.length > sizeof(u32)) { + acpi_handle_debug(handle, + "_DSM UUID %s rev %d function 0 evaluation failed\n", uuid, rev); + goto out; + } + + ret = *(int *)obj->buffer.pointer; + acpi_handle_debug(handle, "_DSM UUID %s rev %d function mask: 0x%x\n", uuid, rev, ret); + +out: + ACPI_FREE(obj); + return ret; +} + static int lps0_device_attach(struct acpi_device *adev, const struct acpi_device_id *not_used) { - union acpi_object *out_obj; - if (lps0_device_handle) return 0; @@ -346,28 +371,36 @@ static int lps0_device_attach(struct acpi_device *adev, return 0; if (acpi_s2idle_vendor_amd()) { - guid_parse(ACPI_LPS0_DSM_UUID_AMD, &lps0_dsm_guid); - out_obj = acpi_evaluate_dsm(adev->handle, &lps0_dsm_guid, 0, 0, NULL); + /* AMD0004, AMDI0005: + * - Should use rev_id 0x0 + * - function mask > 0x3: Should use AMD method, but has off by one bug + * - function mask = 0x3: Should use Microsoft method + * AMDI0006: + * - should use rev_id 0x0 + * - function mask = 0x3: Should use Microsoft method + */ + const char *hid = acpi_device_hid(adev); rev_id = 0; + lps0_dsm_func_mask = validate_dsm(adev->handle, + ACPI_LPS0_DSM_UUID_AMD, rev_id, &lps0_dsm_guid); + lps0_dsm_func_mask_microsoft = validate_dsm(adev->handle, + ACPI_LPS0_DSM_UUID_MICROSOFT, rev_id, + &lps0_dsm_guid_microsoft); + if (lps0_dsm_func_mask > 0x3 && (!strcmp(hid, "AMD0004") || + !strcmp(hid, "AMDI0005"))) { + lps0_dsm_func_mask = (lps0_dsm_func_mask << 1) | 0x1; + acpi_handle_debug(adev->handle, "_DSM UUID %s: Adjusted function mask: 0x%x\n", + ACPI_LPS0_DSM_UUID_AMD, lps0_dsm_func_mask); + } } else { - guid_parse(ACPI_LPS0_DSM_UUID, &lps0_dsm_guid); - out_obj = acpi_evaluate_dsm(adev->handle, &lps0_dsm_guid, 1, 0, NULL); rev_id = 1; + lps0_dsm_func_mask = validate_dsm(adev->handle, + ACPI_LPS0_DSM_UUID, rev_id, &lps0_dsm_guid); + lps0_dsm_func_mask_microsoft = -EINVAL; } - /* Check if the _DSM is present and as expected. */ - if (!out_obj || out_obj->type != ACPI_TYPE_BUFFER) { - acpi_handle_debug(adev->handle, - "_DSM function 0 evaluation failed\n"); - return 0; - } - - lps0_dsm_func_mask = *(char *)out_obj->buffer.pointer; - - ACPI_FREE(out_obj); - - acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n", - lps0_dsm_func_mask); + if (lps0_dsm_func_mask < 0 && lps0_dsm_func_mask_microsoft < 0) + return 0; //function evaluation failed lps0_device_handle = adev->handle; @@ -406,11 +439,23 @@ int acpi_s2idle_prepare_late(void) if (pm_debug_messages_on) lpi_check_constraints(); - if (acpi_s2idle_vendor_amd()) { - acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF_AMD); + if (lps0_dsm_func_mask_microsoft > 0) { + acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF, + lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft); + acpi_sleep_run_lps0_dsm(ACPI_LPS0_MS_EXIT, + lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft); + acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY, + lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft); + } else if (acpi_s2idle_vendor_amd()) { + acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF_AMD, + lps0_dsm_func_mask, lps0_dsm_guid); + acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY_AMD, + lps0_dsm_func_mask, lps0_dsm_guid); } else { - acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF); - acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY); + acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF, + lps0_dsm_func_mask, lps0_dsm_guid); + acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY, + lps0_dsm_func_mask, lps0_dsm_guid); } return 0; @@ -421,11 +466,23 @@ void acpi_s2idle_restore_early(void) if (!lps0_device_handle || sleep_no_lps0) return; - if (acpi_s2idle_vendor_amd()) { - acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON_AMD); + if (lps0_dsm_func_mask_microsoft > 0) { + acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT, + lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft); + acpi_sleep_run_lps0_dsm(ACPI_LPS0_MS_ENTRY, + lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft); + acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON, + lps0_dsm_func_mask_microsoft, lps0_dsm_guid_microsoft); + } else if (acpi_s2idle_vendor_amd()) { + acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT_AMD, + lps0_dsm_func_mask, lps0_dsm_guid); + acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON_AMD, + lps0_dsm_func_mask, lps0_dsm_guid); } else { - acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT); - acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON); + acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT, + lps0_dsm_func_mask, lps0_dsm_guid); + acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON, + lps0_dsm_func_mask, lps0_dsm_guid); } } diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index bdc1ba00aee9..f22f23933063 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -135,3 +135,28 @@ bool acpi_device_always_present(struct acpi_device *adev) return ret; } + +/* + * AMD systems from Renoir and Lucienne *require* that the NVME controller + * is put into D3 over a Modern Standby / suspend-to-idle cycle. + * + * This is "typically" accomplished using the `StorageD3Enable` + * property in the _DSD that is checked via the `acpi_storage_d3` function + * but this property was introduced after many of these systems launched + * and most OEM systems don't have it in their BIOS. + * + * The Microsoft documentation for StorageD3Enable mentioned that Windows has + * a hardcoded allowlist for D3 support, which was used for these platforms. + * + * This allows quirking on Linux in a similar fashion. + */ +static const struct x86_cpu_id storage_d3_cpu_ids[] = { + X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 96, NULL), /* Renoir */ + X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 104, NULL), /* Lucienne */ + {} +}; + +bool force_storage_d3(void) +{ + return x86_match_cpu(storage_d3_cpu_ids); +} diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c index 933e3ff2ee8d..bc8e8d9f176b 100644 --- a/drivers/atm/iphase.c +++ b/drivers/atm/iphase.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include #include @@ -996,10 +997,12 @@ static void xdump( u_char* cp, int length, char* prefix ) } pBuf += sprintf( pBuf, " " ); for(col = 0;count + col < length && col < 16; col++){ - if (isprint((int)cp[count + col])) - pBuf += sprintf( pBuf, "%c", cp[count + col] ); - else - pBuf += sprintf( pBuf, "." ); + u_char c = cp[count + col]; + + if (isascii(c) && isprint(c)) + pBuf += sprintf(pBuf, "%c", c); + else + pBuf += sprintf(pBuf, "."); } printk("%s\n", prntBuf); count += col; @@ -3279,7 +3282,7 @@ static void __exit ia_module_exit(void) { pci_unregister_driver(&ia_driver); - del_timer(&ia_timer); + del_timer_sync(&ia_timer); } module_init(ia_module_init); diff --git a/drivers/atm/iphase.h b/drivers/atm/iphase.h index 2beacf2fc1ec..2f5f8875cbd1 100644 --- a/drivers/atm/iphase.h +++ b/drivers/atm/iphase.h @@ -124,7 +124,6 @@ #define IF_RXPKT(A) #endif /* CONFIG_ATM_IA_DEBUG */ -#define isprint(a) ((a >=' ')&&(a <= '~')) #define ATM_DESC(skb) (skb->protocol) #define IA_SKB_STATE(skb) (skb->protocol) #define IA_DLED 1 diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c index 5c7e4df159b9..bc5a6ab6fa4b 100644 --- a/drivers/atm/nicstar.c +++ b/drivers/atm/nicstar.c @@ -299,7 +299,7 @@ static void __exit nicstar_cleanup(void) { XPRINTK("nicstar: nicstar_cleanup() called.\n"); - del_timer(&ns_timer); + del_timer_sync(&ns_timer); pci_unregister_driver(&nicstar_driver); @@ -527,6 +527,15 @@ static int ns_init_card(int i, struct pci_dev *pcidev) /* Set the VPI/VCI MSb mask to zero so we can receive OAM cells */ writel(0x00000000, card->membase + VPM); + card->intcnt = 0; + if (request_irq + (pcidev->irq, &ns_irq_handler, IRQF_SHARED, "nicstar", card) != 0) { + pr_err("nicstar%d: can't allocate IRQ %d.\n", i, pcidev->irq); + error = 9; + ns_init_card_error(card, error); + return error; + } + /* Initialize TSQ */ card->tsq.org = dma_alloc_coherent(&card->pcidev->dev, NS_TSQSIZE + NS_TSQ_ALIGNMENT, @@ -753,15 +762,6 @@ static int ns_init_card(int i, struct pci_dev *pcidev) card->efbie = 1; - card->intcnt = 0; - if (request_irq - (pcidev->irq, &ns_irq_handler, IRQF_SHARED, "nicstar", card) != 0) { - printk("nicstar%d: can't allocate IRQ %d.\n", i, pcidev->irq); - error = 9; - ns_init_card_error(card, error); - return error; - } - /* Register device */ card->atmdev = atm_dev_register("nicstar", &card->pcidev->dev, &atm_ops, -1, NULL); @@ -839,10 +839,12 @@ static void ns_init_card_error(ns_dev *card, int error) dev_kfree_skb_any(hb); } if (error >= 12) { - kfree(card->rsq.org); + dma_free_coherent(&card->pcidev->dev, NS_RSQSIZE + NS_RSQ_ALIGNMENT, + card->rsq.org, card->rsq.dma); } if (error >= 11) { - kfree(card->tsq.org); + dma_free_coherent(&card->pcidev->dev, NS_TSQSIZE + NS_TSQ_ALIGNMENT, + card->tsq.org, card->tsq.dma); } if (error >= 10) { free_irq(card->pcidev->irq, card); diff --git a/drivers/atm/zeprom.h b/drivers/atm/zeprom.h index 88e01f808a86..8e8819a3840d 100644 --- a/drivers/atm/zeprom.h +++ b/drivers/atm/zeprom.h @@ -12,7 +12,7 @@ #define ZEPROM_V1_REG PCI_VENDOR_ID /* PCI register */ #define ZEPROM_V2_REG 0x40 -/* Bits in contol register */ +/* Bits in control register */ #define ZEPROM_SK 0x80000000 /* strobe (probably on raising edge) */ #define ZEPROM_CS 0x40000000 /* Chip Select */ diff --git a/drivers/base/core.c b/drivers/base/core.c index 54ba506e5a89..2a61003ea2c1 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4727,6 +4727,13 @@ void device_set_of_node_from_dev(struct device *dev, const struct device *dev2) } EXPORT_SYMBOL_GPL(device_set_of_node_from_dev); +void device_set_node(struct device *dev, struct fwnode_handle *fwnode) +{ + dev->fwnode = fwnode; + dev->of_node = to_of_node(fwnode); +} +EXPORT_SYMBOL_GPL(device_set_node); + int device_match_name(struct device *dev, const void *name) { return sysfs_streq(dev_name(dev), name); diff --git a/drivers/base/node.c b/drivers/base/node.c index 2c36f61d30bc..9db297431b97 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -482,6 +482,7 @@ static DEVICE_ATTR(meminfo, 0444, node_read_meminfo, NULL); static ssize_t node_read_numastat(struct device *dev, struct device_attribute *attr, char *buf) { + fold_vm_numa_events(); return sysfs_emit(buf, "numa_hit %lu\n" "numa_miss %lu\n" @@ -489,12 +490,12 @@ static ssize_t node_read_numastat(struct device *dev, "interleave_hit %lu\n" "local_node %lu\n" "other_node %lu\n", - sum_zone_numa_state(dev->id, NUMA_HIT), - sum_zone_numa_state(dev->id, NUMA_MISS), - sum_zone_numa_state(dev->id, NUMA_FOREIGN), - sum_zone_numa_state(dev->id, NUMA_INTERLEAVE_HIT), - sum_zone_numa_state(dev->id, NUMA_LOCAL), - sum_zone_numa_state(dev->id, NUMA_OTHER)); + sum_zone_numa_event_state(dev->id, NUMA_HIT), + sum_zone_numa_event_state(dev->id, NUMA_MISS), + sum_zone_numa_event_state(dev->id, NUMA_FOREIGN), + sum_zone_numa_event_state(dev->id, NUMA_INTERLEAVE_HIT), + sum_zone_numa_event_state(dev->id, NUMA_LOCAL), + sum_zone_numa_event_state(dev->id, NUMA_OTHER)); } static DEVICE_ATTR(numastat, 0444, node_read_numastat, NULL); @@ -512,10 +513,11 @@ static ssize_t node_read_vmstat(struct device *dev, sum_zone_node_page_state(nid, i)); #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) + fold_vm_numa_events(); + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) len += sysfs_emit_at(buf, len, "%s %lu\n", numa_stat_name(i), - sum_zone_numa_state(nid, i)); + sum_zone_numa_event_state(nid, i)); #endif for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index b6a782c31613..ab0b740cc0f1 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -379,6 +379,44 @@ err: return ret; } +static int genpd_set_performance_state(struct device *dev, unsigned int state) +{ + struct generic_pm_domain *genpd = dev_to_genpd(dev); + struct generic_pm_domain_data *gpd_data = dev_gpd_data(dev); + unsigned int prev_state; + int ret; + + prev_state = gpd_data->performance_state; + if (prev_state == state) + return 0; + + gpd_data->performance_state = state; + state = _genpd_reeval_performance_state(genpd, state); + + ret = _genpd_set_performance_state(genpd, state, 0); + if (ret) + gpd_data->performance_state = prev_state; + + return ret; +} + +static int genpd_drop_performance_state(struct device *dev) +{ + unsigned int prev_state = dev_gpd_data(dev)->performance_state; + + if (!genpd_set_performance_state(dev, 0)) + return prev_state; + + return 0; +} + +static void genpd_restore_performance_state(struct device *dev, + unsigned int state) +{ + if (state) + genpd_set_performance_state(dev, state); +} + /** * dev_pm_genpd_set_performance_state- Set performance state of device's power * domain. @@ -397,8 +435,6 @@ err: int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state) { struct generic_pm_domain *genpd; - struct generic_pm_domain_data *gpd_data; - unsigned int prev; int ret; genpd = dev_to_genpd_safe(dev); @@ -410,16 +446,7 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state) return -EINVAL; genpd_lock(genpd); - - gpd_data = to_gpd_data(dev->power.subsys_data->domain_data); - prev = gpd_data->performance_state; - gpd_data->performance_state = state; - - state = _genpd_reeval_performance_state(genpd, state); - ret = _genpd_set_performance_state(genpd, state, 0); - if (ret) - gpd_data->performance_state = prev; - + ret = genpd_set_performance_state(dev, state); genpd_unlock(genpd); return ret; @@ -572,6 +599,7 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd) * RPM status of the releated device is in an intermediate state, not yet turned * into RPM_SUSPENDED. This means genpd_power_off() must allow one device to not * be RPM_SUSPENDED, while it tries to power off the PM domain. + * @depth: nesting count for lockdep. * * If all of the @genpd's devices have been suspended and all of its subdomains * have been powered down, remove power from @genpd. @@ -832,7 +860,8 @@ static int genpd_runtime_suspend(struct device *dev) { struct generic_pm_domain *genpd; bool (*suspend_ok)(struct device *__dev); - struct gpd_timing_data *td = &dev_gpd_data(dev)->td; + struct generic_pm_domain_data *gpd_data = dev_gpd_data(dev); + struct gpd_timing_data *td = &gpd_data->td; bool runtime_pm = pm_runtime_enabled(dev); ktime_t time_start; s64 elapsed_ns; @@ -889,6 +918,7 @@ static int genpd_runtime_suspend(struct device *dev) return 0; genpd_lock(genpd); + gpd_data->rpm_pstate = genpd_drop_performance_state(dev); genpd_power_off(genpd, true, 0); genpd_unlock(genpd); @@ -906,7 +936,8 @@ static int genpd_runtime_suspend(struct device *dev) static int genpd_runtime_resume(struct device *dev) { struct generic_pm_domain *genpd; - struct gpd_timing_data *td = &dev_gpd_data(dev)->td; + struct generic_pm_domain_data *gpd_data = dev_gpd_data(dev); + struct gpd_timing_data *td = &gpd_data->td; bool runtime_pm = pm_runtime_enabled(dev); ktime_t time_start; s64 elapsed_ns; @@ -930,6 +961,8 @@ static int genpd_runtime_resume(struct device *dev) genpd_lock(genpd); ret = genpd_power_on(genpd, 0); + if (!ret) + genpd_restore_performance_state(dev, gpd_data->rpm_pstate); genpd_unlock(genpd); if (ret) @@ -968,6 +1001,7 @@ err_stop: err_poweroff: if (!pm_runtime_is_irq_safe(dev) || genpd_is_irq_safe(genpd)) { genpd_lock(genpd); + gpd_data->rpm_pstate = genpd_drop_performance_state(dev); genpd_power_off(genpd, true, 0); genpd_unlock(genpd); } @@ -2505,7 +2539,7 @@ EXPORT_SYMBOL_GPL(of_genpd_remove_subdomain); /** * of_genpd_remove_last - Remove the last PM domain registered for a provider - * @provider: Pointer to device structure associated with provider + * @np: Pointer to device node associated with provider * * Find the last PM domain that was added by a particular provider and * remove this PM domain from the list of PM domains. The provider is diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c index c6c218758f0b..cd08c5885190 100644 --- a/drivers/base/power/domain_governor.c +++ b/drivers/base/power/domain_governor.c @@ -252,6 +252,7 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd, /** * _default_power_down_ok - Default generic PM domain power off governor routine. * @pd: PM domain to check. + * @now: current ktime. * * This routine must be executed under the PM domain's lock. */ diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index b570848d23e0..8a66eaf731e4 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -345,7 +345,7 @@ static void rpm_suspend_suppliers(struct device *dev) static int __rpm_callback(int (*cb)(struct device *), struct device *dev) __releases(&dev->power.lock) __acquires(&dev->power.lock) { - int retval, idx; + int retval = 0, idx; bool use_links = dev->power.links_count > 0; if (dev->power.irq_safe) { @@ -373,7 +373,8 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev) } } - retval = cb(dev); + if (cb) + retval = cb(dev); if (dev->power.irq_safe) { spin_lock(&dev->power.lock); @@ -446,7 +447,10 @@ static int rpm_idle(struct device *dev, int rpmflags) /* Pending requests need to be canceled. */ dev->power.request = RPM_REQ_NONE; - if (dev->power.no_callbacks) + callback = RPM_GET_CALLBACK(dev, runtime_idle); + + /* If no callback assume success. */ + if (!callback || dev->power.no_callbacks) goto out; /* Carry out an asynchronous or a synchronous idle notification. */ @@ -462,10 +466,7 @@ static int rpm_idle(struct device *dev, int rpmflags) dev->power.idle_notification = true; - callback = RPM_GET_CALLBACK(dev, runtime_idle); - - if (callback) - retval = __rpm_callback(callback, dev); + retval = __rpm_callback(callback, dev); dev->power.idle_notification = false; wake_up_all(&dev->power.wait_queue); @@ -484,9 +485,6 @@ static int rpm_callback(int (*cb)(struct device *), struct device *dev) { int retval; - if (!cb) - return -ENOSYS; - if (dev->power.memalloc_noio) { unsigned int noio_flag; diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index 8e021082dba8..3bad3266a2ad 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -182,7 +182,6 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) wirq->dev = dev; wirq->irq = irq; - irq_set_status_flags(irq, IRQ_NOAUTOEN); /* Prevent deferred spurious wakeirqs with disable_irq_nosync() */ irq_set_status_flags(irq, IRQ_DISABLE_UNLAZY); @@ -192,7 +191,8 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) * so we use a threaded irq. */ err = request_threaded_irq(irq, NULL, handle_threaded_wake_irq, - IRQF_ONESHOT, wirq->name, wirq); + IRQF_ONESHOT | IRQF_NO_AUTOEN, + wirq->name, wirq); if (err) goto err_free_name; diff --git a/drivers/base/property.c b/drivers/base/property.c index 1421e9548857..1f533b314efc 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -21,7 +21,7 @@ struct fwnode_handle *dev_fwnode(struct device *dev) { return IS_ENABLED(CONFIG_OF) && dev->of_node ? - &dev->of_node->fwnode : dev->fwnode; + of_fwnode_handle(dev->of_node) : dev->fwnode; } EXPORT_SYMBOL_GPL(dev_fwnode); @@ -759,13 +759,8 @@ EXPORT_SYMBOL_GPL(fwnode_get_next_available_child_node); struct fwnode_handle *device_get_next_child_node(struct device *dev, struct fwnode_handle *child) { - struct acpi_device *adev = ACPI_COMPANION(dev); - struct fwnode_handle *fwnode = NULL, *next; - - if (dev->of_node) - fwnode = &dev->of_node->fwnode; - else if (adev) - fwnode = acpi_fwnode_handle(adev); + const struct fwnode_handle *fwnode = dev_fwnode(dev); + struct fwnode_handle *next; /* Try to find a child in primary fwnode */ next = fwnode_get_next_child_node(fwnode, child); @@ -868,28 +863,31 @@ EXPORT_SYMBOL_GPL(device_get_child_node_count); bool device_dma_supported(struct device *dev) { + const struct fwnode_handle *fwnode = dev_fwnode(dev); + /* For DT, this is always supported. * For ACPI, this depends on CCA, which * is determined by the acpi_dma_supported(). */ - if (IS_ENABLED(CONFIG_OF) && dev->of_node) + if (is_of_node(fwnode)) return true; - return acpi_dma_supported(ACPI_COMPANION(dev)); + return acpi_dma_supported(to_acpi_device_node(fwnode)); } EXPORT_SYMBOL_GPL(device_dma_supported); enum dev_dma_attr device_get_dma_attr(struct device *dev) { + const struct fwnode_handle *fwnode = dev_fwnode(dev); enum dev_dma_attr attr = DEV_DMA_NOT_SUPPORTED; - if (IS_ENABLED(CONFIG_OF) && dev->of_node) { - if (of_dma_is_coherent(dev->of_node)) + if (is_of_node(fwnode)) { + if (of_dma_is_coherent(to_of_node(fwnode))) attr = DEV_DMA_COHERENT; else attr = DEV_DMA_NON_COHERENT; } else - attr = acpi_get_dma_attr(ACPI_COMPANION(dev)); + attr = acpi_get_dma_attr(to_acpi_device_node(fwnode)); return attr; } @@ -1007,14 +1005,13 @@ EXPORT_SYMBOL(device_get_mac_address); * Returns Linux IRQ number on success. Other values are determined * accordingly to acpi_/of_ irq_get() operation. */ -int fwnode_irq_get(struct fwnode_handle *fwnode, unsigned int index) +int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index) { - struct device_node *of_node = to_of_node(fwnode); struct resource res; int ret; - if (IS_ENABLED(CONFIG_OF) && of_node) - return of_irq_get(of_node, index); + if (is_of_node(fwnode)) + return of_irq_get(to_of_node(fwnode), index); ret = acpi_irq_get(ACPI_HANDLE_FWNODE(fwnode), index, &res); if (ret) diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 9e2d0c6a3877..8b1714021498 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1781,15 +1781,13 @@ static int fd_alloc_disk(int drive, int system) { struct gendisk *disk; - disk = alloc_disk(1); - if (!disk) - goto out; - disk->queue = blk_mq_init_queue(&unit[drive].tag_set); - if (IS_ERR(disk->queue)) - goto out_put_disk; + disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL); + if (IS_ERR(disk)) + return PTR_ERR(disk); disk->major = FLOPPY_MAJOR; disk->first_minor = drive + system; + disk->minors = 1; disk->fops = &floppy_fops; disk->events = DISK_EVENT_MEDIA_CHANGE; if (system) @@ -1802,12 +1800,6 @@ static int fd_alloc_disk(int drive, int system) unit[drive].gendisk[system] = disk; add_disk(disk); return 0; - -out_put_disk: - disk->queue = NULL; - put_disk(disk); -out: - return -ENOMEM; } static int fd_alloc_drive(int drive) diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index c34e71b0c4a9..06b360f7123a 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -338,14 +338,13 @@ static const struct blk_mq_ops aoeblk_mq_ops = { .queue_rq = aoeblk_queue_rq, }; -/* alloc_disk and add_disk can sleep */ +/* blk_mq_alloc_disk and add_disk can sleep */ void aoeblk_gdalloc(void *vp) { struct aoedev *d = vp; struct gendisk *gd; mempool_t *mp; - struct request_queue *q; struct blk_mq_tag_set *set; ulong flags; int late = 0; @@ -362,19 +361,12 @@ aoeblk_gdalloc(void *vp) if (late) return; - gd = alloc_disk(AOE_PARTITIONS); - if (gd == NULL) { - pr_err("aoe: cannot allocate disk structure for %ld.%d\n", - d->aoemajor, d->aoeminor); - goto err; - } - mp = mempool_create(MIN_BUFS, mempool_alloc_slab, mempool_free_slab, buf_pool_cache); if (mp == NULL) { printk(KERN_ERR "aoe: cannot allocate bufpool for %ld.%d\n", d->aoemajor, d->aoeminor); - goto err_disk; + goto err; } set = &d->tag_set; @@ -391,12 +383,11 @@ aoeblk_gdalloc(void *vp) goto err_mempool; } - q = blk_mq_init_queue(set); - if (IS_ERR(q)) { + gd = blk_mq_alloc_disk(set, d); + if (IS_ERR(gd)) { pr_err("aoe: cannot allocate block queue for %ld.%d\n", d->aoemajor, d->aoeminor); - blk_mq_free_tag_set(set); - goto err_mempool; + goto err_tagset; } spin_lock_irqsave(&d->lock, flags); @@ -405,16 +396,16 @@ aoeblk_gdalloc(void *vp) WARN_ON(d->flags & DEVFL_TKILL); WARN_ON(d->gd); WARN_ON(d->flags & DEVFL_UP); - blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS); - blk_queue_io_opt(q, SZ_2M); + blk_queue_max_hw_sectors(gd->queue, BLK_DEF_MAX_SECTORS); + blk_queue_io_opt(gd->queue, SZ_2M); d->bufpool = mp; - d->blkq = gd->queue = q; - q->queuedata = d; + d->blkq = gd->queue; d->gd = gd; if (aoe_maxsectors) - blk_queue_max_hw_sectors(q, aoe_maxsectors); + blk_queue_max_hw_sectors(gd->queue, aoe_maxsectors); gd->major = AOE_MAJOR; gd->first_minor = d->sysminor; + gd->minors = AOE_PARTITIONS; gd->fops = &aoe_bdops; gd->private_data = d; set_capacity(gd, d->ssize); @@ -435,10 +426,10 @@ aoeblk_gdalloc(void *vp) spin_unlock_irqrestore(&d->lock, flags); return; +err_tagset: + blk_mq_free_tag_set(set); err_mempool: mempool_destroy(mp); -err_disk: - put_disk(gd); err: spin_lock_irqsave(&d->lock, flags); d->flags &= ~DEVFL_GD_NOW; diff --git a/drivers/block/aoe/aoechr.c b/drivers/block/aoe/aoechr.c index ab41be625a53..8eea2529da20 100644 --- a/drivers/block/aoe/aoechr.c +++ b/drivers/block/aoe/aoechr.c @@ -140,10 +140,8 @@ bail: spin_unlock_irqrestore(&emsgs_lock, flags); } mp = kmemdup(msg, n, GFP_ATOMIC); - if (mp == NULL) { - printk(KERN_ERR "aoe: allocation failure, len=%ld\n", n); + if (!mp) goto bail; - } em->msg = mp; em->flags |= EMFL_VALID; diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index ecd77897a761..588889bea7c3 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -1701,8 +1701,6 @@ aoecmd_init(void) goto ktiowq_fail; } - mutex_init(&ktio_spawn_lock); - for (i = 0; i < ncpus; i++) { INIT_LIST_HEAD(&iocq[i].head); spin_lock_init(&iocq[i].lock); diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c index e2ea2356da06..c5753c6bfe80 100644 --- a/drivers/block/aoe/aoedev.c +++ b/drivers/block/aoe/aoedev.c @@ -277,9 +277,8 @@ freedev(struct aoedev *d) if (d->gd) { aoedisk_rm_debugfs(d); del_gendisk(d->gd); - put_disk(d->gd); + blk_cleanup_disk(d->gd); blk_mq_free_tag_set(&d->tag_set); - blk_cleanup_queue(d->blkq); } t = d->targets; e = t + d->ntargets; diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index d601e49f80e0..a093644ac39f 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -1968,22 +1968,14 @@ static const struct blk_mq_ops ataflop_mq_ops = { static int ataflop_alloc_disk(unsigned int drive, unsigned int type) { struct gendisk *disk; - int ret; - disk = alloc_disk(1); - if (!disk) - return -ENOMEM; - - disk->queue = blk_mq_init_queue(&unit[drive].tag_set); - if (IS_ERR(disk->queue)) { - ret = PTR_ERR(disk->queue); - disk->queue = NULL; - put_disk(disk); - return ret; - } + disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL); + if (IS_ERR(disk)) + return PTR_ERR(disk); disk->major = FLOPPY_MAJOR; disk->first_minor = drive + (type << 2); + disk->minors = 1; sprintf(disk->disk_name, "fd%d", drive); disk->fops = &floppy_fops; disk->events = DISK_EVENT_MEDIA_CHANGE; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 7562cf30b14e..95694113e38e 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -38,9 +38,7 @@ * device). */ struct brd_device { - int brd_number; - - struct request_queue *brd_queue; + int brd_number; struct gendisk *brd_disk; struct list_head brd_list; @@ -372,7 +370,7 @@ static LIST_HEAD(brd_devices); static DEFINE_MUTEX(brd_devices_mutex); static struct dentry *brd_debugfs_dir; -static struct brd_device *brd_alloc(int i) +static int brd_alloc(int i) { struct brd_device *brd; struct gendisk *disk; @@ -380,64 +378,55 @@ static struct brd_device *brd_alloc(int i) brd = kzalloc(sizeof(*brd), GFP_KERNEL); if (!brd) - goto out; + return -ENOMEM; brd->brd_number = i; spin_lock_init(&brd->brd_lock); INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC); - brd->brd_queue = blk_alloc_queue(NUMA_NO_NODE); - if (!brd->brd_queue) - goto out_free_dev; - snprintf(buf, DISK_NAME_LEN, "ram%d", i); if (!IS_ERR_OR_NULL(brd_debugfs_dir)) debugfs_create_u64(buf, 0444, brd_debugfs_dir, &brd->brd_nr_pages); - /* This is so fdisk will align partitions on 4k, because of - * direct_access API needing 4k alignment, returning a PFN - * (This is only a problem on very small devices <= 4M, - * otherwise fdisk will align on 1M. Regardless this call - * is harmless) - */ - blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE); - disk = brd->brd_disk = alloc_disk(max_part); + disk = brd->brd_disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) - goto out_free_queue; + goto out_free_dev; + disk->major = RAMDISK_MAJOR; disk->first_minor = i * max_part; + disk->minors = max_part; disk->fops = &brd_fops; disk->private_data = brd; disk->flags = GENHD_FL_EXT_DEVT; strlcpy(disk->disk_name, buf, DISK_NAME_LEN); set_capacity(disk, rd_size * 2); + + /* + * This is so fdisk will align partitions on 4k, because of + * direct_access API needing 4k alignment, returning a PFN + * (This is only a problem on very small devices <= 4M, + * otherwise fdisk will align on 1M. Regardless this call + * is harmless) + */ + blk_queue_physical_block_size(disk->queue, PAGE_SIZE); /* Tell the block layer that this is not a rotational device */ - blk_queue_flag_set(QUEUE_FLAG_NONROT, brd->brd_queue); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, brd->brd_queue); + blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); + blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue); + add_disk(disk); + list_add_tail(&brd->brd_list, &brd_devices); - return brd; + return 0; -out_free_queue: - blk_cleanup_queue(brd->brd_queue); out_free_dev: kfree(brd); -out: - return NULL; -} - -static void brd_free(struct brd_device *brd) -{ - put_disk(brd->brd_disk); - blk_cleanup_queue(brd->brd_queue); - brd_free_pages(brd); - kfree(brd); + return -ENOMEM; } static void brd_probe(dev_t dev) { - struct brd_device *brd; int i = MINOR(dev) / max_part; + struct brd_device *brd; mutex_lock(&brd_devices_mutex); list_for_each_entry(brd, &brd_devices, brd_list) { @@ -445,13 +434,7 @@ static void brd_probe(dev_t dev) goto out_unlock; } - brd = brd_alloc(i); - if (brd) { - brd->brd_disk->queue = brd->brd_queue; - add_disk(brd->brd_disk); - list_add_tail(&brd->brd_list, &brd_devices); - } - + brd_alloc(i); out_unlock: mutex_unlock(&brd_devices_mutex); } @@ -460,7 +443,9 @@ static void brd_del_one(struct brd_device *brd) { list_del(&brd->brd_list); del_gendisk(brd->brd_disk); - brd_free(brd); + blk_cleanup_disk(brd->brd_disk); + brd_free_pages(brd); + kfree(brd); } static inline void brd_check_and_reset_par(void) @@ -485,7 +470,7 @@ static inline void brd_check_and_reset_par(void) static int __init brd_init(void) { struct brd_device *brd, *next; - int i; + int err, i; /* * brd module now has a feature to instantiate underlying device @@ -511,22 +496,11 @@ static int __init brd_init(void) mutex_lock(&brd_devices_mutex); for (i = 0; i < rd_nr; i++) { - brd = brd_alloc(i); - if (!brd) + err = brd_alloc(i); + if (err) goto out_free; - list_add_tail(&brd->brd_list, &brd_devices); } - /* point of no return */ - - list_for_each_entry(brd, &brd_devices, brd_list) { - /* - * associate with queue just before adding disk for - * avoiding to mess up failure path - */ - brd->brd_disk->queue = brd->brd_queue; - add_disk(brd->brd_disk); - } mutex_unlock(&brd_devices_mutex); pr_info("brd: module loaded\n"); @@ -535,15 +509,13 @@ static int __init brd_init(void) out_free: debugfs_remove_recursive(brd_debugfs_dir); - list_for_each_entry_safe(brd, next, &brd_devices, brd_list) { - list_del(&brd->brd_list); - brd_free(brd); - } + list_for_each_entry_safe(brd, next, &brd_devices, brd_list) + brd_del_one(brd); mutex_unlock(&brd_devices_mutex); unregister_blkdev(RAMDISK_MAJOR, "ramdisk"); pr_info("brd: module NOT loaded !!!\n"); - return -ENOMEM; + return err; } static void __exit brd_exit(void) diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index de463773b530..55234a558e98 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2231,8 +2231,7 @@ void drbd_destroy_device(struct kref *kref) if (device->bitmap) /* should no longer be there. */ drbd_bm_cleanup(device); __free_page(device->md_io.page); - put_disk(device->vdisk); - blk_cleanup_queue(device->rq_queue); + blk_cleanup_disk(device->vdisk); kfree(device->rs_plan_s); /* not for_each_connection(connection, resource): @@ -2701,7 +2700,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig struct drbd_device *device; struct drbd_peer_device *peer_device, *tmp_peer_device; struct gendisk *disk; - struct request_queue *q; int id; int vnr = adm_ctx->volume; enum drbd_ret_code err = ERR_NOMEM; @@ -2723,29 +2721,26 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_init_set_defaults(device); - q = blk_alloc_queue(NUMA_NO_NODE); - if (!q) - goto out_no_q; - device->rq_queue = q; - - disk = alloc_disk(1); + disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) goto out_no_disk; + device->vdisk = disk; + device->rq_queue = disk->queue; set_disk_ro(disk, true); - disk->queue = q; disk->major = DRBD_MAJOR; disk->first_minor = minor; + disk->minors = 1; disk->fops = &drbd_ops; sprintf(disk->disk_name, "drbd%d", minor); disk->private_data = device; - blk_queue_write_cache(q, true, true); + blk_queue_write_cache(disk->queue, true, true); /* Setting the max_hw_sectors to an odd value of 8kibyte here This triggers a max_bio_size message upon first attach or connect */ - blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE_SAFE >> 8); + blk_queue_max_hw_sectors(disk->queue, DRBD_MAX_BIO_SIZE_SAFE >> 8); device->md_io.page = alloc_page(GFP_KERNEL); if (!device->md_io.page) @@ -2834,10 +2829,8 @@ out_no_minor_idr: out_no_bitmap: __free_page(device->md_io.page); out_no_io_page: - put_disk(disk); + blk_cleanup_disk(disk); out_no_disk: - blk_cleanup_queue(q); -out_no_q: kref_put(&resource->kref, drbd_destroy_resource); kfree(device); return err; diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 69284ebba786..1f740e42e457 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -3770,10 +3770,8 @@ static int receive_protocol(struct drbd_connection *connection, struct packet_in } new_net_conf = kmalloc(sizeof(struct net_conf), GFP_KERNEL); - if (!new_net_conf) { - drbd_err(connection, "Allocation of new net_conf failed\n"); + if (!new_net_conf) goto disconnect; - } mutex_lock(&connection->data.mutex); mutex_lock(&connection->resource->conf_update); @@ -4020,10 +4018,8 @@ static int receive_SyncParam(struct drbd_connection *connection, struct packet_i if (verify_tfm || csums_tfm) { new_net_conf = kzalloc(sizeof(struct net_conf), GFP_KERNEL); - if (!new_net_conf) { - drbd_err(device, "Allocation of new net_conf failed\n"); + if (!new_net_conf) goto disconnect; - } *new_net_conf = *old_net_conf; @@ -4161,7 +4157,6 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info new_disk_conf = kzalloc(sizeof(struct disk_conf), GFP_KERNEL); if (!new_disk_conf) { - drbd_err(device, "Allocation of new disk_conf failed\n"); put_ldev(device); return -ENOMEM; } @@ -4288,10 +4283,8 @@ static int receive_uuids(struct drbd_connection *connection, struct packet_info device = peer_device->device; p_uuid = kmalloc_array(UI_EXTENDED_SIZE, sizeof(*p_uuid), GFP_NOIO); - if (!p_uuid) { - drbd_err(device, "kmalloc of p_uuid failed\n"); + if (!p_uuid) return false; - } for (i = UI_CURRENT; i < UI_EXTENDED_SIZE; i++) p_uuid[i] = be64_to_cpu(p->uuid[i]); @@ -5484,8 +5477,7 @@ static int drbd_do_auth(struct drbd_connection *connection) } peers_ch = kmalloc(pi.size, GFP_NOIO); - if (peers_ch == NULL) { - drbd_err(connection, "kmalloc of peers_ch failed\n"); + if (!peers_ch) { rv = -1; goto fail; } @@ -5504,8 +5496,7 @@ static int drbd_do_auth(struct drbd_connection *connection) resp_size = crypto_shash_digestsize(connection->cram_hmac_tfm); response = kmalloc(resp_size, GFP_NOIO); - if (response == NULL) { - drbd_err(connection, "kmalloc of response failed\n"); + if (!response) { rv = -1; goto fail; } @@ -5552,8 +5543,7 @@ static int drbd_do_auth(struct drbd_connection *connection) } right_response = kmalloc(resp_size, GFP_NOIO); - if (right_response == NULL) { - drbd_err(connection, "kmalloc of right_response failed\n"); + if (!right_response) { rv = -1; goto fail; } diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 8a9d22207c59..87460e0e5c72 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -2123,6 +2123,7 @@ static void format_interrupt(void) switch (interpret_errors()) { case 1: cont->error(); + break; case 2: break; case 0: @@ -2330,7 +2331,6 @@ static void rw_interrupt(void) if (!drive_state[current_drive].first_read_date) drive_state[current_drive].first_read_date = jiffies; - nr_sectors = 0; ssize = DIV_ROUND_UP(1 << raw_cmd->cmd[SIZECODE], 4); if (reply_buffer[ST1] & ST1_EOC) @@ -4491,23 +4491,15 @@ static bool floppy_available(int drive) static int floppy_alloc_disk(unsigned int drive, unsigned int type) { struct gendisk *disk; - int err; - disk = alloc_disk(1); - if (!disk) - return -ENOMEM; - - disk->queue = blk_mq_init_queue(&tag_sets[drive]); - if (IS_ERR(disk->queue)) { - err = PTR_ERR(disk->queue); - disk->queue = NULL; - put_disk(disk); - return err; - } + disk = blk_mq_alloc_disk(&tag_sets[drive], NULL); + if (IS_ERR(disk)) + return PTR_ERR(disk); blk_queue_max_hw_sectors(disk->queue, 64); disk->major = FLOPPY_MAJOR; disk->first_minor = TOMINOR(drive) | (type << 2); + disk->minors = 1; disk->fops = &floppy_fops; disk->events = DISK_EVENT_MEDIA_CHANGE; if (type) @@ -4727,10 +4719,8 @@ out_put_disk: if (!disks[drive][0]) break; del_timer_sync(&motor_off_timer[drive]); - blk_cleanup_queue(disks[drive][0]->queue); - disks[drive][0]->queue = NULL; + blk_cleanup_disk(disks[drive][0]); blk_mq_free_tag_set(&tag_sets[drive]); - put_disk(disks[drive][0]); } return err; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 76e12f3482a9..cc0e8c39a48b 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -71,7 +71,6 @@ #include #include #include -#include #include #include #include @@ -79,11 +78,14 @@ #include #include #include +#include #include "loop.h" #include +#define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ) + static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_ctl_mutex); @@ -515,8 +517,6 @@ static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2) { struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb); - if (cmd->css) - css_put(cmd->css); cmd->ret = ret; lo_rw_aio_do_completion(cmd); } @@ -577,8 +577,6 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, cmd->iocb.ki_complete = lo_rw_aio_complete; cmd->iocb.ki_flags = IOCB_DIRECT; cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); - if (cmd->css) - kthread_associate_blkcg(cmd->css); if (rw == WRITE) ret = call_write_iter(file, &cmd->iocb, &iter); @@ -586,7 +584,6 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, ret = call_read_iter(file, &cmd->iocb, &iter); lo_rw_aio_do_completion(cmd); - kthread_associate_blkcg(NULL); if (ret != -EIOCBQUEUED) cmd->iocb.ki_complete(&cmd->iocb, ret, 0); @@ -647,14 +644,13 @@ static inline void loop_update_dio(struct loop_device *lo) lo->use_dio); } -static void loop_reread_partitions(struct loop_device *lo, - struct block_device *bdev) +static void loop_reread_partitions(struct loop_device *lo) { int rc; - mutex_lock(&bdev->bd_mutex); - rc = bdev_disk_changed(bdev, false); - mutex_unlock(&bdev->bd_mutex); + mutex_lock(&lo->lo_disk->open_mutex); + rc = bdev_disk_changed(lo->lo_disk, false); + mutex_unlock(&lo->lo_disk->open_mutex); if (rc) pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n", __func__, lo->lo_number, lo->lo_file_name, rc); @@ -747,12 +743,12 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, mutex_unlock(&lo->lo_mutex); /* * We must drop file reference outside of lo_mutex as dropping - * the file ref can take bd_mutex which creates circular locking + * the file ref can take open_mutex which creates circular locking * dependency. */ fput(old_file); if (partscan) - loop_reread_partitions(lo, bdev); + loop_reread_partitions(lo); return 0; out_err: @@ -921,27 +917,100 @@ static void loop_config_discard(struct loop_device *lo) q->limits.discard_alignment = 0; } -static void loop_unprepare_queue(struct loop_device *lo) -{ - kthread_flush_worker(&lo->worker); - kthread_stop(lo->worker_task); -} +struct loop_worker { + struct rb_node rb_node; + struct work_struct work; + struct list_head cmd_list; + struct list_head idle_list; + struct loop_device *lo; + struct cgroup_subsys_state *blkcg_css; + unsigned long last_ran_at; +}; -static int loop_kthread_worker_fn(void *worker_ptr) -{ - current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO; - return kthread_worker_fn(worker_ptr); -} +static void loop_workfn(struct work_struct *work); +static void loop_rootcg_workfn(struct work_struct *work); +static void loop_free_idle_workers(struct timer_list *timer); -static int loop_prepare_queue(struct loop_device *lo) +#ifdef CONFIG_BLK_CGROUP +static inline int queue_on_root_worker(struct cgroup_subsys_state *css) { - kthread_init_worker(&lo->worker); - lo->worker_task = kthread_run(loop_kthread_worker_fn, - &lo->worker, "loop%d", lo->lo_number); - if (IS_ERR(lo->worker_task)) - return -ENOMEM; - set_user_nice(lo->worker_task, MIN_NICE); - return 0; + return !css || css == blkcg_root_css; +} +#else +static inline int queue_on_root_worker(struct cgroup_subsys_state *css) +{ + return !css; +} +#endif + +static void loop_queue_work(struct loop_device *lo, struct loop_cmd *cmd) +{ + struct rb_node **node = &(lo->worker_tree.rb_node), *parent = NULL; + struct loop_worker *cur_worker, *worker = NULL; + struct work_struct *work; + struct list_head *cmd_list; + + spin_lock_irq(&lo->lo_work_lock); + + if (queue_on_root_worker(cmd->blkcg_css)) + goto queue_work; + + node = &lo->worker_tree.rb_node; + + while (*node) { + parent = *node; + cur_worker = container_of(*node, struct loop_worker, rb_node); + if (cur_worker->blkcg_css == cmd->blkcg_css) { + worker = cur_worker; + break; + } else if ((long)cur_worker->blkcg_css < (long)cmd->blkcg_css) { + node = &(*node)->rb_left; + } else { + node = &(*node)->rb_right; + } + } + if (worker) + goto queue_work; + + worker = kzalloc(sizeof(struct loop_worker), GFP_NOWAIT | __GFP_NOWARN); + /* + * In the event we cannot allocate a worker, just queue on the + * rootcg worker and issue the I/O as the rootcg + */ + if (!worker) { + cmd->blkcg_css = NULL; + if (cmd->memcg_css) + css_put(cmd->memcg_css); + cmd->memcg_css = NULL; + goto queue_work; + } + + worker->blkcg_css = cmd->blkcg_css; + css_get(worker->blkcg_css); + INIT_WORK(&worker->work, loop_workfn); + INIT_LIST_HEAD(&worker->cmd_list); + INIT_LIST_HEAD(&worker->idle_list); + worker->lo = lo; + rb_link_node(&worker->rb_node, parent, node); + rb_insert_color(&worker->rb_node, &lo->worker_tree); +queue_work: + if (worker) { + /* + * We need to remove from the idle list here while + * holding the lock so that the idle timer doesn't + * free the worker + */ + if (!list_empty(&worker->idle_list)) + list_del_init(&worker->idle_list); + work = &worker->work; + cmd_list = &worker->cmd_list; + } else { + work = &lo->rootcg_work; + cmd_list = &lo->rootcg_cmd_list; + } + list_add_tail(&cmd->list_entry, cmd_list); + queue_work(lo->workqueue, work); + spin_unlock_irq(&lo->lo_work_lock); } static void loop_update_rotational(struct loop_device *lo) @@ -1127,12 +1196,23 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, !file->f_op->write_iter) lo->lo_flags |= LO_FLAGS_READ_ONLY; - error = loop_prepare_queue(lo); - if (error) + lo->workqueue = alloc_workqueue("loop%d", + WQ_UNBOUND | WQ_FREEZABLE, + 0, + lo->lo_number); + if (!lo->workqueue) { + error = -ENOMEM; goto out_unlock; + } set_disk_ro(lo->lo_disk, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); + INIT_WORK(&lo->rootcg_work, loop_rootcg_workfn); + INIT_LIST_HEAD(&lo->rootcg_cmd_list); + INIT_LIST_HEAD(&lo->idle_worker_list); + lo->worker_tree = RB_ROOT; + timer_setup(&lo->timer, loop_free_idle_workers, + TIMER_DEFERRABLE); lo->use_dio = lo->lo_flags & LO_FLAGS_DIRECT_IO; lo->lo_device = bdev; lo->lo_backing_file = file; @@ -1154,6 +1234,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, blk_queue_physical_block_size(lo->lo_queue, bsize); blk_queue_io_min(lo->lo_queue, bsize); + loop_config_discard(lo); loop_update_rotational(lo); loop_update_dio(lo); loop_sysfs_init(lo); @@ -1174,7 +1255,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, bdgrab(bdev); mutex_unlock(&lo->lo_mutex); if (partscan) - loop_reread_partitions(lo, bdev); + loop_reread_partitions(lo); if (!(mode & FMODE_EXCL)) bd_abort_claiming(bdev, loop_configure); return 0; @@ -1200,6 +1281,7 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) int err = 0; bool partscan = false; int lo_number; + struct loop_worker *pos, *worker; mutex_lock(&lo->lo_mutex); if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) { @@ -1219,6 +1301,18 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) /* freeze request queue during the transition */ blk_mq_freeze_queue(lo->lo_queue); + destroy_workqueue(lo->workqueue); + spin_lock_irq(&lo->lo_work_lock); + list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, + idle_list) { + list_del(&worker->idle_list); + rb_erase(&worker->rb_node, &lo->worker_tree); + css_put(worker->blkcg_css); + kfree(worker); + } + spin_unlock_irq(&lo->lo_work_lock); + del_timer_sync(&lo->timer); + spin_lock_irq(&lo->lo_lock); lo->lo_backing_file = NULL; spin_unlock_irq(&lo->lo_lock); @@ -1255,12 +1349,11 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev; lo_number = lo->lo_number; - loop_unprepare_queue(lo); out_unlock: mutex_unlock(&lo->lo_mutex); if (partscan) { /* - * bd_mutex has been held already in release path, so don't + * open_mutex has been held already in release path, so don't * acquire it if this function is called in such case. * * If the reread partition isn't from release path, lo_refcnt @@ -1268,10 +1361,10 @@ out_unlock: * current holder is released. */ if (!release) - mutex_lock(&bdev->bd_mutex); - err = bdev_disk_changed(bdev, false); + mutex_lock(&lo->lo_disk->open_mutex); + err = bdev_disk_changed(lo->lo_disk, false); if (!release) - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&lo->lo_disk->open_mutex); if (err) pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", __func__, lo_number, err); @@ -1298,7 +1391,7 @@ out_unlock: /* * Need not hold lo_mutex to fput backing file. Calling fput holding * lo_mutex triggers a circular lock dependency possibility warning as - * fput can take bd_mutex which is usually taken before lo_mutex. + * fput can take open_mutex which is usually taken before lo_mutex. */ if (filp) fput(filp); @@ -1416,7 +1509,7 @@ out_unfreeze: out_unlock: mutex_unlock(&lo->lo_mutex); if (partscan) - loop_reread_partitions(lo, bdev); + loop_reread_partitions(lo); return err; } @@ -2008,14 +2101,19 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, } /* always use the first bio's css */ + cmd->blkcg_css = NULL; + cmd->memcg_css = NULL; #ifdef CONFIG_BLK_CGROUP - if (cmd->use_aio && rq->bio && rq->bio->bi_blkg) { - cmd->css = &bio_blkcg(rq->bio)->css; - css_get(cmd->css); - } else + if (rq->bio && rq->bio->bi_blkg) { + cmd->blkcg_css = &bio_blkcg(rq->bio)->css; +#ifdef CONFIG_MEMCG + cmd->memcg_css = + cgroup_get_e_css(cmd->blkcg_css->cgroup, + &memory_cgrp_subsys); #endif - cmd->css = NULL; - kthread_queue_work(&lo->worker, &cmd->work); + } +#endif + loop_queue_work(lo, cmd); return BLK_STS_OK; } @@ -2026,13 +2124,28 @@ static void loop_handle_cmd(struct loop_cmd *cmd) const bool write = op_is_write(req_op(rq)); struct loop_device *lo = rq->q->queuedata; int ret = 0; + struct mem_cgroup *old_memcg = NULL; if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) { ret = -EIO; goto failed; } + if (cmd->blkcg_css) + kthread_associate_blkcg(cmd->blkcg_css); + if (cmd->memcg_css) + old_memcg = set_active_memcg( + mem_cgroup_from_css(cmd->memcg_css)); + ret = do_req_filebacked(lo, rq); + + if (cmd->blkcg_css) + kthread_associate_blkcg(NULL); + + if (cmd->memcg_css) { + set_active_memcg(old_memcg); + css_put(cmd->memcg_css); + } failed: /* complete non-aio request */ if (!cmd->use_aio || ret) { @@ -2045,26 +2158,82 @@ static void loop_handle_cmd(struct loop_cmd *cmd) } } -static void loop_queue_work(struct kthread_work *work) +static void loop_set_timer(struct loop_device *lo) { - struct loop_cmd *cmd = - container_of(work, struct loop_cmd, work); - - loop_handle_cmd(cmd); + timer_reduce(&lo->timer, jiffies + LOOP_IDLE_WORKER_TIMEOUT); } -static int loop_init_request(struct blk_mq_tag_set *set, struct request *rq, - unsigned int hctx_idx, unsigned int numa_node) +static void loop_process_work(struct loop_worker *worker, + struct list_head *cmd_list, struct loop_device *lo) { - struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); + int orig_flags = current->flags; + struct loop_cmd *cmd; - kthread_init_work(&cmd->work, loop_queue_work); - return 0; + current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO; + spin_lock_irq(&lo->lo_work_lock); + while (!list_empty(cmd_list)) { + cmd = container_of( + cmd_list->next, struct loop_cmd, list_entry); + list_del(cmd_list->next); + spin_unlock_irq(&lo->lo_work_lock); + + loop_handle_cmd(cmd); + cond_resched(); + + spin_lock_irq(&lo->lo_work_lock); + } + + /* + * We only add to the idle list if there are no pending cmds + * *and* the worker will not run again which ensures that it + * is safe to free any worker on the idle list + */ + if (worker && !work_pending(&worker->work)) { + worker->last_ran_at = jiffies; + list_add_tail(&worker->idle_list, &lo->idle_worker_list); + loop_set_timer(lo); + } + spin_unlock_irq(&lo->lo_work_lock); + current->flags = orig_flags; +} + +static void loop_workfn(struct work_struct *work) +{ + struct loop_worker *worker = + container_of(work, struct loop_worker, work); + loop_process_work(worker, &worker->cmd_list, worker->lo); +} + +static void loop_rootcg_workfn(struct work_struct *work) +{ + struct loop_device *lo = + container_of(work, struct loop_device, rootcg_work); + loop_process_work(NULL, &lo->rootcg_cmd_list, lo); +} + +static void loop_free_idle_workers(struct timer_list *timer) +{ + struct loop_device *lo = container_of(timer, struct loop_device, timer); + struct loop_worker *pos, *worker; + + spin_lock_irq(&lo->lo_work_lock); + list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, + idle_list) { + if (time_is_after_jiffies(worker->last_ran_at + + LOOP_IDLE_WORKER_TIMEOUT)) + break; + list_del(&worker->idle_list); + rb_erase(&worker->rb_node, &lo->worker_tree); + css_put(worker->blkcg_css); + kfree(worker); + } + if (!list_empty(&lo->idle_worker_list)) + loop_set_timer(lo); + spin_unlock_irq(&lo->lo_work_lock); } static const struct blk_mq_ops loop_mq_ops = { .queue_rq = loop_queue_rq, - .init_request = loop_init_request, .complete = lo_complete_rq, }; @@ -2106,12 +2275,12 @@ static int loop_add(struct loop_device **l, int i) if (err) goto out_free_idr; - lo->lo_queue = blk_mq_init_queue(&lo->tag_set); - if (IS_ERR(lo->lo_queue)) { - err = PTR_ERR(lo->lo_queue); + disk = lo->lo_disk = blk_mq_alloc_disk(&lo->tag_set, lo); + if (IS_ERR(disk)) { + err = PTR_ERR(disk); goto out_cleanup_tags; } - lo->lo_queue->queuedata = lo; + lo->lo_queue = lo->lo_disk->queue; blk_queue_max_hw_sectors(lo->lo_queue, BLK_DEF_MAX_SECTORS); @@ -2123,11 +2292,6 @@ static int loop_add(struct loop_device **l, int i) */ blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue); - err = -ENOMEM; - disk = lo->lo_disk = alloc_disk(1 << part_shift); - if (!disk) - goto out_free_queue; - /* * Disable partition scanning by default. The in-kernel partition * scanning can be requested individually per-device during its @@ -2153,8 +2317,10 @@ static int loop_add(struct loop_device **l, int i) mutex_init(&lo->lo_mutex); lo->lo_number = i; spin_lock_init(&lo->lo_lock); + spin_lock_init(&lo->lo_work_lock); disk->major = LOOP_MAJOR; disk->first_minor = i << part_shift; + disk->minors = 1 << part_shift; disk->fops = &lo_fops; disk->private_data = lo; disk->queue = lo->lo_queue; @@ -2163,8 +2329,6 @@ static int loop_add(struct loop_device **l, int i) *l = lo; return lo->lo_number; -out_free_queue: - blk_cleanup_queue(lo->lo_queue); out_cleanup_tags: blk_mq_free_tag_set(&lo->tag_set); out_free_idr: @@ -2178,9 +2342,8 @@ out: static void loop_remove(struct loop_device *lo) { del_gendisk(lo->lo_disk); - blk_cleanup_queue(lo->lo_queue); + blk_cleanup_disk(lo->lo_disk); blk_mq_free_tag_set(&lo->tag_set); - put_disk(lo->lo_disk); mutex_destroy(&lo->lo_mutex); kfree(lo); } diff --git a/drivers/block/loop.h b/drivers/block/loop.h index 5beb959b94d3..1988899db63a 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -14,7 +14,6 @@ #include #include #include -#include #include /* Possible states of device */ @@ -55,8 +54,13 @@ struct loop_device { spinlock_t lo_lock; int lo_state; - struct kthread_worker worker; - struct task_struct *worker_task; + spinlock_t lo_work_lock; + struct workqueue_struct *workqueue; + struct work_struct rootcg_work; + struct list_head rootcg_cmd_list; + struct list_head idle_worker_list; + struct rb_root worker_tree; + struct timer_list timer; bool use_dio; bool sysfs_inited; @@ -67,13 +71,14 @@ struct loop_device { }; struct loop_cmd { - struct kthread_work work; + struct list_head list_entry; bool use_aio; /* use AIO interface to handle I/O */ atomic_t ref; /* only for aio */ long ret; struct kiocb iocb; struct bio_vec *bvec; - struct cgroup_subsys_state *css; + struct cgroup_subsys_state *blkcg_css; + struct cgroup_subsys_state *memcg_css; }; /* Support for loadable transfer modules */ diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 589cb0f1e030..ff3e7b3f5ad8 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -2238,7 +2238,6 @@ static ssize_t show_device_status(struct device_driver *drv, char *buf) static ssize_t mtip_hw_read_device_status(struct file *f, char __user *ubuf, size_t len, loff_t *offset) { - struct driver_data *dd = (struct driver_data *)f->private_data; int size = *offset; char *buf; int rv = 0; @@ -2247,11 +2246,8 @@ static ssize_t mtip_hw_read_device_status(struct file *f, char __user *ubuf, return 0; buf = kzalloc(MTIP_DFS_MAX_BUF_SIZE, GFP_KERNEL); - if (!buf) { - dev_err(&dd->pdev->dev, - "Memory allocation: status buffer\n"); + if (!buf) return -ENOMEM; - } size += show_device_status(NULL, buf); @@ -2277,11 +2273,8 @@ static ssize_t mtip_hw_read_registers(struct file *f, char __user *ubuf, return 0; buf = kzalloc(MTIP_DFS_MAX_BUF_SIZE, GFP_KERNEL); - if (!buf) { - dev_err(&dd->pdev->dev, - "Memory allocation: register buffer\n"); + if (!buf) return -ENOMEM; - } size += sprintf(&buf[size], "H/ S ACTive : [ 0x"); @@ -2343,11 +2336,8 @@ static ssize_t mtip_hw_read_flags(struct file *f, char __user *ubuf, return 0; buf = kzalloc(MTIP_DFS_MAX_BUF_SIZE, GFP_KERNEL); - if (!buf) { - dev_err(&dd->pdev->dev, - "Memory allocation: flag buffer\n"); + if (!buf) return -ENOMEM; - } size += sprintf(&buf[size], "Flag-port : [ %08lX ]\n", dd->port->flags); @@ -2884,11 +2874,8 @@ static int mtip_hw_init(struct driver_data *dd) dd->port = kzalloc_node(sizeof(struct mtip_port), GFP_KERNEL, dd->numa_node); - if (!dd->port) { - dev_err(&dd->pdev->dev, - "Memory allocation: port structure\n"); + if (!dd->port) return -ENOMEM; - } /* Continue workqueue setup */ for (i = 0; i < MTIP_MAX_SLOT_GROUPS; i++) @@ -4002,11 +3989,8 @@ static int mtip_pci_probe(struct pci_dev *pdev, cpu_to_node(raw_smp_processor_id()), raw_smp_processor_id()); dd = kzalloc_node(sizeof(struct driver_data), GFP_KERNEL, my_node); - if (dd == NULL) { - dev_err(&pdev->dev, - "Unable to allocate memory for driver data\n"); + if (!dd) return -ENOMEM; - } /* Attach the private data to this PCI device. */ pci_set_drvdata(pdev, dd); diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c index 47bdf324e962..7b4dd10af9ec 100644 --- a/drivers/block/n64cart.c +++ b/drivers/block/n64cart.c @@ -132,16 +132,12 @@ static int __init n64cart_probe(struct platform_device *pdev) if (!reg_base) return -EINVAL; - disk = alloc_disk(0); + disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) return -ENOMEM; - disk->queue = blk_alloc_queue(NUMA_NO_NODE); - if (!disk->queue) - return -ENOMEM; - disk->first_minor = 0; - disk->flags = GENHD_FL_NO_PART_SCAN | GENHD_FL_EXT_DEVT; + disk->flags = GENHD_FL_NO_PART_SCAN; disk->fops = &n64cart_fops; disk->private_data = &pdev->dev; strcpy(disk->disk_name, "n64cart"); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 45d2c28c8fc8..614d82e7fae4 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -219,15 +219,11 @@ static const struct device_attribute pid_attr = { static void nbd_dev_remove(struct nbd_device *nbd) { struct gendisk *disk = nbd->disk; - struct request_queue *q; if (disk) { - q = disk->queue; del_gendisk(disk); - blk_cleanup_queue(q); blk_mq_free_tag_set(&nbd->tag_set); - disk->private_data = NULL; - put_disk(disk); + blk_cleanup_disk(disk); } /* @@ -1646,15 +1642,24 @@ static int nbd_dev_add(int index) { struct nbd_device *nbd; struct gendisk *disk; - struct request_queue *q; int err = -ENOMEM; nbd = kzalloc(sizeof(struct nbd_device), GFP_KERNEL); if (!nbd) goto out; - disk = alloc_disk(1 << part_shift); - if (!disk) + nbd->tag_set.ops = &nbd_mq_ops; + nbd->tag_set.nr_hw_queues = 1; + nbd->tag_set.queue_depth = 128; + nbd->tag_set.numa_node = NUMA_NO_NODE; + nbd->tag_set.cmd_size = sizeof(struct nbd_cmd); + nbd->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | + BLK_MQ_F_BLOCKING; + nbd->tag_set.driver_data = nbd; + nbd->destroy_complete = NULL; + + err = blk_mq_alloc_tag_set(&nbd->tag_set); + if (err) goto out_free_nbd; if (index >= 0) { @@ -1668,30 +1673,15 @@ static int nbd_dev_add(int index) index = err; } if (err < 0) - goto out_free_disk; - - nbd->index = index; - nbd->disk = disk; - nbd->tag_set.ops = &nbd_mq_ops; - nbd->tag_set.nr_hw_queues = 1; - nbd->tag_set.queue_depth = 128; - nbd->tag_set.numa_node = NUMA_NO_NODE; - nbd->tag_set.cmd_size = sizeof(struct nbd_cmd); - nbd->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | - BLK_MQ_F_BLOCKING; - nbd->tag_set.driver_data = nbd; - nbd->destroy_complete = NULL; - - err = blk_mq_alloc_tag_set(&nbd->tag_set); - if (err) - goto out_free_idr; - - q = blk_mq_init_queue(&nbd->tag_set); - if (IS_ERR(q)) { - err = PTR_ERR(q); goto out_free_tags; + nbd->index = index; + + disk = blk_mq_alloc_disk(&nbd->tag_set, NULL); + if (IS_ERR(disk)) { + err = PTR_ERR(disk); + goto out_free_idr; } - disk->queue = q; + nbd->disk = disk; /* * Tell the block layer that we are not a rotational device @@ -1712,6 +1702,7 @@ static int nbd_dev_add(int index) INIT_LIST_HEAD(&nbd->list); disk->major = NBD_MAJOR; disk->first_minor = index << part_shift; + disk->minors = 1 << part_shift; disk->fops = &nbd_fops; disk->private_data = nbd; sprintf(disk->disk_name, "nbd%d", index); @@ -1719,12 +1710,10 @@ static int nbd_dev_add(int index) nbd_total_devices++; return index; -out_free_tags: - blk_mq_free_tag_set(&nbd->tag_set); out_free_idr: idr_remove(&nbd_index_idr, index); -out_free_disk: - put_disk(disk); +out_free_tags: + blk_mq_free_tag_set(&nbd->tag_set); out_free_nbd: kfree(nbd); out: diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 5f006d9e1472..3b320b005aa8 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1597,11 +1597,10 @@ static void null_del_dev(struct nullb *nullb) null_restart_queue_async(nullb); } - blk_cleanup_queue(nullb->q); + blk_cleanup_disk(nullb->disk); if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set) blk_mq_free_tag_set(nullb->tag_set); - put_disk(nullb->disk); cleanup_queues(nullb); if (null_cache_active(nullb)) null_free_device_storage(nullb->dev, true); @@ -1700,22 +1699,19 @@ static int init_driver_queues(struct nullb *nullb) static int null_gendisk_register(struct nullb *nullb) { sector_t size = ((sector_t)nullb->dev->size * SZ_1M) >> SECTOR_SHIFT; - struct gendisk *disk; + struct gendisk *disk = nullb->disk; - disk = nullb->disk = alloc_disk_node(1, nullb->dev->home_node); - if (!disk) - return -ENOMEM; set_capacity(disk, size); disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO; disk->major = null_major; disk->first_minor = nullb->index; + disk->minors = 1; if (queue_is_mq(nullb->q)) disk->fops = &null_rq_ops; else disk->fops = &null_bio_ops; disk->private_data = nullb; - disk->queue = nullb->q; strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); if (nullb->dev->zoned) { @@ -1851,23 +1847,26 @@ static int null_add_dev(struct nullb_device *dev) goto out_cleanup_queues; if (!null_setup_fault()) - goto out_cleanup_queues; + goto out_cleanup_tags; + rv = -ENOMEM; nullb->tag_set->timeout = 5 * HZ; - nullb->q = blk_mq_init_queue_data(nullb->tag_set, nullb); - if (IS_ERR(nullb->q)) { - rv = -ENOMEM; + nullb->disk = blk_mq_alloc_disk(nullb->tag_set, nullb); + if (IS_ERR(nullb->disk)) { + rv = PTR_ERR(nullb->disk); goto out_cleanup_tags; } + nullb->q = nullb->disk->queue; } else if (dev->queue_mode == NULL_Q_BIO) { - nullb->q = blk_alloc_queue(dev->home_node); - if (!nullb->q) { - rv = -ENOMEM; + rv = -ENOMEM; + nullb->disk = blk_alloc_disk(nullb->dev->home_node); + if (!nullb->disk) goto out_cleanup_queues; - } + + nullb->q = nullb->disk->queue; rv = init_driver_queues(nullb); if (rv) - goto out_cleanup_blk_queue; + goto out_cleanup_disk; } if (dev->mbps) { @@ -1883,7 +1882,7 @@ static int null_add_dev(struct nullb_device *dev) if (dev->zoned) { rv = null_init_zoned_dev(dev, nullb->q); if (rv) - goto out_cleanup_blk_queue; + goto out_cleanup_disk; } nullb->q->queuedata = nullb; @@ -1921,8 +1920,8 @@ static int null_add_dev(struct nullb_device *dev) return 0; out_cleanup_zone: null_free_zoned_dev(dev); -out_cleanup_blk_queue: - blk_cleanup_queue(nullb->q); +out_cleanup_disk: + blk_cleanup_disk(nullb->disk); out_cleanup_tags: if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set) blk_mq_free_tag_set(nullb->tag_set); diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 70da8b86ce58..f9cdd11f02f5 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -309,21 +309,19 @@ static void pcd_init_units(void) pcd_drive_count = 0; for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { - struct gendisk *disk = alloc_disk(1); + struct gendisk *disk; - if (!disk) + if (blk_mq_alloc_sq_tag_set(&cd->tag_set, &pcd_mq_ops, 1, + BLK_MQ_F_SHOULD_MERGE)) continue; - disk->queue = blk_mq_init_sq_queue(&cd->tag_set, &pcd_mq_ops, - 1, BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(disk->queue)) { - disk->queue = NULL; - put_disk(disk); + disk = blk_mq_alloc_disk(&cd->tag_set, cd); + if (IS_ERR(disk)) { + blk_mq_free_tag_set(&cd->tag_set); continue; } INIT_LIST_HEAD(&cd->rq_list); - disk->queue->queuedata = cd; blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); cd->disk = disk; cd->pi = &cd->pia; @@ -343,6 +341,7 @@ static void pcd_init_units(void) cd->info.mask = 0; disk->major = major; disk->first_minor = unit; + disk->minors = 1; strcpy(disk->disk_name, cd->name); /* umm... */ disk->fops = &pcd_bdops; disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; @@ -759,10 +758,8 @@ static int pcd_detect(void) for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { if (!cd->disk) continue; - blk_cleanup_queue(cd->disk->queue); - cd->disk->queue = NULL; + blk_cleanup_disk(cd->disk); blk_mq_free_tag_set(&cd->tag_set); - put_disk(cd->disk); } pi_unregister_driver(par_drv); return -1; diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 828a45ffe0e7..3b2b8e872beb 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -879,18 +879,6 @@ static void pd_probe_drive(struct pd_unit *disk) { struct gendisk *p; - p = alloc_disk(1 << PD_BITS); - if (!p) - return; - - strcpy(p->disk_name, disk->name); - p->fops = &pd_fops; - p->major = major; - p->first_minor = (disk - pd) << PD_BITS; - p->events = DISK_EVENT_MEDIA_CHANGE; - disk->gd = p; - p->private_data = disk; - memset(&disk->tag_set, 0, sizeof(disk->tag_set)); disk->tag_set.ops = &pd_mq_ops; disk->tag_set.cmd_size = sizeof(struct pd_req); @@ -903,14 +891,21 @@ static void pd_probe_drive(struct pd_unit *disk) if (blk_mq_alloc_tag_set(&disk->tag_set)) return; - p->queue = blk_mq_init_queue(&disk->tag_set); - if (IS_ERR(p->queue)) { + p = blk_mq_alloc_disk(&disk->tag_set, disk); + if (!p) { blk_mq_free_tag_set(&disk->tag_set); - p->queue = NULL; return; } + disk->gd = p; + + strcpy(p->disk_name, disk->name); + p->fops = &pd_fops; + p->major = major; + p->first_minor = (disk - pd) << PD_BITS; + p->minors = 1 << PD_BITS; + p->events = DISK_EVENT_MEDIA_CHANGE; + p->private_data = disk; - p->queue->queuedata = disk; blk_queue_max_hw_sectors(p->queue, cluster); blk_queue_bounce_limit(p->queue, BLK_BOUNCE_HIGH); @@ -1019,9 +1014,8 @@ static void __exit pd_exit(void) if (p) { disk->gd = NULL; del_gendisk(p); - blk_cleanup_queue(p->queue); blk_mq_free_tag_set(&disk->tag_set); - put_disk(p); + blk_cleanup_disk(p); pi_release(disk->pi); } } diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index bb09f21ce21a..d5b9c88ba76f 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -294,20 +294,17 @@ static void __init pf_init_units(void) for (unit = 0, pf = units; unit < PF_UNITS; unit++, pf++) { struct gendisk *disk; - disk = alloc_disk(1); - if (!disk) + if (blk_mq_alloc_sq_tag_set(&pf->tag_set, &pf_mq_ops, 1, + BLK_MQ_F_SHOULD_MERGE)) continue; - disk->queue = blk_mq_init_sq_queue(&pf->tag_set, &pf_mq_ops, - 1, BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(disk->queue)) { - disk->queue = NULL; - put_disk(disk); + disk = blk_mq_alloc_disk(&pf->tag_set, pf); + if (IS_ERR(disk)) { + blk_mq_free_tag_set(&pf->tag_set); continue; } INIT_LIST_HEAD(&pf->rq_list); - disk->queue->queuedata = pf; blk_queue_max_segments(disk->queue, cluster); blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); pf->disk = disk; @@ -318,6 +315,7 @@ static void __init pf_init_units(void) snprintf(pf->name, PF_NAMELEN, "%s%d", name, unit); disk->major = major; disk->first_minor = unit; + disk->minors = 1; strcpy(disk->disk_name, pf->name); disk->fops = &pf_fops; disk->events = DISK_EVENT_MEDIA_CHANGE; @@ -766,10 +764,8 @@ static int pf_detect(void) for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) { if (!pf->disk) continue; - blk_cleanup_queue(pf->disk->queue); - pf->disk->queue = NULL; + blk_cleanup_disk(pf->disk); blk_mq_free_tag_set(&pf->tag_set); - put_disk(pf->disk); } pi_unregister_driver(par_drv); return -1; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index bd3556585122..f69b5c69c2a6 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2711,19 +2711,17 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) pd->write_congestion_off = write_congestion_off; ret = -ENOMEM; - disk = alloc_disk(1); + disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) goto out_mem; pd->disk = disk; disk->major = pktdev_major; disk->first_minor = idx; + disk->minors = 1; disk->fops = &pktcdvd_ops; disk->flags = GENHD_FL_REMOVABLE; strcpy(disk->disk_name, pd->name); disk->private_data = pd; - disk->queue = blk_alloc_queue(NUMA_NO_NODE); - if (!disk->queue) - goto out_mem2; pd->pkt_dev = MKDEV(pktdev_major, idx); ret = pkt_new_dev(pd, dev); @@ -2746,7 +2744,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) return 0; out_mem2: - put_disk(disk); + blk_cleanup_disk(disk); out_mem: mempool_exit(&pd->rb_pool); kfree(pd); @@ -2796,8 +2794,7 @@ static int pkt_remove_dev(dev_t pkt_dev) pkt_dbg(1, pd, "writer unmapped\n"); del_gendisk(pd->disk); - blk_cleanup_queue(pd->disk->queue); - put_disk(pd->disk); + blk_cleanup_disk(pd->disk); mempool_exit(&pd->rb_pool); kfree(pd); diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index ba3ece56cbb3..f374ea2c67ce 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -29,7 +29,6 @@ struct ps3disk_private { spinlock_t lock; /* Request queue spinlock */ - struct request_queue *queue; struct blk_mq_tag_set tag_set; struct gendisk *gendisk; unsigned int blocking_factor; @@ -267,7 +266,7 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data) blk_mq_end_request(req, error); spin_unlock(&priv->lock); - blk_mq_run_hw_queues(priv->queue, true); + blk_mq_run_hw_queues(priv->gendisk->queue, true); return IRQ_HANDLED; } @@ -441,17 +440,20 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) ps3disk_identify(dev); - queue = blk_mq_init_sq_queue(&priv->tag_set, &ps3disk_mq_ops, 1, + error = blk_mq_alloc_sq_tag_set(&priv->tag_set, &ps3disk_mq_ops, 1, BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(queue)) { - dev_err(&dev->sbd.core, "%s:%u: blk_mq_init_queue failed\n", - __func__, __LINE__); - error = PTR_ERR(queue); + if (error) goto fail_teardown; + + gendisk = blk_mq_alloc_disk(&priv->tag_set, dev); + if (IS_ERR(gendisk)) { + dev_err(&dev->sbd.core, "%s:%u: blk_mq_alloc_disk failed\n", + __func__, __LINE__); + error = PTR_ERR(gendisk); + goto fail_free_tag_set; } - priv->queue = queue; - queue->queuedata = dev; + queue = gendisk->queue; blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9); blk_queue_dma_alignment(queue, dev->blk_size-1); @@ -462,19 +464,11 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) blk_queue_max_segments(queue, -1); blk_queue_max_segment_size(queue, dev->bounce_size); - gendisk = alloc_disk(PS3DISK_MINORS); - if (!gendisk) { - dev_err(&dev->sbd.core, "%s:%u: alloc_disk failed\n", __func__, - __LINE__); - error = -ENOMEM; - goto fail_cleanup_queue; - } - priv->gendisk = gendisk; gendisk->major = ps3disk_major; gendisk->first_minor = devidx * PS3DISK_MINORS; + gendisk->minors = PS3DISK_MINORS; gendisk->fops = &ps3disk_fops; - gendisk->queue = queue; gendisk->private_data = dev; snprintf(gendisk->disk_name, sizeof(gendisk->disk_name), PS3DISK_NAME, devidx+'a'); @@ -490,8 +484,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) device_add_disk(&dev->sbd.core, gendisk, NULL); return 0; -fail_cleanup_queue: - blk_cleanup_queue(queue); +fail_free_tag_set: blk_mq_free_tag_set(&priv->tag_set); fail_teardown: ps3stor_teardown(dev); @@ -517,9 +510,8 @@ static void ps3disk_remove(struct ps3_system_bus_device *_dev) &ps3disk_mask); mutex_unlock(&ps3disk_mask_mutex); del_gendisk(priv->gendisk); - blk_cleanup_queue(priv->queue); + blk_cleanup_disk(priv->gendisk); blk_mq_free_tag_set(&priv->tag_set); - put_disk(priv->gendisk); dev_notice(&dev->sbd.core, "Synchronizing disk cache\n"); ps3disk_sync_cache(dev); ps3stor_teardown(dev); diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index 1d738999fb69..7fbf469651c4 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -67,7 +67,6 @@ struct ps3vram_cache { }; struct ps3vram_priv { - struct request_queue *queue; struct gendisk *gendisk; u64 size; @@ -613,7 +612,6 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev) { struct ps3vram_priv *priv; int error, status; - struct request_queue *queue; struct gendisk *gendisk; u64 ddr_size, ddr_lpar, ctrl_lpar, info_lpar, reports_lpar, reports_size, xdr_lpar; @@ -736,33 +734,23 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev) ps3vram_proc_init(dev); - queue = blk_alloc_queue(NUMA_NO_NODE); - if (!queue) { - dev_err(&dev->core, "blk_alloc_queue failed\n"); + gendisk = blk_alloc_disk(NUMA_NO_NODE); + if (!gendisk) { + dev_err(&dev->core, "blk_alloc_disk failed\n"); error = -ENOMEM; goto out_cache_cleanup; } - priv->queue = queue; - blk_queue_max_segments(queue, BLK_MAX_SEGMENTS); - blk_queue_max_segment_size(queue, BLK_MAX_SEGMENT_SIZE); - blk_queue_max_hw_sectors(queue, BLK_SAFE_MAX_SECTORS); - - gendisk = alloc_disk(1); - if (!gendisk) { - dev_err(&dev->core, "alloc_disk failed\n"); - error = -ENOMEM; - goto fail_cleanup_queue; - } - priv->gendisk = gendisk; gendisk->major = ps3vram_major; - gendisk->first_minor = 0; + gendisk->minors = 1; gendisk->fops = &ps3vram_fops; - gendisk->queue = queue; gendisk->private_data = dev; strlcpy(gendisk->disk_name, DEVICE_NAME, sizeof(gendisk->disk_name)); set_capacity(gendisk, priv->size >> 9); + blk_queue_max_segments(gendisk->queue, BLK_MAX_SEGMENTS); + blk_queue_max_segment_size(gendisk->queue, BLK_MAX_SEGMENT_SIZE); + blk_queue_max_hw_sectors(gendisk->queue, BLK_SAFE_MAX_SECTORS); dev_info(&dev->core, "%s: Using %llu MiB of GPU memory\n", gendisk->disk_name, get_capacity(gendisk) >> 11); @@ -770,8 +758,6 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev) device_add_disk(&dev->core, gendisk, NULL); return 0; -fail_cleanup_queue: - blk_cleanup_queue(queue); out_cache_cleanup: remove_proc_entry(DEVICE_NAME, NULL); ps3vram_cache_cleanup(dev); @@ -802,8 +788,7 @@ static void ps3vram_remove(struct ps3_system_bus_device *dev) struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev); del_gendisk(priv->gendisk); - put_disk(priv->gendisk); - blk_cleanup_queue(priv->queue); + blk_cleanup_disk(priv->gendisk); remove_proc_entry(DEVICE_NAME, NULL); ps3vram_cache_cleanup(dev); iounmap(priv->reports); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index bbb88eb009e0..531d390902dd 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4750,9 +4750,8 @@ static blk_status_t rbd_queue_rq(struct blk_mq_hw_ctx *hctx, static void rbd_free_disk(struct rbd_device *rbd_dev) { - blk_cleanup_queue(rbd_dev->disk->queue); + blk_cleanup_disk(rbd_dev->disk); blk_mq_free_tag_set(&rbd_dev->tag_set); - put_disk(rbd_dev->disk); rbd_dev->disk = NULL; } @@ -4922,22 +4921,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) rbd_dev->layout.object_size * rbd_dev->layout.stripe_count; int err; - /* create gendisk info */ - disk = alloc_disk(single_major ? - (1 << RBD_SINGLE_MAJOR_PART_SHIFT) : - RBD_MINORS_PER_MAJOR); - if (!disk) - return -ENOMEM; - - snprintf(disk->disk_name, sizeof(disk->disk_name), RBD_DRV_NAME "%d", - rbd_dev->dev_id); - disk->major = rbd_dev->major; - disk->first_minor = rbd_dev->minor; - if (single_major) - disk->flags |= GENHD_FL_EXT_DEVT; - disk->fops = &rbd_bd_ops; - disk->private_data = rbd_dev; - memset(&rbd_dev->tag_set, 0, sizeof(rbd_dev->tag_set)); rbd_dev->tag_set.ops = &rbd_mq_ops; rbd_dev->tag_set.queue_depth = rbd_dev->opts->queue_depth; @@ -4948,13 +4931,26 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) err = blk_mq_alloc_tag_set(&rbd_dev->tag_set); if (err) - goto out_disk; + return err; - q = blk_mq_init_queue(&rbd_dev->tag_set); - if (IS_ERR(q)) { - err = PTR_ERR(q); + disk = blk_mq_alloc_disk(&rbd_dev->tag_set, rbd_dev); + if (IS_ERR(disk)) { + err = PTR_ERR(disk); goto out_tag_set; } + q = disk->queue; + + snprintf(disk->disk_name, sizeof(disk->disk_name), RBD_DRV_NAME "%d", + rbd_dev->dev_id); + disk->major = rbd_dev->major; + disk->first_minor = rbd_dev->minor; + if (single_major) { + disk->minors = (1 << RBD_SINGLE_MAJOR_PART_SHIFT); + disk->flags |= GENHD_FL_EXT_DEVT; + } else { + disk->minors = RBD_MINORS_PER_MAJOR; + } + disk->fops = &rbd_bd_ops; blk_queue_flag_set(QUEUE_FLAG_NONROT, q); /* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */ @@ -4976,21 +4972,11 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC)) blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q); - /* - * disk_release() expects a queue ref from add_disk() and will - * put it. Hold an extra ref until add_disk() is called. - */ - WARN_ON(!blk_get_queue(q)); - disk->queue = q; - q->queuedata = rbd_dev; - rbd_dev->disk = disk; return 0; out_tag_set: blk_mq_free_tag_set(&rbd_dev->tag_set); -out_disk: - put_disk(disk); return err; } @@ -7088,8 +7074,6 @@ static ssize_t do_rbd_add(struct bus_type *bus, goto err_out_image_lock; device_add_disk(&rbd_dev->dev, rbd_dev->disk, NULL); - /* see rbd_init_disk() */ - blk_put_queue(rbd_dev->disk->queue); spin_lock(&rbd_dev_list_lock); list_add_tail(&rbd_dev->node, &rbd_dev_list); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index c604a402cd5c..f4fa45d24c0b 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1353,18 +1353,6 @@ static void rnbd_init_mq_hw_queues(struct rnbd_clt_dev *dev) } } -static int setup_mq_dev(struct rnbd_clt_dev *dev) -{ - dev->queue = blk_mq_init_queue(&dev->sess->tag_set); - if (IS_ERR(dev->queue)) { - rnbd_clt_err(dev, "Initializing multiqueue queue failed, err: %ld\n", - PTR_ERR(dev->queue)); - return PTR_ERR(dev->queue); - } - rnbd_init_mq_hw_queues(dev); - return 0; -} - static void setup_request_queue(struct rnbd_clt_dev *dev) { blk_queue_logical_block_size(dev->queue, dev->logical_block_size); @@ -1393,13 +1381,13 @@ static void setup_request_queue(struct rnbd_clt_dev *dev) blk_queue_io_opt(dev->queue, dev->sess->max_io_size); blk_queue_virt_boundary(dev->queue, SZ_4K - 1); blk_queue_write_cache(dev->queue, dev->wc, dev->fua); - dev->queue->queuedata = dev; } static void rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) { dev->gd->major = rnbd_client_major; dev->gd->first_minor = idx << RNBD_PART_BITS; + dev->gd->minors = 1 << RNBD_PART_BITS; dev->gd->fops = &rnbd_client_ops; dev->gd->queue = dev->queue; dev->gd->private_data = dev; @@ -1426,24 +1414,18 @@ static void rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) static int rnbd_client_setup_device(struct rnbd_clt_dev *dev) { - int err, idx = dev->clt_device_id; + int idx = dev->clt_device_id; dev->size = dev->nsectors * dev->logical_block_size; - err = setup_mq_dev(dev); - if (err) - return err; + dev->gd = blk_mq_alloc_disk(&dev->sess->tag_set, dev); + if (IS_ERR(dev->gd)) + return PTR_ERR(dev->gd); + dev->queue = dev->gd->queue; + rnbd_init_mq_hw_queues(dev); setup_request_queue(dev); - - dev->gd = alloc_disk_node(1 << RNBD_PART_BITS, NUMA_NO_NODE); - if (!dev->gd) { - blk_cleanup_queue(dev->queue); - return -ENOMEM; - } - rnbd_clt_setup_gen_disk(dev, idx); - return 0; } @@ -1650,8 +1632,7 @@ put_sess: static void destroy_gen_disk(struct rnbd_clt_dev *dev) { del_gendisk(dev->gd); - blk_cleanup_queue(dev->queue); - put_disk(dev->gd); + blk_cleanup_disk(dev->gd); } static void destroy_sysfs(struct rnbd_clt_dev *dev, diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c index 9a28322a8cd8..1cc40b0ea761 100644 --- a/drivers/block/rsxx/dev.c +++ b/drivers/block/rsxx/dev.c @@ -236,47 +236,40 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card) return -ENOMEM; } - card->queue = blk_alloc_queue(NUMA_NO_NODE); - if (!card->queue) { - dev_err(CARD_TO_DEV(card), "Failed queue alloc\n"); - unregister_blkdev(card->major, DRIVER_NAME); - return -ENOMEM; - } - - card->gendisk = alloc_disk(blkdev_minors); + card->gendisk = blk_alloc_disk(blkdev_minors); if (!card->gendisk) { dev_err(CARD_TO_DEV(card), "Failed disk alloc\n"); - blk_cleanup_queue(card->queue); unregister_blkdev(card->major, DRIVER_NAME); return -ENOMEM; } if (card->config_valid) { blk_size = card->config.data.block_size; - blk_queue_dma_alignment(card->queue, blk_size - 1); - blk_queue_logical_block_size(card->queue, blk_size); + blk_queue_dma_alignment(card->gendisk->queue, blk_size - 1); + blk_queue_logical_block_size(card->gendisk->queue, blk_size); } - blk_queue_max_hw_sectors(card->queue, blkdev_max_hw_sectors); - blk_queue_physical_block_size(card->queue, RSXX_HW_BLK_SIZE); + blk_queue_max_hw_sectors(card->gendisk->queue, blkdev_max_hw_sectors); + blk_queue_physical_block_size(card->gendisk->queue, RSXX_HW_BLK_SIZE); - blk_queue_flag_set(QUEUE_FLAG_NONROT, card->queue); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, card->queue); + blk_queue_flag_set(QUEUE_FLAG_NONROT, card->gendisk->queue); + blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, card->gendisk->queue); if (rsxx_discard_supported(card)) { - blk_queue_flag_set(QUEUE_FLAG_DISCARD, card->queue); - blk_queue_max_discard_sectors(card->queue, + blk_queue_flag_set(QUEUE_FLAG_DISCARD, card->gendisk->queue); + blk_queue_max_discard_sectors(card->gendisk->queue, RSXX_HW_BLK_SIZE >> 9); - card->queue->limits.discard_granularity = RSXX_HW_BLK_SIZE; - card->queue->limits.discard_alignment = RSXX_HW_BLK_SIZE; + card->gendisk->queue->limits.discard_granularity = + RSXX_HW_BLK_SIZE; + card->gendisk->queue->limits.discard_alignment = + RSXX_HW_BLK_SIZE; } snprintf(card->gendisk->disk_name, sizeof(card->gendisk->disk_name), "rsxx%d", card->disk_id); card->gendisk->major = card->major; - card->gendisk->first_minor = 0; + card->gendisk->minors = blkdev_minors; card->gendisk->fops = &rsxx_fops; card->gendisk->private_data = card; - card->gendisk->queue = card->queue; return 0; } @@ -286,10 +279,8 @@ void rsxx_destroy_dev(struct rsxx_cardinfo *card) if (!enable_blkdev) return; - put_disk(card->gendisk); + blk_cleanup_disk(card->gendisk); card->gendisk = NULL; - - blk_cleanup_queue(card->queue); unregister_blkdev(card->major, DRIVER_NAME); } diff --git a/drivers/block/rsxx/dma.c b/drivers/block/rsxx/dma.c index 0574f4495755..ed182f3dd054 100644 --- a/drivers/block/rsxx/dma.c +++ b/drivers/block/rsxx/dma.c @@ -74,9 +74,6 @@ struct dma_tracker { struct rsxx_dma *dma; }; -#define DMA_TRACKER_LIST_SIZE8 (sizeof(struct dma_tracker_list) + \ - (sizeof(struct dma_tracker) * RSXX_MAX_OUTSTANDING_CMDS)) - struct dma_tracker_list { spinlock_t lock; int head; @@ -808,7 +805,8 @@ static int rsxx_dma_ctrl_init(struct pci_dev *dev, memset(&ctrl->stats, 0, sizeof(ctrl->stats)); - ctrl->trackers = vmalloc(DMA_TRACKER_LIST_SIZE8); + ctrl->trackers = vmalloc(struct_size(ctrl->trackers, list, + RSXX_MAX_OUTSTANDING_CMDS)); if (!ctrl->trackers) return -ENOMEM; diff --git a/drivers/block/rsxx/rsxx_priv.h b/drivers/block/rsxx/rsxx_priv.h index 6147977994ff..26c320c0d924 100644 --- a/drivers/block/rsxx/rsxx_priv.h +++ b/drivers/block/rsxx/rsxx_priv.h @@ -154,7 +154,6 @@ struct rsxx_cardinfo { bool bdev_attached; int disk_id; int major; - struct request_queue *queue; struct gendisk *gendisk; struct { /* Used to convert a byte address to a device address. */ diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 39aeebc6837d..c4631e684386 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -780,27 +780,6 @@ static const struct blk_mq_ops vdc_mq_ops = { .queue_rq = vdc_queue_rq, }; -static void cleanup_queue(struct request_queue *q) -{ - struct vdc_port *port = q->queuedata; - - blk_cleanup_queue(q); - blk_mq_free_tag_set(&port->tag_set); -} - -static struct request_queue *init_queue(struct vdc_port *port) -{ - struct request_queue *q; - - q = blk_mq_init_sq_queue(&port->tag_set, &vdc_mq_ops, VDC_TX_RING_SIZE, - BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(q)) - return q; - - q->queuedata = port; - return q; -} - static int probe_disk(struct vdc_port *port) { struct request_queue *q; @@ -838,21 +817,21 @@ static int probe_disk(struct vdc_port *port) (u64)geom.num_sec); } - q = init_queue(port); - if (IS_ERR(q)) { - printk(KERN_ERR PFX "%s: Could not allocate queue.\n", - port->vio.name); - return PTR_ERR(q); - } - g = alloc_disk(1 << PARTITION_SHIFT); - if (!g) { + err = blk_mq_alloc_sq_tag_set(&port->tag_set, &vdc_mq_ops, + VDC_TX_RING_SIZE, BLK_MQ_F_SHOULD_MERGE); + if (err) + return err; + + g = blk_mq_alloc_disk(&port->tag_set, port); + if (IS_ERR(g)) { printk(KERN_ERR PFX "%s: Could not allocate gendisk.\n", port->vio.name); - cleanup_queue(q); - return -ENOMEM; + blk_mq_free_tag_set(&port->tag_set); + return PTR_ERR(g); } port->disk = g; + q = g->queue; /* Each segment in a request is up to an aligned page in size. */ blk_queue_segment_boundary(q, PAGE_SIZE - 1); @@ -862,6 +841,7 @@ static int probe_disk(struct vdc_port *port) blk_queue_max_hw_sectors(q, port->max_xfer_size); g->major = vdc_major; g->first_minor = port->vio.vdev->dev_no << PARTITION_SHIFT; + g->minors = 1 << PARTITION_SHIFT; strcpy(g->disk_name, port->disk_name); g->fops = &vdc_fops; @@ -1001,9 +981,8 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) } port = kzalloc(sizeof(*port), GFP_KERNEL); - err = -ENOMEM; if (!port) { - printk(KERN_ERR PFX "Cannot allocate vdc_port.\n"); + err = -ENOMEM; goto err_out_release_mdesc; } @@ -1083,9 +1062,8 @@ static int vdc_port_remove(struct vio_dev *vdev) del_timer_sync(&port->vio.timer); del_gendisk(port->disk); - cleanup_queue(port->disk->queue); - put_disk(port->disk); - port->disk = NULL; + blk_cleanup_disk(port->disk); + blk_mq_free_tag_set(&port->tag_set); vdc_free_tx_ring(port); vio_ldc_free(&port->vio); diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 2917b21f48ff..7ccc8d2a41bc 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -800,23 +800,20 @@ static int swim_floppy_init(struct swim_priv *swd) spin_lock_init(&swd->lock); for (drive = 0; drive < swd->floppy_count; drive++) { - struct request_queue *q; + err = blk_mq_alloc_sq_tag_set(&swd->unit[drive].tag_set, + &swim_mq_ops, 2, BLK_MQ_F_SHOULD_MERGE); + if (err) + goto exit_put_disks; - swd->unit[drive].disk = alloc_disk(1); - if (swd->unit[drive].disk == NULL) { - err = -ENOMEM; + swd->unit[drive].disk = + blk_mq_alloc_disk(&swd->unit[drive].tag_set, + &swd->unit[drive]); + if (IS_ERR(swd->unit[drive].disk)) { + blk_mq_free_tag_set(&swd->unit[drive].tag_set); + err = PTR_ERR(swd->unit[drive].disk); goto exit_put_disks; } - q = blk_mq_init_sq_queue(&swd->unit[drive].tag_set, &swim_mq_ops, - 2, BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(q)) { - err = PTR_ERR(q); - goto exit_put_disks; - } - - swd->unit[drive].disk->queue = q; - swd->unit[drive].disk->queue->queuedata = &swd->unit[drive]; swd->unit[drive].swd = swd; } @@ -824,6 +821,7 @@ static int swim_floppy_init(struct swim_priv *swd) swd->unit[drive].disk->flags = GENHD_FL_REMOVABLE; swd->unit[drive].disk->major = FLOPPY_MAJOR; swd->unit[drive].disk->first_minor = drive; + swd->unit[drive].disk->minors = 1; sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive); swd->unit[drive].disk->fops = &floppy_fops; swd->unit[drive].disk->events = DISK_EVENT_MEDIA_CHANGE; @@ -839,14 +837,10 @@ exit_put_disks: do { struct gendisk *disk = swd->unit[drive].disk; - if (disk) { - if (disk->queue) { - blk_cleanup_queue(disk->queue); - disk->queue = NULL; - } - blk_mq_free_tag_set(&swd->unit[drive].tag_set); - put_disk(disk); - } + if (!disk) + continue; + blk_cleanup_disk(disk); + blk_mq_free_tag_set(&swd->unit[drive].tag_set); } while (drive--); return err; } diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index a515d0c1d2cb..965af0a3e95b 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -1202,30 +1202,27 @@ static int swim3_attach(struct macio_dev *mdev, return rc; } - disk = alloc_disk(1); - if (disk == NULL) { - rc = -ENOMEM; - goto out_unregister; - } - fs = &floppy_states[floppy_count]; memset(fs, 0, sizeof(*fs)); - disk->queue = blk_mq_init_sq_queue(&fs->tag_set, &swim3_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(disk->queue)) { - rc = PTR_ERR(disk->queue); - disk->queue = NULL; - goto out_put_disk; + rc = blk_mq_alloc_sq_tag_set(&fs->tag_set, &swim3_mq_ops, 2, + BLK_MQ_F_SHOULD_MERGE); + if (rc) + goto out_unregister; + + disk = blk_mq_alloc_disk(&fs->tag_set, fs); + if (IS_ERR(disk)) { + rc = PTR_ERR(disk); + goto out_free_tag_set; } - disk->queue->queuedata = fs; rc = swim3_add_device(mdev, floppy_count); if (rc) - goto out_cleanup_queue; + goto out_cleanup_disk; disk->major = FLOPPY_MAJOR; disk->first_minor = floppy_count; + disk->minors = 1; disk->fops = &floppy_fops; disk->private_data = fs; disk->events = DISK_EVENT_MEDIA_CHANGE; @@ -1237,12 +1234,10 @@ static int swim3_attach(struct macio_dev *mdev, disks[floppy_count++] = disk; return 0; -out_cleanup_queue: - blk_cleanup_queue(disk->queue); - disk->queue = NULL; +out_cleanup_disk: + blk_cleanup_disk(disk); +out_free_tag_set: blk_mq_free_tag_set(&fs->tag_set); -out_put_disk: - put_disk(disk); out_unregister: if (floppy_count == 0) unregister_blkdev(FLOPPY_MAJOR, "fd"); diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c index 2cdf2771f8e8..7b54353ee92b 100644 --- a/drivers/block/sx8.c +++ b/drivers/block/sx8.c @@ -1343,32 +1343,25 @@ static int carm_init_disk(struct carm_host *host, unsigned int port_no) { struct carm_port *port = &host->port[port_no]; struct gendisk *disk; - struct request_queue *q; port->host = host; port->port_no = port_no; - disk = alloc_disk(CARM_MINORS_PER_MAJOR); - if (!disk) - return -ENOMEM; + disk = blk_mq_alloc_disk(&host->tag_set, port); + if (IS_ERR(disk)) + return PTR_ERR(disk); port->disk = disk; sprintf(disk->disk_name, DRV_NAME "/%u", (unsigned int)host->id * CARM_MAX_PORTS + port_no); disk->major = host->major; disk->first_minor = port_no * CARM_MINORS_PER_MAJOR; + disk->minors = CARM_MINORS_PER_MAJOR; disk->fops = &carm_bd_ops; disk->private_data = port; - q = blk_mq_init_queue(&host->tag_set); - if (IS_ERR(q)) - return PTR_ERR(q); - - blk_queue_max_segments(q, CARM_MAX_REQ_SG); - blk_queue_segment_boundary(q, CARM_SG_BOUNDARY); - - q->queuedata = port; - disk->queue = q; + blk_queue_max_segments(disk->queue, CARM_MAX_REQ_SG); + blk_queue_segment_boundary(disk->queue, CARM_SG_BOUNDARY); return 0; } @@ -1382,9 +1375,7 @@ static void carm_free_disk(struct carm_host *host, unsigned int port_no) if (disk->flags & GENHD_FL_UP) del_gendisk(disk); - if (disk->queue) - blk_cleanup_queue(disk->queue); - put_disk(disk); + blk_cleanup_disk(disk); } static int carm_init_shm(struct carm_host *host) @@ -1429,8 +1420,6 @@ static int carm_init_one (struct pci_dev *pdev, const struct pci_device_id *ent) host = kzalloc(sizeof(*host), GFP_KERNEL); if (!host) { - printk(KERN_ERR DRV_NAME "(%s): memory alloc failure\n", - pci_name(pdev)); rc = -ENOMEM; goto err_out_regions; } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index fdfe8887332d..b1dcff284b38 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -751,13 +751,6 @@ static int virtblk_probe(struct virtio_device *vdev) if (err) goto out_free_vblk; - /* FIXME: How many partitions? How long is a piece of string? */ - vblk->disk = alloc_disk(1 << PART_BITS); - if (!vblk->disk) { - err = -ENOMEM; - goto out_free_vq; - } - /* Default queue sizing is to fill the ring. */ if (likely(!virtblk_queue_depth)) { queue_depth = vblk->vqs[0].vq->num_free; @@ -781,21 +774,20 @@ static int virtblk_probe(struct virtio_device *vdev) err = blk_mq_alloc_tag_set(&vblk->tag_set); if (err) - goto out_put_disk; + goto out_free_vq; - q = blk_mq_init_queue(&vblk->tag_set); - if (IS_ERR(q)) { - err = -ENOMEM; + vblk->disk = blk_mq_alloc_disk(&vblk->tag_set, vblk); + if (IS_ERR(vblk->disk)) { + err = PTR_ERR(vblk->disk); goto out_free_tags; } - vblk->disk->queue = q; - - q->queuedata = vblk; + q = vblk->disk->queue; virtblk_name_format("vd", index, vblk->disk->disk_name, DISK_NAME_LEN); vblk->disk->major = major; vblk->disk->first_minor = index_to_minor(index); + vblk->disk->minors = 1 << PART_BITS; vblk->disk->private_data = vblk; vblk->disk->fops = &virtblk_fops; vblk->disk->flags |= GENHD_FL_EXT_DEVT; @@ -894,8 +886,6 @@ static int virtblk_probe(struct virtio_device *vdev) out_free_tags: blk_mq_free_tag_set(&vblk->tag_set); -out_put_disk: - put_disk(vblk->disk); out_free_vq: vdev->config->del_vqs(vdev); kfree(vblk->vqs); @@ -915,8 +905,7 @@ static void virtblk_remove(struct virtio_device *vdev) flush_work(&vblk->config_work); del_gendisk(vblk->disk); - blk_cleanup_queue(vblk->disk->queue); - + blk_cleanup_disk(vblk->disk); blk_mq_free_tag_set(&vblk->tag_set); mutex_lock(&vblk->vdev_mutex); @@ -927,7 +916,6 @@ static void virtblk_remove(struct virtio_device *vdev) /* Virtqueues are stopped, nothing can use vblk->vdev anymore. */ vblk->vdev = NULL; - put_disk(vblk->disk); vdev->config->del_vqs(vdev); kfree(vblk->vqs); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 10df39a8b18d..8d49f8fa98bb 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -968,48 +968,6 @@ static void blkif_set_queue_limits(struct blkfront_info *info) blk_queue_dma_alignment(rq, 511); } -static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, - unsigned int physical_sector_size) -{ - struct request_queue *rq; - struct blkfront_info *info = gd->private_data; - - memset(&info->tag_set, 0, sizeof(info->tag_set)); - info->tag_set.ops = &blkfront_mq_ops; - info->tag_set.nr_hw_queues = info->nr_rings; - if (HAS_EXTRA_REQ && info->max_indirect_segments == 0) { - /* - * When indirect descriptior is not supported, the I/O request - * will be split between multiple request in the ring. - * To avoid problems when sending the request, divide by - * 2 the depth of the queue. - */ - info->tag_set.queue_depth = BLK_RING_SIZE(info) / 2; - } else - info->tag_set.queue_depth = BLK_RING_SIZE(info); - info->tag_set.numa_node = NUMA_NO_NODE; - info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; - info->tag_set.cmd_size = sizeof(struct blkif_req); - info->tag_set.driver_data = info; - - if (blk_mq_alloc_tag_set(&info->tag_set)) - return -EINVAL; - rq = blk_mq_init_queue(&info->tag_set); - if (IS_ERR(rq)) { - blk_mq_free_tag_set(&info->tag_set); - return PTR_ERR(rq); - } - - rq->queuedata = info; - info->rq = gd->queue = rq; - info->gd = gd; - info->sector_size = sector_size; - info->physical_sector_size = physical_sector_size; - blkif_set_queue_limits(info); - - return 0; -} - static const char *flush_info(struct blkfront_info *info) { if (info->feature_flush && info->feature_fua) @@ -1146,12 +1104,36 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, err = xlbd_reserve_minors(minor, nr_minors); if (err) - goto out; + return err; err = -ENODEV; - gd = alloc_disk(nr_minors); - if (gd == NULL) - goto release; + memset(&info->tag_set, 0, sizeof(info->tag_set)); + info->tag_set.ops = &blkfront_mq_ops; + info->tag_set.nr_hw_queues = info->nr_rings; + if (HAS_EXTRA_REQ && info->max_indirect_segments == 0) { + /* + * When indirect descriptior is not supported, the I/O request + * will be split between multiple request in the ring. + * To avoid problems when sending the request, divide by + * 2 the depth of the queue. + */ + info->tag_set.queue_depth = BLK_RING_SIZE(info) / 2; + } else + info->tag_set.queue_depth = BLK_RING_SIZE(info); + info->tag_set.numa_node = NUMA_NO_NODE; + info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; + info->tag_set.cmd_size = sizeof(struct blkif_req); + info->tag_set.driver_data = info; + + err = blk_mq_alloc_tag_set(&info->tag_set); + if (err) + goto out_release_minors; + + gd = blk_mq_alloc_disk(&info->tag_set, info); + if (IS_ERR(gd)) { + err = PTR_ERR(gd); + goto out_free_tag_set; + } strcpy(gd->disk_name, DEV_NAME); ptr = encode_disk_name(gd->disk_name + sizeof(DEV_NAME) - 1, offset); @@ -1164,14 +1146,16 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, gd->major = XENVBD_MAJOR; gd->first_minor = minor; + gd->minors = nr_minors; gd->fops = &xlvbd_block_fops; gd->private_data = info; set_capacity(gd, capacity); - if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size)) { - del_gendisk(gd); - goto release; - } + info->rq = gd->queue; + info->gd = gd; + info->sector_size = sector_size; + info->physical_sector_size = physical_sector_size; + blkif_set_queue_limits(info); xlvbd_flush(info); @@ -1186,9 +1170,10 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, return 0; - release: +out_free_tag_set: + blk_mq_free_tag_set(&info->tag_set); +out_release_minors: xlbd_release_minors(minor, nr_minors); - out: return err; } @@ -1217,12 +1202,9 @@ static void xlvbd_release_gendisk(struct blkfront_info *info) nr_minors = info->gd->minors; xlbd_release_minors(minor, nr_minors); - blk_cleanup_queue(info->rq); - blk_mq_free_tag_set(&info->tag_set); - info->rq = NULL; - - put_disk(info->gd); + blk_cleanup_disk(info->gd); info->gd = NULL; + blk_mq_free_tag_set(&info->tag_set); } /* Already hold rinfo->ring_lock. */ @@ -2163,7 +2145,7 @@ static void blkfront_closing(struct blkfront_info *info) return; } - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); if (bdev->bd_openers) { xenbus_dev_error(xbdev, -EBUSY, @@ -2174,7 +2156,7 @@ static void blkfront_closing(struct blkfront_info *info) xenbus_frontend_closed(xbdev); } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); bdput(bdev); } @@ -2531,7 +2513,7 @@ static int blkfront_remove(struct xenbus_device *xbdev) * isn't closed yet, we let release take care of it. */ - mutex_lock(&bdev->bd_mutex); + mutex_lock(&disk->open_mutex); info = disk->private_data; dev_warn(disk_to_dev(disk), @@ -2546,7 +2528,7 @@ static int blkfront_remove(struct xenbus_device *xbdev) mutex_unlock(&blkfront_mutex); } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&disk->open_mutex); bdput(bdev); return 0; diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index c1d20818e649..4eef218108c6 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -236,11 +236,8 @@ static int z2_open(struct block_device *bdev, fmode_t mode) case Z2MINOR_Z2ONLY: z2ram_map = kmalloc(max_z2_map, GFP_KERNEL); - if (z2ram_map == NULL) { - printk(KERN_ERR DEVICE_NAME - ": cannot get mem for z2ram_map\n"); + if (!z2ram_map) goto err_out; - } get_z2ram(); @@ -253,11 +250,8 @@ static int z2_open(struct block_device *bdev, fmode_t mode) case Z2MINOR_CHIPONLY: z2ram_map = kmalloc(max_chip_map, GFP_KERNEL); - if (z2ram_map == NULL) { - printk(KERN_ERR DEVICE_NAME - ": cannot get mem for z2ram_map\n"); + if (!z2ram_map) goto err_out; - } get_chipram(); @@ -323,27 +317,20 @@ static const struct blk_mq_ops z2_mq_ops = { static int z2ram_register_disk(int minor) { - struct request_queue *q; struct gendisk *disk; - disk = alloc_disk(1); - if (!disk) - return -ENOMEM; - - q = blk_mq_init_queue(&tag_set); - if (IS_ERR(q)) { - put_disk(disk); - return PTR_ERR(q); - } + disk = blk_mq_alloc_disk(&tag_set, NULL); + if (IS_ERR(disk)) + return PTR_ERR(disk); disk->major = Z2RAM_MAJOR; disk->first_minor = minor; + disk->minors = 1; disk->fops = &z2_fops; if (minor) sprintf(disk->disk_name, "z2ram%d", minor); else sprintf(disk->disk_name, "z2ram"); - disk->queue = q; z2ram_gendisk[minor] = disk; add_disk(disk); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index cf8deecc39ef..fcaf2750f68f 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1781,24 +1781,24 @@ static ssize_t reset_store(struct device *dev, zram = dev_to_zram(dev); bdev = zram->disk->part0; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); /* Do not reset an active device or claimed device */ if (bdev->bd_openers || zram->claim) { - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); return -EBUSY; } /* From now on, anyone can't open /dev/zram[0-9] */ zram->claim = true; - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); /* Make sure all the pending I/O are finished */ fsync_bdev(bdev); zram_reset_device(zram); - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); zram->claim = false; - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); return len; } @@ -1808,7 +1808,7 @@ static int zram_open(struct block_device *bdev, fmode_t mode) int ret = 0; struct zram *zram; - WARN_ON(!mutex_is_locked(&bdev->bd_mutex)); + WARN_ON(!mutex_is_locked(&bdev->bd_disk->open_mutex)); zram = bdev->bd_disk->private_data; /* zram was claimed to reset so open request fails */ @@ -1890,7 +1890,6 @@ static const struct attribute_group *zram_disk_attr_groups[] = { static int zram_add(void) { struct zram *zram; - struct request_queue *queue; int ret, device_id; zram = kzalloc(sizeof(struct zram), GFP_KERNEL); @@ -1906,27 +1905,20 @@ static int zram_add(void) #ifdef CONFIG_ZRAM_WRITEBACK spin_lock_init(&zram->wb_limit_lock); #endif - queue = blk_alloc_queue(NUMA_NO_NODE); - if (!queue) { - pr_err("Error allocating disk queue for device %d\n", + + /* gendisk structure */ + zram->disk = blk_alloc_disk(NUMA_NO_NODE); + if (!zram->disk) { + pr_err("Error allocating disk structure for device %d\n", device_id); ret = -ENOMEM; goto out_free_idr; } - /* gendisk structure */ - zram->disk = alloc_disk(1); - if (!zram->disk) { - pr_err("Error allocating disk structure for device %d\n", - device_id); - ret = -ENOMEM; - goto out_free_queue; - } - zram->disk->major = zram_major; zram->disk->first_minor = device_id; + zram->disk->minors = 1; zram->disk->fops = &zram_devops; - zram->disk->queue = queue; zram->disk->private_data = zram; snprintf(zram->disk->disk_name, 16, "zram%d", device_id); @@ -1969,8 +1961,6 @@ static int zram_add(void) pr_info("Added device: %s\n", zram->disk->disk_name); return device_id; -out_free_queue: - blk_cleanup_queue(queue); out_free_idr: idr_remove(&zram_index_idr, device_id); out_free_dev: @@ -1982,14 +1972,14 @@ static int zram_remove(struct zram *zram) { struct block_device *bdev = zram->disk->part0; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); if (bdev->bd_openers || zram->claim) { - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); return -EBUSY; } zram->claim = true; - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); zram_debugfs_unregister(zram); @@ -2000,8 +1990,7 @@ static int zram_remove(struct zram *zram) pr_info("Removed device: %s\n", zram->disk->disk_name); del_gendisk(zram->disk); - blk_cleanup_queue(zram->disk->queue); - put_disk(zram->disk); + blk_cleanup_disk(zram->disk); kfree(zram); return 0; } diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 419a7e8281ee..74c411911b6e 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -112,7 +112,7 @@ struct zram { /* * zram is claimed so open request will be failed */ - bool claim; /* Protected by bdev->bd_mutex */ + bool claim; /* Protected by disk->open_mutex */ struct file *backing_dev; #ifdef CONFIG_ZRAM_WRITEBACK spinlock_t wb_limit_lock; diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index 1b9743b7f2ef..e5d706ed55ea 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -404,6 +404,7 @@ static const struct bcm_subver_table bcm_uart_subver_table[] = { { 0x4217, "BCM4329B1" }, /* 002.002.023 */ { 0x6106, "BCM4359C0" }, /* 003.001.006 */ { 0x4106, "BCM4335A0" }, /* 002.001.006 */ + { 0x410c, "BCM43430B0" }, /* 002.001.012 */ { } }; diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index 33d58b30c5ac..cddd350beba3 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -1461,9 +1461,7 @@ static void btmrvl_sdio_coredump(struct device *dev) BT_ERR("Allocated buffer not enough"); } - if (stat != RDWR_STATUS_DONE) { - continue; - } else { + if (stat == RDWR_STATUS_DONE) { BT_INFO("%s done: size=0x%tx", entry->mem_name, dbg_ptr - entry->mem_ptr); diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c index 6c40bc75fb5b..e9d91d7c0db4 100644 --- a/drivers/bluetooth/btmtkuart.c +++ b/drivers/bluetooth/btmtkuart.c @@ -581,11 +581,9 @@ static int btmtkuart_open(struct hci_dev *hdev) /* Enable the power domain and clock the device requires */ pm_runtime_enable(dev); - err = pm_runtime_get_sync(dev); - if (err < 0) { - pm_runtime_put_noidle(dev); + err = pm_runtime_resume_and_get(dev); + if (err < 0) goto err_disable_rpm; - } err = clk_prepare_enable(bdev->clk); if (err < 0) diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index 25114f0d1319..be04d74037d2 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -182,8 +182,9 @@ int qca_send_pre_shutdown_cmd(struct hci_dev *hdev) } EXPORT_SYMBOL_GPL(qca_send_pre_shutdown_cmd); -static void qca_tlv_check_data(struct qca_fw_config *config, - const struct firmware *fw, enum qca_btsoc_type soc_type) +static void qca_tlv_check_data(struct hci_dev *hdev, + struct qca_fw_config *config, + u8 *fw_data, enum qca_btsoc_type soc_type) { const u8 *data; u32 type_len; @@ -194,19 +195,21 @@ static void qca_tlv_check_data(struct qca_fw_config *config, struct tlv_type_nvm *tlv_nvm; uint8_t nvm_baud_rate = config->user_baud_rate; - tlv = (struct tlv_type_hdr *)fw->data; - - type_len = le32_to_cpu(tlv->type_len); - length = (type_len >> 8) & 0x00ffffff; - - BT_DBG("TLV Type\t\t : 0x%x", type_len & 0x000000ff); - BT_DBG("Length\t\t : %d bytes", length); - config->dnld_mode = QCA_SKIP_EVT_NONE; config->dnld_type = QCA_SKIP_EVT_NONE; switch (config->type) { + case ELF_TYPE_PATCH: + config->dnld_mode = QCA_SKIP_EVT_VSE_CC; + config->dnld_type = QCA_SKIP_EVT_VSE_CC; + + bt_dev_dbg(hdev, "File Class : 0x%x", fw_data[4]); + bt_dev_dbg(hdev, "Data Encoding : 0x%x", fw_data[5]); + bt_dev_dbg(hdev, "File version : 0x%x", fw_data[6]); + break; case TLV_TYPE_PATCH: + tlv = (struct tlv_type_hdr *)fw_data; + type_len = le32_to_cpu(tlv->type_len); tlv_patch = (struct tlv_type_patch *)tlv->data; /* For Rome version 1.1 to 3.1, all segment commands @@ -218,6 +221,7 @@ static void qca_tlv_check_data(struct qca_fw_config *config, config->dnld_mode = tlv_patch->download_mode; config->dnld_type = config->dnld_mode; + BT_DBG("TLV Type\t\t : 0x%x", type_len & 0x000000ff); BT_DBG("Total Length : %d bytes", le32_to_cpu(tlv_patch->total_size)); BT_DBG("Patch Data Length : %d bytes", @@ -243,6 +247,14 @@ static void qca_tlv_check_data(struct qca_fw_config *config, break; case TLV_TYPE_NVM: + tlv = (struct tlv_type_hdr *)fw_data; + + type_len = le32_to_cpu(tlv->type_len); + length = (type_len >> 8) & 0x00ffffff; + + BT_DBG("TLV Type\t\t : 0x%x", type_len & 0x000000ff); + BT_DBG("Length\t\t : %d bytes", length); + idx = 0; data = tlv->data; while (idx < length) { @@ -387,25 +399,57 @@ static int qca_inject_cmd_complete_event(struct hci_dev *hdev) static int qca_download_firmware(struct hci_dev *hdev, struct qca_fw_config *config, - enum qca_btsoc_type soc_type) + enum qca_btsoc_type soc_type, + u8 rom_ver) { const struct firmware *fw; + u8 *data; const u8 *segment; - int ret, remain, i = 0; + int ret, size, remain, i = 0; bt_dev_info(hdev, "QCA Downloading %s", config->fwname); ret = request_firmware(&fw, config->fwname, &hdev->dev); if (ret) { - bt_dev_err(hdev, "QCA Failed to request file: %s (%d)", - config->fwname, ret); - return ret; + /* For WCN6750, if mbn file is not present then check for + * tlv file. + */ + if (soc_type == QCA_WCN6750 && config->type == ELF_TYPE_PATCH) { + bt_dev_dbg(hdev, "QCA Failed to request file: %s (%d)", + config->fwname, ret); + config->type = TLV_TYPE_PATCH; + snprintf(config->fwname, sizeof(config->fwname), + "qca/msbtfw%02x.tlv", rom_ver); + bt_dev_info(hdev, "QCA Downloading %s", config->fwname); + ret = request_firmware(&fw, config->fwname, &hdev->dev); + if (ret) { + bt_dev_err(hdev, "QCA Failed to request file: %s (%d)", + config->fwname, ret); + return ret; + } + } else { + bt_dev_err(hdev, "QCA Failed to request file: %s (%d)", + config->fwname, ret); + return ret; + } } - qca_tlv_check_data(config, fw, soc_type); + size = fw->size; + data = vmalloc(fw->size); + if (!data) { + bt_dev_err(hdev, "QCA Failed to allocate memory for file: %s", + config->fwname); + release_firmware(fw); + return -ENOMEM; + } - segment = fw->data; - remain = fw->size; + memcpy(data, fw->data, size); + release_firmware(fw); + + qca_tlv_check_data(hdev, config, data, soc_type); + + segment = data; + remain = size; while (remain > 0) { int segsize = min(MAX_SIZE_PER_TLV_SEGMENT, remain); @@ -435,7 +479,7 @@ static int qca_download_firmware(struct hci_dev *hdev, ret = qca_inject_cmd_complete_event(hdev); out: - release_firmware(fw); + vfree(data); return ret; } @@ -502,27 +546,32 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, config.user_baud_rate = baudrate; + /* Firmware files to download are based on ROM version. + * ROM version is derived from last two bytes of soc_ver. + */ + rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | (soc_ver & 0x0000000f); + /* Download rampatch file */ config.type = TLV_TYPE_PATCH; if (qca_is_wcn399x(soc_type)) { - /* Firmware files to download are based on ROM version. - * ROM version is derived from last two bytes of soc_ver. - */ - rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | - (soc_ver & 0x0000000f); snprintf(config.fwname, sizeof(config.fwname), "qca/crbtfw%02x.tlv", rom_ver); } else if (soc_type == QCA_QCA6390) { - rom_ver = ((soc_ver & 0x00000f00) >> 0x04) | - (soc_ver & 0x0000000f); snprintf(config.fwname, sizeof(config.fwname), "qca/htbtfw%02x.tlv", rom_ver); + } else if (soc_type == QCA_WCN6750) { + /* Choose mbn file by default.If mbn file is not found + * then choose tlv file + */ + config.type = ELF_TYPE_PATCH; + snprintf(config.fwname, sizeof(config.fwname), + "qca/msbtfw%02x.mbn", rom_ver); } else { snprintf(config.fwname, sizeof(config.fwname), "qca/rampatch_%08x.bin", soc_ver); } - err = qca_download_firmware(hdev, &config, soc_type); + err = qca_download_firmware(hdev, &config, soc_type, rom_ver); if (err < 0) { bt_dev_err(hdev, "QCA Failed to download patch (%d)", err); return err; @@ -548,11 +597,14 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, else if (soc_type == QCA_QCA6390) snprintf(config.fwname, sizeof(config.fwname), "qca/htnv%02x.bin", rom_ver); + else if (soc_type == QCA_WCN6750) + snprintf(config.fwname, sizeof(config.fwname), + "qca/msnv%02x.bin", rom_ver); else snprintf(config.fwname, sizeof(config.fwname), "qca/nvm_%08x.bin", soc_ver); - err = qca_download_firmware(hdev, &config, soc_type); + err = qca_download_firmware(hdev, &config, soc_type, rom_ver); if (err < 0) { bt_dev_err(hdev, "QCA Failed to download NVM (%d)", err); return err; @@ -564,13 +616,14 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, return err; } - /* WCN399x supports the Microsoft vendor extension with 0xFD70 as the + /* WCN399x and WCN6750 supports the Microsoft vendor extension with 0xFD70 as the * VsMsftOpCode. */ switch (soc_type) { case QCA_WCN3990: case QCA_WCN3991: case QCA_WCN3998: + case QCA_WCN6750: hci_set_msft_opcode(hdev, 0xFD70); break; default: @@ -584,7 +637,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, return err; } - if (soc_type == QCA_WCN3991) { + if (soc_type == QCA_WCN3991 || soc_type == QCA_WCN6750) { /* get fw build info */ err = qca_read_fw_build_info(hdev); if (err < 0) diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h index b19add7675a4..30afa7703afd 100644 --- a/drivers/bluetooth/btqca.h +++ b/drivers/bluetooth/btqca.h @@ -80,7 +80,8 @@ enum qca_tlv_dnld_mode { enum qca_tlv_type { TLV_TYPE_PATCH = 1, - TLV_TYPE_NVM + TLV_TYPE_NVM, + ELF_TYPE_PATCH, }; struct qca_fw_config { @@ -143,6 +144,7 @@ enum qca_btsoc_type { QCA_WCN3998, QCA_WCN3991, QCA_QCA6390, + QCA_WCN6750, }; #if IS_ENABLED(CONFIG_BT_QCA) @@ -160,6 +162,11 @@ static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type) return soc_type == QCA_WCN3990 || soc_type == QCA_WCN3991 || soc_type == QCA_WCN3998; } +static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type) +{ + return soc_type == QCA_WCN6750; +} + #else static inline int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) @@ -192,6 +199,11 @@ static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type) return false; } +static inline bool qca_is_wcn6750(enum qca_btsoc_type soc_type) +{ + return false; +} + static inline int qca_send_pre_shutdown_cmd(struct hci_dev *hdev) { return -EOPNOTSUPP; diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index e7fe5fb22753..cce0125ec4fd 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -132,12 +132,19 @@ static const struct id_table ic_id_table[] = { .cfg_name = "rtl_bt/rtl8761a_config" }, /* 8761B */ - { IC_INFO(RTL_ROM_LMP_8761A, 0xb, 0xa, HCI_USB), + { IC_INFO(RTL_ROM_LMP_8761A, 0xb, 0xa, HCI_UART), .config_needed = false, .has_rom_version = true, .fw_name = "rtl_bt/rtl8761b_fw.bin", .cfg_name = "rtl_bt/rtl8761b_config" }, + /* 8761BU */ + { IC_INFO(RTL_ROM_LMP_8761A, 0xb, 0xa, HCI_USB), + .config_needed = false, + .has_rom_version = true, + .fw_name = "rtl_bt/rtl8761bu_fw.bin", + .cfg_name = "rtl_bt/rtl8761bu_config" }, + /* 8822C with UART interface */ { IC_INFO(RTL_ROM_LMP_8822B, 0xc, 0xa, HCI_UART), .config_needed = true, @@ -719,17 +726,8 @@ int btrtl_download_firmware(struct hci_dev *hdev, } EXPORT_SYMBOL_GPL(btrtl_download_firmware); -int btrtl_setup_realtek(struct hci_dev *hdev) +void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev) { - struct btrtl_device_info *btrtl_dev; - int ret; - - btrtl_dev = btrtl_initialize(hdev, NULL); - if (IS_ERR(btrtl_dev)) - return PTR_ERR(btrtl_dev); - - ret = btrtl_download_firmware(hdev, btrtl_dev); - /* Enable controller to do both LE scan and BR/EDR inquiry * simultaneously. */ @@ -750,6 +748,21 @@ int btrtl_setup_realtek(struct hci_dev *hdev) rtl_dev_dbg(hdev, "WBS supported not enabled."); break; } +} +EXPORT_SYMBOL_GPL(btrtl_set_quirks); + +int btrtl_setup_realtek(struct hci_dev *hdev) +{ + struct btrtl_device_info *btrtl_dev; + int ret; + + btrtl_dev = btrtl_initialize(hdev, NULL); + if (IS_ERR(btrtl_dev)) + return PTR_ERR(btrtl_dev); + + ret = btrtl_download_firmware(hdev, btrtl_dev); + + btrtl_set_quirks(hdev, btrtl_dev); btrtl_free(btrtl_dev); return ret; diff --git a/drivers/bluetooth/btrtl.h b/drivers/bluetooth/btrtl.h index 2a582682136d..2c441bda390a 100644 --- a/drivers/bluetooth/btrtl.h +++ b/drivers/bluetooth/btrtl.h @@ -54,6 +54,8 @@ struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev, void btrtl_free(struct btrtl_device_info *btrtl_dev); int btrtl_download_firmware(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev); +void btrtl_set_quirks(struct hci_dev *hdev, + struct btrtl_device_info *btrtl_dev); int btrtl_setup_realtek(struct hci_dev *hdev); int btrtl_shutdown_realtek(struct hci_dev *hdev); int btrtl_get_uart_settings(struct hci_dev *hdev, @@ -79,6 +81,11 @@ static inline int btrtl_download_firmware(struct hci_dev *hdev, return -EOPNOTSUPP; } +static inline void btrtl_set_quirks(struct hci_dev *hdev, + struct btrtl_device_info *btrtl_dev) +{ +} + static inline int btrtl_setup_realtek(struct hci_dev *hdev) { return -EOPNOTSUPP; diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 7f6ba2c975ed..a9855a2dd561 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -270,6 +270,8 @@ static const struct usb_device_id blacklist_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0cf3, 0xe360), .driver_info = BTUSB_QCA_ROME | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0cf3, 0xe500), .driver_info = BTUSB_QCA_ROME | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0489, 0xe092), .driver_info = BTUSB_QCA_ROME | BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0489, 0xe09f), .driver_info = BTUSB_QCA_ROME | @@ -408,6 +410,11 @@ static const struct usb_device_id blacklist_table[] = { /* Additional MediaTek MT7615E Bluetooth devices */ { USB_DEVICE(0x13d3, 0x3560), .driver_info = BTUSB_MEDIATEK}, + /* Additional MediaTek MT7921 Bluetooth devices */ + { USB_DEVICE(0x04ca, 0x3802), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, + /* Additional Realtek 8723AE Bluetooth devices */ { USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK }, { USB_DEVICE(0x13d3, 0x3394), .driver_info = BTUSB_REALTEK }, @@ -427,6 +434,10 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0bda, 0xb009), .driver_info = BTUSB_REALTEK }, { USB_DEVICE(0x2ff8, 0xb011), .driver_info = BTUSB_REALTEK }, + /* Additional Realtek 8761BU Bluetooth devices */ + { USB_DEVICE(0x0b05, 0x190e), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, + /* Additional Realtek 8821AE Bluetooth devices */ { USB_DEVICE(0x0b05, 0x17dc), .driver_info = BTUSB_REALTEK }, { USB_DEVICE(0x13d3, 0x3414), .driver_info = BTUSB_REALTEK }, @@ -1749,6 +1760,13 @@ static void btusb_work(struct work_struct *work) * which work with WBS at all. */ new_alts = btusb_find_altsetting(data, 6) ? 6 : 1; + /* Because mSBC frames do not need to be aligned to the + * SCO packet boundary. If support the Alt 3, use the + * Alt 3 for HCI payload >= 60 Bytes let air packet + * data satisfy 60 bytes. + */ + if (new_alts == 1 && btusb_find_altsetting(data, 3)) + new_alts = 3; } if (btusb_switch_alt_setting(hdev, new_alts) < 0) @@ -3312,11 +3330,6 @@ static int btusb_mtk_hci_wmt_sync(struct hci_dev *hdev, struct btmtk_wmt_hdr *hdr; int err; - /* Submit control IN URB on demand to process the WMT event */ - err = btusb_mtk_submit_wmt_recv_urb(hdev); - if (err < 0) - return err; - /* Send the WMT command and wait until the WMT event returns */ hlen = sizeof(*hdr) + wmt_params->dlen; if (hlen > 255) @@ -3342,6 +3355,11 @@ static int btusb_mtk_hci_wmt_sync(struct hci_dev *hdev, goto err_free_wc; } + /* Submit control IN URB on demand to process the WMT event */ + err = btusb_mtk_submit_wmt_recv_urb(hdev); + if (err < 0) + goto err_free_wc; + /* The vendor specific WMT commands are all answered by a vendor * specific event and will have the Command Status or Command * Complete as with usual HCI command flow control. @@ -4062,6 +4080,11 @@ static int btusb_setup_qca_download_fw(struct hci_dev *hdev, sent += size; count -= size; + /* ep2 need time to switch from function acl to function dfu, + * so we add 20ms delay here. + */ + msleep(20); + while (count) { size = min_t(size_t, count, QCA_DFU_PACKET_LEN); @@ -4154,9 +4177,15 @@ static int btusb_setup_qca_load_nvm(struct hci_dev *hdev, int err; if (((ver->flag >> 8) & 0xff) == QCA_FLAG_MULTI_NVM) { - snprintf(fwname, sizeof(fwname), "qca/nvm_usb_%08x_%04x.bin", - le32_to_cpu(ver->rom_version), - le16_to_cpu(ver->board_id)); + /* if boardid equal 0, use default nvm without surfix */ + if (le16_to_cpu(ver->board_id) == 0x0) { + snprintf(fwname, sizeof(fwname), "qca/nvm_usb_%08x.bin", + le32_to_cpu(ver->rom_version)); + } else { + snprintf(fwname, sizeof(fwname), "qca/nvm_usb_%08x_%04x.bin", + le32_to_cpu(ver->rom_version), + le16_to_cpu(ver->board_id)); + } } else { snprintf(fwname, sizeof(fwname), "qca/nvm_usb_%08x.bin", le32_to_cpu(ver->rom_version)); diff --git a/drivers/bluetooth/hci_ag6xx.c b/drivers/bluetooth/hci_ag6xx.c index 1f55df93e4ce..2d40302409ff 100644 --- a/drivers/bluetooth/hci_ag6xx.c +++ b/drivers/bluetooth/hci_ag6xx.c @@ -199,7 +199,6 @@ static int ag6xx_setup(struct hci_uart *hu) fwname, err); goto patch; } - fw_ptr = fw->data; bt_dev_info(hdev, "Applying bddata (%s)", fwname); diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c index 27e96681d583..e0520639f4ba 100644 --- a/drivers/bluetooth/hci_h5.c +++ b/drivers/bluetooth/hci_h5.c @@ -906,10 +906,7 @@ static int h5_btrtl_setup(struct h5 *h5) /* Give the device some time before the hci-core sends it a reset */ usleep_range(10000, 20000); - /* Enable controller to do both LE scan and BR/EDR inquiry - * simultaneously. - */ - set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &h5->hu->hdev->quirks); + btrtl_set_quirks(h5->hu->hdev, btrtl_dev); out_free: btrtl_free(btrtl_dev); diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 0a0056912d51..53deea2eb7b4 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -218,6 +218,7 @@ struct qca_power { struct qca_serdev { struct hci_uart serdev_hu; struct gpio_desc *bt_en; + struct gpio_desc *sw_ctrl; struct clk *susclk; enum qca_btsoc_type btsoc_type; struct qca_power *bt_power; @@ -604,7 +605,8 @@ static int qca_open(struct hci_uart *hu) if (hu->serdev) { qcadev = serdev_device_get_drvdata(hu->serdev); - if (qca_is_wcn399x(qcadev->btsoc_type)) + if (qca_is_wcn399x(qcadev->btsoc_type) || + qca_is_wcn6750(qcadev->btsoc_type)) hu->init_speed = qcadev->init_speed; if (qcadev->oper_speed) @@ -1308,7 +1310,8 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate) msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS)); /* Give the controller time to process the request */ - if (qca_is_wcn399x(qca_soc_type(hu))) + if (qca_is_wcn399x(qca_soc_type(hu)) || + qca_is_wcn6750(qca_soc_type(hu))) usleep_range(1000, 10000); else msleep(300); @@ -1384,7 +1387,8 @@ static unsigned int qca_get_speed(struct hci_uart *hu, static int qca_check_speeds(struct hci_uart *hu) { - if (qca_is_wcn399x(qca_soc_type(hu))) { + if (qca_is_wcn399x(qca_soc_type(hu)) || + qca_is_wcn6750(qca_soc_type(hu))) { if (!qca_get_speed(hu, QCA_INIT_SPEED) && !qca_get_speed(hu, QCA_OPER_SPEED)) return -EINVAL; @@ -1417,7 +1421,8 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type) /* Disable flow control for wcn3990 to deassert RTS while * changing the baudrate of chip and host. */ - if (qca_is_wcn399x(soc_type)) + if (qca_is_wcn399x(soc_type) || + qca_is_wcn6750(soc_type)) hci_uart_set_flow_control(hu, true); if (soc_type == QCA_WCN3990) { @@ -1434,7 +1439,8 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type) host_set_baudrate(hu, speed); error: - if (qca_is_wcn399x(soc_type)) + if (qca_is_wcn399x(soc_type) || + qca_is_wcn6750(soc_type)) hci_uart_set_flow_control(hu, false); if (soc_type == QCA_WCN3990) { @@ -1585,10 +1591,12 @@ static bool qca_prevent_wake(struct hci_dev *hdev) return !wakeup; } -static int qca_wcn3990_init(struct hci_uart *hu) +static int qca_regulator_init(struct hci_uart *hu) { + enum qca_btsoc_type soc_type = qca_soc_type(hu); struct qca_serdev *qcadev; int ret; + bool sw_ctrl_state; /* Check for vregs status, may be hci down has turned * off the voltage regulator. @@ -1607,16 +1615,33 @@ static int qca_wcn3990_init(struct hci_uart *hu) } } - /* Forcefully enable wcn3990 to enter in to boot mode. */ - host_set_baudrate(hu, 2400); - ret = qca_send_power_pulse(hu, false); - if (ret) - return ret; + if (qca_is_wcn399x(soc_type)) { + /* Forcefully enable wcn399x to enter in to boot mode. */ + host_set_baudrate(hu, 2400); + ret = qca_send_power_pulse(hu, false); + if (ret) + return ret; + } + + /* For wcn6750 need to enable gpio bt_en */ + if (qcadev->bt_en) { + gpiod_set_value_cansleep(qcadev->bt_en, 0); + msleep(50); + gpiod_set_value_cansleep(qcadev->bt_en, 1); + msleep(50); + if (qcadev->sw_ctrl) { + sw_ctrl_state = gpiod_get_value_cansleep(qcadev->sw_ctrl); + bt_dev_dbg(hu->hdev, "SW_CTRL is %d", sw_ctrl_state); + } + } qca_set_speed(hu, QCA_INIT_SPEED); - ret = qca_send_power_pulse(hu, true); - if (ret) - return ret; + + if (qca_is_wcn399x(soc_type)) { + ret = qca_send_power_pulse(hu, true); + if (ret) + return ret; + } /* Now the device is in ready state to communicate with host. * To sync host with device we need to reopen port. @@ -1649,8 +1674,9 @@ static int qca_power_on(struct hci_dev *hdev) if (!hu->serdev) return 0; - if (qca_is_wcn399x(soc_type)) { - ret = qca_wcn3990_init(hu); + if (qca_is_wcn399x(soc_type) || + qca_is_wcn6750(soc_type)) { + ret = qca_regulator_init(hu); } else { qcadev = serdev_device_get_drvdata(hu->serdev); if (qcadev->bt_en) { @@ -1689,7 +1715,8 @@ static int qca_setup(struct hci_uart *hu) set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); bt_dev_info(hdev, "setting up %s", - qca_is_wcn399x(soc_type) ? "wcn399x" : "ROME/QCA6390"); + qca_is_wcn399x(soc_type) ? "wcn399x" : + (soc_type == QCA_WCN6750) ? "wcn6750" : "ROME/QCA6390"); qca->memdump_state = QCA_MEMDUMP_IDLE; @@ -1700,7 +1727,8 @@ retry: clear_bit(QCA_SSR_TRIGGERED, &qca->flags); - if (qca_is_wcn399x(soc_type)) { + if (qca_is_wcn399x(soc_type) || + qca_is_wcn6750(soc_type)) { set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); ret = qca_read_soc_version(hdev, &ver, soc_type); @@ -1720,7 +1748,8 @@ retry: qca_baudrate = qca_get_baudrate_value(speed); } - if (!qca_is_wcn399x(soc_type)) { + if (!(qca_is_wcn399x(soc_type) || + qca_is_wcn6750(soc_type))) { /* Get QCA version information */ ret = qca_read_soc_version(hdev, &ver, soc_type); if (ret) @@ -1828,14 +1857,30 @@ static const struct qca_device_data qca_soc_data_qca6390 = { .num_vregs = 0, }; +static const struct qca_device_data qca_soc_data_wcn6750 = { + .soc_type = QCA_WCN6750, + .vregs = (struct qca_vreg []) { + { "vddio", 5000 }, + { "vddaon", 26000 }, + { "vddbtcxmx", 126000 }, + { "vddrfacmn", 12500 }, + { "vddrfa0p8", 102000 }, + { "vddrfa1p7", 302000 }, + { "vddrfa1p2", 257000 }, + { "vddrfa2p2", 1700000 }, + { "vddasd", 200 }, + }, + .num_vregs = 9, + .capabilities = QCA_CAP_WIDEBAND_SPEECH | QCA_CAP_VALID_LE_STATES, +}; + static void qca_power_shutdown(struct hci_uart *hu) { struct qca_serdev *qcadev; struct qca_data *qca = hu->priv; unsigned long flags; enum qca_btsoc_type soc_type = qca_soc_type(hu); - - qcadev = serdev_device_get_drvdata(hu->serdev); + bool sw_ctrl_state; /* From this point we go into power off state. But serial port is * still open, stop queueing the IBS data and flush all the buffered @@ -1852,10 +1897,20 @@ static void qca_power_shutdown(struct hci_uart *hu) if (!hu->serdev) return; + qcadev = serdev_device_get_drvdata(hu->serdev); + if (qca_is_wcn399x(soc_type)) { host_set_baudrate(hu, 2400); qca_send_power_pulse(hu, false); qca_regulator_disable(qcadev); + } else if (soc_type == QCA_WCN6750) { + gpiod_set_value_cansleep(qcadev->bt_en, 0); + msleep(100); + qca_regulator_disable(qcadev); + if (qcadev->sw_ctrl) { + sw_ctrl_state = gpiod_get_value_cansleep(qcadev->sw_ctrl); + bt_dev_dbg(hu->hdev, "SW_CTRL is %d", sw_ctrl_state); + } } else if (qcadev->bt_en) { gpiod_set_value_cansleep(qcadev->bt_en, 0); } @@ -1978,7 +2033,9 @@ static int qca_serdev_probe(struct serdev_device *serdev) if (!qcadev->oper_speed) BT_DBG("UART will pick default operating speed"); - if (data && qca_is_wcn399x(data->soc_type)) { + if (data && + (qca_is_wcn399x(data->soc_type) || + qca_is_wcn6750(data->soc_type))) { qcadev->btsoc_type = data->soc_type; qcadev->bt_power = devm_kzalloc(&serdev->dev, sizeof(struct qca_power), @@ -1996,6 +2053,18 @@ static int qca_serdev_probe(struct serdev_device *serdev) qcadev->bt_power->vregs_on = false; + qcadev->bt_en = devm_gpiod_get_optional(&serdev->dev, "enable", + GPIOD_OUT_LOW); + if (!qcadev->bt_en && data->soc_type == QCA_WCN6750) { + dev_err(&serdev->dev, "failed to acquire BT_EN gpio\n"); + power_ctrl_enabled = false; + } + + qcadev->sw_ctrl = devm_gpiod_get_optional(&serdev->dev, "swctrl", + GPIOD_IN); + if (!qcadev->sw_ctrl && data->soc_type == QCA_WCN6750) + dev_warn(&serdev->dev, "failed to acquire SW_CTRL gpio\n"); + qcadev->susclk = devm_clk_get_optional(&serdev->dev, NULL); if (IS_ERR(qcadev->susclk)) { dev_err(&serdev->dev, "failed to acquire clk\n"); @@ -2068,7 +2137,9 @@ static void qca_serdev_remove(struct serdev_device *serdev) struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev); struct qca_power *power = qcadev->bt_power; - if (qca_is_wcn399x(qcadev->btsoc_type) && power->vregs_on) + if ((qca_is_wcn399x(qcadev->btsoc_type) || + qca_is_wcn6750(qcadev->btsoc_type)) && + power->vregs_on) qca_power_shutdown(&qcadev->serdev_hu); else if (qcadev->susclk) clk_disable_unprepare(qcadev->susclk); @@ -2244,6 +2315,7 @@ static const struct of_device_id qca_bluetooth_of_match[] = { { .compatible = "qcom,wcn3990-bt", .data = &qca_soc_data_wcn3990}, { .compatible = "qcom,wcn3991-bt", .data = &qca_soc_data_wcn3991}, { .compatible = "qcom,wcn3998-bt", .data = &qca_soc_data_wcn3998}, + { .compatible = "qcom,wcn6750-bt", .data = &qca_soc_data_wcn6750}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match); diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c index c804db7e90f8..57908ce4fae8 100644 --- a/drivers/bluetooth/virtio_bt.c +++ b/drivers/bluetooth/virtio_bt.c @@ -34,6 +34,9 @@ static int virtbt_add_inbuf(struct virtio_bluetooth *vbt) int err; skb = alloc_skb(1000, GFP_KERNEL); + if (!skb) + return -ENOMEM; + sg_init_one(sg, skb->data, 1000); err = virtqueue_add_inbuf(vq, sg, 1, skb, GFP_KERNEL); diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index c6d8c0f59722..8e1fe75af93f 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -772,53 +772,50 @@ static int probe_gdrom(struct platform_device *devptr) goto probe_fail_no_mem; } probe_gdrom_setupcd(); - gd.disk = alloc_disk(1); - if (!gd.disk) { - err = -ENODEV; - goto probe_fail_no_disk; + + err = blk_mq_alloc_sq_tag_set(&gd.tag_set, &gdrom_mq_ops, 1, + BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING); + if (err) + goto probe_fail_free_cd_info; + + gd.disk = blk_mq_alloc_disk(&gd.tag_set, NULL); + if (IS_ERR(gd.disk)) { + err = PTR_ERR(gd.disk); + goto probe_fail_free_tag_set; } + gd.gdrom_rq = gd.disk->queue; probe_gdrom_setupdisk(); if (register_cdrom(gd.disk, gd.cd_info)) { err = -ENODEV; - goto probe_fail_cdrom_register; + goto probe_fail_cleanup_disk; } gd.disk->fops = &gdrom_bdops; gd.disk->events = DISK_EVENT_MEDIA_CHANGE; /* latch on to the interrupt */ err = gdrom_set_interrupt_handlers(); if (err) - goto probe_fail_cmdirq_register; - - gd.gdrom_rq = blk_mq_init_sq_queue(&gd.tag_set, &gdrom_mq_ops, 1, - BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING); - if (IS_ERR(gd.gdrom_rq)) { - err = PTR_ERR(gd.gdrom_rq); - gd.gdrom_rq = NULL; - goto probe_fail_requestq; - } + goto probe_fail_cleanup_disk; err = probe_gdrom_setupqueue(); if (err) - goto probe_fail_toc; + goto probe_fail_free_irqs; gd.toc = kzalloc(sizeof(struct gdromtoc), GFP_KERNEL); if (!gd.toc) { err = -ENOMEM; - goto probe_fail_toc; + goto probe_fail_free_irqs; } add_disk(gd.disk); return 0; -probe_fail_toc: - blk_cleanup_queue(gd.gdrom_rq); - blk_mq_free_tag_set(&gd.tag_set); -probe_fail_requestq: +probe_fail_free_irqs: free_irq(HW_EVENT_GDROM_DMA, &gd); free_irq(HW_EVENT_GDROM_CMD, &gd); -probe_fail_cmdirq_register: -probe_fail_cdrom_register: - del_gendisk(gd.disk); -probe_fail_no_disk: +probe_fail_cleanup_disk: + blk_cleanup_disk(gd.disk); +probe_fail_free_tag_set: + blk_mq_free_tag_set(&gd.tag_set); +probe_fail_free_cd_info: kfree(gd.cd_info); probe_fail_no_mem: unregister_blkdev(gdrom_major, GDROM_DEV_NAME); diff --git a/drivers/char/ipmi/Kconfig b/drivers/char/ipmi/Kconfig index 07847d9a459a..249b31197eea 100644 --- a/drivers/char/ipmi/Kconfig +++ b/drivers/char/ipmi/Kconfig @@ -124,6 +124,33 @@ config NPCM7XX_KCS_IPMI_BMC This support is also available as a module. If so, the module will be called kcs_bmc_npcm7xx. +config IPMI_KCS_BMC_CDEV_IPMI + depends on IPMI_KCS_BMC + tristate "IPMI character device interface for BMC KCS devices" + help + Provides a BMC-side character device implementing IPMI + semantics for KCS IPMI devices. + + Say YES if you wish to expose KCS devices on the BMC for IPMI + purposes. + + This support is also available as a module. The module will be + called kcs_bmc_cdev_ipmi. + +config IPMI_KCS_BMC_SERIO + depends on IPMI_KCS_BMC && SERIO + tristate "SerIO adaptor for BMC KCS devices" + help + Adapts the BMC KCS device for the SerIO subsystem. This allows users + to take advantage of userspace interfaces provided by SerIO where + appropriate. + + Say YES if you wish to expose KCS devices on the BMC via SerIO + interfaces. + + This support is also available as a module. The module will be + called kcs_bmc_serio. + config ASPEED_BT_IPMI_BMC depends on ARCH_ASPEED || COMPILE_TEST depends on REGMAP && REGMAP_MMIO && MFD_SYSCON diff --git a/drivers/char/ipmi/Makefile b/drivers/char/ipmi/Makefile index 0822adc2ec41..84f47d18007f 100644 --- a/drivers/char/ipmi/Makefile +++ b/drivers/char/ipmi/Makefile @@ -23,6 +23,8 @@ obj-$(CONFIG_IPMI_POWERNV) += ipmi_powernv.o obj-$(CONFIG_IPMI_WATCHDOG) += ipmi_watchdog.o obj-$(CONFIG_IPMI_POWEROFF) += ipmi_poweroff.o obj-$(CONFIG_IPMI_KCS_BMC) += kcs_bmc.o +obj-$(CONFIG_IPMI_KCS_BMC_SERIO) += kcs_bmc_serio.o +obj-$(CONFIG_IPMI_KCS_BMC_CDEV_IPMI) += kcs_bmc_cdev_ipmi.o obj-$(CONFIG_ASPEED_BT_IPMI_BMC) += bt-bmc.o obj-$(CONFIG_ASPEED_KCS_IPMI_BMC) += kcs_bmc_aspeed.o obj-$(CONFIG_NPCM7XX_KCS_IPMI_BMC) += kcs_bmc_npcm7xx.o diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index 32c334e34d55..e4ff3b50de7f 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -371,16 +371,18 @@ static int __ipmi_set_timeout(struct ipmi_smi_msg *smi_msg, data[0] = 0; WDOG_SET_TIMER_USE(data[0], WDOG_TIMER_USE_SMS_OS); - if ((ipmi_version_major > 1) - || ((ipmi_version_major == 1) && (ipmi_version_minor >= 5))) { - /* This is an IPMI 1.5-only feature. */ - data[0] |= WDOG_DONT_STOP_ON_SET; - } else if (ipmi_watchdog_state != WDOG_TIMEOUT_NONE) { - /* - * In ipmi 1.0, setting the timer stops the watchdog, we - * need to start it back up again. - */ - hbnow = 1; + if (ipmi_watchdog_state != WDOG_TIMEOUT_NONE) { + if ((ipmi_version_major > 1) || + ((ipmi_version_major == 1) && (ipmi_version_minor >= 5))) { + /* This is an IPMI 1.5-only feature. */ + data[0] |= WDOG_DONT_STOP_ON_SET; + } else { + /* + * In ipmi 1.0, setting the timer stops the watchdog, we + * need to start it back up again. + */ + hbnow = 1; + } } data[1] = 0; diff --git a/drivers/char/ipmi/kcs_bmc.c b/drivers/char/ipmi/kcs_bmc.c index f292e74bd4a5..03d02a848f3a 100644 --- a/drivers/char/ipmi/kcs_bmc.c +++ b/drivers/char/ipmi/kcs_bmc.c @@ -1,458 +1,189 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2015-2018, Intel Corporation. + * Copyright (c) 2021, IBM Corp. */ -#define pr_fmt(fmt) "kcs-bmc: " fmt - -#include -#include -#include +#include +#include #include -#include -#include -#include -#include +#include #include "kcs_bmc.h" -#define DEVICE_NAME "ipmi-kcs" +/* Implement both the device and client interfaces here */ +#include "kcs_bmc_device.h" +#include "kcs_bmc_client.h" -#define KCS_MSG_BUFSIZ 1000 +/* Record registered devices and drivers */ +static DEFINE_MUTEX(kcs_bmc_lock); +static LIST_HEAD(kcs_bmc_devices); +static LIST_HEAD(kcs_bmc_drivers); -#define KCS_ZERO_DATA 0 +/* Consumer data access */ - -/* IPMI 2.0 - Table 9-1, KCS Interface Status Register Bits */ -#define KCS_STATUS_STATE(state) (state << 6) -#define KCS_STATUS_STATE_MASK GENMASK(7, 6) -#define KCS_STATUS_CMD_DAT BIT(3) -#define KCS_STATUS_SMS_ATN BIT(2) -#define KCS_STATUS_IBF BIT(1) -#define KCS_STATUS_OBF BIT(0) - -/* IPMI 2.0 - Table 9-2, KCS Interface State Bits */ -enum kcs_states { - IDLE_STATE = 0, - READ_STATE = 1, - WRITE_STATE = 2, - ERROR_STATE = 3, -}; - -/* IPMI 2.0 - Table 9-3, KCS Interface Control Codes */ -#define KCS_CMD_GET_STATUS_ABORT 0x60 -#define KCS_CMD_WRITE_START 0x61 -#define KCS_CMD_WRITE_END 0x62 -#define KCS_CMD_READ_BYTE 0x68 - -static inline u8 read_data(struct kcs_bmc *kcs_bmc) +u8 kcs_bmc_read_data(struct kcs_bmc_device *kcs_bmc) { - return kcs_bmc->io_inputb(kcs_bmc, kcs_bmc->ioreg.idr); + return kcs_bmc->ops->io_inputb(kcs_bmc, kcs_bmc->ioreg.idr); } +EXPORT_SYMBOL(kcs_bmc_read_data); -static inline void write_data(struct kcs_bmc *kcs_bmc, u8 data) +void kcs_bmc_write_data(struct kcs_bmc_device *kcs_bmc, u8 data) { - kcs_bmc->io_outputb(kcs_bmc, kcs_bmc->ioreg.odr, data); + kcs_bmc->ops->io_outputb(kcs_bmc, kcs_bmc->ioreg.odr, data); } +EXPORT_SYMBOL(kcs_bmc_write_data); -static inline u8 read_status(struct kcs_bmc *kcs_bmc) +u8 kcs_bmc_read_status(struct kcs_bmc_device *kcs_bmc) { - return kcs_bmc->io_inputb(kcs_bmc, kcs_bmc->ioreg.str); + return kcs_bmc->ops->io_inputb(kcs_bmc, kcs_bmc->ioreg.str); } +EXPORT_SYMBOL(kcs_bmc_read_status); -static inline void write_status(struct kcs_bmc *kcs_bmc, u8 data) +void kcs_bmc_write_status(struct kcs_bmc_device *kcs_bmc, u8 data) { - kcs_bmc->io_outputb(kcs_bmc, kcs_bmc->ioreg.str, data); + kcs_bmc->ops->io_outputb(kcs_bmc, kcs_bmc->ioreg.str, data); } +EXPORT_SYMBOL(kcs_bmc_write_status); -static void update_status_bits(struct kcs_bmc *kcs_bmc, u8 mask, u8 val) +void kcs_bmc_update_status(struct kcs_bmc_device *kcs_bmc, u8 mask, u8 val) { - u8 tmp = read_status(kcs_bmc); - - tmp &= ~mask; - tmp |= val & mask; - - write_status(kcs_bmc, tmp); + kcs_bmc->ops->io_updateb(kcs_bmc, kcs_bmc->ioreg.str, mask, val); } +EXPORT_SYMBOL(kcs_bmc_update_status); -static inline void set_state(struct kcs_bmc *kcs_bmc, u8 state) +irqreturn_t kcs_bmc_handle_event(struct kcs_bmc_device *kcs_bmc) { - update_status_bits(kcs_bmc, KCS_STATUS_STATE_MASK, - KCS_STATUS_STATE(state)); -} + struct kcs_bmc_client *client; + irqreturn_t rc = IRQ_NONE; -static void kcs_force_abort(struct kcs_bmc *kcs_bmc) -{ - set_state(kcs_bmc, ERROR_STATE); - read_data(kcs_bmc); - write_data(kcs_bmc, KCS_ZERO_DATA); + spin_lock(&kcs_bmc->lock); + client = kcs_bmc->client; + if (client) + rc = client->ops->event(client); + spin_unlock(&kcs_bmc->lock); - kcs_bmc->phase = KCS_PHASE_ERROR; - kcs_bmc->data_in_avail = false; - kcs_bmc->data_in_idx = 0; -} - -static void kcs_bmc_handle_data(struct kcs_bmc *kcs_bmc) -{ - u8 data; - - switch (kcs_bmc->phase) { - case KCS_PHASE_WRITE_START: - kcs_bmc->phase = KCS_PHASE_WRITE_DATA; - fallthrough; - - case KCS_PHASE_WRITE_DATA: - if (kcs_bmc->data_in_idx < KCS_MSG_BUFSIZ) { - set_state(kcs_bmc, WRITE_STATE); - write_data(kcs_bmc, KCS_ZERO_DATA); - kcs_bmc->data_in[kcs_bmc->data_in_idx++] = - read_data(kcs_bmc); - } else { - kcs_force_abort(kcs_bmc); - kcs_bmc->error = KCS_LENGTH_ERROR; - } - break; - - case KCS_PHASE_WRITE_END_CMD: - if (kcs_bmc->data_in_idx < KCS_MSG_BUFSIZ) { - set_state(kcs_bmc, READ_STATE); - kcs_bmc->data_in[kcs_bmc->data_in_idx++] = - read_data(kcs_bmc); - kcs_bmc->phase = KCS_PHASE_WRITE_DONE; - kcs_bmc->data_in_avail = true; - wake_up_interruptible(&kcs_bmc->queue); - } else { - kcs_force_abort(kcs_bmc); - kcs_bmc->error = KCS_LENGTH_ERROR; - } - break; - - case KCS_PHASE_READ: - if (kcs_bmc->data_out_idx == kcs_bmc->data_out_len) - set_state(kcs_bmc, IDLE_STATE); - - data = read_data(kcs_bmc); - if (data != KCS_CMD_READ_BYTE) { - set_state(kcs_bmc, ERROR_STATE); - write_data(kcs_bmc, KCS_ZERO_DATA); - break; - } - - if (kcs_bmc->data_out_idx == kcs_bmc->data_out_len) { - write_data(kcs_bmc, KCS_ZERO_DATA); - kcs_bmc->phase = KCS_PHASE_IDLE; - break; - } - - write_data(kcs_bmc, - kcs_bmc->data_out[kcs_bmc->data_out_idx++]); - break; - - case KCS_PHASE_ABORT_ERROR1: - set_state(kcs_bmc, READ_STATE); - read_data(kcs_bmc); - write_data(kcs_bmc, kcs_bmc->error); - kcs_bmc->phase = KCS_PHASE_ABORT_ERROR2; - break; - - case KCS_PHASE_ABORT_ERROR2: - set_state(kcs_bmc, IDLE_STATE); - read_data(kcs_bmc); - write_data(kcs_bmc, KCS_ZERO_DATA); - kcs_bmc->phase = KCS_PHASE_IDLE; - break; - - default: - kcs_force_abort(kcs_bmc); - break; - } -} - -static void kcs_bmc_handle_cmd(struct kcs_bmc *kcs_bmc) -{ - u8 cmd; - - set_state(kcs_bmc, WRITE_STATE); - write_data(kcs_bmc, KCS_ZERO_DATA); - - cmd = read_data(kcs_bmc); - switch (cmd) { - case KCS_CMD_WRITE_START: - kcs_bmc->phase = KCS_PHASE_WRITE_START; - kcs_bmc->error = KCS_NO_ERROR; - kcs_bmc->data_in_avail = false; - kcs_bmc->data_in_idx = 0; - break; - - case KCS_CMD_WRITE_END: - if (kcs_bmc->phase != KCS_PHASE_WRITE_DATA) { - kcs_force_abort(kcs_bmc); - break; - } - - kcs_bmc->phase = KCS_PHASE_WRITE_END_CMD; - break; - - case KCS_CMD_GET_STATUS_ABORT: - if (kcs_bmc->error == KCS_NO_ERROR) - kcs_bmc->error = KCS_ABORTED_BY_COMMAND; - - kcs_bmc->phase = KCS_PHASE_ABORT_ERROR1; - kcs_bmc->data_in_avail = false; - kcs_bmc->data_in_idx = 0; - break; - - default: - kcs_force_abort(kcs_bmc); - kcs_bmc->error = KCS_ILLEGAL_CONTROL_CODE; - break; - } -} - -int kcs_bmc_handle_event(struct kcs_bmc *kcs_bmc) -{ - unsigned long flags; - int ret = -ENODATA; - u8 status; - - spin_lock_irqsave(&kcs_bmc->lock, flags); - - status = read_status(kcs_bmc); - if (status & KCS_STATUS_IBF) { - if (!kcs_bmc->running) - kcs_force_abort(kcs_bmc); - else if (status & KCS_STATUS_CMD_DAT) - kcs_bmc_handle_cmd(kcs_bmc); - else - kcs_bmc_handle_data(kcs_bmc); - - ret = 0; - } - - spin_unlock_irqrestore(&kcs_bmc->lock, flags); - - return ret; + return rc; } EXPORT_SYMBOL(kcs_bmc_handle_event); -static inline struct kcs_bmc *to_kcs_bmc(struct file *filp) +int kcs_bmc_enable_device(struct kcs_bmc_device *kcs_bmc, struct kcs_bmc_client *client) { - return container_of(filp->private_data, struct kcs_bmc, miscdev); -} - -static int kcs_bmc_open(struct inode *inode, struct file *filp) -{ - struct kcs_bmc *kcs_bmc = to_kcs_bmc(filp); - int ret = 0; + int rc; spin_lock_irq(&kcs_bmc->lock); - if (!kcs_bmc->running) - kcs_bmc->running = 1; - else - ret = -EBUSY; - spin_unlock_irq(&kcs_bmc->lock); - - return ret; -} - -static __poll_t kcs_bmc_poll(struct file *filp, poll_table *wait) -{ - struct kcs_bmc *kcs_bmc = to_kcs_bmc(filp); - __poll_t mask = 0; - - poll_wait(filp, &kcs_bmc->queue, wait); - - spin_lock_irq(&kcs_bmc->lock); - if (kcs_bmc->data_in_avail) - mask |= EPOLLIN; - spin_unlock_irq(&kcs_bmc->lock); - - return mask; -} - -static ssize_t kcs_bmc_read(struct file *filp, char __user *buf, - size_t count, loff_t *ppos) -{ - struct kcs_bmc *kcs_bmc = to_kcs_bmc(filp); - bool data_avail; - size_t data_len; - ssize_t ret; - - if (!(filp->f_flags & O_NONBLOCK)) - wait_event_interruptible(kcs_bmc->queue, - kcs_bmc->data_in_avail); - - mutex_lock(&kcs_bmc->mutex); - - spin_lock_irq(&kcs_bmc->lock); - data_avail = kcs_bmc->data_in_avail; - if (data_avail) { - data_len = kcs_bmc->data_in_idx; - memcpy(kcs_bmc->kbuffer, kcs_bmc->data_in, data_len); - } - spin_unlock_irq(&kcs_bmc->lock); - - if (!data_avail) { - ret = -EAGAIN; - goto out_unlock; - } - - if (count < data_len) { - pr_err("channel=%u with too large data : %zu\n", - kcs_bmc->channel, data_len); - - spin_lock_irq(&kcs_bmc->lock); - kcs_force_abort(kcs_bmc); - spin_unlock_irq(&kcs_bmc->lock); - - ret = -EOVERFLOW; - goto out_unlock; - } - - if (copy_to_user(buf, kcs_bmc->kbuffer, data_len)) { - ret = -EFAULT; - goto out_unlock; - } - - ret = data_len; - - spin_lock_irq(&kcs_bmc->lock); - if (kcs_bmc->phase == KCS_PHASE_WRITE_DONE) { - kcs_bmc->phase = KCS_PHASE_WAIT_READ; - kcs_bmc->data_in_avail = false; - kcs_bmc->data_in_idx = 0; + if (kcs_bmc->client) { + rc = -EBUSY; } else { - ret = -EAGAIN; + u8 mask = KCS_BMC_EVENT_TYPE_IBF; + + kcs_bmc->client = client; + kcs_bmc_update_event_mask(kcs_bmc, mask, mask); + rc = 0; } spin_unlock_irq(&kcs_bmc->lock); -out_unlock: - mutex_unlock(&kcs_bmc->mutex); - - return ret; + return rc; } +EXPORT_SYMBOL(kcs_bmc_enable_device); -static ssize_t kcs_bmc_write(struct file *filp, const char __user *buf, - size_t count, loff_t *ppos) +void kcs_bmc_disable_device(struct kcs_bmc_device *kcs_bmc, struct kcs_bmc_client *client) { - struct kcs_bmc *kcs_bmc = to_kcs_bmc(filp); - ssize_t ret; - - /* a minimum response size '3' : netfn + cmd + ccode */ - if (count < 3 || count > KCS_MSG_BUFSIZ) - return -EINVAL; - - mutex_lock(&kcs_bmc->mutex); - - if (copy_from_user(kcs_bmc->kbuffer, buf, count)) { - ret = -EFAULT; - goto out_unlock; - } - spin_lock_irq(&kcs_bmc->lock); - if (kcs_bmc->phase == KCS_PHASE_WAIT_READ) { - kcs_bmc->phase = KCS_PHASE_READ; - kcs_bmc->data_out_idx = 1; - kcs_bmc->data_out_len = count; - memcpy(kcs_bmc->data_out, kcs_bmc->kbuffer, count); - write_data(kcs_bmc, kcs_bmc->data_out[0]); - ret = count; - } else { - ret = -EINVAL; + if (client == kcs_bmc->client) { + u8 mask = KCS_BMC_EVENT_TYPE_IBF | KCS_BMC_EVENT_TYPE_OBE; + + kcs_bmc_update_event_mask(kcs_bmc, mask, 0); + kcs_bmc->client = NULL; } spin_unlock_irq(&kcs_bmc->lock); - -out_unlock: - mutex_unlock(&kcs_bmc->mutex); - - return ret; } +EXPORT_SYMBOL(kcs_bmc_disable_device); -static long kcs_bmc_ioctl(struct file *filp, unsigned int cmd, - unsigned long arg) +int kcs_bmc_add_device(struct kcs_bmc_device *kcs_bmc) { - struct kcs_bmc *kcs_bmc = to_kcs_bmc(filp); - long ret = 0; - - spin_lock_irq(&kcs_bmc->lock); - - switch (cmd) { - case IPMI_BMC_IOCTL_SET_SMS_ATN: - update_status_bits(kcs_bmc, KCS_STATUS_SMS_ATN, - KCS_STATUS_SMS_ATN); - break; - - case IPMI_BMC_IOCTL_CLEAR_SMS_ATN: - update_status_bits(kcs_bmc, KCS_STATUS_SMS_ATN, - 0); - break; - - case IPMI_BMC_IOCTL_FORCE_ABORT: - kcs_force_abort(kcs_bmc); - break; - - default: - ret = -EINVAL; - break; - } - - spin_unlock_irq(&kcs_bmc->lock); - - return ret; -} - -static int kcs_bmc_release(struct inode *inode, struct file *filp) -{ - struct kcs_bmc *kcs_bmc = to_kcs_bmc(filp); - - spin_lock_irq(&kcs_bmc->lock); - kcs_bmc->running = 0; - kcs_force_abort(kcs_bmc); - spin_unlock_irq(&kcs_bmc->lock); - - return 0; -} - -static const struct file_operations kcs_bmc_fops = { - .owner = THIS_MODULE, - .open = kcs_bmc_open, - .read = kcs_bmc_read, - .write = kcs_bmc_write, - .release = kcs_bmc_release, - .poll = kcs_bmc_poll, - .unlocked_ioctl = kcs_bmc_ioctl, -}; - -struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) -{ - struct kcs_bmc *kcs_bmc; - - kcs_bmc = devm_kzalloc(dev, sizeof(*kcs_bmc) + sizeof_priv, GFP_KERNEL); - if (!kcs_bmc) - return NULL; + struct kcs_bmc_driver *drv; + int error = 0; + int rc; spin_lock_init(&kcs_bmc->lock); - kcs_bmc->channel = channel; + kcs_bmc->client = NULL; - mutex_init(&kcs_bmc->mutex); - init_waitqueue_head(&kcs_bmc->queue); + mutex_lock(&kcs_bmc_lock); + list_add(&kcs_bmc->entry, &kcs_bmc_devices); + list_for_each_entry(drv, &kcs_bmc_drivers, entry) { + rc = drv->ops->add_device(kcs_bmc); + if (!rc) + continue; - kcs_bmc->data_in = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->data_out = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); - kcs_bmc->kbuffer = devm_kmalloc(dev, KCS_MSG_BUFSIZ, GFP_KERNEL); + dev_err(kcs_bmc->dev, "Failed to add chardev for KCS channel %d: %d", + kcs_bmc->channel, rc); + error = rc; + } + mutex_unlock(&kcs_bmc_lock); - kcs_bmc->miscdev.minor = MISC_DYNAMIC_MINOR; - kcs_bmc->miscdev.name = devm_kasprintf(dev, GFP_KERNEL, "%s%u", - DEVICE_NAME, channel); - if (!kcs_bmc->data_in || !kcs_bmc->data_out || !kcs_bmc->kbuffer || - !kcs_bmc->miscdev.name) - return NULL; - kcs_bmc->miscdev.fops = &kcs_bmc_fops; - - return kcs_bmc; + return error; } -EXPORT_SYMBOL(kcs_bmc_alloc); +EXPORT_SYMBOL(kcs_bmc_add_device); + +void kcs_bmc_remove_device(struct kcs_bmc_device *kcs_bmc) +{ + struct kcs_bmc_driver *drv; + int rc; + + mutex_lock(&kcs_bmc_lock); + list_del(&kcs_bmc->entry); + list_for_each_entry(drv, &kcs_bmc_drivers, entry) { + rc = drv->ops->remove_device(kcs_bmc); + if (rc) + dev_err(kcs_bmc->dev, "Failed to remove chardev for KCS channel %d: %d", + kcs_bmc->channel, rc); + } + mutex_unlock(&kcs_bmc_lock); +} +EXPORT_SYMBOL(kcs_bmc_remove_device); + +void kcs_bmc_register_driver(struct kcs_bmc_driver *drv) +{ + struct kcs_bmc_device *kcs_bmc; + int rc; + + mutex_lock(&kcs_bmc_lock); + list_add(&drv->entry, &kcs_bmc_drivers); + list_for_each_entry(kcs_bmc, &kcs_bmc_devices, entry) { + rc = drv->ops->add_device(kcs_bmc); + if (rc) + dev_err(kcs_bmc->dev, "Failed to add driver for KCS channel %d: %d", + kcs_bmc->channel, rc); + } + mutex_unlock(&kcs_bmc_lock); +} +EXPORT_SYMBOL(kcs_bmc_register_driver); + +void kcs_bmc_unregister_driver(struct kcs_bmc_driver *drv) +{ + struct kcs_bmc_device *kcs_bmc; + int rc; + + mutex_lock(&kcs_bmc_lock); + list_del(&drv->entry); + list_for_each_entry(kcs_bmc, &kcs_bmc_devices, entry) { + rc = drv->ops->remove_device(kcs_bmc); + if (rc) + dev_err(kcs_bmc->dev, "Failed to remove driver for KCS channel %d: %d", + kcs_bmc->channel, rc); + } + mutex_unlock(&kcs_bmc_lock); +} +EXPORT_SYMBOL(kcs_bmc_unregister_driver); + +void kcs_bmc_update_event_mask(struct kcs_bmc_device *kcs_bmc, u8 mask, u8 events) +{ + kcs_bmc->ops->irq_mask_update(kcs_bmc, mask, events); +} +EXPORT_SYMBOL(kcs_bmc_update_event_mask); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Haiyue Wang "); +MODULE_AUTHOR("Andrew Jeffery "); MODULE_DESCRIPTION("KCS BMC to handle the IPMI request from system software"); diff --git a/drivers/char/ipmi/kcs_bmc.h b/drivers/char/ipmi/kcs_bmc.h index eb9ea4ce78b8..fa408b802c79 100644 --- a/drivers/char/ipmi/kcs_bmc.h +++ b/drivers/char/ipmi/kcs_bmc.h @@ -6,54 +6,14 @@ #ifndef __KCS_BMC_H__ #define __KCS_BMC_H__ -#include +#include -/* Different phases of the KCS BMC module. - * KCS_PHASE_IDLE: - * BMC should not be expecting nor sending any data. - * KCS_PHASE_WRITE_START: - * BMC is receiving a WRITE_START command from system software. - * KCS_PHASE_WRITE_DATA: - * BMC is receiving a data byte from system software. - * KCS_PHASE_WRITE_END_CMD: - * BMC is waiting a last data byte from system software. - * KCS_PHASE_WRITE_DONE: - * BMC has received the whole request from system software. - * KCS_PHASE_WAIT_READ: - * BMC is waiting the response from the upper IPMI service. - * KCS_PHASE_READ: - * BMC is transferring the response to system software. - * KCS_PHASE_ABORT_ERROR1: - * BMC is waiting error status request from system software. - * KCS_PHASE_ABORT_ERROR2: - * BMC is waiting for idle status afer error from system software. - * KCS_PHASE_ERROR: - * BMC has detected a protocol violation at the interface level. - */ -enum kcs_phases { - KCS_PHASE_IDLE, +#define KCS_BMC_EVENT_TYPE_OBE BIT(0) +#define KCS_BMC_EVENT_TYPE_IBF BIT(1) - KCS_PHASE_WRITE_START, - KCS_PHASE_WRITE_DATA, - KCS_PHASE_WRITE_END_CMD, - KCS_PHASE_WRITE_DONE, - - KCS_PHASE_WAIT_READ, - KCS_PHASE_READ, - - KCS_PHASE_ABORT_ERROR1, - KCS_PHASE_ABORT_ERROR2, - KCS_PHASE_ERROR -}; - -/* IPMI 2.0 - Table 9-4, KCS Interface Status Codes */ -enum kcs_errors { - KCS_NO_ERROR = 0x00, - KCS_ABORTED_BY_COMMAND = 0x01, - KCS_ILLEGAL_CONTROL_CODE = 0x02, - KCS_LENGTH_ERROR = 0x06, - KCS_UNSPECIFIED_ERROR = 0xFF -}; +#define KCS_BMC_STR_OBF BIT(0) +#define KCS_BMC_STR_IBF BIT(1) +#define KCS_BMC_STR_CMD_DAT BIT(3) /* IPMI 2.0 - 9.5, KCS Interface Registers * @idr: Input Data Register @@ -66,43 +26,21 @@ struct kcs_ioreg { u32 str; }; -struct kcs_bmc { - spinlock_t lock; +struct kcs_bmc_device_ops; +struct kcs_bmc_client; +struct kcs_bmc_device { + struct list_head entry; + + struct device *dev; u32 channel; - int running; - /* Setup by BMC KCS controller driver */ struct kcs_ioreg ioreg; - u8 (*io_inputb)(struct kcs_bmc *kcs_bmc, u32 reg); - void (*io_outputb)(struct kcs_bmc *kcs_bmc, u32 reg, u8 b); - enum kcs_phases phase; - enum kcs_errors error; + const struct kcs_bmc_device_ops *ops; - wait_queue_head_t queue; - bool data_in_avail; - int data_in_idx; - u8 *data_in; - - int data_out_idx; - int data_out_len; - u8 *data_out; - - struct mutex mutex; - u8 *kbuffer; - - struct miscdevice miscdev; - - unsigned long priv[]; + spinlock_t lock; + struct kcs_bmc_client *client; }; -static inline void *kcs_bmc_priv(struct kcs_bmc *kcs_bmc) -{ - return kcs_bmc->priv; -} - -int kcs_bmc_handle_event(struct kcs_bmc *kcs_bmc); -struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, - u32 channel); #endif /* __KCS_BMC_H__ */ diff --git a/drivers/char/ipmi/kcs_bmc_aspeed.c b/drivers/char/ipmi/kcs_bmc_aspeed.c index eefe362f65f0..92a37b33494c 100644 --- a/drivers/char/ipmi/kcs_bmc_aspeed.c +++ b/drivers/char/ipmi/kcs_bmc_aspeed.c @@ -9,10 +9,12 @@ #include #include #include +#include #include #include #include #include +#include #include #include #include @@ -20,24 +22,53 @@ #include #include -#include "kcs_bmc.h" +#include "kcs_bmc_device.h" #define DEVICE_NAME "ast-kcs-bmc" #define KCS_CHANNEL_MAX 4 +/* + * Field class descriptions + * + * LPCyE Enable LPC channel y + * IBFIEy Input Buffer Full IRQ Enable for LPC channel y + * IRQxEy Assert SerIRQ x for LPC channel y (Deprecated, use IDyIRQX, IRQXEy) + * IDyIRQX Use the specified 4-bit SerIRQ for LPC channel y + * SELyIRQX SerIRQ polarity for LPC channel y (low: 0, high: 1) + * IRQXEy Assert the SerIRQ specified in IDyIRQX for LPC channel y + */ + +#define LPC_TYIRQX_LOW 0b00 +#define LPC_TYIRQX_HIGH 0b01 +#define LPC_TYIRQX_RSVD 0b10 +#define LPC_TYIRQX_RISING 0b11 + #define LPC_HICR0 0x000 #define LPC_HICR0_LPC3E BIT(7) #define LPC_HICR0_LPC2E BIT(6) #define LPC_HICR0_LPC1E BIT(5) #define LPC_HICR2 0x008 -#define LPC_HICR2_IBFIF3 BIT(3) -#define LPC_HICR2_IBFIF2 BIT(2) -#define LPC_HICR2_IBFIF1 BIT(1) +#define LPC_HICR2_IBFIE3 BIT(3) +#define LPC_HICR2_IBFIE2 BIT(2) +#define LPC_HICR2_IBFIE1 BIT(1) #define LPC_HICR4 0x010 #define LPC_HICR4_LADR12AS BIT(7) #define LPC_HICR4_KCSENBL BIT(2) +#define LPC_SIRQCR0 0x070 +/* IRQ{12,1}E1 are deprecated as of AST2600 A3 but necessary for prior chips */ +#define LPC_SIRQCR0_IRQ12E1 BIT(1) +#define LPC_SIRQCR0_IRQ1E1 BIT(0) +#define LPC_HICR5 0x080 +#define LPC_HICR5_ID3IRQX_MASK GENMASK(23, 20) +#define LPC_HICR5_ID3IRQX_SHIFT 20 +#define LPC_HICR5_ID2IRQX_MASK GENMASK(19, 16) +#define LPC_HICR5_ID2IRQX_SHIFT 16 +#define LPC_HICR5_SEL3IRQX BIT(15) +#define LPC_HICR5_IRQXE3 BIT(14) +#define LPC_HICR5_SEL2IRQX BIT(13) +#define LPC_HICR5_IRQXE2 BIT(12) #define LPC_LADR3H 0x014 #define LPC_LADR3L 0x018 #define LPC_LADR12H 0x01C @@ -52,21 +83,64 @@ #define LPC_STR2 0x040 #define LPC_STR3 0x044 #define LPC_HICRB 0x100 -#define LPC_HICRB_IBFIF4 BIT(1) +#define LPC_HICRB_EN16LADR2 BIT(5) +#define LPC_HICRB_EN16LADR1 BIT(4) +#define LPC_HICRB_IBFIE4 BIT(1) #define LPC_HICRB_LPC4E BIT(0) +#define LPC_HICRC 0x104 +#define LPC_HICRC_ID4IRQX_MASK GENMASK(7, 4) +#define LPC_HICRC_ID4IRQX_SHIFT 4 +#define LPC_HICRC_TY4IRQX_MASK GENMASK(3, 2) +#define LPC_HICRC_TY4IRQX_SHIFT 2 +#define LPC_HICRC_OBF4_AUTO_CLR BIT(1) +#define LPC_HICRC_IRQXE4 BIT(0) #define LPC_LADR4 0x110 #define LPC_IDR4 0x114 #define LPC_ODR4 0x118 #define LPC_STR4 0x11C +#define LPC_LSADR12 0x120 +#define LPC_LSADR12_LSADR2_MASK GENMASK(31, 16) +#define LPC_LSADR12_LSADR2_SHIFT 16 +#define LPC_LSADR12_LSADR1_MASK GENMASK(15, 0) +#define LPC_LSADR12_LSADR1_SHIFT 0 -struct aspeed_kcs_bmc { - struct regmap *map; +#define OBE_POLL_PERIOD (HZ / 2) + +enum aspeed_kcs_irq_mode { + aspeed_kcs_irq_none, + aspeed_kcs_irq_serirq, }; +struct aspeed_kcs_bmc { + struct kcs_bmc_device kcs_bmc; -static u8 aspeed_kcs_inb(struct kcs_bmc *kcs_bmc, u32 reg) + struct regmap *map; + + struct { + enum aspeed_kcs_irq_mode mode; + int id; + } upstream_irq; + + struct { + spinlock_t lock; + bool remove; + struct timer_list timer; + } obe; +}; + +struct aspeed_kcs_of_ops { + int (*get_channel)(struct platform_device *pdev); + int (*get_io_address)(struct platform_device *pdev, u32 addrs[2]); +}; + +static inline struct aspeed_kcs_bmc *to_aspeed_kcs_bmc(struct kcs_bmc_device *kcs_bmc) { - struct aspeed_kcs_bmc *priv = kcs_bmc_priv(kcs_bmc); + return container_of(kcs_bmc, struct aspeed_kcs_bmc, kcs_bmc); +} + +static u8 aspeed_kcs_inb(struct kcs_bmc_device *kcs_bmc, u32 reg) +{ + struct aspeed_kcs_bmc *priv = to_aspeed_kcs_bmc(kcs_bmc); u32 val = 0; int rc; @@ -76,15 +150,66 @@ static u8 aspeed_kcs_inb(struct kcs_bmc *kcs_bmc, u32 reg) return rc == 0 ? (u8) val : 0; } -static void aspeed_kcs_outb(struct kcs_bmc *kcs_bmc, u32 reg, u8 data) +static void aspeed_kcs_outb(struct kcs_bmc_device *kcs_bmc, u32 reg, u8 data) { - struct aspeed_kcs_bmc *priv = kcs_bmc_priv(kcs_bmc); + struct aspeed_kcs_bmc *priv = to_aspeed_kcs_bmc(kcs_bmc); int rc; rc = regmap_write(priv->map, reg, data); WARN(rc != 0, "regmap_write() failed: %d\n", rc); + + /* Trigger the upstream IRQ on ODR writes, if enabled */ + + switch (reg) { + case LPC_ODR1: + case LPC_ODR2: + case LPC_ODR3: + case LPC_ODR4: + break; + default: + return; + } + + if (priv->upstream_irq.mode != aspeed_kcs_irq_serirq) + return; + + switch (kcs_bmc->channel) { + case 1: + switch (priv->upstream_irq.id) { + case 12: + regmap_update_bits(priv->map, LPC_SIRQCR0, LPC_SIRQCR0_IRQ12E1, + LPC_SIRQCR0_IRQ12E1); + break; + case 1: + regmap_update_bits(priv->map, LPC_SIRQCR0, LPC_SIRQCR0_IRQ1E1, + LPC_SIRQCR0_IRQ1E1); + break; + default: + break; + } + break; + case 2: + regmap_update_bits(priv->map, LPC_HICR5, LPC_HICR5_IRQXE2, LPC_HICR5_IRQXE2); + break; + case 3: + regmap_update_bits(priv->map, LPC_HICR5, LPC_HICR5_IRQXE3, LPC_HICR5_IRQXE3); + break; + case 4: + regmap_update_bits(priv->map, LPC_HICRC, LPC_HICRC_IRQXE4, LPC_HICRC_IRQXE4); + break; + default: + break; + } } +static void aspeed_kcs_updateb(struct kcs_bmc_device *kcs_bmc, u32 reg, u8 mask, u8 val) +{ + struct aspeed_kcs_bmc *priv = to_aspeed_kcs_bmc(kcs_bmc); + int rc; + + rc = regmap_update_bits(priv->map, reg, mask, val); + WARN(rc != 0, "regmap_update_bits() failed: %d\n", rc); +} /* * AST_usrGuide_KCS.pdf @@ -99,118 +224,237 @@ static void aspeed_kcs_outb(struct kcs_bmc *kcs_bmc, u32 reg, u8 data) * C. KCS4 * D / C : CA4h / CA5h */ -static void aspeed_kcs_set_address(struct kcs_bmc *kcs_bmc, u16 addr) +static int aspeed_kcs_set_address(struct kcs_bmc_device *kcs_bmc, u32 addrs[2], int nr_addrs) { - struct aspeed_kcs_bmc *priv = kcs_bmc_priv(kcs_bmc); + struct aspeed_kcs_bmc *priv = to_aspeed_kcs_bmc(kcs_bmc); - switch (kcs_bmc->channel) { + if (WARN_ON(nr_addrs < 1 || nr_addrs > 2)) + return -EINVAL; + + switch (priv->kcs_bmc.channel) { case 1: - regmap_update_bits(priv->map, LPC_HICR4, - LPC_HICR4_LADR12AS, 0); - regmap_write(priv->map, LPC_LADR12H, addr >> 8); - regmap_write(priv->map, LPC_LADR12L, addr & 0xFF); - break; + regmap_update_bits(priv->map, LPC_HICR4, LPC_HICR4_LADR12AS, 0); + regmap_write(priv->map, LPC_LADR12H, addrs[0] >> 8); + regmap_write(priv->map, LPC_LADR12L, addrs[0] & 0xFF); + if (nr_addrs == 2) { + regmap_update_bits(priv->map, LPC_LSADR12, LPC_LSADR12_LSADR1_MASK, + addrs[1] << LPC_LSADR12_LSADR1_SHIFT); - case 2: - regmap_update_bits(priv->map, LPC_HICR4, - LPC_HICR4_LADR12AS, LPC_HICR4_LADR12AS); - regmap_write(priv->map, LPC_LADR12H, addr >> 8); - regmap_write(priv->map, LPC_LADR12L, addr & 0xFF); - break; - - case 3: - regmap_write(priv->map, LPC_LADR3H, addr >> 8); - regmap_write(priv->map, LPC_LADR3L, addr & 0xFF); - break; - - case 4: - regmap_write(priv->map, LPC_LADR4, ((addr + 1) << 16) | - addr); - break; - - default: - break; - } -} - -static void aspeed_kcs_enable_channel(struct kcs_bmc *kcs_bmc, bool enable) -{ - struct aspeed_kcs_bmc *priv = kcs_bmc_priv(kcs_bmc); - - switch (kcs_bmc->channel) { - case 1: - if (enable) { - regmap_update_bits(priv->map, LPC_HICR2, - LPC_HICR2_IBFIF1, LPC_HICR2_IBFIF1); - regmap_update_bits(priv->map, LPC_HICR0, - LPC_HICR0_LPC1E, LPC_HICR0_LPC1E); - } else { - regmap_update_bits(priv->map, LPC_HICR0, - LPC_HICR0_LPC1E, 0); - regmap_update_bits(priv->map, LPC_HICR2, - LPC_HICR2_IBFIF1, 0); + regmap_update_bits(priv->map, LPC_HICRB, LPC_HICRB_EN16LADR1, + LPC_HICRB_EN16LADR1); } break; case 2: - if (enable) { - regmap_update_bits(priv->map, LPC_HICR2, - LPC_HICR2_IBFIF2, LPC_HICR2_IBFIF2); - regmap_update_bits(priv->map, LPC_HICR0, - LPC_HICR0_LPC2E, LPC_HICR0_LPC2E); - } else { - regmap_update_bits(priv->map, LPC_HICR0, - LPC_HICR0_LPC2E, 0); - regmap_update_bits(priv->map, LPC_HICR2, - LPC_HICR2_IBFIF2, 0); + regmap_update_bits(priv->map, LPC_HICR4, LPC_HICR4_LADR12AS, LPC_HICR4_LADR12AS); + regmap_write(priv->map, LPC_LADR12H, addrs[0] >> 8); + regmap_write(priv->map, LPC_LADR12L, addrs[0] & 0xFF); + if (nr_addrs == 2) { + regmap_update_bits(priv->map, LPC_LSADR12, LPC_LSADR12_LSADR2_MASK, + addrs[1] << LPC_LSADR12_LSADR2_SHIFT); + + regmap_update_bits(priv->map, LPC_HICRB, LPC_HICRB_EN16LADR2, + LPC_HICRB_EN16LADR2); } break; case 3: - if (enable) { - regmap_update_bits(priv->map, LPC_HICR2, - LPC_HICR2_IBFIF3, LPC_HICR2_IBFIF3); - regmap_update_bits(priv->map, LPC_HICR0, - LPC_HICR0_LPC3E, LPC_HICR0_LPC3E); - regmap_update_bits(priv->map, LPC_HICR4, - LPC_HICR4_KCSENBL, LPC_HICR4_KCSENBL); - } else { - regmap_update_bits(priv->map, LPC_HICR0, - LPC_HICR0_LPC3E, 0); - regmap_update_bits(priv->map, LPC_HICR4, - LPC_HICR4_KCSENBL, 0); - regmap_update_bits(priv->map, LPC_HICR2, - LPC_HICR2_IBFIF3, 0); + if (nr_addrs == 2) { + dev_err(priv->kcs_bmc.dev, + "Channel 3 only supports inferred status IO address\n"); + return -EINVAL; } + + regmap_write(priv->map, LPC_LADR3H, addrs[0] >> 8); + regmap_write(priv->map, LPC_LADR3L, addrs[0] & 0xFF); break; case 4: - if (enable) - regmap_update_bits(priv->map, LPC_HICRB, - LPC_HICRB_IBFIF4 | LPC_HICRB_LPC4E, - LPC_HICRB_IBFIF4 | LPC_HICRB_LPC4E); + if (nr_addrs == 1) + regmap_write(priv->map, LPC_LADR4, ((addrs[0] + 1) << 16) | addrs[0]); else - regmap_update_bits(priv->map, LPC_HICRB, - LPC_HICRB_IBFIF4 | LPC_HICRB_LPC4E, - 0); + regmap_write(priv->map, LPC_LADR4, (addrs[1] << 16) | addrs[0]); + break; default: - break; + return -EINVAL; + } + + return 0; +} + +static inline int aspeed_kcs_map_serirq_type(u32 dt_type) +{ + switch (dt_type) { + case IRQ_TYPE_EDGE_RISING: + return LPC_TYIRQX_RISING; + case IRQ_TYPE_LEVEL_HIGH: + return LPC_TYIRQX_HIGH; + case IRQ_TYPE_LEVEL_LOW: + return LPC_TYIRQX_LOW; + default: + return -EINVAL; } } +static int aspeed_kcs_config_upstream_irq(struct aspeed_kcs_bmc *priv, u32 id, u32 dt_type) +{ + unsigned int mask, val, hw_type; + int ret; + + if (id > 15) + return -EINVAL; + + ret = aspeed_kcs_map_serirq_type(dt_type); + if (ret < 0) + return ret; + hw_type = ret; + + priv->upstream_irq.mode = aspeed_kcs_irq_serirq; + priv->upstream_irq.id = id; + + switch (priv->kcs_bmc.channel) { + case 1: + /* Needs IRQxE1 rather than (ID1IRQX, SEL1IRQX, IRQXE1) before AST2600 A3 */ + break; + case 2: + if (!(hw_type == LPC_TYIRQX_LOW || hw_type == LPC_TYIRQX_HIGH)) + return -EINVAL; + + mask = LPC_HICR5_SEL2IRQX | LPC_HICR5_ID2IRQX_MASK; + val = (id << LPC_HICR5_ID2IRQX_SHIFT); + val |= (hw_type == LPC_TYIRQX_HIGH) ? LPC_HICR5_SEL2IRQX : 0; + regmap_update_bits(priv->map, LPC_HICR5, mask, val); + + break; + case 3: + if (!(hw_type == LPC_TYIRQX_LOW || hw_type == LPC_TYIRQX_HIGH)) + return -EINVAL; + + mask = LPC_HICR5_SEL3IRQX | LPC_HICR5_ID3IRQX_MASK; + val = (id << LPC_HICR5_ID3IRQX_SHIFT); + val |= (hw_type == LPC_TYIRQX_HIGH) ? LPC_HICR5_SEL3IRQX : 0; + regmap_update_bits(priv->map, LPC_HICR5, mask, val); + + break; + case 4: + mask = LPC_HICRC_ID4IRQX_MASK | LPC_HICRC_TY4IRQX_MASK | LPC_HICRC_OBF4_AUTO_CLR; + val = (id << LPC_HICRC_ID4IRQX_SHIFT) | (hw_type << LPC_HICRC_TY4IRQX_SHIFT); + regmap_update_bits(priv->map, LPC_HICRC, mask, val); + break; + default: + dev_warn(priv->kcs_bmc.dev, + "SerIRQ configuration not supported on KCS channel %d\n", + priv->kcs_bmc.channel); + return -EINVAL; + } + + return 0; +} + +static void aspeed_kcs_enable_channel(struct kcs_bmc_device *kcs_bmc, bool enable) +{ + struct aspeed_kcs_bmc *priv = to_aspeed_kcs_bmc(kcs_bmc); + + switch (kcs_bmc->channel) { + case 1: + regmap_update_bits(priv->map, LPC_HICR0, LPC_HICR0_LPC1E, enable * LPC_HICR0_LPC1E); + return; + case 2: + regmap_update_bits(priv->map, LPC_HICR0, LPC_HICR0_LPC2E, enable * LPC_HICR0_LPC2E); + return; + case 3: + regmap_update_bits(priv->map, LPC_HICR0, LPC_HICR0_LPC3E, enable * LPC_HICR0_LPC3E); + regmap_update_bits(priv->map, LPC_HICR4, + LPC_HICR4_KCSENBL, enable * LPC_HICR4_KCSENBL); + return; + case 4: + regmap_update_bits(priv->map, LPC_HICRB, LPC_HICRB_LPC4E, enable * LPC_HICRB_LPC4E); + return; + default: + pr_warn("%s: Unsupported channel: %d", __func__, kcs_bmc->channel); + return; + } +} + +static void aspeed_kcs_check_obe(struct timer_list *timer) +{ + struct aspeed_kcs_bmc *priv = container_of(timer, struct aspeed_kcs_bmc, obe.timer); + unsigned long flags; + u8 str; + + spin_lock_irqsave(&priv->obe.lock, flags); + if (priv->obe.remove) { + spin_unlock_irqrestore(&priv->obe.lock, flags); + return; + } + + str = aspeed_kcs_inb(&priv->kcs_bmc, priv->kcs_bmc.ioreg.str); + if (str & KCS_BMC_STR_OBF) { + mod_timer(timer, jiffies + OBE_POLL_PERIOD); + spin_unlock_irqrestore(&priv->obe.lock, flags); + return; + } + spin_unlock_irqrestore(&priv->obe.lock, flags); + + kcs_bmc_handle_event(&priv->kcs_bmc); +} + +static void aspeed_kcs_irq_mask_update(struct kcs_bmc_device *kcs_bmc, u8 mask, u8 state) +{ + struct aspeed_kcs_bmc *priv = to_aspeed_kcs_bmc(kcs_bmc); + + /* We don't have an OBE IRQ, emulate it */ + if (mask & KCS_BMC_EVENT_TYPE_OBE) { + if (KCS_BMC_EVENT_TYPE_OBE & state) + mod_timer(&priv->obe.timer, jiffies + OBE_POLL_PERIOD); + else + del_timer(&priv->obe.timer); + } + + if (mask & KCS_BMC_EVENT_TYPE_IBF) { + const bool enable = !!(state & KCS_BMC_EVENT_TYPE_IBF); + + switch (kcs_bmc->channel) { + case 1: + regmap_update_bits(priv->map, LPC_HICR2, LPC_HICR2_IBFIE1, + enable * LPC_HICR2_IBFIE1); + return; + case 2: + regmap_update_bits(priv->map, LPC_HICR2, LPC_HICR2_IBFIE2, + enable * LPC_HICR2_IBFIE2); + return; + case 3: + regmap_update_bits(priv->map, LPC_HICR2, LPC_HICR2_IBFIE3, + enable * LPC_HICR2_IBFIE3); + return; + case 4: + regmap_update_bits(priv->map, LPC_HICRB, LPC_HICRB_IBFIE4, + enable * LPC_HICRB_IBFIE4); + return; + default: + pr_warn("%s: Unsupported channel: %d", __func__, kcs_bmc->channel); + return; + } + } +} + +static const struct kcs_bmc_device_ops aspeed_kcs_ops = { + .irq_mask_update = aspeed_kcs_irq_mask_update, + .io_inputb = aspeed_kcs_inb, + .io_outputb = aspeed_kcs_outb, + .io_updateb = aspeed_kcs_updateb, +}; + static irqreturn_t aspeed_kcs_irq(int irq, void *arg) { - struct kcs_bmc *kcs_bmc = arg; + struct kcs_bmc_device *kcs_bmc = arg; - if (!kcs_bmc_handle_event(kcs_bmc)) - return IRQ_HANDLED; - - return IRQ_NONE; + return kcs_bmc_handle_event(kcs_bmc); } -static int aspeed_kcs_config_irq(struct kcs_bmc *kcs_bmc, +static int aspeed_kcs_config_downstream_irq(struct kcs_bmc_device *kcs_bmc, struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -231,13 +475,10 @@ static const struct kcs_ioreg ast_kcs_bmc_ioregs[KCS_CHANNEL_MAX] = { { .idr = LPC_IDR4, .odr = LPC_ODR4, .str = LPC_STR4 }, }; -static struct kcs_bmc *aspeed_kcs_probe_of_v1(struct platform_device *pdev) +static int aspeed_kcs_of_v1_get_channel(struct platform_device *pdev) { - struct aspeed_kcs_bmc *priv; struct device_node *np; - struct kcs_bmc *kcs; u32 channel; - u32 slave; int rc; np = pdev->dev.of_node; @@ -245,166 +486,213 @@ static struct kcs_bmc *aspeed_kcs_probe_of_v1(struct platform_device *pdev) rc = of_property_read_u32(np, "kcs_chan", &channel); if ((rc != 0) || (channel == 0 || channel > KCS_CHANNEL_MAX)) { dev_err(&pdev->dev, "no valid 'kcs_chan' configured\n"); - return ERR_PTR(-EINVAL); + return -EINVAL; } - kcs = kcs_bmc_alloc(&pdev->dev, sizeof(struct aspeed_kcs_bmc), channel); - if (!kcs) - return ERR_PTR(-ENOMEM); + return channel; +} - priv = kcs_bmc_priv(kcs); - priv->map = syscon_node_to_regmap(pdev->dev.parent->of_node); - if (IS_ERR(priv->map)) { - dev_err(&pdev->dev, "Couldn't get regmap\n"); - return ERR_PTR(-ENODEV); - } +static int +aspeed_kcs_of_v1_get_io_address(struct platform_device *pdev, u32 addrs[2]) +{ + int rc; - rc = of_property_read_u32(np, "kcs_addr", &slave); - if (rc) { + rc = of_property_read_u32(pdev->dev.of_node, "kcs_addr", addrs); + if (rc || addrs[0] > 0xffff) { dev_err(&pdev->dev, "no valid 'kcs_addr' configured\n"); - return ERR_PTR(-EINVAL); + return -EINVAL; } - kcs->ioreg = ast_kcs_bmc_ioregs[channel - 1]; - aspeed_kcs_set_address(kcs, slave); - - return kcs; + return 1; } -static int aspeed_kcs_calculate_channel(const struct kcs_ioreg *regs) +static int aspeed_kcs_of_v2_get_channel(struct platform_device *pdev) { - int i; - - for (i = 0; i < ARRAY_SIZE(ast_kcs_bmc_ioregs); i++) { - if (!memcmp(&ast_kcs_bmc_ioregs[i], regs, sizeof(*regs))) - return i + 1; - } - - return -EINVAL; -} - -static struct kcs_bmc *aspeed_kcs_probe_of_v2(struct platform_device *pdev) -{ - struct aspeed_kcs_bmc *priv; struct device_node *np; struct kcs_ioreg ioreg; - struct kcs_bmc *kcs; const __be32 *reg; - int channel; - u32 slave; - int rc; + int i; np = pdev->dev.of_node; /* Don't translate addresses, we want offsets for the regmaps */ reg = of_get_address(np, 0, NULL, NULL); if (!reg) - return ERR_PTR(-EINVAL); + return -EINVAL; ioreg.idr = be32_to_cpup(reg); reg = of_get_address(np, 1, NULL, NULL); if (!reg) - return ERR_PTR(-EINVAL); + return -EINVAL; ioreg.odr = be32_to_cpup(reg); reg = of_get_address(np, 2, NULL, NULL); if (!reg) - return ERR_PTR(-EINVAL); + return -EINVAL; ioreg.str = be32_to_cpup(reg); - channel = aspeed_kcs_calculate_channel(&ioreg); - if (channel < 0) - return ERR_PTR(channel); - - kcs = kcs_bmc_alloc(&pdev->dev, sizeof(struct aspeed_kcs_bmc), channel); - if (!kcs) - return ERR_PTR(-ENOMEM); - - kcs->ioreg = ioreg; - - priv = kcs_bmc_priv(kcs); - priv->map = syscon_node_to_regmap(pdev->dev.parent->of_node); - if (IS_ERR(priv->map)) { - dev_err(&pdev->dev, "Couldn't get regmap\n"); - return ERR_PTR(-ENODEV); + for (i = 0; i < ARRAY_SIZE(ast_kcs_bmc_ioregs); i++) { + if (!memcmp(&ast_kcs_bmc_ioregs[i], &ioreg, sizeof(ioreg))) + return i + 1; } - rc = of_property_read_u32(np, "aspeed,lpc-io-reg", &slave); - if (rc) - return ERR_PTR(rc); + return -EINVAL; +} - aspeed_kcs_set_address(kcs, slave); +static int +aspeed_kcs_of_v2_get_io_address(struct platform_device *pdev, u32 addrs[2]) +{ + int rc; - return kcs; + rc = of_property_read_variable_u32_array(pdev->dev.of_node, + "aspeed,lpc-io-reg", + addrs, 1, 2); + if (rc < 0) { + dev_err(&pdev->dev, "No valid 'aspeed,lpc-io-reg' configured\n"); + return rc; + } + + if (addrs[0] > 0xffff) { + dev_err(&pdev->dev, "Invalid data address in 'aspeed,lpc-io-reg'\n"); + return -EINVAL; + } + + if (rc == 2 && addrs[1] > 0xffff) { + dev_err(&pdev->dev, "Invalid status address in 'aspeed,lpc-io-reg'\n"); + return -EINVAL; + } + + return rc; } static int aspeed_kcs_probe(struct platform_device *pdev) { - struct device *dev = &pdev->dev; - struct kcs_bmc *kcs_bmc; + const struct aspeed_kcs_of_ops *ops; + struct kcs_bmc_device *kcs_bmc; + struct aspeed_kcs_bmc *priv; struct device_node *np; - int rc; + bool have_upstream_irq; + u32 upstream_irq[2]; + int rc, channel; + int nr_addrs; + u32 addrs[2]; - np = dev->of_node->parent; + np = pdev->dev.of_node->parent; if (!of_device_is_compatible(np, "aspeed,ast2400-lpc-v2") && !of_device_is_compatible(np, "aspeed,ast2500-lpc-v2") && !of_device_is_compatible(np, "aspeed,ast2600-lpc-v2")) { - dev_err(dev, "unsupported LPC device binding\n"); + dev_err(&pdev->dev, "unsupported LPC device binding\n"); return -ENODEV; } - np = dev->of_node; - if (of_device_is_compatible(np, "aspeed,ast2400-kcs-bmc") || - of_device_is_compatible(np, "aspeed,ast2500-kcs-bmc")) - kcs_bmc = aspeed_kcs_probe_of_v1(pdev); - else if (of_device_is_compatible(np, "aspeed,ast2400-kcs-bmc-v2") || - of_device_is_compatible(np, "aspeed,ast2500-kcs-bmc-v2")) - kcs_bmc = aspeed_kcs_probe_of_v2(pdev); - else + ops = of_device_get_match_data(&pdev->dev); + if (!ops) return -EINVAL; - if (IS_ERR(kcs_bmc)) - return PTR_ERR(kcs_bmc); + channel = ops->get_channel(pdev); + if (channel < 0) + return channel; - kcs_bmc->io_inputb = aspeed_kcs_inb; - kcs_bmc->io_outputb = aspeed_kcs_outb; + nr_addrs = ops->get_io_address(pdev, addrs); + if (nr_addrs < 0) + return nr_addrs; - rc = aspeed_kcs_config_irq(kcs_bmc, pdev); + np = pdev->dev.of_node; + rc = of_property_read_u32_array(np, "aspeed,lpc-interrupts", upstream_irq, 2); + if (rc && rc != -EINVAL) + return -EINVAL; + + have_upstream_irq = !rc; + + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + kcs_bmc = &priv->kcs_bmc; + kcs_bmc->dev = &pdev->dev; + kcs_bmc->channel = channel; + kcs_bmc->ioreg = ast_kcs_bmc_ioregs[channel - 1]; + kcs_bmc->ops = &aspeed_kcs_ops; + + priv->map = syscon_node_to_regmap(pdev->dev.parent->of_node); + if (IS_ERR(priv->map)) { + dev_err(&pdev->dev, "Couldn't get regmap\n"); + return -ENODEV; + } + + spin_lock_init(&priv->obe.lock); + priv->obe.remove = false; + timer_setup(&priv->obe.timer, aspeed_kcs_check_obe, 0); + + rc = aspeed_kcs_set_address(kcs_bmc, addrs, nr_addrs); if (rc) return rc; - dev_set_drvdata(dev, kcs_bmc); + /* Host to BMC IRQ */ + rc = aspeed_kcs_config_downstream_irq(kcs_bmc, pdev); + if (rc) + return rc; + /* BMC to Host IRQ */ + if (have_upstream_irq) { + rc = aspeed_kcs_config_upstream_irq(priv, upstream_irq[0], upstream_irq[1]); + if (rc < 0) + return rc; + } else { + priv->upstream_irq.mode = aspeed_kcs_irq_none; + } + + platform_set_drvdata(pdev, priv); + + aspeed_kcs_irq_mask_update(kcs_bmc, (KCS_BMC_EVENT_TYPE_IBF | KCS_BMC_EVENT_TYPE_OBE), 0); aspeed_kcs_enable_channel(kcs_bmc, true); - rc = misc_register(&kcs_bmc->miscdev); + rc = kcs_bmc_add_device(&priv->kcs_bmc); if (rc) { - dev_err(dev, "Unable to register device\n"); + dev_warn(&pdev->dev, "Failed to register channel %d: %d\n", kcs_bmc->channel, rc); return rc; } - dev_dbg(&pdev->dev, - "Probed KCS device %d (IDR=0x%x, ODR=0x%x, STR=0x%x)\n", - kcs_bmc->channel, kcs_bmc->ioreg.idr, kcs_bmc->ioreg.odr, - kcs_bmc->ioreg.str); + dev_info(&pdev->dev, "Initialised channel %d at 0x%x\n", + kcs_bmc->channel, addrs[0]); return 0; } static int aspeed_kcs_remove(struct platform_device *pdev) { - struct kcs_bmc *kcs_bmc = dev_get_drvdata(&pdev->dev); + struct aspeed_kcs_bmc *priv = platform_get_drvdata(pdev); + struct kcs_bmc_device *kcs_bmc = &priv->kcs_bmc; - misc_deregister(&kcs_bmc->miscdev); + kcs_bmc_remove_device(kcs_bmc); + + aspeed_kcs_enable_channel(kcs_bmc, false); + aspeed_kcs_irq_mask_update(kcs_bmc, (KCS_BMC_EVENT_TYPE_IBF | KCS_BMC_EVENT_TYPE_OBE), 0); + + /* Make sure it's proper dead */ + spin_lock_irq(&priv->obe.lock); + priv->obe.remove = true; + spin_unlock_irq(&priv->obe.lock); + del_timer_sync(&priv->obe.timer); return 0; } +static const struct aspeed_kcs_of_ops of_v1_ops = { + .get_channel = aspeed_kcs_of_v1_get_channel, + .get_io_address = aspeed_kcs_of_v1_get_io_address, +}; + +static const struct aspeed_kcs_of_ops of_v2_ops = { + .get_channel = aspeed_kcs_of_v2_get_channel, + .get_io_address = aspeed_kcs_of_v2_get_io_address, +}; + static const struct of_device_id ast_kcs_bmc_match[] = { - { .compatible = "aspeed,ast2400-kcs-bmc" }, - { .compatible = "aspeed,ast2500-kcs-bmc" }, - { .compatible = "aspeed,ast2400-kcs-bmc-v2" }, - { .compatible = "aspeed,ast2500-kcs-bmc-v2" }, + { .compatible = "aspeed,ast2400-kcs-bmc", .data = &of_v1_ops }, + { .compatible = "aspeed,ast2500-kcs-bmc", .data = &of_v1_ops }, + { .compatible = "aspeed,ast2400-kcs-bmc-v2", .data = &of_v2_ops }, + { .compatible = "aspeed,ast2500-kcs-bmc-v2", .data = &of_v2_ops }, { } }; MODULE_DEVICE_TABLE(of, ast_kcs_bmc_match); @@ -421,4 +709,5 @@ module_platform_driver(ast_kcs_bmc_driver); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Haiyue Wang "); +MODULE_AUTHOR("Andrew Jeffery "); MODULE_DESCRIPTION("Aspeed device interface to the KCS BMC device"); diff --git a/drivers/char/ipmi/kcs_bmc_cdev_ipmi.c b/drivers/char/ipmi/kcs_bmc_cdev_ipmi.c new file mode 100644 index 000000000000..486834a962c3 --- /dev/null +++ b/drivers/char/ipmi/kcs_bmc_cdev_ipmi.c @@ -0,0 +1,568 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2015-2018, Intel Corporation. + */ + +#define pr_fmt(fmt) "kcs-bmc: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "kcs_bmc_client.h" + +/* Different phases of the KCS BMC module. + * KCS_PHASE_IDLE: + * BMC should not be expecting nor sending any data. + * KCS_PHASE_WRITE_START: + * BMC is receiving a WRITE_START command from system software. + * KCS_PHASE_WRITE_DATA: + * BMC is receiving a data byte from system software. + * KCS_PHASE_WRITE_END_CMD: + * BMC is waiting a last data byte from system software. + * KCS_PHASE_WRITE_DONE: + * BMC has received the whole request from system software. + * KCS_PHASE_WAIT_READ: + * BMC is waiting the response from the upper IPMI service. + * KCS_PHASE_READ: + * BMC is transferring the response to system software. + * KCS_PHASE_ABORT_ERROR1: + * BMC is waiting error status request from system software. + * KCS_PHASE_ABORT_ERROR2: + * BMC is waiting for idle status afer error from system software. + * KCS_PHASE_ERROR: + * BMC has detected a protocol violation at the interface level. + */ +enum kcs_ipmi_phases { + KCS_PHASE_IDLE, + + KCS_PHASE_WRITE_START, + KCS_PHASE_WRITE_DATA, + KCS_PHASE_WRITE_END_CMD, + KCS_PHASE_WRITE_DONE, + + KCS_PHASE_WAIT_READ, + KCS_PHASE_READ, + + KCS_PHASE_ABORT_ERROR1, + KCS_PHASE_ABORT_ERROR2, + KCS_PHASE_ERROR +}; + +/* IPMI 2.0 - Table 9-4, KCS Interface Status Codes */ +enum kcs_ipmi_errors { + KCS_NO_ERROR = 0x00, + KCS_ABORTED_BY_COMMAND = 0x01, + KCS_ILLEGAL_CONTROL_CODE = 0x02, + KCS_LENGTH_ERROR = 0x06, + KCS_UNSPECIFIED_ERROR = 0xFF +}; + +struct kcs_bmc_ipmi { + struct list_head entry; + + struct kcs_bmc_client client; + + spinlock_t lock; + + enum kcs_ipmi_phases phase; + enum kcs_ipmi_errors error; + + wait_queue_head_t queue; + bool data_in_avail; + int data_in_idx; + u8 *data_in; + + int data_out_idx; + int data_out_len; + u8 *data_out; + + struct mutex mutex; + u8 *kbuffer; + + struct miscdevice miscdev; +}; + +#define DEVICE_NAME "ipmi-kcs" + +#define KCS_MSG_BUFSIZ 1000 + +#define KCS_ZERO_DATA 0 + +/* IPMI 2.0 - Table 9-1, KCS Interface Status Register Bits */ +#define KCS_STATUS_STATE(state) (state << 6) +#define KCS_STATUS_STATE_MASK GENMASK(7, 6) +#define KCS_STATUS_CMD_DAT BIT(3) +#define KCS_STATUS_SMS_ATN BIT(2) +#define KCS_STATUS_IBF BIT(1) +#define KCS_STATUS_OBF BIT(0) + +/* IPMI 2.0 - Table 9-2, KCS Interface State Bits */ +enum kcs_states { + IDLE_STATE = 0, + READ_STATE = 1, + WRITE_STATE = 2, + ERROR_STATE = 3, +}; + +/* IPMI 2.0 - Table 9-3, KCS Interface Control Codes */ +#define KCS_CMD_GET_STATUS_ABORT 0x60 +#define KCS_CMD_WRITE_START 0x61 +#define KCS_CMD_WRITE_END 0x62 +#define KCS_CMD_READ_BYTE 0x68 + +static inline void set_state(struct kcs_bmc_ipmi *priv, u8 state) +{ + kcs_bmc_update_status(priv->client.dev, KCS_STATUS_STATE_MASK, KCS_STATUS_STATE(state)); +} + +static void kcs_bmc_ipmi_force_abort(struct kcs_bmc_ipmi *priv) +{ + set_state(priv, ERROR_STATE); + kcs_bmc_read_data(priv->client.dev); + kcs_bmc_write_data(priv->client.dev, KCS_ZERO_DATA); + + priv->phase = KCS_PHASE_ERROR; + priv->data_in_avail = false; + priv->data_in_idx = 0; +} + +static void kcs_bmc_ipmi_handle_data(struct kcs_bmc_ipmi *priv) +{ + struct kcs_bmc_device *dev; + u8 data; + + dev = priv->client.dev; + + switch (priv->phase) { + case KCS_PHASE_WRITE_START: + priv->phase = KCS_PHASE_WRITE_DATA; + fallthrough; + + case KCS_PHASE_WRITE_DATA: + if (priv->data_in_idx < KCS_MSG_BUFSIZ) { + set_state(priv, WRITE_STATE); + kcs_bmc_write_data(dev, KCS_ZERO_DATA); + priv->data_in[priv->data_in_idx++] = kcs_bmc_read_data(dev); + } else { + kcs_bmc_ipmi_force_abort(priv); + priv->error = KCS_LENGTH_ERROR; + } + break; + + case KCS_PHASE_WRITE_END_CMD: + if (priv->data_in_idx < KCS_MSG_BUFSIZ) { + set_state(priv, READ_STATE); + priv->data_in[priv->data_in_idx++] = kcs_bmc_read_data(dev); + priv->phase = KCS_PHASE_WRITE_DONE; + priv->data_in_avail = true; + wake_up_interruptible(&priv->queue); + } else { + kcs_bmc_ipmi_force_abort(priv); + priv->error = KCS_LENGTH_ERROR; + } + break; + + case KCS_PHASE_READ: + if (priv->data_out_idx == priv->data_out_len) + set_state(priv, IDLE_STATE); + + data = kcs_bmc_read_data(dev); + if (data != KCS_CMD_READ_BYTE) { + set_state(priv, ERROR_STATE); + kcs_bmc_write_data(dev, KCS_ZERO_DATA); + break; + } + + if (priv->data_out_idx == priv->data_out_len) { + kcs_bmc_write_data(dev, KCS_ZERO_DATA); + priv->phase = KCS_PHASE_IDLE; + break; + } + + kcs_bmc_write_data(dev, priv->data_out[priv->data_out_idx++]); + break; + + case KCS_PHASE_ABORT_ERROR1: + set_state(priv, READ_STATE); + kcs_bmc_read_data(dev); + kcs_bmc_write_data(dev, priv->error); + priv->phase = KCS_PHASE_ABORT_ERROR2; + break; + + case KCS_PHASE_ABORT_ERROR2: + set_state(priv, IDLE_STATE); + kcs_bmc_read_data(dev); + kcs_bmc_write_data(dev, KCS_ZERO_DATA); + priv->phase = KCS_PHASE_IDLE; + break; + + default: + kcs_bmc_ipmi_force_abort(priv); + break; + } +} + +static void kcs_bmc_ipmi_handle_cmd(struct kcs_bmc_ipmi *priv) +{ + u8 cmd; + + set_state(priv, WRITE_STATE); + kcs_bmc_write_data(priv->client.dev, KCS_ZERO_DATA); + + cmd = kcs_bmc_read_data(priv->client.dev); + switch (cmd) { + case KCS_CMD_WRITE_START: + priv->phase = KCS_PHASE_WRITE_START; + priv->error = KCS_NO_ERROR; + priv->data_in_avail = false; + priv->data_in_idx = 0; + break; + + case KCS_CMD_WRITE_END: + if (priv->phase != KCS_PHASE_WRITE_DATA) { + kcs_bmc_ipmi_force_abort(priv); + break; + } + + priv->phase = KCS_PHASE_WRITE_END_CMD; + break; + + case KCS_CMD_GET_STATUS_ABORT: + if (priv->error == KCS_NO_ERROR) + priv->error = KCS_ABORTED_BY_COMMAND; + + priv->phase = KCS_PHASE_ABORT_ERROR1; + priv->data_in_avail = false; + priv->data_in_idx = 0; + break; + + default: + kcs_bmc_ipmi_force_abort(priv); + priv->error = KCS_ILLEGAL_CONTROL_CODE; + break; + } +} + +static inline struct kcs_bmc_ipmi *client_to_kcs_bmc_ipmi(struct kcs_bmc_client *client) +{ + return container_of(client, struct kcs_bmc_ipmi, client); +} + +static irqreturn_t kcs_bmc_ipmi_event(struct kcs_bmc_client *client) +{ + struct kcs_bmc_ipmi *priv; + u8 status; + int ret; + + priv = client_to_kcs_bmc_ipmi(client); + if (!priv) + return IRQ_NONE; + + spin_lock(&priv->lock); + + status = kcs_bmc_read_status(client->dev); + if (status & KCS_STATUS_IBF) { + if (status & KCS_STATUS_CMD_DAT) + kcs_bmc_ipmi_handle_cmd(priv); + else + kcs_bmc_ipmi_handle_data(priv); + + ret = IRQ_HANDLED; + } else { + ret = IRQ_NONE; + } + + spin_unlock(&priv->lock); + + return ret; +} + +static const struct kcs_bmc_client_ops kcs_bmc_ipmi_client_ops = { + .event = kcs_bmc_ipmi_event, +}; + +static inline struct kcs_bmc_ipmi *to_kcs_bmc(struct file *filp) +{ + return container_of(filp->private_data, struct kcs_bmc_ipmi, miscdev); +} + +static int kcs_bmc_ipmi_open(struct inode *inode, struct file *filp) +{ + struct kcs_bmc_ipmi *priv = to_kcs_bmc(filp); + + return kcs_bmc_enable_device(priv->client.dev, &priv->client); +} + +static __poll_t kcs_bmc_ipmi_poll(struct file *filp, poll_table *wait) +{ + struct kcs_bmc_ipmi *priv = to_kcs_bmc(filp); + __poll_t mask = 0; + + poll_wait(filp, &priv->queue, wait); + + spin_lock_irq(&priv->lock); + if (priv->data_in_avail) + mask |= EPOLLIN; + spin_unlock_irq(&priv->lock); + + return mask; +} + +static ssize_t kcs_bmc_ipmi_read(struct file *filp, char __user *buf, + size_t count, loff_t *ppos) +{ + struct kcs_bmc_ipmi *priv = to_kcs_bmc(filp); + bool data_avail; + size_t data_len; + ssize_t ret; + + if (!(filp->f_flags & O_NONBLOCK)) + wait_event_interruptible(priv->queue, + priv->data_in_avail); + + mutex_lock(&priv->mutex); + + spin_lock_irq(&priv->lock); + data_avail = priv->data_in_avail; + if (data_avail) { + data_len = priv->data_in_idx; + memcpy(priv->kbuffer, priv->data_in, data_len); + } + spin_unlock_irq(&priv->lock); + + if (!data_avail) { + ret = -EAGAIN; + goto out_unlock; + } + + if (count < data_len) { + pr_err("channel=%u with too large data : %zu\n", + priv->client.dev->channel, data_len); + + spin_lock_irq(&priv->lock); + kcs_bmc_ipmi_force_abort(priv); + spin_unlock_irq(&priv->lock); + + ret = -EOVERFLOW; + goto out_unlock; + } + + if (copy_to_user(buf, priv->kbuffer, data_len)) { + ret = -EFAULT; + goto out_unlock; + } + + ret = data_len; + + spin_lock_irq(&priv->lock); + if (priv->phase == KCS_PHASE_WRITE_DONE) { + priv->phase = KCS_PHASE_WAIT_READ; + priv->data_in_avail = false; + priv->data_in_idx = 0; + } else { + ret = -EAGAIN; + } + spin_unlock_irq(&priv->lock); + +out_unlock: + mutex_unlock(&priv->mutex); + + return ret; +} + +static ssize_t kcs_bmc_ipmi_write(struct file *filp, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct kcs_bmc_ipmi *priv = to_kcs_bmc(filp); + ssize_t ret; + + /* a minimum response size '3' : netfn + cmd + ccode */ + if (count < 3 || count > KCS_MSG_BUFSIZ) + return -EINVAL; + + mutex_lock(&priv->mutex); + + if (copy_from_user(priv->kbuffer, buf, count)) { + ret = -EFAULT; + goto out_unlock; + } + + spin_lock_irq(&priv->lock); + if (priv->phase == KCS_PHASE_WAIT_READ) { + priv->phase = KCS_PHASE_READ; + priv->data_out_idx = 1; + priv->data_out_len = count; + memcpy(priv->data_out, priv->kbuffer, count); + kcs_bmc_write_data(priv->client.dev, priv->data_out[0]); + ret = count; + } else { + ret = -EINVAL; + } + spin_unlock_irq(&priv->lock); + +out_unlock: + mutex_unlock(&priv->mutex); + + return ret; +} + +static long kcs_bmc_ipmi_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + struct kcs_bmc_ipmi *priv = to_kcs_bmc(filp); + long ret = 0; + + spin_lock_irq(&priv->lock); + + switch (cmd) { + case IPMI_BMC_IOCTL_SET_SMS_ATN: + kcs_bmc_update_status(priv->client.dev, KCS_STATUS_SMS_ATN, KCS_STATUS_SMS_ATN); + break; + + case IPMI_BMC_IOCTL_CLEAR_SMS_ATN: + kcs_bmc_update_status(priv->client.dev, KCS_STATUS_SMS_ATN, 0); + break; + + case IPMI_BMC_IOCTL_FORCE_ABORT: + kcs_bmc_ipmi_force_abort(priv); + break; + + default: + ret = -EINVAL; + break; + } + + spin_unlock_irq(&priv->lock); + + return ret; +} + +static int kcs_bmc_ipmi_release(struct inode *inode, struct file *filp) +{ + struct kcs_bmc_ipmi *priv = to_kcs_bmc(filp); + + kcs_bmc_ipmi_force_abort(priv); + kcs_bmc_disable_device(priv->client.dev, &priv->client); + + return 0; +} + +static const struct file_operations kcs_bmc_ipmi_fops = { + .owner = THIS_MODULE, + .open = kcs_bmc_ipmi_open, + .read = kcs_bmc_ipmi_read, + .write = kcs_bmc_ipmi_write, + .release = kcs_bmc_ipmi_release, + .poll = kcs_bmc_ipmi_poll, + .unlocked_ioctl = kcs_bmc_ipmi_ioctl, +}; + +static DEFINE_SPINLOCK(kcs_bmc_ipmi_instances_lock); +static LIST_HEAD(kcs_bmc_ipmi_instances); + +static int kcs_bmc_ipmi_add_device(struct kcs_bmc_device *kcs_bmc) +{ + struct kcs_bmc_ipmi *priv; + int rc; + + priv = devm_kzalloc(kcs_bmc->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + spin_lock_init(&priv->lock); + mutex_init(&priv->mutex); + + init_waitqueue_head(&priv->queue); + + priv->client.dev = kcs_bmc; + priv->client.ops = &kcs_bmc_ipmi_client_ops; + priv->data_in = devm_kmalloc(kcs_bmc->dev, KCS_MSG_BUFSIZ, GFP_KERNEL); + priv->data_out = devm_kmalloc(kcs_bmc->dev, KCS_MSG_BUFSIZ, GFP_KERNEL); + priv->kbuffer = devm_kmalloc(kcs_bmc->dev, KCS_MSG_BUFSIZ, GFP_KERNEL); + + priv->miscdev.minor = MISC_DYNAMIC_MINOR; + priv->miscdev.name = devm_kasprintf(kcs_bmc->dev, GFP_KERNEL, "%s%u", DEVICE_NAME, + kcs_bmc->channel); + if (!priv->data_in || !priv->data_out || !priv->kbuffer || !priv->miscdev.name) + return -EINVAL; + + priv->miscdev.fops = &kcs_bmc_ipmi_fops; + + rc = misc_register(&priv->miscdev); + if (rc) { + dev_err(kcs_bmc->dev, "Unable to register device: %d\n", rc); + return rc; + } + + spin_lock_irq(&kcs_bmc_ipmi_instances_lock); + list_add(&priv->entry, &kcs_bmc_ipmi_instances); + spin_unlock_irq(&kcs_bmc_ipmi_instances_lock); + + dev_info(kcs_bmc->dev, "Initialised IPMI client for channel %d", kcs_bmc->channel); + + return 0; +} + +static int kcs_bmc_ipmi_remove_device(struct kcs_bmc_device *kcs_bmc) +{ + struct kcs_bmc_ipmi *priv = NULL, *pos; + + spin_lock_irq(&kcs_bmc_ipmi_instances_lock); + list_for_each_entry(pos, &kcs_bmc_ipmi_instances, entry) { + if (pos->client.dev == kcs_bmc) { + priv = pos; + list_del(&pos->entry); + break; + } + } + spin_unlock_irq(&kcs_bmc_ipmi_instances_lock); + + if (!priv) + return -ENODEV; + + misc_deregister(&priv->miscdev); + kcs_bmc_disable_device(priv->client.dev, &priv->client); + devm_kfree(kcs_bmc->dev, priv->kbuffer); + devm_kfree(kcs_bmc->dev, priv->data_out); + devm_kfree(kcs_bmc->dev, priv->data_in); + devm_kfree(kcs_bmc->dev, priv); + + return 0; +} + +static const struct kcs_bmc_driver_ops kcs_bmc_ipmi_driver_ops = { + .add_device = kcs_bmc_ipmi_add_device, + .remove_device = kcs_bmc_ipmi_remove_device, +}; + +static struct kcs_bmc_driver kcs_bmc_ipmi_driver = { + .ops = &kcs_bmc_ipmi_driver_ops, +}; + +static int kcs_bmc_ipmi_init(void) +{ + kcs_bmc_register_driver(&kcs_bmc_ipmi_driver); + + return 0; +} +module_init(kcs_bmc_ipmi_init); + +static void kcs_bmc_ipmi_exit(void) +{ + kcs_bmc_unregister_driver(&kcs_bmc_ipmi_driver); +} +module_exit(kcs_bmc_ipmi_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Haiyue Wang "); +MODULE_AUTHOR("Andrew Jeffery "); +MODULE_DESCRIPTION("KCS BMC to handle the IPMI request from system software"); diff --git a/drivers/char/ipmi/kcs_bmc_client.h b/drivers/char/ipmi/kcs_bmc_client.h new file mode 100644 index 000000000000..6fdcde0a7169 --- /dev/null +++ b/drivers/char/ipmi/kcs_bmc_client.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2021, IBM Corp. */ + +#ifndef __KCS_BMC_CONSUMER_H__ +#define __KCS_BMC_CONSUMER_H__ + +#include + +#include "kcs_bmc.h" + +struct kcs_bmc_driver_ops { + int (*add_device)(struct kcs_bmc_device *kcs_bmc); + int (*remove_device)(struct kcs_bmc_device *kcs_bmc); +}; + +struct kcs_bmc_driver { + struct list_head entry; + + const struct kcs_bmc_driver_ops *ops; +}; + +struct kcs_bmc_client_ops { + irqreturn_t (*event)(struct kcs_bmc_client *client); +}; + +struct kcs_bmc_client { + const struct kcs_bmc_client_ops *ops; + + struct kcs_bmc_device *dev; +}; + +void kcs_bmc_register_driver(struct kcs_bmc_driver *drv); +void kcs_bmc_unregister_driver(struct kcs_bmc_driver *drv); + +int kcs_bmc_enable_device(struct kcs_bmc_device *kcs_bmc, struct kcs_bmc_client *client); +void kcs_bmc_disable_device(struct kcs_bmc_device *kcs_bmc, struct kcs_bmc_client *client); + +void kcs_bmc_update_event_mask(struct kcs_bmc_device *kcs_bmc, u8 mask, u8 events); + +u8 kcs_bmc_read_data(struct kcs_bmc_device *kcs_bmc); +void kcs_bmc_write_data(struct kcs_bmc_device *kcs_bmc, u8 data); +u8 kcs_bmc_read_status(struct kcs_bmc_device *kcs_bmc); +void kcs_bmc_write_status(struct kcs_bmc_device *kcs_bmc, u8 data); +void kcs_bmc_update_status(struct kcs_bmc_device *kcs_bmc, u8 mask, u8 val); +#endif diff --git a/drivers/char/ipmi/kcs_bmc_device.h b/drivers/char/ipmi/kcs_bmc_device.h new file mode 100644 index 000000000000..17c572f25c54 --- /dev/null +++ b/drivers/char/ipmi/kcs_bmc_device.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2021, IBM Corp. */ + +#ifndef __KCS_BMC_DEVICE_H__ +#define __KCS_BMC_DEVICE_H__ + +#include + +#include "kcs_bmc.h" + +struct kcs_bmc_device_ops { + void (*irq_mask_update)(struct kcs_bmc_device *kcs_bmc, u8 mask, u8 enable); + u8 (*io_inputb)(struct kcs_bmc_device *kcs_bmc, u32 reg); + void (*io_outputb)(struct kcs_bmc_device *kcs_bmc, u32 reg, u8 b); + void (*io_updateb)(struct kcs_bmc_device *kcs_bmc, u32 reg, u8 mask, u8 b); +}; + +irqreturn_t kcs_bmc_handle_event(struct kcs_bmc_device *kcs_bmc); +int kcs_bmc_add_device(struct kcs_bmc_device *kcs_bmc); +void kcs_bmc_remove_device(struct kcs_bmc_device *kcs_bmc); + +#endif diff --git a/drivers/char/ipmi/kcs_bmc_npcm7xx.c b/drivers/char/ipmi/kcs_bmc_npcm7xx.c index 722f7391fe1f..7961fec56476 100644 --- a/drivers/char/ipmi/kcs_bmc_npcm7xx.c +++ b/drivers/char/ipmi/kcs_bmc_npcm7xx.c @@ -17,7 +17,7 @@ #include #include -#include "kcs_bmc.h" +#include "kcs_bmc_device.h" #define DEVICE_NAME "npcm-kcs-bmc" #define KCS_CHANNEL_MAX 3 @@ -38,6 +38,7 @@ #define KCS2CTL 0x2A #define KCS3CTL 0x3C #define KCS_CTL_IBFIE BIT(0) +#define KCS_CTL_OBEIE BIT(1) #define KCS1IE 0x1C #define KCS2IE 0x2E @@ -65,6 +66,8 @@ struct npcm7xx_kcs_reg { }; struct npcm7xx_kcs_bmc { + struct kcs_bmc_device kcs_bmc; + struct regmap *map; const struct npcm7xx_kcs_reg *reg; @@ -76,9 +79,14 @@ static const struct npcm7xx_kcs_reg npcm7xx_kcs_reg_tbl[KCS_CHANNEL_MAX] = { { .sts = KCS3ST, .dob = KCS3DO, .dib = KCS3DI, .ctl = KCS3CTL, .ie = KCS3IE }, }; -static u8 npcm7xx_kcs_inb(struct kcs_bmc *kcs_bmc, u32 reg) +static inline struct npcm7xx_kcs_bmc *to_npcm7xx_kcs_bmc(struct kcs_bmc_device *kcs_bmc) { - struct npcm7xx_kcs_bmc *priv = kcs_bmc_priv(kcs_bmc); + return container_of(kcs_bmc, struct npcm7xx_kcs_bmc, kcs_bmc); +} + +static u8 npcm7xx_kcs_inb(struct kcs_bmc_device *kcs_bmc, u32 reg) +{ + struct npcm7xx_kcs_bmc *priv = to_npcm7xx_kcs_bmc(kcs_bmc); u32 val = 0; int rc; @@ -88,37 +96,53 @@ static u8 npcm7xx_kcs_inb(struct kcs_bmc *kcs_bmc, u32 reg) return rc == 0 ? (u8)val : 0; } -static void npcm7xx_kcs_outb(struct kcs_bmc *kcs_bmc, u32 reg, u8 data) +static void npcm7xx_kcs_outb(struct kcs_bmc_device *kcs_bmc, u32 reg, u8 data) { - struct npcm7xx_kcs_bmc *priv = kcs_bmc_priv(kcs_bmc); + struct npcm7xx_kcs_bmc *priv = to_npcm7xx_kcs_bmc(kcs_bmc); int rc; rc = regmap_write(priv->map, reg, data); WARN(rc != 0, "regmap_write() failed: %d\n", rc); } -static void npcm7xx_kcs_enable_channel(struct kcs_bmc *kcs_bmc, bool enable) +static void npcm7xx_kcs_updateb(struct kcs_bmc_device *kcs_bmc, u32 reg, u8 mask, u8 data) { - struct npcm7xx_kcs_bmc *priv = kcs_bmc_priv(kcs_bmc); + struct npcm7xx_kcs_bmc *priv = to_npcm7xx_kcs_bmc(kcs_bmc); + int rc; - regmap_update_bits(priv->map, priv->reg->ctl, KCS_CTL_IBFIE, - enable ? KCS_CTL_IBFIE : 0); + rc = regmap_update_bits(priv->map, reg, mask, data); + WARN(rc != 0, "regmap_update_bits() failed: %d\n", rc); +} + +static void npcm7xx_kcs_enable_channel(struct kcs_bmc_device *kcs_bmc, bool enable) +{ + struct npcm7xx_kcs_bmc *priv = to_npcm7xx_kcs_bmc(kcs_bmc); regmap_update_bits(priv->map, priv->reg->ie, KCS_IE_IRQE | KCS_IE_HIRQE, enable ? KCS_IE_IRQE | KCS_IE_HIRQE : 0); } -static irqreturn_t npcm7xx_kcs_irq(int irq, void *arg) +static void npcm7xx_kcs_irq_mask_update(struct kcs_bmc_device *kcs_bmc, u8 mask, u8 state) { - struct kcs_bmc *kcs_bmc = arg; + struct npcm7xx_kcs_bmc *priv = to_npcm7xx_kcs_bmc(kcs_bmc); - if (!kcs_bmc_handle_event(kcs_bmc)) - return IRQ_HANDLED; + if (mask & KCS_BMC_EVENT_TYPE_OBE) + regmap_update_bits(priv->map, priv->reg->ctl, KCS_CTL_OBEIE, + !!(state & KCS_BMC_EVENT_TYPE_OBE) * KCS_CTL_OBEIE); - return IRQ_NONE; + if (mask & KCS_BMC_EVENT_TYPE_IBF) + regmap_update_bits(priv->map, priv->reg->ctl, KCS_CTL_IBFIE, + !!(state & KCS_BMC_EVENT_TYPE_IBF) * KCS_CTL_IBFIE); } -static int npcm7xx_kcs_config_irq(struct kcs_bmc *kcs_bmc, +static irqreturn_t npcm7xx_kcs_irq(int irq, void *arg) +{ + struct kcs_bmc_device *kcs_bmc = arg; + + return kcs_bmc_handle_event(kcs_bmc); +} + +static int npcm7xx_kcs_config_irq(struct kcs_bmc_device *kcs_bmc, struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -132,11 +156,18 @@ static int npcm7xx_kcs_config_irq(struct kcs_bmc *kcs_bmc, dev_name(dev), kcs_bmc); } +static const struct kcs_bmc_device_ops npcm7xx_kcs_ops = { + .irq_mask_update = npcm7xx_kcs_irq_mask_update, + .io_inputb = npcm7xx_kcs_inb, + .io_outputb = npcm7xx_kcs_outb, + .io_updateb = npcm7xx_kcs_updateb, +}; + static int npcm7xx_kcs_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct npcm7xx_kcs_bmc *priv; - struct kcs_bmc *kcs_bmc; + struct kcs_bmc_device *kcs_bmc; u32 chan; int rc; @@ -146,11 +177,10 @@ static int npcm7xx_kcs_probe(struct platform_device *pdev) return -ENODEV; } - kcs_bmc = kcs_bmc_alloc(dev, sizeof(*priv), chan); - if (!kcs_bmc) + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) return -ENOMEM; - priv = kcs_bmc_priv(kcs_bmc); priv->map = syscon_node_to_regmap(dev->parent->of_node); if (IS_ERR(priv->map)) { dev_err(dev, "Couldn't get regmap\n"); @@ -158,22 +188,26 @@ static int npcm7xx_kcs_probe(struct platform_device *pdev) } priv->reg = &npcm7xx_kcs_reg_tbl[chan - 1]; + kcs_bmc = &priv->kcs_bmc; + kcs_bmc->dev = &pdev->dev; + kcs_bmc->channel = chan; kcs_bmc->ioreg.idr = priv->reg->dib; kcs_bmc->ioreg.odr = priv->reg->dob; kcs_bmc->ioreg.str = priv->reg->sts; - kcs_bmc->io_inputb = npcm7xx_kcs_inb; - kcs_bmc->io_outputb = npcm7xx_kcs_outb; + kcs_bmc->ops = &npcm7xx_kcs_ops; - dev_set_drvdata(dev, kcs_bmc); + platform_set_drvdata(pdev, priv); - npcm7xx_kcs_enable_channel(kcs_bmc, true); rc = npcm7xx_kcs_config_irq(kcs_bmc, pdev); if (rc) return rc; - rc = misc_register(&kcs_bmc->miscdev); + npcm7xx_kcs_irq_mask_update(kcs_bmc, (KCS_BMC_EVENT_TYPE_IBF | KCS_BMC_EVENT_TYPE_OBE), 0); + npcm7xx_kcs_enable_channel(kcs_bmc, true); + + rc = kcs_bmc_add_device(kcs_bmc); if (rc) { - dev_err(dev, "Unable to register device\n"); + dev_warn(&pdev->dev, "Failed to register channel %d: %d\n", kcs_bmc->channel, rc); return rc; } @@ -186,9 +220,13 @@ static int npcm7xx_kcs_probe(struct platform_device *pdev) static int npcm7xx_kcs_remove(struct platform_device *pdev) { - struct kcs_bmc *kcs_bmc = dev_get_drvdata(&pdev->dev); + struct npcm7xx_kcs_bmc *priv = platform_get_drvdata(pdev); + struct kcs_bmc_device *kcs_bmc = &priv->kcs_bmc; - misc_deregister(&kcs_bmc->miscdev); + kcs_bmc_remove_device(kcs_bmc); + + npcm7xx_kcs_enable_channel(kcs_bmc, false); + npcm7xx_kcs_irq_mask_update(kcs_bmc, (KCS_BMC_EVENT_TYPE_IBF | KCS_BMC_EVENT_TYPE_OBE), 0); return 0; } diff --git a/drivers/char/ipmi/kcs_bmc_serio.c b/drivers/char/ipmi/kcs_bmc_serio.c new file mode 100644 index 000000000000..7948cabde50b --- /dev/null +++ b/drivers/char/ipmi/kcs_bmc_serio.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Copyright (c) 2021 IBM Corp. */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "kcs_bmc_client.h" + +struct kcs_bmc_serio { + struct list_head entry; + + struct kcs_bmc_client client; + struct serio *port; + + spinlock_t lock; +}; + +static inline struct kcs_bmc_serio *client_to_kcs_bmc_serio(struct kcs_bmc_client *client) +{ + return container_of(client, struct kcs_bmc_serio, client); +} + +static irqreturn_t kcs_bmc_serio_event(struct kcs_bmc_client *client) +{ + struct kcs_bmc_serio *priv; + u8 handled = IRQ_NONE; + u8 status; + + priv = client_to_kcs_bmc_serio(client); + + spin_lock(&priv->lock); + + status = kcs_bmc_read_status(client->dev); + + if (status & KCS_BMC_STR_IBF) + handled = serio_interrupt(priv->port, kcs_bmc_read_data(client->dev), 0); + + spin_unlock(&priv->lock); + + return handled; +} + +static const struct kcs_bmc_client_ops kcs_bmc_serio_client_ops = { + .event = kcs_bmc_serio_event, +}; + +static int kcs_bmc_serio_open(struct serio *port) +{ + struct kcs_bmc_serio *priv = port->port_data; + + return kcs_bmc_enable_device(priv->client.dev, &priv->client); +} + +static void kcs_bmc_serio_close(struct serio *port) +{ + struct kcs_bmc_serio *priv = port->port_data; + + kcs_bmc_disable_device(priv->client.dev, &priv->client); +} + +static DEFINE_SPINLOCK(kcs_bmc_serio_instances_lock); +static LIST_HEAD(kcs_bmc_serio_instances); + +static int kcs_bmc_serio_add_device(struct kcs_bmc_device *kcs_bmc) +{ + struct kcs_bmc_serio *priv; + struct serio *port; + + priv = devm_kzalloc(kcs_bmc->dev, sizeof(*priv), GFP_KERNEL); + + /* Use kzalloc() as the allocation is cleaned up with kfree() via serio_unregister_port() */ + port = kzalloc(sizeof(*port), GFP_KERNEL); + if (!(priv && port)) + return -ENOMEM; + + port->id.type = SERIO_8042; + port->open = kcs_bmc_serio_open; + port->close = kcs_bmc_serio_close; + port->port_data = priv; + port->dev.parent = kcs_bmc->dev; + + spin_lock_init(&priv->lock); + priv->port = port; + priv->client.dev = kcs_bmc; + priv->client.ops = &kcs_bmc_serio_client_ops; + + spin_lock_irq(&kcs_bmc_serio_instances_lock); + list_add(&priv->entry, &kcs_bmc_serio_instances); + spin_unlock_irq(&kcs_bmc_serio_instances_lock); + + serio_register_port(port); + + dev_info(kcs_bmc->dev, "Initialised serio client for channel %d", kcs_bmc->channel); + + return 0; +} + +static int kcs_bmc_serio_remove_device(struct kcs_bmc_device *kcs_bmc) +{ + struct kcs_bmc_serio *priv = NULL, *pos; + + spin_lock_irq(&kcs_bmc_serio_instances_lock); + list_for_each_entry(pos, &kcs_bmc_serio_instances, entry) { + if (pos->client.dev == kcs_bmc) { + priv = pos; + list_del(&pos->entry); + break; + } + } + spin_unlock_irq(&kcs_bmc_serio_instances_lock); + + if (!priv) + return -ENODEV; + + /* kfree()s priv->port via put_device() */ + serio_unregister_port(priv->port); + + /* Ensure the IBF IRQ is disabled if we were the active client */ + kcs_bmc_disable_device(kcs_bmc, &priv->client); + + devm_kfree(priv->client.dev->dev, priv); + + return 0; +} + +static const struct kcs_bmc_driver_ops kcs_bmc_serio_driver_ops = { + .add_device = kcs_bmc_serio_add_device, + .remove_device = kcs_bmc_serio_remove_device, +}; + +static struct kcs_bmc_driver kcs_bmc_serio_driver = { + .ops = &kcs_bmc_serio_driver_ops, +}; + +static int kcs_bmc_serio_init(void) +{ + kcs_bmc_register_driver(&kcs_bmc_serio_driver); + + return 0; +} +module_init(kcs_bmc_serio_init); + +static void kcs_bmc_serio_exit(void) +{ + kcs_bmc_unregister_driver(&kcs_bmc_serio_driver); +} +module_exit(kcs_bmc_serio_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Andrew Jeffery "); +MODULE_DESCRIPTION("Adapter driver for serio access to BMC KCS devices"); diff --git a/drivers/char/tpm/tpm1-cmd.c b/drivers/char/tpm/tpm1-cmd.c index ca7158fa6e6c..f7dc986fa4a0 100644 --- a/drivers/char/tpm/tpm1-cmd.c +++ b/drivers/char/tpm/tpm1-cmd.c @@ -312,7 +312,7 @@ unsigned long tpm1_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal) #define TPM_ST_CLEAR 1 /** - * tpm_startup() - turn on the TPM + * tpm1_startup() - turn on the TPM * @chip: TPM chip to use * * Normally the firmware should start the TPM. This function is provided as a @@ -611,7 +611,7 @@ out: #define TPM_ORD_CONTINUE_SELFTEST 83 /** - * tpm_continue_selftest() - run TPM's selftest + * tpm1_continue_selftest() - run TPM's selftest * @chip: TPM chip to use * * Returns 0 on success, < 0 in case of fatal error or a value > 0 representing diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index c84d23951219..a25815a6f625 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -87,7 +87,7 @@ static u8 tpm2_ordinal_duration_index(u32 ordinal) return TPM_MEDIUM; case TPM2_CC_VERIFY_SIGNATURE: /* 177 */ - return TPM_LONG; + return TPM_LONG_LONG; case TPM2_CC_PCR_EXTEND: /* 182 */ return TPM_MEDIUM; diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index a9dcf31eadd2..18606651d1aa 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -464,7 +464,7 @@ static void __iomem *crb_map_res(struct device *dev, struct resource *iores, /* Detect a 64 bit address on a 32 bit system */ if (start != new_res.start) - return (void __iomem *) ERR_PTR(-EINVAL); + return IOMEM_ERR_PTR(-EINVAL); if (!iores) return devm_ioremap_resource(dev, &new_res); diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 4ed6e660273a..d3f2e5364c27 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -363,11 +363,7 @@ static int tpm_tis_force_device(void) { struct platform_device *pdev; static const struct resource x86_resources[] = { - { - .start = 0xFED40000, - .end = 0xFED40000 + TIS_MEM_LEN - 1, - .flags = IORESOURCE_MEM, - }, + DEFINE_RES_MEM(0xFED40000, TIS_MEM_LEN) }; if (!force) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 55b9d3965ae1..69579efb247b 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -196,13 +196,24 @@ static u8 tpm_tis_status(struct tpm_chip *chip) return 0; if (unlikely((status & TPM_STS_READ_ZERO) != 0)) { - /* - * If this trips, the chances are the read is - * returning 0xff because the locality hasn't been - * acquired. Usually because tpm_try_get_ops() hasn't - * been called before doing a TPM operation. - */ - WARN_ONCE(1, "TPM returned invalid status\n"); + if (!test_and_set_bit(TPM_TIS_INVALID_STATUS, &priv->flags)) { + /* + * If this trips, the chances are the read is + * returning 0xff because the locality hasn't been + * acquired. Usually because tpm_try_get_ops() hasn't + * been called before doing a TPM operation. + */ + dev_err(&chip->dev, "invalid TPM_STS.x 0x%02x, dumping stack for forensics\n", + status); + + /* + * Dump stack for forensics, as invalid TPM_STS.x could be + * potentially triggered by impaired tpm_try_get_ops() or + * tpm_find_get_ops(). + */ + dump_stack(); + } + return 0; } diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h index 9b2d32a59f67..b2a3c6c72882 100644 --- a/drivers/char/tpm/tpm_tis_core.h +++ b/drivers/char/tpm/tpm_tis_core.h @@ -83,6 +83,7 @@ enum tis_defaults { enum tpm_tis_flags { TPM_TIS_ITPM_WORKAROUND = BIT(0), + TPM_TIS_INVALID_STATUS = BIT(1), }; struct tpm_tis_data { @@ -90,7 +91,7 @@ struct tpm_tis_data { int locality; int irq; bool irq_tested; - unsigned int flags; + unsigned long flags; void __iomem *ilb_base_addr; u16 clkrun_enabled; wait_queue_head_t int_queue; diff --git a/drivers/char/tpm/tpm_tis_i2c_cr50.c b/drivers/char/tpm/tpm_tis_i2c_cr50.c index f19c227d20f4..44dde2fbe2fb 100644 --- a/drivers/char/tpm/tpm_tis_i2c_cr50.c +++ b/drivers/char/tpm/tpm_tis_i2c_cr50.c @@ -706,14 +706,14 @@ static int tpm_cr50_i2c_probe(struct i2c_client *client, if (client->irq > 0) { rc = devm_request_irq(dev, client->irq, tpm_cr50_i2c_int_handler, - IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT | + IRQF_NO_AUTOEN, dev->driver->name, chip); if (rc < 0) { dev_err(dev, "Failed to probe IRQ %d\n", client->irq); return rc; } - disable_irq(client->irq); priv->irq = client->irq; } else { dev_warn(dev, "No IRQ, will use %ums delay for TPM ready\n", diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c index 3856f6ebcb34..54584b4b00d1 100644 --- a/drivers/char/tpm/tpm_tis_spi_main.c +++ b/drivers/char/tpm/tpm_tis_spi_main.c @@ -240,10 +240,14 @@ static int tpm_tis_spi_driver_probe(struct spi_device *spi) tpm_tis_spi_probe_func probe_func; probe_func = of_device_get_match_data(&spi->dev); - if (!probe_func && spi_dev_id) - probe_func = (tpm_tis_spi_probe_func)spi_dev_id->driver_data; - if (!probe_func) - return -ENODEV; + if (!probe_func) { + if (spi_dev_id) { + probe_func = (tpm_tis_spi_probe_func)spi_dev_id->driver_data; + if (!probe_func) + return -ENODEV; + } else + probe_func = tpm_tis_spi_probe; + } return probe_func(spi); } @@ -260,6 +264,8 @@ static int tpm_tis_spi_remove(struct spi_device *dev) } static const struct spi_device_id tpm_tis_spi_id[] = { + { "st33htpm-spi", (unsigned long)tpm_tis_spi_probe }, + { "slb9670", (unsigned long)tpm_tis_spi_probe }, { "tpm_tis_spi", (unsigned long)tpm_tis_spi_probe }, { "cr50", (unsigned long)cr50_spi_probe }, {} diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 1c31badb6c14..22ebb985c18d 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -358,6 +358,20 @@ config ARM_GLOBAL_TIMER help This option enables support for the ARM global timer unit. +config ARM_GT_INITIAL_PRESCALER_VAL + int "ARM global timer initial prescaler value" + default 2 if ARCH_ZYNQ + default 1 + depends on ARM_GLOBAL_TIMER + help + When the ARM global timer initializes, its current rate is declared + to the kernel and maintained forever. Should it's parent clock + change, the driver tries to fix the timer's internal prescaler. + On some machs (i.e. Zynq) the initial prescaler value thus poses + bounds about how much the parent clock is allowed to decrease or + increase wrt the initial clock value. + This affects CPU_FREQ max delta from the initial frequency. + config ARM_TIMER_SP804 bool "Support for Dual Timer SP804 module" if COMPILE_TEST depends on GENERIC_SCHED_CLOCK && CLKDEV_LOOKUP diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index fe1a82627d57..be6d741d404c 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -64,7 +64,6 @@ struct arch_timer { #define to_arch_timer(e) container_of(e, struct arch_timer, evt) static u32 arch_timer_rate __ro_after_init; -u32 arch_timer_rate1 __ro_after_init; static int arch_timer_ppi[ARCH_TIMER_MAX_TIMER_PPI] __ro_after_init; static const char *arch_timer_ppi_names[ARCH_TIMER_MAX_TIMER_PPI] = { @@ -365,7 +364,7 @@ static u64 notrace arm64_858921_read_cntvct_el0(void) do { \ _val = read_sysreg(reg); \ _retries--; \ - } while (((_val + 1) & GENMASK(9, 0)) <= 1 && _retries); \ + } while (((_val + 1) & GENMASK(8, 0)) <= 1 && _retries); \ \ WARN_ON_ONCE(!_retries); \ _val; \ diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c index 88b2d38a7a61..44a61dc6f932 100644 --- a/drivers/clocksource/arm_global_timer.c +++ b/drivers/clocksource/arm_global_timer.c @@ -31,6 +31,10 @@ #define GT_CONTROL_COMP_ENABLE BIT(1) /* banked */ #define GT_CONTROL_IRQ_ENABLE BIT(2) /* banked */ #define GT_CONTROL_AUTO_INC BIT(3) /* banked */ +#define GT_CONTROL_PRESCALER_SHIFT 8 +#define GT_CONTROL_PRESCALER_MAX 0xF +#define GT_CONTROL_PRESCALER_MASK (GT_CONTROL_PRESCALER_MAX << \ + GT_CONTROL_PRESCALER_SHIFT) #define GT_INT_STATUS 0x0c #define GT_INT_STATUS_EVENT_FLAG BIT(0) @@ -39,6 +43,7 @@ #define GT_COMP1 0x14 #define GT_AUTO_INC 0x18 +#define MAX_F_ERR 50 /* * We are expecting to be clocked by the ARM peripheral clock. * @@ -46,7 +51,8 @@ * the units for all operations. */ static void __iomem *gt_base; -static unsigned long gt_clk_rate; +static struct notifier_block gt_clk_rate_change_nb; +static u32 gt_psv_new, gt_psv_bck, gt_target_rate; static int gt_ppi; static struct clock_event_device __percpu *gt_evt; @@ -96,7 +102,10 @@ static void gt_compare_set(unsigned long delta, int periodic) unsigned long ctrl; counter += delta; - ctrl = GT_CONTROL_TIMER_ENABLE; + ctrl = readl(gt_base + GT_CONTROL); + ctrl &= ~(GT_CONTROL_COMP_ENABLE | GT_CONTROL_IRQ_ENABLE | + GT_CONTROL_AUTO_INC); + ctrl |= GT_CONTROL_TIMER_ENABLE; writel_relaxed(ctrl, gt_base + GT_CONTROL); writel_relaxed(lower_32_bits(counter), gt_base + GT_COMP0); writel_relaxed(upper_32_bits(counter), gt_base + GT_COMP1); @@ -123,7 +132,7 @@ static int gt_clockevent_shutdown(struct clock_event_device *evt) static int gt_clockevent_set_periodic(struct clock_event_device *evt) { - gt_compare_set(DIV_ROUND_CLOSEST(gt_clk_rate, HZ), 1); + gt_compare_set(DIV_ROUND_CLOSEST(gt_target_rate, HZ), 1); return 0; } @@ -177,7 +186,7 @@ static int gt_starting_cpu(unsigned int cpu) clk->cpumask = cpumask_of(cpu); clk->rating = 300; clk->irq = gt_ppi; - clockevents_config_and_register(clk, gt_clk_rate, + clockevents_config_and_register(clk, gt_target_rate, 1, 0xffffffff); enable_percpu_irq(clk->irq, IRQ_TYPE_NONE); return 0; @@ -232,9 +241,28 @@ static struct delay_timer gt_delay_timer = { .read_current_timer = gt_read_long, }; +static void gt_write_presc(u32 psv) +{ + u32 reg; + + reg = readl(gt_base + GT_CONTROL); + reg &= ~GT_CONTROL_PRESCALER_MASK; + reg |= psv << GT_CONTROL_PRESCALER_SHIFT; + writel(reg, gt_base + GT_CONTROL); +} + +static u32 gt_read_presc(void) +{ + u32 reg; + + reg = readl(gt_base + GT_CONTROL); + reg &= GT_CONTROL_PRESCALER_MASK; + return reg >> GT_CONTROL_PRESCALER_SHIFT; +} + static void __init gt_delay_timer_init(void) { - gt_delay_timer.freq = gt_clk_rate; + gt_delay_timer.freq = gt_target_rate; register_current_timer_delay(>_delay_timer); } @@ -243,18 +271,81 @@ static int __init gt_clocksource_init(void) writel(0, gt_base + GT_CONTROL); writel(0, gt_base + GT_COUNTER0); writel(0, gt_base + GT_COUNTER1); - /* enables timer on all the cores */ - writel(GT_CONTROL_TIMER_ENABLE, gt_base + GT_CONTROL); + /* set prescaler and enable timer on all the cores */ + writel(((CONFIG_ARM_GT_INITIAL_PRESCALER_VAL - 1) << + GT_CONTROL_PRESCALER_SHIFT) + | GT_CONTROL_TIMER_ENABLE, gt_base + GT_CONTROL); #ifdef CONFIG_CLKSRC_ARM_GLOBAL_TIMER_SCHED_CLOCK - sched_clock_register(gt_sched_clock_read, 64, gt_clk_rate); + sched_clock_register(gt_sched_clock_read, 64, gt_target_rate); #endif - return clocksource_register_hz(>_clocksource, gt_clk_rate); + return clocksource_register_hz(>_clocksource, gt_target_rate); +} + +static int gt_clk_rate_change_cb(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct clk_notifier_data *ndata = data; + + switch (event) { + case PRE_RATE_CHANGE: + { + int psv; + + psv = DIV_ROUND_CLOSEST(ndata->new_rate, + gt_target_rate); + + if (abs(gt_target_rate - (ndata->new_rate / psv)) > MAX_F_ERR) + return NOTIFY_BAD; + + psv--; + + /* prescaler within legal range? */ + if (psv < 0 || psv > GT_CONTROL_PRESCALER_MAX) + return NOTIFY_BAD; + + /* + * store timer clock ctrl register so we can restore it in case + * of an abort. + */ + gt_psv_bck = gt_read_presc(); + gt_psv_new = psv; + /* scale down: adjust divider in post-change notification */ + if (ndata->new_rate < ndata->old_rate) + return NOTIFY_DONE; + + /* scale up: adjust divider now - before frequency change */ + gt_write_presc(psv); + break; + } + case POST_RATE_CHANGE: + /* scale up: pre-change notification did the adjustment */ + if (ndata->new_rate > ndata->old_rate) + return NOTIFY_OK; + + /* scale down: adjust divider now - after frequency change */ + gt_write_presc(gt_psv_new); + break; + + case ABORT_RATE_CHANGE: + /* we have to undo the adjustment in case we scale up */ + if (ndata->new_rate < ndata->old_rate) + return NOTIFY_OK; + + /* restore original register value */ + gt_write_presc(gt_psv_bck); + break; + default: + return NOTIFY_DONE; + } + + return NOTIFY_DONE; } static int __init global_timer_of_register(struct device_node *np) { struct clk *gt_clk; + static unsigned long gt_clk_rate; int err = 0; /* @@ -292,11 +383,20 @@ static int __init global_timer_of_register(struct device_node *np) } gt_clk_rate = clk_get_rate(gt_clk); + gt_target_rate = gt_clk_rate / CONFIG_ARM_GT_INITIAL_PRESCALER_VAL; + gt_clk_rate_change_nb.notifier_call = + gt_clk_rate_change_cb; + err = clk_notifier_register(gt_clk, >_clk_rate_change_nb); + if (err) { + pr_warn("Unable to register clock notifier\n"); + goto out_clk; + } + gt_evt = alloc_percpu(struct clock_event_device); if (!gt_evt) { pr_warn("global-timer: can't allocate memory\n"); err = -ENOMEM; - goto out_clk; + goto out_clk_nb; } err = request_percpu_irq(gt_ppi, gt_clockevent_interrupt, @@ -326,6 +426,8 @@ out_irq: free_percpu_irq(gt_ppi, gt_evt); out_free: free_percpu(gt_evt); +out_clk_nb: + clk_notifier_unregister(gt_clk, >_clk_rate_change_nb); out_clk: clk_disable_unprepare(gt_clk); out_unmap: diff --git a/drivers/clocksource/ingenic-sysost.c b/drivers/clocksource/ingenic-sysost.c index e77d58449005..a129840f14f9 100644 --- a/drivers/clocksource/ingenic-sysost.c +++ b/drivers/clocksource/ingenic-sysost.c @@ -186,7 +186,7 @@ static const struct clk_ops ingenic_ost_global_timer_ops = { static const char * const ingenic_ost_clk_parents[] = { "ext" }; -static const struct ingenic_ost_clk_info ingenic_ost_clk_info[] = { +static const struct ingenic_ost_clk_info x1000_ost_clk_info[] = { [OST_CLK_PERCPU_TIMER] = { .init_data = { .name = "percpu timer", @@ -414,14 +414,14 @@ static const struct ingenic_soc_info x1000_soc_info = { .num_channels = 2, }; -static const struct of_device_id __maybe_unused ingenic_ost_of_match[] __initconst = { - { .compatible = "ingenic,x1000-ost", .data = &x1000_soc_info, }, +static const struct of_device_id __maybe_unused ingenic_ost_of_matches[] __initconst = { + { .compatible = "ingenic,x1000-ost", .data = &x1000_soc_info }, { /* sentinel */ } }; static int __init ingenic_ost_probe(struct device_node *np) { - const struct of_device_id *id = of_match_node(ingenic_ost_of_match, np); + const struct of_device_id *id = of_match_node(ingenic_ost_of_matches, np); struct ingenic_ost *ost; unsigned int i; int ret; @@ -462,7 +462,7 @@ static int __init ingenic_ost_probe(struct device_node *np) ost->clocks->num = ost->soc_info->num_channels; for (i = 0; i < ost->clocks->num; i++) { - ret = ingenic_ost_register_clock(ost, i, &ingenic_ost_clk_info[i], ost->clocks); + ret = ingenic_ost_register_clock(ost, i, &x1000_ost_clk_info[i], ost->clocks); if (ret) { pr_crit("%s: Cannot register clock %d\n", __func__, i); goto err_unregister_ost_clocks; diff --git a/drivers/clocksource/samsung_pwm_timer.c b/drivers/clocksource/samsung_pwm_timer.c index f760229d0c7f..6e46781bc9ac 100644 --- a/drivers/clocksource/samsung_pwm_timer.c +++ b/drivers/clocksource/samsung_pwm_timer.c @@ -4,7 +4,7 @@ * http://www.samsung.com/ * * samsung - Common hr-timer support (s3c and s5p) -*/ + */ #include #include @@ -22,7 +22,6 @@ #include - /* * Clocksource driver */ @@ -38,8 +37,8 @@ #define TCFG0_PRESCALER_MASK 0xff #define TCFG0_PRESCALER1_SHIFT 8 -#define TCFG1_SHIFT(x) ((x) * 4) -#define TCFG1_MUX_MASK 0xf +#define TCFG1_SHIFT(x) ((x) * 4) +#define TCFG1_MUX_MASK 0xf /* * Each channel occupies 4 bits in TCON register, but there is a gap of 4 @@ -62,7 +61,7 @@ EXPORT_SYMBOL(samsung_pwm_lock); struct samsung_pwm_clocksource { void __iomem *base; - void __iomem *source_reg; + const void __iomem *source_reg; unsigned int irq[SAMSUNG_PWM_NUM]; struct samsung_pwm_variant variant; @@ -183,7 +182,7 @@ static void samsung_time_start(unsigned int channel, bool periodic) } static int samsung_set_next_event(unsigned long cycles, - struct clock_event_device *evt) + struct clock_event_device *evt) { /* * This check is needed to account for internal rounding @@ -225,6 +224,7 @@ static void samsung_clockevent_resume(struct clock_event_device *cev) if (pwm.variant.has_tint_cstat) { u32 mask = (1 << pwm.event_id); + writel(mask | (mask << 5), pwm.base + REG_TINT_CSTAT); } } @@ -248,6 +248,7 @@ static irqreturn_t samsung_clock_event_isr(int irq, void *dev_id) if (pwm.variant.has_tint_cstat) { u32 mask = (1 << pwm.event_id); + writel(mask | (mask << 5), pwm.base + REG_TINT_CSTAT); } @@ -272,7 +273,7 @@ static void __init samsung_clockevent_init(void) time_event_device.cpumask = cpumask_of(0); clockevents_config_and_register(&time_event_device, - clock_rate, 1, pwm.tcnt_max); + clock_rate, 1, pwm.tcnt_max); irq_number = pwm.irq[pwm.event_id]; if (request_irq(irq_number, samsung_clock_event_isr, @@ -282,6 +283,7 @@ static void __init samsung_clockevent_init(void) if (pwm.variant.has_tint_cstat) { u32 mask = (1 << pwm.event_id); + writel(mask | (mask << 5), pwm.base + REG_TINT_CSTAT); } } @@ -347,7 +349,7 @@ static int __init samsung_clocksource_init(void) pwm.source_reg = pwm.base + pwm.source_id * 0x0c + 0x14; sched_clock_register(samsung_read_sched_clock, - pwm.variant.bits, clock_rate); + pwm.variant.bits, clock_rate); samsung_clocksource.mask = CLOCKSOURCE_MASK(pwm.variant.bits); return clocksource_register_hz(&samsung_clocksource, clock_rate); @@ -398,7 +400,8 @@ static int __init _samsung_pwm_clocksource_init(void) } void __init samsung_pwm_clocksource_init(void __iomem *base, - unsigned int *irqs, struct samsung_pwm_variant *variant) + unsigned int *irqs, + const struct samsung_pwm_variant *variant) { pwm.base = base; memcpy(&pwm.variant, variant, sizeof(pwm.variant)); @@ -418,7 +421,7 @@ static int __init samsung_pwm_alloc(struct device_node *np, struct property *prop; const __be32 *cur; u32 val; - int i; + int i, ret; memcpy(&pwm.variant, variant, sizeof(pwm.variant)); for (i = 0; i < SAMSUNG_PWM_NUM; ++i) @@ -441,10 +444,24 @@ static int __init samsung_pwm_alloc(struct device_node *np, pwm.timerclk = of_clk_get_by_name(np, "timers"); if (IS_ERR(pwm.timerclk)) { pr_crit("failed to get timers clock for timer\n"); - return PTR_ERR(pwm.timerclk); + ret = PTR_ERR(pwm.timerclk); + goto err_clk; } - return _samsung_pwm_clocksource_init(); + ret = _samsung_pwm_clocksource_init(); + if (ret) + goto err_clocksource; + + return 0; + +err_clocksource: + clk_put(pwm.timerclk); + pwm.timerclk = NULL; +err_clk: + iounmap(pwm.base); + pwm.base = NULL; + + return ret; } static const struct samsung_pwm_variant s3c24xx_variant = { diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c index 9318edcd8963..ab63b95e414f 100644 --- a/drivers/clocksource/timer-mediatek.c +++ b/drivers/clocksource/timer-mediatek.c @@ -241,6 +241,28 @@ static void mtk_gpt_enable_irq(struct timer_of *to, u8 timer) timer_of_base(to) + GPT_IRQ_EN_REG); } +static void mtk_gpt_resume(struct clock_event_device *clk) +{ + struct timer_of *to = to_timer_of(clk); + + mtk_gpt_enable_irq(to, TIMER_CLK_EVT); +} + +static void mtk_gpt_suspend(struct clock_event_device *clk) +{ + struct timer_of *to = to_timer_of(clk); + + /* Disable all interrupts */ + writel(0x0, timer_of_base(to) + GPT_IRQ_EN_REG); + + /* + * This is called with interrupts disabled, + * so we need to ack any interrupt that is pending + * or for example ATF will prevent a suspend from completing. + */ + writel(0x3f, timer_of_base(to) + GPT_IRQ_ACK_REG); +} + static struct timer_of to = { .flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK, @@ -286,6 +308,8 @@ static int __init mtk_gpt_init(struct device_node *node) to.clkevt.set_state_oneshot = mtk_gpt_clkevt_shutdown; to.clkevt.tick_resume = mtk_gpt_clkevt_shutdown; to.clkevt.set_next_event = mtk_gpt_clkevt_next_event; + to.clkevt.suspend = mtk_gpt_suspend; + to.clkevt.resume = mtk_gpt_resume; to.of_irq.handler = mtk_gpt_interrupt; ret = timer_of_init(node, &to); diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index 33eeabf9c3d1..3e52c5226c4d 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -78,6 +78,9 @@ static void omap_dm_timer_write_reg(struct omap_dm_timer *timer, u32 reg, static void omap_timer_restore_context(struct omap_dm_timer *timer) { + __omap_dm_timer_write(timer, OMAP_TIMER_OCP_CFG_OFFSET, + timer->context.ocp_cfg, 0); + omap_dm_timer_write_reg(timer, OMAP_TIMER_WAKEUP_EN_REG, timer->context.twer); omap_dm_timer_write_reg(timer, OMAP_TIMER_COUNTER_REG, @@ -95,6 +98,9 @@ static void omap_timer_restore_context(struct omap_dm_timer *timer) static void omap_timer_save_context(struct omap_dm_timer *timer) { + timer->context.ocp_cfg = + __omap_dm_timer_read(timer, OMAP_TIMER_OCP_CFG_OFFSET, 0); + timer->context.tclr = omap_dm_timer_read_reg(timer, OMAP_TIMER_CTRL_REG); timer->context.twer = @@ -122,7 +128,8 @@ static int omap_timer_context_notifier(struct notifier_block *nb, break; omap_timer_save_context(timer); break; - case CPU_CLUSTER_PM_ENTER_FAILED: + case CPU_CLUSTER_PM_ENTER_FAILED: /* No need to restore context */ + break; case CPU_CLUSTER_PM_EXIT: if ((timer->capability & OMAP_TIMER_ALWON) || !atomic_read(&timer->enabled)) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 30bb41f32265..e872e0ce0011 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1377,9 +1377,14 @@ static int cpufreq_online(unsigned int cpu) goto out_free_policy; } + /* + * The initialization has succeeded and the policy is online. + * If there is a problem with its frequency table, take it + * offline and drop it. + */ ret = cpufreq_table_validate_and_sort(policy); if (ret) - goto out_exit_policy; + goto out_offline_policy; /* related_cpus should at least include policy->cpus. */ cpumask_copy(policy->related_cpus, policy->cpus); @@ -1526,6 +1531,10 @@ out_destroy_policy: up_write(&policy->rwsem); +out_offline_policy: + if (cpufreq_driver->offline) + cpufreq_driver->offline(policy); + out_exit_policy: if (cpufreq_driver->exit) cpufreq_driver->exit(policy); diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index da717f7cd9a9..1570d6f3e75d 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -211,7 +211,7 @@ void cpufreq_stats_free_table(struct cpufreq_policy *policy) void cpufreq_stats_create_table(struct cpufreq_policy *policy) { - unsigned int i = 0, count = 0, ret = -ENOMEM; + unsigned int i = 0, count; struct cpufreq_stats *stats; unsigned int alloc_size; struct cpufreq_frequency_table *pos; @@ -253,8 +253,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy) stats->last_index = freq_table_get_index(stats, policy->cur); policy->stats = stats; - ret = sysfs_create_group(&policy->kobj, &stats_attr_group); - if (!ret) + if (!sysfs_create_group(&policy->kobj, &stats_attr_group)) return; /* We failed, release resources */ diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 0e69dffd5a76..6012964df51b 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -121,9 +121,10 @@ struct sample { * @max_pstate_physical:This is physical Max P state for a processor * This can be higher than the max_pstate which can * be limited by platform thermal design power limits - * @scaling: Scaling factor to convert frequency to cpufreq - * frequency units + * @perf_ctl_scaling: PERF_CTL P-state to frequency scaling factor + * @scaling: Scaling factor between performance and frequency * @turbo_pstate: Max Turbo P state possible for this platform + * @min_freq: @min_pstate frequency in cpufreq units * @max_freq: @max_pstate frequency in cpufreq units * @turbo_freq: @turbo_pstate frequency in cpufreq units * @@ -134,8 +135,10 @@ struct pstate_data { int min_pstate; int max_pstate; int max_pstate_physical; + int perf_ctl_scaling; int scaling; int turbo_pstate; + unsigned int min_freq; unsigned int max_freq; unsigned int turbo_freq; }; @@ -366,7 +369,7 @@ static void intel_pstate_set_itmt_prio(int cpu) } } -static int intel_pstate_get_cppc_guranteed(int cpu) +static int intel_pstate_get_cppc_guaranteed(int cpu) { struct cppc_perf_caps cppc_perf; int ret; @@ -382,7 +385,7 @@ static int intel_pstate_get_cppc_guranteed(int cpu) } #else /* CONFIG_ACPI_CPPC_LIB */ -static void intel_pstate_set_itmt_prio(int cpu) +static inline void intel_pstate_set_itmt_prio(int cpu) { } #endif /* CONFIG_ACPI_CPPC_LIB */ @@ -467,6 +470,20 @@ static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) acpi_processor_unregister_performance(policy->cpu); } + +static bool intel_pstate_cppc_perf_valid(u32 perf, struct cppc_perf_caps *caps) +{ + return perf && perf <= caps->highest_perf && perf >= caps->lowest_perf; +} + +static bool intel_pstate_cppc_perf_caps(struct cpudata *cpu, + struct cppc_perf_caps *caps) +{ + if (cppc_get_perf_caps(cpu->cpu, caps)) + return false; + + return caps->highest_perf && caps->lowest_perf <= caps->highest_perf; +} #else /* CONFIG_ACPI */ static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) { @@ -483,12 +500,146 @@ static inline bool intel_pstate_acpi_pm_profile_server(void) #endif /* CONFIG_ACPI */ #ifndef CONFIG_ACPI_CPPC_LIB -static int intel_pstate_get_cppc_guranteed(int cpu) +static inline int intel_pstate_get_cppc_guaranteed(int cpu) { return -ENOTSUPP; } #endif /* CONFIG_ACPI_CPPC_LIB */ +static void intel_pstate_hybrid_hwp_perf_ctl_parity(struct cpudata *cpu) +{ + pr_debug("CPU%d: Using PERF_CTL scaling for HWP\n", cpu->cpu); + + cpu->pstate.scaling = cpu->pstate.perf_ctl_scaling; +} + +/** + * intel_pstate_hybrid_hwp_calibrate - Calibrate HWP performance levels. + * @cpu: Target CPU. + * + * On hybrid processors, HWP may expose more performance levels than there are + * P-states accessible through the PERF_CTL interface. If that happens, the + * scaling factor between HWP performance levels and CPU frequency will be less + * than the scaling factor between P-state values and CPU frequency. + * + * In that case, the scaling factor between HWP performance levels and CPU + * frequency needs to be determined which can be done with the help of the + * observation that certain HWP performance levels should correspond to certain + * P-states, like for example the HWP highest performance should correspond + * to the maximum turbo P-state of the CPU. + */ +static void intel_pstate_hybrid_hwp_calibrate(struct cpudata *cpu) +{ + int perf_ctl_max_phys = cpu->pstate.max_pstate_physical; + int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling; + int perf_ctl_turbo = pstate_funcs.get_turbo(); + int turbo_freq = perf_ctl_turbo * perf_ctl_scaling; + int perf_ctl_max = pstate_funcs.get_max(); + int max_freq = perf_ctl_max * perf_ctl_scaling; + int scaling = INT_MAX; + int freq; + + pr_debug("CPU%d: perf_ctl_max_phys = %d\n", cpu->cpu, perf_ctl_max_phys); + pr_debug("CPU%d: perf_ctl_max = %d\n", cpu->cpu, perf_ctl_max); + pr_debug("CPU%d: perf_ctl_turbo = %d\n", cpu->cpu, perf_ctl_turbo); + pr_debug("CPU%d: perf_ctl_scaling = %d\n", cpu->cpu, perf_ctl_scaling); + + pr_debug("CPU%d: HWP_CAP guaranteed = %d\n", cpu->cpu, cpu->pstate.max_pstate); + pr_debug("CPU%d: HWP_CAP highest = %d\n", cpu->cpu, cpu->pstate.turbo_pstate); + +#ifdef CONFIG_ACPI + if (IS_ENABLED(CONFIG_ACPI_CPPC_LIB)) { + struct cppc_perf_caps caps; + + if (intel_pstate_cppc_perf_caps(cpu, &caps)) { + if (intel_pstate_cppc_perf_valid(caps.nominal_perf, &caps)) { + pr_debug("CPU%d: Using CPPC nominal\n", cpu->cpu); + + /* + * If the CPPC nominal performance is valid, it + * can be assumed to correspond to cpu_khz. + */ + if (caps.nominal_perf == perf_ctl_max_phys) { + intel_pstate_hybrid_hwp_perf_ctl_parity(cpu); + return; + } + scaling = DIV_ROUND_UP(cpu_khz, caps.nominal_perf); + } else if (intel_pstate_cppc_perf_valid(caps.guaranteed_perf, &caps)) { + pr_debug("CPU%d: Using CPPC guaranteed\n", cpu->cpu); + + /* + * If the CPPC guaranteed performance is valid, + * it can be assumed to correspond to max_freq. + */ + if (caps.guaranteed_perf == perf_ctl_max) { + intel_pstate_hybrid_hwp_perf_ctl_parity(cpu); + return; + } + scaling = DIV_ROUND_UP(max_freq, caps.guaranteed_perf); + } + } + } +#endif + /* + * If using the CPPC data to compute the HWP-to-frequency scaling factor + * doesn't work, use the HWP_CAP gauranteed perf for this purpose with + * the assumption that it corresponds to max_freq. + */ + if (scaling > perf_ctl_scaling) { + pr_debug("CPU%d: Using HWP_CAP guaranteed\n", cpu->cpu); + + if (cpu->pstate.max_pstate == perf_ctl_max) { + intel_pstate_hybrid_hwp_perf_ctl_parity(cpu); + return; + } + scaling = DIV_ROUND_UP(max_freq, cpu->pstate.max_pstate); + if (scaling > perf_ctl_scaling) { + /* + * This should not happen, because it would mean that + * the number of HWP perf levels was less than the + * number of P-states, so use the PERF_CTL scaling in + * that case. + */ + pr_debug("CPU%d: scaling (%d) out of range\n", cpu->cpu, + scaling); + + intel_pstate_hybrid_hwp_perf_ctl_parity(cpu); + return; + } + } + + /* + * If the product of the HWP performance scaling factor obtained above + * and the HWP_CAP highest performance is greater than the maximum turbo + * frequency corresponding to the pstate_funcs.get_turbo() return value, + * the scaling factor is too high, so recompute it so that the HWP_CAP + * highest performance corresponds to the maximum turbo frequency. + */ + if (turbo_freq < cpu->pstate.turbo_pstate * scaling) { + pr_debug("CPU%d: scaling too high (%d)\n", cpu->cpu, scaling); + + cpu->pstate.turbo_freq = turbo_freq; + scaling = DIV_ROUND_UP(turbo_freq, cpu->pstate.turbo_pstate); + } + + cpu->pstate.scaling = scaling; + + pr_debug("CPU%d: HWP-to-frequency scaling factor: %d\n", cpu->cpu, scaling); + + cpu->pstate.max_freq = rounddown(cpu->pstate.max_pstate * scaling, + perf_ctl_scaling); + + freq = perf_ctl_max_phys * perf_ctl_scaling; + cpu->pstate.max_pstate_physical = DIV_ROUND_UP(freq, scaling); + + cpu->pstate.min_freq = cpu->pstate.min_pstate * perf_ctl_scaling; + /* + * Cast the min P-state value retrieved via pstate_funcs.get_min() to + * the effective range of HWP performance levels. + */ + cpu->pstate.min_pstate = DIV_ROUND_UP(cpu->pstate.min_freq, scaling); +} + static inline void update_turbo_state(void) { u64 misc_en; @@ -795,19 +946,22 @@ cpufreq_freq_attr_rw(energy_performance_preference); static ssize_t show_base_frequency(struct cpufreq_policy *policy, char *buf) { - struct cpudata *cpu; - u64 cap; - int ratio; + struct cpudata *cpu = all_cpu_data[policy->cpu]; + int ratio, freq; - ratio = intel_pstate_get_cppc_guranteed(policy->cpu); + ratio = intel_pstate_get_cppc_guaranteed(policy->cpu); if (ratio <= 0) { + u64 cap; + rdmsrl_on_cpu(policy->cpu, MSR_HWP_CAPABILITIES, &cap); ratio = HWP_GUARANTEED_PERF(cap); } - cpu = all_cpu_data[policy->cpu]; + freq = ratio * cpu->pstate.scaling; + if (cpu->pstate.scaling != cpu->pstate.perf_ctl_scaling) + freq = rounddown(freq, cpu->pstate.perf_ctl_scaling); - return sprintf(buf, "%d\n", ratio * cpu->pstate.scaling); + return sprintf(buf, "%d\n", freq); } cpufreq_freq_attr_ro(base_frequency); @@ -831,9 +985,20 @@ static void __intel_pstate_get_hwp_cap(struct cpudata *cpu) static void intel_pstate_get_hwp_cap(struct cpudata *cpu) { + int scaling = cpu->pstate.scaling; + __intel_pstate_get_hwp_cap(cpu); - cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling; - cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; + + cpu->pstate.max_freq = cpu->pstate.max_pstate * scaling; + cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * scaling; + if (scaling != cpu->pstate.perf_ctl_scaling) { + int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling; + + cpu->pstate.max_freq = rounddown(cpu->pstate.max_freq, + perf_ctl_scaling); + cpu->pstate.turbo_freq = rounddown(cpu->pstate.turbo_freq, + perf_ctl_scaling); + } } static void intel_pstate_hwp_set(unsigned int cpu) @@ -1365,8 +1530,6 @@ define_one_global_rw(energy_efficiency); static struct attribute *intel_pstate_attributes[] = { &status.attr, &no_turbo.attr, - &turbo_pct.attr, - &num_pstates.attr, NULL }; @@ -1391,6 +1554,14 @@ static void __init intel_pstate_sysfs_expose_params(void) if (WARN_ON(rc)) return; + if (!boot_cpu_has(X86_FEATURE_HYBRID_CPU)) { + rc = sysfs_create_file(intel_pstate_kobject, &turbo_pct.attr); + WARN_ON(rc); + + rc = sysfs_create_file(intel_pstate_kobject, &num_pstates.attr); + WARN_ON(rc); + } + /* * If per cpu limits are enforced there are no global limits, so * return without creating max/min_perf_pct attributes @@ -1417,6 +1588,11 @@ static void __init intel_pstate_sysfs_remove(void) sysfs_remove_group(intel_pstate_kobject, &intel_pstate_attr_group); + if (!boot_cpu_has(X86_FEATURE_HYBRID_CPU)) { + sysfs_remove_file(intel_pstate_kobject, &num_pstates.attr); + sysfs_remove_file(intel_pstate_kobject, &turbo_pct.attr); + } + if (!per_cpu_limits) { sysfs_remove_file(intel_pstate_kobject, &max_perf_pct.attr); sysfs_remove_file(intel_pstate_kobject, &min_perf_pct.attr); @@ -1713,19 +1889,33 @@ static void intel_pstate_max_within_limits(struct cpudata *cpu) static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) { + bool hybrid_cpu = boot_cpu_has(X86_FEATURE_HYBRID_CPU); + int perf_ctl_max_phys = pstate_funcs.get_max_physical(); + int perf_ctl_scaling = hybrid_cpu ? cpu_khz / perf_ctl_max_phys : + pstate_funcs.get_scaling(); + cpu->pstate.min_pstate = pstate_funcs.get_min(); - cpu->pstate.max_pstate_physical = pstate_funcs.get_max_physical(); - cpu->pstate.scaling = pstate_funcs.get_scaling(); + cpu->pstate.max_pstate_physical = perf_ctl_max_phys; + cpu->pstate.perf_ctl_scaling = perf_ctl_scaling; if (hwp_active && !hwp_mode_bdw) { __intel_pstate_get_hwp_cap(cpu); + + if (hybrid_cpu) + intel_pstate_hybrid_hwp_calibrate(cpu); + else + cpu->pstate.scaling = perf_ctl_scaling; } else { + cpu->pstate.scaling = perf_ctl_scaling; cpu->pstate.max_pstate = pstate_funcs.get_max(); cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(); } - cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling; - cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling; + if (cpu->pstate.scaling == perf_ctl_scaling) { + cpu->pstate.min_freq = cpu->pstate.min_pstate * perf_ctl_scaling; + cpu->pstate.max_freq = cpu->pstate.max_pstate * perf_ctl_scaling; + cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * perf_ctl_scaling; + } if (pstate_funcs.get_aperf_mperf_shift) cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift(); @@ -2087,6 +2277,8 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = { X86_MATCH(ATOM_GOLDMONT, core_funcs), X86_MATCH(ATOM_GOLDMONT_PLUS, core_funcs), X86_MATCH(SKYLAKE_X, core_funcs), + X86_MATCH(COMETLAKE, core_funcs), + X86_MATCH(ICELAKE_X, core_funcs), {} }; MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids); @@ -2195,23 +2387,34 @@ static void intel_pstate_update_perf_limits(struct cpudata *cpu, unsigned int policy_min, unsigned int policy_max) { - int scaling = cpu->pstate.scaling; + int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling; int32_t max_policy_perf, min_policy_perf; + max_policy_perf = policy_max / perf_ctl_scaling; + if (policy_max == policy_min) { + min_policy_perf = max_policy_perf; + } else { + min_policy_perf = policy_min / perf_ctl_scaling; + min_policy_perf = clamp_t(int32_t, min_policy_perf, + 0, max_policy_perf); + } + /* * HWP needs some special consideration, because HWP_REQUEST uses * abstract values to represent performance rather than pure ratios. */ - if (hwp_active) + if (hwp_active) { intel_pstate_get_hwp_cap(cpu); - max_policy_perf = policy_max / scaling; - if (policy_max == policy_min) { - min_policy_perf = max_policy_perf; - } else { - min_policy_perf = policy_min / scaling; - min_policy_perf = clamp_t(int32_t, min_policy_perf, - 0, max_policy_perf); + if (cpu->pstate.scaling != perf_ctl_scaling) { + int scaling = cpu->pstate.scaling; + int freq; + + freq = max_policy_perf * perf_ctl_scaling; + max_policy_perf = DIV_ROUND_UP(freq, scaling); + freq = min_policy_perf * perf_ctl_scaling; + min_policy_perf = DIV_ROUND_UP(freq, scaling); + } } pr_debug("cpu:%d min_policy_perf:%d max_policy_perf:%d\n", @@ -2405,7 +2608,7 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) cpu->min_perf_ratio = 0; /* cpuinfo and default policy values */ - policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling; + policy->cpuinfo.min_freq = cpu->pstate.min_freq; update_turbo_state(); global.turbo_disabled_mf = global.turbo_disabled; policy->cpuinfo.max_freq = global.turbo_disabled ? @@ -3135,6 +3338,8 @@ hwp_cpu_matched: } pr_info("HWP enabled\n"); + } else if (boot_cpu_has(X86_FEATURE_HYBRID_CPU)) { + pr_warn("Problematic setup: Hybrid processor with disabled HWP\n"); } return 0; diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c index d05e761d9572..afc59b292153 100644 --- a/drivers/cpufreq/loongson2_cpufreq.c +++ b/drivers/cpufreq/loongson2_cpufreq.c @@ -16,7 +16,6 @@ #include #include #include -#include /* set_cpus_allowed() */ #include #include diff --git a/drivers/cpufreq/sc520_freq.c b/drivers/cpufreq/sc520_freq.c index 73a208559fe2..330c8d6cf93c 100644 --- a/drivers/cpufreq/sc520_freq.c +++ b/drivers/cpufreq/sc520_freq.c @@ -42,6 +42,7 @@ static unsigned int sc520_freq_get_cpu_frequency(unsigned int cpu) default: pr_err("error: cpuctl register has unexpected value %02x\n", clockspeed_reg); + fallthrough; case 0x01: return 100000; case 0x02: diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c index 0ac265d47ef0..1a251e635ebd 100644 --- a/drivers/cpufreq/sh-cpufreq.c +++ b/drivers/cpufreq/sh-cpufreq.c @@ -23,7 +23,6 @@ #include #include #include -#include /* set_cpus_allowed() */ #include #include #include diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index ac4bb27d69b0..7b91060e82f6 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -2,47 +2,103 @@ /* * Timer events oriented CPU idle governor * - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018 - 2021 Intel Corporation * Author: Rafael J. Wysocki + */ + +/** + * DOC: teo-description * * The idea of this governor is based on the observation that on many systems * timer events are two or more orders of magnitude more frequent than any - * other interrupts, so they are likely to be the most significant source of CPU + * other interrupts, so they are likely to be the most significant cause of CPU * wakeups from idle states. Moreover, information about what happened in the * (relatively recent) past can be used to estimate whether or not the deepest - * idle state with target residency within the time to the closest timer is - * likely to be suitable for the upcoming idle time of the CPU and, if not, then - * which of the shallower idle states to choose. + * idle state with target residency within the (known) time till the closest + * timer event, referred to as the sleep length, is likely to be suitable for + * the upcoming CPU idle period and, if not, then which of the shallower idle + * states to choose instead of it. * - * Of course, non-timer wakeup sources are more important in some use cases and - * they can be covered by taking a few most recent idle time intervals of the - * CPU into account. However, even in that case it is not necessary to consider - * idle duration values greater than the time till the closest timer, as the - * patterns that they may belong to produce average values close enough to - * the time till the closest timer (sleep length) anyway. + * Of course, non-timer wakeup sources are more important in some use cases + * which can be covered by taking a few most recent idle time intervals of the + * CPU into account. However, even in that context it is not necessary to + * consider idle duration values greater than the sleep length, because the + * closest timer will ultimately wake up the CPU anyway unless it is woken up + * earlier. * - * Thus this governor estimates whether or not the upcoming idle time of the CPU - * is likely to be significantly shorter than the sleep length and selects an - * idle state for it in accordance with that, as follows: + * Thus this governor estimates whether or not the prospective idle duration of + * a CPU is likely to be significantly shorter than the sleep length and selects + * an idle state for it accordingly. * - * - Find an idle state on the basis of the sleep length and state statistics - * collected over time: + * The computations carried out by this governor are based on using bins whose + * boundaries are aligned with the target residency parameter values of the CPU + * idle states provided by the %CPUIdle driver in the ascending order. That is, + * the first bin spans from 0 up to, but not including, the target residency of + * the second idle state (idle state 1), the second bin spans from the target + * residency of idle state 1 up to, but not including, the target residency of + * idle state 2, the third bin spans from the target residency of idle state 2 + * up to, but not including, the target residency of idle state 3 and so on. + * The last bin spans from the target residency of the deepest idle state + * supplied by the driver to infinity. * - * o Find the deepest idle state whose target residency is less than or equal - * to the sleep length. + * Two metrics called "hits" and "intercepts" are associated with each bin. + * They are updated every time before selecting an idle state for the given CPU + * in accordance with what happened last time. * - * o Select it if it matched both the sleep length and the observed idle - * duration in the past more often than it matched the sleep length alone - * (i.e. the observed idle duration was significantly shorter than the sleep - * length matched by it). + * The "hits" metric reflects the relative frequency of situations in which the + * sleep length and the idle duration measured after CPU wakeup fall into the + * same bin (that is, the CPU appears to wake up "on time" relative to the sleep + * length). In turn, the "intercepts" metric reflects the relative frequency of + * situations in which the measured idle duration is so much shorter than the + * sleep length that the bin it falls into corresponds to an idle state + * shallower than the one whose bin is fallen into by the sleep length (these + * situations are referred to as "intercepts" below). * - * o Otherwise, select the shallower state with the greatest matched "early" - * wakeups metric. + * In addition to the metrics described above, the governor counts recent + * intercepts (that is, intercepts that have occurred during the last + * %NR_RECENT invocations of it for the given CPU) for each bin. * - * - If the majority of the most recent idle duration values are below the - * target residency of the idle state selected so far, use those values to - * compute the new expected idle duration and find an idle state matching it - * (which has to be shallower than the one selected so far). + * In order to select an idle state for a CPU, the governor takes the following + * steps (modulo the possible latency constraint that must be taken into account + * too): + * + * 1. Find the deepest CPU idle state whose target residency does not exceed + * the current sleep length (the candidate idle state) and compute 3 sums as + * follows: + * + * - The sum of the "hits" and "intercepts" metrics for the candidate state + * and all of the deeper idle states (it represents the cases in which the + * CPU was idle long enough to avoid being intercepted if the sleep length + * had been equal to the current one). + * + * - The sum of the "intercepts" metrics for all of the idle states shallower + * than the candidate one (it represents the cases in which the CPU was not + * idle long enough to avoid being intercepted if the sleep length had been + * equal to the current one). + * + * - The sum of the numbers of recent intercepts for all of the idle states + * shallower than the candidate one. + * + * 2. If the second sum is greater than the first one or the third sum is + * greater than %NR_RECENT / 2, the CPU is likely to wake up early, so look + * for an alternative idle state to select. + * + * - Traverse the idle states shallower than the candidate one in the + * descending order. + * + * - For each of them compute the sum of the "intercepts" metrics and the sum + * of the numbers of recent intercepts over all of the idle states between + * it and the candidate one (including the former and excluding the + * latter). + * + * - If each of these sums that needs to be taken into account (because the + * check related to it has indicated that the CPU is likely to wake up + * early) is greater than a half of the corresponding sum computed in step + * 1 (which means that the target residency of the state in question had + * not exceeded the idle duration in over a half of the relevant cases), + * select the given idle state instead of the candidate one. + * + * 3. By default, select the candidate state. */ #include @@ -60,65 +116,51 @@ /* * Number of the most recent idle duration values to take into consideration for - * the detection of wakeup patterns. + * the detection of recent early wakeup patterns. */ -#define INTERVALS 8 +#define NR_RECENT 9 /** - * struct teo_idle_state - Idle state data used by the TEO cpuidle governor. - * @early_hits: "Early" CPU wakeups "matching" this state. - * @hits: "On time" CPU wakeups "matching" this state. - * @misses: CPU wakeups "missing" this state. - * - * A CPU wakeup is "matched" by a given idle state if the idle duration measured - * after the wakeup is between the target residency of that state and the target - * residency of the next one (or if this is the deepest available idle state, it - * "matches" a CPU wakeup when the measured idle duration is at least equal to - * its target residency). - * - * Also, from the TEO governor perspective, a CPU wakeup from idle is "early" if - * it occurs significantly earlier than the closest expected timer event (that - * is, early enough to match an idle state shallower than the one matching the - * time till the closest timer event). Otherwise, the wakeup is "on time", or - * it is a "hit". - * - * A "miss" occurs when the given state doesn't match the wakeup, but it matches - * the time till the closest timer event used for idle state selection. + * struct teo_bin - Metrics used by the TEO cpuidle governor. + * @intercepts: The "intercepts" metric. + * @hits: The "hits" metric. + * @recent: The number of recent "intercepts". */ -struct teo_idle_state { - unsigned int early_hits; +struct teo_bin { + unsigned int intercepts; unsigned int hits; - unsigned int misses; + unsigned int recent; }; /** * struct teo_cpu - CPU data used by the TEO cpuidle governor. * @time_span_ns: Time between idle state selection and post-wakeup update. * @sleep_length_ns: Time till the closest timer event (at the selection time). - * @states: Idle states data corresponding to this CPU. - * @interval_idx: Index of the most recent saved idle interval. - * @intervals: Saved idle duration values. + * @state_bins: Idle state data bins for this CPU. + * @total: Grand total of the "intercepts" and "hits" mertics for all bins. + * @next_recent_idx: Index of the next @recent_idx entry to update. + * @recent_idx: Indices of bins corresponding to recent "intercepts". */ struct teo_cpu { s64 time_span_ns; s64 sleep_length_ns; - struct teo_idle_state states[CPUIDLE_STATE_MAX]; - int interval_idx; - u64 intervals[INTERVALS]; + struct teo_bin state_bins[CPUIDLE_STATE_MAX]; + unsigned int total; + int next_recent_idx; + int recent_idx[NR_RECENT]; }; static DEFINE_PER_CPU(struct teo_cpu, teo_cpus); /** - * teo_update - Update CPU data after wakeup. + * teo_update - Update CPU metrics after wakeup. * @drv: cpuidle driver containing state data. * @dev: Target CPU. */ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) { struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); - int i, idx_hit = 0, idx_timer = 0; - unsigned int hits, misses; + int i, idx_timer = 0, idx_duration = 0; u64 measured_ns; if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) { @@ -151,53 +193,52 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) measured_ns /= 2; } + cpu_data->total = 0; + /* - * Decay the "early hits" metric for all of the states and find the - * states matching the sleep length and the measured idle duration. + * Decay the "hits" and "intercepts" metrics for all of the bins and + * find the bins that the sleep length and the measured idle duration + * fall into. */ for (i = 0; i < drv->state_count; i++) { - unsigned int early_hits = cpu_data->states[i].early_hits; + s64 target_residency_ns = drv->states[i].target_residency_ns; + struct teo_bin *bin = &cpu_data->state_bins[i]; - cpu_data->states[i].early_hits -= early_hits >> DECAY_SHIFT; + bin->hits -= bin->hits >> DECAY_SHIFT; + bin->intercepts -= bin->intercepts >> DECAY_SHIFT; - if (drv->states[i].target_residency_ns <= cpu_data->sleep_length_ns) { + cpu_data->total += bin->hits + bin->intercepts; + + if (target_residency_ns <= cpu_data->sleep_length_ns) { idx_timer = i; - if (drv->states[i].target_residency_ns <= measured_ns) - idx_hit = i; + if (target_residency_ns <= measured_ns) + idx_duration = i; } } + i = cpu_data->next_recent_idx++; + if (cpu_data->next_recent_idx >= NR_RECENT) + cpu_data->next_recent_idx = 0; + + if (cpu_data->recent_idx[i] >= 0) + cpu_data->state_bins[cpu_data->recent_idx[i]].recent--; + /* - * Update the "hits" and "misses" data for the state matching the sleep - * length. If it matches the measured idle duration too, this is a hit, - * so increase the "hits" metric for it then. Otherwise, this is a - * miss, so increase the "misses" metric for it. In the latter case - * also increase the "early hits" metric for the state that actually - * matches the measured idle duration. + * If the measured idle duration falls into the same bin as the sleep + * length, this is a "hit", so update the "hits" metric for that bin. + * Otherwise, update the "intercepts" metric for the bin fallen into by + * the measured idle duration. */ - hits = cpu_data->states[idx_timer].hits; - hits -= hits >> DECAY_SHIFT; - - misses = cpu_data->states[idx_timer].misses; - misses -= misses >> DECAY_SHIFT; - - if (idx_timer == idx_hit) { - hits += PULSE; + if (idx_timer == idx_duration) { + cpu_data->state_bins[idx_timer].hits += PULSE; + cpu_data->recent_idx[i] = -1; } else { - misses += PULSE; - cpu_data->states[idx_hit].early_hits += PULSE; + cpu_data->state_bins[idx_duration].intercepts += PULSE; + cpu_data->state_bins[idx_duration].recent++; + cpu_data->recent_idx[i] = idx_duration; } - cpu_data->states[idx_timer].misses = misses; - cpu_data->states[idx_timer].hits = hits; - - /* - * Save idle duration values corresponding to non-timer wakeups for - * pattern detection. - */ - cpu_data->intervals[cpu_data->interval_idx++] = measured_ns; - if (cpu_data->interval_idx >= INTERVALS) - cpu_data->interval_idx = 0; + cpu_data->total += PULSE; } static bool teo_time_ok(u64 interval_ns) @@ -205,6 +246,12 @@ static bool teo_time_ok(u64 interval_ns) return !tick_nohz_tick_stopped() || interval_ns >= TICK_NSEC; } +static s64 teo_middle_of_bin(int idx, struct cpuidle_driver *drv) +{ + return (drv->states[idx].target_residency_ns + + drv->states[idx+1].target_residency_ns) / 2; +} + /** * teo_find_shallower_state - Find shallower idle state matching given duration. * @drv: cpuidle driver containing state data. @@ -240,10 +287,18 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, { struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); s64 latency_req = cpuidle_governor_latency_req(dev->cpu); - int max_early_idx, prev_max_early_idx, constraint_idx, idx0, idx, i; - unsigned int hits, misses, early_hits; + unsigned int idx_intercept_sum = 0; + unsigned int intercept_sum = 0; + unsigned int idx_recent_sum = 0; + unsigned int recent_sum = 0; + unsigned int idx_hit_sum = 0; + unsigned int hit_sum = 0; + int constraint_idx = 0; + int idx0 = 0, idx = -1; + bool alt_intercepts, alt_recent; ktime_t delta_tick; s64 duration_ns; + int i; if (dev->last_state_idx >= 0) { teo_update(drv, dev); @@ -255,170 +310,135 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, duration_ns = tick_nohz_get_sleep_length(&delta_tick); cpu_data->sleep_length_ns = duration_ns; - hits = 0; - misses = 0; - early_hits = 0; - max_early_idx = -1; - prev_max_early_idx = -1; - constraint_idx = drv->state_count; - idx = -1; - idx0 = idx; + /* Check if there is any choice in the first place. */ + if (drv->state_count < 2) { + idx = 0; + goto end; + } + if (!dev->states_usage[0].disable) { + idx = 0; + if (drv->states[1].target_residency_ns > duration_ns) + goto end; + } - for (i = 0; i < drv->state_count; i++) { + /* + * Find the deepest idle state whose target residency does not exceed + * the current sleep length and the deepest idle state not deeper than + * the former whose exit latency does not exceed the current latency + * constraint. Compute the sums of metrics for early wakeup pattern + * detection. + */ + for (i = 1; i < drv->state_count; i++) { + struct teo_bin *prev_bin = &cpu_data->state_bins[i-1]; struct cpuidle_state *s = &drv->states[i]; - if (dev->states_usage[i].disable) { - /* - * Ignore disabled states with target residencies beyond - * the anticipated idle duration. - */ - if (s->target_residency_ns > duration_ns) - continue; - - /* - * This state is disabled, so the range of idle duration - * values corresponding to it is covered by the current - * candidate state, but still the "hits" and "misses" - * metrics of the disabled state need to be used to - * decide whether or not the state covering the range in - * question is good enough. - */ - hits = cpu_data->states[i].hits; - misses = cpu_data->states[i].misses; - - if (early_hits >= cpu_data->states[i].early_hits || - idx < 0) - continue; - - /* - * If the current candidate state has been the one with - * the maximum "early hits" metric so far, the "early - * hits" metric of the disabled state replaces the - * current "early hits" count to avoid selecting a - * deeper state with lower "early hits" metric. - */ - if (max_early_idx == idx) { - early_hits = cpu_data->states[i].early_hits; - continue; - } - - /* - * The current candidate state is closer to the disabled - * one than the current maximum "early hits" state, so - * replace the latter with it, but in case the maximum - * "early hits" state index has not been set so far, - * check if the current candidate state is not too - * shallow for that role. - */ - if (teo_time_ok(drv->states[idx].target_residency_ns)) { - prev_max_early_idx = max_early_idx; - early_hits = cpu_data->states[i].early_hits; - max_early_idx = idx; - } + /* + * Update the sums of idle state mertics for all of the states + * shallower than the current one. + */ + intercept_sum += prev_bin->intercepts; + hit_sum += prev_bin->hits; + recent_sum += prev_bin->recent; + if (dev->states_usage[i].disable) continue; - } if (idx < 0) { idx = i; /* first enabled state */ - hits = cpu_data->states[i].hits; - misses = cpu_data->states[i].misses; idx0 = i; } if (s->target_residency_ns > duration_ns) break; - if (s->exit_latency_ns > latency_req && constraint_idx > i) + idx = i; + + if (s->exit_latency_ns <= latency_req) constraint_idx = i; - idx = i; - hits = cpu_data->states[i].hits; - misses = cpu_data->states[i].misses; - - if (early_hits < cpu_data->states[i].early_hits && - teo_time_ok(drv->states[i].target_residency_ns)) { - prev_max_early_idx = max_early_idx; - early_hits = cpu_data->states[i].early_hits; - max_early_idx = i; - } + idx_intercept_sum = intercept_sum; + idx_hit_sum = hit_sum; + idx_recent_sum = recent_sum; } - /* - * If the "hits" metric of the idle state matching the sleep length is - * greater than its "misses" metric, that is the one to use. Otherwise, - * it is more likely that one of the shallower states will match the - * idle duration observed after wakeup, so take the one with the maximum - * "early hits" metric, but if that cannot be determined, just use the - * state selected so far. - */ - if (hits <= misses) { - /* - * The current candidate state is not suitable, so take the one - * whose "early hits" metric is the maximum for the range of - * shallower states. - */ - if (idx == max_early_idx) - max_early_idx = prev_max_early_idx; - - if (max_early_idx >= 0) { - idx = max_early_idx; - duration_ns = drv->states[idx].target_residency_ns; - } - } - - /* - * If there is a latency constraint, it may be necessary to use a - * shallower idle state than the one selected so far. - */ - if (constraint_idx < idx) - idx = constraint_idx; - + /* Avoid unnecessary overhead. */ if (idx < 0) { - idx = 0; /* No states enabled. Must use 0. */ - } else if (idx > idx0) { - unsigned int count = 0; - u64 sum = 0; + idx = 0; /* No states enabled, must use 0. */ + goto end; + } else if (idx == idx0) { + goto end; + } + + /* + * If the sum of the intercepts metric for all of the idle states + * shallower than the current candidate one (idx) is greater than the + * sum of the intercepts and hits metrics for the candidate state and + * all of the deeper states, or the sum of the numbers of recent + * intercepts over all of the states shallower than the candidate one + * is greater than a half of the number of recent events taken into + * account, the CPU is likely to wake up early, so find an alternative + * idle state to select. + */ + alt_intercepts = 2 * idx_intercept_sum > cpu_data->total - idx_hit_sum; + alt_recent = idx_recent_sum > NR_RECENT / 2; + if (alt_recent || alt_intercepts) { + s64 last_enabled_span_ns = duration_ns; + int last_enabled_idx = idx; /* - * The target residencies of at least two different enabled idle - * states are less than or equal to the current expected idle - * duration. Try to refine the selection using the most recent - * measured idle duration values. + * Look for the deepest idle state whose target residency had + * not exceeded the idle duration in over a half of the relevant + * cases (both with respect to intercepts overall and with + * respect to the recent intercepts only) in the past. * - * Count and sum the most recent idle duration values less than - * the current expected idle duration value. + * Take the possible latency constraint and duration limitation + * present if the tick has been stopped already into account. */ - for (i = 0; i < INTERVALS; i++) { - u64 val = cpu_data->intervals[i]; + intercept_sum = 0; + recent_sum = 0; - if (val >= duration_ns) + for (i = idx - 1; i >= idx0; i--) { + struct teo_bin *bin = &cpu_data->state_bins[i]; + s64 span_ns; + + intercept_sum += bin->intercepts; + recent_sum += bin->recent; + + if (dev->states_usage[i].disable) continue; - count++; - sum += val; - } - - /* - * Give up unless the majority of the most recent idle duration - * values are in the interesting range. - */ - if (count > INTERVALS / 2) { - u64 avg_ns = div64_u64(sum, count); - - /* - * Avoid spending too much time in an idle state that - * would be too shallow. - */ - if (teo_time_ok(avg_ns)) { - duration_ns = avg_ns; - if (drv->states[idx].target_residency_ns > avg_ns) - idx = teo_find_shallower_state(drv, dev, - idx, avg_ns); + span_ns = teo_middle_of_bin(i, drv); + if (!teo_time_ok(span_ns)) { + /* + * The current state is too shallow, so select + * the first enabled deeper state. + */ + duration_ns = last_enabled_span_ns; + idx = last_enabled_idx; + break; } + + if ((!alt_recent || 2 * recent_sum > idx_recent_sum) && + (!alt_intercepts || + 2 * intercept_sum > idx_intercept_sum)) { + idx = i; + duration_ns = span_ns; + break; + } + + last_enabled_span_ns = span_ns; + last_enabled_idx = i; } } + /* + * If there is a latency constraint, it may be necessary to select an + * idle state shallower than the current candidate one. + */ + if (idx > constraint_idx) + idx = constraint_idx; + +end: /* * Don't stop the tick if the selected state is a polling one or if the * expected idle duration is shorter than the tick period length. @@ -478,8 +498,8 @@ static int teo_enable_device(struct cpuidle_driver *drv, memset(cpu_data, 0, sizeof(*cpu_data)); - for (i = 0; i < INTERVALS; i++) - cpu_data->intervals[i] = U64_MAX; + for (i = 0; i < NR_RECENT; i++) + cpu_data->recent_idx[i] = -1; return 0; } diff --git a/drivers/dax/device.c b/drivers/dax/device.c index db92573c94e8..dd8222a42808 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -337,7 +337,7 @@ static unsigned long dax_get_unmapped_area(struct file *filp, } static const struct address_space_operations dev_dax_aops = { - .set_page_dirty = noop_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, .invalidatepage = noop_invalidatepage, }; diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig index 20373a893b44..e87d01c0b76a 100644 --- a/drivers/devfreq/Kconfig +++ b/drivers/devfreq/Kconfig @@ -103,7 +103,6 @@ config ARM_IMX8M_DDRC_DEVFREQ tristate "i.MX8M DDRC DEVFREQ Driver" depends on (ARCH_MXC && HAVE_ARM_SMCCC) || \ (COMPILE_TEST && HAVE_ARM_SMCCC) - select DEVFREQ_GOV_SIMPLE_ONDEMAND select DEVFREQ_GOV_USERSPACE help This adds the DEVFREQ driver for the i.MX8M DDR Controller. It allows diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index fe08c46642f7..28f3e0ba6cdd 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -823,6 +823,7 @@ struct devfreq *devfreq_add_device(struct device *dev, if (devfreq->profile->timer < 0 || devfreq->profile->timer >= DEVFREQ_TIMER_NUM) { mutex_unlock(&devfreq->lock); + err = -EINVAL; goto err_dev; } diff --git a/drivers/devfreq/governor_passive.c b/drivers/devfreq/governor_passive.c index b094132bd20b..fc09324a03e0 100644 --- a/drivers/devfreq/governor_passive.c +++ b/drivers/devfreq/governor_passive.c @@ -65,7 +65,7 @@ static int devfreq_passive_get_target_freq(struct devfreq *devfreq, dev_pm_opp_put(p_opp); if (IS_ERR(opp)) - return PTR_ERR(opp); + goto no_required_opp; *freq = dev_pm_opp_get_freq(opp); dev_pm_opp_put(opp); @@ -73,6 +73,7 @@ static int devfreq_passive_get_target_freq(struct devfreq *devfreq, return 0; } +no_required_opp: /* * Get the OPP table's index of decided frequency by governor * of parent device. diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c index 0fd6c4851071..ab9db7adb3ad 100644 --- a/drivers/devfreq/governor_userspace.c +++ b/drivers/devfreq/governor_userspace.c @@ -31,8 +31,8 @@ static int devfreq_userspace_func(struct devfreq *df, unsigned long *freq) return 0; } -static ssize_t store_freq(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t set_freq_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct devfreq *devfreq = to_devfreq(dev); struct userspace_data *data; @@ -52,8 +52,8 @@ static ssize_t store_freq(struct device *dev, struct device_attribute *attr, return err; } -static ssize_t show_freq(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t set_freq_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct devfreq *devfreq = to_devfreq(dev); struct userspace_data *data; @@ -70,7 +70,7 @@ static ssize_t show_freq(struct device *dev, struct device_attribute *attr, return err; } -static DEVICE_ATTR(set_freq, 0644, show_freq, store_freq); +static DEVICE_ATTR_RW(set_freq); static struct attribute *dev_entries[] = { &dev_attr_set_freq.attr, NULL, diff --git a/drivers/devfreq/imx-bus.c b/drivers/devfreq/imx-bus.c index 3fc3fd77492d..f3f6e25053ed 100644 --- a/drivers/devfreq/imx-bus.c +++ b/drivers/devfreq/imx-bus.c @@ -45,18 +45,6 @@ static int imx_bus_get_cur_freq(struct device *dev, unsigned long *freq) return 0; } -static int imx_bus_get_dev_status(struct device *dev, - struct devfreq_dev_status *stat) -{ - struct imx_bus *priv = dev_get_drvdata(dev); - - stat->busy_time = 0; - stat->total_time = 0; - stat->current_frequency = clk_get_rate(priv->clk); - - return 0; -} - static void imx_bus_exit(struct device *dev) { struct imx_bus *priv = dev_get_drvdata(dev); @@ -129,9 +117,7 @@ static int imx_bus_probe(struct platform_device *pdev) return ret; } - priv->profile.polling_ms = 1000; priv->profile.target = imx_bus_target; - priv->profile.get_dev_status = imx_bus_get_dev_status; priv->profile.exit = imx_bus_exit; priv->profile.get_cur_freq = imx_bus_get_cur_freq; priv->profile.initial_freq = clk_get_rate(priv->clk); diff --git a/drivers/devfreq/tegra30-devfreq.c b/drivers/devfreq/tegra30-devfreq.c index ce83f883ca65..10661eb2aed8 100644 --- a/drivers/devfreq/tegra30-devfreq.c +++ b/drivers/devfreq/tegra30-devfreq.c @@ -688,6 +688,7 @@ static struct devfreq_dev_profile tegra_devfreq_profile = { .polling_ms = ACTMON_SAMPLING_PERIOD, .target = tegra_devfreq_target, .get_dev_status = tegra_devfreq_get_dev_status, + .is_cooling_device = true, }; static int tegra_governor_get_target(struct devfreq *devfreq, diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 1e836e320edd..91164c5f0757 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -270,7 +270,8 @@ config EDAC_PND2 config EDAC_IGEN6 tristate "Intel client SoC Integrated MC" - depends on PCI && X86_64 && PCI_MMCONFIG && ARCH_HAVE_NMI_SAFE_CMPXCHG + depends on PCI && PCI_MMCONFIG && ARCH_HAVE_NMI_SAFE_CMPXCHG + depends on X64_64 && X86_MCE_INTEL help Support for error detection and correction on the Intel client SoC Integrated Memory Controller using In-Band ECC IP. diff --git a/drivers/edac/aspeed_edac.c b/drivers/edac/aspeed_edac.c index a46da56d6d54..6bd5f8815919 100644 --- a/drivers/edac/aspeed_edac.c +++ b/drivers/edac/aspeed_edac.c @@ -254,8 +254,8 @@ static int init_csrows(struct mem_ctl_info *mci) return rc; } - dev_dbg(mci->pdev, "dt: /memory node resources: first page r.start=0x%x, resource_size=0x%x, PAGE_SHIFT macro=0x%x\n", - r.start, resource_size(&r), PAGE_SHIFT); + dev_dbg(mci->pdev, "dt: /memory node resources: first page %pR, PAGE_SHIFT macro=0x%x\n", + &r, PAGE_SHIFT); csrow->first_page = r.start >> PAGE_SHIFT; nr_pages = resource_size(&r) >> PAGE_SHIFT; diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c index 238a4ad1e526..6ce0ed2ffaaf 100644 --- a/drivers/edac/i10nm_base.c +++ b/drivers/edac/i10nm_base.c @@ -13,7 +13,7 @@ #include "edac_module.h" #include "skx_common.h" -#define I10NM_REVISION "v0.0.4" +#define I10NM_REVISION "v0.0.5" #define EDAC_MOD_STR "i10nm_edac" /* Debug macros */ @@ -24,19 +24,39 @@ pci_read_config_dword((d)->uracu, 0xd0, &(reg)) #define I10NM_GET_IMC_BAR(d, i, reg) \ pci_read_config_dword((d)->uracu, 0xd8 + (i) * 4, &(reg)) +#define I10NM_GET_SAD(d, offset, i, reg)\ + pci_read_config_dword((d)->sad_all, (offset) + (i) * 8, &(reg)) +#define I10NM_GET_HBM_IMC_BAR(d, reg) \ + pci_read_config_dword((d)->uracu, 0xd4, &(reg)) +#define I10NM_GET_CAPID3_CFG(d, reg) \ + pci_read_config_dword((d)->pcu_cr3, 0x90, &(reg)) #define I10NM_GET_DIMMMTR(m, i, j) \ - readl((m)->mbase + 0x2080c + (i) * (m)->chan_mmio_sz + (j) * 4) + readl((m)->mbase + ((m)->hbm_mc ? 0x80c : 0x2080c) + \ + (i) * (m)->chan_mmio_sz + (j) * 4) #define I10NM_GET_MCDDRTCFG(m, i, j) \ - readl((m)->mbase + 0x20970 + (i) * (m)->chan_mmio_sz + (j) * 4) + readl((m)->mbase + ((m)->hbm_mc ? 0x970 : 0x20970) + \ + (i) * (m)->chan_mmio_sz + (j) * 4) #define I10NM_GET_MCMTR(m, i) \ - readl((m)->mbase + 0x20ef8 + (i) * (m)->chan_mmio_sz) + readl((m)->mbase + ((m)->hbm_mc ? 0xef8 : 0x20ef8) + \ + (i) * (m)->chan_mmio_sz) #define I10NM_GET_AMAP(m, i) \ - readl((m)->mbase + 0x20814 + (i) * (m)->chan_mmio_sz) + readl((m)->mbase + ((m)->hbm_mc ? 0x814 : 0x20814) + \ + (i) * (m)->chan_mmio_sz) #define I10NM_GET_SCK_MMIO_BASE(reg) (GET_BITFIELD(reg, 0, 28) << 23) #define I10NM_GET_IMC_MMIO_OFFSET(reg) (GET_BITFIELD(reg, 0, 10) << 12) #define I10NM_GET_IMC_MMIO_SIZE(reg) ((GET_BITFIELD(reg, 13, 23) - \ GET_BITFIELD(reg, 0, 10) + 1) << 12) +#define I10NM_GET_HBM_IMC_MMIO_OFFSET(reg) \ + ((GET_BITFIELD(reg, 0, 10) << 12) + 0x140000) + +#define I10NM_HBM_IMC_MMIO_SIZE 0x9000 +#define I10NM_IS_HBM_PRESENT(reg) GET_BITFIELD(reg, 27, 30) +#define I10NM_IS_HBM_IMC(reg) GET_BITFIELD(reg, 29, 29) + +#define I10NM_MAX_SAD 16 +#define I10NM_SAD_ENABLE(reg) GET_BITFIELD(reg, 0, 0) +#define I10NM_SAD_NM_CACHEABLE(reg) GET_BITFIELD(reg, 5, 5) static struct list_head *i10nm_edac_list; @@ -63,7 +83,32 @@ static struct pci_dev *pci_get_dev_wrapper(int dom, unsigned int bus, return pdev; } -static int i10nm_get_all_munits(void) +static bool i10nm_check_2lm(struct res_config *cfg) +{ + struct skx_dev *d; + u32 reg; + int i; + + list_for_each_entry(d, i10nm_edac_list, list) { + d->sad_all = pci_get_dev_wrapper(d->seg, d->bus[1], + PCI_SLOT(cfg->sad_all_devfn), + PCI_FUNC(cfg->sad_all_devfn)); + if (!d->sad_all) + continue; + + for (i = 0; i < I10NM_MAX_SAD; i++) { + I10NM_GET_SAD(d, cfg->sad_all_offset, i, reg); + if (I10NM_SAD_ENABLE(reg) && I10NM_SAD_NM_CACHEABLE(reg)) { + edac_dbg(2, "2-level memory configuration.\n"); + return true; + } + } + } + + return false; +} + +static int i10nm_get_ddr_munits(void) { struct pci_dev *mdev; void __iomem *mbase; @@ -91,7 +136,7 @@ static int i10nm_get_all_munits(void) edac_dbg(2, "socket%d mmio base 0x%llx (reg 0x%x)\n", j++, base, reg); - for (i = 0; i < I10NM_NUM_IMC; i++) { + for (i = 0; i < I10NM_NUM_DDR_IMC; i++) { mdev = pci_get_dev_wrapper(d->seg, d->bus[0], 12 + i, 0); if (i == 0 && !mdev) { @@ -127,11 +172,97 @@ static int i10nm_get_all_munits(void) return 0; } +static bool i10nm_check_hbm_imc(struct skx_dev *d) +{ + u32 reg; + + if (I10NM_GET_CAPID3_CFG(d, reg)) { + i10nm_printk(KERN_ERR, "Failed to get capid3_cfg\n"); + return false; + } + + return I10NM_IS_HBM_PRESENT(reg) != 0; +} + +static int i10nm_get_hbm_munits(void) +{ + struct pci_dev *mdev; + void __iomem *mbase; + u32 reg, off, mcmtr; + struct skx_dev *d; + int i, lmc; + u64 base; + + list_for_each_entry(d, i10nm_edac_list, list) { + d->pcu_cr3 = pci_get_dev_wrapper(d->seg, d->bus[1], 30, 3); + if (!d->pcu_cr3) + return -ENODEV; + + if (!i10nm_check_hbm_imc(d)) { + i10nm_printk(KERN_DEBUG, "No hbm memory\n"); + return -ENODEV; + } + + if (I10NM_GET_SCK_BAR(d, reg)) { + i10nm_printk(KERN_ERR, "Failed to get socket bar\n"); + return -ENODEV; + } + base = I10NM_GET_SCK_MMIO_BASE(reg); + + if (I10NM_GET_HBM_IMC_BAR(d, reg)) { + i10nm_printk(KERN_ERR, "Failed to get hbm mc bar\n"); + return -ENODEV; + } + base += I10NM_GET_HBM_IMC_MMIO_OFFSET(reg); + + lmc = I10NM_NUM_DDR_IMC; + + for (i = 0; i < I10NM_NUM_HBM_IMC; i++) { + mdev = pci_get_dev_wrapper(d->seg, d->bus[0], + 12 + i / 4, 1 + i % 4); + if (i == 0 && !mdev) { + i10nm_printk(KERN_ERR, "No hbm mc found\n"); + return -ENODEV; + } + if (!mdev) + continue; + + d->imc[lmc].mdev = mdev; + off = i * I10NM_HBM_IMC_MMIO_SIZE; + + edac_dbg(2, "hbm mc%d mmio base 0x%llx size 0x%x\n", + lmc, base + off, I10NM_HBM_IMC_MMIO_SIZE); + + mbase = ioremap(base + off, I10NM_HBM_IMC_MMIO_SIZE); + if (!mbase) { + i10nm_printk(KERN_ERR, "Failed to ioremap for hbm mc 0x%llx\n", + base + off); + return -ENOMEM; + } + + d->imc[lmc].mbase = mbase; + d->imc[lmc].hbm_mc = true; + + mcmtr = I10NM_GET_MCMTR(&d->imc[lmc], 0); + if (!I10NM_IS_HBM_IMC(mcmtr)) { + i10nm_printk(KERN_ERR, "This isn't an hbm mc!\n"); + return -ENODEV; + } + + lmc++; + } + } + + return 0; +} + static struct res_config i10nm_cfg0 = { .type = I10NM, .decs_did = 0x3452, .busno_cfg_offset = 0xcc, .ddr_chan_mmio_sz = 0x4000, + .sad_all_devfn = PCI_DEVFN(29, 0), + .sad_all_offset = 0x108, }; static struct res_config i10nm_cfg1 = { @@ -139,6 +270,8 @@ static struct res_config i10nm_cfg1 = { .decs_did = 0x3452, .busno_cfg_offset = 0xd0, .ddr_chan_mmio_sz = 0x4000, + .sad_all_devfn = PCI_DEVFN(29, 0), + .sad_all_offset = 0x108, }; static struct res_config spr_cfg = { @@ -146,7 +279,10 @@ static struct res_config spr_cfg = { .decs_did = 0x3252, .busno_cfg_offset = 0xd0, .ddr_chan_mmio_sz = 0x8000, + .hbm_chan_mmio_sz = 0x4000, .support_ddr5 = true, + .sad_all_devfn = PCI_DEVFN(10, 0), + .sad_all_offset = 0x300, }; static const struct x86_cpu_id i10nm_cpuids[] = { @@ -179,13 +315,13 @@ static int i10nm_get_dimm_config(struct mem_ctl_info *mci, struct dimm_info *dimm; int i, j, ndimms; - for (i = 0; i < I10NM_NUM_CHANNELS; i++) { + for (i = 0; i < imc->num_channels; i++) { if (!imc->mbase) continue; ndimms = 0; amap = I10NM_GET_AMAP(imc, i); - for (j = 0; j < I10NM_NUM_DIMMS; j++) { + for (j = 0; j < imc->num_dimms; j++) { dimm = edac_get_dimm(mci, i, j, 0); mtr = I10NM_GET_DIMMMTR(imc, i, j); mcddrtcfg = I10NM_GET_MCDDRTCFG(imc, i, j); @@ -278,6 +414,9 @@ static int __init i10nm_init(void) if (owner && strncmp(owner, EDAC_MOD_STR, sizeof(EDAC_MOD_STR))) return -EBUSY; + if (cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + return -ENODEV; + id = x86_match_cpu(i10nm_cpuids); if (!id) return -ENODEV; @@ -296,8 +435,11 @@ static int __init i10nm_init(void) return -ENODEV; } - rc = i10nm_get_all_munits(); - if (rc < 0) + skx_set_mem_cfg(i10nm_check_2lm(cfg)); + + rc = i10nm_get_ddr_munits(); + + if (i10nm_get_hbm_munits() && rc) goto fail; list_for_each_entry(d, i10nm_edac_list, list) { @@ -318,7 +460,15 @@ static int __init i10nm_init(void) d->imc[i].lmc = i; d->imc[i].src_id = src_id; d->imc[i].node_id = node_id; - d->imc[i].chan_mmio_sz = cfg->ddr_chan_mmio_sz; + if (d->imc[i].hbm_mc) { + d->imc[i].chan_mmio_sz = cfg->hbm_chan_mmio_sz; + d->imc[i].num_channels = I10NM_NUM_HBM_CHANNELS; + d->imc[i].num_dimms = I10NM_NUM_HBM_DIMMS; + } else { + d->imc[i].chan_mmio_sz = cfg->ddr_chan_mmio_sz; + d->imc[i].num_channels = I10NM_NUM_DDR_CHANNELS; + d->imc[i].num_dimms = I10NM_NUM_DDR_DIMMS; + } rc = skx_register_mci(&d->imc[i], d->imc[i].mdev, "Intel_10nm Socket", EDAC_MOD_STR, diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index 6be9986fc6bd..a07bbfd075d0 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -22,11 +22,12 @@ #include #include #include +#include #include "edac_mc.h" #include "edac_module.h" -#define IGEN6_REVISION "v2.4" +#define IGEN6_REVISION "v2.5" #define EDAC_MOD_STR "igen6_edac" #define IGEN6_NMI_NAME "igen6_ibecc" @@ -40,7 +41,7 @@ #define GET_BITFIELD(v, lo, hi) (((v) & GENMASK_ULL(hi, lo)) >> (lo)) -#define NUM_IMC 1 /* Max memory controllers */ +#define NUM_IMC 2 /* Max memory controllers */ #define NUM_CHANNELS 2 /* Max channels */ #define NUM_DIMMS 2 /* Max DIMMs per channel */ @@ -54,6 +55,10 @@ #define CAPID_C_OFFSET 0xec #define CAPID_C_IBECC BIT(15) +/* Capability register E */ +#define CAPID_E_OFFSET 0xf0 +#define CAPID_E_IBECC BIT(12) + /* Error Status */ #define ERRSTS_OFFSET 0xc8 #define ERRSTS_CE BIT_ULL(6) @@ -70,7 +75,7 @@ #define IBECC_ACTIVATE_EN BIT(0) /* IBECC error log */ -#define ECC_ERROR_LOG_OFFSET (IBECC_BASE + 0x170) +#define ECC_ERROR_LOG_OFFSET (IBECC_BASE + res_cfg->ibecc_error_log_offset) #define ECC_ERROR_LOG_CE BIT_ULL(62) #define ECC_ERROR_LOG_UE BIT_ULL(63) #define ECC_ERROR_LOG_ADDR_SHIFT 5 @@ -84,39 +89,54 @@ #define MCHBAR_SIZE 0x10000 /* Parameters for the channel decode stage */ -#define MAD_INTER_CHANNEL_OFFSET 0x5000 +#define IMC_BASE (res_cfg->imc_base) +#define MAD_INTER_CHANNEL_OFFSET IMC_BASE #define MAD_INTER_CHANNEL_DDR_TYPE(v) GET_BITFIELD(v, 0, 2) #define MAD_INTER_CHANNEL_ECHM(v) GET_BITFIELD(v, 3, 3) #define MAD_INTER_CHANNEL_CH_L_MAP(v) GET_BITFIELD(v, 4, 4) #define MAD_INTER_CHANNEL_CH_S_SIZE(v) ((u64)GET_BITFIELD(v, 12, 19) << 29) /* Parameters for DRAM decode stage */ -#define MAD_INTRA_CH0_OFFSET 0x5004 +#define MAD_INTRA_CH0_OFFSET (IMC_BASE + 4) #define MAD_INTRA_CH_DIMM_L_MAP(v) GET_BITFIELD(v, 0, 0) /* DIMM characteristics */ -#define MAD_DIMM_CH0_OFFSET 0x500c +#define MAD_DIMM_CH0_OFFSET (IMC_BASE + 0xc) #define MAD_DIMM_CH_DIMM_L_SIZE(v) ((u64)GET_BITFIELD(v, 0, 6) << 29) #define MAD_DIMM_CH_DLW(v) GET_BITFIELD(v, 7, 8) #define MAD_DIMM_CH_DIMM_S_SIZE(v) ((u64)GET_BITFIELD(v, 16, 22) << 29) #define MAD_DIMM_CH_DSW(v) GET_BITFIELD(v, 24, 25) +/* Hash for memory controller selection */ +#define MAD_MC_HASH_OFFSET (IMC_BASE + 0x1b8) +#define MAC_MC_HASH_LSB(v) GET_BITFIELD(v, 1, 3) + /* Hash for channel selection */ -#define CHANNEL_HASH_OFFSET 0X5024 +#define CHANNEL_HASH_OFFSET (IMC_BASE + 0x24) /* Hash for enhanced channel selection */ -#define CHANNEL_EHASH_OFFSET 0X5028 +#define CHANNEL_EHASH_OFFSET (IMC_BASE + 0x28) #define CHANNEL_HASH_MASK(v) (GET_BITFIELD(v, 6, 19) << 6) #define CHANNEL_HASH_LSB_MASK_BIT(v) GET_BITFIELD(v, 24, 26) #define CHANNEL_HASH_MODE(v) GET_BITFIELD(v, 28, 28) +/* Parameters for memory slice decode stage */ +#define MEM_SLICE_HASH_MASK(v) (GET_BITFIELD(v, 6, 19) << 6) +#define MEM_SLICE_HASH_LSB_MASK_BIT(v) GET_BITFIELD(v, 24, 26) + static struct res_config { + bool machine_check; int num_imc; + u32 imc_base; + u32 cmf_base; + u32 cmf_size; + u32 ms_hash_offset; u32 ibecc_base; + u32 ibecc_error_log_offset; bool (*ibecc_available)(struct pci_dev *pdev); /* Convert error address logged in IBECC to system physical address */ - u64 (*err_addr_to_sys_addr)(u64 eaddr); + u64 (*err_addr_to_sys_addr)(u64 eaddr, int mc); /* Convert error address logged in IBECC to integrated memory controller address */ - u64 (*err_addr_to_imc_addr)(u64 eaddr); + u64 (*err_addr_to_imc_addr)(u64 eaddr, int mc); } *res_cfg; struct igen6_imc { @@ -125,6 +145,7 @@ struct igen6_imc { struct pci_dev *pdev; struct device dev; void __iomem *window; + u64 size; u64 ch_s_size; int ch_l_map; u64 dimm_s_size[NUM_CHANNELS]; @@ -134,6 +155,9 @@ struct igen6_imc { static struct igen6_pvt { struct igen6_imc imc[NUM_IMC]; + u64 ms_hash; + u64 ms_s_size; + int ms_l_map; } *igen6_pvt; /* The top of low usable DRAM */ @@ -183,6 +207,21 @@ static struct work_struct ecclog_work; #define DID_EHL_SKU14 0x4534 #define DID_EHL_SKU15 0x4536 +/* Compute die IDs for ICL-NNPI with IBECC */ +#define DID_ICL_SKU8 0x4581 +#define DID_ICL_SKU10 0x4585 +#define DID_ICL_SKU11 0x4589 +#define DID_ICL_SKU12 0x458d + +/* Compute die IDs for Tiger Lake with IBECC */ +#define DID_TGL_SKU 0x9a14 + +/* Compute die IDs for Alder Lake with IBECC */ +#define DID_ADL_SKU1 0x4601 +#define DID_ADL_SKU2 0x4602 +#define DID_ADL_SKU3 0x4621 +#define DID_ADL_SKU4 0x4641 + static bool ehl_ibecc_available(struct pci_dev *pdev) { u32 v; @@ -193,12 +232,12 @@ static bool ehl_ibecc_available(struct pci_dev *pdev) return !!(CAPID_C_IBECC & v); } -static u64 ehl_err_addr_to_sys_addr(u64 eaddr) +static u64 ehl_err_addr_to_sys_addr(u64 eaddr, int mc) { return eaddr; } -static u64 ehl_err_addr_to_imc_addr(u64 eaddr) +static u64 ehl_err_addr_to_imc_addr(u64 eaddr, int mc) { if (eaddr < igen6_tolud) return eaddr; @@ -212,12 +251,156 @@ static u64 ehl_err_addr_to_imc_addr(u64 eaddr) return eaddr; } +static bool icl_ibecc_available(struct pci_dev *pdev) +{ + u32 v; + + if (pci_read_config_dword(pdev, CAPID_C_OFFSET, &v)) + return false; + + return !(CAPID_C_IBECC & v) && + (boot_cpu_data.x86_stepping >= 1); +} + +static bool tgl_ibecc_available(struct pci_dev *pdev) +{ + u32 v; + + if (pci_read_config_dword(pdev, CAPID_E_OFFSET, &v)) + return false; + + return !(CAPID_E_IBECC & v); +} + +static u64 mem_addr_to_sys_addr(u64 maddr) +{ + if (maddr < igen6_tolud) + return maddr; + + if (igen6_tom <= _4GB) + return maddr - igen6_tolud + _4GB; + + if (maddr < _4GB) + return maddr - igen6_tolud + igen6_tom; + + return maddr; +} + +static u64 mem_slice_hash(u64 addr, u64 mask, u64 hash_init, int intlv_bit) +{ + u64 hash_addr = addr & mask, hash = hash_init; + u64 intlv = (addr >> intlv_bit) & 1; + int i; + + for (i = 6; i < 20; i++) + hash ^= (hash_addr >> i) & 1; + + return hash ^ intlv; +} + +static u64 tgl_err_addr_to_mem_addr(u64 eaddr, int mc) +{ + u64 maddr, hash, mask, ms_s_size; + int intlv_bit; + u32 ms_hash; + + ms_s_size = igen6_pvt->ms_s_size; + if (eaddr >= ms_s_size) + return eaddr + ms_s_size; + + ms_hash = igen6_pvt->ms_hash; + + mask = MEM_SLICE_HASH_MASK(ms_hash); + intlv_bit = MEM_SLICE_HASH_LSB_MASK_BIT(ms_hash) + 6; + + maddr = GET_BITFIELD(eaddr, intlv_bit, 63) << (intlv_bit + 1) | + GET_BITFIELD(eaddr, 0, intlv_bit - 1); + + hash = mem_slice_hash(maddr, mask, mc, intlv_bit); + + return maddr | (hash << intlv_bit); +} + +static u64 tgl_err_addr_to_sys_addr(u64 eaddr, int mc) +{ + u64 maddr = tgl_err_addr_to_mem_addr(eaddr, mc); + + return mem_addr_to_sys_addr(maddr); +} + +static u64 tgl_err_addr_to_imc_addr(u64 eaddr, int mc) +{ + return eaddr; +} + +static u64 adl_err_addr_to_sys_addr(u64 eaddr, int mc) +{ + return mem_addr_to_sys_addr(eaddr); +} + +static u64 adl_err_addr_to_imc_addr(u64 eaddr, int mc) +{ + u64 imc_addr, ms_s_size = igen6_pvt->ms_s_size; + struct igen6_imc *imc = &igen6_pvt->imc[mc]; + int intlv_bit; + u32 mc_hash; + + if (eaddr >= 2 * ms_s_size) + return eaddr - ms_s_size; + + mc_hash = readl(imc->window + MAD_MC_HASH_OFFSET); + + intlv_bit = MAC_MC_HASH_LSB(mc_hash) + 6; + + imc_addr = GET_BITFIELD(eaddr, intlv_bit + 1, 63) << intlv_bit | + GET_BITFIELD(eaddr, 0, intlv_bit - 1); + + return imc_addr; +} + static struct res_config ehl_cfg = { - .num_imc = 1, - .ibecc_base = 0xdc00, - .ibecc_available = ehl_ibecc_available, - .err_addr_to_sys_addr = ehl_err_addr_to_sys_addr, - .err_addr_to_imc_addr = ehl_err_addr_to_imc_addr, + .num_imc = 1, + .imc_base = 0x5000, + .ibecc_base = 0xdc00, + .ibecc_available = ehl_ibecc_available, + .ibecc_error_log_offset = 0x170, + .err_addr_to_sys_addr = ehl_err_addr_to_sys_addr, + .err_addr_to_imc_addr = ehl_err_addr_to_imc_addr, +}; + +static struct res_config icl_cfg = { + .num_imc = 1, + .imc_base = 0x5000, + .ibecc_base = 0xd800, + .ibecc_error_log_offset = 0x170, + .ibecc_available = icl_ibecc_available, + .err_addr_to_sys_addr = ehl_err_addr_to_sys_addr, + .err_addr_to_imc_addr = ehl_err_addr_to_imc_addr, +}; + +static struct res_config tgl_cfg = { + .machine_check = true, + .num_imc = 2, + .imc_base = 0x5000, + .cmf_base = 0x11000, + .cmf_size = 0x800, + .ms_hash_offset = 0xac, + .ibecc_base = 0xd400, + .ibecc_error_log_offset = 0x170, + .ibecc_available = tgl_ibecc_available, + .err_addr_to_sys_addr = tgl_err_addr_to_sys_addr, + .err_addr_to_imc_addr = tgl_err_addr_to_imc_addr, +}; + +static struct res_config adl_cfg = { + .machine_check = true, + .num_imc = 2, + .imc_base = 0xd800, + .ibecc_base = 0xd400, + .ibecc_error_log_offset = 0x68, + .ibecc_available = tgl_ibecc_available, + .err_addr_to_sys_addr = adl_err_addr_to_sys_addr, + .err_addr_to_imc_addr = adl_err_addr_to_imc_addr, }; static const struct pci_device_id igen6_pci_tbl[] = { @@ -232,6 +415,15 @@ static const struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_EHL_SKU13), (kernel_ulong_t)&ehl_cfg }, { PCI_VDEVICE(INTEL, DID_EHL_SKU14), (kernel_ulong_t)&ehl_cfg }, { PCI_VDEVICE(INTEL, DID_EHL_SKU15), (kernel_ulong_t)&ehl_cfg }, + { PCI_VDEVICE(INTEL, DID_ICL_SKU8), (kernel_ulong_t)&icl_cfg }, + { PCI_VDEVICE(INTEL, DID_ICL_SKU10), (kernel_ulong_t)&icl_cfg }, + { PCI_VDEVICE(INTEL, DID_ICL_SKU11), (kernel_ulong_t)&icl_cfg }, + { PCI_VDEVICE(INTEL, DID_ICL_SKU12), (kernel_ulong_t)&icl_cfg }, + { PCI_VDEVICE(INTEL, DID_TGL_SKU), (kernel_ulong_t)&tgl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_SKU1), (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_SKU2), (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_SKU3), (kernel_ulong_t)&adl_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_SKU4), (kernel_ulong_t)&adl_cfg }, { }, }; MODULE_DEVICE_TABLE(pci, igen6_pci_tbl); @@ -490,8 +682,8 @@ static void ecclog_work_cb(struct work_struct *work) eaddr = ECC_ERROR_LOG_ADDR(node->ecclog) << ECC_ERROR_LOG_ADDR_SHIFT; res.mc = node->mc; - res.sys_addr = res_cfg->err_addr_to_sys_addr(eaddr); - res.imc_addr = res_cfg->err_addr_to_imc_addr(eaddr); + res.sys_addr = res_cfg->err_addr_to_sys_addr(eaddr, res.mc); + res.imc_addr = res_cfg->err_addr_to_imc_addr(eaddr, res.mc); mci = igen6_pvt->imc[res.mc].mci; @@ -540,6 +732,57 @@ static int ecclog_nmi_handler(unsigned int cmd, struct pt_regs *regs) return NMI_HANDLED; } +static int ecclog_mce_handler(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *mce = (struct mce *)data; + char *type; + + if (mce->kflags & MCE_HANDLED_CEC) + return NOTIFY_DONE; + + /* + * Ignore unless this is a memory related error. + * We don't check the bit MCI_STATUS_ADDRV of MCi_STATUS here, + * since this bit isn't set on some CPU (e.g., Tiger Lake UP3). + */ + if ((mce->status & 0xefff) >> 7 != 1) + return NOTIFY_DONE; + + if (mce->mcgstatus & MCG_STATUS_MCIP) + type = "Exception"; + else + type = "Event"; + + edac_dbg(0, "CPU %d: Machine Check %s: 0x%llx Bank %d: 0x%llx\n", + mce->extcpu, type, mce->mcgstatus, + mce->bank, mce->status); + edac_dbg(0, "TSC 0x%llx\n", mce->tsc); + edac_dbg(0, "ADDR 0x%llx\n", mce->addr); + edac_dbg(0, "MISC 0x%llx\n", mce->misc); + edac_dbg(0, "PROCESSOR %u:0x%x TIME %llu SOCKET %u APIC 0x%x\n", + mce->cpuvendor, mce->cpuid, mce->time, + mce->socketid, mce->apicid); + /* + * We just use the Machine Check for the memory error notification. + * Each memory controller is associated with an IBECC instance. + * Directly read and clear the error information(error address and + * error type) on all the IBECC instances so that we know on which + * memory controller the memory error(s) occurred. + */ + if (!ecclog_handler()) + return NOTIFY_DONE; + + mce->kflags |= MCE_HANDLED_EDAC; + + return NOTIFY_DONE; +} + +static struct notifier_block ecclog_mce_dec = { + .notifier_call = ecclog_mce_handler, + .priority = MCE_PRIO_EDAC, +}; + static bool igen6_check_ecc(struct igen6_imc *imc) { u32 activate = readl(imc->window + IBECC_ACTIVATE_OFFSET); @@ -573,6 +816,8 @@ static int igen6_get_dimm_config(struct mem_ctl_info *mci) imc->dimm_l_size[i] = MAD_DIMM_CH_DIMM_L_SIZE(mad_dimm); imc->dimm_s_size[i] = MAD_DIMM_CH_DIMM_S_SIZE(mad_dimm); imc->dimm_l_map[i] = MAD_INTRA_CH_DIMM_L_MAP(mad_intra); + imc->size += imc->dimm_s_size[i]; + imc->size += imc->dimm_l_size[i]; ndimms = 0; for (j = 0; j < NUM_DIMMS; j++) { @@ -608,6 +853,8 @@ static int igen6_get_dimm_config(struct mem_ctl_info *mci) } } + edac_dbg(0, "MC %d, total size %llu MiB\n", mc, imc->size >> 20); + return 0; } @@ -857,6 +1104,80 @@ static void igen6_unregister_mcis(void) } } +static int igen6_mem_slice_setup(u64 mchbar) +{ + struct igen6_imc *imc = &igen6_pvt->imc[0]; + u64 base = mchbar + res_cfg->cmf_base; + u32 offset = res_cfg->ms_hash_offset; + u32 size = res_cfg->cmf_size; + u64 ms_s_size, ms_hash; + void __iomem *cmf; + int ms_l_map; + + edac_dbg(2, "\n"); + + if (imc[0].size < imc[1].size) { + ms_s_size = imc[0].size; + ms_l_map = 1; + } else { + ms_s_size = imc[1].size; + ms_l_map = 0; + } + + igen6_pvt->ms_s_size = ms_s_size; + igen6_pvt->ms_l_map = ms_l_map; + + edac_dbg(0, "ms_s_size: %llu MiB, ms_l_map %d\n", + ms_s_size >> 20, ms_l_map); + + if (!size) + return 0; + + cmf = ioremap(base, size); + if (!cmf) { + igen6_printk(KERN_ERR, "Failed to ioremap cmf 0x%llx\n", base); + return -ENODEV; + } + + ms_hash = readq(cmf + offset); + igen6_pvt->ms_hash = ms_hash; + + edac_dbg(0, "MEM_SLICE_HASH: 0x%llx\n", ms_hash); + + iounmap(cmf); + + return 0; +} + +static int register_err_handler(void) +{ + int rc; + + if (res_cfg->machine_check) { + mce_register_decode_chain(&ecclog_mce_dec); + return 0; + } + + rc = register_nmi_handler(NMI_SERR, ecclog_nmi_handler, + 0, IGEN6_NMI_NAME); + if (rc) { + igen6_printk(KERN_ERR, "Failed to register NMI handler\n"); + return rc; + } + + return 0; +} + +static void unregister_err_handler(void) +{ + if (res_cfg->machine_check) { + mce_unregister_decode_chain(&ecclog_mce_dec); + return; + } + + unregister_nmi_handler(NMI_SERR, IGEN6_NMI_NAME); +} + static int igen6_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { u64 mchbar; @@ -880,6 +1201,12 @@ static int igen6_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto fail2; } + if (res_cfg->num_imc > 1) { + rc = igen6_mem_slice_setup(mchbar); + if (rc) + goto fail2; + } + ecclog_pool = ecclog_gen_pool_create(); if (!ecclog_pool) { rc = -ENOMEM; @@ -892,12 +1219,9 @@ static int igen6_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Check if any pending errors before registering the NMI handler */ ecclog_handler(); - rc = register_nmi_handler(NMI_SERR, ecclog_nmi_handler, - 0, IGEN6_NMI_NAME); - if (rc) { - igen6_printk(KERN_ERR, "Failed to register NMI handler\n"); + rc = register_err_handler(); + if (rc) goto fail3; - } /* Enable error reporting */ rc = errcmd_enable_error_reporting(true); @@ -925,7 +1249,7 @@ static void igen6_remove(struct pci_dev *pdev) igen6_debug_teardown(); errcmd_enable_error_reporting(false); - unregister_nmi_handler(NMI_SERR, IGEN6_NMI_NAME); + unregister_err_handler(); irq_work_sync(&ecclog_irq_work); flush_work(&ecclog_work); gen_pool_destroy(ecclog_pool); diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c index 928f63a374c7..c94ca1f790c4 100644 --- a/drivers/edac/pnd2_edac.c +++ b/drivers/edac/pnd2_edac.c @@ -1554,6 +1554,9 @@ static int __init pnd2_init(void) if (owner && strncmp(owner, EDAC_MOD_STR, sizeof(EDAC_MOD_STR))) return -EBUSY; + if (cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + return -ENODEV; + id = x86_match_cpu(pnd2_cpuids); if (!id) return -ENODEV; diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 93daa4297f2e..4c626fcd4dcb 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -3510,6 +3510,9 @@ static int __init sbridge_init(void) if (owner && strncmp(owner, EDAC_MOD_STR, sizeof(EDAC_MOD_STR))) return -EBUSY; + if (cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + return -ENODEV; + id = x86_match_cpu(sbridge_cpuids); if (!id) return -ENODEV; diff --git a/drivers/edac/skx_base.c b/drivers/edac/skx_base.c index 6a4f0b27c654..4dbd46575bfb 100644 --- a/drivers/edac/skx_base.c +++ b/drivers/edac/skx_base.c @@ -656,6 +656,9 @@ static int __init skx_init(void) if (owner && strncmp(owner, EDAC_MOD_STR, sizeof(EDAC_MOD_STR))) return -EBUSY; + if (cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) + return -ENODEV; + id = x86_match_cpu(skx_cpuids); if (!id) return -ENODEV; diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index 81c3e2ec6f56..5e83f59bef8a 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -23,10 +23,13 @@ #include "skx_common.h" static const char * const component_names[] = { - [INDEX_SOCKET] = "ProcessorSocketId", - [INDEX_MEMCTRL] = "MemoryControllerId", - [INDEX_CHANNEL] = "ChannelId", - [INDEX_DIMM] = "DimmSlotId", + [INDEX_SOCKET] = "ProcessorSocketId", + [INDEX_MEMCTRL] = "MemoryControllerId", + [INDEX_CHANNEL] = "ChannelId", + [INDEX_DIMM] = "DimmSlotId", + [INDEX_NM_MEMCTRL] = "NmMemoryControllerId", + [INDEX_NM_CHANNEL] = "NmChannelId", + [INDEX_NM_DIMM] = "NmDimmSlotId", }; static int component_indices[ARRAY_SIZE(component_names)]; @@ -34,12 +37,14 @@ static int adxl_component_count; static const char * const *adxl_component_names; static u64 *adxl_values; static char *adxl_msg; +static unsigned long adxl_nm_bitmap; static char skx_msg[MSG_SIZE]; static skx_decode_f skx_decode; static skx_show_retry_log_f skx_show_retry_rd_err_log; static u64 skx_tolm, skx_tohm; static LIST_HEAD(dev_edac_list); +static bool skx_mem_cfg_2lm; int __init skx_adxl_get(void) { @@ -56,14 +61,25 @@ int __init skx_adxl_get(void) for (j = 0; names[j]; j++) { if (!strcmp(component_names[i], names[j])) { component_indices[i] = j; + + if (i >= INDEX_NM_FIRST) + adxl_nm_bitmap |= 1 << i; + break; } } - if (!names[j]) + if (!names[j] && i < INDEX_NM_FIRST) goto err; } + if (skx_mem_cfg_2lm) { + if (!adxl_nm_bitmap) + skx_printk(KERN_NOTICE, "Not enough ADXL components for 2-level memory.\n"); + else + edac_dbg(2, "adxl_nm_bitmap: 0x%lx\n", adxl_nm_bitmap); + } + adxl_component_names = names; while (*names++) adxl_component_count++; @@ -99,7 +115,7 @@ void __exit skx_adxl_put(void) kfree(adxl_msg); } -static bool skx_adxl_decode(struct decoded_addr *res) +static bool skx_adxl_decode(struct decoded_addr *res, bool error_in_1st_level_mem) { struct skx_dev *d; int i, len = 0; @@ -116,11 +132,20 @@ static bool skx_adxl_decode(struct decoded_addr *res) } res->socket = (int)adxl_values[component_indices[INDEX_SOCKET]]; - res->imc = (int)adxl_values[component_indices[INDEX_MEMCTRL]]; - res->channel = (int)adxl_values[component_indices[INDEX_CHANNEL]]; - res->dimm = (int)adxl_values[component_indices[INDEX_DIMM]]; + if (error_in_1st_level_mem) { + res->imc = (adxl_nm_bitmap & BIT_NM_MEMCTRL) ? + (int)adxl_values[component_indices[INDEX_NM_MEMCTRL]] : -1; + res->channel = (adxl_nm_bitmap & BIT_NM_CHANNEL) ? + (int)adxl_values[component_indices[INDEX_NM_CHANNEL]] : -1; + res->dimm = (adxl_nm_bitmap & BIT_NM_DIMM) ? + (int)adxl_values[component_indices[INDEX_NM_DIMM]] : -1; + } else { + res->imc = (int)adxl_values[component_indices[INDEX_MEMCTRL]]; + res->channel = (int)adxl_values[component_indices[INDEX_CHANNEL]]; + res->dimm = (int)adxl_values[component_indices[INDEX_DIMM]]; + } - if (res->imc > NUM_IMC - 1) { + if (res->imc > NUM_IMC - 1 || res->imc < 0) { skx_printk(KERN_ERR, "Bad imc %d\n", res->imc); return false; } @@ -151,6 +176,11 @@ static bool skx_adxl_decode(struct decoded_addr *res) return true; } +void skx_set_mem_cfg(bool mem_cfg_2lm) +{ + skx_mem_cfg_2lm = mem_cfg_2lm; +} + void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log) { skx_decode = decode; @@ -313,9 +343,9 @@ int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm, ranks = numrank(mtr); rows = numrow(mtr); - cols = numcol(mtr); + cols = imc->hbm_mc ? 6 : numcol(mtr); - if (cfg->support_ddr5 && (amap & 0x8)) { + if (cfg->support_ddr5 && ((amap & 0x8) || imc->hbm_mc)) { banks = 32; mtype = MEM_DDR5; } else { @@ -344,8 +374,13 @@ int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm, dimm->dtype = get_width(mtr); dimm->mtype = mtype; dimm->edac_mode = EDAC_SECDED; /* likely better than this */ - snprintf(dimm->label, sizeof(dimm->label), "CPU_SrcID#%u_MC#%u_Chan#%u_DIMM#%u", - imc->src_id, imc->lmc, chan, dimmno); + + if (imc->hbm_mc) + snprintf(dimm->label, sizeof(dimm->label), "CPU_SrcID#%u_HBMC#%u_Chan#%u", + imc->src_id, imc->lmc, chan); + else + snprintf(dimm->label, sizeof(dimm->label), "CPU_SrcID#%u_MC#%u_Chan#%u_DIMM#%u", + imc->src_id, imc->lmc, chan, dimmno); return 1; } @@ -578,6 +613,21 @@ static void skx_mce_output_error(struct mem_ctl_info *mci, optype, skx_msg); } +static bool skx_error_in_1st_level_mem(const struct mce *m) +{ + u32 errcode; + + if (!skx_mem_cfg_2lm) + return false; + + errcode = GET_BITFIELD(m->status, 0, 15); + + if ((errcode & 0xef80) != 0x280) + return false; + + return true; +} + int skx_mce_check_error(struct notifier_block *nb, unsigned long val, void *data) { @@ -597,7 +647,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val, res.addr = mce->addr; if (adxl_component_count) { - if (!skx_adxl_decode(&res)) + if (!skx_adxl_decode(&res, skx_error_in_1st_level_mem(mce))) return NOTIFY_DONE; } else if (!skx_decode || !skx_decode(&res)) { return NOTIFY_DONE; @@ -658,6 +708,8 @@ void skx_remove(void) } if (d->util_all) pci_dev_put(d->util_all); + if (d->pcu_cr3) + pci_dev_put(d->pcu_cr3); if (d->sad_all) pci_dev_put(d->sad_all); if (d->uracu) diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h index bf56bebff138..01f67e731766 100644 --- a/drivers/edac/skx_common.h +++ b/drivers/edac/skx_common.h @@ -9,6 +9,8 @@ #ifndef _SKX_COMM_EDAC_H #define _SKX_COMM_EDAC_H +#include + #define MSG_SIZE 1024 /* @@ -30,9 +32,17 @@ #define SKX_NUM_CHANNELS 3 /* Channels per memory controller */ #define SKX_NUM_DIMMS 2 /* Max DIMMS per channel */ -#define I10NM_NUM_IMC 4 -#define I10NM_NUM_CHANNELS 2 -#define I10NM_NUM_DIMMS 2 +#define I10NM_NUM_DDR_IMC 4 +#define I10NM_NUM_DDR_CHANNELS 2 +#define I10NM_NUM_DDR_DIMMS 2 + +#define I10NM_NUM_HBM_IMC 16 +#define I10NM_NUM_HBM_CHANNELS 2 +#define I10NM_NUM_HBM_DIMMS 1 + +#define I10NM_NUM_IMC (I10NM_NUM_DDR_IMC + I10NM_NUM_HBM_IMC) +#define I10NM_NUM_CHANNELS MAX(I10NM_NUM_DDR_CHANNELS, I10NM_NUM_HBM_CHANNELS) +#define I10NM_NUM_DIMMS MAX(I10NM_NUM_DDR_DIMMS, I10NM_NUM_HBM_DIMMS) #define MAX(a, b) ((a) > (b) ? (a) : (b)) #define NUM_IMC MAX(SKX_NUM_IMC, I10NM_NUM_IMC) @@ -54,12 +64,16 @@ struct skx_dev { struct pci_dev *sad_all; struct pci_dev *util_all; struct pci_dev *uracu; /* for i10nm CPU */ + struct pci_dev *pcu_cr3; /* for HBM memory detection */ u32 mcroute; struct skx_imc { struct mem_ctl_info *mci; struct pci_dev *mdev; /* for i10nm CPU */ void __iomem *mbase; /* for i10nm CPU */ int chan_mmio_sz; /* for i10nm CPU */ + int num_channels; /* channels per memory controller */ + int num_dimms; /* dimms per channel */ + bool hbm_mc; u8 mc; /* system wide mc# */ u8 lmc; /* socket relative mc# */ u8 src_id, node_id; @@ -92,9 +106,17 @@ enum { INDEX_MEMCTRL, INDEX_CHANNEL, INDEX_DIMM, + INDEX_NM_FIRST, + INDEX_NM_MEMCTRL = INDEX_NM_FIRST, + INDEX_NM_CHANNEL, + INDEX_NM_DIMM, INDEX_MAX }; +#define BIT_NM_MEMCTRL BIT_ULL(INDEX_NM_MEMCTRL) +#define BIT_NM_CHANNEL BIT_ULL(INDEX_NM_CHANNEL) +#define BIT_NM_DIMM BIT_ULL(INDEX_NM_DIMM) + struct decoded_addr { struct skx_dev *dev; u64 addr; @@ -122,7 +144,12 @@ struct res_config { int busno_cfg_offset; /* Per DDR channel memory-mapped I/O size */ int ddr_chan_mmio_sz; + /* Per HBM channel memory-mapped I/O size */ + int hbm_chan_mmio_sz; bool support_ddr5; + /* SAD device number and function number */ + unsigned int sad_all_devfn; + int sad_all_offset; }; typedef int (*get_dimm_config_f)(struct mem_ctl_info *mci, @@ -133,6 +160,7 @@ typedef void (*skx_show_retry_log_f)(struct decoded_addr *res, char *msg, int le int __init skx_adxl_get(void); void __exit skx_adxl_put(void); void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log); +void skx_set_mem_cfg(bool mem_cfg_2lm); int skx_get_src_id(struct skx_dev *d, int off, u8 *id); int skx_get_node_id(struct skx_dev *d, u8 *id); diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c index 0eb5eb97fd74..f13674081cb6 100644 --- a/drivers/edac/thunderx_edac.c +++ b/drivers/edac/thunderx_edac.c @@ -1368,7 +1368,7 @@ static int thunderx_ocx_probe(struct pci_dev *pdev, name, 1, "CCPI", 1, 0, NULL, 0, idx); if (!edac_dev) { - dev_err(&pdev->dev, "Cannot allocate EDAC device: %d\n", ret); + dev_err(&pdev->dev, "Cannot allocate EDAC device\n"); return -ENOMEM; } ocx = edac_dev->pvt_info; @@ -1380,7 +1380,7 @@ static int thunderx_ocx_probe(struct pci_dev *pdev, ocx->regs = pcim_iomap_table(pdev)[0]; if (!ocx->regs) { - dev_err(&pdev->dev, "Cannot map PCI resources: %d\n", ret); + dev_err(&pdev->dev, "Cannot map PCI resources\n"); ret = -ENODEV; goto err_free; } diff --git a/drivers/edac/ti_edac.c b/drivers/edac/ti_edac.c index e7eae20f83d1..169f96e51c29 100644 --- a/drivers/edac/ti_edac.c +++ b/drivers/edac/ti_edac.c @@ -197,6 +197,7 @@ static const struct of_device_id ti_edac_of_match[] = { { .compatible = "ti,emif-dra7xx", .data = (void *)EMIF_TYPE_DRA7 }, {}, }; +MODULE_DEVICE_TABLE(of, ti_edac_of_match); static int _emif_get_id(struct device_node *node) { diff --git a/drivers/extcon/extcon-max14577.c b/drivers/extcon/extcon-max14577.c index ace523924e58..5476f48ed74b 100644 --- a/drivers/extcon/extcon-max14577.c +++ b/drivers/extcon/extcon-max14577.c @@ -6,6 +6,7 @@ // Chanwoo Choi // Krzysztof Kozlowski +#include #include #include #include @@ -673,7 +674,10 @@ static int max14577_muic_probe(struct platform_device *pdev) platform_set_drvdata(pdev, info); mutex_init(&info->mutex); - INIT_WORK(&info->irq_work, max14577_muic_irq_work); + ret = devm_work_autocancel(&pdev->dev, &info->irq_work, + max14577_muic_irq_work); + if (ret) + return ret; switch (max14577->dev_type) { case MAXIM_DEVICE_TYPE_MAX77836: @@ -766,15 +770,6 @@ static int max14577_muic_probe(struct platform_device *pdev) return ret; } -static int max14577_muic_remove(struct platform_device *pdev) -{ - struct max14577_muic_info *info = platform_get_drvdata(pdev); - - cancel_work_sync(&info->irq_work); - - return 0; -} - static const struct platform_device_id max14577_muic_id[] = { { "max14577-muic", MAXIM_DEVICE_TYPE_MAX14577, }, { "max77836-muic", MAXIM_DEVICE_TYPE_MAX77836, }, @@ -797,7 +792,6 @@ static struct platform_driver max14577_muic_driver = { .of_match_table = of_max14577_muic_dt_match, }, .probe = max14577_muic_probe, - .remove = max14577_muic_remove, .id_table = max14577_muic_id, }; diff --git a/drivers/extcon/extcon-max77693.c b/drivers/extcon/extcon-max77693.c index 92af97e00828..1f1d9ab0c5c7 100644 --- a/drivers/extcon/extcon-max77693.c +++ b/drivers/extcon/extcon-max77693.c @@ -5,6 +5,7 @@ // Copyright (C) 2012 Samsung Electrnoics // Chanwoo Choi +#include #include #include #include @@ -1127,7 +1128,10 @@ static int max77693_muic_probe(struct platform_device *pdev) platform_set_drvdata(pdev, info); mutex_init(&info->mutex); - INIT_WORK(&info->irq_work, max77693_muic_irq_work); + ret = devm_work_autocancel(&pdev->dev, &info->irq_work, + max77693_muic_irq_work); + if (ret) + return ret; /* Support irq domain for MAX77693 MUIC device */ for (i = 0; i < ARRAY_SIZE(muic_irqs); i++) { @@ -1254,22 +1258,11 @@ static int max77693_muic_probe(struct platform_device *pdev) return ret; } -static int max77693_muic_remove(struct platform_device *pdev) -{ - struct max77693_muic_info *info = platform_get_drvdata(pdev); - - cancel_work_sync(&info->irq_work); - input_unregister_device(info->dock); - - return 0; -} - static struct platform_driver max77693_muic_driver = { .driver = { .name = DEV_NAME, }, .probe = max77693_muic_probe, - .remove = max77693_muic_remove, }; module_platform_driver(max77693_muic_driver); diff --git a/drivers/extcon/extcon-max8997.c b/drivers/extcon/extcon-max8997.c index e1408075ef7d..bbc592823570 100644 --- a/drivers/extcon/extcon-max8997.c +++ b/drivers/extcon/extcon-max8997.c @@ -5,6 +5,7 @@ // Copyright (C) 2012 Samsung Electronics // Donggeun Kim +#include #include #include #include @@ -650,27 +651,30 @@ static int max8997_muic_probe(struct platform_device *pdev) mutex_init(&info->mutex); INIT_WORK(&info->irq_work, max8997_muic_irq_work); + ret = devm_work_autocancel(&pdev->dev, &info->irq_work, + max8997_muic_irq_work); + if (ret) + return ret; for (i = 0; i < ARRAY_SIZE(muic_irqs); i++) { struct max8997_muic_irq *muic_irq = &muic_irqs[i]; unsigned int virq = 0; virq = irq_create_mapping(max8997->irq_domain, muic_irq->irq); - if (!virq) { - ret = -EINVAL; - goto err_irq; - } + if (!virq) + return -EINVAL; + muic_irq->virq = virq; - ret = request_threaded_irq(virq, NULL, - max8997_muic_irq_handler, - IRQF_NO_SUSPEND, - muic_irq->name, info); + ret = devm_request_threaded_irq(&pdev->dev, virq, NULL, + max8997_muic_irq_handler, + IRQF_NO_SUSPEND, + muic_irq->name, info); if (ret) { dev_err(&pdev->dev, "failed: irq request (IRQ: %d, error :%d)\n", muic_irq->irq, ret); - goto err_irq; + return ret; } } @@ -678,14 +682,13 @@ static int max8997_muic_probe(struct platform_device *pdev) info->edev = devm_extcon_dev_allocate(&pdev->dev, max8997_extcon_cable); if (IS_ERR(info->edev)) { dev_err(&pdev->dev, "failed to allocate memory for extcon\n"); - ret = PTR_ERR(info->edev); - goto err_irq; + return PTR_ERR(info->edev); } ret = devm_extcon_dev_register(&pdev->dev, info->edev); if (ret) { dev_err(&pdev->dev, "failed to register extcon device\n"); - goto err_irq; + return ret; } if (pdata && pdata->muic_pdata) { @@ -756,23 +759,6 @@ static int max8997_muic_probe(struct platform_device *pdev) delay_jiffies); return 0; - -err_irq: - while (--i >= 0) - free_irq(muic_irqs[i].virq, info); - return ret; -} - -static int max8997_muic_remove(struct platform_device *pdev) -{ - struct max8997_muic_info *info = platform_get_drvdata(pdev); - int i; - - for (i = 0; i < ARRAY_SIZE(muic_irqs); i++) - free_irq(muic_irqs[i].virq, info); - cancel_work_sync(&info->irq_work); - - return 0; } static struct platform_driver max8997_muic_driver = { @@ -780,7 +766,6 @@ static struct platform_driver max8997_muic_driver = { .name = DEV_NAME, }, .probe = max8997_muic_probe, - .remove = max8997_muic_remove, }; module_platform_driver(max8997_muic_driver); diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c index 0078260fbabe..172c751a4f6c 100644 --- a/drivers/firmware/qemu_fw_cfg.c +++ b/drivers/firmware/qemu_fw_cfg.c @@ -299,15 +299,13 @@ static int fw_cfg_do_platform_probe(struct platform_device *pdev) return 0; } -static ssize_t fw_cfg_showrev(struct kobject *k, struct attribute *a, char *buf) +static ssize_t fw_cfg_showrev(struct kobject *k, struct kobj_attribute *a, + char *buf) { return sprintf(buf, "%u\n", fw_cfg_rev); } -static const struct { - struct attribute attr; - ssize_t (*show)(struct kobject *k, struct attribute *a, char *buf); -} fw_cfg_rev_attr = { +static const struct kobj_attribute fw_cfg_rev_attr = { .attr = { .name = "rev", .mode = S_IRUSR }, .show = fw_cfg_showrev, }; diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 3c69b785cb79..63b84ba161dc 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -1367,7 +1367,7 @@ config GPIO_TPS65912 config GPIO_TPS68470 bool "TPS68470 GPIO" - depends on MFD_TPS68470 + depends on INTEL_SKL_INT3472 help Select this option to enable GPIO driver for the TPS68470 chip family. diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c index 2ba225720086..5a909f3c79e8 100644 --- a/drivers/gpio/gpio-crystalcove.c +++ b/drivers/gpio/gpio-crystalcove.c @@ -339,8 +339,6 @@ static int crystalcove_gpio_probe(struct platform_device *pdev) if (!cg) return -ENOMEM; - platform_set_drvdata(pdev, cg); - mutex_init(&cg->buslock); cg->chip.label = KBUILD_MODNAME; cg->chip.direction_input = crystalcove_gpio_dir_in; @@ -372,13 +370,7 @@ static int crystalcove_gpio_probe(struct platform_device *pdev) return retval; } - retval = devm_gpiochip_add_data(&pdev->dev, &cg->chip, cg); - if (retval) { - dev_warn(&pdev->dev, "add gpio chip error: %d\n", retval); - return retval; - } - - return 0; + return devm_gpiochip_add_data(&pdev->dev, &cg->chip, cg); } static struct platform_driver crystalcove_gpio_driver = { diff --git a/drivers/gpio/gpio-wcove.c b/drivers/gpio/gpio-wcove.c index a19eeef6cf1e..16a0fae1e32e 100644 --- a/drivers/gpio/gpio-wcove.c +++ b/drivers/gpio/gpio-wcove.c @@ -99,19 +99,14 @@ struct wcove_gpio { bool set_irq_mask; }; -static inline int to_reg(int gpio, enum ctrl_register reg_type) +static inline int to_reg(int gpio, enum ctrl_register type) { - unsigned int reg; + unsigned int reg = type == CTRL_IN ? GPIO_IN_CTRL_BASE : GPIO_OUT_CTRL_BASE; if (gpio >= WCOVE_GPIO_NUM) return -EOPNOTSUPP; - if (reg_type == CTRL_IN) - reg = GPIO_IN_CTRL_BASE + gpio; - else - reg = GPIO_OUT_CTRL_BASE + gpio; - - return reg; + return reg + gpio; } static inline int to_ireg(int gpio, enum ctrl_register type, unsigned int *mask) @@ -129,7 +124,7 @@ static inline int to_ireg(int gpio, enum ctrl_register type, unsigned int *mask) return reg; } -static void wcove_update_irq_mask(struct wcove_gpio *wg, int gpio) +static void wcove_update_irq_mask(struct wcove_gpio *wg, irq_hw_number_t gpio) { unsigned int mask, reg = to_ireg(gpio, IRQ_MASK, &mask); @@ -139,13 +134,10 @@ static void wcove_update_irq_mask(struct wcove_gpio *wg, int gpio) regmap_clear_bits(wg->regmap, reg, mask); } -static void wcove_update_irq_ctrl(struct wcove_gpio *wg, int gpio) +static void wcove_update_irq_ctrl(struct wcove_gpio *wg, irq_hw_number_t gpio) { int reg = to_reg(gpio, CTRL_IN); - if (reg < 0) - return; - regmap_update_bits(wg->regmap, reg, CTLI_INTCNT_BE, wg->intcnt); } @@ -248,8 +240,9 @@ static int wcove_irq_type(struct irq_data *data, unsigned int type) { struct gpio_chip *chip = irq_data_get_irq_chip_data(data); struct wcove_gpio *wg = gpiochip_get_data(chip); + irq_hw_number_t gpio = irqd_to_hwirq(data); - if (data->hwirq >= WCOVE_GPIO_NUM) + if (gpio >= WCOVE_GPIO_NUM) return 0; switch (type) { @@ -286,7 +279,7 @@ static void wcove_bus_sync_unlock(struct irq_data *data) { struct gpio_chip *chip = irq_data_get_irq_chip_data(data); struct wcove_gpio *wg = gpiochip_get_data(chip); - int gpio = data->hwirq; + irq_hw_number_t gpio = irqd_to_hwirq(data); if (wg->update & UPDATE_IRQ_TYPE) wcove_update_irq_ctrl(wg, gpio); @@ -301,8 +294,9 @@ static void wcove_irq_unmask(struct irq_data *data) { struct gpio_chip *chip = irq_data_get_irq_chip_data(data); struct wcove_gpio *wg = gpiochip_get_data(chip); + irq_hw_number_t gpio = irqd_to_hwirq(data); - if (data->hwirq >= WCOVE_GPIO_NUM) + if (gpio >= WCOVE_GPIO_NUM) return; wg->set_irq_mask = false; @@ -313,8 +307,9 @@ static void wcove_irq_mask(struct irq_data *data) { struct gpio_chip *chip = irq_data_get_irq_chip_data(data); struct wcove_gpio *wg = gpiochip_get_data(chip); + irq_hw_number_t gpio = irqd_to_hwirq(data); - if (data->hwirq >= WCOVE_GPIO_NUM) + if (gpio >= WCOVE_GPIO_NUM) return; wg->set_irq_mask = true; @@ -369,8 +364,7 @@ static irqreturn_t wcove_gpio_irq_handler(int irq, void *data) return IRQ_HANDLED; } -static void wcove_gpio_dbg_show(struct seq_file *s, - struct gpio_chip *chip) +static void wcove_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) { unsigned int ctlo, ctli, irq_mask, irq_status; struct wcove_gpio *wg = gpiochip_get_data(chip); @@ -379,10 +373,15 @@ static void wcove_gpio_dbg_show(struct seq_file *s, for (gpio = 0; gpio < WCOVE_GPIO_NUM; gpio++) { ret += regmap_read(wg->regmap, to_reg(gpio, CTRL_OUT), &ctlo); ret += regmap_read(wg->regmap, to_reg(gpio, CTRL_IN), &ctli); + if (ret) { + dev_err(wg->dev, "Failed to read registers: CTRL out/in\n"); + break; + } + ret += regmap_read(wg->regmap, to_ireg(gpio, IRQ_MASK, &mask), &irq_mask); ret += regmap_read(wg->regmap, to_ireg(gpio, IRQ_STATUS, &mask), &irq_status); if (ret) { - pr_err("Failed to read registers: ctrl out/in or irq status/mask\n"); + dev_err(wg->dev, "Failed to read registers: IRQ status/mask\n"); break; } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 3ef22a3c104d..411525ac4cc4 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -128,6 +128,34 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin) return gpiochip_get_desc(chip, pin); } +/** + * acpi_get_and_request_gpiod - Translate ACPI GPIO pin to GPIO descriptor and + * hold a refcount to the GPIO device. + * @path: ACPI GPIO controller full path name, (e.g. "\\_SB.GPO1") + * @pin: ACPI GPIO pin number (0-based, controller-relative) + * @label: Label to pass to gpiod_request() + * + * This function is a simple pass-through to acpi_get_gpiod(), except that + * as it is intended for use outside of the GPIO layer (in a similar fashion to + * gpiod_get_index() for example) it also holds a reference to the GPIO device. + */ +struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label) +{ + struct gpio_desc *gpio; + int ret; + + gpio = acpi_get_gpiod(path, pin); + if (IS_ERR(gpio)) + return gpio; + + ret = gpiod_request(gpio, label); + if (ret) + return ERR_PTR(ret); + + return gpio; +} +EXPORT_SYMBOL_GPL(acpi_get_and_request_gpiod); + static irqreturn_t acpi_gpio_irq_handler(int irq, void *data) { struct acpi_gpio_event *event = data; @@ -168,6 +196,29 @@ bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, } EXPORT_SYMBOL_GPL(acpi_gpio_get_irq_resource); +/** + * acpi_gpio_get_io_resource - Fetch details of an ACPI resource if it is a GPIO + * I/O resource or return False if not. + * @ares: Pointer to the ACPI resource to fetch + * @agpio: Pointer to a &struct acpi_resource_gpio to store the output pointer + */ +bool acpi_gpio_get_io_resource(struct acpi_resource *ares, + struct acpi_resource_gpio **agpio) +{ + struct acpi_resource_gpio *gpio; + + if (ares->type != ACPI_RESOURCE_TYPE_GPIO) + return false; + + gpio = &ares->data.gpio; + if (gpio->connection_type != ACPI_RESOURCE_GPIO_TYPE_IO) + return false; + + *agpio = gpio; + return true; +} +EXPORT_SYMBOL_GPL(acpi_gpio_get_io_resource); + static void acpi_gpiochip_request_irq(struct acpi_gpio_chip *acpi_gpio, struct acpi_gpio_event *event) { @@ -1233,14 +1284,14 @@ static void acpi_gpiochip_scan_gpios(struct acpi_gpio_chip *achip) void acpi_gpiochip_add(struct gpio_chip *chip) { struct acpi_gpio_chip *acpi_gpio; - acpi_handle handle; + struct acpi_device *adev; acpi_status status; if (!chip || !chip->parent) return; - handle = ACPI_HANDLE(chip->parent); - if (!handle) + adev = ACPI_COMPANION(chip->parent); + if (!adev) return; acpi_gpio = kzalloc(sizeof(*acpi_gpio), GFP_KERNEL); @@ -1254,7 +1305,7 @@ void acpi_gpiochip_add(struct gpio_chip *chip) INIT_LIST_HEAD(&acpi_gpio->events); INIT_LIST_HEAD(&acpi_gpio->deferred_req_irqs_list_entry); - status = acpi_attach_data(handle, acpi_gpio_chip_dh, acpi_gpio); + status = acpi_attach_data(adev->handle, acpi_gpio_chip_dh, acpi_gpio); if (ACPI_FAILURE(status)) { dev_err(chip->parent, "Failed to attach ACPI GPIO chip\n"); kfree(acpi_gpio); @@ -1263,7 +1314,7 @@ void acpi_gpiochip_add(struct gpio_chip *chip) acpi_gpiochip_request_regions(acpi_gpio); acpi_gpiochip_scan_gpios(acpi_gpio); - acpi_walk_dep_device_list(handle); + acpi_dev_clear_dependencies(adev); } void acpi_gpiochip_remove(struct gpio_chip *chip) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index d5cbc51c5eaa..61c4fb1b87fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -709,8 +709,8 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) } mmap_read_lock(mm); - vma = find_vma(mm, start); - if (unlikely(!vma || start < vma->vm_start)) { + vma = vma_lookup(mm, start); + if (unlikely(!vma)) { r = -EFAULT; goto out_unlock; } diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index 5cf6df49c333..35c15ef1327d 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -871,7 +871,7 @@ static int __igt_mmap(struct drm_i915_private *i915, pr_debug("igt_mmap(%s, %d) @ %lx\n", obj->mm.region->name, type, addr); - area = find_vma(current->mm, addr); + area = vma_lookup(current->mm, addr); if (!area) { pr_err("%s: Did not create a vm_area_struct for the mmap\n", obj->mm.region->name); diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c index 3589d9945da1..efb849411d25 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c @@ -77,6 +77,7 @@ int amd_sfh_get_report(struct hid_device *hid, int report_id, int report_type) static void amd_sfh_work(struct work_struct *work) { struct amdtp_cl_data *cli_data = container_of(work, struct amdtp_cl_data, work.work); + struct amd_input_data *in_data = cli_data->in_data; struct request_list *req_node; u8 current_index, sensor_index; u8 report_id, node_type; @@ -101,13 +102,11 @@ static void amd_sfh_work(struct work_struct *work) pr_err("AMDSFH: Invalid report size\n"); } else if (node_type == HID_INPUT_REPORT) { - report_size = get_input_report(sensor_index, report_id, - cli_data->input_report[current_index], - cli_data->sensor_virt_addr[current_index]); + report_size = get_input_report(current_index, sensor_index, report_id, in_data); if (report_size) hid_input_report(cli_data->hid_sensor_hubs[current_index], cli_data->report_type[current_index], - cli_data->input_report[current_index], report_size, 0); + in_data->input_report[current_index], report_size, 0); else pr_err("AMDSFH: Invalid report size\n"); } @@ -119,21 +118,22 @@ static void amd_sfh_work(struct work_struct *work) static void amd_sfh_work_buffer(struct work_struct *work) { struct amdtp_cl_data *cli_data = container_of(work, struct amdtp_cl_data, work_buffer.work); + struct amd_input_data *in_data = cli_data->in_data; u8 report_size; int i; for (i = 0; i < cli_data->num_hid_devices; i++) { - report_size = get_input_report(cli_data->sensor_idx[i], cli_data->report_id[i], - cli_data->input_report[i], - cli_data->sensor_virt_addr[i]); + report_size = get_input_report(i, cli_data->sensor_idx[i], cli_data->report_id[i], + in_data); hid_input_report(cli_data->hid_sensor_hubs[i], HID_INPUT_REPORT, - cli_data->input_report[i], report_size, 0); + in_data->input_report[i], report_size, 0); } schedule_delayed_work(&cli_data->work_buffer, msecs_to_jiffies(AMD_SFH_IDLE_LOOP)); } int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) { + struct amd_input_data *in_data = &privdata->in_data; struct amdtp_cl_data *cl_data = privdata->cl_data; struct amd_mp2_sensor_info info; struct device *dev; @@ -143,18 +143,16 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) int rc, i; dev = &privdata->pdev->dev; - cl_data = devm_kzalloc(dev, sizeof(*cl_data), GFP_KERNEL); - if (!cl_data) - return -ENOMEM; cl_data->num_hid_devices = amd_mp2_get_sensor_num(privdata, &cl_data->sensor_idx[0]); INIT_DELAYED_WORK(&cl_data->work, amd_sfh_work); INIT_DELAYED_WORK(&cl_data->work_buffer, amd_sfh_work_buffer); INIT_LIST_HEAD(&req_list.list); + cl_data->in_data = in_data; for (i = 0; i < cl_data->num_hid_devices; i++) { - cl_data->sensor_virt_addr[i] = dma_alloc_coherent(dev, sizeof(int) * 8, + in_data->sensor_virt_addr[i] = dma_alloc_coherent(dev, sizeof(int) * 8, &cl_data->sensor_dma_addr[i], GFP_KERNEL); cl_data->sensor_sts[i] = 0; @@ -181,8 +179,8 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) rc = -ENOMEM; goto cleanup; } - cl_data->input_report[i] = devm_kzalloc(dev, input_report_size, GFP_KERNEL); - if (!cl_data->input_report[i]) { + in_data->input_report[i] = devm_kzalloc(dev, input_report_size, GFP_KERNEL); + if (!in_data->input_report[i]) { rc = -ENOMEM; goto cleanup; } @@ -202,44 +200,43 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) rc = amdtp_hid_probe(cl_data->cur_hid_dev, cl_data); if (rc) return rc; - amd_start_sensor(privdata, info); + privdata->mp2_ops->start(privdata, info); cl_data->sensor_sts[i] = 1; } - privdata->cl_data = cl_data; schedule_delayed_work(&cl_data->work_buffer, msecs_to_jiffies(AMD_SFH_IDLE_LOOP)); return 0; cleanup: for (i = 0; i < cl_data->num_hid_devices; i++) { - if (cl_data->sensor_virt_addr[i]) { + if (in_data->sensor_virt_addr[i]) { dma_free_coherent(&privdata->pdev->dev, 8 * sizeof(int), - cl_data->sensor_virt_addr[i], + in_data->sensor_virt_addr[i], cl_data->sensor_dma_addr[i]); } devm_kfree(dev, cl_data->feature_report[i]); - devm_kfree(dev, cl_data->input_report[i]); + devm_kfree(dev, in_data->input_report[i]); devm_kfree(dev, cl_data->report_descr[i]); } - devm_kfree(dev, cl_data); return rc; } int amd_sfh_hid_client_deinit(struct amd_mp2_dev *privdata) { struct amdtp_cl_data *cl_data = privdata->cl_data; + struct amd_input_data *in_data = cl_data->in_data; int i; for (i = 0; i < cl_data->num_hid_devices; i++) - amd_stop_sensor(privdata, i); + privdata->mp2_ops->stop(privdata, i); cancel_delayed_work_sync(&cl_data->work); cancel_delayed_work_sync(&cl_data->work_buffer); amdtp_hid_remove(cl_data); for (i = 0; i < cl_data->num_hid_devices; i++) { - if (cl_data->sensor_virt_addr[i]) { + if (in_data->sensor_virt_addr[i]) { dma_free_coherent(&privdata->pdev->dev, 8 * sizeof(int), - cl_data->sensor_virt_addr[i], + in_data->sensor_virt_addr[i], cl_data->sensor_dma_addr[i]); } } diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_hid.h b/drivers/hid/amd-sfh-hid/amd_sfh_hid.h index d7eac1728e31..ae2ac9191ba7 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_hid.h +++ b/drivers/hid/amd-sfh-hid/amd_sfh_hid.h @@ -9,11 +9,16 @@ #ifndef AMDSFH_HID_H #define AMDSFH_HID_H -#define MAX_HID_DEVICES 4 +#define MAX_HID_DEVICES 5 #define BUS_AMD_AMDTP 0x20 #define AMD_SFH_HID_VENDOR 0x1022 #define AMD_SFH_HID_PRODUCT 0x0001 +struct amd_input_data { + u32 *sensor_virt_addr[MAX_HID_DEVICES]; + u8 *input_report[MAX_HID_DEVICES]; +}; + struct amdtp_cl_data { u8 init_done; u32 cur_hid_dev; @@ -26,7 +31,6 @@ struct amdtp_cl_data { u8 *hid_descr[MAX_HID_DEVICES]; int hid_descr_size[MAX_HID_DEVICES]; phys_addr_t phys_addr_base; - u32 *sensor_virt_addr[MAX_HID_DEVICES]; dma_addr_t sensor_dma_addr[MAX_HID_DEVICES]; u32 sensor_sts[MAX_HID_DEVICES]; u32 sensor_requested_cnt[MAX_HID_DEVICES]; @@ -34,8 +38,8 @@ struct amdtp_cl_data { u8 report_id[MAX_HID_DEVICES]; u8 sensor_idx[MAX_HID_DEVICES]; u8 *feature_report[MAX_HID_DEVICES]; - u8 *input_report[MAX_HID_DEVICES]; u8 request_done[MAX_HID_DEVICES]; + struct amd_input_data *in_data; struct delayed_work work; struct delayed_work work_buffer; }; @@ -64,4 +68,6 @@ void amdtp_hid_remove(struct amdtp_cl_data *cli_data); int amd_sfh_get_report(struct hid_device *hid, int report_id, int report_type); void amd_sfh_set_report(struct hid_device *hid, int report_id, int report_type); void amdtp_hid_wakeup(struct hid_device *hid); +u8 get_input_report(u8 current_index, int sensor_idx, int report_id, + struct amd_input_data *in_data); #endif diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c index ddecc84fd6f0..96e2577fa37e 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c @@ -24,12 +24,55 @@ #define ACEL_EN BIT(0) #define GYRO_EN BIT(1) #define MAGNO_EN BIT(2) +#define HPD_EN BIT(16) #define ALS_EN BIT(19) static int sensor_mask_override = -1; module_param_named(sensor_mask, sensor_mask_override, int, 0444); MODULE_PARM_DESC(sensor_mask, "override the detected sensors mask"); +static void amd_start_sensor_v2(struct amd_mp2_dev *privdata, struct amd_mp2_sensor_info info) +{ + union sfh_cmd_base cmd_base; + + cmd_base.ul = 0; + cmd_base.cmd_v2.cmd_id = ENABLE_SENSOR; + cmd_base.cmd_v2.period = info.period; + cmd_base.cmd_v2.sensor_id = info.sensor_idx; + cmd_base.cmd_v2.length = 16; + + if (info.sensor_idx == als_idx) + cmd_base.cmd_v2.mem_type = USE_C2P_REG; + + writeq(info.dma_address, privdata->mmio + AMD_C2P_MSG1); + writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG0); +} + +static void amd_stop_sensor_v2(struct amd_mp2_dev *privdata, u16 sensor_idx) +{ + union sfh_cmd_base cmd_base; + + cmd_base.ul = 0; + cmd_base.cmd_v2.cmd_id = DISABLE_SENSOR; + cmd_base.cmd_v2.period = 0; + cmd_base.cmd_v2.sensor_id = sensor_idx; + cmd_base.cmd_v2.length = 16; + + writeq(0x0, privdata->mmio + AMD_C2P_MSG2); + writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG0); +} + +static void amd_stop_all_sensor_v2(struct amd_mp2_dev *privdata) +{ + union sfh_cmd_base cmd_base; + + cmd_base.cmd_v2.cmd_id = STOP_ALL_SENSORS; + cmd_base.cmd_v2.period = 0; + cmd_base.cmd_v2.sensor_id = 0; + + writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG0); +} + void amd_start_sensor(struct amd_mp2_dev *privdata, struct amd_mp2_sensor_info info) { union sfh_cmd_param cmd_param; @@ -98,7 +141,6 @@ int amd_mp2_get_sensor_num(struct amd_mp2_dev *privdata, u8 *sensor_id) { int activestatus, num_of_sensors = 0; const struct dmi_system_id *dmi_id; - u32 activecontrolstatus; if (sensor_mask_override == -1) { dmi_id = dmi_first_match(dmi_sensor_mask_overrides); @@ -109,8 +151,7 @@ int amd_mp2_get_sensor_num(struct amd_mp2_dev *privdata, u8 *sensor_id) if (sensor_mask_override >= 0) { activestatus = sensor_mask_override; } else { - activecontrolstatus = readl(privdata->mmio + AMD_P2C_MSG3); - activestatus = activecontrolstatus >> 4; + activestatus = privdata->mp2_acs >> 4; } if (ACEL_EN & activestatus) @@ -125,13 +166,46 @@ int amd_mp2_get_sensor_num(struct amd_mp2_dev *privdata, u8 *sensor_id) if (ALS_EN & activestatus) sensor_id[num_of_sensors++] = als_idx; + if (HPD_EN & activestatus) + sensor_id[num_of_sensors++] = HPD_IDX; + return num_of_sensors; } static void amd_mp2_pci_remove(void *privdata) { + struct amd_mp2_dev *mp2 = privdata; amd_sfh_hid_client_deinit(privdata); - amd_stop_all_sensors(privdata); + mp2->mp2_ops->stop_all(mp2); +} + +static const struct amd_mp2_ops amd_sfh_ops_v2 = { + .start = amd_start_sensor_v2, + .stop = amd_stop_sensor_v2, + .stop_all = amd_stop_all_sensor_v2, +}; + +static const struct amd_mp2_ops amd_sfh_ops = { + .start = amd_start_sensor, + .stop = amd_stop_sensor, + .stop_all = amd_stop_all_sensors, +}; + +static void mp2_select_ops(struct amd_mp2_dev *privdata) +{ + u8 acs; + + privdata->mp2_acs = readl(privdata->mmio + AMD_P2C_MSG3); + acs = privdata->mp2_acs & GENMASK(3, 0); + + switch (acs) { + case V2_STATUS: + privdata->mp2_ops = &amd_sfh_ops_v2; + break; + default: + privdata->mp2_ops = &amd_sfh_ops; + break; + } } static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) @@ -160,10 +234,17 @@ static int amd_mp2_pci_probe(struct pci_dev *pdev, const struct pci_device_id *i rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); return rc; } + + privdata->cl_data = devm_kzalloc(&pdev->dev, sizeof(struct amdtp_cl_data), GFP_KERNEL); + if (!privdata->cl_data) + return -ENOMEM; + rc = devm_add_action_or_reset(&pdev->dev, amd_mp2_pci_remove, privdata); if (rc) return rc; + mp2_select_ops(privdata); + return amd_sfh_hid_client_init(privdata); } diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h index 489415f7c22c..2d5c57e3782d 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h @@ -10,6 +10,7 @@ #define PCIE_MP2_AMD_H #include +#include "amd_sfh_hid.h" #define PCI_DEVICE_ID_AMD_MP2 0x15E4 @@ -22,9 +23,15 @@ #define AMD_C2P_MSG1 0x10504 #define AMD_C2P_MSG2 0x10508 +#define AMD_C2P_MSG(regno) (0x10500 + ((regno) * 4)) + /* MP2 P2C Message Registers */ #define AMD_P2C_MSG3 0x1068C /* Supported Sensors info */ +#define V2_STATUS 0x2 + +#define HPD_IDX 16 + /* SFH Command register */ union sfh_cmd_base { u32 ul; @@ -33,6 +40,15 @@ union sfh_cmd_base { u32 sensor_id : 8; u32 period : 16; } s; + struct { + u32 cmd_id : 4; + u32 intr_enable : 1; + u32 rsvd1 : 3; + u32 length : 7; + u32 mem_type : 1; + u32 sensor_id : 8; + u32 period : 8; + } cmd_v2; }; union sfh_cmd_param { @@ -61,6 +77,10 @@ struct amd_mp2_dev { struct pci_dev *pdev; struct amdtp_cl_data *cl_data; void __iomem *mmio; + const struct amd_mp2_ops *mp2_ops; + struct amd_input_data in_data; + /* mp2 active control status */ + u32 mp2_acs; }; struct amd_mp2_sensor_info { @@ -69,10 +89,33 @@ struct amd_mp2_sensor_info { dma_addr_t dma_address; }; +enum mem_use_type { + USE_DRAM, + USE_C2P_REG, +}; + +struct hpd_status { + union { + struct { + u32 human_presence_report : 4; + u32 human_presence_actual : 4; + u32 probablity : 8; + u32 object_distance : 16; + } shpd; + u32 val; + }; +}; + void amd_start_sensor(struct amd_mp2_dev *privdata, struct amd_mp2_sensor_info info); void amd_stop_sensor(struct amd_mp2_dev *privdata, u16 sensor_idx); void amd_stop_all_sensors(struct amd_mp2_dev *privdata); int amd_mp2_get_sensor_num(struct amd_mp2_dev *privdata, u8 *sensor_id); int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata); int amd_sfh_hid_client_deinit(struct amd_mp2_dev *privdata); + +struct amd_mp2_ops { + void (*start)(struct amd_mp2_dev *privdata, struct amd_mp2_sensor_info info); + void (*stop)(struct amd_mp2_dev *privdata, u16 sensor_idx); + void (*stop_all)(struct amd_mp2_dev *privdata); +}; #endif diff --git a/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_desc.c b/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_desc.c index 6e3ad66e57a4..0c3697219382 100644 --- a/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_desc.c +++ b/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_desc.c @@ -12,6 +12,7 @@ #include "amd_sfh_pcie.h" #include "amd_sfh_hid_desc.h" #include "amd_sfh_hid_report_desc.h" +#include "amd_sfh_hid.h" #define AMD_SFH_FW_MULTIPLIER (1000) #define HID_USAGE_SENSOR_PROP_REPORTING_STATE_ALL_EVENTS_ENUM 0x41 @@ -49,6 +50,11 @@ int get_report_descriptor(int sensor_idx, u8 *rep_desc) memcpy(rep_desc, als_report_descriptor, sizeof(als_report_descriptor)); break; + case HPD_IDX: /* HPD sensor */ + memset(rep_desc, 0, sizeof(hpd_report_descriptor)); + memcpy(rep_desc, hpd_report_descriptor, + sizeof(hpd_report_descriptor)); + break; default: break; } @@ -98,6 +104,17 @@ u32 get_descr_sz(int sensor_idx, int descriptor_name) return sizeof(struct als_feature_report); } break; + case HPD_IDX: + switch (descriptor_name) { + case descr_size: + return sizeof(hpd_report_descriptor); + case input_size: + return sizeof(struct hpd_input_report); + case feature_size: + return sizeof(struct hpd_feature_report); + } + break; + default: break; } @@ -119,6 +136,7 @@ u8 get_feature_report(int sensor_idx, int report_id, u8 *feature_report) struct accel3_feature_report acc_feature; struct gyro_feature_report gyro_feature; struct magno_feature_report magno_feature; + struct hpd_feature_report hpd_feature; struct als_feature_report als_feature; u8 report_size = 0; @@ -161,6 +179,12 @@ u8 get_feature_report(int sensor_idx, int report_id, u8 *feature_report) memcpy(feature_report, &als_feature, sizeof(als_feature)); report_size = sizeof(als_feature); break; + case HPD_IDX: /* human presence detection sensor */ + get_common_features(&hpd_feature.common_property, report_id); + memcpy(feature_report, &hpd_feature, sizeof(hpd_feature)); + report_size = sizeof(hpd_feature); + break; + default: break; } @@ -174,12 +198,18 @@ static void get_common_inputs(struct common_input_property *common, int report_i common->event_type = HID_USAGE_SENSOR_EVENT_DATA_UPDATED_ENUM; } -u8 get_input_report(int sensor_idx, int report_id, u8 *input_report, u32 *sensor_virt_addr) +u8 get_input_report(u8 current_index, int sensor_idx, int report_id, struct amd_input_data *in_data) { + struct amd_mp2_dev *privdata = container_of(in_data, struct amd_mp2_dev, in_data); + u32 *sensor_virt_addr = in_data->sensor_virt_addr[current_index]; + u8 *input_report = in_data->input_report[current_index]; + u8 supported_input = privdata->mp2_acs & GENMASK(3, 0); + struct magno_input_report magno_input; struct accel3_input_report acc_input; struct gyro_input_report gyro_input; - struct magno_input_report magno_input; + struct hpd_input_report hpd_input; struct als_input_report als_input; + struct hpd_status hpdstatus; u8 report_size = 0; if (!sensor_virt_addr || !input_report) @@ -213,10 +243,22 @@ u8 get_input_report(int sensor_idx, int report_id, u8 *input_report, u32 *sensor break; case als_idx: /* Als */ get_common_inputs(&als_input.common_property, report_id); - als_input.illuminance_value = (int)sensor_virt_addr[0] / AMD_SFH_FW_MULTIPLIER; + /* For ALS ,V2 Platforms uses C2P_MSG5 register instead of DRAM access method */ + if (supported_input == V2_STATUS) + als_input.illuminance_value = (int)readl(privdata->mmio + AMD_C2P_MSG(5)); + else + als_input.illuminance_value = + (int)sensor_virt_addr[0] / AMD_SFH_FW_MULTIPLIER; report_size = sizeof(als_input); memcpy(input_report, &als_input, sizeof(als_input)); break; + case HPD_IDX: /* hpd */ + get_common_inputs(&hpd_input.common_property, report_id); + hpdstatus.val = readl(privdata->mmio + AMD_C2P_MSG(4)); + hpd_input.human_presence = hpdstatus.shpd.human_presence_actual; + report_size = sizeof(hpd_input); + memcpy(input_report, &hpd_input, sizeof(hpd_input)); + break; default: break; } diff --git a/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_desc.h b/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_desc.h index 095c471d8fd6..16f563d1823b 100644 --- a/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_desc.h +++ b/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_desc.h @@ -100,8 +100,17 @@ struct als_input_report { int illuminance_value; } __packed; +struct hpd_feature_report { + struct common_feature_property common_property; +} __packed; + +struct hpd_input_report { + struct common_input_property common_property; + /* values specific to human presence sensor */ + u8 human_presence; +} __packed; + int get_report_descriptor(int sensor_idx, u8 rep_desc[]); u32 get_descr_sz(int sensor_idx, int descriptor_name); u8 get_feature_report(int sensor_idx, int report_id, u8 *feature_report); -u8 get_input_report(int sensor_idx, int report_id, u8 *input_report, u32 *sensor_virt_addr); #endif diff --git a/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_report_desc.h b/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_report_desc.h index 44271d39b322..66d6b26e4708 100644 --- a/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_report_desc.h +++ b/drivers/hid/amd-sfh-hid/hid_descriptor/amd_sfh_hid_report_desc.h @@ -642,4 +642,116 @@ const u8 als_report_descriptor[] = { 0X81, 0x02, /* HID Input (Data_Arr_Abs) */ 0xC0 /* HID end collection */ }; + +/* BIOMETRIC PRESENCE*/ +static const u8 hpd_report_descriptor[] = { +0x05, 0x20, /* Usage page */ +0x09, 0x11, /* BIOMETRIC PRESENCE */ +0xA1, 0x00, /* HID Collection (Physical) */ + +//feature reports(xmit/receive) +0x85, 5, /* HID Report ID */ +0x05, 0x20, /* HID usage page sensor */ +0x0A, 0x09, 0x03, /* Sensor property and sensor connection type */ +0x15, 0, /* HID logical MIN_8(0) */ +0x25, 2, /* HID logical MAX_8(2) */ +0x75, 8, /* HID report size(8) */ +0x95, 1, /* HID report count(1) */ +0xA1, 0x02, /* HID collection (logical) */ +0x0A, 0x30, 0x08, /* Sensor property connection type intergated sel*/ +0x0A, 0x31, 0x08, /* Sensor property connection type attached sel */ +0x0A, 0x32, 0x08, /* Sensor property connection type external sel */ +0xB1, 0x00, /* HID feature (Data_Arr_Abs) */ +0xC0, /* HID end collection */ +0x0A, 0x16, 0x03, /* HID usage sensor property reporting state */ +0x15, 0, /* HID logical Min_8(0) */ +0x25, 5, /* HID logical Max_8(5) */ +0x75, 8, /* HID report size(8) */ +0x95, 1, /* HID report count(1) */ +0xA1, 0x02, /* HID collection(logical) */ +0x0A, 0x40, 0x08, /* Sensor property report state no events sel */ +0x0A, 0x41, 0x08, /* Sensor property report state all events sel */ +0x0A, 0x42, 0x08, /* Sensor property report state threshold events sel */ +0x0A, 0x43, 0x08, /* Sensor property report state no events wake sel */ +0x0A, 0x44, 0x08, /* Sensor property report state all events wake sel */ +0x0A, 0x45, 0x08, /* Sensor property report state threshold events wake sel */ +0xB1, 0x00, /* HID feature (Data_Arr_Abs) */ +0xC0, /* HID end collection */ +0x0A, 0x19, 0x03, /* HID usage sensor property power state */ +0x15, 0, /* HID logical Min_8(0) */ +0x25, 5, /* HID logical Max_8(5) */ +0x75, 8, /* HID report size(8) */ +0x95, 1, /* HID report count(1) */ +0xA1, 0x02, /* HID collection(logical) */ +0x0A, 0x50, 0x08, /* Sensor property power state undefined sel */ +0x0A, 0x51, 0x08, /* Sensor property power state D0 full power sel */ +0x0A, 0x52, 0x08, /* Sensor property power state D1 low power sel */ +0x0A, 0x53, 0x08, /* Sensor property power state D2 standby with wake sel */ +0x0A, 0x54, 0x08, /* Sensor property power state D3 sleep with wake sel */ +0x0A, 0x55, 0x08, /* Sensor property power state D4 power off sel */ +0xB1, 0x00, /* HID feature (Data_Arr_Abs) */ +0xC0, /* HID end collection */ +0x0A, 0x01, 0x02, /* HID usage sensor state */ +0x15, 0, /* HID logical Min_8(0) */ +0x25, 6, /* HID logical Max_8(6) */ +0x75, 8, /* HID report size(8) */ +0x95, 1, /* HID report count(1) */ +0xA1, 0x02, /* HID collection(logical) */ +0x0A, 0x00, 0x08, /* HID usage sensor state unknown sel */ +0x0A, 0x01, 0x08, /* HID usage sensor state ready sel */ +0x0A, 0x02, 0x08, /* HID usage sensor state not available sel */ +0x0A, 0x03, 0x08, /* HID usage sensor state no data sel */ +0x0A, 0x04, 0x08, /* HID usage sensor state initializing sel */ +0x0A, 0x05, 0x08, /* HID usage sensor state access denied sel */ +0x0A, 0x06, 0x08, /* HID usage sensor state error sel */ +0xB1, 0x00, /* HID feature (Data_Arr_Abs) */ +0xC0, /* HID end collection */ +0x0A, 0x0E, 0x03, /* HID usage sensor property report interval */ +0x15, 0, /* HID logical Min_8(0) */ +0x27, 0xFF, 0xFF, 0xFF, 0xFF, /* HID logical Max_32 */ + +0x75, 32, /* HID report size(32) */ +0x95, 1, /* HID report count(1) */ +0x55, 0, /* HID unit exponent(0) */ +0xB1, 0x02, /* HID feature (Data_Var_Abs) */ + +//input report (transmit) +0x05, 0x20, /* HID usage page sensors */ +0x0A, 0x01, 0x02, /* HID usage sensor state */ +0x15, 0, /* HID logical Min_8(0) */ +0x25, 6, /* HID logical Max_8(6) */ +0x75, 8, /* HID report size(8) */ +0x95, 1, /* HID report count (1) */ +0xA1, 0x02, /* HID end collection (logical) */ +0x0A, 0x00, 0x08, /* HID usage sensor state unknown sel */ +0x0A, 0x01, 0x08, /* HID usage sensor state ready sel */ +0x0A, 0x02, 0x08, /* HID usage sensor state not available sel */ +0x0A, 0x03, 0x08, /* HID usage sensor state no data sel */ +0x0A, 0x04, 0x08, /* HID usage sensor state initializing sel */ +0x0A, 0x05, 0x08, /* HID usage sensor state access denied sel */ +0x0A, 0x06, 0x08, /* HID usage sensor state error sel */ +0X81, 0x00, /* HID Input (Data_Arr_Abs) */ +0xC0, /* HID end collection */ +0x0A, 0x02, 0x02, /* HID usage sensor event */ +0x15, 0, /* HID logical Min_8(0) */ +0x25, 5, /* HID logical Max_8(5) */ +0x75, 8, /* HID report size(8) */ +0x95, 1, /* HID report count (1) */ +0xA1, 0x02, /* HID end collection (logical) */ +0x0A, 0x10, 0x08, /* HID usage sensor event unknown sel */ +0x0A, 0x11, 0x08, /* HID usage sensor event state changed sel */ +0x0A, 0x12, 0x08, /* HID usage sensor event property changed sel */ +0x0A, 0x13, 0x08, /* HID usage sensor event data updated sel */ +0x0A, 0x14, 0x08, /* HID usage sensor event poll response sel */ +0x0A, 0x15, 0x08, /* HID usage sensor event change sensitivity sel */ +0X81, 0x00, /* HID Input (Data_Arr_Abs) */ +0xC0, /* HID end collection */ +0x0A, 0xB1, 0x04, /* HID usage sensor data BIOMETRIC HUMAN PRESENCE */ +0x15, 0, /* HID logical Min_8(0) */ +0x25, 1, /* HID logical Max_8(1) */ +0x75, 8, /* HID report size(8) */ +0x95, 1, /* HID report count (1) */ +0X81, 0x02, /* HID Input (Data_Var_Abs) */ +0xC0 /* HID end collection */ +}; #endif diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 0de2788b9814..7db332139f7d 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2306,12 +2306,8 @@ static int hid_device_remove(struct device *dev) { struct hid_device *hdev = to_hid_device(dev); struct hid_driver *hdrv; - int ret = 0; - if (down_interruptible(&hdev->driver_input_lock)) { - ret = -EINTR; - goto end; - } + down(&hdev->driver_input_lock); hdev->io_started = false; hdrv = hdev->driver; @@ -2326,8 +2322,8 @@ static int hid_device_remove(struct device *dev) if (!hdev->io_started) up(&hdev->driver_input_lock); -end: - return ret; + + return 0; } static ssize_t modalias_show(struct device *dev, struct device_attribute *a, diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index a311fb87b02a..fa57d05badf7 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -122,6 +122,7 @@ static const struct hid_usage_entry hid_usage_table[] = { { 9, 0, "Button" }, { 10, 0, "Ordinal" }, { 12, 0, "Consumer" }, + {0, 0x003, "ProgrammableButtons"}, {0, 0x238, "HorizontalWheel"}, { 13, 0, "Digitizers" }, {0, 0x01, "Digitizer"}, @@ -942,6 +943,16 @@ static const char *keys[KEY_MAX + 1] = { [KEY_KBDINPUTASSIST_NEXTGROUP] = "KbdInputAssistNextGroup", [KEY_KBDINPUTASSIST_ACCEPT] = "KbdInputAssistAccept", [KEY_KBDINPUTASSIST_CANCEL] = "KbdInputAssistCancel", + [KEY_MACRO1] = "Macro1", [KEY_MACRO2] = "Macro2", [KEY_MACRO3] = "Macro3", + [KEY_MACRO4] = "Macro4", [KEY_MACRO5] = "Macro5", [KEY_MACRO6] = "Macro6", + [KEY_MACRO7] = "Macro7", [KEY_MACRO8] = "Macro8", [KEY_MACRO9] = "Macro9", + [KEY_MACRO10] = "Macro10", [KEY_MACRO11] = "Macro11", [KEY_MACRO12] = "Macro12", + [KEY_MACRO13] = "Macro13", [KEY_MACRO14] = "Macro14", [KEY_MACRO15] = "Macro15", + [KEY_MACRO16] = "Macro16", [KEY_MACRO17] = "Macro17", [KEY_MACRO18] = "Macro18", + [KEY_MACRO19] = "Macro19", [KEY_MACRO20] = "Macro20", [KEY_MACRO21] = "Macro21", + [KEY_MACRO22] = "Macro22", [KEY_MACRO23] = "Macro23", [KEY_MACRO24] = "Macro24", + [KEY_MACRO25] = "Macro25", [KEY_MACRO26] = "Macro26", [KEY_MACRO27] = "Macro27", + [KEY_MACRO28] = "Macro28", [KEY_MACRO29] = "Macro29", [KEY_MACRO30] = "Macro30", }; static const char *relatives[REL_MAX + 1] = { diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index e60c31dd05ff..8123b871a3eb 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -272,12 +273,21 @@ static const struct acpi_device_id cbas_ec_acpi_ids[] = { }; MODULE_DEVICE_TABLE(acpi, cbas_ec_acpi_ids); +#ifdef CONFIG_OF +static const struct of_device_id cbas_ec_of_match[] = { + { .compatible = "google,cros-cbas" }, + { }, +}; +MODULE_DEVICE_TABLE(of, cbas_ec_of_match); +#endif + static struct platform_driver cbas_ec_driver = { .probe = cbas_ec_probe, .remove = cbas_ec_remove, .driver = { .name = "cbas_ec", .acpi_match_table = ACPI_PTR(cbas_ec_acpi_ids), + .of_match_table = of_match_ptr(cbas_ec_of_match), .pm = &cbas_ec_pm_ops, }, }; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 8cfb6f45bb94..5420f288d2aa 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -396,6 +396,7 @@ #define USB_DEVICE_ID_HP_X2_10_COVER 0x0755 #define I2C_DEVICE_ID_HP_SPECTRE_X360_15 0x2817 #define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN 0x2706 +#define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN 0x261A #define USB_VENDOR_ID_ELECOM 0x056e #define USB_DEVICE_ID_ELECOM_BM084 0x0061 @@ -763,6 +764,7 @@ #define I2C_DEVICE_ID_LG_7010 0x7010 #define USB_VENDOR_ID_LOGITECH 0x046d +#define USB_DEVICE_ID_LOGITECH_Z_10_SPK 0x0a07 #define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e #define USB_DEVICE_ID_LOGITECH_T651 0xb00c #define USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD 0xb309 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index abbfa91e73e4..4286a51f7f16 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -326,6 +326,8 @@ static const struct hid_device_id hid_battery_quirks[] = { HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_15), HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN), + HID_BATTERY_QUIRK_IGNORE }, {} }; @@ -567,6 +569,16 @@ static void hidinput_update_battery(struct hid_device *dev, int value) } #endif /* CONFIG_HID_BATTERY_STRENGTH */ +static bool hidinput_field_in_collection(struct hid_device *device, struct hid_field *field, + unsigned int type, unsigned int usage) +{ + struct hid_collection *collection; + + collection = &device->collection[field->usage->collection_index]; + + return collection->type == type && collection->usage == usage; +} + static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_field *field, struct hid_usage *usage) { @@ -632,6 +644,18 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel else code += BTN_TRIGGER_HAPPY - 0x10; break; + case HID_CP_CONSUMER_CONTROL: + if (hidinput_field_in_collection(device, field, + HID_COLLECTION_NAMED_ARRAY, + HID_CP_PROGRAMMABLEBUTTONS)) { + if (code <= 0x1d) + code += KEY_MACRO1; + else + code += BTN_TRIGGER_HAPPY - 0x1e; + } else { + goto ignore; + } + break; default: switch (field->physical) { case HID_GD_MOUSE: @@ -1316,12 +1340,12 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct return; } - if (usage->hid == (HID_UP_DIGITIZER | 0x003c)) { /* Invert */ + if (usage->hid == HID_DG_INVERT) { *quirks = value ? (*quirks | HID_QUIRK_INVERT) : (*quirks & ~HID_QUIRK_INVERT); return; } - if (usage->hid == (HID_UP_DIGITIZER | 0x0032)) { /* InRange */ + if (usage->hid == HID_DG_INRANGE) { if (value) { input_event(input, usage->type, (*quirks & HID_QUIRK_INVERT) ? BTN_TOOL_RUBBER : usage->code, 1); return; @@ -1331,7 +1355,7 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct return; } - if (usage->hid == (HID_UP_DIGITIZER | 0x0030) && (*quirks & HID_QUIRK_NOTOUCH)) { /* Pressure */ + if (usage->hid == HID_DG_TIPPRESSURE && (*quirks & HID_QUIRK_NOTOUCH)) { int a = field->logical_minimum; int b = field->logical_maximum; input_event(input, EV_KEY, BTN_TOUCH, value > a + ((b - a) >> 3)); diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 14fc068affad..430fa4f52ed3 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -135,4 +135,5 @@ static struct hid_driver ite_driver = { }; module_hid_driver(ite_driver); +MODULE_AUTHOR("Hans de Goede "); MODULE_LICENSE("GPL"); diff --git a/drivers/hid/hid-lg-g15.c b/drivers/hid/hid-lg-g15.c index bfbba0d41933..b2a08233f8d5 100644 --- a/drivers/hid/hid-lg-g15.c +++ b/drivers/hid/hid-lg-g15.c @@ -28,6 +28,7 @@ enum lg_g15_model { LG_G15_V2, LG_G510, LG_G510_USB_AUDIO, + LG_Z10, }; enum lg_g15_led_type { @@ -457,6 +458,13 @@ static int lg_g15_get_initial_led_brightness(struct lg_g15_data *g15) return ret; return lg_g510_update_mkey_led_brightness(g15); + case LG_Z10: + /* + * Getting the LCD backlight brightness is not supported. + * Reading Feature(2) fails with -EPIPE and this crashes + * the LCD and touch keys part of the speakers. + */ + return 0; } return -EINVAL; /* Never reached */ } @@ -464,7 +472,20 @@ static int lg_g15_get_initial_led_brightness(struct lg_g15_data *g15) /******** Input functions ********/ /* On the G15 Mark I Logitech has been quite creative with which bit is what */ -static int lg_g15_event(struct lg_g15_data *g15, u8 *data, int size) +static void lg_g15_handle_lcd_menu_keys(struct lg_g15_data *g15, u8 *data) +{ + int i, val; + + /* Most left (round/display) button below the LCD */ + input_report_key(g15->input, KEY_KBD_LCD_MENU1, data[8] & 0x80); + /* 4 other buttons below the LCD */ + for (i = 0; i < 4; i++) { + val = data[i + 2] & 0x80; + input_report_key(g15->input, KEY_KBD_LCD_MENU2 + i, val); + } +} + +static int lg_g15_event(struct lg_g15_data *g15, u8 *data) { int i, val; @@ -494,13 +515,7 @@ static int lg_g15_event(struct lg_g15_data *g15, u8 *data, int size) /* MR */ input_report_key(g15->input, KEY_MACRO_RECORD_START, data[7] & 0x40); - /* Most left (round) button below the LCD */ - input_report_key(g15->input, KEY_KBD_LCD_MENU1, data[8] & 0x80); - /* 4 other buttons below the LCD */ - for (i = 0; i < 4; i++) { - val = data[i + 2] & 0x80; - input_report_key(g15->input, KEY_KBD_LCD_MENU2 + i, val); - } + lg_g15_handle_lcd_menu_keys(g15, data); /* Backlight cycle button pressed? */ if (data[1] & 0x80) @@ -510,7 +525,7 @@ static int lg_g15_event(struct lg_g15_data *g15, u8 *data, int size) return 0; } -static int lg_g15_v2_event(struct lg_g15_data *g15, u8 *data, int size) +static int lg_g15_v2_event(struct lg_g15_data *g15, u8 *data) { int i, val; @@ -542,7 +557,7 @@ static int lg_g15_v2_event(struct lg_g15_data *g15, u8 *data, int size) return 0; } -static int lg_g510_event(struct lg_g15_data *g15, u8 *data, int size) +static int lg_g510_event(struct lg_g15_data *g15, u8 *data) { bool game_mode_enabled; int i, val; @@ -586,7 +601,7 @@ static int lg_g510_event(struct lg_g15_data *g15, u8 *data, int size) return 0; } -static int lg_g510_leds_event(struct lg_g15_data *g15, u8 *data, int size) +static int lg_g510_leds_event(struct lg_g15_data *g15, u8 *data) { bool backlight_disabled; @@ -613,18 +628,24 @@ static int lg_g15_raw_event(struct hid_device *hdev, struct hid_report *report, switch (g15->model) { case LG_G15: if (data[0] == 0x02 && size == 9) - return lg_g15_event(g15, data, size); + return lg_g15_event(g15, data); break; case LG_G15_V2: if (data[0] == 0x02 && size == 5) - return lg_g15_v2_event(g15, data, size); + return lg_g15_v2_event(g15, data); + break; + case LG_Z10: + if (data[0] == 0x02 && size == 9) { + lg_g15_handle_lcd_menu_keys(g15, data); + input_sync(g15->input); + } break; case LG_G510: case LG_G510_USB_AUDIO: if (data[0] == 0x03 && size == 5) - return lg_g510_event(g15, data, size); + return lg_g510_event(g15, data); if (data[0] == 0x04 && size == 2) - return lg_g510_leds_event(g15, data, size); + return lg_g510_leds_event(g15, data); break; } @@ -645,25 +666,18 @@ static void lg_g15_input_close(struct input_dev *dev) hid_hw_close(hdev); } -static int lg_g15_register_led(struct lg_g15_data *g15, int i) +static int lg_g15_register_led(struct lg_g15_data *g15, int i, const char *name) { - static const char * const led_names[] = { - "g15::kbd_backlight", - "g15::lcd_backlight", - "g15::macro_preset1", - "g15::macro_preset2", - "g15::macro_preset3", - "g15::macro_record", - }; - g15->leds[i].led = i; - g15->leds[i].cdev.name = led_names[i]; + g15->leds[i].cdev.name = name; switch (g15->model) { case LG_G15: case LG_G15_V2: - g15->leds[i].cdev.brightness_set_blocking = lg_g15_led_set; g15->leds[i].cdev.brightness_get = lg_g15_led_get; + fallthrough; + case LG_Z10: + g15->leds[i].cdev.brightness_set_blocking = lg_g15_led_set; if (i < LG_G15_BRIGHTNESS_MAX) { g15->leds[i].cdev.flags = LED_BRIGHT_HW_CHANGED; g15->leds[i].cdev.max_brightness = 2; @@ -702,8 +716,38 @@ static int lg_g15_register_led(struct lg_g15_data *g15, int i) return devm_led_classdev_register(&g15->hdev->dev, &g15->leds[i].cdev); } +/* Common input device init code shared between keyboards and Z-10 speaker handling */ +static void lg_g15_init_input_dev(struct hid_device *hdev, struct input_dev *input, + const char *name) +{ + int i; + + input->name = name; + input->phys = hdev->phys; + input->uniq = hdev->uniq; + input->id.bustype = hdev->bus; + input->id.vendor = hdev->vendor; + input->id.product = hdev->product; + input->id.version = hdev->version; + input->dev.parent = &hdev->dev; + input->open = lg_g15_input_open; + input->close = lg_g15_input_close; + + /* Keys below the LCD, intended for controlling a menu on the LCD */ + for (i = 0; i < 5; i++) + input_set_capability(input, EV_KEY, KEY_KBD_LCD_MENU1 + i); +} + static int lg_g15_probe(struct hid_device *hdev, const struct hid_device_id *id) { + static const char * const led_names[] = { + "g15::kbd_backlight", + "g15::lcd_backlight", + "g15::macro_preset1", + "g15::macro_preset2", + "g15::macro_preset3", + "g15::macro_record", + }; u8 gkeys_settings_output_report = 0; u8 gkeys_settings_feature_report = 0; struct hid_report_enum *rep_enum; @@ -744,6 +788,8 @@ static int lg_g15_probe(struct hid_device *hdev, const struct hid_device_id *id) g15->hdev = hdev; g15->model = id->driver_data; + g15->input = input; + input_set_drvdata(input, hdev); hid_set_drvdata(hdev, (void *)g15); switch (g15->model) { @@ -772,6 +818,9 @@ static int lg_g15_probe(struct hid_device *hdev, const struct hid_device_id *id) gkeys_settings_feature_report = 0x01; gkeys = 18; break; + case LG_Z10: + connect_mask = HID_CONNECT_HIDRAW; + break; } ret = hid_hw_start(hdev, connect_mask); @@ -814,17 +863,21 @@ static int lg_g15_probe(struct hid_device *hdev, const struct hid_device_id *id) if (ret) goto error_hw_stop; + if (g15->model == LG_Z10) { + lg_g15_init_input_dev(hdev, g15->input, "Logitech Z-10 LCD Menu Keys"); + ret = input_register_device(g15->input); + if (ret) + goto error_hw_stop; + + ret = lg_g15_register_led(g15, 1, "z-10::lcd_backlight"); + if (ret) + goto error_hw_stop; + + return 0; /* All done */ + } + /* Setup and register input device */ - input->name = "Logitech Gaming Keyboard Gaming Keys"; - input->phys = hdev->phys; - input->uniq = hdev->uniq; - input->id.bustype = hdev->bus; - input->id.vendor = hdev->vendor; - input->id.product = hdev->product; - input->id.version = hdev->version; - input->dev.parent = &hdev->dev; - input->open = lg_g15_input_open; - input->close = lg_g15_input_close; + lg_g15_init_input_dev(hdev, input, "Logitech Gaming Keyboard Gaming Keys"); /* G-keys */ for (i = 0; i < gkeys; i++) @@ -835,10 +888,6 @@ static int lg_g15_probe(struct hid_device *hdev, const struct hid_device_id *id) input_set_capability(input, EV_KEY, KEY_MACRO_PRESET1 + i); input_set_capability(input, EV_KEY, KEY_MACRO_RECORD_START); - /* Keys below the LCD, intended for controlling a menu on the LCD */ - for (i = 0; i < 5; i++) - input_set_capability(input, EV_KEY, KEY_KBD_LCD_MENU1 + i); - /* * On the G510 only report headphone and mic mute keys when *not* using * the builtin USB audio device. When the builtin audio is used these @@ -850,16 +899,13 @@ static int lg_g15_probe(struct hid_device *hdev, const struct hid_device_id *id) input_set_capability(input, EV_KEY, KEY_F20); } - g15->input = input; - input_set_drvdata(input, hdev); - ret = input_register_device(input); if (ret) goto error_hw_stop; /* Register LED devices */ for (i = 0; i < LG_G15_LED_MAX; i++) { - ret = lg_g15_register_led(g15, i); + ret = lg_g15_register_led(g15, i, led_names[i]); if (ret) goto error_hw_stop; } @@ -890,6 +936,10 @@ static const struct hid_device_id lg_g15_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G510_USB_AUDIO), .driver_data = LG_G510_USB_AUDIO }, + /* Z-10 speakers */ + { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, + USB_DEVICE_ID_LOGITECH_Z_10_SPK), + .driver_data = LG_Z10 }, { } }; MODULE_DEVICE_TABLE(hid, lg_g15_devices); @@ -902,4 +952,5 @@ static struct hid_driver lg_g15_driver = { }; module_hid_driver(lg_g15_driver); +MODULE_AUTHOR("Hans de Goede "); MODULE_LICENSE("GPL"); diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index fa835d565982..a0017b010c34 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -100,6 +100,7 @@ #define HIDPP_DEVICE_TYPE_MASK GENMASK(3, 0) #define HIDPP_LINK_STATUS_MASK BIT(6) #define HIDPP_MANUFACTURER_MASK BIT(7) +#define HIDPP_27MHZ_SECURE_MASK BIT(7) #define HIDPP_DEVICE_TYPE_KEYBOARD 1 #define HIDPP_DEVICE_TYPE_MOUSE 2 @@ -984,6 +985,13 @@ static void logi_hidpp_dev_conn_notif_27mhz(struct hid_device *hdev, workitem->reports_supported |= STD_MOUSE | HIDPP; break; case 3: /* Index 3 is always the keyboard */ + if (hidpp_report->params[HIDPP_PARAM_DEVICE_INFO] & HIDPP_27MHZ_SECURE_MASK) { + hid_info(hdev, "Keyboard connection is encrypted\n"); + } else { + hid_warn(hdev, "Keyboard events are send over the air in plain-text / unencrypted\n"); + hid_warn(hdev, "See: https://gitlab.freedesktop.org/jwrdegoede/logitech-27mhz-keyboard-encryption-setup/\n"); + } + fallthrough; case 4: /* Index 4 is used for an optional separate numpad */ workitem->device_type = HIDPP_DEVICE_TYPE_KEYBOARD; workitem->reports_supported |= STD_KEYBOARD | MULTIMEDIA | @@ -1489,6 +1497,13 @@ static void logi_dj_ll_stop(struct hid_device *hid) dbg_hid("%s\n", __func__); } +static bool logi_dj_ll_may_wakeup(struct hid_device *hid) +{ + struct dj_device *djdev = hid->driver_data; + struct dj_receiver_dev *djrcv_dev = djdev->dj_receiver_dev; + + return hid_hw_may_wakeup(djrcv_dev->hidpp); +} static struct hid_ll_driver logi_dj_ll_driver = { .parse = logi_dj_ll_parse, @@ -1497,6 +1512,7 @@ static struct hid_ll_driver logi_dj_ll_driver = { .open = logi_dj_ll_open, .close = logi_dj_ll_close, .raw_request = logi_dj_ll_raw_request, + .may_wakeup = logi_dj_ll_may_wakeup, }; static int logi_dj_dj_event(struct hid_device *hdev, diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index fee4e54a3ce0..61635e629469 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -56,6 +56,8 @@ MODULE_PARM_DESC(disable_tap_to_click, #define HIDPP_SUB_ID_CONSUMER_VENDOR_KEYS 0x03 #define HIDPP_SUB_ID_ROLLER 0x05 #define HIDPP_SUB_ID_MOUSE_EXTRA_BTNS 0x06 +#define HIDPP_SUB_ID_USER_IFACE_EVENT 0x08 +#define HIDPP_USER_IFACE_EVENT_ENCRYPTION_KEY_LOST BIT(5) #define HIDPP_QUIRK_CLASS_WTP BIT(0) #define HIDPP_QUIRK_CLASS_M560 BIT(1) @@ -3529,6 +3531,16 @@ static int hidpp_raw_hidpp_event(struct hidpp_device *hidpp, u8 *data, return 1; } + if (hidpp->hid_dev->group == HID_GROUP_LOGITECH_27MHZ_DEVICE && + data[0] == REPORT_ID_HIDPP_SHORT && + data[2] == HIDPP_SUB_ID_USER_IFACE_EVENT && + (data[3] & HIDPP_USER_IFACE_EVENT_ENCRYPTION_KEY_LOST)) { + dev_err_ratelimited(&hidpp->hid_dev->dev, + "Error the keyboard's wireless encryption key has been lost, your keyboard will not work unless you re-configure encryption.\n"); + dev_err_ratelimited(&hidpp->hid_dev->dev, + "See: https://gitlab.freedesktop.org/jwrdegoede/logitech-27mhz-keyboard-encryption-setup/\n"); + } + if (hidpp->capabilities & HIDPP_CAPABILITY_HIDPP20_BATTERY) { ret = hidpp20_battery_event_1000(hidpp, data, size); if (ret != 0) diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 2e4fb76c45f3..3ea7cb1cda84 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1768,7 +1768,8 @@ static int mt_suspend(struct hid_device *hdev, pm_message_t state) struct mt_device *td = hid_get_drvdata(hdev); /* High latency is desirable for power savings during S3/S0ix */ - if (td->mtclass.quirks & MT_QUIRK_DISABLE_WAKEUP) + if ((td->mtclass.quirks & MT_QUIRK_DISABLE_WAKEUP) || + !hid_hw_may_wakeup(hdev)) mt_set_modes(hdev, HID_LATENCY_HIGH, false, false); else mt_set_modes(hdev, HID_LATENCY_HIGH, true, true); diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index 8319b0ce385a..b3722c51ec78 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -597,9 +597,8 @@ struct sony_sc { /* DS4 calibration data */ struct ds4_calibration_data ds4_calib_data[6]; /* GH Live */ + struct urb *ghl_urb; struct timer_list ghl_poke_timer; - struct usb_ctrlrequest *ghl_cr; - u8 *ghl_databuf; }; static void sony_set_leds(struct sony_sc *sc); @@ -625,66 +624,54 @@ static inline void sony_schedule_work(struct sony_sc *sc, static void ghl_magic_poke_cb(struct urb *urb) { - if (urb) { - /* Free sc->ghl_cr and sc->ghl_databuf allocated in - * ghl_magic_poke() - */ - kfree(urb->setup_packet); - kfree(urb->transfer_buffer); - } + struct sony_sc *sc = urb->context; + + if (urb->status < 0) + hid_err(sc->hdev, "URB transfer failed : %d", urb->status); + + mod_timer(&sc->ghl_poke_timer, jiffies + GHL_GUITAR_POKE_INTERVAL*HZ); } static void ghl_magic_poke(struct timer_list *t) { + int ret; struct sony_sc *sc = from_timer(sc, t, ghl_poke_timer); - int ret; - unsigned int pipe; - struct urb *urb; - struct usb_device *usbdev = to_usb_device(sc->hdev->dev.parent->parent); - const u16 poke_size = - ARRAY_SIZE(ghl_ps3wiiu_magic_data); + ret = usb_submit_urb(sc->ghl_urb, GFP_ATOMIC); + if (ret < 0) + hid_err(sc->hdev, "usb_submit_urb failed: %d", ret); +} +static int ghl_init_urb(struct sony_sc *sc, struct usb_device *usbdev) +{ + struct usb_ctrlrequest *cr; + u16 poke_size; + u8 *databuf; + unsigned int pipe; + + poke_size = ARRAY_SIZE(ghl_ps3wiiu_magic_data); pipe = usb_sndctrlpipe(usbdev, 0); - if (!sc->ghl_cr) { - sc->ghl_cr = kzalloc(sizeof(*sc->ghl_cr), GFP_ATOMIC); - if (!sc->ghl_cr) - goto resched; - } + cr = devm_kzalloc(&sc->hdev->dev, sizeof(*cr), GFP_ATOMIC); + if (cr == NULL) + return -ENOMEM; - if (!sc->ghl_databuf) { - sc->ghl_databuf = kzalloc(poke_size, GFP_ATOMIC); - if (!sc->ghl_databuf) - goto resched; - } + databuf = devm_kzalloc(&sc->hdev->dev, poke_size, GFP_ATOMIC); + if (databuf == NULL) + return -ENOMEM; - urb = usb_alloc_urb(0, GFP_ATOMIC); - if (!urb) - goto resched; - - sc->ghl_cr->bRequestType = + cr->bRequestType = USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_OUT; - sc->ghl_cr->bRequest = USB_REQ_SET_CONFIGURATION; - sc->ghl_cr->wValue = cpu_to_le16(ghl_ps3wiiu_magic_value); - sc->ghl_cr->wIndex = 0; - sc->ghl_cr->wLength = cpu_to_le16(poke_size); - memcpy(sc->ghl_databuf, ghl_ps3wiiu_magic_data, poke_size); - + cr->bRequest = USB_REQ_SET_CONFIGURATION; + cr->wValue = cpu_to_le16(ghl_ps3wiiu_magic_value); + cr->wIndex = 0; + cr->wLength = cpu_to_le16(poke_size); + memcpy(databuf, ghl_ps3wiiu_magic_data, poke_size); usb_fill_control_urb( - urb, usbdev, pipe, - (unsigned char *) sc->ghl_cr, sc->ghl_databuf, - poke_size, ghl_magic_poke_cb, NULL); - ret = usb_submit_urb(urb, GFP_ATOMIC); - if (ret < 0) { - kfree(sc->ghl_databuf); - kfree(sc->ghl_cr); - } - usb_free_urb(urb); - -resched: - /* Reschedule for next time */ - mod_timer(&sc->ghl_poke_timer, jiffies + GHL_GUITAR_POKE_INTERVAL*HZ); + sc->ghl_urb, usbdev, pipe, + (unsigned char *) cr, databuf, poke_size, + ghl_magic_poke_cb, sc); + return 0; } static int guitar_mapping(struct hid_device *hdev, struct hid_input *hi, @@ -2981,6 +2968,7 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) int ret; unsigned long quirks = id->driver_data; struct sony_sc *sc; + struct usb_device *usbdev; unsigned int connect_mask = HID_CONNECT_DEFAULT; if (!strcmp(hdev->name, "FutureMax Dance Mat")) @@ -3000,6 +2988,7 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) sc->quirks = quirks; hid_set_drvdata(hdev, sc); sc->hdev = hdev; + usbdev = to_usb_device(sc->hdev->dev.parent->parent); ret = hid_parse(hdev); if (ret) { @@ -3042,6 +3031,15 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) } if (sc->quirks & GHL_GUITAR_PS3WIIU) { + sc->ghl_urb = usb_alloc_urb(0, GFP_ATOMIC); + if (!sc->ghl_urb) + return -ENOMEM; + ret = ghl_init_urb(sc, usbdev); + if (ret) { + hid_err(hdev, "error preparing URB\n"); + return ret; + } + timer_setup(&sc->ghl_poke_timer, ghl_magic_poke, 0); mod_timer(&sc->ghl_poke_timer, jiffies + GHL_GUITAR_POKE_INTERVAL*HZ); @@ -3054,8 +3052,10 @@ static void sony_remove(struct hid_device *hdev) { struct sony_sc *sc = hid_get_drvdata(hdev); - if (sc->quirks & GHL_GUITAR_PS3WIIU) + if (sc->quirks & GHL_GUITAR_PS3WIIU) { del_timer_sync(&sc->ghl_poke_timer); + usb_free_urb(sc->ghl_urb); + } hid_hw_close(hdev); diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c index f643b1cb112d..cdc7d82ae9ed 100644 --- a/drivers/hid/hid-thrustmaster.c +++ b/drivers/hid/hid-thrustmaster.c @@ -311,12 +311,13 @@ static int thrustmaster_probe(struct hid_device *hdev, const struct hid_device_i goto error4; } - tm_wheel->change_request = kzalloc(sizeof(struct usb_ctrlrequest), GFP_KERNEL); + tm_wheel->change_request = kmemdup(&change_request, + sizeof(struct usb_ctrlrequest), + GFP_KERNEL); if (!tm_wheel->change_request) { ret = -ENOMEM; goto error5; } - memcpy(tm_wheel->change_request, &change_request, sizeof(struct usb_ctrlrequest)); tm_wheel->usb_dev = interface_to_usbdev(to_usb_interface(hdev->dev.parent)); hid_set_drvdata(hdev, tm_wheel); diff --git a/drivers/hid/intel-ish-hid/Kconfig b/drivers/hid/intel-ish-hid/Kconfig index c6c9cfe2475e..689da84a520d 100644 --- a/drivers/hid/intel-ish-hid/Kconfig +++ b/drivers/hid/intel-ish-hid/Kconfig @@ -5,6 +5,7 @@ menu "Intel ISH HID support" config INTEL_ISH_HID tristate "Intel Integrated Sensor Hub" default n + depends on X86 select HID help The Integrated Sensor Hub (ISH) enables the ability to offload diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c index 47bbeb8b492b..45e0c7b1c9ec 100644 --- a/drivers/hid/intel-ish-hid/ipc/ipc.c +++ b/drivers/hid/intel-ish-hid/ipc/ipc.c @@ -544,7 +544,7 @@ static int ish_fw_reset_handler(struct ishtp_device *dev) #define TIMEOUT_FOR_HW_RDY_MS 300 /** - * ish_fw_reset_work_fn() - FW reset worker function + * fw_reset_work_fn() - FW reset worker function * @unused: not used * * Call ish_fw_reset_handler to complete FW reset @@ -889,6 +889,29 @@ static uint32_t ish_ipc_get_header(struct ishtp_device *dev, int length, return drbl_val; } +/** + * _dma_no_cache_snooping() + * + * Check on current platform, DMA supports cache snooping or not. + * This callback is used to notify uplayer driver if manully cache + * flush is needed when do DMA operation. + * + * Please pay attention to this callback implementation, if declare + * having cache snooping on a cache snooping not supported platform + * will cause uplayer driver receiving mismatched data; and if + * declare no cache snooping on a cache snooping supported platform + * will cause cache be flushed twice and performance hit. + * + * @dev: ishtp device pointer + * + * Return: false - has cache snooping capability + * true - no cache snooping, need manually cache flush + */ +static bool _dma_no_cache_snooping(struct ishtp_device *dev) +{ + return dev->pdev->device == EHL_Ax_DEVICE_ID; +} + static const struct ishtp_hw_ops ish_hw_ops = { .hw_reset = _ish_hw_reset, .ipc_reset = _ish_ipc_reset, @@ -897,7 +920,8 @@ static const struct ishtp_hw_ops ish_hw_ops = { .write = write_ipc_to_queue, .get_fw_status = _ish_read_fw_sts_reg, .sync_fw_clock = _ish_sync_fw_clock, - .ishtp_read_hdr = _ishtp_read_hdr + .ishtp_read_hdr = _ishtp_read_hdr, + .dma_no_cache_snooping = _dma_no_cache_snooping }; /** diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index a6d5173ac003..1c5039081db2 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -263,7 +263,6 @@ static void __maybe_unused ish_resume_handler(struct work_struct *work) struct pci_dev *pdev = to_pci_dev(ish_resume_device); struct ishtp_device *dev = pci_get_drvdata(pdev); uint32_t fwsts = dev->ops->get_fw_status(dev); - int ret; if (ish_should_leave_d0i3(pdev) && !dev->suspend_flag && IPC_IS_ISH_ILUP(fwsts)) { @@ -275,7 +274,7 @@ static void __maybe_unused ish_resume_handler(struct work_struct *work) /* Waiting to get resume response */ if (dev->resume_flag) - ret = wait_event_interruptible_timeout(dev->resume_wait, + wait_event_interruptible_timeout(dev->resume_wait, !dev->resume_flag, msecs_to_jiffies(WAIT_FOR_RESUME_ACK_MS)); diff --git a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c index 6cf59fd26ad7..1b486f262747 100644 --- a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c +++ b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c @@ -31,13 +31,13 @@ /** * enum ish_loader_commands - ISH loader host commands. - * LOADER_CMD_XFER_QUERY Query the Shim firmware loader for + * @LOADER_CMD_XFER_QUERY: Query the Shim firmware loader for * capabilities - * LOADER_CMD_XFER_FRAGMENT Transfer one firmware image fragment at a + * @LOADER_CMD_XFER_FRAGMENT: Transfer one firmware image fragment at a * time. The command may be executed * multiple times until the entire firmware * image is downloaded to SRAM. - * LOADER_CMD_START Start executing the main firmware. + * @LOADER_CMD_START: Start executing the main firmware. */ enum ish_loader_commands { LOADER_CMD_XFER_QUERY = 0, @@ -95,6 +95,7 @@ static int dma_buf_size_limit = 4 * PAGE_SIZE; /** * struct loader_msg_hdr - Header for ISH Loader commands. * @command: LOADER_CMD* commands. Bit 7 is the response. + * @reserved: Reserved space * @status: Command response status. Non 0, is error * condition. * @@ -173,16 +174,16 @@ struct loader_start { * struct response_info - Encapsulate firmware response related * information for passing between function * loader_cl_send() and process_recv() callback. - * @data Copy the data received from firmware here. - * @max_size Max size allocated for the @data buffer. If the + * @data: Copy the data received from firmware here. + * @max_size: Max size allocated for the @data buffer. If the * received data exceeds this value, we log an * error. - * @size Actual size of data received from firmware. - * @error Returns 0 for success, negative error code for a + * @size: Actual size of data received from firmware. + * @error: Returns 0 for success, negative error code for a * failure in function process_recv(). - * @received Set to true on receiving a valid firmware + * @received: Set to true on receiving a valid firmware * response to host command - * @wait_queue Wait queue for Host firmware loading where the + * @wait_queue: Wait queue for Host firmware loading where the * client sends message to ISH firmware and waits * for response */ @@ -195,13 +196,13 @@ struct response_info { wait_queue_head_t wait_queue; }; -/** +/* * struct ishtp_cl_data - Encapsulate per ISH-TP Client Data. * @work_ishtp_reset: Work queue for reset handling. * @work_fw_load: Work queue for host firmware loading. - * @flag_retry Flag for indicating host firmware loading should + * @flag_retry: Flag for indicating host firmware loading should * be retried. - * @retry_count Count the number of retries. + * @retry_count: Count the number of retries. * * This structure is used to store data per client. */ @@ -240,8 +241,8 @@ struct ishtp_cl_data { /** * get_firmware_variant() - Gets the filename of firmware image to be * loaded based on platform variant. - * @client_data Client data instance. - * @filename Returns firmware filename. + * @client_data: Client data instance. + * @filename: Returns firmware filename. * * Queries the firmware-name device property string. * @@ -266,11 +267,11 @@ static int get_firmware_variant(struct ishtp_cl_data *client_data, /** * loader_cl_send() Send message from host to firmware * @client_data: Client data instance - * @out_msg Message buffer to be sent to firmware - * @out_size Size of out going message - * @in_msg Message buffer where the incoming data copied. + * @out_msg: Message buffer to be sent to firmware + * @out_size: Size of out going message + * @in_msg: Message buffer where the incoming data copied. * This buffer is allocated by calling - * @in_size Max size of incoming message + * @in_size: Max size of incoming message * * Return: Number of bytes copied in the in_msg on success, negative * error code on failure. @@ -435,7 +436,7 @@ end: /** * loader_cl_event_cb() - bus driver callback for incoming message - * @device: Pointer to the ishtp client device for which this + * @cl_device: Pointer to the ishtp client device for which this * message is targeted * * Remove the packet from the list and process the message by calling @@ -455,7 +456,7 @@ static void loader_cl_event_cb(struct ishtp_cl_device *cl_device) /** * ish_query_loader_prop() - Query ISH Shim firmware loader * @client_data: Client data instance - * @fw: Poiner to firmware data struct in host memory + * @fw: Pointer to firmware data struct in host memory * @fw_info: Loader firmware properties * * This function queries the ISH Shim firmware loader for capabilities. @@ -536,7 +537,7 @@ static int ish_query_loader_prop(struct ishtp_cl_data *client_data, } /** - * ish_fw_xfer_ishtp() Loads ISH firmware using ishtp interface + * ish_fw_xfer_ishtp() - Loads ISH firmware using ishtp interface * @client_data: Client data instance * @fw: Pointer to firmware data struct in host memory * @@ -733,7 +734,7 @@ end_err_dma_buf_release: } /** - * ish_fw_start() Start executing ISH main firmware + * ish_fw_start() - Start executing ISH main firmware * @client_data: client data instance * * This function sends message to Shim firmware loader to start @@ -756,7 +757,7 @@ static int ish_fw_start(struct ishtp_cl_data *client_data) } /** - * load_fw_from_host() Loads ISH firmware from host + * load_fw_from_host() - Loads ISH firmware from host * @client_data: Client data instance * * This function loads the ISH firmware to ISH SRAM and starts execution @@ -1015,7 +1016,7 @@ static int loader_ishtp_cl_probe(struct ishtp_cl_device *cl_device) * * Return: 0 */ -static int loader_ishtp_cl_remove(struct ishtp_cl_device *cl_device) +static void loader_ishtp_cl_remove(struct ishtp_cl_device *cl_device) { struct ishtp_cl_data *client_data; struct ishtp_cl *loader_ishtp_cl = ishtp_get_drvdata(cl_device); @@ -1032,8 +1033,6 @@ static int loader_ishtp_cl_remove(struct ishtp_cl_device *cl_device) cancel_work_sync(&client_data->work_ishtp_reset); loader_deinit(loader_ishtp_cl); ishtp_put_device(cl_device); - - return 0; } /** diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c index 6ba944b40fdb..6b1fa971b33e 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c @@ -11,6 +11,11 @@ #include #include "ishtp-hid.h" +/* ISH Transport protocol (ISHTP in short) GUID */ +static const guid_t hid_ishtp_guid = + GUID_INIT(0x33AECD58, 0xB679, 0x4E54, + 0x9B, 0xD9, 0xA0, 0x4D, 0x34, 0xF0, 0xC2, 0x26); + /* Rx ring buffer pool size */ #define HID_CL_RX_RING_SIZE 32 #define HID_CL_TX_RING_SIZE 16 @@ -18,7 +23,7 @@ #define cl_data_to_dev(client_data) ishtp_device(client_data->cl_device) /** - * report_bad_packets() - Report bad packets + * report_bad_packet() - Report bad packets * @hid_ishtp_cl: Client instance to get stats * @recv_buf: Raw received host interface message * @cur_pos: Current position index in payload @@ -779,7 +784,7 @@ static void hid_ishtp_cl_reset_handler(struct work_struct *work) } } -void (*hid_print_trace)(void *unused, const char *format, ...); +ishtp_print_log ishtp_hid_print_trace; /** * hid_ishtp_cl_probe() - ISHTP client driver probe @@ -818,7 +823,7 @@ static int hid_ishtp_cl_probe(struct ishtp_cl_device *cl_device) INIT_WORK(&client_data->work, hid_ishtp_cl_reset_handler); - hid_print_trace = ishtp_trace_callback(cl_device); + ishtp_hid_print_trace = ishtp_trace_callback(cl_device); rv = hid_ishtp_cl_init(hid_ishtp_cl, 0); if (rv) { @@ -838,7 +843,7 @@ static int hid_ishtp_cl_probe(struct ishtp_cl_device *cl_device) * * Return: 0 */ -static int hid_ishtp_cl_remove(struct ishtp_cl_device *cl_device) +static void hid_ishtp_cl_remove(struct ishtp_cl_device *cl_device) { struct ishtp_cl *hid_ishtp_cl = ishtp_get_drvdata(cl_device); struct ishtp_cl_data *client_data = ishtp_get_client_data(hid_ishtp_cl); @@ -856,8 +861,6 @@ static int hid_ishtp_cl_remove(struct ishtp_cl_device *cl_device) hid_ishtp_cl = NULL; client_data->num_hid_devices = 0; - - return 0; } /** diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.c b/drivers/hid/intel-ish-hid/ishtp-hid.c index 393bed0abee9..14c271d7d8a9 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid.c @@ -254,7 +254,7 @@ err_hid_data: } /** - * ishtp_hid_probe() - Remove registered hid device + * ishtp_hid_remove() - Remove registered hid device * @client_data: client data pointer * * This function is used to destroy allocatd HID device. diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.h b/drivers/hid/intel-ish-hid/ishtp-hid.h index 5ffd0da3cf1f..f88443a7d935 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid.h +++ b/drivers/hid/intel-ish-hid/ishtp-hid.h @@ -16,14 +16,9 @@ #define IS_RESPONSE 0x80 /* Used to dump to Linux trace buffer, if enabled */ -extern void (*hid_print_trace)(void *unused, const char *format, ...); +extern ishtp_print_log ishtp_hid_print_trace; #define hid_ishtp_trace(client, ...) \ - (hid_print_trace)(NULL, __VA_ARGS__) - -/* ISH Transport protocol (ISHTP in short) GUID */ -static const guid_t hid_ishtp_guid = - GUID_INIT(0x33AECD58, 0xB679, 0x4E54, - 0x9B, 0xD9, 0xA0, 0x4D, 0x34, 0xF0, 0xC2, 0x26); + (ishtp_hid_print_trace)(NULL, __VA_ARGS__) /* ISH HID message structure */ struct hostif_msg_hdr { diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index bba29cd36d29..f0802b047ed8 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -164,6 +164,7 @@ EXPORT_SYMBOL(ishtp_fw_cl_get_client); /** * ishtp_get_fw_client_id() - Get fw client id + * @fw_client: firmware client used to fetch the ID * * This interface is used to reset HW get FW client id. * @@ -257,24 +258,17 @@ static int ishtp_cl_bus_match(struct device *dev, struct device_driver *drv) static int ishtp_cl_device_remove(struct device *dev) { struct ishtp_cl_device *device = to_ishtp_cl_device(dev); - struct ishtp_cl_driver *driver; - - if (!device || !dev->driver) - return 0; + struct ishtp_cl_driver *driver = to_ishtp_cl_driver(dev->driver); if (device->event_cb) { device->event_cb = NULL; cancel_work_sync(&device->event_work); } - driver = to_ishtp_cl_driver(dev->driver); - if (!driver->remove) { - dev->driver = NULL; + if (driver->remove) + driver->remove(device); - return 0; - } - - return driver->remove(device); + return 0; } /** @@ -842,6 +836,7 @@ int ishtp_use_dma_transfer(void) /** * ishtp_device() - Return device pointer + * @device: ISH-TP client device instance * * This interface is used to return device pointer from ishtp_cl_device * instance. @@ -858,6 +853,7 @@ EXPORT_SYMBOL(ishtp_device); * ishtp_get_pci_device() - Return PCI device dev pointer * This interface is used to return PCI device pointer * from ishtp_cl_device instance. + * @device: ISH-TP client device instance * * Return: device *. */ @@ -869,12 +865,13 @@ EXPORT_SYMBOL(ishtp_get_pci_device); /** * ishtp_trace_callback() - Return trace callback + * @cl_device: ISH-TP client device instance * * This interface is used to return trace callback function pointer. * - * Return: void *. + * Return: *ishtp_print_log() */ -void *ishtp_trace_callback(struct ishtp_cl_device *cl_device) +ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device) { return cl_device->ishtp_dev->print_log; } @@ -882,6 +879,7 @@ EXPORT_SYMBOL(ishtp_trace_callback); /** * ish_hw_reset() - Call HW reset IPC callback + * @dev: ISHTP device instance * * This interface is used to reset HW in case of error. * diff --git a/drivers/hid/intel-ish-hid/ishtp/client.c b/drivers/hid/intel-ish-hid/ishtp/client.c index 1cc157126fce..405e0d5212cc 100644 --- a/drivers/hid/intel-ish-hid/ishtp/client.c +++ b/drivers/hid/intel-ish-hid/ishtp/client.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "hbm.h" #include "client.h" @@ -111,7 +112,7 @@ static void ishtp_cl_init(struct ishtp_cl *cl, struct ishtp_device *dev) /** * ishtp_cl_allocate() - allocates client structure and sets it up. - * @dev: ishtp device + * @cl_device: ishtp client device * * Allocate memory for new client device and call to initialize each field. * @@ -263,7 +264,6 @@ EXPORT_SYMBOL(ishtp_cl_unlink); int ishtp_cl_disconnect(struct ishtp_cl *cl) { struct ishtp_device *dev; - int err; if (WARN_ON(!cl || !cl->dev)) return -ENODEV; @@ -283,7 +283,7 @@ int ishtp_cl_disconnect(struct ishtp_cl *cl) return -ENODEV; } - err = wait_event_interruptible_timeout(cl->wait_ctrl_res, + wait_event_interruptible_timeout(cl->wait_ctrl_res, (dev->dev_state != ISHTP_DEV_ENABLED || cl->state == ISHTP_CL_DISCONNECTED), ishtp_secs_to_jiffies(ISHTP_CL_CONNECT_TIMEOUT)); @@ -773,6 +773,14 @@ static void ishtp_cl_send_msg_dma(struct ishtp_device *dev, /* write msg to dma buf */ memcpy(msg_addr, cl_msg->send_buf.data, cl_msg->send_buf.size); + /* + * if current fw don't support cache snooping, driver have to + * flush the cache manually. + */ + if (dev->ops->dma_no_cache_snooping && + dev->ops->dma_no_cache_snooping(dev)) + clflush_cache_range(msg_addr, cl_msg->send_buf.size); + /* send dma_xfer hbm msg */ off = msg_addr - (unsigned char *)dev->ishtp_host_dma_tx_buf; ishtp_hbm_hdr(&hdr, sizeof(struct dma_xfer_hbm)); @@ -997,6 +1005,15 @@ void recv_ishtp_cl_msg_dma(struct ishtp_device *dev, void *msg, } buffer = rb->buffer.data; + + /* + * if current fw don't support cache snooping, driver have to + * flush the cache manually. + */ + if (dev->ops->dma_no_cache_snooping && + dev->ops->dma_no_cache_snooping(dev)) + clflush_cache_range(msg, hbm->msg_length); + memcpy(buffer, msg, hbm->msg_length); rb->buf_idx = hbm->msg_length; diff --git a/drivers/hid/intel-ish-hid/ishtp/hbm.c b/drivers/hid/intel-ish-hid/ishtp/hbm.c index 30a91d068306..9c031a06e4c4 100644 --- a/drivers/hid/intel-ish-hid/ishtp/hbm.c +++ b/drivers/hid/intel-ish-hid/ishtp/hbm.c @@ -398,7 +398,7 @@ static void ishtp_hbm_cl_connect_res(struct ishtp_device *dev, } /** - * ishtp_client_disconnect_request() - Receive disconnect request + * ishtp_hbm_fw_disconnect_req() - Receive disconnect request * @dev: ISHTP device instance * @disconnect_req: disconnect request structure * @@ -430,7 +430,7 @@ static void ishtp_hbm_fw_disconnect_req(struct ishtp_device *dev, } /** - * ishtp_hbm_dma_xfer_ack(() - Receive transfer ACK + * ishtp_hbm_dma_xfer_ack() - Receive transfer ACK * @dev: ISHTP device instance * @dma_xfer: HBM transfer message * @@ -914,7 +914,7 @@ static inline void fix_cl_hdr(struct ishtp_msg_hdr *hdr, size_t length, /*** Suspend and resume notification ***/ static uint32_t current_state; -static uint32_t supported_states = 0 | SUSPEND_STATE_BIT; +static uint32_t supported_states = SUSPEND_STATE_BIT | CONNECTED_STANDBY_STATE_BIT; /** * ishtp_send_suspend() - Send suspend message to FW @@ -933,7 +933,7 @@ void ishtp_send_suspend(struct ishtp_device *dev) memset(&state_status_msg, 0, len); state_status_msg.hdr.cmd = SYSTEM_STATE_STATUS; state_status_msg.supported_states = supported_states; - current_state |= SUSPEND_STATE_BIT; + current_state |= (SUSPEND_STATE_BIT | CONNECTED_STANDBY_STATE_BIT); dev->print_log(dev, "%s() sends SUSPEND notification\n", __func__); state_status_msg.states_status = current_state; @@ -959,7 +959,7 @@ void ishtp_send_resume(struct ishtp_device *dev) memset(&state_status_msg, 0, len); state_status_msg.hdr.cmd = SYSTEM_STATE_STATUS; state_status_msg.supported_states = supported_states; - current_state &= ~SUSPEND_STATE_BIT; + current_state &= ~(CONNECTED_STANDBY_STATE_BIT | SUSPEND_STATE_BIT); dev->print_log(dev, "%s() sends RESUME notification\n", __func__); state_status_msg.states_status = current_state; diff --git a/drivers/hid/intel-ish-hid/ishtp/hbm.h b/drivers/hid/intel-ish-hid/ishtp/hbm.h index 7c445b203f2a..08f3f3ceb18c 100644 --- a/drivers/hid/intel-ish-hid/ishtp/hbm.h +++ b/drivers/hid/intel-ish-hid/ishtp/hbm.h @@ -235,6 +235,7 @@ struct dma_xfer_hbm { #define SYSTEM_STATE_QUERY_SUBSCRIBERS 0x3 #define SYSTEM_STATE_STATE_CHANGE_REQ 0x4 /*indicates suspend and resume states*/ +#define CONNECTED_STANDBY_STATE_BIT (1<<0) #define SUSPEND_STATE_BIT (1<<1) struct ish_system_states_header { diff --git a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h index 1cc6364aa957..32142c7d9a04 100644 --- a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h +++ b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h @@ -10,6 +10,7 @@ #include #include +#include #include "bus.h" #include "hbm.h" @@ -118,6 +119,7 @@ struct ishtp_hw_ops { unsigned long buffer_length); uint32_t (*get_fw_status)(struct ishtp_device *dev); void (*sync_fw_clock)(struct ishtp_device *dev); + bool (*dma_no_cache_snooping)(struct ishtp_device *dev); }; /** @@ -202,8 +204,7 @@ struct ishtp_device { uint64_t ishtp_host_dma_rx_buf_phys; /* Dump to trace buffers if enabled*/ - __printf(2, 3) void (*print_log)(struct ishtp_device *dev, - const char *format, ...); + ishtp_print_log print_log; /* Debug stats */ unsigned int ipc_rx_cnt; diff --git a/drivers/hid/surface-hid/surface_hid.c b/drivers/hid/surface-hid/surface_hid.c index 3477b31611ae..a3a70e4f3f6c 100644 --- a/drivers/hid/surface-hid/surface_hid.c +++ b/drivers/hid/surface-hid/surface_hid.c @@ -143,7 +143,7 @@ static int ssam_hid_get_raw_report(struct surface_hid_device *shid, u8 rprt_id, rqst.target_id = shid->uid.target; rqst.instance_id = shid->uid.instance; rqst.command_id = SURFACE_HID_CID_GET_FEATURE_REPORT; - rqst.flags = 0; + rqst.flags = SSAM_REQUEST_HAS_RESPONSE; rqst.length = sizeof(rprt_id); rqst.payload = &rprt_id; diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 4e9077363c96..06130dc431a0 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -1304,6 +1304,13 @@ static int usbhid_idle(struct hid_device *hid, int report, int idle, return hid_set_idle(dev, ifnum, report, idle); } +static bool usbhid_may_wakeup(struct hid_device *hid) +{ + struct usb_device *dev = hid_to_usb_dev(hid); + + return device_may_wakeup(&dev->dev); +} + struct hid_ll_driver usb_hid_driver = { .parse = usbhid_parse, .start = usbhid_start, @@ -1316,6 +1323,7 @@ struct hid_ll_driver usb_hid_driver = { .raw_request = usbhid_raw_request, .output_report = usbhid_output_report, .idle = usbhid_idle, + .may_wakeup = usbhid_may_wakeup, }; EXPORT_SYMBOL_GPL(usb_hid_driver); diff --git a/drivers/hid/usbhid/usbkbd.c b/drivers/hid/usbhid/usbkbd.c index e22434dfc9ef..df02002066ce 100644 --- a/drivers/hid/usbhid/usbkbd.c +++ b/drivers/hid/usbhid/usbkbd.c @@ -239,11 +239,11 @@ static int usb_kbd_alloc_mem(struct usb_device *dev, struct usb_kbd *kbd) return -1; if (!(kbd->led = usb_alloc_urb(0, GFP_KERNEL))) return -1; - if (!(kbd->new = usb_alloc_coherent(dev, 8, GFP_ATOMIC, &kbd->new_dma))) + if (!(kbd->new = usb_alloc_coherent(dev, 8, GFP_KERNEL, &kbd->new_dma))) return -1; if (!(kbd->cr = kmalloc(sizeof(struct usb_ctrlrequest), GFP_KERNEL))) return -1; - if (!(kbd->leds = usb_alloc_coherent(dev, 1, GFP_ATOMIC, &kbd->leds_dma))) + if (!(kbd->leds = usb_alloc_coherent(dev, 1, GFP_KERNEL, &kbd->leds_dma))) return -1; return 0; diff --git a/drivers/hid/usbhid/usbmouse.c b/drivers/hid/usbhid/usbmouse.c index 073127e65ac1..c89332017d5d 100644 --- a/drivers/hid/usbhid/usbmouse.c +++ b/drivers/hid/usbhid/usbmouse.c @@ -130,7 +130,7 @@ static int usb_mouse_probe(struct usb_interface *intf, const struct usb_device_i if (!mouse || !input_dev) goto fail1; - mouse->data = usb_alloc_coherent(dev, 8, GFP_ATOMIC, &mouse->data_dma); + mouse->data = usb_alloc_coherent(dev, 8, GFP_KERNEL, &mouse->data_dma); if (!mouse->data) goto fail1; diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h index 71c886245dbf..8f16654eca09 100644 --- a/drivers/hid/wacom_wac.h +++ b/drivers/hid/wacom_wac.h @@ -122,7 +122,7 @@ #define WACOM_HID_WD_TOUCHONOFF (WACOM_HID_UP_WACOMDIGITIZER | 0x0454) #define WACOM_HID_WD_BATTERY_LEVEL (WACOM_HID_UP_WACOMDIGITIZER | 0x043b) #define WACOM_HID_WD_EXPRESSKEY00 (WACOM_HID_UP_WACOMDIGITIZER | 0x0910) -#define WACOM_HID_WD_EXPRESSKEYCAP00 (WACOM_HID_UP_WACOMDIGITIZER | 0x0950) +#define WACOM_HID_WD_EXPRESSKEYCAP00 (WACOM_HID_UP_WACOMDIGITIZER | 0x0940) #define WACOM_HID_WD_MODE_CHANGE (WACOM_HID_UP_WACOMDIGITIZER | 0x0980) #define WACOM_HID_WD_MUTE_DEVICE (WACOM_HID_UP_WACOMDIGITIZER | 0x0981) #define WACOM_HID_WD_CONTROLPANEL (WACOM_HID_UP_WACOMDIGITIZER | 0x0982) diff --git a/drivers/hv/Makefile b/drivers/hv/Makefile index 94daf8240c95..d76df5c8c2a9 100644 --- a/drivers/hv/Makefile +++ b/drivers/hv/Makefile @@ -11,3 +11,6 @@ hv_vmbus-y := vmbus_drv.o \ channel_mgmt.o ring_buffer.o hv_trace.o hv_vmbus-$(CONFIG_HYPERV_TESTING) += hv_debugfs.o hv_utils-y := hv_util.o hv_kvp.o hv_snapshot.o hv_fcopy.o hv_utils_transport.o + +# Code that must be built-in +obj-$(subst m,y,$(CONFIG_HYPERV)) += hv_common.o diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index c2635e913a92..f3761c73b074 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -662,12 +662,15 @@ static int __vmbus_open(struct vmbus_channel *newchannel, newchannel->onchannel_callback = onchannelcallback; newchannel->channel_callback_context = context; - err = hv_ringbuffer_init(&newchannel->outbound, page, send_pages); + if (!newchannel->max_pkt_size) + newchannel->max_pkt_size = VMBUS_DEFAULT_MAX_PKT_SIZE; + + err = hv_ringbuffer_init(&newchannel->outbound, page, send_pages, 0); if (err) goto error_clean_ring; - err = hv_ringbuffer_init(&newchannel->inbound, - &page[send_pages], recv_pages); + err = hv_ringbuffer_init(&newchannel->inbound, &page[send_pages], + recv_pages, newchannel->max_pkt_size); if (err) goto error_clean_ring; @@ -1186,15 +1189,14 @@ EXPORT_SYMBOL_GPL(vmbus_recvpacket_raw); * vmbus_next_request_id - Returns a new request id. It is also * the index at which the guest memory address is stored. * Uses a spin lock to avoid race conditions. - * @rqstor: Pointer to the requestor struct + * @channel: Pointer to the VMbus channel struct * @rqst_add: Guest memory address to be stored in the array */ -u64 vmbus_next_request_id(struct vmbus_requestor *rqstor, u64 rqst_addr) +u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr) { + struct vmbus_requestor *rqstor = &channel->requestor; unsigned long flags; u64 current_id; - const struct vmbus_channel *channel = - container_of(rqstor, const struct vmbus_channel, requestor); /* Check rqstor has been initialized */ if (!channel->rqstor_size) @@ -1228,16 +1230,15 @@ EXPORT_SYMBOL_GPL(vmbus_next_request_id); /* * vmbus_request_addr - Returns the memory address stored at @trans_id * in @rqstor. Uses a spin lock to avoid race conditions. - * @rqstor: Pointer to the requestor struct + * @channel: Pointer to the VMbus channel struct * @trans_id: Request id sent back from Hyper-V. Becomes the requestor's * next request id. */ -u64 vmbus_request_addr(struct vmbus_requestor *rqstor, u64 trans_id) +u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id) { + struct vmbus_requestor *rqstor = &channel->requestor; unsigned long flags; u64 req_addr; - const struct vmbus_channel *channel = - container_of(rqstor, const struct vmbus_channel, requestor); /* Check rqstor has been initialized */ if (!channel->rqstor_size) diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 311cd005b3be..5e479d54918c 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -232,8 +232,10 @@ int vmbus_connect(void) */ for (i = 0; ; i++) { - if (i == ARRAY_SIZE(vmbus_versions)) + if (i == ARRAY_SIZE(vmbus_versions)) { + ret = -EDOM; goto cleanup; + } version = vmbus_versions[i]; if (version > max_version) diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 58af84e30144..7f11ea07d698 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -1010,7 +1010,6 @@ static void hot_add_req(struct work_struct *dummy) * that need to be hot-added while ensuring the alignment * and size requirements of Linux as it relates to hot-add. */ - region_start = pg_start; region_size = (pfn_cnt / HA_CHUNK) * HA_CHUNK; if (pfn_cnt % HA_CHUNK) region_size += HA_CHUNK; diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c new file mode 100644 index 000000000000..7f42da98d377 --- /dev/null +++ b/drivers/hv/hv_common.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Architecture neutral utility routines for interacting with + * Hyper-V. This file is specifically for code that must be + * built-in to the kernel image when CONFIG_HYPERV is set + * (vs. being in a module) because it is called from architecture + * specific code under arch/. + * + * Copyright (C) 2021, Microsoft, Inc. + * + * Author : Michael Kelley + */ + +#include +#include +#include +#include +#include + + +/* Bit mask of the extended capability to query: see HV_EXT_CAPABILITY_xxx */ +bool hv_query_ext_cap(u64 cap_query) +{ + /* + * The address of the 'hv_extended_cap' variable will be used as an + * output parameter to the hypercall below and so it should be + * compatible with 'virt_to_phys'. Which means, it's address should be + * directly mapped. Use 'static' to keep it compatible; stack variables + * can be virtually mapped, making them incompatible with + * 'virt_to_phys'. + * Hypercall input/output addresses should also be 8-byte aligned. + */ + static u64 hv_extended_cap __aligned(8); + static bool hv_extended_cap_queried; + u64 status; + + /* + * Querying extended capabilities is an extended hypercall. Check if the + * partition supports extended hypercall, first. + */ + if (!(ms_hyperv.priv_high & HV_ENABLE_EXTENDED_HYPERCALLS)) + return false; + + /* Extended capabilities do not change at runtime. */ + if (hv_extended_cap_queried) + return hv_extended_cap & cap_query; + + status = hv_do_hypercall(HV_EXT_CALL_QUERY_CAPABILITIES, NULL, + &hv_extended_cap); + + /* + * The query extended capabilities hypercall should not fail under + * any normal circumstances. Avoid repeatedly making the hypercall, on + * error. + */ + hv_extended_cap_queried = true; + if (!hv_result_success(status)) { + pr_err("Hyper-V: Extended query capabilities hypercall failed 0x%llx\n", + status); + return false; + } + + return hv_extended_cap & cap_query; +} +EXPORT_SYMBOL_GPL(hv_query_ext_cap); diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c index 59ce85e00a02..660036da7449 100644 --- a/drivers/hv/hv_fcopy.c +++ b/drivers/hv/hv_fcopy.c @@ -349,6 +349,7 @@ int hv_fcopy_init(struct hv_util_service *srv) { recv_buffer = srv->recv_buffer; fcopy_transaction.recv_channel = srv->channel; + fcopy_transaction.recv_channel->max_pkt_size = HV_HYP_PAGE_SIZE * 2; /* * When this driver loads, the user level daemon that diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index b49962d312ce..c698592b83e4 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -757,6 +757,7 @@ hv_kvp_init(struct hv_util_service *srv) { recv_buffer = srv->recv_buffer; kvp_transaction.recv_channel = srv->channel; + kvp_transaction.recv_channel->max_pkt_size = HV_HYP_PAGE_SIZE * 4; /* * When this driver loads, the user level daemon that diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index e4aefeb330da..136576cba26f 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -750,8 +750,8 @@ static int hv_timesync_init(struct hv_util_service *srv) */ hv_ptp_clock = ptp_clock_register(&ptp_hyperv_info, NULL); if (IS_ERR_OR_NULL(hv_ptp_clock)) { - pr_err("cannot register PTP clock: %ld\n", - PTR_ERR(hv_ptp_clock)); + pr_err("cannot register PTP clock: %d\n", + PTR_ERR_OR_ZERO(hv_ptp_clock)); hv_ptp_clock = NULL; } diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 9416e09ebd58..42f3d9d123a1 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -174,7 +174,7 @@ extern int hv_synic_cleanup(unsigned int cpu); void hv_ringbuffer_pre_init(struct vmbus_channel *channel); int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, - struct page *pages, u32 pagecnt); + struct page *pages, u32 pagecnt, u32 max_pkt_size); void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info); diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 374f8afbf8a5..2aee356840a2 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -181,7 +181,7 @@ void hv_ringbuffer_pre_init(struct vmbus_channel *channel) /* Initialize the ring buffer. */ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, - struct page *pages, u32 page_cnt) + struct page *pages, u32 page_cnt, u32 max_pkt_size) { int i; struct page **pages_wraparound; @@ -223,6 +223,14 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, sizeof(struct hv_ring_buffer); ring_info->priv_read_index = 0; + /* Initialize buffer that holds copies of incoming packets */ + if (max_pkt_size) { + ring_info->pkt_buffer = kzalloc(max_pkt_size, GFP_KERNEL); + if (!ring_info->pkt_buffer) + return -ENOMEM; + ring_info->pkt_buffer_size = max_pkt_size; + } + spin_lock_init(&ring_info->ring_lock); return 0; @@ -235,6 +243,9 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info) vunmap(ring_info->ring_buffer); ring_info->ring_buffer = NULL; mutex_unlock(&ring_info->ring_buffer_mutex); + + kfree(ring_info->pkt_buffer); + ring_info->pkt_buffer_size = 0; } /* Write to the ring buffer. */ @@ -301,10 +312,12 @@ int hv_ringbuffer_write(struct vmbus_channel *channel, */ if (desc->flags == VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED) { - rqst_id = vmbus_next_request_id(&channel->requestor, requestid); - if (rqst_id == VMBUS_RQST_ERROR) { - spin_unlock_irqrestore(&outring_info->ring_lock, flags); - return -EAGAIN; + if (channel->next_request_id_callback != NULL) { + rqst_id = channel->next_request_id_callback(channel, requestid); + if (rqst_id == VMBUS_RQST_ERROR) { + spin_unlock_irqrestore(&outring_info->ring_lock, flags); + return -EAGAIN; + } } } desc = hv_get_ring_buffer(outring_info) + old_write; @@ -332,7 +345,8 @@ int hv_ringbuffer_write(struct vmbus_channel *channel, if (channel->rescind) { if (rqst_id != VMBUS_NO_RQSTOR) { /* Reclaim request ID to avoid leak of IDs */ - vmbus_request_addr(&channel->requestor, rqst_id); + if (channel->request_addr_callback != NULL) + channel->request_addr_callback(channel, rqst_id); } return -ENODEV; } @@ -375,7 +389,7 @@ int hv_ringbuffer_read(struct vmbus_channel *channel, memcpy(buffer, (const char *)desc + offset, packetlen); /* Advance ring index to next packet descriptor */ - __hv_pkt_iter_next(channel, desc); + __hv_pkt_iter_next(channel, desc, true); /* Notify host of update */ hv_pkt_iter_close(channel); @@ -401,6 +415,22 @@ static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi) return (rbi->ring_datasize - priv_read_loc) + write_loc; } +/* + * Get first vmbus packet without copying it out of the ring buffer + */ +struct vmpacket_descriptor *hv_pkt_iter_first_raw(struct vmbus_channel *channel) +{ + struct hv_ring_buffer_info *rbi = &channel->inbound; + + hv_debug_delay_test(channel, MESSAGE_DELAY); + + if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor)) + return NULL; + + return (struct vmpacket_descriptor *)(hv_get_ring_buffer(rbi) + rbi->priv_read_index); +} +EXPORT_SYMBOL_GPL(hv_pkt_iter_first_raw); + /* * Get first vmbus packet from ring buffer after read_index * @@ -409,17 +439,49 @@ static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi) struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel) { struct hv_ring_buffer_info *rbi = &channel->inbound; - struct vmpacket_descriptor *desc; + struct vmpacket_descriptor *desc, *desc_copy; + u32 bytes_avail, pkt_len, pkt_offset; - hv_debug_delay_test(channel, MESSAGE_DELAY); - if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor)) + desc = hv_pkt_iter_first_raw(channel); + if (!desc) return NULL; - desc = hv_get_ring_buffer(rbi) + rbi->priv_read_index; - if (desc) - prefetch((char *)desc + (desc->len8 << 3)); + bytes_avail = min(rbi->pkt_buffer_size, hv_pkt_iter_avail(rbi)); - return desc; + /* + * Ensure the compiler does not use references to incoming Hyper-V values (which + * could change at any moment) when reading local variables later in the code + */ + pkt_len = READ_ONCE(desc->len8) << 3; + pkt_offset = READ_ONCE(desc->offset8) << 3; + + /* + * If pkt_len is invalid, set it to the smaller of hv_pkt_iter_avail() and + * rbi->pkt_buffer_size + */ + if (pkt_len < sizeof(struct vmpacket_descriptor) || pkt_len > bytes_avail) + pkt_len = bytes_avail; + + /* + * If pkt_offset is invalid, arbitrarily set it to + * the size of vmpacket_descriptor + */ + if (pkt_offset < sizeof(struct vmpacket_descriptor) || pkt_offset > pkt_len) + pkt_offset = sizeof(struct vmpacket_descriptor); + + /* Copy the Hyper-V packet out of the ring buffer */ + desc_copy = (struct vmpacket_descriptor *)rbi->pkt_buffer; + memcpy(desc_copy, desc, pkt_len); + + /* + * Hyper-V could still change len8 and offset8 after the earlier read. + * Ensure that desc_copy has legal values for len8 and offset8 that + * are consistent with the copy we just made + */ + desc_copy->len8 = pkt_len >> 3; + desc_copy->offset8 = pkt_offset >> 3; + + return desc_copy; } EXPORT_SYMBOL_GPL(hv_pkt_iter_first); @@ -431,7 +493,8 @@ EXPORT_SYMBOL_GPL(hv_pkt_iter_first); */ struct vmpacket_descriptor * __hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *desc) + const struct vmpacket_descriptor *desc, + bool copy) { struct hv_ring_buffer_info *rbi = &channel->inbound; u32 packetlen = desc->len8 << 3; @@ -444,7 +507,7 @@ __hv_pkt_iter_next(struct vmbus_channel *channel, rbi->priv_read_index -= dsize; /* more data? */ - return hv_pkt_iter_first(channel); + return copy ? hv_pkt_iter_first(channel) : hv_pkt_iter_first_raw(channel); } EXPORT_SYMBOL_GPL(__hv_pkt_iter_next); diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 8ceaa88dd78f..6f0aa0ed3241 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -259,8 +259,8 @@ static acpi_status i2c_acpi_add_device(acpi_handle handle, u32 level, */ void i2c_acpi_register_devices(struct i2c_adapter *adap) { + struct acpi_device *adev; acpi_status status; - acpi_handle handle; if (!has_acpi_companion(&adap->dev)) return; @@ -275,11 +275,11 @@ void i2c_acpi_register_devices(struct i2c_adapter *adap) if (!adap->dev.parent) return; - handle = ACPI_HANDLE(adap->dev.parent); - if (!handle) + adev = ACPI_COMPANION(adap->dev.parent); + if (!adev) return; - acpi_walk_dep_device_list(handle); + acpi_dev_clear_dependencies(adev); } static const struct acpi_device_id i2c_acpi_force_400khz_device_ids[] = { diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index ec1b9d306ba6..e6c543b5ee1d 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -1484,6 +1484,36 @@ static void __init sklh_idle_state_table_update(void) skl_cstates[6].flags |= CPUIDLE_FLAG_UNUSABLE; /* C9-SKL */ } +/** + * skx_idle_state_table_update - Adjust the Sky Lake/Cascade Lake + * idle states table. + */ +static void __init skx_idle_state_table_update(void) +{ + unsigned long long msr; + + rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, msr); + + /* + * 000b: C0/C1 (no package C-state support) + * 001b: C2 + * 010b: C6 (non-retention) + * 011b: C6 (retention) + * 111b: No Package C state limits. + */ + if ((msr & 0x7) < 2) { + /* + * Uses the CC6 + PC0 latency and 3 times of + * latency for target_residency if the PC6 + * is disabled in BIOS. This is consistent + * with how intel_idle driver uses _CST + * to set the target_residency. + */ + skx_cstates[2].exit_latency = 92; + skx_cstates[2].target_residency = 276; + } +} + static bool __init intel_idle_verify_cstate(unsigned int mwait_hint) { unsigned int mwait_cstate = MWAIT_HINT2CSTATE(mwait_hint) + 1; @@ -1515,6 +1545,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv) case INTEL_FAM6_SKYLAKE: sklh_idle_state_table_update(); break; + case INTEL_FAM6_SKYLAKE_X: + skx_idle_state_table_update(); + break; } for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) { diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index b496f30ce066..364f69cd620f 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -1423,7 +1423,7 @@ static enum i40iw_status_code i40iw_save_msix_info(struct i40iw_device *iwdev, struct i40e_qv_info *iw_qvinfo; u32 ceq_idx; u32 i; - u32 size; + size_t size; if (!ldev->msix_count) { i40iw_pr_err("No MSI-X vectors\n"); @@ -1433,8 +1433,7 @@ static enum i40iw_status_code i40iw_save_msix_info(struct i40iw_device *iwdev, iwdev->msix_count = ldev->msix_count; size = sizeof(struct i40iw_msix_vector) * iwdev->msix_count; - size += sizeof(struct i40e_qvlist_info); - size += sizeof(struct i40e_qv_info) * iwdev->msix_count - 1; + size += struct_size(iw_qvlist, qv_info, iwdev->msix_count); iwdev->iw_msixtbl = kzalloc(size, GFP_KERNEL); if (!iwdev->iw_msixtbl) diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c index 18ee2f293825..5fbc0a8454b9 100644 --- a/drivers/infiniband/hw/mlx5/fs.c +++ b/drivers/infiniband/hw/mlx5/fs.c @@ -2285,6 +2285,7 @@ static int mlx5_ib_flow_action_create_packet_reformat_ctx( u8 ft_type, u8 dv_prt, void *in, size_t len) { + struct mlx5_pkt_reformat_params reformat_params; enum mlx5_flow_namespace_type namespace; u8 prm_prt; int ret; @@ -2297,9 +2298,13 @@ static int mlx5_ib_flow_action_create_packet_reformat_ctx( if (ret) return ret; + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = prm_prt; + reformat_params.size = len; + reformat_params.data = in; maction->flow_action_raw.pkt_reformat = - mlx5_packet_reformat_alloc(dev->mdev, prm_prt, len, - in, namespace); + mlx5_packet_reformat_alloc(dev->mdev, &reformat_params, + namespace); if (IS_ERR(maction->flow_action_raw.pkt_reformat)) { ret = PTR_ERR(maction->flow_action_raw.pkt_reformat); return ret; diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 782b2af8f211..1338c11fd121 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -1559,12 +1559,16 @@ int mlx5r_odp_create_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq) } eq->irq_nb.notifier_call = mlx5_ib_eq_pf_int; - param = (struct mlx5_eq_param){ - .irq_index = 0, + param = (struct mlx5_eq_param) { .nent = MLX5_IB_NUM_PF_EQE, }; param.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_FAULT; + if (!zalloc_cpumask_var(¶m.affinity, GFP_KERNEL)) { + err = -ENOMEM; + goto err_wq; + } eq->core = mlx5_eq_create_generic(dev->mdev, ¶m); + free_cpumask_var(param.affinity); if (IS_ERR(eq->core)) { err = PTR_ERR(eq->core); goto err_wq; diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index c682b028f0a2..4f53d3c57e69 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -178,51 +178,6 @@ static const unsigned long goodix_irq_flags[] = { IRQ_TYPE_LEVEL_HIGH, }; -/* - * Those tablets have their coordinates origin at the bottom right - * of the tablet, as if rotated 180 degrees - */ -static const struct dmi_system_id rotated_screen[] = { -#if defined(CONFIG_DMI) && defined(CONFIG_X86) - { - .ident = "Teclast X89", - .matches = { - /* tPAD is too generic, also match on bios date */ - DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"), - DMI_MATCH(DMI_BOARD_NAME, "tPAD"), - DMI_MATCH(DMI_BIOS_DATE, "12/19/2014"), - }, - }, - { - .ident = "Teclast X98 Pro", - .matches = { - /* - * Only match BIOS date, because the manufacturers - * BIOS does not report the board name at all - * (sometimes)... - */ - DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"), - DMI_MATCH(DMI_BIOS_DATE, "10/28/2015"), - }, - }, - { - .ident = "WinBook TW100", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "WinBook"), - DMI_MATCH(DMI_PRODUCT_NAME, "TW100") - } - }, - { - .ident = "WinBook TW700", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "WinBook"), - DMI_MATCH(DMI_PRODUCT_NAME, "TW700") - }, - }, -#endif - {} -}; - static const struct dmi_system_id nine_bytes_report[] = { #if defined(CONFIG_DMI) && defined(CONFIG_X86) { @@ -1123,13 +1078,6 @@ static int goodix_configure_dev(struct goodix_ts_data *ts) ABS_MT_POSITION_Y, ts->prop.max_y); } - if (dmi_check_system(rotated_screen)) { - ts->prop.invert_x = true; - ts->prop.invert_y = true; - dev_dbg(&ts->client->dev, - "Applying '180 degrees rotated screen' quirk\n"); - } - if (dmi_check_system(nine_bytes_report)) { ts->contact_size = 9; diff --git a/drivers/irqchip/exynos-combiner.c b/drivers/irqchip/exynos-combiner.c index 0b85d9a3fbff..552aa04ff063 100644 --- a/drivers/irqchip/exynos-combiner.c +++ b/drivers/irqchip/exynos-combiner.c @@ -66,8 +66,9 @@ static void combiner_handle_cascade_irq(struct irq_desc *desc) { struct combiner_chip_data *chip_data = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); - unsigned int cascade_irq, combiner_irq; + unsigned int combiner_irq; unsigned long status; + int ret; chained_irq_enter(chip, desc); @@ -80,12 +81,9 @@ static void combiner_handle_cascade_irq(struct irq_desc *desc) goto out; combiner_irq = chip_data->hwirq_offset + __ffs(status); - cascade_irq = irq_find_mapping(combiner_irq_domain, combiner_irq); - - if (unlikely(!cascade_irq)) + ret = generic_handle_domain_irq(combiner_irq_domain, combiner_irq); + if (unlikely(ret)) handle_bad_irq(desc); - else - generic_handle_irq(cascade_irq); out: chained_irq_exit(chip, desc); @@ -179,10 +177,8 @@ static void __init combiner_init(void __iomem *combiner_base, nr_irq = max_nr * IRQ_IN_COMBINER; combiner_data = kcalloc(max_nr, sizeof (*combiner_data), GFP_KERNEL); - if (!combiner_data) { - pr_warn("%s: could not allocate combiner data\n", __func__); + if (!combiner_data) return; - } combiner_irq_domain = irq_domain_add_linear(np, nr_irq, &combiner_irq_domain_ops, combiner_data); diff --git a/drivers/irqchip/irq-al-fic.c b/drivers/irqchip/irq-al-fic.c index 0b0a73739756..886de028a901 100644 --- a/drivers/irqchip/irq-al-fic.c +++ b/drivers/irqchip/irq-al-fic.c @@ -111,7 +111,6 @@ static void al_fic_irq_handler(struct irq_desc *desc) struct irq_chip *irqchip = irq_desc_get_chip(desc); struct irq_chip_generic *gc = irq_get_domain_generic_chip(domain, 0); unsigned long pending; - unsigned int irq; u32 hwirq; chained_irq_enter(irqchip, desc); @@ -119,10 +118,8 @@ static void al_fic_irq_handler(struct irq_desc *desc) pending = readl_relaxed(fic->base + AL_FIC_CAUSE); pending &= ~gc->mask_cache; - for_each_set_bit(hwirq, &pending, NR_FIC_IRQS) { - irq = irq_find_mapping(domain, hwirq); - generic_handle_irq(irq); - } + for_each_set_bit(hwirq, &pending, NR_FIC_IRQS) + generic_handle_domain_irq(domain, hwirq); chained_irq_exit(irqchip, desc); } diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 32938dfc0e46..7557ab551295 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -582,20 +582,19 @@ static void armada_370_xp_handle_msi_irq(struct pt_regs *regs, bool is_chained) for (msinr = PCI_MSI_DOORBELL_START; msinr < PCI_MSI_DOORBELL_END; msinr++) { - int irq; + unsigned int irq; if (!(msimask & BIT(msinr))) continue; - if (is_chained) { - irq = irq_find_mapping(armada_370_xp_msi_inner_domain, - msinr - PCI_MSI_DOORBELL_START); - generic_handle_irq(irq); - } else { - irq = msinr - PCI_MSI_DOORBELL_START; + irq = msinr - PCI_MSI_DOORBELL_START; + + if (is_chained) + generic_handle_domain_irq(armada_370_xp_msi_inner_domain, + irq); + else handle_domain_irq(armada_370_xp_msi_inner_domain, irq, regs); - } } } #else @@ -606,7 +605,6 @@ static void armada_370_xp_mpic_handle_cascade_irq(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); unsigned long irqmap, irqn, irqsrc, cpuid; - unsigned int cascade_irq; chained_irq_enter(chip, desc); @@ -628,8 +626,7 @@ static void armada_370_xp_mpic_handle_cascade_irq(struct irq_desc *desc) continue; } - cascade_irq = irq_find_mapping(armada_370_xp_mpic_domain, irqn); - generic_handle_irq(cascade_irq); + generic_handle_domain_irq(armada_370_xp_mpic_domain, irqn); } chained_irq_exit(chip, desc); diff --git a/drivers/irqchip/irq-aspeed-i2c-ic.c b/drivers/irqchip/irq-aspeed-i2c-ic.c index 8d591c179f81..a47db16ff960 100644 --- a/drivers/irqchip/irq-aspeed-i2c-ic.c +++ b/drivers/irqchip/irq-aspeed-i2c-ic.c @@ -34,14 +34,12 @@ static void aspeed_i2c_ic_irq_handler(struct irq_desc *desc) struct aspeed_i2c_ic *i2c_ic = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); unsigned long bit, status; - unsigned int bus_irq; chained_irq_enter(chip, desc); status = readl(i2c_ic->base); - for_each_set_bit(bit, &status, ASPEED_I2C_IC_NUM_BUS) { - bus_irq = irq_find_mapping(i2c_ic->irq_domain, bit); - generic_handle_irq(bus_irq); - } + for_each_set_bit(bit, &status, ASPEED_I2C_IC_NUM_BUS) + generic_handle_domain_irq(i2c_ic->irq_domain, bit); + chained_irq_exit(chip, desc); } diff --git a/drivers/irqchip/irq-aspeed-scu-ic.c b/drivers/irqchip/irq-aspeed-scu-ic.c index c90a3346b985..f3c6855a4cef 100644 --- a/drivers/irqchip/irq-aspeed-scu-ic.c +++ b/drivers/irqchip/irq-aspeed-scu-ic.c @@ -44,7 +44,6 @@ struct aspeed_scu_ic { static void aspeed_scu_ic_irq_handler(struct irq_desc *desc) { - unsigned int irq; unsigned int sts; unsigned long bit; unsigned long enabled; @@ -74,9 +73,8 @@ static void aspeed_scu_ic_irq_handler(struct irq_desc *desc) max = scu_ic->num_irqs + bit; for_each_set_bit_from(bit, &status, max) { - irq = irq_find_mapping(scu_ic->irq_domain, - bit - scu_ic->irq_shift); - generic_handle_irq(irq); + generic_handle_domain_irq(scu_ic->irq_domain, + bit - scu_ic->irq_shift); regmap_update_bits(scu_ic->scu, scu_ic->reg, mask, BIT(bit + ASPEED_SCU_IC_STATUS_SHIFT)); diff --git a/drivers/irqchip/irq-ath79-misc.c b/drivers/irqchip/irq-ath79-misc.c index 3d641bb6f3f1..92f001a5ff8d 100644 --- a/drivers/irqchip/irq-ath79-misc.c +++ b/drivers/irqchip/irq-ath79-misc.c @@ -50,7 +50,7 @@ static void ath79_misc_irq_handler(struct irq_desc *desc) while (pending) { int bit = __ffs(pending); - generic_handle_irq(irq_linear_revmap(domain, bit)); + generic_handle_domain_irq(domain, bit); pending &= ~BIT(bit); } diff --git a/drivers/irqchip/irq-bcm2835.c b/drivers/irqchip/irq-bcm2835.c index a1e004af23e7..adc1556ed332 100644 --- a/drivers/irqchip/irq-bcm2835.c +++ b/drivers/irqchip/irq-bcm2835.c @@ -254,7 +254,7 @@ static void bcm2836_chained_handle_irq(struct irq_desc *desc) u32 hwirq; while ((hwirq = get_next_armctrl_hwirq()) != ~0) - generic_handle_irq(irq_linear_revmap(intc.domain, hwirq)); + generic_handle_domain_irq(intc.domain, hwirq); } IRQCHIP_DECLARE(bcm2835_armctrl_ic, "brcm,bcm2835-armctrl-ic", diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c index 25c9a9c06e41..501facdb4570 100644 --- a/drivers/irqchip/irq-bcm2836.c +++ b/drivers/irqchip/irq-bcm2836.c @@ -161,7 +161,7 @@ static void bcm2836_arm_irqchip_handle_ipi(struct irq_desc *desc) mbox_val = readl_relaxed(intc.base + LOCAL_MAILBOX0_CLR0 + 16 * cpu); if (mbox_val) { int hwirq = ffs(mbox_val) - 1; - generic_handle_irq(irq_find_mapping(ipi_domain, hwirq)); + generic_handle_domain_irq(ipi_domain, hwirq); } chained_irq_exit(chip, desc); diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c index 9dc9bf8cdcc4..a035c385ca7a 100644 --- a/drivers/irqchip/irq-bcm7038-l1.c +++ b/drivers/irqchip/irq-bcm7038-l1.c @@ -145,10 +145,8 @@ static void bcm7038_l1_irq_handle(struct irq_desc *desc) ~cpu->mask_cache[idx]; raw_spin_unlock_irqrestore(&intc->lock, flags); - for_each_set_bit(hwirq, &pending, IRQS_PER_WORD) { - generic_handle_irq(irq_find_mapping(intc->domain, - base + hwirq)); - } + for_each_set_bit(hwirq, &pending, IRQS_PER_WORD) + generic_handle_domain_irq(intc->domain, base + hwirq); } chained_irq_exit(chip, desc); diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c index ad59656ccc28..f23d7651ea84 100644 --- a/drivers/irqchip/irq-bcm7120-l2.c +++ b/drivers/irqchip/irq-bcm7120-l2.c @@ -74,10 +74,8 @@ static void bcm7120_l2_intc_irq_handle(struct irq_desc *desc) data->irq_map_mask[idx]; irq_gc_unlock(gc); - for_each_set_bit(hwirq, &pending, IRQS_PER_WORD) { - generic_handle_irq(irq_find_mapping(b->domain, - base + hwirq)); - } + for_each_set_bit(hwirq, &pending, IRQS_PER_WORD) + generic_handle_domain_irq(b->domain, base + hwirq); } chained_irq_exit(chip, desc); diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index cdd6a42d4efa..8e0911561f2d 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -110,7 +110,7 @@ static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc) do { irq = ffs(status) - 1; status &= ~(1 << irq); - generic_handle_irq(irq_linear_revmap(b->domain, irq)); + generic_handle_domain_irq(b->domain, irq); } while (status); out: chained_irq_exit(chip, desc); diff --git a/drivers/irqchip/irq-dw-apb-ictl.c b/drivers/irqchip/irq-dw-apb-ictl.c index 54b09d6c407c..a67266e44491 100644 --- a/drivers/irqchip/irq-dw-apb-ictl.c +++ b/drivers/irqchip/irq-dw-apb-ictl.c @@ -62,9 +62,8 @@ static void dw_apb_ictl_handle_irq_cascaded(struct irq_desc *desc) while (stat) { u32 hwirq = ffs(stat) - 1; - u32 virq = irq_find_mapping(d, gc->irq_base + hwirq); + generic_handle_domain_irq(d, gc->irq_base + hwirq); - generic_handle_irq(virq); stat &= ~BIT(hwirq); } } diff --git a/drivers/irqchip/irq-gic-pm.c b/drivers/irqchip/irq-gic-pm.c index 1337ceceb59b..b60e1853593f 100644 --- a/drivers/irqchip/irq-gic-pm.c +++ b/drivers/irqchip/irq-gic-pm.c @@ -30,10 +30,8 @@ static int gic_runtime_resume(struct device *dev) int ret; ret = clk_bulk_prepare_enable(data->num_clocks, chip_pm->clks); - if (ret) { - dev_err(dev, "clk_enable failed: %d\n", ret); + if (ret) return ret; - } /* * On the very first resume, the pointer to chip_pm->chip_data diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c index 4116b48e60af..be9ea6fd6f8b 100644 --- a/drivers/irqchip/irq-gic-v2m.c +++ b/drivers/irqchip/irq-gic-v2m.c @@ -323,10 +323,8 @@ static int __init gicv2m_init_one(struct fwnode_handle *fwnode, struct v2m_data *v2m; v2m = kzalloc(sizeof(struct v2m_data), GFP_KERNEL); - if (!v2m) { - pr_err("Failed to allocate struct v2m_data.\n"); + if (!v2m) return -ENOMEM; - } INIT_LIST_HEAD(&v2m->entry); v2m->fwnode = fwnode; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 2e6923c2c8a8..ba39668c3e08 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -4895,10 +4895,8 @@ static int its_init_vpe_domain(void) entries = roundup_pow_of_two(nr_cpu_ids); vpe_proxy.vpes = kcalloc(entries, sizeof(*vpe_proxy.vpes), GFP_KERNEL); - if (!vpe_proxy.vpes) { - pr_err("ITS: Can't allocate GICv4 proxy device array\n"); + if (!vpe_proxy.vpes) return -ENOMEM; - } /* Use the last possible DevID */ devid = GENMASK(device_ids(its) - 1, 0); @@ -5314,10 +5312,8 @@ static void __init acpi_table_parse_srat_its(void) its_srat_maps = kmalloc_array(count, sizeof(struct its_srat_map), GFP_KERNEL); - if (!its_srat_maps) { - pr_warn("SRAT: Failed to allocate memory for its_srat_maps!\n"); + if (!its_srat_maps) return; - } acpi_table_parse_entries(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat), diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 2de9ec8ece0c..d329ec3d64d8 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -375,8 +375,9 @@ static void gic_handle_cascade_irq(struct irq_desc *desc) { struct gic_chip_data *chip_data = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); - unsigned int cascade_irq, gic_irq; + unsigned int gic_irq; unsigned long status; + int ret; chained_irq_enter(chip, desc); @@ -386,14 +387,10 @@ static void gic_handle_cascade_irq(struct irq_desc *desc) if (gic_irq == GICC_INT_SPURIOUS) goto out; - cascade_irq = irq_find_mapping(chip_data->domain, gic_irq); - if (unlikely(gic_irq < 32 || gic_irq > 1020)) { + isb(); + ret = generic_handle_domain_irq(chip_data->domain, gic_irq); + if (unlikely(ret)) handle_bad_irq(desc); - } else { - isb(); - generic_handle_irq(cascade_irq); - } - out: chained_irq_exit(chip, desc); } diff --git a/drivers/irqchip/irq-goldfish-pic.c b/drivers/irqchip/irq-goldfish-pic.c index 4f021530e7f3..513f6edbbe95 100644 --- a/drivers/irqchip/irq-goldfish-pic.c +++ b/drivers/irqchip/irq-goldfish-pic.c @@ -34,15 +34,14 @@ static void goldfish_pic_cascade(struct irq_desc *desc) { struct goldfish_pic_data *gfpic = irq_desc_get_handler_data(desc); struct irq_chip *host_chip = irq_desc_get_chip(desc); - u32 pending, hwirq, virq; + u32 pending, hwirq; chained_irq_enter(host_chip, desc); pending = readl(gfpic->base + GFPIC_REG_IRQ_PENDING); while (pending) { hwirq = __fls(pending); - virq = irq_linear_revmap(gfpic->irq_domain, hwirq); - generic_handle_irq(virq); + generic_handle_domain_irq(gfpic->irq_domain, hwirq); pending &= ~(1 << hwirq); } diff --git a/drivers/irqchip/irq-i8259.c b/drivers/irqchip/irq-i8259.c index b6f6aa7b2862..b70ce0d3c092 100644 --- a/drivers/irqchip/irq-i8259.c +++ b/drivers/irqchip/irq-i8259.c @@ -333,13 +333,11 @@ static void i8259_irq_dispatch(struct irq_desc *desc) { struct irq_domain *domain = irq_desc_get_handler_data(desc); int hwirq = i8259_poll(); - unsigned int irq; if (hwirq < 0) return; - irq = irq_linear_revmap(domain, hwirq); - generic_handle_irq(irq); + generic_handle_domain_irq(domain, hwirq); } int __init i8259_of_init(struct device_node *node, struct device_node *parent) diff --git a/drivers/irqchip/irq-idt3243x.c b/drivers/irqchip/irq-idt3243x.c index f0996820077a..0732a0e9af62 100644 --- a/drivers/irqchip/irq-idt3243x.c +++ b/drivers/irqchip/irq-idt3243x.c @@ -28,7 +28,7 @@ static void idt_irq_dispatch(struct irq_desc *desc) { struct idt_pic_data *idtpic = irq_desc_get_handler_data(desc); struct irq_chip *host_chip = irq_desc_get_chip(desc); - u32 pending, hwirq, virq; + u32 pending, hwirq; chained_irq_enter(host_chip, desc); @@ -36,9 +36,7 @@ static void idt_irq_dispatch(struct irq_desc *desc) pending &= ~idtpic->gc->mask_cache; while (pending) { hwirq = __fls(pending); - virq = irq_linear_revmap(idtpic->irq_domain, hwirq); - if (virq) - generic_handle_irq(virq); + generic_handle_domain_irq(idtpic->irq_domain, hwirq); pending &= ~(1 << hwirq); } diff --git a/drivers/irqchip/irq-imgpdc.c b/drivers/irqchip/irq-imgpdc.c index 698d07f48fed..5831be454673 100644 --- a/drivers/irqchip/irq-imgpdc.c +++ b/drivers/irqchip/irq-imgpdc.c @@ -223,7 +223,7 @@ static void pdc_intc_perip_isr(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct pdc_intc_priv *priv; - unsigned int i, irq_no; + unsigned int i; priv = (struct pdc_intc_priv *)irq_desc_get_handler_data(desc); @@ -237,14 +237,13 @@ static void pdc_intc_perip_isr(struct irq_desc *desc) found: /* pass on the interrupt */ - irq_no = irq_linear_revmap(priv->domain, i); - generic_handle_irq(irq_no); + generic_handle_domain_irq(priv->domain, i); } static void pdc_intc_syswake_isr(struct irq_desc *desc) { struct pdc_intc_priv *priv; - unsigned int syswake, irq_no; + unsigned int syswake; unsigned int status; priv = (struct pdc_intc_priv *)irq_desc_get_handler_data(desc); @@ -258,9 +257,7 @@ static void pdc_intc_syswake_isr(struct irq_desc *desc) if (!(status & 1)) continue; - irq_no = irq_linear_revmap(priv->domain, - syswake_to_hwirq(syswake)); - generic_handle_irq(irq_no); + generic_handle_domain_irq(priv->domain, syswake_to_hwirq(syswake)); } } @@ -316,10 +313,8 @@ static int pdc_intc_probe(struct platform_device *pdev) /* Allocate driver data */ priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); - if (!priv) { - dev_err(&pdev->dev, "cannot allocate device data\n"); + if (!priv) return -ENOMEM; - } raw_spin_lock_init(&priv->lock); platform_set_drvdata(pdev, priv); @@ -356,10 +351,8 @@ static int pdc_intc_probe(struct platform_device *pdev) /* Get peripheral IRQ numbers */ priv->perip_irqs = devm_kcalloc(&pdev->dev, 4, priv->nr_perips, GFP_KERNEL); - if (!priv->perip_irqs) { - dev_err(&pdev->dev, "cannot allocate perip IRQ list\n"); + if (!priv->perip_irqs) return -ENOMEM; - } for (i = 0; i < priv->nr_perips; ++i) { irq = platform_get_irq(pdev, 1 + i); if (irq < 0) diff --git a/drivers/irqchip/irq-imx-gpcv2.c b/drivers/irqchip/irq-imx-gpcv2.c index 7031ef44de4f..5b5a365dbd5e 100644 --- a/drivers/irqchip/irq-imx-gpcv2.c +++ b/drivers/irqchip/irq-imx-gpcv2.c @@ -228,10 +228,8 @@ static int __init imx_gpcv2_irqchip_init(struct device_node *node, } cd = kzalloc(sizeof(struct gpcv2_irqchip_data), GFP_KERNEL); - if (!cd) { - pr_err("%pOF: kzalloc failed!\n", node); + if (!cd) return -ENOMEM; - } raw_spin_lock_init(&cd->rlock); diff --git a/drivers/irqchip/irq-imx-intmux.c b/drivers/irqchip/irq-imx-intmux.c index 7709f9712cb3..e86ff743e98c 100644 --- a/drivers/irqchip/irq-imx-intmux.c +++ b/drivers/irqchip/irq-imx-intmux.c @@ -182,18 +182,15 @@ static void imx_intmux_irq_handler(struct irq_desc *desc) struct intmux_data *data = container_of(irqchip_data, struct intmux_data, irqchip_data[idx]); unsigned long irqstat; - int pos, virq; + int pos; chained_irq_enter(irq_desc_get_chip(desc), desc); /* read the interrupt source pending status of this channel */ irqstat = readl_relaxed(data->regs + CHANIPR(idx)); - for_each_set_bit(pos, &irqstat, 32) { - virq = irq_find_mapping(irqchip_data->domain, pos); - if (virq) - generic_handle_irq(virq); - } + for_each_set_bit(pos, &irqstat, 32) + generic_handle_domain_irq(irqchip_data->domain, pos); chained_irq_exit(irq_desc_get_chip(desc), desc); } diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c index 1edf7692a790..8d91a02593fc 100644 --- a/drivers/irqchip/irq-imx-irqsteer.c +++ b/drivers/irqchip/irq-imx-irqsteer.c @@ -122,7 +122,7 @@ static void imx_irqsteer_irq_handler(struct irq_desc *desc) for (i = 0; i < 2; i++, hwirq += 32) { int idx = imx_irqsteer_get_reg_index(data, hwirq); unsigned long irqmap; - int pos, virq; + int pos; if (hwirq >= data->reg_num * 32) break; @@ -130,11 +130,8 @@ static void imx_irqsteer_irq_handler(struct irq_desc *desc) irqmap = readl_relaxed(data->regs + CHANSTATUS(idx, data->reg_num)); - for_each_set_bit(pos, &irqmap, 32) { - virq = irq_find_mapping(data->domain, pos + hwirq); - if (virq) - generic_handle_irq(virq); - } + for_each_set_bit(pos, &irqmap, 32) + generic_handle_domain_irq(data->domain, pos + hwirq); } chained_irq_exit(irq_desc_get_chip(desc), desc); diff --git a/drivers/irqchip/irq-ingenic-tcu.c b/drivers/irqchip/irq-ingenic-tcu.c index b938d1d04d96..34a7d261b710 100644 --- a/drivers/irqchip/irq-ingenic-tcu.c +++ b/drivers/irqchip/irq-ingenic-tcu.c @@ -38,7 +38,7 @@ static void ingenic_tcu_intc_cascade(struct irq_desc *desc) irq_reg &= ~irq_mask; for_each_set_bit(i, (unsigned long *)&irq_reg, 32) - generic_handle_irq(irq_linear_revmap(domain, i)); + generic_handle_domain_irq(domain, i); chained_irq_exit(irq_chip, desc); } diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c index ea36bb00be80..cee839ca627e 100644 --- a/drivers/irqchip/irq-ingenic.c +++ b/drivers/irqchip/irq-ingenic.c @@ -49,8 +49,7 @@ static irqreturn_t intc_cascade(int irq, void *data) while (pending) { int bit = __fls(pending); - irq = irq_linear_revmap(domain, bit + (i * 32)); - generic_handle_irq(irq); + generic_handle_domain_irq(domain, bit + (i * 32)); pending &= ~BIT(bit); } } diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c index 8118ebe80b09..d47c8041e5bc 100644 --- a/drivers/irqchip/irq-keystone.c +++ b/drivers/irqchip/irq-keystone.c @@ -89,7 +89,7 @@ static irqreturn_t keystone_irq_handler(int irq, void *keystone_irq) struct keystone_irq_device *kirq = keystone_irq; unsigned long wa_lock_flags; unsigned long pending; - int src, virq; + int src, err; dev_dbg(kirq->dev, "start irq %d\n", irq); @@ -104,16 +104,14 @@ static irqreturn_t keystone_irq_handler(int irq, void *keystone_irq) for (src = 0; src < KEYSTONE_N_IRQ; src++) { if (BIT(src) & pending) { - virq = irq_find_mapping(kirq->irqd, src); - dev_dbg(kirq->dev, "dispatch bit %d, virq %d\n", - src, virq); - if (!virq) - dev_warn(kirq->dev, "spurious irq detected hwirq %d, virq %d\n", - src, virq); raw_spin_lock_irqsave(&kirq->wa_lock, wa_lock_flags); - generic_handle_irq(virq); + err = generic_handle_domain_irq(kirq->irqd, src); raw_spin_unlock_irqrestore(&kirq->wa_lock, wa_lock_flags); + + if (err) + dev_warn_ratelimited(kirq->dev, "spurious irq detected hwirq %d\n", + src); } } diff --git a/drivers/irqchip/irq-loongson-htpic.c b/drivers/irqchip/irq-loongson-htpic.c index 1b801c4fb026..f4abdf156de7 100644 --- a/drivers/irqchip/irq-loongson-htpic.c +++ b/drivers/irqchip/irq-loongson-htpic.c @@ -48,7 +48,7 @@ static void htpic_irq_dispatch(struct irq_desc *desc) break; } - generic_handle_irq(irq_linear_revmap(priv->domain, bit)); + generic_handle_domain_irq(priv->domain, bit); pending &= ~BIT(bit); } chained_irq_exit(chip, desc); diff --git a/drivers/irqchip/irq-loongson-htvec.c b/drivers/irqchip/irq-loongson-htvec.c index 6392aafb9a63..60a335d7e64e 100644 --- a/drivers/irqchip/irq-loongson-htvec.c +++ b/drivers/irqchip/irq-loongson-htvec.c @@ -47,8 +47,8 @@ static void htvec_irq_dispatch(struct irq_desc *desc) while (pending) { int bit = __ffs(pending); - generic_handle_irq(irq_linear_revmap(priv->htvec_domain, bit + - VEC_COUNT_PER_REG * i)); + generic_handle_domain_irq(priv->htvec_domain, + bit + VEC_COUNT_PER_REG * i); pending &= ~BIT(bit); handled = true; } diff --git a/drivers/irqchip/irq-loongson-liointc.c b/drivers/irqchip/irq-loongson-liointc.c index 8ccb30421806..649c58391618 100644 --- a/drivers/irqchip/irq-loongson-liointc.c +++ b/drivers/irqchip/irq-loongson-liointc.c @@ -73,7 +73,7 @@ static void liointc_chained_handle_irq(struct irq_desc *desc) while (pending) { int bit = __ffs(pending); - generic_handle_irq(irq_find_mapping(gc->domain, bit)); + generic_handle_domain_irq(gc->domain, bit); pending &= ~BIT(bit); } diff --git a/drivers/irqchip/irq-lpc32xx.c b/drivers/irqchip/irq-lpc32xx.c index 7d9b388afe64..5e6f6e25f2ae 100644 --- a/drivers/irqchip/irq-lpc32xx.c +++ b/drivers/irqchip/irq-lpc32xx.c @@ -141,7 +141,7 @@ static void lpc32xx_sic_handler(struct irq_desc *desc) while (hwirq) { irq = __ffs(hwirq); hwirq &= ~BIT(irq); - generic_handle_irq(irq_find_mapping(ic->domain, irq)); + generic_handle_domain_irq(ic->domain, irq); } chained_irq_exit(chip, desc); diff --git a/drivers/irqchip/irq-ls-scfg-msi.c b/drivers/irqchip/irq-ls-scfg-msi.c index 61dbfda08527..55322da51c56 100644 --- a/drivers/irqchip/irq-ls-scfg-msi.c +++ b/drivers/irqchip/irq-ls-scfg-msi.c @@ -194,7 +194,7 @@ static void ls_scfg_msi_irq_handler(struct irq_desc *desc) struct ls_scfg_msir *msir = irq_desc_get_handler_data(desc); struct ls_scfg_msi *msi_data = msir->msi_data; unsigned long val; - int pos, size, virq, hwirq; + int pos, size, hwirq; chained_irq_enter(irq_desc_get_chip(desc), desc); @@ -206,9 +206,7 @@ static void ls_scfg_msi_irq_handler(struct irq_desc *desc) for_each_set_bit_from(pos, &val, size) { hwirq = ((msir->bit_end - pos) << msi_data->cfg->ibs_shift) | msir->srs; - virq = irq_find_mapping(msi_data->parent, hwirq); - if (virq) - generic_handle_irq(virq); + generic_handle_domain_irq(msi_data->parent, hwirq); } chained_irq_exit(irq_desc_get_chip(desc), desc); diff --git a/drivers/irqchip/irq-ls1x.c b/drivers/irqchip/irq-ls1x.c index 353111a10413..77a3f7dfaaf0 100644 --- a/drivers/irqchip/irq-ls1x.c +++ b/drivers/irqchip/irq-ls1x.c @@ -50,7 +50,7 @@ static void ls1x_chained_handle_irq(struct irq_desc *desc) while (pending) { int bit = __ffs(pending); - generic_handle_irq(irq_find_mapping(priv->domain, bit)); + generic_handle_domain_irq(priv->domain, bit); pending &= ~BIT(bit); } diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index 2cb45c6b8501..f565317a3da3 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -273,6 +273,12 @@ static int mbigen_of_create_domain(struct platform_device *pdev, } #ifdef CONFIG_ACPI +static const struct acpi_device_id mbigen_acpi_match[] = { + { "HISI0152", 0 }, + {} +}; +MODULE_DEVICE_TABLE(acpi, mbigen_acpi_match); + static int mbigen_acpi_create_domain(struct platform_device *pdev, struct mbigen_device *mgn_chip) { @@ -369,12 +375,6 @@ static const struct of_device_id mbigen_of_match[] = { }; MODULE_DEVICE_TABLE(of, mbigen_of_match); -static const struct acpi_device_id mbigen_acpi_match[] = { - { "HISI0152", 0 }, - {} -}; -MODULE_DEVICE_TABLE(acpi, mbigen_acpi_match); - static struct platform_driver mbigen_platform_driver = { .driver = { .name = "Hisilicon MBIGEN-V2", diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 215885962bb0..b146e069bf5b 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -147,7 +148,7 @@ int gic_get_c0_fdc_int(void) static void gic_handle_shared_int(bool chained) { - unsigned int intr, virq; + unsigned int intr; unsigned long *pcpu_mask; DECLARE_BITMAP(pending, GIC_MAX_INTRS); @@ -164,12 +165,12 @@ static void gic_handle_shared_int(bool chained) bitmap_and(pending, pending, pcpu_mask, gic_shared_intrs); for_each_set_bit(intr, pending, gic_shared_intrs) { - virq = irq_linear_revmap(gic_irq_domain, - GIC_SHARED_TO_HWIRQ(intr)); if (chained) - generic_handle_irq(virq); + generic_handle_domain_irq(gic_irq_domain, + GIC_SHARED_TO_HWIRQ(intr)); else - do_IRQ(virq); + do_IRQ(irq_find_mapping(gic_irq_domain, + GIC_SHARED_TO_HWIRQ(intr))); } } @@ -307,7 +308,7 @@ static struct irq_chip gic_edge_irq_controller = { static void gic_handle_local_int(bool chained) { unsigned long pending, masked; - unsigned int intr, virq; + unsigned int intr; pending = read_gic_vl_pend(); masked = read_gic_vl_mask(); @@ -315,12 +316,12 @@ static void gic_handle_local_int(bool chained) bitmap_and(&pending, &pending, &masked, GIC_NUM_LOCAL_INTRS); for_each_set_bit(intr, &pending, GIC_NUM_LOCAL_INTRS) { - virq = irq_linear_revmap(gic_irq_domain, - GIC_LOCAL_TO_HWIRQ(intr)); if (chained) - generic_handle_irq(virq); + generic_handle_domain_irq(gic_irq_domain, + GIC_LOCAL_TO_HWIRQ(intr)); else - do_IRQ(virq); + do_IRQ(irq_find_mapping(gic_irq_domain, + GIC_LOCAL_TO_HWIRQ(intr))); } } diff --git a/drivers/irqchip/irq-mscc-ocelot.c b/drivers/irqchip/irq-mscc-ocelot.c index 8235d98650c1..4d0c3532dbe7 100644 --- a/drivers/irqchip/irq-mscc-ocelot.c +++ b/drivers/irqchip/irq-mscc-ocelot.c @@ -107,7 +107,7 @@ static void ocelot_irq_handler(struct irq_desc *desc) while (reg) { u32 hwirq = __fls(reg); - generic_handle_irq(irq_find_mapping(d, hwirq)); + generic_handle_domain_irq(d, hwirq); reg &= ~(BIT(hwirq)); } diff --git a/drivers/irqchip/irq-mvebu-pic.c b/drivers/irqchip/irq-mvebu-pic.c index eec63951129a..dc1cee4b0fe1 100644 --- a/drivers/irqchip/irq-mvebu-pic.c +++ b/drivers/irqchip/irq-mvebu-pic.c @@ -91,15 +91,12 @@ static void mvebu_pic_handle_cascade_irq(struct irq_desc *desc) struct mvebu_pic *pic = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); unsigned long irqmap, irqn; - unsigned int cascade_irq; irqmap = readl_relaxed(pic->base + PIC_CAUSE); chained_irq_enter(chip, desc); - for_each_set_bit(irqn, &irqmap, BITS_PER_LONG) { - cascade_irq = irq_find_mapping(pic->domain, irqn); - generic_handle_irq(cascade_irq); - } + for_each_set_bit(irqn, &irqmap, BITS_PER_LONG) + generic_handle_domain_irq(pic->domain, irqn); chained_irq_exit(chip, desc); } diff --git a/drivers/irqchip/irq-mvebu-sei.c b/drivers/irqchip/irq-mvebu-sei.c index 3a7b7a7f20ca..4ecef6d83777 100644 --- a/drivers/irqchip/irq-mvebu-sei.c +++ b/drivers/irqchip/irq-mvebu-sei.c @@ -337,17 +337,12 @@ static void mvebu_sei_handle_cascade_irq(struct irq_desc *desc) irqmap = readl_relaxed(sei->base + GICP_SECR(idx)); for_each_set_bit(bit, &irqmap, SEI_IRQ_COUNT_PER_REG) { unsigned long hwirq; - unsigned int virq; + int err; hwirq = idx * SEI_IRQ_COUNT_PER_REG + bit; - virq = irq_find_mapping(sei->sei_domain, hwirq); - if (likely(virq)) { - generic_handle_irq(virq); - continue; - } - - dev_warn(sei->dev, - "Spurious IRQ detected (hwirq %lu)\n", hwirq); + err = generic_handle_domain_irq(sei->sei_domain, hwirq); + if (unlikely(err)) + dev_warn(sei->dev, "Spurious IRQ detected (hwirq %lu)\n", hwirq); } } diff --git a/drivers/irqchip/irq-nvic.c b/drivers/irqchip/irq-nvic.c index f747e2209ea9..b31c4cff4d3a 100644 --- a/drivers/irqchip/irq-nvic.c +++ b/drivers/irqchip/irq-nvic.c @@ -40,9 +40,7 @@ static struct irq_domain *nvic_irq_domain; asmlinkage void __exception_irq_entry nvic_handle_irq(irq_hw_number_t hwirq, struct pt_regs *regs) { - unsigned int irq = irq_linear_revmap(nvic_irq_domain, hwirq); - - handle_IRQ(irq, regs); + handle_domain_irq(nvic_irq_domain, hwirq, regs); } static int nvic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, diff --git a/drivers/irqchip/irq-orion.c b/drivers/irqchip/irq-orion.c index c4b5ffb61954..b6868f7b805a 100644 --- a/drivers/irqchip/irq-orion.c +++ b/drivers/irqchip/irq-orion.c @@ -117,7 +117,7 @@ static void orion_bridge_irq_handler(struct irq_desc *desc) while (stat) { u32 hwirq = __fls(stat); - generic_handle_irq(irq_find_mapping(d, gc->irq_base + hwirq)); + generic_handle_domain_irq(d, gc->irq_base + hwirq); stat &= ~(1 << hwirq); } } diff --git a/drivers/irqchip/irq-partition-percpu.c b/drivers/irqchip/irq-partition-percpu.c index 0c4c8ed7064e..89c23a1566dc 100644 --- a/drivers/irqchip/irq-partition-percpu.c +++ b/drivers/irqchip/irq-partition-percpu.c @@ -124,13 +124,10 @@ static void partition_handle_irq(struct irq_desc *desc) break; } - if (unlikely(hwirq == part->nr_parts)) { + if (unlikely(hwirq == part->nr_parts)) handle_bad_irq(desc); - } else { - unsigned int irq; - irq = irq_find_mapping(part->domain, hwirq); - generic_handle_irq(irq); - } + else + generic_handle_domain_irq(part->domain, hwirq); chained_irq_exit(chip, desc); } diff --git a/drivers/irqchip/irq-pruss-intc.c b/drivers/irqchip/irq-pruss-intc.c index 92fb5780dc10..fa8d89b02ec0 100644 --- a/drivers/irqchip/irq-pruss-intc.c +++ b/drivers/irqchip/irq-pruss-intc.c @@ -488,8 +488,7 @@ static void pruss_intc_irq_handler(struct irq_desc *desc) while (true) { u32 hipir; - unsigned int virq; - int hwirq; + int hwirq, err; /* get highest priority pending PRUSS system event */ hipir = pruss_intc_read_reg(intc, PRU_INTC_HIPIR(host_irq)); @@ -497,16 +496,14 @@ static void pruss_intc_irq_handler(struct irq_desc *desc) break; hwirq = hipir & GENMASK(9, 0); - virq = irq_find_mapping(intc->domain, hwirq); + err = generic_handle_domain_irq(intc->domain, hwirq); /* * NOTE: manually ACK any system events that do not have a * handler mapped yet */ - if (WARN_ON_ONCE(!virq)) + if (WARN_ON_ONCE(err)) pruss_intc_write_reg(intc, PRU_INTC_SICR, hwirq); - else - generic_handle_irq(virq); } chained_irq_exit(chip, desc); diff --git a/drivers/irqchip/irq-realtek-rtl.c b/drivers/irqchip/irq-realtek-rtl.c index b57c67dfab5b..fd9f275592d2 100644 --- a/drivers/irqchip/irq-realtek-rtl.c +++ b/drivers/irqchip/irq-realtek-rtl.c @@ -85,7 +85,7 @@ static void realtek_irq_dispatch(struct irq_desc *desc) goto out; } domain = irq_desc_get_handler_data(desc); - generic_handle_irq(irq_find_mapping(domain, __ffs(pending))); + generic_handle_domain_irq(domain, __ffs(pending)); out: chained_irq_exit(chip, desc); diff --git a/drivers/irqchip/irq-renesas-irqc.c b/drivers/irqchip/irq-renesas-irqc.c index 11abc09ef76c..07a6d8b42b63 100644 --- a/drivers/irqchip/irq-renesas-irqc.c +++ b/drivers/irqchip/irq-renesas-irqc.c @@ -115,7 +115,7 @@ static irqreturn_t irqc_irq_handler(int irq, void *dev_id) if (ioread32(p->iomem + DETECT_STATUS) & bit) { iowrite32(bit, p->iomem + DETECT_STATUS); irqc_dbg(i, "demux2"); - generic_handle_irq(irq_find_mapping(p->irq_domain, i->hw_irq)); + generic_handle_domain_irq(p->irq_domain, i->hw_irq); return IRQ_HANDLED; } return IRQ_NONE; diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index 97d4d04b0a80..cf74cfa82045 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -233,13 +233,11 @@ static void plic_handle_irq(struct irq_desc *desc) chained_irq_enter(chip, desc); while ((hwirq = readl(claim))) { - int irq = irq_find_mapping(handler->priv->irqdomain, hwirq); - - if (unlikely(irq <= 0)) + int err = generic_handle_domain_irq(handler->priv->irqdomain, + hwirq); + if (unlikely(err)) pr_warn_ratelimited("can't find mapping for hwirq %lu\n", hwirq); - else - generic_handle_irq(irq); } chained_irq_exit(chip, desc); diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index 4704f2ee5797..33c76710f845 100644 --- a/drivers/irqchip/irq-stm32-exti.c +++ b/drivers/irqchip/irq-stm32-exti.c @@ -257,7 +257,7 @@ static void stm32_irq_handler(struct irq_desc *desc) { struct irq_domain *domain = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); - unsigned int virq, nbanks = domain->gc->num_chips; + unsigned int nbanks = domain->gc->num_chips; struct irq_chip_generic *gc; unsigned long pending; int n, i, irq_base = 0; @@ -268,11 +268,9 @@ static void stm32_irq_handler(struct irq_desc *desc) gc = irq_get_domain_generic_chip(domain, irq_base); while ((pending = stm32_exti_pending(gc))) { - for_each_set_bit(n, &pending, IRQS_PER_BANK) { - virq = irq_find_mapping(domain, irq_base + n); - generic_handle_irq(virq); - } - } + for_each_set_bit(n, &pending, IRQS_PER_BANK) + generic_handle_domain_irq(domain, irq_base + n); + } } chained_irq_exit(chip, desc); diff --git a/drivers/irqchip/irq-sun4i.c b/drivers/irqchip/irq-sun4i.c index 9ea94456b178..8a315d6a3399 100644 --- a/drivers/irqchip/irq-sun4i.c +++ b/drivers/irqchip/irq-sun4i.c @@ -147,10 +147,8 @@ static int __init sun4i_ic_of_init(struct device_node *node, struct device_node *parent) { irq_ic_data = kzalloc(sizeof(struct sun4i_irq_chip_data), GFP_KERNEL); - if (!irq_ic_data) { - pr_err("kzalloc failed!\n"); + if (!irq_ic_data) return -ENOMEM; - } irq_ic_data->enable_reg_offset = SUN4I_IRQ_ENABLE_REG_OFFSET; irq_ic_data->mask_reg_offset = SUN4I_IRQ_MASK_REG_OFFSET; @@ -164,10 +162,8 @@ static int __init suniv_ic_of_init(struct device_node *node, struct device_node *parent) { irq_ic_data = kzalloc(sizeof(struct sun4i_irq_chip_data), GFP_KERNEL); - if (!irq_ic_data) { - pr_err("kzalloc failed!\n"); + if (!irq_ic_data) return -ENOMEM; - } irq_ic_data->enable_reg_offset = SUNIV_IRQ_ENABLE_REG_OFFSET; irq_ic_data->mask_reg_offset = SUNIV_IRQ_MASK_REG_OFFSET; diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c index 9f2bd0c5d289..21d49791f855 100644 --- a/drivers/irqchip/irq-sunxi-nmi.c +++ b/drivers/irqchip/irq-sunxi-nmi.c @@ -88,10 +88,9 @@ static void sunxi_sc_nmi_handle_irq(struct irq_desc *desc) { struct irq_domain *domain = irq_desc_get_handler_data(desc); struct irq_chip *chip = irq_desc_get_chip(desc); - unsigned int virq = irq_find_mapping(domain, 0); chained_irq_enter(chip, desc); - generic_handle_irq(virq); + generic_handle_domain_irq(domain, 0); chained_irq_exit(chip, desc); } diff --git a/drivers/irqchip/irq-tb10x.c b/drivers/irqchip/irq-tb10x.c index 9a63b02b8176..8a0e69298e83 100644 --- a/drivers/irqchip/irq-tb10x.c +++ b/drivers/irqchip/irq-tb10x.c @@ -91,7 +91,7 @@ static void tb10x_irq_cascade(struct irq_desc *desc) struct irq_domain *domain = irq_desc_get_handler_data(desc); unsigned int irq = irq_desc_get_irq(desc); - generic_handle_irq(irq_find_mapping(domain, irq)); + generic_handle_domain_irq(domain, irq); } static int __init of_tb10x_init_irq(struct device_node *ictl, diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c index ca1f593f4d13..97f454ec376b 100644 --- a/drivers/irqchip/irq-ti-sci-inta.c +++ b/drivers/irqchip/irq-ti-sci-inta.c @@ -147,7 +147,7 @@ static void ti_sci_inta_irq_handler(struct irq_desc *desc) struct ti_sci_inta_vint_desc *vint_desc; struct ti_sci_inta_irq_domain *inta; struct irq_domain *domain; - unsigned int virq, bit; + unsigned int bit; unsigned long val; vint_desc = irq_desc_get_handler_data(desc); @@ -159,11 +159,8 @@ static void ti_sci_inta_irq_handler(struct irq_desc *desc) val = readq_relaxed(inta->base + vint_desc->vint_id * 0x1000 + VINT_STATUS_MASKED_OFFSET); - for_each_set_bit(bit, &val, MAX_EVENTS_PER_VINT) { - virq = irq_find_mapping(domain, vint_desc->events[bit].hwirq); - if (virq) - generic_handle_irq(virq); - } + for_each_set_bit(bit, &val, MAX_EVENTS_PER_VINT) + generic_handle_domain_irq(domain, vint_desc->events[bit].hwirq); chained_irq_exit(irq_desc_get_chip(desc), desc); } diff --git a/drivers/irqchip/irq-ts4800.c b/drivers/irqchip/irq-ts4800.c index 2325fb3c482b..34337a61b1ef 100644 --- a/drivers/irqchip/irq-ts4800.c +++ b/drivers/irqchip/irq-ts4800.c @@ -79,10 +79,9 @@ static void ts4800_ic_chained_handle_irq(struct irq_desc *desc) do { unsigned int bit = __ffs(status); - int irq = irq_find_mapping(data->domain, bit); + generic_handle_domain_irq(data->domain, bit); status &= ~(1 << bit); - generic_handle_irq(irq); } while (status); out: diff --git a/drivers/irqchip/irq-versatile-fpga.c b/drivers/irqchip/irq-versatile-fpga.c index f1386733d3bc..75be350cf82f 100644 --- a/drivers/irqchip/irq-versatile-fpga.c +++ b/drivers/irqchip/irq-versatile-fpga.c @@ -85,7 +85,7 @@ static void fpga_irq_handle(struct irq_desc *desc) unsigned int irq = ffs(status) - 1; status &= ~(1 << irq); - generic_handle_irq(irq_find_mapping(f->domain, irq)); + generic_handle_domain_irq(f->domain, irq); } while (status); out: diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c index 62f3d29f9042..1e1f2d115257 100644 --- a/drivers/irqchip/irq-vic.c +++ b/drivers/irqchip/irq-vic.c @@ -225,7 +225,7 @@ static void vic_handle_irq_cascaded(struct irq_desc *desc) while ((stat = readl_relaxed(vic->base + VIC_IRQ_STATUS))) { hwirq = ffs(stat) - 1; - generic_handle_irq(irq_find_mapping(vic->domain, hwirq)); + generic_handle_domain_irq(vic->domain, hwirq); } chained_irq_exit(host_chip, desc); diff --git a/drivers/irqchip/irq-xilinx-intc.c b/drivers/irqchip/irq-xilinx-intc.c index 8cd1bfc73057..356a59755d63 100644 --- a/drivers/irqchip/irq-xilinx-intc.c +++ b/drivers/irqchip/irq-xilinx-intc.c @@ -110,20 +110,6 @@ static struct irq_chip intc_dev = { .irq_mask_ack = intc_mask_ack, }; -static unsigned int xintc_get_irq_local(struct xintc_irq_chip *irqc) -{ - unsigned int irq = 0; - u32 hwirq; - - hwirq = xintc_read(irqc, IVR); - if (hwirq != -1U) - irq = irq_find_mapping(irqc->root_domain, hwirq); - - pr_debug("irq-xilinx: hwirq=%d, irq=%d\n", hwirq, irq); - - return irq; -} - unsigned int xintc_get_irq(void) { unsigned int irq = -1; @@ -164,15 +150,16 @@ static void xil_intc_irq_handler(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct xintc_irq_chip *irqc; - u32 pending; irqc = irq_data_get_irq_handler_data(&desc->irq_data); chained_irq_enter(chip, desc); do { - pending = xintc_get_irq_local(irqc); - if (pending == 0) + u32 hwirq = xintc_read(irqc, IVR); + + if (hwirq == -1U) break; - generic_handle_irq(pending); + + generic_handle_domain_irq(irqc->root_domain, hwirq); } while (true); chained_irq_exit(chip, desc); } diff --git a/drivers/irqchip/qcom-irq-combiner.c b/drivers/irqchip/qcom-irq-combiner.c index aa54bfcb0433..18e696dc7f4d 100644 --- a/drivers/irqchip/qcom-irq-combiner.c +++ b/drivers/irqchip/qcom-irq-combiner.c @@ -53,7 +53,6 @@ static void combiner_handle_irq(struct irq_desc *desc) chained_irq_enter(chip, desc); for (reg = 0; reg < combiner->nregs; reg++) { - int virq; int hwirq; u32 bit; u32 status; @@ -70,10 +69,7 @@ static void combiner_handle_irq(struct irq_desc *desc) bit = __ffs(status); status &= ~(1 << bit); hwirq = irq_nr(reg, bit); - virq = irq_find_mapping(combiner->domain, hwirq); - if (virq > 0) - generic_handle_irq(virq); - + generic_handle_domain_irq(combiner->domain, hwirq); } } diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index 56bd2e9db6ed..e501cb03f211 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -2342,7 +2342,7 @@ static void __exit HFC_cleanup(void) { if (timer_pending(&hfc_tl)) - del_timer(&hfc_tl); + del_timer_sync(&hfc_tl); pci_unregister_driver(&hfc_driver); } diff --git a/drivers/isdn/mISDN/dsp_pipeline.c b/drivers/isdn/mISDN/dsp_pipeline.c index 40588692cec7..e11ca6bbc7f4 100644 --- a/drivers/isdn/mISDN/dsp_pipeline.c +++ b/drivers/isdn/mISDN/dsp_pipeline.c @@ -17,9 +17,6 @@ #include "dsp.h" #include "dsp_hwec.h" -/* uncomment for debugging */ -/*#define PIPELINE_DEBUG*/ - struct dsp_pipeline_entry { struct mISDN_dsp_element *elem; void *p; @@ -104,10 +101,6 @@ int mISDN_dsp_element_register(struct mISDN_dsp_element *elem) } } -#ifdef PIPELINE_DEBUG - printk(KERN_DEBUG "%s: %s registered\n", __func__, elem->name); -#endif - return 0; err2: @@ -129,10 +122,6 @@ void mISDN_dsp_element_unregister(struct mISDN_dsp_element *elem) list_for_each_entry_safe(entry, n, &dsp_elements, list) if (entry->elem == elem) { device_unregister(&entry->dev); -#ifdef PIPELINE_DEBUG - printk(KERN_DEBUG "%s: %s unregistered\n", - __func__, elem->name); -#endif return; } printk(KERN_ERR "%s: element %s not in list.\n", __func__, elem->name); @@ -145,10 +134,6 @@ int dsp_pipeline_module_init(void) if (IS_ERR(elements_class)) return PTR_ERR(elements_class); -#ifdef PIPELINE_DEBUG - printk(KERN_DEBUG "%s: dsp pipeline module initialized\n", __func__); -#endif - dsp_hwec_init(); return 0; @@ -168,10 +153,6 @@ void dsp_pipeline_module_exit(void) __func__, entry->elem->name); kfree(entry); } - -#ifdef PIPELINE_DEBUG - printk(KERN_DEBUG "%s: dsp pipeline module exited\n", __func__); -#endif } int dsp_pipeline_init(struct dsp_pipeline *pipeline) @@ -181,10 +162,6 @@ int dsp_pipeline_init(struct dsp_pipeline *pipeline) INIT_LIST_HEAD(&pipeline->list); -#ifdef PIPELINE_DEBUG - printk(KERN_DEBUG "%s: dsp pipeline ready\n", __func__); -#endif - return 0; } @@ -210,15 +187,11 @@ void dsp_pipeline_destroy(struct dsp_pipeline *pipeline) return; _dsp_pipeline_destroy(pipeline); - -#ifdef PIPELINE_DEBUG - printk(KERN_DEBUG "%s: dsp pipeline destroyed\n", __func__); -#endif } int dsp_pipeline_build(struct dsp_pipeline *pipeline, const char *cfg) { - int incomplete = 0, found = 0; + int found = 0; char *dup, *tok, *name, *args; struct dsp_element_entry *entry, *n; struct dsp_pipeline_entry *pipeline_entry; @@ -251,7 +224,6 @@ int dsp_pipeline_build(struct dsp_pipeline *pipeline, const char *cfg) printk(KERN_ERR "%s: failed to add " "entry to pipeline: %s (out of " "memory)\n", __func__, elem->name); - incomplete = 1; goto _out; } pipeline_entry->elem = elem; @@ -268,20 +240,12 @@ int dsp_pipeline_build(struct dsp_pipeline *pipeline, const char *cfg) if (pipeline_entry->p) { list_add_tail(&pipeline_entry-> list, &pipeline->list); -#ifdef PIPELINE_DEBUG - printk(KERN_DEBUG "%s: created " - "instance of %s%s%s\n", - __func__, name, args ? - " with args " : "", args ? - args : ""); -#endif } else { printk(KERN_ERR "%s: failed " "to add entry to pipeline: " "%s (new() returned NULL)\n", __func__, elem->name); kfree(pipeline_entry); - incomplete = 1; } } found = 1; @@ -290,11 +254,9 @@ int dsp_pipeline_build(struct dsp_pipeline *pipeline, const char *cfg) if (found) found = 0; - else { + else printk(KERN_ERR "%s: element not found, skipping: " "%s\n", __func__, name); - incomplete = 1; - } } _out: @@ -303,10 +265,6 @@ _out: else pipeline->inuse = 0; -#ifdef PIPELINE_DEBUG - printk(KERN_DEBUG "%s: dsp pipeline built%s: %s\n", - __func__, incomplete ? " incomplete" : "", cfg); -#endif kfree(dup); return 0; } diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index 40a948c08a0b..cf8a75494833 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -305,7 +305,6 @@ static int __nvm_config_extended(struct nvm_dev *dev, static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) { struct nvm_ioctl_create_extended e; - struct request_queue *tqueue; struct gendisk *tdisk; struct nvm_tgt_type *tt; struct nvm_target *t; @@ -370,24 +369,16 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) goto err_t; } - tdisk = alloc_disk(0); + tdisk = blk_alloc_disk(dev->q->node); if (!tdisk) { ret = -ENOMEM; goto err_dev; } - tqueue = blk_alloc_queue(dev->q->node); - if (!tqueue) { - ret = -ENOMEM; - goto err_disk; - } - strlcpy(tdisk->disk_name, create->tgtname, sizeof(tdisk->disk_name)); - tdisk->flags = GENHD_FL_EXT_DEVT; tdisk->major = 0; tdisk->first_minor = 0; tdisk->fops = tt->bops; - tdisk->queue = tqueue; targetdata = tt->init(tgt_dev, tdisk, create->flags); if (IS_ERR(targetdata)) { @@ -396,14 +387,14 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) } tdisk->private_data = targetdata; - tqueue->queuedata = targetdata; + tdisk->queue->queuedata = targetdata; mdts = (dev->geo.csecs >> 9) * NVM_MAX_VLBA; if (dev->geo.mdts) { mdts = min_t(u32, dev->geo.mdts, (dev->geo.csecs >> 9) * NVM_MAX_VLBA); } - blk_queue_max_hw_sectors(tqueue, mdts); + blk_queue_max_hw_sectors(tdisk->queue, mdts); set_capacity(tdisk, tt->capacity(targetdata)); add_disk(tdisk); @@ -428,10 +419,7 @@ err_sysfs: if (tt->exit) tt->exit(targetdata, true); err_init: - blk_cleanup_queue(tqueue); - tdisk->queue = NULL; -err_disk: - put_disk(tdisk); + blk_cleanup_disk(tdisk); err_dev: nvm_remove_tgt_dev(tgt_dev, 0); err_t: @@ -445,10 +433,8 @@ static void __nvm_remove_target(struct nvm_target *t, bool graceful) { struct nvm_tgt_type *tt = t->type; struct gendisk *tdisk = t->disk; - struct request_queue *q = tdisk->queue; del_gendisk(tdisk); - blk_cleanup_queue(q); if (tt->sysfs_exit) tt->sysfs_exit(tdisk); @@ -457,7 +443,7 @@ static void __nvm_remove_target(struct nvm_target *t, bool graceful) tt->exit(tdisk->private_data, graceful); nvm_remove_tgt_dev(t->dev, 1); - put_disk(tdisk); + blk_cleanup_disk(tdisk); module_put(t->type->owner); list_del(&t->list); diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig index 68de2c6af727..b4b780ea2ac8 100644 --- a/drivers/mailbox/Kconfig +++ b/drivers/mailbox/Kconfig @@ -160,6 +160,18 @@ config MAILBOX_TEST Test client to help with testing new Controller driver implementations. +config POLARFIRE_SOC_MAILBOX + tristate "PolarFire SoC (MPFS) Mailbox" + depends on HAS_IOMEM + depends on SOC_MICROCHIP_POLARFIRE || COMPILE_TEST + help + This driver adds support for the PolarFire SoC (MPFS) mailbox controller. + + To compile this driver as a module, choose M here. the + module will be called mailbox-mpfs. + + If unsure, say N. + config QCOM_APCS_IPC tristate "Qualcomm APCS IPC driver" depends on ARCH_QCOM || COMPILE_TEST diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile index 7194fa92c787..c2089f04887e 100644 --- a/drivers/mailbox/Makefile +++ b/drivers/mailbox/Makefile @@ -41,6 +41,8 @@ obj-$(CONFIG_BCM_PDC_MBOX) += bcm-pdc-mailbox.o obj-$(CONFIG_BCM_FLEXRM_MBOX) += bcm-flexrm-mailbox.o +obj-$(CONFIG_POLARFIRE_SOC_MAILBOX) += mailbox-mpfs.o + obj-$(CONFIG_QCOM_APCS_IPC) += qcom-apcs-ipc-mailbox.o obj-$(CONFIG_TEGRA_HSP_MBOX) += tegra-hsp.o diff --git a/drivers/mailbox/arm_mhu.c b/drivers/mailbox/arm_mhu.c index b7fbf276eb62..22243cabe056 100644 --- a/drivers/mailbox/arm_mhu.c +++ b/drivers/mailbox/arm_mhu.c @@ -122,10 +122,8 @@ static int mhu_probe(struct amba_device *adev, const struct amba_id *id) return -ENOMEM; mhu->base = devm_ioremap_resource(dev, &adev->res); - if (IS_ERR(mhu->base)) { - dev_err(dev, "ioremap failed\n"); + if (IS_ERR(mhu->base)) return PTR_ERR(mhu->base); - } for (i = 0; i < MHU_CHANS; i++) { mhu->chan[i].con_priv = &mhu->mlink[i]; diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c index b4f33dc399a0..78073ad1f2f1 100644 --- a/drivers/mailbox/bcm-flexrm-mailbox.c +++ b/drivers/mailbox/bcm-flexrm-mailbox.c @@ -1523,7 +1523,6 @@ static int flexrm_mbox_probe(struct platform_device *pdev) mbox->regs = devm_ioremap_resource(&pdev->dev, iomem); if (IS_ERR(mbox->regs)) { ret = PTR_ERR(mbox->regs); - dev_err(&pdev->dev, "Failed to remap mailbox regs: %d\n", ret); goto fail; } regs_end = mbox->regs + resource_size(iomem); diff --git a/drivers/mailbox/bcm-pdc-mailbox.c b/drivers/mailbox/bcm-pdc-mailbox.c index 5b375985f7b8..8d3a4c1fe761 100644 --- a/drivers/mailbox/bcm-pdc-mailbox.c +++ b/drivers/mailbox/bcm-pdc-mailbox.c @@ -1577,7 +1577,6 @@ static int pdc_probe(struct platform_device *pdev) pdcs->pdc_reg_vbase = devm_ioremap_resource(&pdev->dev, pdc_regs); if (IS_ERR(pdcs->pdc_reg_vbase)) { err = PTR_ERR(pdcs->pdc_reg_vbase); - dev_err(&pdev->dev, "Failed to map registers: %d\n", err); goto cleanup_ring_pool; } diff --git a/drivers/mailbox/bcm2835-mailbox.c b/drivers/mailbox/bcm2835-mailbox.c index 39761d190545..86b7ce3549c5 100644 --- a/drivers/mailbox/bcm2835-mailbox.c +++ b/drivers/mailbox/bcm2835-mailbox.c @@ -157,7 +157,6 @@ static int bcm2835_mbox_probe(struct platform_device *pdev) mbox->regs = devm_ioremap_resource(&pdev->dev, iomem); if (IS_ERR(mbox->regs)) { ret = PTR_ERR(mbox->regs); - dev_err(&pdev->dev, "Failed to remap mailbox regs: %d\n", ret); return ret; } diff --git a/drivers/mailbox/hi3660-mailbox.c b/drivers/mailbox/hi3660-mailbox.c index 53f4bc2488c5..395ddc250828 100644 --- a/drivers/mailbox/hi3660-mailbox.c +++ b/drivers/mailbox/hi3660-mailbox.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -// Copyright (c) 2017-2018 Hisilicon Limited. +// Copyright (c) 2017-2018 HiSilicon Limited. // Copyright (c) 2017-2018 Linaro Limited. #include diff --git a/drivers/mailbox/hi6220-mailbox.c b/drivers/mailbox/hi6220-mailbox.c index cc236ac7a0b5..560cd09538b1 100644 --- a/drivers/mailbox/hi6220-mailbox.c +++ b/drivers/mailbox/hi6220-mailbox.c @@ -2,7 +2,7 @@ /* * Hisilicon's Hi6220 mailbox driver * - * Copyright (c) 2015 Hisilicon Limited. + * Copyright (c) 2015 HiSilicon Limited. * Copyright (c) 2015 Linaro Limited. * * Author: Leo Yan diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c index 2543c7b6948b..0ce75c6b36b6 100644 --- a/drivers/mailbox/imx-mailbox.c +++ b/drivers/mailbox/imx-mailbox.c @@ -15,20 +15,6 @@ #include #include -#define IMX_MU_xSR_GIPn(x) BIT(28 + (3 - (x))) -#define IMX_MU_xSR_RFn(x) BIT(24 + (3 - (x))) -#define IMX_MU_xSR_TEn(x) BIT(20 + (3 - (x))) -#define IMX_MU_xSR_BRDIP BIT(9) - -/* General Purpose Interrupt Enable */ -#define IMX_MU_xCR_GIEn(x) BIT(28 + (3 - (x))) -/* Receive Interrupt Enable */ -#define IMX_MU_xCR_RIEn(x) BIT(24 + (3 - (x))) -/* Transmit Interrupt Enable */ -#define IMX_MU_xCR_TIEn(x) BIT(20 + (3 - (x))) -/* General Purpose Interrupt Request */ -#define IMX_MU_xCR_GIRn(x) BIT(16 + (3 - (x))) - #define IMX_MU_CHANS 16 /* TX0/RX0/RXDB[0-3] */ #define IMX_MU_SCU_CHANS 6 @@ -41,6 +27,21 @@ enum imx_mu_chan_type { IMX_MU_TYPE_RXDB, /* Rx doorbell */ }; +enum imx_mu_xcr { + IMX_MU_GIER, + IMX_MU_GCR, + IMX_MU_TCR, + IMX_MU_RCR, + IMX_MU_xCR_MAX, +}; + +enum imx_mu_xsr { + IMX_MU_SR, + IMX_MU_GSR, + IMX_MU_TSR, + IMX_MU_RSR, +}; + struct imx_sc_rpc_msg_max { struct imx_sc_rpc_msg hdr; u32 data[7]; @@ -67,21 +68,41 @@ struct imx_mu_priv { struct clk *clk; int irq; - u32 xcr; + u32 xcr[4]; bool side_b; }; +enum imx_mu_type { + IMX_MU_V1, + IMX_MU_V2, +}; + struct imx_mu_dcfg { int (*tx)(struct imx_mu_priv *priv, struct imx_mu_con_priv *cp, void *data); int (*rx)(struct imx_mu_priv *priv, struct imx_mu_con_priv *cp); void (*init)(struct imx_mu_priv *priv); - u32 xTR[4]; /* Transmit Registers */ - u32 xRR[4]; /* Receive Registers */ - u32 xSR; /* Status Register */ - u32 xCR; /* Control Register */ + enum imx_mu_type type; + u32 xTR; /* Transmit Register0 */ + u32 xRR; /* Receive Register0 */ + u32 xSR[4]; /* Status Registers */ + u32 xCR[4]; /* Control Registers */ }; +#define IMX_MU_xSR_GIPn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(28 + (3 - (x)))) +#define IMX_MU_xSR_RFn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(24 + (3 - (x)))) +#define IMX_MU_xSR_TEn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(20 + (3 - (x)))) + +/* General Purpose Interrupt Enable */ +#define IMX_MU_xCR_GIEn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(28 + (3 - (x)))) +/* Receive Interrupt Enable */ +#define IMX_MU_xCR_RIEn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(24 + (3 - (x)))) +/* Transmit Interrupt Enable */ +#define IMX_MU_xCR_TIEn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(20 + (3 - (x)))) +/* General Purpose Interrupt Request */ +#define IMX_MU_xCR_GIRn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(16 + (3 - (x)))) + + static struct imx_mu_priv *to_imx_mu_priv(struct mbox_controller *mbox) { return container_of(mbox, struct imx_mu_priv, mbox); @@ -97,16 +118,16 @@ static u32 imx_mu_read(struct imx_mu_priv *priv, u32 offs) return ioread32(priv->base + offs); } -static u32 imx_mu_xcr_rmw(struct imx_mu_priv *priv, u32 set, u32 clr) +static u32 imx_mu_xcr_rmw(struct imx_mu_priv *priv, enum imx_mu_xcr type, u32 set, u32 clr) { unsigned long flags; u32 val; spin_lock_irqsave(&priv->xcr_lock, flags); - val = imx_mu_read(priv, priv->dcfg->xCR); + val = imx_mu_read(priv, priv->dcfg->xCR[type]); val &= ~clr; val |= set; - imx_mu_write(priv, val, priv->dcfg->xCR); + imx_mu_write(priv, val, priv->dcfg->xCR[type]); spin_unlock_irqrestore(&priv->xcr_lock, flags); return val; @@ -120,11 +141,11 @@ static int imx_mu_generic_tx(struct imx_mu_priv *priv, switch (cp->type) { case IMX_MU_TYPE_TX: - imx_mu_write(priv, *arg, priv->dcfg->xTR[cp->idx]); - imx_mu_xcr_rmw(priv, IMX_MU_xCR_TIEn(cp->idx), 0); + imx_mu_write(priv, *arg, priv->dcfg->xTR + cp->idx * 4); + imx_mu_xcr_rmw(priv, IMX_MU_TCR, IMX_MU_xCR_TIEn(priv->dcfg->type, cp->idx), 0); break; case IMX_MU_TYPE_TXDB: - imx_mu_xcr_rmw(priv, IMX_MU_xCR_GIRn(cp->idx), 0); + imx_mu_xcr_rmw(priv, IMX_MU_GCR, IMX_MU_xCR_GIRn(priv->dcfg->type, cp->idx), 0); tasklet_schedule(&cp->txdb_tasklet); break; default: @@ -140,7 +161,7 @@ static int imx_mu_generic_rx(struct imx_mu_priv *priv, { u32 dat; - dat = imx_mu_read(priv, priv->dcfg->xRR[cp->idx]); + dat = imx_mu_read(priv, priv->dcfg->xRR + (cp->idx) * 4); mbox_chan_received_data(cp->chan, (void *)&dat); return 0; @@ -172,20 +193,20 @@ static int imx_mu_scu_tx(struct imx_mu_priv *priv, } for (i = 0; i < 4 && i < msg->hdr.size; i++) - imx_mu_write(priv, *arg++, priv->dcfg->xTR[i % 4]); + imx_mu_write(priv, *arg++, priv->dcfg->xTR + (i % 4) * 4); for (; i < msg->hdr.size; i++) { - ret = readl_poll_timeout(priv->base + priv->dcfg->xSR, + ret = readl_poll_timeout(priv->base + priv->dcfg->xSR[IMX_MU_TSR], xsr, - xsr & IMX_MU_xSR_TEn(i % 4), + xsr & IMX_MU_xSR_TEn(priv->dcfg->type, i % 4), 0, 100); if (ret) { dev_err(priv->dev, "Send data index: %d timeout\n", i); return ret; } - imx_mu_write(priv, *arg++, priv->dcfg->xTR[i % 4]); + imx_mu_write(priv, *arg++, priv->dcfg->xTR + (i % 4) * 4); } - imx_mu_xcr_rmw(priv, IMX_MU_xCR_TIEn(cp->idx), 0); + imx_mu_xcr_rmw(priv, IMX_MU_TCR, IMX_MU_xCR_TIEn(priv->dcfg->type, cp->idx), 0); break; default: dev_warn_ratelimited(priv->dev, "Send data on wrong channel type: %d\n", cp->type); @@ -203,8 +224,8 @@ static int imx_mu_scu_rx(struct imx_mu_priv *priv, int i, ret; u32 xsr; - imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_RIEn(0)); - *data++ = imx_mu_read(priv, priv->dcfg->xRR[0]); + imx_mu_xcr_rmw(priv, IMX_MU_RCR, 0, IMX_MU_xCR_RIEn(priv->dcfg->type, 0)); + *data++ = imx_mu_read(priv, priv->dcfg->xRR); if (msg.hdr.size > sizeof(msg) / 4) { dev_err(priv->dev, "Maximal message size (%zu bytes) exceeded on RX; got: %i bytes\n", sizeof(msg), msg.hdr.size << 2); @@ -212,16 +233,16 @@ static int imx_mu_scu_rx(struct imx_mu_priv *priv, } for (i = 1; i < msg.hdr.size; i++) { - ret = readl_poll_timeout(priv->base + priv->dcfg->xSR, xsr, - xsr & IMX_MU_xSR_RFn(i % 4), 0, 100); + ret = readl_poll_timeout(priv->base + priv->dcfg->xSR[IMX_MU_RSR], xsr, + xsr & IMX_MU_xSR_RFn(priv->dcfg->type, i % 4), 0, 100); if (ret) { dev_err(priv->dev, "timeout read idx %d\n", i); return ret; } - *data++ = imx_mu_read(priv, priv->dcfg->xRR[i % 4]); + *data++ = imx_mu_read(priv, priv->dcfg->xRR + (i % 4) * 4); } - imx_mu_xcr_rmw(priv, IMX_MU_xCR_RIEn(0), 0); + imx_mu_xcr_rmw(priv, IMX_MU_RCR, IMX_MU_xCR_RIEn(priv->dcfg->type, 0), 0); mbox_chan_received_data(cp->chan, (void *)&msg); return 0; @@ -241,36 +262,45 @@ static irqreturn_t imx_mu_isr(int irq, void *p) struct imx_mu_con_priv *cp = chan->con_priv; u32 val, ctrl; - ctrl = imx_mu_read(priv, priv->dcfg->xCR); - val = imx_mu_read(priv, priv->dcfg->xSR); - switch (cp->type) { case IMX_MU_TYPE_TX: - val &= IMX_MU_xSR_TEn(cp->idx) & - (ctrl & IMX_MU_xCR_TIEn(cp->idx)); + ctrl = imx_mu_read(priv, priv->dcfg->xCR[IMX_MU_TCR]); + val = imx_mu_read(priv, priv->dcfg->xSR[IMX_MU_TSR]); + val &= IMX_MU_xSR_TEn(priv->dcfg->type, cp->idx) & + (ctrl & IMX_MU_xCR_TIEn(priv->dcfg->type, cp->idx)); break; case IMX_MU_TYPE_RX: - val &= IMX_MU_xSR_RFn(cp->idx) & - (ctrl & IMX_MU_xCR_RIEn(cp->idx)); + ctrl = imx_mu_read(priv, priv->dcfg->xCR[IMX_MU_RCR]); + val = imx_mu_read(priv, priv->dcfg->xSR[IMX_MU_RSR]); + val &= IMX_MU_xSR_RFn(priv->dcfg->type, cp->idx) & + (ctrl & IMX_MU_xCR_RIEn(priv->dcfg->type, cp->idx)); break; case IMX_MU_TYPE_RXDB: - val &= IMX_MU_xSR_GIPn(cp->idx) & - (ctrl & IMX_MU_xCR_GIEn(cp->idx)); + ctrl = imx_mu_read(priv, priv->dcfg->xCR[IMX_MU_GIER]); + val = imx_mu_read(priv, priv->dcfg->xSR[IMX_MU_GSR]); + val &= IMX_MU_xSR_GIPn(priv->dcfg->type, cp->idx) & + (ctrl & IMX_MU_xCR_GIEn(priv->dcfg->type, cp->idx)); break; default: - break; + dev_warn_ratelimited(priv->dev, "Unhandled channel type %d\n", + cp->type); + return IRQ_NONE; } if (!val) return IRQ_NONE; - if (val == IMX_MU_xSR_TEn(cp->idx)) { - imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_TIEn(cp->idx)); + if ((val == IMX_MU_xSR_TEn(priv->dcfg->type, cp->idx)) && + (cp->type == IMX_MU_TYPE_TX)) { + imx_mu_xcr_rmw(priv, IMX_MU_TCR, 0, IMX_MU_xCR_TIEn(priv->dcfg->type, cp->idx)); mbox_chan_txdone(chan, 0); - } else if (val == IMX_MU_xSR_RFn(cp->idx)) { + } else if ((val == IMX_MU_xSR_RFn(priv->dcfg->type, cp->idx)) && + (cp->type == IMX_MU_TYPE_RX)) { priv->dcfg->rx(priv, cp); - } else if (val == IMX_MU_xSR_GIPn(cp->idx)) { - imx_mu_write(priv, IMX_MU_xSR_GIPn(cp->idx), priv->dcfg->xSR); + } else if ((val == IMX_MU_xSR_GIPn(priv->dcfg->type, cp->idx)) && + (cp->type == IMX_MU_TYPE_RXDB)) { + imx_mu_write(priv, IMX_MU_xSR_GIPn(priv->dcfg->type, cp->idx), + priv->dcfg->xSR[IMX_MU_GSR]); mbox_chan_received_data(chan, NULL); } else { dev_warn_ratelimited(priv->dev, "Not handled interrupt\n"); @@ -317,10 +347,10 @@ static int imx_mu_startup(struct mbox_chan *chan) switch (cp->type) { case IMX_MU_TYPE_RX: - imx_mu_xcr_rmw(priv, IMX_MU_xCR_RIEn(cp->idx), 0); + imx_mu_xcr_rmw(priv, IMX_MU_RCR, IMX_MU_xCR_RIEn(priv->dcfg->type, cp->idx), 0); break; case IMX_MU_TYPE_RXDB: - imx_mu_xcr_rmw(priv, IMX_MU_xCR_GIEn(cp->idx), 0); + imx_mu_xcr_rmw(priv, IMX_MU_GIER, IMX_MU_xCR_GIEn(priv->dcfg->type, cp->idx), 0); break; default: break; @@ -342,13 +372,13 @@ static void imx_mu_shutdown(struct mbox_chan *chan) switch (cp->type) { case IMX_MU_TYPE_TX: - imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_TIEn(cp->idx)); + imx_mu_xcr_rmw(priv, IMX_MU_TCR, 0, IMX_MU_xCR_TIEn(priv->dcfg->type, cp->idx)); break; case IMX_MU_TYPE_RX: - imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_RIEn(cp->idx)); + imx_mu_xcr_rmw(priv, IMX_MU_RCR, 0, IMX_MU_xCR_RIEn(priv->dcfg->type, cp->idx)); break; case IMX_MU_TYPE_RXDB: - imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_GIEn(cp->idx)); + imx_mu_xcr_rmw(priv, IMX_MU_GIER, 0, IMX_MU_xCR_GIEn(priv->dcfg->type, cp->idx)); break; default: break; @@ -444,7 +474,8 @@ static void imx_mu_init_generic(struct imx_mu_priv *priv) return; /* Set default MU configuration */ - imx_mu_write(priv, 0, priv->dcfg->xCR); + for (i = 0; i < IMX_MU_xCR_MAX; i++) + imx_mu_write(priv, 0, priv->dcfg->xCR[i]); } static void imx_mu_init_scu(struct imx_mu_priv *priv) @@ -466,7 +497,8 @@ static void imx_mu_init_scu(struct imx_mu_priv *priv) priv->mbox.of_xlate = imx_mu_scu_xlate; /* Set default MU configuration */ - imx_mu_write(priv, 0, priv->dcfg->xCR); + for (i = 0; i < IMX_MU_xCR_MAX; i++) + imx_mu_write(priv, 0, priv->dcfg->xCR[i]); } static int imx_mu_probe(struct platform_device *pdev) @@ -564,35 +596,47 @@ static const struct imx_mu_dcfg imx_mu_cfg_imx6sx = { .tx = imx_mu_generic_tx, .rx = imx_mu_generic_rx, .init = imx_mu_init_generic, - .xTR = {0x0, 0x4, 0x8, 0xc}, - .xRR = {0x10, 0x14, 0x18, 0x1c}, - .xSR = 0x20, - .xCR = 0x24, + .xTR = 0x0, + .xRR = 0x10, + .xSR = {0x20, 0x20, 0x20, 0x20}, + .xCR = {0x24, 0x24, 0x24, 0x24}, }; static const struct imx_mu_dcfg imx_mu_cfg_imx7ulp = { .tx = imx_mu_generic_tx, .rx = imx_mu_generic_rx, .init = imx_mu_init_generic, - .xTR = {0x20, 0x24, 0x28, 0x2c}, - .xRR = {0x40, 0x44, 0x48, 0x4c}, - .xSR = 0x60, - .xCR = 0x64, + .xTR = 0x20, + .xRR = 0x40, + .xSR = {0x60, 0x60, 0x60, 0x60}, + .xCR = {0x64, 0x64, 0x64, 0x64}, +}; + +static const struct imx_mu_dcfg imx_mu_cfg_imx8ulp = { + .tx = imx_mu_generic_tx, + .rx = imx_mu_generic_rx, + .init = imx_mu_init_generic, + .type = IMX_MU_V2, + .xTR = 0x200, + .xRR = 0x280, + .xSR = {0xC, 0x118, 0x124, 0x12C}, + .xCR = {0x110, 0x114, 0x120, 0x128}, }; static const struct imx_mu_dcfg imx_mu_cfg_imx8_scu = { .tx = imx_mu_scu_tx, .rx = imx_mu_scu_rx, .init = imx_mu_init_scu, - .xTR = {0x0, 0x4, 0x8, 0xc}, - .xRR = {0x10, 0x14, 0x18, 0x1c}, - .xSR = 0x20, - .xCR = 0x24, + .xTR = 0x0, + .xRR = 0x10, + .xSR = {0x20, 0x20, 0x20, 0x20}, + .xCR = {0x24, 0x24, 0x24, 0x24}, }; static const struct of_device_id imx_mu_dt_ids[] = { { .compatible = "fsl,imx7ulp-mu", .data = &imx_mu_cfg_imx7ulp }, { .compatible = "fsl,imx6sx-mu", .data = &imx_mu_cfg_imx6sx }, + { .compatible = "fsl,imx8ulp-mu", .data = &imx_mu_cfg_imx8ulp }, { .compatible = "fsl,imx8-mu-scu", .data = &imx_mu_cfg_imx8_scu }, { }, }; @@ -601,9 +645,12 @@ MODULE_DEVICE_TABLE(of, imx_mu_dt_ids); static int __maybe_unused imx_mu_suspend_noirq(struct device *dev) { struct imx_mu_priv *priv = dev_get_drvdata(dev); + int i; - if (!priv->clk) - priv->xcr = imx_mu_read(priv, priv->dcfg->xCR); + if (!priv->clk) { + for (i = 0; i < IMX_MU_xCR_MAX; i++) + priv->xcr[i] = imx_mu_read(priv, priv->dcfg->xCR[i]); + } return 0; } @@ -611,6 +658,7 @@ static int __maybe_unused imx_mu_suspend_noirq(struct device *dev) static int __maybe_unused imx_mu_resume_noirq(struct device *dev) { struct imx_mu_priv *priv = dev_get_drvdata(dev); + int i; /* * ONLY restore MU when context lost, the TIE could @@ -620,8 +668,10 @@ static int __maybe_unused imx_mu_resume_noirq(struct device *dev) * send failed, may lead to system freeze. This issue * is observed by testing freeze mode suspend. */ - if (!imx_mu_read(priv, priv->dcfg->xCR) && !priv->clk) - imx_mu_write(priv, priv->xcr, priv->dcfg->xCR); + if (!imx_mu_read(priv, priv->dcfg->xCR[0]) && !priv->clk) { + for (i = 0; i < IMX_MU_xCR_MAX; i++) + imx_mu_write(priv, priv->xcr[i], priv->dcfg->xCR[i]); + } return 0; } diff --git a/drivers/mailbox/mailbox-mpfs.c b/drivers/mailbox/mailbox-mpfs.c new file mode 100644 index 000000000000..0d6e2231a2c7 --- /dev/null +++ b/drivers/mailbox/mailbox-mpfs.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Microchip PolarFire SoC (MPFS) system controller/mailbox controller driver + * + * Copyright (c) 2020 Microchip Corporation. All rights reserved. + * + * Author: Conor Dooley + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define SERVICES_CR_OFFSET 0x50u +#define SERVICES_SR_OFFSET 0x54u +#define MAILBOX_REG_OFFSET 0x800u +#define MSS_SYS_MAILBOX_DATA_OFFSET 0u +#define SCB_MASK_WIDTH 16u + +/* SCBCTRL service control register */ + +#define SCB_CTRL_REQ (0) +#define SCB_CTRL_REQ_MASK BIT(SCB_CTRL_REQ) + +#define SCB_CTRL_BUSY (1) +#define SCB_CTRL_BUSY_MASK BIT(SCB_CTRL_BUSY) + +#define SCB_CTRL_ABORT (2) +#define SCB_CTRL_ABORT_MASK BIT(SCB_CTRL_ABORT) + +#define SCB_CTRL_NOTIFY (3) +#define SCB_CTRL_NOTIFY_MASK BIT(SCB_CTRL_NOTIFY) + +#define SCB_CTRL_POS (16) +#define SCB_CTRL_MASK GENMASK_ULL(SCB_CTRL_POS + SCB_MASK_WIDTH, SCB_CTRL_POS) + +/* SCBCTRL service status register */ + +#define SCB_STATUS_REQ (0) +#define SCB_STATUS_REQ_MASK BIT(SCB_STATUS_REQ) + +#define SCB_STATUS_BUSY (1) +#define SCB_STATUS_BUSY_MASK BIT(SCB_STATUS_BUSY) + +#define SCB_STATUS_ABORT (2) +#define SCB_STATUS_ABORT_MASK BIT(SCB_STATUS_ABORT) + +#define SCB_STATUS_NOTIFY (3) +#define SCB_STATUS_NOTIFY_MASK BIT(SCB_STATUS_NOTIFY) + +#define SCB_STATUS_POS (16) +#define SCB_STATUS_MASK GENMASK_ULL(SCB_STATUS_POS + SCB_MASK_WIDTH, SCB_STATUS_POS) + +struct mpfs_mbox { + struct mbox_controller controller; + struct device *dev; + int irq; + void __iomem *mbox_base; + void __iomem *int_reg; + struct mbox_chan chans[1]; + struct mpfs_mss_response *response; + u16 resp_offset; +}; + +static bool mpfs_mbox_busy(struct mpfs_mbox *mbox) +{ + u32 status; + + status = readl_relaxed(mbox->mbox_base + SERVICES_SR_OFFSET); + + return status & SCB_STATUS_BUSY_MASK; +} + +static int mpfs_mbox_send_data(struct mbox_chan *chan, void *data) +{ + struct mpfs_mbox *mbox = (struct mpfs_mbox *)chan->con_priv; + struct mpfs_mss_msg *msg = data; + u32 tx_trigger; + u16 opt_sel; + u32 val = 0u; + + mbox->response = msg->response; + mbox->resp_offset = msg->resp_offset; + + if (mpfs_mbox_busy(mbox)) + return -EBUSY; + + if (msg->cmd_data_size) { + u32 index; + u8 extra_bits = msg->cmd_data_size & 3; + u32 *word_buf = (u32 *)msg->cmd_data; + + for (index = 0; index < (msg->cmd_data_size / 4); index++) + writel_relaxed(word_buf[index], + mbox->mbox_base + MAILBOX_REG_OFFSET + index * 0x4); + if (extra_bits) { + u8 i; + u8 byte_off = ALIGN_DOWN(msg->cmd_data_size, 4); + u8 *byte_buf = msg->cmd_data + byte_off; + + val = readl_relaxed(mbox->mbox_base + + MAILBOX_REG_OFFSET + index * 0x4); + + for (i = 0u; i < extra_bits; i++) { + val &= ~(0xffu << (i * 8u)); + val |= (byte_buf[i] << (i * 8u)); + } + + writel_relaxed(val, + mbox->mbox_base + MAILBOX_REG_OFFSET + index * 0x4); + } + } + + opt_sel = ((msg->mbox_offset << 7u) | (msg->cmd_opcode & 0x7fu)); + tx_trigger = (opt_sel << SCB_CTRL_POS) & SCB_CTRL_MASK; + tx_trigger |= SCB_CTRL_REQ_MASK | SCB_STATUS_NOTIFY_MASK; + writel_relaxed(tx_trigger, mbox->mbox_base + SERVICES_CR_OFFSET); + + return 0; +} + +static void mpfs_mbox_rx_data(struct mbox_chan *chan) +{ + struct mpfs_mbox *mbox = (struct mpfs_mbox *)chan->con_priv; + struct mpfs_mss_response *response = mbox->response; + u16 num_words = ALIGN((response->resp_size), (4)) / 4U; + u32 i; + + if (!response->resp_msg) { + dev_err(mbox->dev, "failed to assign memory for response %d\n", -ENOMEM); + return; + } + + if (!mpfs_mbox_busy(mbox)) { + for (i = 0; i < num_words; i++) { + response->resp_msg[i] = + readl_relaxed(mbox->mbox_base + MAILBOX_REG_OFFSET + + mbox->resp_offset + i * 0x4); + } + } + + mbox_chan_received_data(chan, response); +} + +static irqreturn_t mpfs_mbox_inbox_isr(int irq, void *data) +{ + struct mbox_chan *chan = data; + struct mpfs_mbox *mbox = (struct mpfs_mbox *)chan->con_priv; + + writel_relaxed(0, mbox->int_reg); + + mpfs_mbox_rx_data(chan); + + mbox_chan_txdone(chan, 0); + return IRQ_HANDLED; +} + +static int mpfs_mbox_startup(struct mbox_chan *chan) +{ + struct mpfs_mbox *mbox = (struct mpfs_mbox *)chan->con_priv; + int ret = 0; + + if (!mbox) + return -EINVAL; + + ret = devm_request_irq(mbox->dev, mbox->irq, mpfs_mbox_inbox_isr, 0, "mpfs-mailbox", chan); + if (ret) + dev_err(mbox->dev, "failed to register mailbox interrupt:%d\n", ret); + + return ret; +} + +static void mpfs_mbox_shutdown(struct mbox_chan *chan) +{ + struct mpfs_mbox *mbox = (struct mpfs_mbox *)chan->con_priv; + + devm_free_irq(mbox->dev, mbox->irq, chan); +} + +static const struct mbox_chan_ops mpfs_mbox_ops = { + .send_data = mpfs_mbox_send_data, + .startup = mpfs_mbox_startup, + .shutdown = mpfs_mbox_shutdown, +}; + +static int mpfs_mbox_probe(struct platform_device *pdev) +{ + struct mpfs_mbox *mbox; + struct resource *regs; + int ret; + + mbox = devm_kzalloc(&pdev->dev, sizeof(*mbox), GFP_KERNEL); + if (!mbox) + return -ENOMEM; + + mbox->mbox_base = devm_platform_get_and_ioremap_resource(pdev, 0, ®s); + if (IS_ERR(mbox->mbox_base)) + return PTR_ERR(mbox->mbox_base); + + mbox->int_reg = devm_platform_get_and_ioremap_resource(pdev, 1, ®s); + if (IS_ERR(mbox->int_reg)) + return PTR_ERR(mbox->int_reg); + + mbox->irq = platform_get_irq(pdev, 0); + if (mbox->irq < 0) + return mbox->irq; + + mbox->dev = &pdev->dev; + + mbox->chans[0].con_priv = mbox; + mbox->controller.dev = mbox->dev; + mbox->controller.num_chans = 1; + mbox->controller.chans = mbox->chans; + mbox->controller.ops = &mpfs_mbox_ops; + mbox->controller.txdone_irq = true; + + ret = devm_mbox_controller_register(&pdev->dev, &mbox->controller); + if (ret) { + dev_err(&pdev->dev, "Registering MPFS mailbox controller failed\n"); + return ret; + } + dev_info(&pdev->dev, "Registered MPFS mailbox controller driver\n"); + + return 0; +} + +static const struct of_device_id mpfs_mbox_of_match[] = { + {.compatible = "microchip,polarfire-soc-mailbox", }, + {}, +}; +MODULE_DEVICE_TABLE(of, mpfs_mbox_of_match); + +static struct platform_driver mpfs_mbox_driver = { + .driver = { + .name = "mpfs-mailbox", + .of_match_table = mpfs_mbox_of_match, + }, + .probe = mpfs_mbox_probe, +}; +module_platform_driver(mpfs_mbox_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Conor Dooley "); +MODULE_DESCRIPTION("MPFS mailbox controller driver"); diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c index 5665b6ea8119..67a42b514429 100644 --- a/drivers/mailbox/mtk-cmdq-mailbox.c +++ b/drivers/mailbox/mtk-cmdq-mailbox.c @@ -180,7 +180,7 @@ static bool cmdq_thread_is_in_wfe(struct cmdq_thread *thread) return readl(thread->base + CMDQ_THR_WAIT_TOKEN) & CMDQ_THR_IS_WAITING; } -static void cmdq_task_exec_done(struct cmdq_task *task, enum cmdq_cb_status sta) +static void cmdq_task_exec_done(struct cmdq_task *task, int sta) { struct cmdq_task_cb *cb = &task->pkt->async_cb; struct cmdq_cb_data data; @@ -188,7 +188,11 @@ static void cmdq_task_exec_done(struct cmdq_task *task, enum cmdq_cb_status sta) WARN_ON(cb->cb == (cmdq_async_flush_cb)NULL); data.sta = sta; data.data = cb->data; - cb->cb(data); + data.pkt = task->pkt; + if (cb->cb) + cb->cb(data); + + mbox_chan_received_data(task->thread->chan, &data); list_del(&task->list_entry); } @@ -244,10 +248,10 @@ static void cmdq_thread_irq_handler(struct cmdq *cmdq, curr_task = task; if (!curr_task || curr_pa == task_end_pa - CMDQ_INST_SIZE) { - cmdq_task_exec_done(task, CMDQ_CB_NORMAL); + cmdq_task_exec_done(task, 0); kfree(task); } else if (err) { - cmdq_task_exec_done(task, CMDQ_CB_ERROR); + cmdq_task_exec_done(task, -ENOEXEC); cmdq_task_handle_error(curr_task); kfree(task); } @@ -415,7 +419,7 @@ static void cmdq_mbox_shutdown(struct mbox_chan *chan) list_for_each_entry_safe(task, tmp, &thread->task_busy_list, list_entry) { - cmdq_task_exec_done(task, CMDQ_CB_ERROR); + cmdq_task_exec_done(task, -ECONNABORTED); kfree(task); } @@ -452,11 +456,13 @@ static int cmdq_mbox_flush(struct mbox_chan *chan, unsigned long timeout) list_for_each_entry_safe(task, tmp, &thread->task_busy_list, list_entry) { cb = &task->pkt->async_cb; - if (cb->cb) { - data.sta = CMDQ_CB_ERROR; - data.data = cb->data; + data.sta = -ECONNABORTED; + data.data = cb->data; + data.pkt = task->pkt; + if (cb->cb) cb->cb(data); - } + + mbox_chan_received_data(task->thread->chan, &data); list_del(&task->list_entry); kfree(task); } @@ -519,10 +525,8 @@ static int cmdq_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); cmdq->base = devm_ioremap_resource(dev, res); - if (IS_ERR(cmdq->base)) { - dev_err(dev, "failed to ioremap gce\n"); + if (IS_ERR(cmdq->base)) return PTR_ERR(cmdq->base); - } cmdq->irq = platform_get_irq(pdev, 0); if (cmdq->irq < 0) diff --git a/drivers/mailbox/qcom-apcs-ipc-mailbox.c b/drivers/mailbox/qcom-apcs-ipc-mailbox.c index f25324d03842..03bdc96dc457 100644 --- a/drivers/mailbox/qcom-apcs-ipc-mailbox.c +++ b/drivers/mailbox/qcom-apcs-ipc-mailbox.c @@ -57,6 +57,10 @@ static const struct qcom_apcs_ipc_data sdm660_apcs_data = { .offset = 8, .clk_name = NULL }; +static const struct qcom_apcs_ipc_data sm6125_apcs_data = { + .offset = 8, .clk_name = NULL +}; + static const struct qcom_apcs_ipc_data apps_shared_apcs_data = { .offset = 12, .clk_name = NULL }; @@ -132,7 +136,7 @@ static int qcom_apcs_ipc_probe(struct platform_device *pdev) if (apcs_data->clk_name) { apcs->clk = platform_device_register_data(&pdev->dev, apcs_data->clk_name, - PLATFORM_DEVID_NONE, + PLATFORM_DEVID_AUTO, NULL, 0); if (IS_ERR(apcs->clk)) dev_err(&pdev->dev, "failed to register APCS clk\n"); @@ -158,6 +162,7 @@ static const struct of_device_id qcom_apcs_ipc_of_match[] = { { .compatible = "qcom,ipq6018-apcs-apps-global", .data = &ipq6018_apcs_data }, { .compatible = "qcom,ipq8074-apcs-apps-global", .data = &ipq8074_apcs_data }, { .compatible = "qcom,msm8916-apcs-kpss-global", .data = &msm8916_apcs_data }, + { .compatible = "qcom,msm8939-apcs-kpss-global", .data = &msm8916_apcs_data }, { .compatible = "qcom,msm8994-apcs-kpss-global", .data = &msm8994_apcs_data }, { .compatible = "qcom,msm8996-apcs-hmss-global", .data = &msm8996_apcs_data }, { .compatible = "qcom,msm8998-apcs-hmss-global", .data = &msm8998_apcs_data }, @@ -166,6 +171,7 @@ static const struct of_device_id qcom_apcs_ipc_of_match[] = { { .compatible = "qcom,sc8180x-apss-shared", .data = &apps_shared_apcs_data }, { .compatible = "qcom,sdm660-apcs-hmss-global", .data = &sdm660_apcs_data }, { .compatible = "qcom,sdm845-apss-shared", .data = &apps_shared_apcs_data }, + { .compatible = "qcom,sm6125-apcs-hmss-global", .data = &sm6125_apcs_data }, { .compatible = "qcom,sm8150-apss-shared", .data = &apps_shared_apcs_data }, { .compatible = "qcom,sdx55-apcs-gcc", .data = &sdx55_apcs_data }, {} diff --git a/drivers/mailbox/qcom-ipcc.c b/drivers/mailbox/qcom-ipcc.c index 2d13c72944c6..584700cd1585 100644 --- a/drivers/mailbox/qcom-ipcc.c +++ b/drivers/mailbox/qcom-ipcc.c @@ -155,6 +155,11 @@ static int qcom_ipcc_mbox_send_data(struct mbox_chan *chan, void *data) return 0; } +static void qcom_ipcc_mbox_shutdown(struct mbox_chan *chan) +{ + chan->con_priv = NULL; +} + static struct mbox_chan *qcom_ipcc_mbox_xlate(struct mbox_controller *mbox, const struct of_phandle_args *ph) { @@ -184,6 +189,7 @@ static struct mbox_chan *qcom_ipcc_mbox_xlate(struct mbox_controller *mbox, static const struct mbox_chan_ops ipcc_mbox_chan_ops = { .send_data = qcom_ipcc_mbox_send_data, + .shutdown = qcom_ipcc_mbox_shutdown, }; static int qcom_ipcc_setup_mbox(struct qcom_ipcc *ipcc) diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 741574b94c22..dae460699a8f 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -47,7 +47,7 @@ config MD_AUTODETECT If unsure, say Y. config MD_LINEAR - tristate "Linear (append) mode" + tristate "Linear (append) mode (deprecated)" depends on BLK_DEV_MD help If you say Y here, then your multiple devices driver will be able to @@ -158,7 +158,7 @@ config MD_RAID456 If unsure, say Y. config MD_MULTIPATH - tristate "Multipath I/O support" + tristate "Multipath I/O support (deprecated)" depends on BLK_DEV_MD help MD_MULTIPATH provides a simple multi-path personality for use @@ -169,7 +169,7 @@ config MD_MULTIPATH If unsure, say N. config MD_FAULTY - tristate "Faulty test module for MD" + tristate "Faulty test module for MD (deprecated)" depends on BLK_DEV_MD help The "faulty" module allows for a block device that occasionally returns diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 780e478de264..224986c9fe74 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -95,6 +95,10 @@ ifeq ($(CONFIG_DM_UEVENT),y) dm-mod-objs += dm-uevent.o endif +ifeq ($(CONFIG_BLK_DEV_ZONED),y) +dm-mod-objs += dm-zone.o +endif + ifeq ($(CONFIG_DM_VERITY_FEC),y) dm-verity-objs += dm-verity-fec.o endif diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index bea8c4429ae8..185246a0d855 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -890,13 +890,9 @@ static void bcache_device_free(struct bcache_device *d) if (disk_added) del_gendisk(disk); - if (disk->queue) - blk_cleanup_queue(disk->queue); - + blk_cleanup_disk(disk); ida_simple_remove(&bcache_device_idx, first_minor_to_idx(disk->first_minor)); - if (disk_added) - put_disk(disk); } bioset_exit(&d->bio_split); @@ -946,7 +942,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER)) goto err; - d->disk = alloc_disk(BCACHE_MINORS); + d->disk = blk_alloc_disk(NUMA_NO_NODE); if (!d->disk) goto err; @@ -955,14 +951,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, d->disk->major = bcache_major; d->disk->first_minor = idx_to_first_minor(idx); + d->disk->minors = BCACHE_MINORS; d->disk->fops = ops; d->disk->private_data = d; - q = blk_alloc_queue(NUMA_NO_NODE); - if (!q) - return -ENOMEM; - - d->disk->queue = q; + q = d->disk->queue; q->limits.max_hw_sectors = UINT_MAX; q->limits.max_sectors = UINT_MAX; q->limits.max_segment_size = UINT_MAX; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 6ab01ff25747..8e4ced5a2516 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -8,6 +8,7 @@ #include "dm-bio-prison-v2.h" #include "dm-bio-record.h" #include "dm-cache-metadata.h" +#include "dm-io-tracker.h" #include #include @@ -39,77 +40,6 @@ DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(cache_copy_throttle, /*----------------------------------------------------------------*/ -struct io_tracker { - spinlock_t lock; - - /* - * Sectors of in-flight IO. - */ - sector_t in_flight; - - /* - * The time, in jiffies, when this device became idle (if it is - * indeed idle). - */ - unsigned long idle_time; - unsigned long last_update_time; -}; - -static void iot_init(struct io_tracker *iot) -{ - spin_lock_init(&iot->lock); - iot->in_flight = 0ul; - iot->idle_time = 0ul; - iot->last_update_time = jiffies; -} - -static bool __iot_idle_for(struct io_tracker *iot, unsigned long jifs) -{ - if (iot->in_flight) - return false; - - return time_after(jiffies, iot->idle_time + jifs); -} - -static bool iot_idle_for(struct io_tracker *iot, unsigned long jifs) -{ - bool r; - - spin_lock_irq(&iot->lock); - r = __iot_idle_for(iot, jifs); - spin_unlock_irq(&iot->lock); - - return r; -} - -static void iot_io_begin(struct io_tracker *iot, sector_t len) -{ - spin_lock_irq(&iot->lock); - iot->in_flight += len; - spin_unlock_irq(&iot->lock); -} - -static void __iot_io_end(struct io_tracker *iot, sector_t len) -{ - if (!len) - return; - - iot->in_flight -= len; - if (!iot->in_flight) - iot->idle_time = jiffies; -} - -static void iot_io_end(struct io_tracker *iot, sector_t len) -{ - unsigned long flags; - - spin_lock_irqsave(&iot->lock, flags); - __iot_io_end(iot, len); - spin_unlock_irqrestore(&iot->lock, flags); -} - -/*----------------------------------------------------------------*/ - /* * Represents a chunk of future work. 'input' allows continuations to pass * values between themselves, typically error values. @@ -470,7 +400,7 @@ struct cache { struct batcher committer; struct work_struct commit_ws; - struct io_tracker tracker; + struct dm_io_tracker tracker; mempool_t migration_pool; @@ -866,7 +796,7 @@ static void accounted_begin(struct cache *cache, struct bio *bio) if (accountable_bio(cache, bio)) { pb = get_per_bio_data(bio); pb->len = bio_sectors(bio); - iot_io_begin(&cache->tracker, pb->len); + dm_iot_io_begin(&cache->tracker, pb->len); } } @@ -874,7 +804,7 @@ static void accounted_complete(struct cache *cache, struct bio *bio) { struct per_bio_data *pb = get_per_bio_data(bio); - iot_io_end(&cache->tracker, pb->len); + dm_iot_io_end(&cache->tracker, pb->len); } static void accounted_request(struct cache *cache, struct bio *bio) @@ -1642,7 +1572,7 @@ enum busy { static enum busy spare_migration_bandwidth(struct cache *cache) { - bool idle = iot_idle_for(&cache->tracker, HZ); + bool idle = dm_iot_idle_for(&cache->tracker, HZ); sector_t current_volume = (atomic_read(&cache->nr_io_migrations) + 1) * cache->sectors_per_block; @@ -2603,7 +2533,7 @@ static int cache_create(struct cache_args *ca, struct cache **result) batcher_init(&cache->committer, commit_op, cache, issue_op, cache, cache->wq); - iot_init(&cache->tracker); + dm_iot_init(&cache->tracker); init_rwsem(&cache->background_work_lock); prevent_background_work(cache); diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 5953ff2bd260..edc1553c4eea 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -114,8 +114,27 @@ struct mapped_device { bool init_tio_pdu:1; struct srcu_struct io_barrier; + +#ifdef CONFIG_BLK_DEV_ZONED + unsigned int nr_zones; + unsigned int *zwp_offset; +#endif }; +/* + * Bits for the flags field of struct mapped_device. + */ +#define DMF_BLOCK_IO_FOR_SUSPEND 0 +#define DMF_SUSPENDED 1 +#define DMF_FROZEN 2 +#define DMF_FREEING 3 +#define DMF_DELETING 4 +#define DMF_NOFLUSH_SUSPENDING 5 +#define DMF_DEFERRED_REMOVE 6 +#define DMF_SUSPENDED_INTERNALLY 7 +#define DMF_POST_SUSPENDING 8 +#define DMF_EMULATE_ZONE_APPEND 9 + void disable_discard(struct mapped_device *md); void disable_write_same(struct mapped_device *md); void disable_write_zeroes(struct mapped_device *md); @@ -130,6 +149,13 @@ static inline struct dm_stats *dm_get_stats(struct mapped_device *md) return &md->stats; } +static inline bool dm_emulate_zone_append(struct mapped_device *md) +{ + if (blk_queue_is_zoned(md->queue)) + return test_bit(DMF_EMULATE_ZONE_APPEND, &md->flags); + return false; +} + #define DM_TABLE_MAX_DEPTH 16 struct dm_table { @@ -173,6 +199,45 @@ struct dm_table { #endif }; +/* + * One of these is allocated per clone bio. + */ +#define DM_TIO_MAGIC 7282014 +struct dm_target_io { + unsigned int magic; + struct dm_io *io; + struct dm_target *ti; + unsigned int target_bio_nr; + unsigned int *len_ptr; + bool inside_dm_io; + struct bio clone; +}; + +/* + * One of these is allocated per original bio. + * It contains the first clone used for that original. + */ +#define DM_IO_MAGIC 5191977 +struct dm_io { + unsigned int magic; + struct mapped_device *md; + blk_status_t status; + atomic_t io_count; + struct bio *orig_bio; + unsigned long start_time; + spinlock_t endio_lock; + struct dm_stats_aux stats_aux; + /* last member of dm_target_io is 'struct bio' */ + struct dm_target_io tio; +}; + +static inline void dm_io_inc_pending(struct dm_io *io) +{ + atomic_inc(&io->io_count); +} + +void dm_io_dec_pending(struct dm_io *io, blk_status_t error); + static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj) { return &container_of(kobj, struct dm_kobject_holder, kobj)->completion; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index b0ab080f2567..50f4cbd600d5 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -3138,11 +3138,10 @@ static int crypt_report_zones(struct dm_target *ti, struct dm_report_zones_args *args, unsigned int nr_zones) { struct crypt_config *cc = ti->private; - sector_t sector = cc->start + dm_target_offset(ti, args->next_sector); - args->start = cc->start; - return blkdev_report_zones(cc->dev->bdev, sector, nr_zones, - dm_report_zones_cb, args); + return dm_report_zones(cc->dev->bdev, cc->start, + cc->start + dm_target_offset(ti, args->next_sector), + args, nr_zones); } #else #define crypt_report_zones NULL @@ -3281,14 +3280,28 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) } cc->start = tmpll; - /* - * For zoned block devices, we need to preserve the issuer write - * ordering. To do so, disable write workqueues and force inline - * encryption completion. - */ if (bdev_is_zoned(cc->dev->bdev)) { + /* + * For zoned block devices, we need to preserve the issuer write + * ordering. To do so, disable write workqueues and force inline + * encryption completion. + */ set_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags); set_bit(DM_CRYPT_WRITE_INLINE, &cc->flags); + + /* + * All zone append writes to a zone of a zoned block device will + * have the same BIO sector, the start of the zone. When the + * cypher IV mode uses sector values, all data targeting a + * zone will be encrypted using the first sector numbers of the + * zone. This will not result in write errors but will + * cause most reads to fail as reads will use the sector values + * for the actual data locations, resulting in IV mismatch. + * To avoid this problem, ask DM core to emulate zone append + * operations with regular writes. + */ + DMDEBUG("Zone append operations will be emulated"); + ti->emulate_zone_append = true; } if (crypt_integrity_aead(cc) || cc->integrity_iv_size) { diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index d9ac7372108c..3b748393fca5 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -363,28 +363,32 @@ static void ws_unpack(const struct writeset_disk *disk, struct writeset_metadata core->root = le64_to_cpu(disk->root); } -static void ws_inc(void *context, const void *value) +static void ws_inc(void *context, const void *value, unsigned count) { struct era_metadata *md = context; struct writeset_disk ws_d; dm_block_t b; + unsigned i; - memcpy(&ws_d, value, sizeof(ws_d)); - b = le64_to_cpu(ws_d.root); - - dm_tm_inc(md->tm, b); + for (i = 0; i < count; i++) { + memcpy(&ws_d, value + (i * sizeof(ws_d)), sizeof(ws_d)); + b = le64_to_cpu(ws_d.root); + dm_tm_inc(md->tm, b); + } } -static void ws_dec(void *context, const void *value) +static void ws_dec(void *context, const void *value, unsigned count) { struct era_metadata *md = context; struct writeset_disk ws_d; dm_block_t b; + unsigned i; - memcpy(&ws_d, value, sizeof(ws_d)); - b = le64_to_cpu(ws_d.root); - - dm_bitset_del(&md->bitset_info, b); + for (i = 0; i < count; i++) { + memcpy(&ws_d, value + (i * sizeof(ws_d)), sizeof(ws_d)); + b = le64_to_cpu(ws_d.root); + dm_bitset_del(&md->bitset_info, b); + } } static int ws_eq(void *context, const void *value1, const void *value2) diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index b7fee9936f05..5877220c01ed 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -463,11 +463,10 @@ static int flakey_report_zones(struct dm_target *ti, struct dm_report_zones_args *args, unsigned int nr_zones) { struct flakey_c *fc = ti->private; - sector_t sector = flakey_map_sector(ti, args->next_sector); - args->start = fc->start; - return blkdev_report_zones(fc->dev->bdev, sector, nr_zones, - dm_report_zones_cb, args); + return dm_report_zones(fc->dev->bdev, fc->start, + flakey_map_sector(ti, args->next_sector), + args, nr_zones); } #else #define flakey_report_zones NULL diff --git a/drivers/md/dm-io-tracker.h b/drivers/md/dm-io-tracker.h new file mode 100644 index 000000000000..bdcc6273ebf0 --- /dev/null +++ b/drivers/md/dm-io-tracker.h @@ -0,0 +1,81 @@ +/* + * Copyright (C) 2021 Red Hat, Inc. All rights reserved. + * + * This file is released under the GPL. + */ + +#ifndef DM_IO_TRACKER_H +#define DM_IO_TRACKER_H + +#include + +struct dm_io_tracker { + spinlock_t lock; + + /* + * Sectors of in-flight IO. + */ + sector_t in_flight; + + /* + * The time, in jiffies, when this device became idle + * (if it is indeed idle). + */ + unsigned long idle_time; + unsigned long last_update_time; +}; + +static inline void dm_iot_init(struct dm_io_tracker *iot) +{ + spin_lock_init(&iot->lock); + iot->in_flight = 0ul; + iot->idle_time = 0ul; + iot->last_update_time = jiffies; +} + +static inline bool dm_iot_idle_for(struct dm_io_tracker *iot, unsigned long j) +{ + bool r = false; + + spin_lock_irq(&iot->lock); + if (!iot->in_flight) + r = time_after(jiffies, iot->idle_time + j); + spin_unlock_irq(&iot->lock); + + return r; +} + +static inline unsigned long dm_iot_idle_time(struct dm_io_tracker *iot) +{ + unsigned long r = 0; + + spin_lock_irq(&iot->lock); + if (!iot->in_flight) + r = jiffies - iot->idle_time; + spin_unlock_irq(&iot->lock); + + return r; +} + +static inline void dm_iot_io_begin(struct dm_io_tracker *iot, sector_t len) +{ + spin_lock_irq(&iot->lock); + iot->in_flight += len; + spin_unlock_irq(&iot->lock); +} + +static inline void dm_iot_io_end(struct dm_io_tracker *iot, sector_t len) +{ + unsigned long flags; + + if (!len) + return; + + spin_lock_irqsave(&iot->lock, flags); + iot->in_flight -= len; + if (!iot->in_flight) + iot->idle_time = jiffies; + spin_unlock_irqrestore(&iot->lock, flags); +} + +#endif diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 1bbe4a34ef4c..37b03ab7e5c9 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -341,7 +341,7 @@ static void client_free_pages(struct dm_kcopyd_client *kc) struct kcopyd_job { struct dm_kcopyd_client *kc; struct list_head list; - unsigned long flags; + unsigned flags; /* * Error state of the job. @@ -418,7 +418,7 @@ static struct kcopyd_job *pop_io_job(struct list_head *jobs, * constraint and sequential writes that are at the right position. */ list_for_each_entry(job, jobs, list) { - if (job->rw == READ || !test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags)) { + if (job->rw == READ || !(job->flags & BIT(DM_KCOPYD_WRITE_SEQ))) { list_del(&job->list); return job; } @@ -437,9 +437,8 @@ static struct kcopyd_job *pop(struct list_head *jobs, struct dm_kcopyd_client *kc) { struct kcopyd_job *job = NULL; - unsigned long flags; - spin_lock_irqsave(&kc->job_lock, flags); + spin_lock_irq(&kc->job_lock); if (!list_empty(jobs)) { if (jobs == &kc->io_jobs) @@ -449,7 +448,7 @@ static struct kcopyd_job *pop(struct list_head *jobs, list_del(&job->list); } } - spin_unlock_irqrestore(&kc->job_lock, flags); + spin_unlock_irq(&kc->job_lock); return job; } @@ -467,12 +466,11 @@ static void push(struct list_head *jobs, struct kcopyd_job *job) static void push_head(struct list_head *jobs, struct kcopyd_job *job) { - unsigned long flags; struct dm_kcopyd_client *kc = job->kc; - spin_lock_irqsave(&kc->job_lock, flags); + spin_lock_irq(&kc->job_lock); list_add(&job->list, jobs); - spin_unlock_irqrestore(&kc->job_lock, flags); + spin_unlock_irq(&kc->job_lock); } /* @@ -525,7 +523,7 @@ static void complete_io(unsigned long error, void *context) else job->read_err = 1; - if (!test_bit(DM_KCOPYD_IGNORE_ERROR, &job->flags)) { + if (!(job->flags & BIT(DM_KCOPYD_IGNORE_ERROR))) { push(&kc->complete_jobs, job); wake(kc); return; @@ -565,7 +563,7 @@ static int run_io_job(struct kcopyd_job *job) * If we need to write sequentially and some reads or writes failed, * no point in continuing. */ - if (test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags) && + if (job->flags & BIT(DM_KCOPYD_WRITE_SEQ) && job->master_job->write_err) { job->write_err = job->master_job->write_err; return -EIO; @@ -648,7 +646,6 @@ static void do_work(struct work_struct *work) struct dm_kcopyd_client *kc = container_of(work, struct dm_kcopyd_client, kcopyd_work); struct blk_plug plug; - unsigned long flags; /* * The order that these are called is *very* important. @@ -657,9 +654,9 @@ static void do_work(struct work_struct *work) * list. io jobs call wake when they complete and it all * starts again. */ - spin_lock_irqsave(&kc->job_lock, flags); + spin_lock_irq(&kc->job_lock); list_splice_tail_init(&kc->callback_jobs, &kc->complete_jobs); - spin_unlock_irqrestore(&kc->job_lock, flags); + spin_unlock_irq(&kc->job_lock); blk_start_plug(&plug); process_jobs(&kc->complete_jobs, kc, run_complete_job); @@ -709,7 +706,7 @@ static void segment_complete(int read_err, unsigned long write_err, * Only dispatch more work if there hasn't been an error. */ if ((!job->read_err && !job->write_err) || - test_bit(DM_KCOPYD_IGNORE_ERROR, &job->flags)) { + job->flags & BIT(DM_KCOPYD_IGNORE_ERROR)) { /* get the next chunk of work */ progress = job->progress; count = job->source.count - progress; @@ -801,10 +798,10 @@ void dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from, * we need to write sequentially. If one of the destination is a * host-aware device, then leave it to the caller to choose what to do. */ - if (!test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags)) { + if (!(job->flags & BIT(DM_KCOPYD_WRITE_SEQ))) { for (i = 0; i < job->num_dests; i++) { if (bdev_zoned_model(dests[i].bdev) == BLK_ZONED_HM) { - set_bit(DM_KCOPYD_WRITE_SEQ, &job->flags); + job->flags |= BIT(DM_KCOPYD_WRITE_SEQ); break; } } @@ -813,9 +810,9 @@ void dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from, /* * If we need to write sequentially, errors cannot be ignored. */ - if (test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags) && - test_bit(DM_KCOPYD_IGNORE_ERROR, &job->flags)) - clear_bit(DM_KCOPYD_IGNORE_ERROR, &job->flags); + if (job->flags & BIT(DM_KCOPYD_WRITE_SEQ) && + job->flags & BIT(DM_KCOPYD_IGNORE_ERROR)) + job->flags &= ~BIT(DM_KCOPYD_IGNORE_ERROR); if (from) { job->source = *from; @@ -983,3 +980,9 @@ void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc) kfree(kc); } EXPORT_SYMBOL(dm_kcopyd_client_destroy); + +void dm_kcopyd_client_flush(struct dm_kcopyd_client *kc) +{ + flush_workqueue(kc->kcopyd_wq); +} +EXPORT_SYMBOL(dm_kcopyd_client_flush); diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 92db0f5e7f28..c91f1e2e2f65 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -140,11 +140,10 @@ static int linear_report_zones(struct dm_target *ti, struct dm_report_zones_args *args, unsigned int nr_zones) { struct linear_c *lc = ti->private; - sector_t sector = linear_map_sector(ti, args->next_sector); - args->start = lc->start; - return blkdev_report_zones(lc->dev->bdev, sector, nr_zones, - dm_report_zones_cb, args); + return dm_report_zones(lc->dev->bdev, lc->start, + linear_map_sector(ti, args->next_sector), + args, nr_zones); } #else #define linear_report_zones NULL diff --git a/drivers/md/dm-ps-io-affinity.c b/drivers/md/dm-ps-io-affinity.c index 077655cd4fae..cb8e83bfb1a7 100644 --- a/drivers/md/dm-ps-io-affinity.c +++ b/drivers/md/dm-ps-io-affinity.c @@ -91,7 +91,6 @@ static int ioa_add_path(struct path_selector *ps, struct dm_path *path, cpumask_set_cpu(cpu, s->path_mask); s->path_map[cpu] = pi; refcount_inc(&pi->refcount); - continue; } if (refcount_dec_and_test(&pi->refcount)) { diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index b0a82f29a2e4..ebb4810cc3b4 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -364,7 +364,7 @@ static void recover(struct mirror_set *ms, struct dm_region *reg) /* hand to kcopyd */ if (!errors_handled(ms)) - set_bit(DM_KCOPYD_IGNORE_ERROR, &flags); + flags |= BIT(DM_KCOPYD_IGNORE_ERROR); dm_kcopyd_copy(ms->kcopyd_client, &from, ms->nr_mirrors - 1, to, flags, recovery_complete, reg); diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 9c3bc3711b33..0dbd48cbdff9 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -530,7 +530,6 @@ static const struct blk_mq_ops dm_mq_ops = { int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t) { - struct request_queue *q; struct dm_target *immutable_tgt; int err; @@ -557,12 +556,10 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t) if (err) goto out_kfree_tag_set; - q = blk_mq_init_allocated_queue(md->tag_set, md->queue, true); - if (IS_ERR(q)) { - err = PTR_ERR(q); + err = blk_mq_init_allocated_queue(md->tag_set, md->queue); + if (err) goto out_tag_set; - } - + elevator_init_mq(md->queue); return 0; out_tag_set: diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 03f9fe594c9b..27d36f26fb7b 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -249,7 +249,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, * If the target is mapped to zoned block device(s), check * that the zones are not partially mapped. */ - if (bdev_zoned_model(bdev) != BLK_ZONED_NONE) { + if (bdev_is_zoned(bdev)) { unsigned int zone_sectors = bdev_zone_sectors(bdev); if (start & (zone_sectors - 1)) { @@ -1318,7 +1318,7 @@ static int dm_derive_raw_secret(struct blk_keyslot_manager *ksm, } -static struct blk_ksm_ll_ops dm_ksm_ll_ops = { +static const struct blk_ksm_ll_ops dm_ksm_ll_ops = { .keyslot_evict = dm_keyslot_evict, .derive_raw_secret = dm_derive_raw_secret, }; @@ -2058,11 +2058,12 @@ static int device_requires_stable_pages(struct dm_target *ti, return blk_queue_stable_writes(q); } -void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, - struct queue_limits *limits) +int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, + struct queue_limits *limits) { bool wc = false, fua = false; int page_size = PAGE_SIZE; + int r; /* * Copy table's limits to the DM device's request_queue @@ -2142,19 +2143,19 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); /* - * For a zoned target, the number of zones should be updated for the - * correct value to be exposed in sysfs queue/nr_zones. For a BIO based - * target, this is all that is needed. + * For a zoned target, setup the zones related queue attributes + * and resources necessary for zone append emulation if necessary. */ -#ifdef CONFIG_BLK_DEV_ZONED if (blk_queue_is_zoned(q)) { - WARN_ON_ONCE(queue_is_mq(q)); - q->nr_zones = blkdev_nr_zones(t->md->disk); + r = dm_set_zones_restrictions(t, q); + if (r) + return r; } -#endif dm_update_keyslot_manager(q, t); blk_queue_update_readahead(q); + + return 0; } unsigned int dm_table_get_num_targets(struct dm_table *t) diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index e75b20480e46..c88ed14d49e6 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -311,28 +311,53 @@ static void unpack_block_time(uint64_t v, dm_block_t *b, uint32_t *t) *t = v & ((1 << 24) - 1); } -static void data_block_inc(void *context, const void *value_le) -{ - struct dm_space_map *sm = context; - __le64 v_le; - uint64_t b; - uint32_t t; +/* + * It's more efficient to call dm_sm_{inc,dec}_blocks as few times as + * possible. 'with_runs' reads contiguous runs of blocks, and calls the + * given sm function. + */ +typedef int (*run_fn)(struct dm_space_map *, dm_block_t, dm_block_t); - memcpy(&v_le, value_le, sizeof(v_le)); - unpack_block_time(le64_to_cpu(v_le), &b, &t); - dm_sm_inc_block(sm, b); +static void with_runs(struct dm_space_map *sm, const __le64 *value_le, unsigned count, run_fn fn) +{ + uint64_t b, begin, end; + uint32_t t; + bool in_run = false; + unsigned i; + + for (i = 0; i < count; i++, value_le++) { + /* We know value_le is 8 byte aligned */ + unpack_block_time(le64_to_cpu(*value_le), &b, &t); + + if (in_run) { + if (b == end) { + end++; + } else { + fn(sm, begin, end); + begin = b; + end = b + 1; + } + } else { + in_run = true; + begin = b; + end = b + 1; + } + } + + if (in_run) + fn(sm, begin, end); } -static void data_block_dec(void *context, const void *value_le) +static void data_block_inc(void *context, const void *value_le, unsigned count) { - struct dm_space_map *sm = context; - __le64 v_le; - uint64_t b; - uint32_t t; + with_runs((struct dm_space_map *) context, + (const __le64 *) value_le, count, dm_sm_inc_blocks); +} - memcpy(&v_le, value_le, sizeof(v_le)); - unpack_block_time(le64_to_cpu(v_le), &b, &t); - dm_sm_dec_block(sm, b); +static void data_block_dec(void *context, const void *value_le, unsigned count) +{ + with_runs((struct dm_space_map *) context, + (const __le64 *) value_le, count, dm_sm_dec_blocks); } static int data_block_equal(void *context, const void *value1_le, const void *value2_le) @@ -349,27 +374,25 @@ static int data_block_equal(void *context, const void *value1_le, const void *va return b1 == b2; } -static void subtree_inc(void *context, const void *value) +static void subtree_inc(void *context, const void *value, unsigned count) { struct dm_btree_info *info = context; - __le64 root_le; - uint64_t root; + const __le64 *root_le = value; + unsigned i; - memcpy(&root_le, value, sizeof(root_le)); - root = le64_to_cpu(root_le); - dm_tm_inc(info->tm, root); + for (i = 0; i < count; i++, root_le++) + dm_tm_inc(info->tm, le64_to_cpu(*root_le)); } -static void subtree_dec(void *context, const void *value) +static void subtree_dec(void *context, const void *value, unsigned count) { struct dm_btree_info *info = context; - __le64 root_le; - uint64_t root; + const __le64 *root_le = value; + unsigned i; - memcpy(&root_le, value, sizeof(root_le)); - root = le64_to_cpu(root_le); - if (dm_btree_del(info, root)) - DMERR("btree delete failed"); + for (i = 0; i < count; i++, root_le++) + if (dm_btree_del(info, le64_to_cpu(*root_le))) + DMERR("btree delete failed"); } static int subtree_equal(void *context, const void *value1_le, const void *value2_le) @@ -1761,11 +1784,7 @@ int dm_pool_inc_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_ int r = 0; pmd_write_lock(pmd); - for (; b != e; b++) { - r = dm_sm_inc_block(pmd->data_sm, b); - if (r) - break; - } + r = dm_sm_inc_blocks(pmd->data_sm, b, e); pmd_write_unlock(pmd); return r; @@ -1776,11 +1795,7 @@ int dm_pool_dec_data_range(struct dm_pool_metadata *pmd, dm_block_t b, dm_block_ int r = 0; pmd_write_lock(pmd); - for (; b != e; b++) { - r = dm_sm_dec_block(pmd->data_sm, b); - if (r) - break; - } + r = dm_sm_dec_blocks(pmd->data_sm, b, e); pmd_write_unlock(pmd); return r; diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index aecc246ade26..e21e29e81bbf 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -15,6 +15,8 @@ #include #include #include +#include +#include "dm-io-tracker.h" #define DM_MSG_PREFIX "writecache" @@ -28,6 +30,7 @@ #define AUTOCOMMIT_MSEC 1000 #define MAX_AGE_DIV 16 #define MAX_AGE_UNSPECIFIED -1UL +#define PAUSE_WRITEBACK (HZ * 3) #define BITMAP_GRANULARITY 65536 #if BITMAP_GRANULARITY < PAGE_SIZE @@ -123,6 +126,7 @@ struct dm_writecache { size_t freelist_high_watermark; size_t freelist_low_watermark; unsigned long max_age; + unsigned long pause; unsigned uncommitted_blocks; unsigned autocommit_blocks; @@ -171,17 +175,22 @@ struct dm_writecache { bool flush_on_suspend:1; bool cleaner:1; bool cleaner_set:1; + bool metadata_only:1; + bool pause_set:1; unsigned high_wm_percent_value; unsigned low_wm_percent_value; unsigned autocommit_time_value; unsigned max_age_value; + unsigned pause_value; unsigned writeback_all; struct workqueue_struct *writeback_wq; struct work_struct writeback_work; struct work_struct flush_work; + struct dm_io_tracker iot; + struct dm_io_client *dm_io; raw_spinlock_t endio_list_lock; @@ -532,7 +541,7 @@ static void ssd_commit_superblock(struct dm_writecache *wc) region.bdev = wc->ssd_dev->bdev; region.sector = 0; - region.count = PAGE_SIZE >> SECTOR_SHIFT; + region.count = max(4096U, wc->block_size) >> SECTOR_SHIFT; if (unlikely(region.sector + region.count > wc->metadata_sectors)) region.count = wc->metadata_sectors - region.sector; @@ -1301,8 +1310,12 @@ static int writecache_map(struct dm_target *ti, struct bio *bio) writecache_flush(wc); if (writecache_has_error(wc)) goto unlock_error; + if (unlikely(wc->cleaner) || unlikely(wc->metadata_only)) + goto unlock_remap_origin; goto unlock_submit; } else { + if (dm_bio_get_target_bio_nr(bio)) + goto unlock_remap_origin; writecache_offload_bio(wc, bio); goto unlock_return; } @@ -1360,24 +1373,29 @@ read_next_block: } else { do { bool found_entry = false; + bool search_used = false; if (writecache_has_error(wc)) goto unlock_error; e = writecache_find_entry(wc, bio->bi_iter.bi_sector, 0); if (e) { - if (!writecache_entry_is_committed(wc, e)) + if (!writecache_entry_is_committed(wc, e)) { + search_used = true; goto bio_copy; + } if (!WC_MODE_PMEM(wc) && !e->write_in_progress) { wc->overwrote_committed = true; + search_used = true; goto bio_copy; } found_entry = true; } else { - if (unlikely(wc->cleaner)) + if (unlikely(wc->cleaner) || + (wc->metadata_only && !(bio->bi_opf & REQ_META))) goto direct_write; } e = writecache_pop_from_freelist(wc, (sector_t)-1); if (unlikely(!e)) { - if (!found_entry) { + if (!WC_MODE_PMEM(wc) && !found_entry) { direct_write: e = writecache_find_entry(wc, bio->bi_iter.bi_sector, WFE_RETURN_FOLLOWING); if (e) { @@ -1404,13 +1422,31 @@ bio_copy: sector_t current_cache_sec = start_cache_sec + (bio_size >> SECTOR_SHIFT); while (bio_size < bio->bi_iter.bi_size) { - struct wc_entry *f = writecache_pop_from_freelist(wc, current_cache_sec); - if (!f) - break; - write_original_sector_seq_count(wc, f, bio->bi_iter.bi_sector + - (bio_size >> SECTOR_SHIFT), wc->seq_count); - writecache_insert_entry(wc, f); - wc->uncommitted_blocks++; + if (!search_used) { + struct wc_entry *f = writecache_pop_from_freelist(wc, current_cache_sec); + if (!f) + break; + write_original_sector_seq_count(wc, f, bio->bi_iter.bi_sector + + (bio_size >> SECTOR_SHIFT), wc->seq_count); + writecache_insert_entry(wc, f); + wc->uncommitted_blocks++; + } else { + struct wc_entry *f; + struct rb_node *next = rb_next(&e->rb_node); + if (!next) + break; + f = container_of(next, struct wc_entry, rb_node); + if (f != e + 1) + break; + if (read_original_sector(wc, f) != + read_original_sector(wc, e) + (wc->block_size >> SECTOR_SHIFT)) + break; + if (unlikely(f->write_in_progress)) + break; + if (writecache_entry_is_committed(wc, f)) + wc->overwrote_committed = true; + e = f; + } bio_size += wc->block_size; current_cache_sec += wc->block_size >> SECTOR_SHIFT; } @@ -1438,6 +1474,12 @@ bio_copy: } unlock_remap_origin: + if (likely(wc->pause != 0)) { + if (bio_op(bio) == REQ_OP_WRITE) { + dm_iot_io_begin(&wc->iot, 1); + bio->bi_private = (void *)2; + } + } bio_set_dev(bio, wc->dev->bdev); wc_unlock(wc); return DM_MAPIO_REMAPPED; @@ -1468,11 +1510,13 @@ static int writecache_end_io(struct dm_target *ti, struct bio *bio, blk_status_t { struct dm_writecache *wc = ti->private; - if (bio->bi_private != NULL) { + if (bio->bi_private == (void *)1) { int dir = bio_data_dir(bio); if (atomic_dec_and_test(&wc->bio_in_progress[dir])) if (unlikely(waitqueue_active(&wc->bio_in_progress_wait[dir]))) wake_up(&wc->bio_in_progress_wait[dir]); + } else if (bio->bi_private == (void *)2) { + dm_iot_io_end(&wc->iot, 1); } return 0; } @@ -1642,7 +1686,7 @@ pop_from_list: return 0; } -static bool wc_add_block(struct writeback_struct *wb, struct wc_entry *e, gfp_t gfp) +static bool wc_add_block(struct writeback_struct *wb, struct wc_entry *e) { struct dm_writecache *wc = wb->wc; unsigned block_size = wc->block_size; @@ -1703,7 +1747,7 @@ static void __writecache_writeback_pmem(struct dm_writecache *wc, struct writeba max_pages = WB_LIST_INLINE; } - BUG_ON(!wc_add_block(wb, e, GFP_NOIO)); + BUG_ON(!wc_add_block(wb, e)); wb->wc_list[0] = e; wb->wc_list_n = 1; @@ -1713,7 +1757,7 @@ static void __writecache_writeback_pmem(struct dm_writecache *wc, struct writeba if (read_original_sector(wc, f) != read_original_sector(wc, e) + (wc->block_size >> SECTOR_SHIFT)) break; - if (!wc_add_block(wb, f, GFP_NOWAIT | __GFP_NOWARN)) + if (!wc_add_block(wb, f)) break; wbl->size--; list_del(&f->lru); @@ -1794,6 +1838,27 @@ static void writecache_writeback(struct work_struct *work) struct writeback_list wbl; unsigned long n_walked; + if (!WC_MODE_PMEM(wc)) { + /* Wait for any active kcopyd work on behalf of ssd writeback */ + dm_kcopyd_client_flush(wc->dm_kcopyd); + } + + if (likely(wc->pause != 0)) { + while (1) { + unsigned long idle; + if (unlikely(wc->cleaner) || unlikely(wc->writeback_all) || + unlikely(dm_suspended(wc->ti))) + break; + idle = dm_iot_idle_time(&wc->iot); + if (idle >= wc->pause) + break; + idle = wc->pause - idle; + if (idle > HZ) + idle = HZ; + schedule_timeout_idle(idle); + } + } + wc_lock(wc); restart: if (writecache_has_error(wc)) { @@ -1822,8 +1887,9 @@ restart: n_walked++; if (unlikely(n_walked > WRITEBACK_LATENCY) && - likely(!wc->writeback_all) && likely(!dm_suspended(wc->ti))) { - queue_work(wc->writeback_wq, &wc->writeback_work); + likely(!wc->writeback_all)) { + if (likely(!dm_suspended(wc->ti))) + queue_work(wc->writeback_wq, &wc->writeback_work); break; } @@ -1845,15 +1911,13 @@ restart: if (unlikely(read_original_sector(wc, f) == read_original_sector(wc, e))) { BUG_ON(!f->write_in_progress); - list_del(&e->lru); - list_add(&e->lru, &skipped); + list_move(&e->lru, &skipped); cond_resched(); continue; } } wc->writeback_size++; - list_del(&e->lru); - list_add(&e->lru, &wbl.list); + list_move(&e->lru, &wbl.list); wbl.size++; e->write_in_progress = true; e->wc_list_contiguous = 1; @@ -1888,8 +1952,7 @@ restart: // break; wc->writeback_size++; - list_del(&g->lru); - list_add(&g->lru, &wbl.list); + list_move(&g->lru, &wbl.list); wbl.size++; g->write_in_progress = true; g->wc_list_contiguous = BIO_MAX_VECS; @@ -2065,7 +2128,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) struct wc_memory_superblock s; static struct dm_arg _args[] = { - {0, 16, "Invalid number of feature args"}, + {0, 18, "Invalid number of feature args"}, }; as.argc = argc; @@ -2109,6 +2172,8 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) INIT_WORK(&wc->writeback_work, writecache_writeback); INIT_WORK(&wc->flush_work, writecache_flush_work); + dm_iot_init(&wc->iot); + raw_spin_lock_init(&wc->endio_list_lock); INIT_LIST_HEAD(&wc->endio_list); wc->endio_thread = kthread_create(writecache_endio_thread, wc, "writecache_endio"); @@ -2156,6 +2221,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) goto bad; } } else { + wc->pause = PAUSE_WRITEBACK; r = mempool_init_kmalloc_pool(&wc->copy_pool, 1, sizeof(struct copy_struct)); if (r) { ti->error = "Could not allocate mempool"; @@ -2292,6 +2358,20 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) wc->writeback_fua = false; wc->writeback_fua_set = true; } else goto invalid_optional; + } else if (!strcasecmp(string, "metadata_only")) { + wc->metadata_only = true; + } else if (!strcasecmp(string, "pause_writeback") && opt_params >= 1) { + unsigned pause_msecs; + if (WC_MODE_PMEM(wc)) + goto invalid_optional; + string = dm_shift_arg(&as), opt_params--; + if (sscanf(string, "%u%c", &pause_msecs, &dummy) != 1) + goto invalid_optional; + if (pause_msecs > 60000) + goto invalid_optional; + wc->pause = msecs_to_jiffies(pause_msecs); + wc->pause_set = true; + wc->pause_value = pause_msecs; } else { invalid_optional: r = -EINVAL; @@ -2463,7 +2543,7 @@ overflow: goto bad; } - ti->num_flush_bios = 1; + ti->num_flush_bios = WC_MODE_PMEM(wc) ? 1 : 2; ti->flush_supported = true; ti->num_discard_bios = 1; @@ -2515,6 +2595,10 @@ static void writecache_status(struct dm_target *ti, status_type_t type, extra_args++; if (wc->writeback_fua_set) extra_args++; + if (wc->metadata_only) + extra_args++; + if (wc->pause_set) + extra_args += 2; DMEMIT("%u", extra_args); if (wc->start_sector_set) @@ -2535,13 +2619,17 @@ static void writecache_status(struct dm_target *ti, status_type_t type, DMEMIT(" cleaner"); if (wc->writeback_fua_set) DMEMIT(" %sfua", wc->writeback_fua ? "" : "no"); + if (wc->metadata_only) + DMEMIT(" metadata_only"); + if (wc->pause_set) + DMEMIT(" pause_writeback %u", wc->pause_value); break; } } static struct target_type writecache_target = { .name = "writecache", - .version = {1, 4, 0}, + .version = {1, 5, 0}, .module = THIS_MODULE, .ctr = writecache_ctr, .dtr = writecache_dtr, diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c new file mode 100644 index 000000000000..6d82a34438c8 --- /dev/null +++ b/drivers/md/dm-zone.c @@ -0,0 +1,660 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ + +#include +#include +#include +#include + +#include "dm-core.h" + +#define DM_MSG_PREFIX "zone" + +#define DM_ZONE_INVALID_WP_OFST UINT_MAX + +/* + * For internal zone reports bypassing the top BIO submission path. + */ +static int dm_blk_do_report_zones(struct mapped_device *md, struct dm_table *t, + sector_t sector, unsigned int nr_zones, + report_zones_cb cb, void *data) +{ + struct gendisk *disk = md->disk; + int ret; + struct dm_report_zones_args args = { + .next_sector = sector, + .orig_data = data, + .orig_cb = cb, + }; + + do { + struct dm_target *tgt; + + tgt = dm_table_find_target(t, args.next_sector); + if (WARN_ON_ONCE(!tgt->type->report_zones)) + return -EIO; + + args.tgt = tgt; + ret = tgt->type->report_zones(tgt, &args, + nr_zones - args.zone_idx); + if (ret < 0) + return ret; + } while (args.zone_idx < nr_zones && + args.next_sector < get_capacity(disk)); + + return args.zone_idx; +} + +/* + * User facing dm device block device report zone operation. This calls the + * report_zones operation for each target of a device table. This operation is + * generally implemented by targets using dm_report_zones(). + */ +int dm_blk_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data) +{ + struct mapped_device *md = disk->private_data; + struct dm_table *map; + int srcu_idx, ret; + + if (dm_suspended_md(md)) + return -EAGAIN; + + map = dm_get_live_table(md, &srcu_idx); + if (!map) + return -EIO; + + ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb, data); + + dm_put_live_table(md, srcu_idx); + + return ret; +} + +static int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct dm_report_zones_args *args = data; + sector_t sector_diff = args->tgt->begin - args->start; + + /* + * Ignore zones beyond the target range. + */ + if (zone->start >= args->start + args->tgt->len) + return 0; + + /* + * Remap the start sector and write pointer position of the zone + * to match its position in the target range. + */ + zone->start += sector_diff; + if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) { + if (zone->cond == BLK_ZONE_COND_FULL) + zone->wp = zone->start + zone->len; + else if (zone->cond == BLK_ZONE_COND_EMPTY) + zone->wp = zone->start; + else + zone->wp += sector_diff; + } + + args->next_sector = zone->start + zone->len; + return args->orig_cb(zone, args->zone_idx++, args->orig_data); +} + +/* + * Helper for drivers of zoned targets to implement struct target_type + * report_zones operation. + */ +int dm_report_zones(struct block_device *bdev, sector_t start, sector_t sector, + struct dm_report_zones_args *args, unsigned int nr_zones) +{ + /* + * Set the target mapping start sector first so that + * dm_report_zones_cb() can correctly remap zone information. + */ + args->start = start; + + return blkdev_report_zones(bdev, sector, nr_zones, + dm_report_zones_cb, args); +} +EXPORT_SYMBOL_GPL(dm_report_zones); + +bool dm_is_zone_write(struct mapped_device *md, struct bio *bio) +{ + struct request_queue *q = md->queue; + + if (!blk_queue_is_zoned(q)) + return false; + + switch (bio_op(bio)) { + case REQ_OP_WRITE_ZEROES: + case REQ_OP_WRITE_SAME: + case REQ_OP_WRITE: + return !op_is_flush(bio->bi_opf) && bio_sectors(bio); + default: + return false; + } +} + +void dm_cleanup_zoned_dev(struct mapped_device *md) +{ + struct request_queue *q = md->queue; + + if (q) { + kfree(q->conv_zones_bitmap); + q->conv_zones_bitmap = NULL; + kfree(q->seq_zones_wlock); + q->seq_zones_wlock = NULL; + } + + kvfree(md->zwp_offset); + md->zwp_offset = NULL; + md->nr_zones = 0; +} + +static unsigned int dm_get_zone_wp_offset(struct blk_zone *zone) +{ + switch (zone->cond) { + case BLK_ZONE_COND_IMP_OPEN: + case BLK_ZONE_COND_EXP_OPEN: + case BLK_ZONE_COND_CLOSED: + return zone->wp - zone->start; + case BLK_ZONE_COND_FULL: + return zone->len; + case BLK_ZONE_COND_EMPTY: + case BLK_ZONE_COND_NOT_WP: + case BLK_ZONE_COND_OFFLINE: + case BLK_ZONE_COND_READONLY: + default: + /* + * Conventional, offline and read-only zones do not have a valid + * write pointer. Use 0 as for an empty zone. + */ + return 0; + } +} + +static int dm_zone_revalidate_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ + struct mapped_device *md = data; + struct request_queue *q = md->queue; + + switch (zone->type) { + case BLK_ZONE_TYPE_CONVENTIONAL: + if (!q->conv_zones_bitmap) { + q->conv_zones_bitmap = + kcalloc(BITS_TO_LONGS(q->nr_zones), + sizeof(unsigned long), GFP_NOIO); + if (!q->conv_zones_bitmap) + return -ENOMEM; + } + set_bit(idx, q->conv_zones_bitmap); + break; + case BLK_ZONE_TYPE_SEQWRITE_REQ: + case BLK_ZONE_TYPE_SEQWRITE_PREF: + if (!q->seq_zones_wlock) { + q->seq_zones_wlock = + kcalloc(BITS_TO_LONGS(q->nr_zones), + sizeof(unsigned long), GFP_NOIO); + if (!q->seq_zones_wlock) + return -ENOMEM; + } + if (!md->zwp_offset) { + md->zwp_offset = + kvcalloc(q->nr_zones, sizeof(unsigned int), + GFP_KERNEL); + if (!md->zwp_offset) + return -ENOMEM; + } + md->zwp_offset[idx] = dm_get_zone_wp_offset(zone); + + break; + default: + DMERR("Invalid zone type 0x%x at sectors %llu", + (int)zone->type, zone->start); + return -ENODEV; + } + + return 0; +} + +/* + * Revalidate the zones of a mapped device to initialize resource necessary + * for zone append emulation. Note that we cannot simply use the block layer + * blk_revalidate_disk_zones() function here as the mapped device is suspended + * (this is called from __bind() context). + */ +static int dm_revalidate_zones(struct mapped_device *md, struct dm_table *t) +{ + struct request_queue *q = md->queue; + unsigned int noio_flag; + int ret; + + /* + * Check if something changed. If yes, cleanup the current resources + * and reallocate everything. + */ + if (!q->nr_zones || q->nr_zones != md->nr_zones) + dm_cleanup_zoned_dev(md); + if (md->nr_zones) + return 0; + + /* + * Scan all zones to initialize everything. Ensure that all vmalloc + * operations in this context are done as if GFP_NOIO was specified. + */ + noio_flag = memalloc_noio_save(); + ret = dm_blk_do_report_zones(md, t, 0, q->nr_zones, + dm_zone_revalidate_cb, md); + memalloc_noio_restore(noio_flag); + if (ret < 0) + goto err; + if (ret != q->nr_zones) { + ret = -EIO; + goto err; + } + + md->nr_zones = q->nr_zones; + + return 0; + +err: + DMERR("Revalidate zones failed %d", ret); + dm_cleanup_zoned_dev(md); + return ret; +} + +static int device_not_zone_append_capable(struct dm_target *ti, + struct dm_dev *dev, sector_t start, + sector_t len, void *data) +{ + return !blk_queue_is_zoned(bdev_get_queue(dev->bdev)); +} + +static bool dm_table_supports_zone_append(struct dm_table *t) +{ + struct dm_target *ti; + unsigned int i; + + for (i = 0; i < dm_table_get_num_targets(t); i++) { + ti = dm_table_get_target(t, i); + + if (ti->emulate_zone_append) + return false; + + if (!ti->type->iterate_devices || + ti->type->iterate_devices(ti, device_not_zone_append_capable, NULL)) + return false; + } + + return true; +} + +int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q) +{ + struct mapped_device *md = t->md; + + /* + * For a zoned target, the number of zones should be updated for the + * correct value to be exposed in sysfs queue/nr_zones. + */ + WARN_ON_ONCE(queue_is_mq(q)); + q->nr_zones = blkdev_nr_zones(md->disk); + + /* Check if zone append is natively supported */ + if (dm_table_supports_zone_append(t)) { + clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags); + dm_cleanup_zoned_dev(md); + return 0; + } + + /* + * Mark the mapped device as needing zone append emulation and + * initialize the emulation resources once the capacity is set. + */ + set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags); + if (!get_capacity(md->disk)) + return 0; + + return dm_revalidate_zones(md, t); +} + +static int dm_update_zone_wp_offset_cb(struct blk_zone *zone, unsigned int idx, + void *data) +{ + unsigned int *wp_offset = data; + + *wp_offset = dm_get_zone_wp_offset(zone); + + return 0; +} + +static int dm_update_zone_wp_offset(struct mapped_device *md, unsigned int zno, + unsigned int *wp_ofst) +{ + sector_t sector = zno * blk_queue_zone_sectors(md->queue); + unsigned int noio_flag; + struct dm_table *t; + int srcu_idx, ret; + + t = dm_get_live_table(md, &srcu_idx); + if (!t) + return -EIO; + + /* + * Ensure that all memory allocations in this context are done as if + * GFP_NOIO was specified. + */ + noio_flag = memalloc_noio_save(); + ret = dm_blk_do_report_zones(md, t, sector, 1, + dm_update_zone_wp_offset_cb, wp_ofst); + memalloc_noio_restore(noio_flag); + + dm_put_live_table(md, srcu_idx); + + if (ret != 1) + return -EIO; + + return 0; +} + +/* + * First phase of BIO mapping for targets with zone append emulation: + * check all BIO that change a zone writer pointer and change zone + * append operations into regular write operations. + */ +static bool dm_zone_map_bio_begin(struct mapped_device *md, + struct bio *orig_bio, struct bio *clone) +{ + sector_t zsectors = blk_queue_zone_sectors(md->queue); + unsigned int zno = bio_zone_no(orig_bio); + unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]); + + /* + * If the target zone is in an error state, recover by inspecting the + * zone to get its current write pointer position. Note that since the + * target zone is already locked, a BIO issuing context should never + * see the zone write in the DM_ZONE_UPDATING_WP_OFST state. + */ + if (zwp_offset == DM_ZONE_INVALID_WP_OFST) { + if (dm_update_zone_wp_offset(md, zno, &zwp_offset)) + return false; + WRITE_ONCE(md->zwp_offset[zno], zwp_offset); + } + + switch (bio_op(orig_bio)) { + case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_FINISH: + return true; + case REQ_OP_WRITE_ZEROES: + case REQ_OP_WRITE_SAME: + case REQ_OP_WRITE: + /* Writes must be aligned to the zone write pointer */ + if ((clone->bi_iter.bi_sector & (zsectors - 1)) != zwp_offset) + return false; + break; + case REQ_OP_ZONE_APPEND: + /* + * Change zone append operations into a non-mergeable regular + * writes directed at the current write pointer position of the + * target zone. + */ + clone->bi_opf = REQ_OP_WRITE | REQ_NOMERGE | + (orig_bio->bi_opf & (~REQ_OP_MASK)); + clone->bi_iter.bi_sector = + orig_bio->bi_iter.bi_sector + zwp_offset; + break; + default: + DMWARN_LIMIT("Invalid BIO operation"); + return false; + } + + /* Cannot write to a full zone */ + if (zwp_offset >= zsectors) + return false; + + return true; +} + +/* + * Second phase of BIO mapping for targets with zone append emulation: + * update the zone write pointer offset array to account for the additional + * data written to a zone. Note that at this point, the remapped clone BIO + * may already have completed, so we do not touch it. + */ +static blk_status_t dm_zone_map_bio_end(struct mapped_device *md, + struct bio *orig_bio, + unsigned int nr_sectors) +{ + unsigned int zno = bio_zone_no(orig_bio); + unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]); + + /* The clone BIO may already have been completed and failed */ + if (zwp_offset == DM_ZONE_INVALID_WP_OFST) + return BLK_STS_IOERR; + + /* Update the zone wp offset */ + switch (bio_op(orig_bio)) { + case REQ_OP_ZONE_RESET: + WRITE_ONCE(md->zwp_offset[zno], 0); + return BLK_STS_OK; + case REQ_OP_ZONE_FINISH: + WRITE_ONCE(md->zwp_offset[zno], + blk_queue_zone_sectors(md->queue)); + return BLK_STS_OK; + case REQ_OP_WRITE_ZEROES: + case REQ_OP_WRITE_SAME: + case REQ_OP_WRITE: + WRITE_ONCE(md->zwp_offset[zno], zwp_offset + nr_sectors); + return BLK_STS_OK; + case REQ_OP_ZONE_APPEND: + /* + * Check that the target did not truncate the write operation + * emulating a zone append. + */ + if (nr_sectors != bio_sectors(orig_bio)) { + DMWARN_LIMIT("Truncated write for zone append"); + return BLK_STS_IOERR; + } + WRITE_ONCE(md->zwp_offset[zno], zwp_offset + nr_sectors); + return BLK_STS_OK; + default: + DMWARN_LIMIT("Invalid BIO operation"); + return BLK_STS_IOERR; + } +} + +static inline void dm_zone_lock(struct request_queue *q, + unsigned int zno, struct bio *clone) +{ + if (WARN_ON_ONCE(bio_flagged(clone, BIO_ZONE_WRITE_LOCKED))) + return; + + wait_on_bit_lock_io(q->seq_zones_wlock, zno, TASK_UNINTERRUPTIBLE); + bio_set_flag(clone, BIO_ZONE_WRITE_LOCKED); +} + +static inline void dm_zone_unlock(struct request_queue *q, + unsigned int zno, struct bio *clone) +{ + if (!bio_flagged(clone, BIO_ZONE_WRITE_LOCKED)) + return; + + WARN_ON_ONCE(!test_bit(zno, q->seq_zones_wlock)); + clear_bit_unlock(zno, q->seq_zones_wlock); + smp_mb__after_atomic(); + wake_up_bit(q->seq_zones_wlock, zno); + + bio_clear_flag(clone, BIO_ZONE_WRITE_LOCKED); +} + +static bool dm_need_zone_wp_tracking(struct bio *orig_bio) +{ + /* + * Special processing is not needed for operations that do not need the + * zone write lock, that is, all operations that target conventional + * zones and all operations that do not modify directly a sequential + * zone write pointer. + */ + if (op_is_flush(orig_bio->bi_opf) && !bio_sectors(orig_bio)) + return false; + switch (bio_op(orig_bio)) { + case REQ_OP_WRITE_ZEROES: + case REQ_OP_WRITE_SAME: + case REQ_OP_WRITE: + case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_FINISH: + case REQ_OP_ZONE_APPEND: + return bio_zone_is_seq(orig_bio); + default: + return false; + } +} + +/* + * Special IO mapping for targets needing zone append emulation. + */ +int dm_zone_map_bio(struct dm_target_io *tio) +{ + struct dm_io *io = tio->io; + struct dm_target *ti = tio->ti; + struct mapped_device *md = io->md; + struct request_queue *q = md->queue; + struct bio *orig_bio = io->orig_bio; + struct bio *clone = &tio->clone; + unsigned int zno; + blk_status_t sts; + int r; + + /* + * IOs that do not change a zone write pointer do not need + * any additional special processing. + */ + if (!dm_need_zone_wp_tracking(orig_bio)) + return ti->type->map(ti, clone); + + /* Lock the target zone */ + zno = bio_zone_no(orig_bio); + dm_zone_lock(q, zno, clone); + + /* + * Check that the bio and the target zone write pointer offset are + * both valid, and if the bio is a zone append, remap it to a write. + */ + if (!dm_zone_map_bio_begin(md, orig_bio, clone)) { + dm_zone_unlock(q, zno, clone); + return DM_MAPIO_KILL; + } + + /* + * The target map function may issue and complete the IO quickly. + * Take an extra reference on the IO to make sure it does disappear + * until we run dm_zone_map_bio_end(). + */ + dm_io_inc_pending(io); + + /* Let the target do its work */ + r = ti->type->map(ti, clone); + switch (r) { + case DM_MAPIO_SUBMITTED: + /* + * The target submitted the clone BIO. The target zone will + * be unlocked on completion of the clone. + */ + sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr); + break; + case DM_MAPIO_REMAPPED: + /* + * The target only remapped the clone BIO. In case of error, + * unlock the target zone here as the clone will not be + * submitted. + */ + sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr); + if (sts != BLK_STS_OK) + dm_zone_unlock(q, zno, clone); + break; + case DM_MAPIO_REQUEUE: + case DM_MAPIO_KILL: + default: + dm_zone_unlock(q, zno, clone); + sts = BLK_STS_IOERR; + break; + } + + /* Drop the extra reference on the IO */ + dm_io_dec_pending(io, sts); + + if (sts != BLK_STS_OK) + return DM_MAPIO_KILL; + + return r; +} + +/* + * IO completion callback called from clone_endio(). + */ +void dm_zone_endio(struct dm_io *io, struct bio *clone) +{ + struct mapped_device *md = io->md; + struct request_queue *q = md->queue; + struct bio *orig_bio = io->orig_bio; + unsigned int zwp_offset; + unsigned int zno; + + /* + * For targets that do not emulate zone append, we only need to + * handle native zone-append bios. + */ + if (!dm_emulate_zone_append(md)) { + /* + * Get the offset within the zone of the written sector + * and add that to the original bio sector position. + */ + if (clone->bi_status == BLK_STS_OK && + bio_op(clone) == REQ_OP_ZONE_APPEND) { + sector_t mask = (sector_t)blk_queue_zone_sectors(q) - 1; + + orig_bio->bi_iter.bi_sector += + clone->bi_iter.bi_sector & mask; + } + + return; + } + + /* + * For targets that do emulate zone append, if the clone BIO does not + * own the target zone write lock, we have nothing to do. + */ + if (!bio_flagged(clone, BIO_ZONE_WRITE_LOCKED)) + return; + + zno = bio_zone_no(orig_bio); + + if (clone->bi_status != BLK_STS_OK) { + /* + * BIOs that modify a zone write pointer may leave the zone + * in an unknown state in case of failure (e.g. the write + * pointer was only partially advanced). In this case, set + * the target zone write pointer as invalid unless it is + * already being updated. + */ + WRITE_ONCE(md->zwp_offset[zno], DM_ZONE_INVALID_WP_OFST); + } else if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) { + /* + * Get the written sector for zone append operation that were + * emulated using regular write operations. + */ + zwp_offset = READ_ONCE(md->zwp_offset[zno]); + if (WARN_ON_ONCE(zwp_offset < bio_sectors(orig_bio))) + WRITE_ONCE(md->zwp_offset[zno], + DM_ZONE_INVALID_WP_OFST); + else + orig_bio->bi_iter.bi_sector += + zwp_offset - bio_sectors(orig_bio); + } + + dm_zone_unlock(q, zno, clone); +} diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 039d17b28938..ee4626d08557 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -1390,6 +1390,13 @@ static int dmz_init_zone(struct blk_zone *blkz, unsigned int num, void *data) return -ENXIO; } + /* + * Devices that have zones with a capacity smaller than the zone size + * (e.g. NVMe zoned namespaces) are not supported. + */ + if (blkz->capacity != blkz->len) + return -ENXIO; + switch (blkz->type) { case BLK_ZONE_TYPE_CONVENTIONAL: set_bit(DMZ_RND, &zone->flags); diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c index 9c0ecc9568a4..d58db9a27e6c 100644 --- a/drivers/md/dm-zoned-reclaim.c +++ b/drivers/md/dm-zoned-reclaim.c @@ -134,7 +134,7 @@ static int dmz_reclaim_copy(struct dmz_reclaim *zrc, dst_zone_block = dmz_start_block(zmd, dst_zone); if (dmz_is_seq(dst_zone)) - set_bit(DM_KCOPYD_WRITE_SEQ, &flags); + flags |= BIT(DM_KCOPYD_WRITE_SEQ); while (block < end_block) { if (src_zone->dev->flags & DMZ_BDEV_DYING) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 190e714cb565..2c5f9e585211 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -74,38 +74,6 @@ struct clone_info { unsigned sector_count; }; -/* - * One of these is allocated per clone bio. - */ -#define DM_TIO_MAGIC 7282014 -struct dm_target_io { - unsigned magic; - struct dm_io *io; - struct dm_target *ti; - unsigned target_bio_nr; - unsigned *len_ptr; - bool inside_dm_io; - struct bio clone; -}; - -/* - * One of these is allocated per original bio. - * It contains the first clone used for that original. - */ -#define DM_IO_MAGIC 5191977 -struct dm_io { - unsigned magic; - struct mapped_device *md; - blk_status_t status; - atomic_t io_count; - struct bio *orig_bio; - unsigned long start_time; - spinlock_t endio_lock; - struct dm_stats_aux stats_aux; - /* last member of dm_target_io is 'struct bio' */ - struct dm_target_io tio; -}; - #define DM_TARGET_IO_BIO_OFFSET (offsetof(struct dm_target_io, clone)) #define DM_IO_BIO_OFFSET \ (offsetof(struct dm_target_io, clone) + offsetof(struct dm_io, tio)) @@ -137,19 +105,6 @@ EXPORT_SYMBOL_GPL(dm_bio_get_target_bio_nr); #define MINOR_ALLOCED ((void *)-1) -/* - * Bits for the md->flags field. - */ -#define DMF_BLOCK_IO_FOR_SUSPEND 0 -#define DMF_SUSPENDED 1 -#define DMF_FROZEN 2 -#define DMF_FREEING 3 -#define DMF_DELETING 4 -#define DMF_NOFLUSH_SUSPENDING 5 -#define DMF_DEFERRED_REMOVE 6 -#define DMF_SUSPENDED_INTERNALLY 7 -#define DMF_POST_SUSPENDING 8 - #define DM_NUMA_NODE NUMA_NO_NODE static int dm_numa_node = DM_NUMA_NODE; @@ -444,84 +399,6 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) return dm_get_geometry(md, geo); } -#ifdef CONFIG_BLK_DEV_ZONED -int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data) -{ - struct dm_report_zones_args *args = data; - sector_t sector_diff = args->tgt->begin - args->start; - - /* - * Ignore zones beyond the target range. - */ - if (zone->start >= args->start + args->tgt->len) - return 0; - - /* - * Remap the start sector and write pointer position of the zone - * to match its position in the target range. - */ - zone->start += sector_diff; - if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) { - if (zone->cond == BLK_ZONE_COND_FULL) - zone->wp = zone->start + zone->len; - else if (zone->cond == BLK_ZONE_COND_EMPTY) - zone->wp = zone->start; - else - zone->wp += sector_diff; - } - - args->next_sector = zone->start + zone->len; - return args->orig_cb(zone, args->zone_idx++, args->orig_data); -} -EXPORT_SYMBOL_GPL(dm_report_zones_cb); - -static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, - unsigned int nr_zones, report_zones_cb cb, void *data) -{ - struct mapped_device *md = disk->private_data; - struct dm_table *map; - int srcu_idx, ret; - struct dm_report_zones_args args = { - .next_sector = sector, - .orig_data = data, - .orig_cb = cb, - }; - - if (dm_suspended_md(md)) - return -EAGAIN; - - map = dm_get_live_table(md, &srcu_idx); - if (!map) { - ret = -EIO; - goto out; - } - - do { - struct dm_target *tgt; - - tgt = dm_table_find_target(map, args.next_sector); - if (WARN_ON_ONCE(!tgt->type->report_zones)) { - ret = -EIO; - goto out; - } - - args.tgt = tgt; - ret = tgt->type->report_zones(tgt, &args, - nr_zones - args.zone_idx); - if (ret < 0) - goto out; - } while (args.zone_idx < nr_zones && - args.next_sector < get_capacity(disk)); - - ret = args.zone_idx; -out: - dm_put_live_table(md, srcu_idx); - return ret; -} -#else -#define dm_blk_report_zones NULL -#endif /* CONFIG_BLK_DEV_ZONED */ - static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx, struct block_device **bdev) { @@ -903,7 +780,7 @@ static int __noflush_suspending(struct mapped_device *md) * Decrements the number of outstanding ios that a bio has been * cloned into, completing the original io if necc. */ -static void dec_pending(struct dm_io *io, blk_status_t error) +void dm_io_dec_pending(struct dm_io *io, blk_status_t error) { unsigned long flags; blk_status_t io_error; @@ -919,22 +796,27 @@ static void dec_pending(struct dm_io *io, blk_status_t error) } if (atomic_dec_and_test(&io->io_count)) { + bio = io->orig_bio; if (io->status == BLK_STS_DM_REQUEUE) { /* * Target requested pushing back the I/O. */ spin_lock_irqsave(&md->deferred_lock, flags); - if (__noflush_suspending(md)) + if (__noflush_suspending(md) && + !WARN_ON_ONCE(dm_is_zone_write(md, bio))) { /* NOTE early return due to BLK_STS_DM_REQUEUE below */ - bio_list_add_head(&md->deferred, io->orig_bio); - else - /* noflush suspend was interrupted. */ + bio_list_add_head(&md->deferred, bio); + } else { + /* + * noflush suspend was interrupted or this is + * a write to a zoned target. + */ io->status = BLK_STS_IOERR; + } spin_unlock_irqrestore(&md->deferred_lock, flags); } io_error = io->status; - bio = io->orig_bio; end_io_acct(io); free_io(md, io); @@ -994,7 +876,6 @@ static void clone_endio(struct bio *bio) struct dm_io *io = tio->io; struct mapped_device *md = tio->io->md; dm_endio_fn endio = tio->ti->type->end_io; - struct bio *orig_bio = io->orig_bio; struct request_queue *q = bio->bi_bdev->bd_disk->queue; if (unlikely(error == BLK_STS_TARGET)) { @@ -1009,23 +890,22 @@ static void clone_endio(struct bio *bio) disable_write_zeroes(md); } - /* - * For zone-append bios get offset in zone of the written - * sector and add that to the original bio sector pos. - */ - if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) { - sector_t written_sector = bio->bi_iter.bi_sector; - struct request_queue *q = orig_bio->bi_bdev->bd_disk->queue; - u64 mask = (u64)blk_queue_zone_sectors(q) - 1; - - orig_bio->bi_iter.bi_sector += written_sector & mask; - } + if (blk_queue_is_zoned(q)) + dm_zone_endio(io, bio); if (endio) { int r = endio(tio->ti, bio, &error); switch (r) { case DM_ENDIO_REQUEUE: - error = BLK_STS_DM_REQUEUE; + /* + * Requeuing writes to a sequential zone of a zoned + * target will break the sequential write pattern: + * fail such IO. + */ + if (WARN_ON_ONCE(dm_is_zone_write(md, bio))) + error = BLK_STS_IOERR; + else + error = BLK_STS_DM_REQUEUE; fallthrough; case DM_ENDIO_DONE: break; @@ -1044,7 +924,7 @@ static void clone_endio(struct bio *bio) } free_tio(tio); - dec_pending(io, error); + dm_io_dec_pending(io, error); } /* @@ -1237,8 +1117,8 @@ static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, /* * A target may call dm_accept_partial_bio only from the map routine. It is - * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_RESET, - * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE and REQ_OP_ZONE_FINISH. + * allowed for all bio types except REQ_PREFLUSH, REQ_OP_ZONE_* zone management + * operations and REQ_OP_ZONE_APPEND (zone append writes). * * dm_accept_partial_bio informs the dm that the target only wants to process * additional n_sectors sectors of the bio and the rest of the data should be @@ -1268,9 +1148,13 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) { struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); unsigned bi_size = bio->bi_iter.bi_size >> SECTOR_SHIFT; + BUG_ON(bio->bi_opf & REQ_PREFLUSH); + BUG_ON(op_is_zone_mgmt(bio_op(bio))); + BUG_ON(bio_op(bio) == REQ_OP_ZONE_APPEND); BUG_ON(bi_size > *tio->len_ptr); BUG_ON(n_sectors > bi_size); + *tio->len_ptr -= bi_size - n_sectors; bio->bi_iter.bi_size = n_sectors << SECTOR_SHIFT; } @@ -1308,7 +1192,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) * anything, the target has assumed ownership of * this io. */ - atomic_inc(&io->io_count); + dm_io_inc_pending(io); sector = clone->bi_iter.bi_sector; if (unlikely(swap_bios_limit(ti, clone))) { @@ -1319,7 +1203,16 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) down(&md->swap_bios_semaphore); } - r = ti->type->map(ti, clone); + /* + * Check if the IO needs a special mapping due to zone append emulation + * on zoned target. In this case, dm_zone_map_bio() calls the target + * map operation. + */ + if (dm_emulate_zone_append(io->md)) + r = dm_zone_map_bio(tio); + else + r = ti->type->map(ti, clone); + switch (r) { case DM_MAPIO_SUBMITTED: break; @@ -1334,7 +1227,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) up(&md->swap_bios_semaphore); } free_tio(tio); - dec_pending(io, BLK_STS_IOERR); + dm_io_dec_pending(io, BLK_STS_IOERR); break; case DM_MAPIO_REQUEUE: if (unlikely(swap_bios_limit(ti, clone))) { @@ -1342,7 +1235,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) up(&md->swap_bios_semaphore); } free_tio(tio); - dec_pending(io, BLK_STS_DM_REQUEUE); + dm_io_dec_pending(io, BLK_STS_DM_REQUEUE); break; default: DMWARN("unimplemented target map return value: %d", r); @@ -1631,7 +1524,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, if (bio->bi_opf & REQ_PREFLUSH) { error = __send_empty_flush(&ci); - /* dec_pending submits any data associated with flush */ + /* dm_io_dec_pending submits any data associated with flush */ } else if (op_is_zone_mgmt(bio_op(bio))) { ci.bio = bio; ci.sector_count = 0; @@ -1672,7 +1565,7 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, } /* drop the extra reference count */ - dec_pending(ci.io, errno_to_blk_status(error)); + dm_io_dec_pending(ci.io, errno_to_blk_status(error)); return ret; } @@ -1801,13 +1694,13 @@ static void cleanup_mapped_device(struct mapped_device *md) md->disk->private_data = NULL; spin_unlock(&_minor_lock); del_gendisk(md->disk); - put_disk(md->disk); } - if (md->queue) { + if (md->queue) dm_queue_destroy_keyslot_manager(md->queue); - blk_cleanup_queue(md->queue); - } + + if (md->disk) + blk_cleanup_disk(md->disk); cleanup_srcu_struct(&md->io_barrier); @@ -1817,6 +1710,7 @@ static void cleanup_mapped_device(struct mapped_device *md) mutex_destroy(&md->swap_bios_lock); dm_mq_cleanup_mapped_device(md); + dm_cleanup_zoned_dev(md); } /* @@ -1869,13 +1763,10 @@ static struct mapped_device *alloc_dev(int minor) * established. If request-based table is loaded: blk-mq will * override accordingly. */ - md->queue = blk_alloc_queue(numa_node_id); - if (!md->queue) - goto bad; - - md->disk = alloc_disk_node(1, md->numa_node_id); + md->disk = blk_alloc_disk(md->numa_node_id); if (!md->disk) goto bad; + md->queue = md->disk->queue; init_waitqueue_head(&md->wait); INIT_WORK(&md->work, dm_wq_work); @@ -1888,6 +1779,7 @@ static struct mapped_device *alloc_dev(int minor) md->disk->major = _major; md->disk->first_minor = minor; + md->disk->minors = 1; md->disk->fops = &dm_blk_dops; md->disk->queue = md->queue; md->disk->private_data = md; @@ -2062,11 +1954,16 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, goto out; } + ret = dm_table_set_restrictions(t, q, limits); + if (ret) { + old_map = ERR_PTR(ret); + goto out; + } + old_map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock)); rcu_assign_pointer(md->map, (void *)t); md->immutable_target_type = dm_table_get_immutable_target_type(t); - dm_table_set_restrictions(t, q, limits); if (old_map) dm_sync_table(md); @@ -2185,7 +2082,10 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t) DMERR("Cannot calculate initial queue limits"); return r; } - dm_table_set_restrictions(t, md->queue, &limits); + r = dm_table_set_restrictions(t, md->queue, &limits); + if (r) + return r; + blk_register_queue(md->disk); return 0; diff --git a/drivers/md/dm.h b/drivers/md/dm.h index b441ad772c18..742d9c80efe1 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -45,6 +45,8 @@ struct dm_dev_internal { struct dm_table; struct dm_md_mempools; +struct dm_target_io; +struct dm_io; /*----------------------------------------------------------------- * Internal table functions. @@ -56,8 +58,8 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector); bool dm_table_has_no_data_devices(struct dm_table *table); int dm_calculate_queue_limits(struct dm_table *table, struct queue_limits *limits); -void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, - struct queue_limits *limits); +int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, + struct queue_limits *limits); struct list_head *dm_table_get_devices(struct dm_table *t); void dm_table_presuspend_targets(struct dm_table *t); void dm_table_presuspend_undo_targets(struct dm_table *t); @@ -100,6 +102,30 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t); */ #define dm_target_hybrid(t) (dm_target_bio_based(t) && dm_target_request_based(t)) +/* + * Zoned targets related functions. + */ +int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q); +void dm_zone_endio(struct dm_io *io, struct bio *clone); +#ifdef CONFIG_BLK_DEV_ZONED +void dm_cleanup_zoned_dev(struct mapped_device *md); +int dm_blk_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data); +bool dm_is_zone_write(struct mapped_device *md, struct bio *bio); +int dm_zone_map_bio(struct dm_target_io *io); +#else +static inline void dm_cleanup_zoned_dev(struct mapped_device *md) {} +#define dm_blk_report_zones NULL +static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio) +{ + return false; +} +static inline int dm_zone_map_bio(struct dm_target_io *tio) +{ + return DM_MAPIO_KILL; +} +#endif + /*----------------------------------------------------------------- * A registry of target types. *---------------------------------------------------------------*/ diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index ea3130e11680..e29c6298ef5c 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2616,7 +2616,7 @@ static struct attribute *md_bitmap_attrs[] = { &max_backlog_used.attr, NULL }; -struct attribute_group md_bitmap_group = { +const struct attribute_group md_bitmap_group = { .name = "bitmap", .attrs = md_bitmap_attrs, }; diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c index fda4cb3f936f..c0dc6f2ef4a3 100644 --- a/drivers/md/md-faulty.c +++ b/drivers/md/md-faulty.c @@ -357,7 +357,7 @@ static void raid_exit(void) module_init(raid_init); module_exit(raid_exit); MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Fault injection personality for MD"); +MODULE_DESCRIPTION("Fault injection personality for MD (deprecated)"); MODULE_ALIAS("md-personality-10"); /* faulty */ MODULE_ALIAS("md-faulty"); MODULE_ALIAS("md-level--5"); diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 63ed8329a98d..1ff51647a682 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -312,7 +312,7 @@ static void linear_exit (void) module_init(linear_init); module_exit(linear_exit); MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Linear device concatenation personality for MD"); +MODULE_DESCRIPTION("Linear device concatenation personality for MD (deprecated)"); MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/ MODULE_ALIAS("md-linear"); MODULE_ALIAS("md-level--1"); diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index 776bbe542db5..e7d6486f090f 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -471,7 +471,7 @@ static void __exit multipath_exit (void) module_init(multipath_init); module_exit(multipath_exit); MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("simple multi-path personality for MD"); +MODULE_DESCRIPTION("simple multi-path personality for MD (deprecated)"); MODULE_ALIAS("md-personality-7"); /* MULTIPATH */ MODULE_ALIAS("md-multipath"); MODULE_ALIAS("md-level--4"); diff --git a/drivers/md/md.c b/drivers/md/md.c index 49f897fbb89b..ae8fe54ea358 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -441,30 +441,6 @@ check_suspended: } EXPORT_SYMBOL(md_handle_request); -struct md_io { - struct mddev *mddev; - bio_end_io_t *orig_bi_end_io; - void *orig_bi_private; - struct block_device *orig_bi_bdev; - unsigned long start_time; -}; - -static void md_end_io(struct bio *bio) -{ - struct md_io *md_io = bio->bi_private; - struct mddev *mddev = md_io->mddev; - - bio_end_io_acct_remapped(bio, md_io->start_time, md_io->orig_bi_bdev); - - bio->bi_end_io = md_io->orig_bi_end_io; - bio->bi_private = md_io->orig_bi_private; - - mempool_free(md_io, &mddev->md_io_pool); - - if (bio->bi_end_io) - bio->bi_end_io(bio); -} - static blk_qc_t md_submit_bio(struct bio *bio) { const int rw = bio_data_dir(bio); @@ -489,21 +465,6 @@ static blk_qc_t md_submit_bio(struct bio *bio) return BLK_QC_T_NONE; } - if (bio->bi_end_io != md_end_io) { - struct md_io *md_io; - - md_io = mempool_alloc(&mddev->md_io_pool, GFP_NOIO); - md_io->mddev = mddev; - md_io->orig_bi_end_io = bio->bi_end_io; - md_io->orig_bi_private = bio->bi_private; - md_io->orig_bi_bdev = bio->bi_bdev; - - bio->bi_end_io = md_end_io; - bio->bi_private = md_io; - - md_io->start_time = bio_start_io_acct(bio); - } - /* bio could be mergeable after passing to underlayer */ bio->bi_opf &= ~REQ_NOMERGE; @@ -824,7 +785,7 @@ out_free_new: return ERR_PTR(error); } -static struct attribute_group md_redundancy_group; +static const struct attribute_group md_redundancy_group; void mddev_unlock(struct mddev *mddev) { @@ -841,7 +802,7 @@ void mddev_unlock(struct mddev *mddev) * test it under the same mutex to ensure its correct value * is seen. */ - struct attribute_group *to_remove = mddev->to_remove; + const struct attribute_group *to_remove = mddev->to_remove; mddev->to_remove = NULL; mddev->sysfs_active = 1; mutex_unlock(&mddev->reconfig_mutex); @@ -2379,7 +2340,15 @@ int md_integrity_register(struct mddev *mddev) bdev_get_integrity(reference->bdev)); pr_debug("md: data integrity enabled on %s\n", mdname(mddev)); - if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE)) { + if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE) || + (mddev->level != 1 && mddev->level != 10 && + bioset_integrity_create(&mddev->io_acct_set, BIO_POOL_SIZE))) { + /* + * No need to handle the failure of bioset_integrity_create, + * because the function is called by md_run() -> pers->run(), + * md_run calls bioset_exit -> bioset_integrity_free in case + * of failure case. + */ pr_err("md: failed to create integrity pool for %s\n", mdname(mddev)); return -EINVAL; @@ -5538,7 +5507,7 @@ static struct attribute *md_redundancy_attrs[] = { &md_degraded.attr, NULL, }; -static struct attribute_group md_redundancy_group = { +static const struct attribute_group md_redundancy_group = { .name = NULL, .attrs = md_redundancy_attrs, }; @@ -5598,17 +5567,16 @@ static void md_free(struct kobject *ko) if (mddev->sysfs_level) sysfs_put(mddev->sysfs_level); - if (mddev->gendisk) + if (mddev->gendisk) { del_gendisk(mddev->gendisk); - if (mddev->queue) - blk_cleanup_queue(mddev->queue); - if (mddev->gendisk) - put_disk(mddev->gendisk); + blk_cleanup_disk(mddev->gendisk); + } percpu_ref_exit(&mddev->writes_pending); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); - mempool_exit(&mddev->md_io_pool); + if (mddev->level != 1 && mddev->level != 10) + bioset_exit(&mddev->io_acct_set); kfree(mddev); } @@ -5705,26 +5673,14 @@ static int md_alloc(dev_t dev, char *name) */ mddev->hold_active = UNTIL_STOP; - error = mempool_init_kmalloc_pool(&mddev->md_io_pool, BIO_POOL_SIZE, - sizeof(struct md_io)); - if (error) - goto abort; - error = -ENOMEM; - mddev->queue = blk_alloc_queue(NUMA_NO_NODE); - if (!mddev->queue) + disk = blk_alloc_disk(NUMA_NO_NODE); + if (!disk) goto abort; - blk_set_stacking_limits(&mddev->queue->limits); - - disk = alloc_disk(1 << shift); - if (!disk) { - blk_cleanup_queue(mddev->queue); - mddev->queue = NULL; - goto abort; - } disk->major = MAJOR(mddev->unit); disk->first_minor = unit << shift; + disk->minors = 1 << shift; if (name) strcpy(disk->disk_name, name); else if (partitioned) @@ -5733,7 +5689,9 @@ static int md_alloc(dev_t dev, char *name) sprintf(disk->disk_name, "md%d", unit); disk->fops = &md_fops; disk->private_data = mddev; - disk->queue = mddev->queue; + + mddev->queue = disk->queue; + blk_set_stacking_limits(&mddev->queue->limits); blk_queue_write_cache(mddev->queue, true, true); /* Allow extended partitions. This makes the * 'mdp' device redundant, but we can't really @@ -5907,7 +5865,14 @@ int md_run(struct mddev *mddev) if (!bioset_initialized(&mddev->sync_set)) { err = bioset_init(&mddev->sync_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (err) - return err; + goto exit_bio_set; + } + if (mddev->level != 1 && mddev->level != 10 && + !bioset_initialized(&mddev->io_acct_set)) { + err = bioset_init(&mddev->io_acct_set, BIO_POOL_SIZE, + offsetof(struct md_io_acct, bio_clone), 0); + if (err) + goto exit_sync_set; } spin_lock(&pers_lock); @@ -6035,6 +6000,7 @@ int md_run(struct mddev *mddev) blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue); else blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue); + blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue); } if (pers->sync_request) { if (mddev->kobj.sd && @@ -6084,8 +6050,12 @@ bitmap_abort: module_put(pers->owner); md_bitmap_destroy(mddev); abort: - bioset_exit(&mddev->bio_set); + if (mddev->level != 1 && mddev->level != 10) + bioset_exit(&mddev->io_acct_set); +exit_sync_set: bioset_exit(&mddev->sync_set); +exit_bio_set: + bioset_exit(&mddev->bio_set); return err; } EXPORT_SYMBOL_GPL(md_run); @@ -6309,6 +6279,8 @@ void md_stop(struct mddev *mddev) __md_stop(mddev); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); + if (mddev->level != 1 && mddev->level != 10) + bioset_exit(&mddev->io_acct_set); } EXPORT_SYMBOL_GPL(md_stop); @@ -8613,6 +8585,41 @@ void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, } EXPORT_SYMBOL_GPL(md_submit_discard_bio); +static void md_end_io_acct(struct bio *bio) +{ + struct md_io_acct *md_io_acct = bio->bi_private; + struct bio *orig_bio = md_io_acct->orig_bio; + + orig_bio->bi_status = bio->bi_status; + + bio_end_io_acct(orig_bio, md_io_acct->start_time); + bio_put(bio); + bio_endio(orig_bio); +} + +/* + * Used by personalities that don't already clone the bio and thus can't + * easily add the timestamp to their extended bio structure. + */ +void md_account_bio(struct mddev *mddev, struct bio **bio) +{ + struct md_io_acct *md_io_acct; + struct bio *clone; + + if (!blk_queue_io_stat((*bio)->bi_bdev->bd_disk->queue)) + return; + + clone = bio_clone_fast(*bio, GFP_NOIO, &mddev->io_acct_set); + md_io_acct = container_of(clone, struct md_io_acct, bio_clone); + md_io_acct->orig_bio = *bio; + md_io_acct->start_time = bio_start_io_acct(*bio); + + clone->bi_end_io = md_end_io_acct; + clone->bi_private = md_io_acct; + *bio = clone; +} +EXPORT_SYMBOL_GPL(md_account_bio); + /* md_allow_write(mddev) * Calling this ensures that the array is marked 'active' so that writes * may proceed without blocking. It is important to call this before diff --git a/drivers/md/md.h b/drivers/md/md.h index fb7eab58cfd5..832547cf038f 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -395,10 +395,10 @@ struct mddev { * that we are never stopping an array while it is open. * 'reconfig_mutex' protects all other reconfiguration. * These locks are separate due to conflicting interactions - * with bdev->bd_mutex. + * with disk->open_mutex. * Lock ordering is: - * reconfig_mutex -> bd_mutex - * bd_mutex -> open_mutex: e.g. __blkdev_get -> md_open + * reconfig_mutex -> disk->open_mutex + * disk->open_mutex -> open_mutex: e.g. __blkdev_get -> md_open */ struct mutex open_mutex; struct mutex reconfig_mutex; @@ -481,13 +481,13 @@ struct mddev { atomic_t max_corr_read_errors; /* max read retries */ struct list_head all_mddevs; - struct attribute_group *to_remove; + const struct attribute_group *to_remove; struct bio_set bio_set; struct bio_set sync_set; /* for sync operations like * metadata and bitmap writes */ - mempool_t md_io_pool; + struct bio_set io_acct_set; /* for raid0 and raid5 io accounting */ /* Generic flush handling. * The last to finish preflush schedules a worker to submit @@ -613,7 +613,7 @@ struct md_sysfs_entry { ssize_t (*show)(struct mddev *, char *); ssize_t (*store)(struct mddev *, const char *, size_t); }; -extern struct attribute_group md_bitmap_group; +extern const struct attribute_group md_bitmap_group; static inline struct kernfs_node *sysfs_get_dirent_safe(struct kernfs_node *sd, char *name) { @@ -684,6 +684,12 @@ struct md_thread { void *private; }; +struct md_io_acct { + struct bio *orig_bio; + unsigned long start_time; + struct bio bio_clone; +}; + #define THREAD_WAKEUP 0 static inline void safe_put_page(struct page *p) @@ -715,6 +721,7 @@ extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); void md_submit_discard_bio(struct mddev *mddev, struct md_rdev *rdev, struct bio *bio, sector_t start, sector_t size); +void md_account_bio(struct mddev *mddev, struct bio **bio); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c index 185dc60360b5..3a963d783a86 100644 --- a/drivers/md/persistent-data/dm-array.c +++ b/drivers/md/persistent-data/dm-array.c @@ -108,12 +108,10 @@ static void *element_at(struct dm_array_info *info, struct array_block *ab, * in an array block. */ static void on_entries(struct dm_array_info *info, struct array_block *ab, - void (*fn)(void *, const void *)) + void (*fn)(void *, const void *, unsigned)) { - unsigned i, nr_entries = le32_to_cpu(ab->nr_entries); - - for (i = 0; i < nr_entries; i++) - fn(info->value_type.context, element_at(info, ab, i)); + unsigned nr_entries = le32_to_cpu(ab->nr_entries); + fn(info->value_type.context, element_at(info, ab, 0), nr_entries); } /* @@ -175,19 +173,18 @@ static int alloc_ablock(struct dm_array_info *info, size_t size_of_block, static void fill_ablock(struct dm_array_info *info, struct array_block *ab, const void *value, unsigned new_nr) { - unsigned i; - uint32_t nr_entries; + uint32_t nr_entries, delta, i; struct dm_btree_value_type *vt = &info->value_type; BUG_ON(new_nr > le32_to_cpu(ab->max_entries)); BUG_ON(new_nr < le32_to_cpu(ab->nr_entries)); nr_entries = le32_to_cpu(ab->nr_entries); - for (i = nr_entries; i < new_nr; i++) { - if (vt->inc) - vt->inc(vt->context, value); + delta = new_nr - nr_entries; + if (vt->inc) + vt->inc(vt->context, value, delta); + for (i = nr_entries; i < new_nr; i++) memcpy(element_at(info, ab, i), value, vt->size); - } ab->nr_entries = cpu_to_le32(new_nr); } @@ -199,17 +196,16 @@ static void fill_ablock(struct dm_array_info *info, struct array_block *ab, static void trim_ablock(struct dm_array_info *info, struct array_block *ab, unsigned new_nr) { - unsigned i; - uint32_t nr_entries; + uint32_t nr_entries, delta; struct dm_btree_value_type *vt = &info->value_type; BUG_ON(new_nr > le32_to_cpu(ab->max_entries)); BUG_ON(new_nr > le32_to_cpu(ab->nr_entries)); nr_entries = le32_to_cpu(ab->nr_entries); - for (i = nr_entries; i > new_nr; i--) - if (vt->dec) - vt->dec(vt->context, element_at(info, ab, i - 1)); + delta = nr_entries - new_nr; + if (vt->dec) + vt->dec(vt->context, element_at(info, ab, new_nr - 1), delta); ab->nr_entries = cpu_to_le32(new_nr); } @@ -573,16 +569,17 @@ static int grow(struct resize *resize) * These are the value_type functions for the btree elements, which point * to array blocks. */ -static void block_inc(void *context, const void *value) +static void block_inc(void *context, const void *value, unsigned count) { - __le64 block_le; + const __le64 *block_le = value; struct dm_array_info *info = context; + unsigned i; - memcpy(&block_le, value, sizeof(block_le)); - dm_tm_inc(info->btree_info.tm, le64_to_cpu(block_le)); + for (i = 0; i < count; i++, block_le++) + dm_tm_inc(info->btree_info.tm, le64_to_cpu(*block_le)); } -static void block_dec(void *context, const void *value) +static void __block_dec(void *context, const void *value) { int r; uint64_t b; @@ -621,6 +618,13 @@ static void block_dec(void *context, const void *value) dm_tm_dec(info->btree_info.tm, b); } +static void block_dec(void *context, const void *value, unsigned count) +{ + unsigned i; + for (i = 0; i < count; i++, value += sizeof(__le64)) + __block_dec(context, value); +} + static int block_equal(void *context, const void *value1, const void *value2) { return !memcmp(value1, value2, sizeof(__le64)); @@ -711,7 +715,7 @@ static int populate_ablock_with_values(struct dm_array_info *info, struct array_ return r; if (vt->inc) - vt->inc(vt->context, element_at(info, ab, i)); + vt->inc(vt->context, element_at(info, ab, i), 1); } ab->nr_entries = cpu_to_le32(new_nr); @@ -822,9 +826,9 @@ static int array_set_value(struct dm_array_info *info, dm_block_t root, old_value = element_at(info, ab, entry); if (vt->dec && (!vt->equal || !vt->equal(vt->context, old_value, value))) { - vt->dec(vt->context, old_value); + vt->dec(vt->context, old_value, 1); if (vt->inc) - vt->inc(vt->context, value); + vt->inc(vt->context, value, 1); } memcpy(old_value, value, info->value_type.size); diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h index b1788853a355..893edb426dba 100644 --- a/drivers/md/persistent-data/dm-btree-internal.h +++ b/drivers/md/persistent-data/dm-btree-internal.h @@ -144,4 +144,17 @@ extern struct dm_block_validator btree_node_validator; extern void init_le64_type(struct dm_transaction_manager *tm, struct dm_btree_value_type *vt); +/* + * This returns a shadowed btree leaf that you may modify. In practise + * this means overwrites only, since an insert could cause a node to + * be split. Useful if you need access to the old value to calculate the + * new one. + * + * This only works with single level btrees. The given key must be present in + * the tree, otherwise -EINVAL will be returned. + */ +int btree_get_overwrite_leaf(struct dm_btree_info *info, dm_block_t root, + uint64_t key, int *index, + dm_block_t *new_root, struct dm_block **leaf); + #endif /* DM_BTREE_INTERNAL_H */ diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index eff04fa23dfa..70532335c7c7 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -544,12 +544,13 @@ int dm_btree_remove(struct dm_btree_info *info, dm_block_t root, if (info->value_type.dec) info->value_type.dec(info->value_type.context, - value_ptr(n, index)); + value_ptr(n, index), 1); delete_at(n, index); } - *new_root = shadow_root(&spine); + if (!r) + *new_root = shadow_root(&spine); exit_shadow_spine(&spine); return r; @@ -653,7 +654,7 @@ static int remove_one(struct dm_btree_info *info, dm_block_t root, if (k >= keys[last_level] && k < end_key) { if (info->value_type.dec) info->value_type.dec(info->value_type.context, - value_ptr(n, index)); + value_ptr(n, index), 1); delete_at(n, index); keys[last_level] = k + 1ull; diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index 2061ab865567..f5bd76ed8fe6 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -236,22 +236,14 @@ dm_block_t shadow_root(struct shadow_spine *s) return s->root; } -static void le64_inc(void *context, const void *value_le) +static void le64_inc(void *context, const void *value_le, unsigned count) { - struct dm_transaction_manager *tm = context; - __le64 v_le; - - memcpy(&v_le, value_le, sizeof(v_le)); - dm_tm_inc(tm, le64_to_cpu(v_le)); + dm_tm_with_runs(context, value_le, count, dm_tm_inc_range); } -static void le64_dec(void *context, const void *value_le) +static void le64_dec(void *context, const void *value_le, unsigned count) { - struct dm_transaction_manager *tm = context; - __le64 v_le; - - memcpy(&v_le, value_le, sizeof(v_le)); - dm_tm_dec(tm, le64_to_cpu(v_le)); + dm_tm_with_runs(context, value_le, count, dm_tm_dec_range); } static int le64_equal(void *context, const void *value1_le, const void *value2_le) diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c index ef6e78d45d5b..0703ca7a7d9a 100644 --- a/drivers/md/persistent-data/dm-btree.c +++ b/drivers/md/persistent-data/dm-btree.c @@ -71,15 +71,13 @@ static int upper_bound(struct btree_node *n, uint64_t key) void inc_children(struct dm_transaction_manager *tm, struct btree_node *n, struct dm_btree_value_type *vt) { - unsigned i; uint32_t nr_entries = le32_to_cpu(n->header.nr_entries); if (le32_to_cpu(n->header.flags) & INTERNAL_NODE) - for (i = 0; i < nr_entries; i++) - dm_tm_inc(tm, value64(n, i)); + dm_tm_with_runs(tm, value_ptr(n, 0), nr_entries, dm_tm_inc_range); + else if (vt->inc) - for (i = 0; i < nr_entries; i++) - vt->inc(vt->context, value_ptr(n, i)); + vt->inc(vt->context, value_ptr(n, 0), nr_entries); } static int insert_at(size_t value_size, struct btree_node *node, unsigned index, @@ -318,13 +316,9 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root) goto out; } else { - if (info->value_type.dec) { - unsigned i; - - for (i = 0; i < f->nr_children; i++) - info->value_type.dec(info->value_type.context, - value_ptr(f->n, i)); - } + if (info->value_type.dec) + info->value_type.dec(info->value_type.context, + value_ptr(f->n, 0), f->nr_children); pop_frame(s); } } @@ -500,6 +494,122 @@ out: EXPORT_SYMBOL_GPL(dm_btree_lookup_next); +/*----------------------------------------------------------------*/ + +/* + * Copies entries from one region of a btree node to another. The regions + * must not overlap. + */ +static void copy_entries(struct btree_node *dest, unsigned dest_offset, + struct btree_node *src, unsigned src_offset, + unsigned count) +{ + size_t value_size = le32_to_cpu(dest->header.value_size); + memcpy(dest->keys + dest_offset, src->keys + src_offset, count * sizeof(uint64_t)); + memcpy(value_ptr(dest, dest_offset), value_ptr(src, src_offset), count * value_size); +} + +/* + * Moves entries from one region fo a btree node to another. The regions + * may overlap. + */ +static void move_entries(struct btree_node *dest, unsigned dest_offset, + struct btree_node *src, unsigned src_offset, + unsigned count) +{ + size_t value_size = le32_to_cpu(dest->header.value_size); + memmove(dest->keys + dest_offset, src->keys + src_offset, count * sizeof(uint64_t)); + memmove(value_ptr(dest, dest_offset), value_ptr(src, src_offset), count * value_size); +} + +/* + * Erases the first 'count' entries of a btree node, shifting following + * entries down into their place. + */ +static void shift_down(struct btree_node *n, unsigned count) +{ + move_entries(n, 0, n, count, le32_to_cpu(n->header.nr_entries) - count); +} + +/* + * Moves entries in a btree node up 'count' places, making space for + * new entries at the start of the node. + */ +static void shift_up(struct btree_node *n, unsigned count) +{ + move_entries(n, count, n, 0, le32_to_cpu(n->header.nr_entries)); +} + +/* + * Redistributes entries between two btree nodes to make them + * have similar numbers of entries. + */ +static void redistribute2(struct btree_node *left, struct btree_node *right) +{ + unsigned nr_left = le32_to_cpu(left->header.nr_entries); + unsigned nr_right = le32_to_cpu(right->header.nr_entries); + unsigned total = nr_left + nr_right; + unsigned target_left = total / 2; + unsigned target_right = total - target_left; + + if (nr_left < target_left) { + unsigned delta = target_left - nr_left; + copy_entries(left, nr_left, right, 0, delta); + shift_down(right, delta); + } else if (nr_left > target_left) { + unsigned delta = nr_left - target_left; + if (nr_right) + shift_up(right, delta); + copy_entries(right, 0, left, target_left, delta); + } + + left->header.nr_entries = cpu_to_le32(target_left); + right->header.nr_entries = cpu_to_le32(target_right); +} + +/* + * Redistribute entries between three nodes. Assumes the central + * node is empty. + */ +static void redistribute3(struct btree_node *left, struct btree_node *center, + struct btree_node *right) +{ + unsigned nr_left = le32_to_cpu(left->header.nr_entries); + unsigned nr_center = le32_to_cpu(center->header.nr_entries); + unsigned nr_right = le32_to_cpu(right->header.nr_entries); + unsigned total, target_left, target_center, target_right; + + BUG_ON(nr_center); + + total = nr_left + nr_right; + target_left = total / 3; + target_center = (total - target_left) / 2; + target_right = (total - target_left - target_center); + + if (nr_left < target_left) { + unsigned left_short = target_left - nr_left; + copy_entries(left, nr_left, right, 0, left_short); + copy_entries(center, 0, right, left_short, target_center); + shift_down(right, nr_right - target_right); + + } else if (nr_left < (target_left + target_center)) { + unsigned left_to_center = nr_left - target_left; + copy_entries(center, 0, left, target_left, left_to_center); + copy_entries(center, left_to_center, right, 0, target_center - left_to_center); + shift_down(right, nr_right - target_right); + + } else { + unsigned right_short = target_right - nr_right; + shift_up(right, right_short); + copy_entries(right, 0, left, nr_left - right_short, right_short); + copy_entries(center, 0, left, target_left, nr_left - target_left); + } + + left->header.nr_entries = cpu_to_le32(target_left); + center->header.nr_entries = cpu_to_le32(target_center); + right->header.nr_entries = cpu_to_le32(target_right); +} + /* * Splits a node by creating a sibling node and shifting half the nodes * contents across. Assumes there is a parent node, and it has room for @@ -530,12 +640,10 @@ EXPORT_SYMBOL_GPL(dm_btree_lookup_next); * * Where A* is a shadow of A. */ -static int btree_split_sibling(struct shadow_spine *s, unsigned parent_index, - uint64_t key) +static int split_one_into_two(struct shadow_spine *s, unsigned parent_index, + struct dm_btree_value_type *vt, uint64_t key) { int r; - size_t size; - unsigned nr_left, nr_right; struct dm_block *left, *right, *parent; struct btree_node *ln, *rn, *pn; __le64 location; @@ -549,36 +657,18 @@ static int btree_split_sibling(struct shadow_spine *s, unsigned parent_index, ln = dm_block_data(left); rn = dm_block_data(right); - nr_left = le32_to_cpu(ln->header.nr_entries) / 2; - nr_right = le32_to_cpu(ln->header.nr_entries) - nr_left; - - ln->header.nr_entries = cpu_to_le32(nr_left); - rn->header.flags = ln->header.flags; - rn->header.nr_entries = cpu_to_le32(nr_right); + rn->header.nr_entries = cpu_to_le32(0); rn->header.max_entries = ln->header.max_entries; rn->header.value_size = ln->header.value_size; - memcpy(rn->keys, ln->keys + nr_left, nr_right * sizeof(rn->keys[0])); + redistribute2(ln, rn); - size = le32_to_cpu(ln->header.flags) & INTERNAL_NODE ? - sizeof(uint64_t) : s->info->value_type.size; - memcpy(value_ptr(rn, 0), value_ptr(ln, nr_left), - size * nr_right); - - /* - * Patch up the parent - */ + /* patch up the parent */ parent = shadow_parent(s); - pn = dm_block_data(parent); - location = cpu_to_le64(dm_block_location(left)); - __dm_bless_for_disk(&location); - memcpy_disk(value_ptr(pn, parent_index), - &location, sizeof(__le64)); location = cpu_to_le64(dm_block_location(right)); __dm_bless_for_disk(&location); - r = insert_at(sizeof(__le64), pn, parent_index + 1, le64_to_cpu(rn->keys[0]), &location); if (r) { @@ -586,6 +676,7 @@ static int btree_split_sibling(struct shadow_spine *s, unsigned parent_index, return r; } + /* patch up the spine */ if (key < le64_to_cpu(rn->keys[0])) { unlock_block(s->info, right); s->nodes[1] = left; @@ -597,6 +688,121 @@ static int btree_split_sibling(struct shadow_spine *s, unsigned parent_index, return 0; } +/* + * We often need to modify a sibling node. This function shadows a particular + * child of the given parent node. Making sure to update the parent to point + * to the new shadow. + */ +static int shadow_child(struct dm_btree_info *info, struct dm_btree_value_type *vt, + struct btree_node *parent, unsigned index, + struct dm_block **result) +{ + int r, inc; + dm_block_t root; + struct btree_node *node; + + root = value64(parent, index); + + r = dm_tm_shadow_block(info->tm, root, &btree_node_validator, + result, &inc); + if (r) + return r; + + node = dm_block_data(*result); + + if (inc) + inc_children(info->tm, node, vt); + + *((__le64 *) value_ptr(parent, index)) = + cpu_to_le64(dm_block_location(*result)); + + return 0; +} + +/* + * Splits two nodes into three. This is more work, but results in fuller + * nodes, so saves metadata space. + */ +static int split_two_into_three(struct shadow_spine *s, unsigned parent_index, + struct dm_btree_value_type *vt, uint64_t key) +{ + int r; + unsigned middle_index; + struct dm_block *left, *middle, *right, *parent; + struct btree_node *ln, *rn, *mn, *pn; + __le64 location; + + parent = shadow_parent(s); + pn = dm_block_data(parent); + + if (parent_index == 0) { + middle_index = 1; + left = shadow_current(s); + r = shadow_child(s->info, vt, pn, parent_index + 1, &right); + if (r) + return r; + } else { + middle_index = parent_index; + right = shadow_current(s); + r = shadow_child(s->info, vt, pn, parent_index - 1, &left); + if (r) + return r; + } + + r = new_block(s->info, &middle); + if (r < 0) + return r; + + ln = dm_block_data(left); + mn = dm_block_data(middle); + rn = dm_block_data(right); + + mn->header.nr_entries = cpu_to_le32(0); + mn->header.flags = ln->header.flags; + mn->header.max_entries = ln->header.max_entries; + mn->header.value_size = ln->header.value_size; + + redistribute3(ln, mn, rn); + + /* patch up the parent */ + pn->keys[middle_index] = rn->keys[0]; + location = cpu_to_le64(dm_block_location(middle)); + __dm_bless_for_disk(&location); + r = insert_at(sizeof(__le64), pn, middle_index, + le64_to_cpu(mn->keys[0]), &location); + if (r) { + if (shadow_current(s) != left) + unlock_block(s->info, left); + + unlock_block(s->info, middle); + + if (shadow_current(s) != right) + unlock_block(s->info, right); + + return r; + } + + + /* patch up the spine */ + if (key < le64_to_cpu(mn->keys[0])) { + unlock_block(s->info, middle); + unlock_block(s->info, right); + s->nodes[1] = left; + } else if (key < le64_to_cpu(rn->keys[0])) { + unlock_block(s->info, left); + unlock_block(s->info, right); + s->nodes[1] = middle; + } else { + unlock_block(s->info, left); + unlock_block(s->info, middle); + s->nodes[1] = right; + } + + return 0; +} + +/*----------------------------------------------------------------*/ + /* * Splits a node by creating two new children beneath the given node. * @@ -690,6 +896,186 @@ static int btree_split_beneath(struct shadow_spine *s, uint64_t key) return 0; } +/*----------------------------------------------------------------*/ + +/* + * Redistributes a node's entries with its left sibling. + */ +static int rebalance_left(struct shadow_spine *s, struct dm_btree_value_type *vt, + unsigned parent_index, uint64_t key) +{ + int r; + struct dm_block *sib; + struct btree_node *left, *right, *parent = dm_block_data(shadow_parent(s)); + + r = shadow_child(s->info, vt, parent, parent_index - 1, &sib); + if (r) + return r; + + left = dm_block_data(sib); + right = dm_block_data(shadow_current(s)); + redistribute2(left, right); + *key_ptr(parent, parent_index) = right->keys[0]; + + if (key < le64_to_cpu(right->keys[0])) { + unlock_block(s->info, s->nodes[1]); + s->nodes[1] = sib; + } else { + unlock_block(s->info, sib); + } + + return 0; +} + +/* + * Redistributes a nodes entries with its right sibling. + */ +static int rebalance_right(struct shadow_spine *s, struct dm_btree_value_type *vt, + unsigned parent_index, uint64_t key) +{ + int r; + struct dm_block *sib; + struct btree_node *left, *right, *parent = dm_block_data(shadow_parent(s)); + + r = shadow_child(s->info, vt, parent, parent_index + 1, &sib); + if (r) + return r; + + left = dm_block_data(shadow_current(s)); + right = dm_block_data(sib); + redistribute2(left, right); + *key_ptr(parent, parent_index + 1) = right->keys[0]; + + if (key < le64_to_cpu(right->keys[0])) { + unlock_block(s->info, sib); + } else { + unlock_block(s->info, s->nodes[1]); + s->nodes[1] = sib; + } + + return 0; +} + +/* + * Returns the number of spare entries in a node. + */ +static int get_node_free_space(struct dm_btree_info *info, dm_block_t b, unsigned *space) +{ + int r; + unsigned nr_entries; + struct dm_block *block; + struct btree_node *node; + + r = bn_read_lock(info, b, &block); + if (r) + return r; + + node = dm_block_data(block); + nr_entries = le32_to_cpu(node->header.nr_entries); + *space = le32_to_cpu(node->header.max_entries) - nr_entries; + + unlock_block(info, block); + return 0; +} + +/* + * Make space in a node, either by moving some entries to a sibling, + * or creating a new sibling node. SPACE_THRESHOLD defines the minimum + * number of free entries that must be in the sibling to make the move + * worth while. If the siblings are shared (eg, part of a snapshot), + * then they are not touched, since this break sharing and so consume + * more space than we save. + */ +#define SPACE_THRESHOLD 8 +static int rebalance_or_split(struct shadow_spine *s, struct dm_btree_value_type *vt, + unsigned parent_index, uint64_t key) +{ + int r; + struct btree_node *parent = dm_block_data(shadow_parent(s)); + unsigned nr_parent = le32_to_cpu(parent->header.nr_entries); + unsigned free_space; + int left_shared = 0, right_shared = 0; + + /* Should we move entries to the left sibling? */ + if (parent_index > 0) { + dm_block_t left_b = value64(parent, parent_index - 1); + r = dm_tm_block_is_shared(s->info->tm, left_b, &left_shared); + if (r) + return r; + + if (!left_shared) { + r = get_node_free_space(s->info, left_b, &free_space); + if (r) + return r; + + if (free_space >= SPACE_THRESHOLD) + return rebalance_left(s, vt, parent_index, key); + } + } + + /* Should we move entries to the right sibling? */ + if (parent_index < (nr_parent - 1)) { + dm_block_t right_b = value64(parent, parent_index + 1); + r = dm_tm_block_is_shared(s->info->tm, right_b, &right_shared); + if (r) + return r; + + if (!right_shared) { + r = get_node_free_space(s->info, right_b, &free_space); + if (r) + return r; + + if (free_space >= SPACE_THRESHOLD) + return rebalance_right(s, vt, parent_index, key); + } + } + + /* + * We need to split the node, normally we split two nodes + * into three. But when inserting a sequence that is either + * monotonically increasing or decreasing it's better to split + * a single node into two. + */ + if (left_shared || right_shared || (nr_parent <= 2) || + (parent_index == 0) || (parent_index + 1 == nr_parent)) { + return split_one_into_two(s, parent_index, vt, key); + } else { + return split_two_into_three(s, parent_index, vt, key); + } +} + +/* + * Does the node contain a particular key? + */ +static bool contains_key(struct btree_node *node, uint64_t key) +{ + int i = lower_bound(node, key); + + if (i >= 0 && le64_to_cpu(node->keys[i]) == key) + return true; + + return false; +} + +/* + * In general we preemptively make sure there's a free entry in every + * node on the spine when doing an insert. But we can avoid that with + * leaf nodes if we know it's an overwrite. + */ +static bool has_space_for_insert(struct btree_node *node, uint64_t key) +{ + if (node->header.nr_entries == node->header.max_entries) { + if (le32_to_cpu(node->header.flags) & LEAF_NODE) { + /* we don't need space if it's an overwrite */ + return contains_key(node, key); + } + + return false; + } + + return true; +} + static int btree_insert_raw(struct shadow_spine *s, dm_block_t root, struct dm_btree_value_type *vt, uint64_t key, unsigned *index) @@ -719,17 +1105,18 @@ static int btree_insert_raw(struct shadow_spine *s, dm_block_t root, node = dm_block_data(shadow_current(s)); - if (node->header.nr_entries == node->header.max_entries) { + if (!has_space_for_insert(node, key)) { if (top) r = btree_split_beneath(s, key); else - r = btree_split_sibling(s, i, key); + r = rebalance_or_split(s, vt, i, key); if (r < 0) return r; - } - node = dm_block_data(shadow_current(s)); + /* making space can cause the current node to change */ + node = dm_block_data(shadow_current(s)); + } i = lower_bound(node, key); @@ -753,6 +1140,77 @@ static int btree_insert_raw(struct shadow_spine *s, dm_block_t root, return 0; } +static int __btree_get_overwrite_leaf(struct shadow_spine *s, dm_block_t root, + uint64_t key, int *index) +{ + int r, i = -1; + struct btree_node *node; + + *index = 0; + for (;;) { + r = shadow_step(s, root, &s->info->value_type); + if (r < 0) + return r; + + node = dm_block_data(shadow_current(s)); + + /* + * We have to patch up the parent node, ugly, but I don't + * see a way to do this automatically as part of the spine + * op. + */ + if (shadow_has_parent(s) && i >= 0) { + __le64 location = cpu_to_le64(dm_block_location(shadow_current(s))); + + __dm_bless_for_disk(&location); + memcpy_disk(value_ptr(dm_block_data(shadow_parent(s)), i), + &location, sizeof(__le64)); + } + + node = dm_block_data(shadow_current(s)); + i = lower_bound(node, key); + + BUG_ON(i < 0); + BUG_ON(i >= le32_to_cpu(node->header.nr_entries)); + + if (le32_to_cpu(node->header.flags) & LEAF_NODE) { + if (key != le64_to_cpu(node->keys[i])) + return -EINVAL; + break; + } + + root = value64(node, i); + } + + *index = i; + return 0; +} + +int btree_get_overwrite_leaf(struct dm_btree_info *info, dm_block_t root, + uint64_t key, int *index, + dm_block_t *new_root, struct dm_block **leaf) +{ + int r; + struct shadow_spine spine; + + BUG_ON(info->levels > 1); + init_shadow_spine(&spine, info); + r = __btree_get_overwrite_leaf(&spine, root, key, index); + if (!r) { + *new_root = shadow_root(&spine); + *leaf = shadow_current(&spine); + + /* + * Decrement the count so exit_shadow_spine() doesn't + * unlock the leaf. + */ + spine.count--; + } + exit_shadow_spine(&spine); + + return r; +} + static bool need_insert(struct btree_node *node, uint64_t *keys, unsigned level, unsigned index) { @@ -829,7 +1287,7 @@ static int insert(struct dm_btree_info *info, dm_block_t root, value_ptr(n, index), value))) { info->value_type.dec(info->value_type.context, - value_ptr(n, index)); + value_ptr(n, index), 1); } memcpy_disk(value_ptr(n, index), value, info->value_type.size); diff --git a/drivers/md/persistent-data/dm-btree.h b/drivers/md/persistent-data/dm-btree.h index 3dc5bb1a4748..d2ae5aa4d00b 100644 --- a/drivers/md/persistent-data/dm-btree.h +++ b/drivers/md/persistent-data/dm-btree.h @@ -51,21 +51,21 @@ struct dm_btree_value_type { */ /* - * The btree is making a duplicate of the value, for instance + * The btree is making a duplicate of a run of values, for instance * because previously-shared btree nodes have now diverged. * @value argument is the new copy that the copy function may modify. * (Probably it just wants to increment a reference count * somewhere.) This method is _not_ called for insertion of a new * value: It is assumed the ref count is already 1. */ - void (*inc)(void *context, const void *value); + void (*inc)(void *context, const void *value, unsigned count); /* - * This value is being deleted. The btree takes care of freeing + * These values are being deleted. The btree takes care of freeing * the memory pointed to by @value. Often the del function just - * needs to decrement a reference count somewhere. + * needs to decrement a reference counts somewhere. */ - void (*dec)(void *context, const void *value); + void (*dec)(void *context, const void *value, unsigned count); /* * A test for equality between two values. When a value is diff --git a/drivers/md/persistent-data/dm-space-map-common.c b/drivers/md/persistent-data/dm-space-map-common.c index a213bf11738f..4a6a2a9b4eb4 100644 --- a/drivers/md/persistent-data/dm-space-map-common.c +++ b/drivers/md/persistent-data/dm-space-map-common.c @@ -6,6 +6,8 @@ #include "dm-space-map-common.h" #include "dm-transaction-manager.h" +#include "dm-btree-internal.h" +#include "dm-persistent-data-internal.h" #include #include @@ -409,12 +411,13 @@ int sm_ll_find_common_free_block(struct ll_disk *old_ll, struct ll_disk *new_ll, return r; } -static int sm_ll_mutate(struct ll_disk *ll, dm_block_t b, - int (*mutator)(void *context, uint32_t old, uint32_t *new), - void *context, enum allocation_event *ev) +/*----------------------------------------------------------------*/ + +int sm_ll_insert(struct ll_disk *ll, dm_block_t b, + uint32_t ref_count, int32_t *nr_allocations) { int r; - uint32_t bit, old, ref_count; + uint32_t bit, old; struct dm_block *nb; dm_block_t index = b; struct disk_index_entry ie_disk; @@ -433,10 +436,9 @@ static int sm_ll_mutate(struct ll_disk *ll, dm_block_t b, return r; } ie_disk.blocknr = cpu_to_le64(dm_block_location(nb)); - bm_le = dm_bitmap_data(nb); - old = sm_lookup_bitmap(bm_le, bit); + old = sm_lookup_bitmap(bm_le, bit); if (old > 2) { r = sm_ll_lookup_big_ref_count(ll, b, &old); if (r < 0) { @@ -445,7 +447,6 @@ static int sm_ll_mutate(struct ll_disk *ll, dm_block_t b, } } - r = mutator(context, old, &ref_count); if (r) { dm_tm_unlock(ll->tm, nb); return r; @@ -453,7 +454,6 @@ static int sm_ll_mutate(struct ll_disk *ll, dm_block_t b, if (ref_count <= 2) { sm_set_bitmap(bm_le, bit, ref_count); - dm_tm_unlock(ll->tm, nb); if (old > 2) { @@ -480,62 +480,459 @@ static int sm_ll_mutate(struct ll_disk *ll, dm_block_t b, } if (ref_count && !old) { - *ev = SM_ALLOC; + *nr_allocations = 1; ll->nr_allocated++; le32_add_cpu(&ie_disk.nr_free, -1); if (le32_to_cpu(ie_disk.none_free_before) == bit) ie_disk.none_free_before = cpu_to_le32(bit + 1); } else if (old && !ref_count) { - *ev = SM_FREE; + *nr_allocations = -1; ll->nr_allocated--; le32_add_cpu(&ie_disk.nr_free, 1); ie_disk.none_free_before = cpu_to_le32(min(le32_to_cpu(ie_disk.none_free_before), bit)); } else - *ev = SM_NONE; + *nr_allocations = 0; return ll->save_ie(ll, index, &ie_disk); } -static int set_ref_count(void *context, uint32_t old, uint32_t *new) +/*----------------------------------------------------------------*/ + +/* + * Holds useful intermediate results for the range based inc and dec + * operations. + */ +struct inc_context { + struct disk_index_entry ie_disk; + struct dm_block *bitmap_block; + void *bitmap; + + struct dm_block *overflow_leaf; +}; + +static inline void init_inc_context(struct inc_context *ic) { - *new = *((uint32_t *) context); - return 0; + ic->bitmap_block = NULL; + ic->bitmap = NULL; + ic->overflow_leaf = NULL; } -int sm_ll_insert(struct ll_disk *ll, dm_block_t b, - uint32_t ref_count, enum allocation_event *ev) +static inline void exit_inc_context(struct ll_disk *ll, struct inc_context *ic) { - return sm_ll_mutate(ll, b, set_ref_count, &ref_count, ev); + if (ic->bitmap_block) + dm_tm_unlock(ll->tm, ic->bitmap_block); + if (ic->overflow_leaf) + dm_tm_unlock(ll->tm, ic->overflow_leaf); } -static int inc_ref_count(void *context, uint32_t old, uint32_t *new) +static inline void reset_inc_context(struct ll_disk *ll, struct inc_context *ic) { - *new = old + 1; - return 0; + exit_inc_context(ll, ic); + init_inc_context(ic); } -int sm_ll_inc(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev) +/* + * Confirms a btree node contains a particular key at an index. + */ +static bool contains_key(struct btree_node *n, uint64_t key, int index) { - return sm_ll_mutate(ll, b, inc_ref_count, NULL, ev); + return index >= 0 && + index < le32_to_cpu(n->header.nr_entries) && + le64_to_cpu(n->keys[index]) == key; } -static int dec_ref_count(void *context, uint32_t old, uint32_t *new) +static int __sm_ll_inc_overflow(struct ll_disk *ll, dm_block_t b, struct inc_context *ic) { - if (!old) { - DMERR_LIMIT("unable to decrement a reference count below 0"); + int r; + int index; + struct btree_node *n; + __le32 *v_ptr; + uint32_t rc; + + /* + * bitmap_block needs to be unlocked because getting the + * overflow_leaf may need to allocate, and thus use the space map. + */ + reset_inc_context(ll, ic); + + r = btree_get_overwrite_leaf(&ll->ref_count_info, ll->ref_count_root, + b, &index, &ll->ref_count_root, &ic->overflow_leaf); + if (r < 0) + return r; + + n = dm_block_data(ic->overflow_leaf); + + if (!contains_key(n, b, index)) { + DMERR("overflow btree is missing an entry"); return -EINVAL; } - *new = old - 1; + v_ptr = value_ptr(n, index); + rc = le32_to_cpu(*v_ptr) + 1; + *v_ptr = cpu_to_le32(rc); + return 0; } -int sm_ll_dec(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev) +static int sm_ll_inc_overflow(struct ll_disk *ll, dm_block_t b, struct inc_context *ic) { - return sm_ll_mutate(ll, b, dec_ref_count, NULL, ev); + int index; + struct btree_node *n; + __le32 *v_ptr; + uint32_t rc; + + /* + * Do we already have the correct overflow leaf? + */ + if (ic->overflow_leaf) { + n = dm_block_data(ic->overflow_leaf); + index = lower_bound(n, b); + if (contains_key(n, b, index)) { + v_ptr = value_ptr(n, index); + rc = le32_to_cpu(*v_ptr) + 1; + *v_ptr = cpu_to_le32(rc); + + return 0; + } + } + + return __sm_ll_inc_overflow(ll, b, ic); } +static inline int shadow_bitmap(struct ll_disk *ll, struct inc_context *ic) +{ + int r, inc; + r = dm_tm_shadow_block(ll->tm, le64_to_cpu(ic->ie_disk.blocknr), + &dm_sm_bitmap_validator, &ic->bitmap_block, &inc); + if (r < 0) { + DMERR("dm_tm_shadow_block() failed"); + return r; + } + ic->ie_disk.blocknr = cpu_to_le64(dm_block_location(ic->bitmap_block)); + ic->bitmap = dm_bitmap_data(ic->bitmap_block); + return 0; +} + +/* + * Once shadow_bitmap has been called, which always happens at the start of inc/dec, + * we can reopen the bitmap with a simple write lock, rather than re calling + * dm_tm_shadow_block(). + */ +static inline int ensure_bitmap(struct ll_disk *ll, struct inc_context *ic) +{ + if (!ic->bitmap_block) { + int r = dm_bm_write_lock(dm_tm_get_bm(ll->tm), le64_to_cpu(ic->ie_disk.blocknr), + &dm_sm_bitmap_validator, &ic->bitmap_block); + if (r) { + DMERR("unable to re-get write lock for bitmap"); + return r; + } + ic->bitmap = dm_bitmap_data(ic->bitmap_block); + } + + return 0; +} + +/* + * Loops round incrementing entries in a single bitmap. + */ +static inline int sm_ll_inc_bitmap(struct ll_disk *ll, dm_block_t b, + uint32_t bit, uint32_t bit_end, + int32_t *nr_allocations, dm_block_t *new_b, + struct inc_context *ic) +{ + int r; + __le32 le_rc; + uint32_t old; + + for (; bit != bit_end; bit++, b++) { + /* + * We only need to drop the bitmap if we need to find a new btree + * leaf for the overflow. So if it was dropped last iteration, + * we now re-get it. + */ + r = ensure_bitmap(ll, ic); + if (r) + return r; + + old = sm_lookup_bitmap(ic->bitmap, bit); + switch (old) { + case 0: + /* inc bitmap, adjust nr_allocated */ + sm_set_bitmap(ic->bitmap, bit, 1); + (*nr_allocations)++; + ll->nr_allocated++; + le32_add_cpu(&ic->ie_disk.nr_free, -1); + if (le32_to_cpu(ic->ie_disk.none_free_before) == bit) + ic->ie_disk.none_free_before = cpu_to_le32(bit + 1); + break; + + case 1: + /* inc bitmap */ + sm_set_bitmap(ic->bitmap, bit, 2); + break; + + case 2: + /* inc bitmap and insert into overflow */ + sm_set_bitmap(ic->bitmap, bit, 3); + reset_inc_context(ll, ic); + + le_rc = cpu_to_le32(3); + __dm_bless_for_disk(&le_rc); + r = dm_btree_insert(&ll->ref_count_info, ll->ref_count_root, + &b, &le_rc, &ll->ref_count_root); + if (r < 0) { + DMERR("ref count insert failed"); + return r; + } + break; + + default: + /* + * inc within the overflow tree only. + */ + r = sm_ll_inc_overflow(ll, b, ic); + if (r < 0) + return r; + } + } + + *new_b = b; + return 0; +} + +/* + * Finds a bitmap that contains entries in the block range, and increments + * them. + */ +static int __sm_ll_inc(struct ll_disk *ll, dm_block_t b, dm_block_t e, + int32_t *nr_allocations, dm_block_t *new_b) +{ + int r; + struct inc_context ic; + uint32_t bit, bit_end; + dm_block_t index = b; + + init_inc_context(&ic); + + bit = do_div(index, ll->entries_per_block); + r = ll->load_ie(ll, index, &ic.ie_disk); + if (r < 0) + return r; + + r = shadow_bitmap(ll, &ic); + if (r) + return r; + + bit_end = min(bit + (e - b), (dm_block_t) ll->entries_per_block); + r = sm_ll_inc_bitmap(ll, b, bit, bit_end, nr_allocations, new_b, &ic); + + exit_inc_context(ll, &ic); + + if (r) + return r; + + return ll->save_ie(ll, index, &ic.ie_disk); +} + +int sm_ll_inc(struct ll_disk *ll, dm_block_t b, dm_block_t e, + int32_t *nr_allocations) +{ + *nr_allocations = 0; + while (b != e) { + int r = __sm_ll_inc(ll, b, e, nr_allocations, &b); + if (r) + return r; + } + + return 0; +} + +/*----------------------------------------------------------------*/ + +static int __sm_ll_del_overflow(struct ll_disk *ll, dm_block_t b, + struct inc_context *ic) +{ + reset_inc_context(ll, ic); + return dm_btree_remove(&ll->ref_count_info, ll->ref_count_root, + &b, &ll->ref_count_root); +} + +static int __sm_ll_dec_overflow(struct ll_disk *ll, dm_block_t b, + struct inc_context *ic, uint32_t *old_rc) +{ + int r; + int index = -1; + struct btree_node *n; + __le32 *v_ptr; + uint32_t rc; + + reset_inc_context(ll, ic); + r = btree_get_overwrite_leaf(&ll->ref_count_info, ll->ref_count_root, + b, &index, &ll->ref_count_root, &ic->overflow_leaf); + if (r < 0) + return r; + + n = dm_block_data(ic->overflow_leaf); + + if (!contains_key(n, b, index)) { + DMERR("overflow btree is missing an entry"); + return -EINVAL; + } + + v_ptr = value_ptr(n, index); + rc = le32_to_cpu(*v_ptr); + *old_rc = rc; + + if (rc == 3) { + return __sm_ll_del_overflow(ll, b, ic); + } else { + rc--; + *v_ptr = cpu_to_le32(rc); + return 0; + } +} + +static int sm_ll_dec_overflow(struct ll_disk *ll, dm_block_t b, + struct inc_context *ic, uint32_t *old_rc) +{ + /* + * Do we already have the correct overflow leaf? + */ + if (ic->overflow_leaf) { + int index; + struct btree_node *n; + __le32 *v_ptr; + uint32_t rc; + + n = dm_block_data(ic->overflow_leaf); + index = lower_bound(n, b); + if (contains_key(n, b, index)) { + v_ptr = value_ptr(n, index); + rc = le32_to_cpu(*v_ptr); + *old_rc = rc; + + if (rc > 3) { + rc--; + *v_ptr = cpu_to_le32(rc); + return 0; + } else { + return __sm_ll_del_overflow(ll, b, ic); + } + + } + } + + return __sm_ll_dec_overflow(ll, b, ic, old_rc); +} + +/* + * Loops round incrementing entries in a single bitmap. + */ +static inline int sm_ll_dec_bitmap(struct ll_disk *ll, dm_block_t b, + uint32_t bit, uint32_t bit_end, + struct inc_context *ic, + int32_t *nr_allocations, dm_block_t *new_b) +{ + int r; + uint32_t old; + + for (; bit != bit_end; bit++, b++) { + /* + * We only need to drop the bitmap if we need to find a new btree + * leaf for the overflow. So if it was dropped last iteration, + * we now re-get it. + */ + r = ensure_bitmap(ll, ic); + if (r) + return r; + + old = sm_lookup_bitmap(ic->bitmap, bit); + switch (old) { + case 0: + DMERR("unable to decrement block"); + return -EINVAL; + + case 1: + /* dec bitmap */ + sm_set_bitmap(ic->bitmap, bit, 0); + (*nr_allocations)--; + ll->nr_allocated--; + le32_add_cpu(&ic->ie_disk.nr_free, 1); + ic->ie_disk.none_free_before = + cpu_to_le32(min(le32_to_cpu(ic->ie_disk.none_free_before), bit)); + break; + + case 2: + /* dec bitmap and insert into overflow */ + sm_set_bitmap(ic->bitmap, bit, 1); + break; + + case 3: + r = sm_ll_dec_overflow(ll, b, ic, &old); + if (r < 0) + return r; + + if (old == 3) { + r = ensure_bitmap(ll, ic); + if (r) + return r; + + sm_set_bitmap(ic->bitmap, bit, 2); + } + break; + } + } + + *new_b = b; + return 0; +} + +static int __sm_ll_dec(struct ll_disk *ll, dm_block_t b, dm_block_t e, + int32_t *nr_allocations, dm_block_t *new_b) +{ + int r; + uint32_t bit, bit_end; + struct inc_context ic; + dm_block_t index = b; + + init_inc_context(&ic); + + bit = do_div(index, ll->entries_per_block); + r = ll->load_ie(ll, index, &ic.ie_disk); + if (r < 0) + return r; + + r = shadow_bitmap(ll, &ic); + if (r) + return r; + + bit_end = min(bit + (e - b), (dm_block_t) ll->entries_per_block); + r = sm_ll_dec_bitmap(ll, b, bit, bit_end, &ic, nr_allocations, new_b); + exit_inc_context(ll, &ic); + + if (r) + return r; + + return ll->save_ie(ll, index, &ic.ie_disk); +} + +int sm_ll_dec(struct ll_disk *ll, dm_block_t b, dm_block_t e, + int32_t *nr_allocations) +{ + *nr_allocations = 0; + while (b != e) { + int r = __sm_ll_dec(ll, b, e, nr_allocations, &b); + if (r) + return r; + } + + return 0; +} + +/*----------------------------------------------------------------*/ + int sm_ll_commit(struct ll_disk *ll) { int r = 0; @@ -687,28 +1084,92 @@ int sm_ll_open_metadata(struct ll_disk *ll, struct dm_transaction_manager *tm, /*----------------------------------------------------------------*/ +static inline int ie_cache_writeback(struct ll_disk *ll, struct ie_cache *iec) +{ + iec->dirty = false; + __dm_bless_for_disk(iec->ie); + return dm_btree_insert(&ll->bitmap_info, ll->bitmap_root, + &iec->index, &iec->ie, &ll->bitmap_root); +} + +static inline unsigned hash_index(dm_block_t index) +{ + return dm_hash_block(index, IE_CACHE_MASK); +} + static int disk_ll_load_ie(struct ll_disk *ll, dm_block_t index, struct disk_index_entry *ie) { - return dm_btree_lookup(&ll->bitmap_info, ll->bitmap_root, &index, ie); + int r; + unsigned h = hash_index(index); + struct ie_cache *iec = ll->ie_cache + h; + + if (iec->valid) { + if (iec->index == index) { + memcpy(ie, &iec->ie, sizeof(*ie)); + return 0; + } + + if (iec->dirty) { + r = ie_cache_writeback(ll, iec); + if (r) + return r; + } + } + + r = dm_btree_lookup(&ll->bitmap_info, ll->bitmap_root, &index, ie); + if (!r) { + iec->valid = true; + iec->dirty = false; + iec->index = index; + memcpy(&iec->ie, ie, sizeof(*ie)); + } + + return r; } static int disk_ll_save_ie(struct ll_disk *ll, dm_block_t index, struct disk_index_entry *ie) { - __dm_bless_for_disk(ie); - return dm_btree_insert(&ll->bitmap_info, ll->bitmap_root, - &index, ie, &ll->bitmap_root); + int r; + unsigned h = hash_index(index); + struct ie_cache *iec = ll->ie_cache + h; + + ll->bitmap_index_changed = true; + if (iec->valid) { + if (iec->index == index) { + memcpy(&iec->ie, ie, sizeof(*ie)); + iec->dirty = true; + return 0; + } + + if (iec->dirty) { + r = ie_cache_writeback(ll, iec); + if (r) + return r; + } + } + + iec->valid = true; + iec->dirty = true; + iec->index = index; + memcpy(&iec->ie, ie, sizeof(*ie)); + return 0; } static int disk_ll_init_index(struct ll_disk *ll) { + unsigned i; + for (i = 0; i < IE_CACHE_SIZE; i++) { + struct ie_cache *iec = ll->ie_cache + i; + iec->valid = false; + iec->dirty = false; + } return dm_btree_empty(&ll->bitmap_info, &ll->bitmap_root); } static int disk_ll_open(struct ll_disk *ll) { - /* nothing to do */ return 0; } @@ -719,7 +1180,16 @@ static dm_block_t disk_ll_max_entries(struct ll_disk *ll) static int disk_ll_commit(struct ll_disk *ll) { - return 0; + int r = 0; + unsigned i; + + for (i = 0; i < IE_CACHE_SIZE; i++) { + struct ie_cache *iec = ll->ie_cache + i; + if (iec->valid && iec->dirty) + r = ie_cache_writeback(ll, iec); + } + + return r; } int sm_ll_new_disk(struct ll_disk *ll, struct dm_transaction_manager *tm) diff --git a/drivers/md/persistent-data/dm-space-map-common.h b/drivers/md/persistent-data/dm-space-map-common.h index 87e17909ef52..706ceb85d680 100644 --- a/drivers/md/persistent-data/dm-space-map-common.h +++ b/drivers/md/persistent-data/dm-space-map-common.h @@ -54,6 +54,20 @@ typedef int (*open_index_fn)(struct ll_disk *ll); typedef dm_block_t (*max_index_entries_fn)(struct ll_disk *ll); typedef int (*commit_fn)(struct ll_disk *ll); +/* + * A lot of time can be wasted reading and writing the same + * index entry. So we cache a few entries. + */ +#define IE_CACHE_SIZE 64 +#define IE_CACHE_MASK (IE_CACHE_SIZE - 1) + +struct ie_cache { + bool valid; + bool dirty; + dm_block_t index; + struct disk_index_entry ie; +}; + struct ll_disk { struct dm_transaction_manager *tm; struct dm_btree_info bitmap_info; @@ -79,6 +93,8 @@ struct ll_disk { max_index_entries_fn max_entries; commit_fn commit; bool bitmap_index_changed:1; + + struct ie_cache ie_cache[IE_CACHE_SIZE]; }; struct disk_sm_root { @@ -96,12 +112,6 @@ struct disk_bitmap_header { __le64 blocknr; } __attribute__ ((packed, aligned(8))); -enum allocation_event { - SM_NONE, - SM_ALLOC, - SM_FREE, -}; - /*----------------------------------------------------------------*/ int sm_ll_extend(struct ll_disk *ll, dm_block_t extra_blocks); @@ -111,9 +121,15 @@ int sm_ll_find_free_block(struct ll_disk *ll, dm_block_t begin, dm_block_t end, dm_block_t *result); int sm_ll_find_common_free_block(struct ll_disk *old_ll, struct ll_disk *new_ll, dm_block_t begin, dm_block_t end, dm_block_t *result); -int sm_ll_insert(struct ll_disk *ll, dm_block_t b, uint32_t ref_count, enum allocation_event *ev); -int sm_ll_inc(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev); -int sm_ll_dec(struct ll_disk *ll, dm_block_t b, enum allocation_event *ev); + +/* + * The next three functions return (via nr_allocations) the net number of + * allocations that were made. This number may be negative if there were + * more frees than allocs. + */ +int sm_ll_insert(struct ll_disk *ll, dm_block_t b, uint32_t ref_count, int32_t *nr_allocations); +int sm_ll_inc(struct ll_disk *ll, dm_block_t b, dm_block_t e, int32_t *nr_allocations); +int sm_ll_dec(struct ll_disk *ll, dm_block_t b, dm_block_t e, int32_t *nr_allocations); int sm_ll_commit(struct ll_disk *ll); int sm_ll_new_metadata(struct ll_disk *ll, struct dm_transaction_manager *tm); diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c index 61f56909e00b..d0a8d5e73c28 100644 --- a/drivers/md/persistent-data/dm-space-map-disk.c +++ b/drivers/md/persistent-data/dm-space-map-disk.c @@ -87,76 +87,39 @@ static int sm_disk_set_count(struct dm_space_map *sm, dm_block_t b, uint32_t count) { int r; - uint32_t old_count; - enum allocation_event ev; + int32_t nr_allocations; struct sm_disk *smd = container_of(sm, struct sm_disk, sm); - r = sm_ll_insert(&smd->ll, b, count, &ev); + r = sm_ll_insert(&smd->ll, b, count, &nr_allocations); if (!r) { - switch (ev) { - case SM_NONE: - break; - - case SM_ALLOC: - /* - * This _must_ be free in the prior transaction - * otherwise we've lost atomicity. - */ - smd->nr_allocated_this_transaction++; - break; - - case SM_FREE: - /* - * It's only free if it's also free in the last - * transaction. - */ - r = sm_ll_lookup(&smd->old_ll, b, &old_count); - if (r) - return r; - - if (!old_count) - smd->nr_allocated_this_transaction--; - break; - } + smd->nr_allocated_this_transaction += nr_allocations; } return r; } -static int sm_disk_inc_block(struct dm_space_map *sm, dm_block_t b) +static int sm_disk_inc_blocks(struct dm_space_map *sm, dm_block_t b, dm_block_t e) { int r; - enum allocation_event ev; + int32_t nr_allocations; struct sm_disk *smd = container_of(sm, struct sm_disk, sm); - r = sm_ll_inc(&smd->ll, b, &ev); - if (!r && (ev == SM_ALLOC)) - /* - * This _must_ be free in the prior transaction - * otherwise we've lost atomicity. - */ - smd->nr_allocated_this_transaction++; + r = sm_ll_inc(&smd->ll, b, e, &nr_allocations); + if (!r) + smd->nr_allocated_this_transaction += nr_allocations; return r; } -static int sm_disk_dec_block(struct dm_space_map *sm, dm_block_t b) +static int sm_disk_dec_blocks(struct dm_space_map *sm, dm_block_t b, dm_block_t e) { int r; - uint32_t old_count; - enum allocation_event ev; + int32_t nr_allocations; struct sm_disk *smd = container_of(sm, struct sm_disk, sm); - r = sm_ll_dec(&smd->ll, b, &ev); - if (!r && (ev == SM_FREE)) { - /* - * It's only free if it's also free in the last - * transaction. - */ - r = sm_ll_lookup(&smd->old_ll, b, &old_count); - if (!r && !old_count) - smd->nr_allocated_this_transaction--; - } + r = sm_ll_dec(&smd->ll, b, e, &nr_allocations); + if (!r) + smd->nr_allocated_this_transaction += nr_allocations; return r; } @@ -164,21 +127,28 @@ static int sm_disk_dec_block(struct dm_space_map *sm, dm_block_t b) static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b) { int r; - enum allocation_event ev; + int32_t nr_allocations; struct sm_disk *smd = container_of(sm, struct sm_disk, sm); /* * Any block we allocate has to be free in both the old and current ll. */ r = sm_ll_find_common_free_block(&smd->old_ll, &smd->ll, smd->begin, smd->ll.nr_blocks, b); + if (r == -ENOSPC) { + /* + * There's no free block between smd->begin and the end of the metadata device. + * We search before smd->begin in case something has been freed. + */ + r = sm_ll_find_common_free_block(&smd->old_ll, &smd->ll, 0, smd->begin, b); + } + if (r) return r; smd->begin = *b + 1; - r = sm_ll_inc(&smd->ll, *b, &ev); + r = sm_ll_inc(&smd->ll, *b, *b + 1, &nr_allocations); if (!r) { - BUG_ON(ev != SM_ALLOC); - smd->nr_allocated_this_transaction++; + smd->nr_allocated_this_transaction += nr_allocations; } return r; @@ -194,7 +164,6 @@ static int sm_disk_commit(struct dm_space_map *sm) return r; memcpy(&smd->old_ll, &smd->ll, sizeof(smd->old_ll)); - smd->begin = 0; smd->nr_allocated_this_transaction = 0; return 0; @@ -235,8 +204,8 @@ static struct dm_space_map ops = { .get_count = sm_disk_get_count, .count_is_more_than_one = sm_disk_count_is_more_than_one, .set_count = sm_disk_set_count, - .inc_block = sm_disk_inc_block, - .dec_block = sm_disk_dec_block, + .inc_blocks = sm_disk_inc_blocks, + .dec_blocks = sm_disk_dec_blocks, .new_block = sm_disk_new_block, .commit = sm_disk_commit, .root_size = sm_disk_root_size, diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index 9e3c64ec2026..392ae26134a4 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -89,7 +89,8 @@ enum block_op_type { struct block_op { enum block_op_type type; - dm_block_t block; + dm_block_t b; + dm_block_t e; }; struct bop_ring_buffer { @@ -116,7 +117,7 @@ static unsigned brb_next(struct bop_ring_buffer *brb, unsigned old) } static int brb_push(struct bop_ring_buffer *brb, - enum block_op_type type, dm_block_t b) + enum block_op_type type, dm_block_t b, dm_block_t e) { struct block_op *bop; unsigned next = brb_next(brb, brb->end); @@ -130,7 +131,8 @@ static int brb_push(struct bop_ring_buffer *brb, bop = brb->bops + brb->end; bop->type = type; - bop->block = b; + bop->b = b; + bop->e = e; brb->end = next; @@ -145,9 +147,7 @@ static int brb_peek(struct bop_ring_buffer *brb, struct block_op *result) return -ENODATA; bop = brb->bops + brb->begin; - result->type = bop->type; - result->block = bop->block; - + memcpy(result, bop, sizeof(*result)); return 0; } @@ -178,10 +178,9 @@ struct sm_metadata { struct threshold threshold; }; -static int add_bop(struct sm_metadata *smm, enum block_op_type type, dm_block_t b) +static int add_bop(struct sm_metadata *smm, enum block_op_type type, dm_block_t b, dm_block_t e) { - int r = brb_push(&smm->uncommitted, type, b); - + int r = brb_push(&smm->uncommitted, type, b, e); if (r) { DMERR("too many recursive allocations"); return -ENOMEM; @@ -193,15 +192,15 @@ static int add_bop(struct sm_metadata *smm, enum block_op_type type, dm_block_t static int commit_bop(struct sm_metadata *smm, struct block_op *op) { int r = 0; - enum allocation_event ev; + int32_t nr_allocations; switch (op->type) { case BOP_INC: - r = sm_ll_inc(&smm->ll, op->block, &ev); + r = sm_ll_inc(&smm->ll, op->b, op->e, &nr_allocations); break; case BOP_DEC: - r = sm_ll_dec(&smm->ll, op->block, &ev); + r = sm_ll_dec(&smm->ll, op->b, op->e, &nr_allocations); break; } @@ -314,7 +313,7 @@ static int sm_metadata_get_count(struct dm_space_map *sm, dm_block_t b, i = brb_next(&smm->uncommitted, i)) { struct block_op *op = smm->uncommitted.bops + i; - if (op->block != b) + if (b < op->b || b >= op->e) continue; switch (op->type) { @@ -355,7 +354,7 @@ static int sm_metadata_count_is_more_than_one(struct dm_space_map *sm, struct block_op *op = smm->uncommitted.bops + i; - if (op->block != b) + if (b < op->b || b >= op->e) continue; switch (op->type) { @@ -393,7 +392,7 @@ static int sm_metadata_set_count(struct dm_space_map *sm, dm_block_t b, uint32_t count) { int r, r2; - enum allocation_event ev; + int32_t nr_allocations; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); if (smm->recursion_count) { @@ -402,40 +401,42 @@ static int sm_metadata_set_count(struct dm_space_map *sm, dm_block_t b, } in(smm); - r = sm_ll_insert(&smm->ll, b, count, &ev); + r = sm_ll_insert(&smm->ll, b, count, &nr_allocations); r2 = out(smm); return combine_errors(r, r2); } -static int sm_metadata_inc_block(struct dm_space_map *sm, dm_block_t b) +static int sm_metadata_inc_blocks(struct dm_space_map *sm, dm_block_t b, dm_block_t e) { int r, r2 = 0; - enum allocation_event ev; + int32_t nr_allocations; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); - if (recursing(smm)) - r = add_bop(smm, BOP_INC, b); - else { + if (recursing(smm)) { + r = add_bop(smm, BOP_INC, b, e); + if (r) + return r; + } else { in(smm); - r = sm_ll_inc(&smm->ll, b, &ev); + r = sm_ll_inc(&smm->ll, b, e, &nr_allocations); r2 = out(smm); } return combine_errors(r, r2); } -static int sm_metadata_dec_block(struct dm_space_map *sm, dm_block_t b) +static int sm_metadata_dec_blocks(struct dm_space_map *sm, dm_block_t b, dm_block_t e) { int r, r2 = 0; - enum allocation_event ev; + int32_t nr_allocations; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); if (recursing(smm)) - r = add_bop(smm, BOP_DEC, b); + r = add_bop(smm, BOP_DEC, b, e); else { in(smm); - r = sm_ll_dec(&smm->ll, b, &ev); + r = sm_ll_dec(&smm->ll, b, e, &nr_allocations); r2 = out(smm); } @@ -445,23 +446,31 @@ static int sm_metadata_dec_block(struct dm_space_map *sm, dm_block_t b) static int sm_metadata_new_block_(struct dm_space_map *sm, dm_block_t *b) { int r, r2 = 0; - enum allocation_event ev; + int32_t nr_allocations; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); /* * Any block we allocate has to be free in both the old and current ll. */ r = sm_ll_find_common_free_block(&smm->old_ll, &smm->ll, smm->begin, smm->ll.nr_blocks, b); + if (r == -ENOSPC) { + /* + * There's no free block between smm->begin and the end of the metadata device. + * We search before smm->begin in case something has been freed. + */ + r = sm_ll_find_common_free_block(&smm->old_ll, &smm->ll, 0, smm->begin, b); + } + if (r) return r; smm->begin = *b + 1; if (recursing(smm)) - r = add_bop(smm, BOP_INC, *b); + r = add_bop(smm, BOP_INC, *b, *b + 1); else { in(smm); - r = sm_ll_inc(&smm->ll, *b, &ev); + r = sm_ll_inc(&smm->ll, *b, *b + 1, &nr_allocations); r2 = out(smm); } @@ -503,7 +512,6 @@ static int sm_metadata_commit(struct dm_space_map *sm) return r; memcpy(&smm->old_ll, &smm->ll, sizeof(smm->old_ll)); - smm->begin = 0; smm->allocated_this_transaction = 0; return 0; @@ -556,8 +564,8 @@ static const struct dm_space_map ops = { .get_count = sm_metadata_get_count, .count_is_more_than_one = sm_metadata_count_is_more_than_one, .set_count = sm_metadata_set_count, - .inc_block = sm_metadata_inc_block, - .dec_block = sm_metadata_dec_block, + .inc_blocks = sm_metadata_inc_blocks, + .dec_blocks = sm_metadata_dec_blocks, .new_block = sm_metadata_new_block, .commit = sm_metadata_commit, .root_size = sm_metadata_root_size, @@ -641,18 +649,28 @@ static int sm_bootstrap_new_block(struct dm_space_map *sm, dm_block_t *b) return 0; } -static int sm_bootstrap_inc_block(struct dm_space_map *sm, dm_block_t b) +static int sm_bootstrap_inc_blocks(struct dm_space_map *sm, dm_block_t b, dm_block_t e) { + int r; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); - return add_bop(smm, BOP_INC, b); + r = add_bop(smm, BOP_INC, b, e); + if (r) + return r; + + return 0; } -static int sm_bootstrap_dec_block(struct dm_space_map *sm, dm_block_t b) +static int sm_bootstrap_dec_blocks(struct dm_space_map *sm, dm_block_t b, dm_block_t e) { + int r; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); - return add_bop(smm, BOP_DEC, b); + r = add_bop(smm, BOP_DEC, b, e); + if (r) + return r; + + return 0; } static int sm_bootstrap_commit(struct dm_space_map *sm) @@ -683,8 +701,8 @@ static const struct dm_space_map bootstrap_ops = { .get_count = sm_bootstrap_get_count, .count_is_more_than_one = sm_bootstrap_count_is_more_than_one, .set_count = sm_bootstrap_set_count, - .inc_block = sm_bootstrap_inc_block, - .dec_block = sm_bootstrap_dec_block, + .inc_blocks = sm_bootstrap_inc_blocks, + .dec_blocks = sm_bootstrap_dec_blocks, .new_block = sm_bootstrap_new_block, .commit = sm_bootstrap_commit, .root_size = sm_bootstrap_root_size, @@ -696,7 +714,7 @@ static const struct dm_space_map bootstrap_ops = { static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks) { - int r, i; + int r; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); dm_block_t old_len = smm->ll.nr_blocks; @@ -718,9 +736,7 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks) * allocate any new blocks. */ do { - for (i = old_len; !r && i < smm->begin; i++) - r = add_bop(smm, BOP_INC, i); - + r = add_bop(smm, BOP_INC, old_len, smm->begin); if (r) goto out; @@ -767,7 +783,6 @@ int dm_sm_metadata_create(struct dm_space_map *sm, dm_block_t superblock) { int r; - dm_block_t i; struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); smm->begin = superblock + 1; @@ -792,9 +807,7 @@ int dm_sm_metadata_create(struct dm_space_map *sm, * Now we need to update the newly created data structures with the * allocated blocks that they were built from. */ - for (i = superblock; !r && i < smm->begin; i++) - r = add_bop(smm, BOP_INC, i); - + r = add_bop(smm, BOP_INC, superblock, smm->begin); if (r) return r; diff --git a/drivers/md/persistent-data/dm-space-map.h b/drivers/md/persistent-data/dm-space-map.h index 3e6d1153b7c4..a015cd11f6e9 100644 --- a/drivers/md/persistent-data/dm-space-map.h +++ b/drivers/md/persistent-data/dm-space-map.h @@ -46,8 +46,8 @@ struct dm_space_map { int (*commit)(struct dm_space_map *sm); - int (*inc_block)(struct dm_space_map *sm, dm_block_t b); - int (*dec_block)(struct dm_space_map *sm, dm_block_t b); + int (*inc_blocks)(struct dm_space_map *sm, dm_block_t b, dm_block_t e); + int (*dec_blocks)(struct dm_space_map *sm, dm_block_t b, dm_block_t e); /* * new_block will increment the returned block. @@ -117,14 +117,24 @@ static inline int dm_sm_commit(struct dm_space_map *sm) return sm->commit(sm); } +static inline int dm_sm_inc_blocks(struct dm_space_map *sm, dm_block_t b, dm_block_t e) +{ + return sm->inc_blocks(sm, b, e); +} + static inline int dm_sm_inc_block(struct dm_space_map *sm, dm_block_t b) { - return sm->inc_block(sm, b); + return dm_sm_inc_blocks(sm, b, b + 1); +} + +static inline int dm_sm_dec_blocks(struct dm_space_map *sm, dm_block_t b, dm_block_t e) +{ + return sm->dec_blocks(sm, b, e); } static inline int dm_sm_dec_block(struct dm_space_map *sm, dm_block_t b) { - return sm->dec_block(sm, b); + return dm_sm_dec_blocks(sm, b, b + 1); } static inline int dm_sm_new_block(struct dm_space_map *sm, dm_block_t *b) diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c index abe2c5dd0993..16643fc974e8 100644 --- a/drivers/md/persistent-data/dm-transaction-manager.c +++ b/drivers/md/persistent-data/dm-transaction-manager.c @@ -359,6 +359,17 @@ void dm_tm_inc(struct dm_transaction_manager *tm, dm_block_t b) } EXPORT_SYMBOL_GPL(dm_tm_inc); +void dm_tm_inc_range(struct dm_transaction_manager *tm, dm_block_t b, dm_block_t e) +{ + /* + * The non-blocking clone doesn't support this. + */ + BUG_ON(tm->is_clone); + + dm_sm_inc_blocks(tm->sm, b, e); +} +EXPORT_SYMBOL_GPL(dm_tm_inc_range); + void dm_tm_dec(struct dm_transaction_manager *tm, dm_block_t b) { /* @@ -370,6 +381,47 @@ void dm_tm_dec(struct dm_transaction_manager *tm, dm_block_t b) } EXPORT_SYMBOL_GPL(dm_tm_dec); +void dm_tm_dec_range(struct dm_transaction_manager *tm, dm_block_t b, dm_block_t e) +{ + /* + * The non-blocking clone doesn't support this. + */ + BUG_ON(tm->is_clone); + + dm_sm_dec_blocks(tm->sm, b, e); +} +EXPORT_SYMBOL_GPL(dm_tm_dec_range); + +void dm_tm_with_runs(struct dm_transaction_manager *tm, + const __le64 *value_le, unsigned count, dm_tm_run_fn fn) +{ + uint64_t b, begin, end; + bool in_run = false; + unsigned i; + + for (i = 0; i < count; i++, value_le++) { + b = le64_to_cpu(*value_le); + + if (in_run) { + if (b == end) + end++; + else { + fn(tm, begin, end); + begin = b; + end = b + 1; + } + } else { + in_run = true; + begin = b; + end = b + 1; + } + } + + if (in_run) + fn(tm, begin, end); +} +EXPORT_SYMBOL_GPL(dm_tm_with_runs); + int dm_tm_ref(struct dm_transaction_manager *tm, dm_block_t b, uint32_t *result) { @@ -379,6 +431,15 @@ int dm_tm_ref(struct dm_transaction_manager *tm, dm_block_t b, return dm_sm_get_count(tm->sm, b, result); } +int dm_tm_block_is_shared(struct dm_transaction_manager *tm, dm_block_t b, + int *result) +{ + if (tm->is_clone) + return -EWOULDBLOCK; + + return dm_sm_count_is_more_than_one(tm->sm, b, result); +} + struct dm_block_manager *dm_tm_get_bm(struct dm_transaction_manager *tm) { return tm->bm; diff --git a/drivers/md/persistent-data/dm-transaction-manager.h b/drivers/md/persistent-data/dm-transaction-manager.h index f3a18be68f30..906c02ed0365 100644 --- a/drivers/md/persistent-data/dm-transaction-manager.h +++ b/drivers/md/persistent-data/dm-transaction-manager.h @@ -100,11 +100,27 @@ void dm_tm_unlock(struct dm_transaction_manager *tm, struct dm_block *b); * Functions for altering the reference count of a block directly. */ void dm_tm_inc(struct dm_transaction_manager *tm, dm_block_t b); - +void dm_tm_inc_range(struct dm_transaction_manager *tm, dm_block_t b, dm_block_t e); void dm_tm_dec(struct dm_transaction_manager *tm, dm_block_t b); +void dm_tm_dec_range(struct dm_transaction_manager *tm, dm_block_t b, dm_block_t e); -int dm_tm_ref(struct dm_transaction_manager *tm, dm_block_t b, - uint32_t *result); +/* + * Builds up runs of adjacent blocks, and then calls the given fn + * (typically dm_tm_inc/dec). Very useful when you have to perform + * the same tm operation on all values in a btree leaf. + */ +typedef void (*dm_tm_run_fn)(struct dm_transaction_manager *, dm_block_t, dm_block_t); +void dm_tm_with_runs(struct dm_transaction_manager *tm, + const __le64 *value_le, unsigned count, dm_tm_run_fn fn); + +int dm_tm_ref(struct dm_transaction_manager *tm, dm_block_t b, uint32_t *result); + +/* + * Finds out if a given block is shared (ie. has a reference count higher + * than one). + */ +int dm_tm_block_is_shared(struct dm_transaction_manager *tm, dm_block_t b, + int *result); struct dm_block_manager *dm_tm_get_bm(struct dm_transaction_manager *tm); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index e5d7411cba9b..62c8b6adac70 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -546,6 +546,9 @@ static bool raid0_make_request(struct mddev *mddev, struct bio *bio) bio = split; } + if (bio->bi_pool != &mddev->bio_set) + md_account_bio(mddev, &bio); + orig_sector = sector; zone = find_zone(mddev->private, §or); switch (conf->layout) { diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index ced076ba560e..51f2547c2007 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -300,6 +300,8 @@ static void call_bio_endio(struct r1bio *r1_bio) if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) bio->bi_status = BLK_STS_IOERR; + if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue)) + bio_end_io_acct(bio, r1_bio->start_time); bio_endio(bio); } @@ -1210,7 +1212,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, const unsigned long do_sync = (bio->bi_opf & REQ_SYNC); int max_sectors; int rdisk; - bool print_msg = !!r1_bio; + bool r1bio_existed = !!r1_bio; char b[BDEVNAME_SIZE]; /* @@ -1220,7 +1222,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, */ gfp_t gfp = r1_bio ? (GFP_NOIO | __GFP_HIGH) : GFP_NOIO; - if (print_msg) { + if (r1bio_existed) { /* Need to get the block device name carefully */ struct md_rdev *rdev; rcu_read_lock(); @@ -1252,7 +1254,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, if (rdisk < 0) { /* couldn't find anywhere to read from */ - if (print_msg) { + if (r1bio_existed) { pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n", mdname(mddev), b, @@ -1263,7 +1265,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, } mirror = conf->mirrors + rdisk; - if (print_msg) + if (r1bio_existed) pr_info_ratelimited("md/raid1:%s: redirecting sector %llu to other mirror: %s\n", mdname(mddev), (unsigned long long)r1_bio->sector, @@ -1292,6 +1294,9 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, r1_bio->read_disk = rdisk; + if (!r1bio_existed && blk_queue_io_stat(bio->bi_bdev->bd_disk->queue)) + r1_bio->start_time = bio_start_io_acct(bio); + read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set); r1_bio->bios[rdisk] = read_bio; @@ -1461,6 +1466,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, r1_bio->sectors = max_sectors; } + if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue)) + r1_bio->start_time = bio_start_io_acct(bio); atomic_set(&r1_bio->remaining, 1); atomic_set(&r1_bio->behind_remaining, 0); diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index b7eb09e8c025..ccf10e59b116 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -158,6 +158,7 @@ struct r1bio { sector_t sector; int sectors; unsigned long state; + unsigned long start_time; struct mddev *mddev; /* * original bio going to /dev/mdx diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 13f5e6b2a73d..16977e8e075d 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -297,6 +297,8 @@ static void raid_end_bio_io(struct r10bio *r10_bio) if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) bio->bi_status = BLK_STS_IOERR; + if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue)) + bio_end_io_acct(bio, r10_bio->start_time); bio_endio(bio); /* * Wake up any possible resync thread that waits for the device @@ -1184,6 +1186,8 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, } slot = r10_bio->read_slot; + if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue)) + r10_bio->start_time = bio_start_io_acct(bio); read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set); r10_bio->devs[slot].bio = read_bio; @@ -1483,6 +1487,8 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, r10_bio->master_bio = bio; } + if (blk_queue_io_stat(bio->bi_bdev->bd_disk->queue)) + r10_bio->start_time = bio_start_io_acct(bio); atomic_set(&r10_bio->remaining, 1); md_bitmap_startwrite(mddev->bitmap, r10_bio->sector, r10_bio->sectors, 0); diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 1461fd55311b..c34bb196790e 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -124,6 +124,7 @@ struct r10bio { sector_t sector; /* virtual sector number */ int sectors; unsigned long state; + unsigned long start_time; struct mddev *mddev; /* * original bio going to /dev/mdx diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 7d4ff8a5c55e..b8436e4930ed 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5362,11 +5362,13 @@ static struct bio *remove_bio_from_retry(struct r5conf *conf, */ static void raid5_align_endio(struct bio *bi) { - struct bio* raid_bi = bi->bi_private; + struct md_io_acct *md_io_acct = bi->bi_private; + struct bio *raid_bi = md_io_acct->orig_bio; struct mddev *mddev; struct r5conf *conf; struct md_rdev *rdev; blk_status_t error = bi->bi_status; + unsigned long start_time = md_io_acct->start_time; bio_put(bi); @@ -5378,6 +5380,8 @@ static void raid5_align_endio(struct bio *bi) rdev_dec_pending(rdev, conf->mddev); if (!error) { + if (blk_queue_io_stat(raid_bi->bi_bdev->bd_disk->queue)) + bio_end_io_acct(raid_bi, start_time); bio_endio(raid_bi); if (atomic_dec_and_test(&conf->active_aligned_reads)) wake_up(&conf->wait_for_quiescent); @@ -5396,6 +5400,8 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) struct md_rdev *rdev; sector_t sector, end_sector, first_bad; int bad_sectors, dd_idx; + struct md_io_acct *md_io_acct; + bool did_inc; if (!in_chunk_boundary(mddev, raid_bio)) { pr_debug("%s: non aligned\n", __func__); @@ -5425,29 +5431,46 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) atomic_inc(&rdev->nr_pending); rcu_read_unlock(); - align_bio = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->bio_set); - bio_set_dev(align_bio, rdev->bdev); - align_bio->bi_end_io = raid5_align_endio; - align_bio->bi_private = raid_bio; - align_bio->bi_iter.bi_sector = sector; - - raid_bio->bi_next = (void *)rdev; - - if (is_badblock(rdev, sector, bio_sectors(align_bio), &first_bad, + if (is_badblock(rdev, sector, bio_sectors(raid_bio), &first_bad, &bad_sectors)) { - bio_put(align_bio); + bio_put(raid_bio); rdev_dec_pending(rdev, mddev); return 0; } + align_bio = bio_clone_fast(raid_bio, GFP_NOIO, &mddev->io_acct_set); + md_io_acct = container_of(align_bio, struct md_io_acct, bio_clone); + raid_bio->bi_next = (void *)rdev; + if (blk_queue_io_stat(raid_bio->bi_bdev->bd_disk->queue)) + md_io_acct->start_time = bio_start_io_acct(raid_bio); + md_io_acct->orig_bio = raid_bio; + + bio_set_dev(align_bio, rdev->bdev); + align_bio->bi_end_io = raid5_align_endio; + align_bio->bi_private = md_io_acct; + align_bio->bi_iter.bi_sector = sector; + /* No reshape active, so we can trust rdev->data_offset */ align_bio->bi_iter.bi_sector += rdev->data_offset; - spin_lock_irq(&conf->device_lock); - wait_event_lock_irq(conf->wait_for_quiescent, conf->quiesce == 0, - conf->device_lock); - atomic_inc(&conf->active_aligned_reads); - spin_unlock_irq(&conf->device_lock); + did_inc = false; + if (conf->quiesce == 0) { + atomic_inc(&conf->active_aligned_reads); + did_inc = true; + } + /* need a memory barrier to detect the race with raid5_quiesce() */ + if (!did_inc || smp_load_acquire(&conf->quiesce) != 0) { + /* quiesce is in progress, so we need to undo io activation and wait + * for it to finish + */ + if (did_inc && atomic_dec_and_test(&conf->active_aligned_reads)) + wake_up(&conf->wait_for_quiescent); + spin_lock_irq(&conf->device_lock); + wait_event_lock_irq(conf->wait_for_quiescent, conf->quiesce == 0, + conf->device_lock); + atomic_inc(&conf->active_aligned_reads); + spin_unlock_irq(&conf->device_lock); + } if (mddev->gendisk) trace_block_bio_remap(align_bio, disk_devt(mddev->gendisk), @@ -5796,6 +5819,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi) last_sector = bio_end_sector(bi); bi->bi_next = NULL; + md_account_bio(mddev, &bi); prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE); for (; logical_sector < last_sector; logical_sector += RAID5_STRIPE_SECTORS(conf)) { int previous; @@ -6928,7 +6952,7 @@ static struct attribute *raid5_attrs[] = { &ppl_write_hint.attr, NULL, }; -static struct attribute_group raid5_attrs_group = { +static const struct attribute_group raid5_attrs_group = { .name = NULL, .attrs = raid5_attrs, }; @@ -8334,7 +8358,10 @@ static void raid5_quiesce(struct mddev *mddev, int quiesce) * active stripes can drain */ r5c_flush_cache(conf, INT_MAX); - conf->quiesce = 2; + /* need a memory barrier to make sure read_one_chunk() sees + * quiesce started and reverts to slow (locked) path. + */ + smp_store_release(&conf->quiesce, 2); wait_event_cmd(conf->wait_for_quiescent, atomic_read(&conf->active_stripes) == 0 && atomic_read(&conf->active_aligned_reads) == 0, diff --git a/drivers/media/common/videobuf2/frame_vector.c b/drivers/media/common/videobuf2/frame_vector.c index 381158320a90..ce879f6f8f82 100644 --- a/drivers/media/common/videobuf2/frame_vector.c +++ b/drivers/media/common/videobuf2/frame_vector.c @@ -64,7 +64,7 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, do { unsigned long *nums = frame_vector_pfns(vec); - vma = find_vma_intersection(mm, start, start + 1); + vma = vma_lookup(mm, start); if (!vma) break; diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index 3fe3edd80876..afae0afe3f81 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -326,7 +326,8 @@ int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) } if (attr->query.prog_cnt != 0 && prog_ids && cnt) - ret = bpf_prog_array_copy_to_user(progs, prog_ids, cnt); + ret = bpf_prog_array_copy_to_user(progs, prog_ids, + attr->query.prog_cnt); unlock: mutex_unlock(&ir_raw_handler_lock); diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c index d971acd98236..4a4573fa7b0f 100644 --- a/drivers/memstick/core/ms_block.c +++ b/drivers/memstick/core/ms_block.c @@ -2120,21 +2120,17 @@ static int msb_init_disk(struct memstick_dev *card) if (msb->disk_id < 0) return msb->disk_id; - msb->disk = alloc_disk(0); - if (!msb->disk) { - rc = -ENOMEM; + rc = blk_mq_alloc_sq_tag_set(&msb->tag_set, &msb_mq_ops, 2, + BLK_MQ_F_SHOULD_MERGE); + if (rc) goto out_release_id; - } - msb->queue = blk_mq_init_sq_queue(&msb->tag_set, &msb_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(msb->queue)) { - rc = PTR_ERR(msb->queue); - msb->queue = NULL; - goto out_put_disk; + msb->disk = blk_mq_alloc_disk(&msb->tag_set, card); + if (IS_ERR(msb->disk)) { + rc = PTR_ERR(msb->disk); + goto out_free_tag_set; } - - msb->queue->queuedata = card; + msb->queue = msb->disk->queue; blk_queue_max_hw_sectors(msb->queue, MS_BLOCK_MAX_PAGES); blk_queue_max_segments(msb->queue, MS_BLOCK_MAX_SEGS); @@ -2145,8 +2141,6 @@ static int msb_init_disk(struct memstick_dev *card) sprintf(msb->disk->disk_name, "msblk%d", msb->disk_id); msb->disk->fops = &msb_bdops; msb->disk->private_data = msb; - msb->disk->queue = msb->queue; - msb->disk->flags |= GENHD_FL_EXT_DEVT; capacity = msb->pages_in_block * msb->logical_block_count; capacity *= (msb->page_size / 512); @@ -2166,8 +2160,8 @@ static int msb_init_disk(struct memstick_dev *card) dbg("Disk added"); return 0; -out_put_disk: - put_disk(msb->disk); +out_free_tag_set: + blk_mq_free_tag_set(&msb->tag_set); out_release_id: mutex_lock(&msb_disk_lock); idr_remove(&msb_disk_idr, msb->disk_id); diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c index cf7fe0d58ee7..22778d0e24f5 100644 --- a/drivers/memstick/core/mspro_block.c +++ b/drivers/memstick/core/mspro_block.c @@ -1205,21 +1205,17 @@ static int mspro_block_init_disk(struct memstick_dev *card) if (disk_id < 0) return disk_id; - msb->disk = alloc_disk(1 << MSPRO_BLOCK_PART_SHIFT); - if (!msb->disk) { - rc = -ENOMEM; + rc = blk_mq_alloc_sq_tag_set(&msb->tag_set, &mspro_mq_ops, 2, + BLK_MQ_F_SHOULD_MERGE); + if (rc) goto out_release_id; - } - msb->queue = blk_mq_init_sq_queue(&msb->tag_set, &mspro_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE); - if (IS_ERR(msb->queue)) { - rc = PTR_ERR(msb->queue); - msb->queue = NULL; - goto out_put_disk; + msb->disk = blk_mq_alloc_disk(&msb->tag_set, card); + if (IS_ERR(msb->disk)) { + rc = PTR_ERR(msb->disk); + goto out_free_tag_set; } - - msb->queue->queuedata = card; + msb->queue = msb->disk->queue; blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES); blk_queue_max_segments(msb->queue, MSPRO_BLOCK_MAX_SEGS); @@ -1228,10 +1224,10 @@ static int mspro_block_init_disk(struct memstick_dev *card) msb->disk->major = major; msb->disk->first_minor = disk_id << MSPRO_BLOCK_PART_SHIFT; + msb->disk->minors = 1 << MSPRO_BLOCK_PART_SHIFT; msb->disk->fops = &ms_block_bdops; msb->usage_count = 1; msb->disk->private_data = msb; - msb->disk->queue = msb->queue; sprintf(msb->disk->disk_name, "mspblk%d", disk_id); @@ -1247,8 +1243,8 @@ static int mspro_block_init_disk(struct memstick_dev *card) msb->active = 1; return 0; -out_put_disk: - put_disk(msb->disk); +out_free_tag_set: + blk_mq_free_tag_set(&msb->tag_set); out_release_id: mutex_lock(&mspro_block_disk_lock); idr_remove(&mspro_block_disk_idr, disk_id); diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 5c7f2b100191..99c4e1a80ae0 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1499,24 +1499,6 @@ config MFD_TPS65217 This driver can also be built as a module. If so, the module will be called tps65217. -config MFD_TPS68470 - bool "TI TPS68470 Power Management / LED chips" - depends on ACPI && PCI && I2C=y - depends on I2C_DESIGNWARE_PLATFORM=y - select MFD_CORE - select REGMAP_I2C - help - If you say yes here you get support for the TPS68470 series of - Power Management / LED chips. - - These include voltage regulators, LEDs and other features - that are often used in portable devices. - - This option is a bool as it provides an ACPI operation - region, which must be available before any of the devices - using this are probed. This option also configures the - designware-i2c driver to be built-in, for the same reason. - config MFD_TI_LP873X tristate "TI LP873X Power Management IC" depends on I2C diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 4f6d2b8a5f76..8b322d89a0c5 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -105,7 +105,6 @@ obj-$(CONFIG_MFD_TPS65910) += tps65910.o obj-$(CONFIG_MFD_TPS65912) += tps65912-core.o obj-$(CONFIG_MFD_TPS65912_I2C) += tps65912-i2c.o obj-$(CONFIG_MFD_TPS65912_SPI) += tps65912-spi.o -obj-$(CONFIG_MFD_TPS68470) += tps68470.o obj-$(CONFIG_MFD_TPS80031) += tps80031.o obj-$(CONFIG_MENELAUS) += menelaus.o diff --git a/drivers/mfd/ioc3.c b/drivers/mfd/ioc3.c index c73ec78f255b..99b9c113f964 100644 --- a/drivers/mfd/ioc3.c +++ b/drivers/mfd/ioc3.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/mfd/tps68470.c b/drivers/mfd/tps68470.c deleted file mode 100644 index 4a4df4ffd18c..000000000000 --- a/drivers/mfd/tps68470.c +++ /dev/null @@ -1,97 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * TPS68470 chip Parent driver - * - * Copyright (C) 2017 Intel Corporation - * - * Authors: - * Rajmohan Mani - * Tianshu Qiu - * Jian Xu Zheng - * Yuning Pu - */ - -#include -#include -#include -#include -#include -#include -#include - -static const struct mfd_cell tps68470s[] = { - { .name = "tps68470-gpio" }, - { .name = "tps68470_pmic_opregion" }, -}; - -static const struct regmap_config tps68470_regmap_config = { - .reg_bits = 8, - .val_bits = 8, - .max_register = TPS68470_REG_MAX, -}; - -static int tps68470_chip_init(struct device *dev, struct regmap *regmap) -{ - unsigned int version; - int ret; - - /* Force software reset */ - ret = regmap_write(regmap, TPS68470_REG_RESET, TPS68470_REG_RESET_MASK); - if (ret) - return ret; - - ret = regmap_read(regmap, TPS68470_REG_REVID, &version); - if (ret) { - dev_err(dev, "Failed to read revision register: %d\n", ret); - return ret; - } - - dev_info(dev, "TPS68470 REVID: 0x%x\n", version); - - return 0; -} - -static int tps68470_probe(struct i2c_client *client) -{ - struct device *dev = &client->dev; - struct regmap *regmap; - int ret; - - regmap = devm_regmap_init_i2c(client, &tps68470_regmap_config); - if (IS_ERR(regmap)) { - dev_err(dev, "devm_regmap_init_i2c Error %ld\n", - PTR_ERR(regmap)); - return PTR_ERR(regmap); - } - - i2c_set_clientdata(client, regmap); - - ret = tps68470_chip_init(dev, regmap); - if (ret < 0) { - dev_err(dev, "TPS68470 Init Error %d\n", ret); - return ret; - } - - ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_NONE, tps68470s, - ARRAY_SIZE(tps68470s), NULL, 0, NULL); - if (ret < 0) { - dev_err(dev, "devm_mfd_add_devices failed: %d\n", ret); - return ret; - } - - return 0; -} - -static const struct acpi_device_id tps68470_acpi_ids[] = { - {"INT3472"}, - {}, -}; - -static struct i2c_driver tps68470_driver = { - .driver = { - .name = "tps68470", - .acpi_match_table = tps68470_acpi_ids, - }, - .probe_new = tps68470_probe, -}; -builtin_i2c_driver(tps68470_driver); diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c index 723825524ea0..d7ef61e602ed 100644 --- a/drivers/misc/sgi-gru/grufault.c +++ b/drivers/misc/sgi-gru/grufault.c @@ -49,8 +49,8 @@ struct vm_area_struct *gru_find_vma(unsigned long vaddr) { struct vm_area_struct *vma; - vma = find_vma(current->mm, vaddr); - if (vma && vma->vm_start <= vaddr && vma->vm_ops == &gru_vm_ops) + vma = vma_lookup(current->mm, vaddr); + if (vma && vma->vm_ops == &gru_vm_ops) return vma; return NULL; } diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index fb8e12d590a1..6ce4bc57f919 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -30,11 +30,9 @@ static void blktrans_dev_release(struct kref *kref) struct mtd_blktrans_dev *dev = container_of(kref, struct mtd_blktrans_dev, ref); - dev->disk->private_data = NULL; - blk_cleanup_queue(dev->rq); + blk_cleanup_disk(dev->disk); blk_mq_free_tag_set(dev->tag_set); kfree(dev->tag_set); - put_disk(dev->disk); list_del(&dev->list); kfree(dev); } @@ -354,7 +352,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) if (new->devnum > (MINORMASK >> tr->part_bits) || (tr->part_bits && new->devnum >= 27 * 26)) { mutex_unlock(&blktrans_ref_mutex); - goto error1; + return ret; } list_add_tail(&new->list, &tr->devs); @@ -366,17 +364,29 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) if (!tr->writesect) new->readonly = 1; - /* Create gendisk */ ret = -ENOMEM; - gd = alloc_disk(1 << tr->part_bits); + new->tag_set = kzalloc(sizeof(*new->tag_set), GFP_KERNEL); + if (!new->tag_set) + goto out_list_del; - if (!gd) - goto error2; + ret = blk_mq_alloc_sq_tag_set(new->tag_set, &mtd_mq_ops, 2, + BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING); + if (ret) + goto out_kfree_tag_set; + + /* Create gendisk */ + gd = blk_mq_alloc_disk(new->tag_set, new); + if (IS_ERR(gd)) { + ret = PTR_ERR(gd); + goto out_free_tag_set; + } new->disk = gd; + new->rq = new->disk->queue; gd->private_data = new; gd->major = tr->major; gd->first_minor = (new->devnum) << tr->part_bits; + gd->minors = 1 << tr->part_bits; gd->fops = &mtd_block_ops; if (tr->part_bits) @@ -398,22 +408,9 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) spin_lock_init(&new->queue_lock); INIT_LIST_HEAD(&new->rq_list); - new->tag_set = kzalloc(sizeof(*new->tag_set), GFP_KERNEL); - if (!new->tag_set) - goto error3; - - new->rq = blk_mq_init_sq_queue(new->tag_set, &mtd_mq_ops, 2, - BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING); - if (IS_ERR(new->rq)) { - ret = PTR_ERR(new->rq); - new->rq = NULL; - goto error4; - } - if (tr->flush) blk_queue_write_cache(new->rq, true, false); - new->rq->queuedata = new; blk_queue_logical_block_size(new->rq, tr->blksize); blk_queue_flag_set(QUEUE_FLAG_NONROT, new->rq); @@ -437,13 +434,13 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) WARN_ON(ret); } return 0; -error4: + +out_free_tag_set: + blk_mq_free_tag_set(new->tag_set); +out_kfree_tag_set: kfree(new->tag_set); -error3: - put_disk(new->disk); -error2: +out_list_del: list_del(&new->list); -error1: return ret; } diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index e1a2ae21dfd3..e003b4b44ffa 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -394,28 +394,6 @@ int ubiblock_create(struct ubi_volume_info *vi) dev->vol_id = vi->vol_id; dev->leb_size = vi->usable_leb_size; - /* Initialize the gendisk of this ubiblock device */ - gd = alloc_disk(1); - if (!gd) { - pr_err("UBI: block: alloc_disk failed\n"); - ret = -ENODEV; - goto out_free_dev; - } - - gd->fops = &ubiblock_ops; - gd->major = ubiblock_major; - gd->first_minor = idr_alloc(&ubiblock_minor_idr, dev, 0, 0, GFP_KERNEL); - if (gd->first_minor < 0) { - dev_err(disk_to_dev(gd), - "block: dynamic minor allocation failed"); - ret = -ENODEV; - goto out_put_disk; - } - gd->private_data = dev; - sprintf(gd->disk_name, "ubiblock%d_%d", dev->ubi_num, dev->vol_id); - set_capacity(gd, disk_capacity); - dev->gd = gd; - dev->tag_set.ops = &ubiblock_mq_ops; dev->tag_set.queue_depth = 64; dev->tag_set.numa_node = NUMA_NO_NODE; @@ -427,19 +405,34 @@ int ubiblock_create(struct ubi_volume_info *vi) ret = blk_mq_alloc_tag_set(&dev->tag_set); if (ret) { dev_err(disk_to_dev(dev->gd), "blk_mq_alloc_tag_set failed"); - goto out_remove_minor; + goto out_free_dev;; } - dev->rq = blk_mq_init_queue(&dev->tag_set); - if (IS_ERR(dev->rq)) { - dev_err(disk_to_dev(gd), "blk_mq_init_queue failed"); - ret = PTR_ERR(dev->rq); + + /* Initialize the gendisk of this ubiblock device */ + gd = blk_mq_alloc_disk(&dev->tag_set, dev); + if (IS_ERR(gd)) { + ret = PTR_ERR(gd); goto out_free_tags; } - blk_queue_max_segments(dev->rq, UBI_MAX_SG_COUNT); - dev->rq->queuedata = dev; - dev->gd->queue = dev->rq; + gd->fops = &ubiblock_ops; + gd->major = ubiblock_major; + gd->minors = 1; + gd->first_minor = idr_alloc(&ubiblock_minor_idr, dev, 0, 0, GFP_KERNEL); + if (gd->first_minor < 0) { + dev_err(disk_to_dev(gd), + "block: dynamic minor allocation failed"); + ret = -ENODEV; + goto out_cleanup_disk; + } + gd->private_data = dev; + sprintf(gd->disk_name, "ubiblock%d_%d", dev->ubi_num, dev->vol_id); + set_capacity(gd, disk_capacity); + dev->gd = gd; + + dev->rq = gd->queue; + blk_queue_max_segments(dev->rq, UBI_MAX_SG_COUNT); /* * Create one workqueue per volume (per registered block device). @@ -448,7 +441,7 @@ int ubiblock_create(struct ubi_volume_info *vi) dev->wq = alloc_workqueue("%s", 0, 0, gd->disk_name); if (!dev->wq) { ret = -ENOMEM; - goto out_free_queue; + goto out_remove_minor; } list_add_tail(&dev->list, &ubiblock_devices); @@ -460,14 +453,12 @@ int ubiblock_create(struct ubi_volume_info *vi) mutex_unlock(&devices_mutex); return 0; -out_free_queue: - blk_cleanup_queue(dev->rq); -out_free_tags: - blk_mq_free_tag_set(&dev->tag_set); out_remove_minor: idr_remove(&ubiblock_minor_idr, gd->first_minor); -out_put_disk: - put_disk(dev->gd); +out_cleanup_disk: + blk_cleanup_disk(dev->gd); +out_free_tags: + blk_mq_free_tag_set(&dev->tag_set); out_free_dev: kfree(dev); out_unlock: @@ -483,11 +474,10 @@ static void ubiblock_cleanup(struct ubiblock *dev) /* Flush pending work */ destroy_workqueue(dev->wq); /* Finally destroy the blk queue */ - blk_cleanup_queue(dev->rq); - blk_mq_free_tag_set(&dev->tag_set); dev_info(disk_to_dev(dev->gd), "released"); + blk_cleanup_disk(dev->gd); + blk_mq_free_tag_set(&dev->tag_set); idr_remove(&ubiblock_minor_idr, dev->gd->first_minor); - put_disk(dev->gd); } int ubiblock_remove(struct ubi_volume_info *vi) diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 74dc8e249faa..6977f8248df7 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -262,17 +262,17 @@ config GENEVE will be called geneve. config BAREUDP - tristate "Bare UDP Encapsulation" - depends on INET - depends on IPV6 || !IPV6 - select NET_UDP_TUNNEL - select GRO_CELLS - help - This adds a bare UDP tunnel module for tunnelling different - kinds of traffic like MPLS, IP, etc. inside a UDP tunnel. + tristate "Bare UDP Encapsulation" + depends on INET + depends on IPV6 || !IPV6 + select NET_UDP_TUNNEL + select GRO_CELLS + help + This adds a bare UDP tunnel module for tunnelling different + kinds of traffic like MPLS, IP, etc. inside a UDP tunnel. - To compile this driver as a module, choose M here: the module - will be called bareudp. + To compile this driver as a module, choose M here: the module + will be called bareudp. config GTP tristate "GPRS Tunneling Protocol datapath (GTP-U)" @@ -431,6 +431,7 @@ config VSOCKMON config MHI_NET tristate "MHI network driver" depends on MHI_BUS + select WWAN help This is the network driver for MHI bus. It can be used with QCOM based WWAN modems (like SDX55). Say Y or M. diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c index 6b12ce822e51..f0695d68c47e 100644 --- a/drivers/net/appletalk/cops.c +++ b/drivers/net/appletalk/cops.c @@ -609,12 +609,12 @@ static int cops_nodeid (struct net_device *dev, int nodeid) if(lp->board == DAYNA) { - /* Empty any pending adapter responses. */ + /* Empty any pending adapter responses. */ while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0) { outb(0, ioaddr+COPS_CLEAR_INT); /* Clear interrupts. */ - if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST) - cops_rx(dev); /* Kick any packets waiting. */ + if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST) + cops_rx(dev); /* Kick any packets waiting. */ schedule(); } @@ -630,13 +630,13 @@ static int cops_nodeid (struct net_device *dev, int nodeid) while(inb(ioaddr+TANG_CARD_STATUS)&TANG_RX_READY) { outb(0, ioaddr+COPS_CLEAR_INT); /* Clear interrupt. */ - cops_rx(dev); /* Kick out packets waiting. */ + cops_rx(dev); /* Kick out packets waiting. */ schedule(); } /* Not sure what Tangent does if nodeid picked is used. */ if(nodeid == 0) /* Seed. */ - nodeid = jiffies&0xFF; /* Get a random try */ + nodeid = jiffies&0xFF; /* Get a random try */ outb(2, ioaddr); /* Command length LSB */ outb(0, ioaddr); /* Command length MSB */ outb(LAP_INIT, ioaddr); /* Send LAP_INIT byte */ @@ -651,13 +651,13 @@ static int cops_nodeid (struct net_device *dev, int nodeid) if(lp->board == DAYNA) { - if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST) - cops_rx(dev); /* Grab the nodeid put in lp->node_acquire. */ + if((inb(ioaddr+DAYNA_CARD_STATUS)&0x03)==DAYNA_RX_REQUEST) + cops_rx(dev); /* Grab the nodeid put in lp->node_acquire. */ } if(lp->board == TANGENT) { if(inb(ioaddr+TANG_CARD_STATUS)&TANG_RX_READY) - cops_rx(dev); /* Grab the nodeid put in lp->node_acquire. */ + cops_rx(dev); /* Grab the nodeid put in lp->node_acquire. */ } schedule(); } @@ -719,16 +719,16 @@ static irqreturn_t cops_interrupt(int irq, void *dev_id) { do { outb(0, ioaddr + COPS_CLEAR_INT); - status=inb(ioaddr+DAYNA_CARD_STATUS); - if((status&0x03)==DAYNA_RX_REQUEST) - cops_rx(dev); - netif_wake_queue(dev); + status=inb(ioaddr+DAYNA_CARD_STATUS); + if((status&0x03)==DAYNA_RX_REQUEST) + cops_rx(dev); + netif_wake_queue(dev); } while(++boguscount < 20); } else { do { - status=inb(ioaddr+TANG_CARD_STATUS); + status=inb(ioaddr+TANG_CARD_STATUS); if(status & TANG_RX_READY) cops_rx(dev); if(status & TANG_TX_READY) @@ -855,7 +855,7 @@ static void cops_timeout(struct net_device *dev, unsigned int txqueue) if(lp->board==TANGENT) { if((inb(ioaddr+TANG_CARD_STATUS)&TANG_TX_READY)==0) - printk(KERN_WARNING "%s: No TX complete interrupt.\n", dev->name); + printk(KERN_WARNING "%s: No TX complete interrupt.\n", dev->name); } printk(KERN_WARNING "%s: Transmit timed out.\n", dev->name); cops_jumpstart(dev); /* Restart the card. */ @@ -897,7 +897,7 @@ static netdev_tx_t cops_send_packet(struct sk_buff *skb, outb(LAP_WRITE, ioaddr); if(lp->board == DAYNA) /* Check the transmit buffer again. */ - while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0); + while((inb(ioaddr+DAYNA_CARD_STATUS)&DAYNA_TX_READY)==0); outsb(ioaddr, skb->data, skb->len); /* Send out the data. */ diff --git a/drivers/net/appletalk/ltpc.c b/drivers/net/appletalk/ltpc.c index c6f73aa3700c..69c270885ff0 100644 --- a/drivers/net/appletalk/ltpc.c +++ b/drivers/net/appletalk/ltpc.c @@ -584,11 +584,13 @@ loop: printk("%02x ",ltdmacbuf[i]); printk("\n"); } + handlecommand(dev); - if(0xfa==inb_p(base+6)) { - /* we timed out, so return */ - goto done; - } + + if (0xfa == inb_p(base + 6)) { + /* we timed out, so return */ + goto done; + } } else { /* we don't seem to have a command */ if (!mboxinuse[0]) { @@ -935,10 +937,10 @@ static netdev_tx_t ltpc_xmit(struct sk_buff *skb, struct net_device *dev) static int __init ltpc_probe_dma(int base, int dma) { int want = (dma == 3) ? 2 : (dma == 1) ? 1 : 3; - unsigned long timeout; - unsigned long f; + unsigned long timeout; + unsigned long f; - if (want & 1) { + if (want & 1) { if (request_dma(1,"ltpc")) { want &= ~1; } else { diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index edfad93e7b68..a7ee0af1af90 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -133,6 +133,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) skb->dev = bareudp->dev; oiph = skb_network_header(skb); skb_reset_network_header(skb); + skb_reset_mac_header(skb); if (!IS_ENABLED(CONFIG_IPV6) || family == AF_INET) err = IP_ECN_decapsulate(oiph, skb); diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 3455f2cc13f2..22e5632089ac 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -104,6 +104,7 @@ static void __tlb_clear_slave(struct bonding *bond, struct slave *slave, index = SLAVE_TLB_INFO(slave).head; while (index != TLB_NULL_INDEX) { u32 next_index = tx_hash_table[index].next; + tlb_init_table_entry(&tx_hash_table[index], save_load); index = next_index; } @@ -228,7 +229,7 @@ static struct slave *tlb_choose_channel(struct bonding *bond, u32 hash_index, { struct slave *tx_slave; - /* We don't need to disable softirq here, becase + /* We don't need to disable softirq here, because * tlb_choose_channel() is only called by bond_alb_xmit() * which already has softirq disabled. */ @@ -608,7 +609,7 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, client_info->ip_src = arp->ip_src; client_info->ip_dst = arp->ip_dst; - /* arp->mac_dst is broadcast for arp reqeusts. + /* arp->mac_dst is broadcast for arp requests. * will be updated with clients actual unicast mac address * upon receiving an arp reply. */ @@ -628,6 +629,7 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, if (!client_info->assigned) { u32 prev_tbl_head = bond_info->rx_hashtbl_used_head; + bond_info->rx_hashtbl_used_head = hash_index; client_info->used_next = prev_tbl_head; if (prev_tbl_head != RLB_NULL_INDEX) { @@ -830,9 +832,10 @@ static void rlb_purge_src_ip(struct bonding *bond, struct arp_pkt *arp) while (index != RLB_NULL_INDEX) { struct rlb_client_info *entry = &(bond_info->rx_hashtbl[index]); u32 next_index = entry->src_next; + if (entry->ip_src == arp->ip_src && !ether_addr_equal_64bits(arp->mac_src, entry->mac_src)) - rlb_delete_table_entry(bond, index); + rlb_delete_table_entry(bond, index); index = next_index; } spin_unlock_bh(&bond->mode_lock); @@ -1268,7 +1271,7 @@ unwind: return res; } -/************************ exported alb funcions ************************/ +/************************ exported alb functions ************************/ int bond_alb_initialize(struct bonding *bond, int rlb_enabled) { @@ -1547,7 +1550,7 @@ void bond_alb_monitor(struct work_struct *work) bond_for_each_slave_rcu(bond, slave, iter) { /* If updating current_active, use all currently - * user mac addreses (!strict_match). Otherwise, only + * user mac addresses (!strict_match). Otherwise, only * use mac of the slave device. * In RLB mode, we always use strict matches. */ diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index f3f86ef68ae0..4f9b4a18c74c 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -88,9 +88,8 @@ void bond_create_debugfs(void) { bonding_debug_root = debugfs_create_dir("bonding", NULL); - if (!bonding_debug_root) { + if (!bonding_debug_root) pr_warn("Warning: Cannot create bonding directory in debugfs\n"); - } } void bond_destroy_debugfs(void) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index c5a646d06102..0ff7567bd04f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -620,7 +620,7 @@ static int bond_check_dev_link(struct bonding *bond, */ /* Yes, the mii is overlaid on the ifreq.ifr_ifru */ - strncpy(ifr.ifr_name, slave_dev->name, IFNAMSIZ); + strscpy_pad(ifr.ifr_name, slave_dev->name, IFNAMSIZ); mii = if_mii(&ifr); if (ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) { mii->reg_num = MII_BMSR; @@ -1013,9 +1013,8 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) if (bond_is_lb(bond)) bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP); } else { - if (bond_uses_primary(bond)) { + if (bond_uses_primary(bond)) slave_info(bond->dev, new_active->dev, "making interface the new active one\n"); - } } } @@ -1601,6 +1600,14 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, int link_reporting; int res = 0, i; + if (slave_dev->flags & IFF_MASTER && + !netif_is_bond_master(slave_dev)) { + NL_SET_ERR_MSG(extack, "Device with IFF_MASTER cannot be enslaved"); + netdev_err(bond_dev, + "Error: Device with IFF_MASTER cannot be enslaved\n"); + return -EPERM; + } + if (!bond->params.use_carrier && slave_dev->ethtool_ops->get_link == NULL && slave_ops->ndo_do_ioctl == NULL) { @@ -2272,6 +2279,7 @@ static int bond_release_and_destroy(struct net_device *bond_dev, static void bond_info_query(struct net_device *bond_dev, struct ifbond *info) { struct bonding *bond = netdev_priv(bond_dev); + bond_fill_ifbond(bond, info); } @@ -4202,16 +4210,16 @@ static u32 bond_rr_gen_slave_id(struct bonding *bond) slave_id = prandom_u32(); break; case 1: - slave_id = bond->rr_tx_counter; + slave_id = this_cpu_inc_return(*bond->rr_tx_counter); break; default: reciprocal_packets_per_slave = bond->params.reciprocal_packets_per_slave; - slave_id = reciprocal_divide(bond->rr_tx_counter, + slave_id = this_cpu_inc_return(*bond->rr_tx_counter); + slave_id = reciprocal_divide(slave_id, reciprocal_packets_per_slave); break; } - bond->rr_tx_counter++; return slave_id; } @@ -4849,8 +4857,12 @@ static const struct device_type bond_type = { static void bond_destructor(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + if (bond->wq) destroy_workqueue(bond->wq); + + if (bond->rr_tx_counter) + free_percpu(bond->rr_tx_counter); } void bond_setup(struct net_device *bond_dev) @@ -5329,10 +5341,8 @@ static int bond_check_params(struct bond_params *params) (struct reciprocal_value) { 0 }; } - if (primary) { - strncpy(params->primary, primary, IFNAMSIZ); - params->primary[IFNAMSIZ - 1] = 0; - } + if (primary) + strscpy_pad(params->primary, primary, sizeof(params->primary)); memcpy(params->arp_targets, arp_target, sizeof(arp_target)); @@ -5351,6 +5361,15 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; + if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN) { + bond->rr_tx_counter = alloc_percpu(u32); + if (!bond->rr_tx_counter) { + destroy_workqueue(bond->wq); + bond->wq = NULL; + return -ENOMEM; + } + } + spin_lock_init(&bond->stats_lock); netdev_lockdep_set_classes(bond_dev); diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index f0f9138e967f..0561ece1ba45 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -598,7 +598,7 @@ static int bond_fill_info(struct sk_buff *skb, goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_RESEND_IGMP, - bond->params.resend_igmp)) + bond->params.resend_igmp)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_NUM_PEER_NOTIF, diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index c9d3604ae129..0cf25de6f46d 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -705,7 +705,7 @@ out: int __bond_opt_set_notify(struct bonding *bond, unsigned int option, struct bond_opt_value *val) { - int ret = -ENOENT; + int ret; ASSERT_RTNL(); @@ -1206,8 +1206,7 @@ static int bond_option_primary_set(struct bonding *bond, RCU_INIT_POINTER(bond->primary_slave, NULL); bond_select_active_slave(bond); } - strncpy(bond->params.primary, primary, IFNAMSIZ); - bond->params.primary[IFNAMSIZ - 1] = 0; + strscpy_pad(bond->params.primary, primary, IFNAMSIZ); netdev_dbg(bond->dev, "Recording %s as primary, but it has not been enslaved yet\n", primary); diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 56d34be5e797..0fb1da361bb1 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -112,6 +112,7 @@ static void bond_info_show_master(struct seq_file *seq) /* ARP information */ if (bond->params.arp_interval > 0) { int printed = 0; + seq_printf(seq, "ARP Polling Interval (ms): %d\n", bond->params.arp_interval); diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 2d615a93685e..5f9e9a240226 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -385,6 +385,7 @@ static ssize_t bonding_show_num_peer_notif(struct device *d, char *buf) { struct bonding *bond = to_bond(d); + return sprintf(buf, "%d\n", bond->params.num_peer_notif); } static DEVICE_ATTR(num_grat_arp, 0644, @@ -496,6 +497,7 @@ static ssize_t bonding_show_ad_aggregator(struct device *d, if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info ad_info; + count = sprintf(buf, "%d\n", bond_3ad_get_active_agg_info(bond, &ad_info) ? 0 : ad_info.aggregator_id); @@ -516,6 +518,7 @@ static ssize_t bonding_show_ad_num_ports(struct device *d, if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info ad_info; + count = sprintf(buf, "%d\n", bond_3ad_get_active_agg_info(bond, &ad_info) ? 0 : ad_info.ports); @@ -536,6 +539,7 @@ static ssize_t bonding_show_ad_actor_key(struct device *d, if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) { struct ad_info ad_info; + count = sprintf(buf, "%d\n", bond_3ad_get_active_agg_info(bond, &ad_info) ? 0 : ad_info.actor_key); @@ -556,6 +560,7 @@ static ssize_t bonding_show_ad_partner_key(struct device *d, if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) { struct ad_info ad_info; + count = sprintf(buf, "%d\n", bond_3ad_get_active_agg_info(bond, &ad_info) ? 0 : ad_info.partner_key); @@ -576,6 +581,7 @@ static ssize_t bonding_show_ad_partner_mac(struct device *d, if (BOND_MODE(bond) == BOND_MODE_8023AD && capable(CAP_NET_ADMIN)) { struct ad_info ad_info; + if (!bond_3ad_get_active_agg_info(bond, &ad_info)) count = sprintf(buf, "%pM\n", ad_info.partner_system); } @@ -660,6 +666,7 @@ static ssize_t bonding_show_tlb_dynamic_lb(struct device *d, char *buf) { struct bonding *bond = to_bond(d); + return sprintf(buf, "%d\n", bond->params.tlb_dynamic_lb); } static DEVICE_ATTR(tlb_dynamic_lb, 0644, diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c index 106f089eb2a8..91230894692d 100644 --- a/drivers/net/caif/caif_virtio.c +++ b/drivers/net/caif/caif_virtio.c @@ -315,7 +315,7 @@ exit: case 0: ++cfv->stats.rx_napi_complete; - /* Really out of patckets? (stolen from virtio_net)*/ + /* Really out of packets? (stolen from virtio_net)*/ napi_complete(napi); if (unlikely(!vringh_notify_enable_kern(cfv->vr_rx)) && napi_schedule_prep(napi)) { @@ -463,7 +463,7 @@ static int cfv_netdev_close(struct net_device *netdev) vringh_notify_disable_kern(cfv->vr_rx); napi_disable(&cfv->napi); - /* Release any TX buffers on both used and avilable rings */ + /* Release any TX buffers on both used and available rings */ cfv_release_used_buf(cfv->vq_tx); spin_lock_irqsave(&cfv->tx_lock, flags); while ((buf_info = virtqueue_detach_unused_buf(cfv->vq_tx))) @@ -497,7 +497,7 @@ static struct buf_info *cfv_alloc_and_copy_to_shm(struct cfv_info *cfv, if (unlikely(!buf_info)) goto err; - /* Make the IP header aligned in tbe buffer */ + /* Make the IP header aligned in the buffer */ hdr_ofs = cfv->tx_hr + info->hdr_len; pad_len = hdr_ofs & (IP_HDR_ALIGN - 1); buf_info->size = cfv->tx_hr + skb->len + cfv->tx_tr + pad_len; diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 9ad9b39f480e..04d0bb3ffe89 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -169,7 +169,7 @@ static const struct can_bittiming_const at91_bittiming_const = { }; #define AT91_IS(_model) \ -static inline int at91_is_sam##_model(const struct at91_priv *priv) \ +static inline int __maybe_unused at91_is_sam##_model(const struct at91_priv *priv) \ { \ return priv->devtype_data.type == AT91_DEVTYPE_SAM##_model; \ } diff --git a/drivers/net/can/c_can/Makefile b/drivers/net/can/c_can/Makefile index e6a94c948531..6fa3b2b9e4b9 100644 --- a/drivers/net/can/c_can/Makefile +++ b/drivers/net/can/c_can/Makefile @@ -4,5 +4,10 @@ # obj-$(CONFIG_CAN_C_CAN) += c_can.o + +c_can-objs := +c_can-objs += c_can_ethtool.o +c_can-objs += c_can_main.o + obj-$(CONFIG_CAN_C_CAN_PLATFORM) += c_can_platform.o obj-$(CONFIG_CAN_C_CAN_PCI) += c_can_pci.o diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h index 06045f610f0e..4247ff80a29c 100644 --- a/drivers/net/can/c_can/c_can.h +++ b/drivers/net/can/c_can/c_can.h @@ -205,7 +205,6 @@ struct c_can_priv { struct c_can_raminit raminit_sys; /* RAMINIT via syscon regmap */ void (*raminit)(const struct c_can_priv *priv, bool enable); u32 comm_rcv_high; - u32 rxmasked; u32 dlc[]; }; @@ -219,4 +218,6 @@ int c_can_power_up(struct net_device *dev); int c_can_power_down(struct net_device *dev); #endif +void c_can_set_ethtool_ops(struct net_device *dev); + #endif /* C_CAN_H */ diff --git a/drivers/net/can/c_can/c_can_ethtool.c b/drivers/net/can/c_can/c_can_ethtool.c new file mode 100644 index 000000000000..cd5f07fca2a5 --- /dev/null +++ b/drivers/net/can/c_can/c_can_ethtool.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2021, Dario Binacchi + */ + +#include +#include +#include +#include +#include + +#include "c_can.h" + +static void c_can_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *info) +{ + struct c_can_priv *priv = netdev_priv(netdev); + struct platform_device *pdev = to_platform_device(priv->device); + + strscpy(info->driver, "c_can", sizeof(info->driver)); + strscpy(info->bus_info, pdev->name, sizeof(info->bus_info)); +} + +static void c_can_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct c_can_priv *priv = netdev_priv(netdev); + + ring->rx_max_pending = priv->msg_obj_num; + ring->tx_max_pending = priv->msg_obj_num; + ring->rx_pending = priv->msg_obj_rx_num; + ring->tx_pending = priv->msg_obj_tx_num; +} + +static const struct ethtool_ops c_can_ethtool_ops = { + .get_drvinfo = c_can_get_drvinfo, + .get_ringparam = c_can_get_ringparam, +}; + +void c_can_set_ethtool_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &c_can_ethtool_ops; +} diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can_main.c similarity index 99% rename from drivers/net/can/c_can/c_can.c rename to drivers/net/can/c_can/c_can_main.c index 313793f6922d..7588f70ca0fe 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can_main.c @@ -599,7 +599,6 @@ static int c_can_chip_config(struct net_device *dev) /* Clear all internal status */ atomic_set(&priv->tx_active, 0); - priv->rxmasked = 0; priv->tx_dir = 0; /* set bittiming params */ @@ -1335,6 +1334,7 @@ int register_c_can_dev(struct net_device *dev) dev->flags |= IFF_ECHO; /* we support local echo */ dev->netdev_ops = &c_can_netdev_ops; + c_can_set_ethtool_ops(dev); err = register_candev(dev); if (!err) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 3cf6de21d19c..bba2a449ac70 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -83,44 +83,25 @@ enum m_can_reg { #define MRAM_CFG_LEN 8 /* Core Release Register (CREL) */ -#define CREL_REL_SHIFT 28 -#define CREL_REL_MASK (0xF << CREL_REL_SHIFT) -#define CREL_STEP_SHIFT 24 -#define CREL_STEP_MASK (0xF << CREL_STEP_SHIFT) -#define CREL_SUBSTEP_SHIFT 20 -#define CREL_SUBSTEP_MASK (0xF << CREL_SUBSTEP_SHIFT) +#define CREL_REL_MASK GENMASK(31, 28) +#define CREL_STEP_MASK GENMASK(27, 24) +#define CREL_SUBSTEP_MASK GENMASK(23, 20) /* Data Bit Timing & Prescaler Register (DBTP) */ #define DBTP_TDC BIT(23) -#define DBTP_DBRP_SHIFT 16 -#define DBTP_DBRP_MASK (0x1f << DBTP_DBRP_SHIFT) -#define DBTP_DTSEG1_SHIFT 8 -#define DBTP_DTSEG1_MASK (0x1f << DBTP_DTSEG1_SHIFT) -#define DBTP_DTSEG2_SHIFT 4 -#define DBTP_DTSEG2_MASK (0xf << DBTP_DTSEG2_SHIFT) -#define DBTP_DSJW_SHIFT 0 -#define DBTP_DSJW_MASK (0xf << DBTP_DSJW_SHIFT) +#define DBTP_DBRP_MASK GENMASK(20, 16) +#define DBTP_DTSEG1_MASK GENMASK(12, 8) +#define DBTP_DTSEG2_MASK GENMASK(7, 4) +#define DBTP_DSJW_MASK GENMASK(3, 0) /* Transmitter Delay Compensation Register (TDCR) */ -#define TDCR_TDCO_SHIFT 8 -#define TDCR_TDCO_MASK (0x7F << TDCR_TDCO_SHIFT) -#define TDCR_TDCF_SHIFT 0 -#define TDCR_TDCF_MASK (0x7F << TDCR_TDCF_SHIFT) +#define TDCR_TDCO_MASK GENMASK(14, 8) +#define TDCR_TDCF_MASK GENMASK(6, 0) /* Test Register (TEST) */ #define TEST_LBCK BIT(4) -/* CC Control Register(CCCR) */ -#define CCCR_CMR_MASK 0x3 -#define CCCR_CMR_SHIFT 10 -#define CCCR_CMR_CANFD 0x1 -#define CCCR_CMR_CANFD_BRS 0x2 -#define CCCR_CMR_CAN 0x3 -#define CCCR_CME_MASK 0x3 -#define CCCR_CME_SHIFT 8 -#define CCCR_CME_CAN 0 -#define CCCR_CME_CANFD 0x1 -#define CCCR_CME_CANFD_BRS 0x2 +/* CC Control Register (CCCR) */ #define CCCR_TXP BIT(14) #define CCCR_TEST BIT(7) #define CCCR_DAR BIT(6) @@ -130,24 +111,31 @@ enum m_can_reg { #define CCCR_ASM BIT(2) #define CCCR_CCE BIT(1) #define CCCR_INIT BIT(0) -#define CCCR_CANFD 0x10 +/* for version 3.0.x */ +#define CCCR_CMR_MASK GENMASK(11, 10) +#define CCCR_CMR_CANFD 0x1 +#define CCCR_CMR_CANFD_BRS 0x2 +#define CCCR_CMR_CAN 0x3 +#define CCCR_CME_MASK GENMASK(9, 8) +#define CCCR_CME_CAN 0 +#define CCCR_CME_CANFD 0x1 +#define CCCR_CME_CANFD_BRS 0x2 /* for version >=3.1.x */ #define CCCR_EFBI BIT(13) #define CCCR_PXHD BIT(12) #define CCCR_BRSE BIT(9) #define CCCR_FDOE BIT(8) -/* only for version >=3.2.x */ +/* for version >=3.2.x */ #define CCCR_NISO BIT(15) +/* for version >=3.3.x */ +#define CCCR_WMM BIT(11) +#define CCCR_UTSU BIT(10) /* Nominal Bit Timing & Prescaler Register (NBTP) */ -#define NBTP_NSJW_SHIFT 25 -#define NBTP_NSJW_MASK (0x7f << NBTP_NSJW_SHIFT) -#define NBTP_NBRP_SHIFT 16 -#define NBTP_NBRP_MASK (0x1ff << NBTP_NBRP_SHIFT) -#define NBTP_NTSEG1_SHIFT 8 -#define NBTP_NTSEG1_MASK (0xff << NBTP_NTSEG1_SHIFT) -#define NBTP_NTSEG2_SHIFT 0 -#define NBTP_NTSEG2_MASK (0x7f << NBTP_NTSEG2_SHIFT) +#define NBTP_NSJW_MASK GENMASK(31, 25) +#define NBTP_NBRP_MASK GENMASK(24, 16) +#define NBTP_NTSEG1_MASK GENMASK(15, 8) +#define NBTP_NTSEG2_MASK GENMASK(6, 0) /* Timestamp Counter Configuration Register (TSCC) */ #define TSCC_TCP_MASK GENMASK(19, 16) @@ -159,20 +147,18 @@ enum m_can_reg { /* Timestamp Counter Value Register (TSCV) */ #define TSCV_TSC_MASK GENMASK(15, 0) -/* Error Counter Register(ECR) */ +/* Error Counter Register (ECR) */ #define ECR_RP BIT(15) -#define ECR_REC_SHIFT 8 -#define ECR_REC_MASK (0x7f << ECR_REC_SHIFT) -#define ECR_TEC_SHIFT 0 -#define ECR_TEC_MASK 0xff +#define ECR_REC_MASK GENMASK(14, 8) +#define ECR_TEC_MASK GENMASK(7, 0) -/* Protocol Status Register(PSR) */ +/* Protocol Status Register (PSR) */ #define PSR_BO BIT(7) #define PSR_EW BIT(6) #define PSR_EP BIT(5) -#define PSR_LEC_MASK 0x7 +#define PSR_LEC_MASK GENMASK(2, 0) -/* Interrupt Register(IR) */ +/* Interrupt Register (IR) */ #define IR_ALL_INT 0xffffffff /* Renamed bits for versions > 3.1.x */ @@ -221,6 +207,7 @@ enum m_can_reg { IR_BEC | IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | \ IR_RF1L | IR_RF0L) #define IR_ERR_ALL_30X (IR_ERR_STATE | IR_ERR_BUS_30X) + /* Interrupts for version >= 3.1.x */ #define IR_ERR_LEC_31X (IR_PED | IR_PEA) #define IR_ERR_BUS_31X (IR_ERR_LEC_31X | IR_WDI | IR_ELO | IR_BEU | \ @@ -237,58 +224,47 @@ enum m_can_reg { #define ILE_EINT0 BIT(0) /* Rx FIFO 0/1 Configuration (RXF0C/RXF1C) */ -#define RXFC_FWM_SHIFT 24 -#define RXFC_FWM_MASK (0x7f << RXFC_FWM_SHIFT) -#define RXFC_FS_SHIFT 16 -#define RXFC_FS_MASK (0x7f << RXFC_FS_SHIFT) +#define RXFC_FWM_MASK GENMASK(30, 24) +#define RXFC_FS_MASK GENMASK(22, 16) /* Rx FIFO 0/1 Status (RXF0S/RXF1S) */ #define RXFS_RFL BIT(25) #define RXFS_FF BIT(24) -#define RXFS_FPI_SHIFT 16 -#define RXFS_FPI_MASK 0x3f0000 -#define RXFS_FGI_SHIFT 8 -#define RXFS_FGI_MASK 0x3f00 -#define RXFS_FFL_MASK 0x7f +#define RXFS_FPI_MASK GENMASK(21, 16) +#define RXFS_FGI_MASK GENMASK(13, 8) +#define RXFS_FFL_MASK GENMASK(6, 0) /* Rx Buffer / FIFO Element Size Configuration (RXESC) */ -#define M_CAN_RXESC_8BYTES 0x0 -#define M_CAN_RXESC_64BYTES 0x777 +#define RXESC_RBDS_MASK GENMASK(10, 8) +#define RXESC_F1DS_MASK GENMASK(6, 4) +#define RXESC_F0DS_MASK GENMASK(2, 0) +#define RXESC_64B 0x7 -/* Tx Buffer Configuration(TXBC) */ -#define TXBC_NDTB_SHIFT 16 -#define TXBC_NDTB_MASK (0x3f << TXBC_NDTB_SHIFT) -#define TXBC_TFQS_SHIFT 24 -#define TXBC_TFQS_MASK (0x3f << TXBC_TFQS_SHIFT) +/* Tx Buffer Configuration (TXBC) */ +#define TXBC_TFQS_MASK GENMASK(29, 24) +#define TXBC_NDTB_MASK GENMASK(21, 16) /* Tx FIFO/Queue Status (TXFQS) */ #define TXFQS_TFQF BIT(21) -#define TXFQS_TFQPI_SHIFT 16 -#define TXFQS_TFQPI_MASK (0x1f << TXFQS_TFQPI_SHIFT) -#define TXFQS_TFGI_SHIFT 8 -#define TXFQS_TFGI_MASK (0x1f << TXFQS_TFGI_SHIFT) -#define TXFQS_TFFL_SHIFT 0 -#define TXFQS_TFFL_MASK (0x3f << TXFQS_TFFL_SHIFT) +#define TXFQS_TFQPI_MASK GENMASK(20, 16) +#define TXFQS_TFGI_MASK GENMASK(12, 8) +#define TXFQS_TFFL_MASK GENMASK(5, 0) -/* Tx Buffer Element Size Configuration(TXESC) */ -#define TXESC_TBDS_8BYTES 0x0 -#define TXESC_TBDS_64BYTES 0x7 +/* Tx Buffer Element Size Configuration (TXESC) */ +#define TXESC_TBDS_MASK GENMASK(2, 0) +#define TXESC_TBDS_64B 0x7 /* Tx Event FIFO Configuration (TXEFC) */ -#define TXEFC_EFS_SHIFT 16 -#define TXEFC_EFS_MASK (0x3f << TXEFC_EFS_SHIFT) +#define TXEFC_EFS_MASK GENMASK(21, 16) /* Tx Event FIFO Status (TXEFS) */ #define TXEFS_TEFL BIT(25) #define TXEFS_EFF BIT(24) -#define TXEFS_EFGI_SHIFT 8 -#define TXEFS_EFGI_MASK (0x1f << TXEFS_EFGI_SHIFT) -#define TXEFS_EFFL_SHIFT 0 -#define TXEFS_EFFL_MASK (0x3f << TXEFS_EFFL_SHIFT) +#define TXEFS_EFGI_MASK GENMASK(12, 8) +#define TXEFS_EFFL_MASK GENMASK(5, 0) /* Tx Event FIFO Acknowledge (TXEFA) */ -#define TXEFA_EFAI_SHIFT 0 -#define TXEFA_EFAI_MASK (0x1f << TXEFA_EFAI_SHIFT) +#define TXEFA_EFAI_MASK GENMASK(4, 0) /* Message RAM Configuration (in bytes) */ #define SIDF_ELEMENT_SIZE 4 @@ -324,13 +300,12 @@ enum m_can_reg { #define TX_BUF_EFC BIT(23) #define TX_BUF_FDF BIT(21) #define TX_BUF_BRS BIT(20) -#define TX_BUF_MM_SHIFT 24 -#define TX_BUF_MM_MASK (0xff << TX_BUF_MM_SHIFT) +#define TX_BUF_MM_MASK GENMASK(31, 24) +#define TX_BUF_DLC_MASK GENMASK(19, 16) /* Tx event FIFO Element */ /* E1 */ -#define TX_EVENT_MM_SHIFT TX_BUF_MM_SHIFT -#define TX_EVENT_MM_MASK (0xff << TX_EVENT_MM_SHIFT) +#define TX_EVENT_MM_MASK GENMASK(31, 24) #define TX_EVENT_TXTS_MASK GENMASK(15, 0) static inline u32 m_can_read(struct m_can_classdev *cdev, enum m_can_reg reg) @@ -449,8 +424,8 @@ static void m_can_clean(struct net_device *net) net->stats.tx_errors++; if (cdev->version > 30) - putidx = ((m_can_read(cdev, M_CAN_TXFQS) & - TXFQS_TFQPI_MASK) >> TXFQS_TFQPI_SHIFT); + putidx = FIELD_GET(TXFQS_TFQPI_MASK, + m_can_read(cdev, M_CAN_TXFQS)); can_free_echo_skb(cdev->net, putidx, NULL); cdev->tx_skb = NULL; @@ -490,7 +465,7 @@ static void m_can_read_fifo(struct net_device *dev, u32 rxfs) int i; /* calculate the fifo get index for where to read data */ - fgi = (rxfs & RXFS_FGI_MASK) >> RXFS_FGI_SHIFT; + fgi = FIELD_GET(RXFS_FGI_MASK, rxfs); dlc = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_DLC); if (dlc & RX_BUF_FDF) skb = alloc_canfd_skb(dev, &cf); @@ -663,8 +638,8 @@ static int __m_can_get_berr_counter(const struct net_device *dev, unsigned int ecr; ecr = m_can_read(cdev, M_CAN_ECR); - bec->rxerr = (ecr & ECR_REC_MASK) >> ECR_REC_SHIFT; - bec->txerr = (ecr & ECR_TEC_MASK) >> ECR_TEC_SHIFT; + bec->rxerr = FIELD_GET(ECR_REC_MASK, ecr); + bec->txerr = FIELD_GET(ECR_TEC_MASK, ecr); return 0; } @@ -1004,24 +979,23 @@ static void m_can_echo_tx_event(struct net_device *dev) m_can_txefs = m_can_read(cdev, M_CAN_TXEFS); /* Get Tx Event fifo element count */ - txe_count = (m_can_txefs & TXEFS_EFFL_MASK) >> TXEFS_EFFL_SHIFT; + txe_count = FIELD_GET(TXEFS_EFFL_MASK, m_can_txefs); /* Get and process all sent elements */ for (i = 0; i < txe_count; i++) { u32 txe, timestamp = 0; /* retrieve get index */ - fgi = (m_can_read(cdev, M_CAN_TXEFS) & TXEFS_EFGI_MASK) >> - TXEFS_EFGI_SHIFT; + fgi = FIELD_GET(TXEFS_EFGI_MASK, m_can_read(cdev, M_CAN_TXEFS)); /* get message marker, timestamp */ txe = m_can_txe_fifo_read(cdev, fgi, 4); - msg_mark = (txe & TX_EVENT_MM_MASK) >> TX_EVENT_MM_SHIFT; + msg_mark = FIELD_GET(TX_EVENT_MM_MASK, txe); timestamp = FIELD_GET(TX_EVENT_TXTS_MASK, txe); /* ack txe element */ - m_can_write(cdev, M_CAN_TXEFA, (TXEFA_EFAI_MASK & - (fgi << TXEFA_EFAI_SHIFT))); + m_can_write(cdev, M_CAN_TXEFA, FIELD_PREP(TXEFA_EFAI_MASK, + fgi)); /* update stats */ m_can_tx_update_stats(cdev, msg_mark, timestamp); @@ -1147,8 +1121,10 @@ static int m_can_set_bittiming(struct net_device *dev) sjw = bt->sjw - 1; tseg1 = bt->prop_seg + bt->phase_seg1 - 1; tseg2 = bt->phase_seg2 - 1; - reg_btp = (brp << NBTP_NBRP_SHIFT) | (sjw << NBTP_NSJW_SHIFT) | - (tseg1 << NBTP_NTSEG1_SHIFT) | (tseg2 << NBTP_NTSEG2_SHIFT); + reg_btp = FIELD_PREP(NBTP_NBRP_MASK, brp) | + FIELD_PREP(NBTP_NSJW_MASK, sjw) | + FIELD_PREP(NBTP_NTSEG1_MASK, tseg1) | + FIELD_PREP(NBTP_NTSEG2_MASK, tseg2); m_can_write(cdev, M_CAN_NBTP, reg_btp); if (cdev->can.ctrlmode & CAN_CTRLMODE_FD) { @@ -1185,13 +1161,13 @@ static int m_can_set_bittiming(struct net_device *dev) reg_btp |= DBTP_TDC; m_can_write(cdev, M_CAN_TDCR, - tdco << TDCR_TDCO_SHIFT); + FIELD_PREP(TDCR_TDCO_MASK, tdco)); } - reg_btp |= (brp << DBTP_DBRP_SHIFT) | - (sjw << DBTP_DSJW_SHIFT) | - (tseg1 << DBTP_DTSEG1_SHIFT) | - (tseg2 << DBTP_DTSEG2_SHIFT); + reg_btp = FIELD_PREP(NBTP_NBRP_MASK, brp) | + FIELD_PREP(NBTP_NSJW_MASK, sjw) | + FIELD_PREP(NBTP_NTSEG1_MASK, tseg1) | + FIELD_PREP(NBTP_NTSEG2_MASK, tseg2); m_can_write(cdev, M_CAN_DBTP, reg_btp); } @@ -1217,44 +1193,50 @@ static void m_can_chip_config(struct net_device *dev) m_can_config_endisable(cdev, true); /* RX Buffer/FIFO Element Size 64 bytes data field */ - m_can_write(cdev, M_CAN_RXESC, M_CAN_RXESC_64BYTES); + m_can_write(cdev, M_CAN_RXESC, + FIELD_PREP(RXESC_RBDS_MASK, RXESC_64B) | + FIELD_PREP(RXESC_F1DS_MASK, RXESC_64B) | + FIELD_PREP(RXESC_F0DS_MASK, RXESC_64B)); /* Accept Non-matching Frames Into FIFO 0 */ m_can_write(cdev, M_CAN_GFC, 0x0); if (cdev->version == 30) { /* only support one Tx Buffer currently */ - m_can_write(cdev, M_CAN_TXBC, (1 << TXBC_NDTB_SHIFT) | + m_can_write(cdev, M_CAN_TXBC, FIELD_PREP(TXBC_NDTB_MASK, 1) | cdev->mcfg[MRAM_TXB].off); } else { /* TX FIFO is used for newer IP Core versions */ m_can_write(cdev, M_CAN_TXBC, - (cdev->mcfg[MRAM_TXB].num << TXBC_TFQS_SHIFT) | - (cdev->mcfg[MRAM_TXB].off)); + FIELD_PREP(TXBC_TFQS_MASK, + cdev->mcfg[MRAM_TXB].num) | + cdev->mcfg[MRAM_TXB].off); } /* support 64 bytes payload */ - m_can_write(cdev, M_CAN_TXESC, TXESC_TBDS_64BYTES); + m_can_write(cdev, M_CAN_TXESC, + FIELD_PREP(TXESC_TBDS_MASK, TXESC_TBDS_64B)); /* TX Event FIFO */ if (cdev->version == 30) { - m_can_write(cdev, M_CAN_TXEFC, (1 << TXEFC_EFS_SHIFT) | + m_can_write(cdev, M_CAN_TXEFC, + FIELD_PREP(TXEFC_EFS_MASK, 1) | cdev->mcfg[MRAM_TXE].off); } else { /* Full TX Event FIFO is used */ m_can_write(cdev, M_CAN_TXEFC, - ((cdev->mcfg[MRAM_TXE].num << TXEFC_EFS_SHIFT) - & TXEFC_EFS_MASK) | + FIELD_PREP(TXEFC_EFS_MASK, + cdev->mcfg[MRAM_TXE].num) | cdev->mcfg[MRAM_TXE].off); } /* rx fifo configuration, blocking mode, fifo size 1 */ m_can_write(cdev, M_CAN_RXF0C, - (cdev->mcfg[MRAM_RXF0].num << RXFC_FS_SHIFT) | + FIELD_PREP(RXFC_FS_MASK, cdev->mcfg[MRAM_RXF0].num) | cdev->mcfg[MRAM_RXF0].off); m_can_write(cdev, M_CAN_RXF1C, - (cdev->mcfg[MRAM_RXF1].num << RXFC_FS_SHIFT) | + FIELD_PREP(RXFC_FS_MASK, cdev->mcfg[MRAM_RXF1].num) | cdev->mcfg[MRAM_RXF1].off); cccr = m_can_read(cdev, M_CAN_CCCR); @@ -1264,11 +1246,11 @@ static void m_can_chip_config(struct net_device *dev) /* Version 3.0.x */ cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_DAR | - (CCCR_CMR_MASK << CCCR_CMR_SHIFT) | - (CCCR_CME_MASK << CCCR_CME_SHIFT)); + FIELD_PREP(CCCR_CMR_MASK, FIELD_MAX(CCCR_CMR_MASK)) | + FIELD_PREP(CCCR_CME_MASK, FIELD_MAX(CCCR_CME_MASK))); if (cdev->can.ctrlmode & CAN_CTRLMODE_FD) - cccr |= CCCR_CME_CANFD_BRS << CCCR_CME_SHIFT; + cccr |= FIELD_PREP(CCCR_CME_MASK, CCCR_CME_CANFD_BRS); } else { /* Version 3.1.x or 3.2.x */ @@ -1372,8 +1354,8 @@ static int m_can_check_core_release(struct m_can_classdev *cdev) * Example: Version 3.2.1 => rel = 3; step = 2; substep = 1; */ crel_reg = m_can_read(cdev, M_CAN_CREL); - rel = (u8)((crel_reg & CREL_REL_MASK) >> CREL_REL_SHIFT); - step = (u8)((crel_reg & CREL_STEP_MASK) >> CREL_STEP_SHIFT); + rel = (u8)FIELD_GET(CREL_REL_MASK, crel_reg); + step = (u8)FIELD_GET(CREL_STEP_MASK, crel_reg); if (rel == 3) { /* M_CAN v3.x.y: create return value */ @@ -1593,16 +1575,16 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev) if (cdev->can.ctrlmode & CAN_CTRLMODE_FD) { cccr = m_can_read(cdev, M_CAN_CCCR); - cccr &= ~(CCCR_CMR_MASK << CCCR_CMR_SHIFT); + cccr &= ~CCCR_CMR_MASK; if (can_is_canfd_skb(skb)) { if (cf->flags & CANFD_BRS) - cccr |= CCCR_CMR_CANFD_BRS << - CCCR_CMR_SHIFT; + cccr |= FIELD_PREP(CCCR_CMR_MASK, + CCCR_CMR_CANFD_BRS); else - cccr |= CCCR_CMR_CANFD << - CCCR_CMR_SHIFT; + cccr |= FIELD_PREP(CCCR_CMR_MASK, + CCCR_CMR_CANFD); } else { - cccr |= CCCR_CMR_CAN << CCCR_CMR_SHIFT; + cccr |= FIELD_PREP(CCCR_CMR_MASK, CCCR_CMR_CAN); } m_can_write(cdev, M_CAN_CCCR, cccr); } @@ -1629,8 +1611,8 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev) } /* get put index for frame */ - putidx = ((m_can_read(cdev, M_CAN_TXFQS) & TXFQS_TFQPI_MASK) - >> TXFQS_TFQPI_SHIFT); + putidx = FIELD_GET(TXFQS_TFQPI_MASK, + m_can_read(cdev, M_CAN_TXFQS)); /* Write ID Field to FIFO Element */ m_can_fifo_write(cdev, putidx, M_CAN_FIFO_ID, id); @@ -1648,9 +1630,9 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev) * sending the correct echo frame */ m_can_fifo_write(cdev, putidx, M_CAN_FIFO_DLC, - ((putidx << TX_BUF_MM_SHIFT) & - TX_BUF_MM_MASK) | - (can_fd_len2dlc(cf->len) << 16) | + FIELD_PREP(TX_BUF_MM_MASK, putidx) | + FIELD_PREP(TX_BUF_DLC_MASK, + can_fd_len2dlc(cf->len)) | fdflags | TX_BUF_EFC); for (i = 0; i < cf->len; i += 4) @@ -1810,11 +1792,11 @@ static void m_can_of_parse_mram(struct m_can_classdev *cdev, cdev->mcfg[MRAM_RXF0].off = cdev->mcfg[MRAM_XIDF].off + cdev->mcfg[MRAM_XIDF].num * XIDF_ELEMENT_SIZE; cdev->mcfg[MRAM_RXF0].num = mram_config_vals[3] & - (RXFC_FS_MASK >> RXFC_FS_SHIFT); + FIELD_MAX(RXFC_FS_MASK); cdev->mcfg[MRAM_RXF1].off = cdev->mcfg[MRAM_RXF0].off + cdev->mcfg[MRAM_RXF0].num * RXF0_ELEMENT_SIZE; cdev->mcfg[MRAM_RXF1].num = mram_config_vals[4] & - (RXFC_FS_MASK >> RXFC_FS_SHIFT); + FIELD_MAX(RXFC_FS_MASK); cdev->mcfg[MRAM_RXB].off = cdev->mcfg[MRAM_RXF1].off + cdev->mcfg[MRAM_RXF1].num * RXF1_ELEMENT_SIZE; cdev->mcfg[MRAM_RXB].num = mram_config_vals[5]; @@ -1824,7 +1806,7 @@ static void m_can_of_parse_mram(struct m_can_classdev *cdev, cdev->mcfg[MRAM_TXB].off = cdev->mcfg[MRAM_TXE].off + cdev->mcfg[MRAM_TXE].num * TXE_ELEMENT_SIZE; cdev->mcfg[MRAM_TXB].num = mram_config_vals[7] & - (TXBC_NDTB_MASK >> TXBC_NDTB_SHIFT); + FIELD_MAX(TXBC_NDTB_MASK); dev_dbg(cdev->dev, "sidf 0x%x %d xidf 0x%x %d rxf0 0x%x %d rxf1 0x%x %d rxb 0x%x %d txe 0x%x %d txb 0x%x %d\n", diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c index 00847cbaf7b6..d08718e98e11 100644 --- a/drivers/net/can/peak_canfd/peak_canfd.c +++ b/drivers/net/can/peak_canfd/peak_canfd.c @@ -351,8 +351,8 @@ static int pucan_handle_status(struct peak_canfd_priv *priv, return err; } - /* start network queue (echo_skb array is empty) */ - netif_start_queue(ndev); + /* wake network queue up (echo_skb array is empty) */ + netif_wake_queue(ndev); return 0; } diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c index c44f3411e561..cfc1325aad10 100644 --- a/drivers/net/can/softing/softing_main.c +++ b/drivers/net/can/softing/softing_main.c @@ -239,7 +239,6 @@ static int softing_handle_1(struct softing *card) DPRAM_INFO_BUSSTATE2 : DPRAM_INFO_BUSSTATE]); /* timestamp */ tmp_u32 = le32_to_cpup((void *)ptr); - ptr += 4; ktime = softing_raw2ktime(card, tmp_u32); ++netdev->stats.rx_errors; @@ -276,7 +275,6 @@ static int softing_handle_1(struct softing *card) ktime = softing_raw2ktime(card, tmp_u32); if (!(msg.can_id & CAN_RTR_FLAG)) memcpy(&msg.data[0], ptr, 8); - ptr += 8; /* update socket */ if (cmd & CMD_ACK) { /* acknowledge, was tx msg */ diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index 6f5d6d04a8b9..dd17b8c53e1c 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -871,7 +871,7 @@ static int hi3110_can_probe(struct spi_device *spi) CAN_CTRLMODE_BERR_REPORTING; if (of_id) - priv->model = (enum hi3110_model)of_id->data; + priv->model = (enum hi3110_model)(uintptr_t)of_id->data; else priv->model = spi_get_device_id(spi)->driver_data; priv->net = net; diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 173c6614086f..0579ab74f728 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -1330,7 +1330,7 @@ static int mcp251x_can_probe(struct spi_device *spi) priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY; if (match) - priv->model = (enum mcp251x_model)match; + priv->model = (enum mcp251x_model)(uintptr_t)match; else priv->model = spi_get_device_id(spi)->driver_data; priv->net = net; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index e0ae00e34c7b..47c3f408a799 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -560,7 +560,7 @@ mcp251xfd_chip_set_mode(const struct mcp251xfd_priv *priv, return __mcp251xfd_chip_set_mode(priv, mode_req, false); } -static inline int +static inline int __maybe_unused mcp251xfd_chip_set_mode_nowait(const struct mcp251xfd_priv *priv, const u8 mode_req) { diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig index 3deb9f1cd292..f959215c9d53 100644 --- a/drivers/net/can/usb/Kconfig +++ b/drivers/net/can/usb/Kconfig @@ -76,7 +76,9 @@ config CAN_KVASER_USB - Scania VCI2 (if you have the Kvaser logo on top) - Kvaser BlackBird v2 - Kvaser Leaf Pro HS v2 + - Kvaser Hybrid CAN/LIN - Kvaser Hybrid 2xCAN/LIN + - Kvaser Hybrid Pro CAN/LIN - Kvaser Hybrid Pro 2xCAN/LIN - Kvaser Memorator 2xHS v2 - Kvaser Memorator Pro 2xHS v2 diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 5af69787d9d5..0a37af4a3fa4 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -1053,7 +1053,6 @@ static void ems_usb_disconnect(struct usb_interface *intf) if (dev) { unregister_netdev(dev->netdev); - free_candev(dev->netdev); unlink_all_urbs(dev); @@ -1061,6 +1060,8 @@ static void ems_usb_disconnect(struct usb_interface *intf) kfree(dev->intr_in_buffer); kfree(dev->tx_msg_buffer); + + free_candev(dev->netdev); } } diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 90ebcae13409..0cc0fc866a2a 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -79,16 +79,18 @@ #define USB_USBCAN_PRO_2HS_V2_PRODUCT_ID 264 #define USB_MEMO_2HS_PRODUCT_ID 265 #define USB_MEMO_PRO_2HS_V2_PRODUCT_ID 266 -#define USB_HYBRID_CANLIN_PRODUCT_ID 267 +#define USB_HYBRID_2CANLIN_PRODUCT_ID 267 #define USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID 268 #define USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID 269 -#define USB_HYBRID_PRO_CANLIN_PRODUCT_ID 270 +#define USB_HYBRID_PRO_2CANLIN_PRODUCT_ID 270 #define USB_U100_PRODUCT_ID 273 #define USB_U100P_PRODUCT_ID 274 #define USB_U100S_PRODUCT_ID 275 #define USB_USBCAN_PRO_4HS_PRODUCT_ID 276 +#define USB_HYBRID_CANLIN_PRODUCT_ID 277 +#define USB_HYBRID_PRO_CANLIN_PRODUCT_ID 278 #define USB_HYDRA_PRODUCT_ID_END \ - USB_USBCAN_PRO_4HS_PRODUCT_ID + USB_HYBRID_PRO_CANLIN_PRODUCT_ID static inline bool kvaser_is_leaf(const struct usb_device_id *id) { @@ -187,14 +189,16 @@ static const struct usb_device_id kvaser_usb_table[] = { { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_2HS_V2_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_2HS_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_PRO_2HS_V2_PRODUCT_ID) }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_CANLIN_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_2CANLIN_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID) }, - { USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_CANLIN_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_2CANLIN_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_U100_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_U100P_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_U100S_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_4HS_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_CANLIN_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_CANLIN_PRODUCT_ID) }, { } }; MODULE_DEVICE_TABLE(usb, kvaser_usb_table); diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 3ca6b394dd5f..b23e3488695b 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -728,6 +728,13 @@ static u16 b53_default_pvid(struct b53_device *dev) return 0; } +static bool b53_vlan_port_needs_forced_tagged(struct dsa_switch *ds, int port) +{ + struct b53_device *dev = ds->priv; + + return dev->tag_protocol == DSA_TAG_PROTO_NONE && dsa_is_cpu_port(ds, port); +} + int b53_configure_vlan(struct dsa_switch *ds) { struct b53_device *dev = ds->priv; @@ -748,9 +755,20 @@ int b53_configure_vlan(struct dsa_switch *ds) b53_enable_vlan(dev, -1, dev->vlan_enabled, ds->vlan_filtering); - b53_for_each_port(dev, i) + /* Create an untagged VLAN entry for the default PVID in case + * CONFIG_VLAN_8021Q is disabled and there are no calls to + * dsa_slave_vlan_rx_add_vid() to create the default VLAN + * entry. Do this only when the tagging protocol is not + * DSA_TAG_PROTO_NONE + */ + b53_for_each_port(dev, i) { + v = &dev->vlans[def_vid]; + v->members |= BIT(i); + if (!b53_vlan_port_needs_forced_tagged(ds, i)) + v->untag = v->members; b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(i), def_vid); + } /* Upon initial call we have not set-up any VLANs, but upon * system resume, we need to restore all VLAN entries. @@ -1084,6 +1102,11 @@ static int b53_setup(struct dsa_switch *ds) unsigned int port; int ret; + /* Request bridge PVID untagged when DSA_TAG_PROTO_NONE is set + * which forces the CPU port to be tagged in all VLANs. + */ + ds->untag_bridge_pvid = dev->tag_protocol == DSA_TAG_PROTO_NONE; + ret = b53_reset_switch(dev); if (ret) { dev_err(ds->dev, "failed to reset switch\n"); @@ -1477,7 +1500,7 @@ int b53_vlan_add(struct dsa_switch *ds, int port, untagged = true; vl->members |= BIT(port); - if (untagged && !dsa_is_cpu_port(ds, port)) + if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port)) vl->untag |= BIT(port); else vl->untag &= ~BIT(port); @@ -1514,7 +1537,7 @@ int b53_vlan_del(struct dsa_switch *ds, int port, if (pvid == vlan->vid) pvid = b53_default_pvid(dev); - if (untagged && !dsa_is_cpu_port(ds, port)) + if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port)) vl->untag &= ~(BIT(port)); b53_set_vlan_entry(dev, vlan->vid, vl); @@ -2660,7 +2683,6 @@ struct b53_device *b53_switch_alloc(struct device *base, dev->priv = priv; dev->ops = ops; ds->ops = &b53_switch_ops; - ds->untag_bridge_pvid = true; dev->vlan_enabled = true; /* Let DSA handle the case were multiple bridges span the same switch * device and different VLAN awareness settings are requested, which diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index aaa12d73784e..3f4249de70c5 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -632,8 +632,7 @@ static int b53_srab_remove(struct platform_device *pdev) struct b53_srab_priv *priv = dev->priv; b53_srab_intr_set(priv, false); - if (dev) - b53_switch_remove(dev); + b53_switch_remove(dev); return 0; } diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c index 4d78219da253..9fdcc4bde480 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.c +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -927,7 +927,6 @@ static int hellcreek_fdb_dump(struct dsa_switch *ds, int port, /* Read table */ for (i = 0; i < hellcreek->fdb_entries; ++i) { - unsigned char null_addr[ETH_ALEN] = { 0 }; struct hellcreek_fdb_entry entry = { 0 }; /* Read entry */ @@ -937,7 +936,7 @@ static int hellcreek_fdb_dump(struct dsa_switch *ds, int port, hellcreek_write(hellcreek, 0x00, HR_FDBRDH); /* Check valid */ - if (!memcmp(entry.mac, null_addr, ETH_ALEN)) + if (is_zero_ether_addr(entry.mac)) continue; /* Check port mask */ diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index ad509a57a945..560f6843bb65 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -6,6 +6,7 @@ * Tristram Ha */ +#include #include #include #include @@ -15,8 +16,10 @@ #include #include #include +#include #include #include +#include #include "ksz_common.h" #include "ksz8795_reg.h" @@ -727,92 +730,114 @@ static void ksz8_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val) u8 restart, speed, ctrl, link; const u8 *regs = ksz8->regs; int processed = true; + u8 val1, val2; u16 data = 0; u8 p = phy; switch (reg) { - case PHY_REG_CTRL: + case MII_BMCR: ksz_pread8(dev, p, regs[P_NEG_RESTART_CTRL], &restart); ksz_pread8(dev, p, regs[P_SPEED_STATUS], &speed); ksz_pread8(dev, p, regs[P_FORCE_CTRL], &ctrl); if (restart & PORT_PHY_LOOPBACK) - data |= PHY_LOOPBACK; + data |= BMCR_LOOPBACK; if (ctrl & PORT_FORCE_100_MBIT) - data |= PHY_SPEED_100MBIT; + data |= BMCR_SPEED100; if (ksz_is_ksz88x3(dev)) { if ((ctrl & PORT_AUTO_NEG_ENABLE)) - data |= PHY_AUTO_NEG_ENABLE; + data |= BMCR_ANENABLE; } else { if (!(ctrl & PORT_AUTO_NEG_DISABLE)) - data |= PHY_AUTO_NEG_ENABLE; + data |= BMCR_ANENABLE; } if (restart & PORT_POWER_DOWN) - data |= PHY_POWER_DOWN; + data |= BMCR_PDOWN; if (restart & PORT_AUTO_NEG_RESTART) - data |= PHY_AUTO_NEG_RESTART; + data |= BMCR_ANRESTART; if (ctrl & PORT_FORCE_FULL_DUPLEX) - data |= PHY_FULL_DUPLEX; + data |= BMCR_FULLDPLX; if (speed & PORT_HP_MDIX) - data |= PHY_HP_MDIX; + data |= KSZ886X_BMCR_HP_MDIX; if (restart & PORT_FORCE_MDIX) - data |= PHY_FORCE_MDIX; + data |= KSZ886X_BMCR_FORCE_MDI; if (restart & PORT_AUTO_MDIX_DISABLE) - data |= PHY_AUTO_MDIX_DISABLE; + data |= KSZ886X_BMCR_DISABLE_AUTO_MDIX; if (restart & PORT_TX_DISABLE) - data |= PHY_TRANSMIT_DISABLE; + data |= KSZ886X_BMCR_DISABLE_TRANSMIT; if (restart & PORT_LED_OFF) - data |= PHY_LED_DISABLE; + data |= KSZ886X_BMCR_DISABLE_LED; break; - case PHY_REG_STATUS: + case MII_BMSR: ksz_pread8(dev, p, regs[P_LINK_STATUS], &link); - data = PHY_100BTX_FD_CAPABLE | - PHY_100BTX_CAPABLE | - PHY_10BT_FD_CAPABLE | - PHY_10BT_CAPABLE | - PHY_AUTO_NEG_CAPABLE; + data = BMSR_100FULL | + BMSR_100HALF | + BMSR_10FULL | + BMSR_10HALF | + BMSR_ANEGCAPABLE; if (link & PORT_AUTO_NEG_COMPLETE) - data |= PHY_AUTO_NEG_ACKNOWLEDGE; + data |= BMSR_ANEGCOMPLETE; if (link & PORT_STAT_LINK_GOOD) - data |= PHY_LINK_STATUS; + data |= BMSR_LSTATUS; break; - case PHY_REG_ID_1: + case MII_PHYSID1: data = KSZ8795_ID_HI; break; - case PHY_REG_ID_2: + case MII_PHYSID2: if (ksz_is_ksz88x3(dev)) data = KSZ8863_ID_LO; else data = KSZ8795_ID_LO; break; - case PHY_REG_AUTO_NEGOTIATION: + case MII_ADVERTISE: ksz_pread8(dev, p, regs[P_LOCAL_CTRL], &ctrl); - data = PHY_AUTO_NEG_802_3; + data = ADVERTISE_CSMA; if (ctrl & PORT_AUTO_NEG_SYM_PAUSE) - data |= PHY_AUTO_NEG_SYM_PAUSE; + data |= ADVERTISE_PAUSE_CAP; if (ctrl & PORT_AUTO_NEG_100BTX_FD) - data |= PHY_AUTO_NEG_100BTX_FD; + data |= ADVERTISE_100FULL; if (ctrl & PORT_AUTO_NEG_100BTX) - data |= PHY_AUTO_NEG_100BTX; + data |= ADVERTISE_100HALF; if (ctrl & PORT_AUTO_NEG_10BT_FD) - data |= PHY_AUTO_NEG_10BT_FD; + data |= ADVERTISE_10FULL; if (ctrl & PORT_AUTO_NEG_10BT) - data |= PHY_AUTO_NEG_10BT; + data |= ADVERTISE_10HALF; break; - case PHY_REG_REMOTE_CAPABILITY: + case MII_LPA: ksz_pread8(dev, p, regs[P_REMOTE_STATUS], &link); - data = PHY_AUTO_NEG_802_3; + data = LPA_SLCT; if (link & PORT_REMOTE_SYM_PAUSE) - data |= PHY_AUTO_NEG_SYM_PAUSE; + data |= LPA_PAUSE_CAP; if (link & PORT_REMOTE_100BTX_FD) - data |= PHY_AUTO_NEG_100BTX_FD; + data |= LPA_100FULL; if (link & PORT_REMOTE_100BTX) - data |= PHY_AUTO_NEG_100BTX; + data |= LPA_100HALF; if (link & PORT_REMOTE_10BT_FD) - data |= PHY_AUTO_NEG_10BT_FD; + data |= LPA_10FULL; if (link & PORT_REMOTE_10BT) - data |= PHY_AUTO_NEG_10BT; - if (data & ~PHY_AUTO_NEG_802_3) - data |= PHY_REMOTE_ACKNOWLEDGE_NOT; + data |= LPA_10HALF; + if (data & ~LPA_SLCT) + data |= LPA_LPACK; + break; + case PHY_REG_LINK_MD: + ksz_pread8(dev, p, REG_PORT_LINK_MD_CTRL, &val1); + ksz_pread8(dev, p, REG_PORT_LINK_MD_RESULT, &val2); + if (val1 & PORT_START_CABLE_DIAG) + data |= PHY_START_CABLE_DIAG; + + if (val1 & PORT_CABLE_10M_SHORT) + data |= PHY_CABLE_10M_SHORT; + + data |= FIELD_PREP(PHY_CABLE_DIAG_RESULT_M, + FIELD_GET(PORT_CABLE_DIAG_RESULT_M, val1)); + + data |= FIELD_PREP(PHY_CABLE_FAULT_COUNTER_M, + (FIELD_GET(PORT_CABLE_FAULT_COUNTER_H, val1) << 8) | + FIELD_GET(PORT_CABLE_FAULT_COUNTER_L, val2)); + break; + case PHY_REG_PHY_CTRL: + ksz_pread8(dev, p, regs[P_LINK_STATUS], &link); + if (link & PORT_MDIX_STATUS) + data |= KSZ886X_CTRL_MDIX_STAT; break; default: processed = false; @@ -830,14 +855,14 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) u8 p = phy; switch (reg) { - case PHY_REG_CTRL: + case MII_BMCR: /* Do not support PHY reset function. */ - if (val & PHY_RESET) + if (val & BMCR_RESET) break; ksz_pread8(dev, p, regs[P_SPEED_STATUS], &speed); data = speed; - if (val & PHY_HP_MDIX) + if (val & KSZ886X_BMCR_HP_MDIX) data |= PORT_HP_MDIX; else data &= ~PORT_HP_MDIX; @@ -846,12 +871,12 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) ksz_pread8(dev, p, regs[P_FORCE_CTRL], &ctrl); data = ctrl; if (ksz_is_ksz88x3(dev)) { - if ((val & PHY_AUTO_NEG_ENABLE)) + if ((val & BMCR_ANENABLE)) data |= PORT_AUTO_NEG_ENABLE; else data &= ~PORT_AUTO_NEG_ENABLE; } else { - if (!(val & PHY_AUTO_NEG_ENABLE)) + if (!(val & BMCR_ANENABLE)) data |= PORT_AUTO_NEG_DISABLE; else data &= ~PORT_AUTO_NEG_DISABLE; @@ -861,11 +886,11 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) data |= PORT_AUTO_NEG_DISABLE; } - if (val & PHY_SPEED_100MBIT) + if (val & BMCR_SPEED100) data |= PORT_FORCE_100_MBIT; else data &= ~PORT_FORCE_100_MBIT; - if (val & PHY_FULL_DUPLEX) + if (val & BMCR_FULLDPLX) data |= PORT_FORCE_FULL_DUPLEX; else data &= ~PORT_FORCE_FULL_DUPLEX; @@ -873,38 +898,38 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) ksz_pwrite8(dev, p, regs[P_FORCE_CTRL], data); ksz_pread8(dev, p, regs[P_NEG_RESTART_CTRL], &restart); data = restart; - if (val & PHY_LED_DISABLE) + if (val & KSZ886X_BMCR_DISABLE_LED) data |= PORT_LED_OFF; else data &= ~PORT_LED_OFF; - if (val & PHY_TRANSMIT_DISABLE) + if (val & KSZ886X_BMCR_DISABLE_TRANSMIT) data |= PORT_TX_DISABLE; else data &= ~PORT_TX_DISABLE; - if (val & PHY_AUTO_NEG_RESTART) + if (val & BMCR_ANRESTART) data |= PORT_AUTO_NEG_RESTART; else data &= ~(PORT_AUTO_NEG_RESTART); - if (val & PHY_POWER_DOWN) + if (val & BMCR_PDOWN) data |= PORT_POWER_DOWN; else data &= ~PORT_POWER_DOWN; - if (val & PHY_AUTO_MDIX_DISABLE) + if (val & KSZ886X_BMCR_DISABLE_AUTO_MDIX) data |= PORT_AUTO_MDIX_DISABLE; else data &= ~PORT_AUTO_MDIX_DISABLE; - if (val & PHY_FORCE_MDIX) + if (val & KSZ886X_BMCR_FORCE_MDI) data |= PORT_FORCE_MDIX; else data &= ~PORT_FORCE_MDIX; - if (val & PHY_LOOPBACK) + if (val & BMCR_LOOPBACK) data |= PORT_PHY_LOOPBACK; else data &= ~PORT_PHY_LOOPBACK; if (data != restart) ksz_pwrite8(dev, p, regs[P_NEG_RESTART_CTRL], data); break; - case PHY_REG_AUTO_NEGOTIATION: + case MII_ADVERTISE: ksz_pread8(dev, p, regs[P_LOCAL_CTRL], &ctrl); data = ctrl; data &= ~(PORT_AUTO_NEG_SYM_PAUSE | @@ -912,19 +937,23 @@ static void ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) PORT_AUTO_NEG_100BTX | PORT_AUTO_NEG_10BT_FD | PORT_AUTO_NEG_10BT); - if (val & PHY_AUTO_NEG_SYM_PAUSE) + if (val & ADVERTISE_PAUSE_CAP) data |= PORT_AUTO_NEG_SYM_PAUSE; - if (val & PHY_AUTO_NEG_100BTX_FD) + if (val & ADVERTISE_100FULL) data |= PORT_AUTO_NEG_100BTX_FD; - if (val & PHY_AUTO_NEG_100BTX) + if (val & ADVERTISE_100HALF) data |= PORT_AUTO_NEG_100BTX; - if (val & PHY_AUTO_NEG_10BT_FD) + if (val & ADVERTISE_10FULL) data |= PORT_AUTO_NEG_10BT_FD; - if (val & PHY_AUTO_NEG_10BT) + if (val & ADVERTISE_10HALF) data |= PORT_AUTO_NEG_10BT; if (data != ctrl) ksz_pwrite8(dev, p, regs[P_LOCAL_CTRL], data); break; + case PHY_REG_LINK_MD: + if (val & PHY_START_CABLE_DIAG) + ksz_port_cfg(dev, p, REG_PORT_LINK_MD_CTRL, PORT_START_CABLE_DIAG, true); + break; default: break; } @@ -941,6 +970,18 @@ static enum dsa_tag_protocol ksz8_get_tag_protocol(struct dsa_switch *ds, DSA_TAG_PROTO_KSZ9893 : DSA_TAG_PROTO_KSZ8795; } +static u32 ksz8_sw_get_phy_flags(struct dsa_switch *ds, int port) +{ + /* Silicon Errata Sheet (DS80000830A): + * Port 1 does not work with LinkMD Cable-Testing. + * Port 1 does not respond to received PAUSE control frames. + */ + if (!port) + return MICREL_KSZ8_P1_ERRATA; + + return 0; +} + static void ksz8_get_strings(struct dsa_switch *ds, int port, u32 stringset, uint8_t *buf) { @@ -1419,11 +1460,66 @@ static int ksz8_setup(struct dsa_switch *ds) return 0; } +static void ksz8_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + struct ksz_device *dev = ds->priv; + + if (port == dev->cpu_port) { + if (state->interface != PHY_INTERFACE_MODE_RMII && + state->interface != PHY_INTERFACE_MODE_MII && + state->interface != PHY_INTERFACE_MODE_NA) + goto unsupported; + } else { + if (state->interface != PHY_INTERFACE_MODE_INTERNAL && + state->interface != PHY_INTERFACE_MODE_NA) + goto unsupported; + } + + /* Allow all the expected bits */ + phylink_set_port_modes(mask); + phylink_set(mask, Autoneg); + + /* Silicon Errata Sheet (DS80000830A): + * "Port 1 does not respond to received flow control PAUSE frames" + * So, disable Pause support on "Port 1" (port == 0) for all ksz88x3 + * switches. + */ + if (!ksz_is_ksz88x3(dev) || port) + phylink_set(mask, Pause); + + /* Asym pause is not supported on KSZ8863 and KSZ8873 */ + if (!ksz_is_ksz88x3(dev)) + phylink_set(mask, Asym_Pause); + + /* 10M and 100M are only supported */ + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 100baseT_Full); + + bitmap_and(supported, supported, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_and(state->advertising, state->advertising, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + + return; + +unsupported: + bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); + dev_err(ds->dev, "Unsupported interface: %s, port: %d\n", + phy_modes(state->interface), port); +} + static const struct dsa_switch_ops ksz8_switch_ops = { .get_tag_protocol = ksz8_get_tag_protocol, + .get_phy_flags = ksz8_sw_get_phy_flags, .setup = ksz8_setup, .phy_read = ksz_phy_read16, .phy_write = ksz_phy_write16, + .phylink_validate = ksz8_validate, .phylink_mac_link_down = ksz_mac_link_down, .port_enable = ksz_enable_port, .get_strings = ksz8_get_strings, diff --git a/drivers/net/dsa/microchip/ksz8795_reg.h b/drivers/net/dsa/microchip/ksz8795_reg.h index c2e52c40a54c..a32355624f31 100644 --- a/drivers/net/dsa/microchip/ksz8795_reg.h +++ b/drivers/net/dsa/microchip/ksz8795_reg.h @@ -249,7 +249,7 @@ #define REG_PORT_4_LINK_MD_CTRL 0x4A #define PORT_CABLE_10M_SHORT BIT(7) -#define PORT_CABLE_DIAG_RESULT_M 0x3 +#define PORT_CABLE_DIAG_RESULT_M GENMASK(6, 5) #define PORT_CABLE_DIAG_RESULT_S 5 #define PORT_CABLE_STAT_NORMAL 0 #define PORT_CABLE_STAT_OPEN 1 @@ -744,68 +744,6 @@ #define PORT_ACL_FORCE_DLR_MISS BIT(0) -#ifndef PHY_REG_CTRL -#define PHY_REG_CTRL 0 - -#define PHY_RESET BIT(15) -#define PHY_LOOPBACK BIT(14) -#define PHY_SPEED_100MBIT BIT(13) -#define PHY_AUTO_NEG_ENABLE BIT(12) -#define PHY_POWER_DOWN BIT(11) -#define PHY_MII_DISABLE BIT(10) -#define PHY_AUTO_NEG_RESTART BIT(9) -#define PHY_FULL_DUPLEX BIT(8) -#define PHY_COLLISION_TEST_NOT BIT(7) -#define PHY_HP_MDIX BIT(5) -#define PHY_FORCE_MDIX BIT(4) -#define PHY_AUTO_MDIX_DISABLE BIT(3) -#define PHY_REMOTE_FAULT_DISABLE BIT(2) -#define PHY_TRANSMIT_DISABLE BIT(1) -#define PHY_LED_DISABLE BIT(0) - -#define PHY_REG_STATUS 1 - -#define PHY_100BT4_CAPABLE BIT(15) -#define PHY_100BTX_FD_CAPABLE BIT(14) -#define PHY_100BTX_CAPABLE BIT(13) -#define PHY_10BT_FD_CAPABLE BIT(12) -#define PHY_10BT_CAPABLE BIT(11) -#define PHY_MII_SUPPRESS_CAPABLE_NOT BIT(6) -#define PHY_AUTO_NEG_ACKNOWLEDGE BIT(5) -#define PHY_REMOTE_FAULT BIT(4) -#define PHY_AUTO_NEG_CAPABLE BIT(3) -#define PHY_LINK_STATUS BIT(2) -#define PHY_JABBER_DETECT_NOT BIT(1) -#define PHY_EXTENDED_CAPABILITY BIT(0) - -#define PHY_REG_ID_1 2 -#define PHY_REG_ID_2 3 - -#define PHY_REG_AUTO_NEGOTIATION 4 - -#define PHY_AUTO_NEG_NEXT_PAGE_NOT BIT(15) -#define PHY_AUTO_NEG_REMOTE_FAULT_NOT BIT(13) -#define PHY_AUTO_NEG_SYM_PAUSE BIT(10) -#define PHY_AUTO_NEG_100BT4 BIT(9) -#define PHY_AUTO_NEG_100BTX_FD BIT(8) -#define PHY_AUTO_NEG_100BTX BIT(7) -#define PHY_AUTO_NEG_10BT_FD BIT(6) -#define PHY_AUTO_NEG_10BT BIT(5) -#define PHY_AUTO_NEG_SELECTOR 0x001F -#define PHY_AUTO_NEG_802_3 0x0001 - -#define PHY_REG_REMOTE_CAPABILITY 5 - -#define PHY_REMOTE_NEXT_PAGE_NOT BIT(15) -#define PHY_REMOTE_ACKNOWLEDGE_NOT BIT(14) -#define PHY_REMOTE_REMOTE_FAULT_NOT BIT(13) -#define PHY_REMOTE_SYM_PAUSE BIT(10) -#define PHY_REMOTE_100BTX_FD BIT(8) -#define PHY_REMOTE_100BTX BIT(7) -#define PHY_REMOTE_10BT_FD BIT(6) -#define PHY_REMOTE_10BT BIT(5) -#endif - #define KSZ8795_ID_HI 0x0022 #define KSZ8795_ID_LO 0x1550 #define KSZ8863_ID_LO 0x1430 @@ -815,13 +753,14 @@ #define PHY_REG_LINK_MD 0x1D #define PHY_START_CABLE_DIAG BIT(15) +#define PHY_CABLE_DIAG_RESULT_M GENMASK(14, 13) #define PHY_CABLE_DIAG_RESULT 0x6000 #define PHY_CABLE_STAT_NORMAL 0x0000 #define PHY_CABLE_STAT_OPEN 0x2000 #define PHY_CABLE_STAT_SHORT 0x4000 #define PHY_CABLE_STAT_FAILED 0x6000 #define PHY_CABLE_10M_SHORT BIT(12) -#define PHY_CABLE_FAULT_COUNTER 0x01FF +#define PHY_CABLE_FAULT_COUNTER_M GENMASK(8, 0) #define PHY_REG_PHY_CTRL 0x1F diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 9b90f3d3a8f5..93136f7e69f5 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -596,18 +597,14 @@ mt7530_mib_reset(struct dsa_switch *ds) mt7530_write(priv, MT7530_MIB_CCR, CCR_MIB_ACTIVATE); } -static int mt7530_phy_read(struct dsa_switch *ds, int port, int regnum) +static int mt7530_phy_read(struct mt7530_priv *priv, int port, int regnum) { - struct mt7530_priv *priv = ds->priv; - return mdiobus_read_nested(priv->bus, port, regnum); } -static int mt7530_phy_write(struct dsa_switch *ds, int port, int regnum, +static int mt7530_phy_write(struct mt7530_priv *priv, int port, int regnum, u16 val) { - struct mt7530_priv *priv = ds->priv; - return mdiobus_write_nested(priv->bus, port, regnum, val); } @@ -785,9 +782,8 @@ out: } static int -mt7531_ind_phy_read(struct dsa_switch *ds, int port, int regnum) +mt7531_ind_phy_read(struct mt7530_priv *priv, int port, int regnum) { - struct mt7530_priv *priv = ds->priv; int devad; int ret; @@ -803,10 +799,9 @@ mt7531_ind_phy_read(struct dsa_switch *ds, int port, int regnum) } static int -mt7531_ind_phy_write(struct dsa_switch *ds, int port, int regnum, +mt7531_ind_phy_write(struct mt7530_priv *priv, int port, int regnum, u16 data) { - struct mt7530_priv *priv = ds->priv; int devad; int ret; @@ -822,6 +817,22 @@ mt7531_ind_phy_write(struct dsa_switch *ds, int port, int regnum, return ret; } +static int +mt753x_phy_read(struct mii_bus *bus, int port, int regnum) +{ + struct mt7530_priv *priv = bus->priv; + + return priv->info->phy_read(priv, port, regnum); +} + +static int +mt753x_phy_write(struct mii_bus *bus, int port, int regnum, u16 val) +{ + struct mt7530_priv *priv = bus->priv; + + return priv->info->phy_write(priv, port, regnum, val); +} + static void mt7530_get_strings(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data) @@ -1820,6 +1831,210 @@ mt7530_setup_gpio(struct mt7530_priv *priv) } #endif /* CONFIG_GPIOLIB */ +static irqreturn_t +mt7530_irq_thread_fn(int irq, void *dev_id) +{ + struct mt7530_priv *priv = dev_id; + bool handled = false; + u32 val; + int p; + + mutex_lock_nested(&priv->bus->mdio_lock, MDIO_MUTEX_NESTED); + val = mt7530_mii_read(priv, MT7530_SYS_INT_STS); + mt7530_mii_write(priv, MT7530_SYS_INT_STS, val); + mutex_unlock(&priv->bus->mdio_lock); + + for (p = 0; p < MT7530_NUM_PHYS; p++) { + if (BIT(p) & val) { + unsigned int irq; + + irq = irq_find_mapping(priv->irq_domain, p); + handle_nested_irq(irq); + handled = true; + } + } + + return IRQ_RETVAL(handled); +} + +static void +mt7530_irq_mask(struct irq_data *d) +{ + struct mt7530_priv *priv = irq_data_get_irq_chip_data(d); + + priv->irq_enable &= ~BIT(d->hwirq); +} + +static void +mt7530_irq_unmask(struct irq_data *d) +{ + struct mt7530_priv *priv = irq_data_get_irq_chip_data(d); + + priv->irq_enable |= BIT(d->hwirq); +} + +static void +mt7530_irq_bus_lock(struct irq_data *d) +{ + struct mt7530_priv *priv = irq_data_get_irq_chip_data(d); + + mutex_lock_nested(&priv->bus->mdio_lock, MDIO_MUTEX_NESTED); +} + +static void +mt7530_irq_bus_sync_unlock(struct irq_data *d) +{ + struct mt7530_priv *priv = irq_data_get_irq_chip_data(d); + + mt7530_mii_write(priv, MT7530_SYS_INT_EN, priv->irq_enable); + mutex_unlock(&priv->bus->mdio_lock); +} + +static struct irq_chip mt7530_irq_chip = { + .name = KBUILD_MODNAME, + .irq_mask = mt7530_irq_mask, + .irq_unmask = mt7530_irq_unmask, + .irq_bus_lock = mt7530_irq_bus_lock, + .irq_bus_sync_unlock = mt7530_irq_bus_sync_unlock, +}; + +static int +mt7530_irq_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_data(irq, domain->host_data); + irq_set_chip_and_handler(irq, &mt7530_irq_chip, handle_simple_irq); + irq_set_nested_thread(irq, true); + irq_set_noprobe(irq); + + return 0; +} + +static const struct irq_domain_ops mt7530_irq_domain_ops = { + .map = mt7530_irq_map, + .xlate = irq_domain_xlate_onecell, +}; + +static void +mt7530_setup_mdio_irq(struct mt7530_priv *priv) +{ + struct dsa_switch *ds = priv->ds; + int p; + + for (p = 0; p < MT7530_NUM_PHYS; p++) { + if (BIT(p) & ds->phys_mii_mask) { + unsigned int irq; + + irq = irq_create_mapping(priv->irq_domain, p); + ds->slave_mii_bus->irq[p] = irq; + } + } +} + +static int +mt7530_setup_irq(struct mt7530_priv *priv) +{ + struct device *dev = priv->dev; + struct device_node *np = dev->of_node; + int ret; + + if (!of_property_read_bool(np, "interrupt-controller")) { + dev_info(dev, "no interrupt support\n"); + return 0; + } + + priv->irq = of_irq_get(np, 0); + if (priv->irq <= 0) { + dev_err(dev, "failed to get parent IRQ: %d\n", priv->irq); + return priv->irq ? : -EINVAL; + } + + priv->irq_domain = irq_domain_add_linear(np, MT7530_NUM_PHYS, + &mt7530_irq_domain_ops, priv); + if (!priv->irq_domain) { + dev_err(dev, "failed to create IRQ domain\n"); + return -ENOMEM; + } + + /* This register must be set for MT7530 to properly fire interrupts */ + if (priv->id != ID_MT7531) + mt7530_set(priv, MT7530_TOP_SIG_CTRL, TOP_SIG_CTRL_NORMAL); + + ret = request_threaded_irq(priv->irq, NULL, mt7530_irq_thread_fn, + IRQF_ONESHOT, KBUILD_MODNAME, priv); + if (ret) { + irq_domain_remove(priv->irq_domain); + dev_err(dev, "failed to request IRQ: %d\n", ret); + return ret; + } + + return 0; +} + +static void +mt7530_free_mdio_irq(struct mt7530_priv *priv) +{ + int p; + + for (p = 0; p < MT7530_NUM_PHYS; p++) { + if (BIT(p) & priv->ds->phys_mii_mask) { + unsigned int irq; + + irq = irq_find_mapping(priv->irq_domain, p); + irq_dispose_mapping(irq); + } + } +} + +static void +mt7530_free_irq_common(struct mt7530_priv *priv) +{ + free_irq(priv->irq, priv); + irq_domain_remove(priv->irq_domain); +} + +static void +mt7530_free_irq(struct mt7530_priv *priv) +{ + mt7530_free_mdio_irq(priv); + mt7530_free_irq_common(priv); +} + +static int +mt7530_setup_mdio(struct mt7530_priv *priv) +{ + struct dsa_switch *ds = priv->ds; + struct device *dev = priv->dev; + struct mii_bus *bus; + static int idx; + int ret; + + bus = devm_mdiobus_alloc(dev); + if (!bus) + return -ENOMEM; + + ds->slave_mii_bus = bus; + bus->priv = priv; + bus->name = KBUILD_MODNAME "-mii"; + snprintf(bus->id, MII_BUS_ID_SIZE, KBUILD_MODNAME "-%d", idx++); + bus->read = mt753x_phy_read; + bus->write = mt753x_phy_write; + bus->parent = dev; + bus->phy_mask = ~ds->phys_mii_mask; + + if (priv->irq) + mt7530_setup_mdio_irq(priv); + + ret = mdiobus_register(bus); + if (ret) { + dev_err(dev, "failed to register MDIO bus: %d\n", ret); + if (priv->irq) + mt7530_free_mdio_irq(priv); + } + + return ret; +} + static int mt7530_setup(struct dsa_switch *ds) { @@ -2783,24 +2998,20 @@ static int mt753x_setup(struct dsa_switch *ds) { struct mt7530_priv *priv = ds->priv; + int ret = priv->info->sw_setup(ds); - return priv->info->sw_setup(ds); -} + if (ret) + return ret; -static int -mt753x_phy_read(struct dsa_switch *ds, int port, int regnum) -{ - struct mt7530_priv *priv = ds->priv; + ret = mt7530_setup_irq(priv); + if (ret) + return ret; - return priv->info->phy_read(ds, port, regnum); -} + ret = mt7530_setup_mdio(priv); + if (ret && priv->irq) + mt7530_free_irq_common(priv); -static int -mt753x_phy_write(struct dsa_switch *ds, int port, int regnum, u16 val) -{ - struct mt7530_priv *priv = ds->priv; - - return priv->info->phy_write(ds, port, regnum, val); + return ret; } static int mt753x_get_mac_eee(struct dsa_switch *ds, int port, @@ -2837,8 +3048,6 @@ static const struct dsa_switch_ops mt7530_switch_ops = { .get_tag_protocol = mtk_get_tag_protocol, .setup = mt753x_setup, .get_strings = mt7530_get_strings, - .phy_read = mt753x_phy_read, - .phy_write = mt753x_phy_write, .get_ethtool_stats = mt7530_get_ethtool_stats, .get_sset_count = mt7530_get_sset_count, .set_ageing_time = mt7530_set_ageing_time, @@ -3021,6 +3230,9 @@ mt7530_remove(struct mdio_device *mdiodev) dev_err(priv->dev, "Failed to disable io pwr: %d\n", ret); + if (priv->irq) + mt7530_free_irq(priv); + dsa_unregister_switch(priv->ds); mutex_destroy(&priv->reg_mutex); } diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 0204da486f3a..334d610a503d 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -7,6 +7,7 @@ #define __MT7530_H #define MT7530_NUM_PORTS 7 +#define MT7530_NUM_PHYS 5 #define MT7530_CPU_PORT 6 #define MT7530_NUM_FDB_RECORDS 2048 #define MT7530_ALL_MEMBERS 0xff @@ -393,6 +394,12 @@ enum mt7531_sgmii_force_duplex { #define SYS_CTRL_SW_RST BIT(1) #define SYS_CTRL_REG_RST BIT(0) +/* Register for system interrupt */ +#define MT7530_SYS_INT_EN 0x7008 + +/* Register for system interrupt status */ +#define MT7530_SYS_INT_STS 0x700c + /* Register for PHY Indirect Access Control */ #define MT7531_PHY_IAC 0x701C #define MT7531_PHY_ACS_ST BIT(31) @@ -714,6 +721,8 @@ static const char *p5_intf_modes(unsigned int p5_interface) } } +struct mt7530_priv; + /* struct mt753x_info - This is the main data structure for holding the specific * part for each supported device * @sw_setup: Holding the handler to a device initialization @@ -738,8 +747,8 @@ struct mt753x_info { enum mt753x_id id; int (*sw_setup)(struct dsa_switch *ds); - int (*phy_read)(struct dsa_switch *ds, int port, int regnum); - int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val); + int (*phy_read)(struct mt7530_priv *priv, int port, int regnum); + int (*phy_write)(struct mt7530_priv *priv, int port, int regnum, u16 val); int (*pad_setup)(struct dsa_switch *ds, phy_interface_t interface); int (*cpu_port_config)(struct dsa_switch *ds, int port); bool (*phy_mode_supported)(struct dsa_switch *ds, int port, @@ -773,6 +782,10 @@ struct mt753x_info { * registers * @p6_interface Holding the current port 6 interface * @p5_intf_sel: Holding the current port 5 interface select + * + * @irq: IRQ number of the switch + * @irq_domain: IRQ domain of the switch irq_chip + * @irq_enable: IRQ enable bits, synced to SYS_INT_EN */ struct mt7530_priv { struct device *dev; @@ -794,6 +807,9 @@ struct mt7530_priv { struct mt7530_port ports[MT7530_NUM_PORTS]; /* protect among processes for registers access*/ struct mutex reg_mutex; + int irq; + struct irq_domain *irq_domain; + u32 irq_enable; }; struct mt7530_hw_vlan_entry { diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index eca285aaf72f..961fa6b75cad 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1618,9 +1618,6 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, struct mv88e6xxx_vtu_entry vlan; int i, err; - if (!vid) - return -EOPNOTSUPP; - /* DSA and CPU ports have to be members of multiple vlans */ if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) return 0; @@ -2109,6 +2106,9 @@ static int mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, u8 member; int err; + if (!vlan->vid) + return 0; + err = mv88e6xxx_port_vlan_prepare(ds, port, vlan); if (err) return err; diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index ce607fbaaa3a..a2a15919b960 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -940,6 +940,8 @@ static void felix_phylink_mac_link_up(struct dsa_switch *ds, int port, ocelot_write_rix(ocelot, 0, ANA_POL_FLOWC, port); + ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_ENA, tx_pause); + /* Undo the effects of felix_phylink_mac_link_down: * enable MAC module */ diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 84f93a874d50..deae923c8b7a 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -1206,6 +1206,11 @@ static int seville_probe(struct platform_device *pdev) felix->info = &seville_info_vsc9953; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + err = -EINVAL; + dev_err(&pdev->dev, "Invalid resource\n"); + goto err_alloc_felix; + } felix->switch_base = res->start; ds = kzalloc(sizeof(struct dsa_switch), GFP_KERNEL); diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index cdaf9f85a2cb..1f63f50f73f1 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -88,26 +89,26 @@ qca8k_split_addr(u32 regaddr, u16 *r1, u16 *r2, u16 *page) *page = regaddr & 0x3ff; } -static u32 -qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum) +static int +qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val) { - u32 val; int ret; ret = bus->read(bus, phy_id, regnum); if (ret >= 0) { - val = ret; + *val = ret; ret = bus->read(bus, phy_id, regnum + 1); - val |= ret << 16; + *val |= ret << 16; } if (ret < 0) { dev_err_ratelimited(&bus->dev, "failed to read qca8k 32bit register\n"); + *val = 0; return ret; } - return val; + return 0; } static void @@ -127,82 +128,110 @@ qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val) "failed to write qca8k 32bit register\n"); } -static void +static int qca8k_set_page(struct mii_bus *bus, u16 page) { - if (page == qca8k_current_page) - return; + int ret; - if (bus->write(bus, 0x18, 0, page) < 0) + if (page == qca8k_current_page) + return 0; + + ret = bus->write(bus, 0x18, 0, page); + if (ret < 0) { dev_err_ratelimited(&bus->dev, "failed to set qca8k page\n"); + return ret; + } + qca8k_current_page = page; + usleep_range(1000, 2000); + return 0; } -static u32 -qca8k_read(struct qca8k_priv *priv, u32 reg) +static int +qca8k_read(struct qca8k_priv *priv, u32 reg, u32 *val) { + struct mii_bus *bus = priv->bus; u16 r1, r2, page; - u32 val; + int ret; qca8k_split_addr(reg, &r1, &r2, &page); - mutex_lock_nested(&priv->bus->mdio_lock, MDIO_MUTEX_NESTED); + mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - qca8k_set_page(priv->bus, page); - val = qca8k_mii_read32(priv->bus, 0x10 | r2, r1); + ret = qca8k_set_page(bus, page); + if (ret < 0) + goto exit; - mutex_unlock(&priv->bus->mdio_lock); + ret = qca8k_mii_read32(bus, 0x10 | r2, r1, val); - return val; +exit: + mutex_unlock(&bus->mdio_lock); + return ret; } -static void +static int qca8k_write(struct qca8k_priv *priv, u32 reg, u32 val) { + struct mii_bus *bus = priv->bus; u16 r1, r2, page; + int ret; qca8k_split_addr(reg, &r1, &r2, &page); - mutex_lock_nested(&priv->bus->mdio_lock, MDIO_MUTEX_NESTED); + mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - qca8k_set_page(priv->bus, page); - qca8k_mii_write32(priv->bus, 0x10 | r2, r1, val); + ret = qca8k_set_page(bus, page); + if (ret < 0) + goto exit; - mutex_unlock(&priv->bus->mdio_lock); + qca8k_mii_write32(bus, 0x10 | r2, r1, val); + +exit: + mutex_unlock(&bus->mdio_lock); + return ret; } -static u32 -qca8k_rmw(struct qca8k_priv *priv, u32 reg, u32 mask, u32 val) +static int +qca8k_rmw(struct qca8k_priv *priv, u32 reg, u32 mask, u32 write_val) { + struct mii_bus *bus = priv->bus; u16 r1, r2, page; - u32 ret; + u32 val; + int ret; qca8k_split_addr(reg, &r1, &r2, &page); - mutex_lock_nested(&priv->bus->mdio_lock, MDIO_MUTEX_NESTED); + mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - qca8k_set_page(priv->bus, page); - ret = qca8k_mii_read32(priv->bus, 0x10 | r2, r1); - ret &= ~mask; - ret |= val; - qca8k_mii_write32(priv->bus, 0x10 | r2, r1, ret); + ret = qca8k_set_page(bus, page); + if (ret < 0) + goto exit; - mutex_unlock(&priv->bus->mdio_lock); + ret = qca8k_mii_read32(bus, 0x10 | r2, r1, &val); + if (ret < 0) + goto exit; + + val &= ~mask; + val |= write_val; + qca8k_mii_write32(bus, 0x10 | r2, r1, val); + +exit: + mutex_unlock(&bus->mdio_lock); return ret; } -static void +static int qca8k_reg_set(struct qca8k_priv *priv, u32 reg, u32 val) { - qca8k_rmw(priv, reg, 0, val); + return qca8k_rmw(priv, reg, 0, val); } -static void +static int qca8k_reg_clear(struct qca8k_priv *priv, u32 reg, u32 val) { - qca8k_rmw(priv, reg, val, 0); + return qca8k_rmw(priv, reg, val, 0); } static int @@ -210,9 +239,7 @@ qca8k_regmap_read(void *ctx, uint32_t reg, uint32_t *val) { struct qca8k_priv *priv = (struct qca8k_priv *)ctx; - *val = qca8k_read(priv, reg); - - return 0; + return qca8k_read(priv, reg, val); } static int @@ -220,9 +247,7 @@ qca8k_regmap_write(void *ctx, uint32_t reg, uint32_t val) { struct qca8k_priv *priv = (struct qca8k_priv *)ctx; - qca8k_write(priv, reg, val); - - return 0; + return qca8k_write(priv, reg, val); } static const struct regmap_range qca8k_readable_ranges[] = { @@ -262,32 +287,36 @@ static struct regmap_config qca8k_regmap_config = { static int qca8k_busy_wait(struct qca8k_priv *priv, u32 reg, u32 mask) { - unsigned long timeout; + int ret, ret1; + u32 val; - timeout = jiffies + msecs_to_jiffies(20); + ret = read_poll_timeout(qca8k_read, ret1, !(val & mask), + 0, QCA8K_BUSY_WAIT_TIMEOUT * USEC_PER_MSEC, false, + priv, reg, &val); - /* loop until the busy flag has cleared */ - do { - u32 val = qca8k_read(priv, reg); - int busy = val & mask; + /* Check if qca8k_read has failed for a different reason + * before returning -ETIMEDOUT + */ + if (ret < 0 && ret1 < 0) + return ret1; - if (!busy) - break; - cond_resched(); - } while (!time_after_eq(jiffies, timeout)); - - return time_after_eq(jiffies, timeout); + return ret; } -static void +static int qca8k_fdb_read(struct qca8k_priv *priv, struct qca8k_fdb *fdb) { - u32 reg[4]; - int i; + u32 reg[4], val; + int i, ret; /* load the ARL table into an array */ - for (i = 0; i < 4; i++) - reg[i] = qca8k_read(priv, QCA8K_REG_ATU_DATA0 + (i * 4)); + for (i = 0; i < 4; i++) { + ret = qca8k_read(priv, QCA8K_REG_ATU_DATA0 + (i * 4), &val); + if (ret < 0) + return ret; + + reg[i] = val; + } /* vid - 83:72 */ fdb->vid = (reg[2] >> QCA8K_ATU_VID_S) & QCA8K_ATU_VID_M; @@ -302,6 +331,8 @@ qca8k_fdb_read(struct qca8k_priv *priv, struct qca8k_fdb *fdb) fdb->mac[3] = (reg[0] >> QCA8K_ATU_ADDR3_S) & 0xff; fdb->mac[4] = (reg[0] >> QCA8K_ATU_ADDR4_S) & 0xff; fdb->mac[5] = reg[0] & 0xff; + + return 0; } static void @@ -334,6 +365,7 @@ static int qca8k_fdb_access(struct qca8k_priv *priv, enum qca8k_fdb_cmd cmd, int port) { u32 reg; + int ret; /* Set the command and FDB index */ reg = QCA8K_ATU_FUNC_BUSY; @@ -344,15 +376,20 @@ qca8k_fdb_access(struct qca8k_priv *priv, enum qca8k_fdb_cmd cmd, int port) } /* Write the function register triggering the table access */ - qca8k_write(priv, QCA8K_REG_ATU_FUNC, reg); + ret = qca8k_write(priv, QCA8K_REG_ATU_FUNC, reg); + if (ret) + return ret; /* wait for completion */ - if (qca8k_busy_wait(priv, QCA8K_REG_ATU_FUNC, QCA8K_ATU_FUNC_BUSY)) - return -1; + ret = qca8k_busy_wait(priv, QCA8K_REG_ATU_FUNC, QCA8K_ATU_FUNC_BUSY); + if (ret) + return ret; /* Check for table full violation when adding an entry */ if (cmd == QCA8K_FDB_LOAD) { - reg = qca8k_read(priv, QCA8K_REG_ATU_FUNC); + ret = qca8k_read(priv, QCA8K_REG_ATU_FUNC, ®); + if (ret < 0) + return ret; if (reg & QCA8K_ATU_FUNC_FULL) return -1; } @@ -367,10 +404,10 @@ qca8k_fdb_next(struct qca8k_priv *priv, struct qca8k_fdb *fdb, int port) qca8k_fdb_write(priv, fdb->vid, fdb->port_mask, fdb->mac, fdb->aging); ret = qca8k_fdb_access(priv, QCA8K_FDB_NEXT, port); - if (ret >= 0) - qca8k_fdb_read(priv, fdb); + if (ret < 0) + return ret; - return ret; + return qca8k_fdb_read(priv, fdb); } static int @@ -412,6 +449,7 @@ static int qca8k_vlan_access(struct qca8k_priv *priv, enum qca8k_vlan_cmd cmd, u16 vid) { u32 reg; + int ret; /* Set the command and VLAN index */ reg = QCA8K_VTU_FUNC1_BUSY; @@ -419,15 +457,20 @@ qca8k_vlan_access(struct qca8k_priv *priv, enum qca8k_vlan_cmd cmd, u16 vid) reg |= vid << QCA8K_VTU_FUNC1_VID_S; /* Write the function register triggering the table access */ - qca8k_write(priv, QCA8K_REG_VTU_FUNC1, reg); + ret = qca8k_write(priv, QCA8K_REG_VTU_FUNC1, reg); + if (ret) + return ret; /* wait for completion */ - if (qca8k_busy_wait(priv, QCA8K_REG_VTU_FUNC1, QCA8K_VTU_FUNC1_BUSY)) - return -ETIMEDOUT; + ret = qca8k_busy_wait(priv, QCA8K_REG_VTU_FUNC1, QCA8K_VTU_FUNC1_BUSY); + if (ret) + return ret; /* Check for table full violation when adding an entry */ if (cmd == QCA8K_VLAN_LOAD) { - reg = qca8k_read(priv, QCA8K_REG_VTU_FUNC1); + ret = qca8k_read(priv, QCA8K_REG_VTU_FUNC1, ®); + if (ret < 0) + return ret; if (reg & QCA8K_VTU_FUNC1_FULL) return -ENOMEM; } @@ -453,7 +496,9 @@ qca8k_vlan_add(struct qca8k_priv *priv, u8 port, u16 vid, bool untagged) if (ret < 0) goto out; - reg = qca8k_read(priv, QCA8K_REG_VTU_FUNC0); + ret = qca8k_read(priv, QCA8K_REG_VTU_FUNC0, ®); + if (ret < 0) + goto out; reg |= QCA8K_VTU_FUNC0_VALID | QCA8K_VTU_FUNC0_IVL_EN; reg &= ~(QCA8K_VTU_FUNC0_EG_MODE_MASK << QCA8K_VTU_FUNC0_EG_MODE_S(port)); if (untagged) @@ -463,7 +508,9 @@ qca8k_vlan_add(struct qca8k_priv *priv, u8 port, u16 vid, bool untagged) reg |= QCA8K_VTU_FUNC0_EG_MODE_TAG << QCA8K_VTU_FUNC0_EG_MODE_S(port); - qca8k_write(priv, QCA8K_REG_VTU_FUNC0, reg); + ret = qca8k_write(priv, QCA8K_REG_VTU_FUNC0, reg); + if (ret) + goto out; ret = qca8k_vlan_access(priv, QCA8K_VLAN_LOAD, vid); out: @@ -484,7 +531,9 @@ qca8k_vlan_del(struct qca8k_priv *priv, u8 port, u16 vid) if (ret < 0) goto out; - reg = qca8k_read(priv, QCA8K_REG_VTU_FUNC0); + ret = qca8k_read(priv, QCA8K_REG_VTU_FUNC0, ®); + if (ret < 0) + goto out; reg &= ~(3 << QCA8K_VTU_FUNC0_EG_MODE_S(port)); reg |= QCA8K_VTU_FUNC0_EG_MODE_NOT << QCA8K_VTU_FUNC0_EG_MODE_S(port); @@ -504,7 +553,9 @@ qca8k_vlan_del(struct qca8k_priv *priv, u8 port, u16 vid) if (del) { ret = qca8k_vlan_access(priv, QCA8K_VLAN_PURGE, vid); } else { - qca8k_write(priv, QCA8K_REG_VTU_FUNC0, reg); + ret = qca8k_write(priv, QCA8K_REG_VTU_FUNC0, reg); + if (ret) + goto out; ret = qca8k_vlan_access(priv, QCA8K_VLAN_LOAD, vid); } @@ -514,15 +565,29 @@ out: return ret; } -static void +static int qca8k_mib_init(struct qca8k_priv *priv) { + int ret; + mutex_lock(&priv->reg_mutex); - qca8k_reg_set(priv, QCA8K_REG_MIB, QCA8K_MIB_FLUSH | QCA8K_MIB_BUSY); - qca8k_busy_wait(priv, QCA8K_REG_MIB, QCA8K_MIB_BUSY); - qca8k_reg_set(priv, QCA8K_REG_MIB, QCA8K_MIB_CPU_KEEP); - qca8k_write(priv, QCA8K_REG_MODULE_EN, QCA8K_MODULE_EN_MIB); + ret = qca8k_reg_set(priv, QCA8K_REG_MIB, QCA8K_MIB_FLUSH | QCA8K_MIB_BUSY); + if (ret) + goto exit; + + ret = qca8k_busy_wait(priv, QCA8K_REG_MIB, QCA8K_MIB_BUSY); + if (ret) + goto exit; + + ret = qca8k_reg_set(priv, QCA8K_REG_MIB, QCA8K_MIB_CPU_KEEP); + if (ret) + goto exit; + + ret = qca8k_write(priv, QCA8K_REG_MODULE_EN, QCA8K_MODULE_EN_MIB); + +exit: mutex_unlock(&priv->reg_mutex); + return ret; } static void @@ -556,54 +621,109 @@ qca8k_port_to_phy(int port) } static int -qca8k_mdio_write(struct qca8k_priv *priv, int port, u32 regnum, u16 data) +qca8k_mdio_busy_wait(struct mii_bus *bus, u32 reg, u32 mask) { - u32 phy, val; + u16 r1, r2, page; + u32 val; + int ret, ret1; + + qca8k_split_addr(reg, &r1, &r2, &page); + + ret = read_poll_timeout(qca8k_mii_read32, ret1, !(val & mask), 0, + QCA8K_BUSY_WAIT_TIMEOUT * USEC_PER_MSEC, false, + bus, 0x10 | r2, r1, &val); + + /* Check if qca8k_read has failed for a different reason + * before returnting -ETIMEDOUT + */ + if (ret < 0 && ret1 < 0) + return ret1; + + return ret; +} + +static int +qca8k_mdio_write(struct mii_bus *salve_bus, int phy, int regnum, u16 data) +{ + struct qca8k_priv *priv = salve_bus->priv; + struct mii_bus *bus = priv->bus; + u16 r1, r2, page; + u32 val; + int ret; if (regnum >= QCA8K_MDIO_MASTER_MAX_REG) return -EINVAL; - /* callee is responsible for not passing bad ports, - * but we still would like to make spills impossible. - */ - phy = qca8k_port_to_phy(port) % PHY_MAX_ADDR; val = QCA8K_MDIO_MASTER_BUSY | QCA8K_MDIO_MASTER_EN | QCA8K_MDIO_MASTER_WRITE | QCA8K_MDIO_MASTER_PHY_ADDR(phy) | QCA8K_MDIO_MASTER_REG_ADDR(regnum) | QCA8K_MDIO_MASTER_DATA(data); - qca8k_write(priv, QCA8K_MDIO_MASTER_CTRL, val); + qca8k_split_addr(QCA8K_MDIO_MASTER_CTRL, &r1, &r2, &page); - return qca8k_busy_wait(priv, QCA8K_MDIO_MASTER_CTRL, - QCA8K_MDIO_MASTER_BUSY); + mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); + + ret = qca8k_set_page(bus, page); + if (ret) + goto exit; + + qca8k_mii_write32(bus, 0x10 | r2, r1, val); + + ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL, + QCA8K_MDIO_MASTER_BUSY); + +exit: + /* even if the busy_wait timeouts try to clear the MASTER_EN */ + qca8k_mii_write32(bus, 0x10 | r2, r1, 0); + + mutex_unlock(&bus->mdio_lock); + + return ret; } static int -qca8k_mdio_read(struct qca8k_priv *priv, int port, u32 regnum) +qca8k_mdio_read(struct mii_bus *salve_bus, int phy, int regnum) { - u32 phy, val; + struct qca8k_priv *priv = salve_bus->priv; + struct mii_bus *bus = priv->bus; + u16 r1, r2, page; + u32 val; + int ret; if (regnum >= QCA8K_MDIO_MASTER_MAX_REG) return -EINVAL; - /* callee is responsible for not passing bad ports, - * but we still would like to make spills impossible. - */ - phy = qca8k_port_to_phy(port) % PHY_MAX_ADDR; val = QCA8K_MDIO_MASTER_BUSY | QCA8K_MDIO_MASTER_EN | QCA8K_MDIO_MASTER_READ | QCA8K_MDIO_MASTER_PHY_ADDR(phy) | QCA8K_MDIO_MASTER_REG_ADDR(regnum); - qca8k_write(priv, QCA8K_MDIO_MASTER_CTRL, val); + qca8k_split_addr(QCA8K_MDIO_MASTER_CTRL, &r1, &r2, &page); - if (qca8k_busy_wait(priv, QCA8K_MDIO_MASTER_CTRL, - QCA8K_MDIO_MASTER_BUSY)) - return -ETIMEDOUT; + mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); - val = (qca8k_read(priv, QCA8K_MDIO_MASTER_CTRL) & - QCA8K_MDIO_MASTER_DATA_MASK); + ret = qca8k_set_page(bus, page); + if (ret) + goto exit; - return val; + qca8k_mii_write32(bus, 0x10 | r2, r1, val); + + ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL, + QCA8K_MDIO_MASTER_BUSY); + if (ret) + goto exit; + + ret = qca8k_mii_read32(bus, 0x10 | r2, r1, &val); + +exit: + /* even if the busy_wait timeouts try to clear the MASTER_EN */ + qca8k_mii_write32(bus, 0x10 | r2, r1, 0); + + mutex_unlock(&bus->mdio_lock); + + if (ret >= 0) + ret = val & QCA8K_MDIO_MASTER_DATA_MASK; + + return ret; } static int @@ -611,7 +731,14 @@ qca8k_phy_write(struct dsa_switch *ds, int port, int regnum, u16 data) { struct qca8k_priv *priv = ds->priv; - return qca8k_mdio_write(priv, port, regnum, data); + /* Check if the legacy mapping should be used and the + * port is not correctly mapped to the right PHY in the + * devicetree + */ + if (priv->legacy_phy_port_mapping) + port = qca8k_port_to_phy(port) % PHY_MAX_ADDR; + + return qca8k_mdio_write(priv->bus, port, regnum, data); } static int @@ -620,7 +747,14 @@ qca8k_phy_read(struct dsa_switch *ds, int port, int regnum) struct qca8k_priv *priv = ds->priv; int ret; - ret = qca8k_mdio_read(priv, port, regnum); + /* Check if the legacy mapping should be used and the + * port is not correctly mapped to the right PHY in the + * devicetree + */ + if (priv->legacy_phy_port_mapping) + port = qca8k_port_to_phy(port) % PHY_MAX_ADDR; + + ret = qca8k_mdio_read(priv->bus, port, regnum); if (ret < 0) return 0xffff; @@ -628,14 +762,44 @@ qca8k_phy_read(struct dsa_switch *ds, int port, int regnum) return ret; } +static int +qca8k_mdio_register(struct qca8k_priv *priv, struct device_node *mdio) +{ + struct dsa_switch *ds = priv->ds; + struct mii_bus *bus; + + bus = devm_mdiobus_alloc(ds->dev); + + if (!bus) + return -ENOMEM; + + bus->priv = (void *)priv; + bus->name = "qca8k slave mii"; + bus->read = qca8k_mdio_read; + bus->write = qca8k_mdio_write; + snprintf(bus->id, MII_BUS_ID_SIZE, "qca8k-%d", + ds->index); + + bus->parent = ds->dev; + bus->phy_mask = ~ds->phys_mii_mask; + + ds->slave_mii_bus = bus; + + return devm_of_mdiobus_register(priv->dev, bus, mdio); +} + static int qca8k_setup_mdio_bus(struct qca8k_priv *priv) { u32 internal_mdio_mask = 0, external_mdio_mask = 0, reg; - struct device_node *ports, *port; + struct device_node *ports, *port, *mdio; + phy_interface_t mode; int err; ports = of_get_child_by_name(priv->dev->of_node, "ports"); + if (!ports) + ports = of_get_child_by_name(priv->dev->of_node, "ethernet-ports"); + if (!ports) return -EINVAL; @@ -650,7 +814,10 @@ qca8k_setup_mdio_bus(struct qca8k_priv *priv) if (!dsa_is_user_port(priv->ds, reg)) continue; - if (of_property_read_bool(port, "phy-handle")) + of_get_phy_mode(port, &mode); + + if (of_property_read_bool(port, "phy-handle") && + mode != PHY_INTERFACE_MODE_INTERNAL) external_mdio_mask |= BIT(reg); else internal_mdio_mask |= BIT(reg); @@ -683,13 +850,89 @@ qca8k_setup_mdio_bus(struct qca8k_priv *priv) * a dt-overlay and driver reload changed the configuration */ - qca8k_reg_clear(priv, QCA8K_MDIO_MASTER_CTRL, - QCA8K_MDIO_MASTER_EN); + return qca8k_reg_clear(priv, QCA8K_MDIO_MASTER_CTRL, + QCA8K_MDIO_MASTER_EN); + } + + /* Check if the devicetree declare the port:phy mapping */ + mdio = of_get_child_by_name(priv->dev->of_node, "mdio"); + if (of_device_is_available(mdio)) { + err = qca8k_mdio_register(priv, mdio); + if (err) + of_node_put(mdio); + + return err; + } + + /* If a mapping can't be found the legacy mapping is used, + * using the qca8k_port_to_phy function + */ + priv->legacy_phy_port_mapping = true; + priv->ops.phy_read = qca8k_phy_read; + priv->ops.phy_write = qca8k_phy_write; + + return 0; +} + +static int +qca8k_setup_of_rgmii_delay(struct qca8k_priv *priv) +{ + struct device_node *port_dn; + phy_interface_t mode; + struct dsa_port *dp; + u32 val; + + /* CPU port is already checked */ + dp = dsa_to_port(priv->ds, 0); + + port_dn = dp->dn; + + /* Check if port 0 is set to the correct type */ + of_get_phy_mode(port_dn, &mode); + if (mode != PHY_INTERFACE_MODE_RGMII_ID && + mode != PHY_INTERFACE_MODE_RGMII_RXID && + mode != PHY_INTERFACE_MODE_RGMII_TXID) { + return 0; + } + + switch (mode) { + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + if (of_property_read_u32(port_dn, "rx-internal-delay-ps", &val)) + val = 2; + else + /* Switch regs accept value in ns, convert ps to ns */ + val = val / 1000; + + if (val > QCA8K_MAX_DELAY) { + dev_err(priv->dev, "rgmii rx delay is limited to a max value of 3ns, setting to the max value"); + val = 3; + } + + priv->rgmii_rx_delay = val; + /* Stop here if we need to check only for rx delay */ + if (mode != PHY_INTERFACE_MODE_RGMII_ID) + break; + + fallthrough; + case PHY_INTERFACE_MODE_RGMII_TXID: + if (of_property_read_u32(port_dn, "tx-internal-delay-ps", &val)) + val = 1; + else + /* Switch regs accept value in ns, convert ps to ns */ + val = val / 1000; + + if (val > QCA8K_MAX_DELAY) { + dev_err(priv->dev, "rgmii tx delay is limited to a max value of 3ns, setting to the max value"); + val = 3; + } + + priv->rgmii_tx_delay = val; + break; + default: return 0; } - priv->ops.phy_read = qca8k_phy_read; - priv->ops.phy_write = qca8k_phy_write; return 0; } @@ -698,10 +941,11 @@ qca8k_setup(struct dsa_switch *ds) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; int ret, i; + u32 mask; /* Make sure that port 0 is the cpu port */ if (!dsa_is_cpu_port(ds, 0)) { - pr_err("port 0 is not the CPU port\n"); + dev_err(priv->dev, "port 0 is not the CPU port"); return -EINVAL; } @@ -711,76 +955,163 @@ qca8k_setup(struct dsa_switch *ds) priv->regmap = devm_regmap_init(ds->dev, NULL, priv, &qca8k_regmap_config); if (IS_ERR(priv->regmap)) - pr_warn("regmap initialization failed"); + dev_warn(priv->dev, "regmap initialization failed"); ret = qca8k_setup_mdio_bus(priv); if (ret) return ret; + ret = qca8k_setup_of_rgmii_delay(priv); + if (ret) + return ret; + /* Enable CPU Port */ - qca8k_reg_set(priv, QCA8K_REG_GLOBAL_FW_CTRL0, - QCA8K_GLOBAL_FW_CTRL0_CPU_PORT_EN); + ret = qca8k_reg_set(priv, QCA8K_REG_GLOBAL_FW_CTRL0, + QCA8K_GLOBAL_FW_CTRL0_CPU_PORT_EN); + if (ret) { + dev_err(priv->dev, "failed enabling CPU port"); + return ret; + } /* Enable MIB counters */ - qca8k_mib_init(priv); + ret = qca8k_mib_init(priv); + if (ret) + dev_warn(priv->dev, "mib init failed"); /* Enable QCA header mode on the cpu port */ - qca8k_write(priv, QCA8K_REG_PORT_HDR_CTRL(QCA8K_CPU_PORT), - QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_TX_S | - QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_RX_S); + ret = qca8k_write(priv, QCA8K_REG_PORT_HDR_CTRL(QCA8K_CPU_PORT), + QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_TX_S | + QCA8K_PORT_HDR_CTRL_ALL << QCA8K_PORT_HDR_CTRL_RX_S); + if (ret) { + dev_err(priv->dev, "failed enabling QCA header mode"); + return ret; + } /* Disable forwarding by default on all ports */ - for (i = 0; i < QCA8K_NUM_PORTS; i++) - qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i), - QCA8K_PORT_LOOKUP_MEMBER, 0); + for (i = 0; i < QCA8K_NUM_PORTS; i++) { + ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i), + QCA8K_PORT_LOOKUP_MEMBER, 0); + if (ret) + return ret; + } /* Disable MAC by default on all ports */ for (i = 1; i < QCA8K_NUM_PORTS; i++) qca8k_port_set_status(priv, i, 0); /* Forward all unknown frames to CPU port for Linux processing */ - qca8k_write(priv, QCA8K_REG_GLOBAL_FW_CTRL1, - BIT(0) << QCA8K_GLOBAL_FW_CTRL1_IGMP_DP_S | - BIT(0) << QCA8K_GLOBAL_FW_CTRL1_BC_DP_S | - BIT(0) << QCA8K_GLOBAL_FW_CTRL1_MC_DP_S | - BIT(0) << QCA8K_GLOBAL_FW_CTRL1_UC_DP_S); + ret = qca8k_write(priv, QCA8K_REG_GLOBAL_FW_CTRL1, + BIT(0) << QCA8K_GLOBAL_FW_CTRL1_IGMP_DP_S | + BIT(0) << QCA8K_GLOBAL_FW_CTRL1_BC_DP_S | + BIT(0) << QCA8K_GLOBAL_FW_CTRL1_MC_DP_S | + BIT(0) << QCA8K_GLOBAL_FW_CTRL1_UC_DP_S); + if (ret) + return ret; /* Setup connection between CPU port & user ports */ for (i = 0; i < QCA8K_NUM_PORTS; i++) { /* CPU port gets connected to all user ports of the switch */ if (dsa_is_cpu_port(ds, i)) { - qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(QCA8K_CPU_PORT), - QCA8K_PORT_LOOKUP_MEMBER, dsa_user_ports(ds)); + ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(QCA8K_CPU_PORT), + QCA8K_PORT_LOOKUP_MEMBER, dsa_user_ports(ds)); + if (ret) + return ret; } /* Individual user ports get connected to CPU port only */ if (dsa_is_user_port(ds, i)) { int shift = 16 * (i % 2); - qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i), - QCA8K_PORT_LOOKUP_MEMBER, - BIT(QCA8K_CPU_PORT)); + ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(i), + QCA8K_PORT_LOOKUP_MEMBER, + BIT(QCA8K_CPU_PORT)); + if (ret) + return ret; /* Enable ARP Auto-learning by default */ - qca8k_reg_set(priv, QCA8K_PORT_LOOKUP_CTRL(i), - QCA8K_PORT_LOOKUP_LEARN); + ret = qca8k_reg_set(priv, QCA8K_PORT_LOOKUP_CTRL(i), + QCA8K_PORT_LOOKUP_LEARN); + if (ret) + return ret; /* For port based vlans to work we need to set the * default egress vid */ - qca8k_rmw(priv, QCA8K_EGRESS_VLAN(i), - 0xfff << shift, - QCA8K_PORT_VID_DEF << shift); - qca8k_write(priv, QCA8K_REG_PORT_VLAN_CTRL0(i), - QCA8K_PORT_VLAN_CVID(QCA8K_PORT_VID_DEF) | - QCA8K_PORT_VLAN_SVID(QCA8K_PORT_VID_DEF)); + ret = qca8k_rmw(priv, QCA8K_EGRESS_VLAN(i), + 0xfff << shift, + QCA8K_PORT_VID_DEF << shift); + if (ret) + return ret; + + ret = qca8k_write(priv, QCA8K_REG_PORT_VLAN_CTRL0(i), + QCA8K_PORT_VLAN_CVID(QCA8K_PORT_VID_DEF) | + QCA8K_PORT_VLAN_SVID(QCA8K_PORT_VID_DEF)); + if (ret) + return ret; } } + /* The port 5 of the qca8337 have some problem in flood condition. The + * original legacy driver had some specific buffer and priority settings + * for the different port suggested by the QCA switch team. Add this + * missing settings to improve switch stability under load condition. + * This problem is limited to qca8337 and other qca8k switch are not affected. + */ + if (priv->switch_id == QCA8K_ID_QCA8337) { + for (i = 0; i < QCA8K_NUM_PORTS; i++) { + switch (i) { + /* The 2 CPU port and port 5 requires some different + * priority than any other ports. + */ + case 0: + case 5: + case 6: + mask = QCA8K_PORT_HOL_CTRL0_EG_PRI0(0x3) | + QCA8K_PORT_HOL_CTRL0_EG_PRI1(0x4) | + QCA8K_PORT_HOL_CTRL0_EG_PRI2(0x4) | + QCA8K_PORT_HOL_CTRL0_EG_PRI3(0x4) | + QCA8K_PORT_HOL_CTRL0_EG_PRI4(0x6) | + QCA8K_PORT_HOL_CTRL0_EG_PRI5(0x8) | + QCA8K_PORT_HOL_CTRL0_EG_PORT(0x1e); + break; + default: + mask = QCA8K_PORT_HOL_CTRL0_EG_PRI0(0x3) | + QCA8K_PORT_HOL_CTRL0_EG_PRI1(0x4) | + QCA8K_PORT_HOL_CTRL0_EG_PRI2(0x6) | + QCA8K_PORT_HOL_CTRL0_EG_PRI3(0x8) | + QCA8K_PORT_HOL_CTRL0_EG_PORT(0x19); + } + qca8k_write(priv, QCA8K_REG_PORT_HOL_CTRL0(i), mask); + + mask = QCA8K_PORT_HOL_CTRL1_ING(0x6) | + QCA8K_PORT_HOL_CTRL1_EG_PRI_BUF_EN | + QCA8K_PORT_HOL_CTRL1_EG_PORT_BUF_EN | + QCA8K_PORT_HOL_CTRL1_WRED_EN; + qca8k_rmw(priv, QCA8K_REG_PORT_HOL_CTRL1(i), + QCA8K_PORT_HOL_CTRL1_ING_BUF | + QCA8K_PORT_HOL_CTRL1_EG_PRI_BUF_EN | + QCA8K_PORT_HOL_CTRL1_EG_PORT_BUF_EN | + QCA8K_PORT_HOL_CTRL1_WRED_EN, + mask); + } + } + + /* Special GLOBAL_FC_THRESH value are needed for ar8327 switch */ + if (priv->switch_id == QCA8K_ID_QCA8327) { + mask = QCA8K_GLOBAL_FC_GOL_XON_THRES(288) | + QCA8K_GLOBAL_FC_GOL_XOFF_THRES(496); + qca8k_rmw(priv, QCA8K_REG_GLOBAL_FC_THRESH, + QCA8K_GLOBAL_FC_GOL_XON_THRES_S | + QCA8K_GLOBAL_FC_GOL_XOFF_THRES_S, + mask); + } + /* Setup our port MTUs to match power on defaults */ for (i = 0; i < QCA8K_NUM_PORTS; i++) priv->port_mtu[i] = ETH_FRAME_LEN + ETH_FCS_LEN; - qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, ETH_FRAME_LEN + ETH_FCS_LEN); + ret = qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, ETH_FRAME_LEN + ETH_FCS_LEN); + if (ret) + dev_warn(priv->dev, "failed setting MTU settings"); /* Flush the FDB table */ qca8k_fdb_flush(priv); @@ -797,11 +1128,14 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, { struct qca8k_priv *priv = ds->priv; u32 reg, val; + int ret; switch (port) { case 0: /* 1st CPU port */ if (state->interface != PHY_INTERFACE_MODE_RGMII && state->interface != PHY_INTERFACE_MODE_RGMII_ID && + state->interface != PHY_INTERFACE_MODE_RGMII_TXID && + state->interface != PHY_INTERFACE_MODE_RGMII_RXID && state->interface != PHY_INTERFACE_MODE_SGMII) return; @@ -817,6 +1151,8 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, case 6: /* 2nd CPU port / external PHY */ if (state->interface != PHY_INTERFACE_MODE_RGMII && state->interface != PHY_INTERFACE_MODE_RGMII_ID && + state->interface != PHY_INTERFACE_MODE_RGMII_TXID && + state->interface != PHY_INTERFACE_MODE_RGMII_RXID && state->interface != PHY_INTERFACE_MODE_SGMII && state->interface != PHY_INTERFACE_MODE_1000BASEX) return; @@ -840,16 +1176,22 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, qca8k_write(priv, reg, QCA8K_PORT_PAD_RGMII_EN); break; case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_TXID: + case PHY_INTERFACE_MODE_RGMII_RXID: /* RGMII_ID needs internal delay. This is enabled through * PORT5_PAD_CTRL for all ports, rather than individual port * registers */ qca8k_write(priv, reg, QCA8K_PORT_PAD_RGMII_EN | - QCA8K_PORT_PAD_RGMII_TX_DELAY(QCA8K_MAX_DELAY) | - QCA8K_PORT_PAD_RGMII_RX_DELAY(QCA8K_MAX_DELAY)); - qca8k_write(priv, QCA8K_REG_PORT5_PAD_CTRL, + QCA8K_PORT_PAD_RGMII_TX_DELAY(priv->rgmii_tx_delay) | + QCA8K_PORT_PAD_RGMII_RX_DELAY(priv->rgmii_rx_delay) | + QCA8K_PORT_PAD_RGMII_TX_DELAY_EN | QCA8K_PORT_PAD_RGMII_RX_DELAY_EN); + /* QCA8337 requires to set rgmii rx delay */ + if (priv->switch_id == QCA8K_ID_QCA8337) + qca8k_write(priv, QCA8K_REG_PORT5_PAD_CTRL, + QCA8K_PORT_PAD_RGMII_RX_DELAY_EN); break; case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_1000BASEX: @@ -857,7 +1199,9 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, qca8k_write(priv, reg, QCA8K_PORT_PAD_SGMII_EN); /* Enable/disable SerDes auto-negotiation as necessary */ - val = qca8k_read(priv, QCA8K_REG_PWS); + ret = qca8k_read(priv, QCA8K_REG_PWS, &val); + if (ret) + return; if (phylink_autoneg_inband(mode)) val &= ~QCA8K_PWS_SERDES_AEN_DIS; else @@ -865,7 +1209,9 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, qca8k_write(priv, QCA8K_REG_PWS, val); /* Configure the SGMII parameters */ - val = qca8k_read(priv, QCA8K_REG_SGMII_CTRL); + ret = qca8k_read(priv, QCA8K_REG_SGMII_CTRL, &val); + if (ret) + return; val |= QCA8K_SGMII_EN_PLL | QCA8K_SGMII_EN_RX | QCA8K_SGMII_EN_TX | QCA8K_SGMII_EN_SD; @@ -903,6 +1249,8 @@ qca8k_phylink_validate(struct dsa_switch *ds, int port, if (state->interface != PHY_INTERFACE_MODE_NA && state->interface != PHY_INTERFACE_MODE_RGMII && state->interface != PHY_INTERFACE_MODE_RGMII_ID && + state->interface != PHY_INTERFACE_MODE_RGMII_TXID && + state->interface != PHY_INTERFACE_MODE_RGMII_RXID && state->interface != PHY_INTERFACE_MODE_SGMII) goto unsupported; break; @@ -913,13 +1261,16 @@ qca8k_phylink_validate(struct dsa_switch *ds, int port, case 5: /* Internal PHY */ if (state->interface != PHY_INTERFACE_MODE_NA && - state->interface != PHY_INTERFACE_MODE_GMII) + state->interface != PHY_INTERFACE_MODE_GMII && + state->interface != PHY_INTERFACE_MODE_INTERNAL) goto unsupported; break; case 6: /* 2nd CPU port / external PHY */ if (state->interface != PHY_INTERFACE_MODE_NA && state->interface != PHY_INTERFACE_MODE_RGMII && state->interface != PHY_INTERFACE_MODE_RGMII_ID && + state->interface != PHY_INTERFACE_MODE_RGMII_TXID && + state->interface != PHY_INTERFACE_MODE_RGMII_RXID && state->interface != PHY_INTERFACE_MODE_SGMII && state->interface != PHY_INTERFACE_MODE_1000BASEX) goto unsupported; @@ -955,8 +1306,11 @@ qca8k_phylink_mac_link_state(struct dsa_switch *ds, int port, { struct qca8k_priv *priv = ds->priv; u32 reg; + int ret; - reg = qca8k_read(priv, QCA8K_REG_PORT_STATUS(port)); + ret = qca8k_read(priv, QCA8K_REG_PORT_STATUS(port), ®); + if (ret < 0) + return ret; state->link = !!(reg & QCA8K_PORT_STATUS_LINK_UP); state->an_complete = state->link; @@ -1057,18 +1411,27 @@ qca8k_get_ethtool_stats(struct dsa_switch *ds, int port, { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; const struct qca8k_mib_desc *mib; - u32 reg, i; - u64 hi; + u32 reg, i, val; + u32 hi = 0; + int ret; for (i = 0; i < ARRAY_SIZE(ar8327_mib); i++) { mib = &ar8327_mib[i]; reg = QCA8K_PORT_MIB_COUNTER(port) + mib->offset; - data[i] = qca8k_read(priv, reg); + ret = qca8k_read(priv, reg, &val); + if (ret < 0) + continue; + if (mib->size == 2) { - hi = qca8k_read(priv, reg + 4); - data[i] |= hi << 32; + ret = qca8k_read(priv, reg + 4, &hi); + if (ret < 0) + continue; } + + data[i] = val; + if (mib->size == 2) + data[i] |= (u64)hi << 32; } } @@ -1087,17 +1450,22 @@ qca8k_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_eee *eee) struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; u32 lpi_en = QCA8K_REG_EEE_CTRL_LPI_EN(port); u32 reg; + int ret; mutex_lock(&priv->reg_mutex); - reg = qca8k_read(priv, QCA8K_REG_EEE_CTRL); + ret = qca8k_read(priv, QCA8K_REG_EEE_CTRL, ®); + if (ret < 0) + goto exit; + if (eee->eee_enabled) reg |= lpi_en; else reg &= ~lpi_en; - qca8k_write(priv, QCA8K_REG_EEE_CTRL, reg); - mutex_unlock(&priv->reg_mutex); + ret = qca8k_write(priv, QCA8K_REG_EEE_CTRL, reg); - return 0; +exit: + mutex_unlock(&priv->reg_mutex); + return ret; } static int @@ -1141,7 +1509,7 @@ qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; int port_mask = BIT(QCA8K_CPU_PORT); - int i; + int i, ret; for (i = 1; i < QCA8K_NUM_PORTS; i++) { if (dsa_to_port(ds, i)->bridge_dev != br) @@ -1149,17 +1517,20 @@ qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) /* Add this port to the portvlan mask of the other ports * in the bridge */ - qca8k_reg_set(priv, - QCA8K_PORT_LOOKUP_CTRL(i), - BIT(port)); + ret = qca8k_reg_set(priv, + QCA8K_PORT_LOOKUP_CTRL(i), + BIT(port)); + if (ret) + return ret; if (i != port) port_mask |= BIT(i); } - /* Add all other ports to this ports portvlan mask */ - qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), - QCA8K_PORT_LOOKUP_MEMBER, port_mask); - return 0; + /* Add all other ports to this ports portvlan mask */ + ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), + QCA8K_PORT_LOOKUP_MEMBER, port_mask); + + return ret; } static void @@ -1223,9 +1594,7 @@ qca8k_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu) mtu = priv->port_mtu[i]; /* Include L2 header / FCS length */ - qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, mtu + ETH_HLEN + ETH_FCS_LEN); - - return 0; + return qca8k_write(priv, QCA8K_MAX_FRAME_SIZE, mtu + ETH_HLEN + ETH_FCS_LEN); } static int @@ -1298,18 +1667,19 @@ qca8k_port_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack) { struct qca8k_priv *priv = ds->priv; + int ret; if (vlan_filtering) { - qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), - QCA8K_PORT_LOOKUP_VLAN_MODE, - QCA8K_PORT_LOOKUP_VLAN_MODE_SECURE); + ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), + QCA8K_PORT_LOOKUP_VLAN_MODE, + QCA8K_PORT_LOOKUP_VLAN_MODE_SECURE); } else { - qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), - QCA8K_PORT_LOOKUP_VLAN_MODE, - QCA8K_PORT_LOOKUP_VLAN_MODE_NONE); + ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), + QCA8K_PORT_LOOKUP_VLAN_MODE, + QCA8K_PORT_LOOKUP_VLAN_MODE_NONE); } - return 0; + return ret; } static int @@ -1320,7 +1690,7 @@ qca8k_port_vlan_add(struct dsa_switch *ds, int port, bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; struct qca8k_priv *priv = ds->priv; - int ret = 0; + int ret; ret = qca8k_vlan_add(priv, port, vlan->vid, untagged); if (ret) { @@ -1331,14 +1701,17 @@ qca8k_port_vlan_add(struct dsa_switch *ds, int port, if (pvid) { int shift = 16 * (port % 2); - qca8k_rmw(priv, QCA8K_EGRESS_VLAN(port), - 0xfff << shift, vlan->vid << shift); - qca8k_write(priv, QCA8K_REG_PORT_VLAN_CTRL0(port), - QCA8K_PORT_VLAN_CVID(vlan->vid) | - QCA8K_PORT_VLAN_SVID(vlan->vid)); + ret = qca8k_rmw(priv, QCA8K_EGRESS_VLAN(port), + 0xfff << shift, vlan->vid << shift); + if (ret) + return ret; + + ret = qca8k_write(priv, QCA8K_REG_PORT_VLAN_CTRL0(port), + QCA8K_PORT_VLAN_CVID(vlan->vid) | + QCA8K_PORT_VLAN_SVID(vlan->vid)); } - return 0; + return ret; } static int @@ -1346,7 +1719,7 @@ qca8k_port_vlan_del(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { struct qca8k_priv *priv = ds->priv; - int ret = 0; + int ret; ret = qca8k_vlan_del(priv, port, vlan->vid); if (ret) @@ -1355,6 +1728,22 @@ qca8k_port_vlan_del(struct dsa_switch *ds, int port, return ret; } +static u32 qca8k_get_phy_flags(struct dsa_switch *ds, int port) +{ + struct qca8k_priv *priv = ds->priv; + + /* Communicate to the phy internal driver the switch revision. + * Based on the switch revision different values needs to be + * set to the dbg and mmd reg on the phy. + * The first 2 bit are used to communicate the switch revision + * to the phy driver. + */ + if (port > 0 && port < 6) + return priv->switch_revision; + + return 0; +} + static enum dsa_tag_protocol qca8k_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) @@ -1388,13 +1777,44 @@ static const struct dsa_switch_ops qca8k_switch_ops = { .phylink_mac_config = qca8k_phylink_mac_config, .phylink_mac_link_down = qca8k_phylink_mac_link_down, .phylink_mac_link_up = qca8k_phylink_mac_link_up, + .get_phy_flags = qca8k_get_phy_flags, }; +static int qca8k_read_switch_id(struct qca8k_priv *priv) +{ + const struct qca8k_match_data *data; + u32 val; + u8 id; + int ret; + + /* get the switches ID from the compatible */ + data = of_device_get_match_data(priv->dev); + if (!data) + return -ENODEV; + + ret = qca8k_read(priv, QCA8K_REG_MASK_CTRL, &val); + if (ret < 0) + return -ENODEV; + + id = QCA8K_MASK_CTRL_DEVICE_ID(val & QCA8K_MASK_CTRL_DEVICE_ID_MASK); + if (id != data->id) { + dev_err(priv->dev, "Switch id detected %x but expected %x", id, data->id); + return -ENODEV; + } + + priv->switch_id = id; + + /* Save revision to communicate to the internal PHY driver */ + priv->switch_revision = (val & QCA8K_MASK_CTRL_REV_ID_MASK); + + return 0; +} + static int qca8k_sw_probe(struct mdio_device *mdiodev) { struct qca8k_priv *priv; - u32 id; + int ret; /* allocate the private data struct so that we can probe the switches * ID register @@ -1420,12 +1840,10 @@ qca8k_sw_probe(struct mdio_device *mdiodev) gpiod_set_value_cansleep(priv->reset_gpio, 0); } - /* read the switches ID register */ - id = qca8k_read(priv, QCA8K_REG_MASK_CTRL); - id >>= QCA8K_MASK_CTRL_ID_S; - id &= QCA8K_MASK_CTRL_ID_M; - if (id != QCA8K_ID_QCA8337) - return -ENODEV; + /* Check the detected switch id */ + ret = qca8k_read_switch_id(priv); + if (ret) + return ret; priv->ds = devm_kzalloc(&mdiodev->dev, sizeof(*priv->ds), GFP_KERNEL); if (!priv->ds) @@ -1490,9 +1908,18 @@ static int qca8k_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(qca8k_pm_ops, qca8k_suspend, qca8k_resume); +static const struct qca8k_match_data qca832x = { + .id = QCA8K_ID_QCA8327, +}; + +static const struct qca8k_match_data qca833x = { + .id = QCA8K_ID_QCA8337, +}; + static const struct of_device_id qca8k_of_match[] = { - { .compatible = "qca,qca8334" }, - { .compatible = "qca,qca8337" }, + { .compatible = "qca,qca8327", .data = &qca832x }, + { .compatible = "qca,qca8334", .data = &qca833x }, + { .compatible = "qca,qca8337", .data = &qca833x }, { /* sentinel */ }, }; diff --git a/drivers/net/dsa/qca8k.h b/drivers/net/dsa/qca8k.h index 7ca4b93e0bb5..ed3b05ad6745 100644 --- a/drivers/net/dsa/qca8k.h +++ b/drivers/net/dsa/qca8k.h @@ -15,9 +15,13 @@ #define QCA8K_NUM_PORTS 7 #define QCA8K_MAX_MTU 9000 +#define PHY_ID_QCA8327 0x004dd034 +#define QCA8K_ID_QCA8327 0x12 #define PHY_ID_QCA8337 0x004dd036 #define QCA8K_ID_QCA8337 0x13 +#define QCA8K_BUSY_WAIT_TIMEOUT 2000 + #define QCA8K_NUM_FDB_RECORDS 2048 #define QCA8K_CPU_PORT 0 @@ -26,18 +30,19 @@ /* Global control registers */ #define QCA8K_REG_MASK_CTRL 0x000 -#define QCA8K_MASK_CTRL_ID_M 0xff -#define QCA8K_MASK_CTRL_ID_S 8 +#define QCA8K_MASK_CTRL_REV_ID_MASK GENMASK(7, 0) +#define QCA8K_MASK_CTRL_REV_ID(x) ((x) >> 0) +#define QCA8K_MASK_CTRL_DEVICE_ID_MASK GENMASK(15, 8) +#define QCA8K_MASK_CTRL_DEVICE_ID(x) ((x) >> 8) #define QCA8K_REG_PORT0_PAD_CTRL 0x004 #define QCA8K_REG_PORT5_PAD_CTRL 0x008 #define QCA8K_REG_PORT6_PAD_CTRL 0x00c #define QCA8K_PORT_PAD_RGMII_EN BIT(26) -#define QCA8K_PORT_PAD_RGMII_TX_DELAY(x) \ - ((0x8 + (x & 0x3)) << 22) -#define QCA8K_PORT_PAD_RGMII_RX_DELAY(x) \ - ((0x10 + (x & 0x3)) << 20) -#define QCA8K_MAX_DELAY 3 +#define QCA8K_PORT_PAD_RGMII_TX_DELAY(x) ((x) << 22) +#define QCA8K_PORT_PAD_RGMII_RX_DELAY(x) ((x) << 20) +#define QCA8K_PORT_PAD_RGMII_TX_DELAY_EN BIT(25) #define QCA8K_PORT_PAD_RGMII_RX_DELAY_EN BIT(24) +#define QCA8K_MAX_DELAY 3 #define QCA8K_PORT_PAD_SGMII_EN BIT(7) #define QCA8K_REG_PWS 0x010 #define QCA8K_PWS_SERDES_AEN_DIS BIT(7) @@ -164,6 +169,36 @@ #define QCA8K_PORT_LOOKUP_STATE GENMASK(18, 16) #define QCA8K_PORT_LOOKUP_LEARN BIT(20) +#define QCA8K_REG_GLOBAL_FC_THRESH 0x800 +#define QCA8K_GLOBAL_FC_GOL_XON_THRES(x) ((x) << 16) +#define QCA8K_GLOBAL_FC_GOL_XON_THRES_S GENMASK(24, 16) +#define QCA8K_GLOBAL_FC_GOL_XOFF_THRES(x) ((x) << 0) +#define QCA8K_GLOBAL_FC_GOL_XOFF_THRES_S GENMASK(8, 0) + +#define QCA8K_REG_PORT_HOL_CTRL0(_i) (0x970 + (_i) * 0x8) +#define QCA8K_PORT_HOL_CTRL0_EG_PRI0_BUF GENMASK(3, 0) +#define QCA8K_PORT_HOL_CTRL0_EG_PRI0(x) ((x) << 0) +#define QCA8K_PORT_HOL_CTRL0_EG_PRI1_BUF GENMASK(7, 4) +#define QCA8K_PORT_HOL_CTRL0_EG_PRI1(x) ((x) << 4) +#define QCA8K_PORT_HOL_CTRL0_EG_PRI2_BUF GENMASK(11, 8) +#define QCA8K_PORT_HOL_CTRL0_EG_PRI2(x) ((x) << 8) +#define QCA8K_PORT_HOL_CTRL0_EG_PRI3_BUF GENMASK(15, 12) +#define QCA8K_PORT_HOL_CTRL0_EG_PRI3(x) ((x) << 12) +#define QCA8K_PORT_HOL_CTRL0_EG_PRI4_BUF GENMASK(19, 16) +#define QCA8K_PORT_HOL_CTRL0_EG_PRI4(x) ((x) << 16) +#define QCA8K_PORT_HOL_CTRL0_EG_PRI5_BUF GENMASK(23, 20) +#define QCA8K_PORT_HOL_CTRL0_EG_PRI5(x) ((x) << 20) +#define QCA8K_PORT_HOL_CTRL0_EG_PORT_BUF GENMASK(29, 24) +#define QCA8K_PORT_HOL_CTRL0_EG_PORT(x) ((x) << 24) + +#define QCA8K_REG_PORT_HOL_CTRL1(_i) (0x974 + (_i) * 0x8) +#define QCA8K_PORT_HOL_CTRL1_ING_BUF GENMASK(3, 0) +#define QCA8K_PORT_HOL_CTRL1_ING(x) ((x) << 0) +#define QCA8K_PORT_HOL_CTRL1_EG_PRI_BUF_EN BIT(6) +#define QCA8K_PORT_HOL_CTRL1_EG_PORT_BUF_EN BIT(7) +#define QCA8K_PORT_HOL_CTRL1_WRED_EN BIT(8) +#define QCA8K_PORT_HOL_CTRL1_EG_MIRROR_EN BIT(16) + /* Pkt edit registers */ #define QCA8K_EGRESS_VLAN(x) (0x0c70 + (4 * (x / 2))) @@ -211,7 +246,16 @@ struct ar8xxx_port_status { int enabled; }; +struct qca8k_match_data { + u8 id; +}; + struct qca8k_priv { + u8 switch_id; + u8 switch_revision; + u8 rgmii_tx_delay; + u8 rgmii_rx_delay; + bool legacy_phy_port_mapping; struct regmap *regmap; struct mii_bus *bus; struct ar8xxx_port_status port_sts[QCA8K_NUM_PORTS]; diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig index 5e83b365f17a..b29d41e5e1e7 100644 --- a/drivers/net/dsa/sja1105/Kconfig +++ b/drivers/net/dsa/sja1105/Kconfig @@ -3,11 +3,12 @@ config NET_DSA_SJA1105 tristate "NXP SJA1105 Ethernet switch family support" depends on NET_DSA && SPI select NET_DSA_TAG_SJA1105 + select PCS_XPCS select PACKING select CRC32 help - This is the driver for the NXP SJA1105 automotive Ethernet switch - family. These are 5-port devices and are managed over an SPI + This is the driver for the NXP SJA1105 (5-port) and SJA1110 (10-port) + automotive Ethernet switch family. These are managed over an SPI interface. Probing is handled based on OF bindings and so is the linkage to PHYLINK. The driver supports the following revisions: - SJA1105E (Gen. 1, No TT-Ethernet) @@ -16,6 +17,10 @@ tristate "NXP SJA1105 Ethernet switch family support" - SJA1105Q (Gen. 2, No SGMII, TT-Ethernet) - SJA1105R (Gen. 2, SGMII, No TT-Ethernet) - SJA1105S (Gen. 2, SGMII, TT-Ethernet) + - SJA1110A (Gen. 3, SGMII, TT-Ethernet, 100base-TX PHY, 10 ports) + - SJA1110B (Gen. 3, SGMII, TT-Ethernet, 100base-TX PHY, 9 ports) + - SJA1110C (Gen. 3, SGMII, TT-Ethernet, 100base-TX PHY, 7 ports) + - SJA1110D (Gen. 3, SGMII, TT-Ethernet, no 100base-TX PHY, 7 ports) config NET_DSA_SJA1105_PTP bool "Support for the PTP clock on the NXP SJA1105 Ethernet switch" diff --git a/drivers/net/dsa/sja1105/Makefile b/drivers/net/dsa/sja1105/Makefile index a860e3a910be..40d69e6c0bae 100644 --- a/drivers/net/dsa/sja1105/Makefile +++ b/drivers/net/dsa/sja1105/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_NET_DSA_SJA1105) += sja1105.o sja1105-objs := \ sja1105_spi.o \ sja1105_main.o \ + sja1105_mdio.o \ sja1105_flower.o \ sja1105_ethtool.o \ sja1105_devlink.o \ diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index f9e87fb33da0..221c7abdef0e 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -13,14 +13,12 @@ #include #include "sja1105_static_config.h" -#define SJA1105_NUM_PORTS 5 -#define SJA1105_NUM_TC 8 #define SJA1105ET_FDB_BIN_SIZE 4 /* The hardware value is in multiples of 10 ms. * The passed parameter is in multiples of 1 ms. */ #define SJA1105_AGEING_TIME_MS(ms) ((ms) / 10) -#define SJA1105_NUM_L2_POLICERS 45 +#define SJA1105_NUM_L2_POLICERS SJA1110_MAX_L2_POLICING_COUNT typedef enum { SPI_READ = 0, @@ -30,6 +28,14 @@ typedef enum { #include "sja1105_tas.h" #include "sja1105_ptp.h" +enum sja1105_stats_area { + MAC, + HL1, + HL2, + ETHER, + __MAX_SJA1105_STATS_AREA, +}; + /* Keeps the different addresses between E/T and P/Q/R/S */ struct sja1105_regs { u64 device_id; @@ -39,7 +45,6 @@ struct sja1105_regs { u64 rgu; u64 vl_status; u64 config; - u64 sgmii; u64 rmii_pll1; u64 ptppinst; u64 ptppindur; @@ -49,23 +54,41 @@ struct sja1105_regs { u64 ptpclkcorp; u64 ptpsyncts; u64 ptpschtm; - u64 ptpegr_ts[SJA1105_NUM_PORTS]; - u64 pad_mii_tx[SJA1105_NUM_PORTS]; - u64 pad_mii_rx[SJA1105_NUM_PORTS]; - u64 pad_mii_id[SJA1105_NUM_PORTS]; - u64 cgu_idiv[SJA1105_NUM_PORTS]; - u64 mii_tx_clk[SJA1105_NUM_PORTS]; - u64 mii_rx_clk[SJA1105_NUM_PORTS]; - u64 mii_ext_tx_clk[SJA1105_NUM_PORTS]; - u64 mii_ext_rx_clk[SJA1105_NUM_PORTS]; - u64 rgmii_tx_clk[SJA1105_NUM_PORTS]; - u64 rmii_ref_clk[SJA1105_NUM_PORTS]; - u64 rmii_ext_tx_clk[SJA1105_NUM_PORTS]; - u64 mac[SJA1105_NUM_PORTS]; - u64 mac_hl1[SJA1105_NUM_PORTS]; - u64 mac_hl2[SJA1105_NUM_PORTS]; - u64 ether_stats[SJA1105_NUM_PORTS]; - u64 qlevel[SJA1105_NUM_PORTS]; + u64 ptpegr_ts[SJA1105_MAX_NUM_PORTS]; + u64 pad_mii_tx[SJA1105_MAX_NUM_PORTS]; + u64 pad_mii_rx[SJA1105_MAX_NUM_PORTS]; + u64 pad_mii_id[SJA1105_MAX_NUM_PORTS]; + u64 cgu_idiv[SJA1105_MAX_NUM_PORTS]; + u64 mii_tx_clk[SJA1105_MAX_NUM_PORTS]; + u64 mii_rx_clk[SJA1105_MAX_NUM_PORTS]; + u64 mii_ext_tx_clk[SJA1105_MAX_NUM_PORTS]; + u64 mii_ext_rx_clk[SJA1105_MAX_NUM_PORTS]; + u64 rgmii_tx_clk[SJA1105_MAX_NUM_PORTS]; + u64 rmii_ref_clk[SJA1105_MAX_NUM_PORTS]; + u64 rmii_ext_tx_clk[SJA1105_MAX_NUM_PORTS]; + u64 stats[__MAX_SJA1105_STATS_AREA][SJA1105_MAX_NUM_PORTS]; + u64 mdio_100base_tx; + u64 mdio_100base_t1; + u64 pcs_base[SJA1105_MAX_NUM_PORTS]; +}; + +struct sja1105_mdio_private { + struct sja1105_private *priv; +}; + +enum { + SJA1105_SPEED_AUTO, + SJA1105_SPEED_10MBPS, + SJA1105_SPEED_100MBPS, + SJA1105_SPEED_1000MBPS, + SJA1105_SPEED_2500MBPS, + SJA1105_SPEED_MAX, +}; + +enum sja1105_internal_phy_t { + SJA1105_NO_PHY = 0, + SJA1105_PHY_BASE_TX, + SJA1105_PHY_BASE_T1, }; struct sja1105_info { @@ -85,6 +108,10 @@ struct sja1105_info { */ int ptpegr_ts_bytes; int num_cbs_shapers; + int max_frame_mem; + int num_ports; + bool multiple_cascade_ports; + enum dsa_tag_protocol tag_proto; const struct sja1105_dynamic_table_ops *dyn_ops; const struct sja1105_table_ops *static_ops; const struct sja1105_regs *regs; @@ -104,7 +131,20 @@ struct sja1105_info { const unsigned char *addr, u16 vid); void (*ptp_cmd_packing)(u8 *buf, struct sja1105_ptp_cmd *cmd, enum packing_op op); + bool (*rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); + void (*txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); + int (*clocking_setup)(struct sja1105_private *priv); + int (*pcs_mdio_read)(struct mii_bus *bus, int phy, int reg); + int (*pcs_mdio_write)(struct mii_bus *bus, int phy, int reg, u16 val); + int (*disable_microcontroller)(struct sja1105_private *priv); const char *name; + bool supports_mii[SJA1105_MAX_NUM_PORTS]; + bool supports_rmii[SJA1105_MAX_NUM_PORTS]; + bool supports_rgmii[SJA1105_MAX_NUM_PORTS]; + bool supports_sgmii[SJA1105_MAX_NUM_PORTS]; + bool supports_2500basex[SJA1105_MAX_NUM_PORTS]; + enum sja1105_internal_phy_t internal_phy[SJA1105_MAX_NUM_PORTS]; + const u64 port_speed[SJA1105_SPEED_MAX]; }; enum sja1105_key_type { @@ -202,20 +242,23 @@ enum sja1105_vlan_state { struct sja1105_private { struct sja1105_static_config static_config; - bool rgmii_rx_delay[SJA1105_NUM_PORTS]; - bool rgmii_tx_delay[SJA1105_NUM_PORTS]; + bool rgmii_rx_delay[SJA1105_MAX_NUM_PORTS]; + bool rgmii_tx_delay[SJA1105_MAX_NUM_PORTS]; + phy_interface_t phy_mode[SJA1105_MAX_NUM_PORTS]; + bool fixed_link[SJA1105_MAX_NUM_PORTS]; bool best_effort_vlan_filtering; unsigned long learn_ena; unsigned long ucast_egress_floods; unsigned long bcast_egress_floods; const struct sja1105_info *info; + size_t max_xfer_len; struct gpio_desc *reset_gpio; struct spi_device *spidev; struct dsa_switch *ds; struct list_head dsa_8021q_vlans; struct list_head bridge_vlans; struct sja1105_flow_block flow_block; - struct sja1105_port ports[SJA1105_NUM_PORTS]; + struct sja1105_port ports[SJA1105_MAX_NUM_PORTS]; /* Serializes transmission of management frames so that * the switch doesn't confuse them with one another. */ @@ -224,6 +267,10 @@ struct sja1105_private { enum sja1105_vlan_state vlan_state; struct devlink_region **regions; struct sja1105_cbs_entry *cbs; + struct mii_bus *mdio_base_t1; + struct mii_bus *mdio_base_tx; + struct mii_bus *mdio_pcs; + struct dw_xpcs *xpcs[SJA1105_MAX_NUM_PORTS]; struct sja1105_tagger_data tagger_data; struct sja1105_ptp_data ptp_data; struct sja1105_tas_data tas_data; @@ -253,6 +300,14 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, struct netlink_ext_ack *extack); void sja1105_frame_memory_partitioning(struct sja1105_private *priv); +/* From sja1105_mdio.c */ +int sja1105_mdiobus_register(struct dsa_switch *ds); +void sja1105_mdiobus_unregister(struct dsa_switch *ds); +int sja1105_pcs_mdio_read(struct mii_bus *bus, int phy, int reg); +int sja1105_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val); +int sja1110_pcs_mdio_read(struct mii_bus *bus, int phy, int reg); +int sja1110_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val); + /* From sja1105_devlink.c */ int sja1105_devlink_setup(struct dsa_switch *ds); void sja1105_devlink_teardown(struct dsa_switch *ds); @@ -286,6 +341,10 @@ extern const struct sja1105_info sja1105p_info; extern const struct sja1105_info sja1105q_info; extern const struct sja1105_info sja1105r_info; extern const struct sja1105_info sja1105s_info; +extern const struct sja1105_info sja1110a_info; +extern const struct sja1105_info sja1110b_info; +extern const struct sja1105_info sja1110c_info; +extern const struct sja1105_info sja1110d_info; /* From sja1105_clocking.c */ @@ -301,16 +360,11 @@ typedef enum { XMII_MODE_SGMII = 3, } sja1105_phy_interface_t; -typedef enum { - SJA1105_SPEED_10MBPS = 3, - SJA1105_SPEED_100MBPS = 2, - SJA1105_SPEED_1000MBPS = 1, - SJA1105_SPEED_AUTO = 0, -} sja1105_speed_t; - int sja1105pqrs_setup_rgmii_delay(const void *ctx, int port); +int sja1110_setup_rgmii_delay(const void *ctx, int port); int sja1105_clocking_setup_port(struct sja1105_private *priv, int port); int sja1105_clocking_setup(struct sja1105_private *priv); +int sja1110_disable_microcontroller(struct sja1105_private *priv); /* From sja1105_ethtool.c */ void sja1105_get_ethtool_stats(struct dsa_switch *ds, int port, u64 *data); @@ -331,6 +385,18 @@ enum sja1105_iotag { SJA1105_S_TAG = 1, /* Outer VLAN header */ }; +enum sja1110_vlan_type { + SJA1110_VLAN_INVALID = 0, + SJA1110_VLAN_C_TAG = 1, /* Single inner VLAN tag */ + SJA1110_VLAN_S_TAG = 2, /* Single outer VLAN tag */ + SJA1110_VLAN_D_TAG = 3, /* Double tagged, use outer tag for lookup */ +}; + +enum sja1110_shaper_type { + SJA1110_LEAKY_BUCKET_SHAPER = 0, + SJA1110_CBS_SHAPER = 1, +}; + u8 sja1105et_fdb_hash(struct sja1105_private *priv, const u8 *addr, u16 vid); int sja1105et_fdb_add(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid); diff --git a/drivers/net/dsa/sja1105/sja1105_clocking.c b/drivers/net/dsa/sja1105/sja1105_clocking.c index 2a9b8a6a5306..387a1f2f161c 100644 --- a/drivers/net/dsa/sja1105/sja1105_clocking.c +++ b/drivers/net/dsa/sja1105/sja1105_clocking.c @@ -6,6 +6,8 @@ #include "sja1105.h" #define SJA1105_SIZE_CGU_CMD 4 +#define SJA1110_BASE_MCSS_CLK SJA1110_CGU_ADDR(0x70) +#define SJA1110_BASE_TIMER_CLK SJA1110_CGU_ADDR(0x74) /* Common structure for CFG_PAD_MIIx_RX and CFG_PAD_MIIx_TX */ struct sja1105_cfg_pad_mii { @@ -61,6 +63,12 @@ struct sja1105_cgu_pll_ctrl { u64 pd; }; +struct sja1110_cgu_outclk { + u64 clksrc; + u64 autoblock; + u64 pd; +}; + enum { CLKSRC_MII0_TX_CLK = 0x00, CLKSRC_MII0_RX_CLK = 0x01, @@ -110,6 +118,9 @@ static int sja1105_cgu_idiv_config(struct sja1105_private *priv, int port, struct sja1105_cgu_idiv idiv; u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + if (regs->cgu_idiv[port] == SJA1105_RSV_ADDR) + return 0; + if (enabled && factor != 1 && factor != 10) { dev_err(dev, "idiv factor must be 1 or 10\n"); return -ERANGE; @@ -159,6 +170,9 @@ static int sja1105_cgu_mii_tx_clk_config(struct sja1105_private *priv, u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; int clksrc; + if (regs->mii_tx_clk[port] == SJA1105_RSV_ADDR) + return 0; + if (role == XMII_MAC) clksrc = mac_clk_sources[port]; else @@ -188,6 +202,9 @@ sja1105_cgu_mii_rx_clk_config(struct sja1105_private *priv, int port) CLKSRC_MII4_RX_CLK, }; + if (regs->mii_rx_clk[port] == SJA1105_RSV_ADDR) + return 0; + /* Payload for packed_buf */ mii_rx_clk.clksrc = clk_sources[port]; mii_rx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */ @@ -212,6 +229,9 @@ sja1105_cgu_mii_ext_tx_clk_config(struct sja1105_private *priv, int port) CLKSRC_IDIV4, }; + if (regs->mii_ext_tx_clk[port] == SJA1105_RSV_ADDR) + return 0; + /* Payload for packed_buf */ mii_ext_tx_clk.clksrc = clk_sources[port]; mii_ext_tx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */ @@ -236,6 +256,9 @@ sja1105_cgu_mii_ext_rx_clk_config(struct sja1105_private *priv, int port) CLKSRC_IDIV4, }; + if (regs->mii_ext_rx_clk[port] == SJA1105_RSV_ADDR) + return 0; + /* Payload for packed_buf */ mii_ext_rx_clk.clksrc = clk_sources[port]; mii_ext_rx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */ @@ -313,14 +336,17 @@ sja1105_cgu_pll_control_packing(void *buf, struct sja1105_cgu_pll_ctrl *cmd, } static int sja1105_cgu_rgmii_tx_clk_config(struct sja1105_private *priv, - int port, sja1105_speed_t speed) + int port, u64 speed) { const struct sja1105_regs *regs = priv->info->regs; struct sja1105_cgu_mii_ctrl txc; u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; int clksrc; - if (speed == SJA1105_SPEED_1000MBPS) { + if (regs->rgmii_tx_clk[port] == SJA1105_RSV_ADDR) + return 0; + + if (speed == priv->info->port_speed[SJA1105_SPEED_1000MBPS]) { clksrc = CLKSRC_PLL0; } else { int clk_sources[] = {CLKSRC_IDIV0, CLKSRC_IDIV1, CLKSRC_IDIV2, @@ -368,6 +394,9 @@ static int sja1105_rgmii_cfg_pad_tx_config(struct sja1105_private *priv, struct sja1105_cfg_pad_mii pad_mii_tx = {0}; u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + if (regs->pad_mii_tx[port] == SJA1105_RSV_ADDR) + return 0; + /* Payload */ pad_mii_tx.d32_os = 3; /* TXD[3:2] output stage: */ /* high noise/high speed */ @@ -394,6 +423,9 @@ static int sja1105_cfg_pad_rx_config(struct sja1105_private *priv, int port) struct sja1105_cfg_pad_mii pad_mii_rx = {0}; u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + if (regs->pad_mii_rx[port] == SJA1105_RSV_ADDR) + return 0; + /* Payload */ pad_mii_rx.d32_ih = 0; /* RXD[3:2] input stage hysteresis: */ /* non-Schmitt (default) */ @@ -437,6 +469,35 @@ sja1105_cfg_pad_mii_id_packing(void *buf, struct sja1105_cfg_pad_mii_id *cmd, sja1105_packing(buf, &cmd->txc_pd, 0, 0, size, op); } +static void +sja1110_cfg_pad_mii_id_packing(void *buf, struct sja1105_cfg_pad_mii_id *cmd, + enum packing_op op) +{ + const int size = SJA1105_SIZE_CGU_CMD; + u64 range = 4; + + /* Fields RXC_RANGE and TXC_RANGE select the input frequency range: + * 0 = 2.5MHz + * 1 = 25MHz + * 2 = 50MHz + * 3 = 125MHz + * 4 = Automatically determined by port speed. + * There's no point in defining a structure different than the one for + * SJA1105, so just hardcode the frequency range to automatic, just as + * before. + */ + sja1105_packing(buf, &cmd->rxc_stable_ovr, 26, 26, size, op); + sja1105_packing(buf, &cmd->rxc_delay, 25, 21, size, op); + sja1105_packing(buf, &range, 20, 18, size, op); + sja1105_packing(buf, &cmd->rxc_bypass, 17, 17, size, op); + sja1105_packing(buf, &cmd->rxc_pd, 16, 16, size, op); + sja1105_packing(buf, &cmd->txc_stable_ovr, 10, 10, size, op); + sja1105_packing(buf, &cmd->txc_delay, 9, 5, size, op); + sja1105_packing(buf, &range, 4, 2, size, op); + sja1105_packing(buf, &cmd->txc_bypass, 1, 1, size, op); + sja1105_packing(buf, &cmd->txc_pd, 0, 0, size, op); +} + /* Valid range in degrees is an integer between 73.8 and 101.7 */ static u64 sja1105_rgmii_delay(u64 phase) { @@ -495,40 +556,65 @@ int sja1105pqrs_setup_rgmii_delay(const void *ctx, int port) packed_buf, SJA1105_SIZE_CGU_CMD); } +int sja1110_setup_rgmii_delay(const void *ctx, int port) +{ + const struct sja1105_private *priv = ctx; + const struct sja1105_regs *regs = priv->info->regs; + struct sja1105_cfg_pad_mii_id pad_mii_id = {0}; + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + + pad_mii_id.rxc_pd = 1; + pad_mii_id.txc_pd = 1; + + if (priv->rgmii_rx_delay[port]) { + pad_mii_id.rxc_delay = sja1105_rgmii_delay(90); + /* The "BYPASS" bit in SJA1110 is actually a "don't bypass" */ + pad_mii_id.rxc_bypass = 1; + pad_mii_id.rxc_pd = 0; + } + + if (priv->rgmii_tx_delay[port]) { + pad_mii_id.txc_delay = sja1105_rgmii_delay(90); + pad_mii_id.txc_bypass = 1; + pad_mii_id.txc_pd = 0; + } + + sja1110_cfg_pad_mii_id_packing(packed_buf, &pad_mii_id, PACK); + + return sja1105_xfer_buf(priv, SPI_WRITE, regs->pad_mii_id[port], + packed_buf, SJA1105_SIZE_CGU_CMD); +} + static int sja1105_rgmii_clocking_setup(struct sja1105_private *priv, int port, sja1105_mii_role_t role) { struct device *dev = priv->ds->dev; struct sja1105_mac_config_entry *mac; - sja1105_speed_t speed; + u64 speed; int rc; mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries; speed = mac[port].speed; - dev_dbg(dev, "Configuring port %d RGMII at speed %dMbps\n", + dev_dbg(dev, "Configuring port %d RGMII at speed %lldMbps\n", port, speed); - switch (speed) { - case SJA1105_SPEED_1000MBPS: + if (speed == priv->info->port_speed[SJA1105_SPEED_1000MBPS]) { /* 1000Mbps, IDIV disabled (125 MHz) */ rc = sja1105_cgu_idiv_config(priv, port, false, 1); - break; - case SJA1105_SPEED_100MBPS: + } else if (speed == priv->info->port_speed[SJA1105_SPEED_100MBPS]) { /* 100Mbps, IDIV enabled, divide by 1 (25 MHz) */ rc = sja1105_cgu_idiv_config(priv, port, true, 1); - break; - case SJA1105_SPEED_10MBPS: + } else if (speed == priv->info->port_speed[SJA1105_SPEED_10MBPS]) { /* 10Mbps, IDIV enabled, divide by 10 (2.5 MHz) */ rc = sja1105_cgu_idiv_config(priv, port, true, 10); - break; - case SJA1105_SPEED_AUTO: + } else if (speed == priv->info->port_speed[SJA1105_SPEED_AUTO]) { /* Skip CGU configuration if there is no speed available * (e.g. link is not established yet) */ dev_dbg(dev, "Speed not available, skipping CGU config\n"); return 0; - default: + } else { rc = -EINVAL; } @@ -546,14 +632,9 @@ static int sja1105_rgmii_clocking_setup(struct sja1105_private *priv, int port, dev_err(dev, "Failed to configure Tx pad registers\n"); return rc; } + if (!priv->info->setup_rgmii_delay) return 0; - /* The role has no hardware effect for RGMII. However we use it as - * a proxy for this interface being a MAC-to-MAC connection, with - * the RGMII internal delays needing to be applied by us. - */ - if (role == XMII_MAC) - return 0; return priv->info->setup_rgmii_delay(priv, port); } @@ -572,6 +653,9 @@ static int sja1105_cgu_rmii_ref_clk_config(struct sja1105_private *priv, CLKSRC_MII4_TX_CLK, }; + if (regs->rmii_ref_clk[port] == SJA1105_RSV_ADDR) + return 0; + /* Payload for packed_buf */ ref_clk.clksrc = clk_sources[port]; ref_clk.autoblock = 1; /* Autoblock clk while changing clksrc */ @@ -589,6 +673,9 @@ sja1105_cgu_rmii_ext_tx_clk_config(struct sja1105_private *priv, int port) struct sja1105_cgu_mii_ctrl ext_tx_clk; u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + if (regs->rmii_ext_tx_clk[port] == SJA1105_RSV_ADDR) + return 0; + /* Payload for packed_buf */ ext_tx_clk.clksrc = CLKSRC_PLL1; ext_tx_clk.autoblock = 1; /* Autoblock clk while changing clksrc */ @@ -607,6 +694,9 @@ static int sja1105_cgu_rmii_pll_config(struct sja1105_private *priv) struct device *dev = priv->ds->dev; int rc; + if (regs->rmii_pll1 == SJA1105_RSV_ADDR) + return 0; + /* PLL1 must be enabled and output 50 Mhz. * This is done by writing first 0x0A010941 to * the PLL_1_C register and then deasserting @@ -721,12 +811,52 @@ int sja1105_clocking_setup_port(struct sja1105_private *priv, int port) int sja1105_clocking_setup(struct sja1105_private *priv) { + struct dsa_switch *ds = priv->ds; int port, rc; - for (port = 0; port < SJA1105_NUM_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { rc = sja1105_clocking_setup_port(priv, port); if (rc < 0) return rc; } return 0; } + +static void +sja1110_cgu_outclk_packing(void *buf, struct sja1110_cgu_outclk *outclk, + enum packing_op op) +{ + const int size = 4; + + sja1105_packing(buf, &outclk->clksrc, 27, 24, size, op); + sja1105_packing(buf, &outclk->autoblock, 11, 11, size, op); + sja1105_packing(buf, &outclk->pd, 0, 0, size, op); +} + +int sja1110_disable_microcontroller(struct sja1105_private *priv) +{ + u8 packed_buf[SJA1105_SIZE_CGU_CMD] = {0}; + struct sja1110_cgu_outclk outclk_6_c = { + .clksrc = 0x3, + .pd = true, + }; + struct sja1110_cgu_outclk outclk_7_c = { + .clksrc = 0x5, + .pd = true, + }; + int rc; + + /* Power down the BASE_TIMER_CLK to disable the watchdog timer */ + sja1110_cgu_outclk_packing(packed_buf, &outclk_7_c, PACK); + + rc = sja1105_xfer_buf(priv, SPI_WRITE, SJA1110_BASE_TIMER_CLK, + packed_buf, SJA1105_SIZE_CGU_CMD); + if (rc) + return rc; + + /* Power down the BASE_MCSS_CLOCK to gate the microcontroller off */ + sja1110_cgu_outclk_packing(packed_buf, &outclk_6_c, PACK); + + return sja1105_xfer_buf(priv, SPI_WRITE, SJA1110_BASE_MCSS_CLK, + packed_buf, SJA1105_SIZE_CGU_CMD); +} diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c index 12cd04b56803..56fead68ea9f 100644 --- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c @@ -78,6 +78,9 @@ * on its ENTRY portion, as a result of a SPI write command. * Only the TCAM-based FDB table on SJA1105 P/Q/R/S supports * this. + * OP_VALID_ANYWAY: Reading some tables through the dynamic config + * interface is possible even if the VALIDENT bit is not + * set in the writeback. So don't error out in that case. * - .max_entry_count: The number of entries, counting from zero, that can be * reconfigured through the dynamic interface. If a static * table can be reconfigured at all dynamically, this @@ -103,6 +106,9 @@ #define SJA1105PQRS_SIZE_VL_LOOKUP_DYN_CMD \ (SJA1105_SIZE_DYN_CMD + SJA1105_SIZE_VL_LOOKUP_ENTRY) +#define SJA1110_SIZE_VL_POLICING_DYN_CMD \ + (SJA1105_SIZE_DYN_CMD + SJA1105_SIZE_VL_POLICING_ENTRY) + #define SJA1105ET_SIZE_MAC_CONFIG_DYN_ENTRY \ SJA1105_SIZE_DYN_CMD @@ -112,9 +118,15 @@ #define SJA1105PQRS_SIZE_L2_LOOKUP_DYN_CMD \ (SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY) +#define SJA1110_SIZE_L2_LOOKUP_DYN_CMD \ + (SJA1105_SIZE_DYN_CMD + SJA1110_SIZE_L2_LOOKUP_ENTRY) + #define SJA1105_SIZE_VLAN_LOOKUP_DYN_CMD \ (SJA1105_SIZE_DYN_CMD + 4 + SJA1105_SIZE_VLAN_LOOKUP_ENTRY) +#define SJA1110_SIZE_VLAN_LOOKUP_DYN_CMD \ + (SJA1105_SIZE_DYN_CMD + SJA1110_SIZE_VLAN_LOOKUP_ENTRY) + #define SJA1105_SIZE_L2_FORWARDING_DYN_CMD \ (SJA1105_SIZE_DYN_CMD + SJA1105_SIZE_L2_FORWARDING_ENTRY) @@ -130,12 +142,18 @@ #define SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_DYN_CMD \ (SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY) +#define SJA1110_SIZE_L2_LOOKUP_PARAMS_DYN_CMD \ + (SJA1105_SIZE_DYN_CMD + SJA1110_SIZE_L2_LOOKUP_PARAMS_ENTRY) + #define SJA1105ET_SIZE_GENERAL_PARAMS_DYN_CMD \ SJA1105_SIZE_DYN_CMD #define SJA1105PQRS_SIZE_GENERAL_PARAMS_DYN_CMD \ (SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY) +#define SJA1110_SIZE_GENERAL_PARAMS_DYN_CMD \ + (SJA1105_SIZE_DYN_CMD + SJA1110_SIZE_GENERAL_PARAMS_ENTRY) + #define SJA1105PQRS_SIZE_AVB_PARAMS_DYN_CMD \ (SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_AVB_PARAMS_ENTRY) @@ -148,8 +166,17 @@ #define SJA1105PQRS_SIZE_CBS_DYN_CMD \ (SJA1105_SIZE_DYN_CMD + SJA1105PQRS_SIZE_CBS_ENTRY) +#define SJA1110_SIZE_XMII_PARAMS_DYN_CMD \ + SJA1110_SIZE_XMII_PARAMS_ENTRY + +#define SJA1110_SIZE_L2_POLICING_DYN_CMD \ + (SJA1105_SIZE_DYN_CMD + SJA1105_SIZE_L2_POLICING_ENTRY) + +#define SJA1110_SIZE_L2_FORWARDING_PARAMS_DYN_CMD \ + SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY + #define SJA1105_MAX_DYN_CMD_SIZE \ - SJA1105PQRS_SIZE_GENERAL_PARAMS_DYN_CMD + SJA1110_SIZE_GENERAL_PARAMS_DYN_CMD struct sja1105_dyn_cmd { bool search; @@ -194,6 +221,19 @@ sja1105pqrs_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, sja1105_packing(p, &cmd->index, 9, 0, size, op); } +static void +sja1110_vl_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->errors, 29, 29, size, op); + sja1105_packing(p, &cmd->index, 11, 0, size, op); +} + static size_t sja1105et_vl_lookup_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -206,11 +246,23 @@ static size_t sja1105et_vl_lookup_entry_packing(void *buf, void *entry_ptr, } static void -sja1105pqrs_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, - enum packing_op op) +sja1110_vl_policing_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) { - u8 *p = buf + SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY; + u8 *p = buf + SJA1105_SIZE_VL_LOOKUP_ENTRY; const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->index, 11, 0, size, op); +} + +static void +sja1105pqrs_common_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op, int entry_size) +{ + const int size = SJA1105_SIZE_DYN_CMD; + u8 *p = buf + entry_size; u64 hostcmd; sja1105_packing(p, &cmd->valid, 31, 31, size, op); @@ -265,6 +317,24 @@ sja1105pqrs_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY, op); } +static void +sja1105pqrs_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + int size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY; + + return sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, size); +} + +static void +sja1110_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + int size = SJA1110_SIZE_L2_LOOKUP_ENTRY; + + return sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, size); +} + /* The switch is so retarded that it makes our command/entry abstraction * crumble apart. * @@ -323,6 +393,18 @@ sja1105pqrs_dyn_l2_lookup_entry_packing(void *buf, void *entry_ptr, return sja1105pqrs_l2_lookup_entry_packing(buf, entry_ptr, op); } +static size_t sja1110_dyn_l2_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_l2_lookup_entry *entry = entry_ptr; + u8 *cmd = buf + SJA1110_SIZE_L2_LOOKUP_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(cmd, &entry->lockeds, 28, 28, size, op); + + return sja1110_l2_lookup_entry_packing(buf, entry_ptr, op); +} + static void sja1105et_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, enum packing_op op) @@ -434,6 +516,39 @@ sja1105_vlan_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, SJA1105_SIZE_VLAN_LOOKUP_ENTRY, op); } +/* In SJA1110 there is no gap between the command and the data, yay... */ +static void +sja1110_vlan_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1110_SIZE_VLAN_LOOKUP_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + u64 type_entry = 0; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->errors, 29, 29, size, op); + /* Hack: treat 'vlanid' field of struct sja1105_vlan_lookup_entry as + * cmd->index. + */ + sja1105_packing(buf, &cmd->index, 38, 27, + SJA1110_SIZE_VLAN_LOOKUP_ENTRY, op); + + /* But the VALIDENT bit has disappeared, now we are supposed to + * invalidate an entry through the TYPE_ENTRY field of the entry.. + * This is a hack to transform the non-zero quality of the TYPE_ENTRY + * field into a VALIDENT bit. + */ + if (op == PACK && !cmd->valident) { + sja1105_packing(buf, &type_entry, 40, 39, + SJA1110_SIZE_VLAN_LOOKUP_ENTRY, PACK); + } else if (op == UNPACK) { + sja1105_packing(buf, &type_entry, 40, 39, + SJA1110_SIZE_VLAN_LOOKUP_ENTRY, UNPACK); + cmd->valident = !!type_entry; + } +} + static void sja1105_l2_forwarding_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, enum packing_op op) @@ -447,6 +562,19 @@ sja1105_l2_forwarding_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, sja1105_packing(p, &cmd->index, 4, 0, size, op); } +static void +sja1110_l2_forwarding_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105_SIZE_L2_FORWARDING_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->errors, 29, 29, size, op); + sja1105_packing(p, &cmd->index, 4, 0, size, op); +} + static void sja1105et_mac_config_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, enum packing_op op) @@ -501,6 +629,19 @@ sja1105pqrs_mac_config_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, sja1105_packing(p, &cmd->index, 2, 0, size, op); } +static void +sja1110_mac_config_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->errors, 29, 29, size, op); + sja1105_packing(p, &cmd->index, 3, 0, size, op); +} + static void sja1105et_l2_lookup_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, enum packing_op op) @@ -533,6 +674,18 @@ sja1105pqrs_l2_lookup_params_cmd_packing(void *buf, sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); } +static void +sja1110_l2_lookup_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1110_SIZE_L2_LOOKUP_PARAMS_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->errors, 29, 29, size, op); +} + static void sja1105et_general_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, enum packing_op op) @@ -567,6 +720,18 @@ sja1105pqrs_general_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, sja1105_packing(p, &cmd->rdwrset, 28, 28, size, op); } +static void +sja1110_general_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1110_SIZE_GENERAL_PARAMS_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->errors, 29, 29, size, op); +} + static void sja1105pqrs_avb_params_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, enum packing_op op) @@ -593,6 +758,20 @@ sja1105_retagging_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, sja1105_packing(p, &cmd->index, 5, 0, size, op); } +static void +sja1110_retagging_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105_SIZE_RETAGGING_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->errors, 29, 29, size, op); + sja1105_packing(p, &cmd->valident, 28, 28, size, op); + sja1105_packing(p, &cmd->index, 4, 0, size, op); +} + static void sja1105et_cbs_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, enum packing_op op) { @@ -632,6 +811,18 @@ static void sja1105pqrs_cbs_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, sja1105_packing(p, &cmd->index, 3, 0, size, op); } +static void sja1110_cbs_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105PQRS_SIZE_CBS_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->errors, 29, 29, size, op); + sja1105_packing(p, &cmd->index, 7, 0, size, op); +} + static size_t sja1105pqrs_cbs_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -647,10 +838,44 @@ static size_t sja1105pqrs_cbs_entry_packing(void *buf, void *entry_ptr, return size; } +static size_t sja1110_cbs_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105PQRS_SIZE_CBS_ENTRY; + struct sja1105_cbs_entry *entry = entry_ptr; + u64 entry_type = SJA1110_CBS_SHAPER; + + sja1105_packing(buf, &entry_type, 159, 159, size, op); + sja1105_packing(buf, &entry->credit_lo, 151, 120, size, op); + sja1105_packing(buf, &entry->credit_hi, 119, 88, size, op); + sja1105_packing(buf, &entry->send_slope, 87, 56, size, op); + sja1105_packing(buf, &entry->idle_slope, 55, 24, size, op); + return size; +} + +static void sja1110_dummy_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ +} + +static void +sja1110_l2_policing_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd, + enum packing_op op) +{ + u8 *p = buf + SJA1105_SIZE_L2_POLICING_ENTRY; + const int size = SJA1105_SIZE_DYN_CMD; + + sja1105_packing(p, &cmd->valid, 31, 31, size, op); + sja1105_packing(p, &cmd->rdwrset, 30, 30, size, op); + sja1105_packing(p, &cmd->errors, 29, 29, size, op); + sja1105_packing(p, &cmd->index, 6, 0, size, op); +} + #define OP_READ BIT(0) #define OP_WRITE BIT(1) #define OP_DEL BIT(2) #define OP_SEARCH BIT(3) +#define OP_VALID_ANYWAY BIT(4) /* SJA1105E/T: First generation */ const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = { @@ -673,7 +898,7 @@ const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = { [BLK_IDX_MGMT_ROUTE] = { .entry_packing = sja1105et_mgmt_route_entry_packing, .cmd_packing = sja1105et_mgmt_route_cmd_packing, - .access = (OP_READ | OP_WRITE), + .access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY), .max_entry_count = SJA1105_NUM_PORTS, .packed_size = SJA1105ET_SIZE_L2_LOOKUP_DYN_CMD, .addr = 0x20, @@ -757,7 +982,7 @@ const struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN] = { [BLK_IDX_MGMT_ROUTE] = { .entry_packing = sja1105pqrs_mgmt_route_entry_packing, .cmd_packing = sja1105pqrs_mgmt_route_cmd_packing, - .access = (OP_READ | OP_WRITE | OP_DEL | OP_SEARCH), + .access = (OP_READ | OP_WRITE | OP_DEL | OP_SEARCH | OP_VALID_ANYWAY), .max_entry_count = SJA1105_NUM_PORTS, .packed_size = SJA1105PQRS_SIZE_L2_LOOKUP_DYN_CMD, .addr = 0x24, @@ -828,6 +1053,122 @@ const struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN] = { }, }; +/* SJA1110: Third generation */ +const struct sja1105_dynamic_table_ops sja1110_dyn_ops[BLK_IDX_MAX_DYN] = { + [BLK_IDX_VL_LOOKUP] = { + .entry_packing = sja1110_vl_lookup_entry_packing, + .cmd_packing = sja1110_vl_lookup_cmd_packing, + .access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY), + .max_entry_count = SJA1110_MAX_VL_LOOKUP_COUNT, + .packed_size = SJA1105PQRS_SIZE_VL_LOOKUP_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0x124), + }, + [BLK_IDX_VL_POLICING] = { + .entry_packing = sja1110_vl_policing_entry_packing, + .cmd_packing = sja1110_vl_policing_cmd_packing, + .access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY), + .max_entry_count = SJA1110_MAX_VL_POLICING_COUNT, + .packed_size = SJA1110_SIZE_VL_POLICING_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0x310), + }, + [BLK_IDX_L2_LOOKUP] = { + .entry_packing = sja1110_dyn_l2_lookup_entry_packing, + .cmd_packing = sja1110_l2_lookup_cmd_packing, + .access = (OP_READ | OP_WRITE | OP_DEL | OP_SEARCH), + .max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT, + .packed_size = SJA1110_SIZE_L2_LOOKUP_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0x8c), + }, + [BLK_IDX_VLAN_LOOKUP] = { + .entry_packing = sja1110_vlan_lookup_entry_packing, + .cmd_packing = sja1110_vlan_lookup_cmd_packing, + .access = (OP_READ | OP_WRITE | OP_DEL), + .max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT, + .packed_size = SJA1110_SIZE_VLAN_LOOKUP_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0xb4), + }, + [BLK_IDX_L2_FORWARDING] = { + .entry_packing = sja1110_l2_forwarding_entry_packing, + .cmd_packing = sja1110_l2_forwarding_cmd_packing, + .max_entry_count = SJA1110_MAX_L2_FORWARDING_COUNT, + .access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY), + .packed_size = SJA1105_SIZE_L2_FORWARDING_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0xa8), + }, + [BLK_IDX_MAC_CONFIG] = { + .entry_packing = sja1110_mac_config_entry_packing, + .cmd_packing = sja1110_mac_config_cmd_packing, + .max_entry_count = SJA1110_MAX_MAC_CONFIG_COUNT, + .access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY), + .packed_size = SJA1105PQRS_SIZE_MAC_CONFIG_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0x134), + }, + [BLK_IDX_L2_LOOKUP_PARAMS] = { + .entry_packing = sja1110_l2_lookup_params_entry_packing, + .cmd_packing = sja1110_l2_lookup_params_cmd_packing, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT, + .access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY), + .packed_size = SJA1110_SIZE_L2_LOOKUP_PARAMS_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0x158), + }, + [BLK_IDX_AVB_PARAMS] = { + .entry_packing = sja1105pqrs_avb_params_entry_packing, + .cmd_packing = sja1105pqrs_avb_params_cmd_packing, + .max_entry_count = SJA1105_MAX_AVB_PARAMS_COUNT, + .access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY), + .packed_size = SJA1105PQRS_SIZE_AVB_PARAMS_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0x2000C), + }, + [BLK_IDX_GENERAL_PARAMS] = { + .entry_packing = sja1110_general_params_entry_packing, + .cmd_packing = sja1110_general_params_cmd_packing, + .max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT, + .access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY), + .packed_size = SJA1110_SIZE_GENERAL_PARAMS_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0xe8), + }, + [BLK_IDX_RETAGGING] = { + .entry_packing = sja1110_retagging_entry_packing, + .cmd_packing = sja1110_retagging_cmd_packing, + .max_entry_count = SJA1105_MAX_RETAGGING_COUNT, + .access = (OP_READ | OP_WRITE | OP_DEL), + .packed_size = SJA1105_SIZE_RETAGGING_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0xdc), + }, + [BLK_IDX_CBS] = { + .entry_packing = sja1110_cbs_entry_packing, + .cmd_packing = sja1110_cbs_cmd_packing, + .max_entry_count = SJA1110_MAX_CBS_COUNT, + .access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY), + .packed_size = SJA1105PQRS_SIZE_CBS_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0xc4), + }, + [BLK_IDX_XMII_PARAMS] = { + .entry_packing = sja1110_xmii_params_entry_packing, + .cmd_packing = sja1110_dummy_cmd_packing, + .max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT, + .access = (OP_READ | OP_VALID_ANYWAY), + .packed_size = SJA1110_SIZE_XMII_PARAMS_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0x3c), + }, + [BLK_IDX_L2_POLICING] = { + .entry_packing = sja1110_l2_policing_entry_packing, + .cmd_packing = sja1110_l2_policing_cmd_packing, + .max_entry_count = SJA1110_MAX_L2_POLICING_COUNT, + .access = (OP_READ | OP_WRITE | OP_VALID_ANYWAY), + .packed_size = SJA1110_SIZE_L2_POLICING_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0x2fc), + }, + [BLK_IDX_L2_FORWARDING_PARAMS] = { + .entry_packing = sja1110_l2_forwarding_params_entry_packing, + .cmd_packing = sja1110_dummy_cmd_packing, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT, + .access = (OP_READ | OP_VALID_ANYWAY), + .packed_size = SJA1110_SIZE_L2_FORWARDING_PARAMS_DYN_CMD, + .addr = SJA1110_SPI_ADDR(0x20000), + }, +}; + /* Provides read access to the settings through the dynamic interface * of the switch. * @blk_idx is used as key to select from the sja1105_dynamic_table_ops. @@ -911,11 +1252,8 @@ int sja1105_dynamic_config_read(struct sja1105_private *priv, cmd = (struct sja1105_dyn_cmd) {0}; ops->cmd_packing(packed_buf, &cmd, UNPACK); - /* UM10944: [valident] will always be found cleared - * during a read access with MGMTROUTE set. - * So don't error out in that case. - */ - if (!cmd.valident && blk_idx != BLK_IDX_MGMT_ROUTE) + + if (!cmd.valident && !(ops->access & OP_VALID_ANYWAY)) return -ENOENT; cpu_relax(); } while (cmd.valid && --retries); diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.h b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h index 28d4eb5efb8b..a1472f80a059 100644 --- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.h +++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h @@ -36,5 +36,6 @@ struct sja1105_mgmt_entry { extern const struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN]; extern const struct sja1105_dynamic_table_ops sja1105pqrs_dyn_ops[BLK_IDX_MAX_DYN]; +extern const struct sja1105_dynamic_table_ops sja1110_dyn_ops[BLK_IDX_MAX_DYN]; #endif diff --git a/drivers/net/dsa/sja1105/sja1105_ethtool.c b/drivers/net/dsa/sja1105/sja1105_ethtool.c index 9133a831ec79..decc6c931dc1 100644 --- a/drivers/net/dsa/sja1105/sja1105_ethtool.c +++ b/drivers/net/dsa/sja1105/sja1105_ethtool.c @@ -3,552 +3,627 @@ */ #include "sja1105.h" -#define SJA1105_SIZE_MAC_AREA (0x02 * 4) -#define SJA1105_SIZE_HL1_AREA (0x10 * 4) -#define SJA1105_SIZE_HL2_AREA (0x4 * 4) -#define SJA1105_SIZE_QLEVEL_AREA (0x8 * 4) /* 0x4 to 0xB */ -#define SJA1105_SIZE_ETHER_AREA (0x17 * 4) - -struct sja1105_port_status_mac { - u64 n_runt; - u64 n_soferr; - u64 n_alignerr; - u64 n_miierr; - u64 typeerr; - u64 sizeerr; - u64 tctimeout; - u64 priorerr; - u64 nomaster; - u64 memov; - u64 memerr; - u64 invtyp; - u64 intcyov; - u64 domerr; - u64 pcfbagdrop; - u64 spcprior; - u64 ageprior; - u64 portdrop; - u64 lendrop; - u64 bagdrop; - u64 policeerr; - u64 drpnona664err; - u64 spcerr; - u64 agedrp; +enum sja1105_counter_index { + __SJA1105_COUNTER_UNUSED, + /* MAC */ + N_RUNT, + N_SOFERR, + N_ALIGNERR, + N_MIIERR, + TYPEERR, + SIZEERR, + TCTIMEOUT, + PRIORERR, + NOMASTER, + MEMOV, + MEMERR, + INVTYP, + INTCYOV, + DOMERR, + PCFBAGDROP, + SPCPRIOR, + AGEPRIOR, + PORTDROP, + LENDROP, + BAGDROP, + POLICEERR, + DRPNONA664ERR, + SPCERR, + AGEDRP, + /* HL1 */ + N_N664ERR, + N_VLANERR, + N_UNRELEASED, + N_SIZEERR, + N_CRCERR, + N_VLNOTFOUND, + N_CTPOLERR, + N_POLERR, + N_RXFRM, + N_RXBYTE, + N_TXFRM, + N_TXBYTE, + /* HL2 */ + N_QFULL, + N_PART_DROP, + N_EGR_DISABLED, + N_NOT_REACH, + __MAX_SJA1105ET_PORT_COUNTER, + /* P/Q/R/S only */ + /* ETHER */ + N_DROPS_NOLEARN = __MAX_SJA1105ET_PORT_COUNTER, + N_DROPS_NOROUTE, + N_DROPS_ILL_DTAG, + N_DROPS_DTAG, + N_DROPS_SOTAG, + N_DROPS_SITAG, + N_DROPS_UTAG, + N_TX_BYTES_1024_2047, + N_TX_BYTES_512_1023, + N_TX_BYTES_256_511, + N_TX_BYTES_128_255, + N_TX_BYTES_65_127, + N_TX_BYTES_64, + N_TX_MCAST, + N_TX_BCAST, + N_RX_BYTES_1024_2047, + N_RX_BYTES_512_1023, + N_RX_BYTES_256_511, + N_RX_BYTES_128_255, + N_RX_BYTES_65_127, + N_RX_BYTES_64, + N_RX_MCAST, + N_RX_BCAST, + __MAX_SJA1105PQRS_PORT_COUNTER, }; -struct sja1105_port_status_hl1 { - u64 n_n664err; - u64 n_vlanerr; - u64 n_unreleased; - u64 n_sizeerr; - u64 n_crcerr; - u64 n_vlnotfound; - u64 n_ctpolerr; - u64 n_polerr; - u64 n_rxfrmsh; - u64 n_rxfrm; - u64 n_rxbytesh; - u64 n_rxbyte; - u64 n_txfrmsh; - u64 n_txfrm; - u64 n_txbytesh; - u64 n_txbyte; +struct sja1105_port_counter { + enum sja1105_stats_area area; + const char name[ETH_GSTRING_LEN]; + int offset; + int start; + int end; + bool is_64bit; }; -struct sja1105_port_status_hl2 { - u64 n_qfull; - u64 n_part_drop; - u64 n_egr_disabled; - u64 n_not_reach; - u64 qlevel_hwm[8]; /* Only for P/Q/R/S */ - u64 qlevel[8]; /* Only for P/Q/R/S */ -}; - -struct sja1105_port_status_ether { - u64 n_drops_nolearn; - u64 n_drops_noroute; - u64 n_drops_ill_dtag; - u64 n_drops_dtag; - u64 n_drops_sotag; - u64 n_drops_sitag; - u64 n_drops_utag; - u64 n_tx_bytes_1024_2047; - u64 n_tx_bytes_512_1023; - u64 n_tx_bytes_256_511; - u64 n_tx_bytes_128_255; - u64 n_tx_bytes_65_127; - u64 n_tx_bytes_64; - u64 n_tx_mcast; - u64 n_tx_bcast; - u64 n_rx_bytes_1024_2047; - u64 n_rx_bytes_512_1023; - u64 n_rx_bytes_256_511; - u64 n_rx_bytes_128_255; - u64 n_rx_bytes_65_127; - u64 n_rx_bytes_64; - u64 n_rx_mcast; - u64 n_rx_bcast; -}; - -struct sja1105_port_status { - struct sja1105_port_status_mac mac; - struct sja1105_port_status_hl1 hl1; - struct sja1105_port_status_hl2 hl2; - struct sja1105_port_status_ether ether; -}; - -static void -sja1105_port_status_mac_unpack(void *buf, - struct sja1105_port_status_mac *status) -{ - /* Make pointer arithmetic work on 4 bytes */ - u32 *p = buf; - - sja1105_unpack(p + 0x0, &status->n_runt, 31, 24, 4); - sja1105_unpack(p + 0x0, &status->n_soferr, 23, 16, 4); - sja1105_unpack(p + 0x0, &status->n_alignerr, 15, 8, 4); - sja1105_unpack(p + 0x0, &status->n_miierr, 7, 0, 4); - sja1105_unpack(p + 0x1, &status->typeerr, 27, 27, 4); - sja1105_unpack(p + 0x1, &status->sizeerr, 26, 26, 4); - sja1105_unpack(p + 0x1, &status->tctimeout, 25, 25, 4); - sja1105_unpack(p + 0x1, &status->priorerr, 24, 24, 4); - sja1105_unpack(p + 0x1, &status->nomaster, 23, 23, 4); - sja1105_unpack(p + 0x1, &status->memov, 22, 22, 4); - sja1105_unpack(p + 0x1, &status->memerr, 21, 21, 4); - sja1105_unpack(p + 0x1, &status->invtyp, 19, 19, 4); - sja1105_unpack(p + 0x1, &status->intcyov, 18, 18, 4); - sja1105_unpack(p + 0x1, &status->domerr, 17, 17, 4); - sja1105_unpack(p + 0x1, &status->pcfbagdrop, 16, 16, 4); - sja1105_unpack(p + 0x1, &status->spcprior, 15, 12, 4); - sja1105_unpack(p + 0x1, &status->ageprior, 11, 8, 4); - sja1105_unpack(p + 0x1, &status->portdrop, 6, 6, 4); - sja1105_unpack(p + 0x1, &status->lendrop, 5, 5, 4); - sja1105_unpack(p + 0x1, &status->bagdrop, 4, 4, 4); - sja1105_unpack(p + 0x1, &status->policeerr, 3, 3, 4); - sja1105_unpack(p + 0x1, &status->drpnona664err, 2, 2, 4); - sja1105_unpack(p + 0x1, &status->spcerr, 1, 1, 4); - sja1105_unpack(p + 0x1, &status->agedrp, 0, 0, 4); -} - -static void -sja1105_port_status_hl1_unpack(void *buf, - struct sja1105_port_status_hl1 *status) -{ - /* Make pointer arithmetic work on 4 bytes */ - u32 *p = buf; - - sja1105_unpack(p + 0xF, &status->n_n664err, 31, 0, 4); - sja1105_unpack(p + 0xE, &status->n_vlanerr, 31, 0, 4); - sja1105_unpack(p + 0xD, &status->n_unreleased, 31, 0, 4); - sja1105_unpack(p + 0xC, &status->n_sizeerr, 31, 0, 4); - sja1105_unpack(p + 0xB, &status->n_crcerr, 31, 0, 4); - sja1105_unpack(p + 0xA, &status->n_vlnotfound, 31, 0, 4); - sja1105_unpack(p + 0x9, &status->n_ctpolerr, 31, 0, 4); - sja1105_unpack(p + 0x8, &status->n_polerr, 31, 0, 4); - sja1105_unpack(p + 0x7, &status->n_rxfrmsh, 31, 0, 4); - sja1105_unpack(p + 0x6, &status->n_rxfrm, 31, 0, 4); - sja1105_unpack(p + 0x5, &status->n_rxbytesh, 31, 0, 4); - sja1105_unpack(p + 0x4, &status->n_rxbyte, 31, 0, 4); - sja1105_unpack(p + 0x3, &status->n_txfrmsh, 31, 0, 4); - sja1105_unpack(p + 0x2, &status->n_txfrm, 31, 0, 4); - sja1105_unpack(p + 0x1, &status->n_txbytesh, 31, 0, 4); - sja1105_unpack(p + 0x0, &status->n_txbyte, 31, 0, 4); - status->n_rxfrm += status->n_rxfrmsh << 32; - status->n_rxbyte += status->n_rxbytesh << 32; - status->n_txfrm += status->n_txfrmsh << 32; - status->n_txbyte += status->n_txbytesh << 32; -} - -static void -sja1105_port_status_hl2_unpack(void *buf, - struct sja1105_port_status_hl2 *status) -{ - /* Make pointer arithmetic work on 4 bytes */ - u32 *p = buf; - - sja1105_unpack(p + 0x3, &status->n_qfull, 31, 0, 4); - sja1105_unpack(p + 0x2, &status->n_part_drop, 31, 0, 4); - sja1105_unpack(p + 0x1, &status->n_egr_disabled, 31, 0, 4); - sja1105_unpack(p + 0x0, &status->n_not_reach, 31, 0, 4); -} - -static void -sja1105pqrs_port_status_qlevel_unpack(void *buf, - struct sja1105_port_status_hl2 *status) -{ - /* Make pointer arithmetic work on 4 bytes */ - u32 *p = buf; - int i; - - for (i = 0; i < 8; i++) { - sja1105_unpack(p + i, &status->qlevel_hwm[i], 24, 16, 4); - sja1105_unpack(p + i, &status->qlevel[i], 8, 0, 4); - } -} - -static void -sja1105pqrs_port_status_ether_unpack(void *buf, - struct sja1105_port_status_ether *status) -{ - /* Make pointer arithmetic work on 4 bytes */ - u32 *p = buf; - - sja1105_unpack(p + 0x16, &status->n_drops_nolearn, 31, 0, 4); - sja1105_unpack(p + 0x15, &status->n_drops_noroute, 31, 0, 4); - sja1105_unpack(p + 0x14, &status->n_drops_ill_dtag, 31, 0, 4); - sja1105_unpack(p + 0x13, &status->n_drops_dtag, 31, 0, 4); - sja1105_unpack(p + 0x12, &status->n_drops_sotag, 31, 0, 4); - sja1105_unpack(p + 0x11, &status->n_drops_sitag, 31, 0, 4); - sja1105_unpack(p + 0x10, &status->n_drops_utag, 31, 0, 4); - sja1105_unpack(p + 0x0F, &status->n_tx_bytes_1024_2047, 31, 0, 4); - sja1105_unpack(p + 0x0E, &status->n_tx_bytes_512_1023, 31, 0, 4); - sja1105_unpack(p + 0x0D, &status->n_tx_bytes_256_511, 31, 0, 4); - sja1105_unpack(p + 0x0C, &status->n_tx_bytes_128_255, 31, 0, 4); - sja1105_unpack(p + 0x0B, &status->n_tx_bytes_65_127, 31, 0, 4); - sja1105_unpack(p + 0x0A, &status->n_tx_bytes_64, 31, 0, 4); - sja1105_unpack(p + 0x09, &status->n_tx_mcast, 31, 0, 4); - sja1105_unpack(p + 0x08, &status->n_tx_bcast, 31, 0, 4); - sja1105_unpack(p + 0x07, &status->n_rx_bytes_1024_2047, 31, 0, 4); - sja1105_unpack(p + 0x06, &status->n_rx_bytes_512_1023, 31, 0, 4); - sja1105_unpack(p + 0x05, &status->n_rx_bytes_256_511, 31, 0, 4); - sja1105_unpack(p + 0x04, &status->n_rx_bytes_128_255, 31, 0, 4); - sja1105_unpack(p + 0x03, &status->n_rx_bytes_65_127, 31, 0, 4); - sja1105_unpack(p + 0x02, &status->n_rx_bytes_64, 31, 0, 4); - sja1105_unpack(p + 0x01, &status->n_rx_mcast, 31, 0, 4); - sja1105_unpack(p + 0x00, &status->n_rx_bcast, 31, 0, 4); -} - -static int -sja1105pqrs_port_status_get_ether(struct sja1105_private *priv, - struct sja1105_port_status_ether *ether, - int port) -{ - const struct sja1105_regs *regs = priv->info->regs; - u8 packed_buf[SJA1105_SIZE_ETHER_AREA] = {0}; - int rc; - - /* Ethernet statistics area */ - rc = sja1105_xfer_buf(priv, SPI_READ, regs->ether_stats[port], - packed_buf, SJA1105_SIZE_ETHER_AREA); - if (rc < 0) - return rc; - - sja1105pqrs_port_status_ether_unpack(packed_buf, ether); - - return 0; -} - -static int sja1105_port_status_get_mac(struct sja1105_private *priv, - struct sja1105_port_status_mac *status, - int port) -{ - const struct sja1105_regs *regs = priv->info->regs; - u8 packed_buf[SJA1105_SIZE_MAC_AREA] = {0}; - int rc; - - /* MAC area */ - rc = sja1105_xfer_buf(priv, SPI_READ, regs->mac[port], packed_buf, - SJA1105_SIZE_MAC_AREA); - if (rc < 0) - return rc; - - sja1105_port_status_mac_unpack(packed_buf, status); - - return 0; -} - -static int sja1105_port_status_get_hl1(struct sja1105_private *priv, - struct sja1105_port_status_hl1 *status, - int port) -{ - const struct sja1105_regs *regs = priv->info->regs; - u8 packed_buf[SJA1105_SIZE_HL1_AREA] = {0}; - int rc; - - rc = sja1105_xfer_buf(priv, SPI_READ, regs->mac_hl1[port], packed_buf, - SJA1105_SIZE_HL1_AREA); - if (rc < 0) - return rc; - - sja1105_port_status_hl1_unpack(packed_buf, status); - - return 0; -} - -static int sja1105_port_status_get_hl2(struct sja1105_private *priv, - struct sja1105_port_status_hl2 *status, - int port) -{ - const struct sja1105_regs *regs = priv->info->regs; - u8 packed_buf[SJA1105_SIZE_QLEVEL_AREA] = {0}; - int rc; - - rc = sja1105_xfer_buf(priv, SPI_READ, regs->mac_hl2[port], packed_buf, - SJA1105_SIZE_HL2_AREA); - if (rc < 0) - return rc; - - sja1105_port_status_hl2_unpack(packed_buf, status); - - /* Code below is strictly P/Q/R/S specific. */ - if (priv->info->device_id == SJA1105E_DEVICE_ID || - priv->info->device_id == SJA1105T_DEVICE_ID) - return 0; - - rc = sja1105_xfer_buf(priv, SPI_READ, regs->qlevel[port], packed_buf, - SJA1105_SIZE_QLEVEL_AREA); - if (rc < 0) - return rc; - - sja1105pqrs_port_status_qlevel_unpack(packed_buf, status); - - return 0; -} - -static int sja1105_port_status_get(struct sja1105_private *priv, - struct sja1105_port_status *status, - int port) -{ - int rc; - - rc = sja1105_port_status_get_mac(priv, &status->mac, port); - if (rc < 0) - return rc; - rc = sja1105_port_status_get_hl1(priv, &status->hl1, port); - if (rc < 0) - return rc; - rc = sja1105_port_status_get_hl2(priv, &status->hl2, port); - if (rc < 0) - return rc; - - if (priv->info->device_id == SJA1105E_DEVICE_ID || - priv->info->device_id == SJA1105T_DEVICE_ID) - return 0; - - return sja1105pqrs_port_status_get_ether(priv, &status->ether, port); -} - -static char sja1105_port_stats[][ETH_GSTRING_LEN] = { +static const struct sja1105_port_counter sja1105_port_counters[] = { /* MAC-Level Diagnostic Counters */ - "n_runt", - "n_soferr", - "n_alignerr", - "n_miierr", + [N_RUNT] = { + .area = MAC, + .name = "n_runt", + .offset = 0, + .start = 31, + .end = 24, + }, + [N_SOFERR] = { + .area = MAC, + .name = "n_soferr", + .offset = 0x0, + .start = 23, + .end = 16, + }, + [N_ALIGNERR] = { + .area = MAC, + .name = "n_alignerr", + .offset = 0x0, + .start = 15, + .end = 8, + }, + [N_MIIERR] = { + .area = MAC, + .name = "n_miierr", + .offset = 0x0, + .start = 7, + .end = 0, + }, /* MAC-Level Diagnostic Flags */ - "typeerr", - "sizeerr", - "tctimeout", - "priorerr", - "nomaster", - "memov", - "memerr", - "invtyp", - "intcyov", - "domerr", - "pcfbagdrop", - "spcprior", - "ageprior", - "portdrop", - "lendrop", - "bagdrop", - "policeerr", - "drpnona664err", - "spcerr", - "agedrp", + [TYPEERR] = { + .area = MAC, + .name = "typeerr", + .offset = 0x1, + .start = 27, + .end = 27, + }, + [SIZEERR] = { + .area = MAC, + .name = "sizeerr", + .offset = 0x1, + .start = 26, + .end = 26, + }, + [TCTIMEOUT] = { + .area = MAC, + .name = "tctimeout", + .offset = 0x1, + .start = 25, + .end = 25, + }, + [PRIORERR] = { + .area = MAC, + .name = "priorerr", + .offset = 0x1, + .start = 24, + .end = 24, + }, + [NOMASTER] = { + .area = MAC, + .name = "nomaster", + .offset = 0x1, + .start = 23, + .end = 23, + }, + [MEMOV] = { + .area = MAC, + .name = "memov", + .offset = 0x1, + .start = 22, + .end = 22, + }, + [MEMERR] = { + .area = MAC, + .name = "memerr", + .offset = 0x1, + .start = 21, + .end = 21, + }, + [INVTYP] = { + .area = MAC, + .name = "invtyp", + .offset = 0x1, + .start = 19, + .end = 19, + }, + [INTCYOV] = { + .area = MAC, + .name = "intcyov", + .offset = 0x1, + .start = 18, + .end = 18, + }, + [DOMERR] = { + .area = MAC, + .name = "domerr", + .offset = 0x1, + .start = 17, + .end = 17, + }, + [PCFBAGDROP] = { + .area = MAC, + .name = "pcfbagdrop", + .offset = 0x1, + .start = 16, + .end = 16, + }, + [SPCPRIOR] = { + .area = MAC, + .name = "spcprior", + .offset = 0x1, + .start = 15, + .end = 12, + }, + [AGEPRIOR] = { + .area = MAC, + .name = "ageprior", + .offset = 0x1, + .start = 11, + .end = 8, + }, + [PORTDROP] = { + .area = MAC, + .name = "portdrop", + .offset = 0x1, + .start = 6, + .end = 6, + }, + [LENDROP] = { + .area = MAC, + .name = "lendrop", + .offset = 0x1, + .start = 5, + .end = 5, + }, + [BAGDROP] = { + .area = MAC, + .name = "bagdrop", + .offset = 0x1, + .start = 4, + .end = 4, + }, + [POLICEERR] = { + .area = MAC, + .name = "policeerr", + .offset = 0x1, + .start = 3, + .end = 3, + }, + [DRPNONA664ERR] = { + .area = MAC, + .name = "drpnona664err", + .offset = 0x1, + .start = 2, + .end = 2, + }, + [SPCERR] = { + .area = MAC, + .name = "spcerr", + .offset = 0x1, + .start = 1, + .end = 1, + }, + [AGEDRP] = { + .area = MAC, + .name = "agedrp", + .offset = 0x1, + .start = 0, + .end = 0, + }, /* High-Level Diagnostic Counters */ - "n_n664err", - "n_vlanerr", - "n_unreleased", - "n_sizeerr", - "n_crcerr", - "n_vlnotfound", - "n_ctpolerr", - "n_polerr", - "n_rxfrm", - "n_rxbyte", - "n_txfrm", - "n_txbyte", - "n_qfull", - "n_part_drop", - "n_egr_disabled", - "n_not_reach", + [N_N664ERR] = { + .area = HL1, + .name = "n_n664err", + .offset = 0xF, + .start = 31, + .end = 0, + }, + [N_VLANERR] = { + .area = HL1, + .name = "n_vlanerr", + .offset = 0xE, + .start = 31, + .end = 0, + }, + [N_UNRELEASED] = { + .area = HL1, + .name = "n_unreleased", + .offset = 0xD, + .start = 31, + .end = 0, + }, + [N_SIZEERR] = { + .area = HL1, + .name = "n_sizeerr", + .offset = 0xC, + .start = 31, + .end = 0, + }, + [N_CRCERR] = { + .area = HL1, + .name = "n_crcerr", + .offset = 0xB, + .start = 31, + .end = 0, + }, + [N_VLNOTFOUND] = { + .area = HL1, + .name = "n_vlnotfound", + .offset = 0xA, + .start = 31, + .end = 0, + }, + [N_CTPOLERR] = { + .area = HL1, + .name = "n_ctpolerr", + .offset = 0x9, + .start = 31, + .end = 0, + }, + [N_POLERR] = { + .area = HL1, + .name = "n_polerr", + .offset = 0x8, + .start = 31, + .end = 0, + }, + [N_RXFRM] = { + .area = HL1, + .name = "n_rxfrm", + .offset = 0x6, + .start = 31, + .end = 0, + .is_64bit = true, + }, + [N_RXBYTE] = { + .area = HL1, + .name = "n_rxbyte", + .offset = 0x4, + .start = 31, + .end = 0, + .is_64bit = true, + }, + [N_TXFRM] = { + .area = HL1, + .name = "n_txfrm", + .offset = 0x2, + .start = 31, + .end = 0, + .is_64bit = true, + }, + [N_TXBYTE] = { + .area = HL1, + .name = "n_txbyte", + .offset = 0x0, + .start = 31, + .end = 0, + .is_64bit = true, + }, + [N_QFULL] = { + .area = HL2, + .name = "n_qfull", + .offset = 0x3, + .start = 31, + .end = 0, + }, + [N_PART_DROP] = { + .area = HL2, + .name = "n_part_drop", + .offset = 0x2, + .start = 31, + .end = 0, + }, + [N_EGR_DISABLED] = { + .area = HL2, + .name = "n_egr_disabled", + .offset = 0x1, + .start = 31, + .end = 0, + }, + [N_NOT_REACH] = { + .area = HL2, + .name = "n_not_reach", + .offset = 0x0, + .start = 31, + .end = 0, + }, + /* Ether Stats */ + [N_DROPS_NOLEARN] = { + .area = ETHER, + .name = "n_drops_nolearn", + .offset = 0x16, + .start = 31, + .end = 0, + }, + [N_DROPS_NOROUTE] = { + .area = ETHER, + .name = "n_drops_noroute", + .offset = 0x15, + .start = 31, + .end = 0, + }, + [N_DROPS_ILL_DTAG] = { + .area = ETHER, + .name = "n_drops_ill_dtag", + .offset = 0x14, + .start = 31, + .end = 0, + }, + [N_DROPS_DTAG] = { + .area = ETHER, + .name = "n_drops_dtag", + .offset = 0x13, + .start = 31, + .end = 0, + }, + [N_DROPS_SOTAG] = { + .area = ETHER, + .name = "n_drops_sotag", + .offset = 0x12, + .start = 31, + .end = 0, + }, + [N_DROPS_SITAG] = { + .area = ETHER, + .name = "n_drops_sitag", + .offset = 0x11, + .start = 31, + .end = 0, + }, + [N_DROPS_UTAG] = { + .area = ETHER, + .name = "n_drops_utag", + .offset = 0x10, + .start = 31, + .end = 0, + }, + [N_TX_BYTES_1024_2047] = { + .area = ETHER, + .name = "n_tx_bytes_1024_2047", + .offset = 0x0F, + .start = 31, + .end = 0, + }, + [N_TX_BYTES_512_1023] = { + .area = ETHER, + .name = "n_tx_bytes_512_1023", + .offset = 0x0E, + .start = 31, + .end = 0, + }, + [N_TX_BYTES_256_511] = { + .area = ETHER, + .name = "n_tx_bytes_256_511", + .offset = 0x0D, + .start = 31, + .end = 0, + }, + [N_TX_BYTES_128_255] = { + .area = ETHER, + .name = "n_tx_bytes_128_255", + .offset = 0x0C, + .start = 31, + .end = 0, + }, + [N_TX_BYTES_65_127] = { + .area = ETHER, + .name = "n_tx_bytes_65_127", + .offset = 0x0B, + .start = 31, + .end = 0, + }, + [N_TX_BYTES_64] = { + .area = ETHER, + .name = "n_tx_bytes_64", + .offset = 0x0A, + .start = 31, + .end = 0, + }, + [N_TX_MCAST] = { + .area = ETHER, + .name = "n_tx_mcast", + .offset = 0x09, + .start = 31, + .end = 0, + }, + [N_TX_BCAST] = { + .area = ETHER, + .name = "n_tx_bcast", + .offset = 0x08, + .start = 31, + .end = 0, + }, + [N_RX_BYTES_1024_2047] = { + .area = ETHER, + .name = "n_rx_bytes_1024_2047", + .offset = 0x07, + .start = 31, + .end = 0, + }, + [N_RX_BYTES_512_1023] = { + .area = ETHER, + .name = "n_rx_bytes_512_1023", + .offset = 0x06, + .start = 31, + .end = 0, + }, + [N_RX_BYTES_256_511] = { + .area = ETHER, + .name = "n_rx_bytes_256_511", + .offset = 0x05, + .start = 31, + .end = 0, + }, + [N_RX_BYTES_128_255] = { + .area = ETHER, + .name = "n_rx_bytes_128_255", + .offset = 0x04, + .start = 31, + .end = 0, + }, + [N_RX_BYTES_65_127] = { + .area = ETHER, + .name = "n_rx_bytes_65_127", + .offset = 0x03, + .start = 31, + .end = 0, + }, + [N_RX_BYTES_64] = { + .area = ETHER, + .name = "n_rx_bytes_64", + .offset = 0x02, + .start = 31, + .end = 0, + }, + [N_RX_MCAST] = { + .area = ETHER, + .name = "n_rx_mcast", + .offset = 0x01, + .start = 31, + .end = 0, + }, + [N_RX_BCAST] = { + .area = ETHER, + .name = "n_rx_bcast", + .offset = 0x00, + .start = 31, + .end = 0, + }, }; -static char sja1105pqrs_extra_port_stats[][ETH_GSTRING_LEN] = { - /* Queue Levels */ - "qlevel_hwm_0", - "qlevel_hwm_1", - "qlevel_hwm_2", - "qlevel_hwm_3", - "qlevel_hwm_4", - "qlevel_hwm_5", - "qlevel_hwm_6", - "qlevel_hwm_7", - "qlevel_0", - "qlevel_1", - "qlevel_2", - "qlevel_3", - "qlevel_4", - "qlevel_5", - "qlevel_6", - "qlevel_7", - /* Ether Stats */ - "n_drops_nolearn", - "n_drops_noroute", - "n_drops_ill_dtag", - "n_drops_dtag", - "n_drops_sotag", - "n_drops_sitag", - "n_drops_utag", - "n_tx_bytes_1024_2047", - "n_tx_bytes_512_1023", - "n_tx_bytes_256_511", - "n_tx_bytes_128_255", - "n_tx_bytes_65_127", - "n_tx_bytes_64", - "n_tx_mcast", - "n_tx_bcast", - "n_rx_bytes_1024_2047", - "n_rx_bytes_512_1023", - "n_rx_bytes_256_511", - "n_rx_bytes_128_255", - "n_rx_bytes_65_127", - "n_rx_bytes_64", - "n_rx_mcast", - "n_rx_bcast", -}; +static int sja1105_port_counter_read(struct sja1105_private *priv, int port, + enum sja1105_counter_index idx, u64 *ctr) +{ + const struct sja1105_port_counter *c = &sja1105_port_counters[idx]; + size_t size = c->is_64bit ? 8 : 4; + u8 buf[8] = {0}; + u64 regs; + int rc; + + regs = priv->info->regs->stats[c->area][port]; + + rc = sja1105_xfer_buf(priv, SPI_READ, regs + c->offset, buf, size); + if (rc) + return rc; + + sja1105_unpack(buf, ctr, c->start, c->end, size); + + return 0; +} void sja1105_get_ethtool_stats(struct dsa_switch *ds, int port, u64 *data) { struct sja1105_private *priv = ds->priv; - struct sja1105_port_status *status; - int rc, i, k = 0; - - status = kzalloc(sizeof(*status), GFP_KERNEL); - if (!status) - goto out; - - rc = sja1105_port_status_get(priv, status, port); - if (rc < 0) { - dev_err(ds->dev, "Failed to read port %d counters: %d\n", - port, rc); - goto out; - } - memset(data, 0, ARRAY_SIZE(sja1105_port_stats) * sizeof(u64)); - data[k++] = status->mac.n_runt; - data[k++] = status->mac.n_soferr; - data[k++] = status->mac.n_alignerr; - data[k++] = status->mac.n_miierr; - data[k++] = status->mac.typeerr; - data[k++] = status->mac.sizeerr; - data[k++] = status->mac.tctimeout; - data[k++] = status->mac.priorerr; - data[k++] = status->mac.nomaster; - data[k++] = status->mac.memov; - data[k++] = status->mac.memerr; - data[k++] = status->mac.invtyp; - data[k++] = status->mac.intcyov; - data[k++] = status->mac.domerr; - data[k++] = status->mac.pcfbagdrop; - data[k++] = status->mac.spcprior; - data[k++] = status->mac.ageprior; - data[k++] = status->mac.portdrop; - data[k++] = status->mac.lendrop; - data[k++] = status->mac.bagdrop; - data[k++] = status->mac.policeerr; - data[k++] = status->mac.drpnona664err; - data[k++] = status->mac.spcerr; - data[k++] = status->mac.agedrp; - data[k++] = status->hl1.n_n664err; - data[k++] = status->hl1.n_vlanerr; - data[k++] = status->hl1.n_unreleased; - data[k++] = status->hl1.n_sizeerr; - data[k++] = status->hl1.n_crcerr; - data[k++] = status->hl1.n_vlnotfound; - data[k++] = status->hl1.n_ctpolerr; - data[k++] = status->hl1.n_polerr; - data[k++] = status->hl1.n_rxfrm; - data[k++] = status->hl1.n_rxbyte; - data[k++] = status->hl1.n_txfrm; - data[k++] = status->hl1.n_txbyte; - data[k++] = status->hl2.n_qfull; - data[k++] = status->hl2.n_part_drop; - data[k++] = status->hl2.n_egr_disabled; - data[k++] = status->hl2.n_not_reach; + enum sja1105_counter_index max_ctr, i; + int rc, k = 0; if (priv->info->device_id == SJA1105E_DEVICE_ID || priv->info->device_id == SJA1105T_DEVICE_ID) - goto out; + max_ctr = __MAX_SJA1105ET_PORT_COUNTER; + else + max_ctr = __MAX_SJA1105PQRS_PORT_COUNTER; - memset(data + k, 0, ARRAY_SIZE(sja1105pqrs_extra_port_stats) * - sizeof(u64)); - for (i = 0; i < 8; i++) { - data[k++] = status->hl2.qlevel_hwm[i]; - data[k++] = status->hl2.qlevel[i]; + for (i = 0; i < max_ctr; i++) { + rc = sja1105_port_counter_read(priv, port, i, &data[k++]); + if (rc) { + dev_err(ds->dev, + "Failed to read port %d counters: %d\n", + port, rc); + break; + } } - data[k++] = status->ether.n_drops_nolearn; - data[k++] = status->ether.n_drops_noroute; - data[k++] = status->ether.n_drops_ill_dtag; - data[k++] = status->ether.n_drops_dtag; - data[k++] = status->ether.n_drops_sotag; - data[k++] = status->ether.n_drops_sitag; - data[k++] = status->ether.n_drops_utag; - data[k++] = status->ether.n_tx_bytes_1024_2047; - data[k++] = status->ether.n_tx_bytes_512_1023; - data[k++] = status->ether.n_tx_bytes_256_511; - data[k++] = status->ether.n_tx_bytes_128_255; - data[k++] = status->ether.n_tx_bytes_65_127; - data[k++] = status->ether.n_tx_bytes_64; - data[k++] = status->ether.n_tx_mcast; - data[k++] = status->ether.n_tx_bcast; - data[k++] = status->ether.n_rx_bytes_1024_2047; - data[k++] = status->ether.n_rx_bytes_512_1023; - data[k++] = status->ether.n_rx_bytes_256_511; - data[k++] = status->ether.n_rx_bytes_128_255; - data[k++] = status->ether.n_rx_bytes_65_127; - data[k++] = status->ether.n_rx_bytes_64; - data[k++] = status->ether.n_rx_mcast; - data[k++] = status->ether.n_rx_bcast; -out: - kfree(status); } void sja1105_get_strings(struct dsa_switch *ds, int port, u32 stringset, u8 *data) { struct sja1105_private *priv = ds->priv; - u8 *p = data; - int i; + enum sja1105_counter_index max_ctr, i; + char *p = data; - switch (stringset) { - case ETH_SS_STATS: - for (i = 0; i < ARRAY_SIZE(sja1105_port_stats); i++) { - strlcpy(p, sja1105_port_stats[i], ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - if (priv->info->device_id == SJA1105E_DEVICE_ID || - priv->info->device_id == SJA1105T_DEVICE_ID) - return; - for (i = 0; i < ARRAY_SIZE(sja1105pqrs_extra_port_stats); i++) { - strlcpy(p, sja1105pqrs_extra_port_stats[i], - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - break; + if (stringset != ETH_SS_STATS) + return; + + if (priv->info->device_id == SJA1105E_DEVICE_ID || + priv->info->device_id == SJA1105T_DEVICE_ID) + max_ctr = __MAX_SJA1105ET_PORT_COUNTER; + else + max_ctr = __MAX_SJA1105PQRS_PORT_COUNTER; + + for (i = 0; i < max_ctr; i++) { + strscpy(p, sja1105_port_counters[i].name, ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; } } int sja1105_get_sset_count(struct dsa_switch *ds, int port, int sset) { - int count = ARRAY_SIZE(sja1105_port_stats); struct sja1105_private *priv = ds->priv; + enum sja1105_counter_index max_ctr, i; + int sset_count = 0; if (sset != ETH_SS_STATS) return -EOPNOTSUPP; - if (priv->info->device_id == SJA1105PR_DEVICE_ID || - priv->info->device_id == SJA1105QS_DEVICE_ID) - count += ARRAY_SIZE(sja1105pqrs_extra_port_stats); + if (priv->info->device_id == SJA1105E_DEVICE_ID || + priv->info->device_id == SJA1105T_DEVICE_ID) + max_ctr = __MAX_SJA1105ET_PORT_COUNTER; + else + max_ctr = __MAX_SJA1105PQRS_PORT_COUNTER; - return count; + for (i = 0; i < max_ctr; i++) { + if (!strlen(sja1105_port_counters[i].name)) + continue; + + sset_count++; + } + + return sset_count; } diff --git a/drivers/net/dsa/sja1105/sja1105_flower.c b/drivers/net/dsa/sja1105/sja1105_flower.c index 973761132fc3..6c10ffa968ce 100644 --- a/drivers/net/dsa/sja1105/sja1105_flower.c +++ b/drivers/net/dsa/sja1105/sja1105_flower.c @@ -35,6 +35,7 @@ static int sja1105_setup_bcast_policer(struct sja1105_private *priv, { struct sja1105_rule *rule = sja1105_rule_find(priv, cookie); struct sja1105_l2_policing_entry *policing; + struct dsa_switch *ds = priv->ds; bool new_rule = false; unsigned long p; int rc; @@ -59,7 +60,7 @@ static int sja1105_setup_bcast_policer(struct sja1105_private *priv, policing = priv->static_config.tables[BLK_IDX_L2_POLICING].entries; - if (policing[(SJA1105_NUM_PORTS * SJA1105_NUM_TC) + port].sharindx != port) { + if (policing[(ds->num_ports * SJA1105_NUM_TC) + port].sharindx != port) { NL_SET_ERR_MSG_MOD(extack, "Port already has a broadcast policer"); rc = -EEXIST; @@ -71,8 +72,8 @@ static int sja1105_setup_bcast_policer(struct sja1105_private *priv, /* Make the broadcast policers of all ports attached to this block * point to the newly allocated policer */ - for_each_set_bit(p, &rule->port_mask, SJA1105_NUM_PORTS) { - int bcast = (SJA1105_NUM_PORTS * SJA1105_NUM_TC) + p; + for_each_set_bit(p, &rule->port_mask, SJA1105_MAX_NUM_PORTS) { + int bcast = (ds->num_ports * SJA1105_NUM_TC) + p; policing[bcast].sharindx = rule->bcast_pol.sharindx; } @@ -143,7 +144,7 @@ static int sja1105_setup_tc_policer(struct sja1105_private *priv, /* Make the policers for traffic class @tc of all ports attached to * this block point to the newly allocated policer */ - for_each_set_bit(p, &rule->port_mask, SJA1105_NUM_PORTS) { + for_each_set_bit(p, &rule->port_mask, SJA1105_MAX_NUM_PORTS) { int index = (p * SJA1105_NUM_TC) + tc; policing[index].sharindx = rule->tc_pol.sharindx; @@ -435,7 +436,7 @@ int sja1105_cls_flower_del(struct dsa_switch *ds, int port, policing = priv->static_config.tables[BLK_IDX_L2_POLICING].entries; if (rule->type == SJA1105_RULE_BCAST_POLICER) { - int bcast = (SJA1105_NUM_PORTS * SJA1105_NUM_TC) + port; + int bcast = (ds->num_ports * SJA1105_NUM_TC) + port; old_sharindx = policing[bcast].sharindx; policing[bcast].sharindx = port; @@ -486,7 +487,7 @@ void sja1105_flower_setup(struct dsa_switch *ds) INIT_LIST_HEAD(&priv->flow_block.rules); - for (port = 0; port < SJA1105_NUM_PORTS; port++) + for (port = 0; port < ds->num_ports; port++) priv->flow_block.l2_policer_used[port] = true; } diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index b88d9ef45a1f..4f0545605f6b 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -16,13 +16,13 @@ #include #include #include +#include #include #include #include #include #include #include "sja1105.h" -#include "sja1105_sgmii.h" #include "sja1105_tas.h" #define SJA1105_UNKNOWN_MULTICAST 0x010000000000ull @@ -57,14 +57,6 @@ static bool sja1105_can_forward(struct sja1105_l2_forwarding_entry *l2_fwd, return !!(l2_fwd[from].reach_port & BIT(to)); } -/* Structure used to temporarily transport device tree - * settings into sja1105_setup - */ -struct sja1105_dt_port { - phy_interface_t phy_mode; - sja1105_mii_role_t role; -}; - static int sja1105_init_mac_settings(struct sja1105_private *priv) { struct sja1105_mac_config_entry default_mac = { @@ -80,7 +72,7 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv) /* Always put the MAC speed in automatic mode, where it can be * adjusted at runtime by PHYLINK. */ - .speed = SJA1105_SPEED_AUTO, + .speed = priv->info->port_speed[SJA1105_SPEED_AUTO], /* No static correction for 1-step 1588 events */ .tp_delin = 0, .tp_delout = 0, @@ -107,6 +99,7 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv) .ingress = false, }; struct sja1105_mac_config_entry *mac; + struct dsa_switch *ds = priv->ds; struct sja1105_table *table; int i; @@ -118,16 +111,16 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv) table->entry_count = 0; } - table->entries = kcalloc(SJA1105_NUM_PORTS, + table->entries = kcalloc(table->ops->max_entry_count, table->ops->unpacked_entry_size, GFP_KERNEL); if (!table->entries) return -ENOMEM; - table->entry_count = SJA1105_NUM_PORTS; + table->entry_count = table->ops->max_entry_count; mac = table->entries; - for (i = 0; i < SJA1105_NUM_PORTS; i++) { + for (i = 0; i < ds->num_ports; i++) { mac[i] = default_mac; if (i == dsa_upstream_port(priv->ds, i)) { /* STP doesn't get called for CPU port, so we need to @@ -142,26 +135,11 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv) return 0; } -static bool sja1105_supports_sgmii(struct sja1105_private *priv, int port) -{ - if (priv->info->part_no != SJA1105R_PART_NO && - priv->info->part_no != SJA1105S_PART_NO) - return false; - - if (port != SJA1105_SGMII_PORT) - return false; - - if (dsa_is_unused_port(priv->ds, port)) - return false; - - return true; -} - -static int sja1105_init_mii_settings(struct sja1105_private *priv, - struct sja1105_dt_port *ports) +static int sja1105_init_mii_settings(struct sja1105_private *priv) { struct device *dev = &priv->spidev->dev; struct sja1105_xmii_params_entry *mii; + struct dsa_switch *ds = priv->ds; struct sja1105_table *table; int i; @@ -173,52 +151,81 @@ static int sja1105_init_mii_settings(struct sja1105_private *priv, table->entry_count = 0; } - table->entries = kcalloc(SJA1105_MAX_XMII_PARAMS_COUNT, + table->entries = kcalloc(table->ops->max_entry_count, table->ops->unpacked_entry_size, GFP_KERNEL); if (!table->entries) return -ENOMEM; /* Override table based on PHYLINK DT bindings */ - table->entry_count = SJA1105_MAX_XMII_PARAMS_COUNT; + table->entry_count = table->ops->max_entry_count; mii = table->entries; - for (i = 0; i < SJA1105_NUM_PORTS; i++) { + for (i = 0; i < ds->num_ports; i++) { + sja1105_mii_role_t role = XMII_MAC; + if (dsa_is_unused_port(priv->ds, i)) continue; - switch (ports[i].phy_mode) { + switch (priv->phy_mode[i]) { + case PHY_INTERFACE_MODE_INTERNAL: + if (priv->info->internal_phy[i] == SJA1105_NO_PHY) + goto unsupported; + + mii->xmii_mode[i] = XMII_MODE_MII; + if (priv->info->internal_phy[i] == SJA1105_PHY_BASE_TX) + mii->special[i] = true; + + break; + case PHY_INTERFACE_MODE_REVMII: + role = XMII_PHY; + fallthrough; case PHY_INTERFACE_MODE_MII: + if (!priv->info->supports_mii[i]) + goto unsupported; + mii->xmii_mode[i] = XMII_MODE_MII; break; + case PHY_INTERFACE_MODE_REVRMII: + role = XMII_PHY; + fallthrough; case PHY_INTERFACE_MODE_RMII: + if (!priv->info->supports_rmii[i]) + goto unsupported; + mii->xmii_mode[i] = XMII_MODE_RMII; break; case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: + if (!priv->info->supports_rgmii[i]) + goto unsupported; + mii->xmii_mode[i] = XMII_MODE_RGMII; break; case PHY_INTERFACE_MODE_SGMII: - if (!sja1105_supports_sgmii(priv, i)) - return -EINVAL; + if (!priv->info->supports_sgmii[i]) + goto unsupported; + mii->xmii_mode[i] = XMII_MODE_SGMII; + mii->special[i] = true; break; + case PHY_INTERFACE_MODE_2500BASEX: + if (!priv->info->supports_2500basex[i]) + goto unsupported; + + mii->xmii_mode[i] = XMII_MODE_SGMII; + mii->special[i] = true; + break; +unsupported: default: - dev_err(dev, "Unsupported PHY mode %s!\n", - phy_modes(ports[i].phy_mode)); + dev_err(dev, "Unsupported PHY mode %s on port %d!\n", + phy_modes(priv->phy_mode[i]), i); return -EINVAL; } - /* Even though the SerDes port is able to drive SGMII autoneg - * like a PHY would, from the perspective of the XMII tables, - * the SGMII port should always be put in MAC mode. - */ - if (ports[i].phy_mode == PHY_INTERFACE_MODE_SGMII) - mii->phy_mac[i] = XMII_MAC; - else - mii->phy_mac[i] = ports[i].role; + mii->phy_mac[i] = role; } return 0; } @@ -267,8 +274,6 @@ static int sja1105_init_static_fdb(struct sja1105_private *priv) static int sja1105_init_l2_lookup_params(struct sja1105_private *priv) { - struct sja1105_table *table; - u64 max_fdb_entries = SJA1105_MAX_L2_LOOKUP_COUNT / SJA1105_NUM_PORTS; struct sja1105_l2_lookup_params_entry default_l2_lookup_params = { /* Learned FDB entries are forgotten after 300 seconds */ .maxage = SJA1105_AGEING_TIME_MS(300000), @@ -276,8 +281,6 @@ static int sja1105_init_l2_lookup_params(struct sja1105_private *priv) .dyn_tbsz = SJA1105ET_FDB_BIN_SIZE, /* And the P/Q/R/S equivalent setting: */ .start_dynspc = 0, - .maxaddrp = {max_fdb_entries, max_fdb_entries, max_fdb_entries, - max_fdb_entries, max_fdb_entries, }, /* 2^8 + 2^5 + 2^3 + 2^2 + 2^1 + 1 in Koopman notation */ .poly = 0x97, /* This selects between Independent VLAN Learning (IVL) and @@ -301,6 +304,23 @@ static int sja1105_init_l2_lookup_params(struct sja1105_private *priv) .owr_dyn = true, .drpnolearn = true, }; + struct dsa_switch *ds = priv->ds; + int port, num_used_ports = 0; + struct sja1105_table *table; + u64 max_fdb_entries; + + for (port = 0; port < ds->num_ports; port++) + if (!dsa_is_unused_port(ds, port)) + num_used_ports++; + + max_fdb_entries = SJA1105_MAX_L2_LOOKUP_COUNT / num_used_ports; + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_is_unused_port(ds, port)) + continue; + + default_l2_lookup_params.maxaddrp[port] = max_fdb_entries; + } table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP_PARAMS]; @@ -309,12 +329,12 @@ static int sja1105_init_l2_lookup_params(struct sja1105_private *priv) table->entry_count = 0; } - table->entries = kcalloc(SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT, + table->entries = kcalloc(table->ops->max_entry_count, table->ops->unpacked_entry_size, GFP_KERNEL); if (!table->entries) return -ENOMEM; - table->entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT; + table->entry_count = table->ops->max_entry_count; /* This table only has a single entry */ ((struct sja1105_l2_lookup_params_entry *)table->entries)[0] = @@ -334,6 +354,7 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) { struct sja1105_table *table; struct sja1105_vlan_lookup_entry pvid = { + .type_entry = SJA1110_VLAN_D_TAG, .ving_mirr = 0, .vegr_mirr = 0, .vmemb_port = 0, @@ -387,6 +408,7 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv) static int sja1105_init_l2_forwarding(struct sja1105_private *priv) { struct sja1105_l2_forwarding_entry *l2fwd; + struct dsa_switch *ds = priv->ds; struct sja1105_table *table; int i, j; @@ -397,19 +419,22 @@ static int sja1105_init_l2_forwarding(struct sja1105_private *priv) table->entry_count = 0; } - table->entries = kcalloc(SJA1105_MAX_L2_FORWARDING_COUNT, + table->entries = kcalloc(table->ops->max_entry_count, table->ops->unpacked_entry_size, GFP_KERNEL); if (!table->entries) return -ENOMEM; - table->entry_count = SJA1105_MAX_L2_FORWARDING_COUNT; + table->entry_count = table->ops->max_entry_count; l2fwd = table->entries; /* First 5 entries define the forwarding rules */ - for (i = 0; i < SJA1105_NUM_PORTS; i++) { + for (i = 0; i < ds->num_ports; i++) { unsigned int upstream = dsa_upstream_port(priv->ds, i); + if (dsa_is_unused_port(ds, i)) + continue; + for (j = 0; j < SJA1105_NUM_TC; j++) l2fwd[i].vlan_pmap[j] = j; @@ -431,24 +456,66 @@ static int sja1105_init_l2_forwarding(struct sja1105_private *priv) l2fwd[upstream].bc_domain |= BIT(i); l2fwd[upstream].fl_domain |= BIT(i); } + /* Next 8 entries define VLAN PCP mapping from ingress to egress. * Create a one-to-one mapping. */ - for (i = 0; i < SJA1105_NUM_TC; i++) - for (j = 0; j < SJA1105_NUM_PORTS; j++) - l2fwd[SJA1105_NUM_PORTS + i].vlan_pmap[j] = i; + for (i = 0; i < SJA1105_NUM_TC; i++) { + for (j = 0; j < ds->num_ports; j++) { + if (dsa_is_unused_port(ds, j)) + continue; + + l2fwd[ds->num_ports + i].vlan_pmap[j] = i; + } + + l2fwd[ds->num_ports + i].type_egrpcp2outputq = true; + } + + return 0; +} + +static int sja1110_init_pcp_remapping(struct sja1105_private *priv) +{ + struct sja1110_pcp_remapping_entry *pcp_remap; + struct dsa_switch *ds = priv->ds; + struct sja1105_table *table; + int port, tc; + + table = &priv->static_config.tables[BLK_IDX_PCP_REMAPPING]; + + /* Nothing to do for SJA1105 */ + if (!table->ops->max_entry_count) + return 0; + + if (table->entry_count) { + kfree(table->entries); + table->entry_count = 0; + } + + table->entries = kcalloc(table->ops->max_entry_count, + table->ops->unpacked_entry_size, GFP_KERNEL); + if (!table->entries) + return -ENOMEM; + + table->entry_count = table->ops->max_entry_count; + + pcp_remap = table->entries; + + /* Repeat the configuration done for vlan_pmap */ + for (port = 0; port < ds->num_ports; port++) { + if (dsa_is_unused_port(ds, port)) + continue; + + for (tc = 0; tc < SJA1105_NUM_TC; tc++) + pcp_remap[port].egrpcp[tc] = tc; + } return 0; } static int sja1105_init_l2_forwarding_params(struct sja1105_private *priv) { - struct sja1105_l2_forwarding_params_entry default_l2fwd_params = { - /* Disallow dynamic reconfiguration of vlan_pmap */ - .max_dynp = 0, - /* Use a single memory partition for all ingress queues */ - .part_spc = { SJA1105_MAX_FRAME_MEMORY, 0, 0, 0, 0, 0, 0, 0 }, - }; + struct sja1105_l2_forwarding_params_entry *l2fwd_params; struct sja1105_table *table; table = &priv->static_config.tables[BLK_IDX_L2_FORWARDING_PARAMS]; @@ -458,16 +525,20 @@ static int sja1105_init_l2_forwarding_params(struct sja1105_private *priv) table->entry_count = 0; } - table->entries = kcalloc(SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT, + table->entries = kcalloc(table->ops->max_entry_count, table->ops->unpacked_entry_size, GFP_KERNEL); if (!table->entries) return -ENOMEM; - table->entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT; + table->entry_count = table->ops->max_entry_count; /* This table only has a single entry */ - ((struct sja1105_l2_forwarding_params_entry *)table->entries)[0] = - default_l2fwd_params; + l2fwd_params = table->entries; + + /* Disallow dynamic reconfiguration of vlan_pmap */ + l2fwd_params->max_dynp = 0; + /* Use a single memory partition for all ingress queues */ + l2fwd_params->part_spc[0] = priv->info->max_frame_mem; return 0; } @@ -476,16 +547,14 @@ void sja1105_frame_memory_partitioning(struct sja1105_private *priv) { struct sja1105_l2_forwarding_params_entry *l2_fwd_params; struct sja1105_vl_forwarding_params_entry *vl_fwd_params; + int max_mem = priv->info->max_frame_mem; struct sja1105_table *table; - int max_mem; /* VLAN retagging is implemented using a loopback port that consumes * frame buffers. That leaves less for us. */ if (priv->vlan_state == SJA1105_VLAN_BEST_EFFORT) - max_mem = SJA1105_MAX_FRAME_MEMORY_RETAGGING; - else - max_mem = SJA1105_MAX_FRAME_MEMORY; + max_mem -= SJA1105_FRAME_MEMORY_RETAGGING_OVERHEAD; table = &priv->static_config.tables[BLK_IDX_L2_FORWARDING_PARAMS]; l2_fwd_params = table->entries; @@ -507,6 +576,60 @@ void sja1105_frame_memory_partitioning(struct sja1105_private *priv) vl_fwd_params->partspc[0] = SJA1105_VL_FRAME_MEMORY; } +/* SJA1110 TDMACONFIGIDX values: + * + * | 100 Mbps ports | 1Gbps ports | 2.5Gbps ports | Disabled ports + * -----+----------------+---------------+---------------+--------------- + * 0 | 0, [5:10] | [1:2] | [3:4] | retag + * 1 |0, [5:10], retag| [1:2] | [3:4] | - + * 2 | 0, [5:10] | [1:3], retag | 4 | - + * 3 | 0, [5:10] |[1:2], 4, retag| 3 | - + * 4 | 0, 2, [5:10] | 1, retag | [3:4] | - + * 5 | 0, 1, [5:10] | 2, retag | [3:4] | - + * 14 | 0, [5:10] | [1:4], retag | - | - + * 15 | [5:10] | [0:4], retag | - | - + */ +static void sja1110_select_tdmaconfigidx(struct sja1105_private *priv) +{ + struct sja1105_general_params_entry *general_params; + struct sja1105_table *table; + bool port_1_is_base_tx; + bool port_3_is_2500; + bool port_4_is_2500; + u64 tdmaconfigidx; + + if (priv->info->device_id != SJA1110_DEVICE_ID) + return; + + table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS]; + general_params = table->entries; + + /* All the settings below are "as opposed to SGMII", which is the + * other pinmuxing option. + */ + port_1_is_base_tx = priv->phy_mode[1] == PHY_INTERFACE_MODE_INTERNAL; + port_3_is_2500 = priv->phy_mode[3] == PHY_INTERFACE_MODE_2500BASEX; + port_4_is_2500 = priv->phy_mode[4] == PHY_INTERFACE_MODE_2500BASEX; + + if (port_1_is_base_tx) + /* Retagging port will operate at 1 Gbps */ + tdmaconfigidx = 5; + else if (port_3_is_2500 && port_4_is_2500) + /* Retagging port will operate at 100 Mbps */ + tdmaconfigidx = 1; + else if (port_3_is_2500) + /* Retagging port will operate at 1 Gbps */ + tdmaconfigidx = 3; + else if (port_4_is_2500) + /* Retagging port will operate at 1 Gbps */ + tdmaconfigidx = 2; + else + /* Retagging port will operate at 1 Gbps */ + tdmaconfigidx = 14; + + general_params->tdmaconfigidx = tdmaconfigidx; +} + static int sja1105_init_general_params(struct sja1105_private *priv) { struct sja1105_general_params_entry default_general_params = { @@ -530,17 +653,9 @@ static int sja1105_init_general_params(struct sja1105_private *priv) * receieved on host_port itself would be dropped, except * by installing a temporary 'management route' */ - .host_port = dsa_upstream_port(priv->ds, 0), + .host_port = priv->ds->num_ports, /* Default to an invalid value */ - .mirr_port = SJA1105_NUM_PORTS, - /* Link-local traffic received on casc_port will be forwarded - * to host_port without embedding the source port and device ID - * info in the destination MAC address (presumably because it - * is a cascaded port and a downstream SJA switch already did - * that). Default to an invalid port (to disable the feature) - * and overwrite this if we find any DSA (cascaded) ports. - */ - .casc_port = SJA1105_NUM_PORTS, + .mirr_port = priv->ds->num_ports, /* No TTEthernet */ .vllupformat = SJA1105_VL_FORMAT_PSFP, .vlmarker = 0, @@ -552,8 +667,22 @@ static int sja1105_init_general_params(struct sja1105_private *priv) */ .tpid = ETH_P_SJA1105, .tpid2 = ETH_P_SJA1105, + /* Enable the TTEthernet engine on SJA1110 */ + .tte_en = true, + /* Set up the EtherType for control packets on SJA1110 */ + .header_type = ETH_P_SJA1110, }; + struct sja1105_general_params_entry *general_params; + struct dsa_switch *ds = priv->ds; struct sja1105_table *table; + int port; + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_is_cpu_port(ds, port)) { + default_general_params.host_port = port; + break; + } + } table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS]; @@ -562,16 +691,32 @@ static int sja1105_init_general_params(struct sja1105_private *priv) table->entry_count = 0; } - table->entries = kcalloc(SJA1105_MAX_GENERAL_PARAMS_COUNT, + table->entries = kcalloc(table->ops->max_entry_count, table->ops->unpacked_entry_size, GFP_KERNEL); if (!table->entries) return -ENOMEM; - table->entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT; + table->entry_count = table->ops->max_entry_count; + + general_params = table->entries; /* This table only has a single entry */ - ((struct sja1105_general_params_entry *)table->entries)[0] = - default_general_params; + general_params[0] = default_general_params; + + sja1110_select_tdmaconfigidx(priv); + + /* Link-local traffic received on casc_port will be forwarded + * to host_port without embedding the source port and device ID + * info in the destination MAC address, and no RX timestamps will be + * taken either (presumably because it is a cascaded port and a + * downstream SJA switch already did that). + * To disable the feature, we need to do different things depending on + * switch generation. On SJA1105 we need to set an invalid port, while + * on SJA1110 which support multiple cascaded ports, this field is a + * bitmask so it must be left zero. + */ + if (!priv->info->multiple_cascade_ports) + general_params->casc_port = ds->num_ports; return 0; } @@ -589,12 +734,12 @@ static int sja1105_init_avb_params(struct sja1105_private *priv) table->entry_count = 0; } - table->entries = kcalloc(SJA1105_MAX_AVB_PARAMS_COUNT, + table->entries = kcalloc(table->ops->max_entry_count, table->ops->unpacked_entry_size, GFP_KERNEL); if (!table->entries) return -ENOMEM; - table->entry_count = SJA1105_MAX_AVB_PARAMS_COUNT; + table->entry_count = table->ops->max_entry_count; avb = table->entries; @@ -661,6 +806,7 @@ static int sja1105_init_avb_params(struct sja1105_private *priv) static int sja1105_init_l2_policing(struct sja1105_private *priv) { struct sja1105_l2_policing_entry *policing; + struct dsa_switch *ds = priv->ds; struct sja1105_table *table; int port, tc; @@ -672,27 +818,31 @@ static int sja1105_init_l2_policing(struct sja1105_private *priv) table->entry_count = 0; } - table->entries = kcalloc(SJA1105_MAX_L2_POLICING_COUNT, + table->entries = kcalloc(table->ops->max_entry_count, table->ops->unpacked_entry_size, GFP_KERNEL); if (!table->entries) return -ENOMEM; - table->entry_count = SJA1105_MAX_L2_POLICING_COUNT; + table->entry_count = table->ops->max_entry_count; policing = table->entries; /* Setup shared indices for the matchall policers */ - for (port = 0; port < SJA1105_NUM_PORTS; port++) { - int bcast = (SJA1105_NUM_PORTS * SJA1105_NUM_TC) + port; + for (port = 0; port < ds->num_ports; port++) { + int mcast = (ds->num_ports * (SJA1105_NUM_TC + 1)) + port; + int bcast = (ds->num_ports * SJA1105_NUM_TC) + port; for (tc = 0; tc < SJA1105_NUM_TC; tc++) policing[port * SJA1105_NUM_TC + tc].sharindx = port; policing[bcast].sharindx = port; + /* Only SJA1110 has multicast policers */ + if (mcast <= table->ops->max_entry_count) + policing[mcast].sharindx = port; } /* Setup the matchall policer parameters */ - for (port = 0; port < SJA1105_NUM_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { int mtu = VLAN_ETH_FRAME_LEN + ETH_FCS_LEN; if (dsa_is_cpu_port(priv->ds, port)) @@ -707,8 +857,7 @@ static int sja1105_init_l2_policing(struct sja1105_private *priv) return 0; } -static int sja1105_static_config_load(struct sja1105_private *priv, - struct sja1105_dt_port *ports) +static int sja1105_static_config_load(struct sja1105_private *priv) { int rc; @@ -723,7 +872,7 @@ static int sja1105_static_config_load(struct sja1105_private *priv, rc = sja1105_init_mac_settings(priv); if (rc < 0) return rc; - rc = sja1105_init_mii_settings(priv, ports); + rc = sja1105_init_mii_settings(priv); if (rc < 0) return rc; rc = sja1105_init_static_fdb(priv); @@ -748,6 +897,9 @@ static int sja1105_static_config_load(struct sja1105_private *priv, if (rc < 0) return rc; rc = sja1105_init_avb_params(priv); + if (rc < 0) + return rc; + rc = sja1110_init_pcp_remapping(priv); if (rc < 0) return rc; @@ -755,32 +907,31 @@ static int sja1105_static_config_load(struct sja1105_private *priv, return sja1105_static_config_upload(priv); } -static int sja1105_parse_rgmii_delays(struct sja1105_private *priv, - const struct sja1105_dt_port *ports) +static int sja1105_parse_rgmii_delays(struct sja1105_private *priv) { - int i; + struct dsa_switch *ds = priv->ds; + int port; - for (i = 0; i < SJA1105_NUM_PORTS; i++) { - if (ports[i].role == XMII_MAC) + for (port = 0; port < ds->num_ports; port++) { + if (!priv->fixed_link[port]) continue; - if (ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_RXID || - ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_ID) - priv->rgmii_rx_delay[i] = true; + if (priv->phy_mode[port] == PHY_INTERFACE_MODE_RGMII_RXID || + priv->phy_mode[port] == PHY_INTERFACE_MODE_RGMII_ID) + priv->rgmii_rx_delay[port] = true; - if (ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_TXID || - ports[i].phy_mode == PHY_INTERFACE_MODE_RGMII_ID) - priv->rgmii_tx_delay[i] = true; + if (priv->phy_mode[port] == PHY_INTERFACE_MODE_RGMII_TXID || + priv->phy_mode[port] == PHY_INTERFACE_MODE_RGMII_ID) + priv->rgmii_tx_delay[port] = true; - if ((priv->rgmii_rx_delay[i] || priv->rgmii_tx_delay[i]) && - !priv->info->setup_rgmii_delay) + if ((priv->rgmii_rx_delay[port] || priv->rgmii_tx_delay[port]) && + !priv->info->setup_rgmii_delay) return -EINVAL; } return 0; } static int sja1105_parse_ports_node(struct sja1105_private *priv, - struct sja1105_dt_port *ports, struct device_node *ports_node) { struct device *dev = &priv->spidev->dev; @@ -809,7 +960,6 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, of_node_put(child); return -ENODEV; } - ports[index].phy_mode = phy_mode; phy_node = of_parse_phandle(child, "phy-handle", 0); if (!phy_node) { @@ -822,25 +972,18 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, /* phy-handle is missing, but fixed-link isn't. * So it's a fixed link. Default to PHY role. */ - ports[index].role = XMII_PHY; + priv->fixed_link[index] = true; } else { - /* phy-handle present => put port in MAC role */ - ports[index].role = XMII_MAC; of_node_put(phy_node); } - /* The MAC/PHY role can be overridden with explicit bindings */ - if (of_property_read_bool(child, "sja1105,role-mac")) - ports[index].role = XMII_MAC; - else if (of_property_read_bool(child, "sja1105,role-phy")) - ports[index].role = XMII_PHY; + priv->phy_mode[index] = phy_mode; } return 0; } -static int sja1105_parse_dt(struct sja1105_private *priv, - struct sja1105_dt_port *ports) +static int sja1105_parse_dt(struct sja1105_private *priv) { struct device *dev = &priv->spidev->dev; struct device_node *switch_node = dev->of_node; @@ -848,113 +991,41 @@ static int sja1105_parse_dt(struct sja1105_private *priv, int rc; ports_node = of_get_child_by_name(switch_node, "ports"); + if (!ports_node) + ports_node = of_get_child_by_name(switch_node, "ethernet-ports"); if (!ports_node) { dev_err(dev, "Incorrect bindings: absent \"ports\" node\n"); return -ENODEV; } - rc = sja1105_parse_ports_node(priv, ports, ports_node); + rc = sja1105_parse_ports_node(priv, ports_node); of_node_put(ports_node); return rc; } -static int sja1105_sgmii_read(struct sja1105_private *priv, int pcs_reg) -{ - const struct sja1105_regs *regs = priv->info->regs; - u32 val; - int rc; - - rc = sja1105_xfer_u32(priv, SPI_READ, regs->sgmii + pcs_reg, &val, - NULL); - if (rc < 0) - return rc; - - return val; -} - -static int sja1105_sgmii_write(struct sja1105_private *priv, int pcs_reg, - u16 pcs_val) -{ - const struct sja1105_regs *regs = priv->info->regs; - u32 val = pcs_val; - int rc; - - rc = sja1105_xfer_u32(priv, SPI_WRITE, regs->sgmii + pcs_reg, &val, - NULL); - if (rc < 0) - return rc; - - return val; -} - -static void sja1105_sgmii_pcs_config(struct sja1105_private *priv, - bool an_enabled, bool an_master) -{ - u16 ac = SJA1105_AC_AUTONEG_MODE_SGMII; - - /* DIGITAL_CONTROL_1: Enable vendor-specific MMD1, allow the PHY to - * stop the clock during LPI mode, make the MAC reconfigure - * autonomously after PCS autoneg is done, flush the internal FIFOs. - */ - sja1105_sgmii_write(priv, SJA1105_DC1, SJA1105_DC1_EN_VSMMD1 | - SJA1105_DC1_CLOCK_STOP_EN | - SJA1105_DC1_MAC_AUTO_SW | - SJA1105_DC1_INIT); - /* DIGITAL_CONTROL_2: No polarity inversion for TX and RX lanes */ - sja1105_sgmii_write(priv, SJA1105_DC2, SJA1105_DC2_TX_POL_INV_DISABLE); - /* AUTONEG_CONTROL: Use SGMII autoneg */ - if (an_master) - ac |= SJA1105_AC_PHY_MODE | SJA1105_AC_SGMII_LINK; - sja1105_sgmii_write(priv, SJA1105_AC, ac); - /* BASIC_CONTROL: enable in-band AN now, if requested. Otherwise, - * sja1105_sgmii_pcs_force_speed must be called later for the link - * to become operational. - */ - if (an_enabled) - sja1105_sgmii_write(priv, MII_BMCR, - BMCR_ANENABLE | BMCR_ANRESTART); -} - -static void sja1105_sgmii_pcs_force_speed(struct sja1105_private *priv, - int speed) -{ - int pcs_speed; - - switch (speed) { - case SPEED_1000: - pcs_speed = BMCR_SPEED1000; - break; - case SPEED_100: - pcs_speed = BMCR_SPEED100; - break; - case SPEED_10: - pcs_speed = BMCR_SPEED10; - break; - default: - dev_err(priv->ds->dev, "Invalid speed %d\n", speed); - return; - } - sja1105_sgmii_write(priv, MII_BMCR, pcs_speed | BMCR_FULLDPLX); -} - /* Convert link speed from SJA1105 to ethtool encoding */ -static int sja1105_speed[] = { - [SJA1105_SPEED_AUTO] = SPEED_UNKNOWN, - [SJA1105_SPEED_10MBPS] = SPEED_10, - [SJA1105_SPEED_100MBPS] = SPEED_100, - [SJA1105_SPEED_1000MBPS] = SPEED_1000, -}; +static int sja1105_port_speed_to_ethtool(struct sja1105_private *priv, + u64 speed) +{ + if (speed == priv->info->port_speed[SJA1105_SPEED_10MBPS]) + return SPEED_10; + if (speed == priv->info->port_speed[SJA1105_SPEED_100MBPS]) + return SPEED_100; + if (speed == priv->info->port_speed[SJA1105_SPEED_1000MBPS]) + return SPEED_1000; + if (speed == priv->info->port_speed[SJA1105_SPEED_2500MBPS]) + return SPEED_2500; + return SPEED_UNKNOWN; +} /* Set link speed in the MAC configuration for a specific port. */ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port, int speed_mbps) { - struct sja1105_xmii_params_entry *mii; struct sja1105_mac_config_entry *mac; struct device *dev = priv->ds->dev; - sja1105_phy_interface_t phy_mode; - sja1105_speed_t speed; + u64 speed; int rc; /* On P/Q/R/S, one can read from the device via the MAC reconfiguration @@ -964,7 +1035,6 @@ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port, * reasonable approximation for both E/T and P/Q/R/S. */ mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries; - mii = priv->static_config.tables[BLK_IDX_XMII_PARAMS].entries; switch (speed_mbps) { case SPEED_UNKNOWN: @@ -975,16 +1045,19 @@ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port, * ok for power consumption in case AN will never complete - * otherwise PHYLINK should come back with a new update. */ - speed = SJA1105_SPEED_AUTO; + speed = priv->info->port_speed[SJA1105_SPEED_AUTO]; break; case SPEED_10: - speed = SJA1105_SPEED_10MBPS; + speed = priv->info->port_speed[SJA1105_SPEED_10MBPS]; break; case SPEED_100: - speed = SJA1105_SPEED_100MBPS; + speed = priv->info->port_speed[SJA1105_SPEED_100MBPS]; break; case SPEED_1000: - speed = SJA1105_SPEED_1000MBPS; + speed = priv->info->port_speed[SJA1105_SPEED_1000MBPS]; + break; + case SPEED_2500: + speed = priv->info->port_speed[SJA1105_SPEED_2500MBPS]; break; default: dev_err(dev, "Invalid speed %iMbps\n", speed_mbps); @@ -998,8 +1071,10 @@ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port, * Actually for the SGMII port, the MAC is fixed at 1 Gbps and * we need to configure the PCS only (if even that). */ - if (sja1105_supports_sgmii(priv, port)) - mac[port].speed = SJA1105_SPEED_1000MBPS; + if (priv->phy_mode[port] == PHY_INTERFACE_MODE_SGMII) + mac[port].speed = priv->info->port_speed[SJA1105_SPEED_1000MBPS]; + else if (priv->phy_mode[port] == PHY_INTERFACE_MODE_2500BASEX) + mac[port].speed = priv->info->port_speed[SJA1105_SPEED_2500MBPS]; else mac[port].speed = speed; @@ -1017,8 +1092,7 @@ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port, * the clock setup does interrupt the clock signal for a certain time * which causes trouble for all PHYs relying on this signal. */ - phy_mode = mii->xmii_mode[port]; - if (phy_mode != XMII_MODE_RGMII) + if (!phy_interface_mode_is_rgmii(priv->phy_mode[port])) return 0; return sja1105_clocking_setup_port(priv, port); @@ -1034,35 +1108,16 @@ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port, static bool sja1105_phy_mode_mismatch(struct sja1105_private *priv, int port, phy_interface_t interface) { - struct sja1105_xmii_params_entry *mii; - sja1105_phy_interface_t phy_mode; - - mii = priv->static_config.tables[BLK_IDX_XMII_PARAMS].entries; - phy_mode = mii->xmii_mode[port]; - - switch (interface) { - case PHY_INTERFACE_MODE_MII: - return (phy_mode != XMII_MODE_MII); - case PHY_INTERFACE_MODE_RMII: - return (phy_mode != XMII_MODE_RMII); - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_TXID: - return (phy_mode != XMII_MODE_RGMII); - case PHY_INTERFACE_MODE_SGMII: - return (phy_mode != XMII_MODE_SGMII); - default: - return true; - } + return priv->phy_mode[port] != interface; } static void sja1105_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state) { + struct dsa_port *dp = dsa_to_port(ds, port); struct sja1105_private *priv = ds->priv; - bool is_sgmii = sja1105_supports_sgmii(priv, port); + struct dw_xpcs *xpcs; if (sja1105_phy_mode_mismatch(priv, port, state->interface)) { dev_err(ds->dev, "Changing PHY mode to %s not supported!\n", @@ -1070,14 +1125,10 @@ static void sja1105_mac_config(struct dsa_switch *ds, int port, return; } - if (phylink_autoneg_inband(mode) && !is_sgmii) { - dev_err(ds->dev, "In-band AN not supported!\n"); - return; - } + xpcs = priv->xpcs[port]; - if (is_sgmii) - sja1105_sgmii_pcs_config(priv, phylink_autoneg_inband(mode), - false); + if (xpcs) + phylink_set_pcs(dp->pl, &xpcs->pcs); } static void sja1105_mac_link_down(struct dsa_switch *ds, int port, @@ -1098,9 +1149,6 @@ static void sja1105_mac_link_up(struct dsa_switch *ds, int port, sja1105_adjust_port_config(priv, port, speed); - if (sja1105_supports_sgmii(priv, port) && !phylink_autoneg_inband(mode)) - sja1105_sgmii_pcs_force_speed(priv, speed); - sja1105_inhibit_tx(priv, BIT(port), false); } @@ -1139,44 +1187,16 @@ static void sja1105_phylink_validate(struct dsa_switch *ds, int port, if (mii->xmii_mode[port] == XMII_MODE_RGMII || mii->xmii_mode[port] == XMII_MODE_SGMII) phylink_set(mask, 1000baseT_Full); + if (priv->info->supports_2500basex[port]) { + phylink_set(mask, 2500baseT_Full); + phylink_set(mask, 2500baseX_Full); + } bitmap_and(supported, supported, mask, __ETHTOOL_LINK_MODE_MASK_NBITS); bitmap_and(state->advertising, state->advertising, mask, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static int sja1105_mac_pcs_get_state(struct dsa_switch *ds, int port, - struct phylink_link_state *state) -{ - struct sja1105_private *priv = ds->priv; - int ais; - - /* Read the vendor-specific AUTONEG_INTR_STATUS register */ - ais = sja1105_sgmii_read(priv, SJA1105_AIS); - if (ais < 0) - return ais; - - switch (SJA1105_AIS_SPEED(ais)) { - case 0: - state->speed = SPEED_10; - break; - case 1: - state->speed = SPEED_100; - break; - case 2: - state->speed = SPEED_1000; - break; - default: - dev_err(ds->dev, "Invalid SGMII PCS speed %lu\n", - SJA1105_AIS_SPEED(ais)); - } - state->duplex = SJA1105_AIS_DUPLEX_MODE(ais); - state->an_complete = SJA1105_AIS_COMPLETE(ais); - state->link = SJA1105_AIS_LINK_STATUS(ais); - - return 0; -} - static int sja1105_find_static_fdb_entry(struct sja1105_private *priv, int port, const struct sja1105_l2_lookup_entry *requested) @@ -1635,7 +1655,7 @@ static int sja1105_bridge_member(struct dsa_switch *ds, int port, l2_fwd = priv->static_config.tables[BLK_IDX_L2_FORWARDING].entries; - for (i = 0; i < SJA1105_NUM_PORTS; i++) { + for (i = 0; i < ds->num_ports; i++) { /* Add this port to the forwarding matrix of the * other ports in the same bridge, and viceversa. */ @@ -1798,6 +1818,12 @@ static int sja1105_reload_cbs(struct sja1105_private *priv) { int rc = 0, i; + /* The credit based shapers are only allocated if + * CONFIG_NET_SCH_CBS is enabled. + */ + if (!priv->cbs) + return 0; + for (i = 0; i < priv->info->num_cbs_shapers; i++) { struct sja1105_cbs_entry *cbs = &priv->cbs[i]; @@ -1833,12 +1859,12 @@ int sja1105_static_config_reload(struct sja1105_private *priv, { struct ptp_system_timestamp ptp_sts_before; struct ptp_system_timestamp ptp_sts_after; + int speed_mbps[SJA1105_MAX_NUM_PORTS]; + u16 bmcr[SJA1105_MAX_NUM_PORTS] = {0}; struct sja1105_mac_config_entry *mac; - int speed_mbps[SJA1105_NUM_PORTS]; struct dsa_switch *ds = priv->ds; s64 t1, t2, t3, t4; s64 t12, t34; - u16 bmcr = 0; int rc, i; s64 now; @@ -1851,29 +1877,38 @@ int sja1105_static_config_reload(struct sja1105_private *priv, * switch wants to see in the static config in order to allow us to * change it through the dynamic interface later. */ - for (i = 0; i < SJA1105_NUM_PORTS; i++) { - speed_mbps[i] = sja1105_speed[mac[i].speed]; - mac[i].speed = SJA1105_SPEED_AUTO; - } + for (i = 0; i < ds->num_ports; i++) { + u32 reg_addr = mdiobus_c45_addr(MDIO_MMD_VEND2, MDIO_CTRL1); - if (sja1105_supports_sgmii(priv, SJA1105_SGMII_PORT)) - bmcr = sja1105_sgmii_read(priv, MII_BMCR); + speed_mbps[i] = sja1105_port_speed_to_ethtool(priv, + mac[i].speed); + mac[i].speed = priv->info->port_speed[SJA1105_SPEED_AUTO]; + + if (priv->xpcs[i]) + bmcr[i] = mdiobus_read(priv->mdio_pcs, i, reg_addr); + } /* No PTP operations can run right now */ mutex_lock(&priv->ptp_data.lock); rc = __sja1105_ptp_gettimex(ds, &now, &ptp_sts_before); - if (rc < 0) - goto out_unlock_ptp; + if (rc < 0) { + mutex_unlock(&priv->ptp_data.lock); + goto out; + } /* Reset switch and send updated static configuration */ rc = sja1105_static_config_upload(priv); - if (rc < 0) - goto out_unlock_ptp; + if (rc < 0) { + mutex_unlock(&priv->ptp_data.lock); + goto out; + } rc = __sja1105_ptp_settime(ds, 0, &ptp_sts_after); - if (rc < 0) - goto out_unlock_ptp; + if (rc < 0) { + mutex_unlock(&priv->ptp_data.lock); + goto out; + } t1 = timespec64_to_ns(&ptp_sts_before.pre_ts); t2 = timespec64_to_ns(&ptp_sts_before.post_ts); @@ -1888,7 +1923,6 @@ int sja1105_static_config_reload(struct sja1105_private *priv, __sja1105_ptp_adjtime(ds, now); -out_unlock_ptp: mutex_unlock(&priv->ptp_data.lock); dev_info(priv->ds->dev, @@ -1899,32 +1933,48 @@ out_unlock_ptp: * For these interfaces there is no dynamic configuration * needed, since PLLs have same settings at all speeds. */ - rc = sja1105_clocking_setup(priv); - if (rc < 0) - goto out; - - for (i = 0; i < SJA1105_NUM_PORTS; i++) { - rc = sja1105_adjust_port_config(priv, i, speed_mbps[i]); + if (priv->info->clocking_setup) { + rc = priv->info->clocking_setup(priv); if (rc < 0) goto out; } - if (sja1105_supports_sgmii(priv, SJA1105_SGMII_PORT)) { - bool an_enabled = !!(bmcr & BMCR_ANENABLE); + for (i = 0; i < ds->num_ports; i++) { + struct dw_xpcs *xpcs = priv->xpcs[i]; + unsigned int mode; - sja1105_sgmii_pcs_config(priv, an_enabled, false); + rc = sja1105_adjust_port_config(priv, i, speed_mbps[i]); + if (rc < 0) + goto out; - if (!an_enabled) { + if (!xpcs) + continue; + + if (bmcr[i] & BMCR_ANENABLE) + mode = MLO_AN_INBAND; + else if (priv->fixed_link[i]) + mode = MLO_AN_FIXED; + else + mode = MLO_AN_PHY; + + rc = xpcs_do_config(xpcs, priv->phy_mode[i], mode); + if (rc < 0) + goto out; + + if (!phylink_autoneg_inband(mode)) { int speed = SPEED_UNKNOWN; - if (bmcr & BMCR_SPEED1000) + if (priv->phy_mode[i] == PHY_INTERFACE_MODE_2500BASEX) + speed = SPEED_2500; + else if (bmcr[i] & BMCR_SPEED1000) speed = SPEED_1000; - else if (bmcr & BMCR_SPEED100) + else if (bmcr[i] & BMCR_SPEED100) speed = SPEED_100; else speed = SPEED_10; - sja1105_sgmii_pcs_force_speed(priv, speed); + xpcs_link_up(&xpcs->pcs, mode, priv->phy_mode[i], + speed, DUPLEX_FULL); } } @@ -2032,7 +2082,9 @@ static enum dsa_tag_protocol sja1105_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) { - return DSA_TAG_PROTO_SJA1105; + struct sja1105_private *priv = ds->priv; + + return priv->info->tag_proto; } static int sja1105_find_free_subvlan(u16 *subvlan_map, bool pvid) @@ -2272,6 +2324,7 @@ sja1105_build_bridge_vlans(struct sja1105_private *priv, new_vlan[match].vlan_bc |= BIT(v->port); if (!v->untagged) new_vlan[match].tag_port |= BIT(v->port); + new_vlan[match].type_entry = SJA1110_VLAN_D_TAG; } return 0; @@ -2294,6 +2347,7 @@ sja1105_build_dsa_8021q_vlans(struct sja1105_private *priv, new_vlan[match].vlan_bc |= BIT(v->port); if (!v->untagged) new_vlan[match].tag_port |= BIT(v->port); + new_vlan[match].type_entry = SJA1110_VLAN_D_TAG; } return 0; @@ -2354,6 +2408,7 @@ static int sja1105_build_subvlans(struct sja1105_private *priv, new_vlan[match].tag_port |= BIT(v->port); /* But it's always tagged towards the CPU */ new_vlan[match].tag_port |= BIT(upstream); + new_vlan[match].type_entry = SJA1110_VLAN_D_TAG; /* The Retagging Table generates packet *clones* with * the new VLAN. This is a very odd hardware quirk @@ -2521,6 +2576,7 @@ sja1105_build_crosschip_subvlans(struct sja1105_private *priv, if (!tmp->untagged) new_vlan[match].tag_port |= BIT(tmp->port); new_vlan[match].tag_port |= BIT(upstream); + new_vlan[match].type_entry = SJA1110_VLAN_D_TAG; /* Deny egress of @rx_vid towards our front-panel port. * This will force the switch to drop it, and we'll see * only the re-retagged packets (having the original, @@ -2611,7 +2667,7 @@ out: static int sja1105_build_vlan_table(struct sja1105_private *priv, bool notify) { - u16 subvlan_map[SJA1105_NUM_PORTS][DSA_8021Q_N_SUBVLAN]; + u16 subvlan_map[SJA1105_MAX_NUM_PORTS][DSA_8021Q_N_SUBVLAN]; struct sja1105_retagging_entry *new_retagging; struct sja1105_vlan_lookup_entry *new_vlan; struct sja1105_table *table; @@ -2958,11 +3014,10 @@ static const struct dsa_8021q_ops sja1105_dsa_8021q_ops = { */ static int sja1105_setup(struct dsa_switch *ds) { - struct sja1105_dt_port ports[SJA1105_NUM_PORTS]; struct sja1105_private *priv = ds->priv; int rc; - rc = sja1105_parse_dt(priv, ports); + rc = sja1105_parse_dt(priv); if (rc < 0) { dev_err(ds->dev, "Failed to parse DT: %d\n", rc); return rc; @@ -2971,7 +3026,7 @@ static int sja1105_setup(struct dsa_switch *ds) /* Error out early if internal delays are required through DT * and we can't apply them. */ - rc = sja1105_parse_rgmii_delays(priv, ports); + rc = sja1105_parse_rgmii_delays(priv); if (rc < 0) { dev_err(ds->dev, "RGMII delay not supported\n"); return rc; @@ -2982,18 +3037,42 @@ static int sja1105_setup(struct dsa_switch *ds) dev_err(ds->dev, "Failed to register PTP clock: %d\n", rc); return rc; } - /* Create and send configuration down to device */ - rc = sja1105_static_config_load(priv, ports); + + rc = sja1105_mdiobus_register(ds); if (rc < 0) { - dev_err(ds->dev, "Failed to load static config: %d\n", rc); + dev_err(ds->dev, "Failed to register MDIO bus: %pe\n", + ERR_PTR(rc)); goto out_ptp_clock_unregister; } - /* Configure the CGU (PHY link modes and speeds) */ - rc = sja1105_clocking_setup(priv); - if (rc < 0) { - dev_err(ds->dev, "Failed to configure MII clocking: %d\n", rc); - goto out_static_config_free; + + if (priv->info->disable_microcontroller) { + rc = priv->info->disable_microcontroller(priv); + if (rc < 0) { + dev_err(ds->dev, + "Failed to disable microcontroller: %pe\n", + ERR_PTR(rc)); + goto out_mdiobus_unregister; + } } + + /* Create and send configuration down to device */ + rc = sja1105_static_config_load(priv); + if (rc < 0) { + dev_err(ds->dev, "Failed to load static config: %d\n", rc); + goto out_mdiobus_unregister; + } + + /* Configure the CGU (PHY link modes and speeds) */ + if (priv->info->clocking_setup) { + rc = priv->info->clocking_setup(priv); + if (rc < 0) { + dev_err(ds->dev, + "Failed to configure MII clocking: %pe\n", + ERR_PTR(rc)); + goto out_static_config_free; + } + } + /* On SJA1105, VLAN filtering per se is always enabled in hardware. * The only thing we can do to disable it is lie about what the 802.1Q * EtherType is. @@ -3029,6 +3108,8 @@ static int sja1105_setup(struct dsa_switch *ds) out_devlink_teardown: sja1105_devlink_teardown(ds); +out_mdiobus_unregister: + sja1105_mdiobus_unregister(ds); out_ptp_clock_unregister: sja1105_ptp_clock_unregister(ds); out_static_config_free: @@ -3043,7 +3124,7 @@ static void sja1105_teardown(struct dsa_switch *ds) struct sja1105_bridge_vlan *v, *n; int port; - for (port = 0; port < SJA1105_NUM_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { struct sja1105_port *sp = &priv->ports[port]; if (!dsa_is_user_port(ds, port)) @@ -3246,6 +3327,7 @@ static int sja1105_mirror_apply(struct sja1105_private *priv, int from, int to, { struct sja1105_general_params_entry *general_params; struct sja1105_mac_config_entry *mac; + struct dsa_switch *ds = priv->ds; struct sja1105_table *table; bool already_enabled; u64 new_mirr_port; @@ -3256,7 +3338,7 @@ static int sja1105_mirror_apply(struct sja1105_private *priv, int from, int to, mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries; - already_enabled = (general_params->mirr_port != SJA1105_NUM_PORTS); + already_enabled = (general_params->mirr_port != ds->num_ports); if (already_enabled && enabled && general_params->mirr_port != to) { dev_err(priv->ds->dev, "Delete mirroring rules towards port %llu first\n", @@ -3270,7 +3352,7 @@ static int sja1105_mirror_apply(struct sja1105_private *priv, int from, int to, int port; /* Anybody still referencing mirr_port? */ - for (port = 0; port < SJA1105_NUM_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { if (mac[port].ing_mirr || mac[port].egr_mirr) { keep = true; break; @@ -3278,7 +3360,7 @@ static int sja1105_mirror_apply(struct sja1105_private *priv, int from, int to, } /* Unset already_enabled for next time */ if (!keep) - new_mirr_port = SJA1105_NUM_PORTS; + new_mirr_port = ds->num_ports; } if (new_mirr_port != general_params->mirr_port) { general_params->mirr_port = new_mirr_port; @@ -3489,7 +3571,6 @@ static const struct dsa_switch_ops sja1105_switch_ops = { .port_change_mtu = sja1105_change_mtu, .port_max_mtu = sja1105_get_max_mtu, .phylink_validate = sja1105_phylink_validate, - .phylink_mac_link_state = sja1105_mac_pcs_get_state, .phylink_mac_config = sja1105_mac_config, .phylink_mac_link_up = sja1105_mac_link_up, .phylink_mac_link_down = sja1105_mac_link_down, @@ -3584,6 +3665,7 @@ static int sja1105_probe(struct spi_device *spi) struct sja1105_tagger_data *tagger_data; struct device *dev = &spi->dev; struct sja1105_private *priv; + size_t max_xfer, max_msg; struct dsa_switch *ds; int rc, port; @@ -3617,6 +3699,33 @@ static int sja1105_probe(struct spi_device *spi) return rc; } + /* In sja1105_xfer, we send spi_messages composed of two spi_transfers: + * a small one for the message header and another one for the current + * chunk of the packed buffer. + * Check that the restrictions imposed by the SPI controller are + * respected: the chunk buffer is smaller than the max transfer size, + * and the total length of the chunk plus its message header is smaller + * than the max message size. + * We do that during probe time since the maximum transfer size is a + * runtime invariant. + */ + max_xfer = spi_max_transfer_size(spi); + max_msg = spi_max_message_size(spi); + + /* We need to send at least one 64-bit word of SPI payload per message + * in order to be able to make useful progress. + */ + if (max_msg < SJA1105_SIZE_SPI_MSG_HEADER + 8) { + dev_err(dev, "SPI master cannot send large enough buffers, aborting\n"); + return -EINVAL; + } + + priv->max_xfer_len = SJA1105_SIZE_SPI_MSG_MAXLEN; + if (priv->max_xfer_len > max_xfer) + priv->max_xfer_len = max_xfer; + if (priv->max_xfer_len > max_msg - SJA1105_SIZE_SPI_MSG_HEADER) + priv->max_xfer_len = max_msg - SJA1105_SIZE_SPI_MSG_HEADER; + priv->info = of_device_get_match_data(dev); /* Detect hardware device */ @@ -3633,7 +3742,7 @@ static int sja1105_probe(struct spi_device *spi) return -ENOMEM; ds->dev = dev; - ds->num_ports = SJA1105_NUM_PORTS; + ds->num_ports = priv->info->num_ports; ds->ops = &sja1105_switch_ops; ds->priv = priv; priv->ds = ds; @@ -3674,7 +3783,7 @@ static int sja1105_probe(struct spi_device *spi) } /* Connections between dsa_port and sja1105_port */ - for (port = 0; port < SJA1105_NUM_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { struct sja1105_port *sp = &priv->ports[port]; struct dsa_port *dp = dsa_to_port(ds, port); struct net_device *slave; @@ -3737,6 +3846,10 @@ static const struct of_device_id sja1105_dt_ids[] = { { .compatible = "nxp,sja1105q", .data = &sja1105q_info }, { .compatible = "nxp,sja1105r", .data = &sja1105r_info }, { .compatible = "nxp,sja1105s", .data = &sja1105s_info }, + { .compatible = "nxp,sja1110a", .data = &sja1110a_info }, + { .compatible = "nxp,sja1110b", .data = &sja1110b_info }, + { .compatible = "nxp,sja1110c", .data = &sja1110c_info }, + { .compatible = "nxp,sja1110d", .data = &sja1110d_info }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, sja1105_dt_ids); diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c new file mode 100644 index 000000000000..19aea8fb76f6 --- /dev/null +++ b/drivers/net/dsa/sja1105/sja1105_mdio.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2021, NXP Semiconductors + */ +#include +#include +#include "sja1105.h" + +#define SJA1110_PCS_BANK_REG SJA1110_SPI_ADDR(0x3fc) + +int sja1105_pcs_mdio_read(struct mii_bus *bus, int phy, int reg) +{ + struct sja1105_mdio_private *mdio_priv = bus->priv; + struct sja1105_private *priv = mdio_priv->priv; + u64 addr; + u32 tmp; + u16 mmd; + int rc; + + if (!(reg & MII_ADDR_C45)) + return -EINVAL; + + mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f; + addr = (mmd << 16) | (reg & GENMASK(15, 0)); + + if (mmd != MDIO_MMD_VEND1 && mmd != MDIO_MMD_VEND2) + return 0xffff; + + if (mmd == MDIO_MMD_VEND2 && (reg & GENMASK(15, 0)) == MII_PHYSID1) + return NXP_SJA1105_XPCS_ID >> 16; + if (mmd == MDIO_MMD_VEND2 && (reg & GENMASK(15, 0)) == MII_PHYSID2) + return NXP_SJA1105_XPCS_ID & GENMASK(15, 0); + + rc = sja1105_xfer_u32(priv, SPI_READ, addr, &tmp, NULL); + if (rc < 0) + return rc; + + return tmp & 0xffff; +} + +int sja1105_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val) +{ + struct sja1105_mdio_private *mdio_priv = bus->priv; + struct sja1105_private *priv = mdio_priv->priv; + u64 addr; + u32 tmp; + u16 mmd; + + if (!(reg & MII_ADDR_C45)) + return -EINVAL; + + mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f; + addr = (mmd << 16) | (reg & GENMASK(15, 0)); + tmp = val; + + if (mmd != MDIO_MMD_VEND1 && mmd != MDIO_MMD_VEND2) + return -EINVAL; + + return sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL); +} + +int sja1110_pcs_mdio_read(struct mii_bus *bus, int phy, int reg) +{ + struct sja1105_mdio_private *mdio_priv = bus->priv; + struct sja1105_private *priv = mdio_priv->priv; + const struct sja1105_regs *regs = priv->info->regs; + int offset, bank; + u64 addr; + u32 tmp; + u16 mmd; + int rc; + + if (!(reg & MII_ADDR_C45)) + return -EINVAL; + + if (regs->pcs_base[phy] == SJA1105_RSV_ADDR) + return -ENODEV; + + mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f; + addr = (mmd << 16) | (reg & GENMASK(15, 0)); + + if (mmd == MDIO_MMD_VEND2 && (reg & GENMASK(15, 0)) == MII_PHYSID1) + return NXP_SJA1110_XPCS_ID >> 16; + if (mmd == MDIO_MMD_VEND2 && (reg & GENMASK(15, 0)) == MII_PHYSID2) + return NXP_SJA1110_XPCS_ID & GENMASK(15, 0); + + bank = addr >> 8; + offset = addr & GENMASK(7, 0); + + /* This addressing scheme reserves register 0xff for the bank address + * register, so that can never be addressed. + */ + if (WARN_ON(offset == 0xff)) + return -ENODEV; + + tmp = bank; + + rc = sja1105_xfer_u32(priv, SPI_WRITE, + regs->pcs_base[phy] + SJA1110_PCS_BANK_REG, + &tmp, NULL); + if (rc < 0) + return rc; + + rc = sja1105_xfer_u32(priv, SPI_READ, regs->pcs_base[phy] + offset, + &tmp, NULL); + if (rc < 0) + return rc; + + return tmp & 0xffff; +} + +int sja1110_pcs_mdio_write(struct mii_bus *bus, int phy, int reg, u16 val) +{ + struct sja1105_mdio_private *mdio_priv = bus->priv; + struct sja1105_private *priv = mdio_priv->priv; + const struct sja1105_regs *regs = priv->info->regs; + int offset, bank; + u64 addr; + u32 tmp; + u16 mmd; + int rc; + + if (!(reg & MII_ADDR_C45)) + return -EINVAL; + + if (regs->pcs_base[phy] == SJA1105_RSV_ADDR) + return -ENODEV; + + mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f; + addr = (mmd << 16) | (reg & GENMASK(15, 0)); + + bank = addr >> 8; + offset = addr & GENMASK(7, 0); + + /* This addressing scheme reserves register 0xff for the bank address + * register, so that can never be addressed. + */ + if (WARN_ON(offset == 0xff)) + return -ENODEV; + + tmp = bank; + + rc = sja1105_xfer_u32(priv, SPI_WRITE, + regs->pcs_base[phy] + SJA1110_PCS_BANK_REG, + &tmp, NULL); + if (rc < 0) + return rc; + + tmp = val; + + return sja1105_xfer_u32(priv, SPI_WRITE, regs->pcs_base[phy] + offset, + &tmp, NULL); +} + +enum sja1105_mdio_opcode { + SJA1105_C45_ADDR = 0, + SJA1105_C22 = 1, + SJA1105_C45_DATA = 2, + SJA1105_C45_DATA_AUTOINC = 3, +}; + +static u64 sja1105_base_t1_encode_addr(struct sja1105_private *priv, + int phy, enum sja1105_mdio_opcode op, + int xad) +{ + const struct sja1105_regs *regs = priv->info->regs; + + return regs->mdio_100base_t1 | (phy << 7) | (op << 5) | (xad << 0); +} + +static int sja1105_base_t1_mdio_read(struct mii_bus *bus, int phy, int reg) +{ + struct sja1105_mdio_private *mdio_priv = bus->priv; + struct sja1105_private *priv = mdio_priv->priv; + u64 addr; + u32 tmp; + int rc; + + if (reg & MII_ADDR_C45) { + u16 mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f; + + addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_ADDR, + mmd); + + tmp = reg & MII_REGADDR_C45_MASK; + + rc = sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL); + if (rc < 0) + return rc; + + addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_DATA, + mmd); + + rc = sja1105_xfer_u32(priv, SPI_READ, addr, &tmp, NULL); + if (rc < 0) + return rc; + + return tmp & 0xffff; + } + + /* Clause 22 read */ + addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C22, reg & 0x1f); + + rc = sja1105_xfer_u32(priv, SPI_READ, addr, &tmp, NULL); + if (rc < 0) + return rc; + + return tmp & 0xffff; +} + +static int sja1105_base_t1_mdio_write(struct mii_bus *bus, int phy, int reg, + u16 val) +{ + struct sja1105_mdio_private *mdio_priv = bus->priv; + struct sja1105_private *priv = mdio_priv->priv; + u64 addr; + u32 tmp; + int rc; + + if (reg & MII_ADDR_C45) { + u16 mmd = (reg >> MII_DEVADDR_C45_SHIFT) & 0x1f; + + addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_ADDR, + mmd); + + tmp = reg & MII_REGADDR_C45_MASK; + + rc = sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL); + if (rc < 0) + return rc; + + addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C45_DATA, + mmd); + + tmp = val & 0xffff; + + rc = sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL); + if (rc < 0) + return rc; + + return 0; + } + + /* Clause 22 write */ + addr = sja1105_base_t1_encode_addr(priv, phy, SJA1105_C22, reg & 0x1f); + + tmp = val & 0xffff; + + return sja1105_xfer_u32(priv, SPI_WRITE, addr, &tmp, NULL); +} + +static int sja1105_base_tx_mdio_read(struct mii_bus *bus, int phy, int reg) +{ + struct sja1105_mdio_private *mdio_priv = bus->priv; + struct sja1105_private *priv = mdio_priv->priv; + const struct sja1105_regs *regs = priv->info->regs; + u32 tmp; + int rc; + + rc = sja1105_xfer_u32(priv, SPI_READ, regs->mdio_100base_tx + reg, + &tmp, NULL); + if (rc < 0) + return rc; + + return tmp & 0xffff; +} + +static int sja1105_base_tx_mdio_write(struct mii_bus *bus, int phy, int reg, + u16 val) +{ + struct sja1105_mdio_private *mdio_priv = bus->priv; + struct sja1105_private *priv = mdio_priv->priv; + const struct sja1105_regs *regs = priv->info->regs; + u32 tmp = val; + + return sja1105_xfer_u32(priv, SPI_WRITE, regs->mdio_100base_tx + reg, + &tmp, NULL); +} + +static int sja1105_mdiobus_base_tx_register(struct sja1105_private *priv, + struct device_node *mdio_node) +{ + struct sja1105_mdio_private *mdio_priv; + struct device_node *np; + struct mii_bus *bus; + int rc = 0; + + np = of_find_compatible_node(mdio_node, NULL, + "nxp,sja1110-base-tx-mdio"); + if (!np) + return 0; + + if (!of_device_is_available(np)) + goto out_put_np; + + bus = mdiobus_alloc_size(sizeof(*mdio_priv)); + if (!bus) { + rc = -ENOMEM; + goto out_put_np; + } + + bus->name = "SJA1110 100base-TX MDIO bus"; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-base-tx", + dev_name(priv->ds->dev)); + bus->read = sja1105_base_tx_mdio_read; + bus->write = sja1105_base_tx_mdio_write; + bus->parent = priv->ds->dev; + mdio_priv = bus->priv; + mdio_priv->priv = priv; + + rc = of_mdiobus_register(bus, np); + if (rc) { + mdiobus_free(bus); + goto out_put_np; + } + + priv->mdio_base_tx = bus; + +out_put_np: + of_node_put(np); + + return rc; +} + +static void sja1105_mdiobus_base_tx_unregister(struct sja1105_private *priv) +{ + if (!priv->mdio_base_tx) + return; + + mdiobus_unregister(priv->mdio_base_tx); + mdiobus_free(priv->mdio_base_tx); + priv->mdio_base_tx = NULL; +} + +static int sja1105_mdiobus_base_t1_register(struct sja1105_private *priv, + struct device_node *mdio_node) +{ + struct sja1105_mdio_private *mdio_priv; + struct device_node *np; + struct mii_bus *bus; + int rc = 0; + + np = of_find_compatible_node(mdio_node, NULL, + "nxp,sja1110-base-t1-mdio"); + if (!np) + return 0; + + if (!of_device_is_available(np)) + goto out_put_np; + + bus = mdiobus_alloc_size(sizeof(*mdio_priv)); + if (!bus) { + rc = -ENOMEM; + goto out_put_np; + } + + bus->name = "SJA1110 100base-T1 MDIO bus"; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-base-t1", + dev_name(priv->ds->dev)); + bus->read = sja1105_base_t1_mdio_read; + bus->write = sja1105_base_t1_mdio_write; + bus->parent = priv->ds->dev; + mdio_priv = bus->priv; + mdio_priv->priv = priv; + + rc = of_mdiobus_register(bus, np); + if (rc) { + mdiobus_free(bus); + goto out_put_np; + } + + priv->mdio_base_t1 = bus; + +out_put_np: + of_node_put(np); + + return rc; +} + +static void sja1105_mdiobus_base_t1_unregister(struct sja1105_private *priv) +{ + if (!priv->mdio_base_t1) + return; + + mdiobus_unregister(priv->mdio_base_t1); + mdiobus_free(priv->mdio_base_t1); + priv->mdio_base_t1 = NULL; +} + +static int sja1105_mdiobus_pcs_register(struct sja1105_private *priv) +{ + struct sja1105_mdio_private *mdio_priv; + struct dsa_switch *ds = priv->ds; + struct mii_bus *bus; + int rc = 0; + int port; + + if (!priv->info->pcs_mdio_read || !priv->info->pcs_mdio_write) + return 0; + + bus = mdiobus_alloc_size(sizeof(*mdio_priv)); + if (!bus) + return -ENOMEM; + + bus->name = "SJA1105 PCS MDIO bus"; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-pcs", + dev_name(ds->dev)); + bus->read = priv->info->pcs_mdio_read; + bus->write = priv->info->pcs_mdio_write; + bus->parent = ds->dev; + /* There is no PHY on this MDIO bus => mask out all PHY addresses + * from auto probing. + */ + bus->phy_mask = ~0; + mdio_priv = bus->priv; + mdio_priv->priv = priv; + + rc = mdiobus_register(bus); + if (rc) { + mdiobus_free(bus); + return rc; + } + + for (port = 0; port < ds->num_ports; port++) { + struct mdio_device *mdiodev; + struct dw_xpcs *xpcs; + + if (dsa_is_unused_port(ds, port)) + continue; + + if (priv->phy_mode[port] != PHY_INTERFACE_MODE_SGMII && + priv->phy_mode[port] != PHY_INTERFACE_MODE_2500BASEX) + continue; + + mdiodev = mdio_device_create(bus, port); + if (IS_ERR(mdiodev)) { + rc = PTR_ERR(mdiodev); + goto out_pcs_free; + } + + xpcs = xpcs_create(mdiodev, priv->phy_mode[port]); + if (IS_ERR(xpcs)) { + rc = PTR_ERR(xpcs); + goto out_pcs_free; + } + + priv->xpcs[port] = xpcs; + } + + priv->mdio_pcs = bus; + + return 0; + +out_pcs_free: + for (port = 0; port < ds->num_ports; port++) { + if (!priv->xpcs[port]) + continue; + + mdio_device_free(priv->xpcs[port]->mdiodev); + xpcs_destroy(priv->xpcs[port]); + priv->xpcs[port] = NULL; + } + + mdiobus_unregister(bus); + mdiobus_free(bus); + + return rc; +} + +static void sja1105_mdiobus_pcs_unregister(struct sja1105_private *priv) +{ + struct dsa_switch *ds = priv->ds; + int port; + + if (!priv->mdio_pcs) + return; + + for (port = 0; port < ds->num_ports; port++) { + if (!priv->xpcs[port]) + continue; + + mdio_device_free(priv->xpcs[port]->mdiodev); + xpcs_destroy(priv->xpcs[port]); + priv->xpcs[port] = NULL; + } + + mdiobus_unregister(priv->mdio_pcs); + mdiobus_free(priv->mdio_pcs); + priv->mdio_pcs = NULL; +} + +int sja1105_mdiobus_register(struct dsa_switch *ds) +{ + struct sja1105_private *priv = ds->priv; + const struct sja1105_regs *regs = priv->info->regs; + struct device_node *switch_node = ds->dev->of_node; + struct device_node *mdio_node; + int rc; + + rc = sja1105_mdiobus_pcs_register(priv); + if (rc) + return rc; + + mdio_node = of_get_child_by_name(switch_node, "mdios"); + if (!mdio_node) + return 0; + + if (!of_device_is_available(mdio_node)) + goto out_put_mdio_node; + + if (regs->mdio_100base_tx != SJA1105_RSV_ADDR) { + rc = sja1105_mdiobus_base_tx_register(priv, mdio_node); + if (rc) + goto err_put_mdio_node; + } + + if (regs->mdio_100base_t1 != SJA1105_RSV_ADDR) { + rc = sja1105_mdiobus_base_t1_register(priv, mdio_node); + if (rc) + goto err_free_base_tx_mdiobus; + } + +out_put_mdio_node: + of_node_put(mdio_node); + + return 0; + +err_free_base_tx_mdiobus: + sja1105_mdiobus_base_tx_unregister(priv); +err_put_mdio_node: + of_node_put(mdio_node); + sja1105_mdiobus_pcs_unregister(priv); + + return rc; +} + +void sja1105_mdiobus_unregister(struct dsa_switch *ds) +{ + struct sja1105_private *priv = ds->priv; + + sja1105_mdiobus_base_t1_unregister(priv); + sja1105_mdiobus_base_tx_unregister(priv); + sja1105_mdiobus_pcs_unregister(priv); +} diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index 0bc566b9e958..691f6dd7e669 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -79,6 +79,7 @@ static int sja1105_change_rxtstamping(struct sja1105_private *priv, priv->tagger_data.stampable_skb = NULL; } ptp_cancel_worker_sync(ptp_data->clock); + skb_queue_purge(&ptp_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); return sja1105_static_config_reload(priv, SJA1105_RX_HWTSTAMPING); @@ -397,7 +398,7 @@ static long sja1105_rxtstamp_work(struct ptp_clock_info *ptp) *shwt = (struct skb_shared_hwtstamps) {0}; - ts = SJA1105_SKB_CB(skb)->meta_tstamp; + ts = SJA1105_SKB_CB(skb)->tstamp; ts = sja1105_tstamp_reconstruct(ds, ticks, ts); shwt->hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(ts)); @@ -413,9 +414,7 @@ static long sja1105_rxtstamp_work(struct ptp_clock_info *ptp) return -1; } -/* Called from dsa_skb_defer_rx_timestamp */ -bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, - struct sk_buff *skb, unsigned int type) +bool sja1105_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) { struct sja1105_private *priv = ds->priv; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; @@ -431,6 +430,89 @@ bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, return true; } +bool sja1110_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) +{ + struct skb_shared_hwtstamps *shwt = skb_hwtstamps(skb); + u64 ts = SJA1105_SKB_CB(skb)->tstamp; + + *shwt = (struct skb_shared_hwtstamps) {0}; + + shwt->hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(ts)); + + /* Don't defer */ + return false; +} + +/* Called from dsa_skb_defer_rx_timestamp */ +bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, + struct sk_buff *skb, unsigned int type) +{ + struct sja1105_private *priv = ds->priv; + + return priv->info->rxtstamp(ds, port, skb); +} + +void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp) +{ + struct sja1105_private *priv = ds->priv; + struct sja1105_ptp_data *ptp_data = &priv->ptp_data; + struct sk_buff *skb, *skb_tmp, *skb_match = NULL; + struct skb_shared_hwtstamps shwt = {0}; + + /* We don't care about RX timestamps on the CPU port */ + if (dir == SJA1110_META_TSTAMP_RX) + return; + + spin_lock(&ptp_data->skb_txtstamp_queue.lock); + + skb_queue_walk_safe(&ptp_data->skb_txtstamp_queue, skb, skb_tmp) { + if (SJA1105_SKB_CB(skb)->ts_id != ts_id) + continue; + + __skb_unlink(skb, &ptp_data->skb_txtstamp_queue); + skb_match = skb; + + break; + } + + spin_unlock(&ptp_data->skb_txtstamp_queue.lock); + + if (WARN_ON(!skb_match)) + return; + + shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp)); + skb_complete_tx_timestamp(skb_match, &shwt); +} +EXPORT_SYMBOL_GPL(sja1110_process_meta_tstamp); + +/* In addition to cloning the skb which is done by the common + * sja1105_port_txtstamp, we need to generate a timestamp ID and save the + * packet to the TX timestamping queue. + */ +void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) +{ + struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; + struct sja1105_private *priv = ds->priv; + struct sja1105_ptp_data *ptp_data = &priv->ptp_data; + struct sja1105_port *sp = &priv->ports[port]; + u8 ts_id; + + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + + spin_lock(&sp->data->meta_lock); + + ts_id = sp->data->ts_id; + /* Deal automatically with 8-bit wraparound */ + sp->data->ts_id++; + + SJA1105_SKB_CB(clone)->ts_id = ts_id; + + spin_unlock(&sp->data->meta_lock); + + skb_queue_tail(&ptp_data->skb_txtstamp_queue, clone); +} + /* Called from dsa_skb_tx_timestamp. This callback is just to clone * the skb and have it available in SJA1105_SKB_CB in the .port_deferred_xmit * callback, where we will timestamp it synchronously. @@ -449,6 +531,9 @@ void sja1105_port_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) return; SJA1105_SKB_CB(skb)->clone = clone; + + if (priv->info->txtstamp) + priv->info->txtstamp(ds, port, skb); } static int sja1105_ptp_reset(struct dsa_switch *ds) @@ -865,7 +950,10 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) .n_per_out = 1, }; + /* Only used on SJA1105 */ skb_queue_head_init(&ptp_data->skb_rxtstamp_queue); + /* Only used on SJA1110 */ + skb_queue_head_init(&ptp_data->skb_txtstamp_queue); spin_lock_init(&tagger_data->meta_lock); ptp_data->clock = ptp_clock_register(&ptp_data->caps, ds->dev); @@ -890,6 +978,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds) del_timer_sync(&ptp_data->extts_timer); ptp_cancel_worker_sync(ptp_data->clock); + skb_queue_purge(&ptp_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); ptp_clock_unregister(ptp_data->clock); ptp_data->clock = NULL; diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h index 34f97f58a355..3c874bb4c17b 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.h +++ b/drivers/net/dsa/sja1105/sja1105_ptp.h @@ -75,7 +75,12 @@ struct sja1105_ptp_cmd { struct sja1105_ptp_data { struct timer_list extts_timer; + /* Used only on SJA1105 to reconstruct partial timestamps */ struct sk_buff_head skb_rxtstamp_queue; + /* Used on SJA1110 where meta frames are generated only for + * 2-step TX timestamps + */ + struct sk_buff_head skb_txtstamp_queue; struct ptp_clock_info caps; struct ptp_clock *clock; struct sja1105_ptp_cmd cmd; @@ -122,6 +127,10 @@ int __sja1105_ptp_adjtime(struct dsa_switch *ds, s64 delta); int sja1105_ptp_commit(struct dsa_switch *ds, struct sja1105_ptp_cmd *cmd, sja1105_spi_rw_mode_t rw); +bool sja1105_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); +bool sja1110_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); +void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); + #else struct sja1105_ptp_cmd; @@ -184,6 +193,10 @@ static inline int sja1105_ptp_commit(struct dsa_switch *ds, #define sja1105_hwtstamp_set NULL +#define sja1105_rxtstamp NULL +#define sja1110_rxtstamp NULL +#define sja1110_txtstamp NULL + #endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ #endif /* _SJA1105_PTP_H */ diff --git a/drivers/net/dsa/sja1105/sja1105_sgmii.h b/drivers/net/dsa/sja1105/sja1105_sgmii.h deleted file mode 100644 index 24d9bc046e70..000000000000 --- a/drivers/net/dsa/sja1105/sja1105_sgmii.h +++ /dev/null @@ -1,53 +0,0 @@ -/* SPDX-License-Identifier: BSD-3-Clause */ -/* Copyright 2020, NXP Semiconductors - */ -#ifndef _SJA1105_SGMII_H -#define _SJA1105_SGMII_H - -#define SJA1105_SGMII_PORT 4 - -/* DIGITAL_CONTROL_1 (address 1f8000h) */ -#define SJA1105_DC1 0x8000 -#define SJA1105_DC1_VS_RESET BIT(15) -#define SJA1105_DC1_REMOTE_LOOPBACK BIT(14) -#define SJA1105_DC1_EN_VSMMD1 BIT(13) -#define SJA1105_DC1_POWER_SAVE BIT(11) -#define SJA1105_DC1_CLOCK_STOP_EN BIT(10) -#define SJA1105_DC1_MAC_AUTO_SW BIT(9) -#define SJA1105_DC1_INIT BIT(8) -#define SJA1105_DC1_TX_DISABLE BIT(4) -#define SJA1105_DC1_AUTONEG_TIMER_OVRR BIT(3) -#define SJA1105_DC1_BYP_POWERUP BIT(1) -#define SJA1105_DC1_PHY_MODE_CONTROL BIT(0) - -/* DIGITAL_CONTROL_2 register (address 1f80E1h) */ -#define SJA1105_DC2 0x80e1 -#define SJA1105_DC2_TX_POL_INV_DISABLE BIT(4) -#define SJA1105_DC2_RX_POL_INV BIT(0) - -/* DIGITAL_ERROR_CNT register (address 1f80E2h) */ -#define SJA1105_DEC 0x80e2 -#define SJA1105_DEC_ICG_EC_ENA BIT(4) -#define SJA1105_DEC_CLEAR_ON_READ BIT(0) - -/* AUTONEG_CONTROL register (address 1f8001h) */ -#define SJA1105_AC 0x8001 -#define SJA1105_AC_MII_CONTROL BIT(8) -#define SJA1105_AC_SGMII_LINK BIT(4) -#define SJA1105_AC_PHY_MODE BIT(3) -#define SJA1105_AC_AUTONEG_MODE(x) (((x) << 1) & GENMASK(2, 1)) -#define SJA1105_AC_AUTONEG_MODE_SGMII SJA1105_AC_AUTONEG_MODE(2) - -/* AUTONEG_INTR_STATUS register (address 1f8002h) */ -#define SJA1105_AIS 0x8002 -#define SJA1105_AIS_LINK_STATUS(x) (!!((x) & BIT(4))) -#define SJA1105_AIS_SPEED(x) (((x) & GENMASK(3, 2)) >> 2) -#define SJA1105_AIS_DUPLEX_MODE(x) (!!((x) & BIT(1))) -#define SJA1105_AIS_COMPLETE(x) (!!((x) & BIT(0))) - -/* DEBUG_CONTROL register (address 1f8005h) */ -#define SJA1105_DC 0x8005 -#define SJA1105_DC_SUPPRESS_LOS BIT(4) -#define SJA1105_DC_RESTART_SYNC BIT(0) - -#endif diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index f7a1514f81e8..08cc5dbf2fa6 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -7,10 +7,6 @@ #include #include "sja1105.h" -#define SJA1105_SIZE_RESET_CMD 4 -#define SJA1105_SIZE_SPI_MSG_HEADER 4 -#define SJA1105_SIZE_SPI_MSG_MAXLEN (64 * 4) - struct sja1105_chunk { u8 *buf; size_t len; @@ -29,13 +25,6 @@ sja1105_spi_message_pack(void *buf, const struct sja1105_spi_message *msg) sja1105_pack(buf, &msg->address, 24, 4, size); } -#define sja1105_hdr_xfer(xfers, chunk) \ - ((xfers) + 2 * (chunk)) -#define sja1105_chunk_xfer(xfers, chunk) \ - ((xfers) + 2 * (chunk) + 1) -#define sja1105_hdr_buf(hdr_bufs, chunk) \ - ((hdr_bufs) + (chunk) * SJA1105_SIZE_SPI_MSG_HEADER) - /* If @rw is: * - SPI_WRITE: creates and sends an SPI write message at absolute * address reg_addr, taking @len bytes from *buf @@ -46,41 +35,25 @@ static int sja1105_xfer(const struct sja1105_private *priv, sja1105_spi_rw_mode_t rw, u64 reg_addr, u8 *buf, size_t len, struct ptp_system_timestamp *ptp_sts) { - struct sja1105_chunk chunk = { - .len = min_t(size_t, len, SJA1105_SIZE_SPI_MSG_MAXLEN), - .reg_addr = reg_addr, - .buf = buf, - }; + u8 hdr_buf[SJA1105_SIZE_SPI_MSG_HEADER] = {0}; struct spi_device *spi = priv->spidev; - struct spi_transfer *xfers; + struct spi_transfer xfers[2] = {0}; + struct spi_transfer *chunk_xfer; + struct spi_transfer *hdr_xfer; + struct sja1105_chunk chunk; int num_chunks; int rc, i = 0; - u8 *hdr_bufs; - num_chunks = DIV_ROUND_UP(len, SJA1105_SIZE_SPI_MSG_MAXLEN); + num_chunks = DIV_ROUND_UP(len, priv->max_xfer_len); - /* One transfer for each message header, one for each message - * payload (chunk). - */ - xfers = kcalloc(2 * num_chunks, sizeof(struct spi_transfer), - GFP_KERNEL); - if (!xfers) - return -ENOMEM; + chunk.reg_addr = reg_addr; + chunk.buf = buf; + chunk.len = min_t(size_t, len, priv->max_xfer_len); - /* Packed buffers for the num_chunks SPI message headers, - * stored as a contiguous array - */ - hdr_bufs = kcalloc(num_chunks, SJA1105_SIZE_SPI_MSG_HEADER, - GFP_KERNEL); - if (!hdr_bufs) { - kfree(xfers); - return -ENOMEM; - } + hdr_xfer = &xfers[0]; + chunk_xfer = &xfers[1]; for (i = 0; i < num_chunks; i++) { - struct spi_transfer *chunk_xfer = sja1105_chunk_xfer(xfers, i); - struct spi_transfer *hdr_xfer = sja1105_hdr_xfer(xfers, i); - u8 *hdr_buf = sja1105_hdr_buf(hdr_bufs, i); struct spi_transfer *ptp_sts_xfer; struct sja1105_spi_message msg; @@ -127,21 +100,16 @@ static int sja1105_xfer(const struct sja1105_private *priv, chunk.buf += chunk.len; chunk.reg_addr += chunk.len / 4; chunk.len = min_t(size_t, (ptrdiff_t)(buf + len - chunk.buf), - SJA1105_SIZE_SPI_MSG_MAXLEN); + priv->max_xfer_len); - /* De-assert the chip select after each chunk. */ - if (chunk.len) - chunk_xfer->cs_change = 1; + rc = spi_sync_transfer(spi, xfers, 2); + if (rc < 0) { + dev_err(&spi->dev, "SPI transfer failed: %d\n", rc); + return rc; + } } - rc = spi_sync_transfer(spi, xfers, 2 * num_chunks); - if (rc < 0) - dev_err(&spi->dev, "SPI transfer failed: %d\n", rc); - - kfree(hdr_bufs); - kfree(xfers); - - return rc; + return 0; } int sja1105_xfer_buf(const struct sja1105_private *priv, @@ -209,28 +177,34 @@ static int sja1105et_reset_cmd(struct dsa_switch *ds) { struct sja1105_private *priv = ds->priv; const struct sja1105_regs *regs = priv->info->regs; - u8 packed_buf[SJA1105_SIZE_RESET_CMD] = {0}; - const int size = SJA1105_SIZE_RESET_CMD; - u64 cold_rst = 1; + u32 cold_reset = BIT(3); - sja1105_pack(packed_buf, &cold_rst, 3, 3, size); - - return sja1105_xfer_buf(priv, SPI_WRITE, regs->rgu, packed_buf, - SJA1105_SIZE_RESET_CMD); + /* Cold reset */ + return sja1105_xfer_u32(priv, SPI_WRITE, regs->rgu, &cold_reset, NULL); } static int sja1105pqrs_reset_cmd(struct dsa_switch *ds) { struct sja1105_private *priv = ds->priv; const struct sja1105_regs *regs = priv->info->regs; - u8 packed_buf[SJA1105_SIZE_RESET_CMD] = {0}; - const int size = SJA1105_SIZE_RESET_CMD; - u64 cold_rst = 1; + u32 cold_reset = BIT(2); - sja1105_pack(packed_buf, &cold_rst, 2, 2, size); + /* Cold reset */ + return sja1105_xfer_u32(priv, SPI_WRITE, regs->rgu, &cold_reset, NULL); +} - return sja1105_xfer_buf(priv, SPI_WRITE, regs->rgu, packed_buf, - SJA1105_SIZE_RESET_CMD); +static int sja1110_reset_cmd(struct dsa_switch *ds) +{ + struct sja1105_private *priv = ds->priv; + const struct sja1105_regs *regs = priv->info->regs; + u32 switch_reset = BIT(20); + + /* Only reset the switch core. + * A full cold reset would re-enable the BASE_MCSS_CLOCK PLL which + * would turn on the microcontroller, potentially letting it execute + * code which could interfere with our configuration. + */ + return sja1105_xfer_u32(priv, SPI_WRITE, regs->rgu, &switch_reset, NULL); } int sja1105_inhibit_tx(const struct sja1105_private *priv, @@ -311,7 +285,8 @@ int static_config_buf_prepare_for_upload(struct sja1105_private *priv, char *final_header_ptr; int crc_len; - valid = sja1105_static_config_check_valid(config); + valid = sja1105_static_config_check_valid(config, + priv->info->max_frame_mem); if (valid != SJA1105_CONFIG_OK) { dev_err(&priv->spidev->dev, sja1105_static_config_error_msg[valid]); @@ -339,10 +314,10 @@ int static_config_buf_prepare_for_upload(struct sja1105_private *priv, int sja1105_static_config_upload(struct sja1105_private *priv) { - unsigned long port_bitmap = GENMASK_ULL(SJA1105_NUM_PORTS - 1, 0); struct sja1105_static_config *config = &priv->static_config; const struct sja1105_regs *regs = priv->info->regs; struct device *dev = &priv->spidev->dev; + struct dsa_switch *ds = priv->ds; struct sja1105_status status; int rc, retries = RETRIES; u8 *config_buf; @@ -363,7 +338,7 @@ int sja1105_static_config_upload(struct sja1105_private *priv) * Tx on all ports and waiting for current packet to drain. * Otherwise, the PHY will see an unterminated Ethernet packet. */ - rc = sja1105_inhibit_tx(priv, port_bitmap, true); + rc = sja1105_inhibit_tx(priv, GENMASK_ULL(ds->num_ports - 1, 0), true); if (rc < 0) { dev_err(dev, "Failed to inhibit Tx on ports\n"); rc = -ENXIO; @@ -433,7 +408,7 @@ out: return rc; } -static struct sja1105_regs sja1105et_regs = { +static const struct sja1105_regs sja1105et_regs = { .device_id = 0x0, .prod_id = 0x100BC3, .status = 0x1, @@ -446,9 +421,9 @@ static struct sja1105_regs sja1105et_regs = { .pad_mii_rx = {0x100801, 0x100803, 0x100805, 0x100807, 0x100809}, .rmii_pll1 = 0x10000A, .cgu_idiv = {0x10000B, 0x10000C, 0x10000D, 0x10000E, 0x10000F}, - .mac = {0x200, 0x202, 0x204, 0x206, 0x208}, - .mac_hl1 = {0x400, 0x410, 0x420, 0x430, 0x440}, - .mac_hl2 = {0x600, 0x610, 0x620, 0x630, 0x640}, + .stats[MAC] = {0x200, 0x202, 0x204, 0x206, 0x208}, + .stats[HL1] = {0x400, 0x410, 0x420, 0x430, 0x440}, + .stats[HL2] = {0x600, 0x610, 0x620, 0x630, 0x640}, /* UM10944.pdf, Table 78, CGU Register overview */ .mii_tx_clk = {0x100013, 0x10001A, 0x100021, 0x100028, 0x10002F}, .mii_rx_clk = {0x100014, 0x10001B, 0x100022, 0x100029, 0x100030}, @@ -465,9 +440,11 @@ static struct sja1105_regs sja1105et_regs = { .ptpclkval = 0x18, /* Spans 0x18 to 0x19 */ .ptpclkrate = 0x1A, .ptpclkcorp = 0x1D, + .mdio_100base_tx = SJA1105_RSV_ADDR, + .mdio_100base_t1 = SJA1105_RSV_ADDR, }; -static struct sja1105_regs sja1105pqrs_regs = { +static const struct sja1105_regs sja1105pqrs_regs = { .device_id = 0x0, .prod_id = 0x100BC3, .status = 0x1, @@ -479,13 +456,12 @@ static struct sja1105_regs sja1105pqrs_regs = { .pad_mii_tx = {0x100800, 0x100802, 0x100804, 0x100806, 0x100808}, .pad_mii_rx = {0x100801, 0x100803, 0x100805, 0x100807, 0x100809}, .pad_mii_id = {0x100810, 0x100811, 0x100812, 0x100813, 0x100814}, - .sgmii = 0x1F0000, .rmii_pll1 = 0x10000A, .cgu_idiv = {0x10000B, 0x10000C, 0x10000D, 0x10000E, 0x10000F}, - .mac = {0x200, 0x202, 0x204, 0x206, 0x208}, - .mac_hl1 = {0x400, 0x410, 0x420, 0x430, 0x440}, - .mac_hl2 = {0x600, 0x610, 0x620, 0x630, 0x640}, - .ether_stats = {0x1400, 0x1418, 0x1430, 0x1448, 0x1460}, + .stats[MAC] = {0x200, 0x202, 0x204, 0x206, 0x208}, + .stats[HL1] = {0x400, 0x410, 0x420, 0x430, 0x440}, + .stats[HL2] = {0x600, 0x610, 0x620, 0x630, 0x640}, + .stats[ETHER] = {0x1400, 0x1418, 0x1430, 0x1448, 0x1460}, /* UM11040.pdf, Table 114 */ .mii_tx_clk = {0x100013, 0x100019, 0x10001F, 0x100025, 0x10002B}, .mii_rx_clk = {0x100014, 0x10001A, 0x100020, 0x100026, 0x10002C}, @@ -494,7 +470,6 @@ static struct sja1105_regs sja1105pqrs_regs = { .rgmii_tx_clk = {0x100016, 0x10001C, 0x100022, 0x100028, 0x10002E}, .rmii_ref_clk = {0x100015, 0x10001B, 0x100021, 0x100027, 0x10002D}, .rmii_ext_tx_clk = {0x100017, 0x10001D, 0x100023, 0x100029, 0x10002F}, - .qlevel = {0x604, 0x614, 0x624, 0x634, 0x644}, .ptpegr_ts = {0xC0, 0xC4, 0xC8, 0xCC, 0xD0}, .ptpschtm = 0x13, /* Spans 0x13 to 0x14 */ .ptppinst = 0x15, @@ -504,6 +479,95 @@ static struct sja1105_regs sja1105pqrs_regs = { .ptpclkrate = 0x1B, .ptpclkcorp = 0x1E, .ptpsyncts = 0x1F, + .mdio_100base_tx = SJA1105_RSV_ADDR, + .mdio_100base_t1 = SJA1105_RSV_ADDR, +}; + +static const struct sja1105_regs sja1110_regs = { + .device_id = SJA1110_SPI_ADDR(0x0), + .prod_id = SJA1110_ACU_ADDR(0xf00), + .status = SJA1110_SPI_ADDR(0x4), + .port_control = SJA1110_SPI_ADDR(0x50), /* actually INHIB_TX */ + .vl_status = 0x10000, + .config = 0x020000, + .rgu = SJA1110_RGU_ADDR(0x100), /* Reset Control Register 0 */ + /* Ports 2 and 3 are capable of xMII, but there isn't anything to + * configure in the CGU/ACU for them. + */ + .pad_mii_tx = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR}, + .pad_mii_rx = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR}, + .pad_mii_id = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1110_ACU_ADDR(0x18), SJA1110_ACU_ADDR(0x28), + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR}, + .rmii_pll1 = SJA1105_RSV_ADDR, + .cgu_idiv = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR}, + .stats[MAC] = {0x200, 0x202, 0x204, 0x206, 0x208, 0x20a, + 0x20c, 0x20e, 0x210, 0x212, 0x214}, + .stats[HL1] = {0x400, 0x410, 0x420, 0x430, 0x440, 0x450, + 0x460, 0x470, 0x480, 0x490, 0x4a0}, + .stats[HL2] = {0x600, 0x610, 0x620, 0x630, 0x640, 0x650, + 0x660, 0x670, 0x680, 0x690, 0x6a0}, + .stats[ETHER] = {0x1400, 0x1418, 0x1430, 0x1448, 0x1460, 0x1478, + 0x1490, 0x14a8, 0x14c0, 0x14d8, 0x14f0}, + .mii_tx_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR}, + .mii_rx_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR}, + .mii_ext_tx_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR}, + .mii_ext_rx_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR}, + .rgmii_tx_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR}, + .rmii_ref_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR}, + .rmii_ext_tx_clk = {SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR}, + .ptpschtm = SJA1110_SPI_ADDR(0x54), + .ptppinst = SJA1110_SPI_ADDR(0x5c), + .ptppindur = SJA1110_SPI_ADDR(0x64), + .ptp_control = SJA1110_SPI_ADDR(0x68), + .ptpclkval = SJA1110_SPI_ADDR(0x6c), + .ptpclkrate = SJA1110_SPI_ADDR(0x74), + .ptpclkcorp = SJA1110_SPI_ADDR(0x80), + .ptpsyncts = SJA1110_SPI_ADDR(0x84), + .mdio_100base_tx = 0x1c2400, + .mdio_100base_t1 = 0x1c1000, + .pcs_base = {SJA1105_RSV_ADDR, 0x1c1400, 0x1c1800, 0x1c1c00, 0x1c2000, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, + SJA1105_RSV_ADDR, SJA1105_RSV_ADDR, SJA1105_RSV_ADDR}, }; const struct sja1105_info sja1105e_info = { @@ -512,15 +576,30 @@ const struct sja1105_info sja1105e_info = { .static_ops = sja1105e_table_ops, .dyn_ops = sja1105et_dyn_ops, .qinq_tpid = ETH_P_8021Q, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = false, .ptp_ts_bits = 24, .ptpegr_ts_bytes = 4, + .max_frame_mem = SJA1105_MAX_FRAME_MEMORY, + .num_ports = SJA1105_NUM_PORTS, .num_cbs_shapers = SJA1105ET_MAX_CBS_COUNT, .reset_cmd = sja1105et_reset_cmd, .fdb_add_cmd = sja1105et_fdb_add, .fdb_del_cmd = sja1105et_fdb_del, .ptp_cmd_packing = sja1105et_ptp_cmd_packing, + .rxtstamp = sja1105_rxtstamp, + .clocking_setup = sja1105_clocking_setup, .regs = &sja1105et_regs, + .port_speed = { + [SJA1105_SPEED_AUTO] = 0, + [SJA1105_SPEED_10MBPS] = 3, + [SJA1105_SPEED_100MBPS] = 2, + [SJA1105_SPEED_1000MBPS] = 1, + [SJA1105_SPEED_2500MBPS] = 0, /* Not supported */ + }, + .supports_mii = {true, true, true, true, true}, + .supports_rmii = {true, true, true, true, true}, + .supports_rgmii = {true, true, true, true, true}, .name = "SJA1105E", }; @@ -530,15 +609,30 @@ const struct sja1105_info sja1105t_info = { .static_ops = sja1105t_table_ops, .dyn_ops = sja1105et_dyn_ops, .qinq_tpid = ETH_P_8021Q, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = false, .ptp_ts_bits = 24, .ptpegr_ts_bytes = 4, + .max_frame_mem = SJA1105_MAX_FRAME_MEMORY, + .num_ports = SJA1105_NUM_PORTS, .num_cbs_shapers = SJA1105ET_MAX_CBS_COUNT, .reset_cmd = sja1105et_reset_cmd, .fdb_add_cmd = sja1105et_fdb_add, .fdb_del_cmd = sja1105et_fdb_del, .ptp_cmd_packing = sja1105et_ptp_cmd_packing, + .rxtstamp = sja1105_rxtstamp, + .clocking_setup = sja1105_clocking_setup, .regs = &sja1105et_regs, + .port_speed = { + [SJA1105_SPEED_AUTO] = 0, + [SJA1105_SPEED_10MBPS] = 3, + [SJA1105_SPEED_100MBPS] = 2, + [SJA1105_SPEED_1000MBPS] = 1, + [SJA1105_SPEED_2500MBPS] = 0, /* Not supported */ + }, + .supports_mii = {true, true, true, true, true}, + .supports_rmii = {true, true, true, true, true}, + .supports_rgmii = {true, true, true, true, true}, .name = "SJA1105T", }; @@ -548,16 +642,31 @@ const struct sja1105_info sja1105p_info = { .static_ops = sja1105p_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, + .max_frame_mem = SJA1105_MAX_FRAME_MEMORY, + .num_ports = SJA1105_NUM_PORTS, .num_cbs_shapers = SJA1105PQRS_MAX_CBS_COUNT, .setup_rgmii_delay = sja1105pqrs_setup_rgmii_delay, .reset_cmd = sja1105pqrs_reset_cmd, .fdb_add_cmd = sja1105pqrs_fdb_add, .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1105_rxtstamp, + .clocking_setup = sja1105_clocking_setup, .regs = &sja1105pqrs_regs, + .port_speed = { + [SJA1105_SPEED_AUTO] = 0, + [SJA1105_SPEED_10MBPS] = 3, + [SJA1105_SPEED_100MBPS] = 2, + [SJA1105_SPEED_1000MBPS] = 1, + [SJA1105_SPEED_2500MBPS] = 0, /* Not supported */ + }, + .supports_mii = {true, true, true, true, true}, + .supports_rmii = {true, true, true, true, true}, + .supports_rgmii = {true, true, true, true, true}, .name = "SJA1105P", }; @@ -567,16 +676,31 @@ const struct sja1105_info sja1105q_info = { .static_ops = sja1105q_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, + .max_frame_mem = SJA1105_MAX_FRAME_MEMORY, + .num_ports = SJA1105_NUM_PORTS, .num_cbs_shapers = SJA1105PQRS_MAX_CBS_COUNT, .setup_rgmii_delay = sja1105pqrs_setup_rgmii_delay, .reset_cmd = sja1105pqrs_reset_cmd, .fdb_add_cmd = sja1105pqrs_fdb_add, .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1105_rxtstamp, + .clocking_setup = sja1105_clocking_setup, .regs = &sja1105pqrs_regs, + .port_speed = { + [SJA1105_SPEED_AUTO] = 0, + [SJA1105_SPEED_10MBPS] = 3, + [SJA1105_SPEED_100MBPS] = 2, + [SJA1105_SPEED_1000MBPS] = 1, + [SJA1105_SPEED_2500MBPS] = 0, /* Not supported */ + }, + .supports_mii = {true, true, true, true, true}, + .supports_rmii = {true, true, true, true, true}, + .supports_rgmii = {true, true, true, true, true}, .name = "SJA1105Q", }; @@ -586,16 +710,34 @@ const struct sja1105_info sja1105r_info = { .static_ops = sja1105r_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, + .max_frame_mem = SJA1105_MAX_FRAME_MEMORY, + .num_ports = SJA1105_NUM_PORTS, .num_cbs_shapers = SJA1105PQRS_MAX_CBS_COUNT, .setup_rgmii_delay = sja1105pqrs_setup_rgmii_delay, .reset_cmd = sja1105pqrs_reset_cmd, .fdb_add_cmd = sja1105pqrs_fdb_add, .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1105_rxtstamp, + .clocking_setup = sja1105_clocking_setup, + .pcs_mdio_read = sja1105_pcs_mdio_read, + .pcs_mdio_write = sja1105_pcs_mdio_write, .regs = &sja1105pqrs_regs, + .port_speed = { + [SJA1105_SPEED_AUTO] = 0, + [SJA1105_SPEED_10MBPS] = 3, + [SJA1105_SPEED_100MBPS] = 2, + [SJA1105_SPEED_1000MBPS] = 1, + [SJA1105_SPEED_2500MBPS] = 0, /* Not supported */ + }, + .supports_mii = {true, true, true, true, true}, + .supports_rmii = {true, true, true, true, true}, + .supports_rgmii = {true, true, true, true, true}, + .supports_sgmii = {false, false, false, false, true}, .name = "SJA1105R", }; @@ -606,14 +748,236 @@ const struct sja1105_info sja1105s_info = { .dyn_ops = sja1105pqrs_dyn_ops, .regs = &sja1105pqrs_regs, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, + .max_frame_mem = SJA1105_MAX_FRAME_MEMORY, + .num_ports = SJA1105_NUM_PORTS, .num_cbs_shapers = SJA1105PQRS_MAX_CBS_COUNT, .setup_rgmii_delay = sja1105pqrs_setup_rgmii_delay, .reset_cmd = sja1105pqrs_reset_cmd, .fdb_add_cmd = sja1105pqrs_fdb_add, .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1105_rxtstamp, + .clocking_setup = sja1105_clocking_setup, + .pcs_mdio_read = sja1105_pcs_mdio_read, + .pcs_mdio_write = sja1105_pcs_mdio_write, + .port_speed = { + [SJA1105_SPEED_AUTO] = 0, + [SJA1105_SPEED_10MBPS] = 3, + [SJA1105_SPEED_100MBPS] = 2, + [SJA1105_SPEED_1000MBPS] = 1, + [SJA1105_SPEED_2500MBPS] = 0, /* Not supported */ + }, + .supports_mii = {true, true, true, true, true}, + .supports_rmii = {true, true, true, true, true}, + .supports_rgmii = {true, true, true, true, true}, + .supports_sgmii = {false, false, false, false, true}, .name = "SJA1105S", }; + +const struct sja1105_info sja1110a_info = { + .device_id = SJA1110_DEVICE_ID, + .part_no = SJA1110A_PART_NO, + .static_ops = sja1110_table_ops, + .dyn_ops = sja1110_dyn_ops, + .regs = &sja1110_regs, + .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1110, + .can_limit_mcast_flood = true, + .multiple_cascade_ports = true, + .ptp_ts_bits = 32, + .ptpegr_ts_bytes = 8, + .max_frame_mem = SJA1110_MAX_FRAME_MEMORY, + .num_ports = SJA1110_NUM_PORTS, + .num_cbs_shapers = SJA1110_MAX_CBS_COUNT, + .setup_rgmii_delay = sja1110_setup_rgmii_delay, + .reset_cmd = sja1110_reset_cmd, + .fdb_add_cmd = sja1105pqrs_fdb_add, + .fdb_del_cmd = sja1105pqrs_fdb_del, + .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1110_rxtstamp, + .txtstamp = sja1110_txtstamp, + .disable_microcontroller = sja1110_disable_microcontroller, + .pcs_mdio_read = sja1110_pcs_mdio_read, + .pcs_mdio_write = sja1110_pcs_mdio_write, + .port_speed = { + [SJA1105_SPEED_AUTO] = 0, + [SJA1105_SPEED_10MBPS] = 4, + [SJA1105_SPEED_100MBPS] = 3, + [SJA1105_SPEED_1000MBPS] = 2, + [SJA1105_SPEED_2500MBPS] = 1, + }, + .supports_mii = {true, true, true, true, false, + true, true, true, true, true, true}, + .supports_rmii = {false, false, true, true, false, + false, false, false, false, false, false}, + .supports_rgmii = {false, false, true, true, false, + false, false, false, false, false, false}, + .supports_sgmii = {false, true, true, true, true, + false, false, false, false, false, false}, + .supports_2500basex = {false, false, false, true, true, + false, false, false, false, false, false}, + .internal_phy = {SJA1105_NO_PHY, SJA1105_PHY_BASE_TX, + SJA1105_NO_PHY, SJA1105_NO_PHY, + SJA1105_NO_PHY, SJA1105_PHY_BASE_T1, + SJA1105_PHY_BASE_T1, SJA1105_PHY_BASE_T1, + SJA1105_PHY_BASE_T1, SJA1105_PHY_BASE_T1, + SJA1105_PHY_BASE_T1}, + .name = "SJA1110A", +}; + +const struct sja1105_info sja1110b_info = { + .device_id = SJA1110_DEVICE_ID, + .part_no = SJA1110B_PART_NO, + .static_ops = sja1110_table_ops, + .dyn_ops = sja1110_dyn_ops, + .regs = &sja1110_regs, + .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1110, + .can_limit_mcast_flood = true, + .multiple_cascade_ports = true, + .ptp_ts_bits = 32, + .ptpegr_ts_bytes = 8, + .max_frame_mem = SJA1110_MAX_FRAME_MEMORY, + .num_ports = SJA1110_NUM_PORTS, + .num_cbs_shapers = SJA1110_MAX_CBS_COUNT, + .setup_rgmii_delay = sja1110_setup_rgmii_delay, + .reset_cmd = sja1110_reset_cmd, + .fdb_add_cmd = sja1105pqrs_fdb_add, + .fdb_del_cmd = sja1105pqrs_fdb_del, + .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1110_rxtstamp, + .txtstamp = sja1110_txtstamp, + .disable_microcontroller = sja1110_disable_microcontroller, + .pcs_mdio_read = sja1110_pcs_mdio_read, + .pcs_mdio_write = sja1110_pcs_mdio_write, + .port_speed = { + [SJA1105_SPEED_AUTO] = 0, + [SJA1105_SPEED_10MBPS] = 4, + [SJA1105_SPEED_100MBPS] = 3, + [SJA1105_SPEED_1000MBPS] = 2, + [SJA1105_SPEED_2500MBPS] = 1, + }, + .supports_mii = {true, true, true, true, false, + true, true, true, true, true, false}, + .supports_rmii = {false, false, true, true, false, + false, false, false, false, false, false}, + .supports_rgmii = {false, false, true, true, false, + false, false, false, false, false, false}, + .supports_sgmii = {false, false, false, true, true, + false, false, false, false, false, false}, + .supports_2500basex = {false, false, false, true, true, + false, false, false, false, false, false}, + .internal_phy = {SJA1105_NO_PHY, SJA1105_PHY_BASE_TX, + SJA1105_NO_PHY, SJA1105_NO_PHY, + SJA1105_NO_PHY, SJA1105_PHY_BASE_T1, + SJA1105_PHY_BASE_T1, SJA1105_PHY_BASE_T1, + SJA1105_PHY_BASE_T1, SJA1105_PHY_BASE_T1, + SJA1105_NO_PHY}, + .name = "SJA1110B", +}; + +const struct sja1105_info sja1110c_info = { + .device_id = SJA1110_DEVICE_ID, + .part_no = SJA1110C_PART_NO, + .static_ops = sja1110_table_ops, + .dyn_ops = sja1110_dyn_ops, + .regs = &sja1110_regs, + .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1110, + .can_limit_mcast_flood = true, + .multiple_cascade_ports = true, + .ptp_ts_bits = 32, + .ptpegr_ts_bytes = 8, + .max_frame_mem = SJA1110_MAX_FRAME_MEMORY, + .num_ports = SJA1110_NUM_PORTS, + .num_cbs_shapers = SJA1110_MAX_CBS_COUNT, + .setup_rgmii_delay = sja1110_setup_rgmii_delay, + .reset_cmd = sja1110_reset_cmd, + .fdb_add_cmd = sja1105pqrs_fdb_add, + .fdb_del_cmd = sja1105pqrs_fdb_del, + .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1110_rxtstamp, + .txtstamp = sja1110_txtstamp, + .disable_microcontroller = sja1110_disable_microcontroller, + .pcs_mdio_read = sja1110_pcs_mdio_read, + .pcs_mdio_write = sja1110_pcs_mdio_write, + .port_speed = { + [SJA1105_SPEED_AUTO] = 0, + [SJA1105_SPEED_10MBPS] = 4, + [SJA1105_SPEED_100MBPS] = 3, + [SJA1105_SPEED_1000MBPS] = 2, + [SJA1105_SPEED_2500MBPS] = 1, + }, + .supports_mii = {true, true, true, true, false, + true, true, true, false, false, false}, + .supports_rmii = {false, false, true, true, false, + false, false, false, false, false, false}, + .supports_rgmii = {false, false, true, true, false, + false, false, false, false, false, false}, + .supports_sgmii = {false, false, false, false, true, + false, false, false, false, false, false}, + .supports_2500basex = {false, false, false, false, true, + false, false, false, false, false, false}, + .internal_phy = {SJA1105_NO_PHY, SJA1105_PHY_BASE_TX, + SJA1105_NO_PHY, SJA1105_NO_PHY, + SJA1105_NO_PHY, SJA1105_PHY_BASE_T1, + SJA1105_PHY_BASE_T1, SJA1105_PHY_BASE_T1, + SJA1105_NO_PHY, SJA1105_NO_PHY, + SJA1105_NO_PHY}, + .name = "SJA1110C", +}; + +const struct sja1105_info sja1110d_info = { + .device_id = SJA1110_DEVICE_ID, + .part_no = SJA1110D_PART_NO, + .static_ops = sja1110_table_ops, + .dyn_ops = sja1110_dyn_ops, + .regs = &sja1110_regs, + .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1110, + .can_limit_mcast_flood = true, + .multiple_cascade_ports = true, + .ptp_ts_bits = 32, + .ptpegr_ts_bytes = 8, + .max_frame_mem = SJA1110_MAX_FRAME_MEMORY, + .num_ports = SJA1110_NUM_PORTS, + .num_cbs_shapers = SJA1110_MAX_CBS_COUNT, + .setup_rgmii_delay = sja1110_setup_rgmii_delay, + .reset_cmd = sja1110_reset_cmd, + .fdb_add_cmd = sja1105pqrs_fdb_add, + .fdb_del_cmd = sja1105pqrs_fdb_del, + .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1110_rxtstamp, + .txtstamp = sja1110_txtstamp, + .disable_microcontroller = sja1110_disable_microcontroller, + .pcs_mdio_read = sja1110_pcs_mdio_read, + .pcs_mdio_write = sja1110_pcs_mdio_write, + .port_speed = { + [SJA1105_SPEED_AUTO] = 0, + [SJA1105_SPEED_10MBPS] = 4, + [SJA1105_SPEED_100MBPS] = 3, + [SJA1105_SPEED_1000MBPS] = 2, + [SJA1105_SPEED_2500MBPS] = 1, + }, + .supports_mii = {true, false, true, false, false, + true, true, true, false, false, false}, + .supports_rmii = {false, false, true, false, false, + false, false, false, false, false, false}, + .supports_rgmii = {false, false, true, false, false, + false, false, false, false, false, false}, + .supports_sgmii = {false, true, true, true, true, + false, false, false, false, false, false}, + .supports_2500basex = {false, false, false, true, true, + false, false, false, false, false, false}, + .internal_phy = {SJA1105_NO_PHY, SJA1105_NO_PHY, + SJA1105_NO_PHY, SJA1105_NO_PHY, + SJA1105_NO_PHY, SJA1105_PHY_BASE_T1, + SJA1105_PHY_BASE_T1, SJA1105_PHY_BASE_T1, + SJA1105_NO_PHY, SJA1105_NO_PHY, + SJA1105_NO_PHY}, + .name = "SJA1110D", +}; diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c index a8efb7fac395..7a422ef4deb6 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.c +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -180,6 +180,43 @@ size_t sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr, return size; } +size_t sja1110_general_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_general_params_entry *entry = entry_ptr; + const size_t size = SJA1110_SIZE_GENERAL_PARAMS_ENTRY; + + sja1105_packing(buf, &entry->vllupformat, 447, 447, size, op); + sja1105_packing(buf, &entry->mirr_ptacu, 446, 446, size, op); + sja1105_packing(buf, &entry->switchid, 445, 442, size, op); + sja1105_packing(buf, &entry->hostprio, 441, 439, size, op); + sja1105_packing(buf, &entry->mac_fltres1, 438, 391, size, op); + sja1105_packing(buf, &entry->mac_fltres0, 390, 343, size, op); + sja1105_packing(buf, &entry->mac_flt1, 342, 295, size, op); + sja1105_packing(buf, &entry->mac_flt0, 294, 247, size, op); + sja1105_packing(buf, &entry->incl_srcpt1, 246, 246, size, op); + sja1105_packing(buf, &entry->incl_srcpt0, 245, 245, size, op); + sja1105_packing(buf, &entry->send_meta1, 244, 244, size, op); + sja1105_packing(buf, &entry->send_meta0, 243, 243, size, op); + sja1105_packing(buf, &entry->casc_port, 242, 232, size, op); + sja1105_packing(buf, &entry->host_port, 231, 228, size, op); + sja1105_packing(buf, &entry->mirr_port, 227, 224, size, op); + sja1105_packing(buf, &entry->vlmarker, 223, 192, size, op); + sja1105_packing(buf, &entry->vlmask, 191, 160, size, op); + sja1105_packing(buf, &entry->tpid2, 159, 144, size, op); + sja1105_packing(buf, &entry->ignore2stf, 143, 143, size, op); + sja1105_packing(buf, &entry->tpid, 142, 127, size, op); + sja1105_packing(buf, &entry->queue_ts, 126, 126, size, op); + sja1105_packing(buf, &entry->egrmirrvid, 125, 114, size, op); + sja1105_packing(buf, &entry->egrmirrpcp, 113, 111, size, op); + sja1105_packing(buf, &entry->egrmirrdei, 110, 110, size, op); + sja1105_packing(buf, &entry->replay_port, 109, 106, size, op); + sja1105_packing(buf, &entry->tdmaconfigidx, 70, 67, size, op); + sja1105_packing(buf, &entry->header_type, 64, 49, size, op); + sja1105_packing(buf, &entry->tte_en, 16, 16, size, op); + return size; +} + static size_t sja1105_l2_forwarding_params_entry_packing(void *buf, void *entry_ptr, enum packing_op op) @@ -195,6 +232,20 @@ sja1105_l2_forwarding_params_entry_packing(void *buf, void *entry_ptr, return size; } +size_t sja1110_l2_forwarding_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_l2_forwarding_params_entry *entry = entry_ptr; + const size_t size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY; + int offset, i; + + sja1105_packing(buf, &entry->max_dynp, 95, 93, size, op); + for (i = 0, offset = 5; i < 8; i++, offset += 11) + sja1105_packing(buf, &entry->part_spc[i], + offset + 10, offset + 0, size, op); + return size; +} + size_t sja1105_l2_forwarding_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -211,6 +262,27 @@ size_t sja1105_l2_forwarding_entry_packing(void *buf, void *entry_ptr, return size; } +size_t sja1110_l2_forwarding_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_l2_forwarding_entry *entry = entry_ptr; + const size_t size = SJA1105_SIZE_L2_FORWARDING_ENTRY; + int offset, i; + + if (entry->type_egrpcp2outputq) { + for (i = 0, offset = 31; i < SJA1110_NUM_PORTS; + i++, offset += 3) { + sja1105_packing(buf, &entry->vlan_pmap[i], + offset + 2, offset + 0, size, op); + } + } else { + sja1105_packing(buf, &entry->bc_domain, 63, 53, size, op); + sja1105_packing(buf, &entry->reach_port, 52, 42, size, op); + sja1105_packing(buf, &entry->fl_domain, 41, 31, size, op); + } + return size; +} + static size_t sja1105et_l2_lookup_params_entry_packing(void *buf, void *entry_ptr, enum packing_op op) @@ -249,6 +321,28 @@ size_t sja1105pqrs_l2_lookup_params_entry_packing(void *buf, void *entry_ptr, return size; } +size_t sja1110_l2_lookup_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_l2_lookup_params_entry *entry = entry_ptr; + const size_t size = SJA1110_SIZE_L2_LOOKUP_PARAMS_ENTRY; + int offset, i; + + for (i = 0, offset = 70; i < SJA1110_NUM_PORTS; i++, offset += 11) + sja1105_packing(buf, &entry->maxaddrp[i], + offset + 10, offset + 0, size, op); + sja1105_packing(buf, &entry->maxage, 69, 55, size, op); + sja1105_packing(buf, &entry->start_dynspc, 54, 45, size, op); + sja1105_packing(buf, &entry->drpnolearn, 44, 34, size, op); + sja1105_packing(buf, &entry->shared_learn, 33, 33, size, op); + sja1105_packing(buf, &entry->no_enf_hostprt, 32, 32, size, op); + sja1105_packing(buf, &entry->no_mgmt_learn, 31, 31, size, op); + sja1105_packing(buf, &entry->use_static, 30, 30, size, op); + sja1105_packing(buf, &entry->owr_dyn, 29, 29, size, op); + sja1105_packing(buf, &entry->learn_once, 28, 28, size, op); + return size; +} + size_t sja1105et_l2_lookup_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -291,6 +385,36 @@ size_t sja1105pqrs_l2_lookup_entry_packing(void *buf, void *entry_ptr, return size; } +size_t sja1110_l2_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1110_SIZE_L2_LOOKUP_ENTRY; + struct sja1105_l2_lookup_entry *entry = entry_ptr; + + if (entry->lockeds) { + sja1105_packing(buf, &entry->trap, 168, 168, size, op); + sja1105_packing(buf, &entry->mirrvlan, 167, 156, size, op); + sja1105_packing(buf, &entry->takets, 155, 155, size, op); + sja1105_packing(buf, &entry->mirr, 154, 154, size, op); + sja1105_packing(buf, &entry->retag, 153, 153, size, op); + } else { + sja1105_packing(buf, &entry->touched, 168, 168, size, op); + sja1105_packing(buf, &entry->age, 167, 153, size, op); + } + sja1105_packing(buf, &entry->mask_iotag, 152, 152, size, op); + sja1105_packing(buf, &entry->mask_vlanid, 151, 140, size, op); + sja1105_packing(buf, &entry->mask_macaddr, 139, 92, size, op); + sja1105_packing(buf, &entry->mask_srcport, 91, 88, size, op); + sja1105_packing(buf, &entry->iotag, 87, 87, size, op); + sja1105_packing(buf, &entry->vlanid, 86, 75, size, op); + sja1105_packing(buf, &entry->macaddr, 74, 27, size, op); + sja1105_packing(buf, &entry->srcport, 26, 23, size, op); + sja1105_packing(buf, &entry->destports, 22, 12, size, op); + sja1105_packing(buf, &entry->enfport, 11, 11, size, op); + sja1105_packing(buf, &entry->index, 10, 1, size, op); + return size; +} + static size_t sja1105_l2_policing_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -305,6 +429,20 @@ static size_t sja1105_l2_policing_entry_packing(void *buf, void *entry_ptr, return size; } +size_t sja1110_l2_policing_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_l2_policing_entry *entry = entry_ptr; + const size_t size = SJA1105_SIZE_L2_POLICING_ENTRY; + + sja1105_packing(buf, &entry->sharindx, 63, 57, size, op); + sja1105_packing(buf, &entry->smax, 56, 39, size, op); + sja1105_packing(buf, &entry->rate, 38, 21, size, op); + sja1105_packing(buf, &entry->maxlen, 20, 10, size, op); + sja1105_packing(buf, &entry->partition, 9, 7, size, op); + return size; +} + static size_t sja1105et_mac_config_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -373,6 +511,40 @@ size_t sja1105pqrs_mac_config_entry_packing(void *buf, void *entry_ptr, return size; } +size_t sja1110_mac_config_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY; + struct sja1105_mac_config_entry *entry = entry_ptr; + int offset, i; + + for (i = 0, offset = 104; i < 8; i++, offset += 19) { + sja1105_packing(buf, &entry->enabled[i], + offset + 0, offset + 0, size, op); + sja1105_packing(buf, &entry->base[i], + offset + 9, offset + 1, size, op); + sja1105_packing(buf, &entry->top[i], + offset + 18, offset + 10, size, op); + } + sja1105_packing(buf, &entry->speed, 98, 96, size, op); + sja1105_packing(buf, &entry->tp_delin, 95, 80, size, op); + sja1105_packing(buf, &entry->tp_delout, 79, 64, size, op); + sja1105_packing(buf, &entry->maxage, 63, 56, size, op); + sja1105_packing(buf, &entry->vlanprio, 55, 53, size, op); + sja1105_packing(buf, &entry->vlanid, 52, 41, size, op); + sja1105_packing(buf, &entry->ing_mirr, 40, 40, size, op); + sja1105_packing(buf, &entry->egr_mirr, 39, 39, size, op); + sja1105_packing(buf, &entry->drpnona664, 38, 38, size, op); + sja1105_packing(buf, &entry->drpdtag, 37, 37, size, op); + sja1105_packing(buf, &entry->drpuntag, 34, 34, size, op); + sja1105_packing(buf, &entry->retag, 33, 33, size, op); + sja1105_packing(buf, &entry->dyn_learn, 32, 32, size, op); + sja1105_packing(buf, &entry->egress, 31, 31, size, op); + sja1105_packing(buf, &entry->ingress, 30, 30, size, op); + sja1105_packing(buf, &entry->ifg, 10, 5, size, op); + return size; +} + static size_t sja1105_schedule_entry_points_params_entry_packing(void *buf, void *entry_ptr, enum packing_op op) @@ -398,6 +570,19 @@ sja1105_schedule_entry_points_entry_packing(void *buf, void *entry_ptr, return size; } +static size_t +sja1110_schedule_entry_points_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_schedule_entry_points_entry *entry = entry_ptr; + const size_t size = SJA1110_SIZE_SCHEDULE_ENTRY_POINTS_ENTRY; + + sja1105_packing(buf, &entry->subschindx, 63, 61, size, op); + sja1105_packing(buf, &entry->delta, 60, 43, size, op); + sja1105_packing(buf, &entry->address, 42, 31, size, op); + return size; +} + static size_t sja1105_schedule_params_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -411,6 +596,19 @@ static size_t sja1105_schedule_params_entry_packing(void *buf, void *entry_ptr, return size; } +static size_t sja1110_schedule_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_schedule_params_entry *entry = entry_ptr; + const size_t size = SJA1105_SIZE_SCHEDULE_PARAMS_ENTRY; + int offset, i; + + for (i = 0, offset = 0; i < 8; i++, offset += 12) + sja1105_packing(buf, &entry->subscheind[i], + offset + 11, offset + 0, size, op); + return size; +} + static size_t sja1105_schedule_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -430,6 +628,25 @@ static size_t sja1105_schedule_entry_packing(void *buf, void *entry_ptr, return size; } +static size_t sja1110_schedule_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1110_SIZE_SCHEDULE_ENTRY; + struct sja1105_schedule_entry *entry = entry_ptr; + + sja1105_packing(buf, &entry->winstindex, 95, 84, size, op); + sja1105_packing(buf, &entry->winend, 83, 83, size, op); + sja1105_packing(buf, &entry->winst, 82, 82, size, op); + sja1105_packing(buf, &entry->destports, 81, 71, size, op); + sja1105_packing(buf, &entry->setvalid, 70, 70, size, op); + sja1105_packing(buf, &entry->txen, 69, 69, size, op); + sja1105_packing(buf, &entry->resmedia_en, 68, 68, size, op); + sja1105_packing(buf, &entry->resmedia, 67, 60, size, op); + sja1105_packing(buf, &entry->vlindex, 59, 48, size, op); + sja1105_packing(buf, &entry->delta, 47, 30, size, op); + return size; +} + static size_t sja1105_vl_forwarding_params_entry_packing(void *buf, void *entry_ptr, enum packing_op op) @@ -445,6 +662,21 @@ sja1105_vl_forwarding_params_entry_packing(void *buf, void *entry_ptr, return size; } +static size_t +sja1110_vl_forwarding_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_vl_forwarding_params_entry *entry = entry_ptr; + const size_t size = SJA1105_SIZE_VL_FORWARDING_PARAMS_ENTRY; + int offset, i; + + for (i = 0, offset = 8; i < 8; i++, offset += 11) + sja1105_packing(buf, &entry->partspc[i], + offset + 10, offset + 0, size, op); + sja1105_packing(buf, &entry->debugen, 7, 7, size, op); + return size; +} + static size_t sja1105_vl_forwarding_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -458,6 +690,19 @@ static size_t sja1105_vl_forwarding_entry_packing(void *buf, void *entry_ptr, return size; } +static size_t sja1110_vl_forwarding_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_vl_forwarding_entry *entry = entry_ptr; + const size_t size = SJA1105_SIZE_VL_FORWARDING_ENTRY; + + sja1105_packing(buf, &entry->type, 31, 31, size, op); + sja1105_packing(buf, &entry->priority, 30, 28, size, op); + sja1105_packing(buf, &entry->partition, 27, 25, size, op); + sja1105_packing(buf, &entry->destports, 24, 14, size, op); + return size; +} + size_t sja1105_vl_lookup_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -492,6 +737,40 @@ size_t sja1105_vl_lookup_entry_packing(void *buf, void *entry_ptr, return size; } +size_t sja1110_vl_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_vl_lookup_entry *entry = entry_ptr; + const size_t size = SJA1105_SIZE_VL_LOOKUP_ENTRY; + + if (entry->format == SJA1105_VL_FORMAT_PSFP) { + /* Interpreting vllupformat as 0 */ + sja1105_packing(buf, &entry->destports, + 94, 84, size, op); + sja1105_packing(buf, &entry->iscritical, + 83, 83, size, op); + sja1105_packing(buf, &entry->macaddr, + 82, 35, size, op); + sja1105_packing(buf, &entry->vlanid, + 34, 23, size, op); + sja1105_packing(buf, &entry->port, + 22, 19, size, op); + sja1105_packing(buf, &entry->vlanprior, + 18, 16, size, op); + } else { + /* Interpreting vllupformat as 1 */ + sja1105_packing(buf, &entry->egrmirr, + 94, 84, size, op); + sja1105_packing(buf, &entry->ingrmirr, + 83, 83, size, op); + sja1105_packing(buf, &entry->vlid, + 50, 35, size, op); + sja1105_packing(buf, &entry->port, + 22, 19, size, op); + } + return size; +} + static size_t sja1105_vl_policing_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -508,6 +787,22 @@ static size_t sja1105_vl_policing_entry_packing(void *buf, void *entry_ptr, return size; } +size_t sja1110_vl_policing_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_vl_policing_entry *entry = entry_ptr; + const size_t size = SJA1105_SIZE_VL_POLICING_ENTRY; + + sja1105_packing(buf, &entry->type, 63, 63, size, op); + sja1105_packing(buf, &entry->maxlen, 62, 52, size, op); + sja1105_packing(buf, &entry->sharindx, 51, 40, size, op); + if (entry->type == 0) { + sja1105_packing(buf, &entry->bag, 41, 28, size, op); + sja1105_packing(buf, &entry->jitter, 27, 18, size, op); + } + return size; +} + size_t sja1105_vlan_lookup_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -523,6 +818,22 @@ size_t sja1105_vlan_lookup_entry_packing(void *buf, void *entry_ptr, return size; } +size_t sja1110_vlan_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_vlan_lookup_entry *entry = entry_ptr; + const size_t size = SJA1110_SIZE_VLAN_LOOKUP_ENTRY; + + sja1105_packing(buf, &entry->ving_mirr, 95, 85, size, op); + sja1105_packing(buf, &entry->vegr_mirr, 84, 74, size, op); + sja1105_packing(buf, &entry->vmemb_port, 73, 63, size, op); + sja1105_packing(buf, &entry->vlan_bc, 62, 52, size, op); + sja1105_packing(buf, &entry->tag_port, 51, 41, size, op); + sja1105_packing(buf, &entry->type_entry, 40, 39, size, op); + sja1105_packing(buf, &entry->vlanid, 38, 27, size, op); + return size; +} + static size_t sja1105_xmii_params_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -539,6 +850,24 @@ static size_t sja1105_xmii_params_entry_packing(void *buf, void *entry_ptr, return size; } +size_t sja1110_xmii_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + const size_t size = SJA1110_SIZE_XMII_PARAMS_ENTRY; + struct sja1105_xmii_params_entry *entry = entry_ptr; + int offset, i; + + for (i = 0, offset = 20; i < SJA1110_NUM_PORTS; i++, offset += 4) { + sja1105_packing(buf, &entry->xmii_mode[i], + offset + 1, offset + 0, size, op); + sja1105_packing(buf, &entry->phy_mac[i], + offset + 2, offset + 2, size, op); + sja1105_packing(buf, &entry->special[i], + offset + 3, offset + 3, size, op); + } + return size; +} + size_t sja1105_retagging_entry_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -555,6 +884,36 @@ size_t sja1105_retagging_entry_packing(void *buf, void *entry_ptr, return size; } +size_t sja1110_retagging_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1105_retagging_entry *entry = entry_ptr; + const size_t size = SJA1105_SIZE_RETAGGING_ENTRY; + + sja1105_packing(buf, &entry->egr_port, 63, 53, size, op); + sja1105_packing(buf, &entry->ing_port, 52, 42, size, op); + sja1105_packing(buf, &entry->vlan_ing, 41, 30, size, op); + sja1105_packing(buf, &entry->vlan_egr, 29, 18, size, op); + sja1105_packing(buf, &entry->do_not_learn, 17, 17, size, op); + sja1105_packing(buf, &entry->use_dest_ports, 16, 16, size, op); + sja1105_packing(buf, &entry->destports, 15, 5, size, op); + return size; +} + +static size_t sja1110_pcp_remapping_entry_packing(void *buf, void *entry_ptr, + enum packing_op op) +{ + struct sja1110_pcp_remapping_entry *entry = entry_ptr; + const size_t size = SJA1110_SIZE_PCP_REMAPPING_ENTRY; + int offset, i; + + for (i = 0, offset = 8; i < SJA1105_NUM_TC; i++, offset += 3) + sja1105_packing(buf, &entry->egrpcp[i], + offset + 2, offset + 0, size, op); + + return size; +} + size_t sja1105_table_header_packing(void *buf, void *entry_ptr, enum packing_op op) { @@ -619,6 +978,7 @@ static u64 blk_id_map[BLK_IDX_MAX] = { [BLK_IDX_GENERAL_PARAMS] = BLKID_GENERAL_PARAMS, [BLK_IDX_RETAGGING] = BLKID_RETAGGING, [BLK_IDX_XMII_PARAMS] = BLKID_XMII_PARAMS, + [BLK_IDX_PCP_REMAPPING] = BLKID_PCP_REMAPPING, }; const char *sja1105_static_config_error_msg[] = { @@ -657,11 +1017,11 @@ const char *sja1105_static_config_error_msg[] = { }; static sja1105_config_valid_t -static_config_check_memory_size(const struct sja1105_table *tables) +static_config_check_memory_size(const struct sja1105_table *tables, int max_mem) { const struct sja1105_l2_forwarding_params_entry *l2_fwd_params; const struct sja1105_vl_forwarding_params_entry *vl_fwd_params; - int i, max_mem, mem = 0; + int i, mem = 0; l2_fwd_params = tables[BLK_IDX_L2_FORWARDING_PARAMS].entries; @@ -675,9 +1035,7 @@ static_config_check_memory_size(const struct sja1105_table *tables) } if (tables[BLK_IDX_RETAGGING].entry_count) - max_mem = SJA1105_MAX_FRAME_MEMORY_RETAGGING; - else - max_mem = SJA1105_MAX_FRAME_MEMORY; + max_mem -= SJA1105_FRAME_MEMORY_RETAGGING_OVERHEAD; if (mem > max_mem) return SJA1105_OVERCOMMITTED_FRAME_MEMORY; @@ -686,15 +1044,15 @@ static_config_check_memory_size(const struct sja1105_table *tables) } sja1105_config_valid_t -sja1105_static_config_check_valid(const struct sja1105_static_config *config) +sja1105_static_config_check_valid(const struct sja1105_static_config *config, + int max_mem) { const struct sja1105_table *tables = config->tables; #define IS_FULL(blk_idx) \ (tables[blk_idx].entry_count == tables[blk_idx].ops->max_entry_count) if (tables[BLK_IDX_SCHEDULE].entry_count) { - if (config->device_id != SJA1105T_DEVICE_ID && - config->device_id != SJA1105QS_DEVICE_ID) + if (!tables[BLK_IDX_SCHEDULE].ops->max_entry_count) return SJA1105_TTETHERNET_NOT_SUPPORTED; if (tables[BLK_IDX_SCHEDULE_ENTRY_POINTS].entry_count == 0) @@ -754,7 +1112,7 @@ sja1105_static_config_check_valid(const struct sja1105_static_config *config) if (!IS_FULL(BLK_IDX_XMII_PARAMS)) return SJA1105_MISSING_XMII_TABLE; - return static_config_check_memory_size(tables); + return static_config_check_memory_size(tables, max_mem); #undef IS_FULL } @@ -1401,6 +1759,130 @@ const struct sja1105_table_ops sja1105s_table_ops[BLK_IDX_MAX] = { }, }; +/* SJA1110A: Third generation */ +const struct sja1105_table_ops sja1110_table_ops[BLK_IDX_MAX] = { + [BLK_IDX_SCHEDULE] = { + .packing = sja1110_schedule_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_schedule_entry), + .packed_entry_size = SJA1110_SIZE_SCHEDULE_ENTRY, + .max_entry_count = SJA1110_MAX_SCHEDULE_COUNT, + }, + [BLK_IDX_SCHEDULE_ENTRY_POINTS] = { + .packing = sja1110_schedule_entry_points_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_schedule_entry_points_entry), + .packed_entry_size = SJA1110_SIZE_SCHEDULE_ENTRY_POINTS_ENTRY, + .max_entry_count = SJA1105_MAX_SCHEDULE_ENTRY_POINTS_COUNT, + }, + [BLK_IDX_VL_LOOKUP] = { + .packing = sja1110_vl_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_vl_lookup_entry), + .packed_entry_size = SJA1105_SIZE_VL_LOOKUP_ENTRY, + .max_entry_count = SJA1110_MAX_VL_LOOKUP_COUNT, + }, + [BLK_IDX_VL_POLICING] = { + .packing = sja1110_vl_policing_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_vl_policing_entry), + .packed_entry_size = SJA1105_SIZE_VL_POLICING_ENTRY, + .max_entry_count = SJA1110_MAX_VL_POLICING_COUNT, + }, + [BLK_IDX_VL_FORWARDING] = { + .packing = sja1110_vl_forwarding_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_vl_forwarding_entry), + .packed_entry_size = SJA1105_SIZE_VL_FORWARDING_ENTRY, + .max_entry_count = SJA1110_MAX_VL_FORWARDING_COUNT, + }, + [BLK_IDX_L2_LOOKUP] = { + .packing = sja1110_l2_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_entry), + .packed_entry_size = SJA1110_SIZE_L2_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT, + }, + [BLK_IDX_L2_POLICING] = { + .packing = sja1110_l2_policing_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_policing_entry), + .packed_entry_size = SJA1105_SIZE_L2_POLICING_ENTRY, + .max_entry_count = SJA1110_MAX_L2_POLICING_COUNT, + }, + [BLK_IDX_VLAN_LOOKUP] = { + .packing = sja1110_vlan_lookup_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_vlan_lookup_entry), + .packed_entry_size = SJA1110_SIZE_VLAN_LOOKUP_ENTRY, + .max_entry_count = SJA1105_MAX_VLAN_LOOKUP_COUNT, + }, + [BLK_IDX_L2_FORWARDING] = { + .packing = sja1110_l2_forwarding_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_ENTRY, + .max_entry_count = SJA1110_MAX_L2_FORWARDING_COUNT, + }, + [BLK_IDX_MAC_CONFIG] = { + .packing = sja1110_mac_config_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_mac_config_entry), + .packed_entry_size = SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY, + .max_entry_count = SJA1110_MAX_MAC_CONFIG_COUNT, + }, + [BLK_IDX_SCHEDULE_PARAMS] = { + .packing = sja1110_schedule_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_schedule_params_entry), + .packed_entry_size = SJA1105_SIZE_SCHEDULE_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_SCHEDULE_PARAMS_COUNT, + }, + [BLK_IDX_SCHEDULE_ENTRY_POINTS_PARAMS] = { + .packing = sja1105_schedule_entry_points_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_schedule_entry_points_params_entry), + .packed_entry_size = SJA1105_SIZE_SCHEDULE_ENTRY_POINTS_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_SCHEDULE_ENTRY_POINTS_PARAMS_COUNT, + }, + [BLK_IDX_VL_FORWARDING_PARAMS] = { + .packing = sja1110_vl_forwarding_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_vl_forwarding_params_entry), + .packed_entry_size = SJA1105_SIZE_VL_FORWARDING_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_VL_FORWARDING_PARAMS_COUNT, + }, + [BLK_IDX_L2_LOOKUP_PARAMS] = { + .packing = sja1110_l2_lookup_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_lookup_params_entry), + .packed_entry_size = SJA1110_SIZE_L2_LOOKUP_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_LOOKUP_PARAMS_COUNT, + }, + [BLK_IDX_L2_FORWARDING_PARAMS] = { + .packing = sja1110_l2_forwarding_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_l2_forwarding_params_entry), + .packed_entry_size = SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_L2_FORWARDING_PARAMS_COUNT, + }, + [BLK_IDX_AVB_PARAMS] = { + .packing = sja1105pqrs_avb_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_avb_params_entry), + .packed_entry_size = SJA1105PQRS_SIZE_AVB_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_AVB_PARAMS_COUNT, + }, + [BLK_IDX_GENERAL_PARAMS] = { + .packing = sja1110_general_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_general_params_entry), + .packed_entry_size = SJA1110_SIZE_GENERAL_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_GENERAL_PARAMS_COUNT, + }, + [BLK_IDX_RETAGGING] = { + .packing = sja1110_retagging_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_retagging_entry), + .packed_entry_size = SJA1105_SIZE_RETAGGING_ENTRY, + .max_entry_count = SJA1105_MAX_RETAGGING_COUNT, + }, + [BLK_IDX_XMII_PARAMS] = { + .packing = sja1110_xmii_params_entry_packing, + .unpacked_entry_size = sizeof(struct sja1105_xmii_params_entry), + .packed_entry_size = SJA1110_SIZE_XMII_PARAMS_ENTRY, + .max_entry_count = SJA1105_MAX_XMII_PARAMS_COUNT, + }, + [BLK_IDX_PCP_REMAPPING] = { + .packing = sja1110_pcp_remapping_entry_packing, + .unpacked_entry_size = sizeof(struct sja1110_pcp_remapping_entry), + .packed_entry_size = SJA1110_SIZE_PCP_REMAPPING_ENTRY, + .max_entry_count = SJA1110_MAX_PCP_REMAPPING_COUNT, + }, +}; + int sja1105_static_config_init(struct sja1105_static_config *config, const struct sja1105_table_ops *static_ops, u64 device_id) diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h index bc7606899289..bce0f5c03d0b 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.h +++ b/drivers/net/dsa/sja1105/sja1105_static_config.h @@ -9,19 +9,30 @@ #include #include +#define SJA1105_NUM_PORTS 5 +#define SJA1110_NUM_PORTS 11 +#define SJA1105_MAX_NUM_PORTS SJA1110_NUM_PORTS +#define SJA1105_NUM_TC 8 + +#define SJA1105_SIZE_SPI_MSG_HEADER 4 +#define SJA1105_SIZE_SPI_MSG_MAXLEN (64 * 4) #define SJA1105_SIZE_DEVICE_ID 4 #define SJA1105_SIZE_TABLE_HEADER 12 #define SJA1105_SIZE_SCHEDULE_ENTRY 8 +#define SJA1110_SIZE_SCHEDULE_ENTRY 12 #define SJA1105_SIZE_SCHEDULE_ENTRY_POINTS_ENTRY 4 +#define SJA1110_SIZE_SCHEDULE_ENTRY_POINTS_ENTRY 8 #define SJA1105_SIZE_VL_LOOKUP_ENTRY 12 #define SJA1105_SIZE_VL_POLICING_ENTRY 8 #define SJA1105_SIZE_VL_FORWARDING_ENTRY 4 #define SJA1105_SIZE_L2_POLICING_ENTRY 8 #define SJA1105_SIZE_VLAN_LOOKUP_ENTRY 8 +#define SJA1110_SIZE_VLAN_LOOKUP_ENTRY 12 #define SJA1105_SIZE_L2_FORWARDING_ENTRY 8 #define SJA1105_SIZE_L2_FORWARDING_PARAMS_ENTRY 12 #define SJA1105_SIZE_RETAGGING_ENTRY 8 #define SJA1105_SIZE_XMII_PARAMS_ENTRY 4 +#define SJA1110_SIZE_XMII_PARAMS_ENTRY 8 #define SJA1105_SIZE_SCHEDULE_PARAMS_ENTRY 12 #define SJA1105_SIZE_SCHEDULE_ENTRY_POINTS_PARAMS_ENTRY 4 #define SJA1105_SIZE_VL_FORWARDING_PARAMS_ENTRY 12 @@ -32,11 +43,15 @@ #define SJA1105ET_SIZE_AVB_PARAMS_ENTRY 12 #define SJA1105ET_SIZE_CBS_ENTRY 16 #define SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY 20 +#define SJA1110_SIZE_L2_LOOKUP_ENTRY 24 #define SJA1105PQRS_SIZE_MAC_CONFIG_ENTRY 32 #define SJA1105PQRS_SIZE_L2_LOOKUP_PARAMS_ENTRY 16 +#define SJA1110_SIZE_L2_LOOKUP_PARAMS_ENTRY 28 #define SJA1105PQRS_SIZE_GENERAL_PARAMS_ENTRY 44 +#define SJA1110_SIZE_GENERAL_PARAMS_ENTRY 56 #define SJA1105PQRS_SIZE_AVB_PARAMS_ENTRY 16 #define SJA1105PQRS_SIZE_CBS_ENTRY 20 +#define SJA1110_SIZE_PCP_REMAPPING_ENTRY 4 /* UM10944.pdf Page 11, Table 2. Configuration Blocks */ enum { @@ -59,6 +74,7 @@ enum { BLKID_GENERAL_PARAMS = 0x11, BLKID_RETAGGING = 0x12, BLKID_CBS = 0x13, + BLKID_PCP_REMAPPING = 0x1C, BLKID_XMII_PARAMS = 0x4E, }; @@ -83,6 +99,7 @@ enum sja1105_blk_idx { BLK_IDX_RETAGGING, BLK_IDX_CBS, BLK_IDX_XMII_PARAMS, + BLK_IDX_PCP_REMAPPING, BLK_IDX_MAX, /* Fake block indices that are only valid for dynamic access */ BLK_IDX_MGMT_ROUTE, @@ -91,15 +108,22 @@ enum sja1105_blk_idx { }; #define SJA1105_MAX_SCHEDULE_COUNT 1024 +#define SJA1110_MAX_SCHEDULE_COUNT 4096 #define SJA1105_MAX_SCHEDULE_ENTRY_POINTS_COUNT 2048 #define SJA1105_MAX_VL_LOOKUP_COUNT 1024 +#define SJA1110_MAX_VL_LOOKUP_COUNT 4096 #define SJA1105_MAX_VL_POLICING_COUNT 1024 +#define SJA1110_MAX_VL_POLICING_COUNT 4096 #define SJA1105_MAX_VL_FORWARDING_COUNT 1024 +#define SJA1110_MAX_VL_FORWARDING_COUNT 4096 #define SJA1105_MAX_L2_LOOKUP_COUNT 1024 #define SJA1105_MAX_L2_POLICING_COUNT 45 +#define SJA1110_MAX_L2_POLICING_COUNT 110 #define SJA1105_MAX_VLAN_LOOKUP_COUNT 4096 #define SJA1105_MAX_L2_FORWARDING_COUNT 13 +#define SJA1110_MAX_L2_FORWARDING_COUNT 19 #define SJA1105_MAX_MAC_CONFIG_COUNT 5 +#define SJA1110_MAX_MAC_CONFIG_COUNT 11 #define SJA1105_MAX_SCHEDULE_PARAMS_COUNT 1 #define SJA1105_MAX_SCHEDULE_ENTRY_POINTS_PARAMS_COUNT 1 #define SJA1105_MAX_VL_FORWARDING_PARAMS_COUNT 1 @@ -111,21 +135,40 @@ enum sja1105_blk_idx { #define SJA1105_MAX_AVB_PARAMS_COUNT 1 #define SJA1105ET_MAX_CBS_COUNT 10 #define SJA1105PQRS_MAX_CBS_COUNT 16 +#define SJA1110_MAX_CBS_COUNT 80 +#define SJA1110_MAX_PCP_REMAPPING_COUNT 11 #define SJA1105_MAX_FRAME_MEMORY 929 -#define SJA1105_MAX_FRAME_MEMORY_RETAGGING 910 +#define SJA1110_MAX_FRAME_MEMORY 1820 +#define SJA1105_FRAME_MEMORY_RETAGGING_OVERHEAD 19 #define SJA1105_VL_FRAME_MEMORY 100 #define SJA1105E_DEVICE_ID 0x9C00000Cull #define SJA1105T_DEVICE_ID 0x9E00030Eull #define SJA1105PR_DEVICE_ID 0xAF00030Eull #define SJA1105QS_DEVICE_ID 0xAE00030Eull +#define SJA1110_DEVICE_ID 0xB700030Full #define SJA1105ET_PART_NO 0x9A83 #define SJA1105P_PART_NO 0x9A84 #define SJA1105Q_PART_NO 0x9A85 #define SJA1105R_PART_NO 0x9A86 #define SJA1105S_PART_NO 0x9A87 +#define SJA1110A_PART_NO 0x1110 +#define SJA1110B_PART_NO 0x1111 +#define SJA1110C_PART_NO 0x1112 +#define SJA1110D_PART_NO 0x1113 + +#define SJA1110_ACU 0x1c4400 +#define SJA1110_RGU 0x1c6000 +#define SJA1110_CGU 0x1c6400 + +#define SJA1110_SPI_ADDR(x) ((x) / 4) +#define SJA1110_ACU_ADDR(x) (SJA1110_ACU + SJA1110_SPI_ADDR(x)) +#define SJA1110_CGU_ADDR(x) (SJA1110_CGU + SJA1110_SPI_ADDR(x)) +#define SJA1110_RGU_ADDR(x) (SJA1110_RGU + SJA1110_SPI_ADDR(x)) + +#define SJA1105_RSV_ADDR 0xffffffffffffffffull struct sja1105_schedule_entry { u64 winstindex; @@ -171,6 +214,10 @@ struct sja1105_general_params_entry { u64 egrmirrpcp; u64 egrmirrdei; u64 replay_port; + /* SJA1110 only */ + u64 tte_en; + u64 tdmaconfigidx; + u64 header_type; }; struct sja1105_schedule_entry_points_entry { @@ -191,6 +238,7 @@ struct sja1105_vlan_lookup_entry { u64 vlan_bc; u64 tag_port; u64 vlanid; + u64 type_entry; /* SJA1110 only */ }; struct sja1105_l2_lookup_entry { @@ -203,11 +251,17 @@ struct sja1105_l2_lookup_entry { u64 mask_iotag; u64 mask_vlanid; u64 mask_macaddr; + u64 mask_srcport; u64 iotag; + u64 srcport; u64 lockeds; union { /* LOCKEDS=1: Static FDB entries */ struct { + /* TSREG is deprecated in SJA1110, TRAP is supported only + * in SJA1110. + */ + u64 trap; u64 tsreg; u64 mirrvlan; u64 takets; @@ -223,7 +277,7 @@ struct sja1105_l2_lookup_entry { }; struct sja1105_l2_lookup_params_entry { - u64 maxaddrp[5]; /* P/Q/R/S only */ + u64 maxaddrp[SJA1105_MAX_NUM_PORTS]; /* P/Q/R/S only */ u64 start_dynspc; /* P/Q/R/S only */ u64 drpnolearn; /* P/Q/R/S only */ u64 use_static; /* P/Q/R/S only */ @@ -241,7 +295,9 @@ struct sja1105_l2_forwarding_entry { u64 bc_domain; u64 reach_port; u64 fl_domain; - u64 vlan_pmap[8]; + /* This is actually max(SJA1105_NUM_TC, SJA1105_MAX_NUM_PORTS) */ + u64 vlan_pmap[SJA1105_MAX_NUM_PORTS]; + bool type_egrpcp2outputq; }; struct sja1105_l2_forwarding_params_entry { @@ -296,8 +352,8 @@ struct sja1105_retagging_entry { }; struct sja1105_cbs_entry { - u64 port; - u64 prio; + u64 port; /* Not used for SJA1110 */ + u64 prio; /* Not used for SJA1110 */ u64 credit_hi; u64 credit_lo; u64 send_slope; @@ -305,8 +361,19 @@ struct sja1105_cbs_entry { }; struct sja1105_xmii_params_entry { - u64 phy_mac[5]; - u64 xmii_mode[5]; + u64 phy_mac[SJA1105_MAX_NUM_PORTS]; + u64 xmii_mode[SJA1105_MAX_NUM_PORTS]; + /* The SJA1110 insists being a snowflake, and requires SGMII, + * 2500base-x and internal MII ports connected to the 100base-TX PHY to + * set this bit. We set it unconditionally from the high-level logic, + * and only sja1110_xmii_params_entry_packing writes it to the static + * config. I have no better name for it than "special". + */ + u64 special[SJA1105_MAX_NUM_PORTS]; +}; + +struct sja1110_pcp_remapping_entry { + u64 egrpcp[SJA1105_NUM_TC]; }; enum { @@ -387,6 +454,7 @@ extern const struct sja1105_table_ops sja1105p_table_ops[BLK_IDX_MAX]; extern const struct sja1105_table_ops sja1105q_table_ops[BLK_IDX_MAX]; extern const struct sja1105_table_ops sja1105r_table_ops[BLK_IDX_MAX]; extern const struct sja1105_table_ops sja1105s_table_ops[BLK_IDX_MAX]; +extern const struct sja1105_table_ops sja1110_table_ops[BLK_IDX_MAX]; size_t sja1105_table_header_packing(void *buf, void *hdr, enum packing_op op); void @@ -412,7 +480,8 @@ typedef enum { extern const char *sja1105_static_config_error_msg[]; sja1105_config_valid_t -sja1105_static_config_check_valid(const struct sja1105_static_config *config); +sja1105_static_config_check_valid(const struct sja1105_static_config *config, + int max_mem); void sja1105_static_config_pack(void *buf, struct sja1105_static_config *config); int sja1105_static_config_init(struct sja1105_static_config *config, @@ -433,23 +502,47 @@ void sja1105_packing(void *buf, u64 *val, int start, int end, /* Common implementations for the static and dynamic configs */ size_t sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr, enum packing_op op); +size_t sja1110_general_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); size_t sja1105pqrs_l2_lookup_params_entry_packing(void *buf, void *entry_ptr, enum packing_op op); +size_t sja1110_l2_lookup_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); size_t sja1105_l2_forwarding_entry_packing(void *buf, void *entry_ptr, enum packing_op op); +size_t sja1110_l2_forwarding_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); size_t sja1105pqrs_l2_lookup_entry_packing(void *buf, void *entry_ptr, enum packing_op op); size_t sja1105et_l2_lookup_entry_packing(void *buf, void *entry_ptr, enum packing_op op); +size_t sja1110_l2_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); size_t sja1105_vlan_lookup_entry_packing(void *buf, void *entry_ptr, enum packing_op op); +size_t sja1110_vlan_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); size_t sja1105_retagging_entry_packing(void *buf, void *entry_ptr, enum packing_op op); +size_t sja1110_retagging_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); size_t sja1105pqrs_mac_config_entry_packing(void *buf, void *entry_ptr, enum packing_op op); +size_t sja1110_mac_config_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); size_t sja1105pqrs_avb_params_entry_packing(void *buf, void *entry_ptr, enum packing_op op); size_t sja1105_vl_lookup_entry_packing(void *buf, void *entry_ptr, enum packing_op op); +size_t sja1110_vl_lookup_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); +size_t sja1110_vl_policing_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); +size_t sja1110_xmii_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); +size_t sja1110_l2_policing_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); +size_t sja1110_l2_forwarding_params_entry_packing(void *buf, void *entry_ptr, + enum packing_op op); #endif diff --git a/drivers/net/dsa/sja1105/sja1105_tas.c b/drivers/net/dsa/sja1105/sja1105_tas.c index 31d8acff1f01..e6153848a950 100644 --- a/drivers/net/dsa/sja1105/sja1105_tas.c +++ b/drivers/net/dsa/sja1105/sja1105_tas.c @@ -27,7 +27,7 @@ static int sja1105_tas_set_runtime_params(struct sja1105_private *priv) tas_data->enabled = false; - for (port = 0; port < SJA1105_NUM_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { const struct tc_taprio_qopt_offload *offload; offload = tas_data->offload[port]; @@ -164,6 +164,7 @@ int sja1105_init_scheduling(struct sja1105_private *priv) struct sja1105_tas_data *tas_data = &priv->tas_data; struct sja1105_gating_config *gating_cfg = &tas_data->gating_cfg; struct sja1105_schedule_entry *schedule; + struct dsa_switch *ds = priv->ds; struct sja1105_table *table; int schedule_start_idx; s64 entry_point_delta; @@ -207,7 +208,7 @@ int sja1105_init_scheduling(struct sja1105_private *priv) } /* Figure out the dimensioning of the problem */ - for (port = 0; port < SJA1105_NUM_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { if (tas_data->offload[port]) { num_entries += tas_data->offload[port]->num_entries; num_cycles++; @@ -269,7 +270,7 @@ int sja1105_init_scheduling(struct sja1105_private *priv) schedule_entry_points_params->clksrc = SJA1105_TAS_CLKSRC_PTP; schedule_entry_points_params->actsubsch = num_cycles - 1; - for (port = 0; port < SJA1105_NUM_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { const struct tc_taprio_qopt_offload *offload; /* Relative base time */ s64 rbt; @@ -468,6 +469,7 @@ bool sja1105_gating_check_conflicts(struct sja1105_private *priv, int port, struct sja1105_gating_config *gating_cfg = &priv->tas_data.gating_cfg; size_t num_entries = gating_cfg->num_entries; struct tc_taprio_qopt_offload *dummy; + struct dsa_switch *ds = priv->ds; struct sja1105_gate_entry *e; bool conflict; int i = 0; @@ -491,7 +493,7 @@ bool sja1105_gating_check_conflicts(struct sja1105_private *priv, int port, if (port != -1) { conflict = sja1105_tas_check_conflicts(priv, port, dummy); } else { - for (port = 0; port < SJA1105_NUM_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { conflict = sja1105_tas_check_conflicts(priv, port, dummy); if (conflict) @@ -554,7 +556,7 @@ int sja1105_setup_tc_taprio(struct dsa_switch *ds, int port, } } - for (other_port = 0; other_port < SJA1105_NUM_PORTS; other_port++) { + for (other_port = 0; other_port < ds->num_ports; other_port++) { if (other_port == port) continue; @@ -885,7 +887,7 @@ void sja1105_tas_teardown(struct dsa_switch *ds) cancel_work_sync(&priv->tas_data.tas_work); - for (port = 0; port < SJA1105_NUM_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { offload = priv->tas_data.offload[port]; if (!offload) continue; diff --git a/drivers/net/dsa/sja1105/sja1105_tas.h b/drivers/net/dsa/sja1105/sja1105_tas.h index 0c173ff51751..c05bd07e8221 100644 --- a/drivers/net/dsa/sja1105/sja1105_tas.h +++ b/drivers/net/dsa/sja1105/sja1105_tas.h @@ -39,7 +39,7 @@ struct sja1105_gating_config { }; struct sja1105_tas_data { - struct tc_taprio_qopt_offload *offload[SJA1105_NUM_PORTS]; + struct tc_taprio_qopt_offload *offload[SJA1105_MAX_NUM_PORTS]; struct sja1105_gating_config gating_cfg; enum sja1105_tas_state state; enum sja1105_ptp_op last_op; diff --git a/drivers/net/dsa/sja1105/sja1105_vl.c b/drivers/net/dsa/sja1105/sja1105_vl.c index ffc4042b4502..f6e13e6c6a18 100644 --- a/drivers/net/dsa/sja1105/sja1105_vl.c +++ b/drivers/net/dsa/sja1105/sja1105_vl.c @@ -386,7 +386,7 @@ static int sja1105_init_virtual_links(struct sja1105_private *priv, if (rule->type != SJA1105_RULE_VL) continue; - for_each_set_bit(port, &rule->port_mask, SJA1105_NUM_PORTS) { + for_each_set_bit(port, &rule->port_mask, SJA1105_MAX_NUM_PORTS) { vl_lookup[k].format = SJA1105_VL_FORMAT_PSFP; vl_lookup[k].port = port; vl_lookup[k].macaddr = rule->key.vl.dmac; diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c index fde6e99274b6..130abb0f1438 100644 --- a/drivers/net/dsa/xrs700x/xrs700x.c +++ b/drivers/net/dsa/xrs700x/xrs700x.c @@ -79,6 +79,9 @@ static const struct xrs700x_mib xrs700x_mibs[] = { XRS700X_MIB(XRS_EARLY_DROP_L, "early_drop", tx_dropped), }; +static const u8 eth_hsrsup_addr[ETH_ALEN] = { + 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00}; + static void xrs700x_get_strings(struct dsa_switch *ds, int port, u32 stringset, u8 *data) { @@ -329,6 +332,54 @@ static int xrs700x_port_add_bpdu_ipf(struct dsa_switch *ds, int port) return 0; } +/* Add an inbound policy filter which matches the HSR/PRP supervision MAC + * range and forwards to the CPU port without discarding duplicates. + * This is required to correctly populate the HSR/PRP node_table. + * Leave the policy disabled, it will be enabled as needed. + */ +static int xrs700x_port_add_hsrsup_ipf(struct dsa_switch *ds, int port, + int fwdport) +{ + struct xrs700x *priv = ds->priv; + unsigned int val = 0; + int i = 0; + int ret; + + /* Compare 40 bits of the destination MAC address. */ + ret = regmap_write(priv->regmap, XRS_ETH_ADDR_CFG(port, 1), 40 << 2); + if (ret) + return ret; + + /* match HSR/PRP supervision destination 01:15:4e:00:01:XX */ + for (i = 0; i < sizeof(eth_hsrsup_addr); i += 2) { + ret = regmap_write(priv->regmap, XRS_ETH_ADDR_0(port, 1) + i, + eth_hsrsup_addr[i] | + (eth_hsrsup_addr[i + 1] << 8)); + if (ret) + return ret; + } + + /* Mirror HSR/PRP supervision to CPU port */ + for (i = 0; i < ds->num_ports; i++) { + if (dsa_is_cpu_port(ds, i)) + val |= BIT(i); + } + + ret = regmap_write(priv->regmap, XRS_ETH_ADDR_FWD_MIRROR(port, 1), val); + if (ret) + return ret; + + if (fwdport >= 0) + val |= BIT(fwdport); + + /* Allow must be set prevent duplicate discard */ + ret = regmap_write(priv->regmap, XRS_ETH_ADDR_FWD_ALLOW(port, 1), val); + if (ret) + return ret; + + return 0; +} + static int xrs700x_port_setup(struct dsa_switch *ds, int port) { bool cpu_port = dsa_is_cpu_port(ds, port); @@ -511,6 +562,7 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port, struct net_device *slave; int ret, i, hsr_pair[2]; enum hsr_version ver; + bool fwd = false; ret = hsr_get_version(hsr, &ver); if (ret) @@ -556,6 +608,7 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port, if (ver == HSR_V1) { val &= ~BIT(partner->index); val &= ~BIT(port); + fwd = true; } val &= ~BIT(dsa_upstream_port(ds, port)); regmap_write(priv->regmap, XRS_PORT_FWD_MASK(partner->index), val); @@ -565,6 +618,23 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port, XRS_PORT_FORWARDING); regmap_fields_write(priv->ps_forward, port, XRS_PORT_FORWARDING); + /* Enable inbound policy which allows HSR/PRP supervision forwarding + * to the CPU port without discarding duplicates. Continue to + * forward to redundant ports when in HSR mode while discarding + * duplicates. + */ + ret = xrs700x_port_add_hsrsup_ipf(ds, partner->index, fwd ? port : -1); + if (ret) + return ret; + + ret = xrs700x_port_add_hsrsup_ipf(ds, port, fwd ? partner->index : -1); + if (ret) + return ret; + + regmap_update_bits(priv->regmap, + XRS_ETH_ADDR_CFG(partner->index, 1), 1, 1); + regmap_update_bits(priv->regmap, XRS_ETH_ADDR_CFG(port, 1), 1, 1); + hsr_pair[0] = port; hsr_pair[1] = partner->index; for (i = 0; i < ARRAY_SIZE(hsr_pair); i++) { @@ -611,6 +681,14 @@ static int xrs700x_hsr_leave(struct dsa_switch *ds, int port, XRS_PORT_FORWARDING); regmap_fields_write(priv->ps_forward, port, XRS_PORT_FORWARDING); + /* Disable inbound policy added by xrs700x_port_add_hsrsup_ipf() + * which allows HSR/PRP supervision forwarding to the CPU port without + * discarding duplicates. + */ + regmap_update_bits(priv->regmap, + XRS_ETH_ADDR_CFG(partner->index, 1), 1, 0); + regmap_update_bits(priv->regmap, XRS_ETH_ADDR_CFG(port, 1), 1, 0); + hsr_pair[0] = port; hsr_pair[1] = partner->index; for (i = 0; i < ARRAY_SIZE(hsr_pair); i++) { diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 741c67e546d4..7d7d3ffe25c3 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -1464,7 +1464,7 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq, if (pdev) { vp->pm_state_valid = 1; pci_save_state(pdev); - acpi_set_WOL(dev); + acpi_set_WOL(dev); } retval = register_netdev(dev); if (retval == 0) diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c index 2488bfdb9133..8c321dfc7b3b 100644 --- a/drivers/net/ethernet/8390/axnet_cs.c +++ b/drivers/net/ethernet/8390/axnet_cs.c @@ -767,7 +767,7 @@ module_pcmcia_driver(axnet_cs_driver); Paul Gortmaker : tweak ANK's above multicast changes a bit. Paul Gortmaker : update packet statistics for v2.1.x Alan Cox : support arbitrary stupid port mappings on the - 68K Macintosh. Support >16bit I/O spaces + 68K Macintosh. Support >16bit I/O spaces Paul Gortmaker : add kmod support for auto-loading of the 8390 module by all drivers that require it. Alan Cox : Spinlocking work, added 'BUG_83C690' @@ -1091,7 +1091,7 @@ static irqreturn_t ax_interrupt(int irq, void *dev_id) long e8390_base; int interrupts, nr_serviced = 0, i; struct ei_device *ei_local; - int handled = 0; + int handled = 0; unsigned long flags; e8390_base = dev->base_addr; @@ -1587,12 +1587,12 @@ static void do_set_multicast_list(struct net_device *dev) } outb_p(E8390_NODMA + E8390_PAGE0, e8390_base + E8390_CMD); - if(dev->flags&IFF_PROMISC) - outb_p(E8390_RXCONFIG | 0x58, e8390_base + EN0_RXCR); + if(dev->flags&IFF_PROMISC) + outb_p(E8390_RXCONFIG | 0x58, e8390_base + EN0_RXCR); else if (dev->flags & IFF_ALLMULTI || !netdev_mc_empty(dev)) - outb_p(E8390_RXCONFIG | 0x48, e8390_base + EN0_RXCR); - else - outb_p(E8390_RXCONFIG | 0x40, e8390_base + EN0_RXCR); + outb_p(E8390_RXCONFIG | 0x48, e8390_base + EN0_RXCR); + else + outb_p(E8390_RXCONFIG | 0x40, e8390_base + EN0_RXCR); outb_p(E8390_NODMA+E8390_PAGE0+E8390_START, e8390_base+E8390_CMD); } diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c index 9d3b1e0e425c..cac036706382 100644 --- a/drivers/net/ethernet/8390/pcnet_cs.c +++ b/drivers/net/ethernet/8390/pcnet_cs.c @@ -1527,7 +1527,7 @@ static const struct pcmcia_device_id pcnet_ids[] = { PCMCIA_DEVICE_PROD_ID12("ACCTON", "EN2216-PCMCIA-ETHERNET", 0xdfc6b5b2, 0x5542bfff), PCMCIA_DEVICE_PROD_ID12("Allied Telesis, K.K.", "CentreCOM LA100-PCM-T V2 100/10M LAN PC Card", 0xbb7fbdd7, 0xcd91cc68), PCMCIA_DEVICE_PROD_ID12("Allied Telesis K.K.", "LA100-PCM V2", 0x36634a66, 0xc6d05997), - PCMCIA_DEVICE_PROD_ID12("Allied Telesis, K.K.", "CentreCOM LA-PCM_V2", 0xbb7fBdd7, 0x28e299f8), + PCMCIA_DEVICE_PROD_ID12("Allied Telesis, K.K.", "CentreCOM LA-PCM_V2", 0xbb7fBdd7, 0x28e299f8), PCMCIA_DEVICE_PROD_ID12("Allied Telesis K.K.", "LA-PCM V3", 0x36634a66, 0x62241d96), PCMCIA_DEVICE_PROD_ID12("AmbiCom", "AMB8010", 0x5070a7f9, 0x82f96e96), PCMCIA_DEVICE_PROD_ID12("AmbiCom", "AMB8610", 0x5070a7f9, 0x86741224), diff --git a/drivers/net/ethernet/8390/smc-ultra.c b/drivers/net/ethernet/8390/smc-ultra.c index 3fe3b4dfa7c5..1d8ed7357b7f 100644 --- a/drivers/net/ethernet/8390/smc-ultra.c +++ b/drivers/net/ethernet/8390/smc-ultra.c @@ -347,11 +347,11 @@ static int __init ultra_probe_isapnp(struct net_device *dev) idev))) { /* Avoid already found cards from previous calls */ if (pnp_device_attach(idev) < 0) - continue; + continue; if (pnp_activate_dev(idev) < 0) { __again: - pnp_device_detach(idev); - continue; + pnp_device_detach(idev); + continue; } /* if no io and irq, search for next */ if (!pnp_port_valid(idev, 0) || !pnp_irq_valid(idev, 0)) diff --git a/drivers/net/ethernet/8390/stnic.c b/drivers/net/ethernet/8390/stnic.c index 1f0670cd3ea3..fbbd7f22c142 100644 --- a/drivers/net/ethernet/8390/stnic.c +++ b/drivers/net/ethernet/8390/stnic.c @@ -114,7 +114,7 @@ static int __init stnic_probe(void) /* New style probing API */ dev = alloc_ei_netdev(); if (!dev) - return -ENOMEM; + return -ENOMEM; #ifdef CONFIG_SH_STANDARD_BIOS sh_bios_get_node_addr (stnic_eadr); diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index d77fafbc1530..c560ad06f0be 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -1539,10 +1539,11 @@ static int greth_of_remove(struct platform_device *of_dev) mdiobus_unregister(greth->mdio); unregister_netdev(ndev); - free_netdev(ndev); of_iounmap(&of_dev->resource[0], greth->regs, resource_size(&of_dev->resource[0])); + free_netdev(ndev); + return 0; } diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index 1a7e4df9b3e9..9dc12b13061f 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -1883,16 +1883,16 @@ static u32 ace_handle_event(struct net_device *dev, u32 evtcsm, u32 evtprd) } } - if (ACE_IS_TIGON_I(ap)) { - struct cmd cmd; - cmd.evt = C_SET_RX_JUMBO_PRD_IDX; - cmd.code = 0; - cmd.idx = 0; - ace_issue_cmd(ap->regs, &cmd); - } else { - writel(0, &((ap->regs)->RxJumboPrd)); - wmb(); - } + if (ACE_IS_TIGON_I(ap)) { + struct cmd cmd; + cmd.evt = C_SET_RX_JUMBO_PRD_IDX; + cmd.code = 0; + cmd.idx = 0; + ace_issue_cmd(ap->regs, &cmd); + } else { + writel(0, &((ap->regs)->RxJumboPrd)); + wmb(); + } ap->jumbo = 0; ap->rx_jumbo_skbprd = 0; @@ -2489,9 +2489,9 @@ restart: } } - wmb(); - ap->tx_prd = idx; - ace_set_txprd(regs, ap, idx); + wmb(); + ap->tx_prd = idx; + ace_set_txprd(regs, ap, idx); if (flagsize & BD_FLG_COAL_NOW) { netif_stop_queue(dev); diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h index 4164eacc5c28..f5ec35fa4c63 100644 --- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h +++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h @@ -1042,8 +1042,6 @@ enum ena_admin_aenq_group { }; enum ena_admin_aenq_notification_syndrome { - ENA_ADMIN_SUSPEND = 0, - ENA_ADMIN_RESUME = 1, ENA_ADMIN_UPDATE_HINTS = 2, }; diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 764852ead1d6..ab413fc1f68e 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -1979,7 +1979,8 @@ int ena_com_get_dev_attr_feat(struct ena_com_dev *ena_dev, if (rc) return rc; - if (get_resp.u.max_queue_ext.version != ENA_FEATURE_MAX_QUEUE_EXT_VER) + if (get_resp.u.max_queue_ext.version != + ENA_FEATURE_MAX_QUEUE_EXT_VER) return -EINVAL; memcpy(&get_feat_ctx->max_queue_ext, &get_resp.u.max_queue_ext, diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c index c3be751e7379..3d6f0a466a9e 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c @@ -151,11 +151,14 @@ static int ena_com_close_bounce_buffer(struct ena_com_io_sq *io_sq) return 0; /* bounce buffer was used, so write it and get a new one */ - if (pkt_ctrl->idx) { + if (likely(pkt_ctrl->idx)) { rc = ena_com_write_bounce_buffer_to_dev(io_sq, pkt_ctrl->curr_bounce_buf); - if (unlikely(rc)) + if (unlikely(rc)) { + netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, + "Failed to write bounce buffer to device\n"); return rc; + } pkt_ctrl->curr_bounce_buf = ena_com_get_next_bounce_buffer(&io_sq->bounce_buf_ctrl); @@ -185,8 +188,11 @@ static int ena_com_sq_update_llq_tail(struct ena_com_io_sq *io_sq) if (!pkt_ctrl->descs_left_in_line) { rc = ena_com_write_bounce_buffer_to_dev(io_sq, pkt_ctrl->curr_bounce_buf); - if (unlikely(rc)) + if (unlikely(rc)) { + netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, + "Failed to write bounce buffer to device\n"); return rc; + } pkt_ctrl->curr_bounce_buf = ena_com_get_next_bounce_buffer(&io_sq->bounce_buf_ctrl); @@ -406,8 +412,11 @@ int ena_com_prepare_tx(struct ena_com_io_sq *io_sq, } if (unlikely(io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_DEV && - !buffer_to_push)) + !buffer_to_push)) { + netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, + "Push header wasn't provided in LLQ mode\n"); return -EINVAL; + } rc = ena_com_write_header_to_bounce(io_sq, buffer_to_push, header_len); if (unlikely(rc)) @@ -423,6 +432,9 @@ int ena_com_prepare_tx(struct ena_com_io_sq *io_sq, /* If the caller doesn't want to send packets */ if (unlikely(!num_bufs && !header_len)) { rc = ena_com_close_bounce_buffer(io_sq); + if (rc) + netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, + "Failed to write buffers to LLQ\n"); *nb_hw_desc = io_sq->tail - start_tail; return rc; } @@ -482,8 +494,11 @@ int ena_com_prepare_tx(struct ena_com_io_sq *io_sq, /* The first desc share the same desc as the header */ if (likely(i != 0)) { rc = ena_com_sq_update_tail(io_sq); - if (unlikely(rc)) + if (unlikely(rc)) { + netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, + "Failed to update sq tail\n"); return rc; + } desc = get_sq_desc(io_sq); if (unlikely(!desc)) @@ -512,8 +527,11 @@ int ena_com_prepare_tx(struct ena_com_io_sq *io_sq, desc->len_ctrl |= ENA_ETH_IO_TX_DESC_LAST_MASK; rc = ena_com_sq_update_tail(io_sq); - if (unlikely(rc)) + if (unlikely(rc)) { + netdev_err(ena_com_io_sq_to_ena_dev(io_sq)->net_device, + "Failed to update sq tail of the last descriptor\n"); return rc; + } rc = ena_com_close_bounce_buffer(io_sq); diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index 2fe7ccee55b2..27dae632efcb 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -233,10 +233,13 @@ int ena_get_sset_count(struct net_device *netdev, int sset) { struct ena_adapter *adapter = netdev_priv(netdev); - if (sset != ETH_SS_STATS) - return -EOPNOTSUPP; + switch (sset) { + case ETH_SS_STATS: + return ena_get_sw_stats_count(adapter) + + ena_get_hw_stats_count(adapter); + } - return ena_get_sw_stats_count(adapter) + ena_get_hw_stats_count(adapter); + return -EOPNOTSUPP; } static void ena_queue_strings(struct ena_adapter *adapter, u8 **data) @@ -314,10 +317,11 @@ static void ena_get_ethtool_strings(struct net_device *netdev, { struct ena_adapter *adapter = netdev_priv(netdev); - if (sset != ETH_SS_STATS) - return; - - ena_get_strings(adapter, data, adapter->eni_stats_supported); + switch (sset) { + case ETH_SS_STATS: + ena_get_strings(adapter, data, adapter->eni_stats_supported); + break; + } } static int ena_get_link_ksettings(struct net_device *netdev, diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 52571486705e..0e43000614ab 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -35,9 +35,6 @@ MODULE_LICENSE("GPL"); #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | \ NETIF_MSG_TX_DONE | NETIF_MSG_TX_ERR | NETIF_MSG_RX_ERR) -static int debug = -1; -module_param(debug, int, 0); -MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); static struct ena_aenq_handlers aenq_handlers; @@ -89,6 +86,12 @@ static void ena_increase_stat(u64 *statp, u64 cnt, u64_stats_update_end(syncp); } +static void ena_ring_tx_doorbell(struct ena_ring *tx_ring) +{ + ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq); + ena_increase_stat(&tx_ring->tx_stats.doorbells, 1, &tx_ring->syncp); +} + static void ena_tx_timeout(struct net_device *dev, unsigned int txqueue) { struct ena_adapter *adapter = netdev_priv(dev); @@ -147,7 +150,7 @@ static int ena_xmit_common(struct net_device *dev, netif_dbg(adapter, tx_queued, dev, "llq tx max burst size of queue %d achieved, writing doorbell to send burst\n", ring->qid); - ena_com_write_sq_doorbell(ring->ena_com_io_sq); + ena_ring_tx_doorbell(ring); } /* prepare the packet's descriptors to dma engine */ @@ -197,7 +200,6 @@ static int ena_xdp_io_poll(struct napi_struct *napi, int budget) int ret; xdp_ring = ena_napi->xdp_ring; - xdp_ring->first_interrupt = ena_napi->first_interrupt; xdp_budget = budget; @@ -229,6 +231,7 @@ static int ena_xdp_io_poll(struct napi_struct *napi, int budget) xdp_ring->tx_stats.napi_comp += napi_comp_call; xdp_ring->tx_stats.tx_poll++; u64_stats_update_end(&xdp_ring->syncp); + xdp_ring->tx_stats.last_napi_jiffies = jiffies; return ret; } @@ -318,14 +321,12 @@ static int ena_xdp_xmit_frame(struct ena_ring *xdp_ring, xdpf->len); if (rc) goto error_unmap_dma; - /* trigger the dma engine. ena_com_write_sq_doorbell() - * has a mb + + /* trigger the dma engine. ena_ring_tx_doorbell() + * calls a memory barrier inside it. */ - if (flags & XDP_XMIT_FLUSH) { - ena_com_write_sq_doorbell(xdp_ring->ena_com_io_sq); - ena_increase_stat(&xdp_ring->tx_stats.doorbells, 1, - &xdp_ring->syncp); - } + if (flags & XDP_XMIT_FLUSH) + ena_ring_tx_doorbell(xdp_ring); return rc; @@ -366,11 +367,8 @@ static int ena_xdp_xmit(struct net_device *dev, int n, } /* Ring doorbell to make device aware of the packets */ - if (flags & XDP_XMIT_FLUSH) { - ena_com_write_sq_doorbell(xdp_ring->ena_com_io_sq); - ena_increase_stat(&xdp_ring->tx_stats.doorbells, 1, - &xdp_ring->syncp); - } + if (flags & XDP_XMIT_FLUSH) + ena_ring_tx_doorbell(xdp_ring); spin_unlock(&xdp_ring->xdp_tx_lock); @@ -385,9 +383,7 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp) u32 verdict = XDP_PASS; struct xdp_frame *xdpf; u64 *xdp_stat; - int qid; - rcu_read_lock(); xdp_prog = READ_ONCE(rx_ring->xdp_bpf_prog); if (!xdp_prog) @@ -406,8 +402,7 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp) } /* Find xmit queue */ - qid = rx_ring->qid + rx_ring->adapter->num_io_queues; - xdp_ring = &rx_ring->adapter->tx_ring[qid]; + xdp_ring = rx_ring->xdp_ring; /* The XDP queues are shared between XDP_TX and XDP_REDIRECT */ spin_lock(&xdp_ring->xdp_tx_lock); @@ -445,8 +440,6 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp) ena_increase_stat(xdp_stat, 1, &rx_ring->syncp); out: - rcu_read_unlock(); - return verdict; } @@ -534,7 +527,7 @@ static void ena_xdp_exchange_program_rx_in_range(struct ena_adapter *adapter, rx_ring->rx_headroom = XDP_PACKET_HEADROOM; } else { ena_xdp_unregister_rxq_info(rx_ring); - rx_ring->rx_headroom = 0; + rx_ring->rx_headroom = NET_SKB_PAD; } } } @@ -683,7 +676,6 @@ static void ena_init_io_rings_common(struct ena_adapter *adapter, ring->ena_dev = adapter->ena_dev; ring->per_napi_packets = 0; ring->cpu = 0; - ring->first_interrupt = false; ring->no_interrupt_event_cnt = 0; u64_stats_init(&ring->syncp); } @@ -726,7 +718,9 @@ static void ena_init_io_rings(struct ena_adapter *adapter, rxr->smoothed_interval = ena_com_get_nonadaptive_moderation_interval_rx(ena_dev); rxr->empty_rx_queue = 0; + rxr->rx_headroom = NET_SKB_PAD; adapter->ena_napi[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; + rxr->xdp_ring = &adapter->tx_ring[i + adapter->num_io_queues]; } } } @@ -980,13 +974,44 @@ static void ena_free_all_io_rx_resources(struct ena_adapter *adapter) ena_free_rx_resources(adapter, i); } -static int ena_alloc_rx_page(struct ena_ring *rx_ring, - struct ena_rx_buffer *rx_info, gfp_t gfp) +static struct page *ena_alloc_map_page(struct ena_ring *rx_ring, + dma_addr_t *dma) +{ + struct page *page; + + /* This would allocate the page on the same NUMA node the executing code + * is running on. + */ + page = dev_alloc_page(); + if (!page) { + ena_increase_stat(&rx_ring->rx_stats.page_alloc_fail, 1, + &rx_ring->syncp); + return ERR_PTR(-ENOSPC); + } + + /* To enable NIC-side port-mirroring, AKA SPAN port, + * we make the buffer readable from the nic as well + */ + *dma = dma_map_page(rx_ring->dev, page, 0, ENA_PAGE_SIZE, + DMA_BIDIRECTIONAL); + if (unlikely(dma_mapping_error(rx_ring->dev, *dma))) { + ena_increase_stat(&rx_ring->rx_stats.dma_mapping_err, 1, + &rx_ring->syncp); + __free_page(page); + return ERR_PTR(-EIO); + } + + return page; +} + +static int ena_alloc_rx_buffer(struct ena_ring *rx_ring, + struct ena_rx_buffer *rx_info) { int headroom = rx_ring->rx_headroom; struct ena_com_buf *ena_buf; struct page *page; dma_addr_t dma; + int tailroom; /* restore page offset value in case it has been changed by device */ rx_info->page_offset = headroom; @@ -995,32 +1020,20 @@ static int ena_alloc_rx_page(struct ena_ring *rx_ring, if (unlikely(rx_info->page)) return 0; - page = alloc_page(gfp); - if (unlikely(!page)) { - ena_increase_stat(&rx_ring->rx_stats.page_alloc_fail, 1, - &rx_ring->syncp); - return -ENOMEM; - } + /* We handle DMA here */ + page = ena_alloc_map_page(rx_ring, &dma); + if (unlikely(IS_ERR(page))) + return PTR_ERR(page); - /* To enable NIC-side port-mirroring, AKA SPAN port, - * we make the buffer readable from the nic as well - */ - dma = dma_map_page(rx_ring->dev, page, 0, ENA_PAGE_SIZE, - DMA_BIDIRECTIONAL); - if (unlikely(dma_mapping_error(rx_ring->dev, dma))) { - ena_increase_stat(&rx_ring->rx_stats.dma_mapping_err, 1, - &rx_ring->syncp); - - __free_page(page); - return -EIO; - } netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "Allocate page %p, rx_info %p\n", page, rx_info); + tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + rx_info->page = page; ena_buf = &rx_info->ena_buf; ena_buf->paddr = dma + headroom; - ena_buf->len = ENA_PAGE_SIZE - headroom; + ena_buf->len = ENA_PAGE_SIZE - headroom - tailroom; return 0; } @@ -1067,8 +1080,7 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num) rx_info = &rx_ring->rx_buffer_info[req_id]; - rc = ena_alloc_rx_page(rx_ring, rx_info, - GFP_ATOMIC | __GFP_COMP); + rc = ena_alloc_rx_buffer(rx_ring, rx_info); if (unlikely(rc < 0)) { netif_warn(rx_ring->adapter, rx_err, rx_ring->netdev, "Failed to allocate buffer for rx queue %d\n", @@ -1386,21 +1398,23 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget) return tx_pkts; } -static struct sk_buff *ena_alloc_skb(struct ena_ring *rx_ring, bool frags) +static struct sk_buff *ena_alloc_skb(struct ena_ring *rx_ring, void *first_frag) { struct sk_buff *skb; - if (frags) - skb = napi_get_frags(rx_ring->napi); - else + if (!first_frag) skb = netdev_alloc_skb_ip_align(rx_ring->netdev, rx_ring->rx_copybreak); + else + skb = build_skb(first_frag, ENA_PAGE_SIZE); if (unlikely(!skb)) { ena_increase_stat(&rx_ring->rx_stats.skb_alloc_fail, 1, &rx_ring->syncp); + netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev, - "Failed to allocate skb. frags: %d\n", frags); + "Failed to allocate skb. first_frag %s\n", + first_frag ? "provided" : "not provided"); return NULL; } @@ -1412,10 +1426,12 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, u32 descs, u16 *next_to_clean) { - struct sk_buff *skb; struct ena_rx_buffer *rx_info; u16 len, req_id, buf = 0; - void *va; + struct sk_buff *skb; + void *page_addr; + u32 page_offset; + void *data_addr; len = ena_bufs[buf].len; req_id = ena_bufs[buf].req_id; @@ -1433,12 +1449,14 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, rx_info, rx_info->page); /* save virt address of first buffer */ - va = page_address(rx_info->page) + rx_info->page_offset; + page_addr = page_address(rx_info->page); + page_offset = rx_info->page_offset; + data_addr = page_addr + page_offset; - prefetch(va); + prefetch(data_addr); if (len <= rx_ring->rx_copybreak) { - skb = ena_alloc_skb(rx_ring, false); + skb = ena_alloc_skb(rx_ring, NULL); if (unlikely(!skb)) return NULL; @@ -1451,7 +1469,7 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, dma_unmap_addr(&rx_info->ena_buf, paddr), len, DMA_FROM_DEVICE); - skb_copy_to_linear_data(skb, va, len); + skb_copy_to_linear_data(skb, data_addr, len); dma_sync_single_for_device(rx_ring->dev, dma_unmap_addr(&rx_info->ena_buf, paddr), len, @@ -1465,16 +1483,18 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, return skb; } - skb = ena_alloc_skb(rx_ring, true); + ena_unmap_rx_buff(rx_ring, rx_info); + + skb = ena_alloc_skb(rx_ring, page_addr); if (unlikely(!skb)) return NULL; + /* Populate skb's linear part */ + skb_reserve(skb, page_offset); + skb_put(skb, len); + skb->protocol = eth_type_trans(skb, rx_ring->netdev); + do { - ena_unmap_rx_buff(rx_ring, rx_info); - - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page, - rx_info->page_offset, len, ENA_PAGE_SIZE); - netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "RX skb updated. len %d. data_len %d\n", skb->len, skb->data_len); @@ -1493,6 +1513,12 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, req_id = ena_bufs[buf].req_id; rx_info = &rx_ring->rx_buffer_info[req_id]; + + ena_unmap_rx_buff(rx_ring, rx_info); + + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page, + rx_info->page_offset, len, ENA_PAGE_SIZE); + } while (1); return skb; @@ -1705,14 +1731,12 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, skb_record_rx_queue(skb, rx_ring->qid); - if (rx_ring->ena_bufs[0].len <= rx_ring->rx_copybreak) { - total_len += rx_ring->ena_bufs[0].len; + if (rx_ring->ena_bufs[0].len <= rx_ring->rx_copybreak) rx_copybreak_pkt++; - napi_gro_receive(napi, skb); - } else { - total_len += skb->len; - napi_gro_frags(napi); - } + + total_len += skb->len; + + napi_gro_receive(napi, skb); res_budget--; } while (likely(res_budget)); @@ -1924,9 +1948,6 @@ static int ena_io_poll(struct napi_struct *napi, int budget) tx_ring = ena_napi->tx_ring; rx_ring = ena_napi->rx_ring; - tx_ring->first_interrupt = ena_napi->first_interrupt; - rx_ring->first_interrupt = ena_napi->first_interrupt; - tx_budget = tx_ring->ring_size / ENA_TX_POLL_BUDGET_DIVIDER; if (!test_bit(ENA_FLAG_DEV_UP, &tx_ring->adapter->flags) || @@ -1981,6 +2002,8 @@ static int ena_io_poll(struct napi_struct *napi, int budget) tx_ring->tx_stats.tx_poll++; u64_stats_update_end(&tx_ring->syncp); + tx_ring->tx_stats.last_napi_jiffies = jiffies; + return ret; } @@ -2005,7 +2028,8 @@ static irqreturn_t ena_intr_msix_io(int irq, void *data) { struct ena_napi *ena_napi = data; - ena_napi->first_interrupt = true; + /* Used to check HW health */ + WRITE_ONCE(ena_napi->first_interrupt, true); WRITE_ONCE(ena_napi->interrupts_masked, true); smp_wmb(); /* write interrupts_masked before calling napi */ @@ -3091,14 +3115,11 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) } } - if (netif_xmit_stopped(txq) || !netdev_xmit_more()) { - /* trigger the dma engine. ena_com_write_sq_doorbell() - * has a mb + if (netif_xmit_stopped(txq) || !netdev_xmit_more()) + /* trigger the dma engine. ena_ring_tx_doorbell() + * calls a memory barrier inside it. */ - ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq); - ena_increase_stat(&tx_ring->tx_stats.doorbells, 1, - &tx_ring->syncp); - } + ena_ring_tx_doorbell(tx_ring); return NETDEV_TX_OK; @@ -3348,7 +3369,7 @@ static int ena_set_queues_placement_policy(struct pci_dev *pdev, llq_feature_mask = 1 << ENA_ADMIN_LLQ; if (!(ena_dev->supported_features & llq_feature_mask)) { - dev_err(&pdev->dev, + dev_warn(&pdev->dev, "LLQ is not supported Fallback to host mode policy.\n"); ena_dev->tx_mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST; return 0; @@ -3659,7 +3680,9 @@ static void ena_fw_reset_device(struct work_struct *work) static int check_for_rx_interrupt_queue(struct ena_adapter *adapter, struct ena_ring *rx_ring) { - if (likely(rx_ring->first_interrupt)) + struct ena_napi *ena_napi = container_of(rx_ring->napi, struct ena_napi, napi); + + if (likely(READ_ONCE(ena_napi->first_interrupt))) return 0; if (ena_com_cq_empty(rx_ring->ena_com_io_cq)) @@ -3683,6 +3706,10 @@ static int check_for_rx_interrupt_queue(struct ena_adapter *adapter, static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter, struct ena_ring *tx_ring) { + struct ena_napi *ena_napi = container_of(tx_ring->napi, struct ena_napi, napi); + unsigned int time_since_last_napi; + unsigned int missing_tx_comp_to; + bool is_tx_comp_time_expired; struct ena_tx_buffer *tx_buf; unsigned long last_jiffies; u32 missed_tx = 0; @@ -3696,8 +3723,10 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter, /* no pending Tx at this location */ continue; - if (unlikely(!tx_ring->first_interrupt && time_is_before_jiffies(last_jiffies + - 2 * adapter->missing_tx_completion_to))) { + is_tx_comp_time_expired = time_is_before_jiffies(last_jiffies + + 2 * adapter->missing_tx_completion_to); + + if (unlikely(!READ_ONCE(ena_napi->first_interrupt) && is_tx_comp_time_expired)) { /* If after graceful period interrupt is still not * received, we schedule a reset */ @@ -3710,12 +3739,17 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter, return -EIO; } - if (unlikely(time_is_before_jiffies(last_jiffies + - adapter->missing_tx_completion_to))) { - if (!tx_buf->print_once) + is_tx_comp_time_expired = time_is_before_jiffies(last_jiffies + + adapter->missing_tx_completion_to); + + if (unlikely(is_tx_comp_time_expired)) { + if (!tx_buf->print_once) { + time_since_last_napi = jiffies_to_usecs(jiffies - tx_ring->tx_stats.last_napi_jiffies); + missing_tx_comp_to = jiffies_to_msecs(adapter->missing_tx_completion_to); netif_notice(adapter, tx_err, adapter->netdev, - "Found a Tx that wasn't completed on time, qid %d, index %d.\n", - tx_ring->qid, i); + "Found a Tx that wasn't completed on time, qid %d, index %d. %u usecs have passed since last napi execution. Missing Tx timeout value %u msecs\n", + tx_ring->qid, i, time_since_last_napi, missing_tx_comp_to); + } tx_buf->print_once = 1; missed_tx++; @@ -4246,7 +4280,7 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->ena_dev = ena_dev; adapter->netdev = netdev; adapter->pdev = pdev; - adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); + adapter->msg_enable = DEFAULT_MSG_ENABLE; ena_dev->net_device = netdev; diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index 74af15d62ee1..0c39fc2fa345 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -55,12 +55,6 @@ #define ENA_TX_WAKEUP_THRESH (MAX_SKB_FRAGS + 2) #define ENA_DEFAULT_RX_COPYBREAK (256 - NET_IP_ALIGN) -/* limit the buffer size to 600 bytes to handle MTU changes from very - * small to very large, in which case the number of buffers per packet - * could exceed ENA_PKT_MAX_BUFS - */ -#define ENA_DEFAULT_MIN_RX_BUFF_ALLOC_SIZE 600 - #define ENA_MIN_MTU 128 #define ENA_NAME_MAX_LEN 20 @@ -135,12 +129,12 @@ struct ena_irq { }; struct ena_napi { - struct napi_struct napi ____cacheline_aligned; + u8 first_interrupt ____cacheline_aligned; + u8 interrupts_masked; + struct napi_struct napi; struct ena_ring *tx_ring; struct ena_ring *rx_ring; struct ena_ring *xdp_ring; - bool first_interrupt; - bool interrupts_masked; u32 qid; struct dim dim; }; @@ -212,6 +206,7 @@ struct ena_stats_tx { u64 llq_buffer_copy; u64 missed_tx; u64 unmask_interrupt; + u64 last_napi_jiffies; }; struct ena_stats_rx { @@ -259,6 +254,10 @@ struct ena_ring { struct bpf_prog *xdp_bpf_prog; struct xdp_rxq_info xdp_rxq; spinlock_t xdp_tx_lock; /* synchronize XDP TX/Redirect traffic */ + /* Used for rx queues only to point to the xdp tx ring, to + * which traffic should be redirected from this rx ring. + */ + struct ena_ring *xdp_ring; u16 next_to_use; u16 next_to_clean; @@ -271,7 +270,6 @@ struct ena_ring { /* The maximum header length the device can handle */ u8 tx_max_header_size; - bool first_interrupt; bool disable_meta_caching; u16 no_interrupt_event_cnt; @@ -414,11 +412,6 @@ enum ena_xdp_errors_t { ENA_XDP_NO_ENOUGH_QUEUES, }; -static inline bool ena_xdp_queues_present(struct ena_adapter *adapter) -{ - return adapter->xdp_first_ring != 0; -} - static inline bool ena_xdp_present(struct ena_adapter *adapter) { return !!adapter->xdp_bpf_prog; diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index 4a1220cc6f10..9cac5aa75a73 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -19,14 +19,14 @@ Module Name: Abstract: - AMD8111 based 10/100 Ethernet Controller Driver. + AMD8111 based 10/100 Ethernet Controller Driver. Environment: Kernel Mode Revision History: - 3.0.0 + 3.0.0 Initial Revision. 3.0.1 1. Dynamic interrupt coalescing. diff --git a/drivers/net/ethernet/amd/amd8111e.h b/drivers/net/ethernet/amd/amd8111e.h index 493f154eccf4..37da79da5f5e 100644 --- a/drivers/net/ethernet/amd/amd8111e.h +++ b/drivers/net/ethernet/amd/amd8111e.h @@ -10,14 +10,14 @@ Module Name: Abstract: - AMD8111 based 10/100 Ethernet Controller driver definitions. + AMD8111 based 10/100 Ethernet Controller driver definitions. Environment: Kernel Mode Revision History: - 3.0.0 + 3.0.0 Initial Revision. 3.0.1 */ @@ -692,7 +692,7 @@ enum coal_type{ }; enum coal_mode{ - RX_INTR_COAL, + RX_INTR_COAL, TX_INTR_COAL, DISABLE_COAL, ENABLE_COAL, diff --git a/drivers/net/ethernet/amd/atarilance.c b/drivers/net/ethernet/amd/atarilance.c index c1eab916438f..36f54d13a2eb 100644 --- a/drivers/net/ethernet/amd/atarilance.c +++ b/drivers/net/ethernet/amd/atarilance.c @@ -706,7 +706,7 @@ static void lance_init_ring( struct net_device *dev ) CHECK_OFFSET(offset); MEM->tx_head[i].base = offset; MEM->tx_head[i].flag = TMD1_OWN_HOST; - MEM->tx_head[i].base_hi = 0; + MEM->tx_head[i].base_hi = 0; MEM->tx_head[i].length = 0; MEM->tx_head[i].misc = 0; offset += PKT_BUF_SZ; diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c index 7282ce55ffb8..493b0cefcc2a 100644 --- a/drivers/net/ethernet/amd/declance.c +++ b/drivers/net/ethernet/amd/declance.c @@ -937,7 +937,7 @@ static netdev_tx_t lance_start_xmit(struct sk_buff *skb, struct net_device *dev) dev_kfree_skb(skb); - return NETDEV_TX_OK; + return NETDEV_TX_OK; } static void lance_load_multicast(struct net_device *dev) diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c index aff44241988c..2178e6b89dbd 100644 --- a/drivers/net/ethernet/amd/lance.c +++ b/drivers/net/ethernet/amd/lance.c @@ -780,7 +780,7 @@ lance_open(struct net_device *dev) outw(0x0002, ioaddr+LANCE_ADDR); /* Only touch autoselect bit. */ outw(inw(ioaddr+LANCE_BUS_IF) | 0x0002, ioaddr+LANCE_BUS_IF); - } + } if (lance_debug > 1) printk("%s: lance_open() irq %d dma %d tx/rx rings %#x/%#x init %#x.\n", @@ -812,7 +812,7 @@ lance_open(struct net_device *dev) * We used to clear the InitDone bit, 0x0100, here but Mark Stockton * reports that doing so triggers a bug in the '974. */ - outw(0x0042, ioaddr+LANCE_DATA); + outw(0x0042, ioaddr+LANCE_DATA); if (lance_debug > 2) printk("%s: LANCE open after %d ticks, init block %#x csr0 %4.4x.\n", diff --git a/drivers/net/ethernet/amd/ni65.c b/drivers/net/ethernet/amd/ni65.c index c38edf6f03a3..5c1cfb0c4a42 100644 --- a/drivers/net/ethernet/amd/ni65.c +++ b/drivers/net/ethernet/amd/ni65.c @@ -193,7 +193,7 @@ static struct card { .vendor_id = ni_vendor, .cardname = "ni6510", .config = 0x1, - }, + }, { .id0 = NI65_EB_ID0, .id1 = NI65_EB_ID1, @@ -204,7 +204,7 @@ static struct card { .vendor_id = ni_vendor, .cardname = "ni6510 EtherBlaster", .config = 0x2, - }, + }, { .id0 = NE2100_ID0, .id1 = NE2100_ID1, @@ -1232,15 +1232,15 @@ MODULE_PARM_DESC(dma, "ni6510 ISA DMA channel (ignored for some cards)"); int __init init_module(void) { - dev_ni65 = ni65_probe(-1); + dev_ni65 = ni65_probe(-1); return PTR_ERR_OR_ZERO(dev_ni65); } void __exit cleanup_module(void) { - unregister_netdev(dev_ni65); - cleanup_card(dev_ni65); - free_netdev(dev_ni65); + unregister_netdev(dev_ni65); + cleanup_card(dev_ni65); + free_netdev(dev_ni65); } #endif /* MODULE */ diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c index 11c0b13edd30..4019cab87505 100644 --- a/drivers/net/ethernet/amd/nmclan_cs.c +++ b/drivers/net/ethernet/amd/nmclan_cs.c @@ -541,7 +541,7 @@ static int mace_init(mace_private *lp, unsigned int ioaddr, char *enet_addr) if(++ct > 500) { pr_err("reset failed, card removed?\n"); - return -1; + return -1; } udelay(1); } @@ -585,11 +585,11 @@ static int mace_init(mace_private *lp, unsigned int ioaddr, char *enet_addr) ct = 0; while (mace_read(lp, ioaddr, MACE_IAC) & MACE_IAC_ADDRCHG) { - if(++ ct > 500) - { + if(++ ct > 500) + { pr_err("ADDRCHG timeout, card removed?\n"); - return -1; - } + return -1; + } } /* Set PADR register */ for (i = 0; i < ETH_ALEN; i++) @@ -655,7 +655,7 @@ static int nmclan_config(struct pcmcia_device *link) } if(mace_init(lp, ioaddr, dev->dev_addr) == -1) - goto failed; + goto failed; /* The if_port symbol can be set when the module is loaded */ if (if_port <= 2) diff --git a/drivers/net/ethernet/amd/sun3lance.c b/drivers/net/ethernet/amd/sun3lance.c index 00ae1081254d..f8d7a9387a56 100644 --- a/drivers/net/ethernet/amd/sun3lance.c +++ b/drivers/net/ethernet/amd/sun3lance.c @@ -150,7 +150,7 @@ struct lance_memory { struct lance_private { volatile unsigned short *iobase; struct lance_memory *mem; - int new_rx, new_tx; /* The next free ring entry */ + int new_rx, new_tx; /* The next free ring entry */ int old_tx, old_rx; /* ring entry to be processed */ /* These two must be longs for set_bit() */ long tx_full; @@ -465,7 +465,7 @@ static void lance_init_ring( struct net_device *dev ) for( i = 0; i < TX_RING_SIZE; i++ ) { MEM->tx_head[i].base = dvma_vtob(MEM->tx_data[i]); MEM->tx_head[i].flag = 0; - MEM->tx_head[i].base_hi = + MEM->tx_head[i].base_hi = (dvma_vtob(MEM->tx_data[i])) >>16; MEM->tx_head[i].length = 0; MEM->tx_head[i].misc = 0; @@ -581,8 +581,8 @@ lance_start_xmit(struct sk_buff *skb, struct net_device *dev) } AREG = CSR0; - DPRINTK( 2, ( "%s: lance_start_xmit() called, csr0 %4.4x.\n", - dev->name, DREG )); + DPRINTK( 2, ( "%s: lance_start_xmit() called, csr0 %4.4x.\n", + dev->name, DREG )); #ifdef CONFIG_SUN3X /* this weirdness doesn't appear on sun3... */ @@ -636,8 +636,8 @@ lance_start_xmit(struct sk_buff *skb, struct net_device *dev) /* Trigger an immediate send poll. */ REGA(CSR0) = CSR0_INEA | CSR0_TDMD | CSR0_STRT; AREG = CSR0; - DPRINTK( 2, ( "%s: lance_start_xmit() exiting, csr0 %4.4x.\n", - dev->name, DREG )); + DPRINTK( 2, ( "%s: lance_start_xmit() exiting, csr0 %4.4x.\n", + dev->name, DREG )); dev_kfree_skb(skb); lp->lock = 0; diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index 1e4e402f07d7..a989d2df59ad 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -477,26 +477,26 @@ static int bmac_suspend(struct macio_dev *mdev, pm_message_t state) config = bmread(dev, RXCFG); bmwrite(dev, RXCFG, (config & ~RxMACEnable)); config = bmread(dev, TXCFG); - bmwrite(dev, TXCFG, (config & ~TxMACEnable)); + bmwrite(dev, TXCFG, (config & ~TxMACEnable)); bmwrite(dev, INTDISABLE, DisableAll); /* disable all intrs */ - /* disable rx and tx dma */ + /* disable rx and tx dma */ rd->control = cpu_to_le32(DBDMA_CLEAR(RUN|PAUSE|FLUSH|WAKE)); /* clear run bit */ td->control = cpu_to_le32(DBDMA_CLEAR(RUN|PAUSE|FLUSH|WAKE)); /* clear run bit */ - /* free some skb's */ - for (i=0; irx_bufs[i] != NULL) { - dev_kfree_skb(bp->rx_bufs[i]); - bp->rx_bufs[i] = NULL; - } - } - for (i = 0; irx_bufs[i] != NULL) { + dev_kfree_skb(bp->rx_bufs[i]); + bp->rx_bufs[i] = NULL; + } + } + for (i = 0; itx_bufs[i] != NULL) { dev_kfree_skb(bp->tx_bufs[i]); bp->tx_bufs[i] = NULL; } } } - pmac_call_feature(PMAC_FTR_BMAC_ENABLE, macio_get_of_node(bp->mdev), 0, 0); + pmac_call_feature(PMAC_FTR_BMAC_ENABLE, macio_get_of_node(bp->mdev), 0, 0); return 0; } @@ -510,9 +510,9 @@ static int bmac_resume(struct macio_dev *mdev) bmac_reset_and_enable(dev); enable_irq(dev->irq); - enable_irq(bp->tx_dma_intr); - enable_irq(bp->rx_dma_intr); - netif_device_attach(dev); + enable_irq(bp->tx_dma_intr); + enable_irq(bp->rx_dma_intr); + netif_device_attach(dev); return 0; } @@ -1599,7 +1599,7 @@ static int bmac_remove(struct macio_dev *mdev) unregister_netdev(dev); - free_irq(dev->irq, dev); + free_irq(dev->irq, dev); free_irq(bp->tx_dma_intr, dev); free_irq(bp->rx_dma_intr, dev); diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c index 9e5006e59215..4b80e3a52a19 100644 --- a/drivers/net/ethernet/apple/mace.c +++ b/drivers/net/ethernet/apple/mace.c @@ -364,9 +364,9 @@ static void mace_reset(struct net_device *dev) out_8(&mb->iac, 0); if (mp->port_aaui) - out_8(&mb->plscc, PORTSEL_AUI + ENPLSIO); + out_8(&mb->plscc, PORTSEL_AUI + ENPLSIO); else - out_8(&mb->plscc, PORTSEL_GPSI + ENPLSIO); + out_8(&mb->plscc, PORTSEL_GPSI + ENPLSIO); } static void __mace_set_address(struct net_device *dev, void *addr) @@ -378,9 +378,9 @@ static void __mace_set_address(struct net_device *dev, void *addr) /* load up the hardware address */ if (mp->chipid == BROKEN_ADDRCHG_REV) - out_8(&mb->iac, PHYADDR); + out_8(&mb->iac, PHYADDR); else { - out_8(&mb->iac, ADDRCHG | PHYADDR); + out_8(&mb->iac, ADDRCHG | PHYADDR); while ((in_8(&mb->iac) & ADDRCHG) != 0) ; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.h b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.h index f5fba8b8cdea..a47e2710487e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.h @@ -91,7 +91,7 @@ struct aq_macsec_txsc { u32 hw_sc_idx; unsigned long tx_sa_idx_busy; const struct macsec_secy *sw_secy; - u8 tx_sa_key[MACSEC_NUM_AN][MACSEC_KEYID_LEN]; + u8 tx_sa_key[MACSEC_NUM_AN][MACSEC_MAX_KEY_LEN]; struct aq_macsec_tx_sc_stats stats; struct aq_macsec_tx_sa_stats tx_sa_stats[MACSEC_NUM_AN]; }; @@ -101,7 +101,7 @@ struct aq_macsec_rxsc { unsigned long rx_sa_idx_busy; const struct macsec_secy *sw_secy; const struct macsec_rx_sc *sw_rxsc; - u8 rx_sa_key[MACSEC_NUM_AN][MACSEC_KEYID_LEN]; + u8 rx_sa_key[MACSEC_NUM_AN][MACSEC_MAX_KEY_LEN]; struct aq_macsec_rx_sa_stats rx_sa_stats[MACSEC_NUM_AN]; }; diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c index 48ecdf15eddc..1c9ca3bcb871 100644 --- a/drivers/net/ethernet/arc/emac_rockchip.c +++ b/drivers/net/ethernet/arc/emac_rockchip.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/** +/* * emac-rockchip.c - Rockchip EMAC specific glue layer * * Copyright (C) 2014 Romain Perier diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h index 9d0e74f6b089..693006c5a498 100644 --- a/drivers/net/ethernet/atheros/alx/alx.h +++ b/drivers/net/ethernet/atheros/alx/alx.h @@ -137,6 +137,8 @@ struct alx_priv { /* protects hw.stats */ spinlock_t stats_lock; + + struct mutex mtx; }; extern const struct ethtool_ops alx_ethtool_ops; diff --git a/drivers/net/ethernet/atheros/alx/ethtool.c b/drivers/net/ethernet/atheros/alx/ethtool.c index 2f4eabf652e8..b716adacd815 100644 --- a/drivers/net/ethernet/atheros/alx/ethtool.c +++ b/drivers/net/ethernet/atheros/alx/ethtool.c @@ -163,8 +163,10 @@ static int alx_get_link_ksettings(struct net_device *netdev, } } + mutex_lock(&alx->mtx); cmd->base.speed = hw->link_speed; cmd->base.duplex = hw->duplex; + mutex_unlock(&alx->mtx); ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, supported); @@ -181,8 +183,7 @@ static int alx_set_link_ksettings(struct net_device *netdev, struct alx_hw *hw = &alx->hw; u32 adv_cfg; u32 advertising; - - ASSERT_RTNL(); + int ret; ethtool_convert_link_mode_to_legacy_u32(&advertising, cmd->link_modes.advertising); @@ -200,7 +201,12 @@ static int alx_set_link_ksettings(struct net_device *netdev, } hw->adv_cfg = adv_cfg; - return alx_setup_speed_duplex(hw, adv_cfg, hw->flowctrl); + + mutex_lock(&alx->mtx); + ret = alx_setup_speed_duplex(hw, adv_cfg, hw->flowctrl); + mutex_unlock(&alx->mtx); + + return ret; } static void alx_get_pauseparam(struct net_device *netdev, @@ -209,10 +215,12 @@ static void alx_get_pauseparam(struct net_device *netdev, struct alx_priv *alx = netdev_priv(netdev); struct alx_hw *hw = &alx->hw; + mutex_lock(&alx->mtx); pause->autoneg = !!(hw->flowctrl & ALX_FC_ANEG && hw->adv_cfg & ADVERTISED_Autoneg); pause->tx_pause = !!(hw->flowctrl & ALX_FC_TX); pause->rx_pause = !!(hw->flowctrl & ALX_FC_RX); + mutex_unlock(&alx->mtx); } @@ -232,7 +240,7 @@ static int alx_set_pauseparam(struct net_device *netdev, if (pause->autoneg) fc |= ALX_FC_ANEG; - ASSERT_RTNL(); + mutex_lock(&alx->mtx); /* restart auto-neg for auto-mode */ if (hw->adv_cfg & ADVERTISED_Autoneg) { @@ -245,8 +253,10 @@ static int alx_set_pauseparam(struct net_device *netdev, if (reconfig_phy) { err = alx_setup_speed_duplex(hw, hw->adv_cfg, fc); - if (err) + if (err) { + mutex_unlock(&alx->mtx); return err; + } } /* flow control on mac */ @@ -254,6 +264,7 @@ static int alx_set_pauseparam(struct net_device *netdev, alx_cfg_mac_flowcontrol(hw, fc); hw->flowctrl = fc; + mutex_unlock(&alx->mtx); return 0; } diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 7748b276e5fd..11ef1fbe7aee 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2013 Johannes Berg + * Copyright (c) 2013, 2021 Johannes Berg * * This file is free software: you may copy, redistribute and/or modify it * under the terms of the GNU General Public License as published by the @@ -1091,8 +1091,9 @@ static int alx_init_sw(struct alx_priv *alx) ALX_MAC_CTRL_RXFC_EN | ALX_MAC_CTRL_TXFC_EN | 7 << ALX_MAC_CTRL_PRMBLEN_SHIFT; + mutex_init(&alx->mtx); - return err; + return 0; } @@ -1122,6 +1123,8 @@ static void alx_halt(struct alx_priv *alx) { struct alx_hw *hw = &alx->hw; + lockdep_assert_held(&alx->mtx); + alx_netif_stop(alx); hw->link_speed = SPEED_UNKNOWN; hw->duplex = DUPLEX_UNKNOWN; @@ -1147,6 +1150,8 @@ static void alx_configure(struct alx_priv *alx) static void alx_activate(struct alx_priv *alx) { + lockdep_assert_held(&alx->mtx); + /* hardware setting lost, restore it */ alx_reinit_rings(alx); alx_configure(alx); @@ -1161,7 +1166,7 @@ static void alx_activate(struct alx_priv *alx) static void alx_reinit(struct alx_priv *alx) { - ASSERT_RTNL(); + lockdep_assert_held(&alx->mtx); alx_halt(alx); alx_activate(alx); @@ -1249,6 +1254,8 @@ out_disable_adv_intr: static void __alx_stop(struct alx_priv *alx) { + lockdep_assert_held(&alx->mtx); + alx_free_irq(alx); cancel_work_sync(&alx->link_check_wk); @@ -1284,6 +1291,8 @@ static void alx_check_link(struct alx_priv *alx) int old_speed; int err; + lockdep_assert_held(&alx->mtx); + /* clear PHY internal interrupt status, otherwise the main * interrupt status will be asserted forever */ @@ -1338,12 +1347,24 @@ reset: static int alx_open(struct net_device *netdev) { - return __alx_open(netdev_priv(netdev), false); + struct alx_priv *alx = netdev_priv(netdev); + int ret; + + mutex_lock(&alx->mtx); + ret = __alx_open(alx, false); + mutex_unlock(&alx->mtx); + + return ret; } static int alx_stop(struct net_device *netdev) { - __alx_stop(netdev_priv(netdev)); + struct alx_priv *alx = netdev_priv(netdev); + + mutex_lock(&alx->mtx); + __alx_stop(alx); + mutex_unlock(&alx->mtx); + return 0; } @@ -1353,18 +1374,18 @@ static void alx_link_check(struct work_struct *work) alx = container_of(work, struct alx_priv, link_check_wk); - rtnl_lock(); + mutex_lock(&alx->mtx); alx_check_link(alx); - rtnl_unlock(); + mutex_unlock(&alx->mtx); } static void alx_reset(struct work_struct *work) { struct alx_priv *alx = container_of(work, struct alx_priv, reset_wk); - rtnl_lock(); + mutex_lock(&alx->mtx); alx_reinit(alx); - rtnl_unlock(); + mutex_unlock(&alx->mtx); } static int alx_tpd_req(struct sk_buff *skb) @@ -1771,6 +1792,8 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto out_unmap; } + mutex_lock(&alx->mtx); + alx_reset_pcie(hw); phy_configured = alx_phy_configured(hw); @@ -1781,7 +1804,7 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = alx_reset_mac(hw); if (err) { dev_err(&pdev->dev, "MAC Reset failed, error = %d\n", err); - goto out_unmap; + goto out_unlock; } /* setup link to put it in a known good starting state */ @@ -1791,7 +1814,7 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_err(&pdev->dev, "failed to configure PHY speed/duplex (err=%d)\n", err); - goto out_unmap; + goto out_unlock; } } @@ -1824,9 +1847,11 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!alx_get_phy_info(hw)) { dev_err(&pdev->dev, "failed to identify PHY\n"); err = -EIO; - goto out_unmap; + goto out_unlock; } + mutex_unlock(&alx->mtx); + INIT_WORK(&alx->link_check_wk, alx_link_check); INIT_WORK(&alx->reset_wk, alx_reset); netif_carrier_off(netdev); @@ -1843,6 +1868,8 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; +out_unlock: + mutex_unlock(&alx->mtx); out_unmap: iounmap(hw->hw_addr); out_free_netdev: @@ -1870,6 +1897,8 @@ static void alx_remove(struct pci_dev *pdev) pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); + mutex_destroy(&alx->mtx); + free_netdev(alx->dev); } @@ -1881,7 +1910,11 @@ static int alx_suspend(struct device *dev) if (!netif_running(alx->dev)) return 0; netif_device_detach(alx->dev); + + mutex_lock(&alx->mtx); __alx_stop(alx); + mutex_unlock(&alx->mtx); + return 0; } @@ -1891,20 +1924,23 @@ static int alx_resume(struct device *dev) struct alx_hw *hw = &alx->hw; int err; + mutex_lock(&alx->mtx); alx_reset_phy(hw); - if (!netif_running(alx->dev)) - return 0; + if (!netif_running(alx->dev)) { + err = 0; + goto unlock; + } - rtnl_lock(); err = __alx_open(alx, true); - rtnl_unlock(); if (err) - return err; + goto unlock; netif_device_attach(alx->dev); - return 0; +unlock: + mutex_unlock(&alx->mtx); + return err; } static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume); @@ -1923,7 +1959,7 @@ static pci_ers_result_t alx_pci_error_detected(struct pci_dev *pdev, dev_info(&pdev->dev, "pci error detected\n"); - rtnl_lock(); + mutex_lock(&alx->mtx); if (netif_running(netdev)) { netif_device_detach(netdev); @@ -1935,7 +1971,7 @@ static pci_ers_result_t alx_pci_error_detected(struct pci_dev *pdev, else pci_disable_device(pdev); - rtnl_unlock(); + mutex_unlock(&alx->mtx); return rc; } @@ -1948,7 +1984,7 @@ static pci_ers_result_t alx_pci_error_slot_reset(struct pci_dev *pdev) dev_info(&pdev->dev, "pci error slot reset\n"); - rtnl_lock(); + mutex_lock(&alx->mtx); if (pci_enable_device(pdev)) { dev_err(&pdev->dev, "Failed to re-enable PCI device after reset\n"); @@ -1961,7 +1997,7 @@ static pci_ers_result_t alx_pci_error_slot_reset(struct pci_dev *pdev) if (!alx_reset_mac(hw)) rc = PCI_ERS_RESULT_RECOVERED; out: - rtnl_unlock(); + mutex_unlock(&alx->mtx); return rc; } @@ -1973,14 +2009,14 @@ static void alx_pci_error_resume(struct pci_dev *pdev) dev_info(&pdev->dev, "pci error resume\n"); - rtnl_lock(); + mutex_lock(&alx->mtx); if (netif_running(netdev)) { alx_activate(alx); netif_device_attach(netdev); } - rtnl_unlock(); + mutex_unlock(&alx->mtx); } static const struct pci_error_handlers alx_err_handlers = { diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c.h b/drivers/net/ethernet/atheros/atl1c/atl1c.h index 28ae5c16831e..43d821fe7a54 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c.h +++ b/drivers/net/ethernet/atheros/atl1c/atl1c.h @@ -63,7 +63,7 @@ #define AT_MAX_RECEIVE_QUEUE 4 #define AT_DEF_RECEIVE_QUEUE 1 -#define AT_MAX_TRANSMIT_QUEUE 2 +#define AT_MAX_TRANSMIT_QUEUE 4 #define AT_DMA_HI_ADDR_MASK 0xffffffff00000000ULL #define AT_DMA_LO_ADDR_MASK 0x00000000ffffffffULL @@ -241,6 +241,8 @@ struct atl1c_tpd_ext_desc { #define RRS_PACKET_PROT_IS_IPV6_ONLY(word) \ ((((word) >> RRS_PROT_ID_SHIFT) & RRS_PROT_ID_MASK) == 6) +#define RRS_MT_PROT_ID_TCPUDP BIT(19) + struct atl1c_recv_ret_status { __le32 word0; __le32 rss_hash; @@ -289,11 +291,7 @@ enum atl1c_nic_type { athr_l2c_b2, athr_l1d, athr_l1d_2, -}; - -enum atl1c_trans_queue { - atl1c_trans_normal = 0, - atl1c_trans_high = 1 + athr_mt, }; struct atl1c_hw_stats { @@ -472,13 +470,16 @@ struct atl1c_buffer { /* transimit packet descriptor (tpd) ring */ struct atl1c_tpd_ring { + struct atl1c_adapter *adapter; void *desc; /* descriptor ring virtual address */ dma_addr_t dma; /* descriptor ring physical address */ + u16 num; u16 size; /* descriptor ring length in bytes */ u16 count; /* number of descriptors in the ring */ u16 next_to_use; atomic_t next_to_clean; struct atl1c_buffer *buffer_info; + struct napi_struct napi; }; /* receive free descriptor (rfd) ring */ @@ -494,27 +495,30 @@ struct atl1c_rfd_ring { /* receive return descriptor (rrd) ring */ struct atl1c_rrd_ring { + struct atl1c_adapter *adapter; void *desc; /* descriptor ring virtual address */ dma_addr_t dma; /* descriptor ring physical address */ + u16 num; u16 size; /* descriptor ring length in bytes */ u16 count; /* number of descriptors in the ring */ u16 next_to_use; u16 next_to_clean; + struct napi_struct napi; + struct page *rx_page; + unsigned int rx_page_offset; }; /* board specific private data structure */ struct atl1c_adapter { struct net_device *netdev; struct pci_dev *pdev; - struct napi_struct napi; - struct napi_struct tx_napi; - struct page *rx_page; - unsigned int rx_page_offset; unsigned int rx_frag_size; struct atl1c_hw hw; struct atl1c_hw_stats hw_stats; struct mii_if_info mii; /* MII interface info */ u16 rx_buffer_len; + unsigned int tx_queue_count; + unsigned int rx_queue_count; unsigned long flags; #define __AT_TESTING 0x0001 @@ -540,8 +544,8 @@ struct atl1c_adapter { /* All Descriptor memory */ struct atl1c_ring_header ring_header; struct atl1c_tpd_ring tpd_ring[AT_MAX_TRANSMIT_QUEUE]; - struct atl1c_rfd_ring rfd_ring; - struct atl1c_rrd_ring rrd_ring; + struct atl1c_rfd_ring rfd_ring[AT_MAX_RECEIVE_QUEUE]; + struct atl1c_rrd_ring rrd_ring[AT_MAX_RECEIVE_QUEUE]; u32 bd_number; /* board number;*/ }; diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c index 140358dcf61e..7dff20350865 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.c @@ -636,6 +636,23 @@ int atl1c_phy_init(struct atl1c_hw *hw) return 0; } +bool atl1c_get_link_status(struct atl1c_hw *hw) +{ + u16 phy_data; + + if (hw->nic_type == athr_mt) { + u32 spd; + + AT_READ_REG(hw, REG_MT_SPEED, &spd); + return !!spd; + } + + /* MII_BMSR must be read twice */ + atl1c_read_phy_reg(hw, MII_BMSR, &phy_data); + atl1c_read_phy_reg(hw, MII_BMSR, &phy_data); + return !!(phy_data & BMSR_LSTATUS); +} + /* * Detects the current speed and duplex settings of the hardware. * @@ -648,6 +665,15 @@ int atl1c_get_speed_and_duplex(struct atl1c_hw *hw, u16 *speed, u16 *duplex) int err; u16 phy_data; + if (hw->nic_type == athr_mt) { + u32 spd; + + AT_READ_REG(hw, REG_MT_SPEED, &spd); + *speed = spd; + *duplex = FULL_DUPLEX; + return 0; + } + /* Read PHY Specific Status Register (17) */ err = atl1c_read_phy_reg(hw, MII_GIGA_PSSR, &phy_data); if (err) @@ -686,15 +712,12 @@ int atl1c_phy_to_ps_link(struct atl1c_hw *hw) int ret = 0; u16 autoneg_advertised = ADVERTISED_10baseT_Half; u16 save_autoneg_advertised; - u16 phy_data; u16 mii_lpa_data; u16 speed = SPEED_0; u16 duplex = FULL_DUPLEX; int i; - atl1c_read_phy_reg(hw, MII_BMSR, &phy_data); - atl1c_read_phy_reg(hw, MII_BMSR, &phy_data); - if (phy_data & BMSR_LSTATUS) { + if (atl1c_get_link_status(hw)) { atl1c_read_phy_reg(hw, MII_LPA, &mii_lpa_data); if (mii_lpa_data & LPA_10FULL) autoneg_advertised = ADVERTISED_10baseT_Full; @@ -717,9 +740,7 @@ int atl1c_phy_to_ps_link(struct atl1c_hw *hw) if (mii_lpa_data) { for (i = 0; i < AT_SUSPEND_LINK_TIMEOUT; i++) { mdelay(100); - atl1c_read_phy_reg(hw, MII_BMSR, &phy_data); - atl1c_read_phy_reg(hw, MII_BMSR, &phy_data); - if (phy_data & BMSR_LSTATUS) { + if (atl1c_get_link_status(hw)) { if (atl1c_get_speed_and_duplex(hw, &speed, &duplex) != 0) dev_dbg(&pdev->dev, diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h index ce1a123dce2c..c567c920628f 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_hw.h @@ -26,6 +26,7 @@ void atl1c_phy_disable(struct atl1c_hw *hw); void atl1c_hw_set_mac_addr(struct atl1c_hw *hw, u8 *mac_addr); int atl1c_phy_reset(struct atl1c_hw *hw); int atl1c_read_mac_addr(struct atl1c_hw *hw); +bool atl1c_get_link_status(struct atl1c_hw *hw); int atl1c_get_speed_and_duplex(struct atl1c_hw *hw, u16 *speed, u16 *duplex); u32 atl1c_hash_mc_addr(struct atl1c_hw *hw, u8 *mc_addr); void atl1c_hash_set(struct atl1c_hw *hw, u32 hash_value); @@ -527,15 +528,24 @@ void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed); #define REG_RX_BASE_ADDR_HI 0x1540 #define REG_TX_BASE_ADDR_HI 0x1544 #define REG_RFD0_HEAD_ADDR_LO 0x1550 +#define REG_RFD1_HEAD_ADDR_LO 0x1554 +#define REG_RFD2_HEAD_ADDR_LO 0x1558 +#define REG_RFD3_HEAD_ADDR_LO 0x155C #define REG_RFD_RING_SIZE 0x1560 #define RFD_RING_SIZE_MASK 0x0FFF #define REG_RX_BUF_SIZE 0x1564 #define RX_BUF_SIZE_MASK 0xFFFF #define REG_RRD0_HEAD_ADDR_LO 0x1568 +#define REG_RRD1_HEAD_ADDR_LO 0x156C +#define REG_RRD2_HEAD_ADDR_LO 0x1570 +#define REG_RRD3_HEAD_ADDR_LO 0x1574 #define REG_RRD_RING_SIZE 0x1578 #define RRD_RING_SIZE_MASK 0x0FFF #define REG_TPD_PRI1_ADDR_LO 0x157C #define REG_TPD_PRI0_ADDR_LO 0x1580 +#define REG_TPD_PRI2_ADDR_LO 0x1F10 +#define REG_TPD_PRI3_ADDR_LO 0x1F14 + #define REG_TPD_RING_SIZE 0x1584 #define TPD_RING_SIZE_MASK 0xFFFF @@ -654,15 +664,26 @@ void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed); /* Mail box */ #define MB_RFDX_PROD_IDX_MASK 0xFFFF #define REG_MB_RFD0_PROD_IDX 0x15E0 +#define REG_MB_RFD1_PROD_IDX 0x15E4 +#define REG_MB_RFD2_PROD_IDX 0x15E8 +#define REG_MB_RFD3_PROD_IDX 0x15EC #define REG_TPD_PRI1_PIDX 0x15F0 /* 16bit,hi-tpd producer idx */ #define REG_TPD_PRI0_PIDX 0x15F2 /* 16bit,lo-tpd producer idx */ #define REG_TPD_PRI1_CIDX 0x15F4 /* 16bit,hi-tpd consumer idx */ #define REG_TPD_PRI0_CIDX 0x15F6 /* 16bit,lo-tpd consumer idx */ +#define REG_TPD_PRI3_PIDX 0x1F18 +#define REG_TPD_PRI2_PIDX 0x1F1A +#define REG_TPD_PRI3_CIDX 0x1F1C +#define REG_TPD_PRI2_CIDX 0x1F1E + #define REG_MB_RFD01_CONS_IDX 0x15F8 #define MB_RFD0_CONS_IDX_MASK 0x0000FFFF #define MB_RFD1_CONS_IDX_MASK 0xFFFF0000 +#define REG_MB_RFD23_CONS_IDX 0x15FC +#define MB_RFD2_CONS_IDX_MASK 0x0000FFFF +#define MB_RFD3_CONS_IDX_MASK 0xFFFF0000 /* Interrupt Status Register */ #define REG_ISR 0x1600 @@ -686,7 +707,7 @@ void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed); /* GPHY low power state interrupt */ #define ISR_GPHY_LPW 0x00002000 #define ISR_TXQ_TO_RST 0x00004000 -#define ISR_TX_PKT 0x00008000 +#define ISR_TX_PKT_0 0x00008000 #define ISR_RX_PKT_0 0x00010000 #define ISR_RX_PKT_1 0x00020000 #define ISR_RX_PKT_2 0x00040000 @@ -698,6 +719,9 @@ void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed); #define ISR_NFERR_DETECTED 0x01000000 #define ISR_CERR_DETECTED 0x02000000 #define ISR_PHY_LINKDOWN 0x04000000 +#define ISR_TX_PKT_1 0x10000000 +#define ISR_TX_PKT_2 0x20000000 +#define ISR_TX_PKT_3 0x40000000 #define ISR_DIS_INT 0x80000000 /* Interrupt Mask Register */ @@ -712,11 +736,15 @@ void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed); ISR_TXQ_TO_RST |\ ISR_DMAW_TO_RST |\ ISR_GPHY |\ - ISR_TX_PKT |\ - ISR_RX_PKT_0 |\ ISR_GPHY_LPW |\ ISR_PHY_LINKDOWN) +#define ISR_TX_PKT ( \ + ISR_TX_PKT_0 | \ + ISR_TX_PKT_1 | \ + ISR_TX_PKT_2 | \ + ISR_TX_PKT_3) + #define ISR_RX_PKT (\ ISR_RX_PKT_0 |\ ISR_RX_PKT_1 |\ @@ -764,6 +792,14 @@ void atl1c_post_phy_linkchg(struct atl1c_hw *hw, u16 link_speed); #define REG_DEBUG_DATA0 0x1900 #define REG_DEBUG_DATA1 0x1904 +#define REG_MT_MAGIC 0x1F00 +#define REG_MT_MODE 0x1F04 +#define REG_MT_SPEED 0x1F08 +#define REG_MT_VERSION 0x1F0C + +#define MT_MAGIC 0xaabb1234 +#define MT_MODE_4Q BIT(0) + #define L1D_MPW_PHYID1 0xD01C /* V7 */ #define L1D_MPW_PHYID2 0xD01D /* V1-V6 */ #define L1D_MPW_PHYID3 0xD01E /* V8 */ diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index c6263cf8d3c0..1c6246a5dc22 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -36,18 +36,51 @@ MODULE_AUTHOR("Qualcomm Atheros Inc."); MODULE_DESCRIPTION("Qualcomm Atheros 100/1000M Ethernet Network Driver"); MODULE_LICENSE("GPL"); +struct atl1c_qregs { + u16 tpd_addr_lo; + u16 tpd_prod; + u16 tpd_cons; + u16 rfd_addr_lo; + u16 rrd_addr_lo; + u16 rfd_prod; + u32 tx_isr; + u32 rx_isr; +}; + +static struct atl1c_qregs atl1c_qregs[AT_MAX_TRANSMIT_QUEUE] = { + { + REG_TPD_PRI0_ADDR_LO, REG_TPD_PRI0_PIDX, REG_TPD_PRI0_CIDX, + REG_RFD0_HEAD_ADDR_LO, REG_RRD0_HEAD_ADDR_LO, + REG_MB_RFD0_PROD_IDX, ISR_TX_PKT_0, ISR_RX_PKT_0 + }, + { + REG_TPD_PRI1_ADDR_LO, REG_TPD_PRI1_PIDX, REG_TPD_PRI1_CIDX, + REG_RFD1_HEAD_ADDR_LO, REG_RRD1_HEAD_ADDR_LO, + REG_MB_RFD1_PROD_IDX, ISR_TX_PKT_1, ISR_RX_PKT_1 + }, + { + REG_TPD_PRI2_ADDR_LO, REG_TPD_PRI2_PIDX, REG_TPD_PRI2_CIDX, + REG_RFD2_HEAD_ADDR_LO, REG_RRD2_HEAD_ADDR_LO, + REG_MB_RFD2_PROD_IDX, ISR_TX_PKT_2, ISR_RX_PKT_2 + }, + { + REG_TPD_PRI3_ADDR_LO, REG_TPD_PRI3_PIDX, REG_TPD_PRI3_CIDX, + REG_RFD3_HEAD_ADDR_LO, REG_RRD3_HEAD_ADDR_LO, + REG_MB_RFD3_PROD_IDX, ISR_TX_PKT_3, ISR_RX_PKT_3 + }, +}; + static int atl1c_stop_mac(struct atl1c_hw *hw); static void atl1c_disable_l0s_l1(struct atl1c_hw *hw); static void atl1c_set_aspm(struct atl1c_hw *hw, u16 link_speed); static void atl1c_start_mac(struct atl1c_adapter *adapter); -static void atl1c_clean_rx_irq(struct atl1c_adapter *adapter, - int *work_done, int work_to_do); static int atl1c_up(struct atl1c_adapter *adapter); static void atl1c_down(struct atl1c_adapter *adapter); static int atl1c_reset_mac(struct atl1c_hw *hw); static void atl1c_reset_dma_ring(struct atl1c_adapter *adapter); static int atl1c_configure(struct atl1c_adapter *adapter); -static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, bool napi_mode); +static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, u32 queue, + bool napi_mode); static const u32 atl1c_default_msg = NETIF_MSG_DRV | NETIF_MSG_PROBE | @@ -232,15 +265,14 @@ static void atl1c_check_link_status(struct atl1c_adapter *adapter) struct pci_dev *pdev = adapter->pdev; int err; unsigned long flags; - u16 speed, duplex, phy_data; + u16 speed, duplex; + bool link; spin_lock_irqsave(&adapter->mdio_lock, flags); - /* MII_BMSR must read twise */ - atl1c_read_phy_reg(hw, MII_BMSR, &phy_data); - atl1c_read_phy_reg(hw, MII_BMSR, &phy_data); + link = atl1c_get_link_status(hw); spin_unlock_irqrestore(&adapter->mdio_lock, flags); - if ((phy_data & BMSR_LSTATUS) == 0) { + if (!link) { /* link down */ netif_carrier_off(netdev); hw->hibernate = true; @@ -284,16 +316,13 @@ static void atl1c_link_chg_event(struct atl1c_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; - u16 phy_data; - u16 link_up; + bool link; spin_lock(&adapter->mdio_lock); - atl1c_read_phy_reg(&adapter->hw, MII_BMSR, &phy_data); - atl1c_read_phy_reg(&adapter->hw, MII_BMSR, &phy_data); + link = atl1c_get_link_status(&adapter->hw); spin_unlock(&adapter->mdio_lock); - link_up = phy_data & BMSR_LSTATUS; /* notify upper layer link down ASAP */ - if (!link_up) { + if (!link) { if (netif_carrier_ok(netdev)) { /* old link state: Up */ netif_carrier_off(netdev); @@ -436,7 +465,7 @@ static void atl1c_restore_vlan(struct atl1c_adapter *adapter) } /** - * atl1c_set_mac - Change the Ethernet Address of the NIC + * atl1c_set_mac_addr - Change the Ethernet Address of the NIC * @netdev: network interface device structure * @p: pointer to an address structure * @@ -478,6 +507,9 @@ static void atl1c_set_rxbufsize(struct atl1c_adapter *adapter, static netdev_features_t atl1c_fix_features(struct net_device *netdev, netdev_features_t features) { + struct atl1c_adapter *adapter = netdev_priv(netdev); + struct atl1c_hw *hw = &adapter->hw; + /* * Since there is no support for separate rx/tx vlan accel * enable/disable make sure tx flag is always in same state as rx. @@ -487,8 +519,10 @@ static netdev_features_t atl1c_fix_features(struct net_device *netdev, else features &= ~NETIF_F_HW_VLAN_CTAG_TX; - if (netdev->mtu > MAX_TSO_FRAME_SIZE) - features &= ~(NETIF_F_TSO | NETIF_F_TSO6); + if (hw->nic_type != athr_mt) { + if (netdev->mtu > MAX_TSO_FRAME_SIZE) + features &= ~(NETIF_F_TSO | NETIF_F_TSO6); + } return features; } @@ -515,9 +549,12 @@ static void atl1c_set_max_mtu(struct net_device *netdev) case athr_l1d: case athr_l1d_2: netdev->max_mtu = MAX_JUMBO_FRAME_SIZE - - (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN); + (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN); break; - /* The 10/100 devices don't support jumbo packets, max_mtu 1500 */ + case athr_mt: + netdev->max_mtu = 9500; + break; + /* The 10/100 devices don't support jumbo packets, max_mtu 1500 */ default: netdev->max_mtu = ETH_DATA_LEN; break; @@ -642,29 +679,26 @@ static int atl1c_alloc_queues(struct atl1c_adapter *adapter) return 0; } -static void atl1c_set_mac_type(struct atl1c_hw *hw) +static enum atl1c_nic_type atl1c_get_mac_type(struct pci_dev *pdev, + u8 __iomem *hw_addr) { - switch (hw->device_id) { + switch (pdev->device) { case PCI_DEVICE_ID_ATTANSIC_L2C: - hw->nic_type = athr_l2c; - break; + return athr_l2c; case PCI_DEVICE_ID_ATTANSIC_L1C: - hw->nic_type = athr_l1c; - break; + return athr_l1c; case PCI_DEVICE_ID_ATHEROS_L2C_B: - hw->nic_type = athr_l2c_b; - break; + return athr_l2c_b; case PCI_DEVICE_ID_ATHEROS_L2C_B2: - hw->nic_type = athr_l2c_b2; - break; + return athr_l2c_b2; case PCI_DEVICE_ID_ATHEROS_L1D: - hw->nic_type = athr_l1d; - break; + return athr_l1d; case PCI_DEVICE_ID_ATHEROS_L1D_2_0: - hw->nic_type = athr_l1d_2; - break; + if (readl(hw_addr + REG_MT_MAGIC) == MT_MAGIC) + return athr_mt; + return athr_l1d_2; default: - break; + return athr_l1c; } } @@ -672,7 +706,6 @@ static int atl1c_setup_mac_funcs(struct atl1c_hw *hw) { u32 link_ctrl_data; - atl1c_set_mac_type(hw); AT_READ_REG(hw, REG_LINK_CTRL, &link_ctrl_data); hw->ctrl_flags = ATL1C_INTR_MODRT_ENABLE | @@ -763,14 +796,14 @@ static int atl1c_sw_init(struct atl1c_adapter *adapter) struct atl1c_hw *hw = &adapter->hw; struct pci_dev *pdev = adapter->pdev; u32 revision; - + int i; adapter->wol = 0; device_set_wakeup_enable(&pdev->dev, false); adapter->link_speed = SPEED_0; adapter->link_duplex = FULL_DUPLEX; adapter->tpd_ring[0].count = 1024; - adapter->rfd_ring.count = 512; + adapter->rfd_ring[0].count = 512; hw->vendor_id = pdev->vendor; hw->device_id = pdev->device; @@ -788,6 +821,10 @@ static int atl1c_sw_init(struct atl1c_adapter *adapter) atl1c_patch_assign(hw); hw->intr_mask = IMR_NORMAL_MASK; + for (i = 0; i < adapter->tx_queue_count; ++i) + hw->intr_mask |= atl1c_qregs[i].tx_isr; + for (i = 0; i < adapter->rx_queue_count; ++i) + hw->intr_mask |= atl1c_qregs[i].rx_isr; hw->phy_configured = false; hw->preamble_len = 7; hw->max_frame_size = adapter->netdev->mtu; @@ -847,12 +884,12 @@ static inline void atl1c_clean_buffer(struct pci_dev *pdev, /** * atl1c_clean_tx_ring - Free Tx-skb * @adapter: board private structure - * @type: type of transmit queue + * @queue: idx of transmit queue */ static void atl1c_clean_tx_ring(struct atl1c_adapter *adapter, - enum atl1c_trans_queue type) + u32 queue) { - struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[type]; + struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[queue]; struct atl1c_buffer *buffer_info; struct pci_dev *pdev = adapter->pdev; u16 index, ring_count; @@ -875,11 +912,12 @@ static void atl1c_clean_tx_ring(struct atl1c_adapter *adapter, /** * atl1c_clean_rx_ring - Free rx-reservation skbs * @adapter: board private structure + * @queue: idx of transmit queue */ -static void atl1c_clean_rx_ring(struct atl1c_adapter *adapter) +static void atl1c_clean_rx_ring(struct atl1c_adapter *adapter, u32 queue) { - struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring; - struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring; + struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring[queue]; + struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring[queue]; struct atl1c_buffer *buffer_info; struct pci_dev *pdev = adapter->pdev; int j; @@ -902,26 +940,28 @@ static void atl1c_clean_rx_ring(struct atl1c_adapter *adapter) static void atl1c_init_ring_ptrs(struct atl1c_adapter *adapter) { struct atl1c_tpd_ring *tpd_ring = adapter->tpd_ring; - struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring; - struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring; + struct atl1c_rfd_ring *rfd_ring = adapter->rfd_ring; + struct atl1c_rrd_ring *rrd_ring = adapter->rrd_ring; struct atl1c_buffer *buffer_info; int i, j; - for (i = 0; i < AT_MAX_TRANSMIT_QUEUE; i++) { + for (i = 0; i < adapter->tx_queue_count; i++) { tpd_ring[i].next_to_use = 0; atomic_set(&tpd_ring[i].next_to_clean, 0); buffer_info = tpd_ring[i].buffer_info; for (j = 0; j < tpd_ring->count; j++) ATL1C_SET_BUFFER_STATE(&buffer_info[i], - ATL1C_BUFFER_FREE); + ATL1C_BUFFER_FREE); } - rfd_ring->next_to_use = 0; - rfd_ring->next_to_clean = 0; - rrd_ring->next_to_use = 0; - rrd_ring->next_to_clean = 0; - for (j = 0; j < rfd_ring->count; j++) { - buffer_info = &rfd_ring->buffer_info[j]; - ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_FREE); + for (i = 0; i < adapter->rx_queue_count; i++) { + rfd_ring[i].next_to_use = 0; + rfd_ring[i].next_to_clean = 0; + rrd_ring[i].next_to_use = 0; + rrd_ring[i].next_to_clean = 0; + for (j = 0; j < rfd_ring[i].count; j++) { + buffer_info = &rfd_ring[i].buffer_info[j]; + ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_FREE); + } } } @@ -934,25 +974,29 @@ static void atl1c_init_ring_ptrs(struct atl1c_adapter *adapter) static void atl1c_free_ring_resources(struct atl1c_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; + int i; dma_free_coherent(&pdev->dev, adapter->ring_header.size, adapter->ring_header.desc, adapter->ring_header.dma); adapter->ring_header.desc = NULL; /* Note: just free tdp_ring.buffer_info, - * it contain rfd_ring.buffer_info, do not double free */ + * it contain rfd_ring.buffer_info, do not double free + */ if (adapter->tpd_ring[0].buffer_info) { kfree(adapter->tpd_ring[0].buffer_info); adapter->tpd_ring[0].buffer_info = NULL; } - if (adapter->rx_page) { - put_page(adapter->rx_page); - adapter->rx_page = NULL; + for (i = 0; i < adapter->rx_queue_count; ++i) { + if (adapter->rrd_ring[i].rx_page) { + put_page(adapter->rrd_ring[i].rx_page); + adapter->rrd_ring[i].rx_page = NULL; + } } } /** - * atl1c_setup_mem_resources - allocate Tx / RX descriptor resources + * atl1c_setup_ring_resources - allocate Tx / RX descriptor resources * @adapter: board private structure * * Return 0 on success, negative on failure @@ -961,37 +1005,46 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; struct atl1c_tpd_ring *tpd_ring = adapter->tpd_ring; - struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring; - struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring; + struct atl1c_rfd_ring *rfd_ring = adapter->rfd_ring; + struct atl1c_rrd_ring *rrd_ring = adapter->rrd_ring; struct atl1c_ring_header *ring_header = &adapter->ring_header; + int tqc = adapter->tx_queue_count; + int rqc = adapter->rx_queue_count; int size; int i; int count = 0; - int rx_desc_count = 0; u32 offset = 0; - rrd_ring->count = rfd_ring->count; - for (i = 1; i < AT_MAX_TRANSMIT_QUEUE; i++) + /* Even though only one tpd queue is actually used, the "high" + * priority tpd queue also gets initialized + */ + if (tqc == 1) + tqc = 2; + + for (i = 1; i < tqc; i++) tpd_ring[i].count = tpd_ring[0].count; - /* 2 tpd queue, one high priority queue, - * another normal priority queue */ - size = sizeof(struct atl1c_buffer) * (tpd_ring->count * 2 + - rfd_ring->count); + size = sizeof(struct atl1c_buffer) * (tpd_ring->count * tqc + + rfd_ring->count * rqc); tpd_ring->buffer_info = kzalloc(size, GFP_KERNEL); if (unlikely(!tpd_ring->buffer_info)) goto err_nomem; - for (i = 0; i < AT_MAX_TRANSMIT_QUEUE; i++) { - tpd_ring[i].buffer_info = - (tpd_ring->buffer_info + count); + for (i = 0; i < tqc; i++) { + tpd_ring[i].adapter = adapter; + tpd_ring[i].num = i; + tpd_ring[i].buffer_info = (tpd_ring->buffer_info + count); count += tpd_ring[i].count; } - rfd_ring->buffer_info = - (tpd_ring->buffer_info + count); - count += rfd_ring->count; - rx_desc_count += rfd_ring->count; + for (i = 0; i < rqc; i++) { + rrd_ring[i].adapter = adapter; + rrd_ring[i].num = i; + rrd_ring[i].count = rfd_ring[0].count; + rfd_ring[i].count = rfd_ring[0].count; + rfd_ring[i].buffer_info = (tpd_ring->buffer_info + count); + count += rfd_ring->count; + } /* * real ring DMA buffer @@ -999,9 +1052,9 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter) * additional bytes tacked onto the end. */ ring_header->size = size = - sizeof(struct atl1c_tpd_desc) * tpd_ring->count * 2 + - sizeof(struct atl1c_rx_free_desc) * rx_desc_count + - sizeof(struct atl1c_recv_ret_status) * rx_desc_count + + sizeof(struct atl1c_tpd_desc) * tpd_ring->count * tqc + + sizeof(struct atl1c_rx_free_desc) * rfd_ring->count * rqc + + sizeof(struct atl1c_recv_ret_status) * rfd_ring->count * rqc + 8 * 4; ring_header->desc = dma_alloc_coherent(&pdev->dev, ring_header->size, @@ -1014,25 +1067,28 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter) tpd_ring[0].dma = roundup(ring_header->dma, 8); offset = tpd_ring[0].dma - ring_header->dma; - for (i = 0; i < AT_MAX_TRANSMIT_QUEUE; i++) { + for (i = 0; i < tqc; i++) { tpd_ring[i].dma = ring_header->dma + offset; - tpd_ring[i].desc = (u8 *) ring_header->desc + offset; + tpd_ring[i].desc = (u8 *)ring_header->desc + offset; tpd_ring[i].size = sizeof(struct atl1c_tpd_desc) * tpd_ring[i].count; offset += roundup(tpd_ring[i].size, 8); } - /* init RFD ring */ - rfd_ring->dma = ring_header->dma + offset; - rfd_ring->desc = (u8 *) ring_header->desc + offset; - rfd_ring->size = sizeof(struct atl1c_rx_free_desc) * rfd_ring->count; - offset += roundup(rfd_ring->size, 8); + for (i = 0; i < rqc; i++) { + /* init RFD ring */ + rfd_ring[i].dma = ring_header->dma + offset; + rfd_ring[i].desc = (u8 *)ring_header->desc + offset; + rfd_ring[i].size = sizeof(struct atl1c_rx_free_desc) * + rfd_ring[i].count; + offset += roundup(rfd_ring[i].size, 8); - /* init RRD ring */ - rrd_ring->dma = ring_header->dma + offset; - rrd_ring->desc = (u8 *) ring_header->desc + offset; - rrd_ring->size = sizeof(struct atl1c_recv_ret_status) * - rrd_ring->count; - offset += roundup(rrd_ring->size, 8); + /* init RRD ring */ + rrd_ring[i].dma = ring_header->dma + offset; + rrd_ring[i].desc = (u8 *)ring_header->desc + offset; + rrd_ring[i].size = sizeof(struct atl1c_recv_ret_status) * + rrd_ring[i].count; + offset += roundup(rrd_ring[i].size, 8); + } return 0; @@ -1044,31 +1100,34 @@ err_nomem: static void atl1c_configure_des_ring(struct atl1c_adapter *adapter) { struct atl1c_hw *hw = &adapter->hw; - struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring; - struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring; - struct atl1c_tpd_ring *tpd_ring = (struct atl1c_tpd_ring *) - adapter->tpd_ring; + struct atl1c_rfd_ring *rfd_ring = adapter->rfd_ring; + struct atl1c_rrd_ring *rrd_ring = adapter->rrd_ring; + struct atl1c_tpd_ring *tpd_ring = adapter->tpd_ring; + int i; + int tx_queue_count = adapter->tx_queue_count; + + if (tx_queue_count == 1) + tx_queue_count = 2; /* TPD */ AT_WRITE_REG(hw, REG_TX_BASE_ADDR_HI, - (u32)((tpd_ring[atl1c_trans_normal].dma & - AT_DMA_HI_ADDR_MASK) >> 32)); + (u32)((tpd_ring[0].dma & AT_DMA_HI_ADDR_MASK) >> 32)); /* just enable normal priority TX queue */ - AT_WRITE_REG(hw, REG_TPD_PRI0_ADDR_LO, - (u32)(tpd_ring[atl1c_trans_normal].dma & - AT_DMA_LO_ADDR_MASK)); - AT_WRITE_REG(hw, REG_TPD_PRI1_ADDR_LO, - (u32)(tpd_ring[atl1c_trans_high].dma & - AT_DMA_LO_ADDR_MASK)); + for (i = 0; i < tx_queue_count; i++) { + AT_WRITE_REG(hw, atl1c_qregs[i].tpd_addr_lo, + (u32)(tpd_ring[i].dma & AT_DMA_LO_ADDR_MASK)); + } AT_WRITE_REG(hw, REG_TPD_RING_SIZE, (u32)(tpd_ring[0].count & TPD_RING_SIZE_MASK)); /* RFD */ AT_WRITE_REG(hw, REG_RX_BASE_ADDR_HI, - (u32)((rfd_ring->dma & AT_DMA_HI_ADDR_MASK) >> 32)); - AT_WRITE_REG(hw, REG_RFD0_HEAD_ADDR_LO, - (u32)(rfd_ring->dma & AT_DMA_LO_ADDR_MASK)); + (u32)((rfd_ring->dma & AT_DMA_HI_ADDR_MASK) >> 32)); + for (i = 0; i < adapter->rx_queue_count; i++) { + AT_WRITE_REG(hw, atl1c_qregs[i].rfd_addr_lo, + (u32)(rfd_ring[i].dma & AT_DMA_LO_ADDR_MASK)); + } AT_WRITE_REG(hw, REG_RFD_RING_SIZE, rfd_ring->count & RFD_RING_SIZE_MASK); @@ -1076,8 +1135,10 @@ static void atl1c_configure_des_ring(struct atl1c_adapter *adapter) adapter->rx_buffer_len & RX_BUF_SIZE_MASK); /* RRD */ - AT_WRITE_REG(hw, REG_RRD0_HEAD_ADDR_LO, - (u32)(rrd_ring->dma & AT_DMA_LO_ADDR_MASK)); + for (i = 0; i < adapter->rx_queue_count; i++) { + AT_WRITE_REG(hw, atl1c_qregs[i].rrd_addr_lo, + (u32)(rrd_ring[i].dma & AT_DMA_LO_ADDR_MASK)); + } AT_WRITE_REG(hw, REG_RRD_RING_SIZE, (rrd_ring->count & RRD_RING_SIZE_MASK)); @@ -1358,7 +1419,7 @@ static void atl1c_set_aspm(struct atl1c_hw *hw, u16 link_speed) } /** - * atl1c_configure - Configure Transmit&Receive Unit after Reset + * atl1c_configure_mac - Configure Transmit&Receive Unit after Reset * @adapter: board private structure * * Configure the Tx /Rx unit of the MAC after a reset. @@ -1430,14 +1491,28 @@ static int atl1c_configure(struct atl1c_adapter *adapter) { struct net_device *netdev = adapter->netdev; int num; + int i; + + if (adapter->hw.nic_type == athr_mt) { + u32 mode; + + AT_READ_REG(&adapter->hw, REG_MT_MODE, &mode); + if (adapter->rx_queue_count == 4) + mode |= MT_MODE_4Q; + else + mode &= ~MT_MODE_4Q; + AT_WRITE_REG(&adapter->hw, REG_MT_MODE, mode); + } atl1c_init_ring_ptrs(adapter); atl1c_set_multi(netdev); atl1c_restore_vlan(adapter); - num = atl1c_alloc_rx_buffer(adapter, false); - if (unlikely(num == 0)) - return -ENOMEM; + for (i = 0; i < adapter->rx_queue_count; ++i) { + num = atl1c_alloc_rx_buffer(adapter, i, false); + if (unlikely(num == 0)) + return -ENOMEM; + } if (atl1c_configure_mac(adapter)) return -EIO; @@ -1533,9 +1608,11 @@ static inline void atl1c_clear_phy_int(struct atl1c_adapter *adapter) static int atl1c_clean_tx(struct napi_struct *napi, int budget) { - struct atl1c_adapter *adapter = - container_of(napi, struct atl1c_adapter, tx_napi); - struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[atl1c_trans_normal]; + struct atl1c_tpd_ring *tpd_ring = + container_of(napi, struct atl1c_tpd_ring, napi); + struct atl1c_adapter *adapter = tpd_ring->adapter; + struct netdev_queue *txq = + netdev_get_tx_queue(napi->dev, tpd_ring->num); struct atl1c_buffer *buffer_info; struct pci_dev *pdev = adapter->pdev; u16 next_to_clean = atomic_read(&tpd_ring->next_to_clean); @@ -1543,7 +1620,8 @@ static int atl1c_clean_tx(struct napi_struct *napi, int budget) unsigned int total_bytes = 0, total_packets = 0; unsigned long flags; - AT_READ_REGW(&adapter->hw, REG_TPD_PRI0_CIDX, &hw_next_to_clean); + AT_READ_REGW(&adapter->hw, atl1c_qregs[tpd_ring->num].tpd_cons, + &hw_next_to_clean); while (next_to_clean != hw_next_to_clean) { buffer_info = &tpd_ring->buffer_info[next_to_clean]; @@ -1557,17 +1635,15 @@ static int atl1c_clean_tx(struct napi_struct *napi, int budget) atomic_set(&tpd_ring->next_to_clean, next_to_clean); } - netdev_completed_queue(adapter->netdev, total_packets, total_bytes); + netdev_tx_completed_queue(txq, total_packets, total_bytes); - if (netif_queue_stopped(adapter->netdev) && - netif_carrier_ok(adapter->netdev)) { - netif_wake_queue(adapter->netdev); - } + if (netif_tx_queue_stopped(txq) && netif_carrier_ok(adapter->netdev)) + netif_tx_wake_queue(txq); if (total_packets < budget) { napi_complete_done(napi, total_packets); spin_lock_irqsave(&adapter->hw.intr_mask_lock, flags); - adapter->hw.intr_mask |= ISR_TX_PKT; + adapter->hw.intr_mask |= atl1c_qregs[tpd_ring->num].tx_isr; AT_WRITE_REG(&adapter->hw, REG_IMR, adapter->hw.intr_mask); spin_unlock_irqrestore(&adapter->hw.intr_mask_lock, flags); return total_packets; @@ -1575,6 +1651,38 @@ static int atl1c_clean_tx(struct napi_struct *napi, int budget) return budget; } +static void atl1c_intr_rx_tx(struct atl1c_adapter *adapter, u32 status) +{ + struct atl1c_hw *hw = &adapter->hw; + u32 intr_mask; + int i; + + spin_lock(&hw->intr_mask_lock); + intr_mask = hw->intr_mask; + for (i = 0; i < adapter->rx_queue_count; ++i) { + if (!(status & atl1c_qregs[i].rx_isr)) + continue; + if (napi_schedule_prep(&adapter->rrd_ring[i].napi)) { + intr_mask &= ~atl1c_qregs[i].rx_isr; + __napi_schedule(&adapter->rrd_ring[i].napi); + } + } + for (i = 0; i < adapter->tx_queue_count; ++i) { + if (!(status & atl1c_qregs[i].tx_isr)) + continue; + if (napi_schedule_prep(&adapter->tpd_ring[i].napi)) { + intr_mask &= ~atl1c_qregs[i].tx_isr; + __napi_schedule(&adapter->tpd_ring[i].napi); + } + } + + if (hw->intr_mask != intr_mask) { + hw->intr_mask = intr_mask; + AT_WRITE_REG(hw, REG_IMR, hw->intr_mask); + } + spin_unlock(&hw->intr_mask_lock); +} + /** * atl1c_intr - Interrupt Handler * @irq: interrupt number @@ -1605,24 +1713,8 @@ static irqreturn_t atl1c_intr(int irq, void *data) atl1c_clear_phy_int(adapter); /* Ack ISR */ AT_WRITE_REG(hw, REG_ISR, status | ISR_DIS_INT); - if (status & ISR_RX_PKT) { - if (likely(napi_schedule_prep(&adapter->napi))) { - spin_lock(&hw->intr_mask_lock); - hw->intr_mask &= ~ISR_RX_PKT; - AT_WRITE_REG(hw, REG_IMR, hw->intr_mask); - spin_unlock(&hw->intr_mask_lock); - __napi_schedule(&adapter->napi); - } - } - if (status & ISR_TX_PKT) { - if (napi_schedule_prep(&adapter->tx_napi)) { - spin_lock(&hw->intr_mask_lock); - hw->intr_mask &= ~ISR_TX_PKT; - AT_WRITE_REG(hw, REG_IMR, hw->intr_mask); - spin_unlock(&hw->intr_mask_lock); - __napi_schedule(&adapter->tx_napi); - } - } + if (status & (ISR_RX_PKT | ISR_TX_PKT)) + atl1c_intr_rx_tx(adapter, status); handled = IRQ_HANDLED; /* check if PCIE PHY Link down */ @@ -1659,6 +1751,11 @@ static irqreturn_t atl1c_intr(int irq, void *data) static inline void atl1c_rx_checksum(struct atl1c_adapter *adapter, struct sk_buff *skb, struct atl1c_recv_ret_status *prrs) { + if (adapter->hw.nic_type == athr_mt) { + if (prrs->word3 & RRS_MT_PROT_ID_TCPUDP) + skb->ip_summed = CHECKSUM_UNNECESSARY; + return; + } /* * The pid field in RRS in not correct sometimes, so we * cannot figure out if the packet is fragmented or not, @@ -1668,44 +1765,47 @@ static inline void atl1c_rx_checksum(struct atl1c_adapter *adapter, } static struct sk_buff *atl1c_alloc_skb(struct atl1c_adapter *adapter, - bool napi_mode) + u32 queue, bool napi_mode) { + struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring[queue]; struct sk_buff *skb; struct page *page; if (adapter->rx_frag_size > PAGE_SIZE) { if (likely(napi_mode)) - return napi_alloc_skb(&adapter->napi, + return napi_alloc_skb(&rrd_ring->napi, adapter->rx_buffer_len); else return netdev_alloc_skb_ip_align(adapter->netdev, adapter->rx_buffer_len); } - page = adapter->rx_page; + page = rrd_ring->rx_page; if (!page) { - adapter->rx_page = page = alloc_page(GFP_ATOMIC); + page = alloc_page(GFP_ATOMIC); if (unlikely(!page)) return NULL; - adapter->rx_page_offset = 0; + rrd_ring->rx_page = page; + rrd_ring->rx_page_offset = 0; } - skb = build_skb(page_address(page) + adapter->rx_page_offset, + skb = build_skb(page_address(page) + rrd_ring->rx_page_offset, adapter->rx_frag_size); if (likely(skb)) { skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); - adapter->rx_page_offset += adapter->rx_frag_size; - if (adapter->rx_page_offset >= PAGE_SIZE) - adapter->rx_page = NULL; + rrd_ring->rx_page_offset += adapter->rx_frag_size; + if (rrd_ring->rx_page_offset >= PAGE_SIZE) + rrd_ring->rx_page = NULL; else get_page(page); } return skb; } -static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, bool napi_mode) +static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, u32 queue, + bool napi_mode) { - struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring; + struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring[queue]; struct pci_dev *pdev = adapter->pdev; struct atl1c_buffer *buffer_info, *next_info; struct sk_buff *skb; @@ -1724,7 +1824,7 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, bool napi_mode) while (next_info->flags & ATL1C_BUFFER_FREE) { rfd_desc = ATL1C_RFD_DESC(rfd_ring, rfd_next_to_use); - skb = atl1c_alloc_skb(adapter, napi_mode); + skb = atl1c_alloc_skb(adapter, queue, napi_mode); if (unlikely(!skb)) { if (netif_msg_rx_err(adapter)) dev_warn(&pdev->dev, "alloc rx buffer failed\n"); @@ -1766,8 +1866,8 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, bool napi_mode) /* TODO: update mailbox here */ wmb(); rfd_ring->next_to_use = rfd_next_to_use; - AT_WRITE_REG(&adapter->hw, REG_MB_RFD0_PROD_IDX, - rfd_ring->next_to_use & MB_RFDX_PROD_IDX_MASK); + AT_WRITE_REG(&adapter->hw, atl1c_qregs[queue].rfd_prod, + rfd_ring->next_to_use & MB_RFDX_PROD_IDX_MASK); } return num_alloc; @@ -1805,22 +1905,33 @@ static void atl1c_clean_rfd(struct atl1c_rfd_ring *rfd_ring, rfd_ring->next_to_clean = rfd_index; } -static void atl1c_clean_rx_irq(struct atl1c_adapter *adapter, - int *work_done, int work_to_do) +/** + * atl1c_clean_rx - NAPI Rx polling callback + * @napi: napi info + * @budget: limit of packets to clean + */ +static int atl1c_clean_rx(struct napi_struct *napi, int budget) { + struct atl1c_rrd_ring *rrd_ring = + container_of(napi, struct atl1c_rrd_ring, napi); + struct atl1c_adapter *adapter = rrd_ring->adapter; u16 rfd_num, rfd_index; - u16 count = 0; u16 length; struct pci_dev *pdev = adapter->pdev; struct net_device *netdev = adapter->netdev; - struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring; - struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring; + struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring[rrd_ring->num]; struct sk_buff *skb; struct atl1c_recv_ret_status *rrs; struct atl1c_buffer *buffer_info; + int work_done = 0; + unsigned long flags; + + /* Keep link state information with original netdev */ + if (!netif_carrier_ok(adapter->netdev)) + goto quit_polling; while (1) { - if (*work_done >= work_to_do) + if (work_done >= budget) break; rrs = ATL1C_RRD_DESC(rrd_ring, rrd_ring->next_to_clean); if (likely(RRS_RXD_IS_VALID(rrs->word3))) { @@ -1874,38 +1985,18 @@ rrs_checked: vlan = le16_to_cpu(vlan); __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan); } - napi_gro_receive(&adapter->napi, skb); + napi_gro_receive(napi, skb); - (*work_done)++; - count++; + work_done++; } - if (count) - atl1c_alloc_rx_buffer(adapter, true); -} - -/** - * atl1c_clean - NAPI Rx polling callback - * @napi: napi info - * @budget: limit of packets to clean - */ -static int atl1c_clean(struct napi_struct *napi, int budget) -{ - struct atl1c_adapter *adapter = - container_of(napi, struct atl1c_adapter, napi); - int work_done = 0; - unsigned long flags; - - /* Keep link state information with original netdev */ - if (!netif_carrier_ok(adapter->netdev)) - goto quit_polling; - /* just enable one RXQ */ - atl1c_clean_rx_irq(adapter, &work_done, budget); + if (work_done) + atl1c_alloc_rx_buffer(adapter, rrd_ring->num, true); if (work_done < budget) { quit_polling: napi_complete_done(napi, work_done); spin_lock_irqsave(&adapter->hw.intr_mask_lock, flags); - adapter->hw.intr_mask |= ISR_RX_PKT; + adapter->hw.intr_mask |= atl1c_qregs[rrd_ring->num].rx_isr; AT_WRITE_REG(&adapter->hw, REG_IMR, adapter->hw.intr_mask); spin_unlock_irqrestore(&adapter->hw.intr_mask_lock, flags); } @@ -1929,9 +2020,9 @@ static void atl1c_netpoll(struct net_device *netdev) } #endif -static inline u16 atl1c_tpd_avail(struct atl1c_adapter *adapter, enum atl1c_trans_queue type) +static inline u16 atl1c_tpd_avail(struct atl1c_adapter *adapter, u32 queue) { - struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[type]; + struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[queue]; u16 next_to_use = 0; u16 next_to_clean = 0; @@ -1949,9 +2040,9 @@ static inline u16 atl1c_tpd_avail(struct atl1c_adapter *adapter, enum atl1c_tran * there is enough tpd to use */ static struct atl1c_tpd_desc *atl1c_get_tpd(struct atl1c_adapter *adapter, - enum atl1c_trans_queue type) + u32 queue) { - struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[type]; + struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[queue]; struct atl1c_tpd_desc *tpd_desc; u16 next_to_use = 0; @@ -1993,7 +2084,7 @@ static u16 atl1c_cal_tpd_req(const struct sk_buff *skb) static int atl1c_tso_csum(struct atl1c_adapter *adapter, struct sk_buff *skb, struct atl1c_tpd_desc **tpd, - enum atl1c_trans_queue type) + u32 queue) { struct pci_dev *pdev = adapter->pdev; unsigned short offload_type; @@ -2038,7 +2129,7 @@ static int atl1c_tso_csum(struct atl1c_adapter *adapter, *(struct atl1c_tpd_ext_desc **)(tpd); memset(etpd, 0, sizeof(struct atl1c_tpd_ext_desc)); - *tpd = atl1c_get_tpd(adapter, type); + *tpd = atl1c_get_tpd(adapter, queue); ipv6_hdr(skb)->payload_len = 0; /* check payload == 0 byte ? */ hdr_len = (skb_transport_offset(skb) + tcp_hdrlen(skb)); @@ -2090,9 +2181,9 @@ check_sum: static void atl1c_tx_rollback(struct atl1c_adapter *adpt, struct atl1c_tpd_desc *first_tpd, - enum atl1c_trans_queue type) + u32 queue) { - struct atl1c_tpd_ring *tpd_ring = &adpt->tpd_ring[type]; + struct atl1c_tpd_ring *tpd_ring = &adpt->tpd_ring[queue]; struct atl1c_buffer *buffer_info; struct atl1c_tpd_desc *tpd; u16 first_index, index; @@ -2111,8 +2202,8 @@ static void atl1c_tx_rollback(struct atl1c_adapter *adpt, } static int atl1c_tx_map(struct atl1c_adapter *adapter, - struct sk_buff *skb, struct atl1c_tpd_desc *tpd, - enum atl1c_trans_queue type) + struct sk_buff *skb, struct atl1c_tpd_desc *tpd, + u32 queue) { struct atl1c_tpd_desc *use_tpd = NULL; struct atl1c_buffer *buffer_info = NULL; @@ -2152,7 +2243,7 @@ static int atl1c_tx_map(struct atl1c_adapter *adapter, if (mapped_len == 0) use_tpd = tpd; else { - use_tpd = atl1c_get_tpd(adapter, type); + use_tpd = atl1c_get_tpd(adapter, queue); memcpy(use_tpd, tpd, sizeof(struct atl1c_tpd_desc)); } buffer_info = atl1c_get_tx_buffer(adapter, use_tpd); @@ -2174,7 +2265,7 @@ static int atl1c_tx_map(struct atl1c_adapter *adapter, for (f = 0; f < nr_frags; f++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; - use_tpd = atl1c_get_tpd(adapter, type); + use_tpd = atl1c_get_tpd(adapter, queue); memcpy(use_tpd, tpd, sizeof(struct atl1c_tpd_desc)); buffer_info = atl1c_get_tx_buffer(adapter, use_tpd); @@ -2207,23 +2298,22 @@ err_dma: return -1; } -static void atl1c_tx_queue(struct atl1c_adapter *adapter, struct sk_buff *skb, - struct atl1c_tpd_desc *tpd, enum atl1c_trans_queue type) +static void atl1c_tx_queue(struct atl1c_adapter *adapter, u32 queue) { - struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[type]; - u16 reg; + struct atl1c_tpd_ring *tpd_ring = &adapter->tpd_ring[queue]; - reg = type == atl1c_trans_high ? REG_TPD_PRI1_PIDX : REG_TPD_PRI0_PIDX; - AT_WRITE_REGW(&adapter->hw, reg, tpd_ring->next_to_use); + AT_WRITE_REGW(&adapter->hw, atl1c_qregs[queue].tpd_prod, + tpd_ring->next_to_use); } static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb, struct net_device *netdev) { struct atl1c_adapter *adapter = netdev_priv(netdev); - u16 tpd_req; + u32 queue = skb_get_queue_mapping(skb); + struct netdev_queue *txq = netdev_get_tx_queue(netdev, queue); struct atl1c_tpd_desc *tpd; - enum atl1c_trans_queue type = atl1c_trans_normal; + u16 tpd_req; if (test_bit(__AT_DOWN, &adapter->flags)) { dev_kfree_skb_any(skb); @@ -2232,16 +2322,18 @@ static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb, tpd_req = atl1c_cal_tpd_req(skb); - if (atl1c_tpd_avail(adapter, type) < tpd_req) { + if (atl1c_tpd_avail(adapter, queue) < tpd_req) { /* no enough descriptor, just stop queue */ - netif_stop_queue(netdev); + atl1c_tx_queue(adapter, queue); + netif_tx_stop_queue(txq); return NETDEV_TX_BUSY; } - tpd = atl1c_get_tpd(adapter, type); + tpd = atl1c_get_tpd(adapter, queue); /* do TSO and check sum */ - if (atl1c_tso_csum(adapter, skb, &tpd, type) != 0) { + if (atl1c_tso_csum(adapter, skb, &tpd, queue) != 0) { + atl1c_tx_queue(adapter, queue); dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -2259,15 +2351,17 @@ static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb, if (skb_network_offset(skb) != ETH_HLEN) tpd->word1 |= 1 << TPD_ETH_TYPE_SHIFT; /* Ethernet frame */ - if (atl1c_tx_map(adapter, skb, tpd, type) < 0) { + if (atl1c_tx_map(adapter, skb, tpd, queue) < 0) { netif_info(adapter, tx_done, adapter->netdev, "tx-skb dropped due to dma error\n"); /* roll back tpd/buffer */ - atl1c_tx_rollback(adapter, tpd, type); + atl1c_tx_rollback(adapter, tpd, queue); dev_kfree_skb_any(skb); } else { - netdev_sent_queue(adapter->netdev, skb->len); - atl1c_tx_queue(adapter, skb, tpd, type); + bool more = netdev_xmit_more(); + + if (__netdev_tx_sent_queue(txq, skb->len, more)) + atl1c_tx_queue(adapter, queue); } return NETDEV_TX_OK; @@ -2321,16 +2415,19 @@ static int atl1c_request_irq(struct atl1c_adapter *adapter) static void atl1c_reset_dma_ring(struct atl1c_adapter *adapter) { + int i; /* release tx-pending skbs and reset tx/rx ring index */ - atl1c_clean_tx_ring(adapter, atl1c_trans_normal); - atl1c_clean_tx_ring(adapter, atl1c_trans_high); - atl1c_clean_rx_ring(adapter); + for (i = 0; i < adapter->tx_queue_count; ++i) + atl1c_clean_tx_ring(adapter, i); + for (i = 0; i < adapter->rx_queue_count; ++i) + atl1c_clean_rx_ring(adapter, i); } static int atl1c_up(struct atl1c_adapter *adapter) { struct net_device *netdev = adapter->netdev; int err; + int i; netif_carrier_off(netdev); @@ -2344,20 +2441,24 @@ static int atl1c_up(struct atl1c_adapter *adapter) atl1c_check_link_status(adapter); clear_bit(__AT_DOWN, &adapter->flags); - napi_enable(&adapter->napi); - napi_enable(&adapter->tx_napi); + for (i = 0; i < adapter->tx_queue_count; ++i) + napi_enable(&adapter->tpd_ring[i].napi); + for (i = 0; i < adapter->rx_queue_count; ++i) + napi_enable(&adapter->rrd_ring[i].napi); atl1c_irq_enable(adapter); netif_start_queue(netdev); return err; err_up: - atl1c_clean_rx_ring(adapter); + for (i = 0; i < adapter->rx_queue_count; ++i) + atl1c_clean_rx_ring(adapter, i); return err; } static void atl1c_down(struct atl1c_adapter *adapter) { struct net_device *netdev = adapter->netdev; + int i; atl1c_del_timer(adapter); adapter->work_event = 0; /* clear all event */ @@ -2365,8 +2466,10 @@ static void atl1c_down(struct atl1c_adapter *adapter) * reschedule our watchdog timer */ set_bit(__AT_DOWN, &adapter->flags); netif_carrier_off(netdev); - napi_disable(&adapter->napi); - napi_disable(&adapter->tx_napi); + for (i = 0; i < adapter->tx_queue_count; ++i) + napi_disable(&adapter->tpd_ring[i].napi); + for (i = 0; i < adapter->rx_queue_count; ++i) + napi_disable(&adapter->rrd_ring[i].napi); atl1c_irq_disable(adapter); atl1c_free_irq(adapter); /* disable ASPM if device inactive */ @@ -2551,8 +2654,11 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct net_device *netdev; struct atl1c_adapter *adapter; static int cards_found; - + u8 __iomem *hw_addr; + enum atl1c_nic_type nic_type; + u32 queue_count = 1; int err = 0; + int i; /* enable device (incl. PCI PM wakeup and hotplug setup) */ err = pci_enable_device_mem(pdev); @@ -2585,7 +2691,18 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); - netdev = alloc_etherdev(sizeof(struct atl1c_adapter)); + hw_addr = pci_ioremap_bar(pdev, 0); + if (!hw_addr) { + err = -EIO; + dev_err(&pdev->dev, "cannot map device registers\n"); + goto err_ioremap; + } + + nic_type = atl1c_get_mac_type(pdev, hw_addr); + if (nic_type == athr_mt) + queue_count = 4; + + netdev = alloc_etherdev_mq(sizeof(struct atl1c_adapter), queue_count); if (netdev == NULL) { err = -ENOMEM; goto err_alloc_etherdev; @@ -2601,13 +2718,11 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->netdev = netdev; adapter->pdev = pdev; adapter->hw.adapter = adapter; + adapter->hw.nic_type = nic_type; adapter->msg_enable = netif_msg_init(-1, atl1c_default_msg); - adapter->hw.hw_addr = ioremap(pci_resource_start(pdev, 0), pci_resource_len(pdev, 0)); - if (!adapter->hw.hw_addr) { - err = -EIO; - dev_err(&pdev->dev, "cannot map device registers\n"); - goto err_ioremap; - } + adapter->hw.hw_addr = hw_addr; + adapter->tx_queue_count = queue_count; + adapter->rx_queue_count = queue_count; /* init mii data */ adapter->mii.dev = netdev; @@ -2616,8 +2731,12 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->mii.phy_id_mask = 0x1f; adapter->mii.reg_num_mask = MDIO_CTRL_REG_MASK; dev_set_threaded(netdev, true); - netif_napi_add(netdev, &adapter->napi, atl1c_clean, 64); - netif_napi_add(netdev, &adapter->tx_napi, atl1c_clean_tx, 64); + for (i = 0; i < adapter->rx_queue_count; ++i) + netif_napi_add(netdev, &adapter->rrd_ring[i].napi, + atl1c_clean_rx, 64); + for (i = 0; i < adapter->tx_queue_count; ++i) + netif_napi_add(netdev, &adapter->tpd_ring[i].napi, + atl1c_clean_tx, 64); timer_setup(&adapter->phy_config_timer, atl1c_phy_config, 0); /* setup the private structure */ err = atl1c_sw_init(adapter); @@ -2670,11 +2789,11 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err_reset: err_register: err_sw_init: - iounmap(adapter->hw.hw_addr); err_init_netdev: -err_ioremap: free_netdev(netdev); err_alloc_etherdev: + iounmap(hw_addr); +err_ioremap: pci_release_regions(pdev); err_pci_reg: err_dma: diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index ff9f96de74b8..2eb0a2ab69f6 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -357,7 +357,7 @@ static void atl1e_restore_vlan(struct atl1e_adapter *adapter) } /** - * atl1e_set_mac - Change the Ethernet Address of the NIC + * atl1e_set_mac_addr - Change the Ethernet Address of the NIC * @netdev: network interface device structure * @p: pointer to an address structure * @@ -787,7 +787,7 @@ static void atl1e_free_ring_resources(struct atl1e_adapter *adapter) } /** - * atl1e_setup_mem_resources - allocate Tx / RX descriptor resources + * atl1e_setup_ring_resources - allocate Tx / RX descriptor resources * @adapter: board private structure * * Return 0 on success, negative on failure diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index eaf96d002fa5..c67201a13cf5 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -1011,7 +1011,7 @@ static int atl1_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) } /** - * atl1_setup_mem_resources - allocate Tx / RX descriptor resources + * atl1_setup_ring_resources - allocate Tx / RX descriptor resources * @adapter: board private structure * * Return 0 on success, negative on failure diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index cb88ffb8f12f..1a02ca600b71 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -206,6 +206,7 @@ config SYSTEMPORT config BNXT tristate "Broadcom NetXtreme-C/E support" depends on PCI + imply PTP_1588_CLOCK select FW_LOADER select LIBCRC32C select NET_DEVLINK diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index b455b60a5434..ad2655efe423 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -1556,8 +1556,8 @@ static void b44_setup_pseudo_magicp(struct b44 *bp) plen0 = b44_magic_pattern(bp->dev->dev_addr, pwol_pattern, pwol_mask, B44_ETHIPV4UDP_HLEN); - bwfilter_table(bp, pwol_pattern, B44_PATTERN_SIZE, B44_PATTERN_BASE); - bwfilter_table(bp, pwol_mask, B44_PMASK_SIZE, B44_PMASK_BASE); + bwfilter_table(bp, pwol_pattern, B44_PATTERN_SIZE, B44_PATTERN_BASE); + bwfilter_table(bp, pwol_mask, B44_PMASK_SIZE, B44_PMASK_BASE); /* Raw ethernet II magic packet pattern - pattern 1 */ memset(pwol_pattern, 0, B44_PATTERN_SIZE); @@ -1565,9 +1565,9 @@ static void b44_setup_pseudo_magicp(struct b44 *bp) plen1 = b44_magic_pattern(bp->dev->dev_addr, pwol_pattern, pwol_mask, ETH_HLEN); - bwfilter_table(bp, pwol_pattern, B44_PATTERN_SIZE, + bwfilter_table(bp, pwol_pattern, B44_PATTERN_SIZE, B44_PATTERN_BASE + B44_PATTERN_SIZE); - bwfilter_table(bp, pwol_mask, B44_PMASK_SIZE, + bwfilter_table(bp, pwol_mask, B44_PMASK_SIZE, B44_PMASK_BASE + B44_PMASK_SIZE); /* Ipv6 magic packet pattern - pattern 2 */ @@ -1576,9 +1576,9 @@ static void b44_setup_pseudo_magicp(struct b44 *bp) plen2 = b44_magic_pattern(bp->dev->dev_addr, pwol_pattern, pwol_mask, B44_ETHIPV6UDP_HLEN); - bwfilter_table(bp, pwol_pattern, B44_PATTERN_SIZE, + bwfilter_table(bp, pwol_pattern, B44_PATTERN_SIZE, B44_PATTERN_BASE + B44_PATTERN_SIZE + B44_PATTERN_SIZE); - bwfilter_table(bp, pwol_mask, B44_PMASK_SIZE, + bwfilter_table(bp, pwol_mask, B44_PMASK_SIZE, B44_PMASK_BASE + B44_PMASK_SIZE + B44_PMASK_SIZE); kfree(pwol_pattern); @@ -1631,9 +1631,9 @@ static void b44_setup_wol(struct b44 *bp) val = br32(bp, B44_DEVCTRL); bw32(bp, B44_DEVCTRL, val | DEVCTRL_MPM | DEVCTRL_PFE); - } else { - b44_setup_pseudo_magicp(bp); - } + } else { + b44_setup_pseudo_magicp(bp); + } b44_setup_wol_pci(bp); } @@ -1757,7 +1757,7 @@ static void __b44_set_rx_mode(struct net_device *dev) __b44_cam_write(bp, zero, i); bw32(bp, B44_RXCONFIG, val); - val = br32(bp, B44_CAM_CTRL); + val = br32(bp, B44_CAM_CTRL); bw32(bp, B44_CAM_CTRL, val | CAM_CTRL_ENABLE); } } diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c index 60d908507f51..02a569500234 100644 --- a/drivers/net/ethernet/broadcom/bcm4908_enet.c +++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c @@ -174,9 +174,6 @@ static int bcm4908_dma_alloc_buf_descs(struct bcm4908_enet *enet, if (!ring->slots) goto err_free_buf_descs; - ring->read_idx = 0; - ring->write_idx = 0; - return 0; err_free_buf_descs: @@ -304,6 +301,9 @@ static void bcm4908_enet_dma_ring_init(struct bcm4908_enet *enet, enet_write(enet, ring->st_ram_block + ENET_DMA_CH_STATE_RAM_BASE_DESC_PTR, (uint32_t)ring->dma_addr); + + ring->read_idx = 0; + ring->write_idx = 0; } static void bcm4908_enet_dma_uninit(struct bcm4908_enet *enet) diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index 9834b77cf4b6..4ab5bf64d353 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -172,7 +172,6 @@ static int bgmac_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct bgmac *bgmac; - struct resource *regs; int ret; bgmac = bgmac_alloc(&pdev->dev); @@ -206,21 +205,15 @@ static int bgmac_probe(struct platform_device *pdev) if (IS_ERR(bgmac->plat.base)) return PTR_ERR(bgmac->plat.base); - regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "idm_base"); - if (regs) { - bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs); - if (IS_ERR(bgmac->plat.idm_base)) - return PTR_ERR(bgmac->plat.idm_base); + bgmac->plat.idm_base = devm_platform_ioremap_resource_byname(pdev, "idm_base"); + if (IS_ERR(bgmac->plat.idm_base)) + return PTR_ERR(bgmac->plat.idm_base); + else bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; - } - regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nicpm_base"); - if (regs) { - bgmac->plat.nicpm_base = devm_ioremap_resource(&pdev->dev, - regs); - if (IS_ERR(bgmac->plat.nicpm_base)) - return PTR_ERR(bgmac->plat.nicpm_base); - } + bgmac->plat.nicpm_base = devm_platform_ioremap_resource_byname(pdev, "nicpm_base"); + if (IS_ERR(bgmac->plat.nicpm_base)) + return PTR_ERR(bgmac->plat.nicpm_base); bgmac->read = platform_bgmac_read; bgmac->write = platform_bgmac_write; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index 5bace8a93d73..bee6cfad9fc6 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -572,7 +572,7 @@ bnx2_write_phy(struct bnx2 *bp, u32 reg, u32 val) } if (val1 & BNX2_EMAC_MDIO_COMM_START_BUSY) - ret = -EBUSY; + ret = -EBUSY; else ret = 0; @@ -3599,7 +3599,7 @@ bnx2_set_rx_mode(struct net_device *dev) for (i = 0; i < NUM_MC_HASH_REGISTERS; i++) { BNX2_WR(bp, BNX2_EMAC_MULTICAST_HASH0 + (i * 4), 0xffffffff); - } + } sort_mode |= BNX2_RPM_SORT_USER0_MC_EN; } else { @@ -4674,7 +4674,7 @@ bnx2_nvram_write(struct bnx2 *bp, u32 offset, u8 *data_buf, if (addr == page_end-4) { cmd_flags = BNX2_NVM_COMMAND_LAST; - } + } rc = bnx2_nvram_write_dword(bp, addr, &flash_buffer[i], cmd_flags); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 281b1c2e04a7..2acbc73dcd18 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13586,7 +13586,7 @@ static int bnx2x_set_qm_cid_count(struct bnx2x *bp) } /** - * bnx2x_get_num_none_def_sbs - return the number of none default SBs + * bnx2x_get_num_non_def_sbs - return the number of none default SBs * @pdev: pci device * @cnic_cnt: count * diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c index 6cd1523ad9e5..542c69822649 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c @@ -4152,7 +4152,7 @@ void bnx2x_init_mcast_obj(struct bnx2x *bp, /*************************** Credit handling **********************************/ /** - * atomic_add_ifless - add if the result is less than a given value. + * __atomic_add_ifless - add if the result is less than a given value. * * @v: pointer of type atomic_t * @a: the amount to add to v... @@ -4180,7 +4180,7 @@ static inline bool __atomic_add_ifless(atomic_t *v, int a, int u) } /** - * atomic_dec_ifmoe - dec if the result is more or equal than a given value. + * __atomic_dec_ifmoe - dec if the result is more or equal than a given value. * * @v: pointer of type atomic_t * @a: the amount to dec from v... diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index 3a716c015415..966d5722c5e2 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -504,7 +504,6 @@ enum sample_bulletin_result bnx2x_sample_bulletin(struct bnx2x *bp); /* VF side vfpf channel functions */ int bnx2x_vfpf_acquire(struct bnx2x *bp, u8 tx_count, u8 rx_count); int bnx2x_vfpf_release(struct bnx2x *bp); -int bnx2x_vfpf_release(struct bnx2x *bp); int bnx2x_vfpf_init(struct bnx2x *bp); void bnx2x_vfpf_close_vf(struct bnx2x *bp); int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp, diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile index cb97ec56fdec..2b8ae687b3c1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/Makefile +++ b/drivers/net/ethernet/broadcom/bnxt/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_BNXT) += bnxt_en.o -bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_devlink.o bnxt_dim.o +bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_ptp.o bnxt_vfr.o bnxt_devlink.o bnxt_dim.o bnxt_en-$(CONFIG_BNXT_FLOWER_OFFLOAD) += bnxt_tc.o bnxt_en-$(CONFIG_DEBUG_FS) += bnxt_debugfs.o diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 598e5e6ace18..f56245eeef7b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -49,6 +49,8 @@ #include #include #include +#include +#include #include #include #include @@ -63,6 +65,7 @@ #include "bnxt_ethtool.h" #include "bnxt_dcb.h" #include "bnxt_xdp.h" +#include "bnxt_ptp.h" #include "bnxt_vfr.h" #include "bnxt_tc.h" #include "bnxt_devlink.h" @@ -418,12 +421,25 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) vlan_tag_flags |= 1 << TX_BD_CFA_META_TPID_SHIFT; } - if (unlikely(skb->no_fcs)) { - lflags |= cpu_to_le32(TX_BD_FLAGS_NO_CRC); - goto normal_tx; + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + + if (ptp && ptp->tx_tstamp_en && !skb_is_gso(skb) && + atomic_dec_if_positive(&ptp->tx_avail) >= 0) { + if (!bnxt_ptp_parse(skb, &ptp->tx_seqid)) { + lflags |= cpu_to_le32(TX_BD_FLAGS_STAMP); + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + } else { + atomic_inc(&bp->ptp_cfg->tx_avail); + } + } } - if (free_size == bp->tx_ring_size && length <= bp->tx_push_thresh) { + if (unlikely(skb->no_fcs)) + lflags |= cpu_to_le32(TX_BD_FLAGS_NO_CRC); + + if (free_size == bp->tx_ring_size && length <= bp->tx_push_thresh && + !lflags) { struct tx_push_buffer *tx_push_buf = txr->tx_push; struct tx_push_bd *tx_push = &tx_push_buf->push_bd; struct tx_bd_ext *tx_push1 = &tx_push->txbd2; @@ -590,6 +606,8 @@ normal_tx: netdev_tx_sent_queue(txq, skb->len); + skb_tx_timestamp(skb); + /* Sync BD data before updating doorbell */ wmb(); @@ -619,6 +637,9 @@ tx_done: return NETDEV_TX_OK; tx_dma_error: + if (BNXT_TX_PTP_IS_SET(lflags)) + atomic_inc(&bp->ptp_cfg->tx_avail); + last_frag = i; /* start back at beginning and unmap skb */ @@ -653,6 +674,7 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) for (i = 0; i < nr_pkts; i++) { struct bnxt_sw_tx_bd *tx_buf; + bool compl_deferred = false; struct sk_buff *skb; int j, last; @@ -679,12 +701,21 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) skb_frag_size(&skb_shinfo(skb)->frags[j]), PCI_DMA_TODEVICE); } + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) { + if (bp->flags & BNXT_FLAG_CHIP_P5) { + if (!bnxt_get_tx_ts_p5(bp, skb)) + compl_deferred = true; + else + atomic_inc(&bp->ptp_cfg->tx_avail); + } + } next_tx_int: cons = NEXT_TX(cons); tx_bytes += skb->len; - dev_kfree_skb_any(skb); + if (!compl_deferred) + dev_kfree_skb_any(skb); } netdev_tx_completed_queue(txq, nr_pkts, tx_bytes); @@ -1706,9 +1737,9 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, u8 *data_ptr, agg_bufs, cmp_type; dma_addr_t dma_addr; struct sk_buff *skb; + u32 flags, misc; void *data; int rc = 0; - u32 misc; rxcmp = (struct rx_cmp *) &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; @@ -1806,7 +1837,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, goto next_rx_no_len; } - len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT; + flags = le32_to_cpu(rxcmp->rx_cmp_len_flags_type); + len = flags >> RX_CMP_LEN_SHIFT; dma_addr = rx_buf->mapping; if (bnxt_rx_xdp(bp, rxr, cons, data, &data_ptr, &len, event)) { @@ -1883,6 +1915,24 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } } + if (unlikely((flags & RX_CMP_FLAGS_ITYPES_MASK) == + RX_CMP_FLAGS_ITYPE_PTP_W_TS)) { + if (bp->flags & BNXT_FLAG_CHIP_P5) { + u32 cmpl_ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp); + u64 ns, ts; + + if (!bnxt_get_rx_ts_p5(bp, &ts, cmpl_ts)) { + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + + spin_lock_bh(&ptp->ptp_lock); + ns = timecounter_cyc2time(&ptp->tc, ts); + spin_unlock_bh(&ptp->ptp_lock); + memset(skb_hwtstamps(skb), 0, + sizeof(*skb_hwtstamps(skb))); + skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(ns); + } + } + } bnxt_deliver_skb(bp, bnapi, skb); rc = 1; @@ -7392,6 +7442,56 @@ hwrm_func_resc_qcaps_exit: return rc; } +/* bp->hwrm_cmd_lock already held. */ +static int __bnxt_hwrm_ptp_qcfg(struct bnxt *bp) +{ + struct hwrm_port_mac_ptp_qcfg_output *resp = bp->hwrm_cmd_resp_addr; + struct hwrm_port_mac_ptp_qcfg_input req = {0}; + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + u8 flags; + int rc; + + if (bp->hwrm_spec_code < 0x10801) { + rc = -ENODEV; + goto no_ptp; + } + + req.port_id = cpu_to_le16(bp->pf.port_id); + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_MAC_PTP_QCFG, -1, -1); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + goto no_ptp; + + flags = resp->flags; + if (!(flags & PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS)) { + rc = -ENODEV; + goto no_ptp; + } + if (!ptp) { + ptp = kzalloc(sizeof(*ptp), GFP_KERNEL); + if (!ptp) + return -ENOMEM; + ptp->bp = bp; + bp->ptp_cfg = ptp; + } + if (flags & PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK) { + ptp->refclk_regs[0] = le32_to_cpu(resp->ts_ref_clock_reg_lower); + ptp->refclk_regs[1] = le32_to_cpu(resp->ts_ref_clock_reg_upper); + } else if (bp->flags & BNXT_FLAG_CHIP_P5) { + ptp->refclk_regs[0] = BNXT_TS_REG_TIMESYNC_TS0_LOWER; + ptp->refclk_regs[1] = BNXT_TS_REG_TIMESYNC_TS0_UPPER; + } else { + rc = -ENODEV; + goto no_ptp; + } + return 0; + +no_ptp: + kfree(ptp); + bp->ptp_cfg = NULL; + return rc; +} + static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) { int rc = 0; @@ -7463,6 +7563,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) bp->flags &= ~BNXT_FLAG_WOL_CAP; if (flags & FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED) bp->flags |= BNXT_FLAG_WOL_CAP; + if (flags & FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED) + __bnxt_hwrm_ptp_qcfg(bp); } else { #ifdef CONFIG_BNXT_SRIOV struct bnxt_vf_info *vf = &bp->vf; @@ -10021,6 +10123,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) } } + bnxt_ptp_start(bp); rc = bnxt_init_nic(bp, irq_re_init); if (rc) { netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc); @@ -10336,6 +10439,12 @@ static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return bnxt_hwrm_port_phy_write(bp, mdio->phy_id, mdio->reg_num, mdio->val_in); + case SIOCSHWTSTAMP: + return bnxt_hwtstamp_set(dev, ifr); + + case SIOCGHWTSTAMP: + return bnxt_hwtstamp_get(dev, ifr); + default: /* do nothing */ break; @@ -12552,6 +12661,8 @@ static void bnxt_remove_one(struct pci_dev *pdev) if (BNXT_PF(bp)) devlink_port_type_clear(&bp->dl_port); + + bnxt_ptp_clear(bp); pci_disable_pcie_error_reporting(pdev); unregister_netdev(dev); clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); @@ -12572,6 +12683,8 @@ static void bnxt_remove_one(struct pci_dev *pdev) bnxt_dcb_free(bp); kfree(bp->edev); bp->edev = NULL; + kfree(bp->ptp_cfg); + bp->ptp_cfg = NULL; kfree(bp->fw_health); bp->fw_health = NULL; bnxt_cleanup_pci(bp); @@ -13133,6 +13246,11 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rc); } + if (bnxt_ptp_init(bp)) { + netdev_warn(dev, "PTP initialization failed.\n"); + kfree(bp->ptp_cfg); + bp->ptp_cfg = NULL; + } bnxt_inv_fw_health_reg(bp); bnxt_dl_register(bp); @@ -13162,6 +13280,8 @@ init_err_pci_clean: bnxt_free_hwrm_short_cmd_req(bp); bnxt_free_hwrm_resources(bp); bnxt_ethtool_free(bp); + kfree(bp->ptp_cfg); + bp->ptp_cfg = NULL; kfree(bp->fw_health); bp->fw_health = NULL; bnxt_cleanup_pci(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 30e47ea343f9..bcf8d00b8c80 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -89,6 +89,8 @@ struct tx_bd_ext { #define TX_BD_CFA_META_KEY_VLAN (1 << 28) }; +#define BNXT_TX_PTP_IS_SET(lflags) ((lflags) & cpu_to_le32(TX_BD_FLAGS_STAMP)) + struct rx_bd { __le32 rx_bd_len_flags_type; #define RX_BD_TYPE (0x3f << 0) @@ -159,6 +161,7 @@ struct rx_cmp { #define RX_CMP_FLAGS_RSS_VALID (1 << 10) #define RX_CMP_FLAGS_UNUSED (1 << 11) #define RX_CMP_FLAGS_ITYPES_SHIFT 12 + #define RX_CMP_FLAGS_ITYPES_MASK 0xf000 #define RX_CMP_FLAGS_ITYPE_UNKNOWN (0 << 12) #define RX_CMP_FLAGS_ITYPE_IP (1 << 12) #define RX_CMP_FLAGS_ITYPE_TCP (2 << 12) @@ -240,7 +243,7 @@ struct rx_cmp_ext { #define RX_CMPL_CFA_CODE_MASK (0xffff << 16) #define RX_CMPL_CFA_CODE_SFT 16 - __le32 rx_cmp_unused3; + __le32 rx_cmp_timestamp; }; #define RX_CMP_L2_ERRORS \ @@ -1362,6 +1365,9 @@ struct bnxt_test_info { #define BNXT_GRC_REG_CHIP_NUM 0x48 #define BNXT_GRC_REG_BASE 0x260000 +#define BNXT_TS_REG_TIMESYNC_TS0_LOWER 0x640180c +#define BNXT_TS_REG_TIMESYNC_TS0_UPPER 0x6401810 + #define BNXT_GRC_BASE_MASK 0xfffff000 #define BNXT_GRC_OFFSET_MASK 0x00000ffc @@ -2042,6 +2048,8 @@ struct bnxt { struct bpf_prog *xdp_prog; + struct bnxt_ptp_cfg *ptp_cfg; + /* devlink interface and vf-rep structs */ struct devlink *dl; struct devlink_port dl_port; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index c664ec52ebcf..786ca51e669b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -19,9 +19,13 @@ #include #include #include +#include +#include +#include #include "bnxt_hsi.h" #include "bnxt.h" #include "bnxt_xdp.h" +#include "bnxt_ptp.h" #include "bnxt_ethtool.h" #include "bnxt_nvm_defs.h" /* NVRAM content constant and structure defs */ #include "bnxt_fw_hdr.h" /* Firmware hdr constant and structure defs */ @@ -3926,6 +3930,35 @@ static int bnxt_get_dump_data(struct net_device *dev, struct ethtool_dump *dump, return 0; } +static int bnxt_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + struct bnxt *bp = netdev_priv(dev); + struct bnxt_ptp_cfg *ptp; + + ptp = bp->ptp_cfg; + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + + info->phc_index = -1; + if (!ptp) + return 0; + + info->so_timestamping |= SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + if (ptp->ptp_clock) + info->phc_index = ptp_clock_index(ptp->ptp_clock); + + info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON); + + info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT); + return 0; +} + void bnxt_ethtool_init(struct bnxt *bp) { struct hwrm_selftest_qlist_output *resp = bp->hwrm_cmd_resp_addr; @@ -4172,6 +4205,7 @@ const struct ethtool_ops bnxt_ethtool_ops = { .nway_reset = bnxt_nway_reset, .set_phys_id = bnxt_set_phys_id, .self_test = bnxt_self_test, + .get_ts_info = bnxt_get_ts_info, .reset = bnxt_reset, .set_dump = bnxt_set_dump, .get_dump_flag = bnxt_get_dump_flag, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 6199f125bc13..3fc6781c5b98 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -189,6 +189,8 @@ struct cmd_nums { #define HWRM_QUEUE_VLANPRI_QCAPS 0x83UL #define HWRM_QUEUE_VLANPRI2PRI_QCFG 0x84UL #define HWRM_QUEUE_VLANPRI2PRI_CFG 0x85UL + #define HWRM_QUEUE_GLOBAL_CFG 0x86UL + #define HWRM_QUEUE_GLOBAL_QCFG 0x87UL #define HWRM_CFA_L2_FILTER_ALLOC 0x90UL #define HWRM_CFA_L2_FILTER_FREE 0x91UL #define HWRM_CFA_L2_FILTER_CFG 0x92UL @@ -250,6 +252,8 @@ struct cmd_nums { #define HWRM_PORT_SFP_SIDEBAND_QCFG 0xd7UL #define HWRM_FW_STATE_UNQUIESCE 0xd8UL #define HWRM_PORT_DSC_DUMP 0xd9UL + #define HWRM_PORT_EP_TX_QCFG 0xdaUL + #define HWRM_PORT_EP_TX_CFG 0xdbUL #define HWRM_TEMP_MONITOR_QUERY 0xe0UL #define HWRM_REG_POWER_QUERY 0xe1UL #define HWRM_CORE_FREQUENCY_QUERY 0xe2UL @@ -305,6 +309,8 @@ struct cmd_nums { #define HWRM_CFA_EEM_OP 0x123UL #define HWRM_CFA_ADV_FLOW_MGNT_QCAPS 0x124UL #define HWRM_CFA_TFLIB 0x125UL + #define HWRM_CFA_LAG_GROUP_MEMBER_RGTR 0x126UL + #define HWRM_CFA_LAG_GROUP_MEMBER_UNRGTR 0x127UL #define HWRM_ENGINE_CKV_STATUS 0x12eUL #define HWRM_ENGINE_CKV_CKEK_ADD 0x12fUL #define HWRM_ENGINE_CKV_CKEK_DELETE 0x130UL @@ -356,6 +362,12 @@ struct cmd_nums { #define HWRM_STAT_EXT_CTX_QUERY 0x199UL #define HWRM_FUNC_SPD_CFG 0x19aUL #define HWRM_FUNC_SPD_QCFG 0x19bUL + #define HWRM_FUNC_PTP_PIN_QCFG 0x19cUL + #define HWRM_FUNC_PTP_PIN_CFG 0x19dUL + #define HWRM_FUNC_PTP_CFG 0x19eUL + #define HWRM_FUNC_PTP_TS_QUERY 0x19fUL + #define HWRM_FUNC_PTP_EXT_CFG 0x1a0UL + #define HWRM_FUNC_PTP_EXT_QCFG 0x1a1UL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -373,6 +385,10 @@ struct cmd_nums { #define HWRM_MFG_PARAM_SEEPROM_SYNC 0x20eUL #define HWRM_MFG_PARAM_SEEPROM_READ 0x20fUL #define HWRM_MFG_PARAM_SEEPROM_HEALTH 0x210UL + #define HWRM_MFG_PRVSN_EXPORT_CSR 0x211UL + #define HWRM_MFG_PRVSN_IMPORT_CERT 0x212UL + #define HWRM_MFG_PRVSN_GET_STATE 0x213UL + #define HWRM_MFG_GET_NVM_MEASUREMENT 0x214UL #define HWRM_TF 0x2bcUL #define HWRM_TF_VERSION_GET 0x2bdUL #define HWRM_TF_SESSION_OPEN 0x2c6UL @@ -385,6 +401,7 @@ struct cmd_nums { #define HWRM_TF_SESSION_RESC_ALLOC 0x2cdUL #define HWRM_TF_SESSION_RESC_FREE 0x2ceUL #define HWRM_TF_SESSION_RESC_FLUSH 0x2cfUL + #define HWRM_TF_SESSION_RESC_INFO 0x2d0UL #define HWRM_TF_TBL_TYPE_GET 0x2daUL #define HWRM_TF_TBL_TYPE_SET 0x2dbUL #define HWRM_TF_TBL_TYPE_BULK_GET 0x2dcUL @@ -399,6 +416,7 @@ struct cmd_nums { #define HWRM_TF_EM_INSERT 0x2eaUL #define HWRM_TF_EM_DELETE 0x2ebUL #define HWRM_TF_EM_HASH_INSERT 0x2ecUL + #define HWRM_TF_EM_MOVE 0x2edUL #define HWRM_TF_TCAM_SET 0x2f8UL #define HWRM_TF_TCAM_GET 0x2f9UL #define HWRM_TF_TCAM_MOVE 0x2faUL @@ -427,6 +445,16 @@ struct cmd_nums { #define HWRM_DBG_QCAPS 0xff20UL #define HWRM_DBG_QCFG 0xff21UL #define HWRM_DBG_CRASHDUMP_MEDIUM_CFG 0xff22UL + #define HWRM_DBG_USEQ_ALLOC 0xff23UL + #define HWRM_DBG_USEQ_FREE 0xff24UL + #define HWRM_DBG_USEQ_FLUSH 0xff25UL + #define HWRM_DBG_USEQ_QCAPS 0xff26UL + #define HWRM_DBG_USEQ_CW_CFG 0xff27UL + #define HWRM_DBG_USEQ_SCHED_CFG 0xff28UL + #define HWRM_DBG_USEQ_RUN 0xff29UL + #define HWRM_DBG_USEQ_DELIVERY_REQ 0xff2aUL + #define HWRM_DBG_USEQ_RESP_HDR 0xff2bUL + #define HWRM_NVM_DEFRAG 0xffecUL #define HWRM_NVM_REQ_ARBITRATION 0xffedUL #define HWRM_NVM_FACTORY_DEFAULTS 0xffeeUL #define HWRM_NVM_VALIDATE_OPTION 0xffefUL @@ -471,6 +499,7 @@ struct ret_codes { #define HWRM_ERR_CODE_HWRM_ERROR 0xfUL #define HWRM_ERR_CODE_BUSY 0x10UL #define HWRM_ERR_CODE_RESOURCE_LOCKED 0x11UL + #define HWRM_ERR_CODE_PF_UNAVAILABLE 0x12UL #define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE 0x8000UL #define HWRM_ERR_CODE_UNKNOWN_ERR 0xfffeUL #define HWRM_ERR_CODE_CMD_NOT_SUPPORTED 0xffffUL @@ -502,8 +531,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 2 -#define HWRM_VERSION_RSVD 16 -#define HWRM_VERSION_STR "1.10.2.16" +#define HWRM_VERSION_RSVD 47 +#define HWRM_VERSION_STR "1.10.2.47" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -604,7 +633,8 @@ struct hwrm_ver_get_output { __le16 roce_fw_build; __le16 roce_fw_patch; __le16 max_ext_req_len; - u8 unused_1[5]; + __le16 max_req_timeout; + u8 unused_1[3]; u8 valid; }; @@ -725,7 +755,10 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE 0x40UL #define ASYNC_EVENT_CMPL_EVENT_ID_PFC_WATCHDOG_CFG_CHANGE 0x41UL #define ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST 0x42UL - #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x43UL + #define ASYNC_EVENT_CMPL_EVENT_ID_PHC_MASTER 0x43UL + #define ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP 0x44UL + #define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT 0x45UL + #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x46UL #define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG 0xfeUL #define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR 0xffUL #define ASYNC_EVENT_CMPL_EVENT_ID_LAST ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR @@ -919,6 +952,8 @@ struct hwrm_async_event_cmpl_vf_cfg_change { #define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_VF_CFG_CHANGE 0x33UL #define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_LAST ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_VF_CFG_CHANGE __le32 event_data2; + #define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA2_VF_ID_MASK 0xffffUL + #define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA2_VF_ID_SFT 0 u8 opaque_v; #define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_V 0x1UL #define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_OPAQUE_MASK 0xfeUL @@ -1074,6 +1109,223 @@ struct hwrm_async_event_cmpl_echo_request { __le32 event_data1; }; +/* hwrm_async_event_cmpl_phc_master (size:128b/16B) */ +struct hwrm_async_event_cmpl_phc_master { + __le16 type; + #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_LAST ASYNC_EVENT_CMPL_PHC_MASTER_TYPE_HWRM_ASYNC_EVENT + __le16 event_id; + #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_ID_PHC_MASTER 0x43UL + #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_ID_LAST ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_ID_PHC_MASTER + __le32 event_data2; + #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_MASTER_FID_MASK 0xffffUL + #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_MASTER_FID_SFT 0 + #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_SEC_FID_MASK 0xffff0000UL + #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA2_PHC_SEC_FID_SFT 16 + u8 opaque_v; + #define ASYNC_EVENT_CMPL_PHC_MASTER_V 0x1UL + #define ASYNC_EVENT_CMPL_PHC_MASTER_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_PHC_MASTER_OPAQUE_SFT 1 + u8 timestamp_lo; + __le16 timestamp_hi; + __le32 event_data1; + #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_MASK 0xfUL + #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_SFT 0 + #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_MASTER 0x1UL + #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_SECONDARY 0x2UL + #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_FAILOVER 0x3UL + #define ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_LAST ASYNC_EVENT_CMPL_PHC_MASTER_EVENT_DATA1_FLAGS_PHC_FAILOVER +}; + +/* hwrm_async_event_cmpl_pps_timestamp (size:128b/16B) */ +struct hwrm_async_event_cmpl_pps_timestamp { + __le16 type; + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_LAST ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_HWRM_ASYNC_EVENT + __le16 event_id; + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_PPS_TIMESTAMP 0x44UL + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_LAST ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_PPS_TIMESTAMP + __le32 event_data2; + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE 0x1UL + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_INTERNAL 0x0UL + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_EXTERNAL 0x1UL + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_LAST ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_EXTERNAL + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PIN_NUMBER_MASK 0xeUL + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PIN_NUMBER_SFT 1 + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PPS_TIMESTAMP_UPPER_MASK 0xffff0UL + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PPS_TIMESTAMP_UPPER_SFT 4 + u8 opaque_v; + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_V 0x1UL + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_OPAQUE_SFT 1 + u8 timestamp_lo; + __le16 timestamp_hi; + __le32 event_data1; + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA1_PPS_TIMESTAMP_LOWER_MASK 0xffffffffUL + #define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA1_PPS_TIMESTAMP_LOWER_SFT 0 +}; + +/* hwrm_async_event_cmpl_error_report (size:128b/16B) */ +struct hwrm_async_event_cmpl_error_report { + __le16 type; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_HWRM_ASYNC_EVENT + __le16 event_id; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_ERROR_REPORT 0x45UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_ERROR_REPORT + __le32 event_data2; + u8 opaque_v; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_V 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_OPAQUE_SFT 1 + u8 timestamp_lo; + __le16 timestamp_hi; + __le32 event_data1; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_DATA1_ERROR_TYPE_SFT 0 +}; + +/* hwrm_async_event_cmpl_hwrm_error (size:128b/16B) */ +struct hwrm_async_event_cmpl_hwrm_error { + __le16 type; + #define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_HWRM_ASYNC_EVENT + __le16 event_id; + #define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_HWRM_ERROR 0xffUL + #define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_LAST ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_HWRM_ERROR + __le32 event_data2; + #define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_MASK 0xffUL + #define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_SFT 0 + #define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_WARNING 0x0UL + #define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_NONFATAL 0x1UL + #define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_FATAL 0x2UL + #define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_LAST ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_FATAL + u8 opaque_v; + #define ASYNC_EVENT_CMPL_HWRM_ERROR_V 0x1UL + #define ASYNC_EVENT_CMPL_HWRM_ERROR_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_HWRM_ERROR_OPAQUE_SFT 1 + u8 timestamp_lo; + __le16 timestamp_hi; + __le32 event_data1; + #define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA1_TIMESTAMP 0x1UL +}; + +/* hwrm_async_event_cmpl_error_report_base (size:128b/16B) */ +struct hwrm_async_event_cmpl_error_report_base { + __le16 type; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_HWRM_ASYNC_EVENT + __le16 event_id; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_ERROR_REPORT 0x45UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_ERROR_REPORT + __le32 event_data2; + u8 opaque_v; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_V 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_OPAQUE_SFT 1 + u8 timestamp_lo; + __le16 timestamp_hi; + __le32 event_data1; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED 0x0UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL 0x2UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM 0x3UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM +}; + +/* hwrm_async_event_cmpl_error_report_pause_storm (size:128b/16B) */ +struct hwrm_async_event_cmpl_error_report_pause_storm { + __le16 type; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_HWRM_ASYNC_EVENT + __le16 event_id; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_ERROR_REPORT 0x45UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_ERROR_REPORT + __le32 event_data2; + u8 opaque_v; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_V 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_OPAQUE_SFT 1 + u8 timestamp_lo; + __le16 timestamp_hi; + __le32 event_data1; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM +}; + +/* hwrm_async_event_cmpl_error_report_invalid_signal (size:128b/16B) */ +struct hwrm_async_event_cmpl_error_report_invalid_signal { + __le16 type; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_HWRM_ASYNC_EVENT + __le16 event_id; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_ERROR_REPORT 0x45UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_ERROR_REPORT + __le32 event_data2; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_SFT 0 + u8 opaque_v; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_V 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_OPAQUE_SFT 1 + u8 timestamp_lo; + __le16 timestamp_hi; + __le32 event_data1; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL 0x2UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL +}; + +/* hwrm_async_event_cmpl_error_report_nvm (size:128b/16B) */ +struct hwrm_async_event_cmpl_error_report_nvm { + __le16 type; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_HWRM_ASYNC_EVENT + __le16 event_id; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_ERROR_REPORT 0x45UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_ERROR_REPORT + __le32 event_data2; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA2_ERR_ADDR_MASK 0xffffffffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA2_ERR_ADDR_SFT 0 + u8 opaque_v; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_V 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_OPAQUE_SFT 1 + u8 timestamp_lo; + __le16 timestamp_hi; + __le32 event_data1; + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_NVM_ERROR 0x3UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_NVM_ERROR + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_MASK 0xff00UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_SFT 8 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_WRITE (0x1UL << 8) + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE (0x2UL << 8) + #define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE +}; + /* hwrm_func_reset_input (size:192b/24B) */ struct hwrm_func_reset_input { __le16 req_type; @@ -1302,7 +1554,7 @@ struct hwrm_func_qcaps_output { __le32 max_flow_id; __le32 max_hw_ring_grps; __le16 max_sp_tx_rings; - u8 unused_0[2]; + __le16 max_msix_vfs; __le32 flags_ext; #define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_MARK_SUPPORTED 0x1UL #define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_STATS_SUPPORTED 0x2UL @@ -1320,6 +1572,14 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_FLAGS_EXT_NVM_OPTION_ACTION_SUPPORTED 0x2000UL #define FUNC_QCAPS_RESP_FLAGS_EXT_BD_METADATA_SUPPORTED 0x4000UL #define FUNC_QCAPS_RESP_FLAGS_EXT_ECHO_REQUEST_SUPPORTED 0x8000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_NPAR_1_2_SUPPORTED 0x10000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PTM_SUPPORTED 0x20000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PPS_SUPPORTED 0x40000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_VF_CFG_ASYNC_FOR_PF_SUPPORTED 0x80000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_PARTITION_BW_SUPPORTED 0x100000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_DFLT_VLAN_TPID_PCP_SUPPORTED 0x200000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_KTLS_SUPPORTED 0x400000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_EP_RATE_CONTROL 0x800000UL u8 max_schqs; u8 mpc_chnls_cap; #define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TCE 0x1UL @@ -1342,7 +1602,7 @@ struct hwrm_func_qcfg_input { u8 unused_0[6]; }; -/* hwrm_func_qcfg_output (size:768b/96B) */ +/* hwrm_func_qcfg_output (size:832b/104B) */ struct hwrm_func_qcfg_output { __le16 error_code; __le16 req_type; @@ -1366,6 +1626,7 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_FLAGS_RING_MONITOR_ENABLED 0x800UL #define FUNC_QCFG_RESP_FLAGS_FAST_RESET_ALLOWED 0x1000UL #define FUNC_QCFG_RESP_FLAGS_MULTI_ROOT 0x2000UL + #define FUNC_QCFG_RESP_FLAGS_ENABLE_RDMA_SRIOV 0x4000UL u8 mac_address[6]; __le16 pci_id; __le16 alloc_rsscos_ctx; @@ -1374,7 +1635,7 @@ struct hwrm_func_qcfg_output { __le16 alloc_rx_rings; __le16 alloc_l2_ctx; __le16 alloc_vnics; - __le16 mtu; + __le16 admin_mtu; __le16 mru; __le16 stat_ctx_id; u8 port_partition_type; @@ -1383,6 +1644,7 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0 0x2UL #define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5 0x3UL #define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0 0x4UL + #define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_2 0x5UL #define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN 0xffUL #define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_LAST FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN u8 port_pf_cnt; @@ -1463,11 +1725,35 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_MPC_CHNLS_TE_CFA_ENABLED 0x4UL #define FUNC_QCFG_RESP_MPC_CHNLS_RE_CFA_ENABLED 0x8UL #define FUNC_QCFG_RESP_MPC_CHNLS_PRIMATE_ENABLED 0x10UL - u8 unused_2[6]; + u8 unused_2[3]; + __le32 partition_min_bw; + #define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_MASK 0xfffffffUL + #define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_SFT 0 + #define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE 0x10000000UL + #define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BITS (0x0UL << 28) + #define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BYTES (0x1UL << 28) + #define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_LAST FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BYTES + #define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_MASK 0xe0000000UL + #define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_SFT 29 + #define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100 (0x1UL << 29) + #define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_LAST FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100 + __le32 partition_max_bw; + #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_MASK 0xfffffffUL + #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_SFT 0 + #define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE 0x10000000UL + #define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BITS (0x0UL << 28) + #define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BYTES (0x1UL << 28) + #define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_LAST FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BYTES + #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_MASK 0xe0000000UL + #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_SFT 29 + #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 (0x1UL << 29) + #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 + __le16 host_mtu; + u8 unused_3; u8 valid; }; -/* hwrm_func_cfg_input (size:768b/96B) */ +/* hwrm_func_cfg_input (size:832b/104B) */ struct hwrm_func_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -1504,7 +1790,7 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_FLAGS_BD_METADATA_ENABLE 0x20000000UL #define FUNC_CFG_REQ_FLAGS_BD_METADATA_DISABLE 0x40000000UL __le32 enables; - #define FUNC_CFG_REQ_ENABLES_MTU 0x1UL + #define FUNC_CFG_REQ_ENABLES_ADMIN_MTU 0x1UL #define FUNC_CFG_REQ_ENABLES_MRU 0x2UL #define FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS 0x4UL #define FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS 0x8UL @@ -1530,7 +1816,11 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_ENABLES_HOT_RESET_IF_SUPPORT 0x800000UL #define FUNC_CFG_REQ_ENABLES_SCHQ_ID 0x1000000UL #define FUNC_CFG_REQ_ENABLES_MPC_CHNLS 0x2000000UL - __le16 mtu; + #define FUNC_CFG_REQ_ENABLES_PARTITION_MIN_BW 0x4000000UL + #define FUNC_CFG_REQ_ENABLES_PARTITION_MAX_BW 0x8000000UL + #define FUNC_CFG_REQ_ENABLES_TPID 0x10000000UL + #define FUNC_CFG_REQ_ENABLES_HOST_MTU 0x20000000UL + __le16 admin_mtu; __le16 mru; __le16 num_rsscos_ctxs; __le16 num_cmpl_rings; @@ -1615,7 +1905,30 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_MPC_CHNLS_RE_CFA_DISABLE 0x80UL #define FUNC_CFG_REQ_MPC_CHNLS_PRIMATE_ENABLE 0x100UL #define FUNC_CFG_REQ_MPC_CHNLS_PRIMATE_DISABLE 0x200UL - u8 unused_0[4]; + __le32 partition_min_bw; + #define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_MASK 0xfffffffUL + #define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_SFT 0 + #define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE 0x10000000UL + #define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BITS (0x0UL << 28) + #define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BYTES (0x1UL << 28) + #define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_LAST FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BYTES + #define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_MASK 0xe0000000UL + #define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_SFT 29 + #define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100 (0x1UL << 29) + #define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_LAST FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100 + __le32 partition_max_bw; + #define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_MASK 0xfffffffUL + #define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_SFT 0 + #define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE 0x10000000UL + #define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BITS (0x0UL << 28) + #define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BYTES (0x1UL << 28) + #define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_LAST FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BYTES + #define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_MASK 0xe0000000UL + #define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_SFT 29 + #define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 (0x1UL << 29) + #define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 + __be16 tpid; + __le16 host_mtu; }; /* hwrm_func_cfg_output (size:128b/16B) */ @@ -1777,14 +2090,15 @@ struct hwrm_func_drv_rgtr_input { __le16 target_id; __le64 resp_addr; __le32 flags; - #define FUNC_DRV_RGTR_REQ_FLAGS_FWD_ALL_MODE 0x1UL - #define FUNC_DRV_RGTR_REQ_FLAGS_FWD_NONE_MODE 0x2UL - #define FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE 0x4UL - #define FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE 0x8UL - #define FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT 0x10UL - #define FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT 0x20UL - #define FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT 0x40UL - #define FUNC_DRV_RGTR_REQ_FLAGS_FAST_RESET_SUPPORT 0x80UL + #define FUNC_DRV_RGTR_REQ_FLAGS_FWD_ALL_MODE 0x1UL + #define FUNC_DRV_RGTR_REQ_FLAGS_FWD_NONE_MODE 0x2UL + #define FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE 0x4UL + #define FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE 0x8UL + #define FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT 0x10UL + #define FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT 0x20UL + #define FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT 0x40UL + #define FUNC_DRV_RGTR_REQ_FLAGS_FAST_RESET_SUPPORT 0x80UL + #define FUNC_DRV_RGTR_REQ_FLAGS_RSS_STRICT_HASH_TYPE_SUPPORT 0x100UL __le32 enables; #define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE 0x1UL #define FUNC_DRV_RGTR_REQ_ENABLES_VER 0x2UL @@ -2047,7 +2361,7 @@ struct hwrm_func_backing_store_qcaps_input { __le64 resp_addr; }; -/* hwrm_func_backing_store_qcaps_output (size:704b/88B) */ +/* hwrm_func_backing_store_qcaps_output (size:832b/104B) */ struct hwrm_func_backing_store_qcaps_output { __le16 error_code; __le16 req_type; @@ -2085,6 +2399,8 @@ struct hwrm_func_backing_store_qcaps_output { #define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_VNIC 0x8UL #define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_STAT 0x10UL #define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_MRAV 0x20UL + #define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_TKC 0x40UL + #define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_RKC 0x80UL u8 qp_init_offset; u8 srq_init_offset; u8 cq_init_offset; @@ -2093,7 +2409,13 @@ struct hwrm_func_backing_store_qcaps_output { u8 stat_init_offset; u8 mrav_init_offset; u8 tqm_fp_rings_count_ext; - u8 rsvd[5]; + u8 tkc_init_offset; + u8 rkc_init_offset; + __le16 tkc_entry_size; + __le16 rkc_entry_size; + __le32 tkc_max_entries; + __le32 rkc_max_entries; + u8 rsvd[7]; u8 valid; }; @@ -2120,7 +2442,7 @@ struct tqm_fp_ring_cfg { __le64 tqm_ring_page_dir; }; -/* hwrm_func_backing_store_cfg_input (size:2432b/304B) */ +/* hwrm_func_backing_store_cfg_input (size:2688b/336B) */ struct hwrm_func_backing_store_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -2150,6 +2472,8 @@ struct hwrm_func_backing_store_cfg_input { #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING8 0x10000UL #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING9 0x20000UL #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING10 0x40000UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TKC 0x80000UL + #define FUNC_BACKING_STORE_CFG_REQ_ENABLES_RKC 0x100000UL u8 qpc_pg_size_qpc_lvl; #define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_MASK 0xfUL #define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_SFT 0 @@ -2508,6 +2832,45 @@ struct hwrm_func_backing_store_cfg_input { u8 ring10_unused[3]; __le32 tqm_ring10_num_entries; __le64 tqm_ring10_page_dir; + __le32 tkc_num_entries; + __le32 rkc_num_entries; + __le64 tkc_page_dir; + __le64 rkc_page_dir; + __le16 tkc_entry_size; + __le16 rkc_entry_size; + u8 tkc_pg_size_tkc_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_1G + u8 rkc_pg_size_rkc_lvl; + #define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_MASK 0xfUL + #define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_SFT 0 + #define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_0 0x0UL + #define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_1 0x1UL + #define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_2 0x2UL + #define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LAST FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_2 + #define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_MASK 0xf0UL + #define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_SFT 4 + #define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_4K (0x0UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_8K (0x1UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_64K (0x2UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_2M (0x3UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_8M (0x4UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_1G (0x5UL << 4) + #define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_LAST FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_1G + u8 rsvd[2]; }; /* hwrm_func_backing_store_cfg_output (size:128b/16B) */ @@ -2634,6 +2997,212 @@ struct hwrm_func_echo_response_output { u8 valid; }; +/* hwrm_func_ptp_pin_qcfg_input (size:192b/24B) */ +struct hwrm_func_ptp_pin_qcfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + u8 unused_0[8]; +}; + +/* hwrm_func_ptp_pin_qcfg_output (size:128b/16B) */ +struct hwrm_func_ptp_pin_qcfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 num_pins; + u8 state; + #define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN0_ENABLED 0x1UL + #define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN1_ENABLED 0x2UL + #define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN2_ENABLED 0x4UL + #define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN3_ENABLED 0x8UL + u8 pin0_usage; + #define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_NONE 0x0UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_PPS_IN 0x1UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_PPS_OUT 0x2UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_IN 0x3UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_OUT 0x4UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_LAST FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_OUT + u8 pin1_usage; + #define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_NONE 0x0UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_PPS_IN 0x1UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_PPS_OUT 0x2UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_IN 0x3UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_OUT 0x4UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_LAST FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_OUT + u8 pin2_usage; + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_NONE 0x0UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_IN 0x1UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_OUT 0x2UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_IN 0x3UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_OUT 0x4UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_LAST FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_OUT + u8 pin3_usage; + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_NONE 0x0UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_IN 0x1UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_OUT 0x2UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_IN 0x3UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_OUT 0x4UL + #define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_LAST FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_OUT + u8 unused_0; + u8 valid; +}; + +/* hwrm_func_ptp_pin_cfg_input (size:256b/32B) */ +struct hwrm_func_ptp_pin_cfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le32 enables; + #define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN0_STATE 0x1UL + #define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN0_USAGE 0x2UL + #define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN1_STATE 0x4UL + #define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN1_USAGE 0x8UL + #define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN2_STATE 0x10UL + #define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN2_USAGE 0x20UL + #define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN3_STATE 0x40UL + #define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN3_USAGE 0x80UL + u8 pin0_state; + #define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_DISABLED 0x0UL + #define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_ENABLED 0x1UL + #define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_LAST FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_ENABLED + u8 pin0_usage; + #define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_NONE 0x0UL + #define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_PPS_IN 0x1UL + #define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_PPS_OUT 0x2UL + #define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_IN 0x3UL + #define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_OUT 0x4UL + #define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_LAST FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_OUT + u8 pin1_state; + #define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_DISABLED 0x0UL + #define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_ENABLED 0x1UL + #define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_LAST FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_ENABLED + u8 pin1_usage; + #define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_NONE 0x0UL + #define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_PPS_IN 0x1UL + #define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_PPS_OUT 0x2UL + #define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_IN 0x3UL + #define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_OUT 0x4UL + #define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_LAST FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_OUT + u8 pin2_state; + #define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_DISABLED 0x0UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_ENABLED 0x1UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_LAST FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_ENABLED + u8 pin2_usage; + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_NONE 0x0UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_IN 0x1UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_OUT 0x2UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_IN 0x3UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_OUT 0x4UL + #define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_LAST FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_OUT + u8 pin3_state; + #define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_DISABLED 0x0UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_ENABLED 0x1UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_LAST FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_ENABLED + u8 pin3_usage; + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_NONE 0x0UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_IN 0x1UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_OUT 0x2UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_IN 0x3UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_OUT 0x4UL + #define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_LAST FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_OUT + u8 unused_0[4]; +}; + +/* hwrm_func_ptp_pin_cfg_output (size:128b/16B) */ +struct hwrm_func_ptp_pin_cfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_0[7]; + u8 valid; +}; + +/* hwrm_func_ptp_cfg_input (size:320b/40B) */ +struct hwrm_func_ptp_cfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 enables; + #define FUNC_PTP_CFG_REQ_ENABLES_PTP_PPS_EVENT 0x1UL + #define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_DLL_SOURCE 0x2UL + #define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_DLL_PHASE 0x4UL + #define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PERIOD 0x8UL + #define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_UP 0x10UL + #define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PHASE 0x20UL + u8 ptp_pps_event; + #define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_INTERNAL 0x1UL + #define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_EXTERNAL 0x2UL + u8 ptp_freq_adj_dll_source; + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_NONE 0x0UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_0 0x1UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_1 0x2UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_2 0x3UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_3 0x4UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_0 0x5UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_1 0x6UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_2 0x7UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_3 0x8UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_INVALID 0xffUL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_LAST FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_INVALID + u8 ptp_freq_adj_dll_phase; + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_NONE 0x0UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_4K 0x1UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_8K 0x2UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_10M 0x3UL + #define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_LAST FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_10M + u8 unused_0[3]; + __le32 ptp_freq_adj_ext_period; + __le32 ptp_freq_adj_ext_up; + __le32 ptp_freq_adj_ext_phase_lower; + __le32 ptp_freq_adj_ext_phase_upper; +}; + +/* hwrm_func_ptp_cfg_output (size:128b/16B) */ +struct hwrm_func_ptp_cfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_0[7]; + u8 valid; +}; + +/* hwrm_func_ptp_ts_query_input (size:192b/24B) */ +struct hwrm_func_ptp_ts_query_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le32 flags; + #define FUNC_PTP_TS_QUERY_REQ_FLAGS_PPS_TIME 0x1UL + #define FUNC_PTP_TS_QUERY_REQ_FLAGS_PTM_TIME 0x2UL + u8 unused_0[4]; +}; + +/* hwrm_func_ptp_ts_query_output (size:320b/40B) */ +struct hwrm_func_ptp_ts_query_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le64 pps_event_ts; + __le64 ptm_res_local_ts; + __le64 ptm_pmstr_ts; + __le32 ptm_mstr_prop_dly; + u8 unused_0[3]; + u8 valid; +}; + /* hwrm_func_drv_if_change_input (size:192b/24B) */ struct hwrm_func_drv_if_change_input { __le16 req_type; @@ -3156,6 +3725,7 @@ struct hwrm_port_mac_cfg_input { #define PORT_MAC_CFG_REQ_ENABLES_TX_TS_CAPTURE_PTP_MSG_TYPE 0x80UL #define PORT_MAC_CFG_REQ_ENABLES_COS_FIELD_CFG 0x100UL #define PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB 0x200UL + #define PORT_MAC_CFG_REQ_ENABLES_PTP_ADJ_PHASE 0x400UL __le16 port_id; u8 ipg; u8 lpbk; @@ -3188,8 +3758,8 @@ struct hwrm_port_mac_cfg_input { #define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_MASK 0xe0UL #define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_SFT 5 u8 unused_0[3]; - __s32 ptp_freq_adj_ppb; - u8 unused_1[4]; + __le32 ptp_freq_adj_ppb; + __le32 ptp_adj_phase; }; /* hwrm_port_mac_cfg_output (size:128b/16B) */ @@ -3221,16 +3791,17 @@ struct hwrm_port_mac_ptp_qcfg_input { u8 unused_0[6]; }; -/* hwrm_port_mac_ptp_qcfg_output (size:640b/80B) */ +/* hwrm_port_mac_ptp_qcfg_output (size:704b/88B) */ struct hwrm_port_mac_ptp_qcfg_output { __le16 error_code; __le16 req_type; __le16 seq_id; __le16 resp_len; u8 flags; - #define PORT_MAC_PTP_QCFG_RESP_FLAGS_DIRECT_ACCESS 0x1UL - #define PORT_MAC_PTP_QCFG_RESP_FLAGS_ONE_STEP_TX_TS 0x4UL - #define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS 0x8UL + #define PORT_MAC_PTP_QCFG_RESP_FLAGS_DIRECT_ACCESS 0x1UL + #define PORT_MAC_PTP_QCFG_RESP_FLAGS_ONE_STEP_TX_TS 0x4UL + #define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS 0x8UL + #define PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK 0x10UL u8 unused_0[3]; __le32 rx_ts_reg_off_lower; __le32 rx_ts_reg_off_upper; @@ -3247,6 +3818,8 @@ struct hwrm_port_mac_ptp_qcfg_output { __le32 tx_ts_reg_off_seq_id; __le32 tx_ts_reg_off_fifo; __le32 tx_ts_reg_off_granularity; + __le32 ts_ref_clock_reg_lower; + __le32 ts_ref_clock_reg_upper; u8 unused_1[7]; u8 valid; }; @@ -3647,7 +4220,7 @@ struct hwrm_port_lpbk_clr_stats_output { u8 valid; }; -/* hwrm_port_ts_query_input (size:192b/24B) */ +/* hwrm_port_ts_query_input (size:256b/32B) */ struct hwrm_port_ts_query_input { __le16 req_type; __le16 cmpl_ring; @@ -3662,6 +4235,11 @@ struct hwrm_port_ts_query_input { #define PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME 0x2UL __le16 port_id; u8 unused_0[2]; + __le16 enables; + #define PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT 0x1UL + #define PORT_TS_QUERY_REQ_ENABLES_PTP_SEQ_ID 0x2UL + __le16 ts_req_timeout; + __le32 ptp_seq_id; }; /* hwrm_port_ts_query_output (size:192b/24B) */ @@ -4215,7 +4793,8 @@ struct hwrm_queue_qportcfg_output { u8 max_configurable_lossless_queues; u8 queue_cfg_allowed; u8 queue_cfg_info; - #define QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG 0x1UL + #define QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG 0x1UL + #define QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_USE_PROFILE_TYPE 0x2UL u8 queue_pfcenable_cfg_allowed; u8 queue_pri2cos_cfg_allowed; u8 queue_cos2bw_cfg_allowed; @@ -5467,6 +6046,7 @@ struct hwrm_vnic_qcaps_output { #define VNIC_QCAPS_RESP_FLAGS_VNIC_STATE_CAP 0x400UL #define VNIC_QCAPS_RESP_FLAGS_VIRTIO_NET_VNIC_ALLOC_CAP 0x800UL #define VNIC_QCAPS_RESP_FLAGS_METADATA_FORMAT_CAP 0x1000UL + #define VNIC_QCAPS_RESP_FLAGS_RSS_STRICT_HASH_TYPE_CAP 0x2000UL __le16 max_aggs_supported; u8 unused_1[5]; u8 valid; @@ -7224,6 +7804,7 @@ struct hwrm_cfa_adv_flow_mgnt_qcaps_output { #define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_ETHERTYPE_IP_SUPPORTED 0x4000UL #define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_TRUFLOW_CAPABLE 0x8000UL #define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_L2_FILTER_TRAFFIC_TYPE_L2_ROCE_SUPPORTED 0x10000UL + #define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_LAG_SUPPORTED 0x20000UL u8 unused_0[3]; u8 valid; }; @@ -7914,11 +8495,14 @@ struct hwrm_temp_monitor_query_output { u8 phy_temp; u8 om_temp; u8 flags; - #define TEMP_MONITOR_QUERY_RESP_FLAGS_TEMP_NOT_AVAILABLE 0x1UL - #define TEMP_MONITOR_QUERY_RESP_FLAGS_PHY_TEMP_NOT_AVAILABLE 0x2UL - #define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_NOT_PRESENT 0x4UL - #define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_TEMP_NOT_AVAILABLE 0x8UL - u8 unused_0[3]; + #define TEMP_MONITOR_QUERY_RESP_FLAGS_TEMP_NOT_AVAILABLE 0x1UL + #define TEMP_MONITOR_QUERY_RESP_FLAGS_PHY_TEMP_NOT_AVAILABLE 0x2UL + #define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_NOT_PRESENT 0x4UL + #define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_TEMP_NOT_AVAILABLE 0x8UL + #define TEMP_MONITOR_QUERY_RESP_FLAGS_EXT_TEMP_FIELDS_AVAILABLE 0x10UL + u8 temp2; + u8 phy_temp2; + u8 om_temp2; u8 valid; }; @@ -8109,6 +8693,7 @@ struct hwrm_dbg_qcaps_output { #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_NVM 0x1UL #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR 0x2UL #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR 0x4UL + #define DBG_QCAPS_RESP_FLAGS_USEQ 0x8UL u8 unused_1[3]; u8 valid; }; @@ -8632,10 +9217,11 @@ struct hwrm_nvm_install_update_output { /* hwrm_nvm_install_update_cmd_err (size:64b/8B) */ struct hwrm_nvm_install_update_cmd_err { u8 code; - #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_UNKNOWN 0x0UL - #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR 0x1UL - #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_SPACE 0x2UL - #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_LAST NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_SPACE + #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_UNKNOWN 0x0UL + #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR 0x1UL + #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_SPACE 0x2UL + #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_ANTI_ROLLBACK 0x3UL + #define NVM_INSTALL_UPDATE_CMD_ERR_CODE_LAST NVM_INSTALL_UPDATE_CMD_ERR_CODE_ANTI_ROLLBACK u8 unused_0[7]; }; @@ -8876,6 +9462,7 @@ struct fw_status_reg { #define FW_STATUS_REG_CRASHDUMP_COMPLETE 0x80000UL #define FW_STATUS_REG_SHUTDOWN 0x100000UL #define FW_STATUS_REG_CRASHED_NO_MASTER 0x200000UL + #define FW_STATUS_REG_RECOVERING 0x400000UL }; /* hcomm_status (size:64b/8B) */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c new file mode 100644 index 000000000000..f698b6bd4ff8 --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -0,0 +1,473 @@ +/* Broadcom NetXtreme-C/E network driver. + * + * Copyright (c) 2021 Broadcom Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "bnxt_hsi.h" +#include "bnxt.h" +#include "bnxt_ptp.h" + +int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id) +{ + unsigned int ptp_class; + struct ptp_header *hdr; + + ptp_class = ptp_classify_raw(skb); + + switch (ptp_class & PTP_CLASS_VMASK) { + case PTP_CLASS_V1: + case PTP_CLASS_V2: + hdr = ptp_parse_header(skb, ptp_class); + if (!hdr) + return -EINVAL; + + *seq_id = ntohs(hdr->sequence_id); + return 0; + default: + return -ERANGE; + } +} + +static int bnxt_ptp_settime(struct ptp_clock_info *ptp_info, + const struct timespec64 *ts) +{ + struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg, + ptp_info); + u64 ns = timespec64_to_ns(ts); + + spin_lock_bh(&ptp->ptp_lock); + timecounter_init(&ptp->tc, &ptp->cc, ns); + spin_unlock_bh(&ptp->ptp_lock); + return 0; +} + +/* Caller holds ptp_lock */ +static u64 bnxt_refclk_read(struct bnxt *bp, struct ptp_system_timestamp *sts) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + u64 ns; + + ptp_read_system_prets(sts); + ns = readl(bp->bar0 + ptp->refclk_mapped_regs[0]); + ptp_read_system_postts(sts); + ns |= (u64)readl(bp->bar0 + ptp->refclk_mapped_regs[1]) << 32; + return ns; +} + +static void bnxt_ptp_get_current_time(struct bnxt *bp) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + + if (!ptp) + return; + spin_lock_bh(&ptp->ptp_lock); + WRITE_ONCE(ptp->old_time, ptp->current_time); + ptp->current_time = bnxt_refclk_read(bp, NULL); + spin_unlock_bh(&ptp->ptp_lock); +} + +static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts) +{ + struct hwrm_port_ts_query_output *resp = bp->hwrm_cmd_resp_addr; + struct hwrm_port_ts_query_input req = {0}; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_TS_QUERY, -1, -1); + req.flags = cpu_to_le32(flags); + if ((flags & PORT_TS_QUERY_REQ_FLAGS_PATH) == + PORT_TS_QUERY_REQ_FLAGS_PATH_TX) { + req.enables = cpu_to_le16(BNXT_PTP_QTS_TX_ENABLES); + req.ptp_seq_id = cpu_to_le32(bp->ptp_cfg->tx_seqid); + req.ts_req_timeout = cpu_to_le16(BNXT_PTP_QTS_TIMEOUT); + } + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc) + *ts = le64_to_cpu(resp->ptp_msg_ts); + mutex_unlock(&bp->hwrm_cmd_lock); + return rc; +} + +static int bnxt_ptp_gettimex(struct ptp_clock_info *ptp_info, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg, + ptp_info); + u64 ns, cycles; + + spin_lock_bh(&ptp->ptp_lock); + cycles = bnxt_refclk_read(ptp->bp, sts); + ns = timecounter_cyc2time(&ptp->tc, cycles); + spin_unlock_bh(&ptp->ptp_lock); + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int bnxt_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta) +{ + struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg, + ptp_info); + + spin_lock_bh(&ptp->ptp_lock); + timecounter_adjtime(&ptp->tc, delta); + spin_unlock_bh(&ptp->ptp_lock); + return 0; +} + +static int bnxt_ptp_adjfreq(struct ptp_clock_info *ptp_info, s32 ppb) +{ + struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg, + ptp_info); + struct hwrm_port_mac_cfg_input req = {0}; + struct bnxt *bp = ptp->bp; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_MAC_CFG, -1, -1); + req.ptp_freq_adj_ppb = cpu_to_le32(ppb); + req.enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB); + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + netdev_err(ptp->bp->dev, + "ptp adjfreq failed. rc = %d\n", rc); + return rc; +} + +static int bnxt_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + return -EOPNOTSUPP; +} + +static int bnxt_hwrm_ptp_cfg(struct bnxt *bp) +{ + struct hwrm_port_mac_cfg_input req = {0}; + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + u32 flags = 0; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_MAC_CFG, -1, -1); + if (ptp->rx_filter) + flags |= PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_ENABLE; + else + flags |= PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_DISABLE; + if (ptp->tx_tstamp_en) + flags |= PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_ENABLE; + else + flags |= PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_DISABLE; + req.flags = cpu_to_le32(flags); + req.enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_RX_TS_CAPTURE_PTP_MSG_TYPE); + req.rx_ts_capture_ptp_msg_type = cpu_to_le16(ptp->rxctl); + + return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); +} + +int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) +{ + struct bnxt *bp = netdev_priv(dev); + struct hwtstamp_config stmpconf; + struct bnxt_ptp_cfg *ptp; + u16 old_rxctl; + int old_rx_filter, rc; + u8 old_tx_tstamp_en; + + ptp = bp->ptp_cfg; + if (!ptp) + return -EOPNOTSUPP; + + if (copy_from_user(&stmpconf, ifr->ifr_data, sizeof(stmpconf))) + return -EFAULT; + + if (stmpconf.flags) + return -EINVAL; + + if (stmpconf.tx_type != HWTSTAMP_TX_ON && + stmpconf.tx_type != HWTSTAMP_TX_OFF) + return -ERANGE; + + old_rx_filter = ptp->rx_filter; + old_rxctl = ptp->rxctl; + old_tx_tstamp_en = ptp->tx_tstamp_en; + switch (stmpconf.rx_filter) { + case HWTSTAMP_FILTER_NONE: + ptp->rxctl = 0; + ptp->rx_filter = HWTSTAMP_FILTER_NONE; + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + ptp->rxctl = BNXT_PTP_MSG_EVENTS; + ptp->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + break; + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + ptp->rxctl = BNXT_PTP_MSG_SYNC; + ptp->rx_filter = HWTSTAMP_FILTER_PTP_V2_SYNC; + break; + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + ptp->rxctl = BNXT_PTP_MSG_DELAY_REQ; + ptp->rx_filter = HWTSTAMP_FILTER_PTP_V2_DELAY_REQ; + break; + default: + return -ERANGE; + } + + if (stmpconf.tx_type == HWTSTAMP_TX_ON) + ptp->tx_tstamp_en = 1; + else + ptp->tx_tstamp_en = 0; + + rc = bnxt_hwrm_ptp_cfg(bp); + if (rc) + goto ts_set_err; + + stmpconf.rx_filter = ptp->rx_filter; + return copy_to_user(ifr->ifr_data, &stmpconf, sizeof(stmpconf)) ? + -EFAULT : 0; + +ts_set_err: + ptp->rx_filter = old_rx_filter; + ptp->rxctl = old_rxctl; + ptp->tx_tstamp_en = old_tx_tstamp_en; + return rc; +} + +int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) +{ + struct bnxt *bp = netdev_priv(dev); + struct hwtstamp_config stmpconf; + struct bnxt_ptp_cfg *ptp; + + ptp = bp->ptp_cfg; + if (!ptp) + return -EOPNOTSUPP; + + stmpconf.flags = 0; + stmpconf.tx_type = ptp->tx_tstamp_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + + stmpconf.rx_filter = ptp->rx_filter; + return copy_to_user(ifr->ifr_data, &stmpconf, sizeof(stmpconf)) ? + -EFAULT : 0; +} + +static int bnxt_map_regs(struct bnxt *bp, u32 *reg_arr, int count, int reg_win) +{ + u32 reg_base = *reg_arr & BNXT_GRC_BASE_MASK; + u32 win_off; + int i; + + for (i = 0; i < count; i++) { + if ((reg_arr[i] & BNXT_GRC_BASE_MASK) != reg_base) + return -ERANGE; + } + win_off = BNXT_GRCPF_REG_WINDOW_BASE_OUT + (reg_win - 1) * 4; + writel(reg_base, bp->bar0 + win_off); + return 0; +} + +static int bnxt_map_ptp_regs(struct bnxt *bp) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + u32 *reg_arr; + int rc, i; + + reg_arr = ptp->refclk_regs; + if (bp->flags & BNXT_FLAG_CHIP_P5) { + rc = bnxt_map_regs(bp, reg_arr, 2, BNXT_PTP_GRC_WIN); + if (rc) + return rc; + for (i = 0; i < 2; i++) + ptp->refclk_mapped_regs[i] = BNXT_PTP_GRC_WIN_BASE + + (ptp->refclk_regs[i] & BNXT_GRC_OFFSET_MASK); + return 0; + } + return -ENODEV; +} + +static void bnxt_unmap_ptp_regs(struct bnxt *bp) +{ + writel(0, bp->bar0 + BNXT_GRCPF_REG_WINDOW_BASE_OUT + + (BNXT_PTP_GRC_WIN - 1) * 4); +} + +static u64 bnxt_cc_read(const struct cyclecounter *cc) +{ + struct bnxt_ptp_cfg *ptp = container_of(cc, struct bnxt_ptp_cfg, cc); + + return bnxt_refclk_read(ptp->bp, NULL); +} + +static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + struct skb_shared_hwtstamps timestamp; + u64 ts = 0, ns = 0; + int rc; + + rc = bnxt_hwrm_port_ts_query(bp, PORT_TS_QUERY_REQ_FLAGS_PATH_TX, &ts); + if (!rc) { + memset(×tamp, 0, sizeof(timestamp)); + spin_lock_bh(&ptp->ptp_lock); + ns = timecounter_cyc2time(&ptp->tc, ts); + spin_unlock_bh(&ptp->ptp_lock); + timestamp.hwtstamp = ns_to_ktime(ns); + skb_tstamp_tx(ptp->tx_skb, ×tamp); + } else { + netdev_err(bp->dev, "TS query for TX timer failed rc = %x\n", + rc); + } + + dev_kfree_skb_any(ptp->tx_skb); + ptp->tx_skb = NULL; + atomic_inc(&ptp->tx_avail); +} + +static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info) +{ + struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg, + ptp_info); + unsigned long now = jiffies; + struct bnxt *bp = ptp->bp; + + if (ptp->tx_skb) + bnxt_stamp_tx_skb(bp, ptp->tx_skb); + + if (!time_after_eq(now, ptp->next_period)) + return ptp->next_period - now; + + bnxt_ptp_get_current_time(bp); + ptp->next_period = now + HZ; + return HZ; +} + +int bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + + if (ptp->tx_skb) { + netdev_err(bp->dev, "deferring skb:one SKB is still outstanding\n"); + return -EBUSY; + } + ptp->tx_skb = skb; + ptp_schedule_worker(ptp->ptp_clock, 0); + return 0; +} + +int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + u64 time; + + if (!ptp) + return -ENODEV; + + BNXT_READ_TIME64(ptp, time, ptp->old_time); + *ts = (time & BNXT_HI_TIMER_MASK) | pkt_ts; + if (pkt_ts < (time & BNXT_LO_TIMER_MASK)) + *ts += BNXT_LO_TIMER_MASK + 1; + + return 0; +} + +void bnxt_ptp_start(struct bnxt *bp) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + + if (!ptp) + return; + + if (bp->flags & BNXT_FLAG_CHIP_P5) { + spin_lock_bh(&ptp->ptp_lock); + ptp->current_time = bnxt_refclk_read(bp, NULL); + WRITE_ONCE(ptp->old_time, ptp->current_time); + spin_unlock_bh(&ptp->ptp_lock); + ptp_schedule_worker(ptp->ptp_clock, 0); + } +} + +static const struct ptp_clock_info bnxt_ptp_caps = { + .owner = THIS_MODULE, + .name = "bnxt clock", + .max_adj = BNXT_MAX_PHC_DRIFT, + .n_alarm = 0, + .n_ext_ts = 0, + .n_per_out = 0, + .n_pins = 0, + .pps = 0, + .adjfreq = bnxt_ptp_adjfreq, + .adjtime = bnxt_ptp_adjtime, + .do_aux_work = bnxt_ptp_ts_aux_work, + .gettimex64 = bnxt_ptp_gettimex, + .settime64 = bnxt_ptp_settime, + .enable = bnxt_ptp_enable, +}; + +int bnxt_ptp_init(struct bnxt *bp) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + int rc; + + if (!ptp) + return 0; + + rc = bnxt_map_ptp_regs(bp); + if (rc) + return rc; + + atomic_set(&ptp->tx_avail, BNXT_MAX_TX_TS); + spin_lock_init(&ptp->ptp_lock); + + memset(&ptp->cc, 0, sizeof(ptp->cc)); + ptp->cc.read = bnxt_cc_read; + ptp->cc.mask = CYCLECOUNTER_MASK(48); + ptp->cc.shift = 0; + ptp->cc.mult = 1; + + timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real())); + + ptp->ptp_info = bnxt_ptp_caps; + ptp->ptp_clock = ptp_clock_register(&ptp->ptp_info, &bp->pdev->dev); + if (IS_ERR(ptp->ptp_clock)) { + int err = PTR_ERR(ptp->ptp_clock); + + ptp->ptp_clock = NULL; + bnxt_unmap_ptp_regs(bp); + return err; + } + + return 0; +} + +void bnxt_ptp_clear(struct bnxt *bp) +{ + struct bnxt_ptp_cfg *ptp = bp->ptp_cfg; + + if (!ptp) + return; + + if (ptp->ptp_clock) + ptp_clock_unregister(ptp->ptp_clock); + + ptp->ptp_clock = NULL; + if (ptp->tx_skb) { + dev_kfree_skb_any(ptp->tx_skb); + ptp->tx_skb = NULL; + } + bnxt_unmap_ptp_regs(bp); +} diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h new file mode 100644 index 000000000000..6b6245750e20 --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -0,0 +1,81 @@ +/* Broadcom NetXtreme-C/E network driver. + * + * Copyright (c) 2021 Broadcom Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + */ + +#ifndef BNXT_PTP_H +#define BNXT_PTP_H + +#define BNXT_PTP_GRC_WIN 5 +#define BNXT_PTP_GRC_WIN_BASE 0x5000 + +#define BNXT_MAX_PHC_DRIFT 31000000 +#define BNXT_LO_TIMER_MASK 0x0000ffffffffUL +#define BNXT_HI_TIMER_MASK 0xffff00000000UL + +#define BNXT_PTP_QTS_TIMEOUT 1000 +#define BNXT_PTP_QTS_TX_ENABLES (PORT_TS_QUERY_REQ_ENABLES_PTP_SEQ_ID | \ + PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT) + +struct bnxt_ptp_cfg { + struct ptp_clock_info ptp_info; + struct ptp_clock *ptp_clock; + struct cyclecounter cc; + struct timecounter tc; + /* serialize timecounter access */ + spinlock_t ptp_lock; + struct sk_buff *tx_skb; + u64 current_time; + u64 old_time; + unsigned long next_period; + u16 tx_seqid; + struct bnxt *bp; + atomic_t tx_avail; +#define BNXT_MAX_TX_TS 1 + u16 rxctl; +#define BNXT_PTP_MSG_SYNC (1 << 0) +#define BNXT_PTP_MSG_DELAY_REQ (1 << 1) +#define BNXT_PTP_MSG_PDELAY_REQ (1 << 2) +#define BNXT_PTP_MSG_PDELAY_RESP (1 << 3) +#define BNXT_PTP_MSG_FOLLOW_UP (1 << 8) +#define BNXT_PTP_MSG_DELAY_RESP (1 << 9) +#define BNXT_PTP_MSG_PDELAY_RESP_FOLLOW_UP (1 << 10) +#define BNXT_PTP_MSG_ANNOUNCE (1 << 11) +#define BNXT_PTP_MSG_SIGNALING (1 << 12) +#define BNXT_PTP_MSG_MANAGEMENT (1 << 13) +#define BNXT_PTP_MSG_EVENTS (BNXT_PTP_MSG_SYNC | \ + BNXT_PTP_MSG_DELAY_REQ | \ + BNXT_PTP_MSG_PDELAY_REQ | \ + BNXT_PTP_MSG_PDELAY_RESP) + u8 tx_tstamp_en:1; + int rx_filter; + + u32 refclk_regs[2]; + u32 refclk_mapped_regs[2]; +}; + +#if BITS_PER_LONG == 32 +#define BNXT_READ_TIME64(ptp, dst, src) \ +do { \ + spin_lock_bh(&(ptp)->ptp_lock); \ + (dst) = (src); \ + spin_unlock_bh(&(ptp)->ptp_lock); \ +} while (0) +#else +#define BNXT_READ_TIME64(ptp, dst, src) \ + ((dst) = READ_ONCE(src)) +#endif + +int bnxt_ptp_parse(struct sk_buff *skb, u16 *seq_id); +int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr); +int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr); +int bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb); +int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts); +void bnxt_ptp_start(struct bnxt *bp); +int bnxt_ptp_init(struct bnxt *bp); +void bnxt_ptp_clear(struct bnxt *bp); +#endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index eb00a219aa51..7fa881e1cd80 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -632,7 +632,7 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs) vf_vnics = (hw_resc->max_vnics - bp->nr_vnics) / num_vfs; vf_vnics = min_t(u16, vf_vnics, vf_rx_rings); - req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MTU | + req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_ADMIN_MTU | FUNC_CFG_REQ_ENABLES_MRU | FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS | FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS | @@ -645,7 +645,7 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs) mtu = bp->dev->mtu + ETH_HLEN + VLAN_HLEN; req.mru = cpu_to_le16(mtu); - req.mtu = cpu_to_le16(mtu); + req.admin_mtu = cpu_to_le16(mtu); req.num_rsscos_ctxs = cpu_to_le16(1); req.num_cmpl_rings = cpu_to_le16(vf_cp_rings); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index ec9564e584e0..bee6e091a997 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -138,9 +138,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, xdp_prepare_buff(&xdp, *data_ptr - offset, offset, *len, false); orig_data = xdp.data; - rcu_read_lock(); act = bpf_prog_run_xdp(xdp_prog, &xdp); - rcu_read_unlock(); tx_avail = bnxt_tx_avail(bp, txr); /* If the tx ring is not full, we must not update the rx producer yet diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index fcca023f22e5..41f7f078cd27 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -4296,3 +4296,4 @@ MODULE_AUTHOR("Broadcom Corporation"); MODULE_DESCRIPTION("Broadcom GENET Ethernet controller driver"); MODULE_ALIAS("platform:bcmgenet"); MODULE_LICENSE("GPL"); +MODULE_SOFTDEP("pre: mdio-bcm-unimac"); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 5335244e4577..89d16c587bb7 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -423,6 +423,10 @@ static int bcmgenet_mii_register(struct bcmgenet_priv *priv) int id, ret; pres = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!pres) { + dev_err(&pdev->dev, "Invalid resource\n"); + return -EINVAL; + } memset(&res, 0, sizeof(res)); memset(&ppd, 0, sizeof(ppd)); diff --git a/drivers/net/ethernet/brocade/bna/bfa_cee.c b/drivers/net/ethernet/brocade/bna/bfa_cee.c index 06f221c44802..eeb05e31713f 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_cee.c +++ b/drivers/net/ethernet/brocade/bna/bfa_cee.c @@ -82,7 +82,7 @@ bfa_cee_get_attr_isr(struct bfa_cee *cee, enum bfa_status status) } /** - * bfa_cee_get_attr_isr - CEE ISR for get-stats responses from f/w + * bfa_cee_get_stats_isr - CEE ISR for get-stats responses from f/w * * @cee: Pointer to the CEE module * @status: Return status from the f/w diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index a0c7b1167dbb..7d2fe13a52f8 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4655,8 +4655,7 @@ static int macb_probe(struct platform_device *pdev) struct macb *bp; int err, val; - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - mem = devm_ioremap_resource(&pdev->dev, regs); + mem = devm_platform_get_and_ioremap_resource(pdev, 0, ®s); if (IS_ERR(mem)) return PTR_ERR(mem); diff --git a/drivers/net/ethernet/cadence/macb_pci.c b/drivers/net/ethernet/cadence/macb_pci.c index 353393dea639..8b7b59908a1a 100644 --- a/drivers/net/ethernet/cadence/macb_pci.c +++ b/drivers/net/ethernet/cadence/macb_pci.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * DOC: Cadence GEM PCI wrapper. * * Copyright (C) 2016 Cadence Design Systems - https://www.cadence.com diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index 283918aeb741..5c368a9cbbbc 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * 1588 PTP support for Cadence GEM device. * * Copyright (C) 2017 Cadence Design Systems - https://www.cadence.com diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c index bbb453c6a5f7..b6a066404f4b 100644 --- a/drivers/net/ethernet/calxeda/xgmac.c +++ b/drivers/net/ethernet/calxeda/xgmac.c @@ -711,7 +711,7 @@ static void xgmac_rx_refill(struct xgmac_priv *priv) } /** - * init_xgmac_dma_desc_rings - init the RX/TX descriptor rings + * xgmac_dma_desc_rings_init - init the RX/TX descriptor rings * @dev: net device structure * Description: this function initializes the DMA RX/TX descriptors * and allocates the socket buffers. @@ -859,7 +859,7 @@ static void xgmac_free_dma_desc_rings(struct xgmac_priv *priv) } /** - * xgmac_tx: + * xgmac_tx_complete: * @priv: private driver structure * Description: it reclaims resources after transmission completes. */ @@ -1040,7 +1040,7 @@ static int xgmac_open(struct net_device *dev) } /** - * xgmac_release - close entry point of the driver + * xgmac_stop - close entry point of the driver * @dev : device pointer. * Description: * This is the stop entry point of the driver. @@ -1812,7 +1812,7 @@ err_alloc: } /** - * xgmac_dvr_remove + * xgmac_remove * @pdev: platform device pointer * Description: this function resets the TX/RX processes, disables the MAC RX/TX * changes the link status, releases the DMA descriptor rings, diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index c33b4e837515..e2b290135fd9 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -555,9 +555,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, xdp_prepare_buff(&xdp, hard_start, data - hard_start, len, false); orig_data = xdp.data; - rcu_read_lock(); action = bpf_prog_run_xdp(prog, &xdp); - rcu_read_unlock(); len = xdp.data_end - xdp.data; /* Check if XDP program has changed headers */ diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 0c783aadf393..c36fed9c3d73 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -594,9 +594,6 @@ static void bgx_lmac_handler(struct net_device *netdev) struct phy_device *phydev; int link_changed = 0; - if (!lmac) - return; - phydev = lmac->phydev; if (!phydev->link && lmac->last_link) diff --git a/drivers/net/ethernet/chelsio/cxgb3/adapter.h b/drivers/net/ethernet/chelsio/cxgb3/adapter.h index f80fbd81b609..6d682b7c7aac 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/adapter.h +++ b/drivers/net/ethernet/chelsio/cxgb3/adapter.h @@ -178,7 +178,7 @@ struct sge_txq { /* state for an SGE Tx queue */ unsigned int token; /* WR token */ dma_addr_t phys_addr; /* physical address of the ring */ struct sk_buff_head sendq; /* List of backpressured offload packets */ - struct tasklet_struct qresume_tsk; /* restarts the queue */ + struct work_struct qresume_task; /* restarts the queue */ unsigned int cntxt_id; /* SGE context id for the Tx q */ unsigned long stops; /* # of times q has been stopped */ unsigned long restarts; /* # of queue restarts */ diff --git a/drivers/net/ethernet/chelsio/cxgb3/common.h b/drivers/net/ethernet/chelsio/cxgb3/common.h index 1bd7d89666c4..b706f2fbe4f4 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/common.h +++ b/drivers/net/ethernet/chelsio/cxgb3/common.h @@ -770,4 +770,6 @@ int t3_xaui_direct_phy_prep(struct cphy *phy, struct adapter *adapter, int phy_addr, const struct mdio_ops *mdio_ops); int t3_aq100x_phy_prep(struct cphy *phy, struct adapter *adapter, int phy_addr, const struct mdio_ops *mdio_ops); + +extern struct workqueue_struct *cxgb3_wq; #endif /* __CHELSIO_COMMON_H */ diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 84ad7261e243..57f210c53afc 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -1273,14 +1273,14 @@ static int cxgb_up(struct adapter *adap) free_irq(adap->msix_info[0].vec, adap); goto irq_err; } - } else if ((err = request_irq(adap->pdev->irq, - t3_intr_handler(adap, - adap->sge.qs[0].rspq. - polling), - (adap->flags & USING_MSI) ? - 0 : IRQF_SHARED, - adap->name, adap))) - goto irq_err; + } else { + err = request_irq(adap->pdev->irq, + t3_intr_handler(adap, adap->sge.qs[0].rspq.polling), + (adap->flags & USING_MSI) ? 0 : IRQF_SHARED, + adap->name, adap); + if (err) + goto irq_err; + } enable_all_napi(adap); t3_sge_start(adap); @@ -3098,8 +3098,9 @@ static void set_nqsets(struct adapter *adap) nqsets = num_cpus; if (nqsets < 1 || hwports == 4) nqsets = 1; - } else + } else { nqsets = 1; + } for_each_port(adap, i) { struct port_info *pi = adap2pinfo(adap, i); diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c index 1cc3c51eff71..cb5c79c43bc9 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c @@ -665,7 +665,7 @@ static void t3_reset_qset(struct sge_qset *q) /** - * free_qset - free the resources of an SGE queue set + * t3_free_qset - free the resources of an SGE queue set * @adapter: the adapter owning the queue set * @q: the queue set * @@ -1256,7 +1256,7 @@ static inline void t3_stop_tx_queue(struct netdev_queue *txq, } /** - * eth_xmit - add a packet to the Ethernet Tx queue + * t3_eth_xmit - add a packet to the Ethernet Tx queue * @skb: the packet * @dev: the egress net device * @@ -1518,14 +1518,15 @@ static int ctrl_xmit(struct adapter *adap, struct sge_txq *q, /** * restart_ctrlq - restart a suspended control queue - * @t: pointer to the tasklet associated with this handler + * @w: pointer to the work associated with this handler * * Resumes transmission on a suspended Tx control queue. */ -static void restart_ctrlq(struct tasklet_struct *t) +static void restart_ctrlq(struct work_struct *w) { struct sk_buff *skb; - struct sge_qset *qs = from_tasklet(qs, t, txq[TXQ_CTRL].qresume_tsk); + struct sge_qset *qs = container_of(w, struct sge_qset, + txq[TXQ_CTRL].qresume_task); struct sge_txq *q = &qs->txq[TXQ_CTRL]; spin_lock(&q->lock); @@ -1736,14 +1737,15 @@ again: reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK); /** * restart_offloadq - restart a suspended offload queue - * @t: pointer to the tasklet associated with this handler + * @w: pointer to the work associated with this handler * * Resumes transmission on a suspended Tx offload queue. */ -static void restart_offloadq(struct tasklet_struct *t) +static void restart_offloadq(struct work_struct *w) { struct sk_buff *skb; - struct sge_qset *qs = from_tasklet(qs, t, txq[TXQ_OFLD].qresume_tsk); + struct sge_qset *qs = container_of(w, struct sge_qset, + txq[TXQ_OFLD].qresume_task); struct sge_txq *q = &qs->txq[TXQ_OFLD]; const struct port_info *pi = netdev_priv(qs->netdev); struct adapter *adap = pi->adapter; @@ -1998,13 +2000,17 @@ static void restart_tx(struct sge_qset *qs) should_restart_tx(&qs->txq[TXQ_OFLD]) && test_and_clear_bit(TXQ_OFLD, &qs->txq_stopped)) { qs->txq[TXQ_OFLD].restarts++; - tasklet_schedule(&qs->txq[TXQ_OFLD].qresume_tsk); + + /* The work can be quite lengthy so we use driver's own queue */ + queue_work(cxgb3_wq, &qs->txq[TXQ_OFLD].qresume_task); } if (test_bit(TXQ_CTRL, &qs->txq_stopped) && should_restart_tx(&qs->txq[TXQ_CTRL]) && test_and_clear_bit(TXQ_CTRL, &qs->txq_stopped)) { qs->txq[TXQ_CTRL].restarts++; - tasklet_schedule(&qs->txq[TXQ_CTRL].qresume_tsk); + + /* The work can be quite lengthy so we use driver's own queue */ + queue_work(cxgb3_wq, &qs->txq[TXQ_CTRL].qresume_task); } } @@ -3085,8 +3091,8 @@ int t3_sge_alloc_qset(struct adapter *adapter, unsigned int id, int nports, skb_queue_head_init(&q->txq[i].sendq); } - tasklet_setup(&q->txq[TXQ_OFLD].qresume_tsk, restart_offloadq); - tasklet_setup(&q->txq[TXQ_CTRL].qresume_tsk, restart_ctrlq); + INIT_WORK(&q->txq[TXQ_OFLD].qresume_task, restart_offloadq); + INIT_WORK(&q->txq[TXQ_CTRL].qresume_task, restart_ctrlq); q->fl[0].gen = q->fl[1].gen = 1; q->fl[0].size = p->fl_size; @@ -3276,11 +3282,11 @@ void t3_sge_start(struct adapter *adap) * * Can be invoked from interrupt context e.g. error handler. * - * Note that this function cannot disable the restart of tasklets as + * Note that this function cannot disable the restart of works as * it cannot wait if called from interrupt context, however the - * tasklets will have no effect since the doorbells are disabled. The + * works will have no effect since the doorbells are disabled. The * driver will call tg3_sge_stop() later from process context, at - * which time the tasklets will be stopped if they are still running. + * which time the works will be stopped if they are still running. */ void t3_sge_stop_dma(struct adapter *adap) { @@ -3292,7 +3298,7 @@ void t3_sge_stop_dma(struct adapter *adap) * @adap: the adapter * * Called from process context. Disables the DMA engine and any - * pending queue restart tasklets. + * pending queue restart works. */ void t3_sge_stop(struct adapter *adap) { @@ -3303,8 +3309,8 @@ void t3_sge_stop(struct adapter *adap) for (i = 0; i < SGE_QSETS; ++i) { struct sge_qset *qs = &adap->sge.qs[i]; - tasklet_kill(&qs->txq[TXQ_OFLD].qresume_tsk); - tasklet_kill(&qs->txq[TXQ_CTRL].qresume_tsk); + cancel_work_sync(&qs->txq[TXQ_OFLD].qresume_task); + cancel_work_sync(&qs->txq[TXQ_CTRL].qresume_task); } } @@ -3371,7 +3377,7 @@ void t3_sge_prep(struct adapter *adap, struct sge_params *p) q->coalesce_usecs = 5; q->rspq_size = 1024; q->fl_size = 1024; - q->jumbo_size = 512; + q->jumbo_size = 512; q->txq_size[TXQ_ETH] = 1024; q->txq_size[TXQ_OFLD] = 1024; q->txq_size[TXQ_CTRL] = 256; diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c index 12fcf84d67ad..163efab27e9b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c +++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c @@ -106,8 +106,7 @@ int cxgb4_clip_get(const struct net_device *dev, const u32 *lip, u8 v6) if (!list_empty(&ctbl->ce_free_head)) { ce = list_first_entry(&ctbl->ce_free_head, struct clip_entry, list); - list_del(&ce->list); - INIT_LIST_HEAD(&ce->list); + list_del_init(&ce->list); spin_lock_init(&ce->lock); refcount_set(&ce->refcnt, 0); atomic_dec(&ctbl->nfree); @@ -179,8 +178,7 @@ found: write_lock_bh(&ctbl->lock); spin_lock_bh(&ce->lock); if (refcount_dec_and_test(&ce->refcnt)) { - list_del(&ce->list); - INIT_LIST_HEAD(&ce->list); + list_del_init(&ce->list); list_add_tail(&ce->list, &ctbl->ce_free_head); atomic_inc(&ctbl->nfree); if (v6) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 762113a04dde..9a2b166d651e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3894,7 +3894,6 @@ static const struct net_device_ops cxgb4_mgmt_netdev_ops = { .ndo_set_vf_vlan = cxgb4_mgmt_set_vf_vlan, .ndo_set_vf_link_state = cxgb4_mgmt_set_vf_link_state, }; -#endif static void cxgb4_mgmt_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) @@ -3909,6 +3908,7 @@ static void cxgb4_mgmt_get_drvinfo(struct net_device *dev, static const struct ethtool_ops cxgb4_mgmt_ethtool_ops = { .get_drvinfo = cxgb4_mgmt_get_drvinfo, }; +#endif static void notify_fatal_err(struct work_struct *work) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c index 70dbee89118e..5bf117d2179f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c @@ -446,7 +446,7 @@ void cxgb4_ptp_init(struct adapter *adapter) } /** - * cxgb4_ptp_remove - disable PTP device and stop the overflow check + * cxgb4_ptp_stop - disable PTP device and stop the overflow check * @adapter: board private structure * * Stop the PTP support. diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index a0555f4d76fc..6606fb8b3e42 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -6993,7 +6993,7 @@ int t4_fw_bye(struct adapter *adap, unsigned int mbox) } /** - * t4_init_cmd - ask FW to initialize the device + * t4_early_init - ask FW to initialize the device * @adap: the adapter * @mbox: mailbox to use for the FW command * @@ -7792,7 +7792,6 @@ int t4_free_encap_mac_filt(struct adapter *adap, unsigned int viid, int idx, bool sleep_ok) { struct fw_vi_mac_exact *p; - u8 addr[] = {0, 0, 0, 0, 0, 0}; struct fw_vi_mac_cmd c; int ret = 0; u32 exact; @@ -7809,7 +7808,7 @@ int t4_free_encap_mac_filt(struct adapter *adap, unsigned int viid, p = c.u.exact; p->valid_to_idx = cpu_to_be16(FW_VI_MAC_CMD_VALID_F | FW_VI_MAC_CMD_IDX_V(idx)); - memcpy(p->macaddr, addr, sizeof(p->macaddr)); + eth_zero_addr(p->macaddr); ret = t4_wr_mbox_meat(adap, adap->mbox, &c, sizeof(c), &c, sleep_ok); return ret; } @@ -10234,7 +10233,7 @@ out: } /** - * t4_set_vf_mac - Set MAC address for the specified VF + * t4_set_vf_mac_acl - Set MAC address for the specified VF * @adapter: The adapter * @vf: one of the VFs instantiated by the specified PF * @naddr: the number of MAC addresses diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index 95657da0aa4b..7bc80eeb2c21 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -954,7 +954,7 @@ static void write_sgl(const struct sk_buff *skb, struct sge_txq *tq, } /** - * check_ring_tx_db - check and potentially ring a TX queue's doorbell + * ring_tx_db - check and potentially ring a TX queue's doorbell * @adapter: the adapter * @tq: the TX queue * @n: number of new descriptors to give to HW diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index 19dc7dc054a2..bcad69c48074 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -2134,7 +2134,7 @@ static void chtls_abort_req_rss(struct sock *sk, struct sk_buff *skb) sk->sk_err = ETIMEDOUT; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); if (sk->sk_state == TCP_SYN_RECV && !abort_syn_rcv(sk, skb)) return; diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 8df6f081f244..c2ebb3388789 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2356,8 +2356,6 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct gemini_ethernet *geth; struct net_device *netdev; - struct resource *gmacres; - struct resource *dmares; struct device *parent; unsigned int id; int irq; @@ -2390,24 +2388,18 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) port->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); /* DMA memory */ - dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!dmares) { - dev_err(dev, "no DMA resource\n"); - return -ENODEV; - } - port->dma_base = devm_ioremap_resource(dev, dmares); - if (IS_ERR(port->dma_base)) + port->dma_base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); + if (IS_ERR(port->dma_base)) { + dev_err(dev, "get DMA address failed\n"); return PTR_ERR(port->dma_base); + } /* GMAC config memory */ - gmacres = platform_get_resource(pdev, IORESOURCE_MEM, 1); - if (!gmacres) { - dev_err(dev, "no GMAC resource\n"); - return -ENODEV; - } - port->gmac_base = devm_ioremap_resource(dev, gmacres); - if (IS_ERR(port->gmac_base)) + port->gmac_base = devm_platform_get_and_ioremap_resource(pdev, 1, NULL); + if (IS_ERR(port->gmac_base)) { + dev_err(dev, "get GMAC address failed\n"); return PTR_ERR(port->gmac_base); + } /* Interrupt */ irq = platform_get_irq(pdev, 0); @@ -2502,10 +2494,6 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) if (ret) goto unprepare; - netdev_info(netdev, - "irq %d, DMA @ 0x%pap, GMAC @ 0x%pap\n", - port->irq, &dmares->start, - &gmacres->start); return 0; unprepare: @@ -2544,17 +2532,13 @@ static int gemini_ethernet_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct gemini_ethernet *geth; unsigned int retry = 5; - struct resource *res; u32 val; /* Global registers */ geth = devm_kzalloc(dev, sizeof(*geth), GFP_KERNEL); if (!geth) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENODEV; - geth->base = devm_ioremap_resource(dev, res); + geth->base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(geth->base)) return PTR_ERR(geth->base); geth->dev = dev; diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index b018195f0243..117c26fa5909 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -832,8 +832,8 @@ static struct net_device_stats *de_get_stats(struct net_device *dev) /* The chip only need report frame silently dropped. */ spin_lock_irq(&de->lock); - if (netif_running(dev) && netif_device_present(dev)) - __de_get_stats(de); + if (netif_running(dev) && netif_device_present(dev)) + __de_get_stats(de); spin_unlock_irq(&de->lock); return &dev->stats; diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 683e328b5461..b125d7faefdf 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -396,7 +396,7 @@ . Updated the PCI interface to conform with the latest version. I hope nothing is broken... - Add TX done interrupt modification from suggestion + Add TX done interrupt modification from suggestion by . Fix is_anc_capable() bug reported by . @@ -1499,7 +1499,7 @@ de4x5_queue_pkt(struct sk_buff *skb, struct net_device *dev) spin_lock_irqsave(&lp->lock, flags); netif_stop_queue(dev); load_packet(dev, skb->data, TD_IC | TD_LS | TD_FS | skb->len, skb); - lp->stats.tx_bytes += skb->len; + lp->stats.tx_bytes += skb->len; outl(POLL_DEMAND, DE4X5_TPD);/* Start the TX */ lp->tx_new = (lp->tx_new + 1) % lp->txRingSize; @@ -1651,7 +1651,7 @@ de4x5_rx(struct net_device *dev) /* Update stats */ lp->stats.rx_packets++; - lp->stats.rx_bytes += pkt_len; + lp->stats.rx_bytes += pkt_len; } } diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c index 87a27fe2992d..c763b692e164 100644 --- a/drivers/net/ethernet/dec/tulip/dmfe.c +++ b/drivers/net/ethernet/dec/tulip/dmfe.c @@ -518,7 +518,7 @@ static void dmfe_remove_one(struct pci_dev *pdev) DMFE_DBUG(0, "dmfe_remove_one()", 0); - if (dev) { + if (dev) { unregister_netdev(dev); pci_iounmap(db->pdev, db->ioaddr); @@ -567,10 +567,10 @@ static int dmfe_open(struct net_device *dev) /* CR6 operation mode decision */ if ( !chkmode || (db->chip_id == PCI_DM9132_ID) || (db->chip_revision >= 0x30) ) { - db->cr6_data |= DMFE_TXTH_256; + db->cr6_data |= DMFE_TXTH_256; db->cr0_data = CR0_DEFAULT; db->dm910x_chk_mode=4; /* Enter the normal mode */ - } else { + } else { db->cr6_data |= CR6_SFT; /* Store & Forward mode */ db->cr0_data = 0; db->dm910x_chk_mode = 1; /* Enter the check mode */ @@ -903,7 +903,7 @@ static void dmfe_free_tx_pkt(struct net_device *dev, struct dmfe_board_info *db) } } - txptr = txptr->next_tx_desc; + txptr = txptr->next_tx_desc; }/* End of while */ /* Update TX remove pointer to next */ @@ -1121,7 +1121,7 @@ static void dmfe_timer(struct timer_list *t) void __iomem *ioaddr = db->ioaddr; u32 tmp_cr8; unsigned char tmp_cr12; - unsigned long flags; + unsigned long flags; int link_ok, link_ok_phy; @@ -1217,7 +1217,7 @@ static void dmfe_timer(struct timer_list *t) if (link_ok_phy != link_ok) { DMFE_DBUG (0, "PHY and chip report different link status", 0); link_ok = link_ok | link_ok_phy; - } + } if ( !link_ok && netif_carrier_ok(dev)) { /* Link Failed */ @@ -1699,14 +1699,14 @@ static void dmfe_set_phyxcer(struct dmfe_board_info *db) if (db->chip_id == PCI_DM9009_ID) phy_reg &= 0x61; } - /* Write new capability to Phyxcer Reg4 */ + /* Write new capability to Phyxcer Reg4 */ if ( !(phy_reg & 0x01e0)) { phy_reg|=db->PHY_reg4; db->media_mode|=DMFE_AUTO; } dmfe_phy_write(db->ioaddr, db->phy_addr, 4, phy_reg, db->chip_id); - /* Restart Auto-Negotiation */ + /* Restart Auto-Negotiation */ if ( db->chip_type && (db->chip_id == PCI_DM9102_ID) ) dmfe_phy_write(db->ioaddr, db->phy_addr, 0, 0x1800, db->chip_id); if ( !db->chip_type ) @@ -1754,7 +1754,7 @@ static void dmfe_process_mode(struct dmfe_board_info *db) } dmfe_phy_write(db->ioaddr, db->phy_addr, 0, phy_reg, db->chip_id); - if ( db->chip_type && (db->chip_id == PCI_DM9102_ID) ) + if ( db->chip_type && (db->chip_id == PCI_DM9102_ID) ) mdelay(20); dmfe_phy_write(db->ioaddr, db->phy_addr, 0, phy_reg, db->chip_id); diff --git a/drivers/net/ethernet/dec/tulip/pnic2.c b/drivers/net/ethernet/dec/tulip/pnic2.c index 412adaa7fdf8..72a09156b48b 100644 --- a/drivers/net/ethernet/dec/tulip/pnic2.c +++ b/drivers/net/ethernet/dec/tulip/pnic2.c @@ -351,7 +351,7 @@ void pnic2_lnk_change(struct net_device *dev, int csr5) del_timer_sync(&tp->timer); pnic2_start_nway(dev); tp->timer.expires = RUN_AT(3*HZ); - add_timer(&tp->timer); + add_timer(&tp->timer); } return; @@ -375,7 +375,7 @@ void pnic2_lnk_change(struct net_device *dev, int csr5) del_timer_sync(&tp->timer); pnic2_start_nway(dev); tp->timer.expires = RUN_AT(3*HZ); - add_timer(&tp->timer); + add_timer(&tp->timer); } return; diff --git a/drivers/net/ethernet/dec/tulip/tulip.h b/drivers/net/ethernet/dec/tulip/tulip.h index 815907259048..0ed598dc7569 100644 --- a/drivers/net/ethernet/dec/tulip/tulip.h +++ b/drivers/net/ethernet/dec/tulip/tulip.h @@ -478,7 +478,6 @@ void t21142_lnk_change(struct net_device *dev, int csr5); void pnic2_lnk_change(struct net_device *dev, int csr5); void pnic2_timer(struct timer_list *t); void pnic2_start_nway(struct net_device *dev); -void pnic2_lnk_change(struct net_device *dev, int csr5); /* eeprom.c */ void tulip_parse_eeprom(struct net_device *dev); diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c index 13e73ed15ef0..d67ef7d02d6b 100644 --- a/drivers/net/ethernet/dec/tulip/uli526x.c +++ b/drivers/net/ethernet/dec/tulip/uli526x.c @@ -780,7 +780,7 @@ static void uli526x_free_tx_pkt(struct net_device *dev, } } - txptr = txptr->next_tx_desc; + txptr = txptr->next_tx_desc; }/* End of while */ /* Update TX remove pointer to next */ @@ -1015,7 +1015,7 @@ static void uli526x_timer(struct timer_list *t) struct net_device *dev = pci_get_drvdata(db->pdev); struct uli_phy_ops *phy = &db->phy; void __iomem *ioaddr = db->ioaddr; - unsigned long flags; + unsigned long flags; u8 tmp_cr12 = 0; u32 tmp_cr8; @@ -1535,14 +1535,14 @@ static void uli526x_set_phyxcer(struct uli526x_board_info *db) } - /* Write new capability to Phyxcer Reg4 */ + /* Write new capability to Phyxcer Reg4 */ if ( !(phy_reg & 0x01e0)) { phy_reg|=db->PHY_reg4; db->media_mode|=ULI526X_AUTO; } phy->write(db, db->phy_addr, 4, phy_reg); - /* Restart Auto-Negotiation */ + /* Restart Auto-Negotiation */ phy->write(db, db->phy_addr, 0, 0x1200); udelay(50); } @@ -1550,7 +1550,7 @@ static void uli526x_set_phyxcer(struct uli526x_board_info *db) /* * Process op-mode - AUTO mode : PHY controller in Auto-negotiation Mode + AUTO mode : PHY controller in Auto-negotiation Mode * Force mode: PHY controller in force mode with HUB * N-way force capability with SWITCH */ diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c index 514df170ec5d..f6ff1f76eacb 100644 --- a/drivers/net/ethernet/dec/tulip/winbond-840.c +++ b/drivers/net/ethernet/dec/tulip/winbond-840.c @@ -36,7 +36,7 @@ power management. support for big endian descriptors Copyright (C) 2001 Manfred Spraul - * ethtool support (jgarzik) + * ethtool support (jgarzik) * Replace some MII-related magic numbers with constants (jgarzik) TODO: @@ -1479,7 +1479,7 @@ static int netdev_close(struct net_device *dev) np->cur_rx, np->dirty_rx); } - /* Stop the chip's Tx and Rx processes. */ + /* Stop the chip's Tx and Rx processes. */ spin_lock_irq(&np->lock); netif_device_detach(dev); update_csr6(dev, 0); diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c index ce61f79f3b7c..ee0ca712dd1c 100644 --- a/drivers/net/ethernet/dlink/sundance.c +++ b/drivers/net/ethernet/dlink/sundance.c @@ -1847,20 +1847,20 @@ static int netdev_close(struct net_device *dev) /* Stop the chip's Tx and Rx processes. */ iowrite16(TxDisable | RxDisable | StatsDisable, ioaddr + MACCtrl1); - for (i = 2000; i > 0; i--) { - if ((ioread32(ioaddr + DMACtrl) & 0xc000) == 0) + for (i = 2000; i > 0; i--) { + if ((ioread32(ioaddr + DMACtrl) & 0xc000) == 0) break; mdelay(1); - } + } - iowrite16(GlobalReset | DMAReset | FIFOReset | NetworkReset, + iowrite16(GlobalReset | DMAReset | FIFOReset | NetworkReset, ioaddr + ASIC_HI_WORD(ASICCtrl)); - for (i = 2000; i > 0; i--) { + for (i = 2000; i > 0; i--) { if ((ioread16(ioaddr + ASIC_HI_WORD(ASICCtrl)) & ResetBusy) == 0) break; mdelay(1); - } + } #ifdef __i386__ if (netif_msg_hw(np)) { diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 701c12c9e033..649c5c429bd7 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -550,7 +550,7 @@ int be_process_mcc(struct be_adapter *adapter) int num = 0, status = 0; struct be_mcc_obj *mcc_obj = &adapter->mcc_obj; - spin_lock_bh(&adapter->mcc_cq_lock); + spin_lock(&adapter->mcc_cq_lock); while ((compl = be_mcc_compl_get(adapter))) { if (compl->flags & CQE_FLAGS_ASYNC_MASK) { @@ -566,7 +566,7 @@ int be_process_mcc(struct be_adapter *adapter) if (num) be_cq_notify(adapter, mcc_obj->cq.id, mcc_obj->rearm_cq, num); - spin_unlock_bh(&adapter->mcc_cq_lock); + spin_unlock(&adapter->mcc_cq_lock); return status; } @@ -581,7 +581,9 @@ static int be_mcc_wait_compl(struct be_adapter *adapter) if (be_check_error(adapter, BE_ERROR_ANY)) return -EIO; + local_bh_disable(); status = be_process_mcc(adapter); + local_bh_enable(); if (atomic_read(&mcc_obj->q.used) == 0) break; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 7968568bbe21..361c1c87c183 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -5501,7 +5501,9 @@ static void be_worker(struct work_struct *work) * mcc completions */ if (!netif_running(adapter->netdev)) { + local_bh_disable(); be_process_mcc(adapter); + local_bh_enable(); goto reschedule; } diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c index e3954d8835e7..f9a288a6ec8c 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.c +++ b/drivers/net/ethernet/ezchip/nps_enet.c @@ -607,7 +607,7 @@ static s32 nps_enet_probe(struct platform_device *pdev) /* Get IRQ number */ priv->irq = platform_get_irq(pdev, 0); - if (!priv->irq) { + if (priv->irq < 0) { dev_err(dev, "failed to retrieve value from device tree\n"); err = -ENODEV; goto out_netdev; @@ -630,8 +630,7 @@ static s32 nps_enet_probe(struct platform_device *pdev) out_netif_api: netif_napi_del(&priv->napi); out_netdev: - if (err) - free_netdev(ndev); + free_netdev(ndev); return err; } @@ -642,8 +641,8 @@ static s32 nps_enet_remove(struct platform_device *pdev) struct nps_enet_priv *priv = netdev_priv(ndev); unregister_netdev(ndev); - free_netdev(ndev); netif_napi_del(&priv->napi); + free_netdev(ndev); return 0; } diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 04421aec2dfd..11dbbfd38770 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1830,14 +1830,17 @@ static int ftgmac100_probe(struct platform_device *pdev) if (np && of_get_property(np, "use-ncsi", NULL)) { if (!IS_ENABLED(CONFIG_NET_NCSI)) { dev_err(&pdev->dev, "NCSI stack not enabled\n"); + err = -EINVAL; goto err_phy_connect; } dev_info(&pdev->dev, "Using NCSI interface\n"); priv->use_ncsi = true; priv->ndev = ncsi_register_dev(netdev, ftgmac100_ncsi_handler); - if (!priv->ndev) + if (!priv->ndev) { + err = -EINVAL; goto err_phy_connect; + } } else if (np && of_get_property(np, "phy-handle", NULL)) { struct phy_device *phy; @@ -1856,6 +1859,7 @@ static int ftgmac100_probe(struct platform_device *pdev) &ftgmac100_adjust_link); if (!phy) { dev_err(&pdev->dev, "Failed to connect to phy\n"); + err = -EINVAL; goto err_phy_connect; } diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c index 0908771aa9ac..0f141c14d72d 100644 --- a/drivers/net/ethernet/fealnx.c +++ b/drivers/net/ethernet/fealnx.c @@ -144,7 +144,7 @@ struct chip_info { }; static const struct chip_info skel_netdrv_tbl[] = { - { "100/10M Ethernet PCI Adapter", HAS_MII_XCVR }, + { "100/10M Ethernet PCI Adapter", HAS_MII_XCVR }, { "100/10M Ethernet PCI Adapter", HAS_CHIP_XCVR }, { "1000/100/10M Ethernet PCI Adapter", HAS_MII_XCVR }, }; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 177c020bf34a..e6826561cf11 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2558,13 +2558,9 @@ static u32 dpaa_run_xdp(struct dpaa_priv *priv, struct qm_fd *fd, void *vaddr, u32 xdp_act; int err; - rcu_read_lock(); - xdp_prog = READ_ONCE(priv->xdp_prog); - if (!xdp_prog) { - rcu_read_unlock(); + if (!xdp_prog) return XDP_PASS; - } xdp_init_buff(&xdp, DPAA_BP_RAW_SIZE - DPAA_TX_PRIV_DATA_SIZE, &dpaa_fq->xdp_rxq); @@ -2638,8 +2634,6 @@ static u32 dpaa_run_xdp(struct dpaa_priv *priv, struct qm_fd *fd, void *vaddr, break; } - rcu_read_unlock(); - return xdp_act; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c index b87db0846e10..8356af4631fd 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c @@ -121,10 +121,14 @@ DEFINE_SHOW_ATTRIBUTE(dpaa2_dbg_ch); void dpaa2_dbg_add(struct dpaa2_eth_priv *priv) { + struct fsl_mc_device *dpni_dev; struct dentry *dir; + char name[10]; /* Create a directory for the interface */ - dir = debugfs_create_dir(priv->net_dev->name, dpaa2_dbg_root); + dpni_dev = to_fsl_mc_device(priv->net_dev->dev.parent); + snprintf(name, 10, "dpni.%d", dpni_dev->obj_desc.id); + dir = debugfs_create_dir(name, dpaa2_dbg_root); priv->dbg.dir = dir; /* per-cpu stats file */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index e0c3c58e2ac7..973352393bd4 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -352,8 +352,6 @@ static u32 dpaa2_eth_run_xdp(struct dpaa2_eth_priv *priv, u32 xdp_act = XDP_PASS; int err, offset; - rcu_read_lock(); - xdp_prog = READ_ONCE(ch->xdp.prog); if (!xdp_prog) goto out; @@ -414,7 +412,6 @@ static u32 dpaa2_eth_run_xdp(struct dpaa2_eth_priv *priv, ch->xdp.res |= xdp_act; out: - rcu_read_unlock(); return xdp_act; } @@ -4164,10 +4161,11 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv) if (dpaa2_eth_is_type_phy(priv)) { err = dpaa2_mac_connect(mac); - if (err) { - netdev_err(priv->net_dev, "Error connecting to the MAC endpoint\n"); + if (err && err != -EPROBE_DEFER) + netdev_err(priv->net_dev, "Error connecting to the MAC endpoint: %pe", + ERR_PTR(err)); + if (err) goto err_close_mac; - } } return 0; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index ccaf7e35abeb..ae6d382d8735 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) /* Copyright 2019 NXP */ +#include +#include + #include "dpaa2-eth.h" #include "dpaa2-mac.h" @@ -34,39 +37,51 @@ static int phy_mode(enum dpmac_eth_if eth_if, phy_interface_t *if_mode) return 0; } -/* Caller must call of_node_put on the returned value */ -static struct device_node *dpaa2_mac_get_node(u16 dpmac_id) +static struct fwnode_handle *dpaa2_mac_get_node(struct device *dev, + u16 dpmac_id) { - struct device_node *dpmacs, *dpmac = NULL; - u32 id; + struct fwnode_handle *fwnode, *parent, *child = NULL; + struct device_node *dpmacs = NULL; int err; + u32 id; - dpmacs = of_find_node_by_name(NULL, "dpmacs"); - if (!dpmacs) - return NULL; - - while ((dpmac = of_get_next_child(dpmacs, dpmac)) != NULL) { - err = of_property_read_u32(dpmac, "reg", &id); - if (err) - continue; - if (id == dpmac_id) - break; + fwnode = dev_fwnode(dev->parent); + if (is_of_node(fwnode)) { + dpmacs = of_find_node_by_name(NULL, "dpmacs"); + if (!dpmacs) + return NULL; + parent = of_fwnode_handle(dpmacs); + } else if (is_acpi_node(fwnode)) { + parent = fwnode; } - of_node_put(dpmacs); + fwnode_for_each_child_node(parent, child) { + err = -EINVAL; + if (is_acpi_device_node(child)) + err = acpi_get_local_address(ACPI_HANDLE_FWNODE(child), &id); + else if (is_of_node(child)) + err = of_property_read_u32(to_of_node(child), "reg", &id); + if (err) + continue; - return dpmac; + if (id == dpmac_id) { + of_node_put(dpmacs); + return child; + } + } + of_node_put(dpmacs); + return NULL; } -static int dpaa2_mac_get_if_mode(struct device_node *node, +static int dpaa2_mac_get_if_mode(struct fwnode_handle *dpmac_node, struct dpmac_attr attr) { phy_interface_t if_mode; int err; - err = of_get_phy_mode(node, &if_mode); - if (!err) - return if_mode; + err = fwnode_get_phy_mode(dpmac_node); + if (err > 0) + return err; err = phy_mode(attr.eth_if, &if_mode); if (!err) @@ -235,26 +250,27 @@ static const struct phylink_mac_ops dpaa2_mac_phylink_ops = { }; static int dpaa2_pcs_create(struct dpaa2_mac *mac, - struct device_node *dpmac_node, int id) + struct fwnode_handle *dpmac_node, + int id) { struct mdio_device *mdiodev; - struct device_node *node; + struct fwnode_handle *node; - node = of_parse_phandle(dpmac_node, "pcs-handle", 0); - if (!node) { + node = fwnode_find_reference(dpmac_node, "pcs-handle", 0); + if (IS_ERR(node)) { /* do not error out on old DTS files */ netdev_warn(mac->net_dev, "pcs-handle node not found\n"); return 0; } - if (!of_device_is_available(node)) { + if (!fwnode_device_is_available(node)) { netdev_err(mac->net_dev, "pcs-handle node not available\n"); - of_node_put(node); + fwnode_handle_put(node); return -ENODEV; } - mdiodev = of_mdio_find_device(node); - of_node_put(node); + mdiodev = fwnode_mdio_find_device(node); + fwnode_handle_put(node); if (!mdiodev) return -EPROBE_DEFER; @@ -283,36 +299,33 @@ static void dpaa2_pcs_destroy(struct dpaa2_mac *mac) int dpaa2_mac_connect(struct dpaa2_mac *mac) { struct net_device *net_dev = mac->net_dev; - struct device_node *dpmac_node; + struct fwnode_handle *dpmac_node; struct phylink *phylink; int err; mac->if_link_type = mac->attr.link_type; - dpmac_node = dpaa2_mac_get_node(mac->attr.id); + dpmac_node = mac->fw_node; if (!dpmac_node) { netdev_err(net_dev, "No dpmac@%d node found.\n", mac->attr.id); return -ENODEV; } err = dpaa2_mac_get_if_mode(dpmac_node, mac->attr); - if (err < 0) { - err = -EINVAL; - goto err_put_node; - } + if (err < 0) + return -EINVAL; mac->if_mode = err; /* The MAC does not have the capability to add RGMII delays so * error out if the interface mode requests them and there is no PHY * to act upon them */ - if (of_phy_is_fixed_link(dpmac_node) && + if (of_phy_is_fixed_link(to_of_node(dpmac_node)) && (mac->if_mode == PHY_INTERFACE_MODE_RGMII_ID || mac->if_mode == PHY_INTERFACE_MODE_RGMII_RXID || mac->if_mode == PHY_INTERFACE_MODE_RGMII_TXID)) { netdev_err(net_dev, "RGMII delay not supported\n"); - err = -EINVAL; - goto err_put_node; + return -EINVAL; } if ((mac->attr.link_type == DPMAC_LINK_TYPE_PHY && @@ -320,14 +333,14 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac) mac->attr.link_type == DPMAC_LINK_TYPE_BACKPLANE) { err = dpaa2_pcs_create(mac, dpmac_node, mac->attr.id); if (err) - goto err_put_node; + return err; } mac->phylink_config.dev = &net_dev->dev; mac->phylink_config.type = PHYLINK_NETDEV; phylink = phylink_create(&mac->phylink_config, - of_fwnode_handle(dpmac_node), mac->if_mode, + dpmac_node, mac->if_mode, &dpaa2_mac_phylink_ops); if (IS_ERR(phylink)) { err = PTR_ERR(phylink); @@ -338,22 +351,18 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac) if (mac->pcs) phylink_set_pcs(mac->phylink, &mac->pcs->pcs); - err = phylink_of_phy_connect(mac->phylink, dpmac_node, 0); + err = phylink_fwnode_phy_connect(mac->phylink, dpmac_node, 0); if (err) { - netdev_err(net_dev, "phylink_of_phy_connect() = %d\n", err); + netdev_err(net_dev, "phylink_fwnode_phy_connect() = %d\n", err); goto err_phylink_destroy; } - of_node_put(dpmac_node); - return 0; err_phylink_destroy: phylink_destroy(mac->phylink); err_pcs_destroy: dpaa2_pcs_destroy(mac); -err_put_node: - of_node_put(dpmac_node); return err; } @@ -388,6 +397,12 @@ int dpaa2_mac_open(struct dpaa2_mac *mac) goto err_close_dpmac; } + /* Find the device node representing the MAC device and link the device + * behind the associated netdev to it. + */ + mac->fw_node = dpaa2_mac_get_node(&mac->mc_dev->dev, mac->attr.id); + net_dev->dev.of_node = to_of_node(mac->fw_node); + return 0; err_close_dpmac: @@ -400,6 +415,8 @@ void dpaa2_mac_close(struct dpaa2_mac *mac) struct fsl_mc_device *dpmac_dev = mac->mc_dev; dpmac_close(mac->mc_io, 0, dpmac_dev->mc_handle); + if (mac->fw_node) + fwnode_handle_put(mac->fw_node); } static char dpaa2_mac_ethtool_stats[][ETH_GSTRING_LEN] = { diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h index 13d42dd58ec9..7842cbb2207a 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h @@ -24,6 +24,7 @@ struct dpaa2_mac { phy_interface_t if_mode; enum dpmac_link_type if_link_type; struct lynx_pcs *pcs; + struct fwnode_handle *fw_node; }; bool dpaa2_mac_is_type_fixed(struct fsl_mc_device *dpmac_dev, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 05de37c3b64c..f3d12d0714fb 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1625,7 +1625,7 @@ static int dpaa2_switch_port_bridge_flags(struct net_device *netdev, return 0; } -static int dpaa2_switch_port_attr_set(struct net_device *netdev, +static int dpaa2_switch_port_attr_set(struct net_device *netdev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c index 8b356c485507..ee1468e3eaa3 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c @@ -99,15 +99,13 @@ EXPORT_SYMBOL(enetc_ierb_register_pf); static int enetc_ierb_probe(struct platform_device *pdev) { struct enetc_ierb *ierb; - struct resource *res; void __iomem *regs; ierb = devm_kzalloc(&pdev->dev, sizeof(*ierb), GFP_KERNEL); if (!ierb) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - regs = devm_ioremap_resource(&pdev->dev, res); + regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(regs)) return PTR_ERR(regs); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 31274325159a..c84f6c226743 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) /* Copyright 2017-2019 NXP */ +#include #include #include #include @@ -17,15 +18,15 @@ static void enetc_pf_get_primary_mac_addr(struct enetc_hw *hw, int si, u8 *addr) u32 upper = __raw_readl(hw->port + ENETC_PSIPMAR0(si)); u16 lower = __raw_readw(hw->port + ENETC_PSIPMAR1(si)); - *(u32 *)addr = upper; - *(u16 *)(addr + 4) = lower; + put_unaligned_le32(upper, addr); + put_unaligned_le16(lower, addr + 4); } static void enetc_pf_set_primary_mac_addr(struct enetc_hw *hw, int si, const u8 *addr) { - u32 upper = *(const u32 *)addr; - u16 lower = *(const u16 *)(addr + 4); + u32 upper = get_unaligned_le32(addr); + u16 lower = get_unaligned_le16(addr + 4); __raw_writel(upper, hw->port + ENETC_PSIPMAR0(si)); __raw_writew(lower, hw->port + ENETC_PSIPMAR1(si)); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index af699f2ad095..4577226d3c6a 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -465,8 +465,13 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv, struct streamid_conf *si_conf; u16 data_size; dma_addr_t dma; + int port; int err; + port = enetc_pf_to_port(priv->si->pdev); + if (port < 0) + return -EINVAL; + if (sid->index >= priv->psfp_cap.max_streamid) return -EINVAL; @@ -499,7 +504,7 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv, si_conf = &cbd.sid_set; /* Only one port supported for one entry, set itself */ - si_conf->iports = cpu_to_le32(1 << enetc_pf_to_port(priv->si->pdev)); + si_conf->iports = cpu_to_le32(1 << port); si_conf->id_type = 1; si_conf->oui[2] = 0x0; si_conf->oui[1] = 0x80; @@ -524,7 +529,7 @@ static int enetc_streamid_hw_set(struct enetc_ndev_priv *priv, si_conf->en = 0x80; si_conf->stream_handle = cpu_to_le32(sid->handle); - si_conf->iports = cpu_to_le32(1 << enetc_pf_to_port(priv->si->pdev)); + si_conf->iports = cpu_to_le32(1 << port); si_conf->id_type = sid->filtertype; si_conf->oui[2] = 0x0; si_conf->oui[1] = 0x80; @@ -567,6 +572,11 @@ static int enetc_streamfilter_hw_set(struct enetc_ndev_priv *priv, { struct enetc_cbd cbd = {.cmd = 0}; struct sfi_conf *sfi_config; + int port; + + port = enetc_pf_to_port(priv->si->pdev); + if (port < 0) + return -EINVAL; cbd.index = cpu_to_le16(sfi->index); cbd.cls = BDCR_CMD_STREAM_FILTER; @@ -586,8 +596,7 @@ static int enetc_streamfilter_hw_set(struct enetc_ndev_priv *priv, } sfi_config->sg_inst_table_index = cpu_to_le16(sfi->gate_id); - sfi_config->input_ports = - cpu_to_le32(1 << enetc_pf_to_port(priv->si->pdev)); + sfi_config->input_ports = cpu_to_le32(1 << port); /* The priority value which may be matched against the * frame’s priority value to determine a match for this entry. @@ -1548,7 +1557,7 @@ int enetc_setup_tc_psfp(struct net_device *ndev, void *type_data) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct flow_block_offload *f = type_data; - int err; + int port, err; err = flow_block_cb_setup_simple(f, &enetc_block_cb_list, enetc_setup_tc_block_cb, @@ -1558,10 +1567,18 @@ int enetc_setup_tc_psfp(struct net_device *ndev, void *type_data) switch (f->command) { case FLOW_BLOCK_BIND: - set_bit(enetc_pf_to_port(priv->si->pdev), &epsfp.dev_bitmap); + port = enetc_pf_to_port(priv->si->pdev); + if (port < 0) + return -EINVAL; + + set_bit(port, &epsfp.dev_bitmap); break; case FLOW_BLOCK_UNBIND: - clear_bit(enetc_pf_to_port(priv->si->pdev), &epsfp.dev_bitmap); + port = enetc_pf_to_port(priv->si->pdev); + if (port < 0) + return -EINVAL; + + clear_bit(port, &epsfp.dev_bitmap); if (!epsfp.dev_bitmap) clean_psfp_all(); break; diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 0602d5d5d2ee..2e002e4b4b4a 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -467,6 +467,11 @@ struct bufdesc_ex { */ #define FEC_QUIRK_NO_HARD_RESET (1 << 18) +/* i.MX6SX ENET IP supports multiple queues (3 queues), use this quirk to + * represents this ENET IP. + */ +#define FEC_QUIRK_HAS_MULTI_QUEUES (1 << 19) + struct bufdesc_prop { int qid; /* Address of Rx and Tx buffers */ diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index ad82cffc6f3f..8aea707a65a7 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -76,6 +76,8 @@ static void fec_enet_itr_coal_init(struct net_device *ndev); #define DRIVER_NAME "fec" +static const u16 fec_enet_vlan_pri_to_queue[8] = {0, 0, 1, 1, 1, 2, 2, 2}; + /* Pause frame feild and FIFO threshold */ #define FEC_ENET_FCE (1 << 5) #define FEC_ENET_RSEM_V 0x84 @@ -122,7 +124,7 @@ static const struct fec_devinfo fec_imx6x_info = { FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB | FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE | FEC_QUIRK_HAS_RACC | FEC_QUIRK_HAS_COALESCE | - FEC_QUIRK_CLEAR_SETUP_MII, + FEC_QUIRK_CLEAR_SETUP_MII | FEC_QUIRK_HAS_MULTI_QUEUES, }; static const struct fec_devinfo fec_imx6ul_info = { @@ -421,6 +423,7 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq, estatus |= FEC_TX_BD_FTYPE(txq->bd.qid); if (skb->ip_summed == CHECKSUM_PARTIAL) estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS; + ebdp->cbd_bdu = 0; ebdp->cbd_esc = cpu_to_fec32(estatus); } @@ -954,7 +957,7 @@ fec_restart(struct net_device *ndev) * For i.MX6SX SOC, enet use AXI bus, we use disable MAC * instead of reset MAC itself. */ - if (fep->quirks & FEC_QUIRK_HAS_AVB || + if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES || ((fep->quirks & FEC_QUIRK_NO_HARD_RESET) && fep->link)) { writel(0, fep->hwp + FEC_ECNTRL); } else { @@ -1165,7 +1168,7 @@ fec_stop(struct net_device *ndev) * instead of reset MAC itself. */ if (!(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) { - if (fep->quirks & FEC_QUIRK_HAS_AVB) { + if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES) { writel(0, fep->hwp + FEC_ECNTRL); } else { writel(1, fep->hwp + FEC_ECNTRL); @@ -2570,7 +2573,7 @@ static void fec_enet_itr_coal_set(struct net_device *ndev) writel(tx_itr, fep->hwp + FEC_TXIC0); writel(rx_itr, fep->hwp + FEC_RXIC0); - if (fep->quirks & FEC_QUIRK_HAS_AVB) { + if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES) { writel(tx_itr, fep->hwp + FEC_TXIC1); writel(rx_itr, fep->hwp + FEC_RXIC1); writel(tx_itr, fep->hwp + FEC_TXIC2); @@ -3239,10 +3242,40 @@ static int fec_set_features(struct net_device *netdev, return 0; } +static u16 fec_enet_get_raw_vlan_tci(struct sk_buff *skb) +{ + struct vlan_ethhdr *vhdr; + unsigned short vlan_TCI = 0; + + if (skb->protocol == htons(ETH_P_ALL)) { + vhdr = (struct vlan_ethhdr *)(skb->data); + vlan_TCI = ntohs(vhdr->h_vlan_TCI); + } + + return vlan_TCI; +} + +static u16 fec_enet_select_queue(struct net_device *ndev, struct sk_buff *skb, + struct net_device *sb_dev) +{ + struct fec_enet_private *fep = netdev_priv(ndev); + u16 vlan_tag; + + if (!(fep->quirks & FEC_QUIRK_HAS_AVB)) + return netdev_pick_tx(ndev, skb, NULL); + + vlan_tag = fec_enet_get_raw_vlan_tci(skb); + if (!vlan_tag) + return vlan_tag; + + return fec_enet_vlan_pri_to_queue[vlan_tag >> 13]; +} + static const struct net_device_ops fec_netdev_ops = { .ndo_open = fec_enet_open, .ndo_stop = fec_enet_close, .ndo_start_xmit = fec_enet_start_xmit, + .ndo_select_queue = fec_enet_select_queue, .ndo_set_rx_mode = set_multicast_list, .ndo_validate_addr = eth_validate_addr, .ndo_tx_timeout = fec_timeout, @@ -3371,7 +3404,7 @@ static int fec_enet_init(struct net_device *ndev) fep->csum_flags |= FLAG_RX_CSUM_ENABLED; } - if (fep->quirks & FEC_QUIRK_HAS_AVB) { + if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES) { fep->tx_align = 0; fep->rx_align = 0x3f; } diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index f2945abdb041..9646483137c4 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -274,32 +274,44 @@ static void gfar_configure_coalescing_all(struct gfar_private *priv) gfar_configure_coalescing(priv, 0xFF, 0xFF); } -static struct net_device_stats *gfar_get_stats(struct net_device *dev) +static void gfar_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct gfar_private *priv = netdev_priv(dev); - unsigned long rx_packets = 0, rx_bytes = 0, rx_dropped = 0; - unsigned long tx_packets = 0, tx_bytes = 0; int i; for (i = 0; i < priv->num_rx_queues; i++) { - rx_packets += priv->rx_queue[i]->stats.rx_packets; - rx_bytes += priv->rx_queue[i]->stats.rx_bytes; - rx_dropped += priv->rx_queue[i]->stats.rx_dropped; + stats->rx_packets += priv->rx_queue[i]->stats.rx_packets; + stats->rx_bytes += priv->rx_queue[i]->stats.rx_bytes; + stats->rx_dropped += priv->rx_queue[i]->stats.rx_dropped; } - dev->stats.rx_packets = rx_packets; - dev->stats.rx_bytes = rx_bytes; - dev->stats.rx_dropped = rx_dropped; - for (i = 0; i < priv->num_tx_queues; i++) { - tx_bytes += priv->tx_queue[i]->stats.tx_bytes; - tx_packets += priv->tx_queue[i]->stats.tx_packets; + stats->tx_bytes += priv->tx_queue[i]->stats.tx_bytes; + stats->tx_packets += priv->tx_queue[i]->stats.tx_packets; } - dev->stats.tx_bytes = tx_bytes; - dev->stats.tx_packets = tx_packets; + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) { + struct rmon_mib __iomem *rmon = &priv->gfargrp[0].regs->rmon; + unsigned long flags; + u32 rdrp, car, car_before; + u64 rdrp_offset; - return &dev->stats; + spin_lock_irqsave(&priv->rmon_overflow.lock, flags); + car = gfar_read(&rmon->car1) & CAR1_C1RDR; + do { + car_before = car; + rdrp = gfar_read(&rmon->rdrp); + car = gfar_read(&rmon->car1) & CAR1_C1RDR; + } while (car != car_before); + if (car) { + priv->rmon_overflow.rdrp++; + gfar_write(&rmon->car1, car); + } + rdrp_offset = priv->rmon_overflow.rdrp; + spin_unlock_irqrestore(&priv->rmon_overflow.lock, flags); + + stats->rx_missed_errors = rdrp + (rdrp_offset << 16); + } } /* Set the appropriate hash bit for the given addr */ @@ -390,7 +402,8 @@ static void gfar_ints_enable(struct gfar_private *priv) for (i = 0; i < priv->num_grps; i++) { struct gfar __iomem *regs = priv->gfargrp[i].regs; /* Unmask the interrupts we look for */ - gfar_write(®s->imask, IMASK_DEFAULT); + gfar_write(®s->imask, + IMASK_DEFAULT | priv->rmon_overflow.imask); } } @@ -2298,7 +2311,7 @@ static irqreturn_t gfar_receive(int irq, void *grp_id) if (likely(napi_schedule_prep(&grp->napi_rx))) { spin_lock_irqsave(&grp->grplock, flags); imask = gfar_read(&grp->regs->imask); - imask &= IMASK_RX_DISABLED; + imask &= IMASK_RX_DISABLED | grp->priv->rmon_overflow.imask; gfar_write(&grp->regs->imask, imask); spin_unlock_irqrestore(&grp->grplock, flags); __napi_schedule(&grp->napi_rx); @@ -2322,7 +2335,7 @@ static irqreturn_t gfar_transmit(int irq, void *grp_id) if (likely(napi_schedule_prep(&grp->napi_tx))) { spin_lock_irqsave(&grp->grplock, flags); imask = gfar_read(&grp->regs->imask); - imask &= IMASK_TX_DISABLED; + imask &= IMASK_TX_DISABLED | grp->priv->rmon_overflow.imask; gfar_write(&grp->regs->imask, imask); spin_unlock_irqrestore(&grp->grplock, flags); __napi_schedule(&grp->napi_tx); @@ -2693,6 +2706,18 @@ static irqreturn_t gfar_error(int irq, void *grp_id) } netif_dbg(priv, tx_err, dev, "Transmit Error\n"); } + if (events & IEVENT_MSRO) { + struct rmon_mib __iomem *rmon = ®s->rmon; + u32 car; + + spin_lock(&priv->rmon_overflow.lock); + car = gfar_read(&rmon->car1) & CAR1_C1RDR; + if (car) { + priv->rmon_overflow.rdrp++; + gfar_write(&rmon->car1, car); + } + spin_unlock(&priv->rmon_overflow.lock); + } if (events & IEVENT_BSY) { dev->stats.rx_over_errors++; atomic64_inc(&priv->extra_stats.rx_bsy); @@ -3109,11 +3134,14 @@ static void gfar_hw_init(struct gfar_private *priv) /* Zero out the rmon mib registers if it has them */ if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) { - memset_io(&(regs->rmon), 0, sizeof(struct rmon_mib)); + memset_io(®s->rmon, 0, offsetof(struct rmon_mib, car1)); /* Mask off the CAM interrupts */ gfar_write(®s->rmon.cam1, 0xffffffff); gfar_write(®s->rmon.cam2, 0xffffffff); + /* Clear the CAR registers (w1c style) */ + gfar_write(®s->rmon.car1, 0xffffffff); + gfar_write(®s->rmon.car2, 0xffffffff); } /* Initialize ECNTRL */ @@ -3157,7 +3185,7 @@ static const struct net_device_ops gfar_netdev_ops = { .ndo_set_rx_mode = gfar_set_multi, .ndo_tx_timeout = gfar_timeout, .ndo_do_ioctl = gfar_ioctl, - .ndo_get_stats = gfar_get_stats, + .ndo_get_stats64 = gfar_get_stats64, .ndo_change_carrier = fixed_phy_change_carrier, .ndo_set_mac_address = gfar_set_mac_addr, .ndo_validate_addr = eth_validate_addr, @@ -3267,6 +3295,14 @@ static int gfar_probe(struct platform_device *ofdev) gfar_hw_init(priv); + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) { + struct rmon_mib __iomem *rmon = &priv->gfargrp[0].regs->rmon; + + spin_lock_init(&priv->rmon_overflow.lock); + priv->rmon_overflow.imask = IMASK_MSRO; + gfar_write(&rmon->cam1, gfar_read(&rmon->cam1) & ~CAM1_M1RDR); + } + /* Carrier starts down, phylib will bring it up */ netif_carrier_off(dev); diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index 5ea47df93e5e..ca5e14f908fe 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -445,6 +445,60 @@ struct ethtool_rx_list { #define RQFPR_PER 0x00000002 #define RQFPR_EER 0x00000001 +/* CAR1 bits */ +#define CAR1_C164 0x80000000 +#define CAR1_C1127 0x40000000 +#define CAR1_C1255 0x20000000 +#define CAR1_C1511 0x10000000 +#define CAR1_C11K 0x08000000 +#define CAR1_C1MAX 0x04000000 +#define CAR1_C1MGV 0x02000000 +#define CAR1_C1REJ 0x00020000 +#define CAR1_C1RBY 0x00010000 +#define CAR1_C1RPK 0x00008000 +#define CAR1_C1RFC 0x00004000 +#define CAR1_C1RMC 0x00002000 +#define CAR1_C1RBC 0x00001000 +#define CAR1_C1RXC 0x00000800 +#define CAR1_C1RXP 0x00000400 +#define CAR1_C1RXU 0x00000200 +#define CAR1_C1RAL 0x00000100 +#define CAR1_C1RFL 0x00000080 +#define CAR1_C1RCD 0x00000040 +#define CAR1_C1RCS 0x00000020 +#define CAR1_C1RUN 0x00000010 +#define CAR1_C1ROV 0x00000008 +#define CAR1_C1RFR 0x00000004 +#define CAR1_C1RJB 0x00000002 +#define CAR1_C1RDR 0x00000001 + +/* CAM1 bits */ +#define CAM1_M164 0x80000000 +#define CAM1_M1127 0x40000000 +#define CAM1_M1255 0x20000000 +#define CAM1_M1511 0x10000000 +#define CAM1_M11K 0x08000000 +#define CAM1_M1MAX 0x04000000 +#define CAM1_M1MGV 0x02000000 +#define CAM1_M1REJ 0x00020000 +#define CAM1_M1RBY 0x00010000 +#define CAM1_M1RPK 0x00008000 +#define CAM1_M1RFC 0x00004000 +#define CAM1_M1RMC 0x00002000 +#define CAM1_M1RBC 0x00001000 +#define CAM1_M1RXC 0x00000800 +#define CAM1_M1RXP 0x00000400 +#define CAM1_M1RXU 0x00000200 +#define CAM1_M1RAL 0x00000100 +#define CAM1_M1RFL 0x00000080 +#define CAM1_M1RCD 0x00000040 +#define CAM1_M1RCS 0x00000020 +#define CAM1_M1RUN 0x00000010 +#define CAM1_M1ROV 0x00000008 +#define CAM1_M1RFR 0x00000004 +#define CAM1_M1RJB 0x00000002 +#define CAM1_M1RDR 0x00000001 + /* TxBD status field bits */ #define TXBD_READY 0x8000 #define TXBD_PADCRC 0x4000 @@ -609,6 +663,15 @@ struct rmon_mib u32 cam2; /* 0x.73c - Carry Mask Register Two */ }; +struct rmon_overflow { + /* lock for synchronization of the rdrp field of this struct, and + * CAR1/CAR2 registers + */ + spinlock_t lock; + u32 imask; + u64 rdrp; +}; + struct gfar_extra_stats { atomic64_t rx_alloc_err; atomic64_t rx_large; @@ -913,8 +976,8 @@ enum { * Per TX queue stats */ struct tx_q_stats { - unsigned long tx_packets; - unsigned long tx_bytes; + u64 tx_packets; + u64 tx_bytes; }; /** @@ -963,9 +1026,9 @@ struct gfar_priv_tx_q { * Per RX queue stats */ struct rx_q_stats { - unsigned long rx_packets; - unsigned long rx_bytes; - unsigned long rx_dropped; + u64 rx_packets; + u64 rx_bytes; + u64 rx_dropped; }; struct gfar_rx_buff { @@ -1096,6 +1159,7 @@ struct gfar_private { /* Network Statistics */ struct gfar_extra_stats extra_stats; + struct rmon_overflow rmon_overflow; /* PHY stuff */ phy_interface_t interface; diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index e0936510fa34..0acfafb73db1 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -3590,10 +3590,9 @@ static int ucc_geth_probe(struct platform_device* ofdev) if ((ucc_num < 0) || (ucc_num > 7)) return -ENODEV; - ug_info = kmalloc(sizeof(*ug_info), GFP_KERNEL); + ug_info = kmemdup(&ugeth_primary_info, sizeof(*ug_info), GFP_KERNEL); if (ug_info == NULL) return -ENOMEM; - memcpy(ug_info, &ugeth_primary_info, sizeof(*ug_info)); ug_info->uf_info.ucc_num = ucc_num; diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c index bfa2826c5545..0b68852379da 100644 --- a/drivers/net/ethernet/freescale/xgmac_mdio.c +++ b/drivers/net/ethernet/freescale/xgmac_mdio.c @@ -2,6 +2,7 @@ * QorIQ 10G MDIO Controller * * Copyright 2012 Freescale Semiconductor, Inc. + * Copyright 2021 NXP * * Authors: Andy Fleming * Timur Tabi @@ -11,15 +12,17 @@ * kind, whether express or implied. */ -#include -#include +#include +#include #include -#include -#include +#include #include +#include #include -#include #include +#include +#include +#include /* Number of microseconds to wait for a register to respond */ #define TIMEOUT 1000 @@ -243,10 +246,10 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum) static int xgmac_mdio_probe(struct platform_device *pdev) { - struct device_node *np = pdev->dev.of_node; - struct mii_bus *bus; - struct resource *res; + struct fwnode_handle *fwnode; struct mdio_fsl_priv *priv; + struct resource *res; + struct mii_bus *bus; int ret; /* In DPAA-1, MDIO is one of the many FMan sub-devices. The FMan @@ -279,13 +282,22 @@ static int xgmac_mdio_probe(struct platform_device *pdev) goto err_ioremap; } + /* For both ACPI and DT cases, endianness of MDIO controller + * needs to be specified using "little-endian" property. + */ priv->is_little_endian = device_property_read_bool(&pdev->dev, "little-endian"); priv->has_a011043 = device_property_read_bool(&pdev->dev, "fsl,erratum-a011043"); - ret = of_mdiobus_register(bus, np); + fwnode = pdev->dev.fwnode; + if (is_of_node(fwnode)) + ret = of_mdiobus_register(bus, to_of_node(fwnode)); + else if (is_acpi_node(fwnode)) + ret = acpi_mdiobus_register(bus, fwnode); + else + ret = -EINVAL; if (ret) { dev_err(&pdev->dev, "cannot register MDIO bus\n"); goto err_registration; diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c index b0c0504950d8..62c0bed82ced 100644 --- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c +++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c @@ -812,9 +812,9 @@ static netdev_tx_t fjn_start_xmit(struct sk_buff *skb, if (length < ETH_ZLEN) { - if (skb_padto(skb, ETH_ZLEN)) - return NETDEV_TX_OK; - length = ETH_ZLEN; + if (skb_padto(skb, ETH_ZLEN)) + return NETDEV_TX_OK; + length = ETH_ZLEN; } netif_stop_queue(dev); diff --git a/drivers/net/ethernet/google/Kconfig b/drivers/net/ethernet/google/Kconfig index b8f04d052fda..8641a00f8e63 100644 --- a/drivers/net/ethernet/google/Kconfig +++ b/drivers/net/ethernet/google/Kconfig @@ -17,7 +17,7 @@ if NET_VENDOR_GOOGLE config GVE tristate "Google Virtual NIC (gVNIC) support" - depends on PCI_MSI + depends on (PCI_MSI && (X86 || CPU_LITTLE_ENDIAN)) help This driver supports Google Virtual NIC (gVNIC)" diff --git a/drivers/net/ethernet/google/gve/Makefile b/drivers/net/ethernet/google/gve/Makefile index 3354ce40eb97..b9a6be76531b 100644 --- a/drivers/net/ethernet/google/gve/Makefile +++ b/drivers/net/ethernet/google/gve/Makefile @@ -1,4 +1,4 @@ # Makefile for the Google virtual Ethernet (gve) driver obj-$(CONFIG_GVE) += gve.o -gve-objs := gve_main.o gve_tx.o gve_rx.o gve_ethtool.o gve_adminq.o +gve-objs := gve_main.o gve_tx.o gve_tx_dqo.o gve_rx.o gve_rx_dqo.o gve_ethtool.o gve_adminq.o gve_utils.o diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index daf07c0f790b..1d3188e8e3b3 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0 OR MIT) * Google virtual Ethernet (gve) driver * - * Copyright (C) 2015-2019 Google, Inc. + * Copyright (C) 2015-2021 Google, Inc. */ #ifndef _GVE_H_ @@ -11,7 +11,9 @@ #include #include #include + #include "gve_desc.h" +#include "gve_desc_dqo.h" #ifndef PCI_VENDOR_ID_GOOGLE #define PCI_VENDOR_ID_GOOGLE 0x1ae0 @@ -40,6 +42,11 @@ #define GVE_DATA_SLOT_ADDR_PAGE_MASK (~(PAGE_SIZE - 1)) +/* PTYPEs are always 10 bits. */ +#define GVE_NUM_PTYPES 1024 + +#define GVE_RX_BUFFER_SIZE_DQO 2048 + /* Each slot in the desc ring has a 1:1 mapping to a slot in the data ring */ struct gve_rx_desc_queue { struct gve_rx_desc *desc_ring; /* the descriptor ring */ @@ -51,7 +58,8 @@ struct gve_rx_desc_queue { struct gve_rx_slot_page_info { struct page *page; void *page_address; - u8 page_offset; /* flipped to second half? */ + u32 page_offset; /* offset to write to in page */ + int pagecnt_bias; /* expected pagecnt if only the driver has a ref */ u8 can_flip; }; @@ -76,17 +84,117 @@ struct gve_rx_data_queue { struct gve_priv; -/* An RX ring that contains a power-of-two sized desc and data ring. */ +/* RX buffer queue for posting buffers to HW. + * Each RX (completion) queue has a corresponding buffer queue. + */ +struct gve_rx_buf_queue_dqo { + struct gve_rx_desc_dqo *desc_ring; + dma_addr_t bus; + u32 head; /* Pointer to start cleaning buffers at. */ + u32 tail; /* Last posted buffer index + 1 */ + u32 mask; /* Mask for indices to the size of the ring */ +}; + +/* RX completion queue to receive packets from HW. */ +struct gve_rx_compl_queue_dqo { + struct gve_rx_compl_desc_dqo *desc_ring; + dma_addr_t bus; + + /* Number of slots which did not have a buffer posted yet. We should not + * post more buffers than the queue size to avoid HW overrunning the + * queue. + */ + int num_free_slots; + + /* HW uses a "generation bit" to notify SW of new descriptors. When a + * descriptor's generation bit is different from the current generation, + * that descriptor is ready to be consumed by SW. + */ + u8 cur_gen_bit; + + /* Pointer into desc_ring where the next completion descriptor will be + * received. + */ + u32 head; + u32 mask; /* Mask for indices to the size of the ring */ +}; + +/* Stores state for tracking buffers posted to HW */ +struct gve_rx_buf_state_dqo { + /* The page posted to HW. */ + struct gve_rx_slot_page_info page_info; + + /* The DMA address corresponding to `page_info`. */ + dma_addr_t addr; + + /* Last offset into the page when it only had a single reference, at + * which point every other offset is free to be reused. + */ + u32 last_single_ref_offset; + + /* Linked list index to next element in the list, or -1 if none */ + s16 next; +}; + +/* `head` and `tail` are indices into an array, or -1 if empty. */ +struct gve_index_list { + s16 head; + s16 tail; +}; + +/* Contains datapath state used to represent an RX queue. */ struct gve_rx_ring { struct gve_priv *gve; - struct gve_rx_desc_queue desc; - struct gve_rx_data_queue data; + union { + /* GQI fields */ + struct { + struct gve_rx_desc_queue desc; + struct gve_rx_data_queue data; + + /* threshold for posting new buffs and descs */ + u32 db_threshold; + }; + + /* DQO fields. */ + struct { + struct gve_rx_buf_queue_dqo bufq; + struct gve_rx_compl_queue_dqo complq; + + struct gve_rx_buf_state_dqo *buf_states; + u16 num_buf_states; + + /* Linked list of gve_rx_buf_state_dqo. Index into + * buf_states, or -1 if empty. + */ + s16 free_buf_states; + + /* Linked list of gve_rx_buf_state_dqo. Indexes into + * buf_states, or -1 if empty. + * + * This list contains buf_states which are pointing to + * valid buffers. + * + * We use a FIFO here in order to increase the + * probability that buffers can be reused by increasing + * the time between usages. + */ + struct gve_index_list recycled_buf_states; + + /* Linked list of gve_rx_buf_state_dqo. Indexes into + * buf_states, or -1 if empty. + * + * This list contains buf_states which have buffers + * which cannot be reused yet. + */ + struct gve_index_list used_buf_states; + } dqo; + }; + u64 rbytes; /* free-running bytes received */ u64 rpackets; /* free-running packets received */ u32 cnt; /* free-running total number of completed packets */ u32 fill_cnt; /* free-running total number of descs and buffs posted */ u32 mask; /* masks the cnt and fill_cnt to the size of the ring */ - u32 db_threshold; /* threshold for posting new buffs and descs */ u64 rx_copybreak_pkt; /* free-running count of copybreak packets */ u64 rx_copied_pkt; /* free-running total number of copied packets */ u64 rx_skb_alloc_fail; /* free-running count of skb alloc fails */ @@ -97,6 +205,10 @@ struct gve_rx_ring { struct gve_queue_resources *q_resources; /* head and tail pointer idx */ dma_addr_t q_resources_bus; /* dma address for the queue resources */ struct u64_stats_sync statss; /* sync stats for 32bit archs */ + + /* head and tail of skb chain for the current packet or NULL if none */ + struct sk_buff *skb_head; + struct sk_buff *skb_tail; }; /* A TX desc ring entry */ @@ -137,23 +249,161 @@ struct gve_tx_fifo { struct gve_queue_page_list *qpl; /* QPL mapped into this FIFO */ }; -/* A TX ring that contains a power-of-two sized desc ring and a FIFO buffer */ +/* TX descriptor for DQO format */ +union gve_tx_desc_dqo { + struct gve_tx_pkt_desc_dqo pkt; + struct gve_tx_tso_context_desc_dqo tso_ctx; + struct gve_tx_general_context_desc_dqo general_ctx; +}; + +enum gve_packet_state { + /* Packet is in free list, available to be allocated. + * This should always be zero since state is not explicitly initialized. + */ + GVE_PACKET_STATE_UNALLOCATED, + /* Packet is expecting a regular data completion or miss completion */ + GVE_PACKET_STATE_PENDING_DATA_COMPL, + /* Packet has received a miss completion and is expecting a + * re-injection completion. + */ + GVE_PACKET_STATE_PENDING_REINJECT_COMPL, + /* No valid completion received within the specified timeout. */ + GVE_PACKET_STATE_TIMED_OUT_COMPL, +}; + +struct gve_tx_pending_packet_dqo { + struct sk_buff *skb; /* skb for this packet */ + + /* 0th element corresponds to the linear portion of `skb`, should be + * unmapped with `dma_unmap_single`. + * + * All others correspond to `skb`'s frags and should be unmapped with + * `dma_unmap_page`. + */ + struct gve_tx_dma_buf bufs[MAX_SKB_FRAGS + 1]; + u16 num_bufs; + + /* Linked list index to next element in the list, or -1 if none */ + s16 next; + + /* Linked list index to prev element in the list, or -1 if none. + * Used for tracking either outstanding miss completions or prematurely + * freed packets. + */ + s16 prev; + + /* Identifies the current state of the packet as defined in + * `enum gve_packet_state`. + */ + u8 state; + + /* If packet is an outstanding miss completion, then the packet is + * freed if the corresponding re-injection completion is not received + * before kernel jiffies exceeds timeout_jiffies. + */ + unsigned long timeout_jiffies; +}; + +/* Contains datapath state used to represent a TX queue. */ struct gve_tx_ring { /* Cacheline 0 -- Accessed & dirtied during transmit */ - struct gve_tx_fifo tx_fifo; - u32 req; /* driver tracked head pointer */ - u32 done; /* driver tracked tail pointer */ + union { + /* GQI fields */ + struct { + struct gve_tx_fifo tx_fifo; + u32 req; /* driver tracked head pointer */ + u32 done; /* driver tracked tail pointer */ + }; + + /* DQO fields. */ + struct { + /* Linked list of gve_tx_pending_packet_dqo. Index into + * pending_packets, or -1 if empty. + * + * This is a consumer list owned by the TX path. When it + * runs out, the producer list is stolen from the + * completion handling path + * (dqo_compl.free_pending_packets). + */ + s16 free_pending_packets; + + /* Cached value of `dqo_compl.hw_tx_head` */ + u32 head; + u32 tail; /* Last posted buffer index + 1 */ + + /* Index of the last descriptor with "report event" bit + * set. + */ + u32 last_re_idx; + } dqo_tx; + }; /* Cacheline 1 -- Accessed & dirtied during gve_clean_tx_done */ - __be32 last_nic_done ____cacheline_aligned; /* NIC tail pointer */ + union { + /* GQI fields */ + struct { + /* NIC tail pointer */ + __be32 last_nic_done; + }; + + /* DQO fields. */ + struct { + u32 head; /* Last read on compl_desc */ + + /* Tracks the current gen bit of compl_q */ + u8 cur_gen_bit; + + /* Linked list of gve_tx_pending_packet_dqo. Index into + * pending_packets, or -1 if empty. + * + * This is the producer list, owned by the completion + * handling path. When the consumer list + * (dqo_tx.free_pending_packets) is runs out, this list + * will be stolen. + */ + atomic_t free_pending_packets; + + /* Last TX ring index fetched by HW */ + atomic_t hw_tx_head; + + /* List to track pending packets which received a miss + * completion but not a corresponding reinjection. + */ + struct gve_index_list miss_completions; + + /* List to track pending packets that were completed + * before receiving a valid completion because they + * reached a specified timeout. + */ + struct gve_index_list timed_out_completions; + } dqo_compl; + } ____cacheline_aligned; u64 pkt_done; /* free-running - total packets completed */ u64 bytes_done; /* free-running - total bytes completed */ u64 dropped_pkt; /* free-running - total packets dropped */ u64 dma_mapping_error; /* count of dma mapping errors */ /* Cacheline 2 -- Read-mostly fields */ - union gve_tx_desc *desc ____cacheline_aligned; - struct gve_tx_buffer_state *info; /* Maps 1:1 to a desc */ + union { + /* GQI fields */ + struct { + union gve_tx_desc *desc; + + /* Maps 1:1 to a desc */ + struct gve_tx_buffer_state *info; + }; + + /* DQO fields. */ + struct { + union gve_tx_desc_dqo *tx_ring; + struct gve_tx_compl_desc *compl_ring; + + struct gve_tx_pending_packet_dqo *pending_packets; + s16 num_pending_packets; + + u32 complq_mask; /* complq size is complq_mask + 1 */ + } dqo; + } ____cacheline_aligned; struct netdev_queue *netdev_txq; struct gve_queue_resources *q_resources; /* head and tail pointer idx */ struct device *dev; @@ -167,6 +417,7 @@ struct gve_tx_ring { u32 ntfy_id; /* notification block index */ dma_addr_t bus; /* dma address of the descr ring */ dma_addr_t q_resources_bus; /* dma address of the queue resources */ + dma_addr_t complq_bus_dqo; /* dma address of the dqo.compl_ring */ struct u64_stats_sync statss; /* sync stats for 32bit archs */ } ____cacheline_aligned; @@ -194,6 +445,31 @@ struct gve_qpl_config { unsigned long *qpl_id_map; /* bitmap of used qpl ids */ }; +struct gve_options_dqo_rda { + u16 tx_comp_ring_entries; /* number of tx_comp descriptors */ + u16 rx_buff_ring_entries; /* number of rx_buff descriptors */ +}; + +struct gve_ptype { + u8 l3_type; /* `gve_l3_type` in gve_adminq.h */ + u8 l4_type; /* `gve_l4_type` in gve_adminq.h */ +}; + +struct gve_ptype_lut { + struct gve_ptype ptypes[GVE_NUM_PTYPES]; +}; + +/* GVE_QUEUE_FORMAT_UNSPECIFIED must be zero since 0 is the default value + * when the entire configure_device_resources command is zeroed out and the + * queue_format is not specified. + */ +enum gve_queue_format { + GVE_QUEUE_FORMAT_UNSPECIFIED = 0x0, + GVE_GQI_RDA_FORMAT = 0x1, + GVE_GQI_QPL_FORMAT = 0x2, + GVE_DQO_RDA_FORMAT = 0x3, +}; + struct gve_priv { struct net_device *dev; struct gve_tx_ring *tx; /* array of tx_cfg.num_queues */ @@ -216,7 +492,6 @@ struct gve_priv { u64 num_registered_pages; /* num pages registered with NIC */ u32 rx_copybreak; /* copy packets smaller than this */ u16 default_num_queues; /* default num queues to set up */ - u8 raw_addressing; /* 1 if this dev supports raw addressing, 0 otherwise */ struct gve_queue_config tx_cfg; struct gve_queue_config rx_cfg; @@ -251,6 +526,7 @@ struct gve_priv { u32 adminq_set_driver_parameter_cnt; u32 adminq_report_stats_cnt; u32 adminq_report_link_speed_cnt; + u32 adminq_get_ptype_map_cnt; /* Global stats */ u32 interface_up_cnt; /* count of times interface turned up since last reset */ @@ -275,6 +551,14 @@ struct gve_priv { /* Gvnic device link speed from hypervisor. */ u64 link_speed; + + struct gve_options_dqo_rda options_dqo_rda; + struct gve_ptype_lut *ptype_lut_dqo; + + /* Must be a power of two. */ + int data_buffer_size_dqo; + + enum gve_queue_format queue_format; }; enum gve_service_task_flags_bit { @@ -454,14 +738,20 @@ static inline u32 gve_rx_idx_to_ntfy(struct gve_priv *priv, u32 queue_idx) */ static inline u32 gve_num_tx_qpls(struct gve_priv *priv) { - return priv->raw_addressing ? 0 : priv->tx_cfg.num_queues; + if (priv->queue_format != GVE_GQI_QPL_FORMAT) + return 0; + + return priv->tx_cfg.num_queues; } /* Returns the number of rx queue page lists */ static inline u32 gve_num_rx_qpls(struct gve_priv *priv) { - return priv->raw_addressing ? 0 : priv->rx_cfg.num_queues; + if (priv->queue_format != GVE_GQI_QPL_FORMAT) + return 0; + + return priv->rx_cfg.num_queues; } /* Returns a pointer to the next available tx qpl in the list of qpls @@ -515,6 +805,12 @@ static inline enum dma_data_direction gve_qpl_dma_dir(struct gve_priv *priv, return DMA_FROM_DEVICE; } +static inline bool gve_is_gqi(struct gve_priv *priv) +{ + return priv->queue_format == GVE_GQI_RDA_FORMAT || + priv->queue_format == GVE_GQI_QPL_FORMAT; +} + /* buffers */ int gve_alloc_page(struct gve_priv *priv, struct device *dev, struct page **page, dma_addr_t *dma, @@ -525,14 +821,14 @@ void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma, netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev); bool gve_tx_poll(struct gve_notify_block *block, int budget); int gve_tx_alloc_rings(struct gve_priv *priv); -void gve_tx_free_rings(struct gve_priv *priv); +void gve_tx_free_rings_gqi(struct gve_priv *priv); __be32 gve_tx_load_event_counter(struct gve_priv *priv, struct gve_tx_ring *tx); /* rx handling */ void gve_rx_write_doorbell(struct gve_priv *priv, struct gve_rx_ring *rx); bool gve_rx_poll(struct gve_notify_block *block, int budget); int gve_rx_alloc_rings(struct gve_priv *priv); -void gve_rx_free_rings(struct gve_priv *priv); +void gve_rx_free_rings_gqi(struct gve_priv *priv); bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget, netdev_features_t feat); /* Reset */ diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 53864f200599..5bb56b454541 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) /* Google virtual Ethernet (gve) driver * - * Copyright (C) 2015-2019 Google, Inc. + * Copyright (C) 2015-2021 Google, Inc. */ #include @@ -18,6 +18,8 @@ "Expected: length=%d, feature_mask=%x.\n" \ "Actual: length=%d, feature_mask=%x.\n" +#define GVE_DEVICE_OPTION_TOO_BIG_FMT "Length of %s option larger than expected. Possible older version of guest driver.\n" + static struct gve_device_option *gve_get_next_option(struct gve_device_descriptor *descriptor, struct gve_device_option *option) @@ -33,28 +35,81 @@ struct gve_device_option *gve_get_next_option(struct gve_device_descriptor *desc static void gve_parse_device_option(struct gve_priv *priv, struct gve_device_descriptor *device_descriptor, - struct gve_device_option *option) + struct gve_device_option *option, + struct gve_device_option_gqi_rda **dev_op_gqi_rda, + struct gve_device_option_gqi_qpl **dev_op_gqi_qpl, + struct gve_device_option_dqo_rda **dev_op_dqo_rda) { + u32 req_feat_mask = be32_to_cpu(option->required_features_mask); u16 option_length = be16_to_cpu(option->option_length); u16 option_id = be16_to_cpu(option->option_id); + /* If the length or feature mask doesn't match, continue without + * enabling the feature. + */ switch (option_id) { - case GVE_DEV_OPT_ID_RAW_ADDRESSING: - /* If the length or feature mask doesn't match, - * continue without enabling the feature. - */ - if (option_length != GVE_DEV_OPT_LEN_RAW_ADDRESSING || - option->feat_mask != cpu_to_be32(GVE_DEV_OPT_FEAT_MASK_RAW_ADDRESSING)) { - dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT, "Raw Addressing", - GVE_DEV_OPT_LEN_RAW_ADDRESSING, - cpu_to_be32(GVE_DEV_OPT_FEAT_MASK_RAW_ADDRESSING), - option_length, option->feat_mask); - priv->raw_addressing = 0; - } else { - dev_info(&priv->pdev->dev, - "Raw addressing device option enabled.\n"); - priv->raw_addressing = 1; + case GVE_DEV_OPT_ID_GQI_RAW_ADDRESSING: + if (option_length != GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING || + req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RAW_ADDRESSING) { + dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT, + "Raw Addressing", + GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING, + GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RAW_ADDRESSING, + option_length, req_feat_mask); + break; } + + dev_info(&priv->pdev->dev, + "Gqi raw addressing device option enabled.\n"); + priv->queue_format = GVE_GQI_RDA_FORMAT; + break; + case GVE_DEV_OPT_ID_GQI_RDA: + if (option_length < sizeof(**dev_op_gqi_rda) || + req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RDA) { + dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT, + "GQI RDA", (int)sizeof(**dev_op_gqi_rda), + GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RDA, + option_length, req_feat_mask); + break; + } + + if (option_length > sizeof(**dev_op_gqi_rda)) { + dev_warn(&priv->pdev->dev, + GVE_DEVICE_OPTION_TOO_BIG_FMT, "GQI RDA"); + } + *dev_op_gqi_rda = (void *)(option + 1); + break; + case GVE_DEV_OPT_ID_GQI_QPL: + if (option_length < sizeof(**dev_op_gqi_qpl) || + req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_GQI_QPL) { + dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT, + "GQI QPL", (int)sizeof(**dev_op_gqi_qpl), + GVE_DEV_OPT_REQ_FEAT_MASK_GQI_QPL, + option_length, req_feat_mask); + break; + } + + if (option_length > sizeof(**dev_op_gqi_qpl)) { + dev_warn(&priv->pdev->dev, + GVE_DEVICE_OPTION_TOO_BIG_FMT, "GQI QPL"); + } + *dev_op_gqi_qpl = (void *)(option + 1); + break; + case GVE_DEV_OPT_ID_DQO_RDA: + if (option_length < sizeof(**dev_op_dqo_rda) || + req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_DQO_RDA) { + dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT, + "DQO RDA", (int)sizeof(**dev_op_dqo_rda), + GVE_DEV_OPT_REQ_FEAT_MASK_DQO_RDA, + option_length, req_feat_mask); + break; + } + + if (option_length > sizeof(**dev_op_dqo_rda)) { + dev_warn(&priv->pdev->dev, + GVE_DEVICE_OPTION_TOO_BIG_FMT, "DQO RDA"); + } + *dev_op_dqo_rda = (void *)(option + 1); break; default: /* If we don't recognize the option just continue @@ -65,6 +120,39 @@ void gve_parse_device_option(struct gve_priv *priv, } } +/* Process all device options for a given describe device call. */ +static int +gve_process_device_options(struct gve_priv *priv, + struct gve_device_descriptor *descriptor, + struct gve_device_option_gqi_rda **dev_op_gqi_rda, + struct gve_device_option_gqi_qpl **dev_op_gqi_qpl, + struct gve_device_option_dqo_rda **dev_op_dqo_rda) +{ + const int num_options = be16_to_cpu(descriptor->num_device_options); + struct gve_device_option *dev_opt; + int i; + + /* The options struct directly follows the device descriptor. */ + dev_opt = (void *)(descriptor + 1); + for (i = 0; i < num_options; i++) { + struct gve_device_option *next_opt; + + next_opt = gve_get_next_option(descriptor, dev_opt); + if (!next_opt) { + dev_err(&priv->dev->dev, + "options exceed device_descriptor's total length.\n"); + return -EINVAL; + } + + gve_parse_device_option(priv, descriptor, dev_opt, + dev_op_gqi_rda, dev_op_gqi_qpl, + dev_op_dqo_rda); + dev_opt = next_opt; + } + + return 0; +} + int gve_adminq_alloc(struct device *dev, struct gve_priv *priv) { priv->adminq = dma_alloc_coherent(dev, PAGE_SIZE, @@ -88,6 +176,7 @@ int gve_adminq_alloc(struct device *dev, struct gve_priv *priv) priv->adminq_set_driver_parameter_cnt = 0; priv->adminq_report_stats_cnt = 0; priv->adminq_report_link_speed_cnt = 0; + priv->adminq_get_ptype_map_cnt = 0; /* Setup Admin queue with the device */ iowrite32be(priv->adminq_bus_addr / PAGE_SIZE, @@ -293,6 +382,9 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv, case GVE_ADMINQ_REPORT_LINK_SPEED: priv->adminq_report_link_speed_cnt++; break; + case GVE_ADMINQ_GET_PTYPE_MAP: + priv->adminq_get_ptype_map_cnt++; + break; default: dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode); } @@ -305,7 +397,8 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv, * The caller is also responsible for making sure there are no commands * waiting to be executed. */ -static int gve_adminq_execute_cmd(struct gve_priv *priv, union gve_adminq_command *cmd_orig) +static int gve_adminq_execute_cmd(struct gve_priv *priv, + union gve_adminq_command *cmd_orig) { u32 tail, head; int err; @@ -350,6 +443,7 @@ int gve_adminq_configure_device_resources(struct gve_priv *priv, .irq_db_stride = cpu_to_be32(sizeof(priv->ntfy_blocks[0])), .ntfy_blk_msix_base_idx = cpu_to_be32(GVE_NTFY_BLK_BASE_MSIX_IDX), + .queue_format = priv->queue_format, }; return gve_adminq_execute_cmd(priv, &cmd); @@ -369,27 +463,32 @@ static int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_index) { struct gve_tx_ring *tx = &priv->tx[queue_index]; union gve_adminq_command cmd; - u32 qpl_id; - int err; - qpl_id = priv->raw_addressing ? GVE_RAW_ADDRESSING_QPL_ID : tx->tx_fifo.qpl->id; memset(&cmd, 0, sizeof(cmd)); cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_TX_QUEUE); cmd.create_tx_queue = (struct gve_adminq_create_tx_queue) { .queue_id = cpu_to_be32(queue_index), - .reserved = 0, .queue_resources_addr = cpu_to_be64(tx->q_resources_bus), .tx_ring_addr = cpu_to_be64(tx->bus), - .queue_page_list_id = cpu_to_be32(qpl_id), .ntfy_id = cpu_to_be32(tx->ntfy_id), }; - err = gve_adminq_issue_cmd(priv, &cmd); - if (err) - return err; + if (gve_is_gqi(priv)) { + u32 qpl_id = priv->queue_format == GVE_GQI_RDA_FORMAT ? + GVE_RAW_ADDRESSING_QPL_ID : tx->tx_fifo.qpl->id; - return 0; + cmd.create_tx_queue.queue_page_list_id = cpu_to_be32(qpl_id); + } else { + cmd.create_tx_queue.tx_ring_size = + cpu_to_be16(priv->tx_desc_cnt); + cmd.create_tx_queue.tx_comp_ring_addr = + cpu_to_be64(tx->complq_bus_dqo); + cmd.create_tx_queue.tx_comp_ring_size = + cpu_to_be16(priv->options_dqo_rda.tx_comp_ring_entries); + } + + return gve_adminq_issue_cmd(priv, &cmd); } int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 num_queues) @@ -410,28 +509,41 @@ static int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index) { struct gve_rx_ring *rx = &priv->rx[queue_index]; union gve_adminq_command cmd; - u32 qpl_id; - int err; - qpl_id = priv->raw_addressing ? GVE_RAW_ADDRESSING_QPL_ID : rx->data.qpl->id; memset(&cmd, 0, sizeof(cmd)); cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_RX_QUEUE); cmd.create_rx_queue = (struct gve_adminq_create_rx_queue) { .queue_id = cpu_to_be32(queue_index), - .index = cpu_to_be32(queue_index), - .reserved = 0, .ntfy_id = cpu_to_be32(rx->ntfy_id), .queue_resources_addr = cpu_to_be64(rx->q_resources_bus), - .rx_desc_ring_addr = cpu_to_be64(rx->desc.bus), - .rx_data_ring_addr = cpu_to_be64(rx->data.data_bus), - .queue_page_list_id = cpu_to_be32(qpl_id), }; - err = gve_adminq_issue_cmd(priv, &cmd); - if (err) - return err; + if (gve_is_gqi(priv)) { + u32 qpl_id = priv->queue_format == GVE_GQI_RDA_FORMAT ? + GVE_RAW_ADDRESSING_QPL_ID : rx->data.qpl->id; - return 0; + cmd.create_rx_queue.rx_desc_ring_addr = + cpu_to_be64(rx->desc.bus), + cmd.create_rx_queue.rx_data_ring_addr = + cpu_to_be64(rx->data.data_bus), + cmd.create_rx_queue.index = cpu_to_be32(queue_index); + cmd.create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id); + } else { + cmd.create_rx_queue.rx_ring_size = + cpu_to_be16(priv->rx_desc_cnt); + cmd.create_rx_queue.rx_desc_ring_addr = + cpu_to_be64(rx->dqo.complq.bus); + cmd.create_rx_queue.rx_data_ring_addr = + cpu_to_be64(rx->dqo.bufq.bus); + cmd.create_rx_queue.packet_buffer_size = + cpu_to_be16(priv->data_buffer_size_dqo); + cmd.create_rx_queue.rx_buff_ring_size = + cpu_to_be16(priv->options_dqo_rda.rx_buff_ring_entries); + cmd.create_rx_queue.enable_rsc = + !!(priv->dev->features & NETIF_F_LRO); + } + + return gve_adminq_issue_cmd(priv, &cmd); } int gve_adminq_create_rx_queues(struct gve_priv *priv, u32 num_queues) @@ -512,17 +624,51 @@ int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 num_queues) return gve_adminq_kick_and_wait(priv); } +static int gve_set_desc_cnt(struct gve_priv *priv, + struct gve_device_descriptor *descriptor) +{ + priv->tx_desc_cnt = be16_to_cpu(descriptor->tx_queue_entries); + if (priv->tx_desc_cnt * sizeof(priv->tx->desc[0]) < PAGE_SIZE) { + dev_err(&priv->pdev->dev, "Tx desc count %d too low\n", + priv->tx_desc_cnt); + return -EINVAL; + } + priv->rx_desc_cnt = be16_to_cpu(descriptor->rx_queue_entries); + if (priv->rx_desc_cnt * sizeof(priv->rx->desc.desc_ring[0]) + < PAGE_SIZE) { + dev_err(&priv->pdev->dev, "Rx desc count %d too low\n", + priv->rx_desc_cnt); + return -EINVAL; + } + return 0; +} + +static int +gve_set_desc_cnt_dqo(struct gve_priv *priv, + const struct gve_device_descriptor *descriptor, + const struct gve_device_option_dqo_rda *dev_op_dqo_rda) +{ + priv->tx_desc_cnt = be16_to_cpu(descriptor->tx_queue_entries); + priv->options_dqo_rda.tx_comp_ring_entries = + be16_to_cpu(dev_op_dqo_rda->tx_comp_ring_entries); + priv->rx_desc_cnt = be16_to_cpu(descriptor->rx_queue_entries); + priv->options_dqo_rda.rx_buff_ring_entries = + be16_to_cpu(dev_op_dqo_rda->rx_buff_ring_entries); + + return 0; +} + int gve_adminq_describe_device(struct gve_priv *priv) { + struct gve_device_option_gqi_rda *dev_op_gqi_rda = NULL; + struct gve_device_option_gqi_qpl *dev_op_gqi_qpl = NULL; + struct gve_device_option_dqo_rda *dev_op_dqo_rda = NULL; struct gve_device_descriptor *descriptor; - struct gve_device_option *dev_opt; union gve_adminq_command cmd; dma_addr_t descriptor_bus; - u16 num_options; int err = 0; u8 *mac; u16 mtu; - int i; memset(&cmd, 0, sizeof(cmd)); descriptor = dma_alloc_coherent(&priv->pdev->dev, PAGE_SIZE, @@ -540,21 +686,41 @@ int gve_adminq_describe_device(struct gve_priv *priv) if (err) goto free_device_descriptor; - priv->tx_desc_cnt = be16_to_cpu(descriptor->tx_queue_entries); - if (priv->tx_desc_cnt * sizeof(priv->tx->desc[0]) < PAGE_SIZE) { - dev_err(&priv->pdev->dev, "Tx desc count %d too low\n", priv->tx_desc_cnt); - err = -EINVAL; + err = gve_process_device_options(priv, descriptor, &dev_op_gqi_rda, + &dev_op_gqi_qpl, &dev_op_dqo_rda); + if (err) goto free_device_descriptor; + + /* If the GQI_RAW_ADDRESSING option is not enabled and the queue format + * is not set to GqiRda, choose the queue format in a priority order: + * DqoRda, GqiRda, GqiQpl. Use GqiQpl as default. + */ + if (priv->queue_format == GVE_GQI_RDA_FORMAT) { + dev_info(&priv->pdev->dev, + "Driver is running with GQI RDA queue format.\n"); + } else if (dev_op_dqo_rda) { + priv->queue_format = GVE_DQO_RDA_FORMAT; + dev_info(&priv->pdev->dev, + "Driver is running with DQO RDA queue format.\n"); + } else if (dev_op_gqi_rda) { + priv->queue_format = GVE_GQI_RDA_FORMAT; + dev_info(&priv->pdev->dev, + "Driver is running with GQI RDA queue format.\n"); + } else { + priv->queue_format = GVE_GQI_QPL_FORMAT; + dev_info(&priv->pdev->dev, + "Driver is running with GQI QPL queue format.\n"); } - priv->rx_desc_cnt = be16_to_cpu(descriptor->rx_queue_entries); - if (priv->rx_desc_cnt * sizeof(priv->rx->desc.desc_ring[0]) - < PAGE_SIZE || - priv->rx_desc_cnt * sizeof(priv->rx->data.data_ring[0]) - < PAGE_SIZE) { - dev_err(&priv->pdev->dev, "Rx desc count %d too low\n", priv->rx_desc_cnt); - err = -EINVAL; + if (gve_is_gqi(priv)) { + err = gve_set_desc_cnt(priv, descriptor); + } else { + /* DQO supports LRO. */ + priv->dev->hw_features |= NETIF_F_LRO; + err = gve_set_desc_cnt_dqo(priv, descriptor, dev_op_dqo_rda); + } + if (err) goto free_device_descriptor; - } + priv->max_registered_pages = be64_to_cpu(descriptor->max_registered_pages); mtu = be16_to_cpu(descriptor->mtu); @@ -570,32 +736,16 @@ int gve_adminq_describe_device(struct gve_priv *priv) dev_info(&priv->pdev->dev, "MAC addr: %pM\n", mac); priv->tx_pages_per_qpl = be16_to_cpu(descriptor->tx_pages_per_qpl); priv->rx_data_slot_cnt = be16_to_cpu(descriptor->rx_pages_per_qpl); - if (priv->rx_data_slot_cnt < priv->rx_desc_cnt) { + + if (gve_is_gqi(priv) && priv->rx_data_slot_cnt < priv->rx_desc_cnt) { dev_err(&priv->pdev->dev, "rx_data_slot_cnt cannot be smaller than rx_desc_cnt, setting rx_desc_cnt down to %d.\n", priv->rx_data_slot_cnt); priv->rx_desc_cnt = priv->rx_data_slot_cnt; } priv->default_num_queues = be16_to_cpu(descriptor->default_num_queues); - dev_opt = (void *)(descriptor + 1); - - num_options = be16_to_cpu(descriptor->num_device_options); - for (i = 0; i < num_options; i++) { - struct gve_device_option *next_opt; - - next_opt = gve_get_next_option(descriptor, dev_opt); - if (!next_opt) { - dev_err(&priv->dev->dev, - "options exceed device_descriptor's total length.\n"); - err = -EINVAL; - goto free_device_descriptor; - } - - gve_parse_device_option(priv, descriptor, dev_opt); - dev_opt = next_opt; - } free_device_descriptor: - dma_free_coherent(&priv->pdev->dev, sizeof(*descriptor), descriptor, + dma_free_coherent(&priv->pdev->dev, PAGE_SIZE, descriptor, descriptor_bus); return err; } @@ -701,3 +851,41 @@ int gve_adminq_report_link_speed(struct gve_priv *priv) link_speed_region_bus); return err; } + +int gve_adminq_get_ptype_map_dqo(struct gve_priv *priv, + struct gve_ptype_lut *ptype_lut) +{ + struct gve_ptype_map *ptype_map; + union gve_adminq_command cmd; + dma_addr_t ptype_map_bus; + int err = 0; + int i; + + memset(&cmd, 0, sizeof(cmd)); + ptype_map = dma_alloc_coherent(&priv->pdev->dev, sizeof(*ptype_map), + &ptype_map_bus, GFP_KERNEL); + if (!ptype_map) + return -ENOMEM; + + cmd.opcode = cpu_to_be32(GVE_ADMINQ_GET_PTYPE_MAP); + cmd.get_ptype_map = (struct gve_adminq_get_ptype_map) { + .ptype_map_len = cpu_to_be64(sizeof(*ptype_map)), + .ptype_map_addr = cpu_to_be64(ptype_map_bus), + }; + + err = gve_adminq_execute_cmd(priv, &cmd); + if (err) + goto err; + + /* Populate ptype_lut. */ + for (i = 0; i < GVE_NUM_PTYPES; i++) { + ptype_lut->ptypes[i].l3_type = + ptype_map->ptypes[i].l3_type; + ptype_lut->ptypes[i].l4_type = + ptype_map->ptypes[i].l4_type; + } +err: + dma_free_coherent(&priv->pdev->dev, sizeof(*ptype_map), ptype_map, + ptype_map_bus); + return err; +} diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index d320c2ffd87c..47c3d8f313fc 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0 OR MIT) * Google virtual Ethernet (gve) driver * - * Copyright (C) 2015-2019 Google, Inc. + * Copyright (C) 2015-2021 Google, Inc. */ #ifndef _GVE_ADMINQ_H @@ -22,7 +22,8 @@ enum gve_adminq_opcodes { GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES = 0x9, GVE_ADMINQ_SET_DRIVER_PARAMETER = 0xB, GVE_ADMINQ_REPORT_STATS = 0xC, - GVE_ADMINQ_REPORT_LINK_SPEED = 0xD + GVE_ADMINQ_REPORT_LINK_SPEED = 0xD, + GVE_ADMINQ_GET_PTYPE_MAP = 0xE, }; /* Admin queue status codes */ @@ -82,14 +83,54 @@ static_assert(sizeof(struct gve_device_descriptor) == 40); struct gve_device_option { __be16 option_id; __be16 option_length; - __be32 feat_mask; + __be32 required_features_mask; }; static_assert(sizeof(struct gve_device_option) == 8); -#define GVE_DEV_OPT_ID_RAW_ADDRESSING 0x1 -#define GVE_DEV_OPT_LEN_RAW_ADDRESSING 0x0 -#define GVE_DEV_OPT_FEAT_MASK_RAW_ADDRESSING 0x0 +struct gve_device_option_gqi_rda { + __be32 supported_features_mask; +}; + +static_assert(sizeof(struct gve_device_option_gqi_rda) == 4); + +struct gve_device_option_gqi_qpl { + __be32 supported_features_mask; +}; + +static_assert(sizeof(struct gve_device_option_gqi_qpl) == 4); + +struct gve_device_option_dqo_rda { + __be32 supported_features_mask; + __be16 tx_comp_ring_entries; + __be16 rx_buff_ring_entries; +}; + +static_assert(sizeof(struct gve_device_option_dqo_rda) == 8); + +/* Terminology: + * + * RDA - Raw DMA Addressing - Buffers associated with SKBs are directly DMA + * mapped and read/updated by the device. + * + * QPL - Queue Page Lists - Driver uses bounce buffers which are DMA mapped with + * the device for read/write and data is copied from/to SKBs. + */ +enum gve_dev_opt_id { + GVE_DEV_OPT_ID_GQI_RAW_ADDRESSING = 0x1, + GVE_DEV_OPT_ID_GQI_RDA = 0x2, + GVE_DEV_OPT_ID_GQI_QPL = 0x3, + GVE_DEV_OPT_ID_DQO_RDA = 0x4, +}; + +enum gve_dev_opt_req_feat_mask { + GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RAW_ADDRESSING = 0x0, + GVE_DEV_OPT_REQ_FEAT_MASK_GQI_RDA = 0x0, + GVE_DEV_OPT_REQ_FEAT_MASK_GQI_QPL = 0x0, + GVE_DEV_OPT_REQ_FEAT_MASK_DQO_RDA = 0x0, +}; + +#define GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING 0x0 struct gve_adminq_configure_device_resources { __be64 counter_array; @@ -98,9 +139,11 @@ struct gve_adminq_configure_device_resources { __be32 num_irq_dbs; __be32 irq_db_stride; __be32 ntfy_blk_msix_base_idx; + u8 queue_format; + u8 padding[7]; }; -static_assert(sizeof(struct gve_adminq_configure_device_resources) == 32); +static_assert(sizeof(struct gve_adminq_configure_device_resources) == 40); struct gve_adminq_register_page_list { __be32 page_list_id; @@ -125,9 +168,13 @@ struct gve_adminq_create_tx_queue { __be64 tx_ring_addr; __be32 queue_page_list_id; __be32 ntfy_id; + __be64 tx_comp_ring_addr; + __be16 tx_ring_size; + __be16 tx_comp_ring_size; + u8 padding[4]; }; -static_assert(sizeof(struct gve_adminq_create_tx_queue) == 32); +static_assert(sizeof(struct gve_adminq_create_tx_queue) == 48); struct gve_adminq_create_rx_queue { __be32 queue_id; @@ -138,10 +185,14 @@ struct gve_adminq_create_rx_queue { __be64 rx_desc_ring_addr; __be64 rx_data_ring_addr; __be32 queue_page_list_id; - u8 padding[4]; + __be16 rx_ring_size; + __be16 packet_buffer_size; + __be16 rx_buff_ring_size; + u8 enable_rsc; + u8 padding[5]; }; -static_assert(sizeof(struct gve_adminq_create_rx_queue) == 48); +static_assert(sizeof(struct gve_adminq_create_rx_queue) == 56); /* Queue resources that are shared with the device */ struct gve_queue_resources { @@ -226,6 +277,41 @@ enum gve_stat_names { RX_DROPS_INVALID_CHECKSUM = 68, }; +enum gve_l3_type { + /* Must be zero so zero initialized LUT is unknown. */ + GVE_L3_TYPE_UNKNOWN = 0, + GVE_L3_TYPE_OTHER, + GVE_L3_TYPE_IPV4, + GVE_L3_TYPE_IPV6, +}; + +enum gve_l4_type { + /* Must be zero so zero initialized LUT is unknown. */ + GVE_L4_TYPE_UNKNOWN = 0, + GVE_L4_TYPE_OTHER, + GVE_L4_TYPE_TCP, + GVE_L4_TYPE_UDP, + GVE_L4_TYPE_ICMP, + GVE_L4_TYPE_SCTP, +}; + +/* These are control path types for PTYPE which are the same as the data path + * types. + */ +struct gve_ptype_entry { + u8 l3_type; + u8 l4_type; +}; + +struct gve_ptype_map { + struct gve_ptype_entry ptypes[1 << 10]; /* PTYPES are always 10 bits. */ +}; + +struct gve_adminq_get_ptype_map { + __be64 ptype_map_len; + __be64 ptype_map_addr; +}; + union gve_adminq_command { struct { __be32 opcode; @@ -243,6 +329,7 @@ union gve_adminq_command { struct gve_adminq_set_driver_parameter set_driver_param; struct gve_adminq_report_stats report_stats; struct gve_adminq_report_link_speed report_link_speed; + struct gve_adminq_get_ptype_map get_ptype_map; }; }; u8 reserved[64]; @@ -271,4 +358,9 @@ int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu); int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len, dma_addr_t stats_report_addr, u64 interval); int gve_adminq_report_link_speed(struct gve_priv *priv); + +struct gve_ptype_lut; +int gve_adminq_get_ptype_map_dqo(struct gve_priv *priv, + struct gve_ptype_lut *ptype_lut); + #endif /* _GVE_ADMINQ_H */ diff --git a/drivers/net/ethernet/google/gve/gve_desc_dqo.h b/drivers/net/ethernet/google/gve/gve_desc_dqo.h new file mode 100644 index 000000000000..e8fe9adef7f2 --- /dev/null +++ b/drivers/net/ethernet/google/gve/gve_desc_dqo.h @@ -0,0 +1,256 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) + * Google virtual Ethernet (gve) driver + * + * Copyright (C) 2015-2021 Google, Inc. + */ + +/* GVE DQO Descriptor formats */ + +#ifndef _GVE_DESC_DQO_H_ +#define _GVE_DESC_DQO_H_ + +#include + +#define GVE_TX_MAX_HDR_SIZE_DQO 255 +#define GVE_TX_MIN_TSO_MSS_DQO 88 + +#ifndef __LITTLE_ENDIAN_BITFIELD +#error "Only little endian supported" +#endif + +/* Basic TX descriptor (DTYPE 0x0C) */ +struct gve_tx_pkt_desc_dqo { + __le64 buf_addr; + + /* Must be GVE_TX_PKT_DESC_DTYPE_DQO (0xc) */ + u8 dtype: 5; + + /* Denotes the last descriptor of a packet. */ + u8 end_of_packet: 1; + u8 checksum_offload_enable: 1; + + /* If set, will generate a descriptor completion for this descriptor. */ + u8 report_event: 1; + u8 reserved0; + __le16 reserved1; + + /* The TX completion associated with this packet will contain this tag. + */ + __le16 compl_tag; + u16 buf_size: 14; + u16 reserved2: 2; +} __packed; +static_assert(sizeof(struct gve_tx_pkt_desc_dqo) == 16); + +#define GVE_TX_PKT_DESC_DTYPE_DQO 0xc +#define GVE_TX_MAX_BUF_SIZE_DQO ((16 * 1024) - 1) + +/* Maximum number of data descriptors allowed per packet, or per-TSO segment. */ +#define GVE_TX_MAX_DATA_DESCS 10 + +/* Min gap between tail and head to avoid cacheline overlap */ +#define GVE_TX_MIN_DESC_PREVENT_CACHE_OVERLAP 4 + +/* "report_event" on TX packet descriptors may only be reported on the last + * descriptor of a TX packet, and they must be spaced apart with at least this + * value. + */ +#define GVE_TX_MIN_RE_INTERVAL 32 + +struct gve_tx_context_cmd_dtype { + u8 dtype: 5; + u8 tso: 1; + u8 reserved1: 2; + + u8 reserved2; +}; + +static_assert(sizeof(struct gve_tx_context_cmd_dtype) == 2); + +/* TX Native TSO Context DTYPE (0x05) + * + * "flex" fields allow the driver to send additional packet context to HW. + */ +struct gve_tx_tso_context_desc_dqo { + /* The L4 payload bytes that should be segmented. */ + u32 tso_total_len: 24; + u32 flex10: 8; + + /* Max segment size in TSO excluding headers. */ + u16 mss: 14; + u16 reserved: 2; + + u8 header_len; /* Header length to use for TSO offload */ + u8 flex11; + struct gve_tx_context_cmd_dtype cmd_dtype; + u8 flex0; + u8 flex5; + u8 flex6; + u8 flex7; + u8 flex8; + u8 flex9; +} __packed; +static_assert(sizeof(struct gve_tx_tso_context_desc_dqo) == 16); + +#define GVE_TX_TSO_CTX_DESC_DTYPE_DQO 0x5 + +/* General context descriptor for sending metadata. */ +struct gve_tx_general_context_desc_dqo { + u8 flex4; + u8 flex5; + u8 flex6; + u8 flex7; + u8 flex8; + u8 flex9; + u8 flex10; + u8 flex11; + struct gve_tx_context_cmd_dtype cmd_dtype; + u16 reserved; + u8 flex0; + u8 flex1; + u8 flex2; + u8 flex3; +} __packed; +static_assert(sizeof(struct gve_tx_general_context_desc_dqo) == 16); + +#define GVE_TX_GENERAL_CTX_DESC_DTYPE_DQO 0x4 + +/* Logical structure of metadata which is packed into context descriptor flex + * fields. + */ +struct gve_tx_metadata_dqo { + union { + struct { + u8 version; + + /* If `skb->l4_hash` is set, this value should be + * derived from `skb->hash`. + * + * A zero value means no l4_hash was associated with the + * skb. + */ + u16 path_hash: 15; + + /* Should be set to 1 if the flow associated with the + * skb had a rehash from the TCP stack. + */ + u16 rehash_event: 1; + } __packed; + u8 bytes[12]; + }; +} __packed; +static_assert(sizeof(struct gve_tx_metadata_dqo) == 12); + +#define GVE_TX_METADATA_VERSION_DQO 0 + +/* TX completion descriptor */ +struct gve_tx_compl_desc { + /* For types 0-4 this is the TX queue ID associated with this + * completion. + */ + u16 id: 11; + + /* See: GVE_COMPL_TYPE_DQO* */ + u16 type: 3; + u16 reserved0: 1; + + /* Flipped by HW to notify the descriptor is populated. */ + u16 generation: 1; + union { + /* For descriptor completions, this is the last index fetched + * by HW + 1. + */ + __le16 tx_head; + + /* For packet completions, this is the completion tag set on the + * TX packet descriptors. + */ + __le16 completion_tag; + }; + __le32 reserved1; +} __packed; +static_assert(sizeof(struct gve_tx_compl_desc) == 8); + +#define GVE_COMPL_TYPE_DQO_PKT 0x2 /* Packet completion */ +#define GVE_COMPL_TYPE_DQO_DESC 0x4 /* Descriptor completion */ +#define GVE_COMPL_TYPE_DQO_MISS 0x1 /* Miss path completion */ +#define GVE_COMPL_TYPE_DQO_REINJECTION 0x3 /* Re-injection completion */ + +/* Descriptor to post buffers to HW on buffer queue. */ +struct gve_rx_desc_dqo { + __le16 buf_id; /* ID returned in Rx completion descriptor */ + __le16 reserved0; + __le32 reserved1; + __le64 buf_addr; /* DMA address of the buffer */ + __le64 header_buf_addr; + __le64 reserved2; +} __packed; +static_assert(sizeof(struct gve_rx_desc_dqo) == 32); + +/* Descriptor for HW to notify SW of new packets received on RX queue. */ +struct gve_rx_compl_desc_dqo { + /* Must be 1 */ + u8 rxdid: 4; + u8 reserved0: 4; + + /* Packet originated from this system rather than the network. */ + u8 loopback: 1; + /* Set when IPv6 packet contains a destination options header or routing + * header. + */ + u8 ipv6_ex_add: 1; + /* Invalid packet was received. */ + u8 rx_error: 1; + u8 reserved1: 5; + + u16 packet_type: 10; + u16 ip_hdr_err: 1; + u16 udp_len_err: 1; + u16 raw_cs_invalid: 1; + u16 reserved2: 3; + + u16 packet_len: 14; + /* Flipped by HW to notify the descriptor is populated. */ + u16 generation: 1; + /* Should be zero. */ + u16 buffer_queue_id: 1; + + u16 header_len: 10; + u16 rsc: 1; + u16 split_header: 1; + u16 reserved3: 4; + + u8 descriptor_done: 1; + u8 end_of_packet: 1; + u8 header_buffer_overflow: 1; + u8 l3_l4_processed: 1; + u8 csum_ip_err: 1; + u8 csum_l4_err: 1; + u8 csum_external_ip_err: 1; + u8 csum_external_udp_err: 1; + + u8 status_error1; + + __le16 reserved5; + __le16 buf_id; /* Buffer ID which was sent on the buffer queue. */ + + union { + /* Packet checksum. */ + __le16 raw_cs; + /* Segment length for RSC packets. */ + __le16 rsc_seg_len; + }; + __le32 hash; + __le32 reserved6; + __le64 reserved7; +} __packed; + +static_assert(sizeof(struct gve_rx_compl_desc_dqo) == 32); + +/* Ringing the doorbell too often can hurt performance. + * + * HW requires this value to be at least 8. + */ +#define GVE_RX_BUF_THRESH_DQO 32 + +#endif /* _GVE_DESC_DQO_H_ */ diff --git a/drivers/net/ethernet/google/gve/gve_dqo.h b/drivers/net/ethernet/google/gve/gve_dqo.h new file mode 100644 index 000000000000..836042364124 --- /dev/null +++ b/drivers/net/ethernet/google/gve/gve_dqo.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) + * Google virtual Ethernet (gve) driver + * + * Copyright (C) 2015-2021 Google, Inc. + */ + +#ifndef _GVE_DQO_H_ +#define _GVE_DQO_H_ + +#include "gve_adminq.h" + +#define GVE_ITR_ENABLE_BIT_DQO BIT(0) +#define GVE_ITR_CLEAR_PBA_BIT_DQO BIT(1) +#define GVE_ITR_NO_UPDATE_DQO (3 << 3) + +#define GVE_ITR_INTERVAL_DQO_SHIFT 5 +#define GVE_ITR_INTERVAL_DQO_MASK ((1 << 12) - 1) + +#define GVE_TX_IRQ_RATELIMIT_US_DQO 50 +#define GVE_RX_IRQ_RATELIMIT_US_DQO 20 + +/* Timeout in seconds to wait for a reinjection completion after receiving + * its corresponding miss completion. + */ +#define GVE_REINJECT_COMPL_TIMEOUT 1 + +/* Timeout in seconds to deallocate the completion tag for a packet that was + * prematurely freed for not receiving a valid completion. This should be large + * enough to rule out the possibility of receiving the corresponding valid + * completion after this interval. + */ +#define GVE_DEALLOCATE_COMPL_TIMEOUT 60 + +netdev_tx_t gve_tx_dqo(struct sk_buff *skb, struct net_device *dev); +bool gve_tx_poll_dqo(struct gve_notify_block *block, bool do_clean); +int gve_rx_poll_dqo(struct gve_notify_block *block, int budget); +int gve_tx_alloc_rings_dqo(struct gve_priv *priv); +void gve_tx_free_rings_dqo(struct gve_priv *priv); +int gve_rx_alloc_rings_dqo(struct gve_priv *priv); +void gve_rx_free_rings_dqo(struct gve_priv *priv); +int gve_clean_tx_done_dqo(struct gve_priv *priv, struct gve_tx_ring *tx, + struct napi_struct *napi); +void gve_rx_post_buffers_dqo(struct gve_rx_ring *rx); +void gve_rx_write_doorbell_dqo(const struct gve_priv *priv, int queue_idx); + +static inline void +gve_tx_put_doorbell_dqo(const struct gve_priv *priv, + const struct gve_queue_resources *q_resources, u32 val) +{ + u64 index; + + index = be32_to_cpu(q_resources->db_index); + iowrite32(val, &priv->db_bar2[index]); +} + +/* Builds register value to write to DQO IRQ doorbell to enable with specified + * ratelimit. + */ +static inline u32 gve_set_itr_ratelimit_dqo(u32 ratelimit_us) +{ + u32 result = GVE_ITR_ENABLE_BIT_DQO; + + /* Interval has 2us granularity. */ + ratelimit_us >>= 1; + + ratelimit_us &= GVE_ITR_INTERVAL_DQO_MASK; + result |= (ratelimit_us << GVE_ITR_INTERVAL_DQO_SHIFT); + + return result; +} + +static inline void +gve_write_irq_doorbell_dqo(const struct gve_priv *priv, + const struct gve_notify_block *block, u32 val) +{ + u32 index = be32_to_cpu(block->irq_db_index); + + iowrite32(val, &priv->db_bar2[index]); +} + +#endif /* _GVE_DQO_H_ */ diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 5fb05cf36b49..716e6240305d 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) /* Google virtual Ethernet (gve) driver * - * Copyright (C) 2015-2019 Google, Inc. + * Copyright (C) 2015-2021 Google, Inc. */ #include @@ -311,8 +311,16 @@ gve_get_ethtool_stats(struct net_device *netdev, for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) { struct gve_tx_ring *tx = &priv->tx[ring]; - data[i++] = tx->req; - data[i++] = tx->done; + if (gve_is_gqi(priv)) { + data[i++] = tx->req; + data[i++] = tx->done; + } else { + /* DQO doesn't currently support + * posted/completed descriptor counts; + */ + data[i++] = 0; + data[i++] = 0; + } do { start = u64_stats_fetch_begin(&priv->tx[ring].statss); @@ -453,11 +461,16 @@ static int gve_set_tunable(struct net_device *netdev, switch (etuna->id) { case ETHTOOL_RX_COPYBREAK: + { + u32 max_copybreak = gve_is_gqi(priv) ? + (PAGE_SIZE / 2) : priv->data_buffer_size_dqo; + len = *(u32 *)value; - if (len > PAGE_SIZE / 2) + if (len > max_copybreak) return -EINVAL; priv->rx_copybreak = len; return 0; + } default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index bbc423e93122..867e87af3432 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) /* Google virtual Ethernet (gve) driver * - * Copyright (C) 2015-2019 Google, Inc. + * Copyright (C) 2015-2021 Google, Inc. */ #include @@ -14,6 +14,7 @@ #include #include #include "gve.h" +#include "gve_dqo.h" #include "gve_adminq.h" #include "gve_register.h" @@ -26,6 +27,16 @@ const char gve_version_str[] = GVE_VERSION; static const char gve_version_prefix[] = GVE_VERSION_PREFIX; +static netdev_tx_t gve_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct gve_priv *priv = netdev_priv(dev); + + if (gve_is_gqi(priv)) + return gve_tx(skb, dev); + else + return gve_tx_dqo(skb, dev); +} + static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) { struct gve_priv *priv = netdev_priv(dev); @@ -155,6 +166,15 @@ static irqreturn_t gve_intr(int irq, void *arg) return IRQ_HANDLED; } +static irqreturn_t gve_intr_dqo(int irq, void *arg) +{ + struct gve_notify_block *block = arg; + + /* Interrupts are automatically masked */ + napi_schedule_irqoff(&block->napi); + return IRQ_HANDLED; +} + static int gve_napi_poll(struct napi_struct *napi, int budget) { struct gve_notify_block *block; @@ -191,6 +211,54 @@ static int gve_napi_poll(struct napi_struct *napi, int budget) return 0; } +static int gve_napi_poll_dqo(struct napi_struct *napi, int budget) +{ + struct gve_notify_block *block = + container_of(napi, struct gve_notify_block, napi); + struct gve_priv *priv = block->priv; + bool reschedule = false; + int work_done = 0; + + /* Clear PCI MSI-X Pending Bit Array (PBA) + * + * This bit is set if an interrupt event occurs while the vector is + * masked. If this bit is set and we reenable the interrupt, it will + * fire again. Since we're just about to poll the queue state, we don't + * need it to fire again. + * + * Under high softirq load, it's possible that the interrupt condition + * is triggered twice before we got the chance to process it. + */ + gve_write_irq_doorbell_dqo(priv, block, + GVE_ITR_NO_UPDATE_DQO | GVE_ITR_CLEAR_PBA_BIT_DQO); + + if (block->tx) + reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true); + + if (block->rx) { + work_done = gve_rx_poll_dqo(block, budget); + reschedule |= work_done == budget; + } + + if (reschedule) + return budget; + + if (likely(napi_complete_done(napi, work_done))) { + /* Enable interrupts again. + * + * We don't need to repoll afterwards because HW supports the + * PCI MSI-X PBA feature. + * + * Another interrupt would be triggered if a new event came in + * since the last one. + */ + gve_write_irq_doorbell_dqo(priv, block, + GVE_ITR_NO_UPDATE_DQO | GVE_ITR_ENABLE_BIT_DQO); + } + + return work_done; +} + static int gve_alloc_notify_blocks(struct gve_priv *priv) { int num_vecs_requested = priv->num_ntfy_blks + 1; @@ -264,7 +332,8 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) name, i); block->priv = priv; err = request_irq(priv->msix_vectors[msix_idx].vector, - gve_intr, 0, block->name, block); + gve_is_gqi(priv) ? gve_intr : gve_intr_dqo, + 0, block->name, block); if (err) { dev_err(&priv->pdev->dev, "Failed to receive msix vector %d\n", i); @@ -346,6 +415,22 @@ static int gve_setup_device_resources(struct gve_priv *priv) err = -ENXIO; goto abort_with_stats_report; } + + if (priv->queue_format == GVE_DQO_RDA_FORMAT) { + priv->ptype_lut_dqo = kvzalloc(sizeof(*priv->ptype_lut_dqo), + GFP_KERNEL); + if (!priv->ptype_lut_dqo) { + err = -ENOMEM; + goto abort_with_stats_report; + } + err = gve_adminq_get_ptype_map_dqo(priv, priv->ptype_lut_dqo); + if (err) { + dev_err(&priv->pdev->dev, + "Failed to get ptype map: err=%d\n", err); + goto abort_with_ptype_lut; + } + } + err = gve_adminq_report_stats(priv, priv->stats_report_len, priv->stats_report_bus, GVE_STATS_REPORT_TIMER_PERIOD); @@ -354,12 +439,17 @@ static int gve_setup_device_resources(struct gve_priv *priv) "Failed to report stats: err=%d\n", err); gve_set_device_resources_ok(priv); return 0; + +abort_with_ptype_lut: + kvfree(priv->ptype_lut_dqo); + priv->ptype_lut_dqo = NULL; abort_with_stats_report: gve_free_stats_report(priv); abort_with_ntfy_blocks: gve_free_notify_blocks(priv); abort_with_counter: gve_free_counter_array(priv); + return err; } @@ -386,17 +476,22 @@ static void gve_teardown_device_resources(struct gve_priv *priv) gve_trigger_reset(priv); } } + + kvfree(priv->ptype_lut_dqo); + priv->ptype_lut_dqo = NULL; + gve_free_counter_array(priv); gve_free_notify_blocks(priv); gve_free_stats_report(priv); gve_clear_device_resources_ok(priv); } -static void gve_add_napi(struct gve_priv *priv, int ntfy_idx) +static void gve_add_napi(struct gve_priv *priv, int ntfy_idx, + int (*gve_poll)(struct napi_struct *, int)) { struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; - netif_napi_add(priv->dev, &block->napi, gve_napi_poll, + netif_napi_add(priv->dev, &block->napi, gve_poll, NAPI_POLL_WEIGHT); } @@ -476,31 +571,75 @@ static int gve_create_rings(struct gve_priv *priv) netif_dbg(priv, drv, priv->dev, "created %d rx queues\n", priv->rx_cfg.num_queues); - /* Rx data ring has been prefilled with packet buffers at queue - * allocation time. - * Write the doorbell to provide descriptor slots and packet buffers - * to the NIC. - */ - for (i = 0; i < priv->rx_cfg.num_queues; i++) - gve_rx_write_doorbell(priv, &priv->rx[i]); + if (gve_is_gqi(priv)) { + /* Rx data ring has been prefilled with packet buffers at queue + * allocation time. + * + * Write the doorbell to provide descriptor slots and packet + * buffers to the NIC. + */ + for (i = 0; i < priv->rx_cfg.num_queues; i++) + gve_rx_write_doorbell(priv, &priv->rx[i]); + } else { + for (i = 0; i < priv->rx_cfg.num_queues; i++) { + /* Post buffers and ring doorbell. */ + gve_rx_post_buffers_dqo(&priv->rx[i]); + } + } return 0; } +static void add_napi_init_sync_stats(struct gve_priv *priv, + int (*napi_poll)(struct napi_struct *napi, + int budget)) +{ + int i; + + /* Add tx napi & init sync stats*/ + for (i = 0; i < priv->tx_cfg.num_queues; i++) { + int ntfy_idx = gve_tx_idx_to_ntfy(priv, i); + + u64_stats_init(&priv->tx[i].statss); + priv->tx[i].ntfy_id = ntfy_idx; + gve_add_napi(priv, ntfy_idx, napi_poll); + } + /* Add rx napi & init sync stats*/ + for (i = 0; i < priv->rx_cfg.num_queues; i++) { + int ntfy_idx = gve_rx_idx_to_ntfy(priv, i); + + u64_stats_init(&priv->rx[i].statss); + priv->rx[i].ntfy_id = ntfy_idx; + gve_add_napi(priv, ntfy_idx, napi_poll); + } +} + +static void gve_tx_free_rings(struct gve_priv *priv) +{ + if (gve_is_gqi(priv)) { + gve_tx_free_rings_gqi(priv); + } else { + gve_tx_free_rings_dqo(priv); + } +} + static int gve_alloc_rings(struct gve_priv *priv) { - int ntfy_idx; int err; - int i; /* Setup tx rings */ priv->tx = kvzalloc(priv->tx_cfg.num_queues * sizeof(*priv->tx), GFP_KERNEL); if (!priv->tx) return -ENOMEM; - err = gve_tx_alloc_rings(priv); + + if (gve_is_gqi(priv)) + err = gve_tx_alloc_rings(priv); + else + err = gve_tx_alloc_rings_dqo(priv); if (err) goto free_tx; + /* Setup rx rings */ priv->rx = kvzalloc(priv->rx_cfg.num_queues * sizeof(*priv->rx), GFP_KERNEL); @@ -508,21 +647,18 @@ static int gve_alloc_rings(struct gve_priv *priv) err = -ENOMEM; goto free_tx_queue; } - err = gve_rx_alloc_rings(priv); + + if (gve_is_gqi(priv)) + err = gve_rx_alloc_rings(priv); + else + err = gve_rx_alloc_rings_dqo(priv); if (err) goto free_rx; - /* Add tx napi & init sync stats*/ - for (i = 0; i < priv->tx_cfg.num_queues; i++) { - u64_stats_init(&priv->tx[i].statss); - ntfy_idx = gve_tx_idx_to_ntfy(priv, i); - gve_add_napi(priv, ntfy_idx); - } - /* Add rx napi & init sync stats*/ - for (i = 0; i < priv->rx_cfg.num_queues; i++) { - u64_stats_init(&priv->rx[i].statss); - ntfy_idx = gve_rx_idx_to_ntfy(priv, i); - gve_add_napi(priv, ntfy_idx); - } + + if (gve_is_gqi(priv)) + add_napi_init_sync_stats(priv, gve_napi_poll); + else + add_napi_init_sync_stats(priv, gve_napi_poll_dqo); return 0; @@ -560,6 +696,14 @@ static int gve_destroy_rings(struct gve_priv *priv) return 0; } +static void gve_rx_free_rings(struct gve_priv *priv) +{ + if (gve_is_gqi(priv)) + gve_rx_free_rings_gqi(priv); + else + gve_rx_free_rings_dqo(priv); +} + static void gve_free_rings(struct gve_priv *priv) { int ntfy_idx; @@ -681,7 +825,7 @@ static int gve_alloc_qpls(struct gve_priv *priv) int err; /* Raw addressing means no QPLs */ - if (priv->raw_addressing) + if (priv->queue_format == GVE_GQI_RDA_FORMAT) return 0; priv->qpls = kvzalloc(num_qpls * sizeof(*priv->qpls), GFP_KERNEL); @@ -725,7 +869,7 @@ static void gve_free_qpls(struct gve_priv *priv) int i; /* Raw addressing means no QPLs */ - if (priv->raw_addressing) + if (priv->queue_format == GVE_GQI_RDA_FORMAT) return; kvfree(priv->qpl_cfg.qpl_id_map); @@ -759,6 +903,7 @@ static int gve_open(struct net_device *dev) err = gve_alloc_qpls(priv); if (err) return err; + err = gve_alloc_rings(priv); if (err) goto free_qpls; @@ -773,9 +918,17 @@ static int gve_open(struct net_device *dev) err = gve_register_qpls(priv); if (err) goto reset; + + if (!gve_is_gqi(priv)) { + /* Hard code this for now. This may be tuned in the future for + * performance. + */ + priv->data_buffer_size_dqo = GVE_RX_BUFFER_SIZE_DQO; + } err = gve_create_rings(priv); if (err) goto reset; + gve_set_device_rings_ok(priv); if (gve_get_report_stats(priv)) @@ -924,14 +1077,26 @@ static void gve_turnup(struct gve_priv *priv) struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; napi_enable(&block->napi); - iowrite32be(0, gve_irq_doorbell(priv, block)); + if (gve_is_gqi(priv)) { + iowrite32be(0, gve_irq_doorbell(priv, block)); + } else { + u32 val = gve_set_itr_ratelimit_dqo(GVE_TX_IRQ_RATELIMIT_US_DQO); + + gve_write_irq_doorbell_dqo(priv, block, val); + } } for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) { int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx); struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; napi_enable(&block->napi); - iowrite32be(0, gve_irq_doorbell(priv, block)); + if (gve_is_gqi(priv)) { + iowrite32be(0, gve_irq_doorbell(priv, block)); + } else { + u32 val = gve_set_itr_ratelimit_dqo(GVE_RX_IRQ_RATELIMIT_US_DQO); + + gve_write_irq_doorbell_dqo(priv, block, val); + } } gve_set_napi_enabled(priv); @@ -945,12 +1110,49 @@ static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) priv->tx_timeo_cnt++; } +static int gve_set_features(struct net_device *netdev, + netdev_features_t features) +{ + const netdev_features_t orig_features = netdev->features; + struct gve_priv *priv = netdev_priv(netdev); + int err; + + if ((netdev->features & NETIF_F_LRO) != (features & NETIF_F_LRO)) { + netdev->features ^= NETIF_F_LRO; + if (netif_carrier_ok(netdev)) { + /* To make this process as simple as possible we + * teardown the device, set the new configuration, + * and then bring the device up again. + */ + err = gve_close(netdev); + /* We have already tried to reset in close, just fail + * at this point. + */ + if (err) + goto err; + + err = gve_open(netdev); + if (err) + goto err; + } + } + + return 0; +err: + /* Reverts the change on error. */ + netdev->features = orig_features; + netif_err(priv, drv, netdev, + "Set features failed! !!! DISABLING ALL QUEUES !!!\n"); + return err; +} + static const struct net_device_ops gve_netdev_ops = { - .ndo_start_xmit = gve_tx, + .ndo_start_xmit = gve_start_xmit, .ndo_open = gve_open, .ndo_stop = gve_close, .ndo_get_stats64 = gve_get_stats, .ndo_tx_timeout = gve_tx_timeout, + .ndo_set_features = gve_set_features, }; static void gve_handle_status(struct gve_priv *priv, u32 status) @@ -994,6 +1196,15 @@ void gve_handle_report_stats(struct gve_priv *priv) /* tx stats */ if (priv->tx) { for (idx = 0; idx < priv->tx_cfg.num_queues; idx++) { + u32 last_completion = 0; + u32 tx_frames = 0; + + /* DQO doesn't currently support these metrics. */ + if (gve_is_gqi(priv)) { + last_completion = priv->tx[idx].done; + tx_frames = priv->tx[idx].req; + } + do { start = u64_stats_fetch_begin(&priv->tx[idx].statss); tx_bytes = priv->tx[idx].bytes_done; @@ -1010,7 +1221,7 @@ void gve_handle_report_stats(struct gve_priv *priv) }; stats[stats_idx++] = (struct stats) { .stat_name = cpu_to_be32(TX_FRAMES_SENT), - .value = cpu_to_be64(priv->tx[idx].req), + .value = cpu_to_be64(tx_frames), .queue_id = cpu_to_be32(idx), }; stats[stats_idx++] = (struct stats) { @@ -1020,7 +1231,7 @@ void gve_handle_report_stats(struct gve_priv *priv) }; stats[stats_idx++] = (struct stats) { .stat_name = cpu_to_be32(TX_LAST_COMPLETION_PROCESSED), - .value = cpu_to_be64(priv->tx[idx].done), + .value = cpu_to_be64(last_completion), .queue_id = cpu_to_be32(idx), }; } @@ -1088,7 +1299,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) if (skip_describe_device) goto setup_device; - priv->raw_addressing = false; + priv->queue_format = GVE_QUEUE_FORMAT_UNSPECIFIED; /* Get the initial information we need from the device */ err = gve_adminq_describe_device(priv); if (err) { @@ -1096,7 +1307,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) "Could not get device information: err=%d\n", err); goto err; } - if (priv->dev->max_mtu > PAGE_SIZE) { + if (gve_is_gqi(priv) && priv->dev->max_mtu > PAGE_SIZE) { priv->dev->max_mtu = PAGE_SIZE; err = gve_adminq_set_mtu(priv, priv->dev->mtu); if (err) { @@ -1295,8 +1506,8 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) gve_write_version(®_bar->driver_version); /* Get max queues to alloc etherdev */ - max_rx_queues = ioread32be(®_bar->max_tx_queues); - max_tx_queues = ioread32be(®_bar->max_rx_queues); + max_tx_queues = ioread32be(®_bar->max_tx_queues); + max_rx_queues = ioread32be(®_bar->max_rx_queues); /* Alloc and setup the netdev and priv */ dev = alloc_etherdev_mqs(sizeof(*priv), max_tx_queues, max_rx_queues); if (!dev) { @@ -1307,7 +1518,12 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, dev); dev->ethtool_ops = &gve_ethtool_ops; dev->netdev_ops = &gve_netdev_ops; - /* advertise features */ + + /* Set default and supported features. + * + * Features might be set in other locations as well (such as + * `gve_adminq_describe_device`). + */ dev->hw_features = NETIF_F_HIGHDMA; dev->hw_features |= NETIF_F_SG; dev->hw_features |= NETIF_F_HW_CSUM; @@ -1352,6 +1568,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto abort_with_wq; dev_info(&pdev->dev, "GVE version %s\n", gve_version_str); + dev_info(&pdev->dev, "GVE queue format %d\n", (int)priv->queue_format); gve_clear_probe_in_progress(priv); queue_work(priv->gve_wq, &priv->service_task); return 0; diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index bf123fe524c4..bb8261368250 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -1,21 +1,14 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) /* Google virtual Ethernet (gve) driver * - * Copyright (C) 2015-2019 Google, Inc. + * Copyright (C) 2015-2021 Google, Inc. */ #include "gve.h" #include "gve_adminq.h" +#include "gve_utils.h" #include -static void gve_rx_remove_from_block(struct gve_priv *priv, int queue_idx) -{ - struct gve_notify_block *block = - &priv->ntfy_blocks[gve_rx_idx_to_ntfy(priv, queue_idx)]; - - block->rx = NULL; -} - static void gve_rx_free_buffer(struct device *dev, struct gve_rx_slot_page_info *page_info, union gve_rx_data_slot *data_slot) @@ -137,16 +130,6 @@ alloc_err: return err; } -static void gve_rx_add_to_block(struct gve_priv *priv, int queue_idx) -{ - u32 ntfy_idx = gve_rx_idx_to_ntfy(priv, queue_idx); - struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; - struct gve_rx_ring *rx = &priv->rx[queue_idx]; - - block->rx = rx; - rx->ntfy_id = ntfy_idx; -} - static int gve_rx_alloc_ring(struct gve_priv *priv, int idx) { struct gve_rx_ring *rx = &priv->rx[idx]; @@ -165,7 +148,7 @@ static int gve_rx_alloc_ring(struct gve_priv *priv, int idx) slots = priv->rx_data_slot_cnt; rx->mask = slots - 1; - rx->data.raw_addressing = priv->raw_addressing; + rx->data.raw_addressing = priv->queue_format == GVE_GQI_RDA_FORMAT; /* alloc rx data ring */ bytes = sizeof(*rx->data.data_ring) * slots; @@ -255,7 +238,7 @@ int gve_rx_alloc_rings(struct gve_priv *priv) return err; } -void gve_rx_free_rings(struct gve_priv *priv) +void gve_rx_free_rings_gqi(struct gve_priv *priv) { int i; @@ -279,27 +262,6 @@ static enum pkt_hash_types gve_rss_type(__be16 pkt_flags) return PKT_HASH_TYPE_L2; } -static struct sk_buff *gve_rx_copy(struct net_device *dev, - struct napi_struct *napi, - struct gve_rx_slot_page_info *page_info, - u16 len) -{ - struct sk_buff *skb = napi_alloc_skb(napi, len); - void *va = page_info->page_address + GVE_RX_PAD + - (page_info->page_offset ? PAGE_SIZE / 2 : 0); - - if (unlikely(!skb)) - return NULL; - - __skb_put(skb, len); - - skb_copy_to_linear_data(skb, va, len); - - skb->protocol = eth_type_trans(skb, dev); - - return skb; -} - static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi, struct gve_rx_slot_page_info *page_info, u16 len) @@ -310,7 +272,7 @@ static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi, return NULL; skb_add_rx_frag(skb, 0, page_info->page, - (page_info->page_offset ? PAGE_SIZE / 2 : 0) + + page_info->page_offset + GVE_RX_PAD, len, PAGE_SIZE / 2); return skb; @@ -321,7 +283,7 @@ static void gve_rx_flip_buff(struct gve_rx_slot_page_info *page_info, __be64 *sl const __be64 offset = cpu_to_be64(PAGE_SIZE / 2); /* "flip" to other packet buffer on this page */ - page_info->page_offset ^= 0x1; + page_info->page_offset ^= PAGE_SIZE / 2; *(slot_addr) ^= offset; } @@ -388,7 +350,7 @@ gve_rx_qpl(struct device *dev, struct net_device *netdev, gve_rx_flip_buff(page_info, &data_slot->qpl_offset); } } else { - skb = gve_rx_copy(netdev, napi, page_info, len); + skb = gve_rx_copy(netdev, napi, page_info, len, GVE_RX_PAD); if (skb) { u64_stats_update_begin(&rx->statss); rx->rx_copied_pkt++; @@ -430,7 +392,7 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, if (len <= priv->rx_copybreak) { /* Just copy small packets */ - skb = gve_rx_copy(dev, napi, page_info, len); + skb = gve_rx_copy(dev, napi, page_info, len, GVE_RX_PAD); u64_stats_update_begin(&rx->statss); rx->rx_copied_pkt++; rx->rx_copybreak_pkt++; diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c new file mode 100644 index 000000000000..77bb8227f89b --- /dev/null +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -0,0 +1,763 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Google virtual Ethernet (gve) driver + * + * Copyright (C) 2015-2021 Google, Inc. + */ + +#include "gve.h" +#include "gve_dqo.h" +#include "gve_adminq.h" +#include "gve_utils.h" +#include +#include +#include +#include +#include +#include +#include + +static int gve_buf_ref_cnt(struct gve_rx_buf_state_dqo *bs) +{ + return page_count(bs->page_info.page) - bs->page_info.pagecnt_bias; +} + +static void gve_free_page_dqo(struct gve_priv *priv, + struct gve_rx_buf_state_dqo *bs) +{ + page_ref_sub(bs->page_info.page, bs->page_info.pagecnt_bias - 1); + gve_free_page(&priv->pdev->dev, bs->page_info.page, bs->addr, + DMA_FROM_DEVICE); + bs->page_info.page = NULL; +} + +static struct gve_rx_buf_state_dqo *gve_alloc_buf_state(struct gve_rx_ring *rx) +{ + struct gve_rx_buf_state_dqo *buf_state; + s16 buffer_id; + + buffer_id = rx->dqo.free_buf_states; + if (unlikely(buffer_id == -1)) + return NULL; + + buf_state = &rx->dqo.buf_states[buffer_id]; + + /* Remove buf_state from free list */ + rx->dqo.free_buf_states = buf_state->next; + + /* Point buf_state to itself to mark it as allocated */ + buf_state->next = buffer_id; + + return buf_state; +} + +static bool gve_buf_state_is_allocated(struct gve_rx_ring *rx, + struct gve_rx_buf_state_dqo *buf_state) +{ + s16 buffer_id = buf_state - rx->dqo.buf_states; + + return buf_state->next == buffer_id; +} + +static void gve_free_buf_state(struct gve_rx_ring *rx, + struct gve_rx_buf_state_dqo *buf_state) +{ + s16 buffer_id = buf_state - rx->dqo.buf_states; + + buf_state->next = rx->dqo.free_buf_states; + rx->dqo.free_buf_states = buffer_id; +} + +static struct gve_rx_buf_state_dqo * +gve_dequeue_buf_state(struct gve_rx_ring *rx, struct gve_index_list *list) +{ + struct gve_rx_buf_state_dqo *buf_state; + s16 buffer_id; + + buffer_id = list->head; + if (unlikely(buffer_id == -1)) + return NULL; + + buf_state = &rx->dqo.buf_states[buffer_id]; + + /* Remove buf_state from list */ + list->head = buf_state->next; + if (buf_state->next == -1) + list->tail = -1; + + /* Point buf_state to itself to mark it as allocated */ + buf_state->next = buffer_id; + + return buf_state; +} + +static void gve_enqueue_buf_state(struct gve_rx_ring *rx, + struct gve_index_list *list, + struct gve_rx_buf_state_dqo *buf_state) +{ + s16 buffer_id = buf_state - rx->dqo.buf_states; + + buf_state->next = -1; + + if (list->head == -1) { + list->head = buffer_id; + list->tail = buffer_id; + } else { + int tail = list->tail; + + rx->dqo.buf_states[tail].next = buffer_id; + list->tail = buffer_id; + } +} + +static struct gve_rx_buf_state_dqo * +gve_get_recycled_buf_state(struct gve_rx_ring *rx) +{ + struct gve_rx_buf_state_dqo *buf_state; + int i; + + /* Recycled buf states are immediately usable. */ + buf_state = gve_dequeue_buf_state(rx, &rx->dqo.recycled_buf_states); + if (likely(buf_state)) + return buf_state; + + if (unlikely(rx->dqo.used_buf_states.head == -1)) + return NULL; + + /* Used buf states are only usable when ref count reaches 0, which means + * no SKBs refer to them. + * + * Search a limited number before giving up. + */ + for (i = 0; i < 5; i++) { + buf_state = gve_dequeue_buf_state(rx, &rx->dqo.used_buf_states); + if (gve_buf_ref_cnt(buf_state) == 0) + return buf_state; + + gve_enqueue_buf_state(rx, &rx->dqo.used_buf_states, buf_state); + } + + /* If there are no free buf states discard an entry from + * `used_buf_states` so it can be used. + */ + if (unlikely(rx->dqo.free_buf_states == -1)) { + buf_state = gve_dequeue_buf_state(rx, &rx->dqo.used_buf_states); + if (gve_buf_ref_cnt(buf_state) == 0) + return buf_state; + + gve_free_page_dqo(rx->gve, buf_state); + gve_free_buf_state(rx, buf_state); + } + + return NULL; +} + +static int gve_alloc_page_dqo(struct gve_priv *priv, + struct gve_rx_buf_state_dqo *buf_state) +{ + int err; + + err = gve_alloc_page(priv, &priv->pdev->dev, &buf_state->page_info.page, + &buf_state->addr, DMA_FROM_DEVICE); + if (err) + return err; + + buf_state->page_info.page_offset = 0; + buf_state->page_info.page_address = + page_address(buf_state->page_info.page); + buf_state->last_single_ref_offset = 0; + + /* The page already has 1 ref. */ + page_ref_add(buf_state->page_info.page, INT_MAX - 1); + buf_state->page_info.pagecnt_bias = INT_MAX; + + return 0; +} + +static void gve_rx_free_ring_dqo(struct gve_priv *priv, int idx) +{ + struct gve_rx_ring *rx = &priv->rx[idx]; + struct device *hdev = &priv->pdev->dev; + size_t completion_queue_slots; + size_t buffer_queue_slots; + size_t size; + int i; + + completion_queue_slots = rx->dqo.complq.mask + 1; + buffer_queue_slots = rx->dqo.bufq.mask + 1; + + gve_rx_remove_from_block(priv, idx); + + if (rx->q_resources) { + dma_free_coherent(hdev, sizeof(*rx->q_resources), + rx->q_resources, rx->q_resources_bus); + rx->q_resources = NULL; + } + + for (i = 0; i < rx->dqo.num_buf_states; i++) { + struct gve_rx_buf_state_dqo *bs = &rx->dqo.buf_states[i]; + + if (bs->page_info.page) + gve_free_page_dqo(priv, bs); + } + + if (rx->dqo.bufq.desc_ring) { + size = sizeof(rx->dqo.bufq.desc_ring[0]) * buffer_queue_slots; + dma_free_coherent(hdev, size, rx->dqo.bufq.desc_ring, + rx->dqo.bufq.bus); + rx->dqo.bufq.desc_ring = NULL; + } + + if (rx->dqo.complq.desc_ring) { + size = sizeof(rx->dqo.complq.desc_ring[0]) * + completion_queue_slots; + dma_free_coherent(hdev, size, rx->dqo.complq.desc_ring, + rx->dqo.complq.bus); + rx->dqo.complq.desc_ring = NULL; + } + + kvfree(rx->dqo.buf_states); + rx->dqo.buf_states = NULL; + + netif_dbg(priv, drv, priv->dev, "freed rx ring %d\n", idx); +} + +static int gve_rx_alloc_ring_dqo(struct gve_priv *priv, int idx) +{ + struct gve_rx_ring *rx = &priv->rx[idx]; + struct device *hdev = &priv->pdev->dev; + size_t size; + int i; + + const u32 buffer_queue_slots = + priv->options_dqo_rda.rx_buff_ring_entries; + const u32 completion_queue_slots = priv->rx_desc_cnt; + + netif_dbg(priv, drv, priv->dev, "allocating rx ring DQO\n"); + + memset(rx, 0, sizeof(*rx)); + rx->gve = priv; + rx->q_num = idx; + rx->dqo.bufq.mask = buffer_queue_slots - 1; + rx->dqo.complq.num_free_slots = completion_queue_slots; + rx->dqo.complq.mask = completion_queue_slots - 1; + rx->skb_head = NULL; + rx->skb_tail = NULL; + + rx->dqo.num_buf_states = min_t(s16, S16_MAX, buffer_queue_slots * 4); + rx->dqo.buf_states = kvcalloc(rx->dqo.num_buf_states, + sizeof(rx->dqo.buf_states[0]), + GFP_KERNEL); + if (!rx->dqo.buf_states) + return -ENOMEM; + + /* Set up linked list of buffer IDs */ + for (i = 0; i < rx->dqo.num_buf_states - 1; i++) + rx->dqo.buf_states[i].next = i + 1; + + rx->dqo.buf_states[rx->dqo.num_buf_states - 1].next = -1; + rx->dqo.recycled_buf_states.head = -1; + rx->dqo.recycled_buf_states.tail = -1; + rx->dqo.used_buf_states.head = -1; + rx->dqo.used_buf_states.tail = -1; + + /* Allocate RX completion queue */ + size = sizeof(rx->dqo.complq.desc_ring[0]) * + completion_queue_slots; + rx->dqo.complq.desc_ring = + dma_alloc_coherent(hdev, size, &rx->dqo.complq.bus, GFP_KERNEL); + if (!rx->dqo.complq.desc_ring) + goto err; + + /* Allocate RX buffer queue */ + size = sizeof(rx->dqo.bufq.desc_ring[0]) * buffer_queue_slots; + rx->dqo.bufq.desc_ring = + dma_alloc_coherent(hdev, size, &rx->dqo.bufq.bus, GFP_KERNEL); + if (!rx->dqo.bufq.desc_ring) + goto err; + + rx->q_resources = dma_alloc_coherent(hdev, sizeof(*rx->q_resources), + &rx->q_resources_bus, GFP_KERNEL); + if (!rx->q_resources) + goto err; + + gve_rx_add_to_block(priv, idx); + + return 0; + +err: + gve_rx_free_ring_dqo(priv, idx); + return -ENOMEM; +} + +void gve_rx_write_doorbell_dqo(const struct gve_priv *priv, int queue_idx) +{ + const struct gve_rx_ring *rx = &priv->rx[queue_idx]; + u64 index = be32_to_cpu(rx->q_resources->db_index); + + iowrite32(rx->dqo.bufq.tail, &priv->db_bar2[index]); +} + +int gve_rx_alloc_rings_dqo(struct gve_priv *priv) +{ + int err = 0; + int i; + + for (i = 0; i < priv->rx_cfg.num_queues; i++) { + err = gve_rx_alloc_ring_dqo(priv, i); + if (err) { + netif_err(priv, drv, priv->dev, + "Failed to alloc rx ring=%d: err=%d\n", + i, err); + goto err; + } + } + + return 0; + +err: + for (i--; i >= 0; i--) + gve_rx_free_ring_dqo(priv, i); + + return err; +} + +void gve_rx_free_rings_dqo(struct gve_priv *priv) +{ + int i; + + for (i = 0; i < priv->rx_cfg.num_queues; i++) + gve_rx_free_ring_dqo(priv, i); +} + +void gve_rx_post_buffers_dqo(struct gve_rx_ring *rx) +{ + struct gve_rx_compl_queue_dqo *complq = &rx->dqo.complq; + struct gve_rx_buf_queue_dqo *bufq = &rx->dqo.bufq; + struct gve_priv *priv = rx->gve; + u32 num_avail_slots; + u32 num_full_slots; + u32 num_posted = 0; + + num_full_slots = (bufq->tail - bufq->head) & bufq->mask; + num_avail_slots = bufq->mask - num_full_slots; + + num_avail_slots = min_t(u32, num_avail_slots, complq->num_free_slots); + while (num_posted < num_avail_slots) { + struct gve_rx_desc_dqo *desc = &bufq->desc_ring[bufq->tail]; + struct gve_rx_buf_state_dqo *buf_state; + + buf_state = gve_get_recycled_buf_state(rx); + if (unlikely(!buf_state)) { + buf_state = gve_alloc_buf_state(rx); + if (unlikely(!buf_state)) + break; + + if (unlikely(gve_alloc_page_dqo(priv, buf_state))) { + u64_stats_update_begin(&rx->statss); + rx->rx_buf_alloc_fail++; + u64_stats_update_end(&rx->statss); + gve_free_buf_state(rx, buf_state); + break; + } + } + + desc->buf_id = cpu_to_le16(buf_state - rx->dqo.buf_states); + desc->buf_addr = cpu_to_le64(buf_state->addr + + buf_state->page_info.page_offset); + + bufq->tail = (bufq->tail + 1) & bufq->mask; + complq->num_free_slots--; + num_posted++; + + if ((bufq->tail & (GVE_RX_BUF_THRESH_DQO - 1)) == 0) + gve_rx_write_doorbell_dqo(priv, rx->q_num); + } + + rx->fill_cnt += num_posted; +} + +static void gve_try_recycle_buf(struct gve_priv *priv, struct gve_rx_ring *rx, + struct gve_rx_buf_state_dqo *buf_state) +{ + const int data_buffer_size = priv->data_buffer_size_dqo; + int pagecount; + + /* Can't reuse if we only fit one buffer per page */ + if (data_buffer_size * 2 > PAGE_SIZE) + goto mark_used; + + pagecount = gve_buf_ref_cnt(buf_state); + + /* Record the offset when we have a single remaining reference. + * + * When this happens, we know all of the other offsets of the page are + * usable. + */ + if (pagecount == 1) { + buf_state->last_single_ref_offset = + buf_state->page_info.page_offset; + } + + /* Use the next buffer sized chunk in the page. */ + buf_state->page_info.page_offset += data_buffer_size; + buf_state->page_info.page_offset &= (PAGE_SIZE - 1); + + /* If we wrap around to the same offset without ever dropping to 1 + * reference, then we don't know if this offset was ever freed. + */ + if (buf_state->page_info.page_offset == + buf_state->last_single_ref_offset) { + goto mark_used; + } + + gve_enqueue_buf_state(rx, &rx->dqo.recycled_buf_states, buf_state); + return; + +mark_used: + gve_enqueue_buf_state(rx, &rx->dqo.used_buf_states, buf_state); +} + +static void gve_rx_skb_csum(struct sk_buff *skb, + const struct gve_rx_compl_desc_dqo *desc, + struct gve_ptype ptype) +{ + skb->ip_summed = CHECKSUM_NONE; + + /* HW did not identify and process L3 and L4 headers. */ + if (unlikely(!desc->l3_l4_processed)) + return; + + if (ptype.l3_type == GVE_L3_TYPE_IPV4) { + if (unlikely(desc->csum_ip_err || desc->csum_external_ip_err)) + return; + } else if (ptype.l3_type == GVE_L3_TYPE_IPV6) { + /* Checksum should be skipped if this flag is set. */ + if (unlikely(desc->ipv6_ex_add)) + return; + } + + if (unlikely(desc->csum_l4_err)) + return; + + switch (ptype.l4_type) { + case GVE_L4_TYPE_TCP: + case GVE_L4_TYPE_UDP: + case GVE_L4_TYPE_ICMP: + case GVE_L4_TYPE_SCTP: + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + default: + break; + } +} + +static void gve_rx_skb_hash(struct sk_buff *skb, + const struct gve_rx_compl_desc_dqo *compl_desc, + struct gve_ptype ptype) +{ + enum pkt_hash_types hash_type = PKT_HASH_TYPE_L2; + + if (ptype.l4_type != GVE_L4_TYPE_UNKNOWN) + hash_type = PKT_HASH_TYPE_L4; + else if (ptype.l3_type != GVE_L3_TYPE_UNKNOWN) + hash_type = PKT_HASH_TYPE_L3; + + skb_set_hash(skb, le32_to_cpu(compl_desc->hash), hash_type); +} + +static void gve_rx_free_skb(struct gve_rx_ring *rx) +{ + if (!rx->skb_head) + return; + + dev_kfree_skb_any(rx->skb_head); + rx->skb_head = NULL; + rx->skb_tail = NULL; +} + +/* Chains multi skbs for single rx packet. + * Returns 0 if buffer is appended, -1 otherwise. + */ +static int gve_rx_append_frags(struct napi_struct *napi, + struct gve_rx_buf_state_dqo *buf_state, + u16 buf_len, struct gve_rx_ring *rx, + struct gve_priv *priv) +{ + int num_frags = skb_shinfo(rx->skb_tail)->nr_frags; + + if (unlikely(num_frags == MAX_SKB_FRAGS)) { + struct sk_buff *skb; + + skb = napi_alloc_skb(napi, 0); + if (!skb) + return -1; + + skb_shinfo(rx->skb_tail)->frag_list = skb; + rx->skb_tail = skb; + num_frags = 0; + } + if (rx->skb_tail != rx->skb_head) { + rx->skb_head->len += buf_len; + rx->skb_head->data_len += buf_len; + rx->skb_head->truesize += priv->data_buffer_size_dqo; + } + + skb_add_rx_frag(rx->skb_tail, num_frags, + buf_state->page_info.page, + buf_state->page_info.page_offset, + buf_len, priv->data_buffer_size_dqo); + gve_dec_pagecnt_bias(&buf_state->page_info); + + return 0; +} + +/* Returns 0 if descriptor is completed successfully. + * Returns -EINVAL if descriptor is invalid. + * Returns -ENOMEM if data cannot be copied to skb. + */ +static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, + const struct gve_rx_compl_desc_dqo *compl_desc, + int queue_idx) +{ + const u16 buffer_id = le16_to_cpu(compl_desc->buf_id); + const bool eop = compl_desc->end_of_packet != 0; + struct gve_rx_buf_state_dqo *buf_state; + struct gve_priv *priv = rx->gve; + u16 buf_len; + + if (unlikely(buffer_id >= rx->dqo.num_buf_states)) { + net_err_ratelimited("%s: Invalid RX buffer_id=%u\n", + priv->dev->name, buffer_id); + return -EINVAL; + } + buf_state = &rx->dqo.buf_states[buffer_id]; + if (unlikely(!gve_buf_state_is_allocated(rx, buf_state))) { + net_err_ratelimited("%s: RX buffer_id is not allocated: %u\n", + priv->dev->name, buffer_id); + return -EINVAL; + } + + if (unlikely(compl_desc->rx_error)) { + gve_enqueue_buf_state(rx, &rx->dqo.recycled_buf_states, + buf_state); + return -EINVAL; + } + + buf_len = compl_desc->packet_len; + + /* Page might have not been used for awhile and was likely last written + * by a different thread. + */ + prefetch(buf_state->page_info.page); + + /* Sync the portion of dma buffer for CPU to read. */ + dma_sync_single_range_for_cpu(&priv->pdev->dev, buf_state->addr, + buf_state->page_info.page_offset, + buf_len, DMA_FROM_DEVICE); + + /* Append to current skb if one exists. */ + if (rx->skb_head) { + if (unlikely(gve_rx_append_frags(napi, buf_state, buf_len, rx, + priv)) != 0) { + goto error; + } + + gve_try_recycle_buf(priv, rx, buf_state); + return 0; + } + + /* Prefetch the payload header. */ + prefetch((char *)buf_state->addr + buf_state->page_info.page_offset); +#if L1_CACHE_BYTES < 128 + prefetch((char *)buf_state->addr + buf_state->page_info.page_offset + + L1_CACHE_BYTES); +#endif + + if (eop && buf_len <= priv->rx_copybreak) { + rx->skb_head = gve_rx_copy(priv->dev, napi, + &buf_state->page_info, buf_len, 0); + if (unlikely(!rx->skb_head)) + goto error; + rx->skb_tail = rx->skb_head; + + u64_stats_update_begin(&rx->statss); + rx->rx_copied_pkt++; + rx->rx_copybreak_pkt++; + u64_stats_update_end(&rx->statss); + + gve_enqueue_buf_state(rx, &rx->dqo.recycled_buf_states, + buf_state); + return 0; + } + + rx->skb_head = napi_get_frags(napi); + if (unlikely(!rx->skb_head)) + goto error; + rx->skb_tail = rx->skb_head; + + skb_add_rx_frag(rx->skb_head, 0, buf_state->page_info.page, + buf_state->page_info.page_offset, buf_len, + priv->data_buffer_size_dqo); + gve_dec_pagecnt_bias(&buf_state->page_info); + + gve_try_recycle_buf(priv, rx, buf_state); + return 0; + +error: + gve_enqueue_buf_state(rx, &rx->dqo.recycled_buf_states, buf_state); + return -ENOMEM; +} + +static int gve_rx_complete_rsc(struct sk_buff *skb, + const struct gve_rx_compl_desc_dqo *desc, + struct gve_ptype ptype) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + + /* Only TCP is supported right now. */ + if (ptype.l4_type != GVE_L4_TYPE_TCP) + return -EINVAL; + + switch (ptype.l3_type) { + case GVE_L3_TYPE_IPV4: + shinfo->gso_type = SKB_GSO_TCPV4; + break; + case GVE_L3_TYPE_IPV6: + shinfo->gso_type = SKB_GSO_TCPV6; + break; + default: + return -EINVAL; + } + + shinfo->gso_size = le16_to_cpu(desc->rsc_seg_len); + return 0; +} + +/* Returns 0 if skb is completed successfully, -1 otherwise. */ +static int gve_rx_complete_skb(struct gve_rx_ring *rx, struct napi_struct *napi, + const struct gve_rx_compl_desc_dqo *desc, + netdev_features_t feat) +{ + struct gve_ptype ptype = + rx->gve->ptype_lut_dqo->ptypes[desc->packet_type]; + int err; + + skb_record_rx_queue(rx->skb_head, rx->q_num); + + if (feat & NETIF_F_RXHASH) + gve_rx_skb_hash(rx->skb_head, desc, ptype); + + if (feat & NETIF_F_RXCSUM) + gve_rx_skb_csum(rx->skb_head, desc, ptype); + + /* RSC packets must set gso_size otherwise the TCP stack will complain + * that packets are larger than MTU. + */ + if (desc->rsc) { + err = gve_rx_complete_rsc(rx->skb_head, desc, ptype); + if (err < 0) + return err; + } + + if (skb_headlen(rx->skb_head) == 0) + napi_gro_frags(napi); + else + napi_gro_receive(napi, rx->skb_head); + + return 0; +} + +int gve_rx_poll_dqo(struct gve_notify_block *block, int budget) +{ + struct napi_struct *napi = &block->napi; + netdev_features_t feat = napi->dev->features; + + struct gve_rx_ring *rx = block->rx; + struct gve_rx_compl_queue_dqo *complq = &rx->dqo.complq; + + u32 work_done = 0; + u64 bytes = 0; + int err; + + while (work_done < budget) { + struct gve_rx_compl_desc_dqo *compl_desc = + &complq->desc_ring[complq->head]; + u32 pkt_bytes; + + /* No more new packets */ + if (compl_desc->generation == complq->cur_gen_bit) + break; + + /* Prefetch the next two descriptors. */ + prefetch(&complq->desc_ring[(complq->head + 1) & complq->mask]); + prefetch(&complq->desc_ring[(complq->head + 2) & complq->mask]); + + /* Do not read data until we own the descriptor */ + dma_rmb(); + + err = gve_rx_dqo(napi, rx, compl_desc, rx->q_num); + if (err < 0) { + gve_rx_free_skb(rx); + u64_stats_update_begin(&rx->statss); + if (err == -ENOMEM) + rx->rx_skb_alloc_fail++; + else if (err == -EINVAL) + rx->rx_desc_err_dropped_pkt++; + u64_stats_update_end(&rx->statss); + } + + complq->head = (complq->head + 1) & complq->mask; + complq->num_free_slots++; + + /* When the ring wraps, the generation bit is flipped. */ + complq->cur_gen_bit ^= (complq->head == 0); + + /* Receiving a completion means we have space to post another + * buffer on the buffer queue. + */ + { + struct gve_rx_buf_queue_dqo *bufq = &rx->dqo.bufq; + + bufq->head = (bufq->head + 1) & bufq->mask; + } + + /* Free running counter of completed descriptors */ + rx->cnt++; + + if (!rx->skb_head) + continue; + + if (!compl_desc->end_of_packet) + continue; + + work_done++; + pkt_bytes = rx->skb_head->len; + /* The ethernet header (first ETH_HLEN bytes) is snipped off + * by eth_type_trans. + */ + if (skb_headlen(rx->skb_head)) + pkt_bytes += ETH_HLEN; + + /* gve_rx_complete_skb() will consume skb if successful */ + if (gve_rx_complete_skb(rx, napi, compl_desc, feat) != 0) { + gve_rx_free_skb(rx); + u64_stats_update_begin(&rx->statss); + rx->rx_desc_err_dropped_pkt++; + u64_stats_update_end(&rx->statss); + continue; + } + + bytes += pkt_bytes; + rx->skb_head = NULL; + rx->skb_tail = NULL; + } + + gve_rx_post_buffers_dqo(rx); + + u64_stats_update_begin(&rx->statss); + rx->rpackets += work_done; + rx->rbytes += bytes; + u64_stats_update_end(&rx->statss); + + return work_done; +} diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 3e04a3973d68..665ac795a1ad 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -1,11 +1,12 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) /* Google virtual Ethernet (gve) driver * - * Copyright (C) 2015-2019 Google, Inc. + * Copyright (C) 2015-2021 Google, Inc. */ #include "gve.h" #include "gve_adminq.h" +#include "gve_utils.h" #include #include #include @@ -131,14 +132,6 @@ static void gve_tx_free_fifo(struct gve_tx_fifo *fifo, size_t bytes) atomic_add(bytes, &fifo->available); } -static void gve_tx_remove_from_block(struct gve_priv *priv, int queue_idx) -{ - struct gve_notify_block *block = - &priv->ntfy_blocks[gve_tx_idx_to_ntfy(priv, queue_idx)]; - - block->tx = NULL; -} - static int gve_clean_tx_done(struct gve_priv *priv, struct gve_tx_ring *tx, u32 to_do, bool try_to_wake); @@ -174,16 +167,6 @@ static void gve_tx_free_ring(struct gve_priv *priv, int idx) netif_dbg(priv, drv, priv->dev, "freed tx queue %d\n", idx); } -static void gve_tx_add_to_block(struct gve_priv *priv, int queue_idx) -{ - int ntfy_idx = gve_tx_idx_to_ntfy(priv, queue_idx); - struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; - struct gve_tx_ring *tx = &priv->tx[queue_idx]; - - block->tx = tx; - tx->ntfy_id = ntfy_idx; -} - static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) { struct gve_tx_ring *tx = &priv->tx[idx]; @@ -208,7 +191,7 @@ static int gve_tx_alloc_ring(struct gve_priv *priv, int idx) if (!tx->desc) goto abort_with_info; - tx->raw_addressing = priv->raw_addressing; + tx->raw_addressing = priv->queue_format == GVE_GQI_RDA_FORMAT; tx->dev = &priv->pdev->dev; if (!tx->raw_addressing) { tx->tx_fifo.qpl = gve_assign_tx_qpl(priv); @@ -273,7 +256,7 @@ int gve_tx_alloc_rings(struct gve_priv *priv) return err; } -void gve_tx_free_rings(struct gve_priv *priv) +void gve_tx_free_rings_gqi(struct gve_priv *priv) { int i; diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c new file mode 100644 index 000000000000..05ddb6a75c38 --- /dev/null +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -0,0 +1,1030 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Google virtual Ethernet (gve) driver + * + * Copyright (C) 2015-2021 Google, Inc. + */ + +#include "gve.h" +#include "gve_adminq.h" +#include "gve_utils.h" +#include "gve_dqo.h" +#include +#include +#include + +/* Returns true if a gve_tx_pending_packet_dqo object is available. */ +static bool gve_has_pending_packet(struct gve_tx_ring *tx) +{ + /* Check TX path's list. */ + if (tx->dqo_tx.free_pending_packets != -1) + return true; + + /* Check completion handler's list. */ + if (atomic_read_acquire(&tx->dqo_compl.free_pending_packets) != -1) + return true; + + return false; +} + +static struct gve_tx_pending_packet_dqo * +gve_alloc_pending_packet(struct gve_tx_ring *tx) +{ + struct gve_tx_pending_packet_dqo *pending_packet; + s16 index; + + index = tx->dqo_tx.free_pending_packets; + + /* No pending_packets available, try to steal the list from the + * completion handler. + */ + if (unlikely(index == -1)) { + tx->dqo_tx.free_pending_packets = + atomic_xchg(&tx->dqo_compl.free_pending_packets, -1); + index = tx->dqo_tx.free_pending_packets; + + if (unlikely(index == -1)) + return NULL; + } + + pending_packet = &tx->dqo.pending_packets[index]; + + /* Remove pending_packet from free list */ + tx->dqo_tx.free_pending_packets = pending_packet->next; + pending_packet->state = GVE_PACKET_STATE_PENDING_DATA_COMPL; + + return pending_packet; +} + +static void +gve_free_pending_packet(struct gve_tx_ring *tx, + struct gve_tx_pending_packet_dqo *pending_packet) +{ + s16 index = pending_packet - tx->dqo.pending_packets; + + pending_packet->state = GVE_PACKET_STATE_UNALLOCATED; + while (true) { + s16 old_head = atomic_read_acquire(&tx->dqo_compl.free_pending_packets); + + pending_packet->next = old_head; + if (atomic_cmpxchg(&tx->dqo_compl.free_pending_packets, + old_head, index) == old_head) { + break; + } + } +} + +/* gve_tx_free_desc - Cleans up all pending tx requests and buffers. + */ +static void gve_tx_clean_pending_packets(struct gve_tx_ring *tx) +{ + int i; + + for (i = 0; i < tx->dqo.num_pending_packets; i++) { + struct gve_tx_pending_packet_dqo *cur_state = + &tx->dqo.pending_packets[i]; + int j; + + for (j = 0; j < cur_state->num_bufs; j++) { + struct gve_tx_dma_buf *buf = &cur_state->bufs[j]; + + if (j == 0) { + dma_unmap_single(tx->dev, + dma_unmap_addr(buf, dma), + dma_unmap_len(buf, len), + DMA_TO_DEVICE); + } else { + dma_unmap_page(tx->dev, + dma_unmap_addr(buf, dma), + dma_unmap_len(buf, len), + DMA_TO_DEVICE); + } + } + if (cur_state->skb) { + dev_consume_skb_any(cur_state->skb); + cur_state->skb = NULL; + } + } +} + +static void gve_tx_free_ring_dqo(struct gve_priv *priv, int idx) +{ + struct gve_tx_ring *tx = &priv->tx[idx]; + struct device *hdev = &priv->pdev->dev; + size_t bytes; + + gve_tx_remove_from_block(priv, idx); + + if (tx->q_resources) { + dma_free_coherent(hdev, sizeof(*tx->q_resources), + tx->q_resources, tx->q_resources_bus); + tx->q_resources = NULL; + } + + if (tx->dqo.compl_ring) { + bytes = sizeof(tx->dqo.compl_ring[0]) * + (tx->dqo.complq_mask + 1); + dma_free_coherent(hdev, bytes, tx->dqo.compl_ring, + tx->complq_bus_dqo); + tx->dqo.compl_ring = NULL; + } + + if (tx->dqo.tx_ring) { + bytes = sizeof(tx->dqo.tx_ring[0]) * (tx->mask + 1); + dma_free_coherent(hdev, bytes, tx->dqo.tx_ring, tx->bus); + tx->dqo.tx_ring = NULL; + } + + kvfree(tx->dqo.pending_packets); + tx->dqo.pending_packets = NULL; + + netif_dbg(priv, drv, priv->dev, "freed tx queue %d\n", idx); +} + +static int gve_tx_alloc_ring_dqo(struct gve_priv *priv, int idx) +{ + struct gve_tx_ring *tx = &priv->tx[idx]; + struct device *hdev = &priv->pdev->dev; + int num_pending_packets; + size_t bytes; + int i; + + memset(tx, 0, sizeof(*tx)); + tx->q_num = idx; + tx->dev = &priv->pdev->dev; + tx->netdev_txq = netdev_get_tx_queue(priv->dev, idx); + atomic_set_release(&tx->dqo_compl.hw_tx_head, 0); + + /* Queue sizes must be a power of 2 */ + tx->mask = priv->tx_desc_cnt - 1; + tx->dqo.complq_mask = priv->options_dqo_rda.tx_comp_ring_entries - 1; + + /* The max number of pending packets determines the maximum number of + * descriptors which maybe written to the completion queue. + * + * We must set the number small enough to make sure we never overrun the + * completion queue. + */ + num_pending_packets = tx->dqo.complq_mask + 1; + + /* Reserve space for descriptor completions, which will be reported at + * most every GVE_TX_MIN_RE_INTERVAL packets. + */ + num_pending_packets -= + (tx->dqo.complq_mask + 1) / GVE_TX_MIN_RE_INTERVAL; + + /* Each packet may have at most 2 buffer completions if it receives both + * a miss and reinjection completion. + */ + num_pending_packets /= 2; + + tx->dqo.num_pending_packets = min_t(int, num_pending_packets, S16_MAX); + tx->dqo.pending_packets = kvcalloc(tx->dqo.num_pending_packets, + sizeof(tx->dqo.pending_packets[0]), + GFP_KERNEL); + if (!tx->dqo.pending_packets) + goto err; + + /* Set up linked list of pending packets */ + for (i = 0; i < tx->dqo.num_pending_packets - 1; i++) + tx->dqo.pending_packets[i].next = i + 1; + + tx->dqo.pending_packets[tx->dqo.num_pending_packets - 1].next = -1; + atomic_set_release(&tx->dqo_compl.free_pending_packets, -1); + tx->dqo_compl.miss_completions.head = -1; + tx->dqo_compl.miss_completions.tail = -1; + tx->dqo_compl.timed_out_completions.head = -1; + tx->dqo_compl.timed_out_completions.tail = -1; + + bytes = sizeof(tx->dqo.tx_ring[0]) * (tx->mask + 1); + tx->dqo.tx_ring = dma_alloc_coherent(hdev, bytes, &tx->bus, GFP_KERNEL); + if (!tx->dqo.tx_ring) + goto err; + + bytes = sizeof(tx->dqo.compl_ring[0]) * (tx->dqo.complq_mask + 1); + tx->dqo.compl_ring = dma_alloc_coherent(hdev, bytes, + &tx->complq_bus_dqo, + GFP_KERNEL); + if (!tx->dqo.compl_ring) + goto err; + + tx->q_resources = dma_alloc_coherent(hdev, sizeof(*tx->q_resources), + &tx->q_resources_bus, GFP_KERNEL); + if (!tx->q_resources) + goto err; + + gve_tx_add_to_block(priv, idx); + + return 0; + +err: + gve_tx_free_ring_dqo(priv, idx); + return -ENOMEM; +} + +int gve_tx_alloc_rings_dqo(struct gve_priv *priv) +{ + int err = 0; + int i; + + for (i = 0; i < priv->tx_cfg.num_queues; i++) { + err = gve_tx_alloc_ring_dqo(priv, i); + if (err) { + netif_err(priv, drv, priv->dev, + "Failed to alloc tx ring=%d: err=%d\n", + i, err); + goto err; + } + } + + return 0; + +err: + for (i--; i >= 0; i--) + gve_tx_free_ring_dqo(priv, i); + + return err; +} + +void gve_tx_free_rings_dqo(struct gve_priv *priv) +{ + int i; + + for (i = 0; i < priv->tx_cfg.num_queues; i++) { + struct gve_tx_ring *tx = &priv->tx[i]; + + gve_clean_tx_done_dqo(priv, tx, /*napi=*/NULL); + netdev_tx_reset_queue(tx->netdev_txq); + gve_tx_clean_pending_packets(tx); + + gve_tx_free_ring_dqo(priv, i); + } +} + +/* Returns the number of slots available in the ring */ +static u32 num_avail_tx_slots(const struct gve_tx_ring *tx) +{ + u32 num_used = (tx->dqo_tx.tail - tx->dqo_tx.head) & tx->mask; + + return tx->mask - num_used; +} + +/* Stops the queue if available descriptors is less than 'count'. + * Return: 0 if stop is not required. + */ +static int gve_maybe_stop_tx_dqo(struct gve_tx_ring *tx, int count) +{ + if (likely(gve_has_pending_packet(tx) && + num_avail_tx_slots(tx) >= count)) + return 0; + + /* Update cached TX head pointer */ + tx->dqo_tx.head = atomic_read_acquire(&tx->dqo_compl.hw_tx_head); + + if (likely(gve_has_pending_packet(tx) && + num_avail_tx_slots(tx) >= count)) + return 0; + + /* No space, so stop the queue */ + tx->stop_queue++; + netif_tx_stop_queue(tx->netdev_txq); + + /* Sync with restarting queue in `gve_tx_poll_dqo()` */ + mb(); + + /* After stopping queue, check if we can transmit again in order to + * avoid TOCTOU bug. + */ + tx->dqo_tx.head = atomic_read_acquire(&tx->dqo_compl.hw_tx_head); + + if (likely(!gve_has_pending_packet(tx) || + num_avail_tx_slots(tx) < count)) + return -EBUSY; + + netif_tx_start_queue(tx->netdev_txq); + tx->wake_queue++; + return 0; +} + +static void gve_extract_tx_metadata_dqo(const struct sk_buff *skb, + struct gve_tx_metadata_dqo *metadata) +{ + memset(metadata, 0, sizeof(*metadata)); + metadata->version = GVE_TX_METADATA_VERSION_DQO; + + if (skb->l4_hash) { + u16 path_hash = skb->hash ^ (skb->hash >> 16); + + path_hash &= (1 << 15) - 1; + if (unlikely(path_hash == 0)) + path_hash = ~path_hash; + + metadata->path_hash = path_hash; + } +} + +static void gve_tx_fill_pkt_desc_dqo(struct gve_tx_ring *tx, u32 *desc_idx, + struct sk_buff *skb, u32 len, u64 addr, + s16 compl_tag, bool eop, bool is_gso) +{ + const bool checksum_offload_en = skb->ip_summed == CHECKSUM_PARTIAL; + + while (len > 0) { + struct gve_tx_pkt_desc_dqo *desc = + &tx->dqo.tx_ring[*desc_idx].pkt; + u32 cur_len = min_t(u32, len, GVE_TX_MAX_BUF_SIZE_DQO); + bool cur_eop = eop && cur_len == len; + + *desc = (struct gve_tx_pkt_desc_dqo){ + .buf_addr = cpu_to_le64(addr), + .dtype = GVE_TX_PKT_DESC_DTYPE_DQO, + .end_of_packet = cur_eop, + .checksum_offload_enable = checksum_offload_en, + .compl_tag = cpu_to_le16(compl_tag), + .buf_size = cur_len, + }; + + addr += cur_len; + len -= cur_len; + *desc_idx = (*desc_idx + 1) & tx->mask; + } +} + +/* Validates and prepares `skb` for TSO. + * + * Returns header length, or < 0 if invalid. + */ +static int gve_prep_tso(struct sk_buff *skb) +{ + struct tcphdr *tcp; + int header_len; + u32 paylen; + int err; + + /* Note: HW requires MSS (gso_size) to be <= 9728 and the total length + * of the TSO to be <= 262143. + * + * However, we don't validate these because: + * - Hypervisor enforces a limit of 9K MTU + * - Kernel will not produce a TSO larger than 64k + */ + + if (unlikely(skb_shinfo(skb)->gso_size < GVE_TX_MIN_TSO_MSS_DQO)) + return -1; + + /* Needed because we will modify header. */ + err = skb_cow_head(skb, 0); + if (err < 0) + return err; + + tcp = tcp_hdr(skb); + + /* Remove payload length from checksum. */ + paylen = skb->len - skb_transport_offset(skb); + + switch (skb_shinfo(skb)->gso_type) { + case SKB_GSO_TCPV4: + case SKB_GSO_TCPV6: + csum_replace_by_diff(&tcp->check, + (__force __wsum)htonl(paylen)); + + /* Compute length of segmentation header. */ + header_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + break; + default: + return -EINVAL; + } + + if (unlikely(header_len > GVE_TX_MAX_HDR_SIZE_DQO)) + return -EINVAL; + + return header_len; +} + +static void gve_tx_fill_tso_ctx_desc(struct gve_tx_tso_context_desc_dqo *desc, + const struct sk_buff *skb, + const struct gve_tx_metadata_dqo *metadata, + int header_len) +{ + *desc = (struct gve_tx_tso_context_desc_dqo){ + .header_len = header_len, + .cmd_dtype = { + .dtype = GVE_TX_TSO_CTX_DESC_DTYPE_DQO, + .tso = 1, + }, + .flex0 = metadata->bytes[0], + .flex5 = metadata->bytes[5], + .flex6 = metadata->bytes[6], + .flex7 = metadata->bytes[7], + .flex8 = metadata->bytes[8], + .flex9 = metadata->bytes[9], + .flex10 = metadata->bytes[10], + .flex11 = metadata->bytes[11], + }; + desc->tso_total_len = skb->len - header_len; + desc->mss = skb_shinfo(skb)->gso_size; +} + +static void +gve_tx_fill_general_ctx_desc(struct gve_tx_general_context_desc_dqo *desc, + const struct gve_tx_metadata_dqo *metadata) +{ + *desc = (struct gve_tx_general_context_desc_dqo){ + .flex0 = metadata->bytes[0], + .flex1 = metadata->bytes[1], + .flex2 = metadata->bytes[2], + .flex3 = metadata->bytes[3], + .flex4 = metadata->bytes[4], + .flex5 = metadata->bytes[5], + .flex6 = metadata->bytes[6], + .flex7 = metadata->bytes[7], + .flex8 = metadata->bytes[8], + .flex9 = metadata->bytes[9], + .flex10 = metadata->bytes[10], + .flex11 = metadata->bytes[11], + .cmd_dtype = {.dtype = GVE_TX_GENERAL_CTX_DESC_DTYPE_DQO}, + }; +} + +/* Returns 0 on success, or < 0 on error. + * + * Before this function is called, the caller must ensure + * gve_has_pending_packet(tx) returns true. + */ +static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx, + struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + const bool is_gso = skb_is_gso(skb); + u32 desc_idx = tx->dqo_tx.tail; + + struct gve_tx_pending_packet_dqo *pending_packet; + struct gve_tx_metadata_dqo metadata; + s16 completion_tag; + int i; + + pending_packet = gve_alloc_pending_packet(tx); + pending_packet->skb = skb; + pending_packet->num_bufs = 0; + completion_tag = pending_packet - tx->dqo.pending_packets; + + gve_extract_tx_metadata_dqo(skb, &metadata); + if (is_gso) { + int header_len = gve_prep_tso(skb); + + if (unlikely(header_len < 0)) + goto err; + + gve_tx_fill_tso_ctx_desc(&tx->dqo.tx_ring[desc_idx].tso_ctx, + skb, &metadata, header_len); + desc_idx = (desc_idx + 1) & tx->mask; + } + + gve_tx_fill_general_ctx_desc(&tx->dqo.tx_ring[desc_idx].general_ctx, + &metadata); + desc_idx = (desc_idx + 1) & tx->mask; + + /* Note: HW requires that the size of a non-TSO packet be within the + * range of [17, 9728]. + * + * We don't double check because + * - We limited `netdev->min_mtu` to ETH_MIN_MTU. + * - Hypervisor won't allow MTU larger than 9216. + */ + + /* Map the linear portion of skb */ + { + struct gve_tx_dma_buf *buf = + &pending_packet->bufs[pending_packet->num_bufs]; + u32 len = skb_headlen(skb); + dma_addr_t addr; + + addr = dma_map_single(tx->dev, skb->data, len, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(tx->dev, addr))) + goto err; + + dma_unmap_len_set(buf, len, len); + dma_unmap_addr_set(buf, dma, addr); + ++pending_packet->num_bufs; + + gve_tx_fill_pkt_desc_dqo(tx, &desc_idx, skb, len, addr, + completion_tag, + /*eop=*/shinfo->nr_frags == 0, is_gso); + } + + for (i = 0; i < shinfo->nr_frags; i++) { + struct gve_tx_dma_buf *buf = + &pending_packet->bufs[pending_packet->num_bufs]; + const skb_frag_t *frag = &shinfo->frags[i]; + bool is_eop = i == (shinfo->nr_frags - 1); + u32 len = skb_frag_size(frag); + dma_addr_t addr; + + addr = skb_frag_dma_map(tx->dev, frag, 0, len, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(tx->dev, addr))) + goto err; + + dma_unmap_len_set(buf, len, len); + dma_unmap_addr_set(buf, dma, addr); + ++pending_packet->num_bufs; + + gve_tx_fill_pkt_desc_dqo(tx, &desc_idx, skb, len, addr, + completion_tag, is_eop, is_gso); + } + + /* Commit the changes to our state */ + tx->dqo_tx.tail = desc_idx; + + /* Request a descriptor completion on the last descriptor of the + * packet if we are allowed to by the HW enforced interval. + */ + { + u32 last_desc_idx = (desc_idx - 1) & tx->mask; + u32 last_report_event_interval = + (last_desc_idx - tx->dqo_tx.last_re_idx) & tx->mask; + + if (unlikely(last_report_event_interval >= + GVE_TX_MIN_RE_INTERVAL)) { + tx->dqo.tx_ring[last_desc_idx].pkt.report_event = true; + tx->dqo_tx.last_re_idx = last_desc_idx; + } + } + + return 0; + +err: + for (i = 0; i < pending_packet->num_bufs; i++) { + struct gve_tx_dma_buf *buf = &pending_packet->bufs[i]; + + if (i == 0) { + dma_unmap_single(tx->dev, dma_unmap_addr(buf, dma), + dma_unmap_len(buf, len), + DMA_TO_DEVICE); + } else { + dma_unmap_page(tx->dev, dma_unmap_addr(buf, dma), + dma_unmap_len(buf, len), DMA_TO_DEVICE); + } + } + + pending_packet->skb = NULL; + pending_packet->num_bufs = 0; + gve_free_pending_packet(tx, pending_packet); + + return -1; +} + +static int gve_num_descs_per_buf(size_t size) +{ + return DIV_ROUND_UP(size, GVE_TX_MAX_BUF_SIZE_DQO); +} + +static int gve_num_buffer_descs_needed(const struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + int num_descs; + int i; + + num_descs = gve_num_descs_per_buf(skb_headlen(skb)); + + for (i = 0; i < shinfo->nr_frags; i++) { + unsigned int frag_size = skb_frag_size(&shinfo->frags[i]); + + num_descs += gve_num_descs_per_buf(frag_size); + } + + return num_descs; +} + +/* Returns true if HW is capable of sending TSO represented by `skb`. + * + * Each segment must not span more than GVE_TX_MAX_DATA_DESCS buffers. + * - The header is counted as one buffer for every single segment. + * - A buffer which is split between two segments is counted for both. + * - If a buffer contains both header and payload, it is counted as two buffers. + */ +static bool gve_can_send_tso(const struct sk_buff *skb) +{ + const int header_len = skb_checksum_start_offset(skb) + tcp_hdrlen(skb); + const int max_bufs_per_seg = GVE_TX_MAX_DATA_DESCS - 1; + const struct skb_shared_info *shinfo = skb_shinfo(skb); + const int gso_size = shinfo->gso_size; + int cur_seg_num_bufs; + int cur_seg_size; + int i; + + cur_seg_size = skb_headlen(skb) - header_len; + cur_seg_num_bufs = cur_seg_size > 0; + + for (i = 0; i < shinfo->nr_frags; i++) { + if (cur_seg_size >= gso_size) { + cur_seg_size %= gso_size; + cur_seg_num_bufs = cur_seg_size > 0; + } + + if (unlikely(++cur_seg_num_bufs > max_bufs_per_seg)) + return false; + + cur_seg_size += skb_frag_size(&shinfo->frags[i]); + } + + return true; +} + +/* Attempt to transmit specified SKB. + * + * Returns 0 if the SKB was transmitted or dropped. + * Returns -1 if there is not currently enough space to transmit the SKB. + */ +static int gve_try_tx_skb(struct gve_priv *priv, struct gve_tx_ring *tx, + struct sk_buff *skb) +{ + int num_buffer_descs; + int total_num_descs; + + if (skb_is_gso(skb)) { + /* If TSO doesn't meet HW requirements, attempt to linearize the + * packet. + */ + if (unlikely(!gve_can_send_tso(skb) && + skb_linearize(skb) < 0)) { + net_err_ratelimited("%s: Failed to transmit TSO packet\n", + priv->dev->name); + goto drop; + } + + num_buffer_descs = gve_num_buffer_descs_needed(skb); + } else { + num_buffer_descs = gve_num_buffer_descs_needed(skb); + + if (unlikely(num_buffer_descs > GVE_TX_MAX_DATA_DESCS)) { + if (unlikely(skb_linearize(skb) < 0)) + goto drop; + + num_buffer_descs = 1; + } + } + + /* Metadata + (optional TSO) + data descriptors. */ + total_num_descs = 1 + skb_is_gso(skb) + num_buffer_descs; + if (unlikely(gve_maybe_stop_tx_dqo(tx, total_num_descs + + GVE_TX_MIN_DESC_PREVENT_CACHE_OVERLAP))) { + return -1; + } + + if (unlikely(gve_tx_add_skb_no_copy_dqo(tx, skb) < 0)) + goto drop; + + netdev_tx_sent_queue(tx->netdev_txq, skb->len); + skb_tx_timestamp(skb); + return 0; + +drop: + tx->dropped_pkt++; + dev_kfree_skb_any(skb); + return 0; +} + +/* Transmit a given skb and ring the doorbell. */ +netdev_tx_t gve_tx_dqo(struct sk_buff *skb, struct net_device *dev) +{ + struct gve_priv *priv = netdev_priv(dev); + struct gve_tx_ring *tx; + + tx = &priv->tx[skb_get_queue_mapping(skb)]; + if (unlikely(gve_try_tx_skb(priv, tx, skb) < 0)) { + /* We need to ring the txq doorbell -- we have stopped the Tx + * queue for want of resources, but prior calls to gve_tx() + * may have added descriptors without ringing the doorbell. + */ + gve_tx_put_doorbell_dqo(priv, tx->q_resources, tx->dqo_tx.tail); + return NETDEV_TX_BUSY; + } + + if (!netif_xmit_stopped(tx->netdev_txq) && netdev_xmit_more()) + return NETDEV_TX_OK; + + gve_tx_put_doorbell_dqo(priv, tx->q_resources, tx->dqo_tx.tail); + return NETDEV_TX_OK; +} + +static void add_to_list(struct gve_tx_ring *tx, struct gve_index_list *list, + struct gve_tx_pending_packet_dqo *pending_packet) +{ + s16 old_tail, index; + + index = pending_packet - tx->dqo.pending_packets; + old_tail = list->tail; + list->tail = index; + if (old_tail == -1) + list->head = index; + else + tx->dqo.pending_packets[old_tail].next = index; + + pending_packet->next = -1; + pending_packet->prev = old_tail; +} + +static void remove_from_list(struct gve_tx_ring *tx, + struct gve_index_list *list, + struct gve_tx_pending_packet_dqo *pending_packet) +{ + s16 prev_index, next_index; + + prev_index = pending_packet->prev; + next_index = pending_packet->next; + + if (prev_index == -1) { + /* Node is head */ + list->head = next_index; + } else { + tx->dqo.pending_packets[prev_index].next = next_index; + } + if (next_index == -1) { + /* Node is tail */ + list->tail = prev_index; + } else { + tx->dqo.pending_packets[next_index].prev = prev_index; + } +} + +static void gve_unmap_packet(struct device *dev, + struct gve_tx_pending_packet_dqo *pending_packet) +{ + struct gve_tx_dma_buf *buf; + int i; + + /* SKB linear portion is guaranteed to be mapped */ + buf = &pending_packet->bufs[0]; + dma_unmap_single(dev, dma_unmap_addr(buf, dma), + dma_unmap_len(buf, len), DMA_TO_DEVICE); + for (i = 1; i < pending_packet->num_bufs; i++) { + buf = &pending_packet->bufs[i]; + dma_unmap_page(dev, dma_unmap_addr(buf, dma), + dma_unmap_len(buf, len), DMA_TO_DEVICE); + } + pending_packet->num_bufs = 0; +} + +/* Completion types and expected behavior: + * No Miss compl + Packet compl = Packet completed normally. + * Miss compl + Re-inject compl = Packet completed normally. + * No Miss compl + Re-inject compl = Skipped i.e. packet not completed. + * Miss compl + Packet compl = Skipped i.e. packet not completed. + */ +static void gve_handle_packet_completion(struct gve_priv *priv, + struct gve_tx_ring *tx, bool is_napi, + u16 compl_tag, u64 *bytes, u64 *pkts, + bool is_reinjection) +{ + struct gve_tx_pending_packet_dqo *pending_packet; + + if (unlikely(compl_tag >= tx->dqo.num_pending_packets)) { + net_err_ratelimited("%s: Invalid TX completion tag: %d\n", + priv->dev->name, (int)compl_tag); + return; + } + + pending_packet = &tx->dqo.pending_packets[compl_tag]; + + if (unlikely(is_reinjection)) { + if (unlikely(pending_packet->state == + GVE_PACKET_STATE_TIMED_OUT_COMPL)) { + net_err_ratelimited("%s: Re-injection completion: %d received after timeout.\n", + priv->dev->name, (int)compl_tag); + /* Packet was already completed as a result of timeout, + * so just remove from list and free pending packet. + */ + remove_from_list(tx, + &tx->dqo_compl.timed_out_completions, + pending_packet); + gve_free_pending_packet(tx, pending_packet); + return; + } + if (unlikely(pending_packet->state != + GVE_PACKET_STATE_PENDING_REINJECT_COMPL)) { + /* No outstanding miss completion but packet allocated + * implies packet receives a re-injection completion + * without a a prior miss completion. Return without + * completing the packet. + */ + net_err_ratelimited("%s: Re-injection completion received without corresponding miss completion: %d\n", + priv->dev->name, (int)compl_tag); + return; + } + remove_from_list(tx, &tx->dqo_compl.miss_completions, + pending_packet); + } else { + /* Packet is allocated but not a pending data completion. */ + if (unlikely(pending_packet->state != + GVE_PACKET_STATE_PENDING_DATA_COMPL)) { + net_err_ratelimited("%s: No pending data completion: %d\n", + priv->dev->name, (int)compl_tag); + return; + } + } + gve_unmap_packet(tx->dev, pending_packet); + + *bytes += pending_packet->skb->len; + (*pkts)++; + napi_consume_skb(pending_packet->skb, is_napi); + pending_packet->skb = NULL; + gve_free_pending_packet(tx, pending_packet); +} + +static void gve_handle_miss_completion(struct gve_priv *priv, + struct gve_tx_ring *tx, u16 compl_tag, + u64 *bytes, u64 *pkts) +{ + struct gve_tx_pending_packet_dqo *pending_packet; + + if (unlikely(compl_tag >= tx->dqo.num_pending_packets)) { + net_err_ratelimited("%s: Invalid TX completion tag: %d\n", + priv->dev->name, (int)compl_tag); + return; + } + + pending_packet = &tx->dqo.pending_packets[compl_tag]; + if (unlikely(pending_packet->state != + GVE_PACKET_STATE_PENDING_DATA_COMPL)) { + net_err_ratelimited("%s: Unexpected packet state: %d for completion tag : %d\n", + priv->dev->name, (int)pending_packet->state, + (int)compl_tag); + return; + } + + pending_packet->state = GVE_PACKET_STATE_PENDING_REINJECT_COMPL; + /* jiffies can wraparound but time comparisons can handle overflows. */ + pending_packet->timeout_jiffies = + jiffies + + msecs_to_jiffies(GVE_REINJECT_COMPL_TIMEOUT * + MSEC_PER_SEC); + add_to_list(tx, &tx->dqo_compl.miss_completions, pending_packet); + + *bytes += pending_packet->skb->len; + (*pkts)++; +} + +static void remove_miss_completions(struct gve_priv *priv, + struct gve_tx_ring *tx) +{ + struct gve_tx_pending_packet_dqo *pending_packet; + s16 next_index; + + next_index = tx->dqo_compl.miss_completions.head; + while (next_index != -1) { + pending_packet = &tx->dqo.pending_packets[next_index]; + next_index = pending_packet->next; + /* Break early because packets should timeout in order. */ + if (time_is_after_jiffies(pending_packet->timeout_jiffies)) + break; + + remove_from_list(tx, &tx->dqo_compl.miss_completions, + pending_packet); + /* Unmap buffers and free skb but do not unallocate packet i.e. + * the completion tag is not freed to ensure that the driver + * can take appropriate action if a corresponding valid + * completion is received later. + */ + gve_unmap_packet(tx->dev, pending_packet); + /* This indicates the packet was dropped. */ + dev_kfree_skb_any(pending_packet->skb); + pending_packet->skb = NULL; + tx->dropped_pkt++; + net_err_ratelimited("%s: No reinjection completion was received for: %d.\n", + priv->dev->name, + (int)(pending_packet - tx->dqo.pending_packets)); + + pending_packet->state = GVE_PACKET_STATE_TIMED_OUT_COMPL; + pending_packet->timeout_jiffies = + jiffies + + msecs_to_jiffies(GVE_DEALLOCATE_COMPL_TIMEOUT * + MSEC_PER_SEC); + /* Maintain pending packet in another list so the packet can be + * unallocated at a later time. + */ + add_to_list(tx, &tx->dqo_compl.timed_out_completions, + pending_packet); + } +} + +static void remove_timed_out_completions(struct gve_priv *priv, + struct gve_tx_ring *tx) +{ + struct gve_tx_pending_packet_dqo *pending_packet; + s16 next_index; + + next_index = tx->dqo_compl.timed_out_completions.head; + while (next_index != -1) { + pending_packet = &tx->dqo.pending_packets[next_index]; + next_index = pending_packet->next; + /* Break early because packets should timeout in order. */ + if (time_is_after_jiffies(pending_packet->timeout_jiffies)) + break; + + remove_from_list(tx, &tx->dqo_compl.timed_out_completions, + pending_packet); + gve_free_pending_packet(tx, pending_packet); + } +} + +int gve_clean_tx_done_dqo(struct gve_priv *priv, struct gve_tx_ring *tx, + struct napi_struct *napi) +{ + u64 reinject_compl_bytes = 0; + u64 reinject_compl_pkts = 0; + int num_descs_cleaned = 0; + u64 miss_compl_bytes = 0; + u64 miss_compl_pkts = 0; + u64 pkt_compl_bytes = 0; + u64 pkt_compl_pkts = 0; + + /* Limit in order to avoid blocking for too long */ + while (!napi || pkt_compl_pkts < napi->weight) { + struct gve_tx_compl_desc *compl_desc = + &tx->dqo.compl_ring[tx->dqo_compl.head]; + u16 type; + + if (compl_desc->generation == tx->dqo_compl.cur_gen_bit) + break; + + /* Prefetch the next descriptor. */ + prefetch(&tx->dqo.compl_ring[(tx->dqo_compl.head + 1) & + tx->dqo.complq_mask]); + + /* Do not read data until we own the descriptor */ + dma_rmb(); + type = compl_desc->type; + + if (type == GVE_COMPL_TYPE_DQO_DESC) { + /* This is the last descriptor fetched by HW plus one */ + u16 tx_head = le16_to_cpu(compl_desc->tx_head); + + atomic_set_release(&tx->dqo_compl.hw_tx_head, tx_head); + } else if (type == GVE_COMPL_TYPE_DQO_PKT) { + u16 compl_tag = le16_to_cpu(compl_desc->completion_tag); + + gve_handle_packet_completion(priv, tx, !!napi, + compl_tag, + &pkt_compl_bytes, + &pkt_compl_pkts, + /*is_reinjection=*/false); + } else if (type == GVE_COMPL_TYPE_DQO_MISS) { + u16 compl_tag = le16_to_cpu(compl_desc->completion_tag); + + gve_handle_miss_completion(priv, tx, compl_tag, + &miss_compl_bytes, + &miss_compl_pkts); + } else if (type == GVE_COMPL_TYPE_DQO_REINJECTION) { + u16 compl_tag = le16_to_cpu(compl_desc->completion_tag); + + gve_handle_packet_completion(priv, tx, !!napi, + compl_tag, + &reinject_compl_bytes, + &reinject_compl_pkts, + /*is_reinjection=*/true); + } + + tx->dqo_compl.head = + (tx->dqo_compl.head + 1) & tx->dqo.complq_mask; + /* Flip the generation bit when we wrap around */ + tx->dqo_compl.cur_gen_bit ^= tx->dqo_compl.head == 0; + num_descs_cleaned++; + } + + netdev_tx_completed_queue(tx->netdev_txq, + pkt_compl_pkts + miss_compl_pkts, + pkt_compl_bytes + miss_compl_bytes); + + remove_miss_completions(priv, tx); + remove_timed_out_completions(priv, tx); + + u64_stats_update_begin(&tx->statss); + tx->bytes_done += pkt_compl_bytes + reinject_compl_bytes; + tx->pkt_done += pkt_compl_pkts + reinject_compl_pkts; + u64_stats_update_end(&tx->statss); + return num_descs_cleaned; +} + +bool gve_tx_poll_dqo(struct gve_notify_block *block, bool do_clean) +{ + struct gve_tx_compl_desc *compl_desc; + struct gve_tx_ring *tx = block->tx; + struct gve_priv *priv = block->priv; + + if (do_clean) { + int num_descs_cleaned = gve_clean_tx_done_dqo(priv, tx, + &block->napi); + + /* Sync with queue being stopped in `gve_maybe_stop_tx_dqo()` */ + mb(); + + if (netif_tx_queue_stopped(tx->netdev_txq) && + num_descs_cleaned > 0) { + tx->wake_queue++; + netif_tx_wake_queue(tx->netdev_txq); + } + } + + /* Return true if we still have work. */ + compl_desc = &tx->dqo.compl_ring[tx->dqo_compl.head]; + return compl_desc->generation != tx->dqo_compl.cur_gen_bit; +} diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c new file mode 100644 index 000000000000..93f3dcbeeea9 --- /dev/null +++ b/drivers/net/ethernet/google/gve/gve_utils.c @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Google virtual Ethernet (gve) driver + * + * Copyright (C) 2015-2021 Google, Inc. + */ + +#include "gve.h" +#include "gve_adminq.h" +#include "gve_utils.h" + +void gve_tx_remove_from_block(struct gve_priv *priv, int queue_idx) +{ + struct gve_notify_block *block = + &priv->ntfy_blocks[gve_tx_idx_to_ntfy(priv, queue_idx)]; + + block->tx = NULL; +} + +void gve_tx_add_to_block(struct gve_priv *priv, int queue_idx) +{ + int ntfy_idx = gve_tx_idx_to_ntfy(priv, queue_idx); + struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; + struct gve_tx_ring *tx = &priv->tx[queue_idx]; + + block->tx = tx; + tx->ntfy_id = ntfy_idx; +} + +void gve_rx_remove_from_block(struct gve_priv *priv, int queue_idx) +{ + struct gve_notify_block *block = + &priv->ntfy_blocks[gve_rx_idx_to_ntfy(priv, queue_idx)]; + + block->rx = NULL; +} + +void gve_rx_add_to_block(struct gve_priv *priv, int queue_idx) +{ + u32 ntfy_idx = gve_rx_idx_to_ntfy(priv, queue_idx); + struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; + struct gve_rx_ring *rx = &priv->rx[queue_idx]; + + block->rx = rx; + rx->ntfy_id = ntfy_idx; +} + +struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi, + struct gve_rx_slot_page_info *page_info, u16 len, + u16 pad) +{ + struct sk_buff *skb = napi_alloc_skb(napi, len); + void *va = page_info->page_address + pad + + page_info->page_offset; + + if (unlikely(!skb)) + return NULL; + + __skb_put(skb, len); + + skb_copy_to_linear_data(skb, va, len); + + skb->protocol = eth_type_trans(skb, dev); + + return skb; +} + +void gve_dec_pagecnt_bias(struct gve_rx_slot_page_info *page_info) +{ + page_info->pagecnt_bias--; + if (page_info->pagecnt_bias == 0) { + int pagecount = page_count(page_info->page); + + /* If we have run out of bias - set it back up to INT_MAX + * minus the existing refs. + */ + page_info->pagecnt_bias = INT_MAX - pagecount; + + /* Set pagecount back up to max. */ + page_ref_add(page_info->page, INT_MAX - pagecount); + } +} diff --git a/drivers/net/ethernet/google/gve/gve_utils.h b/drivers/net/ethernet/google/gve/gve_utils.h new file mode 100644 index 000000000000..79595940b351 --- /dev/null +++ b/drivers/net/ethernet/google/gve/gve_utils.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) + * Google virtual Ethernet (gve) driver + * + * Copyright (C) 2015-2021 Google, Inc. + */ + +#ifndef _GVE_UTILS_H +#define _GVE_UTILS_H + +#include + +#include "gve.h" + +void gve_tx_remove_from_block(struct gve_priv *priv, int queue_idx); +void gve_tx_add_to_block(struct gve_priv *priv, int queue_idx); + +void gve_rx_remove_from_block(struct gve_priv *priv, int queue_idx); +void gve_rx_add_to_block(struct gve_priv *priv, int queue_idx); + +struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi, + struct gve_rx_slot_page_info *page_info, u16 len, + u16 pad); + +/* Decrement pagecnt_bias. Set it back to INT_MAX if it reached zero. */ +void gve_dec_pagecnt_bias(struct gve_rx_slot_page_info *page_info); + +#endif /* _GVE_UTILS_H */ + diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 44f9279cdde1..bb062b02fb85 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -102,6 +102,7 @@ config HNS3_HCLGE tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support" default m depends on PCI_MSI + imply PTP_1588_CLOCK help This selects the HNS3_HCLGE network acceleration engine & its hardware compatibility layer. The engine would be used in Hisilicon hip08 family of @@ -130,6 +131,7 @@ config HNS3_ENET default m depends on 64BIT && PCI depends on INET + select DIMLIB help This selects the Ethernet Driver for Hisilicon Network Subsystem 3 for hip08 family of SoCs. This module depends upon HNAE3 driver to access the HNAE3 diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index c615fbf9094e..75e4ec569da8 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -462,8 +462,6 @@ static void hns_ae_adjust_link(struct hnae_handle *handle, int speed, default: break; } - - return; } static void hns_ae_get_ring_bdnum_limit(struct hnae_queue *queue, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index f4cf569a2599..f41379de2186 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -111,7 +111,7 @@ int hns_mac_get_port_info(struct hns_mac_cb *mac_cb, } /** - *hns_mac_is_adjust_link - check is need change mac speed and duplex register + *hns_mac_need_adjust_link - check is need change mac speed and duplex register *@mac_cb: mac device *@speed: phy device speed *@duplex:phy device duplex @@ -374,7 +374,7 @@ static void hns_mac_param_get(struct mac_params *param, } /** - * hns_mac_queue_config_bc_en - set broadcast rx&tx enable + * hns_mac_port_config_bc_en - set broadcast rx&tx enable * @mac_cb: mac device * @port_num: queue number * @vlan_id: vlan id` @@ -597,7 +597,7 @@ int hns_mac_set_autoneg(struct hns_mac_cb *mac_cb, u8 enable) } /** - * hns_mac_set_autoneg - set rx & tx pause parameter + * hns_mac_set_pauseparam - set rx & tx pause parameter * @mac_cb: mac control block * @rx_en: rx enable or not * @tx_en: tx enable or not @@ -914,8 +914,7 @@ static int hns_mac_get_info(struct hns_mac_cb *mac_cb) } } else if (is_acpi_node(mac_cb->fw_port)) { ret = hns_mac_register_phy(mac_cb); - /* - * Mac can work well if there is phy or not.If the port don't + /* Mac can work well if there is phy or not.If the port don't * connect with phy, the return value will be ignored. Only * when there is phy but can't find mdio bus, the return value * will be handled. diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index c2a60612f503..fcaf5132b865 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -227,7 +227,7 @@ hns_dsaf_reg_cnt_clr_ce(struct dsaf_device *dsaf_dev, u32 reg_cnt_clr_ce) } /** - * hns_ppe_qid_cfg - config ppe qid + * hns_dsaf_ppe_qid_cfg - config ppe qid * @dsaf_dev: dsa fabric id * @qid_cfg: value array */ @@ -613,7 +613,7 @@ static void hns_dsaf_tbl_tcam_data_cfg( } /** - * dsaf_tbl_tcam_mcast_cfg - tbl + * hns_dsaf_tbl_tcam_mcast_cfg - tbl * @dsaf_dev: dsa fabric id * @mcast: addr */ @@ -1213,7 +1213,7 @@ void hns_dsaf_get_rx_mac_pause_en(struct dsaf_device *dsaf_dev, int mac_id, } /** - * hns_dsaf_tbl_tcam_init - INT + * hns_dsaf_comm_init - INT * @dsaf_dev: dsa fabric id */ static void hns_dsaf_comm_init(struct dsaf_device *dsaf_dev) @@ -2111,7 +2111,7 @@ static void hns_dsaf_free_dev(struct dsaf_device *dsaf_dev) } /** - * dsaf_pfc_unit_cnt - set pfc unit count + * hns_dsaf_pfc_unit_cnt - set pfc unit count * @dsaf_dev: dsa fabric id * @mac_id: id in use * @rate: value array @@ -2142,7 +2142,7 @@ static void hns_dsaf_pfc_unit_cnt(struct dsaf_device *dsaf_dev, int mac_id, } /** - * dsaf_port_work_rate_cfg - fifo + * hns_dsaf_port_work_rate_cfg - fifo * @dsaf_dev: dsa fabric id * @mac_id: mac contrl block * @rate_mode: value array @@ -2738,7 +2738,7 @@ void hns_dsaf_get_strings(int stringset, u8 *data, int port, } /** - *hns_dsaf_get_sset_count - get dsaf regs count + *hns_dsaf_get_regs_count - get dsaf regs count *return dsaf regs count */ int hns_dsaf_get_regs_count(void) @@ -2949,7 +2949,7 @@ int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port) } /** - * dsaf_probe - probo dsaf dev + * hns_dsaf_probe - probo dsaf dev * @pdev: dasf platform device * return 0 - success , negative --fail */ @@ -3004,7 +3004,7 @@ free_dev: } /** - * dsaf_remove - remove dsaf dev + * hns_dsaf_remove - remove dsaf dev * @pdev: dasf platform device */ static int hns_dsaf_remove(struct platform_device *pdev) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index 325e81d30cfd..23d9cbf262c3 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -56,31 +56,31 @@ static u32 dsaf_read_sub(struct dsaf_device *dsaf_dev, u32 reg) } static void hns_dsaf_acpi_ledctrl_by_port(struct hns_mac_cb *mac_cb, u8 op_type, - u32 link, u32 port, u32 act) + u32 link, u32 port, u32 act) { - union acpi_object *obj; - union acpi_object obj_args[3], argv4; + union acpi_object *obj; + union acpi_object obj_args[3], argv4; - obj_args[0].integer.type = ACPI_TYPE_INTEGER; - obj_args[0].integer.value = link; - obj_args[1].integer.type = ACPI_TYPE_INTEGER; - obj_args[1].integer.value = port; - obj_args[2].integer.type = ACPI_TYPE_INTEGER; - obj_args[2].integer.value = act; + obj_args[0].integer.type = ACPI_TYPE_INTEGER; + obj_args[0].integer.value = link; + obj_args[1].integer.type = ACPI_TYPE_INTEGER; + obj_args[1].integer.value = port; + obj_args[2].integer.type = ACPI_TYPE_INTEGER; + obj_args[2].integer.value = act; - argv4.type = ACPI_TYPE_PACKAGE; - argv4.package.count = 3; - argv4.package.elements = obj_args; + argv4.type = ACPI_TYPE_PACKAGE; + argv4.package.count = 3; + argv4.package.elements = obj_args; - obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev), - &hns_dsaf_acpi_dsm_guid, 0, op_type, &argv4); - if (!obj) { - dev_warn(mac_cb->dev, "ledctrl fail, link:%d port:%d act:%d!\n", - link, port, act); - return; - } + obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev), + &hns_dsaf_acpi_dsm_guid, 0, op_type, &argv4); + if (!obj) { + dev_warn(mac_cb->dev, "ledctrl fail, link:%d port:%d act:%d!\n", + link, port, act); + return; + } - ACPI_FREE(obj); + ACPI_FREE(obj); } static void hns_dsaf_acpi_locate_ledctrl_by_port(struct hns_mac_cb *mac_cb, @@ -151,15 +151,15 @@ static void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status, } static void hns_cpld_set_led_acpi(struct hns_mac_cb *mac_cb, int link_status, - u16 speed, int data) + u16 speed, int data) { - if (!mac_cb) { - pr_err("cpld_led_set mac_cb is null!\n"); - return; - } + if (!mac_cb) { + pr_err("cpld_led_set mac_cb is null!\n"); + return; + } - hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC, - link_status, mac_cb->mac_id, data); + hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC, + link_status, mac_cb->mac_id, data); } static void cpld_led_reset(struct hns_mac_cb *mac_cb) @@ -174,16 +174,16 @@ static void cpld_led_reset(struct hns_mac_cb *mac_cb) static void cpld_led_reset_acpi(struct hns_mac_cb *mac_cb) { - if (!mac_cb) { - pr_err("cpld_led_reset mac_cb is null!\n"); - return; - } + if (!mac_cb) { + pr_err("cpld_led_reset mac_cb is null!\n"); + return; + } - if (mac_cb->media_type != HNAE_MEDIA_TYPE_FIBER) - return; + if (mac_cb->media_type != HNAE_MEDIA_TYPE_FIBER) + return; - hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC, - 0, mac_cb->mac_id, 0); + hns_dsaf_acpi_ledctrl_by_port(mac_cb, HNS_OP_LED_SET_FUNC, + 0, mac_cb->mac_id, 0); } static int cpld_set_led_id(struct hns_mac_cb *mac_cb, @@ -351,7 +351,7 @@ hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) } /** - * hns_dsaf_srst_chns - reset dsaf channels + * hns_dsaf_srst_chns_acpi - reset dsaf channels * @dsaf_dev: dsaf device struct pointer * @msk: xbar channels mask value: * @dereset: false - request reset , true - drop reset @@ -501,7 +501,7 @@ static void hns_ppe_com_srst(struct dsaf_device *dsaf_dev, bool dereset) } /** - * hns_mac_get_sds_mode - get phy ifterface form serdes mode + * hns_mac_get_phy_if - get phy ifterface form serdes mode * @mac_cb: mac control block * retuen phy interface */ @@ -521,7 +521,7 @@ static phy_interface_t hns_mac_get_phy_if(struct hns_mac_cb *mac_cb) reg = HNS_MAC_HILINK4_REG; else reg = HNS_MAC_HILINK3_REG; - } else{ + } else { if (!HNS_DSAF_IS_DEBUG(mac_cb->dsaf_dev) && mac_id <= 3) reg = HNS_MAC_HILINK4V2_REG; else diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c index ff03cafccb66..a7eb87da4e70 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c @@ -296,7 +296,7 @@ int hns_ppe_wait_tx_fifo_clean(struct hns_ppe_cb *ppe_cb) } /** - * ppe_init_hw - init ppe + * hns_ppe_init_hw - init ppe * @ppe_cb: ppe device */ static void hns_ppe_init_hw(struct hns_ppe_cb *ppe_cb) @@ -343,7 +343,7 @@ static void hns_ppe_init_hw(struct hns_ppe_cb *ppe_cb) } /** - * ppe_uninit_hw - uninit ppe + * hns_ppe_uninit_hw - uninit ppe * @ppe_cb: ppe device */ static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb) @@ -382,7 +382,7 @@ void hns_ppe_uninit(struct dsaf_device *dsaf_dev) } /** - * hns_ppe_reset - reinit ppe/rcb hw + * hns_ppe_reset_common - reinit ppe/rcb hw * @dsaf_dev: dasf device * @ppe_common_index: the index * return void @@ -455,7 +455,7 @@ int hns_ppe_get_regs_count(void) } /** - * ppe_get_strings - get ppe srting + * hns_ppe_get_strings - get ppe srting * @ppe_cb: ppe device * @stringset: string set type * @data: output string diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c index 5d5dc6942232..e2ff3ca198d1 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -913,7 +913,7 @@ int hns_rcb_get_common_regs_count(void) } /** - *rcb_get_sset_count - rcb ring regs count + *hns_rcb_get_ring_regs_count - rcb ring regs count *return regs count */ int hns_rcb_get_ring_regs_count(void) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c index be52acd448f9..401fef5f1d07 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c @@ -104,7 +104,7 @@ static void hns_xgmac_rx_enable(struct mac_driver *drv, u32 value) } /** - * hns_xgmac_tx_lf_rf_insert - insert lf rf control about xgmac + * hns_xgmac_lf_rf_insert - insert lf rf control about xgmac * @mac_drv: mac driver * @mode: inserf rf or lf */ @@ -115,7 +115,7 @@ static void hns_xgmac_lf_rf_insert(struct mac_driver *mac_drv, u32 mode) } /** - * hns_xgmac__lf_rf_control_init - initial the lf rf control register + * hns_xgmac_lf_rf_control_init - initial the lf rf control register * @mac_drv: mac driver */ static void hns_xgmac_lf_rf_control_init(struct mac_driver *mac_drv) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 5e349c0bdecc..ad534f9e41ab 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -770,7 +770,7 @@ static u32 smooth_alg(u32 new_param, u32 old_param) } /** - * hns_nic_adp_coalesce - self adapte coalesce according to rx rate + * hns_nic_adpt_coalesce - self adapte coalesce according to rx rate * @ring_data: pointer to hns_nic_ring_data **/ static void hns_nic_adpt_coalesce(struct hns_nic_ring_data *ring_data) diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index a2c17af57fde..0a6cda309b24 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -20,7 +20,7 @@ enum HCLGE_MBX_OPCODE { HCLGE_MBX_API_NEGOTIATE, /* (VF -> PF) negotiate API version */ HCLGE_MBX_GET_QINFO, /* (VF -> PF) get queue config */ HCLGE_MBX_GET_QDEPTH, /* (VF -> PF) get queue depth */ - HCLGE_MBX_GET_TCINFO, /* (VF -> PF) get TC config */ + HCLGE_MBX_GET_BASIC_INFO, /* (VF -> PF) get basic info */ HCLGE_MBX_GET_RETA, /* (VF -> PF) get RETA */ HCLGE_MBX_GET_RSS_KEY, /* (VF -> PF) get RSS key */ HCLGE_MBX_GET_MAC_ADDR, /* (VF -> PF) get MAC addr */ @@ -69,6 +69,7 @@ enum hclge_mbx_vlan_cfg_subcode { HCLGE_MBX_VLAN_RX_OFF_CFG, /* set rx side vlan offload */ HCLGE_MBX_PORT_BASE_VLAN_CFG, /* set port based vlan configuration */ HCLGE_MBX_GET_PORT_BASE_VLAN_STATE, /* get port based vlan state */ + HCLGE_MBX_ENABLE_VLAN_FILTER, }; enum hclge_mbx_tbl_cfg_subcode { @@ -85,6 +86,13 @@ struct hclge_ring_chain_param { u8 int_gl_index; }; +struct hclge_basic_info { + u8 hw_tc_map; + u8 rsv; + u16 mbx_api_version; + u32 pf_caps; +}; + struct hclgevf_mbx_resp_status { struct mutex mbx_mutex; /* protects against contending sync cmd resp */ u32 origin_mbx_msg; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 1d2189047781..e0b7c3c44e7b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -91,6 +91,10 @@ enum HNAE3_DEV_CAP_BITS { HNAE3_DEV_SUPPORT_STASH_B, HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, HNAE3_DEV_SUPPORT_PAUSE_B, + HNAE3_DEV_SUPPORT_RAS_IMP_B, + HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B, + HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, + HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, }; #define hnae3_dev_fd_supported(hdev) \ @@ -126,6 +130,9 @@ enum HNAE3_DEV_CAP_BITS { #define hnae3_dev_phy_imp_supported(hdev) \ test_bit(HNAE3_DEV_SUPPORT_PHY_IMP_B, (hdev)->ae_dev->caps) +#define hnae3_dev_ras_imp_supported(hdev) \ + test_bit(HNAE3_DEV_SUPPORT_RAS_IMP_B, (hdev)->ae_dev->caps) + #define hnae3_dev_tqp_txrx_indep_supported(hdev) \ test_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, (hdev)->ae_dev->caps) @@ -141,18 +148,17 @@ enum HNAE3_DEV_CAP_BITS { #define hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev) \ test_bit(HNAE3_DEV_SUPPORT_TQP_TXRX_INDEP_B, (ae_dev)->caps) +#define hnae3_ae_dev_rxd_adv_layout_supported(ae_dev) \ + test_bit(HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B, (ae_dev)->caps) + +enum HNAE3_PF_CAP_BITS { + HNAE3_PF_SUPPORT_VLAN_FLTR_MDF_B = 0, +}; #define ring_ptr_move_fw(ring, p) \ ((ring)->p = ((ring)->p + 1) % (ring)->desc_num) #define ring_ptr_move_bw(ring, p) \ ((ring)->p = ((ring)->p - 1 + (ring)->desc_num) % (ring)->desc_num) -enum hns_desc_type { - DESC_TYPE_UNKNOWN, - DESC_TYPE_SKB, - DESC_TYPE_FRAGLIST_SKB, - DESC_TYPE_PAGE, -}; - struct hnae3_handle; struct hnae3_queue { @@ -234,7 +240,6 @@ enum hnae3_reset_type { HNAE3_FUNC_RESET, HNAE3_GLOBAL_RESET, HNAE3_IMP_RESET, - HNAE3_UNKNOWN_RESET, HNAE3_NONE_RESET, HNAE3_MAX_RESET, }; @@ -246,6 +251,52 @@ enum hnae3_port_base_vlan_state { HNAE3_PORT_BASE_VLAN_NOCHANGE, }; +enum hnae3_dbg_cmd { + HNAE3_DBG_CMD_TM_NODES, + HNAE3_DBG_CMD_TM_PRI, + HNAE3_DBG_CMD_TM_QSET, + HNAE3_DBG_CMD_TM_MAP, + HNAE3_DBG_CMD_TM_PG, + HNAE3_DBG_CMD_TM_PORT, + HNAE3_DBG_CMD_TC_SCH_INFO, + HNAE3_DBG_CMD_QOS_PAUSE_CFG, + HNAE3_DBG_CMD_QOS_PRI_MAP, + HNAE3_DBG_CMD_QOS_BUF_CFG, + HNAE3_DBG_CMD_DEV_INFO, + HNAE3_DBG_CMD_TX_BD, + HNAE3_DBG_CMD_RX_BD, + HNAE3_DBG_CMD_MAC_UC, + HNAE3_DBG_CMD_MAC_MC, + HNAE3_DBG_CMD_MNG_TBL, + HNAE3_DBG_CMD_LOOPBACK, + HNAE3_DBG_CMD_PTP_INFO, + HNAE3_DBG_CMD_INTERRUPT_INFO, + HNAE3_DBG_CMD_RESET_INFO, + HNAE3_DBG_CMD_IMP_INFO, + HNAE3_DBG_CMD_NCL_CONFIG, + HNAE3_DBG_CMD_REG_BIOS_COMMON, + HNAE3_DBG_CMD_REG_SSU, + HNAE3_DBG_CMD_REG_IGU_EGU, + HNAE3_DBG_CMD_REG_RPU, + HNAE3_DBG_CMD_REG_NCSI, + HNAE3_DBG_CMD_REG_RTC, + HNAE3_DBG_CMD_REG_PPP, + HNAE3_DBG_CMD_REG_RCB, + HNAE3_DBG_CMD_REG_TQP, + HNAE3_DBG_CMD_REG_MAC, + HNAE3_DBG_CMD_REG_DCB, + HNAE3_DBG_CMD_VLAN_CONFIG, + HNAE3_DBG_CMD_QUEUE_MAP, + HNAE3_DBG_CMD_RX_QUEUE_INFO, + HNAE3_DBG_CMD_TX_QUEUE_INFO, + HNAE3_DBG_CMD_FD_TCAM, + HNAE3_DBG_CMD_FD_COUNTER, + HNAE3_DBG_CMD_MAC_TNL_STATUS, + HNAE3_DBG_CMD_SERV_INFO, + HNAE3_DBG_CMD_UMV_INFO, + HNAE3_DBG_CMD_UNKNOWN, +}; + struct hnae3_vector_info { u8 __iomem *io_addr; int vector; @@ -470,6 +521,12 @@ struct hnae3_ae_dev { * Check if any cls flower rule exist * dbg_read_cmd * Execute debugfs read command. + * set_tx_hwts_info + * Save information for 1588 tx packet + * get_rx_hwts + * Get 1588 rx hwstamp + * get_ts_info + * Get phc info */ struct hnae3_ae_ops { int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev); @@ -585,7 +642,7 @@ struct hnae3_ae_ops { void (*get_mdix_mode)(struct hnae3_handle *handle, u8 *tp_mdix_ctrl, u8 *tp_mdix); - void (*enable_vlan_filter)(struct hnae3_handle *handle, bool enable); + int (*enable_vlan_filter)(struct hnae3_handle *handle, bool enable); int (*set_vlan_filter)(struct hnae3_handle *handle, __be16 proto, u16 vlan_id, bool is_kill); int (*set_vf_vlan_filter)(struct hnae3_handle *handle, int vfid, @@ -622,8 +679,7 @@ struct hnae3_ae_ops { void (*enable_fd)(struct hnae3_handle *handle, bool enable); int (*add_arfs_entry)(struct hnae3_handle *handle, u16 queue_id, u16 flow_id, struct flow_keys *fkeys); - int (*dbg_run_cmd)(struct hnae3_handle *handle, const char *cmd_buf); - int (*dbg_read_cmd)(struct hnae3_handle *handle, const char *cmd_buf, + int (*dbg_read_cmd)(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd, char *buf, int len); pci_ers_result_t (*handle_hw_ras_error)(struct hnae3_ae_dev *ae_dev); bool (*get_hw_reset_stat)(struct hnae3_handle *handle); @@ -656,6 +712,12 @@ struct hnae3_ae_ops { struct ethtool_link_ksettings *cmd); int (*set_phy_link_ksettings)(struct hnae3_handle *handle, const struct ethtool_link_ksettings *cmd); + bool (*set_tx_hwts_info)(struct hnae3_handle *handle, + struct sk_buff *skb); + void (*get_rx_hwts)(struct hnae3_handle *handle, struct sk_buff *skb, + u32 nsec, u32 sec); + int (*get_ts_info)(struct hnae3_handle *handle, + struct ethtool_ts_info *info); }; struct hnae3_dcb_ops { @@ -700,6 +762,7 @@ struct hnae3_knic_private_info { u16 rx_buf_len; u16 num_tx_desc; u16 num_rx_desc; + u32 tx_spare_buf_size; struct hnae3_tc_info tc_info; @@ -738,7 +801,6 @@ struct hnae3_roce_private_info { #define HNAE3_BPE BIT(2) /* broadcast promisc enable */ #define HNAE3_OVERFLOW_UPE BIT(3) /* unicast mac vlan overflow */ #define HNAE3_OVERFLOW_MPE BIT(4) /* multicast mac vlan overflow */ -#define HNAE3_VLAN_FLTR BIT(5) /* enable vlan filter */ #define HNAE3_UPE (HNAE3_USER_UPE | HNAE3_OVERFLOW_UPE) #define HNAE3_MPE (HNAE3_USER_MPE | HNAE3_OVERFLOW_MPE) @@ -786,10 +848,6 @@ struct hnae3_handle { #define hnae3_get_bit(origin, shift) \ hnae3_get_field(origin, 0x1 << (shift), shift) -#define HNAE3_DBG_TM_NODES "tm_nodes" -#define HNAE3_DBG_TM_PRI "tm_priority" -#define HNAE3_DBG_TM_QSET "tm_qset" - int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev); void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 9d702bd0c7c1..532523069d74 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -5,46 +5,539 @@ #include #include "hnae3.h" +#include "hns3_debugfs.h" #include "hns3_enet.h" -#define HNS3_DBG_READ_LEN 65536 -#define HNS3_DBG_WRITE_LEN 1024 - static struct dentry *hns3_dbgfs_root; -static int hns3_dbg_queue_info(struct hnae3_handle *h, - const char *cmd_buf) +static struct hns3_dbg_dentry_info hns3_dbg_dentry[] = { + { + .name = "tm" + }, + { + .name = "tx_bd_info" + }, + { + .name = "rx_bd_info" + }, + { + .name = "mac_list" + }, + { + .name = "reg" + }, + { + .name = "queue" + }, + { + .name = "fd" + }, + /* keep common at the bottom and add new directory above */ + { + .name = "common" + }, +}; + +static int hns3_dbg_bd_file_init(struct hnae3_handle *handle, unsigned int cmd); +static int hns3_dbg_common_file_init(struct hnae3_handle *handle, + unsigned int cmd); + +static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { + { + .name = "tm_nodes", + .cmd = HNAE3_DBG_CMD_TM_NODES, + .dentry = HNS3_DBG_DENTRY_TM, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "tm_priority", + .cmd = HNAE3_DBG_CMD_TM_PRI, + .dentry = HNS3_DBG_DENTRY_TM, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "tm_qset", + .cmd = HNAE3_DBG_CMD_TM_QSET, + .dentry = HNS3_DBG_DENTRY_TM, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "tm_map", + .cmd = HNAE3_DBG_CMD_TM_MAP, + .dentry = HNS3_DBG_DENTRY_TM, + .buf_len = HNS3_DBG_READ_LEN_1MB, + .init = hns3_dbg_common_file_init, + }, + { + .name = "tm_pg", + .cmd = HNAE3_DBG_CMD_TM_PG, + .dentry = HNS3_DBG_DENTRY_TM, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "tm_port", + .cmd = HNAE3_DBG_CMD_TM_PORT, + .dentry = HNS3_DBG_DENTRY_TM, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "tc_sch_info", + .cmd = HNAE3_DBG_CMD_TC_SCH_INFO, + .dentry = HNS3_DBG_DENTRY_TM, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "qos_pause_cfg", + .cmd = HNAE3_DBG_CMD_QOS_PAUSE_CFG, + .dentry = HNS3_DBG_DENTRY_TM, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "qos_pri_map", + .cmd = HNAE3_DBG_CMD_QOS_PRI_MAP, + .dentry = HNS3_DBG_DENTRY_TM, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "qos_buf_cfg", + .cmd = HNAE3_DBG_CMD_QOS_BUF_CFG, + .dentry = HNS3_DBG_DENTRY_TM, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "dev_info", + .cmd = HNAE3_DBG_CMD_DEV_INFO, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "tx_bd_queue", + .cmd = HNAE3_DBG_CMD_TX_BD, + .dentry = HNS3_DBG_DENTRY_TX_BD, + .buf_len = HNS3_DBG_READ_LEN_4MB, + .init = hns3_dbg_bd_file_init, + }, + { + .name = "rx_bd_queue", + .cmd = HNAE3_DBG_CMD_RX_BD, + .dentry = HNS3_DBG_DENTRY_RX_BD, + .buf_len = HNS3_DBG_READ_LEN_4MB, + .init = hns3_dbg_bd_file_init, + }, + { + .name = "uc", + .cmd = HNAE3_DBG_CMD_MAC_UC, + .dentry = HNS3_DBG_DENTRY_MAC, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "mc", + .cmd = HNAE3_DBG_CMD_MAC_MC, + .dentry = HNS3_DBG_DENTRY_MAC, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "mng_tbl", + .cmd = HNAE3_DBG_CMD_MNG_TBL, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "loopback", + .cmd = HNAE3_DBG_CMD_LOOPBACK, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "interrupt_info", + .cmd = HNAE3_DBG_CMD_INTERRUPT_INFO, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "reset_info", + .cmd = HNAE3_DBG_CMD_RESET_INFO, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "imp_info", + .cmd = HNAE3_DBG_CMD_IMP_INFO, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "ncl_config", + .cmd = HNAE3_DBG_CMD_NCL_CONFIG, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN_128KB, + .init = hns3_dbg_common_file_init, + }, + { + .name = "mac_tnl_status", + .cmd = HNAE3_DBG_CMD_MAC_TNL_STATUS, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "bios_common", + .cmd = HNAE3_DBG_CMD_REG_BIOS_COMMON, + .dentry = HNS3_DBG_DENTRY_REG, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "ssu", + .cmd = HNAE3_DBG_CMD_REG_SSU, + .dentry = HNS3_DBG_DENTRY_REG, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "igu_egu", + .cmd = HNAE3_DBG_CMD_REG_IGU_EGU, + .dentry = HNS3_DBG_DENTRY_REG, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "rpu", + .cmd = HNAE3_DBG_CMD_REG_RPU, + .dentry = HNS3_DBG_DENTRY_REG, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "ncsi", + .cmd = HNAE3_DBG_CMD_REG_NCSI, + .dentry = HNS3_DBG_DENTRY_REG, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "rtc", + .cmd = HNAE3_DBG_CMD_REG_RTC, + .dentry = HNS3_DBG_DENTRY_REG, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "ppp", + .cmd = HNAE3_DBG_CMD_REG_PPP, + .dentry = HNS3_DBG_DENTRY_REG, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "rcb", + .cmd = HNAE3_DBG_CMD_REG_RCB, + .dentry = HNS3_DBG_DENTRY_REG, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "tqp", + .cmd = HNAE3_DBG_CMD_REG_TQP, + .dentry = HNS3_DBG_DENTRY_REG, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "mac", + .cmd = HNAE3_DBG_CMD_REG_MAC, + .dentry = HNS3_DBG_DENTRY_REG, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "dcb", + .cmd = HNAE3_DBG_CMD_REG_DCB, + .dentry = HNS3_DBG_DENTRY_REG, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "queue_map", + .cmd = HNAE3_DBG_CMD_QUEUE_MAP, + .dentry = HNS3_DBG_DENTRY_QUEUE, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "rx_queue_info", + .cmd = HNAE3_DBG_CMD_RX_QUEUE_INFO, + .dentry = HNS3_DBG_DENTRY_QUEUE, + .buf_len = HNS3_DBG_READ_LEN_1MB, + .init = hns3_dbg_common_file_init, + }, + { + .name = "tx_queue_info", + .cmd = HNAE3_DBG_CMD_TX_QUEUE_INFO, + .dentry = HNS3_DBG_DENTRY_QUEUE, + .buf_len = HNS3_DBG_READ_LEN_1MB, + .init = hns3_dbg_common_file_init, + }, + { + .name = "fd_tcam", + .cmd = HNAE3_DBG_CMD_FD_TCAM, + .dentry = HNS3_DBG_DENTRY_FD, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "service_task_info", + .cmd = HNAE3_DBG_CMD_SERV_INFO, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "vlan_config", + .cmd = HNAE3_DBG_CMD_VLAN_CONFIG, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "ptp_info", + .cmd = HNAE3_DBG_CMD_PTP_INFO, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "fd_counter", + .cmd = HNAE3_DBG_CMD_FD_COUNTER, + .dentry = HNS3_DBG_DENTRY_FD, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, + { + .name = "umv_info", + .cmd = HNAE3_DBG_CMD_UMV_INFO, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, +}; + +static struct hns3_dbg_cap_info hns3_dbg_cap[] = { + { + .name = "support FD", + .cap_bit = HNAE3_DEV_SUPPORT_FD_B, + }, { + .name = "support GRO", + .cap_bit = HNAE3_DEV_SUPPORT_GRO_B, + }, { + .name = "support FEC", + .cap_bit = HNAE3_DEV_SUPPORT_FEC_B, + }, { + .name = "support UDP GSO", + .cap_bit = HNAE3_DEV_SUPPORT_UDP_GSO_B, + }, { + .name = "support PTP", + .cap_bit = HNAE3_DEV_SUPPORT_PTP_B, + }, { + .name = "support INT QL", + .cap_bit = HNAE3_DEV_SUPPORT_INT_QL_B, + }, { + .name = "support HW TX csum", + .cap_bit = HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, + }, { + .name = "support UDP tunnel csum", + .cap_bit = HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, + }, { + .name = "support TX push", + .cap_bit = HNAE3_DEV_SUPPORT_TX_PUSH_B, + }, { + .name = "support imp-controlled PHY", + .cap_bit = HNAE3_DEV_SUPPORT_PHY_IMP_B, + }, { + .name = "support imp-controlled RAS", + .cap_bit = HNAE3_DEV_SUPPORT_RAS_IMP_B, + }, { + .name = "support rxd advanced layout", + .cap_bit = HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B, + }, { + .name = "support port vlan bypass", + .cap_bit = HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, + }, { + .name = "support modify vlan filter state", + .cap_bit = HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, + } +}; + +static void hns3_dbg_fill_content(char *content, u16 len, + const struct hns3_dbg_item *items, + const char **result, u16 size) +{ + char *pos = content; + u16 i; + + memset(content, ' ', len); + for (i = 0; i < size; i++) { + if (result) + strncpy(pos, result[i], strlen(result[i])); + else + strncpy(pos, items[i].name, strlen(items[i].name)); + + pos += strlen(items[i].name) + items[i].interval; + } + + *pos++ = '\n'; + *pos++ = '\0'; +} + +static const struct hns3_dbg_item tx_spare_info_items[] = { + { "QUEUE_ID", 2 }, + { "COPYBREAK", 2 }, + { "LEN", 7 }, + { "NTU", 4 }, + { "NTC", 4 }, + { "LTC", 4 }, + { "DMA", 17 }, +}; + +static void hns3_dbg_tx_spare_info(struct hns3_enet_ring *ring, char *buf, + int len, u32 ring_num, int *pos) +{ + char data_str[ARRAY_SIZE(tx_spare_info_items)][HNS3_DBG_DATA_STR_LEN]; + struct hns3_tx_spare *tx_spare = ring->tx_spare; + char *result[ARRAY_SIZE(tx_spare_info_items)]; + char content[HNS3_DBG_INFO_LEN]; + u32 i, j; + + if (!tx_spare) { + *pos += scnprintf(buf + *pos, len - *pos, + "tx spare buffer is not enabled\n"); + return; + } + + for (i = 0; i < ARRAY_SIZE(tx_spare_info_items); i++) + result[i] = &data_str[i][0]; + + *pos += scnprintf(buf + *pos, len - *pos, "tx spare buffer info\n"); + hns3_dbg_fill_content(content, sizeof(content), tx_spare_info_items, + NULL, ARRAY_SIZE(tx_spare_info_items)); + *pos += scnprintf(buf + *pos, len - *pos, "%s", content); + + for (i = 0; i < ring_num; i++) { + j = 0; + sprintf(result[j++], "%8u", i); + sprintf(result[j++], "%9u", ring->tx_copybreak); + sprintf(result[j++], "%3u", tx_spare->len); + sprintf(result[j++], "%3u", tx_spare->next_to_use); + sprintf(result[j++], "%3u", tx_spare->next_to_clean); + sprintf(result[j++], "%3u", tx_spare->last_to_clean); + sprintf(result[j++], "%pad", &tx_spare->dma); + hns3_dbg_fill_content(content, sizeof(content), + tx_spare_info_items, + (const char **)result, + ARRAY_SIZE(tx_spare_info_items)); + *pos += scnprintf(buf + *pos, len - *pos, "%s", content); + } +} + +static const struct hns3_dbg_item rx_queue_info_items[] = { + { "QUEUE_ID", 2 }, + { "BD_NUM", 2 }, + { "BD_LEN", 2 }, + { "TAIL", 2 }, + { "HEAD", 2 }, + { "FBDNUM", 2 }, + { "PKTNUM", 2 }, + { "COPYBREAK", 2 }, + { "RING_EN", 2 }, + { "RX_RING_EN", 2 }, + { "BASE_ADDR", 10 }, +}; + +static void hns3_dump_rx_queue_info(struct hns3_enet_ring *ring, + struct hnae3_ae_dev *ae_dev, char **result, + u32 index) { - struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev); - struct hns3_nic_priv *priv = h->priv; - struct hns3_enet_ring *ring; u32 base_add_l, base_add_h; - u32 queue_num, queue_max; - u32 value, i; - int cnt; + u32 j = 0; + + sprintf(result[j++], "%8u", index); + + sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_RX_RING_BD_NUM_REG)); + + sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_RX_RING_BD_LEN_REG)); + + sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_RX_RING_TAIL_REG)); + + sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_RX_RING_HEAD_REG)); + + sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_RX_RING_FBDNUM_REG)); + + sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_RX_RING_PKTNUM_RECORD_REG)); + sprintf(result[j++], "%9u", ring->rx_copybreak); + + sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base + + HNS3_RING_EN_REG) ? "on" : "off"); + + if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) + sprintf(result[j++], "%10s", readl_relaxed(ring->tqp->io_base + + HNS3_RING_RX_EN_REG) ? "on" : "off"); + else + sprintf(result[j++], "%10s", "NA"); + + base_add_h = readl_relaxed(ring->tqp->io_base + + HNS3_RING_RX_RING_BASEADDR_H_REG); + base_add_l = readl_relaxed(ring->tqp->io_base + + HNS3_RING_RX_RING_BASEADDR_L_REG); + sprintf(result[j++], "0x%08x%08x", base_add_h, base_add_l); +} + +static int hns3_dbg_rx_queue_info(struct hnae3_handle *h, + char *buf, int len) +{ + char data_str[ARRAY_SIZE(rx_queue_info_items)][HNS3_DBG_DATA_STR_LEN]; + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev); + char *result[ARRAY_SIZE(rx_queue_info_items)]; + struct hns3_nic_priv *priv = h->priv; + char content[HNS3_DBG_INFO_LEN]; + struct hns3_enet_ring *ring; + int pos = 0; + u32 i; if (!priv->ring) { dev_err(&h->pdev->dev, "priv->ring is NULL\n"); return -EFAULT; } - queue_max = h->kinfo.num_tqps; - cnt = kstrtouint(&cmd_buf[11], 0, &queue_num); - if (cnt) - queue_num = 0; - else - queue_max = queue_num + 1; + for (i = 0; i < ARRAY_SIZE(rx_queue_info_items); i++) + result[i] = &data_str[i][0]; - dev_info(&h->pdev->dev, "queue info\n"); - - if (queue_num >= h->kinfo.num_tqps) { - dev_err(&h->pdev->dev, - "Queue number(%u) is out of range(0-%u)\n", queue_num, - h->kinfo.num_tqps - 1); - return -EINVAL; - } - - for (i = queue_num; i < queue_max; i++) { + hns3_dbg_fill_content(content, sizeof(content), rx_queue_info_items, + NULL, ARRAY_SIZE(rx_queue_info_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + for (i = 0; i < h->kinfo.num_tqps; i++) { /* Each cycle needs to determine whether the instance is reset, * to prevent reference to invalid memory. And need to ensure * that the following code is executed within 100ms. @@ -54,491 +547,524 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h, return -EPERM; ring = &priv->ring[(u32)(i + h->kinfo.num_tqps)]; - base_add_h = readl_relaxed(ring->tqp->io_base + - HNS3_RING_RX_RING_BASEADDR_H_REG); - base_add_l = readl_relaxed(ring->tqp->io_base + - HNS3_RING_RX_RING_BASEADDR_L_REG); - dev_info(&h->pdev->dev, "RX(%u) BASE ADD: 0x%08x%08x\n", i, - base_add_h, base_add_l); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_RX_RING_BD_NUM_REG); - dev_info(&h->pdev->dev, "RX(%u) RING BD NUM: %u\n", i, value); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_RX_RING_BD_LEN_REG); - dev_info(&h->pdev->dev, "RX(%u) RING BD LEN: %u\n", i, value); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_RX_RING_TAIL_REG); - dev_info(&h->pdev->dev, "RX(%u) RING TAIL: %u\n", i, value); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_RX_RING_HEAD_REG); - dev_info(&h->pdev->dev, "RX(%u) RING HEAD: %u\n", i, value); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_RX_RING_FBDNUM_REG); - dev_info(&h->pdev->dev, "RX(%u) RING FBDNUM: %u\n", i, value); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_RX_RING_PKTNUM_RECORD_REG); - dev_info(&h->pdev->dev, "RX(%u) RING PKTNUM: %u\n", i, value); - - ring = &priv->ring[i]; - base_add_h = readl_relaxed(ring->tqp->io_base + - HNS3_RING_TX_RING_BASEADDR_H_REG); - base_add_l = readl_relaxed(ring->tqp->io_base + - HNS3_RING_TX_RING_BASEADDR_L_REG); - dev_info(&h->pdev->dev, "TX(%u) BASE ADD: 0x%08x%08x\n", i, - base_add_h, base_add_l); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_TX_RING_BD_NUM_REG); - dev_info(&h->pdev->dev, "TX(%u) RING BD NUM: %u\n", i, value); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_TX_RING_TC_REG); - dev_info(&h->pdev->dev, "TX(%u) RING TC: %u\n", i, value); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_TX_RING_TAIL_REG); - dev_info(&h->pdev->dev, "TX(%u) RING TAIL: %u\n", i, value); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_TX_RING_HEAD_REG); - dev_info(&h->pdev->dev, "TX(%u) RING HEAD: %u\n", i, value); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_TX_RING_FBDNUM_REG); - dev_info(&h->pdev->dev, "TX(%u) RING FBDNUM: %u\n", i, value); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_TX_RING_OFFSET_REG); - dev_info(&h->pdev->dev, "TX(%u) RING OFFSET: %u\n", i, value); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_TX_RING_PKTNUM_RECORD_REG); - dev_info(&h->pdev->dev, "TX(%u) RING PKTNUM: %u\n", i, value); - - value = readl_relaxed(ring->tqp->io_base + HNS3_RING_EN_REG); - dev_info(&h->pdev->dev, "TX/RX(%u) RING EN: %s\n", i, - value ? "enable" : "disable"); - - if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) { - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_TX_EN_REG); - dev_info(&h->pdev->dev, "TX(%u) RING EN: %s\n", i, - value ? "enable" : "disable"); - - value = readl_relaxed(ring->tqp->io_base + - HNS3_RING_RX_EN_REG); - dev_info(&h->pdev->dev, "RX(%u) RING EN: %s\n", i, - value ? "enable" : "disable"); - } - - dev_info(&h->pdev->dev, "\n"); + hns3_dump_rx_queue_info(ring, ae_dev, result, i); + hns3_dbg_fill_content(content, sizeof(content), + rx_queue_info_items, + (const char **)result, + ARRAY_SIZE(rx_queue_info_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); } return 0; } -static int hns3_dbg_queue_map(struct hnae3_handle *h) +static const struct hns3_dbg_item tx_queue_info_items[] = { + { "QUEUE_ID", 2 }, + { "BD_NUM", 2 }, + { "TC", 2 }, + { "TAIL", 2 }, + { "HEAD", 2 }, + { "FBDNUM", 2 }, + { "OFFSET", 2 }, + { "PKTNUM", 2 }, + { "RING_EN", 2 }, + { "TX_RING_EN", 2 }, + { "BASE_ADDR", 10 }, +}; + +static void hns3_dump_tx_queue_info(struct hns3_enet_ring *ring, + struct hnae3_ae_dev *ae_dev, char **result, + u32 index) { + u32 base_add_l, base_add_h; + u32 j = 0; + + sprintf(result[j++], "%8u", index); + sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_TX_RING_BD_NUM_REG)); + + sprintf(result[j++], "%2u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_TX_RING_TC_REG)); + + sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_TX_RING_TAIL_REG)); + + sprintf(result[j++], "%4u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_TX_RING_HEAD_REG)); + + sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_TX_RING_FBDNUM_REG)); + + sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_TX_RING_OFFSET_REG)); + + sprintf(result[j++], "%6u", readl_relaxed(ring->tqp->io_base + + HNS3_RING_TX_RING_PKTNUM_RECORD_REG)); + + sprintf(result[j++], "%7s", readl_relaxed(ring->tqp->io_base + + HNS3_RING_EN_REG) ? "on" : "off"); + + if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev)) + sprintf(result[j++], "%10s", readl_relaxed(ring->tqp->io_base + + HNS3_RING_TX_EN_REG) ? "on" : "off"); + else + sprintf(result[j++], "%10s", "NA"); + + base_add_h = readl_relaxed(ring->tqp->io_base + + HNS3_RING_TX_RING_BASEADDR_H_REG); + base_add_l = readl_relaxed(ring->tqp->io_base + + HNS3_RING_TX_RING_BASEADDR_L_REG); + sprintf(result[j++], "0x%08x%08x", base_add_h, base_add_l); +} + +static int hns3_dbg_tx_queue_info(struct hnae3_handle *h, + char *buf, int len) +{ + char data_str[ARRAY_SIZE(tx_queue_info_items)][HNS3_DBG_DATA_STR_LEN]; + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev); + char *result[ARRAY_SIZE(tx_queue_info_items)]; struct hns3_nic_priv *priv = h->priv; - int i; + char content[HNS3_DBG_INFO_LEN]; + struct hns3_enet_ring *ring; + int pos = 0; + u32 i; + + if (!priv->ring) { + dev_err(&h->pdev->dev, "priv->ring is NULL\n"); + return -EFAULT; + } + + for (i = 0; i < ARRAY_SIZE(tx_queue_info_items); i++) + result[i] = &data_str[i][0]; + + hns3_dbg_fill_content(content, sizeof(content), tx_queue_info_items, + NULL, ARRAY_SIZE(tx_queue_info_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + + for (i = 0; i < h->kinfo.num_tqps; i++) { + /* Each cycle needs to determine whether the instance is reset, + * to prevent reference to invalid memory. And need to ensure + * that the following code is executed within 100ms. + */ + if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) || + test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) + return -EPERM; + + ring = &priv->ring[i]; + hns3_dump_tx_queue_info(ring, ae_dev, result, i); + hns3_dbg_fill_content(content, sizeof(content), + tx_queue_info_items, + (const char **)result, + ARRAY_SIZE(tx_queue_info_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + } + + hns3_dbg_tx_spare_info(ring, buf, len, h->kinfo.num_tqps, &pos); + + return 0; +} + +static const struct hns3_dbg_item queue_map_items[] = { + { "local_queue_id", 2 }, + { "global_queue_id", 2 }, + { "vector_id", 2 }, +}; + +static int hns3_dbg_queue_map(struct hnae3_handle *h, char *buf, int len) +{ + char data_str[ARRAY_SIZE(queue_map_items)][HNS3_DBG_DATA_STR_LEN]; + char *result[ARRAY_SIZE(queue_map_items)]; + struct hns3_nic_priv *priv = h->priv; + char content[HNS3_DBG_INFO_LEN]; + int pos = 0; + int j; + u32 i; if (!h->ae_algo->ops->get_global_queue_id) return -EOPNOTSUPP; - dev_info(&h->pdev->dev, "map info for queue id and vector id\n"); - dev_info(&h->pdev->dev, - "local queue id | global queue id | vector id\n"); - for (i = 0; i < h->kinfo.num_tqps; i++) { - u16 global_qid; + for (i = 0; i < ARRAY_SIZE(queue_map_items); i++) + result[i] = &data_str[i][0]; - global_qid = h->ae_algo->ops->get_global_queue_id(h, i); + hns3_dbg_fill_content(content, sizeof(content), queue_map_items, + NULL, ARRAY_SIZE(queue_map_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + for (i = 0; i < h->kinfo.num_tqps; i++) { if (!priv->ring || !priv->ring[i].tqp_vector) continue; - - dev_info(&h->pdev->dev, - " %4d %4u %4d\n", - i, global_qid, priv->ring[i].tqp_vector->vector_irq); + j = 0; + sprintf(result[j++], "%u", i); + sprintf(result[j++], "%u", + h->ae_algo->ops->get_global_queue_id(h, i)); + sprintf(result[j++], "%u", + priv->ring[i].tqp_vector->vector_irq); + hns3_dbg_fill_content(content, sizeof(content), queue_map_items, + (const char **)result, + ARRAY_SIZE(queue_map_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); } return 0; } -static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf) +static const struct hns3_dbg_item rx_bd_info_items[] = { + { "BD_IDX", 3 }, + { "L234_INFO", 2 }, + { "PKT_LEN", 3 }, + { "SIZE", 4 }, + { "RSS_HASH", 4 }, + { "FD_ID", 2 }, + { "VLAN_TAG", 2 }, + { "O_DM_VLAN_ID_FB", 2 }, + { "OT_VLAN_TAG", 2 }, + { "BD_BASE_INFO", 2 }, + { "PTYPE", 2 }, + { "HW_CSUM", 2 }, +}; + +static void hns3_dump_rx_bd_info(struct hns3_nic_priv *priv, + struct hns3_desc *desc, char **result, int idx) { - struct hns3_nic_priv *priv = h->priv; - struct hns3_desc *rx_desc, *tx_desc; - struct device *dev = &h->pdev->dev; - struct hns3_enet_ring *ring; - u32 tx_index, rx_index; - u32 q_num, value; - dma_addr_t addr; - u16 mss_hw_csum; - u32 l234info; - int cnt; + unsigned int j = 0; - cnt = sscanf(&cmd_buf[8], "%u %u", &q_num, &tx_index); - if (cnt == 2) { - rx_index = tx_index; - } else if (cnt != 1) { - dev_err(dev, "bd info: bad command string, cnt=%d\n", cnt); - return -EINVAL; - } + sprintf(result[j++], "%5d", idx); + sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.l234_info)); + sprintf(result[j++], "%7u", le16_to_cpu(desc->rx.pkt_len)); + sprintf(result[j++], "%4u", le16_to_cpu(desc->rx.size)); + sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.rss_hash)); + sprintf(result[j++], "%5u", le16_to_cpu(desc->rx.fd_id)); + sprintf(result[j++], "%8u", le16_to_cpu(desc->rx.vlan_tag)); + sprintf(result[j++], "%15u", le16_to_cpu(desc->rx.o_dm_vlan_id_fb)); + sprintf(result[j++], "%11u", le16_to_cpu(desc->rx.ot_vlan_tag)); + sprintf(result[j++], "%#x", le32_to_cpu(desc->rx.bd_base_info)); + if (test_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state)) { + u32 ol_info = le32_to_cpu(desc->rx.ol_info); - if (q_num >= h->kinfo.num_tqps) { - dev_err(dev, "Queue number(%u) is out of range(0-%u)\n", q_num, - h->kinfo.num_tqps - 1); - return -EINVAL; - } - - ring = &priv->ring[q_num]; - value = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG); - tx_index = (cnt == 1) ? value : tx_index; - - if (tx_index >= ring->desc_num) { - dev_err(dev, "bd index(%u) is out of range(0-%u)\n", tx_index, - ring->desc_num - 1); - return -EINVAL; - } - - tx_desc = &ring->desc[tx_index]; - addr = le64_to_cpu(tx_desc->addr); - mss_hw_csum = le16_to_cpu(tx_desc->tx.mss_hw_csum); - dev_info(dev, "TX Queue Num: %u, BD Index: %u\n", q_num, tx_index); - dev_info(dev, "(TX)addr: %pad\n", &addr); - dev_info(dev, "(TX)vlan_tag: %u\n", le16_to_cpu(tx_desc->tx.vlan_tag)); - dev_info(dev, "(TX)send_size: %u\n", - le16_to_cpu(tx_desc->tx.send_size)); - - if (mss_hw_csum & BIT(HNS3_TXD_HW_CS_B)) { - u32 offset = le32_to_cpu(tx_desc->tx.ol_type_vlan_len_msec); - u32 start = le32_to_cpu(tx_desc->tx.type_cs_vlan_tso_len); - - dev_info(dev, "(TX)csum start: %u\n", - hnae3_get_field(start, - HNS3_TXD_CSUM_START_M, - HNS3_TXD_CSUM_START_S)); - dev_info(dev, "(TX)csum offset: %u\n", - hnae3_get_field(offset, - HNS3_TXD_CSUM_OFFSET_M, - HNS3_TXD_CSUM_OFFSET_S)); + sprintf(result[j++], "%5lu", hnae3_get_field(ol_info, + HNS3_RXD_PTYPE_M, + HNS3_RXD_PTYPE_S)); + sprintf(result[j++], "%7u", le16_to_cpu(desc->csum)); } else { - dev_info(dev, "(TX)vlan_tso: %u\n", - tx_desc->tx.type_cs_vlan_tso); - dev_info(dev, "(TX)l2_len: %u\n", tx_desc->tx.l2_len); - dev_info(dev, "(TX)l3_len: %u\n", tx_desc->tx.l3_len); - dev_info(dev, "(TX)l4_len: %u\n", tx_desc->tx.l4_len); - dev_info(dev, "(TX)vlan_msec: %u\n", - tx_desc->tx.ol_type_vlan_msec); - dev_info(dev, "(TX)ol2_len: %u\n", tx_desc->tx.ol2_len); - dev_info(dev, "(TX)ol3_len: %u\n", tx_desc->tx.ol3_len); - dev_info(dev, "(TX)ol4_len: %u\n", tx_desc->tx.ol4_len); + sprintf(result[j++], "NA"); + sprintf(result[j++], "NA"); + } +} + +static int hns3_dbg_rx_bd_info(struct hns3_dbg_data *d, char *buf, int len) +{ + char data_str[ARRAY_SIZE(rx_bd_info_items)][HNS3_DBG_DATA_STR_LEN]; + struct hns3_nic_priv *priv = d->handle->priv; + char *result[ARRAY_SIZE(rx_bd_info_items)]; + char content[HNS3_DBG_INFO_LEN]; + struct hns3_enet_ring *ring; + struct hns3_desc *desc; + unsigned int i; + int pos = 0; + + if (d->qid >= d->handle->kinfo.num_tqps) { + dev_err(&d->handle->pdev->dev, + "queue%u is not in use\n", d->qid); + return -EINVAL; } - dev_info(dev, "(TX)vlan_tag: %u\n", - le16_to_cpu(tx_desc->tx.outer_vlan_tag)); - dev_info(dev, "(TX)tv: %u\n", le16_to_cpu(tx_desc->tx.tv)); - dev_info(dev, "(TX)paylen_ol4cs: %u\n", - le32_to_cpu(tx_desc->tx.paylen_ol4cs)); - dev_info(dev, "(TX)vld_ra_ri: %u\n", - le16_to_cpu(tx_desc->tx.bdtp_fe_sc_vld_ra_ri)); - dev_info(dev, "(TX)mss_hw_csum: %u\n", mss_hw_csum); + for (i = 0; i < ARRAY_SIZE(rx_bd_info_items); i++) + result[i] = &data_str[i][0]; - ring = &priv->ring[q_num + h->kinfo.num_tqps]; - value = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_TAIL_REG); - rx_index = (cnt == 1) ? value : tx_index; - rx_desc = &ring->desc[rx_index]; + pos += scnprintf(buf + pos, len - pos, + "Queue %u rx bd info:\n", d->qid); + hns3_dbg_fill_content(content, sizeof(content), rx_bd_info_items, + NULL, ARRAY_SIZE(rx_bd_info_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); - addr = le64_to_cpu(rx_desc->addr); - l234info = le32_to_cpu(rx_desc->rx.l234_info); - dev_info(dev, "RX Queue Num: %u, BD Index: %u\n", q_num, rx_index); - dev_info(dev, "(RX)addr: %pad\n", &addr); - dev_info(dev, "(RX)l234_info: %u\n", l234info); + ring = &priv->ring[d->qid + d->handle->kinfo.num_tqps]; + for (i = 0; i < ring->desc_num; i++) { + desc = &ring->desc[i]; - if (l234info & BIT(HNS3_RXD_L2_CSUM_B)) { - u32 lo, hi; - - lo = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_L_M, - HNS3_RXD_L2_CSUM_L_S); - hi = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_H_M, - HNS3_RXD_L2_CSUM_H_S); - dev_info(dev, "(RX)csum: %u\n", lo | hi << 8); + hns3_dump_rx_bd_info(priv, desc, result, i); + hns3_dbg_fill_content(content, sizeof(content), + rx_bd_info_items, (const char **)result, + ARRAY_SIZE(rx_bd_info_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); } - dev_info(dev, "(RX)pkt_len: %u\n", le16_to_cpu(rx_desc->rx.pkt_len)); - dev_info(dev, "(RX)size: %u\n", le16_to_cpu(rx_desc->rx.size)); - dev_info(dev, "(RX)rss_hash: %u\n", le32_to_cpu(rx_desc->rx.rss_hash)); - dev_info(dev, "(RX)fd_id: %u\n", le16_to_cpu(rx_desc->rx.fd_id)); - dev_info(dev, "(RX)vlan_tag: %u\n", le16_to_cpu(rx_desc->rx.vlan_tag)); - dev_info(dev, "(RX)o_dm_vlan_id_fb: %u\n", - le16_to_cpu(rx_desc->rx.o_dm_vlan_id_fb)); - dev_info(dev, "(RX)ot_vlan_tag: %u\n", - le16_to_cpu(rx_desc->rx.ot_vlan_tag)); - dev_info(dev, "(RX)bd_base_info: %u\n", - le32_to_cpu(rx_desc->rx.bd_base_info)); - return 0; } -static void hns3_dbg_help(struct hnae3_handle *h) +static const struct hns3_dbg_item tx_bd_info_items[] = { + { "BD_IDX", 5 }, + { "ADDRESS", 2 }, + { "VLAN_TAG", 2 }, + { "SIZE", 2 }, + { "T_CS_VLAN_TSO", 2 }, + { "OT_VLAN_TAG", 3 }, + { "TV", 2 }, + { "OLT_VLAN_LEN", 2}, + { "PAYLEN_OL4CS", 2}, + { "BD_FE_SC_VLD", 2}, + { "MSS_HW_CSUM", 0}, +}; + +static void hns3_dump_tx_bd_info(struct hns3_nic_priv *priv, + struct hns3_desc *desc, char **result, int idx) { -#define HNS3_DBG_BUF_LEN 256 + unsigned int j = 0; - char printf_buf[HNS3_DBG_BUF_LEN]; - - dev_info(&h->pdev->dev, "available commands\n"); - dev_info(&h->pdev->dev, "queue info \n"); - dev_info(&h->pdev->dev, "queue map\n"); - dev_info(&h->pdev->dev, "bd info \n"); - dev_info(&h->pdev->dev, "dev capability\n"); - dev_info(&h->pdev->dev, "dev spec\n"); - - if (!hns3_is_phys_func(h->pdev)) - return; - - dev_info(&h->pdev->dev, "dump fd tcam\n"); - dev_info(&h->pdev->dev, "dump tc\n"); - dev_info(&h->pdev->dev, "dump tm map \n"); - dev_info(&h->pdev->dev, "dump tm\n"); - dev_info(&h->pdev->dev, "dump qos pause cfg\n"); - dev_info(&h->pdev->dev, "dump qos pri map\n"); - dev_info(&h->pdev->dev, "dump qos buf cfg\n"); - dev_info(&h->pdev->dev, "dump mng tbl\n"); - dev_info(&h->pdev->dev, "dump reset info\n"); - dev_info(&h->pdev->dev, "dump m7 info\n"); - dev_info(&h->pdev->dev, "dump ncl_config (in hex)\n"); - dev_info(&h->pdev->dev, "dump mac tnl status\n"); - dev_info(&h->pdev->dev, "dump loopback\n"); - dev_info(&h->pdev->dev, "dump qs shaper [qs id]\n"); - dev_info(&h->pdev->dev, "dump uc mac list \n"); - dev_info(&h->pdev->dev, "dump mc mac list \n"); - dev_info(&h->pdev->dev, "dump intr\n"); - - memset(printf_buf, 0, HNS3_DBG_BUF_LEN); - strncat(printf_buf, "dump reg [[bios common] [ssu ]", - HNS3_DBG_BUF_LEN - 1); - strncat(printf_buf + strlen(printf_buf), - " [igu egu ] [rpu ]", - HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1); - strncat(printf_buf + strlen(printf_buf), - " [rtc] [ppp] [rcb] [tqp ] [mac]]\n", - HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1); - dev_info(&h->pdev->dev, "%s", printf_buf); - - memset(printf_buf, 0, HNS3_DBG_BUF_LEN); - strncat(printf_buf, "dump reg dcb ", - HNS3_DBG_BUF_LEN - 1); - strncat(printf_buf + strlen(printf_buf), " \n", - HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1); - dev_info(&h->pdev->dev, "%s", printf_buf); + sprintf(result[j++], "%6d", idx); + sprintf(result[j++], "%#llx", le64_to_cpu(desc->addr)); + sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.vlan_tag)); + sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.send_size)); + sprintf(result[j++], "%#x", + le32_to_cpu(desc->tx.type_cs_vlan_tso_len)); + sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.outer_vlan_tag)); + sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.tv)); + sprintf(result[j++], "%10u", + le32_to_cpu(desc->tx.ol_type_vlan_len_msec)); + sprintf(result[j++], "%#x", le32_to_cpu(desc->tx.paylen_ol4cs)); + sprintf(result[j++], "%#x", le16_to_cpu(desc->tx.bdtp_fe_sc_vld_ra_ri)); + sprintf(result[j++], "%5u", le16_to_cpu(desc->tx.mss_hw_csum)); } -static void hns3_dbg_dev_caps(struct hnae3_handle *h) +static int hns3_dbg_tx_bd_info(struct hns3_dbg_data *d, char *buf, int len) +{ + char data_str[ARRAY_SIZE(tx_bd_info_items)][HNS3_DBG_DATA_STR_LEN]; + struct hns3_nic_priv *priv = d->handle->priv; + char *result[ARRAY_SIZE(tx_bd_info_items)]; + char content[HNS3_DBG_INFO_LEN]; + struct hns3_enet_ring *ring; + struct hns3_desc *desc; + unsigned int i; + int pos = 0; + + if (d->qid >= d->handle->kinfo.num_tqps) { + dev_err(&d->handle->pdev->dev, + "queue%u is not in use\n", d->qid); + return -EINVAL; + } + + for (i = 0; i < ARRAY_SIZE(tx_bd_info_items); i++) + result[i] = &data_str[i][0]; + + pos += scnprintf(buf + pos, len - pos, + "Queue %u tx bd info:\n", d->qid); + hns3_dbg_fill_content(content, sizeof(content), tx_bd_info_items, + NULL, ARRAY_SIZE(tx_bd_info_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + + ring = &priv->ring[d->qid]; + for (i = 0; i < ring->desc_num; i++) { + desc = &ring->desc[i]; + + hns3_dump_tx_bd_info(priv, desc, result, i); + hns3_dbg_fill_content(content, sizeof(content), + tx_bd_info_items, (const char **)result, + ARRAY_SIZE(tx_bd_info_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + } + + return 0; +} + +static void +hns3_dbg_dev_caps(struct hnae3_handle *h, char *buf, int len, int *pos) { struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev); - unsigned long *caps; + static const char * const str[] = {"no", "yes"}; + unsigned long *caps = ae_dev->caps; + u32 i, state; - caps = ae_dev->caps; + *pos += scnprintf(buf + *pos, len - *pos, "dev capability:\n"); - dev_info(&h->pdev->dev, "support FD: %s\n", - test_bit(HNAE3_DEV_SUPPORT_FD_B, caps) ? "yes" : "no"); - dev_info(&h->pdev->dev, "support GRO: %s\n", - test_bit(HNAE3_DEV_SUPPORT_GRO_B, caps) ? "yes" : "no"); - dev_info(&h->pdev->dev, "support FEC: %s\n", - test_bit(HNAE3_DEV_SUPPORT_FEC_B, caps) ? "yes" : "no"); - dev_info(&h->pdev->dev, "support UDP GSO: %s\n", - test_bit(HNAE3_DEV_SUPPORT_UDP_GSO_B, caps) ? "yes" : "no"); - dev_info(&h->pdev->dev, "support PTP: %s\n", - test_bit(HNAE3_DEV_SUPPORT_PTP_B, caps) ? "yes" : "no"); - dev_info(&h->pdev->dev, "support INT QL: %s\n", - test_bit(HNAE3_DEV_SUPPORT_INT_QL_B, caps) ? "yes" : "no"); - dev_info(&h->pdev->dev, "support HW TX csum: %s\n", - test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, caps) ? "yes" : "no"); - dev_info(&h->pdev->dev, "support UDP tunnel csum: %s\n", - test_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, caps) ? - "yes" : "no"); - dev_info(&h->pdev->dev, "support PAUSE: %s\n", - test_bit(HNAE3_DEV_SUPPORT_PAUSE_B, ae_dev->caps) ? - "yes" : "no"); - dev_info(&h->pdev->dev, "support imp-controlled PHY: %s\n", - test_bit(HNAE3_DEV_SUPPORT_PHY_IMP_B, caps) ? "yes" : "no"); + for (i = 0; i < ARRAY_SIZE(hns3_dbg_cap); i++) { + state = test_bit(hns3_dbg_cap[i].cap_bit, caps); + *pos += scnprintf(buf + *pos, len - *pos, "%s: %s\n", + hns3_dbg_cap[i].name, str[state]); + } + + *pos += scnprintf(buf + *pos, len - *pos, "\n"); } -static void hns3_dbg_dev_specs(struct hnae3_handle *h) +static void +hns3_dbg_dev_specs(struct hnae3_handle *h, char *buf, int len, int *pos) { struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev); struct hnae3_dev_specs *dev_specs = &ae_dev->dev_specs; struct hnae3_knic_private_info *kinfo = &h->kinfo; - struct hns3_nic_priv *priv = h->priv; - dev_info(priv->dev, "MAC entry num: %u\n", dev_specs->mac_entry_num); - dev_info(priv->dev, "MNG entry num: %u\n", dev_specs->mng_entry_num); - dev_info(priv->dev, "MAX non tso bd num: %u\n", - dev_specs->max_non_tso_bd_num); - dev_info(priv->dev, "RSS ind tbl size: %u\n", - dev_specs->rss_ind_tbl_size); - dev_info(priv->dev, "RSS key size: %u\n", dev_specs->rss_key_size); - dev_info(priv->dev, "RSS size: %u\n", kinfo->rss_size); - dev_info(priv->dev, "Allocated RSS size: %u\n", kinfo->req_rss_size); - dev_info(priv->dev, "Task queue pairs numbers: %u\n", kinfo->num_tqps); - - dev_info(priv->dev, "RX buffer length: %u\n", kinfo->rx_buf_len); - dev_info(priv->dev, "Desc num per TX queue: %u\n", kinfo->num_tx_desc); - dev_info(priv->dev, "Desc num per RX queue: %u\n", kinfo->num_rx_desc); - dev_info(priv->dev, "Total number of enabled TCs: %u\n", - kinfo->tc_info.num_tc); - dev_info(priv->dev, "MAX INT QL: %u\n", dev_specs->int_ql_max); - dev_info(priv->dev, "MAX INT GL: %u\n", dev_specs->max_int_gl); - dev_info(priv->dev, "MAX frame size: %u\n", dev_specs->max_frm_size); - dev_info(priv->dev, "MAX TM RATE: %uMbps\n", dev_specs->max_tm_rate); - dev_info(priv->dev, "MAX QSET number: %u\n", dev_specs->max_qset_num); + *pos += scnprintf(buf + *pos, len - *pos, "dev_spec:\n"); + *pos += scnprintf(buf + *pos, len - *pos, "MAC entry num: %u\n", + dev_specs->mac_entry_num); + *pos += scnprintf(buf + *pos, len - *pos, "MNG entry num: %u\n", + dev_specs->mng_entry_num); + *pos += scnprintf(buf + *pos, len - *pos, "MAX non tso bd num: %u\n", + dev_specs->max_non_tso_bd_num); + *pos += scnprintf(buf + *pos, len - *pos, "RSS ind tbl size: %u\n", + dev_specs->rss_ind_tbl_size); + *pos += scnprintf(buf + *pos, len - *pos, "RSS key size: %u\n", + dev_specs->rss_key_size); + *pos += scnprintf(buf + *pos, len - *pos, "RSS size: %u\n", + kinfo->rss_size); + *pos += scnprintf(buf + *pos, len - *pos, "Allocated RSS size: %u\n", + kinfo->req_rss_size); + *pos += scnprintf(buf + *pos, len - *pos, + "Task queue pairs numbers: %u\n", + kinfo->num_tqps); + *pos += scnprintf(buf + *pos, len - *pos, "RX buffer length: %u\n", + kinfo->rx_buf_len); + *pos += scnprintf(buf + *pos, len - *pos, "Desc num per TX queue: %u\n", + kinfo->num_tx_desc); + *pos += scnprintf(buf + *pos, len - *pos, "Desc num per RX queue: %u\n", + kinfo->num_rx_desc); + *pos += scnprintf(buf + *pos, len - *pos, + "Total number of enabled TCs: %u\n", + kinfo->tc_info.num_tc); + *pos += scnprintf(buf + *pos, len - *pos, "MAX INT QL: %u\n", + dev_specs->int_ql_max); + *pos += scnprintf(buf + *pos, len - *pos, "MAX INT GL: %u\n", + dev_specs->max_int_gl); + *pos += scnprintf(buf + *pos, len - *pos, "MAX TM RATE: %u\n", + dev_specs->max_tm_rate); + *pos += scnprintf(buf + *pos, len - *pos, "MAX QSET number: %u\n", + dev_specs->max_qset_num); } -static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer, - size_t count, loff_t *ppos) +static int hns3_dbg_dev_info(struct hnae3_handle *h, char *buf, int len) { - int uncopy_bytes; - char *buf; - int len; + int pos = 0; - if (*ppos != 0) - return 0; + hns3_dbg_dev_caps(h, buf, len, &pos); - if (count < HNS3_DBG_READ_LEN) - return -ENOSPC; + hns3_dbg_dev_specs(h, buf, len, &pos); - buf = kzalloc(HNS3_DBG_READ_LEN, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - len = scnprintf(buf, HNS3_DBG_READ_LEN, "%s\n", - "Please echo help to cmd to get help information"); - uncopy_bytes = copy_to_user(buffer, buf, len); - - kfree(buf); - - if (uncopy_bytes) - return -EFAULT; - - return (*ppos = len); + return 0; } -static int hns3_dbg_check_cmd(struct hnae3_handle *handle, char *cmd_buf) +static int hns3_dbg_get_cmd_index(struct hnae3_handle *handle, + const unsigned char *name, u32 *index) { - int ret = 0; + u32 i; - if (strncmp(cmd_buf, "help", 4) == 0) - hns3_dbg_help(handle); - else if (strncmp(cmd_buf, "queue info", 10) == 0) - ret = hns3_dbg_queue_info(handle, cmd_buf); - else if (strncmp(cmd_buf, "queue map", 9) == 0) - ret = hns3_dbg_queue_map(handle); - else if (strncmp(cmd_buf, "bd info", 7) == 0) - ret = hns3_dbg_bd_info(handle, cmd_buf); - else if (strncmp(cmd_buf, "dev capability", 14) == 0) - hns3_dbg_dev_caps(handle); - else if (strncmp(cmd_buf, "dev spec", 8) == 0) - hns3_dbg_dev_specs(handle); - else if (handle->ae_algo->ops->dbg_run_cmd) - ret = handle->ae_algo->ops->dbg_run_cmd(handle, cmd_buf); - else - ret = -EOPNOTSUPP; - - return ret; -} - -static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer, - size_t count, loff_t *ppos) -{ - struct hnae3_handle *handle = filp->private_data; - struct hns3_nic_priv *priv = handle->priv; - char *cmd_buf, *cmd_buf_tmp; - int uncopied_bytes; - int ret; - - if (*ppos != 0) - return 0; - - /* Judge if the instance is being reset. */ - if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) || - test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) - return 0; - - if (count > HNS3_DBG_WRITE_LEN) - return -ENOSPC; - - cmd_buf = kzalloc(count + 1, GFP_KERNEL); - if (!cmd_buf) - return count; - - uncopied_bytes = copy_from_user(cmd_buf, buffer, count); - if (uncopied_bytes) { - kfree(cmd_buf); - return -EFAULT; + for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) { + if (!strncmp(name, hns3_dbg_cmd[i].name, + strlen(hns3_dbg_cmd[i].name))) { + *index = i; + return 0; + } } - cmd_buf[count] = '\0'; + dev_err(&handle->pdev->dev, "unknown command(%s)\n", name); + return -EINVAL; +} - cmd_buf_tmp = strchr(cmd_buf, '\n'); - if (cmd_buf_tmp) { - *cmd_buf_tmp = '\0'; - count = cmd_buf_tmp - cmd_buf + 1; +static const struct hns3_dbg_func hns3_dbg_cmd_func[] = { + { + .cmd = HNAE3_DBG_CMD_QUEUE_MAP, + .dbg_dump = hns3_dbg_queue_map, + }, + { + .cmd = HNAE3_DBG_CMD_DEV_INFO, + .dbg_dump = hns3_dbg_dev_info, + }, + { + .cmd = HNAE3_DBG_CMD_TX_BD, + .dbg_dump_bd = hns3_dbg_tx_bd_info, + }, + { + .cmd = HNAE3_DBG_CMD_RX_BD, + .dbg_dump_bd = hns3_dbg_rx_bd_info, + }, + { + .cmd = HNAE3_DBG_CMD_RX_QUEUE_INFO, + .dbg_dump = hns3_dbg_rx_queue_info, + }, + { + .cmd = HNAE3_DBG_CMD_TX_QUEUE_INFO, + .dbg_dump = hns3_dbg_tx_queue_info, + }, +}; + +static int hns3_dbg_read_cmd(struct hns3_dbg_data *dbg_data, + enum hnae3_dbg_cmd cmd, char *buf, int len) +{ + const struct hnae3_ae_ops *ops = dbg_data->handle->ae_algo->ops; + const struct hns3_dbg_func *cmd_func; + u32 i; + + for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd_func); i++) { + if (cmd == hns3_dbg_cmd_func[i].cmd) { + cmd_func = &hns3_dbg_cmd_func[i]; + if (cmd_func->dbg_dump) + return cmd_func->dbg_dump(dbg_data->handle, buf, + len); + else + return cmd_func->dbg_dump_bd(dbg_data, buf, + len); + } } - ret = hns3_dbg_check_cmd(handle, cmd_buf); - if (ret) - hns3_dbg_help(handle); + if (!ops->dbg_read_cmd) + return -EOPNOTSUPP; - kfree(cmd_buf); - cmd_buf = NULL; - - return count; + return ops->dbg_read_cmd(dbg_data->handle, cmd, buf, len); } static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { - struct hnae3_handle *handle = filp->private_data; - const struct hnae3_ae_ops *ops = handle->ae_algo->ops; + struct hns3_dbg_data *dbg_data = filp->private_data; + struct hnae3_handle *handle = dbg_data->handle; struct hns3_nic_priv *priv = handle->priv; - char *cmd_buf, *read_buf; ssize_t size = 0; - int ret = 0; + char **save_buf; + char *read_buf; + u32 index; + int ret; - read_buf = kzalloc(HNS3_DBG_READ_LEN, GFP_KERNEL); - if (!read_buf) - return -ENOMEM; + ret = hns3_dbg_get_cmd_index(handle, filp->f_path.dentry->d_iname, + &index); + if (ret) + return ret; - cmd_buf = filp->f_path.dentry->d_iname; + save_buf = &hns3_dbg_cmd[index].buf; - if (ops->dbg_read_cmd) - ret = ops->dbg_read_cmd(handle, cmd_buf, read_buf, - HNS3_DBG_READ_LEN); - - if (ret) { - dev_info(priv->dev, "unknown command\n"); + if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) || + test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) { + ret = -EBUSY; goto out; } + if (*save_buf) { + read_buf = *save_buf; + } else { + read_buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL); + if (!read_buf) + return -ENOMEM; + + /* save the buffer addr until the last read operation */ + *save_buf = read_buf; + } + + /* get data ready for the first time to read */ + if (!*ppos) { + ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd, + read_buf, hns3_dbg_cmd[index].buf_len); + if (ret) + goto out; + } + size = simple_read_from_buffer(buffer, count, ppos, read_buf, strlen(read_buf)); + if (size > 0) + return size; out: - kfree(read_buf); - return size; -} + /* free the buffer for the last read operation */ + if (*save_buf) { + kvfree(*save_buf); + *save_buf = NULL; + } -static const struct file_operations hns3_dbg_cmd_fops = { - .owner = THIS_MODULE, - .open = simple_open, - .read = hns3_dbg_cmd_read, - .write = hns3_dbg_cmd_write, -}; + return ret; +} static const struct file_operations hns3_dbg_fops = { .owner = THIS_MODULE, @@ -546,29 +1072,108 @@ static const struct file_operations hns3_dbg_fops = { .read = hns3_dbg_read, }; -void hns3_dbg_init(struct hnae3_handle *handle) +static int hns3_dbg_bd_file_init(struct hnae3_handle *handle, u32 cmd) +{ + struct dentry *entry_dir; + struct hns3_dbg_data *data; + u16 max_queue_num; + unsigned int i; + + entry_dir = hns3_dbg_dentry[hns3_dbg_cmd[cmd].dentry].dentry; + max_queue_num = hns3_get_max_available_channels(handle); + data = devm_kzalloc(&handle->pdev->dev, max_queue_num * sizeof(*data), + GFP_KERNEL); + if (!data) + return -ENOMEM; + + for (i = 0; i < max_queue_num; i++) { + char name[HNS3_DBG_FILE_NAME_LEN]; + + data[i].handle = handle; + data[i].qid = i; + sprintf(name, "%s%u", hns3_dbg_cmd[cmd].name, i); + debugfs_create_file(name, 0400, entry_dir, &data[i], + &hns3_dbg_fops); + } + + return 0; +} + +static int +hns3_dbg_common_file_init(struct hnae3_handle *handle, u32 cmd) +{ + struct hns3_dbg_data *data; + struct dentry *entry_dir; + + data = devm_kzalloc(&handle->pdev->dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->handle = handle; + entry_dir = hns3_dbg_dentry[hns3_dbg_cmd[cmd].dentry].dentry; + debugfs_create_file(hns3_dbg_cmd[cmd].name, 0400, entry_dir, + data, &hns3_dbg_fops); + + return 0; +} + +int hns3_dbg_init(struct hnae3_handle *handle) { struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev); const char *name = pci_name(handle->pdev); - struct dentry *entry_dir; + int ret; + u32 i; - handle->hnae3_dbgfs = debugfs_create_dir(name, hns3_dbgfs_root); + hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry = + debugfs_create_dir(name, hns3_dbgfs_root); + handle->hnae3_dbgfs = hns3_dbg_dentry[HNS3_DBG_DENTRY_COMMON].dentry; - debugfs_create_file("cmd", 0600, handle->hnae3_dbgfs, handle, - &hns3_dbg_cmd_fops); + for (i = 0; i < HNS3_DBG_DENTRY_COMMON; i++) + hns3_dbg_dentry[i].dentry = + debugfs_create_dir(hns3_dbg_dentry[i].name, + handle->hnae3_dbgfs); - entry_dir = debugfs_create_dir("tm", handle->hnae3_dbgfs); - if (ae_dev->dev_version > HNAE3_DEVICE_VERSION_V2) - debugfs_create_file(HNAE3_DBG_TM_NODES, 0600, entry_dir, handle, - &hns3_dbg_fops); - debugfs_create_file(HNAE3_DBG_TM_PRI, 0600, entry_dir, handle, - &hns3_dbg_fops); - debugfs_create_file(HNAE3_DBG_TM_QSET, 0600, entry_dir, handle, - &hns3_dbg_fops); + for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) { + if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES && + ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) || + (hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_PTP_INFO && + !test_bit(HNAE3_DEV_SUPPORT_PTP_B, ae_dev->caps))) + continue; + + if (!hns3_dbg_cmd[i].init) { + dev_err(&handle->pdev->dev, + "cmd %s lack of init func\n", + hns3_dbg_cmd[i].name); + ret = -EINVAL; + goto out; + } + + ret = hns3_dbg_cmd[i].init(handle, i); + if (ret) { + dev_err(&handle->pdev->dev, "failed to init cmd %s\n", + hns3_dbg_cmd[i].name); + goto out; + } + } + + return 0; + +out: + debugfs_remove_recursive(handle->hnae3_dbgfs); + handle->hnae3_dbgfs = NULL; + return ret; } void hns3_dbg_uninit(struct hnae3_handle *handle) { + u32 i; + + for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) + if (hns3_dbg_cmd[i].buf) { + kvfree(hns3_dbg_cmd[i].buf); + hns3_dbg_cmd[i].buf = NULL; + } + debugfs_remove_recursive(handle->hnae3_dbgfs); handle->hnae3_dbgfs = NULL; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h new file mode 100644 index 000000000000..f3766ff38bb7 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2021 Hisilicon Limited. */ + +#ifndef __HNS3_DEBUGFS_H +#define __HNS3_DEBUGFS_H + +#define HNS3_DBG_READ_LEN 65536 +#define HNS3_DBG_READ_LEN_128KB 0x20000 +#define HNS3_DBG_READ_LEN_1MB 0x100000 +#define HNS3_DBG_READ_LEN_4MB 0x400000 +#define HNS3_DBG_WRITE_LEN 1024 + +#define HNS3_DBG_DATA_STR_LEN 32 +#define HNS3_DBG_INFO_LEN 256 +#define HNS3_DBG_ITEM_NAME_LEN 32 +#define HNS3_DBG_FILE_NAME_LEN 16 + +struct hns3_dbg_item { + char name[HNS3_DBG_ITEM_NAME_LEN]; + u16 interval; /* blank numbers after the item */ +}; + +struct hns3_dbg_data { + struct hnae3_handle *handle; + u16 qid; +}; + +enum hns3_dbg_dentry_type { + HNS3_DBG_DENTRY_TM, + HNS3_DBG_DENTRY_TX_BD, + HNS3_DBG_DENTRY_RX_BD, + HNS3_DBG_DENTRY_MAC, + HNS3_DBG_DENTRY_REG, + HNS3_DBG_DENTRY_QUEUE, + HNS3_DBG_DENTRY_FD, + HNS3_DBG_DENTRY_COMMON, +}; + +struct hns3_dbg_dentry_info { + const char *name; + struct dentry *dentry; +}; + +struct hns3_dbg_cmd_info { + const char *name; + enum hnae3_dbg_cmd cmd; + enum hns3_dbg_dentry_type dentry; + u32 buf_len; + char *buf; + int (*init)(struct hnae3_handle *handle, unsigned int cmd); +}; + +struct hns3_dbg_func { + enum hnae3_dbg_cmd cmd; + int (*dbg_dump)(struct hnae3_handle *handle, char *buf, int len); + int (*dbg_dump_bd)(struct hns3_dbg_data *data, char *buf, int len); +}; + +struct hns3_dbg_cap_info { + const char *name; + enum HNAE3_DEV_CAP_BITS cap_bit; +}; + +#endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 026558f8e04b..cdb5f14fb6bc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -53,6 +53,19 @@ static int debug = -1; module_param(debug, int, 0); MODULE_PARM_DESC(debug, " Network interface message level setting"); +static unsigned int tx_spare_buf_size; +module_param(tx_spare_buf_size, uint, 0400); +MODULE_PARM_DESC(tx_spare_buf_size, "Size used to allocate tx spare buffer"); + +static unsigned int tx_sgl = 1; +module_param(tx_sgl, uint, 0600); +MODULE_PARM_DESC(tx_sgl, "Minimum number of frags when using dma_map_sg() to optimize the IOMMU mapping"); + +#define HNS3_SGL_SIZE(nfrag) (sizeof(struct scatterlist) * (nfrag) + \ + sizeof(struct sg_table)) +#define HNS3_MAX_SGL_SIZE ALIGN(HNS3_SGL_SIZE(HNS3_MAX_TSO_BD_NUM),\ + dma_get_cache_alignment()) + #define DEFAULT_MSG_LEVEL (NETIF_MSG_PROBE | NETIF_MSG_LINK | \ NETIF_MSG_IFDOWN | NETIF_MSG_IFUP) @@ -91,11 +104,284 @@ static const struct pci_device_id hns3_pci_tbl[] = { }; MODULE_DEVICE_TABLE(pci, hns3_pci_tbl); +#define HNS3_RX_PTYPE_ENTRY(ptype, l, s, t) \ + { ptype, \ + l, \ + CHECKSUM_##s, \ + HNS3_L3_TYPE_##t, \ + 1 } + +#define HNS3_RX_PTYPE_UNUSED_ENTRY(ptype) \ + { ptype, 0, CHECKSUM_NONE, HNS3_L3_TYPE_PARSE_FAIL, 0 } + +static const struct hns3_rx_ptype hns3_rx_ptype_tbl[] = { + HNS3_RX_PTYPE_UNUSED_ENTRY(0), + HNS3_RX_PTYPE_ENTRY(1, 0, COMPLETE, ARP), + HNS3_RX_PTYPE_ENTRY(2, 0, COMPLETE, RARP), + HNS3_RX_PTYPE_ENTRY(3, 0, COMPLETE, LLDP), + HNS3_RX_PTYPE_ENTRY(4, 0, COMPLETE, PARSE_FAIL), + HNS3_RX_PTYPE_ENTRY(5, 0, COMPLETE, PARSE_FAIL), + HNS3_RX_PTYPE_ENTRY(6, 0, COMPLETE, PARSE_FAIL), + HNS3_RX_PTYPE_ENTRY(7, 0, COMPLETE, CNM), + HNS3_RX_PTYPE_ENTRY(8, 0, NONE, PARSE_FAIL), + HNS3_RX_PTYPE_UNUSED_ENTRY(9), + HNS3_RX_PTYPE_UNUSED_ENTRY(10), + HNS3_RX_PTYPE_UNUSED_ENTRY(11), + HNS3_RX_PTYPE_UNUSED_ENTRY(12), + HNS3_RX_PTYPE_UNUSED_ENTRY(13), + HNS3_RX_PTYPE_UNUSED_ENTRY(14), + HNS3_RX_PTYPE_UNUSED_ENTRY(15), + HNS3_RX_PTYPE_ENTRY(16, 0, COMPLETE, PARSE_FAIL), + HNS3_RX_PTYPE_ENTRY(17, 0, COMPLETE, IPV4), + HNS3_RX_PTYPE_ENTRY(18, 0, COMPLETE, IPV4), + HNS3_RX_PTYPE_ENTRY(19, 0, UNNECESSARY, IPV4), + HNS3_RX_PTYPE_ENTRY(20, 0, UNNECESSARY, IPV4), + HNS3_RX_PTYPE_ENTRY(21, 0, NONE, IPV4), + HNS3_RX_PTYPE_ENTRY(22, 0, UNNECESSARY, IPV4), + HNS3_RX_PTYPE_ENTRY(23, 0, NONE, IPV4), + HNS3_RX_PTYPE_ENTRY(24, 0, NONE, IPV4), + HNS3_RX_PTYPE_ENTRY(25, 0, UNNECESSARY, IPV4), + HNS3_RX_PTYPE_UNUSED_ENTRY(26), + HNS3_RX_PTYPE_UNUSED_ENTRY(27), + HNS3_RX_PTYPE_UNUSED_ENTRY(28), + HNS3_RX_PTYPE_ENTRY(29, 0, COMPLETE, PARSE_FAIL), + HNS3_RX_PTYPE_ENTRY(30, 0, COMPLETE, PARSE_FAIL), + HNS3_RX_PTYPE_ENTRY(31, 0, COMPLETE, IPV4), + HNS3_RX_PTYPE_ENTRY(32, 0, COMPLETE, IPV4), + HNS3_RX_PTYPE_ENTRY(33, 1, UNNECESSARY, IPV4), + HNS3_RX_PTYPE_ENTRY(34, 1, UNNECESSARY, IPV4), + HNS3_RX_PTYPE_ENTRY(35, 1, UNNECESSARY, IPV4), + HNS3_RX_PTYPE_ENTRY(36, 0, COMPLETE, IPV4), + HNS3_RX_PTYPE_ENTRY(37, 0, COMPLETE, IPV4), + HNS3_RX_PTYPE_UNUSED_ENTRY(38), + HNS3_RX_PTYPE_ENTRY(39, 0, COMPLETE, IPV6), + HNS3_RX_PTYPE_ENTRY(40, 0, COMPLETE, IPV6), + HNS3_RX_PTYPE_ENTRY(41, 1, UNNECESSARY, IPV6), + HNS3_RX_PTYPE_ENTRY(42, 1, UNNECESSARY, IPV6), + HNS3_RX_PTYPE_ENTRY(43, 1, UNNECESSARY, IPV6), + HNS3_RX_PTYPE_ENTRY(44, 0, COMPLETE, IPV6), + HNS3_RX_PTYPE_ENTRY(45, 0, COMPLETE, IPV6), + HNS3_RX_PTYPE_UNUSED_ENTRY(46), + HNS3_RX_PTYPE_UNUSED_ENTRY(47), + HNS3_RX_PTYPE_UNUSED_ENTRY(48), + HNS3_RX_PTYPE_UNUSED_ENTRY(49), + HNS3_RX_PTYPE_UNUSED_ENTRY(50), + HNS3_RX_PTYPE_UNUSED_ENTRY(51), + HNS3_RX_PTYPE_UNUSED_ENTRY(52), + HNS3_RX_PTYPE_UNUSED_ENTRY(53), + HNS3_RX_PTYPE_UNUSED_ENTRY(54), + HNS3_RX_PTYPE_UNUSED_ENTRY(55), + HNS3_RX_PTYPE_UNUSED_ENTRY(56), + HNS3_RX_PTYPE_UNUSED_ENTRY(57), + HNS3_RX_PTYPE_UNUSED_ENTRY(58), + HNS3_RX_PTYPE_UNUSED_ENTRY(59), + HNS3_RX_PTYPE_UNUSED_ENTRY(60), + HNS3_RX_PTYPE_UNUSED_ENTRY(61), + HNS3_RX_PTYPE_UNUSED_ENTRY(62), + HNS3_RX_PTYPE_UNUSED_ENTRY(63), + HNS3_RX_PTYPE_UNUSED_ENTRY(64), + HNS3_RX_PTYPE_UNUSED_ENTRY(65), + HNS3_RX_PTYPE_UNUSED_ENTRY(66), + HNS3_RX_PTYPE_UNUSED_ENTRY(67), + HNS3_RX_PTYPE_UNUSED_ENTRY(68), + HNS3_RX_PTYPE_UNUSED_ENTRY(69), + HNS3_RX_PTYPE_UNUSED_ENTRY(70), + HNS3_RX_PTYPE_UNUSED_ENTRY(71), + HNS3_RX_PTYPE_UNUSED_ENTRY(72), + HNS3_RX_PTYPE_UNUSED_ENTRY(73), + HNS3_RX_PTYPE_UNUSED_ENTRY(74), + HNS3_RX_PTYPE_UNUSED_ENTRY(75), + HNS3_RX_PTYPE_UNUSED_ENTRY(76), + HNS3_RX_PTYPE_UNUSED_ENTRY(77), + HNS3_RX_PTYPE_UNUSED_ENTRY(78), + HNS3_RX_PTYPE_UNUSED_ENTRY(79), + HNS3_RX_PTYPE_UNUSED_ENTRY(80), + HNS3_RX_PTYPE_UNUSED_ENTRY(81), + HNS3_RX_PTYPE_UNUSED_ENTRY(82), + HNS3_RX_PTYPE_UNUSED_ENTRY(83), + HNS3_RX_PTYPE_UNUSED_ENTRY(84), + HNS3_RX_PTYPE_UNUSED_ENTRY(85), + HNS3_RX_PTYPE_UNUSED_ENTRY(86), + HNS3_RX_PTYPE_UNUSED_ENTRY(87), + HNS3_RX_PTYPE_UNUSED_ENTRY(88), + HNS3_RX_PTYPE_UNUSED_ENTRY(89), + HNS3_RX_PTYPE_UNUSED_ENTRY(90), + HNS3_RX_PTYPE_UNUSED_ENTRY(91), + HNS3_RX_PTYPE_UNUSED_ENTRY(92), + HNS3_RX_PTYPE_UNUSED_ENTRY(93), + HNS3_RX_PTYPE_UNUSED_ENTRY(94), + HNS3_RX_PTYPE_UNUSED_ENTRY(95), + HNS3_RX_PTYPE_UNUSED_ENTRY(96), + HNS3_RX_PTYPE_UNUSED_ENTRY(97), + HNS3_RX_PTYPE_UNUSED_ENTRY(98), + HNS3_RX_PTYPE_UNUSED_ENTRY(99), + HNS3_RX_PTYPE_UNUSED_ENTRY(100), + HNS3_RX_PTYPE_UNUSED_ENTRY(101), + HNS3_RX_PTYPE_UNUSED_ENTRY(102), + HNS3_RX_PTYPE_UNUSED_ENTRY(103), + HNS3_RX_PTYPE_UNUSED_ENTRY(104), + HNS3_RX_PTYPE_UNUSED_ENTRY(105), + HNS3_RX_PTYPE_UNUSED_ENTRY(106), + HNS3_RX_PTYPE_UNUSED_ENTRY(107), + HNS3_RX_PTYPE_UNUSED_ENTRY(108), + HNS3_RX_PTYPE_UNUSED_ENTRY(109), + HNS3_RX_PTYPE_UNUSED_ENTRY(110), + HNS3_RX_PTYPE_ENTRY(111, 0, COMPLETE, IPV6), + HNS3_RX_PTYPE_ENTRY(112, 0, COMPLETE, IPV6), + HNS3_RX_PTYPE_ENTRY(113, 0, UNNECESSARY, IPV6), + HNS3_RX_PTYPE_ENTRY(114, 0, UNNECESSARY, IPV6), + HNS3_RX_PTYPE_ENTRY(115, 0, NONE, IPV6), + HNS3_RX_PTYPE_ENTRY(116, 0, UNNECESSARY, IPV6), + HNS3_RX_PTYPE_ENTRY(117, 0, NONE, IPV6), + HNS3_RX_PTYPE_ENTRY(118, 0, NONE, IPV6), + HNS3_RX_PTYPE_ENTRY(119, 0, UNNECESSARY, IPV6), + HNS3_RX_PTYPE_UNUSED_ENTRY(120), + HNS3_RX_PTYPE_UNUSED_ENTRY(121), + HNS3_RX_PTYPE_UNUSED_ENTRY(122), + HNS3_RX_PTYPE_ENTRY(123, 0, COMPLETE, PARSE_FAIL), + HNS3_RX_PTYPE_ENTRY(124, 0, COMPLETE, PARSE_FAIL), + HNS3_RX_PTYPE_ENTRY(125, 0, COMPLETE, IPV4), + HNS3_RX_PTYPE_ENTRY(126, 0, COMPLETE, IPV4), + HNS3_RX_PTYPE_ENTRY(127, 1, UNNECESSARY, IPV4), + HNS3_RX_PTYPE_ENTRY(128, 1, UNNECESSARY, IPV4), + HNS3_RX_PTYPE_ENTRY(129, 1, UNNECESSARY, IPV4), + HNS3_RX_PTYPE_ENTRY(130, 0, COMPLETE, IPV4), + HNS3_RX_PTYPE_ENTRY(131, 0, COMPLETE, IPV4), + HNS3_RX_PTYPE_UNUSED_ENTRY(132), + HNS3_RX_PTYPE_ENTRY(133, 0, COMPLETE, IPV6), + HNS3_RX_PTYPE_ENTRY(134, 0, COMPLETE, IPV6), + HNS3_RX_PTYPE_ENTRY(135, 1, UNNECESSARY, IPV6), + HNS3_RX_PTYPE_ENTRY(136, 1, UNNECESSARY, IPV6), + HNS3_RX_PTYPE_ENTRY(137, 1, UNNECESSARY, IPV6), + HNS3_RX_PTYPE_ENTRY(138, 0, COMPLETE, IPV6), + HNS3_RX_PTYPE_ENTRY(139, 0, COMPLETE, IPV6), + HNS3_RX_PTYPE_UNUSED_ENTRY(140), + HNS3_RX_PTYPE_UNUSED_ENTRY(141), + HNS3_RX_PTYPE_UNUSED_ENTRY(142), + HNS3_RX_PTYPE_UNUSED_ENTRY(143), + HNS3_RX_PTYPE_UNUSED_ENTRY(144), + HNS3_RX_PTYPE_UNUSED_ENTRY(145), + HNS3_RX_PTYPE_UNUSED_ENTRY(146), + HNS3_RX_PTYPE_UNUSED_ENTRY(147), + HNS3_RX_PTYPE_UNUSED_ENTRY(148), + HNS3_RX_PTYPE_UNUSED_ENTRY(149), + HNS3_RX_PTYPE_UNUSED_ENTRY(150), + HNS3_RX_PTYPE_UNUSED_ENTRY(151), + HNS3_RX_PTYPE_UNUSED_ENTRY(152), + HNS3_RX_PTYPE_UNUSED_ENTRY(153), + HNS3_RX_PTYPE_UNUSED_ENTRY(154), + HNS3_RX_PTYPE_UNUSED_ENTRY(155), + HNS3_RX_PTYPE_UNUSED_ENTRY(156), + HNS3_RX_PTYPE_UNUSED_ENTRY(157), + HNS3_RX_PTYPE_UNUSED_ENTRY(158), + HNS3_RX_PTYPE_UNUSED_ENTRY(159), + HNS3_RX_PTYPE_UNUSED_ENTRY(160), + HNS3_RX_PTYPE_UNUSED_ENTRY(161), + HNS3_RX_PTYPE_UNUSED_ENTRY(162), + HNS3_RX_PTYPE_UNUSED_ENTRY(163), + HNS3_RX_PTYPE_UNUSED_ENTRY(164), + HNS3_RX_PTYPE_UNUSED_ENTRY(165), + HNS3_RX_PTYPE_UNUSED_ENTRY(166), + HNS3_RX_PTYPE_UNUSED_ENTRY(167), + HNS3_RX_PTYPE_UNUSED_ENTRY(168), + HNS3_RX_PTYPE_UNUSED_ENTRY(169), + HNS3_RX_PTYPE_UNUSED_ENTRY(170), + HNS3_RX_PTYPE_UNUSED_ENTRY(171), + HNS3_RX_PTYPE_UNUSED_ENTRY(172), + HNS3_RX_PTYPE_UNUSED_ENTRY(173), + HNS3_RX_PTYPE_UNUSED_ENTRY(174), + HNS3_RX_PTYPE_UNUSED_ENTRY(175), + HNS3_RX_PTYPE_UNUSED_ENTRY(176), + HNS3_RX_PTYPE_UNUSED_ENTRY(177), + HNS3_RX_PTYPE_UNUSED_ENTRY(178), + HNS3_RX_PTYPE_UNUSED_ENTRY(179), + HNS3_RX_PTYPE_UNUSED_ENTRY(180), + HNS3_RX_PTYPE_UNUSED_ENTRY(181), + HNS3_RX_PTYPE_UNUSED_ENTRY(182), + HNS3_RX_PTYPE_UNUSED_ENTRY(183), + HNS3_RX_PTYPE_UNUSED_ENTRY(184), + HNS3_RX_PTYPE_UNUSED_ENTRY(185), + HNS3_RX_PTYPE_UNUSED_ENTRY(186), + HNS3_RX_PTYPE_UNUSED_ENTRY(187), + HNS3_RX_PTYPE_UNUSED_ENTRY(188), + HNS3_RX_PTYPE_UNUSED_ENTRY(189), + HNS3_RX_PTYPE_UNUSED_ENTRY(190), + HNS3_RX_PTYPE_UNUSED_ENTRY(191), + HNS3_RX_PTYPE_UNUSED_ENTRY(192), + HNS3_RX_PTYPE_UNUSED_ENTRY(193), + HNS3_RX_PTYPE_UNUSED_ENTRY(194), + HNS3_RX_PTYPE_UNUSED_ENTRY(195), + HNS3_RX_PTYPE_UNUSED_ENTRY(196), + HNS3_RX_PTYPE_UNUSED_ENTRY(197), + HNS3_RX_PTYPE_UNUSED_ENTRY(198), + HNS3_RX_PTYPE_UNUSED_ENTRY(199), + HNS3_RX_PTYPE_UNUSED_ENTRY(200), + HNS3_RX_PTYPE_UNUSED_ENTRY(201), + HNS3_RX_PTYPE_UNUSED_ENTRY(202), + HNS3_RX_PTYPE_UNUSED_ENTRY(203), + HNS3_RX_PTYPE_UNUSED_ENTRY(204), + HNS3_RX_PTYPE_UNUSED_ENTRY(205), + HNS3_RX_PTYPE_UNUSED_ENTRY(206), + HNS3_RX_PTYPE_UNUSED_ENTRY(207), + HNS3_RX_PTYPE_UNUSED_ENTRY(208), + HNS3_RX_PTYPE_UNUSED_ENTRY(209), + HNS3_RX_PTYPE_UNUSED_ENTRY(210), + HNS3_RX_PTYPE_UNUSED_ENTRY(211), + HNS3_RX_PTYPE_UNUSED_ENTRY(212), + HNS3_RX_PTYPE_UNUSED_ENTRY(213), + HNS3_RX_PTYPE_UNUSED_ENTRY(214), + HNS3_RX_PTYPE_UNUSED_ENTRY(215), + HNS3_RX_PTYPE_UNUSED_ENTRY(216), + HNS3_RX_PTYPE_UNUSED_ENTRY(217), + HNS3_RX_PTYPE_UNUSED_ENTRY(218), + HNS3_RX_PTYPE_UNUSED_ENTRY(219), + HNS3_RX_PTYPE_UNUSED_ENTRY(220), + HNS3_RX_PTYPE_UNUSED_ENTRY(221), + HNS3_RX_PTYPE_UNUSED_ENTRY(222), + HNS3_RX_PTYPE_UNUSED_ENTRY(223), + HNS3_RX_PTYPE_UNUSED_ENTRY(224), + HNS3_RX_PTYPE_UNUSED_ENTRY(225), + HNS3_RX_PTYPE_UNUSED_ENTRY(226), + HNS3_RX_PTYPE_UNUSED_ENTRY(227), + HNS3_RX_PTYPE_UNUSED_ENTRY(228), + HNS3_RX_PTYPE_UNUSED_ENTRY(229), + HNS3_RX_PTYPE_UNUSED_ENTRY(230), + HNS3_RX_PTYPE_UNUSED_ENTRY(231), + HNS3_RX_PTYPE_UNUSED_ENTRY(232), + HNS3_RX_PTYPE_UNUSED_ENTRY(233), + HNS3_RX_PTYPE_UNUSED_ENTRY(234), + HNS3_RX_PTYPE_UNUSED_ENTRY(235), + HNS3_RX_PTYPE_UNUSED_ENTRY(236), + HNS3_RX_PTYPE_UNUSED_ENTRY(237), + HNS3_RX_PTYPE_UNUSED_ENTRY(238), + HNS3_RX_PTYPE_UNUSED_ENTRY(239), + HNS3_RX_PTYPE_UNUSED_ENTRY(240), + HNS3_RX_PTYPE_UNUSED_ENTRY(241), + HNS3_RX_PTYPE_UNUSED_ENTRY(242), + HNS3_RX_PTYPE_UNUSED_ENTRY(243), + HNS3_RX_PTYPE_UNUSED_ENTRY(244), + HNS3_RX_PTYPE_UNUSED_ENTRY(245), + HNS3_RX_PTYPE_UNUSED_ENTRY(246), + HNS3_RX_PTYPE_UNUSED_ENTRY(247), + HNS3_RX_PTYPE_UNUSED_ENTRY(248), + HNS3_RX_PTYPE_UNUSED_ENTRY(249), + HNS3_RX_PTYPE_UNUSED_ENTRY(250), + HNS3_RX_PTYPE_UNUSED_ENTRY(251), + HNS3_RX_PTYPE_UNUSED_ENTRY(252), + HNS3_RX_PTYPE_UNUSED_ENTRY(253), + HNS3_RX_PTYPE_UNUSED_ENTRY(254), + HNS3_RX_PTYPE_UNUSED_ENTRY(255), +}; + +#define HNS3_INVALID_PTYPE \ + ARRAY_SIZE(hns3_rx_ptype_tbl) + static irqreturn_t hns3_irq_handle(int irq, void *vector) { struct hns3_enet_tqp_vector *tqp_vector = vector; napi_schedule_irqoff(&tqp_vector->napi); + tqp_vector->event_cnt++; return IRQ_HANDLED; } @@ -199,6 +485,8 @@ static void hns3_vector_disable(struct hns3_enet_tqp_vector *tqp_vector) disable_irq(tqp_vector->vector_irq); napi_disable(&tqp_vector->napi); + cancel_work_sync(&tqp_vector->rx_group.dim.work); + cancel_work_sync(&tqp_vector->tx_group.dim.work); } void hns3_set_vector_coalesce_rl(struct hns3_enet_tqp_vector *tqp_vector, @@ -357,7 +645,7 @@ static int hns3_nic_set_real_num_queue(struct net_device *netdev) return 0; } -static u16 hns3_get_max_available_channels(struct hnae3_handle *h) +u16 hns3_get_max_available_channels(struct hnae3_handle *h) { u16 alloc_tqps, max_rss_size, rss_size; @@ -633,13 +921,10 @@ static u8 hns3_get_netdev_flags(struct net_device *netdev) { u8 flags = 0; - if (netdev->flags & IFF_PROMISC) { + if (netdev->flags & IFF_PROMISC) flags = HNAE3_USER_UPE | HNAE3_USER_MPE | HNAE3_BPE; - } else { - flags |= HNAE3_VLAN_FLTR; - if (netdev->flags & IFF_ALLMULTI) - flags |= HNAE3_USER_MPE; - } + else if (netdev->flags & IFF_ALLMULTI) + flags = HNAE3_USER_MPE; return flags; } @@ -669,23 +954,202 @@ void hns3_request_update_promisc_mode(struct hnae3_handle *handle) ops->request_update_promisc_mode(handle); } -void hns3_enable_vlan_filter(struct net_device *netdev, bool enable) +static u32 hns3_tx_spare_space(struct hns3_enet_ring *ring) { - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hnae3_handle *h = priv->ae_handle; - struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev); - bool last_state; + struct hns3_tx_spare *tx_spare = ring->tx_spare; + u32 ntc, ntu; - if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2 && - h->ae_algo->ops->enable_vlan_filter) { - last_state = h->netdev_flags & HNAE3_VLAN_FLTR ? true : false; - if (enable != last_state) { - netdev_info(netdev, - "%s vlan filter\n", - enable ? "enable" : "disable"); - h->ae_algo->ops->enable_vlan_filter(h, enable); + /* This smp_load_acquire() pairs with smp_store_release() in + * hns3_tx_spare_update() called in tx desc cleaning process. + */ + ntc = smp_load_acquire(&tx_spare->last_to_clean); + ntu = tx_spare->next_to_use; + + if (ntc > ntu) + return ntc - ntu - 1; + + /* The free tx buffer is divided into two part, so pick the + * larger one. + */ + return (ntc > (tx_spare->len - ntu) ? ntc : + (tx_spare->len - ntu)) - 1; +} + +static void hns3_tx_spare_update(struct hns3_enet_ring *ring) +{ + struct hns3_tx_spare *tx_spare = ring->tx_spare; + + if (!tx_spare || + tx_spare->last_to_clean == tx_spare->next_to_clean) + return; + + /* This smp_store_release() pairs with smp_load_acquire() in + * hns3_tx_spare_space() called in xmit process. + */ + smp_store_release(&tx_spare->last_to_clean, + tx_spare->next_to_clean); +} + +static bool hns3_can_use_tx_bounce(struct hns3_enet_ring *ring, + struct sk_buff *skb, + u32 space) +{ + u32 len = skb->len <= ring->tx_copybreak ? skb->len : + skb_headlen(skb); + + if (len > ring->tx_copybreak) + return false; + + if (ALIGN(len, dma_get_cache_alignment()) > space) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_spare_full++; + u64_stats_update_end(&ring->syncp); + return false; + } + + return true; +} + +static bool hns3_can_use_tx_sgl(struct hns3_enet_ring *ring, + struct sk_buff *skb, + u32 space) +{ + if (skb->len <= ring->tx_copybreak || !tx_sgl || + (!skb_has_frag_list(skb) && + skb_shinfo(skb)->nr_frags < tx_sgl)) + return false; + + if (space < HNS3_MAX_SGL_SIZE) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_spare_full++; + u64_stats_update_end(&ring->syncp); + return false; + } + + return true; +} + +static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring) +{ + struct hns3_tx_spare *tx_spare; + struct page *page; + u32 alloc_size; + dma_addr_t dma; + int order; + + alloc_size = tx_spare_buf_size ? tx_spare_buf_size : + ring->tqp->handle->kinfo.tx_spare_buf_size; + if (!alloc_size) + return; + + order = get_order(alloc_size); + tx_spare = devm_kzalloc(ring_to_dev(ring), sizeof(*tx_spare), + GFP_KERNEL); + if (!tx_spare) { + /* The driver still work without the tx spare buffer */ + dev_warn(ring_to_dev(ring), "failed to allocate hns3_tx_spare\n"); + return; + } + + page = alloc_pages_node(dev_to_node(ring_to_dev(ring)), + GFP_KERNEL, order); + if (!page) { + dev_warn(ring_to_dev(ring), "failed to allocate tx spare pages\n"); + devm_kfree(ring_to_dev(ring), tx_spare); + return; + } + + dma = dma_map_page(ring_to_dev(ring), page, 0, + PAGE_SIZE << order, DMA_TO_DEVICE); + if (dma_mapping_error(ring_to_dev(ring), dma)) { + dev_warn(ring_to_dev(ring), "failed to map pages for tx spare\n"); + put_page(page); + devm_kfree(ring_to_dev(ring), tx_spare); + return; + } + + tx_spare->dma = dma; + tx_spare->buf = page_address(page); + tx_spare->len = PAGE_SIZE << order; + ring->tx_spare = tx_spare; +} + +/* Use hns3_tx_spare_space() to make sure there is enough buffer + * before calling below function to allocate tx buffer. + */ +static void *hns3_tx_spare_alloc(struct hns3_enet_ring *ring, + unsigned int size, dma_addr_t *dma, + u32 *cb_len) +{ + struct hns3_tx_spare *tx_spare = ring->tx_spare; + u32 ntu = tx_spare->next_to_use; + + size = ALIGN(size, dma_get_cache_alignment()); + *cb_len = size; + + /* Tx spare buffer wraps back here because the end of + * freed tx buffer is not enough. + */ + if (ntu + size > tx_spare->len) { + *cb_len += (tx_spare->len - ntu); + ntu = 0; + } + + tx_spare->next_to_use = ntu + size; + if (tx_spare->next_to_use == tx_spare->len) + tx_spare->next_to_use = 0; + + *dma = tx_spare->dma + ntu; + + return tx_spare->buf + ntu; +} + +static void hns3_tx_spare_rollback(struct hns3_enet_ring *ring, u32 len) +{ + struct hns3_tx_spare *tx_spare = ring->tx_spare; + + if (len > tx_spare->next_to_use) { + len -= tx_spare->next_to_use; + tx_spare->next_to_use = tx_spare->len - len; + } else { + tx_spare->next_to_use -= len; + } +} + +static void hns3_tx_spare_reclaim_cb(struct hns3_enet_ring *ring, + struct hns3_desc_cb *cb) +{ + struct hns3_tx_spare *tx_spare = ring->tx_spare; + u32 ntc = tx_spare->next_to_clean; + u32 len = cb->length; + + tx_spare->next_to_clean += len; + + if (tx_spare->next_to_clean >= tx_spare->len) { + tx_spare->next_to_clean -= tx_spare->len; + + if (tx_spare->next_to_clean) { + ntc = 0; + len = tx_spare->next_to_clean; } } + + /* This tx spare buffer is only really reclaimed after calling + * hns3_tx_spare_update(), so it is still safe to use the info in + * the tx buffer to do the dma sync or sg unmapping after + * tx_spare->next_to_clean is moved forword. + */ + if (cb->type & (DESC_TYPE_BOUNCE_HEAD | DESC_TYPE_BOUNCE_ALL)) { + dma_addr_t dma = tx_spare->dma + ntc; + + dma_sync_single_for_cpu(ring_to_dev(ring), dma, len, + DMA_TO_DEVICE); + } else { + struct sg_table *sgt = tx_spare->buf + ntc; + + dma_unmap_sg(ring_to_dev(ring), sgt->sgl, sgt->orig_nents, + DMA_TO_DEVICE); + } } static int hns3_set_tso(struct sk_buff *skb, u32 *paylen_fdop_ol4cs, @@ -1159,40 +1623,14 @@ out_hw_tx_csum: return 0; } -static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, - unsigned int size, enum hns_desc_type type) +static int hns3_fill_desc(struct hns3_enet_ring *ring, dma_addr_t dma, + unsigned int size) { #define HNS3_LIKELY_BD_NUM 1 - struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; struct hns3_desc *desc = &ring->desc[ring->next_to_use]; - struct device *dev = ring_to_dev(ring); - skb_frag_t *frag; unsigned int frag_buf_num; int k, sizeoflast; - dma_addr_t dma; - - if (type == DESC_TYPE_FRAGLIST_SKB || - type == DESC_TYPE_SKB) { - struct sk_buff *skb = (struct sk_buff *)priv; - - dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); - } else { - frag = (skb_frag_t *)priv; - dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE); - } - - if (unlikely(dma_mapping_error(dev, dma))) { - u64_stats_update_begin(&ring->syncp); - ring->stats.sw_err_cnt++; - u64_stats_update_end(&ring->syncp); - return -ENOMEM; - } - - desc_cb->priv = priv; - desc_cb->length = size; - desc_cb->dma = dma; - desc_cb->type = type; if (likely(size <= HNS3_MAX_BD_SIZE)) { desc->addr = cpu_to_le64(dma); @@ -1228,6 +1666,52 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, return frag_buf_num; } +static int hns3_map_and_fill_desc(struct hns3_enet_ring *ring, void *priv, + unsigned int type) +{ + struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; + struct device *dev = ring_to_dev(ring); + unsigned int size; + dma_addr_t dma; + + if (type & (DESC_TYPE_FRAGLIST_SKB | DESC_TYPE_SKB)) { + struct sk_buff *skb = (struct sk_buff *)priv; + + size = skb_headlen(skb); + if (!size) + return 0; + + dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); + } else if (type & DESC_TYPE_BOUNCE_HEAD) { + /* Head data has been filled in hns3_handle_tx_bounce(), + * just return 0 here. + */ + return 0; + } else { + skb_frag_t *frag = (skb_frag_t *)priv; + + size = skb_frag_size(frag); + if (!size) + return 0; + + dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE); + } + + if (unlikely(dma_mapping_error(dev, dma))) { + u64_stats_update_begin(&ring->syncp); + ring->stats.sw_err_cnt++; + u64_stats_update_end(&ring->syncp); + return -ENOMEM; + } + + desc_cb->priv = priv; + desc_cb->length = size; + desc_cb->dma = dma; + desc_cb->type = type; + + return hns3_fill_desc(ring, dma, size); +} + static unsigned int hns3_skb_bd_num(struct sk_buff *skb, unsigned int *bd_size, unsigned int bd_num) { @@ -1451,6 +1935,7 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig) for (i = 0; i < ring->desc_num; i++) { struct hns3_desc *desc = &ring->desc[ring->next_to_use]; + struct hns3_desc_cb *desc_cb; memset(desc, 0, sizeof(*desc)); @@ -1461,52 +1946,44 @@ static void hns3_clear_desc(struct hns3_enet_ring *ring, int next_to_use_orig) /* rollback one */ ring_ptr_move_bw(ring, next_to_use); - if (!ring->desc_cb[ring->next_to_use].dma) + desc_cb = &ring->desc_cb[ring->next_to_use]; + + if (!desc_cb->dma) continue; /* unmap the descriptor dma address */ - if (ring->desc_cb[ring->next_to_use].type == DESC_TYPE_SKB || - ring->desc_cb[ring->next_to_use].type == - DESC_TYPE_FRAGLIST_SKB) - dma_unmap_single(dev, - ring->desc_cb[ring->next_to_use].dma, - ring->desc_cb[ring->next_to_use].length, - DMA_TO_DEVICE); - else if (ring->desc_cb[ring->next_to_use].length) - dma_unmap_page(dev, - ring->desc_cb[ring->next_to_use].dma, - ring->desc_cb[ring->next_to_use].length, + if (desc_cb->type & (DESC_TYPE_SKB | DESC_TYPE_FRAGLIST_SKB)) + dma_unmap_single(dev, desc_cb->dma, desc_cb->length, + DMA_TO_DEVICE); + else if (desc_cb->type & + (DESC_TYPE_BOUNCE_HEAD | DESC_TYPE_BOUNCE_ALL)) + hns3_tx_spare_rollback(ring, desc_cb->length); + else if (desc_cb->length) + dma_unmap_page(dev, desc_cb->dma, desc_cb->length, DMA_TO_DEVICE); - ring->desc_cb[ring->next_to_use].length = 0; - ring->desc_cb[ring->next_to_use].dma = 0; - ring->desc_cb[ring->next_to_use].type = DESC_TYPE_UNKNOWN; + desc_cb->length = 0; + desc_cb->dma = 0; + desc_cb->type = DESC_TYPE_UNKNOWN; } } static int hns3_fill_skb_to_desc(struct hns3_enet_ring *ring, - struct sk_buff *skb, enum hns_desc_type type) + struct sk_buff *skb, unsigned int type) { - unsigned int size = skb_headlen(skb); struct sk_buff *frag_skb; int i, ret, bd_num = 0; - if (size) { - ret = hns3_fill_desc(ring, skb, size, type); - if (unlikely(ret < 0)) - return ret; + ret = hns3_map_and_fill_desc(ring, skb, type); + if (unlikely(ret < 0)) + return ret; - bd_num += ret; - } + bd_num += ret; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - size = skb_frag_size(frag); - if (!size) - continue; - - ret = hns3_fill_desc(ring, frag, size, DESC_TYPE_PAGE); + ret = hns3_map_and_fill_desc(ring, frag, DESC_TYPE_PAGE); if (unlikely(ret < 0)) return ret; @@ -1546,6 +2023,153 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num, WRITE_ONCE(ring->last_to_use, ring->next_to_use); } +static void hns3_tsyn(struct net_device *netdev, struct sk_buff *skb, + struct hns3_desc *desc) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + + if (!(h->ae_algo->ops->set_tx_hwts_info && + h->ae_algo->ops->set_tx_hwts_info(h, skb))) + return; + + desc->tx.bdtp_fe_sc_vld_ra_ri |= cpu_to_le16(BIT(HNS3_TXD_TSYN_B)); +} + +static int hns3_handle_tx_bounce(struct hns3_enet_ring *ring, + struct sk_buff *skb) +{ + struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; + unsigned int type = DESC_TYPE_BOUNCE_HEAD; + unsigned int size = skb_headlen(skb); + dma_addr_t dma; + int bd_num = 0; + u32 cb_len; + void *buf; + int ret; + + if (skb->len <= ring->tx_copybreak) { + size = skb->len; + type = DESC_TYPE_BOUNCE_ALL; + } + + /* hns3_can_use_tx_bounce() is called to ensure the below + * function can always return the tx buffer. + */ + buf = hns3_tx_spare_alloc(ring, size, &dma, &cb_len); + + ret = skb_copy_bits(skb, 0, buf, size); + if (unlikely(ret < 0)) { + hns3_tx_spare_rollback(ring, cb_len); + u64_stats_update_begin(&ring->syncp); + ring->stats.copy_bits_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } + + desc_cb->priv = skb; + desc_cb->length = cb_len; + desc_cb->dma = dma; + desc_cb->type = type; + + bd_num += hns3_fill_desc(ring, dma, size); + + if (type == DESC_TYPE_BOUNCE_HEAD) { + ret = hns3_fill_skb_to_desc(ring, skb, + DESC_TYPE_BOUNCE_HEAD); + if (unlikely(ret < 0)) + return ret; + + bd_num += ret; + } + + dma_sync_single_for_device(ring_to_dev(ring), dma, size, + DMA_TO_DEVICE); + + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_bounce++; + u64_stats_update_end(&ring->syncp); + return bd_num; +} + +static int hns3_handle_tx_sgl(struct hns3_enet_ring *ring, + struct sk_buff *skb) +{ + struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; + u32 nfrag = skb_shinfo(skb)->nr_frags + 1; + struct sg_table *sgt; + int i, bd_num = 0; + dma_addr_t dma; + u32 cb_len; + int nents; + + if (skb_has_frag_list(skb)) + nfrag = HNS3_MAX_TSO_BD_NUM; + + /* hns3_can_use_tx_sgl() is called to ensure the below + * function can always return the tx buffer. + */ + sgt = hns3_tx_spare_alloc(ring, HNS3_SGL_SIZE(nfrag), + &dma, &cb_len); + + /* scatterlist follows by the sg table */ + sgt->sgl = (struct scatterlist *)(sgt + 1); + sg_init_table(sgt->sgl, nfrag); + nents = skb_to_sgvec(skb, sgt->sgl, 0, skb->len); + if (unlikely(nents < 0)) { + hns3_tx_spare_rollback(ring, cb_len); + u64_stats_update_begin(&ring->syncp); + ring->stats.skb2sgl_err++; + u64_stats_update_end(&ring->syncp); + return -ENOMEM; + } + + sgt->orig_nents = nents; + sgt->nents = dma_map_sg(ring_to_dev(ring), sgt->sgl, sgt->orig_nents, + DMA_TO_DEVICE); + if (unlikely(!sgt->nents)) { + hns3_tx_spare_rollback(ring, cb_len); + u64_stats_update_begin(&ring->syncp); + ring->stats.map_sg_err++; + u64_stats_update_end(&ring->syncp); + return -ENOMEM; + } + + desc_cb->priv = skb; + desc_cb->length = cb_len; + desc_cb->dma = dma; + desc_cb->type = DESC_TYPE_SGL_SKB; + + for (i = 0; i < sgt->nents; i++) + bd_num += hns3_fill_desc(ring, sg_dma_address(sgt->sgl + i), + sg_dma_len(sgt->sgl + i)); + + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_sgl++; + u64_stats_update_end(&ring->syncp); + + return bd_num; +} + +static int hns3_handle_desc_filling(struct hns3_enet_ring *ring, + struct sk_buff *skb) +{ + u32 space; + + if (!ring->tx_spare) + goto out; + + space = hns3_tx_spare_space(ring); + + if (hns3_can_use_tx_sgl(ring, skb, space)) + return hns3_handle_tx_sgl(ring, skb); + + if (hns3_can_use_tx_bounce(ring, skb, space)) + return hns3_handle_tx_bounce(ring, skb); + +out: + return hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB); +} + netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) { struct hns3_nic_priv *priv = netdev_priv(netdev); @@ -1592,16 +2216,22 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) * zero, which is unlikely, and 'ret > 0' means how many tx desc * need to be notified to the hw. */ - ret = hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB); + ret = hns3_handle_desc_filling(ring, skb); if (unlikely(ret <= 0)) goto fill_err; pre_ntu = ring->next_to_use ? (ring->next_to_use - 1) : (ring->desc_num - 1); + + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) + hns3_tsyn(netdev, skb, &ring->desc[pre_ntu]); + ring->desc[pre_ntu].tx.bdtp_fe_sc_vld_ra_ri |= cpu_to_le16(BIT(HNS3_TXD_FE_B)); trace_hns3_tx_desc(ring, pre_ntu); + skb_tx_timestamp(skb); + /* Complete translate all packets */ dev_queue = netdev_get_tx_queue(netdev, ring->queue_index); doorbell = __netdev_tx_sent_queue(dev_queue, desc_cb->send_bytes, @@ -1705,6 +2335,14 @@ static int hns3_nic_set_features(struct net_device *netdev, return -EINVAL; } + if ((changed & NETIF_F_HW_VLAN_CTAG_FILTER) && + h->ae_algo->ops->enable_vlan_filter) { + enable = !!(features & NETIF_F_HW_VLAN_CTAG_FILTER); + ret = h->ae_algo->ops->enable_vlan_filter(h, enable); + if (ret) + return ret; + } + netdev->features = features; return 0; } @@ -1780,6 +2418,9 @@ static void hns3_nic_get_stats64(struct net_device *netdev, tx_drop += ring->stats.tx_tso_err; tx_drop += ring->stats.over_max_recursion; tx_drop += ring->stats.hw_limitation; + tx_drop += ring->stats.copy_bits_err; + tx_drop += ring->stats.skb2sgl_err; + tx_drop += ring->stats.map_sg_err; tx_errors += ring->stats.sw_err_cnt; tx_errors += ring->stats.tx_vlan_err; tx_errors += ring->stats.tx_l4_proto_err; @@ -1787,6 +2428,9 @@ static void hns3_nic_get_stats64(struct net_device *netdev, tx_errors += ring->stats.tx_tso_err; tx_errors += ring->stats.over_max_recursion; tx_errors += ring->stats.hw_limitation; + tx_errors += ring->stats.copy_bits_err; + tx_errors += ring->stats.skb2sgl_err; + tx_errors += ring->stats.map_sg_err; } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); /* fetch the rx stats */ @@ -2550,6 +3194,9 @@ static void hns3_set_default_feature(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_TC; netdev->features |= NETIF_F_HW_TC; } + + if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps)) + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; } static int hns3_alloc_buffer(struct hns3_enet_ring *ring, @@ -2577,7 +3224,8 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring, static void hns3_free_buffer(struct hns3_enet_ring *ring, struct hns3_desc_cb *cb, int budget) { - if (cb->type == DESC_TYPE_SKB) + if (cb->type & (DESC_TYPE_SKB | DESC_TYPE_BOUNCE_HEAD | + DESC_TYPE_BOUNCE_ALL | DESC_TYPE_SGL_SKB)) napi_consume_skb(cb->priv, budget); else if (!HNAE3_IS_TX_RING(ring) && cb->pagecnt_bias) __page_frag_cache_drain(cb->priv, cb->pagecnt_bias); @@ -2598,12 +3246,15 @@ static int hns3_map_buffer(struct hns3_enet_ring *ring, struct hns3_desc_cb *cb) static void hns3_unmap_buffer(struct hns3_enet_ring *ring, struct hns3_desc_cb *cb) { - if (cb->type == DESC_TYPE_SKB || cb->type == DESC_TYPE_FRAGLIST_SKB) + if (cb->type & (DESC_TYPE_SKB | DESC_TYPE_FRAGLIST_SKB)) dma_unmap_single(ring_to_dev(ring), cb->dma, cb->length, ring_to_dma_dir(ring)); - else if (cb->length) + else if ((cb->type & DESC_TYPE_PAGE) && cb->length) dma_unmap_page(ring_to_dev(ring), cb->dma, cb->length, ring_to_dma_dir(ring)); + else if (cb->type & (DESC_TYPE_BOUNCE_ALL | DESC_TYPE_BOUNCE_HEAD | + DESC_TYPE_SGL_SKB)) + hns3_tx_spare_reclaim_cb(ring, cb); } static void hns3_buffer_detach(struct hns3_enet_ring *ring, int i) @@ -2755,7 +3406,9 @@ static bool hns3_nic_reclaim_desc(struct hns3_enet_ring *ring, desc_cb = &ring->desc_cb[ntc]; - if (desc_cb->type == DESC_TYPE_SKB) { + if (desc_cb->type & (DESC_TYPE_SKB | DESC_TYPE_BOUNCE_ALL | + DESC_TYPE_BOUNCE_HEAD | + DESC_TYPE_SGL_SKB)) { (*pkts)++; (*bytes) += desc_cb->send_bytes; } @@ -2778,6 +3431,9 @@ static bool hns3_nic_reclaim_desc(struct hns3_enet_ring *ring, * ring_space called by hns3_nic_net_xmit. */ smp_store_release(&ring->next_to_clean, ntc); + + hns3_tx_spare_update(ring); + return true; } @@ -2869,7 +3525,7 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring, static bool hns3_can_reuse_page(struct hns3_desc_cb *cb) { - return (page_count(cb->priv) - cb->pagecnt_bias) == 1; + return page_count(cb->priv) == cb->pagecnt_bias; } static void hns3_nic_reuse_page(struct sk_buff *skb, int i, @@ -2877,40 +3533,74 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i, struct hns3_desc_cb *desc_cb) { struct hns3_desc *desc = &ring->desc[ring->next_to_clean]; + u32 frag_offset = desc_cb->page_offset + pull_len; int size = le16_to_cpu(desc->rx.size); u32 truesize = hns3_buf_size(ring); + u32 frag_size = size - pull_len; + bool reused; - desc_cb->pagecnt_bias--; - skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len, - size - pull_len, truesize); + /* Avoid re-using remote or pfmem page */ + if (unlikely(!dev_page_is_reusable(desc_cb->priv))) + goto out; - /* Avoid re-using remote and pfmemalloc pages, or the stack is still - * using the page when page_offset rollback to zero, flag default - * unreuse + reused = hns3_can_reuse_page(desc_cb); + + /* Rx page can be reused when: + * 1. Rx page is only owned by the driver when page_offset + * is zero, which means 0 @ truesize will be used by + * stack after skb_add_rx_frag() is called, and the rest + * of rx page can be reused by driver. + * Or + * 2. Rx page is only owned by the driver when page_offset + * is non-zero, which means page_offset @ truesize will + * be used by stack after skb_add_rx_frag() is called, + * and 0 @ truesize can be reused by driver. */ - if (!dev_page_is_reusable(desc_cb->priv) || - (!desc_cb->page_offset && !hns3_can_reuse_page(desc_cb))) { - __page_frag_cache_drain(desc_cb->priv, desc_cb->pagecnt_bias); - return; - } - - /* Move offset up to the next cache line */ - desc_cb->page_offset += truesize; - - if (desc_cb->page_offset + truesize <= hns3_page_size(ring)) { - desc_cb->reuse_flag = 1; - } else if (hns3_can_reuse_page(desc_cb)) { + if ((!desc_cb->page_offset && reused) || + ((desc_cb->page_offset + truesize + truesize) <= + hns3_page_size(ring) && desc_cb->page_offset)) { + desc_cb->page_offset += truesize; desc_cb->reuse_flag = 1; + } else if (desc_cb->page_offset && reused) { desc_cb->page_offset = 0; - } else if (desc_cb->pagecnt_bias) { - __page_frag_cache_drain(desc_cb->priv, desc_cb->pagecnt_bias); + desc_cb->reuse_flag = 1; + } else if (frag_size <= ring->rx_copybreak) { + void *frag = napi_alloc_frag(frag_size); + + if (unlikely(!frag)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.frag_alloc_err++; + u64_stats_update_end(&ring->syncp); + + hns3_rl_err(ring_to_netdev(ring), + "failed to allocate rx frag\n"); + goto out; + } + + desc_cb->reuse_flag = 1; + memcpy(frag, desc_cb->buf + frag_offset, frag_size); + skb_add_rx_frag(skb, i, virt_to_page(frag), + offset_in_page(frag), frag_size, frag_size); + + u64_stats_update_begin(&ring->syncp); + ring->stats.frag_alloc++; + u64_stats_update_end(&ring->syncp); return; } +out: + desc_cb->pagecnt_bias--; + if (unlikely(!desc_cb->pagecnt_bias)) { page_ref_add(desc_cb->priv, USHRT_MAX); desc_cb->pagecnt_bias = USHRT_MAX; } + + skb_add_rx_frag(skb, i, desc_cb->priv, frag_offset, + frag_size, truesize); + + if (unlikely(!desc_cb->reuse_flag)) + __page_frag_cache_drain(desc_cb->priv, desc_cb->pagecnt_bias); } static int hns3_gro_complete(struct sk_buff *skb, u32 l234info) @@ -2971,51 +3661,31 @@ static int hns3_gro_complete(struct sk_buff *skb, u32 l234info) return 0; } -static void hns3_checksum_complete(struct hns3_enet_ring *ring, - struct sk_buff *skb, u32 l234info) +static bool hns3_checksum_complete(struct hns3_enet_ring *ring, + struct sk_buff *skb, u32 ptype, u16 csum) { - u32 lo, hi; + if (ptype == HNS3_INVALID_PTYPE || + hns3_rx_ptype_tbl[ptype].ip_summed != CHECKSUM_COMPLETE) + return false; u64_stats_update_begin(&ring->syncp); ring->stats.csum_complete++; u64_stats_update_end(&ring->syncp); skb->ip_summed = CHECKSUM_COMPLETE; - lo = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_L_M, - HNS3_RXD_L2_CSUM_L_S); - hi = hnae3_get_field(l234info, HNS3_RXD_L2_CSUM_H_M, - HNS3_RXD_L2_CSUM_H_S); - skb->csum = csum_unfold((__force __sum16)(lo | hi << 8)); + skb->csum = csum_unfold((__force __sum16)csum); + + return true; } -static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, - u32 l234info, u32 bd_base_info, u32 ol_info) +static void hns3_rx_handle_csum(struct sk_buff *skb, u32 l234info, + u32 ol_info, u32 ptype) { - struct net_device *netdev = ring_to_netdev(ring); int l3_type, l4_type; int ol4_type; - skb->ip_summed = CHECKSUM_NONE; - - skb_checksum_none_assert(skb); - - if (!(netdev->features & NETIF_F_RXCSUM)) - return; - - if (l234info & BIT(HNS3_RXD_L2_CSUM_B)) { - hns3_checksum_complete(ring, skb, l234info); - return; - } - - /* check if hardware has done checksum */ - if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B))) - return; - - if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) | - BIT(HNS3_RXD_OL3E_B) | - BIT(HNS3_RXD_OL4E_B)))) { - u64_stats_update_begin(&ring->syncp); - ring->stats.l3l4_csum_err++; - u64_stats_update_end(&ring->syncp); + if (ptype != HNS3_INVALID_PTYPE) { + skb->csum_level = hns3_rx_ptype_tbl[ptype].csum_level; + skb->ip_summed = hns3_rx_ptype_tbl[ptype].ip_summed; return; } @@ -3045,6 +3715,45 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, } } +static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, + u32 l234info, u32 bd_base_info, u32 ol_info, + u16 csum) +{ + struct net_device *netdev = ring_to_netdev(ring); + struct hns3_nic_priv *priv = netdev_priv(netdev); + u32 ptype = HNS3_INVALID_PTYPE; + + skb->ip_summed = CHECKSUM_NONE; + + skb_checksum_none_assert(skb); + + if (!(netdev->features & NETIF_F_RXCSUM)) + return; + + if (test_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state)) + ptype = hnae3_get_field(ol_info, HNS3_RXD_PTYPE_M, + HNS3_RXD_PTYPE_S); + + if (hns3_checksum_complete(ring, skb, ptype, csum)) + return; + + /* check if hardware has done checksum */ + if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B))) + return; + + if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) | + BIT(HNS3_RXD_OL3E_B) | + BIT(HNS3_RXD_OL4E_B)))) { + u64_stats_update_begin(&ring->syncp); + ring->stats.l3l4_csum_err++; + u64_stats_update_end(&ring->syncp); + + return; + } + + hns3_rx_handle_csum(skb, l234info, ol_info, ptype); +} + static void hns3_rx_skb(struct hns3_enet_ring *ring, struct sk_buff *skb) { if (skb_has_frag_list(skb)) @@ -3226,8 +3935,10 @@ static int hns3_add_frag(struct hns3_enet_ring *ring) static int hns3_set_gro_and_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb, u32 l234info, - u32 bd_base_info, u32 ol_info) + u32 bd_base_info, u32 ol_info, u16 csum) { + struct net_device *netdev = ring_to_netdev(ring); + struct hns3_nic_priv *priv = netdev_priv(netdev); u32 l3_type; skb_shinfo(skb)->gso_size = hnae3_get_field(bd_base_info, @@ -3235,7 +3946,8 @@ static int hns3_set_gro_and_checksum(struct hns3_enet_ring *ring, HNS3_RXD_GRO_SIZE_S); /* if there is no HW GRO, do not set gro params */ if (!skb_shinfo(skb)->gso_size) { - hns3_rx_checksum(ring, skb, l234info, bd_base_info, ol_info); + hns3_rx_checksum(ring, skb, l234info, bd_base_info, ol_info, + csum); return 0; } @@ -3243,7 +3955,16 @@ static int hns3_set_gro_and_checksum(struct hns3_enet_ring *ring, HNS3_RXD_GRO_COUNT_M, HNS3_RXD_GRO_COUNT_S); - l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M, HNS3_RXD_L3ID_S); + if (test_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state)) { + u32 ptype = hnae3_get_field(ol_info, HNS3_RXD_PTYPE_M, + HNS3_RXD_PTYPE_S); + + l3_type = hns3_rx_ptype_tbl[ptype].l3_type; + } else { + l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M, + HNS3_RXD_L3ID_S); + } + if (l3_type == HNS3_L3_TYPE_IPV4) skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; else if (l3_type == HNS3_L3_TYPE_IPV6) @@ -3276,6 +3997,7 @@ static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb) struct hns3_desc *desc; unsigned int len; int pre_ntc, ret; + u16 csum; /* bdinfo handled below is only valid on the last BD of the * current packet, and ring->next_to_clean indicates the first @@ -3287,6 +4009,16 @@ static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb) bd_base_info = le32_to_cpu(desc->rx.bd_base_info); l234info = le32_to_cpu(desc->rx.l234_info); ol_info = le32_to_cpu(desc->rx.ol_info); + csum = le16_to_cpu(desc->csum); + + if (unlikely(bd_base_info & BIT(HNS3_RXD_TS_VLD_B))) { + struct hnae3_handle *h = hns3_get_handle(netdev); + u32 nsec = le32_to_cpu(desc->ts_nsec); + u32 sec = le32_to_cpu(desc->ts_sec); + + if (h->ae_algo->ops->get_rx_hwts) + h->ae_algo->ops->get_rx_hwts(h, skb, nsec, sec); + } /* Based on hw strategy, the tag offloaded will be stored at * ot_vlan_tag in two layer tag case, and stored at vlan_tag @@ -3319,7 +4051,7 @@ static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb) /* This is needed in order to enable forwarding support */ ret = hns3_set_gro_and_checksum(ring, skb, l234info, - bd_base_info, ol_info); + bd_base_info, ol_info, csum); if (unlikely(ret)) { u64_stats_update_begin(&ring->syncp); ring->stats.rx_err_cnt++; @@ -3458,139 +4190,30 @@ out: return recv_pkts; } -static bool hns3_get_new_flow_lvl(struct hns3_enet_ring_group *ring_group) -{ -#define HNS3_RX_LOW_BYTE_RATE 10000 -#define HNS3_RX_MID_BYTE_RATE 20000 -#define HNS3_RX_ULTRA_PACKET_RATE 40 - - enum hns3_flow_level_range new_flow_level; - struct hns3_enet_tqp_vector *tqp_vector; - int packets_per_msecs, bytes_per_msecs; - u32 time_passed_ms; - - tqp_vector = ring_group->ring->tqp_vector; - time_passed_ms = - jiffies_to_msecs(jiffies - tqp_vector->last_jiffies); - if (!time_passed_ms) - return false; - - do_div(ring_group->total_packets, time_passed_ms); - packets_per_msecs = ring_group->total_packets; - - do_div(ring_group->total_bytes, time_passed_ms); - bytes_per_msecs = ring_group->total_bytes; - - new_flow_level = ring_group->coal.flow_level; - - /* Simple throttlerate management - * 0-10MB/s lower (50000 ints/s) - * 10-20MB/s middle (20000 ints/s) - * 20-1249MB/s high (18000 ints/s) - * > 40000pps ultra (8000 ints/s) - */ - switch (new_flow_level) { - case HNS3_FLOW_LOW: - if (bytes_per_msecs > HNS3_RX_LOW_BYTE_RATE) - new_flow_level = HNS3_FLOW_MID; - break; - case HNS3_FLOW_MID: - if (bytes_per_msecs > HNS3_RX_MID_BYTE_RATE) - new_flow_level = HNS3_FLOW_HIGH; - else if (bytes_per_msecs <= HNS3_RX_LOW_BYTE_RATE) - new_flow_level = HNS3_FLOW_LOW; - break; - case HNS3_FLOW_HIGH: - case HNS3_FLOW_ULTRA: - default: - if (bytes_per_msecs <= HNS3_RX_MID_BYTE_RATE) - new_flow_level = HNS3_FLOW_MID; - break; - } - - if (packets_per_msecs > HNS3_RX_ULTRA_PACKET_RATE && - &tqp_vector->rx_group == ring_group) - new_flow_level = HNS3_FLOW_ULTRA; - - ring_group->total_bytes = 0; - ring_group->total_packets = 0; - ring_group->coal.flow_level = new_flow_level; - - return true; -} - -static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group) -{ - struct hns3_enet_tqp_vector *tqp_vector; - u16 new_int_gl; - - if (!ring_group->ring) - return false; - - tqp_vector = ring_group->ring->tqp_vector; - if (!tqp_vector->last_jiffies) - return false; - - if (ring_group->total_packets == 0) { - ring_group->coal.int_gl = HNS3_INT_GL_50K; - ring_group->coal.flow_level = HNS3_FLOW_LOW; - return true; - } - - if (!hns3_get_new_flow_lvl(ring_group)) - return false; - - new_int_gl = ring_group->coal.int_gl; - switch (ring_group->coal.flow_level) { - case HNS3_FLOW_LOW: - new_int_gl = HNS3_INT_GL_50K; - break; - case HNS3_FLOW_MID: - new_int_gl = HNS3_INT_GL_20K; - break; - case HNS3_FLOW_HIGH: - new_int_gl = HNS3_INT_GL_18K; - break; - case HNS3_FLOW_ULTRA: - new_int_gl = HNS3_INT_GL_8K; - break; - default: - break; - } - - if (new_int_gl != ring_group->coal.int_gl) { - ring_group->coal.int_gl = new_int_gl; - return true; - } - return false; -} - -static void hns3_update_new_int_gl(struct hns3_enet_tqp_vector *tqp_vector) +static void hns3_update_rx_int_coalesce(struct hns3_enet_tqp_vector *tqp_vector) { struct hns3_enet_ring_group *rx_group = &tqp_vector->rx_group; - struct hns3_enet_ring_group *tx_group = &tqp_vector->tx_group; - bool rx_update, tx_update; + struct dim_sample sample = {}; - /* update param every 1000ms */ - if (time_before(jiffies, - tqp_vector->last_jiffies + msecs_to_jiffies(1000))) + if (!rx_group->coal.adapt_enable) return; - if (rx_group->coal.adapt_enable) { - rx_update = hns3_get_new_int_gl(rx_group); - if (rx_update) - hns3_set_vector_coalesce_rx_gl(tqp_vector, - rx_group->coal.int_gl); - } + dim_update_sample(tqp_vector->event_cnt, rx_group->total_packets, + rx_group->total_bytes, &sample); + net_dim(&rx_group->dim, sample); +} - if (tx_group->coal.adapt_enable) { - tx_update = hns3_get_new_int_gl(tx_group); - if (tx_update) - hns3_set_vector_coalesce_tx_gl(tqp_vector, - tx_group->coal.int_gl); - } +static void hns3_update_tx_int_coalesce(struct hns3_enet_tqp_vector *tqp_vector) +{ + struct hns3_enet_ring_group *tx_group = &tqp_vector->tx_group; + struct dim_sample sample = {}; - tqp_vector->last_jiffies = jiffies; + if (!tx_group->coal.adapt_enable) + return; + + dim_update_sample(tqp_vector->event_cnt, tx_group->total_packets, + tx_group->total_bytes, &sample); + net_dim(&tx_group->dim, sample); } static int hns3_nic_common_poll(struct napi_struct *napi, int budget) @@ -3635,7 +4258,9 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget) if (napi_complete(napi) && likely(!test_bit(HNS3_NIC_STATE_DOWN, &priv->state))) { - hns3_update_new_int_gl(tqp_vector); + hns3_update_rx_int_coalesce(tqp_vector); + hns3_update_tx_int_coalesce(tqp_vector); + hns3_mask_vector_irq(tqp_vector, 1); } @@ -3766,6 +4391,54 @@ static void hns3_nic_set_cpumask(struct hns3_nic_priv *priv) } } +static void hns3_rx_dim_work(struct work_struct *work) +{ + struct dim *dim = container_of(work, struct dim, work); + struct hns3_enet_ring_group *group = container_of(dim, + struct hns3_enet_ring_group, dim); + struct hns3_enet_tqp_vector *tqp_vector = group->ring->tqp_vector; + struct dim_cq_moder cur_moder = + net_dim_get_rx_moderation(dim->mode, dim->profile_ix); + + hns3_set_vector_coalesce_rx_gl(group->ring->tqp_vector, cur_moder.usec); + tqp_vector->rx_group.coal.int_gl = cur_moder.usec; + + if (cur_moder.pkts < tqp_vector->rx_group.coal.int_ql_max) { + hns3_set_vector_coalesce_rx_ql(tqp_vector, cur_moder.pkts); + tqp_vector->rx_group.coal.int_ql = cur_moder.pkts; + } + + dim->state = DIM_START_MEASURE; +} + +static void hns3_tx_dim_work(struct work_struct *work) +{ + struct dim *dim = container_of(work, struct dim, work); + struct hns3_enet_ring_group *group = container_of(dim, + struct hns3_enet_ring_group, dim); + struct hns3_enet_tqp_vector *tqp_vector = group->ring->tqp_vector; + struct dim_cq_moder cur_moder = + net_dim_get_tx_moderation(dim->mode, dim->profile_ix); + + hns3_set_vector_coalesce_tx_gl(tqp_vector, cur_moder.usec); + tqp_vector->tx_group.coal.int_gl = cur_moder.usec; + + if (cur_moder.pkts < tqp_vector->tx_group.coal.int_ql_max) { + hns3_set_vector_coalesce_tx_ql(tqp_vector, cur_moder.pkts); + tqp_vector->tx_group.coal.int_ql = cur_moder.pkts; + } + + dim->state = DIM_START_MEASURE; +} + +static void hns3_nic_init_dim(struct hns3_enet_tqp_vector *tqp_vector) +{ + INIT_WORK(&tqp_vector->rx_group.dim.work, hns3_rx_dim_work); + tqp_vector->rx_group.dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; + INIT_WORK(&tqp_vector->tx_group.dim.work, hns3_tx_dim_work); + tqp_vector->tx_group.dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; +} + static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv) { struct hnae3_handle *h = priv->ae_handle; @@ -3779,6 +4452,7 @@ static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv) tqp_vector = &priv->tqp_vector[i]; hns3_vector_coalesce_init_hw(tqp_vector, priv); tqp_vector->num_tqps = 0; + hns3_nic_init_dim(tqp_vector); } for (i = 0; i < h->kinfo.num_tqps; i++) { @@ -3974,10 +4648,13 @@ static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv, ring = &priv->ring[q->tqp_index]; desc_num = priv->ae_handle->kinfo.num_tx_desc; ring->queue_index = q->tqp_index; + ring->tx_copybreak = priv->tx_copybreak; + ring->last_to_use = 0; } else { ring = &priv->ring[q->tqp_index + queue_num]; desc_num = priv->ae_handle->kinfo.num_rx_desc; ring->queue_index = q->tqp_index; + ring->rx_copybreak = priv->rx_copybreak; } hnae3_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type); @@ -3991,7 +4668,6 @@ static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv, ring->desc_num = desc_num; ring->next_to_use = 0; ring->next_to_clean = 0; - ring->last_to_use = 0; } static void hns3_queue_to_ring(struct hnae3_queue *tqp, @@ -4051,6 +4727,8 @@ static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring) ret = hns3_alloc_ring_buffers(ring); if (ret) goto out_with_desc; + } else { + hns3_init_tx_spare_buffer(ring); } return 0; @@ -4073,9 +4751,18 @@ void hns3_fini_ring(struct hns3_enet_ring *ring) ring->next_to_use = 0; ring->last_to_use = 0; ring->pending_buf = 0; - if (ring->skb) { + if (!HNAE3_IS_TX_RING(ring) && ring->skb) { dev_kfree_skb_any(ring->skb); ring->skb = NULL; + } else if (HNAE3_IS_TX_RING(ring) && ring->tx_spare) { + struct hns3_tx_spare *tx_spare = ring->tx_spare; + + dma_unmap_page(ring_to_dev(ring), tx_spare->dma, tx_spare->len, + DMA_TO_DEVICE); + free_pages((unsigned long)tx_spare->buf, + get_order(tx_spare->len)); + devm_kfree(ring_to_dev(ring), tx_spare); + ring->tx_spare = NULL; } } @@ -4358,13 +5045,21 @@ static int hns3_client_init(struct hnae3_handle *handle) hns3_dcbnl_setup(handle); - hns3_dbg_init(handle); + ret = hns3_dbg_init(handle); + if (ret) { + dev_err(priv->dev, "failed to init debugfs, ret = %d\n", + ret); + goto out_client_start; + } netdev->max_mtu = HNS3_MAX_MTU(ae_dev->dev_specs.max_frm_size); if (test_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps)) set_bit(HNS3_NIC_STATE_HW_TX_CSUM_ENABLE, &priv->state); + if (hnae3_ae_dev_rxd_adv_layout_supported(ae_dev)) + set_bit(HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, &priv->state); + set_bit(HNS3_NIC_STATE_INITED, &priv->state); if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index daa04aeb0942..15af3d93857b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -4,6 +4,7 @@ #ifndef __HNS3_ENET_H #define __HNS3_ENET_H +#include #include #include "hnae3.h" @@ -19,6 +20,7 @@ enum hns3_nic_state { HNS3_NIC_STATE_SERVICE_SCHED, HNS3_NIC_STATE2_RESET_REQUESTED, HNS3_NIC_STATE_HW_TX_CSUM_ENABLE, + HNS3_NIC_STATE_RXD_ADV_LAYOUT_ENABLE, HNS3_NIC_STATE_MAX }; @@ -82,12 +84,6 @@ enum hns3_nic_state { #define HNS3_RXD_STRP_TAGP_S 13 #define HNS3_RXD_STRP_TAGP_M (0x3 << HNS3_RXD_STRP_TAGP_S) -#define HNS3_RXD_L2_CSUM_B 15 -#define HNS3_RXD_L2_CSUM_L_S 4 -#define HNS3_RXD_L2_CSUM_L_M (0xff << HNS3_RXD_L2_CSUM_L_S) -#define HNS3_RXD_L2_CSUM_H_S 24 -#define HNS3_RXD_L2_CSUM_H_M (0xff << HNS3_RXD_L2_CSUM_H_S) - #define HNS3_RXD_L2E_B 16 #define HNS3_RXD_L3E_B 17 #define HNS3_RXD_L4E_B 18 @@ -114,6 +110,9 @@ enum hns3_nic_state { #define HNS3_RXD_FBLI_S 14 #define HNS3_RXD_FBLI_M (0x3 << HNS3_RXD_FBLI_S) +#define HNS3_RXD_PTYPE_S 4 +#define HNS3_RXD_PTYPE_M GENMASK(11, 4) + #define HNS3_RXD_BDTYPE_S 0 #define HNS3_RXD_BDTYPE_M (0xf << HNS3_RXD_BDTYPE_S) #define HNS3_RXD_VLD_B 4 @@ -123,8 +122,9 @@ enum hns3_nic_state { #define HNS3_RXD_LUM_B 9 #define HNS3_RXD_CRCP_B 10 #define HNS3_RXD_L3L4P_B 11 -#define HNS3_RXD_TSIND_S 12 -#define HNS3_RXD_TSIND_M (0x7 << HNS3_RXD_TSIND_S) +#define HNS3_RXD_TSIDX_S 12 +#define HNS3_RXD_TSIDX_M (0x3 << HNS3_RXD_TSIDX_S) +#define HNS3_RXD_TS_VLD_B 14 #define HNS3_RXD_LKBK_B 15 #define HNS3_RXD_GRO_SIZE_S 16 #define HNS3_RXD_GRO_SIZE_M (0x3fff << HNS3_RXD_GRO_SIZE_S) @@ -238,7 +238,14 @@ enum hns3_pkt_tun_type { /* hardware spec ring buffer format */ struct __packed hns3_desc { - __le64 addr; + union { + __le64 addr; + __le16 csum; + struct { + __le32 ts_nsec; + __le32 ts_sec; + }; + }; union { struct { __le16 vlan_tag; @@ -292,6 +299,16 @@ struct __packed hns3_desc { }; }; +enum hns3_desc_type { + DESC_TYPE_UNKNOWN = 0, + DESC_TYPE_SKB = 1 << 0, + DESC_TYPE_FRAGLIST_SKB = 1 << 1, + DESC_TYPE_PAGE = 1 << 2, + DESC_TYPE_BOUNCE_ALL = 1 << 3, + DESC_TYPE_BOUNCE_HEAD = 1 << 4, + DESC_TYPE_SGL_SKB = 1 << 5, +}; + struct hns3_desc_cb { dma_addr_t dma; /* dma address of this desc */ void *buf; /* cpu addr for a desc */ @@ -366,6 +383,14 @@ enum hns3_pkt_ol4type { HNS3_OL4_TYPE_UNKNOWN }; +struct hns3_rx_ptype { + u32 ptype:8; + u32 csum_level:2; + u32 ip_summed:2; + u32 l3_type:4; + u32 valid:1; +}; + struct ring_stats { u64 sw_err_cnt; u64 seg_pkt_cnt; @@ -383,6 +408,12 @@ struct ring_stats { u64 tx_tso_err; u64 over_max_recursion; u64 hw_limitation; + u64 tx_bounce; + u64 tx_spare_full; + u64 copy_bits_err; + u64 tx_sgl; + u64 skb2sgl_err; + u64 map_sg_err; }; struct { u64 rx_pkts; @@ -396,10 +427,22 @@ struct ring_stats { u64 csum_complete; u64 rx_multicast; u64 non_reuse_pg; + u64 frag_alloc_err; + u64 frag_alloc; }; + __le16 csum; }; }; +struct hns3_tx_spare { + dma_addr_t dma; + void *buf; + u32 next_to_use; + u32 next_to_clean; + u32 last_to_clean; + u32 len; +}; + struct hns3_enet_ring { struct hns3_desc *desc; /* dma map address space */ struct hns3_desc_cb *desc_cb; @@ -422,18 +465,29 @@ struct hns3_enet_ring { * next_to_use */ int next_to_clean; - union { - int last_to_use; /* last idx used by xmit */ - u32 pull_len; /* memcpy len for current rx packet */ - }; - u32 frag_num; - void *va; /* first buffer address for current packet */ - u32 flag; /* ring attribute */ int pending_buf; - struct sk_buff *skb; - struct sk_buff *tail_skb; + union { + /* for Tx ring */ + struct { + u32 fd_qb_tx_sample; + int last_to_use; /* last idx used by xmit */ + u32 tx_copybreak; + struct hns3_tx_spare *tx_spare; + }; + + /* for Rx ring */ + struct { + u32 pull_len; /* memcpy len for current rx packet */ + u32 rx_copybreak; + u32 frag_num; + /* first buffer address for current packet */ + unsigned char *va; + struct sk_buff *skb; + struct sk_buff *tail_skb; + }; + }; } ____cacheline_internodealigned_in_smp; enum hns3_flow_level_range { @@ -472,6 +526,7 @@ struct hns3_enet_ring_group { u64 total_packets; /* total packets processed this group */ u16 count; struct hns3_enet_coalesce coal; + struct dim dim; }; struct hns3_enet_tqp_vector { @@ -493,7 +548,7 @@ struct hns3_enet_tqp_vector { char name[HNAE3_INT_NAME_LEN]; - unsigned long last_jiffies; + u64 event_cnt; } ____cacheline_internodealigned_in_smp; struct hns3_nic_priv { @@ -516,6 +571,8 @@ struct hns3_nic_priv { struct hns3_enet_coalesce tx_coal; struct hns3_enet_coalesce rx_coal; + u32 tx_copybreak; + u32 rx_copybreak; }; union l3_hdr_info { @@ -631,7 +688,6 @@ void hns3_set_vector_coalesce_rx_ql(struct hns3_enet_tqp_vector *tqp_vector, void hns3_set_vector_coalesce_tx_ql(struct hns3_enet_tqp_vector *tqp_vector, u32 ql_value); -void hns3_enable_vlan_filter(struct net_device *netdev, bool enable); void hns3_request_update_promisc_mode(struct hnae3_handle *handle); #ifdef CONFIG_HNS3_DCB @@ -640,9 +696,10 @@ void hns3_dcbnl_setup(struct hnae3_handle *handle); static inline void hns3_dcbnl_setup(struct hnae3_handle *handle) {} #endif -void hns3_dbg_init(struct hnae3_handle *handle); +int hns3_dbg_init(struct hnae3_handle *handle); void hns3_dbg_uninit(struct hnae3_handle *handle); void hns3_dbg_register_debugfs(const char *debugfs_dir_name); void hns3_dbg_unregister_debugfs(void); void hns3_shinfo_pack(struct skb_shared_info *shinfo, __u32 *size); +u16 hns3_get_max_available_channels(struct hnae3_handle *h); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index c1ea403d2b56..82061ab6930f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -46,6 +46,12 @@ static const struct hns3_stats hns3_txq_stats[] = { HNS3_TQP_STAT("tso_err", tx_tso_err), HNS3_TQP_STAT("over_max_recursion", over_max_recursion), HNS3_TQP_STAT("hw_limitation", hw_limitation), + HNS3_TQP_STAT("bounce", tx_bounce), + HNS3_TQP_STAT("spare_full", tx_spare_full), + HNS3_TQP_STAT("copy_bits_err", copy_bits_err), + HNS3_TQP_STAT("sgl", tx_sgl), + HNS3_TQP_STAT("skb2sgl_err", skb2sgl_err), + HNS3_TQP_STAT("map_sg_err", map_sg_err), }; #define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats) @@ -65,6 +71,8 @@ static const struct hns3_stats hns3_rxq_stats[] = { HNS3_TQP_STAT("csum_complete", csum_complete), HNS3_TQP_STAT("multicast", rx_multicast), HNS3_TQP_STAT("non_reuse_pg", non_reuse_pg), + HNS3_TQP_STAT("frag_alloc_err", frag_alloc_err), + HNS3_TQP_STAT("frag_alloc", frag_alloc), }; #define HNS3_PRIV_FLAGS_LEN ARRAY_SIZE(hns3_priv_flags) @@ -88,7 +96,6 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en) { struct hnae3_handle *h = hns3_get_handle(ndev); struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev); - bool vlan_filter_enable; int ret; if (!h->ae_algo->ops->set_loopback || @@ -110,14 +117,11 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en) if (ret || ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) return ret; - if (en) { + if (en) h->ae_algo->ops->set_promisc_mode(h, true, true); - } else { + else /* recover promisc mode before loopback test */ hns3_request_update_promisc_mode(h); - vlan_filter_enable = ndev->flags & IFF_PROMISC ? false : true; - hns3_enable_vlan_filter(ndev, vlan_filter_enable); - } return ret; } @@ -1596,12 +1600,77 @@ static int hns3_set_priv_flags(struct net_device *netdev, u32 pflags) return 0; } +static int hns3_get_tunable(struct net_device *netdev, + const struct ethtool_tunable *tuna, + void *data) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + int ret = 0; + + switch (tuna->id) { + case ETHTOOL_TX_COPYBREAK: + /* all the tx rings have the same tx_copybreak */ + *(u32 *)data = priv->tx_copybreak; + break; + case ETHTOOL_RX_COPYBREAK: + *(u32 *)data = priv->rx_copybreak; + break; + default: + ret = -EOPNOTSUPP; + break; + } + + return ret; +} + +static int hns3_set_tunable(struct net_device *netdev, + const struct ethtool_tunable *tuna, + const void *data) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + struct hnae3_handle *h = priv->ae_handle; + int i, ret = 0; + + switch (tuna->id) { + case ETHTOOL_TX_COPYBREAK: + priv->tx_copybreak = *(u32 *)data; + + for (i = 0; i < h->kinfo.num_tqps; i++) + priv->ring[i].tx_copybreak = priv->tx_copybreak; + + break; + case ETHTOOL_RX_COPYBREAK: + priv->rx_copybreak = *(u32 *)data; + + for (i = h->kinfo.num_tqps; i < h->kinfo.num_tqps * 2; i++) + priv->ring[i].rx_copybreak = priv->rx_copybreak; + + break; + default: + ret = -EOPNOTSUPP; + break; + } + + return ret; +} + #define HNS3_ETHTOOL_COALESCE (ETHTOOL_COALESCE_USECS | \ ETHTOOL_COALESCE_USE_ADAPTIVE | \ ETHTOOL_COALESCE_RX_USECS_HIGH | \ ETHTOOL_COALESCE_TX_USECS_HIGH | \ ETHTOOL_COALESCE_MAX_FRAMES) +static int hns3_get_ts_info(struct net_device *netdev, + struct ethtool_ts_info *info) +{ + struct hnae3_handle *handle = hns3_get_handle(netdev); + + if (handle->ae_algo->ops->get_ts_info) + return handle->ae_algo->ops->get_ts_info(handle, info); + + return ethtool_op_get_ts_info(netdev, info); +} + static const struct ethtool_ops hns3vf_ethtool_ops = { .supported_coalesce_params = HNS3_ETHTOOL_COALESCE, .get_drvinfo = hns3_get_drvinfo, @@ -1628,6 +1697,8 @@ static const struct ethtool_ops hns3vf_ethtool_ops = { .set_msglevel = hns3_set_msglevel, .get_priv_flags = hns3_get_priv_flags, .set_priv_flags = hns3_set_priv_flags, + .get_tunable = hns3_get_tunable, + .set_tunable = hns3_set_tunable, }; static const struct ethtool_ops hns3_ethtool_ops = { @@ -1666,6 +1737,9 @@ static const struct ethtool_ops hns3_ethtool_ops = { .get_module_eeprom = hns3_get_module_eeprom, .get_priv_flags = hns3_get_priv_flags, .set_priv_flags = hns3_set_priv_flags, + .get_ts_info = hns3_get_ts_info, + .get_tunable = hns3_get_tunable, + .set_tunable = hns3_set_tunable, }; void hns3_ethtool_set_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile index 6c28c8f6292c..a685392dbfe9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile @@ -7,6 +7,6 @@ ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3 ccflags-y += -I $(srctree)/$(src) obj-$(CONFIG_HNS3_HCLGE) += hclge.o -hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o hclge_debugfs.o +hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o hclge_debugfs.o hclge_ptp.o hclge-$(CONFIG_HNS3_DCB) += hclge_dcb.o diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 76a482456f1f..887297e37cf3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -178,7 +178,8 @@ static bool hclge_is_special_opcode(u16 opcode) HCLGE_QUERY_CLEAR_MPF_RAS_INT, HCLGE_QUERY_CLEAR_PF_RAS_INT, HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT, - HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT}; + HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT, + HCLGE_QUERY_ALL_ERR_INFO}; int i; for (i = 0; i < ARRAY_SIZE(spec_opcode); i++) { @@ -386,6 +387,14 @@ static void hclge_parse_capability(struct hclge_dev *hdev, set_bit(HNAE3_DEV_SUPPORT_PAUSE_B, ae_dev->caps); if (hnae3_get_bit(caps, HCLGE_CAP_PHY_IMP_B)) set_bit(HNAE3_DEV_SUPPORT_PHY_IMP_B, ae_dev->caps); + if (hnae3_get_bit(caps, HCLGE_CAP_RAS_IMP_B)) + set_bit(HNAE3_DEV_SUPPORT_RAS_IMP_B, ae_dev->caps); + if (hnae3_get_bit(caps, HCLGE_CAP_RXD_ADV_LAYOUT_B)) + set_bit(HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B, ae_dev->caps); + if (hnae3_get_bit(caps, HCLGE_CAP_PORT_VLAN_BYPASS_B)) { + set_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps); + set_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps); + } } static __le32 hclge_build_api_caps(void) @@ -469,7 +478,7 @@ static int hclge_firmware_compat_config(struct hclge_dev *hdev) struct hclge_desc desc; u32 compat = 0; - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_M7_COMPAT_CFG, false); + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_IMP_COMPAT_CFG, false); req = (struct hclge_firmware_compat_cmd *)desc.data; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index c6fc22e29581..18bde77ef944 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -130,6 +130,10 @@ enum hclge_opcode_type { HCLGE_OPC_COMMON_LOOPBACK = 0x0315, HCLGE_OPC_CONFIG_FEC_MODE = 0x031A, + /* PTP commands */ + HCLGE_OPC_PTP_INT_EN = 0x0501, + HCLGE_OPC_PTP_MODE_CFG = 0x0507, + /* PFC/Pause commands */ HCLGE_OPC_CFG_MAC_PAUSE_EN = 0x0701, HCLGE_OPC_CFG_PFC_PAUSE_EN = 0x0702, @@ -236,6 +240,7 @@ enum hclge_opcode_type { HCLGE_OPC_VLAN_FILTER_CTRL = 0x1100, HCLGE_OPC_VLAN_FILTER_PF_CFG = 0x1101, HCLGE_OPC_VLAN_FILTER_VF_CFG = 0x1102, + HCLGE_OPC_PORT_VLAN_BYPASS = 0x1103, /* Flow Director commands */ HCLGE_OPC_FD_MODE_CTRL = 0x1200, @@ -243,6 +248,7 @@ enum hclge_opcode_type { HCLGE_OPC_FD_KEY_CONFIG = 0x1202, HCLGE_OPC_FD_TCAM_OP = 0x1203, HCLGE_OPC_FD_AD_OP = 0x1204, + HCLGE_OPC_FD_CNT_OP = 0x1205, HCLGE_OPC_FD_USER_DEF_OP = 0x1207, /* MDIO command */ @@ -267,10 +273,10 @@ enum hclge_opcode_type { /* NCL config command */ HCLGE_OPC_QUERY_NCL_CONFIG = 0x7011, - /* M7 stats command */ - HCLGE_OPC_M7_STATS_BD = 0x7012, - HCLGE_OPC_M7_STATS_INFO = 0x7013, - HCLGE_OPC_M7_COMPAT_CFG = 0x701A, + /* IMP stats command */ + HCLGE_OPC_IMP_STATS_BD = 0x7012, + HCLGE_OPC_IMP_STATS_INFO = 0x7013, + HCLGE_OPC_IMP_COMPAT_CFG = 0x701A, /* SFP command */ HCLGE_OPC_GET_SFP_EEPROM = 0x7100, @@ -292,6 +298,8 @@ enum hclge_opcode_type { HCLGE_QUERY_MSIX_INT_STS_BD_NUM = 0x1513, HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT = 0x1514, HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT = 0x1515, + HCLGE_QUERY_ALL_ERR_BD_NUM = 0x1516, + HCLGE_QUERY_ALL_ERR_INFO = 0x1517, HCLGE_CONFIG_ROCEE_RAS_INT_EN = 0x1580, HCLGE_QUERY_CLEAR_ROCEE_RAS_INT = 0x1581, HCLGE_ROCEE_PF_RAS_INT_CMD = 0x1584, @@ -389,8 +397,11 @@ enum HCLGE_CAP_BITS { HCLGE_CAP_HW_PAD_B, HCLGE_CAP_STASH_B, HCLGE_CAP_UDP_TUNNEL_CSUM_B, + HCLGE_CAP_RAS_IMP_B = 12, HCLGE_CAP_FEC_B = 13, HCLGE_CAP_PAUSE_B = 14, + HCLGE_CAP_RXD_ADV_LAYOUT_B = 15, + HCLGE_CAP_PORT_VLAN_BYPASS_B = 17, }; enum HCLGE_API_CAP_BITS { @@ -526,10 +537,14 @@ struct hclge_pf_res_cmd { #define HCLGE_CFG_SPEED_ABILITY_M GENMASK(7, 0) #define HCLGE_CFG_SPEED_ABILITY_EXT_S 10 #define HCLGE_CFG_SPEED_ABILITY_EXT_M GENMASK(15, 10) +#define HCLGE_CFG_VLAN_FLTR_CAP_S 8 +#define HCLGE_CFG_VLAN_FLTR_CAP_M GENMASK(9, 8) #define HCLGE_CFG_UMV_TBL_SPACE_S 16 #define HCLGE_CFG_UMV_TBL_SPACE_M GENMASK(31, 16) #define HCLGE_CFG_PF_RSS_SIZE_S 0 #define HCLGE_CFG_PF_RSS_SIZE_M GENMASK(3, 0) +#define HCLGE_CFG_TX_SPARE_BUF_SIZE_S 4 +#define HCLGE_CFG_TX_SPARE_BUF_SIZE_M GENMASK(15, 4) #define HCLGE_CFG_CMD_CNT 4 @@ -810,6 +825,14 @@ struct hclge_vlan_filter_vf_cfg_cmd { u8 vf_bitmap[HCLGE_MAX_VF_BYTES]; }; +#define HCLGE_INGRESS_BYPASS_B 0 +struct hclge_port_vlan_filter_bypass_cmd { + u8 bypass_state; + u8 rsv1[3]; + u8 vf_id; + u8 rsv2[19]; +}; + #define HCLGE_SWITCH_ANTI_SPOOF_B 0U #define HCLGE_SWITCH_ALW_LPBK_B 1U #define HCLGE_SWITCH_ALW_LCL_LPBK_B 2U @@ -1087,6 +1110,14 @@ struct hclge_fd_ad_config_cmd { u8 rsv2[8]; }; +struct hclge_fd_ad_cnt_read_cmd { + u8 rsv0[4]; + __le16 index; + u8 rsv1[2]; + __le64 cnt; + u8 rsv2[8]; +}; + #define HCLGE_FD_USER_DEF_OFT_S 0 #define HCLGE_FD_USER_DEF_OFT_M GENMASK(14, 0) #define HCLGE_FD_USER_DEF_EN_B 15 @@ -1100,7 +1131,7 @@ struct hclge_fd_user_def_cfg_cmd { u8 rsv[12]; }; -struct hclge_get_m7_bd_cmd { +struct hclge_get_imp_bd_cmd { __le32 bd_num; u8 rsv[20]; }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 85d306459e36..288788186ecc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -4,74 +4,110 @@ #include #include "hclge_debugfs.h" +#include "hclge_err.h" #include "hclge_main.h" #include "hclge_tm.h" #include "hnae3.h" +static const char * const state_str[] = { "off", "on" }; +static const char * const hclge_mac_state_str[] = { + "TO_ADD", "TO_DEL", "ACTIVE" +}; + static const struct hclge_dbg_reg_type_info hclge_dbg_reg_info[] = { - { .reg_type = "bios common", + { .cmd = HNAE3_DBG_CMD_REG_BIOS_COMMON, .dfx_msg = &hclge_dbg_bios_common_reg[0], .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_bios_common_reg), .offset = HCLGE_DBG_DFX_BIOS_OFFSET, .cmd = HCLGE_OPC_DFX_BIOS_COMMON_REG } }, - { .reg_type = "ssu", + { .cmd = HNAE3_DBG_CMD_REG_SSU, .dfx_msg = &hclge_dbg_ssu_reg_0[0], .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ssu_reg_0), .offset = HCLGE_DBG_DFX_SSU_0_OFFSET, .cmd = HCLGE_OPC_DFX_SSU_REG_0 } }, - { .reg_type = "ssu", + { .cmd = HNAE3_DBG_CMD_REG_SSU, .dfx_msg = &hclge_dbg_ssu_reg_1[0], .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ssu_reg_1), .offset = HCLGE_DBG_DFX_SSU_1_OFFSET, .cmd = HCLGE_OPC_DFX_SSU_REG_1 } }, - { .reg_type = "ssu", + { .cmd = HNAE3_DBG_CMD_REG_SSU, .dfx_msg = &hclge_dbg_ssu_reg_2[0], .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ssu_reg_2), .offset = HCLGE_DBG_DFX_SSU_2_OFFSET, .cmd = HCLGE_OPC_DFX_SSU_REG_2 } }, - { .reg_type = "igu egu", + { .cmd = HNAE3_DBG_CMD_REG_IGU_EGU, .dfx_msg = &hclge_dbg_igu_egu_reg[0], .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_igu_egu_reg), .offset = HCLGE_DBG_DFX_IGU_OFFSET, .cmd = HCLGE_OPC_DFX_IGU_EGU_REG } }, - { .reg_type = "rpu", + { .cmd = HNAE3_DBG_CMD_REG_RPU, .dfx_msg = &hclge_dbg_rpu_reg_0[0], .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_rpu_reg_0), .offset = HCLGE_DBG_DFX_RPU_0_OFFSET, .cmd = HCLGE_OPC_DFX_RPU_REG_0 } }, - { .reg_type = "rpu", + { .cmd = HNAE3_DBG_CMD_REG_RPU, .dfx_msg = &hclge_dbg_rpu_reg_1[0], .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_rpu_reg_1), .offset = HCLGE_DBG_DFX_RPU_1_OFFSET, .cmd = HCLGE_OPC_DFX_RPU_REG_1 } }, - { .reg_type = "ncsi", + { .cmd = HNAE3_DBG_CMD_REG_NCSI, .dfx_msg = &hclge_dbg_ncsi_reg[0], .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ncsi_reg), .offset = HCLGE_DBG_DFX_NCSI_OFFSET, .cmd = HCLGE_OPC_DFX_NCSI_REG } }, - { .reg_type = "rtc", + { .cmd = HNAE3_DBG_CMD_REG_RTC, .dfx_msg = &hclge_dbg_rtc_reg[0], .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_rtc_reg), .offset = HCLGE_DBG_DFX_RTC_OFFSET, .cmd = HCLGE_OPC_DFX_RTC_REG } }, - { .reg_type = "ppp", + { .cmd = HNAE3_DBG_CMD_REG_PPP, .dfx_msg = &hclge_dbg_ppp_reg[0], .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ppp_reg), .offset = HCLGE_DBG_DFX_PPP_OFFSET, .cmd = HCLGE_OPC_DFX_PPP_REG } }, - { .reg_type = "rcb", + { .cmd = HNAE3_DBG_CMD_REG_RCB, .dfx_msg = &hclge_dbg_rcb_reg[0], .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_rcb_reg), .offset = HCLGE_DBG_DFX_RCB_OFFSET, .cmd = HCLGE_OPC_DFX_RCB_REG } }, - { .reg_type = "tqp", + { .cmd = HNAE3_DBG_CMD_REG_TQP, .dfx_msg = &hclge_dbg_tqp_reg[0], .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_tqp_reg), .offset = HCLGE_DBG_DFX_TQP_OFFSET, .cmd = HCLGE_OPC_DFX_TQP_REG } }, }; -static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset) +static void hclge_dbg_fill_content(char *content, u16 len, + const struct hclge_dbg_item *items, + const char **result, u16 size) +{ + char *pos = content; + u16 i; + + memset(content, ' ', len); + for (i = 0; i < size; i++) { + if (result) + strncpy(pos, result[i], strlen(result[i])); + else + strncpy(pos, items[i].name, strlen(items[i].name)); + pos += strlen(items[i].name) + items[i].interval; + } + *pos++ = '\n'; + *pos++ = '\0'; +} + +static char *hclge_dbg_get_func_id_str(char *buf, u8 id) +{ + if (id) + sprintf(buf, "vf%u", id - 1); + else + sprintf(buf, "pf"); + + return buf; +} + +static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset, + u32 *bd_num) { struct hclge_desc desc[HCLGE_GET_DFX_REG_TYPE_CNT]; int entries_per_desc; @@ -81,13 +117,21 @@ static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset) ret = hclge_query_bd_num_cmd_send(hdev, desc); if (ret) { dev_err(&hdev->pdev->dev, - "get dfx bdnum fail, ret = %d\n", ret); + "failed to get dfx bd_num, offset = %d, ret = %d\n", + offset, ret); return ret; } entries_per_desc = ARRAY_SIZE(desc[0].data); index = offset % entries_per_desc; - return le32_to_cpu(desc[offset / entries_per_desc].data[index]); + + *bd_num = le32_to_cpu(desc[offset / entries_per_desc].data[index]); + if (!(*bd_num)) { + dev_err(&hdev->pdev->dev, "The value of dfx bd_num is 0!\n"); + return -EINVAL; + } + + return 0; } static int hclge_dbg_cmd_send(struct hclge_dev *hdev, @@ -114,66 +158,108 @@ static int hclge_dbg_cmd_send(struct hclge_dev *hdev, return ret; } -static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev, - const struct hclge_dbg_reg_type_info *reg_info, - const char *cmd_buf) +static int +hclge_dbg_dump_reg_tqp(struct hclge_dev *hdev, + const struct hclge_dbg_reg_type_info *reg_info, + char *buf, int len, int *pos) { -#define IDX_OFFSET 1 - - const char *s = &cmd_buf[strlen(reg_info->reg_type) + IDX_OFFSET]; const struct hclge_dbg_dfx_message *dfx_message = reg_info->dfx_msg; const struct hclge_dbg_reg_common_msg *reg_msg = ®_info->reg_msg; struct hclge_desc *desc_src; + u32 index, entry, i, cnt; + int bd_num, min_num, ret; struct hclge_desc *desc; - int entries_per_desc; - int bd_num, buf_len; - int index = 0; - int min_num; - int ret, i; - if (*s) { - ret = kstrtouint(s, 0, &index); - index = (ret != 0) ? 0 : index; - } + ret = hclge_dbg_get_dfx_bd_num(hdev, reg_msg->offset, &bd_num); + if (ret) + return ret; - bd_num = hclge_dbg_get_dfx_bd_num(hdev, reg_msg->offset); - if (bd_num <= 0) { - dev_err(&hdev->pdev->dev, "get cmd(%d) bd num(%d) failed\n", - reg_msg->offset, bd_num); - return; - } - - buf_len = sizeof(struct hclge_desc) * bd_num; - desc_src = kzalloc(buf_len, GFP_KERNEL); + desc_src = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL); if (!desc_src) - return; + return -ENOMEM; - desc = desc_src; - ret = hclge_dbg_cmd_send(hdev, desc, index, bd_num, reg_msg->cmd); - if (ret) { - kfree(desc_src); - return; - } + min_num = min_t(int, bd_num * HCLGE_DESC_DATA_LEN, reg_msg->msg_num); - entries_per_desc = ARRAY_SIZE(desc->data); - min_num = min_t(int, bd_num * entries_per_desc, reg_msg->msg_num); + for (i = 0, cnt = 0; i < min_num; i++, dfx_message++) + *pos += scnprintf(buf + *pos, len - *pos, "item%u = %s\n", + cnt++, dfx_message->message); - desc = desc_src; - for (i = 0; i < min_num; i++) { - if (i > 0 && (i % entries_per_desc) == 0) - desc++; - if (dfx_message->flag) - dev_info(&hdev->pdev->dev, "%s: 0x%x\n", - dfx_message->message, - le32_to_cpu(desc->data[i % entries_per_desc])); + for (i = 0; i < cnt; i++) + *pos += scnprintf(buf + *pos, len - *pos, "item%u\t", i); - dfx_message++; + *pos += scnprintf(buf + *pos, len - *pos, "\n"); + + for (index = 0; index < hdev->vport[0].alloc_tqps; index++) { + dfx_message = reg_info->dfx_msg; + desc = desc_src; + ret = hclge_dbg_cmd_send(hdev, desc, index, bd_num, + reg_msg->cmd); + if (ret) + break; + + for (i = 0; i < min_num; i++, dfx_message++) { + entry = i % HCLGE_DESC_DATA_LEN; + if (i > 0 && !entry) + desc++; + + *pos += scnprintf(buf + *pos, len - *pos, "%#x\t", + le32_to_cpu(desc->data[entry])); + } + *pos += scnprintf(buf + *pos, len - *pos, "\n"); } kfree(desc_src); + return ret; } -static void hclge_dbg_dump_mac_enable_status(struct hclge_dev *hdev) +static int +hclge_dbg_dump_reg_common(struct hclge_dev *hdev, + const struct hclge_dbg_reg_type_info *reg_info, + char *buf, int len, int *pos) +{ + const struct hclge_dbg_reg_common_msg *reg_msg = ®_info->reg_msg; + const struct hclge_dbg_dfx_message *dfx_message = reg_info->dfx_msg; + struct hclge_desc *desc_src; + int bd_num, min_num, ret; + struct hclge_desc *desc; + u32 entry, i; + + ret = hclge_dbg_get_dfx_bd_num(hdev, reg_msg->offset, &bd_num); + if (ret) + return ret; + + desc_src = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL); + if (!desc_src) + return -ENOMEM; + + desc = desc_src; + + ret = hclge_dbg_cmd_send(hdev, desc, 0, bd_num, reg_msg->cmd); + if (ret) { + kfree(desc); + return ret; + } + + min_num = min_t(int, bd_num * HCLGE_DESC_DATA_LEN, reg_msg->msg_num); + + for (i = 0; i < min_num; i++, dfx_message++) { + entry = i % HCLGE_DESC_DATA_LEN; + if (i > 0 && !entry) + desc++; + if (!dfx_message->flag) + continue; + + *pos += scnprintf(buf + *pos, len - *pos, "%s: %#x\n", + dfx_message->message, + le32_to_cpu(desc->data[entry])); + } + + kfree(desc_src); + return 0; +} + +static int hclge_dbg_dump_mac_enable_status(struct hclge_dev *hdev, char *buf, + int len, int *pos) { struct hclge_config_mac_mode_cmd *req; struct hclge_desc desc; @@ -186,43 +272,51 @@ static void hclge_dbg_dump_mac_enable_status(struct hclge_dev *hdev) if (ret) { dev_err(&hdev->pdev->dev, "failed to dump mac enable status, ret = %d\n", ret); - return; + return ret; } req = (struct hclge_config_mac_mode_cmd *)desc.data; loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en); - dev_info(&hdev->pdev->dev, "config_mac_trans_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_TX_EN_B)); - dev_info(&hdev->pdev->dev, "config_mac_rcv_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_RX_EN_B)); - dev_info(&hdev->pdev->dev, "config_pad_trans_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_PAD_TX_B)); - dev_info(&hdev->pdev->dev, "config_pad_rcv_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_PAD_RX_B)); - dev_info(&hdev->pdev->dev, "config_1588_trans_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_1588_TX_B)); - dev_info(&hdev->pdev->dev, "config_1588_rcv_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_1588_RX_B)); - dev_info(&hdev->pdev->dev, "config_mac_app_loop_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_APP_LP_B)); - dev_info(&hdev->pdev->dev, "config_mac_line_loop_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_LINE_LP_B)); - dev_info(&hdev->pdev->dev, "config_mac_fcs_tx_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_FCS_TX_B)); - dev_info(&hdev->pdev->dev, "config_mac_rx_oversize_truncate_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B)); - dev_info(&hdev->pdev->dev, "config_mac_rx_fcs_strip_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B)); - dev_info(&hdev->pdev->dev, "config_mac_rx_fcs_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_RX_FCS_B)); - dev_info(&hdev->pdev->dev, "config_mac_tx_under_min_err_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B)); - dev_info(&hdev->pdev->dev, "config_mac_tx_oversize_truncate_en: %#x\n", - hnae3_get_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B)); + *pos += scnprintf(buf + *pos, len - *pos, "mac_trans_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_TX_EN_B)); + *pos += scnprintf(buf + *pos, len - *pos, "mac_rcv_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_RX_EN_B)); + *pos += scnprintf(buf + *pos, len - *pos, "pad_trans_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_PAD_TX_B)); + *pos += scnprintf(buf + *pos, len - *pos, "pad_rcv_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_PAD_RX_B)); + *pos += scnprintf(buf + *pos, len - *pos, "1588_trans_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_1588_TX_B)); + *pos += scnprintf(buf + *pos, len - *pos, "1588_rcv_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_1588_RX_B)); + *pos += scnprintf(buf + *pos, len - *pos, "mac_app_loop_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_APP_LP_B)); + *pos += scnprintf(buf + *pos, len - *pos, "mac_line_loop_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_LINE_LP_B)); + *pos += scnprintf(buf + *pos, len - *pos, "mac_fcs_tx_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_FCS_TX_B)); + *pos += scnprintf(buf + *pos, len - *pos, + "mac_rx_oversize_truncate_en: %#x\n", + hnae3_get_bit(loop_en, + HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B)); + *pos += scnprintf(buf + *pos, len - *pos, "mac_rx_fcs_strip_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B)); + *pos += scnprintf(buf + *pos, len - *pos, "mac_rx_fcs_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_RX_FCS_B)); + *pos += scnprintf(buf + *pos, len - *pos, + "mac_tx_under_min_err_en: %#x\n", + hnae3_get_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B)); + *pos += scnprintf(buf + *pos, len - *pos, + "mac_tx_oversize_truncate_en: %#x\n", + hnae3_get_bit(loop_en, + HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B)); + + return 0; } -static void hclge_dbg_dump_mac_frame_size(struct hclge_dev *hdev) +static int hclge_dbg_dump_mac_frame_size(struct hclge_dev *hdev, char *buf, + int len, int *pos) { struct hclge_config_max_frm_size_cmd *req; struct hclge_desc desc; @@ -234,17 +328,21 @@ static void hclge_dbg_dump_mac_frame_size(struct hclge_dev *hdev) if (ret) { dev_err(&hdev->pdev->dev, "failed to dump mac frame size, ret = %d\n", ret); - return; + return ret; } req = (struct hclge_config_max_frm_size_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "max_frame_size: %u\n", - le16_to_cpu(req->max_frm_size)); - dev_info(&hdev->pdev->dev, "min_frame_size: %u\n", req->min_frm_size); + *pos += scnprintf(buf + *pos, len - *pos, "max_frame_size: %u\n", + le16_to_cpu(req->max_frm_size)); + *pos += scnprintf(buf + *pos, len - *pos, "min_frame_size: %u\n", + req->min_frm_size); + + return 0; } -static void hclge_dbg_dump_mac_speed_duplex(struct hclge_dev *hdev) +static int hclge_dbg_dump_mac_speed_duplex(struct hclge_dev *hdev, char *buf, + int len, int *pos) { #define HCLGE_MAC_SPEED_SHIFT 0 #define HCLGE_MAC_SPEED_MASK GENMASK(5, 0) @@ -260,543 +358,540 @@ static void hclge_dbg_dump_mac_speed_duplex(struct hclge_dev *hdev) if (ret) { dev_err(&hdev->pdev->dev, "failed to dump mac speed duplex, ret = %d\n", ret); - return; + return ret; } req = (struct hclge_config_mac_speed_dup_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "speed: %#lx\n", - hnae3_get_field(req->speed_dup, HCLGE_MAC_SPEED_MASK, - HCLGE_MAC_SPEED_SHIFT)); - dev_info(&hdev->pdev->dev, "duplex: %#x\n", - hnae3_get_bit(req->speed_dup, HCLGE_MAC_DUPLEX_SHIFT)); + *pos += scnprintf(buf + *pos, len - *pos, "speed: %#lx\n", + hnae3_get_field(req->speed_dup, HCLGE_MAC_SPEED_MASK, + HCLGE_MAC_SPEED_SHIFT)); + *pos += scnprintf(buf + *pos, len - *pos, "duplex: %#x\n", + hnae3_get_bit(req->speed_dup, + HCLGE_MAC_DUPLEX_SHIFT)); + return 0; } -static void hclge_dbg_dump_mac(struct hclge_dev *hdev) +static int hclge_dbg_dump_mac(struct hclge_dev *hdev, char *buf, int len) { - hclge_dbg_dump_mac_enable_status(hdev); + int pos = 0; + int ret; - hclge_dbg_dump_mac_frame_size(hdev); + ret = hclge_dbg_dump_mac_enable_status(hdev, buf, len, &pos); + if (ret) + return ret; - hclge_dbg_dump_mac_speed_duplex(hdev); + ret = hclge_dbg_dump_mac_frame_size(hdev, buf, len, &pos); + if (ret) + return ret; + + return hclge_dbg_dump_mac_speed_duplex(hdev, buf, len, &pos); } -static void hclge_dbg_dump_dcb(struct hclge_dev *hdev, const char *cmd_buf) +static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len, + int *pos) { - struct device *dev = &hdev->pdev->dev; struct hclge_dbg_bitmap_cmd *bitmap; - enum hclge_opcode_type cmd; - int rq_id, pri_id, qset_id; - int port_id, nq_id, pg_id; - struct hclge_desc desc[2]; + struct hclge_desc desc; + u16 qset_id, qset_num; + int ret; - int cnt, ret; + ret = hclge_tm_get_qset_num(hdev, &qset_num); + if (ret) + return ret; - cnt = sscanf(cmd_buf, "%i %i %i %i %i %i", - &port_id, &pri_id, &pg_id, &rq_id, &nq_id, &qset_id); - if (cnt != 6) { - dev_err(&hdev->pdev->dev, - "dump dcb: bad command parameter, cnt=%d\n", cnt); - return; + *pos += scnprintf(buf + *pos, len - *pos, + "qset_id roce_qset_mask nic_qset_mask qset_shaping_pass qset_bp_status\n"); + for (qset_id = 0; qset_id < qset_num; qset_id++) { + ret = hclge_dbg_cmd_send(hdev, &desc, qset_id, 1, + HCLGE_OPC_QSET_DFX_STS); + if (ret) + return ret; + + bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1]; + + *pos += scnprintf(buf + *pos, len - *pos, + "%04u %#x %#x %#x %#x\n", + qset_id, bitmap->bit0, bitmap->bit1, + bitmap->bit2, bitmap->bit3); } - cmd = HCLGE_OPC_QSET_DFX_STS; - ret = hclge_dbg_cmd_send(hdev, desc, qset_id, 1, cmd); - if (ret) - goto err_dcb_cmd_send; - - bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1]; - dev_info(dev, "roce_qset_mask: 0x%x\n", bitmap->bit0); - dev_info(dev, "nic_qs_mask: 0x%x\n", bitmap->bit1); - dev_info(dev, "qs_shaping_pass: 0x%x\n", bitmap->bit2); - dev_info(dev, "qs_bp_sts: 0x%x\n", bitmap->bit3); - - cmd = HCLGE_OPC_PRI_DFX_STS; - ret = hclge_dbg_cmd_send(hdev, desc, pri_id, 1, cmd); - if (ret) - goto err_dcb_cmd_send; - - bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1]; - dev_info(dev, "pri_mask: 0x%x\n", bitmap->bit0); - dev_info(dev, "pri_cshaping_pass: 0x%x\n", bitmap->bit1); - dev_info(dev, "pri_pshaping_pass: 0x%x\n", bitmap->bit2); - - cmd = HCLGE_OPC_PG_DFX_STS; - ret = hclge_dbg_cmd_send(hdev, desc, pg_id, 1, cmd); - if (ret) - goto err_dcb_cmd_send; - - bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1]; - dev_info(dev, "pg_mask: 0x%x\n", bitmap->bit0); - dev_info(dev, "pg_cshaping_pass: 0x%x\n", bitmap->bit1); - dev_info(dev, "pg_pshaping_pass: 0x%x\n", bitmap->bit2); - - cmd = HCLGE_OPC_PORT_DFX_STS; - ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1, cmd); - if (ret) - goto err_dcb_cmd_send; - - bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1]; - dev_info(dev, "port_mask: 0x%x\n", bitmap->bit0); - dev_info(dev, "port_shaping_pass: 0x%x\n", bitmap->bit1); - - cmd = HCLGE_OPC_SCH_NQ_CNT; - ret = hclge_dbg_cmd_send(hdev, desc, nq_id, 1, cmd); - if (ret) - goto err_dcb_cmd_send; - - dev_info(dev, "sch_nq_cnt: 0x%x\n", le32_to_cpu(desc[0].data[1])); - - cmd = HCLGE_OPC_SCH_RQ_CNT; - ret = hclge_dbg_cmd_send(hdev, desc, nq_id, 1, cmd); - if (ret) - goto err_dcb_cmd_send; - - dev_info(dev, "sch_rq_cnt: 0x%x\n", le32_to_cpu(desc[0].data[1])); - - cmd = HCLGE_OPC_TM_INTERNAL_STS; - ret = hclge_dbg_cmd_send(hdev, desc, 0, 2, cmd); - if (ret) - goto err_dcb_cmd_send; - - dev_info(dev, "pri_bp: 0x%x\n", le32_to_cpu(desc[0].data[1])); - dev_info(dev, "fifo_dfx_info: 0x%x\n", le32_to_cpu(desc[0].data[2])); - dev_info(dev, "sch_roce_fifo_afull_gap: 0x%x\n", - le32_to_cpu(desc[0].data[3])); - dev_info(dev, "tx_private_waterline: 0x%x\n", - le32_to_cpu(desc[0].data[4])); - dev_info(dev, "tm_bypass_en: 0x%x\n", le32_to_cpu(desc[0].data[5])); - dev_info(dev, "SSU_TM_BYPASS_EN: 0x%x\n", le32_to_cpu(desc[1].data[0])); - dev_info(dev, "SSU_RESERVE_CFG: 0x%x\n", le32_to_cpu(desc[1].data[1])); - - cmd = HCLGE_OPC_TM_INTERNAL_CNT; - ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1, cmd); - if (ret) - goto err_dcb_cmd_send; - - dev_info(dev, "SCH_NIC_NUM: 0x%x\n", le32_to_cpu(desc[0].data[1])); - dev_info(dev, "SCH_ROCE_NUM: 0x%x\n", le32_to_cpu(desc[0].data[2])); - - cmd = HCLGE_OPC_TM_INTERNAL_STS_1; - ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1, cmd); - if (ret) - goto err_dcb_cmd_send; - - dev_info(dev, "TC_MAP_SEL: 0x%x\n", le32_to_cpu(desc[0].data[1])); - dev_info(dev, "IGU_PFC_PRI_EN: 0x%x\n", le32_to_cpu(desc[0].data[2])); - dev_info(dev, "MAC_PFC_PRI_EN: 0x%x\n", le32_to_cpu(desc[0].data[3])); - dev_info(dev, "IGU_PRI_MAP_TC_CFG: 0x%x\n", - le32_to_cpu(desc[0].data[4])); - dev_info(dev, "IGU_TX_PRI_MAP_TC_CFG: 0x%x\n", - le32_to_cpu(desc[0].data[5])); - return; - -err_dcb_cmd_send: - dev_err(&hdev->pdev->dev, - "failed to dump dcb dfx, cmd = %#x, ret = %d\n", - cmd, ret); + return 0; } -static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, const char *cmd_buf) +static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len, + int *pos) +{ + struct hclge_dbg_bitmap_cmd *bitmap; + struct hclge_desc desc; + u8 pri_id, pri_num; + int ret; + + ret = hclge_tm_get_pri_num(hdev, &pri_num); + if (ret) + return ret; + + *pos += scnprintf(buf + *pos, len - *pos, + "pri_id pri_mask pri_cshaping_pass pri_pshaping_pass\n"); + for (pri_id = 0; pri_id < pri_num; pri_id++) { + ret = hclge_dbg_cmd_send(hdev, &desc, pri_id, 1, + HCLGE_OPC_PRI_DFX_STS); + if (ret) + return ret; + + bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1]; + + *pos += scnprintf(buf + *pos, len - *pos, + "%03u %#x %#x %#x\n", + pri_id, bitmap->bit0, bitmap->bit1, + bitmap->bit2); + } + + return 0; +} + +static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len, + int *pos) +{ + struct hclge_dbg_bitmap_cmd *bitmap; + struct hclge_desc desc; + u8 pg_id; + int ret; + + *pos += scnprintf(buf + *pos, len - *pos, + "pg_id pg_mask pg_cshaping_pass pg_pshaping_pass\n"); + for (pg_id = 0; pg_id < hdev->tm_info.num_pg; pg_id++) { + ret = hclge_dbg_cmd_send(hdev, &desc, pg_id, 1, + HCLGE_OPC_PG_DFX_STS); + if (ret) + return ret; + + bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1]; + + *pos += scnprintf(buf + *pos, len - *pos, + "%03u %#x %#x %#x\n", + pg_id, bitmap->bit0, bitmap->bit1, + bitmap->bit2); + } + + return 0; +} + +static int hclge_dbg_dump_dcb_queue(struct hclge_dev *hdev, char *buf, int len, + int *pos) +{ + struct hclge_desc desc; + u16 nq_id; + int ret; + + *pos += scnprintf(buf + *pos, len - *pos, + "nq_id sch_nic_queue_cnt sch_roce_queue_cnt\n"); + for (nq_id = 0; nq_id < hdev->num_tqps; nq_id++) { + ret = hclge_dbg_cmd_send(hdev, &desc, nq_id, 1, + HCLGE_OPC_SCH_NQ_CNT); + if (ret) + return ret; + + *pos += scnprintf(buf + *pos, len - *pos, "%04u %#x", + nq_id, le32_to_cpu(desc.data[1])); + + ret = hclge_dbg_cmd_send(hdev, &desc, nq_id, 1, + HCLGE_OPC_SCH_RQ_CNT); + if (ret) + return ret; + + *pos += scnprintf(buf + *pos, len - *pos, + " %#x\n", + le32_to_cpu(desc.data[1])); + } + + return 0; +} + +static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len, + int *pos) +{ + struct hclge_dbg_bitmap_cmd *bitmap; + struct hclge_desc desc; + u8 port_id = 0; + int ret; + + ret = hclge_dbg_cmd_send(hdev, &desc, port_id, 1, + HCLGE_OPC_PORT_DFX_STS); + if (ret) + return ret; + + bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1]; + + *pos += scnprintf(buf + *pos, len - *pos, "port_mask: %#x\n", + bitmap->bit0); + *pos += scnprintf(buf + *pos, len - *pos, "port_shaping_pass: %#x\n", + bitmap->bit1); + + return 0; +} + +static int hclge_dbg_dump_dcb_tm(struct hclge_dev *hdev, char *buf, int len, + int *pos) +{ + struct hclge_desc desc[2]; + u8 port_id = 0; + int ret; + + ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1, + HCLGE_OPC_TM_INTERNAL_CNT); + if (ret) + return ret; + + *pos += scnprintf(buf + *pos, len - *pos, "SCH_NIC_NUM: %#x\n", + le32_to_cpu(desc[0].data[1])); + *pos += scnprintf(buf + *pos, len - *pos, "SCH_ROCE_NUM: %#x\n", + le32_to_cpu(desc[0].data[2])); + + ret = hclge_dbg_cmd_send(hdev, desc, port_id, 2, + HCLGE_OPC_TM_INTERNAL_STS); + if (ret) + return ret; + + *pos += scnprintf(buf + *pos, len - *pos, "pri_bp: %#x\n", + le32_to_cpu(desc[0].data[1])); + *pos += scnprintf(buf + *pos, len - *pos, "fifo_dfx_info: %#x\n", + le32_to_cpu(desc[0].data[2])); + *pos += scnprintf(buf + *pos, len - *pos, + "sch_roce_fifo_afull_gap: %#x\n", + le32_to_cpu(desc[0].data[3])); + *pos += scnprintf(buf + *pos, len - *pos, + "tx_private_waterline: %#x\n", + le32_to_cpu(desc[0].data[4])); + *pos += scnprintf(buf + *pos, len - *pos, "tm_bypass_en: %#x\n", + le32_to_cpu(desc[0].data[5])); + *pos += scnprintf(buf + *pos, len - *pos, "SSU_TM_BYPASS_EN: %#x\n", + le32_to_cpu(desc[1].data[0])); + *pos += scnprintf(buf + *pos, len - *pos, "SSU_RESERVE_CFG: %#x\n", + le32_to_cpu(desc[1].data[1])); + + if (hdev->hw.mac.media_type == HNAE3_MEDIA_TYPE_COPPER) + return 0; + + ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1, + HCLGE_OPC_TM_INTERNAL_STS_1); + if (ret) + return ret; + + *pos += scnprintf(buf + *pos, len - *pos, "TC_MAP_SEL: %#x\n", + le32_to_cpu(desc[0].data[1])); + *pos += scnprintf(buf + *pos, len - *pos, "IGU_PFC_PRI_EN: %#x\n", + le32_to_cpu(desc[0].data[2])); + *pos += scnprintf(buf + *pos, len - *pos, "MAC_PFC_PRI_EN: %#x\n", + le32_to_cpu(desc[0].data[3])); + *pos += scnprintf(buf + *pos, len - *pos, "IGU_PRI_MAP_TC_CFG: %#x\n", + le32_to_cpu(desc[0].data[4])); + *pos += scnprintf(buf + *pos, len - *pos, + "IGU_TX_PRI_MAP_TC_CFG: %#x\n", + le32_to_cpu(desc[0].data[5])); + + return 0; +} + +static int hclge_dbg_dump_dcb(struct hclge_dev *hdev, char *buf, int len) +{ + int pos = 0; + int ret; + + ret = hclge_dbg_dump_dcb_qset(hdev, buf, len, &pos); + if (ret) + return ret; + + ret = hclge_dbg_dump_dcb_pri(hdev, buf, len, &pos); + if (ret) + return ret; + + ret = hclge_dbg_dump_dcb_pg(hdev, buf, len, &pos); + if (ret) + return ret; + + ret = hclge_dbg_dump_dcb_queue(hdev, buf, len, &pos); + if (ret) + return ret; + + ret = hclge_dbg_dump_dcb_port(hdev, buf, len, &pos); + if (ret) + return ret; + + return hclge_dbg_dump_dcb_tm(hdev, buf, len, &pos); +} + +static int hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, + enum hnae3_dbg_cmd cmd, char *buf, int len) { const struct hclge_dbg_reg_type_info *reg_info; - bool has_dump = false; + int pos = 0, ret = 0; int i; for (i = 0; i < ARRAY_SIZE(hclge_dbg_reg_info); i++) { reg_info = &hclge_dbg_reg_info[i]; - if (!strncmp(cmd_buf, reg_info->reg_type, - strlen(reg_info->reg_type))) { - hclge_dbg_dump_reg_common(hdev, reg_info, cmd_buf); - has_dump = true; + if (cmd == reg_info->cmd) { + if (cmd == HNAE3_DBG_CMD_REG_TQP) + return hclge_dbg_dump_reg_tqp(hdev, reg_info, + buf, len, &pos); + + ret = hclge_dbg_dump_reg_common(hdev, reg_info, buf, + len, &pos); + if (ret) + break; } } - if (strncmp(cmd_buf, "mac", strlen("mac")) == 0) { - hclge_dbg_dump_mac(hdev); - has_dump = true; - } - - if (strncmp(cmd_buf, "dcb", 3) == 0) { - hclge_dbg_dump_dcb(hdev, &cmd_buf[sizeof("dcb")]); - has_dump = true; - } - - if (!has_dump) { - dev_info(&hdev->pdev->dev, "unknown command\n"); - return; - } + return ret; } -static void hclge_print_tc_info(struct hclge_dev *hdev, bool flag, int index) -{ - if (flag) - dev_info(&hdev->pdev->dev, "tc(%d): no sp mode weight: %u\n", - index, hdev->tm_info.pg_info[0].tc_dwrr[index]); - else - dev_info(&hdev->pdev->dev, "tc(%d): sp mode\n", index); -} - -static void hclge_dbg_dump_tc(struct hclge_dev *hdev) +static int hclge_dbg_dump_tc(struct hclge_dev *hdev, char *buf, int len) { struct hclge_ets_tc_weight_cmd *ets_weight; struct hclge_desc desc; - int i, ret; + char *sch_mode_str; + int pos = 0; + int ret; + u8 i; if (!hnae3_dev_dcb_supported(hdev)) { - dev_info(&hdev->pdev->dev, - "Only DCB-supported dev supports tc\n"); - return; + dev_err(&hdev->pdev->dev, + "Only DCB-supported dev supports tc\n"); + return -EOPNOTSUPP; } hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ETS_TC_WEIGHT, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { - dev_err(&hdev->pdev->dev, "dump tc fail, ret = %d\n", ret); - return; + dev_err(&hdev->pdev->dev, "failed to get tc weight, ret = %d\n", + ret); + return ret; } ets_weight = (struct hclge_ets_tc_weight_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "dump tc: %u tc enabled\n", - hdev->tm_info.num_tc); - dev_info(&hdev->pdev->dev, "weight_offset: %u\n", - ets_weight->weight_offset); + pos += scnprintf(buf + pos, len - pos, "enabled tc number: %u\n", + hdev->tm_info.num_tc); + pos += scnprintf(buf + pos, len - pos, "weight_offset: %u\n", + ets_weight->weight_offset); - for (i = 0; i < HNAE3_MAX_TC; i++) - hclge_print_tc_info(hdev, ets_weight->tc_weight[i], i); -} - -static void hclge_dbg_dump_tm_pg(struct hclge_dev *hdev) -{ - struct hclge_port_shapping_cmd *port_shap_cfg_cmd; - struct hclge_bp_to_qs_map_cmd *bp_to_qs_map_cmd; - struct hclge_pg_shapping_cmd *pg_shap_cfg_cmd; - enum hclge_opcode_type cmd; - struct hclge_desc desc; - int ret; - - cmd = HCLGE_OPC_TM_PG_C_SHAPPING; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_pg_cmd_send; - - pg_shap_cfg_cmd = (struct hclge_pg_shapping_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "PG_C pg_id: %u\n", pg_shap_cfg_cmd->pg_id); - dev_info(&hdev->pdev->dev, "PG_C pg_shapping: 0x%x\n", - le32_to_cpu(pg_shap_cfg_cmd->pg_shapping_para)); - - cmd = HCLGE_OPC_TM_PG_P_SHAPPING; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_pg_cmd_send; - - pg_shap_cfg_cmd = (struct hclge_pg_shapping_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "PG_P pg_id: %u\n", pg_shap_cfg_cmd->pg_id); - dev_info(&hdev->pdev->dev, "PG_P pg_shapping: 0x%x\n", - le32_to_cpu(pg_shap_cfg_cmd->pg_shapping_para)); - dev_info(&hdev->pdev->dev, "PG_P flag: %#x\n", pg_shap_cfg_cmd->flag); - dev_info(&hdev->pdev->dev, "PG_P pg_rate: %u(Mbps)\n", - le32_to_cpu(pg_shap_cfg_cmd->pg_rate)); - - cmd = HCLGE_OPC_TM_PORT_SHAPPING; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_pg_cmd_send; - - port_shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "PORT port_shapping: 0x%x\n", - le32_to_cpu(port_shap_cfg_cmd->port_shapping_para)); - dev_info(&hdev->pdev->dev, "PORT flag: %#x\n", port_shap_cfg_cmd->flag); - dev_info(&hdev->pdev->dev, "PORT port_rate: %u(Mbps)\n", - le32_to_cpu(port_shap_cfg_cmd->port_rate)); - - cmd = HCLGE_OPC_TM_PG_SCH_MODE_CFG; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_pg_cmd_send; - - dev_info(&hdev->pdev->dev, "PG_SCH pg_id: %u\n", - le32_to_cpu(desc.data[0])); - - cmd = HCLGE_OPC_TM_PRI_SCH_MODE_CFG; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_pg_cmd_send; - - dev_info(&hdev->pdev->dev, "PRI_SCH pri_id: %u\n", - le32_to_cpu(desc.data[0])); - - cmd = HCLGE_OPC_TM_QS_SCH_MODE_CFG; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_pg_cmd_send; - - dev_info(&hdev->pdev->dev, "QS_SCH qs_id: %u\n", - le32_to_cpu(desc.data[0])); - - if (!hnae3_dev_dcb_supported(hdev)) { - dev_info(&hdev->pdev->dev, - "Only DCB-supported dev supports tm mapping\n"); - return; + pos += scnprintf(buf + pos, len - pos, "TC MODE WEIGHT\n"); + for (i = 0; i < HNAE3_MAX_TC; i++) { + sch_mode_str = ets_weight->tc_weight[i] ? "dwrr" : "sp"; + pos += scnprintf(buf + pos, len - pos, "%u %4s %3u\n", + i, sch_mode_str, + hdev->tm_info.pg_info[0].tc_dwrr[i]); } - cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_pg_cmd_send; - - bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "BP_TO_QSET tc_id: %u\n", - bp_to_qs_map_cmd->tc_id); - dev_info(&hdev->pdev->dev, "BP_TO_QSET qs_group_id: 0x%x\n", - bp_to_qs_map_cmd->qs_group_id); - dev_info(&hdev->pdev->dev, "BP_TO_QSET qs_bit_map: 0x%x\n", - le32_to_cpu(bp_to_qs_map_cmd->qs_bit_map)); - return; - -err_tm_pg_cmd_send: - dev_err(&hdev->pdev->dev, "dump tm_pg fail(0x%x), ret = %d\n", - cmd, ret); + return 0; } -static void hclge_dbg_dump_tm(struct hclge_dev *hdev) +static const struct hclge_dbg_item tm_pg_items[] = { + { "ID", 2 }, + { "PRI_MAP", 2 }, + { "MODE", 2 }, + { "DWRR", 2 }, + { "C_IR_B", 2 }, + { "C_IR_U", 2 }, + { "C_IR_S", 2 }, + { "C_BS_B", 2 }, + { "C_BS_S", 2 }, + { "C_FLAG", 2 }, + { "C_RATE(Mbps)", 2 }, + { "P_IR_B", 2 }, + { "P_IR_U", 2 }, + { "P_IR_S", 2 }, + { "P_BS_B", 2 }, + { "P_BS_S", 2 }, + { "P_FLAG", 2 }, + { "P_RATE(Mbps)", 0 } +}; + +static void hclge_dbg_fill_shaper_content(struct hclge_tm_shaper_para *para, + char **result, u8 *index) { - struct hclge_priority_weight_cmd *priority_weight; - struct hclge_pg_to_pri_link_cmd *pg_to_pri_map; - struct hclge_qs_to_pri_link_cmd *qs_to_pri_map; - struct hclge_nq_to_qs_link_cmd *nq_to_qs_map; - struct hclge_pri_shapping_cmd *shap_cfg_cmd; - struct hclge_pg_weight_cmd *pg_weight; - struct hclge_qs_weight_cmd *qs_weight; - enum hclge_opcode_type cmd; - struct hclge_desc desc; + sprintf(result[(*index)++], "%3u", para->ir_b); + sprintf(result[(*index)++], "%3u", para->ir_u); + sprintf(result[(*index)++], "%3u", para->ir_s); + sprintf(result[(*index)++], "%3u", para->bs_b); + sprintf(result[(*index)++], "%3u", para->bs_s); + sprintf(result[(*index)++], "%3u", para->flag); + sprintf(result[(*index)++], "%6u", para->rate); +} + +static int hclge_dbg_dump_tm_pg(struct hclge_dev *hdev, char *buf, int len) +{ + char data_str[ARRAY_SIZE(tm_pg_items)][HCLGE_DBG_DATA_STR_LEN]; + struct hclge_tm_shaper_para c_shaper_para, p_shaper_para; + char *result[ARRAY_SIZE(tm_pg_items)], *sch_mode_str; + u8 pg_id, sch_mode, weight, pri_bit_map, i, j; + char content[HCLGE_DBG_TM_INFO_LEN]; + int pos = 0; int ret; - cmd = HCLGE_OPC_TM_PG_TO_PRI_LINK; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_cmd_send; + for (i = 0; i < ARRAY_SIZE(tm_pg_items); i++) + result[i] = &data_str[i][0]; - pg_to_pri_map = (struct hclge_pg_to_pri_link_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "dump tm\n"); - dev_info(&hdev->pdev->dev, "PG_TO_PRI gp_id: %u\n", - pg_to_pri_map->pg_id); - dev_info(&hdev->pdev->dev, "PG_TO_PRI map: 0x%x\n", - pg_to_pri_map->pri_bit_map); + hclge_dbg_fill_content(content, sizeof(content), tm_pg_items, + NULL, ARRAY_SIZE(tm_pg_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); - cmd = HCLGE_OPC_TM_QS_TO_PRI_LINK; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_cmd_send; + for (pg_id = 0; pg_id < hdev->tm_info.num_pg; pg_id++) { + ret = hclge_tm_get_pg_to_pri_map(hdev, pg_id, &pri_bit_map); + if (ret) + return ret; - qs_to_pri_map = (struct hclge_qs_to_pri_link_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "QS_TO_PRI qs_id: %u\n", - le16_to_cpu(qs_to_pri_map->qs_id)); - dev_info(&hdev->pdev->dev, "QS_TO_PRI priority: %u\n", - qs_to_pri_map->priority); - dev_info(&hdev->pdev->dev, "QS_TO_PRI link_vld: %u\n", - qs_to_pri_map->link_vld); + ret = hclge_tm_get_pg_sch_mode(hdev, pg_id, &sch_mode); + if (ret) + return ret; - cmd = HCLGE_OPC_TM_NQ_TO_QS_LINK; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_cmd_send; + ret = hclge_tm_get_pg_weight(hdev, pg_id, &weight); + if (ret) + return ret; - nq_to_qs_map = (struct hclge_nq_to_qs_link_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "NQ_TO_QS nq_id: %u\n", - le16_to_cpu(nq_to_qs_map->nq_id)); - dev_info(&hdev->pdev->dev, "NQ_TO_QS qset_id: 0x%x\n", - le16_to_cpu(nq_to_qs_map->qset_id)); + ret = hclge_tm_get_pg_shaper(hdev, pg_id, + HCLGE_OPC_TM_PG_C_SHAPPING, + &c_shaper_para); + if (ret) + return ret; - cmd = HCLGE_OPC_TM_PG_WEIGHT; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_cmd_send; + ret = hclge_tm_get_pg_shaper(hdev, pg_id, + HCLGE_OPC_TM_PG_P_SHAPPING, + &p_shaper_para); + if (ret) + return ret; - pg_weight = (struct hclge_pg_weight_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "PG pg_id: %u\n", pg_weight->pg_id); - dev_info(&hdev->pdev->dev, "PG dwrr: %u\n", pg_weight->dwrr); + sch_mode_str = sch_mode & HCLGE_TM_TX_SCHD_DWRR_MSK ? "dwrr" : + "sp"; - cmd = HCLGE_OPC_TM_QS_WEIGHT; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_cmd_send; + j = 0; + sprintf(result[j++], "%02u", pg_id); + sprintf(result[j++], "0x%02x", pri_bit_map); + sprintf(result[j++], "%4s", sch_mode_str); + sprintf(result[j++], "%3u", weight); + hclge_dbg_fill_shaper_content(&c_shaper_para, result, &j); + hclge_dbg_fill_shaper_content(&p_shaper_para, result, &j); - qs_weight = (struct hclge_qs_weight_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "QS qs_id: %u\n", - le16_to_cpu(qs_weight->qs_id)); - dev_info(&hdev->pdev->dev, "QS dwrr: %u\n", qs_weight->dwrr); + hclge_dbg_fill_content(content, sizeof(content), tm_pg_items, + (const char **)result, + ARRAY_SIZE(tm_pg_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + } - cmd = HCLGE_OPC_TM_PRI_WEIGHT; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_cmd_send; - - priority_weight = (struct hclge_priority_weight_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "PRI pri_id: %u\n", priority_weight->pri_id); - dev_info(&hdev->pdev->dev, "PRI dwrr: %u\n", priority_weight->dwrr); - - cmd = HCLGE_OPC_TM_PRI_C_SHAPPING; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_cmd_send; - - shap_cfg_cmd = (struct hclge_pri_shapping_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "PRI_C pri_id: %u\n", shap_cfg_cmd->pri_id); - dev_info(&hdev->pdev->dev, "PRI_C pri_shapping: 0x%x\n", - le32_to_cpu(shap_cfg_cmd->pri_shapping_para)); - dev_info(&hdev->pdev->dev, "PRI_C flag: %#x\n", shap_cfg_cmd->flag); - dev_info(&hdev->pdev->dev, "PRI_C pri_rate: %u(Mbps)\n", - le32_to_cpu(shap_cfg_cmd->pri_rate)); - - cmd = HCLGE_OPC_TM_PRI_P_SHAPPING; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_cmd_send; - - shap_cfg_cmd = (struct hclge_pri_shapping_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "PRI_P pri_id: %u\n", shap_cfg_cmd->pri_id); - dev_info(&hdev->pdev->dev, "PRI_P pri_shapping: 0x%x\n", - le32_to_cpu(shap_cfg_cmd->pri_shapping_para)); - dev_info(&hdev->pdev->dev, "PRI_P flag: %#x\n", shap_cfg_cmd->flag); - dev_info(&hdev->pdev->dev, "PRI_P pri_rate: %u(Mbps)\n", - le32_to_cpu(shap_cfg_cmd->pri_rate)); - - hclge_dbg_dump_tm_pg(hdev); - - return; - -err_tm_cmd_send: - dev_err(&hdev->pdev->dev, "dump tm fail(0x%x), ret = %d\n", - cmd, ret); + return 0; } -static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev, - const char *cmd_buf) +static int hclge_dbg_dump_tm_port(struct hclge_dev *hdev, char *buf, int len) +{ + struct hclge_tm_shaper_para shaper_para; + int pos = 0; + int ret; + + ret = hclge_tm_get_port_shaper(hdev, &shaper_para); + if (ret) + return ret; + + pos += scnprintf(buf + pos, len - pos, + "IR_B IR_U IR_S BS_B BS_S FLAG RATE(Mbps)\n"); + pos += scnprintf(buf + pos, len - pos, + "%3u %3u %3u %3u %3u %1u %6u\n", + shaper_para.ir_b, shaper_para.ir_u, shaper_para.ir_s, + shaper_para.bs_b, shaper_para.bs_s, shaper_para.flag, + shaper_para.rate); + + return 0; +} + +static int hclge_dbg_dump_tm_bp_qset_map(struct hclge_dev *hdev, u8 tc_id, + char *buf, int len) { - struct hclge_bp_to_qs_map_cmd *bp_to_qs_map_cmd; - struct hclge_nq_to_qs_link_cmd *nq_to_qs_map; u32 qset_mapping[HCLGE_BP_EXT_GRP_NUM]; - struct hclge_qs_to_pri_link_cmd *map; - struct hclge_tqp_tx_queue_tc_cmd *tc; - u16 group_id, queue_id, qset_id; - enum hclge_opcode_type cmd; - u8 grp_num, pri_id, tc_id; + struct hclge_bp_to_qs_map_cmd *map; struct hclge_desc desc; - u16 qs_id_l; - u16 qs_id_h; + int pos = 0; + u8 group_id; + u8 grp_num; + u16 i = 0; int ret; - u32 i; - - ret = kstrtou16(cmd_buf, 0, &queue_id); - queue_id = (ret != 0) ? 0 : queue_id; - - cmd = HCLGE_OPC_TM_NQ_TO_QS_LINK; - nq_to_qs_map = (struct hclge_nq_to_qs_link_cmd *)desc.data; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - nq_to_qs_map->nq_id = cpu_to_le16(queue_id); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_map_cmd_send; - qset_id = le16_to_cpu(nq_to_qs_map->qset_id); - - /* convert qset_id to the following format, drop the vld bit - * | qs_id_h | vld | qs_id_l | - * qset_id: | 15 ~ 11 | 10 | 9 ~ 0 | - * \ \ / / - * \ \ / / - * qset_id: | 15 | 14 ~ 10 | 9 ~ 0 | - */ - qs_id_l = hnae3_get_field(qset_id, HCLGE_TM_QS_ID_L_MSK, - HCLGE_TM_QS_ID_L_S); - qs_id_h = hnae3_get_field(qset_id, HCLGE_TM_QS_ID_H_EXT_MSK, - HCLGE_TM_QS_ID_H_EXT_S); - qset_id = 0; - hnae3_set_field(qset_id, HCLGE_TM_QS_ID_L_MSK, HCLGE_TM_QS_ID_L_S, - qs_id_l); - hnae3_set_field(qset_id, HCLGE_TM_QS_ID_H_MSK, HCLGE_TM_QS_ID_H_S, - qs_id_h); - - cmd = HCLGE_OPC_TM_QS_TO_PRI_LINK; - map = (struct hclge_qs_to_pri_link_cmd *)desc.data; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - map->qs_id = cpu_to_le16(qset_id); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_map_cmd_send; - pri_id = map->priority; - - cmd = HCLGE_OPC_TQP_TX_QUEUE_TC; - tc = (struct hclge_tqp_tx_queue_tc_cmd *)desc.data; - hclge_cmd_setup_basic_desc(&desc, cmd, true); - tc->queue_id = cpu_to_le16(queue_id); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_map_cmd_send; - tc_id = tc->tc_id & 0x7; - - dev_info(&hdev->pdev->dev, "queue_id | qset_id | pri_id | tc_id\n"); - dev_info(&hdev->pdev->dev, "%04u | %04u | %02u | %02u\n", - queue_id, qset_id, pri_id, tc_id); - - if (!hnae3_dev_dcb_supported(hdev)) { - dev_info(&hdev->pdev->dev, - "Only DCB-supported dev supports tm mapping\n"); - return; - } grp_num = hdev->num_tqps <= HCLGE_TQP_MAX_SIZE_DEV_V2 ? HCLGE_BP_GRP_NUM : HCLGE_BP_EXT_GRP_NUM; - cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING; - bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data; + map = (struct hclge_bp_to_qs_map_cmd *)desc.data; for (group_id = 0; group_id < grp_num; group_id++) { - hclge_cmd_setup_basic_desc(&desc, cmd, true); - bp_to_qs_map_cmd->tc_id = tc_id; - bp_to_qs_map_cmd->qs_group_id = group_id; + hclge_cmd_setup_basic_desc(&desc, + HCLGE_OPC_TM_BP_TO_QSET_MAPPING, + true); + map->tc_id = tc_id; + map->qs_group_id = group_id; ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - goto err_tm_map_cmd_send; + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get bp to qset map, ret = %d\n", + ret); + return ret; + } - qset_mapping[group_id] = - le32_to_cpu(bp_to_qs_map_cmd->qs_bit_map); + qset_mapping[group_id] = le32_to_cpu(map->qs_bit_map); } - dev_info(&hdev->pdev->dev, "index | tm bp qset maping:\n"); - - i = 0; + pos += scnprintf(buf + pos, len - pos, "INDEX | TM BP QSET MAPPING:\n"); for (group_id = 0; group_id < grp_num / 8; group_id++) { - dev_info(&hdev->pdev->dev, + pos += scnprintf(buf + pos, len - pos, "%04d | %08x:%08x:%08x:%08x:%08x:%08x:%08x:%08x\n", - group_id * 256, qset_mapping[(u32)(i + 7)], - qset_mapping[(u32)(i + 6)], qset_mapping[(u32)(i + 5)], - qset_mapping[(u32)(i + 4)], qset_mapping[(u32)(i + 3)], - qset_mapping[(u32)(i + 2)], qset_mapping[(u32)(i + 1)], + group_id * 256, qset_mapping[i + 7], + qset_mapping[i + 6], qset_mapping[i + 5], + qset_mapping[i + 4], qset_mapping[i + 3], + qset_mapping[i + 2], qset_mapping[i + 1], qset_mapping[i]); i += 8; } - return; + return pos; +} -err_tm_map_cmd_send: - dev_err(&hdev->pdev->dev, "dump tqp map fail(0x%x), ret = %d\n", - cmd, ret); +static int hclge_dbg_dump_tm_map(struct hclge_dev *hdev, char *buf, int len) +{ + u16 queue_id; + u16 qset_id; + u8 link_vld; + int pos = 0; + u8 pri_id; + u8 tc_id; + int ret; + + for (queue_id = 0; queue_id < hdev->num_tqps; queue_id++) { + ret = hclge_tm_get_q_to_qs_map(hdev, queue_id, &qset_id); + if (ret) + return ret; + + ret = hclge_tm_get_qset_map_pri(hdev, qset_id, &pri_id, + &link_vld); + if (ret) + return ret; + + ret = hclge_tm_get_q_to_tc(hdev, queue_id, &tc_id); + if (ret) + return ret; + + pos += scnprintf(buf + pos, len - pos, + "QUEUE_ID QSET_ID PRI_ID TC_ID\n"); + pos += scnprintf(buf + pos, len - pos, + "%04u %4u %3u %2u\n", + queue_id, qset_id, pri_id, tc_id); + + if (!hnae3_dev_dcb_supported(hdev)) + continue; + + ret = hclge_dbg_dump_tm_bp_qset_map(hdev, tc_id, buf + pos, + len - pos); + if (ret < 0) + return ret; + pos += ret; + + pos += scnprintf(buf + pos, len - pos, "\n"); + } + + return 0; } static int hclge_dbg_dump_tm_nodes(struct hclge_dev *hdev, char *buf, int len) @@ -833,8 +928,8 @@ static int hclge_dbg_dump_tm_nodes(struct hclge_dev *hdev, char *buf, int len) static int hclge_dbg_dump_tm_pri(struct hclge_dev *hdev, char *buf, int len) { - struct hclge_pri_shaper_para c_shaper_para; - struct hclge_pri_shaper_para p_shaper_para; + struct hclge_tm_shaper_para c_shaper_para; + struct hclge_tm_shaper_para p_shaper_para; u8 pri_num, sch_mode, weight; char *sch_mode_str; int pos = 0; @@ -896,19 +991,42 @@ static int hclge_dbg_dump_tm_pri(struct hclge_dev *hdev, char *buf, int len) return 0; } +static const struct hclge_dbg_item tm_qset_items[] = { + { "ID", 4 }, + { "MAP_PRI", 2 }, + { "LINK_VLD", 2 }, + { "MODE", 2 }, + { "DWRR", 2 }, + { "IR_B", 2 }, + { "IR_U", 2 }, + { "IR_S", 2 }, + { "BS_B", 2 }, + { "BS_S", 2 }, + { "FLAG", 2 }, + { "RATE(Mbps)", 0 } +}; + static int hclge_dbg_dump_tm_qset(struct hclge_dev *hdev, char *buf, int len) { + char data_str[ARRAY_SIZE(tm_qset_items)][HCLGE_DBG_DATA_STR_LEN]; + char *result[ARRAY_SIZE(tm_qset_items)], *sch_mode_str; u8 priority, link_vld, sch_mode, weight; - char *sch_mode_str; + struct hclge_tm_shaper_para shaper_para; + char content[HCLGE_DBG_TM_INFO_LEN]; + u16 qset_num, i; int ret, pos; - u16 qset_num; - u16 i; + u8 j; ret = hclge_tm_get_qset_num(hdev, &qset_num); if (ret) return ret; - pos = scnprintf(buf, len, "ID MAP_PRI LINK_VLD MODE DWRR\n"); + for (i = 0; i < ARRAY_SIZE(tm_qset_items); i++) + result[i] = &data_str[i][0]; + + hclge_dbg_fill_content(content, sizeof(content), tm_qset_items, + NULL, ARRAY_SIZE(tm_qset_items)); + pos = scnprintf(buf, len, "%s", content); for (i = 0; i < qset_num; i++) { ret = hclge_tm_get_qset_map_pri(hdev, i, &priority, &link_vld); @@ -923,280 +1041,326 @@ static int hclge_dbg_dump_tm_qset(struct hclge_dev *hdev, char *buf, int len) if (ret) return ret; + ret = hclge_tm_get_qset_shaper(hdev, i, &shaper_para); + if (ret) + return ret; + sch_mode_str = sch_mode & HCLGE_TM_TX_SCHD_DWRR_MSK ? "dwrr" : "sp"; - pos += scnprintf(buf + pos, len - pos, - "%04u %4u %1u %4s %3u\n", - i, priority, link_vld, sch_mode_str, weight); + + j = 0; + sprintf(result[j++], "%04u", i); + sprintf(result[j++], "%4u", priority); + sprintf(result[j++], "%4u", link_vld); + sprintf(result[j++], "%4s", sch_mode_str); + sprintf(result[j++], "%3u", weight); + hclge_dbg_fill_shaper_content(&shaper_para, result, &j); + + hclge_dbg_fill_content(content, sizeof(content), tm_qset_items, + (const char **)result, + ARRAY_SIZE(tm_qset_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); } return 0; } -static void hclge_dbg_dump_qos_pause_cfg(struct hclge_dev *hdev) +static int hclge_dbg_dump_qos_pause_cfg(struct hclge_dev *hdev, char *buf, + int len) { struct hclge_cfg_pause_param_cmd *pause_param; struct hclge_desc desc; + int pos = 0; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_MAC_PARA, true); - - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) { - dev_err(&hdev->pdev->dev, "dump checksum fail, ret = %d\n", - ret); - return; - } - - pause_param = (struct hclge_cfg_pause_param_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "dump qos pause cfg\n"); - dev_info(&hdev->pdev->dev, "pause_trans_gap: 0x%x\n", - pause_param->pause_trans_gap); - dev_info(&hdev->pdev->dev, "pause_trans_time: 0x%x\n", - le16_to_cpu(pause_param->pause_trans_time)); -} - -static void hclge_dbg_dump_qos_pri_map(struct hclge_dev *hdev) -{ - struct hclge_qos_pri_map_cmd *pri_map; - struct hclge_desc desc; - int ret; - - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PRI_TO_TC_MAPPING, true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { dev_err(&hdev->pdev->dev, - "dump qos pri map fail, ret = %d\n", ret); - return; + "failed to dump qos pause, ret = %d\n", ret); + return ret; + } + + pause_param = (struct hclge_cfg_pause_param_cmd *)desc.data; + + pos += scnprintf(buf + pos, len - pos, "pause_trans_gap: 0x%x\n", + pause_param->pause_trans_gap); + pos += scnprintf(buf + pos, len - pos, "pause_trans_time: 0x%x\n", + le16_to_cpu(pause_param->pause_trans_time)); + return 0; +} + +static int hclge_dbg_dump_qos_pri_map(struct hclge_dev *hdev, char *buf, + int len) +{ +#define HCLGE_DBG_TC_MASK 0x0F +#define HCLGE_DBG_TC_BIT_WIDTH 4 + + struct hclge_qos_pri_map_cmd *pri_map; + struct hclge_desc desc; + int pos = 0; + u8 *pri_tc; + u8 tc, i; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PRI_TO_TC_MAPPING, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump qos pri map, ret = %d\n", ret); + return ret; } pri_map = (struct hclge_qos_pri_map_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "dump qos pri map\n"); - dev_info(&hdev->pdev->dev, "vlan_to_pri: 0x%x\n", pri_map->vlan_pri); - dev_info(&hdev->pdev->dev, "pri_0_to_tc: 0x%x\n", pri_map->pri0_tc); - dev_info(&hdev->pdev->dev, "pri_1_to_tc: 0x%x\n", pri_map->pri1_tc); - dev_info(&hdev->pdev->dev, "pri_2_to_tc: 0x%x\n", pri_map->pri2_tc); - dev_info(&hdev->pdev->dev, "pri_3_to_tc: 0x%x\n", pri_map->pri3_tc); - dev_info(&hdev->pdev->dev, "pri_4_to_tc: 0x%x\n", pri_map->pri4_tc); - dev_info(&hdev->pdev->dev, "pri_5_to_tc: 0x%x\n", pri_map->pri5_tc); - dev_info(&hdev->pdev->dev, "pri_6_to_tc: 0x%x\n", pri_map->pri6_tc); - dev_info(&hdev->pdev->dev, "pri_7_to_tc: 0x%x\n", pri_map->pri7_tc); + + pos += scnprintf(buf + pos, len - pos, "vlan_to_pri: 0x%x\n", + pri_map->vlan_pri); + pos += scnprintf(buf + pos, len - pos, "PRI TC\n"); + + pri_tc = (u8 *)pri_map; + for (i = 0; i < HNAE3_MAX_TC; i++) { + tc = pri_tc[i >> 1] >> ((i & 1) * HCLGE_DBG_TC_BIT_WIDTH); + tc &= HCLGE_DBG_TC_MASK; + pos += scnprintf(buf + pos, len - pos, "%u %u\n", i, tc); + } + + return 0; } -static int hclge_dbg_dump_tx_buf_cfg(struct hclge_dev *hdev) +static int hclge_dbg_dump_tx_buf_cfg(struct hclge_dev *hdev, char *buf, int len) { struct hclge_tx_buff_alloc_cmd *tx_buf_cmd; struct hclge_desc desc; + int pos = 0; int i, ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump tx buf, ret = %d\n", ret); return ret; + } - dev_info(&hdev->pdev->dev, "dump qos buf cfg\n"); tx_buf_cmd = (struct hclge_tx_buff_alloc_cmd *)desc.data; for (i = 0; i < HCLGE_MAX_TC_NUM; i++) - dev_info(&hdev->pdev->dev, "tx_packet_buf_tc_%d: 0x%x\n", i, - le16_to_cpu(tx_buf_cmd->tx_pkt_buff[i])); + pos += scnprintf(buf + pos, len - pos, + "tx_packet_buf_tc_%d: 0x%x\n", i, + le16_to_cpu(tx_buf_cmd->tx_pkt_buff[i])); - return 0; + return pos; } -static int hclge_dbg_dump_rx_priv_buf_cfg(struct hclge_dev *hdev) +static int hclge_dbg_dump_rx_priv_buf_cfg(struct hclge_dev *hdev, char *buf, + int len) { struct hclge_rx_priv_buff_cmd *rx_buf_cmd; struct hclge_desc desc; + int pos = 0; int i, ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_PRIV_BUFF_ALLOC, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump rx priv buf, ret = %d\n", ret); return ret; + } + + pos += scnprintf(buf + pos, len - pos, "\n"); - dev_info(&hdev->pdev->dev, "\n"); rx_buf_cmd = (struct hclge_rx_priv_buff_cmd *)desc.data; for (i = 0; i < HCLGE_MAX_TC_NUM; i++) - dev_info(&hdev->pdev->dev, "rx_packet_buf_tc_%d: 0x%x\n", i, - le16_to_cpu(rx_buf_cmd->buf_num[i])); + pos += scnprintf(buf + pos, len - pos, + "rx_packet_buf_tc_%d: 0x%x\n", i, + le16_to_cpu(rx_buf_cmd->buf_num[i])); - dev_info(&hdev->pdev->dev, "rx_share_buf: 0x%x\n", - le16_to_cpu(rx_buf_cmd->shared_buf)); + pos += scnprintf(buf + pos, len - pos, "rx_share_buf: 0x%x\n", + le16_to_cpu(rx_buf_cmd->shared_buf)); - return 0; + return pos; } -static int hclge_dbg_dump_rx_common_wl_cfg(struct hclge_dev *hdev) +static int hclge_dbg_dump_rx_common_wl_cfg(struct hclge_dev *hdev, char *buf, + int len) { struct hclge_rx_com_wl *rx_com_wl; struct hclge_desc desc; + int pos = 0; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_COM_WL_ALLOC, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump rx common wl, ret = %d\n", ret); return ret; + } rx_com_wl = (struct hclge_rx_com_wl *)desc.data; - dev_info(&hdev->pdev->dev, "\n"); - dev_info(&hdev->pdev->dev, "rx_com_wl: high: 0x%x, low: 0x%x\n", - le16_to_cpu(rx_com_wl->com_wl.high), - le16_to_cpu(rx_com_wl->com_wl.low)); + pos += scnprintf(buf + pos, len - pos, "\n"); + pos += scnprintf(buf + pos, len - pos, + "rx_com_wl: high: 0x%x, low: 0x%x\n", + le16_to_cpu(rx_com_wl->com_wl.high), + le16_to_cpu(rx_com_wl->com_wl.low)); - return 0; + return pos; } -static int hclge_dbg_dump_rx_global_pkt_cnt(struct hclge_dev *hdev) +static int hclge_dbg_dump_rx_global_pkt_cnt(struct hclge_dev *hdev, char *buf, + int len) { struct hclge_rx_com_wl *rx_packet_cnt; struct hclge_desc desc; + int pos = 0; int ret; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_RX_GBL_PKT_CNT, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump rx global pkt cnt, ret = %d\n", ret); return ret; + } rx_packet_cnt = (struct hclge_rx_com_wl *)desc.data; - dev_info(&hdev->pdev->dev, - "rx_global_packet_cnt: high: 0x%x, low: 0x%x\n", - le16_to_cpu(rx_packet_cnt->com_wl.high), - le16_to_cpu(rx_packet_cnt->com_wl.low)); + pos += scnprintf(buf + pos, len - pos, + "rx_global_packet_cnt: high: 0x%x, low: 0x%x\n", + le16_to_cpu(rx_packet_cnt->com_wl.high), + le16_to_cpu(rx_packet_cnt->com_wl.low)); - return 0; + return pos; } -static int hclge_dbg_dump_rx_priv_wl_buf_cfg(struct hclge_dev *hdev) +static int hclge_dbg_dump_rx_priv_wl_buf_cfg(struct hclge_dev *hdev, char *buf, + int len) { struct hclge_rx_priv_wl_buf *rx_priv_wl; struct hclge_desc desc[2]; + int pos = 0; int i, ret; hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_RX_PRIV_WL_ALLOC, true); desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_RX_PRIV_WL_ALLOC, true); ret = hclge_cmd_send(&hdev->hw, desc, 2); - if (ret) + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump rx priv wl buf, ret = %d\n", ret); return ret; + } rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[0].data; for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++) - dev_info(&hdev->pdev->dev, + pos += scnprintf(buf + pos, len - pos, "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n", i, le16_to_cpu(rx_priv_wl->tc_wl[i].high), le16_to_cpu(rx_priv_wl->tc_wl[i].low)); rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[1].data; for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++) - dev_info(&hdev->pdev->dev, + pos += scnprintf(buf + pos, len - pos, "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n", i + HCLGE_TC_NUM_ONE_DESC, le16_to_cpu(rx_priv_wl->tc_wl[i].high), le16_to_cpu(rx_priv_wl->tc_wl[i].low)); - return 0; + return pos; } -static int hclge_dbg_dump_rx_common_threshold_cfg(struct hclge_dev *hdev) +static int hclge_dbg_dump_rx_common_threshold_cfg(struct hclge_dev *hdev, + char *buf, int len) { struct hclge_rx_com_thrd *rx_com_thrd; struct hclge_desc desc[2]; + int pos = 0; int i, ret; hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_RX_COM_THRD_ALLOC, true); desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_RX_COM_THRD_ALLOC, true); ret = hclge_cmd_send(&hdev->hw, desc, 2); - if (ret) + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to dump rx common threshold, ret = %d\n", ret); return ret; + } - dev_info(&hdev->pdev->dev, "\n"); + pos += scnprintf(buf + pos, len - pos, "\n"); rx_com_thrd = (struct hclge_rx_com_thrd *)desc[0].data; for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++) - dev_info(&hdev->pdev->dev, + pos += scnprintf(buf + pos, len - pos, "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n", i, le16_to_cpu(rx_com_thrd->com_thrd[i].high), le16_to_cpu(rx_com_thrd->com_thrd[i].low)); rx_com_thrd = (struct hclge_rx_com_thrd *)desc[1].data; for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++) - dev_info(&hdev->pdev->dev, + pos += scnprintf(buf + pos, len - pos, "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n", i + HCLGE_TC_NUM_ONE_DESC, le16_to_cpu(rx_com_thrd->com_thrd[i].high), le16_to_cpu(rx_com_thrd->com_thrd[i].low)); + return pos; +} + +static int hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev, char *buf, + int len) +{ + int pos = 0; + int ret; + + ret = hclge_dbg_dump_tx_buf_cfg(hdev, buf + pos, len - pos); + if (ret < 0) + return ret; + pos += ret; + + ret = hclge_dbg_dump_rx_priv_buf_cfg(hdev, buf + pos, len - pos); + if (ret < 0) + return ret; + pos += ret; + + ret = hclge_dbg_dump_rx_common_wl_cfg(hdev, buf + pos, len - pos); + if (ret < 0) + return ret; + pos += ret; + + ret = hclge_dbg_dump_rx_global_pkt_cnt(hdev, buf + pos, len - pos); + if (ret < 0) + return ret; + pos += ret; + + pos += scnprintf(buf + pos, len - pos, "\n"); + if (!hnae3_dev_dcb_supported(hdev)) + return 0; + + ret = hclge_dbg_dump_rx_priv_wl_buf_cfg(hdev, buf + pos, len - pos); + if (ret < 0) + return ret; + pos += ret; + + ret = hclge_dbg_dump_rx_common_threshold_cfg(hdev, buf + pos, + len - pos); + if (ret < 0) + return ret; + return 0; } -static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev) -{ - enum hclge_opcode_type cmd; - int ret; - - cmd = HCLGE_OPC_TX_BUFF_ALLOC; - ret = hclge_dbg_dump_tx_buf_cfg(hdev); - if (ret) - goto err_qos_cmd_send; - - cmd = HCLGE_OPC_RX_PRIV_BUFF_ALLOC; - ret = hclge_dbg_dump_rx_priv_buf_cfg(hdev); - if (ret) - goto err_qos_cmd_send; - - cmd = HCLGE_OPC_RX_COM_WL_ALLOC; - ret = hclge_dbg_dump_rx_common_wl_cfg(hdev); - if (ret) - goto err_qos_cmd_send; - - cmd = HCLGE_OPC_RX_GBL_PKT_CNT; - ret = hclge_dbg_dump_rx_global_pkt_cnt(hdev); - if (ret) - goto err_qos_cmd_send; - - dev_info(&hdev->pdev->dev, "\n"); - if (!hnae3_dev_dcb_supported(hdev)) { - dev_info(&hdev->pdev->dev, - "Only DCB-supported dev supports rx priv wl\n"); - return; - } - - cmd = HCLGE_OPC_RX_PRIV_WL_ALLOC; - ret = hclge_dbg_dump_rx_priv_wl_buf_cfg(hdev); - if (ret) - goto err_qos_cmd_send; - - cmd = HCLGE_OPC_RX_COM_THRD_ALLOC; - ret = hclge_dbg_dump_rx_common_threshold_cfg(hdev); - if (ret) - goto err_qos_cmd_send; - - return; - -err_qos_cmd_send: - dev_err(&hdev->pdev->dev, - "dump qos buf cfg fail(0x%x), ret = %d\n", cmd, ret); -} - -static void hclge_dbg_dump_mng_table(struct hclge_dev *hdev) +static int hclge_dbg_dump_mng_table(struct hclge_dev *hdev, char *buf, int len) { struct hclge_mac_ethertype_idx_rd_cmd *req0; - char printf_buf[HCLGE_DBG_BUF_LEN]; struct hclge_desc desc; u32 msg_egress_port; + int pos = 0; int ret, i; - dev_info(&hdev->pdev->dev, "mng tab:\n"); - memset(printf_buf, 0, HCLGE_DBG_BUF_LEN); - strncat(printf_buf, - "entry|mac_addr |mask|ether|mask|vlan|mask", - HCLGE_DBG_BUF_LEN - 1); - strncat(printf_buf + strlen(printf_buf), - "|i_map|i_dir|e_type|pf_id|vf_id|q_id|drop\n", - HCLGE_DBG_BUF_LEN - strlen(printf_buf) - 1); - - dev_info(&hdev->pdev->dev, "%s", printf_buf); + pos += scnprintf(buf + pos, len - pos, + "entry mac_addr mask ether "); + pos += scnprintf(buf + pos, len - pos, + "mask vlan mask i_map i_dir e_type "); + pos += scnprintf(buf + pos, len - pos, "pf_id vf_id q_id drop\n"); for (i = 0; i < HCLGE_DBG_MNG_TBL_MAX; i++) { hclge_cmd_setup_basic_desc(&desc, HCLGE_MAC_ETHERTYPE_IDX_RD, @@ -1207,52 +1371,53 @@ static void hclge_dbg_dump_mng_table(struct hclge_dev *hdev) ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { dev_err(&hdev->pdev->dev, - "call hclge_cmd_send fail, ret = %d\n", ret); - return; + "failed to dump manage table, ret = %d\n", ret); + return ret; } if (!req0->resp_code) continue; - memset(printf_buf, 0, HCLGE_DBG_BUF_LEN); - snprintf(printf_buf, HCLGE_DBG_BUF_LEN, - "%02u |%02x:%02x:%02x:%02x:%02x:%02x|", - le16_to_cpu(req0->index), - req0->mac_addr[0], req0->mac_addr[1], - req0->mac_addr[2], req0->mac_addr[3], - req0->mac_addr[4], req0->mac_addr[5]); + pos += scnprintf(buf + pos, len - pos, "%02u %pM ", + le16_to_cpu(req0->index), req0->mac_addr); - snprintf(printf_buf + strlen(printf_buf), - HCLGE_DBG_BUF_LEN - strlen(printf_buf), - "%x |%04x |%x |%04x|%x |%02x |%02x |", - !!(req0->flags & HCLGE_DBG_MNG_MAC_MASK_B), - le16_to_cpu(req0->ethter_type), - !!(req0->flags & HCLGE_DBG_MNG_ETHER_MASK_B), - le16_to_cpu(req0->vlan_tag) & HCLGE_DBG_MNG_VLAN_TAG, - !!(req0->flags & HCLGE_DBG_MNG_VLAN_MASK_B), - req0->i_port_bitmap, req0->i_port_direction); + pos += scnprintf(buf + pos, len - pos, + "%x %04x %x %04x ", + !!(req0->flags & HCLGE_DBG_MNG_MAC_MASK_B), + le16_to_cpu(req0->ethter_type), + !!(req0->flags & HCLGE_DBG_MNG_ETHER_MASK_B), + le16_to_cpu(req0->vlan_tag) & + HCLGE_DBG_MNG_VLAN_TAG); + + pos += scnprintf(buf + pos, len - pos, + "%x %02x %02x ", + !!(req0->flags & HCLGE_DBG_MNG_VLAN_MASK_B), + req0->i_port_bitmap, req0->i_port_direction); msg_egress_port = le16_to_cpu(req0->egress_port); - snprintf(printf_buf + strlen(printf_buf), - HCLGE_DBG_BUF_LEN - strlen(printf_buf), - "%x |%x |%02x |%04x|%x\n", - !!(msg_egress_port & HCLGE_DBG_MNG_E_TYPE_B), - msg_egress_port & HCLGE_DBG_MNG_PF_ID, - (msg_egress_port >> 3) & HCLGE_DBG_MNG_VF_ID, - le16_to_cpu(req0->egress_queue), - !!(msg_egress_port & HCLGE_DBG_MNG_DROP_B)); - - dev_info(&hdev->pdev->dev, "%s", printf_buf); + pos += scnprintf(buf + pos, len - pos, + "%x %x %02x %04x %x\n", + !!(msg_egress_port & HCLGE_DBG_MNG_E_TYPE_B), + msg_egress_port & HCLGE_DBG_MNG_PF_ID, + (msg_egress_port >> 3) & HCLGE_DBG_MNG_VF_ID, + le16_to_cpu(req0->egress_queue), + !!(msg_egress_port & HCLGE_DBG_MNG_DROP_B)); } + + return 0; } -static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage, - bool sel_x, u32 loc) +#define HCLGE_DBG_TCAM_BUF_SIZE 256 + +static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, bool sel_x, + char *tcam_buf, + struct hclge_dbg_tcam_msg tcam_msg) { struct hclge_fd_tcam_config_1_cmd *req1; struct hclge_fd_tcam_config_2_cmd *req2; struct hclge_fd_tcam_config_3_cmd *req3; struct hclge_desc desc[3]; + int pos = 0; int ret, i; u32 *req; @@ -1266,31 +1431,35 @@ static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage, req2 = (struct hclge_fd_tcam_config_2_cmd *)desc[1].data; req3 = (struct hclge_fd_tcam_config_3_cmd *)desc[2].data; - req1->stage = stage; + req1->stage = tcam_msg.stage; req1->xy_sel = sel_x ? 1 : 0; - req1->index = cpu_to_le32(loc); + req1->index = cpu_to_le32(tcam_msg.loc); ret = hclge_cmd_send(&hdev->hw, desc, 3); if (ret) return ret; - dev_info(&hdev->pdev->dev, " read result tcam key %s(%u):\n", - sel_x ? "x" : "y", loc); + pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos, + "read result tcam key %s(%u):\n", sel_x ? "x" : "y", + tcam_msg.loc); /* tcam_data0 ~ tcam_data1 */ req = (u32 *)req1->tcam_data; for (i = 0; i < 2; i++) - dev_info(&hdev->pdev->dev, "%08x\n", *req++); + pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos, + "%08x\n", *req++); /* tcam_data2 ~ tcam_data7 */ req = (u32 *)req2->tcam_data; for (i = 0; i < 6; i++) - dev_info(&hdev->pdev->dev, "%08x\n", *req++); + pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos, + "%08x\n", *req++); /* tcam_data8 ~ tcam_data12 */ req = (u32 *)req3->tcam_data; for (i = 0; i < 5; i++) - dev_info(&hdev->pdev->dev, "%08x\n", *req++); + pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos, + "%08x\n", *req++); return ret; } @@ -1308,265 +1477,348 @@ static int hclge_dbg_get_rules_location(struct hclge_dev *hdev, u16 *rule_locs) } spin_unlock_bh(&hdev->fd_rule_lock); - if (cnt != hdev->hclge_fd_rule_num) + if (cnt != hdev->hclge_fd_rule_num || cnt == 0) return -EINVAL; return cnt; } -static void hclge_dbg_fd_tcam(struct hclge_dev *hdev) +static int hclge_dbg_dump_fd_tcam(struct hclge_dev *hdev, char *buf, int len) { + u32 rule_num = hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]; + struct hclge_dbg_tcam_msg tcam_msg; int i, ret, rule_cnt; u16 *rule_locs; + char *tcam_buf; + int pos = 0; if (!hnae3_dev_fd_supported(hdev)) { dev_err(&hdev->pdev->dev, "Only FD-supported dev supports dump fd tcam\n"); - return; + return -EOPNOTSUPP; } - if (!hdev->hclge_fd_rule_num || - !hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1]) - return; + if (!hdev->hclge_fd_rule_num || !rule_num) + return 0; - rule_locs = kcalloc(hdev->fd_cfg.rule_num[HCLGE_FD_STAGE_1], - sizeof(u16), GFP_KERNEL); + rule_locs = kcalloc(rule_num, sizeof(u16), GFP_KERNEL); if (!rule_locs) - return; + return -ENOMEM; + + tcam_buf = kzalloc(HCLGE_DBG_TCAM_BUF_SIZE, GFP_KERNEL); + if (!tcam_buf) { + kfree(rule_locs); + return -ENOMEM; + } rule_cnt = hclge_dbg_get_rules_location(hdev, rule_locs); - if (rule_cnt <= 0) { + if (rule_cnt < 0) { + ret = rule_cnt; dev_err(&hdev->pdev->dev, - "failed to get rule number, ret = %d\n", rule_cnt); - kfree(rule_locs); - return; + "failed to get rule number, ret = %d\n", ret); + goto out; } + ret = 0; for (i = 0; i < rule_cnt; i++) { - ret = hclge_dbg_fd_tcam_read(hdev, 0, true, rule_locs[i]); + tcam_msg.stage = HCLGE_FD_STAGE_1; + tcam_msg.loc = rule_locs[i]; + + ret = hclge_dbg_fd_tcam_read(hdev, true, tcam_buf, tcam_msg); if (ret) { dev_err(&hdev->pdev->dev, "failed to get fd tcam key x, ret = %d\n", ret); - kfree(rule_locs); - return; + goto out; } - ret = hclge_dbg_fd_tcam_read(hdev, 0, false, rule_locs[i]); + pos += scnprintf(buf + pos, len - pos, "%s", tcam_buf); + + ret = hclge_dbg_fd_tcam_read(hdev, false, tcam_buf, tcam_msg); if (ret) { dev_err(&hdev->pdev->dev, "failed to get fd tcam key y, ret = %d\n", ret); - kfree(rule_locs); - return; + goto out; } + + pos += scnprintf(buf + pos, len - pos, "%s", tcam_buf); } +out: + kfree(tcam_buf); kfree(rule_locs); + return ret; } -void hclge_dbg_dump_rst_info(struct hclge_dev *hdev) +static int hclge_dbg_dump_fd_counter(struct hclge_dev *hdev, char *buf, int len) { - dev_info(&hdev->pdev->dev, "PF reset count: %u\n", - hdev->rst_stats.pf_rst_cnt); - dev_info(&hdev->pdev->dev, "FLR reset count: %u\n", - hdev->rst_stats.flr_rst_cnt); - dev_info(&hdev->pdev->dev, "GLOBAL reset count: %u\n", - hdev->rst_stats.global_rst_cnt); - dev_info(&hdev->pdev->dev, "IMP reset count: %u\n", - hdev->rst_stats.imp_rst_cnt); - dev_info(&hdev->pdev->dev, "reset done count: %u\n", - hdev->rst_stats.reset_done_cnt); - dev_info(&hdev->pdev->dev, "HW reset done count: %u\n", - hdev->rst_stats.hw_reset_done_cnt); - dev_info(&hdev->pdev->dev, "reset count: %u\n", - hdev->rst_stats.reset_cnt); - dev_info(&hdev->pdev->dev, "reset fail count: %u\n", - hdev->rst_stats.reset_fail_cnt); - dev_info(&hdev->pdev->dev, "vector0 interrupt enable status: 0x%x\n", - hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_REG_BASE)); - dev_info(&hdev->pdev->dev, "reset interrupt source: 0x%x\n", - hclge_read_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG)); - dev_info(&hdev->pdev->dev, "reset interrupt status: 0x%x\n", - hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS)); - dev_info(&hdev->pdev->dev, "hardware reset status: 0x%x\n", - hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG)); - dev_info(&hdev->pdev->dev, "handshake status: 0x%x\n", - hclge_read_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG)); - dev_info(&hdev->pdev->dev, "function reset status: 0x%x\n", - hclge_read_dev(&hdev->hw, HCLGE_FUN_RST_ING)); - dev_info(&hdev->pdev->dev, "hdev state: 0x%lx\n", hdev->state); -} - -static void hclge_dbg_dump_serv_info(struct hclge_dev *hdev) -{ - dev_info(&hdev->pdev->dev, "last_serv_processed: %lu\n", - hdev->last_serv_processed); - dev_info(&hdev->pdev->dev, "last_serv_cnt: %lu\n", - hdev->serv_processed_cnt); -} - -static void hclge_dbg_dump_interrupt(struct hclge_dev *hdev) -{ - dev_info(&hdev->pdev->dev, "num_nic_msi: %u\n", hdev->num_nic_msi); - dev_info(&hdev->pdev->dev, "num_roce_msi: %u\n", hdev->num_roce_msi); - dev_info(&hdev->pdev->dev, "num_msi_used: %u\n", hdev->num_msi_used); - dev_info(&hdev->pdev->dev, "num_msi_left: %u\n", hdev->num_msi_left); -} - -static void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev) -{ - struct hclge_desc *desc_src, *desc_tmp; - struct hclge_get_m7_bd_cmd *req; + u8 func_num = pci_num_vf(hdev->pdev) + 1; /* pf and enabled vf num */ + struct hclge_fd_ad_cnt_read_cmd *req; + char str_id[HCLGE_DBG_ID_LEN]; struct hclge_desc desc; - u32 bd_num, buf_len; - int ret, i; + int pos = 0; + int ret; + u64 cnt; + u8 i; - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_M7_STATS_BD, true); + pos += scnprintf(buf + pos, len - pos, + "func_id\thit_times\n"); - req = (struct hclge_get_m7_bd_cmd *)desc.data; + for (i = 0; i < func_num; i++) { + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_FD_CNT_OP, true); + req = (struct hclge_fd_ad_cnt_read_cmd *)desc.data; + req->index = cpu_to_le16(i); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, "failed to get fd counter, ret = %d\n", + ret); + return ret; + } + cnt = le64_to_cpu(req->cnt); + hclge_dbg_get_func_id_str(str_id, i); + pos += scnprintf(buf + pos, len - pos, + "%s\t%llu\n", str_id, cnt); + } + + return 0; +} + +int hclge_dbg_dump_rst_info(struct hclge_dev *hdev, char *buf, int len) +{ + int pos = 0; + + pos += scnprintf(buf + pos, len - pos, "PF reset count: %u\n", + hdev->rst_stats.pf_rst_cnt); + pos += scnprintf(buf + pos, len - pos, "FLR reset count: %u\n", + hdev->rst_stats.flr_rst_cnt); + pos += scnprintf(buf + pos, len - pos, "GLOBAL reset count: %u\n", + hdev->rst_stats.global_rst_cnt); + pos += scnprintf(buf + pos, len - pos, "IMP reset count: %u\n", + hdev->rst_stats.imp_rst_cnt); + pos += scnprintf(buf + pos, len - pos, "reset done count: %u\n", + hdev->rst_stats.reset_done_cnt); + pos += scnprintf(buf + pos, len - pos, "HW reset done count: %u\n", + hdev->rst_stats.hw_reset_done_cnt); + pos += scnprintf(buf + pos, len - pos, "reset count: %u\n", + hdev->rst_stats.reset_cnt); + pos += scnprintf(buf + pos, len - pos, "reset fail count: %u\n", + hdev->rst_stats.reset_fail_cnt); + pos += scnprintf(buf + pos, len - pos, + "vector0 interrupt enable status: 0x%x\n", + hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_REG_BASE)); + pos += scnprintf(buf + pos, len - pos, "reset interrupt source: 0x%x\n", + hclge_read_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG)); + pos += scnprintf(buf + pos, len - pos, "reset interrupt status: 0x%x\n", + hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS)); + pos += scnprintf(buf + pos, len - pos, "RAS interrupt status: 0x%x\n", + hclge_read_dev(&hdev->hw, + HCLGE_RAS_PF_OTHER_INT_STS_REG)); + pos += scnprintf(buf + pos, len - pos, "hardware reset status: 0x%x\n", + hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG)); + pos += scnprintf(buf + pos, len - pos, "handshake status: 0x%x\n", + hclge_read_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG)); + pos += scnprintf(buf + pos, len - pos, "function reset status: 0x%x\n", + hclge_read_dev(&hdev->hw, HCLGE_FUN_RST_ING)); + pos += scnprintf(buf + pos, len - pos, "hdev state: 0x%lx\n", + hdev->state); + + return 0; +} + +static int hclge_dbg_dump_serv_info(struct hclge_dev *hdev, char *buf, int len) +{ + unsigned long rem_nsec; + int pos = 0; + u64 lc; + + lc = local_clock(); + rem_nsec = do_div(lc, HCLGE_BILLION_NANO_SECONDS); + + pos += scnprintf(buf + pos, len - pos, "local_clock: [%5lu.%06lu]\n", + (unsigned long)lc, rem_nsec / 1000); + pos += scnprintf(buf + pos, len - pos, "delta: %u(ms)\n", + jiffies_to_msecs(jiffies - hdev->last_serv_processed)); + pos += scnprintf(buf + pos, len - pos, + "last_service_task_processed: %lu(jiffies)\n", + hdev->last_serv_processed); + pos += scnprintf(buf + pos, len - pos, "last_service_task_cnt: %lu\n", + hdev->serv_processed_cnt); + + return 0; +} + +static int hclge_dbg_dump_interrupt(struct hclge_dev *hdev, char *buf, int len) +{ + int pos = 0; + + pos += scnprintf(buf + pos, len - pos, "num_nic_msi: %u\n", + hdev->num_nic_msi); + pos += scnprintf(buf + pos, len - pos, "num_roce_msi: %u\n", + hdev->num_roce_msi); + pos += scnprintf(buf + pos, len - pos, "num_msi_used: %u\n", + hdev->num_msi_used); + pos += scnprintf(buf + pos, len - pos, "num_msi_left: %u\n", + hdev->num_msi_left); + + return 0; +} + +static void hclge_dbg_imp_info_data_print(struct hclge_desc *desc_src, + char *buf, int len, u32 bd_num) +{ +#define HCLGE_DBG_IMP_INFO_PRINT_OFFSET 0x2 + + struct hclge_desc *desc_index = desc_src; + u32 offset = 0; + int pos = 0; + u32 i, j; + + pos += scnprintf(buf + pos, len - pos, "offset | data\n"); + + for (i = 0; i < bd_num; i++) { + j = 0; + while (j < HCLGE_DESC_DATA_LEN - 1) { + pos += scnprintf(buf + pos, len - pos, "0x%04x | ", + offset); + pos += scnprintf(buf + pos, len - pos, "0x%08x ", + le32_to_cpu(desc_index->data[j++])); + pos += scnprintf(buf + pos, len - pos, "0x%08x\n", + le32_to_cpu(desc_index->data[j++])); + offset += sizeof(u32) * HCLGE_DBG_IMP_INFO_PRINT_OFFSET; + } + desc_index++; + } +} + +static int +hclge_dbg_get_imp_stats_info(struct hclge_dev *hdev, char *buf, int len) +{ + struct hclge_get_imp_bd_cmd *req; + struct hclge_desc *desc_src; + struct hclge_desc desc; + u32 bd_num; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_IMP_STATS_BD, true); + + req = (struct hclge_get_imp_bd_cmd *)desc.data; ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { dev_err(&hdev->pdev->dev, - "get firmware statistics bd number failed, ret = %d\n", + "failed to get imp statistics bd number, ret = %d\n", ret); - return; + return ret; } bd_num = le32_to_cpu(req->bd_num); - buf_len = sizeof(struct hclge_desc) * bd_num; - desc_src = kzalloc(buf_len, GFP_KERNEL); + desc_src = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL); if (!desc_src) - return; + return -ENOMEM; - desc_tmp = desc_src; - ret = hclge_dbg_cmd_send(hdev, desc_tmp, 0, bd_num, - HCLGE_OPC_M7_STATS_INFO); + ret = hclge_dbg_cmd_send(hdev, desc_src, 0, bd_num, + HCLGE_OPC_IMP_STATS_INFO); if (ret) { kfree(desc_src); dev_err(&hdev->pdev->dev, - "get firmware statistics failed, ret = %d\n", ret); - return; + "failed to get imp statistics, ret = %d\n", ret); + return ret; } - for (i = 0; i < bd_num; i++) { - dev_info(&hdev->pdev->dev, "0x%08x 0x%08x 0x%08x\n", - le32_to_cpu(desc_tmp->data[0]), - le32_to_cpu(desc_tmp->data[1]), - le32_to_cpu(desc_tmp->data[2])); - dev_info(&hdev->pdev->dev, "0x%08x 0x%08x 0x%08x\n", - le32_to_cpu(desc_tmp->data[3]), - le32_to_cpu(desc_tmp->data[4]), - le32_to_cpu(desc_tmp->data[5])); - - desc_tmp++; - } + hclge_dbg_imp_info_data_print(desc_src, buf, len, bd_num); kfree(desc_src); + + return 0; } #define HCLGE_CMD_NCL_CONFIG_BD_NUM 5 +#define HCLGE_MAX_NCL_CONFIG_LENGTH 16384 -static void hclge_ncl_config_data_print(struct hclge_dev *hdev, - struct hclge_desc *desc, int *offset, - int *length) +static void hclge_ncl_config_data_print(struct hclge_desc *desc, int *index, + char *buf, int *len, int *pos) { #define HCLGE_CMD_DATA_NUM 6 - int i; - int j; + int offset = HCLGE_MAX_NCL_CONFIG_LENGTH - *index; + int i, j; for (i = 0; i < HCLGE_CMD_NCL_CONFIG_BD_NUM; i++) { for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) { if (i == 0 && j == 0) continue; - dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n", - *offset, - le32_to_cpu(desc[i].data[j])); - *offset += sizeof(u32); - *length -= sizeof(u32); - if (*length <= 0) + *pos += scnprintf(buf + *pos, *len - *pos, + "0x%04x | 0x%08x\n", offset, + le32_to_cpu(desc[i].data[j])); + + offset += sizeof(u32); + *index -= sizeof(u32); + + if (*index <= 0) return; } } } -/* hclge_dbg_dump_ncl_config: print specified range of NCL_CONFIG file - * @hdev: pointer to struct hclge_dev - * @cmd_buf: string that contains offset and length - */ -static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev, - const char *cmd_buf) +static int +hclge_dbg_dump_ncl_config(struct hclge_dev *hdev, char *buf, int len) { -#define HCLGE_MAX_NCL_CONFIG_OFFSET 4096 #define HCLGE_NCL_CONFIG_LENGTH_IN_EACH_CMD (20 + 24 * 4) -#define HCLGE_NCL_CONFIG_PARAM_NUM 2 struct hclge_desc desc[HCLGE_CMD_NCL_CONFIG_BD_NUM]; int bd_num = HCLGE_CMD_NCL_CONFIG_BD_NUM; - int offset; - int length; - int data0; + int index = HCLGE_MAX_NCL_CONFIG_LENGTH; + int pos = 0; + u32 data0; int ret; - ret = sscanf(cmd_buf, "%x %x", &offset, &length); - if (ret != HCLGE_NCL_CONFIG_PARAM_NUM) { - dev_err(&hdev->pdev->dev, - "Too few parameters, num = %d.\n", ret); - return; - } + pos += scnprintf(buf + pos, len - pos, "offset | data\n"); - if (offset < 0 || offset >= HCLGE_MAX_NCL_CONFIG_OFFSET || - length <= 0 || length > HCLGE_MAX_NCL_CONFIG_OFFSET - offset) { - dev_err(&hdev->pdev->dev, - "Invalid input, offset = %d, length = %d.\n", - offset, length); - return; - } - - dev_info(&hdev->pdev->dev, "offset | data\n"); - - while (length > 0) { - data0 = offset; - if (length >= HCLGE_NCL_CONFIG_LENGTH_IN_EACH_CMD) + while (index > 0) { + data0 = HCLGE_MAX_NCL_CONFIG_LENGTH - index; + if (index >= HCLGE_NCL_CONFIG_LENGTH_IN_EACH_CMD) data0 |= HCLGE_NCL_CONFIG_LENGTH_IN_EACH_CMD << 16; else - data0 |= length << 16; + data0 |= (u32)index << 16; ret = hclge_dbg_cmd_send(hdev, desc, data0, bd_num, HCLGE_OPC_QUERY_NCL_CONFIG); if (ret) - return; + return ret; - hclge_ncl_config_data_print(hdev, desc, &offset, &length); + hclge_ncl_config_data_print(desc, &index, buf, &len, &pos); } + + return 0; } -static void hclge_dbg_dump_loopback(struct hclge_dev *hdev) +static int hclge_dbg_dump_loopback(struct hclge_dev *hdev, char *buf, int len) { struct phy_device *phydev = hdev->hw.mac.phydev; struct hclge_config_mac_mode_cmd *req_app; struct hclge_common_lb_cmd *req_common; struct hclge_desc desc; u8 loopback_en; + int pos = 0; int ret; req_app = (struct hclge_config_mac_mode_cmd *)desc.data; req_common = (struct hclge_common_lb_cmd *)desc.data; - dev_info(&hdev->pdev->dev, "mac id: %u\n", hdev->hw.mac.mac_id); + pos += scnprintf(buf + pos, len - pos, "mac id: %u\n", + hdev->hw.mac.mac_id); hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { dev_err(&hdev->pdev->dev, "failed to dump app loopback status, ret = %d\n", ret); - return; + return ret; } loopback_en = hnae3_get_bit(le32_to_cpu(req_app->txrx_pad_fcs_loop_en), HCLGE_MAC_APP_LP_B); - dev_info(&hdev->pdev->dev, "app loopback: %s\n", - loopback_en ? "on" : "off"); + pos += scnprintf(buf + pos, len - pos, "app loopback: %s\n", + state_str[loopback_en]); hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_COMMON_LOOPBACK, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -1574,247 +1826,647 @@ static void hclge_dbg_dump_loopback(struct hclge_dev *hdev) dev_err(&hdev->pdev->dev, "failed to dump common loopback status, ret = %d\n", ret); - return; + return ret; } loopback_en = req_common->enable & HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B; - dev_info(&hdev->pdev->dev, "serdes serial loopback: %s\n", - loopback_en ? "on" : "off"); + pos += scnprintf(buf + pos, len - pos, "serdes serial loopback: %s\n", + state_str[loopback_en]); loopback_en = req_common->enable & - HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B; - dev_info(&hdev->pdev->dev, "serdes parallel loopback: %s\n", - loopback_en ? "on" : "off"); + HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B ? 1 : 0; + pos += scnprintf(buf + pos, len - pos, "serdes parallel loopback: %s\n", + state_str[loopback_en]); if (phydev) { - dev_info(&hdev->pdev->dev, "phy loopback: %s\n", - phydev->loopback_enabled ? "on" : "off"); + loopback_en = phydev->loopback_enabled; + pos += scnprintf(buf + pos, len - pos, "phy loopback: %s\n", + state_str[loopback_en]); } else if (hnae3_dev_phy_imp_supported(hdev)) { loopback_en = req_common->enable & HCLGE_CMD_GE_PHY_INNER_LOOP_B; - dev_info(&hdev->pdev->dev, "phy loopback: %s\n", - loopback_en ? "on" : "off"); + pos += scnprintf(buf + pos, len - pos, "phy loopback: %s\n", + state_str[loopback_en]); } + + return 0; } /* hclge_dbg_dump_mac_tnl_status: print message about mac tnl interrupt * @hdev: pointer to struct hclge_dev */ -static void hclge_dbg_dump_mac_tnl_status(struct hclge_dev *hdev) +static int +hclge_dbg_dump_mac_tnl_status(struct hclge_dev *hdev, char *buf, int len) { -#define HCLGE_BILLION_NANO_SECONDS 1000000000 - struct hclge_mac_tnl_stats stats; unsigned long rem_nsec; + int pos = 0; - dev_info(&hdev->pdev->dev, "Recently generated mac tnl interruption:\n"); + pos += scnprintf(buf + pos, len - pos, + "Recently generated mac tnl interruption:\n"); while (kfifo_get(&hdev->mac_tnl_log, &stats)) { rem_nsec = do_div(stats.time, HCLGE_BILLION_NANO_SECONDS); - dev_info(&hdev->pdev->dev, "[%07lu.%03lu] status = 0x%x\n", - (unsigned long)stats.time, rem_nsec / 1000, - stats.status); + + pos += scnprintf(buf + pos, len - pos, + "[%07lu.%03lu] status = 0x%x\n", + (unsigned long)stats.time, rem_nsec / 1000, + stats.status); } + + return 0; } -static void hclge_dbg_dump_qs_shaper_single(struct hclge_dev *hdev, u16 qsid) -{ - struct hclge_qs_shapping_cmd *shap_cfg_cmd; - u8 ir_u, ir_b, ir_s, bs_b, bs_s; - struct hclge_desc desc; - u32 shapping_para; - u32 rate; - int ret; - - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QCN_SHAPPING_CFG, true); - - shap_cfg_cmd = (struct hclge_qs_shapping_cmd *)desc.data; - shap_cfg_cmd->qs_id = cpu_to_le16(qsid); - - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) { - dev_err(&hdev->pdev->dev, - "qs%u failed to get tx_rate, ret=%d\n", - qsid, ret); - return; - } - - shapping_para = le32_to_cpu(shap_cfg_cmd->qs_shapping_para); - ir_b = hclge_tm_get_field(shapping_para, IR_B); - ir_u = hclge_tm_get_field(shapping_para, IR_U); - ir_s = hclge_tm_get_field(shapping_para, IR_S); - bs_b = hclge_tm_get_field(shapping_para, BS_B); - bs_s = hclge_tm_get_field(shapping_para, BS_S); - rate = le32_to_cpu(shap_cfg_cmd->qs_rate); - - dev_info(&hdev->pdev->dev, - "qs%u ir_b:%u, ir_u:%u, ir_s:%u, bs_b:%u, bs_s:%u, flag:%#x, rate:%u(Mbps)\n", - qsid, ir_b, ir_u, ir_s, bs_b, bs_s, shap_cfg_cmd->flag, rate); -} - -static void hclge_dbg_dump_qs_shaper_all(struct hclge_dev *hdev) -{ - struct hnae3_knic_private_info *kinfo; - struct hclge_vport *vport; - int vport_id, i; - - for (vport_id = 0; vport_id <= pci_num_vf(hdev->pdev); vport_id++) { - vport = &hdev->vport[vport_id]; - kinfo = &vport->nic.kinfo; - - dev_info(&hdev->pdev->dev, "qs cfg of vport%d:\n", vport_id); - - for (i = 0; i < kinfo->tc_info.num_tc; i++) { - u16 qsid = vport->qs_offset + i; - - hclge_dbg_dump_qs_shaper_single(hdev, qsid); - } - } -} - -static void hclge_dbg_dump_qs_shaper(struct hclge_dev *hdev, - const char *cmd_buf) -{ - u16 qsid; - int ret; - - ret = kstrtou16(cmd_buf, 0, &qsid); - if (ret) { - hclge_dbg_dump_qs_shaper_all(hdev); - return; - } - - if (qsid >= hdev->ae_dev->dev_specs.max_qset_num) { - dev_err(&hdev->pdev->dev, "qsid(%u) out of range[0-%u]\n", - qsid, hdev->ae_dev->dev_specs.max_qset_num - 1); - return; - } - - hclge_dbg_dump_qs_shaper_single(hdev, qsid); -} - -static int hclge_dbg_dump_mac_list(struct hclge_dev *hdev, const char *cmd_buf, - bool is_unicast) + +static const struct hclge_dbg_item mac_list_items[] = { + { "FUNC_ID", 2 }, + { "MAC_ADDR", 12 }, + { "STATE", 2 }, +}; + +static void hclge_dbg_dump_mac_list(struct hclge_dev *hdev, char *buf, int len, + bool is_unicast) { + char data_str[ARRAY_SIZE(mac_list_items)][HCLGE_DBG_DATA_STR_LEN]; + char content[HCLGE_DBG_INFO_LEN], str_id[HCLGE_DBG_ID_LEN]; + char *result[ARRAY_SIZE(mac_list_items)]; struct hclge_mac_node *mac_node, *tmp; struct hclge_vport *vport; struct list_head *list; u32 func_id; + int pos = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(mac_list_items); i++) + result[i] = &data_str[i][0]; + + pos += scnprintf(buf + pos, len - pos, "%s MAC_LIST:\n", + is_unicast ? "UC" : "MC"); + hclge_dbg_fill_content(content, sizeof(content), mac_list_items, + NULL, ARRAY_SIZE(mac_list_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + + for (func_id = 0; func_id < hdev->num_alloc_vport; func_id++) { + vport = &hdev->vport[func_id]; + list = is_unicast ? &vport->uc_mac_list : &vport->mc_mac_list; + spin_lock_bh(&vport->mac_list_lock); + list_for_each_entry_safe(mac_node, tmp, list, node) { + i = 0; + result[i++] = hclge_dbg_get_func_id_str(str_id, + func_id); + sprintf(result[i++], "%pM", mac_node->mac_addr); + sprintf(result[i++], "%5s", + hclge_mac_state_str[mac_node->state]); + hclge_dbg_fill_content(content, sizeof(content), + mac_list_items, + (const char **)result, + ARRAY_SIZE(mac_list_items)); + pos += scnprintf(buf + pos, len - pos, "%s", content); + } + spin_unlock_bh(&vport->mac_list_lock); + } +} + +static int hclge_dbg_dump_umv_info(struct hclge_dev *hdev, char *buf, int len) +{ + u8 func_num = pci_num_vf(hdev->pdev) + 1; + struct hclge_vport *vport; + int pos = 0; + u8 i; + + pos += scnprintf(buf, len, "num_alloc_vport : %u\n", + hdev->num_alloc_vport); + pos += scnprintf(buf + pos, len - pos, "max_umv_size : %u\n", + hdev->max_umv_size); + pos += scnprintf(buf + pos, len - pos, "wanted_umv_size : %u\n", + hdev->wanted_umv_size); + pos += scnprintf(buf + pos, len - pos, "priv_umv_size : %u\n", + hdev->priv_umv_size); + + mutex_lock(&hdev->vport_lock); + pos += scnprintf(buf + pos, len - pos, "share_umv_size : %u\n", + hdev->share_umv_size); + for (i = 0; i < func_num; i++) { + vport = &hdev->vport[i]; + pos += scnprintf(buf + pos, len - pos, + "vport(%u) used_umv_num : %u\n", + i, vport->used_umv_num); + } + mutex_unlock(&hdev->vport_lock); + + return 0; +} + +static int hclge_get_vlan_rx_offload_cfg(struct hclge_dev *hdev, u8 vf_id, + struct hclge_dbg_vlan_cfg *vlan_cfg) +{ + struct hclge_vport_vtag_rx_cfg_cmd *req; + struct hclge_desc desc; + u16 bmap_index; + u8 rx_cfg; int ret; - ret = kstrtouint(cmd_buf, 0, &func_id); - if (ret < 0) { + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_PORT_RX_CFG, true); + + req = (struct hclge_vport_vtag_rx_cfg_cmd *)desc.data; + req->vf_offset = vf_id / HCLGE_VF_NUM_PER_CMD; + bmap_index = vf_id % HCLGE_VF_NUM_PER_CMD / HCLGE_VF_NUM_PER_BYTE; + req->vf_bitmap[bmap_index] = 1U << (vf_id % HCLGE_VF_NUM_PER_BYTE); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { dev_err(&hdev->pdev->dev, - "dump mac list: bad command string, ret = %d\n", ret); - return -EINVAL; + "failed to get vport%u rxvlan cfg, ret = %d\n", + vf_id, ret); + return ret; } - if (func_id >= hdev->num_alloc_vport) { - dev_err(&hdev->pdev->dev, - "function id(%u) is out of range(0-%u)\n", func_id, - hdev->num_alloc_vport - 1); - return -EINVAL; - } - - vport = &hdev->vport[func_id]; - - list = is_unicast ? &vport->uc_mac_list : &vport->mc_mac_list; - - dev_info(&hdev->pdev->dev, "vport %u %s mac list:\n", - func_id, is_unicast ? "uc" : "mc"); - dev_info(&hdev->pdev->dev, "mac address state\n"); - - spin_lock_bh(&vport->mac_list_lock); - - list_for_each_entry_safe(mac_node, tmp, list, node) { - dev_info(&hdev->pdev->dev, "%pM %d\n", - mac_node->mac_addr, mac_node->state); - } - - spin_unlock_bh(&vport->mac_list_lock); + rx_cfg = req->vport_vlan_cfg; + vlan_cfg->strip_tag1 = hnae3_get_bit(rx_cfg, HCLGE_REM_TAG1_EN_B); + vlan_cfg->strip_tag2 = hnae3_get_bit(rx_cfg, HCLGE_REM_TAG2_EN_B); + vlan_cfg->drop_tag1 = hnae3_get_bit(rx_cfg, HCLGE_DISCARD_TAG1_EN_B); + vlan_cfg->drop_tag2 = hnae3_get_bit(rx_cfg, HCLGE_DISCARD_TAG2_EN_B); + vlan_cfg->pri_only1 = hnae3_get_bit(rx_cfg, HCLGE_SHOW_TAG1_EN_B); + vlan_cfg->pri_only2 = hnae3_get_bit(rx_cfg, HCLGE_SHOW_TAG2_EN_B); return 0; } -int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf) +static int hclge_get_vlan_tx_offload_cfg(struct hclge_dev *hdev, u8 vf_id, + struct hclge_dbg_vlan_cfg *vlan_cfg) { -#define DUMP_REG "dump reg" -#define DUMP_TM_MAP "dump tm map" -#define DUMP_LOOPBACK "dump loopback" -#define DUMP_INTERRUPT "dump intr" + struct hclge_vport_vtag_tx_cfg_cmd *req; + struct hclge_desc desc; + u16 bmap_index; + u8 tx_cfg; + int ret; - struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_PORT_TX_CFG, true); + req = (struct hclge_vport_vtag_tx_cfg_cmd *)desc.data; + req->vf_offset = vf_id / HCLGE_VF_NUM_PER_CMD; + bmap_index = vf_id % HCLGE_VF_NUM_PER_CMD / HCLGE_VF_NUM_PER_BYTE; + req->vf_bitmap[bmap_index] = 1U << (vf_id % HCLGE_VF_NUM_PER_BYTE); - if (strncmp(cmd_buf, "dump fd tcam", 12) == 0) { - hclge_dbg_fd_tcam(hdev); - } else if (strncmp(cmd_buf, "dump tc", 7) == 0) { - hclge_dbg_dump_tc(hdev); - } else if (strncmp(cmd_buf, DUMP_TM_MAP, strlen(DUMP_TM_MAP)) == 0) { - hclge_dbg_dump_tm_map(hdev, &cmd_buf[sizeof(DUMP_TM_MAP)]); - } else if (strncmp(cmd_buf, "dump tm", 7) == 0) { - hclge_dbg_dump_tm(hdev); - } else if (strncmp(cmd_buf, "dump qos pause cfg", 18) == 0) { - hclge_dbg_dump_qos_pause_cfg(hdev); - } else if (strncmp(cmd_buf, "dump qos pri map", 16) == 0) { - hclge_dbg_dump_qos_pri_map(hdev); - } else if (strncmp(cmd_buf, "dump qos buf cfg", 16) == 0) { - hclge_dbg_dump_qos_buf_cfg(hdev); - } else if (strncmp(cmd_buf, "dump mng tbl", 12) == 0) { - hclge_dbg_dump_mng_table(hdev); - } else if (strncmp(cmd_buf, DUMP_REG, strlen(DUMP_REG)) == 0) { - hclge_dbg_dump_reg_cmd(hdev, &cmd_buf[sizeof(DUMP_REG)]); - } else if (strncmp(cmd_buf, "dump reset info", 15) == 0) { - hclge_dbg_dump_rst_info(hdev); - } else if (strncmp(cmd_buf, "dump serv info", 14) == 0) { - hclge_dbg_dump_serv_info(hdev); - } else if (strncmp(cmd_buf, "dump m7 info", 12) == 0) { - hclge_dbg_get_m7_stats_info(hdev); - } else if (strncmp(cmd_buf, "dump ncl_config", 15) == 0) { - hclge_dbg_dump_ncl_config(hdev, - &cmd_buf[sizeof("dump ncl_config")]); - } else if (strncmp(cmd_buf, "dump mac tnl status", 19) == 0) { - hclge_dbg_dump_mac_tnl_status(hdev); - } else if (strncmp(cmd_buf, DUMP_LOOPBACK, - strlen(DUMP_LOOPBACK)) == 0) { - hclge_dbg_dump_loopback(hdev); - } else if (strncmp(cmd_buf, "dump qs shaper", 14) == 0) { - hclge_dbg_dump_qs_shaper(hdev, - &cmd_buf[sizeof("dump qs shaper")]); - } else if (strncmp(cmd_buf, "dump uc mac list", 16) == 0) { - hclge_dbg_dump_mac_list(hdev, - &cmd_buf[sizeof("dump uc mac list")], - true); - } else if (strncmp(cmd_buf, "dump mc mac list", 16) == 0) { - hclge_dbg_dump_mac_list(hdev, - &cmd_buf[sizeof("dump mc mac list")], - false); - } else if (strncmp(cmd_buf, DUMP_INTERRUPT, - strlen(DUMP_INTERRUPT)) == 0) { - hclge_dbg_dump_interrupt(hdev); - } else { - dev_info(&hdev->pdev->dev, "unknown command\n"); - return -EINVAL; + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get vport%u txvlan cfg, ret = %d\n", + vf_id, ret); + return ret; + } + + tx_cfg = req->vport_vlan_cfg; + vlan_cfg->pvid = le16_to_cpu(req->def_vlan_tag1); + + vlan_cfg->accept_tag1 = hnae3_get_bit(tx_cfg, HCLGE_ACCEPT_TAG1_B); + vlan_cfg->accept_tag2 = hnae3_get_bit(tx_cfg, HCLGE_ACCEPT_TAG2_B); + vlan_cfg->accept_untag1 = hnae3_get_bit(tx_cfg, HCLGE_ACCEPT_UNTAG1_B); + vlan_cfg->accept_untag2 = hnae3_get_bit(tx_cfg, HCLGE_ACCEPT_UNTAG2_B); + vlan_cfg->insert_tag1 = hnae3_get_bit(tx_cfg, HCLGE_PORT_INS_TAG1_EN_B); + vlan_cfg->insert_tag2 = hnae3_get_bit(tx_cfg, HCLGE_PORT_INS_TAG2_EN_B); + vlan_cfg->shift_tag = hnae3_get_bit(tx_cfg, HCLGE_TAG_SHIFT_MODE_EN_B); + + return 0; +} + +static int hclge_get_vlan_filter_config_cmd(struct hclge_dev *hdev, + u8 vlan_type, u8 vf_id, + struct hclge_desc *desc) +{ + struct hclge_vlan_filter_ctrl_cmd *req; + int ret; + + hclge_cmd_setup_basic_desc(desc, HCLGE_OPC_VLAN_FILTER_CTRL, true); + req = (struct hclge_vlan_filter_ctrl_cmd *)desc->data; + req->vlan_type = vlan_type; + req->vf_id = vf_id; + + ret = hclge_cmd_send(&hdev->hw, desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "failed to get vport%u vlan filter config, ret = %d.\n", + vf_id, ret); + + return ret; +} + +static int hclge_get_vlan_filter_state(struct hclge_dev *hdev, u8 vlan_type, + u8 vf_id, u8 *vlan_fe) +{ + struct hclge_vlan_filter_ctrl_cmd *req; + struct hclge_desc desc; + int ret; + + ret = hclge_get_vlan_filter_config_cmd(hdev, vlan_type, vf_id, &desc); + if (ret) + return ret; + + req = (struct hclge_vlan_filter_ctrl_cmd *)desc.data; + *vlan_fe = req->vlan_fe; + + return 0; +} + +static int hclge_get_port_vlan_filter_bypass_state(struct hclge_dev *hdev, + u8 vf_id, u8 *bypass_en) +{ + struct hclge_port_vlan_filter_bypass_cmd *req; + struct hclge_desc desc; + int ret; + + if (!test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, hdev->ae_dev->caps)) + return 0; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PORT_VLAN_BYPASS, true); + req = (struct hclge_port_vlan_filter_bypass_cmd *)desc.data; + req->vf_id = vf_id; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get vport%u port vlan filter bypass state, ret = %d.\n", + vf_id, ret); + return ret; + } + + *bypass_en = hnae3_get_bit(req->bypass_state, HCLGE_INGRESS_BYPASS_B); + + return 0; +} + +static const struct hclge_dbg_item vlan_filter_items[] = { + { "FUNC_ID", 2 }, + { "I_VF_VLAN_FILTER", 2 }, + { "E_VF_VLAN_FILTER", 2 }, + { "PORT_VLAN_FILTER_BYPASS", 0 } +}; + +static const struct hclge_dbg_item vlan_offload_items[] = { + { "FUNC_ID", 2 }, + { "PVID", 4 }, + { "ACCEPT_TAG1", 2 }, + { "ACCEPT_TAG2", 2 }, + { "ACCEPT_UNTAG1", 2 }, + { "ACCEPT_UNTAG2", 2 }, + { "INSERT_TAG1", 2 }, + { "INSERT_TAG2", 2 }, + { "SHIFT_TAG", 2 }, + { "STRIP_TAG1", 2 }, + { "STRIP_TAG2", 2 }, + { "DROP_TAG1", 2 }, + { "DROP_TAG2", 2 }, + { "PRI_ONLY_TAG1", 2 }, + { "PRI_ONLY_TAG2", 0 } +}; + +static int hclge_dbg_dump_vlan_filter_config(struct hclge_dev *hdev, char *buf, + int len, int *pos) +{ + char content[HCLGE_DBG_VLAN_FLTR_INFO_LEN], str_id[HCLGE_DBG_ID_LEN]; + const char *result[ARRAY_SIZE(vlan_filter_items)]; + u8 i, j, vlan_fe, bypass, ingress, egress; + u8 func_num = pci_num_vf(hdev->pdev) + 1; /* pf and enabled vf num */ + int ret; + + ret = hclge_get_vlan_filter_state(hdev, HCLGE_FILTER_TYPE_PORT, 0, + &vlan_fe); + if (ret) + return ret; + ingress = vlan_fe & HCLGE_FILTER_FE_NIC_INGRESS_B; + egress = vlan_fe & HCLGE_FILTER_FE_NIC_EGRESS_B ? 1 : 0; + + *pos += scnprintf(buf, len, "I_PORT_VLAN_FILTER: %s\n", + state_str[ingress]); + *pos += scnprintf(buf + *pos, len - *pos, "E_PORT_VLAN_FILTER: %s\n", + state_str[egress]); + + hclge_dbg_fill_content(content, sizeof(content), vlan_filter_items, + NULL, ARRAY_SIZE(vlan_filter_items)); + *pos += scnprintf(buf + *pos, len - *pos, "%s", content); + + for (i = 0; i < func_num; i++) { + ret = hclge_get_vlan_filter_state(hdev, HCLGE_FILTER_TYPE_VF, i, + &vlan_fe); + if (ret) + return ret; + + ingress = vlan_fe & HCLGE_FILTER_FE_NIC_INGRESS_B; + egress = vlan_fe & HCLGE_FILTER_FE_NIC_EGRESS_B ? 1 : 0; + ret = hclge_get_port_vlan_filter_bypass_state(hdev, i, &bypass); + if (ret) + return ret; + j = 0; + result[j++] = hclge_dbg_get_func_id_str(str_id, i); + result[j++] = state_str[ingress]; + result[j++] = state_str[egress]; + result[j++] = + test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, + hdev->ae_dev->caps) ? state_str[bypass] : "NA"; + hclge_dbg_fill_content(content, sizeof(content), + vlan_filter_items, result, + ARRAY_SIZE(vlan_filter_items)); + *pos += scnprintf(buf + *pos, len - *pos, "%s", content); + } + *pos += scnprintf(buf + *pos, len - *pos, "\n"); + + return 0; +} + +static int hclge_dbg_dump_vlan_offload_config(struct hclge_dev *hdev, char *buf, + int len, int *pos) +{ + char str_id[HCLGE_DBG_ID_LEN], str_pvid[HCLGE_DBG_ID_LEN]; + const char *result[ARRAY_SIZE(vlan_offload_items)]; + char content[HCLGE_DBG_VLAN_OFFLOAD_INFO_LEN]; + u8 func_num = pci_num_vf(hdev->pdev) + 1; /* pf and enabled vf num */ + struct hclge_dbg_vlan_cfg vlan_cfg; + int ret; + u8 i, j; + + hclge_dbg_fill_content(content, sizeof(content), vlan_offload_items, + NULL, ARRAY_SIZE(vlan_offload_items)); + *pos += scnprintf(buf + *pos, len - *pos, "%s", content); + + for (i = 0; i < func_num; i++) { + ret = hclge_get_vlan_tx_offload_cfg(hdev, i, &vlan_cfg); + if (ret) + return ret; + + ret = hclge_get_vlan_rx_offload_cfg(hdev, i, &vlan_cfg); + if (ret) + return ret; + + sprintf(str_pvid, "%u", vlan_cfg.pvid); + j = 0; + result[j++] = hclge_dbg_get_func_id_str(str_id, i); + result[j++] = str_pvid; + result[j++] = state_str[vlan_cfg.accept_tag1]; + result[j++] = state_str[vlan_cfg.accept_tag2]; + result[j++] = state_str[vlan_cfg.accept_untag1]; + result[j++] = state_str[vlan_cfg.accept_untag2]; + result[j++] = state_str[vlan_cfg.insert_tag1]; + result[j++] = state_str[vlan_cfg.insert_tag2]; + result[j++] = state_str[vlan_cfg.shift_tag]; + result[j++] = state_str[vlan_cfg.strip_tag1]; + result[j++] = state_str[vlan_cfg.strip_tag2]; + result[j++] = state_str[vlan_cfg.drop_tag1]; + result[j++] = state_str[vlan_cfg.drop_tag2]; + result[j++] = state_str[vlan_cfg.pri_only1]; + result[j++] = state_str[vlan_cfg.pri_only2]; + + hclge_dbg_fill_content(content, sizeof(content), + vlan_offload_items, result, + ARRAY_SIZE(vlan_offload_items)); + *pos += scnprintf(buf + *pos, len - *pos, "%s", content); } return 0; } -int hclge_dbg_read_cmd(struct hnae3_handle *handle, const char *cmd_buf, +static int hclge_dbg_dump_vlan_config(struct hclge_dev *hdev, char *buf, + int len) +{ + int pos = 0; + int ret; + + ret = hclge_dbg_dump_vlan_filter_config(hdev, buf, len, &pos); + if (ret) + return ret; + + return hclge_dbg_dump_vlan_offload_config(hdev, buf, len, &pos); +} + +static int hclge_dbg_dump_ptp_info(struct hclge_dev *hdev, char *buf, int len) +{ + struct hclge_ptp *ptp = hdev->ptp; + u32 sw_cfg = ptp->ptp_cfg; + unsigned int tx_start; + unsigned int last_rx; + int pos = 0; + u32 hw_cfg; + int ret; + + pos += scnprintf(buf + pos, len - pos, "phc %s's debug info:\n", + ptp->info.name); + pos += scnprintf(buf + pos, len - pos, "ptp enable: %s\n", + test_bit(HCLGE_PTP_FLAG_EN, &ptp->flags) ? + "yes" : "no"); + pos += scnprintf(buf + pos, len - pos, "ptp tx enable: %s\n", + test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) ? + "yes" : "no"); + pos += scnprintf(buf + pos, len - pos, "ptp rx enable: %s\n", + test_bit(HCLGE_PTP_FLAG_RX_EN, &ptp->flags) ? + "yes" : "no"); + + last_rx = jiffies_to_msecs(ptp->last_rx); + pos += scnprintf(buf + pos, len - pos, "last rx time: %lu.%lu\n", + last_rx / MSEC_PER_SEC, last_rx % MSEC_PER_SEC); + pos += scnprintf(buf + pos, len - pos, "rx count: %lu\n", ptp->rx_cnt); + + tx_start = jiffies_to_msecs(ptp->tx_start); + pos += scnprintf(buf + pos, len - pos, "last tx start time: %lu.%lu\n", + tx_start / MSEC_PER_SEC, tx_start % MSEC_PER_SEC); + pos += scnprintf(buf + pos, len - pos, "tx count: %lu\n", ptp->tx_cnt); + pos += scnprintf(buf + pos, len - pos, "tx skipped count: %lu\n", + ptp->tx_skipped); + pos += scnprintf(buf + pos, len - pos, "tx timeout count: %lu\n", + ptp->tx_timeout); + pos += scnprintf(buf + pos, len - pos, "last tx seqid: %u\n", + ptp->last_tx_seqid); + + ret = hclge_ptp_cfg_qry(hdev, &hw_cfg); + if (ret) + return ret; + + pos += scnprintf(buf + pos, len - pos, "sw_cfg: %#x, hw_cfg: %#x\n", + sw_cfg, hw_cfg); + + pos += scnprintf(buf + pos, len - pos, "tx type: %d, rx filter: %d\n", + ptp->ts_cfg.tx_type, ptp->ts_cfg.rx_filter); + + return 0; +} + +static int hclge_dbg_dump_mac_uc(struct hclge_dev *hdev, char *buf, int len) +{ + hclge_dbg_dump_mac_list(hdev, buf, len, true); + + return 0; +} + +static int hclge_dbg_dump_mac_mc(struct hclge_dev *hdev, char *buf, int len) +{ + hclge_dbg_dump_mac_list(hdev, buf, len, false); + + return 0; +} + +static const struct hclge_dbg_func hclge_dbg_cmd_func[] = { + { + .cmd = HNAE3_DBG_CMD_TM_NODES, + .dbg_dump = hclge_dbg_dump_tm_nodes, + }, + { + .cmd = HNAE3_DBG_CMD_TM_PRI, + .dbg_dump = hclge_dbg_dump_tm_pri, + }, + { + .cmd = HNAE3_DBG_CMD_TM_QSET, + .dbg_dump = hclge_dbg_dump_tm_qset, + }, + { + .cmd = HNAE3_DBG_CMD_TM_MAP, + .dbg_dump = hclge_dbg_dump_tm_map, + }, + { + .cmd = HNAE3_DBG_CMD_TM_PG, + .dbg_dump = hclge_dbg_dump_tm_pg, + }, + { + .cmd = HNAE3_DBG_CMD_TM_PORT, + .dbg_dump = hclge_dbg_dump_tm_port, + }, + { + .cmd = HNAE3_DBG_CMD_TC_SCH_INFO, + .dbg_dump = hclge_dbg_dump_tc, + }, + { + .cmd = HNAE3_DBG_CMD_QOS_PAUSE_CFG, + .dbg_dump = hclge_dbg_dump_qos_pause_cfg, + }, + { + .cmd = HNAE3_DBG_CMD_QOS_PRI_MAP, + .dbg_dump = hclge_dbg_dump_qos_pri_map, + }, + { + .cmd = HNAE3_DBG_CMD_QOS_BUF_CFG, + .dbg_dump = hclge_dbg_dump_qos_buf_cfg, + }, + { + .cmd = HNAE3_DBG_CMD_MAC_UC, + .dbg_dump = hclge_dbg_dump_mac_uc, + }, + { + .cmd = HNAE3_DBG_CMD_MAC_MC, + .dbg_dump = hclge_dbg_dump_mac_mc, + }, + { + .cmd = HNAE3_DBG_CMD_MNG_TBL, + .dbg_dump = hclge_dbg_dump_mng_table, + }, + { + .cmd = HNAE3_DBG_CMD_LOOPBACK, + .dbg_dump = hclge_dbg_dump_loopback, + }, + { + .cmd = HNAE3_DBG_CMD_PTP_INFO, + .dbg_dump = hclge_dbg_dump_ptp_info, + }, + { + .cmd = HNAE3_DBG_CMD_INTERRUPT_INFO, + .dbg_dump = hclge_dbg_dump_interrupt, + }, + { + .cmd = HNAE3_DBG_CMD_RESET_INFO, + .dbg_dump = hclge_dbg_dump_rst_info, + }, + { + .cmd = HNAE3_DBG_CMD_IMP_INFO, + .dbg_dump = hclge_dbg_get_imp_stats_info, + }, + { + .cmd = HNAE3_DBG_CMD_NCL_CONFIG, + .dbg_dump = hclge_dbg_dump_ncl_config, + }, + { + .cmd = HNAE3_DBG_CMD_REG_BIOS_COMMON, + .dbg_dump_reg = hclge_dbg_dump_reg_cmd, + }, + { + .cmd = HNAE3_DBG_CMD_REG_SSU, + .dbg_dump_reg = hclge_dbg_dump_reg_cmd, + }, + { + .cmd = HNAE3_DBG_CMD_REG_IGU_EGU, + .dbg_dump_reg = hclge_dbg_dump_reg_cmd, + }, + { + .cmd = HNAE3_DBG_CMD_REG_RPU, + .dbg_dump_reg = hclge_dbg_dump_reg_cmd, + }, + { + .cmd = HNAE3_DBG_CMD_REG_NCSI, + .dbg_dump_reg = hclge_dbg_dump_reg_cmd, + }, + { + .cmd = HNAE3_DBG_CMD_REG_RTC, + .dbg_dump_reg = hclge_dbg_dump_reg_cmd, + }, + { + .cmd = HNAE3_DBG_CMD_REG_PPP, + .dbg_dump_reg = hclge_dbg_dump_reg_cmd, + }, + { + .cmd = HNAE3_DBG_CMD_REG_RCB, + .dbg_dump_reg = hclge_dbg_dump_reg_cmd, + }, + { + .cmd = HNAE3_DBG_CMD_REG_TQP, + .dbg_dump_reg = hclge_dbg_dump_reg_cmd, + }, + { + .cmd = HNAE3_DBG_CMD_REG_MAC, + .dbg_dump = hclge_dbg_dump_mac, + }, + { + .cmd = HNAE3_DBG_CMD_REG_DCB, + .dbg_dump = hclge_dbg_dump_dcb, + }, + { + .cmd = HNAE3_DBG_CMD_FD_TCAM, + .dbg_dump = hclge_dbg_dump_fd_tcam, + }, + { + .cmd = HNAE3_DBG_CMD_MAC_TNL_STATUS, + .dbg_dump = hclge_dbg_dump_mac_tnl_status, + }, + { + .cmd = HNAE3_DBG_CMD_SERV_INFO, + .dbg_dump = hclge_dbg_dump_serv_info, + }, + { + .cmd = HNAE3_DBG_CMD_VLAN_CONFIG, + .dbg_dump = hclge_dbg_dump_vlan_config, + }, + { + .cmd = HNAE3_DBG_CMD_FD_COUNTER, + .dbg_dump = hclge_dbg_dump_fd_counter, + }, + { + .cmd = HNAE3_DBG_CMD_UMV_INFO, + .dbg_dump = hclge_dbg_dump_umv_info, + }, +}; + +int hclge_dbg_read_cmd(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd, char *buf, int len) { struct hclge_vport *vport = hclge_get_vport(handle); + const struct hclge_dbg_func *cmd_func; struct hclge_dev *hdev = vport->back; + u32 i; - if (strncmp(cmd_buf, HNAE3_DBG_TM_NODES, - strlen(HNAE3_DBG_TM_NODES)) == 0) - return hclge_dbg_dump_tm_nodes(hdev, buf, len); - else if (strncmp(cmd_buf, HNAE3_DBG_TM_PRI, - strlen(HNAE3_DBG_TM_PRI)) == 0) - return hclge_dbg_dump_tm_pri(hdev, buf, len); - else if (strncmp(cmd_buf, HNAE3_DBG_TM_QSET, - strlen(HNAE3_DBG_TM_QSET)) == 0) - return hclge_dbg_dump_tm_qset(hdev, buf, len); + for (i = 0; i < ARRAY_SIZE(hclge_dbg_cmd_func); i++) { + if (cmd == hclge_dbg_cmd_func[i].cmd) { + cmd_func = &hclge_dbg_cmd_func[i]; + if (cmd_func->dbg_dump) + return cmd_func->dbg_dump(hdev, buf, len); + else + return cmd_func->dbg_dump_reg(hdev, cmd, buf, + len); + } + } + dev_err(&hdev->pdev->dev, "invalid command(%d)\n", cmd); return -EINVAL; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h index ca2ab6cf84d9..c526591a7240 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h @@ -7,7 +7,6 @@ #include #include "hclge_cmd.h" -#define HCLGE_DBG_BUF_LEN 256 #define HCLGE_DBG_MNG_TBL_MAX 64 #define HCLGE_DBG_MNG_VLAN_MASK_B BIT(0) @@ -70,6 +69,11 @@ struct hclge_dbg_reg_common_msg { enum hclge_opcode_type cmd; }; +struct hclge_dbg_tcam_msg { + u8 stage; + u32 loc; +}; + #define HCLGE_DBG_MAX_DFX_MSG_LEN 60 struct hclge_dbg_dfx_message { int flag; @@ -78,11 +82,18 @@ struct hclge_dbg_dfx_message { #define HCLGE_DBG_MAC_REG_TYPE_LEN 32 struct hclge_dbg_reg_type_info { - const char *reg_type; + enum hnae3_dbg_cmd cmd; const struct hclge_dbg_dfx_message *dfx_msg; struct hclge_dbg_reg_common_msg reg_msg; }; +struct hclge_dbg_func { + enum hnae3_dbg_cmd cmd; + int (*dbg_dump)(struct hclge_dev *hdev, char *buf, int len); + int (*dbg_dump_reg)(struct hclge_dev *hdev, enum hnae3_dbg_cmd cmd, + char *buf, int len); +}; + static const struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = { {false, "Reserved"}, {true, "BP_CPU_STATE"}, @@ -723,4 +734,36 @@ static const struct hclge_dbg_dfx_message hclge_dbg_tqp_reg[] = { {true, "RCB_CFG_TX_RING_EBDNUM"}, }; +#define HCLGE_DBG_INFO_LEN 256 +#define HCLGE_DBG_VLAN_FLTR_INFO_LEN 256 +#define HCLGE_DBG_VLAN_OFFLOAD_INFO_LEN 512 +#define HCLGE_DBG_ID_LEN 16 +#define HCLGE_DBG_ITEM_NAME_LEN 32 +#define HCLGE_DBG_DATA_STR_LEN 32 +#define HCLGE_DBG_TM_INFO_LEN 256 + +#define HCLGE_BILLION_NANO_SECONDS 1000000000 + +struct hclge_dbg_item { + char name[HCLGE_DBG_ITEM_NAME_LEN]; + u16 interval; /* blank numbers after the item */ +}; + +struct hclge_dbg_vlan_cfg { + u16 pvid; + u8 accept_tag1; + u8 accept_tag2; + u8 accept_untag1; + u8 accept_untag2; + u8 insert_tag1; + u8 insert_tag2; + u8 shift_tag; + u8 strip_tag1; + u8 strip_tag2; + u8 drop_tag1; + u8 drop_tag2; + u8 pri_only1; + u8 pri_only2; +}; + #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index 8223d699cd94..ec9a7f8bc3fe 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -631,6 +631,134 @@ static const struct hclge_hw_error hclge_rocee_qmm_ovf_err_int[] = { { /* sentinel */ } }; +static const struct hclge_hw_module_id hclge_hw_module_id_st[] = { + { + .module_id = MODULE_NONE, + .msg = "MODULE_NONE" + }, { + .module_id = MODULE_BIOS_COMMON, + .msg = "MODULE_BIOS_COMMON" + }, { + .module_id = MODULE_GE, + .msg = "MODULE_GE" + }, { + .module_id = MODULE_IGU_EGU, + .msg = "MODULE_IGU_EGU" + }, { + .module_id = MODULE_LGE, + .msg = "MODULE_LGE" + }, { + .module_id = MODULE_NCSI, + .msg = "MODULE_NCSI" + }, { + .module_id = MODULE_PPP, + .msg = "MODULE_PPP" + }, { + .module_id = MODULE_QCN, + .msg = "MODULE_QCN" + }, { + .module_id = MODULE_RCB_RX, + .msg = "MODULE_RCB_RX" + }, { + .module_id = MODULE_RTC, + .msg = "MODULE_RTC" + }, { + .module_id = MODULE_SSU, + .msg = "MODULE_SSU" + }, { + .module_id = MODULE_TM, + .msg = "MODULE_TM" + }, { + .module_id = MODULE_RCB_TX, + .msg = "MODULE_RCB_TX" + }, { + .module_id = MODULE_TXDMA, + .msg = "MODULE_TXDMA" + }, { + .module_id = MODULE_MASTER, + .msg = "MODULE_MASTER" + }, { + .module_id = MODULE_ROCEE_TOP, + .msg = "MODULE_ROCEE_TOP" + }, { + .module_id = MODULE_ROCEE_TIMER, + .msg = "MODULE_ROCEE_TIMER" + }, { + .module_id = MODULE_ROCEE_MDB, + .msg = "MODULE_ROCEE_MDB" + }, { + .module_id = MODULE_ROCEE_TSP, + .msg = "MODULE_ROCEE_TSP" + }, { + .module_id = MODULE_ROCEE_TRP, + .msg = "MODULE_ROCEE_TRP" + }, { + .module_id = MODULE_ROCEE_SCC, + .msg = "MODULE_ROCEE_SCC" + }, { + .module_id = MODULE_ROCEE_CAEP, + .msg = "MODULE_ROCEE_CAEP" + }, { + .module_id = MODULE_ROCEE_GEN_AC, + .msg = "MODULE_ROCEE_GEN_AC" + }, { + .module_id = MODULE_ROCEE_QMM, + .msg = "MODULE_ROCEE_QMM" + }, { + .module_id = MODULE_ROCEE_LSAN, + .msg = "MODULE_ROCEE_LSAN" + } +}; + +static const struct hclge_hw_type_id hclge_hw_type_id_st[] = { + { + .type_id = NONE_ERROR, + .msg = "none_error" + }, { + .type_id = FIFO_ERROR, + .msg = "fifo_error" + }, { + .type_id = MEMORY_ERROR, + .msg = "memory_error" + }, { + .type_id = POISON_ERROR, + .msg = "poison_error" + }, { + .type_id = MSIX_ECC_ERROR, + .msg = "msix_ecc_error" + }, { + .type_id = TQP_INT_ECC_ERROR, + .msg = "tqp_int_ecc_error" + }, { + .type_id = PF_ABNORMAL_INT_ERROR, + .msg = "pf_abnormal_int_error" + }, { + .type_id = MPF_ABNORMAL_INT_ERROR, + .msg = "mpf_abnormal_int_error" + }, { + .type_id = COMMON_ERROR, + .msg = "common_error" + }, { + .type_id = PORT_ERROR, + .msg = "port_error" + }, { + .type_id = ETS_ERROR, + .msg = "ets_error" + }, { + .type_id = NCSI_ERROR, + .msg = "ncsi_error" + }, { + .type_id = GLB_ERROR, + .msg = "glb_error" + }, { + .type_id = ROCEE_NORMAL_ERR, + .msg = "rocee_normal_error" + }, { + .type_id = ROCEE_OVF_ERR, + .msg = "rocee_ovf_error" + } +}; + static void hclge_log_error(struct device *dev, char *reg, const struct hclge_hw_error *err, u32 err_sts, unsigned long *reset_requests) @@ -1611,11 +1739,27 @@ static const struct hclge_hw_blk hw_blk[] = { { /* sentinel */ } }; +static void hclge_config_all_msix_error(struct hclge_dev *hdev, bool enable) +{ + u32 reg_val; + + reg_val = hclge_read_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG); + + if (enable) + reg_val |= BIT(HCLGE_VECTOR0_ALL_MSIX_ERR_B); + else + reg_val &= ~BIT(HCLGE_VECTOR0_ALL_MSIX_ERR_B); + + hclge_write_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG, reg_val); +} + int hclge_config_nic_hw_error(struct hclge_dev *hdev, bool state) { const struct hclge_hw_blk *module = hw_blk; int ret = 0; + hclge_config_all_msix_error(hdev, state); + while (module->name) { if (module->config_err_int) { ret = module->config_err_int(hdev, state); @@ -1876,11 +2020,8 @@ static int hclge_handle_pf_msix_error(struct hclge_dev *hdev, static int hclge_handle_all_hw_msix_error(struct hclge_dev *hdev, unsigned long *reset_requests) { - struct hclge_mac_tnl_stats mac_tnl_stats; - struct device *dev = &hdev->pdev->dev; u32 mpf_bd_num, pf_bd_num, bd_num; struct hclge_desc *desc; - u32 status; int ret; /* query the number of bds for the MSIx int status */ @@ -1903,29 +2044,7 @@ static int hclge_handle_all_hw_msix_error(struct hclge_dev *hdev, if (ret) goto msi_error; - /* query and clear mac tnl interruptions */ - hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_QUERY_MAC_TNL_INT, - true); - ret = hclge_cmd_send(&hdev->hw, &desc[0], 1); - if (ret) { - dev_err(dev, "query mac tnl int cmd failed (%d)\n", ret); - goto msi_error; - } - - status = le32_to_cpu(desc->data[0]); - if (status) { - /* When mac tnl interrupt occurs, we record current time and - * register status here in a fifo, then clear the status. So - * that if link status changes suddenly at some time, we can - * query them by debugfs. - */ - mac_tnl_stats.time = local_clock(); - mac_tnl_stats.status = status; - kfifo_put(&hdev->mac_tnl_log, mac_tnl_stats); - ret = hclge_clear_mac_tnl_int(hdev); - if (ret) - dev_err(dev, "clear mac tnl int failed (%d)\n", ret); - } + ret = hclge_handle_mac_tnl(hdev); msi_error: kfree(desc); @@ -1940,17 +2059,50 @@ int hclge_handle_hw_msix_error(struct hclge_dev *hdev, if (!test_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state)) { dev_err(dev, - "Can't handle - MSIx error reported during dev init\n"); - return 0; + "failed to handle msix error during dev init\n"); + return -EAGAIN; } return hclge_handle_all_hw_msix_error(hdev, reset_requests); } +int hclge_handle_mac_tnl(struct hclge_dev *hdev) +{ + struct hclge_mac_tnl_stats mac_tnl_stats; + struct device *dev = &hdev->pdev->dev; + struct hclge_desc desc; + u32 status; + int ret; + + /* query and clear mac tnl interruptions */ + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_MAC_TNL_INT, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(dev, "failed to query mac tnl int, ret = %d.\n", ret); + return ret; + } + + status = le32_to_cpu(desc.data[0]); + if (status) { + /* When mac tnl interrupt occurs, we record current time and + * register status here in a fifo, then clear the status. So + * that if link status changes suddenly at some time, we can + * query them by debugfs. + */ + mac_tnl_stats.time = local_clock(); + mac_tnl_stats.status = status; + kfifo_put(&hdev->mac_tnl_log, mac_tnl_stats); + ret = hclge_clear_mac_tnl_int(hdev); + if (ret) + dev_err(dev, "failed to clear mac tnl int, ret = %d.\n", + ret); + } + + return ret; +} + void hclge_handle_all_hns_hw_errors(struct hnae3_ae_dev *ae_dev) { -#define HCLGE_DESC_NO_DATA_LEN 8 - struct hclge_dev *hdev = ae_dev->priv; struct device *dev = &hdev->pdev->dev; u32 mpf_bd_num, pf_bd_num, bd_num; @@ -1999,3 +2151,207 @@ void hclge_handle_all_hns_hw_errors(struct hnae3_ae_dev *ae_dev) msi_error: kfree(desc); } + +bool hclge_find_error_source(struct hclge_dev *hdev) +{ + u32 msix_src_flag, hw_err_src_flag; + + msix_src_flag = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS) & + HCLGE_VECTOR0_REG_MSIX_MASK; + + hw_err_src_flag = hclge_read_dev(&hdev->hw, + HCLGE_RAS_PF_OTHER_INT_STS_REG) & + HCLGE_RAS_REG_ERR_MASK; + + return msix_src_flag || hw_err_src_flag; +} + +void hclge_handle_occurred_error(struct hclge_dev *hdev) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); + + if (hclge_find_error_source(hdev)) + hclge_handle_error_info_log(ae_dev); +} + +static void +hclge_handle_error_type_reg_log(struct device *dev, + struct hclge_mod_err_info *mod_info, + struct hclge_type_reg_err_info *type_reg_info) +{ +#define HCLGE_ERR_TYPE_MASK 0x7F +#define HCLGE_ERR_TYPE_IS_RAS_OFFSET 7 + + u8 mod_id, total_module, type_id, total_type, i, is_ras; + u8 index_module = MODULE_NONE; + u8 index_type = NONE_ERROR; + + mod_id = mod_info->mod_id; + type_id = type_reg_info->type_id & HCLGE_ERR_TYPE_MASK; + is_ras = type_reg_info->type_id >> HCLGE_ERR_TYPE_IS_RAS_OFFSET; + + total_module = ARRAY_SIZE(hclge_hw_module_id_st); + total_type = ARRAY_SIZE(hclge_hw_type_id_st); + + for (i = 0; i < total_module; i++) { + if (mod_id == hclge_hw_module_id_st[i].module_id) { + index_module = i; + break; + } + } + + for (i = 0; i < total_type; i++) { + if (type_id == hclge_hw_type_id_st[i].type_id) { + index_type = i; + break; + } + } + + if (index_module != MODULE_NONE && index_type != NONE_ERROR) + dev_err(dev, + "found %s %s, is %s error.\n", + hclge_hw_module_id_st[index_module].msg, + hclge_hw_type_id_st[index_type].msg, + is_ras ? "ras" : "msix"); + else + dev_err(dev, + "unknown module[%u] or type[%u].\n", mod_id, type_id); + + dev_err(dev, "reg_value:\n"); + for (i = 0; i < type_reg_info->reg_num; i++) + dev_err(dev, "0x%08x\n", type_reg_info->hclge_reg[i]); +} + +static void hclge_handle_error_module_log(struct hnae3_ae_dev *ae_dev, + const u32 *buf, u32 buf_size) +{ + struct hclge_type_reg_err_info *type_reg_info; + struct hclge_dev *hdev = ae_dev->priv; + struct device *dev = &hdev->pdev->dev; + struct hclge_mod_err_info *mod_info; + struct hclge_sum_err_info *sum_info; + u8 mod_num, err_num, i; + u32 offset = 0; + + sum_info = (struct hclge_sum_err_info *)&buf[offset++]; + if (sum_info->reset_type && + sum_info->reset_type != HNAE3_NONE_RESET) + set_bit(sum_info->reset_type, &ae_dev->hw_err_reset_req); + mod_num = sum_info->mod_num; + + while (mod_num--) { + if (offset >= buf_size) { + dev_err(dev, "The offset(%u) exceeds buf's size(%u).\n", + offset, buf_size); + return; + } + mod_info = (struct hclge_mod_err_info *)&buf[offset++]; + err_num = mod_info->err_num; + + for (i = 0; i < err_num; i++) { + if (offset >= buf_size) { + dev_err(dev, + "The offset(%u) exceeds buf size(%u).\n", + offset, buf_size); + return; + } + + type_reg_info = (struct hclge_type_reg_err_info *) + &buf[offset++]; + hclge_handle_error_type_reg_log(dev, mod_info, + type_reg_info); + + offset += type_reg_info->reg_num; + } + } +} + +static int hclge_query_all_err_bd_num(struct hclge_dev *hdev, u32 *bd_num) +{ + struct device *dev = &hdev->pdev->dev; + struct hclge_desc desc_bd; + int ret; + + hclge_cmd_setup_basic_desc(&desc_bd, HCLGE_QUERY_ALL_ERR_BD_NUM, true); + ret = hclge_cmd_send(&hdev->hw, &desc_bd, 1); + if (ret) { + dev_err(dev, "failed to query error bd_num, ret = %d.\n", ret); + return ret; + } + + *bd_num = le32_to_cpu(desc_bd.data[0]); + if (!(*bd_num)) { + dev_err(dev, "The value of bd_num is 0!\n"); + return -EINVAL; + } + + return 0; +} + +static int hclge_query_all_err_info(struct hclge_dev *hdev, + struct hclge_desc *desc, u32 bd_num) +{ + struct device *dev = &hdev->pdev->dev; + int ret; + + hclge_cmd_setup_basic_desc(desc, HCLGE_QUERY_ALL_ERR_INFO, true); + ret = hclge_cmd_send(&hdev->hw, desc, bd_num); + if (ret) + dev_err(dev, "failed to query error info, ret = %d.\n", ret); + + return ret; +} + +int hclge_handle_error_info_log(struct hnae3_ae_dev *ae_dev) +{ + u32 bd_num, desc_len, buf_len, buf_size, i; + struct hclge_dev *hdev = ae_dev->priv; + struct hclge_desc *desc; + __le32 *desc_data; + u32 *buf; + int ret; + + ret = hclge_query_all_err_bd_num(hdev, &bd_num); + if (ret) + goto out; + + desc_len = bd_num * sizeof(struct hclge_desc); + desc = kzalloc(desc_len, GFP_KERNEL); + if (!desc) { + ret = -ENOMEM; + goto out; + } + + ret = hclge_query_all_err_info(hdev, desc, bd_num); + if (ret) + goto err_desc; + + buf_len = bd_num * sizeof(struct hclge_desc) - HCLGE_DESC_NO_DATA_LEN; + buf_size = buf_len / sizeof(u32); + + desc_data = kzalloc(buf_len, GFP_KERNEL); + if (!desc_data) { + ret = -ENOMEM; + goto err_desc; + } + + buf = kzalloc(buf_len, GFP_KERNEL); + if (!buf) { + ret = -ENOMEM; + goto err_buf_alloc; + } + + memcpy(desc_data, &desc[0].data[0], buf_len); + for (i = 0; i < buf_size; i++) + buf[i] = le32_to_cpu(desc_data[i]); + + hclge_handle_error_module_log(ae_dev, buf, buf_size); + kfree(buf); + +err_buf_alloc: + kfree(desc_data); +err_desc: + kfree(desc); +out: + return ret; +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h index d647f3c84134..07987fb8332e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h @@ -15,6 +15,8 @@ #define HCLGE_RAS_PF_OTHER_INT_STS_REG 0x20B00 #define HCLGE_RAS_REG_NFE_MASK 0xFF00 #define HCLGE_RAS_REG_ROCEE_ERR_MASK 0x3000000 +#define HCLGE_RAS_REG_ERR_MASK \ + (HCLGE_RAS_REG_NFE_MASK | HCLGE_RAS_REG_ROCEE_ERR_MASK) #define HCLGE_VECTOR0_REG_MSIX_MASK 0x1FF00 @@ -107,6 +109,10 @@ #define HCLGE_ROCEE_OVF_ERR_INT_MASK 0x10000 #define HCLGE_ROCEE_OVF_ERR_TYPE_MASK 0x3F +#define HCLGE_DESC_DATA_MAX 8 +#define HCLGE_REG_NUM_MAX 256 +#define HCLGE_DESC_NO_DATA_LEN 8 + enum hclge_err_int_type { HCLGE_ERR_INT_MSIX = 0, HCLGE_ERR_INT_RAS_CE = 1, @@ -114,6 +120,56 @@ enum hclge_err_int_type { HCLGE_ERR_INT_RAS_FE = 3, }; +enum hclge_mod_name_list { + MODULE_NONE = 0, + MODULE_BIOS_COMMON = 1, + MODULE_GE = 2, + MODULE_IGU_EGU = 3, + MODULE_LGE = 4, + MODULE_NCSI = 5, + MODULE_PPP = 6, + MODULE_QCN = 7, + MODULE_RCB_RX = 8, + MODULE_RTC = 9, + MODULE_SSU = 10, + MODULE_TM = 11, + MODULE_RCB_TX = 12, + MODULE_TXDMA = 13, + MODULE_MASTER = 14, + /* add new MODULE NAME for NIC here in order */ + MODULE_ROCEE_TOP = 40, + MODULE_ROCEE_TIMER = 41, + MODULE_ROCEE_MDB = 42, + MODULE_ROCEE_TSP = 43, + MODULE_ROCEE_TRP = 44, + MODULE_ROCEE_SCC = 45, + MODULE_ROCEE_CAEP = 46, + MODULE_ROCEE_GEN_AC = 47, + MODULE_ROCEE_QMM = 48, + MODULE_ROCEE_LSAN = 49, + /* add new MODULE NAME for RoCEE here in order */ +}; + +enum hclge_err_type_list { + NONE_ERROR = 0, + FIFO_ERROR = 1, + MEMORY_ERROR = 2, + POISON_ERROR = 3, + MSIX_ECC_ERROR = 4, + TQP_INT_ECC_ERROR = 5, + PF_ABNORMAL_INT_ERROR = 6, + MPF_ABNORMAL_INT_ERROR = 7, + COMMON_ERROR = 8, + PORT_ERROR = 9, + ETS_ERROR = 10, + NCSI_ERROR = 11, + GLB_ERROR = 12, + /* add new ERROR TYPE for NIC here in order */ + ROCEE_NORMAL_ERR = 40, + ROCEE_OVF_ERR = 41, + /* add new ERROR TYPE for ROCEE here in order */ +}; + struct hclge_hw_blk { u32 msk; const char *name; @@ -126,11 +182,44 @@ struct hclge_hw_error { enum hnae3_reset_type reset_level; }; +struct hclge_hw_module_id { + enum hclge_mod_name_list module_id; + const char *msg; +}; + +struct hclge_hw_type_id { + enum hclge_err_type_list type_id; + const char *msg; +}; + +struct hclge_sum_err_info { + u8 reset_type; + u8 mod_num; + u8 rsv[2]; +}; + +struct hclge_mod_err_info { + u8 mod_id; + u8 err_num; + u8 rsv[2]; +}; + +struct hclge_type_reg_err_info { + u8 type_id; + u8 reg_num; + u8 rsv[2]; + u32 hclge_reg[HCLGE_REG_NUM_MAX]; +}; + int hclge_config_mac_tnl_int(struct hclge_dev *hdev, bool en); int hclge_config_nic_hw_error(struct hclge_dev *hdev, bool state); int hclge_config_rocee_ras_interrupt(struct hclge_dev *hdev, bool en); void hclge_handle_all_hns_hw_errors(struct hnae3_ae_dev *ae_dev); +bool hclge_find_error_source(struct hclge_dev *hdev); +void hclge_handle_occurred_error(struct hclge_dev *hdev); pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev); int hclge_handle_hw_msix_error(struct hclge_dev *hdev, unsigned long *reset_requests); +int hclge_handle_error_info_log(struct hnae3_ae_dev *ae_dev); +int hclge_handle_mac_tnl(struct hclge_dev *hdev); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 6304aed49f22..dd3354a57c62 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1279,6 +1279,7 @@ static u32 hclge_get_max_speed(u16 speed_ability) static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) { +#define HCLGE_TX_SPARE_SIZE_UNIT 4096 #define SPEED_ABILITY_EXT_SHIFT 8 struct hclge_cfg_param_cmd *req; @@ -1334,6 +1335,10 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) HCLGE_CFG_SPEED_ABILITY_EXT_S); cfg->speed_ability |= speed_ability_ext << SPEED_ABILITY_EXT_SHIFT; + cfg->vlan_fliter_cap = hnae3_get_field(__le32_to_cpu(req->param[1]), + HCLGE_CFG_VLAN_FLTR_CAP_M, + HCLGE_CFG_VLAN_FLTR_CAP_S); + cfg->umv_space = hnae3_get_field(__le32_to_cpu(req->param[1]), HCLGE_CFG_UMV_TBL_SPACE_M, HCLGE_CFG_UMV_TBL_SPACE_S); @@ -1354,6 +1359,15 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) cfg->pf_rss_size_max = cfg->pf_rss_size_max ? 1U << cfg->pf_rss_size_max : cfg->vf_rss_size_max; + + /* The unit of the tx spare buffer size queried from configuration + * file is HCLGE_TX_SPARE_SIZE_UNIT(4096) bytes, so a conversion is + * needed here. + */ + cfg->tx_spare_buf_size = hnae3_get_field(__le32_to_cpu(req->param[2]), + HCLGE_CFG_TX_SPARE_BUF_SIZE_M, + HCLGE_CFG_TX_SPARE_BUF_SIZE_S); + cfg->tx_spare_buf_size *= HCLGE_TX_SPARE_SIZE_UNIT; } /* hclge_get_cfg: query the static parameter from flash @@ -1513,6 +1527,7 @@ static void hclge_init_kdump_kernel_config(struct hclge_dev *hdev) static int hclge_configure(struct hclge_dev *hdev) { + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); struct hclge_cfg cfg; unsigned int i; int ret; @@ -1534,6 +1549,9 @@ static int hclge_configure(struct hclge_dev *hdev) hdev->tc_max = cfg.tc_num; hdev->tm_info.hw_pfc_map = 0; hdev->wanted_umv_size = cfg.umv_space; + hdev->tx_spare_buf_size = cfg.tx_spare_buf_size; + if (cfg.vlan_fliter_cap == HCLGE_VLAN_FLTR_CAN_MDF) + set_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps); if (hnae3_dev_fd_supported(hdev)) { hdev->fd_en = true; @@ -1729,6 +1747,7 @@ static int hclge_knic_setup(struct hclge_vport *vport, u16 num_tqps, kinfo->num_rx_desc = num_rx_desc; kinfo->rx_buf_len = hdev->rx_buf_len; + kinfo->tx_spare_buf_size = hdev->tx_spare_buf_size; kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, num_tqps, sizeof(struct hnae3_queue *), GFP_KERNEL); @@ -1843,6 +1862,7 @@ static int hclge_alloc_vport(struct hclge_dev *hdev) vport->mps = HCLGE_MAC_DEFAULT_FRAME; vport->port_base_vlan_cfg.state = HNAE3_PORT_BASE_VLAN_DISABLE; vport->rxvlan_cfg.rx_vlan_offload_en = true; + vport->req_vlan_fltr_en = true; INIT_LIST_HEAD(&vport->vlan_list); INIT_LIST_HEAD(&vport->uc_mac_list); INIT_LIST_HEAD(&vport->mc_mac_list); @@ -2835,6 +2855,14 @@ static void hclge_reset_task_schedule(struct hclge_dev *hdev) hclge_wq, &hdev->service_task, 0); } +static void hclge_errhand_task_schedule(struct hclge_dev *hdev) +{ + if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && + !test_and_set_bit(HCLGE_STATE_ERR_SERVICE_SCHED, &hdev->state)) + mod_delayed_work_on(cpumask_first(&hdev->affinity_mask), + hclge_wq, &hdev->service_task, 0); +} + void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time) { if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && @@ -3291,11 +3319,13 @@ static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf, static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) { - u32 cmdq_src_reg, msix_src_reg; + u32 cmdq_src_reg, msix_src_reg, hw_err_src_reg; /* fetch the events from their corresponding regs */ cmdq_src_reg = hclge_read_dev(&hdev->hw, HCLGE_VECTOR0_CMDQ_SRC_REG); msix_src_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS); + hw_err_src_reg = hclge_read_dev(&hdev->hw, + HCLGE_RAS_PF_OTHER_INT_STS_REG); /* Assumption: If by any chance reset and mailbox events are reported * together then we will only process reset event in this go and will @@ -3323,10 +3353,15 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) return HCLGE_VECTOR0_EVENT_RST; } - /* check for vector0 msix event source */ - if (msix_src_reg & HCLGE_VECTOR0_REG_MSIX_MASK) { - *clearval = msix_src_reg; + /* check for vector0 msix event and hardware error event source */ + if (msix_src_reg & HCLGE_VECTOR0_REG_MSIX_MASK || + hw_err_src_reg & HCLGE_RAS_REG_ERR_MASK) return HCLGE_VECTOR0_EVENT_ERR; + + /* check for vector0 ptp event source */ + if (BIT(HCLGE_VECTOR0_REG_PTP_INT_B) & msix_src_reg) { + *clearval = msix_src_reg; + return HCLGE_VECTOR0_EVENT_PTP; } /* check for vector0 mailbox(=CMDQ RX) event source */ @@ -3338,9 +3373,8 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) /* print other vector0 event source */ dev_info(&hdev->pdev->dev, - "CMDQ INT status:0x%x, other INT status:0x%x\n", - cmdq_src_reg, msix_src_reg); - *clearval = msix_src_reg; + "INT status: CMDQ(%#x) HW errors(%#x) other(%#x)\n", + cmdq_src_reg, hw_err_src_reg, msix_src_reg); return HCLGE_VECTOR0_EVENT_OTHER; } @@ -3349,6 +3383,7 @@ static void hclge_clear_event_cause(struct hclge_dev *hdev, u32 event_type, u32 regclr) { switch (event_type) { + case HCLGE_VECTOR0_EVENT_PTP: case HCLGE_VECTOR0_EVENT_RST: hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG, regclr); break; @@ -3377,6 +3412,7 @@ static void hclge_enable_vector(struct hclge_misc_vector *vector, bool enable) static irqreturn_t hclge_misc_irq_handle(int irq, void *data) { struct hclge_dev *hdev = data; + unsigned long flags; u32 clearval = 0; u32 event_cause; @@ -3386,21 +3422,16 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data) /* vector 0 interrupt is shared with reset and mailbox source events.*/ switch (event_cause) { case HCLGE_VECTOR0_EVENT_ERR: - /* we do not know what type of reset is required now. This could - * only be decided after we fetch the type of errors which - * caused this event. Therefore, we will do below for now: - * 1. Assert HNAE3_UNKNOWN_RESET type of reset. This means we - * have defered type of reset to be used. - * 2. Schedule the reset service task. - * 3. When service task receives HNAE3_UNKNOWN_RESET type it - * will fetch the correct type of reset. This would be done - * by first decoding the types of errors. - */ - set_bit(HNAE3_UNKNOWN_RESET, &hdev->reset_request); - fallthrough; + hclge_errhand_task_schedule(hdev); + break; case HCLGE_VECTOR0_EVENT_RST: hclge_reset_task_schedule(hdev); break; + case HCLGE_VECTOR0_EVENT_PTP: + spin_lock_irqsave(&hdev->ptp->lock, flags); + hclge_ptp_clean_tx_hwts(hdev); + spin_unlock_irqrestore(&hdev->ptp->lock, flags); + break; case HCLGE_VECTOR0_EVENT_MBX: /* If we are here then, * 1. Either we are not handling any mbx task and we are not @@ -3421,15 +3452,11 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data) hclge_clear_event_cause(hdev, event_cause, clearval); - /* Enable interrupt if it is not cause by reset. And when - * clearval equal to 0, it means interrupt status may be - * cleared by hardware before driver reads status register. - * For this case, vector0 interrupt also should be enabled. - */ - if (!clearval || - event_cause == HCLGE_VECTOR0_EVENT_MBX) { + /* Enable interrupt if it is not caused by reset event or error event */ + if (event_cause == HCLGE_VECTOR0_EVENT_PTP || + event_cause == HCLGE_VECTOR0_EVENT_MBX || + event_cause == HCLGE_VECTOR0_EVENT_OTHER) hclge_enable_vector(&hdev->misc_vector, true); - } return IRQ_HANDLED; } @@ -3786,28 +3813,6 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev, enum hnae3_reset_type rst_level = HNAE3_NONE_RESET; struct hclge_dev *hdev = ae_dev->priv; - /* first, resolve any unknown reset type to the known type(s) */ - if (test_bit(HNAE3_UNKNOWN_RESET, addr)) { - u32 msix_sts_reg = hclge_read_dev(&hdev->hw, - HCLGE_MISC_VECTOR_INT_STS); - /* we will intentionally ignore any errors from this function - * as we will end up in *some* reset request in any case - */ - if (hclge_handle_hw_msix_error(hdev, addr)) - dev_info(&hdev->pdev->dev, "received msix interrupt 0x%x\n", - msix_sts_reg); - - clear_bit(HNAE3_UNKNOWN_RESET, addr); - /* We defered the clearing of the error event which caused - * interrupt since it was not posssible to do that in - * interrupt context (and this is the reason we introduced - * new UNKNOWN reset type). Now, the errors have been - * handled and cleared in hardware we can safely enable - * interrupts. This is an exception to the norm. - */ - hclge_enable_vector(&hdev->misc_vector, true); - } - /* return the highest priority reset level amongst all */ if (test_bit(HNAE3_IMP_RESET, addr)) { rst_level = HNAE3_IMP_RESET; @@ -3936,6 +3941,21 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev) return ret; } +static void hclge_show_rst_info(struct hclge_dev *hdev) +{ + char *buf; + + buf = kzalloc(HCLGE_DBG_RESET_INFO_LEN, GFP_KERNEL); + if (!buf) + return; + + hclge_dbg_dump_rst_info(hdev, buf, HCLGE_DBG_RESET_INFO_LEN); + + dev_info(&hdev->pdev->dev, "dump reset info:\n%s", buf); + + kfree(buf); +} + static bool hclge_reset_err_handle(struct hclge_dev *hdev) { #define MAX_RESET_FAIL_CNT 5 @@ -3966,7 +3986,7 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev) dev_err(&hdev->pdev->dev, "Reset fail!\n"); - hclge_dbg_dump_rst_info(hdev); + hclge_show_rst_info(hdev); set_bit(HCLGE_STATE_RST_FAIL, &hdev->state); @@ -4241,6 +4261,68 @@ static void hclge_reset_subtask(struct hclge_dev *hdev) hdev->reset_type = HNAE3_NONE_RESET; } +static void hclge_handle_err_reset_request(struct hclge_dev *hdev) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); + enum hnae3_reset_type reset_type; + + if (ae_dev->hw_err_reset_req) { + reset_type = hclge_get_reset_level(ae_dev, + &ae_dev->hw_err_reset_req); + hclge_set_def_reset_request(ae_dev, reset_type); + } + + if (hdev->default_reset_request && ae_dev->ops->reset_event) + ae_dev->ops->reset_event(hdev->pdev, NULL); + + /* enable interrupt after error handling complete */ + hclge_enable_vector(&hdev->misc_vector, true); +} + +static void hclge_handle_err_recovery(struct hclge_dev *hdev) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); + + ae_dev->hw_err_reset_req = 0; + + if (hclge_find_error_source(hdev)) { + hclge_handle_error_info_log(ae_dev); + hclge_handle_mac_tnl(hdev); + } + + hclge_handle_err_reset_request(hdev); +} + +static void hclge_misc_err_recovery(struct hclge_dev *hdev) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); + struct device *dev = &hdev->pdev->dev; + u32 msix_sts_reg; + + msix_sts_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS); + if (msix_sts_reg & HCLGE_VECTOR0_REG_MSIX_MASK) { + if (hclge_handle_hw_msix_error + (hdev, &hdev->default_reset_request)) + dev_info(dev, "received msix interrupt 0x%x\n", + msix_sts_reg); + } + + hclge_handle_hw_ras_error(ae_dev); + + hclge_handle_err_reset_request(hdev); +} + +static void hclge_errhand_service_task(struct hclge_dev *hdev) +{ + if (!test_and_clear_bit(HCLGE_STATE_ERR_SERVICE_SCHED, &hdev->state)) + return; + + if (hnae3_dev_ras_imp_supported(hdev)) + hclge_handle_err_recovery(hdev); + else + hclge_misc_err_recovery(hdev); +} + static void hclge_reset_service_task(struct hclge_dev *hdev) { if (!test_and_clear_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state)) @@ -4319,19 +4401,43 @@ out: hclge_task_schedule(hdev, delta); } +static void hclge_ptp_service_task(struct hclge_dev *hdev) +{ + unsigned long flags; + + if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state) || + !test_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state) || + !time_is_before_jiffies(hdev->ptp->tx_start + HZ)) + return; + + /* to prevent concurrence with the irq handler */ + spin_lock_irqsave(&hdev->ptp->lock, flags); + + /* check HCLGE_STATE_PTP_TX_HANDLING here again, since the irq + * handler may handle it just before spin_lock_irqsave(). + */ + if (test_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state)) + hclge_ptp_clean_tx_hwts(hdev); + + spin_unlock_irqrestore(&hdev->ptp->lock, flags); +} + static void hclge_service_task(struct work_struct *work) { struct hclge_dev *hdev = container_of(work, struct hclge_dev, service_task.work); + hclge_errhand_service_task(hdev); hclge_reset_service_task(hdev); + hclge_ptp_service_task(hdev); hclge_mailbox_service_task(hdev); hclge_periodic_service_task(hdev); - /* Handle reset and mbx again in case periodical task delays the - * handling by calling hclge_task_schedule() in + /* Handle error recovery, reset and mbx again in case periodical task + * delays the handling by calling hclge_task_schedule() in * hclge_periodic_service_task(). */ + hclge_errhand_service_task(hdev); hclge_reset_service_task(hdev); hclge_mailbox_service_task(hdev); } @@ -5168,9 +5274,8 @@ static int hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc, static void hclge_request_update_promisc_mode(struct hnae3_handle *handle) { struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; - set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state); + set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state); } static void hclge_sync_fd_state(struct hclge_dev *hdev) @@ -5895,8 +6000,14 @@ static int hclge_config_action(struct hclge_dev *hdev, u8 stage, ad_data.queue_id = rule->queue_id; } - ad_data.use_counter = false; - ad_data.counter_id = 0; + if (hdev->fd_cfg.cnt_num[HCLGE_FD_STAGE_1]) { + ad_data.use_counter = true; + ad_data.counter_id = rule->vf_id % + hdev->fd_cfg.cnt_num[HCLGE_FD_STAGE_1]; + } else { + ad_data.use_counter = false; + ad_data.counter_id = 0; + } ad_data.use_next_stage = false; ad_data.next_input_key = 0; @@ -8035,6 +8146,7 @@ int hclge_vport_start(struct hclge_vport *vport) struct hclge_dev *hdev = vport->back; set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state); + set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state); vport->last_active_jiffies = jiffies; if (test_bit(vport->vport_id, hdev->vport_config_block)) { @@ -8776,8 +8888,7 @@ static bool hclge_sync_from_add_list(struct list_head *add_list, kfree(mac_node); } else if (mac_node->state == HCLGE_MAC_ACTIVE) { mac_node->state = HCLGE_MAC_TO_DEL; - list_del(&mac_node->node); - list_add_tail(&mac_node->node, mac_list); + list_move_tail(&mac_node->node, mac_list); } else { list_del(&mac_node->node); kfree(mac_node); @@ -8806,8 +8917,7 @@ static void hclge_sync_from_del_list(struct list_head *del_list, list_del(&mac_node->node); kfree(mac_node); } else { - list_del(&mac_node->node); - list_add_tail(&mac_node->node, mac_list); + list_move_tail(&mac_node->node, mac_list); } } } @@ -8851,8 +8961,7 @@ static void hclge_sync_vport_mac_table(struct hclge_vport *vport, list_for_each_entry_safe(mac_node, tmp, list, node) { switch (mac_node->state) { case HCLGE_MAC_TO_DEL: - list_del(&mac_node->node); - list_add_tail(&mac_node->node, &tmp_del_list); + list_move_tail(&mac_node->node, &tmp_del_list); break; case HCLGE_MAC_TO_ADD: new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC); @@ -8934,8 +9043,7 @@ static void hclge_build_del_list(struct list_head *list, switch (mac_cfg->state) { case HCLGE_MAC_TO_DEL: case HCLGE_MAC_ACTIVE: - list_del(&mac_cfg->node); - list_add_tail(&mac_cfg->node, tmp_del_list); + list_move_tail(&mac_cfg->node, tmp_del_list); break; case HCLGE_MAC_TO_ADD: if (is_del_list) { @@ -9030,8 +9138,7 @@ static void hclge_uninit_vport_mac_list(struct hclge_vport *vport, switch (mac_node->state) { case HCLGE_MAC_TO_DEL: case HCLGE_MAC_ACTIVE: - list_del(&mac_node->node); - list_add_tail(&mac_node->node, &tmp_del_list); + list_move_tail(&mac_node->node, &tmp_del_list); break; case HCLGE_MAC_TO_ADD: list_del(&mac_node->node); @@ -9360,12 +9467,41 @@ static int hclge_do_ioctl(struct hnae3_handle *handle, struct ifreq *ifr, struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - if (!hdev->hw.mac.phydev) - return hclge_mii_ioctl(hdev, ifr, cmd); + switch (cmd) { + case SIOCGHWTSTAMP: + return hclge_ptp_get_cfg(hdev, ifr); + case SIOCSHWTSTAMP: + return hclge_ptp_set_cfg(hdev, ifr); + default: + if (!hdev->hw.mac.phydev) + return hclge_mii_ioctl(hdev, ifr, cmd); + } return phy_mii_ioctl(hdev->hw.mac.phydev, ifr, cmd); } +static int hclge_set_port_vlan_filter_bypass(struct hclge_dev *hdev, u8 vf_id, + bool bypass_en) +{ + struct hclge_port_vlan_filter_bypass_cmd *req; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PORT_VLAN_BYPASS, false); + req = (struct hclge_port_vlan_filter_bypass_cmd *)desc.data; + req->vf_id = vf_id; + hnae3_set_bit(req->bypass_state, HCLGE_INGRESS_BYPASS_B, + bypass_en ? 1 : 0); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "failed to set vport%u port vlan filter bypass state, ret = %d.\n", + vf_id, ret); + + return ret; +} + static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, u8 fe_type, bool filter_en, u8 vf_id) { @@ -9399,37 +9535,99 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type, return ret; } -#define HCLGE_FILTER_TYPE_VF 0 -#define HCLGE_FILTER_TYPE_PORT 1 -#define HCLGE_FILTER_FE_EGRESS_V1_B BIT(0) -#define HCLGE_FILTER_FE_NIC_INGRESS_B BIT(0) -#define HCLGE_FILTER_FE_NIC_EGRESS_B BIT(1) -#define HCLGE_FILTER_FE_ROCE_INGRESS_B BIT(2) -#define HCLGE_FILTER_FE_ROCE_EGRESS_B BIT(3) -#define HCLGE_FILTER_FE_EGRESS (HCLGE_FILTER_FE_NIC_EGRESS_B \ - | HCLGE_FILTER_FE_ROCE_EGRESS_B) -#define HCLGE_FILTER_FE_INGRESS (HCLGE_FILTER_FE_NIC_INGRESS_B \ - | HCLGE_FILTER_FE_ROCE_INGRESS_B) - -static void hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable) +static int hclge_set_vport_vlan_filter(struct hclge_vport *vport, bool enable) { - struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hnae3_ae_dev *ae_dev = hdev->ae_dev; + int ret; + + if (hdev->ae_dev->dev_version < HNAE3_DEVICE_VERSION_V2) + return hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, + HCLGE_FILTER_FE_EGRESS_V1_B, + enable, vport->vport_id); + + ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, + HCLGE_FILTER_FE_EGRESS, enable, + vport->vport_id); + if (ret) + return ret; + + if (test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps)) + ret = hclge_set_port_vlan_filter_bypass(hdev, vport->vport_id, + !enable); + else if (!vport->vport_id) + ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT, + HCLGE_FILTER_FE_INGRESS, + enable, 0); + + return ret; +} + +static bool hclge_need_enable_vport_vlan_filter(struct hclge_vport *vport) +{ + struct hnae3_handle *handle = &vport->nic; + struct hclge_vport_vlan_cfg *vlan, *tmp; struct hclge_dev *hdev = vport->back; - if (hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2) { - hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, - HCLGE_FILTER_FE_EGRESS, enable, 0); - hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT, - HCLGE_FILTER_FE_INGRESS, enable, 0); - } else { - hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, - HCLGE_FILTER_FE_EGRESS_V1_B, enable, - 0); + if (vport->vport_id) { + if (vport->port_base_vlan_cfg.state != + HNAE3_PORT_BASE_VLAN_DISABLE) + return true; + + if (vport->vf_info.trusted && vport->vf_info.request_uc_en) + return false; + } else if (handle->netdev_flags & HNAE3_USER_UPE) { + return false; } - if (enable) - handle->netdev_flags |= HNAE3_VLAN_FLTR; - else - handle->netdev_flags &= ~HNAE3_VLAN_FLTR; + + if (!vport->req_vlan_fltr_en) + return false; + + /* compatible with former device, always enable vlan filter */ + if (!test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, hdev->ae_dev->caps)) + return true; + + list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) + if (vlan->vlan_id != 0) + return true; + + return false; +} + +int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en) +{ + struct hclge_dev *hdev = vport->back; + bool need_en; + int ret; + + mutex_lock(&hdev->vport_lock); + + vport->req_vlan_fltr_en = request_en; + + need_en = hclge_need_enable_vport_vlan_filter(vport); + if (need_en == vport->cur_vlan_fltr_en) { + mutex_unlock(&hdev->vport_lock); + return 0; + } + + ret = hclge_set_vport_vlan_filter(vport, need_en); + if (ret) { + mutex_unlock(&hdev->vport_lock); + return ret; + } + + vport->cur_vlan_fltr_en = need_en; + + mutex_unlock(&hdev->vport_lock); + + return 0; +} + +static int hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + + return hclge_enable_vport_vlan_filter(vport, enable); } static int hclge_set_vf_vlan_filter_cmd(struct hclge_dev *hdev, u16 vfid, @@ -9709,7 +9907,7 @@ static int hclge_set_vlan_rx_offload_cfg(struct hclge_vport *vport) static int hclge_vlan_offload_cfg(struct hclge_vport *vport, u16 port_base_vlan_state, - u16 vlan_tag) + u16 vlan_tag, u8 qos) { int ret; @@ -9723,7 +9921,8 @@ static int hclge_vlan_offload_cfg(struct hclge_vport *vport, vport->txvlan_cfg.accept_tag1 = ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3; vport->txvlan_cfg.insert_tag1_en = true; - vport->txvlan_cfg.default_tag1 = vlan_tag; + vport->txvlan_cfg.default_tag1 = (qos << VLAN_PRIO_SHIFT) | + vlan_tag; } vport->txvlan_cfg.accept_untag1 = true; @@ -9822,6 +10021,7 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev) vport->vport_id); if (ret) return ret; + vport->cur_vlan_fltr_en = true; } ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT, @@ -9837,8 +10037,6 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev) return ret; } - handle->netdev_flags |= HNAE3_VLAN_FLTR; - hdev->vlan_type_cfg.rx_in_fst_vlan_type = HCLGE_DEF_VLAN_TYPE; hdev->vlan_type_cfg.rx_in_sec_vlan_type = HCLGE_DEF_VLAN_TYPE; hdev->vlan_type_cfg.rx_ot_fst_vlan_type = HCLGE_DEF_VLAN_TYPE; @@ -9852,13 +10050,15 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev) for (i = 0; i < hdev->num_alloc_vport; i++) { u16 vlan_tag; + u8 qos; vport = &hdev->vport[i]; vlan_tag = vport->port_base_vlan_cfg.vlan_info.vlan_tag; + qos = vport->port_base_vlan_cfg.vlan_info.qos; ret = hclge_vlan_offload_cfg(vport, vport->port_base_vlan_cfg.state, - vlan_tag); + vlan_tag, qos); if (ret) return ret; } @@ -10033,7 +10233,6 @@ static void hclge_restore_hw_table(struct hclge_dev *hdev) hclge_restore_mac_table_common(vport); hclge_restore_vport_vlan_table(vport); - set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state); set_bit(HCLGE_STATE_FD_USER_DEF_CHANGED, &hdev->state); hclge_restore_fd_entries(handle); } @@ -10060,6 +10259,14 @@ int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable) return hclge_set_vlan_rx_offload_cfg(vport); } +static void hclge_set_vport_vlan_fltr_change(struct hclge_vport *vport) +{ + struct hclge_dev *hdev = vport->back; + + if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, hdev->ae_dev->caps)) + set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE, &vport->state); +} + static int hclge_update_vlan_filter_entries(struct hclge_vport *vport, u16 port_base_vlan_state, struct hclge_vlan_info *new_info, @@ -10070,6 +10277,10 @@ static int hclge_update_vlan_filter_entries(struct hclge_vport *vport, if (port_base_vlan_state == HNAE3_PORT_BASE_VLAN_ENABLE) { hclge_rm_vport_all_vlan_table(vport, false); + /* force clear VLAN 0 */ + ret = hclge_set_vf_vlan_common(hdev, vport->vport_id, true, 0); + if (ret) + return ret; return hclge_set_vlan_filter_hw(hdev, htons(new_info->vlan_proto), vport->vport_id, @@ -10077,6 +10288,11 @@ static int hclge_update_vlan_filter_entries(struct hclge_vport *vport, false); } + /* force add VLAN 0 */ + ret = hclge_set_vf_vlan_common(hdev, vport->vport_id, false, 0); + if (ret) + return ret; + ret = hclge_set_vlan_filter_hw(hdev, htons(old_info->vlan_proto), vport->vport_id, old_info->vlan_tag, true); @@ -10086,6 +10302,18 @@ static int hclge_update_vlan_filter_entries(struct hclge_vport *vport, return hclge_add_vport_all_vlan_table(vport); } +static bool hclge_need_update_vlan_filter(const struct hclge_vlan_info *new_cfg, + const struct hclge_vlan_info *old_cfg) +{ + if (new_cfg->vlan_tag != old_cfg->vlan_tag) + return true; + + if (new_cfg->vlan_tag == 0 && (new_cfg->qos == 0 || old_cfg->qos == 0)) + return true; + + return false; +} + int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state, struct hclge_vlan_info *vlan_info) { @@ -10096,10 +10324,14 @@ int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state, old_vlan_info = &vport->port_base_vlan_cfg.vlan_info; - ret = hclge_vlan_offload_cfg(vport, state, vlan_info->vlan_tag); + ret = hclge_vlan_offload_cfg(vport, state, vlan_info->vlan_tag, + vlan_info->qos); if (ret) return ret; + if (!hclge_need_update_vlan_filter(vlan_info, old_vlan_info)) + goto out; + if (state == HNAE3_PORT_BASE_VLAN_MODIFY) { /* add new VLAN tag */ ret = hclge_set_vlan_filter_hw(hdev, @@ -10111,15 +10343,23 @@ int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state, return ret; /* remove old VLAN tag */ - ret = hclge_set_vlan_filter_hw(hdev, - htons(old_vlan_info->vlan_proto), - vport->vport_id, - old_vlan_info->vlan_tag, - true); - if (ret) + if (old_vlan_info->vlan_tag == 0) + ret = hclge_set_vf_vlan_common(hdev, vport->vport_id, + true, 0); + else + ret = hclge_set_vlan_filter_hw(hdev, + htons(ETH_P_8021Q), + vport->vport_id, + old_vlan_info->vlan_tag, + true); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to clear vport%u port base vlan %u, ret = %d.\n", + vport->vport_id, old_vlan_info->vlan_tag, ret); return ret; + } - goto update; + goto out; } ret = hclge_update_vlan_filter_entries(vport, state, vlan_info, @@ -10127,38 +10367,38 @@ int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state, if (ret) return ret; - /* update state only when disable/enable port based VLAN */ +out: vport->port_base_vlan_cfg.state = state; if (state == HNAE3_PORT_BASE_VLAN_DISABLE) nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_DISABLE; else nic->port_base_vlan_state = HNAE3_PORT_BASE_VLAN_ENABLE; -update: - vport->port_base_vlan_cfg.vlan_info.vlan_tag = vlan_info->vlan_tag; - vport->port_base_vlan_cfg.vlan_info.qos = vlan_info->qos; - vport->port_base_vlan_cfg.vlan_info.vlan_proto = vlan_info->vlan_proto; + vport->port_base_vlan_cfg.vlan_info = *vlan_info; + hclge_set_vport_vlan_fltr_change(vport); return 0; } static u16 hclge_get_port_base_vlan_state(struct hclge_vport *vport, enum hnae3_port_base_vlan_state state, - u16 vlan) + u16 vlan, u8 qos) { if (state == HNAE3_PORT_BASE_VLAN_DISABLE) { - if (!vlan) + if (!vlan && !qos) return HNAE3_PORT_BASE_VLAN_NOCHANGE; - else - return HNAE3_PORT_BASE_VLAN_ENABLE; - } else { - if (!vlan) - return HNAE3_PORT_BASE_VLAN_DISABLE; - else if (vport->port_base_vlan_cfg.vlan_info.vlan_tag == vlan) - return HNAE3_PORT_BASE_VLAN_NOCHANGE; - else - return HNAE3_PORT_BASE_VLAN_MODIFY; + + return HNAE3_PORT_BASE_VLAN_ENABLE; } + + if (!vlan && !qos) + return HNAE3_PORT_BASE_VLAN_DISABLE; + + if (vport->port_base_vlan_cfg.vlan_info.vlan_tag == vlan && + vport->port_base_vlan_cfg.vlan_info.qos == qos) + return HNAE3_PORT_BASE_VLAN_NOCHANGE; + + return HNAE3_PORT_BASE_VLAN_MODIFY; } static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid, @@ -10186,7 +10426,7 @@ static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid, state = hclge_get_port_base_vlan_state(vport, vport->port_base_vlan_cfg.state, - vlan); + vlan, qos); if (state == HNAE3_PORT_BASE_VLAN_NOCHANGE) return 0; @@ -10209,8 +10449,7 @@ static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid, test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state)) hclge_push_vf_port_base_vlan_info(&hdev->vport[0], vport->vport_id, state, - vlan, qos, - ntohs(proto)); + &vlan_info); return 0; } @@ -10280,9 +10519,37 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, */ set_bit(vlan_id, vport->vlan_del_fail_bmap); } + + hclge_set_vport_vlan_fltr_change(vport); + return ret; } +static void hclge_sync_vlan_fltr_state(struct hclge_dev *hdev) +{ + struct hclge_vport *vport; + int ret; + u16 i; + + for (i = 0; i < hdev->num_alloc_vport; i++) { + vport = &hdev->vport[i]; + if (!test_and_clear_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE, + &vport->state)) + continue; + + ret = hclge_enable_vport_vlan_filter(vport, + vport->req_vlan_fltr_en); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to sync vlan filter state for vport%u, ret = %d\n", + vport->vport_id, ret); + set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE, + &vport->state); + return; + } + } +} + static void hclge_sync_vlan_filter(struct hclge_dev *hdev) { #define HCLGE_MAX_SYNC_COUNT 60 @@ -10305,6 +10572,7 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev) clear_bit(vlan_id, vport->vlan_del_fail_bmap); hclge_rm_vport_vlan_table(vport, vlan_id, false); + hclge_set_vport_vlan_fltr_change(vport); sync_cnt++; if (sync_cnt >= HCLGE_MAX_SYNC_COUNT) @@ -10314,6 +10582,8 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev) VLAN_N_VID); } } + + hclge_sync_vlan_fltr_state(hdev); } static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps) @@ -10807,6 +11077,8 @@ static void hclge_info_show(struct hclge_dev *hdev) hdev->flag & HCLGE_FLAG_DCB_ENABLE ? "enable" : "disable"); dev_info(dev, "MQPRIO %s\n", hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE ? "enable" : "disable"); + dev_info(dev, "Default tx spare buffer size: %u\n", + hdev->tx_spare_buf_size); dev_info(dev, "PF info end.\n"); } @@ -11167,6 +11439,18 @@ static void hclge_clear_resetting_state(struct hclge_dev *hdev) } } +static void hclge_init_rxd_adv_layout(struct hclge_dev *hdev) +{ + if (hnae3_ae_dev_rxd_adv_layout_supported(hdev->ae_dev)) + hclge_write_dev(&hdev->hw, HCLGE_RXD_ADV_LAYOUT_EN_REG, 1); +} + +static void hclge_uninit_rxd_adv_layout(struct hclge_dev *hdev) +{ + if (hnae3_ae_dev_rxd_adv_layout_supported(hdev->ae_dev)) + hclge_write_dev(&hdev->hw, HCLGE_RXD_ADV_LAYOUT_EN_REG, 0); +} + static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) { struct pci_dev *pdev = ae_dev->pdev; @@ -11309,6 +11593,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) goto err_mdiobus_unreg; } + ret = hclge_ptp_init(hdev); + if (ret) + goto err_mdiobus_unreg; + INIT_KFIFO(hdev->mac_tnl_log); hclge_dcb_ops_set(hdev); @@ -11325,7 +11613,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_clear_resetting_state(hdev); /* Log and clear the hw errors those already occurred */ - hclge_handle_all_hns_hw_errors(ae_dev); + if (hnae3_dev_ras_imp_supported(hdev)) + hclge_handle_occurred_error(hdev); + else + hclge_handle_all_hns_hw_errors(ae_dev); /* request delayed reset for the error recovery because an immediate * global reset on a PF affecting pending initialization of other PFs @@ -11339,6 +11630,8 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) mod_timer(&hdev->reset_timer, jiffies + HCLGE_RESET_INTERVAL); } + hclge_init_rxd_adv_layout(hdev); + /* Enable MISC vector(vector0) */ hclge_enable_vector(&hdev->misc_vector, true); @@ -11471,10 +11764,7 @@ static int hclge_set_vf_trust(struct hnae3_handle *handle, int vf, bool enable) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - struct hnae3_ae_dev *ae_dev = hdev->ae_dev; u32 new_trusted = enable ? 1 : 0; - bool en_bc_pmc; - int ret; vport = hclge_get_vf_vport(hdev, vf); if (!vport) @@ -11483,18 +11773,9 @@ static int hclge_set_vf_trust(struct hnae3_handle *handle, int vf, bool enable) if (vport->vf_info.trusted == new_trusted) return 0; - /* Disable promisc mode for VF if it is not trusted any more. */ - if (!enable && vport->vf_info.promisc_enable) { - en_bc_pmc = ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V2; - ret = hclge_set_vport_promisc_mode(vport, false, false, - en_bc_pmc); - if (ret) - return ret; - vport->vf_info.promisc_enable = 0; - hclge_inform_vf_promisc_info(vport); - } - vport->vf_info.trusted = new_trusted; + set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state); + hclge_task_schedule(hdev, 0); return 0; } @@ -11687,8 +11968,15 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } + ret = hclge_ptp_init(hdev); + if (ret) + return ret; + /* Log and clear the hw errors those already occurred */ - hclge_handle_all_hns_hw_errors(ae_dev); + if (hnae3_dev_ras_imp_supported(hdev)) + hclge_handle_occurred_error(hdev); + else + hclge_handle_all_hns_hw_errors(ae_dev); /* Re-enable the hw error interrupts because * the interrupts get disabled on global reset. @@ -11720,6 +12008,8 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) if (ret) return ret; + hclge_init_rxd_adv_layout(hdev); + dev_info(&pdev->dev, "Reset done, %s driver initialization finished.\n", HCLGE_DRIVER_NAME); @@ -11735,6 +12025,8 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_clear_vf_vlan(hdev); hclge_misc_affinity_teardown(hdev); hclge_state_uninit(hdev); + hclge_ptp_uninit(hdev); + hclge_uninit_rxd_adv_layout(hdev); hclge_uninit_mac_table(hdev); hclge_del_all_fd_entries(hdev); @@ -12385,22 +12677,51 @@ static void hclge_sync_promisc_mode(struct hclge_dev *hdev) struct hnae3_handle *handle = &vport->nic; u8 tmp_flags; int ret; + u16 i; if (vport->last_promisc_flags != vport->overflow_promisc_flags) { - set_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state); + set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state); vport->last_promisc_flags = vport->overflow_promisc_flags; } - if (test_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state)) { + if (test_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state)) { tmp_flags = handle->netdev_flags | vport->last_promisc_flags; ret = hclge_set_promisc_mode(handle, tmp_flags & HNAE3_UPE, tmp_flags & HNAE3_MPE); if (!ret) { - clear_bit(HCLGE_STATE_PROMISC_CHANGED, &hdev->state); - hclge_enable_vlan_filter(handle, - tmp_flags & HNAE3_VLAN_FLTR); + clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, + &vport->state); + set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE, + &vport->state); } } + + for (i = 1; i < hdev->num_alloc_vport; i++) { + bool uc_en = false; + bool mc_en = false; + bool bc_en; + + vport = &hdev->vport[i]; + + if (!test_and_clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, + &vport->state)) + continue; + + if (vport->vf_info.trusted) { + uc_en = vport->vf_info.request_uc_en > 0; + mc_en = vport->vf_info.request_mc_en > 0; + } + bc_en = vport->vf_info.request_bc_en > 0; + + ret = hclge_cmd_set_promisc_mode(hdev, vport->vport_id, uc_en, + mc_en, bc_en); + if (ret) { + set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, + &vport->state); + return; + } + hclge_set_vport_vlan_fltr_change(vport); + } } static bool hclge_module_existed(struct hclge_dev *hdev) @@ -12578,7 +12899,6 @@ static const struct hnae3_ae_ops hclge_ops = { .get_fd_all_rules = hclge_get_all_rules, .enable_fd = hclge_enable_fd, .add_arfs_entry = hclge_add_fd_entry_by_arfs, - .dbg_run_cmd = hclge_dbg_run_cmd, .dbg_read_cmd = hclge_dbg_read_cmd, .handle_hw_ras_error = hclge_handle_hw_ras_error, .get_hw_reset_stat = hclge_get_hw_reset_stat, @@ -12602,6 +12922,9 @@ static const struct hnae3_ae_ops hclge_ops = { .cls_flower_active = hclge_is_cls_flower_active, .get_phy_link_ksettings = hclge_get_phy_link_ksettings, .set_phy_link_ksettings = hclge_set_phy_link_ksettings, + .set_tx_hwts_info = hclge_ptp_set_tx_info, + .get_rx_hwts = hclge_ptp_get_rx_hwts, + .get_ts_info = hclge_ptp_get_ts_info, }; static struct hnae3_ae_algo ae_algo = { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index ff1d47308c2d..3d3352491dba 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -10,6 +10,7 @@ #include #include "hclge_cmd.h" +#include "hclge_ptp.h" #include "hnae3.h" #define HCLGE_MOD_VERSION "1.0" @@ -53,6 +54,7 @@ /* bar registers for common func */ #define HCLGE_VECTOR0_OTER_EN_REG 0x20600 #define HCLGE_GRO_EN_REG 0x28000 +#define HCLGE_RXD_ADV_LAYOUT_EN_REG 0x28008 /* bar registers for rcb */ #define HCLGE_RING_RX_ADDR_L_REG 0x80000 @@ -147,6 +149,8 @@ #define HCLGE_MAX_QSET_NUM 1024 +#define HCLGE_DBG_RESET_INFO_LEN 1024 + enum HLCGE_PORT_TYPE { HOST_PORT, NETWORK_PORT @@ -175,6 +179,7 @@ enum HLCGE_PORT_TYPE { #define HCLGE_FUN_RST_ING_B 0 /* Vector0 register bits define */ +#define HCLGE_VECTOR0_REG_PTP_INT_B 0 #define HCLGE_VECTOR0_GLOBALRESET_INT_B 5 #define HCLGE_VECTOR0_CORERESET_INT_B 6 #define HCLGE_VECTOR0_IMPRESET_INT_B 7 @@ -187,6 +192,7 @@ enum HLCGE_PORT_TYPE { #define HCLGE_VECTOR0_IMP_RESET_INT_B 1 #define HCLGE_VECTOR0_IMP_CMDQ_ERR_B 4U #define HCLGE_VECTOR0_IMP_RD_POISON_B 5U +#define HCLGE_VECTOR0_ALL_MSIX_ERR_B 6U #define HCLGE_MAC_DEFAULT_FRAME \ (ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN + ETH_DATA_LEN) @@ -218,14 +224,16 @@ enum HCLGE_DEV_STATE { HCLGE_STATE_RST_HANDLING, HCLGE_STATE_MBX_SERVICE_SCHED, HCLGE_STATE_MBX_HANDLING, + HCLGE_STATE_ERR_SERVICE_SCHED, HCLGE_STATE_STATISTICS_UPDATING, HCLGE_STATE_CMD_DISABLE, HCLGE_STATE_LINK_UPDATING, - HCLGE_STATE_PROMISC_CHANGED, HCLGE_STATE_RST_FAIL, HCLGE_STATE_FD_TBL_CHANGED, HCLGE_STATE_FD_CLEAR_ALL, HCLGE_STATE_FD_USER_DEF_CHANGED, + HCLGE_STATE_PTP_EN, + HCLGE_STATE_PTP_TX_HANDLING, HCLGE_STATE_MAX }; @@ -233,6 +241,7 @@ enum hclge_evt_cause { HCLGE_VECTOR0_EVENT_RST, HCLGE_VECTOR0_EVENT_MBX, HCLGE_VECTOR0_EVENT_ERR, + HCLGE_VECTOR0_EVENT_PTP, HCLGE_VECTOR0_EVENT_OTHER, }; @@ -319,6 +328,22 @@ enum hclge_fc_mode { HCLGE_FC_DEFAULT }; +#define HCLGE_FILTER_TYPE_VF 0 +#define HCLGE_FILTER_TYPE_PORT 1 +#define HCLGE_FILTER_FE_EGRESS_V1_B BIT(0) +#define HCLGE_FILTER_FE_NIC_INGRESS_B BIT(0) +#define HCLGE_FILTER_FE_NIC_EGRESS_B BIT(1) +#define HCLGE_FILTER_FE_ROCE_INGRESS_B BIT(2) +#define HCLGE_FILTER_FE_ROCE_EGRESS_B BIT(3) +#define HCLGE_FILTER_FE_EGRESS (HCLGE_FILTER_FE_NIC_EGRESS_B \ + | HCLGE_FILTER_FE_ROCE_EGRESS_B) +#define HCLGE_FILTER_FE_INGRESS (HCLGE_FILTER_FE_NIC_INGRESS_B \ + | HCLGE_FILTER_FE_ROCE_INGRESS_B) + +enum hclge_vlan_fltr_cap { + HCLGE_VLAN_FLTR_DEF, + HCLGE_VLAN_FLTR_CAN_MDF, +}; enum hclge_link_fail_code { HCLGE_LF_NORMAL, HCLGE_LF_REF_CLOCK_LOST, @@ -349,6 +374,7 @@ struct hclge_tc_info { struct hclge_cfg { u8 tc_num; + u8 vlan_fliter_cap; u16 tqp_desc_num; u16 rx_buf_len; u16 vf_rss_size_max; @@ -358,6 +384,7 @@ struct hclge_cfg { u8 mac_addr[ETH_ALEN]; u8 default_speed; u32 numa_node_map; + u32 tx_spare_buf_size; u16 speed_ability; u16 umv_space; }; @@ -757,9 +784,14 @@ struct hclge_mac_tnl_stats { struct hclge_vf_vlan_cfg { u8 mbx_cmd; u8 subcode; - u8 is_kill; - u16 vlan; - u16 proto; + union { + struct { + u8 is_kill; + u16 vlan; + u16 proto; + }; + u8 enable; + }; }; #pragma pack() @@ -817,6 +849,7 @@ struct hclge_dev { u16 alloc_rss_size; /* Allocated RSS task queue */ u16 vf_rss_size_max; /* HW defined VF max RSS task queue */ u16 pf_rss_size_max; /* HW defined PF max RSS task queue */ + u32 tx_spare_buf_size; /* HW defined TX spare buffer size */ u16 fdir_pf_filter_count; /* Num of guaranteed filters for this PF */ u16 num_alloc_vport; /* Num vports this driver supports */ @@ -909,6 +942,7 @@ struct hclge_dev { /* affinity mask and notify for misc interrupt */ cpumask_t affinity_mask; struct irq_affinity_notify affinity_notify; + struct hclge_ptp *ptp; }; /* VPort level vlan tag configuration for TX direction */ @@ -949,6 +983,8 @@ struct hclge_rss_tuple_cfg { enum HCLGE_VPORT_STATE { HCLGE_VPORT_STATE_ALIVE, HCLGE_VPORT_STATE_MAC_TBL_CHANGE, + HCLGE_VPORT_STATE_PROMISC_CHANGE, + HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE, HCLGE_VPORT_STATE_MAX }; @@ -969,7 +1005,9 @@ struct hclge_vf_info { u32 spoofchk; u32 max_tx_rate; u32 trusted; - u16 promisc_enable; + u8 request_uc_en; + u8 request_mc_en; + u8 request_bc_en; }; struct hclge_vport { @@ -988,6 +1026,8 @@ struct hclge_vport { u32 bw_limit; /* VSI BW Limit (0 = disabled) */ u8 dwrr; + bool req_vlan_fltr_en; + bool cur_vlan_fltr_en; unsigned long vlan_del_fail_bmap[BITS_TO_LONGS(VLAN_N_VID)]; struct hclge_port_base_vlan_config port_base_vlan_cfg; struct hclge_tx_vtag_cfg txvlan_cfg; @@ -1059,8 +1099,7 @@ int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id); int hclge_vport_start(struct hclge_vport *vport); void hclge_vport_stop(struct hclge_vport *vport); int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu); -int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf); -int hclge_dbg_read_cmd(struct hnae3_handle *handle, const char *cmd_buf, +int hclge_dbg_read_cmd(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd, char *buf, int len); u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id); int hclge_notify_client(struct hclge_dev *hdev, @@ -1080,14 +1119,15 @@ void hclge_restore_vport_vlan_table(struct hclge_vport *vport); int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state, struct hclge_vlan_info *vlan_info); int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid, - u16 state, u16 vlan_tag, u16 qos, - u16 vlan_proto); + u16 state, + struct hclge_vlan_info *vlan_info); void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time); int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc); void hclge_report_hw_error(struct hclge_dev *hdev, enum hnae3_hw_error_type type); void hclge_inform_vf_promisc_info(struct hclge_vport *vport); -void hclge_dbg_dump_rst_info(struct hclge_dev *hdev); +int hclge_dbg_dump_rst_info(struct hclge_dev *hdev, char *buf, int len); int hclge_push_vf_link_status(struct hclge_vport *vport); +int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index f1c9f4ada348..e10a2c36b706 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -231,19 +231,15 @@ static int hclge_map_unmap_ring_to_vf_vector(struct hclge_vport *vport, bool en, return ret; } -static int hclge_set_vf_promisc_mode(struct hclge_vport *vport, - struct hclge_mbx_vf_to_pf_cmd *req) +static void hclge_set_vf_promisc_mode(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *req) { - bool en_bc = req->msg.en_bc ? true : false; - bool en_uc = req->msg.en_uc ? true : false; - bool en_mc = req->msg.en_mc ? true : false; struct hnae3_handle *handle = &vport->nic; - int ret; + struct hclge_dev *hdev = vport->back; - if (!vport->vf_info.trusted) { - en_uc = false; - en_mc = false; - } + vport->vf_info.request_uc_en = req->msg.en_uc; + vport->vf_info.request_mc_en = req->msg.en_mc; + vport->vf_info.request_bc_en = req->msg.en_bc; if (req->msg.en_limit_promisc) set_bit(HNAE3_PFLAG_LIMIT_PROMISC, &handle->priv_flags); @@ -251,22 +247,8 @@ static int hclge_set_vf_promisc_mode(struct hclge_vport *vport, clear_bit(HNAE3_PFLAG_LIMIT_PROMISC, &handle->priv_flags); - ret = hclge_set_vport_promisc_mode(vport, en_uc, en_mc, en_bc); - - vport->vf_info.promisc_enable = (en_uc || en_mc) ? 1 : 0; - - return ret; -} - -void hclge_inform_vf_promisc_info(struct hclge_vport *vport) -{ - u8 dest_vfid = (u8)vport->vport_id; - u8 msg_data[2]; - - memcpy(&msg_data[0], &vport->vf_info.promisc_enable, sizeof(u16)); - - hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data), - HCLGE_MBX_PUSH_PROMISC_INFO, dest_vfid); + set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state); + hclge_task_schedule(hdev, 0); } static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport, @@ -336,17 +318,17 @@ static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport, } int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid, - u16 state, u16 vlan_tag, u16 qos, - u16 vlan_proto) + u16 state, + struct hclge_vlan_info *vlan_info) { #define MSG_DATA_SIZE 8 u8 msg_data[MSG_DATA_SIZE]; memcpy(&msg_data[0], &state, sizeof(u16)); - memcpy(&msg_data[2], &vlan_proto, sizeof(u16)); - memcpy(&msg_data[4], &qos, sizeof(u16)); - memcpy(&msg_data[6], &vlan_tag, sizeof(u16)); + memcpy(&msg_data[2], &vlan_info->vlan_proto, sizeof(u16)); + memcpy(&msg_data[4], &vlan_info->qos, sizeof(u16)); + memcpy(&msg_data[6], &vlan_info->vlan_tag, sizeof(u16)); return hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data), HCLGE_MBX_PUSH_VLAN_INFO, vfid); @@ -359,49 +341,35 @@ static int hclge_set_vf_vlan_cfg(struct hclge_vport *vport, #define HCLGE_MBX_VLAN_STATE_OFFSET 0 #define HCLGE_MBX_VLAN_INFO_OFFSET 2 + struct hnae3_handle *handle = &vport->nic; + struct hclge_dev *hdev = vport->back; struct hclge_vf_vlan_cfg *msg_cmd; - int status = 0; msg_cmd = (struct hclge_vf_vlan_cfg *)&mbx_req->msg; - if (msg_cmd->subcode == HCLGE_MBX_VLAN_FILTER) { - struct hnae3_handle *handle = &vport->nic; - u16 vlan, proto; - bool is_kill; - - is_kill = !!msg_cmd->is_kill; - vlan = msg_cmd->vlan; - proto = msg_cmd->proto; - status = hclge_set_vlan_filter(handle, cpu_to_be16(proto), - vlan, is_kill); - } else if (msg_cmd->subcode == HCLGE_MBX_VLAN_RX_OFF_CFG) { - struct hnae3_handle *handle = &vport->nic; - bool en = msg_cmd->is_kill ? true : false; - - status = hclge_en_hw_strip_rxvtag(handle, en); - } else if (msg_cmd->subcode == HCLGE_MBX_PORT_BASE_VLAN_CFG) { - struct hclge_vlan_info *vlan_info; - u16 *state; - - state = (u16 *)&mbx_req->msg.data[HCLGE_MBX_VLAN_STATE_OFFSET]; - vlan_info = (struct hclge_vlan_info *) - &mbx_req->msg.data[HCLGE_MBX_VLAN_INFO_OFFSET]; - status = hclge_update_port_base_vlan_cfg(vport, *state, - vlan_info); - } else if (msg_cmd->subcode == HCLGE_MBX_GET_PORT_BASE_VLAN_STATE) { - struct hnae3_ae_dev *ae_dev = pci_get_drvdata(vport->nic.pdev); + switch (msg_cmd->subcode) { + case HCLGE_MBX_VLAN_FILTER: + return hclge_set_vlan_filter(handle, + cpu_to_be16(msg_cmd->proto), + msg_cmd->vlan, msg_cmd->is_kill); + case HCLGE_MBX_VLAN_RX_OFF_CFG: + return hclge_en_hw_strip_rxvtag(handle, msg_cmd->enable); + case HCLGE_MBX_GET_PORT_BASE_VLAN_STATE: /* vf does not need to know about the port based VLAN state * on device HNAE3_DEVICE_VERSION_V3. So always return disable * on device HNAE3_DEVICE_VERSION_V3 if vf queries the port * based VLAN state. */ resp_msg->data[0] = - ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3 ? + hdev->ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3 ? HNAE3_PORT_BASE_VLAN_DISABLE : vport->port_base_vlan_cfg.state; resp_msg->len = sizeof(u8); + return 0; + case HCLGE_MBX_ENABLE_VLAN_FILTER: + return hclge_enable_vport_vlan_filter(vport, msg_cmd->enable); + default: + return 0; } - - return status; } static int hclge_set_vf_alive(struct hclge_vport *vport, @@ -418,16 +386,23 @@ static int hclge_set_vf_alive(struct hclge_vport *vport, return ret; } -static void hclge_get_vf_tcinfo(struct hclge_vport *vport, - struct hclge_respond_to_vf_msg *resp_msg) +static void hclge_get_basic_info(struct hclge_vport *vport, + struct hclge_respond_to_vf_msg *resp_msg) { struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo; + struct hnae3_ae_dev *ae_dev = vport->back->ae_dev; + struct hclge_basic_info *basic_info; unsigned int i; + basic_info = (struct hclge_basic_info *)resp_msg->data; for (i = 0; i < kinfo->tc_info.num_tc; i++) - resp_msg->data[0] |= BIT(i); + basic_info->hw_tc_map |= BIT(i); - resp_msg->len = sizeof(u8); + if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps)) + hnae3_set_bit(basic_info->pf_caps, + HNAE3_PF_SUPPORT_VLAN_FLTR_MDF_B, 1); + + resp_msg->len = HCLGE_MBX_MAX_RESP_DATA_SIZE; } static void hclge_get_vf_queue_info(struct hclge_vport *vport, @@ -750,11 +725,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev) req); break; case HCLGE_MBX_SET_PROMISC_MODE: - ret = hclge_set_vf_promisc_mode(vport, req); - if (ret) - dev_err(&hdev->pdev->dev, - "PF fail(%d) to set VF promisc mode\n", - ret); + hclge_set_vf_promisc_mode(vport, req); break; case HCLGE_MBX_SET_UNICAST: ret = hclge_set_vf_uc_mac_addr(vport, req); @@ -790,8 +761,8 @@ void hclge_mbx_handler(struct hclge_dev *hdev) case HCLGE_MBX_GET_QDEPTH: hclge_get_vf_queue_depth(vport, &resp_msg); break; - case HCLGE_MBX_GET_TCINFO: - hclge_get_vf_tcinfo(vport, &resp_msg); + case HCLGE_MBX_GET_BASIC_INFO: + hclge_get_basic_info(vport, &resp_msg); break; case HCLGE_MBX_GET_LINK_STATUS: ret = hclge_push_vf_link_status(vport); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c new file mode 100644 index 000000000000..3b1f84502e36 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -0,0 +1,542 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright (c) 2021 Hisilicon Limited. + +#include +#include "hclge_main.h" +#include "hnae3.h" + +static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +{ + struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp); + u64 adj_val, adj_base, diff; + unsigned long flags; + bool is_neg = false; + u32 quo, numerator; + + if (ppb < 0) { + ppb = -ppb; + is_neg = true; + } + + adj_base = HCLGE_PTP_CYCLE_ADJ_BASE * HCLGE_PTP_CYCLE_ADJ_UNIT; + adj_val = adj_base * ppb; + diff = div_u64(adj_val, 1000000000ULL); + + if (is_neg) + adj_val = adj_base - diff; + else + adj_val = adj_base + diff; + + /* This clock cycle is defined by three part: quotient, numerator + * and denominator. For example, 2.5ns, the quotient is 2, + * denominator is fixed to HCLGE_PTP_CYCLE_ADJ_UNIT, and numerator + * is 0.5 * HCLGE_PTP_CYCLE_ADJ_UNIT. + */ + quo = div_u64_rem(adj_val, HCLGE_PTP_CYCLE_ADJ_UNIT, &numerator); + + spin_lock_irqsave(&hdev->ptp->lock, flags); + writel(quo, hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG); + writel(numerator, hdev->ptp->io_base + HCLGE_PTP_CYCLE_NUM_REG); + writel(HCLGE_PTP_CYCLE_ADJ_UNIT, + hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG); + writel(HCLGE_PTP_CYCLE_ADJ_EN, + hdev->ptp->io_base + HCLGE_PTP_CYCLE_CFG_REG); + spin_unlock_irqrestore(&hdev->ptp->lock, flags); + + return 0; +} + +bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_ptp *ptp = hdev->ptp; + + if (!test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) || + test_and_set_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state)) { + ptp->tx_skipped++; + return false; + } + + ptp->tx_start = jiffies; + ptp->tx_skb = skb_get(skb); + ptp->tx_cnt++; + + return true; +} + +void hclge_ptp_clean_tx_hwts(struct hclge_dev *hdev) +{ + struct sk_buff *skb = hdev->ptp->tx_skb; + struct skb_shared_hwtstamps hwts; + u32 hi, lo; + u64 ns; + + ns = readl(hdev->ptp->io_base + HCLGE_PTP_TX_TS_NSEC_REG) & + HCLGE_PTP_TX_TS_NSEC_MASK; + lo = readl(hdev->ptp->io_base + HCLGE_PTP_TX_TS_SEC_L_REG); + hi = readl(hdev->ptp->io_base + HCLGE_PTP_TX_TS_SEC_H_REG) & + HCLGE_PTP_TX_TS_SEC_H_MASK; + hdev->ptp->last_tx_seqid = readl(hdev->ptp->io_base + + HCLGE_PTP_TX_TS_SEQID_REG); + + if (skb) { + hdev->ptp->tx_skb = NULL; + hdev->ptp->tx_cleaned++; + + ns += (((u64)hi) << 32 | lo) * NSEC_PER_SEC; + hwts.hwtstamp = ns_to_ktime(ns); + skb_tstamp_tx(skb, &hwts); + dev_kfree_skb_any(skb); + } + + clear_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state); +} + +void hclge_ptp_get_rx_hwts(struct hnae3_handle *handle, struct sk_buff *skb, + u32 nsec, u32 sec) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + unsigned long flags; + u64 ns = nsec; + u32 sec_h; + + if (!test_bit(HCLGE_PTP_FLAG_RX_EN, &hdev->ptp->flags)) + return; + + /* Since the BD does not have enough space for the higher 16 bits of + * second, and this part will not change frequently, so read it + * from register. + */ + spin_lock_irqsave(&hdev->ptp->lock, flags); + sec_h = readl(hdev->ptp->io_base + HCLGE_PTP_CUR_TIME_SEC_H_REG); + spin_unlock_irqrestore(&hdev->ptp->lock, flags); + + ns += (((u64)sec_h) << HCLGE_PTP_SEC_H_OFFSET | sec) * NSEC_PER_SEC; + skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(ns); + hdev->ptp->last_rx = jiffies; + hdev->ptp->rx_cnt++; +} + +static int hclge_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp); + unsigned long flags; + u32 hi, lo; + u64 ns; + + spin_lock_irqsave(&hdev->ptp->lock, flags); + ns = readl(hdev->ptp->io_base + HCLGE_PTP_CUR_TIME_NSEC_REG); + hi = readl(hdev->ptp->io_base + HCLGE_PTP_CUR_TIME_SEC_H_REG); + lo = readl(hdev->ptp->io_base + HCLGE_PTP_CUR_TIME_SEC_L_REG); + spin_unlock_irqrestore(&hdev->ptp->lock, flags); + + ns += (((u64)hi) << HCLGE_PTP_SEC_H_OFFSET | lo) * NSEC_PER_SEC; + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int hclge_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp); + unsigned long flags; + + spin_lock_irqsave(&hdev->ptp->lock, flags); + writel(ts->tv_nsec, hdev->ptp->io_base + HCLGE_PTP_TIME_NSEC_REG); + writel(ts->tv_sec >> HCLGE_PTP_SEC_H_OFFSET, + hdev->ptp->io_base + HCLGE_PTP_TIME_SEC_H_REG); + writel(ts->tv_sec & HCLGE_PTP_SEC_L_MASK, + hdev->ptp->io_base + HCLGE_PTP_TIME_SEC_L_REG); + /* synchronize the time of phc */ + writel(HCLGE_PTP_TIME_SYNC_EN, + hdev->ptp->io_base + HCLGE_PTP_TIME_SYNC_REG); + spin_unlock_irqrestore(&hdev->ptp->lock, flags); + + return 0; +} + +static int hclge_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp); + unsigned long flags; + bool is_neg = false; + u32 adj_val = 0; + + if (delta < 0) { + adj_val |= HCLGE_PTP_TIME_NSEC_NEG; + delta = -delta; + is_neg = true; + } + + if (delta > HCLGE_PTP_TIME_NSEC_MASK) { + struct timespec64 ts; + s64 ns; + + hclge_ptp_gettimex(ptp, &ts, NULL); + ns = timespec64_to_ns(&ts); + ns = is_neg ? ns - delta : ns + delta; + ts = ns_to_timespec64(ns); + return hclge_ptp_settime(ptp, &ts); + } + + adj_val |= delta & HCLGE_PTP_TIME_NSEC_MASK; + + spin_lock_irqsave(&hdev->ptp->lock, flags); + writel(adj_val, hdev->ptp->io_base + HCLGE_PTP_TIME_NSEC_REG); + writel(HCLGE_PTP_TIME_ADJ_EN, + hdev->ptp->io_base + HCLGE_PTP_TIME_ADJ_REG); + spin_unlock_irqrestore(&hdev->ptp->lock, flags); + + return 0; +} + +int hclge_ptp_get_cfg(struct hclge_dev *hdev, struct ifreq *ifr) +{ + if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state)) + return -EOPNOTSUPP; + + return copy_to_user(ifr->ifr_data, &hdev->ptp->ts_cfg, + sizeof(struct hwtstamp_config)) ? -EFAULT : 0; +} + +static int hclge_ptp_int_en(struct hclge_dev *hdev, bool en) +{ + struct hclge_ptp_int_cmd *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_ptp_int_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PTP_INT_EN, false); + req->int_en = en ? 1 : 0; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "failed to %s ptp interrupt, ret = %d\n", + en ? "enable" : "disable", ret); + + return ret; +} + +int hclge_ptp_cfg_qry(struct hclge_dev *hdev, u32 *cfg) +{ + struct hclge_ptp_cfg_cmd *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_ptp_cfg_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PTP_MODE_CFG, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to query ptp config, ret = %d\n", ret); + return ret; + } + + *cfg = le32_to_cpu(req->cfg); + + return 0; +} + +static int hclge_ptp_cfg(struct hclge_dev *hdev, u32 cfg) +{ + struct hclge_ptp_cfg_cmd *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_ptp_cfg_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PTP_MODE_CFG, false); + req->cfg = cpu_to_le32(cfg); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "failed to config ptp, ret = %d\n", ret); + + return ret; +} + +static int hclge_ptp_set_tx_mode(struct hwtstamp_config *cfg, + unsigned long *flags, u32 *ptp_cfg) +{ + switch (cfg->tx_type) { + case HWTSTAMP_TX_OFF: + clear_bit(HCLGE_PTP_FLAG_TX_EN, flags); + break; + case HWTSTAMP_TX_ON: + set_bit(HCLGE_PTP_FLAG_TX_EN, flags); + *ptp_cfg |= HCLGE_PTP_TX_EN_B; + break; + default: + return -ERANGE; + } + + return 0; +} + +static int hclge_ptp_set_rx_mode(struct hwtstamp_config *cfg, + unsigned long *flags, u32 *ptp_cfg) +{ + int rx_filter = cfg->rx_filter; + + switch (cfg->rx_filter) { + case HWTSTAMP_FILTER_NONE: + clear_bit(HCLGE_PTP_FLAG_RX_EN, flags); + break; + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + set_bit(HCLGE_PTP_FLAG_RX_EN, flags); + *ptp_cfg |= HCLGE_PTP_RX_EN_B; + *ptp_cfg |= HCLGE_PTP_UDP_FULL_TYPE << HCLGE_PTP_UDP_EN_SHIFT; + rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + set_bit(HCLGE_PTP_FLAG_RX_EN, flags); + *ptp_cfg |= HCLGE_PTP_RX_EN_B; + *ptp_cfg |= HCLGE_PTP_UDP_FULL_TYPE << HCLGE_PTP_UDP_EN_SHIFT; + *ptp_cfg |= HCLGE_PTP_MSG1_V2_DEFAULT << HCLGE_PTP_MSG1_SHIFT; + *ptp_cfg |= HCLGE_PTP_MSG0_V2_EVENT << HCLGE_PTP_MSG0_SHIFT; + *ptp_cfg |= HCLGE_PTP_MSG_TYPE_V2 << HCLGE_PTP_MSG_TYPE_SHIFT; + rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + break; + case HWTSTAMP_FILTER_ALL: + default: + return -ERANGE; + } + + cfg->rx_filter = rx_filter; + + return 0; +} + +static int hclge_ptp_set_ts_mode(struct hclge_dev *hdev, + struct hwtstamp_config *cfg) +{ + unsigned long flags = hdev->ptp->flags; + u32 ptp_cfg = 0; + int ret; + + if (test_bit(HCLGE_PTP_FLAG_EN, &hdev->ptp->flags)) + ptp_cfg |= HCLGE_PTP_EN_B; + + ret = hclge_ptp_set_tx_mode(cfg, &flags, &ptp_cfg); + if (ret) + return ret; + + ret = hclge_ptp_set_rx_mode(cfg, &flags, &ptp_cfg); + if (ret) + return ret; + + ret = hclge_ptp_cfg(hdev, ptp_cfg); + if (ret) + return ret; + + hdev->ptp->flags = flags; + hdev->ptp->ptp_cfg = ptp_cfg; + + return 0; +} + +int hclge_ptp_set_cfg(struct hclge_dev *hdev, struct ifreq *ifr) +{ + struct hwtstamp_config cfg; + int ret; + + if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state)) { + dev_err(&hdev->pdev->dev, "phc is unsupported\n"); + return -EOPNOTSUPP; + } + + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + ret = hclge_ptp_set_ts_mode(hdev, &cfg); + if (ret) + return ret; + + hdev->ptp->ts_cfg = cfg; + + return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; +} + +int hclge_ptp_get_ts_info(struct hnae3_handle *handle, + struct ethtool_ts_info *info) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state)) { + dev_err(&hdev->pdev->dev, "phc is unsupported\n"); + return -EOPNOTSUPP; + } + + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + if (hdev->ptp->clock) + info->phc_index = ptp_clock_index(hdev->ptp->clock); + else + info->phc_index = -1; + + info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON); + + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ); + + info->rx_filters |= BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ); + + return 0; +} + +static int hclge_ptp_create_clock(struct hclge_dev *hdev) +{ + struct hclge_ptp *ptp; + + ptp = devm_kzalloc(&hdev->pdev->dev, sizeof(*ptp), GFP_KERNEL); + if (!ptp) + return -ENOMEM; + + ptp->hdev = hdev; + snprintf(ptp->info.name, sizeof(ptp->info.name), "%s", + HCLGE_DRIVER_NAME); + ptp->info.owner = THIS_MODULE; + ptp->info.max_adj = HCLGE_PTP_CYCLE_ADJ_MAX; + ptp->info.n_ext_ts = 0; + ptp->info.pps = 0; + ptp->info.adjfreq = hclge_ptp_adjfreq; + ptp->info.adjtime = hclge_ptp_adjtime; + ptp->info.gettimex64 = hclge_ptp_gettimex; + ptp->info.settime64 = hclge_ptp_settime; + + ptp->info.n_alarm = 0; + ptp->clock = ptp_clock_register(&ptp->info, &hdev->pdev->dev); + if (IS_ERR(ptp->clock)) { + dev_err(&hdev->pdev->dev, + "%d failed to register ptp clock, ret = %ld\n", + ptp->info.n_alarm, PTR_ERR(ptp->clock)); + return -ENODEV; + } else if (!ptp->clock) { + dev_err(&hdev->pdev->dev, "failed to register ptp clock\n"); + return -ENODEV; + } + + spin_lock_init(&ptp->lock); + ptp->io_base = hdev->hw.io_base + HCLGE_PTP_REG_OFFSET; + ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE; + ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF; + hdev->ptp = ptp; + + return 0; +} + +static void hclge_ptp_destroy_clock(struct hclge_dev *hdev) +{ + ptp_clock_unregister(hdev->ptp->clock); + hdev->ptp->clock = NULL; + devm_kfree(&hdev->pdev->dev, hdev->ptp); + hdev->ptp = NULL; +} + +int hclge_ptp_init(struct hclge_dev *hdev) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); + struct timespec64 ts; + int ret; + + if (!test_bit(HNAE3_DEV_SUPPORT_PTP_B, ae_dev->caps)) + return 0; + + if (!hdev->ptp) { + ret = hclge_ptp_create_clock(hdev); + if (ret) + return ret; + } + + ret = hclge_ptp_int_en(hdev, true); + if (ret) + goto out; + + set_bit(HCLGE_PTP_FLAG_EN, &hdev->ptp->flags); + ret = hclge_ptp_adjfreq(&hdev->ptp->info, 0); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to init freq, ret = %d\n", ret); + goto out; + } + + ret = hclge_ptp_set_ts_mode(hdev, &hdev->ptp->ts_cfg); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to init ts mode, ret = %d\n", ret); + goto out; + } + + ktime_get_real_ts64(&ts); + ret = hclge_ptp_settime(&hdev->ptp->info, &ts); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to init ts time, ret = %d\n", ret); + goto out; + } + + set_bit(HCLGE_STATE_PTP_EN, &hdev->state); + dev_info(&hdev->pdev->dev, "phc initializes ok!\n"); + + return 0; + +out: + hclge_ptp_destroy_clock(hdev); + + return ret; +} + +void hclge_ptp_uninit(struct hclge_dev *hdev) +{ + struct hclge_ptp *ptp = hdev->ptp; + + if (!ptp) + return; + + hclge_ptp_int_en(hdev, false); + clear_bit(HCLGE_STATE_PTP_EN, &hdev->state); + clear_bit(HCLGE_PTP_FLAG_EN, &ptp->flags); + ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE; + ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF; + + if (hclge_ptp_set_ts_mode(hdev, &ptp->ts_cfg)) + dev_err(&hdev->pdev->dev, "failed to disable phc\n"); + + if (ptp->tx_skb) { + struct sk_buff *skb = ptp->tx_skb; + + ptp->tx_skb = NULL; + dev_kfree_skb_any(skb); + } + + hclge_ptp_destroy_clock(hdev); +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h new file mode 100644 index 000000000000..5a202b775471 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +// Copyright (c) 2021 Hisilicon Limited. + +#ifndef __HCLGE_PTP_H +#define __HCLGE_PTP_H + +#include +#include +#include + +#define HCLGE_PTP_REG_OFFSET 0x29000 + +#define HCLGE_PTP_TX_TS_SEQID_REG 0x0 +#define HCLGE_PTP_TX_TS_NSEC_REG 0x4 +#define HCLGE_PTP_TX_TS_NSEC_MASK GENMASK(29, 0) +#define HCLGE_PTP_TX_TS_SEC_L_REG 0x8 +#define HCLGE_PTP_TX_TS_SEC_H_REG 0xC +#define HCLGE_PTP_TX_TS_SEC_H_MASK GENMASK(15, 0) +#define HCLGE_PTP_TX_TS_CNT_REG 0x30 + +#define HCLGE_PTP_TIME_SEC_H_REG 0x50 +#define HCLGE_PTP_TIME_SEC_H_MASK GENMASK(15, 0) +#define HCLGE_PTP_TIME_SEC_L_REG 0x54 +#define HCLGE_PTP_TIME_NSEC_REG 0x58 +#define HCLGE_PTP_TIME_NSEC_MASK GENMASK(29, 0) +#define HCLGE_PTP_TIME_NSEC_NEG BIT(31) +#define HCLGE_PTP_TIME_SYNC_REG 0x5C +#define HCLGE_PTP_TIME_SYNC_EN BIT(0) +#define HCLGE_PTP_TIME_ADJ_REG 0x60 +#define HCLGE_PTP_TIME_ADJ_EN BIT(0) +#define HCLGE_PTP_CYCLE_QUO_REG 0x64 +#define HCLGE_PTP_CYCLE_DEN_REG 0x68 +#define HCLGE_PTP_CYCLE_NUM_REG 0x6C +#define HCLGE_PTP_CYCLE_CFG_REG 0x70 +#define HCLGE_PTP_CYCLE_ADJ_EN BIT(0) +#define HCLGE_PTP_CUR_TIME_SEC_H_REG 0x74 +#define HCLGE_PTP_CUR_TIME_SEC_L_REG 0x78 +#define HCLGE_PTP_CUR_TIME_NSEC_REG 0x7C + +#define HCLGE_PTP_CYCLE_ADJ_BASE 2 +#define HCLGE_PTP_CYCLE_ADJ_MAX 500000000 +#define HCLGE_PTP_CYCLE_ADJ_UNIT 100000000 +#define HCLGE_PTP_SEC_H_OFFSET 32u +#define HCLGE_PTP_SEC_L_MASK GENMASK(31, 0) + +#define HCLGE_PTP_FLAG_EN 0 +#define HCLGE_PTP_FLAG_TX_EN 1 +#define HCLGE_PTP_FLAG_RX_EN 2 + +struct hclge_ptp { + struct hclge_dev *hdev; + struct ptp_clock *clock; + struct sk_buff *tx_skb; + unsigned long flags; + void __iomem *io_base; + struct ptp_clock_info info; + struct hwtstamp_config ts_cfg; + spinlock_t lock; /* protects ptp registers */ + u32 ptp_cfg; + u32 last_tx_seqid; + unsigned long tx_start; + unsigned long tx_cnt; + unsigned long tx_skipped; + unsigned long tx_cleaned; + unsigned long last_rx; + unsigned long rx_cnt; + unsigned long tx_timeout; +}; + +struct hclge_ptp_int_cmd { +#define HCLGE_PTP_INT_EN_B BIT(0) + + u8 int_en; + u8 rsvd[23]; +}; + +enum hclge_ptp_udp_type { + HCLGE_PTP_UDP_NOT_TYPE, + HCLGE_PTP_UDP_P13F_TYPE, + HCLGE_PTP_UDP_P140_TYPE, + HCLGE_PTP_UDP_FULL_TYPE, +}; + +enum hclge_ptp_msg_type { + HCLGE_PTP_MSG_TYPE_V2_L2, + HCLGE_PTP_MSG_TYPE_V2, + HCLGE_PTP_MSG_TYPE_V2_EVENT, +}; + +enum hclge_ptp_msg0_type { + HCLGE_PTP_MSG0_V2_DELAY_REQ = 1, + HCLGE_PTP_MSG0_V2_PDELAY_REQ, + HCLGE_PTP_MSG0_V2_DELAY_RESP, + HCLGE_PTP_MSG0_V2_EVENT = 0xF, +}; + +#define HCLGE_PTP_MSG1_V2_DEFAULT 1 + +struct hclge_ptp_cfg_cmd { +#define HCLGE_PTP_EN_B BIT(0) +#define HCLGE_PTP_TX_EN_B BIT(1) +#define HCLGE_PTP_RX_EN_B BIT(2) +#define HCLGE_PTP_UDP_EN_SHIFT 3 +#define HCLGE_PTP_UDP_EN_MASK GENMASK(4, 3) +#define HCLGE_PTP_MSG_TYPE_SHIFT 8 +#define HCLGE_PTP_MSG_TYPE_MASK GENMASK(9, 8) +#define HCLGE_PTP_MSG1_SHIFT 16 +#define HCLGE_PTP_MSG1_MASK GENMASK(19, 16) +#define HCLGE_PTP_MSG0_SHIFT 24 +#define HCLGE_PTP_MSG0_MASK GENMASK(27, 24) + + __le32 cfg; + u8 rsvd[20]; +}; + +static inline struct hclge_dev *hclge_ptp_get_hdev(struct ptp_clock_info *info) +{ + struct hclge_ptp *ptp = container_of(info, struct hclge_ptp, info); + + return ptp->hdev; +} + +bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb); +void hclge_ptp_clean_tx_hwts(struct hclge_dev *dev); +void hclge_ptp_get_rx_hwts(struct hnae3_handle *handle, struct sk_buff *skb, + u32 nsec, u32 sec); +int hclge_ptp_get_cfg(struct hclge_dev *hdev, struct ifreq *ifr); +int hclge_ptp_set_cfg(struct hclge_dev *hdev, struct ifreq *ifr); +int hclge_ptp_init(struct hclge_dev *hdev); +void hclge_ptp_uninit(struct hclge_dev *hdev); +int hclge_ptp_get_ts_info(struct hnae3_handle *handle, + struct ethtool_ts_info *info); +int hclge_ptp_cfg_qry(struct hclge_dev *hdev, u32 *cfg); +#endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index ebb962bad451..78d5bf1ea561 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -1733,6 +1733,36 @@ int hclge_tm_get_qset_weight(struct hclge_dev *hdev, u16 qset_id, u8 *weight) return 0; } +int hclge_tm_get_qset_shaper(struct hclge_dev *hdev, u16 qset_id, + struct hclge_tm_shaper_para *para) +{ + struct hclge_qs_shapping_cmd *shap_cfg_cmd; + struct hclge_desc desc; + u32 shapping_para; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QCN_SHAPPING_CFG, true); + shap_cfg_cmd = (struct hclge_qs_shapping_cmd *)desc.data; + shap_cfg_cmd->qs_id = cpu_to_le16(qset_id); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get qset %u shaper, ret = %d\n", qset_id, + ret); + return ret; + } + + shapping_para = le32_to_cpu(shap_cfg_cmd->qs_shapping_para); + para->ir_b = hclge_tm_get_field(shapping_para, IR_B); + para->ir_u = hclge_tm_get_field(shapping_para, IR_U); + para->ir_s = hclge_tm_get_field(shapping_para, IR_S); + para->bs_b = hclge_tm_get_field(shapping_para, BS_B); + para->bs_s = hclge_tm_get_field(shapping_para, BS_S); + para->flag = shap_cfg_cmd->flag; + para->rate = le32_to_cpu(shap_cfg_cmd->qs_rate); + return 0; +} + int hclge_tm_get_pri_sch_mode(struct hclge_dev *hdev, u8 pri_id, u8 *mode) { struct hclge_pri_sch_mode_cfg_cmd *pri_sch_mode; @@ -1775,7 +1805,7 @@ int hclge_tm_get_pri_weight(struct hclge_dev *hdev, u8 pri_id, u8 *weight) int hclge_tm_get_pri_shaper(struct hclge_dev *hdev, u8 pri_id, enum hclge_opcode_type cmd, - struct hclge_pri_shaper_para *para) + struct hclge_tm_shaper_para *para) { struct hclge_pri_shapping_cmd *shap_cfg_cmd; struct hclge_desc desc; @@ -1807,3 +1837,186 @@ int hclge_tm_get_pri_shaper(struct hclge_dev *hdev, u8 pri_id, para->rate = le32_to_cpu(shap_cfg_cmd->pri_rate); return 0; } + +int hclge_tm_get_q_to_qs_map(struct hclge_dev *hdev, u16 q_id, u16 *qset_id) +{ + struct hclge_nq_to_qs_link_cmd *map; + struct hclge_desc desc; + u16 qs_id_l; + u16 qs_id_h; + int ret; + + map = (struct hclge_nq_to_qs_link_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_NQ_TO_QS_LINK, true); + map->nq_id = cpu_to_le16(q_id); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get queue to qset map, ret = %d\n", ret); + return ret; + } + *qset_id = le16_to_cpu(map->qset_id); + + /* convert qset_id to the following format, drop the vld bit + * | qs_id_h | vld | qs_id_l | + * qset_id: | 15 ~ 11 | 10 | 9 ~ 0 | + * \ \ / / + * \ \ / / + * qset_id: | 15 | 14 ~ 10 | 9 ~ 0 | + */ + qs_id_l = hnae3_get_field(*qset_id, HCLGE_TM_QS_ID_L_MSK, + HCLGE_TM_QS_ID_L_S); + qs_id_h = hnae3_get_field(*qset_id, HCLGE_TM_QS_ID_H_EXT_MSK, + HCLGE_TM_QS_ID_H_EXT_S); + *qset_id = 0; + hnae3_set_field(*qset_id, HCLGE_TM_QS_ID_L_MSK, HCLGE_TM_QS_ID_L_S, + qs_id_l); + hnae3_set_field(*qset_id, HCLGE_TM_QS_ID_H_MSK, HCLGE_TM_QS_ID_H_S, + qs_id_h); + return 0; +} + +int hclge_tm_get_q_to_tc(struct hclge_dev *hdev, u16 q_id, u8 *tc_id) +{ +#define HCLGE_TM_TC_MASK 0x7 + + struct hclge_tqp_tx_queue_tc_cmd *tc; + struct hclge_desc desc; + int ret; + + tc = (struct hclge_tqp_tx_queue_tc_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TQP_TX_QUEUE_TC, true); + tc->queue_id = cpu_to_le16(q_id); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get queue to tc map, ret = %d\n", ret); + return ret; + } + + *tc_id = tc->tc_id & HCLGE_TM_TC_MASK; + return 0; +} + +int hclge_tm_get_pg_to_pri_map(struct hclge_dev *hdev, u8 pg_id, + u8 *pri_bit_map) +{ + struct hclge_pg_to_pri_link_cmd *map; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PG_TO_PRI_LINK, true); + map = (struct hclge_pg_to_pri_link_cmd *)desc.data; + map->pg_id = pg_id; + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get pg to pri map, ret = %d\n", ret); + return ret; + } + + *pri_bit_map = map->pri_bit_map; + return 0; +} + +int hclge_tm_get_pg_weight(struct hclge_dev *hdev, u8 pg_id, u8 *weight) +{ + struct hclge_pg_weight_cmd *pg_weight_cmd; + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PG_WEIGHT, true); + pg_weight_cmd = (struct hclge_pg_weight_cmd *)desc.data; + pg_weight_cmd->pg_id = pg_id; + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get pg weight, ret = %d\n", ret); + return ret; + } + + *weight = pg_weight_cmd->dwrr; + return 0; +} + +int hclge_tm_get_pg_sch_mode(struct hclge_dev *hdev, u8 pg_id, u8 *mode) +{ + struct hclge_desc desc; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PG_SCH_MODE_CFG, true); + desc.data[0] = cpu_to_le32(pg_id); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get pg sch mode, ret = %d\n", ret); + return ret; + } + + *mode = (u8)le32_to_cpu(desc.data[1]); + return 0; +} + +int hclge_tm_get_pg_shaper(struct hclge_dev *hdev, u8 pg_id, + enum hclge_opcode_type cmd, + struct hclge_tm_shaper_para *para) +{ + struct hclge_pg_shapping_cmd *shap_cfg_cmd; + struct hclge_desc desc; + u32 shapping_para; + int ret; + + if (cmd != HCLGE_OPC_TM_PG_C_SHAPPING && + cmd != HCLGE_OPC_TM_PG_P_SHAPPING) + return -EINVAL; + + hclge_cmd_setup_basic_desc(&desc, cmd, true); + shap_cfg_cmd = (struct hclge_pg_shapping_cmd *)desc.data; + shap_cfg_cmd->pg_id = pg_id; + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get pg shaper(%#x), ret = %d\n", + cmd, ret); + return ret; + } + + shapping_para = le32_to_cpu(shap_cfg_cmd->pg_shapping_para); + para->ir_b = hclge_tm_get_field(shapping_para, IR_B); + para->ir_u = hclge_tm_get_field(shapping_para, IR_U); + para->ir_s = hclge_tm_get_field(shapping_para, IR_S); + para->bs_b = hclge_tm_get_field(shapping_para, BS_B); + para->bs_s = hclge_tm_get_field(shapping_para, BS_S); + para->flag = shap_cfg_cmd->flag; + para->rate = le32_to_cpu(shap_cfg_cmd->pg_rate); + return 0; +} + +int hclge_tm_get_port_shaper(struct hclge_dev *hdev, + struct hclge_tm_shaper_para *para) +{ + struct hclge_port_shapping_cmd *port_shap_cfg_cmd; + struct hclge_desc desc; + u32 shapping_para; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TM_PORT_SHAPPING, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to get port shaper, ret = %d\n", ret); + return ret; + } + + port_shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data; + shapping_para = le32_to_cpu(port_shap_cfg_cmd->port_shapping_para); + para->ir_b = hclge_tm_get_field(shapping_para, IR_B); + para->ir_u = hclge_tm_get_field(shapping_para, IR_U); + para->ir_s = hclge_tm_get_field(shapping_para, IR_S); + para->bs_b = hclge_tm_get_field(shapping_para, BS_B); + para->bs_s = hclge_tm_get_field(shapping_para, BS_S); + para->flag = port_shap_cfg_cmd->flag; + para->rate = le32_to_cpu(port_shap_cfg_cmd->port_rate); + + return 0; +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index b25d76023af0..2ee9b795f71d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -199,14 +199,14 @@ struct hclge_tm_nodes_cmd { __le16 queue_num; }; -struct hclge_pri_shaper_para { +struct hclge_tm_shaper_para { + u32 rate; u8 ir_b; u8 ir_u; u8 ir_s; u8 bs_b; u8 bs_s; u8 flag; - u32 rate; }; #define hclge_tm_set_field(dest, string, val) \ @@ -237,9 +237,22 @@ int hclge_tm_get_qset_map_pri(struct hclge_dev *hdev, u16 qset_id, u8 *priority, u8 *link_vld); int hclge_tm_get_qset_sch_mode(struct hclge_dev *hdev, u16 qset_id, u8 *mode); int hclge_tm_get_qset_weight(struct hclge_dev *hdev, u16 qset_id, u8 *weight); +int hclge_tm_get_qset_shaper(struct hclge_dev *hdev, u16 qset_id, + struct hclge_tm_shaper_para *para); int hclge_tm_get_pri_sch_mode(struct hclge_dev *hdev, u8 pri_id, u8 *mode); int hclge_tm_get_pri_weight(struct hclge_dev *hdev, u8 pri_id, u8 *weight); int hclge_tm_get_pri_shaper(struct hclge_dev *hdev, u8 pri_id, enum hclge_opcode_type cmd, - struct hclge_pri_shaper_para *para); + struct hclge_tm_shaper_para *para); +int hclge_tm_get_q_to_qs_map(struct hclge_dev *hdev, u16 q_id, u16 *qset_id); +int hclge_tm_get_q_to_tc(struct hclge_dev *hdev, u16 q_id, u8 *tc_id); +int hclge_tm_get_pg_to_pri_map(struct hclge_dev *hdev, u8 pg_id, + u8 *pri_bit_map); +int hclge_tm_get_pg_weight(struct hclge_dev *hdev, u8 pg_id, u8 *weight); +int hclge_tm_get_pg_sch_mode(struct hclge_dev *hdev, u8 pg_id, u8 *mode); +int hclge_tm_get_pg_shaper(struct hclge_dev *hdev, u8 pg_id, + enum hclge_opcode_type cmd, + struct hclge_tm_shaper_para *para); +int hclge_tm_get_port_shaper(struct hclge_dev *hdev, + struct hclge_tm_shaper_para *para); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c index d8c5c5810b99..bd19a2d89f6c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c @@ -359,6 +359,8 @@ static void hclgevf_parse_capability(struct hclgevf_dev *hdev, set_bit(HNAE3_DEV_SUPPORT_HW_TX_CSUM_B, ae_dev->caps); if (hnae3_get_bit(caps, HCLGEVF_CAP_UDP_TUNNEL_CSUM_B)) set_bit(HNAE3_DEV_SUPPORT_UDP_TUNNEL_CSUM_B, ae_dev->caps); + if (hnae3_get_bit(caps, HCLGEVF_CAP_RXD_ADV_LAYOUT_B)) + set_bit(HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B, ae_dev->caps); } static __le32 hclgevf_build_api_caps(void) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h index c6dc11b32aa7..202feb70dba5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h @@ -159,6 +159,7 @@ enum HCLGEVF_CAP_BITS { HCLGEVF_CAP_HW_PAD_B, HCLGEVF_CAP_STASH_B, HCLGEVF_CAP_UDP_TUNNEL_CSUM_B, + HCLGEVF_CAP_RXD_ADV_LAYOUT_B = 15, }; enum HCLGEVF_API_CAP_BITS { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 0db51ef15ef6..52eaf82b7cd7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -243,23 +243,31 @@ static void hclgevf_build_send_msg(struct hclge_vf_to_pf_msg *msg, u8 code, } } -static int hclgevf_get_tc_info(struct hclgevf_dev *hdev) +static int hclgevf_get_basic_info(struct hclgevf_dev *hdev) { + struct hnae3_ae_dev *ae_dev = hdev->ae_dev; + u8 resp_msg[HCLGE_MBX_MAX_RESP_DATA_SIZE]; + struct hclge_basic_info *basic_info; struct hclge_vf_to_pf_msg send_msg; - u8 resp_msg; + unsigned long caps; int status; - hclgevf_build_send_msg(&send_msg, HCLGE_MBX_GET_TCINFO, 0); - status = hclgevf_send_mbx_msg(hdev, &send_msg, true, &resp_msg, + hclgevf_build_send_msg(&send_msg, HCLGE_MBX_GET_BASIC_INFO, 0); + status = hclgevf_send_mbx_msg(hdev, &send_msg, true, resp_msg, sizeof(resp_msg)); if (status) { dev_err(&hdev->pdev->dev, - "VF request to get TC info from PF failed %d", - status); + "failed to get basic info from pf, ret = %d", status); return status; } - hdev->hw_tc_map = resp_msg; + basic_info = (struct hclge_basic_info *)resp_msg; + + hdev->hw_tc_map = basic_info->hw_tc_map; + hdev->mbx_api_version = basic_info->mbx_api_version; + caps = basic_info->pf_caps; + if (test_bit(HNAE3_PF_SUPPORT_VLAN_FLTR_MDF_B, &caps)) + set_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps); return 0; } @@ -1528,8 +1536,7 @@ static void hclgevf_sync_from_add_list(struct list_head *add_list, kfree(mac_node); } else if (mac_node->state == HCLGEVF_MAC_ACTIVE) { mac_node->state = HCLGEVF_MAC_TO_DEL; - list_del(&mac_node->node); - list_add_tail(&mac_node->node, mac_list); + list_move_tail(&mac_node->node, mac_list); } else { list_del(&mac_node->node); kfree(mac_node); @@ -1554,8 +1561,7 @@ static void hclgevf_sync_from_del_list(struct list_head *del_list, list_del(&mac_node->node); kfree(mac_node); } else { - list_del(&mac_node->node); - list_add_tail(&mac_node->node, mac_list); + list_move_tail(&mac_node->node, mac_list); } } } @@ -1591,8 +1597,7 @@ static void hclgevf_sync_mac_list(struct hclgevf_dev *hdev, list_for_each_entry_safe(mac_node, tmp, list, node) { switch (mac_node->state) { case HCLGEVF_MAC_TO_DEL: - list_del(&mac_node->node); - list_add_tail(&mac_node->node, &tmp_del_list); + list_move_tail(&mac_node->node, &tmp_del_list); break; case HCLGEVF_MAC_TO_ADD: new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC); @@ -1642,6 +1647,22 @@ static void hclgevf_uninit_mac_list(struct hclgevf_dev *hdev) spin_unlock_bh(&hdev->mac_table.mac_list_lock); } +static int hclgevf_enable_vlan_filter(struct hnae3_handle *handle, bool enable) +{ + struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + struct hnae3_ae_dev *ae_dev = hdev->ae_dev; + struct hclge_vf_to_pf_msg send_msg; + + if (!test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps)) + return -EOPNOTSUPP; + + hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN, + HCLGE_MBX_ENABLE_VLAN_FILTER); + send_msg.data[0] = enable ? 1 : 0; + + return hclgevf_send_mbx_msg(hdev, &send_msg, true, NULL, 0); +} + static int hclgevf_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, u16 vlan_id, bool is_kill) @@ -2466,6 +2487,10 @@ static int hclgevf_configure(struct hclgevf_dev *hdev) { int ret; + ret = hclgevf_get_basic_info(hdev); + if (ret) + return ret; + /* get current port based vlan state from PF */ ret = hclgevf_get_port_base_vlan_filter_state(hdev); if (ret) @@ -2481,12 +2506,7 @@ static int hclgevf_configure(struct hclgevf_dev *hdev) if (ret) return ret; - ret = hclgevf_get_pf_media_type(hdev); - if (ret) - return ret; - - /* get tc configuration from PF */ - return hclgevf_get_tc_info(hdev); + return hclgevf_get_pf_media_type(hdev); } static int hclgevf_alloc_hdev(struct hnae3_ae_dev *ae_dev) @@ -3242,6 +3262,18 @@ static int hclgevf_clear_vport_list(struct hclgevf_dev *hdev) return hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); } +static void hclgevf_init_rxd_adv_layout(struct hclgevf_dev *hdev) +{ + if (hnae3_ae_dev_rxd_adv_layout_supported(hdev->ae_dev)) + hclgevf_write_dev(&hdev->hw, HCLGEVF_RXD_ADV_LAYOUT_EN_REG, 1); +} + +static void hclgevf_uninit_rxd_adv_layout(struct hclgevf_dev *hdev) +{ + if (hnae3_ae_dev_rxd_adv_layout_supported(hdev->ae_dev)) + hclgevf_write_dev(&hdev->hw, HCLGEVF_RXD_ADV_LAYOUT_EN_REG, 0); +} + static int hclgevf_reset_hdev(struct hclgevf_dev *hdev) { struct pci_dev *pdev = hdev->pdev; @@ -3279,6 +3311,8 @@ static int hclgevf_reset_hdev(struct hclgevf_dev *hdev) set_bit(HCLGEVF_STATE_PROMISC_CHANGED, &hdev->state); + hclgevf_init_rxd_adv_layout(hdev); + dev_info(&hdev->pdev->dev, "Reset done\n"); return 0; @@ -3379,6 +3413,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) goto err_config; } + hclgevf_init_rxd_adv_layout(hdev); + hdev->last_reset_time = jiffies; dev_info(&hdev->pdev->dev, "finished initializing %s driver\n", HCLGEVF_DRIVER_NAME); @@ -3405,6 +3441,7 @@ static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev) struct hclge_vf_to_pf_msg send_msg; hclgevf_state_uninit(hdev); + hclgevf_uninit_rxd_adv_layout(hdev); hclgevf_build_send_msg(&send_msg, HCLGE_MBX_VF_UNINIT, 0); hclgevf_send_mbx_msg(hdev, &send_msg, false, NULL, 0); @@ -3784,6 +3821,7 @@ static const struct hnae3_ae_ops hclgevf_ops = { .get_tc_size = hclgevf_get_tc_size, .get_fw_version = hclgevf_get_fw_version, .set_vlan_filter = hclgevf_set_vlan_filter, + .enable_vlan_filter = hclgevf_enable_vlan_filter, .enable_hw_strip_rxvtag = hclgevf_en_hw_strip_rxvtag, .reset_event = hclgevf_reset_event, .set_default_reset_request = hclgevf_set_def_reset_request, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 265c9b0b4728..d7d02848d674 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -47,6 +47,7 @@ /* bar registers for common func */ #define HCLGEVF_GRO_EN_REG 0x28000 +#define HCLGEVF_RXD_ADV_LAYOUT_EN_REG 0x28008 /* bar registers for rcb */ #define HCLGEVF_RING_RX_ADDR_L_REG 0x80000 @@ -284,6 +285,7 @@ struct hclgevf_dev { struct semaphore reset_sem; /* protect reset process */ u32 fw_version; + u16 mbx_api_version; u16 num_tqps; /* num task queue pairs of this VF */ u16 alloc_rss_size; /* allocated RSS task queue */ diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index dc024ef521c0..162d3c330dec 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -1663,7 +1663,6 @@ static void hinic_diag_test(struct net_device *netdev, err = hinic_port_link_state(nic_dev, &link_state); if (!err && link_state == HINIC_LINK_STATE_UP) netif_carrier_on(netdev); - } static int hinic_set_phys_id(struct net_device *netdev, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c index 5a6bbee819cd..307a6d4af993 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c @@ -223,7 +223,7 @@ static void cmdq_prepare_wqe_ctrl(struct hinic_cmdq_wqe *wqe, int wrapped, saved_data = CMDQ_WQE_HEADER(wqe)->saved_data; saved_data = HINIC_SAVED_DATA_CLEAR(saved_data, ARM); - if ((cmd == CMDQ_SET_ARM_CMD) && (mod == HINIC_MOD_COMM)) + if (cmd == CMDQ_SET_ARM_CMD && mod == HINIC_MOD_COMM) CMDQ_WQE_HEADER(wqe)->saved_data |= HINIC_SAVED_DATA_SET(1, ARM); else @@ -594,7 +594,7 @@ static void cmdq_update_errcode(struct hinic_cmdq *cmdq, u16 prod_idx, } /** - * cmdq_arm_ceq_handler - cmdq completion event handler for sync command + * cmdq_sync_cmd_handler - cmdq completion event handler for sync command * @cmdq: the cmdq of the command * @cons_idx: the consumer index to update the error code for * @errcode: the error code diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 0c74f6674634..428108eb10d2 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -48,7 +48,7 @@ enum io_status { }; /** - * get_capability - convert device capabilities to NIC capabilities + * parse_capability - convert device capabilities to NIC capabilities * @hwdev: the HW device to set and convert device capabilities for * @dev_cap: device capabilities from FW * @@ -92,7 +92,7 @@ static int parse_capability(struct hinic_hwdev *hwdev, } /** - * get_cap_from_fw - get device capabilities from FW + * get_capability - get device capabilities from FW * @pfhwdev: the PF HW device to get capabilities for * * Return 0 - Success, negative - Failure @@ -257,7 +257,7 @@ static int init_fw_ctxt(struct hinic_hwdev *hwdev) err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_FWCTXT_INIT, &fw_ctxt, sizeof(fw_ctxt), &fw_ctxt, &out_size); - if (err || (out_size != sizeof(fw_ctxt)) || fw_ctxt.status) { + if (err || out_size != sizeof(fw_ctxt) || fw_ctxt.status) { dev_err(&pdev->dev, "Failed to init FW ctxt, err: %d, status: 0x%x, out size: 0x%x\n", err, fw_ctxt.status, out_size); return -EIO; @@ -346,7 +346,7 @@ static int wait_for_db_state(struct hinic_hwdev *hwdev) } /** - * clear_io_resource - set the IO resources as not active in the NIC + * clear_io_resources - set the IO resources as not active in the NIC * @hwdev: the NIC HW device * * Return 0 - Success, negative - Failure @@ -424,7 +424,7 @@ static int get_base_qpn(struct hinic_hwdev *hwdev, u16 *base_qpn) err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_GLOBAL_QPN, &cmd_base_qpn, sizeof(cmd_base_qpn), &cmd_base_qpn, &out_size); - if (err || (out_size != sizeof(cmd_base_qpn)) || cmd_base_qpn.status) { + if (err || out_size != sizeof(cmd_base_qpn) || cmd_base_qpn.status) { dev_err(&pdev->dev, "Failed to get base qpn, err: %d, status: 0x%x, out size: 0x%x\n", err, cmd_base_qpn.status, out_size); return -EIO; @@ -605,8 +605,8 @@ static void nic_mgmt_msg_handler(void *handle, u8 cmd, void *buf_in, hwif = hwdev->hwif; pdev = hwif->pdev; - if ((cmd < HINIC_MGMT_MSG_CMD_BASE) || - (cmd >= HINIC_MGMT_MSG_CMD_MAX)) { + if (cmd < HINIC_MGMT_MSG_CMD_BASE || + cmd >= HINIC_MGMT_MSG_CMD_MAX) { dev_err(&pdev->dev, "unknown L2NIC event, cmd = %d\n", cmd); return; } @@ -619,7 +619,7 @@ static void nic_mgmt_msg_handler(void *handle, u8 cmd, void *buf_in, HINIC_CB_ENABLED, HINIC_CB_ENABLED | HINIC_CB_RUNNING); - if ((cb_state == HINIC_CB_ENABLED) && (nic_cb->handler)) + if (cb_state == HINIC_CB_ENABLED && nic_cb->handler) nic_cb->handler(nic_cb->handle, buf_in, in_size, buf_out, out_size); else @@ -1090,7 +1090,7 @@ struct hinic_sq *hinic_hwdev_get_sq(struct hinic_hwdev *hwdev, int i) } /** - * hinic_hwdev_get_sq - get RQ + * hinic_hwdev_get_rq - get RQ * @hwdev: the NIC HW device * @i: the position of the RQ * diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c index 19942fef99d9..d3fc05a07fdb 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c @@ -254,8 +254,8 @@ static void aeq_irq_handler(struct hinic_eq *eq) HINIC_EQE_ENABLED, HINIC_EQE_ENABLED | HINIC_EQE_RUNNING); - if ((eqe_state == HINIC_EQE_ENABLED) && - (hwe_cb->hwe_handler)) + if (eqe_state == HINIC_EQE_ENABLED && + hwe_cb->hwe_handler) hwe_cb->hwe_handler(hwe_cb->handle, aeqe_curr->data, size); else @@ -299,7 +299,7 @@ static void ceq_event_handler(struct hinic_ceqs *ceqs, u32 ceqe) HINIC_EQE_ENABLED, HINIC_EQE_ENABLED | HINIC_EQE_RUNNING); - if ((eqe_state == HINIC_EQE_ENABLED) && (ceq_cb->handler)) + if (eqe_state == HINIC_EQE_ENABLED && ceq_cb->handler) ceq_cb->handler(ceq_cb->handle, CEQE_DATA(ceqe)); else dev_err(&pdev->dev, "Unhandled CEQ Event %d\n", event); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c index cab38ff0713c..0428faa68e80 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c @@ -334,7 +334,7 @@ static void set_dma_attr(struct hinic_hwif *hwif, u32 entry_idx, } /** - * dma_attr_table_init - initialize the default dma attributes + * dma_attr_init - initialize the default dma attributes * @hwif: the HW interface of a pci function device **/ static void dma_attr_init(struct hinic_hwif *hwif) @@ -395,7 +395,7 @@ static void __print_selftest_reg(struct hinic_hwif *hwif) /** * hinic_init_hwif - initialize the hw interface * @hwif: the HW interface of a pci function device - * @pdev: the pci device for acessing PCI resources + * @pdev: the pci device for accessing PCI resources * * Return 0 - Success, negative - Failure **/ diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c index 4ef4008e65bd..a6e43d686293 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c @@ -137,7 +137,7 @@ static int write_sq_ctxts(struct hinic_func_to_io *func_to_io, u16 base_qpn, err = hinic_cmdq_direct_resp(&func_to_io->cmdqs, HINIC_MOD_L2NIC, IO_CMD_MODIFY_QUEUE_CTXT, &cmdq_buf, &out_param); - if ((err) || (out_param != 0)) { + if (err || out_param != 0) { dev_err(&pdev->dev, "Failed to set SQ ctxts\n"); err = -EFAULT; } @@ -181,7 +181,7 @@ static int write_rq_ctxts(struct hinic_func_to_io *func_to_io, u16 base_qpn, err = hinic_cmdq_direct_resp(&func_to_io->cmdqs, HINIC_MOD_L2NIC, IO_CMD_MODIFY_QUEUE_CTXT, &cmdq_buf, &out_param); - if ((err) || (out_param != 0)) { + if (err || out_param != 0) { dev_err(&pdev->dev, "Failed to set RQ ctxts\n"); err = -EFAULT; } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c index 817173f1fbb7..ebc77771f5da 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c @@ -294,7 +294,7 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt, goto unlock_sync_msg; } - if ((buf_out) && (recv_msg->msg_len <= MAX_PF_MGMT_BUF_SIZE)) { + if (buf_out && recv_msg->msg_len <= MAX_PF_MGMT_BUF_SIZE) { memcpy(buf_out, recv_msg->msg, recv_msg->msg_len); *out_size = recv_msg->msg_len; } @@ -411,7 +411,7 @@ static void recv_mgmt_msg_work_handler(struct work_struct *work) HINIC_MGMT_CB_ENABLED, HINIC_MGMT_CB_ENABLED | HINIC_MGMT_CB_RUNNING); - if ((cb_state == HINIC_MGMT_CB_ENABLED) && (mgmt_cb->cb)) + if (cb_state == HINIC_MGMT_CB_ENABLED && mgmt_cb->cb) mgmt_cb->cb(mgmt_cb->handle, mgmt_work->cmd, mgmt_work->msg, mgmt_work->msg_len, buf_out, &out_size); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c index dcba4d009bad..336248aa2e48 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c @@ -894,7 +894,7 @@ struct hinic_rq_wqe *hinic_rq_read_next_wqe(struct hinic_rq *rq, } /** - * hinic_put_wqe - release the ci for new wqes + * hinic_rq_put_wqe - release the ci for new wqes * @rq: recv queue * @cons_idx: consumer index of the wqe * @wqe_size: the size of the wqe diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c index 5dc3743f8091..7f0f1aa3cedd 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c @@ -89,6 +89,7 @@ static inline int WQE_PAGE_NUM(struct hinic_wq *wq, u16 idx) return (((idx) >> ((wq)->wqebbs_per_page_shift)) & ((wq)->num_q_pages - 1)); } + /** * queue_alloc_page - allocate page for Queue * @hwif: HW interface for allocating DMA diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 9a9b09401d01..405ee4d2d2b1 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -172,7 +172,6 @@ static int create_txqs(struct hinic_dev *nic_dev) "Failed to add SQ%d debug\n", i); goto err_add_sq_dbg; } - } return 0; @@ -233,7 +232,7 @@ static void free_txqs(struct hinic_dev *nic_dev) } /** - * create_txqs - Create the Logical Rx Queues of specific NIC device + * create_rxqs - Create the Logical Rx Queues of specific NIC device * @nic_dev: the specific NIC device * * Return 0 - Success, negative - Failure @@ -289,7 +288,7 @@ err_init_rxq: } /** - * free_txqs - Free the Logical Rx Queues of specific NIC device + * free_rxqs - Free the Logical Rx Queues of specific NIC device * @nic_dev: the specific NIC device **/ static void free_rxqs(struct hinic_dev *nic_dev) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c index eb97f2d6b1ad..28ae6f1201a8 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c @@ -128,7 +128,7 @@ int hinic_port_get_mac(struct hinic_dev *nic_dev, u8 *addr) err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_MAC, &port_mac_cmd, sizeof(port_mac_cmd), &port_mac_cmd, &out_size); - if (err || (out_size != sizeof(port_mac_cmd)) || port_mac_cmd.status) { + if (err || out_size != sizeof(port_mac_cmd) || port_mac_cmd.status) { dev_err(&pdev->dev, "Failed to get mac, err: %d, status: 0x%x, out size: 0x%x\n", err, port_mac_cmd.status, out_size); return -EFAULT; @@ -263,7 +263,7 @@ int hinic_port_link_state(struct hinic_dev *nic_dev, err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_LINK_STATE, &link_cmd, sizeof(link_cmd), &link_cmd, &out_size); - if (err || (out_size != sizeof(link_cmd)) || link_cmd.status) { + if (err || out_size != sizeof(link_cmd) || link_cmd.status) { dev_err(&pdev->dev, "Failed to get link state, err: %d, status: 0x%x, out size: 0x%x\n", err, link_cmd.status, out_size); return -EINVAL; @@ -297,7 +297,7 @@ int hinic_port_set_state(struct hinic_dev *nic_dev, enum hinic_port_state state) err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_PORT_STATE, &port_state, sizeof(port_state), &port_state, &out_size); - if (err || (out_size != sizeof(port_state)) || port_state.status) { + if (err || out_size != sizeof(port_state) || port_state.status) { dev_err(&pdev->dev, "Failed to set port state, err: %d, status: 0x%x, out size: 0x%x\n", err, port_state.status, out_size); return -EFAULT; @@ -329,7 +329,7 @@ int hinic_port_set_func_state(struct hinic_dev *nic_dev, err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_FUNC_STATE, &func_state, sizeof(func_state), &func_state, &out_size); - if (err || (out_size != sizeof(func_state)) || func_state.status) { + if (err || out_size != sizeof(func_state) || func_state.status) { dev_err(&pdev->dev, "Failed to set port func state, err: %d, status: 0x%x, out size: 0x%x\n", err, func_state.status, out_size); return -EFAULT; @@ -359,7 +359,7 @@ int hinic_port_get_cap(struct hinic_dev *nic_dev, err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_GET_CAP, port_cap, sizeof(*port_cap), port_cap, &out_size); - if (err || (out_size != sizeof(*port_cap)) || port_cap->status) { + if (err || out_size != sizeof(*port_cap) || port_cap->status) { dev_err(&pdev->dev, "Failed to get port capabilities, err: %d, status: 0x%x, out size: 0x%x\n", err, port_cap->status, out_size); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index cce08647b9b2..fed3b6bc0d76 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -118,6 +118,7 @@ static void rx_csum(struct hinic_rxq *rxq, u32 status, skb->ip_summed = CHECKSUM_NONE; } } + /** * rx_alloc_skb - allocate skb and map it to dma address * @rxq: rx queue diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index 710c4ff7bc0e..c5bdb0d374ef 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -660,7 +660,7 @@ static void tx_free_skb(struct hinic_dev *nic_dev, struct sk_buff *skb, } /** - * free_all_rx_skbs - free all skbs in tx queue + * free_all_tx_skbs - free all skbs in tx queue * @txq: tx queue **/ static void free_all_tx_skbs(struct hinic_txq *txq) @@ -717,7 +717,7 @@ static int free_tx_poll(struct napi_struct *napi, int budget) /* Reading a WQEBB to get real WQE size and consumer index. */ sq_wqe = hinic_sq_read_wqebb(sq, &skb, &wqe_size, &sw_ci); - if ((!sq_wqe) || + if (!sq_wqe || (((hw_ci - sw_ci) & wq->mask) * wq->wqebb_size < wqe_size)) break; diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index ea55314b209d..d5df131b183c 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -2618,10 +2618,8 @@ static int ehea_restart_qps(struct net_device *dev) u16 dummy16 = 0; cb0 = (void *)get_zeroed_page(GFP_KERNEL); - if (!cb0) { - ret = -ENOMEM; - goto out; - } + if (!cb0) + return -ENOMEM; for (i = 0; i < (port->num_def_qps); i++) { struct ehea_port_res *pr = &port->port_res[i]; @@ -2641,6 +2639,7 @@ static int ehea_restart_qps(struct net_device *dev) cb0); if (hret != H_SUCCESS) { netdev_err(dev, "query_ehea_qp failed (1)\n"); + ret = -EFAULT; goto out; } @@ -2653,6 +2652,7 @@ static int ehea_restart_qps(struct net_device *dev) &dummy64, &dummy16, &dummy16); if (hret != H_SUCCESS) { netdev_err(dev, "modify_ehea_qp failed (1)\n"); + ret = -EFAULT; goto out; } @@ -2661,6 +2661,7 @@ static int ehea_restart_qps(struct net_device *dev) cb0); if (hret != H_SUCCESS) { netdev_err(dev, "query_ehea_qp failed (2)\n"); + ret = -EFAULT; goto out; } @@ -2867,14 +2868,14 @@ out: return ret; } -static ssize_t ehea_show_port_id(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t log_port_id_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct ehea_port *port = container_of(dev, struct ehea_port, ofdev.dev); return sprintf(buf, "%d", port->logical_port_id); } -static DEVICE_ATTR(log_port_id, 0444, ehea_show_port_id, NULL); +static DEVICE_ATTR_RO(log_port_id); static void logical_port_release(struct device *dev) { @@ -3113,7 +3114,7 @@ static struct device_node *ehea_get_eth_dn(struct ehea_adapter *adapter, return NULL; } -static ssize_t ehea_probe_port(struct device *dev, +static ssize_t probe_port_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -3168,9 +3169,9 @@ static ssize_t ehea_probe_port(struct device *dev, return (ssize_t) count; } -static ssize_t ehea_remove_port(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t remove_port_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct ehea_adapter *adapter = dev_get_drvdata(dev); struct ehea_port *port; @@ -3203,8 +3204,8 @@ static ssize_t ehea_remove_port(struct device *dev, return (ssize_t) count; } -static DEVICE_ATTR(probe_port, 0200, NULL, ehea_probe_port); -static DEVICE_ATTR(remove_port, 0200, NULL, ehea_remove_port); +static DEVICE_ATTR_WO(probe_port); +static DEVICE_ATTR_WO(remove_port); static int ehea_create_device_sysfs(struct platform_device *dev) { diff --git a/drivers/net/ethernet/ibm/emac/emac.h b/drivers/net/ethernet/ibm/emac/emac.h index aa9f651288d5..09d3ac374b2d 100644 --- a/drivers/net/ethernet/ibm/emac/emac.h +++ b/drivers/net/ethernet/ibm/emac/emac.h @@ -77,7 +77,7 @@ struct emac_regs { struct { u32 rsvd1; u32 revid; - u32 rsvd2[2]; + u32 rsvd2[2]; u32 iaht1; /* Reset, R */ u32 iaht2; /* Reset, R */ u32 iaht3; /* Reset, R */ diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 7fea9ae60f13..737ba85e409f 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1285,36 +1285,41 @@ static void ibmveth_rx_csum_helper(struct sk_buff *skb, iph_proto = iph6->nexthdr; } - /* In OVS environment, when a flow is not cached, specifically for a - * new TCP connection, the first packet information is passed up + /* When CSO is enabled the TCP checksum may have be set to NULL by + * the sender given that we zeroed out TCP checksum field in + * transmit path (refer ibmveth_start_xmit routine). In this case set + * up CHECKSUM_PARTIAL. If the packet is forwarded, the checksum will + * then be recalculated by the destination NIC (CSO must be enabled + * on the destination NIC). + * + * In an OVS environment, when a flow is not cached, specifically for a + * new TCP connection, the first packet information is passed up to * the user space for finding a flow. During this process, OVS computes * checksum on the first packet when CHECKSUM_PARTIAL flag is set. * - * Given that we zeroed out TCP checksum field in transmit path - * (refer ibmveth_start_xmit routine) as we set "no checksum bit", - * OVS computed checksum will be incorrect w/o TCP pseudo checksum - * in the packet. This leads to OVS dropping the packet and hence - * TCP retransmissions are seen. - * - * So, re-compute TCP pseudo header checksum. + * So, re-compute TCP pseudo header checksum when configured for + * trunk mode. */ - if (iph_proto == IPPROTO_TCP && adapter->is_active_trunk) { + if (iph_proto == IPPROTO_TCP) { struct tcphdr *tcph = (struct tcphdr *)(skb->data + iphlen); - - tcphdrlen = skb->len - iphlen; - - /* Recompute TCP pseudo header checksum */ - if (skb_proto == ETH_P_IP) - tcph->check = ~csum_tcpudp_magic(iph->saddr, + if (tcph->check == 0x0000) { + /* Recompute TCP pseudo header checksum */ + if (adapter->is_active_trunk) { + tcphdrlen = skb->len - iphlen; + if (skb_proto == ETH_P_IP) + tcph->check = + ~csum_tcpudp_magic(iph->saddr, iph->daddr, tcphdrlen, iph_proto, 0); - else if (skb_proto == ETH_P_IPV6) - tcph->check = ~csum_ipv6_magic(&iph6->saddr, + else if (skb_proto == ETH_P_IPV6) + tcph->check = + ~csum_ipv6_magic(&iph6->saddr, &iph6->daddr, tcphdrlen, iph_proto, 0); - - /* Setup SKB fields for checksum offload */ - skb_partial_csum_set(skb, iphlen, - offsetof(struct tcphdr, check)); - skb_reset_network_header(skb); + } + /* Setup SKB fields for checksum offload */ + skb_partial_csum_set(skb, iphlen, + offsetof(struct tcphdr, check)); + skb_reset_network_header(skb); + } } } @@ -1799,8 +1804,7 @@ static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr, struct ibmveth_buff_pool *pool = container_of(kobj, struct ibmveth_buff_pool, kobj); - struct net_device *netdev = dev_get_drvdata( - container_of(kobj->parent, struct device, kobj)); + struct net_device *netdev = dev_get_drvdata(kobj_to_dev(kobj->parent)); struct ibmveth_adapter *adapter = netdev_priv(netdev); long value = simple_strtol(buf, NULL, 10); long rc; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5788bb956d73..374a75d4faea 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -95,7 +95,7 @@ static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *, struct ibmvnic_sub_crq_queue *); static int ibmvnic_poll(struct napi_struct *napi, int data); static void send_query_map(struct ibmvnic_adapter *adapter); -static int send_request_map(struct ibmvnic_adapter *, dma_addr_t, __be32, u8); +static int send_request_map(struct ibmvnic_adapter *, dma_addr_t, u32, u8); static int send_request_unmap(struct ibmvnic_adapter *, u8); static int send_login(struct ibmvnic_adapter *adapter); static void send_query_cap(struct ibmvnic_adapter *adapter); @@ -106,6 +106,8 @@ static void release_crq_queue(struct ibmvnic_adapter *); static int __ibmvnic_set_mac(struct net_device *, u8 *); static int init_crq_queue(struct ibmvnic_adapter *adapter); static int send_query_phys_parms(struct ibmvnic_adapter *adapter); +static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter, + struct ibmvnic_sub_crq_queue *tx_scrq); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -141,6 +143,29 @@ static const struct ibmvnic_stat ibmvnic_stats[] = { {"internal_mac_rx_errors", IBMVNIC_STAT_OFF(internal_mac_rx_errors)}, }; +static int send_crq_init_complete(struct ibmvnic_adapter *adapter) +{ + union ibmvnic_crq crq; + + memset(&crq, 0, sizeof(crq)); + crq.generic.first = IBMVNIC_CRQ_INIT_CMD; + crq.generic.cmd = IBMVNIC_CRQ_INIT_COMPLETE; + + return ibmvnic_send_crq(adapter, &crq); +} + +static int send_version_xchg(struct ibmvnic_adapter *adapter) +{ + union ibmvnic_crq crq; + + memset(&crq, 0, sizeof(crq)); + crq.version_exchange.first = IBMVNIC_CRQ_CMD; + crq.version_exchange.cmd = VERSION_EXCHANGE; + crq.version_exchange.version = cpu_to_be16(ibmvnic_version); + + return ibmvnic_send_crq(adapter, &crq); +} + static long h_reg_sub_crq(unsigned long unit_address, unsigned long token, unsigned long length, unsigned long *number, unsigned long *irq) @@ -209,12 +234,11 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter, mutex_lock(&adapter->fw_lock); adapter->fw_done_rc = 0; reinit_completion(&adapter->fw_done); - rc = send_request_map(adapter, ltb->addr, - ltb->size, ltb->map_id); + + rc = send_request_map(adapter, ltb->addr, ltb->size, ltb->map_id); if (rc) { - dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr); - mutex_unlock(&adapter->fw_lock); - return rc; + dev_err(dev, "send_request_map failed, rc = %d\n", rc); + goto out; } rc = ibmvnic_wait_for_completion(adapter, &adapter->fw_done, 10000); @@ -222,20 +246,23 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter, dev_err(dev, "Long term map request aborted or timed out,rc = %d\n", rc); - dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr); - mutex_unlock(&adapter->fw_lock); - return rc; + goto out; } if (adapter->fw_done_rc) { dev_err(dev, "Couldn't map long term buffer,rc = %d\n", adapter->fw_done_rc); + rc = -1; + goto out; + } + rc = 0; +out: + if (rc) { dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr); - mutex_unlock(&adapter->fw_lock); - return -1; + ltb->buff = NULL; } mutex_unlock(&adapter->fw_lock); - return 0; + return rc; } static void free_long_term_buff(struct ibmvnic_adapter *adapter, @@ -255,14 +282,44 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter, adapter->reset_reason != VNIC_RESET_TIMEOUT) send_request_unmap(adapter, ltb->map_id); dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr); + ltb->buff = NULL; + ltb->map_id = 0; } -static int reset_long_term_buff(struct ibmvnic_long_term_buff *ltb) +static int reset_long_term_buff(struct ibmvnic_adapter *adapter, + struct ibmvnic_long_term_buff *ltb) { - if (!ltb->buff) - return -EINVAL; + struct device *dev = &adapter->vdev->dev; + int rc; memset(ltb->buff, 0, ltb->size); + + mutex_lock(&adapter->fw_lock); + adapter->fw_done_rc = 0; + + reinit_completion(&adapter->fw_done); + rc = send_request_map(adapter, ltb->addr, ltb->size, ltb->map_id); + if (rc) { + mutex_unlock(&adapter->fw_lock); + return rc; + } + + rc = ibmvnic_wait_for_completion(adapter, &adapter->fw_done, 10000); + if (rc) { + dev_info(dev, + "Reset failed, long term map request timed out or aborted\n"); + mutex_unlock(&adapter->fw_lock); + return rc; + } + + if (adapter->fw_done_rc) { + dev_info(dev, + "Reset failed, attempting to free and reallocate buffer\n"); + free_long_term_buff(adapter, ltb); + mutex_unlock(&adapter->fw_lock); + return alloc_long_term_buff(adapter, ltb, ltb->size); + } + mutex_unlock(&adapter->fw_lock); return 0; } @@ -298,7 +355,14 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, rx_scrq = adapter->rx_scrq[pool->index]; ind_bufp = &rx_scrq->ind_buf; - for (i = 0; i < count; ++i) { + + /* netdev_skb_alloc() could have failed after we saved a few skbs + * in the indir_buf and we would not have sent them to VIOS yet. + * To account for them, start the loop at ind_bufp->index rather + * than 0. If we pushed all the skbs to VIOS, ind_bufp->index will + * be 0. + */ + for (i = ind_bufp->index; i < count; ++i) { skb = netdev_alloc_skb(adapter->netdev, pool->buff_size); if (!skb) { dev_err(dev, "Couldn't replenish rx buff\n"); @@ -484,7 +548,8 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter) rx_pool->size * rx_pool->buff_size); } else { - rc = reset_long_term_buff(&rx_pool->long_term_buff); + rc = reset_long_term_buff(adapter, + &rx_pool->long_term_buff); } if (rc) @@ -607,11 +672,12 @@ static int init_rx_pools(struct net_device *netdev) return 0; } -static int reset_one_tx_pool(struct ibmvnic_tx_pool *tx_pool) +static int reset_one_tx_pool(struct ibmvnic_adapter *adapter, + struct ibmvnic_tx_pool *tx_pool) { int rc, i; - rc = reset_long_term_buff(&tx_pool->long_term_buff); + rc = reset_long_term_buff(adapter, &tx_pool->long_term_buff); if (rc) return rc; @@ -638,10 +704,11 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter) tx_scrqs = adapter->num_active_tx_pools; for (i = 0; i < tx_scrqs; i++) { - rc = reset_one_tx_pool(&adapter->tso_pool[i]); + ibmvnic_tx_scrq_clean_buffer(adapter, adapter->tx_scrq[i]); + rc = reset_one_tx_pool(adapter, &adapter->tso_pool[i]); if (rc) return rc; - rc = reset_one_tx_pool(&adapter->tx_pool[i]); + rc = reset_one_tx_pool(adapter, &adapter->tx_pool[i]); if (rc) return rc; } @@ -734,8 +801,11 @@ static int init_tx_pools(struct net_device *netdev) adapter->tso_pool = kcalloc(tx_subcrqs, sizeof(struct ibmvnic_tx_pool), GFP_KERNEL); - if (!adapter->tso_pool) + if (!adapter->tso_pool) { + kfree(adapter->tx_pool); + adapter->tx_pool = NULL; return -1; + } adapter->num_active_tx_pools = tx_subcrqs; @@ -846,9 +916,10 @@ static const char *adapter_state_to_string(enum vnic_state state) return "REMOVING"; case VNIC_REMOVED: return "REMOVED"; - default: - return "UNKNOWN"; + case VNIC_DOWN: + return "DOWN"; } + return "UNKNOWN"; } static int ibmvnic_login(struct net_device *netdev) @@ -1180,6 +1251,11 @@ static int __ibmvnic_open(struct net_device *netdev) netif_tx_start_all_queues(netdev); + if (prev_state == VNIC_CLOSED) { + for (i = 0; i < adapter->req_rx_queues; i++) + napi_schedule(&adapter->napi[i]); + } + adapter->state = VNIC_OPEN; return rc; } @@ -1502,7 +1578,8 @@ static int create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len, /** * build_hdr_descs_arr - build a header descriptor array - * @txbuff: tx buffer + * @skb: tx socket buffer + * @indir_arr: indirect array * @num_entries: number of descriptors to be sent * @hdr_field: bit field determining which headers will be sent * @@ -1583,7 +1660,8 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter, ind_bufp->index = 0; if (atomic_sub_return(entries, &tx_scrq->used) <= (adapter->req_tx_entries_per_subcrq / 2) && - __netif_subqueue_stopped(adapter->netdev, queue_num)) { + __netif_subqueue_stopped(adapter->netdev, queue_num) && + !test_bit(0, &adapter->resetting)) { netif_wake_subqueue(adapter->netdev, queue_num); netdev_dbg(adapter->netdev, "Started queue %d\n", queue_num); @@ -1676,7 +1754,6 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_send_failed++; tx_dropped++; ret = NETDEV_TX_OK; - ibmvnic_tx_scrq_flush(adapter, tx_scrq); goto out; } @@ -1946,9 +2023,10 @@ static const char *reset_reason_to_string(enum ibmvnic_reset_reason reason) return "TIMEOUT"; case VNIC_RESET_CHANGE_PARAM: return "CHANGE_PARAM"; - default: - return "UNKNOWN"; + case VNIC_RESET_PASSIVE_INIT: + return "PASSIVE_INIT"; } + return "UNKNOWN"; } /* @@ -2085,10 +2163,10 @@ static int do_reset(struct ibmvnic_adapter *adapter, goto out; } - /* If the adapter was in PROBE state prior to the reset, + /* If the adapter was in PROBE or DOWN state prior to the reset, * exit here. */ - if (reset_state == VNIC_PROBED) { + if (reset_state == VNIC_PROBED || reset_state == VNIC_DOWN) { rc = 0; goto out; } @@ -2214,10 +2292,10 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter, if (rc) goto out; - /* If the adapter was in PROBE state prior to the reset, + /* If the adapter was in PROBE or DOWN state prior to the reset, * exit here. */ - if (reset_state == VNIC_PROBED) + if (reset_state == VNIC_PROBED || reset_state == VNIC_DOWN) goto out; rc = ibmvnic_login(netdev); @@ -2270,6 +2348,76 @@ static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter) return rwi; } +/** + * do_passive_init - complete probing when partner device is detected. + * @adapter: ibmvnic_adapter struct + * + * If the ibmvnic device does not have a partner device to communicate with at boot + * and that partner device comes online at a later time, this function is called + * to complete the initialization process of ibmvnic device. + * Caller is expected to hold rtnl_lock(). + * + * Returns non-zero if sub-CRQs are not initialized properly leaving the device + * in the down state. + * Returns 0 upon success and the device is in PROBED state. + */ + +static int do_passive_init(struct ibmvnic_adapter *adapter) +{ + unsigned long timeout = msecs_to_jiffies(30000); + struct net_device *netdev = adapter->netdev; + struct device *dev = &adapter->vdev->dev; + int rc; + + netdev_dbg(netdev, "Partner device found, probing.\n"); + + adapter->state = VNIC_PROBING; + reinit_completion(&adapter->init_done); + adapter->init_done_rc = 0; + adapter->crq.active = true; + + rc = send_crq_init_complete(adapter); + if (rc) + goto out; + + rc = send_version_xchg(adapter); + if (rc) + netdev_dbg(adapter->netdev, "send_version_xchg failed, rc=%d\n", rc); + + if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { + dev_err(dev, "Initialization sequence timed out\n"); + rc = -ETIMEDOUT; + goto out; + } + + rc = init_sub_crqs(adapter); + if (rc) { + dev_err(dev, "Initialization of sub crqs failed, rc=%d\n", rc); + goto out; + } + + rc = init_sub_crq_irqs(adapter); + if (rc) { + dev_err(dev, "Failed to initialize sub crq irqs\n, rc=%d", rc); + goto init_failed; + } + + netdev->mtu = adapter->req_mtu - ETH_HLEN; + netdev->min_mtu = adapter->min_mtu - ETH_HLEN; + netdev->max_mtu = adapter->max_mtu - ETH_HLEN; + + adapter->state = VNIC_PROBED; + netdev_dbg(netdev, "Probed successfully. Waiting for signal from partner device.\n"); + + return 0; + +init_failed: + release_sub_crqs(adapter, 1); +out: + adapter->state = VNIC_DOWN; + return rc; +} + static void __ibmvnic_reset(struct work_struct *work) { struct ibmvnic_rwi *rwi; @@ -2306,7 +2454,13 @@ static void __ibmvnic_reset(struct work_struct *work) } spin_unlock_irqrestore(&adapter->state_lock, flags); - if (adapter->force_reset_recovery) { + if (rwi->reset_reason == VNIC_RESET_PASSIVE_INIT) { + rtnl_lock(); + rc = do_passive_init(adapter); + rtnl_unlock(); + if (!rc) + netif_carrier_on(adapter->netdev); + } else if (adapter->force_reset_recovery) { /* Since we are doing a hard reset now, clear the * failover_pending flag so we don't ignore any * future MOBILITY or other resets. @@ -2402,8 +2556,7 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter, goto err; } - list_for_each(entry, &adapter->rwi_list) { - tmp = list_entry(entry, struct ibmvnic_rwi, list); + list_for_each_entry(tmp, &adapter->rwi_list, list) { if (tmp->reset_reason == reason) { netdev_dbg(netdev, "Skipping matching reset, reason=%s\n", reset_reason_to_string(reason)); @@ -3140,6 +3293,7 @@ static void release_sub_crqs(struct ibmvnic_adapter *adapter, bool do_h_free) netdev_dbg(adapter->netdev, "Releasing tx_scrq[%d]\n", i); + ibmvnic_tx_scrq_clean_buffer(adapter, adapter->tx_scrq[i]); if (adapter->tx_scrq[i]->irq) { free_irq(adapter->tx_scrq[i]->irq, adapter->tx_scrq[i]); @@ -3213,7 +3367,7 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter, /* H_EOI would fail with rc = H_FUNCTION when running * in XIVE mode which is expected, but not an error. */ - if (rc && rc != H_FUNCTION) + if (rc && (rc != H_FUNCTION)) dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n", val, rc); } @@ -3776,18 +3930,6 @@ static int ibmvnic_send_crq_init(struct ibmvnic_adapter *adapter) return 0; } -static int send_version_xchg(struct ibmvnic_adapter *adapter) -{ - union ibmvnic_crq crq; - - memset(&crq, 0, sizeof(crq)); - crq.version_exchange.first = IBMVNIC_CRQ_CMD; - crq.version_exchange.cmd = VERSION_EXCHANGE; - crq.version_exchange.version = cpu_to_be16(ibmvnic_version); - - return ibmvnic_send_crq(adapter, &crq); -} - struct vnic_login_client_data { u8 type; __be16 len; @@ -3820,21 +3962,21 @@ static void vnic_add_client_data(struct ibmvnic_adapter *adapter, vlcd->type = 1; len = strlen(os_name) + 1; vlcd->len = cpu_to_be16(len); - strncpy(vlcd->name, os_name, len); + strscpy(vlcd->name, os_name, len); vlcd = (struct vnic_login_client_data *)(vlcd->name + len); /* Type 2 - LPAR name */ vlcd->type = 2; len = strlen(utsname()->nodename) + 1; vlcd->len = cpu_to_be16(len); - strncpy(vlcd->name, utsname()->nodename, len); + strscpy(vlcd->name, utsname()->nodename, len); vlcd = (struct vnic_login_client_data *)(vlcd->name + len); /* Type 3 - device name */ vlcd->type = 3; len = strlen(adapter->netdev->name) + 1; vlcd->len = cpu_to_be16(len); - strncpy(vlcd->name, adapter->netdev->name, len); + strscpy(vlcd->name, adapter->netdev->name, len); } static int send_login(struct ibmvnic_adapter *adapter) @@ -4301,7 +4443,7 @@ static void handle_vpd_rsp(union ibmvnic_crq *crq, complete: if (adapter->fw_version[0] == '\0') - strncpy((char *)adapter->fw_version, "N/A", 3 * sizeof(char)); + strscpy((char *)adapter->fw_version, "N/A", sizeof(adapter->fw_version)); complete(&adapter->fw_done); } @@ -4907,7 +5049,12 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, complete(&adapter->init_done); adapter->init_done_rc = -EIO; } - rc = ibmvnic_reset(adapter, VNIC_RESET_FAILOVER); + + if (adapter->state == VNIC_DOWN) + rc = ibmvnic_reset(adapter, VNIC_RESET_PASSIVE_INIT); + else + rc = ibmvnic_reset(adapter, VNIC_RESET_FAILOVER); + if (rc && rc != -EBUSY) { /* We were unable to schedule the failover * reset either because the adapter was still @@ -5330,6 +5477,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) struct ibmvnic_adapter *adapter; struct net_device *netdev; unsigned char *mac_addr_p; + bool init_success; int rc; dev_dbg(&dev->dev, "entering ibmvnic_probe for UA 0x%x\n", @@ -5376,6 +5524,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) init_completion(&adapter->stats_done); clear_bit(0, &adapter->resetting); + init_success = false; do { rc = init_crq_queue(adapter); if (rc) { @@ -5385,10 +5534,16 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) } rc = ibmvnic_reset_init(adapter, false); - if (rc && rc != EAGAIN) - goto ibmvnic_init_fail; } while (rc == EAGAIN); + /* We are ignoring the error from ibmvnic_reset_init() assuming that the + * partner is not ready. CRQ is not active. When the partner becomes + * ready, we will do the passive init reset. + */ + + if (!rc) + init_success = true; + rc = init_stats_buffers(adapter); if (rc) goto ibmvnic_init_fail; @@ -5397,10 +5552,6 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) if (rc) goto ibmvnic_stats_fail; - netdev->mtu = adapter->req_mtu - ETH_HLEN; - netdev->min_mtu = adapter->min_mtu - ETH_HLEN; - netdev->max_mtu = adapter->max_mtu - ETH_HLEN; - rc = device_create_file(&dev->dev, &dev_attr_failover); if (rc) goto ibmvnic_dev_file_err; @@ -5413,7 +5564,14 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) } dev_info(&dev->dev, "ibmvnic registered\n"); - adapter->state = VNIC_PROBED; + if (init_success) { + adapter->state = VNIC_PROBED; + netdev->mtu = adapter->req_mtu - ETH_HLEN; + netdev->min_mtu = adapter->min_mtu - ETH_HLEN; + netdev->max_mtu = adapter->max_mtu - ETH_HLEN; + } else { + adapter->state = VNIC_DOWN; + } adapter->wait_for_reset = false; adapter->last_reset_time = jiffies; diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index c1d39a748546..22df602323bc 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -851,14 +851,16 @@ enum vnic_state {VNIC_PROBING = 1, VNIC_CLOSING, VNIC_CLOSED, VNIC_REMOVING, - VNIC_REMOVED}; + VNIC_REMOVED, + VNIC_DOWN}; enum ibmvnic_reset_reason {VNIC_RESET_FAILOVER = 1, VNIC_RESET_MOBILITY, VNIC_RESET_FATAL, VNIC_RESET_NON_FATAL, VNIC_RESET_TIMEOUT, - VNIC_RESET_CHANGE_PARAM}; + VNIC_RESET_CHANGE_PARAM, + VNIC_RESET_PASSIVE_INIT}; struct ibmvnic_rwi { enum ibmvnic_reset_reason reset_reason; diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index c1d155690341..82744a7501c7 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -241,6 +241,7 @@ config I40E tristate "Intel(R) Ethernet Controller XL710 Family support" imply PTP_1588_CLOCK depends on PCI + select AUXILIARY_BUS help This driver supports Intel(R) Ethernet Controller XL710 Family of devices. For more information on how to identify your adapter, go @@ -294,9 +295,11 @@ config ICE tristate "Intel(R) Ethernet Connection E800 Series Support" default n depends on PCI_MSI + select AUXILIARY_BUS select DIMLIB select NET_DEVLINK select PLDMFW + imply PTP_1588_CLOCK help This driver supports Intel(R) Ethernet Connection E800 Series of devices. For more information on how to identify your adapter, go diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index f8d78af76d7d..1b0958bd24f6 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -1395,7 +1395,7 @@ static int e100_phy_check_without_mii(struct nic *nic) u8 phy_type; int without_mii; - phy_type = (nic->eeprom[eeprom_phy_iface] >> 8) & 0x0f; + phy_type = (le16_to_cpu(nic->eeprom[eeprom_phy_iface]) >> 8) & 0x0f; switch (phy_type) { case NoSuchPhy: /* Non-MII PHY; UNTESTED! */ @@ -1515,7 +1515,7 @@ static int e100_phy_init(struct nic *nic) mdio_write(netdev, nic->mii.phy_id, MII_BMCR, bmcr); } else if ((nic->mac >= mac_82550_D102) || ((nic->flags & ich) && (mdio_read(netdev, nic->mii.phy_id, MII_TPISTATUS) & 0x8000) && - (nic->eeprom[eeprom_cnfg_mdix] & eeprom_mdix_enabled))) { + (le16_to_cpu(nic->eeprom[eeprom_cnfg_mdix]) & eeprom_mdix_enabled))) { /* enable/disable MDI/MDI-X auto-switching. */ mdio_write(netdev, nic->mii.phy_id, MII_NCONFIG, nic->mii.force_media ? 0 : NCONFIG_AUTO_SWITCH); @@ -2269,9 +2269,9 @@ static int e100_asf(struct nic *nic) { /* ASF can be enabled from eeprom */ return (nic->pdev->device >= 0x1050) && (nic->pdev->device <= 0x1057) && - (nic->eeprom[eeprom_config_asf] & eeprom_asf) && - !(nic->eeprom[eeprom_config_asf] & eeprom_gcl) && - ((nic->eeprom[eeprom_smbus_addr] & 0xFF) != 0xFE); + (le16_to_cpu(nic->eeprom[eeprom_config_asf]) & eeprom_asf) && + !(le16_to_cpu(nic->eeprom[eeprom_config_asf]) & eeprom_gcl) && + ((le16_to_cpu(nic->eeprom[eeprom_smbus_addr]) & 0xFF) != 0xFE); } static int e100_up(struct nic *nic) @@ -2926,7 +2926,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Wol magic packet can be enabled from eeprom */ if ((nic->mac >= mac_82558_D101_A4) && - (nic->eeprom[eeprom_id] & eeprom_id_wol)) { + (le16_to_cpu(nic->eeprom[eeprom_id]) & eeprom_id_wol)) { nic->flags |= wol_magic; device_set_wakeup_enable(&pdev->dev, true); } diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index f976e9daa3d8..3c51ee94fa00 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -513,7 +513,7 @@ static int e1000_set_eeprom(struct net_device *netdev, memcpy(ptr, bytes, eeprom->len); for (i = 0; i < last_word - first_word + 1; i++) - eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]); + cpu_to_le16s(&eeprom_buff[i]); ret_val = e1000_write_eeprom(hw, first_word, last_word - first_word + 1, eeprom_buff); diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c index 19cf36360933..1042e79a1397 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_hw.c +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c @@ -2522,7 +2522,7 @@ s32 e1000_check_for_link(struct e1000_hw *hw) * turn it on. For compatibility with a TBI link * partner, we will store bad packets. Some * frames have an additional byte on the end and - * will look like CRC errors to to the hardware. + * will look like CRC errors to the hardware. */ if (!hw->tbi_compatibility_on) { hw->tbi_compatibility_on = true; @@ -2723,7 +2723,7 @@ static void e1000_shift_out_mdi_bits(struct e1000_hw *hw, u32 data, u16 count) * e1000_shift_in_mdi_bits - Shifts data bits in from the PHY * @hw: Struct containing variables accessed by shared code * - * Bits are shifted in in MSB to LSB order. + * Bits are shifted in MSB to LSB order. */ static u16 e1000_shift_in_mdi_bits(struct e1000_hw *hw) { diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 042de276e632..c2a109126c27 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -5245,7 +5245,7 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, if (!test_and_set_bit(__E1000_DISABLED, &adapter->flags)) pci_disable_device(pdev); - /* Request a slot slot reset. */ + /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; } diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 590ad110d383..cf7b3887da1d 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -4639,7 +4639,7 @@ static s32 e1000_id_led_init_pchlan(struct e1000_hw *hw) * @hw: pointer to the HW structure * * ICH8 use the PCI Express bus, but does not contain a PCI Express Capability - * register, so the the bus width is hard coded. + * register, so the bus width is hard coded. **/ static s32 e1000_get_bus_info_ich8lan(struct e1000_hw *hw) { diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 88e9035b75cf..d150dade06cf 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5223,18 +5223,20 @@ static void e1000_watchdog_task(struct work_struct *work) pm_runtime_resume(netdev->dev.parent); /* Checking if MAC is in DMoff state*/ - pcim_state = er32(STATUS); - while (pcim_state & E1000_STATUS_PCIM_STATE) { - if (tries++ == dmoff_exit_timeout) { - e_dbg("Error in exiting dmoff\n"); - break; - } - usleep_range(10000, 20000); + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) { pcim_state = er32(STATUS); + while (pcim_state & E1000_STATUS_PCIM_STATE) { + if (tries++ == dmoff_exit_timeout) { + e_dbg("Error in exiting dmoff\n"); + break; + } + usleep_range(10000, 20000); + pcim_state = er32(STATUS); - /* Checking if MAC exited DMoff state */ - if (!(pcim_state & E1000_STATUS_PCIM_STATE)) - e1000_phy_hw_reset(&adapter->hw); + /* Checking if MAC exited DMoff state */ + if (!(pcim_state & E1000_STATUS_PCIM_STATE)) + e1000_phy_hw_reset(&adapter->hw); + } } /* update snapshot of PHY registers on LSC */ @@ -7118,7 +7120,7 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, pci_disable_device(pdev); - /* Request a slot slot reset. */ + /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; } diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index 1db35b2c7750..0f0efee5fc8e 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -2978,7 +2978,7 @@ static u32 e1000_get_phy_addr_for_hv_page(u32 page) * @data: pointer to the data to be read or written * @read: determines if operation is read or write * - * Reads the PHY register at offset and stores the retreived information + * Reads the PHY register at offset and stores the retrieved information * in data. Assumes semaphore already acquired. Note that the procedure * to access these regs uses the address port and data port to read/write. * These accesses done with PHY address 2 and without using pages. diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 9e3103fae723..dbcae92bb18d 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1370,7 +1370,6 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data) struct fm10k_hw *hw = &interface->hw; struct fm10k_mbx_info *mbx = &hw->mbx; u32 eicr; - s32 err = 0; /* unmask any set bits related to this interrupt */ eicr = fm10k_read_reg(hw, FM10K_EICR); @@ -1386,15 +1385,16 @@ static irqreturn_t fm10k_msix_mbx_pf(int __always_unused irq, void *data) /* service mailboxes */ if (fm10k_mbx_trylock(interface)) { - err = mbx->ops.process(hw, mbx); + s32 err = mbx->ops.process(hw, mbx); + + if (err == FM10K_ERR_RESET_REQUESTED) + set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); + /* handle VFLRE events */ fm10k_iov_event(interface); fm10k_mbx_unlock(interface); } - if (err == FM10K_ERR_RESET_REQUESTED) - set_bit(FM10K_FLAG_RESET_REQUESTED, interface->flags); - /* if switch toggled state we should reset GLORTs */ if (eicr & FM10K_EICR_SWITCHNOTREADY) { /* force link down for at least 4 seconds */ diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 85d3dd3a3339..b9417dc0007c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -870,6 +870,8 @@ struct i40e_netdev_priv { struct i40e_vsi *vsi; }; +extern struct ida i40e_client_ida; + /* struct that defines an interrupt vector */ struct i40e_q_vector { struct i40e_vsi *vsi; diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index 32f3facbed1a..e07ed065d3a4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -12,6 +12,7 @@ static const char i40e_client_interface_version_str[] = I40E_CLIENT_VERSION_STR; static struct i40e_client *registered_client; static LIST_HEAD(i40e_devices); static DEFINE_MUTEX(i40e_device_mutex); +DEFINE_IDA(i40e_client_ida); static int i40e_client_virtchnl_send(struct i40e_info *ldev, struct i40e_client *client, @@ -275,6 +276,57 @@ void i40e_client_update_msix_info(struct i40e_pf *pf) cdev->lan_info.msix_entries = &pf->msix_entries[pf->iwarp_base_vector]; } +static void i40e_auxiliary_dev_release(struct device *dev) +{ + struct i40e_auxiliary_device *i40e_aux_dev = + container_of(dev, struct i40e_auxiliary_device, aux_dev.dev); + + ida_free(&i40e_client_ida, i40e_aux_dev->aux_dev.id); + kfree(i40e_aux_dev); +} + +static int i40e_register_auxiliary_dev(struct i40e_info *ldev, const char *name) +{ + struct i40e_auxiliary_device *i40e_aux_dev; + struct pci_dev *pdev = ldev->pcidev; + struct auxiliary_device *aux_dev; + int ret; + + i40e_aux_dev = kzalloc(sizeof(*i40e_aux_dev), GFP_KERNEL); + if (!i40e_aux_dev) + return -ENOMEM; + + i40e_aux_dev->ldev = ldev; + + aux_dev = &i40e_aux_dev->aux_dev; + aux_dev->name = name; + aux_dev->dev.parent = &pdev->dev; + aux_dev->dev.release = i40e_auxiliary_dev_release; + ldev->aux_dev = aux_dev; + + ret = ida_alloc(&i40e_client_ida, GFP_KERNEL); + if (ret < 0) { + kfree(i40e_aux_dev); + return ret; + } + aux_dev->id = ret; + + ret = auxiliary_device_init(aux_dev); + if (ret < 0) { + ida_free(&i40e_client_ida, aux_dev->id); + kfree(i40e_aux_dev); + return ret; + } + + ret = auxiliary_device_add(aux_dev); + if (ret) { + auxiliary_device_uninit(aux_dev); + return ret; + } + + return ret; +} + /** * i40e_client_add_instance - add a client instance struct to the instance list * @pf: pointer to the board struct @@ -286,9 +338,6 @@ static void i40e_client_add_instance(struct i40e_pf *pf) struct netdev_hw_addr *mac = NULL; struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; - if (!registered_client || pf->cinst) - return; - cdev = kzalloc(sizeof(*cdev), GFP_KERNEL); if (!cdev) return; @@ -308,11 +357,8 @@ static void i40e_client_add_instance(struct i40e_pf *pf) cdev->lan_info.fw_build = pf->hw.aq.fw_build; set_bit(__I40E_CLIENT_INSTANCE_NONE, &cdev->state); - if (i40e_client_get_params(vsi, &cdev->lan_info.params)) { - kfree(cdev); - cdev = NULL; - return; - } + if (i40e_client_get_params(vsi, &cdev->lan_info.params)) + goto free_cdev; mac = list_first_entry(&cdev->lan_info.netdev->dev_addrs.list, struct netdev_hw_addr, list); @@ -324,7 +370,17 @@ static void i40e_client_add_instance(struct i40e_pf *pf) cdev->client = registered_client; pf->cinst = cdev; - i40e_client_update_msix_info(pf); + cdev->lan_info.msix_count = pf->num_iwarp_msix; + cdev->lan_info.msix_entries = &pf->msix_entries[pf->iwarp_base_vector]; + + if (i40e_register_auxiliary_dev(&cdev->lan_info, "iwarp")) + goto free_cdev; + + return; + +free_cdev: + kfree(cdev); + pf->cinst = NULL; } /** @@ -345,7 +401,7 @@ void i40e_client_del_instance(struct i40e_pf *pf) **/ void i40e_client_subtask(struct i40e_pf *pf) { - struct i40e_client *client = registered_client; + struct i40e_client *client; struct i40e_client_instance *cdev; struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; int ret = 0; @@ -359,9 +415,11 @@ void i40e_client_subtask(struct i40e_pf *pf) test_bit(__I40E_CONFIG_BUSY, pf->state)) return; - if (!client || !cdev) + if (!cdev || !cdev->client) return; + client = cdev->client; + /* Here we handle client opens. If the client is down, and * the netdev is registered, then open the client. */ @@ -423,16 +481,8 @@ int i40e_lan_add_device(struct i40e_pf *pf) pf->hw.pf_id, pf->hw.bus.bus_id, pf->hw.bus.device, pf->hw.bus.func); - /* If a client has already been registered, we need to add an instance - * of it to our new LAN device. - */ - if (registered_client) - i40e_client_add_instance(pf); + i40e_client_add_instance(pf); - /* Since in some cases register may have happened before a device gets - * added, we can schedule a subtask to go initiate the clients if - * they can be launched at probe time. - */ set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state); i40e_service_event_schedule(pf); @@ -449,9 +499,13 @@ out: **/ int i40e_lan_del_device(struct i40e_pf *pf) { + struct auxiliary_device *aux_dev = pf->cinst->lan_info.aux_dev; struct i40e_device *ldev, *tmp; int ret = -ENODEV; + auxiliary_device_delete(aux_dev); + auxiliary_device_uninit(aux_dev); + /* First, remove any client instance. */ i40e_client_del_instance(pf); @@ -579,7 +633,7 @@ static int i40e_client_setup_qvlist(struct i40e_info *ldev, u32 v_idx, i, reg_idx, reg; ldev->qvlist_info = kzalloc(struct_size(ldev->qvlist_info, qv_info, - qvlist_info->num_vectors - 1), GFP_KERNEL); + qvlist_info->num_vectors), GFP_KERNEL); if (!ldev->qvlist_info) return -ENOMEM; ldev->qvlist_info->num_vectors = qvlist_info->num_vectors; @@ -732,6 +786,42 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, return err; } +void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client) +{ + struct i40e_pf *pf = ldev->pf; + + pf->cinst->client = client; + set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state); + i40e_service_event_schedule(pf); +} +EXPORT_SYMBOL_GPL(i40e_client_device_register); + +void i40e_client_device_unregister(struct i40e_info *ldev) +{ + struct i40e_pf *pf = ldev->pf; + struct i40e_client_instance *cdev = pf->cinst; + + if (!cdev) + return; + + while (test_and_set_bit(__I40E_SERVICE_SCHED, pf->state)) + usleep_range(500, 1000); + + if (test_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state)) { + cdev->client->ops->close(&cdev->lan_info, cdev->client, false); + clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cdev->state); + i40e_client_release_qvlist(&cdev->lan_info); + } + + pf->cinst->client = NULL; + clear_bit(__I40E_SERVICE_SCHED, pf->state); +} +EXPORT_SYMBOL_GPL(i40e_client_device_unregister); + +/* Retain these legacy global registration/unregistration calls till i40iw is + * removed from the kernel. The irdma unified driver does not use these + * exported symbols. + */ /** * i40e_register_client - Register a i40e client driver with the L2 driver * @client: pointer to the i40e_client struct diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 67cb0b47416a..b4d3fed0d2f2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -552,9 +552,9 @@ i40e_status i40e_aq_set_rss_key(struct i40e_hw *hw, * ENDIF */ -/* macro to make the table lines short */ +/* macro to make the table lines short, use explicit indexing with [PTYPE] */ #define I40E_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ - { PTYPE, \ + [PTYPE] = { \ 1, \ I40E_RX_PTYPE_OUTER_##OUTER_IP, \ I40E_RX_PTYPE_OUTER_##OUTER_IP_VER, \ @@ -565,16 +565,15 @@ i40e_status i40e_aq_set_rss_key(struct i40e_hw *hw, I40E_RX_PTYPE_INNER_PROT_##I, \ I40E_RX_PTYPE_PAYLOAD_LAYER_##PL } -#define I40E_PTT_UNUSED_ENTRY(PTYPE) \ - { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 } +#define I40E_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } /* shorter macros makes the table fit but are terse */ #define I40E_RX_PTYPE_NOF I40E_RX_PTYPE_NOT_FRAG #define I40E_RX_PTYPE_FRG I40E_RX_PTYPE_FRAG #define I40E_RX_PTYPE_INNER_PROT_TS I40E_RX_PTYPE_INNER_PROT_TIMESYNC -/* Lookup table mapping the HW PTYPE to the bit field for decoding */ -struct i40e_rx_ptype_decoded i40e_ptype_lookup[] = { +/* Lookup table mapping in the 8-bit HW PTYPE to the bit field for decoding */ +struct i40e_rx_ptype_decoded i40e_ptype_lookup[BIT(8)] = { /* L2 Packet types */ I40E_PTT_UNUSED_ENTRY(0), I40E_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), @@ -780,118 +779,7 @@ struct i40e_rx_ptype_decoded i40e_ptype_lookup[] = { I40E_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), /* unused entries */ - I40E_PTT_UNUSED_ENTRY(154), - I40E_PTT_UNUSED_ENTRY(155), - I40E_PTT_UNUSED_ENTRY(156), - I40E_PTT_UNUSED_ENTRY(157), - I40E_PTT_UNUSED_ENTRY(158), - I40E_PTT_UNUSED_ENTRY(159), - - I40E_PTT_UNUSED_ENTRY(160), - I40E_PTT_UNUSED_ENTRY(161), - I40E_PTT_UNUSED_ENTRY(162), - I40E_PTT_UNUSED_ENTRY(163), - I40E_PTT_UNUSED_ENTRY(164), - I40E_PTT_UNUSED_ENTRY(165), - I40E_PTT_UNUSED_ENTRY(166), - I40E_PTT_UNUSED_ENTRY(167), - I40E_PTT_UNUSED_ENTRY(168), - I40E_PTT_UNUSED_ENTRY(169), - - I40E_PTT_UNUSED_ENTRY(170), - I40E_PTT_UNUSED_ENTRY(171), - I40E_PTT_UNUSED_ENTRY(172), - I40E_PTT_UNUSED_ENTRY(173), - I40E_PTT_UNUSED_ENTRY(174), - I40E_PTT_UNUSED_ENTRY(175), - I40E_PTT_UNUSED_ENTRY(176), - I40E_PTT_UNUSED_ENTRY(177), - I40E_PTT_UNUSED_ENTRY(178), - I40E_PTT_UNUSED_ENTRY(179), - - I40E_PTT_UNUSED_ENTRY(180), - I40E_PTT_UNUSED_ENTRY(181), - I40E_PTT_UNUSED_ENTRY(182), - I40E_PTT_UNUSED_ENTRY(183), - I40E_PTT_UNUSED_ENTRY(184), - I40E_PTT_UNUSED_ENTRY(185), - I40E_PTT_UNUSED_ENTRY(186), - I40E_PTT_UNUSED_ENTRY(187), - I40E_PTT_UNUSED_ENTRY(188), - I40E_PTT_UNUSED_ENTRY(189), - - I40E_PTT_UNUSED_ENTRY(190), - I40E_PTT_UNUSED_ENTRY(191), - I40E_PTT_UNUSED_ENTRY(192), - I40E_PTT_UNUSED_ENTRY(193), - I40E_PTT_UNUSED_ENTRY(194), - I40E_PTT_UNUSED_ENTRY(195), - I40E_PTT_UNUSED_ENTRY(196), - I40E_PTT_UNUSED_ENTRY(197), - I40E_PTT_UNUSED_ENTRY(198), - I40E_PTT_UNUSED_ENTRY(199), - - I40E_PTT_UNUSED_ENTRY(200), - I40E_PTT_UNUSED_ENTRY(201), - I40E_PTT_UNUSED_ENTRY(202), - I40E_PTT_UNUSED_ENTRY(203), - I40E_PTT_UNUSED_ENTRY(204), - I40E_PTT_UNUSED_ENTRY(205), - I40E_PTT_UNUSED_ENTRY(206), - I40E_PTT_UNUSED_ENTRY(207), - I40E_PTT_UNUSED_ENTRY(208), - I40E_PTT_UNUSED_ENTRY(209), - - I40E_PTT_UNUSED_ENTRY(210), - I40E_PTT_UNUSED_ENTRY(211), - I40E_PTT_UNUSED_ENTRY(212), - I40E_PTT_UNUSED_ENTRY(213), - I40E_PTT_UNUSED_ENTRY(214), - I40E_PTT_UNUSED_ENTRY(215), - I40E_PTT_UNUSED_ENTRY(216), - I40E_PTT_UNUSED_ENTRY(217), - I40E_PTT_UNUSED_ENTRY(218), - I40E_PTT_UNUSED_ENTRY(219), - - I40E_PTT_UNUSED_ENTRY(220), - I40E_PTT_UNUSED_ENTRY(221), - I40E_PTT_UNUSED_ENTRY(222), - I40E_PTT_UNUSED_ENTRY(223), - I40E_PTT_UNUSED_ENTRY(224), - I40E_PTT_UNUSED_ENTRY(225), - I40E_PTT_UNUSED_ENTRY(226), - I40E_PTT_UNUSED_ENTRY(227), - I40E_PTT_UNUSED_ENTRY(228), - I40E_PTT_UNUSED_ENTRY(229), - - I40E_PTT_UNUSED_ENTRY(230), - I40E_PTT_UNUSED_ENTRY(231), - I40E_PTT_UNUSED_ENTRY(232), - I40E_PTT_UNUSED_ENTRY(233), - I40E_PTT_UNUSED_ENTRY(234), - I40E_PTT_UNUSED_ENTRY(235), - I40E_PTT_UNUSED_ENTRY(236), - I40E_PTT_UNUSED_ENTRY(237), - I40E_PTT_UNUSED_ENTRY(238), - I40E_PTT_UNUSED_ENTRY(239), - - I40E_PTT_UNUSED_ENTRY(240), - I40E_PTT_UNUSED_ENTRY(241), - I40E_PTT_UNUSED_ENTRY(242), - I40E_PTT_UNUSED_ENTRY(243), - I40E_PTT_UNUSED_ENTRY(244), - I40E_PTT_UNUSED_ENTRY(245), - I40E_PTT_UNUSED_ENTRY(246), - I40E_PTT_UNUSED_ENTRY(247), - I40E_PTT_UNUSED_ENTRY(248), - I40E_PTT_UNUSED_ENTRY(249), - - I40E_PTT_UNUSED_ENTRY(250), - I40E_PTT_UNUSED_ENTRY(251), - I40E_PTT_UNUSED_ENTRY(252), - I40E_PTT_UNUSED_ENTRY(253), - I40E_PTT_UNUSED_ENTRY(254), - I40E_PTT_UNUSED_ENTRY(255) + [154 ... 255] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } }; /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index ccd5b9486ea9..3e822bad4851 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1262,8 +1262,7 @@ static int i40e_set_link_ksettings(struct net_device *netdev, if (ethtool_link_ksettings_test_link_mode(&safe_ks, supported, Autoneg) && - hw->phy.link_info.phy_type != - I40E_PHY_TYPE_10GBASE_T) { + hw->phy.media_type != I40E_MEDIA_TYPE_BASET) { netdev_info(netdev, "Autoneg cannot be disabled on this phy\n"); err = -EINVAL; goto done; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 704e474879c5..861e59a350bd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -32,7 +32,7 @@ static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi); static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired); static int i40e_add_vsi(struct i40e_vsi *vsi); static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi); -static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit); +static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acquired); static int i40e_setup_misc_vector(struct i40e_pf *pf); static void i40e_determine_queue_usage(struct i40e_pf *pf); static int i40e_setup_pf_filter_control(struct i40e_pf *pf); @@ -8703,6 +8703,8 @@ int i40e_vsi_open(struct i40e_vsi *vsi) dev_driver_string(&pf->pdev->dev), dev_name(&pf->pdev->dev)); err = i40e_vsi_request_irq(vsi, int_name); + if (err) + goto err_setup_rx; } else { err = -EINVAL; @@ -10569,7 +10571,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) #endif /* CONFIG_I40E_DCB */ if (!lock_acquired) rtnl_lock(); - ret = i40e_setup_pf_switch(pf, reinit); + ret = i40e_setup_pf_switch(pf, reinit, true); if (ret) goto end_unlock; @@ -14627,10 +14629,11 @@ int i40e_fetch_switch_configuration(struct i40e_pf *pf, bool printconfig) * i40e_setup_pf_switch - Setup the HW switch on startup or after reset * @pf: board private structure * @reinit: if the Main VSI needs to re-initialized. + * @lock_acquired: indicates whether or not the lock has been acquired * * Returns 0 on success, negative value on failure **/ -static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) +static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acquired) { u16 flags = 0; int ret; @@ -14732,9 +14735,15 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit) i40e_ptp_init(pf); + if (!lock_acquired) + rtnl_lock(); + /* repopulate tunnel port filters */ udp_tunnel_nic_reset_ntf(pf->vsi[pf->lan_vsi]->netdev); + if (!lock_acquired) + rtnl_unlock(); + return ret; } @@ -15528,7 +15537,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; } #endif - err = i40e_setup_pf_switch(pf, false); + err = i40e_setup_pf_switch(pf, false, false); if (err) { dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err); goto err_vsis; @@ -16270,6 +16279,7 @@ static void __exit i40e_exit_module(void) { pci_unregister_driver(&i40e_driver); destroy_workqueue(i40e_wq); + ida_destroy(&i40e_client_ida); i40e_dbg_exit(); } module_exit(i40e_exit_module); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index f1f6fc3744e9..7b971b205d36 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -11,13 +11,14 @@ * operate with the nanosecond field directly without fear of overflow. * * Much like the 82599, the update period is dependent upon the link speed: - * At 40Gb link or no link, the period is 1.6ns. - * At 10Gb link, the period is multiplied by 2. (3.2ns) + * At 40Gb, 25Gb, or no link, the period is 1.6ns. + * At 10Gb or 5Gb link, the period is multiplied by 2. (3.2ns) * At 1Gb link, the period is multiplied by 20. (32ns) * 1588 functionality is not supported at 100Mbps. */ #define I40E_PTP_40GB_INCVAL 0x0199999999ULL #define I40E_PTP_10GB_INCVAL_MULT 2 +#define I40E_PTP_5GB_INCVAL_MULT 2 #define I40E_PTP_1GB_INCVAL_MULT 20 #define I40E_PRTTSYN_CTL1_TSYNTYPE_V1 BIT(I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT) @@ -465,6 +466,9 @@ void i40e_ptp_set_increment(struct i40e_pf *pf) case I40E_LINK_SPEED_10GB: mult = I40E_PTP_10GB_INCVAL_MULT; break; + case I40E_LINK_SPEED_5GB: + mult = I40E_PTP_5GB_INCVAL_MULT; + break; case I40E_LINK_SPEED_1GB: mult = I40E_PTP_1GB_INCVAL_MULT; break; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index b883ab809df3..38eb8151ee9a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2298,7 +2298,6 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp) struct bpf_prog *xdp_prog; u32 act; - rcu_read_lock(); xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (!xdp_prog) @@ -2334,7 +2333,6 @@ out_failure: break; } xdp_out: - rcu_read_unlock(); return result; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index c81109a63e90..36a4ca1ffb1a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -804,7 +804,6 @@ enum i40e_rx_l2_ptype { }; struct i40e_rx_ptype_decoded { - u32 ptype:8; u32 known:1; u32 outer_ip:1; u32 outer_ip_ver:1; diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 68f177a86403..e7e778ca074c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -153,7 +153,6 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) struct bpf_prog *xdp_prog; u32 act; - rcu_read_lock(); /* NB! xdp_prog will always be !NULL, due to the fact that * this path is enabled by setting an XDP program. */ @@ -164,7 +163,6 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); if (err) goto out_failure; - rcu_read_unlock(); return I40E_XDP_REDIR; } @@ -188,7 +186,6 @@ out_failure: result = I40E_XDP_CONSUMED; break; } - rcu_read_unlock(); return result; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c index 8547fc8fdfd6..e9cc7f6ddc46 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_common.c +++ b/drivers/net/ethernet/intel/iavf/iavf_common.c @@ -522,9 +522,9 @@ enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id, * ENDIF */ -/* macro to make the table lines short */ +/* macro to make the table lines short, use explicit indexing with [PTYPE] */ #define IAVF_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ - { PTYPE, \ + [PTYPE] = { \ 1, \ IAVF_RX_PTYPE_OUTER_##OUTER_IP, \ IAVF_RX_PTYPE_OUTER_##OUTER_IP_VER, \ @@ -535,16 +535,15 @@ enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id, IAVF_RX_PTYPE_INNER_PROT_##I, \ IAVF_RX_PTYPE_PAYLOAD_LAYER_##PL } -#define IAVF_PTT_UNUSED_ENTRY(PTYPE) \ - { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 } +#define IAVF_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } /* shorter macros makes the table fit but are terse */ #define IAVF_RX_PTYPE_NOF IAVF_RX_PTYPE_NOT_FRAG #define IAVF_RX_PTYPE_FRG IAVF_RX_PTYPE_FRAG #define IAVF_RX_PTYPE_INNER_PROT_TS IAVF_RX_PTYPE_INNER_PROT_TIMESYNC -/* Lookup table mapping the HW PTYPE to the bit field for decoding */ -struct iavf_rx_ptype_decoded iavf_ptype_lookup[] = { +/* Lookup table mapping the 8-bit HW PTYPE to the bit field for decoding */ +struct iavf_rx_ptype_decoded iavf_ptype_lookup[BIT(8)] = { /* L2 Packet types */ IAVF_PTT_UNUSED_ENTRY(0), IAVF_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), @@ -750,118 +749,7 @@ struct iavf_rx_ptype_decoded iavf_ptype_lookup[] = { IAVF_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), /* unused entries */ - IAVF_PTT_UNUSED_ENTRY(154), - IAVF_PTT_UNUSED_ENTRY(155), - IAVF_PTT_UNUSED_ENTRY(156), - IAVF_PTT_UNUSED_ENTRY(157), - IAVF_PTT_UNUSED_ENTRY(158), - IAVF_PTT_UNUSED_ENTRY(159), - - IAVF_PTT_UNUSED_ENTRY(160), - IAVF_PTT_UNUSED_ENTRY(161), - IAVF_PTT_UNUSED_ENTRY(162), - IAVF_PTT_UNUSED_ENTRY(163), - IAVF_PTT_UNUSED_ENTRY(164), - IAVF_PTT_UNUSED_ENTRY(165), - IAVF_PTT_UNUSED_ENTRY(166), - IAVF_PTT_UNUSED_ENTRY(167), - IAVF_PTT_UNUSED_ENTRY(168), - IAVF_PTT_UNUSED_ENTRY(169), - - IAVF_PTT_UNUSED_ENTRY(170), - IAVF_PTT_UNUSED_ENTRY(171), - IAVF_PTT_UNUSED_ENTRY(172), - IAVF_PTT_UNUSED_ENTRY(173), - IAVF_PTT_UNUSED_ENTRY(174), - IAVF_PTT_UNUSED_ENTRY(175), - IAVF_PTT_UNUSED_ENTRY(176), - IAVF_PTT_UNUSED_ENTRY(177), - IAVF_PTT_UNUSED_ENTRY(178), - IAVF_PTT_UNUSED_ENTRY(179), - - IAVF_PTT_UNUSED_ENTRY(180), - IAVF_PTT_UNUSED_ENTRY(181), - IAVF_PTT_UNUSED_ENTRY(182), - IAVF_PTT_UNUSED_ENTRY(183), - IAVF_PTT_UNUSED_ENTRY(184), - IAVF_PTT_UNUSED_ENTRY(185), - IAVF_PTT_UNUSED_ENTRY(186), - IAVF_PTT_UNUSED_ENTRY(187), - IAVF_PTT_UNUSED_ENTRY(188), - IAVF_PTT_UNUSED_ENTRY(189), - - IAVF_PTT_UNUSED_ENTRY(190), - IAVF_PTT_UNUSED_ENTRY(191), - IAVF_PTT_UNUSED_ENTRY(192), - IAVF_PTT_UNUSED_ENTRY(193), - IAVF_PTT_UNUSED_ENTRY(194), - IAVF_PTT_UNUSED_ENTRY(195), - IAVF_PTT_UNUSED_ENTRY(196), - IAVF_PTT_UNUSED_ENTRY(197), - IAVF_PTT_UNUSED_ENTRY(198), - IAVF_PTT_UNUSED_ENTRY(199), - - IAVF_PTT_UNUSED_ENTRY(200), - IAVF_PTT_UNUSED_ENTRY(201), - IAVF_PTT_UNUSED_ENTRY(202), - IAVF_PTT_UNUSED_ENTRY(203), - IAVF_PTT_UNUSED_ENTRY(204), - IAVF_PTT_UNUSED_ENTRY(205), - IAVF_PTT_UNUSED_ENTRY(206), - IAVF_PTT_UNUSED_ENTRY(207), - IAVF_PTT_UNUSED_ENTRY(208), - IAVF_PTT_UNUSED_ENTRY(209), - - IAVF_PTT_UNUSED_ENTRY(210), - IAVF_PTT_UNUSED_ENTRY(211), - IAVF_PTT_UNUSED_ENTRY(212), - IAVF_PTT_UNUSED_ENTRY(213), - IAVF_PTT_UNUSED_ENTRY(214), - IAVF_PTT_UNUSED_ENTRY(215), - IAVF_PTT_UNUSED_ENTRY(216), - IAVF_PTT_UNUSED_ENTRY(217), - IAVF_PTT_UNUSED_ENTRY(218), - IAVF_PTT_UNUSED_ENTRY(219), - - IAVF_PTT_UNUSED_ENTRY(220), - IAVF_PTT_UNUSED_ENTRY(221), - IAVF_PTT_UNUSED_ENTRY(222), - IAVF_PTT_UNUSED_ENTRY(223), - IAVF_PTT_UNUSED_ENTRY(224), - IAVF_PTT_UNUSED_ENTRY(225), - IAVF_PTT_UNUSED_ENTRY(226), - IAVF_PTT_UNUSED_ENTRY(227), - IAVF_PTT_UNUSED_ENTRY(228), - IAVF_PTT_UNUSED_ENTRY(229), - - IAVF_PTT_UNUSED_ENTRY(230), - IAVF_PTT_UNUSED_ENTRY(231), - IAVF_PTT_UNUSED_ENTRY(232), - IAVF_PTT_UNUSED_ENTRY(233), - IAVF_PTT_UNUSED_ENTRY(234), - IAVF_PTT_UNUSED_ENTRY(235), - IAVF_PTT_UNUSED_ENTRY(236), - IAVF_PTT_UNUSED_ENTRY(237), - IAVF_PTT_UNUSED_ENTRY(238), - IAVF_PTT_UNUSED_ENTRY(239), - - IAVF_PTT_UNUSED_ENTRY(240), - IAVF_PTT_UNUSED_ENTRY(241), - IAVF_PTT_UNUSED_ENTRY(242), - IAVF_PTT_UNUSED_ENTRY(243), - IAVF_PTT_UNUSED_ENTRY(244), - IAVF_PTT_UNUSED_ENTRY(245), - IAVF_PTT_UNUSED_ENTRY(246), - IAVF_PTT_UNUSED_ENTRY(247), - IAVF_PTT_UNUSED_ENTRY(248), - IAVF_PTT_UNUSED_ENTRY(249), - - IAVF_PTT_UNUSED_ENTRY(250), - IAVF_PTT_UNUSED_ENTRY(251), - IAVF_PTT_UNUSED_ENTRY(252), - IAVF_PTT_UNUSED_ENTRY(253), - IAVF_PTT_UNUSED_ENTRY(254), - IAVF_PTT_UNUSED_ENTRY(255) + [154 ... 255] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } }; /** diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h index de9fda78b43a..9f1f523807c4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_type.h +++ b/drivers/net/ethernet/intel/iavf/iavf_type.h @@ -370,7 +370,6 @@ enum iavf_rx_l2_ptype { }; struct iavf_rx_ptype_decoded { - u32 ptype:8; u32 known:1; u32 outer_ip:1; u32 outer_ip_ver:1; diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 07fe857e9e3a..4f538cdf42c1 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -22,12 +22,14 @@ ice-y := ice_main.o \ ice_ethtool_fdir.o \ ice_flex_pipe.o \ ice_flow.o \ + ice_idc.o \ ice_devlink.o \ ice_fw_update.o \ ice_lag.o \ ice_ethtool.o ice-$(CONFIG_PCI_IOV) += ice_virtchnl_allowlist.o ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o ice_virtchnl_fdir.o +ice-$(CONFIG_PTP_1588_CLOCK) += ice_ptp.o ice_ptp_hw.o ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 2924c67567b8..a450343fbb92 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -55,8 +56,10 @@ #include "ice_switch.h" #include "ice_common.h" #include "ice_sched.h" +#include "ice_idc_int.h" #include "ice_virtchnl_pf.h" #include "ice_sriov.h" +#include "ice_ptp.h" #include "ice_fdir.h" #include "ice_xsk.h" #include "ice_arfs.h" @@ -72,12 +75,15 @@ #define ICE_DFLT_TRAFFIC_CLASS BIT(0) #define ICE_INT_NAME_STR_LEN (IFNAMSIZ + 16) -#define ICE_AQ_LEN 64 +#define ICE_AQ_LEN 192 #define ICE_MBXSQ_LEN 64 +#define ICE_SBQ_LEN 64 #define ICE_MIN_LAN_TXRX_MSIX 1 #define ICE_MIN_LAN_OICR_MSIX 1 #define ICE_MIN_MSIX (ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX) #define ICE_FDIR_MSIX 2 +#define ICE_RDMA_NUM_AEQ_MSIX 4 +#define ICE_MIN_RDMA_MSIX 2 #define ICE_NO_VSI 0xffff #define ICE_VSI_MAP_CONTIG 0 #define ICE_VSI_MAP_SCATTER 1 @@ -88,8 +94,9 @@ #define ICE_MAX_LG_RSS_QS 256 #define ICE_RES_VALID_BIT 0x8000 #define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1) +#define ICE_RES_RDMA_VEC_ID (ICE_RES_MISC_VEC_ID - 1) /* All VF control VSIs share the same IRQ, so assign a unique ID for them */ -#define ICE_RES_VF_CTRL_VEC_ID (ICE_RES_MISC_VEC_ID - 1) +#define ICE_RES_VF_CTRL_VEC_ID (ICE_RES_RDMA_VEC_ID - 1) #define ICE_INVAL_Q_INDEX 0xffff #define ICE_INVAL_VFID 256 @@ -203,9 +210,9 @@ enum ice_pf_state { ICE_NEEDS_RESTART, ICE_PREPARED_FOR_RESET, /* set by driver when prepared */ ICE_RESET_OICR_RECV, /* set by driver after rcv reset OICR */ - ICE_PFR_REQ, /* set by driver and peers */ - ICE_CORER_REQ, /* set by driver and peers */ - ICE_GLOBR_REQ, /* set by driver and peers */ + ICE_PFR_REQ, /* set by driver */ + ICE_CORER_REQ, /* set by driver */ + ICE_GLOBR_REQ, /* set by driver */ ICE_CORER_RECV, /* set by OICR handler */ ICE_GLOBR_RECV, /* set by OICR handler */ ICE_EMPR_RECV, /* set by OICR handler */ @@ -222,6 +229,7 @@ enum ice_pf_state { ICE_STATE_NOMINAL_CHECK_BITS, ICE_ADMINQ_EVENT_PENDING, ICE_MAILBOXQ_EVENT_PENDING, + ICE_SIDEBANDQ_EVENT_PENDING, ICE_MDD_EVENT_PENDING, ICE_VFLR_EVENT_PENDING, ICE_FLTR_OVERFLOW_PROMISC, @@ -332,6 +340,7 @@ struct ice_vsi { u16 req_rxq; /* User requested Rx queues */ u16 num_rx_desc; u16 num_tx_desc; + u16 qset_handle[ICE_MAX_TRAFFIC_CLASS]; struct ice_tc_cfg tc_cfg; struct bpf_prog *xdp_prog; struct ice_ring **xdp_rings; /* XDP ring array */ @@ -374,17 +383,22 @@ struct ice_q_vector { enum ice_pf_flags { ICE_FLAG_FLTR_SYNC, + ICE_FLAG_RDMA_ENA, ICE_FLAG_RSS_ENA, ICE_FLAG_SRIOV_ENA, ICE_FLAG_SRIOV_CAPABLE, ICE_FLAG_DCB_CAPABLE, ICE_FLAG_DCB_ENA, ICE_FLAG_FD_ENA, + ICE_FLAG_PTP_SUPPORTED, /* PTP is supported by NVM */ + ICE_FLAG_PTP, /* PTP is enabled by software */ + ICE_FLAG_AUX_ENA, ICE_FLAG_ADV_FEATURES, ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, ICE_FLAG_TOTAL_PORT_SHUTDOWN_ENA, ICE_FLAG_NO_MEDIA, ICE_FLAG_FW_LLDP_AGENT, + ICE_FLAG_MOD_POWER_UNSUPPORTED, ICE_FLAG_ETHTOOL_CTXT, /* set when ethtool holds RTNL lock */ ICE_FLAG_LEGACY_RX, ICE_FLAG_VF_TRUE_PROMISC_ENA, @@ -440,12 +454,17 @@ struct ice_pf { struct mutex sw_mutex; /* lock for protecting VSI alloc flow */ struct mutex tc_mutex; /* lock to protect TC changes */ u32 msg_enable; + struct ice_ptp ptp; + u16 num_rdma_msix; /* Total MSIX vectors for RDMA driver */ + u16 rdma_base_vector; /* spinlock to protect the AdminQ wait list */ spinlock_t aq_wait_lock; struct hlist_head aq_wait_list; wait_queue_head_t aq_wait_queue; + wait_queue_head_t reset_wait_queue; + u32 hw_csum_rx_error; u16 oicr_idx; /* Other interrupt cause MSIX vector index */ u16 num_avail_sw_msix; /* remaining MSIX SW vectors left unclaimed */ @@ -472,6 +491,8 @@ struct ice_pf { unsigned long tx_timeout_last_recovery; u32 tx_timeout_recovery_level; char int_name[ICE_INT_NAME_STR_LEN]; + struct auxiliary_device *adev; + int aux_idx; u32 sw_int_count; __le64 nvm_phy_type_lo; /* NVM PHY type low */ @@ -638,6 +659,9 @@ int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed); void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size); int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset); void ice_print_link_msg(struct ice_vsi *vsi, bool isup); +int ice_plug_aux_dev(struct ice_pf *pf); +void ice_unplug_aux_dev(struct ice_pf *pf); +int ice_init_rdma(struct ice_pf *pf); const char *ice_stat_str(enum ice_status stat_err); const char *ice_aq_str(enum ice_aq_err aq_err); bool ice_is_wol_supported(struct ice_hw *hw); @@ -662,4 +686,25 @@ int ice_open_internal(struct net_device *netdev); int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); +/** + * ice_set_rdma_cap - enable RDMA support + * @pf: PF struct + */ +static inline void ice_set_rdma_cap(struct ice_pf *pf) +{ + if (pf->hw.func_caps.common_cap.rdma && pf->num_rdma_msix) { + set_bit(ICE_FLAG_RDMA_ENA, pf->flags); + ice_plug_aux_dev(pf); + } +} + +/** + * ice_clear_rdma_cap - disable RDMA support + * @pf: PF struct + */ +static inline void ice_clear_rdma_cap(struct ice_pf *pf) +{ + ice_unplug_aux_dev(pf); + clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); +} #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 5cdfe406af84..21b4c7cd6f05 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -108,6 +108,7 @@ struct ice_aqc_list_caps_elem { #define ICE_AQC_CAPS_TXQS 0x0042 #define ICE_AQC_CAPS_MSIX 0x0043 #define ICE_AQC_CAPS_FD 0x0045 +#define ICE_AQC_CAPS_1588 0x0046 #define ICE_AQC_CAPS_MAX_MTU 0x0047 #define ICE_AQC_CAPS_NVM_VER 0x0048 #define ICE_AQC_CAPS_PENDING_NVM_VER 0x0049 @@ -115,6 +116,7 @@ struct ice_aqc_list_caps_elem { #define ICE_AQC_CAPS_PENDING_OROM_VER 0x004B #define ICE_AQC_CAPS_NET_VER 0x004C #define ICE_AQC_CAPS_PENDING_NET_VER 0x004D +#define ICE_AQC_CAPS_RDMA 0x0051 #define ICE_AQC_CAPS_NVM_MGMT 0x0080 u8 major_ver; @@ -1122,7 +1124,9 @@ struct ice_aqc_get_link_status_data { #define ICE_AQ_LINK_TOPO_UNDRUTIL_PRT BIT(5) #define ICE_AQ_LINK_TOPO_UNDRUTIL_MEDIA BIT(6) #define ICE_AQ_LINK_TOPO_UNSUPP_MEDIA BIT(7) - u8 reserved1; + u8 link_cfg_err; +#define ICE_AQ_LINK_MODULE_POWER_UNSUPPORTED BIT(5) +#define ICE_AQ_LINK_INVAL_MAX_POWER_LIMIT BIT(7) u8 link_info; #define ICE_AQ_LINK_UP BIT(0) /* Link Status */ #define ICE_AQ_LINK_FAULT BIT(1) @@ -1165,7 +1169,7 @@ struct ice_aqc_get_link_status_data { #define ICE_AQ_CFG_PACING_TYPE_FIXED ICE_AQ_CFG_PACING_TYPE_M /* External Device Power Ability */ u8 power_desc; -#define ICE_AQ_PWR_CLASS_M 0x3 +#define ICE_AQ_PWR_CLASS_M 0x3F #define ICE_AQ_LINK_PWR_BASET_LOW_HIGH 0 #define ICE_AQ_LINK_PWR_BASET_HIGH 1 #define ICE_AQ_LINK_PWR_QSFP_CLASS_1 0 @@ -1608,6 +1612,15 @@ struct ice_aqc_get_set_rss_lut { __le32 addr_low; }; +/* Sideband Control Interface Commands */ +/* Neighbor Device Request (indirect 0x0C00); also used for the response. */ +struct ice_aqc_neigh_dev_req { + __le16 sb_data_len; + u8 reserved[6]; + __le32 addr_high; + __le32 addr_low; +}; + /* Add Tx LAN Queues (indirect 0x0C30) */ struct ice_aqc_add_txqs { u8 num_qgrps; @@ -1684,6 +1697,36 @@ struct ice_aqc_dis_txq_item { __le16 q_id[]; } __packed; +/* Add Tx RDMA Queue Set (indirect 0x0C33) */ +struct ice_aqc_add_rdma_qset { + u8 num_qset_grps; + u8 reserved[7]; + __le32 addr_high; + __le32 addr_low; +}; + +/* This is the descriptor of each Qset entry for the Add Tx RDMA Queue Set + * command (0x0C33). Only used within struct ice_aqc_add_rdma_qset. + */ +struct ice_aqc_add_tx_rdma_qset_entry { + __le16 tx_qset_id; + u8 rsvd[2]; + __le32 qset_teid; + struct ice_aqc_txsched_elem info; +}; + +/* The format of the command buffer for Add Tx RDMA Queue Set(0x0C33) + * is an array of the following structs. Please note that the length of + * each struct ice_aqc_add_rdma_qset is variable due to the variable + * number of queues in each group! + */ +struct ice_aqc_add_rdma_qset_data { + __le32 parent_teid; + __le16 num_qsets; + u8 rsvd[2]; + struct ice_aqc_add_tx_rdma_qset_entry rdma_qsets[]; +}; + /* Configure Firmware Logging Command (indirect 0xFF09) * Logging Information Read Response (indirect 0xFF10) * Note: The 0xFF10 command has no input parameters. @@ -1810,6 +1853,30 @@ struct ice_aqc_get_pkg_info_resp { struct ice_aqc_get_pkg_info pkg_info[]; }; +/* Driver Shared Parameters (direct, 0x0C90) */ +struct ice_aqc_driver_shared_params { + u8 set_or_get_op; +#define ICE_AQC_DRIVER_PARAM_OP_MASK BIT(0) +#define ICE_AQC_DRIVER_PARAM_SET 0 +#define ICE_AQC_DRIVER_PARAM_GET 1 + u8 param_indx; +#define ICE_AQC_DRIVER_PARAM_MAX_IDX 15 + u8 rsvd[2]; + __le32 param_val; + __le32 addr_high; + __le32 addr_low; +}; + +enum ice_aqc_driver_params { + /* OS clock index for PTP timer Domain 0 */ + ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0 = 0, + /* OS clock index for PTP timer Domain 1 */ + ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1, + + /* Add new parameters above */ + ICE_AQC_DRIVER_PARAM_MAX = 16, +}; + /* Lan Queue Overflow Event (direct, 0x1001) */ struct ice_aqc_event_lan_overflow { __le32 prtdcb_ruptq; @@ -1878,13 +1945,16 @@ struct ice_aq_desc { struct ice_aqc_lldp_filter_ctrl lldp_filter_ctrl; struct ice_aqc_get_set_rss_lut get_set_rss_lut; struct ice_aqc_get_set_rss_key get_set_rss_key; + struct ice_aqc_neigh_dev_req neigh_dev; struct ice_aqc_add_txqs add_txqs; struct ice_aqc_dis_txqs dis_txqs; + struct ice_aqc_add_rdma_qset add_rdma_qset; struct ice_aqc_add_get_update_free_vsi vsi_cmd; struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res; struct ice_aqc_fw_logging fw_logging; struct ice_aqc_get_clear_fw_log get_clear_fw_log; struct ice_aqc_download_pkg download_pkg; + struct ice_aqc_driver_shared_params drv_shared_params; struct ice_aqc_set_mac_lb set_mac_lb; struct ice_aqc_alloc_free_res_cmd sw_res_ctrl; struct ice_aqc_set_mac_cfg set_mac_cfg; @@ -2025,15 +2095,21 @@ enum ice_adminq_opc { ice_aqc_opc_get_rss_key = 0x0B04, ice_aqc_opc_get_rss_lut = 0x0B05, + /* Sideband Control Interface commands */ + ice_aqc_opc_neighbour_device_request = 0x0C00, + /* Tx queue handling commands/events */ ice_aqc_opc_add_txqs = 0x0C30, ice_aqc_opc_dis_txqs = 0x0C31, + ice_aqc_opc_add_rdma_qset = 0x0C33, /* package commands */ ice_aqc_opc_download_pkg = 0x0C40, ice_aqc_opc_update_pkg = 0x0C42, ice_aqc_opc_get_pkg_info_list = 0x0C43, + ice_aqc_opc_driver_shared_params = 0x0C90, + /* Standalone Commands/Events */ ice_aqc_opc_event_lan_overflow = 0x1001, diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.h b/drivers/net/ethernet/intel/ice/ice_arfs.h index f39cd16403ed..80ed76f0cace 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.h +++ b/drivers/net/ethernet/intel/ice/ice_arfs.h @@ -52,12 +52,12 @@ bool ice_is_arfs_using_perfect_flow(struct ice_hw *hw, enum ice_fltr_ptype flow_type); #else -#define ice_sync_arfs_fltrs(pf) do {} while (0) -#define ice_init_arfs(vsi) do {} while (0) -#define ice_clear_arfs(vsi) do {} while (0) -#define ice_remove_arfs(pf) do {} while (0) -#define ice_free_cpu_rx_rmap(vsi) do {} while (0) -#define ice_rebuild_arfs(pf) do {} while (0) +static inline void ice_clear_arfs(struct ice_vsi *vsi) { } +static inline void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { } +static inline void ice_init_arfs(struct ice_vsi *vsi) { } +static inline void ice_sync_arfs_fltrs(struct ice_pf *pf) { } +static inline void ice_remove_arfs(struct ice_pf *pf) { } +static inline void ice_rebuild_arfs(struct ice_pf *pf) { } static inline int ice_set_cpu_rx_rmap(struct ice_vsi __always_unused *vsi) { diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 5985a7e5ca8a..c36057efc7ae 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -287,6 +287,15 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) /* make sure the context is associated with the right VSI */ tlan_ctx->src_vsi = ice_get_hw_vsi_num(hw, vsi->idx); + /* Restrict Tx timestamps to the PF VSI */ + switch (vsi->type) { + case ICE_VSI_PF: + tlan_ctx->tsyn_ena = 1; + break; + default: + break; + } + tlan_ctx->tso_ena = ICE_TX_LEGACY; tlan_ctx->tso_qnum = pf_q; @@ -319,11 +328,9 @@ static unsigned int ice_rx_offset(struct ice_ring *rx_ring) * * Configure the Rx descriptor ring in RLAN context. */ -int ice_setup_rx_ctx(struct ice_ring *ring) +static int ice_setup_rx_ctx(struct ice_ring *ring) { - struct device *dev = ice_pf_to_dev(ring->vsi->back); int chain_len = ICE_MAX_CHAINED_RX_BUFS; - u16 num_bufs = ICE_DESC_UNUSED(ring); struct ice_vsi *vsi = ring->vsi; u32 rxdid = ICE_RXDID_FLEX_NIC; struct ice_rlan_ctx rlan_ctx; @@ -339,48 +346,6 @@ int ice_setup_rx_ctx(struct ice_ring *ring) /* clear the context structure first */ memset(&rlan_ctx, 0, sizeof(rlan_ctx)); - ring->rx_buf_len = vsi->rx_buf_len; - - if (ring->vsi->type == ICE_VSI_PF) { - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) - /* coverity[check_return] */ - xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->q_index, ring->q_vector->napi.napi_id); - - ring->xsk_pool = ice_xsk_pool(ring); - if (ring->xsk_pool) { - xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - - ring->rx_buf_len = - xsk_pool_get_rx_frame_size(ring->xsk_pool); - /* For AF_XDP ZC, we disallow packets to span on - * multiple buffers, thus letting us skip that - * handling in the fast-path. - */ - chain_len = 1; - err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_XSK_BUFF_POOL, - NULL); - if (err) - return err; - xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); - - dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", - ring->q_index); - } else { - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) - /* coverity[check_return] */ - xdp_rxq_info_reg(&ring->xdp_rxq, - ring->netdev, - ring->q_index, ring->q_vector->napi.napi_id); - - err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_PAGE_SHARED, - NULL); - if (err) - return err; - } - } /* Receive Queue Base Address. * Indicates the starting address of the descriptor queue defined in * 128 Byte units. @@ -415,6 +380,12 @@ int ice_setup_rx_ctx(struct ice_ring *ring) */ rlan_ctx.showiv = 0; + /* For AF_XDP ZC, we disallow packets to span on + * multiple buffers, thus letting us skip that + * handling in the fast-path. + */ + if (ring->xsk_pool) + chain_len = 1; /* Max packet size for this queue - must not be set to a larger value * than 5 x DBUF */ @@ -431,14 +402,15 @@ int ice_setup_rx_ctx(struct ice_ring *ring) * of same priority */ if (vsi->type != ICE_VSI_VF) - ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3); + ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3, true); else - ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3); + ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3, + false); /* Absolute queue number out of 2K needs to be passed */ err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); if (err) { - dev_err(dev, "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n", + dev_err(ice_pf_to_dev(vsi->back), "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n", pf_q, err); return -EIO; } @@ -458,6 +430,66 @@ int ice_setup_rx_ctx(struct ice_ring *ring) ring->tail = hw->hw_addr + QRX_TAIL(pf_q); writel(0, ring->tail); + return 0; +} + +/** + * ice_vsi_cfg_rxq - Configure an Rx queue + * @ring: the ring being configured + * + * Return 0 on success and a negative value on error. + */ +int ice_vsi_cfg_rxq(struct ice_ring *ring) +{ + struct device *dev = ice_pf_to_dev(ring->vsi->back); + u16 num_bufs = ICE_DESC_UNUSED(ring); + int err; + + ring->rx_buf_len = ring->vsi->rx_buf_len; + + if (ring->vsi->type == ICE_VSI_PF) { + if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) + /* coverity[check_return] */ + xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->q_index, ring->q_vector->napi.napi_id); + + ring->xsk_pool = ice_xsk_pool(ring); + if (ring->xsk_pool) { + xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + + ring->rx_buf_len = + xsk_pool_get_rx_frame_size(ring->xsk_pool); + err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_XSK_BUFF_POOL, + NULL); + if (err) + return err; + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); + + dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", + ring->q_index); + } else { + if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) + /* coverity[check_return] */ + xdp_rxq_info_reg(&ring->xdp_rxq, + ring->netdev, + ring->q_index, ring->q_vector->napi.napi_id); + + err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, + NULL); + if (err) + return err; + } + } + + err = ice_setup_rx_ctx(ring); + if (err) { + dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n", + ring->q_index, err); + return err; + } + if (ring->xsk_pool) { bool ok; @@ -470,9 +502,13 @@ int ice_setup_rx_ctx(struct ice_ring *ring) } ok = ice_alloc_rx_bufs_zc(ring, num_bufs); - if (!ok) + if (!ok) { + u16 pf_q = ring->vsi->rxq_map[ring->q_index]; + dev_info(dev, "Failed to allocate some buffers on XSK buffer pool enabled Rx ring %d (pf_q %d)\n", ring->q_index, pf_q); + } + return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_base.h b/drivers/net/ethernet/intel/ice/ice_base.h index 44efdb627043..20e1c29aa68a 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.h +++ b/drivers/net/ethernet/intel/ice/ice_base.h @@ -6,7 +6,7 @@ #include "ice.h" -int ice_setup_rx_ctx(struct ice_ring *ring); +int ice_vsi_cfg_rxq(struct ice_ring *ring); int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg); int ice_vsi_ctrl_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx, bool wait); diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index e93b1e40f627..2fb81e359cdf 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -2,6 +2,7 @@ /* Copyright (c) 2018, Intel Corporation. */ #include "ice_common.h" +#include "ice_lib.h" #include "ice_sched.h" #include "ice_adminq_cmd.h" #include "ice_flow.h" @@ -57,6 +58,17 @@ static enum ice_status ice_set_mac_type(struct ice_hw *hw) return 0; } +/** + * ice_is_e810 + * @hw: pointer to the hardware structure + * + * returns true if the device is E810 based, false if not. + */ +bool ice_is_e810(struct ice_hw *hw) +{ + return hw->mac_type == ICE_MAC_E810; +} + /** * ice_clear_pf_cfg - Clear PF configuration * @hw: pointer to the hardware structure @@ -424,6 +436,7 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, li->phy_type_high = le64_to_cpu(link_data.phy_type_high); *hw_media_type = ice_get_media_type(pi); li->link_info = link_data.link_info; + li->link_cfg_err = link_data.link_cfg_err; li->an_info = link_data.an_info; li->ext_info = link_data.ext_info; li->max_frame_size = le16_to_cpu(link_data.max_frame_size); @@ -454,6 +467,7 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, (unsigned long long)li->phy_type_high); ice_debug(hw, ICE_DBG_LINK, " media_type = 0x%x\n", *hw_media_type); ice_debug(hw, ICE_DBG_LINK, " link_info = 0x%x\n", li->link_info); + ice_debug(hw, ICE_DBG_LINK, " link_cfg_err = 0x%x\n", li->link_cfg_err); ice_debug(hw, ICE_DBG_LINK, " an_info = 0x%x\n", li->an_info); ice_debug(hw, ICE_DBG_LINK, " ext_info = 0x%x\n", li->ext_info); ice_debug(hw, ICE_DBG_LINK, " fec_info = 0x%x\n", li->fec_info); @@ -1062,7 +1076,8 @@ enum ice_status ice_check_reset(struct ice_hw *hw) GLNVM_ULD_POR_DONE_1_M |\ GLNVM_ULD_PCIER_DONE_2_M) - uld_mask = ICE_RESET_DONE_MASK; + uld_mask = ICE_RESET_DONE_MASK | (hw->func_caps.common_cap.rdma ? + GLNVM_ULD_PE_DONE_M : 0); /* Device is Active; check Global Reset processes are done */ for (cnt = 0; cnt < ICE_PF_RESET_WAIT_COUNT; cnt++) { @@ -1289,6 +1304,64 @@ const struct ice_ctx_ele ice_tlan_ctx_info[] = { { 0 } }; +/* Sideband Queue command wrappers */ + +/** + * ice_sbq_send_cmd - send Sideband Queue command to Sideband Queue + * @hw: pointer to the HW struct + * @desc: descriptor describing the command + * @buf: buffer to use for indirect commands (NULL for direct commands) + * @buf_size: size of buffer for indirect commands (0 for direct commands) + * @cd: pointer to command details structure + */ +static int +ice_sbq_send_cmd(struct ice_hw *hw, struct ice_sbq_cmd_desc *desc, + void *buf, u16 buf_size, struct ice_sq_cd *cd) +{ + return ice_status_to_errno(ice_sq_send_cmd(hw, ice_get_sbq(hw), + (struct ice_aq_desc *)desc, + buf, buf_size, cd)); +} + +/** + * ice_sbq_rw_reg - Fill Sideband Queue command + * @hw: pointer to the HW struct + * @in: message info to be filled in descriptor + */ +int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in) +{ + struct ice_sbq_cmd_desc desc = {0}; + struct ice_sbq_msg_req msg = {0}; + u16 msg_len; + int status; + + msg_len = sizeof(msg); + + msg.dest_dev = in->dest_dev; + msg.opcode = in->opcode; + msg.flags = ICE_SBQ_MSG_FLAGS; + msg.sbe_fbe = ICE_SBQ_MSG_SBE_FBE; + msg.msg_addr_low = cpu_to_le16(in->msg_addr_low); + msg.msg_addr_high = cpu_to_le32(in->msg_addr_high); + + if (in->opcode) + msg.data = cpu_to_le32(in->data); + else + /* data read comes back in completion, so shorten the struct by + * sizeof(msg.data) + */ + msg_len -= sizeof(msg.data); + + desc.flags = cpu_to_le16(ICE_AQ_FLAG_RD); + desc.opcode = cpu_to_le16(ice_sbq_opc_neigh_dev_req); + desc.param0.cmd_len = cpu_to_le16(msg_len); + status = ice_sbq_send_cmd(hw, &desc, &msg, msg_len, NULL); + if (!status && !in->opcode) + in->data = le32_to_cpu + (((struct ice_sbq_msg_cmpl *)&msg)->data); + return status; +} + /* FW Admin Queue command wrappers */ /* Software lock/mutex that is meant to be held while the Global Config Lock @@ -1938,6 +2011,10 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, ice_debug(hw, ICE_DBG_INIT, "%s: nvm_unified_update = %d\n", prefix, caps->nvm_unified_update); break; + case ICE_AQC_CAPS_RDMA: + caps->rdma = (number == 1); + ice_debug(hw, ICE_DBG_INIT, "%s: rdma = %d\n", prefix, caps->rdma); + break; case ICE_AQC_CAPS_MAX_MTU: caps->max_mtu = number; ice_debug(hw, ICE_DBG_INIT, "%s: max_mtu = %d\n", @@ -1971,6 +2048,16 @@ ice_recalc_port_limited_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps) caps->maxtc = 4; ice_debug(hw, ICE_DBG_INIT, "reducing maxtc to %d (based on #ports)\n", caps->maxtc); + if (caps->rdma) { + ice_debug(hw, ICE_DBG_INIT, "forcing RDMA off\n"); + caps->rdma = 0; + } + + /* print message only when processing device capabilities + * during initialization. + */ + if (caps == &hw->dev_caps.common_cap) + dev_info(ice_hw_to_dev(hw), "RDMA functionality is not available with the current device configuration.\n"); } } @@ -2016,6 +2103,48 @@ ice_parse_vsi_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p, func_p->guar_num_vsi); } +/** + * ice_parse_1588_func_caps - Parse ICE_AQC_CAPS_1588 function caps + * @hw: pointer to the HW struct + * @func_p: pointer to function capabilities structure + * @cap: pointer to the capability element to parse + * + * Extract function capabilities for ICE_AQC_CAPS_1588. + */ +static void +ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p, + struct ice_aqc_list_caps_elem *cap) +{ + struct ice_ts_func_info *info = &func_p->ts_func_info; + u32 number = le32_to_cpu(cap->number); + + info->ena = ((number & ICE_TS_FUNC_ENA_M) != 0); + func_p->common_cap.ieee_1588 = info->ena; + + info->src_tmr_owned = ((number & ICE_TS_SRC_TMR_OWND_M) != 0); + info->tmr_ena = ((number & ICE_TS_TMR_ENA_M) != 0); + info->tmr_index_owned = ((number & ICE_TS_TMR_IDX_OWND_M) != 0); + info->tmr_index_assoc = ((number & ICE_TS_TMR_IDX_ASSOC_M) != 0); + + info->clk_freq = (number & ICE_TS_CLK_FREQ_M) >> ICE_TS_CLK_FREQ_S; + info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0); + + ice_debug(hw, ICE_DBG_INIT, "func caps: ieee_1588 = %u\n", + func_p->common_cap.ieee_1588); + ice_debug(hw, ICE_DBG_INIT, "func caps: src_tmr_owned = %u\n", + info->src_tmr_owned); + ice_debug(hw, ICE_DBG_INIT, "func caps: tmr_ena = %u\n", + info->tmr_ena); + ice_debug(hw, ICE_DBG_INIT, "func caps: tmr_index_owned = %u\n", + info->tmr_index_owned); + ice_debug(hw, ICE_DBG_INIT, "func caps: tmr_index_assoc = %u\n", + info->tmr_index_assoc); + ice_debug(hw, ICE_DBG_INIT, "func caps: clk_freq = %u\n", + info->clk_freq); + ice_debug(hw, ICE_DBG_INIT, "func caps: clk_src = %u\n", + info->clk_src); +} + /** * ice_parse_fdir_func_caps - Parse ICE_AQC_CAPS_FD function caps * @hw: pointer to the HW struct @@ -2082,6 +2211,9 @@ ice_parse_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p, case ICE_AQC_CAPS_VSI: ice_parse_vsi_func_caps(hw, func_p, &cap_resp[i]); break; + case ICE_AQC_CAPS_1588: + ice_parse_1588_func_caps(hw, func_p, &cap_resp[i]); + break; case ICE_AQC_CAPS_FD: ice_parse_fdir_func_caps(hw, func_p); break; @@ -2154,6 +2286,57 @@ ice_parse_vsi_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, dev_p->num_vsi_allocd_to_host); } +/** + * ice_parse_1588_dev_caps - Parse ICE_AQC_CAPS_1588 device caps + * @hw: pointer to the HW struct + * @dev_p: pointer to device capabilities structure + * @cap: capability element to parse + * + * Parse ICE_AQC_CAPS_1588 for device capabilities. + */ +static void +ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, + struct ice_aqc_list_caps_elem *cap) +{ + struct ice_ts_dev_info *info = &dev_p->ts_dev_info; + u32 logical_id = le32_to_cpu(cap->logical_id); + u32 phys_id = le32_to_cpu(cap->phys_id); + u32 number = le32_to_cpu(cap->number); + + info->ena = ((number & ICE_TS_DEV_ENA_M) != 0); + dev_p->common_cap.ieee_1588 = info->ena; + + info->tmr0_owner = number & ICE_TS_TMR0_OWNR_M; + info->tmr0_owned = ((number & ICE_TS_TMR0_OWND_M) != 0); + info->tmr0_ena = ((number & ICE_TS_TMR0_ENA_M) != 0); + + info->tmr1_owner = (number & ICE_TS_TMR1_OWNR_M) >> ICE_TS_TMR1_OWNR_S; + info->tmr1_owned = ((number & ICE_TS_TMR1_OWND_M) != 0); + info->tmr1_ena = ((number & ICE_TS_TMR1_ENA_M) != 0); + + info->ena_ports = logical_id; + info->tmr_own_map = phys_id; + + ice_debug(hw, ICE_DBG_INIT, "dev caps: ieee_1588 = %u\n", + dev_p->common_cap.ieee_1588); + ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr0_owner = %u\n", + info->tmr0_owner); + ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr0_owned = %u\n", + info->tmr0_owned); + ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr0_ena = %u\n", + info->tmr0_ena); + ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr1_owner = %u\n", + info->tmr1_owner); + ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr1_owned = %u\n", + info->tmr1_owned); + ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr1_ena = %u\n", + info->tmr1_ena); + ice_debug(hw, ICE_DBG_INIT, "dev caps: ieee_1588 ena_ports = %u\n", + info->ena_ports); + ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr_own_map = %u\n", + info->tmr_own_map); +} + /** * ice_parse_fdir_dev_caps - Parse ICE_AQC_CAPS_FD device caps * @hw: pointer to the HW struct @@ -2215,6 +2398,9 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, case ICE_AQC_CAPS_VSI: ice_parse_vsi_dev_caps(hw, dev_p, &cap_resp[i]); break; + case ICE_AQC_CAPS_1588: + ice_parse_1588_dev_caps(hw, dev_p, &cap_resp[i]); + break; case ICE_AQC_CAPS_FD: ice_parse_fdir_dev_caps(hw, dev_p, &cap_resp[i]); break; @@ -3635,6 +3821,52 @@ do_aq: return status; } +/** + * ice_aq_add_rdma_qsets + * @hw: pointer to the hardware structure + * @num_qset_grps: Number of RDMA Qset groups + * @qset_list: list of Qset groups to be added + * @buf_size: size of buffer for indirect command + * @cd: pointer to command details structure or NULL + * + * Add Tx RDMA Qsets (0x0C33) + */ +static int +ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps, + struct ice_aqc_add_rdma_qset_data *qset_list, + u16 buf_size, struct ice_sq_cd *cd) +{ + struct ice_aqc_add_rdma_qset_data *list; + struct ice_aqc_add_rdma_qset *cmd; + struct ice_aq_desc desc; + u16 i, sum_size = 0; + + cmd = &desc.params.add_rdma_qset; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_rdma_qset); + + if (num_qset_grps > ICE_LAN_TXQ_MAX_QGRPS) + return -EINVAL; + + for (i = 0, list = qset_list; i < num_qset_grps; i++) { + u16 num_qsets = le16_to_cpu(list->num_qsets); + + sum_size += struct_size(list, rdma_qsets, num_qsets); + list = (struct ice_aqc_add_rdma_qset_data *)(list->rdma_qsets + + num_qsets); + } + + if (buf_size != sum_size) + return -EINVAL; + + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + cmd->num_qset_grps = num_qset_grps; + + return ice_status_to_errno(ice_aq_send_cmd(hw, &desc, qset_list, + buf_size, cd)); +} + /* End of FW Admin Queue command wrappers */ /** @@ -4132,6 +4364,162 @@ ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, ICE_SCHED_NODE_OWNER_LAN); } +/** + * ice_cfg_vsi_rdma - configure the VSI RDMA queues + * @pi: port information structure + * @vsi_handle: software VSI handle + * @tc_bitmap: TC bitmap + * @max_rdmaqs: max RDMA queues array per TC + * + * This function adds/updates the VSI RDMA queues per TC. + */ +int +ice_cfg_vsi_rdma(struct ice_port_info *pi, u16 vsi_handle, u16 tc_bitmap, + u16 *max_rdmaqs) +{ + return ice_status_to_errno(ice_cfg_vsi_qs(pi, vsi_handle, tc_bitmap, + max_rdmaqs, + ICE_SCHED_NODE_OWNER_RDMA)); +} + +/** + * ice_ena_vsi_rdma_qset + * @pi: port information structure + * @vsi_handle: software VSI handle + * @tc: TC number + * @rdma_qset: pointer to RDMA Qset + * @num_qsets: number of RDMA Qsets + * @qset_teid: pointer to Qset node TEIDs + * + * This function adds RDMA Qset + */ +int +ice_ena_vsi_rdma_qset(struct ice_port_info *pi, u16 vsi_handle, u8 tc, + u16 *rdma_qset, u16 num_qsets, u32 *qset_teid) +{ + struct ice_aqc_txsched_elem_data node = { 0 }; + struct ice_aqc_add_rdma_qset_data *buf; + struct ice_sched_node *parent; + enum ice_status status; + struct ice_hw *hw; + u16 i, buf_size; + int ret; + + if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) + return -EIO; + hw = pi->hw; + + if (!ice_is_vsi_valid(hw, vsi_handle)) + return -EINVAL; + + buf_size = struct_size(buf, rdma_qsets, num_qsets); + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + mutex_lock(&pi->sched_lock); + + parent = ice_sched_get_free_qparent(pi, vsi_handle, tc, + ICE_SCHED_NODE_OWNER_RDMA); + if (!parent) { + ret = -EINVAL; + goto rdma_error_exit; + } + buf->parent_teid = parent->info.node_teid; + node.parent_teid = parent->info.node_teid; + + buf->num_qsets = cpu_to_le16(num_qsets); + for (i = 0; i < num_qsets; i++) { + buf->rdma_qsets[i].tx_qset_id = cpu_to_le16(rdma_qset[i]); + buf->rdma_qsets[i].info.valid_sections = + ICE_AQC_ELEM_VALID_GENERIC | ICE_AQC_ELEM_VALID_CIR | + ICE_AQC_ELEM_VALID_EIR; + buf->rdma_qsets[i].info.generic = 0; + buf->rdma_qsets[i].info.cir_bw.bw_profile_idx = + cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID); + buf->rdma_qsets[i].info.cir_bw.bw_alloc = + cpu_to_le16(ICE_SCHED_DFLT_BW_WT); + buf->rdma_qsets[i].info.eir_bw.bw_profile_idx = + cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID); + buf->rdma_qsets[i].info.eir_bw.bw_alloc = + cpu_to_le16(ICE_SCHED_DFLT_BW_WT); + } + ret = ice_aq_add_rdma_qsets(hw, 1, buf, buf_size, NULL); + if (ret) { + ice_debug(hw, ICE_DBG_RDMA, "add RDMA qset failed\n"); + goto rdma_error_exit; + } + node.data.elem_type = ICE_AQC_ELEM_TYPE_LEAF; + for (i = 0; i < num_qsets; i++) { + node.node_teid = buf->rdma_qsets[i].qset_teid; + status = ice_sched_add_node(pi, hw->num_tx_sched_layers - 1, + &node); + if (status) { + ret = ice_status_to_errno(status); + break; + } + qset_teid[i] = le32_to_cpu(node.node_teid); + } +rdma_error_exit: + mutex_unlock(&pi->sched_lock); + kfree(buf); + return ret; +} + +/** + * ice_dis_vsi_rdma_qset - free RDMA resources + * @pi: port_info struct + * @count: number of RDMA Qsets to free + * @qset_teid: TEID of Qset node + * @q_id: list of queue IDs being disabled + */ +int +ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, + u16 *q_id) +{ + struct ice_aqc_dis_txq_item *qg_list; + enum ice_status status = 0; + struct ice_hw *hw; + u16 qg_size; + int i; + + if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) + return -EIO; + + hw = pi->hw; + + qg_size = struct_size(qg_list, q_id, 1); + qg_list = kzalloc(qg_size, GFP_KERNEL); + if (!qg_list) + return -ENOMEM; + + mutex_lock(&pi->sched_lock); + + for (i = 0; i < count; i++) { + struct ice_sched_node *node; + + node = ice_sched_find_node_by_teid(pi->root, qset_teid[i]); + if (!node) + continue; + + qg_list->parent_teid = node->info.parent_teid; + qg_list->num_qs = 1; + qg_list->q_id[0] = + cpu_to_le16(q_id[i] | + ICE_AQC_Q_DIS_BUF_ELEM_TYPE_RDMA_QSET); + + status = ice_aq_dis_lan_txq(hw, 1, qg_list, qg_size, + ICE_NO_RESET, 0, NULL); + if (status) + break; + + ice_free_sched_node(pi, node); + } + + mutex_unlock(&pi->sched_lock); + kfree(qg_list); + return ice_status_to_errno(status); +} + /** * ice_replay_pre_init - replay pre initialization * @hw: pointer to the HW struct @@ -4303,6 +4691,81 @@ ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, return status; } +/** + * ice_aq_set_driver_param - Set driver parameter to share via firmware + * @hw: pointer to the HW struct + * @idx: parameter index to set + * @value: the value to set the parameter to + * @cd: pointer to command details structure or NULL + * + * Set the value of one of the software defined parameters. All PFs connected + * to this device can read the value using ice_aq_get_driver_param. + * + * Note that firmware provides no synchronization or locking, and will not + * save the parameter value during a device reset. It is expected that + * a single PF will write the parameter value, while all other PFs will only + * read it. + */ +int +ice_aq_set_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, + u32 value, struct ice_sq_cd *cd) +{ + struct ice_aqc_driver_shared_params *cmd; + struct ice_aq_desc desc; + + if (idx >= ICE_AQC_DRIVER_PARAM_MAX) + return -EIO; + + cmd = &desc.params.drv_shared_params; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_shared_params); + + cmd->set_or_get_op = ICE_AQC_DRIVER_PARAM_SET; + cmd->param_indx = idx; + cmd->param_val = cpu_to_le32(value); + + return ice_status_to_errno(ice_aq_send_cmd(hw, &desc, NULL, 0, cd)); +} + +/** + * ice_aq_get_driver_param - Get driver parameter shared via firmware + * @hw: pointer to the HW struct + * @idx: parameter index to set + * @value: storage to return the shared parameter + * @cd: pointer to command details structure or NULL + * + * Get the value of one of the software defined parameters. + * + * Note that firmware provides no synchronization or locking. It is expected + * that only a single PF will write a given parameter. + */ +int +ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, + u32 *value, struct ice_sq_cd *cd) +{ + struct ice_aqc_driver_shared_params *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + if (idx >= ICE_AQC_DRIVER_PARAM_MAX) + return -EIO; + + cmd = &desc.params.drv_shared_params; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_shared_params); + + cmd->set_or_get_op = ICE_AQC_DRIVER_PARAM_GET; + cmd->param_indx = idx; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + if (status) + return ice_status_to_errno(status); + + *value = le32_to_cpu(cmd->param_val); + + return 0; +} + /** * ice_fw_supports_link_override * @hw: pointer to the hardware structure diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 7a9d2dfb21a2..fb16070f02e2 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -40,6 +40,8 @@ enum ice_status ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, enum ice_adminq_opc opc, struct ice_sq_cd *cd); +bool ice_is_sbq_supported(struct ice_hw *hw); +struct ice_ctl_q_info *ice_get_sbq(struct ice_hw *hw); enum ice_status ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_aq_desc *desc, void *buf, u16 buf_size, @@ -97,6 +99,7 @@ ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high, enum ice_status ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags, struct ice_sq_cd *cd); +bool ice_is_e810(struct ice_hw *hw); enum ice_status ice_clear_pf_cfg(struct ice_hw *hw); enum ice_status ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi, @@ -147,6 +150,15 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length, bool write, struct ice_sq_cd *cd); +int +ice_cfg_vsi_rdma(struct ice_port_info *pi, u16 vsi_handle, u16 tc_bitmap, + u16 *max_rdmaqs); +int +ice_ena_vsi_rdma_qset(struct ice_port_info *pi, u16 vsi_handle, u8 tc, + u16 *rdma_qset, u16 num_qsets, u32 *qset_teid); +int +ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, + u16 *q_id); enum ice_status ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, u16 *q_handle, u16 *q_ids, u32 *q_teids, @@ -164,6 +176,7 @@ void ice_replay_post(struct ice_hw *hw); void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf); struct ice_q_ctx * ice_get_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 q_handle); +int ice_sbq_rw_reg(struct ice_hw *hw, struct ice_sbq_msg_input *in); void ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); @@ -173,6 +186,12 @@ ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, enum ice_status ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_txsched_elem_data *buf); +int +ice_aq_set_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, + u32 value, struct ice_sq_cd *cd); +int +ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, + u32 *value, struct ice_sq_cd *cd); enum ice_status ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, struct ice_sq_cd *cd); diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index 87b33bdd4960..03bdb125be36 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -51,6 +51,19 @@ static void ice_mailbox_init_regs(struct ice_hw *hw) ICE_CQ_INIT_REGS(cq, PF_MBX); } +/** + * ice_sb_init_regs - Initialize Sideband registers + * @hw: pointer to the hardware structure + * + * This assumes the alloc_sq and alloc_rq functions have already been called + */ +static void ice_sb_init_regs(struct ice_hw *hw) +{ + struct ice_ctl_q_info *cq = &hw->sbq; + + ICE_CQ_INIT_REGS(cq, PF_SB); +} + /** * ice_check_sq_alive * @hw: pointer to the HW struct @@ -609,6 +622,10 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) ice_adminq_init_regs(hw); cq = &hw->adminq; break; + case ICE_CTL_Q_SB: + ice_sb_init_regs(hw); + cq = &hw->sbq; + break; case ICE_CTL_Q_MAILBOX: ice_mailbox_init_regs(hw); cq = &hw->mailboxq; @@ -645,6 +662,32 @@ init_ctrlq_free_sq: return ret_code; } +/** + * ice_is_sbq_supported - is the sideband queue supported + * @hw: pointer to the hardware structure + * + * Returns true if the sideband control queue interface is + * supported for the device, false otherwise + */ +bool ice_is_sbq_supported(struct ice_hw *hw) +{ + /* The device sideband queue is only supported on devices with the + * generic MAC type. + */ + return hw->mac_type == ICE_MAC_GENERIC; +} + +/** + * ice_get_sbq - returns the right control queue to use for sideband + * @hw: pointer to the hardware structure + */ +struct ice_ctl_q_info *ice_get_sbq(struct ice_hw *hw) +{ + if (ice_is_sbq_supported(hw)) + return &hw->sbq; + return &hw->adminq; +} + /** * ice_shutdown_ctrlq - shutdown routine for any control queue * @hw: pointer to the hardware structure @@ -662,6 +705,9 @@ static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) if (ice_check_sq_alive(hw, cq)) ice_aq_q_shutdown(hw, true); break; + case ICE_CTL_Q_SB: + cq = &hw->sbq; + break; case ICE_CTL_Q_MAILBOX: cq = &hw->mailboxq; break; @@ -685,6 +731,9 @@ void ice_shutdown_all_ctrlq(struct ice_hw *hw) { /* Shutdown FW admin queue */ ice_shutdown_ctrlq(hw, ICE_CTL_Q_ADMIN); + /* Shutdown PHY Sideband */ + if (ice_is_sbq_supported(hw)) + ice_shutdown_ctrlq(hw, ICE_CTL_Q_SB); /* Shutdown PF-VF Mailbox */ ice_shutdown_ctrlq(hw, ICE_CTL_Q_MAILBOX); } @@ -724,6 +773,15 @@ enum ice_status ice_init_all_ctrlq(struct ice_hw *hw) if (status) return status; + /* sideband control queue (SBQ) interface is not supported on some + * devices. Initialize if supported, else fallback to the admin queue + * interface + */ + if (ice_is_sbq_supported(hw)) { + status = ice_init_ctrlq(hw, ICE_CTL_Q_SB); + if (status) + return status; + } /* Init Mailbox queue */ return ice_init_ctrlq(hw, ICE_CTL_Q_MAILBOX); } @@ -759,6 +817,8 @@ static void ice_init_ctrlq_locks(struct ice_ctl_q_info *cq) enum ice_status ice_create_all_ctrlq(struct ice_hw *hw) { ice_init_ctrlq_locks(&hw->adminq); + if (ice_is_sbq_supported(hw)) + ice_init_ctrlq_locks(&hw->sbq); ice_init_ctrlq_locks(&hw->mailboxq); return ice_init_all_ctrlq(hw); @@ -791,6 +851,8 @@ void ice_destroy_all_ctrlq(struct ice_hw *hw) ice_shutdown_all_ctrlq(hw); ice_destroy_ctrlq_locks(&hw->adminq); + if (ice_is_sbq_supported(hw)) + ice_destroy_ctrlq_locks(&hw->sbq); ice_destroy_ctrlq_locks(&hw->mailboxq); } diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h index fe75871e48ca..c07e9cc9fc6e 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.h +++ b/drivers/net/ethernet/intel/ice/ice_controlq.h @@ -9,6 +9,7 @@ /* Maximum buffer lengths for all control queue types */ #define ICE_AQ_MAX_BUF_LEN 4096 #define ICE_MBXQ_MAX_BUF_LEN 4096 +#define ICE_SBQ_MAX_BUF_LEN 512 #define ICE_CTL_Q_DESC(R, i) \ (&(((struct ice_aq_desc *)((R).desc_buf.va))[i])) @@ -29,6 +30,7 @@ enum ice_ctl_q { ICE_CTL_Q_UNKNOWN = 0, ICE_CTL_Q_ADMIN, ICE_CTL_Q_MAILBOX, + ICE_CTL_Q_SB, }; /* Control Queue timeout settings - max delay 1s */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index df02cffdf209..926cf748c5ec 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -275,6 +275,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) struct ice_dcbx_cfg *old_cfg, *curr_cfg; struct device *dev = ice_pf_to_dev(pf); int ret = ICE_DCB_NO_HW_CHG; + struct iidc_event *event; struct ice_vsi *pf_vsi; curr_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; @@ -313,6 +314,17 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) goto free_cfg; } + /* Notify AUX drivers about impending change to TCs */ + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) { + ret = -ENOMEM; + goto free_cfg; + } + + set_bit(IIDC_EVENT_BEFORE_TC_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); + /* avoid race conditions by holding the lock while disabling and * re-enabling the VSI */ @@ -640,6 +652,7 @@ static int ice_dcb_noncontig_cfg(struct ice_pf *pf) void ice_pf_dcb_recfg(struct ice_pf *pf) { struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; + struct iidc_event *event; u8 tc_map = 0; int v, ret; @@ -675,6 +688,14 @@ void ice_pf_dcb_recfg(struct ice_pf *pf) if (vsi->type == ICE_VSI_PF) ice_dcbnl_set_all(vsi); } + /* Notify the AUX drivers that TC change is finished */ + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return; + + set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h index 35c21d9ae009..261b6e2ed7bc 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h @@ -60,7 +60,7 @@ static inline bool ice_is_dcb_active(struct ice_pf *pf) test_bit(ICE_FLAG_DCB_ENA, pf->flags)); } #else -#define ice_dcb_rebuild(pf) do {} while (0) +static inline void ice_dcb_rebuild(struct ice_pf *pf) { } static inline u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg __always_unused *dcbcfg) { @@ -113,11 +113,12 @@ ice_is_pfc_causing_hung_q(struct ice_pf __always_unused *pf, return false; } -#define ice_update_dcb_stats(pf) do {} while (0) -#define ice_pf_dcb_recfg(pf) do {} while (0) -#define ice_vsi_cfg_dcb_rings(vsi) do {} while (0) -#define ice_dcb_process_lldp_set_mib_change(pf, event) do {} while (0) -#define ice_set_cgd_num(tlan_ctx, ring) do {} while (0) -#define ice_vsi_cfg_netdev_tc(vsi, ena_tc) do {} while (0) +static inline void ice_pf_dcb_recfg(struct ice_pf *pf) { } +static inline void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) { } +static inline void ice_update_dcb_stats(struct ice_pf *pf) { } +static inline void +ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event) { } +static inline void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc) { } +static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, struct ice_ring *ring) { } #endif /* CONFIG_DCB */ #endif /* _ICE_DCB_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.h b/drivers/net/ethernet/intel/ice/ice_dcb_nl.h index 6c630a362293..eac2f34bdcdd 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.h @@ -11,9 +11,10 @@ void ice_dcbnl_flush_apps(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg, struct ice_dcbx_cfg *new_cfg); #else -#define ice_dcbnl_setup(vsi) do {} while (0) -#define ice_dcbnl_set_all(vsi) do {} while (0) -#define ice_dcbnl_flush_apps(pf, old_cfg, new_cfg) do {} while (0) +static inline void ice_dcbnl_setup(struct ice_vsi *vsi) { } +static inline void ice_dcbnl_set_all(struct ice_vsi *vsi) { } +static inline void +ice_dcbnl_flush_apps(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg, + struct ice_dcbx_cfg *new_cfg) { } #endif /* CONFIG_DCB */ - #endif /* _ICE_DCB_NL_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index cf685eeea198..91b545ab8b8f 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -276,6 +276,12 @@ static int ice_devlink_info_get(struct devlink *devlink, size_t i; int err; + err = ice_wait_for_reset(pf, 10 * HZ); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Device is busy resetting"); + return err; + } + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; @@ -283,6 +289,9 @@ static int ice_devlink_info_get(struct devlink *devlink, /* discover capabilities first */ status = ice_discover_dev_caps(hw, &ctx->dev_caps); if (status) { + dev_dbg(dev, "Failed to discover device capabilities, status %s aq_err %s\n", + ice_stat_str(status), ice_aq_str(hw->adminq.sq_last_status)); + NL_SET_ERR_MSG_MOD(extack, "Unable to discover device capabilities"); err = -EIO; goto out_free_ctx; } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 99301ad95290..d95a5daca114 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3195,6 +3195,31 @@ ice_set_rxfh(struct net_device *netdev, const u32 *indir, const u8 *key, return 0; } +static int +ice_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) +{ + struct ice_pf *pf = ice_netdev_to_pf(dev); + + /* only report timestamping if PTP is enabled */ + if (!test_bit(ICE_FLAG_PTP, pf->flags)) + return ethtool_op_get_ts_info(dev, info); + + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + info->phc_index = ice_get_ptp_clock_index(pf); + + info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON); + + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL); + + return 0; +} + /** * ice_get_max_txq - return the maximum number of Tx queues for in a PF * @pf: PF structure @@ -3462,13 +3487,9 @@ static int ice_get_rc_coalesce(struct ethtool_coalesce *ec, enum ice_container_type c_type, struct ice_ring_container *rc) { - struct ice_pf *pf; - if (!rc->ring) return -EINVAL; - pf = rc->ring->vsi->back; - switch (c_type) { case ICE_RX_CONTAINER: ec->use_adaptive_rx_coalesce = ITR_IS_DYNAMIC(rc); @@ -3480,7 +3501,7 @@ ice_get_rc_coalesce(struct ethtool_coalesce *ec, enum ice_container_type c_type, ec->tx_coalesce_usecs = rc->itr_setting; break; default: - dev_dbg(ice_pf_to_dev(pf), "Invalid c_type %d\n", c_type); + dev_dbg(ice_pf_to_dev(rc->ring->vsi->back), "Invalid c_type %d\n", c_type); return -EINVAL; } @@ -3990,7 +4011,7 @@ static const struct ethtool_ops ice_ethtool_ops = { .set_rxfh = ice_set_rxfh, .get_channels = ice_get_channels, .set_channels = ice_set_channels, - .get_ts_info = ethtool_op_get_ts_info, + .get_ts_info = ice_get_ts_info, .get_per_queue_coalesce = ice_get_per_q_coalesce, .set_per_queue_coalesce = ice_set_per_q_coalesce, .get_fecparam = ice_get_fecparam, diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index dcec0360ce55..f8601d5b0b19 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -702,6 +702,16 @@ int ice_flash_pldm_image(struct ice_pf *pf, const struct firmware *fw, } err = pldmfw_flash_image(&priv.context, fw); + if (err == -ENOENT) { + dev_err(dev, "Firmware image has no record matching this device\n"); + NL_SET_ERR_MSG_MOD(extack, "Firmware image has no record matching this device"); + } else if (err) { + /* Do not set a generic extended ACK message here. A more + * specific message may already have been set by one of our + * ops. + */ + dev_err(dev, "Failed to flash PLDM image, err %d", err); + } ice_release_nvm(hw); diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 9b8300d4a267..76021d977b60 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -52,6 +52,54 @@ #define PF_MBX_ATQLEN_ATQCRIT_M BIT(30) #define PF_MBX_ATQLEN_ATQENABLE_M BIT(31) #define PF_MBX_ATQT 0x0022E300 +#define PF_SB_ARQBAH 0x0022FF00 +#define PF_SB_ARQBAH_ARQBAH_S 0 +#define PF_SB_ARQBAH_ARQBAH_M ICE_M(0xFFFFFFFF, 0) +#define PF_SB_ARQBAL 0x0022FE80 +#define PF_SB_ARQBAL_ARQBAL_LSB_S 0 +#define PF_SB_ARQBAL_ARQBAL_LSB_M ICE_M(0x3F, 0) +#define PF_SB_ARQBAL_ARQBAL_S 6 +#define PF_SB_ARQBAL_ARQBAL_M ICE_M(0x3FFFFFF, 6) +#define PF_SB_ARQH 0x00230000 +#define PF_SB_ARQH_ARQH_S 0 +#define PF_SB_ARQH_ARQH_M ICE_M(0x3FF, 0) +#define PF_SB_ARQLEN 0x0022FF80 +#define PF_SB_ARQLEN_ARQLEN_S 0 +#define PF_SB_ARQLEN_ARQLEN_M ICE_M(0x3FF, 0) +#define PF_SB_ARQLEN_ARQVFE_S 28 +#define PF_SB_ARQLEN_ARQVFE_M BIT(28) +#define PF_SB_ARQLEN_ARQOVFL_S 29 +#define PF_SB_ARQLEN_ARQOVFL_M BIT(29) +#define PF_SB_ARQLEN_ARQCRIT_S 30 +#define PF_SB_ARQLEN_ARQCRIT_M BIT(30) +#define PF_SB_ARQLEN_ARQENABLE_S 31 +#define PF_SB_ARQLEN_ARQENABLE_M BIT(31) +#define PF_SB_ARQT 0x00230080 +#define PF_SB_ARQT_ARQT_S 0 +#define PF_SB_ARQT_ARQT_M ICE_M(0x3FF, 0) +#define PF_SB_ATQBAH 0x0022FC80 +#define PF_SB_ATQBAH_ATQBAH_S 0 +#define PF_SB_ATQBAH_ATQBAH_M ICE_M(0xFFFFFFFF, 0) +#define PF_SB_ATQBAL 0x0022FC00 +#define PF_SB_ATQBAL_ATQBAL_S 6 +#define PF_SB_ATQBAL_ATQBAL_M ICE_M(0x3FFFFFF, 6) +#define PF_SB_ATQH 0x0022FD80 +#define PF_SB_ATQH_ATQH_S 0 +#define PF_SB_ATQH_ATQH_M ICE_M(0x3FF, 0) +#define PF_SB_ATQLEN 0x0022FD00 +#define PF_SB_ATQLEN_ATQLEN_S 0 +#define PF_SB_ATQLEN_ATQLEN_M ICE_M(0x3FF, 0) +#define PF_SB_ATQLEN_ATQVFE_S 28 +#define PF_SB_ATQLEN_ATQVFE_M BIT(28) +#define PF_SB_ATQLEN_ATQOVFL_S 29 +#define PF_SB_ATQLEN_ATQOVFL_M BIT(29) +#define PF_SB_ATQLEN_ATQCRIT_S 30 +#define PF_SB_ATQLEN_ATQCRIT_M BIT(30) +#define PF_SB_ATQLEN_ATQENABLE_S 31 +#define PF_SB_ATQLEN_ATQENABLE_M BIT(31) +#define PF_SB_ATQT 0x0022FE00 +#define PF_SB_ATQT_ATQT_S 0 +#define PF_SB_ATQT_ATQT_M ICE_M(0x3FF, 0) #define PRTDCB_GENC 0x00083000 #define PRTDCB_GENC_PFCLDA_S 16 #define PRTDCB_GENC_PFCLDA_M ICE_M(0xFFFF, 16) @@ -90,6 +138,10 @@ #define GLGEN_CLKSTAT_SRC_PSM_CLK_SRC_S 4 #define GLGEN_CLKSTAT_SRC_PSM_CLK_SRC_M ICE_M(0x3, 4) #define GLGEN_CLKSTAT_SRC 0x000B826C +#define GLGEN_GPIO_CTL(_i) (0x000880C8 + ((_i) * 4)) +#define GLGEN_GPIO_CTL_PIN_DIR_M BIT(4) +#define GLGEN_GPIO_CTL_PIN_FUNC_S 8 +#define GLGEN_GPIO_CTL_PIN_FUNC_M ICE_M(0xF, 8) #define GLGEN_RSTAT 0x000B8188 #define GLGEN_RSTAT_DEVSTATE_M ICE_M(0x3, 0) #define GLGEN_RSTCTL 0x000B8180 @@ -111,8 +163,6 @@ #define VPGEN_VFRSTAT_VFRD_M BIT(0) #define VPGEN_VFRTRIG(_VF) (0x00090000 + ((_VF) * 4)) #define VPGEN_VFRTRIG_VFSWR_M BIT(0) -#define PFHMC_ERRORDATA 0x00520500 -#define PFHMC_ERRORINFO 0x00520400 #define GLINT_CTL 0x0016CC54 #define GLINT_CTL_DIS_AUTOMASK_M BIT(0) #define GLINT_CTL_ITR_GRAN_200_S 16 @@ -156,11 +206,14 @@ #define PFINT_MBX_CTL_ITR_INDX_M ICE_M(0x3, 11) #define PFINT_MBX_CTL_CAUSE_ENA_M BIT(30) #define PFINT_OICR 0x0016CA00 +#define PFINT_OICR_TSYN_TX_M BIT(11) +#define PFINT_OICR_TSYN_EVNT_M BIT(12) #define PFINT_OICR_ECC_ERR_M BIT(16) #define PFINT_OICR_MAL_DETECT_M BIT(19) #define PFINT_OICR_GRST_M BIT(20) #define PFINT_OICR_PCI_EXCEPTION_M BIT(21) #define PFINT_OICR_HMC_ERR_M BIT(26) +#define PFINT_OICR_PE_PUSH_M BIT(27) #define PFINT_OICR_PE_CRITERR_M BIT(28) #define PFINT_OICR_VFLR_M BIT(29) #define PFINT_OICR_SWINT_M BIT(31) @@ -170,6 +223,9 @@ #define PFINT_OICR_CTL_ITR_INDX_M ICE_M(0x3, 11) #define PFINT_OICR_CTL_CAUSE_ENA_M BIT(30) #define PFINT_OICR_ENA 0x0016C900 +#define PFINT_SB_CTL 0x0016B600 +#define PFINT_SB_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) +#define PFINT_SB_CTL_CAUSE_ENA_M BIT(30) #define QINT_RQCTL(_QRX) (0x00150000 + ((_QRX) * 4)) #define QINT_RQCTL_MSIX_INDX_S 0 #define QINT_RQCTL_MSIX_INDX_M ICE_M(0x7FF, 0) @@ -383,6 +439,36 @@ #define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) #define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) #define PRTRPB_RDPC 0x000AC260 +#define GLTSYN_AUX_IN_0(_i) (0x000889D8 + ((_i) * 4)) +#define GLTSYN_AUX_IN_0_INT_ENA_M BIT(4) +#define GLTSYN_AUX_OUT_0(_i) (0x00088998 + ((_i) * 4)) +#define GLTSYN_AUX_OUT_0_OUT_ENA_M BIT(0) +#define GLTSYN_AUX_OUT_0_OUTMOD_M ICE_M(0x3, 1) +#define GLTSYN_CLKO_0(_i) (0x000889B8 + ((_i) * 4)) +#define GLTSYN_CMD 0x00088810 +#define GLTSYN_CMD_SYNC 0x00088814 +#define GLTSYN_ENA(_i) (0x00088808 + ((_i) * 4)) +#define GLTSYN_ENA_TSYN_ENA_M BIT(0) +#define GLTSYN_EVNT_H_0(_i) (0x00088970 + ((_i) * 4)) +#define GLTSYN_EVNT_L_0(_i) (0x00088968 + ((_i) * 4)) +#define GLTSYN_INCVAL_H(_i) (0x00088920 + ((_i) * 4)) +#define GLTSYN_INCVAL_L(_i) (0x00088918 + ((_i) * 4)) +#define GLTSYN_SHADJ_H(_i) (0x00088910 + ((_i) * 4)) +#define GLTSYN_SHADJ_L(_i) (0x00088908 + ((_i) * 4)) +#define GLTSYN_SHTIME_0(_i) (0x000888E0 + ((_i) * 4)) +#define GLTSYN_SHTIME_H(_i) (0x000888F0 + ((_i) * 4)) +#define GLTSYN_SHTIME_L(_i) (0x000888E8 + ((_i) * 4)) +#define GLTSYN_STAT(_i) (0x000888C0 + ((_i) * 4)) +#define GLTSYN_STAT_EVENT0_M BIT(0) +#define GLTSYN_STAT_EVENT1_M BIT(1) +#define GLTSYN_STAT_EVENT2_M BIT(2) +#define GLTSYN_SYNC_DLAY 0x00088818 +#define GLTSYN_TGT_H_0(_i) (0x00088930 + ((_i) * 4)) +#define GLTSYN_TGT_L_0(_i) (0x00088928 + ((_i) * 4)) +#define GLTSYN_TIME_H(_i) (0x000888D8 + ((_i) * 4)) +#define GLTSYN_TIME_L(_i) (0x000888D0 + ((_i) * 4)) +#define PFTSYN_SEM 0x00088880 +#define PFTSYN_SEM_BUSY_M BIT(0) #define VSIQF_FD_CNT(_VSI) (0x00464000 + ((_VSI) * 4)) #define VSIQF_FD_CNT_FD_GCNT_S 0 #define VSIQF_FD_CNT_FD_GCNT_M ICE_M(0x3FFF, 0) diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c new file mode 100644 index 000000000000..1f2afdf6cd48 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -0,0 +1,334 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021, Intel Corporation. */ + +/* Inter-Driver Communication */ +#include "ice.h" +#include "ice_lib.h" +#include "ice_dcb_lib.h" + +/** + * ice_get_auxiliary_drv - retrieve iidc_auxiliary_drv struct + * @pf: pointer to PF struct + * + * This function has to be called with a device_lock on the + * pf->adev.dev to avoid race conditions. + */ +static struct iidc_auxiliary_drv *ice_get_auxiliary_drv(struct ice_pf *pf) +{ + struct auxiliary_device *adev; + + adev = pf->adev; + if (!adev || !adev->dev.driver) + return NULL; + + return container_of(adev->dev.driver, struct iidc_auxiliary_drv, + adrv.driver); +} + +/** + * ice_send_event_to_aux - send event to RDMA AUX driver + * @pf: pointer to PF struct + * @event: event struct + */ +void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event) +{ + struct iidc_auxiliary_drv *iadrv; + + if (!pf->adev) + return; + + device_lock(&pf->adev->dev); + iadrv = ice_get_auxiliary_drv(pf); + if (iadrv && iadrv->event_handler) + iadrv->event_handler(pf, event); + device_unlock(&pf->adev->dev); +} + +/** + * ice_find_vsi - Find the VSI from VSI ID + * @pf: The PF pointer to search in + * @vsi_num: The VSI ID to search for + */ +static struct ice_vsi *ice_find_vsi(struct ice_pf *pf, u16 vsi_num) +{ + int i; + + ice_for_each_vsi(pf, i) + if (pf->vsi[i] && pf->vsi[i]->vsi_num == vsi_num) + return pf->vsi[i]; + return NULL; +} + +/** + * ice_add_rdma_qset - Add Leaf Node for RDMA Qset + * @pf: PF struct + * @qset: Resource to be allocated + */ +int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) +{ + u16 max_rdmaqs[ICE_MAX_TRAFFIC_CLASS]; + struct ice_vsi *vsi; + struct device *dev; + u32 qset_teid; + u16 qs_handle; + int status; + int i; + + if (WARN_ON(!pf || !qset)) + return -EINVAL; + + dev = ice_pf_to_dev(pf); + + if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + return -EINVAL; + + vsi = ice_get_main_vsi(pf); + if (!vsi) { + dev_err(dev, "RDMA QSet invalid VSI\n"); + return -EINVAL; + } + + ice_for_each_traffic_class(i) + max_rdmaqs[i] = 0; + + max_rdmaqs[qset->tc]++; + qs_handle = qset->qs_handle; + + status = ice_cfg_vsi_rdma(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, + max_rdmaqs); + if (status) { + dev_err(dev, "Failed VSI RDMA Qset config\n"); + return status; + } + + status = ice_ena_vsi_rdma_qset(vsi->port_info, vsi->idx, qset->tc, + &qs_handle, 1, &qset_teid); + if (status) { + dev_err(dev, "Failed VSI RDMA Qset enable\n"); + return status; + } + vsi->qset_handle[qset->tc] = qset->qs_handle; + qset->teid = qset_teid; + + return 0; +} +EXPORT_SYMBOL_GPL(ice_add_rdma_qset); + +/** + * ice_del_rdma_qset - Delete leaf node for RDMA Qset + * @pf: PF struct + * @qset: Resource to be freed + */ +int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset) +{ + struct ice_vsi *vsi; + u32 teid; + u16 q_id; + + if (WARN_ON(!pf || !qset)) + return -EINVAL; + + vsi = ice_find_vsi(pf, qset->vport_id); + if (!vsi) { + dev_err(ice_pf_to_dev(pf), "RDMA Invalid VSI\n"); + return -EINVAL; + } + + q_id = qset->qs_handle; + teid = qset->teid; + + vsi->qset_handle[qset->tc] = 0; + + return ice_dis_vsi_rdma_qset(vsi->port_info, 1, &teid, &q_id); +} +EXPORT_SYMBOL_GPL(ice_del_rdma_qset); + +/** + * ice_rdma_request_reset - accept request from RDMA to perform a reset + * @pf: struct for PF + * @reset_type: type of reset + */ +int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type) +{ + enum ice_reset_req reset; + + if (WARN_ON(!pf)) + return -EINVAL; + + switch (reset_type) { + case IIDC_PFR: + reset = ICE_RESET_PFR; + break; + case IIDC_CORER: + reset = ICE_RESET_CORER; + break; + case IIDC_GLOBR: + reset = ICE_RESET_GLOBR; + break; + default: + dev_err(ice_pf_to_dev(pf), "incorrect reset request\n"); + return -EINVAL; + } + + return ice_schedule_reset(pf, reset); +} +EXPORT_SYMBOL_GPL(ice_rdma_request_reset); + +/** + * ice_rdma_update_vsi_filter - update main VSI filters for RDMA + * @pf: pointer to struct for PF + * @vsi_id: VSI HW idx to update filter on + * @enable: bool whether to enable or disable filters + */ +int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable) +{ + struct ice_vsi *vsi; + int status; + + if (WARN_ON(!pf)) + return -EINVAL; + + vsi = ice_find_vsi(pf, vsi_id); + if (!vsi) + return -EINVAL; + + status = ice_cfg_rdma_fltr(&pf->hw, vsi->idx, enable); + if (status) { + dev_err(ice_pf_to_dev(pf), "Failed to %sable RDMA filtering\n", + enable ? "en" : "dis"); + } else { + if (enable) + vsi->info.q_opt_flags |= ICE_AQ_VSI_Q_OPT_PE_FLTR_EN; + else + vsi->info.q_opt_flags &= ~ICE_AQ_VSI_Q_OPT_PE_FLTR_EN; + } + + return status; +} +EXPORT_SYMBOL_GPL(ice_rdma_update_vsi_filter); + +/** + * ice_get_qos_params - parse QoS params for RDMA consumption + * @pf: pointer to PF struct + * @qos: set of QoS values + */ +void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos) +{ + struct ice_dcbx_cfg *dcbx_cfg; + unsigned int i; + u32 up2tc; + + dcbx_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; + up2tc = rd32(&pf->hw, PRTDCB_TUP2TC); + + qos->num_tc = ice_dcb_get_num_tc(dcbx_cfg); + for (i = 0; i < IIDC_MAX_USER_PRIORITY; i++) + qos->up2tc[i] = (up2tc >> (i * 3)) & 0x7; + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + qos->tc_info[i].rel_bw = dcbx_cfg->etscfg.tcbwtable[i]; +} +EXPORT_SYMBOL_GPL(ice_get_qos_params); + +/** + * ice_reserve_rdma_qvector - Reserve vector resources for RDMA driver + * @pf: board private structure to initialize + */ +static int ice_reserve_rdma_qvector(struct ice_pf *pf) +{ + if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) { + int index; + + index = ice_get_res(pf, pf->irq_tracker, pf->num_rdma_msix, + ICE_RES_RDMA_VEC_ID); + if (index < 0) + return index; + pf->num_avail_sw_msix -= pf->num_rdma_msix; + pf->rdma_base_vector = (u16)index; + } + return 0; +} + +/** + * ice_adev_release - function to be mapped to AUX dev's release op + * @dev: pointer to device to free + */ +static void ice_adev_release(struct device *dev) +{ + struct iidc_auxiliary_dev *iadev; + + iadev = container_of(dev, struct iidc_auxiliary_dev, adev.dev); + kfree(iadev); +} + +/** + * ice_plug_aux_dev - allocate and register AUX device + * @pf: pointer to pf struct + */ +int ice_plug_aux_dev(struct ice_pf *pf) +{ + struct iidc_auxiliary_dev *iadev; + struct auxiliary_device *adev; + int ret; + + iadev = kzalloc(sizeof(*iadev), GFP_KERNEL); + if (!iadev) + return -ENOMEM; + + adev = &iadev->adev; + pf->adev = adev; + iadev->pf = pf; + + adev->id = pf->aux_idx; + adev->dev.release = ice_adev_release; + adev->dev.parent = &pf->pdev->dev; + adev->name = IIDC_RDMA_ROCE_NAME; + + ret = auxiliary_device_init(adev); + if (ret) { + pf->adev = NULL; + kfree(iadev); + return ret; + } + + ret = auxiliary_device_add(adev); + if (ret) { + pf->adev = NULL; + auxiliary_device_uninit(adev); + return ret; + } + + return 0; +} + +/* ice_unplug_aux_dev - unregister and free AUX device + * @pf: pointer to pf struct + */ +void ice_unplug_aux_dev(struct ice_pf *pf) +{ + if (!pf->adev) + return; + + auxiliary_device_delete(pf->adev); + auxiliary_device_uninit(pf->adev); + pf->adev = NULL; +} + +/** + * ice_init_rdma - initializes PF for RDMA use + * @pf: ptr to ice_pf + */ +int ice_init_rdma(struct ice_pf *pf) +{ + struct device *dev = &pf->pdev->dev; + int ret; + + /* Reserve vector resources */ + ret = ice_reserve_rdma_qvector(pf); + if (ret < 0) { + dev_err(dev, "failed to reserve vectors for RDMA\n"); + return ret; + } + + return ice_plug_aux_dev(pf); +} diff --git a/drivers/net/ethernet/intel/ice/ice_idc_int.h b/drivers/net/ethernet/intel/ice/ice_idc_int.h new file mode 100644 index 000000000000..b7796b8aecbd --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_idc_int.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2021, Intel Corporation. */ + +#ifndef _ICE_IDC_INT_H_ +#define _ICE_IDC_INT_H_ + +#include +#include "ice.h" + +struct ice_pf; + +void ice_send_event_to_aux(struct ice_pf *pf, struct iidc_event *event); + +#endif /* !_ICE_IDC_INT_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 4599fc3b4ed8..37c18c66b5c7 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -172,6 +172,7 @@ ice_lag_link(struct ice_lag *lag, struct netdev_notifier_changeupper_info *info) } ice_clear_sriov_cap(pf); + ice_clear_rdma_cap(pf); lag->bonded = true; lag->role = ICE_LAG_UNSET; @@ -222,6 +223,7 @@ ice_lag_unlink(struct ice_lag *lag, } ice_set_sriov_cap(pf); + ice_set_rdma_cap(pf); lag->bonded = false; lag->role = ICE_LAG_NONE; } diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 21329ed3087e..80736e0ec0dc 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -161,7 +161,6 @@ struct ice_fltr_desc { #define ICE_FXD_FLTR_WB_QW1_FAIL_PROF_YES 0x1ULL struct ice_rx_ptype_decoded { - u32 ptype:10; u32 known:1; u32 outer_ip:1; u32 outer_ip_ver:2; @@ -606,9 +605,32 @@ struct ice_tlan_ctx { u8 int_q_state; /* width not needed - internal - DO NOT WRITE!!! */ }; -/* macro to make the table lines short */ +/* The ice_ptype_lkup table is used to convert from the 10-bit ptype in the + * hardware to a bit-field that can be used by SW to more easily determine the + * packet type. + * + * Macros are used to shorten the table lines and make this table human + * readable. + * + * We store the PTYPE in the top byte of the bit field - this is just so that + * we can check that the table doesn't have a row missing, as the index into + * the table should be the PTYPE. + * + * Typical work flow: + * + * IF NOT ice_ptype_lkup[ptype].known + * THEN + * Packet is unknown + * ELSE IF ice_ptype_lkup[ptype].outer_ip == ICE_RX_PTYPE_OUTER_IP + * Use the rest of the fields to look at the tunnels, inner protocols, etc + * ELSE + * Use the enum ice_rx_l2_ptype to decode the packet type + * ENDIF + */ + +/* macro to make the table lines short, use explicit indexing with [PTYPE] */ #define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ - { PTYPE, \ + [PTYPE] = { \ 1, \ ICE_RX_PTYPE_OUTER_##OUTER_IP, \ ICE_RX_PTYPE_OUTER_##OUTER_IP_VER, \ @@ -619,18 +641,18 @@ struct ice_tlan_ctx { ICE_RX_PTYPE_INNER_PROT_##I, \ ICE_RX_PTYPE_PAYLOAD_LAYER_##PL } -#define ICE_PTT_UNUSED_ENTRY(PTYPE) { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 } +#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } /* shorter macros makes the table fit but are terse */ #define ICE_RX_PTYPE_NOF ICE_RX_PTYPE_NOT_FRAG #define ICE_RX_PTYPE_FRG ICE_RX_PTYPE_FRAG -/* Lookup table mapping the HW PTYPE to the bit field for decoding */ -static const struct ice_rx_ptype_decoded ice_ptype_lkup[] = { +/* Lookup table mapping in the 10-bit HW PTYPE to the bit field for decoding */ +static const struct ice_rx_ptype_decoded ice_ptype_lkup[BIT(10)] = { /* L2 Packet types */ ICE_PTT_UNUSED_ENTRY(0), ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - ICE_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), + ICE_PTT_UNUSED_ENTRY(2), ICE_PTT_UNUSED_ENTRY(3), ICE_PTT_UNUSED_ENTRY(4), ICE_PTT_UNUSED_ENTRY(5), @@ -744,7 +766,7 @@ static const struct ice_rx_ptype_decoded ice_ptype_lkup[] = { /* Non Tunneled IPv6 */ ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), - ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3), + ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY4), ICE_PTT_UNUSED_ENTRY(91), ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), @@ -832,118 +854,7 @@ static const struct ice_rx_ptype_decoded ice_ptype_lkup[] = { ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), /* unused entries */ - ICE_PTT_UNUSED_ENTRY(154), - ICE_PTT_UNUSED_ENTRY(155), - ICE_PTT_UNUSED_ENTRY(156), - ICE_PTT_UNUSED_ENTRY(157), - ICE_PTT_UNUSED_ENTRY(158), - ICE_PTT_UNUSED_ENTRY(159), - - ICE_PTT_UNUSED_ENTRY(160), - ICE_PTT_UNUSED_ENTRY(161), - ICE_PTT_UNUSED_ENTRY(162), - ICE_PTT_UNUSED_ENTRY(163), - ICE_PTT_UNUSED_ENTRY(164), - ICE_PTT_UNUSED_ENTRY(165), - ICE_PTT_UNUSED_ENTRY(166), - ICE_PTT_UNUSED_ENTRY(167), - ICE_PTT_UNUSED_ENTRY(168), - ICE_PTT_UNUSED_ENTRY(169), - - ICE_PTT_UNUSED_ENTRY(170), - ICE_PTT_UNUSED_ENTRY(171), - ICE_PTT_UNUSED_ENTRY(172), - ICE_PTT_UNUSED_ENTRY(173), - ICE_PTT_UNUSED_ENTRY(174), - ICE_PTT_UNUSED_ENTRY(175), - ICE_PTT_UNUSED_ENTRY(176), - ICE_PTT_UNUSED_ENTRY(177), - ICE_PTT_UNUSED_ENTRY(178), - ICE_PTT_UNUSED_ENTRY(179), - - ICE_PTT_UNUSED_ENTRY(180), - ICE_PTT_UNUSED_ENTRY(181), - ICE_PTT_UNUSED_ENTRY(182), - ICE_PTT_UNUSED_ENTRY(183), - ICE_PTT_UNUSED_ENTRY(184), - ICE_PTT_UNUSED_ENTRY(185), - ICE_PTT_UNUSED_ENTRY(186), - ICE_PTT_UNUSED_ENTRY(187), - ICE_PTT_UNUSED_ENTRY(188), - ICE_PTT_UNUSED_ENTRY(189), - - ICE_PTT_UNUSED_ENTRY(190), - ICE_PTT_UNUSED_ENTRY(191), - ICE_PTT_UNUSED_ENTRY(192), - ICE_PTT_UNUSED_ENTRY(193), - ICE_PTT_UNUSED_ENTRY(194), - ICE_PTT_UNUSED_ENTRY(195), - ICE_PTT_UNUSED_ENTRY(196), - ICE_PTT_UNUSED_ENTRY(197), - ICE_PTT_UNUSED_ENTRY(198), - ICE_PTT_UNUSED_ENTRY(199), - - ICE_PTT_UNUSED_ENTRY(200), - ICE_PTT_UNUSED_ENTRY(201), - ICE_PTT_UNUSED_ENTRY(202), - ICE_PTT_UNUSED_ENTRY(203), - ICE_PTT_UNUSED_ENTRY(204), - ICE_PTT_UNUSED_ENTRY(205), - ICE_PTT_UNUSED_ENTRY(206), - ICE_PTT_UNUSED_ENTRY(207), - ICE_PTT_UNUSED_ENTRY(208), - ICE_PTT_UNUSED_ENTRY(209), - - ICE_PTT_UNUSED_ENTRY(210), - ICE_PTT_UNUSED_ENTRY(211), - ICE_PTT_UNUSED_ENTRY(212), - ICE_PTT_UNUSED_ENTRY(213), - ICE_PTT_UNUSED_ENTRY(214), - ICE_PTT_UNUSED_ENTRY(215), - ICE_PTT_UNUSED_ENTRY(216), - ICE_PTT_UNUSED_ENTRY(217), - ICE_PTT_UNUSED_ENTRY(218), - ICE_PTT_UNUSED_ENTRY(219), - - ICE_PTT_UNUSED_ENTRY(220), - ICE_PTT_UNUSED_ENTRY(221), - ICE_PTT_UNUSED_ENTRY(222), - ICE_PTT_UNUSED_ENTRY(223), - ICE_PTT_UNUSED_ENTRY(224), - ICE_PTT_UNUSED_ENTRY(225), - ICE_PTT_UNUSED_ENTRY(226), - ICE_PTT_UNUSED_ENTRY(227), - ICE_PTT_UNUSED_ENTRY(228), - ICE_PTT_UNUSED_ENTRY(229), - - ICE_PTT_UNUSED_ENTRY(230), - ICE_PTT_UNUSED_ENTRY(231), - ICE_PTT_UNUSED_ENTRY(232), - ICE_PTT_UNUSED_ENTRY(233), - ICE_PTT_UNUSED_ENTRY(234), - ICE_PTT_UNUSED_ENTRY(235), - ICE_PTT_UNUSED_ENTRY(236), - ICE_PTT_UNUSED_ENTRY(237), - ICE_PTT_UNUSED_ENTRY(238), - ICE_PTT_UNUSED_ENTRY(239), - - ICE_PTT_UNUSED_ENTRY(240), - ICE_PTT_UNUSED_ENTRY(241), - ICE_PTT_UNUSED_ENTRY(242), - ICE_PTT_UNUSED_ENTRY(243), - ICE_PTT_UNUSED_ENTRY(244), - ICE_PTT_UNUSED_ENTRY(245), - ICE_PTT_UNUSED_ENTRY(246), - ICE_PTT_UNUSED_ENTRY(247), - ICE_PTT_UNUSED_ENTRY(248), - ICE_PTT_UNUSED_ENTRY(249), - - ICE_PTT_UNUSED_ENTRY(250), - ICE_PTT_UNUSED_ENTRY(251), - ICE_PTT_UNUSED_ENTRY(252), - ICE_PTT_UNUSED_ENTRY(253), - ICE_PTT_UNUSED_ENTRY(254), - ICE_PTT_UNUSED_ENTRY(255), + [154 ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } }; static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 27f9dac8719c..dde9802c6c72 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -169,12 +169,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) switch (vsi->type) { case ICE_VSI_PF: - vsi->alloc_txq = min3(pf->num_lan_msix, - ice_get_avail_txq_count(pf), - (u16)num_online_cpus()); if (vsi->req_txq) { vsi->alloc_txq = vsi->req_txq; vsi->num_txq = vsi->req_txq; + } else { + vsi->alloc_txq = min3(pf->num_lan_msix, + ice_get_avail_txq_count(pf), + (u16)num_online_cpus()); } pf->num_lan_tx = vsi->alloc_txq; @@ -183,12 +184,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { vsi->alloc_rxq = 1; } else { - vsi->alloc_rxq = min3(pf->num_lan_msix, - ice_get_avail_rxq_count(pf), - (u16)num_online_cpus()); if (vsi->req_rxq) { vsi->alloc_rxq = vsi->req_rxq; vsi->num_rxq = vsi->req_rxq; + } else { + vsi->alloc_rxq = min3(pf->num_lan_msix, + ice_get_avail_rxq_count(pf), + (u16)num_online_cpus()); } } @@ -628,6 +630,17 @@ bool ice_is_safe_mode(struct ice_pf *pf) return !test_bit(ICE_FLAG_ADV_FEATURES, pf->flags); } +/** + * ice_is_aux_ena + * @pf: pointer to the PF struct + * + * returns true if AUX devices/drivers are supported, false otherwise + */ +bool ice_is_aux_ena(struct ice_pf *pf) +{ + return test_bit(ICE_FLAG_AUX_ENA, pf->flags); +} + /** * ice_vsi_clean_rss_flow_fld - Delete RSS configuration * @vsi: the VSI being cleaned up @@ -1192,11 +1205,11 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) num_q_vectors = vsi->num_q_vectors; /* reserve slots from OS requested IRQs */ if (vsi->type == ICE_VSI_CTRL && vsi->vf_id != ICE_INVAL_VFID) { - struct ice_vf *vf; int i; ice_for_each_vf(pf, i) { - vf = &pf->vf[i]; + struct ice_vf *vf = &pf->vf[i]; + if (i != vsi->vf_id && vf->ctrl_vsi_idx != ICE_NO_VSI) { base = pf->vsi[vf->ctrl_vsi_idx]->base_vector; break; @@ -1285,6 +1298,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->reg_idx = vsi->txq_map[i]; ring->ring_active = false; ring->vsi = vsi; + ring->tx_tstamps = &pf->ptp.port.tx; ring->dev = dev; ring->count = vsi->num_tx_desc; WRITE_ONCE(vsi->tx_rings[i], ring); @@ -1662,9 +1676,11 @@ void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) * @pf_q: index of the Rx queue in the PF's queue space * @rxdid: flexible descriptor RXDID * @prio: priority for the RXDID for this queue + * @ena_ts: true to enable timestamp and false to disable timestamp */ void -ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio) +ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, + bool ena_ts) { int regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); @@ -1679,9 +1695,40 @@ ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio) regval |= (prio << QRXFLXP_CNTXT_RXDID_PRIO_S) & QRXFLXP_CNTXT_RXDID_PRIO_M; + if (ena_ts) + /* Enable TimeSync on this queue */ + regval |= QRXFLXP_CNTXT_TS_M; + wr32(hw, QRXFLXP_CNTXT(pf_q), regval); } +int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) +{ + if (q_idx >= vsi->num_rxq) + return -EINVAL; + + return ice_vsi_cfg_rxq(vsi->rx_rings[q_idx]); +} + +int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_ring **tx_rings, u16 q_idx) +{ + struct ice_aqc_add_tx_qgrp *qg_buf; + int err; + + if (q_idx >= vsi->alloc_txq || !tx_rings || !tx_rings[q_idx]) + return -EINVAL; + + qg_buf = kzalloc(struct_size(qg_buf, txqs, 1), GFP_KERNEL); + if (!qg_buf) + return -ENOMEM; + + qg_buf->num_txqs = 1; + + err = ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf); + kfree(qg_buf); + return err; +} + /** * ice_vsi_cfg_rxqs - Configure the VSI for Rx * @vsi: the VSI being configured @@ -1699,15 +1746,11 @@ int ice_vsi_cfg_rxqs(struct ice_vsi *vsi) ice_vsi_cfg_frame_size(vsi); setup_rings: /* set up individual rings */ - for (i = 0; i < vsi->num_rxq; i++) { - int err; + ice_for_each_rxq(vsi, i) { + int err = ice_vsi_cfg_rxq(vsi->rx_rings[i]); - err = ice_setup_rx_ctx(vsi->rx_rings[i]); - if (err) { - dev_err(ice_pf_to_dev(vsi->back), "ice_setup_rx_ctx failed for RxQ %d, err %d\n", - i, err); + if (err) return err; - } } return 0; @@ -2217,7 +2260,7 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create) } if (status) - dev_err(dev, "Fail %s %s LLDP rule on VSI %i error: %s\n", + dev_dbg(dev, "Fail %s %s LLDP rule on VSI %i error: %s\n", create ? "adding" : "removing", tx ? "TX" : "RX", vsi->vsi_num, ice_stat_str(status)); } @@ -2832,11 +2875,11 @@ int ice_vsi_release(struct ice_vsi *vsi) * cleared in the same manner. */ if (vsi->type == ICE_VSI_CTRL && vsi->vf_id != ICE_INVAL_VFID) { - struct ice_vf *vf; int i; ice_for_each_vf(pf, i) { - vf = &pf->vf[i]; + struct ice_vf *vf = &pf->vf[i]; + if (i != vsi->vf_id && vf->ctrl_vsi_idx != ICE_NO_VSI) break; } @@ -3196,6 +3239,34 @@ bool ice_is_reset_in_progress(unsigned long *state) test_bit(ICE_GLOBR_REQ, state); } +/** + * ice_wait_for_reset - Wait for driver to finish reset and rebuild + * @pf: pointer to the PF structure + * @timeout: length of time to wait, in jiffies + * + * Wait (sleep) for a short time until the driver finishes cleaning up from + * a device reset. The caller must be able to sleep. Use this to delay + * operations that could fail while the driver is cleaning up after a device + * reset. + * + * Returns 0 on success, -EBUSY if the reset is not finished within the + * timeout, and -ERESTARTSYS if the thread was interrupted. + */ +int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout) +{ + long ret; + + ret = wait_event_interruptible_timeout(pf->reset_wait_queue, + !ice_is_reset_in_progress(pf->state), + timeout); + if (ret < 0) + return ret; + else if (!ret) + return -EBUSY; + else + return 0; +} + #ifdef CONFIG_DCB /** * ice_vsi_update_q_map - update our copy of the VSI info with new queue map @@ -3330,13 +3401,22 @@ int ice_status_to_errno(enum ice_status err) case ICE_ERR_DOES_NOT_EXIST: return -ENOENT; case ICE_ERR_OUT_OF_RANGE: - return -ENOTTY; + case ICE_ERR_AQ_ERROR: + case ICE_ERR_AQ_TIMEOUT: + case ICE_ERR_AQ_EMPTY: + case ICE_ERR_AQ_FW_CRITICAL: + return -EIO; case ICE_ERR_PARAM: + case ICE_ERR_INVAL_SIZE: return -EINVAL; case ICE_ERR_NO_MEMORY: return -ENOMEM; case ICE_ERR_MAX_LIMIT: return -EAGAIN; + case ICE_ERR_RESET_ONGOING: + return -EBUSY; + case ICE_ERR_AQ_FULL: + return -ENOSPC; default: return -EINVAL; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 511c2316c40c..d5a28bf0fc2c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -12,6 +12,10 @@ bool ice_pf_state_is_nominal(struct ice_pf *pf); void ice_update_eth_stats(struct ice_vsi *vsi); +int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx); + +int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_ring **tx_rings, u16 q_idx); + int ice_vsi_cfg_rxqs(struct ice_vsi *vsi); int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi); @@ -73,9 +77,11 @@ ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id); int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi); bool ice_is_reset_in_progress(unsigned long *state); +int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout); void -ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio); +ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, + bool ena_ts); void ice_vsi_dis_irq(struct ice_vsi *vsi); @@ -102,7 +108,7 @@ enum ice_status ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set); bool ice_is_safe_mode(struct ice_pf *pf); - +bool ice_is_aux_ena(struct ice_pf *pf); bool ice_is_dflt_vsi_in_use(struct ice_sw *sw); bool ice_is_vsi_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 0eb2307325d3..ef8d1815af56 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -13,6 +13,12 @@ #include "ice_dcb_lib.h" #include "ice_dcb_nl.h" #include "ice_devlink.h" +/* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the + * ice tracepoint functions. This must be done exactly once across the + * ice driver. + */ +#define CREATE_TRACE_POINTS +#include "ice_trace.h" #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" static const char ice_driver_string[] = DRV_SUMMARY; @@ -35,6 +41,8 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all), hw debug_mask (0x8XXXX MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)"); #endif /* !CONFIG_DYNAMIC_DEBUG */ +static DEFINE_IDA(ice_aux_ida); + static struct workqueue_struct *ice_wq; static const struct net_device_ops ice_netdev_safe_mode_ops; static const struct net_device_ops ice_netdev_ops; @@ -454,6 +462,8 @@ ice_prepare_for_reset(struct ice_pf *pf) if (test_bit(ICE_PREPARED_FOR_RESET, pf->state)) return; + ice_unplug_aux_dev(pf); + /* Notify VFs of impending reset */ if (ice_check_sq_alive(hw, &hw->mailboxq)) ice_vc_notify_reset(pf); @@ -467,6 +477,9 @@ ice_prepare_for_reset(struct ice_pf *pf) /* disable the VSIs and their queues that are not already DOWN */ ice_pf_dis_all_vsi(pf, false); + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) + ice_ptp_release(pf); + if (hw->port_info) ice_sched_clear_port(hw->port_info); @@ -499,6 +512,7 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) clear_bit(ICE_PFR_REQ, pf->state); clear_bit(ICE_CORER_REQ, pf->state); clear_bit(ICE_GLOBR_REQ, pf->state); + wake_up(&pf->reset_wait_queue); return; } @@ -511,6 +525,7 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) ice_rebuild(pf, reset_type); clear_bit(ICE_PREPARED_FOR_RESET, pf->state); clear_bit(ICE_PFR_REQ, pf->state); + wake_up(&pf->reset_wait_queue); ice_reset_all_vfs(pf, true); } } @@ -561,6 +576,7 @@ static void ice_reset_subtask(struct ice_pf *pf) clear_bit(ICE_PFR_REQ, pf->state); clear_bit(ICE_CORER_REQ, pf->state); clear_bit(ICE_GLOBR_REQ, pf->state); + wake_up(&pf->reset_wait_queue); ice_reset_all_vfs(pf, true); } @@ -857,6 +873,38 @@ static void ice_set_dflt_mib(struct ice_pf *pf) kfree(lldpmib); } +/** + * ice_check_module_power + * @pf: pointer to PF struct + * @link_cfg_err: bitmap from the link info structure + * + * check module power level returned by a previous call to aq_get_link_info + * and print error messages if module power level is not supported + */ +static void ice_check_module_power(struct ice_pf *pf, u8 link_cfg_err) +{ + /* if module power level is supported, clear the flag */ + if (!(link_cfg_err & (ICE_AQ_LINK_INVAL_MAX_POWER_LIMIT | + ICE_AQ_LINK_MODULE_POWER_UNSUPPORTED))) { + clear_bit(ICE_FLAG_MOD_POWER_UNSUPPORTED, pf->flags); + return; + } + + /* if ICE_FLAG_MOD_POWER_UNSUPPORTED was previously set and the + * above block didn't clear this bit, there's nothing to do + */ + if (test_bit(ICE_FLAG_MOD_POWER_UNSUPPORTED, pf->flags)) + return; + + if (link_cfg_err & ICE_AQ_LINK_INVAL_MAX_POWER_LIMIT) { + dev_err(ice_pf_to_dev(pf), "The installed module is incompatible with the device's NVM image. Cannot start link\n"); + set_bit(ICE_FLAG_MOD_POWER_UNSUPPORTED, pf->flags); + } else if (link_cfg_err & ICE_AQ_LINK_MODULE_POWER_UNSUPPORTED) { + dev_err(ice_pf_to_dev(pf), "The module's power requirements exceed the device's power supply. Cannot start link\n"); + set_bit(ICE_FLAG_MOD_POWER_UNSUPPORTED, pf->flags); + } +} + /** * ice_link_event - process the link event * @pf: PF that the link event is associated with @@ -892,6 +940,8 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, pi->lport, ice_stat_str(status), ice_aq_str(pi->hw->adminq.sq_last_status)); + ice_check_module_power(pf, pi->phy.link_info.link_cfg_err); + /* Check if the link state is up after updating link info, and treat * this event as an UP event since the link is actually UP now. */ @@ -1190,6 +1240,10 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) cq = &hw->adminq; qtype = "Admin"; break; + case ICE_CTL_Q_SB: + cq = &hw->sbq; + qtype = "Sideband"; + break; case ICE_CTL_Q_MAILBOX: cq = &hw->mailboxq; qtype = "Mailbox"; @@ -1363,6 +1417,34 @@ static void ice_clean_mailboxq_subtask(struct ice_pf *pf) ice_flush(hw); } +/** + * ice_clean_sbq_subtask - clean the Sideband Queue rings + * @pf: board private structure + */ +static void ice_clean_sbq_subtask(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + + /* Nothing to do here if sideband queue is not supported */ + if (!ice_is_sbq_supported(hw)) { + clear_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state); + return; + } + + if (!test_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state)) + return; + + if (__ice_clean_ctrlq(pf, ICE_CTL_Q_SB)) + return; + + clear_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state); + + if (ice_ctrlq_pending(hw, &hw->sbq)) + __ice_clean_ctrlq(pf, ICE_CTL_Q_SB); + + ice_flush(hw); +} + /** * ice_service_task_schedule - schedule the service task to wake up * @pf: board private structure @@ -2006,6 +2088,8 @@ static void ice_check_media_subtask(struct ice_pf *pf) if (err) return; + ice_check_module_power(pf, pi->phy.link_info.link_cfg_err); + if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { if (!test_bit(ICE_PHY_INIT_COMPLETE, pf->state)) ice_init_phy_user_cfg(pi); @@ -2063,6 +2147,7 @@ static void ice_service_task(struct work_struct *work) ice_process_vflr_event(pf); ice_clean_mailboxq_subtask(pf); + ice_clean_sbq_subtask(pf); ice_sync_arfs_fltrs(pf); ice_flush_fdir_ctx(pf); @@ -2078,6 +2163,7 @@ static void ice_service_task(struct work_struct *work) test_bit(ICE_VFLR_EVENT_PENDING, pf->state) || test_bit(ICE_MAILBOXQ_EVENT_PENDING, pf->state) || test_bit(ICE_FD_VF_FLUSH_CTX, pf->state) || + test_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state) || test_bit(ICE_ADMINQ_EVENT_PENDING, pf->state)) mod_timer(&pf->serv_tmr, jiffies); } @@ -2096,6 +2182,10 @@ static void ice_set_ctrlq_len(struct ice_hw *hw) hw->mailboxq.num_sq_entries = ICE_MBXSQ_LEN; hw->mailboxq.rq_buf_size = ICE_MBXQ_MAX_BUF_LEN; hw->mailboxq.sq_buf_size = ICE_MBXQ_MAX_BUF_LEN; + hw->sbq.num_rq_entries = ICE_SBQ_LEN; + hw->sbq.num_sq_entries = ICE_SBQ_LEN; + hw->sbq.rq_buf_size = ICE_SBQ_MAX_BUF_LEN; + hw->sbq.sq_buf_size = ICE_SBQ_MAX_BUF_LEN; } /** @@ -2118,6 +2208,8 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset) return -EBUSY; } + ice_unplug_aux_dev(pf); + switch (reset) { case ICE_RESET_PFR: set_bit(ICE_PFR_REQ, pf->state); @@ -2622,6 +2714,7 @@ static void ice_ena_misc_vector(struct ice_pf *pf) PFINT_OICR_PCI_EXCEPTION_M | PFINT_OICR_VFLR_M | PFINT_OICR_HMC_ERR_M | + PFINT_OICR_PE_PUSH_M | PFINT_OICR_PE_CRITERR_M); wr32(hw, PFINT_OICR_ENA, val); @@ -2647,6 +2740,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) dev = ice_pf_to_dev(pf); set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state); set_bit(ICE_MAILBOXQ_EVENT_PENDING, pf->state); + set_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state); oicr = rd32(hw, PFINT_OICR); ena_mask = rd32(hw, PFINT_OICR_ENA); @@ -2692,8 +2786,6 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) /* If a reset cycle isn't already in progress, we set a bit in * pf->state so that the service task can start a reset/rebuild. - * We also make note of which reset happened so that peer - * devices/drivers can be informed. */ if (!test_and_set_bit(ICE_RESET_OICR_RECV, pf->state)) { if (reset == ICE_RESET_CORER) @@ -2720,11 +2812,36 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) } } - if (oicr & PFINT_OICR_HMC_ERR_M) { - ena_mask &= ~PFINT_OICR_HMC_ERR_M; - dev_dbg(dev, "HMC Error interrupt - info 0x%x, data 0x%x\n", - rd32(hw, PFHMC_ERRORINFO), - rd32(hw, PFHMC_ERRORDATA)); + if (oicr & PFINT_OICR_TSYN_TX_M) { + ena_mask &= ~PFINT_OICR_TSYN_TX_M; + ice_ptp_process_ts(pf); + } + + if (oicr & PFINT_OICR_TSYN_EVNT_M) { + u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + u32 gltsyn_stat = rd32(hw, GLTSYN_STAT(tmr_idx)); + + /* Save EVENTs from GTSYN register */ + pf->ptp.ext_ts_irq |= gltsyn_stat & (GLTSYN_STAT_EVENT0_M | + GLTSYN_STAT_EVENT1_M | + GLTSYN_STAT_EVENT2_M); + ena_mask &= ~PFINT_OICR_TSYN_EVNT_M; + kthread_queue_work(pf->ptp.kworker, &pf->ptp.extts_work); + } + +#define ICE_AUX_CRIT_ERR (PFINT_OICR_PE_CRITERR_M | PFINT_OICR_HMC_ERR_M | PFINT_OICR_PE_PUSH_M) + if (oicr & ICE_AUX_CRIT_ERR) { + struct iidc_event *event; + + ena_mask &= ~ICE_AUX_CRIT_ERR; + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (event) { + set_bit(IIDC_EVENT_CRIT_ERR, event->type); + /* report the entire OICR value to AUX driver */ + event->reg = oicr; + ice_send_event_to_aux(pf, event); + kfree(event); + } } /* Report any remaining unexpected interrupts */ @@ -2734,8 +2851,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) /* If a critical error is pending there is no choice but to * reset the device. */ - if (oicr & (PFINT_OICR_PE_CRITERR_M | - PFINT_OICR_PCI_EXCEPTION_M | + if (oicr & (PFINT_OICR_PCI_EXCEPTION_M | PFINT_OICR_ECC_ERR_M)) { set_bit(ICE_PFR_REQ, pf->state); ice_service_task_schedule(pf); @@ -2763,6 +2879,9 @@ static void ice_dis_ctrlq_interrupts(struct ice_hw *hw) wr32(hw, PFINT_MBX_CTL, rd32(hw, PFINT_MBX_CTL) & ~PFINT_MBX_CTL_CAUSE_ENA_M); + wr32(hw, PFINT_SB_CTL, + rd32(hw, PFINT_SB_CTL) & ~PFINT_SB_CTL_CAUSE_ENA_M); + /* disable Control queue Interrupt causes */ wr32(hw, PFINT_OICR_CTL, rd32(hw, PFINT_OICR_CTL) & ~PFINT_OICR_CTL_CAUSE_ENA_M); @@ -2817,6 +2936,11 @@ static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 reg_idx) PFINT_MBX_CTL_CAUSE_ENA_M); wr32(hw, PFINT_MBX_CTL, val); + /* This enables Sideband queue Interrupt causes */ + val = ((reg_idx & PFINT_SB_CTL_MSIX_INDX_M) | + PFINT_SB_CTL_CAUSE_ENA_M); + wr32(hw, PFINT_SB_CTL, val); + ice_flush(hw); } @@ -2986,7 +3110,6 @@ static void ice_set_netdev_features(struct net_device *netdev) */ static int ice_cfg_netdev(struct ice_vsi *vsi) { - struct ice_pf *pf = vsi->back; struct ice_netdev_priv *np; struct net_device *netdev; u8 mac_addr[ETH_ALEN]; @@ -3006,7 +3129,7 @@ static int ice_cfg_netdev(struct ice_vsi *vsi) ice_set_ops(netdev); if (vsi->type == ICE_VSI_PF) { - SET_NETDEV_DEV(netdev, ice_pf_to_dev(pf)); + SET_NETDEV_DEV(netdev, ice_pf_to_dev(vsi->back)); ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr); ether_addr_copy(netdev->dev_addr, mac_addr); ether_addr_copy(netdev->perm_addr, mac_addr); @@ -3280,6 +3403,9 @@ static void ice_deinit_pf(struct ice_pf *pf) bitmap_free(pf->avail_rxqs); pf->avail_rxqs = NULL; } + + if (pf->ptp.clock) + ptp_clock_unregister(pf->ptp.clock); } /** @@ -3290,6 +3416,12 @@ static void ice_set_pf_caps(struct ice_pf *pf) { struct ice_hw_func_caps *func_caps = &pf->hw.func_caps; + clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); + clear_bit(ICE_FLAG_AUX_ENA, pf->flags); + if (func_caps->common_cap.rdma) { + set_bit(ICE_FLAG_RDMA_ENA, pf->flags); + set_bit(ICE_FLAG_AUX_ENA, pf->flags); + } clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); if (func_caps->common_cap.dcb) set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); @@ -3320,6 +3452,10 @@ static void ice_set_pf_caps(struct ice_pf *pf) func_caps->fd_fltr_best_effort); } + clear_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags); + if (func_caps->common_cap.ieee_1588) + set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags); + pf->max_pf_txqs = func_caps->common_cap.num_txq; pf->max_pf_rxqs = func_caps->common_cap.num_rxq; } @@ -3339,6 +3475,8 @@ static int ice_init_pf(struct ice_pf *pf) spin_lock_init(&pf->aq_wait_lock); init_waitqueue_head(&pf->aq_wait_queue); + init_waitqueue_head(&pf->reset_wait_queue); + /* setup service timer and periodic service task */ timer_setup(&pf->serv_tmr, ice_service_timer, 0); pf->serv_tmr_period = HZ; @@ -3369,11 +3507,12 @@ static int ice_init_pf(struct ice_pf *pf) */ static int ice_ena_msix_range(struct ice_pf *pf) { - int v_left, v_actual, v_other, v_budget = 0; + int num_cpus, v_left, v_actual, v_other, v_budget = 0; struct device *dev = ice_pf_to_dev(pf); int needed, err, i; v_left = pf->hw.func_caps.common_cap.num_msix_vectors; + num_cpus = num_online_cpus(); /* reserve for LAN miscellaneous handler */ needed = ICE_MIN_LAN_OICR_MSIX; @@ -3395,13 +3534,23 @@ static int ice_ena_msix_range(struct ice_pf *pf) v_other = v_budget; /* reserve vectors for LAN traffic */ - needed = min_t(int, num_online_cpus(), v_left); + needed = num_cpus; if (v_left < needed) goto no_hw_vecs_left_err; pf->num_lan_msix = needed; v_budget += needed; v_left -= needed; + /* reserve vectors for RDMA auxiliary driver */ + if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) { + needed = num_cpus + ICE_RDMA_NUM_AEQ_MSIX; + if (v_left < needed) + goto no_hw_vecs_left_err; + pf->num_rdma_msix = needed; + v_budget += needed; + v_left -= needed; + } + pf->msix_entries = devm_kcalloc(dev, v_budget, sizeof(*pf->msix_entries), GFP_KERNEL); if (!pf->msix_entries) { @@ -3431,16 +3580,46 @@ static int ice_ena_msix_range(struct ice_pf *pf) err = -ERANGE; goto msix_err; } else { - int v_traffic = v_actual - v_other; + int v_remain = v_actual - v_other; + int v_rdma = 0, v_min_rdma = 0; + + if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) { + /* Need at least 1 interrupt in addition to + * AEQ MSIX + */ + v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1; + v_min_rdma = ICE_MIN_RDMA_MSIX; + } if (v_actual == ICE_MIN_MSIX || - v_traffic < ICE_MIN_LAN_TXRX_MSIX) + v_remain < ICE_MIN_LAN_TXRX_MSIX + v_min_rdma) { + dev_warn(dev, "Not enough MSI-X vectors to support RDMA.\n"); + clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); + + pf->num_rdma_msix = 0; pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX; - else - pf->num_lan_msix = v_traffic; + } else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) || + (v_remain - v_rdma < v_rdma)) { + /* Support minimum RDMA and give remaining + * vectors to LAN MSIX + */ + pf->num_rdma_msix = v_min_rdma; + pf->num_lan_msix = v_remain - v_min_rdma; + } else { + /* Split remaining MSIX with RDMA after + * accounting for AEQ MSIX + */ + pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 + + ICE_RDMA_NUM_AEQ_MSIX; + pf->num_lan_msix = v_remain - pf->num_rdma_msix; + } dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n", pf->num_lan_msix); + + if (test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n", + pf->num_rdma_msix); } } @@ -3455,6 +3634,7 @@ no_hw_vecs_left_err: needed, v_left); err = -ERANGE; exit_err: + pf->num_rdma_msix = 0; pf->num_lan_msix = 0; return err; } @@ -4218,6 +4398,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) ice_init_link_dflt_override(pf->hw.port_info); + ice_check_module_power(pf, pf->hw.port_info->phy.link_info.link_cfg_err); + /* if media available, initialize PHY settings */ if (pf->hw.port_info->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { @@ -4256,6 +4438,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) } /* initialize DDP driven features */ + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) + ice_ptp_init(pf); /* Note: Flow director init failure is non-fatal to load */ if (ice_init_fdir(pf)) @@ -4282,8 +4466,29 @@ probe_done: /* ready to go, so clear down state bit */ clear_bit(ICE_DOWN, pf->state); + if (ice_is_aux_ena(pf)) { + pf->aux_idx = ida_alloc(&ice_aux_ida, GFP_KERNEL); + if (pf->aux_idx < 0) { + dev_err(dev, "Failed to allocate device ID for AUX driver\n"); + err = -ENOMEM; + goto err_netdev_reg; + } + + err = ice_init_rdma(pf); + if (err) { + dev_err(dev, "Failed to initialize RDMA: %d\n", err); + err = -EIO; + goto err_init_aux_unroll; + } + } else { + dev_warn(dev, "RDMA is not supported on this device\n"); + } + return 0; +err_init_aux_unroll: + pf->adev = NULL; + ida_free(&ice_aux_ida, pf->aux_idx); err_netdev_reg: err_send_version_unroll: ice_vsi_release_all(pf); @@ -4393,13 +4598,17 @@ static void ice_remove(struct pci_dev *pdev) ice_free_vfs(pf); } - set_bit(ICE_DOWN, pf->state); ice_service_task_stop(pf); ice_aq_cancel_waiting_tasks(pf); + ice_unplug_aux_dev(pf); + ida_free(&ice_aux_ida, pf->aux_idx); + set_bit(ICE_DOWN, pf->state); mutex_destroy(&(&pf->hw)->fdir_fltr_lock); ice_deinit_lag(pf); + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) + ice_ptp_release(pf); if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); ice_setup_mc_magic_wake(pf); @@ -4552,6 +4761,8 @@ static int __maybe_unused ice_suspend(struct device *dev) */ disabled = ice_service_task_stop(pf); + ice_unplug_aux_dev(pf); + /* Already suspended?, then there is nothing to do */ if (test_and_set_bit(ICE_SUSPENDED, pf->state)) { if (!disabled) @@ -5284,6 +5495,7 @@ static void ice_tx_dim_work(struct work_struct *work) itr = tx_profile[dim->profile_ix].itr; intrl = tx_profile[dim->profile_ix].intrl; + ice_trace(tx_dim_work, q_vector, dim); ice_write_itr(rc, itr); ice_write_intrl(q_vector, intrl); @@ -5308,6 +5520,7 @@ static void ice_rx_dim_work(struct work_struct *work) itr = rx_profile[dim->profile_ix].itr; intrl = rx_profile[dim->profile_ix].intrl; + ice_trace(rx_dim_work, q_vector, dim); ice_write_itr(rc, itr); ice_write_intrl(q_vector, intrl); @@ -5451,7 +5664,6 @@ ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_ring **rings, static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) { struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats; - struct ice_ring *ring; u64 pkts, bytes; int i; @@ -5475,7 +5687,8 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) /* update Rx rings counters */ ice_for_each_rxq(vsi, i) { - ring = READ_ONCE(vsi->rx_rings[i]); + struct ice_ring *ring = READ_ONCE(vsi->rx_rings[i]); + ice_fetch_u64_stats_per_ring(ring, &pkts, &bytes); vsi_stats->rx_packets += pkts; vsi_stats->rx_bytes += bytes; @@ -6142,6 +6355,12 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_clear_pxe_mode(hw); + ret = ice_init_nvm(hw); + if (ret) { + dev_err(dev, "ice_init_nvm failed %s\n", ice_stat_str(ret)); + goto err_init_ctrlq; + } + ret = ice_get_caps(hw); if (ret) { dev_err(dev, "ice_get_caps failed %s\n", ice_stat_str(ret)); @@ -6183,6 +6402,13 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) if (test_bit(ICE_FLAG_DCB_ENA, pf->flags)) ice_dcb_rebuild(pf); + /* If the PF previously had enabled PTP, PTP init needs to happen before + * the VSI rebuild. If not, this causes the PTP link status events to + * fail. + */ + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) + ice_ptp_init(pf); + /* rebuild PF VSI */ err = ice_vsi_rebuild_by_type(pf, ICE_VSI_PF); if (err) { @@ -6222,6 +6448,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) /* if we get here, reset flow is successful */ clear_bit(ICE_RESET_FAILED, pf->state); + + ice_plug_aux_dev(pf); return; err_vsi_rebuild: @@ -6260,7 +6488,9 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; + struct iidc_event *event; u8 count = 0; + int err = 0; if (new_mtu == (int)netdev->mtu) { netdev_warn(netdev, "MTU is already %u\n", netdev->mtu); @@ -6293,27 +6523,59 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) return -EBUSY; } + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return -ENOMEM; + + set_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + clear_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type); + netdev->mtu = (unsigned int)new_mtu; /* if VSI is up, bring it down and then back up */ if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { - int err; - err = ice_down(vsi); if (err) { netdev_err(netdev, "change MTU if_down err %d\n", err); - return err; + goto event_after; } err = ice_up(vsi); if (err) { netdev_err(netdev, "change MTU if_up err %d\n", err); - return err; + goto event_after; } } netdev_dbg(netdev, "changed MTU to %d\n", new_mtu); - return 0; +event_after: + set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); + + return err; +} + +/** + * ice_do_ioctl - Access the hwtstamp interface + * @netdev: network interface device structure + * @ifr: interface request data + * @cmd: ioctl command + */ +static int ice_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + + switch (cmd) { + case SIOCGHWTSTAMP: + return ice_ptp_get_ts_config(pf, ifr); + case SIOCSHWTSTAMP: + return ice_ptp_set_ts_config(pf, ifr); + default: + return -EOPNOTSUPP; + } } /** @@ -6832,6 +7094,8 @@ int ice_open_internal(struct net_device *netdev) return -EIO; } + ice_check_module_power(pf, pi->phy.link_info.link_cfg_err); + /* Set PHY if there is media, otherwise, turn off PHY */ if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { clear_bit(ICE_FLAG_NO_MEDIA, pf->flags); @@ -6965,6 +7229,7 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_change_mtu = ice_change_mtu, .ndo_get_stats64 = ice_get_stats64, .ndo_set_tx_maxrate = ice_set_tx_maxrate, + .ndo_do_ioctl = ice_do_ioctl, .ndo_set_vf_spoofchk = ice_set_vf_spoofchk, .ndo_set_vf_mac = ice_set_vf_mac, .ndo_get_vf_config = ice_get_vf_cfg, diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c new file mode 100644 index 000000000000..5d5207b56ca9 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -0,0 +1,1558 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021, Intel Corporation. */ + +#include "ice.h" +#include "ice_lib.h" + +#define E810_OUT_PROP_DELAY_NS 1 + +/** + * ice_set_tx_tstamp - Enable or disable Tx timestamping + * @pf: The PF pointer to search in + * @on: bool value for whether timestamps are enabled or disabled + */ +static void ice_set_tx_tstamp(struct ice_pf *pf, bool on) +{ + struct ice_vsi *vsi; + u32 val; + u16 i; + + vsi = ice_get_main_vsi(pf); + if (!vsi) + return; + + /* Set the timestamp enable flag for all the Tx rings */ + ice_for_each_rxq(vsi, i) { + if (!vsi->tx_rings[i]) + continue; + vsi->tx_rings[i]->ptp_tx = on; + } + + /* Configure the Tx timestamp interrupt */ + val = rd32(&pf->hw, PFINT_OICR_ENA); + if (on) + val |= PFINT_OICR_TSYN_TX_M; + else + val &= ~PFINT_OICR_TSYN_TX_M; + wr32(&pf->hw, PFINT_OICR_ENA, val); +} + +/** + * ice_set_rx_tstamp - Enable or disable Rx timestamping + * @pf: The PF pointer to search in + * @on: bool value for whether timestamps are enabled or disabled + */ +static void ice_set_rx_tstamp(struct ice_pf *pf, bool on) +{ + struct ice_vsi *vsi; + u16 i; + + vsi = ice_get_main_vsi(pf); + if (!vsi) + return; + + /* Set the timestamp flag for all the Rx rings */ + ice_for_each_rxq(vsi, i) { + if (!vsi->rx_rings[i]) + continue; + vsi->rx_rings[i]->ptp_rx = on; + } +} + +/** + * ice_ptp_cfg_timestamp - Configure timestamp for init/deinit + * @pf: Board private structure + * @ena: bool value to enable or disable time stamp + * + * This function will configure timestamping during PTP initialization + * and deinitialization + */ +static void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena) +{ + ice_set_tx_tstamp(pf, ena); + ice_set_rx_tstamp(pf, ena); + + if (ena) { + pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL; + pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_ON; + } else { + pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_OFF; + } +} + +/** + * ice_get_ptp_clock_index - Get the PTP clock index + * @pf: the PF pointer + * + * Determine the clock index of the PTP clock associated with this device. If + * this is the PF controlling the clock, just use the local access to the + * clock device pointer. + * + * Otherwise, read from the driver shared parameters to determine the clock + * index value. + * + * Returns: the index of the PTP clock associated with this device, or -1 if + * there is no associated clock. + */ +int ice_get_ptp_clock_index(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + enum ice_aqc_driver_params param_idx; + struct ice_hw *hw = &pf->hw; + u8 tmr_idx; + u32 value; + int err; + + /* Use the ptp_clock structure if we're the main PF */ + if (pf->ptp.clock) + return ptp_clock_index(pf->ptp.clock); + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; + if (!tmr_idx) + param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0; + else + param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1; + + err = ice_aq_get_driver_param(hw, param_idx, &value, NULL); + if (err) { + dev_err(dev, "Failed to read PTP clock index parameter, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + return -1; + } + + /* The PTP clock index is an integer, and will be between 0 and + * INT_MAX. The highest bit of the driver shared parameter is used to + * indicate whether or not the currently stored clock index is valid. + */ + if (!(value & PTP_SHARED_CLK_IDX_VALID)) + return -1; + + return value & ~PTP_SHARED_CLK_IDX_VALID; +} + +/** + * ice_set_ptp_clock_index - Set the PTP clock index + * @pf: the PF pointer + * + * Set the PTP clock index for this device into the shared driver parameters, + * so that other PFs associated with this device can read it. + * + * If the PF is unable to store the clock index, it will log an error, but + * will continue operating PTP. + */ +static void ice_set_ptp_clock_index(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + enum ice_aqc_driver_params param_idx; + struct ice_hw *hw = &pf->hw; + u8 tmr_idx; + u32 value; + int err; + + if (!pf->ptp.clock) + return; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; + if (!tmr_idx) + param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0; + else + param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1; + + value = (u32)ptp_clock_index(pf->ptp.clock); + if (value > INT_MAX) { + dev_err(dev, "PTP Clock index is too large to store\n"); + return; + } + value |= PTP_SHARED_CLK_IDX_VALID; + + err = ice_aq_set_driver_param(hw, param_idx, value, NULL); + if (err) { + dev_err(dev, "Failed to set PTP clock index parameter, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + } +} + +/** + * ice_clear_ptp_clock_index - Clear the PTP clock index + * @pf: the PF pointer + * + * Clear the PTP clock index for this device. Must be called when + * unregistering the PTP clock, in order to ensure other PFs stop reporting + * a clock object that no longer exists. + */ +static void ice_clear_ptp_clock_index(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + enum ice_aqc_driver_params param_idx; + struct ice_hw *hw = &pf->hw; + u8 tmr_idx; + int err; + + /* Do not clear the index if we don't own the timer */ + if (!hw->func_caps.ts_func_info.src_tmr_owned) + return; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; + if (!tmr_idx) + param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR0; + else + param_idx = ICE_AQC_DRIVER_PARAM_CLK_IDX_TMR1; + + err = ice_aq_set_driver_param(hw, param_idx, 0, NULL); + if (err) { + dev_dbg(dev, "Failed to clear PTP clock index parameter, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + } +} + +/** + * ice_ptp_read_src_clk_reg - Read the source clock register + * @pf: Board private structure + * @sts: Optional parameter for holding a pair of system timestamps from + * the system clock. Will be ignored if NULL is given. + */ +static u64 +ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) +{ + struct ice_hw *hw = &pf->hw; + u32 hi, lo, lo2; + u8 tmr_idx; + + tmr_idx = ice_get_ptp_src_clock_index(hw); + /* Read the system timestamp pre PHC read */ + ptp_read_system_prets(sts); + + lo = rd32(hw, GLTSYN_TIME_L(tmr_idx)); + + /* Read the system timestamp post PHC read */ + ptp_read_system_postts(sts); + + hi = rd32(hw, GLTSYN_TIME_H(tmr_idx)); + lo2 = rd32(hw, GLTSYN_TIME_L(tmr_idx)); + + if (lo2 < lo) { + /* if TIME_L rolled over read TIME_L again and update + * system timestamps + */ + ptp_read_system_prets(sts); + lo = rd32(hw, GLTSYN_TIME_L(tmr_idx)); + ptp_read_system_postts(sts); + hi = rd32(hw, GLTSYN_TIME_H(tmr_idx)); + } + + return ((u64)hi << 32) | lo; +} + +/** + * ice_ptp_update_cached_phctime - Update the cached PHC time values + * @pf: Board specific private structure + * + * This function updates the system time values which are cached in the PF + * structure and the Rx rings. + * + * This function must be called periodically to ensure that the cached value + * is never more than 2 seconds old. It must also be called whenever the PHC + * time has been changed. + */ +static void ice_ptp_update_cached_phctime(struct ice_pf *pf) +{ + u64 systime; + int i; + + /* Read the current PHC time */ + systime = ice_ptp_read_src_clk_reg(pf, NULL); + + /* Update the cached PHC time stored in the PF structure */ + WRITE_ONCE(pf->ptp.cached_phc_time, systime); + + ice_for_each_vsi(pf, i) { + struct ice_vsi *vsi = pf->vsi[i]; + int j; + + if (!vsi) + continue; + + if (vsi->type != ICE_VSI_PF) + continue; + + ice_for_each_rxq(vsi, j) { + if (!vsi->rx_rings[j]) + continue; + WRITE_ONCE(vsi->rx_rings[j]->cached_phctime, systime); + } + } +} + +/** + * ice_ptp_extend_32b_ts - Convert a 32b nanoseconds timestamp to 64b + * @cached_phc_time: recently cached copy of PHC time + * @in_tstamp: Ingress/egress 32b nanoseconds timestamp value + * + * Hardware captures timestamps which contain only 32 bits of nominal + * nanoseconds, as opposed to the 64bit timestamps that the stack expects. + * Note that the captured timestamp values may be 40 bits, but the lower + * 8 bits are sub-nanoseconds and generally discarded. + * + * Extend the 32bit nanosecond timestamp using the following algorithm and + * assumptions: + * + * 1) have a recently cached copy of the PHC time + * 2) assume that the in_tstamp was captured 2^31 nanoseconds (~2.1 + * seconds) before or after the PHC time was captured. + * 3) calculate the delta between the cached time and the timestamp + * 4) if the delta is smaller than 2^31 nanoseconds, then the timestamp was + * captured after the PHC time. In this case, the full timestamp is just + * the cached PHC time plus the delta. + * 5) otherwise, if the delta is larger than 2^31 nanoseconds, then the + * timestamp was captured *before* the PHC time, i.e. because the PHC + * cache was updated after the timestamp was captured by hardware. In this + * case, the full timestamp is the cached time minus the inverse delta. + * + * This algorithm works even if the PHC time was updated after a Tx timestamp + * was requested, but before the Tx timestamp event was reported from + * hardware. + * + * This calculation primarily relies on keeping the cached PHC time up to + * date. If the timestamp was captured more than 2^31 nanoseconds after the + * PHC time, it is possible that the lower 32bits of PHC time have + * overflowed more than once, and we might generate an incorrect timestamp. + * + * This is prevented by (a) periodically updating the cached PHC time once + * a second, and (b) discarding any Tx timestamp packet if it has waited for + * a timestamp for more than one second. + */ +static u64 ice_ptp_extend_32b_ts(u64 cached_phc_time, u32 in_tstamp) +{ + u32 delta, phc_time_lo; + u64 ns; + + /* Extract the lower 32 bits of the PHC time */ + phc_time_lo = (u32)cached_phc_time; + + /* Calculate the delta between the lower 32bits of the cached PHC + * time and the in_tstamp value + */ + delta = (in_tstamp - phc_time_lo); + + /* Do not assume that the in_tstamp is always more recent than the + * cached PHC time. If the delta is large, it indicates that the + * in_tstamp was taken in the past, and should be converted + * forward. + */ + if (delta > (U32_MAX / 2)) { + /* reverse the delta calculation here */ + delta = (phc_time_lo - in_tstamp); + ns = cached_phc_time - delta; + } else { + ns = cached_phc_time + delta; + } + + return ns; +} + +/** + * ice_ptp_extend_40b_ts - Convert a 40b timestamp to 64b nanoseconds + * @pf: Board private structure + * @in_tstamp: Ingress/egress 40b timestamp value + * + * The Tx and Rx timestamps are 40 bits wide, including 32 bits of nominal + * nanoseconds, 7 bits of sub-nanoseconds, and a valid bit. + * + * *--------------------------------------------------------------* + * | 32 bits of nanoseconds | 7 high bits of sub ns underflow | v | + * *--------------------------------------------------------------* + * + * The low bit is an indicator of whether the timestamp is valid. The next + * 7 bits are a capture of the upper 7 bits of the sub-nanosecond underflow, + * and the remaining 32 bits are the lower 32 bits of the PHC timer. + * + * It is assumed that the caller verifies the timestamp is valid prior to + * calling this function. + * + * Extract the 32bit nominal nanoseconds and extend them. Use the cached PHC + * time stored in the device private PTP structure as the basis for timestamp + * extension. + * + * See ice_ptp_extend_32b_ts for a detailed explanation of the extension + * algorithm. + */ +static u64 ice_ptp_extend_40b_ts(struct ice_pf *pf, u64 in_tstamp) +{ + const u64 mask = GENMASK_ULL(31, 0); + + return ice_ptp_extend_32b_ts(pf->ptp.cached_phc_time, + (in_tstamp >> 8) & mask); +} + +/** + * ice_ptp_read_time - Read the time from the device + * @pf: Board private structure + * @ts: timespec structure to hold the current time value + * @sts: Optional parameter for holding a pair of system timestamps from + * the system clock. Will be ignored if NULL is given. + * + * This function reads the source clock registers and stores them in a timespec. + * However, since the registers are 64 bits of nanoseconds, we must convert the + * result to a timespec before we can return. + */ +static void +ice_ptp_read_time(struct ice_pf *pf, struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + u64 time_ns = ice_ptp_read_src_clk_reg(pf, sts); + + *ts = ns_to_timespec64(time_ns); +} + +/** + * ice_ptp_write_init - Set PHC time to provided value + * @pf: Board private structure + * @ts: timespec structure that holds the new time value + * + * Set the PHC time to the specified time provided in the timespec. + */ +static int ice_ptp_write_init(struct ice_pf *pf, struct timespec64 *ts) +{ + u64 ns = timespec64_to_ns(ts); + struct ice_hw *hw = &pf->hw; + + return ice_ptp_init_time(hw, ns); +} + +/** + * ice_ptp_write_adj - Adjust PHC clock time atomically + * @pf: Board private structure + * @adj: Adjustment in nanoseconds + * + * Perform an atomic adjustment of the PHC time by the specified number of + * nanoseconds. + */ +static int ice_ptp_write_adj(struct ice_pf *pf, s32 adj) +{ + struct ice_hw *hw = &pf->hw; + + return ice_ptp_adj_clock(hw, adj); +} + +/** + * ice_ptp_adjfine - Adjust clock increment rate + * @info: the driver's PTP info structure + * @scaled_ppm: Parts per million with 16-bit fractional field + * + * Adjust the frequency of the clock by the indicated scaled ppm from the + * base frequency. + */ +static int ice_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm) +{ + struct ice_pf *pf = ptp_info_to_pf(info); + u64 freq, divisor = 1000000ULL; + struct ice_hw *hw = &pf->hw; + s64 incval, diff; + int neg_adj = 0; + int err; + + incval = ICE_PTP_NOMINAL_INCVAL_E810; + + if (scaled_ppm < 0) { + neg_adj = 1; + scaled_ppm = -scaled_ppm; + } + + while ((u64)scaled_ppm > div_u64(U64_MAX, incval)) { + /* handle overflow by scaling down the scaled_ppm and + * the divisor, losing some precision + */ + scaled_ppm >>= 2; + divisor >>= 2; + } + + freq = (incval * (u64)scaled_ppm) >> 16; + diff = div_u64(freq, divisor); + + if (neg_adj) + incval -= diff; + else + incval += diff; + + err = ice_ptp_write_incval_locked(hw, incval); + if (err) { + dev_err(ice_pf_to_dev(pf), "PTP failed to set incval, err %d\n", + err); + return -EIO; + } + + return 0; +} + +/** + * ice_ptp_extts_work - Workqueue task function + * @work: external timestamp work structure + * + * Service for PTP external clock event + */ +static void ice_ptp_extts_work(struct kthread_work *work) +{ + struct ice_ptp *ptp = container_of(work, struct ice_ptp, extts_work); + struct ice_pf *pf = container_of(ptp, struct ice_pf, ptp); + struct ptp_clock_event event; + struct ice_hw *hw = &pf->hw; + u8 chan, tmr_idx; + u32 hi, lo; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + /* Event time is captured by one of the two matched registers + * GLTSYN_EVNT_L: 32 LSB of sampled time event + * GLTSYN_EVNT_H: 32 MSB of sampled time event + * Event is defined in GLTSYN_EVNT_0 register + */ + for (chan = 0; chan < GLTSYN_EVNT_H_IDX_MAX; chan++) { + /* Check if channel is enabled */ + if (pf->ptp.ext_ts_irq & (1 << chan)) { + lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx)); + hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx)); + event.timestamp = (((u64)hi) << 32) | lo; + event.type = PTP_CLOCK_EXTTS; + event.index = chan; + + /* Fire event */ + ptp_clock_event(pf->ptp.clock, &event); + pf->ptp.ext_ts_irq &= ~(1 << chan); + } + } +} + +/** + * ice_ptp_cfg_extts - Configure EXTTS pin and channel + * @pf: Board private structure + * @ena: true to enable; false to disable + * @chan: GPIO channel (0-3) + * @gpio_pin: GPIO pin + * @extts_flags: request flags from the ptp_extts_request.flags + */ +static int +ice_ptp_cfg_extts(struct ice_pf *pf, bool ena, unsigned int chan, u32 gpio_pin, + unsigned int extts_flags) +{ + u32 func, aux_reg, gpio_reg, irq_reg; + struct ice_hw *hw = &pf->hw; + u8 tmr_idx; + + if (chan > (unsigned int)pf->ptp.info.n_ext_ts) + return -EINVAL; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + irq_reg = rd32(hw, PFINT_OICR_ENA); + + if (ena) { + /* Enable the interrupt */ + irq_reg |= PFINT_OICR_TSYN_EVNT_M; + aux_reg = GLTSYN_AUX_IN_0_INT_ENA_M; + +#define GLTSYN_AUX_IN_0_EVNTLVL_RISING_EDGE BIT(0) +#define GLTSYN_AUX_IN_0_EVNTLVL_FALLING_EDGE BIT(1) + + /* set event level to requested edge */ + if (extts_flags & PTP_FALLING_EDGE) + aux_reg |= GLTSYN_AUX_IN_0_EVNTLVL_FALLING_EDGE; + if (extts_flags & PTP_RISING_EDGE) + aux_reg |= GLTSYN_AUX_IN_0_EVNTLVL_RISING_EDGE; + + /* Write GPIO CTL reg. + * 0x1 is input sampled by EVENT register(channel) + * + num_in_channels * tmr_idx + */ + func = 1 + chan + (tmr_idx * 3); + gpio_reg = ((func << GLGEN_GPIO_CTL_PIN_FUNC_S) & + GLGEN_GPIO_CTL_PIN_FUNC_M); + pf->ptp.ext_ts_chan |= (1 << chan); + } else { + /* clear the values we set to reset defaults */ + aux_reg = 0; + gpio_reg = 0; + pf->ptp.ext_ts_chan &= ~(1 << chan); + if (!pf->ptp.ext_ts_chan) + irq_reg &= ~PFINT_OICR_TSYN_EVNT_M; + } + + wr32(hw, PFINT_OICR_ENA, irq_reg); + wr32(hw, GLTSYN_AUX_IN(chan, tmr_idx), aux_reg); + wr32(hw, GLGEN_GPIO_CTL(gpio_pin), gpio_reg); + + return 0; +} + +/** + * ice_ptp_cfg_clkout - Configure clock to generate periodic wave + * @pf: Board private structure + * @chan: GPIO channel (0-3) + * @config: desired periodic clk configuration. NULL will disable channel + * @store: If set to true the values will be stored + * + * Configure the internal clock generator modules to generate the clock wave of + * specified period. + */ +static int ice_ptp_cfg_clkout(struct ice_pf *pf, unsigned int chan, + struct ice_perout_channel *config, bool store) +{ + u64 current_time, period, start_time, phase; + struct ice_hw *hw = &pf->hw; + u32 func, val, gpio_pin; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + /* 0. Reset mode & out_en in AUX_OUT */ + wr32(hw, GLTSYN_AUX_OUT(chan, tmr_idx), 0); + + /* If we're disabling the output, clear out CLKO and TGT and keep + * output level low + */ + if (!config || !config->ena) { + wr32(hw, GLTSYN_CLKO(chan, tmr_idx), 0); + wr32(hw, GLTSYN_TGT_L(chan, tmr_idx), 0); + wr32(hw, GLTSYN_TGT_H(chan, tmr_idx), 0); + + val = GLGEN_GPIO_CTL_PIN_DIR_M; + gpio_pin = pf->ptp.perout_channels[chan].gpio_pin; + wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val); + + /* Store the value if requested */ + if (store) + memset(&pf->ptp.perout_channels[chan], 0, + sizeof(struct ice_perout_channel)); + + return 0; + } + period = config->period; + start_time = config->start_time; + div64_u64_rem(start_time, period, &phase); + gpio_pin = config->gpio_pin; + + /* 1. Write clkout with half of required period value */ + if (period & 0x1) { + dev_err(ice_pf_to_dev(pf), "CLK Period must be an even value\n"); + goto err; + } + + period >>= 1; + + /* For proper operation, the GLTSYN_CLKO must be larger than clock tick + */ +#define MIN_PULSE 3 + if (period <= MIN_PULSE || period > U32_MAX) { + dev_err(ice_pf_to_dev(pf), "CLK Period must be > %d && < 2^33", + MIN_PULSE * 2); + goto err; + } + + wr32(hw, GLTSYN_CLKO(chan, tmr_idx), lower_32_bits(period)); + + /* Allow time for programming before start_time is hit */ + current_time = ice_ptp_read_src_clk_reg(pf, NULL); + + /* if start time is in the past start the timer at the nearest second + * maintaining phase + */ + if (start_time < current_time) + start_time = div64_u64(current_time + NSEC_PER_MSEC - 1, + NSEC_PER_SEC) * NSEC_PER_SEC + phase; + + start_time -= E810_OUT_PROP_DELAY_NS; + + /* 2. Write TARGET time */ + wr32(hw, GLTSYN_TGT_L(chan, tmr_idx), lower_32_bits(start_time)); + wr32(hw, GLTSYN_TGT_H(chan, tmr_idx), upper_32_bits(start_time)); + + /* 3. Write AUX_OUT register */ + val = GLTSYN_AUX_OUT_0_OUT_ENA_M | GLTSYN_AUX_OUT_0_OUTMOD_M; + wr32(hw, GLTSYN_AUX_OUT(chan, tmr_idx), val); + + /* 4. write GPIO CTL reg */ + func = 8 + chan + (tmr_idx * 4); + val = GLGEN_GPIO_CTL_PIN_DIR_M | + ((func << GLGEN_GPIO_CTL_PIN_FUNC_S) & GLGEN_GPIO_CTL_PIN_FUNC_M); + wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val); + + /* Store the value if requested */ + if (store) { + memcpy(&pf->ptp.perout_channels[chan], config, + sizeof(struct ice_perout_channel)); + pf->ptp.perout_channels[chan].start_time = phase; + } + + return 0; +err: + dev_err(ice_pf_to_dev(pf), "PTP failed to cfg per_clk\n"); + return -EFAULT; +} + +/** + * ice_ptp_gpio_enable_e810 - Enable/disable ancillary features of PHC + * @info: the driver's PTP info structure + * @rq: The requested feature to change + * @on: Enable/disable flag + */ +static int +ice_ptp_gpio_enable_e810(struct ptp_clock_info *info, + struct ptp_clock_request *rq, int on) +{ + struct ice_pf *pf = ptp_info_to_pf(info); + struct ice_perout_channel clk_cfg = {0}; + unsigned int chan; + u32 gpio_pin; + int err; + + switch (rq->type) { + case PTP_CLK_REQ_PEROUT: + chan = rq->perout.index; + if (chan == PPS_CLK_GEN_CHAN) + clk_cfg.gpio_pin = PPS_PIN_INDEX; + else + clk_cfg.gpio_pin = chan; + + clk_cfg.period = ((rq->perout.period.sec * NSEC_PER_SEC) + + rq->perout.period.nsec); + clk_cfg.start_time = ((rq->perout.start.sec * NSEC_PER_SEC) + + rq->perout.start.nsec); + clk_cfg.ena = !!on; + + err = ice_ptp_cfg_clkout(pf, chan, &clk_cfg, true); + break; + case PTP_CLK_REQ_EXTTS: + chan = rq->extts.index; + gpio_pin = chan; + + err = ice_ptp_cfg_extts(pf, !!on, chan, gpio_pin, + rq->extts.flags); + break; + default: + return -EOPNOTSUPP; + } + + return err; +} + +/** + * ice_ptp_gettimex64 - Get the time of the clock + * @info: the driver's PTP info structure + * @ts: timespec64 structure to hold the current time value + * @sts: Optional parameter for holding a pair of system timestamps from + * the system clock. Will be ignored if NULL is given. + * + * Read the device clock and return the correct value on ns, after converting it + * into a timespec struct. + */ +static int +ice_ptp_gettimex64(struct ptp_clock_info *info, struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct ice_pf *pf = ptp_info_to_pf(info); + struct ice_hw *hw = &pf->hw; + + if (!ice_ptp_lock(hw)) { + dev_err(ice_pf_to_dev(pf), "PTP failed to get time\n"); + return -EBUSY; + } + + ice_ptp_read_time(pf, ts, sts); + ice_ptp_unlock(hw); + + return 0; +} + +/** + * ice_ptp_settime64 - Set the time of the clock + * @info: the driver's PTP info structure + * @ts: timespec64 structure that holds the new time value + * + * Set the device clock to the user input value. The conversion from timespec + * to ns happens in the write function. + */ +static int +ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) +{ + struct ice_pf *pf = ptp_info_to_pf(info); + struct timespec64 ts64 = *ts; + struct ice_hw *hw = &pf->hw; + int err; + + if (!ice_ptp_lock(hw)) { + err = -EBUSY; + goto exit; + } + + err = ice_ptp_write_init(pf, &ts64); + ice_ptp_unlock(hw); + + if (!err) + ice_ptp_update_cached_phctime(pf); + +exit: + if (err) { + dev_err(ice_pf_to_dev(pf), "PTP failed to set time %d\n", err); + return err; + } + + return 0; +} + +/** + * ice_ptp_adjtime_nonatomic - Do a non-atomic clock adjustment + * @info: the driver's PTP info structure + * @delta: Offset in nanoseconds to adjust the time by + */ +static int ice_ptp_adjtime_nonatomic(struct ptp_clock_info *info, s64 delta) +{ + struct timespec64 now, then; + + then = ns_to_timespec64(delta); + ice_ptp_gettimex64(info, &now, NULL); + now = timespec64_add(now, then); + + return ice_ptp_settime64(info, (const struct timespec64 *)&now); +} + +/** + * ice_ptp_adjtime - Adjust the time of the clock by the indicated delta + * @info: the driver's PTP info structure + * @delta: Offset in nanoseconds to adjust the time by + */ +static int ice_ptp_adjtime(struct ptp_clock_info *info, s64 delta) +{ + struct ice_pf *pf = ptp_info_to_pf(info); + struct ice_hw *hw = &pf->hw; + struct device *dev; + int err; + + dev = ice_pf_to_dev(pf); + + /* Hardware only supports atomic adjustments using signed 32-bit + * integers. For any adjustment outside this range, perform + * a non-atomic get->adjust->set flow. + */ + if (delta > S32_MAX || delta < S32_MIN) { + dev_dbg(dev, "delta = %lld, adjtime non-atomic\n", delta); + return ice_ptp_adjtime_nonatomic(info, delta); + } + + if (!ice_ptp_lock(hw)) { + dev_err(dev, "PTP failed to acquire semaphore in adjtime\n"); + return -EBUSY; + } + + err = ice_ptp_write_adj(pf, delta); + + ice_ptp_unlock(hw); + + if (err) { + dev_err(dev, "PTP failed to adjust time, err %d\n", err); + return err; + } + + ice_ptp_update_cached_phctime(pf); + + return 0; +} + +/** + * ice_ptp_get_ts_config - ioctl interface to read the timestamping config + * @pf: Board private structure + * @ifr: ioctl data + * + * Copy the timestamping config to user buffer + */ +int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr) +{ + struct hwtstamp_config *config; + + if (!test_bit(ICE_FLAG_PTP, pf->flags)) + return -EIO; + + config = &pf->ptp.tstamp_config; + + return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ? + -EFAULT : 0; +} + +/** + * ice_ptp_set_timestamp_mode - Setup driver for requested timestamp mode + * @pf: Board private structure + * @config: hwtstamp settings requested or saved + */ +static int +ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) +{ + /* Reserved for future extensions. */ + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + ice_set_tx_tstamp(pf, false); + break; + case HWTSTAMP_TX_ON: + ice_set_tx_tstamp(pf, true); + break; + default: + return -ERANGE; + } + + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + ice_set_rx_tstamp(pf, false); + break; + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_NTP_ALL: + case HWTSTAMP_FILTER_ALL: + config->rx_filter = HWTSTAMP_FILTER_ALL; + ice_set_rx_tstamp(pf, true); + break; + default: + return -ERANGE; + } + + return 0; +} + +/** + * ice_ptp_set_ts_config - ioctl interface to control the timestamping + * @pf: Board private structure + * @ifr: ioctl data + * + * Get the user config and store it + */ +int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr) +{ + struct hwtstamp_config config; + int err; + + if (!test_bit(ICE_FLAG_PTP, pf->flags)) + return -EAGAIN; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + err = ice_ptp_set_timestamp_mode(pf, &config); + if (err) + return err; + + /* Save these settings for future reference */ + pf->ptp.tstamp_config = config; + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + +/** + * ice_ptp_rx_hwtstamp - Check for an Rx timestamp + * @rx_ring: Ring to get the VSI info + * @rx_desc: Receive descriptor + * @skb: Particular skb to send timestamp with + * + * The driver receives a notification in the receive descriptor with timestamp. + * The timestamp is in ns, so we must convert the result first. + */ +void +ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring, + union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) +{ + u32 ts_high; + u64 ts_ns; + + /* Populate timesync data into skb */ + if (rx_desc->wb.time_stamp_low & ICE_PTP_TS_VALID) { + struct skb_shared_hwtstamps *hwtstamps; + + /* Use ice_ptp_extend_32b_ts directly, using the ring-specific + * cached PHC value, rather than accessing the PF. This also + * allows us to simply pass the upper 32bits of nanoseconds + * directly. Calling ice_ptp_extend_40b_ts is unnecessary as + * it would just discard these bits itself. + */ + ts_high = le32_to_cpu(rx_desc->wb.flex_ts.ts_high); + ts_ns = ice_ptp_extend_32b_ts(rx_ring->cached_phctime, ts_high); + + hwtstamps = skb_hwtstamps(skb); + memset(hwtstamps, 0, sizeof(*hwtstamps)); + hwtstamps->hwtstamp = ns_to_ktime(ts_ns); + } +} + +/** + * ice_ptp_setup_pins_e810 - Setup PTP pins in sysfs + * @info: PTP clock capabilities + */ +static void ice_ptp_setup_pins_e810(struct ptp_clock_info *info) +{ + info->n_per_out = E810_N_PER_OUT; + info->n_ext_ts = E810_N_EXT_TS; +} + +/** + * ice_ptp_set_funcs_e810 - Set specialized functions for E810 support + * @pf: Board private structure + * @info: PTP info to fill + * + * Assign functions to the PTP capabiltiies structure for E810 devices. + * Functions which operate across all device families should be set directly + * in ice_ptp_set_caps. Only add functions here which are distinct for e810 + * devices. + */ +static void +ice_ptp_set_funcs_e810(struct ice_pf *pf, struct ptp_clock_info *info) +{ + info->enable = ice_ptp_gpio_enable_e810; + + ice_ptp_setup_pins_e810(info); +} + +/** + * ice_ptp_set_caps - Set PTP capabilities + * @pf: Board private structure + */ +static void ice_ptp_set_caps(struct ice_pf *pf) +{ + struct ptp_clock_info *info = &pf->ptp.info; + struct device *dev = ice_pf_to_dev(pf); + + snprintf(info->name, sizeof(info->name) - 1, "%s-%s-clk", + dev_driver_string(dev), dev_name(dev)); + info->owner = THIS_MODULE; + info->max_adj = 999999999; + info->adjtime = ice_ptp_adjtime; + info->adjfine = ice_ptp_adjfine; + info->gettimex64 = ice_ptp_gettimex64; + info->settime64 = ice_ptp_settime64; + + ice_ptp_set_funcs_e810(pf, info); +} + +/** + * ice_ptp_create_clock - Create PTP clock device for userspace + * @pf: Board private structure + * + * This function creates a new PTP clock device. It only creates one if we + * don't already have one. Will return error if it can't create one, but success + * if we already have a device. Should be used by ice_ptp_init to create clock + * initially, and prevent global resets from creating new clock devices. + */ +static long ice_ptp_create_clock(struct ice_pf *pf) +{ + struct ptp_clock_info *info; + struct ptp_clock *clock; + struct device *dev; + + /* No need to create a clock device if we already have one */ + if (pf->ptp.clock) + return 0; + + ice_ptp_set_caps(pf); + + info = &pf->ptp.info; + dev = ice_pf_to_dev(pf); + + /* Allocate memory for kernel pins interface */ + if (info->n_pins) { + info->pin_config = devm_kcalloc(dev, info->n_pins, + sizeof(*info->pin_config), + GFP_KERNEL); + if (!info->pin_config) { + info->n_pins = 0; + return -ENOMEM; + } + } + + /* Attempt to register the clock before enabling the hardware. */ + clock = ptp_clock_register(info, dev); + if (IS_ERR(clock)) + return PTR_ERR(clock); + + pf->ptp.clock = clock; + + return 0; +} + +/** + * ice_ptp_tx_tstamp_work - Process Tx timestamps for a port + * @work: pointer to the kthread_work struct + * + * Process timestamps captured by the PHY associated with this port. To do + * this, loop over each index with a waiting skb. + * + * If a given index has a valid timestamp, perform the following steps: + * + * 1) copy the timestamp out of the PHY register + * 4) clear the timestamp valid bit in the PHY register + * 5) unlock the index by clearing the associated in_use bit. + * 2) extend the 40b timestamp value to get a 64bit timestamp + * 3) send that timestamp to the stack + * + * After looping, if we still have waiting SKBs, then re-queue the work. This + * may cause us effectively poll even when not strictly necessary. We do this + * because it's possible a new timestamp was requested around the same time as + * the interrupt. In some cases hardware might not interrupt us again when the + * timestamp is captured. + * + * Note that we only take the tracking lock when clearing the bit and when + * checking if we need to re-queue this task. The only place where bits can be + * set is the hard xmit routine where an SKB has a request flag set. The only + * places where we clear bits are this work function, or the periodic cleanup + * thread. If the cleanup thread clears a bit we're processing we catch it + * when we lock to clear the bit and then grab the SKB pointer. If a Tx thread + * starts a new timestamp, we might not begin processing it right away but we + * will notice it at the end when we re-queue the work item. If a Tx thread + * starts a new timestamp just after this function exits without re-queuing, + * the interrupt when the timestamp finishes should trigger. Avoiding holding + * the lock for the entire function is important in order to ensure that Tx + * threads do not get blocked while waiting for the lock. + */ +static void ice_ptp_tx_tstamp_work(struct kthread_work *work) +{ + struct ice_ptp_port *ptp_port; + struct ice_ptp_tx *tx; + struct ice_pf *pf; + struct ice_hw *hw; + u8 idx; + + tx = container_of(work, struct ice_ptp_tx, work); + if (!tx->init) + return; + + ptp_port = container_of(tx, struct ice_ptp_port, tx); + pf = ptp_port_to_pf(ptp_port); + hw = &pf->hw; + + for_each_set_bit(idx, tx->in_use, tx->len) { + struct skb_shared_hwtstamps shhwtstamps = {}; + u8 phy_idx = idx + tx->quad_offset; + u64 raw_tstamp, tstamp; + struct sk_buff *skb; + int err; + + err = ice_read_phy_tstamp(hw, tx->quad, phy_idx, + &raw_tstamp); + if (err) + continue; + + /* Check if the timestamp is valid */ + if (!(raw_tstamp & ICE_PTP_TS_VALID)) + continue; + + /* clear the timestamp register, so that it won't show valid + * again when re-used. + */ + ice_clear_phy_tstamp(hw, tx->quad, phy_idx); + + /* The timestamp is valid, so we'll go ahead and clear this + * index and then send the timestamp up to the stack. + */ + spin_lock(&tx->lock); + clear_bit(idx, tx->in_use); + skb = tx->tstamps[idx].skb; + tx->tstamps[idx].skb = NULL; + spin_unlock(&tx->lock); + + /* it's (unlikely but) possible we raced with the cleanup + * thread for discarding old timestamp requests. + */ + if (!skb) + continue; + + /* Extend the timestamp using cached PHC time */ + tstamp = ice_ptp_extend_40b_ts(pf, raw_tstamp); + shhwtstamps.hwtstamp = ns_to_ktime(tstamp); + + skb_tstamp_tx(skb, &shhwtstamps); + dev_kfree_skb_any(skb); + } + + /* Check if we still have work to do. If so, re-queue this task to + * poll for remaining timestamps. + */ + spin_lock(&tx->lock); + if (!bitmap_empty(tx->in_use, tx->len)) + kthread_queue_work(pf->ptp.kworker, &tx->work); + spin_unlock(&tx->lock); +} + +/** + * ice_ptp_request_ts - Request an available Tx timestamp index + * @tx: the PTP Tx timestamp tracker to request from + * @skb: the SKB to associate with this timestamp request + */ +s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) +{ + u8 idx; + + /* Check if this tracker is initialized */ + if (!tx->init) + return -1; + + spin_lock(&tx->lock); + /* Find and set the first available index */ + idx = find_first_zero_bit(tx->in_use, tx->len); + if (idx < tx->len) { + /* We got a valid index that no other thread could have set. Store + * a reference to the skb and the start time to allow discarding old + * requests. + */ + set_bit(idx, tx->in_use); + tx->tstamps[idx].start = jiffies; + tx->tstamps[idx].skb = skb_get(skb); + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + } + + spin_unlock(&tx->lock); + + /* return the appropriate PHY timestamp register index, -1 if no + * indexes were available. + */ + if (idx >= tx->len) + return -1; + else + return idx + tx->quad_offset; +} + +/** + * ice_ptp_process_ts - Spawn kthread work to handle timestamps + * @pf: Board private structure + * + * Queue work required to process the PTP Tx timestamps outside of interrupt + * context. + */ +void ice_ptp_process_ts(struct ice_pf *pf) +{ + if (pf->ptp.port.tx.init) + kthread_queue_work(pf->ptp.kworker, &pf->ptp.port.tx.work); +} + +/** + * ice_ptp_alloc_tx_tracker - Initialize tracking for Tx timestamps + * @tx: Tx tracking structure to initialize + * + * Assumes that the length has already been initialized. Do not call directly, + * use the ice_ptp_init_tx_e822 or ice_ptp_init_tx_e810 instead. + */ +static int +ice_ptp_alloc_tx_tracker(struct ice_ptp_tx *tx) +{ + tx->tstamps = kcalloc(tx->len, sizeof(*tx->tstamps), GFP_KERNEL); + if (!tx->tstamps) + return -ENOMEM; + + tx->in_use = bitmap_zalloc(tx->len, GFP_KERNEL); + if (!tx->in_use) { + kfree(tx->tstamps); + tx->tstamps = NULL; + return -ENOMEM; + } + + spin_lock_init(&tx->lock); + kthread_init_work(&tx->work, ice_ptp_tx_tstamp_work); + + tx->init = 1; + + return 0; +} + +/** + * ice_ptp_flush_tx_tracker - Flush any remaining timestamps from the tracker + * @pf: Board private structure + * @tx: the tracker to flush + */ +static void +ice_ptp_flush_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) +{ + u8 idx; + + for (idx = 0; idx < tx->len; idx++) { + u8 phy_idx = idx + tx->quad_offset; + + /* Clear any potential residual timestamp in the PHY block */ + if (!pf->hw.reset_ongoing) + ice_clear_phy_tstamp(&pf->hw, tx->quad, phy_idx); + + if (tx->tstamps[idx].skb) { + dev_kfree_skb_any(tx->tstamps[idx].skb); + tx->tstamps[idx].skb = NULL; + } + } +} + +/** + * ice_ptp_release_tx_tracker - Release allocated memory for Tx tracker + * @pf: Board private structure + * @tx: Tx tracking structure to release + * + * Free memory associated with the Tx timestamp tracker. + */ +static void +ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) +{ + tx->init = 0; + + kthread_cancel_work_sync(&tx->work); + + ice_ptp_flush_tx_tracker(pf, tx); + + kfree(tx->tstamps); + tx->tstamps = NULL; + + kfree(tx->in_use); + tx->in_use = NULL; + + tx->len = 0; +} + +/** + * ice_ptp_init_tx_e810 - Initialize tracking for Tx timestamps + * @pf: Board private structure + * @tx: the Tx tracking structure to initialize + * + * Initialize the Tx timestamp tracker for this PF. For E810 devices, each + * port has its own block of timestamps, independent of the other ports. + */ +static int +ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx) +{ + tx->quad = pf->hw.port_info->lport; + tx->quad_offset = 0; + tx->len = INDEX_PER_QUAD; + + return ice_ptp_alloc_tx_tracker(tx); +} + +/** + * ice_ptp_tx_tstamp_cleanup - Cleanup old timestamp requests that got dropped + * @tx: PTP Tx tracker to clean up + * + * Loop through the Tx timestamp requests and see if any of them have been + * waiting for a long time. Discard any SKBs that have been waiting for more + * than 2 seconds. This is long enough to be reasonably sure that the + * timestamp will never be captured. This might happen if the packet gets + * discarded before it reaches the PHY timestamping block. + */ +static void ice_ptp_tx_tstamp_cleanup(struct ice_ptp_tx *tx) +{ + u8 idx; + + if (!tx->init) + return; + + for_each_set_bit(idx, tx->in_use, tx->len) { + struct sk_buff *skb; + + /* Check if this SKB has been waiting for too long */ + if (time_is_after_jiffies(tx->tstamps[idx].start + 2 * HZ)) + continue; + + spin_lock(&tx->lock); + skb = tx->tstamps[idx].skb; + tx->tstamps[idx].skb = NULL; + clear_bit(idx, tx->in_use); + spin_unlock(&tx->lock); + + /* Free the SKB after we've cleared the bit */ + dev_kfree_skb_any(skb); + } +} + +static void ice_ptp_periodic_work(struct kthread_work *work) +{ + struct ice_ptp *ptp = container_of(work, struct ice_ptp, work.work); + struct ice_pf *pf = container_of(ptp, struct ice_pf, ptp); + + if (!test_bit(ICE_FLAG_PTP, pf->flags)) + return; + + ice_ptp_update_cached_phctime(pf); + + ice_ptp_tx_tstamp_cleanup(&pf->ptp.port.tx); + + /* Run twice a second */ + kthread_queue_delayed_work(ptp->kworker, &ptp->work, + msecs_to_jiffies(500)); +} + +/** + * ice_ptp_init_owner - Initialize PTP_1588_CLOCK device + * @pf: Board private structure + * + * Setup and initialize a PTP clock device that represents the device hardware + * clock. Save the clock index for other functions connected to the same + * hardware resource. + */ +static int ice_ptp_init_owner(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + struct timespec64 ts; + u8 src_idx; + int err; + + wr32(hw, GLTSYN_SYNC_DLAY, 0); + + /* Clear some HW residue and enable source clock */ + src_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + /* Enable source clocks */ + wr32(hw, GLTSYN_ENA(src_idx), GLTSYN_ENA_TSYN_ENA_M); + + /* Enable PHY time sync */ + err = ice_ptp_init_phy_e810(hw); + if (err) + goto err_exit; + + /* Clear event status indications for auxiliary pins */ + (void)rd32(hw, GLTSYN_STAT(src_idx)); + + /* Acquire the global hardware lock */ + if (!ice_ptp_lock(hw)) { + err = -EBUSY; + goto err_exit; + } + + /* Write the increment time value to PHY and LAN */ + err = ice_ptp_write_incval(hw, ICE_PTP_NOMINAL_INCVAL_E810); + if (err) { + ice_ptp_unlock(hw); + goto err_exit; + } + + ts = ktime_to_timespec64(ktime_get_real()); + /* Write the initial Time value to PHY and LAN */ + err = ice_ptp_write_init(pf, &ts); + if (err) { + ice_ptp_unlock(hw); + goto err_exit; + } + + /* Release the global hardware lock */ + ice_ptp_unlock(hw); + + /* Ensure we have a clock device */ + err = ice_ptp_create_clock(pf); + if (err) + goto err_clk; + + /* Store the PTP clock index for other PFs */ + ice_set_ptp_clock_index(pf); + + return 0; + +err_clk: + pf->ptp.clock = NULL; +err_exit: + dev_err(dev, "PTP failed to register clock, err %d\n", err); + + return err; +} + +/** + * ice_ptp_init - Initialize the PTP support after device probe or reset + * @pf: Board private structure + * + * This function sets device up for PTP support. The first time it is run, it + * will create a clock device. It does not create a clock device if one + * already exists. It also reconfigures the device after a reset. + */ +void ice_ptp_init(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct kthread_worker *kworker; + struct ice_hw *hw = &pf->hw; + int err; + + /* PTP is currently only supported on E810 devices */ + if (!ice_is_e810(hw)) + return; + + /* Check if this PF owns the source timer */ + if (hw->func_caps.ts_func_info.src_tmr_owned) { + err = ice_ptp_init_owner(pf); + if (err) + return; + } + + /* Disable timestamping for both Tx and Rx */ + ice_ptp_cfg_timestamp(pf, false); + + /* Initialize the PTP port Tx timestamp tracker */ + ice_ptp_init_tx_e810(pf, &pf->ptp.port.tx); + + /* Initialize work functions */ + kthread_init_delayed_work(&pf->ptp.work, ice_ptp_periodic_work); + kthread_init_work(&pf->ptp.extts_work, ice_ptp_extts_work); + + /* Allocate a kworker for handling work required for the ports + * connected to the PTP hardware clock. + */ + kworker = kthread_create_worker(0, "ice-ptp-%s", dev_name(dev)); + if (IS_ERR(kworker)) { + err = PTR_ERR(kworker); + goto err_kworker; + } + pf->ptp.kworker = kworker; + + set_bit(ICE_FLAG_PTP, pf->flags); + + /* Start periodic work going */ + kthread_queue_delayed_work(pf->ptp.kworker, &pf->ptp.work, 0); + + dev_info(dev, "PTP init successful\n"); + return; + +err_kworker: + /* If we registered a PTP clock, release it */ + if (pf->ptp.clock) { + ptp_clock_unregister(pf->ptp.clock); + pf->ptp.clock = NULL; + } + dev_err(dev, "PTP failed %d\n", err); +} + +/** + * ice_ptp_release - Disable the driver/HW support and unregister the clock + * @pf: Board private structure + * + * This function handles the cleanup work required from the initialization by + * clearing out the important information and unregistering the clock + */ +void ice_ptp_release(struct ice_pf *pf) +{ + /* Disable timestamping for both Tx and Rx */ + ice_ptp_cfg_timestamp(pf, false); + + ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx); + + clear_bit(ICE_FLAG_PTP, pf->flags); + + kthread_cancel_delayed_work_sync(&pf->ptp.work); + + if (pf->ptp.kworker) { + kthread_destroy_worker(pf->ptp.kworker); + pf->ptp.kworker = NULL; + } + + if (!pf->ptp.clock) + return; + + ice_clear_ptp_clock_index(pf); + ptp_clock_unregister(pf->ptp.clock); + pf->ptp.clock = NULL; + + dev_info(ice_pf_to_dev(pf), "Removed PTP clock\n"); +} diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h new file mode 100644 index 000000000000..e1c787bd5b96 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -0,0 +1,204 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021, Intel Corporation. */ + +#ifndef _ICE_PTP_H_ +#define _ICE_PTP_H_ + +#include +#include + +#include "ice_ptp_hw.h" + +enum ice_ptp_pin { + GPIO_20 = 0, + GPIO_21, + GPIO_22, + GPIO_23, + NUM_ICE_PTP_PIN +}; + +struct ice_perout_channel { + bool ena; + u32 gpio_pin; + u64 period; + u64 start_time; +}; + +/* The ice hardware captures Tx hardware timestamps in the PHY. The timestamp + * is stored in a buffer of registers. Depending on the specific hardware, + * this buffer might be shared across multiple PHY ports. + * + * On transmit of a packet to be timestamped, software is responsible for + * selecting an open index. Hardware makes no attempt to lock or prevent + * re-use of an index for multiple packets. + * + * To handle this, timestamp indexes must be tracked by software to ensure + * that an index is not re-used for multiple transmitted packets. The + * structures and functions declared in this file track the available Tx + * register indexes, as well as provide storage for the SKB pointers. + * + * To allow multiple ports to access the shared register block independently, + * the blocks are split up so that indexes are assigned to each port based on + * hardware logical port number. + */ + +/** + * struct ice_tx_tstamp - Tracking for a single Tx timestamp + * @skb: pointer to the SKB for this timestamp request + * @start: jiffies when the timestamp was first requested + * + * This structure tracks a single timestamp request. The SKB pointer is + * provided when initiating a request. The start time is used to ensure that + * we discard old requests that were not fulfilled within a 2 second time + * window. + */ +struct ice_tx_tstamp { + struct sk_buff *skb; + unsigned long start; +}; + +/** + * struct ice_ptp_tx - Tracking structure for all Tx timestamp requests on a port + * @work: work function to handle processing of Tx timestamps + * @lock: lock to prevent concurrent write to in_use bitmap + * @tstamps: array of len to store outstanding requests + * @in_use: bitmap of len to indicate which slots are in use + * @quad: which quad the timestamps are captured in + * @quad_offset: offset into timestamp block of the quad to get the real index + * @len: length of the tstamps and in_use fields. + * @init: if true, the tracker is initialized; + */ +struct ice_ptp_tx { + struct kthread_work work; + spinlock_t lock; /* lock protecting in_use bitmap */ + struct ice_tx_tstamp *tstamps; + unsigned long *in_use; + u8 quad; + u8 quad_offset; + u8 len; + u8 init; +}; + +/* Quad and port information for initializing timestamp blocks */ +#define INDEX_PER_QUAD 64 +#define INDEX_PER_PORT (INDEX_PER_QUAD / ICE_PORTS_PER_QUAD) + +/** + * struct ice_ptp_port - data used to initialize an external port for PTP + * + * This structure contains PTP data related to the external ports. Currently + * it is used for tracking the Tx timestamps of a port. In the future this + * structure will also hold information for the E822 port initialization + * logic. + * + * @tx: Tx timestamp tracking for this port + */ +struct ice_ptp_port { + struct ice_ptp_tx tx; +}; + +#define GLTSYN_TGT_H_IDX_MAX 4 + +/** + * struct ice_ptp - data used for integrating with CONFIG_PTP_1588_CLOCK + * @port: data for the PHY port initialization procedure + * @work: delayed work function for periodic tasks + * @extts_work: work function for handling external Tx timestamps + * @cached_phc_time: a cached copy of the PHC time for timestamp extension + * @ext_ts_chan: the external timestamp channel in use + * @ext_ts_irq: the external timestamp IRQ in use + * @kworker: kwork thread for handling periodic work + * @perout_channels: periodic output data + * @info: structure defining PTP hardware capabilities + * @clock: pointer to registered PTP clock device + * @tstamp_config: hardware timestamping configuration + */ +struct ice_ptp { + struct ice_ptp_port port; + struct kthread_delayed_work work; + struct kthread_work extts_work; + u64 cached_phc_time; + u8 ext_ts_chan; + u8 ext_ts_irq; + struct kthread_worker *kworker; + struct ice_perout_channel perout_channels[GLTSYN_TGT_H_IDX_MAX]; + struct ptp_clock_info info; + struct ptp_clock *clock; + struct hwtstamp_config tstamp_config; +}; + +#define __ptp_port_to_ptp(p) \ + container_of((p), struct ice_ptp, port) +#define ptp_port_to_pf(p) \ + container_of(__ptp_port_to_ptp((p)), struct ice_pf, ptp) + +#define __ptp_info_to_ptp(i) \ + container_of((i), struct ice_ptp, info) +#define ptp_info_to_pf(i) \ + container_of(__ptp_info_to_ptp((i)), struct ice_pf, ptp) + +#define PTP_SHARED_CLK_IDX_VALID BIT(31) +#define ICE_PTP_TS_VALID BIT(0) + +/* Per-channel register definitions */ +#define GLTSYN_AUX_OUT(_chan, _idx) (GLTSYN_AUX_OUT_0(_idx) + ((_chan) * 8)) +#define GLTSYN_AUX_IN(_chan, _idx) (GLTSYN_AUX_IN_0(_idx) + ((_chan) * 8)) +#define GLTSYN_CLKO(_chan, _idx) (GLTSYN_CLKO_0(_idx) + ((_chan) * 8)) +#define GLTSYN_TGT_L(_chan, _idx) (GLTSYN_TGT_L_0(_idx) + ((_chan) * 16)) +#define GLTSYN_TGT_H(_chan, _idx) (GLTSYN_TGT_H_0(_idx) + ((_chan) * 16)) +#define GLTSYN_EVNT_L(_chan, _idx) (GLTSYN_EVNT_L_0(_idx) + ((_chan) * 16)) +#define GLTSYN_EVNT_H(_chan, _idx) (GLTSYN_EVNT_H_0(_idx) + ((_chan) * 16)) +#define GLTSYN_EVNT_H_IDX_MAX 3 + +/* Pin definitions for PTP PPS out */ +#define PPS_CLK_GEN_CHAN 3 +#define PPS_CLK_SRC_CHAN 2 +#define PPS_PIN_INDEX 5 +#define TIME_SYNC_PIN_INDEX 4 +#define E810_N_EXT_TS 3 +#define E810_N_PER_OUT 4 + +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +struct ice_pf; +int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr); +int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr); +int ice_get_ptp_clock_index(struct ice_pf *pf); + +s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); +void ice_ptp_process_ts(struct ice_pf *pf); + +void +ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring, + union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb); +void ice_ptp_init(struct ice_pf *pf); +void ice_ptp_release(struct ice_pf *pf); +#else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ +static inline int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr) +{ + return -EOPNOTSUPP; +} + +static inline int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr) +{ + return -EOPNOTSUPP; +} + +static inline int ice_get_ptp_clock_index(struct ice_pf *pf) +{ + return -1; +} + +static inline s8 +ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) +{ + return -1; +} + +static inline void ice_ptp_process_ts(struct ice_pf *pf) { } +static inline void +ice_ptp_rx_hwtstamp(struct ice_ring *rx_ring, + union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { } +static inline void ice_ptp_init(struct ice_pf *pf) { } +static inline void ice_ptp_release(struct ice_pf *pf) { } +#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ +#endif /* _ICE_PTP_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c new file mode 100644 index 000000000000..3eca0e4eab0b --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -0,0 +1,651 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2021, Intel Corporation. */ + +#include "ice_common.h" +#include "ice_ptp_hw.h" + +/* Low level functions for interacting with and managing the device clock used + * for the Precision Time Protocol. + * + * The ice hardware represents the current time using three registers: + * + * GLTSYN_TIME_H GLTSYN_TIME_L GLTSYN_TIME_R + * +---------------+ +---------------+ +---------------+ + * | 32 bits | | 32 bits | | 32 bits | + * +---------------+ +---------------+ +---------------+ + * + * The registers are incremented every clock tick using a 40bit increment + * value defined over two registers: + * + * GLTSYN_INCVAL_H GLTSYN_INCVAL_L + * +---------------+ +---------------+ + * | 8 bit s | | 32 bits | + * +---------------+ +---------------+ + * + * The increment value is added to the GLSTYN_TIME_R and GLSTYN_TIME_L + * registers every clock source tick. Depending on the specific device + * configuration, the clock source frequency could be one of a number of + * values. + * + * For E810 devices, the increment frequency is 812.5 MHz + * + * The hardware captures timestamps in the PHY for incoming packets, and for + * outgoing packets on request. To support this, the PHY maintains a timer + * that matches the lower 64 bits of the global source timer. + * + * In order to ensure that the PHY timers and the source timer are equivalent, + * shadow registers are used to prepare the desired initial values. A special + * sync command is issued to trigger copying from the shadow registers into + * the appropriate source and PHY registers simultaneously. + */ + +/** + * ice_get_ptp_src_clock_index - determine source clock index + * @hw: pointer to HW struct + * + * Determine the source clock index currently in use, based on device + * capabilities reported during initialization. + */ +u8 ice_get_ptp_src_clock_index(struct ice_hw *hw) +{ + return hw->func_caps.ts_func_info.tmr_index_assoc; +} + +/* E810 functions + * + * The following functions operate on the E810 series devices which use + * a separate external PHY. + */ + +/** + * ice_read_phy_reg_e810 - Read register from external PHY on E810 + * @hw: pointer to the HW struct + * @addr: the address to read from + * @val: On return, the value read from the PHY + * + * Read a register from the external PHY on the E810 device. + */ +static int ice_read_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 *val) +{ + struct ice_sbq_msg_input msg = {0}; + int status; + + msg.msg_addr_low = lower_16_bits(addr); + msg.msg_addr_high = upper_16_bits(addr); + msg.opcode = ice_sbq_msg_rd; + msg.dest_dev = rmn_0; + + status = ice_sbq_rw_reg(hw, &msg); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, status %d\n", + status); + return status; + } + + *val = msg.data; + + return 0; +} + +/** + * ice_write_phy_reg_e810 - Write register on external PHY on E810 + * @hw: pointer to the HW struct + * @addr: the address to writem to + * @val: the value to write to the PHY + * + * Write a value to a register of the external PHY on the E810 device. + */ +static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val) +{ + struct ice_sbq_msg_input msg = {0}; + int status; + + msg.msg_addr_low = lower_16_bits(addr); + msg.msg_addr_high = upper_16_bits(addr); + msg.opcode = ice_sbq_msg_wr; + msg.dest_dev = rmn_0; + msg.data = val; + + status = ice_sbq_rw_reg(hw, &msg); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, status %d\n", + status); + return status; + } + + return 0; +} + +/** + * ice_read_phy_tstamp_e810 - Read a PHY timestamp out of the external PHY + * @hw: pointer to the HW struct + * @lport: the lport to read from + * @idx: the timestamp index to read + * @tstamp: on return, the 40bit timestamp value + * + * Read a 40bit timestamp value out of the timestamp block of the external PHY + * on the E810 device. + */ +static int +ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp) +{ + u32 lo_addr, hi_addr, lo, hi; + int status; + + lo_addr = TS_EXT(LOW_TX_MEMORY_BANK_START, lport, idx); + hi_addr = TS_EXT(HIGH_TX_MEMORY_BANK_START, lport, idx); + + status = ice_read_phy_reg_e810(hw, lo_addr, &lo); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read low PTP timestamp register, status %d\n", + status); + return status; + } + + status = ice_read_phy_reg_e810(hw, hi_addr, &hi); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read high PTP timestamp register, status %d\n", + status); + return status; + } + + /* For E810 devices, the timestamp is reported with the lower 32 bits + * in the low register, and the upper 8 bits in the high register. + */ + *tstamp = ((u64)hi) << TS_HIGH_S | ((u64)lo & TS_LOW_M); + + return 0; +} + +/** + * ice_clear_phy_tstamp_e810 - Clear a timestamp from the external PHY + * @hw: pointer to the HW struct + * @lport: the lport to read from + * @idx: the timestamp index to reset + * + * Clear a timestamp, resetting its valid bit, from the timestamp block of the + * external PHY on the E810 device. + */ +static int ice_clear_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx) +{ + u32 lo_addr, hi_addr; + int status; + + lo_addr = TS_EXT(LOW_TX_MEMORY_BANK_START, lport, idx); + hi_addr = TS_EXT(HIGH_TX_MEMORY_BANK_START, lport, idx); + + status = ice_write_phy_reg_e810(hw, lo_addr, 0); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to clear low PTP timestamp register, status %d\n", + status); + return status; + } + + status = ice_write_phy_reg_e810(hw, hi_addr, 0); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to clear high PTP timestamp register, status %d\n", + status); + return status; + } + + return 0; +} + +/** + * ice_ptp_init_phy_e810 - Enable PTP function on the external PHY + * @hw: pointer to HW struct + * + * Enable the timesync PTP functionality for the external PHY connected to + * this function. + */ +int ice_ptp_init_phy_e810(struct ice_hw *hw) +{ + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_ENA(tmr_idx), + GLTSYN_ENA_TSYN_ENA_M); + if (status) + ice_debug(hw, ICE_DBG_PTP, "PTP failed in ena_phy_time_syn %d\n", + status); + + return status; +} + +/** + * ice_ptp_prep_phy_time_e810 - Prepare PHY port with initial time + * @hw: Board private structure + * @time: Time to initialize the PHY port clock to + * + * Program the PHY port ETH_GLTSYN_SHTIME registers in preparation setting the + * initial clock time. The time will not actually be programmed until the + * driver issues an INIT_TIME command. + * + * The time value is the upper 32 bits of the PHY timer, usually in units of + * nominal nanoseconds. + */ +static int ice_ptp_prep_phy_time_e810(struct ice_hw *hw, u32 time) +{ + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHTIME_0(tmr_idx), 0); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write SHTIME_0, status %d\n", + status); + return status; + } + + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHTIME_L(tmr_idx), time); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write SHTIME_L, status %d\n", + status); + return status; + } + + return 0; +} + +/** + * ice_ptp_prep_phy_adj_e810 - Prep PHY port for a time adjustment + * @hw: pointer to HW struct + * @adj: adjustment value to program + * + * Prepare the PHY port for an atomic adjustment by programming the PHY + * ETH_GLTSYN_SHADJ_L and ETH_GLTSYN_SHADJ_H registers. The actual adjustment + * is completed by issuing an ADJ_TIME sync command. + * + * The adjustment value only contains the portion used for the upper 32bits of + * the PHY timer, usually in units of nominal nanoseconds. Negative + * adjustments are supported using 2s complement arithmetic. + */ +static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj) +{ + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + /* Adjustments are represented as signed 2's complement values in + * nanoseconds. Sub-nanosecond adjustment is not supported. + */ + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHADJ_L(tmr_idx), 0); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write adj to PHY SHADJ_L, status %d\n", + status); + return status; + } + + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHADJ_H(tmr_idx), adj); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write adj to PHY SHADJ_H, status %d\n", + status); + return status; + } + + return 0; +} + +/** + * ice_ptp_prep_phy_incval_e810 - Prep PHY port increment value change + * @hw: pointer to HW struct + * @incval: The new 40bit increment value to prepare + * + * Prepare the PHY port for a new increment value by programming the PHY + * ETH_GLTSYN_SHADJ_L and ETH_GLTSYN_SHADJ_H registers. The actual change is + * completed by issuing an INIT_INCVAL command. + */ +static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval) +{ + u32 high, low; + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + low = lower_32_bits(incval); + high = upper_32_bits(incval); + + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHADJ_L(tmr_idx), low); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write incval to PHY SHADJ_L, status %d\n", + status); + return status; + } + + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_SHADJ_H(tmr_idx), high); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write incval PHY SHADJ_H, status %d\n", + status); + return status; + } + + return 0; +} + +/** + * ice_ptp_port_cmd_e810 - Prepare all external PHYs for a timer command + * @hw: pointer to HW struct + * @cmd: Command to be sent to the port + * + * Prepare the external PHYs connected to this device for a timer sync + * command. + */ +static int ice_ptp_port_cmd_e810(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +{ + u32 cmd_val, val; + int status; + + switch (cmd) { + case INIT_TIME: + cmd_val = GLTSYN_CMD_INIT_TIME; + break; + case INIT_INCVAL: + cmd_val = GLTSYN_CMD_INIT_INCVAL; + break; + case ADJ_TIME: + cmd_val = GLTSYN_CMD_ADJ_TIME; + break; + case READ_TIME: + cmd_val = GLTSYN_CMD_READ_TIME; + break; + case ADJ_TIME_AT_TIME: + cmd_val = GLTSYN_CMD_ADJ_INIT_TIME; + break; + } + + /* Read, modify, write */ + status = ice_read_phy_reg_e810(hw, ETH_GLTSYN_CMD, &val); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read GLTSYN_CMD, status %d\n", status); + return status; + } + + /* Modify necessary bits only and perform write */ + val &= ~TS_CMD_MASK_E810; + val |= cmd_val; + + status = ice_write_phy_reg_e810(hw, ETH_GLTSYN_CMD, val); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to write back GLTSYN_CMD, status %d\n", status); + return status; + } + + return 0; +} + +/* Device agnostic functions + * + * The following functions implement useful behavior to hide the differences + * between E810 and other devices. They call the device-specific + * implementations where necessary. + * + * Currently, the driver only supports E810, but future work will enable + * support for E822-based devices. + */ + +/** + * ice_ptp_lock - Acquire PTP global semaphore register lock + * @hw: pointer to the HW struct + * + * Acquire the global PTP hardware semaphore lock. Returns true if the lock + * was acquired, false otherwise. + * + * The PFTSYN_SEM register sets the busy bit on read, returning the previous + * value. If software sees the busy bit cleared, this means that this function + * acquired the lock (and the busy bit is now set). If software sees the busy + * bit set, it means that another function acquired the lock. + * + * Software must clear the busy bit with a write to release the lock for other + * functions when done. + */ +bool ice_ptp_lock(struct ice_hw *hw) +{ + u32 hw_lock; + int i; + +#define MAX_TRIES 5 + + for (i = 0; i < MAX_TRIES; i++) { + hw_lock = rd32(hw, PFTSYN_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); + hw_lock = hw_lock & PFTSYN_SEM_BUSY_M; + if (!hw_lock) + break; + + /* Somebody is holding the lock */ + usleep_range(10000, 20000); + } + + return !hw_lock; +} + +/** + * ice_ptp_unlock - Release PTP global semaphore register lock + * @hw: pointer to the HW struct + * + * Release the global PTP hardware semaphore lock. This is done by writing to + * the PFTSYN_SEM register. + */ +void ice_ptp_unlock(struct ice_hw *hw) +{ + wr32(hw, PFTSYN_SEM + (PFTSYN_SEM_BYTES * hw->pf_id), 0); +} + +/** + * ice_ptp_src_cmd - Prepare source timer for a timer command + * @hw: pointer to HW structure + * @cmd: Timer command + * + * Prepare the source timer for an upcoming timer sync command. + */ +static void ice_ptp_src_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +{ + u32 cmd_val; + u8 tmr_idx; + + tmr_idx = ice_get_ptp_src_clock_index(hw); + cmd_val = tmr_idx << SEL_CPK_SRC; + + switch (cmd) { + case INIT_TIME: + cmd_val |= GLTSYN_CMD_INIT_TIME; + break; + case INIT_INCVAL: + cmd_val |= GLTSYN_CMD_INIT_INCVAL; + break; + case ADJ_TIME: + cmd_val |= GLTSYN_CMD_ADJ_TIME; + break; + case ADJ_TIME_AT_TIME: + cmd_val |= GLTSYN_CMD_ADJ_INIT_TIME; + break; + case READ_TIME: + cmd_val |= GLTSYN_CMD_READ_TIME; + break; + } + + wr32(hw, GLTSYN_CMD, cmd_val); +} + +/** + * ice_ptp_tmr_cmd - Prepare and trigger a timer sync command + * @hw: pointer to HW struct + * @cmd: the command to issue + * + * Prepare the source timer and PHY timers and then trigger the requested + * command. This causes the shadow registers previously written in preparation + * for the command to be synchronously applied to both the source and PHY + * timers. + */ +static int ice_ptp_tmr_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +{ + int status; + + /* First, prepare the source timer */ + ice_ptp_src_cmd(hw, cmd); + + /* Next, prepare the ports */ + status = ice_ptp_port_cmd_e810(hw, cmd); + if (status) { + ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY ports for timer command %u, status %d\n", + cmd, status); + return status; + } + + /* Write the sync command register to drive both source and PHY timer commands + * synchronously + */ + wr32(hw, GLTSYN_CMD_SYNC, SYNC_EXEC_CMD); + + return 0; +} + +/** + * ice_ptp_init_time - Initialize device time to provided value + * @hw: pointer to HW struct + * @time: 64bits of time (GLTSYN_TIME_L and GLTSYN_TIME_H) + * + * Initialize the device to the specified time provided. This requires a three + * step process: + * + * 1) write the new init time to the source timer shadow registers + * 2) write the new init time to the PHY timer shadow registers + * 3) issue an init_time timer command to synchronously switch both the source + * and port timers to the new init time value at the next clock cycle. + */ +int ice_ptp_init_time(struct ice_hw *hw, u64 time) +{ + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + /* Source timers */ + wr32(hw, GLTSYN_SHTIME_L(tmr_idx), lower_32_bits(time)); + wr32(hw, GLTSYN_SHTIME_H(tmr_idx), upper_32_bits(time)); + wr32(hw, GLTSYN_SHTIME_0(tmr_idx), 0); + + /* PHY timers */ + /* Fill Rx and Tx ports and send msg to PHY */ + status = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF); + if (status) + return status; + + return ice_ptp_tmr_cmd(hw, INIT_TIME); +} + +/** + * ice_ptp_write_incval - Program PHC with new increment value + * @hw: pointer to HW struct + * @incval: Source timer increment value per clock cycle + * + * Program the PHC with a new increment value. This requires a three-step + * process: + * + * 1) Write the increment value to the source timer shadow registers + * 2) Write the increment value to the PHY timer shadow registers + * 3) Issue an INIT_INCVAL timer command to synchronously switch both the + * source and port timers to the new increment value at the next clock + * cycle. + */ +int ice_ptp_write_incval(struct ice_hw *hw, u64 incval) +{ + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + /* Shadow Adjust */ + wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval)); + wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval)); + + status = ice_ptp_prep_phy_incval_e810(hw, incval); + if (status) + return status; + + return ice_ptp_tmr_cmd(hw, INIT_INCVAL); +} + +/** + * ice_ptp_write_incval_locked - Program new incval while holding semaphore + * @hw: pointer to HW struct + * @incval: Source timer increment value per clock cycle + * + * Program a new PHC incval while holding the PTP semaphore. + */ +int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval) +{ + int status; + + if (!ice_ptp_lock(hw)) + return -EBUSY; + + status = ice_ptp_write_incval(hw, incval); + + ice_ptp_unlock(hw); + + return status; +} + +/** + * ice_ptp_adj_clock - Adjust PHC clock time atomically + * @hw: pointer to HW struct + * @adj: Adjustment in nanoseconds + * + * Perform an atomic adjustment of the PHC time by the specified number of + * nanoseconds. This requires a three-step process: + * + * 1) Write the adjustment to the source timer shadow registers + * 2) Write the adjustment to the PHY timer shadow registers + * 3) Issue an ADJ_TIME timer command to synchronously apply the adjustment to + * both the source and port timers at the next clock cycle. + */ +int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) +{ + int status; + u8 tmr_idx; + + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + /* Write the desired clock adjustment into the GLTSYN_SHADJ register. + * For an ADJ_TIME command, this set of registers represents the value + * to add to the clock time. It supports subtraction by interpreting + * the value as a 2's complement integer. + */ + wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0); + wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj); + + status = ice_ptp_prep_phy_adj_e810(hw, adj); + if (status) + return status; + + return ice_ptp_tmr_cmd(hw, ADJ_TIME); +} + +/** + * ice_read_phy_tstamp - Read a PHY timestamp from the timestamo block + * @hw: pointer to the HW struct + * @block: the block to read from + * @idx: the timestamp index to read + * @tstamp: on return, the 40bit timestamp value + * + * Read a 40bit timestamp value out of the timestamp block. + */ +int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) +{ + return ice_read_phy_tstamp_e810(hw, block, idx, tstamp); +} + +/** + * ice_clear_phy_tstamp - Clear a timestamp from the timestamp block + * @hw: pointer to the HW struct + * @block: the block to read from + * @idx: the timestamp index to reset + * + * Clear a timestamp, resetting its valid bit, from the timestamp block. + */ +int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) +{ + return ice_clear_phy_tstamp_e810(hw, block, idx); +} diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h new file mode 100644 index 000000000000..55a414e87018 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021, Intel Corporation. */ + +#ifndef _ICE_PTP_HW_H_ +#define _ICE_PTP_HW_H_ + +enum ice_ptp_tmr_cmd { + INIT_TIME, + INIT_INCVAL, + ADJ_TIME, + ADJ_TIME_AT_TIME, + READ_TIME +}; + +/* Increment value to generate nanoseconds in the GLTSYN_TIME_L register for + * the E810 devices. Based off of a PLL with an 812.5 MHz frequency. + */ +#define ICE_PTP_NOMINAL_INCVAL_E810 0x13b13b13bULL + +/* Device agnostic functions */ +u8 ice_get_ptp_src_clock_index(struct ice_hw *hw); +bool ice_ptp_lock(struct ice_hw *hw); +void ice_ptp_unlock(struct ice_hw *hw); +int ice_ptp_init_time(struct ice_hw *hw, u64 time); +int ice_ptp_write_incval(struct ice_hw *hw, u64 incval); +int ice_ptp_write_incval_locked(struct ice_hw *hw, u64 incval); +int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj); +int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp); +int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx); + +/* E810 family functions */ +int ice_ptp_init_phy_e810(struct ice_hw *hw); + +#define PFTSYN_SEM_BYTES 4 + +/* PHY timer commands */ +#define SEL_CPK_SRC 8 + +/* Time Sync command Definitions */ +#define GLTSYN_CMD_INIT_TIME BIT(0) +#define GLTSYN_CMD_INIT_INCVAL BIT(1) +#define GLTSYN_CMD_ADJ_TIME BIT(2) +#define GLTSYN_CMD_ADJ_INIT_TIME (BIT(2) | BIT(3)) +#define GLTSYN_CMD_READ_TIME BIT(7) + +#define TS_CMD_MASK_E810 0xFF +#define SYNC_EXEC_CMD 0x3 + +/* E810 timesync enable register */ +#define ETH_GLTSYN_ENA(_i) (0x03000348 + ((_i) * 4)) + +/* E810 shadow init time registers */ +#define ETH_GLTSYN_SHTIME_0(i) (0x03000368 + ((i) * 32)) +#define ETH_GLTSYN_SHTIME_L(i) (0x0300036C + ((i) * 32)) + +/* E810 shadow time adjust registers */ +#define ETH_GLTSYN_SHADJ_L(_i) (0x03000378 + ((_i) * 32)) +#define ETH_GLTSYN_SHADJ_H(_i) (0x0300037C + ((_i) * 32)) + +/* E810 timer command register */ +#define ETH_GLTSYN_CMD 0x03000344 + +/* Source timer incval macros */ +#define INCVAL_HIGH_M 0xFF + +/* Timestamp block macros */ +#define TS_LOW_M 0xFFFFFFFF +#define TS_HIGH_S 32 + +#define BYTES_PER_IDX_ADDR_L_U 8 + +/* External PHY timestamp address */ +#define TS_EXT(a, port, idx) ((a) + (0x1000 * (port)) + \ + ((idx) * BYTES_PER_IDX_ADDR_L_U)) + +#define LOW_TX_MEMORY_BANK_START 0x03090000 +#define HIGH_TX_MEMORY_BANK_START 0x03090004 + +#endif /* _ICE_PTP_HW_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h new file mode 100644 index 000000000000..ead75fe2bcda --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021, Intel Corporation. */ + +#ifndef _ICE_SBQ_CMD_H_ +#define _ICE_SBQ_CMD_H_ + +/* This header file defines the Sideband Queue commands, error codes and + * descriptor format. It is shared between Firmware and Software. + */ + +/* Sideband Queue command structure and opcodes */ +enum ice_sbq_opc { + /* Sideband Queue commands */ + ice_sbq_opc_neigh_dev_req = 0x0C00, + ice_sbq_opc_neigh_dev_ev = 0x0C01 +}; + +/* Sideband Queue descriptor. Indirect command + * and non posted + */ +struct ice_sbq_cmd_desc { + __le16 flags; + __le16 opcode; + __le16 datalen; + __le16 cmd_retval; + + /* Opaque message data */ + __le32 cookie_high; + __le32 cookie_low; + + union { + __le16 cmd_len; + __le16 cmpl_len; + } param0; + + u8 reserved[6]; + __le32 addr_high; + __le32 addr_low; +}; + +struct ice_sbq_evt_desc { + __le16 flags; + __le16 opcode; + __le16 datalen; + __le16 cmd_retval; + u8 data[24]; +}; + +enum ice_sbq_msg_dev { + rmn_0 = 0x02, + rmn_1 = 0x03, + rmn_2 = 0x04, + cgu = 0x06 +}; + +enum ice_sbq_msg_opcode { + ice_sbq_msg_rd = 0x00, + ice_sbq_msg_wr = 0x01 +}; + +#define ICE_SBQ_MSG_FLAGS 0x40 +#define ICE_SBQ_MSG_SBE_FBE 0x0F + +struct ice_sbq_msg_req { + u8 dest_dev; + u8 src_dev; + u8 opcode; + u8 flags; + u8 sbe_fbe; + u8 func_id; + __le16 msg_addr_low; + __le32 msg_addr_high; + __le32 data; +}; + +struct ice_sbq_msg_cmpl { + u8 dest_dev; + u8 src_dev; + u8 opcode; + u8 flags; + __le32 data; +}; + +/* Internal struct */ +struct ice_sbq_msg_input { + u8 dest_dev; + u8 opcode; + u16 msg_addr_low; + u32 msg_addr_high; + u32 data; +}; +#endif /* _ICE_SBQ_CMD_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 2f097637e405..9f07b6641705 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -595,6 +595,50 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) return 0; } +/** + * ice_alloc_rdma_q_ctx - allocate RDMA queue contexts for the given VSI and TC + * @hw: pointer to the HW struct + * @vsi_handle: VSI handle + * @tc: TC number + * @new_numqs: number of queues + */ +static enum ice_status +ice_alloc_rdma_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) +{ + struct ice_vsi_ctx *vsi_ctx; + struct ice_q_ctx *q_ctx; + + vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); + if (!vsi_ctx) + return ICE_ERR_PARAM; + /* allocate RDMA queue contexts */ + if (!vsi_ctx->rdma_q_ctx[tc]) { + vsi_ctx->rdma_q_ctx[tc] = devm_kcalloc(ice_hw_to_dev(hw), + new_numqs, + sizeof(*q_ctx), + GFP_KERNEL); + if (!vsi_ctx->rdma_q_ctx[tc]) + return ICE_ERR_NO_MEMORY; + vsi_ctx->num_rdma_q_entries[tc] = new_numqs; + return 0; + } + /* num queues are increased, update the queue contexts */ + if (new_numqs > vsi_ctx->num_rdma_q_entries[tc]) { + u16 prev_num = vsi_ctx->num_rdma_q_entries[tc]; + + q_ctx = devm_kcalloc(ice_hw_to_dev(hw), new_numqs, + sizeof(*q_ctx), GFP_KERNEL); + if (!q_ctx) + return ICE_ERR_NO_MEMORY; + memcpy(q_ctx, vsi_ctx->rdma_q_ctx[tc], + prev_num * sizeof(*q_ctx)); + devm_kfree(ice_hw_to_dev(hw), vsi_ctx->rdma_q_ctx[tc]); + vsi_ctx->rdma_q_ctx[tc] = q_ctx; + vsi_ctx->num_rdma_q_entries[tc] = new_numqs; + } + return 0; +} + /** * ice_aq_rl_profile - performs a rate limiting task * @hw: pointer to the HW struct @@ -1774,13 +1818,22 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, if (!vsi_ctx) return ICE_ERR_PARAM; - prev_numqs = vsi_ctx->sched.max_lanq[tc]; + if (owner == ICE_SCHED_NODE_OWNER_LAN) + prev_numqs = vsi_ctx->sched.max_lanq[tc]; + else + prev_numqs = vsi_ctx->sched.max_rdmaq[tc]; /* num queues are not changed or less than the previous number */ if (new_numqs <= prev_numqs) return status; - status = ice_alloc_lan_q_ctx(hw, vsi_handle, tc, new_numqs); - if (status) - return status; + if (owner == ICE_SCHED_NODE_OWNER_LAN) { + status = ice_alloc_lan_q_ctx(hw, vsi_handle, tc, new_numqs); + if (status) + return status; + } else { + status = ice_alloc_rdma_q_ctx(hw, vsi_handle, tc, new_numqs); + if (status) + return status; + } if (new_numqs) ice_sched_calc_vsi_child_nodes(hw, new_numqs, new_num_nodes); @@ -1795,7 +1848,10 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, new_num_nodes, owner); if (status) return status; - vsi_ctx->sched.max_lanq[tc] = new_numqs; + if (owner == ICE_SCHED_NODE_OWNER_LAN) + vsi_ctx->sched.max_lanq[tc] = new_numqs; + else + vsi_ctx->sched.max_rdmaq[tc] = new_numqs; return 0; } @@ -1861,6 +1917,7 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, * recreate the child nodes all the time in these cases. */ vsi_ctx->sched.max_lanq[tc] = 0; + vsi_ctx->sched.max_rdmaq[tc] = 0; } /* update the VSI child nodes */ @@ -1990,6 +2047,8 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner) } if (owner == ICE_SCHED_NODE_OWNER_LAN) vsi_ctx->sched.max_lanq[i] = 0; + else + vsi_ctx->sched.max_rdmaq[i] = 0; } status = 0; @@ -2686,8 +2745,8 @@ static enum ice_status ice_sched_assoc_vsi_to_agg(struct ice_port_info *pi, u32 agg_id, u16 vsi_handle, unsigned long *tc_bitmap) { - struct ice_sched_agg_vsi_info *agg_vsi_info; - struct ice_sched_agg_info *agg_info; + struct ice_sched_agg_vsi_info *agg_vsi_info, *old_agg_vsi_info = NULL; + struct ice_sched_agg_info *agg_info, *old_agg_info; enum ice_status status = 0; struct ice_hw *hw = pi->hw; u8 tc; @@ -2697,6 +2756,20 @@ ice_sched_assoc_vsi_to_agg(struct ice_port_info *pi, u32 agg_id, agg_info = ice_get_agg_info(hw, agg_id); if (!agg_info) return ICE_ERR_PARAM; + /* If the VSI is already part of another aggregator then update + * its VSI info list + */ + old_agg_info = ice_get_vsi_agg_info(hw, vsi_handle); + if (old_agg_info && old_agg_info != agg_info) { + struct ice_sched_agg_vsi_info *vtmp; + + list_for_each_entry_safe(old_agg_vsi_info, vtmp, + &old_agg_info->agg_vsi_list, + list_entry) + if (old_agg_vsi_info->vsi_handle == vsi_handle) + break; + } + /* check if entry already exist */ agg_vsi_info = ice_get_agg_vsi_info(agg_info, vsi_handle); if (!agg_vsi_info) { @@ -2721,6 +2794,12 @@ ice_sched_assoc_vsi_to_agg(struct ice_port_info *pi, u32 agg_id, break; set_bit(tc, agg_vsi_info->tc_bitmap); + if (old_agg_vsi_info) + clear_bit(tc, old_agg_vsi_info->tc_bitmap); + } + if (old_agg_vsi_info && !old_agg_vsi_info->tc_bitmap[0]) { + list_del(&old_agg_vsi_info->list_entry); + devm_kfree(ice_hw_to_dev(pi->hw), old_agg_vsi_info); } return status; } diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 357d3073d814..3b6c1420aa7b 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018, Intel Corporation. */ +#include "ice_lib.h" #include "ice_switch.h" #define ICE_ETH_DA_OFFSET 0 @@ -302,6 +303,10 @@ static void ice_clear_vsi_q_ctx(struct ice_hw *hw, u16 vsi_handle) devm_kfree(ice_hw_to_dev(hw), vsi->lan_q_ctx[i]); vsi->lan_q_ctx[i] = NULL; } + if (vsi->rdma_q_ctx[i]) { + devm_kfree(ice_hw_to_dev(hw), vsi->rdma_q_ctx[i]); + vsi->rdma_q_ctx[i] = NULL; + } } } @@ -422,6 +427,29 @@ ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, return ice_aq_update_vsi(hw, vsi_ctx, cd); } +/** + * ice_cfg_rdma_fltr - enable/disable RDMA filtering on VSI + * @hw: pointer to HW struct + * @vsi_handle: VSI SW index + * @enable: boolean for enable/disable + */ +int +ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable) +{ + struct ice_vsi_ctx *ctx; + + ctx = ice_get_vsi_ctx(hw, vsi_handle); + if (!ctx) + return -EIO; + + if (enable) + ctx->info.q_opt_flags |= ICE_AQ_VSI_Q_OPT_PE_FLTR_EN; + else + ctx->info.q_opt_flags &= ~ICE_AQ_VSI_Q_OPT_PE_FLTR_EN; + + return ice_status_to_errno(ice_update_vsi(hw, vsi_handle, ctx, NULL)); +} + /** * ice_aq_alloc_free_vsi_list * @hw: pointer to the HW struct diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 8b4f9d35c860..c5db8d56133f 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -26,6 +26,8 @@ struct ice_vsi_ctx { u8 vf_num; u16 num_lan_q_entries[ICE_MAX_TRAFFIC_CLASS]; struct ice_q_ctx *lan_q_ctx[ICE_MAX_TRAFFIC_CLASS]; + u16 num_rdma_q_entries[ICE_MAX_TRAFFIC_CLASS]; + struct ice_q_ctx *rdma_q_ctx[ICE_MAX_TRAFFIC_CLASS]; }; enum ice_sw_fwd_act_type { @@ -223,6 +225,8 @@ enum ice_status ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list); enum ice_status ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list); +int +ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable); void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle); enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *m_list); @@ -243,7 +247,6 @@ ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, enum ice_status ice_init_def_sw_recp(struct ice_hw *hw); u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle); -bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle); enum ice_status ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle); void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw); diff --git a/drivers/net/ethernet/intel/ice/ice_trace.h b/drivers/net/ethernet/intel/ice/ice_trace.h new file mode 100644 index 000000000000..9bc0b8fdfc77 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_trace.h @@ -0,0 +1,232 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021 Intel Corporation. */ + +/* Modeled on trace-events-sample.h */ + +/* The trace subsystem name for ice will be "ice". + * + * This file is named ice_trace.h. + * + * Since this include file's name is different from the trace + * subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end + * of this file. + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM ice + +/* See trace-events-sample.h for a detailed description of why this + * guard clause is different from most normal include files. + */ +#if !defined(_ICE_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _ICE_TRACE_H_ + +#include + +/* ice_trace() macro enables shared code to refer to trace points + * like: + * + * trace_ice_example(args...) + * + * ... as: + * + * ice_trace(example, args...) + * + * ... to resolve to the PF version of the tracepoint without + * ifdefs, and to allow tracepoints to be disabled entirely at build + * time. + * + * Trace point should always be referred to in the driver via this + * macro. + * + * Similarly, ice_trace_enabled(trace_name) wraps references to + * trace_ice__enabled() functions. + * @trace_name: name of tracepoint + */ +#define _ICE_TRACE_NAME(trace_name) (trace_##ice##_##trace_name) +#define ICE_TRACE_NAME(trace_name) _ICE_TRACE_NAME(trace_name) + +#define ice_trace(trace_name, args...) ICE_TRACE_NAME(trace_name)(args) + +#define ice_trace_enabled(trace_name) ICE_TRACE_NAME(trace_name##_enabled)() + +/* This is for events common to PF. Corresponding versions will be named + * trace_ice_*. The ice_trace() macro above will select the right trace point + * name for the driver. + */ + +/* Begin tracepoints */ + +/* Global tracepoints */ + +/* Events related to DIM, q_vectors and ring containers */ +DECLARE_EVENT_CLASS(ice_rx_dim_template, + TP_PROTO(struct ice_q_vector *q_vector, struct dim *dim), + TP_ARGS(q_vector, dim), + TP_STRUCT__entry(__field(struct ice_q_vector *, q_vector) + __field(struct dim *, dim) + __string(devname, q_vector->rx.ring->netdev->name)), + + TP_fast_assign(__entry->q_vector = q_vector; + __entry->dim = dim; + __assign_str(devname, q_vector->rx.ring->netdev->name);), + + TP_printk("netdev: %s Rx-Q: %d dim-state: %d dim-profile: %d dim-tune: %d dim-st-right: %d dim-st-left: %d dim-tired: %d", + __get_str(devname), + __entry->q_vector->rx.ring->q_index, + __entry->dim->state, + __entry->dim->profile_ix, + __entry->dim->tune_state, + __entry->dim->steps_right, + __entry->dim->steps_left, + __entry->dim->tired) +); + +DEFINE_EVENT(ice_rx_dim_template, ice_rx_dim_work, + TP_PROTO(struct ice_q_vector *q_vector, struct dim *dim), + TP_ARGS(q_vector, dim) +); + +DECLARE_EVENT_CLASS(ice_tx_dim_template, + TP_PROTO(struct ice_q_vector *q_vector, struct dim *dim), + TP_ARGS(q_vector, dim), + TP_STRUCT__entry(__field(struct ice_q_vector *, q_vector) + __field(struct dim *, dim) + __string(devname, q_vector->tx.ring->netdev->name)), + + TP_fast_assign(__entry->q_vector = q_vector; + __entry->dim = dim; + __assign_str(devname, q_vector->tx.ring->netdev->name);), + + TP_printk("netdev: %s Tx-Q: %d dim-state: %d dim-profile: %d dim-tune: %d dim-st-right: %d dim-st-left: %d dim-tired: %d", + __get_str(devname), + __entry->q_vector->tx.ring->q_index, + __entry->dim->state, + __entry->dim->profile_ix, + __entry->dim->tune_state, + __entry->dim->steps_right, + __entry->dim->steps_left, + __entry->dim->tired) +); + +DEFINE_EVENT(ice_tx_dim_template, ice_tx_dim_work, + TP_PROTO(struct ice_q_vector *q_vector, struct dim *dim), + TP_ARGS(q_vector, dim) +); + +/* Events related to a vsi & ring */ +DECLARE_EVENT_CLASS(ice_tx_template, + TP_PROTO(struct ice_ring *ring, struct ice_tx_desc *desc, + struct ice_tx_buf *buf), + + TP_ARGS(ring, desc, buf), + TP_STRUCT__entry(__field(void *, ring) + __field(void *, desc) + __field(void *, buf) + __string(devname, ring->netdev->name)), + + TP_fast_assign(__entry->ring = ring; + __entry->desc = desc; + __entry->buf = buf; + __assign_str(devname, ring->netdev->name);), + + TP_printk("netdev: %s ring: %pK desc: %pK buf %pK", __get_str(devname), + __entry->ring, __entry->desc, __entry->buf) +); + +#define DEFINE_TX_TEMPLATE_OP_EVENT(name) \ +DEFINE_EVENT(ice_tx_template, name, \ + TP_PROTO(struct ice_ring *ring, \ + struct ice_tx_desc *desc, \ + struct ice_tx_buf *buf), \ + TP_ARGS(ring, desc, buf)) + +DEFINE_TX_TEMPLATE_OP_EVENT(ice_clean_tx_irq); +DEFINE_TX_TEMPLATE_OP_EVENT(ice_clean_tx_irq_unmap); +DEFINE_TX_TEMPLATE_OP_EVENT(ice_clean_tx_irq_unmap_eop); + +DECLARE_EVENT_CLASS(ice_rx_template, + TP_PROTO(struct ice_ring *ring, union ice_32b_rx_flex_desc *desc), + + TP_ARGS(ring, desc), + + TP_STRUCT__entry(__field(void *, ring) + __field(void *, desc) + __string(devname, ring->netdev->name)), + + TP_fast_assign(__entry->ring = ring; + __entry->desc = desc; + __assign_str(devname, ring->netdev->name);), + + TP_printk("netdev: %s ring: %pK desc: %pK", __get_str(devname), + __entry->ring, __entry->desc) +); +DEFINE_EVENT(ice_rx_template, ice_clean_rx_irq, + TP_PROTO(struct ice_ring *ring, union ice_32b_rx_flex_desc *desc), + TP_ARGS(ring, desc) +); + +DECLARE_EVENT_CLASS(ice_rx_indicate_template, + TP_PROTO(struct ice_ring *ring, union ice_32b_rx_flex_desc *desc, + struct sk_buff *skb), + + TP_ARGS(ring, desc, skb), + + TP_STRUCT__entry(__field(void *, ring) + __field(void *, desc) + __field(void *, skb) + __string(devname, ring->netdev->name)), + + TP_fast_assign(__entry->ring = ring; + __entry->desc = desc; + __entry->skb = skb; + __assign_str(devname, ring->netdev->name);), + + TP_printk("netdev: %s ring: %pK desc: %pK skb %pK", __get_str(devname), + __entry->ring, __entry->desc, __entry->skb) +); + +DEFINE_EVENT(ice_rx_indicate_template, ice_clean_rx_irq_indicate, + TP_PROTO(struct ice_ring *ring, union ice_32b_rx_flex_desc *desc, + struct sk_buff *skb), + TP_ARGS(ring, desc, skb) +); + +DECLARE_EVENT_CLASS(ice_xmit_template, + TP_PROTO(struct ice_ring *ring, struct sk_buff *skb), + + TP_ARGS(ring, skb), + + TP_STRUCT__entry(__field(void *, ring) + __field(void *, skb) + __string(devname, ring->netdev->name)), + + TP_fast_assign(__entry->ring = ring; + __entry->skb = skb; + __assign_str(devname, ring->netdev->name);), + + TP_printk("netdev: %s skb: %pK ring: %pK", __get_str(devname), + __entry->skb, __entry->ring) +); + +#define DEFINE_XMIT_TEMPLATE_OP_EVENT(name) \ +DEFINE_EVENT(ice_xmit_template, name, \ + TP_PROTO(struct ice_ring *ring, struct sk_buff *skb), \ + TP_ARGS(ring, skb)) + +DEFINE_XMIT_TEMPLATE_OP_EVENT(ice_xmit_frame_ring); +DEFINE_XMIT_TEMPLATE_OP_EVENT(ice_xmit_frame_ring_drop); + +/* End tracepoints */ + +#endif /* _ICE_TRACE_H_ */ +/* This must be outside ifdef _ICE_TRACE_H */ + +/* This trace include file is not located in the .../include/trace + * with the kernel tracepoint definitions, because we're a loadable + * module. + */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE ../../drivers/net/ethernet/intel/ice/ice_trace +#include diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 04748aa4c7c8..6ee8e0032d52 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -10,6 +10,7 @@ #include "ice_txrx_lib.h" #include "ice_lib.h" #include "ice.h" +#include "ice_trace.h" #include "ice_dcb_lib.h" #include "ice_xsk.h" @@ -224,6 +225,7 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) smp_rmb(); /* prevent any other reads prior to eop_desc */ + ice_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); /* if the descriptor isn't done, no work yet to do */ if (!(eop_desc->cmd_type_offset_bsz & cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) @@ -254,6 +256,7 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) /* unmap remaining buffers */ while (tx_desc != eop_desc) { + ice_trace(clean_tx_irq_unmap, tx_ring, tx_desc, tx_buf); tx_buf++; tx_desc++; i++; @@ -272,6 +275,7 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) dma_unmap_len_set(tx_buf, len, 0); } } + ice_trace(clean_tx_irq_unmap_eop, tx_ring, tx_desc, tx_buf); /* move us one more past the eop_desc for start of next pkt */ tx_buf++; @@ -1082,7 +1086,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) u16 stat_err_bits; int rx_buf_pgcnt; u16 vlan_tag = 0; - u8 rx_ptype; + u16 rx_ptype; /* get the Rx desc from Rx ring based on 'next_to_clean' */ rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean); @@ -1102,6 +1106,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) */ dma_rmb(); + ice_trace(clean_rx_irq, rx_ring, rx_desc); if (rx_desc->wb.rxdid == FDIR_DESC_RXDID || !rx_ring->netdev) { struct ice_vsi *ctrl_vsi = rx_ring->vsi; @@ -1135,15 +1140,11 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) xdp.frame_sz = ice_rx_frame_truesize(rx_ring, size); #endif - rcu_read_lock(); xdp_prog = READ_ONCE(rx_ring->xdp_prog); - if (!xdp_prog) { - rcu_read_unlock(); + if (!xdp_prog) goto construct_skb; - } xdp_res = ice_run_xdp(rx_ring, &xdp, xdp_prog); - rcu_read_unlock(); if (!xdp_res) goto construct_skb; if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) { @@ -1207,6 +1208,7 @@ construct_skb: ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); + ice_trace(clean_rx_irq_indicate, rx_ring, rx_desc, skb); /* send completed skb up the stack */ ice_receive_skb(rx_ring, skb, vlan_tag); skb = NULL; @@ -2136,6 +2138,41 @@ static bool ice_chk_linearize(struct sk_buff *skb, unsigned int count) return count != ICE_MAX_BUF_TXD; } +/** + * ice_tstamp - set up context descriptor for hardware timestamp + * @tx_ring: pointer to the Tx ring to send buffer on + * @skb: pointer to the SKB we're sending + * @first: Tx buffer + * @off: Tx offload parameters + */ +static void +ice_tstamp(struct ice_ring *tx_ring, struct sk_buff *skb, + struct ice_tx_buf *first, struct ice_tx_offload_params *off) +{ + s8 idx; + + /* only timestamp the outbound packet if the user has requested it */ + if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) + return; + + if (!tx_ring->ptp_tx) + return; + + /* Tx timestamps cannot be sampled when doing TSO */ + if (first->tx_flags & ICE_TX_FLAGS_TSO) + return; + + /* Grab an open timestamp slot */ + idx = ice_ptp_request_ts(tx_ring->tx_tstamps, skb); + if (idx < 0) + return; + + off->cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | + (ICE_TX_CTX_DESC_TSYN << ICE_TXD_CTX_QW1_CMD_S) | + ((u64)idx << ICE_TXD_CTX_QW1_TSO_LEN_S)); + first->tx_flags |= ICE_TX_FLAGS_TSYN; +} + /** * ice_xmit_frame_ring - Sends buffer on Tx ring * @skb: send buffer @@ -2153,6 +2190,8 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) unsigned int count; int tso, csum; + ice_trace(xmit_frame_ring, tx_ring, skb); + count = ice_xmit_desc_count(skb); if (ice_chk_linearize(skb, count)) { if (__skb_linearize(skb)) @@ -2205,6 +2244,8 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) ICE_TX_CTX_DESC_SWTCH_UPLINK << ICE_TXD_CTX_QW1_CMD_S); + ice_tstamp(tx_ring, skb, first, &offload); + if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) { struct ice_tx_ctx_desc *cdesc; u16 i = tx_ring->next_to_use; @@ -2225,6 +2266,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) return NETDEV_TX_OK; out_drop: + ice_trace(xmit_frame_ring_drop, tx_ring, skb); dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index c5a92ac787d6..1e46e80f3d6f 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -118,6 +118,7 @@ static inline int ice_skb_pad(void) * freed instead of returned like skb packets. */ #define ICE_TX_FLAGS_DUMMY_PKT BIT(3) +#define ICE_TX_FLAGS_TSYN BIT(4) #define ICE_TX_FLAGS_IPV4 BIT(5) #define ICE_TX_FLAGS_IPV6 BIT(6) #define ICE_TX_FLAGS_TUNNEL BIT(7) @@ -311,6 +312,10 @@ struct ice_ring { u32 txq_teid; /* Added Tx queue TEID */ u16 rx_buf_len; u8 dcb_tc; /* Traffic class of ring */ + struct ice_ptp_tx *tx_tstamps; + u64 cached_phctime; + u8 ptp_rx:1; + u8 ptp_tx:1; } ____cacheline_internodealigned_in_smp; static inline bool ice_ring_uses_build_skb(struct ice_ring *ring) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 207f6ee3a7f6..171397dcf00a 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -38,10 +38,23 @@ void ice_release_rx_desc(struct ice_ring *rx_ring, u16 val) * ice_ptype_to_htype - get a hash type * @ptype: the ptype value from the descriptor * - * Returns a hash type to be used by skb_set_hash + * Returns appropriate hash type (such as PKT_HASH_TYPE_L2/L3/L4) to be used by + * skb_set_hash based on PTYPE as parsed by HW Rx pipeline and is part of + * Rx desc. */ -static enum pkt_hash_types ice_ptype_to_htype(u8 __always_unused ptype) +static enum pkt_hash_types ice_ptype_to_htype(u16 ptype) { + struct ice_rx_ptype_decoded decoded = ice_decode_rx_desc_ptype(ptype); + + if (!decoded.known) + return PKT_HASH_TYPE_NONE; + if (decoded.payload_layer == ICE_RX_PTYPE_PAYLOAD_LAYER_PAY4) + return PKT_HASH_TYPE_L4; + if (decoded.payload_layer == ICE_RX_PTYPE_PAYLOAD_LAYER_PAY3) + return PKT_HASH_TYPE_L3; + if (decoded.outer_ip == ICE_RX_PTYPE_OUTER_L2) + return PKT_HASH_TYPE_L2; + return PKT_HASH_TYPE_NONE; } @@ -54,7 +67,7 @@ static enum pkt_hash_types ice_ptype_to_htype(u8 __always_unused ptype) */ static void ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, - struct sk_buff *skb, u8 rx_ptype) + struct sk_buff *skb, u16 rx_ptype) { struct ice_32b_rx_flex_desc_nic *nic_mdid; u32 hash; @@ -81,7 +94,7 @@ ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, */ static void ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb, - union ice_32b_rx_flex_desc *rx_desc, u8 ptype) + union ice_32b_rx_flex_desc *rx_desc, u16 ptype) { struct ice_rx_ptype_decoded decoded; u16 rx_status0, rx_status1; @@ -167,7 +180,7 @@ checksum_fail: void ice_process_skb_fields(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, - struct sk_buff *skb, u8 ptype) + struct sk_buff *skb, u16 ptype) { ice_rx_hash(rx_ring, rx_desc, skb, ptype); @@ -175,6 +188,9 @@ ice_process_skb_fields(struct ice_ring *rx_ring, skb->protocol = eth_type_trans(skb, rx_ring->netdev); ice_rx_csum(rx_ring, skb, rx_desc, ptype); + + if (rx_ring->ptp_rx) + ice_ptp_rx_hwtstamp(rx_ring, rx_desc, skb); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index 58ff58f0f972..05ac30752902 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -53,7 +53,7 @@ void ice_release_rx_desc(struct ice_ring *rx_ring, u16 val); void ice_process_skb_fields(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, - struct sk_buff *skb, u8 ptype); + struct sk_buff *skb, u16 ptype); void ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag); #endif /* !_ICE_TXRX_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 4474dd6a7ba1..d33d1906103c 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -14,6 +14,7 @@ #include "ice_lan_tx_rx.h" #include "ice_flex_type.h" #include "ice_protocol_type.h" +#include "ice_sbq_cmd.h" static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc) { @@ -45,8 +46,10 @@ static inline u32 ice_round_to_num(u32 N, u32 R) #define ICE_DBG_FLOW BIT_ULL(9) #define ICE_DBG_SW BIT_ULL(13) #define ICE_DBG_SCHED BIT_ULL(14) +#define ICE_DBG_RDMA BIT_ULL(15) #define ICE_DBG_PKG BIT_ULL(16) #define ICE_DBG_RES BIT_ULL(17) +#define ICE_DBG_PTP BIT_ULL(19) #define ICE_DBG_AQ_MSG BIT_ULL(24) #define ICE_DBG_AQ_DESC BIT_ULL(25) #define ICE_DBG_AQ_DESC_BUF BIT_ULL(26) @@ -63,7 +66,7 @@ enum ice_aq_res_ids { /* FW update timeout definitions are in milliseconds */ #define ICE_NVM_TIMEOUT 180000 #define ICE_CHANGE_LOCK_TIMEOUT 1000 -#define ICE_GLOBAL_CFG_LOCK_TIMEOUT 3000 +#define ICE_GLOBAL_CFG_LOCK_TIMEOUT 5000 enum ice_aq_res_access_type { ICE_RES_READ = 1, @@ -146,6 +149,7 @@ struct ice_link_status { u16 max_frame_size; u16 link_speed; u16 req_speeds; + u8 link_cfg_err; u8 lse_ena; /* Link Status Event notification */ u8 link_info; u8 an_info; @@ -262,6 +266,8 @@ struct ice_hw_common_caps { u8 rss_table_entry_width; /* RSS Entry width in bits */ u8 dcb; + u8 ieee_1588; + u8 rdma; bool nvm_update_pending_nvm; bool nvm_update_pending_orom; @@ -273,6 +279,54 @@ struct ice_hw_common_caps { #define ICE_NVM_MGMT_UNIFIED_UPD_SUPPORT BIT(3) }; +/* IEEE 1588 TIME_SYNC specific info */ +/* Function specific definitions */ +#define ICE_TS_FUNC_ENA_M BIT(0) +#define ICE_TS_SRC_TMR_OWND_M BIT(1) +#define ICE_TS_TMR_ENA_M BIT(2) +#define ICE_TS_TMR_IDX_OWND_S 4 +#define ICE_TS_TMR_IDX_OWND_M BIT(4) +#define ICE_TS_CLK_FREQ_S 16 +#define ICE_TS_CLK_FREQ_M ICE_M(0x7, ICE_TS_CLK_FREQ_S) +#define ICE_TS_CLK_SRC_S 20 +#define ICE_TS_CLK_SRC_M BIT(20) +#define ICE_TS_TMR_IDX_ASSOC_S 24 +#define ICE_TS_TMR_IDX_ASSOC_M BIT(24) + +struct ice_ts_func_info { + /* Function specific info */ + u32 clk_freq; + u8 clk_src; + u8 tmr_index_assoc; + u8 ena; + u8 tmr_index_owned; + u8 src_tmr_owned; + u8 tmr_ena; +}; + +/* Device specific definitions */ +#define ICE_TS_TMR0_OWNR_M 0x7 +#define ICE_TS_TMR0_OWND_M BIT(3) +#define ICE_TS_TMR1_OWNR_S 4 +#define ICE_TS_TMR1_OWNR_M ICE_M(0x7, ICE_TS_TMR1_OWNR_S) +#define ICE_TS_TMR1_OWND_M BIT(7) +#define ICE_TS_DEV_ENA_M BIT(24) +#define ICE_TS_TMR0_ENA_M BIT(25) +#define ICE_TS_TMR1_ENA_M BIT(26) + +struct ice_ts_dev_info { + /* Device specific info */ + u32 ena_ports; + u32 tmr_own_map; + u32 tmr0_owner; + u32 tmr1_owner; + u8 tmr0_owned; + u8 tmr1_owned; + u8 ena; + u8 tmr0_ena; + u8 tmr1_ena; +}; + /* Function specific capabilities */ struct ice_hw_func_caps { struct ice_hw_common_caps common_cap; @@ -281,6 +335,7 @@ struct ice_hw_func_caps { u32 guar_num_vsi; u32 fd_fltr_guar; /* Number of filters guaranteed */ u32 fd_fltr_best_effort; /* Number of best effort filters */ + struct ice_ts_func_info ts_func_info; }; /* Device wide capabilities */ @@ -289,6 +344,7 @@ struct ice_hw_dev_caps { u32 num_vfs_exposed; /* Total number of VFs exposed */ u32 num_vsi_allocd_to_host; /* Excluding EMP VSI */ u32 num_flow_director_fltr; /* Number of FD filters available */ + struct ice_ts_dev_info ts_dev_info; u32 num_funcs; }; @@ -440,6 +496,7 @@ struct ice_sched_node { u8 tc_num; u8 owner; #define ICE_SCHED_NODE_OWNER_LAN 0 +#define ICE_SCHED_NODE_OWNER_RDMA 2 }; /* Access Macros for Tx Sched Elements data */ @@ -511,6 +568,7 @@ struct ice_sched_vsi_info { struct ice_sched_node *ag_node[ICE_MAX_TRAFFIC_CLASS]; struct list_head list_entry; u16 max_lanq[ICE_MAX_TRAFFIC_CLASS]; + u16 max_rdmaq[ICE_MAX_TRAFFIC_CLASS]; }; /* driver defines the policy */ @@ -749,6 +807,7 @@ struct ice_hw { /* Control Queue info */ struct ice_ctl_q_info adminq; + struct ice_ctl_q_info sbq; struct ice_ctl_q_info mailboxq; u8 api_branch; /* API branch version */ @@ -784,6 +843,14 @@ struct ice_hw { u8 ucast_shared; /* true if VSIs can share unicast addr */ +#define ICE_PHY_PER_NAC 1 +#define ICE_MAX_QUAD 2 +#define ICE_NUM_QUAD_TYPE 2 +#define ICE_PORTS_PER_QUAD 4 +#define ICE_PHY_0_LAST_QUAD 1 +#define ICE_PORTS_PER_PHY 8 +#define ICE_NUM_EXTERNAL_PORTS ICE_PORTS_PER_PHY + /* Active package version (currently active) */ struct ice_pkg_ver active_pkg_ver; u32 active_track_id; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 97a46c616aca..2826570dab51 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -939,16 +939,18 @@ static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) vf->num_mac++; - if (is_valid_ether_addr(vf->dflt_lan_addr.addr)) { - status = ice_fltr_add_mac(vsi, vf->dflt_lan_addr.addr, + if (is_valid_ether_addr(vf->hw_lan_addr.addr)) { + status = ice_fltr_add_mac(vsi, vf->hw_lan_addr.addr, ICE_FWD_TO_VSI); if (status) { dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %s\n", - &vf->dflt_lan_addr.addr[0], vf->vf_id, + &vf->hw_lan_addr.addr[0], vf->vf_id, ice_stat_str(status)); return ice_status_to_errno(status); } vf->num_mac++; + + ether_addr_copy(vf->dev_lan_addr.addr, vf->hw_lan_addr.addr); } return 0; @@ -1687,7 +1689,6 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) else promisc_m = ICE_UCAST_PROMISC_BITS; - vsi = ice_get_vf_vsi(vf); if (ice_vf_set_vsi_promisc(vf, vsi, promisc_m, true)) dev_err(dev, "disabling promiscuous mode failed\n"); } @@ -2386,7 +2387,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; vfres->vsi_res[0].num_queue_pairs = vsi->num_txq; ether_addr_copy(vfres->vsi_res[0].default_mac_addr, - vf->dflt_lan_addr.addr); + vf->hw_lan_addr.addr); /* match guest capabilities */ vf->driver_caps = vfres->vf_cap_flags; @@ -3542,10 +3543,9 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) struct virtchnl_vsi_queue_config_info *qci = (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; - u16 num_rxq = 0, num_txq = 0; struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; - int i; + int i, q_idx; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -3583,18 +3583,31 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } + + q_idx = qpi->rxq.queue_id; + + /* make sure selected "q_idx" is in valid range of queues + * for selected "vsi" + */ + if (q_idx >= vsi->alloc_txq || q_idx >= vsi->alloc_rxq) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + /* copy Tx queue info from VF into VSI */ if (qpi->txq.ring_len > 0) { - num_txq++; vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr; vsi->tx_rings[i]->count = qpi->txq.ring_len; + if (ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } } /* copy Rx queue info from VF into VSI */ if (qpi->rxq.ring_len > 0) { u16 max_frame_size = ice_vc_get_max_frame_size(vf); - num_rxq++; vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; vsi->rx_rings[i]->count = qpi->rxq.ring_len; @@ -3611,28 +3624,21 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } + + vsi->max_frame = qpi->rxq.max_pkt_size; + /* add space for the port VLAN since the VF driver is not + * expected to account for it in the MTU calculation + */ + if (vf->port_vlan_info) + vsi->max_frame += VLAN_HLEN; + + if (ice_vsi_cfg_single_rxq(vsi, q_idx)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } } - - vsi->max_frame = qpi->rxq.max_pkt_size; - /* add space for the port VLAN since the VF driver is not - * expected to account for it in the MTU calculation - */ - if (vf->port_vlan_info) - vsi->max_frame += VLAN_HLEN; } - /* VF can request to configure less than allocated queues or default - * allocated queues. So update the VSI with new number - */ - vsi->num_txq = num_txq; - vsi->num_rxq = num_rxq; - /* All queues of VF VSI are in TC 0 */ - vsi->tc_cfg.tc_info[0].qcount_tx = num_txq; - vsi->tc_cfg.tc_info[0].qcount_rx = num_rxq; - - if (ice_vsi_cfg_lan_txqs(vsi) || ice_vsi_cfg_rxqs(vsi)) - v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; - error_param: /* send the response to the VF */ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, v_ret, @@ -3666,20 +3672,96 @@ static bool ice_can_vf_change_mac(struct ice_vf *vf) return true; } +/** + * ice_vc_ether_addr_type - get type of virtchnl_ether_addr + * @vc_ether_addr: used to extract the type + */ +static u8 +ice_vc_ether_addr_type(struct virtchnl_ether_addr *vc_ether_addr) +{ + return (vc_ether_addr->type & VIRTCHNL_ETHER_ADDR_TYPE_MASK); +} + +/** + * ice_is_vc_addr_legacy - check if the MAC address is from an older VF + * @vc_ether_addr: VIRTCHNL structure that contains MAC and type + */ +static bool +ice_is_vc_addr_legacy(struct virtchnl_ether_addr *vc_ether_addr) +{ + u8 type = ice_vc_ether_addr_type(vc_ether_addr); + + return (type == VIRTCHNL_ETHER_ADDR_LEGACY); +} + +/** + * ice_is_vc_addr_primary - check if the MAC address is the VF's primary MAC + * @vc_ether_addr: VIRTCHNL structure that contains MAC and type + * + * This function should only be called when the MAC address in + * virtchnl_ether_addr is a valid unicast MAC + */ +static bool +ice_is_vc_addr_primary(struct virtchnl_ether_addr __maybe_unused *vc_ether_addr) +{ + u8 type = ice_vc_ether_addr_type(vc_ether_addr); + + return (type == VIRTCHNL_ETHER_ADDR_PRIMARY); +} + +/** + * ice_vfhw_mac_add - update the VF's cached hardware MAC if allowed + * @vf: VF to update + * @vc_ether_addr: structure from VIRTCHNL with MAC to add + */ +static void +ice_vfhw_mac_add(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) +{ + u8 *mac_addr = vc_ether_addr->addr; + + if (!is_valid_ether_addr(mac_addr)) + return; + + /* only allow legacy VF drivers to set the device and hardware MAC if it + * is zero and allow new VF drivers to set the hardware MAC if the type + * was correctly specified over VIRTCHNL + */ + if ((ice_is_vc_addr_legacy(vc_ether_addr) && + is_zero_ether_addr(vf->hw_lan_addr.addr)) || + ice_is_vc_addr_primary(vc_ether_addr)) { + ether_addr_copy(vf->dev_lan_addr.addr, mac_addr); + ether_addr_copy(vf->hw_lan_addr.addr, mac_addr); + } + + /* hardware and device MACs are already set, but its possible that the + * VF driver sent the VIRTCHNL_OP_ADD_ETH_ADDR message before the + * VIRTCHNL_OP_DEL_ETH_ADDR when trying to update its MAC, so save it + * away for the legacy VF driver case as it will be updated in the + * delete flow for this case + */ + if (ice_is_vc_addr_legacy(vc_ether_addr)) { + ether_addr_copy(vf->legacy_last_added_umac.addr, + mac_addr); + vf->legacy_last_added_umac.time_modified = jiffies; + } +} + /** * ice_vc_add_mac_addr - attempt to add the MAC address passed in * @vf: pointer to the VF info * @vsi: pointer to the VF's VSI - * @mac_addr: MAC address to add + * @vc_ether_addr: VIRTCHNL MAC address structure used to add MAC */ static int -ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr) +ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, + struct virtchnl_ether_addr *vc_ether_addr) { struct device *dev = ice_pf_to_dev(vf->pf); + u8 *mac_addr = vc_ether_addr->addr; enum ice_status status; - /* default unicast MAC already added */ - if (ether_addr_equal(mac_addr, vf->dflt_lan_addr.addr)) + /* device MAC already added */ + if (ether_addr_equal(mac_addr, vf->dev_lan_addr.addr)) return 0; if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) { @@ -3698,32 +3780,73 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr) return -EIO; } - /* Set the default LAN address to the latest unicast MAC address added - * by the VF. The default LAN address is reported by the PF via - * ndo_get_vf_config. - */ - if (is_unicast_ether_addr(mac_addr)) - ether_addr_copy(vf->dflt_lan_addr.addr, mac_addr); + ice_vfhw_mac_add(vf, vc_ether_addr); vf->num_mac++; return 0; } +/** + * ice_is_legacy_umac_expired - check if last added legacy unicast MAC expired + * @last_added_umac: structure used to check expiration + */ +static bool ice_is_legacy_umac_expired(struct ice_time_mac *last_added_umac) +{ +#define ICE_LEGACY_VF_MAC_CHANGE_EXPIRE_TIME msecs_to_jiffies(3000) + return time_is_before_jiffies(last_added_umac->time_modified + + ICE_LEGACY_VF_MAC_CHANGE_EXPIRE_TIME); +} + +/** + * ice_vfhw_mac_del - update the VF's cached hardware MAC if allowed + * @vf: VF to update + * @vc_ether_addr: structure from VIRTCHNL with MAC to delete + */ +static void +ice_vfhw_mac_del(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) +{ + u8 *mac_addr = vc_ether_addr->addr; + + if (!is_valid_ether_addr(mac_addr) || + !ether_addr_equal(vf->dev_lan_addr.addr, mac_addr)) + return; + + /* allow the device MAC to be repopulated in the add flow and don't + * clear the hardware MAC (i.e. hw_lan_addr.addr) here as that is meant + * to be persistent on VM reboot and across driver unload/load, which + * won't work if we clear the hardware MAC here + */ + eth_zero_addr(vf->dev_lan_addr.addr); + + /* only update cached hardware MAC for legacy VF drivers on delete + * because we cannot guarantee order/type of MAC from the VF driver + */ + if (ice_is_vc_addr_legacy(vc_ether_addr) && + !ice_is_legacy_umac_expired(&vf->legacy_last_added_umac)) { + ether_addr_copy(vf->dev_lan_addr.addr, + vf->legacy_last_added_umac.addr); + ether_addr_copy(vf->hw_lan_addr.addr, + vf->legacy_last_added_umac.addr); + } +} + /** * ice_vc_del_mac_addr - attempt to delete the MAC address passed in * @vf: pointer to the VF info * @vsi: pointer to the VF's VSI - * @mac_addr: MAC address to delete + * @vc_ether_addr: VIRTCHNL MAC address structure used to delete MAC */ static int -ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr) +ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, + struct virtchnl_ether_addr *vc_ether_addr) { struct device *dev = ice_pf_to_dev(vf->pf); + u8 *mac_addr = vc_ether_addr->addr; enum ice_status status; if (!ice_can_vf_change_mac(vf) && - ether_addr_equal(mac_addr, vf->dflt_lan_addr.addr)) + ether_addr_equal(vf->dev_lan_addr.addr, mac_addr)) return 0; status = ice_fltr_remove_mac(vsi, mac_addr, ICE_FWD_TO_VSI); @@ -3737,8 +3860,7 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr) return -EIO; } - if (ether_addr_equal(mac_addr, vf->dflt_lan_addr.addr)) - eth_zero_addr(vf->dflt_lan_addr.addr); + ice_vfhw_mac_del(vf, vc_ether_addr); vf->num_mac--; @@ -3757,7 +3879,8 @@ static int ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set) { int (*ice_vc_cfg_mac) - (struct ice_vf *vf, struct ice_vsi *vsi, u8 *mac_addr); + (struct ice_vf *vf, struct ice_vsi *vsi, + struct virtchnl_ether_addr *virtchnl_ether_addr); enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; struct virtchnl_ether_addr_list *al = (struct virtchnl_ether_addr_list *)msg; @@ -3806,7 +3929,7 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set) is_zero_ether_addr(mac_addr)) continue; - result = ice_vc_cfg_mac(vf, vsi, mac_addr); + result = ice_vc_cfg_mac(vf, vsi, &al->list[i]); if (result == -EEXIST || result == -ENOENT) { continue; } else if (result) { @@ -4444,7 +4567,7 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi) return -EBUSY; ivi->vf = vf_id; - ether_addr_copy(ivi->mac, vf->dflt_lan_addr.addr); + ether_addr_copy(ivi->mac, vf->hw_lan_addr.addr); /* VF configuration for VLAN and applicable QoS */ ivi->vlan = vf->port_vlan_info & VLAN_VID_MASK; @@ -4520,7 +4643,8 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) vf = &pf->vf[vf_id]; /* nothing left to do, unicast MAC already set */ - if (ether_addr_equal(vf->dflt_lan_addr.addr, mac)) + if (ether_addr_equal(vf->dev_lan_addr.addr, mac) && + ether_addr_equal(vf->hw_lan_addr.addr, mac)) return 0; ret = ice_check_vf_ready_for_cfg(vf); @@ -4536,7 +4660,8 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) /* VF is notified of its new MAC via the PF's response to the * VIRTCHNL_OP_GET_VF_RESOURCES message after the VF has been reset */ - ether_addr_copy(vf->dflt_lan_addr.addr, mac); + ether_addr_copy(vf->dev_lan_addr.addr, mac); + ether_addr_copy(vf->hw_lan_addr.addr, mac); if (is_zero_ether_addr(mac)) { /* VF will send VIRTCHNL_OP_ADD_ETH_ADDR message with its MAC */ vf->pf_set_mac = false; @@ -4689,7 +4814,7 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf) dev_info(dev, "%d Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n", vf->mdd_rx_events.count, pf->hw.pf_id, vf->vf_id, - vf->dflt_lan_addr.addr, + vf->dev_lan_addr.addr, test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags) ? "on" : "off"); } @@ -4733,7 +4858,7 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf) dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM.\n", vf->mdd_tx_events.count, hw->pf_id, i, - vf->dflt_lan_addr.addr); + vf->dev_lan_addr.addr); } } } @@ -4823,7 +4948,7 @@ ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event, if (pf_vsi) dev_warn(dev, "VF MAC %pM on PF MAC %pM is generating asynchronous messages and may be overflowing the PF message queue. Please see the Adapter User Guide for more information\n", - &vf->dflt_lan_addr.addr[0], + &vf->dev_lan_addr.addr[0], pf_vsi->netdev->dev_addr); } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index d800ed83d6c3..842cb077df86 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -58,6 +58,11 @@ enum ice_virtchnl_cap { ICE_VIRTCHNL_VF_CAP_PRIVILEGE, }; +struct ice_time_mac { + unsigned long time_modified; + u8 addr[ETH_ALEN]; +}; + /* VF MDD events print structure */ struct ice_mdd_vf_events { u16 count; /* total count of Rx|Tx events */ @@ -78,7 +83,9 @@ struct ice_vf { struct ice_sw *vf_sw_id; /* switch ID the VF VSIs connect to */ struct virtchnl_version_info vf_ver; u32 driver_caps; /* reported by VF driver */ - struct virtchnl_ether_addr dflt_lan_addr; + struct virtchnl_ether_addr dev_lan_addr; + struct virtchnl_ether_addr hw_lan_addr; + struct ice_time_mac legacy_last_added_umac; DECLARE_BITMAP(txq_ena, ICE_MAX_RSS_QS_PER_VF); DECLARE_BITMAP(rxq_ena, ICE_MAX_RSS_QS_PER_VF); u16 port_vlan_info; /* Port VLAN ID and QoS */ @@ -151,16 +158,18 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, enum virtchnl_status_code v_retval, u8 *msg, u16 msglen); bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id); #else /* CONFIG_PCI_IOV */ -#define ice_process_vflr_event(pf) do {} while (0) -#define ice_free_vfs(pf) do {} while (0) -#define ice_vc_process_vf_msg(pf, event) do {} while (0) -#define ice_vc_notify_link_state(pf) do {} while (0) -#define ice_vc_notify_reset(pf) do {} while (0) -#define ice_set_vf_state_qs_dis(vf) do {} while (0) -#define ice_vf_lan_overflow_event(pf, event) do {} while (0) -#define ice_print_vfs_mdd_events(pf) do {} while (0) -#define ice_print_vf_rx_mdd_event(vf) do {} while (0) -#define ice_restore_all_vfs_msi_state(pdev) do {} while (0) +static inline void ice_process_vflr_event(struct ice_pf *pf) { } +static inline void ice_free_vfs(struct ice_pf *pf) { } +static inline +void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) { } +static inline void ice_vc_notify_link_state(struct ice_pf *pf) { } +static inline void ice_vc_notify_reset(struct ice_pf *pf) { } +static inline void ice_set_vf_state_qs_dis(struct ice_vf *vf) { } +static inline +void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) { } +static inline void ice_print_vfs_mdd_events(struct ice_pf *pf) { } +static inline void ice_print_vf_rx_mdd_event(struct ice_vf *vf) { } +static inline void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) { } static inline bool ice_is_malicious_vf(struct ice_pf __always_unused *pf, diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index a1f89ea3c2bd..5a9f61deeb38 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -236,7 +236,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring); } - err = ice_setup_rx_ctx(rx_ring); + err = ice_vsi_cfg_rxq(rx_ring); if (err) goto free_buf; @@ -466,7 +466,6 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) struct ice_ring *xdp_ring; u32 act; - rcu_read_lock(); /* ZC patch is enabled only when XDP program is set, * so here it can not be NULL */ @@ -478,7 +477,6 @@ ice_run_xdp_zc(struct ice_ring *rx_ring, struct xdp_buff *xdp) err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); if (err) goto out_failure; - rcu_read_unlock(); return ICE_XDP_REDIR; } @@ -503,7 +501,6 @@ out_failure: break; } - rcu_read_unlock(); return result; } @@ -528,7 +525,7 @@ int ice_clean_rx_irq_zc(struct ice_ring *rx_ring, int budget) struct sk_buff *skb; u16 stat_err_bits; u16 vlan_tag = 0; - u8 rx_ptype; + u16 rx_ptype; rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index fad783690134..ea208808623a 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -60,7 +60,7 @@ ice_xsk_wakeup(struct net_device __always_unused *netdev, return -EOPNOTSUPP; } -#define ice_xsk_clean_rx_ring(rx_ring) do {} while (0) -#define ice_xsk_clean_xdp_ring(xdp_ring) do {} while (0) +static inline void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) { } +static inline void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring) { } #endif /* CONFIG_XDP_SOCKETS */ #endif /* !_ICE_XSK_H_ */ diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index 50863fd87d53..cbe92fd23a70 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -2756,6 +2756,7 @@ out: return ret_val; } +#ifdef CONFIG_IGB_HWMON static const u8 e1000_emc_temp_data[4] = { E1000_EMC_INTERNAL_DATA, E1000_EMC_DIODE1_DATA, @@ -2769,7 +2770,6 @@ static const u8 e1000_emc_therm_limit[4] = { E1000_EMC_DIODE3_THERM_LIMIT }; -#ifdef CONFIG_IGB_HWMON /** * igb_get_thermal_sensor_data_generic - Gathers thermal sensor data * @hw: pointer to hardware structure diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 7545da216d8b..636a1b1fb7e1 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -831,7 +831,7 @@ static int igb_set_eeprom(struct net_device *netdev, memcpy(ptr, bytes, eeprom->len); for (i = 0; i < last_word - first_word + 1; i++) - eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]); + cpu_to_le16s(&eeprom_buff[i]); ret_val = hw->nvm.ops.write(hw, first_word, last_word - first_word + 1, eeprom_buff); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index b2a042f825ff..7e6435dc7e80 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -356,7 +356,7 @@ static void igb_dump(struct igb_adapter *adapter) struct igb_reg_info *reginfo; struct igb_ring *tx_ring; union e1000_adv_tx_desc *tx_desc; - struct my_u0 { u64 a; u64 b; } *u0; + struct my_u0 { __le64 a; __le64 b; } *u0; struct igb_ring *rx_ring; union e1000_adv_rx_desc *rx_desc; u32 staterr; @@ -2643,7 +2643,8 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter, } input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI; - input->filter.vlan_tci = match.key->vlan_priority; + input->filter.vlan_tci = + (__force __be16)match.key->vlan_priority; } } @@ -6275,12 +6276,12 @@ int igb_xmit_xdp_ring(struct igb_adapter *adapter, cmd_type |= len | IGB_TXD_DCMD; tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); - olinfo_status = cpu_to_le32(len << E1000_ADVTXD_PAYLEN_SHIFT); + olinfo_status = len << E1000_ADVTXD_PAYLEN_SHIFT; /* 82575 requires a unique index per ring */ if (test_bit(IGB_RING_FLAG_TX_CTX_IDX, &tx_ring->flags)) olinfo_status |= tx_ring->reg_idx << 4; - tx_desc->read.olinfo_status = olinfo_status; + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); netdev_tx_sent_queue(txring_txq(tx_ring), tx_buffer->bytecount); @@ -8380,7 +8381,6 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter, struct bpf_prog *xdp_prog; u32 act; - rcu_read_lock(); xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (!xdp_prog) @@ -8415,7 +8415,6 @@ out_failure: break; } xdp_out: - rcu_read_unlock(); return ERR_PTR(-result); } @@ -8592,7 +8591,7 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring, if (igb_test_staterr(rx_desc, E1000_RXDEXT_STATERR_LB) && test_bit(IGB_RING_FLAG_RX_LB_VLAN_BSWAP, &rx_ring->flags)) - vid = be16_to_cpu(rx_desc->wb.upper.vlan); + vid = be16_to_cpu((__force __be16)rx_desc->wb.upper.vlan); else vid = le16_to_cpu(rx_desc->wb.upper.vlan); diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index d68cd4466a54..0011b15e678c 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -1131,12 +1131,12 @@ static int igb_ptp_set_timestamp_mode(struct igb_adapter *adapter, | E1000_FTQF_MASK); /* mask all inputs */ ftqf &= ~E1000_FTQF_MASK_PROTO_BP; /* enable protocol check */ - wr32(E1000_IMIR(3), htons(PTP_EV_PORT)); + wr32(E1000_IMIR(3), (__force unsigned int)htons(PTP_EV_PORT)); wr32(E1000_IMIREXT(3), (E1000_IMIREXT_SIZE_BP | E1000_IMIREXT_CTRL_BP)); if (hw->mac.type == e1000_82576) { /* enable source port check */ - wr32(E1000_SPQF(3), htons(PTP_EV_PORT)); + wr32(E1000_SPQF(3), (__force unsigned int)htons(PTP_EV_PORT)); ftqf &= ~E1000_FTQF_MASK_SOURCE_PORT_BP; } wr32(E1000_FTQF(3), ftqf); diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index fb3fbcb13331..1bbe9862a758 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -83,14 +83,14 @@ static int igbvf_desc_unused(struct igbvf_ring *ring) static void igbvf_receive_skb(struct igbvf_adapter *adapter, struct net_device *netdev, struct sk_buff *skb, - u32 status, u16 vlan) + u32 status, __le16 vlan) { u16 vid; if (status & E1000_RXD_STAT_VP) { if ((adapter->flags & IGBVF_FLAG_RX_LB_VLAN_BSWAP) && (status & E1000_RXDEXT_STATERR_LB)) - vid = be16_to_cpu(vlan) & E1000_RXD_SPC_VLAN_MASK; + vid = be16_to_cpu((__force __be16)vlan) & E1000_RXD_SPC_VLAN_MASK; else vid = le16_to_cpu(vlan) & E1000_RXD_SPC_VLAN_MASK; if (test_bit(vid, adapter->active_vlans)) @@ -2056,7 +2056,7 @@ static int igbvf_tso(struct igbvf_ring *tx_ring, /* remove payload length from inner checksum */ paylen = skb->len - l4_offset; - csum_replace_by_diff(&l4.tcp->check, htonl(paylen)); + csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen)); /* MSS L4LEN IDX */ mss_l4len_idx = (*hdr_len - l4_offset) << E1000_ADVTXD_L4LEN_SHIFT; diff --git a/drivers/net/ethernet/intel/igbvf/vf.h b/drivers/net/ethernet/intel/igbvf/vf.h index c71b0d7dbcee..ba9bb3132d5d 100644 --- a/drivers/net/ethernet/intel/igbvf/vf.h +++ b/drivers/net/ethernet/intel/igbvf/vf.h @@ -35,31 +35,31 @@ struct e1000_hw; /* Receive Descriptor - Advanced */ union e1000_adv_rx_desc { struct { - u64 pkt_addr; /* Packet buffer address */ - u64 hdr_addr; /* Header buffer address */ + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ } read; struct { struct { union { - u32 data; + __le32 data; struct { - u16 pkt_info; /* RSS/Packet type */ + __le16 pkt_info; /* RSS/Packet type */ /* Split Header, hdr buffer length */ - u16 hdr_info; + __le16 hdr_info; } hs_rss; } lo_dword; union { - u32 rss; /* RSS Hash */ + __le32 rss; /* RSS Hash */ struct { - u16 ip_id; /* IP id */ - u16 csum; /* Packet Checksum */ + __le16 ip_id; /* IP id */ + __le16 csum; /* Packet Checksum */ } csum_ip; } hi_dword; } lower; struct { - u32 status_error; /* ext status/error */ - u16 length; /* Packet length */ - u16 vlan; /* VLAN tag */ + __le32 status_error; /* ext status/error */ + __le16 length; /* Packet length */ + __le16 vlan; /* VLAN tag */ } upper; } wb; /* writeback */ }; @@ -70,14 +70,14 @@ union e1000_adv_rx_desc { /* Transmit Descriptor - Advanced */ union e1000_adv_tx_desc { struct { - u64 buffer_addr; /* Address of descriptor's data buf */ - u32 cmd_type_len; - u32 olinfo_status; + __le64 buffer_addr; /* Address of descriptor's data buf */ + __le32 cmd_type_len; + __le32 olinfo_status; } read; struct { - u64 rsvd; /* Reserved */ - u32 nxtseq_seed; - u32 status; + __le64 rsvd; /* Reserved */ + __le32 nxtseq_seed; + __le32 status; } wb; }; @@ -94,10 +94,10 @@ union e1000_adv_tx_desc { /* Context descriptors */ struct e1000_adv_tx_context_desc { - u32 vlan_macip_lens; - u32 seqnum_seed; - u32 type_tucmd_mlhl; - u32 mss_l4len_idx; + __le32 vlan_macip_lens; + __le32 seqnum_seed; + __le32 type_tucmd_mlhl; + __le32 mss_l4len_idx; }; #define E1000_ADVTXD_MACLEN_SHIFT 9 /* Adv ctxt desc mac len shift */ diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 25871351730b..9e0bbb2e55e3 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -118,6 +118,7 @@ struct igc_ring { }; struct xdp_rxq_info xdp_rxq; + struct xsk_buff_pool *xsk_pool; } ____cacheline_internodealigned_in_smp; /* Board specific private data structure */ @@ -255,6 +256,11 @@ bool igc_has_link(struct igc_adapter *adapter); void igc_reset(struct igc_adapter *adapter); int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx); void igc_update_stats(struct igc_adapter *adapter); +void igc_disable_rx_ring(struct igc_ring *ring); +void igc_enable_rx_ring(struct igc_ring *ring); +void igc_disable_tx_ring(struct igc_ring *ring); +void igc_enable_tx_ring(struct igc_ring *ring); +int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); /* igc_dump declarations */ void igc_rings_dump(struct igc_adapter *adapter); @@ -366,6 +372,7 @@ extern char igc_driver_name[]; /* VLAN info */ #define IGC_TX_FLAGS_VLAN_MASK 0xffff0000 +#define IGC_TX_FLAGS_VLAN_SHIFT 16 /* igc_test_staterr - tests bits within Rx descriptor status and error fields */ static inline __le32 igc_test_staterr(union igc_adv_rx_desc *rx_desc, @@ -390,8 +397,6 @@ enum igc_tx_flags { /* olinfo flags */ IGC_TX_FLAGS_IPV4 = 0x10, IGC_TX_FLAGS_CSUM = 0x20, - - IGC_TX_FLAGS_XDP = 0x100, }; enum igc_boards { @@ -408,12 +413,19 @@ enum igc_boards { #define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IGC_MAX_DATA_PER_TXD) #define DESC_NEEDED (MAX_SKB_FRAGS + 4) +enum igc_tx_buffer_type { + IGC_TX_BUFFER_TYPE_SKB, + IGC_TX_BUFFER_TYPE_XDP, + IGC_TX_BUFFER_TYPE_XSK, +}; + /* wrapper around a pointer to a socket buffer, * so a DMA handle can be stored along with the buffer */ struct igc_tx_buffer { union igc_adv_tx_desc *next_to_watch; unsigned long time_stamp; + enum igc_tx_buffer_type type; union { struct sk_buff *skb; struct xdp_frame *xdpf; @@ -428,14 +440,19 @@ struct igc_tx_buffer { }; struct igc_rx_buffer { - dma_addr_t dma; - struct page *page; + union { + struct { + dma_addr_t dma; + struct page *page; #if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) - __u32 page_offset; + __u32 page_offset; #else - __u16 page_offset; + __u16 page_offset; #endif - __u16 pagecnt_bias; + __u16 pagecnt_bias; + }; + struct xdp_buff *xdp; + }; }; struct igc_q_vector { @@ -521,7 +538,8 @@ enum igc_ring_flags_t { IGC_RING_FLAG_RX_SCTP_CSUM, IGC_RING_FLAG_RX_LB_VLAN_BSWAP, IGC_RING_FLAG_TX_CTX_IDX, - IGC_RING_FLAG_TX_DETECT_HANG + IGC_RING_FLAG_TX_DETECT_HANG, + IGC_RING_FLAG_AF_XDP_ZC, }; #define ring_uses_large_buffer(ring) \ diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index ea627ce52525..ce530f5fd7bd 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -78,9 +78,11 @@ union igc_adv_rx_desc { /* Additional Transmit Descriptor Control definitions */ #define IGC_TXDCTL_QUEUE_ENABLE 0x02000000 /* Ena specific Tx Queue */ +#define IGC_TXDCTL_SWFLUSH 0x04000000 /* Transmit Software Flush */ /* Additional Receive Descriptor Control definitions */ #define IGC_RXDCTL_QUEUE_ENABLE 0x02000000 /* Ena specific Rx Queue */ +#define IGC_RXDCTL_SWFLUSH 0x04000000 /* Receive Software Flush */ /* SRRCTL bit definitions */ #define IGC_SRRCTL_BSIZEPKT_SHIFT 10 /* Shift _right_ */ diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 0103dda32f39..c3a5a5518790 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -94,12 +94,13 @@ #define IGC_CTRL_SLU 0x00000040 /* Set link up (Force Link) */ #define IGC_CTRL_FRCSPD 0x00000800 /* Force Speed */ #define IGC_CTRL_FRCDPX 0x00001000 /* Force Duplex */ +#define IGC_CTRL_VME 0x40000000 /* IEEE VLAN mode enable */ #define IGC_CTRL_RFCE 0x08000000 /* Receive Flow Control enable */ #define IGC_CTRL_TFCE 0x10000000 /* Transmit flow control enable */ -#define IGC_CTRL_SDP0_DIR 0x00400000 /* SDP0 Data direction */ -#define IGC_CTRL_SDP1_DIR 0x00800000 /* SDP1 Data direction */ +#define IGC_CTRL_SDP0_DIR 0x00400000 /* SDP0 Data direction */ +#define IGC_CTRL_SDP1_DIR 0x00800000 /* SDP1 Data direction */ /* As per the EAS the maximum supported size is 9.5KB (9728 bytes) */ #define MAX_JUMBO_FRAME_SIZE 0x2600 @@ -128,7 +129,6 @@ #define NWAY_LPAR_ASM_DIR 0x0800 /* LP Asymmetric Pause Direction bit */ /* 1000BASE-T Control Register */ -#define CR_1000T_ASYM_PAUSE 0x0080 /* Advertise asymmetric pause bit */ #define CR_1000T_HD_CAPS 0x0100 /* Advertise 1000T HD capability */ #define CR_1000T_FD_CAPS 0x0200 /* Advertise 1000T FD capability */ @@ -323,6 +323,9 @@ #define IGC_RXD_STAT_IXSM 0x04 /* Ignore checksum */ #define IGC_RXD_STAT_UDPCS 0x10 /* UDP xsum calculated */ #define IGC_RXD_STAT_TCPCS 0x20 /* TCP xsum calculated */ +#define IGC_RXD_STAT_VP 0x08 /* IEEE VLAN Packet */ + +#define IGC_RXDEXT_STATERR_LB 0x00040000 /* Advanced Receive Descriptor bit definitions */ #define IGC_RXDADV_STAT_TSIP 0x08000 /* timestamp in packet */ diff --git a/drivers/net/ethernet/intel/igc/igc_dump.c b/drivers/net/ethernet/intel/igc/igc_dump.c index 495bed47ed0a..c09c95cc5f70 100644 --- a/drivers/net/ethernet/intel/igc/igc_dump.c +++ b/drivers/net/ethernet/intel/igc/igc_dump.c @@ -112,7 +112,7 @@ static void igc_regdump(struct igc_hw *hw, struct igc_reg_info *reginfo) void igc_rings_dump(struct igc_adapter *adapter) { struct net_device *netdev = adapter->netdev; - struct my_u0 { u64 a; u64 b; } *u0; + struct my_u0 { __le64 a; __le64 b; } *u0; union igc_adv_tx_desc *tx_desc; union igc_adv_rx_desc *rx_desc; struct igc_ring *tx_ring; diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 9722449d7633..fa4171860623 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -554,7 +554,7 @@ static int igc_ethtool_set_eeprom(struct net_device *netdev, memcpy(ptr, bytes, eeprom->len); for (i = 0; i < last_word - first_word + 1; i++) - eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]); + cpu_to_le16s(&eeprom_buff[i]); ret_val = hw->nvm.ops.write(hw, first_word, last_word - first_word + 1, eeprom_buff); @@ -765,35 +765,22 @@ static void igc_ethtool_get_strings(struct net_device *netdev, u32 stringset, IGC_TEST_LEN * ETH_GSTRING_LEN); break; case ETH_SS_STATS: - for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++) { - memcpy(p, igc_gstrings_stats[i].stat_string, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - for (i = 0; i < IGC_NETDEV_STATS_LEN; i++) { - memcpy(p, igc_gstrings_net_stats[i].stat_string, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++) + ethtool_sprintf(&p, igc_gstrings_stats[i].stat_string); + for (i = 0; i < IGC_NETDEV_STATS_LEN; i++) + ethtool_sprintf(&p, + igc_gstrings_net_stats[i].stat_string); for (i = 0; i < adapter->num_tx_queues; i++) { - sprintf(p, "tx_queue_%u_packets", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_bytes", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_restart", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "tx_queue_%u_packets", i); + ethtool_sprintf(&p, "tx_queue_%u_bytes", i); + ethtool_sprintf(&p, "tx_queue_%u_restart", i); } for (i = 0; i < adapter->num_rx_queues; i++) { - sprintf(p, "rx_queue_%u_packets", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_bytes", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_drops", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_csum_err", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_alloc_failed", i); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&p, "rx_queue_%u_packets", i); + ethtool_sprintf(&p, "rx_queue_%u_bytes", i); + ethtool_sprintf(&p, "rx_queue_%u_drops", i); + ethtool_sprintf(&p, "rx_queue_%u_csum_err", i); + ethtool_sprintf(&p, "rx_queue_%u_alloc_failed", i); } /* BUG_ON(p - data != IGC_STATS_LEN * ETH_GSTRING_LEN); */ break; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index f1adf154ec4a..95323095094d 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -11,7 +11,7 @@ #include #include #include - +#include #include #include "igc.h" @@ -111,6 +111,9 @@ void igc_reset(struct igc_adapter *adapter) if (!netif_running(adapter->netdev)) igc_power_down_phy_copper_base(&adapter->hw); + /* Enable HW to recognize an 802.1Q VLAN Ethernet packet */ + wr32(IGC_VET, ETH_P_8021Q); + /* Re-enable PTP, where applicable. */ igc_ptp_reset(adapter); @@ -171,6 +174,14 @@ static void igc_get_hw_control(struct igc_adapter *adapter) ctrl_ext | IGC_CTRL_EXT_DRV_LOAD); } +static void igc_unmap_tx_buffer(struct device *dev, struct igc_tx_buffer *buf) +{ + dma_unmap_single(dev, dma_unmap_addr(buf, dma), + dma_unmap_len(buf, len), DMA_TO_DEVICE); + + dma_unmap_len_set(buf, len, 0); +} + /** * igc_clean_tx_ring - Free Tx Buffers * @tx_ring: ring to be cleaned @@ -179,20 +190,27 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) { u16 i = tx_ring->next_to_clean; struct igc_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; + u32 xsk_frames = 0; while (i != tx_ring->next_to_use) { union igc_adv_tx_desc *eop_desc, *tx_desc; - if (tx_buffer->tx_flags & IGC_TX_FLAGS_XDP) + switch (tx_buffer->type) { + case IGC_TX_BUFFER_TYPE_XSK: + xsk_frames++; + break; + case IGC_TX_BUFFER_TYPE_XDP: xdp_return_frame(tx_buffer->xdpf); - else + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); + break; + case IGC_TX_BUFFER_TYPE_SKB: dev_kfree_skb_any(tx_buffer->skb); - - /* unmap skb header data */ - dma_unmap_single(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); + break; + default: + netdev_warn_once(tx_ring->netdev, "Unknown Tx buffer type\n"); + break; + } /* check for eop_desc to determine the end of the packet */ eop_desc = tx_buffer->next_to_watch; @@ -211,10 +229,7 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) /* unmap any remaining paged data */ if (dma_unmap_len(tx_buffer, len)) - dma_unmap_page(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); } /* move us one more past the eop_desc for start of next pkt */ @@ -226,6 +241,9 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) } } + if (tx_ring->xsk_pool && xsk_frames) + xsk_tx_completed(tx_ring->xsk_pool, xsk_frames); + /* reset BQL for queue */ netdev_tx_reset_queue(txring_txq(tx_ring)); @@ -346,11 +364,7 @@ static int igc_setup_all_tx_resources(struct igc_adapter *adapter) return err; } -/** - * igc_clean_rx_ring - Free Rx Buffers per Queue - * @rx_ring: ring to free buffers from - */ -static void igc_clean_rx_ring(struct igc_ring *rx_ring) +static void igc_clean_rx_ring_page_shared(struct igc_ring *rx_ring) { u16 i = rx_ring->next_to_clean; @@ -383,12 +397,39 @@ static void igc_clean_rx_ring(struct igc_ring *rx_ring) if (i == rx_ring->count) i = 0; } +} - clear_ring_uses_large_buffer(rx_ring); +static void igc_clean_rx_ring_xsk_pool(struct igc_ring *ring) +{ + struct igc_rx_buffer *bi; + u16 i; - rx_ring->next_to_alloc = 0; - rx_ring->next_to_clean = 0; - rx_ring->next_to_use = 0; + for (i = 0; i < ring->count; i++) { + bi = &ring->rx_buffer_info[i]; + if (!bi->xdp) + continue; + + xsk_buff_free(bi->xdp); + bi->xdp = NULL; + } +} + +/** + * igc_clean_rx_ring - Free Rx Buffers per Queue + * @ring: ring to free buffers from + */ +static void igc_clean_rx_ring(struct igc_ring *ring) +{ + if (ring->xsk_pool) + igc_clean_rx_ring_xsk_pool(ring); + else + igc_clean_rx_ring_page_shared(ring); + + clear_ring_uses_large_buffer(ring); + + ring->next_to_alloc = 0; + ring->next_to_clean = 0; + ring->next_to_use = 0; } /** @@ -414,7 +455,7 @@ void igc_free_rx_resources(struct igc_ring *rx_ring) { igc_clean_rx_ring(rx_ring); - igc_xdp_unregister_rxq_info(rx_ring); + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; @@ -453,11 +494,16 @@ int igc_setup_rx_resources(struct igc_ring *rx_ring) { struct net_device *ndev = rx_ring->netdev; struct device *dev = rx_ring->dev; + u8 index = rx_ring->queue_index; int size, desc_len, res; - res = igc_xdp_register_rxq_info(rx_ring); - if (res < 0) + res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, ndev, index, + rx_ring->q_vector->napi.napi_id); + if (res < 0) { + netdev_err(ndev, "Failed to register xdp_rxq index %u\n", + index); return res; + } size = sizeof(struct igc_rx_buffer) * rx_ring->count; rx_ring->rx_buffer_info = vzalloc(size); @@ -483,7 +529,7 @@ int igc_setup_rx_resources(struct igc_ring *rx_ring) return 0; err: - igc_xdp_unregister_rxq_info(rx_ring); + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; netdev_err(ndev, "Unable to allocate memory for Rx descriptor ring\n"); @@ -515,9 +561,14 @@ static int igc_setup_all_rx_resources(struct igc_adapter *adapter) return err; } -static bool igc_xdp_is_enabled(struct igc_adapter *adapter) +static struct xsk_buff_pool *igc_get_xsk_pool(struct igc_adapter *adapter, + struct igc_ring *ring) { - return !!adapter->xdp_prog; + if (!igc_xdp_is_enabled(adapter) || + !test_bit(IGC_RING_FLAG_AF_XDP_ZC, &ring->flags)) + return NULL; + + return xsk_get_pool_from_qid(ring->netdev, ring->queue_index); } /** @@ -535,6 +586,20 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter, int reg_idx = ring->reg_idx; u32 srrctl = 0, rxdctl = 0; u64 rdba = ring->dma; + u32 buf_size; + + xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + ring->xsk_pool = igc_get_xsk_pool(adapter, ring); + if (ring->xsk_pool) { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_XSK_BUFF_POOL, + NULL)); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); + } else { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, + NULL)); + } if (igc_xdp_is_enabled(adapter)) set_ring_uses_large_buffer(ring); @@ -558,12 +623,15 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter, ring->next_to_clean = 0; ring->next_to_use = 0; - /* set descriptor configuration */ - srrctl = IGC_RX_HDR_LEN << IGC_SRRCTL_BSIZEHDRSIZE_SHIFT; - if (ring_uses_large_buffer(ring)) - srrctl |= IGC_RXBUFFER_3072 >> IGC_SRRCTL_BSIZEPKT_SHIFT; + if (ring->xsk_pool) + buf_size = xsk_pool_get_rx_frame_size(ring->xsk_pool); + else if (ring_uses_large_buffer(ring)) + buf_size = IGC_RXBUFFER_3072; else - srrctl |= IGC_RXBUFFER_2048 >> IGC_SRRCTL_BSIZEPKT_SHIFT; + buf_size = IGC_RXBUFFER_2048; + + srrctl = IGC_RX_HDR_LEN << IGC_SRRCTL_BSIZEHDRSIZE_SHIFT; + srrctl |= buf_size >> IGC_SRRCTL_BSIZEPKT_SHIFT; srrctl |= IGC_SRRCTL_DESCTYPE_ADV_ONEBUF; wr32(IGC_SRRCTL(reg_idx), srrctl); @@ -618,6 +686,8 @@ static void igc_configure_tx_ring(struct igc_adapter *adapter, u64 tdba = ring->dma; u32 txdctl = 0; + ring->xsk_pool = igc_get_xsk_pool(adapter, ring); + /* disable the queue */ wr32(IGC_TXDCTL(reg_idx), 0); wrfl(); @@ -1055,13 +1125,17 @@ static inline int igc_maybe_stop_tx(struct igc_ring *tx_ring, const u16 size) ((u32)((_input) & (_flag)) * ((_result) / (_flag))) : \ ((u32)((_input) & (_flag)) / ((_flag) / (_result)))) -static u32 igc_tx_cmd_type(u32 tx_flags) +static u32 igc_tx_cmd_type(struct sk_buff *skb, u32 tx_flags) { /* set type for advanced descriptor with frame checksum insertion */ u32 cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | IGC_ADVTXD_DCMD_IFCS; + /* set HW vlan bit if vlan is present */ + cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_VLAN, + IGC_ADVTXD_DCMD_VLE); + /* set segmentation bits for TSO */ cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSO, (IGC_ADVTXD_DCMD_TSE)); @@ -1070,6 +1144,9 @@ static u32 igc_tx_cmd_type(u32 tx_flags) cmd_type |= IGC_SET_FLAG(tx_flags, IGC_TX_FLAGS_TSTAMP, (IGC_ADVTXD_MAC_TSTAMP)); + /* insert frame checksum */ + cmd_type ^= IGC_SET_FLAG(skb->no_fcs, 1, IGC_ADVTXD_DCMD_IFCS); + return cmd_type; } @@ -1104,8 +1181,9 @@ static int igc_tx_map(struct igc_ring *tx_ring, u16 i = tx_ring->next_to_use; unsigned int data_len, size; dma_addr_t dma; - u32 cmd_type = igc_tx_cmd_type(tx_flags); + u32 cmd_type; + cmd_type = igc_tx_cmd_type(skb, tx_flags); tx_desc = IGC_TX_DESC(tx_ring, i); igc_tx_olinfo_status(tx_ring, tx_desc, tx_flags, skb->len - hdr_len); @@ -1211,11 +1289,7 @@ dma_error: /* clear dma mappings for failed tx_buffer_info map */ while (tx_buffer != first) { if (dma_unmap_len(tx_buffer, len)) - dma_unmap_page(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - dma_unmap_len_set(tx_buffer, len, 0); + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); if (i-- == 0) i += tx_ring->count; @@ -1223,11 +1297,7 @@ dma_error: } if (dma_unmap_len(tx_buffer, len)) - dma_unmap_single(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - dma_unmap_len_set(tx_buffer, len, 0); + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); dev_kfree_skb_any(tx_buffer->skb); tx_buffer->skb = NULL; @@ -1359,6 +1429,7 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, /* record the location of the first descriptor for this packet */ first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + first->type = IGC_TX_BUFFER_TYPE_SKB; first->skb = skb; first->bytecount = skb->len; first->gso_segs = 1; @@ -1383,6 +1454,11 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, } } + if (skb_vlan_tag_present(skb)) { + tx_flags |= IGC_TX_FLAGS_VLAN; + tx_flags |= (skb_vlan_tag_get(skb) << IGC_TX_FLAGS_VLAN_SHIFT); + } + /* record initial flags and protocol */ first->tx_flags = tx_flags; first->protocol = protocol; @@ -1482,6 +1558,25 @@ static inline void igc_rx_hash(struct igc_ring *ring, PKT_HASH_TYPE_L3); } +static void igc_rx_vlan(struct igc_ring *rx_ring, + union igc_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct net_device *dev = rx_ring->netdev; + u16 vid; + + if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) && + igc_test_staterr(rx_desc, IGC_RXD_STAT_VP)) { + if (igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_LB) && + test_bit(IGC_RING_FLAG_RX_LB_VLAN_BSWAP, &rx_ring->flags)) + vid = be16_to_cpu((__force __be16)rx_desc->wb.upper.vlan); + else + vid = le16_to_cpu(rx_desc->wb.upper.vlan); + + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); + } +} + /** * igc_process_skb_fields - Populate skb header fields from Rx descriptor * @rx_ring: rx descriptor ring packet is being transacted on @@ -1500,11 +1595,37 @@ static void igc_process_skb_fields(struct igc_ring *rx_ring, igc_rx_checksum(rx_ring, rx_desc, skb); + igc_rx_vlan(rx_ring, rx_desc, skb); + skb_record_rx_queue(skb, rx_ring->queue_index); skb->protocol = eth_type_trans(skb, rx_ring->netdev); } +static void igc_vlan_mode(struct net_device *netdev, netdev_features_t features) +{ + bool enable = !!(features & NETIF_F_HW_VLAN_CTAG_RX); + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + u32 ctrl; + + ctrl = rd32(IGC_CTRL); + + if (enable) { + /* enable VLAN tag insert/strip */ + ctrl |= IGC_CTRL_VME; + } else { + /* disable VLAN tag insert/strip */ + ctrl &= ~IGC_CTRL_VME; + } + wr32(IGC_CTRL, ctrl); +} + +static void igc_restore_vlan(struct igc_adapter *adapter) +{ + igc_vlan_mode(adapter->netdev, adapter->netdev->features); +} + static struct igc_rx_buffer *igc_get_rx_buffer(struct igc_ring *rx_ring, const unsigned int size, int *rx_buffer_pgcnt) @@ -1930,6 +2051,63 @@ static void igc_alloc_rx_buffers(struct igc_ring *rx_ring, u16 cleaned_count) } } +static bool igc_alloc_rx_buffers_zc(struct igc_ring *ring, u16 count) +{ + union igc_adv_rx_desc *desc; + u16 i = ring->next_to_use; + struct igc_rx_buffer *bi; + dma_addr_t dma; + bool ok = true; + + if (!count) + return ok; + + desc = IGC_RX_DESC(ring, i); + bi = &ring->rx_buffer_info[i]; + i -= ring->count; + + do { + bi->xdp = xsk_buff_alloc(ring->xsk_pool); + if (!bi->xdp) { + ok = false; + break; + } + + dma = xsk_buff_xdp_get_dma(bi->xdp); + desc->read.pkt_addr = cpu_to_le64(dma); + + desc++; + bi++; + i++; + if (unlikely(!i)) { + desc = IGC_RX_DESC(ring, 0); + bi = ring->rx_buffer_info; + i -= ring->count; + } + + /* Clear the length for the next_to_use descriptor. */ + desc->wb.upper.length = 0; + + count--; + } while (count); + + i += ring->count; + + if (ring->next_to_use != i) { + ring->next_to_use = i; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(i, ring->tail); + } + + return ok; +} + static int igc_xdp_init_tx_buffer(struct igc_tx_buffer *buffer, struct xdp_frame *xdpf, struct igc_ring *ring) @@ -1942,8 +2120,8 @@ static int igc_xdp_init_tx_buffer(struct igc_tx_buffer *buffer, return -ENOMEM; } + buffer->type = IGC_TX_BUFFER_TYPE_XDP; buffer->xdpf = xdpf; - buffer->tx_flags = IGC_TX_FLAGS_XDP; buffer->protocol = 0; buffer->bytecount = xdpf->len; buffer->gso_segs = 1; @@ -2025,35 +2203,24 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp) return res; } -static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, - struct xdp_buff *xdp) +/* This function assumes rcu_read_lock() is held by the caller. */ +static int __igc_xdp_run_prog(struct igc_adapter *adapter, + struct bpf_prog *prog, + struct xdp_buff *xdp) { - struct bpf_prog *prog; - int res; - u32 act; + u32 act = bpf_prog_run_xdp(prog, xdp); - rcu_read_lock(); - - prog = READ_ONCE(adapter->xdp_prog); - if (!prog) { - res = IGC_XDP_PASS; - goto unlock; - } - - act = bpf_prog_run_xdp(prog, xdp); switch (act) { case XDP_PASS: - res = IGC_XDP_PASS; - break; + return IGC_XDP_PASS; case XDP_TX: if (igc_xdp_xmit_back(adapter, xdp) < 0) goto out_failure; - res = IGC_XDP_TX; - break; + return IGC_XDP_TX; case XDP_REDIRECT: if (xdp_do_redirect(adapter->netdev, xdp, prog) < 0) goto out_failure; - res = IGC_XDP_REDIRECT; + return IGC_XDP_REDIRECT; break; default: bpf_warn_invalid_xdp_action(act); @@ -2063,12 +2230,25 @@ out_failure: trace_xdp_exception(adapter->netdev, prog, act); fallthrough; case XDP_DROP: - res = IGC_XDP_CONSUMED; - break; + return IGC_XDP_CONSUMED; + } +} + +static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, + struct xdp_buff *xdp) +{ + struct bpf_prog *prog; + int res; + + prog = READ_ONCE(adapter->xdp_prog); + if (!prog) { + res = IGC_XDP_PASS; + goto out; } -unlock: - rcu_read_unlock(); + res = __igc_xdp_run_prog(adapter, prog, xdp); + +out: return ERR_PTR(-res); } @@ -2102,6 +2282,20 @@ static void igc_finalize_xdp(struct igc_adapter *adapter, int status) xdp_do_flush(); } +static void igc_update_rx_stats(struct igc_q_vector *q_vector, + unsigned int packets, unsigned int bytes) +{ + struct igc_ring *ring = q_vector->rx.ring; + + u64_stats_update_begin(&ring->rx_syncp); + ring->rx_stats.packets += packets; + ring->rx_stats.bytes += bytes; + u64_stats_update_end(&ring->rx_syncp); + + q_vector->rx.total_packets += packets; + q_vector->rx.total_bytes += bytes; +} + static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) { unsigned int total_bytes = 0, total_packets = 0; @@ -2150,12 +2344,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) } if (!skb) { - xdp.data = pktbuf + pkt_offset; - xdp.data_end = xdp.data + size; - xdp.data_hard_start = pktbuf - igc_rx_offset(rx_ring); - xdp_set_data_meta_invalid(&xdp); - xdp.frame_sz = truesize; - xdp.rxq = &rx_ring->xdp_rxq; + xdp_init_buff(&xdp, truesize, &rx_ring->xdp_rxq); + xdp_prepare_buff(&xdp, pktbuf - igc_rx_offset(rx_ring), + igc_rx_offset(rx_ring) + pkt_offset, size, false); skb = igc_xdp_run_prog(adapter, &xdp); } @@ -2225,12 +2416,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) /* place incomplete frames back on ring for completion */ rx_ring->skb = skb; - u64_stats_update_begin(&rx_ring->rx_syncp); - rx_ring->rx_stats.packets += total_packets; - rx_ring->rx_stats.bytes += total_bytes; - u64_stats_update_end(&rx_ring->rx_syncp); - q_vector->rx.total_packets += total_packets; - q_vector->rx.total_bytes += total_bytes; + igc_update_rx_stats(q_vector, total_packets, total_bytes); if (cleaned_count) igc_alloc_rx_buffers(rx_ring, cleaned_count); @@ -2238,6 +2424,221 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) return total_packets; } +static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, + struct xdp_buff *xdp) +{ + unsigned int metasize = xdp->data - xdp->data_meta; + unsigned int datasize = xdp->data_end - xdp->data; + unsigned int totalsize = metasize + datasize; + struct sk_buff *skb; + + skb = __napi_alloc_skb(&ring->q_vector->napi, + xdp->data_end - xdp->data_hard_start, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!skb)) + return NULL; + + skb_reserve(skb, xdp->data_meta - xdp->data_hard_start); + memcpy(__skb_put(skb, totalsize), xdp->data_meta, totalsize); + if (metasize) + skb_metadata_set(skb, metasize); + + return skb; +} + +static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector, + union igc_adv_rx_desc *desc, + struct xdp_buff *xdp, + ktime_t timestamp) +{ + struct igc_ring *ring = q_vector->rx.ring; + struct sk_buff *skb; + + skb = igc_construct_skb_zc(ring, xdp); + if (!skb) { + ring->rx_stats.alloc_failed++; + return; + } + + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; + + if (igc_cleanup_headers(ring, desc, skb)) + return; + + igc_process_skb_fields(ring, desc, skb); + napi_gro_receive(&q_vector->napi, skb); +} + +static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) +{ + struct igc_adapter *adapter = q_vector->adapter; + struct igc_ring *ring = q_vector->rx.ring; + u16 cleaned_count = igc_desc_unused(ring); + int total_bytes = 0, total_packets = 0; + u16 ntc = ring->next_to_clean; + struct bpf_prog *prog; + bool failure = false; + int xdp_status = 0; + + rcu_read_lock(); + + prog = READ_ONCE(adapter->xdp_prog); + + while (likely(total_packets < budget)) { + union igc_adv_rx_desc *desc; + struct igc_rx_buffer *bi; + ktime_t timestamp = 0; + unsigned int size; + int res; + + desc = IGC_RX_DESC(ring, ntc); + size = le16_to_cpu(desc->wb.upper.length); + if (!size) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * descriptor has been written back + */ + dma_rmb(); + + bi = &ring->rx_buffer_info[ntc]; + + if (igc_test_staterr(desc, IGC_RXDADV_STAT_TSIP)) { + timestamp = igc_ptp_rx_pktstamp(q_vector->adapter, + bi->xdp->data); + + bi->xdp->data += IGC_TS_HDR_LEN; + + /* HW timestamp has been copied into local variable. Metadata + * length when XDP program is called should be 0. + */ + bi->xdp->data_meta += IGC_TS_HDR_LEN; + size -= IGC_TS_HDR_LEN; + } + + bi->xdp->data_end = bi->xdp->data + size; + xsk_buff_dma_sync_for_cpu(bi->xdp, ring->xsk_pool); + + res = __igc_xdp_run_prog(adapter, prog, bi->xdp); + switch (res) { + case IGC_XDP_PASS: + igc_dispatch_skb_zc(q_vector, desc, bi->xdp, timestamp); + fallthrough; + case IGC_XDP_CONSUMED: + xsk_buff_free(bi->xdp); + break; + case IGC_XDP_TX: + case IGC_XDP_REDIRECT: + xdp_status |= res; + break; + } + + bi->xdp = NULL; + total_bytes += size; + total_packets++; + cleaned_count++; + ntc++; + if (ntc == ring->count) + ntc = 0; + } + + ring->next_to_clean = ntc; + rcu_read_unlock(); + + if (cleaned_count >= IGC_RX_BUFFER_WRITE) + failure = !igc_alloc_rx_buffers_zc(ring, cleaned_count); + + if (xdp_status) + igc_finalize_xdp(adapter, xdp_status); + + igc_update_rx_stats(q_vector, total_packets, total_bytes); + + if (xsk_uses_need_wakeup(ring->xsk_pool)) { + if (failure || ring->next_to_clean == ring->next_to_use) + xsk_set_rx_need_wakeup(ring->xsk_pool); + else + xsk_clear_rx_need_wakeup(ring->xsk_pool); + return total_packets; + } + + return failure ? budget : total_packets; +} + +static void igc_update_tx_stats(struct igc_q_vector *q_vector, + unsigned int packets, unsigned int bytes) +{ + struct igc_ring *ring = q_vector->tx.ring; + + u64_stats_update_begin(&ring->tx_syncp); + ring->tx_stats.bytes += bytes; + ring->tx_stats.packets += packets; + u64_stats_update_end(&ring->tx_syncp); + + q_vector->tx.total_bytes += bytes; + q_vector->tx.total_packets += packets; +} + +static void igc_xdp_xmit_zc(struct igc_ring *ring) +{ + struct xsk_buff_pool *pool = ring->xsk_pool; + struct netdev_queue *nq = txring_txq(ring); + union igc_adv_tx_desc *tx_desc = NULL; + int cpu = smp_processor_id(); + u16 ntu = ring->next_to_use; + struct xdp_desc xdp_desc; + u16 budget; + + if (!netif_carrier_ok(ring->netdev)) + return; + + __netif_tx_lock(nq, cpu); + + budget = igc_desc_unused(ring); + + while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) { + u32 cmd_type, olinfo_status; + struct igc_tx_buffer *bi; + dma_addr_t dma; + + cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | + IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | + xdp_desc.len; + olinfo_status = xdp_desc.len << IGC_ADVTXD_PAYLEN_SHIFT; + + dma = xsk_buff_raw_get_dma(pool, xdp_desc.addr); + xsk_buff_raw_dma_sync_for_device(pool, dma, xdp_desc.len); + + tx_desc = IGC_TX_DESC(ring, ntu); + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + bi = &ring->tx_buffer_info[ntu]; + bi->type = IGC_TX_BUFFER_TYPE_XSK; + bi->protocol = 0; + bi->bytecount = xdp_desc.len; + bi->gso_segs = 1; + bi->time_stamp = jiffies; + bi->next_to_watch = tx_desc; + + netdev_tx_sent_queue(txring_txq(ring), xdp_desc.len); + + ntu++; + if (ntu == ring->count) + ntu = 0; + } + + ring->next_to_use = ntu; + if (tx_desc) { + igc_flush_tx_descriptors(ring); + xsk_tx_release(pool); + } + + __netif_tx_unlock(nq); +} + /** * igc_clean_tx_irq - Reclaim resources after transmit completes * @q_vector: pointer to q_vector containing needed info @@ -2254,6 +2655,7 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) unsigned int i = tx_ring->next_to_clean; struct igc_tx_buffer *tx_buffer; union igc_adv_tx_desc *tx_desc; + u32 xsk_frames = 0; if (test_bit(__IGC_DOWN, &adapter->state)) return true; @@ -2283,19 +2685,22 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) total_bytes += tx_buffer->bytecount; total_packets += tx_buffer->gso_segs; - if (tx_buffer->tx_flags & IGC_TX_FLAGS_XDP) + switch (tx_buffer->type) { + case IGC_TX_BUFFER_TYPE_XSK: + xsk_frames++; + break; + case IGC_TX_BUFFER_TYPE_XDP: xdp_return_frame(tx_buffer->xdpf); - else + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); + break; + case IGC_TX_BUFFER_TYPE_SKB: napi_consume_skb(tx_buffer->skb, napi_budget); - - /* unmap skb header data */ - dma_unmap_single(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - - /* clear tx_buffer data */ - dma_unmap_len_set(tx_buffer, len, 0); + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); + break; + default: + netdev_warn_once(tx_ring->netdev, "Unknown Tx buffer type\n"); + break; + } /* clear last DMA location and unmap remaining buffers */ while (tx_desc != eop_desc) { @@ -2309,13 +2714,8 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) } /* unmap any remaining paged data */ - if (dma_unmap_len(tx_buffer, len)) { - dma_unmap_page(tx_ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - dma_unmap_len_set(tx_buffer, len, 0); - } + if (dma_unmap_len(tx_buffer, len)) + igc_unmap_tx_buffer(tx_ring->dev, tx_buffer); } /* move us one more past the eop_desc for start of next pkt */ @@ -2340,12 +2740,16 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) i += tx_ring->count; tx_ring->next_to_clean = i; - u64_stats_update_begin(&tx_ring->tx_syncp); - tx_ring->tx_stats.bytes += total_bytes; - tx_ring->tx_stats.packets += total_packets; - u64_stats_update_end(&tx_ring->tx_syncp); - q_vector->tx.total_bytes += total_bytes; - q_vector->tx.total_packets += total_packets; + + igc_update_tx_stats(q_vector, total_packets, total_bytes); + + if (tx_ring->xsk_pool) { + if (xsk_frames) + xsk_tx_completed(tx_ring->xsk_pool, xsk_frames); + if (xsk_uses_need_wakeup(tx_ring->xsk_pool)) + xsk_set_tx_need_wakeup(tx_ring->xsk_pool); + igc_xdp_xmit_zc(tx_ring); + } if (test_bit(IGC_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) { struct igc_hw *hw = &adapter->hw; @@ -2906,6 +3310,8 @@ static void igc_configure(struct igc_adapter *adapter) igc_get_hw_control(adapter); igc_set_rx_mode(netdev); + igc_restore_vlan(adapter); + igc_setup_tctl(adapter); igc_setup_mrqc(adapter); igc_setup_rctl(adapter); @@ -2925,7 +3331,10 @@ static void igc_configure(struct igc_adapter *adapter) for (i = 0; i < adapter->num_rx_queues; i++) { struct igc_ring *ring = adapter->rx_ring[i]; - igc_alloc_rx_buffers(ring, igc_desc_unused(ring)); + if (ring->xsk_pool) + igc_alloc_rx_buffers_zc(ring, igc_desc_unused(ring)); + else + igc_alloc_rx_buffers(ring, igc_desc_unused(ring)); } } @@ -3540,14 +3949,17 @@ static int igc_poll(struct napi_struct *napi, int budget) struct igc_q_vector *q_vector = container_of(napi, struct igc_q_vector, napi); + struct igc_ring *rx_ring = q_vector->rx.ring; bool clean_complete = true; int work_done = 0; if (q_vector->tx.ring) clean_complete = igc_clean_tx_irq(q_vector, budget); - if (q_vector->rx.ring) { - int cleaned = igc_clean_rx_irq(q_vector, budget); + if (rx_ring) { + int cleaned = rx_ring->xsk_pool ? + igc_clean_rx_irq_zc(q_vector, budget) : + igc_clean_rx_irq(q_vector, budget); work_done += cleaned; if (cleaned >= budget) @@ -4199,6 +4611,9 @@ static int igc_set_features(struct net_device *netdev, netdev_features_t changed = netdev->features ^ features; struct igc_adapter *adapter = netdev_priv(netdev); + if (changed & NETIF_F_HW_VLAN_CTAG_RX) + igc_vlan_mode(netdev, features); + /* Add VLAN support */ if (!(changed & (NETIF_F_RXALL | NETIF_F_NTUPLE))) return 0; @@ -5185,6 +5600,9 @@ static int igc_bpf(struct net_device *dev, struct netdev_bpf *bpf) switch (bpf->command) { case XDP_SETUP_PROG: return igc_xdp_set_prog(adapter, bpf->prog, bpf->extack); + case XDP_SETUP_XSK_POOL: + return igc_xdp_setup_pool(adapter, bpf->xsk.pool, + bpf->xsk.queue_id); default: return -EOPNOTSUPP; } @@ -5230,6 +5648,43 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, return num_frames - drops; } +static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter, + struct igc_q_vector *q_vector) +{ + struct igc_hw *hw = &adapter->hw; + u32 eics = 0; + + eics |= q_vector->eims_value; + wr32(IGC_EICS, eics); +} + +int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) +{ + struct igc_adapter *adapter = netdev_priv(dev); + struct igc_q_vector *q_vector; + struct igc_ring *ring; + + if (test_bit(__IGC_DOWN, &adapter->state)) + return -ENETDOWN; + + if (!igc_xdp_is_enabled(adapter)) + return -ENXIO; + + if (queue_id >= adapter->num_rx_queues) + return -EINVAL; + + ring = adapter->rx_ring[queue_id]; + + if (!ring->xsk_pool) + return -ENXIO; + + q_vector = adapter->q_vector[queue_id]; + if (!napi_if_scheduled_mark_missed(&q_vector->napi)) + igc_trigger_rxtxq_interrupt(adapter, q_vector); + + return 0; +} + static const struct net_device_ops igc_netdev_ops = { .ndo_open = igc_open, .ndo_stop = igc_close, @@ -5245,6 +5700,7 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_setup_tc = igc_setup_tc, .ndo_bpf = igc_bpf, .ndo_xdp_xmit = igc_xdp_xmit, + .ndo_xsk_wakeup = igc_xsk_wakeup, }; /* PCIe configuration access */ @@ -5484,11 +5940,15 @@ static int igc_probe(struct pci_dev *pdev, /* copy netdev features into list of user selectable features */ netdev->hw_features |= NETIF_F_NTUPLE; + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX; + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; netdev->hw_features |= netdev->features; if (pci_using_dac) netdev->features |= NETIF_F_HIGHDMA; + netdev->vlan_features |= netdev->features; + /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE; @@ -5997,6 +6457,61 @@ struct net_device *igc_get_hw_dev(struct igc_hw *hw) return adapter->netdev; } +static void igc_disable_rx_ring_hw(struct igc_ring *ring) +{ + struct igc_hw *hw = &ring->q_vector->adapter->hw; + u8 idx = ring->reg_idx; + u32 rxdctl; + + rxdctl = rd32(IGC_RXDCTL(idx)); + rxdctl &= ~IGC_RXDCTL_QUEUE_ENABLE; + rxdctl |= IGC_RXDCTL_SWFLUSH; + wr32(IGC_RXDCTL(idx), rxdctl); +} + +void igc_disable_rx_ring(struct igc_ring *ring) +{ + igc_disable_rx_ring_hw(ring); + igc_clean_rx_ring(ring); +} + +void igc_enable_rx_ring(struct igc_ring *ring) +{ + struct igc_adapter *adapter = ring->q_vector->adapter; + + igc_configure_rx_ring(adapter, ring); + + if (ring->xsk_pool) + igc_alloc_rx_buffers_zc(ring, igc_desc_unused(ring)); + else + igc_alloc_rx_buffers(ring, igc_desc_unused(ring)); +} + +static void igc_disable_tx_ring_hw(struct igc_ring *ring) +{ + struct igc_hw *hw = &ring->q_vector->adapter->hw; + u8 idx = ring->reg_idx; + u32 txdctl; + + txdctl = rd32(IGC_TXDCTL(idx)); + txdctl &= ~IGC_TXDCTL_QUEUE_ENABLE; + txdctl |= IGC_TXDCTL_SWFLUSH; + wr32(IGC_TXDCTL(idx), txdctl); +} + +void igc_disable_tx_ring(struct igc_ring *ring) +{ + igc_disable_tx_ring_hw(ring); + igc_clean_tx_ring(ring); +} + +void igc_enable_tx_ring(struct igc_ring *ring) +{ + struct igc_adapter *adapter = ring->q_vector->adapter; + + igc_configure_tx_ring(adapter, ring); +} + /** * igc_init_module - Driver Registration Routine * diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index cc174853554b..0f82990567d9 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -10,8 +10,8 @@ #define IGC_EECD 0x00010 /* EEPROM/Flash Control - RW */ #define IGC_CTRL_EXT 0x00018 /* Extended Device Control - RW */ #define IGC_MDIC 0x00020 /* MDI Control - RW */ -#define IGC_MDICNFG 0x00E04 /* MDC/MDIO Configuration - RW */ #define IGC_CONNSW 0x00034 /* Copper/Fiber switch control - RW */ +#define IGC_VET 0x00038 /* VLAN Ether Type - RW */ #define IGC_I225_PHPM 0x00E14 /* I225 PHY Power Management */ #define IGC_GPHY_VERSION 0x0001E /* I225 gPHY Firmware Version */ diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c index 11133c4619bb..a8cf5374be47 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.c +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020, Intel Corporation. */ +#include + #include "igc.h" #include "igc_xdp.h" @@ -32,29 +34,112 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, return 0; } -int igc_xdp_register_rxq_info(struct igc_ring *ring) +static int igc_xdp_enable_pool(struct igc_adapter *adapter, + struct xsk_buff_pool *pool, u16 queue_id) { - struct net_device *dev = ring->netdev; + struct net_device *ndev = adapter->netdev; + struct device *dev = &adapter->pdev->dev; + struct igc_ring *rx_ring, *tx_ring; + struct napi_struct *napi; + bool needs_reset; + u32 frame_size; int err; - err = xdp_rxq_info_reg(&ring->xdp_rxq, dev, ring->queue_index, 0); + if (queue_id >= adapter->num_rx_queues || + queue_id >= adapter->num_tx_queues) + return -EINVAL; + + frame_size = xsk_pool_get_rx_frame_size(pool); + if (frame_size < ETH_FRAME_LEN + VLAN_HLEN * 2) { + /* When XDP is enabled, the driver doesn't support frames that + * span over multiple buffers. To avoid that, we check if xsk + * frame size is big enough to fit the max ethernet frame size + * + vlan double tagging. + */ + return -EOPNOTSUPP; + } + + err = xsk_pool_dma_map(pool, dev, IGC_RX_DMA_ATTR); if (err) { - netdev_err(dev, "Failed to register xdp rxq info\n"); + netdev_err(ndev, "Failed to map xsk pool\n"); return err; } - err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, - NULL); - if (err) { - netdev_err(dev, "Failed to register xdp rxq mem model\n"); - xdp_rxq_info_unreg(&ring->xdp_rxq); - return err; + needs_reset = netif_running(adapter->netdev) && igc_xdp_is_enabled(adapter); + + rx_ring = adapter->rx_ring[queue_id]; + tx_ring = adapter->tx_ring[queue_id]; + /* Rx and Tx rings share the same napi context. */ + napi = &rx_ring->q_vector->napi; + + if (needs_reset) { + igc_disable_rx_ring(rx_ring); + igc_disable_tx_ring(tx_ring); + napi_disable(napi); + } + + set_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags); + set_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags); + + if (needs_reset) { + napi_enable(napi); + igc_enable_rx_ring(rx_ring); + igc_enable_tx_ring(tx_ring); + + err = igc_xsk_wakeup(ndev, queue_id, XDP_WAKEUP_RX); + if (err) { + xsk_pool_dma_unmap(pool, IGC_RX_DMA_ATTR); + return err; + } } return 0; } -void igc_xdp_unregister_rxq_info(struct igc_ring *ring) +static int igc_xdp_disable_pool(struct igc_adapter *adapter, u16 queue_id) { - xdp_rxq_info_unreg(&ring->xdp_rxq); + struct igc_ring *rx_ring, *tx_ring; + struct xsk_buff_pool *pool; + struct napi_struct *napi; + bool needs_reset; + + if (queue_id >= adapter->num_rx_queues || + queue_id >= adapter->num_tx_queues) + return -EINVAL; + + pool = xsk_get_pool_from_qid(adapter->netdev, queue_id); + if (!pool) + return -EINVAL; + + needs_reset = netif_running(adapter->netdev) && igc_xdp_is_enabled(adapter); + + rx_ring = adapter->rx_ring[queue_id]; + tx_ring = adapter->tx_ring[queue_id]; + /* Rx and Tx rings share the same napi context. */ + napi = &rx_ring->q_vector->napi; + + if (needs_reset) { + igc_disable_rx_ring(rx_ring); + igc_disable_tx_ring(tx_ring); + napi_disable(napi); + } + + xsk_pool_dma_unmap(pool, IGC_RX_DMA_ATTR); + clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags); + clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags); + + if (needs_reset) { + napi_enable(napi); + igc_enable_rx_ring(rx_ring); + igc_enable_tx_ring(tx_ring); + } + + return 0; +} + +int igc_xdp_setup_pool(struct igc_adapter *adapter, struct xsk_buff_pool *pool, + u16 queue_id) +{ + return pool ? igc_xdp_enable_pool(adapter, pool, queue_id) : + igc_xdp_disable_pool(adapter, queue_id); } diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.h b/drivers/net/ethernet/intel/igc/igc_xdp.h index cfecb515b718..a74e5487d199 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.h +++ b/drivers/net/ethernet/intel/igc/igc_xdp.h @@ -6,8 +6,12 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, struct netlink_ext_ack *extack); +int igc_xdp_setup_pool(struct igc_adapter *adapter, struct xsk_buff_pool *pool, + u16 queue_id); -int igc_xdp_register_rxq_info(struct igc_ring *ring); -void igc_xdp_unregister_rxq_info(struct igc_ring *ring); +static inline bool igc_xdp_is_enabled(struct igc_adapter *adapter) +{ + return !!adapter->xdp_prog; +} #endif /* _IGC_XDP_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index e324e42fab2d..58ea959a4482 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -1514,8 +1514,7 @@ static u32 ixgbe_get_fdirtcpm_82599(union ixgbe_atr_input *input_mask) #define IXGBE_WRITE_REG_BE32(a, reg, value) \ IXGBE_WRITE_REG((a), (reg), IXGBE_STORE_AS_BE32(ntohl(value))) -#define IXGBE_STORE_AS_BE16(_value) \ - ntohs(((u16)(_value) >> 8) | ((u16)(_value) << 8)) +#define IXGBE_STORE_AS_BE16(_value) __swab16(ntohs((_value))) s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, union ixgbe_atr_input *input_mask) @@ -1651,13 +1650,13 @@ s32 ixgbe_fdir_write_perfect_filter_82599(struct ixgbe_hw *hw, IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRIPDA, input->formatted.dst_ip[0]); /* record source and destination port (little-endian)*/ - fdirport = ntohs(input->formatted.dst_port); + fdirport = be16_to_cpu(input->formatted.dst_port); fdirport <<= IXGBE_FDIRPORT_DESTINATION_SHIFT; - fdirport |= ntohs(input->formatted.src_port); + fdirport |= be16_to_cpu(input->formatted.src_port); IXGBE_WRITE_REG(hw, IXGBE_FDIRPORT, fdirport); /* record vlan (little-endian) and flex_bytes(big-endian) */ - fdirvlan = IXGBE_STORE_AS_BE16((__force u16)input->formatted.flex_bytes); + fdirvlan = IXGBE_STORE_AS_BE16(input->formatted.flex_bytes); fdirvlan <<= IXGBE_FDIRVLAN_FLEX_SHIFT; fdirvlan |= ntohs(input->formatted.vlan_id); IXGBE_WRITE_REG(hw, IXGBE_FDIRVLAN, fdirvlan); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 03ccbe6b66d2..e90b5047e695 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -3678,10 +3678,8 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, bool return_data) { u32 hdr_size = sizeof(struct ixgbe_hic_hdr); - union { - struct ixgbe_hic_hdr hdr; - u32 u32arr[1]; - } *bp = buffer; + struct ixgbe_hic_hdr *hdr = buffer; + u32 *u32arr = buffer; u16 buf_len, dword_len; s32 status; u32 bi; @@ -3707,12 +3705,12 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, /* first pull in the header so we know the buffer length */ for (bi = 0; bi < dword_len; bi++) { - bp->u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi); - le32_to_cpus(&bp->u32arr[bi]); + u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi); + le32_to_cpus(&u32arr[bi]); } /* If there is any thing in data position pull it in */ - buf_len = bp->hdr.buf_len; + buf_len = hdr->buf_len; if (!buf_len) goto rel_out; @@ -3727,8 +3725,8 @@ s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, /* Pull in the rest of the buffer (bi is where we left off) */ for (; bi <= dword_len; bi++) { - bp->u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi); - le32_to_cpus(&bp->u32arr[bi]); + u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi); + le32_to_cpus(&u32arr[bi]); } rel_out: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index 54d47265a7ac..e596e1a9fc75 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -511,14 +511,14 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs) continue; reg = IXGBE_READ_REG(hw, MIPAF_ARR(3, i)); - if (reg == xs->id.daddr.a4) + if (reg == (__force u32)xs->id.daddr.a4) return 1; } } if ((bmcipval & BMCIP_MASK) == BMCIP_V4) { reg = IXGBE_READ_REG(hw, IXGBE_BMCIP(3)); - if (reg == xs->id.daddr.a4) + if (reg == (__force u32)xs->id.daddr.a4) return 1; } @@ -533,7 +533,7 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs) for (j = 0; j < 4; j++) { reg = IXGBE_READ_REG(hw, MIPAF_ARR(i, j)); - if (reg != xs->id.daddr.a6[j]) + if (reg != (__force u32)xs->id.daddr.a6[j]) break; } if (j == 4) /* did we match all 4 words? */ @@ -543,7 +543,7 @@ static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs) if ((bmcipval & BMCIP_MASK) == BMCIP_V6) { for (j = 0; j < 4; j++) { reg = IXGBE_READ_REG(hw, IXGBE_BMCIP(j)); - if (reg != xs->id.daddr.a6[j]) + if (reg != (__force u32)xs->id.daddr.a6[j]) break; } if (j == 4) /* did we match all 4 words? */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 2ac5b82676f3..ffff69efd78a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2199,7 +2199,6 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, struct xdp_frame *xdpf; u32 act; - rcu_read_lock(); xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (!xdp_prog) @@ -2237,7 +2236,6 @@ out_failure: break; } xdp_out: - rcu_read_unlock(); return ERR_PTR(-result); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index f72d2978263b..96dd1a4f956a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -100,7 +100,6 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, struct xdp_frame *xdpf; u32 act; - rcu_read_lock(); xdp_prog = READ_ONCE(rx_ring->xdp_prog); act = bpf_prog_run_xdp(xdp_prog, xdp); @@ -108,7 +107,6 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); if (err) goto out_failure; - rcu_read_unlock(); return IXGBE_XDP_REDIR; } @@ -134,7 +132,6 @@ out_failure: result = IXGBE_XDP_CONSUMED; break; } - rcu_read_unlock(); return result; } diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 0e733cc15c58..c714e1ecd308 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1054,7 +1054,6 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter, struct bpf_prog *xdp_prog; u32 act; - rcu_read_lock(); xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (!xdp_prog) @@ -1082,7 +1081,6 @@ out_failure: break; } xdp_out: - rcu_read_unlock(); return ERR_PTR(-result); } @@ -3817,7 +3815,7 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, /* remove payload length from inner checksum */ paylen = skb->len - l4_offset; - csum_replace_by_diff(&l4.tcp->check, htonl(paylen)); + csum_replace_by_diff(&l4.tcp->check, (__force __wsum)htonl(paylen)); /* update gso size and bytecount with header size */ first->gso_segs = skb_shinfo(skb)->gso_segs; diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 21ef2f128070..fb78f17d734f 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -437,7 +437,6 @@ static int xrx200_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; - struct resource *res; struct xrx200_priv *priv; struct net_device *net_dev; int err; @@ -457,13 +456,7 @@ static int xrx200_probe(struct platform_device *pdev) net_dev->max_mtu = XRX200_DMA_DATA_LEN; /* load the memory ranges */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - dev_err(dev, "failed to get resources\n"); - return -ENOENT; - } - - priv->pmac_reg = devm_ioremap_resource(dev, res); + priv->pmac_reg = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(priv->pmac_reg)) return PTR_ERR(priv->pmac_reg); diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index d14762d93640..62a97c46fba0 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -17,6 +17,8 @@ * warranty of any kind, whether express or implied. */ +#include +#include #include #include #include @@ -281,7 +283,7 @@ static int orion_mdio_probe(struct platform_device *pdev) struct orion_mdio_dev *dev; int i, ret; - type = (enum orion_mdio_bus_type)of_device_get_match_data(&pdev->dev); + type = (enum orion_mdio_bus_type)device_get_match_data(&pdev->dev); r = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!r) { @@ -369,7 +371,13 @@ static int orion_mdio_probe(struct platform_device *pdev) goto out_mdio; } - ret = of_mdiobus_register(bus, pdev->dev.of_node); + /* For the platforms not supporting DT/ACPI fall-back + * to mdiobus_register via of_mdiobus_register. + */ + if (is_acpi_node(pdev->dev.fwnode)) + ret = acpi_mdiobus_register(bus, pdev->dev.fwnode); + else + ret = of_mdiobus_register(bus, pdev->dev.of_node); if (ret < 0) { dev_err(&pdev->dev, "Cannot register MDIO bus (%d)\n", ret); goto out_mdio; @@ -421,12 +429,20 @@ static const struct of_device_id orion_mdio_match[] = { }; MODULE_DEVICE_TABLE(of, orion_mdio_match); +static const struct acpi_device_id orion_mdio_acpi_match[] = { + { "MRVL0100", BUS_TYPE_SMI }, + { "MRVL0101", BUS_TYPE_XSMI }, + { }, +}; +MODULE_DEVICE_TABLE(acpi, orion_mdio_acpi_match); + static struct platform_driver orion_mdio_driver = { .probe = orion_mdio_probe, .remove = orion_mdio_remove, .driver = { .name = "orion-mdio", .of_match_table = orion_mdio_match, + .acpi_match_table = ACPI_PTR(orion_mdio_acpi_match), }, }; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 7d5cd9bc6c99..361bc4fbe20b 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1805,18 +1805,14 @@ static void mvneta_rx_error(struct mvneta_port *pp, } /* Handle RX checksum offload based on the descriptor's status */ -static void mvneta_rx_csum(struct mvneta_port *pp, u32 status, - struct sk_buff *skb) +static int mvneta_rx_csum(struct mvneta_port *pp, u32 status) { if ((pp->dev->features & NETIF_F_RXCSUM) && (status & MVNETA_RXD_L3_IP4) && - (status & MVNETA_RXD_L4_CSUM_OK)) { - skb->csum = 0; - skb->ip_summed = CHECKSUM_UNNECESSARY; - return; - } + (status & MVNETA_RXD_L4_CSUM_OK)) + return CHECKSUM_UNNECESSARY; - skb->ip_summed = CHECKSUM_NONE; + return CHECKSUM_NONE; } /* Return tx queue pointer (find last set bit) according to returned @@ -2320,7 +2316,7 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp, } static struct sk_buff * -mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, +mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool, struct xdp_buff *xdp, u32 desc_status) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); @@ -2331,11 +2327,11 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, if (!skb) return ERR_PTR(-ENOMEM); - page_pool_release_page(rxq->page_pool, virt_to_page(xdp->data)); + skb_mark_for_recycle(skb, virt_to_page(xdp->data), pool); skb_reserve(skb, xdp->data - xdp->data_hard_start); skb_put(skb, xdp->data_end - xdp->data); - mvneta_rx_csum(pp, desc_status, skb); + skb->ip_summed = mvneta_rx_csum(pp, desc_status); for (i = 0; i < num_frags; i++) { skb_frag_t *frag = &sinfo->frags[i]; @@ -2343,7 +2339,10 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, skb_frag_page(frag), skb_frag_off(frag), skb_frag_size(frag), PAGE_SIZE); - page_pool_release_page(rxq->page_pool, skb_frag_page(frag)); + /* We don't need to reset pp_recycle here. It's already set, so + * just mark fragments for recycling. + */ + page_pool_store_mem_info(skb_frag_page(frag), pool); } return skb; @@ -2370,7 +2369,6 @@ static int mvneta_rx_swbm(struct napi_struct *napi, /* Get number of received packets */ rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq); - rcu_read_lock(); xdp_prog = READ_ONCE(pp->xdp_prog); /* Fairness NAPI loop */ @@ -2425,7 +2423,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, mvneta_run_xdp(pp, rxq, xdp_prog, &xdp_buf, frame_sz, &ps)) goto next; - skb = mvneta_swbm_build_skb(pp, rxq, &xdp_buf, desc_status); + skb = mvneta_swbm_build_skb(pp, rxq->page_pool, &xdp_buf, desc_status); if (IS_ERR(skb)) { struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats); @@ -2448,7 +2446,6 @@ next: xdp_buf.data_hard_start = NULL; sinfo.nr_frags = 0; } - rcu_read_unlock(); if (xdp_buf.data_hard_start) mvneta_xdp_put_buff(pp, rxq, &xdp_buf, &sinfo, -1); @@ -2532,7 +2529,7 @@ err_drop_frame: rx_bytes); skb->protocol = eth_type_trans(skb, dev); - mvneta_rx_csum(pp, rx_status, skb); + skb->ip_summed = mvneta_rx_csum(pp, rx_status); napi_gro_receive(napi, skb); rcvd_pkts++; @@ -2581,8 +2578,7 @@ err_drop_frame: skb_put(skb, rx_bytes); skb->protocol = eth_type_trans(skb, dev); - - mvneta_rx_csum(pp, rx_status, skb); + skb->ip_summed = mvneta_rx_csum(pp, rx_status); napi_gro_receive(napi, skb); } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 4a61c90003b5..b9fbc9f000f2 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -1197,9 +1197,6 @@ struct mvpp2_port { /* Firmware node associated to the port */ struct fwnode_handle *fwnode; - /* Is a PHY always connected to the port */ - bool has_phy; - /* Per-port registers' base address */ void __iomem *base; void __iomem *stats_base; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index d39c7639cdba..3229bafa2a2c 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3543,21 +3543,17 @@ static void mvpp2_rx_error(struct mvpp2_port *port, } /* Handle RX checksum offload */ -static void mvpp2_rx_csum(struct mvpp2_port *port, u32 status, - struct sk_buff *skb) +static int mvpp2_rx_csum(struct mvpp2_port *port, u32 status) { if (((status & MVPP2_RXD_L3_IP4) && !(status & MVPP2_RXD_IP4_HEADER_ERR)) || (status & MVPP2_RXD_L3_IP6)) if (((status & MVPP2_RXD_L4_UDP) || (status & MVPP2_RXD_L4_TCP)) && - (status & MVPP2_RXD_L4_CSUM_OK)) { - skb->csum = 0; - skb->ip_summed = CHECKSUM_UNNECESSARY; - return; - } + (status & MVPP2_RXD_L4_CSUM_OK)) + return CHECKSUM_UNNECESSARY; - skb->ip_summed = CHECKSUM_NONE; + return CHECKSUM_NONE; } /* Allocate a new skb and add it to BM pool */ @@ -3784,9 +3780,9 @@ mvpp2_xdp_xmit(struct net_device *dev, int num_frame, } static int -mvpp2_run_xdp(struct mvpp2_port *port, struct mvpp2_rx_queue *rxq, - struct bpf_prog *prog, struct xdp_buff *xdp, - struct page_pool *pp, struct mvpp2_pcpu_stats *stats) +mvpp2_run_xdp(struct mvpp2_port *port, struct bpf_prog *prog, + struct xdp_buff *xdp, struct page_pool *pp, + struct mvpp2_pcpu_stats *stats) { unsigned int len, sync, err; struct page *page; @@ -3881,8 +3877,6 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, int rx_done = 0; u32 xdp_ret = 0; - rcu_read_lock(); - xdp_prog = READ_ONCE(port->xdp_prog); /* Get number of received packets and clamp the to-do */ @@ -3900,15 +3894,19 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, phys_addr_t phys_addr; u32 rx_status, timestamp; int pool, rx_bytes, err, ret; + struct page *page; void *data; + phys_addr = mvpp2_rxdesc_cookie_get(port, rx_desc); + data = (void *)phys_to_virt(phys_addr); + page = virt_to_page(data); + prefetch(page); + rx_done++; rx_status = mvpp2_rxdesc_status_get(port, rx_desc); rx_bytes = mvpp2_rxdesc_size_get(port, rx_desc); rx_bytes -= MVPP2_MH_SIZE; dma_addr = mvpp2_rxdesc_dma_addr_get(port, rx_desc); - phys_addr = mvpp2_rxdesc_cookie_get(port, rx_desc); - data = (void *)phys_to_virt(phys_addr); pool = (rx_status & MVPP2_RXD_BM_POOL_ID_MASK) >> MVPP2_RXD_BM_POOL_ID_OFFS; @@ -3938,7 +3936,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, goto err_drop_frame; /* Prefetch header */ - prefetch(data); + prefetch(data + MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM); if (bm_pool->frag_size > PAGE_SIZE) frag_size = 0; @@ -3958,7 +3956,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM, rx_bytes, false); - ret = mvpp2_run_xdp(port, rxq, xdp_prog, &xdp, pp, &ps); + ret = mvpp2_run_xdp(port, xdp_prog, &xdp, pp, &ps); if (ret) { xdp_ret |= ret; @@ -3997,7 +3995,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, } if (pp) - page_pool_release_page(pp, virt_to_page(data)); + skb_mark_for_recycle(skb, page, pp); else dma_unmap_single_attrs(dev->dev.parent, dma_addr, bm_pool->buf_size, DMA_FROM_DEVICE, @@ -4008,8 +4006,8 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, skb_reserve(skb, MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM); skb_put(skb, rx_bytes); + skb->ip_summed = mvpp2_rx_csum(port, rx_status); skb->protocol = eth_type_trans(skb, dev); - mvpp2_rx_csum(port, rx_status, skb); napi_gro_receive(napi, skb); continue; @@ -4024,8 +4022,6 @@ err_drop_frame: mvpp2_bm_pool_put(port, pool, dma_addr, phys_addr); } - rcu_read_unlock(); - if (xdp_ret & MVPP2_XDP_REDIR) xdp_do_flush_map(); @@ -4789,9 +4785,8 @@ static int mvpp2_open(struct net_device *dev) goto err_cleanup_txqs; } - /* Phylink isn't supported yet in ACPI mode */ - if (port->of_node) { - err = phylink_of_phy_connect(port->phylink, port->of_node, 0); + if (port->phylink) { + err = phylink_fwnode_phy_connect(port->phylink, port->fwnode, 0); if (err) { netdev_err(port->dev, "could not attach PHY (%d)\n", err); @@ -6699,6 +6694,19 @@ static void mvpp2_acpi_start(struct mvpp2_port *port) SPEED_UNKNOWN, DUPLEX_UNKNOWN, false, false); } +/* In order to ensure backward compatibility for ACPI, check if the port + * firmware node comprises the necessary description allowing to use phylink. + */ +static bool mvpp2_use_acpi_compat_mode(struct fwnode_handle *port_fwnode) +{ + if (!is_acpi_node(port_fwnode)) + return false; + + return (!fwnode_property_present(port_fwnode, "phy-handle") && + !fwnode_property_present(port_fwnode, "managed") && + !fwnode_get_named_child_node(port_fwnode, "fixed-link")); +} + /* Ports initialization */ static int mvpp2_port_probe(struct platform_device *pdev, struct fwnode_handle *port_fwnode, @@ -6774,7 +6782,6 @@ static int mvpp2_port_probe(struct platform_device *pdev, port = netdev_priv(dev); port->dev = dev; port->fwnode = port_fwnode; - port->has_phy = !!of_find_property(port_node, "phy", NULL); port->ntxqs = ntxqs; port->nrxqs = nrxqs; port->priv = priv; @@ -6917,8 +6924,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev->max_mtu = MVPP2_BM_JUMBO_PKT_SIZE; dev->dev.of_node = port_node; - /* Phylink isn't used w/ ACPI as of now */ - if (port_node) { + if (!mvpp2_use_acpi_compat_mode(port_fwnode)) { port->phylink_config.dev = &dev->dev; port->phylink_config.type = PHYLINK_NETDEV; @@ -6930,6 +6936,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, } port->phylink = phylink; } else { + dev_warn(&pdev->dev, "Use link irqs for port#%d. FW update required\n", port->id); port->phylink = NULL; } @@ -7347,7 +7354,6 @@ static int mvpp2_get_sram(struct platform_device *pdev, static int mvpp2_probe(struct platform_device *pdev) { - const struct acpi_device_id *acpi_id; struct fwnode_handle *fwnode = pdev->dev.fwnode; struct fwnode_handle *port_fwnode; struct mvpp2 *priv; @@ -7360,16 +7366,7 @@ static int mvpp2_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - if (has_acpi_companion(&pdev->dev)) { - acpi_id = acpi_match_device(pdev->dev.driver->acpi_match_table, - &pdev->dev); - if (!acpi_id) - return -EINVAL; - priv->hw_version = (unsigned long)acpi_id->driver_data; - } else { - priv->hw_version = - (unsigned long)of_device_get_match_data(&pdev->dev); - } + priv->hw_version = (unsigned long)device_get_match_data(&pdev->dev); /* multi queue mode isn't supported on PPV2.1, fallback to single * mode @@ -7387,6 +7384,10 @@ static int mvpp2_probe(struct platform_device *pdev) return PTR_ERR(priv->lms_base); } else { res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!res) { + dev_err(&pdev->dev, "Invalid resource\n"); + return -EINVAL; + } if (has_acpi_companion(&pdev->dev)) { /* In case the MDIO memory region is declared in * the ACPI, it can already appear as 'in-use' @@ -7481,34 +7482,35 @@ static int mvpp2_probe(struct platform_device *pdev) if (err < 0) goto err_gop_clk; - priv->mg_core_clk = devm_clk_get(&pdev->dev, "mg_core_clk"); + priv->mg_core_clk = devm_clk_get_optional(&pdev->dev, "mg_core_clk"); if (IS_ERR(priv->mg_core_clk)) { - priv->mg_core_clk = NULL; - } else { - err = clk_prepare_enable(priv->mg_core_clk); - if (err < 0) - goto err_mg_clk; + err = PTR_ERR(priv->mg_core_clk); + goto err_mg_clk; } + + err = clk_prepare_enable(priv->mg_core_clk); + if (err < 0) + goto err_mg_clk; } - priv->axi_clk = devm_clk_get(&pdev->dev, "axi_clk"); + priv->axi_clk = devm_clk_get_optional(&pdev->dev, "axi_clk"); if (IS_ERR(priv->axi_clk)) { err = PTR_ERR(priv->axi_clk); - if (err == -EPROBE_DEFER) - goto err_mg_core_clk; - priv->axi_clk = NULL; - } else { - err = clk_prepare_enable(priv->axi_clk); - if (err < 0) - goto err_mg_core_clk; + goto err_mg_core_clk; } + err = clk_prepare_enable(priv->axi_clk); + if (err < 0) + goto err_mg_core_clk; + /* Get system's tclk rate */ priv->tclk = clk_get_rate(priv->pp_clk); - } else if (device_property_read_u32(&pdev->dev, "clock-frequency", - &priv->tclk)) { - dev_err(&pdev->dev, "missing clock-frequency value\n"); - return -EINVAL; + } else { + err = device_property_read_u32(&pdev->dev, "clock-frequency", &priv->tclk); + if (err) { + dev_err(&pdev->dev, "missing clock-frequency value\n"); + return err; + } } if (priv->hw_version >= MVPP22) { @@ -7588,6 +7590,8 @@ static int mvpp2_probe(struct platform_device *pdev) return 0; err_port_probe: + fwnode_handle_put(port_fwnode); + i = 0; fwnode_for_each_available_child_node(fwnode, port_fwnode) { if (priv->port_list[i]) @@ -7596,13 +7600,10 @@ err_port_probe: } err_axi_clk: clk_disable_unprepare(priv->axi_clk); - err_mg_core_clk: - if (priv->hw_version >= MVPP22) - clk_disable_unprepare(priv->mg_core_clk); + clk_disable_unprepare(priv->mg_core_clk); err_mg_clk: - if (priv->hw_version >= MVPP22) - clk_disable_unprepare(priv->mg_clk); + clk_disable_unprepare(priv->mg_clk); err_gop_clk: clk_disable_unprepare(priv->gop_clk); err_pp_clk: diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c index 7cc7d72d761e..93575800ca92 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c @@ -394,9 +394,6 @@ static int mvpp2_prs_tcam_first_free(struct mvpp2 *priv, unsigned char start, if (start > end) swap(start, end); - if (end >= MVPP2_PRS_TCAM_SRAM_SIZE) - end = MVPP2_PRS_TCAM_SRAM_SIZE - 1; - for (tid = start; tid <= end; tid++) { if (!priv->prs_shadow[tid].valid) return tid; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h index e66109367487..47f5ed006a93 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h @@ -197,6 +197,11 @@ enum nix_scheduler { #define SDP_CHANNELS 256 +/* The mask is to extract lower 10-bits of channel number + * which CPT will pass to X2P. + */ +#define NIX_CHAN_CPT_X2P_MASK (0x3ffull) + /* NIX LSO format indices. * As of now TSO is the only one using, so statically assigning indices. */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index cedb2616c509..770d86262838 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -134,6 +134,7 @@ M(MSIX_OFFSET, 0x005, msix_offset, msg_req, msix_offset_rsp) \ M(VF_FLR, 0x006, vf_flr, msg_req, msg_rsp) \ M(PTP_OP, 0x007, ptp_op, ptp_req, ptp_rsp) \ M(GET_HW_CAP, 0x008, get_hw_cap, msg_req, get_hw_cap_rsp) \ +M(SET_VF_PERM, 0x00b, set_vf_perm, set_vf_perm, msg_rsp) \ /* CGX mbox IDs (range 0x200 - 0x3FF) */ \ M(CGX_START_RXTX, 0x200, cgx_start_rxtx, msg_req, msg_rsp) \ M(CGX_STOP_RXTX, 0x201, cgx_stop_rxtx, msg_req, msg_rsp) \ @@ -259,7 +260,11 @@ M(NIX_BP_DISABLE, 0x8017, nix_bp_disable, nix_bp_cfg_req, msg_rsp) \ M(NIX_GET_MAC_ADDR, 0x8018, nix_get_mac_addr, msg_req, nix_get_mac_addr_rsp) \ M(NIX_CN10K_AQ_ENQ, 0x8019, nix_cn10k_aq_enq, nix_cn10k_aq_enq_req, \ nix_cn10k_aq_enq_rsp) \ -M(NIX_GET_HW_INFO, 0x801a, nix_get_hw_info, msg_req, nix_hw_info) +M(NIX_GET_HW_INFO, 0x801c, nix_get_hw_info, msg_req, nix_hw_info) \ +M(NIX_BANDPROF_ALLOC, 0x801d, nix_bandprof_alloc, nix_bandprof_alloc_req, \ + nix_bandprof_alloc_rsp) \ +M(NIX_BANDPROF_FREE, 0x801e, nix_bandprof_free, nix_bandprof_free_req, \ + msg_rsp) /* Messages initiated by AF (range 0xC00 - 0xDFF) */ #define MBOX_UP_CGX_MESSAGES \ @@ -611,7 +616,12 @@ enum nix_af_status { NIX_AF_INVAL_SSO_PF_FUNC = -420, NIX_AF_ERR_TX_VTAG_NOSPC = -421, NIX_AF_ERR_RX_VTAG_INUSE = -422, - NIX_AF_ERR_NPC_KEY_NOT_SUPP = -423, + NIX_AF_ERR_PTP_CONFIG_FAIL = -423, + NIX_AF_ERR_NPC_KEY_NOT_SUPP = -424, + NIX_AF_ERR_INVALID_NIXBLK = -425, + NIX_AF_ERR_INVALID_BANDPROF = -426, + NIX_AF_ERR_IPOLICER_NOTSUPP = -427, + NIX_AF_ERR_BANDPROF_INVAL_REQ = -428, }; /* For NIX RX vtag action */ @@ -680,6 +690,7 @@ struct nix_cn10k_aq_enq_req { struct nix_cq_ctx_s cq; struct nix_rsse_s rss; struct nix_rx_mce_s mce; + struct nix_bandprof_s prof; }; union { struct nix_cn10k_rq_ctx_s rq_mask; @@ -687,6 +698,7 @@ struct nix_cn10k_aq_enq_req { struct nix_cq_ctx_s cq_mask; struct nix_rsse_s rss_mask; struct nix_rx_mce_s mce_mask; + struct nix_bandprof_s prof_mask; }; }; @@ -698,6 +710,7 @@ struct nix_cn10k_aq_enq_rsp { struct nix_cq_ctx_s cq; struct nix_rsse_s rss; struct nix_rx_mce_s mce; + struct nix_bandprof_s prof; }; }; @@ -713,6 +726,7 @@ struct nix_aq_enq_req { struct nix_cq_ctx_s cq; struct nix_rsse_s rss; struct nix_rx_mce_s mce; + u64 prof; }; union { struct nix_rq_ctx_s rq_mask; @@ -720,6 +734,7 @@ struct nix_aq_enq_req { struct nix_cq_ctx_s cq_mask; struct nix_rsse_s rss_mask; struct nix_rx_mce_s mce_mask; + u64 prof_mask; }; }; @@ -731,6 +746,7 @@ struct nix_aq_enq_rsp { struct nix_cq_ctx_s cq; struct nix_rsse_s rss; struct nix_rx_mce_s mce; + struct nix_bandprof_s prof; }; }; @@ -913,6 +929,7 @@ struct nix_rx_mode { #define NIX_RX_MODE_UCAST BIT(0) #define NIX_RX_MODE_PROMISC BIT(1) #define NIX_RX_MODE_ALLMULTI BIT(2) +#define NIX_RX_MODE_USE_MCE BIT(3) u16 mode; }; @@ -971,6 +988,31 @@ struct nix_hw_info { u16 min_mtu; }; +struct nix_bandprof_alloc_req { + struct mbox_msghdr hdr; + /* Count of profiles needed per layer */ + u16 prof_count[BAND_PROF_NUM_LAYERS]; +}; + +struct nix_bandprof_alloc_rsp { + struct mbox_msghdr hdr; + u16 prof_count[BAND_PROF_NUM_LAYERS]; + + /* There is no need to allocate morethan 1 bandwidth profile + * per RQ of a PF_FUNC's NIXLF. So limit the maximum + * profiles to 64 per PF_FUNC. + */ +#define MAX_BANDPROF_PER_PFFUNC 64 + u16 prof_idx[BAND_PROF_NUM_LAYERS][MAX_BANDPROF_PER_PFFUNC]; +}; + +struct nix_bandprof_free_req { + struct mbox_msghdr hdr; + u8 free_all; + u16 prof_count[BAND_PROF_NUM_LAYERS]; + u16 prof_idx[BAND_PROF_NUM_LAYERS][MAX_BANDPROF_PER_PFFUNC]; +}; + /* NPC mbox message structs */ #define NPC_MCAM_ENTRY_INVALID 0xFFFF @@ -1228,6 +1270,14 @@ struct ptp_rsp { u64 clk; }; +struct set_vf_perm { + struct mbox_msghdr hdr; + u16 vf; +#define RESET_VF_PERM BIT_ULL(0) +#define VF_TRUSTED BIT_ULL(1) + u64 flags; +}; + /* CPT mailbox error codes * Range 901 - 1000. */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index 1e012e787260..19bad9a59c8f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -33,6 +33,10 @@ enum npc_kpu_la_ltype { NPC_LT_LA_IH_2_ETHER, NPC_LT_LA_HIGIG2_ETHER, NPC_LT_LA_IH_NIX_HIGIG2_ETHER, + NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_LT_LA_CH_LEN_90B_ETHER, + NPC_LT_LA_CPT_HDR, + NPC_LT_LA_CUSTOM_L2_24B_ETHER, NPC_LT_LA_CUSTOM0 = 0xE, NPC_LT_LA_CUSTOM1 = 0xF, }; @@ -42,7 +46,7 @@ enum npc_kpu_lb_ltype { NPC_LT_LB_CTAG, NPC_LT_LB_STAG_QINQ, NPC_LT_LB_BTAG, - NPC_LT_LB_ITAG, + NPC_LT_LB_PPPOE, NPC_LT_LB_DSA, NPC_LT_LB_DSA_VLAN, NPC_LT_LB_EDSA, @@ -50,6 +54,7 @@ enum npc_kpu_lb_ltype { NPC_LT_LB_EXDSA, NPC_LT_LB_EXDSA_VLAN, NPC_LT_LB_FDSA, + NPC_LT_LB_VLAN_EXDSA, NPC_LT_LB_CUSTOM0 = 0xE, NPC_LT_LB_CUSTOM1 = 0xF, }; @@ -65,6 +70,7 @@ enum npc_kpu_lc_ltype { NPC_LT_LC_NSH, NPC_LT_LC_PTP, NPC_LT_LC_FCOE, + NPC_LT_LC_NGIO, NPC_LT_LC_CUSTOM0 = 0xE, NPC_LT_LC_CUSTOM1 = 0xF, }; @@ -146,7 +152,14 @@ enum npc_kpu_lh_ltype { * Ethernet interfaces, LBK interfaces, etc. */ enum npc_pkind_type { - NPC_TX_DEF_PKIND = 63ULL, /* NIX-TX PKIND */ + NPC_RX_VLAN_EXDSA_PKIND = 56ULL, + NPC_RX_CHLEN24B_PKIND = 57ULL, + NPC_RX_CPT_HDR_PKIND, + NPC_RX_CHLEN90B_PKIND, + NPC_TX_HIGIG_PKIND, + NPC_RX_HIGIG_PKIND, + NPC_RX_EDSA_PKIND, + NPC_TX_DEF_PKIND, /* NIX-TX PKIND */ }; /* list of known and supported fields in packet header and @@ -213,7 +226,7 @@ struct npc_kpu_profile_cam { u16 dp1_mask; u16 dp2; u16 dp2_mask; -}; +} __packed; struct npc_kpu_profile_action { u8 errlev; @@ -233,13 +246,13 @@ struct npc_kpu_profile_action { u8 mask; u8 right; u8 shift; -}; +} __packed; struct npc_kpu_profile { int cam_entries; int action_entries; - const struct npc_kpu_profile_cam *cam; - const struct npc_kpu_profile_action *action; + struct npc_kpu_profile_cam *cam; + struct npc_kpu_profile_action *action; }; /* NPC KPU register formats */ @@ -425,7 +438,19 @@ struct nix_tx_action { /* NPC MCAM reserved entry index per nixlf */ #define NIXLF_UCAST_ENTRY 0 #define NIXLF_BCAST_ENTRY 1 -#define NIXLF_PROMISC_ENTRY 2 +#define NIXLF_ALLMULTI_ENTRY 2 +#define NIXLF_PROMISC_ENTRY 3 + +struct npc_coalesced_kpu_prfl { +#define NPC_SIGN 0x00666f727063706e +#define NPC_PRFL_NAME "npc_prfls_array" +#define NPC_NAME_LEN 32 + __le64 signature; /* "npcprof\0" (8 bytes/ASCII characters) */ + u8 name[NPC_NAME_LEN]; /* KPU Profile name */ + u64 version; /* KPU firmware/profile version */ + u8 num_prfl; /* No of NPC profiles. */ + u16 prfl_sz[0]; +}; struct npc_mcam_kex { /* MKEX Profle Header */ @@ -445,6 +470,15 @@ struct npc_mcam_kex { u64 intf_ld_flags[NPC_MAX_INTF][NPC_MAX_LD][NPC_MAX_LFL]; } __packed; +struct npc_kpu_fwdata { + int entries; + /* What follows is: + * struct npc_kpu_profile_cam[entries]; + * struct npc_kpu_profile_action[entries]; + */ + u8 data[0]; +} __packed; + struct npc_lt_def { u8 ltype_mask; u8 ltype_match; @@ -459,6 +493,29 @@ struct npc_lt_def_ipsec { u8 spi_nz; }; +struct npc_lt_def_apad { + u8 ltype_mask; + u8 ltype_match; + u8 lid; + u8 valid; +} __packed; + +struct npc_lt_def_color { + u8 ltype_mask; + u8 ltype_match; + u8 lid; + u8 noffset; + u8 offset; +} __packed; + +struct npc_lt_def_et { + u8 ltype_mask; + u8 ltype_match; + u8 lid; + u8 valid; + u8 offset; +} __packed; + struct npc_lt_def_cfg { struct npc_lt_def rx_ol2; struct npc_lt_def rx_oip4; @@ -476,7 +533,41 @@ struct npc_lt_def_cfg { struct npc_lt_def pck_oip4; struct npc_lt_def pck_oip6; struct npc_lt_def pck_iip4; -}; + struct npc_lt_def_apad rx_apad0; + struct npc_lt_def_apad rx_apad1; + struct npc_lt_def_color ovlan; + struct npc_lt_def_color ivlan; + struct npc_lt_def_color rx_gen0_color; + struct npc_lt_def_color rx_gen1_color; + struct npc_lt_def_et rx_et[2]; +} __packed; + +/* Loadable KPU profile firmware data */ +struct npc_kpu_profile_fwdata { +#define KPU_SIGN 0x00666f727075706b +#define KPU_NAME_LEN 32 +/** Maximum number of custom KPU entries supported by the built-in profile. */ +#define KPU_MAX_CST_ENT 2 + /* KPU Profle Header */ + __le64 signature; /* "kpuprof\0" (8 bytes/ASCII characters) */ + u8 name[KPU_NAME_LEN]; /* KPU Profile name */ + __le64 version; /* KPU profile version */ + u8 kpus; + u8 reserved[7]; + + /* Default MKEX profile to be used with this KPU profile. May be + * overridden with mkex_profile module parameter. Format is same as for + * the MKEX profile to streamline processing. + */ + struct npc_mcam_kex mkex; + /* LTYPE values for specific HW offloaded protocols. */ + struct npc_lt_def_cfg lt_def; + /* Dynamically sized data: + * Custom KPU CAM and ACTION configuration entries. + * struct npc_kpu_fwdata kpu[kpus]; + */ + u8 data[0]; +} __packed; struct rvu_npc_mcam_rule { struct flow_msg packet; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h index 5c372d2c24a1..fee655cc7523 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h @@ -11,7 +11,10 @@ #ifndef NPC_PROFILE_H #define NPC_PROFILE_H -#define NPC_KPU_PROFILE_VER 0x0000000100050000 +#define NPC_KPU_PROFILE_VER 0x0000000100060000 +#define NPC_KPU_VER_MAJ(ver) ((u16)(((ver) >> 32) & 0xFFFF)) +#define NPC_KPU_VER_MIN(ver) ((u16)(((ver) >> 16) & 0xFFFF)) +#define NPC_KPU_VER_PATCH(ver) ((u16)((ver) & 0xFFFF)) #define NPC_IH_W 0x8000 #define NPC_IH_UTAG 0x2000 @@ -20,6 +23,7 @@ #define NPC_ETYPE_IP6 0x86dd #define NPC_ETYPE_ARP 0x0806 #define NPC_ETYPE_RARP 0x8035 +#define NPC_ETYPE_NGIO 0x8842 #define NPC_ETYPE_MPLSU 0x8847 #define NPC_ETYPE_MPLSM 0x8848 #define NPC_ETYPE_ETAG 0x893f @@ -33,6 +37,10 @@ #define NPC_ETYPE_PPP 0x880b #define NPC_ETYPE_NSH 0x894f #define NPC_ETYPE_DSA 0xdada +#define NPC_ETYPE_PPPOE 0x8864 + +#define NPC_PPP_IP 0x0021 +#define NPC_PPP_IP6 0x0057 #define NPC_IPNH_HOP 0 #define NPC_IPNH_ICMP 1 @@ -142,14 +150,15 @@ #define NPC_DSA_EDSA 0x8000 #define NPC_DSA_FDSA 0xc000 -#define NPC_KEXOF_DMAC 8 -#define MKEX_SIGN 0x19bbfdbd15f /* strtoull of "mkexprof" with base:36 */ +#define NPC_KEXOF_DMAC 9 +#define MKEX_SIGN 0x19bbfdbd15f #define KEX_LD_CFG(bytesm1, hdr_ofs, ena, flags_ena, key_ofs) \ (((bytesm1) << 16) | ((hdr_ofs) << 8) | ((ena) << 7) | \ ((flags_ena) << 6) | ((key_ofs) & 0x3F)) /* Rx parse key extract nibble enable */ #define NPC_PARSE_NIBBLE_INTF_RX (NPC_PARSE_NIBBLE_CHAN | \ + NPC_PARSE_NIBBLE_ERRCODE | \ NPC_PARSE_NIBBLE_LA_LTYPE | \ NPC_PARSE_NIBBLE_LB_LTYPE | \ NPC_PARSE_NIBBLE_LC_LTYPE | \ @@ -170,25 +179,31 @@ enum npc_kpu_parser_state { NPC_S_KPU1_EXDSA, NPC_S_KPU1_HIGIG2, NPC_S_KPU1_IH_NIX_HIGIG2, + NPC_S_KPU1_CUSTOM_L2_90B, + NPC_S_KPU1_CPT_HDR, + NPC_S_KPU1_CUSTOM_L2_24B, + NPC_S_KPU1_VLAN_EXDSA, NPC_S_KPU2_CTAG, NPC_S_KPU2_CTAG2, NPC_S_KPU2_SBTAG, NPC_S_KPU2_QINQ, NPC_S_KPU2_ETAG, - NPC_S_KPU2_ITAG, NPC_S_KPU2_PREHEADER, NPC_S_KPU2_EXDSA, + NPC_S_KPU2_NGIO, NPC_S_KPU3_CTAG, NPC_S_KPU3_STAG, NPC_S_KPU3_QINQ, - NPC_S_KPU3_ITAG, NPC_S_KPU3_CTAG_C, NPC_S_KPU3_STAG_C, NPC_S_KPU3_QINQ_C, NPC_S_KPU3_DSA, + NPC_S_KPU3_VLAN_EXDSA, NPC_S_KPU4_MPLS, NPC_S_KPU4_NSH, NPC_S_KPU4_FDSA, + NPC_S_KPU4_VLAN_EXDSA, + NPC_S_KPU4_PPPOE, NPC_S_KPU5_IP, NPC_S_KPU5_IP6, NPC_S_KPU5_ARP, @@ -198,13 +213,19 @@ enum npc_kpu_parser_state { NPC_S_KPU5_MPLS, NPC_S_KPU5_MPLS_PL, NPC_S_KPU5_NSH, + NPC_S_KPU5_CPT_IP, + NPC_S_KPU5_CPT_IP6, NPC_S_KPU6_IP6_EXT, NPC_S_KPU6_IP6_HOP_DEST, NPC_S_KPU6_IP6_ROUT, NPC_S_KPU6_IP6_FRAG, + NPC_S_KPU6_IP6_CPT_FRAG, + NPC_S_KPU6_IP6_CPT_HOP_DEST, + NPC_S_KPU6_IP6_CPT_ROUT, NPC_S_KPU7_IP6_EXT, NPC_S_KPU7_IP6_ROUT, NPC_S_KPU7_IP6_FRAG, + NPC_S_KPU7_CPT_IP6_FRAG, NPC_S_KPU8_TCP, NPC_S_KPU8_UDP, NPC_S_KPU8_SCTP, @@ -265,7 +286,6 @@ enum npc_kpu_la_lflag { NPC_F_LA_L_UNK_ETYPE = 1, NPC_F_LA_L_WITH_VLAN, NPC_F_LA_L_WITH_ETAG, - NPC_F_LA_L_WITH_ITAG, NPC_F_LA_L_WITH_MPLS, NPC_F_LA_L_WITH_NSH, }; @@ -442,7 +462,28 @@ enum NPC_ERRLEV_E { NPC_ERRLEV_ENUM_LAST = 16, }; -static const struct npc_kpu_profile_action ikpu_action_entries[] = { +#define NPC_KPU_NOP_CAM \ + { \ + NPC_S_NA, 0xff, \ + 0x0000, \ + 0x0000, \ + 0x0000, \ + 0x0000, \ + 0x0000, \ + 0x0000, \ + } + +#define NPC_KPU_NOP_ACTION \ + { \ + NPC_ERRLEV_RE, NPC_EC_NOERR, \ + 0, 0, 0, 0, 0, \ + NPC_S_NA, 0, 0, \ + NPC_LID_LA, NPC_LT_NA, \ + 0, \ + 0, 0, 0, 0, \ + } + +static struct npc_kpu_profile_action ikpu_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 12, 16, 20, 0, 0, @@ -950,7 +991,7 @@ static const struct npc_kpu_profile_action ikpu_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 12, 16, 20, 0, 0, - NPC_S_KPU1_ETHER, 0, 0, + NPC_S_KPU1_VLAN_EXDSA, 0, 0, NPC_LID_LA, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -958,8 +999,8 @@ static const struct npc_kpu_profile_action ikpu_action_entries[] = { }, { NPC_ERRLEV_RE, NPC_EC_NOERR, - 12, 16, 20, 0, 0, - NPC_S_KPU1_ETHER, 0, 0, + 36, 40, 44, 0, 0, + NPC_S_KPU1_CUSTOM_L2_24B, 0, 0, NPC_LID_LA, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -967,8 +1008,8 @@ static const struct npc_kpu_profile_action ikpu_action_entries[] = { }, { NPC_ERRLEV_RE, NPC_EC_NOERR, - 12, 16, 20, 0, 0, - NPC_S_KPU1_ETHER, 0, 0, + 40, 54, 58, 0, 0, + NPC_S_KPU1_CPT_HDR, 0, 0, NPC_LID_LA, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -976,8 +1017,8 @@ static const struct npc_kpu_profile_action ikpu_action_entries[] = { }, { NPC_ERRLEV_RE, NPC_EC_NOERR, - 12, 16, 20, 0, 0, - NPC_S_KPU1_ETHER, 0, 0, + 102, 106, 110, 0, 0, + NPC_S_KPU1_CUSTOM_L2_90B, 0, 0, NPC_LID_LA, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -1021,7 +1062,9 @@ static const struct npc_kpu_profile_action ikpu_action_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu1_cam_entries[] = { +static struct npc_kpu_profile_cam kpu1_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU1_ETHER, 0xff, NPC_ETYPE_IP, @@ -1076,6 +1119,15 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, 0x0000, }, + { + NPC_S_KPU1_ETHER, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_NGIO, + 0xffff, + 0x0000, + 0x0000, + }, { NPC_S_KPU1_ETHER, 0xff, NPC_ETYPE_CTAG, @@ -1121,15 +1173,6 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, 0x0000, }, - { - NPC_S_KPU1_ETHER, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, { NPC_S_KPU1_ETHER, 0xff, NPC_ETYPE_MPLSU, @@ -1166,6 +1209,15 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, 0x0000, }, + { + NPC_S_KPU1_ETHER, 0xff, + NPC_ETYPE_PPPOE, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, { NPC_S_KPU1_ETHER, 0xff, 0x0000, @@ -1292,15 +1344,6 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, 0x0000, }, - { - NPC_S_KPU1_IH_NIX, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, { NPC_S_KPU1_IH_NIX, 0xff, NPC_ETYPE_MPLSU, @@ -1339,8 +1382,8 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = { }, { NPC_S_KPU1_IH, 0xff, - NPC_IH_W|NPC_IH_UTAG, - NPC_IH_W|NPC_IH_UTAG, + NPC_IH_W | NPC_IH_UTAG, + NPC_IH_W | NPC_IH_UTAG, 0x0000, 0x0000, 0x0000, @@ -1349,7 +1392,7 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = { { NPC_S_KPU1_IH, 0xff, NPC_IH_W, - NPC_IH_W|NPC_IH_UTAG, + NPC_IH_W | NPC_IH_UTAG, 0x0000, 0x0000, 0x0000, @@ -1358,7 +1401,7 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = { { NPC_S_KPU1_IH, 0xff, 0x0000, - NPC_IH_W|NPC_IH_UTAG, + NPC_IH_W | NPC_IH_UTAG, 0x0000, 0x0000, 0x0000, @@ -1499,15 +1542,6 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, 0x0000, }, - { - NPC_S_KPU1_HIGIG2, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, { NPC_S_KPU1_HIGIG2, 0xff, NPC_ETYPE_MPLSU, @@ -1643,15 +1677,6 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, 0x0000, }, - { - NPC_S_KPU1_IH_NIX_HIGIG2, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, { NPC_S_KPU1_IH_NIX_HIGIG2, 0xff, NPC_ETYPE_MPLSU, @@ -1688,6 +1713,1361 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, 0x0000, }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_IP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_IP6, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_ARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_RARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_PTP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_FCOE, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_SBTAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_QINQ, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_ETAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_MPLSU, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_MPLSM, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_ETYPE_NSH, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CPT_HDR, 0xff, + 0x0000, + 0xffff, + NPC_ETYPE_IP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CPT_HDR, 0xff, + 0x0000, + 0xffff, + NPC_ETYPE_IP6, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CPT_HDR, 0xff, + 0x0000, + 0xffff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CPT_HDR, 0xff, + 0x0000, + 0xffff, + NPC_ETYPE_QINQ, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CPT_HDR, 0xff, + 0x0000, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_IP, + 0xffff, + }, + { + NPC_S_KPU1_CPT_HDR, 0xff, + 0x0000, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_IP6, + 0xffff, + }, + { + NPC_S_KPU1_CPT_HDR, 0xff, + 0x0000, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_CTAG, + 0xffff, + }, + { + NPC_S_KPU1_CPT_HDR, 0xff, + 0x0000, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_QINQ, + 0xffff, + }, + { + NPC_S_KPU1_CPT_HDR, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_IP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_IP6, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_ARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_RARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_PTP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_FCOE, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_SBTAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_QINQ, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_ETAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_MPLSU, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_MPLSM, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + NPC_ETYPE_NSH, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_CUSTOM_L2_24B, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU1_VLAN_EXDSA, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_NA, 0X00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, +}; + +static struct npc_kpu_profile_cam kpu2_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, + { + NPC_S_KPU2_CTAG, 0xff, + NPC_ETYPE_IP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG, 0xff, + NPC_ETYPE_IP6, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG, 0xff, + NPC_ETYPE_ARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG, 0xff, + NPC_ETYPE_RARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG, 0xff, + NPC_ETYPE_PTP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG, 0xff, + NPC_ETYPE_FCOE, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG, 0xff, + NPC_ETYPE_MPLSU, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG, 0xff, + NPC_ETYPE_MPLSM, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG, 0xff, + NPC_ETYPE_NSH, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG, 0xff, + NPC_ETYPE_PPPOE, + 0xffff, + 0x0000, + 0x0000, + NPC_PPP_IP, + 0xffff, + }, + { + NPC_S_KPU2_CTAG, 0xff, + NPC_ETYPE_PPPOE, + 0xffff, + 0x0000, + 0x0000, + NPC_PPP_IP6, + 0xffff, + }, + { + NPC_S_KPU2_CTAG, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_IP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_IP6, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_ARP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_RARP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_PTP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_FCOE, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_MPLSU, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_MPLSM, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_NSH, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_SBTAG, + 0xffff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_SBTAG, + 0xffff, + NPC_ETYPE_SBTAG, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_IP, + 0xffff, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_IP6, + 0xffff, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_ARP, + 0xffff, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_RARP, + 0xffff, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_PTP, + 0xffff, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_FCOE, + 0xffff, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_MPLSU, + 0xffff, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_MPLSM, + 0xffff, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_NSH, + 0xffff, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_SBTAG, + 0xffff, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_CTAG, + 0xffff, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_SBTAG, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_IP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_IP6, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_ARP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_RARP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_PTP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_FCOE, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_MPLSU, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_MPLSM, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_NSH, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + NPC_ETYPE_QINQ, + 0xffff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + NPC_ETYPE_QINQ, + 0xffff, + NPC_ETYPE_QINQ, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_QINQ, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_IP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_IP6, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_ARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_RARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_PTP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_FCOE, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_MPLSU, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_MPLSM, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_NSH, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_SBTAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_QINQ, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_IP, + 0xffff, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_IP6, + 0xffff, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_ARP, + 0xffff, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_SBTAG, + 0xffff, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + NPC_ETYPE_CTAG, + 0xffff, + }, + { + NPC_S_KPU2_ETAG, 0xff, + NPC_ETYPE_ITAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_ETAG, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG2, 0xff, + NPC_ETYPE_IP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG2, 0xff, + NPC_ETYPE_IP6, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG2, 0xff, + NPC_ETYPE_ARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG2, 0xff, + NPC_ETYPE_RARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG2, 0xff, + NPC_ETYPE_PTP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG2, 0xff, + NPC_ETYPE_FCOE, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG2, 0xff, + NPC_ETYPE_MPLSU, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG2, 0xff, + NPC_ETYPE_MPLSM, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG2, 0xff, + NPC_ETYPE_NSH, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG2, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_CTAG2, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_PREHEADER, 0xff, + NPC_ETYPE_IP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_PREHEADER, 0xff, + NPC_ETYPE_IP6, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_PREHEADER, 0xff, + NPC_ETYPE_ARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_PREHEADER, 0xff, + NPC_ETYPE_RARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_PREHEADER, 0xff, + NPC_ETYPE_PTP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_PREHEADER, 0xff, + NPC_ETYPE_FCOE, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_PREHEADER, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_PREHEADER, 0xff, + NPC_ETYPE_SBTAG, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_PREHEADER, 0xff, + NPC_ETYPE_QINQ, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_PREHEADER, 0xff, + NPC_ETYPE_MPLSU, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_PREHEADER, 0xff, + NPC_ETYPE_MPLSM, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_PREHEADER, 0xff, + NPC_ETYPE_NSH, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + NPC_DSA_EDSA, + NPC_DSA_EDSA, + 0x0000, + 0x0000, + NPC_ETYPE_IP, + 0xffff, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + NPC_DSA_EDSA, + NPC_DSA_EDSA, + 0x0000, + 0x0000, + NPC_ETYPE_IP6, + 0xffff, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + NPC_DSA_EDSA, + NPC_DSA_EDSA, + 0x0000, + 0x0000, + NPC_ETYPE_ARP, + 0xffff, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + NPC_DSA_EDSA, + NPC_DSA_EDSA, + 0x0000, + 0x0000, + NPC_ETYPE_RARP, + 0xffff, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + NPC_DSA_EDSA, + NPC_DSA_EDSA, + 0x0000, + 0x0000, + NPC_ETYPE_PTP, + 0xffff, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + NPC_DSA_EDSA, + NPC_DSA_EDSA, + 0x0000, + 0x0000, + NPC_ETYPE_FCOE, + 0xffff, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + NPC_DSA_EDSA, + NPC_DSA_EDSA, + 0x0000, + 0x0000, + NPC_ETYPE_CTAG, + 0xffff, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + NPC_DSA_EDSA, + NPC_DSA_EDSA, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + 0x0000, + NPC_DSA_EDSA, + NPC_ETYPE_IP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + 0x0000, + NPC_DSA_EDSA, + NPC_ETYPE_IP6, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + 0x0000, + NPC_DSA_EDSA, + NPC_ETYPE_ARP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + 0x0000, + NPC_DSA_EDSA, + NPC_ETYPE_RARP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + 0x0000, + NPC_DSA_EDSA, + NPC_ETYPE_PTP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + 0x0000, + NPC_DSA_EDSA, + NPC_ETYPE_FCOE, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + 0x0000, + NPC_DSA_EDSA, + NPC_ETYPE_CTAG, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_EXDSA, 0xff, + 0x0000, + NPC_DSA_EDSA, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU2_NGIO, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, { NPC_S_NA, 0X00, 0x0000, @@ -1699,1135 +3079,9 @@ static const struct npc_kpu_profile_cam kpu1_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu2_cam_entries[] = { - { - NPC_S_KPU2_CTAG, 0xff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG, 0xff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG, 0xff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG, 0xff, - NPC_ETYPE_RARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG, 0xff, - NPC_ETYPE_PTP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG, 0xff, - NPC_ETYPE_FCOE, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG, 0xff, - NPC_ETYPE_MPLSU, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG, 0xff, - NPC_ETYPE_MPLSM, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG, 0xff, - NPC_ETYPE_NSH, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG, 0xff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_RARP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_PTP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_FCOE, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_MPLSU, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_MPLSM, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_NSH, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_SBTAG, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_IP, - 0xffff, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_IP6, - 0xffff, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_ARP, - 0xffff, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_RARP, - 0xffff, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_PTP, - 0xffff, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_FCOE, - 0xffff, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_MPLSU, - 0xffff, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_MPLSM, - 0xffff, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_NSH, - 0xffff, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_SBTAG, - 0xffff, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_CTAG, - 0xffff, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_SBTAG, 0xff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_RARP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_PTP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_FCOE, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_MPLSU, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_MPLSM, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_NSH, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - NPC_ETYPE_QINQ, - 0xffff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - NPC_ETYPE_QINQ, - 0xffff, - NPC_ETYPE_QINQ, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_QINQ, 0xff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_RARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_PTP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_FCOE, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_MPLSU, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_MPLSM, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_NSH, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_QINQ, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_IP, - 0xffff, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_IP6, - 0xffff, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_ARP, - 0xffff, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_SBTAG, - 0xffff, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - NPC_ETYPE_CTAG, - 0xffff, - }, - { - NPC_S_KPU2_ETAG, 0xff, - NPC_ETYPE_ITAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ETAG, 0xff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_RARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_IP, - 0xffff, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_IP6, - 0xffff, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_ARP, - 0xffff, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_ITAG, 0xff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG2, 0xff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG2, 0xff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG2, 0xff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG2, 0xff, - NPC_ETYPE_RARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG2, 0xff, - NPC_ETYPE_PTP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG2, 0xff, - NPC_ETYPE_FCOE, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG2, 0xff, - NPC_ETYPE_MPLSU, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG2, 0xff, - NPC_ETYPE_MPLSM, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG2, 0xff, - NPC_ETYPE_NSH, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG2, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_CTAG2, 0xff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_PREHEADER, 0xff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_PREHEADER, 0xff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_PREHEADER, 0xff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_PREHEADER, 0xff, - NPC_ETYPE_RARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_PREHEADER, 0xff, - NPC_ETYPE_PTP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_PREHEADER, 0xff, - NPC_ETYPE_FCOE, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_PREHEADER, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_PREHEADER, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_PREHEADER, 0xff, - NPC_ETYPE_QINQ, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_PREHEADER, 0xff, - NPC_ETYPE_MPLSU, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_PREHEADER, 0xff, - NPC_ETYPE_MPLSM, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_PREHEADER, 0xff, - NPC_ETYPE_NSH, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - NPC_DSA_EDSA, - NPC_DSA_EDSA, - 0x0000, - 0x0000, - NPC_ETYPE_IP, - 0xffff, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - NPC_DSA_EDSA, - NPC_DSA_EDSA, - 0x0000, - 0x0000, - NPC_ETYPE_IP6, - 0xffff, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - NPC_DSA_EDSA, - NPC_DSA_EDSA, - 0x0000, - 0x0000, - NPC_ETYPE_ARP, - 0xffff, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - NPC_DSA_EDSA, - NPC_DSA_EDSA, - 0x0000, - 0x0000, - NPC_ETYPE_RARP, - 0xffff, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - NPC_DSA_EDSA, - NPC_DSA_EDSA, - 0x0000, - 0x0000, - NPC_ETYPE_PTP, - 0xffff, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - NPC_DSA_EDSA, - NPC_DSA_EDSA, - 0x0000, - 0x0000, - NPC_ETYPE_FCOE, - 0xffff, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - NPC_DSA_EDSA, - NPC_DSA_EDSA, - 0x0000, - 0x0000, - NPC_ETYPE_CTAG, - 0xffff, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - NPC_DSA_EDSA, - NPC_DSA_EDSA, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - 0x0000, - NPC_DSA_EDSA, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - 0x0000, - NPC_DSA_EDSA, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - 0x0000, - NPC_DSA_EDSA, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - 0x0000, - NPC_DSA_EDSA, - NPC_ETYPE_RARP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - 0x0000, - NPC_DSA_EDSA, - NPC_ETYPE_PTP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - 0x0000, - NPC_DSA_EDSA, - NPC_ETYPE_FCOE, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - 0x0000, - NPC_DSA_EDSA, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU2_EXDSA, 0xff, - 0x0000, - NPC_DSA_EDSA, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_NA, 0X00, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, -}; - -static const struct npc_kpu_profile_cam kpu3_cam_entries[] = { +static struct npc_kpu_profile_cam kpu3_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU3_CTAG, 0xff, NPC_ETYPE_IP, @@ -3242,159 +3496,6 @@ static const struct npc_kpu_profile_cam kpu3_cam_entries[] = { 0x0000, 0x0000, }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_RARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_IP, - 0xffff, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_IP6, - 0xffff, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_ARP, - 0xffff, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU3_ITAG, 0xff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, { NPC_S_KPU3_CTAG_C, 0xff, NPC_ETYPE_IP, @@ -3935,6 +4036,15 @@ static const struct npc_kpu_profile_cam kpu3_cam_entries[] = { 0x0000, 0x0000, }, + { + NPC_S_KPU3_VLAN_EXDSA, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, { NPC_S_NA, 0X00, 0x0000, @@ -3946,7 +4056,9 @@ static const struct npc_kpu_profile_cam kpu3_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu4_cam_entries[] = { +static struct npc_kpu_profile_cam kpu4_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU4_MPLS, 0xff, NPC_MPLS_S, @@ -4082,6 +4194,78 @@ static const struct npc_kpu_profile_cam kpu4_cam_entries[] = { 0x0000, 0x0000, }, + { + NPC_S_KPU4_FDSA, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_IP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_FDSA, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_IP6, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_FDSA, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_ARP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_FDSA, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_RARP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_FDSA, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_PTP, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_FDSA, 0xff, + NPC_ETYPE_CTAG, + 0xffff, + NPC_ETYPE_FCOE, + 0xffff, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_FDSA, 0xff, + NPC_ETYPE_PPPOE, + 0xffff, + 0x0000, + 0x0000, + NPC_PPP_IP, + 0xffff, + }, + { + NPC_S_KPU4_FDSA, 0xff, + NPC_ETYPE_PPPOE, + 0xffff, + 0x0000, + 0x0000, + NPC_PPP_IP6, + 0xffff, + }, { NPC_S_KPU4_FDSA, 0xff, 0x0000, @@ -4091,6 +4275,87 @@ static const struct npc_kpu_profile_cam kpu4_cam_entries[] = { 0x0000, 0x0000, }, + { + NPC_S_KPU4_VLAN_EXDSA, 0xff, + NPC_ETYPE_IP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_VLAN_EXDSA, 0xff, + NPC_ETYPE_IP6, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_VLAN_EXDSA, 0xff, + NPC_ETYPE_ARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_VLAN_EXDSA, 0xff, + NPC_ETYPE_RARP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_VLAN_EXDSA, 0xff, + NPC_ETYPE_PTP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_VLAN_EXDSA, 0xff, + NPC_ETYPE_FCOE, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_VLAN_EXDSA, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_PPPOE, 0xff, + NPC_PPP_IP, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU4_PPPOE, 0xff, + NPC_PPP_IP6, + 0xffff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, { NPC_S_NA, 0X00, 0x0000, @@ -4102,7 +4367,9 @@ static const struct npc_kpu_profile_cam kpu4_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { +static struct npc_kpu_profile_cam kpu5_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU5_IP, 0xff, 0x0000, @@ -4125,116 +4392,116 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_S_KPU5_IP, 0xff, NPC_IPNH_TCP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, NPC_IPNH_UDP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, NPC_IPNH_SCTP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, NPC_IPNH_ICMP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, NPC_IPNH_IGMP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, NPC_IPNH_ESP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, NPC_IPNH_AH, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, NPC_IPNH_GRE, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, NPC_IPNH_IP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, NPC_IPNH_IP6, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, NPC_IPNH_MPLS, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, 0x0000, 0x0000, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, 0x0000, 0x0000, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, 0x0000, }, @@ -4245,7 +4512,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_IP_VER_4, NPC_IP_VER_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, @@ -4254,7 +4521,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_IP_VER_4, NPC_IP_VER_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, @@ -4263,7 +4530,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_IP_VER_4, NPC_IP_VER_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, @@ -4272,7 +4539,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_IP_VER_4, NPC_IP_VER_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, @@ -4281,7 +4548,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_IP_VER_4, NPC_IP_VER_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, @@ -4290,7 +4557,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_IP_VER_4, NPC_IP_VER_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, @@ -4299,7 +4566,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_IP_VER_4, NPC_IP_VER_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, @@ -4308,7 +4575,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_IP_VER_4, NPC_IP_VER_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, @@ -4317,7 +4584,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_IP_VER_4, NPC_IP_VER_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, @@ -4326,7 +4593,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_IP_VER_4, NPC_IP_VER_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, @@ -4335,7 +4602,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_IP_VER_4, NPC_IP_VER_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, @@ -4344,7 +4611,7 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { NPC_IP_VER_4, NPC_IP_VER_MASK, 0x0000, - NPC_IP_HDR_MF|NPC_IP_HDR_FRAGOFF, + NPC_IP_HDR_MF | NPC_IP_HDR_FRAGOFF, }, { NPC_S_KPU5_IP, 0xff, @@ -4661,6 +4928,429 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { 0x0000, 0x0000, }, + { + NPC_S_KPU5_CPT_IP, 0xff, + 0x0000, + NPC_IP_TTL_MASK, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0001, + NPC_IP_HDR_FRAGOFF, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_TCP, + 0x00ff, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_UDP, + 0x00ff, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_SCTP, + 0x00ff, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_ICMP, + 0x00ff, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_IGMP, + 0x00ff, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_ESP, + 0x00ff, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_AH, + 0x00ff, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_GRE, + 0x00ff, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_IP, + 0x00ff, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_IP6, + 0x00ff, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_MPLS, + 0x00ff, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + 0x0000, + 0x0000, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_TCP, + 0x00ff, + NPC_IP_VER_4, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_UDP, + 0x00ff, + NPC_IP_VER_4, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_SCTP, + 0x00ff, + NPC_IP_VER_4, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_ICMP, + 0x00ff, + NPC_IP_VER_4, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_IGMP, + 0x00ff, + NPC_IP_VER_4, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_ESP, + 0x00ff, + NPC_IP_VER_4, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_AH, + 0x00ff, + NPC_IP_VER_4, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_GRE, + 0x00ff, + NPC_IP_VER_4, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_IP, + 0x00ff, + NPC_IP_VER_4, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_IP6, + 0x00ff, + NPC_IP_VER_4, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + NPC_IPNH_MPLS, + 0x00ff, + NPC_IP_VER_4, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + 0x0000, + 0x0000, + NPC_IP_VER_4, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + 0x0000, + NPC_IP6_HOP_MASK, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_TCP << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_UDP << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_SCTP << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_ICMP << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_ICMP6 << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_GRE << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_IP6 << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_MPLS << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_HOP << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_DEST << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_ROUT << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_FRAG << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_ESP << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_AH << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_MOBILITY << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_HOSTID << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + NPC_IPNH_SHIM6 << 8, + 0xff00, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + 0x0000, + 0x0000, + NPC_IP_VER_6, + NPC_IP_VER_MASK, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU5_CPT_IP6, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, { NPC_S_NA, 0X00, 0x0000, @@ -4672,7 +5362,9 @@ static const struct npc_kpu_profile_cam kpu5_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu6_cam_entries[] = { +static struct npc_kpu_profile_cam kpu6_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU6_IP6_EXT, 0xff, 0x0000, @@ -5006,6 +5698,330 @@ static const struct npc_kpu_profile_cam kpu6_cam_entries[] = { 0x0000, 0x0000, }, + { + NPC_S_KPU6_IP6_CPT_FRAG, 0xff, + NPC_IPNH_TCP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_FRAG, 0xff, + NPC_IPNH_UDP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_FRAG, 0xff, + NPC_IPNH_SCTP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_FRAG, 0xff, + NPC_IPNH_ICMP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_FRAG, 0xff, + NPC_IPNH_ICMP6 << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_FRAG, 0xff, + NPC_IPNH_ESP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_FRAG, 0xff, + NPC_IPNH_AH << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_FRAG, 0xff, + NPC_IPNH_GRE << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_FRAG, 0xff, + NPC_IPNH_IP6 << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_FRAG, 0xff, + NPC_IPNH_MPLS << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_FRAG, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + NPC_IPNH_TCP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + NPC_IPNH_UDP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + NPC_IPNH_SCTP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + NPC_IPNH_ICMP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + NPC_IPNH_ICMP6 << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + NPC_IPNH_ESP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + NPC_IPNH_AH << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + NPC_IPNH_GRE << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + NPC_IPNH_IP6 << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + NPC_IPNH_MPLS << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + NPC_IPNH_ROUT << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + NPC_IPNH_FRAG << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_HOP_DEST, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_ROUT, 0xff, + NPC_IPNH_TCP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_ROUT, 0xff, + NPC_IPNH_UDP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_ROUT, 0xff, + NPC_IPNH_SCTP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_ROUT, 0xff, + NPC_IPNH_ICMP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_ROUT, 0xff, + NPC_IPNH_ICMP6 << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_ROUT, 0xff, + NPC_IPNH_ESP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_ROUT, 0xff, + NPC_IPNH_AH << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_ROUT, 0xff, + NPC_IPNH_GRE << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_ROUT, 0xff, + NPC_IPNH_IP6 << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_ROUT, 0xff, + NPC_IPNH_MPLS << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_ROUT, 0xff, + NPC_IPNH_FRAG << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU6_IP6_CPT_ROUT, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, { NPC_S_NA, 0X00, 0x0000, @@ -5017,7 +6033,9 @@ static const struct npc_kpu_profile_cam kpu6_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu7_cam_entries[] = { +static struct npc_kpu_profile_cam kpu7_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU7_IP6_EXT, 0xff, 0x0000, @@ -5225,6 +6243,105 @@ static const struct npc_kpu_profile_cam kpu7_cam_entries[] = { 0x0000, 0x0000, }, + { + NPC_S_KPU7_CPT_IP6_FRAG, 0xff, + NPC_IPNH_TCP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU7_CPT_IP6_FRAG, 0xff, + NPC_IPNH_UDP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU7_CPT_IP6_FRAG, 0xff, + NPC_IPNH_SCTP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU7_CPT_IP6_FRAG, 0xff, + NPC_IPNH_ICMP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU7_CPT_IP6_FRAG, 0xff, + NPC_IPNH_ICMP6 << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU7_CPT_IP6_FRAG, 0xff, + NPC_IPNH_ESP << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU7_CPT_IP6_FRAG, 0xff, + NPC_IPNH_AH << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU7_CPT_IP6_FRAG, 0xff, + NPC_IPNH_GRE << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU7_CPT_IP6_FRAG, 0xff, + NPC_IPNH_IP6 << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU7_CPT_IP6_FRAG, 0xff, + NPC_IPNH_MPLS << 8, + 0xff00, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, + { + NPC_S_KPU7_CPT_IP6_FRAG, 0xff, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + 0x0000, + }, { NPC_S_NA, 0X00, 0x0000, @@ -5236,7 +6353,9 @@ static const struct npc_kpu_profile_cam kpu7_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { +static struct npc_kpu_profile_cam kpu8_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU8_TCP, 0xff, 0x0000, @@ -5259,8 +6378,8 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_TCP, 0xff, 0x0000, 0x0000, - NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_FIN, - NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_FIN, + NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_FIN, + NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_FIN, 0x0000, 0x0000, }, @@ -5268,8 +6387,8 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_TCP, 0xff, 0x0000, 0x0000, - NPC_TCP_FLAGS_URG|NPC_TCP_FLAGS_SYN, - NPC_TCP_FLAGS_URG|NPC_TCP_FLAGS_SYN, + NPC_TCP_FLAGS_URG | NPC_TCP_FLAGS_SYN, + NPC_TCP_FLAGS_URG | NPC_TCP_FLAGS_SYN, 0x0000, 0x0000, }, @@ -5277,8 +6396,8 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_TCP, 0xff, 0x0000, 0x0000, - NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_SYN, - NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_SYN, + NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_SYN, + NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_SYN, 0x0000, 0x0000, }, @@ -5286,8 +6405,8 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_TCP, 0xff, 0x0000, 0x0000, - NPC_TCP_FLAGS_SYN|NPC_TCP_FLAGS_FIN, - NPC_TCP_FLAGS_SYN|NPC_TCP_FLAGS_FIN, + NPC_TCP_FLAGS_SYN | NPC_TCP_FLAGS_FIN, + NPC_TCP_FLAGS_SYN | NPC_TCP_FLAGS_FIN, 0x0000, 0x0000, }, @@ -5565,7 +6684,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_MPLSU, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_KEY, + NPC_GRE_F_CSUM | NPC_GRE_F_KEY, 0xffff, 0x0000, 0x0000, @@ -5574,7 +6693,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_MPLSU, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_SEQ, + NPC_GRE_F_CSUM | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5583,7 +6702,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_MPLSU, 0xffff, - NPC_GRE_F_KEY|NPC_GRE_F_SEQ, + NPC_GRE_F_KEY | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5592,7 +6711,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_MPLSU, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_KEY|NPC_GRE_F_SEQ, + NPC_GRE_F_CSUM | NPC_GRE_F_KEY | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5637,7 +6756,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_MPLSM, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_KEY, + NPC_GRE_F_CSUM | NPC_GRE_F_KEY, 0xffff, 0x0000, 0x0000, @@ -5646,7 +6765,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_MPLSM, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_SEQ, + NPC_GRE_F_CSUM | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5655,7 +6774,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_MPLSM, 0xffff, - NPC_GRE_F_KEY|NPC_GRE_F_SEQ, + NPC_GRE_F_KEY | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5664,7 +6783,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_MPLSM, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_KEY|NPC_GRE_F_SEQ, + NPC_GRE_F_CSUM | NPC_GRE_F_KEY | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5709,7 +6828,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_NSH, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_KEY, + NPC_GRE_F_CSUM | NPC_GRE_F_KEY, 0xffff, 0x0000, 0x0000, @@ -5718,7 +6837,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_NSH, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_SEQ, + NPC_GRE_F_CSUM | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5727,7 +6846,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_NSH, 0xffff, - NPC_GRE_F_KEY|NPC_GRE_F_SEQ, + NPC_GRE_F_KEY | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5736,7 +6855,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_NSH, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_KEY|NPC_GRE_F_SEQ, + NPC_GRE_F_CSUM | NPC_GRE_F_KEY | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5781,7 +6900,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_IP, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_KEY, + NPC_GRE_F_CSUM | NPC_GRE_F_KEY, 0xffff, 0x0000, 0x0000, @@ -5790,7 +6909,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_IP, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_SEQ, + NPC_GRE_F_CSUM | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5799,7 +6918,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_IP, 0xffff, - NPC_GRE_F_KEY|NPC_GRE_F_SEQ, + NPC_GRE_F_KEY | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5808,7 +6927,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_IP, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_KEY|NPC_GRE_F_SEQ, + NPC_GRE_F_CSUM | NPC_GRE_F_KEY | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5853,7 +6972,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_IP6, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_KEY, + NPC_GRE_F_CSUM | NPC_GRE_F_KEY, 0xffff, 0x0000, 0x0000, @@ -5862,7 +6981,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_IP6, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_SEQ, + NPC_GRE_F_CSUM | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5871,7 +6990,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_IP6, 0xffff, - NPC_GRE_F_KEY|NPC_GRE_F_SEQ, + NPC_GRE_F_KEY | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5880,7 +6999,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_IP6, 0xffff, - NPC_GRE_F_CSUM|NPC_GRE_F_KEY|NPC_GRE_F_SEQ, + NPC_GRE_F_CSUM | NPC_GRE_F_KEY | NPC_GRE_F_SEQ, 0xffff, 0x0000, 0x0000, @@ -5916,7 +7035,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_PPP, 0xffff, - NPC_GRE_F_KEY|NPC_GRE_VER_1, + NPC_GRE_F_KEY | NPC_GRE_VER_1, 0xffff, 0x0000, 0x0000, @@ -5925,7 +7044,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_PPP, 0xffff, - NPC_GRE_F_KEY|NPC_GRE_F_SEQ|NPC_GRE_VER_1, + NPC_GRE_F_KEY | NPC_GRE_F_SEQ | NPC_GRE_VER_1, 0xffff, 0x0000, 0x0000, @@ -5934,7 +7053,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_PPP, 0xffff, - NPC_GRE_F_KEY|NPC_GRE_F_ACK|NPC_GRE_VER_1, + NPC_GRE_F_KEY | NPC_GRE_F_ACK | NPC_GRE_VER_1, 0xffff, 0x0000, 0x0000, @@ -5943,7 +7062,7 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { NPC_S_KPU8_GRE, 0xff, NPC_ETYPE_PPP, 0xffff, - NPC_GRE_F_KEY|NPC_GRE_F_SEQ|NPC_GRE_F_ACK|NPC_GRE_VER_1, + NPC_GRE_F_KEY | NPC_GRE_F_SEQ | NPC_GRE_F_ACK | NPC_GRE_VER_1, 0xffff, 0x0000, 0x0000, @@ -5977,7 +7096,9 @@ static const struct npc_kpu_profile_cam kpu8_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu9_cam_entries[] = { +static struct npc_kpu_profile_cam kpu9_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU9_TU_MPLS_IN_GRE, 0xff, NPC_MPLS_S, @@ -6387,8 +7508,8 @@ static const struct npc_kpu_profile_cam kpu9_cam_entries[] = { NPC_S_KPU9_GTPU, 0xff, 0x0000, 0x0000, - 0x0000, - 0x0000, + NPC_GTP_PT_GTP | NPC_GTP_VER1, + NPC_GTP_PT_MASK | NPC_GTP_VER_MASK, 0x0000, 0x0000, }, @@ -6448,7 +7569,9 @@ static const struct npc_kpu_profile_cam kpu9_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu10_cam_entries[] = { +static struct npc_kpu_profile_cam kpu10_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU10_TU_MPLS, 0xff, NPC_MPLS_S, @@ -6613,7 +7736,9 @@ static const struct npc_kpu_profile_cam kpu10_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu11_cam_entries[] = { +static struct npc_kpu_profile_cam kpu11_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU11_TU_ETHER, 0xff, NPC_ETYPE_IP, @@ -6922,13 +8047,15 @@ static const struct npc_kpu_profile_cam kpu11_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu12_cam_entries[] = { +static struct npc_kpu_profile_cam kpu12_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU12_TU_IP, 0xff, NPC_IPNH_TCP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, 0x0000, }, @@ -6936,8 +8063,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = { NPC_S_KPU12_TU_IP, 0xff, NPC_IPNH_UDP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, 0x0000, }, @@ -6945,8 +8072,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = { NPC_S_KPU12_TU_IP, 0xff, NPC_IPNH_SCTP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, 0x0000, }, @@ -6954,8 +8081,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = { NPC_S_KPU12_TU_IP, 0xff, NPC_IPNH_ICMP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, 0x0000, }, @@ -6963,8 +8090,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = { NPC_S_KPU12_TU_IP, 0xff, NPC_IPNH_IGMP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, 0x0000, }, @@ -6972,8 +8099,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = { NPC_S_KPU12_TU_IP, 0xff, NPC_IPNH_ESP, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, 0x0000, }, @@ -6981,8 +8108,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = { NPC_S_KPU12_TU_IP, 0xff, NPC_IPNH_AH, 0x00ff, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, 0x0000, }, @@ -6990,8 +8117,8 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = { NPC_S_KPU12_TU_IP, 0xff, 0x0000, 0x0000, - NPC_IP_VER_4|NPC_IP_HDR_LEN_5, - NPC_IP_VER_MASK|NPC_IP_HDR_LEN_MASK, + NPC_IP_VER_4 | NPC_IP_HDR_LEN_5, + NPC_IP_VER_MASK | NPC_IP_HDR_LEN_MASK, 0x0000, 0x0000, }, @@ -7177,7 +8304,9 @@ static const struct npc_kpu_profile_cam kpu12_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu13_cam_entries[] = { +static struct npc_kpu_profile_cam kpu13_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU13_TU_IP6_EXT, 0xff, 0x0000, @@ -7189,7 +8318,9 @@ static const struct npc_kpu_profile_cam kpu13_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu14_cam_entries[] = { +static struct npc_kpu_profile_cam kpu14_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU14_TU_IP6_EXT, 0xff, 0x0000, @@ -7201,7 +8332,9 @@ static const struct npc_kpu_profile_cam kpu14_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu15_cam_entries[] = { +static struct npc_kpu_profile_cam kpu15_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU15_TU_TCP, 0xff, 0x0000, @@ -7224,8 +8357,8 @@ static const struct npc_kpu_profile_cam kpu15_cam_entries[] = { NPC_S_KPU15_TU_TCP, 0xff, 0x0000, 0x0000, - NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_FIN, - NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_FIN, + NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_FIN, + NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_FIN, 0x0000, 0x0000, }, @@ -7233,8 +8366,8 @@ static const struct npc_kpu_profile_cam kpu15_cam_entries[] = { NPC_S_KPU15_TU_TCP, 0xff, 0x0000, 0x0000, - NPC_TCP_FLAGS_URG|NPC_TCP_FLAGS_SYN, - NPC_TCP_FLAGS_URG|NPC_TCP_FLAGS_SYN, + NPC_TCP_FLAGS_URG | NPC_TCP_FLAGS_SYN, + NPC_TCP_FLAGS_URG | NPC_TCP_FLAGS_SYN, 0x0000, 0x0000, }, @@ -7242,8 +8375,8 @@ static const struct npc_kpu_profile_cam kpu15_cam_entries[] = { NPC_S_KPU15_TU_TCP, 0xff, 0x0000, 0x0000, - NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_SYN, - NPC_TCP_FLAGS_RST|NPC_TCP_FLAGS_SYN, + NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_SYN, + NPC_TCP_FLAGS_RST | NPC_TCP_FLAGS_SYN, 0x0000, 0x0000, }, @@ -7251,8 +8384,8 @@ static const struct npc_kpu_profile_cam kpu15_cam_entries[] = { NPC_S_KPU15_TU_TCP, 0xff, 0x0000, 0x0000, - NPC_TCP_FLAGS_SYN|NPC_TCP_FLAGS_FIN, - NPC_TCP_FLAGS_SYN|NPC_TCP_FLAGS_FIN, + NPC_TCP_FLAGS_SYN | NPC_TCP_FLAGS_FIN, + NPC_TCP_FLAGS_SYN | NPC_TCP_FLAGS_FIN, 0x0000, 0x0000, }, @@ -7402,7 +8535,9 @@ static const struct npc_kpu_profile_cam kpu15_cam_entries[] = { }, }; -static const struct npc_kpu_profile_cam kpu16_cam_entries[] = { +static struct npc_kpu_profile_cam kpu16_cam_entries[] = { + NPC_KPU_NOP_CAM, + NPC_KPU_NOP_CAM, { NPC_S_KPU16_TCP_DATA, 0xff, 0x0000, @@ -7459,7 +8594,9 @@ static const struct npc_kpu_profile_cam kpu16_cam_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu1_action_entries[] = { +static struct npc_kpu_profile_action kpu1_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 0, 6, 3, 0, @@ -7508,6 +8645,14 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = { 0, 0, 0, 0, 0, }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 12, 0, 0, 0, + NPC_S_KPU2_NGIO, 12, 1, + NPC_LID_LA, NPC_LT_LA_ETHER, + 0, + 0, 0, 0, 0, + }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 12, 0, 0, 0, @@ -7518,7 +8663,7 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = { }, { NPC_ERRLEV_RE, NPC_EC_NOERR, - 4, 8, 0, 0, 0, + 4, 8, 12, 0, 0, NPC_S_KPU2_CTAG, 12, 1, NPC_LID_LA, NPC_LT_LA_ETHER, NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, @@ -7548,14 +8693,6 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = { NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_ETAG, 0, 0, 0, 0, }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 18, 22, 26, 0, 0, - NPC_S_KPU2_ITAG, 12, 1, - NPC_LID_LA, NPC_LT_LA_ETHER, - NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_ITAG, - 0, 0, 0, 0, - }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 2, 6, 10, 2, 0, @@ -7588,6 +8725,14 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = { 0, 0, 0, 0, 0, }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 12, 0, 2, 0, + NPC_S_KPU4_PPPOE, 12, 1, + NPC_LID_LA, NPC_LT_LA_ETHER, + 0, + 0, 0, 0, 0, + }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 0, 1, @@ -7705,15 +8850,6 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = { | NPC_F_LA_L_WITH_ETAG, 0, 0, 0, 0, }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 18, 22, 26, 0, 0, - NPC_S_KPU2_ITAG, 20, 1, - NPC_LID_LA, NPC_LT_LA_IH_NIX_ETHER, - NPC_F_LA_U_HAS_IH_NIX | NPC_F_LA_U_HAS_TAG - | NPC_F_LA_L_WITH_ITAG, - 0, 0, 0, 0, - }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 2, 6, 10, 2, 0, @@ -7788,7 +8924,7 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = { }, { NPC_ERRLEV_RE, NPC_EC_NOERR, - 4, 8, 16, 2, 0, + 4, 8, 12, 2, 0, NPC_S_KPU4_FDSA, 12, 1, NPC_LID_LA, NPC_LT_LA_ETHER, 0, @@ -7895,15 +9031,6 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = { | NPC_F_LA_L_WITH_ETAG, 0, 0, 0, 0, }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 18, 22, 26, 0, 0, - NPC_S_KPU2_ITAG, 28, 1, - NPC_LID_LA, NPC_LT_LA_HIGIG2_ETHER, - NPC_F_LA_U_HAS_HIGIG2 | NPC_F_LA_U_HAS_TAG - | NPC_F_LA_L_WITH_ITAG, - 0, 0, 0, 0, - }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 2, 6, 10, 2, 0, @@ -8029,15 +9156,6 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = { | NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_ETAG, 0, 0, 0, 0, }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 18, 22, 26, 0, 0, - NPC_S_KPU2_ITAG, 36, 1, - NPC_LID_LA, NPC_LT_LA_IH_NIX_HIGIG2_ETHER, - NPC_F_LA_U_HAS_IH_NIX | NPC_F_LA_U_HAS_HIGIG2 - | NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_ITAG, - 0, 0, 0, 0, - }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 2, 6, 10, 2, 0, @@ -8074,6 +9192,326 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = { | NPC_F_LA_L_UNK_ETYPE, 0, 0, 0, 0, }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 3, 0, + NPC_S_KPU5_IP, 104, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 3, 0, + NPC_S_KPU5_IP6, 104, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 3, 0, + NPC_S_KPU5_ARP, 104, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 3, 0, + NPC_S_KPU5_RARP, 104, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 3, 0, + NPC_S_KPU5_PTP, 104, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 3, 0, + NPC_S_KPU5_FCOE, 104, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 12, 0, 0, 0, + NPC_S_KPU2_CTAG2, 102, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 4, 8, 0, 0, 0, + NPC_S_KPU2_CTAG, 102, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 4, 8, 22, 0, 0, + NPC_S_KPU2_SBTAG, 102, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 4, 8, 0, 0, 0, + NPC_S_KPU2_QINQ, 102, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 12, 26, 0, 0, + NPC_S_KPU2_ETAG, 102, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_ETAG, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 6, 10, 2, 0, + NPC_S_KPU4_MPLS, 104, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_F_LA_L_WITH_MPLS, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 6, 10, 2, 0, + NPC_S_KPU4_MPLS, 104, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_F_LA_L_WITH_MPLS, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 0, 0, 2, 0, + NPC_S_KPU4_NSH, 104, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_F_LA_L_WITH_NSH, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_F_LA_L_UNK_ETYPE, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 3, 0, + NPC_S_KPU5_CPT_IP, 56, 1, + NPC_LID_LA, NPC_LT_LA_CPT_HDR, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 3, 0, + NPC_S_KPU5_CPT_IP6, 56, 1, + NPC_LID_LA, NPC_LT_LA_CPT_HDR, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 4, 8, 0, 0, 0, + NPC_S_KPU2_CTAG, 54, 1, + NPC_LID_LA, NPC_LT_LA_CPT_HDR, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 4, 8, 0, 0, 0, + NPC_S_KPU2_QINQ, 54, 1, + NPC_LID_LA, NPC_LT_LA_CPT_HDR, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 3, 0, + NPC_S_KPU5_CPT_IP, 60, 1, + NPC_LID_LA, NPC_LT_LA_CPT_HDR, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 3, 0, + NPC_S_KPU5_CPT_IP6, 60, 1, + NPC_LID_LA, NPC_LT_LA_CPT_HDR, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 4, 8, 0, 0, 0, + NPC_S_KPU2_CTAG, 58, 1, + NPC_LID_LA, NPC_LT_LA_CPT_HDR, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 4, 8, 0, 0, 0, + NPC_S_KPU2_QINQ, 58, 1, + NPC_LID_LA, NPC_LT_LA_CPT_HDR, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LA, NPC_LT_LA_CPT_HDR, + NPC_F_LA_L_UNK_ETYPE, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 3, 0, + NPC_S_KPU5_IP, 38, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 3, 0, + NPC_S_KPU5_IP6, 38, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 3, 0, + NPC_S_KPU5_ARP, 38, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 3, 0, + NPC_S_KPU5_RARP, 38, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 3, 0, + NPC_S_KPU5_PTP, 38, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 3, 0, + NPC_S_KPU5_FCOE, 38, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 12, 0, 0, 0, + NPC_S_KPU2_CTAG2, 36, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 4, 8, 0, 0, 0, + NPC_S_KPU2_CTAG, 36, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 4, 8, 22, 0, 0, + NPC_S_KPU2_SBTAG, 36, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 4, 8, 0, 0, 0, + NPC_S_KPU2_QINQ, 36, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 12, 26, 0, 0, + NPC_S_KPU2_ETAG, 36, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_ETAG, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 6, 10, 2, 0, + NPC_S_KPU4_MPLS, 38, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + NPC_F_LA_L_WITH_MPLS, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 6, 10, 2, 0, + NPC_S_KPU4_MPLS, 38, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + NPC_F_LA_L_WITH_MPLS, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 0, 0, 2, 0, + NPC_S_KPU4_NSH, 38, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + NPC_F_LA_L_WITH_NSH, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + NPC_F_LA_L_UNK_ETYPE, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 12, 0, 0, 1, 0, + NPC_S_KPU3_VLAN_EXDSA, 12, 1, + NPC_LID_LA, NPC_LT_LA_ETHER, + 0, + 0, 0, 0, 0, + }, { NPC_ERRLEV_LA, NPC_EC_L2_K1, 0, 0, 0, 0, 1, @@ -8084,7 +9522,9 @@ static const struct npc_kpu_profile_action kpu1_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu2_action_entries[] = { +static struct npc_kpu_profile_action kpu2_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 0, 6, 2, 0, @@ -8157,6 +9597,22 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 0, 0, }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 2, 0, + NPC_S_KPU5_IP, 14, 1, + NPC_LID_LB, NPC_LT_LB_PPPOE, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 2, 0, + NPC_S_KPU5_IP6, 14, 1, + NPC_LID_LB, NPC_LT_LB_PPPOE, + 0, + 0, 0, 0, 0, + }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 0, 1, @@ -8170,7 +9626,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 8, 0, 6, 2, 0, NPC_S_KPU5_IP, 10, 1, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG, 0, 0, 0, 0, }, { @@ -8178,7 +9634,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 6, 0, 0, 2, 0, NPC_S_KPU5_IP6, 10, 1, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG, 0, 0, 0, 0, }, { @@ -8186,7 +9642,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 2, 0, NPC_S_KPU5_ARP, 10, 1, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG, 0, 0, 0, 0, }, { @@ -8194,7 +9650,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 2, 0, NPC_S_KPU5_RARP, 10, 1, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG, 0, 0, 0, 0, }, { @@ -8202,7 +9658,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 2, 0, NPC_S_KPU5_PTP, 10, 1, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG, 0, 0, 0, 0, }, { @@ -8210,7 +9666,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 2, 0, NPC_S_KPU5_FCOE, 10, 1, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG, 0, 0, 0, 0, }, { @@ -8218,7 +9674,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 6, 10, 1, 0, NPC_S_KPU4_MPLS, 10, 1, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG, 0, 0, 0, 0, }, { @@ -8226,7 +9682,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 6, 10, 1, 0, NPC_S_KPU4_MPLS, 10, 1, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG, 0, 0, 0, 0, }, { @@ -8234,7 +9690,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 0, 0, 1, 0, NPC_S_KPU4_NSH, 10, 1, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG, 0, 0, 0, 0, }, { @@ -8242,7 +9698,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 0, 1, NPC_S_NA, 0, 1, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG_UNK, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG_UNK, 0, 0, 0, 0, }, { @@ -8250,7 +9706,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 6, 0, 0, 0, NPC_S_KPU3_CTAG, 10, 1, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG_CTAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_STAG_CTAG, 0, 0, 0, 0, }, { @@ -8258,7 +9714,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 6, 0, 0, 0, NPC_S_KPU3_STAG, 10, 1, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG_STAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_STAG_STAG, 0, 0, 0, 0, }, { @@ -8266,7 +9722,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 8, 0, 6, 2, 0, NPC_S_KPU5_IP, 24, 1, NPC_LID_LB, NPC_LT_LB_BTAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG, 0, 0, 0, 0, }, { @@ -8274,7 +9730,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 6, 0, 0, 2, 0, NPC_S_KPU5_IP6, 24, 1, NPC_LID_LB, NPC_LT_LB_BTAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG, 0, 0, 0, 0, }, { @@ -8282,7 +9738,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 2, 0, NPC_S_KPU5_ARP, 24, 1, NPC_LID_LB, NPC_LT_LB_BTAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG, 0, 0, 0, 0, }, { @@ -8290,7 +9746,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 2, 0, NPC_S_KPU5_RARP, 24, 1, NPC_LID_LB, NPC_LT_LB_BTAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG, 0, 0, 0, 0, }, { @@ -8298,7 +9754,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 2, 0, NPC_S_KPU5_PTP, 24, 1, NPC_LID_LB, NPC_LT_LB_BTAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG, 0, 0, 0, 0, }, { @@ -8306,7 +9762,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 2, 0, NPC_S_KPU5_FCOE, 24, 1, NPC_LID_LB, NPC_LT_LB_BTAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG, 0, 0, 0, 0, }, { @@ -8314,7 +9770,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 6, 10, 1, 0, NPC_S_KPU4_MPLS, 24, 1, NPC_LID_LB, NPC_LT_LB_BTAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG, 0, 0, 0, 0, }, { @@ -8322,7 +9778,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 6, 10, 1, 0, NPC_S_KPU4_MPLS, 24, 1, NPC_LID_LB, NPC_LT_LB_BTAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG, 0, 0, 0, 0, }, { @@ -8330,7 +9786,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 0, 0, 1, 0, NPC_S_KPU4_NSH, 24, 1, NPC_LID_LB, NPC_LT_LB_BTAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG, 0, 0, 0, 0, }, { @@ -8338,7 +9794,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 0, 0, 0, 0, NPC_S_KPU3_STAG, 24, 1, NPC_LID_LB, NPC_LT_LB_BTAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG_STAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG_STAG, 0, 0, 0, 0, }, { @@ -8346,7 +9802,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 0, 0, 0, 0, NPC_S_KPU3_CTAG, 24, 1, NPC_LID_LB, NPC_LT_LB_BTAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG_CTAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG_CTAG, 0, 0, 0, 0, }, { @@ -8354,7 +9810,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 0, 1, NPC_S_NA, 0, 1, NPC_LID_LB, NPC_LT_LB_BTAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG_UNK, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG_UNK, 0, 0, 0, 0, }, { @@ -8546,15 +10002,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 0, 0, 0, 0, NPC_S_KPU3_CTAG, 10, 1, NPC_LID_LB, NPC_LT_LB_ETAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 16, 20, 24, 0, 0, - NPC_S_KPU3_ITAG, 14, 1, - NPC_LID_LB, NPC_LT_LB_ETAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_BTAG_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_CTAG, 0, 0, 0, 0, }, { @@ -8562,7 +10010,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 6, 0, 0, 0, NPC_S_KPU3_STAG, 10, 1, NPC_LID_LB, NPC_LT_LB_ETAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_STAG, 0, 0, 0, 0, }, { @@ -8570,7 +10018,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 6, 0, 0, 0, NPC_S_KPU3_QINQ, 10, 1, NPC_LID_LB, NPC_LT_LB_ETAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_QINQ, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_QINQ, 0, 0, 0, 0, }, { @@ -8578,7 +10026,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 8, 0, 6, 2, 0, NPC_S_KPU5_IP, 28, 1, NPC_LID_LB, NPC_LT_LB_ETAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG, 0, 0, 0, 0, }, { @@ -8586,7 +10034,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 6, 0, 0, 2, 0, NPC_S_KPU5_IP6, 28, 1, NPC_LID_LB, NPC_LT_LB_ETAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG, 0, 0, 0, 0, }, { @@ -8594,7 +10042,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 2, 0, NPC_S_KPU5_ARP, 28, 1, NPC_LID_LB, NPC_LT_LB_ETAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG, 0, 0, 0, 0, }, { @@ -8602,7 +10050,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 0, 0, 0, 0, NPC_S_KPU3_STAG, 28, 1, NPC_LID_LB, NPC_LT_LB_ETAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG_STAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG_STAG, 0, 0, 0, 0, }, { @@ -8610,7 +10058,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 2, 0, 0, 0, 0, NPC_S_KPU3_CTAG, 28, 1, NPC_LID_LB, NPC_LT_LB_ETAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG_CTAG, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG_CTAG, 0, 0, 0, 0, }, { @@ -8618,7 +10066,7 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { 0, 0, 0, 0, 1, NPC_S_NA, 0, 1, NPC_LID_LB, NPC_LT_LB_ETAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_ITAG_UNK, + NPC_F_LB_U_MORE_TAG | NPC_F_LB_L_WITH_ITAG_UNK, 0, 0, 0, 0, }, { @@ -8629,142 +10077,6 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { NPC_F_LB_U_UNK_ETYPE, 0, 0, 0, 0, }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 0, 6, 2, 0, - NPC_S_KPU5_IP, 20, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 6, 0, 0, 2, 0, - NPC_S_KPU5_IP6, 20, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 2, 0, - NPC_S_KPU5_ARP, 20, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 2, 0, - NPC_S_KPU5_RARP, 20, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 0, 6, 2, 0, - NPC_S_KPU5_IP, 28, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG_CTAG, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 6, 0, 0, 2, 0, - NPC_S_KPU5_IP6, 28, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG_CTAG, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 2, 0, - NPC_S_KPU5_ARP, 28, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG_CTAG, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK, - 0, 0, 0, 0, 1, - NPC_S_NA, 0, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 0, 6, 2, 0, - NPC_S_KPU5_IP, 24, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 6, 0, 0, 2, 0, - NPC_S_KPU5_IP6, 24, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 2, 0, - NPC_S_KPU5_ARP, 24, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_STAG, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK, - 0, 0, 0, 0, 1, - NPC_S_NA, 0, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 0, 6, 2, 0, - NPC_S_KPU5_IP, 24, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 6, 0, 0, 2, 0, - NPC_S_KPU5_IP6, 24, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 2, 0, - NPC_S_KPU5_ARP, 24, 1, - NPC_LID_LB, NPC_LT_LB_ITAG, - NPC_F_LB_U_MORE_TAG|NPC_F_LB_L_WITH_CTAG, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK, - 0, 0, 0, 0, 1, - NPC_S_NA, 0, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK, - 0, 0, 0, 0, 1, - NPC_S_NA, 0, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 0, 6, 2, 0, @@ -9077,6 +10389,14 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { NPC_F_LB_U_UNK_ETYPE | NPC_F_LB_L_EXDSA, 0, 0, 0, 0, }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_NGIO, + 0, + 0, 0, 0, 0, + }, { NPC_ERRLEV_LB, NPC_EC_L2_K3, 0, 0, 0, 0, 1, @@ -9087,11 +10407,13 @@ static const struct npc_kpu_profile_action kpu2_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu3_action_entries[] = { +static struct npc_kpu_profile_action kpu3_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 0, 6, 1, 0, - NPC_S_KPU5_IP, 4, 0, + NPC_S_KPU5_IP, 6, 0, NPC_LID_LB, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -9099,7 +10421,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 6, 0, 0, 1, 0, - NPC_S_KPU5_IP6, 4, 0, + NPC_S_KPU5_IP6, 6, 0, NPC_LID_LB, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -9107,7 +10429,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 1, 0, - NPC_S_KPU5_ARP, 4, 0, + NPC_S_KPU5_ARP, 6, 0, NPC_LID_LB, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -9115,7 +10437,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 1, 0, - NPC_S_KPU5_RARP, 4, 0, + NPC_S_KPU5_RARP, 6, 0, NPC_LID_LB, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -9123,7 +10445,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 1, 0, - NPC_S_KPU5_PTP, 4, 0, + NPC_S_KPU5_PTP, 6, 0, NPC_LID_LB, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -9131,7 +10453,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 1, 0, - NPC_S_KPU5_FCOE, 4, 0, + NPC_S_KPU5_FCOE, 6, 0, NPC_LID_LB, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -9139,7 +10461,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 2, 6, 10, 0, 0, - NPC_S_KPU4_MPLS, 4, 0, + NPC_S_KPU4_MPLS, 6, 0, NPC_LID_LB, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -9147,7 +10469,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 2, 6, 10, 0, 0, - NPC_S_KPU4_MPLS, 4, 0, + NPC_S_KPU4_MPLS, 6, 0, NPC_LID_LB, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -9155,7 +10477,7 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 2, 0, 0, 0, 0, - NPC_S_KPU4_NSH, 4, 0, + NPC_S_KPU4_NSH, 6, 0, NPC_LID_LB, NPC_LT_NA, 0, 0, 0, 0, 0, @@ -9456,142 +10778,6 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = { 0, 0, 0, 0, 0, }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 0, 6, 2, 0, - NPC_S_KPU5_IP, 18, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 6, 0, 0, 2, 0, - NPC_S_KPU5_IP6, 18, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 2, 0, - NPC_S_KPU5_ARP, 18, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 2, 0, - NPC_S_KPU5_RARP, 18, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 0, 6, 1, 0, - NPC_S_KPU5_IP, 26, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 6, 0, 0, 1, 0, - NPC_S_KPU5_IP6, 26, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 1, 0, - NPC_S_KPU5_ARP, 26, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 0, 6, 1, 0, - NPC_S_KPU5_IP, 22, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 6, 0, 0, 1, 0, - NPC_S_KPU5_IP6, 22, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 1, 0, - NPC_S_KPU5_ARP, 22, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK, - 0, 0, 0, 0, 1, - NPC_S_NA, 0, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK, - 0, 0, 0, 0, 1, - NPC_S_NA, 0, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 0, 6, 1, 0, - NPC_S_KPU5_IP, 22, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 6, 0, 0, 1, 0, - NPC_S_KPU5_IP6, 22, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 1, 0, - NPC_S_KPU5_ARP, 22, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK, - 0, 0, 0, 0, 1, - NPC_S_NA, 0, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_LB, NPC_EC_L2_K3_ETYPE_UNK, - 0, 0, 0, 0, 1, - NPC_S_NA, 0, 0, - NPC_LID_LB, NPC_LT_NA, - 0, - 0, 0, 0, 0, - }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 0, 6, 1, 0, @@ -10072,6 +11258,14 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = { NPC_F_LB_U_UNK_ETYPE | NPC_F_LB_L_DSA_VLAN, 0, 0, 0, 0, }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU4_VLAN_EXDSA, 12, 1, + NPC_LID_LB, NPC_LT_LB_VLAN_EXDSA, + 0, + 0, 0, 0, 0, + }, { NPC_ERRLEV_LB, NPC_EC_L2_K3, 0, 0, 0, 0, 1, @@ -10082,7 +11276,9 @@ static const struct npc_kpu_profile_action kpu3_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu4_action_entries[] = { +static struct npc_kpu_profile_action kpu4_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 0, 0, @@ -10203,6 +11399,70 @@ static const struct npc_kpu_profile_action kpu4_action_entries[] = { NPC_F_LB_L_FDSA, 0, 0, 0, 0, }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 0, 0, + NPC_S_KPU5_IP, 10, 1, + NPC_LID_LB, NPC_LT_LB_FDSA, + NPC_F_LB_L_FDSA, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 0, 0, + NPC_S_KPU5_IP6, 10, 1, + NPC_LID_LB, NPC_LT_LB_FDSA, + NPC_F_LB_L_FDSA, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU5_ARP, 10, 1, + NPC_LID_LB, NPC_LT_LB_FDSA, + NPC_F_LB_L_FDSA, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 0, 0, + NPC_S_KPU5_RARP, 10, 1, + NPC_LID_LB, NPC_LT_LB_FDSA, + NPC_F_LB_L_FDSA, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 0, 0, + NPC_S_KPU5_PTP, 10, 1, + NPC_LID_LB, NPC_LT_LB_FDSA, + NPC_F_LB_L_FDSA, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU5_FCOE, 10, 1, + NPC_LID_LB, NPC_LT_LB_FDSA, + NPC_F_LB_L_FDSA, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 0, 0, + NPC_S_KPU5_IP, 14, 1, + NPC_LID_LB, NPC_LT_LB_PPPOE, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 0, 0, + NPC_S_KPU5_IP6, 14, 1, + NPC_LID_LB, NPC_LT_LB_PPPOE, + 0, + 0, 0, 0, 0, + }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 0, 1, @@ -10211,6 +11471,78 @@ static const struct npc_kpu_profile_action kpu4_action_entries[] = { NPC_F_LB_U_UNK_ETYPE | NPC_F_LB_L_FDSA, 0, 0, 0, 0, }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 0, 0, + NPC_S_KPU5_IP, 2, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 0, 0, + NPC_S_KPU5_IP6, 2, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU5_ARP, 2, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 0, 0, + NPC_S_KPU5_RARP, 2, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 0, 0, + NPC_S_KPU5_PTP, 2, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU5_FCOE, 2, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 0, 0, + NPC_S_KPU5_IP, 10, 0, + NPC_LID_LB, NPC_LT_LB_PPPOE, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 0, 0, + NPC_S_KPU5_IP6, 10, 0, + NPC_LID_LB, NPC_LT_LB_PPPOE, + 0, + 0, 0, 0, 0, + }, { NPC_ERRLEV_LB, NPC_EC_L2_K4, 0, 0, 0, 0, 1, @@ -10221,7 +11553,9 @@ static const struct npc_kpu_profile_action kpu4_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu5_action_entries[] = { +static struct npc_kpu_profile_action kpu5_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_LC, NPC_EC_IP_TTL_0, 0, 0, 0, 0, 1, @@ -10718,6 +12052,382 @@ static const struct npc_kpu_profile_action kpu5_action_entries[] = { 0, 0, 0, 0, 0, }, + { + NPC_ERRLEV_LC, NPC_EC_IP_TTL_0, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_LC, NPC_EC_IP_FRAG_OFFSET_1, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP, + NPC_F_LC_U_IP_FRAG, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 12, 0, 2, 0, + NPC_S_KPU8_TCP, 20, 1, + NPC_LID_LC, NPC_LT_LC_IP, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 0, 0, 2, 0, + NPC_S_KPU8_UDP, 20, 1, + NPC_LID_LC, NPC_LT_LC_IP, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_SCTP, 20, 1, + NPC_LID_LC, NPC_LT_LC_IP, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_ICMP, 20, 1, + NPC_LID_LC, NPC_LT_LC_IP, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_IGMP, 20, 1, + NPC_LID_LC, NPC_LT_LC_IP, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 3, 0, + NPC_S_KPU9_ESP, 20, 1, + NPC_LID_LC, NPC_LT_LC_IP, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_AH, 20, 1, + NPC_LID_LC, NPC_LT_LC_IP, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 0, 0, 2, 0, + NPC_S_KPU8_GRE, 20, 1, + NPC_LID_LC, NPC_LT_LC_IP, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 6, 0, + NPC_S_KPU12_TU_IP, 20, 1, + NPC_LID_LC, NPC_LT_LC_IP, + NPC_F_LC_L_IP_IN_IP, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 6, 0, + NPC_S_KPU12_TU_IP6, 20, 1, + NPC_LID_LC, NPC_LT_LC_IP, + NPC_F_LC_L_6TO4, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 6, 10, 3, 0, + NPC_S_KPU9_TU_MPLS_IN_IP, 20, 1, + NPC_LID_LC, NPC_LT_LC_IP, + NPC_F_LC_L_MPLS_IN_IP, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP, + NPC_F_LC_U_UNK_PROTO, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 12, 0, 2, 0, + NPC_S_KPU8_TCP, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP_OPT, + 0, + 0, 0xf, 0, 2, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 8, 10, 2, 0, + NPC_S_KPU8_UDP, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP_OPT, + 0, + 0, 0xf, 0, 2, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_SCTP, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP_OPT, + 0, + 0, 0xf, 0, 2, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_ICMP, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP_OPT, + 0, + 0, 0xf, 0, 2, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_IGMP, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP_OPT, + 0, + 0, 0xf, 0, 2, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 3, 0, + NPC_S_KPU9_ESP, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP_OPT, + 0, + 0, 0xf, 0, 2, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_AH, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP_OPT, + 0, + 0, 0xf, 0, 2, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 0, 0, 2, 0, + NPC_S_KPU8_GRE, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP_OPT, + 0, + 0, 0xf, 0, 2, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 8, 0, 6, 6, 0, + NPC_S_KPU12_TU_IP, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP_OPT, + NPC_F_LC_L_IP_IN_IP, + 0, 0xf, 0, 2, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 6, 0, + NPC_S_KPU12_TU_IP6, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP_OPT, + NPC_F_LC_L_6TO4, + 0, 0xf, 0, 2, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 6, 10, 3, 0, + NPC_S_KPU9_TU_MPLS_IN_IP, 20, 1, + NPC_LID_LC, NPC_LT_LC_IP_OPT, + NPC_F_LC_L_MPLS_IN_IP, + 0, 0xf, 0, 2, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP_OPT, + NPC_F_LC_U_UNK_PROTO, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_LC, NPC_EC_IP_VER, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_LC, NPC_EC_IP6_HOP_0, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP6, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 12, 0, 2, 0, + NPC_S_KPU8_TCP, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 0, 0, 2, 0, + NPC_S_KPU8_UDP, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_SCTP, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_ICMP, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_ICMP6, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_GRE, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 6, 0, + NPC_S_KPU12_TU_IP6, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6, + NPC_F_LC_L_IP6_TUN_IP6, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 6, 10, 3, 0, + NPC_S_KPU9_TU_MPLS_IN_IP, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6, + NPC_F_LC_L_IP6_MPLS_IN_IP, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU6_IP6_CPT_HOP_DEST, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6_EXT, + NPC_F_LC_L_EXT_HOP, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU6_IP6_CPT_HOP_DEST, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6_EXT, + NPC_F_LC_L_EXT_DEST, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU6_IP6_CPT_ROUT, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6_EXT, + NPC_F_LC_L_EXT_ROUT, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 2, 0, 0, 0, + NPC_S_KPU6_IP6_CPT_FRAG, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6_EXT, + NPC_F_LC_U_IP6_FRAG, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 3, 0, + NPC_S_KPU9_ESP, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6_EXT, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU8_AH, 40, 1, + NPC_LID_LC, NPC_LT_LC_IP6_EXT, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP6_EXT, + NPC_F_LC_L_EXT_MOBILITY, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP6_EXT, + NPC_F_LC_L_EXT_HOSTID, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP6_EXT, + NPC_F_LC_L_EXT_SHIM6, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP6, + NPC_F_LC_U_UNK_PROTO, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_LC, NPC_EC_IP6_VER, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 1, + NPC_LID_LC, NPC_LT_LC_IP6, + 0, + 0, 0, 0, 0, + }, { NPC_ERRLEV_LC, NPC_EC_UNK, 0, 0, 0, 0, 1, @@ -10728,7 +12438,9 @@ static const struct npc_kpu_profile_action kpu5_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu6_action_entries[] = { +static struct npc_kpu_profile_action kpu6_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 0, 1, @@ -11025,6 +12737,294 @@ static const struct npc_kpu_profile_action kpu6_action_entries[] = { 0, 0, 0, 0, 0, }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 12, 0, 1, 0, + NPC_S_KPU8_TCP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 8, 10, 1, 0, + NPC_S_KPU8_UDP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_SCTP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_ICMP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_ICMP6, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU9_ESP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_AH, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_GRE, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 5, 0, + NPC_S_KPU12_TU_IP6, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 6, 10, 2, 0, + NPC_S_KPU9_TU_MPLS_IN_IP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 12, 0, 1, 0, + NPC_S_KPU8_TCP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 8, 10, 1, 0, + NPC_S_KPU8_UDP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_SCTP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_ICMP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_ICMP6, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU9_ESP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_AH, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_GRE, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 5, 0, + NPC_S_KPU12_TU_IP6, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 6, 10, 2, 0, + NPC_S_KPU9_TU_MPLS_IN_IP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU7_IP6_ROUT, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 2, 0, 0, 0, + NPC_S_KPU7_CPT_IP6_FRAG, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 12, 0, 1, 0, + NPC_S_KPU8_TCP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 8, 10, 1, 0, + NPC_S_KPU8_UDP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_SCTP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_ICMP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_ICMP6, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 2, 0, + NPC_S_KPU9_ESP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_AH, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU8_GRE, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 5, 0, + NPC_S_KPU12_TU_IP6, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 6, 10, 2, 0, + NPC_S_KPU9_TU_MPLS_IN_IP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 2, 0, 0, 0, + NPC_S_KPU7_CPT_IP6_FRAG, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 1, 0xff, 0, 3, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, { NPC_ERRLEV_LC, NPC_EC_UNK, 0, 0, 0, 0, 1, @@ -11035,7 +13035,9 @@ static const struct npc_kpu_profile_action kpu6_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu7_action_entries[] = { +static struct npc_kpu_profile_action kpu7_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 0, 1, @@ -11220,6 +13222,94 @@ static const struct npc_kpu_profile_action kpu7_action_entries[] = { 0, 0, 0, 0, 0, }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 12, 0, 0, 0, + NPC_S_KPU8_TCP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 8, 10, 0, 0, + NPC_S_KPU8_UDP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU8_SCTP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU8_ICMP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU8_ICMP6, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 1, 0, + NPC_S_KPU9_ESP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU8_AH, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 0, + NPC_S_KPU8_GRE, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 6, 0, 0, 4, 0, + NPC_S_KPU12_TU_IP6, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 2, 6, 10, 1, 0, + NPC_S_KPU9_TU_MPLS_IN_IP, 8, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, + { + NPC_ERRLEV_RE, NPC_EC_NOERR, + 0, 0, 0, 0, 1, + NPC_S_NA, 0, 0, + NPC_LID_LC, NPC_LT_NA, + 0, + 0, 0, 0, 0, + }, { NPC_ERRLEV_LC, NPC_EC_UNK, 0, 0, 0, 0, 1, @@ -11230,7 +13320,9 @@ static const struct npc_kpu_profile_action kpu7_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu8_action_entries[] = { +static struct npc_kpu_profile_action kpu8_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_LD, NPC_EC_TCP_FLAGS_FIN_ONLY, 0, 0, 0, 0, 1, @@ -11889,7 +13981,9 @@ static const struct npc_kpu_profile_action kpu8_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu9_action_entries[] = { +static struct npc_kpu_profile_action kpu9_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 0, 0, @@ -12252,10 +14346,10 @@ static const struct npc_kpu_profile_action kpu9_action_entries[] = { }, { NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 0, 1, - NPC_S_NA, 0, 1, + 8, 0, 6, 2, 0, + NPC_S_KPU12_TU_IP, 8, 1, NPC_LID_LE, NPC_LT_LE_GTPU, - NPC_F_LE_L_GTPU_UNK, + 0, 0, 0, 0, 0, }, { @@ -12308,7 +14402,9 @@ static const struct npc_kpu_profile_action kpu9_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu10_action_entries[] = { +static struct npc_kpu_profile_action kpu10_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 0, 6, 1, 0, @@ -12455,7 +14551,9 @@ static const struct npc_kpu_profile_action kpu10_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu11_action_entries[] = { +static struct npc_kpu_profile_action kpu11_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 0, 6, 0, 0, @@ -12730,7 +14828,9 @@ static const struct npc_kpu_profile_action kpu11_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu12_action_entries[] = { +static struct npc_kpu_profile_action kpu12_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 2, 12, 0, 2, 0, @@ -12957,7 +15057,9 @@ static const struct npc_kpu_profile_action kpu12_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu13_action_entries[] = { +static struct npc_kpu_profile_action kpu13_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 0, 1, @@ -12968,7 +15070,9 @@ static const struct npc_kpu_profile_action kpu13_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu14_action_entries[] = { +static struct npc_kpu_profile_action kpu14_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 0, 1, @@ -12979,7 +15083,9 @@ static const struct npc_kpu_profile_action kpu14_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu15_action_entries[] = { +static struct npc_kpu_profile_action kpu15_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_LG, NPC_EC_TCP_FLAGS_FIN_ONLY, 0, 0, 0, 0, 1, @@ -13158,7 +15264,9 @@ static const struct npc_kpu_profile_action kpu15_action_entries[] = { }, }; -static const struct npc_kpu_profile_action kpu16_action_entries[] = { +static struct npc_kpu_profile_action kpu16_action_entries[] = { + NPC_KPU_NOP_ACTION, + NPC_KPU_NOP_ACTION, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 0, 1, @@ -13209,7 +15317,7 @@ static const struct npc_kpu_profile_action kpu16_action_entries[] = { }, }; -static const struct npc_kpu_profile npc_kpu_profiles[] = { +static struct npc_kpu_profile npc_kpu_profiles[] = { { ARRAY_SIZE(kpu1_cam_entries), ARRAY_SIZE(kpu1_action_entries), @@ -13308,12 +15416,22 @@ static const struct npc_kpu_profile npc_kpu_profiles[] = { }, }; -static const struct npc_lt_def_cfg npc_lt_defaults = { +static struct npc_lt_def_cfg npc_lt_defaults = { .rx_ol2 = { .lid = NPC_LID_LA, .ltype_match = NPC_LT_LA_ETHER, .ltype_mask = 0x0F, }, + .ovlan = { + .lid = NPC_LID_LB, + .ltype_match = NPC_LT_LB_CTAG, + .ltype_mask = 0x0F, + }, + .ivlan = { + .lid = NPC_LID_LB, + .ltype_match = NPC_LT_LB_STAG_QINQ, + .ltype_mask = 0x0F, + }, .rx_oip4 = { .lid = NPC_LID_LC, .ltype_match = NPC_LT_LC_IP, @@ -13392,6 +15510,30 @@ static const struct npc_lt_def_cfg npc_lt_defaults = { .ltype_match = NPC_LT_LG_TU_IP, .ltype_mask = 0x0F, }, + .rx_apad0 = { + .valid = 0, + .lid = NPC_LID_LC, + .ltype_match = NPC_LT_LC_IP6, + .ltype_mask = 0x0F, + }, + .rx_apad1 = { + .valid = 0, + .lid = NPC_LID_LC, + .ltype_match = NPC_LT_LC_IP6, + .ltype_mask = 0x0F, + }, + .rx_et = { + { + .lid = NPC_LID_LB, + .ltype_match = NPC_LT_NA, + .ltype_mask = 0x0, + }, + { + .lid = NPC_LID_LB, + .ltype_match = NPC_LT_NA, + .ltype_mask = 0x0, + }, + }, }; static struct npc_mcam_kex npc_mkex_default = { @@ -13399,7 +15541,7 @@ static struct npc_mcam_kex npc_mkex_default = { .name = "default", .kpu_version = NPC_KPU_PROFILE_VER, .keyx_cfg = { - /* nibble: LA..LE (ltype only) + channel */ + /* nibble: LA..LE (ltype only) + Error code + Channel */ [NIX_INTF_RX] = ((u64)NPC_MCAM_KEY_X2 << 32) | NPC_PARSE_NIBBLE_INTF_RX, /* nibble: LA..LE (ltype only) */ [NIX_INTF_TX] = ((u64)NPC_MCAM_KEY_X2 << 32) | NPC_PARSE_NIBBLE_INTF_TX, @@ -13410,30 +15552,40 @@ static struct npc_mcam_kex npc_mkex_default = { [NPC_LID_LA] = { /* Layer A: Ethernet: */ [NPC_LT_LA_ETHER] = { - /* DMAC: 6 bytes, KW1[47:0] */ + /* DMAC: 6 bytes, KW1[55:8] */ KEX_LD_CFG(0x05, 0x0, 0x1, 0x0, NPC_KEXOF_DMAC), - /* Ethertype: 2 bytes, KW0[47:32] */ - KEX_LD_CFG(0x01, 0xc, 0x1, 0x0, 0x4), + /* Ethertype: 2 bytes, KW0[55:40] */ + KEX_LD_CFG(0x01, 0xc, 0x1, 0x0, 0x5), + }, + /* Layer A: HiGig2: */ + [NPC_LT_LA_HIGIG2_ETHER] = { + /* Classification: 2 bytes, KW1[23:8] */ + KEX_LD_CFG(0x01, 0x8, 0x1, 0x0, NPC_KEXOF_DMAC), + /* VID: 2 bytes, KW1[39:24] */ + KEX_LD_CFG(0x01, 0xc, 0x1, 0x0, + NPC_KEXOF_DMAC + 2), }, }, [NPC_LID_LB] = { /* Layer B: Single VLAN (CTAG) */ - /* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */ [NPC_LT_LB_CTAG] = { - KEX_LD_CFG(0x03, 0x2, 0x1, 0x0, 0x4), + /* CTAG VLAN: 2 bytes, KW1[7:0], KW0[63:56] */ + KEX_LD_CFG(0x01, 0x2, 0x1, 0x0, 0x7), + /* Ethertype: 2 bytes, KW0[55:40] */ + KEX_LD_CFG(0x01, 0x4, 0x1, 0x0, 0x5), }, /* Layer B: Stacked VLAN (STAG|QinQ) */ [NPC_LT_LB_STAG_QINQ] = { - /* Outer VLAN: 2 bytes, KW0[63:48] */ - KEX_LD_CFG(0x01, 0x2, 0x1, 0x0, 0x6), - /* Ethertype: 2 bytes, KW0[47:32] */ - KEX_LD_CFG(0x01, 0x8, 0x1, 0x0, 0x4), + /* Outer VLAN: 2 bytes, KW1[7:0], KW0[63:56] */ + KEX_LD_CFG(0x01, 0x2, 0x1, 0x0, 0x7), + /* Ethertype: 2 bytes, KW0[55:40] */ + KEX_LD_CFG(0x01, 0x8, 0x1, 0x0, 0x5), }, [NPC_LT_LB_FDSA] = { - /* SWITCH PORT: 1 byte, KW0[63:48] */ - KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0x6), - /* Ethertype: 2 bytes, KW0[47:32] */ - KEX_LD_CFG(0x01, 0x4, 0x1, 0x0, 0x4), + /* SWITCH PORT: 1 byte, KW0[63:56] */ + KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0x7), + /* Ethertype: 2 bytes, KW0[55:40] */ + KEX_LD_CFG(0x01, 0x4, 0x1, 0x0, 0x5), }, }, [NPC_LID_LC] = { @@ -13477,6 +15629,13 @@ static struct npc_mcam_kex npc_mkex_default = { /* DMAC: 6 bytes, KW1[63:16] */ KEX_LD_CFG(0x05, 0x8, 0x1, 0x0, 0xa), }, + /* Layer A: HiGig2: */ + [NPC_LT_LA_IH_NIX_HIGIG2_ETHER] = { + /* PF_FUNC: 2B , KW0 [47:32] */ + KEX_LD_CFG(0x01, 0x0, 0x1, 0x0, 0x4), + /* VID: 2 bytes, KW1[31:16] */ + KEX_LD_CFG(0x01, 0x10, 0x1, 0x0, 0xa), + }, }, [NPC_LID_LB] = { /* Layer B: Single VLAN (CTAG) */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index ab24a5e8ee8a..0b092949d7ac 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -57,6 +57,10 @@ static char *mkex_profile; /* MKEX profile name */ module_param(mkex_profile, charp, 0000); MODULE_PARM_DESC(mkex_profile, "MKEX profile name string"); +static char *kpu_profile; /* KPU profile name */ +module_param(kpu_profile, charp, 0000); +MODULE_PARM_DESC(kpu_profile, "KPU profile name string"); + static void rvu_setup_hw_capabilities(struct rvu *rvu) { struct rvu_hwinfo *hw = rvu->hw; @@ -180,6 +184,14 @@ int rvu_rsrc_free_count(struct rsrc_bmap *rsrc) return (rsrc->max - used); } +bool is_rsrc_free(struct rsrc_bmap *rsrc, int id) +{ + if (!rsrc->bmap) + return false; + + return !test_bit(id, rsrc->bmap); +} + int rvu_alloc_bitmap(struct rsrc_bmap *rsrc) { rsrc->bmap = kcalloc(BITS_TO_LONGS(rsrc->max), @@ -1754,6 +1766,48 @@ int rvu_mbox_handler_get_hw_cap(struct rvu *rvu, struct msg_req *req, return 0; } +int rvu_mbox_handler_set_vf_perm(struct rvu *rvu, struct set_vf_perm *req, + struct msg_rsp *rsp) +{ + struct rvu_hwinfo *hw = rvu->hw; + u16 pcifunc = req->hdr.pcifunc; + struct rvu_pfvf *pfvf; + int blkaddr, nixlf; + u16 target; + + /* Only PF can add VF permissions */ + if ((pcifunc & RVU_PFVF_FUNC_MASK) || is_afvf(pcifunc)) + return -EOPNOTSUPP; + + target = (pcifunc & ~RVU_PFVF_FUNC_MASK) | (req->vf + 1); + pfvf = rvu_get_pfvf(rvu, target); + + if (req->flags & RESET_VF_PERM) { + pfvf->flags &= RVU_CLEAR_VF_PERM; + } else if (test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) ^ + (req->flags & VF_TRUSTED)) { + change_bit(PF_SET_VF_TRUSTED, &pfvf->flags); + /* disable multicast and promisc entries */ + if (!test_bit(PF_SET_VF_TRUSTED, &pfvf->flags)) { + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, target); + if (blkaddr < 0) + return 0; + nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], + target, 0); + if (nixlf < 0) + return 0; + npc_enadis_default_mce_entry(rvu, target, nixlf, + NIXLF_ALLMULTI_ENTRY, + false); + npc_enadis_default_mce_entry(rvu, target, nixlf, + NIXLF_PROMISC_ENTRY, + false); + } + } + + return 0; +} + static int rvu_process_mbox_msg(struct otx2_mbox *mbox, int devid, struct mbox_msghdr *req) { @@ -2842,6 +2896,8 @@ static void rvu_update_module_params(struct rvu *rvu) strscpy(rvu->mkex_pfl_name, mkex_profile ? mkex_profile : default_pfl_name, MKEX_NAME_LEN); + strscpy(rvu->kpu_pfl_name, + kpu_profile ? kpu_profile : default_pfl_name, KPU_NAME_LEN); } static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index c2cc4806d13c..9e5d9ba6f01e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -223,13 +223,17 @@ struct rvu_pfvf { u16 maxlen; u16 minlen; - u8 pf_set_vf_cfg; u8 mac_addr[ETH_ALEN]; /* MAC address of this PF/VF */ u8 default_mac[ETH_ALEN]; /* MAC address from FWdata */ - /* Broadcast pkt replication info */ + /* Broadcast/Multicast/Promisc pkt replication info */ u16 bcast_mce_idx; + u16 mcast_mce_idx; + u16 promisc_mce_idx; struct nix_mce_list bcast_mce_list; + struct nix_mce_list mcast_mce_list; + struct nix_mce_list promisc_mce_list; + bool use_mce_list; struct rvu_npc_mcam_rule *def_ucast_rule; @@ -239,8 +243,18 @@ struct rvu_pfvf { u8 nix_blkaddr; /* BLKADDR_NIX0/1 assigned to this PF */ u8 nix_rx_intf; /* NIX0_RX/NIX1_RX interface to NPC */ u8 nix_tx_intf; /* NIX0_TX/NIX1_TX interface to NPC */ + unsigned long flags; }; +enum rvu_pfvf_flags { + NIXLF_INITIALIZED = 0, + PF_SET_VF_MAC, + PF_SET_VF_CFG, + PF_SET_VF_TRUSTED, +}; + +#define RVU_CLEAR_VF_PERM ~GENMASK(PF_SET_VF_TRUSTED, PF_SET_VF_MAC) + struct nix_txsch { struct rsrc_bmap schq; u8 lvl; @@ -282,6 +296,13 @@ struct nix_txvlan { struct mutex rsrc_lock; /* Serialize resource alloc/free */ }; +struct nix_ipolicer { + struct rsrc_bmap band_prof; + u16 *pfvf_map; + u16 *match_id; + u16 *ref_count; +}; + struct nix_hw { int blkaddr; struct rvu *rvu; @@ -291,6 +312,7 @@ struct nix_hw { struct nix_mark_format mark_format; struct nix_lso lso; struct nix_txvlan txvlan; + struct nix_ipolicer *ipolicer; }; /* RVU block's capabilities or functionality, @@ -308,6 +330,7 @@ struct hw_cap { bool nix_rx_multicast; /* Rx packet replication support */ bool per_pf_mbox_regs; /* PF mbox specified in per PF registers ? */ bool programmable_chans; /* Channels programmable ? */ + bool ipolicer; }; struct rvu_hwinfo { @@ -386,6 +409,7 @@ struct npc_kpu_profile_adapter { const struct npc_kpu_profile_action *ikpu; /* array[pkinds] */ const struct npc_kpu_profile *kpu; /* array[kpus] */ struct npc_mcam_kex *mkex; + bool custom; size_t pkinds; size_t kpus; }; @@ -435,9 +459,13 @@ struct rvu { struct mutex cgx_cfg_lock; /* serialize cgx configuration */ char mkex_pfl_name[MKEX_NAME_LEN]; /* Configured MKEX profile name */ + char kpu_pfl_name[KPU_NAME_LEN]; /* Configured KPU profile name */ /* Firmware data */ struct rvu_fwdata *fwdata; + void *kpu_fwdata; + size_t kpu_fwdata_sz; + void __iomem *kpu_prfl_addr; /* NPC KPU data */ struct npc_kpu_profile_adapter kpu; @@ -543,11 +571,16 @@ static inline u16 rvu_nix_chan_cpt(struct rvu *rvu, u8 chan) /* Function Prototypes * RVU */ -static inline int is_afvf(u16 pcifunc) +static inline bool is_afvf(u16 pcifunc) { return !(pcifunc & ~RVU_PFVF_FUNC_MASK); } +static inline bool is_vf(u16 pcifunc) +{ + return !!(pcifunc & RVU_PFVF_FUNC_MASK); +} + /* check if PF_FUNC is AF */ static inline bool is_pffunc_af(u16 pcifunc) { @@ -563,6 +596,7 @@ static inline bool is_rvu_fwdata_valid(struct rvu *rvu) int rvu_alloc_bitmap(struct rsrc_bmap *rsrc); int rvu_alloc_rsrc(struct rsrc_bmap *rsrc); void rvu_free_rsrc(struct rsrc_bmap *rsrc, int id); +bool is_rsrc_free(struct rsrc_bmap *rsrc, int id); int rvu_rsrc_free_count(struct rsrc_bmap *rsrc); int rvu_alloc_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc); bool rvu_rsrc_check_contig(struct rsrc_bmap *rsrc, int nrsrc); @@ -603,6 +637,12 @@ static inline void rvu_get_cgx_lmac_id(u8 map, u8 *cgx_id, u8 *lmac_id) *lmac_id = (map & 0xF); } +static inline bool is_cgx_vf(struct rvu *rvu, u16 pcifunc) +{ + return ((pcifunc & RVU_PFVF_FUNC_MASK) && + is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))); +} + #define M(_name, _id, fn_name, req, rsp) \ int rvu_mbox_handler_ ## fn_name(struct rvu *, struct req *, struct rsp *); MBOX_MESSAGES @@ -632,10 +672,22 @@ void rvu_nix_freemem(struct rvu *rvu); int rvu_get_nixlf_count(struct rvu *rvu); void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf); int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr); -int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add); +int nix_update_mce_list(struct rvu *rvu, u16 pcifunc, + struct nix_mce_list *mce_list, + int mce_idx, int mcam_index, bool add); +void nix_get_mce_list(struct rvu *rvu, u16 pcifunc, int type, + struct nix_mce_list **mce_list, int *mce_idx); struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr); int rvu_get_next_nix_blkaddr(struct rvu *rvu, int blkaddr); void rvu_nix_reset_mac(struct rvu_pfvf *pfvf, int pcifunc); +int nix_get_struct_ptrs(struct rvu *rvu, u16 pcifunc, + struct nix_hw **nix_hw, int *blkaddr); +int rvu_nix_setup_ratelimit_aggr(struct rvu *rvu, u16 pcifunc, + u16 rq_idx, u16 match_id); +int nix_aq_context_read(struct rvu *rvu, struct nix_hw *nix_hw, + struct nix_cn10k_aq_enq_req *aq_req, + struct nix_cn10k_aq_enq_rsp *aq_rsp, + u16 pcifunc, u8 ctype, u32 qidx); /* NPC APIs */ int rvu_npc_init(struct rvu *rvu); @@ -646,13 +698,19 @@ int npc_config_ts_kpuaction(struct rvu *rvu, int pf, u16 pcifunc, bool en); void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u64 chan, u8 *mac_addr); void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, - int nixlf, u64 chan, u8 chan_cnt, - bool allmulti); -void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf); -void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf); + int nixlf, u64 chan, u8 chan_cnt); +void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + bool enable); void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u64 chan); -void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable); +void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + bool enable); +void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + u64 chan); +void rvu_npc_enable_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + bool enable); +void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc, + int nixlf, int type, bool enable); void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_free_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 9bf8eaabf9ab..3cc3c6fd1d84 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -1632,6 +1632,165 @@ static int rvu_dbg_nix_qsize_display(struct seq_file *filp, void *unused) RVU_DEBUG_SEQ_FOPS(nix_qsize, nix_qsize_display, nix_qsize_write); +static void print_band_prof_ctx(struct seq_file *m, + struct nix_bandprof_s *prof) +{ + char *str; + + switch (prof->pc_mode) { + case NIX_RX_PC_MODE_VLAN: + str = "VLAN"; + break; + case NIX_RX_PC_MODE_DSCP: + str = "DSCP"; + break; + case NIX_RX_PC_MODE_GEN: + str = "Generic"; + break; + case NIX_RX_PC_MODE_RSVD: + str = "Reserved"; + break; + } + seq_printf(m, "W0: pc_mode\t\t%s\n", str); + str = (prof->icolor == 3) ? "Color blind" : + (prof->icolor == 0) ? "Green" : + (prof->icolor == 1) ? "Yellow" : "Red"; + seq_printf(m, "W0: icolor\t\t%s\n", str); + seq_printf(m, "W0: tnl_ena\t\t%d\n", prof->tnl_ena); + seq_printf(m, "W0: peir_exponent\t%d\n", prof->peir_exponent); + seq_printf(m, "W0: pebs_exponent\t%d\n", prof->pebs_exponent); + seq_printf(m, "W0: cir_exponent\t%d\n", prof->cir_exponent); + seq_printf(m, "W0: cbs_exponent\t%d\n", prof->cbs_exponent); + seq_printf(m, "W0: peir_mantissa\t%d\n", prof->peir_mantissa); + seq_printf(m, "W0: pebs_mantissa\t%d\n", prof->pebs_mantissa); + seq_printf(m, "W0: cir_mantissa\t%d\n", prof->cir_mantissa); + + seq_printf(m, "W1: cbs_mantissa\t%d\n", prof->cbs_mantissa); + str = (prof->lmode == 0) ? "byte" : "packet"; + seq_printf(m, "W1: lmode\t\t%s\n", str); + seq_printf(m, "W1: l_select\t\t%d\n", prof->l_sellect); + seq_printf(m, "W1: rdiv\t\t%d\n", prof->rdiv); + seq_printf(m, "W1: adjust_exponent\t%d\n", prof->adjust_exponent); + seq_printf(m, "W1: adjust_mantissa\t%d\n", prof->adjust_mantissa); + str = (prof->gc_action == 0) ? "PASS" : + (prof->gc_action == 1) ? "DROP" : "RED"; + seq_printf(m, "W1: gc_action\t\t%s\n", str); + str = (prof->yc_action == 0) ? "PASS" : + (prof->yc_action == 1) ? "DROP" : "RED"; + seq_printf(m, "W1: yc_action\t\t%s\n", str); + str = (prof->rc_action == 0) ? "PASS" : + (prof->rc_action == 1) ? "DROP" : "RED"; + seq_printf(m, "W1: rc_action\t\t%s\n", str); + seq_printf(m, "W1: meter_algo\t\t%d\n", prof->meter_algo); + seq_printf(m, "W1: band_prof_id\t%d\n", prof->band_prof_id); + seq_printf(m, "W1: hl_en\t\t%d\n", prof->hl_en); + + seq_printf(m, "W2: ts\t\t\t%lld\n", (u64)prof->ts); + seq_printf(m, "W3: pe_accum\t\t%d\n", prof->pe_accum); + seq_printf(m, "W3: c_accum\t\t%d\n", prof->c_accum); + seq_printf(m, "W4: green_pkt_pass\t%lld\n", + (u64)prof->green_pkt_pass); + seq_printf(m, "W5: yellow_pkt_pass\t%lld\n", + (u64)prof->yellow_pkt_pass); + seq_printf(m, "W6: red_pkt_pass\t%lld\n", (u64)prof->red_pkt_pass); + seq_printf(m, "W7: green_octs_pass\t%lld\n", + (u64)prof->green_octs_pass); + seq_printf(m, "W8: yellow_octs_pass\t%lld\n", + (u64)prof->yellow_octs_pass); + seq_printf(m, "W9: red_octs_pass\t%lld\n", (u64)prof->red_octs_pass); + seq_printf(m, "W10: green_pkt_drop\t%lld\n", + (u64)prof->green_pkt_drop); + seq_printf(m, "W11: yellow_pkt_drop\t%lld\n", + (u64)prof->yellow_pkt_drop); + seq_printf(m, "W12: red_pkt_drop\t%lld\n", (u64)prof->red_pkt_drop); + seq_printf(m, "W13: green_octs_drop\t%lld\n", + (u64)prof->green_octs_drop); + seq_printf(m, "W14: yellow_octs_drop\t%lld\n", + (u64)prof->yellow_octs_drop); + seq_printf(m, "W15: red_octs_drop\t%lld\n", (u64)prof->red_octs_drop); + seq_puts(m, "==============================\n"); +} + +static int rvu_dbg_nix_band_prof_ctx_display(struct seq_file *m, void *unused) +{ + struct nix_hw *nix_hw = m->private; + struct nix_cn10k_aq_enq_req aq_req; + struct nix_cn10k_aq_enq_rsp aq_rsp; + struct rvu *rvu = nix_hw->rvu; + struct nix_ipolicer *ipolicer; + int layer, prof_idx, idx, rc; + u16 pcifunc; + char *str; + + for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) { + if (layer == BAND_PROF_INVAL_LAYER) + continue; + str = (layer == BAND_PROF_LEAF_LAYER) ? "Leaf" : + (layer == BAND_PROF_MID_LAYER) ? "Mid" : "Top"; + + seq_printf(m, "\n%s bandwidth profiles\n", str); + seq_puts(m, "=======================\n"); + + ipolicer = &nix_hw->ipolicer[layer]; + + for (idx = 0; idx < ipolicer->band_prof.max; idx++) { + if (is_rsrc_free(&ipolicer->band_prof, idx)) + continue; + + prof_idx = (idx & 0x3FFF) | (layer << 14); + rc = nix_aq_context_read(rvu, nix_hw, &aq_req, &aq_rsp, + 0x00, NIX_AQ_CTYPE_BANDPROF, + prof_idx); + if (rc) { + dev_err(rvu->dev, + "%s: Failed to fetch context of %s profile %d, err %d\n", + __func__, str, idx, rc); + return 0; + } + seq_printf(m, "\n%s bandwidth profile:: %d\n", str, idx); + pcifunc = ipolicer->pfvf_map[idx]; + if (!(pcifunc & RVU_PFVF_FUNC_MASK)) + seq_printf(m, "Allocated to :: PF %d\n", + rvu_get_pf(pcifunc)); + else + seq_printf(m, "Allocated to :: PF %d VF %d\n", + rvu_get_pf(pcifunc), + (pcifunc & RVU_PFVF_FUNC_MASK) - 1); + print_band_prof_ctx(m, &aq_rsp.prof); + } + } + return 0; +} + +RVU_DEBUG_SEQ_FOPS(nix_band_prof_ctx, nix_band_prof_ctx_display, NULL); + +static int rvu_dbg_nix_band_prof_rsrc_display(struct seq_file *m, void *unused) +{ + struct nix_hw *nix_hw = m->private; + struct nix_ipolicer *ipolicer; + int layer; + char *str; + + seq_puts(m, "\nBandwidth profile resource free count\n"); + seq_puts(m, "=====================================\n"); + for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) { + if (layer == BAND_PROF_INVAL_LAYER) + continue; + str = (layer == BAND_PROF_LEAF_LAYER) ? "Leaf" : + (layer == BAND_PROF_MID_LAYER) ? "Mid " : "Top "; + + ipolicer = &nix_hw->ipolicer[layer]; + seq_printf(m, "%s :: Max: %4d Free: %4d\n", str, + ipolicer->band_prof.max, + rvu_rsrc_free_count(&ipolicer->band_prof)); + } + seq_puts(m, "=====================================\n"); + + return 0; +} + +RVU_DEBUG_SEQ_FOPS(nix_band_prof_rsrc, nix_band_prof_rsrc_display, NULL); + static void rvu_dbg_nix_init(struct rvu *rvu, int blkaddr) { struct nix_hw *nix_hw; @@ -1664,6 +1823,10 @@ static void rvu_dbg_nix_init(struct rvu *rvu, int blkaddr) &rvu_dbg_nix_ndc_rx_hits_miss_fops); debugfs_create_file("qsize", 0600, rvu->rvu_dbg.nix, rvu, &rvu_dbg_nix_qsize_fops); + debugfs_create_file("ingress_policer_ctx", 0600, rvu->rvu_dbg.nix, nix_hw, + &rvu_dbg_nix_band_prof_ctx_fops); + debugfs_create_file("ingress_policer_rsrc", 0600, rvu->rvu_dbg.nix, nix_hw, + &rvu_dbg_nix_band_prof_rsrc_fops); } static void rvu_dbg_npa_init(struct rvu *rvu) @@ -2132,6 +2295,7 @@ static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused) struct rvu *rvu = s->private; struct npc_mcam *mcam; int pf, vf = -1; + bool enabled; int blkaddr; u16 target; u64 hits; @@ -2173,7 +2337,9 @@ static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused) } rvu_dbg_npc_mcam_show_action(s, iter); - seq_printf(s, "\tenabled: %s\n", iter->enable ? "yes" : "no"); + + enabled = is_mcam_entry_enabled(rvu, mcam, blkaddr, iter->entry); + seq_printf(s, "\tenabled: %s\n", enabled ? "yes" : "no"); if (!iter->has_cntr) continue; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 0a8bd667cb11..d6f8210652c5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -21,6 +21,16 @@ static void nix_free_tx_vtag_entries(struct rvu *rvu, u16 pcifunc); static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req, int type, int chan_id); +static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc, + int type, bool add); +static int nix_setup_ipolicers(struct rvu *rvu, + struct nix_hw *nix_hw, int blkaddr); +static void nix_ipolicer_freemem(struct nix_hw *nix_hw); +static int nix_verify_bandprof(struct nix_cn10k_aq_enq_req *req, + struct nix_hw *nix_hw, u16 pcifunc); +static int nix_free_all_bandprof(struct rvu *rvu, u16 pcifunc); +static void nix_clear_ratelimit_aggr(struct rvu *rvu, struct nix_hw *nix_hw, + u32 leaf_prof); enum mc_tbl_sz { MC_TBL_SZ_256, @@ -132,6 +142,22 @@ int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr) return 0; } +int nix_get_struct_ptrs(struct rvu *rvu, u16 pcifunc, + struct nix_hw **nix_hw, int *blkaddr) +{ + struct rvu_pfvf *pfvf; + + pfvf = rvu_get_pfvf(rvu, pcifunc); + *blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); + if (!pfvf->nixlf || *blkaddr < 0) + return NIX_AF_ERR_AF_LF_INVALID; + + *nix_hw = get_nix_hw(rvu->hw, *blkaddr); + if (!*nix_hw) + return NIX_AF_ERR_INVALID_NIXBLK; + return 0; +} + static void nix_mce_list_init(struct nix_mce_list *list, int max) { INIT_HLIST_HEAD(&list->head); @@ -274,7 +300,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf) pfvf->tx_chan_cnt = 1; rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base, - pfvf->rx_chan_cnt, false); + pfvf->rx_chan_cnt); break; } @@ -285,16 +311,17 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf) pfvf->rx_chan_base, pfvf->mac_addr); /* Add this PF_FUNC to bcast pkt replication list */ - err = nix_update_bcast_mce_list(rvu, pcifunc, true); + err = nix_update_mce_rule(rvu, pcifunc, NIXLF_BCAST_ENTRY, true); if (err) { dev_err(rvu->dev, "Bcast list, failed to enable PF_FUNC 0x%x\n", pcifunc); return err; } - + /* Install MCAM rule matching Ethernet broadcast mac address */ rvu_npc_install_bcast_match_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base); + pfvf->maxlen = NIC_HW_MIN_FRS; pfvf->minlen = NIC_HW_MIN_FRS; @@ -310,7 +337,7 @@ static void nix_interface_deinit(struct rvu *rvu, u16 pcifunc, u8 nixlf) pfvf->minlen = 0; /* Remove this PF_FUNC from bcast pkt replication list */ - err = nix_update_bcast_mce_list(rvu, pcifunc, false); + err = nix_update_mce_rule(rvu, pcifunc, NIXLF_BCAST_ENTRY, false); if (err) { dev_err(rvu->dev, "Bcast list, failed to disable PF_FUNC 0x%x\n", @@ -680,8 +707,11 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw, pfvf = rvu_get_pfvf(rvu, pcifunc); nixlf = rvu_get_lf(rvu, block, pcifunc, 0); - /* Skip NIXLF check for broadcast MCE entry init */ - if (!(!rsp && req->ctype == NIX_AQ_CTYPE_MCE)) { + /* Skip NIXLF check for broadcast MCE entry and bandwidth profile + * operations done by AF itself. + */ + if (!((!rsp && req->ctype == NIX_AQ_CTYPE_MCE) || + (req->ctype == NIX_AQ_CTYPE_BANDPROF && !pcifunc))) { if (!pfvf->nixlf || nixlf < 0) return NIX_AF_ERR_AF_LF_INVALID; } @@ -721,6 +751,11 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw, if (rsp) rc = NIX_AF_ERR_AQ_ENQUEUE; break; + case NIX_AQ_CTYPE_BANDPROF: + if (nix_verify_bandprof((struct nix_cn10k_aq_enq_req *)req, + nix_hw, pcifunc)) + rc = NIX_AF_ERR_INVALID_BANDPROF; + break; default: rc = NIX_AF_ERR_AQ_ENQUEUE; } @@ -777,6 +812,9 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw, else if (req->ctype == NIX_AQ_CTYPE_MCE) memcpy(mask, &req->mce_mask, sizeof(struct nix_rx_mce_s)); + else if (req->ctype == NIX_AQ_CTYPE_BANDPROF) + memcpy(mask, &req->prof_mask, + sizeof(struct nix_bandprof_s)); fallthrough; case NIX_AQ_INSTOP_INIT: if (req->ctype == NIX_AQ_CTYPE_RQ) @@ -789,6 +827,8 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw, memcpy(ctx, &req->rss, sizeof(struct nix_rsse_s)); else if (req->ctype == NIX_AQ_CTYPE_MCE) memcpy(ctx, &req->mce, sizeof(struct nix_rx_mce_s)); + else if (req->ctype == NIX_AQ_CTYPE_BANDPROF) + memcpy(ctx, &req->prof, sizeof(struct nix_bandprof_s)); break; case NIX_AQ_INSTOP_NOP: case NIX_AQ_INSTOP_READ: @@ -866,6 +906,9 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw, else if (req->ctype == NIX_AQ_CTYPE_MCE) memcpy(&rsp->mce, ctx, sizeof(struct nix_rx_mce_s)); + else if (req->ctype == NIX_AQ_CTYPE_BANDPROF) + memcpy(&rsp->prof, ctx, + sizeof(struct nix_bandprof_s)); } } @@ -2203,8 +2246,8 @@ static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw, aq_req.op = op; aq_req.qidx = mce; - /* Forward bcast pkts to RQ0, RSS not needed */ - aq_req.mce.op = 0; + /* Use RSS with RSS index 0 */ + aq_req.mce.op = 1; aq_req.mce.index = 0; aq_req.mce.eol = eol; aq_req.mce.pf_func = pcifunc; @@ -2222,8 +2265,8 @@ static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw, return 0; } -static int nix_update_mce_list(struct nix_mce_list *mce_list, - u16 pcifunc, bool add) +static int nix_update_mce_list_entry(struct nix_mce_list *mce_list, + u16 pcifunc, bool add) { struct mce *mce, *tail = NULL; bool delete = false; @@ -2234,6 +2277,9 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list, if (mce->pcifunc == pcifunc && !add) { delete = true; break; + } else if (mce->pcifunc == pcifunc && add) { + /* entry already exists */ + return 0; } tail = mce; } @@ -2261,36 +2307,23 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list, return 0; } -int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add) +int nix_update_mce_list(struct rvu *rvu, u16 pcifunc, + struct nix_mce_list *mce_list, + int mce_idx, int mcam_index, bool add) { - int err = 0, idx, next_idx, last_idx; - struct nix_mce_list *mce_list; + int err = 0, idx, next_idx, last_idx, blkaddr, npc_blkaddr; + struct npc_mcam *mcam = &rvu->hw->mcam; struct nix_mcast *mcast; struct nix_hw *nix_hw; - struct rvu_pfvf *pfvf; struct mce *mce; - int blkaddr; - /* Broadcast pkt replication is not needed for AF's VFs, hence skip */ - if (is_afvf(pcifunc)) - return 0; - - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); - if (blkaddr < 0) - return 0; - - nix_hw = get_nix_hw(rvu->hw, blkaddr); - if (!nix_hw) - return 0; - - mcast = &nix_hw->mcast; + if (!mce_list) + return -EINVAL; /* Get this PF/VF func's MCE index */ - pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK); - idx = pfvf->bcast_mce_idx + (pcifunc & RVU_PFVF_FUNC_MASK); + idx = mce_idx + (pcifunc & RVU_PFVF_FUNC_MASK); - mce_list = &pfvf->bcast_mce_list; - if (idx > (pfvf->bcast_mce_idx + mce_list->max)) { + if (idx > (mce_idx + mce_list->max)) { dev_err(rvu->dev, "%s: Idx %d > max MCE idx %d, for PF%d bcast list\n", __func__, idx, mce_list->max, @@ -2298,20 +2331,26 @@ int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add) return -EINVAL; } + err = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr); + if (err) + return err; + + mcast = &nix_hw->mcast; mutex_lock(&mcast->mce_lock); - err = nix_update_mce_list(mce_list, pcifunc, add); + err = nix_update_mce_list_entry(mce_list, pcifunc, add); if (err) goto end; /* Disable MCAM entry in NPC */ if (!mce_list->count) { - rvu_npc_enable_bcast_entry(rvu, pcifunc, false); + npc_blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); + npc_enable_mcam_entry(rvu, mcam, npc_blkaddr, mcam_index, false); goto end; } /* Dump the updated list to HW */ - idx = pfvf->bcast_mce_idx; + idx = mce_idx; last_idx = idx + mce_list->count - 1; hlist_for_each_entry(mce, &mce_list->head, node) { if (idx > last_idx) @@ -2332,7 +2371,71 @@ end: return err; } -static int nix_setup_bcast_tables(struct rvu *rvu, struct nix_hw *nix_hw) +void nix_get_mce_list(struct rvu *rvu, u16 pcifunc, int type, + struct nix_mce_list **mce_list, int *mce_idx) +{ + struct rvu_hwinfo *hw = rvu->hw; + struct rvu_pfvf *pfvf; + + if (!hw->cap.nix_rx_multicast || + !is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc & ~RVU_PFVF_FUNC_MASK))) { + *mce_list = NULL; + *mce_idx = 0; + return; + } + + /* Get this PF/VF func's MCE index */ + pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK); + + if (type == NIXLF_BCAST_ENTRY) { + *mce_list = &pfvf->bcast_mce_list; + *mce_idx = pfvf->bcast_mce_idx; + } else if (type == NIXLF_ALLMULTI_ENTRY) { + *mce_list = &pfvf->mcast_mce_list; + *mce_idx = pfvf->mcast_mce_idx; + } else if (type == NIXLF_PROMISC_ENTRY) { + *mce_list = &pfvf->promisc_mce_list; + *mce_idx = pfvf->promisc_mce_idx; + } else { + *mce_list = NULL; + *mce_idx = 0; + } +} + +static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc, + int type, bool add) +{ + int err = 0, nixlf, blkaddr, mcam_index, mce_idx; + struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; + struct nix_mce_list *mce_list; + + /* skip multicast pkt replication for AF's VFs */ + if (is_afvf(pcifunc)) + return 0; + + if (!hw->cap.nix_rx_multicast) + return 0; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); + if (blkaddr < 0) + return -EINVAL; + + nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0); + if (nixlf < 0) + return -EINVAL; + + nix_get_mce_list(rvu, pcifunc, type, &mce_list, &mce_idx); + + mcam_index = npc_get_nixlf_mcam_index(mcam, + pcifunc & ~RVU_PFVF_FUNC_MASK, + nixlf, type); + err = nix_update_mce_list(rvu, pcifunc, mce_list, + mce_idx, mcam_index, add); + return err; +} + +static int nix_setup_mce_tables(struct rvu *rvu, struct nix_hw *nix_hw) { struct nix_mcast *mcast = &nix_hw->mcast; int err, pf, numvfs, idx; @@ -2355,11 +2458,18 @@ static int nix_setup_bcast_tables(struct rvu *rvu, struct nix_hw *nix_hw) if (pfvf->nix_blkaddr != nix_hw->blkaddr) continue; - /* Save the start MCE */ + /* save start idx of broadcast mce list */ pfvf->bcast_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1); - nix_mce_list_init(&pfvf->bcast_mce_list, numvfs + 1); + /* save start idx of multicast mce list */ + pfvf->mcast_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1); + nix_mce_list_init(&pfvf->mcast_mce_list, numvfs + 1); + + /* save the start idx of promisc mce list */ + pfvf->promisc_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1); + nix_mce_list_init(&pfvf->promisc_mce_list, numvfs + 1); + for (idx = 0; idx < (numvfs + 1); idx++) { /* idx-0 is for PF, followed by VFs */ pcifunc = (pf << RVU_PFVF_PF_SHIFT); @@ -2375,6 +2485,22 @@ static int nix_setup_bcast_tables(struct rvu *rvu, struct nix_hw *nix_hw) pcifunc, 0, true); if (err) return err; + + /* add dummy entries to multicast mce list */ + err = nix_blk_setup_mce(rvu, nix_hw, + pfvf->mcast_mce_idx + idx, + NIX_AQ_INSTOP_INIT, + pcifunc, 0, true); + if (err) + return err; + + /* add dummy entries to promisc mce list */ + err = nix_blk_setup_mce(rvu, nix_hw, + pfvf->promisc_mce_idx + idx, + NIX_AQ_INSTOP_INIT, + pcifunc, 0, true); + if (err) + return err; } } return 0; @@ -2421,7 +2547,7 @@ static int nix_setup_mcast(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr) mutex_init(&mcast->mce_lock); - return nix_setup_bcast_tables(rvu, nix_hw); + return nix_setup_mce_tables(rvu, nix_hw); } static int nix_setup_txvlan(struct rvu *rvu, struct nix_hw *nix_hw) @@ -3035,15 +3161,22 @@ int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu, pfvf = rvu_get_pfvf(rvu, pcifunc); - /* VF can't overwrite admin(PF) changes */ - if (from_vf && pfvf->pf_set_vf_cfg) + /* untrusted VF can't overwrite admin(PF) changes */ + if (!test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) && + (from_vf && test_bit(PF_SET_VF_MAC, &pfvf->flags))) { + dev_warn(rvu->dev, + "MAC address set by admin(PF) cannot be overwritten by untrusted VF"); return -EPERM; + } ether_addr_copy(pfvf->mac_addr, req->mac_addr); rvu_npc_install_ucast_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base, req->mac_addr); + if (test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) && from_vf) + ether_addr_copy(pfvf->default_mac, req->mac_addr); + return 0; } @@ -3067,30 +3200,75 @@ int rvu_mbox_handler_nix_get_mac_addr(struct rvu *rvu, int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req, struct msg_rsp *rsp) { - bool allmulti = false, disable_promisc = false; + bool allmulti, promisc, nix_rx_multicast; u16 pcifunc = req->hdr.pcifunc; - int blkaddr, nixlf, err; struct rvu_pfvf *pfvf; + int nixlf, err; - err = nix_get_nixlf(rvu, pcifunc, &nixlf, &blkaddr); + pfvf = rvu_get_pfvf(rvu, pcifunc); + promisc = req->mode & NIX_RX_MODE_PROMISC ? true : false; + allmulti = req->mode & NIX_RX_MODE_ALLMULTI ? true : false; + pfvf->use_mce_list = req->mode & NIX_RX_MODE_USE_MCE ? true : false; + + nix_rx_multicast = rvu->hw->cap.nix_rx_multicast & pfvf->use_mce_list; + + if (is_vf(pcifunc) && !nix_rx_multicast && + (promisc || allmulti)) { + dev_warn_ratelimited(rvu->dev, + "VF promisc/multicast not supported\n"); + return 0; + } + + /* untrusted VF can't configure promisc/allmulti */ + if (is_vf(pcifunc) && !test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) && + (promisc || allmulti)) + return 0; + + err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL); if (err) return err; - pfvf = rvu_get_pfvf(rvu, pcifunc); + if (nix_rx_multicast) { + /* add/del this PF_FUNC to/from mcast pkt replication list */ + err = nix_update_mce_rule(rvu, pcifunc, NIXLF_ALLMULTI_ENTRY, + allmulti); + if (err) { + dev_err(rvu->dev, + "Failed to update pcifunc 0x%x to multicast list\n", + pcifunc); + return err; + } - if (req->mode & NIX_RX_MODE_PROMISC) - allmulti = false; - else if (req->mode & NIX_RX_MODE_ALLMULTI) - allmulti = true; - else - disable_promisc = true; + /* add/del this PF_FUNC to/from promisc pkt replication list */ + err = nix_update_mce_rule(rvu, pcifunc, NIXLF_PROMISC_ENTRY, + promisc); + if (err) { + dev_err(rvu->dev, + "Failed to update pcifunc 0x%x to promisc list\n", + pcifunc); + return err; + } + } - if (disable_promisc) - rvu_npc_disable_promisc_entry(rvu, pcifunc, nixlf); - else + /* install/uninstall allmulti entry */ + if (allmulti) { + rvu_npc_install_allmulti_entry(rvu, pcifunc, nixlf, + pfvf->rx_chan_base); + } else { + if (!nix_rx_multicast) + rvu_npc_enable_allmulti_entry(rvu, pcifunc, nixlf, false); + } + + /* install/uninstall promisc entry */ + if (promisc) { rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base, - pfvf->rx_chan_cnt, allmulti); + pfvf->rx_chan_cnt); + } else { + if (!nix_rx_multicast) + rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf, false); + } + return 0; } @@ -3470,6 +3648,10 @@ static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw) if (err) return err; + err = nix_setup_ipolicers(rvu, nix_hw, blkaddr); + if (err) + return err; + err = nix_af_mark_format_setup(rvu, nix_hw, blkaddr); if (err) return err; @@ -3523,6 +3705,40 @@ static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw) (ltdefs->rx_isctp.lid << 8) | (ltdefs->rx_isctp.ltype_match << 4) | ltdefs->rx_isctp.ltype_mask); + if (!is_rvu_otx2(rvu)) { + /* Enable APAD calculation for other protocols + * matching APAD0 and APAD1 lt def registers. + */ + rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_CST_APAD0, + (ltdefs->rx_apad0.valid << 11) | + (ltdefs->rx_apad0.lid << 8) | + (ltdefs->rx_apad0.ltype_match << 4) | + ltdefs->rx_apad0.ltype_mask); + rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_CST_APAD1, + (ltdefs->rx_apad1.valid << 11) | + (ltdefs->rx_apad1.lid << 8) | + (ltdefs->rx_apad1.ltype_match << 4) | + ltdefs->rx_apad1.ltype_mask); + + /* Receive ethertype defination register defines layer + * information in NPC_RESULT_S to identify the Ethertype + * location in L2 header. Used for Ethertype overwriting + * in inline IPsec flow. + */ + rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_ET(0), + (ltdefs->rx_et[0].offset << 12) | + (ltdefs->rx_et[0].valid << 11) | + (ltdefs->rx_et[0].lid << 8) | + (ltdefs->rx_et[0].ltype_match << 4) | + ltdefs->rx_et[0].ltype_mask); + rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_ET(1), + (ltdefs->rx_et[1].offset << 12) | + (ltdefs->rx_et[1].valid << 11) | + (ltdefs->rx_et[1].lid << 8) | + (ltdefs->rx_et[1].ltype_match << 4) | + ltdefs->rx_et[1].ltype_mask); + } + err = nix_rx_flowkey_alg_cfg(rvu, blkaddr); if (err) return err; @@ -3584,6 +3800,8 @@ static void rvu_nix_block_freemem(struct rvu *rvu, int blkaddr, kfree(txsch->schq.bmap); } + nix_ipolicer_freemem(nix_hw); + vlan = &nix_hw->txvlan; kfree(vlan->rsrc.bmap); mutex_destroy(&vlan->rsrc_lock); @@ -3614,6 +3832,7 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { u16 pcifunc = req->hdr.pcifunc; + struct rvu_pfvf *pfvf; int nixlf, err; err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL); @@ -3624,6 +3843,9 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req, npc_mcam_enable_flows(rvu, pcifunc); + pfvf = rvu_get_pfvf(rvu, pcifunc); + set_bit(NIXLF_INITIALIZED, &pfvf->flags); + return rvu_cgx_start_stop_io(rvu, pcifunc, true); } @@ -3631,6 +3853,7 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { u16 pcifunc = req->hdr.pcifunc; + struct rvu_pfvf *pfvf; int nixlf, err; err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL); @@ -3639,6 +3862,9 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, rvu_npc_disable_mcam_entries(rvu, pcifunc, nixlf); + pfvf = rvu_get_pfvf(rvu, pcifunc); + clear_bit(NIXLF_INITIALIZED, &pfvf->flags); + return rvu_cgx_start_stop_io(rvu, pcifunc, false); } @@ -3657,6 +3883,8 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) nix_rx_sync(rvu, blkaddr); nix_txschq_free(rvu, pcifunc); + clear_bit(NIXLF_INITIALIZED, &pfvf->flags); + rvu_cgx_start_stop_io(rvu, pcifunc, false); if (pfvf->sq_ctx) { @@ -3681,6 +3909,8 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) } nix_ctx_free(rvu, pfvf); + + nix_free_all_bandprof(rvu, pcifunc); } #define NIX_AF_LFX_TX_CFG_PTP_EN BIT_ULL(32) @@ -3789,3 +4019,586 @@ void rvu_nix_reset_mac(struct rvu_pfvf *pfvf, int pcifunc) if (from_vf) ether_addr_copy(pfvf->mac_addr, pfvf->default_mac); } + +/* NIX ingress policers or bandwidth profiles APIs */ +static void nix_config_rx_pkt_policer_precolor(struct rvu *rvu, int blkaddr) +{ + struct npc_lt_def_cfg defs, *ltdefs; + + ltdefs = &defs; + memcpy(ltdefs, rvu->kpu.lt_def, sizeof(struct npc_lt_def_cfg)); + + /* Extract PCP and DEI fields from outer VLAN from byte offset + * 2 from the start of LB_PTR (ie TAG). + * VLAN0 is Outer VLAN and VLAN1 is Inner VLAN. Inner VLAN + * fields are considered when 'Tunnel enable' is set in profile. + */ + rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_VLAN0_PCP_DEI, + (2UL << 12) | (ltdefs->ovlan.lid << 8) | + (ltdefs->ovlan.ltype_match << 4) | + ltdefs->ovlan.ltype_mask); + rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_VLAN1_PCP_DEI, + (2UL << 12) | (ltdefs->ivlan.lid << 8) | + (ltdefs->ivlan.ltype_match << 4) | + ltdefs->ivlan.ltype_mask); + + /* DSCP field in outer and tunneled IPv4 packets */ + rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OIP4_DSCP, + (1UL << 12) | (ltdefs->rx_oip4.lid << 8) | + (ltdefs->rx_oip4.ltype_match << 4) | + ltdefs->rx_oip4.ltype_mask); + rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IIP4_DSCP, + (1UL << 12) | (ltdefs->rx_iip4.lid << 8) | + (ltdefs->rx_iip4.ltype_match << 4) | + ltdefs->rx_iip4.ltype_mask); + + /* DSCP field (traffic class) in outer and tunneled IPv6 packets */ + rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OIP6_DSCP, + (1UL << 11) | (ltdefs->rx_oip6.lid << 8) | + (ltdefs->rx_oip6.ltype_match << 4) | + ltdefs->rx_oip6.ltype_mask); + rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IIP6_DSCP, + (1UL << 11) | (ltdefs->rx_iip6.lid << 8) | + (ltdefs->rx_iip6.ltype_match << 4) | + ltdefs->rx_iip6.ltype_mask); +} + +static int nix_init_policer_context(struct rvu *rvu, struct nix_hw *nix_hw, + int layer, int prof_idx) +{ + struct nix_cn10k_aq_enq_req aq_req; + int rc; + + memset(&aq_req, 0, sizeof(struct nix_cn10k_aq_enq_req)); + + aq_req.qidx = (prof_idx & 0x3FFF) | (layer << 14); + aq_req.ctype = NIX_AQ_CTYPE_BANDPROF; + aq_req.op = NIX_AQ_INSTOP_INIT; + + /* Context is all zeros, submit to AQ */ + rc = rvu_nix_blk_aq_enq_inst(rvu, nix_hw, + (struct nix_aq_enq_req *)&aq_req, NULL); + if (rc) + dev_err(rvu->dev, "Failed to INIT bandwidth profile layer %d profile %d\n", + layer, prof_idx); + return rc; +} + +static int nix_setup_ipolicers(struct rvu *rvu, + struct nix_hw *nix_hw, int blkaddr) +{ + struct rvu_hwinfo *hw = rvu->hw; + struct nix_ipolicer *ipolicer; + int err, layer, prof_idx; + u64 cfg; + + cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST); + if (!(cfg & BIT_ULL(61))) { + hw->cap.ipolicer = false; + return 0; + } + + hw->cap.ipolicer = true; + nix_hw->ipolicer = devm_kcalloc(rvu->dev, BAND_PROF_NUM_LAYERS, + sizeof(*ipolicer), GFP_KERNEL); + if (!nix_hw->ipolicer) + return -ENOMEM; + + cfg = rvu_read64(rvu, blkaddr, NIX_AF_PL_CONST); + + for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) { + ipolicer = &nix_hw->ipolicer[layer]; + switch (layer) { + case BAND_PROF_LEAF_LAYER: + ipolicer->band_prof.max = cfg & 0XFFFF; + break; + case BAND_PROF_MID_LAYER: + ipolicer->band_prof.max = (cfg >> 16) & 0XFFFF; + break; + case BAND_PROF_TOP_LAYER: + ipolicer->band_prof.max = (cfg >> 32) & 0XFFFF; + break; + } + + if (!ipolicer->band_prof.max) + continue; + + err = rvu_alloc_bitmap(&ipolicer->band_prof); + if (err) + return err; + + ipolicer->pfvf_map = devm_kcalloc(rvu->dev, + ipolicer->band_prof.max, + sizeof(u16), GFP_KERNEL); + if (!ipolicer->pfvf_map) + return -ENOMEM; + + ipolicer->match_id = devm_kcalloc(rvu->dev, + ipolicer->band_prof.max, + sizeof(u16), GFP_KERNEL); + if (!ipolicer->match_id) + return -ENOMEM; + + for (prof_idx = 0; + prof_idx < ipolicer->band_prof.max; prof_idx++) { + /* Set AF as current owner for INIT ops to succeed */ + ipolicer->pfvf_map[prof_idx] = 0x00; + + /* There is no enable bit in the profile context, + * so no context disable. So let's INIT them here + * so that PF/VF later on have to just do WRITE to + * setup policer rates and config. + */ + err = nix_init_policer_context(rvu, nix_hw, + layer, prof_idx); + if (err) + return err; + } + + /* Allocate memory for maintaining ref_counts for MID level + * profiles, this will be needed for leaf layer profiles' + * aggregation. + */ + if (layer != BAND_PROF_MID_LAYER) + continue; + + ipolicer->ref_count = devm_kcalloc(rvu->dev, + ipolicer->band_prof.max, + sizeof(u16), GFP_KERNEL); + } + + /* Set policer timeunit to 2us ie (19 + 1) * 100 nsec = 2us */ + rvu_write64(rvu, blkaddr, NIX_AF_PL_TS, 19); + + nix_config_rx_pkt_policer_precolor(rvu, blkaddr); + + return 0; +} + +static void nix_ipolicer_freemem(struct nix_hw *nix_hw) +{ + struct nix_ipolicer *ipolicer; + int layer; + + for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) { + ipolicer = &nix_hw->ipolicer[layer]; + + if (!ipolicer->band_prof.max) + continue; + + kfree(ipolicer->band_prof.bmap); + } +} + +static int nix_verify_bandprof(struct nix_cn10k_aq_enq_req *req, + struct nix_hw *nix_hw, u16 pcifunc) +{ + struct nix_ipolicer *ipolicer; + int layer, hi_layer, prof_idx; + + /* Bits [15:14] in profile index represent layer */ + layer = (req->qidx >> 14) & 0x03; + prof_idx = req->qidx & 0x3FFF; + + ipolicer = &nix_hw->ipolicer[layer]; + if (prof_idx >= ipolicer->band_prof.max) + return -EINVAL; + + /* Check if the profile is allocated to the requesting PCIFUNC or not + * with the exception of AF. AF is allowed to read and update contexts. + */ + if (pcifunc && ipolicer->pfvf_map[prof_idx] != pcifunc) + return -EINVAL; + + /* If this profile is linked to higher layer profile then check + * if that profile is also allocated to the requesting PCIFUNC + * or not. + */ + if (!req->prof.hl_en) + return 0; + + /* Leaf layer profile can link only to mid layer and + * mid layer to top layer. + */ + if (layer == BAND_PROF_LEAF_LAYER) + hi_layer = BAND_PROF_MID_LAYER; + else if (layer == BAND_PROF_MID_LAYER) + hi_layer = BAND_PROF_TOP_LAYER; + else + return -EINVAL; + + ipolicer = &nix_hw->ipolicer[hi_layer]; + prof_idx = req->prof.band_prof_id; + if (prof_idx >= ipolicer->band_prof.max || + ipolicer->pfvf_map[prof_idx] != pcifunc) + return -EINVAL; + + return 0; +} + +int rvu_mbox_handler_nix_bandprof_alloc(struct rvu *rvu, + struct nix_bandprof_alloc_req *req, + struct nix_bandprof_alloc_rsp *rsp) +{ + int blkaddr, layer, prof, idx, err; + u16 pcifunc = req->hdr.pcifunc; + struct nix_ipolicer *ipolicer; + struct nix_hw *nix_hw; + + if (!rvu->hw->cap.ipolicer) + return NIX_AF_ERR_IPOLICER_NOTSUPP; + + err = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr); + if (err) + return err; + + mutex_lock(&rvu->rsrc_lock); + for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) { + if (layer == BAND_PROF_INVAL_LAYER) + continue; + if (!req->prof_count[layer]) + continue; + + ipolicer = &nix_hw->ipolicer[layer]; + for (idx = 0; idx < req->prof_count[layer]; idx++) { + /* Allocate a max of 'MAX_BANDPROF_PER_PFFUNC' profiles */ + if (idx == MAX_BANDPROF_PER_PFFUNC) + break; + + prof = rvu_alloc_rsrc(&ipolicer->band_prof); + if (prof < 0) + break; + rsp->prof_count[layer]++; + rsp->prof_idx[layer][idx] = prof; + ipolicer->pfvf_map[prof] = pcifunc; + } + } + mutex_unlock(&rvu->rsrc_lock); + return 0; +} + +static int nix_free_all_bandprof(struct rvu *rvu, u16 pcifunc) +{ + int blkaddr, layer, prof_idx, err; + struct nix_ipolicer *ipolicer; + struct nix_hw *nix_hw; + + if (!rvu->hw->cap.ipolicer) + return NIX_AF_ERR_IPOLICER_NOTSUPP; + + err = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr); + if (err) + return err; + + mutex_lock(&rvu->rsrc_lock); + /* Free all the profiles allocated to the PCIFUNC */ + for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) { + if (layer == BAND_PROF_INVAL_LAYER) + continue; + ipolicer = &nix_hw->ipolicer[layer]; + + for (prof_idx = 0; prof_idx < ipolicer->band_prof.max; prof_idx++) { + if (ipolicer->pfvf_map[prof_idx] != pcifunc) + continue; + + /* Clear ratelimit aggregation, if any */ + if (layer == BAND_PROF_LEAF_LAYER && + ipolicer->match_id[prof_idx]) + nix_clear_ratelimit_aggr(rvu, nix_hw, prof_idx); + + ipolicer->pfvf_map[prof_idx] = 0x00; + ipolicer->match_id[prof_idx] = 0; + rvu_free_rsrc(&ipolicer->band_prof, prof_idx); + } + } + mutex_unlock(&rvu->rsrc_lock); + return 0; +} + +int rvu_mbox_handler_nix_bandprof_free(struct rvu *rvu, + struct nix_bandprof_free_req *req, + struct msg_rsp *rsp) +{ + int blkaddr, layer, prof_idx, idx, err; + u16 pcifunc = req->hdr.pcifunc; + struct nix_ipolicer *ipolicer; + struct nix_hw *nix_hw; + + if (req->free_all) + return nix_free_all_bandprof(rvu, pcifunc); + + if (!rvu->hw->cap.ipolicer) + return NIX_AF_ERR_IPOLICER_NOTSUPP; + + err = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr); + if (err) + return err; + + mutex_lock(&rvu->rsrc_lock); + /* Free the requested profile indices */ + for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) { + if (layer == BAND_PROF_INVAL_LAYER) + continue; + if (!req->prof_count[layer]) + continue; + + ipolicer = &nix_hw->ipolicer[layer]; + for (idx = 0; idx < req->prof_count[layer]; idx++) { + prof_idx = req->prof_idx[layer][idx]; + if (prof_idx >= ipolicer->band_prof.max || + ipolicer->pfvf_map[prof_idx] != pcifunc) + continue; + + /* Clear ratelimit aggregation, if any */ + if (layer == BAND_PROF_LEAF_LAYER && + ipolicer->match_id[prof_idx]) + nix_clear_ratelimit_aggr(rvu, nix_hw, prof_idx); + + ipolicer->pfvf_map[prof_idx] = 0x00; + ipolicer->match_id[prof_idx] = 0; + rvu_free_rsrc(&ipolicer->band_prof, prof_idx); + if (idx == MAX_BANDPROF_PER_PFFUNC) + break; + } + } + mutex_unlock(&rvu->rsrc_lock); + return 0; +} + +int nix_aq_context_read(struct rvu *rvu, struct nix_hw *nix_hw, + struct nix_cn10k_aq_enq_req *aq_req, + struct nix_cn10k_aq_enq_rsp *aq_rsp, + u16 pcifunc, u8 ctype, u32 qidx) +{ + memset(aq_req, 0, sizeof(struct nix_cn10k_aq_enq_req)); + aq_req->hdr.pcifunc = pcifunc; + aq_req->ctype = ctype; + aq_req->op = NIX_AQ_INSTOP_READ; + aq_req->qidx = qidx; + + return rvu_nix_blk_aq_enq_inst(rvu, nix_hw, + (struct nix_aq_enq_req *)aq_req, + (struct nix_aq_enq_rsp *)aq_rsp); +} + +static int nix_ipolicer_map_leaf_midprofs(struct rvu *rvu, + struct nix_hw *nix_hw, + struct nix_cn10k_aq_enq_req *aq_req, + struct nix_cn10k_aq_enq_rsp *aq_rsp, + u32 leaf_prof, u16 mid_prof) +{ + memset(aq_req, 0, sizeof(struct nix_cn10k_aq_enq_req)); + aq_req->hdr.pcifunc = 0x00; + aq_req->ctype = NIX_AQ_CTYPE_BANDPROF; + aq_req->op = NIX_AQ_INSTOP_WRITE; + aq_req->qidx = leaf_prof; + + aq_req->prof.band_prof_id = mid_prof; + aq_req->prof_mask.band_prof_id = GENMASK(6, 0); + aq_req->prof.hl_en = 1; + aq_req->prof_mask.hl_en = 1; + + return rvu_nix_blk_aq_enq_inst(rvu, nix_hw, + (struct nix_aq_enq_req *)aq_req, + (struct nix_aq_enq_rsp *)aq_rsp); +} + +int rvu_nix_setup_ratelimit_aggr(struct rvu *rvu, u16 pcifunc, + u16 rq_idx, u16 match_id) +{ + int leaf_prof, mid_prof, leaf_match; + struct nix_cn10k_aq_enq_req aq_req; + struct nix_cn10k_aq_enq_rsp aq_rsp; + struct nix_ipolicer *ipolicer; + struct nix_hw *nix_hw; + int blkaddr, idx, rc; + + if (!rvu->hw->cap.ipolicer) + return 0; + + rc = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr); + if (rc) + return rc; + + /* Fetch the RQ's context to see if policing is enabled */ + rc = nix_aq_context_read(rvu, nix_hw, &aq_req, &aq_rsp, pcifunc, + NIX_AQ_CTYPE_RQ, rq_idx); + if (rc) { + dev_err(rvu->dev, + "%s: Failed to fetch RQ%d context of PFFUNC 0x%x\n", + __func__, rq_idx, pcifunc); + return rc; + } + + if (!aq_rsp.rq.policer_ena) + return 0; + + /* Get the bandwidth profile ID mapped to this RQ */ + leaf_prof = aq_rsp.rq.band_prof_id; + + ipolicer = &nix_hw->ipolicer[BAND_PROF_LEAF_LAYER]; + ipolicer->match_id[leaf_prof] = match_id; + + /* Check if any other leaf profile is marked with same match_id */ + for (idx = 0; idx < ipolicer->band_prof.max; idx++) { + if (idx == leaf_prof) + continue; + if (ipolicer->match_id[idx] != match_id) + continue; + + leaf_match = idx; + break; + } + + if (idx == ipolicer->band_prof.max) + return 0; + + /* Fetch the matching profile's context to check if it's already + * mapped to a mid level profile. + */ + rc = nix_aq_context_read(rvu, nix_hw, &aq_req, &aq_rsp, 0x00, + NIX_AQ_CTYPE_BANDPROF, leaf_match); + if (rc) { + dev_err(rvu->dev, + "%s: Failed to fetch context of leaf profile %d\n", + __func__, leaf_match); + return rc; + } + + ipolicer = &nix_hw->ipolicer[BAND_PROF_MID_LAYER]; + if (aq_rsp.prof.hl_en) { + /* Get Mid layer prof index and map leaf_prof index + * also such that flows that are being steered + * to different RQs and marked with same match_id + * are rate limited in a aggregate fashion + */ + mid_prof = aq_rsp.prof.band_prof_id; + rc = nix_ipolicer_map_leaf_midprofs(rvu, nix_hw, + &aq_req, &aq_rsp, + leaf_prof, mid_prof); + if (rc) { + dev_err(rvu->dev, + "%s: Failed to map leaf(%d) and mid(%d) profiles\n", + __func__, leaf_prof, mid_prof); + goto exit; + } + + mutex_lock(&rvu->rsrc_lock); + ipolicer->ref_count[mid_prof]++; + mutex_unlock(&rvu->rsrc_lock); + goto exit; + } + + /* Allocate a mid layer profile and + * map both 'leaf_prof' and 'leaf_match' profiles to it. + */ + mutex_lock(&rvu->rsrc_lock); + mid_prof = rvu_alloc_rsrc(&ipolicer->band_prof); + if (mid_prof < 0) { + dev_err(rvu->dev, + "%s: Unable to allocate mid layer profile\n", __func__); + mutex_unlock(&rvu->rsrc_lock); + goto exit; + } + mutex_unlock(&rvu->rsrc_lock); + ipolicer->pfvf_map[mid_prof] = 0x00; + ipolicer->ref_count[mid_prof] = 0; + + /* Initialize mid layer profile same as 'leaf_prof' */ + rc = nix_aq_context_read(rvu, nix_hw, &aq_req, &aq_rsp, 0x00, + NIX_AQ_CTYPE_BANDPROF, leaf_prof); + if (rc) { + dev_err(rvu->dev, + "%s: Failed to fetch context of leaf profile %d\n", + __func__, leaf_prof); + goto exit; + } + + memset(&aq_req, 0, sizeof(struct nix_cn10k_aq_enq_req)); + aq_req.hdr.pcifunc = 0x00; + aq_req.qidx = (mid_prof & 0x3FFF) | (BAND_PROF_MID_LAYER << 14); + aq_req.ctype = NIX_AQ_CTYPE_BANDPROF; + aq_req.op = NIX_AQ_INSTOP_WRITE; + memcpy(&aq_req.prof, &aq_rsp.prof, sizeof(struct nix_bandprof_s)); + /* Clear higher layer enable bit in the mid profile, just in case */ + aq_req.prof.hl_en = 0; + aq_req.prof_mask.hl_en = 1; + + rc = rvu_nix_blk_aq_enq_inst(rvu, nix_hw, + (struct nix_aq_enq_req *)&aq_req, NULL); + if (rc) { + dev_err(rvu->dev, + "%s: Failed to INIT context of mid layer profile %d\n", + __func__, mid_prof); + goto exit; + } + + /* Map both leaf profiles to this mid layer profile */ + rc = nix_ipolicer_map_leaf_midprofs(rvu, nix_hw, + &aq_req, &aq_rsp, + leaf_prof, mid_prof); + if (rc) { + dev_err(rvu->dev, + "%s: Failed to map leaf(%d) and mid(%d) profiles\n", + __func__, leaf_prof, mid_prof); + goto exit; + } + + mutex_lock(&rvu->rsrc_lock); + ipolicer->ref_count[mid_prof]++; + mutex_unlock(&rvu->rsrc_lock); + + rc = nix_ipolicer_map_leaf_midprofs(rvu, nix_hw, + &aq_req, &aq_rsp, + leaf_match, mid_prof); + if (rc) { + dev_err(rvu->dev, + "%s: Failed to map leaf(%d) and mid(%d) profiles\n", + __func__, leaf_match, mid_prof); + ipolicer->ref_count[mid_prof]--; + goto exit; + } + + mutex_lock(&rvu->rsrc_lock); + ipolicer->ref_count[mid_prof]++; + mutex_unlock(&rvu->rsrc_lock); + +exit: + return rc; +} + +/* Called with mutex rsrc_lock */ +static void nix_clear_ratelimit_aggr(struct rvu *rvu, struct nix_hw *nix_hw, + u32 leaf_prof) +{ + struct nix_cn10k_aq_enq_req aq_req; + struct nix_cn10k_aq_enq_rsp aq_rsp; + struct nix_ipolicer *ipolicer; + u16 mid_prof; + int rc; + + mutex_unlock(&rvu->rsrc_lock); + + rc = nix_aq_context_read(rvu, nix_hw, &aq_req, &aq_rsp, 0x00, + NIX_AQ_CTYPE_BANDPROF, leaf_prof); + + mutex_lock(&rvu->rsrc_lock); + if (rc) { + dev_err(rvu->dev, + "%s: Failed to fetch context of leaf profile %d\n", + __func__, leaf_prof); + return; + } + + if (!aq_rsp.prof.hl_en) + return; + + mid_prof = aq_rsp.prof.band_prof_id; + ipolicer = &nix_hw->ipolicer[BAND_PROF_MID_LAYER]; + ipolicer->ref_count[mid_prof]--; + /* If ref_count is zero, free mid layer profile */ + if (!ipolicer->ref_count[mid_prof]) { + ipolicer->pfvf_map[mid_prof] = 0x00; + rvu_free_rsrc(&ipolicer->band_prof, mid_prof); + } +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 0bc4529691ec..3612e0a2cab3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -19,7 +19,7 @@ #include "cgx.h" #include "npc_profile.h" -#define RSVD_MCAM_ENTRIES_PER_PF 2 /* Bcast & Promisc */ +#define RSVD_MCAM_ENTRIES_PER_PF 3 /* Broadcast, Promisc and AllMulticast */ #define RSVD_MCAM_ENTRIES_PER_NIXLF 1 /* Ucast for LFs */ #define NPC_PARSE_RESULT_DMAC_OFFSET 8 @@ -27,6 +27,8 @@ #define NPC_KEX_CHAN_MASK 0xFFFULL #define NPC_KEX_PF_FUNC_MASK 0xFFFFULL +#define ALIGN_8B_CEIL(__a) (((__a) + 7) & (-8)) + static const char def_pfl_name[] = "default"; static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam, @@ -212,8 +214,10 @@ int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, */ if (type == NIXLF_BCAST_ENTRY) return index; - else if (type == NIXLF_PROMISC_ENTRY) + else if (type == NIXLF_ALLMULTI_ENTRY) return index + 1; + else if (type == NIXLF_PROMISC_ENTRY) + return index + 2; } return npc_get_ucast_mcam_index(mcam, pcifunc, nixlf); @@ -411,37 +415,49 @@ static void npc_fill_entryword(struct mcam_entry *entry, int idx, } } -static void npc_get_default_entry_action(struct rvu *rvu, struct npc_mcam *mcam, - int blkaddr, int index, - struct mcam_entry *entry) +static u64 npc_get_default_entry_action(struct rvu *rvu, struct npc_mcam *mcam, + int blkaddr, u16 pf_func) +{ + int bank, nixlf, index; + + /* get ucast entry rule entry index */ + nix_get_nixlf(rvu, pf_func, &nixlf, NULL); + index = npc_get_nixlf_mcam_index(mcam, pf_func, nixlf, + NIXLF_UCAST_ENTRY); + bank = npc_get_bank(mcam, index); + index &= (mcam->banksize - 1); + + return rvu_read64(rvu, blkaddr, + NPC_AF_MCAMEX_BANKX_ACTION(index, bank)); +} + +static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam, + int blkaddr, int index, struct mcam_entry *entry, + bool *enable) { u16 owner, target_func; struct rvu_pfvf *pfvf; - int bank, nixlf; u64 rx_action; owner = mcam->entry2pfvf_map[index]; target_func = (entry->action >> 4) & 0xffff; - /* return incase target is PF or LBK or rule owner is not PF */ + /* do nothing when target is LBK/PF or owner is not PF */ if (is_afvf(target_func) || (owner & RVU_PFVF_FUNC_MASK) || !(target_func & RVU_PFVF_FUNC_MASK)) return; + /* save entry2target_pffunc */ pfvf = rvu_get_pfvf(rvu, target_func); mcam->entry2target_pffunc[index] = target_func; - /* return if nixlf is not attached or initialized */ - if (!is_nixlf_attached(rvu, target_func) || !pfvf->def_ucast_rule) - return; - /* get VF ucast entry rule */ - nix_get_nixlf(rvu, target_func, &nixlf, NULL); - index = npc_get_nixlf_mcam_index(mcam, target_func, - nixlf, NIXLF_UCAST_ENTRY); - bank = npc_get_bank(mcam, index); - index &= (mcam->banksize - 1); + /* don't enable rule when nixlf not attached or initialized */ + if (!(is_nixlf_attached(rvu, target_func) && + test_bit(NIXLF_INITIALIZED, &pfvf->flags))) + *enable = false; - rx_action = rvu_read64(rvu, blkaddr, - NPC_AF_MCAMEX_BANKX_ACTION(index, bank)); + /* copy VF default entry action to the VF mcam entry */ + rx_action = npc_get_default_entry_action(rvu, mcam, blkaddr, + target_func); if (rx_action) entry->action = rx_action; } @@ -493,10 +509,9 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, NPC_AF_MCAMEX_BANKX_CAMX_W1(index, bank, 0), cam0); } - /* copy VF default entry action to the VF mcam entry */ + /* PF installing VF rule */ if (intf == NIX_INTF_RX && actindex < mcam->bmap_entries) - npc_get_default_entry_action(rvu, mcam, blkaddr, actindex, - entry); + npc_fixup_vf_rule(rvu, mcam, blkaddr, index, entry, &enable); /* Set 'action' */ rvu_write64(rvu, blkaddr, @@ -647,30 +662,32 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, } void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, - int nixlf, u64 chan, u8 chan_cnt, - bool allmulti) + int nixlf, u64 chan, u8 chan_cnt) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); struct npc_install_flow_req req = { 0 }; struct npc_install_flow_rsp rsp = { 0 }; struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; int blkaddr, ucast_idx, index; - u8 mac_addr[ETH_ALEN] = { 0 }; struct nix_rx_action action; u64 relaxed_mask; - /* Only PF or AF VF can add a promiscuous entry */ - if ((pcifunc & RVU_PFVF_FUNC_MASK) && !is_afvf(pcifunc)) + if (!hw->cap.nix_rx_multicast && is_cgx_vf(rvu, pcifunc)) return; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); if (blkaddr < 0) return; - *(u64 *)&action = 0x00; index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_PROMISC_ENTRY); + if (is_cgx_vf(rvu, pcifunc)) + index = npc_get_nixlf_mcam_index(mcam, + pcifunc & ~RVU_PFVF_FUNC_MASK, + nixlf, NIXLF_PROMISC_ENTRY); + /* If the corresponding PF's ucast action is RSS, * use the same action for promisc also */ @@ -678,19 +695,20 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, nixlf, NIXLF_UCAST_ENTRY); if (is_mcam_entry_enabled(rvu, mcam, blkaddr, ucast_idx)) *(u64 *)&action = npc_get_mcam_action(rvu, mcam, - blkaddr, ucast_idx); + blkaddr, ucast_idx); if (action.op != NIX_RX_ACTIONOP_RSS) { *(u64 *)&action = 0x00; action.op = NIX_RX_ACTIONOP_UCAST; - action.pf_func = pcifunc; } - if (allmulti) { - mac_addr[0] = 0x01; /* LSB bit of 1st byte in DMAC */ - ether_addr_copy(req.packet.dmac, mac_addr); - ether_addr_copy(req.mask.dmac, mac_addr); - req.features = BIT_ULL(NPC_DMAC); + /* RX_ACTION set to MCAST for CGX PF's */ + if (hw->cap.nix_rx_multicast && pfvf->use_mce_list && + is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) { + *(u64 *)&action = 0x00; + action.op = NIX_RX_ACTIONOP_MCAST; + pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK); + action.index = pfvf->promisc_mce_idx; } req.chan_mask = 0xFFFU; @@ -718,8 +736,8 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); } -static void npc_enadis_promisc_entry(struct rvu *rvu, u16 pcifunc, - int nixlf, bool enable) +void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, + int nixlf, bool enable) { struct npc_mcam *mcam = &rvu->hw->mcam; int blkaddr, index; @@ -728,25 +746,14 @@ static void npc_enadis_promisc_entry(struct rvu *rvu, u16 pcifunc, if (blkaddr < 0) return; - /* Only PF's have a promiscuous entry */ - if (pcifunc & RVU_PFVF_FUNC_MASK) - return; + /* Get 'pcifunc' of PF device */ + pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_PROMISC_ENTRY); npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); } -void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf) -{ - npc_enadis_promisc_entry(rvu, pcifunc, nixlf, false); -} - -void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf) -{ - npc_enadis_promisc_entry(rvu, pcifunc, nixlf, true); -} - void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u64 chan) { @@ -756,8 +763,6 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, struct npc_mcam *mcam = &rvu->hw->mcam; struct rvu_hwinfo *hw = rvu->hw; int blkaddr, index; - u32 req_index = 0; - u8 op; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); if (blkaddr < 0) @@ -770,7 +775,7 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, /* If pkt replication is not supported, * then only PF is allowed to add a bcast match entry. */ - if (!hw->cap.nix_rx_multicast && pcifunc & RVU_PFVF_FUNC_MASK) + if (!hw->cap.nix_rx_multicast && is_vf(pcifunc)) return; /* Get 'pcifunc' of PF device */ @@ -784,10 +789,10 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, * so install entry with UCAST action, so that PF * receives all broadcast packets. */ - op = NIX_RX_ACTIONOP_UCAST; + req.op = NIX_RX_ACTIONOP_UCAST; } else { - op = NIX_RX_ACTIONOP_MCAST; - req_index = pfvf->bcast_mce_idx; + req.op = NIX_RX_ACTIONOP_MCAST; + req.index = pfvf->bcast_mce_idx; } eth_broadcast_addr((u8 *)&req.packet.dmac); @@ -796,15 +801,14 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, req.channel = chan; req.intf = pfvf->nix_rx_intf; req.entry = index; - req.op = op; req.hdr.pcifunc = 0; /* AF is requester */ req.vf = pcifunc; - req.index = req_index; rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); } -void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable) +void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + bool enable) { struct npc_mcam *mcam = &rvu->hw->mcam; int blkaddr, index; @@ -816,7 +820,104 @@ void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable) /* Get 'pcifunc' of PF device */ pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; - index = npc_get_nixlf_mcam_index(mcam, pcifunc, 0, NIXLF_BCAST_ENTRY); + index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, + NIXLF_BCAST_ENTRY); + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); +} + +void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + u64 chan) +{ + struct npc_install_flow_req req = { 0 }; + struct npc_install_flow_rsp rsp = { 0 }; + struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; + int blkaddr, ucast_idx, index; + u8 mac_addr[ETH_ALEN] = { 0 }; + struct nix_rx_action action; + struct rvu_pfvf *pfvf; + u16 vf_func; + + /* Only CGX PF/VF can add allmulticast entry */ + if (is_afvf(pcifunc)) + return; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); + if (blkaddr < 0) + return; + + /* Get 'pcifunc' of PF device */ + vf_func = pcifunc & RVU_PFVF_FUNC_MASK; + pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; + pfvf = rvu_get_pfvf(rvu, pcifunc); + index = npc_get_nixlf_mcam_index(mcam, pcifunc, + nixlf, NIXLF_ALLMULTI_ENTRY); + + /* If the corresponding PF's ucast action is RSS, + * use the same action for multicast entry also + */ + ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc, + nixlf, NIXLF_UCAST_ENTRY); + if (is_mcam_entry_enabled(rvu, mcam, blkaddr, ucast_idx)) + *(u64 *)&action = npc_get_mcam_action(rvu, mcam, + blkaddr, ucast_idx); + + if (action.op != NIX_RX_ACTIONOP_RSS) { + *(u64 *)&action = 0x00; + action.op = NIX_RX_ACTIONOP_UCAST; + action.pf_func = pcifunc; + } + + /* RX_ACTION set to MCAST for CGX PF's */ + if (hw->cap.nix_rx_multicast && pfvf->use_mce_list) { + *(u64 *)&action = 0x00; + action.op = NIX_RX_ACTIONOP_MCAST; + action.index = pfvf->mcast_mce_idx; + } + + mac_addr[0] = 0x01; /* LSB bit of 1st byte in DMAC */ + ether_addr_copy(req.packet.dmac, mac_addr); + ether_addr_copy(req.mask.dmac, mac_addr); + req.features = BIT_ULL(NPC_DMAC); + + /* For cn10k the upper two bits of the channel number are + * cpt channel number. with masking out these bits in the + * mcam entry, same entry used for NIX will allow packets + * received from cpt for parsing. + */ + if (!is_rvu_otx2(rvu)) + req.chan_mask = NIX_CHAN_CPT_X2P_MASK; + else + req.chan_mask = 0xFFFU; + + req.channel = chan; + req.intf = pfvf->nix_rx_intf; + req.entry = index; + req.op = action.op; + req.hdr.pcifunc = 0; /* AF is requester */ + req.vf = pcifunc | vf_func; + req.index = action.index; + req.match_id = action.match_id; + req.flow_key_alg = action.flow_key_alg; + + rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); +} + +void rvu_npc_enable_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + bool enable) +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + int blkaddr, index; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); + if (blkaddr < 0) + return; + + /* Get 'pcifunc' of PF device */ + pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; + + index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, + NIXLF_ALLMULTI_ENTRY); npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); } @@ -858,6 +959,7 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, int group, int alg_idx, int mcam_index) { struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; struct nix_rx_action action; int blkaddr, index, bank; struct rvu_pfvf *pfvf; @@ -913,7 +1015,8 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, /* If PF's promiscuous entry is enabled, * Set RSS action for that entry as well */ - if (is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) { + if ((!hw->cap.nix_rx_multicast || !pfvf->use_mce_list) && + is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) { bank = npc_get_bank(mcam, index); index &= (mcam->banksize - 1); @@ -923,12 +1026,47 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, } } +void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc, + int nixlf, int type, bool enable) +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; + struct nix_mce_list *mce_list; + int index, blkaddr, mce_idx; + struct rvu_pfvf *pfvf; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); + if (blkaddr < 0) + return; + + index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK, + nixlf, type); + + /* disable MCAM entry when packet replication is not supported by hw */ + if (!hw->cap.nix_rx_multicast && !is_vf(pcifunc)) { + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); + return; + } + + /* return incase mce list is not enabled */ + pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK); + if (hw->cap.nix_rx_multicast && is_vf(pcifunc) && + type != NIXLF_BCAST_ENTRY && !pfvf->use_mce_list) + return; + + nix_get_mce_list(rvu, pcifunc, type, &mce_list, &mce_idx); + + nix_update_mce_list(rvu, pcifunc, mce_list, + mce_idx, index, enable); + if (enable) + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); +} + static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf, bool enable) { struct npc_mcam *mcam = &rvu->hw->mcam; - struct nix_rx_action action; - int index, bank, blkaddr; + int index, blkaddr; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); if (blkaddr < 0) @@ -939,48 +1077,33 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc, nixlf, NIXLF_UCAST_ENTRY); npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); - /* For PF, ena/dis promisc and bcast MCAM match entries. - * For VFs add/delete from bcast list when RX multicast - * feature is present. + /* Nothing to do for VFs, on platforms where pkt replication + * is not supported */ - if (pcifunc & RVU_PFVF_FUNC_MASK && !rvu->hw->cap.nix_rx_multicast) + if ((pcifunc & RVU_PFVF_FUNC_MASK) && !rvu->hw->cap.nix_rx_multicast) return; - /* For bcast, enable/disable only if it's action is not - * packet replication, incase if action is replication - * then this PF/VF's nixlf is removed from bcast replication - * list. - */ - index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK, - nixlf, NIXLF_BCAST_ENTRY); - bank = npc_get_bank(mcam, index); - *(u64 *)&action = rvu_read64(rvu, blkaddr, - NPC_AF_MCAMEX_BANKX_ACTION(index & (mcam->banksize - 1), bank)); - - /* VFs will not have BCAST entry */ - if (action.op != NIX_RX_ACTIONOP_MCAST && - !(pcifunc & RVU_PFVF_FUNC_MASK)) { - npc_enable_mcam_entry(rvu, mcam, - blkaddr, index, enable); - } else { - nix_update_bcast_mce_list(rvu, pcifunc, enable); - /* Enable PF's BCAST entry for packet replication */ - rvu_npc_enable_bcast_entry(rvu, pcifunc, enable); - } - - if (enable) - rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf); - else - rvu_npc_disable_promisc_entry(rvu, pcifunc, nixlf); + /* add/delete pf_func to broadcast MCE list */ + npc_enadis_default_mce_entry(rvu, pcifunc, nixlf, + NIXLF_BCAST_ENTRY, enable); } void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf) { npc_enadis_default_entries(rvu, pcifunc, nixlf, false); + + /* Delete multicast and promisc MCAM entries */ + npc_enadis_default_mce_entry(rvu, pcifunc, nixlf, + NIXLF_ALLMULTI_ENTRY, false); + npc_enadis_default_mce_entry(rvu, pcifunc, nixlf, + NIXLF_PROMISC_ENTRY, false); } void rvu_npc_enable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf) { + /* Enables only broadcast match entry. Promisc/Allmulti are enabled + * in set_rx_mode mbox handler. + */ npc_enadis_default_entries(rvu, pcifunc, nixlf, true); } @@ -1000,7 +1123,8 @@ void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf) /* Disable MCAM entries directing traffic to this 'pcifunc' */ list_for_each_entry_safe(rule, tmp, &mcam->mcam_rules, list) { if (is_npc_intf_rx(rule->intf) && - rule->rx_action.pf_func == pcifunc) { + rule->rx_action.pf_func == pcifunc && + rule->rx_action.op != NIX_RX_ACTIONOP_MCAST) { npc_enable_mcam_entry(rvu, mcam, blkaddr, rule->entry, false); rule->enable = false; @@ -1134,6 +1258,30 @@ static void npc_program_mkex_profile(struct rvu *rvu, int blkaddr, } } +static int npc_fwdb_prfl_img_map(struct rvu *rvu, void __iomem **prfl_img_addr, + u64 *size) +{ + u64 prfl_addr, prfl_sz; + + if (!rvu->fwdata) + return -EINVAL; + + prfl_addr = rvu->fwdata->mcam_addr; + prfl_sz = rvu->fwdata->mcam_sz; + + if (!prfl_addr || !prfl_sz) + return -EINVAL; + + *prfl_img_addr = ioremap_wc(prfl_addr, prfl_sz); + if (!(*prfl_img_addr)) + return -ENOMEM; + + *size = prfl_sz; + + return 0; +} + +/* strtoull of "mkexprof" with base:36 */ #define MKEX_END_SIGN 0xdeadbeef static void npc_load_mkex_profile(struct rvu *rvu, int blkaddr, @@ -1141,26 +1289,21 @@ static void npc_load_mkex_profile(struct rvu *rvu, int blkaddr, { struct device *dev = &rvu->pdev->dev; struct npc_mcam_kex *mcam_kex; - void *mkex_prfl_addr = NULL; - u64 prfl_addr, prfl_sz; + void __iomem *mkex_prfl_addr = NULL; + u64 prfl_sz; + int ret; /* If user not selected mkex profile */ - if (!strncmp(mkex_profile, def_pfl_name, MKEX_NAME_LEN)) + if (rvu->kpu_fwdata_sz || + !strncmp(mkex_profile, def_pfl_name, MKEX_NAME_LEN)) goto program_mkex; - if (!rvu->fwdata) - goto program_mkex; - prfl_addr = rvu->fwdata->mcam_addr; - prfl_sz = rvu->fwdata->mcam_sz; - - if (!prfl_addr || !prfl_sz) + /* Setting up the mapping for mkex profile image */ + ret = npc_fwdb_prfl_img_map(rvu, &mkex_prfl_addr, &prfl_sz); + if (ret < 0) goto program_mkex; - mkex_prfl_addr = memremap(prfl_addr, prfl_sz, MEMREMAP_WC); - if (!mkex_prfl_addr) - goto program_mkex; - - mcam_kex = (struct npc_mcam_kex *)mkex_prfl_addr; + mcam_kex = (struct npc_mcam_kex __force *)mkex_prfl_addr; while (((s64)prfl_sz > 0) && (mcam_kex->mkex_sign != MKEX_END_SIGN)) { /* Compare with mkex mod_param name string */ @@ -1186,7 +1329,7 @@ program_mkex: /* Program selected mkex profile */ npc_program_mkex_profile(rvu, blkaddr, rvu->kpu.mkex); if (mkex_prfl_addr) - memunmap(mkex_prfl_addr); + iounmap(mkex_prfl_addr); } static void npc_config_kpuaction(struct rvu *rvu, int blkaddr, @@ -1263,6 +1406,7 @@ static void npc_program_kpu_profile(struct rvu *rvu, int blkaddr, int kpu, const struct npc_kpu_profile *profile) { int entry, num_entries, max_entries; + u64 entry_mask; if (profile->cam_entries != profile->action_entries) { dev_err(rvu->dev, @@ -1286,8 +1430,12 @@ static void npc_program_kpu_profile(struct rvu *rvu, int blkaddr, int kpu, /* Enable all programmed entries */ num_entries = min_t(int, profile->action_entries, profile->cam_entries); + entry_mask = enable_mask(num_entries); + /* Disable first KPU_MAX_CST_ENT entries for built-in profile */ + if (!rvu->kpu.custom) + entry_mask |= GENMASK_ULL(KPU_MAX_CST_ENT - 1, 0); rvu_write64(rvu, blkaddr, - NPC_AF_KPUX_ENTRY_DISX(kpu, 0), enable_mask(num_entries)); + NPC_AF_KPUX_ENTRY_DISX(kpu, 0), entry_mask); if (num_entries > 64) { rvu_write64(rvu, blkaddr, NPC_AF_KPUX_ENTRY_DISX(kpu, 1), @@ -1300,6 +1448,7 @@ static void npc_program_kpu_profile(struct rvu *rvu, int blkaddr, int kpu, static int npc_prepare_default_kpu(struct npc_kpu_profile_adapter *profile) { + profile->custom = 0; profile->name = def_pfl_name; profile->version = NPC_KPU_PROFILE_VER; profile->ikpu = ikpu_action_entries; @@ -1312,10 +1461,245 @@ static int npc_prepare_default_kpu(struct npc_kpu_profile_adapter *profile) return 0; } +static int npc_apply_custom_kpu(struct rvu *rvu, + struct npc_kpu_profile_adapter *profile) +{ + size_t hdr_sz = sizeof(struct npc_kpu_profile_fwdata), offset = 0; + struct npc_kpu_profile_fwdata *fw = rvu->kpu_fwdata; + struct npc_kpu_profile_action *action; + struct npc_kpu_profile_cam *cam; + struct npc_kpu_fwdata *fw_kpu; + int entries; + u16 kpu, entry; + + if (rvu->kpu_fwdata_sz < hdr_sz) { + dev_warn(rvu->dev, "Invalid KPU profile size\n"); + return -EINVAL; + } + if (le64_to_cpu(fw->signature) != KPU_SIGN) { + dev_warn(rvu->dev, "Invalid KPU profile signature %llx\n", + fw->signature); + return -EINVAL; + } + /* Verify if the using known profile structure */ + if (NPC_KPU_VER_MAJ(profile->version) > + NPC_KPU_VER_MAJ(NPC_KPU_PROFILE_VER)) { + dev_warn(rvu->dev, "Not supported Major version: %d > %d\n", + NPC_KPU_VER_MAJ(profile->version), + NPC_KPU_VER_MAJ(NPC_KPU_PROFILE_VER)); + return -EINVAL; + } + /* Verify if profile is aligned with the required kernel changes */ + if (NPC_KPU_VER_MIN(profile->version) < + NPC_KPU_VER_MIN(NPC_KPU_PROFILE_VER)) { + dev_warn(rvu->dev, + "Invalid KPU profile version: %d.%d.%d expected version <= %d.%d.%d\n", + NPC_KPU_VER_MAJ(profile->version), + NPC_KPU_VER_MIN(profile->version), + NPC_KPU_VER_PATCH(profile->version), + NPC_KPU_VER_MAJ(NPC_KPU_PROFILE_VER), + NPC_KPU_VER_MIN(NPC_KPU_PROFILE_VER), + NPC_KPU_VER_PATCH(NPC_KPU_PROFILE_VER)); + return -EINVAL; + } + /* Verify if profile fits the HW */ + if (fw->kpus > profile->kpus) { + dev_warn(rvu->dev, "Not enough KPUs: %d > %ld\n", fw->kpus, + profile->kpus); + return -EINVAL; + } + + profile->custom = 1; + profile->name = fw->name; + profile->version = le64_to_cpu(fw->version); + profile->mkex = &fw->mkex; + profile->lt_def = &fw->lt_def; + + for (kpu = 0; kpu < fw->kpus; kpu++) { + fw_kpu = (struct npc_kpu_fwdata *)(fw->data + offset); + if (fw_kpu->entries > KPU_MAX_CST_ENT) + dev_warn(rvu->dev, + "Too many custom entries on KPU%d: %d > %d\n", + kpu, fw_kpu->entries, KPU_MAX_CST_ENT); + entries = min(fw_kpu->entries, KPU_MAX_CST_ENT); + cam = (struct npc_kpu_profile_cam *)fw_kpu->data; + offset += sizeof(*fw_kpu) + fw_kpu->entries * sizeof(*cam); + action = (struct npc_kpu_profile_action *)(fw->data + offset); + offset += fw_kpu->entries * sizeof(*action); + if (rvu->kpu_fwdata_sz < hdr_sz + offset) { + dev_warn(rvu->dev, + "Profile size mismatch on KPU%i parsing.\n", + kpu + 1); + return -EINVAL; + } + for (entry = 0; entry < entries; entry++) { + profile->kpu[kpu].cam[entry] = cam[entry]; + profile->kpu[kpu].action[entry] = action[entry]; + } + } + + return 0; +} + +static int npc_load_kpu_prfl_img(struct rvu *rvu, void __iomem *prfl_addr, + u64 prfl_sz, const char *kpu_profile) +{ + struct npc_kpu_profile_fwdata *kpu_data = NULL; + int rc = -EINVAL; + + kpu_data = (struct npc_kpu_profile_fwdata __force *)prfl_addr; + if (le64_to_cpu(kpu_data->signature) == KPU_SIGN && + !strncmp(kpu_data->name, kpu_profile, KPU_NAME_LEN)) { + dev_info(rvu->dev, "Loading KPU profile from firmware db: %s\n", + kpu_profile); + rvu->kpu_fwdata = kpu_data; + rvu->kpu_fwdata_sz = prfl_sz; + rvu->kpu_prfl_addr = prfl_addr; + rc = 0; + } + + return rc; +} + +static int npc_fwdb_detect_load_prfl_img(struct rvu *rvu, uint64_t prfl_sz, + const char *kpu_profile) +{ + struct npc_coalesced_kpu_prfl *img_data = NULL; + int i = 0, rc = -EINVAL; + void __iomem *kpu_prfl_addr; + u16 offset; + + img_data = (struct npc_coalesced_kpu_prfl __force *)rvu->kpu_prfl_addr; + if (le64_to_cpu(img_data->signature) == KPU_SIGN && + !strncmp(img_data->name, kpu_profile, KPU_NAME_LEN)) { + /* Loaded profile is a single KPU profile. */ + rc = npc_load_kpu_prfl_img(rvu, rvu->kpu_prfl_addr, + prfl_sz, kpu_profile); + goto done; + } + + /* Loaded profile is coalesced image, offset of first KPU profile.*/ + offset = offsetof(struct npc_coalesced_kpu_prfl, prfl_sz) + + (img_data->num_prfl * sizeof(uint16_t)); + /* Check if mapped image is coalesced image. */ + while (i < img_data->num_prfl) { + /* Profile image offsets are rounded up to next 8 multiple.*/ + offset = ALIGN_8B_CEIL(offset); + kpu_prfl_addr = (void __iomem *)((uintptr_t)rvu->kpu_prfl_addr + + offset); + rc = npc_load_kpu_prfl_img(rvu, kpu_prfl_addr, + img_data->prfl_sz[i], kpu_profile); + if (!rc) + break; + /* Calculating offset of profile image based on profile size.*/ + offset += img_data->prfl_sz[i]; + i++; + } +done: + return rc; +} + +static int npc_load_kpu_profile_fwdb(struct rvu *rvu, const char *kpu_profile) +{ + int ret = -EINVAL; + u64 prfl_sz; + + /* Setting up the mapping for NPC profile image */ + ret = npc_fwdb_prfl_img_map(rvu, &rvu->kpu_prfl_addr, &prfl_sz); + if (ret < 0) + goto done; + + /* Detect if profile is coalesced or single KPU profile and load */ + ret = npc_fwdb_detect_load_prfl_img(rvu, prfl_sz, kpu_profile); + if (ret == 0) + goto done; + + /* Cleaning up if KPU profile image from fwdata is not valid. */ + if (rvu->kpu_prfl_addr) { + iounmap(rvu->kpu_prfl_addr); + rvu->kpu_prfl_addr = NULL; + rvu->kpu_fwdata_sz = 0; + rvu->kpu_fwdata = NULL; + } + +done: + return ret; +} + static void npc_load_kpu_profile(struct rvu *rvu) { struct npc_kpu_profile_adapter *profile = &rvu->kpu; + const char *kpu_profile = rvu->kpu_pfl_name; + const struct firmware *fw = NULL; + bool retry_fwdb = false; + /* If user not specified profile customization */ + if (!strncmp(kpu_profile, def_pfl_name, KPU_NAME_LEN)) + goto revert_to_default; + /* First prepare default KPU, then we'll customize top entries. */ + npc_prepare_default_kpu(profile); + + /* Order of preceedence for load loading NPC profile (high to low) + * Firmware binary in filesystem. + * Firmware database method. + * Default KPU profile. + */ + if (!request_firmware(&fw, kpu_profile, rvu->dev)) { + dev_info(rvu->dev, "Loading KPU profile from firmware: %s\n", + kpu_profile); + rvu->kpu_fwdata = kzalloc(fw->size, GFP_KERNEL); + if (rvu->kpu_fwdata) { + memcpy(rvu->kpu_fwdata, fw->data, fw->size); + rvu->kpu_fwdata_sz = fw->size; + } + release_firmware(fw); + retry_fwdb = true; + goto program_kpu; + } + +load_image_fwdb: + /* Loading the KPU profile using firmware database */ + if (npc_load_kpu_profile_fwdb(rvu, kpu_profile)) + goto revert_to_default; + +program_kpu: + /* Apply profile customization if firmware was loaded. */ + if (!rvu->kpu_fwdata_sz || npc_apply_custom_kpu(rvu, profile)) { + /* If image from firmware filesystem fails to load or invalid + * retry with firmware database method. + */ + if (rvu->kpu_fwdata || rvu->kpu_fwdata_sz) { + /* Loading image from firmware database failed. */ + if (rvu->kpu_prfl_addr) { + iounmap(rvu->kpu_prfl_addr); + rvu->kpu_prfl_addr = NULL; + } else { + kfree(rvu->kpu_fwdata); + } + rvu->kpu_fwdata = NULL; + rvu->kpu_fwdata_sz = 0; + if (retry_fwdb) { + retry_fwdb = false; + goto load_image_fwdb; + } + } + + dev_warn(rvu->dev, + "Can't load KPU profile %s. Using default.\n", + kpu_profile); + kfree(rvu->kpu_fwdata); + rvu->kpu_fwdata = NULL; + goto revert_to_default; + } + + dev_info(rvu->dev, "Using custom profile '%s', version %d.%d.%d\n", + profile->name, NPC_KPU_VER_MAJ(profile->version), + NPC_KPU_VER_MIN(profile->version), + NPC_KPU_VER_PATCH(profile->version)); + + return; + +revert_to_default: npc_prepare_default_kpu(profile); } @@ -1654,6 +2038,10 @@ void rvu_npc_freemem(struct rvu *rvu) kfree(pkind->rsrc.bmap); kfree(mcam->counters.bmap); + if (rvu->kpu_prfl_addr) + iounmap(rvu->kpu_prfl_addr); + else + kfree(rvu->kpu_fwdata); mutex_destroy(&mcam->lock); } @@ -2149,8 +2537,11 @@ int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu, rsp->free_count = 0; /* Check if ref_entry is within range */ - if (req->priority && req->ref_entry >= mcam->bmap_entries) + if (req->priority && req->ref_entry >= mcam->bmap_entries) { + dev_err(rvu->dev, "%s: reference entry %d is out of range\n", + __func__, req->ref_entry); return NPC_MCAM_INVALID_REQ; + } /* ref_entry can't be '0' if requested priority is high. * Can't be last entry if requested priority is low. @@ -2163,8 +2554,12 @@ int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu, /* Since list of allocated indices needs to be sent to requester, * max number of non-contiguous entries per mbox msg is limited. */ - if (!req->contig && req->count > NPC_MAX_NONCONTIG_ENTRIES) + if (!req->contig && req->count > NPC_MAX_NONCONTIG_ENTRIES) { + dev_err(rvu->dev, + "%s: %d Non-contiguous MCAM entries requested is more than max (%d) allowed\n", + __func__, req->count, NPC_MAX_NONCONTIG_ENTRIES); return NPC_MCAM_INVALID_REQ; + } /* Alloc request from PFFUNC with no NIXLF attached should be denied */ if (!is_nixlf_attached(rvu, pcifunc)) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index 7f35b62eea13..68633145a8b8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -123,11 +123,8 @@ static bool npc_is_field_present(struct rvu *rvu, enum key_fields type, u8 intf) static bool npc_is_same(struct npc_key_field *input, struct npc_key_field *field) { - int ret; - - ret = memcmp(&input->layer_mdata, &field->layer_mdata, - sizeof(struct npc_layer_mdata)); - return ret == 0; + return memcmp(&input->layer_mdata, &field->layer_mdata, + sizeof(struct npc_layer_mdata)) == 0; } static void npc_set_layer_mdata(struct npc_mcam *mcam, enum key_fields type, @@ -1103,11 +1100,18 @@ find_rule: if (pf_set_vfs_mac) { ether_addr_copy(pfvf->default_mac, req->packet.dmac); ether_addr_copy(pfvf->mac_addr, req->packet.dmac); + set_bit(PF_SET_VF_MAC, &pfvf->flags); } - if (pfvf->pf_set_vf_cfg && req->vtag0_type == NIX_AF_LFX_RX_VTAG_TYPE7) + if (test_bit(PF_SET_VF_CFG, &pfvf->flags) && + req->vtag0_type == NIX_AF_LFX_RX_VTAG_TYPE7) rule->vfvlan_cfg = true; + if (is_npc_intf_rx(req->intf) && req->match_id && + (req->op == NIX_RX_ACTIONOP_UCAST || req->op == NIX_RX_ACTIONOP_RSS)) + return rvu_nix_setup_ratelimit_aggr(rvu, req->hdr.pcifunc, + req->index, req->match_id); + return 0; } @@ -1167,7 +1171,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu, /* PF installing for its VF */ if (req->hdr.pcifunc && !from_vf && req->vf) - pfvf->pf_set_vf_cfg = 1; + set_bit(PF_SET_VF_CFG, &pfvf->flags); /* update req destination mac addr */ if ((req->features & BIT_ULL(NPC_DMAC)) && is_npc_intf_rx(req->intf) && @@ -1177,9 +1181,12 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu, } err = nix_get_nixlf(rvu, target, &nixlf, NULL); + if (err && is_npc_intf_rx(req->intf) && !pf_set_vfs_mac) + return -EINVAL; - /* If interface is uninitialized then do not enable entry */ - if (err || (!req->default_rule && !pfvf->def_ucast_rule)) + /* don't enable rule when nixlf not attached or initialized */ + if (!(is_nixlf_attached(rvu, target) && + test_bit(NIXLF_INITIALIZED, &pfvf->flags))) enable = false; /* Packets reaching NPC in Tx path implies that a @@ -1193,6 +1200,14 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu, if (from_vf && !enable) return -EINVAL; + /* PF sets VF mac & VF NIXLF is not attached, update the mac addr */ + if (pf_set_vfs_mac && !enable) { + ether_addr_copy(pfvf->default_mac, req->packet.dmac); + ether_addr_copy(pfvf->mac_addr, req->packet.dmac); + set_bit(PF_SET_VF_MAC, &pfvf->flags); + return 0; + } + /* If message is from VF then its flow should not overlap with * reserved unicast flow. */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index ac71c0f2f960..76837d5e19c6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -171,6 +171,7 @@ #define NIX_AF_SQ_CONST (0x0040) #define NIX_AF_CQ_CONST (0x0048) #define NIX_AF_RQ_CONST (0x0050) +#define NIX_AF_PL_CONST (0x0058) #define NIX_AF_PSE_CONST (0x0060) #define NIX_AF_TL1_CONST (0x0070) #define NIX_AF_TL2_CONST (0x0078) @@ -181,6 +182,7 @@ #define NIX_AF_LSO_CFG (0x00A8) #define NIX_AF_BLK_RST (0x00B0) #define NIX_AF_TX_TSTMP_CFG (0x00C0) +#define NIX_AF_PL_TS (0x00C8) #define NIX_AF_RX_CFG (0x00D0) #define NIX_AF_AVG_DELAY (0x00E0) #define NIX_AF_CINT_DELAY (0x00F0) @@ -208,19 +210,27 @@ #define NIX_AF_RVU_INT_ENA_W1S (0x01D0) #define NIX_AF_RVU_INT_ENA_W1C (0x01D8) #define NIX_AF_TCP_TIMER (0x01E0) -#define NIX_AF_RX_WQE_TAG_CTL (0x01F0) +#define NIX_AF_RX_DEF_ET(a) (0x01F0ull | (uint64_t)(a) << 3) #define NIX_AF_RX_DEF_OL2 (0x0200) #define NIX_AF_RX_DEF_OIP4 (0x0210) #define NIX_AF_RX_DEF_IIP4 (0x0220) +#define NIX_AF_RX_DEF_VLAN0_PCP_DEI (0x0228) #define NIX_AF_RX_DEF_OIP6 (0x0230) +#define NIX_AF_RX_DEF_VLAN1_PCP_DEI (0x0238) #define NIX_AF_RX_DEF_IIP6 (0x0240) #define NIX_AF_RX_DEF_OTCP (0x0250) #define NIX_AF_RX_DEF_ITCP (0x0260) #define NIX_AF_RX_DEF_OUDP (0x0270) #define NIX_AF_RX_DEF_IUDP (0x0280) #define NIX_AF_RX_DEF_OSCTP (0x0290) +#define NIX_AF_RX_DEF_CST_APAD0 (0x0298) #define NIX_AF_RX_DEF_ISCTP (0x02A0) #define NIX_AF_RX_DEF_IPSECX (0x02B0) +#define NIX_AF_RX_DEF_CST_APAD1 (0x02A8) +#define NIX_AF_RX_DEF_IIP4_DSCP (0x02E0) +#define NIX_AF_RX_DEF_OIP4_DSCP (0x02E8) +#define NIX_AF_RX_DEF_IIP6_DSCP (0x02F0) +#define NIX_AF_RX_DEF_OIP6_DSCP (0x02F8) #define NIX_AF_RX_IPSEC_GEN_CFG (0x0300) #define NIX_AF_RX_CPTX_INST_ADDR (0x0310) #define NIX_AF_NDC_TX_SYNC (0x03F0) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h index 5e5f45c7eab0..14aa8e37ea41 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h @@ -286,7 +286,7 @@ enum nix_aq_ctype { NIX_AQ_CTYPE_MCE = 0x3, NIX_AQ_CTYPE_RSS = 0x4, NIX_AQ_CTYPE_DYNO = 0x5, - NIX_AQ_CTYPE_BAND_PROF = 0x6, + NIX_AQ_CTYPE_BANDPROF = 0x6, }; /* NIX admin queue instruction opcodes */ @@ -665,6 +665,89 @@ struct nix_rx_mce_s { uint64_t next : 16; }; +enum nix_band_prof_layers { + BAND_PROF_LEAF_LAYER = 0, + BAND_PROF_INVAL_LAYER = 1, + BAND_PROF_MID_LAYER = 2, + BAND_PROF_TOP_LAYER = 3, + BAND_PROF_NUM_LAYERS = 4, +}; + +enum NIX_RX_BAND_PROF_ACTIONRESULT_E { + NIX_RX_BAND_PROF_ACTIONRESULT_PASS = 0x0, + NIX_RX_BAND_PROF_ACTIONRESULT_DROP = 0x1, + NIX_RX_BAND_PROF_ACTIONRESULT_RED = 0x2, +}; + +enum nix_band_prof_pc_mode { + NIX_RX_PC_MODE_VLAN = 0, + NIX_RX_PC_MODE_DSCP = 1, + NIX_RX_PC_MODE_GEN = 2, + NIX_RX_PC_MODE_RSVD = 3, +}; + +/* NIX ingress policer bandwidth profile structure */ +struct nix_bandprof_s { + uint64_t pc_mode : 2; /* W0 */ + uint64_t icolor : 2; + uint64_t tnl_ena : 1; + uint64_t reserved_5_7 : 3; + uint64_t peir_exponent : 5; + uint64_t reserved_13_15 : 3; + uint64_t pebs_exponent : 5; + uint64_t reserved_21_23 : 3; + uint64_t cir_exponent : 5; + uint64_t reserved_29_31 : 3; + uint64_t cbs_exponent : 5; + uint64_t reserved_37_39 : 3; + uint64_t peir_mantissa : 8; + uint64_t pebs_mantissa : 8; + uint64_t cir_mantissa : 8; + uint64_t cbs_mantissa : 8; /* W1 */ + uint64_t lmode : 1; + uint64_t l_sellect : 3; + uint64_t rdiv : 4; + uint64_t adjust_exponent : 5; + uint64_t reserved_85_86 : 2; + uint64_t adjust_mantissa : 9; + uint64_t gc_action : 2; + uint64_t yc_action : 2; + uint64_t rc_action : 2; + uint64_t meter_algo : 2; + uint64_t band_prof_id : 7; + uint64_t reserved_111_118 : 8; + uint64_t hl_en : 1; + uint64_t reserved_120_127 : 8; + uint64_t ts : 48; /* W2 */ + uint64_t reserved_176_191 : 16; + uint64_t pe_accum : 32; /* W3 */ + uint64_t c_accum : 32; + uint64_t green_pkt_pass : 48; /* W4 */ + uint64_t reserved_304_319 : 16; + uint64_t yellow_pkt_pass : 48; /* W5 */ + uint64_t reserved_368_383 : 16; + uint64_t red_pkt_pass : 48; /* W6 */ + uint64_t reserved_432_447 : 16; + uint64_t green_octs_pass : 48; /* W7 */ + uint64_t reserved_496_511 : 16; + uint64_t yellow_octs_pass : 48; /* W8 */ + uint64_t reserved_560_575 : 16; + uint64_t red_octs_pass : 48; /* W9 */ + uint64_t reserved_624_639 : 16; + uint64_t green_pkt_drop : 48; /* W10 */ + uint64_t reserved_688_703 : 16; + uint64_t yellow_pkt_drop : 48; /* W11 */ + uint64_t reserved_752_767 : 16; + uint64_t red_pkt_drop : 48; /* W12 */ + uint64_t reserved_816_831 : 16; + uint64_t green_octs_drop : 48; /* W13 */ + uint64_t reserved_880_895 : 16; + uint64_t yellow_octs_drop : 48; /* W14 */ + uint64_t reserved_944_959 : 16; + uint64_t red_octs_drop : 48; /* W15 */ + uint64_t reserved_1008_1023 : 16; +}; + enum nix_lsoalg { NIX_LSOALG_NOP, NIX_LSOALG_ADD_SEGNUM, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c index 9ec0313f13fc..1b08896b46d2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c @@ -179,3 +179,326 @@ void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx) sq->head++; sq->head &= (sq->sqe_cnt - 1); } + +int cn10k_free_all_ipolicers(struct otx2_nic *pfvf) +{ + struct nix_bandprof_free_req *req; + int rc; + + if (is_dev_otx2(pfvf->pdev)) + return 0; + + mutex_lock(&pfvf->mbox.lock); + + req = otx2_mbox_alloc_msg_nix_bandprof_free(&pfvf->mbox); + if (!req) { + rc = -ENOMEM; + goto out; + } + + /* Free all bandwidth profiles allocated */ + req->free_all = true; + + rc = otx2_sync_mbox_msg(&pfvf->mbox); +out: + mutex_unlock(&pfvf->mbox.lock); + return rc; +} + +int cn10k_alloc_leaf_profile(struct otx2_nic *pfvf, u16 *leaf) +{ + struct nix_bandprof_alloc_req *req; + struct nix_bandprof_alloc_rsp *rsp; + int rc; + + req = otx2_mbox_alloc_msg_nix_bandprof_alloc(&pfvf->mbox); + if (!req) + return -ENOMEM; + + req->prof_count[BAND_PROF_LEAF_LAYER] = 1; + + rc = otx2_sync_mbox_msg(&pfvf->mbox); + if (rc) + goto out; + + rsp = (struct nix_bandprof_alloc_rsp *) + otx2_mbox_get_rsp(&pfvf->mbox.mbox, 0, &req->hdr); + if (!rsp->prof_count[BAND_PROF_LEAF_LAYER]) { + rc = -EIO; + goto out; + } + + *leaf = rsp->prof_idx[BAND_PROF_LEAF_LAYER][0]; +out: + if (rc) { + dev_warn(pfvf->dev, + "Failed to allocate ingress bandwidth policer\n"); + } + + return rc; +} + +int cn10k_alloc_matchall_ipolicer(struct otx2_nic *pfvf) +{ + struct otx2_hw *hw = &pfvf->hw; + int ret; + + mutex_lock(&pfvf->mbox.lock); + + ret = cn10k_alloc_leaf_profile(pfvf, &hw->matchall_ipolicer); + + mutex_unlock(&pfvf->mbox.lock); + + return ret; +} + +#define POLICER_TIMESTAMP 1 /* 1 second */ +#define MAX_RATE_EXP 22 /* Valid rate exponent range: 0 - 22 */ + +static void cn10k_get_ingress_burst_cfg(u32 burst, u32 *burst_exp, + u32 *burst_mantissa) +{ + int tmp; + + /* Burst is calculated as + * (1+[BURST_MANTISSA]/256)*2^[BURST_EXPONENT] + * This is the upper limit on number tokens (bytes) that + * can be accumulated in the bucket. + */ + *burst_exp = ilog2(burst); + if (burst < 256) { + /* No float: can't express mantissa in this case */ + *burst_mantissa = 0; + return; + } + + if (*burst_exp > MAX_RATE_EXP) + *burst_exp = MAX_RATE_EXP; + + /* Calculate mantissa + * Find remaining bytes 'burst - 2^burst_exp' + * mantissa = (remaining bytes) / 2^ (burst_exp - 8) + */ + tmp = burst - rounddown_pow_of_two(burst); + *burst_mantissa = tmp / (1UL << (*burst_exp - 8)); +} + +static void cn10k_get_ingress_rate_cfg(u64 rate, u32 *rate_exp, + u32 *rate_mantissa, u32 *rdiv) +{ + u32 div = 0; + u32 exp = 0; + u64 tmp; + + /* Figure out mantissa, exponent and divider from given max pkt rate + * + * To achieve desired rate HW adds + * (1+[RATE_MANTISSA]/256)*2^[RATE_EXPONENT] tokens (bytes) at every + * policer timeunit * 2^rdiv ie 2 * 2^rdiv usecs, to the token bucket. + * Here policer timeunit is 2 usecs and rate is in bits per sec. + * Since floating point cannot be used below algorithm uses 1000000 + * scale factor to support rates upto 100Gbps. + */ + tmp = rate * 32 * 2; + if (tmp < 256000000) { + while (tmp < 256000000) { + tmp = tmp * 2; + div++; + } + } else { + for (exp = 0; tmp >= 512000000 && exp <= MAX_RATE_EXP; exp++) + tmp = tmp / 2; + + if (exp > MAX_RATE_EXP) + exp = MAX_RATE_EXP; + } + + *rate_mantissa = (tmp - 256000000) / 1000000; + *rate_exp = exp; + *rdiv = div; +} + +int cn10k_map_unmap_rq_policer(struct otx2_nic *pfvf, int rq_idx, + u16 policer, bool map) +{ + struct nix_cn10k_aq_enq_req *aq; + + aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox); + if (!aq) + return -ENOMEM; + + /* Enable policing and set the bandwidth profile (policer) index */ + if (map) + aq->rq.policer_ena = 1; + else + aq->rq.policer_ena = 0; + aq->rq_mask.policer_ena = 1; + + aq->rq.band_prof_id = policer; + aq->rq_mask.band_prof_id = GENMASK(9, 0); + + /* Fill AQ info */ + aq->qidx = rq_idx; + aq->ctype = NIX_AQ_CTYPE_RQ; + aq->op = NIX_AQ_INSTOP_WRITE; + + return otx2_sync_mbox_msg(&pfvf->mbox); +} + +int cn10k_free_leaf_profile(struct otx2_nic *pfvf, u16 leaf) +{ + struct nix_bandprof_free_req *req; + + req = otx2_mbox_alloc_msg_nix_bandprof_free(&pfvf->mbox); + if (!req) + return -ENOMEM; + + req->prof_count[BAND_PROF_LEAF_LAYER] = 1; + req->prof_idx[BAND_PROF_LEAF_LAYER][0] = leaf; + + return otx2_sync_mbox_msg(&pfvf->mbox); +} + +int cn10k_free_matchall_ipolicer(struct otx2_nic *pfvf) +{ + struct otx2_hw *hw = &pfvf->hw; + int qidx, rc; + + mutex_lock(&pfvf->mbox.lock); + + /* Remove RQ's policer mapping */ + for (qidx = 0; qidx < hw->rx_queues; qidx++) + cn10k_map_unmap_rq_policer(pfvf, qidx, + hw->matchall_ipolicer, false); + + rc = cn10k_free_leaf_profile(pfvf, hw->matchall_ipolicer); + + mutex_unlock(&pfvf->mbox.lock); + return rc; +} + +int cn10k_set_ipolicer_rate(struct otx2_nic *pfvf, u16 profile, + u32 burst, u64 rate, bool pps) +{ + struct nix_cn10k_aq_enq_req *aq; + u32 burst_exp, burst_mantissa; + u32 rate_exp, rate_mantissa; + u32 rdiv; + + /* Get exponent and mantissa values for the desired rate */ + cn10k_get_ingress_burst_cfg(burst, &burst_exp, &burst_mantissa); + cn10k_get_ingress_rate_cfg(rate, &rate_exp, &rate_mantissa, &rdiv); + + /* Init bandwidth profile */ + aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox); + if (!aq) + return -ENOMEM; + + /* Set initial color mode to blind */ + aq->prof.icolor = 0x03; + aq->prof_mask.icolor = 0x03; + + /* Set rate and burst values */ + aq->prof.cir_exponent = rate_exp; + aq->prof_mask.cir_exponent = 0x1F; + + aq->prof.cir_mantissa = rate_mantissa; + aq->prof_mask.cir_mantissa = 0xFF; + + aq->prof.cbs_exponent = burst_exp; + aq->prof_mask.cbs_exponent = 0x1F; + + aq->prof.cbs_mantissa = burst_mantissa; + aq->prof_mask.cbs_mantissa = 0xFF; + + aq->prof.rdiv = rdiv; + aq->prof_mask.rdiv = 0xF; + + if (pps) { + /* The amount of decremented tokens is calculated according to + * the following equation: + * max([ LMODE ? 0 : (packet_length - LXPTR)] + + * ([ADJUST_MANTISSA]/256 - 1) * 2^[ADJUST_EXPONENT], + * 1/256) + * if LMODE is 1 then rate limiting will be based on + * PPS otherwise bps. + * The aim of the ADJUST value is to specify a token cost per + * packet in contrary to the packet length that specifies a + * cost per byte. To rate limit based on PPS adjust mantissa + * is set as 384 and exponent as 1 so that number of tokens + * decremented becomes 1 i.e, 1 token per packeet. + */ + aq->prof.adjust_exponent = 1; + aq->prof_mask.adjust_exponent = 0x1F; + + aq->prof.adjust_mantissa = 384; + aq->prof_mask.adjust_mantissa = 0x1FF; + + aq->prof.lmode = 0x1; + aq->prof_mask.lmode = 0x1; + } + + /* Two rate three color marker + * With PEIR/EIR set to zero, color will be either green or red + */ + aq->prof.meter_algo = 2; + aq->prof_mask.meter_algo = 0x3; + + aq->prof.rc_action = NIX_RX_BAND_PROF_ACTIONRESULT_DROP; + aq->prof_mask.rc_action = 0x3; + + aq->prof.yc_action = NIX_RX_BAND_PROF_ACTIONRESULT_PASS; + aq->prof_mask.yc_action = 0x3; + + aq->prof.gc_action = NIX_RX_BAND_PROF_ACTIONRESULT_PASS; + aq->prof_mask.gc_action = 0x3; + + /* Setting exponent value as 24 and mantissa as 0 configures + * the bucket with zero values making bucket unused. Peak + * information rate and Excess information rate buckets are + * unused here. + */ + aq->prof.peir_exponent = 24; + aq->prof_mask.peir_exponent = 0x1F; + + aq->prof.peir_mantissa = 0; + aq->prof_mask.peir_mantissa = 0xFF; + + aq->prof.pebs_exponent = 24; + aq->prof_mask.pebs_exponent = 0x1F; + + aq->prof.pebs_mantissa = 0; + aq->prof_mask.pebs_mantissa = 0xFF; + + /* Fill AQ info */ + aq->qidx = profile; + aq->ctype = NIX_AQ_CTYPE_BANDPROF; + aq->op = NIX_AQ_INSTOP_WRITE; + + return otx2_sync_mbox_msg(&pfvf->mbox); +} + +int cn10k_set_matchall_ipolicer_rate(struct otx2_nic *pfvf, + u32 burst, u64 rate) +{ + struct otx2_hw *hw = &pfvf->hw; + int qidx, rc; + + mutex_lock(&pfvf->mbox.lock); + + rc = cn10k_set_ipolicer_rate(pfvf, hw->matchall_ipolicer, burst, + rate, false); + if (rc) + goto out; + + for (qidx = 0; qidx < hw->rx_queues; qidx++) { + rc = cn10k_map_unmap_rq_policer(pfvf, qidx, + hw->matchall_ipolicer, true); + if (rc) + break; + } + +out: + mutex_unlock(&pfvf->mbox.lock); + return rc; +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h index e0bc595cbb78..71292a4cf1f3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h @@ -14,4 +14,15 @@ void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx); int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura); int cn10k_pf_lmtst_init(struct otx2_nic *pf); int cn10k_vf_lmtst_init(struct otx2_nic *vf); +int cn10k_free_all_ipolicers(struct otx2_nic *pfvf); +int cn10k_alloc_matchall_ipolicer(struct otx2_nic *pfvf); +int cn10k_free_matchall_ipolicer(struct otx2_nic *pfvf); +int cn10k_set_matchall_ipolicer_rate(struct otx2_nic *pfvf, + u32 burst, u64 rate); +int cn10k_map_unmap_rq_policer(struct otx2_nic *pfvf, int rq_idx, + u16 policer, bool map); +int cn10k_alloc_leaf_profile(struct otx2_nic *pfvf, u16 *leaf); +int cn10k_set_ipolicer_rate(struct otx2_nic *pfvf, u16 profile, + u32 burst, u64 rate, bool pps); +int cn10k_free_leaf_profile(struct otx2_nic *pfvf, u16 leaf); #endif /* CN10K_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 45730d0d92f2..234b330f3183 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -180,6 +180,7 @@ struct otx2_hw { /* NIX */ u16 txschq_list[NIX_TXSCH_LVL_CNT][MAX_TXSCHQ_PER_FUNC]; + u16 matchall_ipolicer; /* HW settings, coalescing etc */ u16 rx_chan_base; @@ -223,6 +224,11 @@ struct otx2_hw { u64 *nix_lmt_base; }; +enum vfperm { + OTX2_RESET_VF_PERM, + OTX2_TRUSTED_VF, +}; + struct otx2_vf_config { struct otx2_nic *pf; struct delayed_work link_event_work; @@ -230,6 +236,7 @@ struct otx2_vf_config { u8 mac[ETH_ALEN]; u16 vlan; int tx_vtag_idx; + bool trusted; }; struct flr_work { @@ -261,24 +268,26 @@ struct otx2_mac_table { struct otx2_flow_config { u16 entry[NPC_MAX_NONCONTIG_ENTRIES]; - u32 nr_flows; -#define OTX2_MAX_NTUPLE_FLOWS 32 -#define OTX2_MAX_UNICAST_FLOWS 8 -#define OTX2_MAX_VLAN_FLOWS 1 -#define OTX2_MAX_TC_FLOWS OTX2_MAX_NTUPLE_FLOWS -#define OTX2_MCAM_COUNT (OTX2_MAX_NTUPLE_FLOWS + \ + u16 *flow_ent; + u16 *def_ent; + u16 nr_flows; +#define OTX2_DEFAULT_FLOWCOUNT 16 +#define OTX2_MAX_UNICAST_FLOWS 8 +#define OTX2_MAX_VLAN_FLOWS 1 +#define OTX2_MAX_TC_FLOWS OTX2_DEFAULT_FLOWCOUNT +#define OTX2_MCAM_COUNT (OTX2_DEFAULT_FLOWCOUNT + \ OTX2_MAX_UNICAST_FLOWS + \ OTX2_MAX_VLAN_FLOWS) - u32 ntuple_offset; - u32 unicast_offset; - u32 rx_vlan_offset; - u32 vf_vlan_offset; -#define OTX2_PER_VF_VLAN_FLOWS 2 /* rx+tx per VF */ + u16 ntuple_offset; + u16 unicast_offset; + u16 rx_vlan_offset; + u16 vf_vlan_offset; +#define OTX2_PER_VF_VLAN_FLOWS 2 /* Rx + Tx per VF */ #define OTX2_VF_VLAN_RX_INDEX 0 #define OTX2_VF_VLAN_TX_INDEX 1 - u32 tc_flower_offset; - u32 ntuple_max_flows; - u32 tc_max_flows; + u16 tc_flower_offset; + u16 ntuple_max_flows; + u16 tc_max_flows; struct list_head flow_list; }; @@ -319,6 +328,7 @@ struct otx2_nic { #define OTX2_FLAG_TX_PAUSE_ENABLED BIT_ULL(10) #define OTX2_FLAG_TC_FLOWER_SUPPORT BIT_ULL(11) #define OTX2_FLAG_TC_MATCHALL_EGRESS_ENABLED BIT_ULL(12) +#define OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED BIT_ULL(13) u64 flags; struct otx2_qset qset; @@ -362,6 +372,7 @@ struct otx2_nic { struct otx2_flow_config *flow_cfg; struct otx2_tc_info tc_info; + unsigned long rq_bmap; }; static inline bool is_otx2_lbkvf(struct pci_dev *pdev) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 9d9a2e438acf..8df748e0677b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -286,6 +286,12 @@ static int otx2_set_channels(struct net_device *dev, if (!channel->rx_count || !channel->tx_count) return -EINVAL; + if (bitmap_weight(&pfvf->rq_bmap, pfvf->hw.rx_queues) > 1) { + netdev_err(dev, + "Receive queues are in use by TC police action\n"); + return -EINVAL; + } + if (if_up) dev->netdev_ops->ndo_stop(dev); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 0b4fa92ba821..8c97106bdd1c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -20,13 +20,125 @@ struct otx2_flow { int vf; }; +static void otx2_clear_ntuple_flow_info(struct otx2_nic *pfvf, struct otx2_flow_config *flow_cfg) +{ + devm_kfree(pfvf->dev, flow_cfg->flow_ent); + flow_cfg->flow_ent = NULL; + flow_cfg->ntuple_max_flows = 0; + flow_cfg->tc_max_flows = 0; +} + +static int otx2_free_ntuple_mcam_entries(struct otx2_nic *pfvf) +{ + struct otx2_flow_config *flow_cfg = pfvf->flow_cfg; + struct npc_mcam_free_entry_req *req; + int ent, err; + + if (!flow_cfg->ntuple_max_flows) + return 0; + + mutex_lock(&pfvf->mbox.lock); + for (ent = 0; ent < flow_cfg->ntuple_max_flows; ent++) { + req = otx2_mbox_alloc_msg_npc_mcam_free_entry(&pfvf->mbox); + if (!req) + break; + + req->entry = flow_cfg->flow_ent[ent]; + + /* Send message to AF to free MCAM entries */ + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) + break; + } + mutex_unlock(&pfvf->mbox.lock); + otx2_clear_ntuple_flow_info(pfvf, flow_cfg); + return 0; +} + +static int otx2_alloc_ntuple_mcam_entries(struct otx2_nic *pfvf, u16 count) +{ + struct otx2_flow_config *flow_cfg = pfvf->flow_cfg; + struct npc_mcam_alloc_entry_req *req; + struct npc_mcam_alloc_entry_rsp *rsp; + int ent, allocated = 0; + + /* Free current ones and allocate new ones with requested count */ + otx2_free_ntuple_mcam_entries(pfvf); + + if (!count) + return 0; + + flow_cfg->flow_ent = devm_kmalloc_array(pfvf->dev, count, + sizeof(u16), GFP_KERNEL); + if (!flow_cfg->flow_ent) + return -ENOMEM; + + mutex_lock(&pfvf->mbox.lock); + + /* In a single request a max of NPC_MAX_NONCONTIG_ENTRIES MCAM entries + * can only be allocated. + */ + while (allocated < count) { + req = otx2_mbox_alloc_msg_npc_mcam_alloc_entry(&pfvf->mbox); + if (!req) + goto exit; + + req->contig = false; + req->count = (count - allocated) > NPC_MAX_NONCONTIG_ENTRIES ? + NPC_MAX_NONCONTIG_ENTRIES : count - allocated; + req->priority = NPC_MCAM_HIGHER_PRIO; + req->ref_entry = flow_cfg->def_ent[0]; + + /* Send message to AF */ + if (otx2_sync_mbox_msg(&pfvf->mbox)) + goto exit; + + rsp = (struct npc_mcam_alloc_entry_rsp *)otx2_mbox_get_rsp + (&pfvf->mbox.mbox, 0, &req->hdr); + + for (ent = 0; ent < rsp->count; ent++) + flow_cfg->flow_ent[ent + allocated] = rsp->entry_list[ent]; + + allocated += rsp->count; + + /* If this request is not fulfilled, no need to send + * further requests. + */ + if (rsp->count != req->count) + break; + } + +exit: + mutex_unlock(&pfvf->mbox.lock); + + flow_cfg->ntuple_offset = 0; + flow_cfg->ntuple_max_flows = allocated; + flow_cfg->tc_max_flows = allocated; + + if (allocated != count) + netdev_info(pfvf->netdev, + "Unable to allocate %d MCAM entries for ntuple, got %d\n", + count, allocated); + + return allocated; +} + int otx2_alloc_mcam_entries(struct otx2_nic *pfvf) { struct otx2_flow_config *flow_cfg = pfvf->flow_cfg; struct npc_mcam_alloc_entry_req *req; struct npc_mcam_alloc_entry_rsp *rsp; int vf_vlan_max_flows; - int i; + int ent, count; + + vf_vlan_max_flows = pfvf->total_vfs * OTX2_PER_VF_VLAN_FLOWS; + count = OTX2_MAX_UNICAST_FLOWS + + OTX2_MAX_VLAN_FLOWS + vf_vlan_max_flows; + + flow_cfg->def_ent = devm_kmalloc_array(pfvf->dev, count, + sizeof(u16), GFP_KERNEL); + if (!flow_cfg->def_ent) + return -ENOMEM; mutex_lock(&pfvf->mbox.lock); @@ -36,9 +148,8 @@ int otx2_alloc_mcam_entries(struct otx2_nic *pfvf) return -ENOMEM; } - vf_vlan_max_flows = pfvf->total_vfs * OTX2_PER_VF_VLAN_FLOWS; req->contig = false; - req->count = OTX2_MCAM_COUNT + vf_vlan_max_flows; + req->count = count; /* Send message to AF */ if (otx2_sync_mbox_msg(&pfvf->mbox)) { @@ -51,37 +162,36 @@ int otx2_alloc_mcam_entries(struct otx2_nic *pfvf) if (rsp->count != req->count) { netdev_info(pfvf->netdev, - "Unable to allocate %d MCAM entries, got %d\n", - req->count, rsp->count); - /* support only ntuples here */ - flow_cfg->ntuple_max_flows = rsp->count; - flow_cfg->ntuple_offset = 0; - pfvf->flags |= OTX2_FLAG_NTUPLE_SUPPORT; - flow_cfg->tc_max_flows = flow_cfg->ntuple_max_flows; - pfvf->flags |= OTX2_FLAG_TC_FLOWER_SUPPORT; - } else { - flow_cfg->vf_vlan_offset = 0; - flow_cfg->ntuple_offset = flow_cfg->vf_vlan_offset + - vf_vlan_max_flows; - flow_cfg->tc_flower_offset = flow_cfg->ntuple_offset; - flow_cfg->unicast_offset = flow_cfg->ntuple_offset + - OTX2_MAX_NTUPLE_FLOWS; - flow_cfg->rx_vlan_offset = flow_cfg->unicast_offset + - OTX2_MAX_UNICAST_FLOWS; - pfvf->flags |= OTX2_FLAG_NTUPLE_SUPPORT; - pfvf->flags |= OTX2_FLAG_UCAST_FLTR_SUPPORT; - pfvf->flags |= OTX2_FLAG_RX_VLAN_SUPPORT; - pfvf->flags |= OTX2_FLAG_VF_VLAN_SUPPORT; - pfvf->flags |= OTX2_FLAG_TC_FLOWER_SUPPORT; + "Unable to allocate MCAM entries for ucast, vlan and vf_vlan\n"); + mutex_unlock(&pfvf->mbox.lock); + devm_kfree(pfvf->dev, flow_cfg->def_ent); + return 0; } - for (i = 0; i < rsp->count; i++) - flow_cfg->entry[i] = rsp->entry_list[i]; + for (ent = 0; ent < rsp->count; ent++) + flow_cfg->def_ent[ent] = rsp->entry_list[ent]; + + flow_cfg->vf_vlan_offset = 0; + flow_cfg->unicast_offset = vf_vlan_max_flows; + flow_cfg->rx_vlan_offset = flow_cfg->unicast_offset + + OTX2_MAX_UNICAST_FLOWS; + pfvf->flags |= OTX2_FLAG_UCAST_FLTR_SUPPORT; + pfvf->flags |= OTX2_FLAG_RX_VLAN_SUPPORT; + pfvf->flags |= OTX2_FLAG_VF_VLAN_SUPPORT; pfvf->flags |= OTX2_FLAG_MCAM_ENTRIES_ALLOC; - mutex_unlock(&pfvf->mbox.lock); + /* Allocate entries for Ntuple filters */ + count = otx2_alloc_ntuple_mcam_entries(pfvf, OTX2_DEFAULT_FLOWCOUNT); + if (count <= 0) { + otx2_clear_ntuple_flow_info(pfvf, flow_cfg); + return 0; + } + + pfvf->flags |= OTX2_FLAG_NTUPLE_SUPPORT; + pfvf->flags |= OTX2_FLAG_TC_FLOWER_SUPPORT; + return 0; } @@ -96,13 +206,14 @@ int otx2_mcam_flow_init(struct otx2_nic *pf) INIT_LIST_HEAD(&pf->flow_cfg->flow_list); - pf->flow_cfg->ntuple_max_flows = OTX2_MAX_NTUPLE_FLOWS; - pf->flow_cfg->tc_max_flows = pf->flow_cfg->ntuple_max_flows; - err = otx2_alloc_mcam_entries(pf); if (err) return err; + /* Check if MCAM entries are allocate or not */ + if (!(pf->flags & OTX2_FLAG_UCAST_FLTR_SUPPORT)) + return 0; + pf->mac_table = devm_kzalloc(pf->dev, sizeof(struct otx2_mac_table) * OTX2_MAX_UNICAST_FLOWS, GFP_KERNEL); if (!pf->mac_table) @@ -146,7 +257,7 @@ static int otx2_do_add_macfilter(struct otx2_nic *pf, const u8 *mac) ether_addr_copy(pf->mac_table[i].addr, mac); pf->mac_table[i].inuse = true; pf->mac_table[i].mcam_entry = - flow_cfg->entry[i + flow_cfg->unicast_offset]; + flow_cfg->def_ent[i + flow_cfg->unicast_offset]; req->entry = pf->mac_table[i].mcam_entry; break; } @@ -551,6 +662,7 @@ static int otx2_prepare_ipv6_flow(struct ethtool_rx_flow_spec *fsp, req->features |= BIT_ULL(NPC_IPPROTO_AH); else req->features |= BIT_ULL(NPC_IPPROTO_ESP); + break; default: break; } @@ -731,8 +843,7 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) if (!flow) return -ENOMEM; flow->location = fsp->location; - flow->entry = flow_cfg->entry[flow_cfg->ntuple_offset + - flow->location]; + flow->entry = flow_cfg->flow_ent[flow->location]; new = true; } /* struct copy */ @@ -836,9 +947,8 @@ int otx2_destroy_ntuple_flows(struct otx2_nic *pfvf) return -ENOMEM; } - req->start = flow_cfg->entry[flow_cfg->ntuple_offset]; - req->end = flow_cfg->entry[flow_cfg->ntuple_offset + - flow_cfg->ntuple_max_flows - 1]; + req->start = flow_cfg->flow_ent[0]; + req->end = flow_cfg->flow_ent[flow_cfg->ntuple_max_flows - 1]; err = otx2_sync_mbox_msg(&pfvf->mbox); mutex_unlock(&pfvf->mbox.lock); @@ -905,7 +1015,7 @@ int otx2_install_rxvlan_offload_flow(struct otx2_nic *pfvf) return -ENOMEM; } - req->entry = flow_cfg->entry[flow_cfg->rx_vlan_offset]; + req->entry = flow_cfg->def_ent[flow_cfg->rx_vlan_offset]; req->intf = NIX_INTF_RX; ether_addr_copy(req->packet.dmac, pfvf->netdev->dev_addr); eth_broadcast_addr((u8 *)&req->mask.dmac); @@ -934,7 +1044,7 @@ static int otx2_delete_rxvlan_offload_flow(struct otx2_nic *pfvf) return -ENOMEM; } - req->entry = flow_cfg->entry[flow_cfg->rx_vlan_offset]; + req->entry = flow_cfg->def_ent[flow_cfg->rx_vlan_offset]; /* Send message to AF */ err = otx2_sync_mbox_msg(&pfvf->mbox); mutex_unlock(&pfvf->mbox.lock); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 03004fdac0c6..59912f73417b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -39,6 +39,8 @@ MODULE_DESCRIPTION(DRV_STRING); MODULE_LICENSE("GPL v2"); MODULE_DEVICE_TABLE(pci, otx2_pf_id_table); +static void otx2_vf_link_event_task(struct work_struct *work); + enum { TYPE_PFAF, TYPE_PFVF, @@ -1459,6 +1461,9 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) otx2_free_cq_res(pf); + /* Free all ingress bandwidth profiles allocated */ + cn10k_free_all_ipolicers(pf); + mutex_lock(&mbox->lock); /* Reset NIX LF */ free_req = otx2_mbox_alloc_msg_nix_lf_free(mbox); @@ -1820,9 +1825,11 @@ static void otx2_do_set_rx_mode(struct work_struct *work) if (promisc) req->mode |= NIX_RX_MODE_PROMISC; - else if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST)) + if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST)) req->mode |= NIX_RX_MODE_ALLMULTI; + req->mode |= NIX_RX_MODE_USE_MCE; + otx2_sync_mbox_msg(&pf->mbox); mutex_unlock(&pf->mbox.lock); } @@ -2044,7 +2051,7 @@ static int otx2_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) if (!netif_running(netdev)) return -EAGAIN; - if (vf >= pci_num_vf(pdev)) + if (vf >= pf->total_vfs) return -EINVAL; if (!is_valid_ether_addr(mac)) @@ -2055,7 +2062,8 @@ static int otx2_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) ret = otx2_do_set_vf_mac(pf, vf, mac); if (ret == 0) - dev_info(&pdev->dev, "Reload VF driver to apply the changes\n"); + dev_info(&pdev->dev, + "Load/Reload VF driver\n"); return ret; } @@ -2104,7 +2112,7 @@ static int otx2_do_set_vf_vlan(struct otx2_nic *pf, int vf, u16 vlan, u8 qos, } idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_RX_INDEX); del_req->entry = - flow_cfg->entry[flow_cfg->vf_vlan_offset + idx]; + flow_cfg->def_ent[flow_cfg->vf_vlan_offset + idx]; err = otx2_sync_mbox_msg(&pf->mbox); if (err) goto out; @@ -2117,7 +2125,7 @@ static int otx2_do_set_vf_vlan(struct otx2_nic *pf, int vf, u16 vlan, u8 qos, } idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_TX_INDEX); del_req->entry = - flow_cfg->entry[flow_cfg->vf_vlan_offset + idx]; + flow_cfg->def_ent[flow_cfg->vf_vlan_offset + idx]; err = otx2_sync_mbox_msg(&pf->mbox); goto out; @@ -2131,7 +2139,7 @@ static int otx2_do_set_vf_vlan(struct otx2_nic *pf, int vf, u16 vlan, u8 qos, } idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_RX_INDEX); - req->entry = flow_cfg->entry[flow_cfg->vf_vlan_offset + idx]; + req->entry = flow_cfg->def_ent[flow_cfg->vf_vlan_offset + idx]; req->packet.vlan_tci = htons(vlan); req->mask.vlan_tci = htons(VLAN_VID_MASK); /* af fills the destination mac addr */ @@ -2182,7 +2190,7 @@ static int otx2_do_set_vf_vlan(struct otx2_nic *pf, int vf, u16 vlan, u8 qos, eth_zero_addr((u8 *)&req->mask.dmac); idx = ((vf * OTX2_PER_VF_VLAN_FLOWS) + OTX2_VF_VLAN_TX_INDEX); - req->entry = flow_cfg->entry[flow_cfg->vf_vlan_offset + idx]; + req->entry = flow_cfg->def_ent[flow_cfg->vf_vlan_offset + idx]; req->features = BIT_ULL(NPC_DMAC); req->channel = pf->hw.tx_chan_base; req->intf = NIX_INTF_TX; @@ -2241,10 +2249,63 @@ static int otx2_get_vf_config(struct net_device *netdev, int vf, ivi->vf = vf; ether_addr_copy(ivi->mac, config->mac); ivi->vlan = config->vlan; + ivi->trusted = config->trusted; return 0; } +static int otx2_set_vf_permissions(struct otx2_nic *pf, int vf, + int req_perm) +{ + struct set_vf_perm *req; + int rc; + + mutex_lock(&pf->mbox.lock); + req = otx2_mbox_alloc_msg_set_vf_perm(&pf->mbox); + if (!req) { + rc = -ENOMEM; + goto out; + } + + /* Let AF reset VF permissions as sriov is disabled */ + if (req_perm == OTX2_RESET_VF_PERM) { + req->flags |= RESET_VF_PERM; + } else if (req_perm == OTX2_TRUSTED_VF) { + if (pf->vf_configs[vf].trusted) + req->flags |= VF_TRUSTED; + } + + req->vf = vf; + rc = otx2_sync_mbox_msg(&pf->mbox); +out: + mutex_unlock(&pf->mbox.lock); + return rc; +} + +static int otx2_ndo_set_vf_trust(struct net_device *netdev, int vf, + bool enable) +{ + struct otx2_nic *pf = netdev_priv(netdev); + struct pci_dev *pdev = pf->pdev; + int rc; + + if (vf >= pci_num_vf(pdev)) + return -EINVAL; + + if (pf->vf_configs[vf].trusted == enable) + return 0; + + pf->vf_configs[vf].trusted = enable; + rc = otx2_set_vf_permissions(pf, vf, OTX2_TRUSTED_VF); + + if (rc) + pf->vf_configs[vf].trusted = !enable; + else + netdev_info(pf->netdev, "VF %d is %strusted\n", + vf, enable ? "" : "not "); + return rc; +} + static const struct net_device_ops otx2_netdev_ops = { .ndo_open = otx2_open, .ndo_stop = otx2_stop, @@ -2261,6 +2322,7 @@ static const struct net_device_ops otx2_netdev_ops = { .ndo_set_vf_vlan = otx2_set_vf_vlan, .ndo_get_vf_config = otx2_get_vf_config, .ndo_setup_tc = otx2_setup_tc, + .ndo_set_vf_trust = otx2_ndo_set_vf_trust, }; static int otx2_wq_init(struct otx2_nic *pf) @@ -2315,6 +2377,40 @@ static int otx2_realloc_msix_vectors(struct otx2_nic *pf) return otx2_register_mbox_intr(pf, false); } +static int otx2_sriov_vfcfg_init(struct otx2_nic *pf) +{ + int i; + + pf->vf_configs = devm_kcalloc(pf->dev, pf->total_vfs, + sizeof(struct otx2_vf_config), + GFP_KERNEL); + if (!pf->vf_configs) + return -ENOMEM; + + for (i = 0; i < pf->total_vfs; i++) { + pf->vf_configs[i].pf = pf; + pf->vf_configs[i].intf_down = true; + pf->vf_configs[i].trusted = false; + INIT_DELAYED_WORK(&pf->vf_configs[i].link_event_work, + otx2_vf_link_event_task); + } + + return 0; +} + +static void otx2_sriov_vfcfg_cleanup(struct otx2_nic *pf) +{ + int i; + + if (!pf->vf_configs) + return; + + for (i = 0; i < pf->total_vfs; i++) { + cancel_delayed_work_sync(&pf->vf_configs[i].link_event_work); + otx2_set_vf_permissions(pf, i, OTX2_RESET_VF_PERM); + } +} + static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct device *dev = &pdev->dev; @@ -2509,6 +2605,11 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (err) goto err_mcam_flow_del; + /* Initialize SR-IOV resources */ + err = otx2_sriov_vfcfg_init(pf); + if (err) + goto err_pf_sriov_init; + /* Enable link notifications */ otx2_cgx_config_linkevents(pf, true); @@ -2518,6 +2619,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; +err_pf_sriov_init: + otx2_shutdown_tc(pf); err_mcam_flow_del: otx2_mcam_flow_del(pf); err_unreg_netdev: @@ -2576,7 +2679,7 @@ static int otx2_sriov_enable(struct pci_dev *pdev, int numvfs) { struct net_device *netdev = pci_get_drvdata(pdev); struct otx2_nic *pf = netdev_priv(netdev); - int ret, i; + int ret; /* Init PF <=> VF mailbox stuff */ ret = otx2_pfvf_mbox_init(pf, numvfs); @@ -2587,23 +2690,9 @@ static int otx2_sriov_enable(struct pci_dev *pdev, int numvfs) if (ret) goto free_mbox; - pf->vf_configs = kcalloc(numvfs, sizeof(struct otx2_vf_config), - GFP_KERNEL); - if (!pf->vf_configs) { - ret = -ENOMEM; - goto free_intr; - } - - for (i = 0; i < numvfs; i++) { - pf->vf_configs[i].pf = pf; - pf->vf_configs[i].intf_down = true; - INIT_DELAYED_WORK(&pf->vf_configs[i].link_event_work, - otx2_vf_link_event_task); - } - ret = otx2_pf_flr_init(pf, numvfs); if (ret) - goto free_configs; + goto free_intr; ret = otx2_register_flr_me_intr(pf, numvfs); if (ret) @@ -2618,8 +2707,6 @@ free_flr_intr: otx2_disable_flr_me_intr(pf); free_flr: otx2_flr_wq_destroy(pf); -free_configs: - kfree(pf->vf_configs); free_intr: otx2_disable_pfvf_mbox_intr(pf, numvfs); free_mbox: @@ -2632,17 +2719,12 @@ static int otx2_sriov_disable(struct pci_dev *pdev) struct net_device *netdev = pci_get_drvdata(pdev); struct otx2_nic *pf = netdev_priv(netdev); int numvfs = pci_num_vf(pdev); - int i; if (!numvfs) return 0; pci_disable_sriov(pdev); - for (i = 0; i < pci_num_vf(pdev); i++) - cancel_delayed_work_sync(&pf->vf_configs[i].link_event_work); - kfree(pf->vf_configs); - otx2_disable_flr_me_intr(pf); otx2_flr_wq_destroy(pf); otx2_disable_pfvf_mbox_intr(pf, numvfs); @@ -2682,6 +2764,7 @@ static void otx2_remove(struct pci_dev *pdev) unregister_netdev(netdev); otx2_sriov_disable(pf->pdev); + otx2_sriov_vfcfg_cleanup(pf); if (pf->otx2_wq) destroy_workqueue(pf->otx2_wq); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 51157b283f6f..905fc02a7dfe 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -15,6 +15,7 @@ #include #include +#include "cn10k.h" #include "otx2_common.h" /* Egress rate limiting definitions */ @@ -41,11 +42,14 @@ struct otx2_tc_flow_stats { struct otx2_tc_flow { struct rhash_head node; unsigned long cookie; - u16 entry; unsigned int bitpos; struct rcu_head rcu; struct otx2_tc_flow_stats stats; spinlock_t lock; /* lock for stats */ + u16 rq; + u16 entry; + u16 leaf_profile; + bool is_act_police; }; static void otx2_get_egress_burst_cfg(u32 burst, u32 *burst_exp, @@ -220,17 +224,76 @@ static int otx2_tc_egress_matchall_delete(struct otx2_nic *nic, return err; } +static int otx2_tc_act_set_police(struct otx2_nic *nic, + struct otx2_tc_flow *node, + struct flow_cls_offload *f, + u64 rate, u32 burst, u32 mark, + struct npc_install_flow_req *req, bool pps) +{ + struct netlink_ext_ack *extack = f->common.extack; + struct otx2_hw *hw = &nic->hw; + int rq_idx, rc; + + rq_idx = find_first_zero_bit(&nic->rq_bmap, hw->rx_queues); + if (rq_idx >= hw->rx_queues) { + NL_SET_ERR_MSG_MOD(extack, "Police action rules exceeded"); + return -EINVAL; + } + + mutex_lock(&nic->mbox.lock); + + rc = cn10k_alloc_leaf_profile(nic, &node->leaf_profile); + if (rc) { + mutex_unlock(&nic->mbox.lock); + return rc; + } + + rc = cn10k_set_ipolicer_rate(nic, node->leaf_profile, burst, rate, pps); + if (rc) + goto free_leaf; + + rc = cn10k_map_unmap_rq_policer(nic, rq_idx, node->leaf_profile, true); + if (rc) + goto free_leaf; + + mutex_unlock(&nic->mbox.lock); + + req->match_id = mark & 0xFFFFULL; + req->index = rq_idx; + req->op = NIX_RX_ACTIONOP_UCAST; + set_bit(rq_idx, &nic->rq_bmap); + node->is_act_police = true; + node->rq = rq_idx; + + return 0; + +free_leaf: + if (cn10k_free_leaf_profile(nic, node->leaf_profile)) + netdev_err(nic->netdev, + "Unable to free leaf bandwidth profile(%d)\n", + node->leaf_profile); + mutex_unlock(&nic->mbox.lock); + return rc; +} + static int otx2_tc_parse_actions(struct otx2_nic *nic, struct flow_action *flow_action, - struct npc_install_flow_req *req) + struct npc_install_flow_req *req, + struct flow_cls_offload *f, + struct otx2_tc_flow *node) { + struct netlink_ext_ack *extack = f->common.extack; struct flow_action_entry *act; struct net_device *target; struct otx2_nic *priv; + u32 burst, mark = 0; + u8 nr_police = 0; + bool pps; + u64 rate; int i; if (!flow_action_has_entries(flow_action)) { - netdev_info(nic->netdev, "no tc actions specified"); + NL_SET_ERR_MSG_MOD(extack, "no tc actions specified"); return -EINVAL; } @@ -247,8 +310,8 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic, priv = netdev_priv(target); /* npc_install_flow_req doesn't support passing a target pcifunc */ if (rvu_get_pf(nic->pcifunc) != rvu_get_pf(priv->pcifunc)) { - netdev_info(nic->netdev, - "can't redirect to other pf/vf\n"); + NL_SET_ERR_MSG_MOD(extack, + "can't redirect to other pf/vf"); return -EOPNOTSUPP; } req->vf = priv->pcifunc & RVU_PFVF_FUNC_MASK; @@ -259,18 +322,55 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic, /* use RX_VTAG_TYPE7 which is initialized to strip vlan tag */ req->vtag0_type = NIX_AF_LFX_RX_VTAG_TYPE7; break; + case FLOW_ACTION_POLICE: + /* Ingress ratelimiting is not supported on OcteonTx2 */ + if (is_dev_otx2(nic->pdev)) { + NL_SET_ERR_MSG_MOD(extack, + "Ingress policing not supported on this platform"); + return -EOPNOTSUPP; + } + + if (act->police.rate_bytes_ps > 0) { + rate = act->police.rate_bytes_ps * 8; + burst = act->police.burst; + } else if (act->police.rate_pkt_ps > 0) { + /* The algorithm used to calculate rate + * mantissa, exponent values for a given token + * rate (token can be byte or packet) requires + * token rate to be mutiplied by 8. + */ + rate = act->police.rate_pkt_ps * 8; + burst = act->police.burst_pkt; + pps = true; + } + nr_police++; + break; + case FLOW_ACTION_MARK: + mark = act->mark; + break; default: return -EOPNOTSUPP; } } + if (nr_police > 1) { + NL_SET_ERR_MSG_MOD(extack, + "rate limit police offload requires a single action"); + return -EOPNOTSUPP; + } + + if (nr_police) + return otx2_tc_act_set_police(nic, node, f, rate, burst, + mark, req, pps); + return 0; } -static int otx2_tc_prepare_flow(struct otx2_nic *nic, +static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, struct flow_cls_offload *f, struct npc_install_flow_req *req) { + struct netlink_ext_ack *extack = f->common.extack; struct flow_msg *flow_spec = &req->packet; struct flow_msg *flow_mask = &req->mask; struct flow_dissector *dissector; @@ -335,7 +435,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, flow_rule_match_eth_addrs(rule, &match); if (!is_zero_ether_addr(match.mask->src)) { - netdev_err(nic->netdev, "src mac match not supported\n"); + NL_SET_ERR_MSG_MOD(extack, "src mac match not supported"); return -EOPNOTSUPP; } @@ -353,11 +453,11 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, flow_rule_match_ip(rule, &match); if ((ntohs(flow_spec->etype) != ETH_P_IP) && match.mask->tos) { - netdev_err(nic->netdev, "tos not supported\n"); + NL_SET_ERR_MSG_MOD(extack, "tos not supported"); return -EOPNOTSUPP; } if (match.mask->ttl) { - netdev_err(nic->netdev, "ttl not supported\n"); + NL_SET_ERR_MSG_MOD(extack, "ttl not supported"); return -EOPNOTSUPP; } flow_spec->tos = match.key->tos; @@ -413,8 +513,8 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, if (ipv6_addr_loopback(&match.key->dst) || ipv6_addr_loopback(&match.key->src)) { - netdev_err(nic->netdev, - "Flow matching on IPv6 loopback addr is not supported\n"); + NL_SET_ERR_MSG_MOD(extack, + "Flow matching IPv6 loopback addr not supported"); return -EOPNOTSUPP; } @@ -463,7 +563,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, req->features |= BIT_ULL(NPC_SPORT_SCTP); } - return otx2_tc_parse_actions(nic, &rule->action, req); + return otx2_tc_parse_actions(nic, &rule->action, req, f, node); } static int otx2_del_mcam_flow_entry(struct otx2_nic *nic, u16 entry) @@ -498,6 +598,7 @@ static int otx2_tc_del_flow(struct otx2_nic *nic, { struct otx2_tc_info *tc_info = &nic->tc_info; struct otx2_tc_flow *flow_node; + int err; flow_node = rhashtable_lookup_fast(&tc_info->flow_table, &tc_flow_cmd->cookie, @@ -508,6 +609,27 @@ static int otx2_tc_del_flow(struct otx2_nic *nic, return -EINVAL; } + if (flow_node->is_act_police) { + mutex_lock(&nic->mbox.lock); + + err = cn10k_map_unmap_rq_policer(nic, flow_node->rq, + flow_node->leaf_profile, false); + if (err) + netdev_err(nic->netdev, + "Unmapping RQ %d & profile %d failed\n", + flow_node->rq, flow_node->leaf_profile); + + err = cn10k_free_leaf_profile(nic, flow_node->leaf_profile); + if (err) + netdev_err(nic->netdev, + "Unable to free leaf bandwidth profile(%d)\n", + flow_node->leaf_profile); + + __clear_bit(flow_node->rq, &nic->rq_bmap); + + mutex_unlock(&nic->mbox.lock); + } + otx2_del_mcam_flow_entry(nic, flow_node->entry); WARN_ON(rhashtable_remove_fast(&nic->tc_info.flow_table, @@ -524,14 +646,21 @@ static int otx2_tc_del_flow(struct otx2_nic *nic, static int otx2_tc_add_flow(struct otx2_nic *nic, struct flow_cls_offload *tc_flow_cmd) { + struct netlink_ext_ack *extack = tc_flow_cmd->common.extack; struct otx2_tc_info *tc_info = &nic->tc_info; struct otx2_tc_flow *new_node, *old_node; - struct npc_install_flow_req *req; - int rc; + struct npc_install_flow_req *req, dummy; + int rc, err; if (!(nic->flags & OTX2_FLAG_TC_FLOWER_SUPPORT)) return -ENOMEM; + if (bitmap_full(tc_info->tc_entries_bitmap, nic->flow_cfg->tc_max_flows)) { + NL_SET_ERR_MSG_MOD(extack, + "Not enough MCAM space to add the flow"); + return -ENOMEM; + } + /* allocate memory for the new flow and it's node */ new_node = kzalloc(sizeof(*new_node), GFP_KERNEL); if (!new_node) @@ -539,17 +668,11 @@ static int otx2_tc_add_flow(struct otx2_nic *nic, spin_lock_init(&new_node->lock); new_node->cookie = tc_flow_cmd->cookie; - mutex_lock(&nic->mbox.lock); - req = otx2_mbox_alloc_msg_npc_install_flow(&nic->mbox); - if (!req) { - mutex_unlock(&nic->mbox.lock); - return -ENOMEM; - } + memset(&dummy, 0, sizeof(struct npc_install_flow_req)); - rc = otx2_tc_prepare_flow(nic, tc_flow_cmd, req); + rc = otx2_tc_prepare_flow(nic, new_node, tc_flow_cmd, &dummy); if (rc) { - otx2_mbox_reset(&nic->mbox.mbox, 0); - mutex_unlock(&nic->mbox.lock); + kfree_rcu(new_node, rcu); return rc; } @@ -560,18 +683,22 @@ static int otx2_tc_add_flow(struct otx2_nic *nic, if (old_node) otx2_tc_del_flow(nic, tc_flow_cmd); - if (bitmap_full(tc_info->tc_entries_bitmap, nic->flow_cfg->tc_max_flows)) { - netdev_err(nic->netdev, "Not enough MCAM space to add the flow\n"); - otx2_mbox_reset(&nic->mbox.mbox, 0); + mutex_lock(&nic->mbox.lock); + req = otx2_mbox_alloc_msg_npc_install_flow(&nic->mbox); + if (!req) { mutex_unlock(&nic->mbox.lock); - return -ENOMEM; + rc = -ENOMEM; + goto free_leaf; } + memcpy(&dummy.hdr, &req->hdr, sizeof(struct mbox_msghdr)); + memcpy(req, &dummy, sizeof(struct npc_install_flow_req)); + new_node->bitpos = find_first_zero_bit(tc_info->tc_entries_bitmap, nic->flow_cfg->tc_max_flows); req->channel = nic->hw.rx_chan_base; - req->entry = nic->flow_cfg->entry[nic->flow_cfg->tc_flower_offset + - nic->flow_cfg->tc_max_flows - new_node->bitpos]; + req->entry = nic->flow_cfg->flow_ent[nic->flow_cfg->tc_flower_offset + + nic->flow_cfg->tc_max_flows - new_node->bitpos]; req->intf = NIX_INTF_RX; req->set_cntr = 1; new_node->entry = req->entry; @@ -579,9 +706,10 @@ static int otx2_tc_add_flow(struct otx2_nic *nic, /* Send message to AF */ rc = otx2_sync_mbox_msg(&nic->mbox); if (rc) { - netdev_err(nic->netdev, "Failed to install MCAM flow entry\n"); + NL_SET_ERR_MSG_MOD(extack, "Failed to install MCAM flow entry"); mutex_unlock(&nic->mbox.lock); - goto out; + kfree_rcu(new_node, rcu); + goto free_leaf; } mutex_unlock(&nic->mbox.lock); @@ -591,12 +719,35 @@ static int otx2_tc_add_flow(struct otx2_nic *nic, if (rc) { otx2_del_mcam_flow_entry(nic, req->entry); kfree_rcu(new_node, rcu); - goto out; + goto free_leaf; } set_bit(new_node->bitpos, tc_info->tc_entries_bitmap); tc_info->num_entries++; -out: + + return 0; + +free_leaf: + if (new_node->is_act_police) { + mutex_lock(&nic->mbox.lock); + + err = cn10k_map_unmap_rq_policer(nic, new_node->rq, + new_node->leaf_profile, false); + if (err) + netdev_err(nic->netdev, + "Unmapping RQ %d & profile %d failed\n", + new_node->rq, new_node->leaf_profile); + err = cn10k_free_leaf_profile(nic, new_node->leaf_profile); + if (err) + netdev_err(nic->netdev, + "Unable to free leaf bandwidth profile(%d)\n", + new_node->leaf_profile); + + __clear_bit(new_node->rq, &nic->rq_bmap); + + mutex_unlock(&nic->mbox.lock); + } + return rc; } @@ -675,6 +826,87 @@ static int otx2_setup_tc_cls_flower(struct otx2_nic *nic, } } +static int otx2_tc_ingress_matchall_install(struct otx2_nic *nic, + struct tc_cls_matchall_offload *cls) +{ + struct netlink_ext_ack *extack = cls->common.extack; + struct flow_action *actions = &cls->rule->action; + struct flow_action_entry *entry; + u64 rate; + int err; + + err = otx2_tc_validate_flow(nic, actions, extack); + if (err) + return err; + + if (nic->flags & OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED) { + NL_SET_ERR_MSG_MOD(extack, + "Only one ingress MATCHALL ratelimitter can be offloaded"); + return -ENOMEM; + } + + entry = &cls->rule->action.entries[0]; + switch (entry->id) { + case FLOW_ACTION_POLICE: + /* Ingress ratelimiting is not supported on OcteonTx2 */ + if (is_dev_otx2(nic->pdev)) { + NL_SET_ERR_MSG_MOD(extack, + "Ingress policing not supported on this platform"); + return -EOPNOTSUPP; + } + + err = cn10k_alloc_matchall_ipolicer(nic); + if (err) + return err; + + /* Convert to bits per second */ + rate = entry->police.rate_bytes_ps * 8; + err = cn10k_set_matchall_ipolicer_rate(nic, entry->police.burst, rate); + if (err) + return err; + nic->flags |= OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED; + break; + default: + NL_SET_ERR_MSG_MOD(extack, + "Only police action supported with Ingress MATCHALL offload"); + return -EOPNOTSUPP; + } + + return 0; +} + +static int otx2_tc_ingress_matchall_delete(struct otx2_nic *nic, + struct tc_cls_matchall_offload *cls) +{ + struct netlink_ext_ack *extack = cls->common.extack; + int err; + + if (nic->flags & OTX2_FLAG_INTF_DOWN) { + NL_SET_ERR_MSG_MOD(extack, "Interface not initialized"); + return -EINVAL; + } + + err = cn10k_free_matchall_ipolicer(nic); + nic->flags &= ~OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED; + return err; +} + +static int otx2_setup_tc_ingress_matchall(struct otx2_nic *nic, + struct tc_cls_matchall_offload *cls_matchall) +{ + switch (cls_matchall->command) { + case TC_CLSMATCHALL_REPLACE: + return otx2_tc_ingress_matchall_install(nic, cls_matchall); + case TC_CLSMATCHALL_DESTROY: + return otx2_tc_ingress_matchall_delete(nic, cls_matchall); + case TC_CLSMATCHALL_STATS: + default: + break; + } + + return -EOPNOTSUPP; +} + static int otx2_setup_tc_block_ingress_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { @@ -686,6 +918,8 @@ static int otx2_setup_tc_block_ingress_cb(enum tc_setup_type type, switch (type) { case TC_SETUP_CLSFLOWER: return otx2_setup_tc_cls_flower(nic, type_data); + case TC_SETUP_CLSMATCHALL: + return otx2_setup_tc_ingress_matchall(nic, type_data); default: break; } @@ -775,6 +1009,9 @@ int otx2_init_tc(struct otx2_nic *nic) { struct otx2_tc_info *tc = &nic->tc_info; + /* Exclude receive queue 0 being used for police action */ + set_bit(0, &nic->rq_bmap); + tc->flow_ht_params = tc_flow_ht_params; return rhashtable_init(&tc->flow_table, &tc->flow_ht_params); } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 085be90a03eb..13a908f75ba0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -395,6 +395,42 @@ static netdev_tx_t otx2vf_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } +static void otx2vf_set_rx_mode(struct net_device *netdev) +{ + struct otx2_nic *vf = netdev_priv(netdev); + + queue_work(vf->otx2_wq, &vf->rx_mode_work); +} + +static void otx2vf_do_set_rx_mode(struct work_struct *work) +{ + struct otx2_nic *vf = container_of(work, struct otx2_nic, rx_mode_work); + struct net_device *netdev = vf->netdev; + unsigned int flags = netdev->flags; + struct nix_rx_mode *req; + + mutex_lock(&vf->mbox.lock); + + req = otx2_mbox_alloc_msg_nix_set_rx_mode(&vf->mbox); + if (!req) { + mutex_unlock(&vf->mbox.lock); + return; + } + + req->mode = NIX_RX_MODE_UCAST; + + if (flags & IFF_PROMISC) + req->mode |= NIX_RX_MODE_PROMISC; + if (flags & (IFF_ALLMULTI | IFF_MULTICAST)) + req->mode |= NIX_RX_MODE_ALLMULTI; + + req->mode |= NIX_RX_MODE_USE_MCE; + + otx2_sync_mbox_msg(&vf->mbox); + + mutex_unlock(&vf->mbox.lock); +} + static int otx2vf_change_mtu(struct net_device *netdev, int new_mtu) { bool if_up = netif_running(netdev); @@ -432,12 +468,24 @@ static const struct net_device_ops otx2vf_netdev_ops = { .ndo_open = otx2vf_open, .ndo_stop = otx2vf_stop, .ndo_start_xmit = otx2vf_xmit, + .ndo_set_rx_mode = otx2vf_set_rx_mode, .ndo_set_mac_address = otx2_set_mac_address, .ndo_change_mtu = otx2vf_change_mtu, .ndo_get_stats64 = otx2_get_stats64, .ndo_tx_timeout = otx2_tx_timeout, }; +static int otx2_wq_init(struct otx2_nic *vf) +{ + vf->otx2_wq = create_singlethread_workqueue("otx2vf_wq"); + if (!vf->otx2_wq) + return -ENOMEM; + + INIT_WORK(&vf->rx_mode_work, otx2vf_do_set_rx_mode); + INIT_WORK(&vf->reset_task, otx2vf_reset_task); + return 0; +} + static int otx2vf_realloc_msix_vectors(struct otx2_nic *vf) { struct otx2_hw *hw = &vf->hw; @@ -588,8 +636,6 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->min_mtu = OTX2_MIN_MTU; netdev->max_mtu = otx2_get_max_mtu(vf); - INIT_WORK(&vf->reset_task, otx2vf_reset_task); - /* To distinguish, for LBK VFs set netdev name explicitly */ if (is_otx2_lbkvf(vf->pdev)) { int n; @@ -606,6 +652,10 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_detach_rsrc; } + err = otx2_wq_init(vf); + if (err) + goto err_unreg_netdev; + otx2vf_set_ethtool_ops(netdev); /* Enable pause frames by default */ @@ -614,6 +664,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; +err_unreg_netdev: + unregister_netdev(netdev); err_detach_rsrc: if (hw->lmt_base) iounmap(hw->lmt_base); @@ -644,6 +696,8 @@ static void otx2vf_remove(struct pci_dev *pdev) cancel_work_sync(&vf->reset_task); unregister_netdev(netdev); + if (vf->otx2_wq) + destroy_workqueue(vf->otx2_wq); otx2vf_disable_mbox_intr(vf); otx2_detach_resources(&vf->mbox); diff --git a/drivers/net/ethernet/marvell/prestera/Makefile b/drivers/net/ethernet/marvell/prestera/Makefile index 93129e32ebc5..0609df8b913d 100644 --- a/drivers/net/ethernet/marvell/prestera/Makefile +++ b/drivers/net/ethernet/marvell/prestera/Makefile @@ -2,6 +2,7 @@ obj-$(CONFIG_PRESTERA) += prestera.o prestera-objs := prestera_main.o prestera_hw.o prestera_dsa.o \ prestera_rxtx.o prestera_devlink.o prestera_ethtool.o \ - prestera_switchdev.o + prestera_switchdev.o prestera_acl.o prestera_flow.o \ + prestera_flower.o prestera_span.o obj-$(CONFIG_PRESTERA_PCI) += prestera_pci.o diff --git a/drivers/net/ethernet/marvell/prestera/prestera.h b/drivers/net/ethernet/marvell/prestera/prestera.h index 55aa4bf8a27c..f18fe664b373 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera.h +++ b/drivers/net/ethernet/marvell/prestera/prestera.h @@ -60,10 +60,22 @@ struct prestera_port_caps { u8 transceiver; }; +struct prestera_lag { + struct net_device *dev; + struct list_head members; + u16 member_count; + u16 lag_id; +}; + +struct prestera_flow_block; + struct prestera_port { struct net_device *dev; struct prestera_switch *sw; + struct prestera_flow_block *flow_block; struct devlink_port dl_port; + struct list_head lag_member; + struct prestera_lag *lag; u32 id; u32 hw_id; u32 dev_id; @@ -127,6 +139,12 @@ struct prestera_port_event { } data; }; +enum prestera_fdb_entry_type { + PRESTERA_FDB_ENTRY_TYPE_REG_PORT, + PRESTERA_FDB_ENTRY_TYPE_LAG, + PRESTERA_FDB_ENTRY_TYPE_MAX +}; + enum prestera_fdb_event_id { PRESTERA_FDB_EVENT_UNSPEC, PRESTERA_FDB_EVENT_LEARNED, @@ -134,7 +152,11 @@ enum prestera_fdb_event_id { }; struct prestera_fdb_event { - u32 port_id; + enum prestera_fdb_entry_type type; + union { + u32 port_id; + u16 lag_id; + } dest; u32 vid; union { u8 mac[ETH_ALEN]; @@ -150,14 +172,20 @@ struct prestera_event { }; struct prestera_switchdev; +struct prestera_span; struct prestera_rxtx; +struct prestera_trap_data; +struct prestera_acl; struct prestera_switch { struct prestera_device *dev; struct prestera_switchdev *swdev; struct prestera_rxtx *rxtx; + struct prestera_acl *acl; + struct prestera_span *span; struct list_head event_handlers; struct notifier_block netdev_nb; + struct prestera_trap_data *trap_data; char base_mac[ETH_ALEN]; struct list_head port_list; rwlock_t port_list_lock; @@ -165,6 +193,9 @@ struct prestera_switch { u32 mtu_min; u32 mtu_max; u8 id; + struct prestera_lag *lags; + u8 lag_member_max; + u8 lag_max; }; struct prestera_rxtx_params { @@ -203,4 +234,10 @@ int prestera_port_pvid_set(struct prestera_port *port, u16 vid); bool prestera_netdev_check(const struct net_device *dev); +bool prestera_port_is_lag_member(const struct prestera_port *port); + +struct prestera_lag *prestera_lag_by_id(struct prestera_switch *sw, u16 id); + +u16 prestera_port_lag_id(const struct prestera_port *port); + #endif /* _PRESTERA_H_ */ diff --git a/drivers/net/ethernet/marvell/prestera/prestera_acl.c b/drivers/net/ethernet/marvell/prestera/prestera_acl.c new file mode 100644 index 000000000000..83c75ffb1a1c --- /dev/null +++ b/drivers/net/ethernet/marvell/prestera/prestera_acl.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 +/* Copyright (c) 2020 Marvell International Ltd. All rights reserved */ + +#include + +#include "prestera.h" +#include "prestera_hw.h" +#include "prestera_acl.h" +#include "prestera_span.h" + +struct prestera_acl { + struct prestera_switch *sw; + struct list_head rules; +}; + +struct prestera_acl_ruleset { + struct rhashtable rule_ht; + struct prestera_switch *sw; + u16 id; +}; + +struct prestera_acl_rule { + struct rhash_head ht_node; + struct list_head list; + struct list_head match_list; + struct list_head action_list; + struct prestera_flow_block *block; + unsigned long cookie; + u32 priority; + u8 n_actions; + u8 n_matches; + u32 id; +}; + +static const struct rhashtable_params prestera_acl_rule_ht_params = { + .key_len = sizeof(unsigned long), + .key_offset = offsetof(struct prestera_acl_rule, cookie), + .head_offset = offsetof(struct prestera_acl_rule, ht_node), + .automatic_shrinking = true, +}; + +static struct prestera_acl_ruleset * +prestera_acl_ruleset_create(struct prestera_switch *sw) +{ + struct prestera_acl_ruleset *ruleset; + int err; + + ruleset = kzalloc(sizeof(*ruleset), GFP_KERNEL); + if (!ruleset) + return ERR_PTR(-ENOMEM); + + err = rhashtable_init(&ruleset->rule_ht, &prestera_acl_rule_ht_params); + if (err) + goto err_rhashtable_init; + + err = prestera_hw_acl_ruleset_create(sw, &ruleset->id); + if (err) + goto err_ruleset_create; + + ruleset->sw = sw; + + return ruleset; + +err_ruleset_create: + rhashtable_destroy(&ruleset->rule_ht); +err_rhashtable_init: + kfree(ruleset); + return ERR_PTR(err); +} + +static void prestera_acl_ruleset_destroy(struct prestera_acl_ruleset *ruleset) +{ + prestera_hw_acl_ruleset_del(ruleset->sw, ruleset->id); + rhashtable_destroy(&ruleset->rule_ht); + kfree(ruleset); +} + +struct prestera_flow_block * +prestera_acl_block_create(struct prestera_switch *sw, struct net *net) +{ + struct prestera_flow_block *block; + + block = kzalloc(sizeof(*block), GFP_KERNEL); + if (!block) + return NULL; + INIT_LIST_HEAD(&block->binding_list); + block->net = net; + block->sw = sw; + + block->ruleset = prestera_acl_ruleset_create(sw); + if (IS_ERR(block->ruleset)) { + kfree(block); + return NULL; + } + + return block; +} + +void prestera_acl_block_destroy(struct prestera_flow_block *block) +{ + prestera_acl_ruleset_destroy(block->ruleset); + WARN_ON(!list_empty(&block->binding_list)); + kfree(block); +} + +static struct prestera_flow_block_binding * +prestera_acl_block_lookup(struct prestera_flow_block *block, + struct prestera_port *port) +{ + struct prestera_flow_block_binding *binding; + + list_for_each_entry(binding, &block->binding_list, list) + if (binding->port == port) + return binding; + + return NULL; +} + +int prestera_acl_block_bind(struct prestera_flow_block *block, + struct prestera_port *port) +{ + struct prestera_flow_block_binding *binding; + int err; + + if (WARN_ON(prestera_acl_block_lookup(block, port))) + return -EEXIST; + + binding = kzalloc(sizeof(*binding), GFP_KERNEL); + if (!binding) + return -ENOMEM; + binding->span_id = PRESTERA_SPAN_INVALID_ID; + binding->port = port; + + err = prestera_hw_acl_port_bind(port, block->ruleset->id); + if (err) + goto err_rules_bind; + + list_add(&binding->list, &block->binding_list); + return 0; + +err_rules_bind: + kfree(binding); + return err; +} + +int prestera_acl_block_unbind(struct prestera_flow_block *block, + struct prestera_port *port) +{ + struct prestera_flow_block_binding *binding; + + binding = prestera_acl_block_lookup(block, port); + if (!binding) + return -ENOENT; + + list_del(&binding->list); + + prestera_hw_acl_port_unbind(port, block->ruleset->id); + + kfree(binding); + return 0; +} + +struct prestera_acl_ruleset * +prestera_acl_block_ruleset_get(struct prestera_flow_block *block) +{ + return block->ruleset; +} + +u16 prestera_acl_rule_ruleset_id_get(const struct prestera_acl_rule *rule) +{ + return rule->block->ruleset->id; +} + +struct net *prestera_acl_block_net(struct prestera_flow_block *block) +{ + return block->net; +} + +struct prestera_switch *prestera_acl_block_sw(struct prestera_flow_block *block) +{ + return block->sw; +} + +struct prestera_acl_rule * +prestera_acl_rule_lookup(struct prestera_acl_ruleset *ruleset, + unsigned long cookie) +{ + return rhashtable_lookup_fast(&ruleset->rule_ht, &cookie, + prestera_acl_rule_ht_params); +} + +struct prestera_acl_rule * +prestera_acl_rule_create(struct prestera_flow_block *block, + unsigned long cookie) +{ + struct prestera_acl_rule *rule; + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&rule->match_list); + INIT_LIST_HEAD(&rule->action_list); + rule->cookie = cookie; + rule->block = block; + + return rule; +} + +struct list_head * +prestera_acl_rule_match_list_get(struct prestera_acl_rule *rule) +{ + return &rule->match_list; +} + +struct list_head * +prestera_acl_rule_action_list_get(struct prestera_acl_rule *rule) +{ + return &rule->action_list; +} + +int prestera_acl_rule_action_add(struct prestera_acl_rule *rule, + struct prestera_acl_rule_action_entry *entry) +{ + struct prestera_acl_rule_action_entry *a_entry; + + a_entry = kmalloc(sizeof(*a_entry), GFP_KERNEL); + if (!a_entry) + return -ENOMEM; + + memcpy(a_entry, entry, sizeof(*entry)); + list_add(&a_entry->list, &rule->action_list); + + rule->n_actions++; + return 0; +} + +u8 prestera_acl_rule_action_len(struct prestera_acl_rule *rule) +{ + return rule->n_actions; +} + +u32 prestera_acl_rule_priority_get(struct prestera_acl_rule *rule) +{ + return rule->priority; +} + +void prestera_acl_rule_priority_set(struct prestera_acl_rule *rule, + u32 priority) +{ + rule->priority = priority; +} + +int prestera_acl_rule_match_add(struct prestera_acl_rule *rule, + struct prestera_acl_rule_match_entry *entry) +{ + struct prestera_acl_rule_match_entry *m_entry; + + m_entry = kmalloc(sizeof(*m_entry), GFP_KERNEL); + if (!m_entry) + return -ENOMEM; + + memcpy(m_entry, entry, sizeof(*entry)); + list_add(&m_entry->list, &rule->match_list); + + rule->n_matches++; + return 0; +} + +u8 prestera_acl_rule_match_len(struct prestera_acl_rule *rule) +{ + return rule->n_matches; +} + +void prestera_acl_rule_destroy(struct prestera_acl_rule *rule) +{ + struct prestera_acl_rule_action_entry *a_entry; + struct prestera_acl_rule_match_entry *m_entry; + struct list_head *pos, *n; + + list_for_each_safe(pos, n, &rule->match_list) { + m_entry = list_entry(pos, typeof(*m_entry), list); + list_del(pos); + kfree(m_entry); + } + + list_for_each_safe(pos, n, &rule->action_list) { + a_entry = list_entry(pos, typeof(*a_entry), list); + list_del(pos); + kfree(a_entry); + } + + kfree(rule); +} + +int prestera_acl_rule_add(struct prestera_switch *sw, + struct prestera_acl_rule *rule) +{ + u32 rule_id; + int err; + + /* try to add rule to hash table first */ + err = rhashtable_insert_fast(&rule->block->ruleset->rule_ht, + &rule->ht_node, + prestera_acl_rule_ht_params); + if (err) + return err; + + /* add rule to hw */ + err = prestera_hw_acl_rule_add(sw, rule, &rule_id); + if (err) + goto err_rule_add; + + rule->id = rule_id; + + list_add_tail(&rule->list, &sw->acl->rules); + + return 0; + +err_rule_add: + rhashtable_remove_fast(&rule->block->ruleset->rule_ht, &rule->ht_node, + prestera_acl_rule_ht_params); + return err; +} + +void prestera_acl_rule_del(struct prestera_switch *sw, + struct prestera_acl_rule *rule) +{ + rhashtable_remove_fast(&rule->block->ruleset->rule_ht, &rule->ht_node, + prestera_acl_rule_ht_params); + list_del(&rule->list); + prestera_hw_acl_rule_del(sw, rule->id); +} + +int prestera_acl_rule_get_stats(struct prestera_switch *sw, + struct prestera_acl_rule *rule, + u64 *packets, u64 *bytes, u64 *last_use) +{ + u64 current_packets; + u64 current_bytes; + int err; + + err = prestera_hw_acl_rule_stats_get(sw, rule->id, ¤t_packets, + ¤t_bytes); + if (err) + return err; + + *packets = current_packets; + *bytes = current_bytes; + *last_use = jiffies; + + return 0; +} + +int prestera_acl_init(struct prestera_switch *sw) +{ + struct prestera_acl *acl; + + acl = kzalloc(sizeof(*acl), GFP_KERNEL); + if (!acl) + return -ENOMEM; + + INIT_LIST_HEAD(&acl->rules); + sw->acl = acl; + acl->sw = sw; + + return 0; +} + +void prestera_acl_fini(struct prestera_switch *sw) +{ + struct prestera_acl *acl = sw->acl; + + WARN_ON(!list_empty(&acl->rules)); + kfree(acl); +} diff --git a/drivers/net/ethernet/marvell/prestera/prestera_acl.h b/drivers/net/ethernet/marvell/prestera/prestera_acl.h new file mode 100644 index 000000000000..39b7869be659 --- /dev/null +++ b/drivers/net/ethernet/marvell/prestera/prestera_acl.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* Copyright (c) 2020 Marvell International Ltd. All rights reserved. */ + +#ifndef _PRESTERA_ACL_H_ +#define _PRESTERA_ACL_H_ + +enum prestera_acl_rule_match_entry_type { + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_TYPE = 1, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_DMAC, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_SMAC, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_PROTO, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_PORT, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_SRC, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_DST, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_SRC, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_DST, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_RANGE_SRC, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_RANGE_DST, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_VLAN_ID, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_VLAN_TPID, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ICMP_TYPE, + PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ICMP_CODE +}; + +enum prestera_acl_rule_action { + PRESTERA_ACL_RULE_ACTION_ACCEPT, + PRESTERA_ACL_RULE_ACTION_DROP, + PRESTERA_ACL_RULE_ACTION_TRAP +}; + +struct prestera_switch; +struct prestera_port; +struct prestera_acl_rule; +struct prestera_acl_ruleset; + +struct prestera_flow_block_binding { + struct list_head list; + struct prestera_port *port; + int span_id; +}; + +struct prestera_flow_block { + struct list_head binding_list; + struct prestera_switch *sw; + struct net *net; + struct prestera_acl_ruleset *ruleset; + struct flow_block_cb *block_cb; +}; + +struct prestera_acl_rule_action_entry { + struct list_head list; + enum prestera_acl_rule_action id; +}; + +struct prestera_acl_rule_match_entry { + struct list_head list; + enum prestera_acl_rule_match_entry_type type; + union { + struct { + u8 key; + u8 mask; + } u8; + struct { + u16 key; + u16 mask; + } u16; + struct { + u32 key; + u32 mask; + } u32; + struct { + u64 key; + u64 mask; + } u64; + struct { + u8 key[ETH_ALEN]; + u8 mask[ETH_ALEN]; + } mac; + } keymask; +}; + +int prestera_acl_init(struct prestera_switch *sw); +void prestera_acl_fini(struct prestera_switch *sw); +struct prestera_flow_block * +prestera_acl_block_create(struct prestera_switch *sw, struct net *net); +void prestera_acl_block_destroy(struct prestera_flow_block *block); +struct net *prestera_acl_block_net(struct prestera_flow_block *block); +struct prestera_switch *prestera_acl_block_sw(struct prestera_flow_block *block); +int prestera_acl_block_bind(struct prestera_flow_block *block, + struct prestera_port *port); +int prestera_acl_block_unbind(struct prestera_flow_block *block, + struct prestera_port *port); +struct prestera_acl_ruleset * +prestera_acl_block_ruleset_get(struct prestera_flow_block *block); +struct prestera_acl_rule * +prestera_acl_rule_create(struct prestera_flow_block *block, + unsigned long cookie); +u32 prestera_acl_rule_priority_get(struct prestera_acl_rule *rule); +void prestera_acl_rule_priority_set(struct prestera_acl_rule *rule, + u32 priority); +u16 prestera_acl_rule_ruleset_id_get(const struct prestera_acl_rule *rule); +struct list_head * +prestera_acl_rule_action_list_get(struct prestera_acl_rule *rule); +u8 prestera_acl_rule_action_len(struct prestera_acl_rule *rule); +u8 prestera_acl_rule_match_len(struct prestera_acl_rule *rule); +int prestera_acl_rule_action_add(struct prestera_acl_rule *rule, + struct prestera_acl_rule_action_entry *entry); +struct list_head * +prestera_acl_rule_match_list_get(struct prestera_acl_rule *rule); +int prestera_acl_rule_match_add(struct prestera_acl_rule *rule, + struct prestera_acl_rule_match_entry *entry); +void prestera_acl_rule_destroy(struct prestera_acl_rule *rule); +struct prestera_acl_rule * +prestera_acl_rule_lookup(struct prestera_acl_ruleset *ruleset, + unsigned long cookie); +int prestera_acl_rule_add(struct prestera_switch *sw, + struct prestera_acl_rule *rule); +void prestera_acl_rule_del(struct prestera_switch *sw, + struct prestera_acl_rule *rule); +int prestera_acl_rule_get_stats(struct prestera_switch *sw, + struct prestera_acl_rule *rule, + u64 *packets, u64 *bytes, u64 *last_use); + +#endif /* _PRESTERA_ACL_H_ */ diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c index 94c185a0e2b8..d12e21db9fd6 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c @@ -4,6 +4,352 @@ #include #include "prestera_devlink.h" +#include "prestera_hw.h" + +/* All driver-specific traps must be documented in + * Documentation/networking/devlink/prestera.rst + */ +enum { + DEVLINK_PRESTERA_TRAP_ID_BASE = DEVLINK_TRAP_GENERIC_ID_MAX, + DEVLINK_PRESTERA_TRAP_ID_ARP_BC, + DEVLINK_PRESTERA_TRAP_ID_IS_IS, + DEVLINK_PRESTERA_TRAP_ID_OSPF, + DEVLINK_PRESTERA_TRAP_ID_IP_BC_MAC, + DEVLINK_PRESTERA_TRAP_ID_ROUTER_MC, + DEVLINK_PRESTERA_TRAP_ID_VRRP, + DEVLINK_PRESTERA_TRAP_ID_DHCP, + DEVLINK_PRESTERA_TRAP_ID_MAC_TO_ME, + DEVLINK_PRESTERA_TRAP_ID_IPV4_OPTIONS, + DEVLINK_PRESTERA_TRAP_ID_IP_DEFAULT_ROUTE, + DEVLINK_PRESTERA_TRAP_ID_IP_TO_ME, + DEVLINK_PRESTERA_TRAP_ID_IPV4_ICMP_REDIRECT, + DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_0, + DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_1, + DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_2, + DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_3, + DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_4, + DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_5, + DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_6, + DEVLINK_PRESTERA_TRAP_ID_ACL_CODE_7, + DEVLINK_PRESTERA_TRAP_ID_BGP, + DEVLINK_PRESTERA_TRAP_ID_SSH, + DEVLINK_PRESTERA_TRAP_ID_TELNET, + DEVLINK_PRESTERA_TRAP_ID_ICMP, + DEVLINK_PRESTERA_TRAP_ID_MET_RED, + DEVLINK_PRESTERA_TRAP_ID_IP_SIP_IS_ZERO, + DEVLINK_PRESTERA_TRAP_ID_IP_UC_DIP_DA_MISMATCH, + DEVLINK_PRESTERA_TRAP_ID_ILLEGAL_IPV4_HDR, + DEVLINK_PRESTERA_TRAP_ID_ILLEGAL_IP_ADDR, + DEVLINK_PRESTERA_TRAP_ID_INVALID_SA, + DEVLINK_PRESTERA_TRAP_ID_LOCAL_PORT, + DEVLINK_PRESTERA_TRAP_ID_PORT_NO_VLAN, + DEVLINK_PRESTERA_TRAP_ID_RXDMA_DROP, +}; + +#define DEVLINK_PRESTERA_TRAP_NAME_ARP_BC \ + "arp_bc" +#define DEVLINK_PRESTERA_TRAP_NAME_IS_IS \ + "is_is" +#define DEVLINK_PRESTERA_TRAP_NAME_OSPF \ + "ospf" +#define DEVLINK_PRESTERA_TRAP_NAME_IP_BC_MAC \ + "ip_bc_mac" +#define DEVLINK_PRESTERA_TRAP_NAME_ROUTER_MC \ + "router_mc" +#define DEVLINK_PRESTERA_TRAP_NAME_VRRP \ + "vrrp" +#define DEVLINK_PRESTERA_TRAP_NAME_DHCP \ + "dhcp" +#define DEVLINK_PRESTERA_TRAP_NAME_MAC_TO_ME \ + "mac_to_me" +#define DEVLINK_PRESTERA_TRAP_NAME_IPV4_OPTIONS \ + "ipv4_options" +#define DEVLINK_PRESTERA_TRAP_NAME_IP_DEFAULT_ROUTE \ + "ip_default_route" +#define DEVLINK_PRESTERA_TRAP_NAME_IP_TO_ME \ + "ip_to_me" +#define DEVLINK_PRESTERA_TRAP_NAME_IPV4_ICMP_REDIRECT \ + "ipv4_icmp_redirect" +#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_0 \ + "acl_code_0" +#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_1 \ + "acl_code_1" +#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_2 \ + "acl_code_2" +#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_3 \ + "acl_code_3" +#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_4 \ + "acl_code_4" +#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_5 \ + "acl_code_5" +#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_6 \ + "acl_code_6" +#define DEVLINK_PRESTERA_TRAP_NAME_ACL_CODE_7 \ + "acl_code_7" +#define DEVLINK_PRESTERA_TRAP_NAME_BGP \ + "bgp" +#define DEVLINK_PRESTERA_TRAP_NAME_SSH \ + "ssh" +#define DEVLINK_PRESTERA_TRAP_NAME_TELNET \ + "telnet" +#define DEVLINK_PRESTERA_TRAP_NAME_ICMP \ + "icmp" +#define DEVLINK_PRESTERA_TRAP_NAME_RXDMA_DROP \ + "rxdma_drop" +#define DEVLINK_PRESTERA_TRAP_NAME_PORT_NO_VLAN \ + "port_no_vlan" +#define DEVLINK_PRESTERA_TRAP_NAME_LOCAL_PORT \ + "local_port" +#define DEVLINK_PRESTERA_TRAP_NAME_INVALID_SA \ + "invalid_sa" +#define DEVLINK_PRESTERA_TRAP_NAME_ILLEGAL_IP_ADDR \ + "illegal_ip_addr" +#define DEVLINK_PRESTERA_TRAP_NAME_ILLEGAL_IPV4_HDR \ + "illegal_ipv4_hdr" +#define DEVLINK_PRESTERA_TRAP_NAME_IP_UC_DIP_DA_MISMATCH \ + "ip_uc_dip_da_mismatch" +#define DEVLINK_PRESTERA_TRAP_NAME_IP_SIP_IS_ZERO \ + "ip_sip_is_zero" +#define DEVLINK_PRESTERA_TRAP_NAME_MET_RED \ + "met_red" + +struct prestera_trap { + struct devlink_trap trap; + u8 cpu_code; +}; + +struct prestera_trap_item { + enum devlink_trap_action action; + void *trap_ctx; +}; + +struct prestera_trap_data { + struct prestera_switch *sw; + struct prestera_trap_item *trap_items_arr; + u32 traps_count; +}; + +#define PRESTERA_TRAP_METADATA DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT + +#define PRESTERA_TRAP_CONTROL(_id, _group_id, _action) \ + DEVLINK_TRAP_GENERIC(CONTROL, _action, _id, \ + DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ + PRESTERA_TRAP_METADATA) + +#define PRESTERA_TRAP_DRIVER_CONTROL(_id, _group_id) \ + DEVLINK_TRAP_DRIVER(CONTROL, TRAP, DEVLINK_PRESTERA_TRAP_ID_##_id, \ + DEVLINK_PRESTERA_TRAP_NAME_##_id, \ + DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ + PRESTERA_TRAP_METADATA) + +#define PRESTERA_TRAP_EXCEPTION(_id, _group_id) \ + DEVLINK_TRAP_GENERIC(EXCEPTION, TRAP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ + PRESTERA_TRAP_METADATA) + +#define PRESTERA_TRAP_DRIVER_EXCEPTION(_id, _group_id) \ + DEVLINK_TRAP_DRIVER(EXCEPTION, TRAP, DEVLINK_PRESTERA_TRAP_ID_##_id, \ + DEVLINK_PRESTERA_TRAP_NAME_##_id, \ + DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ + PRESTERA_TRAP_METADATA) + +#define PRESTERA_TRAP_DRIVER_DROP(_id, _group_id) \ + DEVLINK_TRAP_DRIVER(DROP, DROP, DEVLINK_PRESTERA_TRAP_ID_##_id, \ + DEVLINK_PRESTERA_TRAP_NAME_##_id, \ + DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ + PRESTERA_TRAP_METADATA) + +static const struct devlink_trap_group prestera_trap_groups_arr[] = { + /* No policer is associated with following groups (policerid == 0)*/ + DEVLINK_TRAP_GROUP_GENERIC(L2_DROPS, 0), + DEVLINK_TRAP_GROUP_GENERIC(L3_DROPS, 0), + DEVLINK_TRAP_GROUP_GENERIC(L3_EXCEPTIONS, 0), + DEVLINK_TRAP_GROUP_GENERIC(NEIGH_DISCOVERY, 0), + DEVLINK_TRAP_GROUP_GENERIC(ACL_TRAP, 0), + DEVLINK_TRAP_GROUP_GENERIC(ACL_DROPS, 0), + DEVLINK_TRAP_GROUP_GENERIC(ACL_SAMPLE, 0), + DEVLINK_TRAP_GROUP_GENERIC(OSPF, 0), + DEVLINK_TRAP_GROUP_GENERIC(STP, 0), + DEVLINK_TRAP_GROUP_GENERIC(LACP, 0), + DEVLINK_TRAP_GROUP_GENERIC(LLDP, 0), + DEVLINK_TRAP_GROUP_GENERIC(VRRP, 0), + DEVLINK_TRAP_GROUP_GENERIC(DHCP, 0), + DEVLINK_TRAP_GROUP_GENERIC(BGP, 0), + DEVLINK_TRAP_GROUP_GENERIC(LOCAL_DELIVERY, 0), + DEVLINK_TRAP_GROUP_GENERIC(BUFFER_DROPS, 0), +}; + +/* Initialize trap list, as well as associate CPU code with them. */ +static struct prestera_trap prestera_trap_items_arr[] = { + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(ARP_BC, NEIGH_DISCOVERY), + .cpu_code = 5, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(IS_IS, LOCAL_DELIVERY), + .cpu_code = 13, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(OSPF, OSPF), + .cpu_code = 16, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(IP_BC_MAC, LOCAL_DELIVERY), + .cpu_code = 19, + }, + { + .trap = PRESTERA_TRAP_CONTROL(STP, STP, TRAP), + .cpu_code = 26, + }, + { + .trap = PRESTERA_TRAP_CONTROL(LACP, LACP, TRAP), + .cpu_code = 27, + }, + { + .trap = PRESTERA_TRAP_CONTROL(LLDP, LLDP, TRAP), + .cpu_code = 28, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(ROUTER_MC, LOCAL_DELIVERY), + .cpu_code = 29, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(VRRP, VRRP), + .cpu_code = 30, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(DHCP, DHCP), + .cpu_code = 33, + }, + { + .trap = PRESTERA_TRAP_EXCEPTION(MTU_ERROR, L3_EXCEPTIONS), + .cpu_code = 63, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(MAC_TO_ME, LOCAL_DELIVERY), + .cpu_code = 65, + }, + { + .trap = PRESTERA_TRAP_EXCEPTION(TTL_ERROR, L3_EXCEPTIONS), + .cpu_code = 133, + }, + { + .trap = PRESTERA_TRAP_DRIVER_EXCEPTION(IPV4_OPTIONS, + L3_EXCEPTIONS), + .cpu_code = 141, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(IP_DEFAULT_ROUTE, + LOCAL_DELIVERY), + .cpu_code = 160, + }, + { + .trap = PRESTERA_TRAP_CONTROL(LOCAL_ROUTE, LOCAL_DELIVERY, + TRAP), + .cpu_code = 161, + }, + { + .trap = PRESTERA_TRAP_DRIVER_EXCEPTION(IPV4_ICMP_REDIRECT, + L3_EXCEPTIONS), + .cpu_code = 180, + }, + { + .trap = PRESTERA_TRAP_CONTROL(ARP_RESPONSE, NEIGH_DISCOVERY, + TRAP), + .cpu_code = 188, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_0, ACL_TRAP), + .cpu_code = 192, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_1, ACL_TRAP), + .cpu_code = 193, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_2, ACL_TRAP), + .cpu_code = 194, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_3, ACL_TRAP), + .cpu_code = 195, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_4, ACL_TRAP), + .cpu_code = 196, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_5, ACL_TRAP), + .cpu_code = 197, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_6, ACL_TRAP), + .cpu_code = 198, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(ACL_CODE_7, ACL_TRAP), + .cpu_code = 199, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(BGP, BGP), + .cpu_code = 206, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(SSH, LOCAL_DELIVERY), + .cpu_code = 207, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(TELNET, LOCAL_DELIVERY), + .cpu_code = 208, + }, + { + .trap = PRESTERA_TRAP_DRIVER_CONTROL(ICMP, LOCAL_DELIVERY), + .cpu_code = 209, + }, + { + .trap = PRESTERA_TRAP_DRIVER_DROP(RXDMA_DROP, BUFFER_DROPS), + .cpu_code = 37, + }, + { + .trap = PRESTERA_TRAP_DRIVER_DROP(PORT_NO_VLAN, L2_DROPS), + .cpu_code = 39, + }, + { + .trap = PRESTERA_TRAP_DRIVER_DROP(LOCAL_PORT, L2_DROPS), + .cpu_code = 56, + }, + { + .trap = PRESTERA_TRAP_DRIVER_DROP(INVALID_SA, L2_DROPS), + .cpu_code = 60, + }, + { + .trap = PRESTERA_TRAP_DRIVER_DROP(ILLEGAL_IP_ADDR, L3_DROPS), + .cpu_code = 136, + }, + { + .trap = PRESTERA_TRAP_DRIVER_DROP(ILLEGAL_IPV4_HDR, L3_DROPS), + .cpu_code = 137, + }, + { + .trap = PRESTERA_TRAP_DRIVER_DROP(IP_UC_DIP_DA_MISMATCH, + L3_DROPS), + .cpu_code = 138, + }, + { + .trap = PRESTERA_TRAP_DRIVER_DROP(IP_SIP_IS_ZERO, L3_DROPS), + .cpu_code = 145, + }, + { + .trap = PRESTERA_TRAP_DRIVER_DROP(MET_RED, BUFFER_DROPS), + .cpu_code = 185, + }, +}; + +static void prestera_devlink_traps_fini(struct prestera_switch *sw); + +static int prestera_drop_counter_get(struct devlink *devlink, + const struct devlink_trap *trap, + u64 *p_drops); static int prestera_dl_info_get(struct devlink *dl, struct devlink_info_req *req, @@ -27,8 +373,21 @@ static int prestera_dl_info_get(struct devlink *dl, buf); } +static int prestera_trap_init(struct devlink *devlink, + const struct devlink_trap *trap, void *trap_ctx); + +static int prestera_trap_action_set(struct devlink *devlink, + const struct devlink_trap *trap, + enum devlink_trap_action action, + struct netlink_ext_ack *extack); + +static int prestera_devlink_traps_register(struct prestera_switch *sw); + static const struct devlink_ops prestera_dl_ops = { .info_get = prestera_dl_info_get, + .trap_init = prestera_trap_init, + .trap_action_set = prestera_trap_action_set, + .trap_drop_counter_get = prestera_drop_counter_get, }; struct prestera_switch *prestera_devlink_alloc(void) @@ -53,17 +412,32 @@ int prestera_devlink_register(struct prestera_switch *sw) int err; err = devlink_register(dl, sw->dev->dev); - if (err) + if (err) { dev_err(prestera_dev(sw), "devlink_register failed: %d\n", err); + return err; + } - return err; + err = prestera_devlink_traps_register(sw); + if (err) { + devlink_unregister(dl); + dev_err(sw->dev->dev, "devlink_traps_register failed: %d\n", + err); + return err; + } + + return 0; } void prestera_devlink_unregister(struct prestera_switch *sw) { + struct prestera_trap_data *trap_data = sw->trap_data; struct devlink *dl = priv_to_devlink(sw); + prestera_devlink_traps_fini(sw); devlink_unregister(dl); + + kfree(trap_data->trap_items_arr); + kfree(trap_data); } int prestera_devlink_port_register(struct prestera_port *port) @@ -110,3 +484,155 @@ struct devlink_port *prestera_devlink_get_port(struct net_device *dev) return &port->dl_port; } + +static int prestera_devlink_traps_register(struct prestera_switch *sw) +{ + const u32 groups_count = ARRAY_SIZE(prestera_trap_groups_arr); + const u32 traps_count = ARRAY_SIZE(prestera_trap_items_arr); + struct devlink *devlink = priv_to_devlink(sw); + struct prestera_trap_data *trap_data; + struct prestera_trap *prestera_trap; + int err, i; + + trap_data = kzalloc(sizeof(*trap_data), GFP_KERNEL); + if (!trap_data) + return -ENOMEM; + + trap_data->trap_items_arr = kcalloc(traps_count, + sizeof(struct prestera_trap_item), + GFP_KERNEL); + if (!trap_data->trap_items_arr) { + err = -ENOMEM; + goto err_trap_items_alloc; + } + + trap_data->sw = sw; + trap_data->traps_count = traps_count; + sw->trap_data = trap_data; + + err = devlink_trap_groups_register(devlink, prestera_trap_groups_arr, + groups_count); + if (err) + goto err_groups_register; + + for (i = 0; i < traps_count; i++) { + prestera_trap = &prestera_trap_items_arr[i]; + err = devlink_traps_register(devlink, &prestera_trap->trap, 1, + sw); + if (err) + goto err_trap_register; + } + + return 0; + +err_trap_register: + for (i--; i >= 0; i--) { + prestera_trap = &prestera_trap_items_arr[i]; + devlink_traps_unregister(devlink, &prestera_trap->trap, 1); + } +err_groups_register: + kfree(trap_data->trap_items_arr); +err_trap_items_alloc: + kfree(trap_data); + return err; +} + +static struct prestera_trap_item * +prestera_get_trap_item_by_cpu_code(struct prestera_switch *sw, u8 cpu_code) +{ + struct prestera_trap_data *trap_data = sw->trap_data; + struct prestera_trap *prestera_trap; + int i; + + for (i = 0; i < trap_data->traps_count; i++) { + prestera_trap = &prestera_trap_items_arr[i]; + if (cpu_code == prestera_trap->cpu_code) + return &trap_data->trap_items_arr[i]; + } + + return NULL; +} + +void prestera_devlink_trap_report(struct prestera_port *port, + struct sk_buff *skb, u8 cpu_code) +{ + struct prestera_trap_item *trap_item; + struct devlink *devlink; + + devlink = port->dl_port.devlink; + + trap_item = prestera_get_trap_item_by_cpu_code(port->sw, cpu_code); + if (unlikely(!trap_item)) + return; + + devlink_trap_report(devlink, skb, trap_item->trap_ctx, + &port->dl_port, NULL); +} + +static struct prestera_trap_item * +prestera_devlink_trap_item_lookup(struct prestera_switch *sw, u16 trap_id) +{ + struct prestera_trap_data *trap_data = sw->trap_data; + int i; + + for (i = 0; i < ARRAY_SIZE(prestera_trap_items_arr); i++) { + if (prestera_trap_items_arr[i].trap.id == trap_id) + return &trap_data->trap_items_arr[i]; + } + + return NULL; +} + +static int prestera_trap_init(struct devlink *devlink, + const struct devlink_trap *trap, void *trap_ctx) +{ + struct prestera_switch *sw = devlink_priv(devlink); + struct prestera_trap_item *trap_item; + + trap_item = prestera_devlink_trap_item_lookup(sw, trap->id); + if (WARN_ON(!trap_item)) + return -EINVAL; + + trap_item->trap_ctx = trap_ctx; + trap_item->action = trap->init_action; + + return 0; +} + +static int prestera_trap_action_set(struct devlink *devlink, + const struct devlink_trap *trap, + enum devlink_trap_action action, + struct netlink_ext_ack *extack) +{ + /* Currently, driver does not support trap action altering */ + return -EOPNOTSUPP; +} + +static int prestera_drop_counter_get(struct devlink *devlink, + const struct devlink_trap *trap, + u64 *p_drops) +{ + struct prestera_switch *sw = devlink_priv(devlink); + enum prestera_hw_cpu_code_cnt_t cpu_code_type = + PRESTERA_HW_CPU_CODE_CNT_TYPE_DROP; + struct prestera_trap *prestera_trap = + container_of(trap, struct prestera_trap, trap); + + return prestera_hw_cpu_code_counters_get(sw, prestera_trap->cpu_code, + cpu_code_type, p_drops); +} + +static void prestera_devlink_traps_fini(struct prestera_switch *sw) +{ + struct devlink *dl = priv_to_devlink(sw); + const struct devlink_trap *trap; + int i; + + for (i = 0; i < ARRAY_SIZE(prestera_trap_items_arr); ++i) { + trap = &prestera_trap_items_arr[i].trap; + devlink_traps_unregister(dl, trap, 1); + } + + devlink_trap_groups_unregister(dl, prestera_trap_groups_arr, + ARRAY_SIZE(prestera_trap_groups_arr)); +} diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h index 51bee9f75415..5d73aa9db897 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h @@ -20,4 +20,7 @@ void prestera_devlink_port_clear(struct prestera_port *port); struct devlink_port *prestera_devlink_get_port(struct net_device *dev); +void prestera_devlink_trap_report(struct prestera_port *port, + struct sk_buff *skb, u8 cpu_code); + #endif /* _PRESTERA_DEVLINK_H_ */ diff --git a/drivers/net/ethernet/marvell/prestera/prestera_dsa.c b/drivers/net/ethernet/marvell/prestera/prestera_dsa.c index a5e01c7a307b..b7e89c0ca5c0 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_dsa.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_dsa.c @@ -19,6 +19,7 @@ #define PRESTERA_DSA_W1_EXT_BIT BIT(31) #define PRESTERA_DSA_W1_CFI_BIT BIT(30) #define PRESTERA_DSA_W1_PORT_NUM GENMASK(11, 10) +#define PRESTERA_DSA_W1_MASK_CPU_CODE GENMASK(7, 0) #define PRESTERA_DSA_W2_EXT_BIT BIT(31) #define PRESTERA_DSA_W2_PORT_NUM BIT(20) @@ -74,6 +75,8 @@ int prestera_dsa_parse(struct prestera_dsa *dsa, const u8 *dsa_buf) (FIELD_GET(PRESTERA_DSA_W1_PORT_NUM, words[1]) << 5) | (FIELD_GET(PRESTERA_DSA_W2_PORT_NUM, words[2]) << 7); + dsa->cpu_code = FIELD_GET(PRESTERA_DSA_W1_MASK_CPU_CODE, words[1]); + return 0; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_dsa.h b/drivers/net/ethernet/marvell/prestera/prestera_dsa.h index 67018629bdd2..c99342f475cf 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_dsa.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_dsa.h @@ -27,6 +27,7 @@ struct prestera_dsa { struct prestera_dsa_vlan vlan; u32 hw_dev_num; u32 port_num; + u8 cpu_code; }; int prestera_dsa_parse(struct prestera_dsa *dsa, const u8 *dsa_buf); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flow.c b/drivers/net/ethernet/marvell/prestera/prestera_flow.c new file mode 100644 index 000000000000..c9891e968259 --- /dev/null +++ b/drivers/net/ethernet/marvell/prestera/prestera_flow.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 +/* Copyright (c) 2020 Marvell International Ltd. All rights reserved */ + +#include +#include + +#include "prestera.h" +#include "prestera_acl.h" +#include "prestera_flow.h" +#include "prestera_span.h" +#include "prestera_flower.h" + +static LIST_HEAD(prestera_block_cb_list); + +static int prestera_flow_block_mall_cb(struct prestera_flow_block *block, + struct tc_cls_matchall_offload *f) +{ + switch (f->command) { + case TC_CLSMATCHALL_REPLACE: + return prestera_span_replace(block, f); + case TC_CLSMATCHALL_DESTROY: + prestera_span_destroy(block); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int prestera_flow_block_flower_cb(struct prestera_flow_block *block, + struct flow_cls_offload *f) +{ + if (f->common.chain_index != 0) + return -EOPNOTSUPP; + + switch (f->command) { + case FLOW_CLS_REPLACE: + return prestera_flower_replace(block, f); + case FLOW_CLS_DESTROY: + prestera_flower_destroy(block, f); + return 0; + case FLOW_CLS_STATS: + return prestera_flower_stats(block, f); + default: + return -EOPNOTSUPP; + } +} + +static int prestera_flow_block_cb(enum tc_setup_type type, + void *type_data, void *cb_priv) +{ + struct prestera_flow_block *block = cb_priv; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return prestera_flow_block_flower_cb(block, type_data); + case TC_SETUP_CLSMATCHALL: + return prestera_flow_block_mall_cb(block, type_data); + default: + return -EOPNOTSUPP; + } +} + +static void prestera_flow_block_release(void *cb_priv) +{ + struct prestera_flow_block *block = cb_priv; + + prestera_acl_block_destroy(block); +} + +static struct prestera_flow_block * +prestera_flow_block_get(struct prestera_switch *sw, + struct flow_block_offload *f, + bool *register_block) +{ + struct prestera_flow_block *block; + struct flow_block_cb *block_cb; + + block_cb = flow_block_cb_lookup(f->block, + prestera_flow_block_cb, sw); + if (!block_cb) { + block = prestera_acl_block_create(sw, f->net); + if (!block) + return ERR_PTR(-ENOMEM); + + block_cb = flow_block_cb_alloc(prestera_flow_block_cb, + sw, block, + prestera_flow_block_release); + if (IS_ERR(block_cb)) { + prestera_acl_block_destroy(block); + return ERR_CAST(block_cb); + } + + block->block_cb = block_cb; + *register_block = true; + } else { + block = flow_block_cb_priv(block_cb); + *register_block = false; + } + + flow_block_cb_incref(block_cb); + + return block; +} + +static void prestera_flow_block_put(struct prestera_flow_block *block) +{ + struct flow_block_cb *block_cb = block->block_cb; + + if (flow_block_cb_decref(block_cb)) + return; + + flow_block_cb_free(block_cb); + prestera_acl_block_destroy(block); +} + +static int prestera_setup_flow_block_bind(struct prestera_port *port, + struct flow_block_offload *f) +{ + struct prestera_switch *sw = port->sw; + struct prestera_flow_block *block; + struct flow_block_cb *block_cb; + bool register_block; + int err; + + block = prestera_flow_block_get(sw, f, ®ister_block); + if (IS_ERR(block)) + return PTR_ERR(block); + + block_cb = block->block_cb; + + err = prestera_acl_block_bind(block, port); + if (err) + goto err_block_bind; + + if (register_block) { + flow_block_cb_add(block_cb, f); + list_add_tail(&block_cb->driver_list, &prestera_block_cb_list); + } + + port->flow_block = block; + return 0; + +err_block_bind: + prestera_flow_block_put(block); + + return err; +} + +static void prestera_setup_flow_block_unbind(struct prestera_port *port, + struct flow_block_offload *f) +{ + struct prestera_switch *sw = port->sw; + struct prestera_flow_block *block; + struct flow_block_cb *block_cb; + int err; + + block_cb = flow_block_cb_lookup(f->block, prestera_flow_block_cb, sw); + if (!block_cb) + return; + + block = flow_block_cb_priv(block_cb); + + prestera_span_destroy(block); + + err = prestera_acl_block_unbind(block, port); + if (err) + goto error; + + if (!flow_block_cb_decref(block_cb)) { + flow_block_cb_remove(block_cb, f); + list_del(&block_cb->driver_list); + } +error: + port->flow_block = NULL; +} + +int prestera_flow_block_setup(struct prestera_port *port, + struct flow_block_offload *f) +{ + if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + return -EOPNOTSUPP; + + f->driver_block_list = &prestera_block_cb_list; + + switch (f->command) { + case FLOW_BLOCK_BIND: + return prestera_setup_flow_block_bind(port, f); + case FLOW_BLOCK_UNBIND: + prestera_setup_flow_block_unbind(port, f); + return 0; + default: + return -EOPNOTSUPP; + } +} diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flow.h b/drivers/net/ethernet/marvell/prestera/prestera_flow.h new file mode 100644 index 000000000000..467c7038cace --- /dev/null +++ b/drivers/net/ethernet/marvell/prestera/prestera_flow.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* Copyright (c) 2020 Marvell International Ltd. All rights reserved. */ + +#ifndef _PRESTERA_FLOW_H_ +#define _PRESTERA_FLOW_H_ + +#include + +struct prestera_port; + +int prestera_flow_block_setup(struct prestera_port *port, + struct flow_block_offload *f); + +#endif /* _PRESTERA_FLOW_H_ */ diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.c b/drivers/net/ethernet/marvell/prestera/prestera_flower.c new file mode 100644 index 000000000000..e571ba09ec08 --- /dev/null +++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.c @@ -0,0 +1,359 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 +/* Copyright (c) 2020 Marvell International Ltd. All rights reserved */ + +#include "prestera.h" +#include "prestera_acl.h" +#include "prestera_flower.h" + +static int prestera_flower_parse_actions(struct prestera_flow_block *block, + struct prestera_acl_rule *rule, + struct flow_action *flow_action, + struct netlink_ext_ack *extack) +{ + struct prestera_acl_rule_action_entry a_entry; + const struct flow_action_entry *act; + int err, i; + + if (!flow_action_has_entries(flow_action)) + return 0; + + flow_action_for_each(i, act, flow_action) { + memset(&a_entry, 0, sizeof(a_entry)); + + switch (act->id) { + case FLOW_ACTION_ACCEPT: + a_entry.id = PRESTERA_ACL_RULE_ACTION_ACCEPT; + break; + case FLOW_ACTION_DROP: + a_entry.id = PRESTERA_ACL_RULE_ACTION_DROP; + break; + case FLOW_ACTION_TRAP: + a_entry.id = PRESTERA_ACL_RULE_ACTION_TRAP; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unsupported action"); + pr_err("Unsupported action\n"); + return -EOPNOTSUPP; + } + + err = prestera_acl_rule_action_add(rule, &a_entry); + if (err) + return err; + } + + return 0; +} + +static int prestera_flower_parse_meta(struct prestera_acl_rule *rule, + struct flow_cls_offload *f, + struct prestera_flow_block *block) +{ + struct flow_rule *f_rule = flow_cls_offload_flow_rule(f); + struct prestera_acl_rule_match_entry m_entry = {0}; + struct net_device *ingress_dev; + struct flow_match_meta match; + struct prestera_port *port; + + flow_rule_match_meta(f_rule, &match); + if (match.mask->ingress_ifindex != 0xFFFFFFFF) { + NL_SET_ERR_MSG_MOD(f->common.extack, + "Unsupported ingress ifindex mask"); + return -EINVAL; + } + + ingress_dev = __dev_get_by_index(prestera_acl_block_net(block), + match.key->ingress_ifindex); + if (!ingress_dev) { + NL_SET_ERR_MSG_MOD(f->common.extack, + "Can't find specified ingress port to match on"); + return -EINVAL; + } + + if (!prestera_netdev_check(ingress_dev)) { + NL_SET_ERR_MSG_MOD(f->common.extack, + "Can't match on switchdev ingress port"); + return -EINVAL; + } + port = netdev_priv(ingress_dev); + + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_PORT; + m_entry.keymask.u64.key = port->hw_id | ((u64)port->dev_id << 32); + m_entry.keymask.u64.mask = ~(u64)0; + + return prestera_acl_rule_match_add(rule, &m_entry); +} + +static int prestera_flower_parse(struct prestera_flow_block *block, + struct prestera_acl_rule *rule, + struct flow_cls_offload *f) +{ + struct flow_rule *f_rule = flow_cls_offload_flow_rule(f); + struct flow_dissector *dissector = f_rule->match.dissector; + struct prestera_acl_rule_match_entry m_entry; + u16 n_proto_mask = 0; + u16 n_proto_key = 0; + u16 addr_type = 0; + u8 ip_proto = 0; + int err; + + if (dissector->used_keys & + ~(BIT(FLOW_DISSECTOR_KEY_META) | + BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_ICMP) | + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_VLAN))) { + NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported key"); + return -EOPNOTSUPP; + } + + prestera_acl_rule_priority_set(rule, f->common.prio); + + if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_META)) { + err = prestera_flower_parse_meta(rule, f, block); + if (err) + return err; + } + + if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; + + flow_rule_match_control(f_rule, &match); + addr_type = match.key->addr_type; + } + + if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + + flow_rule_match_basic(f_rule, &match); + n_proto_key = ntohs(match.key->n_proto); + n_proto_mask = ntohs(match.mask->n_proto); + + if (n_proto_key == ETH_P_ALL) { + n_proto_key = 0; + n_proto_mask = 0; + } + + /* add eth type key,mask */ + memset(&m_entry, 0, sizeof(m_entry)); + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_TYPE; + m_entry.keymask.u16.key = n_proto_key; + m_entry.keymask.u16.mask = n_proto_mask; + err = prestera_acl_rule_match_add(rule, &m_entry); + if (err) + return err; + + /* add ip proto key,mask */ + memset(&m_entry, 0, sizeof(m_entry)); + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_PROTO; + m_entry.keymask.u8.key = match.key->ip_proto; + m_entry.keymask.u8.mask = match.mask->ip_proto; + err = prestera_acl_rule_match_add(rule, &m_entry); + if (err) + return err; + + ip_proto = match.key->ip_proto; + } + + if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + + flow_rule_match_eth_addrs(f_rule, &match); + + /* add ethernet dst key,mask */ + memset(&m_entry, 0, sizeof(m_entry)); + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_DMAC; + memcpy(&m_entry.keymask.mac.key, + &match.key->dst, sizeof(match.key->dst)); + memcpy(&m_entry.keymask.mac.mask, + &match.mask->dst, sizeof(match.mask->dst)); + err = prestera_acl_rule_match_add(rule, &m_entry); + if (err) + return err; + + /* add ethernet src key,mask */ + memset(&m_entry, 0, sizeof(m_entry)); + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_SMAC; + memcpy(&m_entry.keymask.mac.key, + &match.key->src, sizeof(match.key->src)); + memcpy(&m_entry.keymask.mac.mask, + &match.mask->src, sizeof(match.mask->src)); + err = prestera_acl_rule_match_add(rule, &m_entry); + if (err) + return err; + } + + if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(f_rule, &match); + + memset(&m_entry, 0, sizeof(m_entry)); + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_SRC; + memcpy(&m_entry.keymask.u32.key, + &match.key->src, sizeof(match.key->src)); + memcpy(&m_entry.keymask.u32.mask, + &match.mask->src, sizeof(match.mask->src)); + err = prestera_acl_rule_match_add(rule, &m_entry); + if (err) + return err; + + memset(&m_entry, 0, sizeof(m_entry)); + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_DST; + memcpy(&m_entry.keymask.u32.key, + &match.key->dst, sizeof(match.key->dst)); + memcpy(&m_entry.keymask.u32.mask, + &match.mask->dst, sizeof(match.mask->dst)); + err = prestera_acl_rule_match_add(rule, &m_entry); + if (err) + return err; + } + + if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + + if (ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) { + NL_SET_ERR_MSG_MOD + (f->common.extack, + "Only UDP and TCP keys are supported"); + return -EINVAL; + } + + flow_rule_match_ports(f_rule, &match); + + memset(&m_entry, 0, sizeof(m_entry)); + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_SRC; + m_entry.keymask.u16.key = ntohs(match.key->src); + m_entry.keymask.u16.mask = ntohs(match.mask->src); + err = prestera_acl_rule_match_add(rule, &m_entry); + if (err) + return err; + + memset(&m_entry, 0, sizeof(m_entry)); + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_DST; + m_entry.keymask.u16.key = ntohs(match.key->dst); + m_entry.keymask.u16.mask = ntohs(match.mask->dst); + err = prestera_acl_rule_match_add(rule, &m_entry); + if (err) + return err; + } + + if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(f_rule, &match); + + if (match.mask->vlan_id != 0) { + memset(&m_entry, 0, sizeof(m_entry)); + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_VLAN_ID; + m_entry.keymask.u16.key = match.key->vlan_id; + m_entry.keymask.u16.mask = match.mask->vlan_id; + err = prestera_acl_rule_match_add(rule, &m_entry); + if (err) + return err; + } + + memset(&m_entry, 0, sizeof(m_entry)); + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_VLAN_TPID; + m_entry.keymask.u16.key = ntohs(match.key->vlan_tpid); + m_entry.keymask.u16.mask = ntohs(match.mask->vlan_tpid); + err = prestera_acl_rule_match_add(rule, &m_entry); + if (err) + return err; + } + + if (flow_rule_match_key(f_rule, FLOW_DISSECTOR_KEY_ICMP)) { + struct flow_match_icmp match; + + flow_rule_match_icmp(f_rule, &match); + + memset(&m_entry, 0, sizeof(m_entry)); + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ICMP_TYPE; + m_entry.keymask.u8.key = match.key->type; + m_entry.keymask.u8.mask = match.mask->type; + err = prestera_acl_rule_match_add(rule, &m_entry); + if (err) + return err; + + memset(&m_entry, 0, sizeof(m_entry)); + m_entry.type = PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ICMP_CODE; + m_entry.keymask.u8.key = match.key->code; + m_entry.keymask.u8.mask = match.mask->code; + err = prestera_acl_rule_match_add(rule, &m_entry); + if (err) + return err; + } + + return prestera_flower_parse_actions(block, rule, + &f->rule->action, + f->common.extack); +} + +int prestera_flower_replace(struct prestera_flow_block *block, + struct flow_cls_offload *f) +{ + struct prestera_switch *sw = prestera_acl_block_sw(block); + struct prestera_acl_rule *rule; + int err; + + rule = prestera_acl_rule_create(block, f->cookie); + if (IS_ERR(rule)) + return PTR_ERR(rule); + + err = prestera_flower_parse(block, rule, f); + if (err) + goto err_flower_parse; + + err = prestera_acl_rule_add(sw, rule); + if (err) + goto err_rule_add; + + return 0; + +err_rule_add: +err_flower_parse: + prestera_acl_rule_destroy(rule); + return err; +} + +void prestera_flower_destroy(struct prestera_flow_block *block, + struct flow_cls_offload *f) +{ + struct prestera_acl_rule *rule; + struct prestera_switch *sw; + + rule = prestera_acl_rule_lookup(prestera_acl_block_ruleset_get(block), + f->cookie); + if (rule) { + sw = prestera_acl_block_sw(block); + prestera_acl_rule_del(sw, rule); + prestera_acl_rule_destroy(rule); + } +} + +int prestera_flower_stats(struct prestera_flow_block *block, + struct flow_cls_offload *f) +{ + struct prestera_switch *sw = prestera_acl_block_sw(block); + struct prestera_acl_rule *rule; + u64 packets; + u64 lastuse; + u64 bytes; + int err; + + rule = prestera_acl_rule_lookup(prestera_acl_block_ruleset_get(block), + f->cookie); + if (!rule) + return -EINVAL; + + err = prestera_acl_rule_get_stats(sw, rule, &packets, &bytes, &lastuse); + if (err) + return err; + + flow_stats_update(&f->stats, bytes, packets, 0, lastuse, + FLOW_ACTION_HW_STATS_IMMEDIATE); + return 0; +} diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.h b/drivers/net/ethernet/marvell/prestera/prestera_flower.h new file mode 100644 index 000000000000..91e045eec58b --- /dev/null +++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* Copyright (c) 2020 Marvell International Ltd. All rights reserved. */ + +#ifndef _PRESTERA_FLOWER_H_ +#define _PRESTERA_FLOWER_H_ + +#include + +struct prestera_flow_block; + +int prestera_flower_replace(struct prestera_flow_block *block, + struct flow_cls_offload *f); +void prestera_flower_destroy(struct prestera_flow_block *block, + struct flow_cls_offload *f); +int prestera_flower_stats(struct prestera_flow_block *block, + struct flow_cls_offload *f); + +#endif /* _PRESTERA_FLOWER_H_ */ diff --git a/drivers/net/ethernet/marvell/prestera/prestera_hw.c b/drivers/net/ethernet/marvell/prestera/prestera_hw.c index 0424718d5998..c1297859e471 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_hw.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_hw.c @@ -2,11 +2,13 @@ /* Copyright (c) 2019-2020 Marvell International Ltd. All rights reserved */ #include +#include #include #include #include "prestera.h" #include "prestera_hw.h" +#include "prestera_acl.h" #define PRESTERA_SWITCH_INIT_TIMEOUT_MS (30 * 1000) @@ -36,11 +38,31 @@ enum prestera_cmd_type_t { PRESTERA_CMD_TYPE_BRIDGE_PORT_ADD = 0x402, PRESTERA_CMD_TYPE_BRIDGE_PORT_DELETE = 0x403, + PRESTERA_CMD_TYPE_ACL_RULE_ADD = 0x500, + PRESTERA_CMD_TYPE_ACL_RULE_DELETE = 0x501, + PRESTERA_CMD_TYPE_ACL_RULE_STATS_GET = 0x510, + PRESTERA_CMD_TYPE_ACL_RULESET_CREATE = 0x520, + PRESTERA_CMD_TYPE_ACL_RULESET_DELETE = 0x521, + PRESTERA_CMD_TYPE_ACL_PORT_BIND = 0x530, + PRESTERA_CMD_TYPE_ACL_PORT_UNBIND = 0x531, + PRESTERA_CMD_TYPE_RXTX_INIT = 0x800, PRESTERA_CMD_TYPE_RXTX_PORT_INIT = 0x801, + PRESTERA_CMD_TYPE_LAG_MEMBER_ADD = 0x900, + PRESTERA_CMD_TYPE_LAG_MEMBER_DELETE = 0x901, + PRESTERA_CMD_TYPE_LAG_MEMBER_ENABLE = 0x902, + PRESTERA_CMD_TYPE_LAG_MEMBER_DISABLE = 0x903, + PRESTERA_CMD_TYPE_STP_PORT_SET = 0x1000, + PRESTERA_CMD_TYPE_SPAN_GET = 0x1100, + PRESTERA_CMD_TYPE_SPAN_BIND = 0x1101, + PRESTERA_CMD_TYPE_SPAN_UNBIND = 0x1102, + PRESTERA_CMD_TYPE_SPAN_RELEASE = 0x1103, + + PRESTERA_CMD_TYPE_CPU_CODE_COUNTERS_GET = 0x2000, + PRESTERA_CMD_TYPE_ACK = 0x10000, PRESTERA_CMD_TYPE_MAX }; @@ -85,6 +107,11 @@ enum { PRESTERA_PORT_TP_AUTO, }; +enum { + PRESTERA_PORT_FLOOD_TYPE_UC = 0, + PRESTERA_PORT_FLOOD_TYPE_MC = 1, +}; + enum { PRESTERA_PORT_GOOD_OCTETS_RCV_CNT, PRESTERA_PORT_BAD_OCTETS_RCV_CNT, @@ -127,6 +154,12 @@ enum { PRESTERA_FC_SYMM_ASYMM, }; +enum { + PRESTERA_HW_FDB_ENTRY_TYPE_REG_PORT = 0, + PRESTERA_HW_FDB_ENTRY_TYPE_LAG = 1, + PRESTERA_HW_FDB_ENTRY_TYPE_MAX = 2, +}; + struct prestera_fw_event_handler { struct list_head list; struct rcu_head rcu; @@ -168,6 +201,8 @@ struct prestera_msg_switch_init_resp { u32 port_count; u32 mtu_max; u8 switch_id; + u8 lag_max; + u8 lag_member_max; }; struct prestera_msg_port_autoneg_param { @@ -188,6 +223,11 @@ struct prestera_msg_port_mdix_param { u8 admin_mode; }; +struct prestera_msg_port_flood_param { + u8 type; + u8 enable; +}; + union prestera_msg_port_param { u8 admin_state; u8 oper_state; @@ -205,6 +245,7 @@ union prestera_msg_port_param { struct prestera_msg_port_mdix_param mdix; struct prestera_msg_port_autoneg_param autoneg; struct prestera_msg_port_cap_param cap; + struct prestera_msg_port_flood_param flood_ext; }; struct prestera_msg_port_attr_req { @@ -249,8 +290,13 @@ struct prestera_msg_vlan_req { struct prestera_msg_fdb_req { struct prestera_msg_cmd cmd; u8 dest_type; - u32 port; - u32 dev; + union { + struct { + u32 port; + u32 dev; + }; + u16 lag_id; + } dest; u8 mac[ETH_ALEN]; u16 vid; u8 dynamic; @@ -269,6 +315,85 @@ struct prestera_msg_bridge_resp { u16 bridge; }; +struct prestera_msg_acl_action { + u32 id; +}; + +struct prestera_msg_acl_match { + u32 type; + union { + struct { + u8 key; + u8 mask; + } u8; + struct { + u16 key; + u16 mask; + } u16; + struct { + u32 key; + u32 mask; + } u32; + struct { + u64 key; + u64 mask; + } u64; + struct { + u8 key[ETH_ALEN]; + u8 mask[ETH_ALEN]; + } mac; + } __packed keymask; +}; + +struct prestera_msg_acl_rule_req { + struct prestera_msg_cmd cmd; + u32 id; + u32 priority; + u16 ruleset_id; + u8 n_actions; + u8 n_matches; +}; + +struct prestera_msg_acl_rule_resp { + struct prestera_msg_ret ret; + u32 id; +}; + +struct prestera_msg_acl_rule_stats_resp { + struct prestera_msg_ret ret; + u64 packets; + u64 bytes; +}; + +struct prestera_msg_acl_ruleset_bind_req { + struct prestera_msg_cmd cmd; + u32 port; + u32 dev; + u16 ruleset_id; +}; + +struct prestera_msg_acl_ruleset_req { + struct prestera_msg_cmd cmd; + u16 id; +}; + +struct prestera_msg_acl_ruleset_resp { + struct prestera_msg_ret ret; + u16 id; +}; + +struct prestera_msg_span_req { + struct prestera_msg_cmd cmd; + u32 port; + u32 dev; + u8 id; +} __packed __aligned(4); + +struct prestera_msg_span_resp { + struct prestera_msg_ret ret; + u8 id; +} __packed __aligned(4); + struct prestera_msg_stp_req { struct prestera_msg_cmd cmd; u32 port; @@ -293,6 +418,24 @@ struct prestera_msg_rxtx_port_req { u32 dev; }; +struct prestera_msg_lag_req { + struct prestera_msg_cmd cmd; + u32 port; + u32 dev; + u16 lag_id; +}; + +struct prestera_msg_cpu_code_counter_req { + struct prestera_msg_cmd cmd; + u8 counter_type; + u8 code; +}; + +struct mvsw_msg_cpu_code_counter_ret { + struct prestera_msg_ret ret; + u64 packet_count; +}; + struct prestera_msg_event { u16 type; u16 id; @@ -315,7 +458,10 @@ union prestera_msg_event_fdb_param { struct prestera_msg_event_fdb { struct prestera_msg_event id; u8 dest_type; - u32 port_id; + union { + u32 port_id; + u16 lag_id; + } dest; u32 vid; union prestera_msg_event_fdb_param param; }; @@ -386,7 +532,19 @@ static int prestera_fw_parse_fdb_evt(void *msg, struct prestera_event *evt) { struct prestera_msg_event_fdb *hw_evt = msg; - evt->fdb_evt.port_id = hw_evt->port_id; + switch (hw_evt->dest_type) { + case PRESTERA_HW_FDB_ENTRY_TYPE_REG_PORT: + evt->fdb_evt.type = PRESTERA_FDB_ENTRY_TYPE_REG_PORT; + evt->fdb_evt.dest.port_id = hw_evt->dest.port_id; + break; + case PRESTERA_HW_FDB_ENTRY_TYPE_LAG: + evt->fdb_evt.type = PRESTERA_FDB_ENTRY_TYPE_LAG; + evt->fdb_evt.dest.lag_id = hw_evt->dest.lag_id; + break; + default: + return -EINVAL; + } + evt->fdb_evt.vid = hw_evt->vid; ether_addr_copy(evt->fdb_evt.data.mac, hw_evt->param.mac); @@ -531,6 +689,8 @@ int prestera_hw_switch_init(struct prestera_switch *sw) sw->mtu_min = PRESTERA_MIN_MTU; sw->mtu_max = resp.mtu_max; sw->id = resp.switch_id; + sw->lag_member_max = resp.lag_member_max; + sw->lag_max = resp.lag_max; return 0; } @@ -696,6 +856,274 @@ int prestera_hw_port_remote_fc_get(const struct prestera_port *port, return 0; } +int prestera_hw_acl_ruleset_create(struct prestera_switch *sw, u16 *ruleset_id) +{ + struct prestera_msg_acl_ruleset_resp resp; + struct prestera_msg_acl_ruleset_req req; + int err; + + err = prestera_cmd_ret(sw, PRESTERA_CMD_TYPE_ACL_RULESET_CREATE, + &req.cmd, sizeof(req), &resp.ret, sizeof(resp)); + if (err) + return err; + + *ruleset_id = resp.id; + + return 0; +} + +int prestera_hw_acl_ruleset_del(struct prestera_switch *sw, u16 ruleset_id) +{ + struct prestera_msg_acl_ruleset_req req = { + .id = ruleset_id, + }; + + return prestera_cmd(sw, PRESTERA_CMD_TYPE_ACL_RULESET_DELETE, + &req.cmd, sizeof(req)); +} + +static int prestera_hw_acl_actions_put(struct prestera_msg_acl_action *action, + struct prestera_acl_rule *rule) +{ + struct list_head *a_list = prestera_acl_rule_action_list_get(rule); + struct prestera_acl_rule_action_entry *a_entry; + int i = 0; + + list_for_each_entry(a_entry, a_list, list) { + action[i].id = a_entry->id; + + switch (a_entry->id) { + case PRESTERA_ACL_RULE_ACTION_ACCEPT: + case PRESTERA_ACL_RULE_ACTION_DROP: + case PRESTERA_ACL_RULE_ACTION_TRAP: + /* just rule action id, no specific data */ + break; + default: + return -EINVAL; + } + + i++; + } + + return 0; +} + +static int prestera_hw_acl_matches_put(struct prestera_msg_acl_match *match, + struct prestera_acl_rule *rule) +{ + struct list_head *m_list = prestera_acl_rule_match_list_get(rule); + struct prestera_acl_rule_match_entry *m_entry; + int i = 0; + + list_for_each_entry(m_entry, m_list, list) { + match[i].type = m_entry->type; + + switch (m_entry->type) { + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_TYPE: + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_SRC: + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_DST: + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_VLAN_ID: + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_VLAN_TPID: + match[i].keymask.u16.key = m_entry->keymask.u16.key; + match[i].keymask.u16.mask = m_entry->keymask.u16.mask; + break; + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ICMP_TYPE: + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ICMP_CODE: + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_PROTO: + match[i].keymask.u8.key = m_entry->keymask.u8.key; + match[i].keymask.u8.mask = m_entry->keymask.u8.mask; + break; + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_SMAC: + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_ETH_DMAC: + memcpy(match[i].keymask.mac.key, + m_entry->keymask.mac.key, + sizeof(match[i].keymask.mac.key)); + memcpy(match[i].keymask.mac.mask, + m_entry->keymask.mac.mask, + sizeof(match[i].keymask.mac.mask)); + break; + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_SRC: + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_IP_DST: + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_RANGE_SRC: + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_L4_PORT_RANGE_DST: + match[i].keymask.u32.key = m_entry->keymask.u32.key; + match[i].keymask.u32.mask = m_entry->keymask.u32.mask; + break; + case PRESTERA_ACL_RULE_MATCH_ENTRY_TYPE_PORT: + match[i].keymask.u64.key = m_entry->keymask.u64.key; + match[i].keymask.u64.mask = m_entry->keymask.u64.mask; + break; + default: + return -EINVAL; + } + + i++; + } + + return 0; +} + +int prestera_hw_acl_rule_add(struct prestera_switch *sw, + struct prestera_acl_rule *rule, + u32 *rule_id) +{ + struct prestera_msg_acl_action *actions; + struct prestera_msg_acl_match *matches; + struct prestera_msg_acl_rule_resp resp; + struct prestera_msg_acl_rule_req *req; + u8 n_actions; + u8 n_matches; + void *buff; + u32 size; + int err; + + n_actions = prestera_acl_rule_action_len(rule); + n_matches = prestera_acl_rule_match_len(rule); + + size = sizeof(*req) + sizeof(*actions) * n_actions + + sizeof(*matches) * n_matches; + + buff = kzalloc(size, GFP_KERNEL); + if (!buff) + return -ENOMEM; + + req = buff; + actions = buff + sizeof(*req); + matches = buff + sizeof(*req) + sizeof(*actions) * n_actions; + + /* put acl actions into the message */ + err = prestera_hw_acl_actions_put(actions, rule); + if (err) + goto free_buff; + + /* put acl matches into the message */ + err = prestera_hw_acl_matches_put(matches, rule); + if (err) + goto free_buff; + + req->ruleset_id = prestera_acl_rule_ruleset_id_get(rule); + req->priority = prestera_acl_rule_priority_get(rule); + req->n_actions = prestera_acl_rule_action_len(rule); + req->n_matches = prestera_acl_rule_match_len(rule); + + err = prestera_cmd_ret(sw, PRESTERA_CMD_TYPE_ACL_RULE_ADD, + &req->cmd, size, &resp.ret, sizeof(resp)); + if (err) + goto free_buff; + + *rule_id = resp.id; +free_buff: + kfree(buff); + return err; +} + +int prestera_hw_acl_rule_del(struct prestera_switch *sw, u32 rule_id) +{ + struct prestera_msg_acl_rule_req req = { + .id = rule_id + }; + + return prestera_cmd(sw, PRESTERA_CMD_TYPE_ACL_RULE_DELETE, + &req.cmd, sizeof(req)); +} + +int prestera_hw_acl_rule_stats_get(struct prestera_switch *sw, u32 rule_id, + u64 *packets, u64 *bytes) +{ + struct prestera_msg_acl_rule_stats_resp resp; + struct prestera_msg_acl_rule_req req = { + .id = rule_id + }; + int err; + + err = prestera_cmd_ret(sw, PRESTERA_CMD_TYPE_ACL_RULE_STATS_GET, + &req.cmd, sizeof(req), &resp.ret, sizeof(resp)); + if (err) + return err; + + *packets = resp.packets; + *bytes = resp.bytes; + + return 0; +} + +int prestera_hw_acl_port_bind(const struct prestera_port *port, u16 ruleset_id) +{ + struct prestera_msg_acl_ruleset_bind_req req = { + .port = port->hw_id, + .dev = port->dev_id, + .ruleset_id = ruleset_id, + }; + + return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_ACL_PORT_BIND, + &req.cmd, sizeof(req)); +} + +int prestera_hw_acl_port_unbind(const struct prestera_port *port, + u16 ruleset_id) +{ + struct prestera_msg_acl_ruleset_bind_req req = { + .port = port->hw_id, + .dev = port->dev_id, + .ruleset_id = ruleset_id, + }; + + return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_ACL_PORT_UNBIND, + &req.cmd, sizeof(req)); +} + +int prestera_hw_span_get(const struct prestera_port *port, u8 *span_id) +{ + struct prestera_msg_span_resp resp; + struct prestera_msg_span_req req = { + .port = port->hw_id, + .dev = port->dev_id, + }; + int err; + + err = prestera_cmd_ret(port->sw, PRESTERA_CMD_TYPE_SPAN_GET, + &req.cmd, sizeof(req), &resp.ret, sizeof(resp)); + if (err) + return err; + + *span_id = resp.id; + + return 0; +} + +int prestera_hw_span_bind(const struct prestera_port *port, u8 span_id) +{ + struct prestera_msg_span_req req = { + .port = port->hw_id, + .dev = port->dev_id, + .id = span_id, + }; + + return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_SPAN_BIND, + &req.cmd, sizeof(req)); +} + +int prestera_hw_span_unbind(const struct prestera_port *port) +{ + struct prestera_msg_span_req req = { + .port = port->hw_id, + .dev = port->dev_id, + }; + + return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_SPAN_UNBIND, + &req.cmd, sizeof(req)); +} + +int prestera_hw_span_release(struct prestera_switch *sw, u8 span_id) +{ + struct prestera_msg_span_req req = { + .id = span_id + }; + + return prestera_cmd(sw, PRESTERA_CMD_TYPE_SPAN_RELEASE, + &req.cmd, sizeof(req)); +} + int prestera_hw_port_type_get(const struct prestera_port *port, u8 *type) { struct prestera_msg_port_attr_req req = { @@ -988,7 +1416,43 @@ int prestera_hw_port_learning_set(struct prestera_port *port, bool enable) &req.cmd, sizeof(req)); } -int prestera_hw_port_flood_set(struct prestera_port *port, bool flood) +static int prestera_hw_port_uc_flood_set(struct prestera_port *port, bool flood) +{ + struct prestera_msg_port_attr_req req = { + .attr = PRESTERA_CMD_PORT_ATTR_FLOOD, + .port = port->hw_id, + .dev = port->dev_id, + .param = { + .flood_ext = { + .type = PRESTERA_PORT_FLOOD_TYPE_UC, + .enable = flood, + } + } + }; + + return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_PORT_ATTR_SET, + &req.cmd, sizeof(req)); +} + +static int prestera_hw_port_mc_flood_set(struct prestera_port *port, bool flood) +{ + struct prestera_msg_port_attr_req req = { + .attr = PRESTERA_CMD_PORT_ATTR_FLOOD, + .port = port->hw_id, + .dev = port->dev_id, + .param = { + .flood_ext = { + .type = PRESTERA_PORT_FLOOD_TYPE_MC, + .enable = flood, + } + } + }; + + return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_PORT_ATTR_SET, + &req.cmd, sizeof(req)); +} + +static int prestera_hw_port_flood_set_v2(struct prestera_port *port, bool flood) { struct prestera_msg_port_attr_req req = { .attr = PRESTERA_CMD_PORT_ATTR_FLOOD, @@ -1003,6 +1467,41 @@ int prestera_hw_port_flood_set(struct prestera_port *port, bool flood) &req.cmd, sizeof(req)); } +int prestera_hw_port_flood_set(struct prestera_port *port, unsigned long mask, + unsigned long val) +{ + int err; + + if (port->sw->dev->fw_rev.maj <= 2) { + if (!(mask & BR_FLOOD)) + return 0; + + return prestera_hw_port_flood_set_v2(port, val & BR_FLOOD); + } + + if (mask & BR_FLOOD) { + err = prestera_hw_port_uc_flood_set(port, val & BR_FLOOD); + if (err) + goto err_uc_flood; + } + + if (mask & BR_MCAST_FLOOD) { + err = prestera_hw_port_mc_flood_set(port, val & BR_MCAST_FLOOD); + if (err) + goto err_mc_flood; + } + + return 0; + +err_mc_flood: + prestera_hw_port_mc_flood_set(port, 0); +err_uc_flood: + if (mask & BR_FLOOD) + prestera_hw_port_uc_flood_set(port, 0); + + return err; +} + int prestera_hw_vlan_create(struct prestera_switch *sw, u16 vid) { struct prestera_msg_vlan_req req = { @@ -1067,8 +1566,10 @@ int prestera_hw_fdb_add(struct prestera_port *port, const unsigned char *mac, u16 vid, bool dynamic) { struct prestera_msg_fdb_req req = { - .port = port->hw_id, - .dev = port->dev_id, + .dest = { + .dev = port->dev_id, + .port = port->hw_id, + }, .vid = vid, .dynamic = dynamic, }; @@ -1083,8 +1584,10 @@ int prestera_hw_fdb_del(struct prestera_port *port, const unsigned char *mac, u16 vid) { struct prestera_msg_fdb_req req = { - .port = port->hw_id, - .dev = port->dev_id, + .dest = { + .dev = port->dev_id, + .port = port->hw_id, + }, .vid = vid, }; @@ -1094,11 +1597,48 @@ int prestera_hw_fdb_del(struct prestera_port *port, const unsigned char *mac, &req.cmd, sizeof(req)); } +int prestera_hw_lag_fdb_add(struct prestera_switch *sw, u16 lag_id, + const unsigned char *mac, u16 vid, bool dynamic) +{ + struct prestera_msg_fdb_req req = { + .dest_type = PRESTERA_HW_FDB_ENTRY_TYPE_LAG, + .dest = { + .lag_id = lag_id, + }, + .vid = vid, + .dynamic = dynamic, + }; + + ether_addr_copy(req.mac, mac); + + return prestera_cmd(sw, PRESTERA_CMD_TYPE_FDB_ADD, + &req.cmd, sizeof(req)); +} + +int prestera_hw_lag_fdb_del(struct prestera_switch *sw, u16 lag_id, + const unsigned char *mac, u16 vid) +{ + struct prestera_msg_fdb_req req = { + .dest_type = PRESTERA_HW_FDB_ENTRY_TYPE_LAG, + .dest = { + .lag_id = lag_id, + }, + .vid = vid, + }; + + ether_addr_copy(req.mac, mac); + + return prestera_cmd(sw, PRESTERA_CMD_TYPE_FDB_DELETE, + &req.cmd, sizeof(req)); +} + int prestera_hw_fdb_flush_port(struct prestera_port *port, u32 mode) { struct prestera_msg_fdb_req req = { - .port = port->hw_id, - .dev = port->dev_id, + .dest = { + .dev = port->dev_id, + .port = port->hw_id, + }, .flush_mode = mode, }; @@ -1121,8 +1661,10 @@ int prestera_hw_fdb_flush_port_vlan(struct prestera_port *port, u16 vid, u32 mode) { struct prestera_msg_fdb_req req = { - .port = port->hw_id, - .dev = port->dev_id, + .dest = { + .dev = port->dev_id, + .port = port->hw_id, + }, .vid = vid, .flush_mode = mode, }; @@ -1131,6 +1673,37 @@ int prestera_hw_fdb_flush_port_vlan(struct prestera_port *port, u16 vid, &req.cmd, sizeof(req)); } +int prestera_hw_fdb_flush_lag(struct prestera_switch *sw, u16 lag_id, + u32 mode) +{ + struct prestera_msg_fdb_req req = { + .dest_type = PRESTERA_HW_FDB_ENTRY_TYPE_LAG, + .dest = { + .lag_id = lag_id, + }, + .flush_mode = mode, + }; + + return prestera_cmd(sw, PRESTERA_CMD_TYPE_FDB_FLUSH_PORT, + &req.cmd, sizeof(req)); +} + +int prestera_hw_fdb_flush_lag_vlan(struct prestera_switch *sw, + u16 lag_id, u16 vid, u32 mode) +{ + struct prestera_msg_fdb_req req = { + .dest_type = PRESTERA_HW_FDB_ENTRY_TYPE_LAG, + .dest = { + .lag_id = lag_id, + }, + .vid = vid, + .flush_mode = mode, + }; + + return prestera_cmd(sw, PRESTERA_CMD_TYPE_FDB_FLUSH_PORT_VLAN, + &req.cmd, sizeof(req)); +} + int prestera_hw_bridge_create(struct prestera_switch *sw, u16 *bridge_id) { struct prestera_msg_bridge_resp resp; @@ -1212,6 +1785,68 @@ int prestera_hw_rxtx_port_init(struct prestera_port *port) &req.cmd, sizeof(req)); } +int prestera_hw_lag_member_add(struct prestera_port *port, u16 lag_id) +{ + struct prestera_msg_lag_req req = { + .port = port->hw_id, + .dev = port->dev_id, + .lag_id = lag_id, + }; + + return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_LAG_MEMBER_ADD, + &req.cmd, sizeof(req)); +} + +int prestera_hw_lag_member_del(struct prestera_port *port, u16 lag_id) +{ + struct prestera_msg_lag_req req = { + .port = port->hw_id, + .dev = port->dev_id, + .lag_id = lag_id, + }; + + return prestera_cmd(port->sw, PRESTERA_CMD_TYPE_LAG_MEMBER_DELETE, + &req.cmd, sizeof(req)); +} + +int prestera_hw_lag_member_enable(struct prestera_port *port, u16 lag_id, + bool enable) +{ + struct prestera_msg_lag_req req = { + .port = port->hw_id, + .dev = port->dev_id, + .lag_id = lag_id, + }; + u32 cmd; + + cmd = enable ? PRESTERA_CMD_TYPE_LAG_MEMBER_ENABLE : + PRESTERA_CMD_TYPE_LAG_MEMBER_DISABLE; + + return prestera_cmd(port->sw, cmd, &req.cmd, sizeof(req)); +} + +int +prestera_hw_cpu_code_counters_get(struct prestera_switch *sw, u8 code, + enum prestera_hw_cpu_code_cnt_t counter_type, + u64 *packet_count) +{ + struct prestera_msg_cpu_code_counter_req req = { + .counter_type = counter_type, + .code = code, + }; + struct mvsw_msg_cpu_code_counter_ret resp; + int err; + + err = prestera_cmd_ret(sw, PRESTERA_CMD_TYPE_CPU_CODE_COUNTERS_GET, + &req.cmd, sizeof(req), &resp.ret, sizeof(resp)); + if (err) + return err; + + *packet_count = resp.packet_count; + + return 0; +} + int prestera_hw_event_handler_register(struct prestera_switch *sw, enum prestera_event_type type, prestera_event_cb_t fn, diff --git a/drivers/net/ethernet/marvell/prestera/prestera_hw.h b/drivers/net/ethernet/marvell/prestera/prestera_hw.h index b2b5ac95b4e3..546d5fd8240d 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_hw.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_hw.h @@ -89,12 +89,18 @@ enum { PRESTERA_STP_FORWARD, }; +enum prestera_hw_cpu_code_cnt_t { + PRESTERA_HW_CPU_CODE_CNT_TYPE_DROP = 0, + PRESTERA_HW_CPU_CODE_CNT_TYPE_TRAP = 1, +}; + struct prestera_switch; struct prestera_port; struct prestera_port_stats; struct prestera_port_caps; enum prestera_event_type; struct prestera_event; +struct prestera_acl_rule; typedef void (*prestera_event_cb_t) (struct prestera_switch *sw, struct prestera_event *evt, void *arg); @@ -138,7 +144,8 @@ int prestera_hw_port_mdix_get(const struct prestera_port *port, u8 *status, int prestera_hw_port_mdix_set(const struct prestera_port *port, u8 mode); int prestera_hw_port_speed_get(const struct prestera_port *port, u32 *speed); int prestera_hw_port_learning_set(struct prestera_port *port, bool enable); -int prestera_hw_port_flood_set(struct prestera_port *port, bool flood); +int prestera_hw_port_flood_set(struct prestera_port *port, unsigned long mask, + unsigned long val); int prestera_hw_port_accept_frm_type(struct prestera_port *port, enum prestera_accept_frm_type type); /* Vlan API */ @@ -165,6 +172,28 @@ int prestera_hw_bridge_delete(struct prestera_switch *sw, u16 bridge_id); int prestera_hw_bridge_port_add(struct prestera_port *port, u16 bridge_id); int prestera_hw_bridge_port_delete(struct prestera_port *port, u16 bridge_id); +/* ACL API */ +int prestera_hw_acl_ruleset_create(struct prestera_switch *sw, + u16 *ruleset_id); +int prestera_hw_acl_ruleset_del(struct prestera_switch *sw, + u16 ruleset_id); +int prestera_hw_acl_rule_add(struct prestera_switch *sw, + struct prestera_acl_rule *rule, + u32 *rule_id); +int prestera_hw_acl_rule_del(struct prestera_switch *sw, u32 rule_id); +int prestera_hw_acl_rule_stats_get(struct prestera_switch *sw, + u32 rule_id, u64 *packets, u64 *bytes); +int prestera_hw_acl_port_bind(const struct prestera_port *port, + u16 ruleset_id); +int prestera_hw_acl_port_unbind(const struct prestera_port *port, + u16 ruleset_id); + +/* SPAN API */ +int prestera_hw_span_get(const struct prestera_port *port, u8 *span_id); +int prestera_hw_span_bind(const struct prestera_port *port, u8 span_id); +int prestera_hw_span_unbind(const struct prestera_port *port); +int prestera_hw_span_release(struct prestera_switch *sw, u8 span_id); + /* Event handlers */ int prestera_hw_event_handler_register(struct prestera_switch *sw, enum prestera_event_type type, @@ -179,4 +208,24 @@ int prestera_hw_rxtx_init(struct prestera_switch *sw, struct prestera_rxtx_params *params); int prestera_hw_rxtx_port_init(struct prestera_port *port); +/* LAG API */ +int prestera_hw_lag_member_add(struct prestera_port *port, u16 lag_id); +int prestera_hw_lag_member_del(struct prestera_port *port, u16 lag_id); +int prestera_hw_lag_member_enable(struct prestera_port *port, u16 lag_id, + bool enable); +int prestera_hw_lag_fdb_add(struct prestera_switch *sw, u16 lag_id, + const unsigned char *mac, u16 vid, bool dynamic); +int prestera_hw_lag_fdb_del(struct prestera_switch *sw, u16 lag_id, + const unsigned char *mac, u16 vid); +int prestera_hw_fdb_flush_lag(struct prestera_switch *sw, u16 lag_id, + u32 mode); +int prestera_hw_fdb_flush_lag_vlan(struct prestera_switch *sw, + u16 lag_id, u16 vid, u32 mode); + +/* HW trap/drop counters API */ +int +prestera_hw_cpu_code_counters_get(struct prestera_switch *sw, u8 code, + enum prestera_hw_cpu_code_cnt_t counter_type, + u64 *packet_count); + #endif /* _PRESTERA_HW_H_ */ diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 2768c78528a5..226f4ff29f6e 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -8,9 +8,13 @@ #include #include #include +#include #include "prestera.h" #include "prestera_hw.h" +#include "prestera_acl.h" +#include "prestera_flow.h" +#include "prestera_span.h" #include "prestera_rxtx.h" #include "prestera_devlink.h" #include "prestera_ethtool.h" @@ -199,10 +203,25 @@ static void prestera_port_stats_update(struct work_struct *work) msecs_to_jiffies(PRESTERA_STATS_DELAY_MS)); } +static int prestera_port_setup_tc(struct net_device *dev, + enum tc_setup_type type, + void *type_data) +{ + struct prestera_port *port = netdev_priv(dev); + + switch (type) { + case TC_SETUP_BLOCK: + return prestera_flow_block_setup(port, type_data); + default: + return -EOPNOTSUPP; + } +} + static const struct net_device_ops prestera_netdev_ops = { .ndo_open = prestera_port_open, .ndo_stop = prestera_port_close, .ndo_start_xmit = prestera_port_xmit, + .ndo_setup_tc = prestera_port_setup_tc, .ndo_change_mtu = prestera_port_change_mtu, .ndo_get_stats64 = prestera_port_get_stats64, .ndo_set_mac_address = prestera_port_set_mac_address, @@ -281,6 +300,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) INIT_LIST_HEAD(&port->vlans_list); port->pvid = PRESTERA_DEFAULT_VID; + port->lag = NULL; port->dev = dev; port->id = id; port->sw = sw; @@ -296,7 +316,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) if (err) goto err_dl_port_register; - dev->features |= NETIF_F_NETNS_LOCAL; + dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_HW_TC; dev->netdev_ops = &prestera_netdev_ops; dev->ethtool_ops = &prestera_ethtool_ops; @@ -472,6 +492,149 @@ static int prestera_switch_set_base_mac_addr(struct prestera_switch *sw) return prestera_hw_switch_mac_set(sw, sw->base_mac); } +struct prestera_lag *prestera_lag_by_id(struct prestera_switch *sw, u16 id) +{ + return id < sw->lag_max ? &sw->lags[id] : NULL; +} + +static struct prestera_lag *prestera_lag_by_dev(struct prestera_switch *sw, + struct net_device *dev) +{ + struct prestera_lag *lag; + u16 id; + + for (id = 0; id < sw->lag_max; id++) { + lag = &sw->lags[id]; + if (lag->dev == dev) + return lag; + } + + return NULL; +} + +static struct prestera_lag *prestera_lag_create(struct prestera_switch *sw, + struct net_device *lag_dev) +{ + struct prestera_lag *lag = NULL; + u16 id; + + for (id = 0; id < sw->lag_max; id++) { + lag = &sw->lags[id]; + if (!lag->dev) + break; + } + if (lag) { + INIT_LIST_HEAD(&lag->members); + lag->dev = lag_dev; + } + + return lag; +} + +static void prestera_lag_destroy(struct prestera_switch *sw, + struct prestera_lag *lag) +{ + WARN_ON(!list_empty(&lag->members)); + lag->member_count = 0; + lag->dev = NULL; +} + +static int prestera_lag_port_add(struct prestera_port *port, + struct net_device *lag_dev) +{ + struct prestera_switch *sw = port->sw; + struct prestera_lag *lag; + int err; + + lag = prestera_lag_by_dev(sw, lag_dev); + if (!lag) { + lag = prestera_lag_create(sw, lag_dev); + if (!lag) + return -ENOSPC; + } + + if (lag->member_count >= sw->lag_member_max) + return -ENOSPC; + + err = prestera_hw_lag_member_add(port, lag->lag_id); + if (err) { + if (!lag->member_count) + prestera_lag_destroy(sw, lag); + return err; + } + + list_add(&port->lag_member, &lag->members); + lag->member_count++; + port->lag = lag; + + return 0; +} + +static int prestera_lag_port_del(struct prestera_port *port) +{ + struct prestera_switch *sw = port->sw; + struct prestera_lag *lag = port->lag; + int err; + + if (!lag || !lag->member_count) + return -EINVAL; + + err = prestera_hw_lag_member_del(port, lag->lag_id); + if (err) + return err; + + list_del(&port->lag_member); + lag->member_count--; + port->lag = NULL; + + if (netif_is_bridge_port(lag->dev)) { + struct net_device *br_dev; + + br_dev = netdev_master_upper_dev_get(lag->dev); + + prestera_bridge_port_leave(br_dev, port); + } + + if (!lag->member_count) + prestera_lag_destroy(sw, lag); + + return 0; +} + +bool prestera_port_is_lag_member(const struct prestera_port *port) +{ + return !!port->lag; +} + +u16 prestera_port_lag_id(const struct prestera_port *port) +{ + return port->lag->lag_id; +} + +static int prestera_lag_init(struct prestera_switch *sw) +{ + u16 id; + + sw->lags = kcalloc(sw->lag_max, sizeof(*sw->lags), GFP_KERNEL); + if (!sw->lags) + return -ENOMEM; + + for (id = 0; id < sw->lag_max; id++) + sw->lags[id].lag_id = id; + + return 0; +} + +static void prestera_lag_fini(struct prestera_switch *sw) +{ + u8 idx; + + for (idx = 0; idx < sw->lag_max; idx++) + WARN_ON(sw->lags[idx].member_count); + + kfree(sw->lags); +} + bool prestera_netdev_check(const struct net_device *dev) { return dev->netdev_ops == &prestera_netdev_ops; @@ -505,16 +668,119 @@ struct prestera_port *prestera_port_dev_lower_find(struct net_device *dev) return port; } -static int prestera_netdev_port_event(struct net_device *dev, +static int prestera_netdev_port_lower_event(struct net_device *dev, + unsigned long event, void *ptr) +{ + struct netdev_notifier_changelowerstate_info *info = ptr; + struct netdev_lag_lower_state_info *lower_state_info; + struct prestera_port *port = netdev_priv(dev); + bool enabled; + + if (!netif_is_lag_port(dev)) + return 0; + if (!prestera_port_is_lag_member(port)) + return 0; + + lower_state_info = info->lower_state_info; + enabled = lower_state_info->link_up && lower_state_info->tx_enabled; + + return prestera_hw_lag_member_enable(port, port->lag->lag_id, enabled); +} + +static bool prestera_lag_master_check(struct net_device *lag_dev, + struct netdev_lag_upper_info *info, + struct netlink_ext_ack *ext_ack) +{ + if (info->tx_type != NETDEV_LAG_TX_TYPE_HASH) { + NL_SET_ERR_MSG_MOD(ext_ack, "Unsupported LAG Tx type"); + return false; + } + + return true; +} + +static int prestera_netdev_port_event(struct net_device *lower, + struct net_device *dev, unsigned long event, void *ptr) { + struct netdev_notifier_changeupper_info *info = ptr; + struct prestera_port *port = netdev_priv(dev); + struct netlink_ext_ack *extack; + struct net_device *upper; + + extack = netdev_notifier_info_to_extack(&info->info); + upper = info->upper_dev; + switch (event) { case NETDEV_PRECHANGEUPPER: + if (!netif_is_bridge_master(upper) && + !netif_is_lag_master(upper)) { + NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type"); + return -EINVAL; + } + + if (!info->linking) + break; + + if (netdev_has_any_upper_dev(upper)) { + NL_SET_ERR_MSG_MOD(extack, "Upper device is already enslaved"); + return -EINVAL; + } + + if (netif_is_lag_master(upper) && + !prestera_lag_master_check(upper, info->upper_info, extack)) + return -EOPNOTSUPP; + if (netif_is_lag_master(upper) && vlan_uses_dev(dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Master device is a LAG master and port has a VLAN"); + return -EINVAL; + } + if (netif_is_lag_port(dev) && is_vlan_dev(upper) && + !netif_is_lag_master(vlan_dev_real_dev(upper))) { + NL_SET_ERR_MSG_MOD(extack, + "Can not put a VLAN on a LAG port"); + return -EINVAL; + } + break; + case NETDEV_CHANGEUPPER: - return prestera_bridge_port_event(dev, event, ptr); - default: - return 0; + if (netif_is_bridge_master(upper)) { + if (info->linking) + return prestera_bridge_port_join(upper, port); + else + prestera_bridge_port_leave(upper, port); + } else if (netif_is_lag_master(upper)) { + if (info->linking) + return prestera_lag_port_add(port, upper); + else + prestera_lag_port_del(port); + } + break; + + case NETDEV_CHANGELOWERSTATE: + return prestera_netdev_port_lower_event(dev, event, ptr); } + + return 0; +} + +static int prestera_netdevice_lag_event(struct net_device *lag_dev, + unsigned long event, void *ptr) +{ + struct net_device *dev; + struct list_head *iter; + int err; + + netdev_for_each_lower_dev(lag_dev, dev, iter) { + if (prestera_netdev_check(dev)) { + err = prestera_netdev_port_event(lag_dev, dev, event, + ptr); + if (err) + return err; + } + } + + return 0; } static int prestera_netdev_event_handler(struct notifier_block *nb, @@ -524,7 +790,9 @@ static int prestera_netdev_event_handler(struct notifier_block *nb, int err = 0; if (prestera_netdev_check(dev)) - err = prestera_netdev_port_event(dev, event, ptr); + err = prestera_netdev_port_event(dev, dev, event, ptr); + else if (netif_is_lag_master(dev)) + err = prestera_netdevice_lag_event(dev, event, ptr); return notifier_from_errno(err); } @@ -574,10 +842,22 @@ static int prestera_switch_init(struct prestera_switch *sw) if (err) goto err_handlers_register; + err = prestera_acl_init(sw); + if (err) + goto err_acl_init; + + err = prestera_span_init(sw); + if (err) + goto err_span_init; + err = prestera_devlink_register(sw); if (err) goto err_dl_register; + err = prestera_lag_init(sw); + if (err) + goto err_lag_init; + err = prestera_create_ports(sw); if (err) goto err_ports_create; @@ -585,8 +865,14 @@ static int prestera_switch_init(struct prestera_switch *sw) return 0; err_ports_create: + prestera_lag_fini(sw); +err_lag_init: prestera_devlink_unregister(sw); err_dl_register: + prestera_span_fini(sw); +err_span_init: + prestera_acl_fini(sw); +err_acl_init: prestera_event_handlers_unregister(sw); err_handlers_register: prestera_rxtx_switch_fini(sw); @@ -602,7 +888,10 @@ err_swdev_register: static void prestera_switch_fini(struct prestera_switch *sw) { prestera_destroy_ports(sw); + prestera_lag_fini(sw); prestera_devlink_unregister(sw); + prestera_span_fini(sw); + prestera_acl_fini(sw); prestera_event_handlers_unregister(sw); prestera_rxtx_switch_fini(sw); prestera_switchdev_fini(sw); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index 298110119272..a250d394da38 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 /* Copyright (c) 2019-2020 Marvell International Ltd. All rights reserved */ +#include #include #include #include @@ -13,9 +14,12 @@ #define PRESTERA_MSG_MAX_SIZE 1500 -#define PRESTERA_SUPP_FW_MAJ_VER 2 +#define PRESTERA_SUPP_FW_MAJ_VER 3 #define PRESTERA_SUPP_FW_MIN_VER 0 +#define PRESTERA_PREV_FW_MAJ_VER 2 +#define PRESTERA_PREV_FW_MIN_VER 0 + #define PRESTERA_FW_PATH_FMT "mrvl/prestera/mvsw_prestera_fw-v%u.%u.img" #define PRESTERA_FW_HDR_MAGIC 0x351D9D06 @@ -144,6 +148,11 @@ struct prestera_fw_regs { /* PRESTERA_CMD_RCV_CTL_REG flags */ #define PRESTERA_CMD_F_REPL_SENT BIT(0) +#define PRESTERA_FW_EVT_CTL_STATUS_MASK GENMASK(1, 0) + +#define PRESTERA_FW_EVT_CTL_STATUS_ON 0 +#define PRESTERA_FW_EVT_CTL_STATUS_OFF 1 + #define PRESTERA_EVTQ_REG_OFFSET(q, f) \ (PRESTERA_FW_REG_OFFSET(evtq_list) + \ (q) * sizeof(struct prestera_fw_evtq_regs) + \ @@ -166,6 +175,8 @@ struct prestera_fw_evtq { }; struct prestera_fw { + struct prestera_fw_rev rev_supp; + const struct firmware *bin; struct workqueue_struct *wq; struct prestera_device dev; u8 __iomem *ldr_regs; @@ -260,6 +271,15 @@ static u8 prestera_fw_evtq_pick(struct prestera_fw *fw) return PRESTERA_EVT_QNUM_MAX; } +static void prestera_fw_evt_ctl_status_set(struct prestera_fw *fw, u32 val) +{ + u32 status = prestera_fw_read(fw, PRESTERA_FW_STATUS_REG); + + u32p_replace_bits(&status, val, PRESTERA_FW_EVT_CTL_STATUS_MASK); + + prestera_fw_write(fw, PRESTERA_FW_STATUS_REG, status); +} + static void prestera_fw_evt_work_fn(struct work_struct *work) { struct prestera_fw *fw; @@ -269,6 +289,8 @@ static void prestera_fw_evt_work_fn(struct work_struct *work) fw = container_of(work, struct prestera_fw, evt_work); msg = fw->evt_msg; + prestera_fw_evt_ctl_status_set(fw, PRESTERA_FW_EVT_CTL_STATUS_OFF); + while ((qid = prestera_fw_evtq_pick(fw)) < PRESTERA_EVT_QNUM_MAX) { u32 idx; u32 len; @@ -288,6 +310,8 @@ static void prestera_fw_evt_work_fn(struct work_struct *work) if (fw->dev.recv_msg) fw->dev.recv_msg(&fw->dev, msg, len); } + + prestera_fw_evt_ctl_status_set(fw, PRESTERA_FW_EVT_CTL_STATUS_ON); } static int prestera_fw_wait_reg32(struct prestera_fw *fw, u32 reg, u32 cmp, @@ -576,25 +600,24 @@ static void prestera_fw_rev_parse(const struct prestera_fw_header *hdr, static int prestera_fw_rev_check(struct prestera_fw *fw) { struct prestera_fw_rev *rev = &fw->dev.fw_rev; - u16 maj_supp = PRESTERA_SUPP_FW_MAJ_VER; - u16 min_supp = PRESTERA_SUPP_FW_MIN_VER; - if (rev->maj == maj_supp && rev->min >= min_supp) + if (rev->maj == fw->rev_supp.maj && rev->min >= fw->rev_supp.min) return 0; dev_err(fw->dev.dev, "Driver supports FW version only '%u.%u.x'", - PRESTERA_SUPP_FW_MAJ_VER, PRESTERA_SUPP_FW_MIN_VER); + fw->rev_supp.maj, fw->rev_supp.min); return -EINVAL; } -static int prestera_fw_hdr_parse(struct prestera_fw *fw, - const struct firmware *img) +static int prestera_fw_hdr_parse(struct prestera_fw *fw) { - struct prestera_fw_header *hdr = (struct prestera_fw_header *)img->data; struct prestera_fw_rev *rev = &fw->dev.fw_rev; + struct prestera_fw_header *hdr; u32 magic; + hdr = (struct prestera_fw_header *)fw->bin->data; + magic = be32_to_cpu(hdr->magic_number); if (magic != PRESTERA_FW_HDR_MAGIC) { dev_err(fw->dev.dev, "FW img hdr magic is invalid"); @@ -609,11 +632,52 @@ static int prestera_fw_hdr_parse(struct prestera_fw *fw, return prestera_fw_rev_check(fw); } +static int prestera_fw_get(struct prestera_fw *fw) +{ + int ver_maj = PRESTERA_SUPP_FW_MAJ_VER; + int ver_min = PRESTERA_SUPP_FW_MIN_VER; + char fw_path[128]; + int err; + +pick_fw_ver: + snprintf(fw_path, sizeof(fw_path), PRESTERA_FW_PATH_FMT, + ver_maj, ver_min); + + err = request_firmware_direct(&fw->bin, fw_path, fw->dev.dev); + if (err) { + if (ver_maj == PRESTERA_SUPP_FW_MAJ_VER) { + ver_maj = PRESTERA_PREV_FW_MAJ_VER; + ver_min = PRESTERA_PREV_FW_MIN_VER; + + dev_warn(fw->dev.dev, + "missing latest %s firmware, fall-back to previous %u.%u version\n", + fw_path, ver_maj, ver_min); + + goto pick_fw_ver; + } else { + dev_err(fw->dev.dev, "failed to request previous firmware: %s\n", + fw_path); + return err; + } + } + + dev_info(fw->dev.dev, "Loading %s ...", fw_path); + + fw->rev_supp.maj = ver_maj; + fw->rev_supp.min = ver_min; + fw->rev_supp.sub = 0; + + return 0; +} + +static void prestera_fw_put(struct prestera_fw *fw) +{ + release_firmware(fw->bin); +} + static int prestera_fw_load(struct prestera_fw *fw) { size_t hlen = sizeof(struct prestera_fw_header); - const struct firmware *f; - char fw_path[128]; int err; err = prestera_ldr_wait_reg32(fw, PRESTERA_LDR_READY_REG, @@ -632,30 +696,24 @@ static int prestera_fw_load(struct prestera_fw *fw) fw->ldr_wr_idx = 0; - snprintf(fw_path, sizeof(fw_path), PRESTERA_FW_PATH_FMT, - PRESTERA_SUPP_FW_MAJ_VER, PRESTERA_SUPP_FW_MIN_VER); - - err = request_firmware_direct(&f, fw_path, fw->dev.dev); - if (err) { - dev_err(fw->dev.dev, "failed to request firmware file\n"); + err = prestera_fw_get(fw); + if (err) return err; - } - err = prestera_fw_hdr_parse(fw, f); + err = prestera_fw_hdr_parse(fw); if (err) { dev_err(fw->dev.dev, "FW image header is invalid\n"); goto out_release; } - prestera_ldr_write(fw, PRESTERA_LDR_IMG_SIZE_REG, f->size - hlen); + prestera_ldr_write(fw, PRESTERA_LDR_IMG_SIZE_REG, fw->bin->size - hlen); prestera_ldr_write(fw, PRESTERA_LDR_CTL_REG, PRESTERA_LDR_CTL_DL_START); - dev_info(fw->dev.dev, "Loading %s ...", fw_path); - - err = prestera_ldr_fw_send(fw, f->data + hlen, f->size - hlen); + err = prestera_ldr_fw_send(fw, fw->bin->data + hlen, + fw->bin->size - hlen); out_release: - release_firmware(f); + prestera_fw_put(fw); return err; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c index 2a13c318048c..73d2eba5262f 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c @@ -14,6 +14,7 @@ #include "prestera.h" #include "prestera_hw.h" #include "prestera_rxtx.h" +#include "prestera_devlink.h" #define PRESTERA_SDMA_WAIT_MUL 10 @@ -214,9 +215,10 @@ static struct sk_buff *prestera_sdma_rx_skb_get(struct prestera_sdma *sdma, static int prestera_rxtx_process_skb(struct prestera_sdma *sdma, struct sk_buff *skb) { - const struct prestera_port *port; + struct prestera_port *port; struct prestera_dsa dsa; u32 hw_port, dev_id; + u8 cpu_code; int err; skb_pull(skb, ETH_HLEN); @@ -259,6 +261,9 @@ static int prestera_rxtx_process_skb(struct prestera_sdma *sdma, __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tci); } + cpu_code = dsa.cpu_code; + prestera_devlink_trap_report(port, skb, cpu_code); + return 0; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_span.c b/drivers/net/ethernet/marvell/prestera/prestera_span.c new file mode 100644 index 000000000000..3cafca827bb7 --- /dev/null +++ b/drivers/net/ethernet/marvell/prestera/prestera_span.c @@ -0,0 +1,239 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 +/* Copyright (c) 2020 Marvell International Ltd. All rights reserved */ + +#include +#include + +#include "prestera.h" +#include "prestera_hw.h" +#include "prestera_acl.h" +#include "prestera_span.h" + +struct prestera_span_entry { + struct list_head list; + struct prestera_port *port; + refcount_t ref_count; + u8 id; +}; + +struct prestera_span { + struct prestera_switch *sw; + struct list_head entries; +}; + +static struct prestera_span_entry * +prestera_span_entry_create(struct prestera_port *port, u8 span_id) +{ + struct prestera_span_entry *entry; + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return ERR_PTR(-ENOMEM); + + refcount_set(&entry->ref_count, 1); + entry->port = port; + entry->id = span_id; + list_add_tail(&entry->list, &port->sw->span->entries); + + return entry; +} + +static void prestera_span_entry_del(struct prestera_span_entry *entry) +{ + list_del(&entry->list); + kfree(entry); +} + +static struct prestera_span_entry * +prestera_span_entry_find_by_id(struct prestera_span *span, u8 span_id) +{ + struct prestera_span_entry *entry; + + list_for_each_entry(entry, &span->entries, list) { + if (entry->id == span_id) + return entry; + } + + return NULL; +} + +static struct prestera_span_entry * +prestera_span_entry_find_by_port(struct prestera_span *span, + struct prestera_port *port) +{ + struct prestera_span_entry *entry; + + list_for_each_entry(entry, &span->entries, list) { + if (entry->port == port) + return entry; + } + + return NULL; +} + +static int prestera_span_get(struct prestera_port *port, u8 *span_id) +{ + u8 new_span_id; + struct prestera_switch *sw = port->sw; + struct prestera_span_entry *entry; + int err; + + entry = prestera_span_entry_find_by_port(sw->span, port); + if (entry) { + refcount_inc(&entry->ref_count); + *span_id = entry->id; + return 0; + } + + err = prestera_hw_span_get(port, &new_span_id); + if (err) + return err; + + entry = prestera_span_entry_create(port, new_span_id); + if (IS_ERR(entry)) { + prestera_hw_span_release(sw, new_span_id); + return PTR_ERR(entry); + } + + *span_id = new_span_id; + return 0; +} + +static int prestera_span_put(struct prestera_switch *sw, u8 span_id) +{ + struct prestera_span_entry *entry; + int err; + + entry = prestera_span_entry_find_by_id(sw->span, span_id); + if (!entry) + return false; + + if (!refcount_dec_and_test(&entry->ref_count)) + return 0; + + err = prestera_hw_span_release(sw, span_id); + if (err) + return err; + + prestera_span_entry_del(entry); + return 0; +} + +static int prestera_span_rule_add(struct prestera_flow_block_binding *binding, + struct prestera_port *to_port) +{ + struct prestera_switch *sw = binding->port->sw; + u8 span_id; + int err; + + if (binding->span_id != PRESTERA_SPAN_INVALID_ID) + /* port already in mirroring */ + return -EEXIST; + + err = prestera_span_get(to_port, &span_id); + if (err) + return err; + + err = prestera_hw_span_bind(binding->port, span_id); + if (err) { + prestera_span_put(sw, span_id); + return err; + } + + binding->span_id = span_id; + return 0; +} + +static int prestera_span_rule_del(struct prestera_flow_block_binding *binding) +{ + int err; + + err = prestera_hw_span_unbind(binding->port); + if (err) + return err; + + err = prestera_span_put(binding->port->sw, binding->span_id); + if (err) + return err; + + binding->span_id = PRESTERA_SPAN_INVALID_ID; + return 0; +} + +int prestera_span_replace(struct prestera_flow_block *block, + struct tc_cls_matchall_offload *f) +{ + struct prestera_flow_block_binding *binding; + __be16 protocol = f->common.protocol; + struct flow_action_entry *act; + struct prestera_port *port; + int err; + + if (!flow_offload_has_one_action(&f->rule->action)) { + NL_SET_ERR_MSG(f->common.extack, + "Only singular actions are supported"); + return -EOPNOTSUPP; + } + + act = &f->rule->action.entries[0]; + + if (!prestera_netdev_check(act->dev)) { + NL_SET_ERR_MSG(f->common.extack, + "Only Marvell Prestera port is supported"); + return -EINVAL; + } + if (!tc_cls_can_offload_and_chain0(act->dev, &f->common)) + return -EOPNOTSUPP; + if (act->id != FLOW_ACTION_MIRRED) + return -EOPNOTSUPP; + if (protocol != htons(ETH_P_ALL)) + return -EOPNOTSUPP; + + port = netdev_priv(act->dev); + + list_for_each_entry(binding, &block->binding_list, list) { + err = prestera_span_rule_add(binding, port); + if (err) + goto rollback; + } + + return 0; + +rollback: + list_for_each_entry_continue_reverse(binding, + &block->binding_list, list) + prestera_span_rule_del(binding); + return err; +} + +void prestera_span_destroy(struct prestera_flow_block *block) +{ + struct prestera_flow_block_binding *binding; + + list_for_each_entry(binding, &block->binding_list, list) + prestera_span_rule_del(binding); +} + +int prestera_span_init(struct prestera_switch *sw) +{ + struct prestera_span *span; + + span = kzalloc(sizeof(*span), GFP_KERNEL); + if (!span) + return -ENOMEM; + + INIT_LIST_HEAD(&span->entries); + + sw->span = span; + span->sw = sw; + + return 0; +} + +void prestera_span_fini(struct prestera_switch *sw) +{ + struct prestera_span *span = sw->span; + + WARN_ON(!list_empty(&span->entries)); + kfree(span); +} diff --git a/drivers/net/ethernet/marvell/prestera/prestera_span.h b/drivers/net/ethernet/marvell/prestera/prestera_span.h new file mode 100644 index 000000000000..f0644521f78a --- /dev/null +++ b/drivers/net/ethernet/marvell/prestera/prestera_span.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* Copyright (c) 2019-2020 Marvell International Ltd. All rights reserved. */ + +#ifndef _PRESTERA_SPAN_H_ +#define _PRESTERA_SPAN_H_ + +#include + +#define PRESTERA_SPAN_INVALID_ID -1 + +struct prestera_switch; +struct prestera_flow_block; + +int prestera_span_init(struct prestera_switch *sw); +void prestera_span_fini(struct prestera_switch *sw); +int prestera_span_replace(struct prestera_flow_block *block, + struct tc_cls_matchall_offload *f); +void prestera_span_destroy(struct prestera_flow_block *block); + +#endif /* _PRESTERA_SPAN_H_ */ diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c index cb564890a3dc..0b3e8f2db294 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c @@ -180,6 +180,45 @@ err_port_vlan_alloc: return ERR_PTR(err); } +static int prestera_fdb_add(struct prestera_port *port, + const unsigned char *mac, u16 vid, bool dynamic) +{ + if (prestera_port_is_lag_member(port)) + return prestera_hw_lag_fdb_add(port->sw, prestera_port_lag_id(port), + mac, vid, dynamic); + + return prestera_hw_fdb_add(port, mac, vid, dynamic); +} + +static int prestera_fdb_del(struct prestera_port *port, + const unsigned char *mac, u16 vid) +{ + if (prestera_port_is_lag_member(port)) + return prestera_hw_lag_fdb_del(port->sw, prestera_port_lag_id(port), + mac, vid); + else + return prestera_hw_fdb_del(port, mac, vid); +} + +static int prestera_fdb_flush_port_vlan(struct prestera_port *port, u16 vid, + u32 mode) +{ + if (prestera_port_is_lag_member(port)) + return prestera_hw_fdb_flush_lag_vlan(port->sw, prestera_port_lag_id(port), + vid, mode); + else + return prestera_hw_fdb_flush_port_vlan(port, vid, mode); +} + +static int prestera_fdb_flush_port(struct prestera_port *port, u32 mode) +{ + if (prestera_port_is_lag_member(port)) + return prestera_hw_fdb_flush_lag(port->sw, prestera_port_lag_id(port), + mode); + else + return prestera_hw_fdb_flush_port(port, mode); +} + static void prestera_port_vlan_bridge_leave(struct prestera_port_vlan *port_vlan) { @@ -199,11 +238,11 @@ prestera_port_vlan_bridge_leave(struct prestera_port_vlan *port_vlan) last_port = port_count == 1; if (last_vlan) - prestera_hw_fdb_flush_port(port, fdb_flush_mode); + prestera_fdb_flush_port(port, fdb_flush_mode); else if (last_port) prestera_hw_fdb_flush_vlan(port->sw, vid, fdb_flush_mode); else - prestera_hw_fdb_flush_port_vlan(port, vid, fdb_flush_mode); + prestera_fdb_flush_port_vlan(port, vid, fdb_flush_mode); list_del(&port_vlan->br_vlan_head); prestera_bridge_vlan_put(br_vlan); @@ -312,11 +351,29 @@ __prestera_bridge_port_by_dev(struct prestera_bridge *bridge, return NULL; } +static int prestera_match_upper_bridge_dev(struct net_device *dev, + struct netdev_nested_priv *priv) +{ + if (netif_is_bridge_master(dev)) + priv->data = dev; + + return 0; +} + +static struct net_device *prestera_get_upper_bridge_dev(struct net_device *dev) +{ + struct netdev_nested_priv priv = { }; + + netdev_walk_all_upper_dev_rcu(dev, prestera_match_upper_bridge_dev, + &priv); + return priv.data; +} + static struct prestera_bridge_port * prestera_bridge_port_by_dev(struct prestera_switchdev *swdev, struct net_device *dev) { - struct net_device *br_dev = netdev_master_upper_dev_get(dev); + struct net_device *br_dev = prestera_get_upper_bridge_dev(dev); struct prestera_bridge *bridge; if (!br_dev) @@ -404,7 +461,8 @@ prestera_bridge_1d_port_join(struct prestera_bridge_port *br_port) if (err) return err; - err = prestera_hw_port_flood_set(port, br_port->flags & BR_FLOOD); + err = prestera_hw_port_flood_set(port, BR_FLOOD | BR_MCAST_FLOOD, + br_port->flags); if (err) goto err_port_flood_set; @@ -415,24 +473,23 @@ prestera_bridge_1d_port_join(struct prestera_bridge_port *br_port) return 0; err_port_learning_set: - prestera_hw_port_flood_set(port, false); err_port_flood_set: prestera_hw_bridge_port_delete(port, bridge->bridge_id); return err; } -static int prestera_port_bridge_join(struct prestera_port *port, - struct net_device *upper) +int prestera_bridge_port_join(struct net_device *br_dev, + struct prestera_port *port) { struct prestera_switchdev *swdev = port->sw->swdev; struct prestera_bridge_port *br_port; struct prestera_bridge *bridge; int err; - bridge = prestera_bridge_by_dev(swdev, upper); + bridge = prestera_bridge_by_dev(swdev, br_dev); if (!bridge) { - bridge = prestera_bridge_create(swdev, upper); + bridge = prestera_bridge_create(swdev, br_dev); if (IS_ERR(bridge)) return PTR_ERR(bridge); } @@ -505,14 +562,14 @@ static int prestera_port_vid_stp_set(struct prestera_port *port, u16 vid, return prestera_hw_vlan_port_stp_set(port, vid, hw_state); } -static void prestera_port_bridge_leave(struct prestera_port *port, - struct net_device *upper) +void prestera_bridge_port_leave(struct net_device *br_dev, + struct prestera_port *port) { struct prestera_switchdev *swdev = port->sw->swdev; struct prestera_bridge_port *br_port; struct prestera_bridge *bridge; - bridge = prestera_bridge_by_dev(swdev, upper); + bridge = prestera_bridge_by_dev(swdev, br_dev); if (!bridge) return; @@ -528,57 +585,11 @@ static void prestera_port_bridge_leave(struct prestera_port *port, prestera_bridge_1d_port_leave(br_port); prestera_hw_port_learning_set(port, false); - prestera_hw_port_flood_set(port, false); + prestera_hw_port_flood_set(port, BR_FLOOD | BR_MCAST_FLOOD, 0); prestera_port_vid_stp_set(port, PRESTERA_VID_ALL, BR_STATE_FORWARDING); prestera_bridge_port_put(br_port); } -int prestera_bridge_port_event(struct net_device *dev, unsigned long event, - void *ptr) -{ - struct netdev_notifier_changeupper_info *info = ptr; - struct netlink_ext_ack *extack; - struct prestera_port *port; - struct net_device *upper; - int err; - - extack = netdev_notifier_info_to_extack(&info->info); - port = netdev_priv(dev); - upper = info->upper_dev; - - switch (event) { - case NETDEV_PRECHANGEUPPER: - if (!netif_is_bridge_master(upper)) { - NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type"); - return -EINVAL; - } - - if (!info->linking) - break; - - if (netdev_has_any_upper_dev(upper)) { - NL_SET_ERR_MSG_MOD(extack, "Upper device is already enslaved"); - return -EINVAL; - } - break; - - case NETDEV_CHANGEUPPER: - if (!netif_is_bridge_master(upper)) - break; - - if (info->linking) { - err = prestera_port_bridge_join(port, upper); - if (err) - return err; - } else { - prestera_port_bridge_leave(port, upper); - } - break; - } - - return 0; -} - static int prestera_port_attr_br_flags_set(struct prestera_port *port, struct net_device *dev, struct switchdev_brport_flags flags) @@ -590,11 +601,9 @@ static int prestera_port_attr_br_flags_set(struct prestera_port *port, if (!br_port) return 0; - if (flags.mask & BR_FLOOD) { - err = prestera_hw_port_flood_set(port, flags.val & BR_FLOOD); - if (err) - return err; - } + err = prestera_hw_port_flood_set(port, flags.mask, flags.val); + if (err) + return err; if (flags.mask & BR_LEARNING) { err = prestera_hw_port_learning_set(port, @@ -699,7 +708,7 @@ err_port_stp_set: return err; } -static int prestera_port_obj_attr_set(struct net_device *dev, +static int prestera_port_obj_attr_set(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { @@ -771,9 +780,9 @@ static int prestera_port_fdb_set(struct prestera_port *port, vid = bridge->bridge_id; if (adding) - err = prestera_hw_fdb_add(port, fdb_info->addr, vid, false); + err = prestera_fdb_add(port, fdb_info->addr, vid, false); else - err = prestera_hw_fdb_del(port, fdb_info->addr, vid); + err = prestera_fdb_del(port, fdb_info->addr, vid); return err; } @@ -901,7 +910,8 @@ prestera_port_vlan_bridge_join(struct prestera_port_vlan *port_vlan, if (port_vlan->br_port) return 0; - err = prestera_hw_port_flood_set(port, br_port->flags & BR_FLOOD); + err = prestera_hw_port_flood_set(port, BR_FLOOD | BR_MCAST_FLOOD, + br_port->flags); if (err) return err; @@ -1009,15 +1019,15 @@ static int prestera_port_vlans_add(struct prestera_port *port, { bool flag_untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; bool flag_pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; - struct net_device *dev = vlan->obj.orig_dev; + struct net_device *orig_dev = vlan->obj.orig_dev; struct prestera_bridge_port *br_port; struct prestera_switch *sw = port->sw; struct prestera_bridge *bridge; - if (netif_is_bridge_master(dev)) + if (netif_is_bridge_master(orig_dev)) return 0; - br_port = prestera_bridge_port_by_dev(sw->swdev, dev); + br_port = prestera_bridge_port_by_dev(sw->swdev, port->dev); if (WARN_ON(!br_port)) return -EINVAL; @@ -1030,7 +1040,7 @@ static int prestera_port_vlans_add(struct prestera_port *port, flag_pvid, extack); } -static int prestera_port_obj_add(struct net_device *dev, +static int prestera_port_obj_add(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { @@ -1049,14 +1059,14 @@ static int prestera_port_obj_add(struct net_device *dev, static int prestera_port_vlans_del(struct prestera_port *port, const struct switchdev_obj_port_vlan *vlan) { - struct net_device *dev = vlan->obj.orig_dev; + struct net_device *orig_dev = vlan->obj.orig_dev; struct prestera_bridge_port *br_port; struct prestera_switch *sw = port->sw; - if (netif_is_bridge_master(dev)) + if (netif_is_bridge_master(orig_dev)) return -EOPNOTSUPP; - br_port = prestera_bridge_port_by_dev(sw->swdev, dev); + br_port = prestera_bridge_port_by_dev(sw->swdev, port->dev); if (WARN_ON(!br_port)) return -EINVAL; @@ -1068,7 +1078,7 @@ static int prestera_port_vlans_del(struct prestera_port *port, return 0; } -static int prestera_port_obj_del(struct net_device *dev, +static int prestera_port_obj_del(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj) { struct prestera_port *port = netdev_priv(dev); @@ -1114,10 +1124,26 @@ static void prestera_fdb_event(struct prestera_switch *sw, struct prestera_event *evt, void *arg) { struct switchdev_notifier_fdb_info info; + struct net_device *dev = NULL; struct prestera_port *port; + struct prestera_lag *lag; - port = prestera_find_port(sw, evt->fdb_evt.port_id); - if (!port) + switch (evt->fdb_evt.type) { + case PRESTERA_FDB_ENTRY_TYPE_REG_PORT: + port = prestera_find_port(sw, evt->fdb_evt.dest.port_id); + if (port) + dev = port->dev; + break; + case PRESTERA_FDB_ENTRY_TYPE_LAG: + lag = prestera_lag_by_id(sw, evt->fdb_evt.dest.lag_id); + if (lag) + dev = lag->dev; + break; + default: + return; + } + + if (!dev) return; info.addr = evt->fdb_evt.data.mac; @@ -1129,11 +1155,11 @@ static void prestera_fdb_event(struct prestera_switch *sw, switch (evt->id) { case PRESTERA_FDB_EVENT_LEARNED: call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE, - port->dev, &info.info, NULL); + dev, &info.info, NULL); break; case PRESTERA_FDB_EVENT_AGED: call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, - port->dev, &info.info, NULL); + dev, &info.info, NULL); break; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h index 606e21d2355b..a91bc35d235f 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.h @@ -7,7 +7,10 @@ int prestera_switchdev_init(struct prestera_switch *sw); void prestera_switchdev_fini(struct prestera_switch *sw); -int prestera_bridge_port_event(struct net_device *dev, unsigned long event, - void *ptr); +int prestera_bridge_port_join(struct net_device *br_dev, + struct prestera_port *port); + +void prestera_bridge_port_leave(struct net_device *br_dev, + struct prestera_port *port); #endif /* _PRESTERA_SWITCHDEV_H_ */ diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index e967867828d8..9b48ae4bac39 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -1528,6 +1528,7 @@ static int pxa168_eth_remove(struct platform_device *pdev) struct net_device *dev = platform_get_drvdata(pdev); struct pxa168_eth_private *pep = netdev_priv(dev); + cancel_work_sync(&pep->tx_timeout_task); if (pep->htpr) { dma_free_coherent(pep->dev->dev.parent, HASH_ADDR_TABLE_SIZE, pep->htpr, pep->htpr_dma); @@ -1539,7 +1540,6 @@ static int pxa168_eth_remove(struct platform_device *pdev) clk_disable_unprepare(pep->clk); mdiobus_unregister(pep->smi_bus); mdiobus_free(pep->smi_bus); - cancel_work_sync(&pep->tx_timeout_task); unregister_netdev(dev); free_netdev(dev); return 0; diff --git a/drivers/net/ethernet/marvell/skge.h b/drivers/net/ethernet/marvell/skge.h index 6928abcec0a3..f72217348eb4 100644 --- a/drivers/net/ethernet/marvell/skge.h +++ b/drivers/net/ethernet/marvell/skge.h @@ -263,7 +263,7 @@ enum { CHIP_ID_YUKON_LP = 0xb2, /* Chip ID for YUKON-LP */ CHIP_ID_YUKON_XL = 0xb3, /* Chip ID for YUKON-2 XL */ CHIP_ID_YUKON_EC = 0xb6, /* Chip ID for YUKON-2 EC */ - CHIP_ID_YUKON_FE = 0xb7, /* Chip ID for YUKON-2 FE */ + CHIP_ID_YUKON_FE = 0xb7, /* Chip ID for YUKON-2 FE */ CHIP_REV_YU_LITE_A1 = 3, /* Chip Rev. for YUKON-Lite A1,A2 */ CHIP_REV_YU_LITE_A3 = 7, /* Chip Rev. for YUKON-Lite A3 */ diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 222c32367b2c..8b8bff59c8fe 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -471,7 +471,7 @@ static void sky2_phy_init(struct sky2_hw *hw, unsigned port) adv |= fiber_fc_adv[sky2->flow_mode]; } else { reg |= GM_GPCR_AU_FCT_DIS; - reg |= gm_fc_disable[sky2->flow_mode]; + reg |= gm_fc_disable[sky2->flow_mode]; /* Forward pause packets to GMAC? */ if (sky2->flow_mode & FC_RX) @@ -1656,16 +1656,16 @@ static void sky2_hw_up(struct sky2_port *sky2) tx_init(sky2); /* - * On dual port PCI-X card, there is an problem where status + * On dual port PCI-X card, there is an problem where status * can be received out of order due to split transactions */ if (otherdev && netif_running(otherdev) && - (cap = pci_find_capability(hw->pdev, PCI_CAP_ID_PCIX))) { - u16 cmd; + (cap = pci_find_capability(hw->pdev, PCI_CAP_ID_PCIX))) { + u16 cmd; cmd = sky2_pci_read16(hw, cap + PCI_X_CMD); - cmd &= ~PCI_X_CMD_MAX_SPLIT; - sky2_pci_write16(hw, cap + PCI_X_CMD, cmd); + cmd &= ~PCI_X_CMD_MAX_SPLIT; + sky2_pci_write16(hw, cap + PCI_X_CMD, cmd); } sky2_mac_init(hw, port); @@ -1836,8 +1836,8 @@ static netdev_tx_t sky2_xmit_frame(struct sk_buff *skb, u16 mss; u8 ctrl; - if (unlikely(tx_avail(sky2) < tx_le_req(skb))) - return NETDEV_TX_BUSY; + if (unlikely(tx_avail(sky2) < tx_le_req(skb))) + return NETDEV_TX_BUSY; len = skb_headlen(skb); mapping = dma_map_single(&hw->pdev->dev, skb->data, len, @@ -1866,9 +1866,9 @@ static netdev_tx_t sky2_xmit_frame(struct sk_buff *skb, if (!(hw->flags & SKY2_HW_NEW_LE)) mss += ETH_HLEN + ip_hdrlen(skb) + tcp_hdrlen(skb); - if (mss != sky2->tx_last_mss) { + if (mss != sky2->tx_last_mss) { le = get_tx_le(sky2, &slot); - le->addr = cpu_to_le32(mss); + le->addr = cpu_to_le32(mss); if (hw->flags & SKY2_HW_NEW_LE) le->opcode = OP_MSS | HW_OWNER; @@ -1895,8 +1895,8 @@ static netdev_tx_t sky2_xmit_frame(struct sk_buff *skb, /* Handle TCP checksum offload */ if (skb->ip_summed == CHECKSUM_PARTIAL) { /* On Yukon EX (some versions) encoding change. */ - if (hw->flags & SKY2_HW_AUTO_TX_SUM) - ctrl |= CALSUM; /* auto checksum */ + if (hw->flags & SKY2_HW_AUTO_TX_SUM) + ctrl |= CALSUM; /* auto checksum */ else { const unsigned offset = skb_transport_offset(skb); u32 tcpsum; @@ -2503,7 +2503,7 @@ static void skb_put_frags(struct sk_buff *skb, unsigned int hdr_space, if (length == 0) { /* don't need this page */ - __skb_frag_unref(frag); + __skb_frag_unref(frag, false); --skb_shinfo(skb)->nr_frags; } else { size = min(length, (unsigned) PAGE_SIZE); @@ -2557,7 +2557,7 @@ nobuf: static struct sk_buff *sky2_receive(struct net_device *dev, u16 length, u32 status) { - struct sky2_port *sky2 = netdev_priv(dev); + struct sky2_port *sky2 = netdev_priv(dev); struct rx_ring_info *re = sky2->rx_ring + sky2->rx_next; struct sk_buff *skb = NULL; u16 count = (status & GMR_FS_LEN) >> 16; @@ -5063,11 +5063,11 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!disable_msi && pci_enable_msi(pdev) == 0) { err = sky2_test_msi(hw); if (err) { - pci_disable_msi(pdev); + pci_disable_msi(pdev); if (err != -EOPNOTSUPP) goto err_out_free_netdev; } - } + } netif_napi_add(dev, &hw->napi, sky2_poll, NAPI_WEIGHT); diff --git a/drivers/net/ethernet/marvell/sky2.h b/drivers/net/ethernet/marvell/sky2.h index b2dddd8a246c..ddec1627f1a7 100644 --- a/drivers/net/ethernet/marvell/sky2.h +++ b/drivers/net/ethernet/marvell/sky2.h @@ -538,8 +538,8 @@ enum { CHIP_ID_YUKON_EC_U = 0xb4, /* YUKON-2 EC Ultra */ CHIP_ID_YUKON_EX = 0xb5, /* YUKON-2 Extreme */ CHIP_ID_YUKON_EC = 0xb6, /* YUKON-2 EC */ - CHIP_ID_YUKON_FE = 0xb7, /* YUKON-2 FE */ - CHIP_ID_YUKON_FE_P = 0xb8, /* YUKON-2 FE+ */ + CHIP_ID_YUKON_FE = 0xb7, /* YUKON-2 FE */ + CHIP_ID_YUKON_FE_P = 0xb8, /* YUKON-2 FE+ */ CHIP_ID_YUKON_SUPR = 0xb9, /* YUKON-2 Supreme */ CHIP_ID_YUKON_UL_2 = 0xba, /* YUKON-2 Ultra 2 */ CHIP_ID_YUKON_OPT = 0xbc, /* YUKON-2 Optima */ @@ -2262,8 +2262,8 @@ struct sky2_port { #define SKY2_FLAG_AUTO_SPEED 0x0002 #define SKY2_FLAG_AUTO_PAUSE 0x0004 - enum flow_control flow_mode; - enum flow_control flow_status; + enum flow_control flow_mode; + enum flow_control flow_status; #ifdef CONFIG_SKY2_DEBUG struct dentry *debugfs; diff --git a/drivers/net/ethernet/mellanox/Kconfig b/drivers/net/ethernet/mellanox/Kconfig index ff6613a5cdd3..b4f66eb9ddb9 100644 --- a/drivers/net/ethernet/mellanox/Kconfig +++ b/drivers/net/ethernet/mellanox/Kconfig @@ -22,5 +22,6 @@ source "drivers/net/ethernet/mellanox/mlx4/Kconfig" source "drivers/net/ethernet/mellanox/mlx5/core/Kconfig" source "drivers/net/ethernet/mellanox/mlxsw/Kconfig" source "drivers/net/ethernet/mellanox/mlxfw/Kconfig" +source "drivers/net/ethernet/mellanox/mlxbf_gige/Kconfig" endif # NET_VENDOR_MELLANOX diff --git a/drivers/net/ethernet/mellanox/Makefile b/drivers/net/ethernet/mellanox/Makefile index 79773ac331ee..d4b5f547a727 100644 --- a/drivers/net/ethernet/mellanox/Makefile +++ b/drivers/net/ethernet/mellanox/Makefile @@ -7,3 +7,4 @@ obj-$(CONFIG_MLX4_CORE) += mlx4/ obj-$(CONFIG_MLX5_CORE) += mlx5/core/ obj-$(CONFIG_MLXSW_CORE) += mlxsw/ obj-$(CONFIG_MLXFW) += mlxfw/ +obj-$(CONFIG_MLXBF_GIGE) += mlxbf_gige/ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index e35e4d7ef4d1..442991d91c15 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -526,7 +526,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, fail: while (nr > 0) { nr--; - __skb_frag_unref(skb_shinfo(skb)->frags + nr); + __skb_frag_unref(skb_shinfo(skb)->frags + nr, false); } return 0; } @@ -679,9 +679,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud ring = priv->rx_ring[cq_ring]; - /* Protect accesses to: ring->xdp_prog, priv->mac_hash list */ - rcu_read_lock(); - xdp_prog = rcu_dereference(ring->xdp_prog); + xdp_prog = rcu_dereference_bh(ring->xdp_prog); xdp_init_buff(&xdp, priv->frag_info[0].frag_stride, &ring->xdp_rxq); doorbell_pending = false; @@ -744,7 +742,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud /* Drop the packet, since HW loopback-ed it */ mac_hash = ethh->h_source[MLX4_EN_MAC_HASH_IDX]; bucket = &priv->mac_hash[mac_hash]; - hlist_for_each_entry_rcu(entry, bucket, hlist) { + hlist_for_each_entry_rcu_bh(entry, bucket, hlist) { if (ether_addr_equal_64bits(entry->mac, ethh->h_source)) goto next; @@ -899,8 +897,6 @@ next: break; } - rcu_read_unlock(); - if (likely(polled)) { if (doorbell_pending) { priv->tx_cq[TX_XDP][cq_ring]->xdp_busy = true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 461a43f338e6..e1a5a79e27c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -12,7 +12,6 @@ config MLX5_CORE depends on MLXFW || !MLXFW depends on PTP_1588_CLOCK || !PTP_1588_CLOCK depends on PCI_HYPERV_INTERFACE || !PCI_HYPERV_INTERFACE - default n help Core driver for low level functionality of the ConnectX-4 and Connect-IB cards by Mellanox Technologies. @@ -36,7 +35,6 @@ config MLX5_CORE_EN depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE select PAGE_POOL select DIMLIB - default n help Ethernet support in Mellanox Technologies ConnectX-4 NIC. @@ -79,6 +77,16 @@ config MLX5_ESWITCH Legacy SRIOV mode (L2 mac vlan steering based). Switchdev mode (eswitch offloads). +config MLX5_BRIDGE + bool + depends on MLX5_ESWITCH && BRIDGE + default y + help + mlx5 ConnectX offloads support for Ethernet Bridging (BRIDGE). + Enable adding representors of mlx5 uplink and VF ports to Bridge and + offloading rules for traffic between such ports. Supports VLANs (trunk and + access modes). + config MLX5_CLS_ACT bool "MLX5 TC classifier action support" depends on MLX5_ESWITCH && NET_CLS_ACT @@ -131,7 +139,6 @@ config MLX5_CORE_EN_DCB config MLX5_CORE_IPOIB bool "Mellanox 5th generation network adapters (connectX series) IPoIB offloads support" depends on MLX5_CORE_EN - default n help MLX5 IPoIB offloads & acceleration support. @@ -139,7 +146,6 @@ config MLX5_FPGA_IPSEC bool "Mellanox Technologies IPsec Innova support" depends on MLX5_CORE depends on MLX5_FPGA - default n help Build IPsec support for the Innova family of network cards by Mellanox Technologies. Innova network cards are comprised of a ConnectX chip @@ -153,7 +159,6 @@ config MLX5_IPSEC depends on XFRM_OFFLOAD depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD select MLX5_ACCEL - default n help Build IPsec support for the Connect-X family of network cards by Mellanox Technologies. @@ -166,7 +171,6 @@ config MLX5_EN_IPSEC depends on XFRM_OFFLOAD depends on INET_ESP_OFFLOAD || INET6_ESP_OFFLOAD depends on MLX5_FPGA_IPSEC || MLX5_IPSEC - default n help Build support for IPsec cryptography-offload acceleration in the NIC. Note: Support for hardware with this capability needs to be selected @@ -179,7 +183,6 @@ config MLX5_FPGA_TLS depends on MLX5_CORE_EN depends on MLX5_FPGA select MLX5_EN_TLS - default n help Build TLS support for the Innova family of network cards by Mellanox Technologies. Innova network cards are comprised of a ConnectX chip @@ -194,7 +197,6 @@ config MLX5_TLS depends on MLX5_CORE_EN select MLX5_ACCEL select MLX5_EN_TLS - default n help Build TLS support for the Connect-X family of network cards by Mellanox Technologies. @@ -217,7 +219,6 @@ config MLX5_SW_STEERING config MLX5_SF bool "Mellanox Technologies subfunction device support using auxiliary device" depends on MLX5_CORE && MLX5_CORE_EN - default n help Build support for subfuction device in the NIC. A Mellanox subfunction device can support RDMA, netdevice and vdpa device. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index a1223e904190..b5072a3a2585 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -14,7 +14,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o alloc.o port.o mr.o pd.o \ transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \ - fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ + fs_counters.o fs_ft_pool.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o lib/pci_vsc.o lib/dm.o diag/fs_tracepoint.o \ diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \ fw_reset.o qos.o @@ -56,6 +56,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += esw/acl/helper.o \ esw/acl/ingress_lgcy.o esw/acl/ingress_ofld.o \ esw/devlink_port.o esw/vporttbl.o mlx5_core-$(CONFIG_MLX5_TC_SAMPLE) += esw/sample.o +mlx5_core-$(CONFIG_MLX5_BRIDGE) += esw/bridge.o en/rep/bridge.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 44c458443428..d791d351b489 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -63,6 +63,11 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, err = devlink_info_version_running_put(req, "fw.version", version_str); if (err) return err; + err = devlink_info_version_running_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW, + version_str); + if (err) + return err; /* no pending version, return running (stored) version */ if (stored_fw == 0) @@ -74,8 +79,9 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, err = devlink_info_version_stored_put(req, "fw.version", version_str); if (err) return err; - - return 0; + return devlink_info_version_stored_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW, + version_str); } static int mlx5_devlink_reload_fw_activate(struct devlink *devlink, struct netlink_ext_ack *extack) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b636d63358d2..b1b51bbba054 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -974,7 +974,6 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk, int node, struct mlx5e_rq *rq); int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time); -void mlx5e_deactivate_rq(struct mlx5e_rq *rq); void mlx5e_close_rq(struct mlx5e_rq *rq); int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param); void mlx5e_destroy_rq(struct mlx5e_rq *rq); @@ -1163,6 +1162,13 @@ mlx5e_calc_max_nch(struct mlx5e_priv *priv, const struct mlx5e_profile *profile) return priv->netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1); } +static inline bool +mlx5e_tx_mpwqe_supported(struct mlx5_core_dev *mdev) +{ + return !is_kdump_kernel() && + MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe); +} + int mlx5e_priv_init(struct mlx5e_priv *priv, struct net_device *netdev, struct mlx5_core_dev *mdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index f410c1268422..150c8e82c738 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -201,7 +201,7 @@ int mlx5e_validate_params(struct mlx5_core_dev *mdev, struct mlx5e_params *param static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode) { - struct dim_cq_moder moder; + struct dim_cq_moder moder = {}; moder.cq_period_mode = cq_period_mode; moder.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS; @@ -214,7 +214,7 @@ static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode) static struct dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode) { - struct dim_cq_moder moder; + struct dim_cq_moder moder = {}; moder.cq_period_mode = cq_period_mode; moder.pkts = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS; @@ -614,7 +614,7 @@ static u8 mlx5e_build_icosq_log_wq_sz(struct mlx5e_params *params, static u8 mlx5e_build_async_icosq_log_wq_sz(struct mlx5_core_dev *mdev) { - if (mlx5_accel_is_ktls_rx(mdev)) + if (mlx5e_accel_is_ktls_rx(mdev)) return MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE; return MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE; @@ -643,7 +643,7 @@ static void mlx5e_build_async_icosq_param(struct mlx5_core_dev *mdev, mlx5e_build_sq_param_common(mdev, param); param->stop_room = mlx5e_stop_room_for_wqe(1); /* for XSK NOP */ - param->is_tls = mlx5_accel_is_ktls_rx(mdev); + param->is_tls = mlx5e_accel_is_ktls_rx(mdev); if (param->is_tls) param->stop_room += mlx5e_stop_room_for_wqe(1); /* for TLS RX resync NOP */ MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(mdev, reg_umr_sq)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c new file mode 100644 index 000000000000..3c0032c9647c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -0,0 +1,427 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021 Mellanox Technologies. */ + +#include +#include +#include +#include +#include "bridge.h" +#include "esw/bridge.h" +#include "en_rep.h" + +#define MLX5_ESW_BRIDGE_UPDATE_INTERVAL 1000 + +struct mlx5_bridge_switchdev_fdb_work { + struct work_struct work; + struct switchdev_notifier_fdb_info fdb_info; + struct net_device *dev; + bool add; +}; + +static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr) +{ + struct mlx5_esw_bridge_offloads *br_offloads = container_of(nb, + struct mlx5_esw_bridge_offloads, + netdev_nb); + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + struct netlink_ext_ack *extack; + struct mlx5e_rep_priv *rpriv; + struct mlx5_eswitch *esw; + struct mlx5_vport *vport; + struct net_device *upper; + struct mlx5e_priv *priv; + u16 vport_num; + + if (!mlx5e_eswitch_rep(dev)) + return 0; + + upper = info->upper_dev; + if (!netif_is_bridge_master(upper)) + return 0; + + esw = br_offloads->esw; + priv = netdev_priv(dev); + if (esw != priv->mdev->priv.eswitch) + return 0; + + rpriv = priv->ppriv; + vport_num = rpriv->rep->vport; + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + extack = netdev_notifier_info_to_extack(&info->info); + + return info->linking ? + mlx5_esw_bridge_vport_link(upper->ifindex, br_offloads, vport, extack) : + mlx5_esw_bridge_vport_unlink(upper->ifindex, br_offloads, vport, extack); +} + +static int mlx5_esw_bridge_switchdev_port_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + int err = 0; + + switch (event) { + case NETDEV_PRECHANGEUPPER: + break; + + case NETDEV_CHANGEUPPER: + err = mlx5_esw_bridge_port_changeupper(nb, ptr); + break; + } + + return notifier_from_errno(err); +} + +static int mlx5_esw_bridge_port_obj_add(struct net_device *dev, + const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) +{ + const struct switchdev_obj_port_vlan *vlan; + struct mlx5e_rep_priv *rpriv; + struct mlx5_eswitch *esw; + struct mlx5_vport *vport; + struct mlx5e_priv *priv; + u16 vport_num; + int err = 0; + + priv = netdev_priv(dev); + rpriv = priv->ppriv; + vport_num = rpriv->rep->vport; + esw = priv->mdev->priv.eswitch; + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + err = mlx5_esw_bridge_port_vlan_add(vlan->vid, vlan->flags, esw, vport, extack); + break; + default: + return -EOPNOTSUPP; + } + return err; +} + +static int mlx5_esw_bridge_port_obj_del(struct net_device *dev, + const void *ctx, + const struct switchdev_obj *obj) +{ + const struct switchdev_obj_port_vlan *vlan; + struct mlx5e_rep_priv *rpriv; + struct mlx5_eswitch *esw; + struct mlx5_vport *vport; + struct mlx5e_priv *priv; + u16 vport_num; + + priv = netdev_priv(dev); + rpriv = priv->ppriv; + vport_num = rpriv->rep->vport; + esw = priv->mdev->priv.eswitch; + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + mlx5_esw_bridge_port_vlan_del(vlan->vid, esw, vport); + break; + default: + return -EOPNOTSUPP; + } + return 0; +} + +static int mlx5_esw_bridge_port_obj_attr_set(struct net_device *dev, + const void *ctx, + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) +{ + struct mlx5e_rep_priv *rpriv; + struct mlx5_eswitch *esw; + struct mlx5_vport *vport; + struct mlx5e_priv *priv; + u16 vport_num; + int err = 0; + + priv = netdev_priv(dev); + rpriv = priv->ppriv; + vport_num = rpriv->rep->vport; + esw = priv->mdev->priv.eswitch; + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + return PTR_ERR(vport); + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: + if (attr->u.brport_flags.mask & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD)) { + NL_SET_ERR_MSG_MOD(extack, "Flag is not supported"); + err = -EINVAL; + } + break; + case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: + break; + case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: + err = mlx5_esw_bridge_ageing_time_set(attr->u.ageing_time, esw, vport); + break; + case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: + err = mlx5_esw_bridge_vlan_filtering_set(attr->u.vlan_filtering, esw, vport); + break; + default: + err = -EOPNOTSUPP; + } + + return err; +} + +static int mlx5_esw_bridge_event_blocking(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + int err; + + switch (event) { + case SWITCHDEV_PORT_OBJ_ADD: + err = switchdev_handle_port_obj_add(dev, ptr, + mlx5e_eswitch_rep, + mlx5_esw_bridge_port_obj_add); + break; + case SWITCHDEV_PORT_OBJ_DEL: + err = switchdev_handle_port_obj_del(dev, ptr, + mlx5e_eswitch_rep, + mlx5_esw_bridge_port_obj_del); + break; + case SWITCHDEV_PORT_ATTR_SET: + err = switchdev_handle_port_attr_set(dev, ptr, + mlx5e_eswitch_rep, + mlx5_esw_bridge_port_obj_attr_set); + break; + default: + err = 0; + } + + return notifier_from_errno(err); +} + +static void +mlx5_esw_bridge_cleanup_switchdev_fdb_work(struct mlx5_bridge_switchdev_fdb_work *fdb_work) +{ + dev_put(fdb_work->dev); + kfree(fdb_work->fdb_info.addr); + kfree(fdb_work); +} + +static void mlx5_esw_bridge_switchdev_fdb_event_work(struct work_struct *work) +{ + struct mlx5_bridge_switchdev_fdb_work *fdb_work = + container_of(work, struct mlx5_bridge_switchdev_fdb_work, work); + struct switchdev_notifier_fdb_info *fdb_info = + &fdb_work->fdb_info; + struct net_device *dev = fdb_work->dev; + struct mlx5e_rep_priv *rpriv; + struct mlx5_eswitch *esw; + struct mlx5_vport *vport; + struct mlx5e_priv *priv; + u16 vport_num; + + rtnl_lock(); + + priv = netdev_priv(dev); + rpriv = priv->ppriv; + vport_num = rpriv->rep->vport; + esw = priv->mdev->priv.eswitch; + vport = mlx5_eswitch_get_vport(esw, vport_num); + if (IS_ERR(vport)) + goto out; + + if (fdb_work->add) + mlx5_esw_bridge_fdb_create(dev, esw, vport, fdb_info); + else + mlx5_esw_bridge_fdb_remove(dev, esw, vport, fdb_info); + +out: + rtnl_unlock(); + mlx5_esw_bridge_cleanup_switchdev_fdb_work(fdb_work); +} + +static struct mlx5_bridge_switchdev_fdb_work * +mlx5_esw_bridge_init_switchdev_fdb_work(struct net_device *dev, bool add, + struct switchdev_notifier_fdb_info *fdb_info) +{ + struct mlx5_bridge_switchdev_fdb_work *work; + u8 *addr; + + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return ERR_PTR(-ENOMEM); + + INIT_WORK(&work->work, mlx5_esw_bridge_switchdev_fdb_event_work); + memcpy(&work->fdb_info, fdb_info, sizeof(work->fdb_info)); + + addr = kzalloc(ETH_ALEN, GFP_ATOMIC); + if (!addr) { + kfree(work); + return ERR_PTR(-ENOMEM); + } + ether_addr_copy(addr, fdb_info->addr); + work->fdb_info.addr = addr; + + dev_hold(dev); + work->dev = dev; + work->add = add; + return work; +} + +static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct mlx5_esw_bridge_offloads *br_offloads = container_of(nb, + struct mlx5_esw_bridge_offloads, + nb); + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + struct switchdev_notifier_fdb_info *fdb_info; + struct mlx5_bridge_switchdev_fdb_work *work; + struct switchdev_notifier_info *info = ptr; + struct net_device *upper; + struct mlx5e_priv *priv; + + if (!mlx5e_eswitch_rep(dev)) + return NOTIFY_DONE; + priv = netdev_priv(dev); + if (priv->mdev->priv.eswitch != br_offloads->esw) + return NOTIFY_DONE; + + if (event == SWITCHDEV_PORT_ATTR_SET) { + int err = switchdev_handle_port_attr_set(dev, ptr, + mlx5e_eswitch_rep, + mlx5_esw_bridge_port_obj_attr_set); + return notifier_from_errno(err); + } + + upper = netdev_master_upper_dev_get_rcu(dev); + if (!upper) + return NOTIFY_DONE; + if (!netif_is_bridge_master(upper)) + return NOTIFY_DONE; + + switch (event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: + fdb_info = container_of(info, + struct switchdev_notifier_fdb_info, + info); + + work = mlx5_esw_bridge_init_switchdev_fdb_work(dev, + event == SWITCHDEV_FDB_ADD_TO_DEVICE, + fdb_info); + if (IS_ERR(work)) { + WARN_ONCE(1, "Failed to init switchdev work, err=%ld", + PTR_ERR(work)); + return notifier_from_errno(PTR_ERR(work)); + } + + queue_work(br_offloads->wq, &work->work); + break; + default: + break; + } + return NOTIFY_DONE; +} + +static void mlx5_esw_bridge_update_work(struct work_struct *work) +{ + struct mlx5_esw_bridge_offloads *br_offloads = container_of(work, + struct mlx5_esw_bridge_offloads, + update_work.work); + + rtnl_lock(); + mlx5_esw_bridge_update(br_offloads); + rtnl_unlock(); + + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + msecs_to_jiffies(MLX5_ESW_BRIDGE_UPDATE_INTERVAL)); +} + +void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) +{ + struct mlx5_esw_bridge_offloads *br_offloads; + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_eswitch *esw = + mdev->priv.eswitch; + int err; + + rtnl_lock(); + br_offloads = mlx5_esw_bridge_init(esw); + rtnl_unlock(); + if (IS_ERR(br_offloads)) { + esw_warn(mdev, "Failed to init esw bridge (err=%ld)\n", PTR_ERR(br_offloads)); + return; + } + + br_offloads->wq = alloc_ordered_workqueue("mlx5_bridge_wq", 0); + if (!br_offloads->wq) { + esw_warn(mdev, "Failed to allocate bridge offloads workqueue\n"); + goto err_alloc_wq; + } + INIT_DELAYED_WORK(&br_offloads->update_work, mlx5_esw_bridge_update_work); + queue_delayed_work(br_offloads->wq, &br_offloads->update_work, + msecs_to_jiffies(MLX5_ESW_BRIDGE_UPDATE_INTERVAL)); + + br_offloads->nb.notifier_call = mlx5_esw_bridge_switchdev_event; + err = register_switchdev_notifier(&br_offloads->nb); + if (err) { + esw_warn(mdev, "Failed to register switchdev notifier (err=%d)\n", err); + goto err_register_swdev; + } + + br_offloads->nb_blk.notifier_call = mlx5_esw_bridge_event_blocking; + err = register_switchdev_blocking_notifier(&br_offloads->nb_blk); + if (err) { + esw_warn(mdev, "Failed to register blocking switchdev notifier (err=%d)\n", err); + goto err_register_swdev_blk; + } + + br_offloads->netdev_nb.notifier_call = mlx5_esw_bridge_switchdev_port_event; + err = register_netdevice_notifier(&br_offloads->netdev_nb); + if (err) { + esw_warn(mdev, "Failed to register bridge offloads netdevice notifier (err=%d)\n", + err); + goto err_register_netdev; + } + return; + +err_register_netdev: + unregister_switchdev_blocking_notifier(&br_offloads->nb_blk); +err_register_swdev_blk: + unregister_switchdev_notifier(&br_offloads->nb); +err_register_swdev: + destroy_workqueue(br_offloads->wq); +err_alloc_wq: + mlx5_esw_bridge_cleanup(esw); +} + +void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) +{ + struct mlx5_esw_bridge_offloads *br_offloads; + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5_eswitch *esw = + mdev->priv.eswitch; + + br_offloads = esw->br_offloads; + if (!br_offloads) + return; + + unregister_netdevice_notifier(&br_offloads->netdev_nb); + unregister_switchdev_blocking_notifier(&br_offloads->nb_blk); + unregister_switchdev_notifier(&br_offloads->nb); + cancel_delayed_work(&br_offloads->update_work); + destroy_workqueue(br_offloads->wq); + rtnl_lock(); + mlx5_esw_bridge_cleanup(esw); + rtnl_unlock(); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.h new file mode 100644 index 000000000000..fbeb64242831 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#ifndef __MLX5_EN_REP_BRIDGE__ +#define __MLX5_EN_REP_BRIDGE__ + +#include "en.h" + +#if IS_ENABLED(CONFIG_MLX5_BRIDGE) + +void mlx5e_rep_bridge_init(struct mlx5e_priv *priv); +void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv); + +#else /* CONFIG_MLX5_BRIDGE */ + +static inline void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) {} +static inline void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) {} + +#endif /* CONFIG_MLX5_BRIDGE */ + +#endif /* __MLX5_EN_REP_BRIDGE__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index 85eaadc989df..059799e4f483 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -613,7 +613,7 @@ static bool mlx5e_restore_skb(struct sk_buff *skb, u32 chain, u32 reg_c1, struct mlx5e_tc_update_priv *tc_priv) { struct mlx5e_priv *priv = netdev_priv(skb->dev); - u32 tunnel_id = reg_c1 >> ESW_TUN_OFFSET; + u32 tunnel_id = (reg_c1 >> ESW_TUN_OFFSET) & TUNNEL_ID_MASK; if (chain) { struct mlx5_rep_uplink_priv *uplink_priv; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 5da5e5323a44..91e7a01e32be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -23,7 +23,7 @@ #include "en_tc.h" #include "en_rep.h" -#define MLX5_CT_ZONE_BITS (mlx5e_tc_attr_to_reg_mappings[ZONE_TO_REG].mlen * 8) +#define MLX5_CT_ZONE_BITS (mlx5e_tc_attr_to_reg_mappings[ZONE_TO_REG].mlen) #define MLX5_CT_ZONE_MASK GENMASK(MLX5_CT_ZONE_BITS - 1, 0) #define MLX5_CT_STATE_ESTABLISHED_BIT BIT(1) #define MLX5_CT_STATE_TRK_BIT BIT(2) @@ -32,11 +32,11 @@ #define MLX5_CT_STATE_RELATED_BIT BIT(5) #define MLX5_CT_STATE_INVALID_BIT BIT(6) -#define MLX5_FTE_ID_BITS (mlx5e_tc_attr_to_reg_mappings[FTEID_TO_REG].mlen * 8) +#define MLX5_FTE_ID_BITS (mlx5e_tc_attr_to_reg_mappings[FTEID_TO_REG].mlen) #define MLX5_FTE_ID_MAX GENMASK(MLX5_FTE_ID_BITS - 1, 0) #define MLX5_FTE_ID_MASK MLX5_FTE_ID_MAX -#define MLX5_CT_LABELS_BITS (mlx5e_tc_attr_to_reg_mappings[LABELS_TO_REG].mlen * 8) +#define MLX5_CT_LABELS_BITS (mlx5e_tc_attr_to_reg_mappings[LABELS_TO_REG].mlen) #define MLX5_CT_LABELS_MASK GENMASK(MLX5_CT_LABELS_BITS - 1, 0) #define ct_dbg(fmt, args...)\ @@ -150,6 +150,11 @@ struct mlx5_ct_entry { unsigned long flags; }; +static void +mlx5_tc_ct_entry_destroy_mod_hdr(struct mlx5_tc_ct_priv *ct_priv, + struct mlx5_flow_attr *attr, + struct mlx5e_mod_hdr_handle *mh); + static const struct rhashtable_params cts_ht_params = { .head_offset = offsetof(struct mlx5_ct_entry, node), .key_offset = offsetof(struct mlx5_ct_entry, cookie), @@ -458,8 +463,7 @@ mlx5_tc_ct_entry_del_rule(struct mlx5_tc_ct_priv *ct_priv, ct_dbg("Deleting ct entry rule in zone %d", entry->tuple.zone); mlx5_tc_rule_delete(netdev_priv(ct_priv->netdev), zone_rule->rule, attr); - mlx5e_mod_hdr_detach(ct_priv->dev, - ct_priv->mod_hdr_tbl, zone_rule->mh); + mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, zone_rule->mh); mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); kfree(attr); } @@ -686,15 +690,27 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv, if (err) goto err_mapping; - *mh = mlx5e_mod_hdr_attach(ct_priv->dev, - ct_priv->mod_hdr_tbl, - ct_priv->ns_type, - &mod_acts); - if (IS_ERR(*mh)) { - err = PTR_ERR(*mh); - goto err_mapping; + if (nat) { + attr->modify_hdr = mlx5_modify_header_alloc(ct_priv->dev, ct_priv->ns_type, + mod_acts.num_actions, + mod_acts.actions); + if (IS_ERR(attr->modify_hdr)) { + err = PTR_ERR(attr->modify_hdr); + goto err_mapping; + } + + *mh = NULL; + } else { + *mh = mlx5e_mod_hdr_attach(ct_priv->dev, + ct_priv->mod_hdr_tbl, + ct_priv->ns_type, + &mod_acts); + if (IS_ERR(*mh)) { + err = PTR_ERR(*mh); + goto err_mapping; + } + attr->modify_hdr = mlx5e_mod_hdr_get(*mh); } - attr->modify_hdr = mlx5e_mod_hdr_get(*mh); dealloc_mod_hdr_actions(&mod_acts); return 0; @@ -705,6 +721,17 @@ err_mapping: return err; } +static void +mlx5_tc_ct_entry_destroy_mod_hdr(struct mlx5_tc_ct_priv *ct_priv, + struct mlx5_flow_attr *attr, + struct mlx5e_mod_hdr_handle *mh) +{ + if (mh) + mlx5e_mod_hdr_detach(ct_priv->dev, ct_priv->mod_hdr_tbl, mh); + else + mlx5_modify_header_dealloc(ct_priv->dev, attr->modify_hdr); +} + static int mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, struct flow_rule *flow_rule, @@ -767,8 +794,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, return 0; err_rule: - mlx5e_mod_hdr_detach(ct_priv->dev, - ct_priv->mod_hdr_tbl, zone_rule->mh); + mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, zone_rule->mh); mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); err_mod_hdr: kfree(attr); @@ -918,7 +944,7 @@ mlx5_tc_ct_shared_counter_get(struct mlx5_tc_ct_priv *ct_priv, } if (rev_entry && refcount_inc_not_zero(&rev_entry->counter->refcount)) { - ct_dbg("Using shared counter entry=0x%p rev=0x%p\n", entry, rev_entry); + ct_dbg("Using shared counter entry=0x%p rev=0x%p", entry, rev_entry); shared_counter = rev_entry->counter; spin_unlock_bh(&ct_priv->ht_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 69e618d17071..644cf1641cde 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -33,15 +33,15 @@ struct mlx5_ct_attr { #define zone_to_reg_ct {\ .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_2,\ .moffset = 0,\ - .mlen = 2,\ + .mlen = 16,\ .soffset = MLX5_BYTE_OFF(fte_match_param,\ - misc_parameters_2.metadata_reg_c_2) + 2,\ + misc_parameters_2.metadata_reg_c_2),\ } #define ctstate_to_reg_ct {\ .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_2,\ - .moffset = 2,\ - .mlen = 2,\ + .moffset = 16,\ + .mlen = 16,\ .soffset = MLX5_BYTE_OFF(fte_match_param,\ misc_parameters_2.metadata_reg_c_2),\ } @@ -49,7 +49,7 @@ struct mlx5_ct_attr { #define mark_to_reg_ct {\ .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_3,\ .moffset = 0,\ - .mlen = 4,\ + .mlen = 32,\ .soffset = MLX5_BYTE_OFF(fte_match_param,\ misc_parameters_2.metadata_reg_c_3),\ } @@ -57,7 +57,7 @@ struct mlx5_ct_attr { #define labels_to_reg_ct {\ .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_4,\ .moffset = 0,\ - .mlen = 4,\ + .mlen = 32,\ .soffset = MLX5_BYTE_OFF(fte_match_param,\ misc_parameters_2.metadata_reg_c_4),\ } @@ -65,7 +65,7 @@ struct mlx5_ct_attr { #define fteid_to_reg_ct {\ .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_5,\ .moffset = 0,\ - .mlen = 4,\ + .mlen = 32,\ .soffset = MLX5_BYTE_OFF(fte_match_param,\ misc_parameters_2.metadata_reg_c_5),\ } @@ -73,20 +73,19 @@ struct mlx5_ct_attr { #define zone_restore_to_reg_ct {\ .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_1,\ .moffset = 0,\ - .mlen = (ESW_ZONE_ID_BITS / 8),\ + .mlen = ESW_ZONE_ID_BITS,\ .soffset = MLX5_BYTE_OFF(fte_match_param,\ - misc_parameters_2.metadata_reg_c_1) + 3,\ + misc_parameters_2.metadata_reg_c_1),\ } #define nic_zone_restore_to_reg_ct {\ .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_B,\ - .moffset = 2,\ - .mlen = (ESW_ZONE_ID_BITS / 8),\ + .moffset = 16,\ + .mlen = ESW_ZONE_ID_BITS,\ } #define REG_MAPPING_MLEN(reg) (mlx5e_tc_attr_to_reg_mappings[reg].mlen) #define REG_MAPPING_MOFFSET(reg) (mlx5e_tc_attr_to_reg_mappings[reg].moffset) -#define REG_MAPPING_SHIFT(reg) (REG_MAPPING_MOFFSET(reg) * 8) #if IS_ENABLED(CONFIG_MLX5_TC_CT) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 172e0474f2e6..8f79f04eccd6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -212,6 +212,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, { int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); const struct ip_tunnel_key *tun_key = &e->tun_info->key; + struct mlx5_pkt_reformat_params reformat_params; struct mlx5e_neigh m_neigh = {}; TC_TUN_ROUTE_ATTR_INIT(attr); int ipv4_encap_size; @@ -295,9 +296,12 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, */ goto release_neigh; } - e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv4_encap_size, encap_header, + + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = e->reformat_type; + reformat_params.size = ipv4_encap_size; + reformat_params.data = encap_header; + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { err = PTR_ERR(e->pkt_reformat); @@ -324,6 +328,7 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv, { int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); const struct ip_tunnel_key *tun_key = &e->tun_info->key; + struct mlx5_pkt_reformat_params reformat_params; TC_TUN_ROUTE_ATTR_INIT(attr); int ipv4_encap_size; char *encap_header; @@ -396,9 +401,12 @@ int mlx5e_tc_tun_update_header_ipv4(struct mlx5e_priv *priv, */ goto release_neigh; } - e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv4_encap_size, encap_header, + + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = e->reformat_type; + reformat_params.size = ipv4_encap_size; + reformat_params.data = encap_header; + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { err = PTR_ERR(e->pkt_reformat); @@ -471,6 +479,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, { int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); const struct ip_tunnel_key *tun_key = &e->tun_info->key; + struct mlx5_pkt_reformat_params reformat_params; struct mlx5e_neigh m_neigh = {}; TC_TUN_ROUTE_ATTR_INIT(attr); struct ipv6hdr *ip6h; @@ -553,9 +562,11 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, goto release_neigh; } - e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv6_encap_size, encap_header, + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = e->reformat_type; + reformat_params.size = ipv6_encap_size; + reformat_params.data = encap_header; + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { err = PTR_ERR(e->pkt_reformat); @@ -582,6 +593,7 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv, { int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size); const struct ip_tunnel_key *tun_key = &e->tun_info->key; + struct mlx5_pkt_reformat_params reformat_params; TC_TUN_ROUTE_ATTR_INIT(attr); struct ipv6hdr *ip6h; int ipv6_encap_size; @@ -654,9 +666,11 @@ int mlx5e_tc_tun_update_header_ipv6(struct mlx5e_priv *priv, goto release_neigh; } - e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv6_encap_size, encap_header, + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = e->reformat_type; + reformat_params.size = ipv6_encap_size; + reformat_params.data = encap_header; + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { err = PTR_ERR(e->pkt_reformat); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 490131e06efb..2e846b741280 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -120,6 +120,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, struct list_head *flow_list) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5_pkt_reformat_params reformat_params; struct mlx5_esw_flow_attr *esw_attr; struct mlx5_flow_handle *rule; struct mlx5_flow_attr *attr; @@ -130,9 +131,12 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, if (e->flags & MLX5_ENCAP_ENTRY_NO_ROUTE) return; + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = e->reformat_type; + reformat_params.size = e->encap_size; + reformat_params.data = e->encap_header; e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - e->encap_size, e->encap_header, + &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(e->pkt_reformat)) { mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %lu\n", @@ -839,6 +843,7 @@ int mlx5e_attach_decap(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr *attr = flow->attr->esw_attr; + struct mlx5_pkt_reformat_params reformat_params; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5e_decap_entry *d; struct mlx5e_decap_key key; @@ -880,10 +885,12 @@ int mlx5e_attach_decap(struct mlx5e_priv *priv, hash_add_rcu(esw->offloads.decap_tbl, &d->hlist, hash_key); mutex_unlock(&esw->offloads.decap_tbl_lock); + memset(&reformat_params, 0, sizeof(reformat_params)); + reformat_params.type = MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2; + reformat_params.size = sizeof(parse_attr->eth); + reformat_params.data = &parse_attr->eth; d->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, - MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2, - sizeof(parse_attr->eth), - &parse_attr->eth, + &reformat_params, MLX5_FLOW_NAMESPACE_FDB); if (IS_ERR(d->pkt_reformat)) { err = PTR_ERR(d->pkt_reformat); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h index 00af0b831a28..d964665eaa63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h @@ -162,7 +162,7 @@ static inline unsigned int mlx5e_accel_tx_ids_len(struct mlx5e_txqsq *sq, /* Part of the eseg touched by TX offloads */ #define MLX5E_ACCEL_ESEG_LEN offsetof(struct mlx5_wqe_eth_seg, mss) -static inline bool mlx5e_accel_tx_eseg(struct mlx5e_priv *priv, +static inline void mlx5e_accel_tx_eseg(struct mlx5e_priv *priv, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg, u16 ihs) { @@ -175,8 +175,6 @@ static inline bool mlx5e_accel_tx_eseg(struct mlx5e_priv *priv, if (skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL) mlx5e_tx_tunnel_accel(skb, eseg, ihs); #endif - - return true; } static inline void mlx5e_accel_tx_finish(struct mlx5e_txqsq *sq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 26f7fab109d9..7cab08a2f715 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -428,7 +428,6 @@ int mlx5e_ipsec_init(struct mlx5e_priv *priv) spin_lock_init(&ipsec->sadb_rx_lock); ida_init(&ipsec->halloc); ipsec->en_priv = priv; - ipsec->en_priv->ipsec = ipsec; ipsec->no_trailer = !!(mlx5_accel_ipsec_device_caps(priv->mdev) & MLX5_ACCEL_IPSEC_CAP_RX_NO_TRAILER); ipsec->wq = alloc_ordered_workqueue("mlx5e_ipsec: %s", 0, @@ -438,6 +437,7 @@ int mlx5e_ipsec_init(struct mlx5e_priv *priv) return -ENOMEM; } + priv->ipsec = ipsec; mlx5e_accel_ipsec_fs_init(priv); netdev_dbg(priv->netdev, "IPSec attached to netdevice\n"); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index a97e8d205094..33de8f0092a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -136,8 +136,6 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg, u8 mode, struct xfrm_offload *xo) { - struct mlx5e_swp_spec swp_spec = {}; - /* Tunnel Mode: * SWP: OutL3 InL3 InL4 * Pkt: MAC IP ESP IP L4 @@ -146,23 +144,58 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb, * SWP: OutL3 InL4 * InL3 * Pkt: MAC IP ESP L4 + * + * Tunnel(VXLAN TCP/UDP) over Transport Mode + * SWP: OutL3 InL3 InL4 + * Pkt: MAC IP ESP UDP VXLAN IP L4 */ - swp_spec.l3_proto = skb->protocol; - swp_spec.is_tun = mode == XFRM_MODE_TUNNEL; - if (swp_spec.is_tun) { - if (xo->proto == IPPROTO_IPV6) { - swp_spec.tun_l3_proto = htons(ETH_P_IPV6); - swp_spec.tun_l4_proto = inner_ipv6_hdr(skb)->nexthdr; - } else { - swp_spec.tun_l3_proto = htons(ETH_P_IP); - swp_spec.tun_l4_proto = inner_ip_hdr(skb)->protocol; - } - } else { - swp_spec.tun_l3_proto = skb->protocol; - swp_spec.tun_l4_proto = xo->proto; + + /* Shared settings */ + eseg->swp_outer_l3_offset = skb_network_offset(skb) / 2; + if (skb->protocol == htons(ETH_P_IPV6)) + eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L3_IPV6; + + /* Tunnel mode */ + if (mode == XFRM_MODE_TUNNEL) { + eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2; + eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2; + if (xo->proto == IPPROTO_IPV6) + eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; + if (inner_ip_hdr(skb)->protocol == IPPROTO_UDP) + eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; + return; } - mlx5e_set_eseg_swp(skb, eseg, &swp_spec); + /* Transport mode */ + if (mode != XFRM_MODE_TRANSPORT) + return; + + if (!xo->inner_ipproto) { + eseg->swp_inner_l3_offset = skb_network_offset(skb) / 2; + eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2; + if (skb->protocol == htons(ETH_P_IPV6)) + eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; + if (xo->proto == IPPROTO_UDP) + eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; + return; + } + + /* Tunnel(VXLAN TCP/UDP) over Transport Mode */ + switch (xo->inner_ipproto) { + case IPPROTO_UDP: + eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; + fallthrough; + case IPPROTO_TCP: + eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2; + eseg->swp_inner_l4_offset = (skb->csum_start + skb->head - skb->data) / 2; + if (skb->protocol == htons(ETH_P_IPV6)) + eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; + break; + default: + break; + } + + return; } void mlx5e_ipsec_set_iv_esn(struct sk_buff *skb, struct xfrm_state *x, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index 3e80742a3caf..5120a59361e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -93,18 +93,38 @@ static inline bool mlx5e_ipsec_eseg_meta(struct mlx5_wqe_eth_seg *eseg) void mlx5e_ipsec_tx_build_eseg(struct mlx5e_priv *priv, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg); -static inline bool mlx5e_ipsec_feature_check(struct sk_buff *skb, struct net_device *netdev, - netdev_features_t features) +static inline netdev_features_t +mlx5e_ipsec_feature_check(struct sk_buff *skb, netdev_features_t features) { + struct xfrm_offload *xo = xfrm_offload(skb); struct sec_path *sp = skb_sec_path(skb); - if (sp && sp->len) { + if (sp && sp->len && xo) { struct xfrm_state *x = sp->xvec[0]; - if (x && x->xso.offload_handle) - return true; + if (!x || !x->xso.offload_handle) + goto out_disable; + + if (xo->inner_ipproto) { + /* Cannot support tunnel packet over IPsec tunnel mode + * because we cannot offload three IP header csum + */ + if (x->props.mode == XFRM_MODE_TUNNEL) + goto out_disable; + + /* Only support UDP or TCP L4 checksum */ + if (xo->inner_ipproto != IPPROTO_UDP && + xo->inner_ipproto != IPPROTO_TCP) + goto out_disable; + } + + return features; + } - return false; + + /* Disable CSUM and GSO for software IPsec */ +out_disable: + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } #else @@ -120,8 +140,9 @@ static inline bool mlx5e_ipsec_eseg_meta(struct mlx5_wqe_eth_seg *eseg) } static inline bool mlx5_ipsec_is_rx_flow(struct mlx5_cqe64 *cqe) { return false; } -static inline bool mlx5e_ipsec_feature_check(struct sk_buff *skb, struct net_device *netdev, - netdev_features_t features) { return false; } +static inline netdev_features_t +mlx5e_ipsec_feature_check(struct sk_buff *skb, netdev_features_t features) +{ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } #endif /* CONFIG_MLX5_EN_IPSEC */ #endif /* __MLX5E_IPSEC_RXTX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c index 95293ee0d38d..d93aadbf10da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c @@ -59,12 +59,15 @@ void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv) struct net_device *netdev = priv->netdev; struct mlx5_core_dev *mdev = priv->mdev; - if (mlx5_accel_is_ktls_tx(mdev)) { + if (!mlx5e_accel_is_ktls_tx(mdev) && !mlx5e_accel_is_ktls_rx(mdev)) + return; + + if (mlx5e_accel_is_ktls_tx(mdev)) { netdev->hw_features |= NETIF_F_HW_TLS_TX; netdev->features |= NETIF_F_HW_TLS_TX; } - if (mlx5_accel_is_ktls_rx(mdev)) + if (mlx5e_accel_is_ktls_rx(mdev)) netdev->hw_features |= NETIF_F_HW_TLS_RX; netdev->tlsdev_ops = &mlx5e_ktls_ops; @@ -89,7 +92,7 @@ int mlx5e_ktls_init_rx(struct mlx5e_priv *priv) { int err; - if (!mlx5_accel_is_ktls_rx(priv->mdev)) + if (!mlx5e_accel_is_ktls_rx(priv->mdev)) return 0; priv->tls->rx_wq = create_singlethread_workqueue("mlx5e_tls_rx"); @@ -109,7 +112,7 @@ int mlx5e_ktls_init_rx(struct mlx5e_priv *priv) void mlx5e_ktls_cleanup_rx(struct mlx5e_priv *priv) { - if (!mlx5_accel_is_ktls_rx(priv->mdev)) + if (!mlx5e_accel_is_ktls_rx(priv->mdev)) return; if (priv->netdev->features & NETIF_F_HW_TLS_RX) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h index aaa579bf9a39..5833deb2354c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h @@ -15,6 +15,25 @@ int mlx5e_ktls_set_feature_rx(struct net_device *netdev, bool enable); struct mlx5e_ktls_resync_resp * mlx5e_ktls_rx_resync_create_resp_list(void); void mlx5e_ktls_rx_resync_destroy_resp_list(struct mlx5e_ktls_resync_resp *resp_list); + +static inline bool mlx5e_accel_is_ktls_tx(struct mlx5_core_dev *mdev) +{ + return !is_kdump_kernel() && + mlx5_accel_is_ktls_tx(mdev); +} + +static inline bool mlx5e_accel_is_ktls_rx(struct mlx5_core_dev *mdev) +{ + return !is_kdump_kernel() && + mlx5_accel_is_ktls_rx(mdev); +} + +static inline bool mlx5e_accel_is_ktls_device(struct mlx5_core_dev *mdev) +{ + return !is_kdump_kernel() && + mlx5_accel_is_ktls_device(mdev); +} + #else static inline void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv) @@ -44,6 +63,11 @@ mlx5e_ktls_rx_resync_create_resp_list(void) static inline void mlx5e_ktls_rx_resync_destroy_resp_list(struct mlx5e_ktls_resync_resp *resp_list) {} + +static inline bool mlx5e_accel_is_ktls_tx(struct mlx5_core_dev *mdev) { return false; } +static inline bool mlx5e_accel_is_ktls_rx(struct mlx5_core_dev *mdev) { return false; } +static inline bool mlx5e_accel_is_ktls_device(struct mlx5_core_dev *mdev) { return false; } + #endif #endif /* __MLX5E_TLS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index 51bdf71073f3..9ad3459fb63a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -23,10 +23,13 @@ mlx5e_ktls_dumps_num_wqes(struct mlx5e_params *params, unsigned int nfrags, return nfrags + DIV_ROUND_UP(sync_len, MLX5E_SW2HW_MTU(params, params->sw_mtu)); } -u16 mlx5e_ktls_get_stop_room(struct mlx5e_params *params) +u16 mlx5e_ktls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { u16 num_dumps, stop_room = 0; + if (!mlx5e_accel_is_ktls_tx(mdev)) + return 0; + num_dumps = mlx5e_ktls_dumps_num_wqes(params, MAX_SKB_FRAGS, TLS_MAX_PAYLOAD_SIZE); stop_room += mlx5e_stop_room_for_wqe(MLX5E_TLS_SET_STATIC_PARAMS_WQEBBS); @@ -135,6 +138,7 @@ void mlx5e_ktls_del_tx(struct net_device *netdev, struct tls_context *tls_ctx) priv = netdev_priv(netdev); mdev = priv->mdev; + atomic64_inc(&priv_tx->sw_stats->tx_tls_del); mlx5e_destroy_tis(mdev, priv_tx->tisn); mlx5_ktls_destroy_key(mdev, priv_tx->key_id); kfree(priv_tx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h index 8f79335057dc..08c9d5134479 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h @@ -14,7 +14,7 @@ struct mlx5e_accel_tx_tls_state { u32 tls_tisn; }; -u16 mlx5e_ktls_get_stop_room(struct mlx5e_params *params); +u16 mlx5e_ktls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params); bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *sq, struct sk_buff *skb, int datalen, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c index d6b21b899dbc..b8fc863aa68d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c @@ -192,13 +192,13 @@ void mlx5e_tls_build_netdev(struct mlx5e_priv *priv) struct net_device *netdev = priv->netdev; u32 caps; - if (mlx5_accel_is_ktls_device(priv->mdev)) { + if (mlx5e_accel_is_ktls_device(priv->mdev)) { mlx5e_ktls_build_netdev(priv); return; } /* FPGA */ - if (!mlx5_accel_is_tls_device(priv->mdev)) + if (!mlx5e_accel_is_tls_device(priv->mdev)) return; caps = mlx5_accel_tls_device_caps(priv->mdev); @@ -224,7 +224,7 @@ int mlx5e_tls_init(struct mlx5e_priv *priv) { struct mlx5e_tls *tls; - if (!mlx5_accel_is_tls_device(priv->mdev)) + if (!mlx5e_accel_is_tls_device(priv->mdev)) return 0; tls = kzalloc(sizeof(*tls), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h index 4c9274d390da..62ecf14bf86a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h @@ -42,6 +42,7 @@ struct mlx5e_tls_sw_stats { atomic64_t tx_tls_ctx; + atomic64_t tx_tls_del; atomic64_t tx_tls_drop_metadata; atomic64_t tx_tls_drop_resync_alloc; atomic64_t tx_tls_drop_no_sync_data; @@ -103,11 +104,18 @@ int mlx5e_tls_get_count(struct mlx5e_priv *priv); int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data); int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data); +static inline bool mlx5e_accel_is_tls_device(struct mlx5_core_dev *mdev) +{ + return !is_kdump_kernel() && + mlx5_accel_is_tls_device(mdev); +} + #else static inline void mlx5e_tls_build_netdev(struct mlx5e_priv *priv) { - if (mlx5_accel_is_ktls_device(priv->mdev)) + if (!is_kdump_kernel() && + mlx5_accel_is_ktls_device(priv->mdev)) mlx5e_ktls_build_netdev(priv); } @@ -117,6 +125,7 @@ static inline void mlx5e_tls_cleanup(struct mlx5e_priv *priv) { } static inline int mlx5e_tls_get_count(struct mlx5e_priv *priv) { return 0; } static inline int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) { return 0; } static inline int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) { return 0; } +static inline bool mlx5e_accel_is_tls_device(struct mlx5_core_dev *mdev) { return false; } #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c index 82dc09aaa7fc..7a700f913582 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c @@ -273,7 +273,7 @@ bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq, if (WARN_ON_ONCE(tls_ctx->netdev != netdev)) goto err_out; - if (mlx5_accel_is_ktls_tx(sq->mdev)) + if (mlx5e_accel_is_ktls_tx(sq->mdev)) return mlx5e_ktls_handle_tx_skb(tls_ctx, sq, skb, datalen, state); /* FPGA */ @@ -378,11 +378,11 @@ void mlx5e_tls_handle_rx_skb_metadata(struct mlx5e_rq *rq, struct sk_buff *skb, u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { - if (!mlx5_accel_is_tls_device(mdev)) + if (!mlx5e_accel_is_tls_device(mdev)) return 0; - if (mlx5_accel_is_ktls_device(mdev)) - return mlx5e_ktls_get_stop_room(params); + if (mlx5e_accel_is_ktls_device(mdev)) + return mlx5e_ktls_get_stop_room(mdev, params); /* FPGA */ /* Resync SKB. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c index 29463bdb7715..56e7b2aee85f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c @@ -47,6 +47,7 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = { static const struct counter_desc mlx5e_ktls_sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_ctx) }, + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_del) }, { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, rx_tls_ctx) }, { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, rx_tls_del) }, }; @@ -58,7 +59,7 @@ static const struct counter_desc *get_tls_atomic_stats(struct mlx5e_priv *priv) { if (!priv->tls) return NULL; - if (mlx5_accel_is_ktls_device(priv->mdev)) + if (mlx5e_accel_is_ktls_device(priv->mdev)) return mlx5e_ktls_sw_stats_desc; return mlx5e_tls_sw_stats_desc; } @@ -67,7 +68,7 @@ int mlx5e_tls_get_count(struct mlx5e_priv *priv) { if (!priv->tls) return 0; - if (mlx5_accel_is_ktls_device(priv->mdev)) + if (mlx5e_accel_is_ktls_device(priv->mdev)) return ARRAY_SIZE(mlx5e_ktls_sw_stats_desc); return ARRAY_SIZE(mlx5e_tls_sw_stats_desc); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index d6513aef5cd4..bd72572e03d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1992,7 +1992,7 @@ static int set_pflag_tx_mpwqe_common(struct net_device *netdev, u32 flag, bool e struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_params new_params; - if (enable && !MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe)) + if (enable && !mlx5e_tx_mpwqe_supported(mdev)) return -EOPNOTSUPP; new_params = priv->channels.params; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d26b8ed51195..414a73d16619 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -91,12 +91,16 @@ void mlx5e_update_carrier(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; u8 port_state; + bool up; port_state = mlx5_query_vport_state(mdev, MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0); - if (port_state == VPORT_STATE_UP) { + up = port_state == VPORT_STATE_UP; + if (up == netif_carrier_ok(priv->netdev)) + netif_carrier_event(priv->netdev); + if (up) { netdev_info(priv->netdev, "Link up\n"); netif_carrier_on(priv->netdev); } else { @@ -853,7 +857,7 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param, if (err) goto err_destroy_rq; - if (mlx5e_is_tls_on(rq->priv) && !mlx5_accel_is_ktls_device(mdev)) + if (mlx5e_is_tls_on(rq->priv) && !mlx5e_accel_is_ktls_device(mdev)) __set_bit(MLX5E_RQ_STATE_FPGA_TLS, &rq->state); /* must be FPGA */ if (MLX5_CAP_ETH(mdev, cqe_checksum_full)) @@ -4326,6 +4330,11 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, /* Support Geneve offload for default UDP port */ if (port == GENEVE_UDP_PORT && mlx5_geneve_tx_allowed(priv->mdev)) return features; +#endif + break; +#ifdef CONFIG_MLX5_EN_IPSEC + case IPPROTO_ESP: + return mlx5e_ipsec_feature_check(skb, features); #endif } @@ -4343,9 +4352,6 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb, features = vlan_features_check(skb, features); features = vxlan_features_check(skb, features); - if (mlx5e_ipsec_feature_check(skb, netdev, features)) - return features; - /* Validate if the tunneled packet is being offloaded by HW */ if (skb->encapsulation && (features & NETIF_F_CSUM_MASK || features & NETIF_F_GSO_MASK)) @@ -4661,12 +4667,10 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 params->log_sq_size = is_kdump_kernel() ? MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE : MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE; - MLX5E_SET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE, - MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe)); + MLX5E_SET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE, mlx5e_tx_mpwqe_supported(mdev)); /* XDP SQ */ - MLX5E_SET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE, - MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe)); + MLX5E_SET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE, mlx5e_tx_mpwqe_supported(mdev)); /* set CQE compression */ params->rx_cqe_compress_def = false; @@ -5103,7 +5107,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) mlx5e_set_netdev_mtu_boundaries(priv); mlx5e_set_dev_port_mtu(priv); - mlx5_lag_add(mdev, netdev); + mlx5_lag_add_netdev(mdev, netdev); mlx5e_enable_async_events(priv); mlx5e_enable_blocking_events(priv); @@ -5151,7 +5155,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) priv->en_trap = NULL; } mlx5e_disable_async_events(priv); - mlx5_lag_remove(mdev); + mlx5_lag_remove_netdev(mdev, priv->netdev); mlx5_vxlan_reset_to_default(mdev->vxlan); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 34eb1118670f..bf94bcb6fa5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -45,11 +45,13 @@ #include "en_tc.h" #include "en/rep/tc.h" #include "en/rep/neigh.h" +#include "en/rep/bridge.h" #include "en/devlink.h" #include "fs_core.h" #include "lib/mlx5.h" #define CREATE_TRACE_POINTS #include "diag/en_rep_tracepoint.h" +#include "en_accel/ipsec.h" #define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \ max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE) @@ -536,13 +538,13 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = { .ndo_change_carrier = mlx5e_rep_change_carrier, }; -bool mlx5e_eswitch_uplink_rep(struct net_device *netdev) +bool mlx5e_eswitch_uplink_rep(const struct net_device *netdev) { return netdev->netdev_ops == &mlx5e_netdev_ops && mlx5e_is_uplink_rep(netdev_priv(netdev)); } -bool mlx5e_eswitch_vf_rep(struct net_device *netdev) +bool mlx5e_eswitch_vf_rep(const struct net_device *netdev) { return netdev->netdev_ops == &mlx5e_netdev_ops_rep; } @@ -629,6 +631,11 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); + int err; + + err = mlx5e_ipsec_init(priv); + if (err) + mlx5_core_err(mdev, "Uplink rep IPsec initialization failed, %d\n", err); mlx5e_vxlan_set_netdev_info(priv); return mlx5e_init_rep(mdev, netdev); @@ -636,6 +643,7 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev, static void mlx5e_cleanup_rep(struct mlx5e_priv *priv) { + mlx5e_ipsec_cleanup(priv); } static int mlx5e_create_rep_ttc_table(struct mlx5e_priv *priv) @@ -975,12 +983,13 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) if (MLX5_CAP_GEN(mdev, uplink_follow)) mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK, 0, 0, MLX5_VPORT_ADMIN_STATE_AUTO); - mlx5_lag_add(mdev, netdev); + mlx5_lag_add_netdev(mdev, netdev); priv->events_nb.notifier_call = uplink_rep_async_event; mlx5_notifier_register(mdev, &priv->events_nb); mlx5e_dcbnl_initialize(priv); mlx5e_dcbnl_init_app(priv); mlx5e_rep_neigh_init(rpriv); + mlx5e_rep_bridge_init(priv); netdev->wanted_features |= NETIF_F_HW_TC; @@ -1002,11 +1011,12 @@ static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv) netif_device_detach(priv->netdev); rtnl_unlock(); + mlx5e_rep_bridge_cleanup(priv); mlx5e_rep_neigh_cleanup(rpriv); mlx5e_dcbnl_delete_app(priv); mlx5_notifier_unregister(mdev, &priv->events_nb); mlx5e_rep_tc_disable(priv); - mlx5_lag_remove(mdev); + mlx5_lag_remove_netdev(mdev, priv->netdev); } static MLX5E_DEFINE_STATS_GRP(sw_rep, 0); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 22585015c7a7..47a2dfb7792a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -231,9 +231,9 @@ void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv); void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv); -bool mlx5e_eswitch_vf_rep(struct net_device *netdev); -bool mlx5e_eswitch_uplink_rep(struct net_device *netdev); -static inline bool mlx5e_eswitch_rep(struct net_device *netdev) +bool mlx5e_eswitch_vf_rep(const struct net_device *netdev); +bool mlx5e_eswitch_uplink_rep(const struct net_device *netdev); +static inline bool mlx5e_eswitch_rep(const struct net_device *netdev) { return mlx5e_eswitch_vf_rep(netdev) || mlx5e_eswitch_uplink_rep(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index f90894eea9e0..3c65fd0bcf31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -579,6 +579,9 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) if (mlx5_wq_cyc_missing(wq) < wqe_bulk) return false; + if (rq->page_pool) + page_pool_nid_changed(rq->page_pool, numa_mem_id()); + do { u16 head = mlx5_wq_cyc_get_head(wq); @@ -734,6 +737,9 @@ INDIRECT_CALLABLE_SCOPE bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) if (likely(missing < UMR_WQE_BULK)) return false; + if (rq->page_pool) + page_pool_nid_changed(rq->page_pool, numa_mem_id()); + head = rq->mpwqe.actual_wq_head; i = missing; do { @@ -1310,7 +1316,8 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) if (rep->vlan && skb_vlan_tag_present(skb)) skb_vlan_pop(skb); - if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv)) { + if (unlikely(!mlx5_ipsec_is_rx_flow(cqe) && + !mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv))) { dev_kfree_skb_any(skb); goto free_wqe; } @@ -1367,7 +1374,8 @@ static void mlx5e_handle_rx_cqe_mpwrq_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); - if (!mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv)) { + if (unlikely(!mlx5_ipsec_is_rx_flow(cqe) && + !mlx5e_rep_tc_update_skb(cqe, skb, &tc_priv))) { dev_kfree_skb_any(skb); goto mpwrq_cqe_out; } @@ -1553,12 +1561,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) return 0; - if (rq->page_pool) - page_pool_nid_changed(rq->page_pool, numa_mem_id()); - if (rq->cqd.left) { work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget); - if (rq->cqd.left || work_done >= budget) + if (work_done >= budget) goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index d4b0f270b6bb..629a61e8022f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -83,17 +83,17 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { [CHAIN_TO_REG] = { .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_0, .moffset = 0, - .mlen = 2, + .mlen = 16, }, [VPORT_TO_REG] = { .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_0, - .moffset = 2, - .mlen = 2, + .moffset = 16, + .mlen = 16, }, [TUNNEL_TO_REG] = { .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_1, - .moffset = 1, - .mlen = ((ESW_TUN_OPTS_BITS + ESW_TUN_ID_BITS) / 8), + .moffset = 8, + .mlen = ESW_TUN_OPTS_BITS + ESW_TUN_ID_BITS, .soffset = MLX5_BYTE_OFF(fte_match_param, misc_parameters_2.metadata_reg_c_1), }, @@ -110,7 +110,7 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = { [NIC_CHAIN_TO_REG] = { .mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_B, .moffset = 0, - .mlen = 2, + .mlen = 16, }, [NIC_ZONE_RESTORE_TO_REG] = nic_zone_restore_to_reg_ct, }; @@ -128,23 +128,46 @@ static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow); void mlx5e_tc_match_to_reg_match(struct mlx5_flow_spec *spec, enum mlx5e_tc_attr_to_reg type, - u32 data, + u32 val, u32 mask) { + void *headers_c = spec->match_criteria, *headers_v = spec->match_value, *fmask, *fval; int soffset = mlx5e_tc_attr_to_reg_mappings[type].soffset; + int moffset = mlx5e_tc_attr_to_reg_mappings[type].moffset; int match_len = mlx5e_tc_attr_to_reg_mappings[type].mlen; - void *headers_c = spec->match_criteria; - void *headers_v = spec->match_value; - void *fmask, *fval; + u32 max_mask = GENMASK(match_len - 1, 0); + __be32 curr_mask_be, curr_val_be; + u32 curr_mask, curr_val; fmask = headers_c + soffset; fval = headers_v + soffset; - mask = (__force u32)(cpu_to_be32(mask)) >> (32 - (match_len * 8)); - data = (__force u32)(cpu_to_be32(data)) >> (32 - (match_len * 8)); + memcpy(&curr_mask_be, fmask, 4); + memcpy(&curr_val_be, fval, 4); - memcpy(fmask, &mask, match_len); - memcpy(fval, &data, match_len); + curr_mask = be32_to_cpu(curr_mask_be); + curr_val = be32_to_cpu(curr_val_be); + + //move to correct offset + WARN_ON(mask > max_mask); + mask <<= moffset; + val <<= moffset; + max_mask <<= moffset; + + //zero val and mask + curr_mask &= ~max_mask; + curr_val &= ~max_mask; + + //add current to mask + curr_mask |= mask; + curr_val |= val; + + //back to be32 and write + curr_mask_be = cpu_to_be32(curr_mask); + curr_val_be = cpu_to_be32(curr_val); + + memcpy(fmask, &curr_mask_be, 4); + memcpy(fval, &curr_val_be, 4); spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2; } @@ -152,23 +175,28 @@ mlx5e_tc_match_to_reg_match(struct mlx5_flow_spec *spec, void mlx5e_tc_match_to_reg_get_match(struct mlx5_flow_spec *spec, enum mlx5e_tc_attr_to_reg type, - u32 *data, + u32 *val, u32 *mask) { + void *headers_c = spec->match_criteria, *headers_v = spec->match_value, *fmask, *fval; int soffset = mlx5e_tc_attr_to_reg_mappings[type].soffset; + int moffset = mlx5e_tc_attr_to_reg_mappings[type].moffset; int match_len = mlx5e_tc_attr_to_reg_mappings[type].mlen; - void *headers_c = spec->match_criteria; - void *headers_v = spec->match_value; - void *fmask, *fval; + u32 max_mask = GENMASK(match_len - 1, 0); + __be32 curr_mask_be, curr_val_be; + u32 curr_mask, curr_val; fmask = headers_c + soffset; fval = headers_v + soffset; - memcpy(mask, fmask, match_len); - memcpy(data, fval, match_len); + memcpy(&curr_mask_be, fmask, 4); + memcpy(&curr_val_be, fval, 4); - *mask = be32_to_cpu((__force __be32)(*mask << (32 - (match_len * 8)))); - *data = be32_to_cpu((__force __be32)(*data << (32 - (match_len * 8)))); + curr_mask = be32_to_cpu(curr_mask_be); + curr_val = be32_to_cpu(curr_val_be); + + *mask = (curr_mask >> moffset) & max_mask; + *val = (curr_val >> moffset) & max_mask; } int @@ -192,13 +220,13 @@ mlx5e_tc_match_to_reg_set_and_get_id(struct mlx5_core_dev *mdev, (mod_hdr_acts->num_actions * MLX5_MH_ACT_SZ); /* Firmware has 5bit length field and 0 means 32bits */ - if (mlen == 4) + if (mlen == 32) mlen = 0; MLX5_SET(set_action_in, modact, action_type, MLX5_ACTION_TYPE_SET); MLX5_SET(set_action_in, modact, field, mfield); - MLX5_SET(set_action_in, modact, offset, moffset * 8); - MLX5_SET(set_action_in, modact, length, mlen * 8); + MLX5_SET(set_action_in, modact, offset, moffset); + MLX5_SET(set_action_in, modact, length, mlen); MLX5_SET(set_action_in, modact, data, data); err = mod_hdr_acts->num_actions; mod_hdr_acts->num_actions++; @@ -296,13 +324,13 @@ void mlx5e_tc_match_to_reg_mod_hdr_change(struct mlx5_core_dev *mdev, modact = mod_hdr_acts->actions + (act_id * MLX5_MH_ACT_SZ); /* Firmware has 5bit length field and 0 means 32bits */ - if (mlen == 4) + if (mlen == 32) mlen = 0; MLX5_SET(set_action_in, modact, action_type, MLX5_ACTION_TYPE_SET); MLX5_SET(set_action_in, modact, field, mfield); - MLX5_SET(set_action_in, modact, offset, moffset * 8); - MLX5_SET(set_action_in, modact, length, mlen * 8); + MLX5_SET(set_action_in, modact, offset, moffset); + MLX5_SET(set_action_in, modact, length, mlen); MLX5_SET(set_action_in, modact, data, data); } @@ -818,7 +846,7 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, hash_hairpin_info(peer_id, match_prio)); mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); - params.log_data_size = 15; + params.log_data_size = 16; params.log_data_size = min_t(u8, params.log_data_size, MLX5_CAP_GEN(priv->mdev, log_max_hairpin_wq_data_sz)); params.log_data_size = max_t(u8, params.log_data_size, @@ -5105,7 +5133,7 @@ bool mlx5e_tc_update_skb(struct mlx5_cqe64 *cqe, tc_skb_ext->chain = chain; - zone_restore_id = (reg_b >> REG_MAPPING_SHIFT(NIC_ZONE_RESTORE_TO_REG)) & + zone_restore_id = (reg_b >> REG_MAPPING_MOFFSET(NIC_ZONE_RESTORE_TO_REG)) & ESW_ZONE_ID_MASK; if (!mlx5e_tc_ct_restore_flow(tc->ct, skb, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 17027536efba..f7cbeb0b66d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -129,7 +129,7 @@ struct tunnel_match_enc_opts { */ #define TUNNEL_INFO_BITS 12 #define TUNNEL_INFO_BITS_MASK GENMASK(TUNNEL_INFO_BITS - 1, 0) -#define ENC_OPTS_BITS 12 +#define ENC_OPTS_BITS 11 #define ENC_OPTS_BITS_MASK GENMASK(ENC_OPTS_BITS - 1, 0) #define TUNNEL_ID_BITS (TUNNEL_INFO_BITS + ENC_OPTS_BITS) #define TUNNEL_ID_MASK GENMASK(TUNNEL_ID_BITS - 1, 0) @@ -201,10 +201,10 @@ enum mlx5e_tc_attr_to_reg { struct mlx5e_tc_attr_to_reg_mapping { int mfield; /* rewrite field */ - int moffset; /* offset of mfield */ - int mlen; /* bytes to rewrite/match */ + int moffset; /* bit offset of mfield */ + int mlen; /* bits to rewrite/match */ - int soffset; /* offset of spec for match */ + int soffset; /* byte offset of spec for match */ }; extern struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 320fe0cda917..c63d78eda606 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -687,16 +687,12 @@ void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq) mlx5e_tx_mpwqe_session_complete(sq); } -static bool mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq, +static void mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5e_accel_tx_state *accel, struct mlx5_wqe_eth_seg *eseg, u16 ihs) { - if (unlikely(!mlx5e_accel_tx_eseg(priv, skb, eseg, ihs))) - return false; - + mlx5e_accel_tx_eseg(priv, skb, eseg, ihs); mlx5e_txwqe_build_eseg_csum(sq, skb, accel, eseg); - - return true; } netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) @@ -725,10 +721,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) if (mlx5e_tx_skb_supports_mpwqe(skb, &attr)) { struct mlx5_wqe_eth_seg eseg = {}; - if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg, - attr.ihs))) - return NETDEV_TX_OK; - + mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &eseg, attr.ihs); mlx5e_sq_xmit_mpwqe(sq, skb, &eseg, netdev_xmit_more()); return NETDEV_TX_OK; } @@ -743,9 +736,7 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) /* May update the WQE, but may not post other WQEs. */ mlx5e_accel_tx_finish(sq, wqe, &accel, (struct mlx5_wqe_inline_seg *)(wqe->data + wqe_attr.ds_cnt_inl)); - if (unlikely(!mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth, attr.ihs))) - return NETDEV_TX_OK; - + mlx5e_txwqe_build_eseg(priv, sq, skb, &accel, &wqe->eth, attr.ihs); mlx5e_sq_xmit_wqe(sq, skb, &attr, &wqe_attr, wqe, pi, netdev_xmit_more()); return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 940333410267..6e074cc457de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -1,33 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* - * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. + * Copyright (c) 2013-2021, Mellanox Technologies inc. All rights reserved. */ #include @@ -45,6 +18,7 @@ #include "eswitch.h" #include "lib/clock.h" #include "diag/fw_tracer.h" +#include "mlx5_irq.h" enum { MLX5_EQE_OWNER_INIT_VAL = 0x1, @@ -84,6 +58,9 @@ struct mlx5_eq_table { struct mutex lock; /* sync async eqs creations */ int num_comp_eqs; struct mlx5_irq_table *irq_table; +#ifdef CONFIG_RFS_ACCEL + struct cpu_rmap *rmap; +#endif }; #define MLX5_ASYNC_EVENT_MASK ((1ull << MLX5_EVENT_TYPE_PATH_MIG) | \ @@ -288,7 +265,7 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u32 out[MLX5_ST_SZ_DW(create_eq_out)] = {0}; u8 log_eq_stride = ilog2(MLX5_EQE_SIZE); struct mlx5_priv *priv = &dev->priv; - u8 vecidx = param->irq_index; + u16 vecidx = param->irq_index; __be64 *pas; void *eqc; int inlen; @@ -311,13 +288,20 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, mlx5_init_fbc(eq->frag_buf.frags, log_eq_stride, log_eq_size, &eq->fbc); init_eq_buf(eq); + eq->irq = mlx5_irq_request(dev, vecidx, param->affinity); + if (IS_ERR(eq->irq)) { + err = PTR_ERR(eq->irq); + goto err_buf; + } + + vecidx = mlx5_irq_get_index(eq->irq); inlen = MLX5_ST_SZ_BYTES(create_eq_in) + MLX5_FLD_SZ_BYTES(create_eq_in, pas[0]) * eq->frag_buf.npages; in = kvzalloc(inlen, GFP_KERNEL); if (!in) { err = -ENOMEM; - goto err_buf; + goto err_irq; } pas = (__be64 *)MLX5_ADDR_OF(create_eq_in, in, pas); @@ -361,6 +345,8 @@ err_eq: err_in: kvfree(in); +err_irq: + mlx5_irq_release(eq->irq); err_buf: mlx5_frag_buf_free(dev, &eq->frag_buf); return err; @@ -379,10 +365,9 @@ err_buf: int mlx5_eq_enable(struct mlx5_core_dev *dev, struct mlx5_eq *eq, struct notifier_block *nb) { - struct mlx5_eq_table *eq_table = dev->priv.eq_table; int err; - err = mlx5_irq_attach_nb(eq_table->irq_table, eq->vecidx, nb); + err = mlx5_irq_attach_nb(eq->irq, nb); if (!err) eq_update_ci(eq, 1); @@ -401,9 +386,7 @@ EXPORT_SYMBOL(mlx5_eq_enable); void mlx5_eq_disable(struct mlx5_core_dev *dev, struct mlx5_eq *eq, struct notifier_block *nb) { - struct mlx5_eq_table *eq_table = dev->priv.eq_table; - - mlx5_irq_detach_nb(eq_table->irq_table, eq->vecidx, nb); + mlx5_irq_detach_nb(eq->irq, nb); } EXPORT_SYMBOL(mlx5_eq_disable); @@ -417,10 +400,9 @@ static int destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq) if (err) mlx5_core_warn(dev, "failed to destroy a previously created eq: eqn %d\n", eq->eqn); - synchronize_irq(eq->irqn); + mlx5_irq_release(eq->irq); mlx5_frag_buf_free(dev, &eq->frag_buf); - return err; } @@ -492,14 +474,7 @@ static int create_async_eq(struct mlx5_core_dev *dev, int err; mutex_lock(&eq_table->lock); - /* Async EQs must share irq index 0 */ - if (param->irq_index != 0) { - err = -EINVAL; - goto unlock; - } - err = create_map_eq(dev, eq, param); -unlock: mutex_unlock(&eq_table->lock); return err; } @@ -618,8 +593,11 @@ setup_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq_async *eq, eq->irq_nb.notifier_call = mlx5_eq_async_int; spin_lock_init(&eq->lock); + if (!zalloc_cpumask_var(¶m->affinity, GFP_KERNEL)) + return -ENOMEM; err = create_async_eq(dev, &eq->core, param); + free_cpumask_var(param->affinity); if (err) { mlx5_core_warn(dev, "failed to create %s EQ %d\n", name, err); return err; @@ -654,7 +632,6 @@ static int create_async_eqs(struct mlx5_core_dev *dev) mlx5_eq_notifier_register(dev, &table->cq_err_nb); param = (struct mlx5_eq_param) { - .irq_index = 0, .nent = MLX5_NUM_CMD_EQE, .mask[0] = 1ull << MLX5_EVENT_TYPE_CMD, }; @@ -667,7 +644,6 @@ static int create_async_eqs(struct mlx5_core_dev *dev) mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL); param = (struct mlx5_eq_param) { - .irq_index = 0, .nent = MLX5_NUM_ASYNC_EQE, }; @@ -677,7 +653,6 @@ static int create_async_eqs(struct mlx5_core_dev *dev) goto err2; param = (struct mlx5_eq_param) { - .irq_index = 0, .nent = /* TODO: sriov max_vf + */ 1, .mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_REQUEST, }; @@ -737,6 +712,9 @@ mlx5_eq_create_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq = kvzalloc(sizeof(*eq), GFP_KERNEL); int err; + if (!cpumask_available(param->affinity)) + return ERR_PTR(-EINVAL); + if (!eq) return ERR_PTR(-ENOMEM); @@ -847,16 +825,21 @@ static int create_comp_eqs(struct mlx5_core_dev *dev) .irq_index = vecidx, .nent = nent, }; - err = create_map_eq(dev, &eq->core, ¶m); - if (err) { - kfree(eq); - goto clean; + + if (!zalloc_cpumask_var(¶m.affinity, GFP_KERNEL)) { + err = -ENOMEM; + goto clean_eq; } + cpumask_set_cpu(cpumask_local_spread(i, dev->priv.numa_node), + param.affinity); + err = create_map_eq(dev, &eq->core, ¶m); + free_cpumask_var(param.affinity); + if (err) + goto clean_eq; err = mlx5_eq_enable(dev, &eq->core, &eq->irq_nb); if (err) { destroy_unmap_eq(dev, &eq->core); - kfree(eq); - goto clean; + goto clean_eq; } mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->core.eqn); @@ -865,7 +848,8 @@ static int create_comp_eqs(struct mlx5_core_dev *dev) } return 0; - +clean_eq: + kfree(eq); clean: destroy_comp_eqs(dev); return err; @@ -901,17 +885,23 @@ EXPORT_SYMBOL(mlx5_comp_vectors_count); struct cpumask * mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector) { - int vecidx = vector + MLX5_IRQ_VEC_COMP_BASE; + struct mlx5_eq_table *table = dev->priv.eq_table; + struct mlx5_eq_comp *eq, *n; + int i = 0; - return mlx5_irq_get_affinity_mask(dev->priv.eq_table->irq_table, - vecidx); + list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) { + if (i++ == vector) + break; + } + + return mlx5_irq_get_affinity_mask(eq->core.irq); } EXPORT_SYMBOL(mlx5_comp_irq_get_affinity_mask); #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev) { - return mlx5_irq_get_rmap(dev->priv.eq_table->irq_table); + return dev->priv.eq_table->rmap; } #endif @@ -928,12 +918,57 @@ struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn) return ERR_PTR(-ENOENT); } +static void clear_rmap(struct mlx5_core_dev *dev) +{ +#ifdef CONFIG_RFS_ACCEL + struct mlx5_eq_table *eq_table = dev->priv.eq_table; + + free_irq_cpu_rmap(eq_table->rmap); +#endif +} + +static int set_rmap(struct mlx5_core_dev *mdev) +{ + int err = 0; +#ifdef CONFIG_RFS_ACCEL + struct mlx5_eq_table *eq_table = mdev->priv.eq_table; + int vecidx; + + eq_table->rmap = alloc_irq_cpu_rmap(eq_table->num_comp_eqs); + if (!eq_table->rmap) { + err = -ENOMEM; + mlx5_core_err(mdev, "Failed to allocate cpu_rmap. err %d", err); + goto err_out; + } + + vecidx = MLX5_IRQ_VEC_COMP_BASE; + for (; vecidx < eq_table->num_comp_eqs + MLX5_IRQ_VEC_COMP_BASE; + vecidx++) { + err = irq_cpu_rmap_add(eq_table->rmap, + pci_irq_vector(mdev->pdev, vecidx)); + if (err) { + mlx5_core_err(mdev, "irq_cpu_rmap_add failed. err %d", + err); + goto err_irq_cpu_rmap_add; + } + } + return 0; + +err_irq_cpu_rmap_add: + clear_rmap(mdev); +err_out: +#endif + return err; +} + /* This function should only be called after mlx5_cmd_force_teardown_hca */ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev) { struct mlx5_eq_table *table = dev->priv.eq_table; mutex_lock(&table->lock); /* sync with create/destroy_async_eq */ + if (!mlx5_core_is_sf(dev)) + clear_rmap(dev); mlx5_irq_table_destroy(dev); mutex_unlock(&table->lock); } @@ -950,12 +985,19 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev) int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ? MLX5_CAP_GEN(dev, max_num_eqs) : 1 << MLX5_CAP_GEN(dev, log_max_eq); + int max_eqs_sf; int err; eq_table->num_comp_eqs = min_t(int, - mlx5_irq_get_num_comp(eq_table->irq_table), + mlx5_irq_table_get_num_comp(eq_table->irq_table), num_eqs - MLX5_MAX_ASYNC_EQS); + if (mlx5_core_is_sf(dev)) { + max_eqs_sf = min_t(int, MLX5_COMP_EQS_PER_SF, + mlx5_irq_table_get_sfs_vec(eq_table->irq_table)); + eq_table->num_comp_eqs = min_t(int, eq_table->num_comp_eqs, + max_eqs_sf); + } err = create_async_eqs(dev); if (err) { @@ -963,6 +1005,18 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev) goto err_async_eqs; } + if (!mlx5_core_is_sf(dev)) { + /* rmap is a mapping between irq number and queue number. + * each irq can be assign only to a single rmap. + * since SFs share IRQs, rmap mapping cannot function correctly + * for irqs that are shared for different core/netdev RX rings. + * Hence we don't allow netdev rmap for SFs + */ + err = set_rmap(dev); + if (err) + goto err_rmap; + } + err = create_comp_eqs(dev); if (err) { mlx5_core_err(dev, "Failed to create completion EQs\n"); @@ -971,6 +1025,9 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev) return 0; err_comp_eqs: + if (!mlx5_core_is_sf(dev)) + clear_rmap(dev); +err_rmap: destroy_async_eqs(dev); err_async_eqs: return err; @@ -978,6 +1035,8 @@ err_async_eqs: void mlx5_eq_table_destroy(struct mlx5_core_dev *dev) { + if (!mlx5_core_is_sf(dev)) + clear_rmap(dev); destroy_comp_eqs(dev); destroy_async_eqs(dev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c new file mode 100644 index 000000000000..a6e1d4f78268 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -0,0 +1,1299 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021 Mellanox Technologies. */ + +#include +#include +#include +#include +#include "bridge.h" +#include "eswitch.h" +#include "bridge_priv.h" +#define CREATE_TRACE_POINTS +#include "diag/bridge_tracepoint.h" + +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE 64000 +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_FROM 0 +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_TO (MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE / 4 - 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_FILTER_GRP_IDX_FROM \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_TO + 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_FILTER_GRP_IDX_TO \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE / 2 - 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_FROM \ + (MLX5_ESW_BRIDGE_INGRESS_TABLE_FILTER_GRP_IDX_TO + 1) +#define MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_TO (MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE - 1) + +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE 64000 +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_FROM 0 +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE / 2 - 1) +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_FROM \ + (MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO + 1) +#define MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO (MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE - 1) + +#define MLX5_ESW_BRIDGE_SKIP_TABLE_SIZE 0 + +enum { + MLX5_ESW_BRIDGE_LEVEL_INGRESS_TABLE, + MLX5_ESW_BRIDGE_LEVEL_EGRESS_TABLE, + MLX5_ESW_BRIDGE_LEVEL_SKIP_TABLE, +}; + +static const struct rhashtable_params fdb_ht_params = { + .key_offset = offsetof(struct mlx5_esw_bridge_fdb_entry, key), + .key_len = sizeof(struct mlx5_esw_bridge_fdb_key), + .head_offset = offsetof(struct mlx5_esw_bridge_fdb_entry, ht_node), + .automatic_shrinking = true, +}; + +enum { + MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG = BIT(0), +}; + +struct mlx5_esw_bridge { + int ifindex; + int refcnt; + struct list_head list; + struct mlx5_esw_bridge_offloads *br_offloads; + + struct list_head fdb_list; + struct rhashtable fdb_ht; + struct xarray vports; + + struct mlx5_flow_table *egress_ft; + struct mlx5_flow_group *egress_vlan_fg; + struct mlx5_flow_group *egress_mac_fg; + unsigned long ageing_time; + u32 flags; +}; + +static void +mlx5_esw_bridge_fdb_offload_notify(struct net_device *dev, const unsigned char *addr, u16 vid, + unsigned long val) +{ + struct switchdev_notifier_fdb_info send_info; + + send_info.addr = addr; + send_info.vid = vid; + send_info.offloaded = true; + call_switchdev_notifiers(val, dev, &send_info.info, NULL); +} + +static struct mlx5_flow_table * +mlx5_esw_bridge_table_create(int max_fte, u32 level, struct mlx5_eswitch *esw) +{ + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_namespace *ns; + struct mlx5_flow_table *fdb; + + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); + if (!ns) { + esw_warn(dev, "Failed to get FDB namespace\n"); + return ERR_PTR(-ENOENT); + } + + ft_attr.flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; + ft_attr.max_fte = max_fte; + ft_attr.level = level; + ft_attr.prio = FDB_BR_OFFLOAD; + fdb = mlx5_create_flow_table(ns, &ft_attr); + if (IS_ERR(fdb)) + esw_warn(dev, "Failed to create bridge FDB Table (err=%ld)\n", PTR_ERR(fdb)); + + return fdb; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_ingress_vlan_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *ingress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_15_0); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.first_vid); + + MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + + MLX5_SET(create_flow_group_in, in, start_flow_index, + MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_FROM); + MLX5_SET(create_flow_group_in, in, end_flow_index, + MLX5_ESW_BRIDGE_INGRESS_TABLE_VLAN_GRP_IDX_TO); + + fg = mlx5_create_flow_group(ingress_ft, in); + kvfree(in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create VLAN flow group for bridge ingress table (err=%ld)\n", + PTR_ERR(fg)); + + return fg; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_ingress_filter_fg_create(struct mlx5_eswitch *esw, + struct mlx5_flow_table *ingress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_15_0); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.cvlan_tag); + + MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + + MLX5_SET(create_flow_group_in, in, start_flow_index, + MLX5_ESW_BRIDGE_INGRESS_TABLE_FILTER_GRP_IDX_FROM); + MLX5_SET(create_flow_group_in, in, end_flow_index, + MLX5_ESW_BRIDGE_INGRESS_TABLE_FILTER_GRP_IDX_TO); + + fg = mlx5_create_flow_group(ingress_ft, in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create bridge ingress table VLAN filter flow group (err=%ld)\n", + PTR_ERR(fg)); + + kvfree(in); + return fg; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_ingress_mac_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *ingress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, + MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.smac_15_0); + + MLX5_SET(fte_match_param, match, misc_parameters_2.metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + + MLX5_SET(create_flow_group_in, in, start_flow_index, + MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_FROM); + MLX5_SET(create_flow_group_in, in, end_flow_index, + MLX5_ESW_BRIDGE_INGRESS_TABLE_MAC_GRP_IDX_TO); + + fg = mlx5_create_flow_group(ingress_ft, in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create MAC flow group for bridge ingress table (err=%ld)\n", + PTR_ERR(fg)); + + kvfree(in); + return fg; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_egress_vlan_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *egress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_15_0); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.first_vid); + + MLX5_SET(create_flow_group_in, in, start_flow_index, + MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_FROM); + MLX5_SET(create_flow_group_in, in, end_flow_index, + MLX5_ESW_BRIDGE_EGRESS_TABLE_VLAN_GRP_IDX_TO); + + fg = mlx5_create_flow_group(egress_ft, in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create VLAN flow group for bridge egress table (err=%ld)\n", + PTR_ERR(fg)); + kvfree(in); + return fg; +} + +static struct mlx5_flow_group * +mlx5_esw_bridge_egress_mac_fg_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *egress_ft) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_group *fg; + u32 *in, *match; + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return ERR_PTR(-ENOMEM); + + MLX5_SET(create_flow_group_in, in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS); + match = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_47_16); + MLX5_SET_TO_ONES(fte_match_param, match, outer_headers.dmac_15_0); + + MLX5_SET(create_flow_group_in, in, start_flow_index, + MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_FROM); + MLX5_SET(create_flow_group_in, in, end_flow_index, + MLX5_ESW_BRIDGE_EGRESS_TABLE_MAC_GRP_IDX_TO); + + fg = mlx5_create_flow_group(egress_ft, in); + if (IS_ERR(fg)) + esw_warn(esw->dev, + "Failed to create bridge egress table MAC flow group (err=%ld)\n", + PTR_ERR(fg)); + kvfree(in); + return fg; +} + +static int +mlx5_esw_bridge_ingress_table_init(struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_flow_group *mac_fg, *filter_fg, *vlan_fg; + struct mlx5_flow_table *ingress_ft, *skip_ft; + int err; + + if (!mlx5_eswitch_vport_match_metadata_enabled(br_offloads->esw)) + return -EOPNOTSUPP; + + ingress_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_INGRESS_TABLE_SIZE, + MLX5_ESW_BRIDGE_LEVEL_INGRESS_TABLE, + br_offloads->esw); + if (IS_ERR(ingress_ft)) + return PTR_ERR(ingress_ft); + + skip_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_SKIP_TABLE_SIZE, + MLX5_ESW_BRIDGE_LEVEL_SKIP_TABLE, + br_offloads->esw); + if (IS_ERR(skip_ft)) { + err = PTR_ERR(skip_ft); + goto err_skip_tbl; + } + + vlan_fg = mlx5_esw_bridge_ingress_vlan_fg_create(br_offloads->esw, ingress_ft); + if (IS_ERR(vlan_fg)) { + err = PTR_ERR(vlan_fg); + goto err_vlan_fg; + } + + filter_fg = mlx5_esw_bridge_ingress_filter_fg_create(br_offloads->esw, ingress_ft); + if (IS_ERR(filter_fg)) { + err = PTR_ERR(filter_fg); + goto err_filter_fg; + } + + mac_fg = mlx5_esw_bridge_ingress_mac_fg_create(br_offloads->esw, ingress_ft); + if (IS_ERR(mac_fg)) { + err = PTR_ERR(mac_fg); + goto err_mac_fg; + } + + br_offloads->ingress_ft = ingress_ft; + br_offloads->skip_ft = skip_ft; + br_offloads->ingress_vlan_fg = vlan_fg; + br_offloads->ingress_filter_fg = filter_fg; + br_offloads->ingress_mac_fg = mac_fg; + return 0; + +err_mac_fg: + mlx5_destroy_flow_group(filter_fg); +err_filter_fg: + mlx5_destroy_flow_group(vlan_fg); +err_vlan_fg: + mlx5_destroy_flow_table(skip_ft); +err_skip_tbl: + mlx5_destroy_flow_table(ingress_ft); + return err; +} + +static void +mlx5_esw_bridge_ingress_table_cleanup(struct mlx5_esw_bridge_offloads *br_offloads) +{ + mlx5_destroy_flow_group(br_offloads->ingress_mac_fg); + br_offloads->ingress_mac_fg = NULL; + mlx5_destroy_flow_group(br_offloads->ingress_filter_fg); + br_offloads->ingress_filter_fg = NULL; + mlx5_destroy_flow_group(br_offloads->ingress_vlan_fg); + br_offloads->ingress_vlan_fg = NULL; + mlx5_destroy_flow_table(br_offloads->skip_ft); + br_offloads->skip_ft = NULL; + mlx5_destroy_flow_table(br_offloads->ingress_ft); + br_offloads->ingress_ft = NULL; +} + +static int +mlx5_esw_bridge_egress_table_init(struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_flow_group *mac_fg, *vlan_fg; + struct mlx5_flow_table *egress_ft; + int err; + + egress_ft = mlx5_esw_bridge_table_create(MLX5_ESW_BRIDGE_EGRESS_TABLE_SIZE, + MLX5_ESW_BRIDGE_LEVEL_EGRESS_TABLE, + br_offloads->esw); + if (IS_ERR(egress_ft)) + return PTR_ERR(egress_ft); + + vlan_fg = mlx5_esw_bridge_egress_vlan_fg_create(br_offloads->esw, egress_ft); + if (IS_ERR(vlan_fg)) { + err = PTR_ERR(vlan_fg); + goto err_vlan_fg; + } + + mac_fg = mlx5_esw_bridge_egress_mac_fg_create(br_offloads->esw, egress_ft); + if (IS_ERR(mac_fg)) { + err = PTR_ERR(mac_fg); + goto err_mac_fg; + } + + bridge->egress_ft = egress_ft; + bridge->egress_vlan_fg = vlan_fg; + bridge->egress_mac_fg = mac_fg; + return 0; + +err_mac_fg: + mlx5_destroy_flow_group(vlan_fg); +err_vlan_fg: + mlx5_destroy_flow_table(egress_ft); + return err; +} + +static void +mlx5_esw_bridge_egress_table_cleanup(struct mlx5_esw_bridge *bridge) +{ + mlx5_destroy_flow_group(bridge->egress_mac_fg); + mlx5_destroy_flow_group(bridge->egress_vlan_fg); + mlx5_destroy_flow_table(bridge->egress_ft); +} + +static struct mlx5_flow_handle * +mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr, + struct mlx5_esw_bridge_vlan *vlan, u32 counter_id, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_esw_bridge_offloads *br_offloads = bridge->br_offloads; + struct mlx5_flow_act flow_act = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT, + .flags = FLOW_ACT_NO_APPEND, + }; + struct mlx5_flow_destination dests[2] = {}; + struct mlx5_flow_spec *rule_spec; + struct mlx5_flow_handle *handle; + u8 *smac_v, *smac_c; + + rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL); + if (!rule_spec) + return ERR_PTR(-ENOMEM); + + rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2; + + smac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, + outer_headers.smac_47_16); + ether_addr_copy(smac_v, addr); + smac_c = MLX5_ADDR_OF(fte_match_param, rule_spec->match_criteria, + outer_headers.smac_47_16); + eth_broadcast_addr(smac_c); + + MLX5_SET(fte_match_param, rule_spec->match_criteria, + misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask()); + MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_for_match(br_offloads->esw, vport_num)); + + if (vlan && vlan->pkt_reformat_push) { + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + flow_act.pkt_reformat = vlan->pkt_reformat_push; + } else if (vlan) { + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_value, + outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.first_vid); + MLX5_SET(fte_match_param, rule_spec->match_value, outer_headers.first_vid, + vlan->vid); + } + + dests[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dests[0].ft = bridge->egress_ft; + dests[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dests[1].counter_id = counter_id; + + handle = mlx5_add_flow_rules(br_offloads->ingress_ft, rule_spec, &flow_act, dests, + ARRAY_SIZE(dests)); + + kvfree(rule_spec); + return handle; +} + +static struct mlx5_flow_handle * +mlx5_esw_bridge_ingress_filter_flow_create(u16 vport_num, const unsigned char *addr, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_esw_bridge_offloads *br_offloads = bridge->br_offloads; + struct mlx5_flow_destination dest = { + .type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE, + .ft = br_offloads->skip_ft, + }; + struct mlx5_flow_act flow_act = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + .flags = FLOW_ACT_NO_APPEND, + }; + struct mlx5_flow_spec *rule_spec; + struct mlx5_flow_handle *handle; + u8 *smac_v, *smac_c; + + rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL); + if (!rule_spec) + return ERR_PTR(-ENOMEM); + + rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS_2; + + smac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, + outer_headers.smac_47_16); + ether_addr_copy(smac_v, addr); + smac_c = MLX5_ADDR_OF(fte_match_param, rule_spec->match_criteria, + outer_headers.smac_47_16); + eth_broadcast_addr(smac_c); + + MLX5_SET(fte_match_param, rule_spec->match_criteria, + misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask()); + MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_for_match(br_offloads->esw, vport_num)); + + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_value, + outer_headers.cvlan_tag); + + handle = mlx5_add_flow_rules(br_offloads->ingress_ft, rule_spec, &flow_act, &dest, 1); + + kvfree(rule_spec); + return handle; +} + +static struct mlx5_flow_handle * +mlx5_esw_bridge_egress_flow_create(u16 vport_num, const unsigned char *addr, + struct mlx5_esw_bridge_vlan *vlan, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_flow_destination dest = { + .type = MLX5_FLOW_DESTINATION_TYPE_VPORT, + .vport.num = vport_num, + }; + struct mlx5_flow_act flow_act = { + .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST, + .flags = FLOW_ACT_NO_APPEND, + }; + struct mlx5_flow_spec *rule_spec; + struct mlx5_flow_handle *handle; + u8 *dmac_v, *dmac_c; + + rule_spec = kvzalloc(sizeof(*rule_spec), GFP_KERNEL); + if (!rule_spec) + return ERR_PTR(-ENOMEM); + + rule_spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS; + + dmac_v = MLX5_ADDR_OF(fte_match_param, rule_spec->match_value, + outer_headers.dmac_47_16); + ether_addr_copy(dmac_v, addr); + dmac_c = MLX5_ADDR_OF(fte_match_param, rule_spec->match_criteria, + outer_headers.dmac_47_16); + eth_broadcast_addr(dmac_c); + + if (vlan) { + if (vlan->pkt_reformat_pop) { + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + flow_act.pkt_reformat = vlan->pkt_reformat_pop; + } + + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_value, + outer_headers.cvlan_tag); + MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, + outer_headers.first_vid); + MLX5_SET(fte_match_param, rule_spec->match_value, outer_headers.first_vid, + vlan->vid); + } + + handle = mlx5_add_flow_rules(bridge->egress_ft, rule_spec, &flow_act, &dest, 1); + + kvfree(rule_spec); + return handle; +} + +static struct mlx5_esw_bridge *mlx5_esw_bridge_create(int ifindex, + struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_esw_bridge *bridge; + int err; + + bridge = kvzalloc(sizeof(*bridge), GFP_KERNEL); + if (!bridge) + return ERR_PTR(-ENOMEM); + + bridge->br_offloads = br_offloads; + err = mlx5_esw_bridge_egress_table_init(br_offloads, bridge); + if (err) + goto err_egress_tbl; + + err = rhashtable_init(&bridge->fdb_ht, &fdb_ht_params); + if (err) + goto err_fdb_ht; + + INIT_LIST_HEAD(&bridge->fdb_list); + xa_init(&bridge->vports); + bridge->ifindex = ifindex; + bridge->refcnt = 1; + bridge->ageing_time = BR_DEFAULT_AGEING_TIME; + list_add(&bridge->list, &br_offloads->bridges); + + return bridge; + +err_fdb_ht: + mlx5_esw_bridge_egress_table_cleanup(bridge); +err_egress_tbl: + kvfree(bridge); + return ERR_PTR(err); +} + +static void mlx5_esw_bridge_get(struct mlx5_esw_bridge *bridge) +{ + bridge->refcnt++; +} + +static void mlx5_esw_bridge_put(struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_esw_bridge *bridge) +{ + if (--bridge->refcnt) + return; + + mlx5_esw_bridge_egress_table_cleanup(bridge); + WARN_ON(!xa_empty(&bridge->vports)); + list_del(&bridge->list); + rhashtable_destroy(&bridge->fdb_ht); + kvfree(bridge); + + if (list_empty(&br_offloads->bridges)) + mlx5_esw_bridge_ingress_table_cleanup(br_offloads); +} + +static struct mlx5_esw_bridge * +mlx5_esw_bridge_lookup(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_esw_bridge *bridge; + + ASSERT_RTNL(); + + list_for_each_entry(bridge, &br_offloads->bridges, list) { + if (bridge->ifindex == ifindex) { + mlx5_esw_bridge_get(bridge); + return bridge; + } + } + + if (!br_offloads->ingress_ft) { + int err = mlx5_esw_bridge_ingress_table_init(br_offloads); + + if (err) + return ERR_PTR(err); + } + + bridge = mlx5_esw_bridge_create(ifindex, br_offloads); + if (IS_ERR(bridge) && list_empty(&br_offloads->bridges)) + mlx5_esw_bridge_ingress_table_cleanup(br_offloads); + return bridge; +} + +static int mlx5_esw_bridge_port_insert(struct mlx5_esw_bridge_port *port, + struct mlx5_esw_bridge *bridge) +{ + return xa_insert(&bridge->vports, port->vport_num, port, GFP_KERNEL); +} + +static struct mlx5_esw_bridge_port * +mlx5_esw_bridge_port_lookup(u16 vport_num, struct mlx5_esw_bridge *bridge) +{ + return xa_load(&bridge->vports, vport_num); +} + +static void mlx5_esw_bridge_port_erase(struct mlx5_esw_bridge_port *port, + struct mlx5_esw_bridge *bridge) +{ + xa_erase(&bridge->vports, port->vport_num); +} + +static void mlx5_esw_bridge_fdb_entry_refresh(unsigned long lastuse, + struct mlx5_esw_bridge_fdb_entry *entry) +{ + trace_mlx5_esw_bridge_fdb_entry_refresh(entry); + + entry->lastuse = lastuse; + mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr, + entry->key.vid, + SWITCHDEV_FDB_ADD_TO_BRIDGE); +} + +static void +mlx5_esw_bridge_fdb_entry_cleanup(struct mlx5_esw_bridge_fdb_entry *entry, + struct mlx5_esw_bridge *bridge) +{ + trace_mlx5_esw_bridge_fdb_entry_cleanup(entry); + + rhashtable_remove_fast(&bridge->fdb_ht, &entry->ht_node, fdb_ht_params); + mlx5_del_flow_rules(entry->egress_handle); + if (entry->filter_handle) + mlx5_del_flow_rules(entry->filter_handle); + mlx5_del_flow_rules(entry->ingress_handle); + mlx5_fc_destroy(bridge->br_offloads->esw->dev, entry->ingress_counter); + list_del(&entry->vlan_list); + list_del(&entry->list); + kvfree(entry); +} + +static void mlx5_esw_bridge_fdb_flush(struct mlx5_esw_bridge *bridge) +{ + struct mlx5_esw_bridge_fdb_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) { + if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)) + mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr, + entry->key.vid, + SWITCHDEV_FDB_DEL_TO_BRIDGE); + mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); + } +} + +static struct mlx5_esw_bridge_vlan * +mlx5_esw_bridge_vlan_lookup(u16 vid, struct mlx5_esw_bridge_port *port) +{ + return xa_load(&port->vlans, vid); +} + +static int +mlx5_esw_bridge_vlan_push_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + struct { + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + } vlan_hdr = { htons(ETH_P_8021Q), htons(vlan->vid) }; + struct mlx5_pkt_reformat_params reformat_params = {}; + struct mlx5_pkt_reformat *pkt_reformat; + + if (!BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat_insert)) || + MLX5_CAP_GEN_2(esw->dev, max_reformat_insert_size) < sizeof(vlan_hdr) || + MLX5_CAP_GEN_2(esw->dev, max_reformat_insert_offset) < + offsetof(struct vlan_ethhdr, h_vlan_proto)) { + esw_warn(esw->dev, "Packet reformat INSERT_HEADER is not supported\n"); + return -EOPNOTSUPP; + } + + reformat_params.type = MLX5_REFORMAT_TYPE_INSERT_HDR; + reformat_params.param_0 = MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START; + reformat_params.param_1 = offsetof(struct vlan_ethhdr, h_vlan_proto); + reformat_params.size = sizeof(vlan_hdr); + reformat_params.data = &vlan_hdr; + pkt_reformat = mlx5_packet_reformat_alloc(esw->dev, + &reformat_params, + MLX5_FLOW_NAMESPACE_FDB); + if (IS_ERR(pkt_reformat)) { + esw_warn(esw->dev, "Failed to alloc packet reformat INSERT_HEADER (err=%ld)\n", + PTR_ERR(pkt_reformat)); + return PTR_ERR(pkt_reformat); + } + + vlan->pkt_reformat_push = pkt_reformat; + return 0; +} + +static void +mlx5_esw_bridge_vlan_push_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + mlx5_packet_reformat_dealloc(esw->dev, vlan->pkt_reformat_push); + vlan->pkt_reformat_push = NULL; +} + +static int +mlx5_esw_bridge_vlan_pop_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + struct mlx5_pkt_reformat_params reformat_params = {}; + struct mlx5_pkt_reformat *pkt_reformat; + + if (!BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat_remove)) || + MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_size) < sizeof(struct vlan_hdr) || + MLX5_CAP_GEN_2(esw->dev, max_reformat_remove_offset) < + offsetof(struct vlan_ethhdr, h_vlan_proto)) { + esw_warn(esw->dev, "Packet reformat REMOVE_HEADER is not supported\n"); + return -EOPNOTSUPP; + } + + reformat_params.type = MLX5_REFORMAT_TYPE_REMOVE_HDR; + reformat_params.param_0 = MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START; + reformat_params.param_1 = offsetof(struct vlan_ethhdr, h_vlan_proto); + reformat_params.size = sizeof(struct vlan_hdr); + pkt_reformat = mlx5_packet_reformat_alloc(esw->dev, + &reformat_params, + MLX5_FLOW_NAMESPACE_FDB); + if (IS_ERR(pkt_reformat)) { + esw_warn(esw->dev, "Failed to alloc packet reformat REMOVE_HEADER (err=%ld)\n", + PTR_ERR(pkt_reformat)); + return PTR_ERR(pkt_reformat); + } + + vlan->pkt_reformat_pop = pkt_reformat; + return 0; +} + +static void +mlx5_esw_bridge_vlan_pop_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + mlx5_packet_reformat_dealloc(esw->dev, vlan->pkt_reformat_pop); + vlan->pkt_reformat_pop = NULL; +} + +static struct mlx5_esw_bridge_vlan * +mlx5_esw_bridge_vlan_create(u16 vid, u16 flags, struct mlx5_esw_bridge_port *port, + struct mlx5_eswitch *esw) +{ + struct mlx5_esw_bridge_vlan *vlan; + int err; + + vlan = kvzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) + return ERR_PTR(-ENOMEM); + + vlan->vid = vid; + vlan->flags = flags; + INIT_LIST_HEAD(&vlan->fdb_list); + + if (flags & BRIDGE_VLAN_INFO_PVID) { + err = mlx5_esw_bridge_vlan_push_create(vlan, esw); + if (err) + goto err_vlan_push; + } + if (flags & BRIDGE_VLAN_INFO_UNTAGGED) { + err = mlx5_esw_bridge_vlan_pop_create(vlan, esw); + if (err) + goto err_vlan_pop; + } + + err = xa_insert(&port->vlans, vid, vlan, GFP_KERNEL); + if (err) + goto err_xa_insert; + + trace_mlx5_esw_bridge_vlan_create(vlan); + return vlan; + +err_xa_insert: + if (vlan->pkt_reformat_pop) + mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw); +err_vlan_pop: + if (vlan->pkt_reformat_push) + mlx5_esw_bridge_vlan_push_cleanup(vlan, esw); +err_vlan_push: + kvfree(vlan); + return ERR_PTR(err); +} + +static void mlx5_esw_bridge_vlan_erase(struct mlx5_esw_bridge_port *port, + struct mlx5_esw_bridge_vlan *vlan) +{ + xa_erase(&port->vlans, vlan->vid); +} + +static void mlx5_esw_bridge_vlan_flush(struct mlx5_esw_bridge_vlan *vlan, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_esw_bridge_fdb_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &vlan->fdb_list, vlan_list) { + if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)) + mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr, + entry->key.vid, + SWITCHDEV_FDB_DEL_TO_BRIDGE); + mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); + } + + if (vlan->pkt_reformat_pop) + mlx5_esw_bridge_vlan_pop_cleanup(vlan, bridge->br_offloads->esw); + if (vlan->pkt_reformat_push) + mlx5_esw_bridge_vlan_push_cleanup(vlan, bridge->br_offloads->esw); +} + +static void mlx5_esw_bridge_vlan_cleanup(struct mlx5_esw_bridge_port *port, + struct mlx5_esw_bridge_vlan *vlan, + struct mlx5_esw_bridge *bridge) +{ + trace_mlx5_esw_bridge_vlan_cleanup(vlan); + mlx5_esw_bridge_vlan_flush(vlan, bridge); + mlx5_esw_bridge_vlan_erase(port, vlan); + kvfree(vlan); +} + +static void mlx5_esw_bridge_port_vlans_flush(struct mlx5_esw_bridge_port *port, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_esw_bridge_vlan *vlan; + unsigned long index; + + xa_for_each(&port->vlans, index, vlan) + mlx5_esw_bridge_vlan_cleanup(port, vlan, bridge); +} + +static struct mlx5_esw_bridge_vlan * +mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, struct mlx5_esw_bridge *bridge, + struct mlx5_eswitch *esw) +{ + struct mlx5_esw_bridge_port *port; + struct mlx5_esw_bridge_vlan *vlan; + + port = mlx5_esw_bridge_port_lookup(vport_num, bridge); + if (!port) { + /* FDB is added asynchronously on wq while port might have been deleted + * concurrently. Report on 'info' logging level and skip the FDB offload. + */ + esw_info(esw->dev, "Failed to lookup bridge port (vport=%u)\n", vport_num); + return ERR_PTR(-EINVAL); + } + + vlan = mlx5_esw_bridge_vlan_lookup(vid, port); + if (!vlan) { + /* FDB is added asynchronously on wq while vlan might have been deleted + * concurrently. Report on 'info' logging level and skip the FDB offload. + */ + esw_info(esw->dev, "Failed to lookup bridge port vlan metadata (vport=%u)\n", + vport_num); + return ERR_PTR(-EINVAL); + } + + return vlan; +} + +static struct mlx5_esw_bridge_fdb_entry * +mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, const unsigned char *addr, + u16 vid, bool added_by_user, struct mlx5_eswitch *esw, + struct mlx5_esw_bridge *bridge) +{ + struct mlx5_esw_bridge_vlan *vlan = NULL; + struct mlx5_esw_bridge_fdb_entry *entry; + struct mlx5_flow_handle *handle; + struct mlx5_fc *counter; + struct mlx5e_priv *priv; + int err; + + if (bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG && vid) { + vlan = mlx5_esw_bridge_port_vlan_lookup(vid, vport_num, bridge, esw); + if (IS_ERR(vlan)) + return ERR_CAST(vlan); + } + + priv = netdev_priv(dev); + entry = kvzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return ERR_PTR(-ENOMEM); + + ether_addr_copy(entry->key.addr, addr); + entry->key.vid = vid; + entry->dev = dev; + entry->vport_num = vport_num; + entry->lastuse = jiffies; + if (added_by_user) + entry->flags |= MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER; + + counter = mlx5_fc_create(priv->mdev, true); + if (IS_ERR(counter)) { + err = PTR_ERR(counter); + goto err_ingress_fc_create; + } + entry->ingress_counter = counter; + + handle = mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan, mlx5_fc_id(counter), + bridge); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + esw_warn(esw->dev, "Failed to create ingress flow(vport=%u,err=%d)\n", + vport_num, err); + goto err_ingress_flow_create; + } + entry->ingress_handle = handle; + + if (bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG) { + handle = mlx5_esw_bridge_ingress_filter_flow_create(vport_num, addr, bridge); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + esw_warn(esw->dev, "Failed to create ingress filter(vport=%u,err=%d)\n", + vport_num, err); + goto err_ingress_filter_flow_create; + } + entry->filter_handle = handle; + } + + handle = mlx5_esw_bridge_egress_flow_create(vport_num, addr, vlan, bridge); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + esw_warn(esw->dev, "Failed to create egress flow(vport=%u,err=%d)\n", + vport_num, err); + goto err_egress_flow_create; + } + entry->egress_handle = handle; + + err = rhashtable_insert_fast(&bridge->fdb_ht, &entry->ht_node, fdb_ht_params); + if (err) { + esw_warn(esw->dev, "Failed to insert FDB flow(vport=%u,err=%d)\n", vport_num, err); + goto err_ht_init; + } + + if (vlan) + list_add(&entry->vlan_list, &vlan->fdb_list); + else + INIT_LIST_HEAD(&entry->vlan_list); + list_add(&entry->list, &bridge->fdb_list); + + trace_mlx5_esw_bridge_fdb_entry_init(entry); + return entry; + +err_ht_init: + mlx5_del_flow_rules(entry->egress_handle); +err_egress_flow_create: + if (entry->filter_handle) + mlx5_del_flow_rules(entry->filter_handle); +err_ingress_filter_flow_create: + mlx5_del_flow_rules(entry->ingress_handle); +err_ingress_flow_create: + mlx5_fc_destroy(priv->mdev, entry->ingress_counter); +err_ingress_fc_create: + kvfree(entry); + return ERR_PTR(err); +} + +int mlx5_esw_bridge_ageing_time_set(unsigned long ageing_time, struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + if (!vport->bridge) + return -EINVAL; + + vport->bridge->ageing_time = ageing_time; + return 0; +} + +int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + struct mlx5_esw_bridge *bridge; + bool filtering; + + if (!vport->bridge) + return -EINVAL; + + bridge = vport->bridge; + filtering = bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG; + if (filtering == enable) + return 0; + + mlx5_esw_bridge_fdb_flush(bridge); + if (enable) + bridge->flags |= MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG; + else + bridge->flags &= ~MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG; + + return 0; +} + +static int mlx5_esw_bridge_vport_init(struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_esw_bridge *bridge, + struct mlx5_vport *vport) +{ + struct mlx5_eswitch *esw = br_offloads->esw; + struct mlx5_esw_bridge_port *port; + int err; + + port = kvzalloc(sizeof(*port), GFP_KERNEL); + if (!port) { + err = -ENOMEM; + goto err_port_alloc; + } + + port->vport_num = vport->vport; + xa_init(&port->vlans); + err = mlx5_esw_bridge_port_insert(port, bridge); + if (err) { + esw_warn(esw->dev, "Failed to insert port metadata (vport=%u,err=%d)\n", + vport->vport, err); + goto err_port_insert; + } + trace_mlx5_esw_bridge_vport_init(port); + + vport->bridge = bridge; + return 0; + +err_port_insert: + kvfree(port); +err_port_alloc: + mlx5_esw_bridge_put(br_offloads, bridge); + return err; +} + +static int mlx5_esw_bridge_vport_cleanup(struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_vport *vport) +{ + struct mlx5_esw_bridge *bridge = vport->bridge; + struct mlx5_esw_bridge_fdb_entry *entry, *tmp; + struct mlx5_esw_bridge_port *port; + + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) + if (entry->vport_num == vport->vport) + mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); + + port = mlx5_esw_bridge_port_lookup(vport->vport, bridge); + if (!port) { + WARN(1, "Vport %u metadata not found on bridge", vport->vport); + return -EINVAL; + } + + trace_mlx5_esw_bridge_vport_cleanup(port); + mlx5_esw_bridge_port_vlans_flush(port, bridge); + mlx5_esw_bridge_port_erase(port, bridge); + kvfree(port); + mlx5_esw_bridge_put(br_offloads, bridge); + vport->bridge = NULL; + return 0; +} + +int mlx5_esw_bridge_vport_link(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_vport *vport, struct netlink_ext_ack *extack) +{ + struct mlx5_esw_bridge *bridge; + int err; + + WARN_ON(vport->bridge); + + bridge = mlx5_esw_bridge_lookup(ifindex, br_offloads); + if (IS_ERR(bridge)) { + NL_SET_ERR_MSG_MOD(extack, "Error checking for existing bridge with same ifindex"); + return PTR_ERR(bridge); + } + + err = mlx5_esw_bridge_vport_init(br_offloads, bridge, vport); + if (err) + NL_SET_ERR_MSG_MOD(extack, "Error initializing port"); + return err; +} + +int mlx5_esw_bridge_vport_unlink(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_vport *vport, struct netlink_ext_ack *extack) +{ + struct mlx5_esw_bridge *bridge = vport->bridge; + int err; + + if (!bridge) { + NL_SET_ERR_MSG_MOD(extack, "Port is not attached to any bridge"); + return -EINVAL; + } + if (bridge->ifindex != ifindex) { + NL_SET_ERR_MSG_MOD(extack, "Port is attached to another bridge"); + return -EINVAL; + } + + err = mlx5_esw_bridge_vport_cleanup(br_offloads, vport); + if (err) + NL_SET_ERR_MSG_MOD(extack, "Port cleanup failed"); + return err; +} + +int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw, + struct mlx5_vport *vport, struct netlink_ext_ack *extack) +{ + struct mlx5_esw_bridge_port *port; + struct mlx5_esw_bridge_vlan *vlan; + + port = mlx5_esw_bridge_port_lookup(vport->vport, vport->bridge); + if (!port) + return -EINVAL; + + vlan = mlx5_esw_bridge_vlan_lookup(vid, port); + if (vlan) { + if (vlan->flags == flags) + return 0; + mlx5_esw_bridge_vlan_cleanup(port, vlan, vport->bridge); + } + + vlan = mlx5_esw_bridge_vlan_create(vid, flags, port, esw); + if (IS_ERR(vlan)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to create VLAN entry"); + return PTR_ERR(vlan); + } + return 0; +} + +void mlx5_esw_bridge_port_vlan_del(u16 vid, struct mlx5_eswitch *esw, struct mlx5_vport *vport) +{ + struct mlx5_esw_bridge_port *port; + struct mlx5_esw_bridge_vlan *vlan; + + port = mlx5_esw_bridge_port_lookup(vport->vport, vport->bridge); + if (!port) + return; + + vlan = mlx5_esw_bridge_vlan_lookup(vid, port); + if (!vlan) + return; + mlx5_esw_bridge_vlan_cleanup(port, vlan, vport->bridge); +} + +void mlx5_esw_bridge_fdb_create(struct net_device *dev, struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + struct switchdev_notifier_fdb_info *fdb_info) +{ + struct mlx5_esw_bridge *bridge = vport->bridge; + struct mlx5_esw_bridge_fdb_entry *entry; + u16 vport_num = vport->vport; + + if (!bridge) { + esw_info(esw->dev, "Vport is not assigned to bridge (vport=%u)\n", vport_num); + return; + } + + entry = mlx5_esw_bridge_fdb_entry_init(dev, vport_num, fdb_info->addr, fdb_info->vid, + fdb_info->added_by_user, esw, bridge); + if (IS_ERR(entry)) + return; + + if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER) + mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid, + SWITCHDEV_FDB_OFFLOADED); + else + /* Take over dynamic entries to prevent kernel bridge from aging them out. */ + mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid, + SWITCHDEV_FDB_ADD_TO_BRIDGE); +} + +void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + struct switchdev_notifier_fdb_info *fdb_info) +{ + struct mlx5_esw_bridge *bridge = vport->bridge; + struct mlx5_esw_bridge_fdb_entry *entry; + struct mlx5_esw_bridge_fdb_key key; + u16 vport_num = vport->vport; + + if (!bridge) { + esw_warn(esw->dev, "Vport is not assigned to bridge (vport=%u)\n", vport_num); + return; + } + + ether_addr_copy(key.addr, fdb_info->addr); + key.vid = fdb_info->vid; + entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params); + if (!entry) { + esw_warn(esw->dev, + "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n", + key.addr, key.vid, vport_num); + return; + } + + if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)) + mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid, + SWITCHDEV_FDB_DEL_TO_BRIDGE); + mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); +} + +void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_esw_bridge_fdb_entry *entry, *tmp; + struct mlx5_esw_bridge *bridge; + + list_for_each_entry(bridge, &br_offloads->bridges, list) { + list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) { + unsigned long lastuse = + (unsigned long)mlx5_fc_query_lastuse(entry->ingress_counter); + + if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER) + continue; + + if (time_after(lastuse, entry->lastuse)) { + mlx5_esw_bridge_fdb_entry_refresh(lastuse, entry); + } else if (time_is_before_jiffies(entry->lastuse + bridge->ageing_time)) { + mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr, + entry->key.vid, + SWITCHDEV_FDB_DEL_TO_BRIDGE); + mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge); + } + } + } +} + +static void mlx5_esw_bridge_flush(struct mlx5_esw_bridge_offloads *br_offloads) +{ + struct mlx5_eswitch *esw = br_offloads->esw; + struct mlx5_vport *vport; + unsigned long i; + + mlx5_esw_for_each_vport(esw, i, vport) + if (vport->bridge) + mlx5_esw_bridge_vport_cleanup(br_offloads, vport); + + WARN_ONCE(!list_empty(&br_offloads->bridges), + "Cleaning up bridge offloads while still having bridges attached\n"); +} + +struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw) +{ + struct mlx5_esw_bridge_offloads *br_offloads; + + br_offloads = kvzalloc(sizeof(*br_offloads), GFP_KERNEL); + if (!br_offloads) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&br_offloads->bridges); + br_offloads->esw = esw; + esw->br_offloads = br_offloads; + + return br_offloads; +} + +void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw) +{ + struct mlx5_esw_bridge_offloads *br_offloads = esw->br_offloads; + + if (!br_offloads) + return; + + mlx5_esw_bridge_flush(br_offloads); + + esw->br_offloads = NULL; + kvfree(br_offloads); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h new file mode 100644 index 000000000000..d826942b27fc --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#ifndef __MLX5_ESW_BRIDGE_H__ +#define __MLX5_ESW_BRIDGE_H__ + +#include +#include +#include +#include "eswitch.h" + +struct mlx5_flow_table; +struct mlx5_flow_group; + +struct mlx5_esw_bridge_offloads { + struct mlx5_eswitch *esw; + struct list_head bridges; + struct notifier_block netdev_nb; + struct notifier_block nb_blk; + struct notifier_block nb; + struct workqueue_struct *wq; + struct delayed_work update_work; + + struct mlx5_flow_table *ingress_ft; + struct mlx5_flow_group *ingress_vlan_fg; + struct mlx5_flow_group *ingress_filter_fg; + struct mlx5_flow_group *ingress_mac_fg; + + struct mlx5_flow_table *skip_ft; +}; + +struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw); +void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw); +int mlx5_esw_bridge_vport_link(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_vport *vport, struct netlink_ext_ack *extack); +int mlx5_esw_bridge_vport_unlink(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads, + struct mlx5_vport *vport, struct netlink_ext_ack *extack); +void mlx5_esw_bridge_fdb_create(struct net_device *dev, struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + struct switchdev_notifier_fdb_info *fdb_info); +void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw, + struct mlx5_vport *vport, + struct switchdev_notifier_fdb_info *fdb_info); +void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads); +int mlx5_esw_bridge_ageing_time_set(unsigned long ageing_time, struct mlx5_eswitch *esw, + struct mlx5_vport *vport); +int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw, + struct mlx5_vport *vport); +int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw, + struct mlx5_vport *vport, struct netlink_ext_ack *extack); +void mlx5_esw_bridge_port_vlan_del(u16 vid, struct mlx5_eswitch *esw, struct mlx5_vport *vport); + +#endif /* __MLX5_ESW_BRIDGE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h new file mode 100644 index 000000000000..d9ab2e8bc2cb --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#ifndef _MLX5_ESW_BRIDGE_PRIVATE_ +#define _MLX5_ESW_BRIDGE_PRIVATE_ + +#include +#include +#include +#include +#include +#include +#include "fs_core.h" + +struct mlx5_esw_bridge_fdb_key { + unsigned char addr[ETH_ALEN]; + u16 vid; +}; + +enum { + MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER = BIT(0), +}; + +struct mlx5_esw_bridge_fdb_entry { + struct mlx5_esw_bridge_fdb_key key; + struct rhash_head ht_node; + struct net_device *dev; + struct list_head list; + struct list_head vlan_list; + u16 vport_num; + u16 flags; + + struct mlx5_flow_handle *ingress_handle; + struct mlx5_fc *ingress_counter; + unsigned long lastuse; + struct mlx5_flow_handle *egress_handle; + struct mlx5_flow_handle *filter_handle; +}; + +struct mlx5_esw_bridge_vlan { + u16 vid; + u16 flags; + struct list_head fdb_list; + struct mlx5_pkt_reformat *pkt_reformat_push; + struct mlx5_pkt_reformat *pkt_reformat_pop; +}; + +struct mlx5_esw_bridge_port { + u16 vport_num; + struct xarray vlans; +}; + +#endif /* _MLX5_ESW_BRIDGE_PRIVATE_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h new file mode 100644 index 000000000000..227964b7d3b9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#if !defined(_MLX5_ESW_BRIDGE_TRACEPOINT_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_ESW_BRIDGE_TRACEPOINT_ + +#include +#include "../bridge_priv.h" + +DECLARE_EVENT_CLASS(mlx5_esw_bridge_fdb_template, + TP_PROTO(const struct mlx5_esw_bridge_fdb_entry *fdb), + TP_ARGS(fdb), + TP_STRUCT__entry( + __array(char, dev_name, IFNAMSIZ) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __field(u16, flags) + __field(unsigned int, used) + ), + TP_fast_assign( + strncpy(__entry->dev_name, + netdev_name(fdb->dev), + IFNAMSIZ); + memcpy(__entry->addr, fdb->key.addr, ETH_ALEN); + __entry->vid = fdb->key.vid; + __entry->flags = fdb->flags; + __entry->used = jiffies_to_msecs(jiffies - fdb->lastuse) + ), + TP_printk("net_device=%s addr=%pM vid=%hu flags=%hx used=%u", + __entry->dev_name, + __entry->addr, + __entry->vid, + __entry->flags, + __entry->used / 1000) + ); + +DEFINE_EVENT(mlx5_esw_bridge_fdb_template, + mlx5_esw_bridge_fdb_entry_init, + TP_PROTO(const struct mlx5_esw_bridge_fdb_entry *fdb), + TP_ARGS(fdb) + ); +DEFINE_EVENT(mlx5_esw_bridge_fdb_template, + mlx5_esw_bridge_fdb_entry_refresh, + TP_PROTO(const struct mlx5_esw_bridge_fdb_entry *fdb), + TP_ARGS(fdb) + ); +DEFINE_EVENT(mlx5_esw_bridge_fdb_template, + mlx5_esw_bridge_fdb_entry_cleanup, + TP_PROTO(const struct mlx5_esw_bridge_fdb_entry *fdb), + TP_ARGS(fdb) + ); + +DECLARE_EVENT_CLASS(mlx5_esw_bridge_vlan_template, + TP_PROTO(const struct mlx5_esw_bridge_vlan *vlan), + TP_ARGS(vlan), + TP_STRUCT__entry( + __field(u16, vid) + __field(u16, flags) + ), + TP_fast_assign( + __entry->vid = vlan->vid; + __entry->flags = vlan->flags; + ), + TP_printk("vid=%hu flags=%hx", + __entry->vid, + __entry->flags) + ); + +DEFINE_EVENT(mlx5_esw_bridge_vlan_template, + mlx5_esw_bridge_vlan_create, + TP_PROTO(const struct mlx5_esw_bridge_vlan *vlan), + TP_ARGS(vlan) + ); +DEFINE_EVENT(mlx5_esw_bridge_vlan_template, + mlx5_esw_bridge_vlan_cleanup, + TP_PROTO(const struct mlx5_esw_bridge_vlan *vlan), + TP_ARGS(vlan) + ); + +DECLARE_EVENT_CLASS(mlx5_esw_bridge_port_template, + TP_PROTO(const struct mlx5_esw_bridge_port *port), + TP_ARGS(port), + TP_STRUCT__entry( + __field(u16, vport_num) + ), + TP_fast_assign( + __entry->vport_num = port->vport_num; + ), + TP_printk("vport_num=%hu", __entry->vport_num) + ); + +DEFINE_EVENT(mlx5_esw_bridge_port_template, + mlx5_esw_bridge_vport_init, + TP_PROTO(const struct mlx5_esw_bridge_port *port), + TP_ARGS(port) + ); +DEFINE_EVENT(mlx5_esw_bridge_port_template, + mlx5_esw_bridge_vport_cleanup, + TP_PROTO(const struct mlx5_esw_bridge_port *port), + TP_ARGS(port) + ); + +#endif + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH esw/diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE bridge_tracepoint +#include diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 64ccb2bc0b58..48cac5bf606d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -150,6 +150,8 @@ enum mlx5_eswitch_vport_event { MLX5_VPORT_PROMISC_CHANGE = BIT(3), }; +struct mlx5_esw_bridge; + struct mlx5_vport { struct mlx5_core_dev *dev; struct hlist_head uc_list[MLX5_L2_ADDR_HASH_SIZE]; @@ -178,6 +180,7 @@ struct mlx5_vport { enum mlx5_eswitch_vport_event enabled_events; int index; struct devlink_port *dl_port; + struct mlx5_esw_bridge *bridge; }; struct mlx5_esw_indir_table; @@ -196,6 +199,7 @@ struct mlx5_eswitch_fdb { struct offloads_fdb { struct mlx5_flow_namespace *ns; + struct mlx5_flow_table *tc_miss_table; struct mlx5_flow_table *slow_fdb; struct mlx5_flow_group *send_to_vport_grp; struct mlx5_flow_group *send_to_vport_meta_grp; @@ -270,6 +274,8 @@ enum { MLX5_ESWITCH_REG_C1_LOOPBACK_ENABLED = BIT(1), }; +struct mlx5_esw_bridge_offloads; + struct mlx5_eswitch { struct mlx5_core_dev *dev; struct mlx5_nb nb; @@ -299,6 +305,7 @@ struct mlx5_eswitch { u32 root_tsar_id; } qos; + struct mlx5_esw_bridge_offloads *br_offloads; struct mlx5_esw_offload offloads; int mode; u16 manager_vport; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d18a28a6e9a6..7579f3402776 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1634,7 +1634,21 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) } esw->fdb_table.offloads.slow_fdb = fdb; - err = esw_chains_create(esw, fdb); + /* Create empty TC-miss managed table. This allows plugging in following + * priorities without directly exposing their level 0 table to + * eswitch_offloads and passing it as miss_fdb to following call to + * esw_chains_create(). + */ + memset(&ft_attr, 0, sizeof(ft_attr)); + ft_attr.prio = FDB_TC_MISS; + esw->fdb_table.offloads.tc_miss_table = mlx5_create_flow_table(root_ns, &ft_attr); + if (IS_ERR(esw->fdb_table.offloads.tc_miss_table)) { + err = PTR_ERR(esw->fdb_table.offloads.tc_miss_table); + esw_warn(dev, "Failed to create TC miss FDB Table err %d\n", err); + goto tc_miss_table_err; + } + + err = esw_chains_create(esw, esw->fdb_table.offloads.tc_miss_table); if (err) { esw_warn(dev, "Failed to open fdb chains err(%d)\n", err); goto fdb_chains_err; @@ -1779,6 +1793,8 @@ send_vport_meta_err: send_vport_err: esw_chains_destroy(esw, esw_chains(esw)); fdb_chains_err: + mlx5_destroy_flow_table(esw->fdb_table.offloads.tc_miss_table); +tc_miss_table_err: mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb); slow_fdb_err: /* Holds true only as long as DMFS is the default */ @@ -1806,6 +1822,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) esw_chains_destroy(esw, esw_chains(esw)); + mlx5_destroy_flow_table(esw->fdb_table.offloads.tc_miss_table); mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb); /* Holds true only as long as DMFS is the default */ mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 8e06731d3cb3..896a6c3dbdb7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -36,6 +36,7 @@ #include "fs_core.h" #include "fs_cmd.h" +#include "fs_ft_pool.h" #include "mlx5_core.h" #include "eswitch.h" @@ -49,9 +50,11 @@ static int mlx5_cmd_stub_update_root_ft(struct mlx5_flow_root_namespace *ns, static int mlx5_cmd_stub_create_flow_table(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, - unsigned int log_size, + unsigned int size, struct mlx5_flow_table *next_ft) { + ft->max_fte = size ? roundup_pow_of_two(size) : 1; + return 0; } @@ -108,9 +111,7 @@ static int mlx5_cmd_stub_delete_fte(struct mlx5_flow_root_namespace *ns, } static int mlx5_cmd_stub_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type namespace, struct mlx5_pkt_reformat *pkt_reformat) { @@ -181,7 +182,7 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, - unsigned int log_size, + unsigned int size, struct mlx5_flow_table *next_ft) { int en_encap = !!(ft->flags & MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT); @@ -192,12 +193,18 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, struct mlx5_core_dev *dev = ns->dev; int err; + if (size != POOL_NEXT_SIZE) + size = roundup_pow_of_two(size); + size = mlx5_ft_pool_get_avail_sz(dev, ft->type, size); + if (!size) + return -ENOSPC; + MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE); MLX5_SET(create_flow_table_in, in, table_type, ft->type); MLX5_SET(create_flow_table_in, in, flow_table_context.level, ft->level); - MLX5_SET(create_flow_table_in, in, flow_table_context.log_size, log_size); + MLX5_SET(create_flow_table_in, in, flow_table_context.log_size, size ? ilog2(size) : 0); MLX5_SET(create_flow_table_in, in, vport_number, ft->vport); MLX5_SET(create_flow_table_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); @@ -234,9 +241,14 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, } err = mlx5_cmd_exec_inout(dev, create_flow_table, in, out); - if (!err) + if (!err) { ft->id = MLX5_GET(create_flow_table_out, out, table_id); + ft->max_fte = size; + } else { + mlx5_ft_pool_put_sz(ns->dev, size); + } + return err; } @@ -245,6 +257,7 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns, { u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)] = {}; struct mlx5_core_dev *dev = ns->dev; + int err; MLX5_SET(destroy_flow_table_in, in, opcode, MLX5_CMD_OP_DESTROY_FLOW_TABLE); @@ -254,7 +267,11 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns, MLX5_SET(destroy_flow_table_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); - return mlx5_cmd_exec_in(dev, destroy_flow_table, in); + err = mlx5_cmd_exec_in(dev, destroy_flow_table, in); + if (!err) + mlx5_ft_pool_put_sz(ns->dev, ft->max_fte); + + return err; } static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns, @@ -682,9 +699,7 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, } static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type namespace, struct mlx5_pkt_reformat *pkt_reformat) { @@ -702,14 +717,14 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, else max_encap_size = MLX5_CAP_FLOWTABLE(dev, max_encap_header_size); - if (size > max_encap_size) { + if (params->size > max_encap_size) { mlx5_core_warn(dev, "encap size %zd too big, max supported is %d\n", - size, max_encap_size); + params->size, max_encap_size); return -EINVAL; } - in = kzalloc(MLX5_ST_SZ_BYTES(alloc_packet_reformat_context_in) + size, - GFP_KERNEL); + in = kzalloc(MLX5_ST_SZ_BYTES(alloc_packet_reformat_context_in) + + params->size, GFP_KERNEL); if (!in) return -ENOMEM; @@ -718,15 +733,20 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, reformat = MLX5_ADDR_OF(packet_reformat_context_in, packet_reformat_context_in, reformat_data); - inlen = reformat - (void *)in + size; + inlen = reformat - (void *)in + params->size; MLX5_SET(alloc_packet_reformat_context_in, in, opcode, MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT); MLX5_SET(packet_reformat_context_in, packet_reformat_context_in, - reformat_data_size, size); + reformat_data_size, params->size); MLX5_SET(packet_reformat_context_in, packet_reformat_context_in, - reformat_type, reformat_type); - memcpy(reformat, reformat_data, size); + reformat_type, params->type); + MLX5_SET(packet_reformat_context_in, packet_reformat_context_in, + reformat_param_0, params->param_0); + MLX5_SET(packet_reformat_context_in, packet_reformat_context_in, + reformat_param_1, params->param_1); + if (params->data && params->size) + memcpy(reformat, params->data, params->size); err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index d62de642eca9..5ecd33cdc087 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -38,7 +38,7 @@ struct mlx5_flow_cmds { int (*create_flow_table)(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, - unsigned int log_size, + unsigned int size, struct mlx5_flow_table *next_ft); int (*destroy_flow_table)(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft); @@ -77,9 +77,7 @@ struct mlx5_flow_cmds { bool disconnect); int (*packet_reformat_alloc)(struct mlx5_flow_root_namespace *ns, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type namespace, struct mlx5_pkt_reformat *pkt_reformat); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index f74d2c834037..d7bf0a3e4a52 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -38,6 +38,7 @@ #include "mlx5_core.h" #include "fs_core.h" #include "fs_cmd.h" +#include "fs_ft_pool.h" #include "diag/fs_tracepoint.h" #include "accel/ipsec.h" #include "fpga/ipsec.h" @@ -752,7 +753,7 @@ static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *f return fg; } -static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_fte, +static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, enum fs_flow_table_type table_type, enum fs_flow_table_op_mod op_mod, u32 flags) @@ -775,7 +776,6 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, int max_ft ft->op_mod = op_mod; ft->type = table_type; ft->vport = vport; - ft->max_fte = max_fte; ft->flags = flags; INIT_LIST_HEAD(&ft->fwd_rules); mutex_init(&ft->lock); @@ -1070,7 +1070,6 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa struct mlx5_flow_table *next_ft; struct fs_prio *fs_prio = NULL; struct mlx5_flow_table *ft; - int log_table_sz; int err; if (!root) { @@ -1101,7 +1100,6 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa */ ft = alloc_flow_table(ft_attr->level, vport, - ft_attr->max_fte ? roundup_pow_of_two(ft_attr->max_fte) : 0, root->table_type, op_mod, ft_attr->flags); if (IS_ERR(ft)) { @@ -1110,12 +1108,11 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa } tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table); - log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0; next_ft = unmanaged ? ft_attr->next_ft : find_next_chained_ft(fs_prio); ft->def_miss_action = ns->def_miss_action; ft->ns = ns; - err = root->cmds->create_flow_table(root, ft, log_table_sz, next_ft); + err = root->cmds->create_flow_table(root, ft, ft_attr->max_fte, next_ft); if (err) goto free_ft; @@ -1170,28 +1167,36 @@ mlx5_create_lag_demux_flow_table(struct mlx5_flow_namespace *ns, ft_attr.level = level; ft_attr.prio = prio; + ft_attr.max_fte = 1; + return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_LAG_DEMUX, 0); } EXPORT_SYMBOL(mlx5_create_lag_demux_flow_table); +#define MAX_FLOW_GROUP_SIZE BIT(24) struct mlx5_flow_table* mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, struct mlx5_flow_table_attr *ft_attr) { int num_reserved_entries = ft_attr->autogroup.num_reserved_entries; - int autogroups_max_fte = ft_attr->max_fte - num_reserved_entries; int max_num_groups = ft_attr->autogroup.max_num_groups; struct mlx5_flow_table *ft; - - if (max_num_groups > autogroups_max_fte) - return ERR_PTR(-EINVAL); - if (num_reserved_entries > ft_attr->max_fte) - return ERR_PTR(-EINVAL); + int autogroups_max_fte; ft = mlx5_create_flow_table(ns, ft_attr); if (IS_ERR(ft)) return ft; + autogroups_max_fte = ft->max_fte - num_reserved_entries; + if (max_num_groups > autogroups_max_fte) + goto err_validate; + if (num_reserved_entries > ft->max_fte) + goto err_validate; + + /* Align the number of groups according to the largest group size */ + if (autogroups_max_fte / (max_num_groups + 1) > MAX_FLOW_GROUP_SIZE) + max_num_groups = (autogroups_max_fte / MAX_FLOW_GROUP_SIZE) - 1; + ft->autogroup.active = true; ft->autogroup.required_groups = max_num_groups; ft->autogroup.max_fte = autogroups_max_fte; @@ -1199,6 +1204,10 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns, ft->autogroup.group_size = autogroups_max_fte / (max_num_groups + 1); return ft; + +err_validate: + mlx5_destroy_flow_table(ft); + return ERR_PTR(-ENOSPC); } EXPORT_SYMBOL(mlx5_create_auto_grouped_flow_table); @@ -1495,7 +1504,9 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR && d1->tir_num == d2->tir_num) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM && - d1->ft_num == d2->ft_num)) + d1->ft_num == d2->ft_num) || + (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER && + d1->sampler_id == d2->sampler_id)) return true; } @@ -2592,6 +2603,7 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev) mlx5_cleanup_fc_stats(dev); kmem_cache_destroy(steering->ftes_cache); kmem_cache_destroy(steering->fgs_cache); + mlx5_ft_pool_destroy(dev); kfree(steering); } @@ -2770,6 +2782,18 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) if (err) goto out_err; + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_TC_MISS, 1); + if (IS_ERR(maj_prio)) { + err = PTR_ERR(maj_prio); + goto out_err; + } + + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_BR_OFFLOAD, 3); + if (IS_ERR(maj_prio)) { + err = PTR_ERR(maj_prio); + goto out_err; + } + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_SLOW_PATH, 1); if (IS_ERR(maj_prio)) { err = PTR_ERR(maj_prio); @@ -2942,9 +2966,16 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) if (err) return err; + err = mlx5_ft_pool_init(dev); + if (err) + return err; + steering = kzalloc(sizeof(*steering), GFP_KERNEL); - if (!steering) - return -ENOMEM; + if (!steering) { + err = -ENOMEM; + goto err; + } + steering->dev = dev; dev->priv.steering = steering; @@ -3151,9 +3182,7 @@ void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, EXPORT_SYMBOL(mlx5_modify_header_dealloc); struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type ns_type) { struct mlx5_pkt_reformat *pkt_reformat; @@ -3169,9 +3198,8 @@ struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, return ERR_PTR(-ENOMEM); pkt_reformat->ns_type = ns_type; - pkt_reformat->reformat_type = reformat_type; - err = root->cmds->packet_reformat_alloc(root, reformat_type, size, - reformat_data, ns_type, + pkt_reformat->reformat_type = params->type; + err = root->cmds->packet_reformat_alloc(root, params, ns_type, pkt_reformat); if (err) { kfree(pkt_reformat); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index e577a2c424af..7317cdeab661 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -331,6 +331,7 @@ void mlx5_fs_ingress_acls_cleanup(struct mlx5_core_dev *dev); #define MLX5_CAP_FLOWTABLE_TYPE(mdev, cap, type) ( \ (type == FS_FT_NIC_RX) ? MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) : \ + (type == FS_FT_NIC_TX) ? MLX5_CAP_FLOWTABLE_NIC_TX(mdev, cap) : \ (type == FS_FT_ESW_EGRESS_ACL) ? MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) : \ (type == FS_FT_ESW_INGRESS_ACL) ? MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) : \ (type == FS_FT_FDB) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) : \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c new file mode 100644 index 000000000000..c14590acc772 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021 Mellanox Technologies. */ + +#include "fs_ft_pool.h" + +/* Firmware currently has 4 pool of 4 sizes that it supports (FT_POOLS), + * and a virtual memory region of 16M (MLX5_FT_SIZE), this region is duplicated + * for each flow table pool. We can allocate up to 16M of each pool, + * and we keep track of how much we used via mlx5_ft_pool_get_avail_sz. + * Firmware doesn't report any of this for now. + * ESW_POOL is expected to be sorted from large to small and match firmware + * pools. + */ +#define FT_SIZE (16 * 1024 * 1024) +static const unsigned int FT_POOLS[] = { 4 * 1024 * 1024, + 1 * 1024 * 1024, + 64 * 1024, + 128, + 1 /* size for termination tables */ }; +struct mlx5_ft_pool { + int ft_left[ARRAY_SIZE(FT_POOLS)]; +}; + +int mlx5_ft_pool_init(struct mlx5_core_dev *dev) +{ + struct mlx5_ft_pool *ft_pool; + int i; + + ft_pool = kzalloc(sizeof(*ft_pool), GFP_KERNEL); + if (!ft_pool) + return -ENOMEM; + + for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) + ft_pool->ft_left[i] = FT_SIZE / FT_POOLS[i]; + + dev->priv.ft_pool = ft_pool; + return 0; +} + +void mlx5_ft_pool_destroy(struct mlx5_core_dev *dev) +{ + kfree(dev->priv.ft_pool); +} + +int +mlx5_ft_pool_get_avail_sz(struct mlx5_core_dev *dev, enum fs_flow_table_type table_type, + int desired_size) +{ + u32 max_ft_size = 1 << MLX5_CAP_FLOWTABLE_TYPE(dev, log_max_ft_size, table_type); + int i, found_i = -1; + + for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) { + if (dev->priv.ft_pool->ft_left[i] && FT_POOLS[i] >= desired_size && + FT_POOLS[i] <= max_ft_size) { + found_i = i; + if (desired_size != POOL_NEXT_SIZE) + break; + } + } + + if (found_i != -1) { + --dev->priv.ft_pool->ft_left[found_i]; + return FT_POOLS[found_i]; + } + + return 0; +} + +void +mlx5_ft_pool_put_sz(struct mlx5_core_dev *dev, int sz) +{ + int i; + + if (!sz) + return; + + for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) { + if (sz == FT_POOLS[i]) { + ++dev->priv.ft_pool->ft_left[i]; + return; + } + } + + WARN_ONCE(1, "Couldn't find size %d in flow table size pool", sz); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h new file mode 100644 index 000000000000..25f4274b372b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#ifndef __MLX5_FS_FT_POOL_H__ +#define __MLX5_FS_FT_POOL_H__ + +#include +#include "fs_core.h" + +#define POOL_NEXT_SIZE 0 + +int mlx5_ft_pool_init(struct mlx5_core_dev *dev); +void mlx5_ft_pool_destroy(struct mlx5_core_dev *dev); + +int +mlx5_ft_pool_get_avail_sz(struct mlx5_core_dev *dev, enum fs_flow_table_type table_type, + int desired_size); +void +mlx5_ft_pool_put_sz(struct mlx5_core_dev *dev, int sz); + +#endif /* __MLX5_FS_FT_POOL_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 02558ac2ace6..016d26f809a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -148,6 +148,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) if (err) return err; + if (MLX5_CAP_GEN(dev, hca_cap_2)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL_2); + if (err) + return err; + } + if (MLX5_CAP_GEN(dev, eth_net_offloads)) { err = mlx5_core_get_caps(dev, MLX5_CAP_ETHERNET_OFFLOADS); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 97d96fc38a65..0e487ec57d5c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -150,6 +150,7 @@ enum mlx5_ptys_rate { MLX5_PTYS_RATE_FDR = 1 << 4, MLX5_PTYS_RATE_EDR = 1 << 5, MLX5_PTYS_RATE_HDR = 1 << 6, + MLX5_PTYS_RATE_NDR = 1 << 7, }; static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate) @@ -162,6 +163,7 @@ static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate) case MLX5_PTYS_RATE_FDR: return 14000; case MLX5_PTYS_RATE_EDR: return 25000; case MLX5_PTYS_RATE_HDR: return 50000; + case MLX5_PTYS_RATE_NDR: return 100000; default: return -1; } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index b8748390335f..5c043c5cc403 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -93,6 +93,64 @@ int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_cmd_destroy_vport_lag); +static int mlx5_lag_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr); +static void mlx5_do_bond_work(struct work_struct *work); + +static void mlx5_ldev_free(struct kref *ref) +{ + struct mlx5_lag *ldev = container_of(ref, struct mlx5_lag, ref); + + if (ldev->nb.notifier_call) + unregister_netdevice_notifier_net(&init_net, &ldev->nb); + mlx5_lag_mp_cleanup(ldev); + cancel_delayed_work_sync(&ldev->bond_work); + destroy_workqueue(ldev->wq); + kfree(ldev); +} + +static void mlx5_ldev_put(struct mlx5_lag *ldev) +{ + kref_put(&ldev->ref, mlx5_ldev_free); +} + +static void mlx5_ldev_get(struct mlx5_lag *ldev) +{ + kref_get(&ldev->ref); +} + +static struct mlx5_lag *mlx5_lag_dev_alloc(struct mlx5_core_dev *dev) +{ + struct mlx5_lag *ldev; + int err; + + ldev = kzalloc(sizeof(*ldev), GFP_KERNEL); + if (!ldev) + return NULL; + + ldev->wq = create_singlethread_workqueue("mlx5_lag"); + if (!ldev->wq) { + kfree(ldev); + return NULL; + } + + kref_init(&ldev->ref); + INIT_DELAYED_WORK(&ldev->bond_work, mlx5_do_bond_work); + + ldev->nb.notifier_call = mlx5_lag_netdev_event; + if (register_netdevice_notifier_net(&init_net, &ldev->nb)) { + ldev->nb.notifier_call = NULL; + mlx5_core_err(dev, "Failed to register LAG netdev notifier\n"); + } + + err = mlx5_lag_mp_init(ldev); + if (err) + mlx5_core_err(dev, "Failed to init multipath lag err=%d\n", + err); + + return ldev; +} + int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev, struct net_device *ndev) { @@ -118,17 +176,24 @@ static bool __mlx5_lag_is_sriov(struct mlx5_lag *ldev) static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker, u8 *port1, u8 *port2) { + bool p1en; + bool p2en; + + p1en = tracker->netdev_state[MLX5_LAG_P1].tx_enabled && + tracker->netdev_state[MLX5_LAG_P1].link_up; + + p2en = tracker->netdev_state[MLX5_LAG_P2].tx_enabled && + tracker->netdev_state[MLX5_LAG_P2].link_up; + *port1 = 1; *port2 = 2; - if (!tracker->netdev_state[MLX5_LAG_P1].tx_enabled || - !tracker->netdev_state[MLX5_LAG_P1].link_up) { - *port1 = 2; + if ((!p1en && !p2en) || (p1en && p2en)) return; - } - if (!tracker->netdev_state[MLX5_LAG_P2].tx_enabled || - !tracker->netdev_state[MLX5_LAG_P2].link_up) + if (p1en) *port2 = 1; + else + *port1 = 2; } void mlx5_modify_lag(struct mlx5_lag *ldev, @@ -251,6 +316,10 @@ static void mlx5_lag_add_devices(struct mlx5_lag *ldev) if (!ldev->pf[i].dev) continue; + if (ldev->pf[i].dev->priv.flags & + MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV) + continue; + ldev->pf[i].dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(ldev->pf[i].dev); } @@ -269,6 +338,31 @@ static void mlx5_lag_remove_devices(struct mlx5_lag *ldev) } } +static void mlx5_disable_lag(struct mlx5_lag *ldev) +{ + struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; + struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev; + bool roce_lag; + int err; + + roce_lag = __mlx5_lag_is_roce(ldev); + + if (roce_lag) { + if (!(dev0->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) { + dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; + mlx5_rescan_drivers_locked(dev0); + } + mlx5_nic_vport_disable_roce(dev1); + } + + err = mlx5_deactivate_lag(ldev); + if (err) + return; + + if (roce_lag) + mlx5_lag_add_devices(ldev); +} + static void mlx5_do_bond(struct mlx5_lag *ldev) { struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev; @@ -280,9 +374,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) if (!mlx5_lag_is_ready(ldev)) return; - spin_lock(&lag_lock); tracker = ldev->tracker; - spin_unlock(&lag_lock); do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev); @@ -291,8 +383,9 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) !mlx5_sriov_is_enabled(dev1); #ifdef CONFIG_MLX5_ESWITCH - roce_lag &= dev0->priv.eswitch->mode == MLX5_ESWITCH_NONE && - dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE; + roce_lag = roce_lag && + dev0->priv.eswitch->mode == MLX5_ESWITCH_NONE && + dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE; #endif if (roce_lag) @@ -316,20 +409,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) } else if (do_bond && __mlx5_lag_is_active(ldev)) { mlx5_modify_lag(ldev, &tracker); } else if (!do_bond && __mlx5_lag_is_active(ldev)) { - roce_lag = __mlx5_lag_is_roce(ldev); - - if (roce_lag) { - dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; - mlx5_rescan_drivers_locked(dev0); - mlx5_nic_vport_disable_roce(dev1); - } - - err = mlx5_deactivate_lag(ldev); - if (err) - return; - - if (roce_lag) - mlx5_lag_add_devices(ldev); + mlx5_disable_lag(ldev); } } @@ -481,9 +561,7 @@ static int mlx5_lag_netdev_event(struct notifier_block *this, break; } - spin_lock(&lag_lock); ldev->tracker = tracker; - spin_unlock(&lag_lock); if (changed) mlx5_queue_bond_work(ldev, 0); @@ -491,55 +569,52 @@ static int mlx5_lag_netdev_event(struct notifier_block *this, return NOTIFY_DONE; } -static struct mlx5_lag *mlx5_lag_dev_alloc(void) -{ - struct mlx5_lag *ldev; - - ldev = kzalloc(sizeof(*ldev), GFP_KERNEL); - if (!ldev) - return NULL; - - ldev->wq = create_singlethread_workqueue("mlx5_lag"); - if (!ldev->wq) { - kfree(ldev); - return NULL; - } - - INIT_DELAYED_WORK(&ldev->bond_work, mlx5_do_bond_work); - - return ldev; -} - -static void mlx5_lag_dev_free(struct mlx5_lag *ldev) -{ - destroy_workqueue(ldev->wq); - kfree(ldev); -} - -static int mlx5_lag_dev_add_pf(struct mlx5_lag *ldev, - struct mlx5_core_dev *dev, - struct net_device *netdev) +static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev, + struct mlx5_core_dev *dev, + struct net_device *netdev) { unsigned int fn = PCI_FUNC(dev->pdev->devfn); if (fn >= MLX5_MAX_PORTS) - return -EPERM; + return; spin_lock(&lag_lock); - ldev->pf[fn].dev = dev; ldev->pf[fn].netdev = netdev; ldev->tracker.netdev_state[fn].link_up = 0; ldev->tracker.netdev_state[fn].tx_enabled = 0; - - dev->priv.lag = ldev; - spin_unlock(&lag_lock); - - return fn; } -static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev, - struct mlx5_core_dev *dev) +static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev, + struct net_device *netdev) +{ + int i; + + spin_lock(&lag_lock); + for (i = 0; i < MLX5_MAX_PORTS; i++) { + if (ldev->pf[i].netdev == netdev) { + ldev->pf[i].netdev = NULL; + break; + } + } + spin_unlock(&lag_lock); +} + +static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev, + struct mlx5_core_dev *dev) +{ + unsigned int fn = PCI_FUNC(dev->pdev->devfn); + + if (fn >= MLX5_MAX_PORTS) + return; + + ldev->pf[fn].dev = dev; + dev->priv.lag = ldev; +} + +/* Must be called with intf_mutex held */ +static void mlx5_ldev_remove_mdev(struct mlx5_lag *ldev, + struct mlx5_core_dev *dev) { int i; @@ -550,19 +625,15 @@ static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev, if (i == MLX5_MAX_PORTS) return; - spin_lock(&lag_lock); - memset(&ldev->pf[i], 0, sizeof(*ldev->pf)); - + ldev->pf[i].dev = NULL; dev->priv.lag = NULL; - spin_unlock(&lag_lock); } /* Must be called with intf_mutex held */ -void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) +static void __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) { struct mlx5_lag *ldev = NULL; struct mlx5_core_dev *tmp_dev; - int i, err; if (!MLX5_CAP_GEN(dev, vport_group_manager) || !MLX5_CAP_GEN(dev, lag_master) || @@ -574,67 +645,77 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) ldev = tmp_dev->priv.lag; if (!ldev) { - ldev = mlx5_lag_dev_alloc(); + ldev = mlx5_lag_dev_alloc(dev); if (!ldev) { mlx5_core_err(dev, "Failed to alloc lag dev\n"); return; } + } else { + mlx5_ldev_get(ldev); } - if (mlx5_lag_dev_add_pf(ldev, dev, netdev) < 0) + mlx5_ldev_add_mdev(ldev, dev); + + return; +} + +void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev) +{ + struct mlx5_lag *ldev; + + ldev = mlx5_lag_dev(dev); + if (!ldev) return; + mlx5_dev_list_lock(); + mlx5_ldev_remove_mdev(ldev, dev); + mlx5_dev_list_unlock(); + mlx5_ldev_put(ldev); +} + +void mlx5_lag_add_mdev(struct mlx5_core_dev *dev) +{ + mlx5_dev_list_lock(); + __mlx5_lag_dev_add_mdev(dev); + mlx5_dev_list_unlock(); +} + +/* Must be called with intf_mutex held */ +void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev, + struct net_device *netdev) +{ + struct mlx5_lag *ldev; + + ldev = mlx5_lag_dev(dev); + if (!ldev) + return; + + if (__mlx5_lag_is_active(ldev)) + mlx5_disable_lag(ldev); + + mlx5_ldev_remove_netdev(ldev, netdev); + ldev->flags &= ~MLX5_LAG_FLAG_READY; +} + +/* Must be called with intf_mutex held */ +void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, + struct net_device *netdev) +{ + struct mlx5_lag *ldev; + int i; + + ldev = mlx5_lag_dev(dev); + if (!ldev) + return; + + mlx5_ldev_add_netdev(ldev, dev, netdev); + for (i = 0; i < MLX5_MAX_PORTS; i++) if (!ldev->pf[i].dev) break; if (i >= MLX5_MAX_PORTS) ldev->flags |= MLX5_LAG_FLAG_READY; - - if (!ldev->nb.notifier_call) { - ldev->nb.notifier_call = mlx5_lag_netdev_event; - if (register_netdevice_notifier_net(&init_net, &ldev->nb)) { - ldev->nb.notifier_call = NULL; - mlx5_core_err(dev, "Failed to register LAG netdev notifier\n"); - } - } - - err = mlx5_lag_mp_init(ldev); - if (err) - mlx5_core_err(dev, "Failed to init multipath lag err=%d\n", - err); -} - -/* Must be called with intf_mutex held */ -void mlx5_lag_remove(struct mlx5_core_dev *dev) -{ - struct mlx5_lag *ldev; - int i; - - ldev = mlx5_lag_dev_get(dev); - if (!ldev) - return; - - if (__mlx5_lag_is_active(ldev)) - mlx5_deactivate_lag(ldev); - - mlx5_lag_dev_remove_pf(ldev, dev); - - ldev->flags &= ~MLX5_LAG_FLAG_READY; - - for (i = 0; i < MLX5_MAX_PORTS; i++) - if (ldev->pf[i].dev) - break; - - if (i == MLX5_MAX_PORTS) { - if (ldev->nb.notifier_call) { - unregister_netdevice_notifier_net(&init_net, &ldev->nb); - ldev->nb.notifier_call = NULL; - } - mlx5_lag_mp_cleanup(ldev); - cancel_delayed_work_sync(&ldev->bond_work); - mlx5_lag_dev_free(ldev); - } } bool mlx5_lag_is_roce(struct mlx5_core_dev *dev) @@ -643,7 +724,7 @@ bool mlx5_lag_is_roce(struct mlx5_core_dev *dev) bool res; spin_lock(&lag_lock); - ldev = mlx5_lag_dev_get(dev); + ldev = mlx5_lag_dev(dev); res = ldev && __mlx5_lag_is_roce(ldev); spin_unlock(&lag_lock); @@ -657,7 +738,7 @@ bool mlx5_lag_is_active(struct mlx5_core_dev *dev) bool res; spin_lock(&lag_lock); - ldev = mlx5_lag_dev_get(dev); + ldev = mlx5_lag_dev(dev); res = ldev && __mlx5_lag_is_active(ldev); spin_unlock(&lag_lock); @@ -671,7 +752,7 @@ bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev) bool res; spin_lock(&lag_lock); - ldev = mlx5_lag_dev_get(dev); + ldev = mlx5_lag_dev(dev); res = ldev && __mlx5_lag_is_sriov(ldev); spin_unlock(&lag_lock); @@ -684,7 +765,7 @@ void mlx5_lag_update(struct mlx5_core_dev *dev) struct mlx5_lag *ldev; mlx5_dev_list_lock(); - ldev = mlx5_lag_dev_get(dev); + ldev = mlx5_lag_dev(dev); if (!ldev) goto unlock; @@ -700,7 +781,7 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev) struct mlx5_lag *ldev; spin_lock(&lag_lock); - ldev = mlx5_lag_dev_get(dev); + ldev = mlx5_lag_dev(dev); if (!(ldev && __mlx5_lag_is_roce(ldev))) goto unlock; @@ -729,7 +810,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, u8 port = 0; spin_lock(&lag_lock); - ldev = mlx5_lag_dev_get(dev); + ldev = mlx5_lag_dev(dev); if (!(ldev && __mlx5_lag_is_roce(ldev))) goto unlock; @@ -765,7 +846,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, memset(values, 0, sizeof(*values) * num_counters); spin_lock(&lag_lock); - ldev = mlx5_lag_dev_get(dev); + ldev = mlx5_lag_dev(dev); if (ldev && __mlx5_lag_is_active(ldev)) { num_ports = MLX5_MAX_PORTS; mdev[MLX5_LAG_P1] = ldev->pf[MLX5_LAG_P1].dev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h index 8d8cf2d0bc6d..191392c37558 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h @@ -40,6 +40,7 @@ struct lag_tracker { struct mlx5_lag { u8 flags; u8 v2p_map[MLX5_MAX_PORTS]; + struct kref ref; struct lag_func pf[MLX5_MAX_PORTS]; struct lag_tracker tracker; struct workqueue_struct *wq; @@ -49,7 +50,7 @@ struct mlx5_lag { }; static inline struct mlx5_lag * -mlx5_lag_dev_get(struct mlx5_core_dev *dev) +mlx5_lag_dev(struct mlx5_core_dev *dev) { return dev->priv.lag; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index fd6196b5e163..c4bf8b679541 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -28,7 +28,7 @@ bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev) struct mlx5_lag *ldev; bool res; - ldev = mlx5_lag_dev_get(dev); + ldev = mlx5_lag_dev(dev); res = ldev && __mlx5_lag_is_multipath(ldev); return res; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index f607a3858ef5..624cedebb510 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ -/* Copyright (c) 2018 Mellanox Technologies */ +/* Copyright (c) 2018-2021, Mellanox Technologies inc. All rights reserved. */ #ifndef __LIB_MLX5_EQ_H__ #define __LIB_MLX5_EQ_H__ @@ -32,6 +32,7 @@ struct mlx5_eq { unsigned int irqn; u8 eqn; struct mlx5_rsc_debug *dbg; + struct mlx5_irq *irq; }; struct mlx5_eq_async { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c index 20a4047f2737..97e5845b4cfd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c @@ -6,6 +6,7 @@ #include #include "lib/fs_chains.h" +#include "fs_ft_pool.h" #include "en/mapping.h" #include "fs_core.h" #include "en_tc.h" @@ -13,25 +14,10 @@ #define chains_lock(chains) ((chains)->lock) #define chains_ht(chains) ((chains)->chains_ht) #define prios_ht(chains) ((chains)->prios_ht) -#define ft_pool_left(chains) ((chains)->ft_left) #define tc_default_ft(chains) ((chains)->tc_default_ft) #define tc_end_ft(chains) ((chains)->tc_end_ft) #define ns_to_chains_fs_prio(ns) ((ns) == MLX5_FLOW_NAMESPACE_FDB ? \ FDB_TC_OFFLOAD : MLX5E_TC_PRIO) - -/* Firmware currently has 4 pool of 4 sizes that it supports (FT_POOLS), - * and a virtual memory region of 16M (MLX5_FT_SIZE), this region is duplicated - * for each flow table pool. We can allocate up to 16M of each pool, - * and we keep track of how much we used via get_next_avail_sz_from_pool. - * Firmware doesn't report any of this for now. - * ESW_POOL is expected to be sorted from large to small and match firmware - * pools. - */ -#define FT_SIZE (16 * 1024 * 1024) -static const unsigned int FT_POOLS[] = { 4 * 1024 * 1024, - 1 * 1024 * 1024, - 64 * 1024, - 128 }; #define FT_TBL_SZ (64 * 1024) struct mlx5_fs_chains { @@ -49,8 +35,6 @@ struct mlx5_fs_chains { enum mlx5_flow_namespace_type ns; u32 group_num; u32 flags; - - int ft_left[ARRAY_SIZE(FT_POOLS)]; }; struct fs_chain { @@ -160,54 +144,6 @@ mlx5_chains_set_end_ft(struct mlx5_fs_chains *chains, tc_end_ft(chains) = ft; } -#define POOL_NEXT_SIZE 0 -static int -mlx5_chains_get_avail_sz_from_pool(struct mlx5_fs_chains *chains, - int desired_size) -{ - int i, found_i = -1; - - for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) { - if (ft_pool_left(chains)[i] && FT_POOLS[i] > desired_size) { - found_i = i; - if (desired_size != POOL_NEXT_SIZE) - break; - } - } - - if (found_i != -1) { - --ft_pool_left(chains)[found_i]; - return FT_POOLS[found_i]; - } - - return 0; -} - -static void -mlx5_chains_put_sz_to_pool(struct mlx5_fs_chains *chains, int sz) -{ - int i; - - for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) { - if (sz == FT_POOLS[i]) { - ++ft_pool_left(chains)[i]; - return; - } - } - - WARN_ONCE(1, "Couldn't find size %d in flow table size pool", sz); -} - -static void -mlx5_chains_init_sz_pool(struct mlx5_fs_chains *chains, u32 ft_max) -{ - int i; - - for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) - ft_pool_left(chains)[i] = - FT_POOLS[i] <= ft_max ? FT_SIZE / FT_POOLS[i] : 0; -} - static struct mlx5_flow_table * mlx5_chains_create_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio, u32 level) @@ -221,11 +157,7 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains, ft_attr.flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT | MLX5_FLOW_TABLE_TUNNEL_EN_DECAP); - sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ? - mlx5_chains_get_avail_sz_from_pool(chains, FT_TBL_SZ) : - mlx5_chains_get_avail_sz_from_pool(chains, POOL_NEXT_SIZE); - if (!sz) - return ERR_PTR(-ENOSPC); + sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ? FT_TBL_SZ : POOL_NEXT_SIZE; ft_attr.max_fte = sz; /* We use tc_default_ft(chains) as the table's next_ft till @@ -266,21 +198,12 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains, if (IS_ERR(ft)) { mlx5_core_warn(chains->dev, "Failed to create chains table err %d (chain: %d, prio: %d, level: %d, size: %d)\n", (int)PTR_ERR(ft), chain, prio, level, sz); - mlx5_chains_put_sz_to_pool(chains, sz); return ft; } return ft; } -static void -mlx5_chains_destroy_table(struct mlx5_fs_chains *chains, - struct mlx5_flow_table *ft) -{ - mlx5_chains_put_sz_to_pool(chains, ft->max_fte); - mlx5_destroy_flow_table(ft); -} - static int create_chain_restore(struct fs_chain *chain) { @@ -336,9 +259,10 @@ create_chain_restore(struct fs_chain *chain) MLX5_SET(set_action_in, modact, field, mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mfield); MLX5_SET(set_action_in, modact, offset, - mlx5e_tc_attr_to_reg_mappings[chain_to_reg].moffset * 8); + mlx5e_tc_attr_to_reg_mappings[chain_to_reg].moffset); MLX5_SET(set_action_in, modact, length, - mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mlen * 8); + mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mlen == 32 ? + 0 : mlx5e_tc_attr_to_reg_mappings[chain_to_reg].mlen); MLX5_SET(set_action_in, modact, data, chain->id); mod_hdr = mlx5_modify_header_alloc(chains->dev, chains->ns, 1, modact); @@ -636,7 +560,7 @@ err_insert: err_miss_rule: mlx5_destroy_flow_group(miss_group); err_group: - mlx5_chains_destroy_table(chains, ft); + mlx5_destroy_flow_table(ft); err_create: err_alloc: kvfree(prio_s); @@ -659,7 +583,7 @@ mlx5_chains_destroy_prio(struct mlx5_fs_chains *chains, prio_params); mlx5_del_flow_rules(prio->miss_rule); mlx5_destroy_flow_group(prio->miss_group); - mlx5_chains_destroy_table(chains, prio->ft); + mlx5_destroy_flow_table(prio->ft); mlx5_chains_put_chain(chain); kvfree(prio); } @@ -784,7 +708,7 @@ void mlx5_chains_destroy_global_table(struct mlx5_fs_chains *chains, struct mlx5_flow_table *ft) { - mlx5_chains_destroy_table(chains, ft); + mlx5_destroy_flow_table(ft); } static struct mlx5_fs_chains * @@ -816,8 +740,6 @@ mlx5_chains_init(struct mlx5_core_dev *dev, struct mlx5_chains_attr *attr) mlx5_chains_get_chain_range(chains_priv), mlx5_chains_get_prio_range(chains_priv)); - mlx5_chains_init_sz_pool(chains_priv, attr->max_ft_sz); - err = rhashtable_init(&chains_ht(chains_priv), &chain_params); if (err) goto init_chains_ht_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/sf.h new file mode 100644 index 000000000000..84e5683861be --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sf.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies Ltd */ + +#ifndef __LIB_MLX5_SF_H__ +#define __LIB_MLX5_SF_H__ + +#include + +static inline u16 mlx5_sf_start_function_id(const struct mlx5_core_dev *dev) +{ + return MLX5_CAP_GEN(dev, sf_base_id); +} + +#ifdef CONFIG_MLX5_SF + +static inline bool mlx5_sf_supported(const struct mlx5_core_dev *dev) +{ + return MLX5_CAP_GEN(dev, sf); +} + +static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev) +{ + if (!mlx5_sf_supported(dev)) + return 0; + if (MLX5_CAP_GEN(dev, max_num_sf)) + return MLX5_CAP_GEN(dev, max_num_sf); + else + return 1 << MLX5_CAP_GEN(dev, log_max_sf); +} + +#else + +static inline bool mlx5_sf_supported(const struct mlx5_core_dev *dev) +{ + return false; +} + +static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev) +{ + return 0; +} + +#endif + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 0d0f63a27aba..eb1b316560a8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -76,6 +76,7 @@ #include "sf/vhca_event.h" #include "sf/dev/dev.h" #include "sf/sf.h" +#include "mlx5_irq.h" MODULE_AUTHOR("Eli Cohen "); MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver"); @@ -1185,6 +1186,7 @@ static int mlx5_load(struct mlx5_core_dev *dev) } mlx5_sf_dev_table_create(dev); + mlx5_lag_add_mdev(dev); return 0; @@ -1220,6 +1222,7 @@ err_irq_table: static void mlx5_unload(struct mlx5_core_dev *dev) { + mlx5_lag_remove_mdev(dev); mlx5_sf_dev_table_destroy(dev); mlx5_sriov_detach(dev); mlx5_ec_cleanup(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index a22b706eebd3..343807ac2036 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -164,27 +164,10 @@ int mlx5_query_mcam_reg(struct mlx5_core_dev *dev, u32 *mcap, u8 feature_group, int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam, u8 feature_group, u8 access_reg_group); -void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev); -void mlx5_lag_remove(struct mlx5_core_dev *dev); - -int mlx5_irq_table_init(struct mlx5_core_dev *dev); -void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev); -int mlx5_irq_table_create(struct mlx5_core_dev *dev); -void mlx5_irq_table_destroy(struct mlx5_core_dev *dev); -int mlx5_irq_attach_nb(struct mlx5_irq_table *irq_table, int vecidx, - struct notifier_block *nb); -int mlx5_irq_detach_nb(struct mlx5_irq_table *irq_table, int vecidx, - struct notifier_block *nb); - -int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int devfn, - int msix_vec_count); -int mlx5_get_default_msix_vec_count(struct mlx5_core_dev *dev, int num_vfs); - -struct cpumask * -mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx); -struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *table); -int mlx5_irq_get_num_comp(struct mlx5_irq_table *table); -struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev); +void mlx5_lag_add_netdev(struct mlx5_core_dev *dev, struct net_device *netdev); +void mlx5_lag_remove_netdev(struct mlx5_core_dev *dev, struct net_device *netdev); +void mlx5_lag_add_mdev(struct mlx5_core_dev *dev); +void mlx5_lag_remove_mdev(struct mlx5_core_dev *dev); int mlx5_events_init(struct mlx5_core_dev *dev); void mlx5_events_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h new file mode 100644 index 000000000000..abd024173c42 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021 Mellanox Technologies. */ + +#ifndef __MLX5_IRQ_H__ +#define __MLX5_IRQ_H__ + +#include + +#define MLX5_COMP_EQS_PER_SF 8 + +#define MLX5_IRQ_EQ_CTRL (0) + +struct mlx5_irq; + +int mlx5_irq_table_init(struct mlx5_core_dev *dev); +void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev); +int mlx5_irq_table_create(struct mlx5_core_dev *dev); +void mlx5_irq_table_destroy(struct mlx5_core_dev *dev); +int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table); +int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table); +struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev); + +int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int devfn, + int msix_vec_count); +int mlx5_get_default_msix_vec_count(struct mlx5_core_dev *dev, int num_vfs); + +struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, u16 vecidx, + struct cpumask *affinity); +void mlx5_irq_release(struct mlx5_irq *irq); +int mlx5_irq_attach_nb(struct mlx5_irq *irq, struct notifier_block *nb); +int mlx5_irq_detach_nb(struct mlx5_irq *irq, struct notifier_block *nb); +struct cpumask *mlx5_irq_get_affinity_mask(struct mlx5_irq *irq); +int mlx5_irq_get_index(struct mlx5_irq *irq); + +#endif /* __MLX5_IRQ_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index c3373fb1cd7f..b25f764daa08 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -6,61 +6,53 @@ #include #include #include "mlx5_core.h" +#include "mlx5_irq.h" +#include "lib/sf.h" #ifdef CONFIG_RFS_ACCEL #include #endif #define MLX5_MAX_IRQ_NAME (32) +/* max irq_index is 255. three chars */ +#define MLX5_MAX_IRQ_IDX_CHARS (3) + +#define MLX5_SFS_PER_CTRL_IRQ 64 +#define MLX5_IRQ_CTRL_SF_MAX 8 +/* min num of vectores for SFs to be enabled */ +#define MLX5_IRQ_VEC_COMP_BASE_SF 2 + +#define MLX5_EQ_SHARE_IRQ_MAX_COMP (8) +#define MLX5_EQ_SHARE_IRQ_MAX_CTRL (UINT_MAX) +#define MLX5_EQ_SHARE_IRQ_MIN_COMP (1) +#define MLX5_EQ_SHARE_IRQ_MIN_CTRL (4) +#define MLX5_EQ_REFS_PER_IRQ (2) struct mlx5_irq { + u32 index; struct atomic_notifier_head nh; cpumask_var_t mask; char name[MLX5_MAX_IRQ_NAME]; + struct kref kref; + int irqn; + struct mlx5_irq_pool *pool; +}; + +struct mlx5_irq_pool { + char name[MLX5_MAX_IRQ_NAME - MLX5_MAX_IRQ_IDX_CHARS]; + struct xa_limit xa_num_irqs; + struct mutex lock; /* sync IRQs creations */ + struct xarray irqs; + u32 max_threshold; + u32 min_threshold; + struct mlx5_core_dev *dev; }; struct mlx5_irq_table { - struct mlx5_irq *irq; - int nvec; -#ifdef CONFIG_RFS_ACCEL - struct cpu_rmap *rmap; -#endif + struct mlx5_irq_pool *pf_pool; + struct mlx5_irq_pool *sf_ctrl_pool; + struct mlx5_irq_pool *sf_comp_pool; }; -int mlx5_irq_table_init(struct mlx5_core_dev *dev) -{ - struct mlx5_irq_table *irq_table; - - if (mlx5_core_is_sf(dev)) - return 0; - - irq_table = kvzalloc(sizeof(*irq_table), GFP_KERNEL); - if (!irq_table) - return -ENOMEM; - - dev->priv.irq_table = irq_table; - return 0; -} - -void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev) -{ - if (mlx5_core_is_sf(dev)) - return; - - kvfree(dev->priv.irq_table); -} - -int mlx5_irq_get_num_comp(struct mlx5_irq_table *table) -{ - return table->nvec - MLX5_IRQ_VEC_COMP_BASE; -} - -static struct mlx5_irq *mlx5_irq_get(struct mlx5_core_dev *dev, int vecidx) -{ - struct mlx5_irq_table *irq_table = dev->priv.irq_table; - - return &irq_table->irq[vecidx]; -} - /** * mlx5_get_default_msix_vec_count - Get the default number of MSI-X vectors * to be ssigned to each VF. @@ -146,34 +138,46 @@ out: return ret; } -int mlx5_irq_attach_nb(struct mlx5_irq_table *irq_table, int vecidx, - struct notifier_block *nb) +static void irq_release(struct kref *kref) { - struct mlx5_irq *irq; + struct mlx5_irq *irq = container_of(kref, struct mlx5_irq, kref); + struct mlx5_irq_pool *pool = irq->pool; - irq = &irq_table->irq[vecidx]; - return atomic_notifier_chain_register(&irq->nh, nb); + xa_erase(&pool->irqs, irq->index); + /* free_irq requires that affinity and rmap will be cleared + * before calling it. This is why there is asymmetry with set_rmap + * which should be called after alloc_irq but before request_irq. + */ + irq_set_affinity_hint(irq->irqn, NULL); + free_cpumask_var(irq->mask); + free_irq(irq->irqn, &irq->nh); + kfree(irq); } -int mlx5_irq_detach_nb(struct mlx5_irq_table *irq_table, int vecidx, - struct notifier_block *nb) +static void irq_put(struct mlx5_irq *irq) { - struct mlx5_irq *irq; + struct mlx5_irq_pool *pool = irq->pool; - irq = &irq_table->irq[vecidx]; - return atomic_notifier_chain_unregister(&irq->nh, nb); + mutex_lock(&pool->lock); + kref_put(&irq->kref, irq_release); + mutex_unlock(&pool->lock); } -static irqreturn_t mlx5_irq_int_handler(int irq, void *nh) +static irqreturn_t irq_int_handler(int irq, void *nh) { atomic_notifier_call_chain(nh, 0, NULL); return IRQ_HANDLED; } +static void irq_sf_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx) +{ + snprintf(name, MLX5_MAX_IRQ_NAME, "%s%d", pool->name, vecidx); +} + static void irq_set_name(char *name, int vecidx) { if (vecidx == 0) { - snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async"); + snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async%d", vecidx); return; } @@ -181,251 +185,431 @@ static void irq_set_name(char *name, int vecidx) vecidx - MLX5_IRQ_VEC_COMP_BASE); } -static int request_irqs(struct mlx5_core_dev *dev, int nvec) +static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i) { + struct mlx5_core_dev *dev = pool->dev; char name[MLX5_MAX_IRQ_NAME]; + struct mlx5_irq *irq; int err; - int i; - - for (i = 0; i < nvec; i++) { - struct mlx5_irq *irq = mlx5_irq_get(dev, i); - int irqn = pci_irq_vector(dev->pdev, i); + irq = kzalloc(sizeof(*irq), GFP_KERNEL); + if (!irq) + return ERR_PTR(-ENOMEM); + irq->irqn = pci_irq_vector(dev->pdev, i); + if (!pool->name[0]) irq_set_name(name, i); - ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh); - snprintf(irq->name, MLX5_MAX_IRQ_NAME, - "%s@pci:%s", name, pci_name(dev->pdev)); - err = request_irq(irqn, mlx5_irq_int_handler, 0, irq->name, - &irq->nh); - if (err) { - mlx5_core_err(dev, "Failed to request irq\n"); - goto err_request_irq; - } + else + irq_sf_set_name(pool, name, i); + ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh); + snprintf(irq->name, MLX5_MAX_IRQ_NAME, + "%s@pci:%s", name, pci_name(dev->pdev)); + err = request_irq(irq->irqn, irq_int_handler, 0, irq->name, + &irq->nh); + if (err) { + mlx5_core_err(dev, "Failed to request irq. err = %d\n", err); + goto err_req_irq; } - return 0; - -err_request_irq: - while (i--) { - struct mlx5_irq *irq = mlx5_irq_get(dev, i); - int irqn = pci_irq_vector(dev->pdev, i); - - free_irq(irqn, &irq->nh); - } - return err; -} - -static void irq_clear_rmap(struct mlx5_core_dev *dev) -{ -#ifdef CONFIG_RFS_ACCEL - struct mlx5_irq_table *irq_table = dev->priv.irq_table; - - free_irq_cpu_rmap(irq_table->rmap); -#endif -} - -static int irq_set_rmap(struct mlx5_core_dev *mdev) -{ - int err = 0; -#ifdef CONFIG_RFS_ACCEL - struct mlx5_irq_table *irq_table = mdev->priv.irq_table; - int num_affinity_vec; - int vecidx; - - num_affinity_vec = mlx5_irq_get_num_comp(irq_table); - irq_table->rmap = alloc_irq_cpu_rmap(num_affinity_vec); - if (!irq_table->rmap) { - err = -ENOMEM; - mlx5_core_err(mdev, "Failed to allocate cpu_rmap. err %d", err); - goto err_out; - } - - vecidx = MLX5_IRQ_VEC_COMP_BASE; - for (; vecidx < irq_table->nvec; vecidx++) { - err = irq_cpu_rmap_add(irq_table->rmap, - pci_irq_vector(mdev->pdev, vecidx)); - if (err) { - mlx5_core_err(mdev, "irq_cpu_rmap_add failed. err %d", - err); - goto err_irq_cpu_rmap_add; - } - } - return 0; - -err_irq_cpu_rmap_add: - irq_clear_rmap(mdev); -err_out: -#endif - return err; -} - -/* Completion IRQ vectors */ - -static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i) -{ - int vecidx = MLX5_IRQ_VEC_COMP_BASE + i; - struct mlx5_irq *irq; - int irqn; - - irq = mlx5_irq_get(mdev, vecidx); - irqn = pci_irq_vector(mdev->pdev, vecidx); if (!zalloc_cpumask_var(&irq->mask, GFP_KERNEL)) { - mlx5_core_warn(mdev, "zalloc_cpumask_var failed"); - return -ENOMEM; + mlx5_core_warn(dev, "zalloc_cpumask_var failed\n"); + err = -ENOMEM; + goto err_cpumask; } - - cpumask_set_cpu(cpumask_local_spread(i, mdev->priv.numa_node), - irq->mask); - if (IS_ENABLED(CONFIG_SMP) && - irq_set_affinity_hint(irqn, irq->mask)) - mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", - irqn); - - return 0; -} - -static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i) -{ - int vecidx = MLX5_IRQ_VEC_COMP_BASE + i; - struct mlx5_irq *irq; - int irqn; - - irq = mlx5_irq_get(mdev, vecidx); - irqn = pci_irq_vector(mdev->pdev, vecidx); - irq_set_affinity_hint(irqn, NULL); + kref_init(&irq->kref); + irq->index = i; + err = xa_err(xa_store(&pool->irqs, irq->index, irq, GFP_KERNEL)); + if (err) { + mlx5_core_err(dev, "Failed to alloc xa entry for irq(%u). err = %d\n", + irq->index, err); + goto err_xa; + } + irq->pool = pool; + return irq; +err_xa: free_cpumask_var(irq->mask); +err_cpumask: + free_irq(irq->irqn, &irq->nh); +err_req_irq: + kfree(irq); + return ERR_PTR(err); } -static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev) +int mlx5_irq_attach_nb(struct mlx5_irq *irq, struct notifier_block *nb) { - int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table); int err; - int i; - - for (i = 0; i < nvec; i++) { - err = set_comp_irq_affinity_hint(mdev, i); - if (err) - goto err_out; - } - - return 0; - -err_out: - for (i--; i >= 0; i--) - clear_comp_irq_affinity_hint(mdev, i); + err = kref_get_unless_zero(&irq->kref); + if (WARN_ON_ONCE(!err)) + /* Something very bad happens here, we are enabling EQ + * on non-existing IRQ. + */ + return -ENOENT; + err = atomic_notifier_chain_register(&irq->nh, nb); + if (err) + irq_put(irq); return err; } -static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev) +int mlx5_irq_detach_nb(struct mlx5_irq *irq, struct notifier_block *nb) { - int nvec = mlx5_irq_get_num_comp(mdev->priv.irq_table); - int i; - - for (i = 0; i < nvec; i++) - clear_comp_irq_affinity_hint(mdev, i); + irq_put(irq); + return atomic_notifier_chain_unregister(&irq->nh, nb); } -struct cpumask * -mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx) +struct cpumask *mlx5_irq_get_affinity_mask(struct mlx5_irq *irq) { - return irq_table->irq[vecidx].mask; + return irq->mask; } -#ifdef CONFIG_RFS_ACCEL -struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *irq_table) +int mlx5_irq_get_index(struct mlx5_irq *irq) { - return irq_table->rmap; + return irq->index; } -#endif -static void unrequest_irqs(struct mlx5_core_dev *dev) +/* irq_pool API */ + +/* creating an irq from irq_pool */ +static struct mlx5_irq *irq_pool_create_irq(struct mlx5_irq_pool *pool, + struct cpumask *affinity) +{ + struct mlx5_irq *irq; + u32 irq_index; + int err; + + err = xa_alloc(&pool->irqs, &irq_index, NULL, pool->xa_num_irqs, + GFP_KERNEL); + if (err) + return ERR_PTR(err); + irq = irq_request(pool, irq_index); + if (IS_ERR(irq)) + return irq; + cpumask_copy(irq->mask, affinity); + irq_set_affinity_hint(irq->irqn, irq->mask); + return irq; +} + +/* looking for the irq with the smallest refcount and the same affinity */ +static struct mlx5_irq *irq_pool_find_least_loaded(struct mlx5_irq_pool *pool, + struct cpumask *affinity) +{ + int start = pool->xa_num_irqs.min; + int end = pool->xa_num_irqs.max; + struct mlx5_irq *irq = NULL; + struct mlx5_irq *iter; + unsigned long index; + + lockdep_assert_held(&pool->lock); + xa_for_each_range(&pool->irqs, index, iter, start, end) { + if (!cpumask_equal(iter->mask, affinity)) + continue; + if (kref_read(&iter->kref) < pool->min_threshold) + return iter; + if (!irq || kref_read(&iter->kref) < + kref_read(&irq->kref)) + irq = iter; + } + return irq; +} + +/* requesting an irq from a given pool according to given affinity */ +static struct mlx5_irq *irq_pool_request_affinity(struct mlx5_irq_pool *pool, + struct cpumask *affinity) +{ + struct mlx5_irq *least_loaded_irq, *new_irq; + + mutex_lock(&pool->lock); + least_loaded_irq = irq_pool_find_least_loaded(pool, affinity); + if (least_loaded_irq && + kref_read(&least_loaded_irq->kref) < pool->min_threshold) + goto out; + new_irq = irq_pool_create_irq(pool, affinity); + if (IS_ERR(new_irq)) { + if (!least_loaded_irq) { + mlx5_core_err(pool->dev, "Didn't find IRQ for cpu = %u\n", + cpumask_first(affinity)); + mutex_unlock(&pool->lock); + return new_irq; + } + /* We failed to create a new IRQ for the requested affinity, + * sharing existing IRQ. + */ + goto out; + } + least_loaded_irq = new_irq; + goto unlock; +out: + kref_get(&least_loaded_irq->kref); + if (kref_read(&least_loaded_irq->kref) > pool->max_threshold) + mlx5_core_dbg(pool->dev, "IRQ %u overloaded, pool_name: %s, %u EQs on this irq\n", + least_loaded_irq->irqn, pool->name, + kref_read(&least_loaded_irq->kref) / MLX5_EQ_REFS_PER_IRQ); +unlock: + mutex_unlock(&pool->lock); + return least_loaded_irq; +} + +/* requesting an irq from a given pool according to given index */ +static struct mlx5_irq * +irq_pool_request_vector(struct mlx5_irq_pool *pool, int vecidx, + struct cpumask *affinity) +{ + struct mlx5_irq *irq; + + mutex_lock(&pool->lock); + irq = xa_load(&pool->irqs, vecidx); + if (irq) { + kref_get(&irq->kref); + goto unlock; + } + irq = irq_request(pool, vecidx); + if (IS_ERR(irq) || !affinity) + goto unlock; + cpumask_copy(irq->mask, affinity); + irq_set_affinity_hint(irq->irqn, irq->mask); +unlock: + mutex_unlock(&pool->lock); + return irq; +} + +static struct mlx5_irq_pool *find_sf_irq_pool(struct mlx5_irq_table *irq_table, + int i, struct cpumask *affinity) +{ + if (cpumask_empty(affinity) && i == MLX5_IRQ_EQ_CTRL) + return irq_table->sf_ctrl_pool; + return irq_table->sf_comp_pool; +} + +/** + * mlx5_irq_release - release an IRQ back to the system. + * @irq: irq to be released. + */ +void mlx5_irq_release(struct mlx5_irq *irq) +{ + synchronize_irq(irq->irqn); + irq_put(irq); +} + +/** + * mlx5_irq_request - request an IRQ for mlx5 device. + * @dev: mlx5 device that requesting the IRQ. + * @vecidx: vector index of the IRQ. This argument is ignore if affinity is + * provided. + * @affinity: cpumask requested for this IRQ. + * + * This function returns a pointer to IRQ, or ERR_PTR in case of error. + */ +struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, u16 vecidx, + struct cpumask *affinity) +{ + struct mlx5_irq_table *irq_table = mlx5_irq_table_get(dev); + struct mlx5_irq_pool *pool; + struct mlx5_irq *irq; + + if (mlx5_core_is_sf(dev)) { + pool = find_sf_irq_pool(irq_table, vecidx, affinity); + if (!pool) + /* we don't have IRQs for SFs, using the PF IRQs */ + goto pf_irq; + if (cpumask_empty(affinity) && !strcmp(pool->name, "mlx5_sf_comp")) + /* In case an SF user request IRQ with vecidx */ + irq = irq_pool_request_vector(pool, vecidx, NULL); + else + irq = irq_pool_request_affinity(pool, affinity); + goto out; + } +pf_irq: + pool = irq_table->pf_pool; + irq = irq_pool_request_vector(pool, vecidx, affinity); +out: + if (IS_ERR(irq)) + return irq; + mlx5_core_dbg(dev, "irq %u mapped to cpu %*pbl, %u EQs on this irq\n", + irq->irqn, cpumask_pr_args(affinity), + kref_read(&irq->kref) / MLX5_EQ_REFS_PER_IRQ); + return irq; +} + +static struct mlx5_irq_pool * +irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name, + u32 min_threshold, u32 max_threshold) +{ + struct mlx5_irq_pool *pool = kvzalloc(sizeof(*pool), GFP_KERNEL); + + if (!pool) + return ERR_PTR(-ENOMEM); + pool->dev = dev; + xa_init_flags(&pool->irqs, XA_FLAGS_ALLOC); + pool->xa_num_irqs.min = start; + pool->xa_num_irqs.max = start + size - 1; + if (name) + snprintf(pool->name, MLX5_MAX_IRQ_NAME - MLX5_MAX_IRQ_IDX_CHARS, + name); + pool->min_threshold = min_threshold * MLX5_EQ_REFS_PER_IRQ; + pool->max_threshold = max_threshold * MLX5_EQ_REFS_PER_IRQ; + mutex_init(&pool->lock); + mlx5_core_dbg(dev, "pool->name = %s, pool->size = %d, pool->start = %d", + name, size, start); + return pool; +} + +static void irq_pool_free(struct mlx5_irq_pool *pool) +{ + struct mlx5_irq *irq; + unsigned long index; + + xa_for_each(&pool->irqs, index, irq) + irq_release(&irq->kref); + xa_destroy(&pool->irqs); + kvfree(pool); +} + +static int irq_pools_init(struct mlx5_core_dev *dev, int sf_vec, int pf_vec) { struct mlx5_irq_table *table = dev->priv.irq_table; - int i; + int num_sf_ctrl_by_msix; + int num_sf_ctrl_by_sfs; + int num_sf_ctrl; + int err; - for (i = 0; i < table->nvec; i++) - free_irq(pci_irq_vector(dev->pdev, i), - &mlx5_irq_get(dev, i)->nh); + /* init pf_pool */ + table->pf_pool = irq_pool_alloc(dev, 0, pf_vec, NULL, + MLX5_EQ_SHARE_IRQ_MIN_COMP, + MLX5_EQ_SHARE_IRQ_MAX_COMP); + if (IS_ERR(table->pf_pool)) + return PTR_ERR(table->pf_pool); + if (!mlx5_sf_max_functions(dev)) + return 0; + if (sf_vec < MLX5_IRQ_VEC_COMP_BASE_SF) { + mlx5_core_err(dev, "Not enough IRQs for SFs. SF may run at lower performance\n"); + return 0; + } + + /* init sf_ctrl_pool */ + num_sf_ctrl_by_msix = DIV_ROUND_UP(sf_vec, MLX5_COMP_EQS_PER_SF); + num_sf_ctrl_by_sfs = DIV_ROUND_UP(mlx5_sf_max_functions(dev), + MLX5_SFS_PER_CTRL_IRQ); + num_sf_ctrl = min_t(int, num_sf_ctrl_by_msix, num_sf_ctrl_by_sfs); + num_sf_ctrl = min_t(int, MLX5_IRQ_CTRL_SF_MAX, num_sf_ctrl); + table->sf_ctrl_pool = irq_pool_alloc(dev, pf_vec, num_sf_ctrl, + "mlx5_sf_ctrl", + MLX5_EQ_SHARE_IRQ_MIN_CTRL, + MLX5_EQ_SHARE_IRQ_MAX_CTRL); + if (IS_ERR(table->sf_ctrl_pool)) { + err = PTR_ERR(table->sf_ctrl_pool); + goto err_pf; + } + /* init sf_comp_pool */ + table->sf_comp_pool = irq_pool_alloc(dev, pf_vec + num_sf_ctrl, + sf_vec - num_sf_ctrl, "mlx5_sf_comp", + MLX5_EQ_SHARE_IRQ_MIN_COMP, + MLX5_EQ_SHARE_IRQ_MAX_COMP); + if (IS_ERR(table->sf_comp_pool)) { + err = PTR_ERR(table->sf_comp_pool); + goto err_sf_ctrl; + } + return 0; +err_sf_ctrl: + irq_pool_free(table->sf_ctrl_pool); +err_pf: + irq_pool_free(table->pf_pool); + return err; +} + +static void irq_pools_destroy(struct mlx5_irq_table *table) +{ + if (table->sf_ctrl_pool) { + irq_pool_free(table->sf_comp_pool); + irq_pool_free(table->sf_ctrl_pool); + } + irq_pool_free(table->pf_pool); +} + +/* irq_table API */ + +int mlx5_irq_table_init(struct mlx5_core_dev *dev) +{ + struct mlx5_irq_table *irq_table; + + if (mlx5_core_is_sf(dev)) + return 0; + + irq_table = kvzalloc(sizeof(*irq_table), GFP_KERNEL); + if (!irq_table) + return -ENOMEM; + + dev->priv.irq_table = irq_table; + return 0; +} + +void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev) +{ + if (mlx5_core_is_sf(dev)) + return; + + kvfree(dev->priv.irq_table); +} + +int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table) +{ + return table->pf_pool->xa_num_irqs.max - table->pf_pool->xa_num_irqs.min; } int mlx5_irq_table_create(struct mlx5_core_dev *dev) { - struct mlx5_priv *priv = &dev->priv; - struct mlx5_irq_table *table = priv->irq_table; int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ? MLX5_CAP_GEN(dev, max_num_eqs) : 1 << MLX5_CAP_GEN(dev, log_max_eq); - int nvec; + int total_vec; + int pf_vec; int err; if (mlx5_core_is_sf(dev)) return 0; - nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + - MLX5_IRQ_VEC_COMP_BASE; - nvec = min_t(int, nvec, num_eqs); - if (nvec <= MLX5_IRQ_VEC_COMP_BASE) + pf_vec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + + MLX5_IRQ_VEC_COMP_BASE; + pf_vec = min_t(int, pf_vec, num_eqs); + if (pf_vec <= MLX5_IRQ_VEC_COMP_BASE) return -ENOMEM; - table->irq = kcalloc(nvec, sizeof(*table->irq), GFP_KERNEL); - if (!table->irq) - return -ENOMEM; + total_vec = pf_vec; + if (mlx5_sf_max_functions(dev)) + total_vec += MLX5_IRQ_CTRL_SF_MAX + + MLX5_COMP_EQS_PER_SF * mlx5_sf_max_functions(dev); - nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_IRQ_VEC_COMP_BASE + 1, - nvec, PCI_IRQ_MSIX); - if (nvec < 0) { - err = nvec; - goto err_free_irq; - } + total_vec = pci_alloc_irq_vectors(dev->pdev, MLX5_IRQ_VEC_COMP_BASE + 1, + total_vec, PCI_IRQ_MSIX); + if (total_vec < 0) + return total_vec; + pf_vec = min(pf_vec, total_vec); - table->nvec = nvec; - - err = irq_set_rmap(dev); + err = irq_pools_init(dev, total_vec - pf_vec, pf_vec); if (err) - goto err_set_rmap; + pci_free_irq_vectors(dev->pdev); - err = request_irqs(dev, nvec); - if (err) - goto err_request_irqs; - - err = set_comp_irq_affinity_hints(dev); - if (err) { - mlx5_core_err(dev, "Failed to alloc affinity hint cpumask\n"); - goto err_set_affinity; - } - - return 0; - -err_set_affinity: - unrequest_irqs(dev); -err_request_irqs: - irq_clear_rmap(dev); -err_set_rmap: - pci_free_irq_vectors(dev->pdev); -err_free_irq: - kfree(table->irq); return err; } void mlx5_irq_table_destroy(struct mlx5_core_dev *dev) { struct mlx5_irq_table *table = dev->priv.irq_table; - int i; if (mlx5_core_is_sf(dev)) return; - /* free_irq requires that affinity and rmap will be cleared - * before calling it. This is why there is asymmetry with set_rmap - * which should be called after alloc_irq but before request_irq. + /* There are cases where IRQs still will be in used when we reaching + * to here. Hence, making sure all the irqs are realeased. */ - irq_clear_rmap(dev); - clear_comp_irqs_affinity_hints(dev); - for (i = 0; i < table->nvec; i++) - free_irq(pci_irq_vector(dev->pdev, i), - &mlx5_irq_get(dev, i)->nh); + irq_pools_destroy(table); pci_free_irq_vectors(dev->pdev); - kfree(table->irq); +} + +int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table) +{ + if (table->sf_comp_pool) + return table->sf_comp_pool->xa_num_irqs.max - + table->sf_comp_pool->xa_num_irqs.min + 1; + else + return mlx5_irq_table_get_num_comp(table); } struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c index ef5f892aafad..d9c69123c1ab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c @@ -6,7 +6,6 @@ #include "sf.h" #include "mlx5_ifc_vhca_event.h" #include "ecpf.h" -#include "vhca_event.h" #include "mlx5_core.h" #include "eswitch.h" @@ -74,26 +73,29 @@ static int mlx5_sf_hw_table_id_alloc(struct mlx5_sf_hw_table *table, u32 control u32 usr_sfnum) { struct mlx5_sf_hwc_table *hwc; + int free_idx = -1; int i; hwc = mlx5_sf_controller_to_hwc(table->dev, controller); if (!hwc->sfs) return -ENOSPC; - /* Check if sf with same sfnum already exists or not. */ for (i = 0; i < hwc->max_fn; i++) { + if (!hwc->sfs[i].allocated && free_idx == -1) { + free_idx = i; + continue; + } + if (hwc->sfs[i].allocated && hwc->sfs[i].usr_sfnum == usr_sfnum) return -EEXIST; } - /* Find the free entry and allocate the entry from the array */ - for (i = 0; i < hwc->max_fn; i++) { - if (!hwc->sfs[i].allocated) { - hwc->sfs[i].usr_sfnum = usr_sfnum; - hwc->sfs[i].allocated = true; - return i; - } - } - return -ENOSPC; + + if (free_idx == -1) + return -ENOSPC; + + hwc->sfs[free_idx].usr_sfnum = usr_sfnum; + hwc->sfs[free_idx].allocated = true; + return free_idx; } static void mlx5_sf_hw_table_id_free(struct mlx5_sf_hw_table *table, u32 controller, int id) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h index 0b6aea1e6a94..81ce13b19ee8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h @@ -5,42 +5,7 @@ #define __MLX5_SF_H__ #include - -static inline u16 mlx5_sf_start_function_id(const struct mlx5_core_dev *dev) -{ - return MLX5_CAP_GEN(dev, sf_base_id); -} - -#ifdef CONFIG_MLX5_SF - -static inline bool mlx5_sf_supported(const struct mlx5_core_dev *dev) -{ - return MLX5_CAP_GEN(dev, sf); -} - -static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev) -{ - if (!mlx5_sf_supported(dev)) - return 0; - if (MLX5_CAP_GEN(dev, max_num_sf)) - return MLX5_CAP_GEN(dev, max_num_sf); - else - return 1 << MLX5_CAP_GEN(dev, log_max_sf); -} - -#else - -static inline bool mlx5_sf_supported(const struct mlx5_core_dev *dev) -{ - return false; -} - -static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev) -{ - return 0; -} - -#endif +#include "lib/sf.h" #ifdef CONFIG_MLX5_SF_MANAGER diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 2338989d4403..e8185b69ac6c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -34,6 +34,7 @@ #include #include #include "mlx5_core.h" +#include "mlx5_irq.h" #include "eswitch.h" static int sriov_restore_guids(struct mlx5_core_dev *dev, int vf) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index 949879cf2092..6475ba35cf6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019 Mellanox Technologies. */ #include "dr_types.h" +#include "dr_ste.h" enum dr_action_domain { DR_ACTION_DOMAIN_NIC_INGRESS, @@ -14,7 +15,8 @@ enum dr_action_domain { enum dr_action_valid_state { DR_ACTION_STATE_ERR, DR_ACTION_STATE_NO_ACTION, - DR_ACTION_STATE_REFORMAT, + DR_ACTION_STATE_ENCAP, + DR_ACTION_STATE_DECAP, DR_ACTION_STATE_MODIFY_HDR, DR_ACTION_STATE_MODIFY_VLAN, DR_ACTION_STATE_NON_TERM, @@ -29,46 +31,74 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, - [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, }, - [DR_ACTION_STATE_REFORMAT] = { + [DR_ACTION_STATE_DECAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, - [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, }, + [DR_ACTION_STATE_ENCAP] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ENCAP, + }, [DR_ACTION_STATE_MODIFY_HDR] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, }, [DR_ACTION_STATE_MODIFY_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, }, [DR_ACTION_STATE_NON_TERM] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, - [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, }, @@ -80,39 +110,48 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NO_ACTION] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, - [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, }, - [DR_ACTION_STATE_REFORMAT] = { + [DR_ACTION_STATE_ENCAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, - [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ENCAP, }, [DR_ACTION_STATE_MODIFY_HDR] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, - [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, }, [DR_ACTION_STATE_MODIFY_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, - [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, }, [DR_ACTION_STATE_NON_TERM] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, - [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, }, @@ -124,41 +163,69 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NO_ACTION] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, - [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, }, - [DR_ACTION_STATE_REFORMAT] = { + [DR_ACTION_STATE_DECAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, - [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, + }, + [DR_ACTION_STATE_ENCAP] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ENCAP, }, [DR_ACTION_STATE_MODIFY_HDR] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, }, [DR_ACTION_STATE_MODIFY_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, }, [DR_ACTION_STATE_NON_TERM] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, - [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_DECAP, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, @@ -171,44 +238,53 @@ next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] [DR_ACTION_STATE_NO_ACTION] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, - [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, }, - [DR_ACTION_STATE_REFORMAT] = { + [DR_ACTION_STATE_ENCAP] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, - [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, }, [DR_ACTION_STATE_MODIFY_HDR] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, - [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, }, [DR_ACTION_STATE_MODIFY_VLAN] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, - [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, }, [DR_ACTION_STATE_NON_TERM] = { [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_SAMPLER] = DR_ACTION_STATE_TERM, [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, - [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, - [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_ENCAP, + [DR_ACTION_TYP_INSERT_HDR] = DR_ACTION_STATE_ENCAP, [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, }, @@ -235,6 +311,9 @@ dr_action_reformat_to_action_type(enum mlx5dr_action_reformat_type reformat_type case DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3: *action_type = DR_ACTION_TYP_L2_TO_TNL_L3; break; + case DR_ACTION_REFORMAT_TYP_INSERT_HDR: + *action_type = DR_ACTION_TYP_INSERT_HDR; + break; default: return -EINVAL; } @@ -454,8 +533,17 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, break; case DR_ACTION_TYP_L2_TO_TNL_L2: case DR_ACTION_TYP_L2_TO_TNL_L3: - attr.reformat_size = action->reformat->reformat_size; - attr.reformat_id = action->reformat->reformat_id; + if (rx_rule && + !(dmn->ste_ctx->actions_caps & DR_STE_CTX_ACTION_CAP_RX_ENCAP)) { + mlx5dr_info(dmn, "Device doesn't support Encap on RX\n"); + goto out_invalid_arg; + } + attr.reformat.size = action->reformat->size; + attr.reformat.id = action->reformat->id; + break; + case DR_ACTION_TYP_SAMPLER: + attr.final_icm_addr = rx_rule ? action->sampler->rx_icm_addr : + action->sampler->tx_icm_addr; break; case DR_ACTION_TYP_VPORT: attr.hit_gvmi = action->vport->caps->vhca_gvmi; @@ -481,6 +569,12 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, attr.vlans.headers[attr.vlans.count++] = action->push_vlan->vlan_hdr; break; + case DR_ACTION_TYP_INSERT_HDR: + attr.reformat.size = action->reformat->size; + attr.reformat.id = action->reformat->id; + attr.reformat.param_0 = action->reformat->param_0; + attr.reformat.param_1 = action->reformat->param_1; + break; default: goto out_invalid_arg; } @@ -543,6 +637,8 @@ static unsigned int action_size[DR_ACTION_TYP_MAX] = { [DR_ACTION_TYP_MODIFY_HDR] = sizeof(struct mlx5dr_action_rewrite), [DR_ACTION_TYP_VPORT] = sizeof(struct mlx5dr_action_vport), [DR_ACTION_TYP_PUSH_VLAN] = sizeof(struct mlx5dr_action_push_vlan), + [DR_ACTION_TYP_INSERT_HDR] = sizeof(struct mlx5dr_action_reformat), + [DR_ACTION_TYP_SAMPLER] = sizeof(struct mlx5dr_action_sampler), }; static struct mlx5dr_action * @@ -651,7 +747,7 @@ mlx5dr_action_create_mult_dest_tbl(struct mlx5dr_domain *dmn, if (reformat_action) { reformat_req = true; hw_dests[i].vport.reformat_id = - reformat_action->reformat->reformat_id; + reformat_action->reformat->id; ref_actions[num_of_ref++] = reformat_action; hw_dests[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID; } @@ -755,14 +851,43 @@ struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value) return action; } +struct mlx5dr_action * +mlx5dr_action_create_flow_sampler(struct mlx5dr_domain *dmn, u32 sampler_id) +{ + struct mlx5dr_action *action; + u64 icm_rx, icm_tx; + int ret; + + ret = mlx5dr_cmd_query_flow_sampler(dmn->mdev, sampler_id, + &icm_rx, &icm_tx); + if (ret) + return NULL; + + action = dr_action_create_generic(DR_ACTION_TYP_SAMPLER); + if (!action) + return NULL; + + action->sampler->dmn = dmn; + action->sampler->sampler_id = sampler_id; + action->sampler->rx_icm_addr = icm_rx; + action->sampler->tx_icm_addr = icm_tx; + + refcount_inc(&dmn->refcount); + return action; +} + static int dr_action_verify_reformat_params(enum mlx5dr_action_type reformat_type, struct mlx5dr_domain *dmn, + u8 reformat_param_0, + u8 reformat_param_1, size_t data_sz, void *data) { - if ((!data && data_sz) || (data && !data_sz) || reformat_type > - DR_ACTION_TYP_L2_TO_TNL_L3) { + if ((!data && data_sz) || (data && !data_sz) || + ((reformat_param_0 || reformat_param_1) && + reformat_type != DR_ACTION_TYP_INSERT_HDR) || + reformat_type > DR_ACTION_TYP_INSERT_HDR) { mlx5dr_dbg(dmn, "Invalid reformat parameter!\n"); goto out_err; } @@ -794,6 +919,7 @@ out_err: static int dr_action_create_reformat_action(struct mlx5dr_domain *dmn, + u8 reformat_param_0, u8 reformat_param_1, size_t data_sz, void *data, struct mlx5dr_action *action) { @@ -811,13 +937,14 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn, else rt = MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL; - ret = mlx5dr_cmd_create_reformat_ctx(dmn->mdev, rt, data_sz, data, + ret = mlx5dr_cmd_create_reformat_ctx(dmn->mdev, rt, 0, 0, + data_sz, data, &reformat_id); if (ret) return ret; - action->reformat->reformat_id = reformat_id; - action->reformat->reformat_size = data_sz; + action->reformat->id = reformat_id; + action->reformat->size = data_sz; return 0; } case DR_ACTION_TYP_TNL_L2_TO_L2: @@ -859,6 +986,23 @@ dr_action_create_reformat_action(struct mlx5dr_domain *dmn, } return 0; } + case DR_ACTION_TYP_INSERT_HDR: + { + ret = mlx5dr_cmd_create_reformat_ctx(dmn->mdev, + MLX5_REFORMAT_TYPE_INSERT_HDR, + reformat_param_0, + reformat_param_1, + data_sz, data, + &reformat_id); + if (ret) + return ret; + + action->reformat->id = reformat_id; + action->reformat->size = data_sz; + action->reformat->param_0 = reformat_param_0; + action->reformat->param_1 = reformat_param_1; + return 0; + } default: mlx5dr_info(dmn, "Reformat type is not supported %d\n", action->action_type); return -EINVAL; @@ -896,6 +1040,8 @@ struct mlx5dr_action *mlx5dr_action_create_push_vlan(struct mlx5dr_domain *dmn, struct mlx5dr_action * mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn, enum mlx5dr_action_reformat_type reformat_type, + u8 reformat_param_0, + u8 reformat_param_1, size_t data_sz, void *data) { @@ -912,7 +1058,9 @@ mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn, goto dec_ref; } - ret = dr_action_verify_reformat_params(action_type, dmn, data_sz, data); + ret = dr_action_verify_reformat_params(action_type, dmn, + reformat_param_0, reformat_param_1, + data_sz, data); if (ret) goto dec_ref; @@ -923,6 +1071,8 @@ mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn, action->reformat->dmn = dmn; ret = dr_action_create_reformat_action(dmn, + reformat_param_0, + reformat_param_1, data_sz, data, action); @@ -1516,8 +1666,9 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action) break; case DR_ACTION_TYP_L2_TO_TNL_L2: case DR_ACTION_TYP_L2_TO_TNL_L3: + case DR_ACTION_TYP_INSERT_HDR: mlx5dr_cmd_destroy_reformat_ctx((action->reformat->dmn)->mdev, - action->reformat->reformat_id); + action->reformat->id); refcount_dec(&action->reformat->dmn->refcount); break; case DR_ACTION_TYP_MODIFY_HDR: @@ -1525,6 +1676,9 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action) kfree(action->rewrite->data); refcount_dec(&action->rewrite->dmn->refcount); break; + case DR_ACTION_TYP_SAMPLER: + refcount_dec(&action->sampler->dmn->refcount); + break; default: break; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 5970cb8fc0c0..54e1f5438bbe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -228,6 +228,36 @@ int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev, return 0; } +int mlx5dr_cmd_query_flow_sampler(struct mlx5_core_dev *dev, + u32 sampler_id, + u64 *rx_icm_addr, + u64 *tx_icm_addr) +{ + u32 out[MLX5_ST_SZ_DW(query_sampler_obj_out)] = {}; + u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {}; + void *attr; + int ret; + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_QUERY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, + MLX5_GENERAL_OBJECT_TYPES_SAMPLER); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, sampler_id); + + ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (ret) + return ret; + + attr = MLX5_ADDR_OF(query_sampler_obj_out, out, sampler_object); + + *rx_icm_addr = MLX5_GET64(sampler_obj, attr, + sw_steering_icm_address_rx); + *tx_icm_addr = MLX5_GET64(sampler_obj, attr, + sw_steering_icm_address_tx); + + return 0; +} + int mlx5dr_cmd_sync_steering(struct mlx5_core_dev *mdev) { u32 in[MLX5_ST_SZ_DW(sync_steering_in)] = {}; @@ -460,6 +490,8 @@ int mlx5dr_cmd_destroy_flow_table(struct mlx5_core_dev *mdev, int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev, enum mlx5_reformat_ctx_type rt, + u8 reformat_param_0, + u8 reformat_param_1, size_t reformat_size, void *reformat_data, u32 *reformat_id) @@ -486,8 +518,11 @@ int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev, pdata = MLX5_ADDR_OF(packet_reformat_context_in, prctx, reformat_data); MLX5_SET(packet_reformat_context_in, prctx, reformat_type, rt); + MLX5_SET(packet_reformat_context_in, prctx, reformat_param_0, reformat_param_0); + MLX5_SET(packet_reformat_context_in, prctx, reformat_param_1, reformat_param_1); MLX5_SET(packet_reformat_context_in, prctx, reformat_data_size, reformat_size); - memcpy(pdata, reformat_data, reformat_size); + if (reformat_data && reformat_size) + memcpy(pdata, reformat_data, reformat_size); err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); if (err) @@ -706,6 +741,9 @@ int mlx5dr_cmd_set_fte(struct mlx5_core_dev *dev, fte->dest_arr[i].vport.reformat_id); } break; + case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER: + id = fte->dest_arr[i].sampler_id; + break; default: id = fte->dest_arr[i].tir_num; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h index 992b591bf0c5..12a8bbbf944b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h @@ -156,6 +156,7 @@ struct mlx5dr_ste_ctx { u16 (*get_byte_mask)(u8 *hw_ste_p); /* Actions */ + u32 actions_caps; void (*set_actions_rx)(struct mlx5dr_domain *dmn, u8 *action_type_set, u8 *hw_ste_arr, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index 0757a4e8540e..f1950e4968da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -437,8 +437,8 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn, attr->gvmi); dr_ste_v0_set_tx_encap(last_ste, - attr->reformat_id, - attr->reformat_size, + attr->reformat.id, + attr->reformat.size, action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]); /* Whenever prio_tag_required enabled, we can be sure that the * previous table (ACL) already push vlan to our packet, @@ -1893,6 +1893,7 @@ struct mlx5dr_ste_ctx ste_ctx_v0 = { .get_byte_mask = &dr_ste_v0_get_byte_mask, /* Actions */ + .actions_caps = DR_STE_CTX_ACTION_CAP_NONE, .set_actions_rx = &dr_ste_v0_set_actions_rx, .set_actions_tx = &dr_ste_v0_set_actions_tx, .modify_field_arr_sz = ARRAY_SIZE(dr_ste_v0_action_modify_field_arr), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index 7466f016375c..4aaca8eb7597 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -116,6 +116,8 @@ enum { DR_STE_V1_ACTION_MDFY_FLD_IPV6_SRC_OUT_3 = 0x4f, DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_0 = 0x5e, DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_1 = 0x5f, + DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_0 = 0x6f, + DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_1 = 0x70, DR_STE_V1_ACTION_MDFY_FLD_METADATA_2_CQE = 0x7b, DR_STE_V1_ACTION_MDFY_FLD_GNRL_PURPOSE = 0x7c, DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2 = 0x8c, @@ -246,6 +248,12 @@ static const struct mlx5dr_ste_action_modify_field dr_ste_v1_action_modify_field [MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = { .hw_field = DR_STE_V1_ACTION_MDFY_FLD_L2_OUT_2, .start = 0, .end = 15, }, + [MLX5_ACTION_IN_FIELD_OUT_EMD_31_0] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_EMD_47_32] = { + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_0, .start = 0, .end = 15, + }, }; static void dr_ste_v1_set_entry_type(u8 *hw_ste_p, u8 entry_type) @@ -361,8 +369,8 @@ static void dr_ste_v1_set_reparse(u8 *hw_ste_p) MLX5_SET(ste_match_bwc_v1, hw_ste_p, reparse, 1); } -static void dr_ste_v1_set_tx_encap(u8 *hw_ste_p, u8 *d_action, - u32 reformat_id, int size) +static void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action, + u32 reformat_id, int size) { MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, action_id, DR_STE_V1_ACTION_ID_INSERT_POINTER); @@ -374,6 +382,26 @@ static void dr_ste_v1_set_tx_encap(u8 *hw_ste_p, u8 *d_action, dr_ste_v1_set_reparse(hw_ste_p); } +static void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action, + u32 reformat_id, + u8 anchor, u8 offset, + int size) +{ + MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, + action_id, DR_STE_V1_ACTION_ID_INSERT_POINTER); + MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, start_anchor, anchor); + + /* The hardware expects here size and offset in words (2 byte) */ + MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, size, size / 2); + MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, start_offset, offset / 2); + + MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, pointer, reformat_id); + MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action, attributes, + DR_STE_V1_ACTION_INSERT_PTR_ATTR_NONE); + + dr_ste_v1_set_reparse(hw_ste_p); +} + static void dr_ste_v1_set_tx_push_vlan(u8 *hw_ste_p, u8 *d_action, u32 vlan_hdr) { @@ -401,11 +429,11 @@ static void dr_ste_v1_set_rx_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num) dr_ste_v1_set_reparse(hw_ste_p); } -static void dr_ste_v1_set_tx_encap_l3(u8 *hw_ste_p, - u8 *frst_s_action, - u8 *scnd_d_action, - u32 reformat_id, - int size) +static void dr_ste_v1_set_encap_l3(u8 *hw_ste_p, + u8 *frst_s_action, + u8 *scnd_d_action, + u32 reformat_id, + int size) { /* Remove L2 headers */ MLX5_SET(ste_single_action_remove_header_v1, frst_s_action, action_id, @@ -519,9 +547,9 @@ static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, action_sz = DR_STE_ACTION_TRIPLE_SZ; allow_encap = true; } - dr_ste_v1_set_tx_encap(last_ste, action, - attr->reformat_id, - attr->reformat_size); + dr_ste_v1_set_encap(last_ste, action, + attr->reformat.id, + attr->reformat.size); action_sz -= DR_STE_ACTION_DOUBLE_SZ; action += DR_STE_ACTION_DOUBLE_SZ; } else if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]) { @@ -532,12 +560,25 @@ static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, action_sz = DR_STE_ACTION_TRIPLE_SZ; d_action = action + DR_STE_ACTION_SINGLE_SZ; - dr_ste_v1_set_tx_encap_l3(last_ste, - action, d_action, - attr->reformat_id, - attr->reformat_size); + dr_ste_v1_set_encap_l3(last_ste, + action, d_action, + attr->reformat.id, + attr->reformat.size); action_sz -= DR_STE_ACTION_TRIPLE_SZ; action += DR_STE_ACTION_TRIPLE_SZ; + } else if (action_type_set[DR_ACTION_TYP_INSERT_HDR]) { + if (!allow_encap || action_sz < DR_STE_ACTION_DOUBLE_SZ) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + } + dr_ste_v1_set_insert_hdr(last_ste, action, + attr->reformat.id, + attr->reformat.param_0, + attr->reformat.param_1, + attr->reformat.size); + action_sz -= DR_STE_ACTION_DOUBLE_SZ; + action += DR_STE_ACTION_DOUBLE_SZ; } dr_ste_v1_set_hit_gvmi(last_ste, attr->hit_gvmi); @@ -616,7 +657,9 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, } if (action_type_set[DR_ACTION_TYP_CTR]) { - /* Counter action set after decap to exclude decaped header */ + /* Counter action set after decap and before insert_hdr + * to exclude decaped / encaped header respectively. + */ if (!allow_ctr) { dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); @@ -627,6 +670,52 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, dr_ste_v1_set_counter_id(last_ste, attr->ctr_id); } + if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L2]) { + if (action_sz < DR_STE_ACTION_DOUBLE_SZ) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + } + dr_ste_v1_set_encap(last_ste, action, + attr->reformat.id, + attr->reformat.size); + action_sz -= DR_STE_ACTION_DOUBLE_SZ; + action += DR_STE_ACTION_DOUBLE_SZ; + allow_modify_hdr = false; + } else if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]) { + u8 *d_action; + + if (action_sz < DR_STE_ACTION_TRIPLE_SZ) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + } + + d_action = action + DR_STE_ACTION_SINGLE_SZ; + + dr_ste_v1_set_encap_l3(last_ste, + action, d_action, + attr->reformat.id, + attr->reformat.size); + action_sz -= DR_STE_ACTION_TRIPLE_SZ; + allow_modify_hdr = false; + } else if (action_type_set[DR_ACTION_TYP_INSERT_HDR]) { + /* Modify header, decap, and encap must use different STEs */ + if (!allow_modify_hdr || action_sz < DR_STE_ACTION_DOUBLE_SZ) { + dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); + action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); + action_sz = DR_STE_ACTION_TRIPLE_SZ; + } + dr_ste_v1_set_insert_hdr(last_ste, action, + attr->reformat.id, + attr->reformat.param_0, + attr->reformat.param_1, + attr->reformat.size); + action_sz -= DR_STE_ACTION_DOUBLE_SZ; + action += DR_STE_ACTION_DOUBLE_SZ; + allow_modify_hdr = false; + } + dr_ste_v1_set_hit_gvmi(last_ste, attr->hit_gvmi); dr_ste_v1_set_hit_addr(last_ste, attr->final_icm_addr, 1); } @@ -1871,6 +1960,7 @@ struct mlx5dr_ste_ctx ste_ctx_v1 = { .set_byte_mask = &dr_ste_v1_set_byte_mask, .get_byte_mask = &dr_ste_v1_get_byte_mask, /* Actions */ + .actions_caps = DR_STE_CTX_ACTION_CAP_RX_ENCAP, .set_actions_rx = &dr_ste_v1_set_actions_rx, .set_actions_tx = &dr_ste_v1_set_actions_tx, .modify_field_arr_sz = ARRAY_SIZE(dr_ste_v1_action_modify_field_arr), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 67460c42a99b..f5e93fa87aff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -89,6 +89,11 @@ enum { DR_STE_SIZE_REDUCED = DR_STE_SIZE - DR_STE_SIZE_MASK, }; +enum mlx5dr_ste_ctx_action_cap { + DR_STE_CTX_ACTION_CAP_NONE = 0, + DR_STE_CTX_ACTION_CAP_RX_ENCAP = 1 << 0, +}; + enum { DR_MODIFY_ACTION_SIZE = 8, }; @@ -118,6 +123,8 @@ enum mlx5dr_action_type { DR_ACTION_TYP_VPORT, DR_ACTION_TYP_POP_VLAN, DR_ACTION_TYP_PUSH_VLAN, + DR_ACTION_TYP_INSERT_HDR, + DR_ACTION_TYP_SAMPLER, DR_ACTION_TYP_MAX, }; @@ -261,8 +268,12 @@ struct mlx5dr_ste_actions_attr { u32 ctr_id; u16 gvmi; u16 hit_gvmi; - u32 reformat_id; - u32 reformat_size; + struct { + u32 id; + u32 size; + u8 param_0; + u8 param_1; + } reformat; struct { int count; u32 headers[MLX5DR_MAX_VLANS]; @@ -903,8 +914,17 @@ struct mlx5dr_action_rewrite { struct mlx5dr_action_reformat { struct mlx5dr_domain *dmn; - u32 reformat_id; - u32 reformat_size; + u32 id; + u32 size; + u8 param_0; + u8 param_1; +}; + +struct mlx5dr_action_sampler { + struct mlx5dr_domain *dmn; + u64 rx_icm_addr; + u64 tx_icm_addr; + u32 sampler_id; }; struct mlx5dr_action_dest_tbl { @@ -950,6 +970,7 @@ struct mlx5dr_action { void *data; struct mlx5dr_action_rewrite *rewrite; struct mlx5dr_action_reformat *reformat; + struct mlx5dr_action_sampler *sampler; struct mlx5dr_action_dest_tbl *dest_tbl; struct mlx5dr_action_ctr *ctr; struct mlx5dr_action_vport *vport; @@ -1104,6 +1125,10 @@ int mlx5dr_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_vport, u16 vport_number, u16 *gvmi); int mlx5dr_cmd_query_esw_caps(struct mlx5_core_dev *mdev, struct mlx5dr_esw_caps *caps); +int mlx5dr_cmd_query_flow_sampler(struct mlx5_core_dev *dev, + u32 sampler_id, + u64 *rx_icm_addr, + u64 *tx_icm_addr); int mlx5dr_cmd_sync_steering(struct mlx5_core_dev *mdev); int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev, u32 table_type, @@ -1142,6 +1167,8 @@ int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev, struct mlx5dr_cmd_query_flow_table_details *output); int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev, enum mlx5_reformat_ctx_type rt, + u8 reformat_param_0, + u8 reformat_param_1, size_t reformat_size, void *reformat_data, u32 *reformat_id); @@ -1252,7 +1279,6 @@ struct mlx5dr_send_ring { u32 tx_head; void *buf; u32 buf_size; - struct ib_wc wc[MAX_SEND_CQE]; u8 sync_buff[MIN_READ_SYNC]; struct mlx5dr_mr *sync_mr; spinlock_t lock; /* Protect the data path of the send ring */ @@ -1290,6 +1316,7 @@ struct mlx5dr_cmd_flow_destination_hw_info { u32 ft_num; u32 ft_id; u32 counter_id; + u32 sampler_id; struct { u16 num; u16 vhca_id; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 96c39a17d026..d5926dd7e972 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -62,7 +62,7 @@ static int set_miss_action(struct mlx5_flow_root_namespace *ns, static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, - unsigned int log_size, + unsigned int size, struct mlx5_flow_table *next_ft) { struct mlx5dr_table *tbl; @@ -71,7 +71,7 @@ static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns, if (mlx5_dr_is_fw_table(ft->flags)) return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft, - log_size, + size, next_ft); flags = ft->flags; /* turn off encap/decap if not supported for sw-str by fw */ @@ -97,6 +97,8 @@ static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns, } } + ft->max_fte = INT_MAX; + return 0; } @@ -287,7 +289,8 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2; tmp_action = mlx5dr_action_create_packet_reformat(domain, - decap_type, 0, + decap_type, + 0, 0, 0, NULL); if (!tmp_action) { err = -ENOMEM; @@ -384,7 +387,7 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { list_for_each_entry(dst, &fte->node.children, node.list) { enum mlx5_flow_destination_type type = dst->dest_attr.type; - u32 ft_id; + u32 id; if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || num_term_actions >= MLX5_FLOW_CONTEXT_ACTION_MAX) { @@ -422,9 +425,20 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, num_term_actions++; break; case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM: - ft_id = dst->dest_attr.ft_num; + id = dst->dest_attr.ft_num; tmp_action = mlx5dr_action_create_dest_table_num(domain, - ft_id); + id); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + term_actions[num_term_actions++].dest = tmp_action; + break; + case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER: + id = dst->dest_attr.sampler_id; + tmp_action = mlx5dr_action_create_flow_sampler(domain, + id); if (!tmp_action) { err = -ENOMEM; goto free_actions; @@ -520,9 +534,7 @@ out_err: } static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type namespace, struct mlx5_pkt_reformat *pkt_reformat) { @@ -530,7 +542,7 @@ static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns struct mlx5dr_action *action; int dr_reformat; - switch (reformat_type) { + switch (params->type) { case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: case MLX5_REFORMAT_TYPE_L2_TO_NVGRE: case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: @@ -542,16 +554,21 @@ static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: dr_reformat = DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3; break; + case MLX5_REFORMAT_TYPE_INSERT_HDR: + dr_reformat = DR_ACTION_REFORMAT_TYP_INSERT_HDR; + break; default: mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n", - reformat_type); + params->type); return -EOPNOTSUPP; } action = mlx5dr_action_create_packet_reformat(dr_domain, dr_reformat, - size, - reformat_data); + params->param_0, + params->param_1, + params->size, + params->data); if (!action) { mlx5_core_err(ns->dev, "Failed allocating packet-reformat action\n"); return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 9737565cd8d4..bbfe101d4e57 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -26,6 +26,7 @@ enum mlx5dr_action_reformat_type { DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2, DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2, DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3, + DR_ACTION_REFORMAT_TYP_INSERT_HDR, }; struct mlx5dr_match_parameters { @@ -99,12 +100,17 @@ struct mlx5dr_action *mlx5dr_action_create_drop(void); struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value); +struct mlx5dr_action * +mlx5dr_action_create_flow_sampler(struct mlx5dr_domain *dmn, u32 sampler_id); + struct mlx5dr_action * mlx5dr_action_create_flow_counter(u32 counter_id); struct mlx5dr_action * mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn, enum mlx5dr_action_reformat_type reformat_type, + u8 reformat_param_0, + u8 reformat_param_1, size_t data_sz, void *data); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/Kconfig b/drivers/net/ethernet/mellanox/mlxbf_gige/Kconfig new file mode 100644 index 000000000000..4cdebafaf222 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/Kconfig @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause +# +# Mellanox GigE driver configuration +# + +config MLXBF_GIGE + tristate "Mellanox Technologies BlueField Gigabit Ethernet support" + depends on (ARM64 && ACPI) || COMPILE_TEST + select PHYLIB + help + The second generation BlueField SoC from Mellanox Technologies + supports an out-of-band Gigabit Ethernet management port to the + Arm subsystem. diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/Makefile b/drivers/net/ethernet/mellanox/mlxbf_gige/Makefile new file mode 100644 index 000000000000..e57c1375f236 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause + +obj-$(CONFIG_MLXBF_GIGE) += mlxbf_gige.o + +mlxbf_gige-y := mlxbf_gige_ethtool.o \ + mlxbf_gige_gpio.o \ + mlxbf_gige_intr.o \ + mlxbf_gige_main.o \ + mlxbf_gige_mdio.o \ + mlxbf_gige_rx.o \ + mlxbf_gige_tx.o diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h new file mode 100644 index 000000000000..e3509e69ed1c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h @@ -0,0 +1,190 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause */ + +/* Header file for Gigabit Ethernet driver for Mellanox BlueField SoC + * - this file contains software data structures and any chip-specific + * data structures (e.g. TX WQE format) that are memory resident. + * + * Copyright (C) 2020-2021 NVIDIA CORPORATION & AFFILIATES + */ + +#ifndef __MLXBF_GIGE_H__ +#define __MLXBF_GIGE_H__ + +#include +#include +#include +#include + +/* The silicon design supports a maximum RX ring size of + * 32K entries. Based on current testing this maximum size + * is not required to be supported. Instead the RX ring + * will be capped at a realistic value of 1024 entries. + */ +#define MLXBF_GIGE_MIN_RXQ_SZ 32 +#define MLXBF_GIGE_MAX_RXQ_SZ 1024 +#define MLXBF_GIGE_DEFAULT_RXQ_SZ 128 + +#define MLXBF_GIGE_MIN_TXQ_SZ 4 +#define MLXBF_GIGE_MAX_TXQ_SZ 256 +#define MLXBF_GIGE_DEFAULT_TXQ_SZ 128 + +#define MLXBF_GIGE_DEFAULT_BUF_SZ 2048 + +#define MLXBF_GIGE_DMA_PAGE_SZ 4096 +#define MLXBF_GIGE_DMA_PAGE_SHIFT 12 + +/* There are four individual MAC RX filters. Currently + * two of them are being used: one for the broadcast MAC + * (index 0) and one for local MAC (index 1) + */ +#define MLXBF_GIGE_BCAST_MAC_FILTER_IDX 0 +#define MLXBF_GIGE_LOCAL_MAC_FILTER_IDX 1 + +/* Define for broadcast MAC literal */ +#define BCAST_MAC_ADDR 0xFFFFFFFFFFFF + +/* There are three individual interrupts: + * 1) Errors, "OOB" interrupt line + * 2) Receive Packet, "OOB_LLU" interrupt line + * 3) LLU and PLU Events, "OOB_PLU" interrupt line + */ +#define MLXBF_GIGE_ERROR_INTR_IDX 0 +#define MLXBF_GIGE_RECEIVE_PKT_INTR_IDX 1 +#define MLXBF_GIGE_LLU_PLU_INTR_IDX 2 +#define MLXBF_GIGE_PHY_INT_N 3 + +#define MLXBF_GIGE_MDIO_DEFAULT_PHY_ADDR 0x3 + +#define MLXBF_GIGE_DEFAULT_PHY_INT_GPIO 12 + +struct mlxbf_gige_stats { + u64 hw_access_errors; + u64 tx_invalid_checksums; + u64 tx_small_frames; + u64 tx_index_errors; + u64 sw_config_errors; + u64 sw_access_errors; + u64 rx_truncate_errors; + u64 rx_mac_errors; + u64 rx_din_dropped_pkts; + u64 tx_fifo_full; + u64 rx_filter_passed_pkts; + u64 rx_filter_discard_pkts; +}; + +struct mlxbf_gige { + void __iomem *base; + void __iomem *llu_base; + void __iomem *plu_base; + struct device *dev; + struct net_device *netdev; + struct platform_device *pdev; + void __iomem *mdio_io; + struct mii_bus *mdiobus; + void __iomem *gpio_io; + struct irq_domain *irqdomain; + u32 phy_int_gpio_mask; + spinlock_t lock; /* for packet processing indices */ + spinlock_t gpio_lock; /* for GPIO bus access */ + u16 rx_q_entries; + u16 tx_q_entries; + u64 *tx_wqe_base; + dma_addr_t tx_wqe_base_dma; + u64 *tx_wqe_next; + u64 *tx_cc; + dma_addr_t tx_cc_dma; + dma_addr_t *rx_wqe_base; + dma_addr_t rx_wqe_base_dma; + u64 *rx_cqe_base; + dma_addr_t rx_cqe_base_dma; + u16 tx_pi; + u16 prev_tx_ci; + u64 error_intr_count; + u64 rx_intr_count; + u64 llu_plu_intr_count; + struct sk_buff *rx_skb[MLXBF_GIGE_MAX_RXQ_SZ]; + struct sk_buff *tx_skb[MLXBF_GIGE_MAX_TXQ_SZ]; + int error_irq; + int rx_irq; + int llu_plu_irq; + int phy_irq; + int hw_phy_irq; + bool promisc_enabled; + u8 valid_polarity; + struct napi_struct napi; + struct mlxbf_gige_stats stats; +}; + +/* Rx Work Queue Element definitions */ +#define MLXBF_GIGE_RX_WQE_SZ 8 + +/* Rx Completion Queue Element definitions */ +#define MLXBF_GIGE_RX_CQE_SZ 8 +#define MLXBF_GIGE_RX_CQE_PKT_LEN_MASK GENMASK(10, 0) +#define MLXBF_GIGE_RX_CQE_VALID_MASK GENMASK(11, 11) +#define MLXBF_GIGE_RX_CQE_PKT_STATUS_MASK GENMASK(15, 12) +#define MLXBF_GIGE_RX_CQE_PKT_STATUS_MAC_ERR GENMASK(12, 12) +#define MLXBF_GIGE_RX_CQE_PKT_STATUS_TRUNCATED GENMASK(13, 13) +#define MLXBF_GIGE_RX_CQE_CHKSUM_MASK GENMASK(31, 16) + +/* Tx Work Queue Element definitions */ +#define MLXBF_GIGE_TX_WQE_SZ_QWORDS 2 +#define MLXBF_GIGE_TX_WQE_SZ 16 +#define MLXBF_GIGE_TX_WQE_PKT_LEN_MASK GENMASK(10, 0) +#define MLXBF_GIGE_TX_WQE_UPDATE_MASK GENMASK(31, 31) +#define MLXBF_GIGE_TX_WQE_CHKSUM_LEN_MASK GENMASK(42, 32) +#define MLXBF_GIGE_TX_WQE_CHKSUM_START_MASK GENMASK(55, 48) +#define MLXBF_GIGE_TX_WQE_CHKSUM_OFFSET_MASK GENMASK(63, 56) + +/* Macro to return packet length of specified TX WQE */ +#define MLXBF_GIGE_TX_WQE_PKT_LEN(tx_wqe_addr) \ + (*((tx_wqe_addr) + 1) & MLXBF_GIGE_TX_WQE_PKT_LEN_MASK) + +/* Tx Completion Count */ +#define MLXBF_GIGE_TX_CC_SZ 8 + +/* List of resources in ACPI table */ +enum mlxbf_gige_res { + MLXBF_GIGE_RES_MAC, + MLXBF_GIGE_RES_MDIO9, + MLXBF_GIGE_RES_GPIO0, + MLXBF_GIGE_RES_LLU, + MLXBF_GIGE_RES_PLU +}; + +/* Version of register data returned by mlxbf_gige_get_regs() */ +#define MLXBF_GIGE_REGS_VERSION 1 + +int mlxbf_gige_mdio_probe(struct platform_device *pdev, + struct mlxbf_gige *priv); +void mlxbf_gige_mdio_remove(struct mlxbf_gige *priv); +irqreturn_t mlxbf_gige_mdio_handle_phy_interrupt(int irq, void *dev_id); +void mlxbf_gige_mdio_enable_phy_int(struct mlxbf_gige *priv); + +void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index, u64 dmac); +void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index, u64 *dmac); +void mlxbf_gige_enable_promisc(struct mlxbf_gige *priv); +void mlxbf_gige_disable_promisc(struct mlxbf_gige *priv); +int mlxbf_gige_rx_init(struct mlxbf_gige *priv); +void mlxbf_gige_rx_deinit(struct mlxbf_gige *priv); +int mlxbf_gige_tx_init(struct mlxbf_gige *priv); +void mlxbf_gige_tx_deinit(struct mlxbf_gige *priv); +bool mlxbf_gige_handle_tx_complete(struct mlxbf_gige *priv); +netdev_tx_t mlxbf_gige_start_xmit(struct sk_buff *skb, + struct net_device *netdev); +struct sk_buff *mlxbf_gige_alloc_skb(struct mlxbf_gige *priv, + unsigned int map_len, + dma_addr_t *buf_dma, + enum dma_data_direction dir); +int mlxbf_gige_request_irqs(struct mlxbf_gige *priv); +void mlxbf_gige_free_irqs(struct mlxbf_gige *priv); +int mlxbf_gige_poll(struct napi_struct *napi, int budget); +extern const struct ethtool_ops mlxbf_gige_ethtool_ops; +void mlxbf_gige_update_tx_wqe_next(struct mlxbf_gige *priv); + +int mlxbf_gige_gpio_init(struct platform_device *pdev, struct mlxbf_gige *priv); +void mlxbf_gige_gpio_free(struct mlxbf_gige *priv); + +#endif /* !defined(__MLXBF_GIGE_H__) */ diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c new file mode 100644 index 000000000000..92b798f8e73a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause + +/* Ethtool support for Mellanox Gigabit Ethernet driver + * + * Copyright (C) 2020-2021 NVIDIA CORPORATION & AFFILIATES + */ + +#include + +#include "mlxbf_gige.h" +#include "mlxbf_gige_regs.h" + +/* Start of struct ethtool_ops functions */ +static int mlxbf_gige_get_regs_len(struct net_device *netdev) +{ + return MLXBF_GIGE_MMIO_REG_SZ; +} + +static void mlxbf_gige_get_regs(struct net_device *netdev, + struct ethtool_regs *regs, void *p) +{ + struct mlxbf_gige *priv = netdev_priv(netdev); + + regs->version = MLXBF_GIGE_REGS_VERSION; + + /* Read entire MMIO register space and store results + * into the provided buffer. Each 64-bit word is converted + * to big-endian to make the output more readable. + * + * NOTE: by design, a read to an offset without an existing + * register will be acknowledged and return zero. + */ + memcpy_fromio(p, priv->base, MLXBF_GIGE_MMIO_REG_SZ); +} + +static void mlxbf_gige_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ering) +{ + struct mlxbf_gige *priv = netdev_priv(netdev); + + ering->rx_max_pending = MLXBF_GIGE_MAX_RXQ_SZ; + ering->tx_max_pending = MLXBF_GIGE_MAX_TXQ_SZ; + ering->rx_pending = priv->rx_q_entries; + ering->tx_pending = priv->tx_q_entries; +} + +static const struct { + const char string[ETH_GSTRING_LEN]; +} mlxbf_gige_ethtool_stats_keys[] = { + { "hw_access_errors" }, + { "tx_invalid_checksums" }, + { "tx_small_frames" }, + { "tx_index_errors" }, + { "sw_config_errors" }, + { "sw_access_errors" }, + { "rx_truncate_errors" }, + { "rx_mac_errors" }, + { "rx_din_dropped_pkts" }, + { "tx_fifo_full" }, + { "rx_filter_passed_pkts" }, + { "rx_filter_discard_pkts" }, +}; + +static int mlxbf_gige_get_sset_count(struct net_device *netdev, int stringset) +{ + if (stringset != ETH_SS_STATS) + return -EOPNOTSUPP; + return ARRAY_SIZE(mlxbf_gige_ethtool_stats_keys); +} + +static void mlxbf_gige_get_strings(struct net_device *netdev, u32 stringset, + u8 *buf) +{ + if (stringset != ETH_SS_STATS) + return; + memcpy(buf, &mlxbf_gige_ethtool_stats_keys, + sizeof(mlxbf_gige_ethtool_stats_keys)); +} + +static void mlxbf_gige_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *estats, + u64 *data) +{ + struct mlxbf_gige *priv = netdev_priv(netdev); + + /* Fill data array with interface statistics + * + * NOTE: the data writes must be in + * sync with the strings shown in + * the mlxbf_gige_ethtool_stats_keys[] array + * + * NOTE2: certain statistics below are zeroed upon + * port disable, so the calculation below + * must include the "cached" value of the stat + * plus the value read directly from hardware. + * Cached statistics are currently: + * rx_din_dropped_pkts + * rx_filter_passed_pkts + * rx_filter_discard_pkts + */ + *data++ = priv->stats.hw_access_errors; + *data++ = priv->stats.tx_invalid_checksums; + *data++ = priv->stats.tx_small_frames; + *data++ = priv->stats.tx_index_errors; + *data++ = priv->stats.sw_config_errors; + *data++ = priv->stats.sw_access_errors; + *data++ = priv->stats.rx_truncate_errors; + *data++ = priv->stats.rx_mac_errors; + *data++ = (priv->stats.rx_din_dropped_pkts + + readq(priv->base + MLXBF_GIGE_RX_DIN_DROP_COUNTER)); + *data++ = priv->stats.tx_fifo_full; + *data++ = (priv->stats.rx_filter_passed_pkts + + readq(priv->base + MLXBF_GIGE_RX_PASS_COUNTER_ALL)); + *data++ = (priv->stats.rx_filter_discard_pkts + + readq(priv->base + MLXBF_GIGE_RX_DISC_COUNTER_ALL)); +} + +static void mlxbf_gige_get_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + pause->autoneg = AUTONEG_DISABLE; + pause->rx_pause = 1; + pause->tx_pause = 1; +} + +const struct ethtool_ops mlxbf_gige_ethtool_ops = { + .get_link = ethtool_op_get_link, + .get_ringparam = mlxbf_gige_get_ringparam, + .get_regs_len = mlxbf_gige_get_regs_len, + .get_regs = mlxbf_gige_get_regs, + .get_strings = mlxbf_gige_get_strings, + .get_sset_count = mlxbf_gige_get_sset_count, + .get_ethtool_stats = mlxbf_gige_get_ethtool_stats, + .nway_reset = phy_ethtool_nway_reset, + .get_pauseparam = mlxbf_gige_get_pauseparam, + .get_link_ksettings = phy_ethtool_get_link_ksettings, +}; diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_gpio.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_gpio.c new file mode 100644 index 000000000000..a8d966db5715 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_gpio.c @@ -0,0 +1,212 @@ +// SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause + +/* Initialize and handle GPIO interrupt triggered by INT_N PHY signal. + * This GPIO interrupt triggers the PHY state machine to bring the link + * up/down. + * + * Copyright (C) 2021 NVIDIA CORPORATION & AFFILIATES + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "mlxbf_gige.h" +#include "mlxbf_gige_regs.h" + +#define MLXBF_GIGE_GPIO_CAUSE_FALL_EN 0x48 +#define MLXBF_GIGE_GPIO_CAUSE_OR_CAUSE_EVTEN0 0x80 +#define MLXBF_GIGE_GPIO_CAUSE_OR_EVTEN0 0x94 +#define MLXBF_GIGE_GPIO_CAUSE_OR_CLRCAUSE 0x98 + +static void mlxbf_gige_gpio_enable(struct mlxbf_gige *priv) +{ + unsigned long flags; + u32 val; + + spin_lock_irqsave(&priv->gpio_lock, flags); + val = readl(priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_CLRCAUSE); + val |= priv->phy_int_gpio_mask; + writel(val, priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_CLRCAUSE); + + /* The INT_N interrupt level is active low. + * So enable cause fall bit to detect when GPIO + * state goes low. + */ + val = readl(priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_FALL_EN); + val |= priv->phy_int_gpio_mask; + writel(val, priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_FALL_EN); + + /* Enable PHY interrupt by setting the priority level */ + val = readl(priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_EVTEN0); + val |= priv->phy_int_gpio_mask; + writel(val, priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_EVTEN0); + spin_unlock_irqrestore(&priv->gpio_lock, flags); +} + +static void mlxbf_gige_gpio_disable(struct mlxbf_gige *priv) +{ + unsigned long flags; + u32 val; + + spin_lock_irqsave(&priv->gpio_lock, flags); + val = readl(priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_EVTEN0); + val &= ~priv->phy_int_gpio_mask; + writel(val, priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_EVTEN0); + spin_unlock_irqrestore(&priv->gpio_lock, flags); +} + +static irqreturn_t mlxbf_gige_gpio_handler(int irq, void *ptr) +{ + struct mlxbf_gige *priv; + u32 val; + + priv = ptr; + + /* Check if this interrupt is from PHY device. + * Return if it is not. + */ + val = readl(priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_CAUSE_EVTEN0); + if (!(val & priv->phy_int_gpio_mask)) + return IRQ_NONE; + + /* Clear interrupt when done, otherwise, no further interrupt + * will be triggered. + */ + val = readl(priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_CLRCAUSE); + val |= priv->phy_int_gpio_mask; + writel(val, priv->gpio_io + MLXBF_GIGE_GPIO_CAUSE_OR_CLRCAUSE); + + generic_handle_irq(priv->phy_irq); + + return IRQ_HANDLED; +} + +static void mlxbf_gige_gpio_mask(struct irq_data *irqd) +{ + struct mlxbf_gige *priv = irq_data_get_irq_chip_data(irqd); + + mlxbf_gige_gpio_disable(priv); +} + +static void mlxbf_gige_gpio_unmask(struct irq_data *irqd) +{ + struct mlxbf_gige *priv = irq_data_get_irq_chip_data(irqd); + + mlxbf_gige_gpio_enable(priv); +} + +static struct irq_chip mlxbf_gige_gpio_chip = { + .name = "mlxbf_gige_phy", + .irq_mask = mlxbf_gige_gpio_mask, + .irq_unmask = mlxbf_gige_gpio_unmask, +}; + +static int mlxbf_gige_gpio_domain_map(struct irq_domain *d, + unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_data(irq, d->host_data); + irq_set_chip_and_handler(irq, &mlxbf_gige_gpio_chip, handle_simple_irq); + irq_set_noprobe(irq); + + return 0; +} + +static const struct irq_domain_ops mlxbf_gige_gpio_domain_ops = { + .map = mlxbf_gige_gpio_domain_map, + .xlate = irq_domain_xlate_twocell, +}; + +#ifdef CONFIG_ACPI +static int mlxbf_gige_gpio_resources(struct acpi_resource *ares, + void *data) +{ + struct acpi_resource_gpio *gpio; + u32 *phy_int_gpio = data; + + if (ares->type == ACPI_RESOURCE_TYPE_GPIO) { + gpio = &ares->data.gpio; + *phy_int_gpio = gpio->pin_table[0]; + } + + return 1; +} +#endif + +void mlxbf_gige_gpio_free(struct mlxbf_gige *priv) +{ + irq_dispose_mapping(priv->phy_irq); + irq_domain_remove(priv->irqdomain); +} + +int mlxbf_gige_gpio_init(struct platform_device *pdev, + struct mlxbf_gige *priv) +{ + struct device *dev = &pdev->dev; + struct resource *res; + u32 phy_int_gpio = 0; + int ret; + + LIST_HEAD(resources); + + res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_GPIO0); + if (!res) + return -ENODEV; + + priv->gpio_io = devm_ioremap(dev, res->start, resource_size(res)); + if (!priv->gpio_io) + return -ENOMEM; + +#ifdef CONFIG_ACPI + ret = acpi_dev_get_resources(ACPI_COMPANION(dev), + &resources, mlxbf_gige_gpio_resources, + &phy_int_gpio); + acpi_dev_free_resource_list(&resources); + if (ret < 0 || !phy_int_gpio) { + dev_err(dev, "Error retrieving the gpio phy pin"); + return -EINVAL; + } +#endif + + priv->phy_int_gpio_mask = BIT(phy_int_gpio); + + mlxbf_gige_gpio_disable(priv); + + priv->hw_phy_irq = platform_get_irq(pdev, MLXBF_GIGE_PHY_INT_N); + + priv->irqdomain = irq_domain_add_simple(NULL, 1, 0, + &mlxbf_gige_gpio_domain_ops, + priv); + if (!priv->irqdomain) { + dev_err(dev, "Failed to add IRQ domain\n"); + return -ENOMEM; + } + + priv->phy_irq = irq_create_mapping(priv->irqdomain, 0); + if (!priv->phy_irq) { + irq_domain_remove(priv->irqdomain); + priv->irqdomain = NULL; + dev_err(dev, "Error mapping PHY IRQ\n"); + return -EINVAL; + } + + ret = devm_request_irq(dev, priv->hw_phy_irq, mlxbf_gige_gpio_handler, + IRQF_ONESHOT | IRQF_SHARED, "mlxbf_gige_phy", priv); + if (ret) { + dev_err(dev, "Failed to request PHY IRQ"); + mlxbf_gige_gpio_free(priv); + return ret; + } + + return ret; +} diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_intr.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_intr.c new file mode 100644 index 000000000000..c38795be04a2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_intr.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause + +/* Interrupt related logic for Mellanox Gigabit Ethernet driver + * + * Copyright (C) 2020-2021 NVIDIA CORPORATION & AFFILIATES + */ + +#include + +#include "mlxbf_gige.h" +#include "mlxbf_gige_regs.h" + +static irqreturn_t mlxbf_gige_error_intr(int irq, void *dev_id) +{ + struct mlxbf_gige *priv; + u64 int_status; + + priv = dev_id; + + priv->error_intr_count++; + + int_status = readq(priv->base + MLXBF_GIGE_INT_STATUS); + + if (int_status & MLXBF_GIGE_INT_STATUS_HW_ACCESS_ERROR) + priv->stats.hw_access_errors++; + + if (int_status & MLXBF_GIGE_INT_STATUS_TX_CHECKSUM_INPUTS) { + priv->stats.tx_invalid_checksums++; + /* This error condition is latched into MLXBF_GIGE_INT_STATUS + * when the GigE silicon operates on the offending + * TX WQE. The write to MLXBF_GIGE_INT_STATUS at the bottom + * of this routine clears this error condition. + */ + } + + if (int_status & MLXBF_GIGE_INT_STATUS_TX_SMALL_FRAME_SIZE) { + priv->stats.tx_small_frames++; + /* This condition happens when the networking stack invokes + * this driver's "start_xmit()" method with a packet whose + * size < 60 bytes. The GigE silicon will automatically pad + * this small frame up to a minimum-sized frame before it is + * sent. The "tx_small_frame" condition is latched into the + * MLXBF_GIGE_INT_STATUS register when the GigE silicon + * operates on the offending TX WQE. The write to + * MLXBF_GIGE_INT_STATUS at the bottom of this routine + * clears this condition. + */ + } + + if (int_status & MLXBF_GIGE_INT_STATUS_TX_PI_CI_EXCEED_WQ_SIZE) + priv->stats.tx_index_errors++; + + if (int_status & MLXBF_GIGE_INT_STATUS_SW_CONFIG_ERROR) + priv->stats.sw_config_errors++; + + if (int_status & MLXBF_GIGE_INT_STATUS_SW_ACCESS_ERROR) + priv->stats.sw_access_errors++; + + /* Clear all error interrupts by writing '1' back to + * all the asserted bits in INT_STATUS. Do not write + * '1' back to 'receive packet' bit, since that is + * managed separately. + */ + + int_status &= ~MLXBF_GIGE_INT_STATUS_RX_RECEIVE_PACKET; + + writeq(int_status, priv->base + MLXBF_GIGE_INT_STATUS); + + return IRQ_HANDLED; +} + +static irqreturn_t mlxbf_gige_rx_intr(int irq, void *dev_id) +{ + struct mlxbf_gige *priv; + + priv = dev_id; + + priv->rx_intr_count++; + + /* NOTE: GigE silicon automatically disables "packet rx" interrupt by + * setting MLXBF_GIGE_INT_MASK bit0 upon triggering the interrupt + * to the ARM cores. Software needs to re-enable "packet rx" + * interrupts by clearing MLXBF_GIGE_INT_MASK bit0. + */ + + napi_schedule(&priv->napi); + + return IRQ_HANDLED; +} + +static irqreturn_t mlxbf_gige_llu_plu_intr(int irq, void *dev_id) +{ + struct mlxbf_gige *priv; + + priv = dev_id; + priv->llu_plu_intr_count++; + + return IRQ_HANDLED; +} + +int mlxbf_gige_request_irqs(struct mlxbf_gige *priv) +{ + int err; + + err = request_irq(priv->error_irq, mlxbf_gige_error_intr, 0, + "mlxbf_gige_error", priv); + if (err) { + dev_err(priv->dev, "Request error_irq failure\n"); + return err; + } + + err = request_irq(priv->rx_irq, mlxbf_gige_rx_intr, 0, + "mlxbf_gige_rx", priv); + if (err) { + dev_err(priv->dev, "Request rx_irq failure\n"); + goto free_error_irq; + } + + err = request_irq(priv->llu_plu_irq, mlxbf_gige_llu_plu_intr, 0, + "mlxbf_gige_llu_plu", priv); + if (err) { + dev_err(priv->dev, "Request llu_plu_irq failure\n"); + goto free_rx_irq; + } + + return 0; + +free_rx_irq: + free_irq(priv->rx_irq, priv); + +free_error_irq: + free_irq(priv->error_irq, priv); + + return err; +} + +void mlxbf_gige_free_irqs(struct mlxbf_gige *priv) +{ + free_irq(priv->error_irq, priv); + free_irq(priv->rx_irq, priv); + free_irq(priv->llu_plu_irq, priv); +} diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c new file mode 100644 index 000000000000..a0a059e0154f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -0,0 +1,452 @@ +// SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause + +/* Gigabit Ethernet driver for Mellanox BlueField SoC + * + * Copyright (C) 2020-2021 NVIDIA CORPORATION & AFFILIATES + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "mlxbf_gige.h" +#include "mlxbf_gige_regs.h" + +#define DRV_NAME "mlxbf_gige" + +/* Allocate SKB whose payload pointer aligns with the Bluefield + * hardware DMA limitation, i.e. DMA operation can't cross + * a 4KB boundary. A maximum packet size of 2KB is assumed in the + * alignment formula. The alignment logic overallocates an SKB, + * and then adjusts the headroom so that the SKB data pointer is + * naturally aligned to a 2KB boundary. + */ +struct sk_buff *mlxbf_gige_alloc_skb(struct mlxbf_gige *priv, + unsigned int map_len, + dma_addr_t *buf_dma, + enum dma_data_direction dir) +{ + struct sk_buff *skb; + u64 addr, offset; + + /* Overallocate the SKB so that any headroom adjustment (to + * provide 2KB natural alignment) does not exceed payload area + */ + skb = netdev_alloc_skb(priv->netdev, MLXBF_GIGE_DEFAULT_BUF_SZ * 2); + if (!skb) + return NULL; + + /* Adjust the headroom so that skb->data is naturally aligned to + * a 2KB boundary, which is the maximum packet size supported. + */ + addr = (long)skb->data; + offset = (addr + MLXBF_GIGE_DEFAULT_BUF_SZ - 1) & + ~(MLXBF_GIGE_DEFAULT_BUF_SZ - 1); + offset -= addr; + if (offset) + skb_reserve(skb, offset); + + /* Return streaming DMA mapping to caller */ + *buf_dma = dma_map_single(priv->dev, skb->data, map_len, dir); + if (dma_mapping_error(priv->dev, *buf_dma)) { + dev_kfree_skb(skb); + *buf_dma = (dma_addr_t)0; + return NULL; + } + + return skb; +} + +static void mlxbf_gige_initial_mac(struct mlxbf_gige *priv) +{ + u8 mac[ETH_ALEN]; + u64 local_mac; + + memset(mac, 0, ETH_ALEN); + mlxbf_gige_get_mac_rx_filter(priv, MLXBF_GIGE_LOCAL_MAC_FILTER_IDX, + &local_mac); + u64_to_ether_addr(local_mac, mac); + + if (is_valid_ether_addr(mac)) { + ether_addr_copy(priv->netdev->dev_addr, mac); + } else { + /* Provide a random MAC if for some reason the device has + * not been configured with a valid MAC address already. + */ + eth_hw_addr_random(priv->netdev); + } + + local_mac = ether_addr_to_u64(priv->netdev->dev_addr); + mlxbf_gige_set_mac_rx_filter(priv, MLXBF_GIGE_LOCAL_MAC_FILTER_IDX, + local_mac); +} + +static void mlxbf_gige_cache_stats(struct mlxbf_gige *priv) +{ + struct mlxbf_gige_stats *p; + + /* Cache stats that will be cleared by clean port operation */ + p = &priv->stats; + p->rx_din_dropped_pkts += readq(priv->base + + MLXBF_GIGE_RX_DIN_DROP_COUNTER); + p->rx_filter_passed_pkts += readq(priv->base + + MLXBF_GIGE_RX_PASS_COUNTER_ALL); + p->rx_filter_discard_pkts += readq(priv->base + + MLXBF_GIGE_RX_DISC_COUNTER_ALL); +} + +static int mlxbf_gige_clean_port(struct mlxbf_gige *priv) +{ + u64 control; + u64 temp; + int err; + + /* Set the CLEAN_PORT_EN bit to trigger SW reset */ + control = readq(priv->base + MLXBF_GIGE_CONTROL); + control |= MLXBF_GIGE_CONTROL_CLEAN_PORT_EN; + writeq(control, priv->base + MLXBF_GIGE_CONTROL); + + /* Ensure completion of "clean port" write before polling status */ + mb(); + + err = readq_poll_timeout_atomic(priv->base + MLXBF_GIGE_STATUS, temp, + (temp & MLXBF_GIGE_STATUS_READY), + 100, 100000); + + /* Clear the CLEAN_PORT_EN bit at end of this loop */ + control = readq(priv->base + MLXBF_GIGE_CONTROL); + control &= ~MLXBF_GIGE_CONTROL_CLEAN_PORT_EN; + writeq(control, priv->base + MLXBF_GIGE_CONTROL); + + return err; +} + +static int mlxbf_gige_open(struct net_device *netdev) +{ + struct mlxbf_gige *priv = netdev_priv(netdev); + struct phy_device *phydev = netdev->phydev; + u64 int_en; + int err; + + err = mlxbf_gige_request_irqs(priv); + if (err) + return err; + mlxbf_gige_cache_stats(priv); + err = mlxbf_gige_clean_port(priv); + if (err) + goto free_irqs; + err = mlxbf_gige_rx_init(priv); + if (err) + goto free_irqs; + err = mlxbf_gige_tx_init(priv); + if (err) + goto rx_deinit; + + phy_start(phydev); + + netif_napi_add(netdev, &priv->napi, mlxbf_gige_poll, NAPI_POLL_WEIGHT); + napi_enable(&priv->napi); + netif_start_queue(netdev); + + /* Set bits in INT_EN that we care about */ + int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR | + MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS | + MLXBF_GIGE_INT_EN_TX_SMALL_FRAME_SIZE | + MLXBF_GIGE_INT_EN_TX_PI_CI_EXCEED_WQ_SIZE | + MLXBF_GIGE_INT_EN_SW_CONFIG_ERROR | + MLXBF_GIGE_INT_EN_SW_ACCESS_ERROR | + MLXBF_GIGE_INT_EN_RX_RECEIVE_PACKET; + + /* Ensure completion of all initialization before enabling interrupts */ + mb(); + + writeq(int_en, priv->base + MLXBF_GIGE_INT_EN); + + return 0; + +rx_deinit: + mlxbf_gige_rx_deinit(priv); + +free_irqs: + mlxbf_gige_free_irqs(priv); + return err; +} + +static int mlxbf_gige_stop(struct net_device *netdev) +{ + struct mlxbf_gige *priv = netdev_priv(netdev); + + writeq(0, priv->base + MLXBF_GIGE_INT_EN); + netif_stop_queue(netdev); + napi_disable(&priv->napi); + netif_napi_del(&priv->napi); + mlxbf_gige_free_irqs(priv); + + phy_stop(netdev->phydev); + + mlxbf_gige_rx_deinit(priv); + mlxbf_gige_tx_deinit(priv); + mlxbf_gige_cache_stats(priv); + mlxbf_gige_clean_port(priv); + + return 0; +} + +static int mlxbf_gige_do_ioctl(struct net_device *netdev, + struct ifreq *ifr, int cmd) +{ + if (!(netif_running(netdev))) + return -EINVAL; + + return phy_mii_ioctl(netdev->phydev, ifr, cmd); +} + +static void mlxbf_gige_set_rx_mode(struct net_device *netdev) +{ + struct mlxbf_gige *priv = netdev_priv(netdev); + bool new_promisc_enabled; + + new_promisc_enabled = netdev->flags & IFF_PROMISC; + + /* Only write to the hardware registers if the new setting + * of promiscuous mode is different from the current one. + */ + if (new_promisc_enabled != priv->promisc_enabled) { + priv->promisc_enabled = new_promisc_enabled; + + if (new_promisc_enabled) + mlxbf_gige_enable_promisc(priv); + else + mlxbf_gige_disable_promisc(priv); + } +} + +static void mlxbf_gige_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct mlxbf_gige *priv = netdev_priv(netdev); + + netdev_stats_to_stats64(stats, &netdev->stats); + + stats->rx_length_errors = priv->stats.rx_truncate_errors; + stats->rx_fifo_errors = priv->stats.rx_din_dropped_pkts + + readq(priv->base + MLXBF_GIGE_RX_DIN_DROP_COUNTER); + stats->rx_crc_errors = priv->stats.rx_mac_errors; + stats->rx_errors = stats->rx_length_errors + + stats->rx_fifo_errors + + stats->rx_crc_errors; + + stats->tx_fifo_errors = priv->stats.tx_fifo_full; + stats->tx_errors = stats->tx_fifo_errors; +} + +static const struct net_device_ops mlxbf_gige_netdev_ops = { + .ndo_open = mlxbf_gige_open, + .ndo_stop = mlxbf_gige_stop, + .ndo_start_xmit = mlxbf_gige_start_xmit, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_do_ioctl = mlxbf_gige_do_ioctl, + .ndo_set_rx_mode = mlxbf_gige_set_rx_mode, + .ndo_get_stats64 = mlxbf_gige_get_stats64, +}; + +static void mlxbf_gige_adjust_link(struct net_device *netdev) +{ + struct phy_device *phydev = netdev->phydev; + + phy_print_status(phydev); +} + +static int mlxbf_gige_probe(struct platform_device *pdev) +{ + struct phy_device *phydev; + struct net_device *netdev; + struct resource *mac_res; + struct resource *llu_res; + struct resource *plu_res; + struct mlxbf_gige *priv; + void __iomem *llu_base; + void __iomem *plu_base; + void __iomem *base; + u64 control; + int addr; + int err; + + mac_res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_MAC); + if (!mac_res) + return -ENXIO; + + base = devm_ioremap_resource(&pdev->dev, mac_res); + if (IS_ERR(base)) + return PTR_ERR(base); + + llu_res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_LLU); + if (!llu_res) + return -ENXIO; + + llu_base = devm_ioremap_resource(&pdev->dev, llu_res); + if (IS_ERR(llu_base)) + return PTR_ERR(llu_base); + + plu_res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_PLU); + if (!plu_res) + return -ENXIO; + + plu_base = devm_ioremap_resource(&pdev->dev, plu_res); + if (IS_ERR(plu_base)) + return PTR_ERR(plu_base); + + /* Perform general init of GigE block */ + control = readq(base + MLXBF_GIGE_CONTROL); + control |= MLXBF_GIGE_CONTROL_PORT_EN; + writeq(control, base + MLXBF_GIGE_CONTROL); + + netdev = devm_alloc_etherdev(&pdev->dev, sizeof(*priv)); + if (!netdev) + return -ENOMEM; + + SET_NETDEV_DEV(netdev, &pdev->dev); + netdev->netdev_ops = &mlxbf_gige_netdev_ops; + netdev->ethtool_ops = &mlxbf_gige_ethtool_ops; + priv = netdev_priv(netdev); + priv->netdev = netdev; + + platform_set_drvdata(pdev, priv); + priv->dev = &pdev->dev; + priv->pdev = pdev; + + spin_lock_init(&priv->lock); + spin_lock_init(&priv->gpio_lock); + + /* Attach MDIO device */ + err = mlxbf_gige_mdio_probe(pdev, priv); + if (err) + return err; + + err = mlxbf_gige_gpio_init(pdev, priv); + if (err) { + dev_err(&pdev->dev, "PHY IRQ initialization failed\n"); + mlxbf_gige_mdio_remove(priv); + return -ENODEV; + } + + priv->base = base; + priv->llu_base = llu_base; + priv->plu_base = plu_base; + + priv->rx_q_entries = MLXBF_GIGE_DEFAULT_RXQ_SZ; + priv->tx_q_entries = MLXBF_GIGE_DEFAULT_TXQ_SZ; + + /* Write initial MAC address to hardware */ + mlxbf_gige_initial_mac(priv); + + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(&pdev->dev, "DMA configuration failed: 0x%x\n", err); + goto out; + } + + priv->error_irq = platform_get_irq(pdev, MLXBF_GIGE_ERROR_INTR_IDX); + priv->rx_irq = platform_get_irq(pdev, MLXBF_GIGE_RECEIVE_PKT_INTR_IDX); + priv->llu_plu_irq = platform_get_irq(pdev, MLXBF_GIGE_LLU_PLU_INTR_IDX); + + phydev = phy_find_first(priv->mdiobus); + if (!phydev) { + err = -ENODEV; + goto out; + } + + addr = phydev->mdio.addr; + priv->mdiobus->irq[addr] = priv->phy_irq; + phydev->irq = priv->phy_irq; + + err = phy_connect_direct(netdev, phydev, + mlxbf_gige_adjust_link, + PHY_INTERFACE_MODE_GMII); + if (err) { + dev_err(&pdev->dev, "Could not attach to PHY\n"); + goto out; + } + + /* MAC only supports 1000T full duplex mode */ + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Full_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Full_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + + /* Only symmetric pause with flow control enabled is supported so no + * need to negotiate pause. + */ + linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->advertising); + linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->advertising); + + /* Display information about attached PHY device */ + phy_attached_info(phydev); + + err = register_netdev(netdev); + if (err) { + dev_err(&pdev->dev, "Failed to register netdev\n"); + phy_disconnect(phydev); + goto out; + } + + return 0; + +out: + mlxbf_gige_gpio_free(priv); + mlxbf_gige_mdio_remove(priv); + return err; +} + +static int mlxbf_gige_remove(struct platform_device *pdev) +{ + struct mlxbf_gige *priv = platform_get_drvdata(pdev); + + unregister_netdev(priv->netdev); + phy_disconnect(priv->netdev->phydev); + mlxbf_gige_gpio_free(priv); + mlxbf_gige_mdio_remove(priv); + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static void mlxbf_gige_shutdown(struct platform_device *pdev) +{ + struct mlxbf_gige *priv = platform_get_drvdata(pdev); + + writeq(0, priv->base + MLXBF_GIGE_INT_EN); + mlxbf_gige_clean_port(priv); +} + +static const struct acpi_device_id __maybe_unused mlxbf_gige_acpi_match[] = { + { "MLNXBF17", 0 }, + {}, +}; +MODULE_DEVICE_TABLE(acpi, mlxbf_gige_acpi_match); + +static struct platform_driver mlxbf_gige_driver = { + .probe = mlxbf_gige_probe, + .remove = mlxbf_gige_remove, + .shutdown = mlxbf_gige_shutdown, + .driver = { + .name = DRV_NAME, + .acpi_match_table = ACPI_PTR(mlxbf_gige_acpi_match), + }, +}; + +module_platform_driver(mlxbf_gige_driver); + +MODULE_DESCRIPTION("Mellanox BlueField SoC Gigabit Ethernet Driver"); +MODULE_AUTHOR("David Thompson "); +MODULE_AUTHOR("Asmaa Mnebhi "); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c new file mode 100644 index 000000000000..e32dd34fdcc0 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_mdio.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause + +/* MDIO support for Mellanox Gigabit Ethernet driver + * + * Copyright (C) 2020-2021 NVIDIA CORPORATION & AFFILIATES + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "mlxbf_gige.h" + +#define MLXBF_GIGE_MDIO_GW_OFFSET 0x0 +#define MLXBF_GIGE_MDIO_CFG_OFFSET 0x4 + +/* Support clause 22 */ +#define MLXBF_GIGE_MDIO_CL22_ST1 0x1 +#define MLXBF_GIGE_MDIO_CL22_WRITE 0x1 +#define MLXBF_GIGE_MDIO_CL22_READ 0x2 + +/* Busy bit is set by software and cleared by hardware */ +#define MLXBF_GIGE_MDIO_SET_BUSY 0x1 + +/* MDIO GW register bits */ +#define MLXBF_GIGE_MDIO_GW_AD_MASK GENMASK(15, 0) +#define MLXBF_GIGE_MDIO_GW_DEVAD_MASK GENMASK(20, 16) +#define MLXBF_GIGE_MDIO_GW_PARTAD_MASK GENMASK(25, 21) +#define MLXBF_GIGE_MDIO_GW_OPCODE_MASK GENMASK(27, 26) +#define MLXBF_GIGE_MDIO_GW_ST1_MASK GENMASK(28, 28) +#define MLXBF_GIGE_MDIO_GW_BUSY_MASK GENMASK(30, 30) + +/* MDIO config register bits */ +#define MLXBF_GIGE_MDIO_CFG_MDIO_MODE_MASK GENMASK(1, 0) +#define MLXBF_GIGE_MDIO_CFG_MDIO3_3_MASK GENMASK(2, 2) +#define MLXBF_GIGE_MDIO_CFG_MDIO_FULL_DRIVE_MASK GENMASK(4, 4) +#define MLXBF_GIGE_MDIO_CFG_MDC_PERIOD_MASK GENMASK(15, 8) +#define MLXBF_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK GENMASK(23, 16) +#define MLXBF_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK GENMASK(31, 24) + +/* Formula for encoding the MDIO period. The encoded value is + * passed to the MDIO config register. + * + * mdc_clk = 2*(val + 1)*i1clk + * + * 400 ns = 2*(val + 1)*(((1/430)*1000) ns) + * + * val = (((400 * 430 / 1000) / 2) - 1) + */ +#define MLXBF_GIGE_I1CLK_MHZ 430 +#define MLXBF_GIGE_MDC_CLK_NS 400 + +#define MLXBF_GIGE_MDIO_PERIOD (((MLXBF_GIGE_MDC_CLK_NS * MLXBF_GIGE_I1CLK_MHZ / 1000) / 2) - 1) + +#define MLXBF_GIGE_MDIO_CFG_VAL (FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_MODE_MASK, 1) | \ + FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO3_3_MASK, 1) | \ + FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_FULL_DRIVE_MASK, 1) | \ + FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDC_PERIOD_MASK, \ + MLXBF_GIGE_MDIO_PERIOD) | \ + FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_IN_SAMP_MASK, 6) | \ + FIELD_PREP(MLXBF_GIGE_MDIO_CFG_MDIO_OUT_SAMP_MASK, 13)) + +static u32 mlxbf_gige_mdio_create_cmd(u16 data, int phy_add, + int phy_reg, u32 opcode) +{ + u32 gw_reg = 0; + + gw_reg |= FIELD_PREP(MLXBF_GIGE_MDIO_GW_AD_MASK, data); + gw_reg |= FIELD_PREP(MLXBF_GIGE_MDIO_GW_DEVAD_MASK, phy_reg); + gw_reg |= FIELD_PREP(MLXBF_GIGE_MDIO_GW_PARTAD_MASK, phy_add); + gw_reg |= FIELD_PREP(MLXBF_GIGE_MDIO_GW_OPCODE_MASK, opcode); + gw_reg |= FIELD_PREP(MLXBF_GIGE_MDIO_GW_ST1_MASK, + MLXBF_GIGE_MDIO_CL22_ST1); + gw_reg |= FIELD_PREP(MLXBF_GIGE_MDIO_GW_BUSY_MASK, + MLXBF_GIGE_MDIO_SET_BUSY); + + return gw_reg; +} + +static int mlxbf_gige_mdio_read(struct mii_bus *bus, int phy_add, int phy_reg) +{ + struct mlxbf_gige *priv = bus->priv; + u32 cmd; + int ret; + u32 val; + + if (phy_reg & MII_ADDR_C45) + return -EOPNOTSUPP; + + /* Send mdio read request */ + cmd = mlxbf_gige_mdio_create_cmd(0, phy_add, phy_reg, MLXBF_GIGE_MDIO_CL22_READ); + + writel(cmd, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + + ret = readl_poll_timeout_atomic(priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET, + val, !(val & MLXBF_GIGE_MDIO_GW_BUSY_MASK), 100, 1000000); + + if (ret) { + writel(0, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + return ret; + } + + ret = readl(priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + /* Only return ad bits of the gw register */ + ret &= MLXBF_GIGE_MDIO_GW_AD_MASK; + + return ret; +} + +static int mlxbf_gige_mdio_write(struct mii_bus *bus, int phy_add, + int phy_reg, u16 val) +{ + struct mlxbf_gige *priv = bus->priv; + u32 cmd; + int ret; + u32 temp; + + if (phy_reg & MII_ADDR_C45) + return -EOPNOTSUPP; + + /* Send mdio write request */ + cmd = mlxbf_gige_mdio_create_cmd(val, phy_add, phy_reg, + MLXBF_GIGE_MDIO_CL22_WRITE); + writel(cmd, priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET); + + /* If the poll timed out, drop the request */ + ret = readl_poll_timeout_atomic(priv->mdio_io + MLXBF_GIGE_MDIO_GW_OFFSET, + temp, !(temp & MLXBF_GIGE_MDIO_GW_BUSY_MASK), 100, 1000000); + + return ret; +} + +int mlxbf_gige_mdio_probe(struct platform_device *pdev, struct mlxbf_gige *priv) +{ + struct device *dev = &pdev->dev; + struct resource *res; + int ret; + + res = platform_get_resource(pdev, IORESOURCE_MEM, MLXBF_GIGE_RES_MDIO9); + if (!res) + return -ENODEV; + + priv->mdio_io = devm_ioremap_resource(dev, res); + if (IS_ERR(priv->mdio_io)) + return PTR_ERR(priv->mdio_io); + + /* Configure mdio parameters */ + writel(MLXBF_GIGE_MDIO_CFG_VAL, + priv->mdio_io + MLXBF_GIGE_MDIO_CFG_OFFSET); + + priv->mdiobus = devm_mdiobus_alloc(dev); + if (!priv->mdiobus) { + dev_err(dev, "Failed to alloc MDIO bus\n"); + return -ENOMEM; + } + + priv->mdiobus->name = "mlxbf-mdio"; + priv->mdiobus->read = mlxbf_gige_mdio_read; + priv->mdiobus->write = mlxbf_gige_mdio_write; + priv->mdiobus->parent = dev; + priv->mdiobus->priv = priv; + snprintf(priv->mdiobus->id, MII_BUS_ID_SIZE, "%s", + dev_name(dev)); + + ret = mdiobus_register(priv->mdiobus); + if (ret) + dev_err(dev, "Failed to register MDIO bus\n"); + + return ret; +} + +void mlxbf_gige_mdio_remove(struct mlxbf_gige *priv) +{ + mdiobus_unregister(priv->mdiobus); +} diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h new file mode 100644 index 000000000000..5fb33c9294bf --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause */ + +/* Header file for Mellanox BlueField GigE register defines + * + * Copyright (C) 2020-2021 NVIDIA CORPORATION & AFFILIATES + */ + +#ifndef __MLXBF_GIGE_REGS_H__ +#define __MLXBF_GIGE_REGS_H__ + +#define MLXBF_GIGE_STATUS 0x0010 +#define MLXBF_GIGE_STATUS_READY BIT(0) +#define MLXBF_GIGE_INT_STATUS 0x0028 +#define MLXBF_GIGE_INT_STATUS_RX_RECEIVE_PACKET BIT(0) +#define MLXBF_GIGE_INT_STATUS_RX_MAC_ERROR BIT(1) +#define MLXBF_GIGE_INT_STATUS_RX_TRN_ERROR BIT(2) +#define MLXBF_GIGE_INT_STATUS_SW_ACCESS_ERROR BIT(3) +#define MLXBF_GIGE_INT_STATUS_SW_CONFIG_ERROR BIT(4) +#define MLXBF_GIGE_INT_STATUS_TX_PI_CI_EXCEED_WQ_SIZE BIT(5) +#define MLXBF_GIGE_INT_STATUS_TX_SMALL_FRAME_SIZE BIT(6) +#define MLXBF_GIGE_INT_STATUS_TX_CHECKSUM_INPUTS BIT(7) +#define MLXBF_GIGE_INT_STATUS_HW_ACCESS_ERROR BIT(8) +#define MLXBF_GIGE_INT_EN 0x0030 +#define MLXBF_GIGE_INT_EN_RX_RECEIVE_PACKET BIT(0) +#define MLXBF_GIGE_INT_EN_RX_MAC_ERROR BIT(1) +#define MLXBF_GIGE_INT_EN_RX_TRN_ERROR BIT(2) +#define MLXBF_GIGE_INT_EN_SW_ACCESS_ERROR BIT(3) +#define MLXBF_GIGE_INT_EN_SW_CONFIG_ERROR BIT(4) +#define MLXBF_GIGE_INT_EN_TX_PI_CI_EXCEED_WQ_SIZE BIT(5) +#define MLXBF_GIGE_INT_EN_TX_SMALL_FRAME_SIZE BIT(6) +#define MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS BIT(7) +#define MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR BIT(8) +#define MLXBF_GIGE_INT_MASK 0x0038 +#define MLXBF_GIGE_INT_MASK_RX_RECEIVE_PACKET BIT(0) +#define MLXBF_GIGE_CONTROL 0x0040 +#define MLXBF_GIGE_CONTROL_PORT_EN BIT(0) +#define MLXBF_GIGE_CONTROL_MAC_ID_RANGE_EN BIT(1) +#define MLXBF_GIGE_CONTROL_EN_SPECIFIC_MAC BIT(4) +#define MLXBF_GIGE_CONTROL_CLEAN_PORT_EN BIT(31) +#define MLXBF_GIGE_RX_WQ_BASE 0x0200 +#define MLXBF_GIGE_RX_WQE_SIZE_LOG2 0x0208 +#define MLXBF_GIGE_RX_WQE_SIZE_LOG2_RESET_VAL 7 +#define MLXBF_GIGE_RX_CQ_BASE 0x0210 +#define MLXBF_GIGE_TX_WQ_BASE 0x0218 +#define MLXBF_GIGE_TX_WQ_SIZE_LOG2 0x0220 +#define MLXBF_GIGE_TX_WQ_SIZE_LOG2_RESET_VAL 7 +#define MLXBF_GIGE_TX_CI_UPDATE_ADDRESS 0x0228 +#define MLXBF_GIGE_RX_WQE_PI 0x0230 +#define MLXBF_GIGE_TX_PRODUCER_INDEX 0x0238 +#define MLXBF_GIGE_RX_MAC_FILTER 0x0240 +#define MLXBF_GIGE_RX_MAC_FILTER_STRIDE 0x0008 +#define MLXBF_GIGE_RX_DIN_DROP_COUNTER 0x0260 +#define MLXBF_GIGE_TX_CONSUMER_INDEX 0x0310 +#define MLXBF_GIGE_TX_CONTROL 0x0318 +#define MLXBF_GIGE_TX_CONTROL_GRACEFUL_STOP BIT(0) +#define MLXBF_GIGE_TX_STATUS 0x0388 +#define MLXBF_GIGE_TX_STATUS_DATA_FIFO_FULL BIT(1) +#define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_START 0x0520 +#define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_END 0x0528 +#define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC 0x0540 +#define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC_EN BIT(0) +#define MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS 0x0548 +#define MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS_EN BIT(0) +#define MLXBF_GIGE_RX_PASS_COUNTER_ALL 0x0550 +#define MLXBF_GIGE_RX_DISC_COUNTER_ALL 0x0560 +#define MLXBF_GIGE_RX 0x0578 +#define MLXBF_GIGE_RX_STRIP_CRC_EN BIT(1) +#define MLXBF_GIGE_RX_DMA 0x0580 +#define MLXBF_GIGE_RX_DMA_EN BIT(0) +#define MLXBF_GIGE_RX_CQE_PACKET_CI 0x05b0 +#define MLXBF_GIGE_MAC_CFG 0x05e8 + +/* NOTE: MLXBF_GIGE_MAC_CFG is the last defined register offset, + * so use that plus size of single register to derive total size + */ +#define MLXBF_GIGE_MMIO_REG_SZ (MLXBF_GIGE_MAC_CFG + 8) + +#endif /* !defined(__MLXBF_GIGE_REGS_H__) */ diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c new file mode 100644 index 000000000000..afa3b92a6905 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c @@ -0,0 +1,320 @@ +// SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause + +/* Packet receive logic for Mellanox Gigabit Ethernet driver + * + * Copyright (C) 2020-2021 NVIDIA CORPORATION & AFFILIATES + */ + +#include +#include + +#include "mlxbf_gige.h" +#include "mlxbf_gige_regs.h" + +void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index, u64 dmac) +{ + void __iomem *base = priv->base; + u64 control; + + /* Write destination MAC to specified MAC RX filter */ + writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER + + (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE)); + + /* Enable MAC receive filter mask for specified index */ + control = readq(base + MLXBF_GIGE_CONTROL); + control |= (MLXBF_GIGE_CONTROL_EN_SPECIFIC_MAC << index); + writeq(control, base + MLXBF_GIGE_CONTROL); +} + +void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv, + unsigned int index, u64 *dmac) +{ + void __iomem *base = priv->base; + + /* Read destination MAC from specified MAC RX filter */ + *dmac = readq(base + MLXBF_GIGE_RX_MAC_FILTER + + (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE)); +} + +void mlxbf_gige_enable_promisc(struct mlxbf_gige *priv) +{ + void __iomem *base = priv->base; + u64 control; + u64 end_mac; + + /* Enable MAC_ID_RANGE match functionality */ + control = readq(base + MLXBF_GIGE_CONTROL); + control |= MLXBF_GIGE_CONTROL_MAC_ID_RANGE_EN; + writeq(control, base + MLXBF_GIGE_CONTROL); + + /* Set start of destination MAC range check to 0 */ + writeq(0, base + MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_START); + + /* Set end of destination MAC range check to all FFs */ + end_mac = BCAST_MAC_ADDR; + writeq(end_mac, base + MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_END); +} + +void mlxbf_gige_disable_promisc(struct mlxbf_gige *priv) +{ + void __iomem *base = priv->base; + u64 control; + + /* Disable MAC_ID_RANGE match functionality */ + control = readq(base + MLXBF_GIGE_CONTROL); + control &= ~MLXBF_GIGE_CONTROL_MAC_ID_RANGE_EN; + writeq(control, base + MLXBF_GIGE_CONTROL); + + /* NOTE: no need to change DMAC_RANGE_START or END; + * those values are ignored since MAC_ID_RANGE_EN=0 + */ +} + +/* Receive Initialization + * 1) Configures RX MAC filters via MMIO registers + * 2) Allocates RX WQE array using coherent DMA mapping + * 3) Initializes each element of RX WQE array with a receive + * buffer pointer (also using coherent DMA mapping) + * 4) Allocates RX CQE array using coherent DMA mapping + * 5) Completes other misc receive initialization + */ +int mlxbf_gige_rx_init(struct mlxbf_gige *priv) +{ + size_t wq_size, cq_size; + dma_addr_t *rx_wqe_ptr; + dma_addr_t rx_buf_dma; + u64 data; + int i, j; + + /* Configure MAC RX filter #0 to allow RX of broadcast pkts */ + mlxbf_gige_set_mac_rx_filter(priv, MLXBF_GIGE_BCAST_MAC_FILTER_IDX, + BCAST_MAC_ADDR); + + wq_size = MLXBF_GIGE_RX_WQE_SZ * priv->rx_q_entries; + priv->rx_wqe_base = dma_alloc_coherent(priv->dev, wq_size, + &priv->rx_wqe_base_dma, + GFP_KERNEL); + if (!priv->rx_wqe_base) + return -ENOMEM; + + /* Initialize 'rx_wqe_ptr' to point to first RX WQE in array + * Each RX WQE is simply a receive buffer pointer, so walk + * the entire array, allocating a 2KB buffer for each element + */ + rx_wqe_ptr = priv->rx_wqe_base; + + for (i = 0; i < priv->rx_q_entries; i++) { + priv->rx_skb[i] = mlxbf_gige_alloc_skb(priv, MLXBF_GIGE_DEFAULT_BUF_SZ, + &rx_buf_dma, DMA_FROM_DEVICE); + if (!priv->rx_skb[i]) + goto free_wqe_and_skb; + *rx_wqe_ptr++ = rx_buf_dma; + } + + /* Write RX WQE base address into MMIO reg */ + writeq(priv->rx_wqe_base_dma, priv->base + MLXBF_GIGE_RX_WQ_BASE); + + cq_size = MLXBF_GIGE_RX_CQE_SZ * priv->rx_q_entries; + priv->rx_cqe_base = dma_alloc_coherent(priv->dev, cq_size, + &priv->rx_cqe_base_dma, + GFP_KERNEL); + if (!priv->rx_cqe_base) + goto free_wqe_and_skb; + + for (i = 0; i < priv->rx_q_entries; i++) + priv->rx_cqe_base[i] |= MLXBF_GIGE_RX_CQE_VALID_MASK; + + /* Write RX CQE base address into MMIO reg */ + writeq(priv->rx_cqe_base_dma, priv->base + MLXBF_GIGE_RX_CQ_BASE); + + /* Write RX_WQE_PI with current number of replenished buffers */ + writeq(priv->rx_q_entries, priv->base + MLXBF_GIGE_RX_WQE_PI); + + /* Enable removal of CRC during RX */ + data = readq(priv->base + MLXBF_GIGE_RX); + data |= MLXBF_GIGE_RX_STRIP_CRC_EN; + writeq(data, priv->base + MLXBF_GIGE_RX); + + /* Enable RX MAC filter pass and discard counters */ + writeq(MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC_EN, + priv->base + MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC); + writeq(MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS_EN, + priv->base + MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS); + + /* Clear MLXBF_GIGE_INT_MASK 'receive pkt' bit to + * indicate readiness to receive interrupts + */ + data = readq(priv->base + MLXBF_GIGE_INT_MASK); + data &= ~MLXBF_GIGE_INT_MASK_RX_RECEIVE_PACKET; + writeq(data, priv->base + MLXBF_GIGE_INT_MASK); + + /* Enable RX DMA to write new packets to memory */ + data = readq(priv->base + MLXBF_GIGE_RX_DMA); + data |= MLXBF_GIGE_RX_DMA_EN; + writeq(data, priv->base + MLXBF_GIGE_RX_DMA); + + writeq(ilog2(priv->rx_q_entries), + priv->base + MLXBF_GIGE_RX_WQE_SIZE_LOG2); + + return 0; + +free_wqe_and_skb: + rx_wqe_ptr = priv->rx_wqe_base; + for (j = 0; j < i; j++) { + dma_unmap_single(priv->dev, *rx_wqe_ptr, + MLXBF_GIGE_DEFAULT_BUF_SZ, DMA_FROM_DEVICE); + dev_kfree_skb(priv->rx_skb[j]); + rx_wqe_ptr++; + } + dma_free_coherent(priv->dev, wq_size, + priv->rx_wqe_base, priv->rx_wqe_base_dma); + return -ENOMEM; +} + +/* Receive Deinitialization + * This routine will free allocations done by mlxbf_gige_rx_init(), + * namely the RX WQE and RX CQE arrays, as well as all RX buffers + */ +void mlxbf_gige_rx_deinit(struct mlxbf_gige *priv) +{ + dma_addr_t *rx_wqe_ptr; + size_t size; + u64 data; + int i; + + /* Disable RX DMA to prevent packet transfers to memory */ + data = readq(priv->base + MLXBF_GIGE_RX_DMA); + data &= ~MLXBF_GIGE_RX_DMA_EN; + writeq(data, priv->base + MLXBF_GIGE_RX_DMA); + + rx_wqe_ptr = priv->rx_wqe_base; + + for (i = 0; i < priv->rx_q_entries; i++) { + dma_unmap_single(priv->dev, *rx_wqe_ptr, MLXBF_GIGE_DEFAULT_BUF_SZ, + DMA_FROM_DEVICE); + dev_kfree_skb(priv->rx_skb[i]); + rx_wqe_ptr++; + } + + size = MLXBF_GIGE_RX_WQE_SZ * priv->rx_q_entries; + dma_free_coherent(priv->dev, size, + priv->rx_wqe_base, priv->rx_wqe_base_dma); + + size = MLXBF_GIGE_RX_CQE_SZ * priv->rx_q_entries; + dma_free_coherent(priv->dev, size, + priv->rx_cqe_base, priv->rx_cqe_base_dma); + + priv->rx_wqe_base = NULL; + priv->rx_wqe_base_dma = 0; + priv->rx_cqe_base = NULL; + priv->rx_cqe_base_dma = 0; + writeq(0, priv->base + MLXBF_GIGE_RX_WQ_BASE); + writeq(0, priv->base + MLXBF_GIGE_RX_CQ_BASE); +} + +static bool mlxbf_gige_rx_packet(struct mlxbf_gige *priv, int *rx_pkts) +{ + struct net_device *netdev = priv->netdev; + struct sk_buff *skb = NULL, *rx_skb; + u16 rx_pi_rem, rx_ci_rem; + dma_addr_t *rx_wqe_addr; + dma_addr_t rx_buf_dma; + u64 *rx_cqe_addr; + u64 datalen; + u64 rx_cqe; + u16 rx_ci; + u16 rx_pi; + + /* Index into RX buffer array is rx_pi w/wrap based on RX_CQE_SIZE */ + rx_pi = readq(priv->base + MLXBF_GIGE_RX_WQE_PI); + rx_pi_rem = rx_pi % priv->rx_q_entries; + + rx_wqe_addr = priv->rx_wqe_base + rx_pi_rem; + rx_cqe_addr = priv->rx_cqe_base + rx_pi_rem; + rx_cqe = *rx_cqe_addr; + + if ((!!(rx_cqe & MLXBF_GIGE_RX_CQE_VALID_MASK)) != priv->valid_polarity) + return false; + + if ((rx_cqe & MLXBF_GIGE_RX_CQE_PKT_STATUS_MASK) == 0) { + /* Packet is OK, increment stats */ + datalen = rx_cqe & MLXBF_GIGE_RX_CQE_PKT_LEN_MASK; + netdev->stats.rx_packets++; + netdev->stats.rx_bytes += datalen; + + skb = priv->rx_skb[rx_pi_rem]; + + skb_put(skb, datalen); + + skb->ip_summed = CHECKSUM_NONE; /* device did not checksum packet */ + + skb->protocol = eth_type_trans(skb, netdev); + + /* Alloc another RX SKB for this same index */ + rx_skb = mlxbf_gige_alloc_skb(priv, MLXBF_GIGE_DEFAULT_BUF_SZ, + &rx_buf_dma, DMA_FROM_DEVICE); + if (!rx_skb) + return false; + priv->rx_skb[rx_pi_rem] = rx_skb; + dma_unmap_single(priv->dev, *rx_wqe_addr, + MLXBF_GIGE_DEFAULT_BUF_SZ, DMA_FROM_DEVICE); + *rx_wqe_addr = rx_buf_dma; + } else if (rx_cqe & MLXBF_GIGE_RX_CQE_PKT_STATUS_MAC_ERR) { + priv->stats.rx_mac_errors++; + } else if (rx_cqe & MLXBF_GIGE_RX_CQE_PKT_STATUS_TRUNCATED) { + priv->stats.rx_truncate_errors++; + } + + /* Let hardware know we've replenished one buffer */ + rx_pi++; + + /* Ensure completion of all writes before notifying HW of replenish */ + wmb(); + writeq(rx_pi, priv->base + MLXBF_GIGE_RX_WQE_PI); + + (*rx_pkts)++; + + rx_pi_rem = rx_pi % priv->rx_q_entries; + if (rx_pi_rem == 0) + priv->valid_polarity ^= 1; + rx_ci = readq(priv->base + MLXBF_GIGE_RX_CQE_PACKET_CI); + rx_ci_rem = rx_ci % priv->rx_q_entries; + + if (skb) + netif_receive_skb(skb); + + return rx_pi_rem != rx_ci_rem; +} + +/* Driver poll() function called by NAPI infrastructure */ +int mlxbf_gige_poll(struct napi_struct *napi, int budget) +{ + struct mlxbf_gige *priv; + bool remaining_pkts; + int work_done = 0; + u64 data; + + priv = container_of(napi, struct mlxbf_gige, napi); + + mlxbf_gige_handle_tx_complete(priv); + + do { + remaining_pkts = mlxbf_gige_rx_packet(priv, &work_done); + } while (remaining_pkts && work_done < budget); + + /* If amount of work done < budget, turn off NAPI polling + * via napi_complete_done(napi, work_done) and then + * re-enable interrupts. + */ + if (work_done < budget && napi_complete_done(napi, work_done)) { + /* Clear MLXBF_GIGE_INT_MASK 'receive pkt' bit to + * indicate receive readiness + */ + data = readq(priv->base + MLXBF_GIGE_INT_MASK); + data &= ~MLXBF_GIGE_INT_MASK_RX_RECEIVE_PACKET; + writeq(data, priv->base + MLXBF_GIGE_INT_MASK); + } + + return work_done; +} diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_tx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_tx.c new file mode 100644 index 000000000000..04982e888c63 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_tx.c @@ -0,0 +1,284 @@ +// SPDX-License-Identifier: GPL-2.0-only OR BSD-3-Clause + +/* Packet transmit logic for Mellanox Gigabit Ethernet driver + * + * Copyright (C) 2020-2021 NVIDIA CORPORATION & AFFILIATES + */ + +#include + +#include "mlxbf_gige.h" +#include "mlxbf_gige_regs.h" + +/* Transmit Initialization + * 1) Allocates TX WQE array using coherent DMA mapping + * 2) Allocates TX completion counter using coherent DMA mapping + */ +int mlxbf_gige_tx_init(struct mlxbf_gige *priv) +{ + size_t size; + + size = MLXBF_GIGE_TX_WQE_SZ * priv->tx_q_entries; + priv->tx_wqe_base = dma_alloc_coherent(priv->dev, size, + &priv->tx_wqe_base_dma, + GFP_KERNEL); + if (!priv->tx_wqe_base) + return -ENOMEM; + + priv->tx_wqe_next = priv->tx_wqe_base; + + /* Write TX WQE base address into MMIO reg */ + writeq(priv->tx_wqe_base_dma, priv->base + MLXBF_GIGE_TX_WQ_BASE); + + /* Allocate address for TX completion count */ + priv->tx_cc = dma_alloc_coherent(priv->dev, MLXBF_GIGE_TX_CC_SZ, + &priv->tx_cc_dma, GFP_KERNEL); + if (!priv->tx_cc) { + dma_free_coherent(priv->dev, size, + priv->tx_wqe_base, priv->tx_wqe_base_dma); + return -ENOMEM; + } + + /* Write TX CC base address into MMIO reg */ + writeq(priv->tx_cc_dma, priv->base + MLXBF_GIGE_TX_CI_UPDATE_ADDRESS); + + writeq(ilog2(priv->tx_q_entries), + priv->base + MLXBF_GIGE_TX_WQ_SIZE_LOG2); + + priv->prev_tx_ci = 0; + priv->tx_pi = 0; + + return 0; +} + +/* Transmit Deinitialization + * This routine will free allocations done by mlxbf_gige_tx_init(), + * namely the TX WQE array and the TX completion counter + */ +void mlxbf_gige_tx_deinit(struct mlxbf_gige *priv) +{ + u64 *tx_wqe_addr; + size_t size; + int i; + + tx_wqe_addr = priv->tx_wqe_base; + + for (i = 0; i < priv->tx_q_entries; i++) { + if (priv->tx_skb[i]) { + dma_unmap_single(priv->dev, *tx_wqe_addr, + priv->tx_skb[i]->len, DMA_TO_DEVICE); + dev_kfree_skb(priv->tx_skb[i]); + priv->tx_skb[i] = NULL; + } + tx_wqe_addr += 2; + } + + size = MLXBF_GIGE_TX_WQE_SZ * priv->tx_q_entries; + dma_free_coherent(priv->dev, size, + priv->tx_wqe_base, priv->tx_wqe_base_dma); + + dma_free_coherent(priv->dev, MLXBF_GIGE_TX_CC_SZ, + priv->tx_cc, priv->tx_cc_dma); + + priv->tx_wqe_base = NULL; + priv->tx_wqe_base_dma = 0; + priv->tx_cc = NULL; + priv->tx_cc_dma = 0; + priv->tx_wqe_next = NULL; + writeq(0, priv->base + MLXBF_GIGE_TX_WQ_BASE); + writeq(0, priv->base + MLXBF_GIGE_TX_CI_UPDATE_ADDRESS); +} + +/* Function that returns status of TX ring: + * 0: TX ring is full, i.e. there are no + * available un-used entries in TX ring. + * non-null: TX ring is not full, i.e. there are + * some available entries in TX ring. + * The non-null value is a measure of + * how many TX entries are available, but + * it is not the exact number of available + * entries (see below). + * + * The algorithm makes the assumption that if + * (prev_tx_ci == tx_pi) then the TX ring is empty. + * An empty ring actually has (tx_q_entries-1) + * entries, which allows the algorithm to differentiate + * the case of an empty ring vs. a full ring. + */ +static u16 mlxbf_gige_tx_buffs_avail(struct mlxbf_gige *priv) +{ + unsigned long flags; + u16 avail; + + spin_lock_irqsave(&priv->lock, flags); + + if (priv->prev_tx_ci == priv->tx_pi) + avail = priv->tx_q_entries - 1; + else + avail = ((priv->tx_q_entries + priv->prev_tx_ci - priv->tx_pi) + % priv->tx_q_entries) - 1; + + spin_unlock_irqrestore(&priv->lock, flags); + + return avail; +} + +bool mlxbf_gige_handle_tx_complete(struct mlxbf_gige *priv) +{ + struct net_device_stats *stats; + u16 tx_wqe_index; + u64 *tx_wqe_addr; + u64 tx_status; + u16 tx_ci; + + tx_status = readq(priv->base + MLXBF_GIGE_TX_STATUS); + if (tx_status & MLXBF_GIGE_TX_STATUS_DATA_FIFO_FULL) + priv->stats.tx_fifo_full++; + tx_ci = readq(priv->base + MLXBF_GIGE_TX_CONSUMER_INDEX); + stats = &priv->netdev->stats; + + /* Transmit completion logic needs to loop until the completion + * index (in SW) equals TX consumer index (from HW). These + * parameters are unsigned 16-bit values and the wrap case needs + * to be supported, that is TX consumer index wrapped from 0xFFFF + * to 0 while TX completion index is still < 0xFFFF. + */ + for (; priv->prev_tx_ci != tx_ci; priv->prev_tx_ci++) { + tx_wqe_index = priv->prev_tx_ci % priv->tx_q_entries; + /* Each TX WQE is 16 bytes. The 8 MSB store the 2KB TX + * buffer address and the 8 LSB contain information + * about the TX WQE. + */ + tx_wqe_addr = priv->tx_wqe_base + + (tx_wqe_index * MLXBF_GIGE_TX_WQE_SZ_QWORDS); + + stats->tx_packets++; + stats->tx_bytes += MLXBF_GIGE_TX_WQE_PKT_LEN(tx_wqe_addr); + + dma_unmap_single(priv->dev, *tx_wqe_addr, + priv->tx_skb[tx_wqe_index]->len, DMA_TO_DEVICE); + dev_consume_skb_any(priv->tx_skb[tx_wqe_index]); + priv->tx_skb[tx_wqe_index] = NULL; + + /* Ensure completion of updates across all cores */ + mb(); + } + + /* Since the TX ring was likely just drained, check if TX queue + * had previously been stopped and now that there are TX buffers + * available the TX queue can be awakened. + */ + if (netif_queue_stopped(priv->netdev) && + mlxbf_gige_tx_buffs_avail(priv)) + netif_wake_queue(priv->netdev); + + return true; +} + +/* Function to advance the tx_wqe_next pointer to next TX WQE */ +void mlxbf_gige_update_tx_wqe_next(struct mlxbf_gige *priv) +{ + /* Advance tx_wqe_next pointer */ + priv->tx_wqe_next += MLXBF_GIGE_TX_WQE_SZ_QWORDS; + + /* Check if 'next' pointer is beyond end of TX ring */ + /* If so, set 'next' back to 'base' pointer of ring */ + if (priv->tx_wqe_next == (priv->tx_wqe_base + + (priv->tx_q_entries * MLXBF_GIGE_TX_WQE_SZ_QWORDS))) + priv->tx_wqe_next = priv->tx_wqe_base; +} + +netdev_tx_t mlxbf_gige_start_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct mlxbf_gige *priv = netdev_priv(netdev); + long buff_addr, start_dma_page, end_dma_page; + struct sk_buff *tx_skb; + dma_addr_t tx_buf_dma; + unsigned long flags; + u64 *tx_wqe_addr; + u64 word2; + + /* If needed, linearize TX SKB as hardware DMA expects this */ + if (skb->len > MLXBF_GIGE_DEFAULT_BUF_SZ || skb_linearize(skb)) { + dev_kfree_skb(skb); + netdev->stats.tx_dropped++; + return NETDEV_TX_OK; + } + + buff_addr = (long)skb->data; + start_dma_page = buff_addr >> MLXBF_GIGE_DMA_PAGE_SHIFT; + end_dma_page = (buff_addr + skb->len - 1) >> MLXBF_GIGE_DMA_PAGE_SHIFT; + + /* Verify that payload pointer and data length of SKB to be + * transmitted does not violate the hardware DMA limitation. + */ + if (start_dma_page != end_dma_page) { + /* DMA operation would fail as-is, alloc new aligned SKB */ + tx_skb = mlxbf_gige_alloc_skb(priv, skb->len, + &tx_buf_dma, DMA_TO_DEVICE); + if (!tx_skb) { + /* Free original skb, could not alloc new aligned SKB */ + dev_kfree_skb(skb); + netdev->stats.tx_dropped++; + return NETDEV_TX_OK; + } + + skb_put_data(tx_skb, skb->data, skb->len); + + /* Free the original SKB */ + dev_kfree_skb(skb); + } else { + tx_skb = skb; + tx_buf_dma = dma_map_single(priv->dev, skb->data, + skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(priv->dev, tx_buf_dma)) { + dev_kfree_skb(skb); + netdev->stats.tx_dropped++; + return NETDEV_TX_OK; + } + } + + /* Get address of TX WQE */ + tx_wqe_addr = priv->tx_wqe_next; + + mlxbf_gige_update_tx_wqe_next(priv); + + /* Put PA of buffer address into first 64-bit word of TX WQE */ + *tx_wqe_addr = tx_buf_dma; + + /* Set TX WQE pkt_len appropriately + * NOTE: GigE silicon will automatically pad up to + * minimum packet length if needed. + */ + word2 = tx_skb->len & MLXBF_GIGE_TX_WQE_PKT_LEN_MASK; + + /* Write entire 2nd word of TX WQE */ + *(tx_wqe_addr + 1) = word2; + + spin_lock_irqsave(&priv->lock, flags); + priv->tx_skb[priv->tx_pi % priv->tx_q_entries] = tx_skb; + priv->tx_pi++; + spin_unlock_irqrestore(&priv->lock, flags); + + if (!netdev_xmit_more()) { + /* Create memory barrier before write to TX PI */ + wmb(); + writeq(priv->tx_pi, priv->base + MLXBF_GIGE_TX_PRODUCER_INDEX); + } + + /* Check if the last TX entry was just used */ + if (!mlxbf_gige_tx_buffs_avail(priv)) { + /* TX ring is full, inform stack */ + netif_stop_queue(netdev); + + /* Since there is no separate "TX complete" interrupt, need + * to explicitly schedule NAPI poll. This will trigger logic + * which processes TX completions, and will hopefully drain + * the TX ring allowing the TX queue to be awakened. + */ + napi_schedule(&priv->napi); + } + + return NETDEV_TX_OK; +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index a619d90559f7..12871c8dc7c1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -49,28 +49,6 @@ config MLXSW_I2C To compile this driver as a module, choose M here: the module will be called mlxsw_i2c. -config MLXSW_SWITCHIB - tristate "Mellanox Technologies SwitchIB and SwitchIB-2 support" - depends on MLXSW_CORE && MLXSW_PCI && NET_SWITCHDEV - default m - help - This driver supports Mellanox Technologies SwitchIB and SwitchIB-2 - Infiniband Switch ASICs. - - To compile this driver as a module, choose M here: the - module will be called mlxsw_switchib. - -config MLXSW_SWITCHX2 - tristate "Mellanox Technologies SwitchX-2 support" - depends on MLXSW_CORE && MLXSW_PCI && NET_SWITCHDEV - default m - help - This driver supports Mellanox Technologies SwitchX-2 Ethernet - Switch ASICs. - - To compile this driver as a module, choose M here: the - module will be called mlxsw_switchx2. - config MLXSW_SPECTRUM tristate "Mellanox Technologies Spectrum family support" depends on MLXSW_CORE && MLXSW_PCI && NET_SWITCHDEV && VLAN_8021Q diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index f545fd2c5896..196adeb33495 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -8,10 +8,6 @@ obj-$(CONFIG_MLXSW_PCI) += mlxsw_pci.o mlxsw_pci-objs := pci.o obj-$(CONFIG_MLXSW_I2C) += mlxsw_i2c.o mlxsw_i2c-objs := i2c.o -obj-$(CONFIG_MLXSW_SWITCHIB) += mlxsw_switchib.o -mlxsw_switchib-objs := switchib.o -obj-$(CONFIG_MLXSW_SWITCHX2) += mlxsw_switchx2.o -mlxsw_switchx2-objs := switchx2.o obj-$(CONFIG_MLXSW_SPECTRUM) += mlxsw_spectrum.o mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ spectrum_switchdev.o spectrum_router.o \ diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 7e9a7cb31720..e775f08fb464 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -630,7 +630,7 @@ static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb; int err; - skb = skb_copy(trans->tx_skb, GFP_KERNEL); + skb = skb_clone(trans->tx_skb, GFP_KERNEL); if (!skb) return -ENOMEM; @@ -1444,7 +1444,9 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, if (err) return err; - err = devlink_info_version_fixed_put(req, "fw.psid", fw_info_psid); + err = devlink_info_version_fixed_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW_PSID, + fw_info_psid); if (err) return err; @@ -1453,7 +1455,9 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, if (err) return err; - return 0; + return devlink_info_version_running_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW, + buf); } static int diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c index dd26865bd587..3713c45cfa1e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -3,6 +3,7 @@ #include #include +#include #include #include "core.h" @@ -25,8 +26,8 @@ struct mlxsw_env { static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, bool *qsfp, bool *cmis) { - char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE]; char mcia_pl[MLXSW_REG_MCIA_LEN]; + char *eeprom_tmp; u8 ident; int err; @@ -35,7 +36,7 @@ static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl); if (err) return err; - mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp); + eeprom_tmp = mlxsw_reg_mcia_eeprom_data(mcia_pl); ident = eeprom_tmp[0]; *cmis = false; switch (ident) { @@ -63,8 +64,8 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module, u16 offset, u16 size, void *data, bool qsfp, unsigned int *p_read_size) { - char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE]; char mcia_pl[MLXSW_REG_MCIA_LEN]; + char *eeprom_tmp; u16 i2c_addr; u8 page = 0; int status; @@ -115,7 +116,7 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module, if (status) return -EIO; - mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp); + eeprom_tmp = mlxsw_reg_mcia_eeprom_data(mcia_pl); memcpy(data, eeprom_tmp, size); *p_read_size = size; @@ -125,14 +126,14 @@ mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module, int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, int off, int *temp) { - char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE]; + unsigned int module_temp, module_crit, module_emerg; union { u8 buf[MLXSW_REG_MCIA_TH_ITEM_SIZE]; u16 temp; } temp_thresh; char mcia_pl[MLXSW_REG_MCIA_LEN] = {0}; char mtmp_pl[MLXSW_REG_MTMP_LEN]; - unsigned int module_temp; + char *eeprom_tmp; bool qsfp, cmis; int page; int err; @@ -142,12 +143,21 @@ int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, err = mlxsw_reg_query(core, MLXSW_REG(mtmp), mtmp_pl); if (err) return err; - mlxsw_reg_mtmp_unpack(mtmp_pl, &module_temp, NULL, NULL); + mlxsw_reg_mtmp_unpack(mtmp_pl, &module_temp, NULL, &module_crit, + &module_emerg, NULL); if (!module_temp) { *temp = 0; return 0; } + /* Validate if threshold reading is available through MTMP register, + * otherwise fallback to read through MCIA. + */ + if (module_emerg) { + *temp = off == SFP_TEMP_HIGH_WARN ? module_crit : module_emerg; + return 0; + } + /* Read Free Side Device Temperature Thresholds from page 03h * (MSB at lower byte address). * Bytes: @@ -185,7 +195,7 @@ int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, if (err) return err; - mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp); + eeprom_tmp = mlxsw_reg_mcia_eeprom_data(mcia_pl); memcpy(temp_thresh.buf, eeprom_tmp, MLXSW_REG_MCIA_TH_ITEM_SIZE); *temp = temp_thresh.temp * 1000; @@ -306,6 +316,79 @@ int mlxsw_env_get_module_eeprom(struct net_device *netdev, } EXPORT_SYMBOL(mlxsw_env_get_module_eeprom); +static int mlxsw_env_mcia_status_process(const char *mcia_pl, + struct netlink_ext_ack *extack) +{ + u8 status = mlxsw_reg_mcia_status_get(mcia_pl); + + switch (status) { + case MLXSW_REG_MCIA_STATUS_GOOD: + return 0; + case MLXSW_REG_MCIA_STATUS_NO_EEPROM_MODULE: + NL_SET_ERR_MSG_MOD(extack, "No response from module's EEPROM"); + return -EIO; + case MLXSW_REG_MCIA_STATUS_MODULE_NOT_SUPPORTED: + NL_SET_ERR_MSG_MOD(extack, "Module type not supported by the device"); + return -EOPNOTSUPP; + case MLXSW_REG_MCIA_STATUS_MODULE_NOT_CONNECTED: + NL_SET_ERR_MSG_MOD(extack, "No module present indication"); + return -EIO; + case MLXSW_REG_MCIA_STATUS_I2C_ERROR: + NL_SET_ERR_MSG_MOD(extack, "Error occurred while trying to access module's EEPROM using I2C"); + return -EIO; + case MLXSW_REG_MCIA_STATUS_MODULE_DISABLED: + NL_SET_ERR_MSG_MOD(extack, "Module is disabled"); + return -EIO; + default: + NL_SET_ERR_MSG_MOD(extack, "Unknown error"); + return -EIO; + } +} + +int +mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core, u8 module, + const struct ethtool_module_eeprom *page, + struct netlink_ext_ack *extack) +{ + u32 bytes_read = 0; + u16 device_addr; + + /* Offset cannot be larger than 2 * ETH_MODULE_EEPROM_PAGE_LEN */ + device_addr = page->offset; + + while (bytes_read < page->length) { + char mcia_pl[MLXSW_REG_MCIA_LEN]; + char *eeprom_tmp; + u8 size; + int err; + + size = min_t(u8, page->length - bytes_read, + MLXSW_REG_MCIA_EEPROM_SIZE); + + mlxsw_reg_mcia_pack(mcia_pl, module, 0, page->page, + device_addr + bytes_read, size, + page->i2c_address); + mlxsw_reg_mcia_bank_number_set(mcia_pl, page->bank); + + err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mcia), mcia_pl); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to access module's EEPROM"); + return err; + } + + err = mlxsw_env_mcia_status_process(mcia_pl, extack); + if (err) + return err; + + eeprom_tmp = mlxsw_reg_mcia_eeprom_data(mcia_pl); + memcpy(page->data + bytes_read, eeprom_tmp, size); + bytes_read += size; + } + + return bytes_read; +} +EXPORT_SYMBOL(mlxsw_env_get_module_eeprom_by_page); + static int mlxsw_env_module_has_temp_sensor(struct mlxsw_core *mlxsw_core, u8 module, bool *p_has_temp_sensor) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h index 2b23f8a87862..0bf5bd0f8a7e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h @@ -4,6 +4,8 @@ #ifndef _MLXSW_CORE_ENV_H #define _MLXSW_CORE_ENV_H +#include + struct ethtool_modinfo; struct ethtool_eeprom; @@ -17,6 +19,11 @@ int mlxsw_env_get_module_eeprom(struct net_device *netdev, struct mlxsw_core *mlxsw_core, int module, struct ethtool_eeprom *ee, u8 *data); +int +mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core, u8 module, + const struct ethtool_module_eeprom *page, + struct netlink_ext_ack *extack); + int mlxsw_env_module_overheat_counter_get(struct mlxsw_core *mlxsw_core, u8 module, u64 *p_counter); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c index 2196c946698a..d41afdfbd085 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c @@ -72,7 +72,7 @@ static ssize_t mlxsw_hwmon_temp_show(struct device *dev, dev_err(mlxsw_hwmon->bus_info->dev, "Failed to query temp sensor\n"); return err; } - mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL); + mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL); return sprintf(buf, "%d\n", temp); } @@ -95,7 +95,7 @@ static ssize_t mlxsw_hwmon_temp_max_show(struct device *dev, dev_err(mlxsw_hwmon->bus_info->dev, "Failed to query temp sensor\n"); return err; } - mlxsw_reg_mtmp_unpack(mtmp_pl, NULL, &temp_max, NULL); + mlxsw_reg_mtmp_unpack(mtmp_pl, NULL, &temp_max, NULL, NULL, NULL); return sprintf(buf, "%d\n", temp_max); } @@ -239,7 +239,7 @@ static int mlxsw_hwmon_module_temp_get(struct device *dev, dev_err(dev, "Failed to query module temperature\n"); return err; } - mlxsw_reg_mtmp_unpack(mtmp_pl, p_temp, NULL, NULL); + mlxsw_reg_mtmp_unpack(mtmp_pl, p_temp, NULL, NULL, NULL, NULL); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index 85f0ce285146..0998dcc9cac0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -149,22 +149,27 @@ mlxsw_thermal_module_trips_reset(struct mlxsw_thermal_module *tz) static int mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core, - struct mlxsw_thermal_module *tz) + struct mlxsw_thermal_module *tz, + int crit_temp, int emerg_temp) { - int crit_temp, emerg_temp; int err; - err = mlxsw_env_module_temp_thresholds_get(core, tz->module, - SFP_TEMP_HIGH_WARN, - &crit_temp); - if (err) - return err; + /* Do not try to query temperature thresholds directly from the module's + * EEPROM if we got valid thresholds from MTMP. + */ + if (!emerg_temp || !crit_temp) { + err = mlxsw_env_module_temp_thresholds_get(core, tz->module, + SFP_TEMP_HIGH_WARN, + &crit_temp); + if (err) + return err; - err = mlxsw_env_module_temp_thresholds_get(core, tz->module, - SFP_TEMP_HIGH_ALARM, - &emerg_temp); - if (err) - return err; + err = mlxsw_env_module_temp_thresholds_get(core, tz->module, + SFP_TEMP_HIGH_ALARM, + &emerg_temp); + if (err) + return err; + } if (crit_temp > emerg_temp) { dev_warn(dev, "%s : Critical threshold %d is above emergency threshold %d\n", @@ -281,7 +286,7 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev, dev_err(dev, "Failed to query temp sensor\n"); return err; } - mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL); + mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL); if (temp > 0) mlxsw_thermal_tz_score_update(thermal, tzdev, thermal->trips, temp); @@ -420,36 +425,57 @@ static int mlxsw_thermal_module_unbind(struct thermal_zone_device *tzdev, return err; } +static void +mlxsw_thermal_module_temp_and_thresholds_get(struct mlxsw_core *core, + u16 sensor_index, int *p_temp, + int *p_crit_temp, + int *p_emerg_temp) +{ + char mtmp_pl[MLXSW_REG_MTMP_LEN]; + int err; + + /* Read module temperature and thresholds. */ + mlxsw_reg_mtmp_pack(mtmp_pl, sensor_index, false, false); + err = mlxsw_reg_query(core, MLXSW_REG(mtmp), mtmp_pl); + if (err) { + /* Set temperature and thresholds to zero to avoid passing + * uninitialized data back to the caller. + */ + *p_temp = 0; + *p_crit_temp = 0; + *p_emerg_temp = 0; + + return; + } + mlxsw_reg_mtmp_unpack(mtmp_pl, p_temp, NULL, p_crit_temp, p_emerg_temp, + NULL); +} + static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev, int *p_temp) { struct mlxsw_thermal_module *tz = tzdev->devdata; struct mlxsw_thermal *thermal = tz->parent; - struct device *dev = thermal->bus_info->dev; - char mtmp_pl[MLXSW_REG_MTMP_LEN]; - int temp; + int temp, crit_temp, emerg_temp; + struct device *dev; + u16 sensor_index; int err; - /* Read module temperature. */ - mlxsw_reg_mtmp_pack(mtmp_pl, MLXSW_REG_MTMP_MODULE_INDEX_MIN + - tz->module, false, false); - err = mlxsw_reg_query(thermal->core, MLXSW_REG(mtmp), mtmp_pl); - if (err) { - /* Do not return error - in case of broken module's sensor - * it will cause error message flooding. - */ - temp = 0; - *p_temp = (int) temp; - return 0; - } - mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL); + dev = thermal->bus_info->dev; + sensor_index = MLXSW_REG_MTMP_MODULE_INDEX_MIN + tz->module; + + /* Read module temperature and thresholds. */ + mlxsw_thermal_module_temp_and_thresholds_get(thermal->core, + sensor_index, &temp, + &crit_temp, &emerg_temp); *p_temp = temp; if (!temp) return 0; /* Update trip points. */ - err = mlxsw_thermal_module_trips_update(dev, thermal->core, tz); + err = mlxsw_thermal_module_trips_update(dev, thermal->core, tz, + crit_temp, emerg_temp); if (!err && temp > 0) mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp); @@ -560,7 +586,7 @@ static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev, if (err) return err; - mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL); + mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL); if (temp > 0) mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp); @@ -717,7 +743,10 @@ mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core, struct mlxsw_thermal *thermal, u8 module) { struct mlxsw_thermal_module *module_tz; + int dummy_temp, crit_temp, emerg_temp; + u16 sensor_index; + sensor_index = MLXSW_REG_MTMP_MODULE_INDEX_MIN + module; module_tz = &thermal->tz_module_arr[module]; /* Skip if parent is already set (case of port split). */ if (module_tz->parent) @@ -728,8 +757,12 @@ mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core, sizeof(thermal->trips)); /* Initialize all trip point. */ mlxsw_thermal_module_trips_reset(module_tz); + /* Read module temperature and thresholds. */ + mlxsw_thermal_module_temp_and_thresholds_get(core, sensor_index, &dummy_temp, + &crit_temp, &emerg_temp); /* Update trip point according to the module data. */ - return mlxsw_thermal_module_trips_update(dev, core, module_tz); + return mlxsw_thermal_module_trips_update(dev, core, module_tz, + crit_temp, emerg_temp); } static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz) diff --git a/drivers/net/ethernet/mellanox/mlxsw/ib.h b/drivers/net/ethernet/mellanox/mlxsw/ib.h deleted file mode 100644 index 2d0cb0f5eb85..000000000000 --- a/drivers/net/ethernet/mellanox/mlxsw/ib.h +++ /dev/null @@ -1,9 +0,0 @@ -/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ -/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */ - -#ifndef _MLXSW_IB_H -#define _MLXSW_IB_H - -#define MLXSW_IB_DEFAULT_MTU 4096 - -#endif /* _MLXSW_IB_H */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index b34c44723f8b..d9d56c44e994 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -112,10 +112,23 @@ mlxsw_m_get_module_eeprom(struct net_device *netdev, struct ethtool_eeprom *ee, ee, data); } +static int +mlxsw_m_get_module_eeprom_by_page(struct net_device *netdev, + const struct ethtool_module_eeprom *page, + struct netlink_ext_ack *extack) +{ + struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev); + struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core; + + return mlxsw_env_get_module_eeprom_by_page(core, mlxsw_m_port->module, + page, extack); +} + static const struct ethtool_ops mlxsw_m_port_ethtool_ops = { .get_drvinfo = mlxsw_m_module_get_drvinfo, .get_module_info = mlxsw_m_get_module_info, .get_module_eeprom = mlxsw_m_get_module_eeprom, + .get_module_eeprom_by_page = mlxsw_m_get_module_eeprom_by_page, }; static int @@ -234,6 +247,7 @@ static void mlxsw_m_port_remove(struct mlxsw_m *mlxsw_m, u8 local_port) static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port, u8 *last_module) { + unsigned int max_ports = mlxsw_core_max_ports(mlxsw_m->core); u8 module, width; int err; @@ -249,6 +263,9 @@ static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port, if (module == *last_module) return 0; *last_module = module; + + if (WARN_ON_ONCE(module >= max_ports)) + return -EINVAL; mlxsw_m->module_to_port[module] = ++mlxsw_m->max_ports; return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 8e8456811384..13b0259f7ea6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1426,11 +1426,6 @@ static int mlxsw_pci_sys_ready_wait(struct mlxsw_pci *mlxsw_pci, unsigned long end; u32 val; - if (id->device == PCI_DEVICE_ID_MELLANOX_SWITCHX2) { - msleep(MLXSW_PCI_SW_RESET_TIMEOUT_MSECS); - return 0; - } - /* We must wait for the HW to become responsive. */ msleep(MLXSW_PCI_SW_RESET_WAIT_MSECS); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h index 5b1323645a5d..9899c1a2ea8f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h @@ -6,12 +6,9 @@ #include -#define PCI_DEVICE_ID_MELLANOX_SWITCHX2 0xc738 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM 0xcb84 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM2 0xcf6c #define PCI_DEVICE_ID_MELLANOX_SPECTRUM3 0xcf70 -#define PCI_DEVICE_ID_MELLANOX_SWITCHIB 0xcb20 -#define PCI_DEVICE_ID_MELLANOX_SWITCHIB2 0xcf08 #if IS_ENABLED(CONFIG_MLXSW_PCI) diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 2bc5a9003c6d..6fbda6ebd590 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -8305,6 +8305,8 @@ enum { MLXSW_REG_RECR2_TCP_UDP_EN_IPV4 = 7, /* Enable TCP/UDP header fields if packet is IPv6 */ MLXSW_REG_RECR2_TCP_UDP_EN_IPV6 = 8, + + __MLXSW_REG_RECR2_HEADER_CNT, }; /* reg_recr2_outer_header_enables @@ -8339,6 +8341,8 @@ enum { MLXSW_REG_RECR2_TCP_UDP_SPORT = 74, /* TCP/UDP Destination Port */ MLXSW_REG_RECR2_TCP_UDP_DPORT = 75, + + __MLXSW_REG_RECR2_FIELD_CNT, }; /* reg_recr2_outer_header_fields_enable @@ -8347,47 +8351,47 @@ enum { */ MLXSW_ITEM_BIT_ARRAY(reg, recr2, outer_header_fields_enable, 0x14, 0x14, 1); -static inline void mlxsw_reg_recr2_ipv4_sip_enable(char *payload) -{ - int i; +/* reg_recr2_inner_header_enables + * Bit mask where each bit enables a specific inner layer to be included in the + * hash calculation. Same values as reg_recr2_outer_header_enables. + * Access: RW + */ +MLXSW_ITEM_BIT_ARRAY(reg, recr2, inner_header_enables, 0x2C, 0x04, 1); - for (i = MLXSW_REG_RECR2_IPV4_SIP0; i <= MLXSW_REG_RECR2_IPV4_SIP3; i++) - mlxsw_reg_recr2_outer_header_fields_enable_set(payload, i, - true); -} +enum { + /* Inner IPv4 Source IP */ + MLXSW_REG_RECR2_INNER_IPV4_SIP0 = 3, + MLXSW_REG_RECR2_INNER_IPV4_SIP3 = 6, + /* Inner IPv4 Destination IP */ + MLXSW_REG_RECR2_INNER_IPV4_DIP0 = 7, + MLXSW_REG_RECR2_INNER_IPV4_DIP3 = 10, + /* Inner IP Protocol */ + MLXSW_REG_RECR2_INNER_IPV4_PROTOCOL = 11, + /* Inner IPv6 Source IP */ + MLXSW_REG_RECR2_INNER_IPV6_SIP0_7 = 12, + MLXSW_REG_RECR2_INNER_IPV6_SIP8 = 20, + MLXSW_REG_RECR2_INNER_IPV6_SIP15 = 27, + /* Inner IPv6 Destination IP */ + MLXSW_REG_RECR2_INNER_IPV6_DIP0_7 = 28, + MLXSW_REG_RECR2_INNER_IPV6_DIP8 = 36, + MLXSW_REG_RECR2_INNER_IPV6_DIP15 = 43, + /* Inner IPv6 Next Header */ + MLXSW_REG_RECR2_INNER_IPV6_NEXT_HEADER = 44, + /* Inner IPv6 Flow Label */ + MLXSW_REG_RECR2_INNER_IPV6_FLOW_LABEL = 45, + /* Inner TCP/UDP Source Port */ + MLXSW_REG_RECR2_INNER_TCP_UDP_SPORT = 46, + /* Inner TCP/UDP Destination Port */ + MLXSW_REG_RECR2_INNER_TCP_UDP_DPORT = 47, -static inline void mlxsw_reg_recr2_ipv4_dip_enable(char *payload) -{ - int i; + __MLXSW_REG_RECR2_INNER_FIELD_CNT, +}; - for (i = MLXSW_REG_RECR2_IPV4_DIP0; i <= MLXSW_REG_RECR2_IPV4_DIP3; i++) - mlxsw_reg_recr2_outer_header_fields_enable_set(payload, i, - true); -} - -static inline void mlxsw_reg_recr2_ipv6_sip_enable(char *payload) -{ - int i = MLXSW_REG_RECR2_IPV6_SIP0_7; - - mlxsw_reg_recr2_outer_header_fields_enable_set(payload, i, true); - - i = MLXSW_REG_RECR2_IPV6_SIP8; - for (; i <= MLXSW_REG_RECR2_IPV6_SIP15; i++) - mlxsw_reg_recr2_outer_header_fields_enable_set(payload, i, - true); -} - -static inline void mlxsw_reg_recr2_ipv6_dip_enable(char *payload) -{ - int i = MLXSW_REG_RECR2_IPV6_DIP0_7; - - mlxsw_reg_recr2_outer_header_fields_enable_set(payload, i, true); - - i = MLXSW_REG_RECR2_IPV6_DIP8; - for (; i <= MLXSW_REG_RECR2_IPV6_DIP15; i++) - mlxsw_reg_recr2_outer_header_fields_enable_set(payload, i, - true); -} +/* reg_recr2_inner_header_fields_enable + * Inner packet fields to enable for ECMP hash subject to inner_header_enables. + * Access: RW + */ +MLXSW_ITEM_BIT_ARRAY(reg, recr2, inner_header_fields_enable, 0x30, 0x08, 1); static inline void mlxsw_reg_recr2_pack(char *payload, u32 seed) { @@ -9459,6 +9463,14 @@ MLXSW_ITEM32(reg, mtmp, sensor_index, 0x00, 0, 12); ((s16)((GENMASK(15, 0) + (v_) + 1) \ * 125)); }) +/* reg_mtmp_max_operational_temperature + * The highest temperature in the nominal operational range. Reading is in + * 0.125 Celsius degrees units. + * In case of module this is SFF critical temperature threshold. + * Access: RO + */ +MLXSW_ITEM32(reg, mtmp, max_operational_temperature, 0x04, 16, 16); + /* reg_mtmp_temperature * Temperature reading from the sensor. Reading is in 0.125 Celsius * degrees units. @@ -9537,7 +9549,9 @@ static inline void mlxsw_reg_mtmp_pack(char *payload, u16 sensor_index, } static inline void mlxsw_reg_mtmp_unpack(char *payload, int *p_temp, - int *p_max_temp, char *sensor_name) + int *p_max_temp, int *p_temp_hi, + int *p_max_oper_temp, + char *sensor_name) { s16 temp; @@ -9549,6 +9563,14 @@ static inline void mlxsw_reg_mtmp_unpack(char *payload, int *p_temp, temp = mlxsw_reg_mtmp_max_temperature_get(payload); *p_max_temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp); } + if (p_temp_hi) { + temp = mlxsw_reg_mtmp_temperature_threshold_hi_get(payload); + *p_temp_hi = MLXSW_REG_MTMP_TEMP_TO_MC(temp); + } + if (p_max_oper_temp) { + temp = mlxsw_reg_mtmp_max_operational_temperature_get(payload); + *p_max_oper_temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp); + } if (sensor_name) mlxsw_reg_mtmp_sensor_name_memcpy_from(payload, sensor_name); } @@ -9668,6 +9690,20 @@ MLXSW_ITEM32(reg, mcia, l, 0x00, 31, 1); */ MLXSW_ITEM32(reg, mcia, module, 0x00, 16, 8); +enum { + MLXSW_REG_MCIA_STATUS_GOOD = 0, + /* No response from module's EEPROM. */ + MLXSW_REG_MCIA_STATUS_NO_EEPROM_MODULE = 1, + /* Module type not supported by the device. */ + MLXSW_REG_MCIA_STATUS_MODULE_NOT_SUPPORTED = 2, + /* No module present indication. */ + MLXSW_REG_MCIA_STATUS_MODULE_NOT_CONNECTED = 3, + /* Error occurred while trying to access module's EEPROM using I2C. */ + MLXSW_REG_MCIA_STATUS_I2C_ERROR = 9, + /* Module is disabled. */ + MLXSW_REG_MCIA_STATUS_MODULE_DISABLED = 16, +}; + /* reg_mcia_status * Module status. * Access: RO @@ -9692,6 +9728,12 @@ MLXSW_ITEM32(reg, mcia, page_number, 0x04, 16, 8); */ MLXSW_ITEM32(reg, mcia, device_address, 0x04, 0, 16); +/* reg_mcia_bank_number + * Bank number. + * Access: Index + */ +MLXSW_ITEM32(reg, mcia, bank_number, 0x08, 16, 8); + /* reg_mcia_size * Number of bytes to read/write (up to 48 bytes). * Access: RW diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index bca0354482cb..88699e678544 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2125,9 +2125,14 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg, struct mlxsw_sp *mlxsw_sp = priv; struct mlxsw_sp_port *mlxsw_sp_port; enum mlxsw_reg_pude_oper_status status; + unsigned int max_ports; u8 local_port; + max_ports = mlxsw_core_max_ports(mlxsw_sp->core); local_port = mlxsw_reg_pude_local_port_get(pude_pl); + + if (WARN_ON_ONCE(local_port >= max_ports)) + return; mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) return; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 37ff29a1686e..9de160e740b2 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -364,7 +364,7 @@ static u16 mlxsw_sp_hdroom_buf_delay_get(const struct mlxsw_sp *mlxsw_sp, static u32 mlxsw_sp_hdroom_int_buf_size_get(struct mlxsw_sp *mlxsw_sp, int mtu, u32 speed) { - u32 buffsize = mlxsw_sp->sb_ops->int_buf_size_get(speed, mtu); + u32 buffsize = mlxsw_sp->sb_ops->int_buf_size_get(mtu, speed); return mlxsw_sp_bytes_cells(mlxsw_sp, buffsize) + 1; } @@ -388,8 +388,8 @@ void mlxsw_sp_hdroom_bufs_reset_sizes(struct mlxsw_sp_port *mlxsw_sp_port, int i; /* Internal buffer. */ - reserve_cells = mlxsw_sp_hdroom_int_buf_size_get(mlxsw_sp, mlxsw_sp_port->max_speed, - mlxsw_sp_port->max_mtu); + reserve_cells = mlxsw_sp_hdroom_int_buf_size_get(mlxsw_sp, mlxsw_sp_port->max_mtu, + mlxsw_sp_port->max_speed); reserve_cells = mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, reserve_cells); hdroom->int_buf.reserve_cells = reserve_cells; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c index c8061beed6db..267590a0eee7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c @@ -1050,6 +1050,19 @@ static int mlxsw_sp_get_module_eeprom(struct net_device *netdev, return err; } +static int +mlxsw_sp_get_module_eeprom_by_page(struct net_device *dev, + const struct ethtool_module_eeprom *page, + struct netlink_ext_ack *extack) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + u8 module = mlxsw_sp_port->mapping.module; + + return mlxsw_env_get_module_eeprom_by_page(mlxsw_sp->core, module, page, + extack); +} + static int mlxsw_sp_get_ts_info(struct net_device *netdev, struct ethtool_ts_info *info) { @@ -1199,6 +1212,7 @@ const struct ethtool_ops mlxsw_sp_port_ethtool_ops = { .set_link_ksettings = mlxsw_sp_port_set_link_ksettings, .get_module_info = mlxsw_sp_get_module_info, .get_module_eeprom = mlxsw_sp_get_module_eeprom, + .get_module_eeprom_by_page = mlxsw_sp_get_module_eeprom_by_page, .get_ts_info = mlxsw_sp_get_ts_info, .get_eth_phy_stats = mlxsw_sp_get_eth_phy_stats, .get_eth_mac_stats = mlxsw_sp_get_eth_mac_stats, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index d6e9ecb14681..bfef65d1587c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -568,10 +568,13 @@ void mlxsw_sp1_ptp_got_timestamp(struct mlxsw_sp *mlxsw_sp, bool ingress, u8 domain_number, u16 sequence_id, u64 timestamp) { + unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); struct mlxsw_sp_port *mlxsw_sp_port; struct mlxsw_sp1_ptp_key key; u8 types; + if (WARN_ON_ONCE(local_port >= max_ports)) + return; mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) return; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 41259c0004d1..7e221ef01437 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2282,6 +2282,7 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp, char *rauhtd_pl, int ent_index) { + u64 max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); struct net_device *dev; struct neighbour *n; __be32 dipn; @@ -2290,6 +2291,8 @@ static void mlxsw_sp_router_neigh_ent_ipv4_process(struct mlxsw_sp *mlxsw_sp, mlxsw_reg_rauhtd_ent_ipv4_unpack(rauhtd_pl, ent_index, &rif, &dip); + if (WARN_ON_ONCE(rif >= max_rifs)) + return; if (!mlxsw_sp->router->rifs[rif]) { dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect RIF in neighbour entry\n"); return; @@ -3841,8 +3844,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, bool offload_change = false; u32 adj_index; bool old_adj_index_valid; - int i, err2, err = 0; u32 old_adj_index; + int i, err2, err; if (!nhgi->gateway) return mlxsw_sp_nexthop_fib_entries_update(mlxsw_sp, nh_grp); @@ -3872,11 +3875,13 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp, return 0; } mlxsw_sp_nexthop_group_normalize(nhgi); - if (!nhgi->sum_norm_weight) + if (!nhgi->sum_norm_weight) { /* No neigh of this group is connected so we just set * the trap and let everthing flow through kernel. */ + err = 0; goto set_trap; + } ecmp_size = nhgi->sum_norm_weight; err = mlxsw_sp_fix_adj_grp_size(mlxsw_sp, &ecmp_size); @@ -4307,9 +4312,6 @@ static void mlxsw_sp_nexthop4_event(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_key key; struct mlxsw_sp_nexthop *nh; - if (mlxsw_sp->router->aborted) - return; - key.fib_nh = fib_nh; nh = mlxsw_sp_nexthop_lookup(mlxsw_sp, key); if (!nh) @@ -5405,7 +5407,6 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp, ipv6_addr_equal((const struct in6_addr *) &nh->gw_addr, &rt->fib6_nh->fib_nh_gw6)) return nh; - continue; } return NULL; @@ -6417,9 +6418,6 @@ mlxsw_sp_router_fib4_replace(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node; int err; - if (mlxsw_sp->router->aborted) - return 0; - if (fen_info->fi->nh && !mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, fen_info->fi->nh->id)) return 0; @@ -6480,9 +6478,6 @@ static int mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node; int err; - if (mlxsw_sp->router->aborted) - return 0; - fib4_entry = mlxsw_sp_fib4_entry_lookup(mlxsw_sp, fen_info); if (!fib4_entry) return 0; @@ -7065,9 +7060,6 @@ static int mlxsw_sp_router_fib6_replace(struct mlxsw_sp *mlxsw_sp, struct fib6_info *rt = rt_arr[0]; int err; - if (mlxsw_sp->router->aborted) - return 0; - if (rt->fib6_src.plen) return -EINVAL; @@ -7131,9 +7123,6 @@ static int mlxsw_sp_router_fib6_append(struct mlxsw_sp *mlxsw_sp, struct fib6_info *rt = rt_arr[0]; int err; - if (mlxsw_sp->router->aborted) - return 0; - if (rt->fib6_src.plen) return -EINVAL; @@ -7175,9 +7164,6 @@ static int mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, struct fib6_info *rt = rt_arr[0]; int err; - if (mlxsw_sp->router->aborted) - return 0; - if (mlxsw_sp_fib6_rt_should_ignore(rt)) return 0; @@ -7206,55 +7192,6 @@ static int mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, return err; } -static int __mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp, - enum mlxsw_sp_l3proto proto, - u8 tree_id) -{ - const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto]; - enum mlxsw_reg_ralxx_protocol ralxx_proto = - (enum mlxsw_reg_ralxx_protocol) proto; - struct mlxsw_sp_fib_entry_priv *priv; - char xralta_pl[MLXSW_REG_XRALTA_LEN]; - char xralst_pl[MLXSW_REG_XRALST_LEN]; - int i, err; - - mlxsw_reg_xralta_pack(xralta_pl, true, ralxx_proto, tree_id); - err = ll_ops->ralta_write(mlxsw_sp, xralta_pl); - if (err) - return err; - - mlxsw_reg_xralst_pack(xralst_pl, 0xff, tree_id); - err = ll_ops->ralst_write(mlxsw_sp, xralst_pl); - if (err) - return err; - - for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { - struct mlxsw_sp_fib_entry_op_ctx *op_ctx = mlxsw_sp->router->ll_op_ctx; - struct mlxsw_sp_vr *vr = &mlxsw_sp->router->vrs[i]; - char xraltb_pl[MLXSW_REG_XRALTB_LEN]; - - mlxsw_sp_fib_entry_op_ctx_clear(op_ctx); - mlxsw_reg_xraltb_pack(xraltb_pl, vr->id, ralxx_proto, tree_id); - err = ll_ops->raltb_write(mlxsw_sp, xraltb_pl); - if (err) - return err; - - priv = mlxsw_sp_fib_entry_priv_create(ll_ops); - if (IS_ERR(priv)) - return PTR_ERR(priv); - - ll_ops->fib_entry_pack(op_ctx, proto, MLXSW_SP_FIB_ENTRY_OP_WRITE, - vr->id, 0, NULL, priv); - ll_ops->fib_entry_act_ip2me_pack(op_ctx); - err = ll_ops->fib_entry_commit(mlxsw_sp, op_ctx, NULL); - mlxsw_sp_fib_entry_priv_put(priv); - if (err) - return err; - } - - return 0; -} - static struct mlxsw_sp_mr_table * mlxsw_sp_router_fibmr_family_to_table(struct mlxsw_sp_vr *vr, int family) { @@ -7271,9 +7208,6 @@ static int mlxsw_sp_router_fibmr_add(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_mr_table *mrt; struct mlxsw_sp_vr *vr; - if (mlxsw_sp->router->aborted) - return 0; - vr = mlxsw_sp_vr_get(mlxsw_sp, men_info->tb_id, NULL); if (IS_ERR(vr)) return PTR_ERR(vr); @@ -7288,9 +7222,6 @@ static void mlxsw_sp_router_fibmr_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_mr_table *mrt; struct mlxsw_sp_vr *vr; - if (mlxsw_sp->router->aborted) - return; - vr = mlxsw_sp_vr_find(mlxsw_sp, men_info->tb_id); if (WARN_ON(!vr)) return; @@ -7308,9 +7239,6 @@ mlxsw_sp_router_fibmr_vif_add(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif; struct mlxsw_sp_vr *vr; - if (mlxsw_sp->router->aborted) - return 0; - vr = mlxsw_sp_vr_get(mlxsw_sp, ven_info->tb_id, NULL); if (IS_ERR(vr)) return PTR_ERR(vr); @@ -7329,9 +7257,6 @@ mlxsw_sp_router_fibmr_vif_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_mr_table *mrt; struct mlxsw_sp_vr *vr; - if (mlxsw_sp->router->aborted) - return; - vr = mlxsw_sp_vr_find(mlxsw_sp, ven_info->tb_id); if (WARN_ON(!vr)) return; @@ -7341,25 +7266,6 @@ mlxsw_sp_router_fibmr_vif_del(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_vr_put(mlxsw_sp, vr); } -static int mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp) -{ - enum mlxsw_sp_l3proto proto = MLXSW_SP_L3_PROTO_IPV4; - int err; - - err = __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto, - MLXSW_SP_LPM_TREE_MIN); - if (err) - return err; - - /* The multicast router code does not need an abort trap as by default, - * packets that don't match any routes are trapped to the CPU. - */ - - proto = MLXSW_SP_L3_PROTO_IPV6; - return __mlxsw_sp_router_set_abort_trap(mlxsw_sp, proto, - MLXSW_SP_LPM_TREE_MIN + 1); -} - static void mlxsw_sp_fib4_node_flush(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node) { @@ -7446,20 +7352,6 @@ static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) mlxsw_sp->router->adj_discard_index_valid = false; } -static void mlxsw_sp_router_fib_abort(struct mlxsw_sp *mlxsw_sp) -{ - int err; - - if (mlxsw_sp->router->aborted) - return; - dev_warn(mlxsw_sp->bus_info->dev, "FIB abort triggered. Note that FIB entries are no longer being offloaded to this device.\n"); - mlxsw_sp_router_fib_flush(mlxsw_sp); - mlxsw_sp->router->aborted = true; - err = mlxsw_sp_router_set_abort_trap(mlxsw_sp); - if (err) - dev_warn(mlxsw_sp->bus_info->dev, "Failed to set abort trap.\n"); -} - struct mlxsw_sp_fib6_event { struct fib6_info **rt_arr; unsigned int nrt6; @@ -7541,7 +7433,7 @@ static void mlxsw_sp_router_fib4_event_process(struct mlxsw_sp *mlxsw_sp, err = mlxsw_sp_router_fib4_replace(mlxsw_sp, op_ctx, &fib_event->fen_info); if (err) { mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); - mlxsw_sp_router_fib_abort(mlxsw_sp); + dev_warn(mlxsw_sp->bus_info->dev, "FIB replace failed.\n"); mlxsw_sp_fib4_offload_failed_flag_set(mlxsw_sp, &fib_event->fen_info); } @@ -7576,7 +7468,7 @@ static void mlxsw_sp_router_fib6_event_process(struct mlxsw_sp *mlxsw_sp, fib_event->fib6_event.nrt6); if (err) { mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); - mlxsw_sp_router_fib_abort(mlxsw_sp); + dev_warn(mlxsw_sp->bus_info->dev, "FIB replace failed.\n"); mlxsw_sp_fib6_offload_failed_flag_set(mlxsw_sp, fib6_event->rt_arr, fib6_event->nrt6); @@ -7588,7 +7480,7 @@ static void mlxsw_sp_router_fib6_event_process(struct mlxsw_sp *mlxsw_sp, fib_event->fib6_event.nrt6); if (err) { mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); - mlxsw_sp_router_fib_abort(mlxsw_sp); + dev_warn(mlxsw_sp->bus_info->dev, "FIB append failed.\n"); mlxsw_sp_fib6_offload_failed_flag_set(mlxsw_sp, fib6_event->rt_arr, fib6_event->nrt6); @@ -7620,7 +7512,7 @@ static void mlxsw_sp_router_fibmr_event_process(struct mlxsw_sp *mlxsw_sp, err = mlxsw_sp_router_fibmr_add(mlxsw_sp, &fib_event->men_info, replace); if (err) - mlxsw_sp_router_fib_abort(mlxsw_sp); + dev_warn(mlxsw_sp->bus_info->dev, "MR entry add failed.\n"); mr_cache_put(fib_event->men_info.mfc); break; case FIB_EVENT_ENTRY_DEL: @@ -7631,7 +7523,7 @@ static void mlxsw_sp_router_fibmr_event_process(struct mlxsw_sp *mlxsw_sp, err = mlxsw_sp_router_fibmr_vif_add(mlxsw_sp, &fib_event->ven_info); if (err) - mlxsw_sp_router_fib_abort(mlxsw_sp); + dev_warn(mlxsw_sp->bus_info->dev, "MR VIF add failed.\n"); dev_put(fib_event->ven_info.dev); break; case FIB_EVENT_VIF_DEL: @@ -7795,9 +7687,6 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event, if (event == FIB_EVENT_RULE_DEL) return 0; - if (mlxsw_sp->router->aborted) - return 0; - fr_info = container_of(info, struct fib_rule_notifier_info, info); rule = fr_info->rule; @@ -7855,10 +7744,6 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, case FIB_EVENT_ENTRY_ADD: case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_APPEND: - if (router->aborted) { - NL_SET_ERR_MSG_MOD(info->extack, "FIB offload was aborted. Not configuring route"); - return notifier_from_errno(-EINVAL); - } if (info->family == AF_INET) { struct fib_entry_notifier_info *fen_info = ptr; @@ -9594,66 +9479,229 @@ static void mlxsw_sp_router_fib_dump_flush(struct notifier_block *nb) } #ifdef CONFIG_IP_ROUTE_MULTIPATH -static void mlxsw_sp_mp_hash_header_set(char *recr2_pl, int header) +struct mlxsw_sp_mp_hash_config { + DECLARE_BITMAP(headers, __MLXSW_REG_RECR2_HEADER_CNT); + DECLARE_BITMAP(fields, __MLXSW_REG_RECR2_FIELD_CNT); + DECLARE_BITMAP(inner_headers, __MLXSW_REG_RECR2_HEADER_CNT); + DECLARE_BITMAP(inner_fields, __MLXSW_REG_RECR2_INNER_FIELD_CNT); +}; + +#define MLXSW_SP_MP_HASH_HEADER_SET(_headers, _header) \ + bitmap_set(_headers, MLXSW_REG_RECR2_##_header, 1) + +#define MLXSW_SP_MP_HASH_FIELD_SET(_fields, _field) \ + bitmap_set(_fields, MLXSW_REG_RECR2_##_field, 1) + +#define MLXSW_SP_MP_HASH_FIELD_RANGE_SET(_fields, _field, _nr) \ + bitmap_set(_fields, MLXSW_REG_RECR2_##_field, _nr) + +static void mlxsw_sp_mp_hash_inner_l3(struct mlxsw_sp_mp_hash_config *config) { - mlxsw_reg_recr2_outer_header_enables_set(recr2_pl, header, true); + unsigned long *inner_headers = config->inner_headers; + unsigned long *inner_fields = config->inner_fields; + + /* IPv4 inner */ + MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV4_EN_NOT_TCP_NOT_UDP); + MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV4_EN_TCP_UDP); + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV4_SIP0, 4); + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV4_DIP0, 4); + /* IPv6 inner */ + MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV6_EN_NOT_TCP_NOT_UDP); + MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV6_EN_TCP_UDP); + MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_SIP0_7); + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV6_SIP8, 8); + MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_DIP0_7); + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV6_DIP8, 8); + MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_NEXT_HEADER); + MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_FLOW_LABEL); } -static void mlxsw_sp_mp_hash_field_set(char *recr2_pl, int field) +static void mlxsw_sp_mp4_hash_outer_addr(struct mlxsw_sp_mp_hash_config *config) { - mlxsw_reg_recr2_outer_header_fields_enable_set(recr2_pl, field, true); + unsigned long *headers = config->headers; + unsigned long *fields = config->fields; + + MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV4_EN_NOT_TCP_NOT_UDP); + MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV4_EN_TCP_UDP); + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV4_SIP0, 4); + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV4_DIP0, 4); } -static void mlxsw_sp_mp4_hash_init(struct mlxsw_sp *mlxsw_sp, char *recr2_pl) +static void +mlxsw_sp_mp_hash_inner_custom(struct mlxsw_sp_mp_hash_config *config, + u32 hash_fields) +{ + unsigned long *inner_headers = config->inner_headers; + unsigned long *inner_fields = config->inner_fields; + + /* IPv4 Inner */ + MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV4_EN_NOT_TCP_NOT_UDP); + MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV4_EN_TCP_UDP); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV4_SIP0, 4); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV4_DIP0, 4); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) + MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV4_PROTOCOL); + /* IPv6 inner */ + MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV6_EN_NOT_TCP_NOT_UDP); + MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, IPV6_EN_TCP_UDP); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) { + MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_SIP0_7); + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV6_SIP8, 8); + } + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) { + MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_DIP0_7); + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(inner_fields, INNER_IPV6_DIP8, 8); + } + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) + MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_NEXT_HEADER); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) + MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_IPV6_FLOW_LABEL); + /* L4 inner */ + MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, TCP_UDP_EN_IPV4); + MLXSW_SP_MP_HASH_HEADER_SET(inner_headers, TCP_UDP_EN_IPV6); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) + MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_TCP_UDP_SPORT); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) + MLXSW_SP_MP_HASH_FIELD_SET(inner_fields, INNER_TCP_UDP_DPORT); +} + +static void mlxsw_sp_mp4_hash_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mp_hash_config *config) { struct net *net = mlxsw_sp_net(mlxsw_sp); - bool only_l3 = !net->ipv4.sysctl_fib_multipath_hash_policy; + unsigned long *headers = config->headers; + unsigned long *fields = config->fields; + u32 hash_fields; - mlxsw_sp_mp_hash_header_set(recr2_pl, - MLXSW_REG_RECR2_IPV4_EN_NOT_TCP_NOT_UDP); - mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_IPV4_EN_TCP_UDP); - mlxsw_reg_recr2_ipv4_sip_enable(recr2_pl); - mlxsw_reg_recr2_ipv4_dip_enable(recr2_pl); - if (only_l3) - return; - mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_TCP_UDP_EN_IPV4); - mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_IPV4_PROTOCOL); - mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_TCP_UDP_SPORT); - mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_TCP_UDP_DPORT); + switch (net->ipv4.sysctl_fib_multipath_hash_policy) { + case 0: + mlxsw_sp_mp4_hash_outer_addr(config); + break; + case 1: + mlxsw_sp_mp4_hash_outer_addr(config); + MLXSW_SP_MP_HASH_HEADER_SET(headers, TCP_UDP_EN_IPV4); + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV4_PROTOCOL); + MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_SPORT); + MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_DPORT); + break; + case 2: + /* Outer */ + mlxsw_sp_mp4_hash_outer_addr(config); + /* Inner */ + mlxsw_sp_mp_hash_inner_l3(config); + break; + case 3: + hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + /* Outer */ + MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV4_EN_NOT_TCP_NOT_UDP); + MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV4_EN_TCP_UDP); + MLXSW_SP_MP_HASH_HEADER_SET(headers, TCP_UDP_EN_IPV4); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV4_SIP0, 4); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV4_DIP0, 4); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV4_PROTOCOL); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) + MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_SPORT); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) + MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_DPORT); + /* Inner */ + mlxsw_sp_mp_hash_inner_custom(config, hash_fields); + break; + } } -static void mlxsw_sp_mp6_hash_init(struct mlxsw_sp *mlxsw_sp, char *recr2_pl) +static void mlxsw_sp_mp6_hash_outer_addr(struct mlxsw_sp_mp_hash_config *config) { - bool only_l3 = !ip6_multipath_hash_policy(mlxsw_sp_net(mlxsw_sp)); + unsigned long *headers = config->headers; + unsigned long *fields = config->fields; - mlxsw_sp_mp_hash_header_set(recr2_pl, - MLXSW_REG_RECR2_IPV6_EN_NOT_TCP_NOT_UDP); - mlxsw_sp_mp_hash_header_set(recr2_pl, MLXSW_REG_RECR2_IPV6_EN_TCP_UDP); - mlxsw_reg_recr2_ipv6_sip_enable(recr2_pl); - mlxsw_reg_recr2_ipv6_dip_enable(recr2_pl); - mlxsw_sp_mp_hash_field_set(recr2_pl, MLXSW_REG_RECR2_IPV6_NEXT_HEADER); - if (only_l3) { - mlxsw_sp_mp_hash_field_set(recr2_pl, - MLXSW_REG_RECR2_IPV6_FLOW_LABEL); - } else { - mlxsw_sp_mp_hash_header_set(recr2_pl, - MLXSW_REG_RECR2_TCP_UDP_EN_IPV6); - mlxsw_sp_mp_hash_field_set(recr2_pl, - MLXSW_REG_RECR2_TCP_UDP_SPORT); - mlxsw_sp_mp_hash_field_set(recr2_pl, - MLXSW_REG_RECR2_TCP_UDP_DPORT); + MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV6_EN_NOT_TCP_NOT_UDP); + MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV6_EN_TCP_UDP); + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_SIP0_7); + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV6_SIP8, 8); + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_DIP0_7); + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV6_DIP8, 8); +} + +static void mlxsw_sp_mp6_hash_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_mp_hash_config *config) +{ + u32 hash_fields = ip6_multipath_hash_fields(mlxsw_sp_net(mlxsw_sp)); + unsigned long *headers = config->headers; + unsigned long *fields = config->fields; + + switch (ip6_multipath_hash_policy(mlxsw_sp_net(mlxsw_sp))) { + case 0: + mlxsw_sp_mp6_hash_outer_addr(config); + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_NEXT_HEADER); + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_FLOW_LABEL); + break; + case 1: + mlxsw_sp_mp6_hash_outer_addr(config); + MLXSW_SP_MP_HASH_HEADER_SET(headers, TCP_UDP_EN_IPV6); + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_NEXT_HEADER); + MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_SPORT); + MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_DPORT); + break; + case 2: + /* Outer */ + mlxsw_sp_mp6_hash_outer_addr(config); + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_NEXT_HEADER); + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_FLOW_LABEL); + /* Inner */ + mlxsw_sp_mp_hash_inner_l3(config); + break; + case 3: + /* Outer */ + MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV6_EN_NOT_TCP_NOT_UDP); + MLXSW_SP_MP_HASH_HEADER_SET(headers, IPV6_EN_TCP_UDP); + MLXSW_SP_MP_HASH_HEADER_SET(headers, TCP_UDP_EN_IPV6); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) { + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_SIP0_7); + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV6_SIP8, 8); + } + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) { + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_DIP0_7); + MLXSW_SP_MP_HASH_FIELD_RANGE_SET(fields, IPV6_DIP8, 8); + } + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_NEXT_HEADER); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) + MLXSW_SP_MP_HASH_FIELD_SET(fields, IPV6_FLOW_LABEL); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) + MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_SPORT); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) + MLXSW_SP_MP_HASH_FIELD_SET(fields, TCP_UDP_DPORT); + /* Inner */ + mlxsw_sp_mp_hash_inner_custom(config, hash_fields); + break; } } static int mlxsw_sp_mp_hash_init(struct mlxsw_sp *mlxsw_sp) { + struct mlxsw_sp_mp_hash_config config = {}; char recr2_pl[MLXSW_REG_RECR2_LEN]; + unsigned long bit; u32 seed; seed = jhash(mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac), 0); mlxsw_reg_recr2_pack(recr2_pl, seed); - mlxsw_sp_mp4_hash_init(mlxsw_sp, recr2_pl); - mlxsw_sp_mp6_hash_init(mlxsw_sp, recr2_pl); + mlxsw_sp_mp4_hash_init(mlxsw_sp, &config); + mlxsw_sp_mp6_hash_init(mlxsw_sp, &config); + + for_each_set_bit(bit, config.headers, __MLXSW_REG_RECR2_HEADER_CNT) + mlxsw_reg_recr2_outer_header_enables_set(recr2_pl, bit, 1); + for_each_set_bit(bit, config.fields, __MLXSW_REG_RECR2_FIELD_CNT) + mlxsw_reg_recr2_outer_header_fields_enable_set(recr2_pl, bit, 1); + for_each_set_bit(bit, config.inner_headers, __MLXSW_REG_RECR2_HEADER_CNT) + mlxsw_reg_recr2_inner_header_enables_set(recr2_pl, bit, 1); + for_each_set_bit(bit, config.inner_fields, __MLXSW_REG_RECR2_INNER_FIELD_CNT) + mlxsw_reg_recr2_inner_header_fields_enable_set(recr2_pl, bit, 1); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(recr2), recr2_pl); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index be7708a375e1..c5d7007f9173 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -58,7 +58,6 @@ struct mlxsw_sp_router { #define MLXSW_SP_UNRESOLVED_NH_PROBE_INTERVAL 5000 /* ms */ struct list_head nexthop_neighs_list; struct list_head ipip_list; - bool aborted; struct notifier_block nexthop_nb; struct notifier_block fib_nb; struct notifier_block netevent_nb; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index eeccd586e781..c5ef9aa64efe 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -898,7 +898,7 @@ mlxsw_sp_port_attr_br_mrouter_set(struct mlxsw_sp_port *mlxsw_sp_port, return 0; } -static int mlxsw_sp_port_attr_set(struct net_device *dev, +static int mlxsw_sp_port_attr_set(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { @@ -1766,7 +1766,7 @@ mlxsw_sp_port_mrouter_update_mdb(struct mlxsw_sp_port *mlxsw_sp_port, } } -static int mlxsw_sp_port_obj_add(struct net_device *dev, +static int mlxsw_sp_port_obj_add(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { @@ -1916,7 +1916,7 @@ mlxsw_sp_bridge_port_mdb_flush(struct mlxsw_sp_port *mlxsw_sp_port, } } -static int mlxsw_sp_port_obj_del(struct net_device *dev, +static int mlxsw_sp_port_obj_del(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); @@ -2520,6 +2520,7 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, char *sfn_pl, int rec_index, bool adding) { + unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core); struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; struct mlxsw_sp_bridge_device *bridge_device; struct mlxsw_sp_bridge_port *bridge_port; @@ -2532,6 +2533,9 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, int err; mlxsw_reg_sfn_mac_unpack(sfn_pl, rec_index, mac, &fid, &local_port); + + if (WARN_ON_ONCE(local_port >= max_ports)) + return; mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) { dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Incorrect local port in FDB notification\n"); diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchib.c b/drivers/net/ethernet/mellanox/mlxsw/switchib.c deleted file mode 100644 index 1e561132eb1e..000000000000 --- a/drivers/net/ethernet/mellanox/mlxsw/switchib.c +++ /dev/null @@ -1,595 +0,0 @@ -// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 -/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "pci.h" -#include "core.h" -#include "reg.h" -#include "port.h" -#include "trap.h" -#include "txheader.h" -#include "ib.h" - -static const char mlxsw_sib_driver_name[] = "mlxsw_switchib"; -static const char mlxsw_sib2_driver_name[] = "mlxsw_switchib2"; - -struct mlxsw_sib_port; - -struct mlxsw_sib { - struct mlxsw_sib_port **ports; - struct mlxsw_core *core; - const struct mlxsw_bus_info *bus_info; - u8 hw_id[ETH_ALEN]; -}; - -struct mlxsw_sib_port { - struct mlxsw_sib *mlxsw_sib; - u8 local_port; - struct { - u8 module; - } mapping; -}; - -/* tx_v1_hdr_version - * Tx header version. - * Must be set to 1. - */ -MLXSW_ITEM32(tx_v1, hdr, version, 0x00, 28, 4); - -/* tx_v1_hdr_ctl - * Packet control type. - * 0 - Ethernet control (e.g. EMADs, LACP) - * 1 - Ethernet data - */ -MLXSW_ITEM32(tx_v1, hdr, ctl, 0x00, 26, 2); - -/* tx_v1_hdr_proto - * Packet protocol type. Must be set to 1 (Ethernet). - */ -MLXSW_ITEM32(tx_v1, hdr, proto, 0x00, 21, 3); - -/* tx_v1_hdr_swid - * Switch partition ID. Must be set to 0. - */ -MLXSW_ITEM32(tx_v1, hdr, swid, 0x00, 12, 3); - -/* tx_v1_hdr_control_tclass - * Indicates if the packet should use the control TClass and not one - * of the data TClasses. - */ -MLXSW_ITEM32(tx_v1, hdr, control_tclass, 0x00, 6, 1); - -/* tx_v1_hdr_port_mid - * Destination local port for unicast packets. - * Destination multicast ID for multicast packets. - * - * Control packets are directed to a specific egress port, while data - * packets are transmitted through the CPU port (0) into the switch partition, - * where forwarding rules are applied. - */ -MLXSW_ITEM32(tx_v1, hdr, port_mid, 0x04, 16, 16); - -/* tx_v1_hdr_type - * 0 - Data packets - * 6 - Control packets - */ -MLXSW_ITEM32(tx_v1, hdr, type, 0x0C, 0, 4); - -static void -mlxsw_sib_tx_v1_hdr_construct(struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - char *txhdr = skb_push(skb, MLXSW_TXHDR_LEN); - - memset(txhdr, 0, MLXSW_TXHDR_LEN); - - mlxsw_tx_v1_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1); - mlxsw_tx_v1_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL); - mlxsw_tx_v1_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH); - mlxsw_tx_v1_hdr_swid_set(txhdr, 0); - mlxsw_tx_v1_hdr_control_tclass_set(txhdr, 1); - mlxsw_tx_v1_hdr_port_mid_set(txhdr, tx_info->local_port); - mlxsw_tx_v1_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL); -} - -static int mlxsw_sib_hw_id_get(struct mlxsw_sib *mlxsw_sib) -{ - char spad_pl[MLXSW_REG_SPAD_LEN] = {0}; - int err; - - err = mlxsw_reg_query(mlxsw_sib->core, MLXSW_REG(spad), spad_pl); - if (err) - return err; - mlxsw_reg_spad_base_mac_memcpy_from(spad_pl, mlxsw_sib->hw_id); - return 0; -} - -static int -mlxsw_sib_port_admin_status_set(struct mlxsw_sib_port *mlxsw_sib_port, - bool is_up) -{ - struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib; - char paos_pl[MLXSW_REG_PAOS_LEN]; - - mlxsw_reg_paos_pack(paos_pl, mlxsw_sib_port->local_port, - is_up ? MLXSW_PORT_ADMIN_STATUS_UP : - MLXSW_PORT_ADMIN_STATUS_DOWN); - return mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(paos), paos_pl); -} - -static int mlxsw_sib_port_mtu_set(struct mlxsw_sib_port *mlxsw_sib_port, - u16 mtu) -{ - struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib; - char pmtu_pl[MLXSW_REG_PMTU_LEN]; - int max_mtu; - int err; - - mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sib_port->local_port, 0); - err = mlxsw_reg_query(mlxsw_sib->core, MLXSW_REG(pmtu), pmtu_pl); - if (err) - return err; - max_mtu = mlxsw_reg_pmtu_max_mtu_get(pmtu_pl); - - if (mtu > max_mtu) - return -EINVAL; - - mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sib_port->local_port, mtu); - return mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(pmtu), pmtu_pl); -} - -static int mlxsw_sib_port_set(struct mlxsw_sib_port *mlxsw_sib_port, u8 port) -{ - struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib; - char plib_pl[MLXSW_REG_PLIB_LEN] = {0}; - int err; - - mlxsw_reg_plib_local_port_set(plib_pl, mlxsw_sib_port->local_port); - mlxsw_reg_plib_ib_port_set(plib_pl, port); - err = mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(plib), plib_pl); - return err; -} - -static int mlxsw_sib_port_swid_set(struct mlxsw_sib_port *mlxsw_sib_port, - u8 swid) -{ - struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib; - char pspa_pl[MLXSW_REG_PSPA_LEN]; - - mlxsw_reg_pspa_pack(pspa_pl, swid, mlxsw_sib_port->local_port); - return mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(pspa), pspa_pl); -} - -static int mlxsw_sib_port_module_info_get(struct mlxsw_sib *mlxsw_sib, - u8 local_port, u8 *p_module, - u8 *p_width) -{ - char pmlp_pl[MLXSW_REG_PMLP_LEN]; - int err; - - mlxsw_reg_pmlp_pack(pmlp_pl, local_port); - err = mlxsw_reg_query(mlxsw_sib->core, MLXSW_REG(pmlp), pmlp_pl); - if (err) - return err; - *p_module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0); - *p_width = mlxsw_reg_pmlp_width_get(pmlp_pl); - return 0; -} - -static int mlxsw_sib_port_speed_set(struct mlxsw_sib_port *mlxsw_sib_port, - u16 speed, u16 width) -{ - struct mlxsw_sib *mlxsw_sib = mlxsw_sib_port->mlxsw_sib; - char ptys_pl[MLXSW_REG_PTYS_LEN]; - - mlxsw_reg_ptys_ib_pack(ptys_pl, mlxsw_sib_port->local_port, speed, - width); - return mlxsw_reg_write(mlxsw_sib->core, MLXSW_REG(ptys), ptys_pl); -} - -static bool mlxsw_sib_port_created(struct mlxsw_sib *mlxsw_sib, u8 local_port) -{ - return mlxsw_sib->ports[local_port] != NULL; -} - -static int __mlxsw_sib_port_create(struct mlxsw_sib *mlxsw_sib, u8 local_port, - u8 module, u8 width) -{ - struct mlxsw_sib_port *mlxsw_sib_port; - int err; - - mlxsw_sib_port = kzalloc(sizeof(*mlxsw_sib_port), GFP_KERNEL); - if (!mlxsw_sib_port) - return -ENOMEM; - mlxsw_sib_port->mlxsw_sib = mlxsw_sib; - mlxsw_sib_port->local_port = local_port; - mlxsw_sib_port->mapping.module = module; - - err = mlxsw_sib_port_swid_set(mlxsw_sib_port, 0); - if (err) { - dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to set SWID\n", - mlxsw_sib_port->local_port); - goto err_port_swid_set; - } - - /* Expose the IB port number as it's front panel name */ - err = mlxsw_sib_port_set(mlxsw_sib_port, module + 1); - if (err) { - dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to set IB port\n", - mlxsw_sib_port->local_port); - goto err_port_ib_set; - } - - /* Supports all speeds from SDR to FDR (bitmask) and support bus width - * of 1x, 2x and 4x (3 bits bitmask) - */ - err = mlxsw_sib_port_speed_set(mlxsw_sib_port, - MLXSW_REG_PTYS_IB_SPEED_EDR - 1, - BIT(3) - 1); - if (err) { - dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to set speed\n", - mlxsw_sib_port->local_port); - goto err_port_speed_set; - } - - /* Change to the maximum MTU the device supports, the SMA will take - * care of the active MTU - */ - err = mlxsw_sib_port_mtu_set(mlxsw_sib_port, MLXSW_IB_DEFAULT_MTU); - if (err) { - dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to set MTU\n", - mlxsw_sib_port->local_port); - goto err_port_mtu_set; - } - - err = mlxsw_sib_port_admin_status_set(mlxsw_sib_port, true); - if (err) { - dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to change admin state to UP\n", - mlxsw_sib_port->local_port); - goto err_port_admin_set; - } - - mlxsw_core_port_ib_set(mlxsw_sib->core, mlxsw_sib_port->local_port, - mlxsw_sib_port); - mlxsw_sib->ports[local_port] = mlxsw_sib_port; - return 0; - -err_port_admin_set: -err_port_mtu_set: -err_port_speed_set: -err_port_ib_set: - mlxsw_sib_port_swid_set(mlxsw_sib_port, MLXSW_PORT_SWID_DISABLED_PORT); -err_port_swid_set: - kfree(mlxsw_sib_port); - return err; -} - -static int mlxsw_sib_port_create(struct mlxsw_sib *mlxsw_sib, u8 local_port, - u8 module, u8 width) -{ - int err; - - err = mlxsw_core_port_init(mlxsw_sib->core, local_port, - module + 1, false, 0, false, 0, - mlxsw_sib->hw_id, sizeof(mlxsw_sib->hw_id)); - if (err) { - dev_err(mlxsw_sib->bus_info->dev, "Port %d: Failed to init core port\n", - local_port); - return err; - } - err = __mlxsw_sib_port_create(mlxsw_sib, local_port, module, width); - if (err) - goto err_port_create; - - return 0; - -err_port_create: - mlxsw_core_port_fini(mlxsw_sib->core, local_port); - return err; -} - -static void __mlxsw_sib_port_remove(struct mlxsw_sib *mlxsw_sib, u8 local_port) -{ - struct mlxsw_sib_port *mlxsw_sib_port = mlxsw_sib->ports[local_port]; - - mlxsw_core_port_clear(mlxsw_sib->core, local_port, mlxsw_sib); - mlxsw_sib->ports[local_port] = NULL; - mlxsw_sib_port_admin_status_set(mlxsw_sib_port, false); - mlxsw_sib_port_swid_set(mlxsw_sib_port, MLXSW_PORT_SWID_DISABLED_PORT); - kfree(mlxsw_sib_port); -} - -static void mlxsw_sib_port_remove(struct mlxsw_sib *mlxsw_sib, u8 local_port) -{ - __mlxsw_sib_port_remove(mlxsw_sib, local_port); - mlxsw_core_port_fini(mlxsw_sib->core, local_port); -} - -static void mlxsw_sib_ports_remove(struct mlxsw_sib *mlxsw_sib) -{ - int i; - - for (i = 1; i < MLXSW_PORT_MAX_IB_PORTS; i++) - if (mlxsw_sib_port_created(mlxsw_sib, i)) - mlxsw_sib_port_remove(mlxsw_sib, i); - kfree(mlxsw_sib->ports); -} - -static int mlxsw_sib_ports_create(struct mlxsw_sib *mlxsw_sib) -{ - size_t alloc_size; - u8 module, width; - int i; - int err; - - alloc_size = sizeof(struct mlxsw_sib_port *) * MLXSW_PORT_MAX_IB_PORTS; - mlxsw_sib->ports = kzalloc(alloc_size, GFP_KERNEL); - if (!mlxsw_sib->ports) - return -ENOMEM; - - for (i = 1; i < MLXSW_PORT_MAX_IB_PORTS; i++) { - err = mlxsw_sib_port_module_info_get(mlxsw_sib, i, &module, - &width); - if (err) - goto err_port_module_info_get; - if (!width) - continue; - err = mlxsw_sib_port_create(mlxsw_sib, i, module, width); - if (err) - goto err_port_create; - } - return 0; - -err_port_create: -err_port_module_info_get: - for (i--; i >= 1; i--) - if (mlxsw_sib_port_created(mlxsw_sib, i)) - mlxsw_sib_port_remove(mlxsw_sib, i); - kfree(mlxsw_sib->ports); - return err; -} - -static void -mlxsw_sib_pude_ib_event_func(struct mlxsw_sib_port *mlxsw_sib_port, - enum mlxsw_reg_pude_oper_status status) -{ - if (status == MLXSW_PORT_OPER_STATUS_UP) - pr_info("ib link for port %d - up\n", - mlxsw_sib_port->mapping.module + 1); - else - pr_info("ib link for port %d - down\n", - mlxsw_sib_port->mapping.module + 1); -} - -static void mlxsw_sib_pude_event_func(const struct mlxsw_reg_info *reg, - char *pude_pl, void *priv) -{ - struct mlxsw_sib *mlxsw_sib = priv; - struct mlxsw_sib_port *mlxsw_sib_port; - enum mlxsw_reg_pude_oper_status status; - u8 local_port; - - local_port = mlxsw_reg_pude_local_port_get(pude_pl); - mlxsw_sib_port = mlxsw_sib->ports[local_port]; - if (!mlxsw_sib_port) { - dev_warn(mlxsw_sib->bus_info->dev, "Port %d: Link event received for non-existent port\n", - local_port); - return; - } - - status = mlxsw_reg_pude_oper_status_get(pude_pl); - mlxsw_sib_pude_ib_event_func(mlxsw_sib_port, status); -} - -static const struct mlxsw_listener mlxsw_sib_listener[] = { - MLXSW_EVENTL(mlxsw_sib_pude_event_func, PUDE, EMAD), -}; - -static int mlxsw_sib_taps_init(struct mlxsw_sib *mlxsw_sib) -{ - int i; - int err; - - for (i = 0; i < ARRAY_SIZE(mlxsw_sib_listener); i++) { - err = mlxsw_core_trap_register(mlxsw_sib->core, - &mlxsw_sib_listener[i], - mlxsw_sib); - if (err) - goto err_rx_listener_register; - } - - return 0; - -err_rx_listener_register: - for (i--; i >= 0; i--) { - mlxsw_core_trap_unregister(mlxsw_sib->core, - &mlxsw_sib_listener[i], - mlxsw_sib); - } - - return err; -} - -static void mlxsw_sib_traps_fini(struct mlxsw_sib *mlxsw_sib) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(mlxsw_sib_listener); i++) { - mlxsw_core_trap_unregister(mlxsw_sib->core, - &mlxsw_sib_listener[i], mlxsw_sib); - } -} - -static int mlxsw_sib_basic_trap_groups_set(struct mlxsw_core *mlxsw_core) -{ - char htgt_pl[MLXSW_REG_HTGT_LEN]; - - mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_EMAD, - MLXSW_REG_HTGT_INVALID_POLICER, - MLXSW_REG_HTGT_DEFAULT_PRIORITY, - MLXSW_REG_HTGT_DEFAULT_TC); - mlxsw_reg_htgt_swid_set(htgt_pl, MLXSW_PORT_SWID_ALL_SWIDS); - mlxsw_reg_htgt_local_path_rdq_set(htgt_pl, - MLXSW_REG_HTGT_LOCAL_PATH_RDQ_SIB_EMAD); - return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); -} - -static int mlxsw_sib_init(struct mlxsw_core *mlxsw_core, - const struct mlxsw_bus_info *mlxsw_bus_info, - struct netlink_ext_ack *extack) -{ - struct mlxsw_sib *mlxsw_sib = mlxsw_core_driver_priv(mlxsw_core); - int err; - - mlxsw_sib->core = mlxsw_core; - mlxsw_sib->bus_info = mlxsw_bus_info; - - err = mlxsw_sib_hw_id_get(mlxsw_sib); - if (err) { - dev_err(mlxsw_sib->bus_info->dev, "Failed to get switch HW ID\n"); - return err; - } - - err = mlxsw_sib_ports_create(mlxsw_sib); - if (err) { - dev_err(mlxsw_sib->bus_info->dev, "Failed to create ports\n"); - return err; - } - - err = mlxsw_sib_taps_init(mlxsw_sib); - if (err) { - dev_err(mlxsw_sib->bus_info->dev, "Failed to set traps\n"); - goto err_traps_init_err; - } - - return 0; - -err_traps_init_err: - mlxsw_sib_ports_remove(mlxsw_sib); - return err; -} - -static void mlxsw_sib_fini(struct mlxsw_core *mlxsw_core) -{ - struct mlxsw_sib *mlxsw_sib = mlxsw_core_driver_priv(mlxsw_core); - - mlxsw_sib_traps_fini(mlxsw_sib); - mlxsw_sib_ports_remove(mlxsw_sib); -} - -static const struct mlxsw_config_profile mlxsw_sib_config_profile = { - .used_max_system_port = 1, - .max_system_port = 48000, - .used_max_ib_mc = 1, - .max_ib_mc = 27, - .used_max_pkey = 1, - .max_pkey = 32, - .swid_config = { - { - .used_type = 1, - .type = MLXSW_PORT_SWID_TYPE_IB, - } - }, -}; - -static struct mlxsw_driver mlxsw_sib_driver = { - .kind = mlxsw_sib_driver_name, - .priv_size = sizeof(struct mlxsw_sib), - .init = mlxsw_sib_init, - .fini = mlxsw_sib_fini, - .basic_trap_groups_set = mlxsw_sib_basic_trap_groups_set, - .txhdr_construct = mlxsw_sib_tx_v1_hdr_construct, - .txhdr_len = MLXSW_TXHDR_LEN, - .profile = &mlxsw_sib_config_profile, -}; - -static struct mlxsw_driver mlxsw_sib2_driver = { - .kind = mlxsw_sib2_driver_name, - .priv_size = sizeof(struct mlxsw_sib), - .init = mlxsw_sib_init, - .fini = mlxsw_sib_fini, - .basic_trap_groups_set = mlxsw_sib_basic_trap_groups_set, - .txhdr_construct = mlxsw_sib_tx_v1_hdr_construct, - .txhdr_len = MLXSW_TXHDR_LEN, - .profile = &mlxsw_sib_config_profile, -}; - -static const struct pci_device_id mlxsw_sib_pci_id_table[] = { - {PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SWITCHIB), 0}, - {0, }, -}; - -static struct pci_driver mlxsw_sib_pci_driver = { - .name = mlxsw_sib_driver_name, - .id_table = mlxsw_sib_pci_id_table, -}; - -static const struct pci_device_id mlxsw_sib2_pci_id_table[] = { - {PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SWITCHIB2), 0}, - {0, }, -}; - -static struct pci_driver mlxsw_sib2_pci_driver = { - .name = mlxsw_sib2_driver_name, - .id_table = mlxsw_sib2_pci_id_table, -}; - -static int __init mlxsw_sib_module_init(void) -{ - int err; - - err = mlxsw_core_driver_register(&mlxsw_sib_driver); - if (err) - return err; - - err = mlxsw_core_driver_register(&mlxsw_sib2_driver); - if (err) - goto err_sib2_driver_register; - - err = mlxsw_pci_driver_register(&mlxsw_sib_pci_driver); - if (err) - goto err_sib_pci_driver_register; - - err = mlxsw_pci_driver_register(&mlxsw_sib2_pci_driver); - if (err) - goto err_sib2_pci_driver_register; - - return 0; - -err_sib2_pci_driver_register: - mlxsw_pci_driver_unregister(&mlxsw_sib_pci_driver); -err_sib_pci_driver_register: - mlxsw_core_driver_unregister(&mlxsw_sib2_driver); -err_sib2_driver_register: - mlxsw_core_driver_unregister(&mlxsw_sib_driver); - return err; -} - -static void __exit mlxsw_sib_module_exit(void) -{ - mlxsw_pci_driver_unregister(&mlxsw_sib2_pci_driver); - mlxsw_pci_driver_unregister(&mlxsw_sib_pci_driver); - mlxsw_core_driver_unregister(&mlxsw_sib2_driver); - mlxsw_core_driver_unregister(&mlxsw_sib_driver); -} - -module_init(mlxsw_sib_module_init); -module_exit(mlxsw_sib_module_exit); - -MODULE_LICENSE("Dual BSD/GPL"); -MODULE_AUTHOR("Elad Raz "); -MODULE_DESCRIPTION("Mellanox SwitchIB and SwitchIB-2 driver"); -MODULE_ALIAS("mlxsw_switchib2"); -MODULE_DEVICE_TABLE(pci, mlxsw_sib_pci_id_table); -MODULE_DEVICE_TABLE(pci, mlxsw_sib2_pci_id_table); diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c deleted file mode 100644 index 131b2a53d261..000000000000 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ /dev/null @@ -1,1691 +0,0 @@ -// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 -/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "pci.h" -#include "core.h" -#include "reg.h" -#include "port.h" -#include "trap.h" -#include "txheader.h" -#include "ib.h" - -static const char mlxsw_sx_driver_name[] = "mlxsw_switchx2"; -static const char mlxsw_sx_driver_version[] = "1.0"; - -struct mlxsw_sx_port; - -struct mlxsw_sx { - struct mlxsw_sx_port **ports; - struct mlxsw_core *core; - const struct mlxsw_bus_info *bus_info; - u8 hw_id[ETH_ALEN]; -}; - -struct mlxsw_sx_port_pcpu_stats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; - struct u64_stats_sync syncp; - u32 tx_dropped; -}; - -struct mlxsw_sx_port { - struct net_device *dev; - struct mlxsw_sx_port_pcpu_stats __percpu *pcpu_stats; - struct mlxsw_sx *mlxsw_sx; - u8 local_port; - struct { - u8 module; - } mapping; -}; - -/* tx_hdr_version - * Tx header version. - * Must be set to 0. - */ -MLXSW_ITEM32(tx, hdr, version, 0x00, 28, 4); - -/* tx_hdr_ctl - * Packet control type. - * 0 - Ethernet control (e.g. EMADs, LACP) - * 1 - Ethernet data - */ -MLXSW_ITEM32(tx, hdr, ctl, 0x00, 26, 2); - -/* tx_hdr_proto - * Packet protocol type. Must be set to 1 (Ethernet). - */ -MLXSW_ITEM32(tx, hdr, proto, 0x00, 21, 3); - -/* tx_hdr_etclass - * Egress TClass to be used on the egress device on the egress port. - * The MSB is specified in the 'ctclass3' field. - * Range is 0-15, where 15 is the highest priority. - */ -MLXSW_ITEM32(tx, hdr, etclass, 0x00, 18, 3); - -/* tx_hdr_swid - * Switch partition ID. - */ -MLXSW_ITEM32(tx, hdr, swid, 0x00, 12, 3); - -/* tx_hdr_port_mid - * Destination local port for unicast packets. - * Destination multicast ID for multicast packets. - * - * Control packets are directed to a specific egress port, while data - * packets are transmitted through the CPU port (0) into the switch partition, - * where forwarding rules are applied. - */ -MLXSW_ITEM32(tx, hdr, port_mid, 0x04, 16, 16); - -/* tx_hdr_ctclass3 - * See field 'etclass'. - */ -MLXSW_ITEM32(tx, hdr, ctclass3, 0x04, 14, 1); - -/* tx_hdr_rdq - * RDQ for control packets sent to remote CPU. - * Must be set to 0x1F for EMADs, otherwise 0. - */ -MLXSW_ITEM32(tx, hdr, rdq, 0x04, 9, 5); - -/* tx_hdr_cpu_sig - * Signature control for packets going to CPU. Must be set to 0. - */ -MLXSW_ITEM32(tx, hdr, cpu_sig, 0x04, 0, 9); - -/* tx_hdr_sig - * Stacking protocl signature. Must be set to 0xE0E0. - */ -MLXSW_ITEM32(tx, hdr, sig, 0x0C, 16, 16); - -/* tx_hdr_stclass - * Stacking TClass. - */ -MLXSW_ITEM32(tx, hdr, stclass, 0x0C, 13, 3); - -/* tx_hdr_emad - * EMAD bit. Must be set for EMADs. - */ -MLXSW_ITEM32(tx, hdr, emad, 0x0C, 5, 1); - -/* tx_hdr_type - * 0 - Data packets - * 6 - Control packets - */ -MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4); - -static void mlxsw_sx_txhdr_construct(struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - char *txhdr = skb_push(skb, MLXSW_TXHDR_LEN); - bool is_emad = tx_info->is_emad; - - memset(txhdr, 0, MLXSW_TXHDR_LEN); - - /* We currently set default values for the egress tclass (QoS). */ - mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_0); - mlxsw_tx_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL); - mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH); - mlxsw_tx_hdr_etclass_set(txhdr, is_emad ? MLXSW_TXHDR_ETCLASS_6 : - MLXSW_TXHDR_ETCLASS_5); - mlxsw_tx_hdr_swid_set(txhdr, 0); - mlxsw_tx_hdr_port_mid_set(txhdr, tx_info->local_port); - mlxsw_tx_hdr_ctclass3_set(txhdr, MLXSW_TXHDR_CTCLASS3); - mlxsw_tx_hdr_rdq_set(txhdr, is_emad ? MLXSW_TXHDR_RDQ_EMAD : - MLXSW_TXHDR_RDQ_OTHER); - mlxsw_tx_hdr_cpu_sig_set(txhdr, MLXSW_TXHDR_CPU_SIG); - mlxsw_tx_hdr_sig_set(txhdr, MLXSW_TXHDR_SIG); - mlxsw_tx_hdr_stclass_set(txhdr, MLXSW_TXHDR_STCLASS_NONE); - mlxsw_tx_hdr_emad_set(txhdr, is_emad ? MLXSW_TXHDR_EMAD : - MLXSW_TXHDR_NOT_EMAD); - mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL); -} - -static int mlxsw_sx_port_admin_status_set(struct mlxsw_sx_port *mlxsw_sx_port, - bool is_up) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - char paos_pl[MLXSW_REG_PAOS_LEN]; - - mlxsw_reg_paos_pack(paos_pl, mlxsw_sx_port->local_port, - is_up ? MLXSW_PORT_ADMIN_STATUS_UP : - MLXSW_PORT_ADMIN_STATUS_DOWN); - return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(paos), paos_pl); -} - -static int mlxsw_sx_port_oper_status_get(struct mlxsw_sx_port *mlxsw_sx_port, - bool *p_is_up) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - char paos_pl[MLXSW_REG_PAOS_LEN]; - u8 oper_status; - int err; - - mlxsw_reg_paos_pack(paos_pl, mlxsw_sx_port->local_port, 0); - err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(paos), paos_pl); - if (err) - return err; - oper_status = mlxsw_reg_paos_oper_status_get(paos_pl); - *p_is_up = oper_status == MLXSW_PORT_ADMIN_STATUS_UP; - return 0; -} - -static int __mlxsw_sx_port_mtu_set(struct mlxsw_sx_port *mlxsw_sx_port, - u16 mtu) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - char pmtu_pl[MLXSW_REG_PMTU_LEN]; - int max_mtu; - int err; - - mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sx_port->local_port, 0); - err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(pmtu), pmtu_pl); - if (err) - return err; - max_mtu = mlxsw_reg_pmtu_max_mtu_get(pmtu_pl); - - if (mtu > max_mtu) - return -EINVAL; - - mlxsw_reg_pmtu_pack(pmtu_pl, mlxsw_sx_port->local_port, mtu); - return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(pmtu), pmtu_pl); -} - -static int mlxsw_sx_port_mtu_eth_set(struct mlxsw_sx_port *mlxsw_sx_port, - u16 mtu) -{ - mtu += MLXSW_TXHDR_LEN + ETH_HLEN; - return __mlxsw_sx_port_mtu_set(mlxsw_sx_port, mtu); -} - -static int mlxsw_sx_port_mtu_ib_set(struct mlxsw_sx_port *mlxsw_sx_port, - u16 mtu) -{ - return __mlxsw_sx_port_mtu_set(mlxsw_sx_port, mtu); -} - -static int mlxsw_sx_port_ib_port_set(struct mlxsw_sx_port *mlxsw_sx_port, - u8 ib_port) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - char plib_pl[MLXSW_REG_PLIB_LEN] = {0}; - int err; - - mlxsw_reg_plib_local_port_set(plib_pl, mlxsw_sx_port->local_port); - mlxsw_reg_plib_ib_port_set(plib_pl, ib_port); - err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(plib), plib_pl); - return err; -} - -static int mlxsw_sx_port_swid_set(struct mlxsw_sx_port *mlxsw_sx_port, u8 swid) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - char pspa_pl[MLXSW_REG_PSPA_LEN]; - - mlxsw_reg_pspa_pack(pspa_pl, swid, mlxsw_sx_port->local_port); - return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(pspa), pspa_pl); -} - -static int -mlxsw_sx_port_system_port_mapping_set(struct mlxsw_sx_port *mlxsw_sx_port) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - char sspr_pl[MLXSW_REG_SSPR_LEN]; - - mlxsw_reg_sspr_pack(sspr_pl, mlxsw_sx_port->local_port); - return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sspr), sspr_pl); -} - -static int mlxsw_sx_port_module_info_get(struct mlxsw_sx *mlxsw_sx, - u8 local_port, u8 *p_module, - u8 *p_width) -{ - char pmlp_pl[MLXSW_REG_PMLP_LEN]; - int err; - - mlxsw_reg_pmlp_pack(pmlp_pl, local_port); - err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(pmlp), pmlp_pl); - if (err) - return err; - *p_module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0); - *p_width = mlxsw_reg_pmlp_width_get(pmlp_pl); - return 0; -} - -static int mlxsw_sx_port_open(struct net_device *dev) -{ - struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); - int err; - - err = mlxsw_sx_port_admin_status_set(mlxsw_sx_port, true); - if (err) - return err; - netif_start_queue(dev); - return 0; -} - -static int mlxsw_sx_port_stop(struct net_device *dev) -{ - struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); - - netif_stop_queue(dev); - return mlxsw_sx_port_admin_status_set(mlxsw_sx_port, false); -} - -static netdev_tx_t mlxsw_sx_port_xmit(struct sk_buff *skb, - struct net_device *dev) -{ - struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - struct mlxsw_sx_port_pcpu_stats *pcpu_stats; - const struct mlxsw_tx_info tx_info = { - .local_port = mlxsw_sx_port->local_port, - .is_emad = false, - }; - u64 len; - int err; - - if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) { - this_cpu_inc(mlxsw_sx_port->pcpu_stats->tx_dropped); - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } - - memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb)); - - if (mlxsw_core_skb_transmit_busy(mlxsw_sx->core, &tx_info)) - return NETDEV_TX_BUSY; - - mlxsw_sx_txhdr_construct(skb, &tx_info); - /* TX header is consumed by HW on the way so we shouldn't count its - * bytes as being sent. - */ - len = skb->len - MLXSW_TXHDR_LEN; - /* Due to a race we might fail here because of a full queue. In that - * unlikely case we simply drop the packet. - */ - err = mlxsw_core_skb_transmit(mlxsw_sx->core, skb, &tx_info); - - if (!err) { - pcpu_stats = this_cpu_ptr(mlxsw_sx_port->pcpu_stats); - u64_stats_update_begin(&pcpu_stats->syncp); - pcpu_stats->tx_packets++; - pcpu_stats->tx_bytes += len; - u64_stats_update_end(&pcpu_stats->syncp); - } else { - this_cpu_inc(mlxsw_sx_port->pcpu_stats->tx_dropped); - dev_kfree_skb_any(skb); - } - return NETDEV_TX_OK; -} - -static int mlxsw_sx_port_change_mtu(struct net_device *dev, int mtu) -{ - struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); - int err; - - err = mlxsw_sx_port_mtu_eth_set(mlxsw_sx_port, mtu); - if (err) - return err; - dev->mtu = mtu; - return 0; -} - -static void -mlxsw_sx_port_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *stats) -{ - struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); - struct mlxsw_sx_port_pcpu_stats *p; - u64 rx_packets, rx_bytes, tx_packets, tx_bytes; - u32 tx_dropped = 0; - unsigned int start; - int i; - - for_each_possible_cpu(i) { - p = per_cpu_ptr(mlxsw_sx_port->pcpu_stats, i); - do { - start = u64_stats_fetch_begin_irq(&p->syncp); - rx_packets = p->rx_packets; - rx_bytes = p->rx_bytes; - tx_packets = p->tx_packets; - tx_bytes = p->tx_bytes; - } while (u64_stats_fetch_retry_irq(&p->syncp, start)); - - stats->rx_packets += rx_packets; - stats->rx_bytes += rx_bytes; - stats->tx_packets += tx_packets; - stats->tx_bytes += tx_bytes; - /* tx_dropped is u32, updated without syncp protection. */ - tx_dropped += p->tx_dropped; - } - stats->tx_dropped = tx_dropped; -} - -static struct devlink_port * -mlxsw_sx_port_get_devlink_port(struct net_device *dev) -{ - struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - - return mlxsw_core_port_devlink_port_get(mlxsw_sx->core, - mlxsw_sx_port->local_port); -} - -static const struct net_device_ops mlxsw_sx_port_netdev_ops = { - .ndo_open = mlxsw_sx_port_open, - .ndo_stop = mlxsw_sx_port_stop, - .ndo_start_xmit = mlxsw_sx_port_xmit, - .ndo_change_mtu = mlxsw_sx_port_change_mtu, - .ndo_get_stats64 = mlxsw_sx_port_get_stats64, - .ndo_get_devlink_port = mlxsw_sx_port_get_devlink_port, -}; - -static void mlxsw_sx_port_get_drvinfo(struct net_device *dev, - struct ethtool_drvinfo *drvinfo) -{ - struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - - strlcpy(drvinfo->driver, mlxsw_sx_driver_name, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, mlxsw_sx_driver_version, - sizeof(drvinfo->version)); - snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), - "%d.%d.%d", - mlxsw_sx->bus_info->fw_rev.major, - mlxsw_sx->bus_info->fw_rev.minor, - mlxsw_sx->bus_info->fw_rev.subminor); - strlcpy(drvinfo->bus_info, mlxsw_sx->bus_info->device_name, - sizeof(drvinfo->bus_info)); -} - -struct mlxsw_sx_port_hw_stats { - char str[ETH_GSTRING_LEN]; - u64 (*getter)(const char *payload); -}; - -static const struct mlxsw_sx_port_hw_stats mlxsw_sx_port_hw_stats[] = { - { - .str = "a_frames_transmitted_ok", - .getter = mlxsw_reg_ppcnt_a_frames_transmitted_ok_get, - }, - { - .str = "a_frames_received_ok", - .getter = mlxsw_reg_ppcnt_a_frames_received_ok_get, - }, - { - .str = "a_frame_check_sequence_errors", - .getter = mlxsw_reg_ppcnt_a_frame_check_sequence_errors_get, - }, - { - .str = "a_alignment_errors", - .getter = mlxsw_reg_ppcnt_a_alignment_errors_get, - }, - { - .str = "a_octets_transmitted_ok", - .getter = mlxsw_reg_ppcnt_a_octets_transmitted_ok_get, - }, - { - .str = "a_octets_received_ok", - .getter = mlxsw_reg_ppcnt_a_octets_received_ok_get, - }, - { - .str = "a_multicast_frames_xmitted_ok", - .getter = mlxsw_reg_ppcnt_a_multicast_frames_xmitted_ok_get, - }, - { - .str = "a_broadcast_frames_xmitted_ok", - .getter = mlxsw_reg_ppcnt_a_broadcast_frames_xmitted_ok_get, - }, - { - .str = "a_multicast_frames_received_ok", - .getter = mlxsw_reg_ppcnt_a_multicast_frames_received_ok_get, - }, - { - .str = "a_broadcast_frames_received_ok", - .getter = mlxsw_reg_ppcnt_a_broadcast_frames_received_ok_get, - }, - { - .str = "a_in_range_length_errors", - .getter = mlxsw_reg_ppcnt_a_in_range_length_errors_get, - }, - { - .str = "a_out_of_range_length_field", - .getter = mlxsw_reg_ppcnt_a_out_of_range_length_field_get, - }, - { - .str = "a_frame_too_long_errors", - .getter = mlxsw_reg_ppcnt_a_frame_too_long_errors_get, - }, - { - .str = "a_symbol_error_during_carrier", - .getter = mlxsw_reg_ppcnt_a_symbol_error_during_carrier_get, - }, - { - .str = "a_mac_control_frames_transmitted", - .getter = mlxsw_reg_ppcnt_a_mac_control_frames_transmitted_get, - }, - { - .str = "a_mac_control_frames_received", - .getter = mlxsw_reg_ppcnt_a_mac_control_frames_received_get, - }, - { - .str = "a_unsupported_opcodes_received", - .getter = mlxsw_reg_ppcnt_a_unsupported_opcodes_received_get, - }, - { - .str = "a_pause_mac_ctrl_frames_received", - .getter = mlxsw_reg_ppcnt_a_pause_mac_ctrl_frames_received_get, - }, - { - .str = "a_pause_mac_ctrl_frames_xmitted", - .getter = mlxsw_reg_ppcnt_a_pause_mac_ctrl_frames_transmitted_get, - }, -}; - -#define MLXSW_SX_PORT_HW_STATS_LEN ARRAY_SIZE(mlxsw_sx_port_hw_stats) - -static void mlxsw_sx_port_get_strings(struct net_device *dev, - u32 stringset, u8 *data) -{ - u8 *p = data; - int i; - - switch (stringset) { - case ETH_SS_STATS: - for (i = 0; i < MLXSW_SX_PORT_HW_STATS_LEN; i++) { - memcpy(p, mlxsw_sx_port_hw_stats[i].str, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - break; - } -} - -static void mlxsw_sx_port_get_stats(struct net_device *dev, - struct ethtool_stats *stats, u64 *data) -{ - struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - char ppcnt_pl[MLXSW_REG_PPCNT_LEN]; - int i; - int err; - - mlxsw_reg_ppcnt_pack(ppcnt_pl, mlxsw_sx_port->local_port, - MLXSW_REG_PPCNT_IEEE_8023_CNT, 0); - err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(ppcnt), ppcnt_pl); - for (i = 0; i < MLXSW_SX_PORT_HW_STATS_LEN; i++) - data[i] = !err ? mlxsw_sx_port_hw_stats[i].getter(ppcnt_pl) : 0; -} - -static int mlxsw_sx_port_get_sset_count(struct net_device *dev, int sset) -{ - switch (sset) { - case ETH_SS_STATS: - return MLXSW_SX_PORT_HW_STATS_LEN; - default: - return -EOPNOTSUPP; - } -} - -struct mlxsw_sx_port_link_mode { - u32 mask; - u32 supported; - u32 advertised; - u32 speed; -}; - -static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = { - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_SGMII | - MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX, - .supported = SUPPORTED_1000baseKX_Full, - .advertised = ADVERTISED_1000baseKX_Full, - .speed = 1000, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4 | - MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4, - .supported = SUPPORTED_10000baseKX4_Full, - .advertised = ADVERTISED_10000baseKX4_Full, - .speed = 10000, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR | - MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR | - MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR | - MLXSW_REG_PTYS_ETH_SPEED_10GBASE_ER_LR, - .supported = SUPPORTED_10000baseKR_Full, - .advertised = ADVERTISED_10000baseKR_Full, - .speed = 10000, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4, - .supported = SUPPORTED_40000baseCR4_Full, - .advertised = ADVERTISED_40000baseCR4_Full, - .speed = 40000, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4, - .supported = SUPPORTED_40000baseKR4_Full, - .advertised = ADVERTISED_40000baseKR4_Full, - .speed = 40000, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4, - .supported = SUPPORTED_40000baseSR4_Full, - .advertised = ADVERTISED_40000baseSR4_Full, - .speed = 40000, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_40GBASE_LR4_ER4, - .supported = SUPPORTED_40000baseLR4_Full, - .advertised = ADVERTISED_40000baseLR4_Full, - .speed = 40000, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_25GBASE_CR | - MLXSW_REG_PTYS_ETH_SPEED_25GBASE_KR | - MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR, - .speed = 25000, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_50GBASE_KR4 | - MLXSW_REG_PTYS_ETH_SPEED_50GBASE_CR2 | - MLXSW_REG_PTYS_ETH_SPEED_50GBASE_KR2, - .speed = 50000, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 | - MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 | - MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 | - MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4, - .speed = 100000, - }, -}; - -#define MLXSW_SX_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sx_port_link_mode) -#define MLXSW_SX_PORT_BASE_SPEED 10000 /* Mb/s */ - -static u32 mlxsw_sx_from_ptys_supported_port(u32 ptys_eth_proto) -{ - if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR | - MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR | - MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 | - MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4 | - MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 | - MLXSW_REG_PTYS_ETH_SPEED_SGMII)) - return SUPPORTED_FIBRE; - - if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR | - MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4 | - MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 | - MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 | - MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX)) - return SUPPORTED_Backplane; - return 0; -} - -static u32 mlxsw_sx_from_ptys_supported_link(u32 ptys_eth_proto) -{ - u32 modes = 0; - int i; - - for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) { - if (ptys_eth_proto & mlxsw_sx_port_link_mode[i].mask) - modes |= mlxsw_sx_port_link_mode[i].supported; - } - return modes; -} - -static u32 mlxsw_sx_from_ptys_advert_link(u32 ptys_eth_proto) -{ - u32 modes = 0; - int i; - - for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) { - if (ptys_eth_proto & mlxsw_sx_port_link_mode[i].mask) - modes |= mlxsw_sx_port_link_mode[i].advertised; - } - return modes; -} - -static void mlxsw_sx_from_ptys_speed_duplex(bool carrier_ok, u32 ptys_eth_proto, - struct ethtool_link_ksettings *cmd) -{ - u32 speed = SPEED_UNKNOWN; - u8 duplex = DUPLEX_UNKNOWN; - int i; - - if (!carrier_ok) - goto out; - - for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) { - if (ptys_eth_proto & mlxsw_sx_port_link_mode[i].mask) { - speed = mlxsw_sx_port_link_mode[i].speed; - duplex = DUPLEX_FULL; - break; - } - } -out: - cmd->base.speed = speed; - cmd->base.duplex = duplex; -} - -static u8 mlxsw_sx_port_connector_port(u32 ptys_eth_proto) -{ - if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR | - MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4 | - MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 | - MLXSW_REG_PTYS_ETH_SPEED_SGMII)) - return PORT_FIBRE; - - if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR | - MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 | - MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4)) - return PORT_DA; - - if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR | - MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4 | - MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 | - MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4)) - return PORT_NONE; - - return PORT_OTHER; -} - -static int -mlxsw_sx_port_get_link_ksettings(struct net_device *dev, - struct ethtool_link_ksettings *cmd) -{ - struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - char ptys_pl[MLXSW_REG_PTYS_LEN]; - u32 eth_proto_cap; - u32 eth_proto_admin; - u32 eth_proto_oper; - u32 supported, advertising, lp_advertising; - int err; - - mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sx_port->local_port, 0, false); - err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl); - if (err) { - netdev_err(dev, "Failed to get proto"); - return err; - } - mlxsw_reg_ptys_eth_unpack(ptys_pl, ð_proto_cap, - ð_proto_admin, ð_proto_oper); - - supported = mlxsw_sx_from_ptys_supported_port(eth_proto_cap) | - mlxsw_sx_from_ptys_supported_link(eth_proto_cap) | - SUPPORTED_Pause | SUPPORTED_Asym_Pause; - advertising = mlxsw_sx_from_ptys_advert_link(eth_proto_admin); - mlxsw_sx_from_ptys_speed_duplex(netif_carrier_ok(dev), - eth_proto_oper, cmd); - - eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; - cmd->base.port = mlxsw_sx_port_connector_port(eth_proto_oper); - lp_advertising = mlxsw_sx_from_ptys_advert_link(eth_proto_oper); - - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, - supported); - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, - advertising); - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.lp_advertising, - lp_advertising); - - return 0; -} - -static u32 mlxsw_sx_to_ptys_advert_link(u32 advertising) -{ - u32 ptys_proto = 0; - int i; - - for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) { - if (advertising & mlxsw_sx_port_link_mode[i].advertised) - ptys_proto |= mlxsw_sx_port_link_mode[i].mask; - } - return ptys_proto; -} - -static u32 mlxsw_sx_to_ptys_speed(u32 speed) -{ - u32 ptys_proto = 0; - int i; - - for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) { - if (speed == mlxsw_sx_port_link_mode[i].speed) - ptys_proto |= mlxsw_sx_port_link_mode[i].mask; - } - return ptys_proto; -} - -static u32 mlxsw_sx_to_ptys_upper_speed(u32 upper_speed) -{ - u32 ptys_proto = 0; - int i; - - for (i = 0; i < MLXSW_SX_PORT_LINK_MODE_LEN; i++) { - if (mlxsw_sx_port_link_mode[i].speed <= upper_speed) - ptys_proto |= mlxsw_sx_port_link_mode[i].mask; - } - return ptys_proto; -} - -static int -mlxsw_sx_port_set_link_ksettings(struct net_device *dev, - const struct ethtool_link_ksettings *cmd) -{ - struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - char ptys_pl[MLXSW_REG_PTYS_LEN]; - u32 speed; - u32 eth_proto_new; - u32 eth_proto_cap; - u32 eth_proto_admin; - u32 advertising; - bool is_up; - int err; - - speed = cmd->base.speed; - - ethtool_convert_link_mode_to_legacy_u32(&advertising, - cmd->link_modes.advertising); - - eth_proto_new = cmd->base.autoneg == AUTONEG_ENABLE ? - mlxsw_sx_to_ptys_advert_link(advertising) : - mlxsw_sx_to_ptys_speed(speed); - - mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sx_port->local_port, 0, false); - err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl); - if (err) { - netdev_err(dev, "Failed to get proto"); - return err; - } - mlxsw_reg_ptys_eth_unpack(ptys_pl, ð_proto_cap, ð_proto_admin, - NULL); - - eth_proto_new = eth_proto_new & eth_proto_cap; - if (!eth_proto_new) { - netdev_err(dev, "Not supported proto admin requested"); - return -EINVAL; - } - if (eth_proto_new == eth_proto_admin) - return 0; - - mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sx_port->local_port, - eth_proto_new, true); - err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl); - if (err) { - netdev_err(dev, "Failed to set proto admin"); - return err; - } - - err = mlxsw_sx_port_oper_status_get(mlxsw_sx_port, &is_up); - if (err) { - netdev_err(dev, "Failed to get oper status"); - return err; - } - if (!is_up) - return 0; - - err = mlxsw_sx_port_admin_status_set(mlxsw_sx_port, false); - if (err) { - netdev_err(dev, "Failed to set admin status"); - return err; - } - - err = mlxsw_sx_port_admin_status_set(mlxsw_sx_port, true); - if (err) { - netdev_err(dev, "Failed to set admin status"); - return err; - } - - return 0; -} - -static const struct ethtool_ops mlxsw_sx_port_ethtool_ops = { - .get_drvinfo = mlxsw_sx_port_get_drvinfo, - .get_link = ethtool_op_get_link, - .get_strings = mlxsw_sx_port_get_strings, - .get_ethtool_stats = mlxsw_sx_port_get_stats, - .get_sset_count = mlxsw_sx_port_get_sset_count, - .get_link_ksettings = mlxsw_sx_port_get_link_ksettings, - .set_link_ksettings = mlxsw_sx_port_set_link_ksettings, -}; - -static int mlxsw_sx_hw_id_get(struct mlxsw_sx *mlxsw_sx) -{ - char spad_pl[MLXSW_REG_SPAD_LEN] = {0}; - int err; - - err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(spad), spad_pl); - if (err) - return err; - mlxsw_reg_spad_base_mac_memcpy_from(spad_pl, mlxsw_sx->hw_id); - return 0; -} - -static int mlxsw_sx_port_dev_addr_get(struct mlxsw_sx_port *mlxsw_sx_port) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - struct net_device *dev = mlxsw_sx_port->dev; - char ppad_pl[MLXSW_REG_PPAD_LEN]; - int err; - - mlxsw_reg_ppad_pack(ppad_pl, false, 0); - err = mlxsw_reg_query(mlxsw_sx->core, MLXSW_REG(ppad), ppad_pl); - if (err) - return err; - mlxsw_reg_ppad_mac_memcpy_from(ppad_pl, dev->dev_addr); - /* The last byte value in base mac address is guaranteed - * to be such it does not overflow when adding local_port - * value. - */ - dev->dev_addr[ETH_ALEN - 1] += mlxsw_sx_port->local_port; - return 0; -} - -static int mlxsw_sx_port_stp_state_set(struct mlxsw_sx_port *mlxsw_sx_port, - u16 vid, enum mlxsw_reg_spms_state state) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - char *spms_pl; - int err; - - spms_pl = kmalloc(MLXSW_REG_SPMS_LEN, GFP_KERNEL); - if (!spms_pl) - return -ENOMEM; - mlxsw_reg_spms_pack(spms_pl, mlxsw_sx_port->local_port); - mlxsw_reg_spms_vid_pack(spms_pl, vid, state); - err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(spms), spms_pl); - kfree(spms_pl); - return err; -} - -static int mlxsw_sx_port_ib_speed_set(struct mlxsw_sx_port *mlxsw_sx_port, - u16 speed, u16 width) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - char ptys_pl[MLXSW_REG_PTYS_LEN]; - - mlxsw_reg_ptys_ib_pack(ptys_pl, mlxsw_sx_port->local_port, speed, - width); - return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl); -} - -static int -mlxsw_sx_port_speed_by_width_set(struct mlxsw_sx_port *mlxsw_sx_port, u8 width) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - u32 upper_speed = MLXSW_SX_PORT_BASE_SPEED * width; - char ptys_pl[MLXSW_REG_PTYS_LEN]; - u32 eth_proto_admin; - - eth_proto_admin = mlxsw_sx_to_ptys_upper_speed(upper_speed); - mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sx_port->local_port, - eth_proto_admin, true); - return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(ptys), ptys_pl); -} - -static int -mlxsw_sx_port_mac_learning_mode_set(struct mlxsw_sx_port *mlxsw_sx_port, - enum mlxsw_reg_spmlr_learn_mode mode) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - char spmlr_pl[MLXSW_REG_SPMLR_LEN]; - - mlxsw_reg_spmlr_pack(spmlr_pl, mlxsw_sx_port->local_port, mode); - return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(spmlr), spmlr_pl); -} - -static int __mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port, - u8 module, u8 width) -{ - struct mlxsw_sx_port *mlxsw_sx_port; - struct net_device *dev; - int err; - - dev = alloc_etherdev(sizeof(struct mlxsw_sx_port)); - if (!dev) - return -ENOMEM; - SET_NETDEV_DEV(dev, mlxsw_sx->bus_info->dev); - dev_net_set(dev, mlxsw_core_net(mlxsw_sx->core)); - mlxsw_sx_port = netdev_priv(dev); - mlxsw_sx_port->dev = dev; - mlxsw_sx_port->mlxsw_sx = mlxsw_sx; - mlxsw_sx_port->local_port = local_port; - mlxsw_sx_port->mapping.module = module; - - mlxsw_sx_port->pcpu_stats = - netdev_alloc_pcpu_stats(struct mlxsw_sx_port_pcpu_stats); - if (!mlxsw_sx_port->pcpu_stats) { - err = -ENOMEM; - goto err_alloc_stats; - } - - dev->netdev_ops = &mlxsw_sx_port_netdev_ops; - dev->ethtool_ops = &mlxsw_sx_port_ethtool_ops; - - err = mlxsw_sx_port_dev_addr_get(mlxsw_sx_port); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Unable to get port mac address\n", - mlxsw_sx_port->local_port); - goto err_dev_addr_get; - } - - netif_carrier_off(dev); - - dev->features |= NETIF_F_NETNS_LOCAL | NETIF_F_LLTX | NETIF_F_SG | - NETIF_F_VLAN_CHALLENGED; - - dev->min_mtu = 0; - dev->max_mtu = ETH_MAX_MTU; - - /* Each packet needs to have a Tx header (metadata) on top all other - * headers. - */ - dev->needed_headroom = MLXSW_TXHDR_LEN; - - err = mlxsw_sx_port_system_port_mapping_set(mlxsw_sx_port); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set system port mapping\n", - mlxsw_sx_port->local_port); - goto err_port_system_port_mapping_set; - } - - err = mlxsw_sx_port_swid_set(mlxsw_sx_port, 0); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set SWID\n", - mlxsw_sx_port->local_port); - goto err_port_swid_set; - } - - err = mlxsw_sx_port_speed_by_width_set(mlxsw_sx_port, width); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set speed\n", - mlxsw_sx_port->local_port); - goto err_port_speed_set; - } - - err = mlxsw_sx_port_mtu_eth_set(mlxsw_sx_port, ETH_DATA_LEN); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set MTU\n", - mlxsw_sx_port->local_port); - goto err_port_mtu_set; - } - - err = mlxsw_sx_port_admin_status_set(mlxsw_sx_port, false); - if (err) - goto err_port_admin_status_set; - - err = mlxsw_sx_port_stp_state_set(mlxsw_sx_port, - MLXSW_PORT_DEFAULT_VID, - MLXSW_REG_SPMS_STATE_FORWARDING); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set STP state\n", - mlxsw_sx_port->local_port); - goto err_port_stp_state_set; - } - - err = mlxsw_sx_port_mac_learning_mode_set(mlxsw_sx_port, - MLXSW_REG_SPMLR_LEARN_MODE_DISABLE); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set MAC learning mode\n", - mlxsw_sx_port->local_port); - goto err_port_mac_learning_mode_set; - } - - err = register_netdev(dev); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to register netdev\n", - mlxsw_sx_port->local_port); - goto err_register_netdev; - } - - mlxsw_core_port_eth_set(mlxsw_sx->core, mlxsw_sx_port->local_port, - mlxsw_sx_port, dev); - mlxsw_sx->ports[local_port] = mlxsw_sx_port; - return 0; - -err_register_netdev: -err_port_mac_learning_mode_set: -err_port_stp_state_set: -err_port_admin_status_set: -err_port_mtu_set: -err_port_speed_set: - mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT); -err_port_swid_set: -err_port_system_port_mapping_set: -err_dev_addr_get: - free_percpu(mlxsw_sx_port->pcpu_stats); -err_alloc_stats: - free_netdev(dev); - return err; -} - -static int mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port, - u8 module, u8 width) -{ - int err; - - err = mlxsw_core_port_init(mlxsw_sx->core, local_port, - module + 1, false, 0, false, 0, - mlxsw_sx->hw_id, sizeof(mlxsw_sx->hw_id)); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to init core port\n", - local_port); - return err; - } - err = __mlxsw_sx_port_eth_create(mlxsw_sx, local_port, module, width); - if (err) - goto err_port_create; - - return 0; - -err_port_create: - mlxsw_core_port_fini(mlxsw_sx->core, local_port); - return err; -} - -static void __mlxsw_sx_port_eth_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port) -{ - struct mlxsw_sx_port *mlxsw_sx_port = mlxsw_sx->ports[local_port]; - - mlxsw_core_port_clear(mlxsw_sx->core, local_port, mlxsw_sx); - unregister_netdev(mlxsw_sx_port->dev); /* This calls ndo_stop */ - mlxsw_sx->ports[local_port] = NULL; - mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT); - free_percpu(mlxsw_sx_port->pcpu_stats); - free_netdev(mlxsw_sx_port->dev); -} - -static bool mlxsw_sx_port_created(struct mlxsw_sx *mlxsw_sx, u8 local_port) -{ - return mlxsw_sx->ports[local_port] != NULL; -} - -static int __mlxsw_sx_port_ib_create(struct mlxsw_sx *mlxsw_sx, u8 local_port, - u8 module, u8 width) -{ - struct mlxsw_sx_port *mlxsw_sx_port; - int err; - - mlxsw_sx_port = kzalloc(sizeof(*mlxsw_sx_port), GFP_KERNEL); - if (!mlxsw_sx_port) - return -ENOMEM; - mlxsw_sx_port->mlxsw_sx = mlxsw_sx; - mlxsw_sx_port->local_port = local_port; - mlxsw_sx_port->mapping.module = module; - - err = mlxsw_sx_port_system_port_mapping_set(mlxsw_sx_port); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set system port mapping\n", - mlxsw_sx_port->local_port); - goto err_port_system_port_mapping_set; - } - - /* Adding port to Infiniband swid (1) */ - err = mlxsw_sx_port_swid_set(mlxsw_sx_port, 1); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set SWID\n", - mlxsw_sx_port->local_port); - goto err_port_swid_set; - } - - /* Expose the IB port number as it's front panel name */ - err = mlxsw_sx_port_ib_port_set(mlxsw_sx_port, module + 1); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set IB port\n", - mlxsw_sx_port->local_port); - goto err_port_ib_set; - } - - /* Supports all speeds from SDR to FDR (bitmask) and support bus width - * of 1x, 2x and 4x (3 bits bitmask) - */ - err = mlxsw_sx_port_ib_speed_set(mlxsw_sx_port, - MLXSW_REG_PTYS_IB_SPEED_EDR - 1, - BIT(3) - 1); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set speed\n", - mlxsw_sx_port->local_port); - goto err_port_speed_set; - } - - /* Change to the maximum MTU the device supports, the SMA will take - * care of the active MTU - */ - err = mlxsw_sx_port_mtu_ib_set(mlxsw_sx_port, MLXSW_IB_DEFAULT_MTU); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to set MTU\n", - mlxsw_sx_port->local_port); - goto err_port_mtu_set; - } - - err = mlxsw_sx_port_admin_status_set(mlxsw_sx_port, true); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Port %d: Failed to change admin state to UP\n", - mlxsw_sx_port->local_port); - goto err_port_admin_set; - } - - mlxsw_core_port_ib_set(mlxsw_sx->core, mlxsw_sx_port->local_port, - mlxsw_sx_port); - mlxsw_sx->ports[local_port] = mlxsw_sx_port; - return 0; - -err_port_admin_set: -err_port_mtu_set: -err_port_speed_set: -err_port_ib_set: - mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT); -err_port_swid_set: -err_port_system_port_mapping_set: - kfree(mlxsw_sx_port); - return err; -} - -static void __mlxsw_sx_port_ib_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port) -{ - struct mlxsw_sx_port *mlxsw_sx_port = mlxsw_sx->ports[local_port]; - - mlxsw_core_port_clear(mlxsw_sx->core, local_port, mlxsw_sx); - mlxsw_sx->ports[local_port] = NULL; - mlxsw_sx_port_admin_status_set(mlxsw_sx_port, false); - mlxsw_sx_port_swid_set(mlxsw_sx_port, MLXSW_PORT_SWID_DISABLED_PORT); - kfree(mlxsw_sx_port); -} - -static void __mlxsw_sx_port_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port) -{ - enum devlink_port_type port_type = - mlxsw_core_port_type_get(mlxsw_sx->core, local_port); - - if (port_type == DEVLINK_PORT_TYPE_ETH) - __mlxsw_sx_port_eth_remove(mlxsw_sx, local_port); - else if (port_type == DEVLINK_PORT_TYPE_IB) - __mlxsw_sx_port_ib_remove(mlxsw_sx, local_port); -} - -static void mlxsw_sx_port_remove(struct mlxsw_sx *mlxsw_sx, u8 local_port) -{ - __mlxsw_sx_port_remove(mlxsw_sx, local_port); - mlxsw_core_port_fini(mlxsw_sx->core, local_port); -} - -static void mlxsw_sx_ports_remove(struct mlxsw_sx *mlxsw_sx) -{ - int i; - - for (i = 1; i < mlxsw_core_max_ports(mlxsw_sx->core); i++) - if (mlxsw_sx_port_created(mlxsw_sx, i)) - mlxsw_sx_port_remove(mlxsw_sx, i); - kfree(mlxsw_sx->ports); - mlxsw_sx->ports = NULL; -} - -static int mlxsw_sx_ports_create(struct mlxsw_sx *mlxsw_sx) -{ - unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sx->core); - size_t alloc_size; - u8 module, width; - int i; - int err; - - alloc_size = sizeof(struct mlxsw_sx_port *) * max_ports; - mlxsw_sx->ports = kzalloc(alloc_size, GFP_KERNEL); - if (!mlxsw_sx->ports) - return -ENOMEM; - - for (i = 1; i < max_ports; i++) { - err = mlxsw_sx_port_module_info_get(mlxsw_sx, i, &module, - &width); - if (err) - goto err_port_module_info_get; - if (!width) - continue; - err = mlxsw_sx_port_eth_create(mlxsw_sx, i, module, width); - if (err) - goto err_port_create; - } - return 0; - -err_port_create: -err_port_module_info_get: - for (i--; i >= 1; i--) - if (mlxsw_sx_port_created(mlxsw_sx, i)) - mlxsw_sx_port_remove(mlxsw_sx, i); - kfree(mlxsw_sx->ports); - mlxsw_sx->ports = NULL; - return err; -} - -static void mlxsw_sx_pude_eth_event_func(struct mlxsw_sx_port *mlxsw_sx_port, - enum mlxsw_reg_pude_oper_status status) -{ - if (status == MLXSW_PORT_OPER_STATUS_UP) { - netdev_info(mlxsw_sx_port->dev, "link up\n"); - netif_carrier_on(mlxsw_sx_port->dev); - } else { - netdev_info(mlxsw_sx_port->dev, "link down\n"); - netif_carrier_off(mlxsw_sx_port->dev); - } -} - -static void mlxsw_sx_pude_ib_event_func(struct mlxsw_sx_port *mlxsw_sx_port, - enum mlxsw_reg_pude_oper_status status) -{ - if (status == MLXSW_PORT_OPER_STATUS_UP) - pr_info("ib link for port %d - up\n", - mlxsw_sx_port->mapping.module + 1); - else - pr_info("ib link for port %d - down\n", - mlxsw_sx_port->mapping.module + 1); -} - -static void mlxsw_sx_pude_event_func(const struct mlxsw_reg_info *reg, - char *pude_pl, void *priv) -{ - struct mlxsw_sx *mlxsw_sx = priv; - struct mlxsw_sx_port *mlxsw_sx_port; - enum mlxsw_reg_pude_oper_status status; - enum devlink_port_type port_type; - u8 local_port; - - local_port = mlxsw_reg_pude_local_port_get(pude_pl); - mlxsw_sx_port = mlxsw_sx->ports[local_port]; - if (!mlxsw_sx_port) { - dev_warn(mlxsw_sx->bus_info->dev, "Port %d: Link event received for non-existent port\n", - local_port); - return; - } - - status = mlxsw_reg_pude_oper_status_get(pude_pl); - port_type = mlxsw_core_port_type_get(mlxsw_sx->core, local_port); - if (port_type == DEVLINK_PORT_TYPE_ETH) - mlxsw_sx_pude_eth_event_func(mlxsw_sx_port, status); - else if (port_type == DEVLINK_PORT_TYPE_IB) - mlxsw_sx_pude_ib_event_func(mlxsw_sx_port, status); -} - -static void mlxsw_sx_rx_listener_func(struct sk_buff *skb, u8 local_port, - void *priv) -{ - struct mlxsw_sx *mlxsw_sx = priv; - struct mlxsw_sx_port *mlxsw_sx_port = mlxsw_sx->ports[local_port]; - struct mlxsw_sx_port_pcpu_stats *pcpu_stats; - - if (unlikely(!mlxsw_sx_port)) { - dev_warn_ratelimited(mlxsw_sx->bus_info->dev, "Port %d: skb received for non-existent port\n", - local_port); - return; - } - - skb->dev = mlxsw_sx_port->dev; - - pcpu_stats = this_cpu_ptr(mlxsw_sx_port->pcpu_stats); - u64_stats_update_begin(&pcpu_stats->syncp); - pcpu_stats->rx_packets++; - pcpu_stats->rx_bytes += skb->len; - u64_stats_update_end(&pcpu_stats->syncp); - - skb->protocol = eth_type_trans(skb, skb->dev); - netif_receive_skb(skb); -} - -static int mlxsw_sx_port_type_set(struct mlxsw_core *mlxsw_core, u8 local_port, - enum devlink_port_type new_type) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_core_driver_priv(mlxsw_core); - u8 module, width; - int err; - - if (!mlxsw_sx->ports || !mlxsw_sx->ports[local_port]) { - dev_err(mlxsw_sx->bus_info->dev, "Port number \"%d\" does not exist\n", - local_port); - return -EINVAL; - } - - if (new_type == DEVLINK_PORT_TYPE_AUTO) - return -EOPNOTSUPP; - - __mlxsw_sx_port_remove(mlxsw_sx, local_port); - err = mlxsw_sx_port_module_info_get(mlxsw_sx, local_port, &module, - &width); - if (err) - goto err_port_module_info_get; - - if (new_type == DEVLINK_PORT_TYPE_ETH) - err = __mlxsw_sx_port_eth_create(mlxsw_sx, local_port, module, - width); - else if (new_type == DEVLINK_PORT_TYPE_IB) - err = __mlxsw_sx_port_ib_create(mlxsw_sx, local_port, module, - width); - -err_port_module_info_get: - return err; -} - -enum { - MLXSW_REG_HTGT_TRAP_GROUP_SX2_RX = 1, - MLXSW_REG_HTGT_TRAP_GROUP_SX2_CTRL = 2, -}; - -#define MLXSW_SX_RXL(_trap_id) \ - MLXSW_RXL(mlxsw_sx_rx_listener_func, _trap_id, TRAP_TO_CPU, \ - false, SX2_RX, FORWARD) - -static const struct mlxsw_listener mlxsw_sx_listener[] = { - MLXSW_EVENTL(mlxsw_sx_pude_event_func, PUDE, EMAD), - MLXSW_SX_RXL(FDB_MC), - MLXSW_SX_RXL(STP), - MLXSW_SX_RXL(LACP), - MLXSW_SX_RXL(EAPOL), - MLXSW_SX_RXL(LLDP), - MLXSW_SX_RXL(MMRP), - MLXSW_SX_RXL(MVRP), - MLXSW_SX_RXL(RPVST), - MLXSW_SX_RXL(DHCP), - MLXSW_SX_RXL(IGMP_QUERY), - MLXSW_SX_RXL(IGMP_V1_REPORT), - MLXSW_SX_RXL(IGMP_V2_REPORT), - MLXSW_SX_RXL(IGMP_V2_LEAVE), - MLXSW_SX_RXL(IGMP_V3_REPORT), -}; - -static int mlxsw_sx_traps_init(struct mlxsw_sx *mlxsw_sx) -{ - char htgt_pl[MLXSW_REG_HTGT_LEN]; - int i; - int err; - - mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_SX2_RX, - MLXSW_REG_HTGT_INVALID_POLICER, - MLXSW_REG_HTGT_DEFAULT_PRIORITY, - MLXSW_REG_HTGT_DEFAULT_TC); - mlxsw_reg_htgt_local_path_rdq_set(htgt_pl, - MLXSW_REG_HTGT_LOCAL_PATH_RDQ_SX2_RX); - - err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(htgt), htgt_pl); - if (err) - return err; - - mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_SX2_CTRL, - MLXSW_REG_HTGT_INVALID_POLICER, - MLXSW_REG_HTGT_DEFAULT_PRIORITY, - MLXSW_REG_HTGT_DEFAULT_TC); - mlxsw_reg_htgt_local_path_rdq_set(htgt_pl, - MLXSW_REG_HTGT_LOCAL_PATH_RDQ_SX2_CTRL); - - err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(htgt), htgt_pl); - if (err) - return err; - - for (i = 0; i < ARRAY_SIZE(mlxsw_sx_listener); i++) { - err = mlxsw_core_trap_register(mlxsw_sx->core, - &mlxsw_sx_listener[i], - mlxsw_sx); - if (err) - goto err_listener_register; - - } - return 0; - -err_listener_register: - for (i--; i >= 0; i--) { - mlxsw_core_trap_unregister(mlxsw_sx->core, - &mlxsw_sx_listener[i], - mlxsw_sx); - } - return err; -} - -static void mlxsw_sx_traps_fini(struct mlxsw_sx *mlxsw_sx) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(mlxsw_sx_listener); i++) { - mlxsw_core_trap_unregister(mlxsw_sx->core, - &mlxsw_sx_listener[i], - mlxsw_sx); - } -} - -static int mlxsw_sx_flood_init(struct mlxsw_sx *mlxsw_sx) -{ - char sfgc_pl[MLXSW_REG_SFGC_LEN]; - char sgcr_pl[MLXSW_REG_SGCR_LEN]; - char *sftr_pl; - int err; - - /* Configure a flooding table, which includes only CPU port. */ - sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL); - if (!sftr_pl) - return -ENOMEM; - mlxsw_reg_sftr_pack(sftr_pl, 0, 0, MLXSW_REG_SFGC_TABLE_TYPE_SINGLE, 0, - MLXSW_PORT_CPU_PORT, true); - err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sftr), sftr_pl); - kfree(sftr_pl); - if (err) - return err; - - /* Flood different packet types using the flooding table. */ - mlxsw_reg_sfgc_pack(sfgc_pl, - MLXSW_REG_SFGC_TYPE_UNKNOWN_UNICAST, - MLXSW_REG_SFGC_BRIDGE_TYPE_1Q_FID, - MLXSW_REG_SFGC_TABLE_TYPE_SINGLE, - 0); - err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sfgc), sfgc_pl); - if (err) - return err; - - mlxsw_reg_sfgc_pack(sfgc_pl, - MLXSW_REG_SFGC_TYPE_BROADCAST, - MLXSW_REG_SFGC_BRIDGE_TYPE_1Q_FID, - MLXSW_REG_SFGC_TABLE_TYPE_SINGLE, - 0); - err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sfgc), sfgc_pl); - if (err) - return err; - - mlxsw_reg_sfgc_pack(sfgc_pl, - MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_NON_IP, - MLXSW_REG_SFGC_BRIDGE_TYPE_1Q_FID, - MLXSW_REG_SFGC_TABLE_TYPE_SINGLE, - 0); - err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sfgc), sfgc_pl); - if (err) - return err; - - mlxsw_reg_sfgc_pack(sfgc_pl, - MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV6, - MLXSW_REG_SFGC_BRIDGE_TYPE_1Q_FID, - MLXSW_REG_SFGC_TABLE_TYPE_SINGLE, - 0); - err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sfgc), sfgc_pl); - if (err) - return err; - - mlxsw_reg_sfgc_pack(sfgc_pl, - MLXSW_REG_SFGC_TYPE_UNREGISTERED_MULTICAST_IPV4, - MLXSW_REG_SFGC_BRIDGE_TYPE_1Q_FID, - MLXSW_REG_SFGC_TABLE_TYPE_SINGLE, - 0); - err = mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sfgc), sfgc_pl); - if (err) - return err; - - mlxsw_reg_sgcr_pack(sgcr_pl, true); - return mlxsw_reg_write(mlxsw_sx->core, MLXSW_REG(sgcr), sgcr_pl); -} - -static int mlxsw_sx_basic_trap_groups_set(struct mlxsw_core *mlxsw_core) -{ - char htgt_pl[MLXSW_REG_HTGT_LEN]; - - mlxsw_reg_htgt_pack(htgt_pl, MLXSW_REG_HTGT_TRAP_GROUP_EMAD, - MLXSW_REG_HTGT_INVALID_POLICER, - MLXSW_REG_HTGT_DEFAULT_PRIORITY, - MLXSW_REG_HTGT_DEFAULT_TC); - mlxsw_reg_htgt_swid_set(htgt_pl, MLXSW_PORT_SWID_ALL_SWIDS); - mlxsw_reg_htgt_local_path_rdq_set(htgt_pl, - MLXSW_REG_HTGT_LOCAL_PATH_RDQ_SX2_EMAD); - return mlxsw_reg_write(mlxsw_core, MLXSW_REG(htgt), htgt_pl); -} - -static int mlxsw_sx_init(struct mlxsw_core *mlxsw_core, - const struct mlxsw_bus_info *mlxsw_bus_info, - struct netlink_ext_ack *extack) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_core_driver_priv(mlxsw_core); - int err; - - mlxsw_sx->core = mlxsw_core; - mlxsw_sx->bus_info = mlxsw_bus_info; - - err = mlxsw_sx_hw_id_get(mlxsw_sx); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Failed to get switch HW ID\n"); - return err; - } - - err = mlxsw_sx_ports_create(mlxsw_sx); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Failed to create ports\n"); - return err; - } - - err = mlxsw_sx_traps_init(mlxsw_sx); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Failed to set traps\n"); - goto err_listener_register; - } - - err = mlxsw_sx_flood_init(mlxsw_sx); - if (err) { - dev_err(mlxsw_sx->bus_info->dev, "Failed to initialize flood tables\n"); - goto err_flood_init; - } - - return 0; - -err_flood_init: - mlxsw_sx_traps_fini(mlxsw_sx); -err_listener_register: - mlxsw_sx_ports_remove(mlxsw_sx); - return err; -} - -static void mlxsw_sx_fini(struct mlxsw_core *mlxsw_core) -{ - struct mlxsw_sx *mlxsw_sx = mlxsw_core_driver_priv(mlxsw_core); - - mlxsw_sx_traps_fini(mlxsw_sx); - mlxsw_sx_ports_remove(mlxsw_sx); -} - -static const struct mlxsw_config_profile mlxsw_sx_config_profile = { - .used_max_vepa_channels = 1, - .max_vepa_channels = 0, - .used_max_mid = 1, - .max_mid = 7000, - .used_max_pgt = 1, - .max_pgt = 0, - .used_max_system_port = 1, - .max_system_port = 48000, - .used_max_vlan_groups = 1, - .max_vlan_groups = 127, - .used_max_regions = 1, - .max_regions = 400, - .used_flood_tables = 1, - .max_flood_tables = 2, - .max_vid_flood_tables = 1, - .used_flood_mode = 1, - .flood_mode = 3, - .used_max_ib_mc = 1, - .max_ib_mc = 6, - .used_max_pkey = 1, - .max_pkey = 0, - .swid_config = { - { - .used_type = 1, - .type = MLXSW_PORT_SWID_TYPE_ETH, - }, - { - .used_type = 1, - .type = MLXSW_PORT_SWID_TYPE_IB, - } - }, -}; - -static struct mlxsw_driver mlxsw_sx_driver = { - .kind = mlxsw_sx_driver_name, - .priv_size = sizeof(struct mlxsw_sx), - .init = mlxsw_sx_init, - .fini = mlxsw_sx_fini, - .basic_trap_groups_set = mlxsw_sx_basic_trap_groups_set, - .txhdr_construct = mlxsw_sx_txhdr_construct, - .txhdr_len = MLXSW_TXHDR_LEN, - .profile = &mlxsw_sx_config_profile, - .port_type_set = mlxsw_sx_port_type_set, -}; - -static const struct pci_device_id mlxsw_sx_pci_id_table[] = { - {PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SWITCHX2), 0}, - {0, }, -}; - -static struct pci_driver mlxsw_sx_pci_driver = { - .name = mlxsw_sx_driver_name, - .id_table = mlxsw_sx_pci_id_table, -}; - -static int __init mlxsw_sx_module_init(void) -{ - int err; - - err = mlxsw_core_driver_register(&mlxsw_sx_driver); - if (err) - return err; - - err = mlxsw_pci_driver_register(&mlxsw_sx_pci_driver); - if (err) - goto err_pci_driver_register; - - return 0; - -err_pci_driver_register: - mlxsw_core_driver_unregister(&mlxsw_sx_driver); - return err; -} - -static void __exit mlxsw_sx_module_exit(void) -{ - mlxsw_pci_driver_unregister(&mlxsw_sx_pci_driver); - mlxsw_core_driver_unregister(&mlxsw_sx_driver); -} - -module_init(mlxsw_sx_module_init); -module_exit(mlxsw_sx_module_exit); - -MODULE_LICENSE("Dual BSD/GPL"); -MODULE_AUTHOR("Jiri Pirko "); -MODULE_DESCRIPTION("Mellanox SwitchX-2 driver"); -MODULE_DEVICE_TABLE(pci, mlxsw_sx_pci_id_table); diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c index caa251d0e381..b27713906d3a 100644 --- a/drivers/net/ethernet/micrel/ks8842.c +++ b/drivers/net/ethernet/micrel/ks8842.c @@ -1135,6 +1135,10 @@ static int ks8842_probe(struct platform_device *pdev) unsigned i; iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!iomem) { + dev_err(&pdev->dev, "Invalid resource\n"); + return -EINVAL; + } if (!request_mem_region(iomem->start, resource_size(iomem), DRV_NAME)) goto err_mem_region; diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index 13eef6e9bd2d..831518466de2 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -1022,30 +1022,23 @@ static int ks8851_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val) * * Read and check the TX/RX memory selftest information. */ -static int ks8851_read_selftest(struct ks8851_net *ks) +static void ks8851_read_selftest(struct ks8851_net *ks) { unsigned both_done = MBIR_TXMBF | MBIR_RXMBF; - int ret = 0; unsigned rd; rd = ks8851_rdreg16(ks, KS_MBIR); if ((rd & both_done) != both_done) { netdev_warn(ks->netdev, "Memory selftest not finished\n"); - return 0; + return; } - if (rd & MBIR_TXMBFA) { + if (rd & MBIR_TXMBFA) netdev_err(ks->netdev, "TX memory selftest fail\n"); - ret |= 1; - } - if (rd & MBIR_RXMBFA) { + if (rd & MBIR_RXMBFA) netdev_err(ks->netdev, "RX memory selftest fail\n"); - ret |= 2; - } - - return 0; } /* driver bus management functions */ diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index 9ed264ed7070..7945eb5e2fe8 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -25,6 +25,7 @@ #include #include #include +#include /* DMA Registers */ @@ -271,84 +272,15 @@ #define KS884X_PHY_CTRL_OFFSET 0x00 -/* Mode Control Register */ -#define PHY_REG_CTRL 0 - -#define PHY_RESET 0x8000 -#define PHY_LOOPBACK 0x4000 -#define PHY_SPEED_100MBIT 0x2000 -#define PHY_AUTO_NEG_ENABLE 0x1000 -#define PHY_POWER_DOWN 0x0800 -#define PHY_MII_DISABLE 0x0400 -#define PHY_AUTO_NEG_RESTART 0x0200 -#define PHY_FULL_DUPLEX 0x0100 -#define PHY_COLLISION_TEST 0x0080 -#define PHY_HP_MDIX 0x0020 -#define PHY_FORCE_MDIX 0x0010 -#define PHY_AUTO_MDIX_DISABLE 0x0008 -#define PHY_REMOTE_FAULT_DISABLE 0x0004 -#define PHY_TRANSMIT_DISABLE 0x0002 -#define PHY_LED_DISABLE 0x0001 - #define KS884X_PHY_STATUS_OFFSET 0x02 -/* Mode Status Register */ -#define PHY_REG_STATUS 1 - -#define PHY_100BT4_CAPABLE 0x8000 -#define PHY_100BTX_FD_CAPABLE 0x4000 -#define PHY_100BTX_CAPABLE 0x2000 -#define PHY_10BT_FD_CAPABLE 0x1000 -#define PHY_10BT_CAPABLE 0x0800 -#define PHY_MII_SUPPRESS_CAPABLE 0x0040 -#define PHY_AUTO_NEG_ACKNOWLEDGE 0x0020 -#define PHY_REMOTE_FAULT 0x0010 -#define PHY_AUTO_NEG_CAPABLE 0x0008 -#define PHY_LINK_STATUS 0x0004 -#define PHY_JABBER_DETECT 0x0002 -#define PHY_EXTENDED_CAPABILITY 0x0001 - #define KS884X_PHY_ID_1_OFFSET 0x04 #define KS884X_PHY_ID_2_OFFSET 0x06 -/* PHY Identifier Registers */ -#define PHY_REG_ID_1 2 -#define PHY_REG_ID_2 3 - #define KS884X_PHY_AUTO_NEG_OFFSET 0x08 -/* Auto-Negotiation Advertisement Register */ -#define PHY_REG_AUTO_NEGOTIATION 4 - -#define PHY_AUTO_NEG_NEXT_PAGE 0x8000 -#define PHY_AUTO_NEG_REMOTE_FAULT 0x2000 -/* Not supported. */ -#define PHY_AUTO_NEG_ASYM_PAUSE 0x0800 -#define PHY_AUTO_NEG_SYM_PAUSE 0x0400 -#define PHY_AUTO_NEG_100BT4 0x0200 -#define PHY_AUTO_NEG_100BTX_FD 0x0100 -#define PHY_AUTO_NEG_100BTX 0x0080 -#define PHY_AUTO_NEG_10BT_FD 0x0040 -#define PHY_AUTO_NEG_10BT 0x0020 -#define PHY_AUTO_NEG_SELECTOR 0x001F -#define PHY_AUTO_NEG_802_3 0x0001 - -#define PHY_AUTO_NEG_PAUSE (PHY_AUTO_NEG_SYM_PAUSE | PHY_AUTO_NEG_ASYM_PAUSE) - #define KS884X_PHY_REMOTE_CAP_OFFSET 0x0A -/* Auto-Negotiation Link Partner Ability Register */ -#define PHY_REG_REMOTE_CAPABILITY 5 - -#define PHY_REMOTE_NEXT_PAGE 0x8000 -#define PHY_REMOTE_ACKNOWLEDGE 0x4000 -#define PHY_REMOTE_REMOTE_FAULT 0x2000 -#define PHY_REMOTE_SYM_PAUSE 0x0400 -#define PHY_REMOTE_100BTX_FD 0x0100 -#define PHY_REMOTE_100BTX 0x0080 -#define PHY_REMOTE_10BT_FD 0x0040 -#define PHY_REMOTE_10BT 0x0020 - /* P1VCT */ #define KS884X_P1VCT_P 0x04F0 #define KS884X_P1PHYCTRL_P 0x04F2 @@ -2153,7 +2085,7 @@ static void sw_cfg_broad_storm(struct ksz_hw *hw, u8 percent) } /** - * sw_get_board_storm - get broadcast storm threshold + * sw_get_broad_storm - get broadcast storm threshold * @hw: The hardware instance. * @percent: Buffer to store the broadcast storm threshold percentage. * @@ -2886,15 +2818,6 @@ static void sw_block_addr(struct ksz_hw *hw) } } -#define PHY_LINK_SUPPORT \ - (PHY_AUTO_NEG_ASYM_PAUSE | \ - PHY_AUTO_NEG_SYM_PAUSE | \ - PHY_AUTO_NEG_100BT4 | \ - PHY_AUTO_NEG_100BTX_FD | \ - PHY_AUTO_NEG_100BTX | \ - PHY_AUTO_NEG_10BT_FD | \ - PHY_AUTO_NEG_10BT) - static inline void hw_r_phy_ctrl(struct ksz_hw *hw, int phy, u16 *data) { *data = readw(hw->io + phy + KS884X_PHY_CTRL_OFFSET); @@ -2973,7 +2896,7 @@ static void hw_r_phy(struct ksz_hw *hw, int port, u16 reg, u16 *val) } /** - * port_w_phy - write data to PHY register + * hw_w_phy - write data to PHY register * @hw: The hardware instance. * @port: Port to write. * @reg: PHY register to write. @@ -3238,16 +3161,18 @@ static void determine_flow_ctrl(struct ksz_hw *hw, struct ksz_port *port, rx = tx = 0; if (port->force_link) rx = tx = 1; - if (remote & PHY_AUTO_NEG_SYM_PAUSE) { - if (local & PHY_AUTO_NEG_SYM_PAUSE) { + if (remote & LPA_PAUSE_CAP) { + if (local & ADVERTISE_PAUSE_CAP) { rx = tx = 1; - } else if ((remote & PHY_AUTO_NEG_ASYM_PAUSE) && - (local & PHY_AUTO_NEG_PAUSE) == - PHY_AUTO_NEG_ASYM_PAUSE) { + } else if ((remote & LPA_PAUSE_ASYM) && + (local & + (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM)) == + ADVERTISE_PAUSE_ASYM) { tx = 1; } - } else if (remote & PHY_AUTO_NEG_ASYM_PAUSE) { - if ((local & PHY_AUTO_NEG_PAUSE) == PHY_AUTO_NEG_PAUSE) + } else if (remote & LPA_PAUSE_ASYM) { + if ((local & (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM)) + == (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM)) rx = 1; } if (!hw->ksz_switch) @@ -3428,16 +3353,16 @@ static void port_force_link_speed(struct ksz_port *port) phy = KS884X_PHY_1_CTRL_OFFSET + p * PHY_CTRL_INTERVAL; hw_r_phy_ctrl(hw, phy, &data); - data &= ~PHY_AUTO_NEG_ENABLE; + data &= ~BMCR_ANENABLE; if (10 == port->speed) - data &= ~PHY_SPEED_100MBIT; + data &= ~BMCR_SPEED100; else if (100 == port->speed) - data |= PHY_SPEED_100MBIT; + data |= BMCR_SPEED100; if (1 == port->duplex) - data &= ~PHY_FULL_DUPLEX; + data &= ~BMCR_FULLDPLX; else if (2 == port->duplex) - data |= PHY_FULL_DUPLEX; + data |= BMCR_FULLDPLX; hw_w_phy_ctrl(hw, phy, data); } } @@ -4782,7 +4707,7 @@ static void transmit_cleanup(struct dev_info *hw_priv, int normal) } /** - * transmit_done - transmit done processing + * tx_done - transmit done processing * @hw_priv: Network device. * * This routine is called when the transmit interrupt is triggered, indicating diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig index d0f6dfe0dcf3..d54aa164c4e9 100644 --- a/drivers/net/ethernet/microchip/Kconfig +++ b/drivers/net/ethernet/microchip/Kconfig @@ -54,4 +54,6 @@ config LAN743X To compile this driver as a module, choose M here. The module will be called lan743x. +source "drivers/net/ethernet/microchip/sparx5/Kconfig" + endif # NET_VENDOR_MICROCHIP diff --git a/drivers/net/ethernet/microchip/Makefile b/drivers/net/ethernet/microchip/Makefile index da603540ca57..c77dc0379bfd 100644 --- a/drivers/net/ethernet/microchip/Makefile +++ b/drivers/net/ethernet/microchip/Makefile @@ -8,3 +8,5 @@ obj-$(CONFIG_ENCX24J600) += encx24j600.o encx24j600-regmap.o obj-$(CONFIG_LAN743X) += lan743x.o lan743x-objs := lan743x_main.o lan743x_ethtool.o lan743x_ptp.o + +obj-$(CONFIG_SPARX5_SWITCH) += sparx5/ diff --git a/drivers/net/ethernet/microchip/sparx5/Kconfig b/drivers/net/ethernet/microchip/sparx5/Kconfig new file mode 100644 index 000000000000..a80419d8d4b5 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/Kconfig @@ -0,0 +1,9 @@ +config SPARX5_SWITCH + tristate "Sparx5 switch driver" + depends on NET_SWITCHDEV + depends on HAS_IOMEM + select PHYLINK + select PHY_SPARX5_SERDES + select RESET_CONTROLLER + help + This driver supports the Sparx5 network switch device. diff --git a/drivers/net/ethernet/microchip/sparx5/Makefile b/drivers/net/ethernet/microchip/sparx5/Makefile new file mode 100644 index 000000000000..faa8f07a6b75 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for the Microchip Sparx5 network device drivers. +# + +obj-$(CONFIG_SPARX5_SWITCH) += sparx5-switch.o + +sparx5-switch-objs := sparx5_main.o sparx5_packet.o \ + sparx5_netdev.o sparx5_phylink.o sparx5_port.o sparx5_mactable.o sparx5_vlan.o \ + sparx5_switchdev.o sparx5_calendar.o sparx5_ethtool.o diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_calendar.c b/drivers/net/ethernet/microchip/sparx5/sparx5_calendar.c new file mode 100644 index 000000000000..76a8bb596aec --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_calendar.c @@ -0,0 +1,596 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries. + */ + +#include +#include + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +/* QSYS calendar information */ +#define SPX5_PORTS_PER_CALREG 10 /* Ports mapped in a calendar register */ +#define SPX5_CALBITS_PER_PORT 3 /* Bit per port in calendar register */ + +/* DSM calendar information */ +#define SPX5_DSM_CAL_LEN 64 +#define SPX5_DSM_CAL_EMPTY 0xFFFF +#define SPX5_DSM_CAL_MAX_DEVS_PER_TAXI 13 +#define SPX5_DSM_CAL_TAXIS 8 +#define SPX5_DSM_CAL_BW_LOSS 553 + +#define SPX5_TAXI_PORT_MAX 70 + +#define SPEED_12500 12500 + +/* Maps from taxis to port numbers */ +static u32 sparx5_taxi_ports[SPX5_DSM_CAL_TAXIS][SPX5_DSM_CAL_MAX_DEVS_PER_TAXI] = { + {57, 12, 0, 1, 2, 16, 17, 18, 19, 20, 21, 22, 23}, + {58, 13, 3, 4, 5, 24, 25, 26, 27, 28, 29, 30, 31}, + {59, 14, 6, 7, 8, 32, 33, 34, 35, 36, 37, 38, 39}, + {60, 15, 9, 10, 11, 40, 41, 42, 43, 44, 45, 46, 47}, + {61, 48, 49, 50, 99, 99, 99, 99, 99, 99, 99, 99, 99}, + {62, 51, 52, 53, 99, 99, 99, 99, 99, 99, 99, 99, 99}, + {56, 63, 54, 55, 99, 99, 99, 99, 99, 99, 99, 99, 99}, + {64, 99, 99, 99, 99, 99, 99, 99, 99, 99, 99, 99, 99}, +}; + +struct sparx5_calendar_data { + u32 schedule[SPX5_DSM_CAL_LEN]; + u32 avg_dist[SPX5_DSM_CAL_MAX_DEVS_PER_TAXI]; + u32 taxi_ports[SPX5_DSM_CAL_MAX_DEVS_PER_TAXI]; + u32 taxi_speeds[SPX5_DSM_CAL_MAX_DEVS_PER_TAXI]; + u32 dev_slots[SPX5_DSM_CAL_MAX_DEVS_PER_TAXI]; + u32 new_slots[SPX5_DSM_CAL_LEN]; + u32 temp_sched[SPX5_DSM_CAL_LEN]; + u32 indices[SPX5_DSM_CAL_LEN]; + u32 short_list[SPX5_DSM_CAL_LEN]; + u32 long_list[SPX5_DSM_CAL_LEN]; +}; + +static u32 sparx5_target_bandwidth(struct sparx5 *sparx5) +{ + switch (sparx5->target_ct) { + case SPX5_TARGET_CT_7546: + case SPX5_TARGET_CT_7546TSN: + return 65000; + case SPX5_TARGET_CT_7549: + case SPX5_TARGET_CT_7549TSN: + return 91000; + case SPX5_TARGET_CT_7552: + case SPX5_TARGET_CT_7552TSN: + return 129000; + case SPX5_TARGET_CT_7556: + case SPX5_TARGET_CT_7556TSN: + return 161000; + case SPX5_TARGET_CT_7558: + case SPX5_TARGET_CT_7558TSN: + return 201000; + default: + return 0; + } +} + +/* This is used in calendar configuration */ +enum sparx5_cal_bw { + SPX5_CAL_SPEED_NONE = 0, + SPX5_CAL_SPEED_1G = 1, + SPX5_CAL_SPEED_2G5 = 2, + SPX5_CAL_SPEED_5G = 3, + SPX5_CAL_SPEED_10G = 4, + SPX5_CAL_SPEED_25G = 5, + SPX5_CAL_SPEED_0G5 = 6, + SPX5_CAL_SPEED_12G5 = 7 +}; + +static u32 sparx5_clk_to_bandwidth(enum sparx5_core_clockfreq cclock) +{ + switch (cclock) { + case SPX5_CORE_CLOCK_250MHZ: return 83000; /* 250000 / 3 */ + case SPX5_CORE_CLOCK_500MHZ: return 166000; /* 500000 / 3 */ + case SPX5_CORE_CLOCK_625MHZ: return 208000; /* 625000 / 3 */ + default: return 0; + } + return 0; +} + +static u32 sparx5_cal_speed_to_value(enum sparx5_cal_bw speed) +{ + switch (speed) { + case SPX5_CAL_SPEED_1G: return 1000; + case SPX5_CAL_SPEED_2G5: return 2500; + case SPX5_CAL_SPEED_5G: return 5000; + case SPX5_CAL_SPEED_10G: return 10000; + case SPX5_CAL_SPEED_25G: return 25000; + case SPX5_CAL_SPEED_0G5: return 500; + case SPX5_CAL_SPEED_12G5: return 12500; + default: return 0; + } +} + +static u32 sparx5_bandwidth_to_calendar(u32 bw) +{ + switch (bw) { + case SPEED_10: return SPX5_CAL_SPEED_0G5; + case SPEED_100: return SPX5_CAL_SPEED_0G5; + case SPEED_1000: return SPX5_CAL_SPEED_1G; + case SPEED_2500: return SPX5_CAL_SPEED_2G5; + case SPEED_5000: return SPX5_CAL_SPEED_5G; + case SPEED_10000: return SPX5_CAL_SPEED_10G; + case SPEED_12500: return SPX5_CAL_SPEED_12G5; + case SPEED_25000: return SPX5_CAL_SPEED_25G; + case SPEED_UNKNOWN: return SPX5_CAL_SPEED_1G; + default: return SPX5_CAL_SPEED_NONE; + } +} + +static enum sparx5_cal_bw sparx5_get_port_cal_speed(struct sparx5 *sparx5, + u32 portno) +{ + struct sparx5_port *port; + + if (portno >= SPX5_PORTS) { + /* Internal ports */ + if (portno == SPX5_PORT_CPU_0 || portno == SPX5_PORT_CPU_1) { + /* Equals 1.25G */ + return SPX5_CAL_SPEED_2G5; + } else if (portno == SPX5_PORT_VD0) { + /* IPMC only idle BW */ + return SPX5_CAL_SPEED_NONE; + } else if (portno == SPX5_PORT_VD1) { + /* OAM only idle BW */ + return SPX5_CAL_SPEED_NONE; + } else if (portno == SPX5_PORT_VD2) { + /* IPinIP gets only idle BW */ + return SPX5_CAL_SPEED_NONE; + } + /* not in port map */ + return SPX5_CAL_SPEED_NONE; + } + /* Front ports - may be used */ + port = sparx5->ports[portno]; + if (!port) + return SPX5_CAL_SPEED_NONE; + return sparx5_bandwidth_to_calendar(port->conf.bandwidth); +} + +/* Auto configure the QSYS calendar based on port configuration */ +int sparx5_config_auto_calendar(struct sparx5 *sparx5) +{ + u32 cal[7], value, idx, portno; + u32 max_core_bw; + u32 total_bw = 0, used_port_bw = 0; + int err = 0; + enum sparx5_cal_bw spd; + + memset(cal, 0, sizeof(cal)); + + max_core_bw = sparx5_clk_to_bandwidth(sparx5->coreclock); + if (max_core_bw == 0) { + dev_err(sparx5->dev, "Core clock not supported"); + return -EINVAL; + } + + /* Setup the calendar with the bandwidth to each port */ + for (portno = 0; portno < SPX5_PORTS_ALL; portno++) { + u64 reg, offset, this_bw; + + spd = sparx5_get_port_cal_speed(sparx5, portno); + if (spd == SPX5_CAL_SPEED_NONE) + continue; + + this_bw = sparx5_cal_speed_to_value(spd); + if (portno < SPX5_PORTS) + used_port_bw += this_bw; + else + /* Internal ports are granted half the value */ + this_bw = this_bw / 2; + total_bw += this_bw; + reg = portno; + offset = do_div(reg, SPX5_PORTS_PER_CALREG); + cal[reg] |= spd << (offset * SPX5_CALBITS_PER_PORT); + } + + if (used_port_bw > sparx5_target_bandwidth(sparx5)) { + dev_err(sparx5->dev, + "Port BW %u above target BW %u\n", + used_port_bw, sparx5_target_bandwidth(sparx5)); + return -EINVAL; + } + + if (total_bw > max_core_bw) { + dev_err(sparx5->dev, + "Total BW %u above switch core BW %u\n", + total_bw, max_core_bw); + return -EINVAL; + } + + /* Halt the calendar while changing it */ + spx5_rmw(QSYS_CAL_CTRL_CAL_MODE_SET(10), + QSYS_CAL_CTRL_CAL_MODE, + sparx5, QSYS_CAL_CTRL); + + /* Assign port bandwidth to auto calendar */ + for (idx = 0; idx < ARRAY_SIZE(cal); idx++) + spx5_wr(cal[idx], sparx5, QSYS_CAL_AUTO(idx)); + + /* Increase grant rate of all ports to account for + * core clock ppm deviations + */ + spx5_rmw(QSYS_CAL_CTRL_CAL_AUTO_GRANT_RATE_SET(671), /* 672->671 */ + QSYS_CAL_CTRL_CAL_AUTO_GRANT_RATE, + sparx5, + QSYS_CAL_CTRL); + + /* Grant idle usage to VD 0-2 */ + for (idx = 2; idx < 5; idx++) + spx5_wr(HSCH_OUTB_SHARE_ENA_OUTB_SHARE_ENA_SET(12), + sparx5, + HSCH_OUTB_SHARE_ENA(idx)); + + /* Enable Auto mode */ + spx5_rmw(QSYS_CAL_CTRL_CAL_MODE_SET(8), + QSYS_CAL_CTRL_CAL_MODE, + sparx5, QSYS_CAL_CTRL); + + /* Verify successful calendar config */ + value = spx5_rd(sparx5, QSYS_CAL_CTRL); + if (QSYS_CAL_CTRL_CAL_AUTO_ERROR_GET(value)) { + dev_err(sparx5->dev, "QSYS calendar error\n"); + err = -EINVAL; + } + return err; +} + +static u32 sparx5_dsm_exb_gcd(u32 a, u32 b) +{ + if (b == 0) + return a; + return sparx5_dsm_exb_gcd(b, a % b); +} + +static u32 sparx5_dsm_cal_len(u32 *cal) +{ + u32 idx = 0, len = 0; + + while (idx < SPX5_DSM_CAL_LEN) { + if (cal[idx] != SPX5_DSM_CAL_EMPTY) + len++; + idx++; + } + return len; +} + +static u32 sparx5_dsm_cp_cal(u32 *sched) +{ + u32 idx = 0, tmp; + + while (idx < SPX5_DSM_CAL_LEN) { + if (sched[idx] != SPX5_DSM_CAL_EMPTY) { + tmp = sched[idx]; + sched[idx] = SPX5_DSM_CAL_EMPTY; + return tmp; + } + idx++; + } + return SPX5_DSM_CAL_EMPTY; +} + +static int sparx5_dsm_calendar_calc(struct sparx5 *sparx5, u32 taxi, + struct sparx5_calendar_data *data) +{ + bool slow_mode; + u32 gcd, idx, sum, min, factor; + u32 num_of_slots, slot_spd, empty_slots; + u32 taxi_bw, clk_period_ps; + + clk_period_ps = sparx5_clk_period(sparx5->coreclock); + taxi_bw = 128 * 1000000 / clk_period_ps; + slow_mode = !!(clk_period_ps > 2000); + memcpy(data->taxi_ports, &sparx5_taxi_ports[taxi], + sizeof(data->taxi_ports)); + + for (idx = 0; idx < SPX5_DSM_CAL_LEN; idx++) { + data->new_slots[idx] = SPX5_DSM_CAL_EMPTY; + data->schedule[idx] = SPX5_DSM_CAL_EMPTY; + data->temp_sched[idx] = SPX5_DSM_CAL_EMPTY; + } + /* Default empty calendar */ + data->schedule[0] = SPX5_DSM_CAL_MAX_DEVS_PER_TAXI; + + /* Map ports to taxi positions */ + for (idx = 0; idx < SPX5_DSM_CAL_MAX_DEVS_PER_TAXI; idx++) { + u32 portno = data->taxi_ports[idx]; + + if (portno < SPX5_TAXI_PORT_MAX) { + data->taxi_speeds[idx] = sparx5_cal_speed_to_value + (sparx5_get_port_cal_speed(sparx5, portno)); + } else { + data->taxi_speeds[idx] = 0; + } + } + + sum = 0; + min = 25000; + for (idx = 0; idx < ARRAY_SIZE(data->taxi_speeds); idx++) { + u32 jdx; + + sum += data->taxi_speeds[idx]; + if (data->taxi_speeds[idx] && data->taxi_speeds[idx] < min) + min = data->taxi_speeds[idx]; + gcd = min; + for (jdx = 0; jdx < ARRAY_SIZE(data->taxi_speeds); jdx++) + gcd = sparx5_dsm_exb_gcd(gcd, data->taxi_speeds[jdx]); + } + if (sum == 0) /* Empty calendar */ + return 0; + /* Make room for overhead traffic */ + factor = 100 * 100 * 1000 / (100 * 100 - SPX5_DSM_CAL_BW_LOSS); + + if (sum * factor > (taxi_bw * 1000)) { + dev_err(sparx5->dev, + "Taxi %u, Requested BW %u above available BW %u\n", + taxi, sum, taxi_bw); + return -EINVAL; + } + for (idx = 0; idx < 4; idx++) { + u32 raw_spd; + + if (idx == 0) + raw_spd = gcd / 5; + else if (idx == 1) + raw_spd = gcd / 2; + else if (idx == 2) + raw_spd = gcd; + else + raw_spd = min; + slot_spd = raw_spd * factor / 1000; + num_of_slots = taxi_bw / slot_spd; + if (num_of_slots <= 64) + break; + } + + num_of_slots = num_of_slots > 64 ? 64 : num_of_slots; + slot_spd = taxi_bw / num_of_slots; + + sum = 0; + for (idx = 0; idx < ARRAY_SIZE(data->taxi_speeds); idx++) { + u32 spd = data->taxi_speeds[idx]; + u32 adjusted_speed = data->taxi_speeds[idx] * factor / 1000; + + if (adjusted_speed > 0) { + data->avg_dist[idx] = (128 * 1000000 * 10) / + (adjusted_speed * clk_period_ps); + } else { + data->avg_dist[idx] = -1; + } + data->dev_slots[idx] = ((spd * factor / slot_spd) + 999) / 1000; + if (spd != 25000 && (spd != 10000 || !slow_mode)) { + if (num_of_slots < (5 * data->dev_slots[idx])) { + dev_err(sparx5->dev, + "Taxi %u, speed %u, Low slot sep.\n", + taxi, spd); + return -EINVAL; + } + } + sum += data->dev_slots[idx]; + if (sum > num_of_slots) { + dev_err(sparx5->dev, + "Taxi %u with overhead factor %u\n", + taxi, factor); + return -EINVAL; + } + } + + empty_slots = num_of_slots - sum; + + for (idx = 0; idx < empty_slots; idx++) + data->schedule[idx] = SPX5_DSM_CAL_MAX_DEVS_PER_TAXI; + + for (idx = 1; idx < num_of_slots; idx++) { + u32 indices_len = 0; + u32 slot, jdx, kdx, ts; + s32 cnt; + u32 num_of_old_slots, num_of_new_slots, tgt_score; + + for (slot = 0; slot < ARRAY_SIZE(data->dev_slots); slot++) { + if (data->dev_slots[slot] == idx) { + data->indices[indices_len] = slot; + indices_len++; + } + } + if (indices_len == 0) + continue; + kdx = 0; + for (slot = 0; slot < idx; slot++) { + for (jdx = 0; jdx < indices_len; jdx++, kdx++) + data->new_slots[kdx] = data->indices[jdx]; + } + + for (slot = 0; slot < SPX5_DSM_CAL_LEN; slot++) { + if (data->schedule[slot] == SPX5_DSM_CAL_EMPTY) + break; + } + + num_of_old_slots = slot; + num_of_new_slots = kdx; + cnt = 0; + ts = 0; + + if (num_of_new_slots > num_of_old_slots) { + memcpy(data->short_list, data->schedule, + sizeof(data->short_list)); + memcpy(data->long_list, data->new_slots, + sizeof(data->long_list)); + tgt_score = 100000 * num_of_old_slots / + num_of_new_slots; + } else { + memcpy(data->short_list, data->new_slots, + sizeof(data->short_list)); + memcpy(data->long_list, data->schedule, + sizeof(data->long_list)); + tgt_score = 100000 * num_of_new_slots / + num_of_old_slots; + } + + while (sparx5_dsm_cal_len(data->short_list) > 0 || + sparx5_dsm_cal_len(data->long_list) > 0) { + u32 act = 0; + + if (sparx5_dsm_cal_len(data->short_list) > 0) { + data->temp_sched[ts] = + sparx5_dsm_cp_cal(data->short_list); + ts++; + cnt += 100000; + act = 1; + } + while (sparx5_dsm_cal_len(data->long_list) > 0 && + cnt > 0) { + data->temp_sched[ts] = + sparx5_dsm_cp_cal(data->long_list); + ts++; + cnt -= tgt_score; + act = 1; + } + if (act == 0) { + dev_err(sparx5->dev, + "Error in DSM calendar calculation\n"); + return -EINVAL; + } + } + + for (slot = 0; slot < SPX5_DSM_CAL_LEN; slot++) { + if (data->temp_sched[slot] == SPX5_DSM_CAL_EMPTY) + break; + } + for (slot = 0; slot < SPX5_DSM_CAL_LEN; slot++) { + data->schedule[slot] = data->temp_sched[slot]; + data->temp_sched[slot] = SPX5_DSM_CAL_EMPTY; + data->new_slots[slot] = SPX5_DSM_CAL_EMPTY; + } + } + return 0; +} + +static int sparx5_dsm_calendar_check(struct sparx5 *sparx5, + struct sparx5_calendar_data *data) +{ + u32 num_of_slots, idx, port; + int cnt, max_dist; + u32 slot_indices[SPX5_DSM_CAL_LEN], distances[SPX5_DSM_CAL_LEN]; + u32 cal_length = sparx5_dsm_cal_len(data->schedule); + + for (port = 0; port < SPX5_DSM_CAL_MAX_DEVS_PER_TAXI; port++) { + num_of_slots = 0; + max_dist = data->avg_dist[port]; + for (idx = 0; idx < SPX5_DSM_CAL_LEN; idx++) { + slot_indices[idx] = SPX5_DSM_CAL_EMPTY; + distances[idx] = SPX5_DSM_CAL_EMPTY; + } + + for (idx = 0; idx < cal_length; idx++) { + if (data->schedule[idx] == port) { + slot_indices[num_of_slots] = idx; + num_of_slots++; + } + } + + slot_indices[num_of_slots] = slot_indices[0] + cal_length; + + for (idx = 0; idx < num_of_slots; idx++) { + distances[idx] = (slot_indices[idx + 1] - + slot_indices[idx]) * 10; + } + + for (idx = 0; idx < num_of_slots; idx++) { + u32 jdx, kdx; + + cnt = distances[idx] - max_dist; + if (cnt < 0) + cnt = -cnt; + kdx = 0; + for (jdx = (idx + 1) % num_of_slots; + jdx != idx; + jdx = (jdx + 1) % num_of_slots, kdx++) { + cnt = cnt + distances[jdx] - max_dist; + if (cnt < 0) + cnt = -cnt; + if (cnt > max_dist) + goto check_err; + } + } + } + return 0; +check_err: + dev_err(sparx5->dev, + "Port %u: distance %u above limit %d\n", + port, cnt, max_dist); + return -EINVAL; +} + +static int sparx5_dsm_calendar_update(struct sparx5 *sparx5, u32 taxi, + struct sparx5_calendar_data *data) +{ + u32 idx; + u32 cal_len = sparx5_dsm_cal_len(data->schedule), len; + + spx5_wr(DSM_TAXI_CAL_CFG_CAL_PGM_ENA_SET(1), + sparx5, + DSM_TAXI_CAL_CFG(taxi)); + for (idx = 0; idx < cal_len; idx++) { + spx5_rmw(DSM_TAXI_CAL_CFG_CAL_IDX_SET(idx), + DSM_TAXI_CAL_CFG_CAL_IDX, + sparx5, + DSM_TAXI_CAL_CFG(taxi)); + spx5_rmw(DSM_TAXI_CAL_CFG_CAL_PGM_VAL_SET(data->schedule[idx]), + DSM_TAXI_CAL_CFG_CAL_PGM_VAL, + sparx5, + DSM_TAXI_CAL_CFG(taxi)); + } + spx5_wr(DSM_TAXI_CAL_CFG_CAL_PGM_ENA_SET(0), + sparx5, + DSM_TAXI_CAL_CFG(taxi)); + len = DSM_TAXI_CAL_CFG_CAL_CUR_LEN_GET(spx5_rd(sparx5, + DSM_TAXI_CAL_CFG(taxi))); + if (len != cal_len - 1) + goto update_err; + return 0; +update_err: + dev_err(sparx5->dev, "Incorrect calendar length: %u\n", len); + return -EINVAL; +} + +/* Configure the DSM calendar based on port configuration */ +int sparx5_config_dsm_calendar(struct sparx5 *sparx5) +{ + int taxi; + struct sparx5_calendar_data *data; + int err = 0; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + for (taxi = 0; taxi < SPX5_DSM_CAL_TAXIS; ++taxi) { + err = sparx5_dsm_calendar_calc(sparx5, taxi, data); + if (err) { + dev_err(sparx5->dev, "DSM calendar calculation failed\n"); + goto cal_out; + } + err = sparx5_dsm_calendar_check(sparx5, data); + if (err) { + dev_err(sparx5->dev, "DSM calendar check failed\n"); + goto cal_out; + } + err = sparx5_dsm_calendar_update(sparx5, taxi, data); + if (err) { + dev_err(sparx5->dev, "DSM calendar update failed\n"); + goto cal_out; + } + } +cal_out: + kfree(data); + return err; +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c new file mode 100644 index 000000000000..59783fc46a7b --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c @@ -0,0 +1,1227 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries. + */ + +#include + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" +#include "sparx5_port.h" + +/* Index of ANA_AC port counters */ +#define SPX5_PORT_POLICER_DROPS 0 + +/* Add a potentially wrapping 32 bit value to a 64 bit counter */ +static void sparx5_update_counter(u64 *cnt, u32 val) +{ + if (val < (*cnt & U32_MAX)) + *cnt += (u64)1 << 32; /* value has wrapped */ + *cnt = (*cnt & ~(u64)U32_MAX) + val; +} + +enum sparx5_stats_entry { + spx5_stats_rx_symbol_err_cnt = 0, + spx5_stats_pmac_rx_symbol_err_cnt = 1, + spx5_stats_tx_uc_cnt = 2, + spx5_stats_pmac_tx_uc_cnt = 3, + spx5_stats_tx_mc_cnt = 4, + spx5_stats_tx_bc_cnt = 5, + spx5_stats_tx_backoff1_cnt = 6, + spx5_stats_tx_multi_coll_cnt = 7, + spx5_stats_rx_uc_cnt = 8, + spx5_stats_pmac_rx_uc_cnt = 9, + spx5_stats_rx_mc_cnt = 10, + spx5_stats_rx_bc_cnt = 11, + spx5_stats_rx_crc_err_cnt = 12, + spx5_stats_pmac_rx_crc_err_cnt = 13, + spx5_stats_rx_alignment_lost_cnt = 14, + spx5_stats_pmac_rx_alignment_lost_cnt = 15, + spx5_stats_tx_ok_bytes_cnt = 16, + spx5_stats_pmac_tx_ok_bytes_cnt = 17, + spx5_stats_tx_defer_cnt = 18, + spx5_stats_tx_late_coll_cnt = 19, + spx5_stats_tx_xcoll_cnt = 20, + spx5_stats_tx_csense_cnt = 21, + spx5_stats_rx_ok_bytes_cnt = 22, + spx5_stats_pmac_rx_ok_bytes_cnt = 23, + spx5_stats_pmac_tx_mc_cnt = 24, + spx5_stats_pmac_tx_bc_cnt = 25, + spx5_stats_tx_xdefer_cnt = 26, + spx5_stats_pmac_rx_mc_cnt = 27, + spx5_stats_pmac_rx_bc_cnt = 28, + spx5_stats_rx_in_range_len_err_cnt = 29, + spx5_stats_pmac_rx_in_range_len_err_cnt = 30, + spx5_stats_rx_out_of_range_len_err_cnt = 31, + spx5_stats_pmac_rx_out_of_range_len_err_cnt = 32, + spx5_stats_rx_oversize_cnt = 33, + spx5_stats_pmac_rx_oversize_cnt = 34, + spx5_stats_tx_pause_cnt = 35, + spx5_stats_pmac_tx_pause_cnt = 36, + spx5_stats_rx_pause_cnt = 37, + spx5_stats_pmac_rx_pause_cnt = 38, + spx5_stats_rx_unsup_opcode_cnt = 39, + spx5_stats_pmac_rx_unsup_opcode_cnt = 40, + spx5_stats_rx_undersize_cnt = 41, + spx5_stats_pmac_rx_undersize_cnt = 42, + spx5_stats_rx_fragments_cnt = 43, + spx5_stats_pmac_rx_fragments_cnt = 44, + spx5_stats_rx_jabbers_cnt = 45, + spx5_stats_pmac_rx_jabbers_cnt = 46, + spx5_stats_rx_size64_cnt = 47, + spx5_stats_pmac_rx_size64_cnt = 48, + spx5_stats_rx_size65to127_cnt = 49, + spx5_stats_pmac_rx_size65to127_cnt = 50, + spx5_stats_rx_size128to255_cnt = 51, + spx5_stats_pmac_rx_size128to255_cnt = 52, + spx5_stats_rx_size256to511_cnt = 53, + spx5_stats_pmac_rx_size256to511_cnt = 54, + spx5_stats_rx_size512to1023_cnt = 55, + spx5_stats_pmac_rx_size512to1023_cnt = 56, + spx5_stats_rx_size1024to1518_cnt = 57, + spx5_stats_pmac_rx_size1024to1518_cnt = 58, + spx5_stats_rx_size1519tomax_cnt = 59, + spx5_stats_pmac_rx_size1519tomax_cnt = 60, + spx5_stats_tx_size64_cnt = 61, + spx5_stats_pmac_tx_size64_cnt = 62, + spx5_stats_tx_size65to127_cnt = 63, + spx5_stats_pmac_tx_size65to127_cnt = 64, + spx5_stats_tx_size128to255_cnt = 65, + spx5_stats_pmac_tx_size128to255_cnt = 66, + spx5_stats_tx_size256to511_cnt = 67, + spx5_stats_pmac_tx_size256to511_cnt = 68, + spx5_stats_tx_size512to1023_cnt = 69, + spx5_stats_pmac_tx_size512to1023_cnt = 70, + spx5_stats_tx_size1024to1518_cnt = 71, + spx5_stats_pmac_tx_size1024to1518_cnt = 72, + spx5_stats_tx_size1519tomax_cnt = 73, + spx5_stats_pmac_tx_size1519tomax_cnt = 74, + spx5_stats_mm_rx_assembly_err_cnt = 75, + spx5_stats_mm_rx_assembly_ok_cnt = 76, + spx5_stats_mm_rx_merge_frag_cnt = 77, + spx5_stats_mm_rx_smd_err_cnt = 78, + spx5_stats_mm_tx_pfragment_cnt = 79, + spx5_stats_rx_bad_bytes_cnt = 80, + spx5_stats_pmac_rx_bad_bytes_cnt = 81, + spx5_stats_rx_in_bytes_cnt = 82, + spx5_stats_rx_ipg_shrink_cnt = 83, + spx5_stats_rx_sync_lost_err_cnt = 84, + spx5_stats_rx_tagged_frms_cnt = 85, + spx5_stats_rx_untagged_frms_cnt = 86, + spx5_stats_tx_out_bytes_cnt = 87, + spx5_stats_tx_tagged_frms_cnt = 88, + spx5_stats_tx_untagged_frms_cnt = 89, + spx5_stats_rx_hih_cksm_err_cnt = 90, + spx5_stats_pmac_rx_hih_cksm_err_cnt = 91, + spx5_stats_rx_xgmii_prot_err_cnt = 92, + spx5_stats_pmac_rx_xgmii_prot_err_cnt = 93, + spx5_stats_ana_ac_port_stat_lsb_cnt = 94, + spx5_stats_green_p0_rx_fwd = 95, + spx5_stats_green_p0_rx_port_drop = 111, + spx5_stats_green_p0_tx_port = 127, + spx5_stats_rx_local_drop = 143, + spx5_stats_tx_local_drop = 144, + spx5_stats_count = 145, +}; + +static const char *const sparx5_stats_layout[] = { + "mm_rx_assembly_err_cnt", + "mm_rx_assembly_ok_cnt", + "mm_rx_merge_frag_cnt", + "mm_rx_smd_err_cnt", + "mm_tx_pfragment_cnt", + "rx_bad_bytes_cnt", + "pmac_rx_bad_bytes_cnt", + "rx_in_bytes_cnt", + "rx_ipg_shrink_cnt", + "rx_sync_lost_err_cnt", + "rx_tagged_frms_cnt", + "rx_untagged_frms_cnt", + "tx_out_bytes_cnt", + "tx_tagged_frms_cnt", + "tx_untagged_frms_cnt", + "rx_hih_cksm_err_cnt", + "pmac_rx_hih_cksm_err_cnt", + "rx_xgmii_prot_err_cnt", + "pmac_rx_xgmii_prot_err_cnt", + "rx_port_policer_drop", + "rx_fwd_green_p0", + "rx_fwd_green_p1", + "rx_fwd_green_p2", + "rx_fwd_green_p3", + "rx_fwd_green_p4", + "rx_fwd_green_p5", + "rx_fwd_green_p6", + "rx_fwd_green_p7", + "rx_fwd_yellow_p0", + "rx_fwd_yellow_p1", + "rx_fwd_yellow_p2", + "rx_fwd_yellow_p3", + "rx_fwd_yellow_p4", + "rx_fwd_yellow_p5", + "rx_fwd_yellow_p6", + "rx_fwd_yellow_p7", + "rx_port_drop_green_p0", + "rx_port_drop_green_p1", + "rx_port_drop_green_p2", + "rx_port_drop_green_p3", + "rx_port_drop_green_p4", + "rx_port_drop_green_p5", + "rx_port_drop_green_p6", + "rx_port_drop_green_p7", + "rx_port_drop_yellow_p0", + "rx_port_drop_yellow_p1", + "rx_port_drop_yellow_p2", + "rx_port_drop_yellow_p3", + "rx_port_drop_yellow_p4", + "rx_port_drop_yellow_p5", + "rx_port_drop_yellow_p6", + "rx_port_drop_yellow_p7", + "tx_port_green_p0", + "tx_port_green_p1", + "tx_port_green_p2", + "tx_port_green_p3", + "tx_port_green_p4", + "tx_port_green_p5", + "tx_port_green_p6", + "tx_port_green_p7", + "tx_port_yellow_p0", + "tx_port_yellow_p1", + "tx_port_yellow_p2", + "tx_port_yellow_p3", + "tx_port_yellow_p4", + "tx_port_yellow_p5", + "tx_port_yellow_p6", + "tx_port_yellow_p7", + "rx_local_drop", + "tx_local_drop", +}; + +static void sparx5_get_queue_sys_stats(struct sparx5 *sparx5, int portno) +{ + u64 *portstats; + u64 *stats; + u32 addr; + int idx; + + portstats = &sparx5->stats[portno * sparx5->num_stats]; + mutex_lock(&sparx5->queue_stats_lock); + spx5_wr(XQS_STAT_CFG_STAT_VIEW_SET(portno), sparx5, XQS_STAT_CFG); + addr = 0; + stats = &portstats[spx5_stats_green_p0_rx_fwd]; + for (idx = 0; idx < 2 * SPX5_PRIOS; ++idx, ++addr, ++stats) + sparx5_update_counter(stats, spx5_rd(sparx5, XQS_CNT(addr))); + addr = 16; + stats = &portstats[spx5_stats_green_p0_rx_port_drop]; + for (idx = 0; idx < 2 * SPX5_PRIOS; ++idx, ++addr, ++stats) + sparx5_update_counter(stats, spx5_rd(sparx5, XQS_CNT(addr))); + addr = 256; + stats = &portstats[spx5_stats_green_p0_tx_port]; + for (idx = 0; idx < 2 * SPX5_PRIOS; ++idx, ++addr, ++stats) + sparx5_update_counter(stats, spx5_rd(sparx5, XQS_CNT(addr))); + sparx5_update_counter(&portstats[spx5_stats_rx_local_drop], + spx5_rd(sparx5, XQS_CNT(32))); + sparx5_update_counter(&portstats[spx5_stats_tx_local_drop], + spx5_rd(sparx5, XQS_CNT(272))); + mutex_unlock(&sparx5->queue_stats_lock); +} + +static void sparx5_get_ana_ac_stats_stats(struct sparx5 *sparx5, int portno) +{ + u64 *portstats = &sparx5->stats[portno * sparx5->num_stats]; + + sparx5_update_counter(&portstats[spx5_stats_ana_ac_port_stat_lsb_cnt], + spx5_rd(sparx5, ANA_AC_PORT_STAT_LSB_CNT(portno, + SPX5_PORT_POLICER_DROPS))); +} + +static void sparx5_get_dev_phy_stats(u64 *portstats, void __iomem *inst, u32 + tinst) +{ + sparx5_update_counter(&portstats[spx5_stats_rx_symbol_err_cnt], + spx5_inst_rd(inst, + DEV5G_RX_SYMBOL_ERR_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_symbol_err_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_SYMBOL_ERR_CNT(tinst))); +} + +static void sparx5_get_dev_mac_stats(u64 *portstats, void __iomem *inst, u32 + tinst) +{ + sparx5_update_counter(&portstats[spx5_stats_tx_uc_cnt], + spx5_inst_rd(inst, DEV5G_TX_UC_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_uc_cnt], + spx5_inst_rd(inst, DEV5G_PMAC_TX_UC_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_mc_cnt], + spx5_inst_rd(inst, DEV5G_TX_MC_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_bc_cnt], + spx5_inst_rd(inst, DEV5G_TX_BC_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_uc_cnt], + spx5_inst_rd(inst, DEV5G_RX_UC_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_uc_cnt], + spx5_inst_rd(inst, DEV5G_PMAC_RX_UC_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_mc_cnt], + spx5_inst_rd(inst, DEV5G_RX_MC_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_bc_cnt], + spx5_inst_rd(inst, DEV5G_RX_BC_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_crc_err_cnt], + spx5_inst_rd(inst, DEV5G_RX_CRC_ERR_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_crc_err_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_CRC_ERR_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_alignment_lost_cnt], + spx5_inst_rd(inst, + DEV5G_RX_ALIGNMENT_LOST_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_alignment_lost_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_ALIGNMENT_LOST_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_ok_bytes_cnt], + spx5_inst_rd(inst, DEV5G_TX_OK_BYTES_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_ok_bytes_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_TX_OK_BYTES_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_ok_bytes_cnt], + spx5_inst_rd(inst, DEV5G_RX_OK_BYTES_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_ok_bytes_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_OK_BYTES_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_mc_cnt], + spx5_inst_rd(inst, DEV5G_PMAC_TX_MC_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_bc_cnt], + spx5_inst_rd(inst, DEV5G_PMAC_TX_BC_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_mc_cnt], + spx5_inst_rd(inst, DEV5G_PMAC_RX_MC_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_bc_cnt], + spx5_inst_rd(inst, DEV5G_PMAC_RX_BC_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_in_range_len_err_cnt], + spx5_inst_rd(inst, + DEV5G_RX_IN_RANGE_LEN_ERR_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_in_range_len_err_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_IN_RANGE_LEN_ERR_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_out_of_range_len_err_cnt], + spx5_inst_rd(inst, + DEV5G_RX_OUT_OF_RANGE_LEN_ERR_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_out_of_range_len_err_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_OUT_OF_RANGE_LEN_ERR_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_oversize_cnt], + spx5_inst_rd(inst, DEV5G_RX_OVERSIZE_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_oversize_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_OVERSIZE_CNT(tinst))); +} + +static void sparx5_get_dev_mac_ctrl_stats(u64 *portstats, void __iomem *inst, + u32 tinst) +{ + sparx5_update_counter(&portstats[spx5_stats_tx_pause_cnt], + spx5_inst_rd(inst, DEV5G_TX_PAUSE_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_pause_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_TX_PAUSE_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_pause_cnt], + spx5_inst_rd(inst, DEV5G_RX_PAUSE_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_pause_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_PAUSE_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_unsup_opcode_cnt], + spx5_inst_rd(inst, + DEV5G_RX_UNSUP_OPCODE_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_unsup_opcode_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_UNSUP_OPCODE_CNT(tinst))); +} + +static void sparx5_get_dev_rmon_stats(u64 *portstats, void __iomem *inst, u32 + tinst) +{ + sparx5_update_counter(&portstats[spx5_stats_rx_undersize_cnt], + spx5_inst_rd(inst, + DEV5G_RX_UNDERSIZE_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_undersize_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_UNDERSIZE_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_oversize_cnt], + spx5_inst_rd(inst, DEV5G_RX_OVERSIZE_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_oversize_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_OVERSIZE_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_fragments_cnt], + spx5_inst_rd(inst, + DEV5G_RX_FRAGMENTS_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_fragments_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_FRAGMENTS_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_jabbers_cnt], + spx5_inst_rd(inst, DEV5G_RX_JABBERS_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_jabbers_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_JABBERS_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_size64_cnt], + spx5_inst_rd(inst, DEV5G_RX_SIZE64_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size64_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_SIZE64_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_size65to127_cnt], + spx5_inst_rd(inst, + DEV5G_RX_SIZE65TO127_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size65to127_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_SIZE65TO127_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_size128to255_cnt], + spx5_inst_rd(inst, + DEV5G_RX_SIZE128TO255_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size128to255_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_SIZE128TO255_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_size256to511_cnt], + spx5_inst_rd(inst, + DEV5G_RX_SIZE256TO511_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size256to511_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_SIZE256TO511_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_size512to1023_cnt], + spx5_inst_rd(inst, + DEV5G_RX_SIZE512TO1023_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size512to1023_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_SIZE512TO1023_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_size1024to1518_cnt], + spx5_inst_rd(inst, + DEV5G_RX_SIZE1024TO1518_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size1024to1518_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_SIZE1024TO1518_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_size1519tomax_cnt], + spx5_inst_rd(inst, + DEV5G_RX_SIZE1519TOMAX_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size1519tomax_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_SIZE1519TOMAX_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_size64_cnt], + spx5_inst_rd(inst, DEV5G_TX_SIZE64_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size64_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_TX_SIZE64_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_size65to127_cnt], + spx5_inst_rd(inst, + DEV5G_TX_SIZE65TO127_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size65to127_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_TX_SIZE65TO127_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_size128to255_cnt], + spx5_inst_rd(inst, + DEV5G_TX_SIZE128TO255_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size128to255_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_TX_SIZE128TO255_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_size256to511_cnt], + spx5_inst_rd(inst, + DEV5G_TX_SIZE256TO511_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size256to511_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_TX_SIZE256TO511_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_size512to1023_cnt], + spx5_inst_rd(inst, + DEV5G_TX_SIZE512TO1023_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size512to1023_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_TX_SIZE512TO1023_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_size1024to1518_cnt], + spx5_inst_rd(inst, + DEV5G_TX_SIZE1024TO1518_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size1024to1518_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_TX_SIZE1024TO1518_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_size1519tomax_cnt], + spx5_inst_rd(inst, + DEV5G_TX_SIZE1519TOMAX_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size1519tomax_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_TX_SIZE1519TOMAX_CNT(tinst))); +} + +static void sparx5_get_dev_misc_stats(u64 *portstats, void __iomem *inst, u32 + tinst) +{ + sparx5_update_counter(&portstats[spx5_stats_mm_rx_assembly_err_cnt], + spx5_inst_rd(inst, + DEV5G_MM_RX_ASSEMBLY_ERR_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_mm_rx_assembly_ok_cnt], + spx5_inst_rd(inst, + DEV5G_MM_RX_ASSEMBLY_OK_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_mm_rx_merge_frag_cnt], + spx5_inst_rd(inst, + DEV5G_MM_RX_MERGE_FRAG_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_mm_rx_smd_err_cnt], + spx5_inst_rd(inst, + DEV5G_MM_RX_SMD_ERR_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_mm_tx_pfragment_cnt], + spx5_inst_rd(inst, + DEV5G_MM_TX_PFRAGMENT_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_bad_bytes_cnt], + spx5_inst_rd(inst, + DEV5G_RX_BAD_BYTES_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_bad_bytes_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_BAD_BYTES_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_in_bytes_cnt], + spx5_inst_rd(inst, DEV5G_RX_IN_BYTES_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_ipg_shrink_cnt], + spx5_inst_rd(inst, + DEV5G_RX_IPG_SHRINK_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_tagged_frms_cnt], + spx5_inst_rd(inst, + DEV5G_RX_TAGGED_FRMS_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_untagged_frms_cnt], + spx5_inst_rd(inst, + DEV5G_RX_UNTAGGED_FRMS_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_out_bytes_cnt], + spx5_inst_rd(inst, + DEV5G_TX_OUT_BYTES_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_tagged_frms_cnt], + spx5_inst_rd(inst, + DEV5G_TX_TAGGED_FRMS_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_tx_untagged_frms_cnt], + spx5_inst_rd(inst, + DEV5G_TX_UNTAGGED_FRMS_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_hih_cksm_err_cnt], + spx5_inst_rd(inst, + DEV5G_RX_HIH_CKSM_ERR_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_hih_cksm_err_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_HIH_CKSM_ERR_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_rx_xgmii_prot_err_cnt], + spx5_inst_rd(inst, + DEV5G_RX_XGMII_PROT_ERR_CNT(tinst))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_xgmii_prot_err_cnt], + spx5_inst_rd(inst, + DEV5G_PMAC_RX_XGMII_PROT_ERR_CNT(tinst))); +} + +static void sparx5_get_device_stats(struct sparx5 *sparx5, int portno) +{ + u64 *portstats = &sparx5->stats[portno * sparx5->num_stats]; + u32 tinst = sparx5_port_dev_index(portno); + u32 dev = sparx5_to_high_dev(portno); + void __iomem *inst; + + inst = spx5_inst_get(sparx5, dev, tinst); + sparx5_get_dev_phy_stats(portstats, inst, tinst); + sparx5_get_dev_mac_stats(portstats, inst, tinst); + sparx5_get_dev_mac_ctrl_stats(portstats, inst, tinst); + sparx5_get_dev_rmon_stats(portstats, inst, tinst); + sparx5_get_dev_misc_stats(portstats, inst, tinst); +} + +static void sparx5_get_asm_phy_stats(u64 *portstats, void __iomem *inst, int + portno) +{ + sparx5_update_counter(&portstats[spx5_stats_rx_symbol_err_cnt], + spx5_inst_rd(inst, + ASM_RX_SYMBOL_ERR_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_symbol_err_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_SYMBOL_ERR_CNT(portno))); +} + +static void sparx5_get_asm_mac_stats(u64 *portstats, void __iomem *inst, int + portno) +{ + sparx5_update_counter(&portstats[spx5_stats_tx_uc_cnt], + spx5_inst_rd(inst, ASM_TX_UC_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_uc_cnt], + spx5_inst_rd(inst, ASM_PMAC_TX_UC_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_mc_cnt], + spx5_inst_rd(inst, ASM_TX_MC_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_bc_cnt], + spx5_inst_rd(inst, ASM_TX_BC_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_backoff1_cnt], + spx5_inst_rd(inst, ASM_TX_BACKOFF1_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_multi_coll_cnt], + spx5_inst_rd(inst, + ASM_TX_MULTI_COLL_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_uc_cnt], + spx5_inst_rd(inst, ASM_RX_UC_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_uc_cnt], + spx5_inst_rd(inst, ASM_PMAC_RX_UC_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_mc_cnt], + spx5_inst_rd(inst, ASM_RX_MC_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_bc_cnt], + spx5_inst_rd(inst, ASM_RX_BC_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_crc_err_cnt], + spx5_inst_rd(inst, ASM_RX_CRC_ERR_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_crc_err_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_CRC_ERR_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_alignment_lost_cnt], + spx5_inst_rd(inst, + ASM_RX_ALIGNMENT_LOST_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_alignment_lost_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_ALIGNMENT_LOST_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_ok_bytes_cnt], + spx5_inst_rd(inst, ASM_TX_OK_BYTES_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_ok_bytes_cnt], + spx5_inst_rd(inst, + ASM_PMAC_TX_OK_BYTES_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_defer_cnt], + spx5_inst_rd(inst, ASM_TX_DEFER_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_late_coll_cnt], + spx5_inst_rd(inst, ASM_TX_LATE_COLL_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_xcoll_cnt], + spx5_inst_rd(inst, ASM_TX_XCOLL_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_csense_cnt], + spx5_inst_rd(inst, ASM_TX_CSENSE_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_ok_bytes_cnt], + spx5_inst_rd(inst, ASM_RX_OK_BYTES_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_ok_bytes_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_OK_BYTES_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_mc_cnt], + spx5_inst_rd(inst, ASM_PMAC_TX_MC_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_bc_cnt], + spx5_inst_rd(inst, ASM_PMAC_TX_BC_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_xdefer_cnt], + spx5_inst_rd(inst, ASM_TX_XDEFER_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_mc_cnt], + spx5_inst_rd(inst, ASM_PMAC_RX_MC_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_bc_cnt], + spx5_inst_rd(inst, ASM_PMAC_RX_BC_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_in_range_len_err_cnt], + spx5_inst_rd(inst, + ASM_RX_IN_RANGE_LEN_ERR_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_in_range_len_err_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_IN_RANGE_LEN_ERR_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_out_of_range_len_err_cnt], + spx5_inst_rd(inst, + ASM_RX_OUT_OF_RANGE_LEN_ERR_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_out_of_range_len_err_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_OUT_OF_RANGE_LEN_ERR_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_oversize_cnt], + spx5_inst_rd(inst, ASM_RX_OVERSIZE_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_oversize_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_OVERSIZE_CNT(portno))); +} + +static void sparx5_get_asm_mac_ctrl_stats(u64 *portstats, void __iomem *inst, + int portno) +{ + sparx5_update_counter(&portstats[spx5_stats_tx_pause_cnt], + spx5_inst_rd(inst, ASM_TX_PAUSE_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_pause_cnt], + spx5_inst_rd(inst, + ASM_PMAC_TX_PAUSE_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_pause_cnt], + spx5_inst_rd(inst, ASM_RX_PAUSE_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_pause_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_PAUSE_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_unsup_opcode_cnt], + spx5_inst_rd(inst, + ASM_RX_UNSUP_OPCODE_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_unsup_opcode_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_UNSUP_OPCODE_CNT(portno))); +} + +static void sparx5_get_asm_rmon_stats(u64 *portstats, void __iomem *inst, int + portno) +{ + sparx5_update_counter(&portstats[spx5_stats_rx_undersize_cnt], + spx5_inst_rd(inst, ASM_RX_UNDERSIZE_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_undersize_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_UNDERSIZE_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_oversize_cnt], + spx5_inst_rd(inst, ASM_RX_OVERSIZE_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_oversize_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_OVERSIZE_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_fragments_cnt], + spx5_inst_rd(inst, ASM_RX_FRAGMENTS_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_fragments_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_FRAGMENTS_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_jabbers_cnt], + spx5_inst_rd(inst, ASM_RX_JABBERS_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_jabbers_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_JABBERS_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_size64_cnt], + spx5_inst_rd(inst, ASM_RX_SIZE64_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size64_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_SIZE64_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_size65to127_cnt], + spx5_inst_rd(inst, + ASM_RX_SIZE65TO127_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size65to127_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_SIZE65TO127_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_size128to255_cnt], + spx5_inst_rd(inst, + ASM_RX_SIZE128TO255_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size128to255_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_SIZE128TO255_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_size256to511_cnt], + spx5_inst_rd(inst, + ASM_RX_SIZE256TO511_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size256to511_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_SIZE256TO511_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_size512to1023_cnt], + spx5_inst_rd(inst, + ASM_RX_SIZE512TO1023_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size512to1023_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_SIZE512TO1023_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_size1024to1518_cnt], + spx5_inst_rd(inst, + ASM_RX_SIZE1024TO1518_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size1024to1518_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_SIZE1024TO1518_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_size1519tomax_cnt], + spx5_inst_rd(inst, + ASM_RX_SIZE1519TOMAX_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_size1519tomax_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_SIZE1519TOMAX_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_size64_cnt], + spx5_inst_rd(inst, ASM_TX_SIZE64_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size64_cnt], + spx5_inst_rd(inst, + ASM_PMAC_TX_SIZE64_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_size65to127_cnt], + spx5_inst_rd(inst, + ASM_TX_SIZE65TO127_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size65to127_cnt], + spx5_inst_rd(inst, + ASM_PMAC_TX_SIZE65TO127_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_size128to255_cnt], + spx5_inst_rd(inst, + ASM_TX_SIZE128TO255_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size128to255_cnt], + spx5_inst_rd(inst, + ASM_PMAC_TX_SIZE128TO255_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_size256to511_cnt], + spx5_inst_rd(inst, + ASM_TX_SIZE256TO511_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size256to511_cnt], + spx5_inst_rd(inst, + ASM_PMAC_TX_SIZE256TO511_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_size512to1023_cnt], + spx5_inst_rd(inst, + ASM_TX_SIZE512TO1023_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size512to1023_cnt], + spx5_inst_rd(inst, + ASM_PMAC_TX_SIZE512TO1023_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_size1024to1518_cnt], + spx5_inst_rd(inst, + ASM_TX_SIZE1024TO1518_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size1024to1518_cnt], + spx5_inst_rd(inst, + ASM_PMAC_TX_SIZE1024TO1518_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_size1519tomax_cnt], + spx5_inst_rd(inst, + ASM_TX_SIZE1519TOMAX_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_tx_size1519tomax_cnt], + spx5_inst_rd(inst, + ASM_PMAC_TX_SIZE1519TOMAX_CNT(portno))); +} + +static void sparx5_get_asm_misc_stats(u64 *portstats, void __iomem *inst, int + portno) +{ + sparx5_update_counter(&portstats[spx5_stats_mm_rx_assembly_err_cnt], + spx5_inst_rd(inst, + ASM_MM_RX_ASSEMBLY_ERR_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_mm_rx_assembly_ok_cnt], + spx5_inst_rd(inst, + ASM_MM_RX_ASSEMBLY_OK_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_mm_rx_merge_frag_cnt], + spx5_inst_rd(inst, + ASM_MM_RX_MERGE_FRAG_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_mm_rx_smd_err_cnt], + spx5_inst_rd(inst, + ASM_MM_RX_SMD_ERR_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_mm_tx_pfragment_cnt], + spx5_inst_rd(inst, + ASM_MM_TX_PFRAGMENT_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_bad_bytes_cnt], + spx5_inst_rd(inst, ASM_RX_BAD_BYTES_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_pmac_rx_bad_bytes_cnt], + spx5_inst_rd(inst, + ASM_PMAC_RX_BAD_BYTES_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_in_bytes_cnt], + spx5_inst_rd(inst, ASM_RX_IN_BYTES_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_ipg_shrink_cnt], + spx5_inst_rd(inst, + ASM_RX_IPG_SHRINK_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_sync_lost_err_cnt], + spx5_inst_rd(inst, + ASM_RX_SYNC_LOST_ERR_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_tagged_frms_cnt], + spx5_inst_rd(inst, + ASM_RX_TAGGED_FRMS_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_rx_untagged_frms_cnt], + spx5_inst_rd(inst, + ASM_RX_UNTAGGED_FRMS_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_out_bytes_cnt], + spx5_inst_rd(inst, ASM_TX_OUT_BYTES_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_tagged_frms_cnt], + spx5_inst_rd(inst, + ASM_TX_TAGGED_FRMS_CNT(portno))); + sparx5_update_counter(&portstats[spx5_stats_tx_untagged_frms_cnt], + spx5_inst_rd(inst, + ASM_TX_UNTAGGED_FRMS_CNT(portno))); +} + +static void sparx5_get_asm_stats(struct sparx5 *sparx5, int portno) +{ + u64 *portstats = &sparx5->stats[portno * sparx5->num_stats]; + void __iomem *inst = spx5_inst_get(sparx5, TARGET_ASM, 0); + + sparx5_get_asm_phy_stats(portstats, inst, portno); + sparx5_get_asm_mac_stats(portstats, inst, portno); + sparx5_get_asm_mac_ctrl_stats(portstats, inst, portno); + sparx5_get_asm_rmon_stats(portstats, inst, portno); + sparx5_get_asm_misc_stats(portstats, inst, portno); +} + +static const struct ethtool_rmon_hist_range sparx5_rmon_ranges[] = { + { 0, 64 }, + { 65, 127 }, + { 128, 255 }, + { 256, 511 }, + { 512, 1023 }, + { 1024, 1518 }, + { 1519, 10239 }, + {} +}; + +static void sparx5_get_eth_phy_stats(struct net_device *ndev, + struct ethtool_eth_phy_stats *phy_stats) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + int portno = port->portno; + void __iomem *inst; + u64 *portstats; + + portstats = &sparx5->stats[portno * sparx5->num_stats]; + if (sparx5_is_baser(port->conf.portmode)) { + u32 tinst = sparx5_port_dev_index(portno); + u32 dev = sparx5_to_high_dev(portno); + + inst = spx5_inst_get(sparx5, dev, tinst); + sparx5_get_dev_phy_stats(portstats, inst, tinst); + } else { + inst = spx5_inst_get(sparx5, TARGET_ASM, 0); + sparx5_get_asm_phy_stats(portstats, inst, portno); + } + phy_stats->SymbolErrorDuringCarrier = + portstats[spx5_stats_rx_symbol_err_cnt] + + portstats[spx5_stats_pmac_rx_symbol_err_cnt]; +} + +static void sparx5_get_eth_mac_stats(struct net_device *ndev, + struct ethtool_eth_mac_stats *mac_stats) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + int portno = port->portno; + void __iomem *inst; + u64 *portstats; + + portstats = &sparx5->stats[portno * sparx5->num_stats]; + if (sparx5_is_baser(port->conf.portmode)) { + u32 tinst = sparx5_port_dev_index(portno); + u32 dev = sparx5_to_high_dev(portno); + + inst = spx5_inst_get(sparx5, dev, tinst); + sparx5_get_dev_mac_stats(portstats, inst, tinst); + } else { + inst = spx5_inst_get(sparx5, TARGET_ASM, 0); + sparx5_get_asm_mac_stats(portstats, inst, portno); + } + mac_stats->FramesTransmittedOK = portstats[spx5_stats_tx_uc_cnt] + + portstats[spx5_stats_pmac_tx_uc_cnt] + + portstats[spx5_stats_tx_mc_cnt] + + portstats[spx5_stats_tx_bc_cnt]; + mac_stats->SingleCollisionFrames = + portstats[spx5_stats_tx_backoff1_cnt]; + mac_stats->MultipleCollisionFrames = + portstats[spx5_stats_tx_multi_coll_cnt]; + mac_stats->FramesReceivedOK = portstats[spx5_stats_rx_uc_cnt] + + portstats[spx5_stats_pmac_rx_uc_cnt] + + portstats[spx5_stats_rx_mc_cnt] + + portstats[spx5_stats_rx_bc_cnt]; + mac_stats->FrameCheckSequenceErrors = + portstats[spx5_stats_rx_crc_err_cnt] + + portstats[spx5_stats_pmac_rx_crc_err_cnt]; + mac_stats->AlignmentErrors = portstats[spx5_stats_rx_alignment_lost_cnt] + + portstats[spx5_stats_pmac_rx_alignment_lost_cnt]; + mac_stats->OctetsTransmittedOK = portstats[spx5_stats_tx_ok_bytes_cnt] + + portstats[spx5_stats_pmac_tx_ok_bytes_cnt]; + mac_stats->FramesWithDeferredXmissions = + portstats[spx5_stats_tx_defer_cnt]; + mac_stats->LateCollisions = + portstats[spx5_stats_tx_late_coll_cnt]; + mac_stats->FramesAbortedDueToXSColls = + portstats[spx5_stats_tx_xcoll_cnt]; + mac_stats->CarrierSenseErrors = portstats[spx5_stats_tx_csense_cnt]; + mac_stats->OctetsReceivedOK = portstats[spx5_stats_rx_ok_bytes_cnt] + + portstats[spx5_stats_pmac_rx_ok_bytes_cnt]; + mac_stats->MulticastFramesXmittedOK = portstats[spx5_stats_tx_mc_cnt] + + portstats[spx5_stats_pmac_tx_mc_cnt]; + mac_stats->BroadcastFramesXmittedOK = portstats[spx5_stats_tx_bc_cnt] + + portstats[spx5_stats_pmac_tx_bc_cnt]; + mac_stats->FramesWithExcessiveDeferral = + portstats[spx5_stats_tx_xdefer_cnt]; + mac_stats->MulticastFramesReceivedOK = portstats[spx5_stats_rx_mc_cnt] + + portstats[spx5_stats_pmac_rx_mc_cnt]; + mac_stats->BroadcastFramesReceivedOK = portstats[spx5_stats_rx_bc_cnt] + + portstats[spx5_stats_pmac_rx_bc_cnt]; + mac_stats->InRangeLengthErrors = + portstats[spx5_stats_rx_in_range_len_err_cnt] + + portstats[spx5_stats_pmac_rx_in_range_len_err_cnt]; + mac_stats->OutOfRangeLengthField = + portstats[spx5_stats_rx_out_of_range_len_err_cnt] + + portstats[spx5_stats_pmac_rx_out_of_range_len_err_cnt]; + mac_stats->FrameTooLongErrors = portstats[spx5_stats_rx_oversize_cnt] + + portstats[spx5_stats_pmac_rx_oversize_cnt]; +} + +static void sparx5_get_eth_mac_ctrl_stats(struct net_device *ndev, + struct ethtool_eth_ctrl_stats *mac_ctrl_stats) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + int portno = port->portno; + void __iomem *inst; + u64 *portstats; + + portstats = &sparx5->stats[portno * sparx5->num_stats]; + if (sparx5_is_baser(port->conf.portmode)) { + u32 tinst = sparx5_port_dev_index(portno); + u32 dev = sparx5_to_high_dev(portno); + + inst = spx5_inst_get(sparx5, dev, tinst); + sparx5_get_dev_mac_ctrl_stats(portstats, inst, tinst); + } else { + inst = spx5_inst_get(sparx5, TARGET_ASM, 0); + sparx5_get_asm_mac_ctrl_stats(portstats, inst, portno); + } + mac_ctrl_stats->MACControlFramesTransmitted = + portstats[spx5_stats_tx_pause_cnt] + + portstats[spx5_stats_pmac_tx_pause_cnt]; + mac_ctrl_stats->MACControlFramesReceived = + portstats[spx5_stats_rx_pause_cnt] + + portstats[spx5_stats_pmac_rx_pause_cnt]; + mac_ctrl_stats->UnsupportedOpcodesReceived = + portstats[spx5_stats_rx_unsup_opcode_cnt] + + portstats[spx5_stats_pmac_rx_unsup_opcode_cnt]; +} + +static void sparx5_get_eth_rmon_stats(struct net_device *ndev, + struct ethtool_rmon_stats *rmon_stats, + const struct ethtool_rmon_hist_range **ranges) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + int portno = port->portno; + void __iomem *inst; + u64 *portstats; + + portstats = &sparx5->stats[portno * sparx5->num_stats]; + if (sparx5_is_baser(port->conf.portmode)) { + u32 tinst = sparx5_port_dev_index(portno); + u32 dev = sparx5_to_high_dev(portno); + + inst = spx5_inst_get(sparx5, dev, tinst); + sparx5_get_dev_rmon_stats(portstats, inst, tinst); + } else { + inst = spx5_inst_get(sparx5, TARGET_ASM, 0); + sparx5_get_asm_rmon_stats(portstats, inst, portno); + } + rmon_stats->undersize_pkts = portstats[spx5_stats_rx_undersize_cnt] + + portstats[spx5_stats_pmac_rx_undersize_cnt]; + rmon_stats->oversize_pkts = portstats[spx5_stats_rx_oversize_cnt] + + portstats[spx5_stats_pmac_rx_oversize_cnt]; + rmon_stats->fragments = portstats[spx5_stats_rx_fragments_cnt] + + portstats[spx5_stats_pmac_rx_fragments_cnt]; + rmon_stats->jabbers = portstats[spx5_stats_rx_jabbers_cnt] + + portstats[spx5_stats_pmac_rx_jabbers_cnt]; + rmon_stats->hist[0] = portstats[spx5_stats_rx_size64_cnt] + + portstats[spx5_stats_pmac_rx_size64_cnt]; + rmon_stats->hist[1] = portstats[spx5_stats_rx_size65to127_cnt] + + portstats[spx5_stats_pmac_rx_size65to127_cnt]; + rmon_stats->hist[2] = portstats[spx5_stats_rx_size128to255_cnt] + + portstats[spx5_stats_pmac_rx_size128to255_cnt]; + rmon_stats->hist[3] = portstats[spx5_stats_rx_size256to511_cnt] + + portstats[spx5_stats_pmac_rx_size256to511_cnt]; + rmon_stats->hist[4] = portstats[spx5_stats_rx_size512to1023_cnt] + + portstats[spx5_stats_pmac_rx_size512to1023_cnt]; + rmon_stats->hist[5] = portstats[spx5_stats_rx_size1024to1518_cnt] + + portstats[spx5_stats_pmac_rx_size1024to1518_cnt]; + rmon_stats->hist[6] = portstats[spx5_stats_rx_size1519tomax_cnt] + + portstats[spx5_stats_pmac_rx_size1519tomax_cnt]; + rmon_stats->hist_tx[0] = portstats[spx5_stats_tx_size64_cnt] + + portstats[spx5_stats_pmac_tx_size64_cnt]; + rmon_stats->hist_tx[1] = portstats[spx5_stats_tx_size65to127_cnt] + + portstats[spx5_stats_pmac_tx_size65to127_cnt]; + rmon_stats->hist_tx[2] = portstats[spx5_stats_tx_size128to255_cnt] + + portstats[spx5_stats_pmac_tx_size128to255_cnt]; + rmon_stats->hist_tx[3] = portstats[spx5_stats_tx_size256to511_cnt] + + portstats[spx5_stats_pmac_tx_size256to511_cnt]; + rmon_stats->hist_tx[4] = portstats[spx5_stats_tx_size512to1023_cnt] + + portstats[spx5_stats_pmac_tx_size512to1023_cnt]; + rmon_stats->hist_tx[5] = portstats[spx5_stats_tx_size1024to1518_cnt] + + portstats[spx5_stats_pmac_tx_size1024to1518_cnt]; + rmon_stats->hist_tx[6] = portstats[spx5_stats_tx_size1519tomax_cnt] + + portstats[spx5_stats_pmac_tx_size1519tomax_cnt]; + *ranges = sparx5_rmon_ranges; +} + +static int sparx5_get_sset_count(struct net_device *ndev, int sset) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + + if (sset != ETH_SS_STATS) + return -EOPNOTSUPP; + return sparx5->num_ethtool_stats; +} + +static void sparx5_get_sset_strings(struct net_device *ndev, u32 sset, u8 *data) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + int idx; + + if (sset != ETH_SS_STATS) + return; + + for (idx = 0; idx < sparx5->num_ethtool_stats; idx++) + strncpy(data + idx * ETH_GSTRING_LEN, + sparx5->stats_layout[idx], ETH_GSTRING_LEN); +} + +static void sparx5_get_sset_data(struct net_device *ndev, + struct ethtool_stats *stats, u64 *data) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + int portno = port->portno; + void __iomem *inst; + u64 *portstats; + int idx; + + portstats = &sparx5->stats[portno * sparx5->num_stats]; + if (sparx5_is_baser(port->conf.portmode)) { + u32 tinst = sparx5_port_dev_index(portno); + u32 dev = sparx5_to_high_dev(portno); + + inst = spx5_inst_get(sparx5, dev, tinst); + sparx5_get_dev_misc_stats(portstats, inst, tinst); + } else { + inst = spx5_inst_get(sparx5, TARGET_ASM, 0); + sparx5_get_asm_misc_stats(portstats, inst, portno); + } + sparx5_get_ana_ac_stats_stats(sparx5, portno); + sparx5_get_queue_sys_stats(sparx5, portno); + /* Copy port counters to the ethtool buffer */ + for (idx = spx5_stats_mm_rx_assembly_err_cnt; + idx < spx5_stats_mm_rx_assembly_err_cnt + + sparx5->num_ethtool_stats; idx++) + *data++ = portstats[idx]; +} + +void sparx5_get_stats64(struct net_device *ndev, + struct rtnl_link_stats64 *stats) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + u64 *portstats; + int idx; + + if (!sparx5->stats) + return; /* Not initialized yet */ + + portstats = &sparx5->stats[port->portno * sparx5->num_stats]; + + stats->rx_packets = portstats[spx5_stats_rx_uc_cnt] + + portstats[spx5_stats_pmac_rx_uc_cnt] + + portstats[spx5_stats_rx_mc_cnt] + + portstats[spx5_stats_rx_bc_cnt]; + stats->tx_packets = portstats[spx5_stats_tx_uc_cnt] + + portstats[spx5_stats_pmac_tx_uc_cnt] + + portstats[spx5_stats_tx_mc_cnt] + + portstats[spx5_stats_tx_bc_cnt]; + stats->rx_bytes = portstats[spx5_stats_rx_ok_bytes_cnt] + + portstats[spx5_stats_pmac_rx_ok_bytes_cnt]; + stats->tx_bytes = portstats[spx5_stats_tx_ok_bytes_cnt] + + portstats[spx5_stats_pmac_tx_ok_bytes_cnt]; + stats->rx_errors = portstats[spx5_stats_rx_in_range_len_err_cnt] + + portstats[spx5_stats_pmac_rx_in_range_len_err_cnt] + + portstats[spx5_stats_rx_out_of_range_len_err_cnt] + + portstats[spx5_stats_pmac_rx_out_of_range_len_err_cnt] + + portstats[spx5_stats_rx_oversize_cnt] + + portstats[spx5_stats_pmac_rx_oversize_cnt] + + portstats[spx5_stats_rx_crc_err_cnt] + + portstats[spx5_stats_pmac_rx_crc_err_cnt] + + portstats[spx5_stats_rx_alignment_lost_cnt] + + portstats[spx5_stats_pmac_rx_alignment_lost_cnt]; + stats->tx_errors = portstats[spx5_stats_tx_xcoll_cnt] + + portstats[spx5_stats_tx_csense_cnt] + + portstats[spx5_stats_tx_late_coll_cnt]; + stats->multicast = portstats[spx5_stats_rx_mc_cnt] + + portstats[spx5_stats_pmac_rx_mc_cnt]; + stats->collisions = portstats[spx5_stats_tx_late_coll_cnt] + + portstats[spx5_stats_tx_xcoll_cnt] + + portstats[spx5_stats_tx_backoff1_cnt]; + stats->rx_length_errors = portstats[spx5_stats_rx_in_range_len_err_cnt] + + portstats[spx5_stats_pmac_rx_in_range_len_err_cnt] + + portstats[spx5_stats_rx_out_of_range_len_err_cnt] + + portstats[spx5_stats_pmac_rx_out_of_range_len_err_cnt] + + portstats[spx5_stats_rx_oversize_cnt] + + portstats[spx5_stats_pmac_rx_oversize_cnt]; + stats->rx_crc_errors = portstats[spx5_stats_rx_crc_err_cnt] + + portstats[spx5_stats_pmac_rx_crc_err_cnt]; + stats->rx_frame_errors = portstats[spx5_stats_rx_alignment_lost_cnt] + + portstats[spx5_stats_pmac_rx_alignment_lost_cnt]; + stats->tx_aborted_errors = portstats[spx5_stats_tx_xcoll_cnt]; + stats->tx_carrier_errors = portstats[spx5_stats_tx_csense_cnt]; + stats->tx_window_errors = portstats[spx5_stats_tx_late_coll_cnt]; + stats->rx_dropped = portstats[spx5_stats_ana_ac_port_stat_lsb_cnt]; + for (idx = 0; idx < 2 * SPX5_PRIOS; ++idx, ++stats) + stats->rx_dropped += portstats[spx5_stats_green_p0_rx_port_drop + + idx]; + stats->tx_dropped = portstats[spx5_stats_tx_local_drop]; +} + +static void sparx5_update_port_stats(struct sparx5 *sparx5, int portno) +{ + if (sparx5_is_baser(sparx5->ports[portno]->conf.portmode)) + sparx5_get_device_stats(sparx5, portno); + else + sparx5_get_asm_stats(sparx5, portno); + sparx5_get_ana_ac_stats_stats(sparx5, portno); + sparx5_get_queue_sys_stats(sparx5, portno); +} + +static void sparx5_update_stats(struct sparx5 *sparx5) +{ + int idx; + + for (idx = 0; idx < SPX5_PORTS; idx++) + if (sparx5->ports[idx]) + sparx5_update_port_stats(sparx5, idx); +} + +static void sparx5_check_stats_work(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct sparx5 *sparx5 = container_of(dwork, + struct sparx5, + stats_work); + + sparx5_update_stats(sparx5); + + queue_delayed_work(sparx5->stats_queue, &sparx5->stats_work, + SPX5_STATS_CHECK_DELAY); +} + +static int sparx5_get_link_settings(struct net_device *ndev, + struct ethtool_link_ksettings *cmd) +{ + struct sparx5_port *port = netdev_priv(ndev); + + return phylink_ethtool_ksettings_get(port->phylink, cmd); +} + +static int sparx5_set_link_settings(struct net_device *ndev, + const struct ethtool_link_ksettings *cmd) +{ + struct sparx5_port *port = netdev_priv(ndev); + + return phylink_ethtool_ksettings_set(port->phylink, cmd); +} + +static void sparx5_config_stats(struct sparx5 *sparx5) +{ + /* Enable global events for port policer drops */ + spx5_rmw(ANA_AC_PORT_SGE_CFG_MASK_SET(0xf0f0), + ANA_AC_PORT_SGE_CFG_MASK, + sparx5, + ANA_AC_PORT_SGE_CFG(SPX5_PORT_POLICER_DROPS)); +} + +static void sparx5_config_port_stats(struct sparx5 *sparx5, int portno) +{ + /* Clear Queue System counters */ + spx5_wr(XQS_STAT_CFG_STAT_VIEW_SET(portno) | + XQS_STAT_CFG_STAT_CLEAR_SHOT_SET(3), sparx5, + XQS_STAT_CFG); + + /* Use counter for port policer drop count */ + spx5_rmw(ANA_AC_PORT_STAT_CFG_CFG_CNT_FRM_TYPE_SET(1) | + ANA_AC_PORT_STAT_CFG_CFG_CNT_BYTE_SET(0) | + ANA_AC_PORT_STAT_CFG_CFG_PRIO_MASK_SET(0xff), + ANA_AC_PORT_STAT_CFG_CFG_CNT_FRM_TYPE | + ANA_AC_PORT_STAT_CFG_CFG_CNT_BYTE | + ANA_AC_PORT_STAT_CFG_CFG_PRIO_MASK, + sparx5, ANA_AC_PORT_STAT_CFG(portno, SPX5_PORT_POLICER_DROPS)); +} + +const struct ethtool_ops sparx5_ethtool_ops = { + .get_sset_count = sparx5_get_sset_count, + .get_strings = sparx5_get_sset_strings, + .get_ethtool_stats = sparx5_get_sset_data, + .get_link_ksettings = sparx5_get_link_settings, + .set_link_ksettings = sparx5_set_link_settings, + .get_link = ethtool_op_get_link, + .get_eth_phy_stats = sparx5_get_eth_phy_stats, + .get_eth_mac_stats = sparx5_get_eth_mac_stats, + .get_eth_ctrl_stats = sparx5_get_eth_mac_ctrl_stats, + .get_rmon_stats = sparx5_get_eth_rmon_stats, +}; + +int sparx_stats_init(struct sparx5 *sparx5) +{ + char queue_name[32]; + int portno; + + sparx5->stats_layout = sparx5_stats_layout; + sparx5->num_stats = spx5_stats_count; + sparx5->num_ethtool_stats = ARRAY_SIZE(sparx5_stats_layout); + sparx5->stats = devm_kcalloc(sparx5->dev, + SPX5_PORTS_ALL * sparx5->num_stats, + sizeof(u64), GFP_KERNEL); + if (!sparx5->stats) + return -ENOMEM; + + mutex_init(&sparx5->queue_stats_lock); + sparx5_config_stats(sparx5); + for (portno = 0; portno < SPX5_PORTS; portno++) + if (sparx5->ports[portno]) + sparx5_config_port_stats(sparx5, portno); + + snprintf(queue_name, sizeof(queue_name), "%s-stats", + dev_name(sparx5->dev)); + sparx5->stats_queue = create_singlethread_workqueue(queue_name); + INIT_DELAYED_WORK(&sparx5->stats_work, sparx5_check_stats_work); + queue_delayed_work(sparx5->stats_queue, &sparx5->stats_work, + SPX5_STATS_CHECK_DELAY); + + return 0; +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c new file mode 100644 index 000000000000..0443f66b5550 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c @@ -0,0 +1,500 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries. + */ + +#include +#include +#include + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +/* Commands for Mac Table Command register */ +#define MAC_CMD_LEARN 0 /* Insert (Learn) 1 entry */ +#define MAC_CMD_UNLEARN 1 /* Unlearn (Forget) 1 entry */ +#define MAC_CMD_LOOKUP 2 /* Look up 1 entry */ +#define MAC_CMD_READ 3 /* Read entry at Mac Table Index */ +#define MAC_CMD_WRITE 4 /* Write entry at Mac Table Index */ +#define MAC_CMD_SCAN 5 /* Scan (Age or find next) */ +#define MAC_CMD_FIND_SMALLEST 6 /* Get next entry */ +#define MAC_CMD_CLEAR_ALL 7 /* Delete all entries in table */ + +/* Commands for MAC_ENTRY_ADDR_TYPE */ +#define MAC_ENTRY_ADDR_TYPE_UPSID_PN 0 +#define MAC_ENTRY_ADDR_TYPE_UPSID_CPU_OR_INT 1 +#define MAC_ENTRY_ADDR_TYPE_GLAG 2 +#define MAC_ENTRY_ADDR_TYPE_MC_IDX 3 + +#define TABLE_UPDATE_SLEEP_US 10 +#define TABLE_UPDATE_TIMEOUT_US 100000 + +struct sparx5_mact_entry { + struct list_head list; + unsigned char mac[ETH_ALEN]; + u32 flags; +#define MAC_ENT_ALIVE BIT(0) +#define MAC_ENT_MOVED BIT(1) +#define MAC_ENT_LOCK BIT(2) + u16 vid; + u16 port; +}; + +static int sparx5_mact_get_status(struct sparx5 *sparx5) +{ + return spx5_rd(sparx5, LRN_COMMON_ACCESS_CTRL); +} + +static int sparx5_mact_wait_for_completion(struct sparx5 *sparx5) +{ + u32 val; + + return readx_poll_timeout(sparx5_mact_get_status, + sparx5, val, + LRN_COMMON_ACCESS_CTRL_MAC_TABLE_ACCESS_SHOT_GET(val) == 0, + TABLE_UPDATE_SLEEP_US, TABLE_UPDATE_TIMEOUT_US); +} + +static void sparx5_mact_select(struct sparx5 *sparx5, + const unsigned char mac[ETH_ALEN], + u16 vid) +{ + u32 macl = 0, mach = 0; + + /* Set the MAC address to handle and the vlan associated in a format + * understood by the hardware. + */ + mach |= vid << 16; + mach |= mac[0] << 8; + mach |= mac[1] << 0; + macl |= mac[2] << 24; + macl |= mac[3] << 16; + macl |= mac[4] << 8; + macl |= mac[5] << 0; + + spx5_wr(mach, sparx5, LRN_MAC_ACCESS_CFG_0); + spx5_wr(macl, sparx5, LRN_MAC_ACCESS_CFG_1); +} + +int sparx5_mact_learn(struct sparx5 *sparx5, int pgid, + const unsigned char mac[ETH_ALEN], u16 vid) +{ + int addr, type, ret; + + if (pgid < SPX5_PORTS) { + type = MAC_ENTRY_ADDR_TYPE_UPSID_PN; + addr = pgid % 32; + addr += (pgid / 32) << 5; /* Add upsid */ + } else { + type = MAC_ENTRY_ADDR_TYPE_MC_IDX; + addr = pgid - SPX5_PORTS; + } + + mutex_lock(&sparx5->lock); + + sparx5_mact_select(sparx5, mac, vid); + + /* MAC entry properties */ + spx5_wr(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR_SET(addr) | + LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR_TYPE_SET(type) | + LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLD_SET(1) | + LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_LOCKED_SET(1), + sparx5, LRN_MAC_ACCESS_CFG_2); + spx5_wr(0, sparx5, LRN_MAC_ACCESS_CFG_3); + + /* Insert/learn new entry */ + spx5_wr(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_CMD_SET(MAC_CMD_LEARN) | + LRN_COMMON_ACCESS_CTRL_MAC_TABLE_ACCESS_SHOT_SET(1), + sparx5, LRN_COMMON_ACCESS_CTRL); + + ret = sparx5_mact_wait_for_completion(sparx5); + + mutex_unlock(&sparx5->lock); + + return ret; +} + +int sparx5_mc_unsync(struct net_device *dev, const unsigned char *addr) +{ + struct sparx5_port *port = netdev_priv(dev); + struct sparx5 *sparx5 = port->sparx5; + + return sparx5_mact_forget(sparx5, addr, port->pvid); +} + +int sparx5_mc_sync(struct net_device *dev, const unsigned char *addr) +{ + struct sparx5_port *port = netdev_priv(dev); + struct sparx5 *sparx5 = port->sparx5; + + return sparx5_mact_learn(sparx5, PGID_CPU, addr, port->pvid); +} + +static int sparx5_mact_get(struct sparx5 *sparx5, + unsigned char mac[ETH_ALEN], + u16 *vid, u32 *pcfg2) +{ + u32 mach, macl, cfg2; + int ret = -ENOENT; + + cfg2 = spx5_rd(sparx5, LRN_MAC_ACCESS_CFG_2); + if (LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLD_GET(cfg2)) { + mach = spx5_rd(sparx5, LRN_MAC_ACCESS_CFG_0); + macl = spx5_rd(sparx5, LRN_MAC_ACCESS_CFG_1); + mac[0] = ((mach >> 8) & 0xff); + mac[1] = ((mach >> 0) & 0xff); + mac[2] = ((macl >> 24) & 0xff); + mac[3] = ((macl >> 16) & 0xff); + mac[4] = ((macl >> 8) & 0xff); + mac[5] = ((macl >> 0) & 0xff); + *vid = mach >> 16; + *pcfg2 = cfg2; + ret = 0; + } + + return ret; +} + +bool sparx5_mact_getnext(struct sparx5 *sparx5, + unsigned char mac[ETH_ALEN], u16 *vid, u32 *pcfg2) +{ + u32 cfg2; + int ret; + + mutex_lock(&sparx5->lock); + + sparx5_mact_select(sparx5, mac, *vid); + + spx5_wr(LRN_SCAN_NEXT_CFG_SCAN_NEXT_IGNORE_LOCKED_ENA_SET(1) | + LRN_SCAN_NEXT_CFG_SCAN_NEXT_UNTIL_FOUND_ENA_SET(1), + sparx5, LRN_SCAN_NEXT_CFG); + spx5_wr(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_CMD_SET + (MAC_CMD_FIND_SMALLEST) | + LRN_COMMON_ACCESS_CTRL_MAC_TABLE_ACCESS_SHOT_SET(1), + sparx5, LRN_COMMON_ACCESS_CTRL); + + ret = sparx5_mact_wait_for_completion(sparx5); + if (ret == 0) { + ret = sparx5_mact_get(sparx5, mac, vid, &cfg2); + if (ret == 0) + *pcfg2 = cfg2; + } + + mutex_unlock(&sparx5->lock); + + return ret == 0; +} + +static int sparx5_mact_lookup(struct sparx5 *sparx5, + const unsigned char mac[ETH_ALEN], + u16 vid) +{ + int ret; + + mutex_lock(&sparx5->lock); + + sparx5_mact_select(sparx5, mac, vid); + + /* Issue a lookup command */ + spx5_wr(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_CMD_SET(MAC_CMD_LOOKUP) | + LRN_COMMON_ACCESS_CTRL_MAC_TABLE_ACCESS_SHOT_SET(1), + sparx5, LRN_COMMON_ACCESS_CTRL); + + ret = sparx5_mact_wait_for_completion(sparx5); + if (ret) + goto out; + + ret = LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLD_GET + (spx5_rd(sparx5, LRN_MAC_ACCESS_CFG_2)); + +out: + mutex_unlock(&sparx5->lock); + + return ret; +} + +int sparx5_mact_forget(struct sparx5 *sparx5, + const unsigned char mac[ETH_ALEN], u16 vid) +{ + int ret; + + mutex_lock(&sparx5->lock); + + sparx5_mact_select(sparx5, mac, vid); + + /* Issue an unlearn command */ + spx5_wr(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_CMD_SET(MAC_CMD_UNLEARN) | + LRN_COMMON_ACCESS_CTRL_MAC_TABLE_ACCESS_SHOT_SET(1), + sparx5, LRN_COMMON_ACCESS_CTRL); + + ret = sparx5_mact_wait_for_completion(sparx5); + + mutex_unlock(&sparx5->lock); + + return ret; +} + +static struct sparx5_mact_entry *alloc_mact_entry(struct sparx5 *sparx5, + const unsigned char *mac, + u16 vid, u16 port_index) +{ + struct sparx5_mact_entry *mact_entry; + + mact_entry = devm_kzalloc(sparx5->dev, + sizeof(*mact_entry), GFP_ATOMIC); + if (!mact_entry) + return NULL; + + memcpy(mact_entry->mac, mac, ETH_ALEN); + mact_entry->vid = vid; + mact_entry->port = port_index; + return mact_entry; +} + +static struct sparx5_mact_entry *find_mact_entry(struct sparx5 *sparx5, + const unsigned char *mac, + u16 vid, u16 port_index) +{ + struct sparx5_mact_entry *mact_entry; + struct sparx5_mact_entry *res = NULL; + + mutex_lock(&sparx5->mact_lock); + list_for_each_entry(mact_entry, &sparx5->mact_entries, list) { + if (mact_entry->vid == vid && + ether_addr_equal(mac, mact_entry->mac) && + mact_entry->port == port_index) { + res = mact_entry; + break; + } + } + mutex_unlock(&sparx5->mact_lock); + + return res; +} + +static void sparx5_fdb_call_notifiers(enum switchdev_notifier_type type, + const char *mac, u16 vid, + struct net_device *dev, bool offloaded) +{ + struct switchdev_notifier_fdb_info info; + + info.addr = mac; + info.vid = vid; + info.offloaded = offloaded; + call_switchdev_notifiers(type, dev, &info.info, NULL); +} + +int sparx5_add_mact_entry(struct sparx5 *sparx5, + struct sparx5_port *port, + const unsigned char *addr, u16 vid) +{ + struct sparx5_mact_entry *mact_entry; + int ret; + + ret = sparx5_mact_lookup(sparx5, addr, vid); + if (ret) + return 0; + + /* In case the entry already exists, don't add it again to SW, + * just update HW, but we need to look in the actual HW because + * it is possible for an entry to be learn by HW and before the + * mact thread to start the frame will reach CPU and the CPU will + * add the entry but without the extern_learn flag. + */ + mact_entry = find_mact_entry(sparx5, addr, vid, port->portno); + if (mact_entry) + goto update_hw; + + /* Add the entry in SW MAC table not to get the notification when + * SW is pulling again + */ + mact_entry = alloc_mact_entry(sparx5, addr, vid, port->portno); + if (!mact_entry) + return -ENOMEM; + + mutex_lock(&sparx5->mact_lock); + list_add_tail(&mact_entry->list, &sparx5->mact_entries); + mutex_unlock(&sparx5->mact_lock); + +update_hw: + ret = sparx5_mact_learn(sparx5, port->portno, addr, vid); + + /* New entry? */ + if (mact_entry->flags == 0) { + mact_entry->flags |= MAC_ENT_LOCK; /* Don't age this */ + sparx5_fdb_call_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE, addr, vid, + port->ndev, true); + } + + return ret; +} + +int sparx5_del_mact_entry(struct sparx5 *sparx5, + const unsigned char *addr, + u16 vid) +{ + struct sparx5_mact_entry *mact_entry, *tmp; + + /* Delete the entry in SW MAC table not to get the notification when + * SW is pulling again + */ + mutex_lock(&sparx5->mact_lock); + list_for_each_entry_safe(mact_entry, tmp, &sparx5->mact_entries, + list) { + if ((vid == 0 || mact_entry->vid == vid) && + ether_addr_equal(addr, mact_entry->mac)) { + list_del(&mact_entry->list); + devm_kfree(sparx5->dev, mact_entry); + + sparx5_mact_forget(sparx5, addr, mact_entry->vid); + } + } + mutex_unlock(&sparx5->mact_lock); + + return 0; +} + +static void sparx5_mact_handle_entry(struct sparx5 *sparx5, + unsigned char mac[ETH_ALEN], + u16 vid, u32 cfg2) +{ + struct sparx5_mact_entry *mact_entry; + bool found = false; + u16 port; + + if (LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR_TYPE_GET(cfg2) != + MAC_ENTRY_ADDR_TYPE_UPSID_PN) + return; + + port = LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR_GET(cfg2); + if (port >= SPX5_PORTS) + return; + + if (!test_bit(port, sparx5->bridge_mask)) + return; + + mutex_lock(&sparx5->mact_lock); + list_for_each_entry(mact_entry, &sparx5->mact_entries, list) { + if (mact_entry->vid == vid && + ether_addr_equal(mac, mact_entry->mac)) { + found = true; + mact_entry->flags |= MAC_ENT_ALIVE; + if (mact_entry->port != port) { + dev_warn(sparx5->dev, "Entry move: %d -> %d\n", + mact_entry->port, port); + mact_entry->port = port; + mact_entry->flags |= MAC_ENT_MOVED; + } + /* Entry handled */ + break; + } + } + mutex_unlock(&sparx5->mact_lock); + + if (found && !(mact_entry->flags & MAC_ENT_MOVED)) + /* Present, not moved */ + return; + + if (!found) { + /* Entry not found - now add */ + mact_entry = alloc_mact_entry(sparx5, mac, vid, port); + if (!mact_entry) + return; + + mact_entry->flags |= MAC_ENT_ALIVE; + mutex_lock(&sparx5->mact_lock); + list_add_tail(&mact_entry->list, &sparx5->mact_entries); + mutex_unlock(&sparx5->mact_lock); + } + + /* New or moved entry - notify bridge */ + sparx5_fdb_call_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE, + mac, vid, sparx5->ports[port]->ndev, + true); +} + +void sparx5_mact_pull_work(struct work_struct *work) +{ + struct delayed_work *del_work = to_delayed_work(work); + struct sparx5 *sparx5 = container_of(del_work, struct sparx5, + mact_work); + struct sparx5_mact_entry *mact_entry, *tmp; + unsigned char mac[ETH_ALEN]; + u32 cfg2; + u16 vid; + int ret; + + /* Reset MAC entry flags */ + mutex_lock(&sparx5->mact_lock); + list_for_each_entry(mact_entry, &sparx5->mact_entries, list) + mact_entry->flags &= MAC_ENT_LOCK; + mutex_unlock(&sparx5->mact_lock); + + /* MAIN mac address processing loop */ + vid = 0; + memset(mac, 0, sizeof(mac)); + do { + mutex_lock(&sparx5->lock); + sparx5_mact_select(sparx5, mac, vid); + spx5_wr(LRN_SCAN_NEXT_CFG_SCAN_NEXT_UNTIL_FOUND_ENA_SET(1), + sparx5, LRN_SCAN_NEXT_CFG); + spx5_wr(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_CMD_SET + (MAC_CMD_FIND_SMALLEST) | + LRN_COMMON_ACCESS_CTRL_MAC_TABLE_ACCESS_SHOT_SET(1), + sparx5, LRN_COMMON_ACCESS_CTRL); + ret = sparx5_mact_wait_for_completion(sparx5); + if (ret == 0) + ret = sparx5_mact_get(sparx5, mac, &vid, &cfg2); + mutex_unlock(&sparx5->lock); + if (ret == 0) + sparx5_mact_handle_entry(sparx5, mac, vid, cfg2); + } while (ret == 0); + + mutex_lock(&sparx5->mact_lock); + list_for_each_entry_safe(mact_entry, tmp, &sparx5->mact_entries, + list) { + /* If the entry is in HW or permanent, then skip */ + if (mact_entry->flags & (MAC_ENT_ALIVE | MAC_ENT_LOCK)) + continue; + + sparx5_fdb_call_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, + mact_entry->mac, mact_entry->vid, + sparx5->ports[mact_entry->port]->ndev, + true); + + list_del(&mact_entry->list); + devm_kfree(sparx5->dev, mact_entry); + } + mutex_unlock(&sparx5->mact_lock); + + queue_delayed_work(sparx5->mact_queue, &sparx5->mact_work, + SPX5_MACT_PULL_DELAY); +} + +void sparx5_set_ageing(struct sparx5 *sparx5, int msecs) +{ + int value = max(1, msecs / 10); /* unit 10 ms */ + + spx5_rmw(LRN_AUTOAGE_CFG_UNIT_SIZE_SET(2) | /* 10 ms */ + LRN_AUTOAGE_CFG_PERIOD_VAL_SET(value / 2), /* one bit ageing */ + LRN_AUTOAGE_CFG_UNIT_SIZE | + LRN_AUTOAGE_CFG_PERIOD_VAL, + sparx5, + LRN_AUTOAGE_CFG(0)); +} + +void sparx5_mact_init(struct sparx5 *sparx5) +{ + mutex_init(&sparx5->lock); + + /* Flush MAC table */ + spx5_wr(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_CMD_SET(MAC_CMD_CLEAR_ALL) | + LRN_COMMON_ACCESS_CTRL_MAC_TABLE_ACCESS_SHOT_SET(1), + sparx5, LRN_COMMON_ACCESS_CTRL); + + if (sparx5_mact_wait_for_completion(sparx5) != 0) + dev_warn(sparx5->dev, "MAC flush error\n"); + + sparx5_set_ageing(sparx5, BR_DEFAULT_AGEING_TIME / HZ * 1000); +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c new file mode 100644 index 000000000000..f666133a15de --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -0,0 +1,853 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries. + * + * The Sparx5 Chip Register Model can be browsed at this location: + * https://github.com/microchip-ung/sparx-5_reginfo + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" +#include "sparx5_port.h" + +#define QLIM_WM(fraction) \ + ((SPX5_BUFFER_MEMORY / SPX5_BUFFER_CELL_SZ - 100) * (fraction) / 100) +#define IO_RANGES 3 + +struct initial_port_config { + u32 portno; + struct device_node *node; + struct sparx5_port_config conf; + struct phy *serdes; +}; + +struct sparx5_ram_config { + void __iomem *init_reg; + u32 init_val; +}; + +struct sparx5_main_io_resource { + enum sparx5_target id; + phys_addr_t offset; + int range; +}; + +static const struct sparx5_main_io_resource sparx5_main_iomap[] = { + { TARGET_CPU, 0, 0 }, /* 0x600000000 */ + { TARGET_FDMA, 0x80000, 0 }, /* 0x600080000 */ + { TARGET_PCEP, 0x400000, 0 }, /* 0x600400000 */ + { TARGET_DEV2G5, 0x10004000, 1 }, /* 0x610004000 */ + { TARGET_DEV5G, 0x10008000, 1 }, /* 0x610008000 */ + { TARGET_PCS5G_BR, 0x1000c000, 1 }, /* 0x61000c000 */ + { TARGET_DEV2G5 + 1, 0x10010000, 1 }, /* 0x610010000 */ + { TARGET_DEV5G + 1, 0x10014000, 1 }, /* 0x610014000 */ + { TARGET_PCS5G_BR + 1, 0x10018000, 1 }, /* 0x610018000 */ + { TARGET_DEV2G5 + 2, 0x1001c000, 1 }, /* 0x61001c000 */ + { TARGET_DEV5G + 2, 0x10020000, 1 }, /* 0x610020000 */ + { TARGET_PCS5G_BR + 2, 0x10024000, 1 }, /* 0x610024000 */ + { TARGET_DEV2G5 + 6, 0x10028000, 1 }, /* 0x610028000 */ + { TARGET_DEV5G + 6, 0x1002c000, 1 }, /* 0x61002c000 */ + { TARGET_PCS5G_BR + 6, 0x10030000, 1 }, /* 0x610030000 */ + { TARGET_DEV2G5 + 7, 0x10034000, 1 }, /* 0x610034000 */ + { TARGET_DEV5G + 7, 0x10038000, 1 }, /* 0x610038000 */ + { TARGET_PCS5G_BR + 7, 0x1003c000, 1 }, /* 0x61003c000 */ + { TARGET_DEV2G5 + 8, 0x10040000, 1 }, /* 0x610040000 */ + { TARGET_DEV5G + 8, 0x10044000, 1 }, /* 0x610044000 */ + { TARGET_PCS5G_BR + 8, 0x10048000, 1 }, /* 0x610048000 */ + { TARGET_DEV2G5 + 9, 0x1004c000, 1 }, /* 0x61004c000 */ + { TARGET_DEV5G + 9, 0x10050000, 1 }, /* 0x610050000 */ + { TARGET_PCS5G_BR + 9, 0x10054000, 1 }, /* 0x610054000 */ + { TARGET_DEV2G5 + 10, 0x10058000, 1 }, /* 0x610058000 */ + { TARGET_DEV5G + 10, 0x1005c000, 1 }, /* 0x61005c000 */ + { TARGET_PCS5G_BR + 10, 0x10060000, 1 }, /* 0x610060000 */ + { TARGET_DEV2G5 + 11, 0x10064000, 1 }, /* 0x610064000 */ + { TARGET_DEV5G + 11, 0x10068000, 1 }, /* 0x610068000 */ + { TARGET_PCS5G_BR + 11, 0x1006c000, 1 }, /* 0x61006c000 */ + { TARGET_DEV2G5 + 12, 0x10070000, 1 }, /* 0x610070000 */ + { TARGET_DEV10G, 0x10074000, 1 }, /* 0x610074000 */ + { TARGET_PCS10G_BR, 0x10078000, 1 }, /* 0x610078000 */ + { TARGET_DEV2G5 + 14, 0x1007c000, 1 }, /* 0x61007c000 */ + { TARGET_DEV10G + 2, 0x10080000, 1 }, /* 0x610080000 */ + { TARGET_PCS10G_BR + 2, 0x10084000, 1 }, /* 0x610084000 */ + { TARGET_DEV2G5 + 15, 0x10088000, 1 }, /* 0x610088000 */ + { TARGET_DEV10G + 3, 0x1008c000, 1 }, /* 0x61008c000 */ + { TARGET_PCS10G_BR + 3, 0x10090000, 1 }, /* 0x610090000 */ + { TARGET_DEV2G5 + 16, 0x10094000, 1 }, /* 0x610094000 */ + { TARGET_DEV2G5 + 17, 0x10098000, 1 }, /* 0x610098000 */ + { TARGET_DEV2G5 + 18, 0x1009c000, 1 }, /* 0x61009c000 */ + { TARGET_DEV2G5 + 19, 0x100a0000, 1 }, /* 0x6100a0000 */ + { TARGET_DEV2G5 + 20, 0x100a4000, 1 }, /* 0x6100a4000 */ + { TARGET_DEV2G5 + 21, 0x100a8000, 1 }, /* 0x6100a8000 */ + { TARGET_DEV2G5 + 22, 0x100ac000, 1 }, /* 0x6100ac000 */ + { TARGET_DEV2G5 + 23, 0x100b0000, 1 }, /* 0x6100b0000 */ + { TARGET_DEV2G5 + 32, 0x100b4000, 1 }, /* 0x6100b4000 */ + { TARGET_DEV2G5 + 33, 0x100b8000, 1 }, /* 0x6100b8000 */ + { TARGET_DEV2G5 + 34, 0x100bc000, 1 }, /* 0x6100bc000 */ + { TARGET_DEV2G5 + 35, 0x100c0000, 1 }, /* 0x6100c0000 */ + { TARGET_DEV2G5 + 36, 0x100c4000, 1 }, /* 0x6100c4000 */ + { TARGET_DEV2G5 + 37, 0x100c8000, 1 }, /* 0x6100c8000 */ + { TARGET_DEV2G5 + 38, 0x100cc000, 1 }, /* 0x6100cc000 */ + { TARGET_DEV2G5 + 39, 0x100d0000, 1 }, /* 0x6100d0000 */ + { TARGET_DEV2G5 + 40, 0x100d4000, 1 }, /* 0x6100d4000 */ + { TARGET_DEV2G5 + 41, 0x100d8000, 1 }, /* 0x6100d8000 */ + { TARGET_DEV2G5 + 42, 0x100dc000, 1 }, /* 0x6100dc000 */ + { TARGET_DEV2G5 + 43, 0x100e0000, 1 }, /* 0x6100e0000 */ + { TARGET_DEV2G5 + 44, 0x100e4000, 1 }, /* 0x6100e4000 */ + { TARGET_DEV2G5 + 45, 0x100e8000, 1 }, /* 0x6100e8000 */ + { TARGET_DEV2G5 + 46, 0x100ec000, 1 }, /* 0x6100ec000 */ + { TARGET_DEV2G5 + 47, 0x100f0000, 1 }, /* 0x6100f0000 */ + { TARGET_DEV2G5 + 57, 0x100f4000, 1 }, /* 0x6100f4000 */ + { TARGET_DEV25G + 1, 0x100f8000, 1 }, /* 0x6100f8000 */ + { TARGET_PCS25G_BR + 1, 0x100fc000, 1 }, /* 0x6100fc000 */ + { TARGET_DEV2G5 + 59, 0x10104000, 1 }, /* 0x610104000 */ + { TARGET_DEV25G + 3, 0x10108000, 1 }, /* 0x610108000 */ + { TARGET_PCS25G_BR + 3, 0x1010c000, 1 }, /* 0x61010c000 */ + { TARGET_DEV2G5 + 60, 0x10114000, 1 }, /* 0x610114000 */ + { TARGET_DEV25G + 4, 0x10118000, 1 }, /* 0x610118000 */ + { TARGET_PCS25G_BR + 4, 0x1011c000, 1 }, /* 0x61011c000 */ + { TARGET_DEV2G5 + 64, 0x10124000, 1 }, /* 0x610124000 */ + { TARGET_DEV5G + 12, 0x10128000, 1 }, /* 0x610128000 */ + { TARGET_PCS5G_BR + 12, 0x1012c000, 1 }, /* 0x61012c000 */ + { TARGET_PORT_CONF, 0x10130000, 1 }, /* 0x610130000 */ + { TARGET_DEV2G5 + 3, 0x10404000, 1 }, /* 0x610404000 */ + { TARGET_DEV5G + 3, 0x10408000, 1 }, /* 0x610408000 */ + { TARGET_PCS5G_BR + 3, 0x1040c000, 1 }, /* 0x61040c000 */ + { TARGET_DEV2G5 + 4, 0x10410000, 1 }, /* 0x610410000 */ + { TARGET_DEV5G + 4, 0x10414000, 1 }, /* 0x610414000 */ + { TARGET_PCS5G_BR + 4, 0x10418000, 1 }, /* 0x610418000 */ + { TARGET_DEV2G5 + 5, 0x1041c000, 1 }, /* 0x61041c000 */ + { TARGET_DEV5G + 5, 0x10420000, 1 }, /* 0x610420000 */ + { TARGET_PCS5G_BR + 5, 0x10424000, 1 }, /* 0x610424000 */ + { TARGET_DEV2G5 + 13, 0x10428000, 1 }, /* 0x610428000 */ + { TARGET_DEV10G + 1, 0x1042c000, 1 }, /* 0x61042c000 */ + { TARGET_PCS10G_BR + 1, 0x10430000, 1 }, /* 0x610430000 */ + { TARGET_DEV2G5 + 24, 0x10434000, 1 }, /* 0x610434000 */ + { TARGET_DEV2G5 + 25, 0x10438000, 1 }, /* 0x610438000 */ + { TARGET_DEV2G5 + 26, 0x1043c000, 1 }, /* 0x61043c000 */ + { TARGET_DEV2G5 + 27, 0x10440000, 1 }, /* 0x610440000 */ + { TARGET_DEV2G5 + 28, 0x10444000, 1 }, /* 0x610444000 */ + { TARGET_DEV2G5 + 29, 0x10448000, 1 }, /* 0x610448000 */ + { TARGET_DEV2G5 + 30, 0x1044c000, 1 }, /* 0x61044c000 */ + { TARGET_DEV2G5 + 31, 0x10450000, 1 }, /* 0x610450000 */ + { TARGET_DEV2G5 + 48, 0x10454000, 1 }, /* 0x610454000 */ + { TARGET_DEV10G + 4, 0x10458000, 1 }, /* 0x610458000 */ + { TARGET_PCS10G_BR + 4, 0x1045c000, 1 }, /* 0x61045c000 */ + { TARGET_DEV2G5 + 49, 0x10460000, 1 }, /* 0x610460000 */ + { TARGET_DEV10G + 5, 0x10464000, 1 }, /* 0x610464000 */ + { TARGET_PCS10G_BR + 5, 0x10468000, 1 }, /* 0x610468000 */ + { TARGET_DEV2G5 + 50, 0x1046c000, 1 }, /* 0x61046c000 */ + { TARGET_DEV10G + 6, 0x10470000, 1 }, /* 0x610470000 */ + { TARGET_PCS10G_BR + 6, 0x10474000, 1 }, /* 0x610474000 */ + { TARGET_DEV2G5 + 51, 0x10478000, 1 }, /* 0x610478000 */ + { TARGET_DEV10G + 7, 0x1047c000, 1 }, /* 0x61047c000 */ + { TARGET_PCS10G_BR + 7, 0x10480000, 1 }, /* 0x610480000 */ + { TARGET_DEV2G5 + 52, 0x10484000, 1 }, /* 0x610484000 */ + { TARGET_DEV10G + 8, 0x10488000, 1 }, /* 0x610488000 */ + { TARGET_PCS10G_BR + 8, 0x1048c000, 1 }, /* 0x61048c000 */ + { TARGET_DEV2G5 + 53, 0x10490000, 1 }, /* 0x610490000 */ + { TARGET_DEV10G + 9, 0x10494000, 1 }, /* 0x610494000 */ + { TARGET_PCS10G_BR + 9, 0x10498000, 1 }, /* 0x610498000 */ + { TARGET_DEV2G5 + 54, 0x1049c000, 1 }, /* 0x61049c000 */ + { TARGET_DEV10G + 10, 0x104a0000, 1 }, /* 0x6104a0000 */ + { TARGET_PCS10G_BR + 10, 0x104a4000, 1 }, /* 0x6104a4000 */ + { TARGET_DEV2G5 + 55, 0x104a8000, 1 }, /* 0x6104a8000 */ + { TARGET_DEV10G + 11, 0x104ac000, 1 }, /* 0x6104ac000 */ + { TARGET_PCS10G_BR + 11, 0x104b0000, 1 }, /* 0x6104b0000 */ + { TARGET_DEV2G5 + 56, 0x104b4000, 1 }, /* 0x6104b4000 */ + { TARGET_DEV25G, 0x104b8000, 1 }, /* 0x6104b8000 */ + { TARGET_PCS25G_BR, 0x104bc000, 1 }, /* 0x6104bc000 */ + { TARGET_DEV2G5 + 58, 0x104c4000, 1 }, /* 0x6104c4000 */ + { TARGET_DEV25G + 2, 0x104c8000, 1 }, /* 0x6104c8000 */ + { TARGET_PCS25G_BR + 2, 0x104cc000, 1 }, /* 0x6104cc000 */ + { TARGET_DEV2G5 + 61, 0x104d4000, 1 }, /* 0x6104d4000 */ + { TARGET_DEV25G + 5, 0x104d8000, 1 }, /* 0x6104d8000 */ + { TARGET_PCS25G_BR + 5, 0x104dc000, 1 }, /* 0x6104dc000 */ + { TARGET_DEV2G5 + 62, 0x104e4000, 1 }, /* 0x6104e4000 */ + { TARGET_DEV25G + 6, 0x104e8000, 1 }, /* 0x6104e8000 */ + { TARGET_PCS25G_BR + 6, 0x104ec000, 1 }, /* 0x6104ec000 */ + { TARGET_DEV2G5 + 63, 0x104f4000, 1 }, /* 0x6104f4000 */ + { TARGET_DEV25G + 7, 0x104f8000, 1 }, /* 0x6104f8000 */ + { TARGET_PCS25G_BR + 7, 0x104fc000, 1 }, /* 0x6104fc000 */ + { TARGET_DSM, 0x10504000, 1 }, /* 0x610504000 */ + { TARGET_ASM, 0x10600000, 1 }, /* 0x610600000 */ + { TARGET_GCB, 0x11010000, 2 }, /* 0x611010000 */ + { TARGET_QS, 0x11030000, 2 }, /* 0x611030000 */ + { TARGET_ANA_ACL, 0x11050000, 2 }, /* 0x611050000 */ + { TARGET_LRN, 0x11060000, 2 }, /* 0x611060000 */ + { TARGET_VCAP_SUPER, 0x11080000, 2 }, /* 0x611080000 */ + { TARGET_QSYS, 0x110a0000, 2 }, /* 0x6110a0000 */ + { TARGET_QFWD, 0x110b0000, 2 }, /* 0x6110b0000 */ + { TARGET_XQS, 0x110c0000, 2 }, /* 0x6110c0000 */ + { TARGET_CLKGEN, 0x11100000, 2 }, /* 0x611100000 */ + { TARGET_ANA_AC_POL, 0x11200000, 2 }, /* 0x611200000 */ + { TARGET_QRES, 0x11280000, 2 }, /* 0x611280000 */ + { TARGET_EACL, 0x112c0000, 2 }, /* 0x6112c0000 */ + { TARGET_ANA_CL, 0x11400000, 2 }, /* 0x611400000 */ + { TARGET_ANA_L3, 0x11480000, 2 }, /* 0x611480000 */ + { TARGET_HSCH, 0x11580000, 2 }, /* 0x611580000 */ + { TARGET_REW, 0x11600000, 2 }, /* 0x611600000 */ + { TARGET_ANA_L2, 0x11800000, 2 }, /* 0x611800000 */ + { TARGET_ANA_AC, 0x11900000, 2 }, /* 0x611900000 */ + { TARGET_VOP, 0x11a00000, 2 }, /* 0x611a00000 */ +}; + +static int sparx5_create_targets(struct sparx5 *sparx5) +{ + struct resource *iores[IO_RANGES]; + void __iomem *iomem[IO_RANGES]; + void __iomem *begin[IO_RANGES]; + int range_id[IO_RANGES]; + int idx, jdx; + + for (idx = 0, jdx = 0; jdx < ARRAY_SIZE(sparx5_main_iomap); jdx++) { + const struct sparx5_main_io_resource *iomap = &sparx5_main_iomap[jdx]; + + if (idx == iomap->range) { + range_id[idx] = jdx; + idx++; + } + } + for (idx = 0; idx < IO_RANGES; idx++) { + iores[idx] = platform_get_resource(sparx5->pdev, IORESOURCE_MEM, + idx); + if (!iores[idx]) { + dev_err(sparx5->dev, "Invalid resource\n"); + return -EINVAL; + } + iomem[idx] = devm_ioremap(sparx5->dev, + iores[idx]->start, + iores[idx]->end - iores[idx]->start + + 1); + if (!iomem[idx]) { + dev_err(sparx5->dev, "Unable to get switch registers: %s\n", + iores[idx]->name); + return -ENOMEM; + } + begin[idx] = iomem[idx] - sparx5_main_iomap[range_id[idx]].offset; + } + for (jdx = 0; jdx < ARRAY_SIZE(sparx5_main_iomap); jdx++) { + const struct sparx5_main_io_resource *iomap = &sparx5_main_iomap[jdx]; + + sparx5->regs[iomap->id] = begin[iomap->range] + iomap->offset; + } + return 0; +} + +static int sparx5_create_port(struct sparx5 *sparx5, + struct initial_port_config *config) +{ + struct sparx5_port *spx5_port; + struct net_device *ndev; + struct phylink *phylink; + int err; + + ndev = sparx5_create_netdev(sparx5, config->portno); + if (IS_ERR(ndev)) { + dev_err(sparx5->dev, "Could not create net device: %02u\n", + config->portno); + return PTR_ERR(ndev); + } + spx5_port = netdev_priv(ndev); + spx5_port->of_node = config->node; + spx5_port->serdes = config->serdes; + spx5_port->pvid = NULL_VID; + spx5_port->signd_internal = true; + spx5_port->signd_active_high = true; + spx5_port->signd_enable = true; + spx5_port->max_vlan_tags = SPX5_PORT_MAX_TAGS_NONE; + spx5_port->vlan_type = SPX5_VLAN_PORT_TYPE_UNAWARE; + spx5_port->custom_etype = 0x8880; /* Vitesse */ + spx5_port->phylink_pcs.poll = true; + spx5_port->phylink_pcs.ops = &sparx5_phylink_pcs_ops; + sparx5->ports[config->portno] = spx5_port; + + err = sparx5_port_init(sparx5, spx5_port, &config->conf); + if (err) { + dev_err(sparx5->dev, "port init failed\n"); + return err; + } + spx5_port->conf = config->conf; + + /* Setup VLAN */ + sparx5_vlan_port_setup(sparx5, spx5_port->portno); + + /* Create a phylink for PHY management. Also handles SFPs */ + spx5_port->phylink_config.dev = &spx5_port->ndev->dev; + spx5_port->phylink_config.type = PHYLINK_NETDEV; + spx5_port->phylink_config.pcs_poll = true; + + phylink = phylink_create(&spx5_port->phylink_config, + of_fwnode_handle(config->node), + config->conf.phy_mode, + &sparx5_phylink_mac_ops); + if (IS_ERR(phylink)) + return PTR_ERR(phylink); + + spx5_port->phylink = phylink; + phylink_set_pcs(phylink, &spx5_port->phylink_pcs); + + return 0; +} + +static int sparx5_init_ram(struct sparx5 *s5) +{ + const struct sparx5_ram_config spx5_ram_cfg[] = { + {spx5_reg_get(s5, ANA_AC_STAT_RESET), ANA_AC_STAT_RESET_RESET}, + {spx5_reg_get(s5, ASM_STAT_CFG), ASM_STAT_CFG_STAT_CNT_CLR_SHOT}, + {spx5_reg_get(s5, QSYS_RAM_INIT), QSYS_RAM_INIT_RAM_INIT}, + {spx5_reg_get(s5, REW_RAM_INIT), QSYS_RAM_INIT_RAM_INIT}, + {spx5_reg_get(s5, VOP_RAM_INIT), QSYS_RAM_INIT_RAM_INIT}, + {spx5_reg_get(s5, ANA_AC_RAM_INIT), QSYS_RAM_INIT_RAM_INIT}, + {spx5_reg_get(s5, ASM_RAM_INIT), QSYS_RAM_INIT_RAM_INIT}, + {spx5_reg_get(s5, EACL_RAM_INIT), QSYS_RAM_INIT_RAM_INIT}, + {spx5_reg_get(s5, VCAP_SUPER_RAM_INIT), QSYS_RAM_INIT_RAM_INIT}, + {spx5_reg_get(s5, DSM_RAM_INIT), QSYS_RAM_INIT_RAM_INIT} + }; + const struct sparx5_ram_config *cfg; + u32 value, pending, jdx, idx; + + for (jdx = 0; jdx < 10; jdx++) { + pending = ARRAY_SIZE(spx5_ram_cfg); + for (idx = 0; idx < ARRAY_SIZE(spx5_ram_cfg); idx++) { + cfg = &spx5_ram_cfg[idx]; + if (jdx == 0) { + writel(cfg->init_val, cfg->init_reg); + } else { + value = readl(cfg->init_reg); + if ((value & cfg->init_val) != cfg->init_val) + pending--; + } + } + if (!pending) + break; + usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC); + } + + if (pending > 0) { + /* Still initializing, should be complete in + * less than 1ms + */ + dev_err(s5->dev, "Memory initialization error\n"); + return -EINVAL; + } + return 0; +} + +static int sparx5_init_switchcore(struct sparx5 *sparx5) +{ + u32 value; + int err = 0; + + spx5_rmw(EACL_POL_EACL_CFG_EACL_FORCE_INIT_SET(1), + EACL_POL_EACL_CFG_EACL_FORCE_INIT, + sparx5, + EACL_POL_EACL_CFG); + + spx5_rmw(EACL_POL_EACL_CFG_EACL_FORCE_INIT_SET(0), + EACL_POL_EACL_CFG_EACL_FORCE_INIT, + sparx5, + EACL_POL_EACL_CFG); + + /* Initialize memories, if not done already */ + value = spx5_rd(sparx5, HSCH_RESET_CFG); + if (!(value & HSCH_RESET_CFG_CORE_ENA)) { + err = sparx5_init_ram(sparx5); + if (err) + return err; + } + + /* Reset counters */ + spx5_wr(ANA_AC_STAT_RESET_RESET_SET(1), sparx5, ANA_AC_STAT_RESET); + spx5_wr(ASM_STAT_CFG_STAT_CNT_CLR_SHOT_SET(1), sparx5, ASM_STAT_CFG); + + /* Enable switch-core and queue system */ + spx5_wr(HSCH_RESET_CFG_CORE_ENA_SET(1), sparx5, HSCH_RESET_CFG); + + return 0; +} + +static int sparx5_init_coreclock(struct sparx5 *sparx5) +{ + enum sparx5_core_clockfreq freq = sparx5->coreclock; + u32 clk_div, clk_period, pol_upd_int, idx; + + /* Verify if core clock frequency is supported on target. + * If 'VTSS_CORE_CLOCK_DEFAULT' then the highest supported + * freq. is used + */ + switch (sparx5->target_ct) { + case SPX5_TARGET_CT_7546: + if (sparx5->coreclock == SPX5_CORE_CLOCK_DEFAULT) + freq = SPX5_CORE_CLOCK_250MHZ; + else if (sparx5->coreclock != SPX5_CORE_CLOCK_250MHZ) + freq = 0; /* Not supported */ + break; + case SPX5_TARGET_CT_7549: + case SPX5_TARGET_CT_7552: + case SPX5_TARGET_CT_7556: + if (sparx5->coreclock == SPX5_CORE_CLOCK_DEFAULT) + freq = SPX5_CORE_CLOCK_500MHZ; + else if (sparx5->coreclock != SPX5_CORE_CLOCK_500MHZ) + freq = 0; /* Not supported */ + break; + case SPX5_TARGET_CT_7558: + case SPX5_TARGET_CT_7558TSN: + if (sparx5->coreclock == SPX5_CORE_CLOCK_DEFAULT) + freq = SPX5_CORE_CLOCK_625MHZ; + else if (sparx5->coreclock != SPX5_CORE_CLOCK_625MHZ) + freq = 0; /* Not supported */ + break; + case SPX5_TARGET_CT_7546TSN: + if (sparx5->coreclock == SPX5_CORE_CLOCK_DEFAULT) + freq = SPX5_CORE_CLOCK_625MHZ; + break; + case SPX5_TARGET_CT_7549TSN: + case SPX5_TARGET_CT_7552TSN: + case SPX5_TARGET_CT_7556TSN: + if (sparx5->coreclock == SPX5_CORE_CLOCK_DEFAULT) + freq = SPX5_CORE_CLOCK_625MHZ; + else if (sparx5->coreclock == SPX5_CORE_CLOCK_250MHZ) + freq = 0; /* Not supported */ + break; + default: + dev_err(sparx5->dev, "Target (%#04x) not supported\n", + sparx5->target_ct); + return -ENODEV; + } + + switch (freq) { + case SPX5_CORE_CLOCK_250MHZ: + clk_div = 10; + pol_upd_int = 312; + break; + case SPX5_CORE_CLOCK_500MHZ: + clk_div = 5; + pol_upd_int = 624; + break; + case SPX5_CORE_CLOCK_625MHZ: + clk_div = 4; + pol_upd_int = 780; + break; + default: + dev_err(sparx5->dev, "%d coreclock not supported on (%#04x)\n", + sparx5->coreclock, sparx5->target_ct); + return -EINVAL; + } + + /* Update state with chosen frequency */ + sparx5->coreclock = freq; + + /* Configure the LCPLL */ + spx5_rmw(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_DIV_SET(clk_div) | + CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_PRE_DIV_SET(0) | + CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_DIR_SET(0) | + CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_SEL_SET(0) | + CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_ENA_SET(0) | + CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_ENA_SET(1), + CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_DIV | + CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_PRE_DIV | + CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_DIR | + CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_SEL | + CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_ENA | + CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_ENA, + sparx5, + CLKGEN_LCPLL1_CORE_CLK_CFG); + + clk_period = sparx5_clk_period(freq); + + spx5_rmw(HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS_SET(clk_period / 100), + HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS, + sparx5, + HSCH_SYS_CLK_PER); + + spx5_rmw(ANA_AC_POL_BDLB_DLB_CTRL_CLK_PERIOD_01NS_SET(clk_period / 100), + ANA_AC_POL_BDLB_DLB_CTRL_CLK_PERIOD_01NS, + sparx5, + ANA_AC_POL_BDLB_DLB_CTRL); + + spx5_rmw(ANA_AC_POL_SLB_DLB_CTRL_CLK_PERIOD_01NS_SET(clk_period / 100), + ANA_AC_POL_SLB_DLB_CTRL_CLK_PERIOD_01NS, + sparx5, + ANA_AC_POL_SLB_DLB_CTRL); + + spx5_rmw(LRN_AUTOAGE_CFG_1_CLK_PERIOD_01NS_SET(clk_period / 100), + LRN_AUTOAGE_CFG_1_CLK_PERIOD_01NS, + sparx5, + LRN_AUTOAGE_CFG_1); + + for (idx = 0; idx < 3; idx++) + spx5_rmw(GCB_SIO_CLOCK_SYS_CLK_PERIOD_SET(clk_period / 100), + GCB_SIO_CLOCK_SYS_CLK_PERIOD, + sparx5, + GCB_SIO_CLOCK(idx)); + + spx5_rmw(HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY_SET + ((256 * 1000) / clk_period), + HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY, + sparx5, + HSCH_TAS_STATEMACHINE_CFG); + + spx5_rmw(ANA_AC_POL_POL_UPD_INT_CFG_POL_UPD_INT_SET(pol_upd_int), + ANA_AC_POL_POL_UPD_INT_CFG_POL_UPD_INT, + sparx5, + ANA_AC_POL_POL_UPD_INT_CFG); + + return 0; +} + +static int sparx5_qlim_set(struct sparx5 *sparx5) +{ + u32 res, dp, prio; + + for (res = 0; res < 2; res++) { + for (prio = 0; prio < 8; prio++) + spx5_wr(0xFFF, sparx5, + QRES_RES_CFG(prio + 630 + res * 1024)); + + for (dp = 0; dp < 4; dp++) + spx5_wr(0xFFF, sparx5, + QRES_RES_CFG(dp + 638 + res * 1024)); + } + + /* Set 80,90,95,100% of memory size for top watermarks */ + spx5_wr(QLIM_WM(80), sparx5, XQS_QLIMIT_SHR_QLIM_CFG(0)); + spx5_wr(QLIM_WM(90), sparx5, XQS_QLIMIT_SHR_CTOP_CFG(0)); + spx5_wr(QLIM_WM(95), sparx5, XQS_QLIMIT_SHR_ATOP_CFG(0)); + spx5_wr(QLIM_WM(100), sparx5, XQS_QLIMIT_SHR_TOP_CFG(0)); + + return 0; +} + +/* Some boards needs to map the SGPIO for signal detect explicitly to the + * port module + */ +static void sparx5_board_init(struct sparx5 *sparx5) +{ + int idx; + + if (!sparx5->sd_sgpio_remapping) + return; + + /* Enable SGPIO Signal Detect remapping */ + spx5_rmw(GCB_HW_SGPIO_SD_CFG_SD_MAP_SEL, + GCB_HW_SGPIO_SD_CFG_SD_MAP_SEL, + sparx5, + GCB_HW_SGPIO_SD_CFG); + + /* Refer to LOS SGPIO */ + for (idx = 0; idx < SPX5_PORTS; idx++) + if (sparx5->ports[idx]) + if (sparx5->ports[idx]->conf.sd_sgpio != ~0) + spx5_wr(sparx5->ports[idx]->conf.sd_sgpio, + sparx5, + GCB_HW_SGPIO_TO_SD_MAP_CFG(idx)); +} + +static int sparx5_start(struct sparx5 *sparx5) +{ + u8 broadcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; + char queue_name[32]; + u32 idx; + int err; + + /* Setup own UPSIDs */ + for (idx = 0; idx < 3; idx++) { + spx5_wr(idx, sparx5, ANA_AC_OWN_UPSID(idx)); + spx5_wr(idx, sparx5, ANA_CL_OWN_UPSID(idx)); + spx5_wr(idx, sparx5, ANA_L2_OWN_UPSID(idx)); + spx5_wr(idx, sparx5, REW_OWN_UPSID(idx)); + } + + /* Enable CPU ports */ + for (idx = SPX5_PORTS; idx < SPX5_PORTS_ALL; idx++) + spx5_rmw(QFWD_SWITCH_PORT_MODE_PORT_ENA_SET(1), + QFWD_SWITCH_PORT_MODE_PORT_ENA, + sparx5, + QFWD_SWITCH_PORT_MODE(idx)); + + /* Init masks */ + sparx5_update_fwd(sparx5); + + /* CPU copy CPU pgids */ + spx5_wr(ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA_SET(1), + sparx5, ANA_AC_PGID_MISC_CFG(PGID_CPU)); + spx5_wr(ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA_SET(1), + sparx5, ANA_AC_PGID_MISC_CFG(PGID_BCAST)); + + /* Recalc injected frame FCS */ + for (idx = SPX5_PORT_CPU_0; idx <= SPX5_PORT_CPU_1; idx++) + spx5_rmw(ANA_CL_FILTER_CTRL_FORCE_FCS_UPDATE_ENA_SET(1), + ANA_CL_FILTER_CTRL_FORCE_FCS_UPDATE_ENA, + sparx5, ANA_CL_FILTER_CTRL(idx)); + + /* Init MAC table, ageing */ + sparx5_mact_init(sparx5); + + /* Setup VLANs */ + sparx5_vlan_init(sparx5); + + /* Add host mode BC address (points only to CPU) */ + sparx5_mact_learn(sparx5, PGID_CPU, broadcast, NULL_VID); + + /* Enable queue limitation watermarks */ + sparx5_qlim_set(sparx5); + + err = sparx5_config_auto_calendar(sparx5); + if (err) + return err; + + err = sparx5_config_dsm_calendar(sparx5); + if (err) + return err; + + /* Init stats */ + err = sparx_stats_init(sparx5); + if (err) + return err; + + /* Init mact_sw struct */ + mutex_init(&sparx5->mact_lock); + INIT_LIST_HEAD(&sparx5->mact_entries); + snprintf(queue_name, sizeof(queue_name), "%s-mact", + dev_name(sparx5->dev)); + sparx5->mact_queue = create_singlethread_workqueue(queue_name); + INIT_DELAYED_WORK(&sparx5->mact_work, sparx5_mact_pull_work); + queue_delayed_work(sparx5->mact_queue, &sparx5->mact_work, + SPX5_MACT_PULL_DELAY); + + err = sparx5_register_netdevs(sparx5); + if (err) + return err; + + sparx5_board_init(sparx5); + err = sparx5_register_notifier_blocks(sparx5); + + /* Start register based INJ/XTR */ + err = -ENXIO; + if (err && sparx5->xtr_irq >= 0) { + err = devm_request_irq(sparx5->dev, sparx5->xtr_irq, + sparx5_xtr_handler, IRQF_SHARED, + "sparx5-xtr", sparx5); + if (!err) + err = sparx5_manual_injection_mode(sparx5); + if (err) + sparx5->xtr_irq = -ENXIO; + } else { + sparx5->xtr_irq = -ENXIO; + } + return err; +} + +static void sparx5_cleanup_ports(struct sparx5 *sparx5) +{ + sparx5_unregister_netdevs(sparx5); + sparx5_destroy_netdevs(sparx5); +} + +static int mchp_sparx5_probe(struct platform_device *pdev) +{ + struct initial_port_config *configs, *config; + struct device_node *np = pdev->dev.of_node; + struct device_node *ports, *portnp; + struct reset_control *reset; + struct sparx5 *sparx5; + int idx = 0, err = 0; + + if (!np && !pdev->dev.platform_data) + return -ENODEV; + + sparx5 = devm_kzalloc(&pdev->dev, sizeof(*sparx5), GFP_KERNEL); + if (!sparx5) + return -ENOMEM; + + platform_set_drvdata(pdev, sparx5); + sparx5->pdev = pdev; + sparx5->dev = &pdev->dev; + + /* Do switch core reset if available */ + reset = devm_reset_control_get_optional_shared(&pdev->dev, "switch"); + if (IS_ERR(reset)) + return dev_err_probe(&pdev->dev, PTR_ERR(reset), + "Failed to get switch reset controller.\n"); + reset_control_reset(reset); + + /* Default values, some from DT */ + sparx5->coreclock = SPX5_CORE_CLOCK_DEFAULT; + + ports = of_get_child_by_name(np, "ethernet-ports"); + if (!ports) { + dev_err(sparx5->dev, "no ethernet-ports child node found\n"); + return -ENODEV; + } + sparx5->port_count = of_get_child_count(ports); + + configs = kcalloc(sparx5->port_count, + sizeof(struct initial_port_config), GFP_KERNEL); + if (!configs) { + err = -ENOMEM; + goto cleanup_pnode; + } + + for_each_available_child_of_node(ports, portnp) { + struct sparx5_port_config *conf; + struct phy *serdes; + u32 portno; + + err = of_property_read_u32(portnp, "reg", &portno); + if (err) { + dev_err(sparx5->dev, "port reg property error\n"); + continue; + } + config = &configs[idx]; + conf = &config->conf; + conf->speed = SPEED_UNKNOWN; + conf->bandwidth = SPEED_UNKNOWN; + err = of_get_phy_mode(portnp, &conf->phy_mode); + if (err) { + dev_err(sparx5->dev, "port %u: missing phy-mode\n", + portno); + continue; + } + err = of_property_read_u32(portnp, "microchip,bandwidth", + &conf->bandwidth); + if (err) { + dev_err(sparx5->dev, "port %u: missing bandwidth\n", + portno); + continue; + } + err = of_property_read_u32(portnp, "microchip,sd-sgpio", &conf->sd_sgpio); + if (err) + conf->sd_sgpio = ~0; + else + sparx5->sd_sgpio_remapping = true; + serdes = devm_of_phy_get(sparx5->dev, portnp, NULL); + if (IS_ERR(serdes)) { + err = dev_err_probe(sparx5->dev, PTR_ERR(serdes), + "port %u: missing serdes\n", + portno); + goto cleanup_config; + } + config->portno = portno; + config->node = portnp; + config->serdes = serdes; + + conf->media = PHY_MEDIA_DAC; + conf->serdes_reset = true; + conf->portmode = conf->phy_mode; + conf->power_down = true; + idx++; + } + + err = sparx5_create_targets(sparx5); + if (err) + goto cleanup_config; + + if (!of_get_mac_address(np, sparx5->base_mac)) { + dev_info(sparx5->dev, "MAC addr was not set, use random MAC\n"); + eth_random_addr(sparx5->base_mac); + sparx5->base_mac[5] = 0; + } + + sparx5->xtr_irq = platform_get_irq_byname(sparx5->pdev, "xtr"); + + /* Read chip ID to check CPU interface */ + sparx5->chip_id = spx5_rd(sparx5, GCB_CHIP_ID); + + sparx5->target_ct = (enum spx5_target_chiptype) + GCB_CHIP_ID_PART_ID_GET(sparx5->chip_id); + + /* Initialize Switchcore and internal RAMs */ + err = sparx5_init_switchcore(sparx5); + if (err) { + dev_err(sparx5->dev, "Switchcore initialization error\n"); + goto cleanup_config; + } + + /* Initialize the LC-PLL (core clock) and set affected registers */ + err = sparx5_init_coreclock(sparx5); + if (err) { + dev_err(sparx5->dev, "LC-PLL initialization error\n"); + goto cleanup_config; + } + + for (idx = 0; idx < sparx5->port_count; ++idx) { + config = &configs[idx]; + if (!config->node) + continue; + + err = sparx5_create_port(sparx5, config); + if (err) { + dev_err(sparx5->dev, "port create error\n"); + goto cleanup_ports; + } + } + + err = sparx5_start(sparx5); + if (err) { + dev_err(sparx5->dev, "Start failed\n"); + goto cleanup_ports; + } + goto cleanup_config; + +cleanup_ports: + sparx5_cleanup_ports(sparx5); +cleanup_config: + kfree(configs); +cleanup_pnode: + of_node_put(ports); + return err; +} + +static int mchp_sparx5_remove(struct platform_device *pdev) +{ + struct sparx5 *sparx5 = platform_get_drvdata(pdev); + + if (sparx5->xtr_irq) { + disable_irq(sparx5->xtr_irq); + sparx5->xtr_irq = -ENXIO; + } + sparx5_cleanup_ports(sparx5); + /* Unregister netdevs */ + sparx5_unregister_notifier_blocks(sparx5); + + return 0; +} + +static const struct of_device_id mchp_sparx5_match[] = { + { .compatible = "microchip,sparx5-switch" }, + { } +}; +MODULE_DEVICE_TABLE(of, mchp_sparx5_match); + +static struct platform_driver mchp_sparx5_driver = { + .probe = mchp_sparx5_probe, + .remove = mchp_sparx5_remove, + .driver = { + .name = "sparx5-switch", + .of_match_table = mchp_sparx5_match, + }, +}; + +module_platform_driver(mchp_sparx5_driver); + +MODULE_DESCRIPTION("Microchip Sparx5 switch driver"); +MODULE_AUTHOR("Steen Hegelund "); +MODULE_LICENSE("Dual MIT/GPL"); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h new file mode 100644 index 000000000000..4d5f44c3a421 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -0,0 +1,375 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries. + */ + +#ifndef __SPARX5_MAIN_H__ +#define __SPARX5_MAIN_H__ + +#include +#include +#include +#include +#include +#include +#include +#include + +/* Target chip type */ +enum spx5_target_chiptype { + SPX5_TARGET_CT_7546 = 0x7546, /* SparX-5-64 Enterprise */ + SPX5_TARGET_CT_7549 = 0x7549, /* SparX-5-90 Enterprise */ + SPX5_TARGET_CT_7552 = 0x7552, /* SparX-5-128 Enterprise */ + SPX5_TARGET_CT_7556 = 0x7556, /* SparX-5-160 Enterprise */ + SPX5_TARGET_CT_7558 = 0x7558, /* SparX-5-200 Enterprise */ + SPX5_TARGET_CT_7546TSN = 0x47546, /* SparX-5-64i Industrial */ + SPX5_TARGET_CT_7549TSN = 0x47549, /* SparX-5-90i Industrial */ + SPX5_TARGET_CT_7552TSN = 0x47552, /* SparX-5-128i Industrial */ + SPX5_TARGET_CT_7556TSN = 0x47556, /* SparX-5-160i Industrial */ + SPX5_TARGET_CT_7558TSN = 0x47558, /* SparX-5-200i Industrial */ +}; + +enum sparx5_port_max_tags { + SPX5_PORT_MAX_TAGS_NONE, /* No extra tags allowed */ + SPX5_PORT_MAX_TAGS_ONE, /* Single tag allowed */ + SPX5_PORT_MAX_TAGS_TWO /* Single and double tag allowed */ +}; + +enum sparx5_vlan_port_type { + SPX5_VLAN_PORT_TYPE_UNAWARE, /* VLAN unaware port */ + SPX5_VLAN_PORT_TYPE_C, /* C-port */ + SPX5_VLAN_PORT_TYPE_S, /* S-port */ + SPX5_VLAN_PORT_TYPE_S_CUSTOM /* S-port using custom type */ +}; + +#define SPX5_PORTS 65 +#define SPX5_PORT_CPU (SPX5_PORTS) /* Next port is CPU port */ +#define SPX5_PORT_CPU_0 (SPX5_PORT_CPU + 0) /* CPU Port 65 */ +#define SPX5_PORT_CPU_1 (SPX5_PORT_CPU + 1) /* CPU Port 66 */ +#define SPX5_PORT_VD0 (SPX5_PORT_CPU + 2) /* VD0/Port 67 used for IPMC */ +#define SPX5_PORT_VD1 (SPX5_PORT_CPU + 3) /* VD1/Port 68 used for AFI/OAM */ +#define SPX5_PORT_VD2 (SPX5_PORT_CPU + 4) /* VD2/Port 69 used for IPinIP*/ +#define SPX5_PORTS_ALL (SPX5_PORT_CPU + 5) /* Total number of ports */ + +#define PGID_BASE SPX5_PORTS /* Starts after port PGIDs */ +#define PGID_UC_FLOOD (PGID_BASE + 0) +#define PGID_MC_FLOOD (PGID_BASE + 1) +#define PGID_IPV4_MC_DATA (PGID_BASE + 2) +#define PGID_IPV4_MC_CTRL (PGID_BASE + 3) +#define PGID_IPV6_MC_DATA (PGID_BASE + 4) +#define PGID_IPV6_MC_CTRL (PGID_BASE + 5) +#define PGID_BCAST (PGID_BASE + 6) +#define PGID_CPU (PGID_BASE + 7) + +#define IFH_LEN 9 /* 36 bytes */ +#define NULL_VID 0 +#define SPX5_MACT_PULL_DELAY (2 * HZ) +#define SPX5_STATS_CHECK_DELAY (1 * HZ) +#define SPX5_PRIOS 8 /* Number of priority queues */ +#define SPX5_BUFFER_CELL_SZ 184 /* Cell size */ +#define SPX5_BUFFER_MEMORY 4194280 /* 22795 words * 184 bytes */ + +#define XTR_QUEUE 0 +#define INJ_QUEUE 0 + +struct sparx5; + +struct sparx5_port_config { + phy_interface_t portmode; + u32 bandwidth; + int speed; + int duplex; + enum phy_media media; + bool inband; + bool power_down; + bool autoneg; + bool serdes_reset; + u32 pause; + u32 pause_adv; + phy_interface_t phy_mode; + u32 sd_sgpio; +}; + +struct sparx5_port { + struct net_device *ndev; + struct sparx5 *sparx5; + struct device_node *of_node; + struct phy *serdes; + struct sparx5_port_config conf; + struct phylink_config phylink_config; + struct phylink *phylink; + struct phylink_pcs phylink_pcs; + u16 portno; + /* Ingress default VLAN (pvid) */ + u16 pvid; + /* Egress default VLAN (vid) */ + u16 vid; + bool signd_internal; + bool signd_active_high; + bool signd_enable; + bool flow_control; + enum sparx5_port_max_tags max_vlan_tags; + enum sparx5_vlan_port_type vlan_type; + u32 custom_etype; + u32 ifh[IFH_LEN]; + bool vlan_aware; + struct hrtimer inj_timer; +}; + +enum sparx5_core_clockfreq { + SPX5_CORE_CLOCK_DEFAULT, /* Defaults to the highest supported frequency */ + SPX5_CORE_CLOCK_250MHZ, /* 250MHZ core clock frequency */ + SPX5_CORE_CLOCK_500MHZ, /* 500MHZ core clock frequency */ + SPX5_CORE_CLOCK_625MHZ, /* 625MHZ core clock frequency */ +}; + +struct sparx5 { + struct platform_device *pdev; + struct device *dev; + u32 chip_id; + enum spx5_target_chiptype target_ct; + void __iomem *regs[NUM_TARGETS]; + int port_count; + struct mutex lock; /* MAC reg lock */ + /* port structures are in net device */ + struct sparx5_port *ports[SPX5_PORTS]; + enum sparx5_core_clockfreq coreclock; + /* Statistics */ + u32 num_stats; + u32 num_ethtool_stats; + const char * const *stats_layout; + u64 *stats; + /* Workqueue for reading stats */ + struct mutex queue_stats_lock; + struct delayed_work stats_work; + struct workqueue_struct *stats_queue; + /* Notifiers */ + struct notifier_block netdevice_nb; + struct notifier_block switchdev_nb; + struct notifier_block switchdev_blocking_nb; + /* Switch state */ + u8 base_mac[ETH_ALEN]; + /* Associated bridge device (when bridged) */ + struct net_device *hw_bridge_dev; + /* Bridged interfaces */ + DECLARE_BITMAP(bridge_mask, SPX5_PORTS); + DECLARE_BITMAP(bridge_fwd_mask, SPX5_PORTS); + DECLARE_BITMAP(bridge_lrn_mask, SPX5_PORTS); + DECLARE_BITMAP(vlan_mask[VLAN_N_VID], SPX5_PORTS); + /* SW MAC table */ + struct list_head mact_entries; + /* mac table list (mact_entries) mutex */ + struct mutex mact_lock; + struct delayed_work mact_work; + struct workqueue_struct *mact_queue; + /* Board specifics */ + bool sd_sgpio_remapping; + /* Register based inj/xtr */ + int xtr_irq; +}; + +/* sparx5_switchdev.c */ +int sparx5_register_notifier_blocks(struct sparx5 *sparx5); +void sparx5_unregister_notifier_blocks(struct sparx5 *sparx5); + +/* sparx5_packet.c */ +irqreturn_t sparx5_xtr_handler(int irq, void *_priv); +int sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev); +int sparx5_manual_injection_mode(struct sparx5 *sparx5); +void sparx5_port_inj_timer_setup(struct sparx5_port *port); + +/* sparx5_mactable.c */ +void sparx5_mact_pull_work(struct work_struct *work); +int sparx5_mact_learn(struct sparx5 *sparx5, int port, + const unsigned char mac[ETH_ALEN], u16 vid); +bool sparx5_mact_getnext(struct sparx5 *sparx5, + unsigned char mac[ETH_ALEN], u16 *vid, u32 *pcfg2); +int sparx5_mact_forget(struct sparx5 *sparx5, + const unsigned char mac[ETH_ALEN], u16 vid); +int sparx5_add_mact_entry(struct sparx5 *sparx5, + struct sparx5_port *port, + const unsigned char *addr, u16 vid); +int sparx5_del_mact_entry(struct sparx5 *sparx5, + const unsigned char *addr, + u16 vid); +int sparx5_mc_sync(struct net_device *dev, const unsigned char *addr); +int sparx5_mc_unsync(struct net_device *dev, const unsigned char *addr); +void sparx5_set_ageing(struct sparx5 *sparx5, int msecs); +void sparx5_mact_init(struct sparx5 *sparx5); + +/* sparx5_vlan.c */ +void sparx5_pgid_update_mask(struct sparx5_port *port, int pgid, bool enable); +void sparx5_update_fwd(struct sparx5 *sparx5); +void sparx5_vlan_init(struct sparx5 *sparx5); +void sparx5_vlan_port_setup(struct sparx5 *sparx5, int portno); +int sparx5_vlan_vid_add(struct sparx5_port *port, u16 vid, bool pvid, + bool untagged); +int sparx5_vlan_vid_del(struct sparx5_port *port, u16 vid); +void sparx5_vlan_port_apply(struct sparx5 *sparx5, struct sparx5_port *port); + +/* sparx5_calendar.c */ +int sparx5_config_auto_calendar(struct sparx5 *sparx5); +int sparx5_config_dsm_calendar(struct sparx5 *sparx5); + +/* sparx5_ethtool.c */ +void sparx5_get_stats64(struct net_device *ndev, struct rtnl_link_stats64 *stats); +int sparx_stats_init(struct sparx5 *sparx5); + +/* sparx5_netdev.c */ +bool sparx5_netdevice_check(const struct net_device *dev); +struct net_device *sparx5_create_netdev(struct sparx5 *sparx5, u32 portno); +int sparx5_register_netdevs(struct sparx5 *sparx5); +void sparx5_destroy_netdevs(struct sparx5 *sparx5); +void sparx5_unregister_netdevs(struct sparx5 *sparx5); + +/* Clock period in picoseconds */ +static inline u32 sparx5_clk_period(enum sparx5_core_clockfreq cclock) +{ + switch (cclock) { + case SPX5_CORE_CLOCK_250MHZ: + return 4000; + case SPX5_CORE_CLOCK_500MHZ: + return 2000; + case SPX5_CORE_CLOCK_625MHZ: + default: + return 1600; + } +} + +static inline bool sparx5_is_baser(phy_interface_t interface) +{ + return interface == PHY_INTERFACE_MODE_5GBASER || + interface == PHY_INTERFACE_MODE_10GBASER || + interface == PHY_INTERFACE_MODE_25GBASER; +} + +extern const struct phylink_mac_ops sparx5_phylink_mac_ops; +extern const struct phylink_pcs_ops sparx5_phylink_pcs_ops; +extern const struct ethtool_ops sparx5_ethtool_ops; + +/* Calculate raw offset */ +static inline __pure int spx5_offset(int id, int tinst, int tcnt, + int gbase, int ginst, + int gcnt, int gwidth, + int raddr, int rinst, + int rcnt, int rwidth) +{ + WARN_ON((tinst) >= tcnt); + WARN_ON((ginst) >= gcnt); + WARN_ON((rinst) >= rcnt); + return gbase + ((ginst) * gwidth) + + raddr + ((rinst) * rwidth); +} + +/* Read, Write and modify registers content. + * The register definition macros start at the id + */ +static inline void __iomem *spx5_addr(void __iomem *base[], + int id, int tinst, int tcnt, + int gbase, int ginst, + int gcnt, int gwidth, + int raddr, int rinst, + int rcnt, int rwidth) +{ + WARN_ON((tinst) >= tcnt); + WARN_ON((ginst) >= gcnt); + WARN_ON((rinst) >= rcnt); + return base[id + (tinst)] + + gbase + ((ginst) * gwidth) + + raddr + ((rinst) * rwidth); +} + +static inline void __iomem *spx5_inst_addr(void __iomem *base, + int gbase, int ginst, + int gcnt, int gwidth, + int raddr, int rinst, + int rcnt, int rwidth) +{ + WARN_ON((ginst) >= gcnt); + WARN_ON((rinst) >= rcnt); + return base + + gbase + ((ginst) * gwidth) + + raddr + ((rinst) * rwidth); +} + +static inline u32 spx5_rd(struct sparx5 *sparx5, int id, int tinst, int tcnt, + int gbase, int ginst, int gcnt, int gwidth, + int raddr, int rinst, int rcnt, int rwidth) +{ + return readl(spx5_addr(sparx5->regs, id, tinst, tcnt, gbase, ginst, + gcnt, gwidth, raddr, rinst, rcnt, rwidth)); +} + +static inline u32 spx5_inst_rd(void __iomem *iomem, int id, int tinst, int tcnt, + int gbase, int ginst, int gcnt, int gwidth, + int raddr, int rinst, int rcnt, int rwidth) +{ + return readl(spx5_inst_addr(iomem, gbase, ginst, + gcnt, gwidth, raddr, rinst, rcnt, rwidth)); +} + +static inline void spx5_wr(u32 val, struct sparx5 *sparx5, + int id, int tinst, int tcnt, + int gbase, int ginst, int gcnt, int gwidth, + int raddr, int rinst, int rcnt, int rwidth) +{ + writel(val, spx5_addr(sparx5->regs, id, tinst, tcnt, + gbase, ginst, gcnt, gwidth, + raddr, rinst, rcnt, rwidth)); +} + +static inline void spx5_inst_wr(u32 val, void __iomem *iomem, + int id, int tinst, int tcnt, + int gbase, int ginst, int gcnt, int gwidth, + int raddr, int rinst, int rcnt, int rwidth) +{ + writel(val, spx5_inst_addr(iomem, + gbase, ginst, gcnt, gwidth, + raddr, rinst, rcnt, rwidth)); +} + +static inline void spx5_rmw(u32 val, u32 mask, struct sparx5 *sparx5, + int id, int tinst, int tcnt, + int gbase, int ginst, int gcnt, int gwidth, + int raddr, int rinst, int rcnt, int rwidth) +{ + u32 nval; + + nval = readl(spx5_addr(sparx5->regs, id, tinst, tcnt, gbase, ginst, + gcnt, gwidth, raddr, rinst, rcnt, rwidth)); + nval = (nval & ~mask) | (val & mask); + writel(nval, spx5_addr(sparx5->regs, id, tinst, tcnt, gbase, ginst, + gcnt, gwidth, raddr, rinst, rcnt, rwidth)); +} + +static inline void spx5_inst_rmw(u32 val, u32 mask, void __iomem *iomem, + int id, int tinst, int tcnt, + int gbase, int ginst, int gcnt, int gwidth, + int raddr, int rinst, int rcnt, int rwidth) +{ + u32 nval; + + nval = readl(spx5_inst_addr(iomem, gbase, ginst, gcnt, gwidth, raddr, + rinst, rcnt, rwidth)); + nval = (nval & ~mask) | (val & mask); + writel(nval, spx5_inst_addr(iomem, gbase, ginst, gcnt, gwidth, raddr, + rinst, rcnt, rwidth)); +} + +static inline void __iomem *spx5_inst_get(struct sparx5 *sparx5, int id, int tinst) +{ + return sparx5->regs[id + tinst]; +} + +static inline void __iomem *spx5_reg_get(struct sparx5 *sparx5, + int id, int tinst, int tcnt, + int gbase, int ginst, int gcnt, int gwidth, + int raddr, int rinst, int rcnt, int rwidth) +{ + return spx5_addr(sparx5->regs, id, tinst, tcnt, + gbase, ginst, gcnt, gwidth, + raddr, rinst, rcnt, rwidth); +} + +#endif /* __SPARX5_MAIN_H__ */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h new file mode 100644 index 000000000000..5ab2373a7178 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h @@ -0,0 +1,4642 @@ +/* SPDX-License-Identifier: GPL-2.0+ + * Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. + */ + +/* This file is autogenerated by cml-utils 2021-05-06 13:06:37 +0200. + * Commit ID: 9ae4ec441e25e4b9003f4e514df5cb12a36b84d3 + */ + +#ifndef _SPARX5_MAIN_REGS_H_ +#define _SPARX5_MAIN_REGS_H_ + +#include +#include +#include + +enum sparx5_target { + TARGET_ANA_AC = 1, + TARGET_ANA_ACL = 2, + TARGET_ANA_AC_POL = 4, + TARGET_ANA_CL = 6, + TARGET_ANA_L2 = 7, + TARGET_ANA_L3 = 8, + TARGET_ASM = 9, + TARGET_CLKGEN = 11, + TARGET_CPU = 12, + TARGET_DEV10G = 17, + TARGET_DEV25G = 29, + TARGET_DEV2G5 = 37, + TARGET_DEV5G = 102, + TARGET_DSM = 115, + TARGET_EACL = 116, + TARGET_FDMA = 117, + TARGET_GCB = 118, + TARGET_HSCH = 119, + TARGET_LRN = 122, + TARGET_PCEP = 129, + TARGET_PCS10G_BR = 132, + TARGET_PCS25G_BR = 144, + TARGET_PCS5G_BR = 160, + TARGET_PORT_CONF = 173, + TARGET_QFWD = 175, + TARGET_QRES = 176, + TARGET_QS = 177, + TARGET_QSYS = 178, + TARGET_REW = 179, + TARGET_VCAP_SUPER = 326, + TARGET_VOP = 327, + TARGET_XQS = 331, + NUM_TARGETS = 332 +}; + +#define __REG(...) __VA_ARGS__ + +/* ANA_AC:RAM_CTRL:RAM_INIT */ +#define ANA_AC_RAM_INIT __REG(TARGET_ANA_AC, 0, 1, 839108, 0, 1, 4, 0, 0, 1, 4) + +#define ANA_AC_RAM_INIT_RAM_INIT BIT(1) +#define ANA_AC_RAM_INIT_RAM_INIT_SET(x)\ + FIELD_PREP(ANA_AC_RAM_INIT_RAM_INIT, x) +#define ANA_AC_RAM_INIT_RAM_INIT_GET(x)\ + FIELD_GET(ANA_AC_RAM_INIT_RAM_INIT, x) + +#define ANA_AC_RAM_INIT_RAM_CFG_HOOK BIT(0) +#define ANA_AC_RAM_INIT_RAM_CFG_HOOK_SET(x)\ + FIELD_PREP(ANA_AC_RAM_INIT_RAM_CFG_HOOK, x) +#define ANA_AC_RAM_INIT_RAM_CFG_HOOK_GET(x)\ + FIELD_GET(ANA_AC_RAM_INIT_RAM_CFG_HOOK, x) + +/* ANA_AC:PS_COMMON:OWN_UPSID */ +#define ANA_AC_OWN_UPSID(r) __REG(TARGET_ANA_AC, 0, 1, 894472, 0, 1, 352, 52, r, 3, 4) + +#define ANA_AC_OWN_UPSID_OWN_UPSID GENMASK(4, 0) +#define ANA_AC_OWN_UPSID_OWN_UPSID_SET(x)\ + FIELD_PREP(ANA_AC_OWN_UPSID_OWN_UPSID, x) +#define ANA_AC_OWN_UPSID_OWN_UPSID_GET(x)\ + FIELD_GET(ANA_AC_OWN_UPSID_OWN_UPSID, x) + +/* ANA_AC:SRC:SRC_CFG */ +#define ANA_AC_SRC_CFG(g) __REG(TARGET_ANA_AC, 0, 1, 849920, g, 102, 16, 0, 0, 1, 4) + +/* ANA_AC:SRC:SRC_CFG1 */ +#define ANA_AC_SRC_CFG1(g) __REG(TARGET_ANA_AC, 0, 1, 849920, g, 102, 16, 4, 0, 1, 4) + +/* ANA_AC:SRC:SRC_CFG2 */ +#define ANA_AC_SRC_CFG2(g) __REG(TARGET_ANA_AC, 0, 1, 849920, g, 102, 16, 8, 0, 1, 4) + +#define ANA_AC_SRC_CFG2_PORT_MASK2 BIT(0) +#define ANA_AC_SRC_CFG2_PORT_MASK2_SET(x)\ + FIELD_PREP(ANA_AC_SRC_CFG2_PORT_MASK2, x) +#define ANA_AC_SRC_CFG2_PORT_MASK2_GET(x)\ + FIELD_GET(ANA_AC_SRC_CFG2_PORT_MASK2, x) + +/* ANA_AC:PGID:PGID_CFG */ +#define ANA_AC_PGID_CFG(g) __REG(TARGET_ANA_AC, 0, 1, 786432, g, 3290, 16, 0, 0, 1, 4) + +/* ANA_AC:PGID:PGID_CFG1 */ +#define ANA_AC_PGID_CFG1(g) __REG(TARGET_ANA_AC, 0, 1, 786432, g, 3290, 16, 4, 0, 1, 4) + +/* ANA_AC:PGID:PGID_CFG2 */ +#define ANA_AC_PGID_CFG2(g) __REG(TARGET_ANA_AC, 0, 1, 786432, g, 3290, 16, 8, 0, 1, 4) + +#define ANA_AC_PGID_CFG2_PORT_MASK2 BIT(0) +#define ANA_AC_PGID_CFG2_PORT_MASK2_SET(x)\ + FIELD_PREP(ANA_AC_PGID_CFG2_PORT_MASK2, x) +#define ANA_AC_PGID_CFG2_PORT_MASK2_GET(x)\ + FIELD_GET(ANA_AC_PGID_CFG2_PORT_MASK2, x) + +/* ANA_AC:PGID:PGID_MISC_CFG */ +#define ANA_AC_PGID_MISC_CFG(g) __REG(TARGET_ANA_AC, 0, 1, 786432, g, 3290, 16, 12, 0, 1, 4) + +#define ANA_AC_PGID_MISC_CFG_PGID_CPU_QU GENMASK(6, 4) +#define ANA_AC_PGID_MISC_CFG_PGID_CPU_QU_SET(x)\ + FIELD_PREP(ANA_AC_PGID_MISC_CFG_PGID_CPU_QU, x) +#define ANA_AC_PGID_MISC_CFG_PGID_CPU_QU_GET(x)\ + FIELD_GET(ANA_AC_PGID_MISC_CFG_PGID_CPU_QU, x) + +#define ANA_AC_PGID_MISC_CFG_STACK_TYPE_ENA BIT(1) +#define ANA_AC_PGID_MISC_CFG_STACK_TYPE_ENA_SET(x)\ + FIELD_PREP(ANA_AC_PGID_MISC_CFG_STACK_TYPE_ENA, x) +#define ANA_AC_PGID_MISC_CFG_STACK_TYPE_ENA_GET(x)\ + FIELD_GET(ANA_AC_PGID_MISC_CFG_STACK_TYPE_ENA, x) + +#define ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA BIT(0) +#define ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA_SET(x)\ + FIELD_PREP(ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA, x) +#define ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA_GET(x)\ + FIELD_GET(ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA, x) + +/* ANA_AC:STAT_GLOBAL_CFG_PORT:STAT_GLOBAL_EVENT_MASK */ +#define ANA_AC_PORT_SGE_CFG(r) __REG(TARGET_ANA_AC, 0, 1, 851552, 0, 1, 20, 0, r, 4, 4) + +#define ANA_AC_PORT_SGE_CFG_MASK GENMASK(15, 0) +#define ANA_AC_PORT_SGE_CFG_MASK_SET(x)\ + FIELD_PREP(ANA_AC_PORT_SGE_CFG_MASK, x) +#define ANA_AC_PORT_SGE_CFG_MASK_GET(x)\ + FIELD_GET(ANA_AC_PORT_SGE_CFG_MASK, x) + +/* ANA_AC:STAT_GLOBAL_CFG_PORT:STAT_RESET */ +#define ANA_AC_STAT_RESET __REG(TARGET_ANA_AC, 0, 1, 851552, 0, 1, 20, 16, 0, 1, 4) + +#define ANA_AC_STAT_RESET_RESET BIT(0) +#define ANA_AC_STAT_RESET_RESET_SET(x)\ + FIELD_PREP(ANA_AC_STAT_RESET_RESET, x) +#define ANA_AC_STAT_RESET_RESET_GET(x)\ + FIELD_GET(ANA_AC_STAT_RESET_RESET, x) + +/* ANA_AC:STAT_CNT_CFG_PORT:STAT_CFG */ +#define ANA_AC_PORT_STAT_CFG(g, r) __REG(TARGET_ANA_AC, 0, 1, 843776, g, 70, 64, 4, r, 4, 4) + +#define ANA_AC_PORT_STAT_CFG_CFG_PRIO_MASK GENMASK(11, 4) +#define ANA_AC_PORT_STAT_CFG_CFG_PRIO_MASK_SET(x)\ + FIELD_PREP(ANA_AC_PORT_STAT_CFG_CFG_PRIO_MASK, x) +#define ANA_AC_PORT_STAT_CFG_CFG_PRIO_MASK_GET(x)\ + FIELD_GET(ANA_AC_PORT_STAT_CFG_CFG_PRIO_MASK, x) + +#define ANA_AC_PORT_STAT_CFG_CFG_CNT_FRM_TYPE GENMASK(3, 1) +#define ANA_AC_PORT_STAT_CFG_CFG_CNT_FRM_TYPE_SET(x)\ + FIELD_PREP(ANA_AC_PORT_STAT_CFG_CFG_CNT_FRM_TYPE, x) +#define ANA_AC_PORT_STAT_CFG_CFG_CNT_FRM_TYPE_GET(x)\ + FIELD_GET(ANA_AC_PORT_STAT_CFG_CFG_CNT_FRM_TYPE, x) + +#define ANA_AC_PORT_STAT_CFG_CFG_CNT_BYTE BIT(0) +#define ANA_AC_PORT_STAT_CFG_CFG_CNT_BYTE_SET(x)\ + FIELD_PREP(ANA_AC_PORT_STAT_CFG_CFG_CNT_BYTE, x) +#define ANA_AC_PORT_STAT_CFG_CFG_CNT_BYTE_GET(x)\ + FIELD_GET(ANA_AC_PORT_STAT_CFG_CFG_CNT_BYTE, x) + +/* ANA_AC:STAT_CNT_CFG_PORT:STAT_LSB_CNT */ +#define ANA_AC_PORT_STAT_LSB_CNT(g, r) __REG(TARGET_ANA_AC, 0, 1, 843776, g, 70, 64, 20, r, 4, 4) + +/* ANA_ACL:COMMON:OWN_UPSID */ +#define ANA_ACL_OWN_UPSID(r) __REG(TARGET_ANA_ACL, 0, 1, 32768, 0, 1, 592, 580, r, 3, 4) + +#define ANA_ACL_OWN_UPSID_OWN_UPSID GENMASK(4, 0) +#define ANA_ACL_OWN_UPSID_OWN_UPSID_SET(x)\ + FIELD_PREP(ANA_ACL_OWN_UPSID_OWN_UPSID, x) +#define ANA_ACL_OWN_UPSID_OWN_UPSID_GET(x)\ + FIELD_GET(ANA_ACL_OWN_UPSID_OWN_UPSID, x) + +/* ANA_AC_POL:POL_ALL_CFG:POL_UPD_INT_CFG */ +#define ANA_AC_POL_POL_UPD_INT_CFG __REG(TARGET_ANA_AC_POL, 0, 1, 75968, 0, 1, 1160, 1148, 0, 1, 4) + +#define ANA_AC_POL_POL_UPD_INT_CFG_POL_UPD_INT GENMASK(9, 0) +#define ANA_AC_POL_POL_UPD_INT_CFG_POL_UPD_INT_SET(x)\ + FIELD_PREP(ANA_AC_POL_POL_UPD_INT_CFG_POL_UPD_INT, x) +#define ANA_AC_POL_POL_UPD_INT_CFG_POL_UPD_INT_GET(x)\ + FIELD_GET(ANA_AC_POL_POL_UPD_INT_CFG_POL_UPD_INT, x) + +/* ANA_AC_POL:COMMON_BDLB:DLB_CTRL */ +#define ANA_AC_POL_BDLB_DLB_CTRL __REG(TARGET_ANA_AC_POL, 0, 1, 79048, 0, 1, 8, 0, 0, 1, 4) + +#define ANA_AC_POL_BDLB_DLB_CTRL_CLK_PERIOD_01NS GENMASK(26, 19) +#define ANA_AC_POL_BDLB_DLB_CTRL_CLK_PERIOD_01NS_SET(x)\ + FIELD_PREP(ANA_AC_POL_BDLB_DLB_CTRL_CLK_PERIOD_01NS, x) +#define ANA_AC_POL_BDLB_DLB_CTRL_CLK_PERIOD_01NS_GET(x)\ + FIELD_GET(ANA_AC_POL_BDLB_DLB_CTRL_CLK_PERIOD_01NS, x) + +#define ANA_AC_POL_BDLB_DLB_CTRL_BASE_TICK_CNT GENMASK(18, 4) +#define ANA_AC_POL_BDLB_DLB_CTRL_BASE_TICK_CNT_SET(x)\ + FIELD_PREP(ANA_AC_POL_BDLB_DLB_CTRL_BASE_TICK_CNT, x) +#define ANA_AC_POL_BDLB_DLB_CTRL_BASE_TICK_CNT_GET(x)\ + FIELD_GET(ANA_AC_POL_BDLB_DLB_CTRL_BASE_TICK_CNT, x) + +#define ANA_AC_POL_BDLB_DLB_CTRL_LEAK_ENA BIT(1) +#define ANA_AC_POL_BDLB_DLB_CTRL_LEAK_ENA_SET(x)\ + FIELD_PREP(ANA_AC_POL_BDLB_DLB_CTRL_LEAK_ENA, x) +#define ANA_AC_POL_BDLB_DLB_CTRL_LEAK_ENA_GET(x)\ + FIELD_GET(ANA_AC_POL_BDLB_DLB_CTRL_LEAK_ENA, x) + +#define ANA_AC_POL_BDLB_DLB_CTRL_DLB_ADD_ENA BIT(0) +#define ANA_AC_POL_BDLB_DLB_CTRL_DLB_ADD_ENA_SET(x)\ + FIELD_PREP(ANA_AC_POL_BDLB_DLB_CTRL_DLB_ADD_ENA, x) +#define ANA_AC_POL_BDLB_DLB_CTRL_DLB_ADD_ENA_GET(x)\ + FIELD_GET(ANA_AC_POL_BDLB_DLB_CTRL_DLB_ADD_ENA, x) + +/* ANA_AC_POL:COMMON_BUM_SLB:DLB_CTRL */ +#define ANA_AC_POL_SLB_DLB_CTRL __REG(TARGET_ANA_AC_POL, 0, 1, 79056, 0, 1, 20, 0, 0, 1, 4) + +#define ANA_AC_POL_SLB_DLB_CTRL_CLK_PERIOD_01NS GENMASK(26, 19) +#define ANA_AC_POL_SLB_DLB_CTRL_CLK_PERIOD_01NS_SET(x)\ + FIELD_PREP(ANA_AC_POL_SLB_DLB_CTRL_CLK_PERIOD_01NS, x) +#define ANA_AC_POL_SLB_DLB_CTRL_CLK_PERIOD_01NS_GET(x)\ + FIELD_GET(ANA_AC_POL_SLB_DLB_CTRL_CLK_PERIOD_01NS, x) + +#define ANA_AC_POL_SLB_DLB_CTRL_BASE_TICK_CNT GENMASK(18, 4) +#define ANA_AC_POL_SLB_DLB_CTRL_BASE_TICK_CNT_SET(x)\ + FIELD_PREP(ANA_AC_POL_SLB_DLB_CTRL_BASE_TICK_CNT, x) +#define ANA_AC_POL_SLB_DLB_CTRL_BASE_TICK_CNT_GET(x)\ + FIELD_GET(ANA_AC_POL_SLB_DLB_CTRL_BASE_TICK_CNT, x) + +#define ANA_AC_POL_SLB_DLB_CTRL_LEAK_ENA BIT(1) +#define ANA_AC_POL_SLB_DLB_CTRL_LEAK_ENA_SET(x)\ + FIELD_PREP(ANA_AC_POL_SLB_DLB_CTRL_LEAK_ENA, x) +#define ANA_AC_POL_SLB_DLB_CTRL_LEAK_ENA_GET(x)\ + FIELD_GET(ANA_AC_POL_SLB_DLB_CTRL_LEAK_ENA, x) + +#define ANA_AC_POL_SLB_DLB_CTRL_DLB_ADD_ENA BIT(0) +#define ANA_AC_POL_SLB_DLB_CTRL_DLB_ADD_ENA_SET(x)\ + FIELD_PREP(ANA_AC_POL_SLB_DLB_CTRL_DLB_ADD_ENA, x) +#define ANA_AC_POL_SLB_DLB_CTRL_DLB_ADD_ENA_GET(x)\ + FIELD_GET(ANA_AC_POL_SLB_DLB_CTRL_DLB_ADD_ENA, x) + +/* ANA_CL:PORT:FILTER_CTRL */ +#define ANA_CL_FILTER_CTRL(g) __REG(TARGET_ANA_CL, 0, 1, 131072, g, 70, 512, 4, 0, 1, 4) + +#define ANA_CL_FILTER_CTRL_FILTER_SMAC_MC_DIS BIT(2) +#define ANA_CL_FILTER_CTRL_FILTER_SMAC_MC_DIS_SET(x)\ + FIELD_PREP(ANA_CL_FILTER_CTRL_FILTER_SMAC_MC_DIS, x) +#define ANA_CL_FILTER_CTRL_FILTER_SMAC_MC_DIS_GET(x)\ + FIELD_GET(ANA_CL_FILTER_CTRL_FILTER_SMAC_MC_DIS, x) + +#define ANA_CL_FILTER_CTRL_FILTER_NULL_MAC_DIS BIT(1) +#define ANA_CL_FILTER_CTRL_FILTER_NULL_MAC_DIS_SET(x)\ + FIELD_PREP(ANA_CL_FILTER_CTRL_FILTER_NULL_MAC_DIS, x) +#define ANA_CL_FILTER_CTRL_FILTER_NULL_MAC_DIS_GET(x)\ + FIELD_GET(ANA_CL_FILTER_CTRL_FILTER_NULL_MAC_DIS, x) + +#define ANA_CL_FILTER_CTRL_FORCE_FCS_UPDATE_ENA BIT(0) +#define ANA_CL_FILTER_CTRL_FORCE_FCS_UPDATE_ENA_SET(x)\ + FIELD_PREP(ANA_CL_FILTER_CTRL_FORCE_FCS_UPDATE_ENA, x) +#define ANA_CL_FILTER_CTRL_FORCE_FCS_UPDATE_ENA_GET(x)\ + FIELD_GET(ANA_CL_FILTER_CTRL_FORCE_FCS_UPDATE_ENA, x) + +/* ANA_CL:PORT:VLAN_FILTER_CTRL */ +#define ANA_CL_VLAN_FILTER_CTRL(g, r) __REG(TARGET_ANA_CL, 0, 1, 131072, g, 70, 512, 8, r, 3, 4) + +#define ANA_CL_VLAN_FILTER_CTRL_TAG_REQUIRED_ENA BIT(10) +#define ANA_CL_VLAN_FILTER_CTRL_TAG_REQUIRED_ENA_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_FILTER_CTRL_TAG_REQUIRED_ENA, x) +#define ANA_CL_VLAN_FILTER_CTRL_TAG_REQUIRED_ENA_GET(x)\ + FIELD_GET(ANA_CL_VLAN_FILTER_CTRL_TAG_REQUIRED_ENA, x) + +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_CTAG_DIS BIT(9) +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_CTAG_DIS_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_FILTER_CTRL_PRIO_CTAG_DIS, x) +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_CTAG_DIS_GET(x)\ + FIELD_GET(ANA_CL_VLAN_FILTER_CTRL_PRIO_CTAG_DIS, x) + +#define ANA_CL_VLAN_FILTER_CTRL_CTAG_DIS BIT(8) +#define ANA_CL_VLAN_FILTER_CTRL_CTAG_DIS_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_FILTER_CTRL_CTAG_DIS, x) +#define ANA_CL_VLAN_FILTER_CTRL_CTAG_DIS_GET(x)\ + FIELD_GET(ANA_CL_VLAN_FILTER_CTRL_CTAG_DIS, x) + +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_STAG_DIS BIT(7) +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_STAG_DIS_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_FILTER_CTRL_PRIO_STAG_DIS, x) +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_STAG_DIS_GET(x)\ + FIELD_GET(ANA_CL_VLAN_FILTER_CTRL_PRIO_STAG_DIS, x) + +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST1_STAG_DIS BIT(6) +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST1_STAG_DIS_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST1_STAG_DIS, x) +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST1_STAG_DIS_GET(x)\ + FIELD_GET(ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST1_STAG_DIS, x) + +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST2_STAG_DIS BIT(5) +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST2_STAG_DIS_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST2_STAG_DIS, x) +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST2_STAG_DIS_GET(x)\ + FIELD_GET(ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST2_STAG_DIS, x) + +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST3_STAG_DIS BIT(4) +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST3_STAG_DIS_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST3_STAG_DIS, x) +#define ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST3_STAG_DIS_GET(x)\ + FIELD_GET(ANA_CL_VLAN_FILTER_CTRL_PRIO_CUST3_STAG_DIS, x) + +#define ANA_CL_VLAN_FILTER_CTRL_STAG_DIS BIT(3) +#define ANA_CL_VLAN_FILTER_CTRL_STAG_DIS_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_FILTER_CTRL_STAG_DIS, x) +#define ANA_CL_VLAN_FILTER_CTRL_STAG_DIS_GET(x)\ + FIELD_GET(ANA_CL_VLAN_FILTER_CTRL_STAG_DIS, x) + +#define ANA_CL_VLAN_FILTER_CTRL_CUST1_STAG_DIS BIT(2) +#define ANA_CL_VLAN_FILTER_CTRL_CUST1_STAG_DIS_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_FILTER_CTRL_CUST1_STAG_DIS, x) +#define ANA_CL_VLAN_FILTER_CTRL_CUST1_STAG_DIS_GET(x)\ + FIELD_GET(ANA_CL_VLAN_FILTER_CTRL_CUST1_STAG_DIS, x) + +#define ANA_CL_VLAN_FILTER_CTRL_CUST2_STAG_DIS BIT(1) +#define ANA_CL_VLAN_FILTER_CTRL_CUST2_STAG_DIS_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_FILTER_CTRL_CUST2_STAG_DIS, x) +#define ANA_CL_VLAN_FILTER_CTRL_CUST2_STAG_DIS_GET(x)\ + FIELD_GET(ANA_CL_VLAN_FILTER_CTRL_CUST2_STAG_DIS, x) + +#define ANA_CL_VLAN_FILTER_CTRL_CUST3_STAG_DIS BIT(0) +#define ANA_CL_VLAN_FILTER_CTRL_CUST3_STAG_DIS_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_FILTER_CTRL_CUST3_STAG_DIS, x) +#define ANA_CL_VLAN_FILTER_CTRL_CUST3_STAG_DIS_GET(x)\ + FIELD_GET(ANA_CL_VLAN_FILTER_CTRL_CUST3_STAG_DIS, x) + +/* ANA_CL:PORT:ETAG_FILTER_CTRL */ +#define ANA_CL_ETAG_FILTER_CTRL(g) __REG(TARGET_ANA_CL, 0, 1, 131072, g, 70, 512, 20, 0, 1, 4) + +#define ANA_CL_ETAG_FILTER_CTRL_ETAG_REQUIRED_ENA BIT(1) +#define ANA_CL_ETAG_FILTER_CTRL_ETAG_REQUIRED_ENA_SET(x)\ + FIELD_PREP(ANA_CL_ETAG_FILTER_CTRL_ETAG_REQUIRED_ENA, x) +#define ANA_CL_ETAG_FILTER_CTRL_ETAG_REQUIRED_ENA_GET(x)\ + FIELD_GET(ANA_CL_ETAG_FILTER_CTRL_ETAG_REQUIRED_ENA, x) + +#define ANA_CL_ETAG_FILTER_CTRL_ETAG_DIS BIT(0) +#define ANA_CL_ETAG_FILTER_CTRL_ETAG_DIS_SET(x)\ + FIELD_PREP(ANA_CL_ETAG_FILTER_CTRL_ETAG_DIS, x) +#define ANA_CL_ETAG_FILTER_CTRL_ETAG_DIS_GET(x)\ + FIELD_GET(ANA_CL_ETAG_FILTER_CTRL_ETAG_DIS, x) + +/* ANA_CL:PORT:VLAN_CTRL */ +#define ANA_CL_VLAN_CTRL(g) __REG(TARGET_ANA_CL, 0, 1, 131072, g, 70, 512, 32, 0, 1, 4) + +#define ANA_CL_VLAN_CTRL_PORT_VOE_TPID_AWARE_DIS GENMASK(30, 26) +#define ANA_CL_VLAN_CTRL_PORT_VOE_TPID_AWARE_DIS_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_CTRL_PORT_VOE_TPID_AWARE_DIS, x) +#define ANA_CL_VLAN_CTRL_PORT_VOE_TPID_AWARE_DIS_GET(x)\ + FIELD_GET(ANA_CL_VLAN_CTRL_PORT_VOE_TPID_AWARE_DIS, x) + +#define ANA_CL_VLAN_CTRL_PORT_VOE_DEFAULT_PCP GENMASK(25, 23) +#define ANA_CL_VLAN_CTRL_PORT_VOE_DEFAULT_PCP_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_CTRL_PORT_VOE_DEFAULT_PCP, x) +#define ANA_CL_VLAN_CTRL_PORT_VOE_DEFAULT_PCP_GET(x)\ + FIELD_GET(ANA_CL_VLAN_CTRL_PORT_VOE_DEFAULT_PCP, x) + +#define ANA_CL_VLAN_CTRL_PORT_VOE_DEFAULT_DEI BIT(22) +#define ANA_CL_VLAN_CTRL_PORT_VOE_DEFAULT_DEI_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_CTRL_PORT_VOE_DEFAULT_DEI, x) +#define ANA_CL_VLAN_CTRL_PORT_VOE_DEFAULT_DEI_GET(x)\ + FIELD_GET(ANA_CL_VLAN_CTRL_PORT_VOE_DEFAULT_DEI, x) + +#define ANA_CL_VLAN_CTRL_VLAN_PCP_DEI_TRANS_ENA BIT(21) +#define ANA_CL_VLAN_CTRL_VLAN_PCP_DEI_TRANS_ENA_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_CTRL_VLAN_PCP_DEI_TRANS_ENA, x) +#define ANA_CL_VLAN_CTRL_VLAN_PCP_DEI_TRANS_ENA_GET(x)\ + FIELD_GET(ANA_CL_VLAN_CTRL_VLAN_PCP_DEI_TRANS_ENA, x) + +#define ANA_CL_VLAN_CTRL_VLAN_TAG_SEL BIT(20) +#define ANA_CL_VLAN_CTRL_VLAN_TAG_SEL_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_CTRL_VLAN_TAG_SEL, x) +#define ANA_CL_VLAN_CTRL_VLAN_TAG_SEL_GET(x)\ + FIELD_GET(ANA_CL_VLAN_CTRL_VLAN_TAG_SEL, x) + +#define ANA_CL_VLAN_CTRL_VLAN_AWARE_ENA BIT(19) +#define ANA_CL_VLAN_CTRL_VLAN_AWARE_ENA_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_CTRL_VLAN_AWARE_ENA, x) +#define ANA_CL_VLAN_CTRL_VLAN_AWARE_ENA_GET(x)\ + FIELD_GET(ANA_CL_VLAN_CTRL_VLAN_AWARE_ENA, x) + +#define ANA_CL_VLAN_CTRL_VLAN_POP_CNT GENMASK(18, 17) +#define ANA_CL_VLAN_CTRL_VLAN_POP_CNT_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_CTRL_VLAN_POP_CNT, x) +#define ANA_CL_VLAN_CTRL_VLAN_POP_CNT_GET(x)\ + FIELD_GET(ANA_CL_VLAN_CTRL_VLAN_POP_CNT, x) + +#define ANA_CL_VLAN_CTRL_PORT_TAG_TYPE BIT(16) +#define ANA_CL_VLAN_CTRL_PORT_TAG_TYPE_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_CTRL_PORT_TAG_TYPE, x) +#define ANA_CL_VLAN_CTRL_PORT_TAG_TYPE_GET(x)\ + FIELD_GET(ANA_CL_VLAN_CTRL_PORT_TAG_TYPE, x) + +#define ANA_CL_VLAN_CTRL_PORT_PCP GENMASK(15, 13) +#define ANA_CL_VLAN_CTRL_PORT_PCP_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_CTRL_PORT_PCP, x) +#define ANA_CL_VLAN_CTRL_PORT_PCP_GET(x)\ + FIELD_GET(ANA_CL_VLAN_CTRL_PORT_PCP, x) + +#define ANA_CL_VLAN_CTRL_PORT_DEI BIT(12) +#define ANA_CL_VLAN_CTRL_PORT_DEI_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_CTRL_PORT_DEI, x) +#define ANA_CL_VLAN_CTRL_PORT_DEI_GET(x)\ + FIELD_GET(ANA_CL_VLAN_CTRL_PORT_DEI, x) + +#define ANA_CL_VLAN_CTRL_PORT_VID GENMASK(11, 0) +#define ANA_CL_VLAN_CTRL_PORT_VID_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_CTRL_PORT_VID, x) +#define ANA_CL_VLAN_CTRL_PORT_VID_GET(x)\ + FIELD_GET(ANA_CL_VLAN_CTRL_PORT_VID, x) + +/* ANA_CL:PORT:VLAN_CTRL_2 */ +#define ANA_CL_VLAN_CTRL_2(g) __REG(TARGET_ANA_CL, 0, 1, 131072, g, 70, 512, 36, 0, 1, 4) + +#define ANA_CL_VLAN_CTRL_2_VLAN_PUSH_CNT GENMASK(1, 0) +#define ANA_CL_VLAN_CTRL_2_VLAN_PUSH_CNT_SET(x)\ + FIELD_PREP(ANA_CL_VLAN_CTRL_2_VLAN_PUSH_CNT, x) +#define ANA_CL_VLAN_CTRL_2_VLAN_PUSH_CNT_GET(x)\ + FIELD_GET(ANA_CL_VLAN_CTRL_2_VLAN_PUSH_CNT, x) + +/* ANA_CL:PORT:CAPTURE_BPDU_CFG */ +#define ANA_CL_CAPTURE_BPDU_CFG(g) __REG(TARGET_ANA_CL, 0, 1, 131072, g, 70, 512, 196, 0, 1, 4) + +/* ANA_CL:COMMON:OWN_UPSID */ +#define ANA_CL_OWN_UPSID(r) __REG(TARGET_ANA_CL, 0, 1, 166912, 0, 1, 756, 0, r, 3, 4) + +#define ANA_CL_OWN_UPSID_OWN_UPSID GENMASK(4, 0) +#define ANA_CL_OWN_UPSID_OWN_UPSID_SET(x)\ + FIELD_PREP(ANA_CL_OWN_UPSID_OWN_UPSID, x) +#define ANA_CL_OWN_UPSID_OWN_UPSID_GET(x)\ + FIELD_GET(ANA_CL_OWN_UPSID_OWN_UPSID, x) + +/* ANA_L2:COMMON:AUTO_LRN_CFG */ +#define ANA_L2_AUTO_LRN_CFG __REG(TARGET_ANA_L2, 0, 1, 566024, 0, 1, 700, 24, 0, 1, 4) + +/* ANA_L2:COMMON:AUTO_LRN_CFG1 */ +#define ANA_L2_AUTO_LRN_CFG1 __REG(TARGET_ANA_L2, 0, 1, 566024, 0, 1, 700, 28, 0, 1, 4) + +/* ANA_L2:COMMON:AUTO_LRN_CFG2 */ +#define ANA_L2_AUTO_LRN_CFG2 __REG(TARGET_ANA_L2, 0, 1, 566024, 0, 1, 700, 32, 0, 1, 4) + +#define ANA_L2_AUTO_LRN_CFG2_AUTO_LRN_ENA2 BIT(0) +#define ANA_L2_AUTO_LRN_CFG2_AUTO_LRN_ENA2_SET(x)\ + FIELD_PREP(ANA_L2_AUTO_LRN_CFG2_AUTO_LRN_ENA2, x) +#define ANA_L2_AUTO_LRN_CFG2_AUTO_LRN_ENA2_GET(x)\ + FIELD_GET(ANA_L2_AUTO_LRN_CFG2_AUTO_LRN_ENA2, x) + +/* ANA_L2:COMMON:OWN_UPSID */ +#define ANA_L2_OWN_UPSID(r) __REG(TARGET_ANA_L2, 0, 1, 566024, 0, 1, 700, 672, r, 3, 4) + +#define ANA_L2_OWN_UPSID_OWN_UPSID GENMASK(4, 0) +#define ANA_L2_OWN_UPSID_OWN_UPSID_SET(x)\ + FIELD_PREP(ANA_L2_OWN_UPSID_OWN_UPSID, x) +#define ANA_L2_OWN_UPSID_OWN_UPSID_GET(x)\ + FIELD_GET(ANA_L2_OWN_UPSID_OWN_UPSID, x) + +/* ANA_L3:COMMON:VLAN_CTRL */ +#define ANA_L3_VLAN_CTRL __REG(TARGET_ANA_L3, 0, 1, 493632, 0, 1, 184, 4, 0, 1, 4) + +#define ANA_L3_VLAN_CTRL_VLAN_ENA BIT(0) +#define ANA_L3_VLAN_CTRL_VLAN_ENA_SET(x)\ + FIELD_PREP(ANA_L3_VLAN_CTRL_VLAN_ENA, x) +#define ANA_L3_VLAN_CTRL_VLAN_ENA_GET(x)\ + FIELD_GET(ANA_L3_VLAN_CTRL_VLAN_ENA, x) + +/* ANA_L3:VLAN:VLAN_CFG */ +#define ANA_L3_VLAN_CFG(g) __REG(TARGET_ANA_L3, 0, 1, 0, g, 5120, 64, 8, 0, 1, 4) + +#define ANA_L3_VLAN_CFG_VLAN_MSTP_PTR GENMASK(30, 24) +#define ANA_L3_VLAN_CFG_VLAN_MSTP_PTR_SET(x)\ + FIELD_PREP(ANA_L3_VLAN_CFG_VLAN_MSTP_PTR, x) +#define ANA_L3_VLAN_CFG_VLAN_MSTP_PTR_GET(x)\ + FIELD_GET(ANA_L3_VLAN_CFG_VLAN_MSTP_PTR, x) + +#define ANA_L3_VLAN_CFG_VLAN_FID GENMASK(20, 8) +#define ANA_L3_VLAN_CFG_VLAN_FID_SET(x)\ + FIELD_PREP(ANA_L3_VLAN_CFG_VLAN_FID, x) +#define ANA_L3_VLAN_CFG_VLAN_FID_GET(x)\ + FIELD_GET(ANA_L3_VLAN_CFG_VLAN_FID, x) + +#define ANA_L3_VLAN_CFG_VLAN_IGR_FILTER_ENA BIT(6) +#define ANA_L3_VLAN_CFG_VLAN_IGR_FILTER_ENA_SET(x)\ + FIELD_PREP(ANA_L3_VLAN_CFG_VLAN_IGR_FILTER_ENA, x) +#define ANA_L3_VLAN_CFG_VLAN_IGR_FILTER_ENA_GET(x)\ + FIELD_GET(ANA_L3_VLAN_CFG_VLAN_IGR_FILTER_ENA, x) + +#define ANA_L3_VLAN_CFG_VLAN_SEC_FWD_ENA BIT(5) +#define ANA_L3_VLAN_CFG_VLAN_SEC_FWD_ENA_SET(x)\ + FIELD_PREP(ANA_L3_VLAN_CFG_VLAN_SEC_FWD_ENA, x) +#define ANA_L3_VLAN_CFG_VLAN_SEC_FWD_ENA_GET(x)\ + FIELD_GET(ANA_L3_VLAN_CFG_VLAN_SEC_FWD_ENA, x) + +#define ANA_L3_VLAN_CFG_VLAN_FLOOD_DIS BIT(4) +#define ANA_L3_VLAN_CFG_VLAN_FLOOD_DIS_SET(x)\ + FIELD_PREP(ANA_L3_VLAN_CFG_VLAN_FLOOD_DIS, x) +#define ANA_L3_VLAN_CFG_VLAN_FLOOD_DIS_GET(x)\ + FIELD_GET(ANA_L3_VLAN_CFG_VLAN_FLOOD_DIS, x) + +#define ANA_L3_VLAN_CFG_VLAN_LRN_DIS BIT(3) +#define ANA_L3_VLAN_CFG_VLAN_LRN_DIS_SET(x)\ + FIELD_PREP(ANA_L3_VLAN_CFG_VLAN_LRN_DIS, x) +#define ANA_L3_VLAN_CFG_VLAN_LRN_DIS_GET(x)\ + FIELD_GET(ANA_L3_VLAN_CFG_VLAN_LRN_DIS, x) + +#define ANA_L3_VLAN_CFG_VLAN_RLEG_ENA BIT(2) +#define ANA_L3_VLAN_CFG_VLAN_RLEG_ENA_SET(x)\ + FIELD_PREP(ANA_L3_VLAN_CFG_VLAN_RLEG_ENA, x) +#define ANA_L3_VLAN_CFG_VLAN_RLEG_ENA_GET(x)\ + FIELD_GET(ANA_L3_VLAN_CFG_VLAN_RLEG_ENA, x) + +#define ANA_L3_VLAN_CFG_VLAN_PRIVATE_ENA BIT(1) +#define ANA_L3_VLAN_CFG_VLAN_PRIVATE_ENA_SET(x)\ + FIELD_PREP(ANA_L3_VLAN_CFG_VLAN_PRIVATE_ENA, x) +#define ANA_L3_VLAN_CFG_VLAN_PRIVATE_ENA_GET(x)\ + FIELD_GET(ANA_L3_VLAN_CFG_VLAN_PRIVATE_ENA, x) + +#define ANA_L3_VLAN_CFG_VLAN_MIRROR_ENA BIT(0) +#define ANA_L3_VLAN_CFG_VLAN_MIRROR_ENA_SET(x)\ + FIELD_PREP(ANA_L3_VLAN_CFG_VLAN_MIRROR_ENA, x) +#define ANA_L3_VLAN_CFG_VLAN_MIRROR_ENA_GET(x)\ + FIELD_GET(ANA_L3_VLAN_CFG_VLAN_MIRROR_ENA, x) + +/* ANA_L3:VLAN:VLAN_MASK_CFG */ +#define ANA_L3_VLAN_MASK_CFG(g) __REG(TARGET_ANA_L3, 0, 1, 0, g, 5120, 64, 16, 0, 1, 4) + +/* ANA_L3:VLAN:VLAN_MASK_CFG1 */ +#define ANA_L3_VLAN_MASK_CFG1(g) __REG(TARGET_ANA_L3, 0, 1, 0, g, 5120, 64, 20, 0, 1, 4) + +/* ANA_L3:VLAN:VLAN_MASK_CFG2 */ +#define ANA_L3_VLAN_MASK_CFG2(g) __REG(TARGET_ANA_L3, 0, 1, 0, g, 5120, 64, 24, 0, 1, 4) + +#define ANA_L3_VLAN_MASK_CFG2_VLAN_PORT_MASK2 BIT(0) +#define ANA_L3_VLAN_MASK_CFG2_VLAN_PORT_MASK2_SET(x)\ + FIELD_PREP(ANA_L3_VLAN_MASK_CFG2_VLAN_PORT_MASK2, x) +#define ANA_L3_VLAN_MASK_CFG2_VLAN_PORT_MASK2_GET(x)\ + FIELD_GET(ANA_L3_VLAN_MASK_CFG2_VLAN_PORT_MASK2, x) + +/* ASM:DEV_STATISTICS:RX_IN_BYTES_CNT */ +#define ASM_RX_IN_BYTES_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 0, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_SYMBOL_ERR_CNT */ +#define ASM_RX_SYMBOL_ERR_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 4, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_PAUSE_CNT */ +#define ASM_RX_PAUSE_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 8, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_UNSUP_OPCODE_CNT */ +#define ASM_RX_UNSUP_OPCODE_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 12, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_OK_BYTES_CNT */ +#define ASM_RX_OK_BYTES_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 16, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_BAD_BYTES_CNT */ +#define ASM_RX_BAD_BYTES_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 20, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_UC_CNT */ +#define ASM_RX_UC_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 24, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_MC_CNT */ +#define ASM_RX_MC_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 28, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_BC_CNT */ +#define ASM_RX_BC_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 32, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_CRC_ERR_CNT */ +#define ASM_RX_CRC_ERR_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 36, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_UNDERSIZE_CNT */ +#define ASM_RX_UNDERSIZE_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 40, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_FRAGMENTS_CNT */ +#define ASM_RX_FRAGMENTS_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 44, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_IN_RANGE_LEN_ERR_CNT */ +#define ASM_RX_IN_RANGE_LEN_ERR_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 48, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_OUT_OF_RANGE_LEN_ERR_CNT */ +#define ASM_RX_OUT_OF_RANGE_LEN_ERR_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 52, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_OVERSIZE_CNT */ +#define ASM_RX_OVERSIZE_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 56, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_JABBERS_CNT */ +#define ASM_RX_JABBERS_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 60, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_SIZE64_CNT */ +#define ASM_RX_SIZE64_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 64, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_SIZE65TO127_CNT */ +#define ASM_RX_SIZE65TO127_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 68, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_SIZE128TO255_CNT */ +#define ASM_RX_SIZE128TO255_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 72, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_SIZE256TO511_CNT */ +#define ASM_RX_SIZE256TO511_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 76, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_SIZE512TO1023_CNT */ +#define ASM_RX_SIZE512TO1023_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 80, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_SIZE1024TO1518_CNT */ +#define ASM_RX_SIZE1024TO1518_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 84, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_SIZE1519TOMAX_CNT */ +#define ASM_RX_SIZE1519TOMAX_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 88, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_IPG_SHRINK_CNT */ +#define ASM_RX_IPG_SHRINK_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 92, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_OUT_BYTES_CNT */ +#define ASM_TX_OUT_BYTES_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 96, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_PAUSE_CNT */ +#define ASM_TX_PAUSE_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 100, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_OK_BYTES_CNT */ +#define ASM_TX_OK_BYTES_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 104, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_UC_CNT */ +#define ASM_TX_UC_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 108, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_MC_CNT */ +#define ASM_TX_MC_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 112, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_BC_CNT */ +#define ASM_TX_BC_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 116, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_SIZE64_CNT */ +#define ASM_TX_SIZE64_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 120, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_SIZE65TO127_CNT */ +#define ASM_TX_SIZE65TO127_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 124, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_SIZE128TO255_CNT */ +#define ASM_TX_SIZE128TO255_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 128, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_SIZE256TO511_CNT */ +#define ASM_TX_SIZE256TO511_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 132, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_SIZE512TO1023_CNT */ +#define ASM_TX_SIZE512TO1023_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 136, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_SIZE1024TO1518_CNT */ +#define ASM_TX_SIZE1024TO1518_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 140, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_SIZE1519TOMAX_CNT */ +#define ASM_TX_SIZE1519TOMAX_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 144, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_ALIGNMENT_LOST_CNT */ +#define ASM_RX_ALIGNMENT_LOST_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 148, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_TAGGED_FRMS_CNT */ +#define ASM_RX_TAGGED_FRMS_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 152, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_UNTAGGED_FRMS_CNT */ +#define ASM_RX_UNTAGGED_FRMS_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 156, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_TAGGED_FRMS_CNT */ +#define ASM_TX_TAGGED_FRMS_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 160, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_UNTAGGED_FRMS_CNT */ +#define ASM_TX_UNTAGGED_FRMS_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 164, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_SYMBOL_ERR_CNT */ +#define ASM_PMAC_RX_SYMBOL_ERR_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 168, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_PAUSE_CNT */ +#define ASM_PMAC_RX_PAUSE_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 172, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_UNSUP_OPCODE_CNT */ +#define ASM_PMAC_RX_UNSUP_OPCODE_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 176, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_OK_BYTES_CNT */ +#define ASM_PMAC_RX_OK_BYTES_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 180, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_BAD_BYTES_CNT */ +#define ASM_PMAC_RX_BAD_BYTES_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 184, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_UC_CNT */ +#define ASM_PMAC_RX_UC_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 188, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_MC_CNT */ +#define ASM_PMAC_RX_MC_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 192, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_BC_CNT */ +#define ASM_PMAC_RX_BC_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 196, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_CRC_ERR_CNT */ +#define ASM_PMAC_RX_CRC_ERR_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 200, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_UNDERSIZE_CNT */ +#define ASM_PMAC_RX_UNDERSIZE_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 204, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_FRAGMENTS_CNT */ +#define ASM_PMAC_RX_FRAGMENTS_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 208, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_IN_RANGE_LEN_ERR_CNT */ +#define ASM_PMAC_RX_IN_RANGE_LEN_ERR_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 212, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_OUT_OF_RANGE_LEN_ERR_CNT */ +#define ASM_PMAC_RX_OUT_OF_RANGE_LEN_ERR_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 216, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_OVERSIZE_CNT */ +#define ASM_PMAC_RX_OVERSIZE_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 220, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_JABBERS_CNT */ +#define ASM_PMAC_RX_JABBERS_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 224, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_SIZE64_CNT */ +#define ASM_PMAC_RX_SIZE64_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 228, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_SIZE65TO127_CNT */ +#define ASM_PMAC_RX_SIZE65TO127_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 232, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_SIZE128TO255_CNT */ +#define ASM_PMAC_RX_SIZE128TO255_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 236, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_SIZE256TO511_CNT */ +#define ASM_PMAC_RX_SIZE256TO511_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 240, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_SIZE512TO1023_CNT */ +#define ASM_PMAC_RX_SIZE512TO1023_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 244, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_SIZE1024TO1518_CNT */ +#define ASM_PMAC_RX_SIZE1024TO1518_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 248, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_SIZE1519TOMAX_CNT */ +#define ASM_PMAC_RX_SIZE1519TOMAX_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 252, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_TX_PAUSE_CNT */ +#define ASM_PMAC_TX_PAUSE_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 256, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_TX_OK_BYTES_CNT */ +#define ASM_PMAC_TX_OK_BYTES_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 260, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_TX_UC_CNT */ +#define ASM_PMAC_TX_UC_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 264, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_TX_MC_CNT */ +#define ASM_PMAC_TX_MC_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 268, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_TX_BC_CNT */ +#define ASM_PMAC_TX_BC_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 272, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_TX_SIZE64_CNT */ +#define ASM_PMAC_TX_SIZE64_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 276, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_TX_SIZE65TO127_CNT */ +#define ASM_PMAC_TX_SIZE65TO127_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 280, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_TX_SIZE128TO255_CNT */ +#define ASM_PMAC_TX_SIZE128TO255_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 284, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_TX_SIZE256TO511_CNT */ +#define ASM_PMAC_TX_SIZE256TO511_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 288, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_TX_SIZE512TO1023_CNT */ +#define ASM_PMAC_TX_SIZE512TO1023_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 292, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_TX_SIZE1024TO1518_CNT */ +#define ASM_PMAC_TX_SIZE1024TO1518_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 296, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_TX_SIZE1519TOMAX_CNT */ +#define ASM_PMAC_TX_SIZE1519TOMAX_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 300, 0, 1, 4) + +/* ASM:DEV_STATISTICS:PMAC_RX_ALIGNMENT_LOST_CNT */ +#define ASM_PMAC_RX_ALIGNMENT_LOST_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 304, 0, 1, 4) + +/* ASM:DEV_STATISTICS:MM_RX_ASSEMBLY_ERR_CNT */ +#define ASM_MM_RX_ASSEMBLY_ERR_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 308, 0, 1, 4) + +/* ASM:DEV_STATISTICS:MM_RX_SMD_ERR_CNT */ +#define ASM_MM_RX_SMD_ERR_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 312, 0, 1, 4) + +/* ASM:DEV_STATISTICS:MM_RX_ASSEMBLY_OK_CNT */ +#define ASM_MM_RX_ASSEMBLY_OK_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 316, 0, 1, 4) + +/* ASM:DEV_STATISTICS:MM_RX_MERGE_FRAG_CNT */ +#define ASM_MM_RX_MERGE_FRAG_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 320, 0, 1, 4) + +/* ASM:DEV_STATISTICS:MM_TX_PFRAGMENT_CNT */ +#define ASM_MM_TX_PFRAGMENT_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 324, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_MULTI_COLL_CNT */ +#define ASM_TX_MULTI_COLL_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 328, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_LATE_COLL_CNT */ +#define ASM_TX_LATE_COLL_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 332, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_XCOLL_CNT */ +#define ASM_TX_XCOLL_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 336, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_DEFER_CNT */ +#define ASM_TX_DEFER_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 340, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_XDEFER_CNT */ +#define ASM_TX_XDEFER_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 344, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_BACKOFF1_CNT */ +#define ASM_TX_BACKOFF1_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 348, 0, 1, 4) + +/* ASM:DEV_STATISTICS:TX_CSENSE_CNT */ +#define ASM_TX_CSENSE_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 352, 0, 1, 4) + +/* ASM:DEV_STATISTICS:RX_IN_BYTES_MSB_CNT */ +#define ASM_RX_IN_BYTES_MSB_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 356, 0, 1, 4) + +#define ASM_RX_IN_BYTES_MSB_CNT_RX_IN_BYTES_MSB_CNT GENMASK(3, 0) +#define ASM_RX_IN_BYTES_MSB_CNT_RX_IN_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(ASM_RX_IN_BYTES_MSB_CNT_RX_IN_BYTES_MSB_CNT, x) +#define ASM_RX_IN_BYTES_MSB_CNT_RX_IN_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(ASM_RX_IN_BYTES_MSB_CNT_RX_IN_BYTES_MSB_CNT, x) + +/* ASM:DEV_STATISTICS:RX_OK_BYTES_MSB_CNT */ +#define ASM_RX_OK_BYTES_MSB_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 360, 0, 1, 4) + +#define ASM_RX_OK_BYTES_MSB_CNT_RX_OK_BYTES_MSB_CNT GENMASK(3, 0) +#define ASM_RX_OK_BYTES_MSB_CNT_RX_OK_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(ASM_RX_OK_BYTES_MSB_CNT_RX_OK_BYTES_MSB_CNT, x) +#define ASM_RX_OK_BYTES_MSB_CNT_RX_OK_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(ASM_RX_OK_BYTES_MSB_CNT_RX_OK_BYTES_MSB_CNT, x) + +/* ASM:DEV_STATISTICS:PMAC_RX_OK_BYTES_MSB_CNT */ +#define ASM_PMAC_RX_OK_BYTES_MSB_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 364, 0, 1, 4) + +#define ASM_PMAC_RX_OK_BYTES_MSB_CNT_PMAC_RX_OK_BYTES_MSB_CNT GENMASK(3, 0) +#define ASM_PMAC_RX_OK_BYTES_MSB_CNT_PMAC_RX_OK_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(ASM_PMAC_RX_OK_BYTES_MSB_CNT_PMAC_RX_OK_BYTES_MSB_CNT, x) +#define ASM_PMAC_RX_OK_BYTES_MSB_CNT_PMAC_RX_OK_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(ASM_PMAC_RX_OK_BYTES_MSB_CNT_PMAC_RX_OK_BYTES_MSB_CNT, x) + +/* ASM:DEV_STATISTICS:RX_BAD_BYTES_MSB_CNT */ +#define ASM_RX_BAD_BYTES_MSB_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 368, 0, 1, 4) + +#define ASM_RX_BAD_BYTES_MSB_CNT_RX_BAD_BYTES_MSB_CNT GENMASK(3, 0) +#define ASM_RX_BAD_BYTES_MSB_CNT_RX_BAD_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(ASM_RX_BAD_BYTES_MSB_CNT_RX_BAD_BYTES_MSB_CNT, x) +#define ASM_RX_BAD_BYTES_MSB_CNT_RX_BAD_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(ASM_RX_BAD_BYTES_MSB_CNT_RX_BAD_BYTES_MSB_CNT, x) + +/* ASM:DEV_STATISTICS:PMAC_RX_BAD_BYTES_MSB_CNT */ +#define ASM_PMAC_RX_BAD_BYTES_MSB_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 372, 0, 1, 4) + +#define ASM_PMAC_RX_BAD_BYTES_MSB_CNT_PMAC_RX_BAD_BYTES_MSB_CNT GENMASK(3, 0) +#define ASM_PMAC_RX_BAD_BYTES_MSB_CNT_PMAC_RX_BAD_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(ASM_PMAC_RX_BAD_BYTES_MSB_CNT_PMAC_RX_BAD_BYTES_MSB_CNT, x) +#define ASM_PMAC_RX_BAD_BYTES_MSB_CNT_PMAC_RX_BAD_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(ASM_PMAC_RX_BAD_BYTES_MSB_CNT_PMAC_RX_BAD_BYTES_MSB_CNT, x) + +/* ASM:DEV_STATISTICS:TX_OUT_BYTES_MSB_CNT */ +#define ASM_TX_OUT_BYTES_MSB_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 376, 0, 1, 4) + +#define ASM_TX_OUT_BYTES_MSB_CNT_TX_OUT_BYTES_MSB_CNT GENMASK(3, 0) +#define ASM_TX_OUT_BYTES_MSB_CNT_TX_OUT_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(ASM_TX_OUT_BYTES_MSB_CNT_TX_OUT_BYTES_MSB_CNT, x) +#define ASM_TX_OUT_BYTES_MSB_CNT_TX_OUT_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(ASM_TX_OUT_BYTES_MSB_CNT_TX_OUT_BYTES_MSB_CNT, x) + +/* ASM:DEV_STATISTICS:TX_OK_BYTES_MSB_CNT */ +#define ASM_TX_OK_BYTES_MSB_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 380, 0, 1, 4) + +#define ASM_TX_OK_BYTES_MSB_CNT_TX_OK_BYTES_MSB_CNT GENMASK(3, 0) +#define ASM_TX_OK_BYTES_MSB_CNT_TX_OK_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(ASM_TX_OK_BYTES_MSB_CNT_TX_OK_BYTES_MSB_CNT, x) +#define ASM_TX_OK_BYTES_MSB_CNT_TX_OK_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(ASM_TX_OK_BYTES_MSB_CNT_TX_OK_BYTES_MSB_CNT, x) + +/* ASM:DEV_STATISTICS:PMAC_TX_OK_BYTES_MSB_CNT */ +#define ASM_PMAC_TX_OK_BYTES_MSB_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 384, 0, 1, 4) + +#define ASM_PMAC_TX_OK_BYTES_MSB_CNT_PMAC_TX_OK_BYTES_MSB_CNT GENMASK(3, 0) +#define ASM_PMAC_TX_OK_BYTES_MSB_CNT_PMAC_TX_OK_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(ASM_PMAC_TX_OK_BYTES_MSB_CNT_PMAC_TX_OK_BYTES_MSB_CNT, x) +#define ASM_PMAC_TX_OK_BYTES_MSB_CNT_PMAC_TX_OK_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(ASM_PMAC_TX_OK_BYTES_MSB_CNT_PMAC_TX_OK_BYTES_MSB_CNT, x) + +/* ASM:DEV_STATISTICS:RX_SYNC_LOST_ERR_CNT */ +#define ASM_RX_SYNC_LOST_ERR_CNT(g) __REG(TARGET_ASM, 0, 1, 0, g, 65, 512, 388, 0, 1, 4) + +/* ASM:CFG:STAT_CFG */ +#define ASM_STAT_CFG __REG(TARGET_ASM, 0, 1, 33280, 0, 1, 1088, 0, 0, 1, 4) + +#define ASM_STAT_CFG_STAT_CNT_CLR_SHOT BIT(0) +#define ASM_STAT_CFG_STAT_CNT_CLR_SHOT_SET(x)\ + FIELD_PREP(ASM_STAT_CFG_STAT_CNT_CLR_SHOT, x) +#define ASM_STAT_CFG_STAT_CNT_CLR_SHOT_GET(x)\ + FIELD_GET(ASM_STAT_CFG_STAT_CNT_CLR_SHOT, x) + +/* ASM:CFG:PORT_CFG */ +#define ASM_PORT_CFG(r) __REG(TARGET_ASM, 0, 1, 33280, 0, 1, 1088, 540, r, 67, 4) + +#define ASM_PORT_CFG_CSC_STAT_DIS BIT(12) +#define ASM_PORT_CFG_CSC_STAT_DIS_SET(x)\ + FIELD_PREP(ASM_PORT_CFG_CSC_STAT_DIS, x) +#define ASM_PORT_CFG_CSC_STAT_DIS_GET(x)\ + FIELD_GET(ASM_PORT_CFG_CSC_STAT_DIS, x) + +#define ASM_PORT_CFG_HIH_AFTER_PREAMBLE_ENA BIT(11) +#define ASM_PORT_CFG_HIH_AFTER_PREAMBLE_ENA_SET(x)\ + FIELD_PREP(ASM_PORT_CFG_HIH_AFTER_PREAMBLE_ENA, x) +#define ASM_PORT_CFG_HIH_AFTER_PREAMBLE_ENA_GET(x)\ + FIELD_GET(ASM_PORT_CFG_HIH_AFTER_PREAMBLE_ENA, x) + +#define ASM_PORT_CFG_IGN_TAXI_ABORT_ENA BIT(10) +#define ASM_PORT_CFG_IGN_TAXI_ABORT_ENA_SET(x)\ + FIELD_PREP(ASM_PORT_CFG_IGN_TAXI_ABORT_ENA, x) +#define ASM_PORT_CFG_IGN_TAXI_ABORT_ENA_GET(x)\ + FIELD_GET(ASM_PORT_CFG_IGN_TAXI_ABORT_ENA, x) + +#define ASM_PORT_CFG_NO_PREAMBLE_ENA BIT(9) +#define ASM_PORT_CFG_NO_PREAMBLE_ENA_SET(x)\ + FIELD_PREP(ASM_PORT_CFG_NO_PREAMBLE_ENA, x) +#define ASM_PORT_CFG_NO_PREAMBLE_ENA_GET(x)\ + FIELD_GET(ASM_PORT_CFG_NO_PREAMBLE_ENA, x) + +#define ASM_PORT_CFG_SKIP_PREAMBLE_ENA BIT(8) +#define ASM_PORT_CFG_SKIP_PREAMBLE_ENA_SET(x)\ + FIELD_PREP(ASM_PORT_CFG_SKIP_PREAMBLE_ENA, x) +#define ASM_PORT_CFG_SKIP_PREAMBLE_ENA_GET(x)\ + FIELD_GET(ASM_PORT_CFG_SKIP_PREAMBLE_ENA, x) + +#define ASM_PORT_CFG_FRM_AGING_DIS BIT(7) +#define ASM_PORT_CFG_FRM_AGING_DIS_SET(x)\ + FIELD_PREP(ASM_PORT_CFG_FRM_AGING_DIS, x) +#define ASM_PORT_CFG_FRM_AGING_DIS_GET(x)\ + FIELD_GET(ASM_PORT_CFG_FRM_AGING_DIS, x) + +#define ASM_PORT_CFG_PAD_ENA BIT(6) +#define ASM_PORT_CFG_PAD_ENA_SET(x)\ + FIELD_PREP(ASM_PORT_CFG_PAD_ENA, x) +#define ASM_PORT_CFG_PAD_ENA_GET(x)\ + FIELD_GET(ASM_PORT_CFG_PAD_ENA, x) + +#define ASM_PORT_CFG_INJ_DISCARD_CFG GENMASK(5, 4) +#define ASM_PORT_CFG_INJ_DISCARD_CFG_SET(x)\ + FIELD_PREP(ASM_PORT_CFG_INJ_DISCARD_CFG, x) +#define ASM_PORT_CFG_INJ_DISCARD_CFG_GET(x)\ + FIELD_GET(ASM_PORT_CFG_INJ_DISCARD_CFG, x) + +#define ASM_PORT_CFG_INJ_FORMAT_CFG GENMASK(3, 2) +#define ASM_PORT_CFG_INJ_FORMAT_CFG_SET(x)\ + FIELD_PREP(ASM_PORT_CFG_INJ_FORMAT_CFG, x) +#define ASM_PORT_CFG_INJ_FORMAT_CFG_GET(x)\ + FIELD_GET(ASM_PORT_CFG_INJ_FORMAT_CFG, x) + +#define ASM_PORT_CFG_VSTAX2_AWR_ENA BIT(1) +#define ASM_PORT_CFG_VSTAX2_AWR_ENA_SET(x)\ + FIELD_PREP(ASM_PORT_CFG_VSTAX2_AWR_ENA, x) +#define ASM_PORT_CFG_VSTAX2_AWR_ENA_GET(x)\ + FIELD_GET(ASM_PORT_CFG_VSTAX2_AWR_ENA, x) + +#define ASM_PORT_CFG_PFRM_FLUSH BIT(0) +#define ASM_PORT_CFG_PFRM_FLUSH_SET(x)\ + FIELD_PREP(ASM_PORT_CFG_PFRM_FLUSH, x) +#define ASM_PORT_CFG_PFRM_FLUSH_GET(x)\ + FIELD_GET(ASM_PORT_CFG_PFRM_FLUSH, x) + +/* ASM:RAM_CTRL:RAM_INIT */ +#define ASM_RAM_INIT __REG(TARGET_ASM, 0, 1, 34832, 0, 1, 4, 0, 0, 1, 4) + +#define ASM_RAM_INIT_RAM_INIT BIT(1) +#define ASM_RAM_INIT_RAM_INIT_SET(x)\ + FIELD_PREP(ASM_RAM_INIT_RAM_INIT, x) +#define ASM_RAM_INIT_RAM_INIT_GET(x)\ + FIELD_GET(ASM_RAM_INIT_RAM_INIT, x) + +#define ASM_RAM_INIT_RAM_CFG_HOOK BIT(0) +#define ASM_RAM_INIT_RAM_CFG_HOOK_SET(x)\ + FIELD_PREP(ASM_RAM_INIT_RAM_CFG_HOOK, x) +#define ASM_RAM_INIT_RAM_CFG_HOOK_GET(x)\ + FIELD_GET(ASM_RAM_INIT_RAM_CFG_HOOK, x) + +/* CLKGEN:LCPLL1:LCPLL1_CORE_CLK_CFG */ +#define CLKGEN_LCPLL1_CORE_CLK_CFG __REG(TARGET_CLKGEN, 0, 1, 12, 0, 1, 36, 0, 0, 1, 4) + +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_DIV GENMASK(7, 0) +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_DIV_SET(x)\ + FIELD_PREP(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_DIV, x) +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_DIV_GET(x)\ + FIELD_GET(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_DIV, x) + +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_PRE_DIV GENMASK(10, 8) +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_PRE_DIV_SET(x)\ + FIELD_PREP(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_PRE_DIV, x) +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_PRE_DIV_GET(x)\ + FIELD_GET(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_PRE_DIV, x) + +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_DIR BIT(11) +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_DIR_SET(x)\ + FIELD_PREP(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_DIR, x) +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_DIR_GET(x)\ + FIELD_GET(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_DIR, x) + +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_SEL GENMASK(13, 12) +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_SEL_SET(x)\ + FIELD_PREP(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_SEL, x) +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_SEL_GET(x)\ + FIELD_GET(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_SEL, x) + +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_ENA BIT(14) +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_ENA_SET(x)\ + FIELD_PREP(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_ENA, x) +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_ENA_GET(x)\ + FIELD_GET(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_ROT_ENA, x) + +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_ENA BIT(15) +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_ENA_SET(x)\ + FIELD_PREP(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_ENA, x) +#define CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_ENA_GET(x)\ + FIELD_GET(CLKGEN_LCPLL1_CORE_CLK_CFG_CORE_CLK_ENA, x) + +/* CPU:CPU_REGS:PROC_CTRL */ +#define CPU_PROC_CTRL __REG(TARGET_CPU, 0, 1, 0, 0, 1, 204, 176, 0, 1, 4) + +#define CPU_PROC_CTRL_AARCH64_MODE_ENA BIT(12) +#define CPU_PROC_CTRL_AARCH64_MODE_ENA_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_AARCH64_MODE_ENA, x) +#define CPU_PROC_CTRL_AARCH64_MODE_ENA_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_AARCH64_MODE_ENA, x) + +#define CPU_PROC_CTRL_L2_RST_INVALIDATE_DIS BIT(11) +#define CPU_PROC_CTRL_L2_RST_INVALIDATE_DIS_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_L2_RST_INVALIDATE_DIS, x) +#define CPU_PROC_CTRL_L2_RST_INVALIDATE_DIS_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_L2_RST_INVALIDATE_DIS, x) + +#define CPU_PROC_CTRL_L1_RST_INVALIDATE_DIS BIT(10) +#define CPU_PROC_CTRL_L1_RST_INVALIDATE_DIS_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_L1_RST_INVALIDATE_DIS, x) +#define CPU_PROC_CTRL_L1_RST_INVALIDATE_DIS_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_L1_RST_INVALIDATE_DIS, x) + +#define CPU_PROC_CTRL_BE_EXCEP_MODE BIT(9) +#define CPU_PROC_CTRL_BE_EXCEP_MODE_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_BE_EXCEP_MODE, x) +#define CPU_PROC_CTRL_BE_EXCEP_MODE_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_BE_EXCEP_MODE, x) + +#define CPU_PROC_CTRL_VINITHI BIT(8) +#define CPU_PROC_CTRL_VINITHI_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_VINITHI, x) +#define CPU_PROC_CTRL_VINITHI_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_VINITHI, x) + +#define CPU_PROC_CTRL_CFGTE BIT(7) +#define CPU_PROC_CTRL_CFGTE_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_CFGTE, x) +#define CPU_PROC_CTRL_CFGTE_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_CFGTE, x) + +#define CPU_PROC_CTRL_CP15S_DISABLE BIT(6) +#define CPU_PROC_CTRL_CP15S_DISABLE_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_CP15S_DISABLE, x) +#define CPU_PROC_CTRL_CP15S_DISABLE_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_CP15S_DISABLE, x) + +#define CPU_PROC_CTRL_PROC_CRYPTO_DISABLE BIT(5) +#define CPU_PROC_CTRL_PROC_CRYPTO_DISABLE_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_PROC_CRYPTO_DISABLE, x) +#define CPU_PROC_CTRL_PROC_CRYPTO_DISABLE_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_PROC_CRYPTO_DISABLE, x) + +#define CPU_PROC_CTRL_ACP_CACHE_FORCE_ENA BIT(4) +#define CPU_PROC_CTRL_ACP_CACHE_FORCE_ENA_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_ACP_CACHE_FORCE_ENA, x) +#define CPU_PROC_CTRL_ACP_CACHE_FORCE_ENA_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_ACP_CACHE_FORCE_ENA, x) + +#define CPU_PROC_CTRL_ACP_AWCACHE BIT(3) +#define CPU_PROC_CTRL_ACP_AWCACHE_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_ACP_AWCACHE, x) +#define CPU_PROC_CTRL_ACP_AWCACHE_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_ACP_AWCACHE, x) + +#define CPU_PROC_CTRL_ACP_ARCACHE BIT(2) +#define CPU_PROC_CTRL_ACP_ARCACHE_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_ACP_ARCACHE, x) +#define CPU_PROC_CTRL_ACP_ARCACHE_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_ACP_ARCACHE, x) + +#define CPU_PROC_CTRL_L2_FLUSH_REQ BIT(1) +#define CPU_PROC_CTRL_L2_FLUSH_REQ_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_L2_FLUSH_REQ, x) +#define CPU_PROC_CTRL_L2_FLUSH_REQ_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_L2_FLUSH_REQ, x) + +#define CPU_PROC_CTRL_ACP_DISABLE BIT(0) +#define CPU_PROC_CTRL_ACP_DISABLE_SET(x)\ + FIELD_PREP(CPU_PROC_CTRL_ACP_DISABLE, x) +#define CPU_PROC_CTRL_ACP_DISABLE_GET(x)\ + FIELD_GET(CPU_PROC_CTRL_ACP_DISABLE, x) + +/* DEV10G:MAC_CFG_STATUS:MAC_ENA_CFG */ +#define DEV10G_MAC_ENA_CFG(t) __REG(TARGET_DEV10G, t, 12, 0, 0, 1, 60, 0, 0, 1, 4) + +#define DEV10G_MAC_ENA_CFG_RX_ENA BIT(4) +#define DEV10G_MAC_ENA_CFG_RX_ENA_SET(x)\ + FIELD_PREP(DEV10G_MAC_ENA_CFG_RX_ENA, x) +#define DEV10G_MAC_ENA_CFG_RX_ENA_GET(x)\ + FIELD_GET(DEV10G_MAC_ENA_CFG_RX_ENA, x) + +#define DEV10G_MAC_ENA_CFG_TX_ENA BIT(0) +#define DEV10G_MAC_ENA_CFG_TX_ENA_SET(x)\ + FIELD_PREP(DEV10G_MAC_ENA_CFG_TX_ENA, x) +#define DEV10G_MAC_ENA_CFG_TX_ENA_GET(x)\ + FIELD_GET(DEV10G_MAC_ENA_CFG_TX_ENA, x) + +/* DEV10G:MAC_CFG_STATUS:MAC_MAXLEN_CFG */ +#define DEV10G_MAC_MAXLEN_CFG(t) __REG(TARGET_DEV10G, t, 12, 0, 0, 1, 60, 8, 0, 1, 4) + +#define DEV10G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK BIT(16) +#define DEV10G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK_SET(x)\ + FIELD_PREP(DEV10G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK, x) +#define DEV10G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK_GET(x)\ + FIELD_GET(DEV10G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK, x) + +#define DEV10G_MAC_MAXLEN_CFG_MAX_LEN GENMASK(15, 0) +#define DEV10G_MAC_MAXLEN_CFG_MAX_LEN_SET(x)\ + FIELD_PREP(DEV10G_MAC_MAXLEN_CFG_MAX_LEN, x) +#define DEV10G_MAC_MAXLEN_CFG_MAX_LEN_GET(x)\ + FIELD_GET(DEV10G_MAC_MAXLEN_CFG_MAX_LEN, x) + +/* DEV10G:MAC_CFG_STATUS:MAC_NUM_TAGS_CFG */ +#define DEV10G_MAC_NUM_TAGS_CFG(t) __REG(TARGET_DEV10G, t, 12, 0, 0, 1, 60, 12, 0, 1, 4) + +#define DEV10G_MAC_NUM_TAGS_CFG_NUM_TAGS GENMASK(1, 0) +#define DEV10G_MAC_NUM_TAGS_CFG_NUM_TAGS_SET(x)\ + FIELD_PREP(DEV10G_MAC_NUM_TAGS_CFG_NUM_TAGS, x) +#define DEV10G_MAC_NUM_TAGS_CFG_NUM_TAGS_GET(x)\ + FIELD_GET(DEV10G_MAC_NUM_TAGS_CFG_NUM_TAGS, x) + +/* DEV10G:MAC_CFG_STATUS:MAC_TAGS_CFG */ +#define DEV10G_MAC_TAGS_CFG(t, r) __REG(TARGET_DEV10G, t, 12, 0, 0, 1, 60, 16, r, 3, 4) + +#define DEV10G_MAC_TAGS_CFG_TAG_ID GENMASK(31, 16) +#define DEV10G_MAC_TAGS_CFG_TAG_ID_SET(x)\ + FIELD_PREP(DEV10G_MAC_TAGS_CFG_TAG_ID, x) +#define DEV10G_MAC_TAGS_CFG_TAG_ID_GET(x)\ + FIELD_GET(DEV10G_MAC_TAGS_CFG_TAG_ID, x) + +#define DEV10G_MAC_TAGS_CFG_TAG_ENA BIT(4) +#define DEV10G_MAC_TAGS_CFG_TAG_ENA_SET(x)\ + FIELD_PREP(DEV10G_MAC_TAGS_CFG_TAG_ENA, x) +#define DEV10G_MAC_TAGS_CFG_TAG_ENA_GET(x)\ + FIELD_GET(DEV10G_MAC_TAGS_CFG_TAG_ENA, x) + +/* DEV10G:MAC_CFG_STATUS:MAC_ADV_CHK_CFG */ +#define DEV10G_MAC_ADV_CHK_CFG(t) __REG(TARGET_DEV10G, t, 12, 0, 0, 1, 60, 28, 0, 1, 4) + +#define DEV10G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA BIT(24) +#define DEV10G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA_SET(x)\ + FIELD_PREP(DEV10G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA, x) +#define DEV10G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA_GET(x)\ + FIELD_GET(DEV10G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA, x) + +#define DEV10G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA BIT(20) +#define DEV10G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA_SET(x)\ + FIELD_PREP(DEV10G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA, x) +#define DEV10G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA_GET(x)\ + FIELD_GET(DEV10G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA, x) + +#define DEV10G_MAC_ADV_CHK_CFG_SFD_CHK_ENA BIT(16) +#define DEV10G_MAC_ADV_CHK_CFG_SFD_CHK_ENA_SET(x)\ + FIELD_PREP(DEV10G_MAC_ADV_CHK_CFG_SFD_CHK_ENA, x) +#define DEV10G_MAC_ADV_CHK_CFG_SFD_CHK_ENA_GET(x)\ + FIELD_GET(DEV10G_MAC_ADV_CHK_CFG_SFD_CHK_ENA, x) + +#define DEV10G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS BIT(12) +#define DEV10G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS_SET(x)\ + FIELD_PREP(DEV10G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS, x) +#define DEV10G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS_GET(x)\ + FIELD_GET(DEV10G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS, x) + +#define DEV10G_MAC_ADV_CHK_CFG_PRM_CHK_ENA BIT(8) +#define DEV10G_MAC_ADV_CHK_CFG_PRM_CHK_ENA_SET(x)\ + FIELD_PREP(DEV10G_MAC_ADV_CHK_CFG_PRM_CHK_ENA, x) +#define DEV10G_MAC_ADV_CHK_CFG_PRM_CHK_ENA_GET(x)\ + FIELD_GET(DEV10G_MAC_ADV_CHK_CFG_PRM_CHK_ENA, x) + +#define DEV10G_MAC_ADV_CHK_CFG_OOR_ERR_ENA BIT(4) +#define DEV10G_MAC_ADV_CHK_CFG_OOR_ERR_ENA_SET(x)\ + FIELD_PREP(DEV10G_MAC_ADV_CHK_CFG_OOR_ERR_ENA, x) +#define DEV10G_MAC_ADV_CHK_CFG_OOR_ERR_ENA_GET(x)\ + FIELD_GET(DEV10G_MAC_ADV_CHK_CFG_OOR_ERR_ENA, x) + +#define DEV10G_MAC_ADV_CHK_CFG_INR_ERR_ENA BIT(0) +#define DEV10G_MAC_ADV_CHK_CFG_INR_ERR_ENA_SET(x)\ + FIELD_PREP(DEV10G_MAC_ADV_CHK_CFG_INR_ERR_ENA, x) +#define DEV10G_MAC_ADV_CHK_CFG_INR_ERR_ENA_GET(x)\ + FIELD_GET(DEV10G_MAC_ADV_CHK_CFG_INR_ERR_ENA, x) + +/* DEV10G:MAC_CFG_STATUS:MAC_TX_MONITOR_STICKY */ +#define DEV10G_MAC_TX_MONITOR_STICKY(t) __REG(TARGET_DEV10G, t, 12, 0, 0, 1, 60, 48, 0, 1, 4) + +#define DEV10G_MAC_TX_MONITOR_STICKY_LOCAL_ERR_STATE_STICKY BIT(4) +#define DEV10G_MAC_TX_MONITOR_STICKY_LOCAL_ERR_STATE_STICKY_SET(x)\ + FIELD_PREP(DEV10G_MAC_TX_MONITOR_STICKY_LOCAL_ERR_STATE_STICKY, x) +#define DEV10G_MAC_TX_MONITOR_STICKY_LOCAL_ERR_STATE_STICKY_GET(x)\ + FIELD_GET(DEV10G_MAC_TX_MONITOR_STICKY_LOCAL_ERR_STATE_STICKY, x) + +#define DEV10G_MAC_TX_MONITOR_STICKY_REMOTE_ERR_STATE_STICKY BIT(3) +#define DEV10G_MAC_TX_MONITOR_STICKY_REMOTE_ERR_STATE_STICKY_SET(x)\ + FIELD_PREP(DEV10G_MAC_TX_MONITOR_STICKY_REMOTE_ERR_STATE_STICKY, x) +#define DEV10G_MAC_TX_MONITOR_STICKY_REMOTE_ERR_STATE_STICKY_GET(x)\ + FIELD_GET(DEV10G_MAC_TX_MONITOR_STICKY_REMOTE_ERR_STATE_STICKY, x) + +#define DEV10G_MAC_TX_MONITOR_STICKY_LINK_INTERRUPTION_STATE_STICKY BIT(2) +#define DEV10G_MAC_TX_MONITOR_STICKY_LINK_INTERRUPTION_STATE_STICKY_SET(x)\ + FIELD_PREP(DEV10G_MAC_TX_MONITOR_STICKY_LINK_INTERRUPTION_STATE_STICKY, x) +#define DEV10G_MAC_TX_MONITOR_STICKY_LINK_INTERRUPTION_STATE_STICKY_GET(x)\ + FIELD_GET(DEV10G_MAC_TX_MONITOR_STICKY_LINK_INTERRUPTION_STATE_STICKY, x) + +#define DEV10G_MAC_TX_MONITOR_STICKY_IDLE_STATE_STICKY BIT(1) +#define DEV10G_MAC_TX_MONITOR_STICKY_IDLE_STATE_STICKY_SET(x)\ + FIELD_PREP(DEV10G_MAC_TX_MONITOR_STICKY_IDLE_STATE_STICKY, x) +#define DEV10G_MAC_TX_MONITOR_STICKY_IDLE_STATE_STICKY_GET(x)\ + FIELD_GET(DEV10G_MAC_TX_MONITOR_STICKY_IDLE_STATE_STICKY, x) + +#define DEV10G_MAC_TX_MONITOR_STICKY_DIS_STATE_STICKY BIT(0) +#define DEV10G_MAC_TX_MONITOR_STICKY_DIS_STATE_STICKY_SET(x)\ + FIELD_PREP(DEV10G_MAC_TX_MONITOR_STICKY_DIS_STATE_STICKY, x) +#define DEV10G_MAC_TX_MONITOR_STICKY_DIS_STATE_STICKY_GET(x)\ + FIELD_GET(DEV10G_MAC_TX_MONITOR_STICKY_DIS_STATE_STICKY, x) + +/* DEV10G:DEV_CFG_STATUS:DEV_RST_CTRL */ +#define DEV10G_DEV_RST_CTRL(t) __REG(TARGET_DEV10G, t, 12, 436, 0, 1, 52, 0, 0, 1, 4) + +#define DEV10G_DEV_RST_CTRL_PARDET_MODE_ENA BIT(28) +#define DEV10G_DEV_RST_CTRL_PARDET_MODE_ENA_SET(x)\ + FIELD_PREP(DEV10G_DEV_RST_CTRL_PARDET_MODE_ENA, x) +#define DEV10G_DEV_RST_CTRL_PARDET_MODE_ENA_GET(x)\ + FIELD_GET(DEV10G_DEV_RST_CTRL_PARDET_MODE_ENA, x) + +#define DEV10G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS BIT(27) +#define DEV10G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS_SET(x)\ + FIELD_PREP(DEV10G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS, x) +#define DEV10G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS_GET(x)\ + FIELD_GET(DEV10G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS, x) + +#define DEV10G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS GENMASK(26, 25) +#define DEV10G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS_SET(x)\ + FIELD_PREP(DEV10G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS, x) +#define DEV10G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS_GET(x)\ + FIELD_GET(DEV10G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS, x) + +#define DEV10G_DEV_RST_CTRL_SERDES_SPEED_SEL GENMASK(24, 23) +#define DEV10G_DEV_RST_CTRL_SERDES_SPEED_SEL_SET(x)\ + FIELD_PREP(DEV10G_DEV_RST_CTRL_SERDES_SPEED_SEL, x) +#define DEV10G_DEV_RST_CTRL_SERDES_SPEED_SEL_GET(x)\ + FIELD_GET(DEV10G_DEV_RST_CTRL_SERDES_SPEED_SEL, x) + +#define DEV10G_DEV_RST_CTRL_SPEED_SEL GENMASK(22, 20) +#define DEV10G_DEV_RST_CTRL_SPEED_SEL_SET(x)\ + FIELD_PREP(DEV10G_DEV_RST_CTRL_SPEED_SEL, x) +#define DEV10G_DEV_RST_CTRL_SPEED_SEL_GET(x)\ + FIELD_GET(DEV10G_DEV_RST_CTRL_SPEED_SEL, x) + +#define DEV10G_DEV_RST_CTRL_PCS_TX_RST BIT(12) +#define DEV10G_DEV_RST_CTRL_PCS_TX_RST_SET(x)\ + FIELD_PREP(DEV10G_DEV_RST_CTRL_PCS_TX_RST, x) +#define DEV10G_DEV_RST_CTRL_PCS_TX_RST_GET(x)\ + FIELD_GET(DEV10G_DEV_RST_CTRL_PCS_TX_RST, x) + +#define DEV10G_DEV_RST_CTRL_PCS_RX_RST BIT(8) +#define DEV10G_DEV_RST_CTRL_PCS_RX_RST_SET(x)\ + FIELD_PREP(DEV10G_DEV_RST_CTRL_PCS_RX_RST, x) +#define DEV10G_DEV_RST_CTRL_PCS_RX_RST_GET(x)\ + FIELD_GET(DEV10G_DEV_RST_CTRL_PCS_RX_RST, x) + +#define DEV10G_DEV_RST_CTRL_MAC_TX_RST BIT(4) +#define DEV10G_DEV_RST_CTRL_MAC_TX_RST_SET(x)\ + FIELD_PREP(DEV10G_DEV_RST_CTRL_MAC_TX_RST, x) +#define DEV10G_DEV_RST_CTRL_MAC_TX_RST_GET(x)\ + FIELD_GET(DEV10G_DEV_RST_CTRL_MAC_TX_RST, x) + +#define DEV10G_DEV_RST_CTRL_MAC_RX_RST BIT(0) +#define DEV10G_DEV_RST_CTRL_MAC_RX_RST_SET(x)\ + FIELD_PREP(DEV10G_DEV_RST_CTRL_MAC_RX_RST, x) +#define DEV10G_DEV_RST_CTRL_MAC_RX_RST_GET(x)\ + FIELD_GET(DEV10G_DEV_RST_CTRL_MAC_RX_RST, x) + +/* DEV10G:PCS25G_CFG_STATUS:PCS25G_CFG */ +#define DEV10G_PCS25G_CFG(t) __REG(TARGET_DEV10G, t, 12, 488, 0, 1, 32, 0, 0, 1, 4) + +#define DEV10G_PCS25G_CFG_PCS25G_ENA BIT(0) +#define DEV10G_PCS25G_CFG_PCS25G_ENA_SET(x)\ + FIELD_PREP(DEV10G_PCS25G_CFG_PCS25G_ENA, x) +#define DEV10G_PCS25G_CFG_PCS25G_ENA_GET(x)\ + FIELD_GET(DEV10G_PCS25G_CFG_PCS25G_ENA, x) + +/* DEV10G:MAC_CFG_STATUS:MAC_ENA_CFG */ +#define DEV25G_MAC_ENA_CFG(t) __REG(TARGET_DEV25G, t, 8, 0, 0, 1, 60, 0, 0, 1, 4) + +#define DEV25G_MAC_ENA_CFG_RX_ENA BIT(4) +#define DEV25G_MAC_ENA_CFG_RX_ENA_SET(x)\ + FIELD_PREP(DEV25G_MAC_ENA_CFG_RX_ENA, x) +#define DEV25G_MAC_ENA_CFG_RX_ENA_GET(x)\ + FIELD_GET(DEV25G_MAC_ENA_CFG_RX_ENA, x) + +#define DEV25G_MAC_ENA_CFG_TX_ENA BIT(0) +#define DEV25G_MAC_ENA_CFG_TX_ENA_SET(x)\ + FIELD_PREP(DEV25G_MAC_ENA_CFG_TX_ENA, x) +#define DEV25G_MAC_ENA_CFG_TX_ENA_GET(x)\ + FIELD_GET(DEV25G_MAC_ENA_CFG_TX_ENA, x) + +/* DEV10G:MAC_CFG_STATUS:MAC_MAXLEN_CFG */ +#define DEV25G_MAC_MAXLEN_CFG(t) __REG(TARGET_DEV25G, t, 8, 0, 0, 1, 60, 8, 0, 1, 4) + +#define DEV25G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK BIT(16) +#define DEV25G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK_SET(x)\ + FIELD_PREP(DEV25G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK, x) +#define DEV25G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK_GET(x)\ + FIELD_GET(DEV25G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK, x) + +#define DEV25G_MAC_MAXLEN_CFG_MAX_LEN GENMASK(15, 0) +#define DEV25G_MAC_MAXLEN_CFG_MAX_LEN_SET(x)\ + FIELD_PREP(DEV25G_MAC_MAXLEN_CFG_MAX_LEN, x) +#define DEV25G_MAC_MAXLEN_CFG_MAX_LEN_GET(x)\ + FIELD_GET(DEV25G_MAC_MAXLEN_CFG_MAX_LEN, x) + +/* DEV10G:MAC_CFG_STATUS:MAC_ADV_CHK_CFG */ +#define DEV25G_MAC_ADV_CHK_CFG(t) __REG(TARGET_DEV25G, t, 8, 0, 0, 1, 60, 28, 0, 1, 4) + +#define DEV25G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA BIT(24) +#define DEV25G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA_SET(x)\ + FIELD_PREP(DEV25G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA, x) +#define DEV25G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA_GET(x)\ + FIELD_GET(DEV25G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA, x) + +#define DEV25G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA BIT(20) +#define DEV25G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA_SET(x)\ + FIELD_PREP(DEV25G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA, x) +#define DEV25G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA_GET(x)\ + FIELD_GET(DEV25G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA, x) + +#define DEV25G_MAC_ADV_CHK_CFG_SFD_CHK_ENA BIT(16) +#define DEV25G_MAC_ADV_CHK_CFG_SFD_CHK_ENA_SET(x)\ + FIELD_PREP(DEV25G_MAC_ADV_CHK_CFG_SFD_CHK_ENA, x) +#define DEV25G_MAC_ADV_CHK_CFG_SFD_CHK_ENA_GET(x)\ + FIELD_GET(DEV25G_MAC_ADV_CHK_CFG_SFD_CHK_ENA, x) + +#define DEV25G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS BIT(12) +#define DEV25G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS_SET(x)\ + FIELD_PREP(DEV25G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS, x) +#define DEV25G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS_GET(x)\ + FIELD_GET(DEV25G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS, x) + +#define DEV25G_MAC_ADV_CHK_CFG_PRM_CHK_ENA BIT(8) +#define DEV25G_MAC_ADV_CHK_CFG_PRM_CHK_ENA_SET(x)\ + FIELD_PREP(DEV25G_MAC_ADV_CHK_CFG_PRM_CHK_ENA, x) +#define DEV25G_MAC_ADV_CHK_CFG_PRM_CHK_ENA_GET(x)\ + FIELD_GET(DEV25G_MAC_ADV_CHK_CFG_PRM_CHK_ENA, x) + +#define DEV25G_MAC_ADV_CHK_CFG_OOR_ERR_ENA BIT(4) +#define DEV25G_MAC_ADV_CHK_CFG_OOR_ERR_ENA_SET(x)\ + FIELD_PREP(DEV25G_MAC_ADV_CHK_CFG_OOR_ERR_ENA, x) +#define DEV25G_MAC_ADV_CHK_CFG_OOR_ERR_ENA_GET(x)\ + FIELD_GET(DEV25G_MAC_ADV_CHK_CFG_OOR_ERR_ENA, x) + +#define DEV25G_MAC_ADV_CHK_CFG_INR_ERR_ENA BIT(0) +#define DEV25G_MAC_ADV_CHK_CFG_INR_ERR_ENA_SET(x)\ + FIELD_PREP(DEV25G_MAC_ADV_CHK_CFG_INR_ERR_ENA, x) +#define DEV25G_MAC_ADV_CHK_CFG_INR_ERR_ENA_GET(x)\ + FIELD_GET(DEV25G_MAC_ADV_CHK_CFG_INR_ERR_ENA, x) + +/* DEV10G:DEV_CFG_STATUS:DEV_RST_CTRL */ +#define DEV25G_DEV_RST_CTRL(t) __REG(TARGET_DEV25G, t, 8, 436, 0, 1, 52, 0, 0, 1, 4) + +#define DEV25G_DEV_RST_CTRL_PARDET_MODE_ENA BIT(28) +#define DEV25G_DEV_RST_CTRL_PARDET_MODE_ENA_SET(x)\ + FIELD_PREP(DEV25G_DEV_RST_CTRL_PARDET_MODE_ENA, x) +#define DEV25G_DEV_RST_CTRL_PARDET_MODE_ENA_GET(x)\ + FIELD_GET(DEV25G_DEV_RST_CTRL_PARDET_MODE_ENA, x) + +#define DEV25G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS BIT(27) +#define DEV25G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS_SET(x)\ + FIELD_PREP(DEV25G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS, x) +#define DEV25G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS_GET(x)\ + FIELD_GET(DEV25G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS, x) + +#define DEV25G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS GENMASK(26, 25) +#define DEV25G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS_SET(x)\ + FIELD_PREP(DEV25G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS, x) +#define DEV25G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS_GET(x)\ + FIELD_GET(DEV25G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS, x) + +#define DEV25G_DEV_RST_CTRL_SERDES_SPEED_SEL GENMASK(24, 23) +#define DEV25G_DEV_RST_CTRL_SERDES_SPEED_SEL_SET(x)\ + FIELD_PREP(DEV25G_DEV_RST_CTRL_SERDES_SPEED_SEL, x) +#define DEV25G_DEV_RST_CTRL_SERDES_SPEED_SEL_GET(x)\ + FIELD_GET(DEV25G_DEV_RST_CTRL_SERDES_SPEED_SEL, x) + +#define DEV25G_DEV_RST_CTRL_SPEED_SEL GENMASK(22, 20) +#define DEV25G_DEV_RST_CTRL_SPEED_SEL_SET(x)\ + FIELD_PREP(DEV25G_DEV_RST_CTRL_SPEED_SEL, x) +#define DEV25G_DEV_RST_CTRL_SPEED_SEL_GET(x)\ + FIELD_GET(DEV25G_DEV_RST_CTRL_SPEED_SEL, x) + +#define DEV25G_DEV_RST_CTRL_PCS_TX_RST BIT(12) +#define DEV25G_DEV_RST_CTRL_PCS_TX_RST_SET(x)\ + FIELD_PREP(DEV25G_DEV_RST_CTRL_PCS_TX_RST, x) +#define DEV25G_DEV_RST_CTRL_PCS_TX_RST_GET(x)\ + FIELD_GET(DEV25G_DEV_RST_CTRL_PCS_TX_RST, x) + +#define DEV25G_DEV_RST_CTRL_PCS_RX_RST BIT(8) +#define DEV25G_DEV_RST_CTRL_PCS_RX_RST_SET(x)\ + FIELD_PREP(DEV25G_DEV_RST_CTRL_PCS_RX_RST, x) +#define DEV25G_DEV_RST_CTRL_PCS_RX_RST_GET(x)\ + FIELD_GET(DEV25G_DEV_RST_CTRL_PCS_RX_RST, x) + +#define DEV25G_DEV_RST_CTRL_MAC_TX_RST BIT(4) +#define DEV25G_DEV_RST_CTRL_MAC_TX_RST_SET(x)\ + FIELD_PREP(DEV25G_DEV_RST_CTRL_MAC_TX_RST, x) +#define DEV25G_DEV_RST_CTRL_MAC_TX_RST_GET(x)\ + FIELD_GET(DEV25G_DEV_RST_CTRL_MAC_TX_RST, x) + +#define DEV25G_DEV_RST_CTRL_MAC_RX_RST BIT(0) +#define DEV25G_DEV_RST_CTRL_MAC_RX_RST_SET(x)\ + FIELD_PREP(DEV25G_DEV_RST_CTRL_MAC_RX_RST, x) +#define DEV25G_DEV_RST_CTRL_MAC_RX_RST_GET(x)\ + FIELD_GET(DEV25G_DEV_RST_CTRL_MAC_RX_RST, x) + +/* DEV10G:PCS25G_CFG_STATUS:PCS25G_CFG */ +#define DEV25G_PCS25G_CFG(t) __REG(TARGET_DEV25G, t, 8, 488, 0, 1, 32, 0, 0, 1, 4) + +#define DEV25G_PCS25G_CFG_PCS25G_ENA BIT(0) +#define DEV25G_PCS25G_CFG_PCS25G_ENA_SET(x)\ + FIELD_PREP(DEV25G_PCS25G_CFG_PCS25G_ENA, x) +#define DEV25G_PCS25G_CFG_PCS25G_ENA_GET(x)\ + FIELD_GET(DEV25G_PCS25G_CFG_PCS25G_ENA, x) + +/* DEV10G:PCS25G_CFG_STATUS:PCS25G_SD_CFG */ +#define DEV25G_PCS25G_SD_CFG(t) __REG(TARGET_DEV25G, t, 8, 488, 0, 1, 32, 4, 0, 1, 4) + +#define DEV25G_PCS25G_SD_CFG_SD_SEL BIT(8) +#define DEV25G_PCS25G_SD_CFG_SD_SEL_SET(x)\ + FIELD_PREP(DEV25G_PCS25G_SD_CFG_SD_SEL, x) +#define DEV25G_PCS25G_SD_CFG_SD_SEL_GET(x)\ + FIELD_GET(DEV25G_PCS25G_SD_CFG_SD_SEL, x) + +#define DEV25G_PCS25G_SD_CFG_SD_POL BIT(4) +#define DEV25G_PCS25G_SD_CFG_SD_POL_SET(x)\ + FIELD_PREP(DEV25G_PCS25G_SD_CFG_SD_POL, x) +#define DEV25G_PCS25G_SD_CFG_SD_POL_GET(x)\ + FIELD_GET(DEV25G_PCS25G_SD_CFG_SD_POL, x) + +#define DEV25G_PCS25G_SD_CFG_SD_ENA BIT(0) +#define DEV25G_PCS25G_SD_CFG_SD_ENA_SET(x)\ + FIELD_PREP(DEV25G_PCS25G_SD_CFG_SD_ENA, x) +#define DEV25G_PCS25G_SD_CFG_SD_ENA_GET(x)\ + FIELD_GET(DEV25G_PCS25G_SD_CFG_SD_ENA, x) + +/* DEV1G:DEV_CFG_STATUS:DEV_RST_CTRL */ +#define DEV2G5_DEV_RST_CTRL(t) __REG(TARGET_DEV2G5, t, 65, 0, 0, 1, 36, 0, 0, 1, 4) + +#define DEV2G5_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS BIT(23) +#define DEV2G5_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS_SET(x)\ + FIELD_PREP(DEV2G5_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS, x) +#define DEV2G5_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS_GET(x)\ + FIELD_GET(DEV2G5_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS, x) + +#define DEV2G5_DEV_RST_CTRL_SPEED_SEL GENMASK(22, 20) +#define DEV2G5_DEV_RST_CTRL_SPEED_SEL_SET(x)\ + FIELD_PREP(DEV2G5_DEV_RST_CTRL_SPEED_SEL, x) +#define DEV2G5_DEV_RST_CTRL_SPEED_SEL_GET(x)\ + FIELD_GET(DEV2G5_DEV_RST_CTRL_SPEED_SEL, x) + +#define DEV2G5_DEV_RST_CTRL_USX_PCS_TX_RST BIT(17) +#define DEV2G5_DEV_RST_CTRL_USX_PCS_TX_RST_SET(x)\ + FIELD_PREP(DEV2G5_DEV_RST_CTRL_USX_PCS_TX_RST, x) +#define DEV2G5_DEV_RST_CTRL_USX_PCS_TX_RST_GET(x)\ + FIELD_GET(DEV2G5_DEV_RST_CTRL_USX_PCS_TX_RST, x) + +#define DEV2G5_DEV_RST_CTRL_USX_PCS_RX_RST BIT(16) +#define DEV2G5_DEV_RST_CTRL_USX_PCS_RX_RST_SET(x)\ + FIELD_PREP(DEV2G5_DEV_RST_CTRL_USX_PCS_RX_RST, x) +#define DEV2G5_DEV_RST_CTRL_USX_PCS_RX_RST_GET(x)\ + FIELD_GET(DEV2G5_DEV_RST_CTRL_USX_PCS_RX_RST, x) + +#define DEV2G5_DEV_RST_CTRL_PCS_TX_RST BIT(12) +#define DEV2G5_DEV_RST_CTRL_PCS_TX_RST_SET(x)\ + FIELD_PREP(DEV2G5_DEV_RST_CTRL_PCS_TX_RST, x) +#define DEV2G5_DEV_RST_CTRL_PCS_TX_RST_GET(x)\ + FIELD_GET(DEV2G5_DEV_RST_CTRL_PCS_TX_RST, x) + +#define DEV2G5_DEV_RST_CTRL_PCS_RX_RST BIT(8) +#define DEV2G5_DEV_RST_CTRL_PCS_RX_RST_SET(x)\ + FIELD_PREP(DEV2G5_DEV_RST_CTRL_PCS_RX_RST, x) +#define DEV2G5_DEV_RST_CTRL_PCS_RX_RST_GET(x)\ + FIELD_GET(DEV2G5_DEV_RST_CTRL_PCS_RX_RST, x) + +#define DEV2G5_DEV_RST_CTRL_MAC_TX_RST BIT(4) +#define DEV2G5_DEV_RST_CTRL_MAC_TX_RST_SET(x)\ + FIELD_PREP(DEV2G5_DEV_RST_CTRL_MAC_TX_RST, x) +#define DEV2G5_DEV_RST_CTRL_MAC_TX_RST_GET(x)\ + FIELD_GET(DEV2G5_DEV_RST_CTRL_MAC_TX_RST, x) + +#define DEV2G5_DEV_RST_CTRL_MAC_RX_RST BIT(0) +#define DEV2G5_DEV_RST_CTRL_MAC_RX_RST_SET(x)\ + FIELD_PREP(DEV2G5_DEV_RST_CTRL_MAC_RX_RST, x) +#define DEV2G5_DEV_RST_CTRL_MAC_RX_RST_GET(x)\ + FIELD_GET(DEV2G5_DEV_RST_CTRL_MAC_RX_RST, x) + +/* DEV1G:MAC_CFG_STATUS:MAC_ENA_CFG */ +#define DEV2G5_MAC_ENA_CFG(t) __REG(TARGET_DEV2G5, t, 65, 52, 0, 1, 36, 0, 0, 1, 4) + +#define DEV2G5_MAC_ENA_CFG_RX_ENA BIT(4) +#define DEV2G5_MAC_ENA_CFG_RX_ENA_SET(x)\ + FIELD_PREP(DEV2G5_MAC_ENA_CFG_RX_ENA, x) +#define DEV2G5_MAC_ENA_CFG_RX_ENA_GET(x)\ + FIELD_GET(DEV2G5_MAC_ENA_CFG_RX_ENA, x) + +#define DEV2G5_MAC_ENA_CFG_TX_ENA BIT(0) +#define DEV2G5_MAC_ENA_CFG_TX_ENA_SET(x)\ + FIELD_PREP(DEV2G5_MAC_ENA_CFG_TX_ENA, x) +#define DEV2G5_MAC_ENA_CFG_TX_ENA_GET(x)\ + FIELD_GET(DEV2G5_MAC_ENA_CFG_TX_ENA, x) + +/* DEV1G:MAC_CFG_STATUS:MAC_MODE_CFG */ +#define DEV2G5_MAC_MODE_CFG(t) __REG(TARGET_DEV2G5, t, 65, 52, 0, 1, 36, 4, 0, 1, 4) + +#define DEV2G5_MAC_MODE_CFG_FC_WORD_SYNC_ENA BIT(8) +#define DEV2G5_MAC_MODE_CFG_FC_WORD_SYNC_ENA_SET(x)\ + FIELD_PREP(DEV2G5_MAC_MODE_CFG_FC_WORD_SYNC_ENA, x) +#define DEV2G5_MAC_MODE_CFG_FC_WORD_SYNC_ENA_GET(x)\ + FIELD_GET(DEV2G5_MAC_MODE_CFG_FC_WORD_SYNC_ENA, x) + +#define DEV2G5_MAC_MODE_CFG_GIGA_MODE_ENA BIT(4) +#define DEV2G5_MAC_MODE_CFG_GIGA_MODE_ENA_SET(x)\ + FIELD_PREP(DEV2G5_MAC_MODE_CFG_GIGA_MODE_ENA, x) +#define DEV2G5_MAC_MODE_CFG_GIGA_MODE_ENA_GET(x)\ + FIELD_GET(DEV2G5_MAC_MODE_CFG_GIGA_MODE_ENA, x) + +#define DEV2G5_MAC_MODE_CFG_FDX_ENA BIT(0) +#define DEV2G5_MAC_MODE_CFG_FDX_ENA_SET(x)\ + FIELD_PREP(DEV2G5_MAC_MODE_CFG_FDX_ENA, x) +#define DEV2G5_MAC_MODE_CFG_FDX_ENA_GET(x)\ + FIELD_GET(DEV2G5_MAC_MODE_CFG_FDX_ENA, x) + +/* DEV1G:MAC_CFG_STATUS:MAC_MAXLEN_CFG */ +#define DEV2G5_MAC_MAXLEN_CFG(t) __REG(TARGET_DEV2G5, t, 65, 52, 0, 1, 36, 8, 0, 1, 4) + +#define DEV2G5_MAC_MAXLEN_CFG_MAX_LEN GENMASK(15, 0) +#define DEV2G5_MAC_MAXLEN_CFG_MAX_LEN_SET(x)\ + FIELD_PREP(DEV2G5_MAC_MAXLEN_CFG_MAX_LEN, x) +#define DEV2G5_MAC_MAXLEN_CFG_MAX_LEN_GET(x)\ + FIELD_GET(DEV2G5_MAC_MAXLEN_CFG_MAX_LEN, x) + +/* DEV1G:MAC_CFG_STATUS:MAC_TAGS_CFG */ +#define DEV2G5_MAC_TAGS_CFG(t) __REG(TARGET_DEV2G5, t, 65, 52, 0, 1, 36, 12, 0, 1, 4) + +#define DEV2G5_MAC_TAGS_CFG_TAG_ID GENMASK(31, 16) +#define DEV2G5_MAC_TAGS_CFG_TAG_ID_SET(x)\ + FIELD_PREP(DEV2G5_MAC_TAGS_CFG_TAG_ID, x) +#define DEV2G5_MAC_TAGS_CFG_TAG_ID_GET(x)\ + FIELD_GET(DEV2G5_MAC_TAGS_CFG_TAG_ID, x) + +#define DEV2G5_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA BIT(3) +#define DEV2G5_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA_SET(x)\ + FIELD_PREP(DEV2G5_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA, x) +#define DEV2G5_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA_GET(x)\ + FIELD_GET(DEV2G5_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA, x) + +#define DEV2G5_MAC_TAGS_CFG_PB_ENA GENMASK(2, 1) +#define DEV2G5_MAC_TAGS_CFG_PB_ENA_SET(x)\ + FIELD_PREP(DEV2G5_MAC_TAGS_CFG_PB_ENA, x) +#define DEV2G5_MAC_TAGS_CFG_PB_ENA_GET(x)\ + FIELD_GET(DEV2G5_MAC_TAGS_CFG_PB_ENA, x) + +#define DEV2G5_MAC_TAGS_CFG_VLAN_AWR_ENA BIT(0) +#define DEV2G5_MAC_TAGS_CFG_VLAN_AWR_ENA_SET(x)\ + FIELD_PREP(DEV2G5_MAC_TAGS_CFG_VLAN_AWR_ENA, x) +#define DEV2G5_MAC_TAGS_CFG_VLAN_AWR_ENA_GET(x)\ + FIELD_GET(DEV2G5_MAC_TAGS_CFG_VLAN_AWR_ENA, x) + +/* DEV1G:MAC_CFG_STATUS:MAC_TAGS_CFG2 */ +#define DEV2G5_MAC_TAGS_CFG2(t) __REG(TARGET_DEV2G5, t, 65, 52, 0, 1, 36, 16, 0, 1, 4) + +#define DEV2G5_MAC_TAGS_CFG2_TAG_ID3 GENMASK(31, 16) +#define DEV2G5_MAC_TAGS_CFG2_TAG_ID3_SET(x)\ + FIELD_PREP(DEV2G5_MAC_TAGS_CFG2_TAG_ID3, x) +#define DEV2G5_MAC_TAGS_CFG2_TAG_ID3_GET(x)\ + FIELD_GET(DEV2G5_MAC_TAGS_CFG2_TAG_ID3, x) + +#define DEV2G5_MAC_TAGS_CFG2_TAG_ID2 GENMASK(15, 0) +#define DEV2G5_MAC_TAGS_CFG2_TAG_ID2_SET(x)\ + FIELD_PREP(DEV2G5_MAC_TAGS_CFG2_TAG_ID2, x) +#define DEV2G5_MAC_TAGS_CFG2_TAG_ID2_GET(x)\ + FIELD_GET(DEV2G5_MAC_TAGS_CFG2_TAG_ID2, x) + +/* DEV1G:MAC_CFG_STATUS:MAC_ADV_CHK_CFG */ +#define DEV2G5_MAC_ADV_CHK_CFG(t) __REG(TARGET_DEV2G5, t, 65, 52, 0, 1, 36, 20, 0, 1, 4) + +#define DEV2G5_MAC_ADV_CHK_CFG_LEN_DROP_ENA BIT(0) +#define DEV2G5_MAC_ADV_CHK_CFG_LEN_DROP_ENA_SET(x)\ + FIELD_PREP(DEV2G5_MAC_ADV_CHK_CFG_LEN_DROP_ENA, x) +#define DEV2G5_MAC_ADV_CHK_CFG_LEN_DROP_ENA_GET(x)\ + FIELD_GET(DEV2G5_MAC_ADV_CHK_CFG_LEN_DROP_ENA, x) + +/* DEV1G:MAC_CFG_STATUS:MAC_IFG_CFG */ +#define DEV2G5_MAC_IFG_CFG(t) __REG(TARGET_DEV2G5, t, 65, 52, 0, 1, 36, 24, 0, 1, 4) + +#define DEV2G5_MAC_IFG_CFG_RESTORE_OLD_IPG_CHECK BIT(17) +#define DEV2G5_MAC_IFG_CFG_RESTORE_OLD_IPG_CHECK_SET(x)\ + FIELD_PREP(DEV2G5_MAC_IFG_CFG_RESTORE_OLD_IPG_CHECK, x) +#define DEV2G5_MAC_IFG_CFG_RESTORE_OLD_IPG_CHECK_GET(x)\ + FIELD_GET(DEV2G5_MAC_IFG_CFG_RESTORE_OLD_IPG_CHECK, x) + +#define DEV2G5_MAC_IFG_CFG_TX_IFG GENMASK(12, 8) +#define DEV2G5_MAC_IFG_CFG_TX_IFG_SET(x)\ + FIELD_PREP(DEV2G5_MAC_IFG_CFG_TX_IFG, x) +#define DEV2G5_MAC_IFG_CFG_TX_IFG_GET(x)\ + FIELD_GET(DEV2G5_MAC_IFG_CFG_TX_IFG, x) + +#define DEV2G5_MAC_IFG_CFG_RX_IFG2 GENMASK(7, 4) +#define DEV2G5_MAC_IFG_CFG_RX_IFG2_SET(x)\ + FIELD_PREP(DEV2G5_MAC_IFG_CFG_RX_IFG2, x) +#define DEV2G5_MAC_IFG_CFG_RX_IFG2_GET(x)\ + FIELD_GET(DEV2G5_MAC_IFG_CFG_RX_IFG2, x) + +#define DEV2G5_MAC_IFG_CFG_RX_IFG1 GENMASK(3, 0) +#define DEV2G5_MAC_IFG_CFG_RX_IFG1_SET(x)\ + FIELD_PREP(DEV2G5_MAC_IFG_CFG_RX_IFG1, x) +#define DEV2G5_MAC_IFG_CFG_RX_IFG1_GET(x)\ + FIELD_GET(DEV2G5_MAC_IFG_CFG_RX_IFG1, x) + +/* DEV1G:MAC_CFG_STATUS:MAC_HDX_CFG */ +#define DEV2G5_MAC_HDX_CFG(t) __REG(TARGET_DEV2G5, t, 65, 52, 0, 1, 36, 28, 0, 1, 4) + +#define DEV2G5_MAC_HDX_CFG_BYPASS_COL_SYNC BIT(26) +#define DEV2G5_MAC_HDX_CFG_BYPASS_COL_SYNC_SET(x)\ + FIELD_PREP(DEV2G5_MAC_HDX_CFG_BYPASS_COL_SYNC, x) +#define DEV2G5_MAC_HDX_CFG_BYPASS_COL_SYNC_GET(x)\ + FIELD_GET(DEV2G5_MAC_HDX_CFG_BYPASS_COL_SYNC, x) + +#define DEV2G5_MAC_HDX_CFG_SEED GENMASK(23, 16) +#define DEV2G5_MAC_HDX_CFG_SEED_SET(x)\ + FIELD_PREP(DEV2G5_MAC_HDX_CFG_SEED, x) +#define DEV2G5_MAC_HDX_CFG_SEED_GET(x)\ + FIELD_GET(DEV2G5_MAC_HDX_CFG_SEED, x) + +#define DEV2G5_MAC_HDX_CFG_SEED_LOAD BIT(12) +#define DEV2G5_MAC_HDX_CFG_SEED_LOAD_SET(x)\ + FIELD_PREP(DEV2G5_MAC_HDX_CFG_SEED_LOAD, x) +#define DEV2G5_MAC_HDX_CFG_SEED_LOAD_GET(x)\ + FIELD_GET(DEV2G5_MAC_HDX_CFG_SEED_LOAD, x) + +#define DEV2G5_MAC_HDX_CFG_RETRY_AFTER_EXC_COL_ENA BIT(8) +#define DEV2G5_MAC_HDX_CFG_RETRY_AFTER_EXC_COL_ENA_SET(x)\ + FIELD_PREP(DEV2G5_MAC_HDX_CFG_RETRY_AFTER_EXC_COL_ENA, x) +#define DEV2G5_MAC_HDX_CFG_RETRY_AFTER_EXC_COL_ENA_GET(x)\ + FIELD_GET(DEV2G5_MAC_HDX_CFG_RETRY_AFTER_EXC_COL_ENA, x) + +#define DEV2G5_MAC_HDX_CFG_LATE_COL_POS GENMASK(6, 0) +#define DEV2G5_MAC_HDX_CFG_LATE_COL_POS_SET(x)\ + FIELD_PREP(DEV2G5_MAC_HDX_CFG_LATE_COL_POS, x) +#define DEV2G5_MAC_HDX_CFG_LATE_COL_POS_GET(x)\ + FIELD_GET(DEV2G5_MAC_HDX_CFG_LATE_COL_POS, x) + +/* DEV1G:PCS1G_CFG_STATUS:PCS1G_CFG */ +#define DEV2G5_PCS1G_CFG(t) __REG(TARGET_DEV2G5, t, 65, 88, 0, 1, 68, 0, 0, 1, 4) + +#define DEV2G5_PCS1G_CFG_LINK_STATUS_TYPE BIT(4) +#define DEV2G5_PCS1G_CFG_LINK_STATUS_TYPE_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_CFG_LINK_STATUS_TYPE, x) +#define DEV2G5_PCS1G_CFG_LINK_STATUS_TYPE_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_CFG_LINK_STATUS_TYPE, x) + +#define DEV2G5_PCS1G_CFG_AN_LINK_CTRL_ENA BIT(1) +#define DEV2G5_PCS1G_CFG_AN_LINK_CTRL_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_CFG_AN_LINK_CTRL_ENA, x) +#define DEV2G5_PCS1G_CFG_AN_LINK_CTRL_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_CFG_AN_LINK_CTRL_ENA, x) + +#define DEV2G5_PCS1G_CFG_PCS_ENA BIT(0) +#define DEV2G5_PCS1G_CFG_PCS_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_CFG_PCS_ENA, x) +#define DEV2G5_PCS1G_CFG_PCS_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_CFG_PCS_ENA, x) + +/* DEV1G:PCS1G_CFG_STATUS:PCS1G_MODE_CFG */ +#define DEV2G5_PCS1G_MODE_CFG(t) __REG(TARGET_DEV2G5, t, 65, 88, 0, 1, 68, 4, 0, 1, 4) + +#define DEV2G5_PCS1G_MODE_CFG_UNIDIR_MODE_ENA BIT(4) +#define DEV2G5_PCS1G_MODE_CFG_UNIDIR_MODE_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_MODE_CFG_UNIDIR_MODE_ENA, x) +#define DEV2G5_PCS1G_MODE_CFG_UNIDIR_MODE_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_MODE_CFG_UNIDIR_MODE_ENA, x) + +#define DEV2G5_PCS1G_MODE_CFG_SAVE_PREAMBLE_ENA BIT(1) +#define DEV2G5_PCS1G_MODE_CFG_SAVE_PREAMBLE_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_MODE_CFG_SAVE_PREAMBLE_ENA, x) +#define DEV2G5_PCS1G_MODE_CFG_SAVE_PREAMBLE_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_MODE_CFG_SAVE_PREAMBLE_ENA, x) + +#define DEV2G5_PCS1G_MODE_CFG_SGMII_MODE_ENA BIT(0) +#define DEV2G5_PCS1G_MODE_CFG_SGMII_MODE_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_MODE_CFG_SGMII_MODE_ENA, x) +#define DEV2G5_PCS1G_MODE_CFG_SGMII_MODE_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_MODE_CFG_SGMII_MODE_ENA, x) + +/* DEV1G:PCS1G_CFG_STATUS:PCS1G_SD_CFG */ +#define DEV2G5_PCS1G_SD_CFG(t) __REG(TARGET_DEV2G5, t, 65, 88, 0, 1, 68, 8, 0, 1, 4) + +#define DEV2G5_PCS1G_SD_CFG_SD_SEL BIT(8) +#define DEV2G5_PCS1G_SD_CFG_SD_SEL_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_SD_CFG_SD_SEL, x) +#define DEV2G5_PCS1G_SD_CFG_SD_SEL_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_SD_CFG_SD_SEL, x) + +#define DEV2G5_PCS1G_SD_CFG_SD_POL BIT(4) +#define DEV2G5_PCS1G_SD_CFG_SD_POL_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_SD_CFG_SD_POL, x) +#define DEV2G5_PCS1G_SD_CFG_SD_POL_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_SD_CFG_SD_POL, x) + +#define DEV2G5_PCS1G_SD_CFG_SD_ENA BIT(0) +#define DEV2G5_PCS1G_SD_CFG_SD_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_SD_CFG_SD_ENA, x) +#define DEV2G5_PCS1G_SD_CFG_SD_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_SD_CFG_SD_ENA, x) + +/* DEV1G:PCS1G_CFG_STATUS:PCS1G_ANEG_CFG */ +#define DEV2G5_PCS1G_ANEG_CFG(t) __REG(TARGET_DEV2G5, t, 65, 88, 0, 1, 68, 12, 0, 1, 4) + +#define DEV2G5_PCS1G_ANEG_CFG_ADV_ABILITY GENMASK(31, 16) +#define DEV2G5_PCS1G_ANEG_CFG_ADV_ABILITY_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_ANEG_CFG_ADV_ABILITY, x) +#define DEV2G5_PCS1G_ANEG_CFG_ADV_ABILITY_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_ANEG_CFG_ADV_ABILITY, x) + +#define DEV2G5_PCS1G_ANEG_CFG_SW_RESOLVE_ENA BIT(8) +#define DEV2G5_PCS1G_ANEG_CFG_SW_RESOLVE_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_ANEG_CFG_SW_RESOLVE_ENA, x) +#define DEV2G5_PCS1G_ANEG_CFG_SW_RESOLVE_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_ANEG_CFG_SW_RESOLVE_ENA, x) + +#define DEV2G5_PCS1G_ANEG_CFG_ANEG_RESTART_ONE_SHOT BIT(1) +#define DEV2G5_PCS1G_ANEG_CFG_ANEG_RESTART_ONE_SHOT_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_ANEG_CFG_ANEG_RESTART_ONE_SHOT, x) +#define DEV2G5_PCS1G_ANEG_CFG_ANEG_RESTART_ONE_SHOT_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_ANEG_CFG_ANEG_RESTART_ONE_SHOT, x) + +#define DEV2G5_PCS1G_ANEG_CFG_ANEG_ENA BIT(0) +#define DEV2G5_PCS1G_ANEG_CFG_ANEG_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_ANEG_CFG_ANEG_ENA, x) +#define DEV2G5_PCS1G_ANEG_CFG_ANEG_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_ANEG_CFG_ANEG_ENA, x) + +/* DEV1G:PCS1G_CFG_STATUS:PCS1G_LB_CFG */ +#define DEV2G5_PCS1G_LB_CFG(t) __REG(TARGET_DEV2G5, t, 65, 88, 0, 1, 68, 20, 0, 1, 4) + +#define DEV2G5_PCS1G_LB_CFG_RA_ENA BIT(4) +#define DEV2G5_PCS1G_LB_CFG_RA_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_LB_CFG_RA_ENA, x) +#define DEV2G5_PCS1G_LB_CFG_RA_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_LB_CFG_RA_ENA, x) + +#define DEV2G5_PCS1G_LB_CFG_GMII_PHY_LB_ENA BIT(1) +#define DEV2G5_PCS1G_LB_CFG_GMII_PHY_LB_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_LB_CFG_GMII_PHY_LB_ENA, x) +#define DEV2G5_PCS1G_LB_CFG_GMII_PHY_LB_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_LB_CFG_GMII_PHY_LB_ENA, x) + +#define DEV2G5_PCS1G_LB_CFG_TBI_HOST_LB_ENA BIT(0) +#define DEV2G5_PCS1G_LB_CFG_TBI_HOST_LB_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_LB_CFG_TBI_HOST_LB_ENA, x) +#define DEV2G5_PCS1G_LB_CFG_TBI_HOST_LB_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_LB_CFG_TBI_HOST_LB_ENA, x) + +/* DEV1G:PCS1G_CFG_STATUS:PCS1G_ANEG_STATUS */ +#define DEV2G5_PCS1G_ANEG_STATUS(t) __REG(TARGET_DEV2G5, t, 65, 88, 0, 1, 68, 32, 0, 1, 4) + +#define DEV2G5_PCS1G_ANEG_STATUS_LP_ADV_ABILITY GENMASK(31, 16) +#define DEV2G5_PCS1G_ANEG_STATUS_LP_ADV_ABILITY_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_ANEG_STATUS_LP_ADV_ABILITY, x) +#define DEV2G5_PCS1G_ANEG_STATUS_LP_ADV_ABILITY_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_ANEG_STATUS_LP_ADV_ABILITY, x) + +#define DEV2G5_PCS1G_ANEG_STATUS_PR BIT(4) +#define DEV2G5_PCS1G_ANEG_STATUS_PR_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_ANEG_STATUS_PR, x) +#define DEV2G5_PCS1G_ANEG_STATUS_PR_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_ANEG_STATUS_PR, x) + +#define DEV2G5_PCS1G_ANEG_STATUS_PAGE_RX_STICKY BIT(3) +#define DEV2G5_PCS1G_ANEG_STATUS_PAGE_RX_STICKY_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_ANEG_STATUS_PAGE_RX_STICKY, x) +#define DEV2G5_PCS1G_ANEG_STATUS_PAGE_RX_STICKY_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_ANEG_STATUS_PAGE_RX_STICKY, x) + +#define DEV2G5_PCS1G_ANEG_STATUS_ANEG_COMPLETE BIT(0) +#define DEV2G5_PCS1G_ANEG_STATUS_ANEG_COMPLETE_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_ANEG_STATUS_ANEG_COMPLETE, x) +#define DEV2G5_PCS1G_ANEG_STATUS_ANEG_COMPLETE_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_ANEG_STATUS_ANEG_COMPLETE, x) + +/* DEV1G:PCS1G_CFG_STATUS:PCS1G_LINK_STATUS */ +#define DEV2G5_PCS1G_LINK_STATUS(t) __REG(TARGET_DEV2G5, t, 65, 88, 0, 1, 68, 40, 0, 1, 4) + +#define DEV2G5_PCS1G_LINK_STATUS_DELAY_VAR GENMASK(15, 12) +#define DEV2G5_PCS1G_LINK_STATUS_DELAY_VAR_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_LINK_STATUS_DELAY_VAR, x) +#define DEV2G5_PCS1G_LINK_STATUS_DELAY_VAR_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_LINK_STATUS_DELAY_VAR, x) + +#define DEV2G5_PCS1G_LINK_STATUS_SIGNAL_DETECT BIT(8) +#define DEV2G5_PCS1G_LINK_STATUS_SIGNAL_DETECT_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_LINK_STATUS_SIGNAL_DETECT, x) +#define DEV2G5_PCS1G_LINK_STATUS_SIGNAL_DETECT_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_LINK_STATUS_SIGNAL_DETECT, x) + +#define DEV2G5_PCS1G_LINK_STATUS_LINK_STATUS BIT(4) +#define DEV2G5_PCS1G_LINK_STATUS_LINK_STATUS_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_LINK_STATUS_LINK_STATUS, x) +#define DEV2G5_PCS1G_LINK_STATUS_LINK_STATUS_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_LINK_STATUS_LINK_STATUS, x) + +#define DEV2G5_PCS1G_LINK_STATUS_SYNC_STATUS BIT(0) +#define DEV2G5_PCS1G_LINK_STATUS_SYNC_STATUS_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_LINK_STATUS_SYNC_STATUS, x) +#define DEV2G5_PCS1G_LINK_STATUS_SYNC_STATUS_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_LINK_STATUS_SYNC_STATUS, x) + +/* DEV1G:PCS1G_CFG_STATUS:PCS1G_STICKY */ +#define DEV2G5_PCS1G_STICKY(t) __REG(TARGET_DEV2G5, t, 65, 88, 0, 1, 68, 48, 0, 1, 4) + +#define DEV2G5_PCS1G_STICKY_LINK_DOWN_STICKY BIT(4) +#define DEV2G5_PCS1G_STICKY_LINK_DOWN_STICKY_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_STICKY_LINK_DOWN_STICKY, x) +#define DEV2G5_PCS1G_STICKY_LINK_DOWN_STICKY_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_STICKY_LINK_DOWN_STICKY, x) + +#define DEV2G5_PCS1G_STICKY_OUT_OF_SYNC_STICKY BIT(0) +#define DEV2G5_PCS1G_STICKY_OUT_OF_SYNC_STICKY_SET(x)\ + FIELD_PREP(DEV2G5_PCS1G_STICKY_OUT_OF_SYNC_STICKY, x) +#define DEV2G5_PCS1G_STICKY_OUT_OF_SYNC_STICKY_GET(x)\ + FIELD_GET(DEV2G5_PCS1G_STICKY_OUT_OF_SYNC_STICKY, x) + +/* DEV1G:PCS_FX100_CONFIGURATION:PCS_FX100_CFG */ +#define DEV2G5_PCS_FX100_CFG(t) __REG(TARGET_DEV2G5, t, 65, 164, 0, 1, 4, 0, 0, 1, 4) + +#define DEV2G5_PCS_FX100_CFG_SD_SEL BIT(26) +#define DEV2G5_PCS_FX100_CFG_SD_SEL_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_SD_SEL, x) +#define DEV2G5_PCS_FX100_CFG_SD_SEL_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_SD_SEL, x) + +#define DEV2G5_PCS_FX100_CFG_SD_POL BIT(25) +#define DEV2G5_PCS_FX100_CFG_SD_POL_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_SD_POL, x) +#define DEV2G5_PCS_FX100_CFG_SD_POL_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_SD_POL, x) + +#define DEV2G5_PCS_FX100_CFG_SD_ENA BIT(24) +#define DEV2G5_PCS_FX100_CFG_SD_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_SD_ENA, x) +#define DEV2G5_PCS_FX100_CFG_SD_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_SD_ENA, x) + +#define DEV2G5_PCS_FX100_CFG_LOOPBACK_ENA BIT(20) +#define DEV2G5_PCS_FX100_CFG_LOOPBACK_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_LOOPBACK_ENA, x) +#define DEV2G5_PCS_FX100_CFG_LOOPBACK_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_LOOPBACK_ENA, x) + +#define DEV2G5_PCS_FX100_CFG_SWAP_MII_ENA BIT(16) +#define DEV2G5_PCS_FX100_CFG_SWAP_MII_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_SWAP_MII_ENA, x) +#define DEV2G5_PCS_FX100_CFG_SWAP_MII_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_SWAP_MII_ENA, x) + +#define DEV2G5_PCS_FX100_CFG_RXBITSEL GENMASK(15, 12) +#define DEV2G5_PCS_FX100_CFG_RXBITSEL_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_RXBITSEL, x) +#define DEV2G5_PCS_FX100_CFG_RXBITSEL_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_RXBITSEL, x) + +#define DEV2G5_PCS_FX100_CFG_SIGDET_CFG GENMASK(10, 9) +#define DEV2G5_PCS_FX100_CFG_SIGDET_CFG_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_SIGDET_CFG, x) +#define DEV2G5_PCS_FX100_CFG_SIGDET_CFG_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_SIGDET_CFG, x) + +#define DEV2G5_PCS_FX100_CFG_LINKHYST_TM_ENA BIT(8) +#define DEV2G5_PCS_FX100_CFG_LINKHYST_TM_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_LINKHYST_TM_ENA, x) +#define DEV2G5_PCS_FX100_CFG_LINKHYST_TM_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_LINKHYST_TM_ENA, x) + +#define DEV2G5_PCS_FX100_CFG_LINKHYSTTIMER GENMASK(7, 4) +#define DEV2G5_PCS_FX100_CFG_LINKHYSTTIMER_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_LINKHYSTTIMER, x) +#define DEV2G5_PCS_FX100_CFG_LINKHYSTTIMER_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_LINKHYSTTIMER, x) + +#define DEV2G5_PCS_FX100_CFG_UNIDIR_MODE_ENA BIT(3) +#define DEV2G5_PCS_FX100_CFG_UNIDIR_MODE_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_UNIDIR_MODE_ENA, x) +#define DEV2G5_PCS_FX100_CFG_UNIDIR_MODE_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_UNIDIR_MODE_ENA, x) + +#define DEV2G5_PCS_FX100_CFG_FEFCHK_ENA BIT(2) +#define DEV2G5_PCS_FX100_CFG_FEFCHK_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_FEFCHK_ENA, x) +#define DEV2G5_PCS_FX100_CFG_FEFCHK_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_FEFCHK_ENA, x) + +#define DEV2G5_PCS_FX100_CFG_FEFGEN_ENA BIT(1) +#define DEV2G5_PCS_FX100_CFG_FEFGEN_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_FEFGEN_ENA, x) +#define DEV2G5_PCS_FX100_CFG_FEFGEN_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_FEFGEN_ENA, x) + +#define DEV2G5_PCS_FX100_CFG_PCS_ENA BIT(0) +#define DEV2G5_PCS_FX100_CFG_PCS_ENA_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_CFG_PCS_ENA, x) +#define DEV2G5_PCS_FX100_CFG_PCS_ENA_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_CFG_PCS_ENA, x) + +/* DEV1G:PCS_FX100_STATUS:PCS_FX100_STATUS */ +#define DEV2G5_PCS_FX100_STATUS(t) __REG(TARGET_DEV2G5, t, 65, 168, 0, 1, 4, 0, 0, 1, 4) + +#define DEV2G5_PCS_FX100_STATUS_EDGE_POS_PTP GENMASK(11, 8) +#define DEV2G5_PCS_FX100_STATUS_EDGE_POS_PTP_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_STATUS_EDGE_POS_PTP, x) +#define DEV2G5_PCS_FX100_STATUS_EDGE_POS_PTP_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_STATUS_EDGE_POS_PTP, x) + +#define DEV2G5_PCS_FX100_STATUS_PCS_ERROR_STICKY BIT(7) +#define DEV2G5_PCS_FX100_STATUS_PCS_ERROR_STICKY_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_STATUS_PCS_ERROR_STICKY, x) +#define DEV2G5_PCS_FX100_STATUS_PCS_ERROR_STICKY_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_STATUS_PCS_ERROR_STICKY, x) + +#define DEV2G5_PCS_FX100_STATUS_FEF_FOUND_STICKY BIT(6) +#define DEV2G5_PCS_FX100_STATUS_FEF_FOUND_STICKY_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_STATUS_FEF_FOUND_STICKY, x) +#define DEV2G5_PCS_FX100_STATUS_FEF_FOUND_STICKY_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_STATUS_FEF_FOUND_STICKY, x) + +#define DEV2G5_PCS_FX100_STATUS_SSD_ERROR_STICKY BIT(5) +#define DEV2G5_PCS_FX100_STATUS_SSD_ERROR_STICKY_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_STATUS_SSD_ERROR_STICKY, x) +#define DEV2G5_PCS_FX100_STATUS_SSD_ERROR_STICKY_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_STATUS_SSD_ERROR_STICKY, x) + +#define DEV2G5_PCS_FX100_STATUS_SYNC_LOST_STICKY BIT(4) +#define DEV2G5_PCS_FX100_STATUS_SYNC_LOST_STICKY_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_STATUS_SYNC_LOST_STICKY, x) +#define DEV2G5_PCS_FX100_STATUS_SYNC_LOST_STICKY_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_STATUS_SYNC_LOST_STICKY, x) + +#define DEV2G5_PCS_FX100_STATUS_FEF_STATUS BIT(2) +#define DEV2G5_PCS_FX100_STATUS_FEF_STATUS_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_STATUS_FEF_STATUS, x) +#define DEV2G5_PCS_FX100_STATUS_FEF_STATUS_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_STATUS_FEF_STATUS, x) + +#define DEV2G5_PCS_FX100_STATUS_SIGNAL_DETECT BIT(1) +#define DEV2G5_PCS_FX100_STATUS_SIGNAL_DETECT_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_STATUS_SIGNAL_DETECT, x) +#define DEV2G5_PCS_FX100_STATUS_SIGNAL_DETECT_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_STATUS_SIGNAL_DETECT, x) + +#define DEV2G5_PCS_FX100_STATUS_SYNC_STATUS BIT(0) +#define DEV2G5_PCS_FX100_STATUS_SYNC_STATUS_SET(x)\ + FIELD_PREP(DEV2G5_PCS_FX100_STATUS_SYNC_STATUS, x) +#define DEV2G5_PCS_FX100_STATUS_SYNC_STATUS_GET(x)\ + FIELD_GET(DEV2G5_PCS_FX100_STATUS_SYNC_STATUS, x) + +/* DEV10G:MAC_CFG_STATUS:MAC_ENA_CFG */ +#define DEV5G_MAC_ENA_CFG(t) __REG(TARGET_DEV5G, t, 13, 0, 0, 1, 60, 0, 0, 1, 4) + +#define DEV5G_MAC_ENA_CFG_RX_ENA BIT(4) +#define DEV5G_MAC_ENA_CFG_RX_ENA_SET(x)\ + FIELD_PREP(DEV5G_MAC_ENA_CFG_RX_ENA, x) +#define DEV5G_MAC_ENA_CFG_RX_ENA_GET(x)\ + FIELD_GET(DEV5G_MAC_ENA_CFG_RX_ENA, x) + +#define DEV5G_MAC_ENA_CFG_TX_ENA BIT(0) +#define DEV5G_MAC_ENA_CFG_TX_ENA_SET(x)\ + FIELD_PREP(DEV5G_MAC_ENA_CFG_TX_ENA, x) +#define DEV5G_MAC_ENA_CFG_TX_ENA_GET(x)\ + FIELD_GET(DEV5G_MAC_ENA_CFG_TX_ENA, x) + +/* DEV10G:MAC_CFG_STATUS:MAC_MAXLEN_CFG */ +#define DEV5G_MAC_MAXLEN_CFG(t) __REG(TARGET_DEV5G, t, 13, 0, 0, 1, 60, 8, 0, 1, 4) + +#define DEV5G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK BIT(16) +#define DEV5G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK_SET(x)\ + FIELD_PREP(DEV5G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK, x) +#define DEV5G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK_GET(x)\ + FIELD_GET(DEV5G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK, x) + +#define DEV5G_MAC_MAXLEN_CFG_MAX_LEN GENMASK(15, 0) +#define DEV5G_MAC_MAXLEN_CFG_MAX_LEN_SET(x)\ + FIELD_PREP(DEV5G_MAC_MAXLEN_CFG_MAX_LEN, x) +#define DEV5G_MAC_MAXLEN_CFG_MAX_LEN_GET(x)\ + FIELD_GET(DEV5G_MAC_MAXLEN_CFG_MAX_LEN, x) + +/* DEV10G:MAC_CFG_STATUS:MAC_ADV_CHK_CFG */ +#define DEV5G_MAC_ADV_CHK_CFG(t) __REG(TARGET_DEV5G, t, 13, 0, 0, 1, 60, 28, 0, 1, 4) + +#define DEV5G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA BIT(24) +#define DEV5G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA_SET(x)\ + FIELD_PREP(DEV5G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA, x) +#define DEV5G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA_GET(x)\ + FIELD_GET(DEV5G_MAC_ADV_CHK_CFG_EXT_EOP_CHK_ENA, x) + +#define DEV5G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA BIT(20) +#define DEV5G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA_SET(x)\ + FIELD_PREP(DEV5G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA, x) +#define DEV5G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA_GET(x)\ + FIELD_GET(DEV5G_MAC_ADV_CHK_CFG_EXT_SOP_CHK_ENA, x) + +#define DEV5G_MAC_ADV_CHK_CFG_SFD_CHK_ENA BIT(16) +#define DEV5G_MAC_ADV_CHK_CFG_SFD_CHK_ENA_SET(x)\ + FIELD_PREP(DEV5G_MAC_ADV_CHK_CFG_SFD_CHK_ENA, x) +#define DEV5G_MAC_ADV_CHK_CFG_SFD_CHK_ENA_GET(x)\ + FIELD_GET(DEV5G_MAC_ADV_CHK_CFG_SFD_CHK_ENA, x) + +#define DEV5G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS BIT(12) +#define DEV5G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS_SET(x)\ + FIELD_PREP(DEV5G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS, x) +#define DEV5G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS_GET(x)\ + FIELD_GET(DEV5G_MAC_ADV_CHK_CFG_PRM_SHK_CHK_DIS, x) + +#define DEV5G_MAC_ADV_CHK_CFG_PRM_CHK_ENA BIT(8) +#define DEV5G_MAC_ADV_CHK_CFG_PRM_CHK_ENA_SET(x)\ + FIELD_PREP(DEV5G_MAC_ADV_CHK_CFG_PRM_CHK_ENA, x) +#define DEV5G_MAC_ADV_CHK_CFG_PRM_CHK_ENA_GET(x)\ + FIELD_GET(DEV5G_MAC_ADV_CHK_CFG_PRM_CHK_ENA, x) + +#define DEV5G_MAC_ADV_CHK_CFG_OOR_ERR_ENA BIT(4) +#define DEV5G_MAC_ADV_CHK_CFG_OOR_ERR_ENA_SET(x)\ + FIELD_PREP(DEV5G_MAC_ADV_CHK_CFG_OOR_ERR_ENA, x) +#define DEV5G_MAC_ADV_CHK_CFG_OOR_ERR_ENA_GET(x)\ + FIELD_GET(DEV5G_MAC_ADV_CHK_CFG_OOR_ERR_ENA, x) + +#define DEV5G_MAC_ADV_CHK_CFG_INR_ERR_ENA BIT(0) +#define DEV5G_MAC_ADV_CHK_CFG_INR_ERR_ENA_SET(x)\ + FIELD_PREP(DEV5G_MAC_ADV_CHK_CFG_INR_ERR_ENA, x) +#define DEV5G_MAC_ADV_CHK_CFG_INR_ERR_ENA_GET(x)\ + FIELD_GET(DEV5G_MAC_ADV_CHK_CFG_INR_ERR_ENA, x) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_SYMBOL_ERR_CNT */ +#define DEV5G_RX_SYMBOL_ERR_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 0, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_PAUSE_CNT */ +#define DEV5G_RX_PAUSE_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 4, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_UNSUP_OPCODE_CNT */ +#define DEV5G_RX_UNSUP_OPCODE_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 8, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_UC_CNT */ +#define DEV5G_RX_UC_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 12, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_MC_CNT */ +#define DEV5G_RX_MC_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 16, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_BC_CNT */ +#define DEV5G_RX_BC_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 20, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_CRC_ERR_CNT */ +#define DEV5G_RX_CRC_ERR_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 24, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_UNDERSIZE_CNT */ +#define DEV5G_RX_UNDERSIZE_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 28, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_FRAGMENTS_CNT */ +#define DEV5G_RX_FRAGMENTS_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 32, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_IN_RANGE_LEN_ERR_CNT */ +#define DEV5G_RX_IN_RANGE_LEN_ERR_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 36, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_OUT_OF_RANGE_LEN_ERR_CNT */ +#define DEV5G_RX_OUT_OF_RANGE_LEN_ERR_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 40, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_OVERSIZE_CNT */ +#define DEV5G_RX_OVERSIZE_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 44, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_JABBERS_CNT */ +#define DEV5G_RX_JABBERS_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 48, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_SIZE64_CNT */ +#define DEV5G_RX_SIZE64_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 52, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_SIZE65TO127_CNT */ +#define DEV5G_RX_SIZE65TO127_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 56, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_SIZE128TO255_CNT */ +#define DEV5G_RX_SIZE128TO255_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 60, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_SIZE256TO511_CNT */ +#define DEV5G_RX_SIZE256TO511_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 64, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_SIZE512TO1023_CNT */ +#define DEV5G_RX_SIZE512TO1023_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 68, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_SIZE1024TO1518_CNT */ +#define DEV5G_RX_SIZE1024TO1518_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 72, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_SIZE1519TOMAX_CNT */ +#define DEV5G_RX_SIZE1519TOMAX_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 76, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_IPG_SHRINK_CNT */ +#define DEV5G_RX_IPG_SHRINK_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 80, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_PAUSE_CNT */ +#define DEV5G_TX_PAUSE_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 84, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_UC_CNT */ +#define DEV5G_TX_UC_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 88, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_MC_CNT */ +#define DEV5G_TX_MC_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 92, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_BC_CNT */ +#define DEV5G_TX_BC_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 96, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_SIZE64_CNT */ +#define DEV5G_TX_SIZE64_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 100, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_SIZE65TO127_CNT */ +#define DEV5G_TX_SIZE65TO127_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 104, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_SIZE128TO255_CNT */ +#define DEV5G_TX_SIZE128TO255_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 108, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_SIZE256TO511_CNT */ +#define DEV5G_TX_SIZE256TO511_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 112, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_SIZE512TO1023_CNT */ +#define DEV5G_TX_SIZE512TO1023_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 116, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_SIZE1024TO1518_CNT */ +#define DEV5G_TX_SIZE1024TO1518_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 120, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_SIZE1519TOMAX_CNT */ +#define DEV5G_TX_SIZE1519TOMAX_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 124, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_ALIGNMENT_LOST_CNT */ +#define DEV5G_RX_ALIGNMENT_LOST_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 128, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_TAGGED_FRMS_CNT */ +#define DEV5G_RX_TAGGED_FRMS_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 132, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_UNTAGGED_FRMS_CNT */ +#define DEV5G_RX_UNTAGGED_FRMS_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 136, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_TAGGED_FRMS_CNT */ +#define DEV5G_TX_TAGGED_FRMS_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 140, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:TX_UNTAGGED_FRMS_CNT */ +#define DEV5G_TX_UNTAGGED_FRMS_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 144, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_SYMBOL_ERR_CNT */ +#define DEV5G_PMAC_RX_SYMBOL_ERR_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 148, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_PAUSE_CNT */ +#define DEV5G_PMAC_RX_PAUSE_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 152, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_UNSUP_OPCODE_CNT */ +#define DEV5G_PMAC_RX_UNSUP_OPCODE_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 156, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_UC_CNT */ +#define DEV5G_PMAC_RX_UC_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 160, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_MC_CNT */ +#define DEV5G_PMAC_RX_MC_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 164, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_BC_CNT */ +#define DEV5G_PMAC_RX_BC_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 168, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_CRC_ERR_CNT */ +#define DEV5G_PMAC_RX_CRC_ERR_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 172, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_UNDERSIZE_CNT */ +#define DEV5G_PMAC_RX_UNDERSIZE_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 176, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_FRAGMENTS_CNT */ +#define DEV5G_PMAC_RX_FRAGMENTS_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 180, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_IN_RANGE_LEN_ERR_CNT */ +#define DEV5G_PMAC_RX_IN_RANGE_LEN_ERR_CNT(t) __REG(TARGET_DEV5G,\ + t, 13, 60, 0, 1, 312, 184, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_OUT_OF_RANGE_LEN_ERR_CNT */ +#define DEV5G_PMAC_RX_OUT_OF_RANGE_LEN_ERR_CNT(t) __REG(TARGET_DEV5G,\ + t, 13, 60, 0, 1, 312, 188, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_OVERSIZE_CNT */ +#define DEV5G_PMAC_RX_OVERSIZE_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 192, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_JABBERS_CNT */ +#define DEV5G_PMAC_RX_JABBERS_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 196, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_SIZE64_CNT */ +#define DEV5G_PMAC_RX_SIZE64_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 200, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_SIZE65TO127_CNT */ +#define DEV5G_PMAC_RX_SIZE65TO127_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 204, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_SIZE128TO255_CNT */ +#define DEV5G_PMAC_RX_SIZE128TO255_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 208, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_SIZE256TO511_CNT */ +#define DEV5G_PMAC_RX_SIZE256TO511_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 212, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_SIZE512TO1023_CNT */ +#define DEV5G_PMAC_RX_SIZE512TO1023_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 216, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_SIZE1024TO1518_CNT */ +#define DEV5G_PMAC_RX_SIZE1024TO1518_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 220, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_SIZE1519TOMAX_CNT */ +#define DEV5G_PMAC_RX_SIZE1519TOMAX_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 224, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_TX_PAUSE_CNT */ +#define DEV5G_PMAC_TX_PAUSE_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 228, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_TX_UC_CNT */ +#define DEV5G_PMAC_TX_UC_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 232, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_TX_MC_CNT */ +#define DEV5G_PMAC_TX_MC_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 236, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_TX_BC_CNT */ +#define DEV5G_PMAC_TX_BC_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 240, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_TX_SIZE64_CNT */ +#define DEV5G_PMAC_TX_SIZE64_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 244, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_TX_SIZE65TO127_CNT */ +#define DEV5G_PMAC_TX_SIZE65TO127_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 248, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_TX_SIZE128TO255_CNT */ +#define DEV5G_PMAC_TX_SIZE128TO255_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 252, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_TX_SIZE256TO511_CNT */ +#define DEV5G_PMAC_TX_SIZE256TO511_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 256, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_TX_SIZE512TO1023_CNT */ +#define DEV5G_PMAC_TX_SIZE512TO1023_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 260, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_TX_SIZE1024TO1518_CNT */ +#define DEV5G_PMAC_TX_SIZE1024TO1518_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 264, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_TX_SIZE1519TOMAX_CNT */ +#define DEV5G_PMAC_TX_SIZE1519TOMAX_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 268, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_ALIGNMENT_LOST_CNT */ +#define DEV5G_PMAC_RX_ALIGNMENT_LOST_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 272, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:MM_RX_ASSEMBLY_ERR_CNT */ +#define DEV5G_MM_RX_ASSEMBLY_ERR_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 276, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:MM_RX_SMD_ERR_CNT */ +#define DEV5G_MM_RX_SMD_ERR_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 280, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:MM_RX_ASSEMBLY_OK_CNT */ +#define DEV5G_MM_RX_ASSEMBLY_OK_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 284, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:MM_RX_MERGE_FRAG_CNT */ +#define DEV5G_MM_RX_MERGE_FRAG_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 288, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:MM_TX_PFRAGMENT_CNT */ +#define DEV5G_MM_TX_PFRAGMENT_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 292, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_HIH_CKSM_ERR_CNT */ +#define DEV5G_RX_HIH_CKSM_ERR_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 296, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:RX_XGMII_PROT_ERR_CNT */ +#define DEV5G_RX_XGMII_PROT_ERR_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 300, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_HIH_CKSM_ERR_CNT */ +#define DEV5G_PMAC_RX_HIH_CKSM_ERR_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 304, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_32BIT:PMAC_RX_XGMII_PROT_ERR_CNT */ +#define DEV5G_PMAC_RX_XGMII_PROT_ERR_CNT(t) __REG(TARGET_DEV5G, t, 13, 60, 0, 1, 312, 308, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_40BIT:RX_IN_BYTES_CNT */ +#define DEV5G_RX_IN_BYTES_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 0, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_40BIT:RX_IN_BYTES_MSB_CNT */ +#define DEV5G_RX_IN_BYTES_MSB_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 4, 0, 1, 4) + +#define DEV5G_RX_IN_BYTES_MSB_CNT_RX_IN_BYTES_MSB_CNT GENMASK(7, 0) +#define DEV5G_RX_IN_BYTES_MSB_CNT_RX_IN_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(DEV5G_RX_IN_BYTES_MSB_CNT_RX_IN_BYTES_MSB_CNT, x) +#define DEV5G_RX_IN_BYTES_MSB_CNT_RX_IN_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(DEV5G_RX_IN_BYTES_MSB_CNT_RX_IN_BYTES_MSB_CNT, x) + +/* DEV10G:DEV_STATISTICS_40BIT:RX_OK_BYTES_CNT */ +#define DEV5G_RX_OK_BYTES_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 8, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_40BIT:RX_OK_BYTES_MSB_CNT */ +#define DEV5G_RX_OK_BYTES_MSB_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 12, 0, 1, 4) + +#define DEV5G_RX_OK_BYTES_MSB_CNT_RX_OK_BYTES_MSB_CNT GENMASK(7, 0) +#define DEV5G_RX_OK_BYTES_MSB_CNT_RX_OK_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(DEV5G_RX_OK_BYTES_MSB_CNT_RX_OK_BYTES_MSB_CNT, x) +#define DEV5G_RX_OK_BYTES_MSB_CNT_RX_OK_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(DEV5G_RX_OK_BYTES_MSB_CNT_RX_OK_BYTES_MSB_CNT, x) + +/* DEV10G:DEV_STATISTICS_40BIT:RX_BAD_BYTES_CNT */ +#define DEV5G_RX_BAD_BYTES_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 16, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_40BIT:RX_BAD_BYTES_MSB_CNT */ +#define DEV5G_RX_BAD_BYTES_MSB_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 20, 0, 1, 4) + +#define DEV5G_RX_BAD_BYTES_MSB_CNT_RX_BAD_BYTES_MSB_CNT GENMASK(7, 0) +#define DEV5G_RX_BAD_BYTES_MSB_CNT_RX_BAD_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(DEV5G_RX_BAD_BYTES_MSB_CNT_RX_BAD_BYTES_MSB_CNT, x) +#define DEV5G_RX_BAD_BYTES_MSB_CNT_RX_BAD_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(DEV5G_RX_BAD_BYTES_MSB_CNT_RX_BAD_BYTES_MSB_CNT, x) + +/* DEV10G:DEV_STATISTICS_40BIT:TX_OUT_BYTES_CNT */ +#define DEV5G_TX_OUT_BYTES_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 24, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_40BIT:TX_OUT_BYTES_MSB_CNT */ +#define DEV5G_TX_OUT_BYTES_MSB_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 28, 0, 1, 4) + +#define DEV5G_TX_OUT_BYTES_MSB_CNT_TX_OUT_BYTES_MSB_CNT GENMASK(7, 0) +#define DEV5G_TX_OUT_BYTES_MSB_CNT_TX_OUT_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(DEV5G_TX_OUT_BYTES_MSB_CNT_TX_OUT_BYTES_MSB_CNT, x) +#define DEV5G_TX_OUT_BYTES_MSB_CNT_TX_OUT_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(DEV5G_TX_OUT_BYTES_MSB_CNT_TX_OUT_BYTES_MSB_CNT, x) + +/* DEV10G:DEV_STATISTICS_40BIT:TX_OK_BYTES_CNT */ +#define DEV5G_TX_OK_BYTES_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 32, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_40BIT:TX_OK_BYTES_MSB_CNT */ +#define DEV5G_TX_OK_BYTES_MSB_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 36, 0, 1, 4) + +#define DEV5G_TX_OK_BYTES_MSB_CNT_TX_OK_BYTES_MSB_CNT GENMASK(7, 0) +#define DEV5G_TX_OK_BYTES_MSB_CNT_TX_OK_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(DEV5G_TX_OK_BYTES_MSB_CNT_TX_OK_BYTES_MSB_CNT, x) +#define DEV5G_TX_OK_BYTES_MSB_CNT_TX_OK_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(DEV5G_TX_OK_BYTES_MSB_CNT_TX_OK_BYTES_MSB_CNT, x) + +/* DEV10G:DEV_STATISTICS_40BIT:PMAC_RX_OK_BYTES_CNT */ +#define DEV5G_PMAC_RX_OK_BYTES_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 40, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_40BIT:PMAC_RX_OK_BYTES_MSB_CNT */ +#define DEV5G_PMAC_RX_OK_BYTES_MSB_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 44, 0, 1, 4) + +#define DEV5G_PMAC_RX_OK_BYTES_MSB_CNT_PMAC_RX_OK_BYTES_MSB_CNT GENMASK(7, 0) +#define DEV5G_PMAC_RX_OK_BYTES_MSB_CNT_PMAC_RX_OK_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(DEV5G_PMAC_RX_OK_BYTES_MSB_CNT_PMAC_RX_OK_BYTES_MSB_CNT, x) +#define DEV5G_PMAC_RX_OK_BYTES_MSB_CNT_PMAC_RX_OK_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(DEV5G_PMAC_RX_OK_BYTES_MSB_CNT_PMAC_RX_OK_BYTES_MSB_CNT, x) + +/* DEV10G:DEV_STATISTICS_40BIT:PMAC_RX_BAD_BYTES_CNT */ +#define DEV5G_PMAC_RX_BAD_BYTES_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 48, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_40BIT:PMAC_RX_BAD_BYTES_MSB_CNT */ +#define DEV5G_PMAC_RX_BAD_BYTES_MSB_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 52, 0, 1, 4) + +#define DEV5G_PMAC_RX_BAD_BYTES_MSB_CNT_PMAC_RX_BAD_BYTES_MSB_CNT GENMASK(7, 0) +#define DEV5G_PMAC_RX_BAD_BYTES_MSB_CNT_PMAC_RX_BAD_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(DEV5G_PMAC_RX_BAD_BYTES_MSB_CNT_PMAC_RX_BAD_BYTES_MSB_CNT, x) +#define DEV5G_PMAC_RX_BAD_BYTES_MSB_CNT_PMAC_RX_BAD_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(DEV5G_PMAC_RX_BAD_BYTES_MSB_CNT_PMAC_RX_BAD_BYTES_MSB_CNT, x) + +/* DEV10G:DEV_STATISTICS_40BIT:PMAC_TX_OK_BYTES_CNT */ +#define DEV5G_PMAC_TX_OK_BYTES_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 56, 0, 1, 4) + +/* DEV10G:DEV_STATISTICS_40BIT:PMAC_TX_OK_BYTES_MSB_CNT */ +#define DEV5G_PMAC_TX_OK_BYTES_MSB_CNT(t) __REG(TARGET_DEV5G, t, 13, 372, 0, 1, 64, 60, 0, 1, 4) + +#define DEV5G_PMAC_TX_OK_BYTES_MSB_CNT_PMAC_TX_OK_BYTES_MSB_CNT GENMASK(7, 0) +#define DEV5G_PMAC_TX_OK_BYTES_MSB_CNT_PMAC_TX_OK_BYTES_MSB_CNT_SET(x)\ + FIELD_PREP(DEV5G_PMAC_TX_OK_BYTES_MSB_CNT_PMAC_TX_OK_BYTES_MSB_CNT, x) +#define DEV5G_PMAC_TX_OK_BYTES_MSB_CNT_PMAC_TX_OK_BYTES_MSB_CNT_GET(x)\ + FIELD_GET(DEV5G_PMAC_TX_OK_BYTES_MSB_CNT_PMAC_TX_OK_BYTES_MSB_CNT, x) + +/* DEV10G:DEV_CFG_STATUS:DEV_RST_CTRL */ +#define DEV5G_DEV_RST_CTRL(t) __REG(TARGET_DEV5G, t, 13, 436, 0, 1, 52, 0, 0, 1, 4) + +#define DEV5G_DEV_RST_CTRL_PARDET_MODE_ENA BIT(28) +#define DEV5G_DEV_RST_CTRL_PARDET_MODE_ENA_SET(x)\ + FIELD_PREP(DEV5G_DEV_RST_CTRL_PARDET_MODE_ENA, x) +#define DEV5G_DEV_RST_CTRL_PARDET_MODE_ENA_GET(x)\ + FIELD_GET(DEV5G_DEV_RST_CTRL_PARDET_MODE_ENA, x) + +#define DEV5G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS BIT(27) +#define DEV5G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS_SET(x)\ + FIELD_PREP(DEV5G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS, x) +#define DEV5G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS_GET(x)\ + FIELD_GET(DEV5G_DEV_RST_CTRL_USXGMII_OSET_FILTER_DIS, x) + +#define DEV5G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS GENMASK(26, 25) +#define DEV5G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS_SET(x)\ + FIELD_PREP(DEV5G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS, x) +#define DEV5G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS_GET(x)\ + FIELD_GET(DEV5G_DEV_RST_CTRL_MUXED_USXGMII_NETWORK_PORTS, x) + +#define DEV5G_DEV_RST_CTRL_SERDES_SPEED_SEL GENMASK(24, 23) +#define DEV5G_DEV_RST_CTRL_SERDES_SPEED_SEL_SET(x)\ + FIELD_PREP(DEV5G_DEV_RST_CTRL_SERDES_SPEED_SEL, x) +#define DEV5G_DEV_RST_CTRL_SERDES_SPEED_SEL_GET(x)\ + FIELD_GET(DEV5G_DEV_RST_CTRL_SERDES_SPEED_SEL, x) + +#define DEV5G_DEV_RST_CTRL_SPEED_SEL GENMASK(22, 20) +#define DEV5G_DEV_RST_CTRL_SPEED_SEL_SET(x)\ + FIELD_PREP(DEV5G_DEV_RST_CTRL_SPEED_SEL, x) +#define DEV5G_DEV_RST_CTRL_SPEED_SEL_GET(x)\ + FIELD_GET(DEV5G_DEV_RST_CTRL_SPEED_SEL, x) + +#define DEV5G_DEV_RST_CTRL_PCS_TX_RST BIT(12) +#define DEV5G_DEV_RST_CTRL_PCS_TX_RST_SET(x)\ + FIELD_PREP(DEV5G_DEV_RST_CTRL_PCS_TX_RST, x) +#define DEV5G_DEV_RST_CTRL_PCS_TX_RST_GET(x)\ + FIELD_GET(DEV5G_DEV_RST_CTRL_PCS_TX_RST, x) + +#define DEV5G_DEV_RST_CTRL_PCS_RX_RST BIT(8) +#define DEV5G_DEV_RST_CTRL_PCS_RX_RST_SET(x)\ + FIELD_PREP(DEV5G_DEV_RST_CTRL_PCS_RX_RST, x) +#define DEV5G_DEV_RST_CTRL_PCS_RX_RST_GET(x)\ + FIELD_GET(DEV5G_DEV_RST_CTRL_PCS_RX_RST, x) + +#define DEV5G_DEV_RST_CTRL_MAC_TX_RST BIT(4) +#define DEV5G_DEV_RST_CTRL_MAC_TX_RST_SET(x)\ + FIELD_PREP(DEV5G_DEV_RST_CTRL_MAC_TX_RST, x) +#define DEV5G_DEV_RST_CTRL_MAC_TX_RST_GET(x)\ + FIELD_GET(DEV5G_DEV_RST_CTRL_MAC_TX_RST, x) + +#define DEV5G_DEV_RST_CTRL_MAC_RX_RST BIT(0) +#define DEV5G_DEV_RST_CTRL_MAC_RX_RST_SET(x)\ + FIELD_PREP(DEV5G_DEV_RST_CTRL_MAC_RX_RST, x) +#define DEV5G_DEV_RST_CTRL_MAC_RX_RST_GET(x)\ + FIELD_GET(DEV5G_DEV_RST_CTRL_MAC_RX_RST, x) + +/* DSM:RAM_CTRL:RAM_INIT */ +#define DSM_RAM_INIT __REG(TARGET_DSM, 0, 1, 0, 0, 1, 4, 0, 0, 1, 4) + +#define DSM_RAM_INIT_RAM_INIT BIT(1) +#define DSM_RAM_INIT_RAM_INIT_SET(x)\ + FIELD_PREP(DSM_RAM_INIT_RAM_INIT, x) +#define DSM_RAM_INIT_RAM_INIT_GET(x)\ + FIELD_GET(DSM_RAM_INIT_RAM_INIT, x) + +#define DSM_RAM_INIT_RAM_CFG_HOOK BIT(0) +#define DSM_RAM_INIT_RAM_CFG_HOOK_SET(x)\ + FIELD_PREP(DSM_RAM_INIT_RAM_CFG_HOOK, x) +#define DSM_RAM_INIT_RAM_CFG_HOOK_GET(x)\ + FIELD_GET(DSM_RAM_INIT_RAM_CFG_HOOK, x) + +/* DSM:CFG:BUF_CFG */ +#define DSM_BUF_CFG(r) __REG(TARGET_DSM, 0, 1, 20, 0, 1, 3528, 0, r, 67, 4) + +#define DSM_BUF_CFG_CSC_STAT_DIS BIT(13) +#define DSM_BUF_CFG_CSC_STAT_DIS_SET(x)\ + FIELD_PREP(DSM_BUF_CFG_CSC_STAT_DIS, x) +#define DSM_BUF_CFG_CSC_STAT_DIS_GET(x)\ + FIELD_GET(DSM_BUF_CFG_CSC_STAT_DIS, x) + +#define DSM_BUF_CFG_AGING_ENA BIT(12) +#define DSM_BUF_CFG_AGING_ENA_SET(x)\ + FIELD_PREP(DSM_BUF_CFG_AGING_ENA, x) +#define DSM_BUF_CFG_AGING_ENA_GET(x)\ + FIELD_GET(DSM_BUF_CFG_AGING_ENA, x) + +#define DSM_BUF_CFG_UNDERFLOW_WATCHDOG_DIS BIT(11) +#define DSM_BUF_CFG_UNDERFLOW_WATCHDOG_DIS_SET(x)\ + FIELD_PREP(DSM_BUF_CFG_UNDERFLOW_WATCHDOG_DIS, x) +#define DSM_BUF_CFG_UNDERFLOW_WATCHDOG_DIS_GET(x)\ + FIELD_GET(DSM_BUF_CFG_UNDERFLOW_WATCHDOG_DIS, x) + +#define DSM_BUF_CFG_UNDERFLOW_WATCHDOG_TIMEOUT GENMASK(10, 0) +#define DSM_BUF_CFG_UNDERFLOW_WATCHDOG_TIMEOUT_SET(x)\ + FIELD_PREP(DSM_BUF_CFG_UNDERFLOW_WATCHDOG_TIMEOUT, x) +#define DSM_BUF_CFG_UNDERFLOW_WATCHDOG_TIMEOUT_GET(x)\ + FIELD_GET(DSM_BUF_CFG_UNDERFLOW_WATCHDOG_TIMEOUT, x) + +/* DSM:CFG:DEV_TX_STOP_WM_CFG */ +#define DSM_DEV_TX_STOP_WM_CFG(r) __REG(TARGET_DSM, 0, 1, 20, 0, 1, 3528, 1360, r, 67, 4) + +#define DSM_DEV_TX_STOP_WM_CFG_FAST_STARTUP_ENA BIT(9) +#define DSM_DEV_TX_STOP_WM_CFG_FAST_STARTUP_ENA_SET(x)\ + FIELD_PREP(DSM_DEV_TX_STOP_WM_CFG_FAST_STARTUP_ENA, x) +#define DSM_DEV_TX_STOP_WM_CFG_FAST_STARTUP_ENA_GET(x)\ + FIELD_GET(DSM_DEV_TX_STOP_WM_CFG_FAST_STARTUP_ENA, x) + +#define DSM_DEV_TX_STOP_WM_CFG_DEV10G_SHADOW_ENA BIT(8) +#define DSM_DEV_TX_STOP_WM_CFG_DEV10G_SHADOW_ENA_SET(x)\ + FIELD_PREP(DSM_DEV_TX_STOP_WM_CFG_DEV10G_SHADOW_ENA, x) +#define DSM_DEV_TX_STOP_WM_CFG_DEV10G_SHADOW_ENA_GET(x)\ + FIELD_GET(DSM_DEV_TX_STOP_WM_CFG_DEV10G_SHADOW_ENA, x) + +#define DSM_DEV_TX_STOP_WM_CFG_DEV_TX_STOP_WM GENMASK(7, 1) +#define DSM_DEV_TX_STOP_WM_CFG_DEV_TX_STOP_WM_SET(x)\ + FIELD_PREP(DSM_DEV_TX_STOP_WM_CFG_DEV_TX_STOP_WM, x) +#define DSM_DEV_TX_STOP_WM_CFG_DEV_TX_STOP_WM_GET(x)\ + FIELD_GET(DSM_DEV_TX_STOP_WM_CFG_DEV_TX_STOP_WM, x) + +#define DSM_DEV_TX_STOP_WM_CFG_DEV_TX_CNT_CLR BIT(0) +#define DSM_DEV_TX_STOP_WM_CFG_DEV_TX_CNT_CLR_SET(x)\ + FIELD_PREP(DSM_DEV_TX_STOP_WM_CFG_DEV_TX_CNT_CLR, x) +#define DSM_DEV_TX_STOP_WM_CFG_DEV_TX_CNT_CLR_GET(x)\ + FIELD_GET(DSM_DEV_TX_STOP_WM_CFG_DEV_TX_CNT_CLR, x) + +/* DSM:CFG:RX_PAUSE_CFG */ +#define DSM_RX_PAUSE_CFG(r) __REG(TARGET_DSM, 0, 1, 20, 0, 1, 3528, 1628, r, 67, 4) + +#define DSM_RX_PAUSE_CFG_RX_PAUSE_EN BIT(1) +#define DSM_RX_PAUSE_CFG_RX_PAUSE_EN_SET(x)\ + FIELD_PREP(DSM_RX_PAUSE_CFG_RX_PAUSE_EN, x) +#define DSM_RX_PAUSE_CFG_RX_PAUSE_EN_GET(x)\ + FIELD_GET(DSM_RX_PAUSE_CFG_RX_PAUSE_EN, x) + +#define DSM_RX_PAUSE_CFG_FC_OBEY_LOCAL BIT(0) +#define DSM_RX_PAUSE_CFG_FC_OBEY_LOCAL_SET(x)\ + FIELD_PREP(DSM_RX_PAUSE_CFG_FC_OBEY_LOCAL, x) +#define DSM_RX_PAUSE_CFG_FC_OBEY_LOCAL_GET(x)\ + FIELD_GET(DSM_RX_PAUSE_CFG_FC_OBEY_LOCAL, x) + +/* DSM:CFG:MAC_CFG */ +#define DSM_MAC_CFG(r) __REG(TARGET_DSM, 0, 1, 20, 0, 1, 3528, 2432, r, 67, 4) + +#define DSM_MAC_CFG_TX_PAUSE_VAL GENMASK(31, 16) +#define DSM_MAC_CFG_TX_PAUSE_VAL_SET(x)\ + FIELD_PREP(DSM_MAC_CFG_TX_PAUSE_VAL, x) +#define DSM_MAC_CFG_TX_PAUSE_VAL_GET(x)\ + FIELD_GET(DSM_MAC_CFG_TX_PAUSE_VAL, x) + +#define DSM_MAC_CFG_HDX_BACKPREASSURE BIT(2) +#define DSM_MAC_CFG_HDX_BACKPREASSURE_SET(x)\ + FIELD_PREP(DSM_MAC_CFG_HDX_BACKPREASSURE, x) +#define DSM_MAC_CFG_HDX_BACKPREASSURE_GET(x)\ + FIELD_GET(DSM_MAC_CFG_HDX_BACKPREASSURE, x) + +#define DSM_MAC_CFG_SEND_PAUSE_FRM_TWICE BIT(1) +#define DSM_MAC_CFG_SEND_PAUSE_FRM_TWICE_SET(x)\ + FIELD_PREP(DSM_MAC_CFG_SEND_PAUSE_FRM_TWICE, x) +#define DSM_MAC_CFG_SEND_PAUSE_FRM_TWICE_GET(x)\ + FIELD_GET(DSM_MAC_CFG_SEND_PAUSE_FRM_TWICE, x) + +#define DSM_MAC_CFG_TX_PAUSE_XON_XOFF BIT(0) +#define DSM_MAC_CFG_TX_PAUSE_XON_XOFF_SET(x)\ + FIELD_PREP(DSM_MAC_CFG_TX_PAUSE_XON_XOFF, x) +#define DSM_MAC_CFG_TX_PAUSE_XON_XOFF_GET(x)\ + FIELD_GET(DSM_MAC_CFG_TX_PAUSE_XON_XOFF, x) + +/* DSM:CFG:MAC_ADDR_BASE_HIGH_CFG */ +#define DSM_MAC_ADDR_BASE_HIGH_CFG(r) __REG(TARGET_DSM, 0, 1, 20, 0, 1, 3528, 2700, r, 65, 4) + +#define DSM_MAC_ADDR_BASE_HIGH_CFG_MAC_ADDR_HIGH GENMASK(23, 0) +#define DSM_MAC_ADDR_BASE_HIGH_CFG_MAC_ADDR_HIGH_SET(x)\ + FIELD_PREP(DSM_MAC_ADDR_BASE_HIGH_CFG_MAC_ADDR_HIGH, x) +#define DSM_MAC_ADDR_BASE_HIGH_CFG_MAC_ADDR_HIGH_GET(x)\ + FIELD_GET(DSM_MAC_ADDR_BASE_HIGH_CFG_MAC_ADDR_HIGH, x) + +/* DSM:CFG:MAC_ADDR_BASE_LOW_CFG */ +#define DSM_MAC_ADDR_BASE_LOW_CFG(r) __REG(TARGET_DSM, 0, 1, 20, 0, 1, 3528, 2960, r, 65, 4) + +#define DSM_MAC_ADDR_BASE_LOW_CFG_MAC_ADDR_LOW GENMASK(23, 0) +#define DSM_MAC_ADDR_BASE_LOW_CFG_MAC_ADDR_LOW_SET(x)\ + FIELD_PREP(DSM_MAC_ADDR_BASE_LOW_CFG_MAC_ADDR_LOW, x) +#define DSM_MAC_ADDR_BASE_LOW_CFG_MAC_ADDR_LOW_GET(x)\ + FIELD_GET(DSM_MAC_ADDR_BASE_LOW_CFG_MAC_ADDR_LOW, x) + +/* DSM:CFG:TAXI_CAL_CFG */ +#define DSM_TAXI_CAL_CFG(r) __REG(TARGET_DSM, 0, 1, 20, 0, 1, 3528, 3224, r, 9, 4) + +#define DSM_TAXI_CAL_CFG_CAL_IDX GENMASK(20, 15) +#define DSM_TAXI_CAL_CFG_CAL_IDX_SET(x)\ + FIELD_PREP(DSM_TAXI_CAL_CFG_CAL_IDX, x) +#define DSM_TAXI_CAL_CFG_CAL_IDX_GET(x)\ + FIELD_GET(DSM_TAXI_CAL_CFG_CAL_IDX, x) + +#define DSM_TAXI_CAL_CFG_CAL_CUR_LEN GENMASK(14, 9) +#define DSM_TAXI_CAL_CFG_CAL_CUR_LEN_SET(x)\ + FIELD_PREP(DSM_TAXI_CAL_CFG_CAL_CUR_LEN, x) +#define DSM_TAXI_CAL_CFG_CAL_CUR_LEN_GET(x)\ + FIELD_GET(DSM_TAXI_CAL_CFG_CAL_CUR_LEN, x) + +#define DSM_TAXI_CAL_CFG_CAL_CUR_VAL GENMASK(8, 5) +#define DSM_TAXI_CAL_CFG_CAL_CUR_VAL_SET(x)\ + FIELD_PREP(DSM_TAXI_CAL_CFG_CAL_CUR_VAL, x) +#define DSM_TAXI_CAL_CFG_CAL_CUR_VAL_GET(x)\ + FIELD_GET(DSM_TAXI_CAL_CFG_CAL_CUR_VAL, x) + +#define DSM_TAXI_CAL_CFG_CAL_PGM_VAL GENMASK(4, 1) +#define DSM_TAXI_CAL_CFG_CAL_PGM_VAL_SET(x)\ + FIELD_PREP(DSM_TAXI_CAL_CFG_CAL_PGM_VAL, x) +#define DSM_TAXI_CAL_CFG_CAL_PGM_VAL_GET(x)\ + FIELD_GET(DSM_TAXI_CAL_CFG_CAL_PGM_VAL, x) + +#define DSM_TAXI_CAL_CFG_CAL_PGM_ENA BIT(0) +#define DSM_TAXI_CAL_CFG_CAL_PGM_ENA_SET(x)\ + FIELD_PREP(DSM_TAXI_CAL_CFG_CAL_PGM_ENA, x) +#define DSM_TAXI_CAL_CFG_CAL_PGM_ENA_GET(x)\ + FIELD_GET(DSM_TAXI_CAL_CFG_CAL_PGM_ENA, x) + +/* EACL:POL_CFG:POL_EACL_CFG */ +#define EACL_POL_EACL_CFG __REG(TARGET_EACL, 0, 1, 150608, 0, 1, 780, 768, 0, 1, 4) + +#define EACL_POL_EACL_CFG_EACL_CNT_MARKED_AS_DROPPED BIT(5) +#define EACL_POL_EACL_CFG_EACL_CNT_MARKED_AS_DROPPED_SET(x)\ + FIELD_PREP(EACL_POL_EACL_CFG_EACL_CNT_MARKED_AS_DROPPED, x) +#define EACL_POL_EACL_CFG_EACL_CNT_MARKED_AS_DROPPED_GET(x)\ + FIELD_GET(EACL_POL_EACL_CFG_EACL_CNT_MARKED_AS_DROPPED, x) + +#define EACL_POL_EACL_CFG_EACL_ALLOW_FP_COPY BIT(4) +#define EACL_POL_EACL_CFG_EACL_ALLOW_FP_COPY_SET(x)\ + FIELD_PREP(EACL_POL_EACL_CFG_EACL_ALLOW_FP_COPY, x) +#define EACL_POL_EACL_CFG_EACL_ALLOW_FP_COPY_GET(x)\ + FIELD_GET(EACL_POL_EACL_CFG_EACL_ALLOW_FP_COPY, x) + +#define EACL_POL_EACL_CFG_EACL_ALLOW_CPU_COPY BIT(3) +#define EACL_POL_EACL_CFG_EACL_ALLOW_CPU_COPY_SET(x)\ + FIELD_PREP(EACL_POL_EACL_CFG_EACL_ALLOW_CPU_COPY, x) +#define EACL_POL_EACL_CFG_EACL_ALLOW_CPU_COPY_GET(x)\ + FIELD_GET(EACL_POL_EACL_CFG_EACL_ALLOW_CPU_COPY, x) + +#define EACL_POL_EACL_CFG_EACL_FORCE_CLOSE BIT(2) +#define EACL_POL_EACL_CFG_EACL_FORCE_CLOSE_SET(x)\ + FIELD_PREP(EACL_POL_EACL_CFG_EACL_FORCE_CLOSE, x) +#define EACL_POL_EACL_CFG_EACL_FORCE_CLOSE_GET(x)\ + FIELD_GET(EACL_POL_EACL_CFG_EACL_FORCE_CLOSE, x) + +#define EACL_POL_EACL_CFG_EACL_FORCE_OPEN BIT(1) +#define EACL_POL_EACL_CFG_EACL_FORCE_OPEN_SET(x)\ + FIELD_PREP(EACL_POL_EACL_CFG_EACL_FORCE_OPEN, x) +#define EACL_POL_EACL_CFG_EACL_FORCE_OPEN_GET(x)\ + FIELD_GET(EACL_POL_EACL_CFG_EACL_FORCE_OPEN, x) + +#define EACL_POL_EACL_CFG_EACL_FORCE_INIT BIT(0) +#define EACL_POL_EACL_CFG_EACL_FORCE_INIT_SET(x)\ + FIELD_PREP(EACL_POL_EACL_CFG_EACL_FORCE_INIT, x) +#define EACL_POL_EACL_CFG_EACL_FORCE_INIT_GET(x)\ + FIELD_GET(EACL_POL_EACL_CFG_EACL_FORCE_INIT, x) + +/* EACL:RAM_CTRL:RAM_INIT */ +#define EACL_RAM_INIT __REG(TARGET_EACL, 0, 1, 118736, 0, 1, 4, 0, 0, 1, 4) + +#define EACL_RAM_INIT_RAM_INIT BIT(1) +#define EACL_RAM_INIT_RAM_INIT_SET(x)\ + FIELD_PREP(EACL_RAM_INIT_RAM_INIT, x) +#define EACL_RAM_INIT_RAM_INIT_GET(x)\ + FIELD_GET(EACL_RAM_INIT_RAM_INIT, x) + +#define EACL_RAM_INIT_RAM_CFG_HOOK BIT(0) +#define EACL_RAM_INIT_RAM_CFG_HOOK_SET(x)\ + FIELD_PREP(EACL_RAM_INIT_RAM_CFG_HOOK, x) +#define EACL_RAM_INIT_RAM_CFG_HOOK_GET(x)\ + FIELD_GET(EACL_RAM_INIT_RAM_CFG_HOOK, x) + +/* FDMA:FDMA:FDMA_CH_ACTIVATE */ +#define FDMA_CH_ACTIVATE __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 0, 0, 1, 4) + +#define FDMA_CH_ACTIVATE_CH_ACTIVATE GENMASK(7, 0) +#define FDMA_CH_ACTIVATE_CH_ACTIVATE_SET(x)\ + FIELD_PREP(FDMA_CH_ACTIVATE_CH_ACTIVATE, x) +#define FDMA_CH_ACTIVATE_CH_ACTIVATE_GET(x)\ + FIELD_GET(FDMA_CH_ACTIVATE_CH_ACTIVATE, x) + +/* FDMA:FDMA:FDMA_CH_RELOAD */ +#define FDMA_CH_RELOAD __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 4, 0, 1, 4) + +#define FDMA_CH_RELOAD_CH_RELOAD GENMASK(7, 0) +#define FDMA_CH_RELOAD_CH_RELOAD_SET(x)\ + FIELD_PREP(FDMA_CH_RELOAD_CH_RELOAD, x) +#define FDMA_CH_RELOAD_CH_RELOAD_GET(x)\ + FIELD_GET(FDMA_CH_RELOAD_CH_RELOAD, x) + +/* FDMA:FDMA:FDMA_CH_DISABLE */ +#define FDMA_CH_DISABLE __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 8, 0, 1, 4) + +#define FDMA_CH_DISABLE_CH_DISABLE GENMASK(7, 0) +#define FDMA_CH_DISABLE_CH_DISABLE_SET(x)\ + FIELD_PREP(FDMA_CH_DISABLE_CH_DISABLE, x) +#define FDMA_CH_DISABLE_CH_DISABLE_GET(x)\ + FIELD_GET(FDMA_CH_DISABLE_CH_DISABLE, x) + +/* FDMA:FDMA:FDMA_DCB_LLP */ +#define FDMA_DCB_LLP(r) __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 52, r, 8, 4) + +/* FDMA:FDMA:FDMA_DCB_LLP1 */ +#define FDMA_DCB_LLP1(r) __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 84, r, 8, 4) + +/* FDMA:FDMA:FDMA_DCB_LLP_PREV */ +#define FDMA_DCB_LLP_PREV(r) __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 116, r, 8, 4) + +/* FDMA:FDMA:FDMA_DCB_LLP_PREV1 */ +#define FDMA_DCB_LLP_PREV1(r) __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 148, r, 8, 4) + +/* FDMA:FDMA:FDMA_CH_CFG */ +#define FDMA_CH_CFG(r) __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 224, r, 8, 4) + +#define FDMA_CH_CFG_CH_XTR_STATUS_MODE BIT(7) +#define FDMA_CH_CFG_CH_XTR_STATUS_MODE_SET(x)\ + FIELD_PREP(FDMA_CH_CFG_CH_XTR_STATUS_MODE, x) +#define FDMA_CH_CFG_CH_XTR_STATUS_MODE_GET(x)\ + FIELD_GET(FDMA_CH_CFG_CH_XTR_STATUS_MODE, x) + +#define FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY BIT(6) +#define FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY_SET(x)\ + FIELD_PREP(FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY, x) +#define FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY_GET(x)\ + FIELD_GET(FDMA_CH_CFG_CH_INTR_DB_EOF_ONLY, x) + +#define FDMA_CH_CFG_CH_INJ_PORT BIT(5) +#define FDMA_CH_CFG_CH_INJ_PORT_SET(x)\ + FIELD_PREP(FDMA_CH_CFG_CH_INJ_PORT, x) +#define FDMA_CH_CFG_CH_INJ_PORT_GET(x)\ + FIELD_GET(FDMA_CH_CFG_CH_INJ_PORT, x) + +#define FDMA_CH_CFG_CH_DCB_DB_CNT GENMASK(4, 1) +#define FDMA_CH_CFG_CH_DCB_DB_CNT_SET(x)\ + FIELD_PREP(FDMA_CH_CFG_CH_DCB_DB_CNT, x) +#define FDMA_CH_CFG_CH_DCB_DB_CNT_GET(x)\ + FIELD_GET(FDMA_CH_CFG_CH_DCB_DB_CNT, x) + +#define FDMA_CH_CFG_CH_MEM BIT(0) +#define FDMA_CH_CFG_CH_MEM_SET(x)\ + FIELD_PREP(FDMA_CH_CFG_CH_MEM, x) +#define FDMA_CH_CFG_CH_MEM_GET(x)\ + FIELD_GET(FDMA_CH_CFG_CH_MEM, x) + +/* FDMA:FDMA:FDMA_CH_TRANSLATE */ +#define FDMA_CH_TRANSLATE(r) __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 256, r, 8, 4) + +#define FDMA_CH_TRANSLATE_OFFSET GENMASK(15, 0) +#define FDMA_CH_TRANSLATE_OFFSET_SET(x)\ + FIELD_PREP(FDMA_CH_TRANSLATE_OFFSET, x) +#define FDMA_CH_TRANSLATE_OFFSET_GET(x)\ + FIELD_GET(FDMA_CH_TRANSLATE_OFFSET, x) + +/* FDMA:FDMA:FDMA_XTR_CFG */ +#define FDMA_XTR_CFG __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 364, 0, 1, 4) + +#define FDMA_XTR_CFG_XTR_FIFO_WM GENMASK(15, 11) +#define FDMA_XTR_CFG_XTR_FIFO_WM_SET(x)\ + FIELD_PREP(FDMA_XTR_CFG_XTR_FIFO_WM, x) +#define FDMA_XTR_CFG_XTR_FIFO_WM_GET(x)\ + FIELD_GET(FDMA_XTR_CFG_XTR_FIFO_WM, x) + +#define FDMA_XTR_CFG_XTR_ARB_SAT GENMASK(10, 0) +#define FDMA_XTR_CFG_XTR_ARB_SAT_SET(x)\ + FIELD_PREP(FDMA_XTR_CFG_XTR_ARB_SAT, x) +#define FDMA_XTR_CFG_XTR_ARB_SAT_GET(x)\ + FIELD_GET(FDMA_XTR_CFG_XTR_ARB_SAT, x) + +/* FDMA:FDMA:FDMA_PORT_CTRL */ +#define FDMA_PORT_CTRL(r) __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 376, r, 2, 4) + +#define FDMA_PORT_CTRL_INJ_STOP BIT(4) +#define FDMA_PORT_CTRL_INJ_STOP_SET(x)\ + FIELD_PREP(FDMA_PORT_CTRL_INJ_STOP, x) +#define FDMA_PORT_CTRL_INJ_STOP_GET(x)\ + FIELD_GET(FDMA_PORT_CTRL_INJ_STOP, x) + +#define FDMA_PORT_CTRL_INJ_STOP_FORCE BIT(3) +#define FDMA_PORT_CTRL_INJ_STOP_FORCE_SET(x)\ + FIELD_PREP(FDMA_PORT_CTRL_INJ_STOP_FORCE, x) +#define FDMA_PORT_CTRL_INJ_STOP_FORCE_GET(x)\ + FIELD_GET(FDMA_PORT_CTRL_INJ_STOP_FORCE, x) + +#define FDMA_PORT_CTRL_XTR_STOP BIT(2) +#define FDMA_PORT_CTRL_XTR_STOP_SET(x)\ + FIELD_PREP(FDMA_PORT_CTRL_XTR_STOP, x) +#define FDMA_PORT_CTRL_XTR_STOP_GET(x)\ + FIELD_GET(FDMA_PORT_CTRL_XTR_STOP, x) + +#define FDMA_PORT_CTRL_XTR_BUF_IS_EMPTY BIT(1) +#define FDMA_PORT_CTRL_XTR_BUF_IS_EMPTY_SET(x)\ + FIELD_PREP(FDMA_PORT_CTRL_XTR_BUF_IS_EMPTY, x) +#define FDMA_PORT_CTRL_XTR_BUF_IS_EMPTY_GET(x)\ + FIELD_GET(FDMA_PORT_CTRL_XTR_BUF_IS_EMPTY, x) + +#define FDMA_PORT_CTRL_XTR_BUF_RST BIT(0) +#define FDMA_PORT_CTRL_XTR_BUF_RST_SET(x)\ + FIELD_PREP(FDMA_PORT_CTRL_XTR_BUF_RST, x) +#define FDMA_PORT_CTRL_XTR_BUF_RST_GET(x)\ + FIELD_GET(FDMA_PORT_CTRL_XTR_BUF_RST, x) + +/* FDMA:FDMA:FDMA_INTR_DCB */ +#define FDMA_INTR_DCB __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 384, 0, 1, 4) + +#define FDMA_INTR_DCB_INTR_DCB GENMASK(7, 0) +#define FDMA_INTR_DCB_INTR_DCB_SET(x)\ + FIELD_PREP(FDMA_INTR_DCB_INTR_DCB, x) +#define FDMA_INTR_DCB_INTR_DCB_GET(x)\ + FIELD_GET(FDMA_INTR_DCB_INTR_DCB, x) + +/* FDMA:FDMA:FDMA_INTR_DCB_ENA */ +#define FDMA_INTR_DCB_ENA __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 388, 0, 1, 4) + +#define FDMA_INTR_DCB_ENA_INTR_DCB_ENA GENMASK(7, 0) +#define FDMA_INTR_DCB_ENA_INTR_DCB_ENA_SET(x)\ + FIELD_PREP(FDMA_INTR_DCB_ENA_INTR_DCB_ENA, x) +#define FDMA_INTR_DCB_ENA_INTR_DCB_ENA_GET(x)\ + FIELD_GET(FDMA_INTR_DCB_ENA_INTR_DCB_ENA, x) + +/* FDMA:FDMA:FDMA_INTR_DB */ +#define FDMA_INTR_DB __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 392, 0, 1, 4) + +#define FDMA_INTR_DB_INTR_DB GENMASK(7, 0) +#define FDMA_INTR_DB_INTR_DB_SET(x)\ + FIELD_PREP(FDMA_INTR_DB_INTR_DB, x) +#define FDMA_INTR_DB_INTR_DB_GET(x)\ + FIELD_GET(FDMA_INTR_DB_INTR_DB, x) + +/* FDMA:FDMA:FDMA_INTR_DB_ENA */ +#define FDMA_INTR_DB_ENA __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 396, 0, 1, 4) + +#define FDMA_INTR_DB_ENA_INTR_DB_ENA GENMASK(7, 0) +#define FDMA_INTR_DB_ENA_INTR_DB_ENA_SET(x)\ + FIELD_PREP(FDMA_INTR_DB_ENA_INTR_DB_ENA, x) +#define FDMA_INTR_DB_ENA_INTR_DB_ENA_GET(x)\ + FIELD_GET(FDMA_INTR_DB_ENA_INTR_DB_ENA, x) + +/* FDMA:FDMA:FDMA_INTR_ERR */ +#define FDMA_INTR_ERR __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 400, 0, 1, 4) + +#define FDMA_INTR_ERR_INTR_PORT_ERR GENMASK(9, 8) +#define FDMA_INTR_ERR_INTR_PORT_ERR_SET(x)\ + FIELD_PREP(FDMA_INTR_ERR_INTR_PORT_ERR, x) +#define FDMA_INTR_ERR_INTR_PORT_ERR_GET(x)\ + FIELD_GET(FDMA_INTR_ERR_INTR_PORT_ERR, x) + +#define FDMA_INTR_ERR_INTR_CH_ERR GENMASK(7, 0) +#define FDMA_INTR_ERR_INTR_CH_ERR_SET(x)\ + FIELD_PREP(FDMA_INTR_ERR_INTR_CH_ERR, x) +#define FDMA_INTR_ERR_INTR_CH_ERR_GET(x)\ + FIELD_GET(FDMA_INTR_ERR_INTR_CH_ERR, x) + +/* FDMA:FDMA:FDMA_ERRORS */ +#define FDMA_ERRORS __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 412, 0, 1, 4) + +#define FDMA_ERRORS_ERR_XTR_WR GENMASK(31, 30) +#define FDMA_ERRORS_ERR_XTR_WR_SET(x)\ + FIELD_PREP(FDMA_ERRORS_ERR_XTR_WR, x) +#define FDMA_ERRORS_ERR_XTR_WR_GET(x)\ + FIELD_GET(FDMA_ERRORS_ERR_XTR_WR, x) + +#define FDMA_ERRORS_ERR_XTR_OVF GENMASK(29, 28) +#define FDMA_ERRORS_ERR_XTR_OVF_SET(x)\ + FIELD_PREP(FDMA_ERRORS_ERR_XTR_OVF, x) +#define FDMA_ERRORS_ERR_XTR_OVF_GET(x)\ + FIELD_GET(FDMA_ERRORS_ERR_XTR_OVF, x) + +#define FDMA_ERRORS_ERR_XTR_TAXI32_OVF GENMASK(27, 26) +#define FDMA_ERRORS_ERR_XTR_TAXI32_OVF_SET(x)\ + FIELD_PREP(FDMA_ERRORS_ERR_XTR_TAXI32_OVF, x) +#define FDMA_ERRORS_ERR_XTR_TAXI32_OVF_GET(x)\ + FIELD_GET(FDMA_ERRORS_ERR_XTR_TAXI32_OVF, x) + +#define FDMA_ERRORS_ERR_DCB_XTR_DATAL GENMASK(25, 24) +#define FDMA_ERRORS_ERR_DCB_XTR_DATAL_SET(x)\ + FIELD_PREP(FDMA_ERRORS_ERR_DCB_XTR_DATAL, x) +#define FDMA_ERRORS_ERR_DCB_XTR_DATAL_GET(x)\ + FIELD_GET(FDMA_ERRORS_ERR_DCB_XTR_DATAL, x) + +#define FDMA_ERRORS_ERR_DCB_RD GENMASK(23, 16) +#define FDMA_ERRORS_ERR_DCB_RD_SET(x)\ + FIELD_PREP(FDMA_ERRORS_ERR_DCB_RD, x) +#define FDMA_ERRORS_ERR_DCB_RD_GET(x)\ + FIELD_GET(FDMA_ERRORS_ERR_DCB_RD, x) + +#define FDMA_ERRORS_ERR_INJ_RD GENMASK(15, 10) +#define FDMA_ERRORS_ERR_INJ_RD_SET(x)\ + FIELD_PREP(FDMA_ERRORS_ERR_INJ_RD, x) +#define FDMA_ERRORS_ERR_INJ_RD_GET(x)\ + FIELD_GET(FDMA_ERRORS_ERR_INJ_RD, x) + +#define FDMA_ERRORS_ERR_INJ_OUT_OF_SYNC GENMASK(9, 8) +#define FDMA_ERRORS_ERR_INJ_OUT_OF_SYNC_SET(x)\ + FIELD_PREP(FDMA_ERRORS_ERR_INJ_OUT_OF_SYNC, x) +#define FDMA_ERRORS_ERR_INJ_OUT_OF_SYNC_GET(x)\ + FIELD_GET(FDMA_ERRORS_ERR_INJ_OUT_OF_SYNC, x) + +#define FDMA_ERRORS_ERR_CH_WR GENMASK(7, 0) +#define FDMA_ERRORS_ERR_CH_WR_SET(x)\ + FIELD_PREP(FDMA_ERRORS_ERR_CH_WR, x) +#define FDMA_ERRORS_ERR_CH_WR_GET(x)\ + FIELD_GET(FDMA_ERRORS_ERR_CH_WR, x) + +/* FDMA:FDMA:FDMA_ERRORS_2 */ +#define FDMA_ERRORS_2 __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 416, 0, 1, 4) + +#define FDMA_ERRORS_2_ERR_XTR_FRAG GENMASK(1, 0) +#define FDMA_ERRORS_2_ERR_XTR_FRAG_SET(x)\ + FIELD_PREP(FDMA_ERRORS_2_ERR_XTR_FRAG, x) +#define FDMA_ERRORS_2_ERR_XTR_FRAG_GET(x)\ + FIELD_GET(FDMA_ERRORS_2_ERR_XTR_FRAG, x) + +/* FDMA:FDMA:FDMA_CTRL */ +#define FDMA_CTRL __REG(TARGET_FDMA, 0, 1, 8, 0, 1, 428, 424, 0, 1, 4) + +#define FDMA_CTRL_NRESET BIT(0) +#define FDMA_CTRL_NRESET_SET(x)\ + FIELD_PREP(FDMA_CTRL_NRESET, x) +#define FDMA_CTRL_NRESET_GET(x)\ + FIELD_GET(FDMA_CTRL_NRESET, x) + +/* DEVCPU_GCB:CHIP_REGS:CHIP_ID */ +#define GCB_CHIP_ID __REG(TARGET_GCB, 0, 1, 0, 0, 1, 424, 0, 0, 1, 4) + +#define GCB_CHIP_ID_REV_ID GENMASK(31, 28) +#define GCB_CHIP_ID_REV_ID_SET(x)\ + FIELD_PREP(GCB_CHIP_ID_REV_ID, x) +#define GCB_CHIP_ID_REV_ID_GET(x)\ + FIELD_GET(GCB_CHIP_ID_REV_ID, x) + +#define GCB_CHIP_ID_PART_ID GENMASK(27, 12) +#define GCB_CHIP_ID_PART_ID_SET(x)\ + FIELD_PREP(GCB_CHIP_ID_PART_ID, x) +#define GCB_CHIP_ID_PART_ID_GET(x)\ + FIELD_GET(GCB_CHIP_ID_PART_ID, x) + +#define GCB_CHIP_ID_MFG_ID GENMASK(11, 1) +#define GCB_CHIP_ID_MFG_ID_SET(x)\ + FIELD_PREP(GCB_CHIP_ID_MFG_ID, x) +#define GCB_CHIP_ID_MFG_ID_GET(x)\ + FIELD_GET(GCB_CHIP_ID_MFG_ID, x) + +#define GCB_CHIP_ID_ONE BIT(0) +#define GCB_CHIP_ID_ONE_SET(x)\ + FIELD_PREP(GCB_CHIP_ID_ONE, x) +#define GCB_CHIP_ID_ONE_GET(x)\ + FIELD_GET(GCB_CHIP_ID_ONE, x) + +/* DEVCPU_GCB:CHIP_REGS:SOFT_RST */ +#define GCB_SOFT_RST __REG(TARGET_GCB, 0, 1, 0, 0, 1, 424, 8, 0, 1, 4) + +#define GCB_SOFT_RST_SOFT_NON_CFG_RST BIT(2) +#define GCB_SOFT_RST_SOFT_NON_CFG_RST_SET(x)\ + FIELD_PREP(GCB_SOFT_RST_SOFT_NON_CFG_RST, x) +#define GCB_SOFT_RST_SOFT_NON_CFG_RST_GET(x)\ + FIELD_GET(GCB_SOFT_RST_SOFT_NON_CFG_RST, x) + +#define GCB_SOFT_RST_SOFT_SWC_RST BIT(1) +#define GCB_SOFT_RST_SOFT_SWC_RST_SET(x)\ + FIELD_PREP(GCB_SOFT_RST_SOFT_SWC_RST, x) +#define GCB_SOFT_RST_SOFT_SWC_RST_GET(x)\ + FIELD_GET(GCB_SOFT_RST_SOFT_SWC_RST, x) + +#define GCB_SOFT_RST_SOFT_CHIP_RST BIT(0) +#define GCB_SOFT_RST_SOFT_CHIP_RST_SET(x)\ + FIELD_PREP(GCB_SOFT_RST_SOFT_CHIP_RST, x) +#define GCB_SOFT_RST_SOFT_CHIP_RST_GET(x)\ + FIELD_GET(GCB_SOFT_RST_SOFT_CHIP_RST, x) + +/* DEVCPU_GCB:CHIP_REGS:HW_SGPIO_SD_CFG */ +#define GCB_HW_SGPIO_SD_CFG __REG(TARGET_GCB, 0, 1, 0, 0, 1, 424, 20, 0, 1, 4) + +#define GCB_HW_SGPIO_SD_CFG_SD_HIGH_ENA BIT(1) +#define GCB_HW_SGPIO_SD_CFG_SD_HIGH_ENA_SET(x)\ + FIELD_PREP(GCB_HW_SGPIO_SD_CFG_SD_HIGH_ENA, x) +#define GCB_HW_SGPIO_SD_CFG_SD_HIGH_ENA_GET(x)\ + FIELD_GET(GCB_HW_SGPIO_SD_CFG_SD_HIGH_ENA, x) + +#define GCB_HW_SGPIO_SD_CFG_SD_MAP_SEL BIT(0) +#define GCB_HW_SGPIO_SD_CFG_SD_MAP_SEL_SET(x)\ + FIELD_PREP(GCB_HW_SGPIO_SD_CFG_SD_MAP_SEL, x) +#define GCB_HW_SGPIO_SD_CFG_SD_MAP_SEL_GET(x)\ + FIELD_GET(GCB_HW_SGPIO_SD_CFG_SD_MAP_SEL, x) + +/* DEVCPU_GCB:CHIP_REGS:HW_SGPIO_TO_SD_MAP_CFG */ +#define GCB_HW_SGPIO_TO_SD_MAP_CFG(r) __REG(TARGET_GCB, 0, 1, 0, 0, 1, 424, 24, r, 65, 4) + +#define GCB_HW_SGPIO_TO_SD_MAP_CFG_SGPIO_TO_SD_SEL GENMASK(8, 0) +#define GCB_HW_SGPIO_TO_SD_MAP_CFG_SGPIO_TO_SD_SEL_SET(x)\ + FIELD_PREP(GCB_HW_SGPIO_TO_SD_MAP_CFG_SGPIO_TO_SD_SEL, x) +#define GCB_HW_SGPIO_TO_SD_MAP_CFG_SGPIO_TO_SD_SEL_GET(x)\ + FIELD_GET(GCB_HW_SGPIO_TO_SD_MAP_CFG_SGPIO_TO_SD_SEL, x) + +/* DEVCPU_GCB:SIO_CTRL:SIO_CLOCK */ +#define GCB_SIO_CLOCK(g) __REG(TARGET_GCB, 0, 1, 876, g, 3, 280, 20, 0, 1, 4) + +#define GCB_SIO_CLOCK_SIO_CLK_FREQ GENMASK(19, 8) +#define GCB_SIO_CLOCK_SIO_CLK_FREQ_SET(x)\ + FIELD_PREP(GCB_SIO_CLOCK_SIO_CLK_FREQ, x) +#define GCB_SIO_CLOCK_SIO_CLK_FREQ_GET(x)\ + FIELD_GET(GCB_SIO_CLOCK_SIO_CLK_FREQ, x) + +#define GCB_SIO_CLOCK_SYS_CLK_PERIOD GENMASK(7, 0) +#define GCB_SIO_CLOCK_SYS_CLK_PERIOD_SET(x)\ + FIELD_PREP(GCB_SIO_CLOCK_SYS_CLK_PERIOD, x) +#define GCB_SIO_CLOCK_SYS_CLK_PERIOD_GET(x)\ + FIELD_GET(GCB_SIO_CLOCK_SYS_CLK_PERIOD, x) + +/* HSCH:HSCH_MISC:SYS_CLK_PER */ +#define HSCH_SYS_CLK_PER __REG(TARGET_HSCH, 0, 1, 163104, 0, 1, 648, 640, 0, 1, 4) + +#define HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS GENMASK(7, 0) +#define HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS_SET(x)\ + FIELD_PREP(HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS, x) +#define HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS_GET(x)\ + FIELD_GET(HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS, x) + +/* HSCH:SYSTEM:FLUSH_CTRL */ +#define HSCH_FLUSH_CTRL __REG(TARGET_HSCH, 0, 1, 184000, 0, 1, 312, 4, 0, 1, 4) + +#define HSCH_FLUSH_CTRL_FLUSH_ENA BIT(27) +#define HSCH_FLUSH_CTRL_FLUSH_ENA_SET(x)\ + FIELD_PREP(HSCH_FLUSH_CTRL_FLUSH_ENA, x) +#define HSCH_FLUSH_CTRL_FLUSH_ENA_GET(x)\ + FIELD_GET(HSCH_FLUSH_CTRL_FLUSH_ENA, x) + +#define HSCH_FLUSH_CTRL_FLUSH_SRC BIT(26) +#define HSCH_FLUSH_CTRL_FLUSH_SRC_SET(x)\ + FIELD_PREP(HSCH_FLUSH_CTRL_FLUSH_SRC, x) +#define HSCH_FLUSH_CTRL_FLUSH_SRC_GET(x)\ + FIELD_GET(HSCH_FLUSH_CTRL_FLUSH_SRC, x) + +#define HSCH_FLUSH_CTRL_FLUSH_DST BIT(25) +#define HSCH_FLUSH_CTRL_FLUSH_DST_SET(x)\ + FIELD_PREP(HSCH_FLUSH_CTRL_FLUSH_DST, x) +#define HSCH_FLUSH_CTRL_FLUSH_DST_GET(x)\ + FIELD_GET(HSCH_FLUSH_CTRL_FLUSH_DST, x) + +#define HSCH_FLUSH_CTRL_FLUSH_PORT GENMASK(24, 18) +#define HSCH_FLUSH_CTRL_FLUSH_PORT_SET(x)\ + FIELD_PREP(HSCH_FLUSH_CTRL_FLUSH_PORT, x) +#define HSCH_FLUSH_CTRL_FLUSH_PORT_GET(x)\ + FIELD_GET(HSCH_FLUSH_CTRL_FLUSH_PORT, x) + +#define HSCH_FLUSH_CTRL_FLUSH_QUEUE BIT(17) +#define HSCH_FLUSH_CTRL_FLUSH_QUEUE_SET(x)\ + FIELD_PREP(HSCH_FLUSH_CTRL_FLUSH_QUEUE, x) +#define HSCH_FLUSH_CTRL_FLUSH_QUEUE_GET(x)\ + FIELD_GET(HSCH_FLUSH_CTRL_FLUSH_QUEUE, x) + +#define HSCH_FLUSH_CTRL_FLUSH_SE BIT(16) +#define HSCH_FLUSH_CTRL_FLUSH_SE_SET(x)\ + FIELD_PREP(HSCH_FLUSH_CTRL_FLUSH_SE, x) +#define HSCH_FLUSH_CTRL_FLUSH_SE_GET(x)\ + FIELD_GET(HSCH_FLUSH_CTRL_FLUSH_SE, x) + +#define HSCH_FLUSH_CTRL_FLUSH_HIER GENMASK(15, 0) +#define HSCH_FLUSH_CTRL_FLUSH_HIER_SET(x)\ + FIELD_PREP(HSCH_FLUSH_CTRL_FLUSH_HIER, x) +#define HSCH_FLUSH_CTRL_FLUSH_HIER_GET(x)\ + FIELD_GET(HSCH_FLUSH_CTRL_FLUSH_HIER, x) + +/* HSCH:SYSTEM:PORT_MODE */ +#define HSCH_PORT_MODE(r) __REG(TARGET_HSCH, 0, 1, 184000, 0, 1, 312, 8, r, 70, 4) + +#define HSCH_PORT_MODE_DEQUEUE_DIS BIT(4) +#define HSCH_PORT_MODE_DEQUEUE_DIS_SET(x)\ + FIELD_PREP(HSCH_PORT_MODE_DEQUEUE_DIS, x) +#define HSCH_PORT_MODE_DEQUEUE_DIS_GET(x)\ + FIELD_GET(HSCH_PORT_MODE_DEQUEUE_DIS, x) + +#define HSCH_PORT_MODE_AGE_DIS BIT(3) +#define HSCH_PORT_MODE_AGE_DIS_SET(x)\ + FIELD_PREP(HSCH_PORT_MODE_AGE_DIS, x) +#define HSCH_PORT_MODE_AGE_DIS_GET(x)\ + FIELD_GET(HSCH_PORT_MODE_AGE_DIS, x) + +#define HSCH_PORT_MODE_TRUNC_ENA BIT(2) +#define HSCH_PORT_MODE_TRUNC_ENA_SET(x)\ + FIELD_PREP(HSCH_PORT_MODE_TRUNC_ENA, x) +#define HSCH_PORT_MODE_TRUNC_ENA_GET(x)\ + FIELD_GET(HSCH_PORT_MODE_TRUNC_ENA, x) + +#define HSCH_PORT_MODE_EIR_REMARK_ENA BIT(1) +#define HSCH_PORT_MODE_EIR_REMARK_ENA_SET(x)\ + FIELD_PREP(HSCH_PORT_MODE_EIR_REMARK_ENA, x) +#define HSCH_PORT_MODE_EIR_REMARK_ENA_GET(x)\ + FIELD_GET(HSCH_PORT_MODE_EIR_REMARK_ENA, x) + +#define HSCH_PORT_MODE_CPU_PRIO_MODE BIT(0) +#define HSCH_PORT_MODE_CPU_PRIO_MODE_SET(x)\ + FIELD_PREP(HSCH_PORT_MODE_CPU_PRIO_MODE, x) +#define HSCH_PORT_MODE_CPU_PRIO_MODE_GET(x)\ + FIELD_GET(HSCH_PORT_MODE_CPU_PRIO_MODE, x) + +/* HSCH:SYSTEM:OUTB_SHARE_ENA */ +#define HSCH_OUTB_SHARE_ENA(r) __REG(TARGET_HSCH, 0, 1, 184000, 0, 1, 312, 288, r, 5, 4) + +#define HSCH_OUTB_SHARE_ENA_OUTB_SHARE_ENA GENMASK(7, 0) +#define HSCH_OUTB_SHARE_ENA_OUTB_SHARE_ENA_SET(x)\ + FIELD_PREP(HSCH_OUTB_SHARE_ENA_OUTB_SHARE_ENA, x) +#define HSCH_OUTB_SHARE_ENA_OUTB_SHARE_ENA_GET(x)\ + FIELD_GET(HSCH_OUTB_SHARE_ENA_OUTB_SHARE_ENA, x) + +/* HSCH:MMGT:RESET_CFG */ +#define HSCH_RESET_CFG __REG(TARGET_HSCH, 0, 1, 162368, 0, 1, 16, 8, 0, 1, 4) + +#define HSCH_RESET_CFG_CORE_ENA BIT(0) +#define HSCH_RESET_CFG_CORE_ENA_SET(x)\ + FIELD_PREP(HSCH_RESET_CFG_CORE_ENA, x) +#define HSCH_RESET_CFG_CORE_ENA_GET(x)\ + FIELD_GET(HSCH_RESET_CFG_CORE_ENA, x) + +/* HSCH:TAS_CONFIG:TAS_STATEMACHINE_CFG */ +#define HSCH_TAS_STATEMACHINE_CFG __REG(TARGET_HSCH, 0, 1, 162384, 0, 1, 12, 8, 0, 1, 4) + +#define HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY GENMASK(7, 0) +#define HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY_SET(x)\ + FIELD_PREP(HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY, x) +#define HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY_GET(x)\ + FIELD_GET(HSCH_TAS_STATEMACHINE_CFG_REVISIT_DLY, x) + +/* LRN:COMMON:COMMON_ACCESS_CTRL */ +#define LRN_COMMON_ACCESS_CTRL __REG(TARGET_LRN, 0, 1, 0, 0, 1, 72, 0, 0, 1, 4) + +#define LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_COL GENMASK(21, 20) +#define LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_COL_SET(x)\ + FIELD_PREP(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_COL, x) +#define LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_COL_GET(x)\ + FIELD_GET(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_COL, x) + +#define LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_TYPE BIT(19) +#define LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_TYPE_SET(x)\ + FIELD_PREP(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_TYPE, x) +#define LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_TYPE_GET(x)\ + FIELD_GET(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_TYPE, x) + +#define LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_ROW GENMASK(18, 5) +#define LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_ROW_SET(x)\ + FIELD_PREP(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_ROW, x) +#define LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_ROW_GET(x)\ + FIELD_GET(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_DIRECT_ROW, x) + +#define LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_CMD GENMASK(4, 1) +#define LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_CMD_SET(x)\ + FIELD_PREP(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_CMD, x) +#define LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_CMD_GET(x)\ + FIELD_GET(LRN_COMMON_ACCESS_CTRL_CPU_ACCESS_CMD, x) + +#define LRN_COMMON_ACCESS_CTRL_MAC_TABLE_ACCESS_SHOT BIT(0) +#define LRN_COMMON_ACCESS_CTRL_MAC_TABLE_ACCESS_SHOT_SET(x)\ + FIELD_PREP(LRN_COMMON_ACCESS_CTRL_MAC_TABLE_ACCESS_SHOT, x) +#define LRN_COMMON_ACCESS_CTRL_MAC_TABLE_ACCESS_SHOT_GET(x)\ + FIELD_GET(LRN_COMMON_ACCESS_CTRL_MAC_TABLE_ACCESS_SHOT, x) + +/* LRN:COMMON:MAC_ACCESS_CFG_0 */ +#define LRN_MAC_ACCESS_CFG_0 __REG(TARGET_LRN, 0, 1, 0, 0, 1, 72, 4, 0, 1, 4) + +#define LRN_MAC_ACCESS_CFG_0_MAC_ENTRY_FID GENMASK(28, 16) +#define LRN_MAC_ACCESS_CFG_0_MAC_ENTRY_FID_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_0_MAC_ENTRY_FID, x) +#define LRN_MAC_ACCESS_CFG_0_MAC_ENTRY_FID_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_0_MAC_ENTRY_FID, x) + +#define LRN_MAC_ACCESS_CFG_0_MAC_ENTRY_MAC_MSB GENMASK(15, 0) +#define LRN_MAC_ACCESS_CFG_0_MAC_ENTRY_MAC_MSB_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_0_MAC_ENTRY_MAC_MSB, x) +#define LRN_MAC_ACCESS_CFG_0_MAC_ENTRY_MAC_MSB_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_0_MAC_ENTRY_MAC_MSB, x) + +/* LRN:COMMON:MAC_ACCESS_CFG_1 */ +#define LRN_MAC_ACCESS_CFG_1 __REG(TARGET_LRN, 0, 1, 0, 0, 1, 72, 8, 0, 1, 4) + +/* LRN:COMMON:MAC_ACCESS_CFG_2 */ +#define LRN_MAC_ACCESS_CFG_2 __REG(TARGET_LRN, 0, 1, 0, 0, 1, 72, 12, 0, 1, 4) + +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_SRC_KILL_FWD BIT(28) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_SRC_KILL_FWD_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_SRC_KILL_FWD, x) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_SRC_KILL_FWD_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_SRC_KILL_FWD, x) + +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_NXT_LRN_ALL BIT(27) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_NXT_LRN_ALL_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_NXT_LRN_ALL, x) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_NXT_LRN_ALL_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_NXT_LRN_ALL, x) + +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_CPU_QU GENMASK(26, 24) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_CPU_QU_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_CPU_QU, x) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_CPU_QU_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_CPU_QU, x) + +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_CPU_COPY BIT(23) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_CPU_COPY_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_CPU_COPY, x) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_CPU_COPY_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_CPU_COPY, x) + +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLAN_IGNORE BIT(22) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLAN_IGNORE_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLAN_IGNORE, x) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLAN_IGNORE_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLAN_IGNORE, x) + +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_MIRROR BIT(21) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_MIRROR_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_MIRROR, x) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_MIRROR_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_MIRROR, x) + +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_AGE_FLAG GENMASK(20, 19) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_AGE_FLAG_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_AGE_FLAG, x) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_AGE_FLAG_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_AGE_FLAG, x) + +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_AGE_INTERVAL GENMASK(18, 17) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_AGE_INTERVAL_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_AGE_INTERVAL, x) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_AGE_INTERVAL_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_AGE_INTERVAL, x) + +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_LOCKED BIT(16) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_LOCKED_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_LOCKED, x) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_LOCKED_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_LOCKED, x) + +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLD BIT(15) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLD_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLD, x) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLD_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_VLD, x) + +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR_TYPE GENMASK(14, 12) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR_TYPE_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR_TYPE, x) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR_TYPE_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR_TYPE, x) + +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR GENMASK(11, 0) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR, x) +#define LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_2_MAC_ENTRY_ADDR, x) + +/* LRN:COMMON:MAC_ACCESS_CFG_3 */ +#define LRN_MAC_ACCESS_CFG_3 __REG(TARGET_LRN, 0, 1, 0, 0, 1, 72, 16, 0, 1, 4) + +#define LRN_MAC_ACCESS_CFG_3_MAC_ENTRY_ISDX_LIMIT_IDX GENMASK(10, 0) +#define LRN_MAC_ACCESS_CFG_3_MAC_ENTRY_ISDX_LIMIT_IDX_SET(x)\ + FIELD_PREP(LRN_MAC_ACCESS_CFG_3_MAC_ENTRY_ISDX_LIMIT_IDX, x) +#define LRN_MAC_ACCESS_CFG_3_MAC_ENTRY_ISDX_LIMIT_IDX_GET(x)\ + FIELD_GET(LRN_MAC_ACCESS_CFG_3_MAC_ENTRY_ISDX_LIMIT_IDX, x) + +/* LRN:COMMON:SCAN_NEXT_CFG */ +#define LRN_SCAN_NEXT_CFG __REG(TARGET_LRN, 0, 1, 0, 0, 1, 72, 20, 0, 1, 4) + +#define LRN_SCAN_NEXT_CFG_SCAN_AGE_FLAG_UPDATE_SEL GENMASK(21, 19) +#define LRN_SCAN_NEXT_CFG_SCAN_AGE_FLAG_UPDATE_SEL_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_SCAN_AGE_FLAG_UPDATE_SEL, x) +#define LRN_SCAN_NEXT_CFG_SCAN_AGE_FLAG_UPDATE_SEL_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_SCAN_AGE_FLAG_UPDATE_SEL, x) + +#define LRN_SCAN_NEXT_CFG_SCAN_NXT_LRN_ALL_UPDATE_SEL GENMASK(18, 17) +#define LRN_SCAN_NEXT_CFG_SCAN_NXT_LRN_ALL_UPDATE_SEL_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_SCAN_NXT_LRN_ALL_UPDATE_SEL, x) +#define LRN_SCAN_NEXT_CFG_SCAN_NXT_LRN_ALL_UPDATE_SEL_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_SCAN_NXT_LRN_ALL_UPDATE_SEL, x) + +#define LRN_SCAN_NEXT_CFG_SCAN_AGE_FILTER_SEL GENMASK(16, 15) +#define LRN_SCAN_NEXT_CFG_SCAN_AGE_FILTER_SEL_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_SCAN_AGE_FILTER_SEL, x) +#define LRN_SCAN_NEXT_CFG_SCAN_AGE_FILTER_SEL_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_SCAN_AGE_FILTER_SEL, x) + +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_MOVE_FOUND_ENA BIT(14) +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_MOVE_FOUND_ENA_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_SCAN_NEXT_MOVE_FOUND_ENA, x) +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_MOVE_FOUND_ENA_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_SCAN_NEXT_MOVE_FOUND_ENA, x) + +#define LRN_SCAN_NEXT_CFG_NXT_LRN_ALL_FILTER_ENA BIT(13) +#define LRN_SCAN_NEXT_CFG_NXT_LRN_ALL_FILTER_ENA_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_NXT_LRN_ALL_FILTER_ENA, x) +#define LRN_SCAN_NEXT_CFG_NXT_LRN_ALL_FILTER_ENA_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_NXT_LRN_ALL_FILTER_ENA, x) + +#define LRN_SCAN_NEXT_CFG_SCAN_USE_PORT_FILTER_ENA BIT(12) +#define LRN_SCAN_NEXT_CFG_SCAN_USE_PORT_FILTER_ENA_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_SCAN_USE_PORT_FILTER_ENA, x) +#define LRN_SCAN_NEXT_CFG_SCAN_USE_PORT_FILTER_ENA_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_SCAN_USE_PORT_FILTER_ENA, x) + +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_REMOVE_FOUND_ENA BIT(11) +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_REMOVE_FOUND_ENA_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_SCAN_NEXT_REMOVE_FOUND_ENA, x) +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_REMOVE_FOUND_ENA_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_SCAN_NEXT_REMOVE_FOUND_ENA, x) + +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_UNTIL_FOUND_ENA BIT(10) +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_UNTIL_FOUND_ENA_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_SCAN_NEXT_UNTIL_FOUND_ENA, x) +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_UNTIL_FOUND_ENA_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_SCAN_NEXT_UNTIL_FOUND_ENA, x) + +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_INC_AGE_BITS_ENA BIT(9) +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_INC_AGE_BITS_ENA_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_SCAN_NEXT_INC_AGE_BITS_ENA, x) +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_INC_AGE_BITS_ENA_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_SCAN_NEXT_INC_AGE_BITS_ENA, x) + +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_AGED_ONLY_ENA BIT(8) +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_AGED_ONLY_ENA_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_SCAN_NEXT_AGED_ONLY_ENA, x) +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_AGED_ONLY_ENA_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_SCAN_NEXT_AGED_ONLY_ENA, x) + +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_IGNORE_LOCKED_ENA BIT(7) +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_IGNORE_LOCKED_ENA_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_SCAN_NEXT_IGNORE_LOCKED_ENA, x) +#define LRN_SCAN_NEXT_CFG_SCAN_NEXT_IGNORE_LOCKED_ENA_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_SCAN_NEXT_IGNORE_LOCKED_ENA, x) + +#define LRN_SCAN_NEXT_CFG_SCAN_AGE_INTERVAL_MASK GENMASK(6, 3) +#define LRN_SCAN_NEXT_CFG_SCAN_AGE_INTERVAL_MASK_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_SCAN_AGE_INTERVAL_MASK, x) +#define LRN_SCAN_NEXT_CFG_SCAN_AGE_INTERVAL_MASK_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_SCAN_AGE_INTERVAL_MASK, x) + +#define LRN_SCAN_NEXT_CFG_ISDX_LIMIT_IDX_FILTER_ENA BIT(2) +#define LRN_SCAN_NEXT_CFG_ISDX_LIMIT_IDX_FILTER_ENA_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_ISDX_LIMIT_IDX_FILTER_ENA, x) +#define LRN_SCAN_NEXT_CFG_ISDX_LIMIT_IDX_FILTER_ENA_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_ISDX_LIMIT_IDX_FILTER_ENA, x) + +#define LRN_SCAN_NEXT_CFG_FID_FILTER_ENA BIT(1) +#define LRN_SCAN_NEXT_CFG_FID_FILTER_ENA_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_FID_FILTER_ENA, x) +#define LRN_SCAN_NEXT_CFG_FID_FILTER_ENA_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_FID_FILTER_ENA, x) + +#define LRN_SCAN_NEXT_CFG_ADDR_FILTER_ENA BIT(0) +#define LRN_SCAN_NEXT_CFG_ADDR_FILTER_ENA_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_ADDR_FILTER_ENA, x) +#define LRN_SCAN_NEXT_CFG_ADDR_FILTER_ENA_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_ADDR_FILTER_ENA, x) + +/* LRN:COMMON:SCAN_NEXT_CFG_1 */ +#define LRN_SCAN_NEXT_CFG_1 __REG(TARGET_LRN, 0, 1, 0, 0, 1, 72, 24, 0, 1, 4) + +#define LRN_SCAN_NEXT_CFG_1_PORT_MOVE_NEW_ADDR GENMASK(30, 16) +#define LRN_SCAN_NEXT_CFG_1_PORT_MOVE_NEW_ADDR_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_1_PORT_MOVE_NEW_ADDR, x) +#define LRN_SCAN_NEXT_CFG_1_PORT_MOVE_NEW_ADDR_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_1_PORT_MOVE_NEW_ADDR, x) + +#define LRN_SCAN_NEXT_CFG_1_SCAN_ENTRY_ADDR_MASK GENMASK(14, 0) +#define LRN_SCAN_NEXT_CFG_1_SCAN_ENTRY_ADDR_MASK_SET(x)\ + FIELD_PREP(LRN_SCAN_NEXT_CFG_1_SCAN_ENTRY_ADDR_MASK, x) +#define LRN_SCAN_NEXT_CFG_1_SCAN_ENTRY_ADDR_MASK_GET(x)\ + FIELD_GET(LRN_SCAN_NEXT_CFG_1_SCAN_ENTRY_ADDR_MASK, x) + +/* LRN:COMMON:AUTOAGE_CFG */ +#define LRN_AUTOAGE_CFG(r) __REG(TARGET_LRN, 0, 1, 0, 0, 1, 72, 36, r, 4, 4) + +#define LRN_AUTOAGE_CFG_UNIT_SIZE GENMASK(29, 28) +#define LRN_AUTOAGE_CFG_UNIT_SIZE_SET(x)\ + FIELD_PREP(LRN_AUTOAGE_CFG_UNIT_SIZE, x) +#define LRN_AUTOAGE_CFG_UNIT_SIZE_GET(x)\ + FIELD_GET(LRN_AUTOAGE_CFG_UNIT_SIZE, x) + +#define LRN_AUTOAGE_CFG_PERIOD_VAL GENMASK(27, 0) +#define LRN_AUTOAGE_CFG_PERIOD_VAL_SET(x)\ + FIELD_PREP(LRN_AUTOAGE_CFG_PERIOD_VAL, x) +#define LRN_AUTOAGE_CFG_PERIOD_VAL_GET(x)\ + FIELD_GET(LRN_AUTOAGE_CFG_PERIOD_VAL, x) + +/* LRN:COMMON:AUTOAGE_CFG_1 */ +#define LRN_AUTOAGE_CFG_1 __REG(TARGET_LRN, 0, 1, 0, 0, 1, 72, 52, 0, 1, 4) + +#define LRN_AUTOAGE_CFG_1_PAUSE_AUTO_AGE_ENA BIT(25) +#define LRN_AUTOAGE_CFG_1_PAUSE_AUTO_AGE_ENA_SET(x)\ + FIELD_PREP(LRN_AUTOAGE_CFG_1_PAUSE_AUTO_AGE_ENA, x) +#define LRN_AUTOAGE_CFG_1_PAUSE_AUTO_AGE_ENA_GET(x)\ + FIELD_GET(LRN_AUTOAGE_CFG_1_PAUSE_AUTO_AGE_ENA, x) + +#define LRN_AUTOAGE_CFG_1_CELLS_BETWEEN_ENTRY_SCAN GENMASK(24, 15) +#define LRN_AUTOAGE_CFG_1_CELLS_BETWEEN_ENTRY_SCAN_SET(x)\ + FIELD_PREP(LRN_AUTOAGE_CFG_1_CELLS_BETWEEN_ENTRY_SCAN, x) +#define LRN_AUTOAGE_CFG_1_CELLS_BETWEEN_ENTRY_SCAN_GET(x)\ + FIELD_GET(LRN_AUTOAGE_CFG_1_CELLS_BETWEEN_ENTRY_SCAN, x) + +#define LRN_AUTOAGE_CFG_1_CLK_PERIOD_01NS GENMASK(14, 7) +#define LRN_AUTOAGE_CFG_1_CLK_PERIOD_01NS_SET(x)\ + FIELD_PREP(LRN_AUTOAGE_CFG_1_CLK_PERIOD_01NS, x) +#define LRN_AUTOAGE_CFG_1_CLK_PERIOD_01NS_GET(x)\ + FIELD_GET(LRN_AUTOAGE_CFG_1_CLK_PERIOD_01NS, x) + +#define LRN_AUTOAGE_CFG_1_USE_PORT_FILTER_ENA BIT(6) +#define LRN_AUTOAGE_CFG_1_USE_PORT_FILTER_ENA_SET(x)\ + FIELD_PREP(LRN_AUTOAGE_CFG_1_USE_PORT_FILTER_ENA, x) +#define LRN_AUTOAGE_CFG_1_USE_PORT_FILTER_ENA_GET(x)\ + FIELD_GET(LRN_AUTOAGE_CFG_1_USE_PORT_FILTER_ENA, x) + +#define LRN_AUTOAGE_CFG_1_FORCE_HW_SCAN_SHOT GENMASK(5, 2) +#define LRN_AUTOAGE_CFG_1_FORCE_HW_SCAN_SHOT_SET(x)\ + FIELD_PREP(LRN_AUTOAGE_CFG_1_FORCE_HW_SCAN_SHOT, x) +#define LRN_AUTOAGE_CFG_1_FORCE_HW_SCAN_SHOT_GET(x)\ + FIELD_GET(LRN_AUTOAGE_CFG_1_FORCE_HW_SCAN_SHOT, x) + +#define LRN_AUTOAGE_CFG_1_FORCE_HW_SCAN_STOP_SHOT BIT(1) +#define LRN_AUTOAGE_CFG_1_FORCE_HW_SCAN_STOP_SHOT_SET(x)\ + FIELD_PREP(LRN_AUTOAGE_CFG_1_FORCE_HW_SCAN_STOP_SHOT, x) +#define LRN_AUTOAGE_CFG_1_FORCE_HW_SCAN_STOP_SHOT_GET(x)\ + FIELD_GET(LRN_AUTOAGE_CFG_1_FORCE_HW_SCAN_STOP_SHOT, x) + +#define LRN_AUTOAGE_CFG_1_FORCE_IDLE_ENA BIT(0) +#define LRN_AUTOAGE_CFG_1_FORCE_IDLE_ENA_SET(x)\ + FIELD_PREP(LRN_AUTOAGE_CFG_1_FORCE_IDLE_ENA, x) +#define LRN_AUTOAGE_CFG_1_FORCE_IDLE_ENA_GET(x)\ + FIELD_GET(LRN_AUTOAGE_CFG_1_FORCE_IDLE_ENA, x) + +/* LRN:COMMON:AUTOAGE_CFG_2 */ +#define LRN_AUTOAGE_CFG_2 __REG(TARGET_LRN, 0, 1, 0, 0, 1, 72, 56, 0, 1, 4) + +#define LRN_AUTOAGE_CFG_2_NEXT_ROW GENMASK(17, 4) +#define LRN_AUTOAGE_CFG_2_NEXT_ROW_SET(x)\ + FIELD_PREP(LRN_AUTOAGE_CFG_2_NEXT_ROW, x) +#define LRN_AUTOAGE_CFG_2_NEXT_ROW_GET(x)\ + FIELD_GET(LRN_AUTOAGE_CFG_2_NEXT_ROW, x) + +#define LRN_AUTOAGE_CFG_2_SCAN_ONGOING_STATUS GENMASK(3, 0) +#define LRN_AUTOAGE_CFG_2_SCAN_ONGOING_STATUS_SET(x)\ + FIELD_PREP(LRN_AUTOAGE_CFG_2_SCAN_ONGOING_STATUS, x) +#define LRN_AUTOAGE_CFG_2_SCAN_ONGOING_STATUS_GET(x)\ + FIELD_GET(LRN_AUTOAGE_CFG_2_SCAN_ONGOING_STATUS, x) + +/* PCIE_DM_EP:PF0_ATU_CAP:IATU_REGION_CTRL_2_OFF_OUTBOUND_0 */ +#define PCEP_RCTRL_2_OUT_0 __REG(TARGET_PCEP, 0, 1, 3145728, 0, 1, 130852, 4, 0, 1, 4) + +#define PCEP_RCTRL_2_OUT_0_MSG_CODE GENMASK(7, 0) +#define PCEP_RCTRL_2_OUT_0_MSG_CODE_SET(x)\ + FIELD_PREP(PCEP_RCTRL_2_OUT_0_MSG_CODE, x) +#define PCEP_RCTRL_2_OUT_0_MSG_CODE_GET(x)\ + FIELD_GET(PCEP_RCTRL_2_OUT_0_MSG_CODE, x) + +#define PCEP_RCTRL_2_OUT_0_TAG GENMASK(15, 8) +#define PCEP_RCTRL_2_OUT_0_TAG_SET(x)\ + FIELD_PREP(PCEP_RCTRL_2_OUT_0_TAG, x) +#define PCEP_RCTRL_2_OUT_0_TAG_GET(x)\ + FIELD_GET(PCEP_RCTRL_2_OUT_0_TAG, x) + +#define PCEP_RCTRL_2_OUT_0_TAG_SUBSTITUTE_EN BIT(16) +#define PCEP_RCTRL_2_OUT_0_TAG_SUBSTITUTE_EN_SET(x)\ + FIELD_PREP(PCEP_RCTRL_2_OUT_0_TAG_SUBSTITUTE_EN, x) +#define PCEP_RCTRL_2_OUT_0_TAG_SUBSTITUTE_EN_GET(x)\ + FIELD_GET(PCEP_RCTRL_2_OUT_0_TAG_SUBSTITUTE_EN, x) + +#define PCEP_RCTRL_2_OUT_0_FUNC_BYPASS BIT(19) +#define PCEP_RCTRL_2_OUT_0_FUNC_BYPASS_SET(x)\ + FIELD_PREP(PCEP_RCTRL_2_OUT_0_FUNC_BYPASS, x) +#define PCEP_RCTRL_2_OUT_0_FUNC_BYPASS_GET(x)\ + FIELD_GET(PCEP_RCTRL_2_OUT_0_FUNC_BYPASS, x) + +#define PCEP_RCTRL_2_OUT_0_SNP BIT(20) +#define PCEP_RCTRL_2_OUT_0_SNP_SET(x)\ + FIELD_PREP(PCEP_RCTRL_2_OUT_0_SNP, x) +#define PCEP_RCTRL_2_OUT_0_SNP_GET(x)\ + FIELD_GET(PCEP_RCTRL_2_OUT_0_SNP, x) + +#define PCEP_RCTRL_2_OUT_0_INHIBIT_PAYLOAD BIT(22) +#define PCEP_RCTRL_2_OUT_0_INHIBIT_PAYLOAD_SET(x)\ + FIELD_PREP(PCEP_RCTRL_2_OUT_0_INHIBIT_PAYLOAD, x) +#define PCEP_RCTRL_2_OUT_0_INHIBIT_PAYLOAD_GET(x)\ + FIELD_GET(PCEP_RCTRL_2_OUT_0_INHIBIT_PAYLOAD, x) + +#define PCEP_RCTRL_2_OUT_0_HEADER_SUBSTITUTE_EN BIT(23) +#define PCEP_RCTRL_2_OUT_0_HEADER_SUBSTITUTE_EN_SET(x)\ + FIELD_PREP(PCEP_RCTRL_2_OUT_0_HEADER_SUBSTITUTE_EN, x) +#define PCEP_RCTRL_2_OUT_0_HEADER_SUBSTITUTE_EN_GET(x)\ + FIELD_GET(PCEP_RCTRL_2_OUT_0_HEADER_SUBSTITUTE_EN, x) + +#define PCEP_RCTRL_2_OUT_0_CFG_SHIFT_MODE BIT(28) +#define PCEP_RCTRL_2_OUT_0_CFG_SHIFT_MODE_SET(x)\ + FIELD_PREP(PCEP_RCTRL_2_OUT_0_CFG_SHIFT_MODE, x) +#define PCEP_RCTRL_2_OUT_0_CFG_SHIFT_MODE_GET(x)\ + FIELD_GET(PCEP_RCTRL_2_OUT_0_CFG_SHIFT_MODE, x) + +#define PCEP_RCTRL_2_OUT_0_INVERT_MODE BIT(29) +#define PCEP_RCTRL_2_OUT_0_INVERT_MODE_SET(x)\ + FIELD_PREP(PCEP_RCTRL_2_OUT_0_INVERT_MODE, x) +#define PCEP_RCTRL_2_OUT_0_INVERT_MODE_GET(x)\ + FIELD_GET(PCEP_RCTRL_2_OUT_0_INVERT_MODE, x) + +#define PCEP_RCTRL_2_OUT_0_REGION_EN BIT(31) +#define PCEP_RCTRL_2_OUT_0_REGION_EN_SET(x)\ + FIELD_PREP(PCEP_RCTRL_2_OUT_0_REGION_EN, x) +#define PCEP_RCTRL_2_OUT_0_REGION_EN_GET(x)\ + FIELD_GET(PCEP_RCTRL_2_OUT_0_REGION_EN, x) + +/* PCIE_DM_EP:PF0_ATU_CAP:IATU_LWR_BASE_ADDR_OFF_OUTBOUND_0 */ +#define PCEP_ADDR_LWR_OUT_0 __REG(TARGET_PCEP, 0, 1, 3145728, 0, 1, 130852, 8, 0, 1, 4) + +#define PCEP_ADDR_LWR_OUT_0_LWR_BASE_HW GENMASK(15, 0) +#define PCEP_ADDR_LWR_OUT_0_LWR_BASE_HW_SET(x)\ + FIELD_PREP(PCEP_ADDR_LWR_OUT_0_LWR_BASE_HW, x) +#define PCEP_ADDR_LWR_OUT_0_LWR_BASE_HW_GET(x)\ + FIELD_GET(PCEP_ADDR_LWR_OUT_0_LWR_BASE_HW, x) + +#define PCEP_ADDR_LWR_OUT_0_LWR_BASE_RW GENMASK(31, 16) +#define PCEP_ADDR_LWR_OUT_0_LWR_BASE_RW_SET(x)\ + FIELD_PREP(PCEP_ADDR_LWR_OUT_0_LWR_BASE_RW, x) +#define PCEP_ADDR_LWR_OUT_0_LWR_BASE_RW_GET(x)\ + FIELD_GET(PCEP_ADDR_LWR_OUT_0_LWR_BASE_RW, x) + +/* PCIE_DM_EP:PF0_ATU_CAP:IATU_UPPER_BASE_ADDR_OFF_OUTBOUND_0 */ +#define PCEP_ADDR_UPR_OUT_0 __REG(TARGET_PCEP, 0, 1, 3145728, 0, 1, 130852, 12, 0, 1, 4) + +/* PCIE_DM_EP:PF0_ATU_CAP:IATU_LIMIT_ADDR_OFF_OUTBOUND_0 */ +#define PCEP_ADDR_LIM_OUT_0 __REG(TARGET_PCEP, 0, 1, 3145728, 0, 1, 130852, 16, 0, 1, 4) + +#define PCEP_ADDR_LIM_OUT_0_LIMIT_ADDR_HW GENMASK(15, 0) +#define PCEP_ADDR_LIM_OUT_0_LIMIT_ADDR_HW_SET(x)\ + FIELD_PREP(PCEP_ADDR_LIM_OUT_0_LIMIT_ADDR_HW, x) +#define PCEP_ADDR_LIM_OUT_0_LIMIT_ADDR_HW_GET(x)\ + FIELD_GET(PCEP_ADDR_LIM_OUT_0_LIMIT_ADDR_HW, x) + +#define PCEP_ADDR_LIM_OUT_0_LIMIT_ADDR_RW GENMASK(31, 16) +#define PCEP_ADDR_LIM_OUT_0_LIMIT_ADDR_RW_SET(x)\ + FIELD_PREP(PCEP_ADDR_LIM_OUT_0_LIMIT_ADDR_RW, x) +#define PCEP_ADDR_LIM_OUT_0_LIMIT_ADDR_RW_GET(x)\ + FIELD_GET(PCEP_ADDR_LIM_OUT_0_LIMIT_ADDR_RW, x) + +/* PCIE_DM_EP:PF0_ATU_CAP:IATU_LWR_TARGET_ADDR_OFF_OUTBOUND_0 */ +#define PCEP_ADDR_LWR_TGT_OUT_0 __REG(TARGET_PCEP, 0, 1, 3145728, 0, 1, 130852, 20, 0, 1, 4) + +/* PCIE_DM_EP:PF0_ATU_CAP:IATU_UPPER_TARGET_ADDR_OFF_OUTBOUND_0 */ +#define PCEP_ADDR_UPR_TGT_OUT_0 __REG(TARGET_PCEP, 0, 1, 3145728, 0, 1, 130852, 24, 0, 1, 4) + +/* PCIE_DM_EP:PF0_ATU_CAP:IATU_UPPR_LIMIT_ADDR_OFF_OUTBOUND_0 */ +#define PCEP_ADDR_UPR_LIM_OUT_0 __REG(TARGET_PCEP, 0, 1, 3145728, 0, 1, 130852, 32, 0, 1, 4) + +#define PCEP_ADDR_UPR_LIM_OUT_0_UPPR_LIMIT_ADDR_RW GENMASK(1, 0) +#define PCEP_ADDR_UPR_LIM_OUT_0_UPPR_LIMIT_ADDR_RW_SET(x)\ + FIELD_PREP(PCEP_ADDR_UPR_LIM_OUT_0_UPPR_LIMIT_ADDR_RW, x) +#define PCEP_ADDR_UPR_LIM_OUT_0_UPPR_LIMIT_ADDR_RW_GET(x)\ + FIELD_GET(PCEP_ADDR_UPR_LIM_OUT_0_UPPR_LIMIT_ADDR_RW, x) + +#define PCEP_ADDR_UPR_LIM_OUT_0_UPPR_LIMIT_ADDR_HW GENMASK(31, 2) +#define PCEP_ADDR_UPR_LIM_OUT_0_UPPR_LIMIT_ADDR_HW_SET(x)\ + FIELD_PREP(PCEP_ADDR_UPR_LIM_OUT_0_UPPR_LIMIT_ADDR_HW, x) +#define PCEP_ADDR_UPR_LIM_OUT_0_UPPR_LIMIT_ADDR_HW_GET(x)\ + FIELD_GET(PCEP_ADDR_UPR_LIM_OUT_0_UPPR_LIMIT_ADDR_HW, x) + +/* PCS_10GBASE_R:PCS_10GBR_CFG:PCS_CFG */ +#define PCS10G_BR_PCS_CFG(t) __REG(TARGET_PCS10G_BR, t, 12, 0, 0, 1, 56, 0, 0, 1, 4) + +#define PCS10G_BR_PCS_CFG_PCS_ENA BIT(31) +#define PCS10G_BR_PCS_CFG_PCS_ENA_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_CFG_PCS_ENA, x) +#define PCS10G_BR_PCS_CFG_PCS_ENA_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_CFG_PCS_ENA, x) + +#define PCS10G_BR_PCS_CFG_PMA_LOOPBACK_ENA BIT(30) +#define PCS10G_BR_PCS_CFG_PMA_LOOPBACK_ENA_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_CFG_PMA_LOOPBACK_ENA, x) +#define PCS10G_BR_PCS_CFG_PMA_LOOPBACK_ENA_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_CFG_PMA_LOOPBACK_ENA, x) + +#define PCS10G_BR_PCS_CFG_SH_CNT_MAX GENMASK(29, 24) +#define PCS10G_BR_PCS_CFG_SH_CNT_MAX_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_CFG_SH_CNT_MAX, x) +#define PCS10G_BR_PCS_CFG_SH_CNT_MAX_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_CFG_SH_CNT_MAX, x) + +#define PCS10G_BR_PCS_CFG_RX_DATA_FLIP BIT(18) +#define PCS10G_BR_PCS_CFG_RX_DATA_FLIP_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_CFG_RX_DATA_FLIP, x) +#define PCS10G_BR_PCS_CFG_RX_DATA_FLIP_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_CFG_RX_DATA_FLIP, x) + +#define PCS10G_BR_PCS_CFG_RESYNC_ENA BIT(15) +#define PCS10G_BR_PCS_CFG_RESYNC_ENA_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_CFG_RESYNC_ENA, x) +#define PCS10G_BR_PCS_CFG_RESYNC_ENA_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_CFG_RESYNC_ENA, x) + +#define PCS10G_BR_PCS_CFG_LF_GEN_DIS BIT(14) +#define PCS10G_BR_PCS_CFG_LF_GEN_DIS_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_CFG_LF_GEN_DIS, x) +#define PCS10G_BR_PCS_CFG_LF_GEN_DIS_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_CFG_LF_GEN_DIS, x) + +#define PCS10G_BR_PCS_CFG_RX_TEST_MODE BIT(13) +#define PCS10G_BR_PCS_CFG_RX_TEST_MODE_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_CFG_RX_TEST_MODE, x) +#define PCS10G_BR_PCS_CFG_RX_TEST_MODE_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_CFG_RX_TEST_MODE, x) + +#define PCS10G_BR_PCS_CFG_RX_SCR_DISABLE BIT(12) +#define PCS10G_BR_PCS_CFG_RX_SCR_DISABLE_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_CFG_RX_SCR_DISABLE, x) +#define PCS10G_BR_PCS_CFG_RX_SCR_DISABLE_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_CFG_RX_SCR_DISABLE, x) + +#define PCS10G_BR_PCS_CFG_TX_DATA_FLIP BIT(7) +#define PCS10G_BR_PCS_CFG_TX_DATA_FLIP_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_CFG_TX_DATA_FLIP, x) +#define PCS10G_BR_PCS_CFG_TX_DATA_FLIP_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_CFG_TX_DATA_FLIP, x) + +#define PCS10G_BR_PCS_CFG_AN_LINK_CTRL_ENA BIT(6) +#define PCS10G_BR_PCS_CFG_AN_LINK_CTRL_ENA_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_CFG_AN_LINK_CTRL_ENA, x) +#define PCS10G_BR_PCS_CFG_AN_LINK_CTRL_ENA_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_CFG_AN_LINK_CTRL_ENA, x) + +#define PCS10G_BR_PCS_CFG_TX_TEST_MODE BIT(4) +#define PCS10G_BR_PCS_CFG_TX_TEST_MODE_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_CFG_TX_TEST_MODE, x) +#define PCS10G_BR_PCS_CFG_TX_TEST_MODE_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_CFG_TX_TEST_MODE, x) + +#define PCS10G_BR_PCS_CFG_TX_SCR_DISABLE BIT(3) +#define PCS10G_BR_PCS_CFG_TX_SCR_DISABLE_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_CFG_TX_SCR_DISABLE, x) +#define PCS10G_BR_PCS_CFG_TX_SCR_DISABLE_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_CFG_TX_SCR_DISABLE, x) + +/* PCS_10GBASE_R:PCS_10GBR_CFG:PCS_SD_CFG */ +#define PCS10G_BR_PCS_SD_CFG(t) __REG(TARGET_PCS10G_BR, t, 12, 0, 0, 1, 56, 4, 0, 1, 4) + +#define PCS10G_BR_PCS_SD_CFG_SD_SEL BIT(8) +#define PCS10G_BR_PCS_SD_CFG_SD_SEL_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_SD_CFG_SD_SEL, x) +#define PCS10G_BR_PCS_SD_CFG_SD_SEL_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_SD_CFG_SD_SEL, x) + +#define PCS10G_BR_PCS_SD_CFG_SD_POL BIT(4) +#define PCS10G_BR_PCS_SD_CFG_SD_POL_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_SD_CFG_SD_POL, x) +#define PCS10G_BR_PCS_SD_CFG_SD_POL_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_SD_CFG_SD_POL, x) + +#define PCS10G_BR_PCS_SD_CFG_SD_ENA BIT(0) +#define PCS10G_BR_PCS_SD_CFG_SD_ENA_SET(x)\ + FIELD_PREP(PCS10G_BR_PCS_SD_CFG_SD_ENA, x) +#define PCS10G_BR_PCS_SD_CFG_SD_ENA_GET(x)\ + FIELD_GET(PCS10G_BR_PCS_SD_CFG_SD_ENA, x) + +/* PCS_10GBASE_R:PCS_10GBR_CFG:PCS_CFG */ +#define PCS25G_BR_PCS_CFG(t) __REG(TARGET_PCS25G_BR, t, 8, 0, 0, 1, 56, 0, 0, 1, 4) + +#define PCS25G_BR_PCS_CFG_PCS_ENA BIT(31) +#define PCS25G_BR_PCS_CFG_PCS_ENA_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_CFG_PCS_ENA, x) +#define PCS25G_BR_PCS_CFG_PCS_ENA_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_CFG_PCS_ENA, x) + +#define PCS25G_BR_PCS_CFG_PMA_LOOPBACK_ENA BIT(30) +#define PCS25G_BR_PCS_CFG_PMA_LOOPBACK_ENA_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_CFG_PMA_LOOPBACK_ENA, x) +#define PCS25G_BR_PCS_CFG_PMA_LOOPBACK_ENA_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_CFG_PMA_LOOPBACK_ENA, x) + +#define PCS25G_BR_PCS_CFG_SH_CNT_MAX GENMASK(29, 24) +#define PCS25G_BR_PCS_CFG_SH_CNT_MAX_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_CFG_SH_CNT_MAX, x) +#define PCS25G_BR_PCS_CFG_SH_CNT_MAX_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_CFG_SH_CNT_MAX, x) + +#define PCS25G_BR_PCS_CFG_RX_DATA_FLIP BIT(18) +#define PCS25G_BR_PCS_CFG_RX_DATA_FLIP_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_CFG_RX_DATA_FLIP, x) +#define PCS25G_BR_PCS_CFG_RX_DATA_FLIP_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_CFG_RX_DATA_FLIP, x) + +#define PCS25G_BR_PCS_CFG_RESYNC_ENA BIT(15) +#define PCS25G_BR_PCS_CFG_RESYNC_ENA_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_CFG_RESYNC_ENA, x) +#define PCS25G_BR_PCS_CFG_RESYNC_ENA_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_CFG_RESYNC_ENA, x) + +#define PCS25G_BR_PCS_CFG_LF_GEN_DIS BIT(14) +#define PCS25G_BR_PCS_CFG_LF_GEN_DIS_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_CFG_LF_GEN_DIS, x) +#define PCS25G_BR_PCS_CFG_LF_GEN_DIS_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_CFG_LF_GEN_DIS, x) + +#define PCS25G_BR_PCS_CFG_RX_TEST_MODE BIT(13) +#define PCS25G_BR_PCS_CFG_RX_TEST_MODE_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_CFG_RX_TEST_MODE, x) +#define PCS25G_BR_PCS_CFG_RX_TEST_MODE_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_CFG_RX_TEST_MODE, x) + +#define PCS25G_BR_PCS_CFG_RX_SCR_DISABLE BIT(12) +#define PCS25G_BR_PCS_CFG_RX_SCR_DISABLE_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_CFG_RX_SCR_DISABLE, x) +#define PCS25G_BR_PCS_CFG_RX_SCR_DISABLE_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_CFG_RX_SCR_DISABLE, x) + +#define PCS25G_BR_PCS_CFG_TX_DATA_FLIP BIT(7) +#define PCS25G_BR_PCS_CFG_TX_DATA_FLIP_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_CFG_TX_DATA_FLIP, x) +#define PCS25G_BR_PCS_CFG_TX_DATA_FLIP_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_CFG_TX_DATA_FLIP, x) + +#define PCS25G_BR_PCS_CFG_AN_LINK_CTRL_ENA BIT(6) +#define PCS25G_BR_PCS_CFG_AN_LINK_CTRL_ENA_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_CFG_AN_LINK_CTRL_ENA, x) +#define PCS25G_BR_PCS_CFG_AN_LINK_CTRL_ENA_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_CFG_AN_LINK_CTRL_ENA, x) + +#define PCS25G_BR_PCS_CFG_TX_TEST_MODE BIT(4) +#define PCS25G_BR_PCS_CFG_TX_TEST_MODE_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_CFG_TX_TEST_MODE, x) +#define PCS25G_BR_PCS_CFG_TX_TEST_MODE_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_CFG_TX_TEST_MODE, x) + +#define PCS25G_BR_PCS_CFG_TX_SCR_DISABLE BIT(3) +#define PCS25G_BR_PCS_CFG_TX_SCR_DISABLE_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_CFG_TX_SCR_DISABLE, x) +#define PCS25G_BR_PCS_CFG_TX_SCR_DISABLE_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_CFG_TX_SCR_DISABLE, x) + +/* PCS_10GBASE_R:PCS_10GBR_CFG:PCS_SD_CFG */ +#define PCS25G_BR_PCS_SD_CFG(t) __REG(TARGET_PCS25G_BR, t, 8, 0, 0, 1, 56, 4, 0, 1, 4) + +#define PCS25G_BR_PCS_SD_CFG_SD_SEL BIT(8) +#define PCS25G_BR_PCS_SD_CFG_SD_SEL_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_SD_CFG_SD_SEL, x) +#define PCS25G_BR_PCS_SD_CFG_SD_SEL_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_SD_CFG_SD_SEL, x) + +#define PCS25G_BR_PCS_SD_CFG_SD_POL BIT(4) +#define PCS25G_BR_PCS_SD_CFG_SD_POL_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_SD_CFG_SD_POL, x) +#define PCS25G_BR_PCS_SD_CFG_SD_POL_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_SD_CFG_SD_POL, x) + +#define PCS25G_BR_PCS_SD_CFG_SD_ENA BIT(0) +#define PCS25G_BR_PCS_SD_CFG_SD_ENA_SET(x)\ + FIELD_PREP(PCS25G_BR_PCS_SD_CFG_SD_ENA, x) +#define PCS25G_BR_PCS_SD_CFG_SD_ENA_GET(x)\ + FIELD_GET(PCS25G_BR_PCS_SD_CFG_SD_ENA, x) + +/* PCS_10GBASE_R:PCS_10GBR_CFG:PCS_CFG */ +#define PCS5G_BR_PCS_CFG(t) __REG(TARGET_PCS5G_BR, t, 13, 0, 0, 1, 56, 0, 0, 1, 4) + +#define PCS5G_BR_PCS_CFG_PCS_ENA BIT(31) +#define PCS5G_BR_PCS_CFG_PCS_ENA_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_CFG_PCS_ENA, x) +#define PCS5G_BR_PCS_CFG_PCS_ENA_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_CFG_PCS_ENA, x) + +#define PCS5G_BR_PCS_CFG_PMA_LOOPBACK_ENA BIT(30) +#define PCS5G_BR_PCS_CFG_PMA_LOOPBACK_ENA_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_CFG_PMA_LOOPBACK_ENA, x) +#define PCS5G_BR_PCS_CFG_PMA_LOOPBACK_ENA_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_CFG_PMA_LOOPBACK_ENA, x) + +#define PCS5G_BR_PCS_CFG_SH_CNT_MAX GENMASK(29, 24) +#define PCS5G_BR_PCS_CFG_SH_CNT_MAX_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_CFG_SH_CNT_MAX, x) +#define PCS5G_BR_PCS_CFG_SH_CNT_MAX_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_CFG_SH_CNT_MAX, x) + +#define PCS5G_BR_PCS_CFG_RX_DATA_FLIP BIT(18) +#define PCS5G_BR_PCS_CFG_RX_DATA_FLIP_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_CFG_RX_DATA_FLIP, x) +#define PCS5G_BR_PCS_CFG_RX_DATA_FLIP_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_CFG_RX_DATA_FLIP, x) + +#define PCS5G_BR_PCS_CFG_RESYNC_ENA BIT(15) +#define PCS5G_BR_PCS_CFG_RESYNC_ENA_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_CFG_RESYNC_ENA, x) +#define PCS5G_BR_PCS_CFG_RESYNC_ENA_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_CFG_RESYNC_ENA, x) + +#define PCS5G_BR_PCS_CFG_LF_GEN_DIS BIT(14) +#define PCS5G_BR_PCS_CFG_LF_GEN_DIS_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_CFG_LF_GEN_DIS, x) +#define PCS5G_BR_PCS_CFG_LF_GEN_DIS_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_CFG_LF_GEN_DIS, x) + +#define PCS5G_BR_PCS_CFG_RX_TEST_MODE BIT(13) +#define PCS5G_BR_PCS_CFG_RX_TEST_MODE_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_CFG_RX_TEST_MODE, x) +#define PCS5G_BR_PCS_CFG_RX_TEST_MODE_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_CFG_RX_TEST_MODE, x) + +#define PCS5G_BR_PCS_CFG_RX_SCR_DISABLE BIT(12) +#define PCS5G_BR_PCS_CFG_RX_SCR_DISABLE_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_CFG_RX_SCR_DISABLE, x) +#define PCS5G_BR_PCS_CFG_RX_SCR_DISABLE_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_CFG_RX_SCR_DISABLE, x) + +#define PCS5G_BR_PCS_CFG_TX_DATA_FLIP BIT(7) +#define PCS5G_BR_PCS_CFG_TX_DATA_FLIP_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_CFG_TX_DATA_FLIP, x) +#define PCS5G_BR_PCS_CFG_TX_DATA_FLIP_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_CFG_TX_DATA_FLIP, x) + +#define PCS5G_BR_PCS_CFG_AN_LINK_CTRL_ENA BIT(6) +#define PCS5G_BR_PCS_CFG_AN_LINK_CTRL_ENA_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_CFG_AN_LINK_CTRL_ENA, x) +#define PCS5G_BR_PCS_CFG_AN_LINK_CTRL_ENA_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_CFG_AN_LINK_CTRL_ENA, x) + +#define PCS5G_BR_PCS_CFG_TX_TEST_MODE BIT(4) +#define PCS5G_BR_PCS_CFG_TX_TEST_MODE_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_CFG_TX_TEST_MODE, x) +#define PCS5G_BR_PCS_CFG_TX_TEST_MODE_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_CFG_TX_TEST_MODE, x) + +#define PCS5G_BR_PCS_CFG_TX_SCR_DISABLE BIT(3) +#define PCS5G_BR_PCS_CFG_TX_SCR_DISABLE_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_CFG_TX_SCR_DISABLE, x) +#define PCS5G_BR_PCS_CFG_TX_SCR_DISABLE_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_CFG_TX_SCR_DISABLE, x) + +/* PCS_10GBASE_R:PCS_10GBR_CFG:PCS_SD_CFG */ +#define PCS5G_BR_PCS_SD_CFG(t) __REG(TARGET_PCS5G_BR, t, 13, 0, 0, 1, 56, 4, 0, 1, 4) + +#define PCS5G_BR_PCS_SD_CFG_SD_SEL BIT(8) +#define PCS5G_BR_PCS_SD_CFG_SD_SEL_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_SD_CFG_SD_SEL, x) +#define PCS5G_BR_PCS_SD_CFG_SD_SEL_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_SD_CFG_SD_SEL, x) + +#define PCS5G_BR_PCS_SD_CFG_SD_POL BIT(4) +#define PCS5G_BR_PCS_SD_CFG_SD_POL_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_SD_CFG_SD_POL, x) +#define PCS5G_BR_PCS_SD_CFG_SD_POL_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_SD_CFG_SD_POL, x) + +#define PCS5G_BR_PCS_SD_CFG_SD_ENA BIT(0) +#define PCS5G_BR_PCS_SD_CFG_SD_ENA_SET(x)\ + FIELD_PREP(PCS5G_BR_PCS_SD_CFG_SD_ENA, x) +#define PCS5G_BR_PCS_SD_CFG_SD_ENA_GET(x)\ + FIELD_GET(PCS5G_BR_PCS_SD_CFG_SD_ENA, x) + +/* PORT_CONF:HW_CFG:DEV5G_MODES */ +#define PORT_CONF_DEV5G_MODES __REG(TARGET_PORT_CONF, 0, 1, 0, 0, 1, 24, 0, 0, 1, 4) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D0_MODE BIT(0) +#define PORT_CONF_DEV5G_MODES_DEV5G_D0_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D0_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D0_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D0_MODE, x) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D1_MODE BIT(1) +#define PORT_CONF_DEV5G_MODES_DEV5G_D1_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D1_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D1_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D1_MODE, x) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D2_MODE BIT(2) +#define PORT_CONF_DEV5G_MODES_DEV5G_D2_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D2_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D2_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D2_MODE, x) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D3_MODE BIT(3) +#define PORT_CONF_DEV5G_MODES_DEV5G_D3_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D3_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D3_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D3_MODE, x) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D4_MODE BIT(4) +#define PORT_CONF_DEV5G_MODES_DEV5G_D4_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D4_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D4_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D4_MODE, x) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D5_MODE BIT(5) +#define PORT_CONF_DEV5G_MODES_DEV5G_D5_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D5_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D5_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D5_MODE, x) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D6_MODE BIT(6) +#define PORT_CONF_DEV5G_MODES_DEV5G_D6_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D6_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D6_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D6_MODE, x) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D7_MODE BIT(7) +#define PORT_CONF_DEV5G_MODES_DEV5G_D7_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D7_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D7_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D7_MODE, x) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D8_MODE BIT(8) +#define PORT_CONF_DEV5G_MODES_DEV5G_D8_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D8_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D8_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D8_MODE, x) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D9_MODE BIT(9) +#define PORT_CONF_DEV5G_MODES_DEV5G_D9_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D9_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D9_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D9_MODE, x) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D10_MODE BIT(10) +#define PORT_CONF_DEV5G_MODES_DEV5G_D10_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D10_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D10_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D10_MODE, x) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D11_MODE BIT(11) +#define PORT_CONF_DEV5G_MODES_DEV5G_D11_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D11_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D11_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D11_MODE, x) + +#define PORT_CONF_DEV5G_MODES_DEV5G_D64_MODE BIT(12) +#define PORT_CONF_DEV5G_MODES_DEV5G_D64_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV5G_MODES_DEV5G_D64_MODE, x) +#define PORT_CONF_DEV5G_MODES_DEV5G_D64_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV5G_MODES_DEV5G_D64_MODE, x) + +/* PORT_CONF:HW_CFG:DEV10G_MODES */ +#define PORT_CONF_DEV10G_MODES __REG(TARGET_PORT_CONF, 0, 1, 0, 0, 1, 24, 4, 0, 1, 4) + +#define PORT_CONF_DEV10G_MODES_DEV10G_D12_MODE BIT(0) +#define PORT_CONF_DEV10G_MODES_DEV10G_D12_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV10G_MODES_DEV10G_D12_MODE, x) +#define PORT_CONF_DEV10G_MODES_DEV10G_D12_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV10G_MODES_DEV10G_D12_MODE, x) + +#define PORT_CONF_DEV10G_MODES_DEV10G_D13_MODE BIT(1) +#define PORT_CONF_DEV10G_MODES_DEV10G_D13_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV10G_MODES_DEV10G_D13_MODE, x) +#define PORT_CONF_DEV10G_MODES_DEV10G_D13_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV10G_MODES_DEV10G_D13_MODE, x) + +#define PORT_CONF_DEV10G_MODES_DEV10G_D14_MODE BIT(2) +#define PORT_CONF_DEV10G_MODES_DEV10G_D14_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV10G_MODES_DEV10G_D14_MODE, x) +#define PORT_CONF_DEV10G_MODES_DEV10G_D14_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV10G_MODES_DEV10G_D14_MODE, x) + +#define PORT_CONF_DEV10G_MODES_DEV10G_D15_MODE BIT(3) +#define PORT_CONF_DEV10G_MODES_DEV10G_D15_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV10G_MODES_DEV10G_D15_MODE, x) +#define PORT_CONF_DEV10G_MODES_DEV10G_D15_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV10G_MODES_DEV10G_D15_MODE, x) + +#define PORT_CONF_DEV10G_MODES_DEV10G_D48_MODE BIT(4) +#define PORT_CONF_DEV10G_MODES_DEV10G_D48_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV10G_MODES_DEV10G_D48_MODE, x) +#define PORT_CONF_DEV10G_MODES_DEV10G_D48_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV10G_MODES_DEV10G_D48_MODE, x) + +#define PORT_CONF_DEV10G_MODES_DEV10G_D49_MODE BIT(5) +#define PORT_CONF_DEV10G_MODES_DEV10G_D49_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV10G_MODES_DEV10G_D49_MODE, x) +#define PORT_CONF_DEV10G_MODES_DEV10G_D49_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV10G_MODES_DEV10G_D49_MODE, x) + +#define PORT_CONF_DEV10G_MODES_DEV10G_D50_MODE BIT(6) +#define PORT_CONF_DEV10G_MODES_DEV10G_D50_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV10G_MODES_DEV10G_D50_MODE, x) +#define PORT_CONF_DEV10G_MODES_DEV10G_D50_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV10G_MODES_DEV10G_D50_MODE, x) + +#define PORT_CONF_DEV10G_MODES_DEV10G_D51_MODE BIT(7) +#define PORT_CONF_DEV10G_MODES_DEV10G_D51_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV10G_MODES_DEV10G_D51_MODE, x) +#define PORT_CONF_DEV10G_MODES_DEV10G_D51_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV10G_MODES_DEV10G_D51_MODE, x) + +#define PORT_CONF_DEV10G_MODES_DEV10G_D52_MODE BIT(8) +#define PORT_CONF_DEV10G_MODES_DEV10G_D52_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV10G_MODES_DEV10G_D52_MODE, x) +#define PORT_CONF_DEV10G_MODES_DEV10G_D52_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV10G_MODES_DEV10G_D52_MODE, x) + +#define PORT_CONF_DEV10G_MODES_DEV10G_D53_MODE BIT(9) +#define PORT_CONF_DEV10G_MODES_DEV10G_D53_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV10G_MODES_DEV10G_D53_MODE, x) +#define PORT_CONF_DEV10G_MODES_DEV10G_D53_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV10G_MODES_DEV10G_D53_MODE, x) + +#define PORT_CONF_DEV10G_MODES_DEV10G_D54_MODE BIT(10) +#define PORT_CONF_DEV10G_MODES_DEV10G_D54_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV10G_MODES_DEV10G_D54_MODE, x) +#define PORT_CONF_DEV10G_MODES_DEV10G_D54_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV10G_MODES_DEV10G_D54_MODE, x) + +#define PORT_CONF_DEV10G_MODES_DEV10G_D55_MODE BIT(11) +#define PORT_CONF_DEV10G_MODES_DEV10G_D55_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV10G_MODES_DEV10G_D55_MODE, x) +#define PORT_CONF_DEV10G_MODES_DEV10G_D55_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV10G_MODES_DEV10G_D55_MODE, x) + +/* PORT_CONF:HW_CFG:DEV25G_MODES */ +#define PORT_CONF_DEV25G_MODES __REG(TARGET_PORT_CONF, 0, 1, 0, 0, 1, 24, 8, 0, 1, 4) + +#define PORT_CONF_DEV25G_MODES_DEV25G_D56_MODE BIT(0) +#define PORT_CONF_DEV25G_MODES_DEV25G_D56_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV25G_MODES_DEV25G_D56_MODE, x) +#define PORT_CONF_DEV25G_MODES_DEV25G_D56_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV25G_MODES_DEV25G_D56_MODE, x) + +#define PORT_CONF_DEV25G_MODES_DEV25G_D57_MODE BIT(1) +#define PORT_CONF_DEV25G_MODES_DEV25G_D57_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV25G_MODES_DEV25G_D57_MODE, x) +#define PORT_CONF_DEV25G_MODES_DEV25G_D57_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV25G_MODES_DEV25G_D57_MODE, x) + +#define PORT_CONF_DEV25G_MODES_DEV25G_D58_MODE BIT(2) +#define PORT_CONF_DEV25G_MODES_DEV25G_D58_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV25G_MODES_DEV25G_D58_MODE, x) +#define PORT_CONF_DEV25G_MODES_DEV25G_D58_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV25G_MODES_DEV25G_D58_MODE, x) + +#define PORT_CONF_DEV25G_MODES_DEV25G_D59_MODE BIT(3) +#define PORT_CONF_DEV25G_MODES_DEV25G_D59_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV25G_MODES_DEV25G_D59_MODE, x) +#define PORT_CONF_DEV25G_MODES_DEV25G_D59_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV25G_MODES_DEV25G_D59_MODE, x) + +#define PORT_CONF_DEV25G_MODES_DEV25G_D60_MODE BIT(4) +#define PORT_CONF_DEV25G_MODES_DEV25G_D60_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV25G_MODES_DEV25G_D60_MODE, x) +#define PORT_CONF_DEV25G_MODES_DEV25G_D60_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV25G_MODES_DEV25G_D60_MODE, x) + +#define PORT_CONF_DEV25G_MODES_DEV25G_D61_MODE BIT(5) +#define PORT_CONF_DEV25G_MODES_DEV25G_D61_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV25G_MODES_DEV25G_D61_MODE, x) +#define PORT_CONF_DEV25G_MODES_DEV25G_D61_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV25G_MODES_DEV25G_D61_MODE, x) + +#define PORT_CONF_DEV25G_MODES_DEV25G_D62_MODE BIT(6) +#define PORT_CONF_DEV25G_MODES_DEV25G_D62_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV25G_MODES_DEV25G_D62_MODE, x) +#define PORT_CONF_DEV25G_MODES_DEV25G_D62_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV25G_MODES_DEV25G_D62_MODE, x) + +#define PORT_CONF_DEV25G_MODES_DEV25G_D63_MODE BIT(7) +#define PORT_CONF_DEV25G_MODES_DEV25G_D63_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_DEV25G_MODES_DEV25G_D63_MODE, x) +#define PORT_CONF_DEV25G_MODES_DEV25G_D63_MODE_GET(x)\ + FIELD_GET(PORT_CONF_DEV25G_MODES_DEV25G_D63_MODE, x) + +/* PORT_CONF:HW_CFG:QSGMII_ENA */ +#define PORT_CONF_QSGMII_ENA __REG(TARGET_PORT_CONF, 0, 1, 0, 0, 1, 24, 12, 0, 1, 4) + +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_0 BIT(0) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_0_SET(x)\ + FIELD_PREP(PORT_CONF_QSGMII_ENA_QSGMII_ENA_0, x) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_0_GET(x)\ + FIELD_GET(PORT_CONF_QSGMII_ENA_QSGMII_ENA_0, x) + +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_1 BIT(1) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_1_SET(x)\ + FIELD_PREP(PORT_CONF_QSGMII_ENA_QSGMII_ENA_1, x) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_1_GET(x)\ + FIELD_GET(PORT_CONF_QSGMII_ENA_QSGMII_ENA_1, x) + +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_2 BIT(2) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_2_SET(x)\ + FIELD_PREP(PORT_CONF_QSGMII_ENA_QSGMII_ENA_2, x) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_2_GET(x)\ + FIELD_GET(PORT_CONF_QSGMII_ENA_QSGMII_ENA_2, x) + +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_3 BIT(3) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_3_SET(x)\ + FIELD_PREP(PORT_CONF_QSGMII_ENA_QSGMII_ENA_3, x) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_3_GET(x)\ + FIELD_GET(PORT_CONF_QSGMII_ENA_QSGMII_ENA_3, x) + +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_4 BIT(4) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_4_SET(x)\ + FIELD_PREP(PORT_CONF_QSGMII_ENA_QSGMII_ENA_4, x) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_4_GET(x)\ + FIELD_GET(PORT_CONF_QSGMII_ENA_QSGMII_ENA_4, x) + +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_5 BIT(5) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_5_SET(x)\ + FIELD_PREP(PORT_CONF_QSGMII_ENA_QSGMII_ENA_5, x) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_5_GET(x)\ + FIELD_GET(PORT_CONF_QSGMII_ENA_QSGMII_ENA_5, x) + +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_6 BIT(6) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_6_SET(x)\ + FIELD_PREP(PORT_CONF_QSGMII_ENA_QSGMII_ENA_6, x) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_6_GET(x)\ + FIELD_GET(PORT_CONF_QSGMII_ENA_QSGMII_ENA_6, x) + +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_7 BIT(7) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_7_SET(x)\ + FIELD_PREP(PORT_CONF_QSGMII_ENA_QSGMII_ENA_7, x) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_7_GET(x)\ + FIELD_GET(PORT_CONF_QSGMII_ENA_QSGMII_ENA_7, x) + +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_8 BIT(8) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_8_SET(x)\ + FIELD_PREP(PORT_CONF_QSGMII_ENA_QSGMII_ENA_8, x) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_8_GET(x)\ + FIELD_GET(PORT_CONF_QSGMII_ENA_QSGMII_ENA_8, x) + +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_9 BIT(9) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_9_SET(x)\ + FIELD_PREP(PORT_CONF_QSGMII_ENA_QSGMII_ENA_9, x) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_9_GET(x)\ + FIELD_GET(PORT_CONF_QSGMII_ENA_QSGMII_ENA_9, x) + +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_10 BIT(10) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_10_SET(x)\ + FIELD_PREP(PORT_CONF_QSGMII_ENA_QSGMII_ENA_10, x) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_10_GET(x)\ + FIELD_GET(PORT_CONF_QSGMII_ENA_QSGMII_ENA_10, x) + +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_11 BIT(11) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_11_SET(x)\ + FIELD_PREP(PORT_CONF_QSGMII_ENA_QSGMII_ENA_11, x) +#define PORT_CONF_QSGMII_ENA_QSGMII_ENA_11_GET(x)\ + FIELD_GET(PORT_CONF_QSGMII_ENA_QSGMII_ENA_11, x) + +/* PORT_CONF:USGMII_CFG_STAT:USGMII_CFG */ +#define PORT_CONF_USGMII_CFG(g) __REG(TARGET_PORT_CONF, 0, 1, 72, g, 6, 8, 0, 0, 1, 4) + +#define PORT_CONF_USGMII_CFG_BYPASS_SCRAM BIT(9) +#define PORT_CONF_USGMII_CFG_BYPASS_SCRAM_SET(x)\ + FIELD_PREP(PORT_CONF_USGMII_CFG_BYPASS_SCRAM, x) +#define PORT_CONF_USGMII_CFG_BYPASS_SCRAM_GET(x)\ + FIELD_GET(PORT_CONF_USGMII_CFG_BYPASS_SCRAM, x) + +#define PORT_CONF_USGMII_CFG_BYPASS_DESCRAM BIT(8) +#define PORT_CONF_USGMII_CFG_BYPASS_DESCRAM_SET(x)\ + FIELD_PREP(PORT_CONF_USGMII_CFG_BYPASS_DESCRAM, x) +#define PORT_CONF_USGMII_CFG_BYPASS_DESCRAM_GET(x)\ + FIELD_GET(PORT_CONF_USGMII_CFG_BYPASS_DESCRAM, x) + +#define PORT_CONF_USGMII_CFG_FLIP_LANES BIT(7) +#define PORT_CONF_USGMII_CFG_FLIP_LANES_SET(x)\ + FIELD_PREP(PORT_CONF_USGMII_CFG_FLIP_LANES, x) +#define PORT_CONF_USGMII_CFG_FLIP_LANES_GET(x)\ + FIELD_GET(PORT_CONF_USGMII_CFG_FLIP_LANES, x) + +#define PORT_CONF_USGMII_CFG_SHYST_DIS BIT(6) +#define PORT_CONF_USGMII_CFG_SHYST_DIS_SET(x)\ + FIELD_PREP(PORT_CONF_USGMII_CFG_SHYST_DIS, x) +#define PORT_CONF_USGMII_CFG_SHYST_DIS_GET(x)\ + FIELD_GET(PORT_CONF_USGMII_CFG_SHYST_DIS, x) + +#define PORT_CONF_USGMII_CFG_E_DET_ENA BIT(5) +#define PORT_CONF_USGMII_CFG_E_DET_ENA_SET(x)\ + FIELD_PREP(PORT_CONF_USGMII_CFG_E_DET_ENA, x) +#define PORT_CONF_USGMII_CFG_E_DET_ENA_GET(x)\ + FIELD_GET(PORT_CONF_USGMII_CFG_E_DET_ENA, x) + +#define PORT_CONF_USGMII_CFG_USE_I1_ENA BIT(4) +#define PORT_CONF_USGMII_CFG_USE_I1_ENA_SET(x)\ + FIELD_PREP(PORT_CONF_USGMII_CFG_USE_I1_ENA, x) +#define PORT_CONF_USGMII_CFG_USE_I1_ENA_GET(x)\ + FIELD_GET(PORT_CONF_USGMII_CFG_USE_I1_ENA, x) + +#define PORT_CONF_USGMII_CFG_QUAD_MODE BIT(1) +#define PORT_CONF_USGMII_CFG_QUAD_MODE_SET(x)\ + FIELD_PREP(PORT_CONF_USGMII_CFG_QUAD_MODE, x) +#define PORT_CONF_USGMII_CFG_QUAD_MODE_GET(x)\ + FIELD_GET(PORT_CONF_USGMII_CFG_QUAD_MODE, x) + +/* QFWD:SYSTEM:SWITCH_PORT_MODE */ +#define QFWD_SWITCH_PORT_MODE(r) __REG(TARGET_QFWD, 0, 1, 0, 0, 1, 340, 0, r, 70, 4) + +#define QFWD_SWITCH_PORT_MODE_PORT_ENA BIT(19) +#define QFWD_SWITCH_PORT_MODE_PORT_ENA_SET(x)\ + FIELD_PREP(QFWD_SWITCH_PORT_MODE_PORT_ENA, x) +#define QFWD_SWITCH_PORT_MODE_PORT_ENA_GET(x)\ + FIELD_GET(QFWD_SWITCH_PORT_MODE_PORT_ENA, x) + +#define QFWD_SWITCH_PORT_MODE_FWD_URGENCY GENMASK(18, 10) +#define QFWD_SWITCH_PORT_MODE_FWD_URGENCY_SET(x)\ + FIELD_PREP(QFWD_SWITCH_PORT_MODE_FWD_URGENCY, x) +#define QFWD_SWITCH_PORT_MODE_FWD_URGENCY_GET(x)\ + FIELD_GET(QFWD_SWITCH_PORT_MODE_FWD_URGENCY, x) + +#define QFWD_SWITCH_PORT_MODE_YEL_RSRVD GENMASK(9, 6) +#define QFWD_SWITCH_PORT_MODE_YEL_RSRVD_SET(x)\ + FIELD_PREP(QFWD_SWITCH_PORT_MODE_YEL_RSRVD, x) +#define QFWD_SWITCH_PORT_MODE_YEL_RSRVD_GET(x)\ + FIELD_GET(QFWD_SWITCH_PORT_MODE_YEL_RSRVD, x) + +#define QFWD_SWITCH_PORT_MODE_INGRESS_DROP_MODE BIT(5) +#define QFWD_SWITCH_PORT_MODE_INGRESS_DROP_MODE_SET(x)\ + FIELD_PREP(QFWD_SWITCH_PORT_MODE_INGRESS_DROP_MODE, x) +#define QFWD_SWITCH_PORT_MODE_INGRESS_DROP_MODE_GET(x)\ + FIELD_GET(QFWD_SWITCH_PORT_MODE_INGRESS_DROP_MODE, x) + +#define QFWD_SWITCH_PORT_MODE_IGR_NO_SHARING BIT(4) +#define QFWD_SWITCH_PORT_MODE_IGR_NO_SHARING_SET(x)\ + FIELD_PREP(QFWD_SWITCH_PORT_MODE_IGR_NO_SHARING, x) +#define QFWD_SWITCH_PORT_MODE_IGR_NO_SHARING_GET(x)\ + FIELD_GET(QFWD_SWITCH_PORT_MODE_IGR_NO_SHARING, x) + +#define QFWD_SWITCH_PORT_MODE_EGR_NO_SHARING BIT(3) +#define QFWD_SWITCH_PORT_MODE_EGR_NO_SHARING_SET(x)\ + FIELD_PREP(QFWD_SWITCH_PORT_MODE_EGR_NO_SHARING, x) +#define QFWD_SWITCH_PORT_MODE_EGR_NO_SHARING_GET(x)\ + FIELD_GET(QFWD_SWITCH_PORT_MODE_EGR_NO_SHARING, x) + +#define QFWD_SWITCH_PORT_MODE_EGRESS_DROP_MODE BIT(2) +#define QFWD_SWITCH_PORT_MODE_EGRESS_DROP_MODE_SET(x)\ + FIELD_PREP(QFWD_SWITCH_PORT_MODE_EGRESS_DROP_MODE, x) +#define QFWD_SWITCH_PORT_MODE_EGRESS_DROP_MODE_GET(x)\ + FIELD_GET(QFWD_SWITCH_PORT_MODE_EGRESS_DROP_MODE, x) + +#define QFWD_SWITCH_PORT_MODE_EGRESS_RSRV_DIS BIT(1) +#define QFWD_SWITCH_PORT_MODE_EGRESS_RSRV_DIS_SET(x)\ + FIELD_PREP(QFWD_SWITCH_PORT_MODE_EGRESS_RSRV_DIS, x) +#define QFWD_SWITCH_PORT_MODE_EGRESS_RSRV_DIS_GET(x)\ + FIELD_GET(QFWD_SWITCH_PORT_MODE_EGRESS_RSRV_DIS, x) + +#define QFWD_SWITCH_PORT_MODE_LEARNALL_MORE BIT(0) +#define QFWD_SWITCH_PORT_MODE_LEARNALL_MORE_SET(x)\ + FIELD_PREP(QFWD_SWITCH_PORT_MODE_LEARNALL_MORE, x) +#define QFWD_SWITCH_PORT_MODE_LEARNALL_MORE_GET(x)\ + FIELD_GET(QFWD_SWITCH_PORT_MODE_LEARNALL_MORE, x) + +/* QRES:RES_CTRL:RES_CFG */ +#define QRES_RES_CFG(g) __REG(TARGET_QRES, 0, 1, 0, g, 5120, 16, 0, 0, 1, 4) + +#define QRES_RES_CFG_WM_HIGH GENMASK(11, 0) +#define QRES_RES_CFG_WM_HIGH_SET(x)\ + FIELD_PREP(QRES_RES_CFG_WM_HIGH, x) +#define QRES_RES_CFG_WM_HIGH_GET(x)\ + FIELD_GET(QRES_RES_CFG_WM_HIGH, x) + +/* QRES:RES_CTRL:RES_STAT */ +#define QRES_RES_STAT(g) __REG(TARGET_QRES, 0, 1, 0, g, 5120, 16, 4, 0, 1, 4) + +#define QRES_RES_STAT_MAXUSE GENMASK(20, 0) +#define QRES_RES_STAT_MAXUSE_SET(x)\ + FIELD_PREP(QRES_RES_STAT_MAXUSE, x) +#define QRES_RES_STAT_MAXUSE_GET(x)\ + FIELD_GET(QRES_RES_STAT_MAXUSE, x) + +/* QRES:RES_CTRL:RES_STAT_CUR */ +#define QRES_RES_STAT_CUR(g) __REG(TARGET_QRES, 0, 1, 0, g, 5120, 16, 8, 0, 1, 4) + +#define QRES_RES_STAT_CUR_INUSE GENMASK(20, 0) +#define QRES_RES_STAT_CUR_INUSE_SET(x)\ + FIELD_PREP(QRES_RES_STAT_CUR_INUSE, x) +#define QRES_RES_STAT_CUR_INUSE_GET(x)\ + FIELD_GET(QRES_RES_STAT_CUR_INUSE, x) + +/* DEVCPU_QS:XTR:XTR_GRP_CFG */ +#define QS_XTR_GRP_CFG(r) __REG(TARGET_QS, 0, 1, 0, 0, 1, 36, 0, r, 2, 4) + +#define QS_XTR_GRP_CFG_MODE GENMASK(3, 2) +#define QS_XTR_GRP_CFG_MODE_SET(x)\ + FIELD_PREP(QS_XTR_GRP_CFG_MODE, x) +#define QS_XTR_GRP_CFG_MODE_GET(x)\ + FIELD_GET(QS_XTR_GRP_CFG_MODE, x) + +#define QS_XTR_GRP_CFG_STATUS_WORD_POS BIT(1) +#define QS_XTR_GRP_CFG_STATUS_WORD_POS_SET(x)\ + FIELD_PREP(QS_XTR_GRP_CFG_STATUS_WORD_POS, x) +#define QS_XTR_GRP_CFG_STATUS_WORD_POS_GET(x)\ + FIELD_GET(QS_XTR_GRP_CFG_STATUS_WORD_POS, x) + +#define QS_XTR_GRP_CFG_BYTE_SWAP BIT(0) +#define QS_XTR_GRP_CFG_BYTE_SWAP_SET(x)\ + FIELD_PREP(QS_XTR_GRP_CFG_BYTE_SWAP, x) +#define QS_XTR_GRP_CFG_BYTE_SWAP_GET(x)\ + FIELD_GET(QS_XTR_GRP_CFG_BYTE_SWAP, x) + +/* DEVCPU_QS:XTR:XTR_RD */ +#define QS_XTR_RD(r) __REG(TARGET_QS, 0, 1, 0, 0, 1, 36, 8, r, 2, 4) + +/* DEVCPU_QS:XTR:XTR_FLUSH */ +#define QS_XTR_FLUSH __REG(TARGET_QS, 0, 1, 0, 0, 1, 36, 24, 0, 1, 4) + +#define QS_XTR_FLUSH_FLUSH GENMASK(1, 0) +#define QS_XTR_FLUSH_FLUSH_SET(x)\ + FIELD_PREP(QS_XTR_FLUSH_FLUSH, x) +#define QS_XTR_FLUSH_FLUSH_GET(x)\ + FIELD_GET(QS_XTR_FLUSH_FLUSH, x) + +/* DEVCPU_QS:XTR:XTR_DATA_PRESENT */ +#define QS_XTR_DATA_PRESENT __REG(TARGET_QS, 0, 1, 0, 0, 1, 36, 28, 0, 1, 4) + +#define QS_XTR_DATA_PRESENT_DATA_PRESENT GENMASK(1, 0) +#define QS_XTR_DATA_PRESENT_DATA_PRESENT_SET(x)\ + FIELD_PREP(QS_XTR_DATA_PRESENT_DATA_PRESENT, x) +#define QS_XTR_DATA_PRESENT_DATA_PRESENT_GET(x)\ + FIELD_GET(QS_XTR_DATA_PRESENT_DATA_PRESENT, x) + +/* DEVCPU_QS:INJ:INJ_GRP_CFG */ +#define QS_INJ_GRP_CFG(r) __REG(TARGET_QS, 0, 1, 36, 0, 1, 40, 0, r, 2, 4) + +#define QS_INJ_GRP_CFG_MODE GENMASK(3, 2) +#define QS_INJ_GRP_CFG_MODE_SET(x)\ + FIELD_PREP(QS_INJ_GRP_CFG_MODE, x) +#define QS_INJ_GRP_CFG_MODE_GET(x)\ + FIELD_GET(QS_INJ_GRP_CFG_MODE, x) + +#define QS_INJ_GRP_CFG_BYTE_SWAP BIT(0) +#define QS_INJ_GRP_CFG_BYTE_SWAP_SET(x)\ + FIELD_PREP(QS_INJ_GRP_CFG_BYTE_SWAP, x) +#define QS_INJ_GRP_CFG_BYTE_SWAP_GET(x)\ + FIELD_GET(QS_INJ_GRP_CFG_BYTE_SWAP, x) + +/* DEVCPU_QS:INJ:INJ_WR */ +#define QS_INJ_WR(r) __REG(TARGET_QS, 0, 1, 36, 0, 1, 40, 8, r, 2, 4) + +/* DEVCPU_QS:INJ:INJ_CTRL */ +#define QS_INJ_CTRL(r) __REG(TARGET_QS, 0, 1, 36, 0, 1, 40, 16, r, 2, 4) + +#define QS_INJ_CTRL_GAP_SIZE GENMASK(24, 21) +#define QS_INJ_CTRL_GAP_SIZE_SET(x)\ + FIELD_PREP(QS_INJ_CTRL_GAP_SIZE, x) +#define QS_INJ_CTRL_GAP_SIZE_GET(x)\ + FIELD_GET(QS_INJ_CTRL_GAP_SIZE, x) + +#define QS_INJ_CTRL_ABORT BIT(20) +#define QS_INJ_CTRL_ABORT_SET(x)\ + FIELD_PREP(QS_INJ_CTRL_ABORT, x) +#define QS_INJ_CTRL_ABORT_GET(x)\ + FIELD_GET(QS_INJ_CTRL_ABORT, x) + +#define QS_INJ_CTRL_EOF BIT(19) +#define QS_INJ_CTRL_EOF_SET(x)\ + FIELD_PREP(QS_INJ_CTRL_EOF, x) +#define QS_INJ_CTRL_EOF_GET(x)\ + FIELD_GET(QS_INJ_CTRL_EOF, x) + +#define QS_INJ_CTRL_SOF BIT(18) +#define QS_INJ_CTRL_SOF_SET(x)\ + FIELD_PREP(QS_INJ_CTRL_SOF, x) +#define QS_INJ_CTRL_SOF_GET(x)\ + FIELD_GET(QS_INJ_CTRL_SOF, x) + +#define QS_INJ_CTRL_VLD_BYTES GENMASK(17, 16) +#define QS_INJ_CTRL_VLD_BYTES_SET(x)\ + FIELD_PREP(QS_INJ_CTRL_VLD_BYTES, x) +#define QS_INJ_CTRL_VLD_BYTES_GET(x)\ + FIELD_GET(QS_INJ_CTRL_VLD_BYTES, x) + +/* DEVCPU_QS:INJ:INJ_STATUS */ +#define QS_INJ_STATUS __REG(TARGET_QS, 0, 1, 36, 0, 1, 40, 24, 0, 1, 4) + +#define QS_INJ_STATUS_WMARK_REACHED GENMASK(5, 4) +#define QS_INJ_STATUS_WMARK_REACHED_SET(x)\ + FIELD_PREP(QS_INJ_STATUS_WMARK_REACHED, x) +#define QS_INJ_STATUS_WMARK_REACHED_GET(x)\ + FIELD_GET(QS_INJ_STATUS_WMARK_REACHED, x) + +#define QS_INJ_STATUS_FIFO_RDY GENMASK(3, 2) +#define QS_INJ_STATUS_FIFO_RDY_SET(x)\ + FIELD_PREP(QS_INJ_STATUS_FIFO_RDY, x) +#define QS_INJ_STATUS_FIFO_RDY_GET(x)\ + FIELD_GET(QS_INJ_STATUS_FIFO_RDY, x) + +#define QS_INJ_STATUS_INJ_IN_PROGRESS GENMASK(1, 0) +#define QS_INJ_STATUS_INJ_IN_PROGRESS_SET(x)\ + FIELD_PREP(QS_INJ_STATUS_INJ_IN_PROGRESS, x) +#define QS_INJ_STATUS_INJ_IN_PROGRESS_GET(x)\ + FIELD_GET(QS_INJ_STATUS_INJ_IN_PROGRESS, x) + +/* QSYS:PAUSE_CFG:PAUSE_CFG */ +#define QSYS_PAUSE_CFG(r) __REG(TARGET_QSYS, 0, 1, 544, 0, 1, 1128, 0, r, 70, 4) + +#define QSYS_PAUSE_CFG_PAUSE_START GENMASK(25, 14) +#define QSYS_PAUSE_CFG_PAUSE_START_SET(x)\ + FIELD_PREP(QSYS_PAUSE_CFG_PAUSE_START, x) +#define QSYS_PAUSE_CFG_PAUSE_START_GET(x)\ + FIELD_GET(QSYS_PAUSE_CFG_PAUSE_START, x) + +#define QSYS_PAUSE_CFG_PAUSE_STOP GENMASK(13, 2) +#define QSYS_PAUSE_CFG_PAUSE_STOP_SET(x)\ + FIELD_PREP(QSYS_PAUSE_CFG_PAUSE_STOP, x) +#define QSYS_PAUSE_CFG_PAUSE_STOP_GET(x)\ + FIELD_GET(QSYS_PAUSE_CFG_PAUSE_STOP, x) + +#define QSYS_PAUSE_CFG_PAUSE_ENA BIT(1) +#define QSYS_PAUSE_CFG_PAUSE_ENA_SET(x)\ + FIELD_PREP(QSYS_PAUSE_CFG_PAUSE_ENA, x) +#define QSYS_PAUSE_CFG_PAUSE_ENA_GET(x)\ + FIELD_GET(QSYS_PAUSE_CFG_PAUSE_ENA, x) + +#define QSYS_PAUSE_CFG_AGGRESSIVE_TAILDROP_ENA BIT(0) +#define QSYS_PAUSE_CFG_AGGRESSIVE_TAILDROP_ENA_SET(x)\ + FIELD_PREP(QSYS_PAUSE_CFG_AGGRESSIVE_TAILDROP_ENA, x) +#define QSYS_PAUSE_CFG_AGGRESSIVE_TAILDROP_ENA_GET(x)\ + FIELD_GET(QSYS_PAUSE_CFG_AGGRESSIVE_TAILDROP_ENA, x) + +/* QSYS:PAUSE_CFG:ATOP */ +#define QSYS_ATOP(r) __REG(TARGET_QSYS, 0, 1, 544, 0, 1, 1128, 284, r, 70, 4) + +#define QSYS_ATOP_ATOP GENMASK(11, 0) +#define QSYS_ATOP_ATOP_SET(x)\ + FIELD_PREP(QSYS_ATOP_ATOP, x) +#define QSYS_ATOP_ATOP_GET(x)\ + FIELD_GET(QSYS_ATOP_ATOP, x) + +/* QSYS:PAUSE_CFG:FWD_PRESSURE */ +#define QSYS_FWD_PRESSURE(r) __REG(TARGET_QSYS, 0, 1, 544, 0, 1, 1128, 564, r, 70, 4) + +#define QSYS_FWD_PRESSURE_FWD_PRESSURE GENMASK(11, 1) +#define QSYS_FWD_PRESSURE_FWD_PRESSURE_SET(x)\ + FIELD_PREP(QSYS_FWD_PRESSURE_FWD_PRESSURE, x) +#define QSYS_FWD_PRESSURE_FWD_PRESSURE_GET(x)\ + FIELD_GET(QSYS_FWD_PRESSURE_FWD_PRESSURE, x) + +#define QSYS_FWD_PRESSURE_FWD_PRESSURE_DIS BIT(0) +#define QSYS_FWD_PRESSURE_FWD_PRESSURE_DIS_SET(x)\ + FIELD_PREP(QSYS_FWD_PRESSURE_FWD_PRESSURE_DIS, x) +#define QSYS_FWD_PRESSURE_FWD_PRESSURE_DIS_GET(x)\ + FIELD_GET(QSYS_FWD_PRESSURE_FWD_PRESSURE_DIS, x) + +/* QSYS:PAUSE_CFG:ATOP_TOT_CFG */ +#define QSYS_ATOP_TOT_CFG __REG(TARGET_QSYS, 0, 1, 544, 0, 1, 1128, 844, 0, 1, 4) + +#define QSYS_ATOP_TOT_CFG_ATOP_TOT GENMASK(11, 0) +#define QSYS_ATOP_TOT_CFG_ATOP_TOT_SET(x)\ + FIELD_PREP(QSYS_ATOP_TOT_CFG_ATOP_TOT, x) +#define QSYS_ATOP_TOT_CFG_ATOP_TOT_GET(x)\ + FIELD_GET(QSYS_ATOP_TOT_CFG_ATOP_TOT, x) + +/* QSYS:CALCFG:CAL_AUTO */ +#define QSYS_CAL_AUTO(r) __REG(TARGET_QSYS, 0, 1, 2304, 0, 1, 40, 0, r, 7, 4) + +#define QSYS_CAL_AUTO_CAL_AUTO GENMASK(29, 0) +#define QSYS_CAL_AUTO_CAL_AUTO_SET(x)\ + FIELD_PREP(QSYS_CAL_AUTO_CAL_AUTO, x) +#define QSYS_CAL_AUTO_CAL_AUTO_GET(x)\ + FIELD_GET(QSYS_CAL_AUTO_CAL_AUTO, x) + +/* QSYS:CALCFG:CAL_CTRL */ +#define QSYS_CAL_CTRL __REG(TARGET_QSYS, 0, 1, 2304, 0, 1, 40, 36, 0, 1, 4) + +#define QSYS_CAL_CTRL_CAL_MODE GENMASK(14, 11) +#define QSYS_CAL_CTRL_CAL_MODE_SET(x)\ + FIELD_PREP(QSYS_CAL_CTRL_CAL_MODE, x) +#define QSYS_CAL_CTRL_CAL_MODE_GET(x)\ + FIELD_GET(QSYS_CAL_CTRL_CAL_MODE, x) + +#define QSYS_CAL_CTRL_CAL_AUTO_GRANT_RATE GENMASK(10, 1) +#define QSYS_CAL_CTRL_CAL_AUTO_GRANT_RATE_SET(x)\ + FIELD_PREP(QSYS_CAL_CTRL_CAL_AUTO_GRANT_RATE, x) +#define QSYS_CAL_CTRL_CAL_AUTO_GRANT_RATE_GET(x)\ + FIELD_GET(QSYS_CAL_CTRL_CAL_AUTO_GRANT_RATE, x) + +#define QSYS_CAL_CTRL_CAL_AUTO_ERROR BIT(0) +#define QSYS_CAL_CTRL_CAL_AUTO_ERROR_SET(x)\ + FIELD_PREP(QSYS_CAL_CTRL_CAL_AUTO_ERROR, x) +#define QSYS_CAL_CTRL_CAL_AUTO_ERROR_GET(x)\ + FIELD_GET(QSYS_CAL_CTRL_CAL_AUTO_ERROR, x) + +/* QSYS:RAM_CTRL:RAM_INIT */ +#define QSYS_RAM_INIT __REG(TARGET_QSYS, 0, 1, 2344, 0, 1, 4, 0, 0, 1, 4) + +#define QSYS_RAM_INIT_RAM_INIT BIT(1) +#define QSYS_RAM_INIT_RAM_INIT_SET(x)\ + FIELD_PREP(QSYS_RAM_INIT_RAM_INIT, x) +#define QSYS_RAM_INIT_RAM_INIT_GET(x)\ + FIELD_GET(QSYS_RAM_INIT_RAM_INIT, x) + +#define QSYS_RAM_INIT_RAM_CFG_HOOK BIT(0) +#define QSYS_RAM_INIT_RAM_CFG_HOOK_SET(x)\ + FIELD_PREP(QSYS_RAM_INIT_RAM_CFG_HOOK, x) +#define QSYS_RAM_INIT_RAM_CFG_HOOK_GET(x)\ + FIELD_GET(QSYS_RAM_INIT_RAM_CFG_HOOK, x) + +/* REW:COMMON:OWN_UPSID */ +#define REW_OWN_UPSID(r) __REG(TARGET_REW, 0, 1, 387264, 0, 1, 1232, 0, r, 3, 4) + +#define REW_OWN_UPSID_OWN_UPSID GENMASK(4, 0) +#define REW_OWN_UPSID_OWN_UPSID_SET(x)\ + FIELD_PREP(REW_OWN_UPSID_OWN_UPSID, x) +#define REW_OWN_UPSID_OWN_UPSID_GET(x)\ + FIELD_GET(REW_OWN_UPSID_OWN_UPSID, x) + +/* REW:PORT:PORT_VLAN_CFG */ +#define REW_PORT_VLAN_CFG(g) __REG(TARGET_REW, 0, 1, 360448, g, 70, 256, 0, 0, 1, 4) + +#define REW_PORT_VLAN_CFG_PORT_PCP GENMASK(15, 13) +#define REW_PORT_VLAN_CFG_PORT_PCP_SET(x)\ + FIELD_PREP(REW_PORT_VLAN_CFG_PORT_PCP, x) +#define REW_PORT_VLAN_CFG_PORT_PCP_GET(x)\ + FIELD_GET(REW_PORT_VLAN_CFG_PORT_PCP, x) + +#define REW_PORT_VLAN_CFG_PORT_DEI BIT(12) +#define REW_PORT_VLAN_CFG_PORT_DEI_SET(x)\ + FIELD_PREP(REW_PORT_VLAN_CFG_PORT_DEI, x) +#define REW_PORT_VLAN_CFG_PORT_DEI_GET(x)\ + FIELD_GET(REW_PORT_VLAN_CFG_PORT_DEI, x) + +#define REW_PORT_VLAN_CFG_PORT_VID GENMASK(11, 0) +#define REW_PORT_VLAN_CFG_PORT_VID_SET(x)\ + FIELD_PREP(REW_PORT_VLAN_CFG_PORT_VID, x) +#define REW_PORT_VLAN_CFG_PORT_VID_GET(x)\ + FIELD_GET(REW_PORT_VLAN_CFG_PORT_VID, x) + +/* REW:PORT:TAG_CTRL */ +#define REW_TAG_CTRL(g) __REG(TARGET_REW, 0, 1, 360448, g, 70, 256, 132, 0, 1, 4) + +#define REW_TAG_CTRL_TAG_CFG_OBEY_WAS_TAGGED BIT(13) +#define REW_TAG_CTRL_TAG_CFG_OBEY_WAS_TAGGED_SET(x)\ + FIELD_PREP(REW_TAG_CTRL_TAG_CFG_OBEY_WAS_TAGGED, x) +#define REW_TAG_CTRL_TAG_CFG_OBEY_WAS_TAGGED_GET(x)\ + FIELD_GET(REW_TAG_CTRL_TAG_CFG_OBEY_WAS_TAGGED, x) + +#define REW_TAG_CTRL_TAG_CFG GENMASK(12, 11) +#define REW_TAG_CTRL_TAG_CFG_SET(x)\ + FIELD_PREP(REW_TAG_CTRL_TAG_CFG, x) +#define REW_TAG_CTRL_TAG_CFG_GET(x)\ + FIELD_GET(REW_TAG_CTRL_TAG_CFG, x) + +#define REW_TAG_CTRL_TAG_TPID_CFG GENMASK(10, 8) +#define REW_TAG_CTRL_TAG_TPID_CFG_SET(x)\ + FIELD_PREP(REW_TAG_CTRL_TAG_TPID_CFG, x) +#define REW_TAG_CTRL_TAG_TPID_CFG_GET(x)\ + FIELD_GET(REW_TAG_CTRL_TAG_TPID_CFG, x) + +#define REW_TAG_CTRL_TAG_VID_CFG GENMASK(7, 6) +#define REW_TAG_CTRL_TAG_VID_CFG_SET(x)\ + FIELD_PREP(REW_TAG_CTRL_TAG_VID_CFG, x) +#define REW_TAG_CTRL_TAG_VID_CFG_GET(x)\ + FIELD_GET(REW_TAG_CTRL_TAG_VID_CFG, x) + +#define REW_TAG_CTRL_TAG_PCP_CFG GENMASK(5, 3) +#define REW_TAG_CTRL_TAG_PCP_CFG_SET(x)\ + FIELD_PREP(REW_TAG_CTRL_TAG_PCP_CFG, x) +#define REW_TAG_CTRL_TAG_PCP_CFG_GET(x)\ + FIELD_GET(REW_TAG_CTRL_TAG_PCP_CFG, x) + +#define REW_TAG_CTRL_TAG_DEI_CFG GENMASK(2, 0) +#define REW_TAG_CTRL_TAG_DEI_CFG_SET(x)\ + FIELD_PREP(REW_TAG_CTRL_TAG_DEI_CFG, x) +#define REW_TAG_CTRL_TAG_DEI_CFG_GET(x)\ + FIELD_GET(REW_TAG_CTRL_TAG_DEI_CFG, x) + +/* REW:RAM_CTRL:RAM_INIT */ +#define REW_RAM_INIT __REG(TARGET_REW, 0, 1, 378696, 0, 1, 4, 0, 0, 1, 4) + +#define REW_RAM_INIT_RAM_INIT BIT(1) +#define REW_RAM_INIT_RAM_INIT_SET(x)\ + FIELD_PREP(REW_RAM_INIT_RAM_INIT, x) +#define REW_RAM_INIT_RAM_INIT_GET(x)\ + FIELD_GET(REW_RAM_INIT_RAM_INIT, x) + +#define REW_RAM_INIT_RAM_CFG_HOOK BIT(0) +#define REW_RAM_INIT_RAM_CFG_HOOK_SET(x)\ + FIELD_PREP(REW_RAM_INIT_RAM_CFG_HOOK, x) +#define REW_RAM_INIT_RAM_CFG_HOOK_GET(x)\ + FIELD_GET(REW_RAM_INIT_RAM_CFG_HOOK, x) + +/* VCAP_SUPER:RAM_CTRL:RAM_INIT */ +#define VCAP_SUPER_RAM_INIT __REG(TARGET_VCAP_SUPER, 0, 1, 1120, 0, 1, 4, 0, 0, 1, 4) + +#define VCAP_SUPER_RAM_INIT_RAM_INIT BIT(1) +#define VCAP_SUPER_RAM_INIT_RAM_INIT_SET(x)\ + FIELD_PREP(VCAP_SUPER_RAM_INIT_RAM_INIT, x) +#define VCAP_SUPER_RAM_INIT_RAM_INIT_GET(x)\ + FIELD_GET(VCAP_SUPER_RAM_INIT_RAM_INIT, x) + +#define VCAP_SUPER_RAM_INIT_RAM_CFG_HOOK BIT(0) +#define VCAP_SUPER_RAM_INIT_RAM_CFG_HOOK_SET(x)\ + FIELD_PREP(VCAP_SUPER_RAM_INIT_RAM_CFG_HOOK, x) +#define VCAP_SUPER_RAM_INIT_RAM_CFG_HOOK_GET(x)\ + FIELD_GET(VCAP_SUPER_RAM_INIT_RAM_CFG_HOOK, x) + +/* VOP:RAM_CTRL:RAM_INIT */ +#define VOP_RAM_INIT __REG(TARGET_VOP, 0, 1, 279176, 0, 1, 4, 0, 0, 1, 4) + +#define VOP_RAM_INIT_RAM_INIT BIT(1) +#define VOP_RAM_INIT_RAM_INIT_SET(x)\ + FIELD_PREP(VOP_RAM_INIT_RAM_INIT, x) +#define VOP_RAM_INIT_RAM_INIT_GET(x)\ + FIELD_GET(VOP_RAM_INIT_RAM_INIT, x) + +#define VOP_RAM_INIT_RAM_CFG_HOOK BIT(0) +#define VOP_RAM_INIT_RAM_CFG_HOOK_SET(x)\ + FIELD_PREP(VOP_RAM_INIT_RAM_CFG_HOOK, x) +#define VOP_RAM_INIT_RAM_CFG_HOOK_GET(x)\ + FIELD_GET(VOP_RAM_INIT_RAM_CFG_HOOK, x) + +/* XQS:SYSTEM:STAT_CFG */ +#define XQS_STAT_CFG __REG(TARGET_XQS, 0, 1, 6768, 0, 1, 872, 860, 0, 1, 4) + +#define XQS_STAT_CFG_STAT_CLEAR_SHOT GENMASK(21, 18) +#define XQS_STAT_CFG_STAT_CLEAR_SHOT_SET(x)\ + FIELD_PREP(XQS_STAT_CFG_STAT_CLEAR_SHOT, x) +#define XQS_STAT_CFG_STAT_CLEAR_SHOT_GET(x)\ + FIELD_GET(XQS_STAT_CFG_STAT_CLEAR_SHOT, x) + +#define XQS_STAT_CFG_STAT_VIEW GENMASK(17, 5) +#define XQS_STAT_CFG_STAT_VIEW_SET(x)\ + FIELD_PREP(XQS_STAT_CFG_STAT_VIEW, x) +#define XQS_STAT_CFG_STAT_VIEW_GET(x)\ + FIELD_GET(XQS_STAT_CFG_STAT_VIEW, x) + +#define XQS_STAT_CFG_STAT_SRV_PKT_ONLY BIT(4) +#define XQS_STAT_CFG_STAT_SRV_PKT_ONLY_SET(x)\ + FIELD_PREP(XQS_STAT_CFG_STAT_SRV_PKT_ONLY, x) +#define XQS_STAT_CFG_STAT_SRV_PKT_ONLY_GET(x)\ + FIELD_GET(XQS_STAT_CFG_STAT_SRV_PKT_ONLY, x) + +#define XQS_STAT_CFG_STAT_WRAP_DIS GENMASK(3, 0) +#define XQS_STAT_CFG_STAT_WRAP_DIS_SET(x)\ + FIELD_PREP(XQS_STAT_CFG_STAT_WRAP_DIS, x) +#define XQS_STAT_CFG_STAT_WRAP_DIS_GET(x)\ + FIELD_GET(XQS_STAT_CFG_STAT_WRAP_DIS, x) + +/* XQS:QLIMIT_SHR:QLIMIT_SHR_TOP_CFG */ +#define XQS_QLIMIT_SHR_TOP_CFG(g) __REG(TARGET_XQS, 0, 1, 7936, g, 4, 48, 0, 0, 1, 4) + +#define XQS_QLIMIT_SHR_TOP_CFG_QLIMIT_SHR_TOP GENMASK(14, 0) +#define XQS_QLIMIT_SHR_TOP_CFG_QLIMIT_SHR_TOP_SET(x)\ + FIELD_PREP(XQS_QLIMIT_SHR_TOP_CFG_QLIMIT_SHR_TOP, x) +#define XQS_QLIMIT_SHR_TOP_CFG_QLIMIT_SHR_TOP_GET(x)\ + FIELD_GET(XQS_QLIMIT_SHR_TOP_CFG_QLIMIT_SHR_TOP, x) + +/* XQS:QLIMIT_SHR:QLIMIT_SHR_ATOP_CFG */ +#define XQS_QLIMIT_SHR_ATOP_CFG(g) __REG(TARGET_XQS, 0, 1, 7936, g, 4, 48, 4, 0, 1, 4) + +#define XQS_QLIMIT_SHR_ATOP_CFG_QLIMIT_SHR_ATOP GENMASK(14, 0) +#define XQS_QLIMIT_SHR_ATOP_CFG_QLIMIT_SHR_ATOP_SET(x)\ + FIELD_PREP(XQS_QLIMIT_SHR_ATOP_CFG_QLIMIT_SHR_ATOP, x) +#define XQS_QLIMIT_SHR_ATOP_CFG_QLIMIT_SHR_ATOP_GET(x)\ + FIELD_GET(XQS_QLIMIT_SHR_ATOP_CFG_QLIMIT_SHR_ATOP, x) + +/* XQS:QLIMIT_SHR:QLIMIT_SHR_CTOP_CFG */ +#define XQS_QLIMIT_SHR_CTOP_CFG(g) __REG(TARGET_XQS, 0, 1, 7936, g, 4, 48, 8, 0, 1, 4) + +#define XQS_QLIMIT_SHR_CTOP_CFG_QLIMIT_SHR_CTOP GENMASK(14, 0) +#define XQS_QLIMIT_SHR_CTOP_CFG_QLIMIT_SHR_CTOP_SET(x)\ + FIELD_PREP(XQS_QLIMIT_SHR_CTOP_CFG_QLIMIT_SHR_CTOP, x) +#define XQS_QLIMIT_SHR_CTOP_CFG_QLIMIT_SHR_CTOP_GET(x)\ + FIELD_GET(XQS_QLIMIT_SHR_CTOP_CFG_QLIMIT_SHR_CTOP, x) + +/* XQS:QLIMIT_SHR:QLIMIT_SHR_QLIM_CFG */ +#define XQS_QLIMIT_SHR_QLIM_CFG(g) __REG(TARGET_XQS, 0, 1, 7936, g, 4, 48, 12, 0, 1, 4) + +#define XQS_QLIMIT_SHR_QLIM_CFG_QLIMIT_SHR_QLIM GENMASK(14, 0) +#define XQS_QLIMIT_SHR_QLIM_CFG_QLIMIT_SHR_QLIM_SET(x)\ + FIELD_PREP(XQS_QLIMIT_SHR_QLIM_CFG_QLIMIT_SHR_QLIM, x) +#define XQS_QLIMIT_SHR_QLIM_CFG_QLIMIT_SHR_QLIM_GET(x)\ + FIELD_GET(XQS_QLIMIT_SHR_QLIM_CFG_QLIMIT_SHR_QLIM, x) + +/* XQS:STAT:CNT */ +#define XQS_CNT(g) __REG(TARGET_XQS, 0, 1, 0, g, 1024, 4, 0, 0, 1, 4) + +#endif /* _SPARX5_MAIN_REGS_H_ */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c new file mode 100644 index 000000000000..9d485a9d1f1f --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c @@ -0,0 +1,264 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" +#include "sparx5_port.h" + +/* The IFH bit position of the first VSTAX bit. This is because the + * VSTAX bit positions in Data sheet is starting from zero. + */ +#define VSTAX 73 + +static void ifh_encode_bitfield(void *ifh, u64 value, u32 pos, u32 width) +{ + u8 *ifh_hdr = ifh; + /* Calculate the Start IFH byte position of this IFH bit position */ + u32 byte = (35 - (pos / 8)); + /* Calculate the Start bit position in the Start IFH byte */ + u32 bit = (pos % 8); + u64 encode = GENMASK(bit + width - 1, bit) & (value << bit); + + /* Max width is 5 bytes - 40 bits. In worst case this will + * spread over 6 bytes - 48 bits + */ + compiletime_assert(width <= 40, "Unsupported width, must be <= 40"); + + /* The b0-b7 goes into the start IFH byte */ + if (encode & 0xFF) + ifh_hdr[byte] |= (u8)((encode & 0xFF)); + /* The b8-b15 goes into the next IFH byte */ + if (encode & 0xFF00) + ifh_hdr[byte - 1] |= (u8)((encode & 0xFF00) >> 8); + /* The b16-b23 goes into the next IFH byte */ + if (encode & 0xFF0000) + ifh_hdr[byte - 2] |= (u8)((encode & 0xFF0000) >> 16); + /* The b24-b31 goes into the next IFH byte */ + if (encode & 0xFF000000) + ifh_hdr[byte - 3] |= (u8)((encode & 0xFF000000) >> 24); + /* The b32-b39 goes into the next IFH byte */ + if (encode & 0xFF00000000) + ifh_hdr[byte - 4] |= (u8)((encode & 0xFF00000000) >> 32); + /* The b40-b47 goes into the next IFH byte */ + if (encode & 0xFF0000000000) + ifh_hdr[byte - 5] |= (u8)((encode & 0xFF0000000000) >> 40); +} + +static void sparx5_set_port_ifh(void *ifh_hdr, u16 portno) +{ + /* VSTAX.RSV = 1. MSBit must be 1 */ + ifh_encode_bitfield(ifh_hdr, 1, VSTAX + 79, 1); + /* VSTAX.INGR_DROP_MODE = Enable. Don't make head-of-line blocking */ + ifh_encode_bitfield(ifh_hdr, 1, VSTAX + 55, 1); + /* MISC.CPU_MASK/DPORT = Destination port */ + ifh_encode_bitfield(ifh_hdr, portno, 29, 8); + /* MISC.PIPELINE_PT */ + ifh_encode_bitfield(ifh_hdr, 16, 37, 5); + /* MISC.PIPELINE_ACT */ + ifh_encode_bitfield(ifh_hdr, 1, 42, 3); + /* FWD.SRC_PORT = CPU */ + ifh_encode_bitfield(ifh_hdr, SPX5_PORT_CPU, 46, 7); + /* FWD.SFLOW_ID (disable SFlow sampling) */ + ifh_encode_bitfield(ifh_hdr, 124, 57, 7); + /* FWD.UPDATE_FCS = Enable. Enforce update of FCS. */ + ifh_encode_bitfield(ifh_hdr, 1, 67, 1); +} + +static int sparx5_port_open(struct net_device *ndev) +{ + struct sparx5_port *port = netdev_priv(ndev); + int err = 0; + + sparx5_port_enable(port, true); + err = phylink_of_phy_connect(port->phylink, port->of_node, 0); + if (err) { + netdev_err(ndev, "Could not attach to PHY\n"); + return err; + } + + phylink_start(port->phylink); + + if (!ndev->phydev) { + /* power up serdes */ + port->conf.power_down = false; + if (port->conf.serdes_reset) + err = sparx5_serdes_set(port->sparx5, port, &port->conf); + else + err = phy_power_on(port->serdes); + if (err) + netdev_err(ndev, "%s failed\n", __func__); + } + + return err; +} + +static int sparx5_port_stop(struct net_device *ndev) +{ + struct sparx5_port *port = netdev_priv(ndev); + int err = 0; + + sparx5_port_enable(port, false); + phylink_stop(port->phylink); + phylink_disconnect_phy(port->phylink); + + if (!ndev->phydev) { + /* power down serdes */ + port->conf.power_down = true; + if (port->conf.serdes_reset) + err = sparx5_serdes_set(port->sparx5, port, &port->conf); + else + err = phy_power_off(port->serdes); + if (err) + netdev_err(ndev, "%s failed\n", __func__); + } + return 0; +} + +static void sparx5_set_rx_mode(struct net_device *dev) +{ + struct sparx5_port *port = netdev_priv(dev); + struct sparx5 *sparx5 = port->sparx5; + + if (!test_bit(port->portno, sparx5->bridge_mask)) + __dev_mc_sync(dev, sparx5_mc_sync, sparx5_mc_unsync); +} + +static int sparx5_port_get_phys_port_name(struct net_device *dev, + char *buf, size_t len) +{ + struct sparx5_port *port = netdev_priv(dev); + int ret; + + ret = snprintf(buf, len, "p%d", port->portno); + if (ret >= len) + return -EINVAL; + + return 0; +} + +static int sparx5_set_mac_address(struct net_device *dev, void *p) +{ + struct sparx5_port *port = netdev_priv(dev); + struct sparx5 *sparx5 = port->sparx5; + const struct sockaddr *addr = p; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + /* Remove current */ + sparx5_mact_forget(sparx5, dev->dev_addr, port->pvid); + + /* Add new */ + sparx5_mact_learn(sparx5, PGID_CPU, addr->sa_data, port->pvid); + + /* Record the address */ + ether_addr_copy(dev->dev_addr, addr->sa_data); + + return 0; +} + +static int sparx5_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) +{ + struct sparx5_port *sparx5_port = netdev_priv(dev); + struct sparx5 *sparx5 = sparx5_port->sparx5; + + ppid->id_len = sizeof(sparx5->base_mac); + memcpy(&ppid->id, &sparx5->base_mac, ppid->id_len); + + return 0; +} + +static const struct net_device_ops sparx5_port_netdev_ops = { + .ndo_open = sparx5_port_open, + .ndo_stop = sparx5_port_stop, + .ndo_start_xmit = sparx5_port_xmit_impl, + .ndo_set_rx_mode = sparx5_set_rx_mode, + .ndo_get_phys_port_name = sparx5_port_get_phys_port_name, + .ndo_set_mac_address = sparx5_set_mac_address, + .ndo_validate_addr = eth_validate_addr, + .ndo_get_stats64 = sparx5_get_stats64, + .ndo_get_port_parent_id = sparx5_get_port_parent_id, +}; + +bool sparx5_netdevice_check(const struct net_device *dev) +{ + return dev && (dev->netdev_ops == &sparx5_port_netdev_ops); +} + +struct net_device *sparx5_create_netdev(struct sparx5 *sparx5, u32 portno) +{ + struct sparx5_port *spx5_port; + struct net_device *ndev; + u64 val; + + ndev = devm_alloc_etherdev(sparx5->dev, sizeof(struct sparx5_port)); + if (!ndev) + return ERR_PTR(-ENOMEM); + + SET_NETDEV_DEV(ndev, sparx5->dev); + spx5_port = netdev_priv(ndev); + spx5_port->ndev = ndev; + spx5_port->sparx5 = sparx5; + spx5_port->portno = portno; + sparx5_set_port_ifh(spx5_port->ifh, portno); + + ndev->netdev_ops = &sparx5_port_netdev_ops; + ndev->ethtool_ops = &sparx5_ethtool_ops; + + val = ether_addr_to_u64(sparx5->base_mac) + portno + 1; + u64_to_ether_addr(val, ndev->dev_addr); + + return ndev; +} + +int sparx5_register_netdevs(struct sparx5 *sparx5) +{ + int portno; + int err; + + for (portno = 0; portno < SPX5_PORTS; portno++) + if (sparx5->ports[portno]) { + err = register_netdev(sparx5->ports[portno]->ndev); + if (err) { + dev_err(sparx5->dev, + "port: %02u: netdev registration failed\n", + portno); + return err; + } + sparx5_port_inj_timer_setup(sparx5->ports[portno]); + } + return 0; +} + +void sparx5_destroy_netdevs(struct sparx5 *sparx5) +{ + struct sparx5_port *port; + int portno; + + for (portno = 0; portno < SPX5_PORTS; portno++) { + port = sparx5->ports[portno]; + if (port && port->phylink) { + /* Disconnect the phy */ + rtnl_lock(); + sparx5_port_stop(port->ndev); + phylink_disconnect_phy(port->phylink); + rtnl_unlock(); + phylink_destroy(port->phylink); + port->phylink = NULL; + } + } +} + +void sparx5_unregister_netdevs(struct sparx5 *sparx5) +{ + int portno; + + for (portno = 0; portno < SPX5_PORTS; portno++) + if (sparx5->ports[portno]) + unregister_netdev(sparx5->ports[portno]->ndev); +} + diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c new file mode 100644 index 000000000000..09ca7a3bafdc --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -0,0 +1,320 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +#define XTR_EOF_0 ntohl((__force __be32)0x80000000u) +#define XTR_EOF_1 ntohl((__force __be32)0x80000001u) +#define XTR_EOF_2 ntohl((__force __be32)0x80000002u) +#define XTR_EOF_3 ntohl((__force __be32)0x80000003u) +#define XTR_PRUNED ntohl((__force __be32)0x80000004u) +#define XTR_ABORT ntohl((__force __be32)0x80000005u) +#define XTR_ESCAPE ntohl((__force __be32)0x80000006u) +#define XTR_NOT_READY ntohl((__force __be32)0x80000007u) + +#define XTR_VALID_BYTES(x) (4 - ((x) & 3)) + +#define INJ_TIMEOUT_NS 50000 + +struct frame_info { + int src_port; +}; + +static void sparx5_xtr_flush(struct sparx5 *sparx5, u8 grp) +{ + /* Start flush */ + spx5_wr(QS_XTR_FLUSH_FLUSH_SET(BIT(grp)), sparx5, QS_XTR_FLUSH); + + /* Allow to drain */ + mdelay(1); + + /* All Queues normal */ + spx5_wr(0, sparx5, QS_XTR_FLUSH); +} + +static void sparx5_ifh_parse(u32 *ifh, struct frame_info *info) +{ + u8 *xtr_hdr = (u8 *)ifh; + + /* FWD is bit 45-72 (28 bits), but we only read the 27 LSB for now */ + u32 fwd = + ((u32)xtr_hdr[27] << 24) | + ((u32)xtr_hdr[28] << 16) | + ((u32)xtr_hdr[29] << 8) | + ((u32)xtr_hdr[30] << 0); + fwd = (fwd >> 5); + info->src_port = FIELD_GET(GENMASK(7, 1), fwd); +} + +static void sparx5_xtr_grp(struct sparx5 *sparx5, u8 grp, bool byte_swap) +{ + bool eof_flag = false, pruned_flag = false, abort_flag = false; + struct net_device *netdev; + struct sparx5_port *port; + struct frame_info fi; + int i, byte_cnt = 0; + struct sk_buff *skb; + u32 ifh[IFH_LEN]; + u32 *rxbuf; + + /* Get IFH */ + for (i = 0; i < IFH_LEN; i++) + ifh[i] = spx5_rd(sparx5, QS_XTR_RD(grp)); + + /* Decode IFH (whats needed) */ + sparx5_ifh_parse(ifh, &fi); + + /* Map to port netdev */ + port = fi.src_port < SPX5_PORTS ? + sparx5->ports[fi.src_port] : NULL; + if (!port || !port->ndev) { + dev_err(sparx5->dev, "Data on inactive port %d\n", fi.src_port); + sparx5_xtr_flush(sparx5, grp); + return; + } + + /* Have netdev, get skb */ + netdev = port->ndev; + skb = netdev_alloc_skb(netdev, netdev->mtu + ETH_HLEN); + if (!skb) { + sparx5_xtr_flush(sparx5, grp); + dev_err(sparx5->dev, "No skb allocated\n"); + netdev->stats.rx_dropped++; + return; + } + rxbuf = (u32 *)skb->data; + + /* Now, pull frame data */ + while (!eof_flag) { + u32 val = spx5_rd(sparx5, QS_XTR_RD(grp)); + u32 cmp = val; + + if (byte_swap) + cmp = ntohl((__force __be32)val); + + switch (cmp) { + case XTR_NOT_READY: + break; + case XTR_ABORT: + /* No accompanying data */ + abort_flag = true; + eof_flag = true; + break; + case XTR_EOF_0: + case XTR_EOF_1: + case XTR_EOF_2: + case XTR_EOF_3: + /* This assumes STATUS_WORD_POS == 1, Status + * just after last data + */ + byte_cnt -= (4 - XTR_VALID_BYTES(val)); + eof_flag = true; + break; + case XTR_PRUNED: + /* But get the last 4 bytes as well */ + eof_flag = true; + pruned_flag = true; + fallthrough; + case XTR_ESCAPE: + *rxbuf = spx5_rd(sparx5, QS_XTR_RD(grp)); + byte_cnt += 4; + rxbuf++; + break; + default: + *rxbuf = val; + byte_cnt += 4; + rxbuf++; + } + } + + if (abort_flag || pruned_flag || !eof_flag) { + netdev_err(netdev, "Discarded frame: abort:%d pruned:%d eof:%d\n", + abort_flag, pruned_flag, eof_flag); + kfree_skb(skb); + netdev->stats.rx_dropped++; + return; + } + + /* Everything we see on an interface that is in the HW bridge + * has already been forwarded + */ + if (test_bit(port->portno, sparx5->bridge_mask)) + skb->offload_fwd_mark = 1; + + /* Finish up skb */ + skb_put(skb, byte_cnt - ETH_FCS_LEN); + eth_skb_pad(skb); + skb->protocol = eth_type_trans(skb, netdev); + netif_rx(skb); + netdev->stats.rx_bytes += skb->len; + netdev->stats.rx_packets++; +} + +static int sparx5_inject(struct sparx5 *sparx5, + u32 *ifh, + struct sk_buff *skb, + struct net_device *ndev) +{ + int grp = INJ_QUEUE; + u32 val, w, count; + u8 *buf; + + val = spx5_rd(sparx5, QS_INJ_STATUS); + if (!(QS_INJ_STATUS_FIFO_RDY_GET(val) & BIT(grp))) { + pr_err_ratelimited("Injection: Queue not ready: 0x%lx\n", + QS_INJ_STATUS_FIFO_RDY_GET(val)); + return -EBUSY; + } + + /* Indicate SOF */ + spx5_wr(QS_INJ_CTRL_SOF_SET(1) | + QS_INJ_CTRL_GAP_SIZE_SET(1), + sparx5, QS_INJ_CTRL(grp)); + + /* Write the IFH to the chip. */ + for (w = 0; w < IFH_LEN; w++) + spx5_wr(ifh[w], sparx5, QS_INJ_WR(grp)); + + /* Write words, round up */ + count = DIV_ROUND_UP(skb->len, 4); + buf = skb->data; + for (w = 0; w < count; w++, buf += 4) { + val = get_unaligned((const u32 *)buf); + spx5_wr(val, sparx5, QS_INJ_WR(grp)); + } + + /* Add padding */ + while (w < (60 / 4)) { + spx5_wr(0, sparx5, QS_INJ_WR(grp)); + w++; + } + + /* Indicate EOF and valid bytes in last word */ + spx5_wr(QS_INJ_CTRL_GAP_SIZE_SET(1) | + QS_INJ_CTRL_VLD_BYTES_SET(skb->len < 60 ? 0 : skb->len % 4) | + QS_INJ_CTRL_EOF_SET(1), + sparx5, QS_INJ_CTRL(grp)); + + /* Add dummy CRC */ + spx5_wr(0, sparx5, QS_INJ_WR(grp)); + w++; + + val = spx5_rd(sparx5, QS_INJ_STATUS); + if (QS_INJ_STATUS_WMARK_REACHED_GET(val) & BIT(grp)) { + struct sparx5_port *port = netdev_priv(ndev); + + pr_err_ratelimited("Injection: Watermark reached: 0x%lx\n", + QS_INJ_STATUS_WMARK_REACHED_GET(val)); + netif_stop_queue(ndev); + hrtimer_start(&port->inj_timer, INJ_TIMEOUT_NS, + HRTIMER_MODE_REL); + } + + return NETDEV_TX_OK; +} + +int sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) +{ + struct net_device_stats *stats = &dev->stats; + struct sparx5_port *port = netdev_priv(dev); + struct sparx5 *sparx5 = port->sparx5; + int ret; + + ret = sparx5_inject(sparx5, port->ifh, skb, dev); + + if (ret == NETDEV_TX_OK) { + stats->tx_bytes += skb->len; + stats->tx_packets++; + skb_tx_timestamp(skb); + dev_kfree_skb_any(skb); + } else { + stats->tx_dropped++; + } + return ret; +} + +static enum hrtimer_restart sparx5_injection_timeout(struct hrtimer *tmr) +{ + struct sparx5_port *port = container_of(tmr, struct sparx5_port, + inj_timer); + int grp = INJ_QUEUE; + u32 val; + + val = spx5_rd(port->sparx5, QS_INJ_STATUS); + if (QS_INJ_STATUS_WMARK_REACHED_GET(val) & BIT(grp)) { + pr_err_ratelimited("Injection: Reset watermark count\n"); + /* Reset Watermark count to restart */ + spx5_rmw(DSM_DEV_TX_STOP_WM_CFG_DEV_TX_CNT_CLR_SET(1), + DSM_DEV_TX_STOP_WM_CFG_DEV_TX_CNT_CLR, + port->sparx5, + DSM_DEV_TX_STOP_WM_CFG(port->portno)); + } + netif_wake_queue(port->ndev); + return HRTIMER_NORESTART; +} + +int sparx5_manual_injection_mode(struct sparx5 *sparx5) +{ + const int byte_swap = 1; + int portno; + + /* Change mode to manual extraction and injection */ + spx5_wr(QS_XTR_GRP_CFG_MODE_SET(1) | + QS_XTR_GRP_CFG_STATUS_WORD_POS_SET(1) | + QS_XTR_GRP_CFG_BYTE_SWAP_SET(byte_swap), + sparx5, QS_XTR_GRP_CFG(XTR_QUEUE)); + spx5_wr(QS_INJ_GRP_CFG_MODE_SET(1) | + QS_INJ_GRP_CFG_BYTE_SWAP_SET(byte_swap), + sparx5, QS_INJ_GRP_CFG(INJ_QUEUE)); + + /* CPU ports capture setup */ + for (portno = SPX5_PORT_CPU_0; portno <= SPX5_PORT_CPU_1; portno++) { + /* ASM CPU port: No preamble, IFH, enable padding */ + spx5_wr(ASM_PORT_CFG_PAD_ENA_SET(1) | + ASM_PORT_CFG_NO_PREAMBLE_ENA_SET(1) | + ASM_PORT_CFG_INJ_FORMAT_CFG_SET(1), /* 1 = IFH */ + sparx5, ASM_PORT_CFG(portno)); + + /* Reset WM cnt to unclog queued frames */ + spx5_rmw(DSM_DEV_TX_STOP_WM_CFG_DEV_TX_CNT_CLR_SET(1), + DSM_DEV_TX_STOP_WM_CFG_DEV_TX_CNT_CLR, + sparx5, + DSM_DEV_TX_STOP_WM_CFG(portno)); + + /* Set Disassembler Stop Watermark level */ + spx5_rmw(DSM_DEV_TX_STOP_WM_CFG_DEV_TX_STOP_WM_SET(0), + DSM_DEV_TX_STOP_WM_CFG_DEV_TX_STOP_WM, + sparx5, + DSM_DEV_TX_STOP_WM_CFG(portno)); + + /* Enable Disassembler buffer underrun watchdog + */ + spx5_rmw(DSM_BUF_CFG_UNDERFLOW_WATCHDOG_DIS_SET(0), + DSM_BUF_CFG_UNDERFLOW_WATCHDOG_DIS, + sparx5, + DSM_BUF_CFG(portno)); + } + return 0; +} + +irqreturn_t sparx5_xtr_handler(int irq, void *_sparx5) +{ + struct sparx5 *s5 = _sparx5; + int poll = 64; + + /* Check data in queue */ + while (spx5_rd(s5, QS_XTR_DATA_PRESENT) & BIT(XTR_QUEUE) && poll-- > 0) + sparx5_xtr_grp(s5, XTR_QUEUE, false); + + return IRQ_HANDLED; +} + +void sparx5_port_inj_timer_setup(struct sparx5_port *port) +{ + hrtimer_init(&port->inj_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + port->inj_timer.function = sparx5_injection_timeout; +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c new file mode 100644 index 000000000000..af70e2795125 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c @@ -0,0 +1,210 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries. + */ + +#include +#include +#include +#include +#include + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" +#include "sparx5_port.h" + +static bool port_conf_has_changed(struct sparx5_port_config *a, struct sparx5_port_config *b) +{ + if (a->speed != b->speed || + a->portmode != b->portmode || + a->autoneg != b->autoneg || + a->pause_adv != b->pause_adv || + a->power_down != b->power_down || + a->media != b->media) + return true; + return false; +} + +static void sparx5_phylink_validate(struct phylink_config *config, + unsigned long *supported, + struct phylink_link_state *state) +{ + struct sparx5_port *port = netdev_priv(to_net_dev(config->dev)); + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + + phylink_set(mask, Autoneg); + phylink_set_port_modes(mask); + phylink_set(mask, Pause); + phylink_set(mask, Asym_Pause); + + switch (state->interface) { + case PHY_INTERFACE_MODE_5GBASER: + case PHY_INTERFACE_MODE_10GBASER: + case PHY_INTERFACE_MODE_25GBASER: + case PHY_INTERFACE_MODE_NA: + if (port->conf.bandwidth == SPEED_5000) + phylink_set(mask, 5000baseT_Full); + if (port->conf.bandwidth == SPEED_10000) { + phylink_set(mask, 5000baseT_Full); + phylink_set(mask, 10000baseT_Full); + phylink_set(mask, 10000baseCR_Full); + phylink_set(mask, 10000baseSR_Full); + phylink_set(mask, 10000baseLR_Full); + phylink_set(mask, 10000baseLRM_Full); + phylink_set(mask, 10000baseER_Full); + } + if (port->conf.bandwidth == SPEED_25000) { + phylink_set(mask, 5000baseT_Full); + phylink_set(mask, 10000baseT_Full); + phylink_set(mask, 10000baseCR_Full); + phylink_set(mask, 10000baseSR_Full); + phylink_set(mask, 10000baseLR_Full); + phylink_set(mask, 10000baseLRM_Full); + phylink_set(mask, 10000baseER_Full); + phylink_set(mask, 25000baseCR_Full); + phylink_set(mask, 25000baseSR_Full); + } + if (state->interface != PHY_INTERFACE_MODE_NA) + break; + fallthrough; + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 100baseT_Full); + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseX_Full); + if (state->interface != PHY_INTERFACE_MODE_NA) + break; + fallthrough; + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: + if (state->interface != PHY_INTERFACE_MODE_2500BASEX) { + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseX_Full); + } + if (state->interface == PHY_INTERFACE_MODE_2500BASEX || + state->interface == PHY_INTERFACE_MODE_NA) { + phylink_set(mask, 2500baseT_Full); + phylink_set(mask, 2500baseX_Full); + } + break; + default: + bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); + return; + } + bitmap_and(supported, supported, mask, __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_and(state->advertising, state->advertising, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static void sparx5_phylink_mac_config(struct phylink_config *config, + unsigned int mode, + const struct phylink_link_state *state) +{ + /* Currently not used */ +} + +static void sparx5_phylink_mac_link_up(struct phylink_config *config, + struct phy_device *phy, + unsigned int mode, + phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) +{ + struct sparx5_port *port = netdev_priv(to_net_dev(config->dev)); + struct sparx5_port_config conf; + int err; + + conf = port->conf; + conf.duplex = duplex; + conf.pause = 0; + conf.pause |= tx_pause ? MLO_PAUSE_TX : 0; + conf.pause |= rx_pause ? MLO_PAUSE_RX : 0; + conf.speed = speed; + /* Configure the port to speed/duplex/pause */ + err = sparx5_port_config(port->sparx5, port, &conf); + if (err) + netdev_err(port->ndev, "port config failed: %d\n", err); +} + +static void sparx5_phylink_mac_link_down(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) +{ + /* Currently not used */ +} + +static struct sparx5_port *sparx5_pcs_to_port(struct phylink_pcs *pcs) +{ + return container_of(pcs, struct sparx5_port, phylink_pcs); +} + +static void sparx5_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) +{ + struct sparx5_port *port = sparx5_pcs_to_port(pcs); + struct sparx5_port_status status; + + sparx5_get_port_status(port->sparx5, port, &status); + state->link = status.link && !status.link_down; + state->an_complete = status.an_complete; + state->speed = status.speed; + state->duplex = status.duplex; + state->pause = status.pause; +} + +static int sparx5_pcs_config(struct phylink_pcs *pcs, + unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) +{ + struct sparx5_port *port = sparx5_pcs_to_port(pcs); + struct sparx5_port_config conf; + int ret = 0; + + conf = port->conf; + conf.power_down = false; + conf.portmode = interface; + conf.inband = phylink_autoneg_inband(mode); + conf.autoneg = phylink_test(advertising, Autoneg); + conf.pause_adv = 0; + if (phylink_test(advertising, Pause)) + conf.pause_adv |= ADVERTISE_1000XPAUSE; + if (phylink_test(advertising, Asym_Pause)) + conf.pause_adv |= ADVERTISE_1000XPSE_ASYM; + if (sparx5_is_baser(interface)) { + if (phylink_test(advertising, FIBRE)) + conf.media = PHY_MEDIA_SR; + else + conf.media = PHY_MEDIA_DAC; + } + if (!port_conf_has_changed(&port->conf, &conf)) + return ret; + /* Enable the PCS matching this interface type */ + ret = sparx5_port_pcs_set(port->sparx5, port, &conf); + if (ret) + netdev_err(port->ndev, "port PCS config failed: %d\n", ret); + return ret; +} + +static void sparx5_pcs_aneg_restart(struct phylink_pcs *pcs) +{ + /* Currently not used */ +} + +const struct phylink_pcs_ops sparx5_phylink_pcs_ops = { + .pcs_get_state = sparx5_pcs_get_state, + .pcs_config = sparx5_pcs_config, + .pcs_an_restart = sparx5_pcs_aneg_restart, +}; + +const struct phylink_mac_ops sparx5_phylink_mac_ops = { + .validate = sparx5_phylink_validate, + .mac_config = sparx5_phylink_mac_config, + .mac_link_down = sparx5_phylink_mac_link_down, + .mac_link_up = sparx5_phylink_mac_link_up, +}; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c new file mode 100644 index 000000000000..d2e3250928bf --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c @@ -0,0 +1,1146 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries. + */ + +#include +#include + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" +#include "sparx5_port.h" + +#define SPX5_ETYPE_TAG_C 0x8100 +#define SPX5_ETYPE_TAG_S 0x88a8 + +#define SPX5_WAIT_US 1000 +#define SPX5_WAIT_MAX_US 2000 + +enum port_error { + SPX5_PERR_SPEED, + SPX5_PERR_IFTYPE, +}; + +#define PAUSE_DISCARD 0xC +#define ETH_MAXLEN (ETH_DATA_LEN + ETH_HLEN + ETH_FCS_LEN) + +static void decode_sgmii_word(u16 lp_abil, struct sparx5_port_status *status) +{ + status->an_complete = true; + if (!(lp_abil & LPA_SGMII_LINK)) { + status->link = false; + return; + } + + switch (lp_abil & LPA_SGMII_SPD_MASK) { + case LPA_SGMII_10: + status->speed = SPEED_10; + break; + case LPA_SGMII_100: + status->speed = SPEED_100; + break; + case LPA_SGMII_1000: + status->speed = SPEED_1000; + break; + default: + status->link = false; + return; + } + if (lp_abil & LPA_SGMII_FULL_DUPLEX) + status->duplex = DUPLEX_FULL; + else + status->duplex = DUPLEX_HALF; +} + +static void decode_cl37_word(u16 lp_abil, uint16_t ld_abil, struct sparx5_port_status *status) +{ + status->link = !(lp_abil & ADVERTISE_RFAULT) && status->link; + status->an_complete = true; + status->duplex = (ADVERTISE_1000XFULL & lp_abil) ? + DUPLEX_FULL : DUPLEX_UNKNOWN; // 1G HDX not supported + + if ((ld_abil & ADVERTISE_1000XPAUSE) && + (lp_abil & ADVERTISE_1000XPAUSE)) { + status->pause = MLO_PAUSE_RX | MLO_PAUSE_TX; + } else if ((ld_abil & ADVERTISE_1000XPSE_ASYM) && + (lp_abil & ADVERTISE_1000XPSE_ASYM)) { + status->pause |= (lp_abil & ADVERTISE_1000XPAUSE) ? + MLO_PAUSE_TX : 0; + status->pause |= (ld_abil & ADVERTISE_1000XPAUSE) ? + MLO_PAUSE_RX : 0; + } else { + status->pause = MLO_PAUSE_NONE; + } +} + +static int sparx5_get_dev2g5_status(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_status *status) +{ + u32 portno = port->portno; + u16 lp_adv, ld_adv; + u32 value; + + /* Get PCS Link down sticky */ + value = spx5_rd(sparx5, DEV2G5_PCS1G_STICKY(portno)); + status->link_down = DEV2G5_PCS1G_STICKY_LINK_DOWN_STICKY_GET(value); + if (status->link_down) /* Clear the sticky */ + spx5_wr(value, sparx5, DEV2G5_PCS1G_STICKY(portno)); + + /* Get both current Link and Sync status */ + value = spx5_rd(sparx5, DEV2G5_PCS1G_LINK_STATUS(portno)); + status->link = DEV2G5_PCS1G_LINK_STATUS_LINK_STATUS_GET(value) && + DEV2G5_PCS1G_LINK_STATUS_SYNC_STATUS_GET(value); + + if (port->conf.portmode == PHY_INTERFACE_MODE_1000BASEX) + status->speed = SPEED_1000; + else if (port->conf.portmode == PHY_INTERFACE_MODE_2500BASEX) + status->speed = SPEED_2500; + + status->duplex = DUPLEX_FULL; + + /* Get PCS ANEG status register */ + value = spx5_rd(sparx5, DEV2G5_PCS1G_ANEG_STATUS(portno)); + + /* Aneg complete provides more information */ + if (DEV2G5_PCS1G_ANEG_STATUS_ANEG_COMPLETE_GET(value)) { + lp_adv = DEV2G5_PCS1G_ANEG_STATUS_LP_ADV_ABILITY_GET(value); + if (port->conf.portmode == PHY_INTERFACE_MODE_SGMII) { + decode_sgmii_word(lp_adv, status); + } else { + value = spx5_rd(sparx5, DEV2G5_PCS1G_ANEG_CFG(portno)); + ld_adv = DEV2G5_PCS1G_ANEG_CFG_ADV_ABILITY_GET(value); + decode_cl37_word(lp_adv, ld_adv, status); + } + } + return 0; +} + +static int sparx5_get_sfi_status(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_status *status) +{ + bool high_speed_dev = sparx5_is_baser(port->conf.portmode); + u32 portno = port->portno; + u32 value, dev, tinst; + void __iomem *inst; + + if (!high_speed_dev) { + netdev_err(port->ndev, "error: low speed and SFI mode\n"); + return -EINVAL; + } + + dev = sparx5_to_high_dev(portno); + tinst = sparx5_port_dev_index(portno); + inst = spx5_inst_get(sparx5, dev, tinst); + + value = spx5_inst_rd(inst, DEV10G_MAC_TX_MONITOR_STICKY(0)); + if (value != DEV10G_MAC_TX_MONITOR_STICKY_IDLE_STATE_STICKY) { + /* The link is or has been down. Clear the sticky bit */ + status->link_down = 1; + spx5_inst_wr(0xffffffff, inst, DEV10G_MAC_TX_MONITOR_STICKY(0)); + value = spx5_inst_rd(inst, DEV10G_MAC_TX_MONITOR_STICKY(0)); + } + status->link = (value == DEV10G_MAC_TX_MONITOR_STICKY_IDLE_STATE_STICKY); + status->duplex = DUPLEX_FULL; + if (port->conf.portmode == PHY_INTERFACE_MODE_5GBASER) + status->speed = SPEED_5000; + else if (port->conf.portmode == PHY_INTERFACE_MODE_10GBASER) + status->speed = SPEED_10000; + else + status->speed = SPEED_25000; + + return 0; +} + +/* Get link status of 1000Base-X/in-band and SFI ports. + */ +int sparx5_get_port_status(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_status *status) +{ + memset(status, 0, sizeof(*status)); + status->speed = port->conf.speed; + if (port->conf.power_down) { + status->link = false; + return 0; + } + switch (port->conf.portmode) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: + return sparx5_get_dev2g5_status(sparx5, port, status); + case PHY_INTERFACE_MODE_5GBASER: + case PHY_INTERFACE_MODE_10GBASER: + case PHY_INTERFACE_MODE_25GBASER: + return sparx5_get_sfi_status(sparx5, port, status); + case PHY_INTERFACE_MODE_NA: + return 0; + default: + netdev_err(port->ndev, "Status not supported"); + return -ENODEV; + } + return 0; +} + +static int sparx5_port_error(struct sparx5_port *port, + struct sparx5_port_config *conf, + enum port_error errtype) +{ + switch (errtype) { + case SPX5_PERR_SPEED: + netdev_err(port->ndev, + "Interface does not support speed: %u: for %s\n", + conf->speed, phy_modes(conf->portmode)); + break; + case SPX5_PERR_IFTYPE: + netdev_err(port->ndev, + "Switch port does not support interface type: %s\n", + phy_modes(conf->portmode)); + break; + default: + netdev_err(port->ndev, + "Interface configuration error\n"); + } + + return -EINVAL; +} + +static int sparx5_port_verify_speed(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + if ((sparx5_port_is_2g5(port->portno) && + conf->speed > SPEED_2500) || + (sparx5_port_is_5g(port->portno) && + conf->speed > SPEED_5000) || + (sparx5_port_is_10g(port->portno) && + conf->speed > SPEED_10000)) + return sparx5_port_error(port, conf, SPX5_PERR_SPEED); + + switch (conf->portmode) { + case PHY_INTERFACE_MODE_NA: + return -EINVAL; + case PHY_INTERFACE_MODE_1000BASEX: + if (conf->speed != SPEED_1000 || + sparx5_port_is_2g5(port->portno)) + return sparx5_port_error(port, conf, SPX5_PERR_SPEED); + if (sparx5_port_is_2g5(port->portno)) + return sparx5_port_error(port, conf, SPX5_PERR_IFTYPE); + break; + case PHY_INTERFACE_MODE_2500BASEX: + if (conf->speed != SPEED_2500 || + sparx5_port_is_2g5(port->portno)) + return sparx5_port_error(port, conf, SPX5_PERR_SPEED); + break; + case PHY_INTERFACE_MODE_QSGMII: + if (port->portno > 47) + return sparx5_port_error(port, conf, SPX5_PERR_IFTYPE); + fallthrough; + case PHY_INTERFACE_MODE_SGMII: + if (conf->speed != SPEED_1000 && + conf->speed != SPEED_100 && + conf->speed != SPEED_10 && + conf->speed != SPEED_2500) + return sparx5_port_error(port, conf, SPX5_PERR_SPEED); + break; + case PHY_INTERFACE_MODE_5GBASER: + case PHY_INTERFACE_MODE_10GBASER: + case PHY_INTERFACE_MODE_25GBASER: + if ((conf->speed != SPEED_5000 && + conf->speed != SPEED_10000 && + conf->speed != SPEED_25000)) + return sparx5_port_error(port, conf, SPX5_PERR_SPEED); + break; + default: + return sparx5_port_error(port, conf, SPX5_PERR_IFTYPE); + } + return 0; +} + +static bool sparx5_dev_change(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + return sparx5_is_baser(port->conf.portmode) ^ + sparx5_is_baser(conf->portmode); +} + +static int sparx5_port_flush_poll(struct sparx5 *sparx5, u32 portno) +{ + u32 value, resource, prio, delay_cnt = 0; + bool poll_src = true; + char *mem = ""; + + /* Resource == 0: Memory tracked per source (SRC-MEM) + * Resource == 1: Frame references tracked per source (SRC-REF) + * Resource == 2: Memory tracked per destination (DST-MEM) + * Resource == 3: Frame references tracked per destination. (DST-REF) + */ + while (1) { + bool empty = true; + + for (resource = 0; resource < (poll_src ? 2 : 1); resource++) { + u32 base; + + base = (resource == 0 ? 2048 : 0) + SPX5_PRIOS * portno; + for (prio = 0; prio < SPX5_PRIOS; prio++) { + value = spx5_rd(sparx5, + QRES_RES_STAT(base + prio)); + if (value) { + mem = resource == 0 ? + "DST-MEM" : "SRC-MEM"; + empty = false; + } + } + } + + if (empty) + break; + + if (delay_cnt++ == 2000) { + dev_err(sparx5->dev, + "Flush timeout port %u. %s queue not empty\n", + portno, mem); + return -EINVAL; + } + + usleep_range(SPX5_WAIT_US, SPX5_WAIT_MAX_US); + } + return 0; +} + +static int sparx5_port_disable(struct sparx5 *sparx5, struct sparx5_port *port, bool high_spd_dev) +{ + u32 tinst = high_spd_dev ? + sparx5_port_dev_index(port->portno) : port->portno; + u32 dev = high_spd_dev ? + sparx5_to_high_dev(port->portno) : TARGET_DEV2G5; + void __iomem *devinst = spx5_inst_get(sparx5, dev, tinst); + u32 spd = port->conf.speed; + u32 spd_prm; + int err; + + if (high_spd_dev) { + /* 1: Reset the PCS Rx clock domain */ + spx5_inst_rmw(DEV10G_DEV_RST_CTRL_PCS_RX_RST, + DEV10G_DEV_RST_CTRL_PCS_RX_RST, + devinst, + DEV10G_DEV_RST_CTRL(0)); + + /* 2: Disable MAC frame reception */ + spx5_inst_rmw(0, + DEV10G_MAC_ENA_CFG_RX_ENA, + devinst, + DEV10G_MAC_ENA_CFG(0)); + } else { + /* 1: Reset the PCS Rx clock domain */ + spx5_inst_rmw(DEV2G5_DEV_RST_CTRL_PCS_RX_RST, + DEV2G5_DEV_RST_CTRL_PCS_RX_RST, + devinst, + DEV2G5_DEV_RST_CTRL(0)); + /* 2: Disable MAC frame reception */ + spx5_inst_rmw(0, + DEV2G5_MAC_ENA_CFG_RX_ENA, + devinst, + DEV2G5_MAC_ENA_CFG(0)); + } + /* 3: Disable traffic being sent to or from switch port->portno */ + spx5_rmw(0, + QFWD_SWITCH_PORT_MODE_PORT_ENA, + sparx5, + QFWD_SWITCH_PORT_MODE(port->portno)); + + /* 4: Disable dequeuing from the egress queues */ + spx5_rmw(HSCH_PORT_MODE_DEQUEUE_DIS, + HSCH_PORT_MODE_DEQUEUE_DIS, + sparx5, + HSCH_PORT_MODE(port->portno)); + + /* 5: Disable Flowcontrol */ + spx5_rmw(QSYS_PAUSE_CFG_PAUSE_STOP_SET(0xFFF - 1), + QSYS_PAUSE_CFG_PAUSE_STOP, + sparx5, + QSYS_PAUSE_CFG(port->portno)); + + spd_prm = spd == SPEED_10 ? 1000 : spd == SPEED_100 ? 100 : 10; + /* 6: Wait while the last frame is exiting the queues */ + usleep_range(8 * spd_prm, 10 * spd_prm); + + /* 7: Flush the queues accociated with the port->portno */ + spx5_rmw(HSCH_FLUSH_CTRL_FLUSH_PORT_SET(port->portno) | + HSCH_FLUSH_CTRL_FLUSH_DST_SET(1) | + HSCH_FLUSH_CTRL_FLUSH_SRC_SET(1) | + HSCH_FLUSH_CTRL_FLUSH_ENA_SET(1), + HSCH_FLUSH_CTRL_FLUSH_PORT | + HSCH_FLUSH_CTRL_FLUSH_DST | + HSCH_FLUSH_CTRL_FLUSH_SRC | + HSCH_FLUSH_CTRL_FLUSH_ENA, + sparx5, + HSCH_FLUSH_CTRL); + + /* 8: Enable dequeuing from the egress queues */ + spx5_rmw(0, + HSCH_PORT_MODE_DEQUEUE_DIS, + sparx5, + HSCH_PORT_MODE(port->portno)); + + /* 9: Wait until flushing is complete */ + err = sparx5_port_flush_poll(sparx5, port->portno); + if (err) + return err; + + /* 10: Reset the MAC clock domain */ + if (high_spd_dev) { + spx5_inst_rmw(DEV10G_DEV_RST_CTRL_PCS_TX_RST_SET(1) | + DEV10G_DEV_RST_CTRL_MAC_RX_RST_SET(1) | + DEV10G_DEV_RST_CTRL_MAC_TX_RST_SET(1), + DEV10G_DEV_RST_CTRL_PCS_TX_RST | + DEV10G_DEV_RST_CTRL_MAC_RX_RST | + DEV10G_DEV_RST_CTRL_MAC_TX_RST, + devinst, + DEV10G_DEV_RST_CTRL(0)); + + } else { + spx5_inst_rmw(DEV2G5_DEV_RST_CTRL_SPEED_SEL_SET(3) | + DEV2G5_DEV_RST_CTRL_PCS_TX_RST_SET(1) | + DEV2G5_DEV_RST_CTRL_PCS_RX_RST_SET(1) | + DEV2G5_DEV_RST_CTRL_MAC_TX_RST_SET(1) | + DEV2G5_DEV_RST_CTRL_MAC_RX_RST_SET(1), + DEV2G5_DEV_RST_CTRL_SPEED_SEL | + DEV2G5_DEV_RST_CTRL_PCS_TX_RST | + DEV2G5_DEV_RST_CTRL_PCS_RX_RST | + DEV2G5_DEV_RST_CTRL_MAC_TX_RST | + DEV2G5_DEV_RST_CTRL_MAC_RX_RST, + devinst, + DEV2G5_DEV_RST_CTRL(0)); + } + /* 11: Clear flushing */ + spx5_rmw(HSCH_FLUSH_CTRL_FLUSH_PORT_SET(port->portno) | + HSCH_FLUSH_CTRL_FLUSH_ENA_SET(0), + HSCH_FLUSH_CTRL_FLUSH_PORT | + HSCH_FLUSH_CTRL_FLUSH_ENA, + sparx5, + HSCH_FLUSH_CTRL); + + if (high_spd_dev) { + u32 pcs = sparx5_to_pcs_dev(port->portno); + void __iomem *pcsinst = spx5_inst_get(sparx5, pcs, tinst); + + /* 12: Disable 5G/10G/25 BaseR PCS */ + spx5_inst_rmw(PCS10G_BR_PCS_CFG_PCS_ENA_SET(0), + PCS10G_BR_PCS_CFG_PCS_ENA, + pcsinst, + PCS10G_BR_PCS_CFG(0)); + + if (sparx5_port_is_25g(port->portno)) + /* Disable 25G PCS */ + spx5_rmw(DEV25G_PCS25G_CFG_PCS25G_ENA_SET(0), + DEV25G_PCS25G_CFG_PCS25G_ENA, + sparx5, + DEV25G_PCS25G_CFG(tinst)); + } else { + /* 12: Disable 1G PCS */ + spx5_rmw(DEV2G5_PCS1G_CFG_PCS_ENA_SET(0), + DEV2G5_PCS1G_CFG_PCS_ENA, + sparx5, + DEV2G5_PCS1G_CFG(port->portno)); + } + + /* The port is now flushed and disabled */ + return 0; +} + +static int sparx5_port_fifo_sz(struct sparx5 *sparx5, + u32 portno, u32 speed) +{ + u32 sys_clk = sparx5_clk_period(sparx5->coreclock); + const u32 taxi_dist[SPX5_PORTS_ALL] = { + 6, 8, 10, 6, 8, 10, 6, 8, 10, 6, 8, 10, + 4, 4, 4, 4, + 11, 12, 13, 14, 15, 16, 17, 18, + 11, 12, 13, 14, 15, 16, 17, 18, + 11, 12, 13, 14, 15, 16, 17, 18, + 11, 12, 13, 14, 15, 16, 17, 18, + 4, 6, 8, 4, 6, 8, 6, 8, + 2, 2, 2, 2, 2, 2, 2, 4, 2 + }; + u32 mac_per = 6400, tmp1, tmp2, tmp3; + u32 fifo_width = 16; + u32 mac_width = 8; + u32 addition = 0; + + switch (speed) { + case SPEED_25000: + return 0; + case SPEED_10000: + mac_per = 6400; + mac_width = 8; + addition = 1; + break; + case SPEED_5000: + mac_per = 12800; + mac_width = 8; + addition = 0; + break; + case SPEED_2500: + mac_per = 3200; + mac_width = 1; + addition = 0; + break; + case SPEED_1000: + mac_per = 8000; + mac_width = 1; + addition = 0; + break; + case SPEED_100: + case SPEED_10: + return 1; + default: + break; + } + + tmp1 = 1000 * mac_width / fifo_width; + tmp2 = 3000 + ((12000 + 2 * taxi_dist[portno] * 1000) + * sys_clk / mac_per); + tmp3 = tmp1 * tmp2 / 1000; + return (tmp3 + 2000 + 999) / 1000 + addition; +} + +/* Configure port muxing: + * QSGMII: 4x2G5 devices + */ +static int sparx5_port_mux_set(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + u32 portno = port->portno; + u32 inst; + + if (port->conf.portmode == conf->portmode) + return 0; /* Nothing to do */ + + switch (conf->portmode) { + case PHY_INTERFACE_MODE_QSGMII: /* QSGMII: 4x2G5 devices. Mode Q' */ + inst = (portno - portno % 4) / 4; + spx5_rmw(BIT(inst), + BIT(inst), + sparx5, + PORT_CONF_QSGMII_ENA); + + if ((portno / 4 % 2) == 0) { + /* Affects d0-d3,d8-d11..d40-d43 */ + spx5_rmw(PORT_CONF_USGMII_CFG_BYPASS_SCRAM_SET(1) | + PORT_CONF_USGMII_CFG_BYPASS_DESCRAM_SET(1) | + PORT_CONF_USGMII_CFG_QUAD_MODE_SET(1), + PORT_CONF_USGMII_CFG_BYPASS_SCRAM | + PORT_CONF_USGMII_CFG_BYPASS_DESCRAM | + PORT_CONF_USGMII_CFG_QUAD_MODE, + sparx5, + PORT_CONF_USGMII_CFG((portno / 8))); + } + break; + default: + break; + } + return 0; +} + +static int sparx5_port_max_tags_set(struct sparx5 *sparx5, + struct sparx5_port *port) +{ + enum sparx5_port_max_tags max_tags = port->max_vlan_tags; + int tag_ct = max_tags == SPX5_PORT_MAX_TAGS_ONE ? 1 : + max_tags == SPX5_PORT_MAX_TAGS_TWO ? 2 : 0; + bool dtag = max_tags == SPX5_PORT_MAX_TAGS_TWO; + enum sparx5_vlan_port_type vlan_type = port->vlan_type; + bool dotag = max_tags != SPX5_PORT_MAX_TAGS_NONE; + u32 dev = sparx5_to_high_dev(port->portno); + u32 tinst = sparx5_port_dev_index(port->portno); + void __iomem *inst = spx5_inst_get(sparx5, dev, tinst); + u32 etype; + + etype = (vlan_type == SPX5_VLAN_PORT_TYPE_S_CUSTOM ? + port->custom_etype : + vlan_type == SPX5_VLAN_PORT_TYPE_C ? + SPX5_ETYPE_TAG_C : SPX5_ETYPE_TAG_S); + + spx5_wr(DEV2G5_MAC_TAGS_CFG_TAG_ID_SET(etype) | + DEV2G5_MAC_TAGS_CFG_PB_ENA_SET(dtag) | + DEV2G5_MAC_TAGS_CFG_VLAN_AWR_ENA_SET(dotag) | + DEV2G5_MAC_TAGS_CFG_VLAN_LEN_AWR_ENA_SET(dotag), + sparx5, + DEV2G5_MAC_TAGS_CFG(port->portno)); + + if (sparx5_port_is_2g5(port->portno)) + return 0; + + spx5_inst_rmw(DEV10G_MAC_TAGS_CFG_TAG_ID_SET(etype) | + DEV10G_MAC_TAGS_CFG_TAG_ENA_SET(dotag), + DEV10G_MAC_TAGS_CFG_TAG_ID | + DEV10G_MAC_TAGS_CFG_TAG_ENA, + inst, + DEV10G_MAC_TAGS_CFG(0, 0)); + + spx5_inst_rmw(DEV10G_MAC_NUM_TAGS_CFG_NUM_TAGS_SET(tag_ct), + DEV10G_MAC_NUM_TAGS_CFG_NUM_TAGS, + inst, + DEV10G_MAC_NUM_TAGS_CFG(0)); + + spx5_inst_rmw(DEV10G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK_SET(dotag), + DEV10G_MAC_MAXLEN_CFG_MAX_LEN_TAG_CHK, + inst, + DEV10G_MAC_MAXLEN_CFG(0)); + return 0; +} + +static int sparx5_port_fwd_urg(struct sparx5 *sparx5, u32 speed) +{ + u32 clk_period_ps = 1600; /* 625Mhz for now */ + u32 urg = 672000; + + switch (speed) { + case SPEED_10: + case SPEED_100: + case SPEED_1000: + urg = 672000; + break; + case SPEED_2500: + urg = 270000; + break; + case SPEED_5000: + urg = 135000; + break; + case SPEED_10000: + urg = 67200; + break; + case SPEED_25000: + urg = 27000; + break; + } + return urg / clk_period_ps - 1; +} + +static u16 sparx5_wm_enc(u16 value) +{ + if (value >= 2048) + return 2048 + value / 16; + + return value; +} + +static int sparx5_port_fc_setup(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + bool fc_obey = conf->pause & MLO_PAUSE_RX ? 1 : 0; + u32 pause_stop = 0xFFF - 1; /* FC gen disabled */ + + if (conf->pause & MLO_PAUSE_TX) + pause_stop = sparx5_wm_enc(4 * (ETH_MAXLEN / + SPX5_BUFFER_CELL_SZ)); + + /* Set HDX flowcontrol */ + spx5_rmw(DSM_MAC_CFG_HDX_BACKPREASSURE_SET(conf->duplex == DUPLEX_HALF), + DSM_MAC_CFG_HDX_BACKPREASSURE, + sparx5, + DSM_MAC_CFG(port->portno)); + + /* Obey flowcontrol */ + spx5_rmw(DSM_RX_PAUSE_CFG_RX_PAUSE_EN_SET(fc_obey), + DSM_RX_PAUSE_CFG_RX_PAUSE_EN, + sparx5, + DSM_RX_PAUSE_CFG(port->portno)); + + /* Disable forward pressure */ + spx5_rmw(QSYS_FWD_PRESSURE_FWD_PRESSURE_DIS_SET(fc_obey), + QSYS_FWD_PRESSURE_FWD_PRESSURE_DIS, + sparx5, + QSYS_FWD_PRESSURE(port->portno)); + + /* Generate pause frames */ + spx5_rmw(QSYS_PAUSE_CFG_PAUSE_STOP_SET(pause_stop), + QSYS_PAUSE_CFG_PAUSE_STOP, + sparx5, + QSYS_PAUSE_CFG(port->portno)); + + return 0; +} + +static u16 sparx5_get_aneg_word(struct sparx5_port_config *conf) +{ + if (conf->portmode == PHY_INTERFACE_MODE_1000BASEX) /* cl-37 aneg */ + return (conf->pause_adv | ADVERTISE_LPACK | ADVERTISE_1000XFULL); + else + return 1; /* Enable SGMII Aneg */ +} + +int sparx5_serdes_set(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + int portmode, err, speed = conf->speed; + + if (conf->portmode == PHY_INTERFACE_MODE_QSGMII && + ((port->portno % 4) != 0)) { + return 0; + } + if (sparx5_is_baser(conf->portmode)) { + if (conf->portmode == PHY_INTERFACE_MODE_25GBASER) + speed = SPEED_25000; + else if (conf->portmode == PHY_INTERFACE_MODE_10GBASER) + speed = SPEED_10000; + else + speed = SPEED_5000; + } + + err = phy_set_media(port->serdes, conf->media); + if (err) + return err; + if (speed > 0) { + err = phy_set_speed(port->serdes, speed); + if (err) + return err; + } + if (conf->serdes_reset) { + err = phy_reset(port->serdes); + if (err) + return err; + } + + /* Configure SerDes with port parameters + * For BaseR, the serdes driver supports 10GGBASE-R and speed 5G/10G/25G + */ + portmode = conf->portmode; + if (sparx5_is_baser(conf->portmode)) + portmode = PHY_INTERFACE_MODE_10GBASER; + err = phy_set_mode_ext(port->serdes, PHY_MODE_ETHERNET, portmode); + if (err) + return err; + conf->serdes_reset = false; + return err; +} + +static int sparx5_port_pcs_low_set(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + bool sgmii = false, inband_aneg = false; + int err; + + if (port->conf.inband) { + if (conf->portmode == PHY_INTERFACE_MODE_SGMII || + conf->portmode == PHY_INTERFACE_MODE_QSGMII) + inband_aneg = true; /* Cisco-SGMII in-band-aneg */ + else if (conf->portmode == PHY_INTERFACE_MODE_1000BASEX && + conf->autoneg) + inband_aneg = true; /* Clause-37 in-band-aneg */ + + err = sparx5_serdes_set(sparx5, port, conf); + if (err) + return -EINVAL; + } else { + sgmii = true; /* Phy is connnected to the MAC */ + } + + /* Choose SGMII or 1000BaseX/2500BaseX PCS mode */ + spx5_rmw(DEV2G5_PCS1G_MODE_CFG_SGMII_MODE_ENA_SET(sgmii), + DEV2G5_PCS1G_MODE_CFG_SGMII_MODE_ENA, + sparx5, + DEV2G5_PCS1G_MODE_CFG(port->portno)); + + /* Enable PCS */ + spx5_wr(DEV2G5_PCS1G_CFG_PCS_ENA_SET(1), + sparx5, + DEV2G5_PCS1G_CFG(port->portno)); + + if (inband_aneg) { + u16 abil = sparx5_get_aneg_word(conf); + + /* Enable in-band aneg */ + spx5_wr(DEV2G5_PCS1G_ANEG_CFG_ADV_ABILITY_SET(abil) | + DEV2G5_PCS1G_ANEG_CFG_SW_RESOLVE_ENA_SET(1) | + DEV2G5_PCS1G_ANEG_CFG_ANEG_ENA_SET(1) | + DEV2G5_PCS1G_ANEG_CFG_ANEG_RESTART_ONE_SHOT_SET(1), + sparx5, + DEV2G5_PCS1G_ANEG_CFG(port->portno)); + } else { + spx5_wr(0, sparx5, DEV2G5_PCS1G_ANEG_CFG(port->portno)); + } + + /* Take PCS out of reset */ + spx5_rmw(DEV2G5_DEV_RST_CTRL_SPEED_SEL_SET(2) | + DEV2G5_DEV_RST_CTRL_PCS_TX_RST_SET(0) | + DEV2G5_DEV_RST_CTRL_PCS_RX_RST_SET(0), + DEV2G5_DEV_RST_CTRL_SPEED_SEL | + DEV2G5_DEV_RST_CTRL_PCS_TX_RST | + DEV2G5_DEV_RST_CTRL_PCS_RX_RST, + sparx5, + DEV2G5_DEV_RST_CTRL(port->portno)); + + return 0; +} + +static int sparx5_port_pcs_high_set(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + u32 clk_spd = conf->portmode == PHY_INTERFACE_MODE_5GBASER ? 1 : 0; + u32 pix = sparx5_port_dev_index(port->portno); + u32 dev = sparx5_to_high_dev(port->portno); + u32 pcs = sparx5_to_pcs_dev(port->portno); + void __iomem *devinst; + void __iomem *pcsinst; + int err; + + devinst = spx5_inst_get(sparx5, dev, pix); + pcsinst = spx5_inst_get(sparx5, pcs, pix); + + /* SFI : No in-band-aneg. Speeds 5G/10G/25G */ + err = sparx5_serdes_set(sparx5, port, conf); + if (err) + return -EINVAL; + if (conf->portmode == PHY_INTERFACE_MODE_25GBASER) { + /* Enable PCS for 25G device, speed 25G */ + spx5_rmw(DEV25G_PCS25G_CFG_PCS25G_ENA_SET(1), + DEV25G_PCS25G_CFG_PCS25G_ENA, + sparx5, + DEV25G_PCS25G_CFG(pix)); + } else { + /* Enable PCS for 5G/10G/25G devices, speed 5G/10G */ + spx5_inst_rmw(PCS10G_BR_PCS_CFG_PCS_ENA_SET(1), + PCS10G_BR_PCS_CFG_PCS_ENA, + pcsinst, + PCS10G_BR_PCS_CFG(0)); + } + + /* Enable 5G/10G/25G MAC module */ + spx5_inst_wr(DEV10G_MAC_ENA_CFG_RX_ENA_SET(1) | + DEV10G_MAC_ENA_CFG_TX_ENA_SET(1), + devinst, + DEV10G_MAC_ENA_CFG(0)); + + /* Take the device out of reset */ + spx5_inst_rmw(DEV10G_DEV_RST_CTRL_PCS_RX_RST_SET(0) | + DEV10G_DEV_RST_CTRL_PCS_TX_RST_SET(0) | + DEV10G_DEV_RST_CTRL_MAC_RX_RST_SET(0) | + DEV10G_DEV_RST_CTRL_MAC_TX_RST_SET(0) | + DEV10G_DEV_RST_CTRL_SPEED_SEL_SET(clk_spd), + DEV10G_DEV_RST_CTRL_PCS_RX_RST | + DEV10G_DEV_RST_CTRL_PCS_TX_RST | + DEV10G_DEV_RST_CTRL_MAC_RX_RST | + DEV10G_DEV_RST_CTRL_MAC_TX_RST | + DEV10G_DEV_RST_CTRL_SPEED_SEL, + devinst, + DEV10G_DEV_RST_CTRL(0)); + + return 0; +} + +/* Switch between 1G/2500 and 5G/10G/25G devices */ +static void sparx5_dev_switch(struct sparx5 *sparx5, int port, bool hsd) +{ + int bt_indx = BIT(sparx5_port_dev_index(port)); + + if (sparx5_port_is_5g(port)) { + spx5_rmw(hsd ? 0 : bt_indx, + bt_indx, + sparx5, + PORT_CONF_DEV5G_MODES); + } else if (sparx5_port_is_10g(port)) { + spx5_rmw(hsd ? 0 : bt_indx, + bt_indx, + sparx5, + PORT_CONF_DEV10G_MODES); + } else if (sparx5_port_is_25g(port)) { + spx5_rmw(hsd ? 0 : bt_indx, + bt_indx, + sparx5, + PORT_CONF_DEV25G_MODES); + } +} + +/* Configure speed/duplex dependent registers */ +static int sparx5_port_config_low_set(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + u32 clk_spd, gig_mode, tx_gap, hdx_gap_1, hdx_gap_2; + bool fdx = conf->duplex == DUPLEX_FULL; + int spd = conf->speed; + + clk_spd = spd == SPEED_10 ? 0 : spd == SPEED_100 ? 1 : 2; + gig_mode = spd == SPEED_1000 || spd == SPEED_2500; + tx_gap = spd == SPEED_1000 ? 4 : fdx ? 6 : 5; + hdx_gap_1 = spd == SPEED_1000 ? 0 : spd == SPEED_100 ? 1 : 2; + hdx_gap_2 = spd == SPEED_1000 ? 0 : spd == SPEED_100 ? 4 : 1; + + /* GIG/FDX mode */ + spx5_rmw(DEV2G5_MAC_MODE_CFG_GIGA_MODE_ENA_SET(gig_mode) | + DEV2G5_MAC_MODE_CFG_FDX_ENA_SET(fdx), + DEV2G5_MAC_MODE_CFG_GIGA_MODE_ENA | + DEV2G5_MAC_MODE_CFG_FDX_ENA, + sparx5, + DEV2G5_MAC_MODE_CFG(port->portno)); + + /* Set MAC IFG Gaps */ + spx5_wr(DEV2G5_MAC_IFG_CFG_TX_IFG_SET(tx_gap) | + DEV2G5_MAC_IFG_CFG_RX_IFG1_SET(hdx_gap_1) | + DEV2G5_MAC_IFG_CFG_RX_IFG2_SET(hdx_gap_2), + sparx5, + DEV2G5_MAC_IFG_CFG(port->portno)); + + /* Disabling frame aging when in HDX (due to HDX issue) */ + spx5_rmw(HSCH_PORT_MODE_AGE_DIS_SET(fdx == 0), + HSCH_PORT_MODE_AGE_DIS, + sparx5, + HSCH_PORT_MODE(port->portno)); + + /* Enable MAC module */ + spx5_wr(DEV2G5_MAC_ENA_CFG_RX_ENA | + DEV2G5_MAC_ENA_CFG_TX_ENA, + sparx5, + DEV2G5_MAC_ENA_CFG(port->portno)); + + /* Select speed and take MAC out of reset */ + spx5_rmw(DEV2G5_DEV_RST_CTRL_SPEED_SEL_SET(clk_spd) | + DEV2G5_DEV_RST_CTRL_MAC_TX_RST_SET(0) | + DEV2G5_DEV_RST_CTRL_MAC_RX_RST_SET(0), + DEV2G5_DEV_RST_CTRL_SPEED_SEL | + DEV2G5_DEV_RST_CTRL_MAC_TX_RST | + DEV2G5_DEV_RST_CTRL_MAC_RX_RST, + sparx5, + DEV2G5_DEV_RST_CTRL(port->portno)); + + return 0; +} + +int sparx5_port_pcs_set(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_config *conf) + +{ + bool high_speed_dev = sparx5_is_baser(conf->portmode); + int err; + + if (sparx5_dev_change(sparx5, port, conf)) { + /* switch device */ + sparx5_dev_switch(sparx5, port->portno, high_speed_dev); + + /* Disable the not-in-use device */ + err = sparx5_port_disable(sparx5, port, !high_speed_dev); + if (err) + return err; + } + /* Disable the port before re-configuring */ + err = sparx5_port_disable(sparx5, port, high_speed_dev); + if (err) + return -EINVAL; + + if (high_speed_dev) + err = sparx5_port_pcs_high_set(sparx5, port, conf); + else + err = sparx5_port_pcs_low_set(sparx5, port, conf); + + if (err) + return -EINVAL; + + if (port->conf.inband) { + /* Enable/disable 1G counters in ASM */ + spx5_rmw(ASM_PORT_CFG_CSC_STAT_DIS_SET(high_speed_dev), + ASM_PORT_CFG_CSC_STAT_DIS, + sparx5, + ASM_PORT_CFG(port->portno)); + + /* Enable/disable 1G counters in DSM */ + spx5_rmw(DSM_BUF_CFG_CSC_STAT_DIS_SET(high_speed_dev), + DSM_BUF_CFG_CSC_STAT_DIS, + sparx5, + DSM_BUF_CFG(port->portno)); + } + + port->conf = *conf; + + return 0; +} + +int sparx5_port_config(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + bool high_speed_dev = sparx5_is_baser(conf->portmode); + int err, urgency, stop_wm; + + err = sparx5_port_verify_speed(sparx5, port, conf); + if (err) + return err; + + /* high speed device is already configured */ + if (!high_speed_dev) + sparx5_port_config_low_set(sparx5, port, conf); + + /* Configure flow control */ + err = sparx5_port_fc_setup(sparx5, port, conf); + if (err) + return err; + + /* Set the DSM stop watermark */ + stop_wm = sparx5_port_fifo_sz(sparx5, port->portno, conf->speed); + spx5_rmw(DSM_DEV_TX_STOP_WM_CFG_DEV_TX_STOP_WM_SET(stop_wm), + DSM_DEV_TX_STOP_WM_CFG_DEV_TX_STOP_WM, + sparx5, + DSM_DEV_TX_STOP_WM_CFG(port->portno)); + + /* Enable port in queue system */ + urgency = sparx5_port_fwd_urg(sparx5, conf->speed); + spx5_rmw(QFWD_SWITCH_PORT_MODE_PORT_ENA_SET(1) | + QFWD_SWITCH_PORT_MODE_FWD_URGENCY_SET(urgency), + QFWD_SWITCH_PORT_MODE_PORT_ENA | + QFWD_SWITCH_PORT_MODE_FWD_URGENCY, + sparx5, + QFWD_SWITCH_PORT_MODE(port->portno)); + + /* Save the new values */ + port->conf = *conf; + + return 0; +} + +/* Initialize port config to default */ +int sparx5_port_init(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_config *conf) +{ + u32 pause_start = sparx5_wm_enc(6 * (ETH_MAXLEN / SPX5_BUFFER_CELL_SZ)); + u32 atop = sparx5_wm_enc(20 * (ETH_MAXLEN / SPX5_BUFFER_CELL_SZ)); + u32 devhigh = sparx5_to_high_dev(port->portno); + u32 pix = sparx5_port_dev_index(port->portno); + u32 pcs = sparx5_to_pcs_dev(port->portno); + bool sd_pol = port->signd_active_high; + bool sd_sel = !port->signd_internal; + bool sd_ena = port->signd_enable; + u32 pause_stop = 0xFFF - 1; /* FC generate disabled */ + void __iomem *devinst; + void __iomem *pcsinst; + int err; + + devinst = spx5_inst_get(sparx5, devhigh, pix); + pcsinst = spx5_inst_get(sparx5, pcs, pix); + + /* Set the mux port mode */ + err = sparx5_port_mux_set(sparx5, port, conf); + if (err) + return err; + + /* Configure MAC vlan awareness */ + err = sparx5_port_max_tags_set(sparx5, port); + if (err) + return err; + + /* Set Max Length */ + spx5_rmw(DEV2G5_MAC_MAXLEN_CFG_MAX_LEN_SET(ETH_MAXLEN), + DEV2G5_MAC_MAXLEN_CFG_MAX_LEN, + sparx5, + DEV2G5_MAC_MAXLEN_CFG(port->portno)); + + /* 1G/2G5: Signal Detect configuration */ + spx5_wr(DEV2G5_PCS1G_SD_CFG_SD_POL_SET(sd_pol) | + DEV2G5_PCS1G_SD_CFG_SD_SEL_SET(sd_sel) | + DEV2G5_PCS1G_SD_CFG_SD_ENA_SET(sd_ena), + sparx5, + DEV2G5_PCS1G_SD_CFG(port->portno)); + + /* Set Pause WM hysteresis */ + spx5_rmw(QSYS_PAUSE_CFG_PAUSE_START_SET(pause_start) | + QSYS_PAUSE_CFG_PAUSE_STOP_SET(pause_stop) | + QSYS_PAUSE_CFG_PAUSE_ENA_SET(1), + QSYS_PAUSE_CFG_PAUSE_START | + QSYS_PAUSE_CFG_PAUSE_STOP | + QSYS_PAUSE_CFG_PAUSE_ENA, + sparx5, + QSYS_PAUSE_CFG(port->portno)); + + /* Port ATOP. Frames are tail dropped when this WM is hit */ + spx5_wr(QSYS_ATOP_ATOP_SET(atop), + sparx5, + QSYS_ATOP(port->portno)); + + /* Discard pause frame 01-80-C2-00-00-01 */ + spx5_wr(PAUSE_DISCARD, sparx5, ANA_CL_CAPTURE_BPDU_CFG(port->portno)); + + if (conf->portmode == PHY_INTERFACE_MODE_QSGMII || + conf->portmode == PHY_INTERFACE_MODE_SGMII) { + err = sparx5_serdes_set(sparx5, port, conf); + if (err) + return err; + + if (!sparx5_port_is_2g5(port->portno)) + /* Enable shadow device */ + spx5_rmw(DSM_DEV_TX_STOP_WM_CFG_DEV10G_SHADOW_ENA_SET(1), + DSM_DEV_TX_STOP_WM_CFG_DEV10G_SHADOW_ENA, + sparx5, + DSM_DEV_TX_STOP_WM_CFG(port->portno)); + + sparx5_dev_switch(sparx5, port->portno, false); + } + if (conf->portmode == PHY_INTERFACE_MODE_QSGMII) { + // All ports must be PCS enabled in QSGMII mode + spx5_rmw(DEV2G5_DEV_RST_CTRL_PCS_TX_RST_SET(0), + DEV2G5_DEV_RST_CTRL_PCS_TX_RST, + sparx5, + DEV2G5_DEV_RST_CTRL(port->portno)); + } + /* Default IFGs for 1G */ + spx5_wr(DEV2G5_MAC_IFG_CFG_TX_IFG_SET(6) | + DEV2G5_MAC_IFG_CFG_RX_IFG1_SET(0) | + DEV2G5_MAC_IFG_CFG_RX_IFG2_SET(0), + sparx5, + DEV2G5_MAC_IFG_CFG(port->portno)); + + if (sparx5_port_is_2g5(port->portno)) + return 0; /* Low speed device only - return */ + + /* Now setup the high speed device */ + if (conf->portmode == PHY_INTERFACE_MODE_NA) + conf->portmode = PHY_INTERFACE_MODE_10GBASER; + + if (sparx5_is_baser(conf->portmode)) + sparx5_dev_switch(sparx5, port->portno, true); + + /* Set Max Length */ + spx5_inst_rmw(DEV10G_MAC_MAXLEN_CFG_MAX_LEN_SET(ETH_MAXLEN), + DEV10G_MAC_MAXLEN_CFG_MAX_LEN, + devinst, + DEV10G_MAC_ENA_CFG(0)); + + /* Handle Signal Detect in 10G PCS */ + spx5_inst_wr(PCS10G_BR_PCS_SD_CFG_SD_POL_SET(sd_pol) | + PCS10G_BR_PCS_SD_CFG_SD_SEL_SET(sd_sel) | + PCS10G_BR_PCS_SD_CFG_SD_ENA_SET(sd_ena), + pcsinst, + PCS10G_BR_PCS_SD_CFG(0)); + + if (sparx5_port_is_25g(port->portno)) { + /* Handle Signal Detect in 25G PCS */ + spx5_wr(DEV25G_PCS25G_SD_CFG_SD_POL_SET(sd_pol) | + DEV25G_PCS25G_SD_CFG_SD_SEL_SET(sd_sel) | + DEV25G_PCS25G_SD_CFG_SD_ENA_SET(sd_ena), + sparx5, + DEV25G_PCS25G_SD_CFG(pix)); + } + + return 0; +} + +void sparx5_port_enable(struct sparx5_port *port, bool enable) +{ + struct sparx5 *sparx5 = port->sparx5; + + /* Enable port for frame transfer? */ + spx5_rmw(QFWD_SWITCH_PORT_MODE_PORT_ENA_SET(enable), + QFWD_SWITCH_PORT_MODE_PORT_ENA, + sparx5, + QFWD_SWITCH_PORT_MODE(port->portno)); +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.h b/drivers/net/ethernet/microchip/sparx5/sparx5_port.h new file mode 100644 index 000000000000..fd05ab6436d1 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.h @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries. + */ + +#ifndef __SPARX5_PORT_H__ +#define __SPARX5_PORT_H__ + +#include "sparx5_main.h" + +static inline bool sparx5_port_is_2g5(int portno) +{ + return portno >= 16 && portno <= 47; +} + +static inline bool sparx5_port_is_5g(int portno) +{ + return portno <= 11 || portno == 64; +} + +static inline bool sparx5_port_is_10g(int portno) +{ + return (portno >= 12 && portno <= 15) || (portno >= 48 && portno <= 55); +} + +static inline bool sparx5_port_is_25g(int portno) +{ + return portno >= 56 && portno <= 63; +} + +static inline u32 sparx5_to_high_dev(int port) +{ + if (sparx5_port_is_5g(port)) + return TARGET_DEV5G; + if (sparx5_port_is_10g(port)) + return TARGET_DEV10G; + return TARGET_DEV25G; +} + +static inline u32 sparx5_to_pcs_dev(int port) +{ + if (sparx5_port_is_5g(port)) + return TARGET_PCS5G_BR; + if (sparx5_port_is_10g(port)) + return TARGET_PCS10G_BR; + return TARGET_PCS25G_BR; +} + +static inline int sparx5_port_dev_index(int port) +{ + if (sparx5_port_is_2g5(port)) + return port; + if (sparx5_port_is_5g(port)) + return (port <= 11 ? port : 12); + if (sparx5_port_is_10g(port)) + return (port >= 12 && port <= 15) ? + port - 12 : port - 44; + return (port - 56); +} + +int sparx5_port_init(struct sparx5 *sparx5, + struct sparx5_port *spx5_port, + struct sparx5_port_config *conf); + +int sparx5_port_config(struct sparx5 *sparx5, + struct sparx5_port *spx5_port, + struct sparx5_port_config *conf); + +int sparx5_port_pcs_set(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_config *conf); + +int sparx5_serdes_set(struct sparx5 *sparx5, + struct sparx5_port *spx5_port, + struct sparx5_port_config *conf); + +struct sparx5_port_status { + bool link; + bool link_down; + int speed; + bool an_complete; + int duplex; + int pause; +}; + +int sparx5_get_port_status(struct sparx5 *sparx5, + struct sparx5_port *port, + struct sparx5_port_status *status); + +void sparx5_port_enable(struct sparx5_port *port, bool enable); + +#endif /* __SPARX5_PORT_H__ */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c new file mode 100644 index 000000000000..a72e3b3b596e --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c @@ -0,0 +1,510 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries. + */ + +#include +#include + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +static struct workqueue_struct *sparx5_owq; + +struct sparx5_switchdev_event_work { + struct work_struct work; + struct switchdev_notifier_fdb_info fdb_info; + struct net_device *dev; + unsigned long event; +}; + +static void sparx5_port_attr_bridge_flags(struct sparx5_port *port, + struct switchdev_brport_flags flags) +{ + if (flags.mask & BR_MCAST_FLOOD) + sparx5_pgid_update_mask(port, PGID_MC_FLOOD, true); +} + +static void sparx5_attr_stp_state_set(struct sparx5_port *port, + u8 state) +{ + struct sparx5 *sparx5 = port->sparx5; + + if (!test_bit(port->portno, sparx5->bridge_mask)) { + netdev_err(port->ndev, + "Controlling non-bridged port %d?\n", port->portno); + return; + } + + switch (state) { + case BR_STATE_FORWARDING: + set_bit(port->portno, sparx5->bridge_fwd_mask); + fallthrough; + case BR_STATE_LEARNING: + set_bit(port->portno, sparx5->bridge_lrn_mask); + break; + + default: + /* All other states treated as blocking */ + clear_bit(port->portno, sparx5->bridge_fwd_mask); + clear_bit(port->portno, sparx5->bridge_lrn_mask); + break; + } + + /* apply the bridge_fwd_mask to all the ports */ + sparx5_update_fwd(sparx5); +} + +static void sparx5_port_attr_ageing_set(struct sparx5_port *port, + unsigned long ageing_clock_t) +{ + unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock_t); + u32 ageing_time = jiffies_to_msecs(ageing_jiffies); + + sparx5_set_ageing(port->sparx5, ageing_time); +} + +static int sparx5_port_attr_set(struct net_device *dev, const void *ctx, + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) +{ + struct sparx5_port *port = netdev_priv(dev); + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: + sparx5_port_attr_bridge_flags(port, attr->u.brport_flags); + break; + case SWITCHDEV_ATTR_ID_PORT_STP_STATE: + sparx5_attr_stp_state_set(port, attr->u.stp_state); + break; + case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: + sparx5_port_attr_ageing_set(port, attr->u.ageing_time); + break; + case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: + port->vlan_aware = attr->u.vlan_filtering; + sparx5_vlan_port_apply(port->sparx5, port); + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int sparx5_port_bridge_join(struct sparx5_port *port, + struct net_device *bridge) +{ + struct sparx5 *sparx5 = port->sparx5; + + if (bitmap_empty(sparx5->bridge_mask, SPX5_PORTS)) + /* First bridged port */ + sparx5->hw_bridge_dev = bridge; + else + if (sparx5->hw_bridge_dev != bridge) + /* This is adding the port to a second bridge, this is + * unsupported + */ + return -ENODEV; + + set_bit(port->portno, sparx5->bridge_mask); + + /* Port enters in bridge mode therefor don't need to copy to CPU + * frames for multicast in case the bridge is not requesting them + */ + __dev_mc_unsync(port->ndev, sparx5_mc_unsync); + + return 0; +} + +static void sparx5_port_bridge_leave(struct sparx5_port *port, + struct net_device *bridge) +{ + struct sparx5 *sparx5 = port->sparx5; + + clear_bit(port->portno, sparx5->bridge_mask); + if (bitmap_empty(sparx5->bridge_mask, SPX5_PORTS)) + sparx5->hw_bridge_dev = NULL; + + /* Clear bridge vlan settings before updating the port settings */ + port->vlan_aware = 0; + port->pvid = NULL_VID; + port->vid = NULL_VID; + + /* Port enters in host more therefore restore mc list */ + __dev_mc_sync(port->ndev, sparx5_mc_sync, sparx5_mc_unsync); +} + +static int sparx5_port_changeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct sparx5_port *port = netdev_priv(dev); + int err = 0; + + if (netif_is_bridge_master(info->upper_dev)) { + if (info->linking) + err = sparx5_port_bridge_join(port, info->upper_dev); + else + sparx5_port_bridge_leave(port, info->upper_dev); + + sparx5_vlan_port_apply(port->sparx5, port); + } + + return err; +} + +static int sparx5_port_add_addr(struct net_device *dev, bool up) +{ + struct sparx5_port *port = netdev_priv(dev); + struct sparx5 *sparx5 = port->sparx5; + u16 vid = port->pvid; + + if (up) + sparx5_mact_learn(sparx5, PGID_CPU, port->ndev->dev_addr, vid); + else + sparx5_mact_forget(sparx5, port->ndev->dev_addr, vid); + + return 0; +} + +static int sparx5_netdevice_port_event(struct net_device *dev, + struct notifier_block *nb, + unsigned long event, void *ptr) +{ + int err = 0; + + if (!sparx5_netdevice_check(dev)) + return 0; + + switch (event) { + case NETDEV_CHANGEUPPER: + err = sparx5_port_changeupper(dev, ptr); + break; + case NETDEV_PRE_UP: + err = sparx5_port_add_addr(dev, true); + break; + case NETDEV_DOWN: + err = sparx5_port_add_addr(dev, false); + break; + } + + return err; +} + +static int sparx5_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + int ret = 0; + + ret = sparx5_netdevice_port_event(dev, nb, event, ptr); + + return notifier_from_errno(ret); +} + +static void sparx5_switchdev_bridge_fdb_event_work(struct work_struct *work) +{ + struct sparx5_switchdev_event_work *switchdev_work = + container_of(work, struct sparx5_switchdev_event_work, work); + struct net_device *dev = switchdev_work->dev; + struct switchdev_notifier_fdb_info *fdb_info; + struct sparx5_port *port; + struct sparx5 *sparx5; + + rtnl_lock(); + if (!sparx5_netdevice_check(dev)) + goto out; + + port = netdev_priv(dev); + sparx5 = port->sparx5; + + fdb_info = &switchdev_work->fdb_info; + + switch (switchdev_work->event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + if (!fdb_info->added_by_user) + break; + sparx5_add_mact_entry(sparx5, port, fdb_info->addr, + fdb_info->vid); + break; + case SWITCHDEV_FDB_DEL_TO_DEVICE: + if (!fdb_info->added_by_user) + break; + sparx5_del_mact_entry(sparx5, fdb_info->addr, fdb_info->vid); + break; + } + +out: + rtnl_unlock(); + kfree(switchdev_work->fdb_info.addr); + kfree(switchdev_work); + dev_put(dev); +} + +static void sparx5_schedule_work(struct work_struct *work) +{ + queue_work(sparx5_owq, work); +} + +static int sparx5_switchdev_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + struct sparx5_switchdev_event_work *switchdev_work; + struct switchdev_notifier_fdb_info *fdb_info; + struct switchdev_notifier_info *info = ptr; + int err; + + switch (event) { + case SWITCHDEV_PORT_ATTR_SET: + err = switchdev_handle_port_attr_set(dev, ptr, + sparx5_netdevice_check, + sparx5_port_attr_set); + return notifier_from_errno(err); + case SWITCHDEV_FDB_ADD_TO_DEVICE: + fallthrough; + case SWITCHDEV_FDB_DEL_TO_DEVICE: + switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); + if (!switchdev_work) + return NOTIFY_BAD; + + switchdev_work->dev = dev; + switchdev_work->event = event; + + fdb_info = container_of(info, + struct switchdev_notifier_fdb_info, + info); + INIT_WORK(&switchdev_work->work, + sparx5_switchdev_bridge_fdb_event_work); + memcpy(&switchdev_work->fdb_info, ptr, + sizeof(switchdev_work->fdb_info)); + switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC); + if (!switchdev_work->fdb_info.addr) + goto err_addr_alloc; + + ether_addr_copy((u8 *)switchdev_work->fdb_info.addr, + fdb_info->addr); + dev_hold(dev); + + sparx5_schedule_work(&switchdev_work->work); + break; + } + + return NOTIFY_DONE; +err_addr_alloc: + kfree(switchdev_work); + return NOTIFY_BAD; +} + +static void sparx5_sync_port_dev_addr(struct sparx5 *sparx5, + struct sparx5_port *port, + u16 vid, bool add) +{ + if (!port || + !test_bit(port->portno, sparx5->bridge_mask)) + return; /* Skip null/host interfaces */ + + /* Bridge connects to vid? */ + if (add) { + /* Add port MAC address from the VLAN */ + sparx5_mact_learn(sparx5, PGID_CPU, + port->ndev->dev_addr, vid); + } else { + /* Control port addr visibility depending on + * port VLAN connectivity. + */ + if (test_bit(port->portno, sparx5->vlan_mask[vid])) + sparx5_mact_learn(sparx5, PGID_CPU, + port->ndev->dev_addr, vid); + else + sparx5_mact_forget(sparx5, + port->ndev->dev_addr, vid); + } +} + +static void sparx5_sync_bridge_dev_addr(struct net_device *dev, + struct sparx5 *sparx5, + u16 vid, bool add) +{ + int i; + + /* First, handle bridge address'es */ + if (add) { + sparx5_mact_learn(sparx5, PGID_CPU, dev->dev_addr, + vid); + sparx5_mact_learn(sparx5, PGID_BCAST, dev->broadcast, + vid); + } else { + sparx5_mact_forget(sparx5, dev->dev_addr, vid); + sparx5_mact_forget(sparx5, dev->broadcast, vid); + } + + /* Now look at bridged ports */ + for (i = 0; i < SPX5_PORTS; i++) + sparx5_sync_port_dev_addr(sparx5, sparx5->ports[i], vid, add); +} + +static int sparx5_handle_port_vlan_add(struct net_device *dev, + struct notifier_block *nb, + const struct switchdev_obj_port_vlan *v) +{ + struct sparx5_port *port = netdev_priv(dev); + + if (netif_is_bridge_master(dev)) { + if (v->flags & BRIDGE_VLAN_INFO_BRENTRY) { + struct sparx5 *sparx5 = + container_of(nb, struct sparx5, + switchdev_blocking_nb); + + sparx5_sync_bridge_dev_addr(dev, sparx5, v->vid, true); + } + return 0; + } + + if (!sparx5_netdevice_check(dev)) + return -EOPNOTSUPP; + + return sparx5_vlan_vid_add(port, v->vid, + v->flags & BRIDGE_VLAN_INFO_PVID, + v->flags & BRIDGE_VLAN_INFO_UNTAGGED); +} + +static int sparx5_handle_port_obj_add(struct net_device *dev, + struct notifier_block *nb, + struct switchdev_notifier_port_obj_info *info) +{ + const struct switchdev_obj *obj = info->obj; + int err; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + err = sparx5_handle_port_vlan_add(dev, nb, + SWITCHDEV_OBJ_PORT_VLAN(obj)); + break; + default: + err = -EOPNOTSUPP; + break; + } + + info->handled = true; + return err; +} + +static int sparx5_handle_port_vlan_del(struct net_device *dev, + struct notifier_block *nb, + u16 vid) +{ + struct sparx5_port *port = netdev_priv(dev); + int ret; + + /* Master bridge? */ + if (netif_is_bridge_master(dev)) { + struct sparx5 *sparx5 = + container_of(nb, struct sparx5, + switchdev_blocking_nb); + + sparx5_sync_bridge_dev_addr(dev, sparx5, vid, false); + return 0; + } + + if (!sparx5_netdevice_check(dev)) + return -EOPNOTSUPP; + + ret = sparx5_vlan_vid_del(port, vid); + if (ret) + return ret; + + /* Delete the port MAC address with the matching VLAN information */ + sparx5_mact_forget(port->sparx5, port->ndev->dev_addr, vid); + + return 0; +} + +static int sparx5_handle_port_obj_del(struct net_device *dev, + struct notifier_block *nb, + struct switchdev_notifier_port_obj_info *info) +{ + const struct switchdev_obj *obj = info->obj; + int err; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + err = sparx5_handle_port_vlan_del(dev, nb, + SWITCHDEV_OBJ_PORT_VLAN(obj)->vid); + break; + default: + err = -EOPNOTSUPP; + break; + } + + info->handled = true; + return err; +} + +static int sparx5_switchdev_blocking_event(struct notifier_block *nb, + unsigned long event, + void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + int err; + + switch (event) { + case SWITCHDEV_PORT_OBJ_ADD: + err = sparx5_handle_port_obj_add(dev, nb, ptr); + return notifier_from_errno(err); + case SWITCHDEV_PORT_OBJ_DEL: + err = sparx5_handle_port_obj_del(dev, nb, ptr); + return notifier_from_errno(err); + case SWITCHDEV_PORT_ATTR_SET: + err = switchdev_handle_port_attr_set(dev, ptr, + sparx5_netdevice_check, + sparx5_port_attr_set); + return notifier_from_errno(err); + } + + return NOTIFY_DONE; +} + +int sparx5_register_notifier_blocks(struct sparx5 *s5) +{ + int err; + + s5->netdevice_nb.notifier_call = sparx5_netdevice_event; + err = register_netdevice_notifier(&s5->netdevice_nb); + if (err) + return err; + + s5->switchdev_nb.notifier_call = sparx5_switchdev_event; + err = register_switchdev_notifier(&s5->switchdev_nb); + if (err) + goto err_switchdev_nb; + + s5->switchdev_blocking_nb.notifier_call = sparx5_switchdev_blocking_event; + err = register_switchdev_blocking_notifier(&s5->switchdev_blocking_nb); + if (err) + goto err_switchdev_blocking_nb; + + sparx5_owq = alloc_ordered_workqueue("sparx5_order", 0); + if (!sparx5_owq) { + err = -ENOMEM; + goto err_switchdev_blocking_nb; + } + + return 0; + +err_switchdev_blocking_nb: + unregister_switchdev_notifier(&s5->switchdev_nb); +err_switchdev_nb: + unregister_netdevice_notifier(&s5->netdevice_nb); + + return err; +} + +void sparx5_unregister_notifier_blocks(struct sparx5 *s5) +{ + destroy_workqueue(sparx5_owq); + + unregister_switchdev_blocking_notifier(&s5->switchdev_blocking_nb); + unregister_switchdev_notifier(&s5->switchdev_nb); + unregister_netdevice_notifier(&s5->netdevice_nb); +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vlan.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vlan.c new file mode 100644 index 000000000000..4ce490a25f33 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vlan.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2021 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +static int sparx5_vlant_set_mask(struct sparx5 *sparx5, u16 vid) +{ + u32 mask[3]; + + /* Divide up mask in 32 bit words */ + bitmap_to_arr32(mask, sparx5->vlan_mask[vid], SPX5_PORTS); + + /* Output mask to respective registers */ + spx5_wr(mask[0], sparx5, ANA_L3_VLAN_MASK_CFG(vid)); + spx5_wr(mask[1], sparx5, ANA_L3_VLAN_MASK_CFG1(vid)); + spx5_wr(mask[2], sparx5, ANA_L3_VLAN_MASK_CFG2(vid)); + + return 0; +} + +void sparx5_vlan_init(struct sparx5 *sparx5) +{ + u16 vid; + + spx5_rmw(ANA_L3_VLAN_CTRL_VLAN_ENA_SET(1), + ANA_L3_VLAN_CTRL_VLAN_ENA, + sparx5, + ANA_L3_VLAN_CTRL); + + /* Map VLAN = FID */ + for (vid = NULL_VID; vid < VLAN_N_VID; vid++) + spx5_rmw(ANA_L3_VLAN_CFG_VLAN_FID_SET(vid), + ANA_L3_VLAN_CFG_VLAN_FID, + sparx5, + ANA_L3_VLAN_CFG(vid)); +} + +void sparx5_vlan_port_setup(struct sparx5 *sparx5, int portno) +{ + struct sparx5_port *port = sparx5->ports[portno]; + + /* Configure PVID */ + spx5_rmw(ANA_CL_VLAN_CTRL_VLAN_AWARE_ENA_SET(0) | + ANA_CL_VLAN_CTRL_PORT_VID_SET(port->pvid), + ANA_CL_VLAN_CTRL_VLAN_AWARE_ENA | + ANA_CL_VLAN_CTRL_PORT_VID, + sparx5, + ANA_CL_VLAN_CTRL(port->portno)); +} + +int sparx5_vlan_vid_add(struct sparx5_port *port, u16 vid, bool pvid, + bool untagged) +{ + struct sparx5 *sparx5 = port->sparx5; + int ret; + + /* Make the port a member of the VLAN */ + set_bit(port->portno, sparx5->vlan_mask[vid]); + ret = sparx5_vlant_set_mask(sparx5, vid); + if (ret) + return ret; + + /* Default ingress vlan classification */ + if (pvid) + port->pvid = vid; + + /* Untagged egress vlan classification */ + if (untagged && port->vid != vid) { + if (port->vid) { + netdev_err(port->ndev, + "Port already has a native VLAN: %d\n", + port->vid); + return -EBUSY; + } + port->vid = vid; + } + + sparx5_vlan_port_apply(sparx5, port); + + return 0; +} + +int sparx5_vlan_vid_del(struct sparx5_port *port, u16 vid) +{ + struct sparx5 *sparx5 = port->sparx5; + int ret; + + /* 8021q removes VID 0 on module unload for all interfaces + * with VLAN filtering feature. We need to keep it to receive + * untagged traffic. + */ + if (vid == 0) + return 0; + + /* Stop the port from being a member of the vlan */ + clear_bit(port->portno, sparx5->vlan_mask[vid]); + ret = sparx5_vlant_set_mask(sparx5, vid); + if (ret) + return ret; + + /* Ingress */ + if (port->pvid == vid) + port->pvid = 0; + + /* Egress */ + if (port->vid == vid) + port->vid = 0; + + sparx5_vlan_port_apply(sparx5, port); + + return 0; +} + +void sparx5_pgid_update_mask(struct sparx5_port *port, int pgid, bool enable) +{ + struct sparx5 *sparx5 = port->sparx5; + u32 val, mask; + + /* mask is spread across 3 registers x 32 bit */ + if (port->portno < 32) { + mask = BIT(port->portno); + val = enable ? mask : 0; + spx5_rmw(val, mask, sparx5, ANA_AC_PGID_CFG(pgid)); + } else if (port->portno < 64) { + mask = BIT(port->portno - 32); + val = enable ? mask : 0; + spx5_rmw(val, mask, sparx5, ANA_AC_PGID_CFG1(pgid)); + } else if (port->portno < SPX5_PORTS) { + mask = BIT(port->portno - 64); + val = enable ? mask : 0; + spx5_rmw(val, mask, sparx5, ANA_AC_PGID_CFG2(pgid)); + } else { + netdev_err(port->ndev, "Invalid port no: %d\n", port->portno); + } +} + +void sparx5_update_fwd(struct sparx5 *sparx5) +{ + DECLARE_BITMAP(workmask, SPX5_PORTS); + u32 mask[3]; + int port; + + /* Divide up fwd mask in 32 bit words */ + bitmap_to_arr32(mask, sparx5->bridge_fwd_mask, SPX5_PORTS); + + /* Update flood masks */ + for (port = PGID_UC_FLOOD; port <= PGID_BCAST; port++) { + spx5_wr(mask[0], sparx5, ANA_AC_PGID_CFG(port)); + spx5_wr(mask[1], sparx5, ANA_AC_PGID_CFG1(port)); + spx5_wr(mask[2], sparx5, ANA_AC_PGID_CFG2(port)); + } + + /* Update SRC masks */ + for (port = 0; port < SPX5_PORTS; port++) { + if (test_bit(port, sparx5->bridge_fwd_mask)) { + /* Allow to send to all bridged but self */ + bitmap_copy(workmask, sparx5->bridge_fwd_mask, SPX5_PORTS); + clear_bit(port, workmask); + bitmap_to_arr32(mask, workmask, SPX5_PORTS); + spx5_wr(mask[0], sparx5, ANA_AC_SRC_CFG(port)); + spx5_wr(mask[1], sparx5, ANA_AC_SRC_CFG1(port)); + spx5_wr(mask[2], sparx5, ANA_AC_SRC_CFG2(port)); + } else { + spx5_wr(0, sparx5, ANA_AC_SRC_CFG(port)); + spx5_wr(0, sparx5, ANA_AC_SRC_CFG1(port)); + spx5_wr(0, sparx5, ANA_AC_SRC_CFG2(port)); + } + } + + /* Learning enabled only for bridged ports */ + bitmap_and(workmask, sparx5->bridge_fwd_mask, + sparx5->bridge_lrn_mask, SPX5_PORTS); + bitmap_to_arr32(mask, workmask, SPX5_PORTS); + + /* Apply learning mask */ + spx5_wr(mask[0], sparx5, ANA_L2_AUTO_LRN_CFG); + spx5_wr(mask[1], sparx5, ANA_L2_AUTO_LRN_CFG1); + spx5_wr(mask[2], sparx5, ANA_L2_AUTO_LRN_CFG2); +} + +void sparx5_vlan_port_apply(struct sparx5 *sparx5, + struct sparx5_port *port) + +{ + u32 val; + + /* Configure PVID, vlan aware */ + val = ANA_CL_VLAN_CTRL_VLAN_AWARE_ENA_SET(port->vlan_aware) | + ANA_CL_VLAN_CTRL_VLAN_POP_CNT_SET(port->vlan_aware) | + ANA_CL_VLAN_CTRL_PORT_VID_SET(port->pvid); + spx5_wr(val, sparx5, ANA_CL_VLAN_CTRL(port->portno)); + + val = 0; + if (port->vlan_aware && !port->pvid) + /* If port is vlan-aware and tagged, drop untagged and + * priority tagged frames. + */ + val = ANA_CL_VLAN_FILTER_CTRL_TAG_REQUIRED_ENA_SET(1) | + ANA_CL_VLAN_FILTER_CTRL_PRIO_CTAG_DIS_SET(1) | + ANA_CL_VLAN_FILTER_CTRL_PRIO_STAG_DIS_SET(1); + spx5_wr(val, sparx5, + ANA_CL_VLAN_FILTER_CTRL(port->portno, 0)); + + /* Egress configuration (REW_TAG_CFG): VLAN tag type to 8021Q */ + val = REW_TAG_CTRL_TAG_TPID_CFG_SET(0); + if (port->vlan_aware) { + if (port->vid) + /* Tag all frames except when VID == DEFAULT_VLAN */ + val |= REW_TAG_CTRL_TAG_CFG_SET(1); + else + val |= REW_TAG_CTRL_TAG_CFG_SET(3); + } + spx5_wr(val, sparx5, REW_TAG_CTRL(port->portno)); + + /* Egress VID */ + spx5_rmw(REW_PORT_VLAN_CFG_PORT_VID_SET(port->vid), + REW_PORT_VLAN_CFG_PORT_VID, + sparx5, + REW_PORT_VLAN_CFG(port->portno)); +} diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 04d067243457..fff78900fc8a 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1230,8 +1230,10 @@ static int mana_create_txq(struct mana_port_context *apc, cq->gdma_id = cq->gdma_cq->id; - if (WARN_ON(cq->gdma_id >= gc->max_num_cqs)) - return -EINVAL; + if (WARN_ON(cq->gdma_id >= gc->max_num_cqs)) { + err = -EINVAL; + goto out; + } gc->cq_table[cq->gdma_id] = cq->gdma_cq; @@ -1387,8 +1389,7 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, gc = gd->gdma_context; - rxq = kzalloc(sizeof(*rxq) + - RX_BUFFERS_PER_QUEUE * sizeof(struct mana_recv_buf_oob), + rxq = kzalloc(struct_size(rxq, rx_oobs, RX_BUFFERS_PER_QUEUE), GFP_KERNEL); if (!rxq) return NULL; diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index b85733942053..5249b64f4fc5 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -481,13 +481,12 @@ static int moxart_mac_probe(struct platform_device *pdev) priv->ndev = ndev; priv->pdev = pdev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ndev->base_addr = res->start; - priv->base = devm_ioremap_resource(p_dev, res); + priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(priv->base)) { ret = PTR_ERR(priv->base); goto init_fail; } + ndev->base_addr = res->start; spin_lock_init(&priv->txlock); diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index aad33d22c33f..3e89e34f86d5 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -939,7 +939,7 @@ static void ocelot_port_attr_mc_set(struct ocelot *ocelot, int port, bool mc) ANA_PORT_CPU_FWD_CFG, port); } -static int ocelot_port_attr_set(struct net_device *dev, +static int ocelot_port_attr_set(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { @@ -948,6 +948,9 @@ static int ocelot_port_attr_set(struct net_device *dev, int port = priv->chip_port; int err = 0; + if (ctx && ctx != priv) + return 0; + switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: ocelot_port_attr_stp_state_set(ocelot, port, attr->u.stp_state); @@ -1058,12 +1061,16 @@ ocelot_port_obj_mrp_del_ring_role(struct net_device *dev, return ocelot_mrp_del_ring_role(ocelot, port, mrp); } -static int ocelot_port_obj_add(struct net_device *dev, +static int ocelot_port_obj_add(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { + struct ocelot_port_private *priv = netdev_priv(dev); int ret = 0; + if (ctx && ctx != priv) + return 0; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: ret = ocelot_port_obj_add_vlan(dev, @@ -1086,11 +1093,15 @@ static int ocelot_port_obj_add(struct net_device *dev, return ret; } -static int ocelot_port_obj_del(struct net_device *dev, +static int ocelot_port_obj_del(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj) { + struct ocelot_port_private *priv = netdev_priv(dev); int ret = 0; + if (ctx && ctx != priv) + return 0; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: ret = ocelot_vlan_vid_del(dev, @@ -1143,10 +1154,14 @@ static int ocelot_switchdev_sync(struct ocelot *ocelot, int port, struct net_device *bridge_dev, struct netlink_ext_ack *extack) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct ocelot_port_private *priv; clock_t ageing_time; u8 stp_state; int err; + priv = container_of(ocelot_port, struct ocelot_port_private, port); + ocelot_inherit_brport_flags(ocelot, port, brport_dev); stp_state = br_port_get_stp_state(brport_dev); @@ -1160,16 +1175,12 @@ static int ocelot_switchdev_sync(struct ocelot *ocelot, int port, ageing_time = br_get_ageing_time(bridge_dev); ocelot_port_attr_ageing_set(ocelot, port, ageing_time); - err = br_mdb_replay(bridge_dev, brport_dev, + err = br_mdb_replay(bridge_dev, brport_dev, priv, true, &ocelot_switchdev_blocking_nb, extack); if (err && err != -EOPNOTSUPP) return err; - err = br_fdb_replay(bridge_dev, brport_dev, &ocelot_switchdev_nb); - if (err) - return err; - - err = br_vlan_replay(bridge_dev, brport_dev, + err = br_vlan_replay(bridge_dev, brport_dev, priv, true, &ocelot_switchdev_blocking_nb, extack); if (err && err != -EOPNOTSUPP) return err; diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c index b81e1487945c..51b4b25d15ad 100644 --- a/drivers/net/ethernet/natsemi/natsemi.c +++ b/drivers/net/ethernet/natsemi/natsemi.c @@ -969,7 +969,7 @@ static int natsemi_probe1(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; err_create_file: - unregister_netdev(dev); + unregister_netdev(dev); err_register_netdev: iounmap(ioaddr); @@ -3103,14 +3103,14 @@ static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) case SIOCSMIIREG: /* Write MII PHY register. */ if (dev->if_port == PORT_TP) { if ((data->phy_id & 0x1f) == np->phy_addr_external) { - if ((data->reg_num & 0x1f) == MII_ADVERTISE) + if ((data->reg_num & 0x1f) == MII_ADVERTISE) np->advertising = data->val_in; mdio_write(dev, data->reg_num & 0x1f, data->val_in); } } else { if ((data->phy_id & 0x1f) == np->phy_addr_external) { - if ((data->reg_num & 0x1f) == MII_ADVERTISE) + if ((data->reg_num & 0x1f) == MII_ADVERTISE) np->advertising = data->val_in; } move_int_phy(dev, data->phy_id & 0x1f); diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 9cfcd5500462..0b017d4f5c08 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -1101,6 +1101,8 @@ static int s2io_print_pci_mode(struct s2io_nic *nic) * @nic: device private variable * @link: link status (UP/DOWN) used to enable/disable continuous * transmit interrupts + * @may_sleep: parameter indicates if sleeping when waiting for + * command complete * Description: The function configures transmit traffic interrupts * Return Value: SUCCESS on success and * '-1' on failure @@ -2743,7 +2745,7 @@ static int s2io_chk_rx_buffers(struct s2io_nic *nic, struct ring_info *ring) } /** - * s2io_poll - Rx interrupt handler for NAPI support + * s2io_poll_msix - Rx interrupt handler for NAPI support * @napi : pointer to the napi structure. * @budget : The number of packets that were budgeted to be processed * during one pass through the 'Poll" function. @@ -3323,6 +3325,8 @@ static void s2io_updt_xpak_counter(struct net_device *dev) * @addr: address * @busy_bit: bit to check for busy * @bit_state: state to check + * @may_sleep: parameter indicates if sleeping when waiting for + * command complete * Description: Function that waits for a command to Write into RMAC * ADDR DATA registers to be completed and returns either success or * error depending on whether the command was complete or not. @@ -4868,6 +4872,8 @@ static struct net_device_stats *s2io_get_stats(struct net_device *dev) /** * s2io_set_multicast - entry point for multicast address enable/disable. * @dev : pointer to the device structure + * @may_sleep: parameter indicates if sleeping when waiting for command + * complete * Description: * This function is a driver entry point which gets called by the kernel * whenever multicast addresses must be enabled/disabled. This also gets @@ -5288,7 +5294,7 @@ s2io_ethtool_set_link_ksettings(struct net_device *dev, } /** - * s2io_ethtol_get_link_ksettings - Return link specific information. + * s2io_ethtool_get_link_ksettings - Return link specific information. * @dev: pointer to netdev * @cmd : pointer to the structure with parameters given by ethtool * to return link information. diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index b47d74743f5a..a3204a7ef750 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -4885,7 +4885,7 @@ vpath_open_exit1: } /** - * vxge_hw_vpath_rx_doorbell_post - Close the handle got from previous vpath + * vxge_hw_vpath_rx_doorbell_init - Close the handle got from previous vpath * (vpath) open * @vp: Handle got from previous vpath open * diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 87892bd992b1..82eef4c72f01 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -87,7 +87,7 @@ static unsigned int bw_percentage[VXGE_HW_MAX_VIRTUAL_PATHS] = module_param_array(bw_percentage, uint, NULL, 0); static struct vxge_drv_config *driver_config; -static enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev); +static void vxge_reset_all_vpaths(struct vxgedev *vdev); static inline int is_vxge_card_up(struct vxgedev *vdev) { @@ -1606,7 +1606,6 @@ static void vxge_config_ci_for_tti_rti(struct vxgedev *vdev) static int do_vxge_reset(struct vxgedev *vdev, int event) { - enum vxge_hw_status status; int ret = 0, vp_id, i; vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__); @@ -1709,14 +1708,7 @@ static int do_vxge_reset(struct vxgedev *vdev, int event) netif_tx_stop_all_queues(vdev->ndev); if (event == VXGE_LL_FULL_RESET) { - status = vxge_reset_all_vpaths(vdev); - if (status != VXGE_HW_OK) { - vxge_debug_init(VXGE_ERR, - "fatal: %s: can not reset vpaths", - vdev->ndev->name); - ret = -EPERM; - goto out; - } + vxge_reset_all_vpaths(vdev); } if (event == VXGE_LL_COMPL_RESET) { @@ -1799,7 +1791,7 @@ static void vxge_reset(struct work_struct *work) } /** - * vxge_poll - Receive handler when Receive Polling is used. + * vxge_poll_msix - Receive handler when Receive Polling is used. * @napi: pointer to the napi structure. * @budget: Number of packets budgeted to be processed in this iteration. * @@ -1969,9 +1961,8 @@ static enum vxge_hw_status vxge_rth_configure(struct vxgedev *vdev) } /* reset vpaths */ -static enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev) +static void vxge_reset_all_vpaths(struct vxgedev *vdev) { - enum vxge_hw_status status = VXGE_HW_OK; struct vxge_vpath *vpath; int i; @@ -1986,18 +1977,16 @@ static enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev) "vxge_hw_vpath_recover_" "from_reset failed for vpath: " "%d", i); - return status; + return; } } else { vxge_debug_init(VXGE_ERR, "vxge_hw_vpath_reset failed for " "vpath:%d", i); - return status; + return; } } } - - return status; } /* close vpaths */ @@ -2676,11 +2665,7 @@ static int vxge_set_features(struct net_device *dev, netdev_features_t features) /* !netif_running() ensured by vxge_fix_features() */ vdev->devh->config.rth_en = !!(features & NETIF_F_RXHASH); - if (vxge_reset_all_vpaths(vdev) != VXGE_HW_OK) { - dev->features = features ^ NETIF_F_RXHASH; - vdev->devh->config.rth_en = !!(dev->features & NETIF_F_RXHASH); - return -EIO; - } + vxge_reset_all_vpaths(vdev); return 0; } @@ -3693,10 +3678,9 @@ static int vxge_config_vpaths(struct vxge_hw_device_config *device_config, driver_config->vpath_per_dev = 1; for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) - if (!vxge_bVALn(vpath_mask, i, 1)) - continue; - else + if (vxge_bVALn(vpath_mask, i, 1)) default_no_vpath++; + if (default_no_vpath < driver_config->vpath_per_dev) driver_config->vpath_per_dev = default_no_vpath; @@ -4752,7 +4736,7 @@ _exit0: } /** - * vxge_rem_nic - Free the PCI device + * vxge_remove - Free the PCI device * @pdev: structure containing the PCI related information of the device. * Description: This function is called by the Pci subsystem to release a * PCI device and free up all resource held up by the device. diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile index d31772ae511d..9cff3d48acbc 100644 --- a/drivers/net/ethernet/netronome/nfp/Makefile +++ b/drivers/net/ethernet/netronome/nfp/Makefile @@ -51,7 +51,8 @@ nfp-objs += \ flower/metadata.o \ flower/offload.o \ flower/tunnel_conf.o \ - flower/qos_conf.o + flower/qos_conf.o \ + flower/conntrack.o endif ifeq ($(CONFIG_BPF_SYSCALL),y) diff --git a/drivers/net/ethernet/netronome/nfp/ccm_mbox.c b/drivers/net/ethernet/netronome/nfp/ccm_mbox.c index f0783aa9e66e..4247bca09807 100644 --- a/drivers/net/ethernet/netronome/nfp/ccm_mbox.c +++ b/drivers/net/ethernet/netronome/nfp/ccm_mbox.c @@ -36,7 +36,7 @@ enum nfp_net_mbox_cmsg_state { }; /** - * struct nfp_ccm_mbox_skb_cb - CCM mailbox specific info + * struct nfp_ccm_mbox_cmsg_cb - CCM mailbox specific info * @state: processing state (/stage) of the message * @err: error encountered during processing if any * @max_len: max(request_len, reply_len) diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.c b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c new file mode 100644 index 000000000000..273d529d43c2 --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.c @@ -0,0 +1,1180 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2021 Corigine, Inc. */ + +#include "conntrack.h" + +const struct rhashtable_params nfp_tc_ct_merge_params = { + .head_offset = offsetof(struct nfp_fl_ct_tc_merge, + hash_node), + .key_len = sizeof(unsigned long) * 2, + .key_offset = offsetof(struct nfp_fl_ct_tc_merge, cookie), + .automatic_shrinking = true, +}; + +const struct rhashtable_params nfp_nft_ct_merge_params = { + .head_offset = offsetof(struct nfp_fl_nft_tc_merge, + hash_node), + .key_len = sizeof(unsigned long) * 3, + .key_offset = offsetof(struct nfp_fl_nft_tc_merge, cookie), + .automatic_shrinking = true, +}; + +static struct flow_action_entry *get_flow_act(struct flow_rule *rule, + enum flow_action_id act_id); + +/** + * get_hashentry() - Wrapper around hashtable lookup. + * @ht: hashtable where entry could be found + * @key: key to lookup + * @params: hashtable params + * @size: size of entry to allocate if not in table + * + * Returns an entry from a hashtable. If entry does not exist + * yet allocate the memory for it and return the new entry. + */ +static void *get_hashentry(struct rhashtable *ht, void *key, + const struct rhashtable_params params, size_t size) +{ + void *result; + + result = rhashtable_lookup_fast(ht, key, params); + + if (result) + return result; + + result = kzalloc(size, GFP_KERNEL); + if (!result) + return ERR_PTR(-ENOMEM); + + return result; +} + +bool is_pre_ct_flow(struct flow_cls_offload *flow) +{ + struct flow_action_entry *act; + int i; + + flow_action_for_each(i, act, &flow->rule->action) { + if (act->id == FLOW_ACTION_CT && !act->ct.action) + return true; + } + return false; +} + +bool is_post_ct_flow(struct flow_cls_offload *flow) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(flow); + struct flow_dissector *dissector = rule->match.dissector; + struct flow_match_ct ct; + + if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT)) { + flow_rule_match_ct(rule, &ct); + if (ct.key->ct_state & TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED) + return true; + } + return false; +} + +static int nfp_ct_merge_check(struct nfp_fl_ct_flow_entry *entry1, + struct nfp_fl_ct_flow_entry *entry2) +{ + unsigned int ovlp_keys = entry1->rule->match.dissector->used_keys & + entry2->rule->match.dissector->used_keys; + bool out; + + /* check the overlapped fields one by one, the unmasked part + * should not conflict with each other. + */ + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match1, match2; + + flow_rule_match_control(entry1->rule, &match1); + flow_rule_match_control(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match1, match2; + + flow_rule_match_basic(entry1->rule, &match1); + flow_rule_match_basic(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + struct flow_match_ipv4_addrs match1, match2; + + flow_rule_match_ipv4_addrs(entry1->rule, &match1); + flow_rule_match_ipv4_addrs(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + struct flow_match_ipv6_addrs match1, match2; + + flow_rule_match_ipv6_addrs(entry1->rule, &match1); + flow_rule_match_ipv6_addrs(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match1, match2; + + flow_rule_match_ports(entry1->rule, &match1); + flow_rule_match_ports(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match1, match2; + + flow_rule_match_eth_addrs(entry1->rule, &match1); + flow_rule_match_eth_addrs(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match1, match2; + + flow_rule_match_vlan(entry1->rule, &match1); + flow_rule_match_vlan(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_MPLS)) { + struct flow_match_mpls match1, match2; + + flow_rule_match_mpls(entry1->rule, &match1); + flow_rule_match_mpls(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_TCP)) { + struct flow_match_tcp match1, match2; + + flow_rule_match_tcp(entry1->rule, &match1); + flow_rule_match_tcp(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_IP)) { + struct flow_match_ip match1, match2; + + flow_rule_match_ip(entry1->rule, &match1); + flow_rule_match_ip(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid match1, match2; + + flow_rule_match_enc_keyid(entry1->rule, &match1); + flow_rule_match_enc_keyid(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { + struct flow_match_ipv4_addrs match1, match2; + + flow_rule_match_enc_ipv4_addrs(entry1->rule, &match1); + flow_rule_match_enc_ipv4_addrs(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { + struct flow_match_ipv6_addrs match1, match2; + + flow_rule_match_enc_ipv6_addrs(entry1->rule, &match1); + flow_rule_match_enc_ipv6_addrs(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL)) { + struct flow_match_control match1, match2; + + flow_rule_match_enc_control(entry1->rule, &match1); + flow_rule_match_enc_control(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_IP)) { + struct flow_match_ip match1, match2; + + flow_rule_match_enc_ip(entry1->rule, &match1); + flow_rule_match_enc_ip(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + if (ovlp_keys & BIT(FLOW_DISSECTOR_KEY_ENC_OPTS)) { + struct flow_match_enc_opts match1, match2; + + flow_rule_match_enc_opts(entry1->rule, &match1); + flow_rule_match_enc_opts(entry2->rule, &match2); + COMPARE_UNMASKED_FIELDS(match1, match2, &out); + if (out) + goto check_failed; + } + + return 0; + +check_failed: + return -EINVAL; +} + +static int nfp_ct_check_mangle_merge(struct flow_action_entry *a_in, + struct flow_rule *rule) +{ + enum flow_action_mangle_base htype = a_in->mangle.htype; + u32 offset = a_in->mangle.offset; + + switch (htype) { + case FLOW_ACT_MANGLE_HDR_TYPE_ETH: + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) + return -EOPNOTSUPP; + break; + case FLOW_ACT_MANGLE_HDR_TYPE_IP4: + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) { + struct flow_match_ip match; + + flow_rule_match_ip(rule, &match); + if (offset == offsetof(struct iphdr, ttl) && + match.mask->ttl) + return -EOPNOTSUPP; + if (offset == round_down(offsetof(struct iphdr, tos), 4) && + match.mask->tos) + return -EOPNOTSUPP; + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(rule, &match); + if (offset == offsetof(struct iphdr, saddr) && + match.mask->src) + return -EOPNOTSUPP; + if (offset == offsetof(struct iphdr, daddr) && + match.mask->dst) + return -EOPNOTSUPP; + } + break; + case FLOW_ACT_MANGLE_HDR_TYPE_IP6: + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) { + struct flow_match_ip match; + + flow_rule_match_ip(rule, &match); + if (offset == round_down(offsetof(struct ipv6hdr, hop_limit), 4) && + match.mask->ttl) + return -EOPNOTSUPP; + /* for ipv6, tos and flow_lbl are in the same word */ + if (offset == round_down(offsetof(struct ipv6hdr, flow_lbl), 4) && + match.mask->tos) + return -EOPNOTSUPP; + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); + if (offset >= offsetof(struct ipv6hdr, saddr) && + offset < offsetof(struct ipv6hdr, daddr) && + memchr_inv(&match.mask->src, 0, sizeof(match.mask->src))) + return -EOPNOTSUPP; + if (offset >= offsetof(struct ipv6hdr, daddr) && + offset < sizeof(struct ipv6hdr) && + memchr_inv(&match.mask->dst, 0, sizeof(match.mask->dst))) + return -EOPNOTSUPP; + } + break; + case FLOW_ACT_MANGLE_HDR_TYPE_TCP: + case FLOW_ACT_MANGLE_HDR_TYPE_UDP: + /* currently only can modify ports */ + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) + return -EOPNOTSUPP; + break; + default: + break; + } + return 0; +} + +static int nfp_ct_merge_act_check(struct nfp_fl_ct_flow_entry *pre_ct_entry, + struct nfp_fl_ct_flow_entry *post_ct_entry, + struct nfp_fl_ct_flow_entry *nft_entry) +{ + struct flow_action_entry *act; + int err, i; + + /* Check for pre_ct->action conflicts */ + flow_action_for_each(i, act, &pre_ct_entry->rule->action) { + switch (act->id) { + case FLOW_ACTION_MANGLE: + err = nfp_ct_check_mangle_merge(act, nft_entry->rule); + if (err) + return err; + err = nfp_ct_check_mangle_merge(act, post_ct_entry->rule); + if (err) + return err; + break; + case FLOW_ACTION_VLAN_PUSH: + case FLOW_ACTION_VLAN_POP: + case FLOW_ACTION_VLAN_MANGLE: + case FLOW_ACTION_MPLS_PUSH: + case FLOW_ACTION_MPLS_POP: + case FLOW_ACTION_MPLS_MANGLE: + return -EOPNOTSUPP; + default: + break; + } + } + + /* Check for nft->action conflicts */ + flow_action_for_each(i, act, &nft_entry->rule->action) { + switch (act->id) { + case FLOW_ACTION_MANGLE: + err = nfp_ct_check_mangle_merge(act, post_ct_entry->rule); + if (err) + return err; + break; + case FLOW_ACTION_VLAN_PUSH: + case FLOW_ACTION_VLAN_POP: + case FLOW_ACTION_VLAN_MANGLE: + case FLOW_ACTION_MPLS_PUSH: + case FLOW_ACTION_MPLS_POP: + case FLOW_ACTION_MPLS_MANGLE: + return -EOPNOTSUPP; + default: + break; + } + } + return 0; +} + +static int nfp_ct_check_meta(struct nfp_fl_ct_flow_entry *post_ct_entry, + struct nfp_fl_ct_flow_entry *nft_entry) +{ + struct flow_dissector *dissector = post_ct_entry->rule->match.dissector; + struct flow_action_entry *ct_met; + struct flow_match_ct ct; + int i; + + ct_met = get_flow_act(nft_entry->rule, FLOW_ACTION_CT_METADATA); + if (ct_met && (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT))) { + u32 *act_lbl; + + act_lbl = ct_met->ct_metadata.labels; + flow_rule_match_ct(post_ct_entry->rule, &ct); + for (i = 0; i < 4; i++) { + if ((ct.key->ct_labels[i] & ct.mask->ct_labels[i]) ^ + (act_lbl[i] & ct.mask->ct_labels[i])) + return -EINVAL; + } + + if ((ct.key->ct_mark & ct.mask->ct_mark) ^ + (ct_met->ct_metadata.mark & ct.mask->ct_mark)) + return -EINVAL; + + return 0; + } + + return -EINVAL; +} + +static int nfp_fl_ct_add_offload(struct nfp_fl_nft_tc_merge *m_entry) +{ + return 0; +} + +static int nfp_fl_ct_del_offload(struct nfp_app *app, unsigned long cookie, + struct net_device *netdev) +{ + return 0; +} + +static int nfp_ct_do_nft_merge(struct nfp_fl_ct_zone_entry *zt, + struct nfp_fl_ct_flow_entry *nft_entry, + struct nfp_fl_ct_tc_merge *tc_m_entry) +{ + struct nfp_fl_ct_flow_entry *post_ct_entry, *pre_ct_entry; + struct nfp_fl_nft_tc_merge *nft_m_entry; + unsigned long new_cookie[3]; + int err; + + pre_ct_entry = tc_m_entry->pre_ct_parent; + post_ct_entry = tc_m_entry->post_ct_parent; + + err = nfp_ct_merge_act_check(pre_ct_entry, post_ct_entry, nft_entry); + if (err) + return err; + + /* Check that the two tc flows are also compatible with + * the nft entry. No need to check the pre_ct and post_ct + * entries as that was already done during pre_merge. + * The nft entry does not have a netdev or chain populated, so + * skip this check. + */ + err = nfp_ct_merge_check(pre_ct_entry, nft_entry); + if (err) + return err; + err = nfp_ct_merge_check(post_ct_entry, nft_entry); + if (err) + return err; + err = nfp_ct_check_meta(post_ct_entry, nft_entry); + if (err) + return err; + + /* Combine tc_merge and nft cookies for this cookie. */ + new_cookie[0] = tc_m_entry->cookie[0]; + new_cookie[1] = tc_m_entry->cookie[1]; + new_cookie[2] = nft_entry->cookie; + nft_m_entry = get_hashentry(&zt->nft_merge_tb, + &new_cookie, + nfp_nft_ct_merge_params, + sizeof(*nft_m_entry)); + + if (IS_ERR(nft_m_entry)) + return PTR_ERR(nft_m_entry); + + /* nft_m_entry already present, not merging again */ + if (!memcmp(&new_cookie, nft_m_entry->cookie, sizeof(new_cookie))) + return 0; + + memcpy(&nft_m_entry->cookie, &new_cookie, sizeof(new_cookie)); + nft_m_entry->zt = zt; + nft_m_entry->tc_m_parent = tc_m_entry; + nft_m_entry->nft_parent = nft_entry; + nft_m_entry->tc_flower_cookie = 0; + /* Copy the netdev from one the pre_ct entry. When the tc_m_entry was created + * it only combined them if the netdevs were the same, so can use any of them. + */ + nft_m_entry->netdev = pre_ct_entry->netdev; + + /* Add this entry to the tc_m_list and nft_flow lists */ + list_add(&nft_m_entry->tc_merge_list, &tc_m_entry->children); + list_add(&nft_m_entry->nft_flow_list, &nft_entry->children); + + /* Generate offload structure and send to nfp */ + err = nfp_fl_ct_add_offload(nft_m_entry); + if (err) + goto err_nft_ct_offload; + + err = rhashtable_insert_fast(&zt->nft_merge_tb, &nft_m_entry->hash_node, + nfp_nft_ct_merge_params); + if (err) + goto err_nft_ct_merge_insert; + + zt->nft_merge_count++; + + return err; + +err_nft_ct_merge_insert: + nfp_fl_ct_del_offload(zt->priv->app, nft_m_entry->tc_flower_cookie, + nft_m_entry->netdev); +err_nft_ct_offload: + list_del(&nft_m_entry->tc_merge_list); + list_del(&nft_m_entry->nft_flow_list); + kfree(nft_m_entry); + return err; +} + +static int nfp_ct_do_tc_merge(struct nfp_fl_ct_zone_entry *zt, + struct nfp_fl_ct_flow_entry *ct_entry1, + struct nfp_fl_ct_flow_entry *ct_entry2) +{ + struct nfp_fl_ct_flow_entry *post_ct_entry, *pre_ct_entry; + struct nfp_fl_ct_flow_entry *nft_entry, *nft_tmp; + struct nfp_fl_ct_tc_merge *m_entry; + unsigned long new_cookie[2]; + int err; + + if (ct_entry1->type == CT_TYPE_PRE_CT) { + pre_ct_entry = ct_entry1; + post_ct_entry = ct_entry2; + } else { + post_ct_entry = ct_entry1; + pre_ct_entry = ct_entry2; + } + + if (post_ct_entry->netdev != pre_ct_entry->netdev) + return -EINVAL; + /* Checks that the chain_index of the filter matches the + * chain_index of the GOTO action. + */ + if (post_ct_entry->chain_index != pre_ct_entry->chain_index) + return -EINVAL; + + err = nfp_ct_merge_check(post_ct_entry, pre_ct_entry); + if (err) + return err; + + new_cookie[0] = pre_ct_entry->cookie; + new_cookie[1] = post_ct_entry->cookie; + m_entry = get_hashentry(&zt->tc_merge_tb, &new_cookie, + nfp_tc_ct_merge_params, sizeof(*m_entry)); + if (IS_ERR(m_entry)) + return PTR_ERR(m_entry); + + /* m_entry already present, not merging again */ + if (!memcmp(&new_cookie, m_entry->cookie, sizeof(new_cookie))) + return 0; + + memcpy(&m_entry->cookie, &new_cookie, sizeof(new_cookie)); + m_entry->zt = zt; + m_entry->post_ct_parent = post_ct_entry; + m_entry->pre_ct_parent = pre_ct_entry; + + /* Add this entry to the pre_ct and post_ct lists */ + list_add(&m_entry->post_ct_list, &post_ct_entry->children); + list_add(&m_entry->pre_ct_list, &pre_ct_entry->children); + INIT_LIST_HEAD(&m_entry->children); + + err = rhashtable_insert_fast(&zt->tc_merge_tb, &m_entry->hash_node, + nfp_tc_ct_merge_params); + if (err) + goto err_ct_tc_merge_insert; + zt->tc_merge_count++; + + /* Merge with existing nft flows */ + list_for_each_entry_safe(nft_entry, nft_tmp, &zt->nft_flows_list, + list_node) { + nfp_ct_do_nft_merge(zt, nft_entry, m_entry); + } + + return 0; + +err_ct_tc_merge_insert: + list_del(&m_entry->post_ct_list); + list_del(&m_entry->pre_ct_list); + kfree(m_entry); + return err; +} + +static struct +nfp_fl_ct_zone_entry *get_nfp_zone_entry(struct nfp_flower_priv *priv, + u16 zone, bool wildcarded) +{ + struct nfp_fl_ct_zone_entry *zt; + int err; + + if (wildcarded && priv->ct_zone_wc) + return priv->ct_zone_wc; + + if (!wildcarded) { + zt = get_hashentry(&priv->ct_zone_table, &zone, + nfp_zone_table_params, sizeof(*zt)); + + /* If priv is set this is an existing entry, just return it */ + if (IS_ERR(zt) || zt->priv) + return zt; + } else { + zt = kzalloc(sizeof(*zt), GFP_KERNEL); + if (!zt) + return ERR_PTR(-ENOMEM); + } + + zt->zone = zone; + zt->priv = priv; + zt->nft = NULL; + + /* init the various hash tables and lists*/ + INIT_LIST_HEAD(&zt->pre_ct_list); + INIT_LIST_HEAD(&zt->post_ct_list); + INIT_LIST_HEAD(&zt->nft_flows_list); + + err = rhashtable_init(&zt->tc_merge_tb, &nfp_tc_ct_merge_params); + if (err) + goto err_tc_merge_tb_init; + + err = rhashtable_init(&zt->nft_merge_tb, &nfp_nft_ct_merge_params); + if (err) + goto err_nft_merge_tb_init; + + if (wildcarded) { + priv->ct_zone_wc = zt; + } else { + err = rhashtable_insert_fast(&priv->ct_zone_table, + &zt->hash_node, + nfp_zone_table_params); + if (err) + goto err_zone_insert; + } + + return zt; + +err_zone_insert: + rhashtable_destroy(&zt->nft_merge_tb); +err_nft_merge_tb_init: + rhashtable_destroy(&zt->tc_merge_tb); +err_tc_merge_tb_init: + kfree(zt); + return ERR_PTR(err); +} + +static struct +nfp_fl_ct_flow_entry *nfp_fl_ct_add_flow(struct nfp_fl_ct_zone_entry *zt, + struct net_device *netdev, + struct flow_cls_offload *flow, + bool is_nft, struct netlink_ext_ack *extack) +{ + struct nf_flow_match *nft_match = NULL; + struct nfp_fl_ct_flow_entry *entry; + struct nfp_fl_ct_map_entry *map; + struct flow_action_entry *act; + int err, i; + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + return ERR_PTR(-ENOMEM); + + entry->rule = flow_rule_alloc(flow->rule->action.num_entries); + if (!entry->rule) { + err = -ENOMEM; + goto err_pre_ct_rule; + } + + /* nft flows gets destroyed after callback return, so need + * to do a full copy instead of just a reference. + */ + if (is_nft) { + nft_match = kzalloc(sizeof(*nft_match), GFP_KERNEL); + if (!nft_match) { + err = -ENOMEM; + goto err_pre_ct_act; + } + memcpy(&nft_match->dissector, flow->rule->match.dissector, + sizeof(nft_match->dissector)); + memcpy(&nft_match->mask, flow->rule->match.mask, + sizeof(nft_match->mask)); + memcpy(&nft_match->key, flow->rule->match.key, + sizeof(nft_match->key)); + entry->rule->match.dissector = &nft_match->dissector; + entry->rule->match.mask = &nft_match->mask; + entry->rule->match.key = &nft_match->key; + } else { + entry->rule->match.dissector = flow->rule->match.dissector; + entry->rule->match.mask = flow->rule->match.mask; + entry->rule->match.key = flow->rule->match.key; + } + + entry->zt = zt; + entry->netdev = netdev; + entry->cookie = flow->cookie; + entry->chain_index = flow->common.chain_index; + entry->tun_offset = NFP_FL_CT_NO_TUN; + + /* Copy over action data. Unfortunately we do not get a handle to the + * original tcf_action data, and the flow objects gets destroyed, so we + * cannot just save a pointer to this either, so need to copy over the + * data unfortunately. + */ + entry->rule->action.num_entries = flow->rule->action.num_entries; + flow_action_for_each(i, act, &flow->rule->action) { + struct flow_action_entry *new_act; + + new_act = &entry->rule->action.entries[i]; + memcpy(new_act, act, sizeof(struct flow_action_entry)); + /* Entunnel is a special case, need to allocate and copy + * tunnel info. + */ + if (act->id == FLOW_ACTION_TUNNEL_ENCAP) { + struct ip_tunnel_info *tun = act->tunnel; + size_t tun_size = sizeof(*tun) + tun->options_len; + + new_act->tunnel = kmemdup(tun, tun_size, GFP_ATOMIC); + if (!new_act->tunnel) { + err = -ENOMEM; + goto err_pre_ct_tun_cp; + } + entry->tun_offset = i; + } + } + + INIT_LIST_HEAD(&entry->children); + + /* Now add a ct map entry to flower-priv */ + map = get_hashentry(&zt->priv->ct_map_table, &flow->cookie, + nfp_ct_map_params, sizeof(*map)); + if (IS_ERR(map)) { + NL_SET_ERR_MSG_MOD(extack, + "offload error: ct map entry creation failed"); + err = -ENOMEM; + goto err_ct_flow_insert; + } + map->cookie = flow->cookie; + map->ct_entry = entry; + err = rhashtable_insert_fast(&zt->priv->ct_map_table, + &map->hash_node, + nfp_ct_map_params); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "offload error: ct map entry table add failed"); + goto err_map_insert; + } + + return entry; + +err_map_insert: + kfree(map); +err_ct_flow_insert: + if (entry->tun_offset != NFP_FL_CT_NO_TUN) + kfree(entry->rule->action.entries[entry->tun_offset].tunnel); +err_pre_ct_tun_cp: + kfree(nft_match); +err_pre_ct_act: + kfree(entry->rule); +err_pre_ct_rule: + kfree(entry); + return ERR_PTR(err); +} + +static void cleanup_nft_merge_entry(struct nfp_fl_nft_tc_merge *m_entry) +{ + struct nfp_fl_ct_zone_entry *zt; + int err; + + zt = m_entry->zt; + + /* Flow is in HW, need to delete */ + if (m_entry->tc_flower_cookie) { + err = nfp_fl_ct_del_offload(zt->priv->app, m_entry->tc_flower_cookie, + m_entry->netdev); + if (err) + return; + } + + WARN_ON_ONCE(rhashtable_remove_fast(&zt->nft_merge_tb, + &m_entry->hash_node, + nfp_nft_ct_merge_params)); + zt->nft_merge_count--; + list_del(&m_entry->tc_merge_list); + list_del(&m_entry->nft_flow_list); + + kfree(m_entry); +} + +static void nfp_free_nft_merge_children(void *entry, bool is_nft_flow) +{ + struct nfp_fl_nft_tc_merge *m_entry, *tmp; + + /* These post entries are parts of two lists, one is a list of nft_entries + * and the other is of from a list of tc_merge structures. Iterate + * through the relevant list and cleanup the entries. + */ + + if (is_nft_flow) { + /* Need to iterate through list of nft_flow entries*/ + struct nfp_fl_ct_flow_entry *ct_entry = entry; + + list_for_each_entry_safe(m_entry, tmp, &ct_entry->children, + nft_flow_list) { + cleanup_nft_merge_entry(m_entry); + } + } else { + /* Need to iterate through list of tc_merged_flow entries*/ + struct nfp_fl_ct_tc_merge *ct_entry = entry; + + list_for_each_entry_safe(m_entry, tmp, &ct_entry->children, + tc_merge_list) { + cleanup_nft_merge_entry(m_entry); + } + } +} + +static void nfp_del_tc_merge_entry(struct nfp_fl_ct_tc_merge *m_ent) +{ + struct nfp_fl_ct_zone_entry *zt; + int err; + + zt = m_ent->zt; + err = rhashtable_remove_fast(&zt->tc_merge_tb, + &m_ent->hash_node, + nfp_tc_ct_merge_params); + if (err) + pr_warn("WARNING: could not remove merge_entry from hashtable\n"); + zt->tc_merge_count--; + list_del(&m_ent->post_ct_list); + list_del(&m_ent->pre_ct_list); + + if (!list_empty(&m_ent->children)) + nfp_free_nft_merge_children(m_ent, false); + kfree(m_ent); +} + +static void nfp_free_tc_merge_children(struct nfp_fl_ct_flow_entry *entry) +{ + struct nfp_fl_ct_tc_merge *m_ent, *tmp; + + switch (entry->type) { + case CT_TYPE_PRE_CT: + list_for_each_entry_safe(m_ent, tmp, &entry->children, pre_ct_list) { + nfp_del_tc_merge_entry(m_ent); + } + break; + case CT_TYPE_POST_CT: + list_for_each_entry_safe(m_ent, tmp, &entry->children, post_ct_list) { + nfp_del_tc_merge_entry(m_ent); + } + break; + default: + break; + } +} + +void nfp_fl_ct_clean_flow_entry(struct nfp_fl_ct_flow_entry *entry) +{ + list_del(&entry->list_node); + + if (!list_empty(&entry->children)) { + if (entry->type == CT_TYPE_NFT) + nfp_free_nft_merge_children(entry, true); + else + nfp_free_tc_merge_children(entry); + } + + if (entry->tun_offset != NFP_FL_CT_NO_TUN) + kfree(entry->rule->action.entries[entry->tun_offset].tunnel); + + if (entry->type == CT_TYPE_NFT) { + struct nf_flow_match *nft_match; + + nft_match = container_of(entry->rule->match.dissector, + struct nf_flow_match, dissector); + kfree(nft_match); + } + + kfree(entry->rule); + kfree(entry); +} + +static struct flow_action_entry *get_flow_act(struct flow_rule *rule, + enum flow_action_id act_id) +{ + struct flow_action_entry *act = NULL; + int i; + + flow_action_for_each(i, act, &rule->action) { + if (act->id == act_id) + return act; + } + return NULL; +} + +static void +nfp_ct_merge_tc_entries(struct nfp_fl_ct_flow_entry *ct_entry1, + struct nfp_fl_ct_zone_entry *zt_src, + struct nfp_fl_ct_zone_entry *zt_dst) +{ + struct nfp_fl_ct_flow_entry *ct_entry2, *ct_tmp; + struct list_head *ct_list; + + if (ct_entry1->type == CT_TYPE_PRE_CT) + ct_list = &zt_src->post_ct_list; + else if (ct_entry1->type == CT_TYPE_POST_CT) + ct_list = &zt_src->pre_ct_list; + else + return; + + list_for_each_entry_safe(ct_entry2, ct_tmp, ct_list, + list_node) { + nfp_ct_do_tc_merge(zt_dst, ct_entry2, ct_entry1); + } +} + +static void +nfp_ct_merge_nft_with_tc(struct nfp_fl_ct_flow_entry *nft_entry, + struct nfp_fl_ct_zone_entry *zt) +{ + struct nfp_fl_ct_tc_merge *tc_merge_entry; + struct rhashtable_iter iter; + + rhashtable_walk_enter(&zt->tc_merge_tb, &iter); + rhashtable_walk_start(&iter); + while ((tc_merge_entry = rhashtable_walk_next(&iter)) != NULL) { + if (IS_ERR(tc_merge_entry)) + continue; + rhashtable_walk_stop(&iter); + nfp_ct_do_nft_merge(zt, nft_entry, tc_merge_entry); + rhashtable_walk_start(&iter); + } + rhashtable_walk_stop(&iter); + rhashtable_walk_exit(&iter); +} + +int nfp_fl_ct_handle_pre_ct(struct nfp_flower_priv *priv, + struct net_device *netdev, + struct flow_cls_offload *flow, + struct netlink_ext_ack *extack) +{ + struct flow_action_entry *ct_act, *ct_goto; + struct nfp_fl_ct_flow_entry *ct_entry; + struct nfp_fl_ct_zone_entry *zt; + int err; + + ct_act = get_flow_act(flow->rule, FLOW_ACTION_CT); + if (!ct_act) { + NL_SET_ERR_MSG_MOD(extack, + "unsupported offload: Conntrack action empty in conntrack offload"); + return -EOPNOTSUPP; + } + + ct_goto = get_flow_act(flow->rule, FLOW_ACTION_GOTO); + if (!ct_goto) { + NL_SET_ERR_MSG_MOD(extack, + "unsupported offload: Conntrack requires ACTION_GOTO"); + return -EOPNOTSUPP; + } + + zt = get_nfp_zone_entry(priv, ct_act->ct.zone, false); + if (IS_ERR(zt)) { + NL_SET_ERR_MSG_MOD(extack, + "offload error: Could not create zone table entry"); + return PTR_ERR(zt); + } + + if (!zt->nft) { + zt->nft = ct_act->ct.flow_table; + err = nf_flow_table_offload_add_cb(zt->nft, nfp_fl_ct_handle_nft_flow, zt); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "offload error: Could not register nft_callback"); + return err; + } + } + + /* Add entry to pre_ct_list */ + ct_entry = nfp_fl_ct_add_flow(zt, netdev, flow, false, extack); + if (IS_ERR(ct_entry)) + return PTR_ERR(ct_entry); + ct_entry->type = CT_TYPE_PRE_CT; + ct_entry->chain_index = ct_goto->chain_index; + list_add(&ct_entry->list_node, &zt->pre_ct_list); + zt->pre_ct_count++; + + nfp_ct_merge_tc_entries(ct_entry, zt, zt); + + /* Need to check and merge with tables in the wc_zone as well */ + if (priv->ct_zone_wc) + nfp_ct_merge_tc_entries(ct_entry, priv->ct_zone_wc, zt); + + return 0; +} + +int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv, + struct net_device *netdev, + struct flow_cls_offload *flow, + struct netlink_ext_ack *extack) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(flow); + struct nfp_fl_ct_flow_entry *ct_entry; + struct nfp_fl_ct_zone_entry *zt; + bool wildcarded = false; + struct flow_match_ct ct; + + flow_rule_match_ct(rule, &ct); + if (!ct.mask->ct_zone) { + wildcarded = true; + } else if (ct.mask->ct_zone != U16_MAX) { + NL_SET_ERR_MSG_MOD(extack, + "unsupported offload: partially wildcarded ct_zone is not supported"); + return -EOPNOTSUPP; + } + + zt = get_nfp_zone_entry(priv, ct.key->ct_zone, wildcarded); + if (IS_ERR(zt)) { + NL_SET_ERR_MSG_MOD(extack, + "offload error: Could not create zone table entry"); + return PTR_ERR(zt); + } + + /* Add entry to post_ct_list */ + ct_entry = nfp_fl_ct_add_flow(zt, netdev, flow, false, extack); + if (IS_ERR(ct_entry)) + return PTR_ERR(ct_entry); + + ct_entry->type = CT_TYPE_POST_CT; + ct_entry->chain_index = flow->common.chain_index; + list_add(&ct_entry->list_node, &zt->post_ct_list); + zt->post_ct_count++; + + if (wildcarded) { + /* Iterate through all zone tables if not empty, look for merges with + * pre_ct entries and merge them. + */ + struct rhashtable_iter iter; + struct nfp_fl_ct_zone_entry *zone_table; + + rhashtable_walk_enter(&priv->ct_zone_table, &iter); + rhashtable_walk_start(&iter); + while ((zone_table = rhashtable_walk_next(&iter)) != NULL) { + if (IS_ERR(zone_table)) + continue; + rhashtable_walk_stop(&iter); + nfp_ct_merge_tc_entries(ct_entry, zone_table, zone_table); + rhashtable_walk_start(&iter); + } + rhashtable_walk_stop(&iter); + rhashtable_walk_exit(&iter); + } else { + nfp_ct_merge_tc_entries(ct_entry, zt, zt); + } + + return 0; +} + +static int +nfp_fl_ct_offload_nft_flow(struct nfp_fl_ct_zone_entry *zt, struct flow_cls_offload *flow) +{ + struct nfp_fl_ct_map_entry *ct_map_ent; + struct nfp_fl_ct_flow_entry *ct_entry; + struct netlink_ext_ack *extack = NULL; + + ASSERT_RTNL(); + + extack = flow->common.extack; + switch (flow->command) { + case FLOW_CLS_REPLACE: + /* Netfilter can request offload multiple times for the same + * flow - protect against adding duplicates. + */ + ct_map_ent = rhashtable_lookup_fast(&zt->priv->ct_map_table, &flow->cookie, + nfp_ct_map_params); + if (!ct_map_ent) { + ct_entry = nfp_fl_ct_add_flow(zt, NULL, flow, true, extack); + if (IS_ERR(ct_entry)) + return PTR_ERR(ct_entry); + ct_entry->type = CT_TYPE_NFT; + list_add(&ct_entry->list_node, &zt->nft_flows_list); + zt->nft_flows_count++; + nfp_ct_merge_nft_with_tc(ct_entry, zt); + } + return 0; + case FLOW_CLS_DESTROY: + ct_map_ent = rhashtable_lookup_fast(&zt->priv->ct_map_table, &flow->cookie, + nfp_ct_map_params); + return nfp_fl_ct_del_flow(ct_map_ent); + case FLOW_CLS_STATS: + return 0; + default: + break; + } + return -EINVAL; +} + +int nfp_fl_ct_handle_nft_flow(enum tc_setup_type type, void *type_data, void *cb_priv) +{ + struct flow_cls_offload *flow = type_data; + struct nfp_fl_ct_zone_entry *zt = cb_priv; + int err = -EOPNOTSUPP; + + switch (type) { + case TC_SETUP_CLSFLOWER: + rtnl_lock(); + err = nfp_fl_ct_offload_nft_flow(zt, flow); + rtnl_unlock(); + break; + default: + return -EOPNOTSUPP; + } + return err; +} + +static void +nfp_fl_ct_clean_nft_entries(struct nfp_fl_ct_zone_entry *zt) +{ + struct nfp_fl_ct_flow_entry *nft_entry, *ct_tmp; + struct nfp_fl_ct_map_entry *ct_map_ent; + + list_for_each_entry_safe(nft_entry, ct_tmp, &zt->nft_flows_list, + list_node) { + ct_map_ent = rhashtable_lookup_fast(&zt->priv->ct_map_table, + &nft_entry->cookie, + nfp_ct_map_params); + nfp_fl_ct_del_flow(ct_map_ent); + } +} + +int nfp_fl_ct_del_flow(struct nfp_fl_ct_map_entry *ct_map_ent) +{ + struct nfp_fl_ct_flow_entry *ct_entry; + struct nfp_fl_ct_zone_entry *zt; + struct rhashtable *m_table; + + if (!ct_map_ent) + return -ENOENT; + + zt = ct_map_ent->ct_entry->zt; + ct_entry = ct_map_ent->ct_entry; + m_table = &zt->priv->ct_map_table; + + switch (ct_entry->type) { + case CT_TYPE_PRE_CT: + zt->pre_ct_count--; + rhashtable_remove_fast(m_table, &ct_map_ent->hash_node, + nfp_ct_map_params); + nfp_fl_ct_clean_flow_entry(ct_entry); + kfree(ct_map_ent); + + /* If this is the last pre_ct_rule it means that it is + * very likely that the nft table will be cleaned up next, + * as this happens on the removal of the last act_ct flow. + * However we cannot deregister the callback on the removal + * of the last nft flow as this runs into a deadlock situation. + * So deregister the callback on removal of the last pre_ct flow + * and remove any remaining nft flow entries. We also cannot + * save this state and delete the callback later since the + * nft table would already have been freed at that time. + */ + if (!zt->pre_ct_count) { + nf_flow_table_offload_del_cb(zt->nft, + nfp_fl_ct_handle_nft_flow, + zt); + zt->nft = NULL; + nfp_fl_ct_clean_nft_entries(zt); + } + break; + case CT_TYPE_POST_CT: + zt->post_ct_count--; + rhashtable_remove_fast(m_table, &ct_map_ent->hash_node, + nfp_ct_map_params); + nfp_fl_ct_clean_flow_entry(ct_entry); + kfree(ct_map_ent); + break; + case CT_TYPE_NFT: + zt->nft_flows_count--; + rhashtable_remove_fast(m_table, &ct_map_ent->hash_node, + nfp_ct_map_params); + nfp_fl_ct_clean_flow_entry(ct_map_ent->ct_entry); + kfree(ct_map_ent); + default: + break; + } + + return 0; +} diff --git a/drivers/net/ethernet/netronome/nfp/flower/conntrack.h b/drivers/net/ethernet/netronome/nfp/flower/conntrack.h new file mode 100644 index 000000000000..170b6cdb8cd0 --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/flower/conntrack.h @@ -0,0 +1,231 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (C) 2021 Corigine, Inc. */ + +#ifndef __NFP_FLOWER_CONNTRACK_H__ +#define __NFP_FLOWER_CONNTRACK_H__ 1 + +#include +#include "main.h" + +#define NFP_FL_CT_NO_TUN 0xff + +#define COMPARE_UNMASKED_FIELDS(__match1, __match2, __out) \ + do { \ + typeof(__match1) _match1 = (__match1); \ + typeof(__match2) _match2 = (__match2); \ + bool *_out = (__out); \ + int i, size = sizeof(*(_match1).key); \ + char *k1, *m1, *k2, *m2; \ + *_out = false; \ + k1 = (char *)_match1.key; \ + m1 = (char *)_match1.mask; \ + k2 = (char *)_match2.key; \ + m2 = (char *)_match2.mask; \ + for (i = 0; i < size; i++) \ + if ((k1[i] & m1[i] & m2[i]) ^ \ + (k2[i] & m1[i] & m2[i])) { \ + *_out = true; \ + break; \ + } \ + } while (0) \ + +extern const struct rhashtable_params nfp_zone_table_params; +extern const struct rhashtable_params nfp_ct_map_params; +extern const struct rhashtable_params nfp_tc_ct_merge_params; +extern const struct rhashtable_params nfp_nft_ct_merge_params; + +/** + * struct nfp_fl_ct_zone_entry - Zone entry containing conntrack flow information + * @zone: The zone number, used as lookup key in hashtable + * @hash_node: Used by the hashtable + * @priv: Pointer to nfp_flower_priv data + * @nft: Pointer to nf_flowtable for this zone + * + * @pre_ct_list: The pre_ct_list of nfp_fl_ct_flow_entry entries + * @pre_ct_count: Keep count of the number of pre_ct entries + * + * @post_ct_list: The post_ct_list of nfp_fl_ct_flow_entry entries + * @post_ct_count: Keep count of the number of post_ct entries + * + * @tc_merge_tb: The table of merged tc flows + * @tc_merge_count: Keep count of the number of merged tc entries + * + * @nft_flows_list: The list of nft relatednfp_fl_ct_flow_entry entries + * @nft_flows_count: Keep count of the number of nft_flow entries + * + * @nft_merge_tb: The table of merged tc+nft flows + * @nft_merge_count: Keep count of the number of merged tc+nft entries + */ +struct nfp_fl_ct_zone_entry { + u16 zone; + struct rhash_head hash_node; + + struct nfp_flower_priv *priv; + struct nf_flowtable *nft; + + struct list_head pre_ct_list; + unsigned int pre_ct_count; + + struct list_head post_ct_list; + unsigned int post_ct_count; + + struct rhashtable tc_merge_tb; + unsigned int tc_merge_count; + + struct list_head nft_flows_list; + unsigned int nft_flows_count; + + struct rhashtable nft_merge_tb; + unsigned int nft_merge_count; +}; + +enum ct_entry_type { + CT_TYPE_PRE_CT, + CT_TYPE_NFT, + CT_TYPE_POST_CT, +}; + +/** + * struct nfp_fl_ct_flow_entry - Flow entry containing conntrack flow information + * @cookie: Flow cookie, same as original TC flow, used as key + * @list_node: Used by the list + * @chain_index: Chain index of the original flow + * @netdev: netdev structure. + * @type: Type of pre-entry from enum ct_entry_type + * @zt: Reference to the zone table this belongs to + * @children: List of tc_merge flows this flow forms part of + * @rule: Reference to the original TC flow rule + * @stats: Used to cache stats for updating + * @tun_offset: Used to indicate tunnel action offset in action list + */ +struct nfp_fl_ct_flow_entry { + unsigned long cookie; + struct list_head list_node; + u32 chain_index; + enum ct_entry_type type; + struct net_device *netdev; + struct nfp_fl_ct_zone_entry *zt; + struct list_head children; + struct flow_rule *rule; + struct flow_stats stats; + u8 tun_offset; // Set to NFP_FL_CT_NO_TUN if no tun +}; + +/** + * struct nfp_fl_ct_tc_merge - Merge of two flows from tc + * @cookie: Flow cookie, combination of pre and post ct cookies + * @hash_node: Used by the hashtable + * @pre_ct_list: This entry is part of a pre_ct_list + * @post_ct_list: This entry is part of a post_ct_list + * @zt: Reference to the zone table this belongs to + * @pre_ct_parent: The pre_ct_parent + * @post_ct_parent: The post_ct_parent + * @children: List of nft merged entries + */ +struct nfp_fl_ct_tc_merge { + unsigned long cookie[2]; + struct rhash_head hash_node; + struct list_head pre_ct_list; + struct list_head post_ct_list; + struct nfp_fl_ct_zone_entry *zt; + struct nfp_fl_ct_flow_entry *pre_ct_parent; + struct nfp_fl_ct_flow_entry *post_ct_parent; + struct list_head children; +}; + +/** + * struct nfp_fl_nft_tc_merge - Merge of tc_merge flows with nft flow + * @netdev: Ingress netdev name + * @cookie: Flow cookie, combination of tc_merge and nft cookies + * @hash_node: Used by the hashtable + * @zt: Reference to the zone table this belongs to + * @nft_flow_list: This entry is part of a nft_flows_list + * @tc_merge_list: This entry is part of a ct_merge_list + * @tc_m_parent: The tc_merge parent + * @nft_parent: The nft_entry parent + * @tc_flower_cookie: The cookie of the flow offloaded to the nfp + * @flow_pay: Reference to the offloaded flow struct + */ +struct nfp_fl_nft_tc_merge { + struct net_device *netdev; + unsigned long cookie[3]; + struct rhash_head hash_node; + struct nfp_fl_ct_zone_entry *zt; + struct list_head nft_flow_list; + struct list_head tc_merge_list; + struct nfp_fl_ct_tc_merge *tc_m_parent; + struct nfp_fl_ct_flow_entry *nft_parent; + unsigned long tc_flower_cookie; + struct nfp_fl_payload *flow_pay; +}; + +/** + * struct nfp_fl_ct_map_entry - Map between flow cookie and specific ct_flow + * @cookie: Flow cookie, same as original TC flow, used as key + * @hash_node: Used by the hashtable + * @ct_entry: Pointer to corresponding ct_entry + */ +struct nfp_fl_ct_map_entry { + unsigned long cookie; + struct rhash_head hash_node; + struct nfp_fl_ct_flow_entry *ct_entry; +}; + +bool is_pre_ct_flow(struct flow_cls_offload *flow); +bool is_post_ct_flow(struct flow_cls_offload *flow); + +/** + * nfp_fl_ct_handle_pre_ct() - Handles -trk conntrack rules + * @priv: Pointer to app priv + * @netdev: netdev structure. + * @flow: TC flower classifier offload structure. + * @extack: Extack pointer for errors + * + * Adds a new entry to the relevant zone table and tries to + * merge with other +trk+est entries and offload if possible. + * + * Return: negative value on error, 0 if configured successfully. + */ +int nfp_fl_ct_handle_pre_ct(struct nfp_flower_priv *priv, + struct net_device *netdev, + struct flow_cls_offload *flow, + struct netlink_ext_ack *extack); +/** + * nfp_fl_ct_handle_post_ct() - Handles +trk+est conntrack rules + * @priv: Pointer to app priv + * @netdev: netdev structure. + * @flow: TC flower classifier offload structure. + * @extack: Extack pointer for errors + * + * Adds a new entry to the relevant zone table and tries to + * merge with other -trk entries and offload if possible. + * + * Return: negative value on error, 0 if configured successfully. + */ +int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv, + struct net_device *netdev, + struct flow_cls_offload *flow, + struct netlink_ext_ack *extack); + +/** + * nfp_fl_ct_clean_flow_entry() - Free a nfp_fl_ct_flow_entry + * @entry: Flow entry to cleanup + */ +void nfp_fl_ct_clean_flow_entry(struct nfp_fl_ct_flow_entry *entry); + +/** + * nfp_fl_ct_del_flow() - Handle flow_del callbacks for conntrack + * @ct_map_ent: ct map entry for the flow that needs deleting + */ +int nfp_fl_ct_del_flow(struct nfp_fl_ct_map_entry *ct_map_ent); + +/** + * nfp_fl_ct_handle_nft_flow() - Handle flower flow callbacks for nft table + * @type: Type provided by callback + * @type_data: Callback data + * @cb_priv: Pointer to data provided when registering the callback, in this + * case it's the zone table. + */ +int nfp_fl_ct_handle_nft_flow(enum tc_setup_type type, void *type_data, + void *cb_priv); +#endif diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 31377923ea3d..0fbd682ccf72 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -193,6 +193,9 @@ struct nfp_fl_internal_ports { * @qos_stats_lock: Lock on qos stats updates * @pre_tun_rule_cnt: Number of pre-tunnel rules offloaded * @merge_table: Hash table to store merged flows + * @ct_zone_table: Hash table used to store the different zones + * @ct_zone_wc: Special zone entry for wildcarded zone matches + * @ct_map_table: Hash table used to referennce ct flows */ struct nfp_flower_priv { struct nfp_app *app; @@ -227,6 +230,9 @@ struct nfp_flower_priv { spinlock_t qos_stats_lock; /* Protect the qos stats */ int pre_tun_rule_cnt; struct rhashtable merge_table; + struct rhashtable ct_zone_table; + struct nfp_fl_ct_zone_entry *ct_zone_wc; + struct rhashtable ct_map_table; }; /** diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c index 327bb56b3ef5..621113650a9b 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c +++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c @@ -9,6 +9,7 @@ #include #include "cmsg.h" +#include "conntrack.h" #include "main.h" #include "../nfp_app.h" @@ -496,6 +497,20 @@ const struct rhashtable_params merge_table_params = { .key_len = sizeof(u64), }; +const struct rhashtable_params nfp_zone_table_params = { + .head_offset = offsetof(struct nfp_fl_ct_zone_entry, hash_node), + .key_len = sizeof(u16), + .key_offset = offsetof(struct nfp_fl_ct_zone_entry, zone), + .automatic_shrinking = false, +}; + +const struct rhashtable_params nfp_ct_map_params = { + .head_offset = offsetof(struct nfp_fl_ct_map_entry, hash_node), + .key_len = sizeof(unsigned long), + .key_offset = offsetof(struct nfp_fl_ct_map_entry, cookie), + .automatic_shrinking = true, +}; + int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, unsigned int host_num_mems) { @@ -516,6 +531,14 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, if (err) goto err_free_stats_ctx_table; + err = rhashtable_init(&priv->ct_zone_table, &nfp_zone_table_params); + if (err) + goto err_free_merge_table; + + err = rhashtable_init(&priv->ct_map_table, &nfp_ct_map_params); + if (err) + goto err_free_ct_zone_table; + get_random_bytes(&priv->mask_id_seed, sizeof(priv->mask_id_seed)); /* Init ring buffer and unallocated mask_ids. */ @@ -523,7 +546,7 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, kmalloc_array(NFP_FLOWER_MASK_ENTRY_RS, NFP_FLOWER_MASK_ELEMENT_RS, GFP_KERNEL); if (!priv->mask_ids.mask_id_free_list.buf) - goto err_free_merge_table; + goto err_free_ct_map_table; priv->mask_ids.init_unallocated = NFP_FLOWER_MASK_ENTRY_RS - 1; @@ -560,6 +583,10 @@ err_free_last_used: kfree(priv->mask_ids.last_used); err_free_mask_id: kfree(priv->mask_ids.mask_id_free_list.buf); +err_free_ct_map_table: + rhashtable_destroy(&priv->ct_map_table); +err_free_ct_zone_table: + rhashtable_destroy(&priv->ct_zone_table); err_free_merge_table: rhashtable_destroy(&priv->merge_table); err_free_stats_ctx_table: @@ -569,6 +596,100 @@ err_free_flow_table: return -ENOMEM; } +static void nfp_zone_table_entry_destroy(struct nfp_fl_ct_zone_entry *zt) +{ + if (!zt) + return; + + if (!list_empty(&zt->pre_ct_list)) { + struct rhashtable *m_table = &zt->priv->ct_map_table; + struct nfp_fl_ct_flow_entry *entry, *tmp; + struct nfp_fl_ct_map_entry *map; + + WARN_ONCE(1, "pre_ct_list not empty as expected, cleaning up\n"); + list_for_each_entry_safe(entry, tmp, &zt->pre_ct_list, + list_node) { + map = rhashtable_lookup_fast(m_table, + &entry->cookie, + nfp_ct_map_params); + WARN_ON_ONCE(rhashtable_remove_fast(m_table, + &map->hash_node, + nfp_ct_map_params)); + nfp_fl_ct_clean_flow_entry(entry); + kfree(map); + } + } + + if (!list_empty(&zt->post_ct_list)) { + struct rhashtable *m_table = &zt->priv->ct_map_table; + struct nfp_fl_ct_flow_entry *entry, *tmp; + struct nfp_fl_ct_map_entry *map; + + WARN_ONCE(1, "post_ct_list not empty as expected, cleaning up\n"); + list_for_each_entry_safe(entry, tmp, &zt->post_ct_list, + list_node) { + map = rhashtable_lookup_fast(m_table, + &entry->cookie, + nfp_ct_map_params); + WARN_ON_ONCE(rhashtable_remove_fast(m_table, + &map->hash_node, + nfp_ct_map_params)); + nfp_fl_ct_clean_flow_entry(entry); + kfree(map); + } + } + + if (zt->nft) { + nf_flow_table_offload_del_cb(zt->nft, + nfp_fl_ct_handle_nft_flow, + zt); + zt->nft = NULL; + } + + if (!list_empty(&zt->nft_flows_list)) { + struct rhashtable *m_table = &zt->priv->ct_map_table; + struct nfp_fl_ct_flow_entry *entry, *tmp; + struct nfp_fl_ct_map_entry *map; + + WARN_ONCE(1, "nft_flows_list not empty as expected, cleaning up\n"); + list_for_each_entry_safe(entry, tmp, &zt->nft_flows_list, + list_node) { + map = rhashtable_lookup_fast(m_table, + &entry->cookie, + nfp_ct_map_params); + WARN_ON_ONCE(rhashtable_remove_fast(m_table, + &map->hash_node, + nfp_ct_map_params)); + nfp_fl_ct_clean_flow_entry(entry); + kfree(map); + } + } + + rhashtable_free_and_destroy(&zt->tc_merge_tb, + nfp_check_rhashtable_empty, NULL); + rhashtable_free_and_destroy(&zt->nft_merge_tb, + nfp_check_rhashtable_empty, NULL); + + kfree(zt); +} + +static void nfp_free_zone_table_entry(void *ptr, void *arg) +{ + struct nfp_fl_ct_zone_entry *zt = ptr; + + nfp_zone_table_entry_destroy(zt); +} + +static void nfp_free_map_table_entry(void *ptr, void *arg) +{ + struct nfp_fl_ct_map_entry *map = ptr; + + if (!map) + return; + + kfree(map); +} + void nfp_flower_metadata_cleanup(struct nfp_app *app) { struct nfp_flower_priv *priv = app->priv; @@ -582,6 +703,12 @@ void nfp_flower_metadata_cleanup(struct nfp_app *app) nfp_check_rhashtable_empty, NULL); rhashtable_free_and_destroy(&priv->merge_table, nfp_check_rhashtable_empty, NULL); + rhashtable_free_and_destroy(&priv->ct_zone_table, + nfp_free_zone_table_entry, NULL); + nfp_zone_table_entry_destroy(priv->ct_zone_wc); + + rhashtable_free_and_destroy(&priv->ct_map_table, + nfp_free_map_table_entry, NULL); kvfree(priv->stats); kfree(priv->mask_ids.mask_id_free_list.buf); kfree(priv->mask_ids.last_used); diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index e95969c462e4..2406d33356ad 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -7,6 +7,7 @@ #include "cmsg.h" #include "main.h" +#include "conntrack.h" #include "../nfpcore/nfp_cpp.h" #include "../nfpcore/nfp_nsp.h" #include "../nfp_app.h" @@ -1276,6 +1277,20 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, return 0; } +static bool offload_pre_check(struct flow_cls_offload *flow) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(flow); + struct flow_dissector *dissector = rule->match.dissector; + + if (dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CT)) + return false; + + if (flow->common.chain_index) + return false; + + return true; +} + /** * nfp_flower_add_offload() - Adds a new flow to hardware. * @app: Pointer to the APP handle @@ -1302,6 +1317,15 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, if (nfp_netdev_is_nfp_repr(netdev)) port = nfp_port_from_netdev(netdev); + if (is_pre_ct_flow(flow)) + return nfp_fl_ct_handle_pre_ct(priv, netdev, flow, extack); + + if (is_post_ct_flow(flow)) + return nfp_fl_ct_handle_post_ct(priv, netdev, flow, extack); + + if (!offload_pre_check(flow)) + return -EOPNOTSUPP; + key_layer = kmalloc(sizeof(*key_layer), GFP_KERNEL); if (!key_layer) return -ENOMEM; @@ -1481,6 +1505,7 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev, struct flow_cls_offload *flow) { struct nfp_flower_priv *priv = app->priv; + struct nfp_fl_ct_map_entry *ct_map_ent; struct netlink_ext_ack *extack = NULL; struct nfp_fl_payload *nfp_flow; struct nfp_port *port = NULL; @@ -1490,6 +1515,14 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev, if (nfp_netdev_is_nfp_repr(netdev)) port = nfp_port_from_netdev(netdev); + /* Check ct_map_table */ + ct_map_ent = rhashtable_lookup_fast(&priv->ct_map_table, &flow->cookie, + nfp_ct_map_params); + if (ct_map_ent) { + err = nfp_fl_ct_del_flow(ct_map_ent); + return err; + } + nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev); if (!nfp_flow) { NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot remove flow that does not exist"); @@ -1646,9 +1679,10 @@ nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev, static int nfp_flower_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { + struct flow_cls_common_offload *common = type_data; struct nfp_repr *repr = cb_priv; - if (!tc_cls_can_offload_and_chain0(repr->netdev, type_data)) + if (!tc_can_offload_extack(repr->netdev, common->extack)) return -EOPNOTSUPP; switch (type) { @@ -1746,10 +1780,6 @@ static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { struct nfp_flower_indr_block_cb_priv *priv = cb_priv; - struct flow_cls_offload *flower = type_data; - - if (flower->common.chain_index) - return -EOPNOTSUPP; switch (type) { case TC_SETUP_CLSFLOWER: diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index d19c02e99114..ab70179728f6 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -21,7 +21,7 @@ #define NFP_TUN_PRE_TUN_IPV6_BIT BIT(7) /** - * struct nfp_tun_pre_run_rule - rule matched before decap + * struct nfp_tun_pre_tun_rule - rule matched before decap * @flags: options for the rule offset * @port_idx: index of destination MAC address for the rule * @vlan_tci: VLAN info associated with MAC diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index eeb30680b4dc..5dfa4799c34f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1819,7 +1819,6 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) struct xdp_buff xdp; int idx; - rcu_read_lock(); xdp_prog = READ_ONCE(dp->xdp_prog); true_bufsz = xdp_prog ? PAGE_SIZE : dp->fl_bufsz; xdp_init_buff(&xdp, PAGE_SIZE - NFP_NET_RX_BUF_HEADROOM, @@ -2036,7 +2035,6 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) if (!nfp_net_xdp_complete(tx_ring)) pkts_polled = budget; } - rcu_read_unlock(); return pkts_polled; } diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c index 94994a939277..d7ac0307797f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c @@ -905,8 +905,7 @@ area_cache_put(struct nfp_cpp *cpp, struct nfp_cpp_area_cache *cache) return; /* Move to front of LRU */ - list_del(&cache->entry); - list_add(&cache->entry, &cpp->area_cache_list); + list_move(&cache->entry, &cpp->area_cache_list); mutex_unlock(&cpp->area_cache_mutex); } diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c index d4e02542e2e9..e2e5fd003ad6 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c @@ -24,7 +24,7 @@ #define NFFW_FWID_ALL 255 -/** +/* * NFFW_INFO_VERSION history: * 0: This was never actually used (before versioning), but it refers to * the previous struct which had FWINFO_CNT = MEINFO_CNT = 120 that later diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index a6861df9904f..2d097dcb7bda 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -1224,7 +1224,6 @@ static int nixge_of_get_resources(struct platform_device *pdev) const struct of_device_id *of_id; enum nixge_version version; struct resource *ctrlres; - struct resource *dmares; struct net_device *ndev; struct nixge_priv *priv; @@ -1236,12 +1235,9 @@ static int nixge_of_get_resources(struct platform_device *pdev) version = (enum nixge_version)of_id->data; if (version <= NIXGE_V2) - dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0); + priv->dma_regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); else - dmares = platform_get_resource_byname(pdev, IORESOURCE_MEM, - "dma"); - - priv->dma_regs = devm_ioremap_resource(&pdev->dev, dmares); + priv->dma_regs = devm_platform_ioremap_resource_byname(pdev, "dma"); if (IS_ERR(priv->dma_regs)) { netdev_err(ndev, "failed to map dma regs\n"); return PTR_ERR(priv->dma_regs); diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h index a6823c4d355d..108f312bc542 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h @@ -596,8 +596,6 @@ struct pch_gbe_adapter { #define pch_gbe_hw_to_adapter(hw) container_of(hw, struct pch_gbe_adapter, hw) -extern const char pch_driver_version[]; - /* pch_gbe_main.c */ int pch_gbe_up(struct pch_gbe_adapter *adapter); void pch_gbe_down(struct pch_gbe_adapter *adapter); diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c index a58f14aca10c..660b07cb5b92 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c @@ -8,6 +8,8 @@ #include "pch_gbe.h" #include "pch_gbe_phy.h" +static const char pch_driver_version[] = "1.01"; + /* * pch_gbe_stats - Stats item information */ diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 334af49e5add..e351f3d1608f 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -8,15 +8,16 @@ #include "pch_gbe.h" #include "pch_gbe_phy.h" + +#include +#include +#include #include #include #include #include #include -#define DRV_VERSION "1.01" -const char pch_driver_version[] = DRV_VERSION; - #define PCH_GBE_MAR_ENTRIES 16 #define PCH_GBE_SHORT_PKT 64 #define DSC_INIT16 0xC000 @@ -97,8 +98,6 @@ const char pch_driver_version[] = DRV_VERSION; #define PTP_L4_MULTICAST_SA "01:00:5e:00:01:81" #define PTP_L2_MULTICAST_SA "01:1b:19:00:00:00" -#define MINNOW_PHY_RESET_GPIO 13 - static int pch_gbe_mdio_read(struct net_device *netdev, int addr, int reg); static void pch_gbe_mdio_write(struct net_device *netdev, int addr, int reg, int data); @@ -108,7 +107,7 @@ static int pch_ptp_match(struct sk_buff *skb, u16 uid_hi, u32 uid_lo, u16 seqid) { u8 *data = skb->data; unsigned int offset; - u16 *hi, *id; + u16 hi, id; u32 lo; if (ptp_classify_raw(skb) == PTP_CLASS_NONE) @@ -119,14 +118,11 @@ static int pch_ptp_match(struct sk_buff *skb, u16 uid_hi, u32 uid_lo, u16 seqid) if (skb->len < offset + OFF_PTP_SEQUENCE_ID + sizeof(seqid)) return 0; - hi = (u16 *)(data + offset + OFF_PTP_SOURCE_UUID); - id = (u16 *)(data + offset + OFF_PTP_SEQUENCE_ID); + hi = get_unaligned_be16(data + offset + OFF_PTP_SOURCE_UUID + 0); + lo = get_unaligned_be32(data + offset + OFF_PTP_SOURCE_UUID + 2); + id = get_unaligned_be16(data + offset + OFF_PTP_SEQUENCE_ID); - memcpy(&lo, &hi[1], sizeof(lo)); - - return (uid_hi == *hi && - uid_lo == lo && - seqid == *id); + return (uid_hi == hi && uid_lo == lo && seqid == id); } static void @@ -136,7 +132,6 @@ pch_rx_timestamp(struct pch_gbe_adapter *adapter, struct sk_buff *skb) struct pci_dev *pdev; u64 ns; u32 hi, lo, val; - u16 uid, seq; if (!adapter->hwts_rx_en) return; @@ -152,10 +147,7 @@ pch_rx_timestamp(struct pch_gbe_adapter *adapter, struct sk_buff *skb) lo = pch_src_uuid_lo_read(pdev); hi = pch_src_uuid_hi_read(pdev); - uid = hi & 0xffff; - seq = (hi >> 16) & 0xffff; - - if (!pch_ptp_match(skb, htons(uid), htonl(lo), htons(seq))) + if (!pch_ptp_match(skb, hi, lo, hi >> 16)) goto out; ns = pch_rx_snap_read(pdev); @@ -298,15 +290,12 @@ static s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw) * @reg: Pointer of register * @bit: Busy bit */ -static void pch_gbe_wait_clr_bit(void *reg, u32 bit) +static void pch_gbe_wait_clr_bit(void __iomem *reg, u32 bit) { u32 tmp; /* wait busy */ - tmp = 1000; - while ((ioread32(reg) & bit) && --tmp) - cpu_relax(); - if (!tmp) + if (readx_poll_timeout_atomic(ioread32, reg, tmp, !(tmp & bit), 0, 10)) pr_err("Error: busy bit is not cleared\n"); } @@ -490,18 +479,13 @@ u16 pch_gbe_mac_ctrl_miim(struct pch_gbe_hw *hw, u32 addr, u32 dir, u32 reg, u16 data) { struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw); - u32 data_out = 0; - unsigned int i; unsigned long flags; + u32 data_out; spin_lock_irqsave(&hw->miim_lock, flags); - for (i = 100; i; --i) { - if ((ioread32(&hw->reg->MIIM) & PCH_GBE_MIIM_OPER_READY)) - break; - udelay(20); - } - if (i == 0) { + if (readx_poll_timeout_atomic(ioread32, &hw->reg->MIIM, data_out, + data_out & PCH_GBE_MIIM_OPER_READY, 20, 2000)) { netdev_err(adapter->netdev, "pch-gbe.miim won't go Ready\n"); spin_unlock_irqrestore(&hw->miim_lock, flags); return 0; /* No way to indicate timeout error */ @@ -509,12 +493,8 @@ u16 pch_gbe_mac_ctrl_miim(struct pch_gbe_hw *hw, u32 addr, u32 dir, u32 reg, iowrite32(((reg << PCH_GBE_MIIM_REG_ADDR_SHIFT) | (addr << PCH_GBE_MIIM_PHY_ADDR_SHIFT) | dir | data), &hw->reg->MIIM); - for (i = 0; i < 100; i++) { - udelay(20); - data_out = ioread32(&hw->reg->MIIM); - if ((data_out & PCH_GBE_MIIM_OPER_READY)) - break; - } + readx_poll_timeout_atomic(ioread32, &hw->reg->MIIM, data_out, + data_out & PCH_GBE_MIIM_OPER_READY, 20, 2000); spin_unlock_irqrestore(&hw->miim_lock, flags); netdev_dbg(adapter->netdev, "PHY %s: reg=%d, data=0x%04X\n", @@ -2532,9 +2512,13 @@ static int pch_gbe_probe(struct pci_dev *pdev, adapter->pdev = pdev; adapter->hw.back = adapter; adapter->hw.reg = pcim_iomap_table(pdev)[PCH_GBE_PCI_BAR]; + adapter->pdata = (struct pch_gbe_privdata *)pci_id->driver_data; - if (adapter->pdata && adapter->pdata->platform_init) - adapter->pdata->platform_init(pdev); + if (adapter->pdata && adapter->pdata->platform_init) { + ret = adapter->pdata->platform_init(pdev); + if (ret) + goto err_free_netdev; + } adapter->ptp_pdev = pci_get_domain_bus_and_slot(pci_domain_nr(adapter->pdev->bus), @@ -2624,26 +2608,45 @@ err_free_netdev: return ret; } +static void pch_gbe_gpio_remove_table(void *table) +{ + gpiod_remove_lookup_table(table); +} + +static int pch_gbe_gpio_add_table(struct device *dev, void *table) +{ + gpiod_add_lookup_table(table); + return devm_add_action_or_reset(dev, pch_gbe_gpio_remove_table, table); +} + +static struct gpiod_lookup_table pch_gbe_minnow_gpio_table = { + .dev_id = "0000:02:00.1", + .table = { + GPIO_LOOKUP("sch_gpio.33158", 13, NULL, GPIO_ACTIVE_LOW), + {} + }, +}; + /* The AR803X PHY on the MinnowBoard requires a physical pin to be toggled to * ensure it is awake for probe and init. Request the line and reset the PHY. */ static int pch_gbe_minnow_platform_init(struct pci_dev *pdev) { - unsigned long flags = GPIOF_DIR_OUT | GPIOF_INIT_HIGH | GPIOF_EXPORT; - unsigned gpio = MINNOW_PHY_RESET_GPIO; + struct gpio_desc *gpiod; int ret; - ret = devm_gpio_request_one(&pdev->dev, gpio, flags, - "minnow_phy_reset"); - if (ret) { - dev_err(&pdev->dev, - "ERR: Can't request PHY reset GPIO line '%d'\n", gpio); + ret = pch_gbe_gpio_add_table(&pdev->dev, &pch_gbe_minnow_gpio_table); + if (ret) return ret; - } - gpio_set_value(gpio, 0); + gpiod = devm_gpiod_get(&pdev->dev, NULL, GPIOD_OUT_HIGH); + if (IS_ERR(gpiod)) + return dev_err_probe(&pdev->dev, PTR_ERR(gpiod), + "Can't request PHY reset GPIO line\n"); + + gpiod_set_value(gpiod, 1); usleep_range(1250, 1500); - gpio_set_value(gpio, 1); + gpiod_set_value(gpiod, 0); usleep_range(1250, 1500); return ret; @@ -2722,7 +2725,6 @@ module_pci_driver(pch_gbe_driver); MODULE_DESCRIPTION("EG20T PCH Gigabit ethernet Driver"); MODULE_AUTHOR("LAPIS SEMICONDUCTOR, "); MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); MODULE_DEVICE_TABLE(pci, pch_gbe_pcidev_id); /* pch_gbe_main.c */ diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig index 6b5ddb07ee83..98f430905ffa 100644 --- a/drivers/net/ethernet/qlogic/Kconfig +++ b/drivers/net/ethernet/qlogic/Kconfig @@ -110,6 +110,9 @@ config QED_RDMA config QED_ISCSI bool +config QED_NVMETCP + bool + config QED_FCOE bool diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile index 8251755ec18c..0d9c2fe0245d 100644 --- a/drivers/net/ethernet/qlogic/qed/Makefile +++ b/drivers/net/ethernet/qlogic/qed/Makefile @@ -28,6 +28,11 @@ qed-$(CONFIG_QED_ISCSI) += qed_iscsi.o qed-$(CONFIG_QED_LL2) += qed_ll2.o qed-$(CONFIG_QED_OOO) += qed_ooo.o +qed-$(CONFIG_QED_NVMETCP) += \ + qed_nvmetcp.o \ + qed_nvmetcp_fw_funcs.o \ + qed_nvmetcp_ip_services.o + qed-$(CONFIG_QED_RDMA) += \ qed_iwarp.o \ qed_rdma.o \ diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index a20cb8a0c377..b590c70539b5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -49,6 +49,8 @@ extern const struct qed_common_ops qed_common_ops_pass; #define QED_MIN_WIDS (4) #define QED_PF_DEMS_SIZE (4) +#define QED_LLH_DONT_CARE 0 + /* cau states */ enum qed_coalescing_mode { QED_COAL_MODE_DISABLE, @@ -200,6 +202,7 @@ enum qed_pci_personality { QED_PCI_ETH, QED_PCI_FCOE, QED_PCI_ISCSI, + QED_PCI_NVMETCP, QED_PCI_ETH_ROCE, QED_PCI_ETH_IWARP, QED_PCI_ETH_RDMA, @@ -239,6 +242,7 @@ enum QED_FEATURE { QED_PF_L2_QUE, QED_VF, QED_RDMA_CNQ, + QED_NVMETCP_CQ, QED_ISCSI_CQ, QED_FCOE_CQ, QED_VF_L2_QUE, @@ -284,6 +288,8 @@ struct qed_hw_info { ((dev)->hw_info.personality == QED_PCI_FCOE) #define QED_IS_ISCSI_PERSONALITY(dev) \ ((dev)->hw_info.personality == QED_PCI_ISCSI) +#define QED_IS_NVMETCP_PERSONALITY(dev) \ + ((dev)->hw_info.personality == QED_PCI_NVMETCP) /* Resource Allocation scheme results */ u32 resc_start[QED_MAX_RESC]; @@ -592,6 +598,7 @@ struct qed_hwfn { struct qed_ooo_info *p_ooo_info; struct qed_rdma_info *p_rdma_info; struct qed_iscsi_info *p_iscsi_info; + struct qed_nvmetcp_info *p_nvmetcp_info; struct qed_fcoe_info *p_fcoe_info; struct qed_pf_params pf_params; @@ -828,6 +835,7 @@ struct qed_dev { struct qed_eth_cb_ops *eth; struct qed_fcoe_cb_ops *fcoe; struct qed_iscsi_cb_ops *iscsi; + struct qed_nvmetcp_cb_ops *nvmetcp; } protocol_ops; void *ops_cookie; @@ -999,4 +1007,10 @@ int qed_mfw_fill_tlv_data(struct qed_hwfn *hwfn, void qed_hw_info_set_offload_tc(struct qed_hw_info *p_info, u8 tc); void qed_periodic_db_rec_start(struct qed_hwfn *p_hwfn); + +int qed_llh_add_src_tcp_port_filter(struct qed_dev *cdev, u16 src_port); +int qed_llh_add_dst_tcp_port_filter(struct qed_dev *cdev, u16 dest_port); +void qed_llh_remove_src_tcp_port_filter(struct qed_dev *cdev, u16 src_port); +void qed_llh_remove_dst_tcp_port_filter(struct qed_dev *cdev, u16 src_port); +void qed_llh_clear_all_filters(struct qed_dev *cdev); #endif /* _QED_H */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 0a22f8ce9a2c..5a0a3cbcc1c1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -94,14 +94,14 @@ struct src_ent { static bool src_proto(enum protocol_type type) { - return type == PROTOCOLID_ISCSI || + return type == PROTOCOLID_TCP_ULP || type == PROTOCOLID_FCOE || type == PROTOCOLID_IWARP; } static bool tm_cid_proto(enum protocol_type type) { - return type == PROTOCOLID_ISCSI || + return type == PROTOCOLID_TCP_ULP || type == PROTOCOLID_FCOE || type == PROTOCOLID_ROCE || type == PROTOCOLID_IWARP; @@ -2072,7 +2072,6 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks) PROTOCOLID_FCOE, p_params->num_cons, 0); - qed_cxt_set_proto_tid_count(p_hwfn, PROTOCOLID_FCOE, QED_CXT_FCOE_TID_SEG, 0, p_params->num_tasks, true); @@ -2090,13 +2089,12 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks) if (p_params->num_cons && p_params->num_tasks) { qed_cxt_set_proto_cid_count(p_hwfn, - PROTOCOLID_ISCSI, + PROTOCOLID_TCP_ULP, p_params->num_cons, 0); - qed_cxt_set_proto_tid_count(p_hwfn, - PROTOCOLID_ISCSI, - QED_CXT_ISCSI_TID_SEG, + PROTOCOLID_TCP_ULP, + QED_CXT_TCP_ULP_TID_SEG, 0, p_params->num_tasks, true); @@ -2106,6 +2104,29 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks) } break; } + case QED_PCI_NVMETCP: + { + struct qed_nvmetcp_pf_params *p_params; + + p_params = &p_hwfn->pf_params.nvmetcp_pf_params; + + if (p_params->num_cons && p_params->num_tasks) { + qed_cxt_set_proto_cid_count(p_hwfn, + PROTOCOLID_TCP_ULP, + p_params->num_cons, + 0); + qed_cxt_set_proto_tid_count(p_hwfn, + PROTOCOLID_TCP_ULP, + QED_CXT_TCP_ULP_TID_SEG, + 0, + p_params->num_tasks, + true); + } else { + DP_INFO(p_hwfn->cdev, + "NvmeTCP personality used without setting params!\n"); + } + break; + } default: return -EINVAL; } @@ -2129,8 +2150,9 @@ int qed_cxt_get_tid_mem_info(struct qed_hwfn *p_hwfn, seg = QED_CXT_FCOE_TID_SEG; break; case QED_PCI_ISCSI: - proto = PROTOCOLID_ISCSI; - seg = QED_CXT_ISCSI_TID_SEG; + case QED_PCI_NVMETCP: + proto = PROTOCOLID_TCP_ULP; + seg = QED_CXT_TCP_ULP_TID_SEG; break; default: return -EINVAL; @@ -2455,8 +2477,9 @@ int qed_cxt_get_task_ctx(struct qed_hwfn *p_hwfn, seg = QED_CXT_FCOE_TID_SEG; break; case QED_PCI_ISCSI: - proto = PROTOCOLID_ISCSI; - seg = QED_CXT_ISCSI_TID_SEG; + case QED_PCI_NVMETCP: + proto = PROTOCOLID_TCP_ULP; + seg = QED_CXT_TCP_ULP_TID_SEG; break; default: return -EINVAL; diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h index 056e79620a0e..8adb7ed0c12d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h @@ -50,7 +50,7 @@ int qed_cxt_get_cid_info(struct qed_hwfn *p_hwfn, int qed_cxt_get_tid_mem_info(struct qed_hwfn *p_hwfn, struct qed_tid_mem *p_info); -#define QED_CXT_ISCSI_TID_SEG PROTOCOLID_ISCSI +#define QED_CXT_TCP_ULP_TID_SEG PROTOCOLID_TCP_ULP #define QED_CXT_ROCE_TID_SEG PROTOCOLID_ROCE #define QED_CXT_FCOE_TID_SEG PROTOCOLID_FCOE enum qed_cxt_elem_type { diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index d2f5855b2ea7..0410c3604abd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -37,6 +37,7 @@ #include "qed_sriov.h" #include "qed_vf.h" #include "qed_rdma.h" +#include "qed_nvmetcp.h" static DEFINE_SPINLOCK(qm_lock); @@ -667,7 +668,8 @@ qed_llh_set_engine_affin(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) } /* Storage PF is bound to a single engine while L2 PF uses both */ - if (QED_IS_FCOE_PERSONALITY(p_hwfn) || QED_IS_ISCSI_PERSONALITY(p_hwfn)) + if (QED_IS_FCOE_PERSONALITY(p_hwfn) || QED_IS_ISCSI_PERSONALITY(p_hwfn) || + QED_IS_NVMETCP_PERSONALITY(p_hwfn)) eng = cdev->fir_affin ? QED_ENG1 : QED_ENG0; else /* L2_PERSONALITY */ eng = QED_BOTH_ENG; @@ -1164,6 +1166,9 @@ void qed_llh_remove_mac_filter(struct qed_dev *cdev, if (!test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits)) goto out; + if (QED_IS_NVMETCP_PERSONALITY(p_hwfn)) + return; + ether_addr_copy(filter.mac.addr, mac_addr); rc = qed_llh_shadow_remove_filter(cdev, ppfid, &filter, &filter_idx, &ref_cnt); @@ -1381,6 +1386,11 @@ void qed_resc_free(struct qed_dev *cdev) qed_ooo_free(p_hwfn); } + if (p_hwfn->hw_info.personality == QED_PCI_NVMETCP) { + qed_nvmetcp_free(p_hwfn); + qed_ooo_free(p_hwfn); + } + if (QED_IS_RDMA_PERSONALITY(p_hwfn) && rdma_info) { qed_spq_unregister_async_cb(p_hwfn, rdma_info->proto); qed_rdma_info_free(p_hwfn); @@ -1423,6 +1433,7 @@ static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn) flags |= PQ_FLAGS_OFLD; break; case QED_PCI_ISCSI: + case QED_PCI_NVMETCP: flags |= PQ_FLAGS_ACK | PQ_FLAGS_OOO | PQ_FLAGS_OFLD; break; case QED_PCI_ETH_ROCE: @@ -2263,10 +2274,11 @@ int qed_resc_alloc(struct qed_dev *cdev) * at the same time */ n_eqes += num_cons + 2 * MAX_NUM_VFS_BB + n_srq; - } else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) { + } else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI || + p_hwfn->hw_info.personality == QED_PCI_NVMETCP) { num_cons = qed_cxt_get_proto_cid_count(p_hwfn, - PROTOCOLID_ISCSI, + PROTOCOLID_TCP_ULP, NULL); n_eqes += 2 * num_cons; } @@ -2313,6 +2325,15 @@ int qed_resc_alloc(struct qed_dev *cdev) goto alloc_err; } + if (p_hwfn->hw_info.personality == QED_PCI_NVMETCP) { + rc = qed_nvmetcp_alloc(p_hwfn); + if (rc) + goto alloc_err; + rc = qed_ooo_alloc(p_hwfn); + if (rc) + goto alloc_err; + } + if (QED_IS_RDMA_PERSONALITY(p_hwfn)) { rc = qed_rdma_info_alloc(p_hwfn); if (rc) @@ -2393,6 +2414,11 @@ void qed_resc_setup(struct qed_dev *cdev) qed_iscsi_setup(p_hwfn); qed_ooo_setup(p_hwfn); } + + if (p_hwfn->hw_info.personality == QED_PCI_NVMETCP) { + qed_nvmetcp_setup(p_hwfn); + qed_ooo_setup(p_hwfn); + } } } @@ -2854,7 +2880,8 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn, /* Protocol Configuration */ STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_TCP_RT_OFFSET, - (p_hwfn->hw_info.personality == QED_PCI_ISCSI) ? 1 : 0); + ((p_hwfn->hw_info.personality == QED_PCI_ISCSI) || + (p_hwfn->hw_info.personality == QED_PCI_NVMETCP)) ? 1 : 0); STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_FCOE_RT_OFFSET, (p_hwfn->hw_info.personality == QED_PCI_FCOE) ? 1 : 0); STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_ROCE_RT_OFFSET, 0); @@ -3535,14 +3562,21 @@ static void qed_hw_set_feat(struct qed_hwfn *p_hwfn) feat_num[QED_ISCSI_CQ] = min_t(u32, sb_cnt.cnt, RESC_NUM(p_hwfn, QED_CMDQS_CQS)); + + if (QED_IS_NVMETCP_PERSONALITY(p_hwfn)) + feat_num[QED_NVMETCP_CQ] = min_t(u32, sb_cnt.cnt, + RESC_NUM(p_hwfn, + QED_CMDQS_CQS)); + DP_VERBOSE(p_hwfn, NETIF_MSG_PROBE, - "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d FCOE_CQ=%d ISCSI_CQ=%d #SBS=%d\n", + "#PF_L2_QUEUES=%d VF_L2_QUEUES=%d #ROCE_CNQ=%d FCOE_CQ=%d ISCSI_CQ=%d NVMETCP_CQ=%d #SBS=%d\n", (int)FEAT_NUM(p_hwfn, QED_PF_L2_QUE), (int)FEAT_NUM(p_hwfn, QED_VF_L2_QUE), (int)FEAT_NUM(p_hwfn, QED_RDMA_CNQ), (int)FEAT_NUM(p_hwfn, QED_FCOE_CQ), (int)FEAT_NUM(p_hwfn, QED_ISCSI_CQ), + (int)FEAT_NUM(p_hwfn, QED_NVMETCP_CQ), (int)sb_cnt.cnt); } @@ -3734,7 +3768,8 @@ int qed_hw_get_dflt_resc(struct qed_hwfn *p_hwfn, break; case QED_BDQ: if (p_hwfn->hw_info.personality != QED_PCI_ISCSI && - p_hwfn->hw_info.personality != QED_PCI_FCOE) + p_hwfn->hw_info.personality != QED_PCI_FCOE && + p_hwfn->hw_info.personality != QED_PCI_NVMETCP) *p_resc_num = 0; else *p_resc_num = 1; @@ -3755,7 +3790,8 @@ int qed_hw_get_dflt_resc(struct qed_hwfn *p_hwfn, *p_resc_start = 0; else if (p_hwfn->cdev->num_ports_in_engine == 4) *p_resc_start = p_hwfn->port_id; - else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) + else if (p_hwfn->hw_info.personality == QED_PCI_ISCSI || + p_hwfn->hw_info.personality == QED_PCI_NVMETCP) *p_resc_start = p_hwfn->port_id; else if (p_hwfn->hw_info.personality == QED_PCI_FCOE) *p_resc_start = p_hwfn->port_id + 2; @@ -5326,3 +5362,93 @@ void qed_set_fw_mac_addr(__le16 *fw_msb, ((u8 *)fw_lsb)[0] = mac[5]; ((u8 *)fw_lsb)[1] = mac[4]; } + +static int qed_llh_shadow_remove_all_filters(struct qed_dev *cdev, u8 ppfid) +{ + struct qed_llh_info *p_llh_info = cdev->p_llh_info; + struct qed_llh_filter_info *p_filters; + int rc; + + rc = qed_llh_shadow_sanity(cdev, ppfid, 0, "remove_all"); + if (rc) + return rc; + + p_filters = p_llh_info->pp_filters[ppfid]; + memset(p_filters, 0, NIG_REG_LLH_FUNC_FILTER_EN_SIZE * + sizeof(*p_filters)); + + return 0; +} + +static void qed_llh_clear_ppfid_filters(struct qed_dev *cdev, u8 ppfid) +{ + struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); + struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn); + u8 filter_idx, abs_ppfid; + int rc = 0; + + if (!p_ptt) + return; + + if (!test_bit(QED_MF_LLH_PROTO_CLSS, &cdev->mf_bits) && + !test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits)) + goto out; + + rc = qed_llh_abs_ppfid(cdev, ppfid, &abs_ppfid); + if (rc) + goto out; + + rc = qed_llh_shadow_remove_all_filters(cdev, ppfid); + if (rc) + goto out; + + for (filter_idx = 0; filter_idx < NIG_REG_LLH_FUNC_FILTER_EN_SIZE; + filter_idx++) { + rc = qed_llh_remove_filter(p_hwfn, p_ptt, + abs_ppfid, filter_idx); + if (rc) + goto out; + } +out: + qed_ptt_release(p_hwfn, p_ptt); +} + +int qed_llh_add_src_tcp_port_filter(struct qed_dev *cdev, u16 src_port) +{ + return qed_llh_add_protocol_filter(cdev, 0, + QED_LLH_FILTER_TCP_SRC_PORT, + src_port, QED_LLH_DONT_CARE); +} + +void qed_llh_remove_src_tcp_port_filter(struct qed_dev *cdev, u16 src_port) +{ + qed_llh_remove_protocol_filter(cdev, 0, + QED_LLH_FILTER_TCP_SRC_PORT, + src_port, QED_LLH_DONT_CARE); +} + +int qed_llh_add_dst_tcp_port_filter(struct qed_dev *cdev, u16 dest_port) +{ + return qed_llh_add_protocol_filter(cdev, 0, + QED_LLH_FILTER_TCP_DEST_PORT, + QED_LLH_DONT_CARE, dest_port); +} + +void qed_llh_remove_dst_tcp_port_filter(struct qed_dev *cdev, u16 dest_port) +{ + qed_llh_remove_protocol_filter(cdev, 0, + QED_LLH_FILTER_TCP_DEST_PORT, + QED_LLH_DONT_CARE, dest_port); +} + +void qed_llh_clear_all_filters(struct qed_dev *cdev) +{ + u8 ppfid; + + if (!test_bit(QED_MF_LLH_PROTO_CLSS, &cdev->mf_bits) && + !test_bit(QED_MF_LLH_MAC_CLSS, &cdev->mf_bits)) + return; + + for (ppfid = 0; ppfid < cdev->p_llh_info->num_ppfid; ppfid++) + qed_llh_clear_ppfid_filters(cdev, ppfid); +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 559df9f4d656..fb1baa2da2d0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -1118,7 +1119,7 @@ struct outer_tag_config_struct { /* personality per PF */ enum personality_type { BAD_PERSONALITY_TYP, - PERSONALITY_ISCSI, + PERSONALITY_TCP_ULP, PERSONALITY_FCOE, PERSONALITY_RDMA_AND_ETH, PERSONALITY_RDMA, @@ -12147,7 +12148,8 @@ struct public_func { #define FUNC_MF_CFG_PROTOCOL_ISCSI 0x00000010 #define FUNC_MF_CFG_PROTOCOL_FCOE 0x00000020 #define FUNC_MF_CFG_PROTOCOL_ROCE 0x00000030 -#define FUNC_MF_CFG_PROTOCOL_MAX 0x00000030 +#define FUNC_MF_CFG_PROTOCOL_NVMETCP 0x00000040 +#define FUNC_MF_CFG_PROTOCOL_MAX 0x00000040 #define FUNC_MF_CFG_MIN_BW_MASK 0x0000ff00 #define FUNC_MF_CFG_MIN_BW_SHIFT 8 diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c index 4eae4ee3538f..db926d8b3033 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c @@ -158,7 +158,7 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_INIT_FUNC, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; @@ -250,7 +250,7 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn, p_hwfn->p_iscsi_info->event_context = event_context; p_hwfn->p_iscsi_info->event_cb = async_event_cb; - qed_spq_register_async_cb(p_hwfn, PROTOCOLID_ISCSI, + qed_spq_register_async_cb(p_hwfn, PROTOCOLID_TCP_ULP, qed_iscsi_async_event); return qed_spq_post(p_hwfn, p_ent, NULL); @@ -286,7 +286,7 @@ static int qed_sp_iscsi_conn_offload(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_OFFLOAD_CONN, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; @@ -453,7 +453,7 @@ static int qed_sp_iscsi_conn_update(struct qed_hwfn *p_hwfn, struct iscsi_conn_update_ramrod_params *p_ramrod = NULL; struct qed_spq_entry *p_ent = NULL; struct qed_sp_init_data init_data; - int rc = -EINVAL; + int rc; u32 dval; /* Get SPQ entry */ @@ -465,7 +465,7 @@ static int qed_sp_iscsi_conn_update(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_UPDATE_CONN, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; @@ -506,7 +506,7 @@ qed_sp_iscsi_mac_update(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_MAC_UPDATE, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; @@ -548,7 +548,7 @@ static int qed_sp_iscsi_conn_terminate(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_TERMINATION_CONN, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; @@ -582,7 +582,7 @@ static int qed_sp_iscsi_conn_clear_sq(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_CLEAR_SQ, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; @@ -606,13 +606,13 @@ static int qed_sp_iscsi_func_stop(struct qed_hwfn *p_hwfn, rc = qed_sp_init_request(p_hwfn, &p_ent, ISCSI_RAMROD_CMD_ID_DESTROY_FUNC, - PROTOCOLID_ISCSI, &init_data); + PROTOCOLID_TCP_ULP, &init_data); if (rc) return rc; rc = qed_spq_post(p_hwfn, p_ent, NULL); - qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_ISCSI); + qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_TCP_ULP); return rc; } @@ -786,7 +786,7 @@ static int qed_iscsi_acquire_connection(struct qed_hwfn *p_hwfn, u32 icid; spin_lock_bh(&p_hwfn->p_iscsi_info->lock); - rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_ISCSI, &icid); + rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_TCP_ULP, &icid); spin_unlock_bh(&p_hwfn->p_iscsi_info->lock); if (rc) return rc; diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 49783f365079..02a4610d9330 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -960,7 +960,8 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn, if (test_bit(QED_MF_LL2_NON_UNICAST, &p_hwfn->cdev->mf_bits) && p_ramrod->main_func_queue && conn_type != QED_LL2_TYPE_ROCE && - conn_type != QED_LL2_TYPE_IWARP) { + conn_type != QED_LL2_TYPE_IWARP && + (!QED_IS_NVMETCP_PERSONALITY(p_hwfn))) { p_ramrod->mf_si_bcast_accept_all = 1; p_ramrod->mf_si_mcast_accept_all = 1; } else { @@ -1037,8 +1038,8 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, case QED_LL2_TYPE_FCOE: p_ramrod->conn_type = PROTOCOLID_FCOE; break; - case QED_LL2_TYPE_ISCSI: - p_ramrod->conn_type = PROTOCOLID_ISCSI; + case QED_LL2_TYPE_TCP_ULP: + p_ramrod->conn_type = PROTOCOLID_TCP_ULP; break; case QED_LL2_TYPE_ROCE: p_ramrod->conn_type = PROTOCOLID_ROCE; @@ -1047,8 +1048,9 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn, p_ramrod->conn_type = PROTOCOLID_IWARP; break; case QED_LL2_TYPE_OOO: - if (p_hwfn->hw_info.personality == QED_PCI_ISCSI) - p_ramrod->conn_type = PROTOCOLID_ISCSI; + if (p_hwfn->hw_info.personality == QED_PCI_ISCSI || + p_hwfn->hw_info.personality == QED_PCI_NVMETCP) + p_ramrod->conn_type = PROTOCOLID_TCP_ULP; else p_ramrod->conn_type = PROTOCOLID_IWARP; break; @@ -1634,7 +1636,8 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle) if (rc) goto out; - if (!QED_IS_RDMA_PERSONALITY(p_hwfn)) + if (!QED_IS_RDMA_PERSONALITY(p_hwfn) && + !QED_IS_NVMETCP_PERSONALITY(p_hwfn)) qed_wr(p_hwfn, p_ptt, PRS_REG_USE_LIGHT_L2, 1); qed_ll2_establish_connection_ooo(p_hwfn, p_ll2_conn); @@ -2376,7 +2379,8 @@ out: static bool qed_ll2_is_storage_eng1(struct qed_dev *cdev) { return (QED_IS_FCOE_PERSONALITY(QED_LEADING_HWFN(cdev)) || - QED_IS_ISCSI_PERSONALITY(QED_LEADING_HWFN(cdev))) && + QED_IS_ISCSI_PERSONALITY(QED_LEADING_HWFN(cdev)) || + QED_IS_NVMETCP_PERSONALITY(QED_LEADING_HWFN(cdev))) && (QED_AFFIN_HWFN(cdev) != QED_LEADING_HWFN(cdev)); } @@ -2402,11 +2406,13 @@ static int qed_ll2_stop(struct qed_dev *cdev) if (cdev->ll2->handle == QED_LL2_UNUSED_HANDLE) return 0; + if (!QED_IS_NVMETCP_PERSONALITY(p_hwfn)) + qed_llh_remove_mac_filter(cdev, 0, cdev->ll2_mac_address); qed_llh_remove_mac_filter(cdev, 0, cdev->ll2_mac_address); eth_zero_addr(cdev->ll2_mac_address); - if (QED_IS_ISCSI_PERSONALITY(p_hwfn)) + if (QED_IS_ISCSI_PERSONALITY(p_hwfn) || QED_IS_NVMETCP_PERSONALITY(p_hwfn)) qed_ll2_stop_ooo(p_hwfn); /* In CMT mode, LL2 is always started on engine 0 for a storage PF */ @@ -2442,7 +2448,8 @@ static int __qed_ll2_start(struct qed_hwfn *p_hwfn, conn_type = QED_LL2_TYPE_FCOE; break; case QED_PCI_ISCSI: - conn_type = QED_LL2_TYPE_ISCSI; + case QED_PCI_NVMETCP: + conn_type = QED_LL2_TYPE_TCP_ULP; break; case QED_PCI_ETH_ROCE: conn_type = QED_LL2_TYPE_ROCE; @@ -2567,7 +2574,7 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params) } } - if (QED_IS_ISCSI_PERSONALITY(p_hwfn)) { + if (QED_IS_ISCSI_PERSONALITY(p_hwfn) || QED_IS_NVMETCP_PERSONALITY(p_hwfn)) { DP_VERBOSE(cdev, QED_MSG_STORAGE, "Starting OOO LL2 queue\n"); rc = qed_ll2_start_ooo(p_hwfn, params); if (rc) { @@ -2576,10 +2583,13 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params) } } - rc = qed_llh_add_mac_filter(cdev, 0, params->ll2_mac_address); - if (rc) { - DP_NOTICE(cdev, "Failed to add an LLH filter\n"); - goto err3; + if (!QED_IS_NVMETCP_PERSONALITY(p_hwfn)) { + rc = qed_llh_add_mac_filter(cdev, 0, params->ll2_mac_address); + if (rc) { + DP_NOTICE(cdev, "Failed to add an LLH filter\n"); + goto err3; + } + } ether_addr_copy(cdev->ll2_mac_address, params->ll2_mac_address); @@ -2587,7 +2597,7 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params) return 0; err3: - if (QED_IS_ISCSI_PERSONALITY(p_hwfn)) + if (QED_IS_ISCSI_PERSONALITY(p_hwfn) || QED_IS_NVMETCP_PERSONALITY(p_hwfn)) qed_ll2_stop_ooo(p_hwfn); err2: if (b_is_storage_eng1) diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index cd882c453394..4387292c37e2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -2446,6 +2446,9 @@ qed_mcp_get_shmem_proto(struct qed_hwfn *p_hwfn, case FUNC_MF_CFG_PROTOCOL_ISCSI: *p_proto = QED_PCI_ISCSI; break; + case FUNC_MF_CFG_PROTOCOL_NVMETCP: + *p_proto = QED_PCI_NVMETCP; + break; case FUNC_MF_CFG_PROTOCOL_FCOE: *p_proto = QED_PCI_FCOE; break; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c index 3e3192a3ad9b..6190adf965bc 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c @@ -1306,7 +1306,8 @@ int qed_mfw_process_tlv_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) } if ((tlv_group & QED_MFW_TLV_ISCSI) && - p_hwfn->hw_info.personality != QED_PCI_ISCSI) { + p_hwfn->hw_info.personality != QED_PCI_ISCSI && + p_hwfn->hw_info.personality != QED_PCI_NVMETCP) { DP_VERBOSE(p_hwfn, QED_MSG_SP, "Skipping iSCSI TLVs for non-iSCSI function\n"); tlv_group &= ~QED_MFW_TLV_ISCSI; diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c new file mode 100644 index 000000000000..f19128c8d9cc --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.c @@ -0,0 +1,829 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) +/* Copyright 2021 Marvell. All rights reserved. */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "qed.h" +#include "qed_cxt.h" +#include "qed_dev_api.h" +#include "qed_hsi.h" +#include "qed_hw.h" +#include "qed_int.h" +#include "qed_nvmetcp.h" +#include "qed_ll2.h" +#include "qed_mcp.h" +#include "qed_sp.h" +#include "qed_reg_addr.h" +#include "qed_nvmetcp_fw_funcs.h" + +static int qed_nvmetcp_async_event(struct qed_hwfn *p_hwfn, u8 fw_event_code, + u16 echo, union event_ring_data *data, + u8 fw_return_code) +{ + if (p_hwfn->p_nvmetcp_info->event_cb) { + struct qed_nvmetcp_info *p_nvmetcp = p_hwfn->p_nvmetcp_info; + + return p_nvmetcp->event_cb(p_nvmetcp->event_context, + fw_event_code, data); + } else { + DP_NOTICE(p_hwfn, "nvmetcp async completion is not set\n"); + + return -EINVAL; + } +} + +static int qed_sp_nvmetcp_func_start(struct qed_hwfn *p_hwfn, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_addr, + void *event_context, + nvmetcp_event_cb_t async_event_cb) +{ + struct nvmetcp_init_ramrod_params *p_ramrod = NULL; + struct qed_nvmetcp_pf_params *p_params = NULL; + struct scsi_init_func_queues *p_queue = NULL; + struct nvmetcp_spe_func_init *p_init = NULL; + struct qed_sp_init_data init_data = {}; + struct qed_spq_entry *p_ent = NULL; + int rc = 0; + u16 val; + u8 i; + + /* Get SPQ entry */ + init_data.cid = qed_spq_get_cid(p_hwfn); + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = comp_mode; + init_data.p_comp_data = p_comp_addr; + rc = qed_sp_init_request(p_hwfn, &p_ent, + NVMETCP_RAMROD_CMD_ID_INIT_FUNC, + PROTOCOLID_TCP_ULP, &init_data); + if (rc) + return rc; + + p_ramrod = &p_ent->ramrod.nvmetcp_init; + p_init = &p_ramrod->nvmetcp_init_spe; + p_params = &p_hwfn->pf_params.nvmetcp_pf_params; + p_queue = &p_init->q_params; + p_init->num_sq_pages_in_ring = p_params->num_sq_pages_in_ring; + p_init->num_r2tq_pages_in_ring = p_params->num_r2tq_pages_in_ring; + p_init->num_uhq_pages_in_ring = p_params->num_uhq_pages_in_ring; + p_init->ll2_rx_queue_id = RESC_START(p_hwfn, QED_LL2_RAM_QUEUE) + + p_params->ll2_ooo_queue_id; + SET_FIELD(p_init->flags, NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE, 1); + p_init->func_params.log_page_size = ilog2(PAGE_SIZE); + p_init->func_params.num_tasks = cpu_to_le16(p_params->num_tasks); + p_init->debug_flags = p_params->debug_mode; + DMA_REGPAIR_LE(p_queue->glbl_q_params_addr, + p_params->glbl_q_params_addr); + p_queue->cq_num_entries = cpu_to_le16(QED_NVMETCP_FW_CQ_SIZE); + p_queue->num_queues = p_params->num_queues; + val = RESC_START(p_hwfn, QED_CMDQS_CQS); + p_queue->queue_relative_offset = cpu_to_le16((u16)val); + p_queue->cq_sb_pi = p_params->gl_rq_pi; + + for (i = 0; i < p_params->num_queues; i++) { + val = qed_get_igu_sb_id(p_hwfn, i); + p_queue->cq_cmdq_sb_num_arr[i] = cpu_to_le16(val); + } + + SET_FIELD(p_queue->q_validity, + SCSI_INIT_FUNC_QUEUES_CMD_VALID, 0); + p_queue->cmdq_num_entries = 0; + p_queue->bdq_resource_id = (u8)RESC_START(p_hwfn, QED_BDQ); + p_ramrod->tcp_init.two_msl_timer = cpu_to_le32(QED_TCP_TWO_MSL_TIMER); + p_ramrod->tcp_init.tx_sws_timer = cpu_to_le16(QED_TCP_SWS_TIMER); + p_init->half_way_close_timeout = cpu_to_le16(QED_TCP_HALF_WAY_CLOSE_TIMEOUT); + p_ramrod->tcp_init.max_fin_rt = QED_TCP_MAX_FIN_RT; + SET_FIELD(p_ramrod->nvmetcp_init_spe.params, + NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT, QED_TCP_MAX_FIN_RT); + p_hwfn->p_nvmetcp_info->event_context = event_context; + p_hwfn->p_nvmetcp_info->event_cb = async_event_cb; + qed_spq_register_async_cb(p_hwfn, PROTOCOLID_TCP_ULP, + qed_nvmetcp_async_event); + + return qed_spq_post(p_hwfn, p_ent, NULL); +} + +static int qed_sp_nvmetcp_func_stop(struct qed_hwfn *p_hwfn, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_addr) +{ + struct qed_spq_entry *p_ent = NULL; + struct qed_sp_init_data init_data; + int rc; + + /* Get SPQ entry */ + memset(&init_data, 0, sizeof(init_data)); + init_data.cid = qed_spq_get_cid(p_hwfn); + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = comp_mode; + init_data.p_comp_data = p_comp_addr; + rc = qed_sp_init_request(p_hwfn, &p_ent, + NVMETCP_RAMROD_CMD_ID_DESTROY_FUNC, + PROTOCOLID_TCP_ULP, &init_data); + if (rc) + return rc; + + rc = qed_spq_post(p_hwfn, p_ent, NULL); + qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_TCP_ULP); + + return rc; +} + +static int qed_fill_nvmetcp_dev_info(struct qed_dev *cdev, + struct qed_dev_nvmetcp_info *info) +{ + struct qed_hwfn *hwfn = QED_AFFIN_HWFN(cdev); + int rc; + + memset(info, 0, sizeof(*info)); + rc = qed_fill_dev_info(cdev, &info->common); + info->port_id = MFW_PORT(hwfn); + info->num_cqs = FEAT_NUM(hwfn, QED_NVMETCP_CQ); + + return rc; +} + +static void qed_register_nvmetcp_ops(struct qed_dev *cdev, + struct qed_nvmetcp_cb_ops *ops, + void *cookie) +{ + cdev->protocol_ops.nvmetcp = ops; + cdev->ops_cookie = cookie; +} + +static int qed_nvmetcp_stop(struct qed_dev *cdev) +{ + int rc; + + if (!(cdev->flags & QED_FLAG_STORAGE_STARTED)) { + DP_NOTICE(cdev, "nvmetcp already stopped\n"); + + return 0; + } + + if (!hash_empty(cdev->connections)) { + DP_NOTICE(cdev, + "Can't stop nvmetcp - not all connections were returned\n"); + + return -EINVAL; + } + + /* Stop the nvmetcp */ + rc = qed_sp_nvmetcp_func_stop(QED_AFFIN_HWFN(cdev), QED_SPQ_MODE_EBLOCK, + NULL); + cdev->flags &= ~QED_FLAG_STORAGE_STARTED; + + return rc; +} + +static int qed_nvmetcp_start(struct qed_dev *cdev, + struct qed_nvmetcp_tid *tasks, + void *event_context, + nvmetcp_event_cb_t async_event_cb) +{ + struct qed_tid_mem *tid_info; + int rc; + + if (cdev->flags & QED_FLAG_STORAGE_STARTED) { + DP_NOTICE(cdev, "nvmetcp already started;\n"); + + return 0; + } + + rc = qed_sp_nvmetcp_func_start(QED_AFFIN_HWFN(cdev), + QED_SPQ_MODE_EBLOCK, NULL, + event_context, async_event_cb); + if (rc) { + DP_NOTICE(cdev, "Failed to start nvmetcp\n"); + + return rc; + } + + cdev->flags |= QED_FLAG_STORAGE_STARTED; + hash_init(cdev->connections); + + if (!tasks) + return 0; + + tid_info = kzalloc(sizeof(*tid_info), GFP_KERNEL); + if (!tid_info) { + qed_nvmetcp_stop(cdev); + + return -ENOMEM; + } + + rc = qed_cxt_get_tid_mem_info(QED_AFFIN_HWFN(cdev), tid_info); + if (rc) { + DP_NOTICE(cdev, "Failed to gather task information\n"); + qed_nvmetcp_stop(cdev); + kfree(tid_info); + + return rc; + } + + /* Fill task information */ + tasks->size = tid_info->tid_size; + tasks->num_tids_per_block = tid_info->num_tids_per_block; + memcpy(tasks->blocks, tid_info->blocks, + MAX_TID_BLOCKS_NVMETCP * sizeof(u8 *)); + kfree(tid_info); + + return 0; +} + +static struct qed_hash_nvmetcp_con *qed_nvmetcp_get_hash(struct qed_dev *cdev, + u32 handle) +{ + struct qed_hash_nvmetcp_con *hash_con = NULL; + + if (!(cdev->flags & QED_FLAG_STORAGE_STARTED)) + return NULL; + + hash_for_each_possible(cdev->connections, hash_con, node, handle) { + if (hash_con->con->icid == handle) + break; + } + + if (!hash_con || hash_con->con->icid != handle) + return NULL; + + return hash_con; +} + +static int qed_sp_nvmetcp_conn_offload(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn *p_conn, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_addr) +{ + struct nvmetcp_spe_conn_offload *p_ramrod = NULL; + struct tcp_offload_params_opt2 *p_tcp = NULL; + struct qed_sp_init_data init_data = { 0 }; + struct qed_spq_entry *p_ent = NULL; + dma_addr_t r2tq_pbl_addr; + dma_addr_t xhq_pbl_addr; + dma_addr_t uhq_pbl_addr; + u16 physical_q; + int rc = 0; + u8 i; + + /* Get SPQ entry */ + init_data.cid = p_conn->icid; + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = comp_mode; + init_data.p_comp_data = p_comp_addr; + rc = qed_sp_init_request(p_hwfn, &p_ent, + NVMETCP_RAMROD_CMD_ID_OFFLOAD_CONN, + PROTOCOLID_TCP_ULP, &init_data); + if (rc) + return rc; + + p_ramrod = &p_ent->ramrod.nvmetcp_conn_offload; + + /* Transmission PQ is the first of the PF */ + physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD); + p_conn->physical_q0 = cpu_to_le16(physical_q); + p_ramrod->nvmetcp.physical_q0 = cpu_to_le16(physical_q); + + /* nvmetcp Pure-ACK PQ */ + physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_ACK); + p_conn->physical_q1 = cpu_to_le16(physical_q); + p_ramrod->nvmetcp.physical_q1 = cpu_to_le16(physical_q); + p_ramrod->conn_id = cpu_to_le16(p_conn->conn_id); + DMA_REGPAIR_LE(p_ramrod->nvmetcp.sq_pbl_addr, p_conn->sq_pbl_addr); + r2tq_pbl_addr = qed_chain_get_pbl_phys(&p_conn->r2tq); + DMA_REGPAIR_LE(p_ramrod->nvmetcp.r2tq_pbl_addr, r2tq_pbl_addr); + xhq_pbl_addr = qed_chain_get_pbl_phys(&p_conn->xhq); + DMA_REGPAIR_LE(p_ramrod->nvmetcp.xhq_pbl_addr, xhq_pbl_addr); + uhq_pbl_addr = qed_chain_get_pbl_phys(&p_conn->uhq); + DMA_REGPAIR_LE(p_ramrod->nvmetcp.uhq_pbl_addr, uhq_pbl_addr); + p_ramrod->nvmetcp.flags = p_conn->offl_flags; + p_ramrod->nvmetcp.default_cq = p_conn->default_cq; + p_ramrod->nvmetcp.initial_ack = 0; + DMA_REGPAIR_LE(p_ramrod->nvmetcp.nvmetcp.cccid_itid_table_addr, + p_conn->nvmetcp_cccid_itid_table_addr); + p_ramrod->nvmetcp.nvmetcp.cccid_max_range = + cpu_to_le16(p_conn->nvmetcp_cccid_max_range); + p_tcp = &p_ramrod->tcp; + qed_set_fw_mac_addr(&p_tcp->remote_mac_addr_hi, + &p_tcp->remote_mac_addr_mid, + &p_tcp->remote_mac_addr_lo, p_conn->remote_mac); + qed_set_fw_mac_addr(&p_tcp->local_mac_addr_hi, + &p_tcp->local_mac_addr_mid, + &p_tcp->local_mac_addr_lo, p_conn->local_mac); + p_tcp->vlan_id = cpu_to_le16(p_conn->vlan_id); + p_tcp->flags = cpu_to_le16(p_conn->tcp_flags); + p_tcp->ip_version = p_conn->ip_version; + if (p_tcp->ip_version == TCP_IPV6) { + for (i = 0; i < 4; i++) { + p_tcp->remote_ip[i] = cpu_to_le32(p_conn->remote_ip[i]); + p_tcp->local_ip[i] = cpu_to_le32(p_conn->local_ip[i]); + } + } else { + p_tcp->remote_ip[0] = cpu_to_le32(p_conn->remote_ip[0]); + p_tcp->local_ip[0] = cpu_to_le32(p_conn->local_ip[0]); + } + + p_tcp->flow_label = cpu_to_le32(p_conn->flow_label); + p_tcp->ttl = p_conn->ttl; + p_tcp->tos_or_tc = p_conn->tos_or_tc; + p_tcp->remote_port = cpu_to_le16(p_conn->remote_port); + p_tcp->local_port = cpu_to_le16(p_conn->local_port); + p_tcp->mss = cpu_to_le16(p_conn->mss); + p_tcp->rcv_wnd_scale = p_conn->rcv_wnd_scale; + p_tcp->connect_mode = p_conn->connect_mode; + p_tcp->cwnd = cpu_to_le32(p_conn->cwnd); + p_tcp->ka_max_probe_cnt = p_conn->ka_max_probe_cnt; + p_tcp->ka_timeout = cpu_to_le32(p_conn->ka_timeout); + p_tcp->max_rt_time = cpu_to_le32(p_conn->max_rt_time); + p_tcp->ka_interval = cpu_to_le32(p_conn->ka_interval); + + return qed_spq_post(p_hwfn, p_ent, NULL); +} + +static int qed_sp_nvmetcp_conn_update(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn *p_conn, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_addr) +{ + struct nvmetcp_conn_update_ramrod_params *p_ramrod = NULL; + struct qed_spq_entry *p_ent = NULL; + struct qed_sp_init_data init_data; + int rc = -EINVAL; + u32 dval; + + /* Get SPQ entry */ + memset(&init_data, 0, sizeof(init_data)); + init_data.cid = p_conn->icid; + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = comp_mode; + init_data.p_comp_data = p_comp_addr; + + rc = qed_sp_init_request(p_hwfn, &p_ent, + NVMETCP_RAMROD_CMD_ID_UPDATE_CONN, + PROTOCOLID_TCP_ULP, &init_data); + if (rc) + return rc; + + p_ramrod = &p_ent->ramrod.nvmetcp_conn_update; + p_ramrod->conn_id = cpu_to_le16(p_conn->conn_id); + p_ramrod->flags = p_conn->update_flag; + p_ramrod->max_seq_size = cpu_to_le32(p_conn->max_seq_size); + dval = p_conn->max_recv_pdu_length; + p_ramrod->max_recv_pdu_length = cpu_to_le32(dval); + dval = p_conn->max_send_pdu_length; + p_ramrod->max_send_pdu_length = cpu_to_le32(dval); + p_ramrod->first_seq_length = cpu_to_le32(p_conn->first_seq_length); + + return qed_spq_post(p_hwfn, p_ent, NULL); +} + +static int qed_sp_nvmetcp_conn_terminate(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn *p_conn, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_addr) +{ + struct nvmetcp_spe_conn_termination *p_ramrod = NULL; + struct qed_spq_entry *p_ent = NULL; + struct qed_sp_init_data init_data; + int rc = -EINVAL; + + /* Get SPQ entry */ + memset(&init_data, 0, sizeof(init_data)); + init_data.cid = p_conn->icid; + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = comp_mode; + init_data.p_comp_data = p_comp_addr; + rc = qed_sp_init_request(p_hwfn, &p_ent, + NVMETCP_RAMROD_CMD_ID_TERMINATION_CONN, + PROTOCOLID_TCP_ULP, &init_data); + if (rc) + return rc; + + p_ramrod = &p_ent->ramrod.nvmetcp_conn_terminate; + p_ramrod->conn_id = cpu_to_le16(p_conn->conn_id); + p_ramrod->abortive = p_conn->abortive_dsconnect; + + return qed_spq_post(p_hwfn, p_ent, NULL); +} + +static int qed_sp_nvmetcp_conn_clear_sq(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn *p_conn, + enum spq_mode comp_mode, + struct qed_spq_comp_cb *p_comp_addr) +{ + struct qed_spq_entry *p_ent = NULL; + struct qed_sp_init_data init_data; + int rc = -EINVAL; + + /* Get SPQ entry */ + memset(&init_data, 0, sizeof(init_data)); + init_data.cid = p_conn->icid; + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = comp_mode; + init_data.p_comp_data = p_comp_addr; + rc = qed_sp_init_request(p_hwfn, &p_ent, + NVMETCP_RAMROD_CMD_ID_CLEAR_SQ, + PROTOCOLID_TCP_ULP, &init_data); + if (rc) + return rc; + + return qed_spq_post(p_hwfn, p_ent, NULL); +} + +static void __iomem *qed_nvmetcp_get_db_addr(struct qed_hwfn *p_hwfn, u32 cid) +{ + return (u8 __iomem *)p_hwfn->doorbells + + qed_db_addr(cid, DQ_DEMS_LEGACY); +} + +static int qed_nvmetcp_allocate_connection(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn **p_out_conn) +{ + struct qed_chain_init_params params = { + .mode = QED_CHAIN_MODE_PBL, + .intended_use = QED_CHAIN_USE_TO_CONSUME_PRODUCE, + .cnt_type = QED_CHAIN_CNT_TYPE_U16, + }; + struct qed_nvmetcp_pf_params *p_params = NULL; + struct qed_nvmetcp_conn *p_conn = NULL; + int rc = 0; + + /* Try finding a free connection that can be used */ + spin_lock_bh(&p_hwfn->p_nvmetcp_info->lock); + if (!list_empty(&p_hwfn->p_nvmetcp_info->free_list)) + p_conn = list_first_entry(&p_hwfn->p_nvmetcp_info->free_list, + struct qed_nvmetcp_conn, list_entry); + if (p_conn) { + list_del(&p_conn->list_entry); + spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock); + *p_out_conn = p_conn; + + return 0; + } + spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock); + + /* Need to allocate a new connection */ + p_params = &p_hwfn->pf_params.nvmetcp_pf_params; + p_conn = kzalloc(sizeof(*p_conn), GFP_KERNEL); + if (!p_conn) + return -ENOMEM; + + params.num_elems = p_params->num_r2tq_pages_in_ring * + QED_CHAIN_PAGE_SIZE / sizeof(struct nvmetcp_wqe); + params.elem_size = sizeof(struct nvmetcp_wqe); + rc = qed_chain_alloc(p_hwfn->cdev, &p_conn->r2tq, ¶ms); + if (rc) + goto nomem_r2tq; + + params.num_elems = p_params->num_uhq_pages_in_ring * + QED_CHAIN_PAGE_SIZE / sizeof(struct iscsi_uhqe); + params.elem_size = sizeof(struct iscsi_uhqe); + rc = qed_chain_alloc(p_hwfn->cdev, &p_conn->uhq, ¶ms); + if (rc) + goto nomem_uhq; + + params.elem_size = sizeof(struct iscsi_xhqe); + rc = qed_chain_alloc(p_hwfn->cdev, &p_conn->xhq, ¶ms); + if (rc) + goto nomem; + + p_conn->free_on_delete = true; + *p_out_conn = p_conn; + + return 0; + +nomem: + qed_chain_free(p_hwfn->cdev, &p_conn->uhq); +nomem_uhq: + qed_chain_free(p_hwfn->cdev, &p_conn->r2tq); +nomem_r2tq: + kfree(p_conn); + + return -ENOMEM; +} + +static int qed_nvmetcp_acquire_connection(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn **p_out_conn) +{ + struct qed_nvmetcp_conn *p_conn = NULL; + int rc = 0; + u32 icid; + + spin_lock_bh(&p_hwfn->p_nvmetcp_info->lock); + rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_TCP_ULP, &icid); + spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock); + + if (rc) + return rc; + + rc = qed_nvmetcp_allocate_connection(p_hwfn, &p_conn); + if (rc) { + spin_lock_bh(&p_hwfn->p_nvmetcp_info->lock); + qed_cxt_release_cid(p_hwfn, icid); + spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock); + + return rc; + } + + p_conn->icid = icid; + p_conn->conn_id = (u16)icid; + p_conn->fw_cid = (p_hwfn->hw_info.opaque_fid << 16) | icid; + *p_out_conn = p_conn; + + return rc; +} + +static void qed_nvmetcp_release_connection(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn *p_conn) +{ + spin_lock_bh(&p_hwfn->p_nvmetcp_info->lock); + list_add_tail(&p_conn->list_entry, &p_hwfn->p_nvmetcp_info->free_list); + qed_cxt_release_cid(p_hwfn, p_conn->icid); + spin_unlock_bh(&p_hwfn->p_nvmetcp_info->lock); +} + +static void qed_nvmetcp_free_connection(struct qed_hwfn *p_hwfn, + struct qed_nvmetcp_conn *p_conn) +{ + qed_chain_free(p_hwfn->cdev, &p_conn->xhq); + qed_chain_free(p_hwfn->cdev, &p_conn->uhq); + qed_chain_free(p_hwfn->cdev, &p_conn->r2tq); + kfree(p_conn); +} + +int qed_nvmetcp_alloc(struct qed_hwfn *p_hwfn) +{ + struct qed_nvmetcp_info *p_nvmetcp_info; + + p_nvmetcp_info = kzalloc(sizeof(*p_nvmetcp_info), GFP_KERNEL); + if (!p_nvmetcp_info) + return -ENOMEM; + + INIT_LIST_HEAD(&p_nvmetcp_info->free_list); + p_hwfn->p_nvmetcp_info = p_nvmetcp_info; + + return 0; +} + +void qed_nvmetcp_setup(struct qed_hwfn *p_hwfn) +{ + spin_lock_init(&p_hwfn->p_nvmetcp_info->lock); +} + +void qed_nvmetcp_free(struct qed_hwfn *p_hwfn) +{ + struct qed_nvmetcp_conn *p_conn = NULL; + + if (!p_hwfn->p_nvmetcp_info) + return; + + while (!list_empty(&p_hwfn->p_nvmetcp_info->free_list)) { + p_conn = list_first_entry(&p_hwfn->p_nvmetcp_info->free_list, + struct qed_nvmetcp_conn, list_entry); + if (p_conn) { + list_del(&p_conn->list_entry); + qed_nvmetcp_free_connection(p_hwfn, p_conn); + } + } + + kfree(p_hwfn->p_nvmetcp_info); + p_hwfn->p_nvmetcp_info = NULL; +} + +static int qed_nvmetcp_acquire_conn(struct qed_dev *cdev, + u32 *handle, + u32 *fw_cid, void __iomem **p_doorbell) +{ + struct qed_hash_nvmetcp_con *hash_con; + int rc; + + /* Allocate a hashed connection */ + hash_con = kzalloc(sizeof(*hash_con), GFP_ATOMIC); + if (!hash_con) + return -ENOMEM; + + /* Acquire the connection */ + rc = qed_nvmetcp_acquire_connection(QED_AFFIN_HWFN(cdev), + &hash_con->con); + if (rc) { + DP_NOTICE(cdev, "Failed to acquire Connection\n"); + kfree(hash_con); + + return rc; + } + + /* Added the connection to hash table */ + *handle = hash_con->con->icid; + *fw_cid = hash_con->con->fw_cid; + hash_add(cdev->connections, &hash_con->node, *handle); + if (p_doorbell) + *p_doorbell = qed_nvmetcp_get_db_addr(QED_AFFIN_HWFN(cdev), + *handle); + + return 0; +} + +static int qed_nvmetcp_release_conn(struct qed_dev *cdev, u32 handle) +{ + struct qed_hash_nvmetcp_con *hash_con; + + hash_con = qed_nvmetcp_get_hash(cdev, handle); + if (!hash_con) { + DP_NOTICE(cdev, "Failed to find connection for handle %d\n", + handle); + + return -EINVAL; + } + + hlist_del(&hash_con->node); + qed_nvmetcp_release_connection(QED_AFFIN_HWFN(cdev), hash_con->con); + kfree(hash_con); + + return 0; +} + +static int qed_nvmetcp_offload_conn(struct qed_dev *cdev, u32 handle, + struct qed_nvmetcp_params_offload *conn_info) +{ + struct qed_hash_nvmetcp_con *hash_con; + struct qed_nvmetcp_conn *con; + + hash_con = qed_nvmetcp_get_hash(cdev, handle); + if (!hash_con) { + DP_NOTICE(cdev, "Failed to find connection for handle %d\n", + handle); + + return -EINVAL; + } + + /* Update the connection with information from the params */ + con = hash_con->con; + + /* FW initializations */ + con->layer_code = NVMETCP_SLOW_PATH_LAYER_CODE; + con->sq_pbl_addr = conn_info->sq_pbl_addr; + con->nvmetcp_cccid_max_range = conn_info->nvmetcp_cccid_max_range; + con->nvmetcp_cccid_itid_table_addr = conn_info->nvmetcp_cccid_itid_table_addr; + con->default_cq = conn_info->default_cq; + SET_FIELD(con->offl_flags, NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE, 0); + SET_FIELD(con->offl_flags, NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE, 1); + SET_FIELD(con->offl_flags, NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B, 1); + + /* Networking and TCP stack initializations */ + ether_addr_copy(con->local_mac, conn_info->src.mac); + ether_addr_copy(con->remote_mac, conn_info->dst.mac); + memcpy(con->local_ip, conn_info->src.ip, sizeof(con->local_ip)); + memcpy(con->remote_ip, conn_info->dst.ip, sizeof(con->remote_ip)); + con->local_port = conn_info->src.port; + con->remote_port = conn_info->dst.port; + con->vlan_id = conn_info->vlan_id; + + if (conn_info->timestamp_en) + SET_FIELD(con->tcp_flags, TCP_OFFLOAD_PARAMS_OPT2_TS_EN, 1); + + if (conn_info->delayed_ack_en) + SET_FIELD(con->tcp_flags, TCP_OFFLOAD_PARAMS_OPT2_DA_EN, 1); + + if (conn_info->tcp_keep_alive_en) + SET_FIELD(con->tcp_flags, TCP_OFFLOAD_PARAMS_OPT2_KA_EN, 1); + + if (conn_info->ecn_en) + SET_FIELD(con->tcp_flags, TCP_OFFLOAD_PARAMS_OPT2_ECN_EN, 1); + + con->ip_version = conn_info->ip_version; + con->flow_label = QED_TCP_FLOW_LABEL; + con->ka_max_probe_cnt = conn_info->ka_max_probe_cnt; + con->ka_timeout = conn_info->ka_timeout; + con->ka_interval = conn_info->ka_interval; + con->max_rt_time = conn_info->max_rt_time; + con->ttl = conn_info->ttl; + con->tos_or_tc = conn_info->tos_or_tc; + con->mss = conn_info->mss; + con->cwnd = conn_info->cwnd; + con->rcv_wnd_scale = conn_info->rcv_wnd_scale; + con->connect_mode = 0; + + return qed_sp_nvmetcp_conn_offload(QED_AFFIN_HWFN(cdev), con, + QED_SPQ_MODE_EBLOCK, NULL); +} + +static int qed_nvmetcp_update_conn(struct qed_dev *cdev, + u32 handle, + struct qed_nvmetcp_params_update *conn_info) +{ + struct qed_hash_nvmetcp_con *hash_con; + struct qed_nvmetcp_conn *con; + + hash_con = qed_nvmetcp_get_hash(cdev, handle); + if (!hash_con) { + DP_NOTICE(cdev, "Failed to find connection for handle %d\n", + handle); + + return -EINVAL; + } + + /* Update the connection with information from the params */ + con = hash_con->con; + SET_FIELD(con->update_flag, + ISCSI_CONN_UPDATE_RAMROD_PARAMS_INITIAL_R2T, 0); + SET_FIELD(con->update_flag, + ISCSI_CONN_UPDATE_RAMROD_PARAMS_IMMEDIATE_DATA, 1); + if (conn_info->hdr_digest_en) + SET_FIELD(con->update_flag, ISCSI_CONN_UPDATE_RAMROD_PARAMS_HD_EN, 1); + + if (conn_info->data_digest_en) + SET_FIELD(con->update_flag, ISCSI_CONN_UPDATE_RAMROD_PARAMS_DD_EN, 1); + + /* Placeholder - initialize pfv, cpda, hpda */ + + con->max_seq_size = conn_info->max_io_size; + con->max_recv_pdu_length = conn_info->max_recv_pdu_length; + con->max_send_pdu_length = conn_info->max_send_pdu_length; + con->first_seq_length = conn_info->max_io_size; + + return qed_sp_nvmetcp_conn_update(QED_AFFIN_HWFN(cdev), con, + QED_SPQ_MODE_EBLOCK, NULL); +} + +static int qed_nvmetcp_clear_conn_sq(struct qed_dev *cdev, u32 handle) +{ + struct qed_hash_nvmetcp_con *hash_con; + + hash_con = qed_nvmetcp_get_hash(cdev, handle); + if (!hash_con) { + DP_NOTICE(cdev, "Failed to find connection for handle %d\n", + handle); + + return -EINVAL; + } + + return qed_sp_nvmetcp_conn_clear_sq(QED_AFFIN_HWFN(cdev), hash_con->con, + QED_SPQ_MODE_EBLOCK, NULL); +} + +static int qed_nvmetcp_destroy_conn(struct qed_dev *cdev, + u32 handle, u8 abrt_conn) +{ + struct qed_hash_nvmetcp_con *hash_con; + + hash_con = qed_nvmetcp_get_hash(cdev, handle); + if (!hash_con) { + DP_NOTICE(cdev, "Failed to find connection for handle %d\n", + handle); + + return -EINVAL; + } + + hash_con->con->abortive_dsconnect = abrt_conn; + + return qed_sp_nvmetcp_conn_terminate(QED_AFFIN_HWFN(cdev), hash_con->con, + QED_SPQ_MODE_EBLOCK, NULL); +} + +static const struct qed_nvmetcp_ops qed_nvmetcp_ops_pass = { + .common = &qed_common_ops_pass, + .ll2 = &qed_ll2_ops_pass, + .fill_dev_info = &qed_fill_nvmetcp_dev_info, + .register_ops = &qed_register_nvmetcp_ops, + .start = &qed_nvmetcp_start, + .stop = &qed_nvmetcp_stop, + .acquire_conn = &qed_nvmetcp_acquire_conn, + .release_conn = &qed_nvmetcp_release_conn, + .offload_conn = &qed_nvmetcp_offload_conn, + .update_conn = &qed_nvmetcp_update_conn, + .destroy_conn = &qed_nvmetcp_destroy_conn, + .clear_sq = &qed_nvmetcp_clear_conn_sq, + .add_src_tcp_port_filter = &qed_llh_add_src_tcp_port_filter, + .remove_src_tcp_port_filter = &qed_llh_remove_src_tcp_port_filter, + .add_dst_tcp_port_filter = &qed_llh_add_dst_tcp_port_filter, + .remove_dst_tcp_port_filter = &qed_llh_remove_dst_tcp_port_filter, + .clear_all_filters = &qed_llh_clear_all_filters, + .init_read_io = &init_nvmetcp_host_read_task, + .init_write_io = &init_nvmetcp_host_write_task, + .init_icreq_exchange = &init_nvmetcp_init_conn_req_task, + .init_task_cleanup = &init_cleanup_task_nvmetcp +}; + +const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void) +{ + return &qed_nvmetcp_ops_pass; +} +EXPORT_SYMBOL(qed_get_nvmetcp_ops); + +void qed_put_nvmetcp_ops(void) +{ +} +EXPORT_SYMBOL(qed_put_nvmetcp_ops); diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h new file mode 100644 index 000000000000..e5e9d075bf4f --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright 2021 Marvell. All rights reserved. */ + +#ifndef _QED_NVMETCP_H +#define _QED_NVMETCP_H + +#include +#include +#include +#include +#include +#include +#include +#include "qed.h" +#include "qed_hsi.h" +#include "qed_mcp.h" +#include "qed_sp.h" + +#define QED_NVMETCP_FW_CQ_SIZE (4 * 1024) + +/* tcp parameters */ +#define QED_TCP_FLOW_LABEL 0 +#define QED_TCP_TWO_MSL_TIMER 4000 +#define QED_TCP_HALF_WAY_CLOSE_TIMEOUT 10 +#define QED_TCP_MAX_FIN_RT 2 +#define QED_TCP_SWS_TIMER 5000 + +struct qed_nvmetcp_info { + spinlock_t lock; /* Connection resources. */ + struct list_head free_list; + u16 max_num_outstanding_tasks; + void *event_context; + nvmetcp_event_cb_t event_cb; +}; + +struct qed_hash_nvmetcp_con { + struct hlist_node node; + struct qed_nvmetcp_conn *con; +}; + +struct qed_nvmetcp_conn { + struct list_head list_entry; + bool free_on_delete; + u16 conn_id; + u32 icid; + u32 fw_cid; + u8 layer_code; + u8 offl_flags; + u8 connect_mode; + dma_addr_t sq_pbl_addr; + struct qed_chain r2tq; + struct qed_chain xhq; + struct qed_chain uhq; + u8 local_mac[6]; + u8 remote_mac[6]; + u8 ip_version; + u8 ka_max_probe_cnt; + u16 vlan_id; + u16 tcp_flags; + u32 remote_ip[4]; + u32 local_ip[4]; + u32 flow_label; + u32 ka_timeout; + u32 ka_interval; + u32 max_rt_time; + u8 ttl; + u8 tos_or_tc; + u16 remote_port; + u16 local_port; + u16 mss; + u8 rcv_wnd_scale; + u32 rcv_wnd; + u32 cwnd; + u8 update_flag; + u8 default_cq; + u8 abortive_dsconnect; + u32 max_seq_size; + u32 max_recv_pdu_length; + u32 max_send_pdu_length; + u32 first_seq_length; + u16 physical_q0; + u16 physical_q1; + u16 nvmetcp_cccid_max_range; + dma_addr_t nvmetcp_cccid_itid_table_addr; +}; + +#if IS_ENABLED(CONFIG_QED_NVMETCP) +int qed_nvmetcp_alloc(struct qed_hwfn *p_hwfn); +void qed_nvmetcp_setup(struct qed_hwfn *p_hwfn); +void qed_nvmetcp_free(struct qed_hwfn *p_hwfn); + +#else /* IS_ENABLED(CONFIG_QED_NVMETCP) */ +static inline int qed_nvmetcp_alloc(struct qed_hwfn *p_hwfn) +{ + return -EINVAL; +} + +static inline void qed_nvmetcp_setup(struct qed_hwfn *p_hwfn) {} +static inline void qed_nvmetcp_free(struct qed_hwfn *p_hwfn) {} + +#endif /* IS_ENABLED(CONFIG_QED_NVMETCP) */ + +#endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c new file mode 100644 index 000000000000..c1dd71d19f3f --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) +/* Copyright 2021 Marvell. All rights reserved. */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "qed_nvmetcp_fw_funcs.h" + +#define NVMETCP_NUM_SGES_IN_CACHE 0x4 + +bool nvmetcp_is_slow_sgl(u16 num_sges, bool small_mid_sge) +{ + return (num_sges > SCSI_NUM_SGES_SLOW_SGL_THR && small_mid_sge); +} + +void init_scsi_sgl_context(struct scsi_sgl_params *ctx_sgl_params, + struct scsi_cached_sges *ctx_data_desc, + struct storage_sgl_task_params *sgl_params) +{ + u8 num_sges_to_init = (u8)(sgl_params->num_sges > NVMETCP_NUM_SGES_IN_CACHE ? + NVMETCP_NUM_SGES_IN_CACHE : sgl_params->num_sges); + u8 sge_index; + + /* sgl params */ + ctx_sgl_params->sgl_addr.lo = cpu_to_le32(sgl_params->sgl_phys_addr.lo); + ctx_sgl_params->sgl_addr.hi = cpu_to_le32(sgl_params->sgl_phys_addr.hi); + ctx_sgl_params->sgl_total_length = cpu_to_le32(sgl_params->total_buffer_size); + ctx_sgl_params->sgl_num_sges = cpu_to_le16(sgl_params->num_sges); + + for (sge_index = 0; sge_index < num_sges_to_init; sge_index++) { + ctx_data_desc->sge[sge_index].sge_addr.lo = + cpu_to_le32(sgl_params->sgl[sge_index].sge_addr.lo); + ctx_data_desc->sge[sge_index].sge_addr.hi = + cpu_to_le32(sgl_params->sgl[sge_index].sge_addr.hi); + ctx_data_desc->sge[sge_index].sge_len = + cpu_to_le32(sgl_params->sgl[sge_index].sge_len); + } +} + +static inline u32 calc_rw_task_size(struct nvmetcp_task_params *task_params, + enum nvmetcp_task_type task_type) +{ + u32 io_size; + + if (task_type == NVMETCP_TASK_TYPE_HOST_WRITE) + io_size = task_params->tx_io_size; + else + io_size = task_params->rx_io_size; + + if (unlikely(!io_size)) + return 0; + + return io_size; +} + +static inline void init_sqe(struct nvmetcp_task_params *task_params, + struct storage_sgl_task_params *sgl_task_params, + enum nvmetcp_task_type task_type) +{ + if (!task_params->sqe) + return; + + memset(task_params->sqe, 0, sizeof(*task_params->sqe)); + task_params->sqe->task_id = cpu_to_le16(task_params->itid); + + switch (task_type) { + case NVMETCP_TASK_TYPE_HOST_WRITE: { + u32 buf_size = 0; + u32 num_sges = 0; + + SET_FIELD(task_params->sqe->contlen_cdbsize, + NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD, 1); + SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_WQE_TYPE, + NVMETCP_WQE_TYPE_NORMAL); + if (task_params->tx_io_size) { + if (task_params->send_write_incapsule) + buf_size = calc_rw_task_size(task_params, task_type); + + if (nvmetcp_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge)) + num_sges = NVMETCP_WQE_NUM_SGES_SLOWIO; + else + num_sges = min((u16)sgl_task_params->num_sges, + (u16)SCSI_NUM_SGES_SLOW_SGL_THR); + } + SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_NUM_SGES, num_sges); + SET_FIELD(task_params->sqe->contlen_cdbsize, NVMETCP_WQE_CONT_LEN, buf_size); + } break; + + case NVMETCP_TASK_TYPE_HOST_READ: { + SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_WQE_TYPE, + NVMETCP_WQE_TYPE_NORMAL); + SET_FIELD(task_params->sqe->contlen_cdbsize, + NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD, 1); + } break; + + case NVMETCP_TASK_TYPE_INIT_CONN_REQUEST: { + SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_WQE_TYPE, + NVMETCP_WQE_TYPE_MIDDLE_PATH); + + if (task_params->tx_io_size) { + SET_FIELD(task_params->sqe->contlen_cdbsize, NVMETCP_WQE_CONT_LEN, + task_params->tx_io_size); + SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_NUM_SGES, + min((u16)sgl_task_params->num_sges, + (u16)SCSI_NUM_SGES_SLOW_SGL_THR)); + } + } break; + + case NVMETCP_TASK_TYPE_CLEANUP: + SET_FIELD(task_params->sqe->flags, NVMETCP_WQE_WQE_TYPE, + NVMETCP_WQE_TYPE_TASK_CLEANUP); + + default: + break; + } +} + +/* The following function initializes of NVMeTCP task params */ +static inline void +init_nvmetcp_task_params(struct e5_nvmetcp_task_context *context, + struct nvmetcp_task_params *task_params, + enum nvmetcp_task_type task_type) +{ + context->ystorm_st_context.state.cccid = task_params->host_cccid; + SET_FIELD(context->ustorm_st_context.error_flags, USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP, 1); + context->ustorm_st_context.nvme_tcp_opaque_lo = cpu_to_le32(task_params->opq.lo); + context->ustorm_st_context.nvme_tcp_opaque_hi = cpu_to_le32(task_params->opq.hi); +} + +/* The following function initializes default values to all tasks */ +static inline void +init_default_nvmetcp_task(struct nvmetcp_task_params *task_params, + void *pdu_header, void *nvme_cmd, + enum nvmetcp_task_type task_type) +{ + struct e5_nvmetcp_task_context *context = task_params->context; + const u8 val_byte = context->mstorm_ag_context.cdu_validation; + u8 dw_index; + + memset(context, 0, sizeof(*context)); + init_nvmetcp_task_params(context, task_params, + (enum nvmetcp_task_type)task_type); + + /* Swapping requirements used below, will be removed in future FW versions */ + if (task_type == NVMETCP_TASK_TYPE_HOST_WRITE || + task_type == NVMETCP_TASK_TYPE_HOST_READ) { + for (dw_index = 0; + dw_index < QED_NVMETCP_CMN_HDR_SIZE / sizeof(u32); + dw_index++) + context->ystorm_st_context.pdu_hdr.task_hdr.reg[dw_index] = + cpu_to_le32(__swab32(((u32 *)pdu_header)[dw_index])); + + for (dw_index = QED_NVMETCP_CMN_HDR_SIZE / sizeof(u32); + dw_index < QED_NVMETCP_CMD_HDR_SIZE / sizeof(u32); + dw_index++) + context->ystorm_st_context.pdu_hdr.task_hdr.reg[dw_index] = + cpu_to_le32(__swab32(((u32 *)nvme_cmd)[dw_index - 2])); + } else { + for (dw_index = 0; + dw_index < QED_NVMETCP_NON_IO_HDR_SIZE / sizeof(u32); + dw_index++) + context->ystorm_st_context.pdu_hdr.task_hdr.reg[dw_index] = + cpu_to_le32(__swab32(((u32 *)pdu_header)[dw_index])); + } + + /* M-Storm Context: */ + context->mstorm_ag_context.cdu_validation = val_byte; + context->mstorm_st_context.task_type = (u8)(task_type); + context->mstorm_ag_context.task_cid = cpu_to_le16(task_params->conn_icid); + + /* Ustorm Context: */ + SET_FIELD(context->ustorm_ag_context.flags1, E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV, 1); + context->ustorm_st_context.task_type = (u8)(task_type); + context->ustorm_st_context.cq_rss_number = task_params->cq_rss_number; + context->ustorm_ag_context.icid = cpu_to_le16(task_params->conn_icid); +} + +/* The following function initializes the U-Storm Task Contexts */ +static inline void +init_ustorm_task_contexts(struct ustorm_nvmetcp_task_st_ctx *ustorm_st_context, + struct e5_ustorm_nvmetcp_task_ag_ctx *ustorm_ag_context, + u32 remaining_recv_len, + u32 expected_data_transfer_len, u8 num_sges, + bool tx_dif_conn_err_en) +{ + /* Remaining data to be received in bytes. Used in validations*/ + ustorm_st_context->rem_rcv_len = cpu_to_le32(remaining_recv_len); + ustorm_ag_context->exp_data_acked = cpu_to_le32(expected_data_transfer_len); + ustorm_st_context->exp_data_transfer_len = cpu_to_le32(expected_data_transfer_len); + SET_FIELD(ustorm_st_context->reg1_map, REG1_NUM_SGES, num_sges); + SET_FIELD(ustorm_ag_context->flags2, E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN, + tx_dif_conn_err_en ? 1 : 0); +} + +/* The following function initializes Local Completion Contexts: */ +static inline void +set_local_completion_context(struct e5_nvmetcp_task_context *context) +{ + SET_FIELD(context->ystorm_st_context.state.flags, + YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP, 1); + SET_FIELD(context->ustorm_st_context.flags, + USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP, 1); +} + +/* Common Fastpath task init function: */ +static inline void +init_rw_nvmetcp_task(struct nvmetcp_task_params *task_params, + enum nvmetcp_task_type task_type, + void *pdu_header, void *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params) +{ + struct e5_nvmetcp_task_context *context = task_params->context; + u32 task_size = calc_rw_task_size(task_params, task_type); + bool slow_io = false; + u8 num_sges = 0; + + init_default_nvmetcp_task(task_params, pdu_header, nvme_cmd, task_type); + + /* Tx/Rx: */ + if (task_params->tx_io_size) { + /* if data to transmit: */ + init_scsi_sgl_context(&context->ystorm_st_context.state.sgl_params, + &context->ystorm_st_context.state.data_desc, + sgl_task_params); + slow_io = nvmetcp_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge); + num_sges = + (u8)(!slow_io ? min((u32)sgl_task_params->num_sges, + (u32)SCSI_NUM_SGES_SLOW_SGL_THR) : + NVMETCP_WQE_NUM_SGES_SLOWIO); + if (slow_io) { + SET_FIELD(context->ystorm_st_context.state.flags, + YSTORM_NVMETCP_TASK_STATE_SLOW_IO, 1); + } + } else if (task_params->rx_io_size) { + /* if data to receive: */ + init_scsi_sgl_context(&context->mstorm_st_context.sgl_params, + &context->mstorm_st_context.data_desc, + sgl_task_params); + num_sges = + (u8)(!nvmetcp_is_slow_sgl(sgl_task_params->num_sges, + sgl_task_params->small_mid_sge) ? + min((u32)sgl_task_params->num_sges, + (u32)SCSI_NUM_SGES_SLOW_SGL_THR) : + NVMETCP_WQE_NUM_SGES_SLOWIO); + context->mstorm_st_context.rem_task_size = cpu_to_le32(task_size); + } + + /* Ustorm context: */ + init_ustorm_task_contexts(&context->ustorm_st_context, + &context->ustorm_ag_context, + /* Remaining Receive length is the Task Size */ + task_size, + /* The size of the transmitted task */ + task_size, + /* num_sges */ + num_sges, + false); + + /* Set exp_data_acked */ + if (task_type == NVMETCP_TASK_TYPE_HOST_WRITE) { + if (task_params->send_write_incapsule) + context->ustorm_ag_context.exp_data_acked = task_size; + else + context->ustorm_ag_context.exp_data_acked = 0; + } else if (task_type == NVMETCP_TASK_TYPE_HOST_READ) { + context->ustorm_ag_context.exp_data_acked = 0; + } + + context->ustorm_ag_context.exp_cont_len = 0; + init_sqe(task_params, sgl_task_params, task_type); +} + +static void +init_common_initiator_read_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params) +{ + init_rw_nvmetcp_task(task_params, NVMETCP_TASK_TYPE_HOST_READ, + cmd_pdu_header, nvme_cmd, sgl_task_params); +} + +void init_nvmetcp_host_read_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params) +{ + init_common_initiator_read_task(task_params, (void *)cmd_pdu_header, + (void *)nvme_cmd, sgl_task_params); +} + +static void +init_common_initiator_write_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params) +{ + init_rw_nvmetcp_task(task_params, NVMETCP_TASK_TYPE_HOST_WRITE, + cmd_pdu_header, nvme_cmd, sgl_task_params); +} + +void init_nvmetcp_host_write_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params) +{ + init_common_initiator_write_task(task_params, (void *)cmd_pdu_header, + (void *)nvme_cmd, sgl_task_params); +} + +static void +init_common_login_request_task(struct nvmetcp_task_params *task_params, + void *login_req_pdu_header, + struct storage_sgl_task_params *tx_sgl_task_params, + struct storage_sgl_task_params *rx_sgl_task_params) +{ + struct e5_nvmetcp_task_context *context = task_params->context; + + init_default_nvmetcp_task(task_params, (void *)login_req_pdu_header, NULL, + NVMETCP_TASK_TYPE_INIT_CONN_REQUEST); + + /* Ustorm Context: */ + init_ustorm_task_contexts(&context->ustorm_st_context, + &context->ustorm_ag_context, + + /* Remaining Receive length is the Task Size */ + task_params->rx_io_size ? + rx_sgl_task_params->total_buffer_size : 0, + + /* The size of the transmitted task */ + task_params->tx_io_size ? + tx_sgl_task_params->total_buffer_size : 0, + 0, /* num_sges */ + 0); /* tx_dif_conn_err_en */ + + /* SGL context: */ + if (task_params->tx_io_size) + init_scsi_sgl_context(&context->ystorm_st_context.state.sgl_params, + &context->ystorm_st_context.state.data_desc, + tx_sgl_task_params); + if (task_params->rx_io_size) + init_scsi_sgl_context(&context->mstorm_st_context.sgl_params, + &context->mstorm_st_context.data_desc, + rx_sgl_task_params); + + context->mstorm_st_context.rem_task_size = + cpu_to_le32(task_params->rx_io_size ? + rx_sgl_task_params->total_buffer_size : 0); + init_sqe(task_params, tx_sgl_task_params, NVMETCP_TASK_TYPE_INIT_CONN_REQUEST); +} + +/* The following function initializes Login task in Host mode: */ +void init_nvmetcp_init_conn_req_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_icreq_pdu *init_conn_req_pdu_hdr, + struct storage_sgl_task_params *tx_sgl_task_params, + struct storage_sgl_task_params *rx_sgl_task_params) +{ + init_common_login_request_task(task_params, init_conn_req_pdu_hdr, + tx_sgl_task_params, rx_sgl_task_params); +} + +void init_cleanup_task_nvmetcp(struct nvmetcp_task_params *task_params) +{ + init_sqe(task_params, NULL, NVMETCP_TASK_TYPE_CLEANUP); +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.h b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.h new file mode 100644 index 000000000000..1d5ddc217bdb --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_fw_funcs.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright 2021 Marvell. All rights reserved. */ + +#ifndef _QED_NVMETCP_FW_FUNCS_H +#define _QED_NVMETCP_FW_FUNCS_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if IS_ENABLED(CONFIG_QED_NVMETCP) + +void init_nvmetcp_host_read_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params); +void init_nvmetcp_host_write_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params); +void init_nvmetcp_init_conn_req_task(struct nvmetcp_task_params *task_params, + struct nvme_tcp_icreq_pdu *init_conn_req_pdu_hdr, + struct storage_sgl_task_params *tx_sgl_task_params, + struct storage_sgl_task_params *rx_sgl_task_params); +void init_cleanup_task_nvmetcp(struct nvmetcp_task_params *task_params); + +#else /* IS_ENABLED(CONFIG_QED_NVMETCP) */ + +#endif /* IS_ENABLED(CONFIG_QED_NVMETCP) */ + +#endif /* _QED_NVMETCP_FW_FUNCS_H */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c new file mode 100644 index 000000000000..96a2077fd315 --- /dev/null +++ b/drivers/net/ethernet/qlogic/qed/qed_nvmetcp_ip_services.c @@ -0,0 +1,238 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) +/* + * Copyright 2021 Marvell. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include + +#define QED_IP_RESOL_TIMEOUT 4 + +int qed_route_ipv4(struct sockaddr_storage *local_addr, + struct sockaddr_storage *remote_addr, + struct sockaddr *hardware_address, + struct net_device **ndev) +{ + struct neighbour *neigh = NULL; + __be32 *loc_ip, *rem_ip; + struct rtable *rt; + int rc = -ENXIO; + int retry; + + loc_ip = &((struct sockaddr_in *)local_addr)->sin_addr.s_addr; + rem_ip = &((struct sockaddr_in *)remote_addr)->sin_addr.s_addr; + *ndev = NULL; + rt = ip_route_output(&init_net, *rem_ip, *loc_ip, 0/*tos*/, 0/*oif*/); + if (IS_ERR(rt)) { + pr_err("lookup route failed\n"); + rc = PTR_ERR(rt); + goto return_err; + } + + neigh = dst_neigh_lookup(&rt->dst, rem_ip); + if (!neigh) { + rc = -ENOMEM; + ip_rt_put(rt); + goto return_err; + } + + *ndev = rt->dst.dev; + ip_rt_put(rt); + + /* If not resolved, kick-off state machine towards resolution */ + if (!(neigh->nud_state & NUD_VALID)) + neigh_event_send(neigh, NULL); + + /* query neighbor until resolved or timeout */ + retry = QED_IP_RESOL_TIMEOUT; + while (!(neigh->nud_state & NUD_VALID) && retry > 0) { + msleep(1000); + retry--; + } + + if (neigh->nud_state & NUD_VALID) { + /* copy resolved MAC address */ + neigh_ha_snapshot(hardware_address->sa_data, neigh, *ndev); + hardware_address->sa_family = (*ndev)->type; + rc = 0; + } + + neigh_release(neigh); + if (!(*loc_ip)) { + *loc_ip = inet_select_addr(*ndev, *rem_ip, RT_SCOPE_UNIVERSE); + local_addr->ss_family = AF_INET; + } + +return_err: + + return rc; +} +EXPORT_SYMBOL(qed_route_ipv4); + +int qed_route_ipv6(struct sockaddr_storage *local_addr, + struct sockaddr_storage *remote_addr, + struct sockaddr *hardware_address, + struct net_device **ndev) +{ + struct neighbour *neigh = NULL; + struct dst_entry *dst; + struct flowi6 fl6; + int rc = -ENXIO; + int retry; + + memset(&fl6, 0, sizeof(fl6)); + fl6.saddr = ((struct sockaddr_in6 *)local_addr)->sin6_addr; + fl6.daddr = ((struct sockaddr_in6 *)remote_addr)->sin6_addr; + dst = ip6_route_output(&init_net, NULL, &fl6); + if (!dst || dst->error) { + if (dst) { + dst_release(dst); + pr_err("lookup route failed %d\n", dst->error); + } + + goto out; + } + + neigh = dst_neigh_lookup(dst, &fl6.daddr); + if (neigh) { + *ndev = ip6_dst_idev(dst)->dev; + + /* If not resolved, kick-off state machine towards resolution */ + if (!(neigh->nud_state & NUD_VALID)) + neigh_event_send(neigh, NULL); + + /* query neighbor until resolved or timeout */ + retry = QED_IP_RESOL_TIMEOUT; + while (!(neigh->nud_state & NUD_VALID) && retry > 0) { + msleep(1000); + retry--; + } + + if (neigh->nud_state & NUD_VALID) { + neigh_ha_snapshot((u8 *)hardware_address->sa_data, + neigh, *ndev); + hardware_address->sa_family = (*ndev)->type; + rc = 0; + } + + neigh_release(neigh); + + if (ipv6_addr_any(&fl6.saddr)) { + if (ipv6_dev_get_saddr(dev_net(*ndev), *ndev, + &fl6.daddr, 0, &fl6.saddr)) { + pr_err("Unable to find source IP address\n"); + goto out; + } + + local_addr->ss_family = AF_INET6; + ((struct sockaddr_in6 *)local_addr)->sin6_addr = + fl6.saddr; + } + } + + dst_release(dst); + +out: + + return rc; +} +EXPORT_SYMBOL(qed_route_ipv6); + +void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id) +{ + if (is_vlan_dev(*ndev)) { + *vlan_id = vlan_dev_vlan_id(*ndev); + *ndev = vlan_dev_real_dev(*ndev); + } +} +EXPORT_SYMBOL(qed_vlan_get_ndev); + +struct pci_dev *qed_validate_ndev(struct net_device *ndev) +{ + struct pci_dev *pdev = NULL; + struct net_device *upper; + + for_each_pci_dev(pdev) { + if (pdev && pdev->driver && + !strcmp(pdev->driver->name, "qede")) { + upper = pci_get_drvdata(pdev); + if (upper->ifindex == ndev->ifindex) + return pdev; + } + } + + return NULL; +} +EXPORT_SYMBOL(qed_validate_ndev); + +__be16 qed_get_in_port(struct sockaddr_storage *sa) +{ + return sa->ss_family == AF_INET + ? ((struct sockaddr_in *)sa)->sin_port + : ((struct sockaddr_in6 *)sa)->sin6_port; +} +EXPORT_SYMBOL(qed_get_in_port); + +int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr, + struct socket **sock, u16 *port) +{ + struct sockaddr_storage sa; + int rc = 0; + + rc = sock_create(local_ip_addr.ss_family, SOCK_STREAM, IPPROTO_TCP, + sock); + if (rc) { + pr_warn("failed to create socket: %d\n", rc); + goto err; + } + + (*sock)->sk->sk_allocation = GFP_KERNEL; + sk_set_memalloc((*sock)->sk); + + rc = kernel_bind(*sock, (struct sockaddr *)&local_ip_addr, + sizeof(local_ip_addr)); + + if (rc) { + pr_warn("failed to bind socket: %d\n", rc); + goto err_sock; + } + + rc = kernel_getsockname(*sock, (struct sockaddr *)&sa); + if (rc < 0) { + pr_warn("getsockname() failed: %d\n", rc); + goto err_sock; + } + + *port = ntohs(qed_get_in_port(&sa)); + + return 0; + +err_sock: + sock_release(*sock); + sock = NULL; +err: + + return rc; +} +EXPORT_SYMBOL(qed_fetch_tcp_port); + +void qed_return_tcp_port(struct socket *sock) +{ + if (sock && sock->sk) { + tcp_set_state(sock->sk, TCP_CLOSE); + sock_release(sock); + } +} +EXPORT_SYMBOL(qed_return_tcp_port); diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c index 88353aa404dc..b8c5641b29a8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c @@ -16,7 +16,7 @@ #include "qed_ll2.h" #include "qed_ooo.h" #include "qed_cxt.h" - +#include "qed_nvmetcp.h" static struct qed_ooo_archipelago *qed_ooo_seek_archipelago(struct qed_hwfn *p_hwfn, struct qed_ooo_info @@ -83,7 +83,8 @@ int qed_ooo_alloc(struct qed_hwfn *p_hwfn) switch (p_hwfn->hw_info.personality) { case QED_PCI_ISCSI: - proto = PROTOCOLID_ISCSI; + case QED_PCI_NVMETCP: + proto = PROTOCOLID_TCP_ULP; break; case QED_PCI_ETH_RDMA: case QED_PCI_ETH_IWARP: diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 993f1357b6fc..60ff3222bf55 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -100,6 +100,11 @@ union ramrod_data { struct iscsi_spe_conn_mac_update iscsi_conn_mac_update; struct iscsi_spe_conn_termination iscsi_conn_terminate; + struct nvmetcp_init_ramrod_params nvmetcp_init; + struct nvmetcp_spe_conn_offload nvmetcp_conn_offload; + struct nvmetcp_conn_update_ramrod_params nvmetcp_conn_update; + struct nvmetcp_spe_conn_termination nvmetcp_conn_terminate; + struct vf_start_ramrod_data vf_start; struct vf_stop_ramrod_data vf_stop; }; diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index aa71adcf31ee..b4ed54ffef9b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -385,7 +385,8 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, p_ramrod->personality = PERSONALITY_FCOE; break; case QED_PCI_ISCSI: - p_ramrod->personality = PERSONALITY_ISCSI; + case QED_PCI_NVMETCP: + p_ramrod->personality = PERSONALITY_TCP_ULP; break; case QED_PCI_ETH_ROCE: case QED_PCI_ETH_IWARP: diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 8e150dd4f899..065e9004598e 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1089,13 +1089,7 @@ static bool qede_rx_xdp(struct qede_dev *edev, xdp_prepare_buff(&xdp, page_address(bd->data), *data_offset, *len, false); - /* Queues always have a full reset currently, so for the time - * being until there's atomic program replace just mark read - * side for map helpers. - */ - rcu_read_lock(); act = bpf_prog_run_xdp(prog, &xdp); - rcu_read_unlock(); /* Recalculate, as XDP might have changed the headers */ *data_offset = xdp.data - xdp.data_hard_start; diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c index 2f6598086d9b..6304514a6f2c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c +++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c @@ -247,12 +247,10 @@ static struct qede_rdma_event_work * qede_rdma_get_free_event_node(struct qede_dev *edev) { struct qede_rdma_event_work *event_node = NULL; - struct list_head *list_node = NULL; bool found = false; - list_for_each(list_node, &edev->rdma_info.rdma_event_list) { - event_node = list_entry(list_node, struct qede_rdma_event_work, - list); + list_for_each_entry(event_node, &edev->rdma_info.rdma_event_list, + list) { if (!work_pending(&event_node->work)) { found = true; break; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index d2c190732d3e..0a2f34fc8b24 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -746,7 +746,7 @@ static int qlcnic_83xx_idc_unknown_state(struct qlcnic_adapter *adapter) } /** - * qlcnic_83xx_idc_cold_state + * qlcnic_83xx_idc_cold_state_handler * * @adapter: adapter structure * diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c index c4297aea7d15..711609503ba6 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_vnic.c @@ -180,7 +180,7 @@ static int qlcnic_83xx_init_non_privileged_vnic(struct qlcnic_adapter *adapter) } /** - * qlcnic_83xx_vnic_opmode + * qlcnic_83xx_config_vnic_opmode * * @adapter: adapter structure * Identify virtual NIC operational modes. diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c index e1b8490bed0a..4b8bc46f55c2 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c @@ -460,12 +460,10 @@ int qlcnic_82xx_sre_macaddr_change(struct qlcnic_adapter *adapter, u8 *addr, int qlcnic_nic_del_mac(struct qlcnic_adapter *adapter, const u8 *addr) { struct qlcnic_mac_vlan_list *cur; - struct list_head *head; int err = -EINVAL; /* Delete MAC from the existing list */ - list_for_each(head, &adapter->mac_list) { - cur = list_entry(head, struct qlcnic_mac_vlan_list, list); + list_for_each_entry(cur, &adapter->mac_list, list) { if (ether_addr_equal(addr, cur->mac_addr)) { err = qlcnic_sre_macaddr_change(adapter, cur->mac_addr, 0, QLCNIC_MAC_DEL); @@ -483,11 +481,9 @@ int qlcnic_nic_add_mac(struct qlcnic_adapter *adapter, const u8 *addr, u16 vlan, enum qlcnic_mac_type mac_type) { struct qlcnic_mac_vlan_list *cur; - struct list_head *head; /* look up if already exists */ - list_for_each(head, &adapter->mac_list) { - cur = list_entry(head, struct qlcnic_mac_vlan_list, list); + list_for_each_entry(cur, &adapter->mac_list, list) { if (ether_addr_equal(addr, cur->mac_addr) && cur->vlan_id == vlan) return 0; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h index 601d22495a88..95ecc84dddcd 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h @@ -203,7 +203,6 @@ int qlcnic_82xx_set_nic_info(struct qlcnic_adapter *, struct qlcnic_info *); int qlcnic_82xx_get_pci_info(struct qlcnic_adapter *, struct qlcnic_pci_info*); int qlcnic_82xx_alloc_mbx_args(struct qlcnic_cmd_args *, struct qlcnic_adapter *, u32); -int qlcnic_82xx_hw_write_wx_2M(struct qlcnic_adapter *, ulong, u32); int qlcnic_82xx_get_board_info(struct qlcnic_adapter *); int qlcnic_82xx_config_led(struct qlcnic_adapter *, u32, u32); void qlcnic_82xx_get_func_no(struct qlcnic_adapter *); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 918220ad0d53..a4fa507903ee 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -319,10 +319,8 @@ int qlcnic_read_mac_addr(struct qlcnic_adapter *adapter) static void qlcnic_delete_adapter_mac(struct qlcnic_adapter *adapter) { struct qlcnic_mac_vlan_list *cur; - struct list_head *head; - list_for_each(head, &adapter->mac_list) { - cur = list_entry(head, struct qlcnic_mac_vlan_list, list); + list_for_each_entry(cur, &adapter->mac_list, list) { if (ether_addr_equal_unaligned(adapter->mac_addr, cur->mac_addr)) { qlcnic_sre_macaddr_change(adapter, cur->mac_addr, 0, QLCNIC_MAC_DEL); @@ -3344,9 +3342,6 @@ qlcnic_can_start_firmware(struct qlcnic_adapter *adapter) do { msleep(1000); prev_state = QLC_SHARED_REG_RD32(adapter, QLCNIC_CRB_DEV_STATE); - - if (prev_state == QLCNIC_DEV_QUISCENT) - continue; } while ((prev_state != QLCNIC_DEV_READY) && --dev_init_timeo); if (!dev_init_timeo) { diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c index 702aa217a27a..d59fff2fbcc6 100644 --- a/drivers/net/ethernet/qualcomm/qca_debug.c +++ b/drivers/net/ethernet/qualcomm/qca_debug.c @@ -62,6 +62,7 @@ static const char qcaspi_gstrings_stats[][ETH_GSTRING_LEN] = { "SPI errors", "Write verify errors", "Buffer available errors", + "Bad signature", }; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 0a6b8112b535..b64c254e00ba 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -504,8 +504,12 @@ qcaspi_qca7k_sync(struct qcaspi *qca, int event) qcaspi_read_register(qca, SPI_REG_SIGNATURE, &signature); qcaspi_read_register(qca, SPI_REG_SIGNATURE, &signature); if (signature != QCASPI_GOOD_SIGNATURE) { + if (qca->sync == QCASPI_SYNC_READY) + qca->stats.bad_signature++; + qca->sync = QCASPI_SYNC_UNKNOWN; netdev_dbg(qca->net_dev, "sync: got CPU on, but signature was invalid, restart\n"); + return; } else { /* ensure that the WRBUF is empty */ qcaspi_read_register(qca, SPI_REG_WRBUF_SPC_AVA, @@ -523,10 +527,14 @@ qcaspi_qca7k_sync(struct qcaspi *qca, int event) switch (qca->sync) { case QCASPI_SYNC_READY: - /* Read signature, if not valid go to unknown state. */ + /* Check signature twice, if not valid go to unknown state. */ qcaspi_read_register(qca, SPI_REG_SIGNATURE, &signature); + if (signature != QCASPI_GOOD_SIGNATURE) + qcaspi_read_register(qca, SPI_REG_SIGNATURE, &signature); + if (signature != QCASPI_GOOD_SIGNATURE) { qca->sync = QCASPI_SYNC_UNKNOWN; + qca->stats.bad_signature++; netdev_dbg(qca->net_dev, "sync: bad signature, restart\n"); /* don't reset right away */ return; diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h index d13a67e20d65..3067356106f0 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.h +++ b/drivers/net/ethernet/qualcomm/qca_spi.h @@ -75,6 +75,7 @@ struct qcaspi_stats { u64 spi_err; u64 write_verify_failed; u64 buf_avail_err; + u64 bad_signature; }; struct qcaspi { diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 8d51b0cb545c..27b1663c476e 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -163,7 +163,8 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, struct ifla_rmnet_flags *flags; flags = nla_data(data[IFLA_RMNET_FLAGS]); - data_format = flags->flags & flags->mask; + data_format &= ~flags->mask; + data_format |= flags->flags & flags->mask; } netdev_dbg(dev, "data format [0x%08X]\n", data_format); @@ -336,7 +337,8 @@ static int rmnet_changelink(struct net_device *dev, struct nlattr *tb[], old_data_format = port->data_format; flags = nla_data(data[IFLA_RMNET_FLAGS]); - port->data_format = flags->flags & flags->mask; + port->data_format &= ~flags->mask; + port->data_format |= flags->flags & flags->mask; if (rmnet_vnd_update_dev_mtu(port, real_dev)) { port->data_format = old_data_format; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index 8d8d4690a074..3d3cba56c516 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (c) 2013-2014, 2016-2018 The Linux Foundation. All rights reserved. +/* Copyright (c) 2013-2014, 2016-2018, 2021 The Linux Foundation. + * All rights reserved. * * RMNET Data configuration engine */ @@ -48,6 +49,7 @@ struct rmnet_pcpu_stats { struct rmnet_priv_stats { u64 csum_ok; + u64 csum_ip4_header_bad; u64 csum_valid_unset; u64 csum_validation_failed; u64 csum_err_bad_buffer; @@ -56,6 +58,7 @@ struct rmnet_priv_stats { u64 csum_fragmented_pkt; u64 csum_skipped; u64 csum_sw; + u64 csum_hw; }; struct rmnet_priv { diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c index 0be5ac7ab261..bfbd7847f946 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved. +/* Copyright (c) 2013-2018, 2021, The Linux Foundation. All rights reserved. * * RMNET Data ingress/egress handler */ @@ -82,12 +82,18 @@ __rmnet_map_ingress_handler(struct sk_buff *skb, skb->dev = ep->egress_dev; - /* Subtract MAP header */ - skb_pull(skb, sizeof(struct rmnet_map_header)); - rmnet_set_skb_proto(skb); - - if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) { - if (!rmnet_map_checksum_downlink_packet(skb, len + pad)) + if ((port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV5) && + (map_header->flags & MAP_NEXT_HEADER_FLAG)) { + if (rmnet_map_process_next_hdr_packet(skb, len)) + goto free_skb; + skb_pull(skb, sizeof(*map_header)); + rmnet_set_skb_proto(skb); + } else { + /* Subtract MAP header */ + skb_pull(skb, sizeof(*map_header)); + rmnet_set_skb_proto(skb); + if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4 && + !rmnet_map_checksum_downlink_packet(skb, len + pad)) skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -128,7 +134,7 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, struct rmnet_port *port, u8 mux_id, struct net_device *orig_dev) { - int required_headroom, additional_header_len; + int required_headroom, additional_header_len, csum_type = 0; struct rmnet_map_header *map_header; additional_header_len = 0; @@ -136,18 +142,23 @@ static int rmnet_map_egress_handler(struct sk_buff *skb, if (port->data_format & RMNET_FLAGS_EGRESS_MAP_CKSUMV4) { additional_header_len = sizeof(struct rmnet_map_ul_csum_header); - required_headroom += additional_header_len; + csum_type = RMNET_FLAGS_EGRESS_MAP_CKSUMV4; + } else if (port->data_format & RMNET_FLAGS_EGRESS_MAP_CKSUMV5) { + additional_header_len = sizeof(struct rmnet_map_v5_csum_header); + csum_type = RMNET_FLAGS_EGRESS_MAP_CKSUMV5; } - if (skb_headroom(skb) < required_headroom) { - if (pskb_expand_head(skb, required_headroom, 0, GFP_ATOMIC)) - return -ENOMEM; - } + required_headroom += additional_header_len; - if (port->data_format & RMNET_FLAGS_EGRESS_MAP_CKSUMV4) - rmnet_map_checksum_uplink_packet(skb, orig_dev); + if (skb_cow_head(skb, required_headroom) < 0) + return -ENOMEM; - map_header = rmnet_map_add_map_header(skb, additional_header_len, 0); + if (csum_type) + rmnet_map_checksum_uplink_packet(skb, port, orig_dev, + csum_type); + + map_header = rmnet_map_add_map_header(skb, additional_header_len, + port, 0); if (!map_header) return -ENOMEM; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h index 2aea153f4247..e5a0b38f7dbe 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved. +/* Copyright (c) 2013-2018, 2021, The Linux Foundation. All rights reserved. */ #ifndef _RMNET_MAP_H_ @@ -43,10 +43,15 @@ enum rmnet_map_commands { struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb, struct rmnet_port *port); struct rmnet_map_header *rmnet_map_add_map_header(struct sk_buff *skb, - int hdrlen, int pad); + int hdrlen, + struct rmnet_port *port, + int pad); void rmnet_map_command(struct sk_buff *skb, struct rmnet_port *port); int rmnet_map_checksum_downlink_packet(struct sk_buff *skb, u16 len); void rmnet_map_checksum_uplink_packet(struct sk_buff *skb, - struct net_device *orig_dev); + struct rmnet_port *port, + struct net_device *orig_dev, + int csum_type); +int rmnet_map_process_next_hdr_packet(struct sk_buff *skb, u16 len); #endif /* _RMNET_MAP_H_ */ diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c index 0ac2ff828320..3676976c875b 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/* Copyright (c) 2013-2018, The Linux Foundation. All rights reserved. +/* Copyright (c) 2013-2018, 2021, The Linux Foundation. All rights reserved. * * RMNET Data MAP protocol */ @@ -8,6 +8,7 @@ #include #include #include +#include #include "rmnet_config.h" #include "rmnet_map.h" #include "rmnet_private.h" @@ -18,23 +19,13 @@ static __sum16 *rmnet_map_get_csum_field(unsigned char protocol, const void *txporthdr) { - __sum16 *check = NULL; + if (protocol == IPPROTO_TCP) + return &((struct tcphdr *)txporthdr)->check; - switch (protocol) { - case IPPROTO_TCP: - check = &(((struct tcphdr *)txporthdr)->check); - break; + if (protocol == IPPROTO_UDP) + return &((struct udphdr *)txporthdr)->check; - case IPPROTO_UDP: - check = &(((struct udphdr *)txporthdr)->check); - break; - - default: - check = NULL; - break; - } - - return check; + return NULL; } static int @@ -42,71 +33,74 @@ rmnet_map_ipv4_dl_csum_trailer(struct sk_buff *skb, struct rmnet_map_dl_csum_trailer *csum_trailer, struct rmnet_priv *priv) { - __sum16 *csum_field, csum_temp, pseudo_csum, hdr_csum, ip_payload_csum; - u16 csum_value, csum_value_final; - struct iphdr *ip4h; - void *txporthdr; - __be16 addend; + struct iphdr *ip4h = (struct iphdr *)skb->data; + void *txporthdr = skb->data + ip4h->ihl * 4; + __sum16 *csum_field, pseudo_csum; + __sum16 ip_payload_csum; - ip4h = (struct iphdr *)(skb->data); - if ((ntohs(ip4h->frag_off) & IP_MF) || - ((ntohs(ip4h->frag_off) & IP_OFFSET) > 0)) { + /* Computing the checksum over just the IPv4 header--including its + * checksum field--should yield 0. If it doesn't, the IP header + * is bad, so return an error and let the IP layer drop it. + */ + if (ip_fast_csum(ip4h, ip4h->ihl)) { + priv->stats.csum_ip4_header_bad++; + return -EINVAL; + } + + /* We don't support checksum offload on IPv4 fragments */ + if (ip_is_fragment(ip4h)) { priv->stats.csum_fragmented_pkt++; return -EOPNOTSUPP; } - txporthdr = skb->data + ip4h->ihl * 4; - + /* Checksum offload is only supported for UDP and TCP protocols */ csum_field = rmnet_map_get_csum_field(ip4h->protocol, txporthdr); - if (!csum_field) { priv->stats.csum_err_invalid_transport++; return -EPROTONOSUPPORT; } - /* RFC 768 - Skip IPv4 UDP packets where sender checksum field is 0 */ - if (*csum_field == 0 && ip4h->protocol == IPPROTO_UDP) { + /* RFC 768: UDP checksum is optional for IPv4, and is 0 if unused */ + if (!*csum_field && ip4h->protocol == IPPROTO_UDP) { priv->stats.csum_skipped++; return 0; } - csum_value = ~ntohs(csum_trailer->csum_value); - hdr_csum = ~ip_fast_csum(ip4h, (int)ip4h->ihl); - ip_payload_csum = csum16_sub((__force __sum16)csum_value, - (__force __be16)hdr_csum); + /* The checksum value in the trailer is computed over the entire + * IP packet, including the IP header and payload. To derive the + * transport checksum from this, we first subract the contribution + * of the IP header from the trailer checksum. We then add the + * checksum computed over the pseudo header. + * + * We verified above that the IP header contributes zero to the + * trailer checksum. Therefore the checksum in the trailer is + * just the checksum computed over the IP payload. - pseudo_csum = ~csum_tcpudp_magic(ip4h->saddr, ip4h->daddr, - ntohs(ip4h->tot_len) - ip4h->ihl * 4, - ip4h->protocol, 0); - addend = (__force __be16)ntohs((__force __be16)pseudo_csum); - pseudo_csum = csum16_add(ip_payload_csum, addend); + * If the IP payload arrives intact, adding the pseudo header + * checksum to the IP payload checksum will yield 0xffff (negative + * zero). This means the trailer checksum and the pseudo checksum + * are additive inverses of each other. Put another way, the + * message passes the checksum test if the trailer checksum value + * is the negated pseudo header checksum. + * + * Knowing this, we don't even need to examine the transport + * header checksum value; it is already accounted for in the + * checksum value found in the trailer. + */ + ip_payload_csum = csum_trailer->csum_value; - addend = (__force __be16)ntohs((__force __be16)*csum_field); - csum_temp = ~csum16_sub(pseudo_csum, addend); - csum_value_final = (__force u16)csum_temp; + pseudo_csum = csum_tcpudp_magic(ip4h->saddr, ip4h->daddr, + ntohs(ip4h->tot_len) - ip4h->ihl * 4, + ip4h->protocol, 0); - if (unlikely(csum_value_final == 0)) { - switch (ip4h->protocol) { - case IPPROTO_UDP: - /* RFC 768 - DL4 1's complement rule for UDP csum 0 */ - csum_value_final = ~csum_value_final; - break; - - case IPPROTO_TCP: - /* DL4 Non-RFC compliant TCP checksum found */ - if (*csum_field == (__force __sum16)0xFFFF) - csum_value_final = ~csum_value_final; - break; - } - } - - if (csum_value_final == ntohs((__force __be16)*csum_field)) { - priv->stats.csum_ok++; - return 0; - } else { + /* The cast is required to ensure only the low 16 bits are examined */ + if (ip_payload_csum != (__sum16)~pseudo_csum) { priv->stats.csum_validation_failed++; return -EINVAL; } + + priv->stats.csum_ok++; + return 0; } #if IS_ENABLED(CONFIG_IPV6) @@ -115,76 +109,66 @@ rmnet_map_ipv6_dl_csum_trailer(struct sk_buff *skb, struct rmnet_map_dl_csum_trailer *csum_trailer, struct rmnet_priv *priv) { - __sum16 *csum_field, ip6_payload_csum, pseudo_csum, csum_temp; - u16 csum_value, csum_value_final; - __be16 ip6_hdr_csum, addend; - struct ipv6hdr *ip6h; - void *txporthdr; - u32 length; + struct ipv6hdr *ip6h = (struct ipv6hdr *)skb->data; + void *txporthdr = skb->data + sizeof(*ip6h); + __sum16 *csum_field, pseudo_csum; + __sum16 ip6_payload_csum; + __be16 ip_header_csum; - ip6h = (struct ipv6hdr *)(skb->data); - - txporthdr = skb->data + sizeof(struct ipv6hdr); + /* Checksum offload is only supported for UDP and TCP protocols; + * the packet cannot include any IPv6 extension headers + */ csum_field = rmnet_map_get_csum_field(ip6h->nexthdr, txporthdr); - if (!csum_field) { priv->stats.csum_err_invalid_transport++; return -EPROTONOSUPPORT; } - csum_value = ~ntohs(csum_trailer->csum_value); - ip6_hdr_csum = (__force __be16) - ~ntohs((__force __be16)ip_compute_csum(ip6h, - (int)(txporthdr - (void *)(skb->data)))); - ip6_payload_csum = csum16_sub((__force __sum16)csum_value, - ip6_hdr_csum); + /* The checksum value in the trailer is computed over the entire + * IP packet, including the IP header and payload. To derive the + * transport checksum from this, we first subract the contribution + * of the IP header from the trailer checksum. We then add the + * checksum computed over the pseudo header. + */ + ip_header_csum = (__force __be16)ip_fast_csum(ip6h, sizeof(*ip6h) / 4); + ip6_payload_csum = csum16_sub(csum_trailer->csum_value, ip_header_csum); - length = (ip6h->nexthdr == IPPROTO_UDP) ? - ntohs(((struct udphdr *)txporthdr)->len) : - ntohs(ip6h->payload_len); - pseudo_csum = ~(csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, - length, ip6h->nexthdr, 0)); - addend = (__force __be16)ntohs((__force __be16)pseudo_csum); - pseudo_csum = csum16_add(ip6_payload_csum, addend); + pseudo_csum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, + ntohs(ip6h->payload_len), + ip6h->nexthdr, 0); - addend = (__force __be16)ntohs((__force __be16)*csum_field); - csum_temp = ~csum16_sub(pseudo_csum, addend); - csum_value_final = (__force u16)csum_temp; - - if (unlikely(csum_value_final == 0)) { - switch (ip6h->nexthdr) { - case IPPROTO_UDP: - /* RFC 2460 section 8.1 - * DL6 One's complement rule for UDP checksum 0 - */ - csum_value_final = ~csum_value_final; - break; - - case IPPROTO_TCP: - /* DL6 Non-RFC compliant TCP checksum found */ - if (*csum_field == (__force __sum16)0xFFFF) - csum_value_final = ~csum_value_final; - break; - } - } - - if (csum_value_final == ntohs((__force __be16)*csum_field)) { - priv->stats.csum_ok++; - return 0; - } else { + /* It's sufficient to compare the IP payload checksum with the + * negated pseudo checksum to determine whether the packet + * checksum was good. (See further explanation in comments + * in rmnet_map_ipv4_dl_csum_trailer()). + * + * The cast is required to ensure only the low 16 bits are + * examined. + */ + if (ip6_payload_csum != (__sum16)~pseudo_csum) { priv->stats.csum_validation_failed++; return -EINVAL; } + + priv->stats.csum_ok++; + return 0; +} +#else +static int +rmnet_map_ipv6_dl_csum_trailer(struct sk_buff *skb, + struct rmnet_map_dl_csum_trailer *csum_trailer, + struct rmnet_priv *priv) +{ + return 0; } #endif -static void rmnet_map_complement_ipv4_txporthdr_csum_field(void *iphdr) +static void rmnet_map_complement_ipv4_txporthdr_csum_field(struct iphdr *ip4h) { - struct iphdr *ip4h = (struct iphdr *)iphdr; void *txphdr; u16 *csum; - txphdr = iphdr + ip4h->ihl * 4; + txphdr = (void *)ip4h + ip4h->ihl * 4; if (ip4h->protocol == IPPROTO_TCP || ip4h->protocol == IPPROTO_UDP) { csum = (u16 *)rmnet_map_get_csum_field(ip4h->protocol, txphdr); @@ -193,15 +177,14 @@ static void rmnet_map_complement_ipv4_txporthdr_csum_field(void *iphdr) } static void -rmnet_map_ipv4_ul_csum_header(void *iphdr, +rmnet_map_ipv4_ul_csum_header(struct iphdr *iphdr, struct rmnet_map_ul_csum_header *ul_header, struct sk_buff *skb) { - struct iphdr *ip4h = iphdr; u16 val; val = MAP_CSUM_UL_ENABLED_FLAG; - if (ip4h->protocol == IPPROTO_UDP) + if (iphdr->protocol == IPPROTO_UDP) val |= MAP_CSUM_UL_UDP_FLAG; val |= skb->csum_offset & MAP_CSUM_UL_OFFSET_MASK; @@ -214,13 +197,13 @@ rmnet_map_ipv4_ul_csum_header(void *iphdr, } #if IS_ENABLED(CONFIG_IPV6) -static void rmnet_map_complement_ipv6_txporthdr_csum_field(void *ip6hdr) +static void +rmnet_map_complement_ipv6_txporthdr_csum_field(struct ipv6hdr *ip6h) { - struct ipv6hdr *ip6h = (struct ipv6hdr *)ip6hdr; void *txphdr; u16 *csum; - txphdr = ip6hdr + sizeof(struct ipv6hdr); + txphdr = ip6h + 1; if (ip6h->nexthdr == IPPROTO_TCP || ip6h->nexthdr == IPPROTO_UDP) { csum = (u16 *)rmnet_map_get_csum_field(ip6h->nexthdr, txphdr); @@ -229,15 +212,14 @@ static void rmnet_map_complement_ipv6_txporthdr_csum_field(void *ip6hdr) } static void -rmnet_map_ipv6_ul_csum_header(void *ip6hdr, +rmnet_map_ipv6_ul_csum_header(struct ipv6hdr *ipv6hdr, struct rmnet_map_ul_csum_header *ul_header, struct sk_buff *skb) { - struct ipv6hdr *ip6h = ip6hdr; u16 val; val = MAP_CSUM_UL_ENABLED_FLAG; - if (ip6h->nexthdr == IPPROTO_UDP) + if (ipv6hdr->nexthdr == IPPROTO_UDP) val |= MAP_CSUM_UL_UDP_FLAG; val |= skb->csum_offset & MAP_CSUM_UL_OFFSET_MASK; @@ -246,16 +228,73 @@ rmnet_map_ipv6_ul_csum_header(void *ip6hdr, skb->ip_summed = CHECKSUM_NONE; - rmnet_map_complement_ipv6_txporthdr_csum_field(ip6hdr); + rmnet_map_complement_ipv6_txporthdr_csum_field(ipv6hdr); +} +#else +static void +rmnet_map_ipv6_ul_csum_header(void *ip6hdr, + struct rmnet_map_ul_csum_header *ul_header, + struct sk_buff *skb) +{ } #endif +static void rmnet_map_v5_checksum_uplink_packet(struct sk_buff *skb, + struct rmnet_port *port, + struct net_device *orig_dev) +{ + struct rmnet_priv *priv = netdev_priv(orig_dev); + struct rmnet_map_v5_csum_header *ul_header; + + ul_header = skb_push(skb, sizeof(*ul_header)); + memset(ul_header, 0, sizeof(*ul_header)); + ul_header->header_info = u8_encode_bits(RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD, + MAPV5_HDRINFO_HDR_TYPE_FMASK); + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + void *iph = ip_hdr(skb); + __sum16 *check; + void *trans; + u8 proto; + + if (skb->protocol == htons(ETH_P_IP)) { + u16 ip_len = ((struct iphdr *)iph)->ihl * 4; + + proto = ((struct iphdr *)iph)->protocol; + trans = iph + ip_len; + } else if (IS_ENABLED(CONFIG_IPV6) && + skb->protocol == htons(ETH_P_IPV6)) { + u16 ip_len = sizeof(struct ipv6hdr); + + proto = ((struct ipv6hdr *)iph)->nexthdr; + trans = iph + ip_len; + } else { + priv->stats.csum_err_invalid_ip_version++; + goto sw_csum; + } + + check = rmnet_map_get_csum_field(proto, trans); + if (check) { + skb->ip_summed = CHECKSUM_NONE; + /* Ask for checksum offloading */ + ul_header->csum_info |= MAPV5_CSUMINFO_VALID_FLAG; + priv->stats.csum_hw++; + return; + } + } + +sw_csum: + priv->stats.csum_sw++; +} + /* Adds MAP header to front of skb->data * Padding is calculated and set appropriately in MAP header. Mux ID is * initialized to 0. */ struct rmnet_map_header *rmnet_map_add_map_header(struct sk_buff *skb, - int hdrlen, int pad) + int hdrlen, + struct rmnet_port *port, + int pad) { struct rmnet_map_header *map_header; u32 padding, map_datalen; @@ -266,6 +305,10 @@ struct rmnet_map_header *rmnet_map_add_map_header(struct sk_buff *skb, skb_push(skb, sizeof(struct rmnet_map_header)); memset(map_header, 0, sizeof(struct rmnet_map_header)); + /* Set next_hdr bit for csum offload packets */ + if (port->data_format & RMNET_FLAGS_EGRESS_MAP_CKSUMV5) + map_header->flags |= MAP_NEXT_HEADER_FLAG; + if (pad == RMNET_MAP_NO_PAD_BYTES) { map_header->pkt_len = htons(map_datalen); return map_header; @@ -300,8 +343,11 @@ done: struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb, struct rmnet_port *port) { + struct rmnet_map_v5_csum_header *next_hdr = NULL; struct rmnet_map_header *maph; + void *data = skb->data; struct sk_buff *skbn; + u8 nexthdr_type; u32 packet_len; if (skb->len == 0) @@ -310,8 +356,18 @@ struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb, maph = (struct rmnet_map_header *)skb->data; packet_len = ntohs(maph->pkt_len) + sizeof(*maph); - if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) + if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV4) { packet_len += sizeof(struct rmnet_map_dl_csum_trailer); + } else if (port->data_format & RMNET_FLAGS_INGRESS_MAP_CKSUMV5) { + if (!(maph->flags & MAP_CMD_FLAG)) { + packet_len += sizeof(*next_hdr); + if (maph->flags & MAP_NEXT_HEADER_FLAG) + next_hdr = data + sizeof(*maph); + else + /* Mapv5 data pkt without csum hdr is invalid */ + return NULL; + } + } if (((int)skb->len - (int)packet_len) < 0) return NULL; @@ -320,6 +376,13 @@ struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb, if (!maph->pkt_len) return NULL; + if (next_hdr) { + nexthdr_type = u8_get_bits(next_hdr->header_info, + MAPV5_HDRINFO_HDR_TYPE_FMASK); + if (nexthdr_type != RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD) + return NULL; + } + skbn = alloc_skb(packet_len + RMNET_MAP_DEAGGR_SPACING, GFP_ATOMIC); if (!skbn) return NULL; @@ -355,28 +418,19 @@ int rmnet_map_checksum_downlink_packet(struct sk_buff *skb, u16 len) return -EINVAL; } - if (skb->protocol == htons(ETH_P_IP)) { + if (skb->protocol == htons(ETH_P_IP)) return rmnet_map_ipv4_dl_csum_trailer(skb, csum_trailer, priv); - } else if (skb->protocol == htons(ETH_P_IPV6)) { -#if IS_ENABLED(CONFIG_IPV6) - return rmnet_map_ipv6_dl_csum_trailer(skb, csum_trailer, priv); -#else - priv->stats.csum_err_invalid_ip_version++; - return -EPROTONOSUPPORT; -#endif - } else { - priv->stats.csum_err_invalid_ip_version++; - return -EPROTONOSUPPORT; - } - return 0; + if (IS_ENABLED(CONFIG_IPV6) && skb->protocol == htons(ETH_P_IPV6)) + return rmnet_map_ipv6_dl_csum_trailer(skb, csum_trailer, priv); + + priv->stats.csum_err_invalid_ip_version++; + + return -EPROTONOSUPPORT; } -/* Generates UL checksum meta info header for IPv4 and IPv6 over TCP and UDP - * packets that are supported for UL checksum offload. - */ -void rmnet_map_checksum_uplink_packet(struct sk_buff *skb, - struct net_device *orig_dev) +static void rmnet_map_v4_checksum_uplink_packet(struct sk_buff *skb, + struct net_device *orig_dev) { struct rmnet_priv *priv = netdev_priv(orig_dev); struct rmnet_map_ul_csum_header *ul_header; @@ -389,28 +443,80 @@ void rmnet_map_checksum_uplink_packet(struct sk_buff *skb, (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)))) goto sw_csum; - if (skb->ip_summed == CHECKSUM_PARTIAL) { - iphdr = (char *)ul_header + - sizeof(struct rmnet_map_ul_csum_header); + if (skb->ip_summed != CHECKSUM_PARTIAL) + goto sw_csum; - if (skb->protocol == htons(ETH_P_IP)) { - rmnet_map_ipv4_ul_csum_header(iphdr, ul_header, skb); - return; - } else if (skb->protocol == htons(ETH_P_IPV6)) { -#if IS_ENABLED(CONFIG_IPV6) - rmnet_map_ipv6_ul_csum_header(iphdr, ul_header, skb); - return; -#else - priv->stats.csum_err_invalid_ip_version++; - goto sw_csum; -#endif - } else { - priv->stats.csum_err_invalid_ip_version++; - } + iphdr = (char *)ul_header + + sizeof(struct rmnet_map_ul_csum_header); + + if (skb->protocol == htons(ETH_P_IP)) { + rmnet_map_ipv4_ul_csum_header(iphdr, ul_header, skb); + priv->stats.csum_hw++; + return; } + if (IS_ENABLED(CONFIG_IPV6) && skb->protocol == htons(ETH_P_IPV6)) { + rmnet_map_ipv6_ul_csum_header(iphdr, ul_header, skb); + priv->stats.csum_hw++; + return; + } + + priv->stats.csum_err_invalid_ip_version++; + sw_csum: memset(ul_header, 0, sizeof(*ul_header)); priv->stats.csum_sw++; } + +/* Generates UL checksum meta info header for IPv4 and IPv6 over TCP and UDP + * packets that are supported for UL checksum offload. + */ +void rmnet_map_checksum_uplink_packet(struct sk_buff *skb, + struct rmnet_port *port, + struct net_device *orig_dev, + int csum_type) +{ + switch (csum_type) { + case RMNET_FLAGS_EGRESS_MAP_CKSUMV4: + rmnet_map_v4_checksum_uplink_packet(skb, orig_dev); + break; + case RMNET_FLAGS_EGRESS_MAP_CKSUMV5: + rmnet_map_v5_checksum_uplink_packet(skb, port, orig_dev); + break; + default: + break; + } +} + +/* Process a MAPv5 packet header */ +int rmnet_map_process_next_hdr_packet(struct sk_buff *skb, + u16 len) +{ + struct rmnet_priv *priv = netdev_priv(skb->dev); + struct rmnet_map_v5_csum_header *next_hdr; + u8 nexthdr_type; + + next_hdr = (struct rmnet_map_v5_csum_header *)(skb->data + + sizeof(struct rmnet_map_header)); + + nexthdr_type = u8_get_bits(next_hdr->header_info, + MAPV5_HDRINFO_HDR_TYPE_FMASK); + + if (nexthdr_type != RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD) + return -EINVAL; + + if (unlikely(!(skb->dev->features & NETIF_F_RXCSUM))) { + priv->stats.csum_sw++; + } else if (next_hdr->csum_info & MAPV5_CSUMINFO_VALID_FLAG) { + priv->stats.csum_ok++; + skb->ip_summed = CHECKSUM_UNNECESSARY; + } else { + priv->stats.csum_valid_unset++; + } + + /* Pull csum v5 header */ + skb_pull(skb, sizeof(*next_hdr)); + + return 0; +} diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index ab1e0fcccabb..13d8eb43a485 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -166,6 +166,7 @@ static const struct net_device_ops rmnet_vnd_ops = { static const char rmnet_gstrings_stats[][ETH_GSTRING_LEN] = { "Checksum ok", + "Bad IPv4 header checksum", "Checksum valid bit not set", "Checksum validation failed", "Checksum error bad buffer", @@ -174,6 +175,7 @@ static const char rmnet_gstrings_stats[][ETH_GSTRING_LEN] = { "Checksum skipped on ip fragment", "Checksum skipped", "Checksum computed in software", + "Checksum computed in hardware", }; static void rmnet_get_strings(struct net_device *dev, u32 stringset, u8 *buf) diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index 7c74318620b1..47e9998b62f0 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -200,7 +200,7 @@ static int r6040_phy_read(void __iomem *ioaddr, int phy_addr, int reg) int limit = MAC_DEF_TIMEOUT; u16 cmd; - iowrite16(MDIO_READ + reg + (phy_addr << 8), ioaddr + MMDIO); + iowrite16(MDIO_READ | reg | (phy_addr << 8), ioaddr + MMDIO); /* Wait for the read bit to be cleared */ while (limit--) { cmd = ioread16(ioaddr + MMDIO); @@ -224,7 +224,7 @@ static int r6040_phy_write(void __iomem *ioaddr, iowrite16(val, ioaddr + MMWD); /* Write the command to the MDIO bus */ - iowrite16(MDIO_WRITE + reg + (phy_addr << 8), ioaddr + MMDIO); + iowrite16(MDIO_WRITE | reg | (phy_addr << 8), ioaddr + MMDIO); /* Wait for the write bit to be cleared */ while (limit--) { cmd = ioread16(ioaddr + MMDIO); @@ -544,7 +544,7 @@ static int r6040_rx(struct net_device *dev, int limit) skb_ptr->dev = priv->dev; /* Do not count the CRC */ - skb_put(skb_ptr, descptr->len - 4); + skb_put(skb_ptr, descptr->len - ETH_FCS_LEN); dma_unmap_single(&priv->pdev->dev, le32_to_cpu(descptr->buf), MAX_BUF_SIZE, DMA_FROM_DEVICE); skb_ptr->protocol = eth_type_trans(skb_ptr, priv->dev); @@ -552,7 +552,7 @@ static int r6040_rx(struct net_device *dev, int limit) /* Send to upper layer */ netif_receive_skb(skb_ptr); dev->stats.rx_packets++; - dev->stats.rx_bytes += descptr->len - 4; + dev->stats.rx_bytes += descptr->len - ETH_FCS_LEN; /* put new skb into descriptor */ descptr->skb_ptr = new_skb; @@ -943,6 +943,7 @@ static const struct ethtool_ops netdev_ethtool_ops = { .get_ts_info = ethtool_op_get_ts_info, .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, + .nway_reset = phy_ethtool_nway_reset, }; static const struct net_device_ops r6040_netdev_ops = { diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 4e44313b7651..9677e257e9a1 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -6,7 +6,7 @@ Copyright (C) 2000, 2001 David S. Miller (davem@redhat.com) [sungem.c] Copyright 2001 Manfred Spraul [natsemi.c] Copyright 1999-2001 by Donald Becker. [natsemi.c] - Written 1997-2001 by Donald Becker. [8139too.c] + Written 1997-2001 by Donald Becker. [8139too.c] Copyright 1998-2001 by Jes Sorensen, . [acenic.c] This software may be used and distributed according to the terms of @@ -947,8 +947,8 @@ static struct net_device_stats *cp_get_stats(struct net_device *dev) /* The chip only need report frame silently dropped. */ spin_lock_irqsave(&cp->lock, flags); - if (netif_running(dev) && netif_device_present(dev)) - __cp_get_stats(cp); + if (netif_running(dev) && netif_device_present(dev)) + __cp_get_stats(cp); spin_unlock_irqrestore(&cp->lock, flags); return &dev->stats; diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index 1e5a453dea14..f0608f050050 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -11,7 +11,7 @@ ---------- - Written 1997-2001 by Donald Becker. + Written 1997-2001 by Donald Becker. This software may be used and distributed according to the terms of the GNU General Public License (GPL), incorporated herein by reference. Drivers based on or derived from this @@ -548,8 +548,8 @@ static const struct { { "RTL-8100", HW_REVID(1, 1, 1, 1, 0, 1, 0), - HasLWake, - }, + HasLWake, + }, { "RTL-8100B/8139D", HW_REVID(1, 1, 1, 0, 1, 0, 1), diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c index 9e3b35c97e63..b6c849b258a0 100644 --- a/drivers/net/ethernet/realtek/atp.c +++ b/drivers/net/ethernet/realtek/atp.c @@ -497,8 +497,8 @@ static void write_packet(long ioaddr, int length, unsigned char *packet, int pad { if (length & 1) { - length++; - pad_len++; + length++; + pad_len++; } outb(EOC+MAR, ioaddr + PAR_DATA); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 2ee72dc431cd..f744557c33a3 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -34,8 +34,6 @@ #include "r8169.h" #include "r8169_firmware.h" -#define MODULENAME "r8169" - #define FIRMWARE_8168D_1 "rtl_nic/rtl8168d-1.fw" #define FIRMWARE_8168D_2 "rtl_nic/rtl8168d-2.fw" #define FIRMWARE_8168E_1 "rtl_nic/rtl8168e-1.fw" @@ -1454,7 +1452,7 @@ static void rtl8169_get_drvinfo(struct net_device *dev, struct rtl8169_private *tp = netdev_priv(dev); struct rtl_fw *rtl_fw = tp->rtl_fw; - strlcpy(info->driver, MODULENAME, sizeof(info->driver)); + strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver)); strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info)); BUILD_BUG_ON(sizeof(info->fw_version) < sizeof(rtl_fw->version)); if (rtl_fw) @@ -3510,7 +3508,6 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000); rtl_pcie_state_l2l3_disable(tp); - rtl_hw_aspm_clkreq_enable(tp, true); } DECLARE_RTL_COND(rtl_mac_ocp_e00e_cond) @@ -4117,6 +4114,7 @@ static unsigned int rtl_quirk_packet_padto(struct rtl8169_private *tp, case RTL_GIGA_MAC_VER_61: case RTL_GIGA_MAC_VER_63: padto = max_t(unsigned int, padto, ETH_ZLEN); + break; default: break; } @@ -5305,7 +5303,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return -ENODEV; } - rc = pcim_iomap_regions(pdev, BIT(region), MODULENAME); + rc = pcim_iomap_regions(pdev, BIT(region), KBUILD_MODNAME); if (rc < 0) { dev_err(&pdev->dev, "cannot remap MMIO, aborting\n"); return rc; @@ -5440,7 +5438,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } static struct pci_driver rtl8169_pci_driver = { - .name = MODULENAME, + .name = KBUILD_MODNAME, .id_table = rtl8169_pci_tbl, .probe = rtl_init_one, .remove = rtl_remove_one, diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 4afff320dfd0..69c50f81e1cb 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -2047,13 +2047,6 @@ static int ravb_probe(struct platform_device *pdev) return -EINVAL; } - /* Get base address */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - dev_err(&pdev->dev, "invalid resource\n"); - return -EINVAL; - } - ndev = alloc_etherdev_mqs(sizeof(struct ravb_private), NUM_TX_QUEUE, NUM_RX_QUEUE); if (!ndev) @@ -2065,9 +2058,6 @@ static int ravb_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); pm_runtime_get_sync(&pdev->dev); - /* The Ether-specific entries in the device structure. */ - ndev->base_addr = res->start; - chip_id = (enum ravb_chip_id)of_device_get_match_data(&pdev->dev); if (chip_id == RCAR_GEN3) @@ -2089,12 +2079,15 @@ static int ravb_probe(struct platform_device *pdev) priv->num_rx_ring[RAVB_BE] = BE_RX_RING_SIZE; priv->num_tx_ring[RAVB_NC] = NC_TX_RING_SIZE; priv->num_rx_ring[RAVB_NC] = NC_RX_RING_SIZE; - priv->addr = devm_ioremap_resource(&pdev->dev, res); + priv->addr = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(priv->addr)) { error = PTR_ERR(priv->addr); goto out_release; } + /* The Ether-specific entries in the device structure. */ + ndev->base_addr = res->start; + spin_lock_init(&priv->lock); INIT_WORK(&priv->work, ravb_tx_timeout_work); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 713d3629b4c1..840478692a37 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3225,9 +3225,6 @@ static int sh_eth_drv_probe(struct platform_device *pdev) struct net_device *ndev; int ret; - /* get base addr */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ndev = alloc_etherdev(sizeof(struct sh_eth_private)); if (!ndev) return -ENOMEM; @@ -3245,7 +3242,7 @@ static int sh_eth_drv_probe(struct platform_device *pdev) mdp = netdev_priv(ndev); mdp->num_tx_ring = TX_RING_SIZE; mdp->num_rx_ring = RX_RING_SIZE; - mdp->addr = devm_ioremap_resource(&pdev->dev, res); + mdp->addr = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(mdp->addr)) { ret = PTR_ERR(mdp->addr); goto out_release; diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index 971f1e54b652..090bcd2fb758 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -789,7 +789,7 @@ static void sxgbe_tx_queue_clean(struct sxgbe_tx_queue *tqueue) } /** - * sxgbe_tx_clean: + * sxgbe_tx_all_clean: * @priv: driver private structure * Description: it reclaims resources after transmission completes. */ @@ -1015,7 +1015,7 @@ static void sxgbe_tx_timer(struct timer_list *t) } /** - * sxgbe_init_tx_coalesce: init tx mitigation options. + * sxgbe_tx_init_coalesce: init tx mitigation options. * @priv: driver private structure * Description: * This inits the transmit coalesce parameters: i.e. timer rate, diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c index 65c98837ec45..16a4cbae9326 100644 --- a/drivers/net/ethernet/seeq/ether3.c +++ b/drivers/net/ethernet/seeq/ether3.c @@ -617,7 +617,7 @@ if (next_ptr < RX_START || next_ptr >= RX_END) { break; } /* - * ignore our own packets... + * ignore our own packets... */ if (!(*(unsigned long *)&dev->dev_addr[0] ^ *(unsigned long *)&addrs[2+6]) && !(*(unsigned short *)&dev->dev_addr[4] ^ *(unsigned short *)&addrs[2+10])) { @@ -672,7 +672,7 @@ done: */ if (!(ether3_inw(REG_STATUS) & STAT_RXON)) { dev->stats.rx_dropped++; - ether3_outw(next_ptr, REG_RECVPTR); + ether3_outw(next_ptr, REG_RECVPTR); ether3_outw(priv(dev)->regs.command | CMD_RXON, REG_COMMAND); } @@ -690,11 +690,11 @@ static void ether3_tx(struct net_device *dev) do { unsigned long status; - /* + /* * Read the packet header - */ + */ ether3_setbuffer(dev, buffer_read, tx_tail * 0x600); - status = ether3_readlong(dev); + status = ether3_readlong(dev); /* * Check to see if this packet has been transmitted diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index c3f35da1b82a..e7e2223aebbf 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -370,9 +370,9 @@ static int efx_ef10_get_mac_address_vf(struct efx_nic *efx, u8 *mac_address) return 0; } -static ssize_t efx_ef10_show_link_control_flag(struct device *dev, - struct device_attribute *attr, - char *buf) +static ssize_t link_control_flag_show(struct device *dev, + struct device_attribute *attr, + char *buf) { struct efx_nic *efx = dev_get_drvdata(dev); @@ -382,9 +382,9 @@ static ssize_t efx_ef10_show_link_control_flag(struct device *dev, ? 1 : 0); } -static ssize_t efx_ef10_show_primary_flag(struct device *dev, - struct device_attribute *attr, - char *buf) +static ssize_t primary_flag_show(struct device *dev, + struct device_attribute *attr, + char *buf) { struct efx_nic *efx = dev_get_drvdata(dev); @@ -519,9 +519,8 @@ static void efx_ef10_cleanup_vlans(struct efx_nic *efx) mutex_unlock(&nic_data->vlan_lock); } -static DEVICE_ATTR(link_control_flag, 0444, efx_ef10_show_link_control_flag, - NULL); -static DEVICE_ATTR(primary_flag, 0444, efx_ef10_show_primary_flag, NULL); +static DEVICE_ATTR_RO(link_control_flag); +static DEVICE_ATTR_RO(primary_flag); static int efx_ef10_probe(struct efx_nic *efx) { @@ -1070,7 +1069,8 @@ static int efx_ef10_probe_vf(struct efx_nic *efx) /* If the parent PF has no VF data structure, it doesn't know about this * VF so fail probe. The VF needs to be re-created. This can happen - * if the PF driver is unloaded while the VF is assigned to a guest. + * if the PF driver was unloaded while any VF was assigned to a guest + * (using Xen, only). */ pci_dev_pf = efx->pci_dev->physfn; if (pci_dev_pf) { diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c index 21fa6c0e8873..752d6406f07e 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.c +++ b/drivers/net/ethernet/sfc/ef10_sriov.c @@ -122,8 +122,7 @@ static void efx_ef10_sriov_free_vf_vports(struct efx_nic *efx) struct ef10_vf *vf = nic_data->vf + i; /* If VF is assigned, do not free the vport */ - if (vf->pci_dev && - vf->pci_dev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) + if (vf->pci_dev && pci_is_dev_assigned(vf->pci_dev)) continue; if (vf->vport_assigned) { @@ -207,9 +206,7 @@ static int efx_ef10_sriov_alloc_vf_vswitching(struct efx_nic *efx) return 0; fail: - efx_ef10_sriov_free_vf_vports(efx); - kfree(nic_data->vf); - nic_data->vf = NULL; + efx_ef10_sriov_free_vf_vswitching(efx); return rc; } @@ -402,12 +399,17 @@ fail1: return rc; } +/* Disable SRIOV and remove VFs + * If some VFs are attached to a guest (using Xen, only) nothing is + * done if force=false, and vports are freed if force=true (for the non + * attachedc ones, only) but SRIOV is not disabled and VFs are not + * removed in either case. + */ static int efx_ef10_pci_sriov_disable(struct efx_nic *efx, bool force) { struct pci_dev *dev = efx->pci_dev; - unsigned int vfs_assigned = 0; - - vfs_assigned = pci_vfs_assigned(dev); + unsigned int vfs_assigned = pci_vfs_assigned(dev); + int rc = 0; if (vfs_assigned && !force) { netif_info(efx, drv, efx->net_dev, "VFs are assigned to guests; " @@ -417,10 +419,12 @@ static int efx_ef10_pci_sriov_disable(struct efx_nic *efx, bool force) if (!vfs_assigned) pci_disable_sriov(dev); + else + rc = -EBUSY; efx_ef10_sriov_free_vf_vswitching(efx); efx->vf_count = 0; - return 0; + return rc; } int efx_ef10_sriov_configure(struct efx_nic *efx, int num_vfs) @@ -439,24 +443,18 @@ int efx_ef10_sriov_init(struct efx_nic *efx) void efx_ef10_sriov_fini(struct efx_nic *efx) { struct efx_ef10_nic_data *nic_data = efx->nic_data; - unsigned int i; int rc; if (!nic_data->vf) { - /* Remove any un-assigned orphaned VFs */ + /* Remove any un-assigned orphaned VFs. This can happen if the PF driver + * was unloaded while any VF was assigned to a guest (using Xen, only). + */ if (pci_num_vf(efx->pci_dev) && !pci_vfs_assigned(efx->pci_dev)) pci_disable_sriov(efx->pci_dev); return; } - /* Remove any VFs in the host */ - for (i = 0; i < efx->vf_count; ++i) { - struct efx_nic *vf_efx = nic_data->vf[i].efx; - - if (vf_efx) - vf_efx->pci_dev->driver->remove(vf_efx->pci_dev); - } - + /* Disable SRIOV and remove any VFs in the host */ rc = efx_ef10_pci_sriov_disable(efx, true); if (rc) netif_dbg(efx, drv, efx->net_dev, diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index c746ca7235f1..37fcf2eb0741 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -689,13 +689,13 @@ static struct notifier_block efx_netdev_notifier = { .notifier_call = efx_netdev_event, }; -static ssize_t -show_phy_type(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t phy_type_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct efx_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", efx->phy_type); } -static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL); +static DEVICE_ATTR_RO(phy_type); static int efx_register_netdev(struct efx_nic *efx) { @@ -722,8 +722,7 @@ static int efx_register_netdev(struct efx_nic *efx) efx->state = STATE_READY; smp_mb(); /* ensure we change state before checking reset_pending */ if (efx->reset_pending) { - netif_err(efx, probe, efx->net_dev, - "aborting probe due to scheduled reset\n"); + pci_err(efx->pci_dev, "aborting probe due to scheduled reset\n"); rc = -EIO; goto fail_locked; } @@ -990,8 +989,7 @@ static int efx_pci_probe_main(struct efx_nic *efx) rc = efx->type->init(efx); up_write(&efx->filter_sem); if (rc) { - netif_err(efx, probe, efx->net_dev, - "failed to initialise NIC\n"); + pci_err(efx->pci_dev, "failed to initialise NIC\n"); goto fail3; } @@ -1038,8 +1036,8 @@ static int efx_pci_probe_post_io(struct efx_nic *efx) if (efx->type->sriov_init) { rc = efx->type->sriov_init(efx); if (rc) - netif_err(efx, probe, efx->net_dev, - "SR-IOV can't be enabled rc %d\n", rc); + pci_err(efx->pci_dev, "SR-IOV can't be enabled rc %d\n", + rc); } /* Determine netdevice features */ @@ -1106,8 +1104,7 @@ static int efx_pci_probe(struct pci_dev *pci_dev, if (rc) goto fail1; - netif_info(efx, probe, efx->net_dev, - "Solarflare NIC detected\n"); + pci_info(pci_dev, "Solarflare NIC detected\n"); if (!efx->type->is_vf) efx_probe_vpd_strings(efx); diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c index de797e1ac5a9..896b59253197 100644 --- a/drivers/net/ethernet/sfc/efx_common.c +++ b/drivers/net/ethernet/sfc/efx_common.c @@ -1160,8 +1160,9 @@ void efx_fini_io(struct efx_nic *efx) } #ifdef CONFIG_SFC_MCDI_LOGGING -static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t mcdi_logging_show(struct device *dev, + struct device_attribute *attr, + char *buf) { struct efx_nic *efx = dev_get_drvdata(dev); struct efx_mcdi_iface *mcdi = efx_mcdi(efx); @@ -1169,8 +1170,9 @@ static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr, return scnprintf(buf, PAGE_SIZE, "%d\n", mcdi->logging_enabled); } -static ssize_t set_mcdi_log(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t mcdi_logging_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct efx_nic *efx = dev_get_drvdata(dev); struct efx_mcdi_iface *mcdi = efx_mcdi(efx); @@ -1180,7 +1182,7 @@ static ssize_t set_mcdi_log(struct device *dev, struct device_attribute *attr, return count; } -static DEVICE_ATTR(mcdi_logging, 0644, show_mcdi_log, set_mcdi_log); +static DEVICE_ATTR_RW(mcdi_logging); void efx_init_mcdi_logging(struct efx_nic *efx) { diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index 5e7a57b680ca..9ec752a43c75 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -2254,12 +2254,12 @@ static struct notifier_block ef4_netdev_notifier = { }; static ssize_t -show_phy_type(struct device *dev, struct device_attribute *attr, char *buf) +phy_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct ef4_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", efx->phy_type); } -static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL); +static DEVICE_ATTR_RO(phy_type); static int ef4_register_netdev(struct ef4_nic *efx) { diff --git a/drivers/net/ethernet/sfc/falcon/falcon_boards.c b/drivers/net/ethernet/sfc/falcon/falcon_boards.c index 729a05c1b0cf..2d2d8099011e 100644 --- a/drivers/net/ethernet/sfc/falcon/falcon_boards.c +++ b/drivers/net/ethernet/sfc/falcon/falcon_boards.c @@ -354,16 +354,16 @@ fail_on: return rc; } -static ssize_t show_phy_flash_cfg(struct device *dev, +static ssize_t phy_flash_cfg_show(struct device *dev, struct device_attribute *attr, char *buf) { struct ef4_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", !!(efx->phy_mode & PHY_MODE_SPECIAL)); } -static ssize_t set_phy_flash_cfg(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t phy_flash_cfg_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct ef4_nic *efx = dev_get_drvdata(dev); enum ef4_phy_mode old_mode, new_mode; @@ -396,7 +396,7 @@ static ssize_t set_phy_flash_cfg(struct device *dev, return err ? err : count; } -static DEVICE_ATTR(phy_flash_cfg, 0644, show_phy_flash_cfg, set_phy_flash_cfg); +static DEVICE_ATTR_RW(phy_flash_cfg); static void sfe4001_fini(struct ef4_nic *efx) { diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index 49df02ecee91..148dcd48b58d 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -1668,13 +1668,17 @@ void efx_farch_rx_pull_indir_table(struct efx_nic *efx) */ void efx_farch_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw) { - unsigned vi_count, buftbl_min, total_tx_channels; - + unsigned vi_count, total_tx_channels; #ifdef CONFIG_SFC_SRIOV - struct siena_nic_data *nic_data = efx->nic_data; + struct siena_nic_data *nic_data; + unsigned buftbl_min; #endif total_tx_channels = efx->n_tx_channels + efx->n_extra_tx_channels; + vi_count = max(efx->n_channels, total_tx_channels * EFX_MAX_TXQ_PER_CHANNEL); + +#ifdef CONFIG_SFC_SRIOV + nic_data = efx->nic_data; /* Account for the buffer table entries backing the datapath channels * and the descriptor caches for those channels. */ @@ -1682,9 +1686,6 @@ void efx_farch_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw) total_tx_channels * EFX_MAX_TXQ_PER_CHANNEL * EFX_MAX_DMAQ_SIZE + efx->n_channels * EFX_MAX_EVQ_SIZE) * sizeof(efx_qword_t) / EFX_BUF_SIZE); - vi_count = max(efx->n_channels, total_tx_channels * EFX_MAX_TXQ_PER_CHANNEL); - -#ifdef CONFIG_SFC_SRIOV if (efx->type->sriov_wanted) { if (efx->type->sriov_wanted(efx)) { unsigned vi_dc_entries, buftbl_free; diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index 17b8119c48e5..606750938b89 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -260,18 +260,14 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel, s16 offset; int err; - rcu_read_lock(); - xdp_prog = rcu_dereference(efx->xdp_prog); - if (!xdp_prog) { - rcu_read_unlock(); + xdp_prog = rcu_dereference_bh(efx->xdp_prog); + if (!xdp_prog) return true; - } rx_queue = efx_channel_get_rx_queue(channel); if (unlikely(channel->rx_pkt_n_frags > 1)) { /* We can't do XDP on fragmented packets - drop. */ - rcu_read_unlock(); efx_free_rx_buffers(rx_queue, rx_buf, channel->rx_pkt_n_frags); if (net_ratelimit()) @@ -296,7 +292,6 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel, rx_buf->len, false); xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp); - rcu_read_unlock(); offset = (u8 *)xdp.data - *ehp; diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 6eef0f45b133..2b29fd4cbdf4 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -835,6 +835,10 @@ static int ioc3eth_probe(struct platform_device *pdev) int err; regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!regs) { + dev_err(&pdev->dev, "Invalid resource\n"); + return -EINVAL; + } /* get mac addr from one wire prom */ if (ioc3eth_get_mac_addr(regs, mac_addr)) return -EPROBE_DEFER; /* not available yet */ diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 620c26f71be8..ca9c00b7f588 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -678,12 +678,12 @@ static int sis900_mii_probe(struct net_device *net_dev) /* Reset phy if default phy is internal sis900 */ if ((sis_priv->mii->phy_id0 == 0x001D) && ((sis_priv->mii->phy_id1&0xFFF0) == 0x8000)) - status = sis900_reset_phy(net_dev, sis_priv->cur_phy); + status = sis900_reset_phy(net_dev, sis_priv->cur_phy); /* workaround for ICS1893 PHY */ if ((sis_priv->mii->phy_id0 == 0x0015) && ((sis_priv->mii->phy_id1&0xFFF0) == 0xF440)) - mdio_write(net_dev, sis_priv->cur_phy, 0x0018, 0xD200); + mdio_write(net_dev, sis_priv->cur_phy, 0x0018, 0xD200); if(status & MII_STAT_LINK){ while (poll_bit) { @@ -727,7 +727,7 @@ static int sis900_mii_probe(struct net_device *net_dev) static u16 sis900_default_phy(struct net_device * net_dev) { struct sis900_private *sis_priv = netdev_priv(net_dev); - struct mii_phy *phy = NULL, *phy_home = NULL, + struct mii_phy *phy = NULL, *phy_home = NULL, *default_phy = NULL, *phy_lan = NULL; u16 status; @@ -1339,18 +1339,18 @@ static void sis900_timer(struct timer_list *t) } else { /* Link ON -> OFF */ if (!(status & MII_STAT_LINK)){ - netif_carrier_off(net_dev); + netif_carrier_off(net_dev); if(netif_msg_link(sis_priv)) - printk(KERN_INFO "%s: Media Link Off\n", net_dev->name); + printk(KERN_INFO "%s: Media Link Off\n", net_dev->name); - /* Change mode issue */ - if ((mii_phy->phy_id0 == 0x001D) && - ((mii_phy->phy_id1 & 0xFFF0) == 0x8000)) - sis900_reset_phy(net_dev, sis_priv->cur_phy); + /* Change mode issue */ + if ((mii_phy->phy_id0 == 0x001D) && + ((mii_phy->phy_id1 & 0xFFF0) == 0x8000)) + sis900_reset_phy(net_dev, sis_priv->cur_phy); sis630_set_eq(net_dev, sis_priv->chipset_rev); - goto LookForLink; + goto LookForLink; } } @@ -2331,7 +2331,7 @@ static int sis900_set_config(struct net_device *dev, struct ifmap *map) case IF_PORT_10BASE2: /* 10Base2 */ case IF_PORT_AUI: /* AUI */ case IF_PORT_100BASEFX: /* 100BaseFx */ - /* These Modes are not supported (are they?)*/ + /* These Modes are not supported (are they?)*/ return -EOPNOTSUPP; default: diff --git a/drivers/net/ethernet/smsc/smc9194.c b/drivers/net/ethernet/smsc/smc9194.c index 4b2330deed47..bf7c8c8b1350 100644 --- a/drivers/net/ethernet/smsc/smc9194.c +++ b/drivers/net/ethernet/smsc/smc9194.c @@ -182,8 +182,8 @@ struct smc_local { struct sk_buff * saved_skb; /* - . This keeps track of how many packets that I have - . sent out. When an TX_EMPTY interrupt comes, I know + . This keeps track of how many packets that I have + . sent out. When an TX_EMPTY interrupt comes, I know . that all of these have been sent. */ int packets_waiting; @@ -343,7 +343,7 @@ static void smc_reset( int ioaddr ) /* Note: It doesn't seem that waiting for the MMU busy is needed here, but this is a place where future chipsets _COULD_ break. Be wary - of issuing another MMU command right after this */ + of issuing another MMU command right after this */ outb( 0, ioaddr + INT_MASK ); } @@ -521,9 +521,9 @@ static netdev_tx_t smc_wait_to_send_packet(struct sk_buff *skb, SMC_SELECT_BANK( 2 ); outw( MC_ALLOC | numPages, ioaddr + MMU_CMD ); /* - . Performance Hack + . Performance Hack . - . wait a short amount of time.. if I can send a packet now, I send + . wait a short amount of time.. if I can send a packet now, I send . it now. Otherwise, I enable an interrupt and wait for one to be . available. . @@ -540,17 +540,17 @@ static netdev_tx_t smc_wait_to_send_packet(struct sk_buff *skb, if ( status & IM_ALLOC_INT ) { /* acknowledge the interrupt */ outb( IM_ALLOC_INT, ioaddr + INTERRUPT ); - break; + break; } - } while ( -- time_out ); + } while ( -- time_out ); - if ( !time_out ) { + if ( !time_out ) { /* oh well, wait until the chip finds memory later */ SMC_ENABLE_INT( IM_ALLOC_INT ); PRINTK2((CARDNAME": memory allocation deferred.\n")); /* it's deferred, but I'll handle it later */ return NETDEV_TX_OK; - } + } /* or YES! I can send the packet now.. */ smc_hardware_send_packet(dev); netif_wake_queue(dev); @@ -616,7 +616,7 @@ static void smc_hardware_send_packet( struct net_device * dev ) #endif /* send the packet length ( +6 for status, length and ctl byte ) - and the status word ( set to zeros ) */ + and the status word ( set to zeros ) */ #ifdef USE_32_BIT outl( (length +6 ) << 16 , ioaddr + DATA_1 ); #else @@ -629,8 +629,8 @@ static void smc_hardware_send_packet( struct net_device * dev ) /* send the actual data . I _think_ it's faster to send the longs first, and then . mop up by sending the last word. It depends heavily - . on alignment, at least on the 486. Maybe it would be - . a good idea to check which is optimal? But that could take + . on alignment, at least on the 486. Maybe it would be + . a good idea to check which is optimal? But that could take . almost as much time as is saved? */ #ifdef USE_32_BIT @@ -757,7 +757,7 @@ static int __init smc_findirq(int ioaddr) outb( IM_ALLOC_INT, ioaddr + INT_MASK ); /* - . Allocate 512 bytes of memory. Note that the chip was just + . Allocate 512 bytes of memory. Note that the chip was just . reset so all the memory is available */ outw( MC_ALLOC | 1, ioaddr + MMU_CMD ); @@ -871,7 +871,7 @@ static int __init smc_probe(struct net_device *dev, int ioaddr) goto err_out; } /* The above MIGHT indicate a device, but I need to write to further - test this. */ + test this. */ outw( 0x0, ioaddr + BANK_SELECT ); bank = inw( ioaddr + BANK_SELECT ); if ( (bank & 0xFF00 ) != 0x3300 ) { @@ -879,7 +879,7 @@ static int __init smc_probe(struct net_device *dev, int ioaddr) goto err_out; } /* well, we've already written once, so hopefully another time won't - hurt. This time, I need to switch the bank register to bank 1, + hurt. This time, I need to switch the bank register to bank 1, so I can access the base address register */ SMC_SELECT_BANK(1); base_address_register = inw( ioaddr + BASE ); @@ -917,7 +917,7 @@ static int __init smc_probe(struct net_device *dev, int ioaddr) dev->base_addr = ioaddr; /* - . Get the MAC address ( bank 1, regs 4 - 9 ) + . Get the MAC address ( bank 1, regs 4 - 9 ) */ SMC_SELECT_BANK( 1 ); for ( i = 0; i < 6; i += 2 ) { @@ -938,8 +938,8 @@ static int __init smc_probe(struct net_device *dev, int ioaddr) /* Now, I want to find out more about the chip. This is sort of - redundant, but it's cleaner to have it in both, rather than having - one VERY long probe procedure. + redundant, but it's cleaner to have it in both, rather than having + one VERY long probe procedure. */ SMC_SELECT_BANK(3); revision_register = inw( ioaddr + REVISION ); @@ -967,7 +967,7 @@ static int __init smc_probe(struct net_device *dev, int ioaddr) /* . If dev->irq is 0, then the device has to be banged on to see . what the IRQ is. - . + . . This banging doesn't always detect the IRQ, for unknown reasons. . a workaround is to reset the chip and try again. . @@ -978,7 +978,7 @@ static int __init smc_probe(struct net_device *dev, int ioaddr) . . Specifying an IRQ is done with the assumption that the user knows . what (s)he is doing. No checking is done!!!! - . + . */ if ( dev->irq < 2 ) { int trials; @@ -1070,7 +1070,7 @@ static int smc_open(struct net_device *dev) } /* - According to Becker, I have to set the hardware address + According to Becker, I have to set the hardware address at this point, because the (l)user can set it with an ioctl. Easily done... */ diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index cbde83f620a0..813ea941b91a 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -671,19 +671,19 @@ smc_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) status = SMC_GET_INT(lp); if (status & IM_ALLOC_INT) { SMC_ACK_INT(lp, IM_ALLOC_INT); - break; + break; } - } while (--poll_count); + } while (--poll_count); smc_special_unlock(&lp->lock, flags); lp->pending_tx_skb = skb; - if (!poll_count) { + if (!poll_count) { /* oh well, wait until the chip finds memory later */ netif_stop_queue(dev); DBG(2, dev, "TX memory allocation deferred.\n"); SMC_ENABLE_INT(lp, IM_ALLOC_INT); - } else { + } else { /* * Allocation succeeded: push packet to the chip's own memory * immediately. @@ -1790,7 +1790,7 @@ static int smc_findirq(struct smc_local *lp) SMC_SET_INT_MASK(lp, IM_ALLOC_INT); /* - * Allocate 512 bytes of memory. Note that the chip was just + * Allocate 512 bytes of memory. Note that the chip was just * reset so all the memory is available */ SMC_SET_MMU_CMD(lp, MC_ALLOC | 1); @@ -1998,8 +1998,8 @@ static int smc_probe(struct net_device *dev, void __iomem *ioaddr, /* Grab the IRQ */ retval = request_irq(dev->irq, smc_interrupt, irq_flags, dev->name, dev); - if (retval) - goto err_out; + if (retval) + goto err_out; #ifdef CONFIG_ARCH_PXA # ifdef SMC_USE_PXA_DMA diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index dfc85cc68173..20d148c019d8 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -958,7 +958,6 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget) xdp_init_buff(&xdp, PAGE_SIZE, &dring->xdp_rxq); - rcu_read_lock(); xdp_prog = READ_ONCE(priv->xdp_prog); dma_dir = page_pool_get_dma_dir(dring->page_pool); @@ -1069,8 +1068,6 @@ next: } netsec_finalize_xdp_rx(priv, xdp_act, xdp_xmit); - rcu_read_unlock(); - return done; } diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index fcbb4bb31408..5eb6bb4f7b6c 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/** +/* * sni_ave.c - Socionext UniPhier AVE ethernet driver * Copyright 2014 Panasonic Corporation * Copyright 2015-2017 Socionext Inc. diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 7737e4d0bb9e..ac3c248d4f9b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -66,6 +66,18 @@ config DWMAC_ANARION This selects the Anarion SoC glue layer support for the stmmac driver. +config DWMAC_INGENIC + tristate "Ingenic MAC support" + default MACH_INGENIC + depends on OF && HAS_IOMEM && (MACH_INGENIC || COMPILE_TEST) + select MFD_SYSCON + help + Support for ethernet controller on Ingenic SoCs. + + This selects Ingenic SoCs glue layer support for the stmmac + device driver. This driver is used on for the Ingenic SoCs + MAC ethernet controller. + config DWMAC_IPQ806X tristate "QCA IPQ806x DWMAC support" default ARCH_QCOM @@ -238,6 +250,15 @@ config DWMAC_INTEL This selects the Intel platform specific bus support for the stmmac driver. This driver is used for Intel Quark/EHL/TGL. +config DWMAC_LOONGSON + tristate "Loongson PCI DWMAC support" + default MACH_LOONGSON64 + depends on STMMAC_ETH && PCI + depends on COMMON_CLK + help + This selects the LOONGSON PCI bus support for the stmmac driver, + Support for ethernet controller on Loongson-2K1000 SoC and LS7A1000 bridge. + config STMMAC_PCI tristate "STMMAC PCI bus support" depends on STMMAC_ETH && PCI diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index f2e478b884b0..d4e12e9ace4f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -14,6 +14,7 @@ stmmac-$(CONFIG_STMMAC_SELFTESTS) += stmmac_selftests.o # Ordering matters. Generic driver must be last. obj-$(CONFIG_STMMAC_PLATFORM) += stmmac-platform.o obj-$(CONFIG_DWMAC_ANARION) += dwmac-anarion.o +obj-$(CONFIG_DWMAC_INGENIC) += dwmac-ingenic.o obj-$(CONFIG_DWMAC_IPQ806X) += dwmac-ipq806x.o obj-$(CONFIG_DWMAC_LPC18XX) += dwmac-lpc18xx.o obj-$(CONFIG_DWMAC_MEDIATEK) += dwmac-mediatek.o @@ -36,4 +37,5 @@ dwmac-altr-socfpga-objs := altr_tse_pcs.o dwmac-socfpga.o obj-$(CONFIG_STMMAC_PCI) += stmmac-pci.o obj-$(CONFIG_DWMAC_INTEL) += dwmac-intel.o +obj-$(CONFIG_DWMAC_LOONGSON) += dwmac-loongson.o stmmac-pci-objs:= stmmac_pci.o diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 619e3c0760d6..5fecc83f175b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -503,8 +503,7 @@ struct mac_device_info { const struct stmmac_hwtimestamp *ptp; const struct stmmac_tc_ops *tc; const struct stmmac_mmc_ops *mmc; - const struct mdio_xpcs_ops *xpcs; - struct mdio_xpcs_args xpcs_args; + struct dw_xpcs *xpcs; struct mii_regs mii; /* MII register Addresses */ struct mac_link link; void __iomem *pcsr; /* vpointer to device CSRs */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c new file mode 100644 index 000000000000..9a6d819b84ae --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c @@ -0,0 +1,398 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * dwmac-ingenic.c - Ingenic SoCs DWMAC specific glue layer + * + * Copyright (c) 2021 周琰杰 (Zhou Yanjie) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "stmmac_platform.h" + +#define MACPHYC_TXCLK_SEL_MASK GENMASK(31, 31) +#define MACPHYC_TXCLK_SEL_OUTPUT 0x1 +#define MACPHYC_TXCLK_SEL_INPUT 0x0 +#define MACPHYC_MODE_SEL_MASK GENMASK(31, 31) +#define MACPHYC_MODE_SEL_RMII 0x0 +#define MACPHYC_TX_SEL_MASK GENMASK(19, 19) +#define MACPHYC_TX_SEL_ORIGIN 0x0 +#define MACPHYC_TX_SEL_DELAY 0x1 +#define MACPHYC_TX_DELAY_MASK GENMASK(18, 12) +#define MACPHYC_RX_SEL_MASK GENMASK(11, 11) +#define MACPHYC_RX_SEL_ORIGIN 0x0 +#define MACPHYC_RX_SEL_DELAY 0x1 +#define MACPHYC_RX_DELAY_MASK GENMASK(10, 4) +#define MACPHYC_SOFT_RST_MASK GENMASK(3, 3) +#define MACPHYC_PHY_INFT_MASK GENMASK(2, 0) +#define MACPHYC_PHY_INFT_RMII 0x4 +#define MACPHYC_PHY_INFT_RGMII 0x1 +#define MACPHYC_PHY_INFT_GMII 0x0 +#define MACPHYC_PHY_INFT_MII 0x0 + +#define MACPHYC_TX_DELAY_PS_MAX 2496 +#define MACPHYC_TX_DELAY_PS_MIN 20 + +#define MACPHYC_RX_DELAY_PS_MAX 2496 +#define MACPHYC_RX_DELAY_PS_MIN 20 + +enum ingenic_mac_version { + ID_JZ4775, + ID_X1000, + ID_X1600, + ID_X1830, + ID_X2000, +}; + +struct ingenic_mac { + const struct ingenic_soc_info *soc_info; + struct device *dev; + struct regmap *regmap; + + int rx_delay; + int tx_delay; +}; + +struct ingenic_soc_info { + enum ingenic_mac_version version; + u32 mask; + + int (*set_mode)(struct plat_stmmacenet_data *plat_dat); +}; + +static int ingenic_mac_init(struct plat_stmmacenet_data *plat_dat) +{ + struct ingenic_mac *mac = plat_dat->bsp_priv; + int ret; + + if (mac->soc_info->set_mode) { + ret = mac->soc_info->set_mode(plat_dat); + if (ret) + return ret; + } + + return 0; +} + +static int jz4775_mac_set_mode(struct plat_stmmacenet_data *plat_dat) +{ + struct ingenic_mac *mac = plat_dat->bsp_priv; + unsigned int val; + + switch (plat_dat->interface) { + case PHY_INTERFACE_MODE_MII: + val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) | + FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_MII); + dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_MII\n"); + break; + + case PHY_INTERFACE_MODE_GMII: + val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) | + FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_GMII); + dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_GMII\n"); + break; + + case PHY_INTERFACE_MODE_RMII: + val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) | + FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII); + dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n"); + break; + + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_TXID: + case PHY_INTERFACE_MODE_RGMII_RXID: + val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) | + FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RGMII); + dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RGMII\n"); + break; + + default: + dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface); + return -EINVAL; + } + + /* Update MAC PHY control register */ + return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, val); +} + +static int x1000_mac_set_mode(struct plat_stmmacenet_data *plat_dat) +{ + struct ingenic_mac *mac = plat_dat->bsp_priv; + + switch (plat_dat->interface) { + case PHY_INTERFACE_MODE_RMII: + dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n"); + break; + + default: + dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface); + return -EINVAL; + } + + /* Update MAC PHY control register */ + return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, 0); +} + +static int x1600_mac_set_mode(struct plat_stmmacenet_data *plat_dat) +{ + struct ingenic_mac *mac = plat_dat->bsp_priv; + unsigned int val; + + switch (plat_dat->interface) { + case PHY_INTERFACE_MODE_RMII: + val = FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII); + dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n"); + break; + + default: + dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface); + return -EINVAL; + } + + /* Update MAC PHY control register */ + return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, val); +} + +static int x1830_mac_set_mode(struct plat_stmmacenet_data *plat_dat) +{ + struct ingenic_mac *mac = plat_dat->bsp_priv; + unsigned int val; + + switch (plat_dat->interface) { + case PHY_INTERFACE_MODE_RMII: + val = FIELD_PREP(MACPHYC_MODE_SEL_MASK, MACPHYC_MODE_SEL_RMII) | + FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII); + dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n"); + break; + + default: + dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface); + return -EINVAL; + } + + /* Update MAC PHY control register */ + return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, val); +} + +static int x2000_mac_set_mode(struct plat_stmmacenet_data *plat_dat) +{ + struct ingenic_mac *mac = plat_dat->bsp_priv; + unsigned int val; + + switch (plat_dat->interface) { + case PHY_INTERFACE_MODE_RMII: + val = FIELD_PREP(MACPHYC_TX_SEL_MASK, MACPHYC_TX_SEL_ORIGIN) | + FIELD_PREP(MACPHYC_RX_SEL_MASK, MACPHYC_RX_SEL_ORIGIN) | + FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII); + dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n"); + break; + + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_TXID: + case PHY_INTERFACE_MODE_RGMII_RXID: + val = FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RGMII); + + if (mac->tx_delay == 0) + val |= FIELD_PREP(MACPHYC_TX_SEL_MASK, MACPHYC_TX_SEL_ORIGIN); + else + val |= FIELD_PREP(MACPHYC_TX_SEL_MASK, MACPHYC_TX_SEL_DELAY) | + FIELD_PREP(MACPHYC_TX_DELAY_MASK, (mac->tx_delay + 9750) / 19500 - 1); + + if (mac->rx_delay == 0) + val |= FIELD_PREP(MACPHYC_RX_SEL_MASK, MACPHYC_RX_SEL_ORIGIN); + else + val |= FIELD_PREP(MACPHYC_RX_SEL_MASK, MACPHYC_RX_SEL_DELAY) | + FIELD_PREP(MACPHYC_RX_DELAY_MASK, (mac->rx_delay + 9750) / 19500 - 1); + + dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RGMII\n"); + break; + + default: + dev_err(mac->dev, "Unsupported interface %d", plat_dat->interface); + return -EINVAL; + } + + /* Update MAC PHY control register */ + return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, val); +} + +static int ingenic_mac_probe(struct platform_device *pdev) +{ + struct plat_stmmacenet_data *plat_dat; + struct stmmac_resources stmmac_res; + struct ingenic_mac *mac; + const struct ingenic_soc_info *data; + u32 tx_delay_ps, rx_delay_ps; + int ret; + + ret = stmmac_get_platform_resources(pdev, &stmmac_res); + if (ret) + return ret; + + plat_dat = stmmac_probe_config_dt(pdev, stmmac_res.mac); + if (IS_ERR(plat_dat)) + return PTR_ERR(plat_dat); + + mac = devm_kzalloc(&pdev->dev, sizeof(*mac), GFP_KERNEL); + if (!mac) { + ret = -ENOMEM; + goto err_remove_config_dt; + } + + data = of_device_get_match_data(&pdev->dev); + if (!data) { + dev_err(&pdev->dev, "No of match data provided\n"); + ret = -EINVAL; + goto err_remove_config_dt; + } + + /* Get MAC PHY control register */ + mac->regmap = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, "mode-reg"); + if (IS_ERR(mac->regmap)) { + dev_err(&pdev->dev, "%s: Failed to get syscon regmap\n", __func__); + ret = PTR_ERR(mac->regmap); + goto err_remove_config_dt; + } + + if (!of_property_read_u32(pdev->dev.of_node, "tx-clk-delay-ps", &tx_delay_ps)) { + if (tx_delay_ps >= MACPHYC_TX_DELAY_PS_MIN && + tx_delay_ps <= MACPHYC_TX_DELAY_PS_MAX) { + mac->tx_delay = tx_delay_ps * 1000; + } else { + dev_err(&pdev->dev, "Invalid TX clock delay: %dps\n", tx_delay_ps); + return -EINVAL; + } + } + + if (!of_property_read_u32(pdev->dev.of_node, "rx-clk-delay-ps", &rx_delay_ps)) { + if (rx_delay_ps >= MACPHYC_RX_DELAY_PS_MIN && + rx_delay_ps <= MACPHYC_RX_DELAY_PS_MAX) { + mac->rx_delay = rx_delay_ps * 1000; + } else { + dev_err(&pdev->dev, "Invalid RX clock delay: %dps\n", rx_delay_ps); + return -EINVAL; + } + } + + mac->soc_info = data; + mac->dev = &pdev->dev; + + plat_dat->bsp_priv = mac; + + ret = ingenic_mac_init(plat_dat); + if (ret) + goto err_remove_config_dt; + + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (ret) + goto err_remove_config_dt; + + return 0; + +err_remove_config_dt: + stmmac_remove_config_dt(pdev, plat_dat); + + return ret; +} + +#ifdef CONFIG_PM_SLEEP +static int ingenic_mac_suspend(struct device *dev) +{ + int ret; + + ret = stmmac_suspend(dev); + + return ret; +} + +static int ingenic_mac_resume(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + int ret; + + ret = ingenic_mac_init(priv->plat); + if (ret) + return ret; + + ret = stmmac_resume(dev); + + return ret; +} +#endif /* CONFIG_PM_SLEEP */ + +static SIMPLE_DEV_PM_OPS(ingenic_mac_pm_ops, ingenic_mac_suspend, ingenic_mac_resume); + +static struct ingenic_soc_info jz4775_soc_info = { + .version = ID_JZ4775, + .mask = MACPHYC_TXCLK_SEL_MASK | MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK, + + .set_mode = jz4775_mac_set_mode, +}; + +static struct ingenic_soc_info x1000_soc_info = { + .version = ID_X1000, + .mask = MACPHYC_SOFT_RST_MASK, + + .set_mode = x1000_mac_set_mode, +}; + +static struct ingenic_soc_info x1600_soc_info = { + .version = ID_X1600, + .mask = MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK, + + .set_mode = x1600_mac_set_mode, +}; + +static struct ingenic_soc_info x1830_soc_info = { + .version = ID_X1830, + .mask = MACPHYC_MODE_SEL_MASK | MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK, + + .set_mode = x1830_mac_set_mode, +}; + +static struct ingenic_soc_info x2000_soc_info = { + .version = ID_X2000, + .mask = MACPHYC_TX_SEL_MASK | MACPHYC_TX_DELAY_MASK | MACPHYC_RX_SEL_MASK | + MACPHYC_RX_DELAY_MASK | MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK, + + .set_mode = x2000_mac_set_mode, +}; + +static const struct of_device_id ingenic_mac_of_matches[] = { + { .compatible = "ingenic,jz4775-mac", .data = &jz4775_soc_info }, + { .compatible = "ingenic,x1000-mac", .data = &x1000_soc_info }, + { .compatible = "ingenic,x1600-mac", .data = &x1600_soc_info }, + { .compatible = "ingenic,x1830-mac", .data = &x1830_soc_info }, + { .compatible = "ingenic,x2000-mac", .data = &x2000_soc_info }, + { } +}; +MODULE_DEVICE_TABLE(of, ingenic_mac_of_matches); + +static struct platform_driver ingenic_mac_driver = { + .probe = ingenic_mac_probe, + .remove = stmmac_pltfr_remove, + .driver = { + .name = "ingenic-mac", + .pm = pm_ptr(&ingenic_mac_pm_ops), + .of_match_table = ingenic_mac_of_matches, + }, +}; +module_platform_driver(ingenic_mac_driver); + +MODULE_AUTHOR("周琰杰 (Zhou Yanjie) "); +MODULE_DESCRIPTION("Ingenic SoCs DWMAC specific glue layer"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 80728a4c0e3f..8e8778cfbbad 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -10,22 +10,6 @@ #include "stmmac.h" #include "stmmac_ptp.h" -#define INTEL_MGBE_ADHOC_ADDR 0x15 -#define INTEL_MGBE_XPCS_ADDR 0x16 - -/* Selection for PTP Clock Freq belongs to PSE & PCH GbE */ -#define PSE_PTP_CLK_FREQ_MASK (GMAC_GPO0 | GMAC_GPO3) -#define PSE_PTP_CLK_FREQ_19_2MHZ (GMAC_GPO0) -#define PSE_PTP_CLK_FREQ_200MHZ (GMAC_GPO0 | GMAC_GPO3) -#define PSE_PTP_CLK_FREQ_256MHZ (0) -#define PCH_PTP_CLK_FREQ_MASK (GMAC_GPO0) -#define PCH_PTP_CLK_FREQ_19_2MHZ (GMAC_GPO0) -#define PCH_PTP_CLK_FREQ_200MHZ (0) - -/* Cross-timestamping defines */ -#define ART_CPUID_LEAF 0x15 -#define EHL_PSE_ART_MHZ 19200000 - struct intel_priv_data { int mdio_adhoc_addr; /* mdio address for serdes & etc */ unsigned long crossts_adj; @@ -102,6 +86,22 @@ static int intel_serdes_powerup(struct net_device *ndev, void *priv_data) serdes_phy_addr = intel_priv->mdio_adhoc_addr; + /* Set the serdes rate and the PCLK rate */ + data = mdiobus_read(priv->mii, serdes_phy_addr, + SERDES_GCR0); + + data &= ~SERDES_RATE_MASK; + data &= ~SERDES_PCLK_MASK; + + if (priv->plat->max_speed == 2500) + data |= SERDES_RATE_PCIE_GEN2 << SERDES_RATE_PCIE_SHIFT | + SERDES_PCLK_37p5MHZ << SERDES_PCLK_SHIFT; + else + data |= SERDES_RATE_PCIE_GEN1 << SERDES_RATE_PCIE_SHIFT | + SERDES_PCLK_70MHZ << SERDES_PCLK_SHIFT; + + mdiobus_write(priv->mii, serdes_phy_addr, SERDES_GCR0, data); + /* assert clk_req */ data = mdiobus_read(priv->mii, serdes_phy_addr, SERDES_GCR0); data |= SERDES_PLL_CLK; @@ -230,6 +230,32 @@ static void intel_serdes_powerdown(struct net_device *ndev, void *intel_data) } } +static void intel_speed_mode_2500(struct net_device *ndev, void *intel_data) +{ + struct intel_priv_data *intel_priv = intel_data; + struct stmmac_priv *priv = netdev_priv(ndev); + int serdes_phy_addr = 0; + u32 data = 0; + + serdes_phy_addr = intel_priv->mdio_adhoc_addr; + + /* Determine the link speed mode: 2.5Gbps/1Gbps */ + data = mdiobus_read(priv->mii, serdes_phy_addr, + SERDES_GCR); + + if (((data & SERDES_LINK_MODE_MASK) >> SERDES_LINK_MODE_SHIFT) == + SERDES_LINK_MODE_2G5) { + dev_info(priv->device, "Link Speed Mode: 2.5Gbps\n"); + priv->plat->max_speed = 2500; + priv->plat->phy_interface = PHY_INTERFACE_MODE_2500BASEX; + priv->plat->mdio_bus_data->xpcs_an_inband = false; + } else { + priv->plat->max_speed = 1000; + priv->plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + priv->plat->mdio_bus_data->xpcs_an_inband = true; + } +} + /* Program PTP Clock Frequency for different variant of * Intel mGBE that has slightly different GPO mapping */ @@ -429,6 +455,17 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->force_sf_dma_mode = 0; plat->tso_en = 1; + /* Multiplying factor to the clk_eee_i clock time + * period to make it closer to 100 ns. This value + * should be programmed such that the clk_eee_time_period * + * (MULT_FACT_100NS + 1) should be within 80 ns to 120 ns + * clk_eee frequency is 19.2Mhz + * clk_eee_time_period is 52ns + * 52ns * (1 + 1) = 104ns + * MULT_FACT_100NS = 1 + */ + plat->mult_fact_100ns = 1; + plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; for (i = 0; i < plat->rx_queues_to_use; i++) { @@ -556,6 +593,17 @@ static int ehl_common_data(struct pci_dev *pdev, plat->rx_queues_to_use = 8; plat->tx_queues_to_use = 8; plat->clk_ptp_rate = 200000000; + plat->use_phy_wol = 1; + + plat->safety_feat_cfg->tsoee = 1; + plat->safety_feat_cfg->mrxpee = 1; + plat->safety_feat_cfg->mestee = 1; + plat->safety_feat_cfg->mrxee = 1; + plat->safety_feat_cfg->mtxee = 1; + plat->safety_feat_cfg->epsi = 0; + plat->safety_feat_cfg->edpp = 0; + plat->safety_feat_cfg->prtyen = 0; + plat->safety_feat_cfg->tmouten = 0; return intel_mgbe_common_data(pdev, plat); } @@ -565,7 +613,7 @@ static int ehl_sgmii_data(struct pci_dev *pdev, { plat->bus_id = 1; plat->phy_interface = PHY_INTERFACE_MODE_SGMII; - + plat->speed_mode_2500 = intel_speed_mode_2500; plat->serdes_powerup = intel_serdes_powerup; plat->serdes_powerdown = intel_serdes_powerdown; @@ -618,6 +666,7 @@ static int ehl_pse0_sgmii1g_data(struct pci_dev *pdev, struct plat_stmmacenet_data *plat) { plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + plat->speed_mode_2500 = intel_speed_mode_2500; plat->serdes_powerup = intel_serdes_powerup; plat->serdes_powerdown = intel_serdes_powerdown; return ehl_pse0_common_data(pdev, plat); @@ -656,6 +705,7 @@ static int ehl_pse1_sgmii1g_data(struct pci_dev *pdev, struct plat_stmmacenet_data *plat) { plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + plat->speed_mode_2500 = intel_speed_mode_2500; plat->serdes_powerup = intel_serdes_powerup; plat->serdes_powerdown = intel_serdes_powerdown; return ehl_pse1_common_data(pdev, plat); @@ -672,6 +722,16 @@ static int tgl_common_data(struct pci_dev *pdev, plat->tx_queues_to_use = 4; plat->clk_ptp_rate = 200000000; + plat->safety_feat_cfg->tsoee = 1; + plat->safety_feat_cfg->mrxpee = 0; + plat->safety_feat_cfg->mestee = 1; + plat->safety_feat_cfg->mrxee = 1; + plat->safety_feat_cfg->mtxee = 1; + plat->safety_feat_cfg->epsi = 0; + plat->safety_feat_cfg->edpp = 0; + plat->safety_feat_cfg->prtyen = 0; + plat->safety_feat_cfg->tmouten = 0; + return intel_mgbe_common_data(pdev, plat); } @@ -680,6 +740,7 @@ static int tgl_sgmii_phy0_data(struct pci_dev *pdev, { plat->bus_id = 1; plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + plat->speed_mode_2500 = intel_speed_mode_2500; plat->serdes_powerup = intel_serdes_powerup; plat->serdes_powerdown = intel_serdes_powerdown; return tgl_common_data(pdev, plat); @@ -694,6 +755,7 @@ static int tgl_sgmii_phy1_data(struct pci_dev *pdev, { plat->bus_id = 2; plat->phy_interface = PHY_INTERFACE_MODE_SGMII; + plat->speed_mode_2500 = intel_speed_mode_2500; plat->serdes_powerup = intel_serdes_powerup; plat->serdes_powerdown = intel_serdes_powerdown; return tgl_common_data(pdev, plat); @@ -948,6 +1010,12 @@ static int intel_eth_pci_probe(struct pci_dev *pdev, if (!plat->dma_cfg) return -ENOMEM; + plat->safety_feat_cfg = devm_kzalloc(&pdev->dev, + sizeof(*plat->safety_feat_cfg), + GFP_KERNEL); + if (!plat->safety_feat_cfg) + return -ENOMEM; + /* Enable pci device */ ret = pcim_enable_device(pdev); if (ret) { @@ -1020,7 +1088,7 @@ err_alloc_irq: /** * intel_eth_pci_remove * - * @pdev: platform device pointer + * @pdev: pci device pointer * Description: this function calls the main to free the net resources * and releases the PCI resources. */ @@ -1050,6 +1118,7 @@ static int __maybe_unused intel_eth_pci_suspend(struct device *dev) return ret; pci_wake_from_d3(pdev, true); + pci_set_power_state(pdev, PCI_D3hot); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h index 542acb8ce467..0a37987478c1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h @@ -9,6 +9,7 @@ #define POLL_DELAY_US 8 /* SERDES Register */ +#define SERDES_GCR 0x0 /* Global Conguration */ #define SERDES_GSR0 0x5 /* Global Status Reg0 */ #define SERDES_GCR0 0xb /* Global Configuration Reg0 */ @@ -17,8 +18,36 @@ #define SERDES_PHY_RX_CLK BIT(1) /* PSE SGMII PHY rx clk */ #define SERDES_RST BIT(2) /* Serdes Reset */ #define SERDES_PWR_ST_MASK GENMASK(6, 4) /* Serdes Power state*/ +#define SERDES_RATE_MASK GENMASK(9, 8) +#define SERDES_PCLK_MASK GENMASK(14, 12) /* PCLK rate to PHY */ +#define SERDES_LINK_MODE_MASK GENMASK(2, 1) +#define SERDES_LINK_MODE_SHIFT 1 #define SERDES_PWR_ST_SHIFT 4 #define SERDES_PWR_ST_P0 0x0 #define SERDES_PWR_ST_P3 0x3 +#define SERDES_LINK_MODE_2G5 0x3 +#define SERSED_LINK_MODE_1G 0x2 +#define SERDES_PCLK_37p5MHZ 0x0 +#define SERDES_PCLK_70MHZ 0x1 +#define SERDES_RATE_PCIE_GEN1 0x0 +#define SERDES_RATE_PCIE_GEN2 0x1 +#define SERDES_RATE_PCIE_SHIFT 8 +#define SERDES_PCLK_SHIFT 12 + +#define INTEL_MGBE_ADHOC_ADDR 0x15 +#define INTEL_MGBE_XPCS_ADDR 0x16 + +/* Cross-timestamping defines */ +#define ART_CPUID_LEAF 0x15 +#define EHL_PSE_ART_MHZ 19200000 + +/* Selection for PTP Clock Freq belongs to PSE & PCH GbE */ +#define PSE_PTP_CLK_FREQ_MASK (GMAC_GPO0 | GMAC_GPO3) +#define PSE_PTP_CLK_FREQ_19_2MHZ (GMAC_GPO0) +#define PSE_PTP_CLK_FREQ_200MHZ (GMAC_GPO0 | GMAC_GPO3) +#define PSE_PTP_CLK_FREQ_256MHZ (0) +#define PCH_PTP_CLK_FREQ_MASK (GMAC_GPO0) +#define PCH_PTP_CLK_FREQ_19_2MHZ (GMAC_GPO0) +#define PCH_PTP_CLK_FREQ_200MHZ (0) #endif /* __DWMAC_INTEL_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c new file mode 100644 index 000000000000..e108b0d2bd28 --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020, Loongson Corporation + */ + +#include +#include +#include +#include +#include +#include "stmmac.h" + +static int loongson_default_data(struct plat_stmmacenet_data *plat) +{ + plat->clk_csr = 2; /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ + plat->has_gmac = 1; + plat->force_sf_dma_mode = 1; + + /* Set default value for multicast hash bins */ + plat->multicast_filter_bins = HASH_TABLE_SIZE; + + /* Set default value for unicast filter entries */ + plat->unicast_filter_entries = 1; + + /* Set the maxmtu to a default of JUMBO_LEN */ + plat->maxmtu = JUMBO_LEN; + + /* Set default number of RX and TX queues to use */ + plat->tx_queues_to_use = 1; + plat->rx_queues_to_use = 1; + + /* Disable Priority config by default */ + plat->tx_queues_cfg[0].use_prio = false; + plat->rx_queues_cfg[0].use_prio = false; + + /* Disable RX queues routing by default */ + plat->rx_queues_cfg[0].pkt_route = 0x0; + + /* Default to phy auto-detection */ + plat->phy_addr = -1; + + plat->dma_cfg->pbl = 32; + plat->dma_cfg->pblx8 = true; + + plat->multicast_filter_bins = 256; + return 0; +} + +static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct plat_stmmacenet_data *plat; + struct stmmac_resources res; + bool mdio = false; + int ret, i; + struct device_node *np; + + np = dev_of_node(&pdev->dev); + + if (!np) { + pr_info("dwmac_loongson_pci: No OF node\n"); + return -ENODEV; + } + + if (!of_device_is_compatible(np, "loongson, pci-gmac")) { + pr_info("dwmac_loongson_pci: Incompatible OF node\n"); + return -ENODEV; + } + + plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); + if (!plat) + return -ENOMEM; + + if (plat->mdio_node) { + dev_err(&pdev->dev, "Found MDIO subnode\n"); + mdio = true; + } + + if (mdio) { + plat->mdio_bus_data = devm_kzalloc(&pdev->dev, + sizeof(*plat->mdio_bus_data), + GFP_KERNEL); + if (!plat->mdio_bus_data) + return -ENOMEM; + plat->mdio_bus_data->needs_reset = true; + } + + plat->dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*plat->dma_cfg), GFP_KERNEL); + if (!plat->dma_cfg) + return -ENOMEM; + + /* Enable pci device */ + ret = pci_enable_device(pdev); + if (ret) { + dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n", __func__); + return ret; + } + + /* Get the base address of device */ + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (pci_resource_len(pdev, i) == 0) + continue; + ret = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev)); + if (ret) + return ret; + break; + } + + plat->bus_id = of_alias_get_id(np, "ethernet"); + if (plat->bus_id < 0) + plat->bus_id = pci_dev_id(pdev); + + plat->phy_interface = device_get_phy_mode(&pdev->dev); + if (plat->phy_interface < 0) + dev_err(&pdev->dev, "phy_mode not found\n"); + + plat->interface = PHY_INTERFACE_MODE_GMII; + + pci_set_master(pdev); + + loongson_default_data(plat); + pci_enable_msi(pdev); + memset(&res, 0, sizeof(res)); + res.addr = pcim_iomap_table(pdev)[0]; + + res.irq = of_irq_get_byname(np, "macirq"); + if (res.irq < 0) { + dev_err(&pdev->dev, "IRQ macirq not found\n"); + ret = -ENODEV; + } + + res.wol_irq = of_irq_get_byname(np, "eth_wake_irq"); + if (res.wol_irq < 0) { + dev_info(&pdev->dev, "IRQ eth_wake_irq not found, using macirq\n"); + res.wol_irq = res.irq; + } + + res.lpi_irq = of_irq_get_byname(np, "eth_lpi"); + if (res.lpi_irq < 0) { + dev_err(&pdev->dev, "IRQ eth_lpi not found\n"); + ret = -ENODEV; + } + + return stmmac_dvr_probe(&pdev->dev, plat, &res); +} + +static void loongson_dwmac_remove(struct pci_dev *pdev) +{ + int i; + + stmmac_dvr_remove(&pdev->dev); + + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (pci_resource_len(pdev, i) == 0) + continue; + pcim_iounmap_regions(pdev, BIT(i)); + break; + } + + pci_disable_device(pdev); +} + +static int __maybe_unused loongson_dwmac_suspend(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + ret = stmmac_suspend(dev); + if (ret) + return ret; + + ret = pci_save_state(pdev); + if (ret) + return ret; + + pci_disable_device(pdev); + pci_wake_from_d3(pdev, true); + return 0; +} + +static int __maybe_unused loongson_dwmac_resume(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + pci_restore_state(pdev); + pci_set_power_state(pdev, PCI_D0); + + ret = pci_enable_device(pdev); + if (ret) + return ret; + + pci_set_master(pdev); + + return stmmac_resume(dev); +} + +static SIMPLE_DEV_PM_OPS(loongson_dwmac_pm_ops, loongson_dwmac_suspend, + loongson_dwmac_resume); + +static const struct pci_device_id loongson_dwmac_id_table[] = { + { PCI_VDEVICE(LOONGSON, 0x7a03) }, + {} +}; +MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table); + +struct pci_driver loongson_dwmac_driver = { + .name = "dwmac-loongson-pci", + .id_table = loongson_dwmac_id_table, + .probe = loongson_dwmac_probe, + .remove = loongson_dwmac_remove, + .driver = { + .pm = &loongson_dwmac_pm_ops, + }, +}; + +module_pci_driver(loongson_dwmac_driver); + +MODULE_DESCRIPTION("Loongson DWMAC PCI driver"); +MODULE_AUTHOR("Qing Zhang "); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 84382fc5cc4d..5c74b6279d69 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -454,7 +454,6 @@ static int qcom_ethqos_probe(struct platform_device *pdev) struct stmmac_resources stmmac_res; const struct ethqos_emac_driver_data *data; struct qcom_ethqos *ethqos; - struct resource *res; int ret; ret = stmmac_get_platform_resources(pdev, &stmmac_res); @@ -474,8 +473,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev) } ethqos->pdev = pdev; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rgmii"); - ethqos->rgmii_base = devm_ioremap_resource(&pdev->dev, res); + ethqos->rgmii_base = devm_platform_ioremap_resource_byname(pdev, "rgmii"); if (IS_ERR(ethqos->rgmii_base)) { ret = PTR_ERR(ethqos->rgmii_base); goto err_mem; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 8d28a536e1bb..280ac0129572 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -33,11 +33,13 @@ struct rk_gmac_ops { void (*set_rgmii_speed)(struct rk_priv_data *bsp_priv, int speed); void (*set_rmii_speed)(struct rk_priv_data *bsp_priv, int speed); void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv); + u32 regs[]; }; struct rk_priv_data { struct platform_device *pdev; phy_interface_t phy_iface; + int id; struct regulator *regulator; bool suspended; const struct rk_gmac_ops *ops; @@ -482,6 +484,54 @@ static const struct rk_gmac_ops rk3288_ops = { .set_rmii_speed = rk3288_set_rmii_speed, }; +#define RK3308_GRF_MAC_CON0 0x04a0 + +/* RK3308_GRF_MAC_CON0 */ +#define RK3308_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(2) | GRF_CLR_BIT(3) | \ + GRF_BIT(4)) +#define RK3308_GMAC_FLOW_CTRL GRF_BIT(3) +#define RK3308_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) +#define RK3308_GMAC_SPEED_10M GRF_CLR_BIT(0) +#define RK3308_GMAC_SPEED_100M GRF_BIT(0) + +static void rk3308_set_to_rmii(struct rk_priv_data *bsp_priv) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "Missing rockchip,grf property\n"); + return; + } + + regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0, + RK3308_GMAC_PHY_INTF_SEL_RMII); +} + +static void rk3308_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed) +{ + struct device *dev = &bsp_priv->pdev->dev; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "Missing rockchip,grf property\n"); + return; + } + + if (speed == 10) { + regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0, + RK3308_GMAC_SPEED_10M); + } else if (speed == 100) { + regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0, + RK3308_GMAC_SPEED_100M); + } else { + dev_err(dev, "unknown speed value for RMII! speed=%d", speed); + } +} + +static const struct rk_gmac_ops rk3308_ops = { + .set_to_rmii = rk3308_set_to_rmii, + .set_rmii_speed = rk3308_set_rmii_speed, +}; + #define RK3328_GRF_MAC_CON0 0x0900 #define RK3328_GRF_MAC_CON1 0x0904 #define RK3328_GRF_MAC_CON2 0x0908 @@ -948,6 +998,107 @@ static const struct rk_gmac_ops rk3399_ops = { .set_rmii_speed = rk3399_set_rmii_speed, }; +#define RK3568_GRF_GMAC0_CON0 0x0380 +#define RK3568_GRF_GMAC0_CON1 0x0384 +#define RK3568_GRF_GMAC1_CON0 0x0388 +#define RK3568_GRF_GMAC1_CON1 0x038c + +/* RK3568_GRF_GMAC0_CON1 && RK3568_GRF_GMAC1_CON1 */ +#define RK3568_GMAC_PHY_INTF_SEL_RGMII \ + (GRF_BIT(4) | GRF_CLR_BIT(5) | GRF_CLR_BIT(6)) +#define RK3568_GMAC_PHY_INTF_SEL_RMII \ + (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | GRF_BIT(6)) +#define RK3568_GMAC_FLOW_CTRL GRF_BIT(3) +#define RK3568_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) +#define RK3568_GMAC_RXCLK_DLY_ENABLE GRF_BIT(1) +#define RK3568_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(1) +#define RK3568_GMAC_TXCLK_DLY_ENABLE GRF_BIT(0) +#define RK3568_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(0) + +/* RK3568_GRF_GMAC0_CON0 && RK3568_GRF_GMAC1_CON0 */ +#define RK3568_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) +#define RK3568_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) + +static void rk3568_set_to_rgmii(struct rk_priv_data *bsp_priv, + int tx_delay, int rx_delay) +{ + struct device *dev = &bsp_priv->pdev->dev; + u32 con0, con1; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "Missing rockchip,grf property\n"); + return; + } + + con0 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON0 : + RK3568_GRF_GMAC0_CON0; + con1 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON1 : + RK3568_GRF_GMAC0_CON1; + + regmap_write(bsp_priv->grf, con0, + RK3568_GMAC_CLK_RX_DL_CFG(rx_delay) | + RK3568_GMAC_CLK_TX_DL_CFG(tx_delay)); + + regmap_write(bsp_priv->grf, con1, + RK3568_GMAC_PHY_INTF_SEL_RGMII | + RK3568_GMAC_RXCLK_DLY_ENABLE | + RK3568_GMAC_TXCLK_DLY_ENABLE); +} + +static void rk3568_set_to_rmii(struct rk_priv_data *bsp_priv) +{ + struct device *dev = &bsp_priv->pdev->dev; + u32 con1; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "%s: Missing rockchip,grf property\n", __func__); + return; + } + + con1 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON1 : + RK3568_GRF_GMAC0_CON1; + regmap_write(bsp_priv->grf, con1, RK3568_GMAC_PHY_INTF_SEL_RMII); +} + +static void rk3568_set_gmac_speed(struct rk_priv_data *bsp_priv, int speed) +{ + struct device *dev = &bsp_priv->pdev->dev; + unsigned long rate; + int ret; + + switch (speed) { + case 10: + rate = 2500000; + break; + case 100: + rate = 25000000; + break; + case 1000: + rate = 125000000; + break; + default: + dev_err(dev, "unknown speed value for GMAC speed=%d", speed); + return; + } + + ret = clk_set_rate(bsp_priv->clk_mac_speed, rate); + if (ret) + dev_err(dev, "%s: set clk_mac_speed rate %ld failed %d\n", + __func__, rate, ret); +} + +static const struct rk_gmac_ops rk3568_ops = { + .set_to_rgmii = rk3568_set_to_rgmii, + .set_to_rmii = rk3568_set_to_rmii, + .set_rgmii_speed = rk3568_set_gmac_speed, + .set_rmii_speed = rk3568_set_gmac_speed, + .regs = { + 0xfe2a0000, /* gmac0 */ + 0xfe010000, /* gmac1 */ + 0x0, /* sentinel */ + }, +}; + #define RV1108_GRF_GMAC_CON0 0X0900 /* RV1108_GRF_GMAC_CON0 */ @@ -1216,6 +1367,7 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev, { struct rk_priv_data *bsp_priv; struct device *dev = &pdev->dev; + struct resource *res; int ret; const char *strings = NULL; int value; @@ -1227,6 +1379,22 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev, of_get_phy_mode(dev->of_node, &bsp_priv->phy_iface); bsp_priv->ops = ops; + /* Some SoCs have multiple MAC controllers, which need + * to be distinguished. + */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (res) { + int i = 0; + + while (ops->regs[i]) { + if (ops->regs[i] == res->start) { + bsp_priv->id = i; + break; + } + i++; + } + } + bsp_priv->regulator = devm_regulator_get_optional(dev, "phy"); if (IS_ERR(bsp_priv->regulator)) { if (PTR_ERR(bsp_priv->regulator) == -EPROBE_DEFER) { @@ -1294,11 +1462,36 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev, return bsp_priv; } +static int rk_gmac_check_ops(struct rk_priv_data *bsp_priv) +{ + switch (bsp_priv->phy_iface) { + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + if (!bsp_priv->ops->set_to_rgmii) + return -EINVAL; + break; + case PHY_INTERFACE_MODE_RMII: + if (!bsp_priv->ops->set_to_rmii) + return -EINVAL; + break; + default: + dev_err(&bsp_priv->pdev->dev, + "unsupported interface %d", bsp_priv->phy_iface); + } + return 0; +} + static int rk_gmac_powerup(struct rk_priv_data *bsp_priv) { int ret; struct device *dev = &bsp_priv->pdev->dev; + ret = rk_gmac_check_ops(bsp_priv); + if (ret) + return ret; + ret = gmac_clk_enable(bsp_priv, true); if (ret) return ret; @@ -1369,10 +1562,12 @@ static void rk_fix_speed(void *priv, unsigned int speed) case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: - bsp_priv->ops->set_rgmii_speed(bsp_priv, speed); + if (bsp_priv->ops->set_rgmii_speed) + bsp_priv->ops->set_rgmii_speed(bsp_priv, speed); break; case PHY_INTERFACE_MODE_RMII: - bsp_priv->ops->set_rmii_speed(bsp_priv, speed); + if (bsp_priv->ops->set_rmii_speed) + bsp_priv->ops->set_rmii_speed(bsp_priv, speed); break; default: dev_err(dev, "unsupported interface %d", bsp_priv->phy_iface); @@ -1400,7 +1595,11 @@ static int rk_gmac_probe(struct platform_device *pdev) if (IS_ERR(plat_dat)) return PTR_ERR(plat_dat); - plat_dat->has_gmac = true; + /* If the stmmac is not already selected as gmac4, + * then make sure we fallback to gmac. + */ + if (!plat_dat->has_gmac4) + plat_dat->has_gmac = true; plat_dat->fix_mac_speed = rk_fix_speed; plat_dat->bsp_priv = rk_gmac_setup(pdev, plat_dat, data); @@ -1477,10 +1676,12 @@ static const struct of_device_id rk_gmac_dwmac_match[] = { { .compatible = "rockchip,rk3128-gmac", .data = &rk3128_ops }, { .compatible = "rockchip,rk3228-gmac", .data = &rk3228_ops }, { .compatible = "rockchip,rk3288-gmac", .data = &rk3288_ops }, + { .compatible = "rockchip,rk3308-gmac", .data = &rk3308_ops }, { .compatible = "rockchip,rk3328-gmac", .data = &rk3328_ops }, { .compatible = "rockchip,rk3366-gmac", .data = &rk3366_ops }, { .compatible = "rockchip,rk3368-gmac", .data = &rk3368_ops }, { .compatible = "rockchip,rk3399-gmac", .data = &rk3399_ops }, + { .compatible = "rockchip,rk3568-gmac", .data = &rk3568_ops }, { .compatible = "rockchip,rv1108-gmac", .data = &rv1108_ops }, { } }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index f35c03c9f91e..67ba083eb90c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -1358,6 +1358,7 @@ int dwmac4_setup(struct stmmac_priv *priv) mac->link.speed10 = GMAC_CONFIG_PS; mac->link.speed100 = GMAC_CONFIG_FES | GMAC_CONFIG_PS; mac->link.speed1000 = 0; + mac->link.speed2500 = GMAC_CONFIG_FES; mac->link.speed_mask = GMAC_CONFIG_FES | GMAC_CONFIG_PS; mac->mii.addr = GMAC_MDIO_ADDR; mac->mii.data = GMAC_MDIO_DATA; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index d8c6ff725237..9c2d40f853ed 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -183,7 +183,8 @@ static void dwmac5_handle_dma_err(struct net_device *ndev, STAT_OFF(dma_errors), stats); } -int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp) +int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp, + struct stmmac_safety_feature_cfg *safety_feat_cfg) { u32 value; @@ -193,11 +194,16 @@ int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp) /* 1. Enable Safety Features */ value = readl(ioaddr + MTL_ECC_CONTROL); value |= MEEAO; /* MTL ECC Error Addr Status Override */ - value |= TSOEE; /* TSO ECC */ - value |= MRXPEE; /* MTL RX Parser ECC */ - value |= MESTEE; /* MTL EST ECC */ - value |= MRXEE; /* MTL RX FIFO ECC */ - value |= MTXEE; /* MTL TX FIFO ECC */ + if (safety_feat_cfg->tsoee) + value |= TSOEE; /* TSO ECC */ + if (safety_feat_cfg->mrxpee) + value |= MRXPEE; /* MTL RX Parser ECC */ + if (safety_feat_cfg->mestee) + value |= MESTEE; /* MTL EST ECC */ + if (safety_feat_cfg->mrxee) + value |= MRXEE; /* MTL RX FIFO ECC */ + if (safety_feat_cfg->mtxee) + value |= MTXEE; /* MTL TX FIFO ECC */ writel(value, ioaddr + MTL_ECC_CONTROL); /* 2. Enable MTL Safety Interrupts */ @@ -219,13 +225,16 @@ int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp) /* 5. Enable Parity and Timeout for FSM */ value = readl(ioaddr + MAC_FSM_CONTROL); - value |= PRTYEN; /* FSM Parity Feature */ - value |= TMOUTEN; /* FSM Timeout Feature */ + if (safety_feat_cfg->prtyen) + value |= PRTYEN; /* FSM Parity Feature */ + if (safety_feat_cfg->tmouten) + value |= TMOUTEN; /* FSM Timeout Feature */ writel(value, ioaddr + MAC_FSM_CONTROL); /* 4. Enable Data Parity Protection */ value = readl(ioaddr + MTL_DPP_CONTROL); - value |= EDPP; + if (safety_feat_cfg->edpp) + value |= EDPP; writel(value, ioaddr + MTL_DPP_CONTROL); /* @@ -235,7 +244,8 @@ int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp) if (asp <= 0x2) return 0; - value |= EPSI; + if (safety_feat_cfg->epsi) + value |= EPSI; writel(value, ioaddr + MTL_DPP_CONTROL); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h index 6b2fd37b29ad..53c138d0ff48 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h @@ -137,7 +137,8 @@ #define GMAC_INT_FPE_EN BIT(17) -int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp); +int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp, + struct stmmac_safety_feature_cfg *safety_cfg); int dwmac5_safety_feat_irq_status(struct net_device *ndev, void __iomem *ioaddr, unsigned int asp, struct stmmac_safety_stats *stats); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index ad4df9bddcf3..c4d78fa93663 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -801,7 +801,9 @@ static void dwxgmac3_handle_dma_err(struct net_device *ndev, dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats); } -static int dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp) +static int +dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp, + struct stmmac_safety_feature_cfg *safety_cfg) { u32 value; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 6d5e0f2b03ce..6dc1c98ebec8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -348,7 +348,8 @@ struct stmmac_ops { void (*pcs_rane)(void __iomem *ioaddr, bool restart); void (*pcs_get_adv_lp)(void __iomem *ioaddr, struct rgmii_adv *adv); /* Safety Features */ - int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp); + int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp, + struct stmmac_safety_feature_cfg *safety_cfg); int (*safety_feat_irq_status)(struct net_device *ndev, void __iomem *ioaddr, unsigned int asp, struct stmmac_safety_stats *stats); @@ -612,18 +613,6 @@ struct stmmac_mmc_ops { #define stmmac_mmc_read(__priv, __args...) \ stmmac_do_void_callback(__priv, mmc, read, __args) -/* XPCS callbacks */ -#define stmmac_xpcs_validate(__priv, __args...) \ - stmmac_do_callback(__priv, xpcs, validate, __args) -#define stmmac_xpcs_config(__priv, __args...) \ - stmmac_do_callback(__priv, xpcs, config, __args) -#define stmmac_xpcs_get_state(__priv, __args...) \ - stmmac_do_callback(__priv, xpcs, get_state, __args) -#define stmmac_xpcs_link_up(__priv, __args...) \ - stmmac_do_callback(__priv, xpcs, link_up, __args) -#define stmmac_xpcs_probe(__priv, __args...) \ - stmmac_do_callback(__priv, xpcs, probe, __args) - struct stmmac_regs_off { u32 ptp_off; u32 mmc_off; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index b6cd43eda7ac..e735134e8487 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -75,7 +75,7 @@ struct stmmac_tx_queue { unsigned int cur_tx; unsigned int dirty_tx; dma_addr_t dma_tx_phy; - u32 tx_tail_addr; + dma_addr_t tx_tail_addr; u32 mss; }; @@ -311,6 +311,7 @@ enum stmmac_state { int stmmac_mdio_unregister(struct net_device *ndev); int stmmac_mdio_register(struct net_device *ndev); int stmmac_mdio_reset(struct mii_bus *mii); +int stmmac_xpcs_setup(struct mii_bus *mii); void stmmac_set_ethtool_ops(struct net_device *netdev); void stmmac_ptp_register(struct stmmac_priv *priv); @@ -338,9 +339,9 @@ static inline bool stmmac_xdp_is_enabled(struct stmmac_priv *priv) static inline unsigned int stmmac_rx_offset(struct stmmac_priv *priv) { if (stmmac_xdp_is_enabled(priv)) - return XDP_PACKET_HEADROOM; + return XDP_PACKET_HEADROOM + NET_IP_ALIGN; - return 0; + return NET_SKB_PAD + NET_IP_ALIGN; } void stmmac_disable_rx_queue(struct stmmac_priv *priv, u32 queue); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 61b11639ee0c..d0ce608b81c3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -720,6 +720,14 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, netdev_warn(priv->dev, "Setting EEE tx-lpi is not supported\n"); + if (priv->hw->xpcs) { + ret = xpcs_config_eee(priv->hw->xpcs, + priv->plat->mult_fact_100ns, + edata->eee_enabled); + if (ret) + return ret; + } + if (!edata->eee_enabled) stmmac_disable_eee_mode(priv); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index c87202cbd3d6..8d9d6ecf8c63 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -931,6 +931,11 @@ static void stmmac_validate(struct phylink_config *config, if ((max_speed > 0) && (max_speed < 1000)) { phylink_set(mask, 1000baseT_Full); phylink_set(mask, 1000baseX_Full); + } else if (priv->plat->has_gmac4) { + if (!max_speed || max_speed >= 2500) { + phylink_set(mac_supported, 2500baseT_Full); + phylink_set(mac_supported, 2500baseX_Full); + } } else if (priv->plat->has_xgmac) { if (!max_speed || (max_speed >= 2500)) { phylink_set(mac_supported, 2500baseT_Full); @@ -996,29 +1001,14 @@ static void stmmac_validate(struct phylink_config *config, linkmode_andnot(state->advertising, state->advertising, mask); /* If PCS is supported, check which modes it supports. */ - stmmac_xpcs_validate(priv, &priv->hw->xpcs_args, supported, state); -} - -static void stmmac_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state) -{ - struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); - - state->link = 0; - stmmac_xpcs_get_state(priv, &priv->hw->xpcs_args, state); + if (priv->hw->xpcs) + xpcs_validate(priv->hw->xpcs, supported, state); } static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { - struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); - - stmmac_xpcs_config(priv, &priv->hw->xpcs_args, state); -} - -static void stmmac_mac_an_restart(struct phylink_config *config) -{ - /* Not Supported */ + /* Nothing to do, xpcs_config() handles everything */ } static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up) @@ -1031,8 +1021,8 @@ static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up) if (is_up && *hs_enable) { stmmac_fpe_send_mpacket(priv, priv->ioaddr, MPACKET_VERIFY); } else { - *lo_state = FPE_EVENT_UNKNOWN; - *lp_state = FPE_EVENT_UNKNOWN; + *lo_state = FPE_STATE_OFF; + *lp_state = FPE_STATE_OFF; } } @@ -1060,8 +1050,6 @@ static void stmmac_mac_link_up(struct phylink_config *config, struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); u32 ctrl; - stmmac_xpcs_link_up(priv, &priv->hw->xpcs_args, speed, interface); - ctrl = readl(priv->ioaddr + MAC_CTRL_REG); ctrl &= ~priv->hw->link.speed_mask; @@ -1154,9 +1142,7 @@ static void stmmac_mac_link_up(struct phylink_config *config, static const struct phylink_mac_ops stmmac_phylink_mac_ops = { .validate = stmmac_validate, - .mac_pcs_get_state = stmmac_mac_pcs_get_state, .mac_config = stmmac_mac_config, - .mac_an_restart = stmmac_mac_an_restart, .mac_link_down = stmmac_mac_link_down, .mac_link_up = stmmac_mac_link_up, }; @@ -1233,6 +1219,7 @@ static int stmmac_init_phy(struct net_device *dev) static int stmmac_phy_setup(struct stmmac_priv *priv) { + struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node); int mode = priv->plat->phy_interface; struct phylink *phylink; @@ -1242,7 +1229,7 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) priv->phylink_config.pcs_poll = true; if (priv->plat->mdio_bus_data) priv->phylink_config.ovr_an_inband = - priv->plat->mdio_bus_data->xpcs_an_inband; + mdio_bus_data->xpcs_an_inband; if (!fwnode) fwnode = dev_fwnode(priv->device); @@ -1252,6 +1239,9 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) if (IS_ERR(phylink)) return PTR_ERR(phylink); + if (priv->hw->xpcs) + phylink_set_pcs(phylink, &priv->hw->xpcs->pcs); + priv->phylink = phylink; return 0; } @@ -3173,7 +3163,8 @@ static void stmmac_safety_feat_configuration(struct stmmac_priv *priv) { if (priv->dma_cap.asp) { netdev_info(priv->dev, "Enabling Safety Features\n"); - stmmac_safety_feat_config(priv, priv->ioaddr, priv->dma_cap.asp); + stmmac_safety_feat_config(priv, priv->ioaddr, priv->dma_cap.asp, + priv->plat->safety_feat_cfg); } else { netdev_info(priv->dev, "No Safety Features support found\n"); } @@ -3415,8 +3406,8 @@ static void stmmac_free_irq(struct net_device *dev, static int stmmac_request_irq_multi_msi(struct net_device *dev) { - enum request_irq_err irq_err = REQ_IRQ_ERR_NO; struct stmmac_priv *priv = netdev_priv(dev); + enum request_irq_err irq_err; cpumask_t cpu_mask; int irq_idx = 0; char *int_name; @@ -3563,8 +3554,8 @@ irq_error: static int stmmac_request_irq_single(struct net_device *dev) { - enum request_irq_err irq_err = REQ_IRQ_ERR_NO; struct stmmac_priv *priv = netdev_priv(dev); + enum request_irq_err irq_err; int ret; ret = request_irq(dev->irq, stmmac_interrupt, @@ -3574,7 +3565,7 @@ static int stmmac_request_irq_single(struct net_device *dev) "%s: ERROR: allocating the IRQ %d (error: %d)\n", __func__, dev->irq, ret); irq_err = REQ_IRQ_ERR_MAC; - return ret; + goto irq_error; } /* Request the Wake IRQ in case of another line @@ -3588,7 +3579,7 @@ static int stmmac_request_irq_single(struct net_device *dev) "%s: ERROR: allocating the WoL IRQ %d (%d)\n", __func__, priv->wol_irq, ret); irq_err = REQ_IRQ_ERR_WOL; - return ret; + goto irq_error; } } @@ -3638,6 +3629,7 @@ static int stmmac_request_irq(struct net_device *dev) int stmmac_open(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + int mode = priv->plat->phy_interface; int bfsize = 0; u32 chan; int ret; @@ -3650,7 +3642,8 @@ int stmmac_open(struct net_device *dev) if (priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI && - priv->hw->xpcs_args.an_mode != DW_AN_C73) { + (!priv->hw->xpcs || + xpcs_get_an_mode(priv->hw->xpcs, mode) != DW_AN_C73)) { ret = stmmac_init_phy(dev); if (ret) { netdev_err(priv->dev, @@ -4658,7 +4651,6 @@ static int stmmac_xdp_xmit_back(struct stmmac_priv *priv, return res; } -/* This function assumes rcu_read_lock() is held by the caller. */ static int __stmmac_xdp_run_prog(struct stmmac_priv *priv, struct bpf_prog *prog, struct xdp_buff *xdp) @@ -4700,17 +4692,14 @@ static struct sk_buff *stmmac_xdp_run_prog(struct stmmac_priv *priv, struct bpf_prog *prog; int res; - rcu_read_lock(); - prog = READ_ONCE(priv->xdp_prog); if (!prog) { res = STMMAC_XDP_PASS; - goto unlock; + goto out; } res = __stmmac_xdp_run_prog(priv, prog, xdp); -unlock: - rcu_read_unlock(); +out: return ERR_PTR(-res); } @@ -4980,10 +4969,8 @@ read_again: buf->xdp->data_end = buf->xdp->data + buf1_len; xsk_buff_dma_sync_for_cpu(buf->xdp, rx_q->xsk_pool); - rcu_read_lock(); prog = READ_ONCE(priv->xdp_prog); res = __stmmac_xdp_run_prog(priv, prog, buf->xdp); - rcu_read_unlock(); switch (res) { case STMMAC_XDP_PASS: @@ -5138,7 +5125,7 @@ read_again: /* Buffer is good. Go on. */ - prefetch(page_address(buf->page)); + prefetch(page_address(buf->page) + buf->page_offset); if (buf->sec_page) prefetch(page_address(buf->sec_page)); @@ -5171,12 +5158,9 @@ read_again: dma_sync_single_for_cpu(priv->device, buf->addr, buf1_len, dma_dir); - xdp.data = page_address(buf->page) + buf->page_offset; - xdp.data_end = xdp.data + buf1_len; - xdp.data_hard_start = page_address(buf->page); - xdp_set_data_meta_invalid(&xdp); - xdp.frame_sz = buf_sz; - xdp.rxq = &rx_q->xdp_rxq; + xdp_init_buff(&xdp, buf_sz, &rx_q->xdp_rxq); + xdp_prepare_buff(&xdp, page_address(buf->page), + buf->page_offset, buf1_len, false); pre_len = xdp.data_end - xdp.data_hard_start - buf->page_offset; @@ -6545,7 +6529,8 @@ static int stmmac_hw_init(struct stmmac_priv *priv) * register (if supported). */ priv->plat->enh_desc = priv->dma_cap.enh_desc; - priv->plat->pmt = priv->dma_cap.pmt_remote_wake_up; + priv->plat->pmt = priv->dma_cap.pmt_remote_wake_up && + !priv->plat->use_phy_wol; priv->hw->pmt = priv->plat->pmt; if (priv->dma_cap.hash_tb_sz) { priv->hw->multicast_filter_bins = @@ -6854,6 +6839,11 @@ int stmmac_dvr_probe(struct device *device, reset_control_reset(priv->plat->stmmac_rst); } + ret = reset_control_deassert(priv->plat->stmmac_ahb_rst); + if (ret == -ENOTSUPP) + dev_err(priv->device, "unable to bring out of ahb reset: %pe\n", + ERR_PTR(ret)); + /* Init MAC and get the capabilities */ ret = stmmac_hw_init(priv); if (ret) @@ -7005,6 +6995,15 @@ int stmmac_dvr_probe(struct device *device, } } + if (priv->plat->speed_mode_2500) + priv->plat->speed_mode_2500(ndev, priv->plat->bsp_priv); + + if (priv->plat->mdio_bus_data && priv->plat->mdio_bus_data->has_xpcs) { + ret = stmmac_xpcs_setup(priv->mii); + if (ret) + goto error_xpcs_setup; + } + ret = stmmac_phy_setup(priv); if (ret) { netdev_err(ndev, "failed to setup phy (%d)\n", ret); @@ -7041,6 +7040,7 @@ error_serdes_powerup: unregister_netdev(ndev); error_netdev_register: phylink_destroy(priv->phylink); +error_xpcs_setup: error_phy_setup: if (priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI) @@ -7085,6 +7085,7 @@ int stmmac_dvr_remove(struct device *dev) phylink_destroy(priv->phylink); if (priv->plat->stmmac_rst) reset_control_assert(priv->plat->stmmac_rst); + reset_control_assert(priv->plat->stmmac_ahb_rst); pm_runtime_put(dev); pm_runtime_disable(dev); if (priv->hw->pcs != STMMAC_PCS_TBI && diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index b750074f8f9c..a5d150c5f3d8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -397,6 +397,41 @@ int stmmac_mdio_reset(struct mii_bus *bus) return 0; } +int stmmac_xpcs_setup(struct mii_bus *bus) +{ + struct net_device *ndev = bus->priv; + struct mdio_device *mdiodev; + struct stmmac_priv *priv; + struct dw_xpcs *xpcs; + int mode, addr; + + priv = netdev_priv(ndev); + mode = priv->plat->phy_interface; + + /* Try to probe the XPCS by scanning all addresses. */ + for (addr = 0; addr < PHY_MAX_ADDR; addr++) { + mdiodev = mdio_device_create(bus, addr); + if (IS_ERR(mdiodev)) + continue; + + xpcs = xpcs_create(mdiodev, mode); + if (IS_ERR_OR_NULL(xpcs)) { + mdio_device_free(mdiodev); + continue; + } + + priv->hw->xpcs = xpcs; + break; + } + + if (!priv->hw->xpcs) { + dev_warn(priv->device, "No xPCS found\n"); + return -ENODEV; + } + + return 0; +} + /** * stmmac_mdio_register * @ndev: net device structure @@ -444,14 +479,6 @@ int stmmac_mdio_register(struct net_device *ndev) max_addr = PHY_MAX_ADDR; } - if (mdio_bus_data->has_xpcs) { - priv->hw->xpcs = mdio_xpcs_get_ops(); - if (!priv->hw->xpcs) { - err = -ENODEV; - goto bus_register_fail; - } - } - if (mdio_bus_data->needs_reset) new_bus->reset = &stmmac_mdio_reset; @@ -503,30 +530,10 @@ int stmmac_mdio_register(struct net_device *ndev) found = 1; } - /* Try to probe the XPCS by scanning all addresses. */ - if (priv->hw->xpcs) { - struct mdio_xpcs_args *xpcs = &priv->hw->xpcs_args; - int ret, mode = priv->plat->phy_interface; - max_addr = PHY_MAX_ADDR; - - xpcs->bus = new_bus; - - for (addr = 0; addr < max_addr; addr++) { - xpcs->addr = addr; - - ret = stmmac_xpcs_probe(priv, xpcs, mode); - if (!ret) { - found = 1; - break; - } - } - } - if (!found && !mdio_node) { dev_warn(dev, "No PHY found\n"); - mdiobus_unregister(new_bus); - mdiobus_free(new_bus); - return -ENODEV; + err = -ENODEV; + goto no_phy_found; } bus_register_done: @@ -534,6 +541,8 @@ bus_register_done: return 0; +no_phy_found: + mdiobus_unregister(new_bus); bus_register_fail: mdiobus_free(new_bus); return err; @@ -551,6 +560,11 @@ int stmmac_mdio_unregister(struct net_device *ndev) if (!priv->mii) return 0; + if (priv->hw->xpcs) { + mdio_device_free(priv->hw->xpcs->mdiodev); + xpcs_destroy(priv->hw->xpcs); + } + mdiobus_unregister(priv->mii); priv->mii->priv = NULL; mdiobus_free(priv->mii); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 95e0e4d6f74d..fcf17d8a0494 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -174,6 +174,12 @@ static int stmmac_pci_probe(struct pci_dev *pdev, if (!plat->dma_cfg) return -ENOMEM; + plat->safety_feat_cfg = devm_kzalloc(&pdev->dev, + sizeof(*plat->safety_feat_cfg), + GFP_KERNEL); + if (!plat->safety_feat_cfg) + return -ENOMEM; + /* Enable pci device */ ret = pci_enable_device(pdev); if (ret) { @@ -203,6 +209,16 @@ static int stmmac_pci_probe(struct pci_dev *pdev, res.wol_irq = pdev->irq; res.irq = pdev->irq; + plat->safety_feat_cfg->tsoee = 1; + plat->safety_feat_cfg->mrxpee = 1; + plat->safety_feat_cfg->mestee = 1; + plat->safety_feat_cfg->mrxee = 1; + plat->safety_feat_cfg->mtxee = 1; + plat->safety_feat_cfg->epsi = 1; + plat->safety_feat_cfg->edpp = 1; + plat->safety_feat_cfg->prtyen = 1; + plat->safety_feat_cfg->tmouten = 1; + return stmmac_dvr_probe(&pdev->dev, plat, &res); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index a696ada013eb..072eff8079d0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -230,8 +230,6 @@ static int stmmac_mtl_setup(struct platform_device *pdev, plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WFQ; else if (of_property_read_bool(tx_node, "snps,tx-sched-dwrr")) plat->tx_sched_algorithm = MTL_TX_ALGORITHM_DWRR; - else if (of_property_read_bool(tx_node, "snps,tx-sched-sp")) - plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP; else plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP; @@ -602,6 +600,13 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) goto error_hw_init; } + plat->stmmac_ahb_rst = devm_reset_control_get_optional_shared( + &pdev->dev, "ahb"); + if (IS_ERR(plat->stmmac_ahb_rst)) { + ret = plat->stmmac_ahb_rst; + goto error_hw_init; + } + return plat; error_hw_init: diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 4e70efc45458..92dab609d4f8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -573,10 +573,8 @@ static int tc_add_flow(struct stmmac_priv *priv, for (i = 0; i < ARRAY_SIZE(tc_flow_parsers); i++) { ret = tc_flow_parsers[i].fn(priv, cls, entry); - if (!ret) { + if (!ret) entry->in_use = true; - continue; - } } if (!entry->in_use) diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 54f45d8c79a7..981685c88308 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -486,7 +486,7 @@ page_err: /* initialize spare pool of rx buffers, but allocate during the open */ static void cas_spare_init(struct cas *cp) { - spin_lock(&cp->rx_inuse_lock); + spin_lock(&cp->rx_inuse_lock); INIT_LIST_HEAD(&cp->rx_inuse_list); spin_unlock(&cp->rx_inuse_lock); diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c index 9790656cf970..cfb9e21b18b7 100644 --- a/drivers/net/ethernet/sun/sungem.c +++ b/drivers/net/ethernet/sun/sungem.c @@ -1258,8 +1258,8 @@ static void gem_begin_auto_negotiation(struct gem *gp, &advertising, ep->link_modes.advertising); if (gp->phy_type != phy_mii_mdio0 && - gp->phy_type != phy_mii_mdio1) - goto non_mii; + gp->phy_type != phy_mii_mdio1) + goto non_mii; /* Setup advertise */ if (found_mii_phy(gp)) @@ -1410,7 +1410,7 @@ static int gem_set_link_modes(struct gem *gp) if (gp->phy_type == phy_serialink || gp->phy_type == phy_serdes) { - u32 pcs_lpa = readl(gp->regs + PCS_MIILP); + u32 pcs_lpa = readl(gp->regs + PCS_MIILP); if (pcs_lpa & (PCS_MIIADV_SP | PCS_MIIADV_AP)) pause = 1; @@ -1892,7 +1892,7 @@ static void gem_init_mac(struct gem *gp) static void gem_init_pause_thresholds(struct gem *gp) { - u32 cfg; + u32 cfg; /* Calculate pause thresholds. Setting the OFF threshold to the * full RX fifo size effectively disables PAUSE generation which @@ -1914,15 +1914,15 @@ static void gem_init_pause_thresholds(struct gem *gp) /* Configure the chip "burst" DMA mode & enable some * HW bug fixes on Apple version */ - cfg = 0; - if (gp->pdev->vendor == PCI_VENDOR_ID_APPLE) + cfg = 0; + if (gp->pdev->vendor == PCI_VENDOR_ID_APPLE) cfg |= GREG_CFG_RONPAULBIT | GREG_CFG_ENBUG2FIX; #if !defined(CONFIG_SPARC64) && !defined(CONFIG_ALPHA) - cfg |= GREG_CFG_IBURST; + cfg |= GREG_CFG_IBURST; #endif - cfg |= ((31 << 1) & GREG_CFG_TXDMALIM); - cfg |= ((31 << 6) & GREG_CFG_RXDMALIM); - writel(cfg, gp->regs + GREG_CFG); + cfg |= ((31 << 1) & GREG_CFG_TXDMALIM); + cfg |= ((31 << 6) & GREG_CFG_RXDMALIM); + writel(cfg, gp->regs + GREG_CFG); /* If Infinite Burst didn't stick, then use different * thresholds (and Apple bug fixes don't exist) diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 54b53dbdb33c..a2c1a404c52d 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -2286,8 +2286,8 @@ static netdev_tx_t happy_meal_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct happy_meal *hp = netdev_priv(dev); - int entry; - u32 tx_flags; + int entry; + u32 tx_flags; tx_flags = TXFLAG_OWN; if (skb->ip_summed == CHECKSUM_PARTIAL) { @@ -2301,7 +2301,7 @@ static netdev_tx_t happy_meal_start_xmit(struct sk_buff *skb, spin_lock_irq(&hp->happy_lock); - if (TX_BUFFS_AVAIL(hp) <= (skb_shinfo(skb)->nr_frags + 1)) { + if (TX_BUFFS_AVAIL(hp) <= (skb_shinfo(skb)->nr_frags + 1)) { netif_stop_queue(dev); spin_unlock_irq(&hp->happy_lock); printk(KERN_ERR "%s: BUG! Tx Ring full when queue awake!\n", diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 6a67b026df0b..718539cdd2f2 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1506,12 +1506,12 @@ static void am65_cpsw_nuss_free_tx_chns(void *data) for (i = 0; i < common->tx_ch_num; i++) { struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i]; - if (!IS_ERR_OR_NULL(tx_chn->tx_chn)) - k3_udma_glue_release_tx_chn(tx_chn->tx_chn); - if (!IS_ERR_OR_NULL(tx_chn->desc_pool)) k3_cppi_desc_pool_destroy(tx_chn->desc_pool); + if (!IS_ERR_OR_NULL(tx_chn->tx_chn)) + k3_udma_glue_release_tx_chn(tx_chn->tx_chn); + memset(tx_chn, 0, sizeof(*tx_chn)); } } @@ -1531,12 +1531,12 @@ void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common) netif_napi_del(&tx_chn->napi_tx); - if (!IS_ERR_OR_NULL(tx_chn->tx_chn)) - k3_udma_glue_release_tx_chn(tx_chn->tx_chn); - if (!IS_ERR_OR_NULL(tx_chn->desc_pool)) k3_cppi_desc_pool_destroy(tx_chn->desc_pool); + if (!IS_ERR_OR_NULL(tx_chn->tx_chn)) + k3_udma_glue_release_tx_chn(tx_chn->tx_chn); + memset(tx_chn, 0, sizeof(*tx_chn)); } } @@ -1624,11 +1624,11 @@ static void am65_cpsw_nuss_free_rx_chns(void *data) rx_chn = &common->rx_chns; - if (!IS_ERR_OR_NULL(rx_chn->rx_chn)) - k3_udma_glue_release_rx_chn(rx_chn->rx_chn); - if (!IS_ERR_OR_NULL(rx_chn->desc_pool)) k3_cppi_desc_pool_destroy(rx_chn->desc_pool); + + if (!IS_ERR_OR_NULL(rx_chn->rx_chn)) + k3_udma_glue_release_rx_chn(rx_chn->rx_chn); } static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) diff --git a/drivers/net/ethernet/ti/am65-cpsw-switchdev.c b/drivers/net/ethernet/ti/am65-cpsw-switchdev.c index 23cfb91e9c4d..9c29b363e9ae 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-switchdev.c +++ b/drivers/net/ethernet/ti/am65-cpsw-switchdev.c @@ -84,7 +84,7 @@ static int am65_cpsw_port_attr_br_flags_pre_set(struct net_device *netdev, return 0; } -static int am65_cpsw_port_attr_set(struct net_device *ndev, +static int am65_cpsw_port_attr_set(struct net_device *ndev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { @@ -302,7 +302,7 @@ static int am65_cpsw_port_mdb_del(struct am65_cpsw_port *port, return 0; } -static int am65_cpsw_port_obj_add(struct net_device *ndev, +static int am65_cpsw_port_obj_add(struct net_device *ndev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { @@ -329,7 +329,7 @@ static int am65_cpsw_port_obj_add(struct net_device *ndev, return err; } -static int am65_cpsw_port_obj_del(struct net_device *ndev, +static int am65_cpsw_port_obj_del(struct net_device *ndev, const void *ctx, const struct switchdev_obj *obj) { struct switchdev_obj_port_vlan *vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index 9caaae79fc95..c30a6e510aa3 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -1037,11 +1037,9 @@ static int am65_cpts_probe(struct platform_device *pdev) struct device_node *node = pdev->dev.of_node; struct device *dev = &pdev->dev; struct am65_cpts *cpts; - struct resource *res; void __iomem *base; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cpts"); - base = devm_ioremap_resource(dev, res); + base = devm_platform_ioremap_resource_byname(pdev, "cpts"); if (IS_ERR(base)) return PTR_ERR(base); diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c index 6e72ecbe5cf7..e8f38e3f7706 100644 --- a/drivers/net/ethernet/ti/cpsw-phy-sel.c +++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c @@ -206,7 +206,6 @@ static const struct of_device_id cpsw_phy_sel_id_table[] = { static int cpsw_phy_sel_probe(struct platform_device *pdev) { - struct resource *res; const struct of_device_id *of_id; struct cpsw_phy_sel_priv *priv; @@ -223,8 +222,7 @@ static int cpsw_phy_sel_probe(struct platform_device *pdev) priv->dev = &pdev->dev; priv->cpsw_phy_sel = of_id->data; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "gmii-sel"); - priv->gmii_sel = devm_ioremap_resource(&pdev->dev, res); + priv->gmii_sel = devm_platform_ioremap_resource_byname(pdev, "gmii-sel"); if (IS_ERR(priv->gmii_sel)) return PTR_ERR(priv->gmii_sel); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index c0cd7de88316..cbbd0f665796 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -430,8 +430,8 @@ static void cpsw_rx_handler(void *token, int len, int status) cpts_rx_timestamp(cpsw->cpts, skb); skb->protocol = eth_type_trans(skb, ndev); - /* unmap page as no netstack skb page recycling */ - page_pool_release_page(pool, page); + /* mark skb for recycling */ + skb_mark_for_recycle(skb, page, pool); netif_receive_skb(skb); ndev->stats.rx_bytes += len; @@ -1532,8 +1532,7 @@ static int cpsw_probe(struct platform_device *pdev) } cpsw->bus_freq_mhz = clk_get_rate(clk) / 1000000; - ss_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ss_regs = devm_ioremap_resource(dev, ss_res); + ss_regs = devm_platform_get_and_ioremap_resource(pdev, 0, &ss_res); if (IS_ERR(ss_regs)) return PTR_ERR(ss_regs); cpsw->regs = ss_regs; diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index d828f856237a..0c75e0576ee1 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -70,7 +70,7 @@ enum { }; /** - * struct ale_dev_id - The ALE version/SoC specific configuration + * struct cpsw_ale_dev_id - The ALE version/SoC specific configuration * @dev_id: ALE version/SoC id * @features: features supported by ALE * @tbl_entries: number of ALE entries diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 69b7a4e0220a..57d279fdcc9f 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -373,8 +373,8 @@ static void cpsw_rx_handler(void *token, int len, int status) cpts_rx_timestamp(cpsw->cpts, skb); skb->protocol = eth_type_trans(skb, ndev); - /* unmap page as no netstack skb page recycling */ - page_pool_release_page(pool, page); + /* mark skb for recycling */ + skb_mark_for_recycle(skb, page, pool); netif_receive_skb(skb); ndev->stats.rx_bytes += len; @@ -1883,8 +1883,7 @@ static int cpsw_probe(struct platform_device *pdev) } cpsw->bus_freq_mhz = clk_get_rate(clk) / 1000000; - ss_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ss_regs = devm_ioremap_resource(dev, ss_res); + ss_regs = devm_platform_get_and_ioremap_resource(pdev, 0, &ss_res); if (IS_ERR(ss_regs)) { ret = PTR_ERR(ss_regs); return ret; diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index 5862f0a4a975..ecc2a6b7e28f 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -1328,13 +1328,9 @@ int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp, struct bpf_prog *prog; u32 act; - rcu_read_lock(); - prog = READ_ONCE(priv->xdp_prog); - if (!prog) { - ret = CPSW_XDP_PASS; - goto out; - } + if (!prog) + return CPSW_XDP_PASS; act = bpf_prog_run_xdp(prog, xdp); /* XDP prog might have changed packet data and boundaries */ @@ -1378,10 +1374,8 @@ int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp, ndev->stats.rx_bytes += *len; ndev->stats.rx_packets++; out: - rcu_read_unlock(); return ret; drop: - rcu_read_unlock(); page_pool_recycle_direct(cpsw->page_pool[ch], page); return ret; } diff --git a/drivers/net/ethernet/ti/cpsw_switchdev.c b/drivers/net/ethernet/ti/cpsw_switchdev.c index 05a64fb7a04f..f7fb6e17dadd 100644 --- a/drivers/net/ethernet/ti/cpsw_switchdev.c +++ b/drivers/net/ethernet/ti/cpsw_switchdev.c @@ -86,7 +86,7 @@ static int cpsw_port_attr_br_flags_pre_set(struct net_device *netdev, return 0; } -static int cpsw_port_attr_set(struct net_device *ndev, +static int cpsw_port_attr_set(struct net_device *ndev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { @@ -310,7 +310,7 @@ static int cpsw_port_mdb_del(struct cpsw_priv *priv, return err; } -static int cpsw_port_obj_add(struct net_device *ndev, +static int cpsw_port_obj_add(struct net_device *ndev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { @@ -338,7 +338,7 @@ static int cpsw_port_obj_add(struct net_device *ndev, return err; } -static int cpsw_port_obj_del(struct net_device *ndev, +static int cpsw_port_obj_del(struct net_device *ndev, const void *ctx, const struct switchdev_obj *obj) { struct switchdev_obj_port_vlan *vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index f9417b44cae8..c674e34b6839 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1814,13 +1814,12 @@ static int davinci_emac_probe(struct platform_device *pdev) priv->bus_freq_mhz = (u32)(emac_bus_frequency / 1000000); /* Get EMAC platform data */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->emac_base_phys = res->start + pdata->ctrl_reg_offset; - priv->remap_addr = devm_ioremap_resource(&pdev->dev, res); + priv->remap_addr = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(priv->remap_addr)) { rc = PTR_ERR(priv->remap_addr); goto no_pdata; } + priv->emac_base_phys = res->start + pdata->ctrl_reg_offset; res_ctrl = platform_get_resource(pdev, IORESOURCE_MEM, 1); if (res_ctrl) { diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index fecc4d7b00b0..88426b5e410b 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -1897,7 +1897,7 @@ static void velocity_error(struct velocity_info *vptr, int status) } /** - * tx_srv - transmit interrupt service + * velocity_tx_srv - transmit interrupt service * @vptr: Velocity * * Scan the queues looking for transmitted packets that @@ -2453,7 +2453,7 @@ static int velocity_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) } /** - * velocity_get_status - statistics callback + * velocity_get_stats - statistics callback * @dev: network device * * Callback from the network layer to allow driver statistics @@ -3723,7 +3723,7 @@ static int __init velocity_init_module(void) } /** - * velocity_cleanup - module unload + * velocity_cleanup_module - module unload * * When the velocity hardware is unloaded this function is called. * It will clean up the notifiers and the unregister the PCI diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c index ec5db481c9cd..811815f8cd3b 100644 --- a/drivers/net/ethernet/wiznet/w5100.c +++ b/drivers/net/ethernet/wiznet/w5100.c @@ -263,19 +263,14 @@ static int w5100_writebulk_direct(struct net_device *ndev, u32 addr, static int w5100_mmio_init(struct net_device *ndev) { struct platform_device *pdev = to_platform_device(ndev->dev.parent); - struct w5100_priv *priv = netdev_priv(ndev); struct w5100_mmio_priv *mmio_priv = w5100_mmio_priv(ndev); - struct resource *mem; spin_lock_init(&mmio_priv->reg_lock); - mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - mmio_priv->base = devm_ioremap_resource(&pdev->dev, mem); + mmio_priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(mmio_priv->base)) return PTR_ERR(mmio_priv->base); - netdev_info(ndev, "at 0x%llx irq %d\n", (u64)mem->start, priv->irq); - return 0; } diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 9a13953ea70f..60a4f79b8fa1 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -942,10 +942,8 @@ temac_start_xmit(struct sk_buff *skb, struct net_device *ndev) wmb(); lp->dma_out(lp, TX_TAILDESC_PTR, tail_p); /* DMA start */ - if (temac_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1)) { - netdev_info(ndev, "%s -> netif_stop_queue\n", __func__); + if (temac_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1)) netif_stop_queue(ndev); - } return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index b508c9453f40..13cd799541aa 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1543,6 +1543,7 @@ static void axienet_validate(struct phylink_config *config, case PHY_INTERFACE_MODE_MII: phylink_set(mask, 100baseT_Full); phylink_set(mask, 10baseT_Full); + fallthrough; default: break; } @@ -1893,8 +1894,7 @@ static int axienet_probe(struct platform_device *pdev) goto cleanup_clk; /* Map device registers */ - ethres = platform_get_resource(pdev, IORESOURCE_MEM, 0); - lp->regs = devm_ioremap_resource(&pdev->dev, ethres); + lp->regs = devm_platform_get_and_ioremap_resource(pdev, 0, ðres); if (IS_ERR(lp->regs)) { ret = PTR_ERR(lp->regs); goto cleanup_clk; @@ -2009,9 +2009,7 @@ static int axienet_probe(struct platform_device *pdev) lp->eth_irq = platform_get_irq_optional(pdev, 0); } else { /* Check for these resources directly on the Ethernet node. */ - struct resource *res = platform_get_resource(pdev, - IORESOURCE_MEM, 1); - lp->dma_regs = devm_ioremap_resource(&pdev->dev, res); + lp->dma_regs = devm_platform_get_and_ioremap_resource(pdev, 1, NULL); lp->rx_irq = platform_get_irq(pdev, 1); lp->tx_irq = platform_get_irq(pdev, 0); lp->eth_irq = platform_get_irq_optional(pdev, 2); diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index d9d58a7dabee..b06377fe7293 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -1189,9 +1189,8 @@ static int xemaclite_of_probe(struct platform_device *ofdev) } dev_info(dev, - "Xilinx EmacLite at 0x%08lX mapped to 0x%08lX, irq=%d\n", - (unsigned long __force)ndev->mem_start, - (unsigned long __force)lp->base_addr, ndev->irq); + "Xilinx EmacLite at 0x%08lX mapped to 0x%p, irq=%d\n", + (unsigned long __force)ndev->mem_start, lp->base_addr, ndev->irq); return 0; error: diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c index 2049d76a0e68..4f6db6f5c272 100644 --- a/drivers/net/ethernet/xircom/xirc2ps_cs.c +++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c @@ -1232,7 +1232,7 @@ do_start_xmit(struct sk_buff *skb, struct net_device *dev) if (pktlen < ETH_ZLEN) { if (skb_padto(skb, ETH_ZLEN)) - return NETDEV_TX_OK; + return NETDEV_TX_OK; pktlen = ETH_ZLEN; } diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c index cb89323855d8..85c66af9e56d 100644 --- a/drivers/net/ethernet/xscale/ixp4xx_eth.c +++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c @@ -1425,7 +1425,6 @@ static int ixp4xx_eth_probe(struct platform_device *pdev) struct device_node *np = dev->of_node; struct eth_plat_info *plat; struct net_device *ndev; - struct resource *res; struct port *port; int err; @@ -1482,10 +1481,7 @@ static int ixp4xx_eth_probe(struct platform_device *pdev) port->id = plat->npe; /* Get the port resource and remap */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENODEV; - port->regs = devm_ioremap_resource(dev, res); + port->regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(port->regs)) return PTR_ERR(port->regs); @@ -1531,8 +1527,8 @@ static int ixp4xx_eth_probe(struct platform_device *pdev) phydev = of_phy_get_and_connect(ndev, np, ixp4xx_adjust_link); } else { phydev = mdiobus_get_phy(mdio_bus, plat->phy); - if (IS_ERR(phydev)) { - err = PTR_ERR(phydev); + if (!phydev) { + err = -ENODEV; dev_err(dev, "could not connect phydev (%d)\n", err); goto err_free_mem; } diff --git a/drivers/net/fddi/skfp/ess.c b/drivers/net/fddi/skfp/ess.c index 35110c0c00a0..41107338f0c0 100644 --- a/drivers/net/fddi/skfp/ess.c +++ b/drivers/net/fddi/skfp/ess.c @@ -379,17 +379,17 @@ static int process_bw_alloc(struct s_smc *smc, long int payload, long int overhe * if the payload is greater than zero. * For the SBAPayload and the SBAOverhead we have the following * unite quations - * _ _ + * _ _ * | bytes | * SBAPayload = | 8000 ------ | * | s | * - - - * _ _ + * _ _ * | bytes | * SBAOverhead = | ------ | * | T-NEG | * - - - * + * * T-NEG is described by the equation: * * (-) fddiMACT-NEG diff --git a/drivers/net/fddi/skfp/h/supern_2.h b/drivers/net/fddi/skfp/h/supern_2.h index 78ae8ea4007c..0bbbd411d000 100644 --- a/drivers/net/fddi/skfp/h/supern_2.h +++ b/drivers/net/fddi/skfp/h/supern_2.h @@ -1025,7 +1025,7 @@ struct tx_queue { #define PLC_QELM_A_BIST 0x5b6b /* BIST signature of QELM Rev. A */ /* - FDDI board recources + FDDI board recources */ /* diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c index 466622664424..185c8a398681 100644 --- a/drivers/net/fjes/fjes_main.c +++ b/drivers/net/fjes/fjes_main.c @@ -90,16 +90,8 @@ static struct platform_driver fjes_driver = { }; static struct resource fjes_resource[] = { - { - .flags = IORESOURCE_MEM, - .start = 0, - .end = 0, - }, - { - .flags = IORESOURCE_IRQ, - .start = 0, - .end = 0, - }, + DEFINE_RES_MEM(0, 1), + DEFINE_RES_IRQ(0) }; static bool is_extended_socket_device(struct acpi_device *device) @@ -1262,6 +1254,10 @@ static int fjes_probe(struct platform_device *plat_dev) adapter->interrupt_watch_enable = false; res = platform_get_resource(plat_dev, IORESOURCE_MEM, 0); + if (!res) { + err = -EINVAL; + goto err_free_control_wq; + } hw->hw_res.start = res->start; hw->hw_res.size = resource_size(res); hw->hw_res.irq = platform_get_irq(plat_dev, 0); diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 39c00f050fbd..30e0a10595a1 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -201,6 +201,7 @@ static int gtp_rx(struct pdp_ctx *pctx, struct sk_buff *skb, * calculate the transport header. */ skb_reset_network_header(skb); + skb_reset_mac_header(skb); skb->dev = pctx->dev; @@ -436,7 +437,7 @@ static inline void gtp1_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) gtp1->length = htons(payload_len); gtp1->tid = htonl(pctx->u.v1.o_tei); - /* TODO: Suppport for extension header, sequence number and N-PDU. + /* TODO: Support for extension header, sequence number and N-PDU. * Update the length field if any of them is available. */ } diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 80f41945709f..a15cc5e50290 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -716,11 +716,11 @@ static int sixpack_ioctl(struct tty_struct *tty, struct file *file, err = 0; break; - case SIOCSIFHWADDR: { - char addr[AX25_ADDR_LEN]; + case SIOCSIFHWADDR: { + char addr[AX25_ADDR_LEN]; - if (copy_from_user(&addr, - (void __user *) arg, AX25_ADDR_LEN)) { + if (copy_from_user(&addr, + (void __user *)arg, AX25_ADDR_LEN)) { err = -EFAULT; break; } @@ -728,11 +728,9 @@ static int sixpack_ioctl(struct tty_struct *tty, struct file *file, netif_tx_lock_bh(dev); memcpy(dev->dev_addr, &addr, AX25_ADDR_LEN); netif_tx_unlock_bh(dev); - err = 0; break; } - default: err = tty_mode_ioctl(tty, file, cmd, arg); } diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index e4e4981ac1d2..4435a1195194 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -231,7 +231,7 @@ struct baycom_state { #if 0 static inline void append_crc_ccitt(unsigned char *buffer, int len) { - unsigned int crc = 0xffff; + unsigned int crc = 0xffff; for (;len>0;len--) crc = (crc >> 8) ^ crc_ccitt_table[(crc ^ *buffer++) & 0xff]; @@ -390,7 +390,7 @@ static void encode_hdlc(struct baycom_state *bc) for (j = 0; j < 8; j++) if (unlikely(!(notbitstream & (0x1f0 << j)))) { bitstream &= ~(0x100 << j); - bitbuf = (bitbuf & (((2 << j) << numbit) - 1)) | + bitbuf = (bitbuf & (((2 << j) << numbit) - 1)) | ((bitbuf & ~(((2 << j) << numbit) - 1)) << 1); numbit++; notbitstream = ~bitstream; diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index 1ad6085994b1..0e623c2e8b2d 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -368,7 +368,7 @@ static int bpq_close(struct net_device *dev) /* ------------------------------------------------------------------------ */ - +#ifdef CONFIG_PROC_FS /* * Proc filesystem */ @@ -440,7 +440,7 @@ static const struct seq_operations bpq_seqops = { .stop = bpq_seq_stop, .show = bpq_seq_show, }; - +#endif /* ------------------------------------------------------------------------ */ static const struct net_device_ops bpq_netdev_ops = { diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c index 9e0058154ac3..cbaf1cdde7cb 100644 --- a/drivers/net/hamradio/hdlcdrv.c +++ b/drivers/net/hamradio/hdlcdrv.c @@ -74,7 +74,7 @@ static inline void append_crc_ccitt(unsigned char *buffer, int len) { - unsigned int crc = crc_ccitt(0xffff, buffer, len) ^ 0xffff; + unsigned int crc = crc_ccitt(0xffff, buffer, len) ^ 0xffff; buffer += len; *buffer++ = crc; *buffer++ = crc >> 8; diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 7685a1721597..b99128669bc8 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -276,7 +276,7 @@ static void ax_bump(struct mkiss *ax) */ *ax->rbuff &= ~0x20; } - } + } count = ax->rcount; @@ -501,7 +501,7 @@ static void ax_encaps(struct net_device *dev, unsigned char *icp, int len) default: count = kiss_esc(p, ax->xbuff, len); } - } + } spin_unlock_bh(&ax->buflock); set_bit(TTY_DO_WRITE_WAKEUP, &ax->tty->flags); @@ -816,7 +816,7 @@ static int mkiss_ioctl(struct tty_struct *tty, struct file *file, dev = ax->dev; switch (cmd) { - case SIOCGIFNAME: + case SIOCGIFNAME: err = copy_to_user((void __user *) arg, ax->dev->name, strlen(ax->dev->name) + 1) ? -EFAULT : 0; break; diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c index 4690c6a59054..3f1edd0526a4 100644 --- a/drivers/net/hamradio/scc.c +++ b/drivers/net/hamradio/scc.c @@ -1192,18 +1192,18 @@ static void t_tail(struct timer_list *t) unsigned long flags; spin_lock_irqsave(&scc->lock, flags); - del_timer(&scc->tx_wdog); - scc_key_trx(scc, TX_OFF); + del_timer(&scc->tx_wdog); + scc_key_trx(scc, TX_OFF); spin_unlock_irqrestore(&scc->lock, flags); - if (scc->stat.tx_state == TXS_TIMEOUT) /* we had a timeout? */ - { - scc->stat.tx_state = TXS_WAIT; + if (scc->stat.tx_state == TXS_TIMEOUT) /* we had a timeout? */ + { + scc->stat.tx_state = TXS_WAIT; scc_start_tx_timer(scc, t_dwait, scc->kiss.mintime*100); - return; - } - - scc->stat.tx_state = TXS_IDLE; + return; + } + + scc->stat.tx_state = TXS_IDLE; netif_wake_queue(scc->dev); } @@ -1580,7 +1580,7 @@ static int scc_net_open(struct net_device *dev) { struct scc_channel *scc = (struct scc_channel *) dev->ml_priv; - if (!scc->init) + if (!scc->init) return -EINVAL; scc->tx_buff = NULL; diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c index 5ab53e9942f3..d4911041596c 100644 --- a/drivers/net/hamradio/yam.c +++ b/drivers/net/hamradio/yam.c @@ -668,7 +668,7 @@ static void yam_tx_byte(struct net_device *dev, struct yam_port *yp) } yp->tx_len = skb->len - 1; /* strip KISS byte */ if (yp->tx_len >= YAM_MAX_FRAME || yp->tx_len < 2) { - dev_kfree_skb_any(skb); + dev_kfree_skb_any(skb); break; } skb_copy_from_linear_data_offset(skb, 1, diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 442c520ab8f3..bc48855dff10 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -895,9 +895,16 @@ static inline u32 netvsc_rqstor_size(unsigned long ringbytes) ringbytes / NETVSC_MIN_IN_MSG_SIZE; } +/* XFER PAGE packets can specify a maximum of 375 ranges for NDIS >= 6.0 + * and a maximum of 64 ranges for NDIS < 6.0 with no RSC; with RSC, this + * limit is raised to 562 (= NVSP_RSC_MAX). + */ +#define NETVSC_MAX_XFER_PAGE_RANGES NVSP_RSC_MAX #define NETVSC_XFER_HEADER_SIZE(rng_cnt) \ (offsetof(struct vmtransfer_page_packet_header, ranges) + \ (rng_cnt) * sizeof(struct vmtransfer_page_range)) +#define NETVSC_MAX_PKT_SIZE (NETVSC_XFER_HEADER_SIZE(NETVSC_MAX_XFER_PAGE_RANGES) + \ + sizeof(struct nvsp_message) + (sizeof(u32) * VRSS_SEND_TAB_SIZE)) struct multi_send_data { struct sk_buff *skb; /* skb containing the pkt */ @@ -1163,6 +1170,7 @@ struct rndis_set_request { u32 info_buflen; u32 info_buf_offset; u32 dev_vc_handle; + u8 info_buf[]; }; /* Response to NdisSetRequest */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 9d07c9ce4be2..7bd935412853 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -757,7 +757,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev, int queue_sends; u64 cmd_rqst; - cmd_rqst = vmbus_request_addr(&channel->requestor, (u64)desc->trans_id); + cmd_rqst = channel->request_addr_callback(channel, (u64)desc->trans_id); if (cmd_rqst == VMBUS_RQST_ERROR) { netdev_err(ndev, "Incorrect transaction id\n"); return; @@ -817,8 +817,8 @@ static void netvsc_send_completion(struct net_device *ndev, /* First check if this is a VMBUS completion without data payload */ if (!msglen) { - cmd_rqst = vmbus_request_addr(&incoming_channel->requestor, - (u64)desc->trans_id); + cmd_rqst = incoming_channel->request_addr_callback(incoming_channel, + (u64)desc->trans_id); if (cmd_rqst == VMBUS_RQST_ERROR) { netdev_err(ndev, "Invalid transaction id\n"); return; @@ -1649,7 +1649,11 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, netvsc_poll, NAPI_POLL_WEIGHT); /* Open the channel */ + device->channel->next_request_id_callback = vmbus_next_request_id; + device->channel->request_addr_callback = vmbus_request_addr; device->channel->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes); + device->channel->max_pkt_size = NETVSC_MAX_PKT_SIZE; + ret = vmbus_open(device->channel, netvsc_ring_bytes, netvsc_ring_bytes, NULL, 0, netvsc_channel_cb, net_device->chan_table); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index f682a5572d84..382bebc2420d 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2384,6 +2384,9 @@ static int netvsc_register_vf(struct net_device *vf_netdev) dev_hold(vf_netdev); rcu_assign_pointer(net_device_ctx->vf_netdev, vf_netdev); + if (ndev->needed_headroom < vf_netdev->needed_headroom) + ndev->needed_headroom = vf_netdev->needed_headroom; + vf_netdev->wanted_features = ndev->features; netdev_update_features(vf_netdev); @@ -2462,6 +2465,8 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev) RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL); dev_put(vf_netdev); + ndev->needed_headroom = RNDIS_AND_PPI_SIZE; + return NOTIFY_OK; } diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index c0e89e107d57..f6c9c2a670f9 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1051,10 +1051,8 @@ static int rndis_filter_set_packet_filter(struct rndis_device *dev, set = &request->request_msg.msg.set_req; set->oid = RNDIS_OID_GEN_CURRENT_PACKET_FILTER; set->info_buflen = sizeof(u32); - set->info_buf_offset = sizeof(struct rndis_set_request); - - memcpy((void *)(unsigned long)set + sizeof(struct rndis_set_request), - &new_filter, sizeof(u32)); + set->info_buf_offset = offsetof(typeof(*set), info_buf); + memcpy(set->info_buf, &new_filter, sizeof(u32)); ret = rndis_filter_send_request(dev, request); if (ret == 0) { @@ -1259,7 +1257,11 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc) /* Set the channel before opening.*/ nvchan->channel = new_sc; + new_sc->next_request_id_callback = vmbus_next_request_id; + new_sc->request_addr_callback = vmbus_request_addr; new_sc->rqstor_size = netvsc_rqstor_size(netvsc_ring_bytes); + new_sc->max_pkt_size = NETVSC_MAX_PKT_SIZE; + ret = vmbus_open(new_sc, netvsc_ring_bytes, netvsc_ring_bytes, NULL, 0, netvsc_channel_cb, nvchan); diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index da9135231c07..ebc976b7fcc2 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -480,7 +480,7 @@ static int hwsim_del_edge_nl(struct sk_buff *msg, struct genl_info *info) struct hwsim_edge *e; u32 v0, v1; - if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] && + if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] || !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE]) return -EINVAL; @@ -715,6 +715,8 @@ static int hwsim_subscribe_all_others(struct hwsim_phy *phy) return 0; +sub_fail: + hwsim_edge_unsubscribe_me(phy); me_fail: rcu_read_lock(); list_for_each_entry_rcu(e, &phy->edges, list) { @@ -722,8 +724,6 @@ me_fail: hwsim_free_edge(e); } rcu_read_unlock(); -sub_fail: - hwsim_edge_unsubscribe_me(phy); return -ENOMEM; } @@ -824,12 +824,17 @@ err_pib: static void hwsim_del(struct hwsim_phy *phy) { struct hwsim_pib *pib; + struct hwsim_edge *e; hwsim_edge_unsubscribe_me(phy); list_del(&phy->list); rcu_read_lock(); + list_for_each_entry_rcu(e, &phy->edges, list) { + list_del_rcu(&e->list); + hwsim_free_edge(e); + } pib = rcu_dereference(phy->pib); rcu_read_unlock(); diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index ab7022582154..e9258a9f3702 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -16,10 +16,10 @@ by Patrick McHardy and then maintained by Andre Correa. You need the tc action mirror or redirect to feed this device - packets. + packets. - Authors: Jamal Hadi Salim (2005) + Authors: Jamal Hadi Salim (2005) */ diff --git a/drivers/net/ipa/Makefile b/drivers/net/ipa/Makefile index 1efe1a88104b..506f8d5cd4ee 100644 --- a/drivers/net/ipa/Makefile +++ b/drivers/net/ipa/Makefile @@ -7,8 +7,9 @@ ipa-y := ipa_main.o ipa_clock.o ipa_reg.o ipa_mem.o \ ipa_table.o ipa_interrupt.o gsi.o gsi_trans.o \ ipa_gsi.o ipa_smp2p.o ipa_uc.o \ ipa_endpoint.o ipa_cmd.o ipa_modem.o \ - ipa_resource.o ipa_qmi.o ipa_qmi_msg.o + ipa_resource.o ipa_qmi.o ipa_qmi_msg.o \ + ipa_sysfs.o -ipa-y += ipa_data-v3.5.1.o ipa_data-v4.2.o \ - ipa_data-v4.5.o ipa_data-v4.9.o \ - ipa_data-v4.11.o +ipa-y += ipa_data-v3.1.o ipa_data-v3.5.1.o \ + ipa_data-v4.2.o ipa_data-v4.5.o \ + ipa_data-v4.9.o ipa_data-v4.11.o diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index e374079603cf..427c68b2ad8f 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -210,13 +210,65 @@ static void gsi_irq_setup(struct gsi *gsi) iowrite32(0, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET); iowrite32(0, gsi->virt + GSI_CNTXT_SRC_IEOB_IRQ_MSK_OFFSET); - /* The inter-EE registers are in the non-adjusted address range */ - iowrite32(0, gsi->virt_raw + GSI_INTER_EE_SRC_CH_IRQ_MSK_OFFSET); - iowrite32(0, gsi->virt_raw + GSI_INTER_EE_SRC_EV_CH_IRQ_MSK_OFFSET); + /* The inter-EE interrupts are not supported for IPA v3.0-v3.1 */ + if (gsi->version > IPA_VERSION_3_1) { + u32 offset; + + /* These registers are in the non-adjusted address range */ + offset = GSI_INTER_EE_SRC_CH_IRQ_MSK_OFFSET; + iowrite32(0, gsi->virt_raw + offset); + offset = GSI_INTER_EE_SRC_EV_CH_IRQ_MSK_OFFSET; + iowrite32(0, gsi->virt_raw + offset); + } iowrite32(0, gsi->virt + GSI_CNTXT_GSI_IRQ_EN_OFFSET); } +/* Get # supported channel and event rings; there is no gsi_ring_teardown() */ +static int gsi_ring_setup(struct gsi *gsi) +{ + struct device *dev = gsi->dev; + u32 count; + u32 val; + + if (gsi->version < IPA_VERSION_3_5_1) { + /* No HW_PARAM_2 register prior to IPA v3.5.1, assume the max */ + gsi->channel_count = GSI_CHANNEL_COUNT_MAX; + gsi->evt_ring_count = GSI_EVT_RING_COUNT_MAX; + + return 0; + } + + val = ioread32(gsi->virt + GSI_GSI_HW_PARAM_2_OFFSET); + + count = u32_get_bits(val, NUM_CH_PER_EE_FMASK); + if (!count) { + dev_err(dev, "GSI reports zero channels supported\n"); + return -EINVAL; + } + if (count > GSI_CHANNEL_COUNT_MAX) { + dev_warn(dev, "limiting to %u channels; hardware supports %u\n", + GSI_CHANNEL_COUNT_MAX, count); + count = GSI_CHANNEL_COUNT_MAX; + } + gsi->channel_count = count; + + count = u32_get_bits(val, NUM_EV_PER_EE_FMASK); + if (!count) { + dev_err(dev, "GSI reports zero event rings supported\n"); + return -EINVAL; + } + if (count > GSI_EVT_RING_COUNT_MAX) { + dev_warn(dev, + "limiting to %u event rings; hardware supports %u\n", + GSI_EVT_RING_COUNT_MAX, count); + count = GSI_EVT_RING_COUNT_MAX; + } + gsi->evt_ring_count = count; + + return 0; +} + /* Event ring commands are performed one at a time. Their completion * is signaled by the event ring control GSI interrupt type, which is * only enabled when we issue an event ring command. Only the event @@ -1827,43 +1879,21 @@ static void gsi_channel_teardown(struct gsi *gsi) /* Setup function for GSI. GSI firmware must be loaded and initialized */ int gsi_setup(struct gsi *gsi) { - struct device *dev = gsi->dev; u32 val; + int ret; /* Here is where we first touch the GSI hardware */ val = ioread32(gsi->virt + GSI_GSI_STATUS_OFFSET); if (!(val & ENABLED_FMASK)) { - dev_err(dev, "GSI has not been enabled\n"); + dev_err(gsi->dev, "GSI has not been enabled\n"); return -EIO; } gsi_irq_setup(gsi); /* No matching teardown required */ - val = ioread32(gsi->virt + GSI_GSI_HW_PARAM_2_OFFSET); - - gsi->channel_count = u32_get_bits(val, NUM_CH_PER_EE_FMASK); - if (!gsi->channel_count) { - dev_err(dev, "GSI reports zero channels supported\n"); - return -EINVAL; - } - if (gsi->channel_count > GSI_CHANNEL_COUNT_MAX) { - dev_warn(dev, - "limiting to %u channels; hardware supports %u\n", - GSI_CHANNEL_COUNT_MAX, gsi->channel_count); - gsi->channel_count = GSI_CHANNEL_COUNT_MAX; - } - - gsi->evt_ring_count = u32_get_bits(val, NUM_EV_PER_EE_FMASK); - if (!gsi->evt_ring_count) { - dev_err(dev, "GSI reports zero event rings supported\n"); - return -EINVAL; - } - if (gsi->evt_ring_count > GSI_EVT_RING_COUNT_MAX) { - dev_warn(dev, - "limiting to %u event rings; hardware supports %u\n", - GSI_EVT_RING_COUNT_MAX, gsi->evt_ring_count); - gsi->evt_ring_count = GSI_EVT_RING_COUNT_MAX; - } + ret = gsi_ring_setup(gsi); /* No matching teardown required */ + if (ret) + return ret; /* Initialize the error log */ iowrite32(0, gsi->virt + GSI_ERROR_LOG_OFFSET); diff --git a/drivers/net/ipa/gsi.h b/drivers/net/ipa/gsi.h index d5996bdb20ef..81cd7b07f6e1 100644 --- a/drivers/net/ipa/gsi.h +++ b/drivers/net/ipa/gsi.h @@ -17,7 +17,7 @@ /* Maximum number of channels and event rings supported by the driver */ #define GSI_CHANNEL_COUNT_MAX 23 -#define GSI_EVT_RING_COUNT_MAX 20 +#define GSI_EVT_RING_COUNT_MAX 24 /* Maximum TLV FIFO size for a channel; 64 here is arbitrary (and high) */ #define GSI_TLV_MAX 64 diff --git a/drivers/net/ipa/gsi_reg.h b/drivers/net/ipa/gsi_reg.h index cb42c5ae86fa..bf9593d9eaea 100644 --- a/drivers/net/ipa/gsi_reg.h +++ b/drivers/net/ipa/gsi_reg.h @@ -52,7 +52,8 @@ */ #define GSI_EE_REG_ADJUST 0x0000d000 /* IPA v4.5+ */ -/* The two inter-EE IRQ register offsets are relative to gsi->virt_raw */ +/* The inter-EE IRQ registers are relative to gsi->virt_raw (IPA v3.5+) */ + #define GSI_INTER_EE_SRC_CH_IRQ_MSK_OFFSET \ GSI_INTER_EE_N_SRC_CH_IRQ_MSK_OFFSET(GSI_EE_AP) #define GSI_INTER_EE_N_SRC_CH_IRQ_MSK_OFFSET(ee) \ diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index 525cdf28d9ea..af44ca41189e 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -200,41 +200,55 @@ bool ipa_cmd_table_valid(struct ipa *ipa, const struct ipa_mem *mem, /* Validate the memory region that holds headers */ static bool ipa_cmd_header_valid(struct ipa *ipa) { - const struct ipa_mem *mem = &ipa->mem[IPA_MEM_MODEM_HEADER]; struct device *dev = &ipa->pdev->dev; + const struct ipa_mem *mem; u32 offset_max; u32 size_max; + u32 offset; u32 size; - /* In ipa_cmd_hdr_init_local_add() we record the offset and size - * of the header table memory area. Make sure the offset and size - * fit in the fields that need to hold them, and that the entire - * range is within the overall IPA memory range. + /* In ipa_cmd_hdr_init_local_add() we record the offset and size of + * the header table memory area in an immediate command. Make sure + * the offset and size fit in the fields that need to hold them, and + * that the entire range is within the overall IPA memory range. */ offset_max = field_max(HDR_INIT_LOCAL_FLAGS_HDR_ADDR_FMASK); - if (mem->offset > offset_max || - ipa->mem_offset > offset_max - mem->offset) { + size_max = field_max(HDR_INIT_LOCAL_FLAGS_TABLE_SIZE_FMASK); + + /* The header memory area contains both the modem and AP header + * regions. The modem portion defines the address of the region. + */ + mem = ipa_mem_find(ipa, IPA_MEM_MODEM_HEADER); + offset = mem->offset; + size = mem->size; + + /* Make sure the offset fits in the IPA command */ + if (offset > offset_max || ipa->mem_offset > offset_max - offset) { dev_err(dev, "header table region offset too large\n"); dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n", - ipa->mem_offset, mem->offset, offset_max); + ipa->mem_offset, offset, offset_max); return false; } - size_max = field_max(HDR_INIT_LOCAL_FLAGS_TABLE_SIZE_FMASK); - size = ipa->mem[IPA_MEM_MODEM_HEADER].size; - size += ipa->mem[IPA_MEM_AP_HEADER].size; + /* Add the size of the AP portion (if defined) to the combined size */ + mem = ipa_mem_find(ipa, IPA_MEM_AP_HEADER); + if (mem) + size += mem->size; + /* Make sure the combined size fits in the IPA command */ if (size > size_max) { dev_err(dev, "header table region size too large\n"); dev_err(dev, " (0x%04x > 0x%08x)\n", size, size_max); return false; } - if (size > ipa->mem_size || mem->offset > ipa->mem_size - size) { + + /* Make sure the entire combined area fits in IPA memory */ + if (size > ipa->mem_size || offset > ipa->mem_size - size) { dev_err(dev, "header table region out of range\n"); dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n", - mem->offset, size, ipa->mem_size); + offset, size, ipa->mem_size); return false; } diff --git a/drivers/net/ipa/ipa_data-v3.1.c b/drivers/net/ipa/ipa_data-v3.1.c new file mode 100644 index 000000000000..4c28189462a7 --- /dev/null +++ b/drivers/net/ipa/ipa_data-v3.1.c @@ -0,0 +1,533 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved. + * Copyright (C) 2019-2021 Linaro Ltd. + */ + +#include + +#include "gsi.h" +#include "ipa_data.h" +#include "ipa_endpoint.h" +#include "ipa_mem.h" + +/** enum ipa_resource_type - IPA resource types for an SoC having IPA v3.1 */ +enum ipa_resource_type { + /* Source resource types; first must have value 0 */ + IPA_RESOURCE_TYPE_SRC_PKT_CONTEXTS = 0, + IPA_RESOURCE_TYPE_SRC_HDR_SECTORS, + IPA_RESOURCE_TYPE_SRC_HDRI1_BUFFER, + IPA_RESOURCE_TYPE_SRC_DESCRIPTOR_LISTS, + IPA_RESOURCE_TYPE_SRC_DESCRIPTOR_BUFF, + IPA_RESOURCE_TYPE_SRC_HDRI2_BUFFERS, + IPA_RESOURCE_TYPE_SRC_HPS_DMARS, + IPA_RESOURCE_TYPE_SRC_ACK_ENTRIES, + + /* Destination resource types; first must have value 0 */ + IPA_RESOURCE_TYPE_DST_DATA_SECTORS = 0, + IPA_RESOURCE_TYPE_DST_DATA_SECTOR_LISTS, + IPA_RESOURCE_TYPE_DST_DPS_DMARS, +}; + +/* Resource groups used for an SoC having IPA v3.1 */ +enum ipa_rsrc_group_id { + /* Source resource group identifiers */ + IPA_RSRC_GROUP_SRC_UL = 0, + IPA_RSRC_GROUP_SRC_DL, + IPA_RSRC_GROUP_SRC_DIAG, + IPA_RSRC_GROUP_SRC_DMA, + IPA_RSRC_GROUP_SRC_UNUSED, + IPA_RSRC_GROUP_SRC_UC_RX_Q, + IPA_RSRC_GROUP_SRC_COUNT, /* Last in set; not a source group */ + + /* Destination resource group identifiers */ + IPA_RSRC_GROUP_DST_UL = 0, + IPA_RSRC_GROUP_DST_DL, + IPA_RSRC_GROUP_DST_DIAG_DPL, + IPA_RSRC_GROUP_DST_DMA, + IPA_RSRC_GROUP_DST_Q6ZIP_GENERAL, + IPA_RSRC_GROUP_DST_Q6ZIP_ENGINE, + IPA_RSRC_GROUP_DST_COUNT, /* Last; not a destination group */ +}; + +/* QSB configuration data for an SoC having IPA v3.1 */ +static const struct ipa_qsb_data ipa_qsb_data[] = { + [IPA_QSB_MASTER_DDR] = { + .max_writes = 8, + .max_reads = 8, + }, + [IPA_QSB_MASTER_PCIE] = { + .max_writes = 2, + .max_reads = 8, + }, +}; + +/* Endpoint data for an SoC having IPA v3.1 */ +static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { + [IPA_ENDPOINT_AP_COMMAND_TX] = { + .ee_id = GSI_EE_AP, + .channel_id = 6, + .endpoint_id = 22, + .toward_ipa = true, + .channel = { + .tre_count = 256, + .event_count = 256, + .tlv_count = 18, + }, + .endpoint = { + .config = { + .resource_group = IPA_RSRC_GROUP_SRC_UL, + .dma_mode = true, + .dma_endpoint = IPA_ENDPOINT_AP_LAN_RX, + .tx = { + .seq_type = IPA_SEQ_DMA, + }, + }, + }, + }, + [IPA_ENDPOINT_AP_LAN_RX] = { + .ee_id = GSI_EE_AP, + .channel_id = 7, + .endpoint_id = 15, + .toward_ipa = false, + .channel = { + .tre_count = 256, + .event_count = 256, + .tlv_count = 8, + }, + .endpoint = { + .config = { + .resource_group = IPA_RSRC_GROUP_SRC_UL, + .aggregation = true, + .status_enable = true, + .rx = { + .pad_align = ilog2(sizeof(u32)), + }, + }, + }, + }, + [IPA_ENDPOINT_AP_MODEM_TX] = { + .ee_id = GSI_EE_AP, + .channel_id = 5, + .endpoint_id = 3, + .toward_ipa = true, + .channel = { + .tre_count = 512, + .event_count = 512, + .tlv_count = 16, + }, + .endpoint = { + .filter_support = true, + .config = { + .resource_group = IPA_RSRC_GROUP_SRC_UL, + .checksum = true, + .qmap = true, + .status_enable = true, + .tx = { + .seq_type = IPA_SEQ_2_PASS_SKIP_LAST_UC, + .status_endpoint = + IPA_ENDPOINT_MODEM_AP_RX, + }, + }, + }, + }, + [IPA_ENDPOINT_AP_MODEM_RX] = { + .ee_id = GSI_EE_AP, + .channel_id = 8, + .endpoint_id = 16, + .toward_ipa = false, + .channel = { + .tre_count = 256, + .event_count = 256, + .tlv_count = 8, + }, + .endpoint = { + .config = { + .resource_group = IPA_RSRC_GROUP_DST_DL, + .checksum = true, + .qmap = true, + .aggregation = true, + .rx = { + .aggr_close_eof = true, + }, + }, + }, + }, + [IPA_ENDPOINT_MODEM_LAN_TX] = { + .ee_id = GSI_EE_MODEM, + .channel_id = 4, + .endpoint_id = 9, + .toward_ipa = true, + .endpoint = { + .filter_support = true, + }, + }, + [IPA_ENDPOINT_MODEM_AP_TX] = { + .ee_id = GSI_EE_MODEM, + .channel_id = 0, + .endpoint_id = 5, + .toward_ipa = true, + .endpoint = { + .filter_support = true, + }, + }, + [IPA_ENDPOINT_MODEM_AP_RX] = { + .ee_id = GSI_EE_MODEM, + .channel_id = 5, + .endpoint_id = 18, + .toward_ipa = false, + }, +}; + +/* Source resource configuration data for an SoC having IPA v3.1 */ +static const struct ipa_resource ipa_resource_src[] = { + [IPA_RESOURCE_TYPE_SRC_PKT_CONTEXTS] = { + .limits[IPA_RSRC_GROUP_SRC_UL] = { + .min = 3, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DL] = { + .min = 3, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DIAG] = { + .min = 1, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DMA] = { + .min = 1, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_UC_RX_Q] = { + .min = 2, .max = 255, + }, + }, + [IPA_RESOURCE_TYPE_SRC_HDR_SECTORS] = { + .limits[IPA_RSRC_GROUP_SRC_UL] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DL] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DIAG] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DMA] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_UC_RX_Q] = { + .min = 0, .max = 255, + }, + }, + [IPA_RESOURCE_TYPE_SRC_HDRI1_BUFFER] = { + .limits[IPA_RSRC_GROUP_SRC_UL] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DL] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DIAG] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DMA] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_UC_RX_Q] = { + .min = 0, .max = 255, + }, + }, + [IPA_RESOURCE_TYPE_SRC_DESCRIPTOR_LISTS] = { + .limits[IPA_RSRC_GROUP_SRC_UL] = { + .min = 14, .max = 14, + }, + .limits[IPA_RSRC_GROUP_SRC_DL] = { + .min = 16, .max = 16, + }, + .limits[IPA_RSRC_GROUP_SRC_DIAG] = { + .min = 5, .max = 5, + }, + .limits[IPA_RSRC_GROUP_SRC_DMA] = { + .min = 5, .max = 5, + }, + .limits[IPA_RSRC_GROUP_SRC_UC_RX_Q] = { + .min = 8, .max = 8, + }, + }, + [IPA_RESOURCE_TYPE_SRC_DESCRIPTOR_BUFF] = { + .limits[IPA_RSRC_GROUP_SRC_UL] = { + .min = 19, .max = 19, + }, + .limits[IPA_RSRC_GROUP_SRC_DL] = { + .min = 26, .max = 26, + }, + .limits[IPA_RSRC_GROUP_SRC_DIAG] = { + .min = 5, .max = 5, /* 3 downstream */ + }, + .limits[IPA_RSRC_GROUP_SRC_DMA] = { + .min = 5, .max = 5, /* 7 downstream */ + }, + .limits[IPA_RSRC_GROUP_SRC_UC_RX_Q] = { + .min = 8, .max = 8, + }, + }, + [IPA_RESOURCE_TYPE_SRC_HDRI2_BUFFERS] = { + .limits[IPA_RSRC_GROUP_SRC_UL] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DL] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DIAG] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DMA] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_UC_RX_Q] = { + .min = 0, .max = 255, + }, + }, + [IPA_RESOURCE_TYPE_SRC_HPS_DMARS] = { + .limits[IPA_RSRC_GROUP_SRC_UL] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DL] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DIAG] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_DMA] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_SRC_UC_RX_Q] = { + .min = 0, .max = 255, + }, + }, + [IPA_RESOURCE_TYPE_SRC_ACK_ENTRIES] = { + .limits[IPA_RSRC_GROUP_SRC_UL] = { + .min = 19, .max = 19, + }, + .limits[IPA_RSRC_GROUP_SRC_DL] = { + .min = 26, .max = 26, + }, + .limits[IPA_RSRC_GROUP_SRC_DIAG] = { + .min = 5, .max = 5, + }, + .limits[IPA_RSRC_GROUP_SRC_DMA] = { + .min = 5, .max = 5, + }, + .limits[IPA_RSRC_GROUP_SRC_UC_RX_Q] = { + .min = 8, .max = 8, + }, + }, +}; + +/* Destination resource configuration data for an SoC having IPA v3.1 */ +static const struct ipa_resource ipa_resource_dst[] = { + [IPA_RESOURCE_TYPE_DST_DATA_SECTORS] = { + .limits[IPA_RSRC_GROUP_DST_UL] = { + .min = 3, .max = 3, /* 2 downstream */ + }, + .limits[IPA_RSRC_GROUP_DST_DL] = { + .min = 3, .max = 3, + }, + .limits[IPA_RSRC_GROUP_DST_DIAG_DPL] = { + .min = 1, .max = 1, /* 0 downstream */ + }, + /* IPA_RSRC_GROUP_DST_DMA uses 2 downstream */ + .limits[IPA_RSRC_GROUP_DST_Q6ZIP_GENERAL] = { + .min = 3, .max = 3, + }, + .limits[IPA_RSRC_GROUP_DST_Q6ZIP_ENGINE] = { + .min = 3, .max = 3, + }, + }, + [IPA_RESOURCE_TYPE_DST_DATA_SECTOR_LISTS] = { + .limits[IPA_RSRC_GROUP_DST_UL] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_DST_DL] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_DST_DIAG_DPL] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_DST_DMA] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_DST_Q6ZIP_GENERAL] = { + .min = 0, .max = 255, + }, + .limits[IPA_RSRC_GROUP_DST_Q6ZIP_ENGINE] = { + .min = 0, .max = 255, + }, + }, + [IPA_RESOURCE_TYPE_DST_DPS_DMARS] = { + .limits[IPA_RSRC_GROUP_DST_UL] = { + .min = 1, .max = 1, + }, + .limits[IPA_RSRC_GROUP_DST_DL] = { + .min = 1, .max = 1, + }, + .limits[IPA_RSRC_GROUP_DST_DIAG_DPL] = { + .min = 1, .max = 1, + }, + .limits[IPA_RSRC_GROUP_DST_DMA] = { + .min = 1, .max = 1, + }, + .limits[IPA_RSRC_GROUP_DST_Q6ZIP_GENERAL] = { + .min = 1, .max = 1, + }, + }, +}; + +/* Resource configuration data for an SoC having IPA v3.1 */ +static const struct ipa_resource_data ipa_resource_data = { + .rsrc_group_src_count = IPA_RSRC_GROUP_SRC_COUNT, + .rsrc_group_dst_count = IPA_RSRC_GROUP_DST_COUNT, + .resource_src_count = ARRAY_SIZE(ipa_resource_src), + .resource_src = ipa_resource_src, + .resource_dst_count = ARRAY_SIZE(ipa_resource_dst), + .resource_dst = ipa_resource_dst, +}; + +/* IPA-resident memory region data for an SoC having IPA v3.1 */ +static const struct ipa_mem ipa_mem_local_data[] = { + { + .id = IPA_MEM_UC_SHARED, + .offset = 0x0000, + .size = 0x0080, + .canary_count = 0, + }, + { + .id = IPA_MEM_UC_INFO, + .offset = 0x0080, + .size = 0x0200, + .canary_count = 0, + }, + { + .id = IPA_MEM_V4_FILTER_HASHED, + .offset = 0x0288, + .size = 0x0078, + .canary_count = 2, + }, + { + .id = IPA_MEM_V4_FILTER, + .offset = 0x0308, + .size = 0x0078, + .canary_count = 2, + }, + { + .id = IPA_MEM_V6_FILTER_HASHED, + .offset = 0x0388, + .size = 0x0078, + .canary_count = 2, + }, + { + .id = IPA_MEM_V6_FILTER, + .offset = 0x0408, + .size = 0x0078, + .canary_count = 2, + }, + { + .id = IPA_MEM_V4_ROUTE_HASHED, + .offset = 0x0488, + .size = 0x0078, + .canary_count = 2, + }, + { + .id = IPA_MEM_V4_ROUTE, + .offset = 0x0508, + .size = 0x0078, + .canary_count = 2, + }, + { + .id = IPA_MEM_V6_ROUTE_HASHED, + .offset = 0x0588, + .size = 0x0078, + .canary_count = 2, + }, + { + .id = IPA_MEM_V6_ROUTE, + .offset = 0x0608, + .size = 0x0078, + .canary_count = 2, + }, + { + .id = IPA_MEM_MODEM_HEADER, + .offset = 0x0688, + .size = 0x0140, + .canary_count = 2, + }, + { + .id = IPA_MEM_MODEM_PROC_CTX, + .offset = 0x07d0, + .size = 0x0200, + .canary_count = 2, + }, + { + .id = IPA_MEM_AP_PROC_CTX, + .offset = 0x09d0, + .size = 0x0200, + .canary_count = 0, + }, + { + .id = IPA_MEM_MODEM, + .offset = 0x0bd8, + .size = 0x1424, + .canary_count = 0, + }, + { + .id = IPA_MEM_END_MARKER, + .offset = 0x2000, + .size = 0, + .canary_count = 1, + }, +}; + +/* Memory configuration data for an SoC having IPA v3.1 */ +static const struct ipa_mem_data ipa_mem_data = { + .local_count = ARRAY_SIZE(ipa_mem_local_data), + .local = ipa_mem_local_data, + .imem_addr = 0x146bd000, + .imem_size = 0x00002000, + .smem_id = 497, + .smem_size = 0x00002000, +}; + +/* Interconnect bandwidths are in 1000 byte/second units */ +static const struct ipa_interconnect_data ipa_interconnect_data[] = { + { + .name = "memory", + .peak_bandwidth = 640000, /* 640 MBps */ + .average_bandwidth = 80000, /* 80 MBps */ + }, + { + .name = "imem", + .peak_bandwidth = 640000, /* 640 MBps */ + .average_bandwidth = 80000, /* 80 MBps */ + }, + /* Average bandwidth is unused for the next interconnect */ + { + .name = "config", + .peak_bandwidth = 80000, /* 80 MBps */ + .average_bandwidth = 0, /* unused */ + }, +}; + +/* Clock and interconnect configuration data for an SoC having IPA v3.1 */ +static const struct ipa_clock_data ipa_clock_data = { + .core_clock_rate = 16 * 1000 * 1000, /* Hz */ + .interconnect_count = ARRAY_SIZE(ipa_interconnect_data), + .interconnect_data = ipa_interconnect_data, +}; + +/* Configuration data for an SoC having IPA v3.1 */ +const struct ipa_data ipa_data_v3_1 = { + .version = IPA_VERSION_3_1, + .backward_compat = BCR_CMDQ_L_LACK_ONE_ENTRY_FMASK, + .qsb_count = ARRAY_SIZE(ipa_qsb_data), + .qsb_data = ipa_qsb_data, + .endpoint_count = ARRAY_SIZE(ipa_gsi_endpoint_data), + .endpoint_data = ipa_gsi_endpoint_data, + .resource_data = &ipa_resource_data, + .mem_data = &ipa_mem_data, + .clock_data = &ipa_clock_data, +}; diff --git a/drivers/net/ipa/ipa_data-v3.5.1.c b/drivers/net/ipa/ipa_data-v3.5.1.c index ead1a82f32f5..af536ef8c120 100644 --- a/drivers/net/ipa/ipa_data-v3.5.1.c +++ b/drivers/net/ipa/ipa_data-v3.5.1.c @@ -271,77 +271,92 @@ static const struct ipa_resource_data ipa_resource_data = { /* IPA-resident memory region data for an SoC having IPA v3.5.1 */ static const struct ipa_mem ipa_mem_local_data[] = { - [IPA_MEM_UC_SHARED] = { + { + .id = IPA_MEM_UC_SHARED, .offset = 0x0000, .size = 0x0080, .canary_count = 0, }, - [IPA_MEM_UC_INFO] = { + { + .id = IPA_MEM_UC_INFO, .offset = 0x0080, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_V4_FILTER_HASHED] = { + { + .id = IPA_MEM_V4_FILTER_HASHED, .offset = 0x0288, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_FILTER] = { + { + .id = IPA_MEM_V4_FILTER, .offset = 0x0308, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_FILTER_HASHED] = { + { + .id = IPA_MEM_V6_FILTER_HASHED, .offset = 0x0388, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_FILTER] = { + { + .id = IPA_MEM_V6_FILTER, .offset = 0x0408, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_ROUTE_HASHED] = { + { + .id = IPA_MEM_V4_ROUTE_HASHED, .offset = 0x0488, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_ROUTE] = { + { + .id = IPA_MEM_V4_ROUTE, .offset = 0x0508, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_ROUTE_HASHED] = { + { + .id = IPA_MEM_V6_ROUTE_HASHED, .offset = 0x0588, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_ROUTE] = { + { + .id = IPA_MEM_V6_ROUTE, .offset = 0x0608, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_MODEM_HEADER] = { + { + .id = IPA_MEM_MODEM_HEADER, .offset = 0x0688, .size = 0x0140, .canary_count = 2, }, - [IPA_MEM_MODEM_PROC_CTX] = { + { + .id = IPA_MEM_MODEM_PROC_CTX, .offset = 0x07d0, .size = 0x0200, .canary_count = 2, }, - [IPA_MEM_AP_PROC_CTX] = { + { + .id = IPA_MEM_AP_PROC_CTX, .offset = 0x09d0, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_MODEM] = { + { + .id = IPA_MEM_MODEM, .offset = 0x0bd8, .size = 0x1024, .canary_count = 0, }, - [IPA_MEM_UC_EVENT_RING] = { + { + .id = IPA_MEM_UC_EVENT_RING, .offset = 0x1c00, .size = 0x0400, .canary_count = 1, diff --git a/drivers/net/ipa/ipa_data-v4.11.c b/drivers/net/ipa/ipa_data-v4.11.c index 05806ceae8b5..9353efbd504f 100644 --- a/drivers/net/ipa/ipa_data-v4.11.c +++ b/drivers/net/ipa/ipa_data-v4.11.c @@ -220,112 +220,134 @@ static const struct ipa_resource_data ipa_resource_data = { /* IPA-resident memory region data for an SoC having IPA v4.11 */ static const struct ipa_mem ipa_mem_local_data[] = { - [IPA_MEM_UC_SHARED] = { + { + .id = IPA_MEM_UC_SHARED, .offset = 0x0000, .size = 0x0080, .canary_count = 0, }, - [IPA_MEM_UC_INFO] = { + { + .id = IPA_MEM_UC_INFO, .offset = 0x0080, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_V4_FILTER_HASHED] = { + { + .id = IPA_MEM_V4_FILTER_HASHED, .offset = 0x0288, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_FILTER] = { + { + .id = IPA_MEM_V4_FILTER, .offset = 0x0308, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_FILTER_HASHED] = { + { + .id = IPA_MEM_V6_FILTER_HASHED, .offset = 0x0388, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_FILTER] = { + { + .id = IPA_MEM_V6_FILTER, .offset = 0x0408, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_ROUTE_HASHED] = { + { + .id = IPA_MEM_V4_ROUTE_HASHED, .offset = 0x0488, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_ROUTE] = { + { + .id = IPA_MEM_V4_ROUTE, .offset = 0x0508, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_ROUTE_HASHED] = { + { + .id = IPA_MEM_V6_ROUTE_HASHED, .offset = 0x0588, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_ROUTE] = { + { + .id = IPA_MEM_V6_ROUTE, .offset = 0x0608, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_MODEM_HEADER] = { + { + .id = IPA_MEM_MODEM_HEADER, .offset = 0x0688, .size = 0x0240, .canary_count = 2, }, - [IPA_MEM_AP_HEADER] = { + { + .id = IPA_MEM_AP_HEADER, .offset = 0x08c8, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_MODEM_PROC_CTX] = { + { + .id = IPA_MEM_MODEM_PROC_CTX, .offset = 0x0ad0, .size = 0x0200, .canary_count = 2, }, - [IPA_MEM_AP_PROC_CTX] = { + { + .id = IPA_MEM_AP_PROC_CTX, .offset = 0x0cd0, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_NAT_TABLE] = { + { + .id = IPA_MEM_NAT_TABLE, .offset = 0x0ee0, .size = 0x0d00, .canary_count = 4, }, - [IPA_MEM_PDN_CONFIG] = { + { + .id = IPA_MEM_PDN_CONFIG, .offset = 0x1be8, .size = 0x0050, .canary_count = 0, }, - [IPA_MEM_STATS_QUOTA_MODEM] = { + { + .id = IPA_MEM_STATS_QUOTA_MODEM, .offset = 0x1c40, .size = 0x0030, .canary_count = 4, }, - [IPA_MEM_STATS_QUOTA_AP] = { + { + .id = IPA_MEM_STATS_QUOTA_AP, .offset = 0x1c70, .size = 0x0048, .canary_count = 0, }, - [IPA_MEM_STATS_TETHERING] = { + { + .id = IPA_MEM_STATS_TETHERING, .offset = 0x1cb8, .size = 0x0238, .canary_count = 0, }, - [IPA_MEM_STATS_DROP] = { + { + .id = IPA_MEM_STATS_DROP, .offset = 0x1ef0, .size = 0x0020, .canary_count = 0, }, - [IPA_MEM_MODEM] = { + { + .id = IPA_MEM_MODEM, .offset = 0x1f18, .size = 0x100c, .canary_count = 2, }, - [IPA_MEM_UC_EVENT_RING] = { + { + .id = IPA_MEM_END_MARKER, .offset = 0x3000, .size = 0x0000, .canary_count = 1, diff --git a/drivers/net/ipa/ipa_data-v4.2.c b/drivers/net/ipa/ipa_data-v4.2.c index 8744f19c6401..3b09b7baa95f 100644 --- a/drivers/net/ipa/ipa_data-v4.2.c +++ b/drivers/net/ipa/ipa_data-v4.2.c @@ -219,92 +219,110 @@ static const struct ipa_resource_data ipa_resource_data = { /* IPA-resident memory region data for an SoC having IPA v4.2 */ static const struct ipa_mem ipa_mem_local_data[] = { - [IPA_MEM_UC_SHARED] = { + { + .id = IPA_MEM_UC_SHARED, .offset = 0x0000, .size = 0x0080, .canary_count = 0, }, - [IPA_MEM_UC_INFO] = { + { + .id = IPA_MEM_UC_INFO, .offset = 0x0080, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_V4_FILTER_HASHED] = { + { + .id = IPA_MEM_V4_FILTER_HASHED, .offset = 0x0288, .size = 0, .canary_count = 2, }, - [IPA_MEM_V4_FILTER] = { + { + .id = IPA_MEM_V4_FILTER, .offset = 0x0290, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_FILTER_HASHED] = { + { + .id = IPA_MEM_V6_FILTER_HASHED, .offset = 0x0310, .size = 0, .canary_count = 2, }, - [IPA_MEM_V6_FILTER] = { + { + .id = IPA_MEM_V6_FILTER, .offset = 0x0318, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_ROUTE_HASHED] = { + { + .id = IPA_MEM_V4_ROUTE_HASHED, .offset = 0x0398, .size = 0, .canary_count = 2, }, - [IPA_MEM_V4_ROUTE] = { + { + .id = IPA_MEM_V4_ROUTE, .offset = 0x03a0, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_ROUTE_HASHED] = { + { + .id = IPA_MEM_V6_ROUTE_HASHED, .offset = 0x0420, .size = 0, .canary_count = 2, }, - [IPA_MEM_V6_ROUTE] = { + { + .id = IPA_MEM_V6_ROUTE, .offset = 0x0428, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_MODEM_HEADER] = { + { + .id = IPA_MEM_MODEM_HEADER, .offset = 0x04a8, .size = 0x0140, .canary_count = 2, }, - [IPA_MEM_MODEM_PROC_CTX] = { + { + .id = IPA_MEM_MODEM_PROC_CTX, .offset = 0x05f0, .size = 0x0200, .canary_count = 2, }, - [IPA_MEM_AP_PROC_CTX] = { + { + .id = IPA_MEM_AP_PROC_CTX, .offset = 0x07f0, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_PDN_CONFIG] = { + { + .id = IPA_MEM_PDN_CONFIG, .offset = 0x09f8, .size = 0x0050, .canary_count = 2, }, - [IPA_MEM_STATS_QUOTA_MODEM] = { + { + .id = IPA_MEM_STATS_QUOTA_MODEM, .offset = 0x0a50, .size = 0x0060, .canary_count = 2, }, - [IPA_MEM_STATS_TETHERING] = { + { + .id = IPA_MEM_STATS_TETHERING, .offset = 0x0ab0, .size = 0x0140, .canary_count = 0, }, - [IPA_MEM_MODEM] = { + { + .id = IPA_MEM_MODEM, .offset = 0x0bf0, .size = 0x140c, .canary_count = 0, }, - [IPA_MEM_UC_EVENT_RING] = { + { + .id = IPA_MEM_END_MARKER, .offset = 0x2000, .size = 0, .canary_count = 1, diff --git a/drivers/net/ipa/ipa_data-v4.5.c b/drivers/net/ipa/ipa_data-v4.5.c index 5f67a3a909ee..a99b6478fa3a 100644 --- a/drivers/net/ipa/ipa_data-v4.5.c +++ b/drivers/net/ipa/ipa_data-v4.5.c @@ -265,117 +265,140 @@ static const struct ipa_resource_data ipa_resource_data = { /* IPA-resident memory region data for an SoC having IPA v4.5 */ static const struct ipa_mem ipa_mem_local_data[] = { - [IPA_MEM_UC_SHARED] = { + { + .id = IPA_MEM_UC_SHARED, .offset = 0x0000, .size = 0x0080, .canary_count = 0, }, - [IPA_MEM_UC_INFO] = { + { + .id = IPA_MEM_UC_INFO, .offset = 0x0080, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_V4_FILTER_HASHED] = { + { + .id = IPA_MEM_V4_FILTER_HASHED, .offset = 0x0288, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_FILTER] = { + { + .id = IPA_MEM_V4_FILTER, .offset = 0x0308, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_FILTER_HASHED] = { + { + .id = IPA_MEM_V6_FILTER_HASHED, .offset = 0x0388, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_FILTER] = { + { + .id = IPA_MEM_V6_FILTER, .offset = 0x0408, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_ROUTE_HASHED] = { + { + .id = IPA_MEM_V4_ROUTE_HASHED, .offset = 0x0488, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_ROUTE] = { + { + .id = IPA_MEM_V4_ROUTE, .offset = 0x0508, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_ROUTE_HASHED] = { + { + .id = IPA_MEM_V6_ROUTE_HASHED, .offset = 0x0588, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_ROUTE] = { + { + .id = IPA_MEM_V6_ROUTE, .offset = 0x0608, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_MODEM_HEADER] = { + { + .id = IPA_MEM_MODEM_HEADER, .offset = 0x0688, .size = 0x0240, .canary_count = 2, }, - [IPA_MEM_AP_HEADER] = { + { + .id = IPA_MEM_AP_HEADER, .offset = 0x08c8, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_MODEM_PROC_CTX] = { + { + .id = IPA_MEM_MODEM_PROC_CTX, .offset = 0x0ad0, .size = 0x0b20, .canary_count = 2, }, - [IPA_MEM_AP_PROC_CTX] = { + { + .id = IPA_MEM_AP_PROC_CTX, .offset = 0x15f0, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_NAT_TABLE] = { + { + .id = IPA_MEM_NAT_TABLE, .offset = 0x1800, .size = 0x0d00, .canary_count = 4, }, - [IPA_MEM_STATS_QUOTA_MODEM] = { + { + .id = IPA_MEM_STATS_QUOTA_MODEM, .offset = 0x2510, .size = 0x0030, .canary_count = 4, }, - [IPA_MEM_STATS_QUOTA_AP] = { + { + .id = IPA_MEM_STATS_QUOTA_AP, .offset = 0x2540, .size = 0x0048, .canary_count = 0, }, - [IPA_MEM_STATS_TETHERING] = { + { + .id = IPA_MEM_STATS_TETHERING, .offset = 0x2588, .size = 0x0238, .canary_count = 0, }, - [IPA_MEM_STATS_FILTER_ROUTE] = { + { + .id = IPA_MEM_STATS_FILTER_ROUTE, .offset = 0x27c0, .size = 0x0800, .canary_count = 0, }, - [IPA_MEM_STATS_DROP] = { + { + .id = IPA_MEM_STATS_DROP, .offset = 0x2fc0, .size = 0x0020, .canary_count = 0, }, - [IPA_MEM_MODEM] = { + { + .id = IPA_MEM_MODEM, .offset = 0x2fe8, .size = 0x0800, .canary_count = 2, }, - [IPA_MEM_UC_EVENT_RING] = { + { + .id = IPA_MEM_UC_EVENT_RING, .offset = 0x3800, .size = 0x1000, .canary_count = 1, }, - [IPA_MEM_PDN_CONFIG] = { + { + .id = IPA_MEM_PDN_CONFIG, .offset = 0x4800, .size = 0x0050, .canary_count = 0, diff --git a/drivers/net/ipa/ipa_data-v4.9.c b/drivers/net/ipa/ipa_data-v4.9.c index e41be790f45e..798d43e1eb13 100644 --- a/drivers/net/ipa/ipa_data-v4.9.c +++ b/drivers/net/ipa/ipa_data-v4.9.c @@ -263,116 +263,140 @@ static const struct ipa_resource_data ipa_resource_data = { /* IPA-resident memory region data for an SoC having IPA v4.9 */ static const struct ipa_mem ipa_mem_local_data[] = { - [IPA_MEM_UC_SHARED] = { + { + .id = IPA_MEM_UC_SHARED, .offset = 0x0000, .size = 0x0080, .canary_count = 0, }, - [IPA_MEM_UC_INFO] = { + { + .id = IPA_MEM_UC_INFO, .offset = 0x0080, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_V4_FILTER_HASHED] = { .offset = 0x0288, + { + .id = IPA_MEM_V4_FILTER_HASHED, + .offset = 0x0288, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_FILTER] = { + { + .id = IPA_MEM_V4_FILTER, .offset = 0x0308, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_FILTER_HASHED] = { + { + .id = IPA_MEM_V6_FILTER_HASHED, .offset = 0x0388, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_FILTER] = { + { + .id = IPA_MEM_V6_FILTER, .offset = 0x0408, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_ROUTE_HASHED] = { + { + .id = IPA_MEM_V4_ROUTE_HASHED, .offset = 0x0488, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V4_ROUTE] = { + { + .id = IPA_MEM_V4_ROUTE, .offset = 0x0508, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_ROUTE_HASHED] = { + { + .id = IPA_MEM_V6_ROUTE_HASHED, .offset = 0x0588, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_V6_ROUTE] = { + { + .id = IPA_MEM_V6_ROUTE, .offset = 0x0608, .size = 0x0078, .canary_count = 2, }, - [IPA_MEM_MODEM_HEADER] = { + { + .id = IPA_MEM_MODEM_HEADER, .offset = 0x0688, .size = 0x0240, .canary_count = 2, }, - [IPA_MEM_AP_HEADER] = { + { + .id = IPA_MEM_AP_HEADER, .offset = 0x08c8, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_MODEM_PROC_CTX] = { + { + .id = IPA_MEM_MODEM_PROC_CTX, .offset = 0x0ad0, .size = 0x0b20, .canary_count = 2, }, - [IPA_MEM_AP_PROC_CTX] = { + { + .id = IPA_MEM_AP_PROC_CTX, .offset = 0x15f0, .size = 0x0200, .canary_count = 0, }, - [IPA_MEM_NAT_TABLE] = { + { + .id = IPA_MEM_NAT_TABLE, .offset = 0x1800, .size = 0x0d00, .canary_count = 4, }, - [IPA_MEM_STATS_QUOTA_MODEM] = { + { + .id = IPA_MEM_STATS_QUOTA_MODEM, .offset = 0x2510, .size = 0x0030, .canary_count = 4, }, - [IPA_MEM_STATS_QUOTA_AP] = { + { + .id = IPA_MEM_STATS_QUOTA_AP, .offset = 0x2540, .size = 0x0048, .canary_count = 0, }, - [IPA_MEM_STATS_TETHERING] = { + { + .id = IPA_MEM_STATS_TETHERING, .offset = 0x2588, .size = 0x0238, .canary_count = 0, }, - [IPA_MEM_STATS_FILTER_ROUTE] = { + { + .id = IPA_MEM_STATS_FILTER_ROUTE, .offset = 0x27c0, .size = 0x0800, .canary_count = 0, }, - [IPA_MEM_STATS_DROP] = { + { + .id = IPA_MEM_STATS_DROP, .offset = 0x2fc0, .size = 0x0020, .canary_count = 0, }, - [IPA_MEM_MODEM] = { + { + .id = IPA_MEM_MODEM, .offset = 0x2fe8, .size = 0x0800, .canary_count = 2, }, - [IPA_MEM_UC_EVENT_RING] = { + { + .id = IPA_MEM_UC_EVENT_RING, .offset = 0x3800, .size = 0x1000, .canary_count = 1, }, - [IPA_MEM_PDN_CONFIG] = { + { + .id = IPA_MEM_PDN_CONFIG, .offset = 0x4800, .size = 0x0050, .canary_count = 0, diff --git a/drivers/net/ipa/ipa_data.h b/drivers/net/ipa/ipa_data.h index 5c4c8d72d7d8..5bc244c8f94e 100644 --- a/drivers/net/ipa/ipa_data.h +++ b/drivers/net/ipa/ipa_data.h @@ -300,6 +300,7 @@ struct ipa_data { const struct ipa_clock_data *clock_data; }; +extern const struct ipa_data ipa_data_v3_1; extern const struct ipa_data ipa_data_v3_5_1; extern const struct ipa_data ipa_data_v4_2; extern const struct ipa_data ipa_data_v4_5; diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index ccc99ad983eb..ab02669bae4e 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -75,8 +75,6 @@ struct ipa_status { #define IPA_STATUS_FLAGS1_RT_RULE_ID_FMASK GENMASK(31, 22) #define IPA_STATUS_FLAGS2_TAG_FMASK GENMASK_ULL(63, 16) -#ifdef IPA_VALIDATE - static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, const struct ipa_gsi_endpoint_data *all_data, const struct ipa_gsi_endpoint_data *data) @@ -88,11 +86,6 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, if (ipa_gsi_endpoint_data_empty(data)) return true; - /* IPA v4.5+ uses checksum offload, not yet supported by RMNet */ - if (ipa->version >= IPA_VERSION_4_5) - if (data->endpoint.config.checksum) - return false; - if (!data->toward_ipa) { if (data->endpoint.filter_support) { dev_err(dev, "filtering not supported for " @@ -230,27 +223,6 @@ static bool ipa_endpoint_data_valid(struct ipa *ipa, u32 count, return true; } -#else /* !IPA_VALIDATE */ - -static bool ipa_endpoint_data_valid(struct ipa *ipa, u32 count, - const struct ipa_gsi_endpoint_data *data) -{ - const struct ipa_gsi_endpoint_data *dp = data; - enum ipa_endpoint_name name; - - if (ipa->version < IPA_VERSION_4_5) - return true; - - /* IPA v4.5+ uses checksum offload, not yet supported by RMNet */ - for (name = 0; name < count; name++, dp++) - if (data->endpoint.config.checksum) - return false; - - return true; -} - -#endif /* !IPA_VALIDATE */ - /* Allocate a transaction to use on a non-command endpoint */ static struct gsi_trans *ipa_endpoint_trans_alloc(struct ipa_endpoint *endpoint, u32 tre_count) @@ -457,28 +429,34 @@ int ipa_endpoint_modem_exception_reset_all(struct ipa *ipa) static void ipa_endpoint_init_cfg(struct ipa_endpoint *endpoint) { u32 offset = IPA_REG_ENDP_INIT_CFG_N_OFFSET(endpoint->endpoint_id); + enum ipa_cs_offload_en enabled; u32 val = 0; /* FRAG_OFFLOAD_EN is 0 */ if (endpoint->data->checksum) { + enum ipa_version version = endpoint->ipa->version; + if (endpoint->toward_ipa) { u32 checksum_offset; - val |= u32_encode_bits(IPA_CS_OFFLOAD_UL, - CS_OFFLOAD_EN_FMASK); /* Checksum header offset is in 4-byte units */ checksum_offset = sizeof(struct rmnet_map_header); checksum_offset /= sizeof(u32); val |= u32_encode_bits(checksum_offset, CS_METADATA_HDR_OFFSET_FMASK); + + enabled = version < IPA_VERSION_4_5 + ? IPA_CS_OFFLOAD_UL + : IPA_CS_OFFLOAD_INLINE; } else { - val |= u32_encode_bits(IPA_CS_OFFLOAD_DL, - CS_OFFLOAD_EN_FMASK); + enabled = version < IPA_VERSION_4_5 + ? IPA_CS_OFFLOAD_DL + : IPA_CS_OFFLOAD_INLINE; } } else { - val |= u32_encode_bits(IPA_CS_OFFLOAD_NONE, - CS_OFFLOAD_EN_FMASK); + enabled = IPA_CS_OFFLOAD_NONE; } + val |= u32_encode_bits(enabled, CS_OFFLOAD_EN_FMASK); /* CS_GEN_QMB_MASTER_SEL is 0 */ iowrite32(val, endpoint->ipa->reg_virt + offset); @@ -498,6 +476,27 @@ static void ipa_endpoint_init_nat(struct ipa_endpoint *endpoint) iowrite32(val, endpoint->ipa->reg_virt + offset); } +static u32 +ipa_qmap_header_size(enum ipa_version version, struct ipa_endpoint *endpoint) +{ + u32 header_size = sizeof(struct rmnet_map_header); + + /* Without checksum offload, we just have the MAP header */ + if (!endpoint->data->checksum) + return header_size; + + if (version < IPA_VERSION_4_5) { + /* Checksum header inserted for AP TX endpoints only */ + if (endpoint->toward_ipa) + header_size += sizeof(struct rmnet_map_ul_csum_header); + } else { + /* Checksum header is used in both directions */ + header_size += sizeof(struct rmnet_map_v5_csum_header); + } + + return header_size; +} + /** * ipa_endpoint_init_hdr() - Initialize HDR endpoint configuration register * @endpoint: Endpoint pointer @@ -526,13 +525,11 @@ static void ipa_endpoint_init_hdr(struct ipa_endpoint *endpoint) u32 val = 0; if (endpoint->data->qmap) { - size_t header_size = sizeof(struct rmnet_map_header); enum ipa_version version = ipa->version; + size_t header_size; - /* We might supply a checksum header after the QMAP header */ - if (endpoint->toward_ipa && endpoint->data->checksum) - header_size += sizeof(struct rmnet_map_ul_csum_header); - val |= ipa_header_size_encoded(version, header_size); + header_size = ipa_qmap_header_size(version, endpoint); + val = ipa_header_size_encoded(version, header_size); /* Define how to fill fields in a received QMAP header */ if (!endpoint->toward_ipa) { @@ -1734,6 +1731,21 @@ int ipa_endpoint_config(struct ipa *ipa) u32 max; u32 val; + /* Prior to IPAv3.5, the FLAVOR_0 register was not supported. + * Furthermore, the endpoints were not grouped such that TX + * endpoint numbers started with 0 and RX endpoints had numbers + * higher than all TX endpoints, so we can't do the simple + * direction check used for newer hardware below. + * + * For hardware that doesn't support the FLAVOR_0 register, + * just set the available mask to support any endpoint, and + * assume the configuration is valid. + */ + if (ipa->version < IPA_VERSION_3_5) { + ipa->available = ~0; + return 0; + } + /* Find out about the endpoints supplied by the hardware, and ensure * the highest one doesn't exceed the number we support. */ diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index 9915603ed10b..9810c61a0320 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -31,6 +31,7 @@ #include "ipa_uc.h" #include "ipa_interrupt.h" #include "gsi_trans.h" +#include "ipa_sysfs.h" /** * DOC: The IP Accelerator @@ -399,16 +400,20 @@ static void ipa_hardware_config(struct ipa *ipa, const struct ipa_data *data) /* Implement some hardware workarounds */ if (version >= IPA_VERSION_4_0 && version < IPA_VERSION_4_5) { - /* Enable open global clocks (not needed for IPA v4.5) */ - val = GLOBAL_FMASK; - val |= GLOBAL_2X_CLK_FMASK; - iowrite32(val, ipa->reg_virt + IPA_REG_CLKON_CFG_OFFSET); - /* Disable PA mask to allow HOLB drop */ val = ioread32(ipa->reg_virt + IPA_REG_TX_CFG_OFFSET); val &= ~PA_MASK_EN_FMASK; iowrite32(val, ipa->reg_virt + IPA_REG_TX_CFG_OFFSET); + + /* Enable open global clocks in the CLKON configuration */ + val = GLOBAL_FMASK | GLOBAL_2X_CLK_FMASK; + } else if (version == IPA_VERSION_3_1) { + val = MISC_FMASK; /* Disable MISC clock gating */ + } else { + val = 0; /* No CLKON configuration needed */ } + if (val) + iowrite32(val, ipa->reg_virt + IPA_REG_CLKON_CFG_OFFSET); ipa_hardware_config_comp(ipa); @@ -529,6 +534,7 @@ static int ipa_firmware_load(struct device *dev) } ret = of_address_to_resource(node, 0, &res); + of_node_put(node); if (ret) { dev_err(dev, "error %d getting \"memory-region\" resource\n", ret); @@ -572,6 +578,10 @@ out_release_firmware: } static const struct of_device_id ipa_match[] = { + { + .compatible = "qcom,msm8998-ipa", + .data = &ipa_data_v3_1, + }, { .compatible = "qcom,sdm845-ipa", .data = &ipa_data_v3_5_1, @@ -639,6 +649,27 @@ static void ipa_validate_build(void) #endif /* IPA_VALIDATE */ } +static bool ipa_version_valid(enum ipa_version version) +{ + switch (version) { + case IPA_VERSION_3_0: + case IPA_VERSION_3_1: + case IPA_VERSION_3_5: + case IPA_VERSION_3_5_1: + case IPA_VERSION_4_0: + case IPA_VERSION_4_1: + case IPA_VERSION_4_2: + case IPA_VERSION_4_5: + case IPA_VERSION_4_7: + case IPA_VERSION_4_9: + case IPA_VERSION_4_11: + return true; + + default: + return false; + } +} + /** * ipa_probe() - IPA platform driver probe function * @pdev: Platform device pointer @@ -676,11 +707,15 @@ static int ipa_probe(struct platform_device *pdev) /* Get configuration data early; needed for clock initialization */ data = of_device_get_match_data(dev); if (!data) { - /* This is really IPA_VALIDATE (should never happen) */ dev_err(dev, "matched hardware not supported\n"); return -ENODEV; } + if (!ipa_version_valid(data->version)) { + dev_err(dev, "invalid IPA version\n"); + return -EINVAL; + } + /* If we need Trust Zone, make sure it's available */ modem_init = of_property_read_bool(dev->of_node, "modem-init"); if (!modem_init) @@ -881,6 +916,13 @@ static const struct dev_pm_ops ipa_pm_ops = { .resume = ipa_resume, }; +static const struct attribute_group *ipa_attribute_groups[] = { + &ipa_attribute_group, + &ipa_feature_attribute_group, + &ipa_modem_attribute_group, + NULL, +}; + static struct platform_driver ipa_driver = { .probe = ipa_probe, .remove = ipa_remove, @@ -889,6 +931,7 @@ static struct platform_driver ipa_driver = { .name = "ipa", .pm = &ipa_pm_ops, .of_match_table = ipa_match, + .dev_groups = ipa_attribute_groups, }, }; diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index 1624125e7459..4337b0920d3d 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -26,11 +26,26 @@ /* SMEM host id representing the modem. */ #define QCOM_SMEM_HOST_MODEM 1 +const struct ipa_mem *ipa_mem_find(struct ipa *ipa, enum ipa_mem_id mem_id) +{ + u32 i; + + for (i = 0; i < ipa->mem_count; i++) { + const struct ipa_mem *mem = &ipa->mem[i]; + + if (mem->id == mem_id) + return mem; + } + + return NULL; +} + /* Add an immediate command to a transaction that zeroes a memory region */ static void -ipa_mem_zero_region_add(struct gsi_trans *trans, const struct ipa_mem *mem) +ipa_mem_zero_region_add(struct gsi_trans *trans, enum ipa_mem_id mem_id) { struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi); + const struct ipa_mem *mem = ipa_mem_find(ipa, mem_id); dma_addr_t addr = ipa->zero_addr; if (!mem->size) @@ -60,6 +75,7 @@ ipa_mem_zero_region_add(struct gsi_trans *trans, const struct ipa_mem *mem) int ipa_mem_setup(struct ipa *ipa) { dma_addr_t addr = ipa->zero_addr; + const struct ipa_mem *mem; struct gsi_trans *trans; u32 offset; u16 size; @@ -74,39 +90,136 @@ int ipa_mem_setup(struct ipa *ipa) return -EBUSY; } - /* Initialize IPA-local header memory. The modem and AP header - * regions are contiguous, and initialized together. + /* Initialize IPA-local header memory. The AP header region, if + * present, is contiguous with and follows the modem header region, + * and they are initialized together. */ - offset = ipa->mem[IPA_MEM_MODEM_HEADER].offset; - size = ipa->mem[IPA_MEM_MODEM_HEADER].size; - size += ipa->mem[IPA_MEM_AP_HEADER].size; + mem = ipa_mem_find(ipa, IPA_MEM_MODEM_HEADER); + offset = mem->offset; + size = mem->size; + mem = ipa_mem_find(ipa, IPA_MEM_AP_HEADER); + if (mem) + size += mem->size; ipa_cmd_hdr_init_local_add(trans, offset, size, addr); - ipa_mem_zero_region_add(trans, &ipa->mem[IPA_MEM_MODEM_PROC_CTX]); - - ipa_mem_zero_region_add(trans, &ipa->mem[IPA_MEM_AP_PROC_CTX]); - - ipa_mem_zero_region_add(trans, &ipa->mem[IPA_MEM_MODEM]); + ipa_mem_zero_region_add(trans, IPA_MEM_MODEM_PROC_CTX); + ipa_mem_zero_region_add(trans, IPA_MEM_AP_PROC_CTX); + ipa_mem_zero_region_add(trans, IPA_MEM_MODEM); gsi_trans_commit_wait(trans); /* Tell the hardware where the processing context area is located */ - offset = ipa->mem_offset + ipa->mem[IPA_MEM_MODEM_PROC_CTX].offset; + mem = ipa_mem_find(ipa, IPA_MEM_MODEM_PROC_CTX); + offset = ipa->mem_offset + mem->offset; val = proc_cntxt_base_addr_encoded(ipa->version, offset); iowrite32(val, ipa->reg_virt + IPA_REG_LOCAL_PKT_PROC_CNTXT_OFFSET); return 0; } -#ifdef IPA_VALIDATE - -static bool ipa_mem_valid(struct ipa *ipa, enum ipa_mem_id mem_id) +/* Is the given memory region ID is valid for the current IPA version? */ +static bool ipa_mem_id_valid(struct ipa *ipa, enum ipa_mem_id mem_id) +{ + enum ipa_version version = ipa->version; + + switch (mem_id) { + case IPA_MEM_UC_SHARED: + case IPA_MEM_UC_INFO: + case IPA_MEM_V4_FILTER_HASHED: + case IPA_MEM_V4_FILTER: + case IPA_MEM_V6_FILTER_HASHED: + case IPA_MEM_V6_FILTER: + case IPA_MEM_V4_ROUTE_HASHED: + case IPA_MEM_V4_ROUTE: + case IPA_MEM_V6_ROUTE_HASHED: + case IPA_MEM_V6_ROUTE: + case IPA_MEM_MODEM_HEADER: + case IPA_MEM_AP_HEADER: + case IPA_MEM_MODEM_PROC_CTX: + case IPA_MEM_AP_PROC_CTX: + case IPA_MEM_MODEM: + case IPA_MEM_UC_EVENT_RING: + case IPA_MEM_PDN_CONFIG: + case IPA_MEM_STATS_QUOTA_MODEM: + case IPA_MEM_STATS_QUOTA_AP: + case IPA_MEM_END_MARKER: /* pseudo region */ + break; + + case IPA_MEM_STATS_TETHERING: + case IPA_MEM_STATS_DROP: + if (version < IPA_VERSION_4_0) + return false; + break; + + case IPA_MEM_STATS_V4_FILTER: + case IPA_MEM_STATS_V6_FILTER: + case IPA_MEM_STATS_V4_ROUTE: + case IPA_MEM_STATS_V6_ROUTE: + if (version < IPA_VERSION_4_0 || version > IPA_VERSION_4_2) + return false; + break; + + case IPA_MEM_NAT_TABLE: + case IPA_MEM_STATS_FILTER_ROUTE: + if (version < IPA_VERSION_4_5) + return false; + break; + + default: + return false; + } + + return true; +} + +/* Must the given memory region be present in the configuration? */ +static bool ipa_mem_id_required(struct ipa *ipa, enum ipa_mem_id mem_id) +{ + switch (mem_id) { + case IPA_MEM_UC_SHARED: + case IPA_MEM_UC_INFO: + case IPA_MEM_V4_FILTER_HASHED: + case IPA_MEM_V4_FILTER: + case IPA_MEM_V6_FILTER_HASHED: + case IPA_MEM_V6_FILTER: + case IPA_MEM_V4_ROUTE_HASHED: + case IPA_MEM_V4_ROUTE: + case IPA_MEM_V6_ROUTE_HASHED: + case IPA_MEM_V6_ROUTE: + case IPA_MEM_MODEM_HEADER: + case IPA_MEM_MODEM_PROC_CTX: + case IPA_MEM_AP_PROC_CTX: + case IPA_MEM_MODEM: + return true; + + case IPA_MEM_PDN_CONFIG: + case IPA_MEM_STATS_QUOTA_MODEM: + case IPA_MEM_STATS_TETHERING: + return ipa->version >= IPA_VERSION_4_0; + + default: + return false; /* Anything else is optional */ + } +} + +static bool ipa_mem_valid_one(struct ipa *ipa, const struct ipa_mem *mem) { - const struct ipa_mem *mem = &ipa->mem[mem_id]; struct device *dev = &ipa->pdev->dev; + enum ipa_mem_id mem_id = mem->id; u16 size_multiple; + /* Make sure the memory region is valid for this version of IPA */ + if (!ipa_mem_id_valid(ipa, mem_id)) { + dev_err(dev, "region id %u not valid\n", mem_id); + return false; + } + + if (!mem->size && !mem->canary_count) { + dev_err(dev, "empty memory region %u\n", mem_id); + return false; + } + /* Other than modem memory, sizes must be a multiple of 8 */ size_multiple = mem_id == IPA_MEM_MODEM ? 4 : 8; if (mem->size % size_multiple) @@ -117,23 +230,74 @@ static bool ipa_mem_valid(struct ipa *ipa, enum ipa_mem_id mem_id) else if (mem->offset < mem->canary_count * sizeof(__le32)) dev_err(dev, "region %u offset too small for %hu canaries\n", mem_id, mem->canary_count); - else if (mem->offset + mem->size > ipa->mem_size) - dev_err(dev, "region %u ends beyond memory limit (0x%08x)\n", - mem_id, ipa->mem_size); + else if (mem_id == IPA_MEM_END_MARKER && mem->size) + dev_err(dev, "non-zero end marker region size\n"); else return true; return false; } -#else /* !IPA_VALIDATE */ - -static bool ipa_mem_valid(struct ipa *ipa, enum ipa_mem_id mem_id) +/* Verify each defined memory region is valid. */ +static bool ipa_mem_valid(struct ipa *ipa, const struct ipa_mem_data *mem_data) { + DECLARE_BITMAP(regions, IPA_MEM_COUNT) = { }; + struct device *dev = &ipa->pdev->dev; + enum ipa_mem_id mem_id; + u32 i; + + if (mem_data->local_count > IPA_MEM_COUNT) { + dev_err(dev, "too many memory regions (%u > %u)\n", + mem_data->local_count, IPA_MEM_COUNT); + return false; + } + + for (i = 0; i < mem_data->local_count; i++) { + const struct ipa_mem *mem = &mem_data->local[i]; + + if (__test_and_set_bit(mem->id, regions)) { + dev_err(dev, "duplicate memory region %u\n", mem->id); + return false; + } + + /* Defined regions have non-zero size and/or canary count */ + if (!ipa_mem_valid_one(ipa, mem)) + return false; + } + + /* Now see if any required regions are not defined */ + for (mem_id = find_first_zero_bit(regions, IPA_MEM_COUNT); + mem_id < IPA_MEM_COUNT; + mem_id = find_next_zero_bit(regions, IPA_MEM_COUNT, mem_id + 1)) { + if (ipa_mem_id_required(ipa, mem_id)) + dev_err(dev, "required memory region %u missing\n", + mem_id); + } + return true; } -#endif /*! IPA_VALIDATE */ +/* Do all memory regions fit within the IPA local memory? */ +static bool ipa_mem_size_valid(struct ipa *ipa) +{ + struct device *dev = &ipa->pdev->dev; + u32 limit = ipa->mem_size; + u32 i; + + for (i = 0; i < ipa->mem_count; i++) { + const struct ipa_mem *mem = &ipa->mem[i]; + + if (mem->offset + mem->size <= limit) + continue; + + dev_err(dev, "region %u ends beyond memory limit (0x%08x)\n", + mem->id, limit); + + return false; + } + + return true; +} /** * ipa_mem_config() - Configure IPA shared memory @@ -144,11 +308,12 @@ static bool ipa_mem_valid(struct ipa *ipa, enum ipa_mem_id mem_id) int ipa_mem_config(struct ipa *ipa) { struct device *dev = &ipa->pdev->dev; - enum ipa_mem_id mem_id; + const struct ipa_mem *mem; dma_addr_t addr; u32 mem_size; void *virt; u32 val; + u32 i; /* Check the advertised location and size of the shared memory area */ val = ioread32(ipa->reg_virt + IPA_REG_SHARED_MEM_SIZE_OFFSET); @@ -168,6 +333,10 @@ int ipa_mem_config(struct ipa *ipa) mem_size); } + /* We know our memory size; make sure regions are all in range */ + if (!ipa_mem_size_valid(ipa)) + return -EINVAL; + /* Prealloc DMA memory for zeroing regions */ virt = dma_alloc_coherent(dev, IPA_MEM_MAX, &addr, GFP_KERNEL); if (!virt) @@ -176,29 +345,18 @@ int ipa_mem_config(struct ipa *ipa) ipa->zero_virt = virt; ipa->zero_size = IPA_MEM_MAX; - /* Verify each defined memory region is valid, and if indicated - * for the region, write "canary" values in the space prior to - * the region's base address. + /* For each defined region, write "canary" values in the + * space prior to the region's base address if indicated. */ - for (mem_id = 0; mem_id < ipa->mem_count; mem_id++) { - const struct ipa_mem *mem = &ipa->mem[mem_id]; - u16 canary_count; + for (i = 0; i < ipa->mem_count; i++) { + u16 canary_count = ipa->mem[i].canary_count; __le32 *canary; - /* Validate all regions (even undefined ones) */ - if (!ipa_mem_valid(ipa, mem_id)) - goto err_dma_free; - - /* Skip over undefined regions */ - if (!mem->offset && !mem->size) - continue; - - canary_count = mem->canary_count; if (!canary_count) continue; /* Write canary values in the space before the region */ - canary = ipa->mem_virt + ipa->mem_offset + mem->offset; + canary = ipa->mem_virt + ipa->mem_offset + ipa->mem[i].offset; do *--canary = IPA_MEM_CANARY_VAL; while (--canary_count); @@ -212,8 +370,9 @@ int ipa_mem_config(struct ipa *ipa) if (!ipa_cmd_data_valid(ipa)) goto err_dma_free; - /* Verify the microcontroller ring alignment (0 is OK too) */ - if (ipa->mem[IPA_MEM_UC_EVENT_RING].offset % 1024) { + /* Verify the microcontroller ring alignment (if defined) */ + mem = ipa_mem_find(ipa, IPA_MEM_UC_EVENT_RING); + if (mem && mem->offset % 1024) { dev_err(dev, "microcontroller ring not 1024-byte aligned\n"); goto err_dma_free; } @@ -261,11 +420,9 @@ int ipa_mem_zero_modem(struct ipa *ipa) return -EBUSY; } - ipa_mem_zero_region_add(trans, &ipa->mem[IPA_MEM_MODEM_HEADER]); - - ipa_mem_zero_region_add(trans, &ipa->mem[IPA_MEM_MODEM_PROC_CTX]); - - ipa_mem_zero_region_add(trans, &ipa->mem[IPA_MEM_MODEM]); + ipa_mem_zero_region_add(trans, IPA_MEM_MODEM_HEADER); + ipa_mem_zero_region_add(trans, IPA_MEM_MODEM_PROC_CTX); + ipa_mem_zero_region_add(trans, IPA_MEM_MODEM); gsi_trans_commit_wait(trans); @@ -380,7 +537,7 @@ static int ipa_smem_init(struct ipa *ipa, u32 item, size_t size) * (in this case, the modem). An allocation from SMEM is persistent * until the AP reboots; there is no way to free an allocated SMEM * region. Allocation only reserves the space; to use it you need - * to "get" a pointer it (this implies no reference counting). + * to "get" a pointer it (this does not imply reference counting). * The item might have already been allocated, in which case we * use it unless the size isn't what we expect. */ @@ -457,11 +614,12 @@ int ipa_mem_init(struct ipa *ipa, const struct ipa_mem_data *mem_data) struct resource *res; int ret; - if (mem_data->local_count > IPA_MEM_COUNT) { - dev_err(dev, "to many memory regions (%u > %u)\n", - mem_data->local_count, IPA_MEM_COUNT); + /* Make sure the set of defined memory regions is valid */ + if (!ipa_mem_valid(ipa, mem_data)) return -EINVAL; - } + + ipa->mem_count = mem_data->local_count; + ipa->mem = mem_data->local; ret = dma_set_mask_and_coherent(&ipa->pdev->dev, DMA_BIT_MASK(64)); if (ret) { @@ -486,10 +644,6 @@ int ipa_mem_init(struct ipa *ipa, const struct ipa_mem_data *mem_data) ipa->mem_addr = res->start; ipa->mem_size = resource_size(res); - /* The ipa->mem[] array is indexed by enum ipa_mem_id values */ - ipa->mem_count = mem_data->local_count; - ipa->mem = mem_data->local; - ret = ipa_imem_init(ipa, mem_data->imem_addr, mem_data->imem_size); if (ret) goto err_unmap; diff --git a/drivers/net/ipa/ipa_mem.h b/drivers/net/ipa/ipa_mem.h index a422aec69e5d..570bfdd99bff 100644 --- a/drivers/net/ipa/ipa_mem.h +++ b/drivers/net/ipa/ipa_mem.h @@ -54,37 +54,43 @@ enum ipa_mem_id { IPA_MEM_V6_ROUTE_HASHED, /* 2 canaries */ IPA_MEM_V6_ROUTE, /* 2 canaries */ IPA_MEM_MODEM_HEADER, /* 2 canaries */ - IPA_MEM_AP_HEADER, /* 0 canaries */ + IPA_MEM_AP_HEADER, /* 0 canaries, optional */ IPA_MEM_MODEM_PROC_CTX, /* 2 canaries */ IPA_MEM_AP_PROC_CTX, /* 0 canaries */ - IPA_MEM_NAT_TABLE, /* 4 canaries (IPA v4.5 and above) */ - IPA_MEM_PDN_CONFIG, /* 0/2 canaries (IPA v4.0 and above) */ - IPA_MEM_STATS_QUOTA_MODEM, /* 2/4 canaries (IPA v4.0 and above) */ - IPA_MEM_STATS_QUOTA_AP, /* 0 canaries (IPA v4.0 and above) */ - IPA_MEM_STATS_TETHERING, /* 0 canaries (IPA v4.0 and above) */ + IPA_MEM_MODEM, /* 0/2 canaries */ + IPA_MEM_UC_EVENT_RING, /* 1 canary, optional */ + IPA_MEM_PDN_CONFIG, /* 0/2 canaries (IPA v4.0+) */ + IPA_MEM_STATS_QUOTA_MODEM, /* 2/4 canaries (IPA v4.0+) */ + IPA_MEM_STATS_QUOTA_AP, /* 0 canaries, optional (IPA v4.0+) */ + IPA_MEM_STATS_TETHERING, /* 0 canaries (IPA v4.0+) */ + IPA_MEM_STATS_DROP, /* 0 canaries, optional (IPA v4.0+) */ + /* The next 5 filter and route statistics regions are optional */ IPA_MEM_STATS_V4_FILTER, /* 0 canaries (IPA v4.0-v4.2) */ IPA_MEM_STATS_V6_FILTER, /* 0 canaries (IPA v4.0-v4.2) */ IPA_MEM_STATS_V4_ROUTE, /* 0 canaries (IPA v4.0-v4.2) */ IPA_MEM_STATS_V6_ROUTE, /* 0 canaries (IPA v4.0-v4.2) */ - IPA_MEM_STATS_FILTER_ROUTE, /* 0 canaries (IPA v4.5 and above) */ - IPA_MEM_STATS_DROP, /* 0 canaries (IPA v4.0 and above) */ - IPA_MEM_MODEM, /* 0/2 canaries */ - IPA_MEM_UC_EVENT_RING, /* 1 canary */ + IPA_MEM_STATS_FILTER_ROUTE, /* 0 canaries (IPA v4.5+) */ + IPA_MEM_NAT_TABLE, /* 4 canaries, optional (IPA v4.5+) */ + IPA_MEM_END_MARKER, /* 1 canary (not a real region) */ IPA_MEM_COUNT, /* Number of regions (not an index) */ }; /** * struct ipa_mem - IPA local memory region description + * @id: memory region identifier * @offset: offset in IPA memory space to base of the region * @size: size in bytes base of the region * @canary_count: Number of 32-bit "canary" values that precede region */ struct ipa_mem { + enum ipa_mem_id id; u32 offset; u16 size; u16 canary_count; }; +const struct ipa_mem *ipa_mem_find(struct ipa *ipa, enum ipa_mem_id mem_id); + int ipa_mem_config(struct ipa *ipa); void ipa_mem_deconfig(struct ipa *ipa); diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c index 593665efbcf9..4661105ce7ab 100644 --- a/drivers/net/ipa/ipa_qmi.c +++ b/drivers/net/ipa/ipa_qmi.c @@ -298,32 +298,32 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi) req.platform_type_valid = 1; req.platform_type = IPA_QMI_PLATFORM_TYPE_MSM_ANDROID; - mem = &ipa->mem[IPA_MEM_MODEM_HEADER]; + mem = ipa_mem_find(ipa, IPA_MEM_MODEM_HEADER); if (mem->size) { req.hdr_tbl_info_valid = 1; req.hdr_tbl_info.start = ipa->mem_offset + mem->offset; req.hdr_tbl_info.end = req.hdr_tbl_info.start + mem->size - 1; } - mem = &ipa->mem[IPA_MEM_V4_ROUTE]; + mem = ipa_mem_find(ipa, IPA_MEM_V4_ROUTE); req.v4_route_tbl_info_valid = 1; req.v4_route_tbl_info.start = ipa->mem_offset + mem->offset; req.v4_route_tbl_info.count = mem->size / sizeof(__le64); - mem = &ipa->mem[IPA_MEM_V6_ROUTE]; + mem = ipa_mem_find(ipa, IPA_MEM_V6_ROUTE); req.v6_route_tbl_info_valid = 1; req.v6_route_tbl_info.start = ipa->mem_offset + mem->offset; req.v6_route_tbl_info.count = mem->size / sizeof(__le64); - mem = &ipa->mem[IPA_MEM_V4_FILTER]; + mem = ipa_mem_find(ipa, IPA_MEM_V4_FILTER); req.v4_filter_tbl_start_valid = 1; req.v4_filter_tbl_start = ipa->mem_offset + mem->offset; - mem = &ipa->mem[IPA_MEM_V6_FILTER]; + mem = ipa_mem_find(ipa, IPA_MEM_V6_FILTER); req.v6_filter_tbl_start_valid = 1; req.v6_filter_tbl_start = ipa->mem_offset + mem->offset; - mem = &ipa->mem[IPA_MEM_MODEM]; + mem = ipa_mem_find(ipa, IPA_MEM_MODEM); if (mem->size) { req.modem_mem_info_valid = 1; req.modem_mem_info.start = ipa->mem_offset + mem->offset; @@ -336,7 +336,7 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi) /* skip_uc_load_valid and skip_uc_load are set above */ - mem = &ipa->mem[IPA_MEM_MODEM_PROC_CTX]; + mem = ipa_mem_find(ipa, IPA_MEM_MODEM_PROC_CTX); if (mem->size) { req.hdr_proc_ctx_tbl_info_valid = 1; req.hdr_proc_ctx_tbl_info.start = @@ -347,7 +347,7 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi) /* Nothing to report for the compression table (zip_tbl_info) */ - mem = &ipa->mem[IPA_MEM_V4_ROUTE_HASHED]; + mem = ipa_mem_find(ipa, IPA_MEM_V4_ROUTE_HASHED); if (mem->size) { req.v4_hash_route_tbl_info_valid = 1; req.v4_hash_route_tbl_info.start = @@ -355,7 +355,7 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi) req.v4_hash_route_tbl_info.count = mem->size / sizeof(__le64); } - mem = &ipa->mem[IPA_MEM_V6_ROUTE_HASHED]; + mem = ipa_mem_find(ipa, IPA_MEM_V6_ROUTE_HASHED); if (mem->size) { req.v6_hash_route_tbl_info_valid = 1; req.v6_hash_route_tbl_info.start = @@ -363,22 +363,21 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi) req.v6_hash_route_tbl_info.count = mem->size / sizeof(__le64); } - mem = &ipa->mem[IPA_MEM_V4_FILTER_HASHED]; + mem = ipa_mem_find(ipa, IPA_MEM_V4_FILTER_HASHED); if (mem->size) { req.v4_hash_filter_tbl_start_valid = 1; req.v4_hash_filter_tbl_start = ipa->mem_offset + mem->offset; } - mem = &ipa->mem[IPA_MEM_V6_FILTER_HASHED]; + mem = ipa_mem_find(ipa, IPA_MEM_V6_FILTER_HASHED); if (mem->size) { req.v6_hash_filter_tbl_start_valid = 1; req.v6_hash_filter_tbl_start = ipa->mem_offset + mem->offset; } - /* None of the stats fields are valid (IPA v4.0 and above) */ - + /* The stats fields are only valid for IPA v4.0+ */ if (ipa->version >= IPA_VERSION_4_0) { - mem = &ipa->mem[IPA_MEM_STATS_QUOTA_MODEM]; + mem = ipa_mem_find(ipa, IPA_MEM_STATS_QUOTA_MODEM); if (mem->size) { req.hw_stats_quota_base_addr_valid = 1; req.hw_stats_quota_base_addr = @@ -387,8 +386,9 @@ init_modem_driver_req(struct ipa_qmi *ipa_qmi) req.hw_stats_quota_size = ipa->mem_offset + mem->size; } - mem = &ipa->mem[IPA_MEM_STATS_DROP]; - if (mem->size) { + /* If the DROP stats region is defined, include it */ + mem = ipa_mem_find(ipa, IPA_MEM_STATS_DROP); + if (mem && mem->size) { req.hw_stats_drop_base_addr_valid = 1; req.hw_stats_drop_base_addr = ipa->mem_offset + mem->offset; diff --git a/drivers/net/ipa/ipa_reg.h b/drivers/net/ipa/ipa_reg.h index 286ea9634c49..b89dec5865a5 100644 --- a/drivers/net/ipa/ipa_reg.h +++ b/drivers/net/ipa/ipa_reg.h @@ -368,6 +368,7 @@ enum ipa_cs_offload_en { IPA_CS_OFFLOAD_NONE = 0x0, IPA_CS_OFFLOAD_UL = 0x1, /* Before IPA v4.5 (TX) */ IPA_CS_OFFLOAD_DL = 0x2, /* Before IPA v4.5 (RX) */ + IPA_CS_OFFLOAD_INLINE = 0x1, /* IPA v4.5 (TX and RX) */ }; /* Valid only for TX (IPA consumer) endpoints */ diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c index a5f7a79a1923..cf709df70d28 100644 --- a/drivers/net/ipa/ipa_smp2p.c +++ b/drivers/net/ipa/ipa_smp2p.c @@ -176,11 +176,8 @@ static int ipa_smp2p_irq_init(struct ipa_smp2p *smp2p, const char *name, int ret; ret = platform_get_irq_byname(smp2p->ipa->pdev, name); - if (ret <= 0) { - dev_err(dev, "DT error %d getting \"%s\" IRQ property\n", - ret, name); + if (ret <= 0) return ret ? : -EINVAL; - } irq = ret; ret = request_threaded_irq(irq, NULL, handler, 0, name, smp2p); diff --git a/drivers/net/ipa/ipa_sysfs.c b/drivers/net/ipa/ipa_sysfs.c new file mode 100644 index 000000000000..ff61dbdd70d8 --- /dev/null +++ b/drivers/net/ipa/ipa_sysfs.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Copyright (C) 2021 Linaro Ltd. */ + +#include +#include +#include +#include + +#include "ipa.h" +#include "ipa_version.h" +#include "ipa_sysfs.h" + +static const char *ipa_version_string(struct ipa *ipa) +{ + switch (ipa->version) { + case IPA_VERSION_3_0: + return "3.0"; + case IPA_VERSION_3_1: + return "3.1"; + case IPA_VERSION_3_5: + return "3.5"; + case IPA_VERSION_3_5_1: + return "3.5.1"; + case IPA_VERSION_4_0: + return "4.0"; + case IPA_VERSION_4_1: + return "4.1"; + case IPA_VERSION_4_2: + return "4.2"; + case IPA_VERSION_4_5: + return "4.5"; + case IPA_VERSION_4_7: + return "4.7"; + case IPA_VERSION_4_9: + return "4.9"; + case IPA_VERSION_4_11: + return "4.11"; + default: + return "0.0"; /* Won't happen (checked at probe time) */ + } +} + +static ssize_t +version_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct ipa *ipa = dev_get_drvdata(dev); + + return scnprintf(buf, PAGE_SIZE, "%s\n", ipa_version_string(ipa)); +} + +static DEVICE_ATTR_RO(version); + +static struct attribute *ipa_attrs[] = { + &dev_attr_version.attr, + NULL +}; + +const struct attribute_group ipa_attribute_group = { + .attrs = ipa_attrs, +}; + +static const char *ipa_offload_string(struct ipa *ipa) +{ + return ipa->version < IPA_VERSION_4_5 ? "MAPv4" : "MAPv5"; +} + +static ssize_t rx_offload_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ipa *ipa = dev_get_drvdata(dev); + + return scnprintf(buf, PAGE_SIZE, "%s\n", ipa_offload_string(ipa)); +} + +static DEVICE_ATTR_RO(rx_offload); + +static ssize_t tx_offload_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ipa *ipa = dev_get_drvdata(dev); + + return scnprintf(buf, PAGE_SIZE, "%s\n", ipa_offload_string(ipa)); +} + +static DEVICE_ATTR_RO(tx_offload); + +static struct attribute *ipa_feature_attrs[] = { + &dev_attr_rx_offload.attr, + &dev_attr_tx_offload.attr, + NULL +}; + +const struct attribute_group ipa_feature_attribute_group = { + .name = "feature", + .attrs = ipa_feature_attrs, +}; + +static ssize_t +ipa_endpoint_id_show(struct ipa *ipa, char *buf, enum ipa_endpoint_name name) +{ + u32 endpoint_id = ipa->name_map[name]->endpoint_id; + + return scnprintf(buf, PAGE_SIZE, "%u\n", endpoint_id); +} + +static ssize_t rx_endpoint_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ipa *ipa = dev_get_drvdata(dev); + + return ipa_endpoint_id_show(ipa, buf, IPA_ENDPOINT_AP_MODEM_RX); +} + +static DEVICE_ATTR_RO(rx_endpoint_id); + +static ssize_t tx_endpoint_id_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ipa *ipa = dev_get_drvdata(dev); + + return ipa_endpoint_id_show(ipa, buf, IPA_ENDPOINT_AP_MODEM_TX); +} + +static DEVICE_ATTR_RO(tx_endpoint_id); + +static struct attribute *ipa_modem_attrs[] = { + &dev_attr_rx_endpoint_id.attr, + &dev_attr_tx_endpoint_id.attr, + NULL +}; + +const struct attribute_group ipa_modem_attribute_group = { + .name = "modem", + .attrs = ipa_modem_attrs, +}; diff --git a/drivers/net/ipa/ipa_sysfs.h b/drivers/net/ipa/ipa_sysfs.h new file mode 100644 index 000000000000..b34e5650bf8c --- /dev/null +++ b/drivers/net/ipa/ipa_sysfs.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved. + * Copyright (C) 2019-2021 Linaro Ltd. + */ +#ifndef _IPA_SYSFS_H_ +#define _IPA_SYSFS_H_ + +struct attribute_group; + +extern const struct attribute_group ipa_attribute_group; +extern const struct attribute_group ipa_feature_attribute_group; +extern const struct attribute_group ipa_modem_attribute_group; + +#endif /* _IPA_SYSFS_H_ */ diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index 3168d72f4245..c617a9156f26 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -150,29 +150,16 @@ static void ipa_table_validate_build(void) } static bool -ipa_table_valid_one(struct ipa *ipa, bool route, bool ipv6, bool hashed) +ipa_table_valid_one(struct ipa *ipa, enum ipa_mem_id mem_id, bool route) { + const struct ipa_mem *mem = ipa_mem_find(ipa, mem_id); struct device *dev = &ipa->pdev->dev; - const struct ipa_mem *mem; u32 size; - if (route) { - if (ipv6) - mem = hashed ? &ipa->mem[IPA_MEM_V6_ROUTE_HASHED] - : &ipa->mem[IPA_MEM_V6_ROUTE]; - else - mem = hashed ? &ipa->mem[IPA_MEM_V4_ROUTE_HASHED] - : &ipa->mem[IPA_MEM_V4_ROUTE]; + if (route) size = IPA_ROUTE_COUNT_MAX * sizeof(__le64); - } else { - if (ipv6) - mem = hashed ? &ipa->mem[IPA_MEM_V6_FILTER_HASHED] - : &ipa->mem[IPA_MEM_V6_FILTER]; - else - mem = hashed ? &ipa->mem[IPA_MEM_V4_FILTER_HASHED] - : &ipa->mem[IPA_MEM_V4_FILTER]; + else size = (1 + IPA_FILTER_COUNT_MAX) * sizeof(__le64); - } if (!ipa_cmd_table_valid(ipa, mem, route, ipv6, hashed)) return false; @@ -185,9 +172,8 @@ ipa_table_valid_one(struct ipa *ipa, bool route, bool ipv6, bool hashed) if (hashed && !mem->size) return true; - dev_err(dev, "IPv%c %s%s table region size 0x%02x, expected 0x%02x\n", - ipv6 ? '6' : '4', hashed ? "hashed " : "", - route ? "route" : "filter", mem->size, size); + dev_err(dev, "%s table region %u size 0x%02x, expected 0x%02x\n", + route ? "route" : "filter", mem_id, mem->size, size); return false; } @@ -195,16 +181,16 @@ ipa_table_valid_one(struct ipa *ipa, bool route, bool ipv6, bool hashed) /* Verify the filter and route table memory regions are the expected size */ bool ipa_table_valid(struct ipa *ipa) { - bool valid = true; + bool valid; - valid = valid && ipa_table_valid_one(ipa, false, false, false); - valid = valid && ipa_table_valid_one(ipa, false, false, true); - valid = valid && ipa_table_valid_one(ipa, false, true, false); - valid = valid && ipa_table_valid_one(ipa, false, true, true); - valid = valid && ipa_table_valid_one(ipa, true, false, false); - valid = valid && ipa_table_valid_one(ipa, true, false, true); - valid = valid && ipa_table_valid_one(ipa, true, true, false); - valid = valid && ipa_table_valid_one(ipa, true, true, true); + valid = ipa_table_valid_one(IPA_MEM_V4_FILTER, false); + valid = valid && ipa_table_valid_one(IPA_MEM_V4_FILTER_HASHED, false); + valid = valid && ipa_table_valid_one(IPA_MEM_V6_FILTER, false); + valid = valid && ipa_table_valid_one(IPA_MEM_V6_FILTER_HASHED, false); + valid = valid && ipa_table_valid_one(IPA_MEM_V4_ROUTE, true); + valid = valid && ipa_table_valid_one(IPA_MEM_V4_ROUTE_HASHED, true); + valid = valid && ipa_table_valid_one(IPA_MEM_V6_ROUTE, true); + valid = valid && ipa_table_valid_one(IPA_MEM_V6_ROUTE_HASHED, true); return valid; } @@ -256,14 +242,15 @@ static dma_addr_t ipa_table_addr(struct ipa *ipa, bool filter_mask, u16 count) } static void ipa_table_reset_add(struct gsi_trans *trans, bool filter, - u16 first, u16 count, const struct ipa_mem *mem) + u16 first, u16 count, enum ipa_mem_id mem_id) { struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi); + const struct ipa_mem *mem = ipa_mem_find(ipa, mem_id); dma_addr_t addr; u32 offset; u16 size; - /* Nothing to do if the table memory regions is empty */ + /* Nothing to do if the table memory region is empty */ if (!mem->size) return; @@ -282,16 +269,13 @@ static void ipa_table_reset_add(struct gsi_trans *trans, bool filter, * for the IPv4 and IPv6 non-hashed and hashed filter tables. */ static int -ipa_filter_reset_table(struct ipa *ipa, const struct ipa_mem *mem, bool modem) +ipa_filter_reset_table(struct ipa *ipa, enum ipa_mem_id mem_id, bool modem) { u32 ep_mask = ipa->filter_map; u32 count = hweight32(ep_mask); struct gsi_trans *trans; enum gsi_ee_id ee_id; - if (!mem->size) - return 0; - trans = ipa_cmd_trans_alloc(ipa, count); if (!trans) { dev_err(&ipa->pdev->dev, @@ -311,7 +295,7 @@ ipa_filter_reset_table(struct ipa *ipa, const struct ipa_mem *mem, bool modem) if (endpoint->ee_id != ee_id) continue; - ipa_table_reset_add(trans, true, endpoint_id, 1, mem); + ipa_table_reset_add(trans, true, endpoint_id, 1, mem_id); } gsi_trans_commit_wait(trans); @@ -327,20 +311,18 @@ static int ipa_filter_reset(struct ipa *ipa, bool modem) { int ret; - ret = ipa_filter_reset_table(ipa, &ipa->mem[IPA_MEM_V4_FILTER], modem); + ret = ipa_filter_reset_table(ipa, IPA_MEM_V4_FILTER, modem); if (ret) return ret; - ret = ipa_filter_reset_table(ipa, &ipa->mem[IPA_MEM_V4_FILTER_HASHED], - modem); + ret = ipa_filter_reset_table(ipa, IPA_MEM_V4_FILTER_HASHED, modem); if (ret) return ret; - ret = ipa_filter_reset_table(ipa, &ipa->mem[IPA_MEM_V6_FILTER], modem); + ret = ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER, modem); if (ret) return ret; - ret = ipa_filter_reset_table(ipa, &ipa->mem[IPA_MEM_V6_FILTER_HASHED], - modem); + ret = ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER_HASHED, modem); return ret; } @@ -371,15 +353,13 @@ static int ipa_route_reset(struct ipa *ipa, bool modem) count = IPA_ROUTE_AP_COUNT; } + ipa_table_reset_add(trans, false, first, count, IPA_MEM_V4_ROUTE); ipa_table_reset_add(trans, false, first, count, - &ipa->mem[IPA_MEM_V4_ROUTE]); - ipa_table_reset_add(trans, false, first, count, - &ipa->mem[IPA_MEM_V4_ROUTE_HASHED]); + IPA_MEM_V4_ROUTE_HASHED); + ipa_table_reset_add(trans, false, first, count, IPA_MEM_V6_ROUTE); ipa_table_reset_add(trans, false, first, count, - &ipa->mem[IPA_MEM_V6_ROUTE]); - ipa_table_reset_add(trans, false, first, count, - &ipa->mem[IPA_MEM_V6_ROUTE_HASHED]); + IPA_MEM_V6_ROUTE_HASHED); gsi_trans_commit_wait(trans); @@ -433,10 +413,12 @@ int ipa_table_hash_flush(struct ipa *ipa) static void ipa_table_init_add(struct gsi_trans *trans, bool filter, enum ipa_cmd_opcode opcode, - const struct ipa_mem *mem, - const struct ipa_mem *hash_mem) + enum ipa_mem_id mem_id, + enum ipa_mem_id hash_mem_id) { struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi); + const struct ipa_mem *hash_mem = ipa_mem_find(ipa, hash_mem_id); + const struct ipa_mem *mem = ipa_mem_find(ipa, mem_id); dma_addr_t hash_addr; dma_addr_t addr; u16 hash_count; @@ -477,20 +459,16 @@ int ipa_table_setup(struct ipa *ipa) } ipa_table_init_add(trans, false, IPA_CMD_IP_V4_ROUTING_INIT, - &ipa->mem[IPA_MEM_V4_ROUTE], - &ipa->mem[IPA_MEM_V4_ROUTE_HASHED]); + IPA_MEM_V4_ROUTE, IPA_MEM_V4_ROUTE_HASHED); ipa_table_init_add(trans, false, IPA_CMD_IP_V6_ROUTING_INIT, - &ipa->mem[IPA_MEM_V6_ROUTE], - &ipa->mem[IPA_MEM_V6_ROUTE_HASHED]); + IPA_MEM_V6_ROUTE, IPA_MEM_V6_ROUTE_HASHED); ipa_table_init_add(trans, true, IPA_CMD_IP_V4_FILTER_INIT, - &ipa->mem[IPA_MEM_V4_FILTER], - &ipa->mem[IPA_MEM_V4_FILTER_HASHED]); + IPA_MEM_V4_FILTER, IPA_MEM_V4_FILTER_HASHED); ipa_table_init_add(trans, true, IPA_CMD_IP_V6_FILTER_INIT, - &ipa->mem[IPA_MEM_V6_FILTER], - &ipa->mem[IPA_MEM_V6_FILTER_HASHED]); + IPA_MEM_V6_FILTER, IPA_MEM_V6_FILTER_HASHED); gsi_trans_commit_wait(trans); diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c index 2756363e6938..fd9219863234 100644 --- a/drivers/net/ipa/ipa_uc.c +++ b/drivers/net/ipa/ipa_uc.c @@ -116,7 +116,8 @@ enum ipa_uc_event { static struct ipa_uc_mem_area *ipa_uc_shared(struct ipa *ipa) { - u32 offset = ipa->mem_offset + ipa->mem[IPA_MEM_UC_SHARED].offset; + const struct ipa_mem *mem = ipa_mem_find(ipa, IPA_MEM_UC_SHARED); + u32 offset = ipa->mem_offset + mem->offset; return ipa->mem_virt + offset; } diff --git a/drivers/net/ipa/ipa_version.h b/drivers/net/ipa/ipa_version.h index ee2b3d02f3cd..6c16c895d842 100644 --- a/drivers/net/ipa/ipa_version.h +++ b/drivers/net/ipa/ipa_version.h @@ -21,6 +21,8 @@ * @IPA_VERSION_4_11: IPA version 4.11/GSI version 2.11 (2.1.1) * * Defines the version of IPA (and GSI) hardware present on the platform. + * Please update ipa_version_valid() and ipa_version_string() whenever a + * new version is added. */ enum ipa_version { IPA_VERSION_3_0, diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 92425e1fd70c..93dc48b9b4f2 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1819,7 +1819,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) ctx.sa.rx_sa = rx_sa; ctx.secy = secy; memcpy(ctx.sa.key, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), - MACSEC_KEYID_LEN); + secy->key_len); err = macsec_offload(ops->mdo_add_rxsa, &ctx); if (err) @@ -2061,7 +2061,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) ctx.sa.tx_sa = tx_sa; ctx.secy = secy; memcpy(ctx.sa.key, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), - MACSEC_KEYID_LEN); + secy->key_len); err = macsec_offload(ops->mdo_add_txsa, &ctx); if (err) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 1b998aa481f8..80de9768ecd4 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1781,7 +1781,7 @@ static int macvlan_device_event(struct notifier_block *unused, unregister_netdevice_many(&list_kill); break; case NETDEV_PRE_TYPE_CHANGE: - /* Forbid underlaying device to change its type. */ + /* Forbid underlying device to change its type. */ return NOTIFY_BAD; case NETDEV_NOTIFY_PEERS: diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig index d06e06f5e31a..99a6c13a11af 100644 --- a/drivers/net/mdio/Kconfig +++ b/drivers/net/mdio/Kconfig @@ -19,6 +19,13 @@ config MDIO_BUS reflects whether the mdio_bus/mdio_device code is built as a loadable module or built-in. +config FWNODE_MDIO + def_tristate PHYLIB + depends on (ACPI || OF) || COMPILE_TEST + select FIXED_PHY + help + FWNODE MDIO bus (Ethernet PHY) accessors + config OF_MDIO def_tristate PHYLIB depends on OF @@ -27,6 +34,13 @@ config OF_MDIO help OpenFirmware MDIO bus (Ethernet PHY) accessors +config ACPI_MDIO + def_tristate PHYLIB + depends on ACPI + depends on PHYLIB + help + ACPI MDIO bus (Ethernet PHY) accessors + if MDIO_BUS config MDIO_DEVRES diff --git a/drivers/net/mdio/Makefile b/drivers/net/mdio/Makefile index c3ec0ef989df..15f8dc4042ce 100644 --- a/drivers/net/mdio/Makefile +++ b/drivers/net/mdio/Makefile @@ -1,7 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for Linux MDIO bus drivers -obj-$(CONFIG_OF_MDIO) += of_mdio.o +obj-$(CONFIG_ACPI_MDIO) += acpi_mdio.o +obj-$(CONFIG_FWNODE_MDIO) += fwnode_mdio.o +obj-$(CONFIG_OF_MDIO) += of_mdio.o obj-$(CONFIG_MDIO_ASPEED) += mdio-aspeed.o obj-$(CONFIG_MDIO_BCM_IPROC) += mdio-bcm-iproc.o diff --git a/drivers/net/mdio/acpi_mdio.c b/drivers/net/mdio/acpi_mdio.c new file mode 100644 index 000000000000..d77c987fda9c --- /dev/null +++ b/drivers/net/mdio/acpi_mdio.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * ACPI helpers for the MDIO (Ethernet PHY) API + * + * This file provides helper functions for extracting PHY device information + * out of the ACPI ASL and using it to populate an mii_bus. + */ + +#include +#include +#include +#include +#include +#include +#include + +MODULE_AUTHOR("Calvin Johnson "); +MODULE_LICENSE("GPL"); + +/** + * acpi_mdiobus_register - Register mii_bus and create PHYs from the ACPI ASL. + * @mdio: pointer to mii_bus structure + * @fwnode: pointer to fwnode of MDIO bus. This fwnode is expected to represent + * an ACPI device object corresponding to the MDIO bus and its children are + * expected to correspond to the PHY devices on that bus. + * + * This function registers the mii_bus structure and registers a phy_device + * for each child node of @fwnode. + */ +int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) +{ + struct fwnode_handle *child; + u32 addr; + int ret; + + /* Mask out all PHYs from auto probing. */ + mdio->phy_mask = GENMASK(31, 0); + ret = mdiobus_register(mdio); + if (ret) + return ret; + + ACPI_COMPANION_SET(&mdio->dev, to_acpi_device_node(fwnode)); + + /* Loop over the child nodes and register a phy_device for each PHY */ + fwnode_for_each_child_node(fwnode, child) { + ret = acpi_get_local_address(ACPI_HANDLE_FWNODE(child), &addr); + if (ret || addr >= PHY_MAX_ADDR) + continue; + + ret = fwnode_mdiobus_register_phy(mdio, child, addr); + if (ret == -ENODEV) + dev_err(&mdio->dev, + "MDIO device at address %d is missing.\n", + addr); + } + return 0; +} +EXPORT_SYMBOL(acpi_mdiobus_register); diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c new file mode 100644 index 000000000000..1becb1a731f6 --- /dev/null +++ b/drivers/net/mdio/fwnode_mdio.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * fwnode helpers for the MDIO (Ethernet PHY) API + * + * This file provides helper functions for extracting PHY device information + * out of the fwnode and using it to populate an mii_bus. + */ + +#include +#include +#include +#include + +MODULE_AUTHOR("Calvin Johnson "); +MODULE_LICENSE("GPL"); + +static struct mii_timestamper * +fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) +{ + struct of_phandle_args arg; + int err; + + if (is_acpi_node(fwnode)) + return NULL; + + err = of_parse_phandle_with_fixed_args(to_of_node(fwnode), + "timestamper", 1, 0, &arg); + if (err == -ENOENT) + return NULL; + else if (err) + return ERR_PTR(err); + + if (arg.args_count != 1) + return ERR_PTR(-EINVAL); + + return register_mii_timestamper(arg.np, arg.args[0]); +} + +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr) +{ + int rc; + + rc = fwnode_irq_get(child, 0); + if (rc == -EPROBE_DEFER) + return rc; + + if (rc > 0) { + phy->irq = rc; + mdio->irq[addr] = rc; + } else { + phy->irq = mdio->irq[addr]; + } + + if (fwnode_property_read_bool(child, "broken-turn-around")) + mdio->phy_ignore_ta_mask |= 1 << addr; + + fwnode_property_read_u32(child, "reset-assert-us", + &phy->mdio.reset_assert_delay); + fwnode_property_read_u32(child, "reset-deassert-us", + &phy->mdio.reset_deassert_delay); + + /* Associate the fwnode with the device structure so it + * can be looked up later + */ + fwnode_handle_get(child); + device_set_node(&phy->mdio.dev, child); + + /* All data is now stored in the phy struct; + * register it + */ + rc = phy_device_register(phy); + if (rc) { + fwnode_handle_put(child); + return rc; + } + + dev_dbg(&mdio->dev, "registered phy %p fwnode at address %i\n", + child, addr); + return 0; +} +EXPORT_SYMBOL(fwnode_mdiobus_phy_device_register); + +int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, u32 addr) +{ + struct mii_timestamper *mii_ts = NULL; + struct phy_device *phy; + bool is_c45 = false; + u32 phy_id; + int rc; + + mii_ts = fwnode_find_mii_timestamper(child); + if (IS_ERR(mii_ts)) + return PTR_ERR(mii_ts); + + rc = fwnode_property_match_string(child, "compatible", + "ethernet-phy-ieee802.3-c45"); + if (rc >= 0) + is_c45 = true; + + if (is_c45 || fwnode_get_phy_id(child, &phy_id)) + phy = get_phy_device(bus, addr, is_c45); + else + phy = phy_device_create(bus, addr, phy_id, 0, NULL); + if (IS_ERR(phy)) { + unregister_mii_timestamper(mii_ts); + return PTR_ERR(phy); + } + + if (is_acpi_node(child)) { + phy->irq = bus->irq[addr]; + + /* Associate the fwnode with the device structure so it + * can be looked up later. + */ + phy->mdio.dev.fwnode = child; + + /* All data is now stored in the phy struct, so register it */ + rc = phy_device_register(phy); + if (rc) { + phy_device_free(phy); + fwnode_handle_put(phy->mdio.dev.fwnode); + return rc; + } + } else if (is_of_node(child)) { + rc = fwnode_mdiobus_phy_device_register(bus, phy, child, addr); + if (rc) { + unregister_mii_timestamper(mii_ts); + phy_device_free(phy); + return rc; + } + } + + /* phy->mii_ts may already be defined by the PHY driver. A + * mii_timestamper probed via the device tree will still have + * precedence. + */ + if (mii_ts) + phy->mii_ts = mii_ts; + return 0; +} +EXPORT_SYMBOL(fwnode_mdiobus_register_phy); diff --git a/drivers/net/mdio/mdio-bcm-unimac.c b/drivers/net/mdio/mdio-bcm-unimac.c index 5d171e7f118d..bfc9be23c973 100644 --- a/drivers/net/mdio/mdio-bcm-unimac.c +++ b/drivers/net/mdio/mdio-bcm-unimac.c @@ -203,7 +203,7 @@ static void unimac_mdio_clk_set(struct unimac_mdio_priv *priv) return; } - /* The MDIO clock is the reference clock (typicaly 250Mhz) divided by + /* The MDIO clock is the reference clock (typically 250Mhz) divided by * 2 x (MDIO_CLK_DIV + 1) */ reg = unimac_mdio_readl(priv, MDIO_CFG); diff --git a/drivers/net/mdio/mdio-ipq8064.c b/drivers/net/mdio/mdio-ipq8064.c index 8fe8f0119fc1..bd1aea2d5a26 100644 --- a/drivers/net/mdio/mdio-ipq8064.c +++ b/drivers/net/mdio/mdio-ipq8064.c @@ -7,33 +7,33 @@ #include #include -#include #include #include -#include +#include #include #include /* MII address register definitions */ -#define MII_ADDR_REG_ADDR 0x10 -#define MII_BUSY BIT(0) -#define MII_WRITE BIT(1) -#define MII_CLKRANGE_60_100M (0 << 2) -#define MII_CLKRANGE_100_150M (1 << 2) -#define MII_CLKRANGE_20_35M (2 << 2) -#define MII_CLKRANGE_35_60M (3 << 2) -#define MII_CLKRANGE_150_250M (4 << 2) -#define MII_CLKRANGE_250_300M (5 << 2) +#define MII_ADDR_REG_ADDR 0x10 +#define MII_BUSY BIT(0) +#define MII_WRITE BIT(1) +#define MII_CLKRANGE(x) ((x) << 2) +#define MII_CLKRANGE_60_100M MII_CLKRANGE(0) +#define MII_CLKRANGE_100_150M MII_CLKRANGE(1) +#define MII_CLKRANGE_20_35M MII_CLKRANGE(2) +#define MII_CLKRANGE_35_60M MII_CLKRANGE(3) +#define MII_CLKRANGE_150_250M MII_CLKRANGE(4) +#define MII_CLKRANGE_250_300M MII_CLKRANGE(5) #define MII_CLKRANGE_MASK GENMASK(4, 2) #define MII_REG_SHIFT 6 #define MII_REG_MASK GENMASK(10, 6) #define MII_ADDR_SHIFT 11 #define MII_ADDR_MASK GENMASK(15, 11) -#define MII_DATA_REG_ADDR 0x14 +#define MII_DATA_REG_ADDR 0x14 -#define MII_MDIO_DELAY_USEC (1000) -#define MII_MDIO_RETRY_MSEC (10) +#define MII_MDIO_DELAY_USEC (1000) +#define MII_MDIO_RETRY_MSEC (10) struct ipq8064_mdio { struct regmap *base; /* NSS_GMAC0_BASE */ @@ -65,7 +65,7 @@ ipq8064_mdio_read(struct mii_bus *bus, int phy_addr, int reg_offset) ((reg_offset << MII_REG_SHIFT) & MII_REG_MASK); regmap_write(priv->base, MII_ADDR_REG_ADDR, miiaddr); - usleep_range(8, 10); + usleep_range(10, 13); err = ipq8064_mdio_wait_busy(priv); if (err) @@ -91,19 +91,46 @@ ipq8064_mdio_write(struct mii_bus *bus, int phy_addr, int reg_offset, u16 data) ((reg_offset << MII_REG_SHIFT) & MII_REG_MASK); regmap_write(priv->base, MII_ADDR_REG_ADDR, miiaddr); - usleep_range(8, 10); + + /* For the specific reg 31 extra time is needed or the next + * read will produce garbage data. + */ + if (reg_offset == 31) + usleep_range(30, 43); + else + usleep_range(10, 13); return ipq8064_mdio_wait_busy(priv); } +static const struct regmap_config ipq8064_mdio_regmap_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .can_multi_write = false, + /* the mdio lock is used by any user of this mdio driver */ + .disable_locking = true, + + .cache_type = REGCACHE_NONE, +}; + static int ipq8064_mdio_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct ipq8064_mdio *priv; + struct resource res; struct mii_bus *bus; + void __iomem *base; int ret; + if (of_address_to_resource(np, 0, &res)) + return -ENOMEM; + + base = ioremap(res.start, resource_size(&res)); + if (!base) + return -ENOMEM; + bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*priv)); if (!bus) return -ENOMEM; @@ -115,15 +142,10 @@ ipq8064_mdio_probe(struct platform_device *pdev) bus->parent = &pdev->dev; priv = bus->priv; - priv->base = device_node_to_regmap(np); - if (IS_ERR(priv->base)) { - if (priv->base == ERR_PTR(-EPROBE_DEFER)) - return -EPROBE_DEFER; - - dev_err(&pdev->dev, "error getting device regmap, error=%pe\n", - priv->base); + priv->base = devm_regmap_init_mmio(&pdev->dev, base, + &ipq8064_mdio_regmap_config); + if (IS_ERR(priv->base)) return PTR_ERR(priv->base); - } ret = of_mdiobus_register(bus, np); if (ret) diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index b36e5ea04ddf..2d67e12c8262 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -139,10 +139,6 @@ static int mscc_miim_probe(struct platform_device *pdev) struct mscc_miim_dev *dev; int ret; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENODEV; - bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*dev)); if (!bus) return -ENOMEM; @@ -155,7 +151,7 @@ static int mscc_miim_probe(struct platform_device *pdev) bus->parent = &pdev->dev; dev = bus->priv; - dev->regs = devm_ioremap_resource(&pdev->dev, res); + dev->regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(dev->regs)) { dev_err(&pdev->dev, "Unable to map MIIM registers\n"); return PTR_ERR(dev->regs); diff --git a/drivers/net/mdio/mdio-mux-bcm-iproc.c b/drivers/net/mdio/mdio-mux-bcm-iproc.c index 03261e6b9ceb..014c0baedbd2 100644 --- a/drivers/net/mdio/mdio-mux-bcm-iproc.c +++ b/drivers/net/mdio/mdio-mux-bcm-iproc.c @@ -65,7 +65,7 @@ static void mdio_mux_iproc_config(struct iproc_mdiomux_desc *md) writel(val, md->base + MDIO_SCAN_CTRL_OFFSET); if (md->core_clk) { - /* use rate adjust regs to derrive the mdio's operating + /* use rate adjust regs to derive the mdio's operating * frequency from the specified core clock */ divisor = clk_get_rate(md->core_clk) / MDIO_OPERATING_FREQUENCY; @@ -187,7 +187,9 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev) return -ENOMEM; md->dev = &pdev->dev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + md->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); + if (IS_ERR(md->base)) + return PTR_ERR(md->base); if (res->start & 0xfff) { /* For backward compatibility in case the * base address is specified with an offset. @@ -196,9 +198,6 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev) res->start &= ~0xfff; res->end = res->start + MDIO_REG_ADDR_SPACE_SIZE - 1; } - md->base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(md->base)) - return PTR_ERR(md->base); md->mii_bus = devm_mdiobus_alloc(&pdev->dev); if (!md->mii_bus) { diff --git a/drivers/net/mdio/mdio-mux-meson-g12a.c b/drivers/net/mdio/mdio-mux-meson-g12a.c index bf86c9c7a288..b8866bc3f2e8 100644 --- a/drivers/net/mdio/mdio-mux-meson-g12a.c +++ b/drivers/net/mdio/mdio-mux-meson-g12a.c @@ -95,7 +95,7 @@ static int g12a_ephy_pll_enable(struct clk_hw *hw) /* Poll on the digital lock instead of the usual analog lock * This is done because bit 31 is unreliable on some SoC. Bit - * 31 may indicate that the PLL is not lock eventhough the clock + * 31 may indicate that the PLL is not lock even though the clock * is actually running */ return readl_poll_timeout(pll->base + ETH_PLL_CTL0, val, diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 094494a68ddf..9e3c815a070f 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include @@ -29,128 +30,28 @@ MODULE_LICENSE("GPL"); * ethernet-phy-idAAAA.BBBB */ static int of_get_phy_id(struct device_node *device, u32 *phy_id) { - struct property *prop; - const char *cp; - unsigned int upper, lower; - - of_property_for_each_string(device, "compatible", prop, cp) { - if (sscanf(cp, "ethernet-phy-id%4x.%4x", &upper, &lower) == 2) { - *phy_id = ((upper & 0xFFFF) << 16) | (lower & 0xFFFF); - return 0; - } - } - return -EINVAL; -} - -static struct mii_timestamper *of_find_mii_timestamper(struct device_node *node) -{ - struct of_phandle_args arg; - int err; - - err = of_parse_phandle_with_fixed_args(node, "timestamper", 1, 0, &arg); - - if (err == -ENOENT) - return NULL; - else if (err) - return ERR_PTR(err); - - if (arg.args_count != 1) - return ERR_PTR(-EINVAL); - - return register_mii_timestamper(arg.np, arg.args[0]); + return fwnode_get_phy_id(of_fwnode_handle(device), phy_id); } int of_mdiobus_phy_device_register(struct mii_bus *mdio, struct phy_device *phy, - struct device_node *child, u32 addr) + struct device_node *child, u32 addr) { - int rc; - - rc = of_irq_get(child, 0); - if (rc == -EPROBE_DEFER) - return rc; - - if (rc > 0) { - phy->irq = rc; - mdio->irq[addr] = rc; - } else { - phy->irq = mdio->irq[addr]; - } - - if (of_property_read_bool(child, "broken-turn-around")) - mdio->phy_ignore_ta_mask |= 1 << addr; - - of_property_read_u32(child, "reset-assert-us", - &phy->mdio.reset_assert_delay); - of_property_read_u32(child, "reset-deassert-us", - &phy->mdio.reset_deassert_delay); - - /* Associate the OF node with the device structure so it - * can be looked up later */ - of_node_get(child); - phy->mdio.dev.of_node = child; - phy->mdio.dev.fwnode = of_fwnode_handle(child); - - /* All data is now stored in the phy struct; - * register it */ - rc = phy_device_register(phy); - if (rc) { - of_node_put(child); - return rc; - } - - dev_dbg(&mdio->dev, "registered phy %pOFn at address %i\n", - child, addr); - return 0; + return fwnode_mdiobus_phy_device_register(mdio, phy, + of_fwnode_handle(child), + addr); } EXPORT_SYMBOL(of_mdiobus_phy_device_register); static int of_mdiobus_register_phy(struct mii_bus *mdio, struct device_node *child, u32 addr) { - struct mii_timestamper *mii_ts; - struct phy_device *phy; - bool is_c45; - int rc; - u32 phy_id; - - mii_ts = of_find_mii_timestamper(child); - if (IS_ERR(mii_ts)) - return PTR_ERR(mii_ts); - - is_c45 = of_device_is_compatible(child, - "ethernet-phy-ieee802.3-c45"); - - if (!is_c45 && !of_get_phy_id(child, &phy_id)) - phy = phy_device_create(mdio, addr, phy_id, 0, NULL); - else - phy = get_phy_device(mdio, addr, is_c45); - if (IS_ERR(phy)) { - if (mii_ts) - unregister_mii_timestamper(mii_ts); - return PTR_ERR(phy); - } - - rc = of_mdiobus_phy_device_register(mdio, phy, child, addr); - if (rc) { - if (mii_ts) - unregister_mii_timestamper(mii_ts); - phy_device_free(phy); - return rc; - } - - /* phy->mii_ts may already be defined by the PHY driver. A - * mii_timestamper probed via the device tree will still have - * precedence. - */ - if (mii_ts) - phy->mii_ts = mii_ts; - - return 0; + return fwnode_mdiobus_register_phy(mdio, of_fwnode_handle(child), addr); } static int of_mdiobus_register_device(struct mii_bus *mdio, struct device_node *child, u32 addr) { + struct fwnode_handle *fwnode = of_fwnode_handle(child); struct mdio_device *mdiodev; int rc; @@ -161,9 +62,8 @@ static int of_mdiobus_register_device(struct mii_bus *mdio, /* Associate the OF node with the device structure so it * can be looked up later. */ - of_node_get(child); - mdiodev->dev.of_node = child; - mdiodev->dev.fwnode = of_fwnode_handle(child); + fwnode_handle_get(fwnode); + device_set_node(&mdiodev->dev, fwnode); /* All data is now stored in the mdiodev struct; register it. */ rc = mdio_device_register(mdiodev); @@ -262,8 +162,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) * the device tree are populated after the bus has been registered */ mdio->phy_mask = ~0; - mdio->dev.of_node = np; - mdio->dev.fwnode = of_fwnode_handle(np); + device_set_node(&mdio->dev, of_fwnode_handle(np)); /* Get bus level PHY reset GPIO details */ mdio->reset_delay_us = DEFAULT_GPIO_RESET_DELAY; @@ -347,16 +246,7 @@ EXPORT_SYMBOL(of_mdiobus_register); */ struct mdio_device *of_mdio_find_device(struct device_node *np) { - struct device *d; - - if (!np) - return NULL; - - d = bus_find_device_by_of_node(&mdio_bus_type, np); - if (!d) - return NULL; - - return to_mdio_device(d); + return fwnode_mdio_find_device(of_fwnode_handle(np)); } EXPORT_SYMBOL(of_mdio_find_device); @@ -369,18 +259,7 @@ EXPORT_SYMBOL(of_mdio_find_device); */ struct phy_device *of_phy_find_device(struct device_node *phy_np) { - struct mdio_device *mdiodev; - - mdiodev = of_mdio_find_device(phy_np); - if (!mdiodev) - return NULL; - - if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY) - return to_phy_device(&mdiodev->dev); - - put_device(&mdiodev->dev); - - return NULL; + return fwnode_phy_find_device(of_fwnode_handle(phy_np)); } EXPORT_SYMBOL(of_phy_find_device); @@ -466,7 +345,7 @@ EXPORT_SYMBOL(of_phy_get_and_connect); * of_phy_is_fixed_link() and of_phy_register_fixed_link() must * support two DT bindings: * - the old DT binding, where 'fixed-link' was a property with 5 - * cells encoding various informations about the fixed PHY + * cells encoding various information about the fixed PHY * - the new DT binding, where 'fixed-link' is a sub-node of the * Ethernet device. */ diff --git a/drivers/net/mhi/net.c b/drivers/net/mhi/net.c index b806f2f8f859..e60e38c1f09d 100644 --- a/drivers/net/mhi/net.c +++ b/drivers/net/mhi/net.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "mhi.h" @@ -18,6 +19,12 @@ #define MHI_NET_MAX_MTU 0xffff #define MHI_NET_DEFAULT_MTU 0x4000 +/* When set to false, the default netdev (link 0) is not created, and it's up + * to user to create the link (via wwan rtnetlink). + */ +static bool create_default_iface = true; +module_param(create_default_iface, bool, 0); + struct mhi_device_info { const char *netname; const struct mhi_net_proto *proto; @@ -25,7 +32,7 @@ struct mhi_device_info { static int mhi_ndo_open(struct net_device *ndev) { - struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev); /* Feed the rx buffer pool */ schedule_delayed_work(&mhi_netdev->rx_refill, 0); @@ -40,7 +47,7 @@ static int mhi_ndo_open(struct net_device *ndev) static int mhi_ndo_stop(struct net_device *ndev) { - struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev); netif_stop_queue(ndev); netif_carrier_off(ndev); @@ -51,7 +58,7 @@ static int mhi_ndo_stop(struct net_device *ndev) static netdev_tx_t mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev) { - struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev); const struct mhi_net_proto *proto = mhi_netdev->proto; struct mhi_device *mdev = mhi_netdev->mdev; int err; @@ -86,7 +93,7 @@ exit_drop: static void mhi_ndo_get_stats64(struct net_device *ndev, struct rtnl_link_stats64 *stats) { - struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev); unsigned int start; do { @@ -295,32 +302,33 @@ static void mhi_net_rx_refill_work(struct work_struct *work) schedule_delayed_work(&mhi_netdev->rx_refill, HZ / 2); } -static struct device_type wwan_type = { - .name = "wwan", -}; - -static int mhi_net_probe(struct mhi_device *mhi_dev, - const struct mhi_device_id *id) +static int mhi_net_newlink(void *ctxt, struct net_device *ndev, u32 if_id, + struct netlink_ext_ack *extack) { - const struct mhi_device_info *info = (struct mhi_device_info *)id->driver_data; - struct device *dev = &mhi_dev->dev; + const struct mhi_device_info *info; + struct mhi_device *mhi_dev = ctxt; struct mhi_net_dev *mhi_netdev; - struct net_device *ndev; int err; - ndev = alloc_netdev(sizeof(*mhi_netdev), info->netname, - NET_NAME_PREDICTABLE, mhi_net_setup); - if (!ndev) - return -ENOMEM; + info = (struct mhi_device_info *)mhi_dev->id->driver_data; - mhi_netdev = netdev_priv(ndev); - dev_set_drvdata(dev, mhi_netdev); + /* For now we only support one link (link context 0), driver must be + * reworked to break 1:1 relationship for net MBIM and to forward setup + * call to rmnet(QMAP) otherwise. + */ + if (if_id != 0) + return -EINVAL; + + if (dev_get_drvdata(&mhi_dev->dev)) + return -EBUSY; + + mhi_netdev = wwan_netdev_drvpriv(ndev); + + dev_set_drvdata(&mhi_dev->dev, mhi_netdev); mhi_netdev->ndev = ndev; mhi_netdev->mdev = mhi_dev; mhi_netdev->skbagg_head = NULL; mhi_netdev->proto = info->proto; - SET_NETDEV_DEV(ndev, &mhi_dev->dev); - SET_NETDEV_DEVTYPE(ndev, &wwan_type); INIT_DELAYED_WORK(&mhi_netdev->rx_refill, mhi_net_rx_refill_work); u64_stats_init(&mhi_netdev->stats.rx_syncp); @@ -334,7 +342,10 @@ static int mhi_net_probe(struct mhi_device *mhi_dev, /* Number of transfer descriptors determines size of the queue */ mhi_netdev->rx_queue_sz = mhi_get_free_desc_count(mhi_dev, DMA_FROM_DEVICE); - err = register_netdev(ndev); + if (extack) + err = register_netdevice(ndev); + else + err = register_netdev(ndev); if (err) goto out_err; @@ -347,23 +358,89 @@ static int mhi_net_probe(struct mhi_device *mhi_dev, return 0; out_err_proto: - unregister_netdev(ndev); + unregister_netdevice(ndev); out_err: free_netdev(ndev); return err; } +static void mhi_net_dellink(void *ctxt, struct net_device *ndev, + struct list_head *head) +{ + struct mhi_net_dev *mhi_netdev = wwan_netdev_drvpriv(ndev); + struct mhi_device *mhi_dev = ctxt; + + if (head) + unregister_netdevice_queue(ndev, head); + else + unregister_netdev(ndev); + + mhi_unprepare_from_transfer(mhi_dev); + + kfree_skb(mhi_netdev->skbagg_head); + + dev_set_drvdata(&mhi_dev->dev, NULL); +} + +static const struct wwan_ops mhi_wwan_ops = { + .priv_size = sizeof(struct mhi_net_dev), + .setup = mhi_net_setup, + .newlink = mhi_net_newlink, + .dellink = mhi_net_dellink, +}; + +static int mhi_net_probe(struct mhi_device *mhi_dev, + const struct mhi_device_id *id) +{ + const struct mhi_device_info *info = (struct mhi_device_info *)id->driver_data; + struct mhi_controller *cntrl = mhi_dev->mhi_cntrl; + struct net_device *ndev; + int err; + + err = wwan_register_ops(&cntrl->mhi_dev->dev, &mhi_wwan_ops, mhi_dev, + WWAN_NO_DEFAULT_LINK); + if (err) + return err; + + if (!create_default_iface) + return 0; + + /* Create a default interface which is used as either RMNET real-dev, + * MBIM link 0 or ip link 0) + */ + ndev = alloc_netdev(sizeof(struct mhi_net_dev), info->netname, + NET_NAME_PREDICTABLE, mhi_net_setup); + if (!ndev) { + err = -ENOMEM; + goto err_unregister; + } + + SET_NETDEV_DEV(ndev, &mhi_dev->dev); + + err = mhi_net_newlink(mhi_dev, ndev, 0, NULL); + if (err) + goto err_release; + + return 0; + +err_release: + free_netdev(ndev); +err_unregister: + wwan_unregister_ops(&cntrl->mhi_dev->dev); + + return err; +} + static void mhi_net_remove(struct mhi_device *mhi_dev) { struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev); + struct mhi_controller *cntrl = mhi_dev->mhi_cntrl; - unregister_netdev(mhi_netdev->ndev); + /* WWAN core takes care of removing remaining links */ + wwan_unregister_ops(&cntrl->mhi_dev->dev); - mhi_unprepare_from_transfer(mhi_netdev->mdev); - - kfree_skb(mhi_netdev->skbagg_head); - - free_netdev(mhi_netdev->ndev); + if (create_default_iface) + mhi_net_dellink(mhi_dev, mhi_netdev->ndev, NULL); } static const struct mhi_device_info mhi_hwip0 = { diff --git a/drivers/net/mhi/proto_mbim.c b/drivers/net/mhi/proto_mbim.c index fc72b3f6ec9e..bf1ad863237d 100644 --- a/drivers/net/mhi/proto_mbim.c +++ b/drivers/net/mhi/proto_mbim.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -56,7 +57,7 @@ static void __mbim_errors_inc(struct mhi_net_dev *dev) static int mbim_rx_verify_nth16(struct sk_buff *skb) { - struct mhi_net_dev *dev = netdev_priv(skb->dev); + struct mhi_net_dev *dev = wwan_netdev_drvpriv(skb->dev); struct mbim_context *ctx = dev->proto_data; struct usb_cdc_ncm_nth16 *nth16; int len; @@ -102,7 +103,7 @@ static int mbim_rx_verify_nth16(struct sk_buff *skb) static int mbim_rx_verify_ndp16(struct sk_buff *skb, struct usb_cdc_ncm_ndp16 *ndp16) { - struct mhi_net_dev *dev = netdev_priv(skb->dev); + struct mhi_net_dev *dev = wwan_netdev_drvpriv(skb->dev); int ret; if (le16_to_cpu(ndp16->wLength) < USB_CDC_NCM_NDP16_LENGTH_MIN) { diff --git a/drivers/net/mii.c b/drivers/net/mii.c index e71ebb933266..779c3a96dba7 100644 --- a/drivers/net/mii.c +++ b/drivers/net/mii.c @@ -81,7 +81,7 @@ int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd) bmcr = mii->mdio_read(dev, mii->phy_id, MII_BMCR); bmsr = mii->mdio_read(dev, mii->phy_id, MII_BMSR); if (mii->supports_gmii) { - ctrl1000 = mii->mdio_read(dev, mii->phy_id, MII_CTRL1000); + ctrl1000 = mii->mdio_read(dev, mii->phy_id, MII_CTRL1000); stat1000 = mii->mdio_read(dev, mii->phy_id, MII_STAT1000); } diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c index 0e9511661601..ccec29970d5b 100644 --- a/drivers/net/netdevsim/bus.c +++ b/drivers/net/netdevsim/bus.c @@ -27,21 +27,34 @@ static struct nsim_bus_dev *to_nsim_bus_dev(struct device *dev) static int nsim_bus_dev_vfs_enable(struct nsim_bus_dev *nsim_bus_dev, unsigned int num_vfs) { - nsim_bus_dev->vfconfigs = kcalloc(num_vfs, - sizeof(struct nsim_vf_config), - GFP_KERNEL | __GFP_NOWARN); + struct nsim_dev *nsim_dev; + int err = 0; + + if (nsim_bus_dev->max_vfs < num_vfs) + return -ENOMEM; + if (!nsim_bus_dev->vfconfigs) return -ENOMEM; nsim_bus_dev->num_vfs = num_vfs; - return 0; + nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev); + if (nsim_esw_mode_is_switchdev(nsim_dev)) { + err = nsim_esw_switchdev_enable(nsim_dev, NULL); + if (err) + nsim_bus_dev->num_vfs = 0; + } + + return err; } -static void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev) +void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev) { - kfree(nsim_bus_dev->vfconfigs); - nsim_bus_dev->vfconfigs = NULL; + struct nsim_dev *nsim_dev; + nsim_bus_dev->num_vfs = 0; + nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev); + if (nsim_esw_mode_is_switchdev(nsim_dev)) + nsim_esw_legacy_enable(nsim_dev, NULL); } static ssize_t @@ -56,7 +69,7 @@ nsim_bus_dev_numvfs_store(struct device *dev, struct device_attribute *attr, if (ret) return ret; - rtnl_lock(); + mutex_lock(&nsim_bus_dev->vfs_lock); if (nsim_bus_dev->num_vfs == num_vfs) goto exit_good; if (nsim_bus_dev->num_vfs && num_vfs) { @@ -74,7 +87,7 @@ nsim_bus_dev_numvfs_store(struct device *dev, struct device_attribute *attr, exit_good: ret = count; exit_unlock: - rtnl_unlock(); + mutex_unlock(&nsim_bus_dev->vfs_lock); return ret; } @@ -92,6 +105,79 @@ static struct device_attribute nsim_bus_dev_numvfs_attr = __ATTR(sriov_numvfs, 0664, nsim_bus_dev_numvfs_show, nsim_bus_dev_numvfs_store); +ssize_t nsim_bus_dev_max_vfs_read(struct file *file, + char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_bus_dev *nsim_bus_dev = file->private_data; + char buf[11]; + ssize_t len; + + len = snprintf(buf, sizeof(buf), "%u\n", nsim_bus_dev->max_vfs); + if (len < 0) + return len; + + return simple_read_from_buffer(data, count, ppos, buf, len); +} + +ssize_t nsim_bus_dev_max_vfs_write(struct file *file, + const char __user *data, + size_t count, loff_t *ppos) +{ + struct nsim_bus_dev *nsim_bus_dev = file->private_data; + struct nsim_vf_config *vfconfigs; + ssize_t ret; + char buf[10]; + u32 val; + + if (*ppos != 0) + return 0; + + if (count >= sizeof(buf)) + return -ENOSPC; + + mutex_lock(&nsim_bus_dev->vfs_lock); + /* Reject if VFs are configured */ + if (nsim_bus_dev->num_vfs) { + ret = -EBUSY; + goto unlock; + } + + ret = copy_from_user(buf, data, count); + if (ret) { + ret = -EFAULT; + goto unlock; + } + + buf[count] = '\0'; + ret = kstrtouint(buf, 10, &val); + if (ret) { + ret = -EIO; + goto unlock; + } + + /* max_vfs limited by the maximum number of provided port indexes */ + if (val > NSIM_DEV_VF_PORT_INDEX_MAX - NSIM_DEV_VF_PORT_INDEX_BASE) { + ret = -ERANGE; + goto unlock; + } + + vfconfigs = kcalloc(val, sizeof(struct nsim_vf_config), GFP_KERNEL | __GFP_NOWARN); + if (!vfconfigs) { + ret = -ENOMEM; + goto unlock; + } + + kfree(nsim_bus_dev->vfconfigs); + nsim_bus_dev->vfconfigs = vfconfigs; + nsim_bus_dev->max_vfs = val; + *ppos += count; + ret = count; +unlock: + mutex_unlock(&nsim_bus_dev->vfs_lock); + return ret; +} + static ssize_t new_port_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -113,7 +199,7 @@ new_port_store(struct device *dev, struct device_attribute *attr, mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock); devlink_reload_disable(devlink); - ret = nsim_dev_port_add(nsim_bus_dev, port_index); + ret = nsim_dev_port_add(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index); devlink_reload_enable(devlink); mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock); return ret ? ret : count; @@ -142,7 +228,7 @@ del_port_store(struct device *dev, struct device_attribute *attr, mutex_lock(&nsim_bus_dev->nsim_bus_reload_lock); devlink_reload_disable(devlink); - ret = nsim_dev_port_del(nsim_bus_dev, port_index); + ret = nsim_dev_port_del(nsim_bus_dev, NSIM_DEV_PORT_TYPE_PF, port_index); devlink_reload_enable(devlink); mutex_unlock(&nsim_bus_dev->nsim_bus_reload_lock); return ret ? ret : count; @@ -168,9 +254,6 @@ static const struct attribute_group *nsim_bus_dev_attr_groups[] = { static void nsim_bus_dev_release(struct device *dev) { - struct nsim_bus_dev *nsim_bus_dev = to_nsim_bus_dev(dev); - - nsim_bus_dev_vfs_disable(nsim_bus_dev); } static struct device_type nsim_bus_dev_type = { @@ -311,6 +394,8 @@ static struct bus_type nsim_bus = { .num_vf = nsim_num_vf, }; +#define NSIM_BUS_DEV_MAX_VFS 4 + static struct nsim_bus_dev * nsim_bus_dev_new(unsigned int id, unsigned int port_count) { @@ -329,15 +414,28 @@ nsim_bus_dev_new(unsigned int id, unsigned int port_count) nsim_bus_dev->dev.type = &nsim_bus_dev_type; nsim_bus_dev->port_count = port_count; nsim_bus_dev->initial_net = current->nsproxy->net_ns; + nsim_bus_dev->max_vfs = NSIM_BUS_DEV_MAX_VFS; mutex_init(&nsim_bus_dev->nsim_bus_reload_lock); + mutex_init(&nsim_bus_dev->vfs_lock); /* Disallow using nsim_bus_dev */ smp_store_release(&nsim_bus_dev->init, false); + nsim_bus_dev->vfconfigs = kcalloc(nsim_bus_dev->max_vfs, + sizeof(struct nsim_vf_config), + GFP_KERNEL | __GFP_NOWARN); + if (!nsim_bus_dev->vfconfigs) { + err = -ENOMEM; + goto err_nsim_bus_dev_id_free; + } + err = device_register(&nsim_bus_dev->dev); if (err) - goto err_nsim_bus_dev_id_free; + goto err_nsim_vfs_free; + return nsim_bus_dev; +err_nsim_vfs_free: + kfree(nsim_bus_dev->vfconfigs); err_nsim_bus_dev_id_free: ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id); err_nsim_bus_dev_free: @@ -351,6 +449,7 @@ static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev) smp_store_release(&nsim_bus_dev->init, false); device_unregister(&nsim_bus_dev->dev); ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id); + kfree(nsim_bus_dev->vfconfigs); kfree(nsim_bus_dev); } diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 6189a4c0d39e..6348307bfa84 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -35,6 +35,25 @@ #include "netdevsim.h" +static unsigned int +nsim_dev_port_index(enum nsim_dev_port_type type, unsigned int port_index) +{ + switch (type) { + case NSIM_DEV_PORT_TYPE_VF: + port_index = NSIM_DEV_VF_PORT_INDEX_BASE + port_index; + break; + case NSIM_DEV_PORT_TYPE_PF: + break; + } + + return port_index; +} + +static inline unsigned int nsim_dev_port_index_to_vf_index(unsigned int port_index) +{ + return port_index - NSIM_DEV_VF_PORT_INDEX_BASE; +} + static struct dentry *nsim_dev_ddir; #define NSIM_DEV_DUMMY_REGION_SIZE (1024 * 32) @@ -192,9 +211,18 @@ static const struct file_operations nsim_dev_trap_fa_cookie_fops = { .owner = THIS_MODULE, }; +static const struct file_operations nsim_dev_max_vfs_fops = { + .open = simple_open, + .read = nsim_bus_dev_max_vfs_read, + .write = nsim_bus_dev_max_vfs_write, + .llseek = generic_file_llseek, + .owner = THIS_MODULE, +}; + static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) { char dev_ddir_name[sizeof(DRV_NAME) + 10]; + int err; sprintf(dev_ddir_name, DRV_NAME "%u", nsim_dev->nsim_bus_dev->dev.id); nsim_dev->ddir = debugfs_create_dir(dev_ddir_name, nsim_dev_ddir); @@ -231,30 +259,84 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) debugfs_create_bool("fail_trap_policer_counter_get", 0600, nsim_dev->ddir, &nsim_dev->fail_trap_policer_counter_get); + nsim_dev->max_vfs = debugfs_create_file("max_vfs", + 0600, + nsim_dev->ddir, + nsim_dev->nsim_bus_dev, + &nsim_dev_max_vfs_fops); + nsim_dev->nodes_ddir = debugfs_create_dir("rate_nodes", nsim_dev->ddir); + if (IS_ERR(nsim_dev->nodes_ddir)) { + err = PTR_ERR(nsim_dev->nodes_ddir); + goto err_out; + } + debugfs_create_bool("fail_trap_drop_counter_get", 0600, + nsim_dev->ddir, + &nsim_dev->fail_trap_drop_counter_get); nsim_udp_tunnels_debugfs_create(nsim_dev); return 0; + +err_out: + debugfs_remove_recursive(nsim_dev->ports_ddir); + debugfs_remove_recursive(nsim_dev->ddir); + return err; } static void nsim_dev_debugfs_exit(struct nsim_dev *nsim_dev) { + debugfs_remove_recursive(nsim_dev->nodes_ddir); debugfs_remove_recursive(nsim_dev->ports_ddir); debugfs_remove_recursive(nsim_dev->ddir); } +static ssize_t nsim_dev_rate_parent_read(struct file *file, + char __user *data, + size_t count, loff_t *ppos) +{ + char **name_ptr = file->private_data; + size_t len; + + if (!*name_ptr) + return 0; + + len = strlen(*name_ptr); + return simple_read_from_buffer(data, count, ppos, *name_ptr, len); +} + +static const struct file_operations nsim_dev_rate_parent_fops = { + .open = simple_open, + .read = nsim_dev_rate_parent_read, + .llseek = generic_file_llseek, + .owner = THIS_MODULE, +}; + static int nsim_dev_port_debugfs_init(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) { + struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev; + unsigned int port_index = nsim_dev_port->port_index; char port_ddir_name[16]; char dev_link_name[32]; - sprintf(port_ddir_name, "%u", nsim_dev_port->port_index); + sprintf(port_ddir_name, "%u", port_index); nsim_dev_port->ddir = debugfs_create_dir(port_ddir_name, nsim_dev->ports_ddir); if (IS_ERR(nsim_dev_port->ddir)) return PTR_ERR(nsim_dev_port->ddir); - sprintf(dev_link_name, "../../../" DRV_NAME "%u", - nsim_dev->nsim_bus_dev->dev.id); + sprintf(dev_link_name, "../../../" DRV_NAME "%u", nsim_bus_dev->dev.id); + if (nsim_dev_port_is_vf(nsim_dev_port)) { + unsigned int vf_id = nsim_dev_port_index_to_vf_index(port_index); + + debugfs_create_u16("tx_share", 0400, nsim_dev_port->ddir, + &nsim_bus_dev->vfconfigs[vf_id].min_tx_rate); + debugfs_create_u16("tx_max", 0400, nsim_dev_port->ddir, + &nsim_bus_dev->vfconfigs[vf_id].max_tx_rate); + nsim_dev_port->rate_parent = debugfs_create_file("rate_parent", + 0400, + nsim_dev_port->ddir, + &nsim_dev_port->parent_name, + &nsim_dev_rate_parent_fops); + } debugfs_create_symlink("dev", nsim_dev_port->ddir, dev_link_name); return 0; @@ -407,6 +489,74 @@ static void nsim_dev_dummy_region_exit(struct nsim_dev *nsim_dev) devlink_region_destroy(nsim_dev->dummy_region); } +static void __nsim_dev_port_del(struct nsim_dev_port *nsim_dev_port); +int nsim_esw_legacy_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack) +{ + struct devlink *devlink = priv_to_devlink(nsim_dev); + struct nsim_dev_port *nsim_dev_port, *tmp; + + devlink_rate_nodes_destroy(devlink); + mutex_lock(&nsim_dev->port_list_lock); + list_for_each_entry_safe(nsim_dev_port, tmp, &nsim_dev->port_list, list) + if (nsim_dev_port_is_vf(nsim_dev_port)) + __nsim_dev_port_del(nsim_dev_port); + mutex_unlock(&nsim_dev->port_list_lock); + nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY; + return 0; +} + +int nsim_esw_switchdev_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack) +{ + struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev; + int i, err; + + for (i = 0; i < nsim_bus_dev->num_vfs; i++) { + err = nsim_dev_port_add(nsim_bus_dev, NSIM_DEV_PORT_TYPE_VF, i); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to initialize VFs' netdevsim ports"); + pr_err("Failed to initialize VF id=%d. %d.\n", i, err); + goto err_port_add_vfs; + } + } + nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_SWITCHDEV; + return 0; + +err_port_add_vfs: + for (i--; i >= 0; i--) + nsim_dev_port_del(nsim_bus_dev, NSIM_DEV_PORT_TYPE_VF, i); + return err; +} + +static int nsim_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + int err = 0; + + mutex_lock(&nsim_dev->nsim_bus_dev->vfs_lock); + if (mode == nsim_dev->esw_mode) + goto unlock; + + if (mode == DEVLINK_ESWITCH_MODE_LEGACY) + err = nsim_esw_legacy_enable(nsim_dev, extack); + else if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) + err = nsim_esw_switchdev_enable(nsim_dev, extack); + else + err = -EINVAL; + +unlock: + mutex_unlock(&nsim_dev->nsim_bus_dev->vfs_lock); + return err; +} + +static int nsim_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + + *mode = nsim_dev->esw_mode; + return 0; +} + struct nsim_trap_item { void *trap_ctx; enum devlink_trap_action action; @@ -416,6 +566,7 @@ struct nsim_trap_data { struct delayed_work trap_report_dw; struct nsim_trap_item *trap_items_arr; u64 *trap_policers_cnt_arr; + u64 trap_pkt_cnt; struct nsim_dev *nsim_dev; spinlock_t trap_lock; /* Protects trap_items_arr */ }; @@ -892,7 +1043,190 @@ nsim_dev_devlink_trap_policer_counter_get(struct devlink *devlink, return 0; } +#define NSIM_LINK_SPEED_MAX 5000 /* Mbps */ +#define NSIM_LINK_SPEED_UNIT 125000 /* 1 Mbps given in bytes/sec to avoid + * u64 overflow during conversion from + * bytes to bits. + */ + +static int nsim_rate_bytes_to_units(char *name, u64 *rate, struct netlink_ext_ack *extack) +{ + u64 val; + u32 rem; + + val = div_u64_rem(*rate, NSIM_LINK_SPEED_UNIT, &rem); + if (rem) { + pr_err("%s rate value %lluBps not in link speed units of 1Mbps.\n", + name, *rate); + NL_SET_ERR_MSG_MOD(extack, "TX rate value not in link speed units of 1Mbps."); + return -EINVAL; + } + + if (val > NSIM_LINK_SPEED_MAX) { + pr_err("%s rate value %lluMbps exceed link maximum speed 5000Mbps.\n", + name, val); + NL_SET_ERR_MSG_MOD(extack, "TX rate value exceed link maximum speed 5000Mbps."); + return -EINVAL; + } + *rate = val; + return 0; +} + +static int nsim_leaf_tx_share_set(struct devlink_rate *devlink_rate, void *priv, + u64 tx_share, struct netlink_ext_ack *extack) +{ + struct nsim_dev_port *nsim_dev_port = priv; + struct nsim_bus_dev *nsim_bus_dev = nsim_dev_port->ns->nsim_bus_dev; + int vf_id = nsim_dev_port_index_to_vf_index(nsim_dev_port->port_index); + int err; + + err = nsim_rate_bytes_to_units("tx_share", &tx_share, extack); + if (err) + return err; + + nsim_bus_dev->vfconfigs[vf_id].min_tx_rate = tx_share; + return 0; +} + +static int nsim_leaf_tx_max_set(struct devlink_rate *devlink_rate, void *priv, + u64 tx_max, struct netlink_ext_ack *extack) +{ + struct nsim_dev_port *nsim_dev_port = priv; + struct nsim_bus_dev *nsim_bus_dev = nsim_dev_port->ns->nsim_bus_dev; + int vf_id = nsim_dev_port_index_to_vf_index(nsim_dev_port->port_index); + int err; + + err = nsim_rate_bytes_to_units("tx_max", &tx_max, extack); + if (err) + return err; + + nsim_bus_dev->vfconfigs[vf_id].max_tx_rate = tx_max; + return 0; +} + +struct nsim_rate_node { + struct dentry *ddir; + struct dentry *rate_parent; + char *parent_name; + u16 tx_share; + u16 tx_max; +}; + +static int nsim_node_tx_share_set(struct devlink_rate *devlink_rate, void *priv, + u64 tx_share, struct netlink_ext_ack *extack) +{ + struct nsim_rate_node *nsim_node = priv; + int err; + + err = nsim_rate_bytes_to_units("tx_share", &tx_share, extack); + if (err) + return err; + + nsim_node->tx_share = tx_share; + return 0; +} + +static int nsim_node_tx_max_set(struct devlink_rate *devlink_rate, void *priv, + u64 tx_max, struct netlink_ext_ack *extack) +{ + struct nsim_rate_node *nsim_node = priv; + int err; + + err = nsim_rate_bytes_to_units("tx_max", &tx_max, extack); + if (err) + return err; + + nsim_node->tx_max = tx_max; + return 0; +} + +static int nsim_rate_node_new(struct devlink_rate *node, void **priv, + struct netlink_ext_ack *extack) +{ + struct nsim_dev *nsim_dev = devlink_priv(node->devlink); + struct nsim_rate_node *nsim_node; + + if (!nsim_esw_mode_is_switchdev(nsim_dev)) { + NL_SET_ERR_MSG_MOD(extack, "Node creation allowed only in switchdev mode."); + return -EOPNOTSUPP; + } + + nsim_node = kzalloc(sizeof(*nsim_node), GFP_KERNEL); + if (!nsim_node) + return -ENOMEM; + + nsim_node->ddir = debugfs_create_dir(node->name, nsim_dev->nodes_ddir); + + debugfs_create_u16("tx_share", 0400, nsim_node->ddir, &nsim_node->tx_share); + debugfs_create_u16("tx_max", 0400, nsim_node->ddir, &nsim_node->tx_max); + nsim_node->rate_parent = debugfs_create_file("rate_parent", 0400, + nsim_node->ddir, + &nsim_node->parent_name, + &nsim_dev_rate_parent_fops); + + *priv = nsim_node; + return 0; +} + +static int nsim_rate_node_del(struct devlink_rate *node, void *priv, + struct netlink_ext_ack *extack) +{ + struct nsim_rate_node *nsim_node = priv; + + debugfs_remove(nsim_node->rate_parent); + debugfs_remove_recursive(nsim_node->ddir); + kfree(nsim_node); + return 0; +} + +static int nsim_rate_leaf_parent_set(struct devlink_rate *child, + struct devlink_rate *parent, + void *priv_child, void *priv_parent, + struct netlink_ext_ack *extack) +{ + struct nsim_dev_port *nsim_dev_port = priv_child; + + if (parent) + nsim_dev_port->parent_name = parent->name; + else + nsim_dev_port->parent_name = NULL; + return 0; +} + +static int nsim_rate_node_parent_set(struct devlink_rate *child, + struct devlink_rate *parent, + void *priv_child, void *priv_parent, + struct netlink_ext_ack *extack) +{ + struct nsim_rate_node *nsim_node = priv_child; + + if (parent) + nsim_node->parent_name = parent->name; + else + nsim_node->parent_name = NULL; + return 0; +} + +static int +nsim_dev_devlink_trap_drop_counter_get(struct devlink *devlink, + const struct devlink_trap *trap, + u64 *p_drops) +{ + struct nsim_dev *nsim_dev = devlink_priv(devlink); + u64 *cnt; + + if (nsim_dev->fail_trap_drop_counter_get) + return -EINVAL; + + cnt = &nsim_dev->trap_data->trap_pkt_cnt; + *p_drops = (*cnt)++; + + return 0; +} + static const struct devlink_ops nsim_dev_devlink_ops = { + .eswitch_mode_set = nsim_devlink_eswitch_mode_set, + .eswitch_mode_get = nsim_devlink_eswitch_mode_get, .supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT | DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK, .reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT), @@ -905,32 +1239,52 @@ static const struct devlink_ops nsim_dev_devlink_ops = { .trap_group_set = nsim_dev_devlink_trap_group_set, .trap_policer_set = nsim_dev_devlink_trap_policer_set, .trap_policer_counter_get = nsim_dev_devlink_trap_policer_counter_get, + .rate_leaf_tx_share_set = nsim_leaf_tx_share_set, + .rate_leaf_tx_max_set = nsim_leaf_tx_max_set, + .rate_node_tx_share_set = nsim_node_tx_share_set, + .rate_node_tx_max_set = nsim_node_tx_max_set, + .rate_node_new = nsim_rate_node_new, + .rate_node_del = nsim_rate_node_del, + .rate_leaf_parent_set = nsim_rate_leaf_parent_set, + .rate_node_parent_set = nsim_rate_node_parent_set, + .trap_drop_counter_get = nsim_dev_devlink_trap_drop_counter_get, }; #define NSIM_DEV_MAX_MACS_DEFAULT 32 #define NSIM_DEV_TEST1_DEFAULT true -static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, +static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, enum nsim_dev_port_type type, unsigned int port_index) { + struct nsim_bus_dev *nsim_bus_dev = nsim_dev->nsim_bus_dev; struct devlink_port_attrs attrs = {}; struct nsim_dev_port *nsim_dev_port; struct devlink_port *devlink_port; int err; + if (type == NSIM_DEV_PORT_TYPE_VF && !nsim_bus_dev->num_vfs) + return -EINVAL; + nsim_dev_port = kzalloc(sizeof(*nsim_dev_port), GFP_KERNEL); if (!nsim_dev_port) return -ENOMEM; - nsim_dev_port->port_index = port_index; + nsim_dev_port->port_index = nsim_dev_port_index(type, port_index); + nsim_dev_port->port_type = type; devlink_port = &nsim_dev_port->devlink_port; - attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - attrs.phys.port_number = port_index + 1; + if (nsim_dev_port_is_pf(nsim_dev_port)) { + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + attrs.phys.port_number = port_index + 1; + } else { + attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF; + attrs.pci_vf.pf = 0; + attrs.pci_vf.vf = port_index; + } memcpy(attrs.switch_id.id, nsim_dev->switch_id.id, nsim_dev->switch_id.id_len); attrs.switch_id.id_len = nsim_dev->switch_id.id_len; devlink_port_attrs_set(devlink_port, &attrs); err = devlink_port_register(priv_to_devlink(nsim_dev), devlink_port, - port_index); + nsim_dev_port->port_index); if (err) goto err_port_free; @@ -944,11 +1298,20 @@ static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, goto err_port_debugfs_exit; } + if (nsim_dev_port_is_vf(nsim_dev_port)) { + err = devlink_rate_leaf_create(&nsim_dev_port->devlink_port, + nsim_dev_port); + if (err) + goto err_nsim_destroy; + } + devlink_port_type_eth_set(devlink_port, nsim_dev_port->ns->netdev); list_add(&nsim_dev_port->list, &nsim_dev->port_list); return 0; +err_nsim_destroy: + nsim_destroy(nsim_dev_port->ns); err_port_debugfs_exit: nsim_dev_port_debugfs_exit(nsim_dev_port); err_dl_port_unregister: @@ -963,6 +1326,8 @@ static void __nsim_dev_port_del(struct nsim_dev_port *nsim_dev_port) struct devlink_port *devlink_port = &nsim_dev_port->devlink_port; list_del(&nsim_dev_port->list); + if (nsim_dev_port_is_vf(nsim_dev_port)) + devlink_rate_leaf_destroy(&nsim_dev_port->devlink_port); devlink_port_type_clear(devlink_port); nsim_destroy(nsim_dev_port->ns); nsim_dev_port_debugfs_exit(nsim_dev_port); @@ -987,7 +1352,7 @@ static int nsim_dev_port_add_all(struct nsim_dev *nsim_dev, int i, err; for (i = 0; i < port_count; i++) { - err = __nsim_dev_port_add(nsim_dev, i); + err = __nsim_dev_port_add(nsim_dev, NSIM_DEV_PORT_TYPE_PF, i); if (err) goto err_port_del_all; } @@ -1134,6 +1499,7 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) devlink_params_publish(devlink); devlink_reload_enable(devlink); + nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY; return 0; err_psample_exit: @@ -1169,6 +1535,12 @@ static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev) if (devlink_is_reload_failed(devlink)) return; debugfs_remove(nsim_dev->take_snapshot); + + mutex_lock(&nsim_dev->nsim_bus_dev->vfs_lock); + if (nsim_dev->nsim_bus_dev->num_vfs) + nsim_bus_dev_vfs_disable(nsim_dev->nsim_bus_dev); + mutex_unlock(&nsim_dev->nsim_bus_dev->vfs_lock); + nsim_dev_port_del_all(nsim_dev); nsim_dev_psample_exit(nsim_dev); nsim_dev_health_exit(nsim_dev); @@ -1197,32 +1569,34 @@ void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev) } static struct nsim_dev_port * -__nsim_dev_port_lookup(struct nsim_dev *nsim_dev, unsigned int port_index) +__nsim_dev_port_lookup(struct nsim_dev *nsim_dev, enum nsim_dev_port_type type, + unsigned int port_index) { struct nsim_dev_port *nsim_dev_port; + port_index = nsim_dev_port_index(type, port_index); list_for_each_entry(nsim_dev_port, &nsim_dev->port_list, list) if (nsim_dev_port->port_index == port_index) return nsim_dev_port; return NULL; } -int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev, +int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev, enum nsim_dev_port_type type, unsigned int port_index) { struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev); int err; mutex_lock(&nsim_dev->port_list_lock); - if (__nsim_dev_port_lookup(nsim_dev, port_index)) + if (__nsim_dev_port_lookup(nsim_dev, type, port_index)) err = -EEXIST; else - err = __nsim_dev_port_add(nsim_dev, port_index); + err = __nsim_dev_port_add(nsim_dev, type, port_index); mutex_unlock(&nsim_dev->port_list_lock); return err; } -int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev, +int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev, enum nsim_dev_port_type type, unsigned int port_index) { struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev); @@ -1230,7 +1604,7 @@ int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev, int err = 0; mutex_lock(&nsim_dev->port_list_lock); - nsim_dev_port = __nsim_dev_port_lookup(nsim_dev, port_index); + nsim_dev_port = __nsim_dev_port_lookup(nsim_dev, type, port_index); if (!nsim_dev_port) err = -ENOENT; else diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 659d3dceb687..c3aeb15843e2 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -113,6 +113,11 @@ static int nsim_set_vf_rate(struct net_device *dev, int vf, int min, int max) struct netdevsim *ns = netdev_priv(dev); struct nsim_bus_dev *nsim_bus_dev = ns->nsim_bus_dev; + if (nsim_esw_mode_is_switchdev(ns->nsim_dev)) { + pr_err("Not supported in switchdev mode. Please use devlink API.\n"); + return -EOPNOTSUPP; + } + if (vf >= nsim_bus_dev->num_vfs) return -EINVAL; @@ -261,6 +266,18 @@ static const struct net_device_ops nsim_netdev_ops = { .ndo_get_devlink_port = nsim_get_devlink_port, }; +static const struct net_device_ops nsim_vf_netdev_ops = { + .ndo_start_xmit = nsim_start_xmit, + .ndo_set_rx_mode = nsim_set_rx_mode, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_change_mtu = nsim_change_mtu, + .ndo_get_stats64 = nsim_get_stats64, + .ndo_setup_tc = nsim_setup_tc, + .ndo_set_features = nsim_set_features, + .ndo_get_devlink_port = nsim_get_devlink_port, +}; + static void nsim_setup(struct net_device *dev) { ether_setup(dev); @@ -280,6 +297,49 @@ static void nsim_setup(struct net_device *dev) dev->max_mtu = ETH_MAX_MTU; } +static int nsim_init_netdevsim(struct netdevsim *ns) +{ + int err; + + ns->netdev->netdev_ops = &nsim_netdev_ops; + + err = nsim_udp_tunnels_info_create(ns->nsim_dev, ns->netdev); + if (err) + return err; + + rtnl_lock(); + err = nsim_bpf_init(ns); + if (err) + goto err_utn_destroy; + + nsim_ipsec_init(ns); + + err = register_netdevice(ns->netdev); + if (err) + goto err_ipsec_teardown; + rtnl_unlock(); + return 0; + +err_ipsec_teardown: + nsim_ipsec_teardown(ns); + nsim_bpf_uninit(ns); +err_utn_destroy: + rtnl_unlock(); + nsim_udp_tunnels_info_destroy(ns->netdev); + return err; +} + +static int nsim_init_netdevsim_vf(struct netdevsim *ns) +{ + int err; + + ns->netdev->netdev_ops = &nsim_vf_netdev_ops; + rtnl_lock(); + err = register_netdevice(ns->netdev); + rtnl_unlock(); + return err; +} + struct netdevsim * nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) { @@ -299,33 +359,15 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) ns->nsim_dev_port = nsim_dev_port; ns->nsim_bus_dev = nsim_dev->nsim_bus_dev; SET_NETDEV_DEV(dev, &ns->nsim_bus_dev->dev); - dev->netdev_ops = &nsim_netdev_ops; nsim_ethtool_init(ns); - - err = nsim_udp_tunnels_info_create(nsim_dev, dev); + if (nsim_dev_port_is_pf(nsim_dev_port)) + err = nsim_init_netdevsim(ns); + else + err = nsim_init_netdevsim_vf(ns); if (err) goto err_free_netdev; - - rtnl_lock(); - err = nsim_bpf_init(ns); - if (err) - goto err_utn_destroy; - - nsim_ipsec_init(ns); - - err = register_netdevice(dev); - if (err) - goto err_ipsec_teardown; - rtnl_unlock(); - return ns; -err_ipsec_teardown: - nsim_ipsec_teardown(ns); - nsim_bpf_uninit(ns); -err_utn_destroy: - rtnl_unlock(); - nsim_udp_tunnels_info_destroy(dev); err_free_netdev: free_netdev(dev); return ERR_PTR(err); @@ -337,10 +379,13 @@ void nsim_destroy(struct netdevsim *ns) rtnl_lock(); unregister_netdevice(dev); - nsim_ipsec_teardown(ns); - nsim_bpf_uninit(ns); + if (nsim_dev_port_is_pf(ns->nsim_dev_port)) { + nsim_ipsec_teardown(ns); + nsim_bpf_uninit(ns); + } rtnl_unlock(); - nsim_udp_tunnels_info_destroy(dev); + if (nsim_dev_port_is_pf(ns->nsim_dev_port)) + nsim_udp_tunnels_info_destroy(dev); free_netdev(dev); } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 7ff24e03577b..ae462957dcee 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -197,11 +197,22 @@ static inline void nsim_dev_psample_exit(struct nsim_dev *nsim_dev) } #endif +enum nsim_dev_port_type { + NSIM_DEV_PORT_TYPE_PF, + NSIM_DEV_PORT_TYPE_VF, +}; + +#define NSIM_DEV_VF_PORT_INDEX_BASE 128 +#define NSIM_DEV_VF_PORT_INDEX_MAX UINT_MAX + struct nsim_dev_port { struct list_head list; struct devlink_port devlink_port; unsigned int port_index; + enum nsim_dev_port_type port_type; struct dentry *ddir; + struct dentry *rate_parent; + char *parent_name; struct netdevsim *ns; }; @@ -212,6 +223,8 @@ struct nsim_dev { struct dentry *ddir; struct dentry *ports_ddir; struct dentry *take_snapshot; + struct dentry *max_vfs; + struct dentry *nodes_ddir; struct bpf_offload_dev *bpf_dev; bool bpf_bind_accept; bool bpf_bind_verifier_accept; @@ -236,6 +249,7 @@ struct nsim_dev { bool fail_trap_group_set; bool fail_trap_policer_set; bool fail_trap_policer_counter_get; + bool fail_trap_drop_counter_get; struct { struct udp_tunnel_nic_shared utn_shared; u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS]; @@ -247,8 +261,22 @@ struct nsim_dev { u32 sleep; } udp_ports; struct nsim_dev_psample *psample; + u16 esw_mode; }; +int nsim_esw_legacy_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack); +int nsim_esw_switchdev_enable(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack); + +static inline bool nsim_esw_mode_is_legacy(struct nsim_dev *nsim_dev) +{ + return nsim_dev->esw_mode == DEVLINK_ESWITCH_MODE_LEGACY; +} + +static inline bool nsim_esw_mode_is_switchdev(struct nsim_dev *nsim_dev) +{ + return nsim_dev->esw_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV; +} + static inline struct net *nsim_dev_net(struct nsim_dev *nsim_dev) { return devlink_net(priv_to_devlink(nsim_dev)); @@ -259,8 +287,10 @@ void nsim_dev_exit(void); int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev); void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev); int nsim_dev_port_add(struct nsim_bus_dev *nsim_bus_dev, + enum nsim_dev_port_type type, unsigned int port_index); int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev, + enum nsim_dev_port_type type, unsigned int port_index); struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, @@ -269,6 +299,23 @@ void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *fib_data); u64 nsim_fib_get_val(struct nsim_fib_data *fib_data, enum nsim_resource_id res_id, bool max); +ssize_t nsim_bus_dev_max_vfs_read(struct file *file, + char __user *data, + size_t count, loff_t *ppos); +ssize_t nsim_bus_dev_max_vfs_write(struct file *file, + const char __user *data, + size_t count, loff_t *ppos); +void nsim_bus_dev_vfs_disable(struct nsim_bus_dev *nsim_bus_dev); + +static inline bool nsim_dev_port_is_pf(struct nsim_dev_port *nsim_dev_port) +{ + return nsim_dev_port->port_type == NSIM_DEV_PORT_TYPE_PF; +} + +static inline bool nsim_dev_port_is_vf(struct nsim_dev_port *nsim_dev_port) +{ + return nsim_dev_port->port_type == NSIM_DEV_PORT_TYPE_VF; +} #if IS_ENABLED(CONFIG_XFRM_OFFLOAD) void nsim_ipsec_init(struct netdevsim *ns); void nsim_ipsec_teardown(struct netdevsim *ns); @@ -308,7 +355,9 @@ struct nsim_bus_dev { struct net *initial_net; /* Purpose of this is to carry net pointer * during the probe time only. */ + unsigned int max_vfs; unsigned int num_vfs; + struct mutex vfs_lock; /* Protects vfconfigs */ struct nsim_vf_config *vfconfigs; /* Lock for devlink->reload_enabled in netdevsim module */ struct mutex nsim_bus_reload_lock; diff --git a/drivers/net/pcs/Makefile b/drivers/net/pcs/Makefile index c23146755972..0603d469bd57 100644 --- a/drivers/net/pcs/Makefile +++ b/drivers/net/pcs/Makefile @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for Linux PCS drivers -obj-$(CONFIG_PCS_XPCS) += pcs-xpcs.o +pcs_xpcs-$(CONFIG_PCS_XPCS) := pcs-xpcs.o pcs-xpcs-nxp.o + +obj-$(CONFIG_PCS_XPCS) += pcs_xpcs.o obj-$(CONFIG_PCS_LYNX) += pcs-lynx.o diff --git a/drivers/net/pcs/pcs-xpcs-nxp.c b/drivers/net/pcs/pcs-xpcs-nxp.c new file mode 100644 index 000000000000..984c9f7f16a8 --- /dev/null +++ b/drivers/net/pcs/pcs-xpcs-nxp.c @@ -0,0 +1,185 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2021 NXP Semiconductors + */ +#include +#include "pcs-xpcs.h" + +/* LANE_DRIVER1_0 register */ +#define SJA1110_LANE_DRIVER1_0 0x8038 +#define SJA1110_TXDRV(x) (((x) << 12) & GENMASK(14, 12)) + +/* LANE_DRIVER2_0 register */ +#define SJA1110_LANE_DRIVER2_0 0x803a +#define SJA1110_TXDRVTRIM_LSB(x) ((x) & GENMASK_ULL(15, 0)) + +/* LANE_DRIVER2_1 register */ +#define SJA1110_LANE_DRIVER2_1 0x803b +#define SJA1110_LANE_DRIVER2_1_RSV BIT(9) +#define SJA1110_TXDRVTRIM_MSB(x) (((x) & GENMASK_ULL(23, 16)) >> 16) + +/* LANE_TRIM register */ +#define SJA1110_LANE_TRIM 0x8040 +#define SJA1110_TXTEN BIT(11) +#define SJA1110_TXRTRIM(x) (((x) << 8) & GENMASK(10, 8)) +#define SJA1110_TXPLL_BWSEL BIT(7) +#define SJA1110_RXTEN BIT(6) +#define SJA1110_RXRTRIM(x) (((x) << 3) & GENMASK(5, 3)) +#define SJA1110_CDR_GAIN BIT(2) +#define SJA1110_ACCOUPLE_RXVCM_EN BIT(0) + +/* LANE_DATAPATH_1 register */ +#define SJA1110_LANE_DATAPATH_1 0x8037 + +/* POWERDOWN_ENABLE register */ +#define SJA1110_POWERDOWN_ENABLE 0x8041 +#define SJA1110_TXPLL_PD BIT(12) +#define SJA1110_TXPD BIT(11) +#define SJA1110_RXPKDETEN BIT(10) +#define SJA1110_RXCH_PD BIT(9) +#define SJA1110_RXBIAS_PD BIT(8) +#define SJA1110_RESET_SER_EN BIT(7) +#define SJA1110_RESET_SER BIT(6) +#define SJA1110_RESET_DES BIT(5) +#define SJA1110_RCVEN BIT(4) + +/* RXPLL_CTRL0 register */ +#define SJA1110_RXPLL_CTRL0 0x8065 +#define SJA1110_RXPLL_FBDIV(x) (((x) << 2) & GENMASK(9, 2)) + +/* RXPLL_CTRL1 register */ +#define SJA1110_RXPLL_CTRL1 0x8066 +#define SJA1110_RXPLL_REFDIV(x) ((x) & GENMASK(4, 0)) + +/* TXPLL_CTRL0 register */ +#define SJA1110_TXPLL_CTRL0 0x806d +#define SJA1110_TXPLL_FBDIV(x) ((x) & GENMASK(11, 0)) + +/* TXPLL_CTRL1 register */ +#define SJA1110_TXPLL_CTRL1 0x806e +#define SJA1110_TXPLL_REFDIV(x) ((x) & GENMASK(5, 0)) + +/* RX_DATA_DETECT register */ +#define SJA1110_RX_DATA_DETECT 0x8045 + +/* RX_CDR_CTLE register */ +#define SJA1110_RX_CDR_CTLE 0x8042 + +/* In NXP SJA1105, the PCS is integrated with a PMA that has the TX lane + * polarity inverted by default (PLUS is MINUS, MINUS is PLUS). To obtain + * normal non-inverted behavior, the TX lane polarity must be inverted in the + * PCS, via the DIGITAL_CONTROL_2 register. + */ +int nxp_sja1105_sgmii_pma_config(struct dw_xpcs *xpcs) +{ + return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL2, + DW_VR_MII_DIG_CTRL2_TX_POL_INV); +} + +static int nxp_sja1110_pma_config(struct dw_xpcs *xpcs, + u16 txpll_fbdiv, u16 txpll_refdiv, + u16 rxpll_fbdiv, u16 rxpll_refdiv, + u16 rx_cdr_ctle) +{ + u16 val; + int ret; + + /* Program TX PLL feedback divider and reference divider settings for + * correct oscillation frequency. + */ + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_TXPLL_CTRL0, + SJA1110_TXPLL_FBDIV(txpll_fbdiv)); + if (ret < 0) + return ret; + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_TXPLL_CTRL1, + SJA1110_TXPLL_REFDIV(txpll_refdiv)); + if (ret < 0) + return ret; + + /* Program transmitter amplitude and disable amplitude trimming */ + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_DRIVER1_0, + SJA1110_TXDRV(0x5)); + if (ret < 0) + return ret; + + val = SJA1110_TXDRVTRIM_LSB(0xffffffull); + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_DRIVER2_0, val); + if (ret < 0) + return ret; + + val = SJA1110_TXDRVTRIM_MSB(0xffffffull) | SJA1110_LANE_DRIVER2_1_RSV; + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_DRIVER2_1, val); + if (ret < 0) + return ret; + + /* Enable input and output resistor terminations for low BER. */ + val = SJA1110_ACCOUPLE_RXVCM_EN | SJA1110_CDR_GAIN | + SJA1110_RXRTRIM(4) | SJA1110_RXTEN | SJA1110_TXPLL_BWSEL | + SJA1110_TXRTRIM(3) | SJA1110_TXTEN; + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_TRIM, val); + if (ret < 0) + return ret; + + /* Select PCS as transmitter data source. */ + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_LANE_DATAPATH_1, 0); + if (ret < 0) + return ret; + + /* Program RX PLL feedback divider and reference divider for correct + * oscillation frequency. + */ + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_RXPLL_CTRL0, + SJA1110_RXPLL_FBDIV(rxpll_fbdiv)); + if (ret < 0) + return ret; + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_RXPLL_CTRL1, + SJA1110_RXPLL_REFDIV(rxpll_refdiv)); + if (ret < 0) + return ret; + + /* Program threshold for receiver signal detector. + * Enable control of RXPLL by receiver signal detector to disable RXPLL + * when an input signal is not present. + */ + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_RX_DATA_DETECT, 0x0005); + if (ret < 0) + return ret; + + /* Enable TX and RX PLLs and circuits. + * Release reset of PMA to enable data flow to/from PCS. + */ + ret = xpcs_read(xpcs, MDIO_MMD_VEND2, SJA1110_POWERDOWN_ENABLE); + if (ret < 0) + return ret; + + val = ret & ~(SJA1110_TXPLL_PD | SJA1110_TXPD | SJA1110_RXCH_PD | + SJA1110_RXBIAS_PD | SJA1110_RESET_SER_EN | + SJA1110_RESET_SER | SJA1110_RESET_DES); + val |= SJA1110_RXPKDETEN | SJA1110_RCVEN; + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_POWERDOWN_ENABLE, val); + if (ret < 0) + return ret; + + /* Program continuous-time linear equalizer (CTLE) settings. */ + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, SJA1110_RX_CDR_CTLE, + rx_cdr_ctle); + if (ret < 0) + return ret; + + return 0; +} + +int nxp_sja1110_sgmii_pma_config(struct dw_xpcs *xpcs) +{ + return nxp_sja1110_pma_config(xpcs, 0x19, 0x1, 0x19, 0x1, 0x212a); +} + +int nxp_sja1110_2500basex_pma_config(struct dw_xpcs *xpcs) +{ + return nxp_sja1110_pma_config(xpcs, 0x7d, 0x2, 0x7d, 0x2, 0x732a); +} diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 944ba105cac1..63fda3fc40aa 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -11,80 +11,10 @@ #include #include #include +#include "pcs-xpcs.h" -#define SYNOPSYS_XPCS_USXGMII_ID 0x7996ced0 -#define SYNOPSYS_XPCS_10GKR_ID 0x7996ced0 -#define SYNOPSYS_XPCS_XLGMII_ID 0x7996ced0 -#define SYNOPSYS_XPCS_SGMII_ID 0x7996ced0 -#define SYNOPSYS_XPCS_MASK 0xffffffff - -/* Vendor regs access */ -#define DW_VENDOR BIT(15) - -/* VR_XS_PCS */ -#define DW_USXGMII_RST BIT(10) -#define DW_USXGMII_EN BIT(9) -#define DW_VR_XS_PCS_DIG_STS 0x0010 -#define DW_RXFIFO_ERR GENMASK(6, 5) - -/* SR_MII */ -#define DW_USXGMII_FULL BIT(8) -#define DW_USXGMII_SS_MASK (BIT(13) | BIT(6) | BIT(5)) -#define DW_USXGMII_10000 (BIT(13) | BIT(6)) -#define DW_USXGMII_5000 (BIT(13) | BIT(5)) -#define DW_USXGMII_2500 (BIT(5)) -#define DW_USXGMII_1000 (BIT(6)) -#define DW_USXGMII_100 (BIT(13)) -#define DW_USXGMII_10 (0) - -/* SR_AN */ -#define DW_SR_AN_ADV1 0x10 -#define DW_SR_AN_ADV2 0x11 -#define DW_SR_AN_ADV3 0x12 -#define DW_SR_AN_LP_ABL1 0x13 -#define DW_SR_AN_LP_ABL2 0x14 -#define DW_SR_AN_LP_ABL3 0x15 - -/* Clause 73 Defines */ -/* AN_LP_ABL1 */ -#define DW_C73_PAUSE BIT(10) -#define DW_C73_ASYM_PAUSE BIT(11) -#define DW_C73_AN_ADV_SF 0x1 -/* AN_LP_ABL2 */ -#define DW_C73_1000KX BIT(5) -#define DW_C73_10000KX4 BIT(6) -#define DW_C73_10000KR BIT(7) -/* AN_LP_ABL3 */ -#define DW_C73_2500KX BIT(0) -#define DW_C73_5000KR BIT(1) - -/* Clause 37 Defines */ -/* VR MII MMD registers offsets */ -#define DW_VR_MII_DIG_CTRL1 0x8000 -#define DW_VR_MII_AN_CTRL 0x8001 -#define DW_VR_MII_AN_INTR_STS 0x8002 - -/* VR_MII_DIG_CTRL1 */ -#define DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW BIT(9) - -/* VR_MII_AN_CTRL */ -#define DW_VR_MII_AN_CTRL_TX_CONFIG_SHIFT 3 -#define DW_VR_MII_TX_CONFIG_MASK BIT(3) -#define DW_VR_MII_TX_CONFIG_PHY_SIDE_SGMII 0x1 -#define DW_VR_MII_TX_CONFIG_MAC_SIDE_SGMII 0x0 -#define DW_VR_MII_AN_CTRL_PCS_MODE_SHIFT 1 -#define DW_VR_MII_PCS_MODE_MASK GENMASK(2, 1) -#define DW_VR_MII_PCS_MODE_C37_1000BASEX 0x0 -#define DW_VR_MII_PCS_MODE_C37_SGMII 0x2 - -/* VR_MII_AN_INTR_STS */ -#define DW_VR_MII_AN_STS_C37_ANSGM_FD BIT(1) -#define DW_VR_MII_AN_STS_C37_ANSGM_SP_SHIFT 2 -#define DW_VR_MII_AN_STS_C37_ANSGM_SP GENMASK(3, 2) -#define DW_VR_MII_C37_ANSGM_SP_10 0x0 -#define DW_VR_MII_C37_ANSGM_SP_100 0x1 -#define DW_VR_MII_C37_ANSGM_SP_1000 0x2 -#define DW_VR_MII_C37_ANSGM_SP_LNKSTS BIT(4) +#define phylink_pcs_to_xpcs(pl_pcs) \ + container_of((pl_pcs), struct dw_xpcs, pcs) static const int xpcs_usxgmii_features[] = { ETHTOOL_LINK_MODE_Pause_BIT, @@ -144,96 +74,141 @@ static const int xpcs_sgmii_features[] = { __ETHTOOL_LINK_MODE_MASK_NBITS, }; +static const int xpcs_2500basex_features[] = { + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ETHTOOL_LINK_MODE_Autoneg_BIT, + ETHTOOL_LINK_MODE_2500baseX_Full_BIT, + ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + __ETHTOOL_LINK_MODE_MASK_NBITS, +}; + static const phy_interface_t xpcs_usxgmii_interfaces[] = { PHY_INTERFACE_MODE_USXGMII, - PHY_INTERFACE_MODE_MAX, }; static const phy_interface_t xpcs_10gkr_interfaces[] = { PHY_INTERFACE_MODE_10GKR, - PHY_INTERFACE_MODE_MAX, }; static const phy_interface_t xpcs_xlgmii_interfaces[] = { PHY_INTERFACE_MODE_XLGMII, - PHY_INTERFACE_MODE_MAX, }; static const phy_interface_t xpcs_sgmii_interfaces[] = { PHY_INTERFACE_MODE_SGMII, +}; + +static const phy_interface_t xpcs_2500basex_interfaces[] = { + PHY_INTERFACE_MODE_2500BASEX, PHY_INTERFACE_MODE_MAX, }; -static struct xpcs_id { - u32 id; - u32 mask; - const int *supported; - const phy_interface_t *interface; - int an_mode; -} xpcs_id_list[] = { - { - .id = SYNOPSYS_XPCS_USXGMII_ID, - .mask = SYNOPSYS_XPCS_MASK, - .supported = xpcs_usxgmii_features, - .interface = xpcs_usxgmii_interfaces, - .an_mode = DW_AN_C73, - }, { - .id = SYNOPSYS_XPCS_10GKR_ID, - .mask = SYNOPSYS_XPCS_MASK, - .supported = xpcs_10gkr_features, - .interface = xpcs_10gkr_interfaces, - .an_mode = DW_AN_C73, - }, { - .id = SYNOPSYS_XPCS_XLGMII_ID, - .mask = SYNOPSYS_XPCS_MASK, - .supported = xpcs_xlgmii_features, - .interface = xpcs_xlgmii_interfaces, - .an_mode = DW_AN_C73, - }, { - .id = SYNOPSYS_XPCS_SGMII_ID, - .mask = SYNOPSYS_XPCS_MASK, - .supported = xpcs_sgmii_features, - .interface = xpcs_sgmii_interfaces, - .an_mode = DW_AN_C37_SGMII, - }, +enum { + DW_XPCS_USXGMII, + DW_XPCS_10GKR, + DW_XPCS_XLGMII, + DW_XPCS_SGMII, + DW_XPCS_2500BASEX, + DW_XPCS_INTERFACE_MAX, }; -static int xpcs_read(struct mdio_xpcs_args *xpcs, int dev, u32 reg) -{ - u32 reg_addr = MII_ADDR_C45 | dev << 16 | reg; +struct xpcs_compat { + const int *supported; + const phy_interface_t *interface; + int num_interfaces; + int an_mode; + int (*pma_config)(struct dw_xpcs *xpcs); +}; - return mdiobus_read(xpcs->bus, xpcs->addr, reg_addr); +struct xpcs_id { + u32 id; + u32 mask; + const struct xpcs_compat *compat; +}; + +static const struct xpcs_compat *xpcs_find_compat(const struct xpcs_id *id, + phy_interface_t interface) +{ + int i, j; + + for (i = 0; i < DW_XPCS_INTERFACE_MAX; i++) { + const struct xpcs_compat *compat = &id->compat[i]; + + for (j = 0; j < compat->num_interfaces; j++) + if (compat->interface[j] == interface) + return compat; + } + + return NULL; } -static int xpcs_write(struct mdio_xpcs_args *xpcs, int dev, u32 reg, u16 val) +int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface) { - u32 reg_addr = MII_ADDR_C45 | dev << 16 | reg; + const struct xpcs_compat *compat; - return mdiobus_write(xpcs->bus, xpcs->addr, reg_addr, val); + compat = xpcs_find_compat(xpcs->id, interface); + if (!compat) + return -ENODEV; + + return compat->an_mode; +} +EXPORT_SYMBOL_GPL(xpcs_get_an_mode); + +static bool __xpcs_linkmode_supported(const struct xpcs_compat *compat, + enum ethtool_link_mode_bit_indices linkmode) +{ + int i; + + for (i = 0; compat->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++) + if (compat->supported[i] == linkmode) + return true; + + return false; } -static int xpcs_read_vendor(struct mdio_xpcs_args *xpcs, int dev, u32 reg) +#define xpcs_linkmode_supported(compat, mode) \ + __xpcs_linkmode_supported(compat, ETHTOOL_LINK_MODE_ ## mode ## _BIT) + +int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg) +{ + u32 reg_addr = mdiobus_c45_addr(dev, reg); + struct mii_bus *bus = xpcs->mdiodev->bus; + int addr = xpcs->mdiodev->addr; + + return mdiobus_read(bus, addr, reg_addr); +} + +int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val) +{ + u32 reg_addr = mdiobus_c45_addr(dev, reg); + struct mii_bus *bus = xpcs->mdiodev->bus; + int addr = xpcs->mdiodev->addr; + + return mdiobus_write(bus, addr, reg_addr, val); +} + +static int xpcs_read_vendor(struct dw_xpcs *xpcs, int dev, u32 reg) { return xpcs_read(xpcs, dev, DW_VENDOR | reg); } -static int xpcs_write_vendor(struct mdio_xpcs_args *xpcs, int dev, int reg, +static int xpcs_write_vendor(struct dw_xpcs *xpcs, int dev, int reg, u16 val) { return xpcs_write(xpcs, dev, DW_VENDOR | reg, val); } -static int xpcs_read_vpcs(struct mdio_xpcs_args *xpcs, int reg) +static int xpcs_read_vpcs(struct dw_xpcs *xpcs, int reg) { return xpcs_read_vendor(xpcs, MDIO_MMD_PCS, reg); } -static int xpcs_write_vpcs(struct mdio_xpcs_args *xpcs, int reg, u16 val) +static int xpcs_write_vpcs(struct dw_xpcs *xpcs, int reg, u16 val) { return xpcs_write_vendor(xpcs, MDIO_MMD_PCS, reg, val); } -static int xpcs_poll_reset(struct mdio_xpcs_args *xpcs, int dev) +static int xpcs_poll_reset(struct dw_xpcs *xpcs, int dev) { /* Poll until the reset bit clears (50ms per retry == 0.6 sec) */ unsigned int retries = 12; @@ -249,15 +224,17 @@ static int xpcs_poll_reset(struct mdio_xpcs_args *xpcs, int dev) return (ret & MDIO_CTRL1_RESET) ? -ETIMEDOUT : 0; } -static int xpcs_soft_reset(struct mdio_xpcs_args *xpcs) +static int xpcs_soft_reset(struct dw_xpcs *xpcs, + const struct xpcs_compat *compat) { int ret, dev; - switch (xpcs->an_mode) { + switch (compat->an_mode) { case DW_AN_C73: dev = MDIO_MMD_PCS; break; case DW_AN_C37_SGMII: + case DW_2500BASEX: dev = MDIO_MMD_VEND2; break; default: @@ -274,10 +251,10 @@ static int xpcs_soft_reset(struct mdio_xpcs_args *xpcs) #define xpcs_warn(__xpcs, __state, __args...) \ ({ \ if ((__state)->link) \ - dev_warn(&(__xpcs)->bus->dev, ##__args); \ + dev_warn(&(__xpcs)->mdiodev->dev, ##__args); \ }) -static int xpcs_read_fault_c73(struct mdio_xpcs_args *xpcs, +static int xpcs_read_fault_c73(struct dw_xpcs *xpcs, struct phylink_link_state *state) { int ret; @@ -328,7 +305,7 @@ static int xpcs_read_fault_c73(struct mdio_xpcs_args *xpcs, return 0; } -static int xpcs_read_link_c73(struct mdio_xpcs_args *xpcs, bool an) +static int xpcs_read_link_c73(struct dw_xpcs *xpcs, bool an) { bool link = true; int ret; @@ -368,7 +345,7 @@ static int xpcs_get_max_usxgmii_speed(const unsigned long *supported) return max; } -static int xpcs_config_usxgmii(struct mdio_xpcs_args *xpcs, int speed) +static void xpcs_config_usxgmii(struct dw_xpcs *xpcs, int speed) { int ret, speed_sel; @@ -393,36 +370,44 @@ static int xpcs_config_usxgmii(struct mdio_xpcs_args *xpcs, int speed) break; default: /* Nothing to do here */ - return -EINVAL; + return; } ret = xpcs_read_vpcs(xpcs, MDIO_CTRL1); if (ret < 0) - return ret; + goto out; ret = xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_EN); if (ret < 0) - return ret; + goto out; ret = xpcs_read(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1); if (ret < 0) - return ret; + goto out; ret &= ~DW_USXGMII_SS_MASK; ret |= speed_sel | DW_USXGMII_FULL; ret = xpcs_write(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1, ret); if (ret < 0) - return ret; + goto out; ret = xpcs_read_vpcs(xpcs, MDIO_CTRL1); if (ret < 0) - return ret; + goto out; - return xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_RST); + ret = xpcs_write_vpcs(xpcs, MDIO_CTRL1, ret | DW_USXGMII_RST); + if (ret < 0) + goto out; + + return; + +out: + pr_err("%s: XPCS access returned %pe\n", __func__, ERR_PTR(ret)); } -static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs) +static int _xpcs_config_aneg_c73(struct dw_xpcs *xpcs, + const struct xpcs_compat *compat) { int ret, adv; @@ -434,7 +419,7 @@ static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs) /* SR_AN_ADV3 */ adv = 0; - if (phylink_test(xpcs->supported, 2500baseX_Full)) + if (xpcs_linkmode_supported(compat, 2500baseX_Full)) adv |= DW_C73_2500KX; /* TODO: 5000baseKR */ @@ -445,11 +430,11 @@ static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs) /* SR_AN_ADV2 */ adv = 0; - if (phylink_test(xpcs->supported, 1000baseKX_Full)) + if (xpcs_linkmode_supported(compat, 1000baseKX_Full)) adv |= DW_C73_1000KX; - if (phylink_test(xpcs->supported, 10000baseKX4_Full)) + if (xpcs_linkmode_supported(compat, 10000baseKX4_Full)) adv |= DW_C73_10000KX4; - if (phylink_test(xpcs->supported, 10000baseKR_Full)) + if (xpcs_linkmode_supported(compat, 10000baseKR_Full)) adv |= DW_C73_10000KR; ret = xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV2, adv); @@ -458,19 +443,20 @@ static int _xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs) /* SR_AN_ADV1 */ adv = DW_C73_AN_ADV_SF; - if (phylink_test(xpcs->supported, Pause)) + if (xpcs_linkmode_supported(compat, Pause)) adv |= DW_C73_PAUSE; - if (phylink_test(xpcs->supported, Asym_Pause)) + if (xpcs_linkmode_supported(compat, Asym_Pause)) adv |= DW_C73_ASYM_PAUSE; return xpcs_write(xpcs, MDIO_MMD_AN, DW_SR_AN_ADV1, adv); } -static int xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs) +static int xpcs_config_aneg_c73(struct dw_xpcs *xpcs, + const struct xpcs_compat *compat) { int ret; - ret = _xpcs_config_aneg_c73(xpcs); + ret = _xpcs_config_aneg_c73(xpcs, compat); if (ret < 0) return ret; @@ -483,8 +469,9 @@ static int xpcs_config_aneg_c73(struct mdio_xpcs_args *xpcs) return xpcs_write(xpcs, MDIO_MMD_AN, MDIO_CTRL1, ret); } -static int xpcs_aneg_done_c73(struct mdio_xpcs_args *xpcs, - struct phylink_link_state *state) +static int xpcs_aneg_done_c73(struct dw_xpcs *xpcs, + struct phylink_link_state *state, + const struct xpcs_compat *compat) { int ret; @@ -499,7 +486,7 @@ static int xpcs_aneg_done_c73(struct mdio_xpcs_args *xpcs, /* Check if Aneg outcome is valid */ if (!(ret & DW_C73_AN_ADV_SF)) { - xpcs_config_aneg_c73(xpcs); + xpcs_config_aneg_c73(xpcs, compat); return 0; } @@ -509,7 +496,7 @@ static int xpcs_aneg_done_c73(struct mdio_xpcs_args *xpcs, return 0; } -static int xpcs_read_lpa_c73(struct mdio_xpcs_args *xpcs, +static int xpcs_read_lpa_c73(struct dw_xpcs *xpcs, struct phylink_link_state *state) { int ret; @@ -558,7 +545,7 @@ static int xpcs_read_lpa_c73(struct mdio_xpcs_args *xpcs, return 0; } -static void xpcs_resolve_lpa_c73(struct mdio_xpcs_args *xpcs, +static void xpcs_resolve_lpa_c73(struct dw_xpcs *xpcs, struct phylink_link_state *state) { int max_speed = xpcs_get_max_usxgmii_speed(state->lp_advertising); @@ -568,7 +555,7 @@ static void xpcs_resolve_lpa_c73(struct mdio_xpcs_args *xpcs, state->duplex = DUPLEX_FULL; } -static int xpcs_get_max_xlgmii_speed(struct mdio_xpcs_args *xpcs, +static int xpcs_get_max_xlgmii_speed(struct dw_xpcs *xpcs, struct phylink_link_state *state) { unsigned long *adv = state->advertising; @@ -622,7 +609,7 @@ static int xpcs_get_max_xlgmii_speed(struct mdio_xpcs_args *xpcs, return speed; } -static void xpcs_resolve_pma(struct mdio_xpcs_args *xpcs, +static void xpcs_resolve_pma(struct dw_xpcs *xpcs, struct phylink_link_state *state) { state->pause = MLO_PAUSE_TX | MLO_PAUSE_RX; @@ -641,16 +628,70 @@ static void xpcs_resolve_pma(struct mdio_xpcs_args *xpcs, } } -static int xpcs_validate(struct mdio_xpcs_args *xpcs, - unsigned long *supported, - struct phylink_link_state *state) +void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, + struct phylink_link_state *state) { - linkmode_and(supported, supported, xpcs->supported); - linkmode_and(state->advertising, state->advertising, xpcs->supported); - return 0; -} + __ETHTOOL_DECLARE_LINK_MODE_MASK(xpcs_supported); + const struct xpcs_compat *compat; + int i; -static int xpcs_config_aneg_c37_sgmii(struct mdio_xpcs_args *xpcs) + /* phylink expects us to report all supported modes with + * PHY_INTERFACE_MODE_NA, just don't limit the supported and + * advertising masks and exit. + */ + if (state->interface == PHY_INTERFACE_MODE_NA) + return; + + bitmap_zero(xpcs_supported, __ETHTOOL_LINK_MODE_MASK_NBITS); + + compat = xpcs_find_compat(xpcs->id, state->interface); + + /* Populate the supported link modes for this + * PHY interface type + */ + if (compat) + for (i = 0; compat->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++) + set_bit(compat->supported[i], xpcs_supported); + + linkmode_and(supported, supported, xpcs_supported); + linkmode_and(state->advertising, state->advertising, xpcs_supported); +} +EXPORT_SYMBOL_GPL(xpcs_validate); + +int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable) +{ + int ret; + + if (enable) { + /* Enable EEE */ + ret = DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN | + DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN | + DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL | + mult_fact_100ns << DW_VR_MII_EEE_MULT_FACT_100NS_SHIFT; + } else { + ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL0); + if (ret < 0) + return ret; + ret &= ~(DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN | + DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN | + DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL | + DW_VR_MII_EEE_MULT_FACT_100NS); + } + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL0, ret); + if (ret < 0) + return ret; + + ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL1); + if (ret < 0) + return ret; + + ret |= DW_VR_MII_EEE_TRN_LPI; + return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL1, ret); +} +EXPORT_SYMBOL_GPL(xpcs_config_eee); + +static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs, unsigned int mode) { int ret; @@ -686,26 +727,61 @@ static int xpcs_config_aneg_c37_sgmii(struct mdio_xpcs_args *xpcs) if (ret < 0) return ret; - ret |= DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW; + if (phylink_autoneg_inband(mode)) + ret |= DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW; + else + ret &= ~DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW; return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1, ret); } -static int xpcs_config(struct mdio_xpcs_args *xpcs, - const struct phylink_link_state *state) +static int xpcs_config_2500basex(struct dw_xpcs *xpcs) { int ret; - switch (xpcs->an_mode) { + ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1); + if (ret < 0) + return ret; + ret |= DW_VR_MII_DIG_CTRL1_2G5_EN; + ret &= ~DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW; + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_DIG_CTRL1, ret); + if (ret < 0) + return ret; + + ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_MMD_CTRL); + if (ret < 0) + return ret; + ret &= ~AN_CL37_EN; + ret |= SGMII_SPEED_SS6; + ret &= ~SGMII_SPEED_SS13; + return xpcs_write(xpcs, MDIO_MMD_VEND2, DW_VR_MII_MMD_CTRL, ret); +} + +int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, + unsigned int mode) +{ + const struct xpcs_compat *compat; + int ret; + + compat = xpcs_find_compat(xpcs->id, interface); + if (!compat) + return -ENODEV; + + switch (compat->an_mode) { case DW_AN_C73: - if (state->an_enabled) { - ret = xpcs_config_aneg_c73(xpcs); + if (phylink_autoneg_inband(mode)) { + ret = xpcs_config_aneg_c73(xpcs, compat); if (ret) return ret; } break; case DW_AN_C37_SGMII: - ret = xpcs_config_aneg_c37_sgmii(xpcs); + ret = xpcs_config_aneg_c37_sgmii(xpcs, mode); + if (ret) + return ret; + break; + case DW_2500BASEX: + ret = xpcs_config_2500basex(xpcs); if (ret) return ret; break; @@ -713,11 +789,29 @@ static int xpcs_config(struct mdio_xpcs_args *xpcs, return -1; } + if (compat->pma_config) { + ret = compat->pma_config(xpcs); + if (ret) + return ret; + } + return 0; } +EXPORT_SYMBOL_GPL(xpcs_do_config); -static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs, - struct phylink_link_state *state) +static int xpcs_config(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) +{ + struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); + + return xpcs_do_config(xpcs, interface, mode); +} + +static int xpcs_get_state_c73(struct dw_xpcs *xpcs, + struct phylink_link_state *state, + const struct xpcs_compat *compat) { int ret; @@ -727,16 +821,16 @@ static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs, /* ... and then we check the faults. */ ret = xpcs_read_fault_c73(xpcs, state); if (ret) { - ret = xpcs_soft_reset(xpcs); + ret = xpcs_soft_reset(xpcs, compat); if (ret) return ret; state->link = 0; - return xpcs_config(xpcs, state); + return xpcs_do_config(xpcs, state->interface, MLO_AN_INBAND); } - if (state->an_enabled && xpcs_aneg_done_c73(xpcs, state)) { + if (state->an_enabled && xpcs_aneg_done_c73(xpcs, state, compat)) { state->an_complete = true; xpcs_read_lpa_c73(xpcs, state); xpcs_resolve_lpa_c73(xpcs, state); @@ -749,7 +843,7 @@ static int xpcs_get_state_c73(struct mdio_xpcs_args *xpcs, return 0; } -static int xpcs_get_state_c37_sgmii(struct mdio_xpcs_args *xpcs, +static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs, struct phylink_link_state *state) { int ret; @@ -790,39 +884,81 @@ static int xpcs_get_state_c37_sgmii(struct mdio_xpcs_args *xpcs, return 0; } -static int xpcs_get_state(struct mdio_xpcs_args *xpcs, - struct phylink_link_state *state) +static void xpcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) { + struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); + const struct xpcs_compat *compat; int ret; - switch (xpcs->an_mode) { + compat = xpcs_find_compat(xpcs->id, state->interface); + if (!compat) + return; + + switch (compat->an_mode) { case DW_AN_C73: - ret = xpcs_get_state_c73(xpcs, state); - if (ret) - return ret; + ret = xpcs_get_state_c73(xpcs, state, compat); + if (ret) { + pr_err("xpcs_get_state_c73 returned %pe\n", + ERR_PTR(ret)); + return; + } break; case DW_AN_C37_SGMII: ret = xpcs_get_state_c37_sgmii(xpcs, state); - if (ret) - return ret; + if (ret) { + pr_err("xpcs_get_state_c37_sgmii returned %pe\n", + ERR_PTR(ret)); + } break; default: - return -1; + return; + } +} + +static void xpcs_link_up_sgmii(struct dw_xpcs *xpcs, unsigned int mode, + int speed, int duplex) +{ + int val, ret; + + if (phylink_autoneg_inband(mode)) + return; + + switch (speed) { + case SPEED_1000: + val = BMCR_SPEED1000; + break; + case SPEED_100: + val = BMCR_SPEED100; + break; + case SPEED_10: + val = BMCR_SPEED10; + break; + default: + return; } - return 0; + if (duplex == DUPLEX_FULL) + val |= BMCR_FULLDPLX; + + ret = xpcs_write(xpcs, MDIO_MMD_VEND2, MDIO_CTRL1, val); + if (ret) + pr_err("%s: xpcs_write returned %pe\n", __func__, ERR_PTR(ret)); } -static int xpcs_link_up(struct mdio_xpcs_args *xpcs, int speed, - phy_interface_t interface) +void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, int speed, int duplex) { + struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); + if (interface == PHY_INTERFACE_MODE_USXGMII) return xpcs_config_usxgmii(xpcs, speed); - - return 0; + if (interface == PHY_INTERFACE_MODE_SGMII) + return xpcs_link_up_sgmii(xpcs, mode, speed, duplex); } +EXPORT_SYMBOL_GPL(xpcs_link_up); -static u32 xpcs_get_id(struct mdio_xpcs_args *xpcs) +static u32 xpcs_get_id(struct dw_xpcs *xpcs) { int ret; u32 id; @@ -838,8 +974,10 @@ static u32 xpcs_get_id(struct mdio_xpcs_args *xpcs) if (ret < 0) return 0xffffffff; - /* If Device IDs are not all zeros, we found C73 AN-type device */ - if (id | ret) + /* If Device IDs are not all zeros or all ones, + * we found C73 AN-type device + */ + if ((id | ret) && (id | ret) != 0xffffffff) return id | ret; /* Next, search C37 PCS using Vendor-Specific MII MMD */ @@ -860,60 +998,141 @@ static u32 xpcs_get_id(struct mdio_xpcs_args *xpcs) return 0xffffffff; } -static bool xpcs_check_features(struct mdio_xpcs_args *xpcs, - struct xpcs_id *match, - phy_interface_t interface) -{ - int i; - - for (i = 0; match->interface[i] != PHY_INTERFACE_MODE_MAX; i++) { - if (match->interface[i] == interface) - break; - } - - if (match->interface[i] == PHY_INTERFACE_MODE_MAX) - return false; - - for (i = 0; match->supported[i] != __ETHTOOL_LINK_MODE_MASK_NBITS; i++) - set_bit(match->supported[i], xpcs->supported); - - xpcs->an_mode = match->an_mode; - - return true; -} - -static int xpcs_probe(struct mdio_xpcs_args *xpcs, phy_interface_t interface) -{ - u32 xpcs_id = xpcs_get_id(xpcs); - struct xpcs_id *match = NULL; - int i; - - for (i = 0; i < ARRAY_SIZE(xpcs_id_list); i++) { - struct xpcs_id *entry = &xpcs_id_list[i]; - - if ((xpcs_id & entry->mask) == entry->id) { - match = entry; - - if (xpcs_check_features(xpcs, match, interface)) - return xpcs_soft_reset(xpcs); - } - } - - return -ENODEV; -} - -static struct mdio_xpcs_ops xpcs_ops = { - .validate = xpcs_validate, - .config = xpcs_config, - .get_state = xpcs_get_state, - .link_up = xpcs_link_up, - .probe = xpcs_probe, +static const struct xpcs_compat synopsys_xpcs_compat[DW_XPCS_INTERFACE_MAX] = { + [DW_XPCS_USXGMII] = { + .supported = xpcs_usxgmii_features, + .interface = xpcs_usxgmii_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_usxgmii_interfaces), + .an_mode = DW_AN_C73, + }, + [DW_XPCS_10GKR] = { + .supported = xpcs_10gkr_features, + .interface = xpcs_10gkr_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_10gkr_interfaces), + .an_mode = DW_AN_C73, + }, + [DW_XPCS_XLGMII] = { + .supported = xpcs_xlgmii_features, + .interface = xpcs_xlgmii_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_xlgmii_interfaces), + .an_mode = DW_AN_C73, + }, + [DW_XPCS_SGMII] = { + .supported = xpcs_sgmii_features, + .interface = xpcs_sgmii_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_sgmii_interfaces), + .an_mode = DW_AN_C37_SGMII, + }, + [DW_XPCS_2500BASEX] = { + .supported = xpcs_2500basex_features, + .interface = xpcs_2500basex_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_2500basex_features), + .an_mode = DW_2500BASEX, + }, }; -struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) +static const struct xpcs_compat nxp_sja1105_xpcs_compat[DW_XPCS_INTERFACE_MAX] = { + [DW_XPCS_SGMII] = { + .supported = xpcs_sgmii_features, + .interface = xpcs_sgmii_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_sgmii_interfaces), + .an_mode = DW_AN_C37_SGMII, + .pma_config = nxp_sja1105_sgmii_pma_config, + }, +}; + +static const struct xpcs_compat nxp_sja1110_xpcs_compat[DW_XPCS_INTERFACE_MAX] = { + [DW_XPCS_SGMII] = { + .supported = xpcs_sgmii_features, + .interface = xpcs_sgmii_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_sgmii_interfaces), + .an_mode = DW_AN_C37_SGMII, + .pma_config = nxp_sja1110_sgmii_pma_config, + }, + [DW_XPCS_2500BASEX] = { + .supported = xpcs_2500basex_features, + .interface = xpcs_2500basex_interfaces, + .num_interfaces = ARRAY_SIZE(xpcs_2500basex_interfaces), + .an_mode = DW_2500BASEX, + .pma_config = nxp_sja1110_2500basex_pma_config, + }, +}; + +static const struct xpcs_id xpcs_id_list[] = { + { + .id = SYNOPSYS_XPCS_ID, + .mask = SYNOPSYS_XPCS_MASK, + .compat = synopsys_xpcs_compat, + }, { + .id = NXP_SJA1105_XPCS_ID, + .mask = SYNOPSYS_XPCS_MASK, + .compat = nxp_sja1105_xpcs_compat, + }, { + .id = NXP_SJA1110_XPCS_ID, + .mask = SYNOPSYS_XPCS_MASK, + .compat = nxp_sja1110_xpcs_compat, + }, +}; + +static const struct phylink_pcs_ops xpcs_phylink_ops = { + .pcs_config = xpcs_config, + .pcs_get_state = xpcs_get_state, + .pcs_link_up = xpcs_link_up, +}; + +struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, + phy_interface_t interface) { - return &xpcs_ops; + struct dw_xpcs *xpcs; + u32 xpcs_id; + int i, ret; + + xpcs = kzalloc(sizeof(*xpcs), GFP_KERNEL); + if (!xpcs) + return NULL; + + xpcs->mdiodev = mdiodev; + + xpcs_id = xpcs_get_id(xpcs); + + for (i = 0; i < ARRAY_SIZE(xpcs_id_list); i++) { + const struct xpcs_id *entry = &xpcs_id_list[i]; + const struct xpcs_compat *compat; + + if ((xpcs_id & entry->mask) != entry->id) + continue; + + xpcs->id = entry; + + compat = xpcs_find_compat(entry, interface); + if (!compat) { + ret = -ENODEV; + goto out; + } + + xpcs->pcs.ops = &xpcs_phylink_ops; + xpcs->pcs.poll = true; + + ret = xpcs_soft_reset(xpcs, compat); + if (ret) + goto out; + + return xpcs; + } + + ret = -ENODEV; + +out: + kfree(xpcs); + + return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(mdio_xpcs_get_ops); +EXPORT_SYMBOL_GPL(xpcs_create); + +void xpcs_destroy(struct dw_xpcs *xpcs) +{ + kfree(xpcs); +} +EXPORT_SYMBOL_GPL(xpcs_destroy); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/pcs/pcs-xpcs.h b/drivers/net/pcs/pcs-xpcs.h new file mode 100644 index 000000000000..35651d32a224 --- /dev/null +++ b/drivers/net/pcs/pcs-xpcs.h @@ -0,0 +1,115 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 Synopsys, Inc. and/or its affiliates. + * Synopsys DesignWare XPCS helpers + * + * Author: Jose Abreu + */ + +#define SYNOPSYS_XPCS_ID 0x7996ced0 +#define SYNOPSYS_XPCS_MASK 0xffffffff + +/* Vendor regs access */ +#define DW_VENDOR BIT(15) + +/* VR_XS_PCS */ +#define DW_USXGMII_RST BIT(10) +#define DW_USXGMII_EN BIT(9) +#define DW_VR_XS_PCS_DIG_STS 0x0010 +#define DW_RXFIFO_ERR GENMASK(6, 5) + +/* SR_MII */ +#define DW_USXGMII_FULL BIT(8) +#define DW_USXGMII_SS_MASK (BIT(13) | BIT(6) | BIT(5)) +#define DW_USXGMII_10000 (BIT(13) | BIT(6)) +#define DW_USXGMII_5000 (BIT(13) | BIT(5)) +#define DW_USXGMII_2500 (BIT(5)) +#define DW_USXGMII_1000 (BIT(6)) +#define DW_USXGMII_100 (BIT(13)) +#define DW_USXGMII_10 (0) + +/* SR_AN */ +#define DW_SR_AN_ADV1 0x10 +#define DW_SR_AN_ADV2 0x11 +#define DW_SR_AN_ADV3 0x12 +#define DW_SR_AN_LP_ABL1 0x13 +#define DW_SR_AN_LP_ABL2 0x14 +#define DW_SR_AN_LP_ABL3 0x15 + +/* Clause 73 Defines */ +/* AN_LP_ABL1 */ +#define DW_C73_PAUSE BIT(10) +#define DW_C73_ASYM_PAUSE BIT(11) +#define DW_C73_AN_ADV_SF 0x1 +/* AN_LP_ABL2 */ +#define DW_C73_1000KX BIT(5) +#define DW_C73_10000KX4 BIT(6) +#define DW_C73_10000KR BIT(7) +/* AN_LP_ABL3 */ +#define DW_C73_2500KX BIT(0) +#define DW_C73_5000KR BIT(1) + +/* Clause 37 Defines */ +/* VR MII MMD registers offsets */ +#define DW_VR_MII_MMD_CTRL 0x0000 +#define DW_VR_MII_DIG_CTRL1 0x8000 +#define DW_VR_MII_AN_CTRL 0x8001 +#define DW_VR_MII_AN_INTR_STS 0x8002 +/* Enable 2.5G Mode */ +#define DW_VR_MII_DIG_CTRL1_2G5_EN BIT(2) +/* EEE Mode Control Register */ +#define DW_VR_MII_EEE_MCTRL0 0x8006 +#define DW_VR_MII_EEE_MCTRL1 0x800b +#define DW_VR_MII_DIG_CTRL2 0x80e1 + +/* VR_MII_DIG_CTRL1 */ +#define DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW BIT(9) + +/* VR_MII_DIG_CTRL2 */ +#define DW_VR_MII_DIG_CTRL2_TX_POL_INV BIT(4) +#define DW_VR_MII_DIG_CTRL2_RX_POL_INV BIT(0) + +/* VR_MII_AN_CTRL */ +#define DW_VR_MII_AN_CTRL_TX_CONFIG_SHIFT 3 +#define DW_VR_MII_TX_CONFIG_MASK BIT(3) +#define DW_VR_MII_TX_CONFIG_PHY_SIDE_SGMII 0x1 +#define DW_VR_MII_TX_CONFIG_MAC_SIDE_SGMII 0x0 +#define DW_VR_MII_AN_CTRL_PCS_MODE_SHIFT 1 +#define DW_VR_MII_PCS_MODE_MASK GENMASK(2, 1) +#define DW_VR_MII_PCS_MODE_C37_1000BASEX 0x0 +#define DW_VR_MII_PCS_MODE_C37_SGMII 0x2 + +/* VR_MII_AN_INTR_STS */ +#define DW_VR_MII_AN_STS_C37_ANSGM_FD BIT(1) +#define DW_VR_MII_AN_STS_C37_ANSGM_SP_SHIFT 2 +#define DW_VR_MII_AN_STS_C37_ANSGM_SP GENMASK(3, 2) +#define DW_VR_MII_C37_ANSGM_SP_10 0x0 +#define DW_VR_MII_C37_ANSGM_SP_100 0x1 +#define DW_VR_MII_C37_ANSGM_SP_1000 0x2 +#define DW_VR_MII_C37_ANSGM_SP_LNKSTS BIT(4) + +/* SR MII MMD Control defines */ +#define AN_CL37_EN BIT(12) /* Enable Clause 37 auto-nego */ +#define SGMII_SPEED_SS13 BIT(13) /* SGMII speed along with SS6 */ +#define SGMII_SPEED_SS6 BIT(6) /* SGMII speed along with SS13 */ + +/* VR MII EEE Control 0 defines */ +#define DW_VR_MII_EEE_LTX_EN BIT(0) /* LPI Tx Enable */ +#define DW_VR_MII_EEE_LRX_EN BIT(1) /* LPI Rx Enable */ +#define DW_VR_MII_EEE_TX_QUIET_EN BIT(2) /* Tx Quiet Enable */ +#define DW_VR_MII_EEE_RX_QUIET_EN BIT(3) /* Rx Quiet Enable */ +#define DW_VR_MII_EEE_TX_EN_CTRL BIT(4) /* Tx Control Enable */ +#define DW_VR_MII_EEE_RX_EN_CTRL BIT(7) /* Rx Control Enable */ + +#define DW_VR_MII_EEE_MULT_FACT_100NS_SHIFT 8 +#define DW_VR_MII_EEE_MULT_FACT_100NS GENMASK(11, 8) + +/* VR MII EEE Control 1 defines */ +#define DW_VR_MII_EEE_TRN_LPI BIT(0) /* Transparent Mode Enable */ + +int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg); +int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val); + +int nxp_sja1105_sgmii_pma_config(struct dw_xpcs *xpcs); +int nxp_sja1110_sgmii_pma_config(struct dw_xpcs *xpcs); +int nxp_sja1110_2500basex_pma_config(struct dw_xpcs *xpcs); diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 288bf405ebdb..c56f703ae998 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -207,6 +207,11 @@ config MARVELL_88X2222_PHY Support for the Marvell 88X2222 Dual-port Multi-speed Ethernet Transceiver. +config MEDIATEK_GE_PHY + tristate "MediaTek Gigabit Ethernet PHYs" + help + Supports the MediaTek Gigabit Ethernet PHYs. + config MICREL_PHY tristate "Micrel PHYs" help @@ -229,6 +234,12 @@ config MICROSEMI_PHY help Currently supports VSC8514, VSC8530, VSC8531, VSC8540 and VSC8541 PHYs +config MOTORCOMM_PHY + tristate "Motorcomm PHYs" + help + Enables support for Motorcomm network PHYs. + Currently supports the YT8511 gigabit PHY. + config NATIONAL_PHY tristate "National Semiconductor PHYs" help @@ -247,10 +258,11 @@ config NXP_TJA11XX_PHY Currently supports the NXP TJA1100 and TJA1101 PHY. config AT803X_PHY - tristate "Qualcomm Atheros AR803X PHYs" + tristate "Qualcomm Atheros AR803X PHYs and QCA833x PHYs" depends on REGULATOR help - Currently supports the AR8030, AR8031, AR8033 and AR8035 model + Currently supports the AR8030, AR8031, AR8033, AR8035 and internal + QCA8337(Internal qca8k PHY) model config QSEMI_PHY tristate "Quality Semiconductor PHYs" diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index bcda7ed2455d..172bb193ae6a 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -64,12 +64,14 @@ obj-$(CONFIG_LXT_PHY) += lxt.o obj-$(CONFIG_MARVELL_10G_PHY) += marvell10g.o obj-$(CONFIG_MARVELL_PHY) += marvell.o obj-$(CONFIG_MARVELL_88X2222_PHY) += marvell-88x2222.o +obj-$(CONFIG_MEDIATEK_GE_PHY) += mediatek-ge.o obj-$(CONFIG_MESON_GXL_PHY) += meson-gxl.o obj-$(CONFIG_MICREL_KS8995MA) += spi_ks8995.o obj-$(CONFIG_MICREL_PHY) += micrel.o obj-$(CONFIG_MICROCHIP_PHY) += microchip.o obj-$(CONFIG_MICROCHIP_T1_PHY) += microchip_t1.o obj-$(CONFIG_MICROSEMI_PHY) += mscc/ +obj-$(CONFIG_MOTORCOMM_PHY) += motorcomm.o obj-$(CONFIG_NATIONAL_PHY) += national.o obj-$(CONFIG_NXP_C45_TJA11XX_PHY) += nxp-c45-tja11xx.o obj-$(CONFIG_NXP_TJA11XX_PHY) += nxp-tja11xx.o diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c index 55a0b91816e2..5ce6da62cc8e 100644 --- a/drivers/net/phy/adin.c +++ b/drivers/net/phy/adin.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0+ -/** +/* * Driver for Analog Devices Industrial Ethernet PHYs * * Copyright 2019 Analog Devices Inc. diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 32af52dd5aed..5d62b85a4024 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -83,8 +83,8 @@ #define AT803X_MODE_CFG_MASK 0x0F #define AT803X_MODE_CFG_SGMII 0x01 -#define AT803X_PSSR 0x11 /*PHY-Specific Status Register*/ -#define AT803X_PSSR_MR_AN_COMPLETE 0x0200 +#define AT803X_PSSR 0x11 /*PHY-Specific Status Register*/ +#define AT803X_PSSR_MR_AN_COMPLETE 0x0200 #define AT803X_DEBUG_REG_0 0x00 #define AT803X_DEBUG_RX_CLK_DLY_EN BIT(15) @@ -92,10 +92,16 @@ #define AT803X_DEBUG_REG_5 0x05 #define AT803X_DEBUG_TX_CLK_DLY_EN BIT(8) +#define AT803X_DEBUG_REG_3C 0x3C + +#define AT803X_DEBUG_REG_3D 0x3D + #define AT803X_DEBUG_REG_1F 0x1F #define AT803X_DEBUG_PLL_ON BIT(2) #define AT803X_DEBUG_RGMII_1V8 BIT(3) +#define MDIO_AZ_DEBUG 0x800D + /* AT803x supports either the XTAL input pad, an internal PLL or the * DSP as clock reference for the clock output pad. The XTAL reference * is only used for 25 MHz output, all other frequencies need the PLL. @@ -128,33 +134,59 @@ #define AT803X_CLK_OUT_STRENGTH_HALF 1 #define AT803X_CLK_OUT_STRENGTH_QUARTER 2 -#define AT803X_DEFAULT_DOWNSHIFT 5 -#define AT803X_MIN_DOWNSHIFT 2 -#define AT803X_MAX_DOWNSHIFT 9 +#define AT803X_DEFAULT_DOWNSHIFT 5 +#define AT803X_MIN_DOWNSHIFT 2 +#define AT803X_MAX_DOWNSHIFT 9 #define AT803X_MMD3_SMARTEEE_CTL1 0x805b #define AT803X_MMD3_SMARTEEE_CTL2 0x805c #define AT803X_MMD3_SMARTEEE_CTL3 0x805d #define AT803X_MMD3_SMARTEEE_CTL3_LPI_EN BIT(8) -#define ATH9331_PHY_ID 0x004dd041 -#define ATH8030_PHY_ID 0x004dd076 -#define ATH8031_PHY_ID 0x004dd074 -#define ATH8032_PHY_ID 0x004dd023 -#define ATH8035_PHY_ID 0x004dd072 +#define ATH9331_PHY_ID 0x004dd041 +#define ATH8030_PHY_ID 0x004dd076 +#define ATH8031_PHY_ID 0x004dd074 +#define ATH8032_PHY_ID 0x004dd023 +#define ATH8035_PHY_ID 0x004dd072 #define AT8030_PHY_ID_MASK 0xffffffef -#define AT803X_PAGE_FIBER 0 -#define AT803X_PAGE_COPPER 1 +#define QCA8327_PHY_ID 0x004dd034 +#define QCA8337_PHY_ID 0x004dd036 +#define QCA8K_PHY_ID_MASK 0xffffffff + +#define QCA8K_DEVFLAGS_REVISION_MASK GENMASK(2, 0) + +#define AT803X_PAGE_FIBER 0 +#define AT803X_PAGE_COPPER 1 + +/* don't turn off internal PLL */ +#define AT803X_KEEP_PLL_ENABLED BIT(0) +#define AT803X_DISABLE_SMARTEEE BIT(1) MODULE_DESCRIPTION("Qualcomm Atheros AR803x PHY driver"); MODULE_AUTHOR("Matus Ujhelyi"); MODULE_LICENSE("GPL"); +enum stat_access_type { + PHY, + MMD +}; + +struct at803x_hw_stat { + const char *string; + u8 reg; + u32 mask; + enum stat_access_type access_type; +}; + +static struct at803x_hw_stat at803x_hw_stats[] = { + { "phy_idle_errors", 0xa, GENMASK(7, 0), PHY}, + { "phy_receive_errors", 0x15, GENMASK(15, 0), PHY}, + { "eee_wake_errors", 0x16, GENMASK(15, 0), MMD}, +}; + struct at803x_priv { int flags; -#define AT803X_KEEP_PLL_ENABLED BIT(0) /* don't turn off internal PLL */ -#define AT803X_DISABLE_SMARTEEE BIT(1) u16 clk_25m_reg; u16 clk_25m_mask; u8 smarteee_lpi_tw_1g; @@ -162,6 +194,7 @@ struct at803x_priv { struct regulator_dev *vddio_rdev; struct regulator_dev *vddh_rdev; struct regulator *vddio; + u64 stats[ARRAY_SIZE(at803x_hw_stats)]; }; struct at803x_context { @@ -173,6 +206,17 @@ struct at803x_context { u16 led_control; }; +static int at803x_debug_reg_write(struct phy_device *phydev, u16 reg, u16 data) +{ + int ret; + + ret = phy_write(phydev, AT803X_DEBUG_ADDR, reg); + if (ret < 0) + return ret; + + return phy_write(phydev, AT803X_DEBUG_DATA, data); +} + static int at803x_debug_reg_read(struct phy_device *phydev, u16 reg) { int ret; @@ -335,6 +379,53 @@ static void at803x_get_wol(struct phy_device *phydev, wol->wolopts |= WAKE_MAGIC; } +static int at803x_get_sset_count(struct phy_device *phydev) +{ + return ARRAY_SIZE(at803x_hw_stats); +} + +static void at803x_get_strings(struct phy_device *phydev, u8 *data) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(at803x_hw_stats); i++) { + strscpy(data + i * ETH_GSTRING_LEN, + at803x_hw_stats[i].string, ETH_GSTRING_LEN); + } +} + +static u64 at803x_get_stat(struct phy_device *phydev, int i) +{ + struct at803x_hw_stat stat = at803x_hw_stats[i]; + struct at803x_priv *priv = phydev->priv; + int val; + u64 ret; + + if (stat.access_type == MMD) + val = phy_read_mmd(phydev, MDIO_MMD_PCS, stat.reg); + else + val = phy_read(phydev, stat.reg); + + if (val < 0) { + ret = U64_MAX; + } else { + val = val & stat.mask; + priv->stats[i] += val; + ret = priv->stats[i]; + } + + return ret; +} + +static void at803x_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(at803x_hw_stats); i++) + data[i] = at803x_get_stat(phydev, i); +} + static int at803x_suspend(struct phy_device *phydev) { int value; @@ -610,6 +701,34 @@ static void at803x_remove(struct phy_device *phydev) regulator_disable(priv->vddio); } +static int at803x_get_features(struct phy_device *phydev) +{ + int err; + + err = genphy_read_abilities(phydev); + if (err) + return err; + + if (!at803x_match_phy_id(phydev, ATH8031_PHY_ID)) + return 0; + + /* AR8031/AR8033 have different status registers + * for copper and fiber operation. However, the + * extended status register is the same for both + * operation modes. + * + * As a result of that, ESTATUS_1000_XFULL is set + * to 1 even when operating in copper TP mode. + * + * Remove this mode from the supported link modes, + * as this driver currently only supports copper + * operation. + */ + linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, + phydev->supported); + return 0; +} + static int at803x_smarteee_config(struct phy_device *phydev) { struct at803x_priv *priv = phydev->priv; @@ -1170,6 +1289,34 @@ static int at803x_cable_test_start(struct phy_device *phydev) return 0; } +static int qca83xx_config_init(struct phy_device *phydev) +{ + u8 switch_revision; + + switch_revision = phydev->dev_flags & QCA8K_DEVFLAGS_REVISION_MASK; + + switch (switch_revision) { + case 1: + /* For 100M waveform */ + at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_0, 0x02ea); + /* Turn on Gigabit clock */ + at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_3D, 0x68a0); + break; + + case 2: + phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, 0x0); + fallthrough; + case 4: + phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_AZ_DEBUG, 0x803f); + at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_3D, 0x6860); + at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_5, 0x2c46); + at803x_debug_reg_write(phydev, AT803X_DEBUG_REG_3C, 0x6000); + break; + } + + return 0; +} + static struct phy_driver at803x_driver[] = { { /* Qualcomm Atheros AR8035 */ @@ -1225,7 +1372,7 @@ static struct phy_driver at803x_driver[] = { .resume = at803x_resume, .read_page = at803x_read_page, .write_page = at803x_write_page, - /* PHY_GBIT_FEATURES */ + .get_features = at803x_get_features, .read_status = at803x_read_status, .config_intr = &at803x_config_intr, .handle_interrupt = at803x_handle_interrupt, @@ -1266,7 +1413,20 @@ static struct phy_driver at803x_driver[] = { .read_status = at803x_read_status, .soft_reset = genphy_soft_reset, .config_aneg = at803x_config_aneg, -} }; +}, { + /* QCA8337 */ + .phy_id = QCA8337_PHY_ID, + .phy_id_mask = QCA8K_PHY_ID_MASK, + .name = "QCA PHY 8337", + /* PHY_GBIT_FEATURES */ + .probe = at803x_probe, + .flags = PHY_IS_INTERNAL, + .config_init = qca83xx_config_init, + .soft_reset = genphy_soft_reset, + .get_sset_count = at803x_get_sset_count, + .get_strings = at803x_get_strings, + .get_stats = at803x_get_stats, +}, }; module_phy_driver(at803x_driver); diff --git a/drivers/net/phy/ax88796b.c b/drivers/net/phy/ax88796b.c index 79bf7ef1fcfd..457896337505 100644 --- a/drivers/net/phy/ax88796b.c +++ b/drivers/net/phy/ax88796b.c @@ -10,6 +10,8 @@ #include #include +#define PHY_ID_ASIX_AX88772A 0x003b1861 +#define PHY_ID_ASIX_AX88772C 0x003b1881 #define PHY_ID_ASIX_AX88796B 0x003b1841 MODULE_DESCRIPTION("Asix PHY driver"); @@ -39,7 +41,75 @@ static int asix_soft_reset(struct phy_device *phydev) return genphy_soft_reset(phydev); } -static struct phy_driver asix_driver[] = { { +/* AX88772A is not working properly with some old switches (NETGEAR EN 108TP): + * after autoneg is done and the link status is reported as active, the MII_LPA + * register is 0. This issue is not reproducible on AX88772C. + */ +static int asix_ax88772a_read_status(struct phy_device *phydev) +{ + int ret, val; + + ret = genphy_update_link(phydev); + if (ret) + return ret; + + if (!phydev->link) + return 0; + + /* If MII_LPA is 0, phy_resolve_aneg_linkmode() will fail to resolve + * linkmode so use MII_BMCR as default values. + */ + val = phy_read(phydev, MII_BMCR); + if (val < 0) + return val; + + if (val & BMCR_SPEED100) + phydev->speed = SPEED_100; + else + phydev->speed = SPEED_10; + + if (val & BMCR_FULLDPLX) + phydev->duplex = DUPLEX_FULL; + else + phydev->duplex = DUPLEX_HALF; + + ret = genphy_read_lpa(phydev); + if (ret < 0) + return ret; + + if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) + phy_resolve_aneg_linkmode(phydev); + + return 0; +} + +static void asix_ax88772a_link_change_notify(struct phy_device *phydev) +{ + /* Reset PHY, otherwise MII_LPA will provide outdated information. + * This issue is reproducible only with some link partner PHYs + */ + if (phydev->state == PHY_NOLINK && phydev->drv->soft_reset) + phydev->drv->soft_reset(phydev); +} + +static struct phy_driver asix_driver[] = { +{ + PHY_ID_MATCH_EXACT(PHY_ID_ASIX_AX88772A), + .name = "Asix Electronics AX88772A", + .flags = PHY_IS_INTERNAL, + .read_status = asix_ax88772a_read_status, + .suspend = genphy_suspend, + .resume = genphy_resume, + .soft_reset = asix_soft_reset, + .link_change_notify = asix_ax88772a_link_change_notify, +}, { + PHY_ID_MATCH_EXACT(PHY_ID_ASIX_AX88772C), + .name = "Asix Electronics AX88772C", + .flags = PHY_IS_INTERNAL, + .suspend = genphy_suspend, + .resume = genphy_resume, + .soft_reset = asix_soft_reset, +}, { .phy_id = PHY_ID_ASIX_AX88796B, .name = "Asix Electronics AX88796B", .phy_id_mask = 0xfffffff0, @@ -50,6 +120,8 @@ static struct phy_driver asix_driver[] = { { module_phy_driver(asix_driver); static struct mdio_device_id __maybe_unused asix_tbl[] = { + { PHY_ID_MATCH_EXACT(PHY_ID_ASIX_AX88772A) }, + { PHY_ID_MATCH_EXACT(PHY_ID_ASIX_AX88772C) }, { PHY_ID_ASIX_AX88796B, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c index 4ac8fd190e9d..313563482690 100644 --- a/drivers/net/phy/bcm87xx.c +++ b/drivers/net/phy/bcm87xx.c @@ -54,9 +54,9 @@ static int bcm87xx_of_reg_init(struct phy_device *phydev) u16 reg = be32_to_cpup(paddr++); u16 mask = be32_to_cpup(paddr++); u16 val_bits = be32_to_cpup(paddr++); - int val; u32 regnum = mdiobus_c45_addr(devid, reg); - val = 0; + int val = 0; + if (mask) { val = phy_read(phydev, regnum); if (val < 0) { diff --git a/drivers/net/phy/davicom.c b/drivers/net/phy/davicom.c index a3b3842c67e5..4ac4bce1bf32 100644 --- a/drivers/net/phy/davicom.c +++ b/drivers/net/phy/davicom.c @@ -43,10 +43,10 @@ #define MII_DM9161_INTR_DPLX_CHANGE 0x0010 #define MII_DM9161_INTR_SPD_CHANGE 0x0008 #define MII_DM9161_INTR_LINK_CHANGE 0x0004 -#define MII_DM9161_INTR_INIT 0x0000 +#define MII_DM9161_INTR_INIT 0x0000 #define MII_DM9161_INTR_STOP \ -(MII_DM9161_INTR_DPLX_MASK | MII_DM9161_INTR_SPD_MASK \ - | MII_DM9161_INTR_LINK_MASK | MII_DM9161_INTR_MASK) + (MII_DM9161_INTR_DPLX_MASK | MII_DM9161_INTR_SPD_MASK | \ + MII_DM9161_INTR_LINK_MASK | MII_DM9161_INTR_MASK) #define MII_DM9161_INTR_CHANGE \ (MII_DM9161_INTR_DPLX_CHANGE | \ MII_DM9161_INTR_SPD_CHANGE | \ diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 0d79f68f301c..705c16675b80 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -170,9 +170,9 @@ static ushort gpio_tab[GPIO_TABLE_SIZE] = { module_param(chosen_phy, int, 0444); module_param_array(gpio_tab, ushort, NULL, 0444); -MODULE_PARM_DESC(chosen_phy, \ +MODULE_PARM_DESC(chosen_phy, "The address of the PHY to use for the ancillary clock features"); -MODULE_PARM_DESC(gpio_tab, \ +MODULE_PARM_DESC(gpio_tab, "Which GPIO line to use for which purpose: cal,perout,extts1,...,extts6"); static void dp83640_gpio_defaults(struct ptp_pin_desc *pd) @@ -615,6 +615,7 @@ static void prune_rx_ts(struct dp83640_private *dp83640) static void enable_broadcast(struct phy_device *phydev, int init_page, int on) { int val; + phy_write(phydev, PAGESEL, 0); val = phy_read(phydev, PHYCR2); if (on) diff --git a/drivers/net/phy/et1011c.c b/drivers/net/phy/et1011c.c index 09e07b902d3a..be1b71d7cab7 100644 --- a/drivers/net/phy/et1011c.c +++ b/drivers/net/phy/et1011c.c @@ -46,8 +46,8 @@ MODULE_LICENSE("GPL"); static int et1011c_config_aneg(struct phy_device *phydev) { - int ctl = 0; - ctl = phy_read(phydev, MII_BMCR); + int ctl = phy_read(phydev, MII_BMCR); + if (ctl < 0) return ctl; ctl &= ~(BMCR_FULLDPLX | BMCR_SPEED100 | BMCR_SPEED1000 | @@ -60,9 +60,10 @@ static int et1011c_config_aneg(struct phy_device *phydev) static int et1011c_read_status(struct phy_device *phydev) { + static int speed; int ret; u32 val; - static int speed; + ret = genphy_read_status(phydev); if (speed != phydev->speed) { @@ -72,10 +73,10 @@ static int et1011c_read_status(struct phy_device *phydev) ET1011C_GIGABIT_SPEED) { val = phy_read(phydev, ET1011C_CONFIG_REG); val &= ~ET1011C_TX_FIFO_MASK; - phy_write(phydev, ET1011C_CONFIG_REG, val\ - | ET1011C_GMII_INTERFACE\ - | ET1011C_SYS_CLK_EN\ - | ET1011C_TX_FIFO_DEPTH_16); + phy_write(phydev, ET1011C_CONFIG_REG, val | + ET1011C_GMII_INTERFACE | + ET1011C_SYS_CLK_EN | + ET1011C_TX_FIFO_DEPTH_16); } } diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 18d81f43f2a8..c65fb5f5d2dc 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -161,8 +161,8 @@ static int fixed_phy_add_gpiod(unsigned int irq, int phy_addr, } int fixed_phy_add(unsigned int irq, int phy_addr, - struct fixed_phy_status *status) { - + struct fixed_phy_status *status) +{ return fixed_phy_add_gpiod(irq, phy_addr, status, NULL); } EXPORT_SYMBOL_GPL(fixed_phy_add); diff --git a/drivers/net/phy/lxt.c b/drivers/net/phy/lxt.c index bde3356a2f86..e3bf827b7959 100644 --- a/drivers/net/phy/lxt.c +++ b/drivers/net/phy/lxt.c @@ -242,8 +242,8 @@ static int lxt973a2_read_status(struct phy_device *phydev) return lpa; /* If both registers are equal, it is suspect but not - * impossible, hence a new try - */ + * impossible, hence a new try + */ } while (lpa == adv && retry--); mii_lpa_to_linkmode_lpa_t(phydev->lp_advertising, lpa); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index e6721c1c26c2..3de93c9f2744 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -367,39 +367,24 @@ static irqreturn_t marvell_handle_interrupt(struct phy_device *phydev) static int marvell_set_polarity(struct phy_device *phydev, int polarity) { - int reg; - int err; - int val; + u16 val; - /* get the current settings */ - reg = phy_read(phydev, MII_M1011_PHY_SCR); - if (reg < 0) - return reg; - - val = reg; - val &= ~MII_M1011_PHY_SCR_AUTO_CROSS; switch (polarity) { case ETH_TP_MDI: - val |= MII_M1011_PHY_SCR_MDI; + val = MII_M1011_PHY_SCR_MDI; break; case ETH_TP_MDI_X: - val |= MII_M1011_PHY_SCR_MDI_X; + val = MII_M1011_PHY_SCR_MDI_X; break; case ETH_TP_MDI_AUTO: case ETH_TP_MDI_INVALID: default: - val |= MII_M1011_PHY_SCR_AUTO_CROSS; + val = MII_M1011_PHY_SCR_AUTO_CROSS; break; } - if (val != reg) { - /* Set the new polarity value in the register */ - err = phy_write(phydev, MII_M1011_PHY_SCR, val); - if (err) - return err; - } - - return val != reg; + return phy_modify_changed(phydev, MII_M1011_PHY_SCR, + MII_M1011_PHY_SCR_AUTO_CROSS, val); } static int marvell_config_aneg(struct phy_device *phydev) @@ -824,14 +809,19 @@ static int m88e1111_config_init_rgmii_delays(struct phy_device *phydev) { int delay; - if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) { + switch (phydev->interface) { + case PHY_INTERFACE_MODE_RGMII_ID: delay = MII_M1111_RGMII_RX_DELAY | MII_M1111_RGMII_TX_DELAY; - } else if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) { + break; + case PHY_INTERFACE_MODE_RGMII_RXID: delay = MII_M1111_RGMII_RX_DELAY; - } else if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) { + break; + case PHY_INTERFACE_MODE_RGMII_TXID: delay = MII_M1111_RGMII_TX_DELAY; - } else { + break; + default: delay = 0; + break; } return phy_modify(phydev, MII_M1111_PHY_EXT_CR, diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 6045ad3def12..53f034fc2ef7 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -175,6 +175,7 @@ EXPORT_SYMBOL(mdiobus_alloc_size); static void mdiobus_release(struct device *d) { struct mii_bus *bus = to_mii_bus(d); + BUG_ON(bus->state != MDIOBUS_RELEASED && /* for compatibility with error handling in drivers */ bus->state != MDIOBUS_ALLOCATED); @@ -458,8 +459,7 @@ static void of_mdiobus_link_mdiodev(struct mii_bus *bus, continue; if (addr == mdiodev->addr) { - dev->of_node = child; - dev->fwnode = of_fwnode_handle(child); + device_set_node(dev, of_fwnode_handle(child)); return; } } diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index 0837319a52d7..c94cb5382dc9 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -77,7 +77,7 @@ int mdio_device_register(struct mdio_device *mdiodev) { int err; - dev_dbg(&mdiodev->dev, "mdio_device_register\n"); + dev_dbg(&mdiodev->dev, "%s\n", __func__); err = mdiobus_register_device(mdiodev); if (err) @@ -188,7 +188,7 @@ int mdio_driver_register(struct mdio_driver *drv) struct mdio_driver_common *mdiodrv = &drv->mdiodrv; int retval; - pr_debug("mdio_driver_register: %s\n", mdiodrv->driver.name); + pr_debug("%s: %s\n", __func__, mdiodrv->driver.name); mdiodrv->driver.bus = &mdio_bus_type; mdiodrv->driver.probe = mdio_probe; diff --git a/drivers/net/phy/mediatek-ge.c b/drivers/net/phy/mediatek-ge.c new file mode 100644 index 000000000000..11ff335d6228 --- /dev/null +++ b/drivers/net/phy/mediatek-ge.c @@ -0,0 +1,112 @@ +// SPDX-License-Identifier: GPL-2.0+ +#include +#include +#include + +#define MTK_EXT_PAGE_ACCESS 0x1f +#define MTK_PHY_PAGE_STANDARD 0x0000 +#define MTK_PHY_PAGE_EXTENDED 0x0001 +#define MTK_PHY_PAGE_EXTENDED_2 0x0002 +#define MTK_PHY_PAGE_EXTENDED_3 0x0003 +#define MTK_PHY_PAGE_EXTENDED_2A30 0x2a30 +#define MTK_PHY_PAGE_EXTENDED_52B5 0x52b5 + +static int mtk_gephy_read_page(struct phy_device *phydev) +{ + return __phy_read(phydev, MTK_EXT_PAGE_ACCESS); +} + +static int mtk_gephy_write_page(struct phy_device *phydev, int page) +{ + return __phy_write(phydev, MTK_EXT_PAGE_ACCESS, page); +} + +static void mtk_gephy_config_init(struct phy_device *phydev) +{ + /* Disable EEE */ + phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, 0); + + /* Enable HW auto downshift */ + phy_modify_paged(phydev, MTK_PHY_PAGE_EXTENDED, 0x14, 0, BIT(4)); + + /* Increase SlvDPSready time */ + phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); + __phy_write(phydev, 0x10, 0xafae); + __phy_write(phydev, 0x12, 0x2f); + __phy_write(phydev, 0x10, 0x8fae); + phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); + + /* Adjust 100_mse_threshold */ + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x123, 0xffff); + + /* Disable mcc */ + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0xa6, 0x300); +} + +static int mt7530_phy_config_init(struct phy_device *phydev) +{ + mtk_gephy_config_init(phydev); + + /* Increase post_update_timer */ + phy_write_paged(phydev, MTK_PHY_PAGE_EXTENDED_3, 0x11, 0x4b); + + return 0; +} + +static int mt7531_phy_config_init(struct phy_device *phydev) +{ + if (phydev->interface != PHY_INTERFACE_MODE_INTERNAL) + return -EINVAL; + + mtk_gephy_config_init(phydev); + + /* PHY link down power saving enable */ + phy_set_bits(phydev, 0x17, BIT(4)); + phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, 0xc6, 0x300); + + /* Set TX Pair delay selection */ + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x13, 0x404); + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x14, 0x404); + + return 0; +} + +static struct phy_driver mtk_gephy_driver[] = { + { + PHY_ID_MATCH_EXACT(0x03a29412), + .name = "MediaTek MT7530 PHY", + .config_init = mt7530_phy_config_init, + /* Interrupts are handled by the switch, not the PHY + * itself. + */ + .config_intr = genphy_no_config_intr, + .handle_interrupt = genphy_handle_interrupt_no_ack, + .read_page = mtk_gephy_read_page, + .write_page = mtk_gephy_write_page, + }, + { + PHY_ID_MATCH_EXACT(0x03a29441), + .name = "MediaTek MT7531 PHY", + .config_init = mt7531_phy_config_init, + /* Interrupts are handled by the switch, not the PHY + * itself. + */ + .config_intr = genphy_no_config_intr, + .handle_interrupt = genphy_handle_interrupt_no_ack, + .read_page = mtk_gephy_read_page, + .write_page = mtk_gephy_write_page, + }, +}; + +module_phy_driver(mtk_gephy_driver); + +static struct mdio_device_id __maybe_unused mtk_gephy_tbl[] = { + { PHY_ID_MATCH_VENDOR(0x03a29400) }, + { } +}; + +MODULE_DESCRIPTION("MediaTek Gigabit Ethernet PHY driver"); +MODULE_AUTHOR("DENG, Qingfang "); +MODULE_LICENSE("GPL"); + +MODULE_DEVICE_TABLE(mdio, mtk_gephy_tbl); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index a14a00328fa3..4d53886f7d51 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -20,6 +20,7 @@ */ #include +#include #include #include #include @@ -38,42 +39,60 @@ /* general Interrupt control/status reg in vendor specific block. */ #define MII_KSZPHY_INTCS 0x1B -#define KSZPHY_INTCS_JABBER BIT(15) -#define KSZPHY_INTCS_RECEIVE_ERR BIT(14) -#define KSZPHY_INTCS_PAGE_RECEIVE BIT(13) -#define KSZPHY_INTCS_PARELLEL BIT(12) -#define KSZPHY_INTCS_LINK_PARTNER_ACK BIT(11) -#define KSZPHY_INTCS_LINK_DOWN BIT(10) -#define KSZPHY_INTCS_REMOTE_FAULT BIT(9) -#define KSZPHY_INTCS_LINK_UP BIT(8) -#define KSZPHY_INTCS_ALL (KSZPHY_INTCS_LINK_UP |\ +#define KSZPHY_INTCS_JABBER BIT(15) +#define KSZPHY_INTCS_RECEIVE_ERR BIT(14) +#define KSZPHY_INTCS_PAGE_RECEIVE BIT(13) +#define KSZPHY_INTCS_PARELLEL BIT(12) +#define KSZPHY_INTCS_LINK_PARTNER_ACK BIT(11) +#define KSZPHY_INTCS_LINK_DOWN BIT(10) +#define KSZPHY_INTCS_REMOTE_FAULT BIT(9) +#define KSZPHY_INTCS_LINK_UP BIT(8) +#define KSZPHY_INTCS_ALL (KSZPHY_INTCS_LINK_UP |\ KSZPHY_INTCS_LINK_DOWN) -#define KSZPHY_INTCS_LINK_DOWN_STATUS BIT(2) -#define KSZPHY_INTCS_LINK_UP_STATUS BIT(0) -#define KSZPHY_INTCS_STATUS (KSZPHY_INTCS_LINK_DOWN_STATUS |\ +#define KSZPHY_INTCS_LINK_DOWN_STATUS BIT(2) +#define KSZPHY_INTCS_LINK_UP_STATUS BIT(0) +#define KSZPHY_INTCS_STATUS (KSZPHY_INTCS_LINK_DOWN_STATUS |\ KSZPHY_INTCS_LINK_UP_STATUS) +/* LinkMD Control/Status */ +#define KSZ8081_LMD 0x1d +#define KSZ8081_LMD_ENABLE_TEST BIT(15) +#define KSZ8081_LMD_STAT_NORMAL 0 +#define KSZ8081_LMD_STAT_OPEN 1 +#define KSZ8081_LMD_STAT_SHORT 2 +#define KSZ8081_LMD_STAT_FAIL 3 +#define KSZ8081_LMD_STAT_MASK GENMASK(14, 13) +/* Short cable (<10 meter) has been detected by LinkMD */ +#define KSZ8081_LMD_SHORT_INDICATOR BIT(12) +#define KSZ8081_LMD_DELTA_TIME_MASK GENMASK(8, 0) + /* PHY Control 1 */ -#define MII_KSZPHY_CTRL_1 0x1e +#define MII_KSZPHY_CTRL_1 0x1e +#define KSZ8081_CTRL1_MDIX_STAT BIT(4) /* PHY Control 2 / PHY Control (if no PHY Control 1) */ -#define MII_KSZPHY_CTRL_2 0x1f -#define MII_KSZPHY_CTRL MII_KSZPHY_CTRL_2 +#define MII_KSZPHY_CTRL_2 0x1f +#define MII_KSZPHY_CTRL MII_KSZPHY_CTRL_2 /* bitmap of PHY register to set interrupt mode */ +#define KSZ8081_CTRL2_HP_MDIX BIT(15) +#define KSZ8081_CTRL2_MDI_MDI_X_SELECT BIT(14) +#define KSZ8081_CTRL2_DISABLE_AUTO_MDIX BIT(13) +#define KSZ8081_CTRL2_FORCE_LINK BIT(11) +#define KSZ8081_CTRL2_POWER_SAVING BIT(10) #define KSZPHY_CTRL_INT_ACTIVE_HIGH BIT(9) #define KSZPHY_RMII_REF_CLK_SEL BIT(7) /* Write/read to/from extended registers */ -#define MII_KSZPHY_EXTREG 0x0b -#define KSZPHY_EXTREG_WRITE 0x8000 +#define MII_KSZPHY_EXTREG 0x0b +#define KSZPHY_EXTREG_WRITE 0x8000 -#define MII_KSZPHY_EXTREG_WRITE 0x0c -#define MII_KSZPHY_EXTREG_READ 0x0d +#define MII_KSZPHY_EXTREG_WRITE 0x0c +#define MII_KSZPHY_EXTREG_READ 0x0d /* Extended registers */ -#define MII_KSZPHY_CLK_CONTROL_PAD_SKEW 0x104 -#define MII_KSZPHY_RX_DATA_PAD_SKEW 0x105 -#define MII_KSZPHY_TX_DATA_PAD_SKEW 0x106 +#define MII_KSZPHY_CLK_CONTROL_PAD_SKEW 0x104 +#define MII_KSZPHY_RX_DATA_PAD_SKEW 0x105 +#define MII_KSZPHY_TX_DATA_PAD_SKEW 0x106 #define PS_TO_REG 200 @@ -422,6 +441,87 @@ static int ksz8081_config_init(struct phy_device *phydev) return kszphy_config_init(phydev); } +static int ksz8081_config_mdix(struct phy_device *phydev, u8 ctrl) +{ + u16 val; + + switch (ctrl) { + case ETH_TP_MDI: + val = KSZ8081_CTRL2_DISABLE_AUTO_MDIX; + break; + case ETH_TP_MDI_X: + val = KSZ8081_CTRL2_DISABLE_AUTO_MDIX | + KSZ8081_CTRL2_MDI_MDI_X_SELECT; + break; + case ETH_TP_MDI_AUTO: + val = 0; + break; + default: + return 0; + } + + return phy_modify(phydev, MII_KSZPHY_CTRL_2, + KSZ8081_CTRL2_HP_MDIX | + KSZ8081_CTRL2_MDI_MDI_X_SELECT | + KSZ8081_CTRL2_DISABLE_AUTO_MDIX, + KSZ8081_CTRL2_HP_MDIX | val); +} + +static int ksz8081_config_aneg(struct phy_device *phydev) +{ + int ret; + + ret = genphy_config_aneg(phydev); + if (ret) + return ret; + + /* The MDI-X configuration is automatically changed by the PHY after + * switching from autoneg off to on. So, take MDI-X configuration under + * own control and set it after autoneg configuration was done. + */ + return ksz8081_config_mdix(phydev, phydev->mdix_ctrl); +} + +static int ksz8081_mdix_update(struct phy_device *phydev) +{ + int ret; + + ret = phy_read(phydev, MII_KSZPHY_CTRL_2); + if (ret < 0) + return ret; + + if (ret & KSZ8081_CTRL2_DISABLE_AUTO_MDIX) { + if (ret & KSZ8081_CTRL2_MDI_MDI_X_SELECT) + phydev->mdix_ctrl = ETH_TP_MDI_X; + else + phydev->mdix_ctrl = ETH_TP_MDI; + } else { + phydev->mdix_ctrl = ETH_TP_MDI_AUTO; + } + + ret = phy_read(phydev, MII_KSZPHY_CTRL_1); + if (ret < 0) + return ret; + + if (ret & KSZ8081_CTRL1_MDIX_STAT) + phydev->mdix = ETH_TP_MDI; + else + phydev->mdix = ETH_TP_MDI_X; + + return 0; +} + +static int ksz8081_read_status(struct phy_device *phydev) +{ + int ret; + + ret = ksz8081_mdix_update(phydev); + if (ret < 0) + return ret; + + return genphy_read_status(phydev); +} + static int ksz8061_config_init(struct phy_device *phydev) { int ret; @@ -488,8 +588,7 @@ static int ksz9021_load_values_from_of(struct phy_device *phydev, static int ksz9021_config_init(struct phy_device *phydev) { - const struct device *dev = &phydev->mdio.dev; - const struct device_node *of_node = dev->of_node; + const struct device_node *of_node; const struct device *dev_walker; /* The Micrel driver has a deprecated option to place phy OF @@ -711,8 +810,7 @@ static int ksz9031_config_rgmii_delay(struct phy_device *phydev) static int ksz9031_config_init(struct phy_device *phydev) { - const struct device *dev = &phydev->mdio.dev; - const struct device_node *of_node = dev->of_node; + const struct device_node *of_node; static const char *clk_skews[2] = {"rxc-skew-ps", "txc-skew-ps"}; static const char *rx_data_skews[4] = { "rxd0-skew-ps", "rxd1-skew-ps", @@ -907,8 +1005,7 @@ static int ksz9131_config_rgmii_delay(struct phy_device *phydev) static int ksz9131_config_init(struct phy_device *phydev) { - const struct device *dev = &phydev->mdio.dev; - struct device_node *of_node = dev->of_node; + struct device_node *of_node; char *clk_skews[2] = {"rxc-skew-psec", "txc-skew-psec"}; char *rx_data_skews[4] = { "rxd0-skew-psec", "rxd1-skew-psec", @@ -1048,6 +1145,92 @@ static int ksz8873mll_config_aneg(struct phy_device *phydev) return 0; } +static int ksz886x_config_mdix(struct phy_device *phydev, u8 ctrl) +{ + u16 val; + + switch (ctrl) { + case ETH_TP_MDI: + val = KSZ886X_BMCR_DISABLE_AUTO_MDIX; + break; + case ETH_TP_MDI_X: + /* Note: The naming of the bit KSZ886X_BMCR_FORCE_MDI is bit + * counter intuitive, the "-X" in "1 = Force MDI" in the data + * sheet seems to be missing: + * 1 = Force MDI (sic!) (transmit on RX+/RX- pins) + * 0 = Normal operation (transmit on TX+/TX- pins) + */ + val = KSZ886X_BMCR_DISABLE_AUTO_MDIX | KSZ886X_BMCR_FORCE_MDI; + break; + case ETH_TP_MDI_AUTO: + val = 0; + break; + default: + return 0; + } + + return phy_modify(phydev, MII_BMCR, + KSZ886X_BMCR_HP_MDIX | KSZ886X_BMCR_FORCE_MDI | + KSZ886X_BMCR_DISABLE_AUTO_MDIX, + KSZ886X_BMCR_HP_MDIX | val); +} + +static int ksz886x_config_aneg(struct phy_device *phydev) +{ + int ret; + + ret = genphy_config_aneg(phydev); + if (ret) + return ret; + + /* The MDI-X configuration is automatically changed by the PHY after + * switching from autoneg off to on. So, take MDI-X configuration under + * own control and set it after autoneg configuration was done. + */ + return ksz886x_config_mdix(phydev, phydev->mdix_ctrl); +} + +static int ksz886x_mdix_update(struct phy_device *phydev) +{ + int ret; + + ret = phy_read(phydev, MII_BMCR); + if (ret < 0) + return ret; + + if (ret & KSZ886X_BMCR_DISABLE_AUTO_MDIX) { + if (ret & KSZ886X_BMCR_FORCE_MDI) + phydev->mdix_ctrl = ETH_TP_MDI_X; + else + phydev->mdix_ctrl = ETH_TP_MDI; + } else { + phydev->mdix_ctrl = ETH_TP_MDI_AUTO; + } + + ret = phy_read(phydev, MII_KSZPHY_CTRL); + if (ret < 0) + return ret; + + /* Same reverse logic as KSZ886X_BMCR_FORCE_MDI */ + if (ret & KSZ886X_CTRL_MDIX_STAT) + phydev->mdix = ETH_TP_MDI_X; + else + phydev->mdix = ETH_TP_MDI; + + return 0; +} + +static int ksz886x_read_status(struct phy_device *phydev) +{ + int ret; + + ret = ksz886x_mdix_update(phydev); + if (ret < 0) + return ret; + + return genphy_read_status(phydev); +} + static int kszphy_get_sset_count(struct phy_device *phydev) { return ARRAY_SIZE(kszphy_hw_stats); @@ -1193,6 +1376,167 @@ static int kszphy_probe(struct phy_device *phydev) return 0; } +static int ksz886x_cable_test_start(struct phy_device *phydev) +{ + if (phydev->dev_flags & MICREL_KSZ8_P1_ERRATA) + return -EOPNOTSUPP; + + /* If autoneg is enabled, we won't be able to test cross pair + * short. In this case, the PHY will "detect" a link and + * confuse the internal state machine - disable auto neg here. + * If autoneg is disabled, we should set the speed to 10mbit. + */ + return phy_clear_bits(phydev, MII_BMCR, BMCR_ANENABLE | BMCR_SPEED100); +} + +static int ksz886x_cable_test_result_trans(u16 status) +{ + switch (FIELD_GET(KSZ8081_LMD_STAT_MASK, status)) { + case KSZ8081_LMD_STAT_NORMAL: + return ETHTOOL_A_CABLE_RESULT_CODE_OK; + case KSZ8081_LMD_STAT_SHORT: + return ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT; + case KSZ8081_LMD_STAT_OPEN: + return ETHTOOL_A_CABLE_RESULT_CODE_OPEN; + case KSZ8081_LMD_STAT_FAIL: + fallthrough; + default: + return ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC; + } +} + +static bool ksz886x_cable_test_failed(u16 status) +{ + return FIELD_GET(KSZ8081_LMD_STAT_MASK, status) == + KSZ8081_LMD_STAT_FAIL; +} + +static bool ksz886x_cable_test_fault_length_valid(u16 status) +{ + switch (FIELD_GET(KSZ8081_LMD_STAT_MASK, status)) { + case KSZ8081_LMD_STAT_OPEN: + fallthrough; + case KSZ8081_LMD_STAT_SHORT: + return true; + } + return false; +} + +static int ksz886x_cable_test_fault_length(u16 status) +{ + int dt; + + /* According to the data sheet the distance to the fault is + * DELTA_TIME * 0.4 meters. + */ + dt = FIELD_GET(KSZ8081_LMD_DELTA_TIME_MASK, status); + + return (dt * 400) / 10; +} + +static int ksz886x_cable_test_wait_for_completion(struct phy_device *phydev) +{ + int val, ret; + + ret = phy_read_poll_timeout(phydev, KSZ8081_LMD, val, + !(val & KSZ8081_LMD_ENABLE_TEST), + 30000, 100000, true); + + return ret < 0 ? ret : 0; +} + +static int ksz886x_cable_test_one_pair(struct phy_device *phydev, int pair) +{ + static const int ethtool_pair[] = { + ETHTOOL_A_CABLE_PAIR_A, + ETHTOOL_A_CABLE_PAIR_B, + }; + int ret, val, mdix; + + /* There is no way to choice the pair, like we do one ksz9031. + * We can workaround this limitation by using the MDI-X functionality. + */ + if (pair == 0) + mdix = ETH_TP_MDI; + else + mdix = ETH_TP_MDI_X; + + switch (phydev->phy_id & MICREL_PHY_ID_MASK) { + case PHY_ID_KSZ8081: + ret = ksz8081_config_mdix(phydev, mdix); + break; + case PHY_ID_KSZ886X: + ret = ksz886x_config_mdix(phydev, mdix); + break; + default: + ret = -ENODEV; + } + + if (ret) + return ret; + + /* Now we are ready to fire. This command will send a 100ns pulse + * to the pair. + */ + ret = phy_write(phydev, KSZ8081_LMD, KSZ8081_LMD_ENABLE_TEST); + if (ret) + return ret; + + ret = ksz886x_cable_test_wait_for_completion(phydev); + if (ret) + return ret; + + val = phy_read(phydev, KSZ8081_LMD); + if (val < 0) + return val; + + if (ksz886x_cable_test_failed(val)) + return -EAGAIN; + + ret = ethnl_cable_test_result(phydev, ethtool_pair[pair], + ksz886x_cable_test_result_trans(val)); + if (ret) + return ret; + + if (!ksz886x_cable_test_fault_length_valid(val)) + return 0; + + return ethnl_cable_test_fault_length(phydev, ethtool_pair[pair], + ksz886x_cable_test_fault_length(val)); +} + +static int ksz886x_cable_test_get_status(struct phy_device *phydev, + bool *finished) +{ + unsigned long pair_mask = 0x3; + int retries = 20; + int pair, ret; + + *finished = false; + + /* Try harder if link partner is active */ + while (pair_mask && retries--) { + for_each_set_bit(pair, &pair_mask, 4) { + ret = ksz886x_cable_test_one_pair(phydev, pair); + if (ret == -EAGAIN) + continue; + if (ret < 0) + return ret; + clear_bit(pair, &pair_mask); + } + /* If link partner is in autonegotiation mode it will send 2ms + * of FLPs with at least 6ms of silence. + * Add 2ms sleep to have better chances to hit this silence. + */ + if (pair_mask) + msleep(2); + } + + *finished = true; + + return ret; +} + static struct phy_driver ksphy_driver[] = { { .phy_id = PHY_ID_KS8737, @@ -1299,11 +1643,14 @@ static struct phy_driver ksphy_driver[] = { .phy_id = PHY_ID_KSZ8081, .name = "Micrel KSZ8081 or KSZ8091", .phy_id_mask = MICREL_PHY_ID_MASK, + .flags = PHY_POLL_CABLE_TEST, /* PHY_BASIC_FEATURES */ .driver_data = &ksz8081_type, .probe = kszphy_probe, .config_init = ksz8081_config_init, .soft_reset = genphy_soft_reset, + .config_aneg = ksz8081_config_aneg, + .read_status = ksz8081_read_status, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, .get_sset_count = kszphy_get_sset_count, @@ -1311,6 +1658,8 @@ static struct phy_driver ksphy_driver[] = { .get_stats = kszphy_get_stats, .suspend = kszphy_suspend, .resume = kszphy_resume, + .cable_test_start = ksz886x_cable_test_start, + .cable_test_get_status = ksz886x_cable_test_get_status, }, { .phy_id = PHY_ID_KSZ8061, .name = "Micrel KSZ8061", @@ -1399,9 +1748,14 @@ static struct phy_driver ksphy_driver[] = { .phy_id_mask = MICREL_PHY_ID_MASK, .name = "Micrel KSZ8851 Ethernet MAC or KSZ886X Switch", /* PHY_BASIC_FEATURES */ + .flags = PHY_POLL_CABLE_TEST, .config_init = kszphy_config_init, + .config_aneg = ksz886x_config_aneg, + .read_status = ksz886x_read_status, .suspend = genphy_suspend, .resume = genphy_resume, + .cable_test_start = ksz886x_cable_test_start, + .cable_test_get_status = ksz886x_cable_test_get_status, }, { .name = "Micrel KSZ87XX Switch", /* PHY_BASIC_FEATURES */ diff --git a/drivers/net/phy/mii_timestamper.c b/drivers/net/phy/mii_timestamper.c index b71b7456462d..51ae0593a04f 100644 --- a/drivers/net/phy/mii_timestamper.c +++ b/drivers/net/phy/mii_timestamper.c @@ -111,6 +111,9 @@ void unregister_mii_timestamper(struct mii_timestamper *mii_ts) struct mii_timestamping_desc *desc; struct list_head *this; + if (!mii_ts) + return; + /* mii_timestamper statically registered by the PHY driver won't use the * register_mii_timestamper() and thus don't have ->device set. Don't * try to unregister these. diff --git a/drivers/net/phy/motorcomm.c b/drivers/net/phy/motorcomm.c new file mode 100644 index 000000000000..7e6ac2c5e27e --- /dev/null +++ b/drivers/net/phy/motorcomm.c @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Driver for Motorcomm PHYs + * + * Author: Peter Geis + */ + +#include +#include +#include + +#define PHY_ID_YT8511 0x0000010a + +#define YT8511_PAGE_SELECT 0x1e +#define YT8511_PAGE 0x1f +#define YT8511_EXT_CLK_GATE 0x0c +#define YT8511_EXT_DELAY_DRIVE 0x0d +#define YT8511_EXT_SLEEP_CTRL 0x27 + +/* 2b00 25m from pll + * 2b01 25m from xtl *default* + * 2b10 62.m from pll + * 2b11 125m from pll + */ +#define YT8511_CLK_125M (BIT(2) | BIT(1)) +#define YT8511_PLLON_SLP BIT(14) + +/* RX Delay enabled = 1.8ns 1000T, 8ns 10/100T */ +#define YT8511_DELAY_RX BIT(0) + +/* TX Gig-E Delay is bits 7:4, default 0x5 + * TX Fast-E Delay is bits 15:12, default 0xf + * Delay = 150ps * N - 250ps + * On = 2000ps, off = 50ps + */ +#define YT8511_DELAY_GE_TX_EN (0xf << 4) +#define YT8511_DELAY_GE_TX_DIS (0x2 << 4) +#define YT8511_DELAY_FE_TX_EN (0xf << 12) +#define YT8511_DELAY_FE_TX_DIS (0x2 << 12) + +static int yt8511_read_page(struct phy_device *phydev) +{ + return __phy_read(phydev, YT8511_PAGE_SELECT); +}; + +static int yt8511_write_page(struct phy_device *phydev, int page) +{ + return __phy_write(phydev, YT8511_PAGE_SELECT, page); +}; + +static int yt8511_config_init(struct phy_device *phydev) +{ + int oldpage, ret = 0; + unsigned int ge, fe; + + oldpage = phy_select_page(phydev, YT8511_EXT_CLK_GATE); + if (oldpage < 0) + goto err_restore_page; + + /* set rgmii delay mode */ + switch (phydev->interface) { + case PHY_INTERFACE_MODE_RGMII: + ge = YT8511_DELAY_GE_TX_DIS; + fe = YT8511_DELAY_FE_TX_DIS; + break; + case PHY_INTERFACE_MODE_RGMII_RXID: + ge = YT8511_DELAY_RX | YT8511_DELAY_GE_TX_DIS; + fe = YT8511_DELAY_FE_TX_DIS; + break; + case PHY_INTERFACE_MODE_RGMII_TXID: + ge = YT8511_DELAY_GE_TX_EN; + fe = YT8511_DELAY_FE_TX_EN; + break; + case PHY_INTERFACE_MODE_RGMII_ID: + ge = YT8511_DELAY_RX | YT8511_DELAY_GE_TX_EN; + fe = YT8511_DELAY_FE_TX_EN; + break; + default: /* do not support other modes */ + ret = -EOPNOTSUPP; + goto err_restore_page; + } + + ret = __phy_modify(phydev, YT8511_PAGE, (YT8511_DELAY_RX | YT8511_DELAY_GE_TX_EN), ge); + if (ret < 0) + goto err_restore_page; + + /* set clock mode to 125mhz */ + ret = __phy_modify(phydev, YT8511_PAGE, 0, YT8511_CLK_125M); + if (ret < 0) + goto err_restore_page; + + /* fast ethernet delay is in a separate page */ + ret = __phy_write(phydev, YT8511_PAGE_SELECT, YT8511_EXT_DELAY_DRIVE); + if (ret < 0) + goto err_restore_page; + + ret = __phy_modify(phydev, YT8511_PAGE, YT8511_DELAY_FE_TX_EN, fe); + if (ret < 0) + goto err_restore_page; + + /* leave pll enabled in sleep */ + ret = __phy_write(phydev, YT8511_PAGE_SELECT, YT8511_EXT_SLEEP_CTRL); + if (ret < 0) + goto err_restore_page; + + ret = __phy_modify(phydev, YT8511_PAGE, 0, YT8511_PLLON_SLP); + if (ret < 0) + goto err_restore_page; + +err_restore_page: + return phy_restore_page(phydev, oldpage, ret); +} + +static struct phy_driver motorcomm_phy_drvs[] = { + { + PHY_ID_MATCH_EXACT(PHY_ID_YT8511), + .name = "YT8511 Gigabit Ethernet", + .config_init = yt8511_config_init, + .suspend = genphy_suspend, + .resume = genphy_resume, + .read_page = yt8511_read_page, + .write_page = yt8511_write_page, + }, +}; + +module_phy_driver(motorcomm_phy_drvs); + +MODULE_DESCRIPTION("Motorcomm PHY driver"); +MODULE_AUTHOR("Peter Geis"); +MODULE_LICENSE("GPL"); + +static const struct mdio_device_id __maybe_unused motorcomm_tbl[] = { + { PHY_ID_MATCH_EXACT(PHY_ID_YT8511) }, + { /* sentinal */ } +}; + +MODULE_DEVICE_TABLE(mdio, motorcomm_tbl); diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c index 10be266e48e8..b7b2521c73fb 100644 --- a/drivers/net/phy/mscc/mscc_macsec.c +++ b/drivers/net/phy/mscc/mscc_macsec.c @@ -501,7 +501,7 @@ static u32 vsc8584_macsec_flow_context_id(struct macsec_flow *flow) } /* Derive the AES key to get a key for the hash autentication */ -static int vsc8584_macsec_derive_key(const u8 key[MACSEC_KEYID_LEN], +static int vsc8584_macsec_derive_key(const u8 key[MACSEC_MAX_KEY_LEN], u16 key_len, u8 hkey[16]) { const u8 input[AES_BLOCK_SIZE] = {0}; diff --git a/drivers/net/phy/mscc/mscc_macsec.h b/drivers/net/phy/mscc/mscc_macsec.h index 9c6d25e36de2..453304bae778 100644 --- a/drivers/net/phy/mscc/mscc_macsec.h +++ b/drivers/net/phy/mscc/mscc_macsec.h @@ -81,7 +81,7 @@ struct macsec_flow { /* Highest takes precedence [0..15] */ u8 priority; - u8 key[MACSEC_KEYID_LEN]; + u8 key[MACSEC_MAX_KEY_LEN]; union { struct macsec_rx_sa *rx_sa; diff --git a/drivers/net/phy/national.c b/drivers/net/phy/national.c index 46160baaafe3..9ae9cc6b23c2 100644 --- a/drivers/net/phy/national.c +++ b/drivers/net/phy/national.c @@ -68,7 +68,8 @@ static int ns_ack_interrupt(struct phy_device *phydev) return ret; /* Clear the interrupt status bit by writing a “1” - * to the corresponding bit in INT_CLEAR (2:0 are reserved) */ + * to the corresponding bit in INT_CLEAR (2:0 are reserved) + */ ret = phy_write(phydev, DP83865_INT_CLEAR, ret & ~0x7); return ret; @@ -150,7 +151,8 @@ static int ns_config_init(struct phy_device *phydev) { ns_giga_speed_fallback(phydev, ALL_FALLBACK_ON); /* In the latest MAC or switches design, the 10 Mbps loopback - is desired to be turned off. */ + * is desired to be turned off. + */ ns_10_base_t_hdx_loopack(phydev, hdx_loopback_off); return ns_ack_interrupt(phydev); } diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 26b9c0d7cb9d..91a327f67a42 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -13,6 +13,9 @@ #include #include #include +#include +#include +#include #define PHY_ID_TJA_1103 0x001BB010 @@ -57,6 +60,9 @@ #define VEND1_PORT_CONTROL 0x8040 #define PORT_CONTROL_EN BIT(14) +#define VEND1_PORT_ABILITIES 0x8046 +#define PTP_ABILITY BIT(3) + #define VEND1_PORT_INFRA_CONTROL 0xAC00 #define PORT_INFRA_CONTROL_EN BIT(14) @@ -91,13 +97,106 @@ #define VEND1_TX_IPG_LENGTH 0xAFD1 #define COUNTER_EN BIT(15) +#define VEND1_LTC_LOAD_CTRL 0x1105 +#define READ_LTC BIT(2) +#define LOAD_LTC BIT(0) + +#define VEND1_LTC_WR_NSEC_0 0x1106 +#define VEND1_LTC_WR_NSEC_1 0x1107 +#define VEND1_LTC_WR_SEC_0 0x1108 +#define VEND1_LTC_WR_SEC_1 0x1109 + +#define VEND1_LTC_RD_NSEC_0 0x110A +#define VEND1_LTC_RD_NSEC_1 0x110B +#define VEND1_LTC_RD_SEC_0 0x110C +#define VEND1_LTC_RD_SEC_1 0x110D + +#define VEND1_RATE_ADJ_SUBNS_0 0x110F +#define VEND1_RATE_ADJ_SUBNS_1 0x1110 +#define CLK_RATE_ADJ_LD BIT(15) +#define CLK_RATE_ADJ_DIR BIT(14) + +#define VEND1_HW_LTC_LOCK_CTRL 0x1115 +#define HW_LTC_LOCK_EN BIT(0) + +#define VEND1_PTP_IRQ_EN 0x1131 +#define VEND1_PTP_IRQ_STATUS 0x1132 +#define PTP_IRQ_EGR_TS BIT(0) + +#define VEND1_RX_TS_INSRT_CTRL 0x114D +#define RX_TS_INSRT_MODE2 0x02 + +#define VEND1_EGR_RING_DATA_0 0x114E +#define VEND1_EGR_RING_DATA_1_SEQ_ID 0x114F +#define VEND1_EGR_RING_DATA_2_NSEC_15_0 0x1150 +#define VEND1_EGR_RING_DATA_3 0x1151 +#define VEND1_EGR_RING_CTRL 0x1154 + +#define RING_DATA_0_DOMAIN_NUMBER GENMASK(7, 0) +#define RING_DATA_0_MSG_TYPE GENMASK(11, 8) +#define RING_DATA_0_SEC_4_2 GENMASK(14, 2) +#define RING_DATA_0_TS_VALID BIT(15) + +#define RING_DATA_3_NSEC_29_16 GENMASK(13, 0) +#define RING_DATA_3_SEC_1_0 GENMASK(15, 14) +#define RING_DATA_5_SEC_16_5 GENMASK(15, 4) +#define RING_DONE BIT(0) + +#define TS_SEC_MASK GENMASK(1, 0) + +#define VEND1_PORT_FUNC_ENABLES 0x8048 +#define PTP_ENABLE BIT(3) + +#define VEND1_PORT_PTP_CONTROL 0x9000 +#define PORT_PTP_CONTROL_BYPASS BIT(11) + +#define VEND1_PTP_CLK_PERIOD 0x1104 +#define PTP_CLK_PERIOD_100BT1 15ULL + +#define VEND1_EVENT_MSG_FILT 0x1148 +#define EVENT_MSG_FILT_ALL 0x0F +#define EVENT_MSG_FILT_NONE 0x00 + +#define VEND1_TX_PIPE_DLY_NS 0x1149 +#define VEND1_TX_PIPEDLY_SUBNS 0x114A +#define VEND1_RX_PIPE_DLY_NS 0x114B +#define VEND1_RX_PIPEDLY_SUBNS 0x114C + #define RGMII_PERIOD_PS 8000U #define PS_PER_DEGREE div_u64(RGMII_PERIOD_PS, 360) #define MIN_ID_PS 1644U #define MAX_ID_PS 2260U #define DEFAULT_ID_PS 2000U +#define PPM_TO_SUBNS_INC(ppb) div_u64(GENMASK(31, 0) * (ppb) * \ + PTP_CLK_PERIOD_100BT1, NSEC_PER_SEC) + +#define NXP_C45_SKB_CB(skb) ((struct nxp_c45_skb_cb *)(skb)->cb) + +struct nxp_c45_skb_cb { + struct ptp_header *header; + unsigned int type; +}; + +struct nxp_c45_hwts { + u32 nsec; + u32 sec; + u8 domain_number; + u16 sequence_id; + u8 msg_type; +}; + struct nxp_c45_phy { + struct phy_device *phydev; + struct mii_timestamper mii_ts; + struct ptp_clock *ptp_clock; + struct ptp_clock_info caps; + struct sk_buff_head tx_queue; + struct sk_buff_head rx_queue; + /* used to access the PTP registers atomic */ + struct mutex ptp_lock; + int hwts_tx; + int hwts_rx; u32 tx_delay; u32 rx_delay; }; @@ -110,6 +209,382 @@ struct nxp_c45_phy_stats { u16 mask; }; +static bool nxp_c45_poll_txts(struct phy_device *phydev) +{ + return phydev->irq <= 0; +} + +static int _nxp_c45_ptp_gettimex64(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps); + + phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_LOAD_CTRL, + READ_LTC); + ts->tv_nsec = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, + VEND1_LTC_RD_NSEC_0); + ts->tv_nsec |= phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, + VEND1_LTC_RD_NSEC_1) << 16; + ts->tv_sec = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, + VEND1_LTC_RD_SEC_0); + ts->tv_sec |= phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, + VEND1_LTC_RD_SEC_1) << 16; + + return 0; +} + +static int nxp_c45_ptp_gettimex64(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps); + + mutex_lock(&priv->ptp_lock); + _nxp_c45_ptp_gettimex64(ptp, ts, sts); + mutex_unlock(&priv->ptp_lock); + + return 0; +} + +static int _nxp_c45_ptp_settime64(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps); + + phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_WR_NSEC_0, + ts->tv_nsec); + phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_WR_NSEC_1, + ts->tv_nsec >> 16); + phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_WR_SEC_0, + ts->tv_sec); + phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_WR_SEC_1, + ts->tv_sec >> 16); + phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_LTC_LOAD_CTRL, + LOAD_LTC); + + return 0; +} + +static int nxp_c45_ptp_settime64(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps); + + mutex_lock(&priv->ptp_lock); + _nxp_c45_ptp_settime64(ptp, ts); + mutex_unlock(&priv->ptp_lock); + + return 0; +} + +static int nxp_c45_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps); + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); + u64 subns_inc_val; + bool inc; + + mutex_lock(&priv->ptp_lock); + inc = ppb >= 0; + ppb = abs(ppb); + + subns_inc_val = PPM_TO_SUBNS_INC(ppb); + + phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_RATE_ADJ_SUBNS_0, + subns_inc_val); + subns_inc_val >>= 16; + subns_inc_val |= CLK_RATE_ADJ_LD; + if (inc) + subns_inc_val |= CLK_RATE_ADJ_DIR; + + phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_RATE_ADJ_SUBNS_1, + subns_inc_val); + mutex_unlock(&priv->ptp_lock); + + return 0; +} + +static int nxp_c45_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps); + struct timespec64 now, then; + + mutex_lock(&priv->ptp_lock); + then = ns_to_timespec64(delta); + _nxp_c45_ptp_gettimex64(ptp, &now, NULL); + now = timespec64_add(now, then); + _nxp_c45_ptp_settime64(ptp, &now); + mutex_unlock(&priv->ptp_lock); + + return 0; +} + +static void nxp_c45_reconstruct_ts(struct timespec64 *ts, + struct nxp_c45_hwts *hwts) +{ + ts->tv_nsec = hwts->nsec; + if ((ts->tv_sec & TS_SEC_MASK) < (hwts->sec & TS_SEC_MASK)) + ts->tv_sec -= TS_SEC_MASK + 1; + ts->tv_sec &= ~TS_SEC_MASK; + ts->tv_sec |= hwts->sec & TS_SEC_MASK; +} + +static bool nxp_c45_match_ts(struct ptp_header *header, + struct nxp_c45_hwts *hwts, + unsigned int type) +{ + return ntohs(header->sequence_id) == hwts->sequence_id && + ptp_get_msgtype(header, type) == hwts->msg_type && + header->domain_number == hwts->domain_number; +} + +static bool nxp_c45_get_hwtxts(struct nxp_c45_phy *priv, + struct nxp_c45_hwts *hwts) +{ + bool valid; + u16 reg; + + mutex_lock(&priv->ptp_lock); + phy_write_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_EGR_RING_CTRL, + RING_DONE); + reg = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_EGR_RING_DATA_0); + valid = !!(reg & RING_DATA_0_TS_VALID); + if (!valid) + goto nxp_c45_get_hwtxts_out; + + hwts->domain_number = reg; + hwts->msg_type = (reg & RING_DATA_0_MSG_TYPE) >> 8; + hwts->sec = (reg & RING_DATA_0_SEC_4_2) >> 10; + hwts->sequence_id = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, + VEND1_EGR_RING_DATA_1_SEQ_ID); + hwts->nsec = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, + VEND1_EGR_RING_DATA_2_NSEC_15_0); + reg = phy_read_mmd(priv->phydev, MDIO_MMD_VEND1, VEND1_EGR_RING_DATA_3); + hwts->nsec |= (reg & RING_DATA_3_NSEC_29_16) << 16; + hwts->sec |= (reg & RING_DATA_3_SEC_1_0) >> 14; + +nxp_c45_get_hwtxts_out: + mutex_unlock(&priv->ptp_lock); + return valid; +} + +static void nxp_c45_process_txts(struct nxp_c45_phy *priv, + struct nxp_c45_hwts *txts) +{ + struct sk_buff *skb, *tmp, *skb_match = NULL; + struct skb_shared_hwtstamps shhwtstamps; + struct timespec64 ts; + unsigned long flags; + bool ts_match; + s64 ts_ns; + + spin_lock_irqsave(&priv->tx_queue.lock, flags); + skb_queue_walk_safe(&priv->tx_queue, skb, tmp) { + ts_match = nxp_c45_match_ts(NXP_C45_SKB_CB(skb)->header, txts, + NXP_C45_SKB_CB(skb)->type); + if (!ts_match) + continue; + skb_match = skb; + __skb_unlink(skb, &priv->tx_queue); + break; + } + spin_unlock_irqrestore(&priv->tx_queue.lock, flags); + + if (skb_match) { + nxp_c45_ptp_gettimex64(&priv->caps, &ts, NULL); + nxp_c45_reconstruct_ts(&ts, txts); + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + ts_ns = timespec64_to_ns(&ts); + shhwtstamps.hwtstamp = ns_to_ktime(ts_ns); + skb_complete_tx_timestamp(skb_match, &shhwtstamps); + } else { + phydev_warn(priv->phydev, + "the tx timestamp doesn't match with any skb\n"); + } +} + +static long nxp_c45_do_aux_work(struct ptp_clock_info *ptp) +{ + struct nxp_c45_phy *priv = container_of(ptp, struct nxp_c45_phy, caps); + bool poll_txts = nxp_c45_poll_txts(priv->phydev); + struct skb_shared_hwtstamps *shhwtstamps_rx; + struct nxp_c45_hwts hwts; + bool reschedule = false; + struct timespec64 ts; + struct sk_buff *skb; + bool txts_valid; + u32 ts_raw; + + while (!skb_queue_empty_lockless(&priv->tx_queue) && poll_txts) { + txts_valid = nxp_c45_get_hwtxts(priv, &hwts); + if (unlikely(!txts_valid)) { + /* Still more skbs in the queue */ + reschedule = true; + break; + } + + nxp_c45_process_txts(priv, &hwts); + } + + while ((skb = skb_dequeue(&priv->rx_queue)) != NULL) { + nxp_c45_ptp_gettimex64(&priv->caps, &ts, NULL); + ts_raw = __be32_to_cpu(NXP_C45_SKB_CB(skb)->header->reserved2); + hwts.sec = ts_raw >> 30; + hwts.nsec = ts_raw & GENMASK(29, 0); + nxp_c45_reconstruct_ts(&ts, &hwts); + shhwtstamps_rx = skb_hwtstamps(skb); + shhwtstamps_rx->hwtstamp = ns_to_ktime(timespec64_to_ns(&ts)); + NXP_C45_SKB_CB(skb)->header->reserved2 = 0; + netif_rx_ni(skb); + } + + return reschedule ? 1 : -1; +} + +static int nxp_c45_init_ptp_clock(struct nxp_c45_phy *priv) +{ + priv->caps = (struct ptp_clock_info) { + .owner = THIS_MODULE, + .name = "NXP C45 PHC", + .max_adj = 16666666, + .adjfine = nxp_c45_ptp_adjfine, + .adjtime = nxp_c45_ptp_adjtime, + .gettimex64 = nxp_c45_ptp_gettimex64, + .settime64 = nxp_c45_ptp_settime64, + .do_aux_work = nxp_c45_do_aux_work, + }; + + priv->ptp_clock = ptp_clock_register(&priv->caps, + &priv->phydev->mdio.dev); + + if (IS_ERR(priv->ptp_clock)) + return PTR_ERR(priv->ptp_clock); + + if (!priv->ptp_clock) + return -ENOMEM; + + return 0; +} + +static void nxp_c45_txtstamp(struct mii_timestamper *mii_ts, + struct sk_buff *skb, int type) +{ + struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy, + mii_ts); + + switch (priv->hwts_tx) { + case HWTSTAMP_TX_ON: + NXP_C45_SKB_CB(skb)->type = type; + NXP_C45_SKB_CB(skb)->header = ptp_parse_header(skb, type); + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + skb_queue_tail(&priv->tx_queue, skb); + if (nxp_c45_poll_txts(priv->phydev)) + ptp_schedule_worker(priv->ptp_clock, 0); + break; + case HWTSTAMP_TX_OFF: + default: + kfree_skb(skb); + break; + } +} + +static bool nxp_c45_rxtstamp(struct mii_timestamper *mii_ts, + struct sk_buff *skb, int type) +{ + struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy, + mii_ts); + struct ptp_header *header = ptp_parse_header(skb, type); + + if (!header) + return false; + + if (!priv->hwts_rx) + return false; + + NXP_C45_SKB_CB(skb)->header = header; + skb_queue_tail(&priv->rx_queue, skb); + ptp_schedule_worker(priv->ptp_clock, 0); + + return true; +} + +static int nxp_c45_hwtstamp(struct mii_timestamper *mii_ts, + struct ifreq *ifreq) +{ + struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy, + mii_ts); + struct phy_device *phydev = priv->phydev; + struct hwtstamp_config cfg; + + if (copy_from_user(&cfg, ifreq->ifr_data, sizeof(cfg))) + return -EFAULT; + + if (cfg.tx_type < 0 || cfg.tx_type > HWTSTAMP_TX_ON) + return -ERANGE; + + priv->hwts_tx = cfg.tx_type; + + switch (cfg.rx_filter) { + case HWTSTAMP_FILTER_NONE: + priv->hwts_rx = 0; + break; + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + priv->hwts_rx = 1; + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; + break; + default: + return -ERANGE; + } + + if (priv->hwts_rx || priv->hwts_tx) { + phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_EVENT_MSG_FILT, + EVENT_MSG_FILT_ALL); + phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + VEND1_PORT_PTP_CONTROL, + PORT_PTP_CONTROL_BYPASS); + } else { + phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_EVENT_MSG_FILT, + EVENT_MSG_FILT_NONE); + phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PORT_PTP_CONTROL, + PORT_PTP_CONTROL_BYPASS); + } + + if (nxp_c45_poll_txts(priv->phydev)) + goto nxp_c45_no_ptp_irq; + + if (priv->hwts_tx) + phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, + VEND1_PTP_IRQ_EN, PTP_IRQ_EGR_TS); + else + phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + VEND1_PTP_IRQ_EN, PTP_IRQ_EGR_TS); + +nxp_c45_no_ptp_irq: + return copy_to_user(ifreq->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; +} + +static int nxp_c45_ts_info(struct mii_timestamper *mii_ts, + struct ethtool_ts_info *ts_info) +{ + struct nxp_c45_phy *priv = container_of(mii_ts, struct nxp_c45_phy, + mii_ts); + + ts_info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + ts_info->phc_index = ptp_clock_index(priv->ptp_clock); + ts_info->tx_types = (1 << HWTSTAMP_TX_OFF) | (1 << HWTSTAMP_TX_ON); + ts_info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT); + + return 0; +} + static const struct nxp_c45_phy_stats nxp_c45_hw_stats[] = { { "phy_symbol_error_cnt", MDIO_MMD_VEND1, VEND1_SYMBOL_ERROR_COUNTER, 0, GENMASK(15, 0) }, @@ -205,7 +680,9 @@ static int nxp_c45_config_intr(struct phy_device *phydev) static irqreturn_t nxp_c45_handle_interrupt(struct phy_device *phydev) { + struct nxp_c45_phy *priv = phydev->priv; irqreturn_t ret = IRQ_NONE; + struct nxp_c45_hwts hwts; int irq; irq = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_PHY_IRQ_STATUS); @@ -216,6 +693,18 @@ static irqreturn_t nxp_c45_handle_interrupt(struct phy_device *phydev) ret = IRQ_HANDLED; } + /* There is no need for ACK. + * The irq signal will be asserted until the EGR TS FIFO will be + * emptied. + */ + irq = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_PTP_IRQ_STATUS); + if (irq & PTP_IRQ_EGR_TS) { + while (nxp_c45_get_hwtxts(priv, &hwts)) + nxp_c45_process_txts(priv, &hwts); + + ret = IRQ_HANDLED; + } + return ret; } @@ -546,6 +1035,12 @@ static int nxp_c45_config_init(struct phy_device *phydev) return ret; } + /* Bug workaround for SJA1110 rev B: enable write access + * to MDIO_MMD_PMAPMD + */ + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 1); + phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 2); + phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PHY_CONFIG, PHY_CONFIG_AUTO); @@ -566,20 +1061,60 @@ static int nxp_c45_config_init(struct phy_device *phydev) phydev->autoneg = AUTONEG_DISABLE; + phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_PTP_CLK_PERIOD, + PTP_CLK_PERIOD_100BT1); + phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_HW_LTC_LOCK_CTRL, + HW_LTC_LOCK_EN); + phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_RX_TS_INSRT_CTRL, + RX_TS_INSRT_MODE2); + phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PORT_FUNC_ENABLES, + PTP_ENABLE); + return nxp_c45_start_op(phydev); } static int nxp_c45_probe(struct phy_device *phydev) { struct nxp_c45_phy *priv; + int ptp_ability; + int ret = 0; priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; + skb_queue_head_init(&priv->tx_queue); + skb_queue_head_init(&priv->rx_queue); + + priv->phydev = phydev; + phydev->priv = priv; - return 0; + mutex_init(&priv->ptp_lock); + + ptp_ability = phy_read_mmd(phydev, MDIO_MMD_VEND1, + VEND1_PORT_ABILITIES); + ptp_ability = !!(ptp_ability & PTP_ABILITY); + if (!ptp_ability) { + phydev_dbg(phydev, "the phy does not support PTP"); + goto no_ptp_support; + } + + if (IS_ENABLED(CONFIG_PTP_1588_CLOCK) && + IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING)) { + priv->mii_ts.rxtstamp = nxp_c45_rxtstamp; + priv->mii_ts.txtstamp = nxp_c45_txtstamp; + priv->mii_ts.hwtstamp = nxp_c45_hwtstamp; + priv->mii_ts.ts_info = nxp_c45_ts_info; + phydev->mii_ts = &priv->mii_ts; + ret = nxp_c45_init_ptp_clock(priv); + } else { + phydev_dbg(phydev, "PTP support not enabled even if the phy supports it"); + } + +no_ptp_support: + + return ret; } static struct phy_driver nxp_c45_driver[] = { diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index f4816b7d31b3..c617dbcad6ea 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -172,7 +172,7 @@ EXPORT_SYMBOL_GPL(genphy_c45_an_config_aneg); * @phydev: target phy_device struct * * Disable auto-negotiation in the Clause 45 PHY. The link parameters - * parameters are controlled through the PMA/PMD MMD registers. + * are controlled through the PMA/PMD MMD registers. * * Returns zero on success, negative errno code on failure. */ diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 8d333d3084ed..2870c33b8975 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -76,7 +76,8 @@ EXPORT_SYMBOL_GPL(phy_duplex_to_str); /* A mapping of all SUPPORTED settings to speed/duplex. This table * must be grouped by speed and sorted in descending match priority - * - iow, descending speed. */ + * - iow, descending speed. + */ #define PHY_SETTING(s, d, b) { .speed = SPEED_ ## s, .duplex = DUPLEX_ ## d, \ .bit = ETHTOOL_LINK_MODE_ ## b ## _BIT} diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 1f0512e39c65..8eeb26d8aeb7 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -380,8 +380,7 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd) else if (val & BMCR_SPEED100) phydev->speed = SPEED_100; else phydev->speed = SPEED_10; - } - else { + } else { if (phydev->autoneg == AUTONEG_DISABLE) change_autoneg = true; phydev->autoneg = AUTONEG_ENABLE; @@ -1136,6 +1135,9 @@ void phy_state_machine(struct work_struct *work) else if (do_suspend) phy_suspend(phydev); + if (err == -ENODEV) + return; + if (err < 0) phy_error(phydev); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 0a2d8bedf73d..5d5f9a9ee768 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -833,6 +834,27 @@ static int get_phy_c22_id(struct mii_bus *bus, int addr, u32 *phy_id) return 0; } +/* Extract the phy ID from the compatible string of the form + * ethernet-phy-idAAAA.BBBB. + */ +int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id) +{ + unsigned int upper, lower; + const char *cp; + int ret; + + ret = fwnode_property_read_string(fwnode, "compatible", &cp); + if (ret) + return ret; + + if (sscanf(cp, "ethernet-phy-id%4x.%4x", &upper, &lower) != 2) + return -EINVAL; + + *phy_id = ((upper & GENMASK(15, 0)) << 16) | (lower & GENMASK(15, 0)); + return 0; +} +EXPORT_SYMBOL(fwnode_get_phy_id); + /** * get_phy_device - reads the specified PHY device and returns its @phy_device * struct @@ -870,6 +892,18 @@ struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) if (r) return ERR_PTR(r); + /* PHY device such as the Marvell Alaska 88E2110 will return a PHY ID + * of 0 when probed using get_phy_c22_id() with no error. Proceed to + * probe with C45 to see if we're able to get a valid PHY ID in the C45 + * space, if successful, create the C45 PHY device. + */ + if (!is_c45 && phy_id == 0 && bus->probe_capabilities >= MDIOBUS_C45) { + r = get_phy_c45_ids(bus, addr, &c45_ids); + if (!r) + return phy_device_create(bus, addr, phy_id, + true, &c45_ids); + } + return phy_device_create(bus, addr, phy_id, is_c45, &c45_ids); } EXPORT_SYMBOL(get_phy_device); @@ -923,8 +957,7 @@ EXPORT_SYMBOL(phy_device_register); */ void phy_device_remove(struct phy_device *phydev) { - if (phydev->mii_ts) - unregister_mii_timestamper(phydev->mii_ts); + unregister_mii_timestamper(phydev->mii_ts); device_del(&phydev->mdio.dev); @@ -2863,6 +2896,90 @@ static bool phy_drv_supports_irq(struct phy_driver *phydrv) return phydrv->config_intr && phydrv->handle_interrupt; } +/** + * fwnode_mdio_find_device - Given a fwnode, find the mdio_device + * @fwnode: pointer to the mdio_device's fwnode + * + * If successful, returns a pointer to the mdio_device with the embedded + * struct device refcount incremented by one, or NULL on failure. + * The caller should call put_device() on the mdio_device after its use. + */ +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) +{ + struct device *d; + + if (!fwnode) + return NULL; + + d = bus_find_device_by_fwnode(&mdio_bus_type, fwnode); + if (!d) + return NULL; + + return to_mdio_device(d); +} +EXPORT_SYMBOL(fwnode_mdio_find_device); + +/** + * fwnode_phy_find_device - For provided phy_fwnode, find phy_device. + * + * @phy_fwnode: Pointer to the phy's fwnode. + * + * If successful, returns a pointer to the phy_device with the embedded + * struct device refcount incremented by one, or NULL on failure. + */ +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode) +{ + struct mdio_device *mdiodev; + + mdiodev = fwnode_mdio_find_device(phy_fwnode); + if (!mdiodev) + return NULL; + + if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY) + return to_phy_device(&mdiodev->dev); + + put_device(&mdiodev->dev); + + return NULL; +} +EXPORT_SYMBOL(fwnode_phy_find_device); + +/** + * device_phy_find_device - For the given device, get the phy_device + * @dev: Pointer to the given device + * + * Refer return conditions of fwnode_phy_find_device(). + */ +struct phy_device *device_phy_find_device(struct device *dev) +{ + return fwnode_phy_find_device(dev_fwnode(dev)); +} +EXPORT_SYMBOL_GPL(device_phy_find_device); + +/** + * fwnode_get_phy_node - Get the phy_node using the named reference. + * @fwnode: Pointer to fwnode from which phy_node has to be obtained. + * + * Refer return conditions of fwnode_find_reference(). + * For ACPI, only "phy-handle" is supported. Legacy DT properties "phy" + * and "phy-device" are not supported in ACPI. DT supports all the three + * named references to the phy node. + */ +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) +{ + struct fwnode_handle *phy_node; + + /* Only phy-handle is used for ACPI */ + phy_node = fwnode_find_reference(fwnode, "phy-handle", 0); + if (is_acpi_node(fwnode) || !IS_ERR(phy_node)) + return phy_node; + phy_node = fwnode_find_reference(fwnode, "phy", 0); + if (IS_ERR(phy_node)) + phy_node = fwnode_find_reference(fwnode, "phy-device", 0); + return phy_node; +} +EXPORT_SYMBOL_GPL(fwnode_get_phy_node); + /** * phy_probe - probe and init a PHY device * @dev: device to probe and init @@ -2883,7 +3000,7 @@ static int phy_probe(struct device *dev) /* Disable the interrupt if the PHY doesn't support it * but the interrupt is still a valid one */ - if (!phy_drv_supports_irq(phydrv) && phy_interrupt_is_valid(phydev)) + if (!phy_drv_supports_irq(phydrv) && phy_interrupt_is_valid(phydev)) phydev->irq = PHY_POLL; if (phydrv->flags & PHY_IS_INTERNAL) @@ -2904,15 +3021,14 @@ static int phy_probe(struct device *dev) * a controller will attach, and may modify one * or both of these values */ - if (phydrv->features) { + if (phydrv->features) linkmode_copy(phydev->supported, phydrv->features); - } else if (phydrv->get_features) { + else if (phydrv->get_features) err = phydrv->get_features(phydev); - } else if (phydev->is_c45) { + else if (phydev->is_c45) err = genphy_c45_pma_read_abilities(phydev); - } else { + else err = genphy_read_abilities(phydev); - } if (err) goto out; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 96d8e88b4e46..eb29ef53d971 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -5,6 +5,7 @@ * * Copyright (C) 2015 Russell King */ +#include #include #include #include @@ -181,7 +182,8 @@ static int phylink_parse_fixedlink(struct phylink *pl, pl->link_config.duplex = DUPLEX_FULL; /* We treat the "pause" and "asym-pause" terminology as - * defining the link partner's ability. */ + * defining the link partner's ability. + */ if (fwnode_property_read_bool(fixed_node, "pause")) __set_bit(ETHTOOL_LINK_MODE_Pause_BIT, pl->link_config.lp_advertising); @@ -311,6 +313,11 @@ static int phylink_parse_mode(struct phylink *pl, struct fwnode_handle *fwnode) phylink_set(pl->supported, 5000baseT_Full); break; + case PHY_INTERFACE_MODE_25GBASER: + phylink_set(pl->supported, 25000baseCR_Full); + phylink_set(pl->supported, 25000baseKR_Full); + phylink_set(pl->supported, 25000baseSR_Full); + fallthrough; case PHY_INTERFACE_MODE_USXGMII: case PHY_INTERFACE_MODE_10GKR: case PHY_INTERFACE_MODE_10GBASER: @@ -679,7 +686,8 @@ static void phylink_resolve(struct work_struct *w) phylink_mac_pcs_get_state(pl, &link_state); /* If we have a phy, the "up" state is the union of - * both the PHY and the MAC */ + * both the PHY and the MAC + */ if (pl->phydev) link_state.link &= pl->phy_state.link; @@ -688,7 +696,8 @@ static void phylink_resolve(struct work_struct *w) link_state.interface = pl->phy_state.interface; /* If we have a PHY, we need to update with - * the PHY flow control bits. */ + * the PHY flow control bits. + */ link_state.pause = pl->phy_state.pause; mac_config = true; } @@ -1084,7 +1093,26 @@ EXPORT_SYMBOL_GPL(phylink_connect_phy); int phylink_of_phy_connect(struct phylink *pl, struct device_node *dn, u32 flags) { - struct device_node *phy_node; + return phylink_fwnode_phy_connect(pl, of_fwnode_handle(dn), flags); +} +EXPORT_SYMBOL_GPL(phylink_of_phy_connect); + +/** + * phylink_fwnode_phy_connect() - connect the PHY specified in the fwnode. + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @fwnode: a pointer to a &struct fwnode_handle. + * @flags: PHY-specific flags to communicate to the PHY device driver + * + * Connect the phy specified @fwnode to the phylink instance specified + * by @pl. + * + * Returns 0 on success or a negative errno. + */ +int phylink_fwnode_phy_connect(struct phylink *pl, + struct fwnode_handle *fwnode, + u32 flags) +{ + struct fwnode_handle *phy_fwnode; struct phy_device *phy_dev; int ret; @@ -1094,28 +1122,25 @@ int phylink_of_phy_connect(struct phylink *pl, struct device_node *dn, phy_interface_mode_is_8023z(pl->link_interface))) return 0; - phy_node = of_parse_phandle(dn, "phy-handle", 0); - if (!phy_node) - phy_node = of_parse_phandle(dn, "phy", 0); - if (!phy_node) - phy_node = of_parse_phandle(dn, "phy-device", 0); - - if (!phy_node) { + phy_fwnode = fwnode_get_phy_node(fwnode); + if (IS_ERR(phy_fwnode)) { if (pl->cfg_link_an_mode == MLO_AN_PHY) return -ENODEV; return 0; } - phy_dev = of_phy_find_device(phy_node); + phy_dev = fwnode_phy_find_device(phy_fwnode); /* We're done with the phy_node handle */ - of_node_put(phy_node); + fwnode_handle_put(phy_fwnode); if (!phy_dev) return -ENODEV; ret = phy_attach_direct(pl->netdev, phy_dev, flags, pl->link_interface); - if (ret) + if (ret) { + phy_device_free(phy_dev); return ret; + } ret = phylink_bringup_phy(pl, phy_dev, pl->link_config.interface); if (ret) @@ -1123,7 +1148,7 @@ int phylink_of_phy_connect(struct phylink *pl, struct device_node *dn, return ret; } -EXPORT_SYMBOL_GPL(phylink_of_phy_connect); +EXPORT_SYMBOL_GPL(phylink_fwnode_phy_connect); /** * phylink_disconnect_phy() - disconnect any PHY attached to the phylink @@ -1358,11 +1383,10 @@ int phylink_ethtool_ksettings_get(struct phylink *pl, ASSERT_RTNL(); - if (pl->phydev) { + if (pl->phydev) phy_ethtool_ksettings_get(pl->phydev, kset); - } else { + else kset->base.port = pl->link_port; - } linkmode_copy(kset->link_modes.supported, pl->supported); diff --git a/drivers/net/phy/qsemi.c b/drivers/net/phy/qsemi.c index d5c1aaa8236a..30d15f7c9b03 100644 --- a/drivers/net/phy/qsemi.c +++ b/drivers/net/phy/qsemi.c @@ -100,6 +100,7 @@ static int qs6612_ack_interrupt(struct phy_device *phydev) static int qs6612_config_intr(struct phy_device *phydev) { int err; + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { /* clear any interrupts before enabling them */ err = qs6612_ack_interrupt(phydev); diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 821e85a97367..11be60333fa8 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -8,6 +8,7 @@ * Copyright (c) 2004 Freescale Semiconductor, Inc. */ #include +#include #include #include #include @@ -27,6 +28,7 @@ #define RTL821x_PAGE_SELECT 0x1f #define RTL8211F_PHYCR1 0x18 +#define RTL8211F_PHYCR2 0x19 #define RTL8211F_INSR 0x1d #define RTL8211F_TX_DELAY BIT(8) @@ -40,6 +42,8 @@ #define RTL8211E_TX_DELAY BIT(12) #define RTL8211E_RX_DELAY BIT(11) +#define RTL8211F_CLKOUT_EN BIT(0) + #define RTL8201F_ISR 0x1e #define RTL8201F_ISR_ANERR BIT(15) #define RTL8201F_ISR_DUPLEX BIT(13) @@ -71,6 +75,11 @@ MODULE_DESCRIPTION("Realtek PHY driver"); MODULE_AUTHOR("Johnson Leung"); MODULE_LICENSE("GPL"); +struct rtl821x_priv { + u16 phycr1; + u16 phycr2; +}; + static int rtl821x_read_page(struct phy_device *phydev) { return __phy_read(phydev, RTL821x_PAGE_SELECT); @@ -81,6 +90,37 @@ static int rtl821x_write_page(struct phy_device *phydev, int page) return __phy_write(phydev, RTL821x_PAGE_SELECT, page); } +static int rtl821x_probe(struct phy_device *phydev) +{ + struct device *dev = &phydev->mdio.dev; + struct rtl821x_priv *priv; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + ret = phy_read_paged(phydev, 0xa43, RTL8211F_PHYCR1); + if (ret < 0) + return ret; + + priv->phycr1 = ret & (RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF); + if (of_property_read_bool(dev->of_node, "realtek,aldps-enable")) + priv->phycr1 |= RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF; + + ret = phy_read_paged(phydev, 0xa43, RTL8211F_PHYCR2); + if (ret < 0) + return ret; + + priv->phycr2 = ret & RTL8211F_CLKOUT_EN; + if (of_property_read_bool(dev->of_node, "realtek,clkout-disable")) + priv->phycr2 &= ~RTL8211F_CLKOUT_EN; + + phydev->priv = priv; + + return 0; +} + static int rtl8201_ack_interrupt(struct phy_device *phydev) { int err; @@ -291,13 +331,19 @@ static int rtl8211c_config_init(struct phy_device *phydev) static int rtl8211f_config_init(struct phy_device *phydev) { + struct rtl821x_priv *priv = phydev->priv; struct device *dev = &phydev->mdio.dev; u16 val_txdly, val_rxdly; - u16 val; int ret; - val = RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_XTAL_OFF; - phy_modify_paged_changed(phydev, 0xa43, RTL8211F_PHYCR1, val, val); + ret = phy_modify_paged_changed(phydev, 0xa43, RTL8211F_PHYCR1, + RTL8211F_ALDPS_PLL_OFF | RTL8211F_ALDPS_ENABLE | RTL8211F_ALDPS_XTAL_OFF, + priv->phycr1); + if (ret < 0) { + dev_err(dev, "aldps mode configuration failed: %pe\n", + ERR_PTR(ret)); + return ret; + } switch (phydev->interface) { case PHY_INTERFACE_MODE_RGMII: @@ -354,6 +400,27 @@ static int rtl8211f_config_init(struct phy_device *phydev) val_rxdly ? "enabled" : "disabled"); } + ret = phy_modify_paged(phydev, 0xa43, RTL8211F_PHYCR2, + RTL8211F_CLKOUT_EN, priv->phycr2); + if (ret < 0) { + dev_err(dev, "clkout configuration failed: %pe\n", + ERR_PTR(ret)); + return ret; + } + + return genphy_soft_reset(phydev); +} + +static int rtl821x_resume(struct phy_device *phydev) +{ + int ret; + + ret = genphy_resume(phydev); + if (ret < 0) + return ret; + + msleep(20); + return 0; } @@ -847,12 +914,13 @@ static struct phy_driver realtek_drvs[] = { }, { PHY_ID_MATCH_EXACT(0x001cc916), .name = "RTL8211F Gigabit Ethernet", + .probe = rtl821x_probe, .config_init = &rtl8211f_config_init, .read_status = rtlgen_read_status, .config_intr = &rtl8211f_config_intr, .handle_interrupt = rtl8211f_handle_interrupt, .suspend = genphy_suspend, - .resume = genphy_resume, + .resume = rtl821x_resume, .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, }, { diff --git a/drivers/net/phy/rockchip.c b/drivers/net/phy/rockchip.c index 52f1f65320fe..bb13e75183ee 100644 --- a/drivers/net/phy/rockchip.c +++ b/drivers/net/phy/rockchip.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0+ -/** +/* * drivers/net/phy/rockchip.c * * Driver for ROCKCHIP Ethernet PHYs diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index e61de66e973b..7362f8c3271c 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -392,6 +392,11 @@ EXPORT_SYMBOL_GPL(sfp_parse_support); phy_interface_t sfp_select_interface(struct sfp_bus *bus, unsigned long *link_modes) { + if (phylink_test(link_modes, 25000baseCR_Full) || + phylink_test(link_modes, 25000baseKR_Full) || + phylink_test(link_modes, 25000baseSR_Full)) + return PHY_INTERFACE_MODE_25GBASER; + if (phylink_test(link_modes, 10000baseCR_Full) || phylink_test(link_modes, 10000baseSR_Full) || phylink_test(link_modes, 10000baseLR_Full) || @@ -624,14 +629,14 @@ static void sfp_upstream_clear(struct sfp_bus *bus) * be put via sfp_bus_put() when done. * * Returns: - * - on success, a pointer to the sfp_bus structure, - * - %NULL if no SFP is specified, - * - on failure, an error pointer value: + * - on success, a pointer to the sfp_bus structure, + * - %NULL if no SFP is specified, + * - on failure, an error pointer value: * - * - corresponding to the errors detailed for - * fwnode_property_get_reference_args(). - * - %-ENOMEM if we failed to allocate the bus. - * - an error from the upstream's connect_phy() method. + * - corresponding to the errors detailed for + * fwnode_property_get_reference_args(). + * - %-ENOMEM if we failed to allocate the bus. + * - an error from the upstream's connect_phy() method. */ struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) { @@ -666,14 +671,14 @@ EXPORT_SYMBOL_GPL(sfp_bus_find_fwnode); * bus, so it is safe to put the bus after this call. * * Returns: - * - on success, a pointer to the sfp_bus structure, - * - %NULL if no SFP is specified, - * - on failure, an error pointer value: + * - on success, a pointer to the sfp_bus structure, + * - %NULL if no SFP is specified, + * - on failure, an error pointer value: * - * - corresponding to the errors detailed for - * fwnode_property_get_reference_args(). - * - %-ENOMEM if we failed to allocate the bus. - * - an error from the upstream's connect_phy() method. + * - corresponding to the errors detailed for + * fwnode_property_get_reference_args(). + * - %-ENOMEM if we failed to allocate the bus. + * - an error from the upstream's connect_phy() method. */ int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, const struct sfp_upstream_ops *ops) diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 37f722c763d7..34e90216bd2c 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -2153,7 +2153,7 @@ static void sfp_sm_main(struct sfp *sfp, unsigned int event) case SFP_S_INIT: if (event == SFP_E_TIMEOUT && sfp->state & SFP_F_TX_FAULT) { - /* TX_FAULT is still asserted after t_init or + /* TX_FAULT is still asserted after t_init * or t_start_up, so assume there is a fault. */ sfp_sm_fault(sfp, SFP_S_INIT_TX_FAULT, diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c index ca49c1ad3efc..8b5445a724ce 100644 --- a/drivers/net/phy/spi_ks8995.c +++ b/drivers/net/phy/spi_ks8995.c @@ -160,11 +160,11 @@ static const struct spi_device_id ks8995_id[] = { MODULE_DEVICE_TABLE(spi, ks8995_id); static const struct of_device_id ks8895_spi_of_match[] = { - { .compatible = "micrel,ks8995" }, - { .compatible = "micrel,ksz8864" }, - { .compatible = "micrel,ksz8795" }, - { }, - }; + { .compatible = "micrel,ks8995" }, + { .compatible = "micrel,ksz8864" }, + { .compatible = "micrel,ksz8795" }, + { }, +}; MODULE_DEVICE_TABLE(of, ks8895_spi_of_match); static inline u8 get_chip_id(u8 val) diff --git a/drivers/net/phy/ste10Xp.c b/drivers/net/phy/ste10Xp.c index 431fe5e0ce31..309e4c3496c4 100644 --- a/drivers/net/phy/ste10Xp.c +++ b/drivers/net/phy/ste10Xp.c @@ -20,12 +20,12 @@ #include #include -#define MII_XCIIS 0x11 /* Configuration Info IRQ & Status Reg */ -#define MII_XIE 0x12 /* Interrupt Enable Register */ +#define MII_XCIIS 0x11 /* Configuration Info IRQ & Status Reg */ +#define MII_XIE 0x12 /* Interrupt Enable Register */ #define MII_XIE_DEFAULT_MASK 0x0070 /* ANE complete, Remote Fault, Link Down */ #define STE101P_PHY_ID 0x00061c50 -#define STE100P_PHY_ID 0x1c040011 +#define STE100P_PHY_ID 0x1c040011 static int ste10Xp_config_init(struct phy_device *phydev) { diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 16704e243162..897b979ec03c 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -249,7 +249,8 @@ static int vsc73xx_config_aneg(struct phy_device *phydev) /* This adds a skew for both TX and RX clocks, so the skew should only be * applied to "rgmii-id" interfaces. It may not work as expected - * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. */ + * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. + */ static int vsc8601_add_skew(struct phy_device *phydev) { int ret; diff --git a/drivers/net/ppp/bsd_comp.c b/drivers/net/ppp/bsd_comp.c index 61fedb23d3cf..db0dc36d12e3 100644 --- a/drivers/net/ppp/bsd_comp.c +++ b/drivers/net/ppp/bsd_comp.c @@ -436,7 +436,7 @@ static void *bsd_alloc (unsigned char *options, int opt_len, int decomp) * Initialize the data information for the compression code */ db->totlen = sizeof (struct bsd_db) + - (sizeof (struct bsd_dict) * hsize); + (sizeof (struct bsd_dict) * hsize); db->hsize = hsize; db->hshift = hshift; diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c index f78ceba42e57..ba93bab948e0 100644 --- a/drivers/net/slip/slhc.c +++ b/drivers/net/slip/slhc.c @@ -325,7 +325,7 @@ found: * Found it -- move to the front on the connection list. */ if(lcs == ocs) { - /* found at most recently used */ + /* found at most recently used */ } else if (cs == ocs) { /* found at least recently used */ comp->xmit_oldest = lcs->cs_this; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 84f832806313..2ced021f4faf 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2559,15 +2559,15 @@ static int tun_flags(struct tun_struct *tun) return tun->flags & (TUN_FEATURES | IFF_PERSIST | IFF_TUN | IFF_TAP); } -static ssize_t tun_show_flags(struct device *dev, struct device_attribute *attr, +static ssize_t tun_flags_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return sprintf(buf, "0x%x\n", tun_flags(tun)); } -static ssize_t tun_show_owner(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t owner_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return uid_valid(tun->owner)? @@ -2576,8 +2576,8 @@ static ssize_t tun_show_owner(struct device *dev, struct device_attribute *attr, sprintf(buf, "-1\n"); } -static ssize_t tun_show_group(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t group_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct tun_struct *tun = netdev_priv(to_net_dev(dev)); return gid_valid(tun->group) ? @@ -2586,9 +2586,9 @@ static ssize_t tun_show_group(struct device *dev, struct device_attribute *attr, sprintf(buf, "-1\n"); } -static DEVICE_ATTR(tun_flags, 0444, tun_show_flags, NULL); -static DEVICE_ATTR(owner, 0444, tun_show_owner, NULL); -static DEVICE_ATTR(group, 0444, tun_show_group, NULL); +static DEVICE_ATTR_RO(tun_flags); +static DEVICE_ATTR_RO(owner); +static DEVICE_ATTR_RO(group); static struct attribute *tun_dev_attrs[] = { &dev_attr_tun_flags.attr, diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index fbbe78643631..4c5d69732a7e 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -164,12 +164,14 @@ config USB_NET_AX8817X depends on USB_USBNET select CRC32 select PHYLIB + select AX88796B_PHY + imply NET_SELFTESTS default y help This option adds support for ASIX AX88xxx based USB 2.0 10/100 Ethernet adapters. - This driver should work with at least the following devices: + This driver should work with at least the following devices: * Aten UC210T * ASIX AX88172 * Billionton Systems, USB2AR @@ -220,13 +222,13 @@ config USB_NET_CDCETHER CDC Ethernet is an implementation option for DOCSIS cable modems that support USB connectivity, used for non-Microsoft USB hosts. The Linux-USB CDC Ethernet Gadget driver is an open implementation. - This driver should work with at least the following devices: + This driver should work with at least the following devices: * Dell Wireless 5530 HSPA - * Ericsson PipeRider (all variants) + * Ericsson PipeRider (all variants) * Ericsson Mobile Broadband Module (all variants) - * Motorola (DM100 and SB4100) - * Broadcom Cable Modem (reference design) + * Motorola (DM100 and SB4100) + * Broadcom Cable Modem (reference design) * Toshiba (PCX1100U and F3507g/F3607gw) * ... diff --git a/drivers/net/usb/asix.h b/drivers/net/usb/asix.h index 3b53685301de..e1994a246122 100644 --- a/drivers/net/usb/asix.h +++ b/drivers/net/usb/asix.h @@ -25,6 +25,8 @@ #include #include #include +#include +#include #define DRIVER_VERSION "22-Dec-2011" #define DRIVER_NAME "asix" @@ -178,6 +180,10 @@ struct asix_common_private { u16 presvd_phy_advertise; u16 presvd_phy_bmcr; struct asix_rx_fixup_info rx_fixup_info; + struct mii_bus *mdio; + struct phy_device *phydev; + u16 phy_addr; + char phy_name[20]; }; extern const struct driver_info ax88172a_info; @@ -205,8 +211,7 @@ struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb, int asix_set_sw_mii(struct usbnet *dev, int in_pm); int asix_set_hw_mii(struct usbnet *dev, int in_pm); -int asix_read_phy_addr(struct usbnet *dev, int internal); -int asix_get_phy_addr(struct usbnet *dev); +int asix_read_phy_addr(struct usbnet *dev, bool internal); int asix_sw_reset(struct usbnet *dev, u8 flags, int in_pm); @@ -215,6 +220,7 @@ int asix_write_rx_ctl(struct usbnet *dev, u16 mode, int in_pm); u16 asix_read_medium_status(struct usbnet *dev, int in_pm); int asix_write_medium_mode(struct usbnet *dev, u16 mode, int in_pm); +void asix_adjust_link(struct net_device *netdev); int asix_write_gpio(struct usbnet *dev, u16 value, int sleep, int in_pm); @@ -223,6 +229,9 @@ void asix_set_multicast(struct net_device *net); int asix_mdio_read(struct net_device *netdev, int phy_id, int loc); void asix_mdio_write(struct net_device *netdev, int phy_id, int loc, int val); +int asix_mdio_bus_read(struct mii_bus *bus, int phy_id, int regnum); +int asix_mdio_bus_write(struct mii_bus *bus, int phy_id, int regnum, u16 val); + int asix_mdio_read_nopm(struct net_device *netdev, int phy_id, int loc); void asix_mdio_write_nopm(struct net_device *netdev, int phy_id, int loc, int val); diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 7bc6e8f856fe..ac92bc52a85e 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -288,33 +288,34 @@ int asix_set_hw_mii(struct usbnet *dev, int in_pm) return ret; } -int asix_read_phy_addr(struct usbnet *dev, int internal) +int asix_read_phy_addr(struct usbnet *dev, bool internal) { - int offset = (internal ? 1 : 0); + int ret, offset; u8 buf[2]; - int ret = asix_read_cmd(dev, AX_CMD_READ_PHY_ID, 0, 0, 2, buf, 0); - netdev_dbg(dev->net, "asix_get_phy_addr()\n"); + ret = asix_read_cmd(dev, AX_CMD_READ_PHY_ID, 0, 0, 2, buf, 0); + if (ret < 0) + goto error; if (ret < 2) { - netdev_err(dev->net, "Error reading PHYID register: %02x\n", ret); - goto out; + ret = -EIO; + goto error; } - netdev_dbg(dev->net, "asix_get_phy_addr() returning 0x%04x\n", - *((__le16 *)buf)); + + offset = (internal ? 1 : 0); ret = buf[offset]; -out: + netdev_dbg(dev->net, "%s PHY address 0x%x\n", + internal ? "internal" : "external", ret); + + return ret; + +error: + netdev_err(dev->net, "Error reading PHY_ID register: %02x\n", ret); + return ret; } -int asix_get_phy_addr(struct usbnet *dev) -{ - /* return the address of the internal phy */ - return asix_read_phy_addr(dev, 1); -} - - int asix_sw_reset(struct usbnet *dev, u8 flags, int in_pm) { int ret; @@ -383,6 +384,27 @@ int asix_write_medium_mode(struct usbnet *dev, u16 mode, int in_pm) return ret; } +/* set MAC link settings according to information from phylib */ +void asix_adjust_link(struct net_device *netdev) +{ + struct phy_device *phydev = netdev->phydev; + struct usbnet *dev = netdev_priv(netdev); + u16 mode = 0; + + if (phydev->link) { + mode = AX88772_MEDIUM_DEFAULT; + + if (phydev->duplex == DUPLEX_HALF) + mode &= ~AX_MEDIUM_FD; + + if (phydev->speed != SPEED_100) + mode &= ~AX_MEDIUM_PS; + } + + asix_write_medium_mode(dev, mode, 0); + phy_print_status(phydev); +} + int asix_write_gpio(struct usbnet *dev, u16 value, int sleep, int in_pm) { int ret; @@ -463,18 +485,23 @@ int asix_mdio_read(struct net_device *netdev, int phy_id, int loc) return ret; } - asix_read_cmd(dev, AX_CMD_READ_MII_REG, phy_id, - (__u16)loc, 2, &res, 0); - asix_set_hw_mii(dev, 0); + ret = asix_read_cmd(dev, AX_CMD_READ_MII_REG, phy_id, (__u16)loc, 2, + &res, 0); + if (ret < 0) + goto out; + + ret = asix_set_hw_mii(dev, 0); +out: mutex_unlock(&dev->phy_mutex); netdev_dbg(dev->net, "asix_mdio_read() phy_id=0x%02x, loc=0x%02x, returns=0x%04x\n", phy_id, loc, le16_to_cpu(res)); - return le16_to_cpu(res); + return ret < 0 ? ret : le16_to_cpu(res); } -void asix_mdio_write(struct net_device *netdev, int phy_id, int loc, int val) +static int __asix_mdio_write(struct net_device *netdev, int phy_id, int loc, + int val) { struct usbnet *dev = netdev_priv(netdev); __le16 res = cpu_to_le16(val); @@ -494,15 +521,40 @@ void asix_mdio_write(struct net_device *netdev, int phy_id, int loc, int val) ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG, 0, 0, 1, &smsr, 0); } while (!(smsr & AX_HOST_EN) && (i++ < 30) && (ret != -ENODEV)); - if (ret == -ENODEV) { - mutex_unlock(&dev->phy_mutex); - return; - } - asix_write_cmd(dev, AX_CMD_WRITE_MII_REG, phy_id, - (__u16)loc, 2, &res, 0); - asix_set_hw_mii(dev, 0); + if (ret == -ENODEV) + goto out; + + ret = asix_write_cmd(dev, AX_CMD_WRITE_MII_REG, phy_id, (__u16)loc, 2, + &res, 0); + if (ret < 0) + goto out; + + ret = asix_set_hw_mii(dev, 0); +out: mutex_unlock(&dev->phy_mutex); + + return ret < 0 ? ret : 0; +} + +void asix_mdio_write(struct net_device *netdev, int phy_id, int loc, int val) +{ + __asix_mdio_write(netdev, phy_id, loc, val); +} + +/* MDIO read and write wrappers for phylib */ +int asix_mdio_bus_read(struct mii_bus *bus, int phy_id, int regnum) +{ + struct usbnet *priv = bus->priv; + + return asix_mdio_read(priv->net, phy_id, regnum); +} + +int asix_mdio_bus_write(struct mii_bus *bus, int phy_id, int regnum, u16 val) +{ + struct usbnet *priv = bus->priv; + + return __asix_mdio_write(priv->net, phy_id, regnum, val); } int asix_mdio_read_nopm(struct net_device *netdev, int phy_id, int loc) diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 19a8fafb8f04..aec97b021a73 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -262,7 +262,10 @@ static int ax88172_bind(struct usbnet *dev, struct usb_interface *intf) dev->mii.mdio_write = asix_mdio_write; dev->mii.phy_id_mask = 0x3f; dev->mii.reg_num_mask = 0x1f; - dev->mii.phy_id = asix_get_phy_addr(dev); + + dev->mii.phy_id = asix_read_phy_addr(dev, true); + if (dev->mii.phy_id < 0) + return dev->mii.phy_id; dev->net->netdev_ops = &ax88172_netdev_ops; dev->net->ethtool_ops = &ax88172_ethtool_ops; @@ -280,9 +283,29 @@ out: return ret; } +static void ax88772_ethtool_get_strings(struct net_device *netdev, u32 sset, + u8 *data) +{ + switch (sset) { + case ETH_SS_TEST: + net_selftest_get_strings(data); + break; + } +} + +static int ax88772_ethtool_get_sset_count(struct net_device *ndev, int sset) +{ + switch (sset) { + case ETH_SS_TEST: + return net_selftest_get_count(); + default: + return -EOPNOTSUPP; + } +} + static const struct ethtool_ops ax88772_ethtool_ops = { .get_drvinfo = asix_get_drvinfo, - .get_link = asix_get_link, + .get_link = usbnet_get_link, .get_msglevel = usbnet_get_msglevel, .set_msglevel = usbnet_set_msglevel, .get_wol = asix_get_wol, @@ -290,37 +313,18 @@ static const struct ethtool_ops ax88772_ethtool_ops = { .get_eeprom_len = asix_get_eeprom_len, .get_eeprom = asix_get_eeprom, .set_eeprom = asix_set_eeprom, - .nway_reset = usbnet_nway_reset, - .get_link_ksettings = usbnet_get_link_ksettings_mii, - .set_link_ksettings = usbnet_set_link_ksettings_mii, + .nway_reset = phy_ethtool_nway_reset, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, + .self_test = net_selftest, + .get_strings = ax88772_ethtool_get_strings, + .get_sset_count = ax88772_ethtool_get_sset_count, }; -static int ax88772_link_reset(struct usbnet *dev) -{ - u16 mode; - struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET }; - - mii_check_media(&dev->mii, 1, 1); - mii_ethtool_gset(&dev->mii, &ecmd); - mode = AX88772_MEDIUM_DEFAULT; - - if (ethtool_cmd_speed(&ecmd) != SPEED_100) - mode &= ~AX_MEDIUM_PS; - - if (ecmd.duplex != DUPLEX_FULL) - mode &= ~AX_MEDIUM_FD; - - netdev_dbg(dev->net, "ax88772_link_reset() speed: %u duplex: %d setting mode to 0x%04x\n", - ethtool_cmd_speed(&ecmd), ecmd.duplex, mode); - - asix_write_medium_mode(dev, mode, 0); - - return 0; -} - static int ax88772_reset(struct usbnet *dev) { struct asix_data *data = (struct asix_data *)&dev->data; + struct asix_common_private *priv = dev->driver_priv; int ret; /* Rewrite MAC address */ @@ -339,6 +343,8 @@ static int ax88772_reset(struct usbnet *dev) if (ret < 0) goto out; + phy_start(priv->phydev); + return 0; out: @@ -583,7 +589,7 @@ static const struct net_device_ops ax88772_netdev_ops = { .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = asix_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_do_ioctl = asix_ioctl, + .ndo_do_ioctl = phy_do_ioctl_running, .ndo_set_rx_mode = asix_set_multicast, }; @@ -592,6 +598,9 @@ static void ax88772_suspend(struct usbnet *dev) struct asix_common_private *priv = dev->driver_priv; u16 medium; + if (netif_running(dev->net)) + phy_stop(priv->phydev); + /* Stop MAC operation */ medium = asix_read_medium_status(dev, 1); medium &= ~AX_MEDIUM_RE; @@ -599,14 +608,6 @@ static void ax88772_suspend(struct usbnet *dev) netdev_dbg(dev->net, "ax88772_suspend: medium=0x%04x\n", asix_read_medium_status(dev, 1)); - - /* Preserve BMCR for restoring */ - priv->presvd_phy_bmcr = - asix_mdio_read_nopm(dev->net, dev->mii.phy_id, MII_BMCR); - - /* Preserve ANAR for restoring */ - priv->presvd_phy_advertise = - asix_mdio_read_nopm(dev->net, dev->mii.phy_id, MII_ADVERTISE); } static int asix_suspend(struct usb_interface *intf, pm_message_t message) @@ -620,39 +621,22 @@ static int asix_suspend(struct usb_interface *intf, pm_message_t message) return usbnet_suspend(intf, message); } -static void ax88772_restore_phy(struct usbnet *dev) -{ - struct asix_common_private *priv = dev->driver_priv; - - if (priv->presvd_phy_advertise) { - /* Restore Advertisement control reg */ - asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_ADVERTISE, - priv->presvd_phy_advertise); - - /* Restore BMCR */ - if (priv->presvd_phy_bmcr & BMCR_ANENABLE) - priv->presvd_phy_bmcr |= BMCR_ANRESTART; - - asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_BMCR, - priv->presvd_phy_bmcr); - - priv->presvd_phy_advertise = 0; - priv->presvd_phy_bmcr = 0; - } -} - static void ax88772_resume(struct usbnet *dev) { + struct asix_common_private *priv = dev->driver_priv; int i; for (i = 0; i < 3; i++) if (!ax88772_hw_reset(dev, 1)) break; - ax88772_restore_phy(dev); + + if (netif_running(dev->net)) + phy_start(priv->phydev); } static void ax88772a_resume(struct usbnet *dev) { + struct asix_common_private *priv = dev->driver_priv; int i; for (i = 0; i < 3; i++) { @@ -660,7 +644,8 @@ static void ax88772a_resume(struct usbnet *dev) break; } - ax88772_restore_phy(dev); + if (netif_running(dev->net)) + phy_start(priv->phydev); } static int asix_resume(struct usb_interface *intf) @@ -674,12 +659,61 @@ static int asix_resume(struct usb_interface *intf) return usbnet_resume(intf); } +static int ax88772_init_mdio(struct usbnet *dev) +{ + struct asix_common_private *priv = dev->driver_priv; + + priv->mdio = devm_mdiobus_alloc(&dev->udev->dev); + if (!priv->mdio) + return -ENOMEM; + + priv->mdio->priv = dev; + priv->mdio->read = &asix_mdio_bus_read; + priv->mdio->write = &asix_mdio_bus_write; + priv->mdio->name = "Asix MDIO Bus"; + /* mii bus name is usb-- */ + snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", + dev->udev->bus->busnum, dev->udev->devnum); + + return devm_mdiobus_register(&dev->udev->dev, priv->mdio); +} + +static int ax88772_init_phy(struct usbnet *dev) +{ + struct asix_common_private *priv = dev->driver_priv; + int ret; + + ret = asix_read_phy_addr(dev, true); + if (ret < 0) + return ret; + + priv->phy_addr = ret; + + snprintf(priv->phy_name, sizeof(priv->phy_name), PHY_ID_FMT, + priv->mdio->id, priv->phy_addr); + + priv->phydev = phy_connect(dev->net, priv->phy_name, &asix_adjust_link, + PHY_INTERFACE_MODE_INTERNAL); + if (IS_ERR(priv->phydev)) { + netdev_err(dev->net, "Could not connect to PHY device %s\n", + priv->phy_name); + ret = PTR_ERR(priv->phydev); + return ret; + } + + priv->phydev->mac_managed_pm = 1; + + phy_attached_info(priv->phydev); + + return 0; +} + static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf) { - int ret, i; u8 buf[ETH_ALEN] = {0}, chipcode = 0; - u32 phyid; struct asix_common_private *priv; + int ret, i; + u32 phyid; usbnet_get_endpoints(dev, intf); @@ -711,14 +745,6 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf) asix_set_netdev_dev_addr(dev, buf); - /* Initialize MII structure */ - dev->mii.dev = dev->net; - dev->mii.mdio_read = asix_mdio_read; - dev->mii.mdio_write = asix_mdio_write; - dev->mii.phy_id_mask = 0x1f; - dev->mii.reg_num_mask = 0x1f; - dev->mii.phy_id = asix_get_phy_addr(dev); - dev->net->netdev_ops = &ax88772_netdev_ops; dev->net->ethtool_ops = &ax88772_ethtool_ops; dev->net->needed_headroom = 4; /* cf asix_tx_fixup() */ @@ -746,11 +772,11 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf) dev->rx_urb_size = 2048; } - dev->driver_priv = kzalloc(sizeof(struct asix_common_private), GFP_KERNEL); - if (!dev->driver_priv) + priv = devm_kzalloc(&dev->udev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) return -ENOMEM; - priv = dev->driver_priv; + dev->driver_priv = priv; priv->presvd_phy_bmcr = 0; priv->presvd_phy_advertise = 0; @@ -762,13 +788,32 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf) priv->suspend = ax88772_suspend; } + ret = ax88772_init_mdio(dev); + if (ret) + return ret; + + return ax88772_init_phy(dev); +} + +static int ax88772_stop(struct usbnet *dev) +{ + struct asix_common_private *priv = dev->driver_priv; + + /* On unplugged USB, we will get MDIO communication errors and the + * PHY will be set in to PHY_HALTED state. + */ + if (priv->phydev->state != PHY_HALTED) + phy_stop(priv->phydev); + return 0; } static void ax88772_unbind(struct usbnet *dev, struct usb_interface *intf) { + struct asix_common_private *priv = dev->driver_priv; + + phy_disconnect(priv->phydev); asix_rx_fixup_common_free(dev->driver_priv); - kfree(dev->driver_priv); } static const struct ethtool_ops ax88178_ethtool_ops = { @@ -1081,7 +1126,10 @@ static int ax88178_bind(struct usbnet *dev, struct usb_interface *intf) dev->mii.phy_id_mask = 0x1f; dev->mii.reg_num_mask = 0xff; dev->mii.supports_gmii = 1; - dev->mii.phy_id = asix_get_phy_addr(dev); + + dev->mii.phy_id = asix_read_phy_addr(dev, true); + if (dev->mii.phy_id < 0) + return dev->mii.phy_id; dev->net->netdev_ops = &ax88178_netdev_ops; dev->net->ethtool_ops = &ax88178_ethtool_ops; @@ -1153,8 +1201,8 @@ static const struct driver_info ax88772_info = { .bind = ax88772_bind, .unbind = ax88772_unbind, .status = asix_status, - .link_reset = ax88772_link_reset, .reset = ax88772_reset, + .stop = ax88772_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET, .rx_fixup = asix_rx_fixup_common, .tx_fixup = asix_tx_fixup, @@ -1165,7 +1213,6 @@ static const struct driver_info ax88772b_info = { .bind = ax88772_bind, .unbind = ax88772_unbind, .status = asix_status, - .link_reset = ax88772_link_reset, .reset = ax88772_reset, .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET, @@ -1201,7 +1248,6 @@ static const struct driver_info hg20f9_info = { .bind = ax88772_bind, .unbind = ax88772_unbind, .status = asix_status, - .link_reset = ax88772_link_reset, .reset = ax88772_reset, .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET, diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index b404c9462dce..530947d7477b 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -25,20 +25,6 @@ struct ax88172a_private { struct asix_rx_fixup_info rx_fixup_info; }; -/* MDIO read and write wrappers for phylib */ -static int asix_mdio_bus_read(struct mii_bus *bus, int phy_id, int regnum) -{ - return asix_mdio_read(((struct usbnet *)bus->priv)->net, phy_id, - regnum); -} - -static int asix_mdio_bus_write(struct mii_bus *bus, int phy_id, int regnum, - u16 val) -{ - asix_mdio_write(((struct usbnet *)bus->priv)->net, phy_id, regnum, val); - return 0; -} - /* set MAC link settings according to information from phylib */ static void ax88172a_adjust_link(struct net_device *netdev) { @@ -219,7 +205,12 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf) goto free; } - priv->phy_addr = asix_read_phy_addr(dev, priv->use_embdphy); + ret = asix_read_phy_addr(dev, priv->use_embdphy); + if (ret < 0) + goto free; + + priv->phy_addr = ret; + ax88172a_reset_phy(dev, priv->use_embdphy); /* Asix framing packs multiple eth frames into a 2K usb bulk transfer */ diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 7eb0109e9baa..eb3817d70f2b 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -217,7 +217,7 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf) goto bad_desc; } skip: - /* Communcation class functions with bmCapabilities are not + /* Communication class functions with bmCapabilities are not * RNDIS. But some Wireless class RNDIS functions use * bmCapabilities for their own purpose. The failsafe is * therefore applied only to Communication class RNDIS diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index 5db66272fc82..4c4ab7b38d78 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -168,6 +168,7 @@ static int cdc_mbim_bind(struct usbnet *dev, struct usb_interface *intf) subdriver = usb_cdc_wdm_register(ctx->control, &dev->status->desc, le16_to_cpu(ctx->mbim_desc->wMaxControlMessage), + WWAN_PORT_MBIM, cdc_mbim_wdm_manage_power); if (IS_ERR(subdriver)) { ret = PTR_ERR(subdriver); @@ -300,8 +301,8 @@ error: return NULL; } -/* Some devices are known to send Neigbor Solicitation messages and - * require Neigbor Advertisement replies. The IPv6 core will not +/* Some devices are known to send Neighbor Solicitation messages and + * require Neighbor Advertisement replies. The IPv6 core will not * respond since IFF_NOARP is set, so we must handle them ourselves. */ static void do_neigh_solicit(struct usbnet *dev, u8 *buf, u16 tci) @@ -588,7 +589,7 @@ static const struct driver_info cdc_mbim_info_zlp = { * * Note: The current implementation of this feature restricts each NTB * to a single NDP, implying that multiplexed sessions cannot share an - * NTB. This might affect performace for multiplexed sessions. + * NTB. This might affect performance for multiplexed sessions. */ static const struct driver_info cdc_mbim_info_ndp_to_end = { .description = "CDC MBIM", diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index df0d1837e4ed..24753a4da7e6 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -192,7 +192,8 @@ static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx) return val; } -static ssize_t cdc_ncm_show_min_tx_pkt(struct device *d, struct device_attribute *attr, char *buf) +static ssize_t min_tx_pkt_show(struct device *d, + struct device_attribute *attr, char *buf) { struct usbnet *dev = netdev_priv(to_net_dev(d)); struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; @@ -200,7 +201,8 @@ static ssize_t cdc_ncm_show_min_tx_pkt(struct device *d, struct device_attribute return sprintf(buf, "%u\n", ctx->min_tx_pkt); } -static ssize_t cdc_ncm_show_rx_max(struct device *d, struct device_attribute *attr, char *buf) +static ssize_t rx_max_show(struct device *d, + struct device_attribute *attr, char *buf) { struct usbnet *dev = netdev_priv(to_net_dev(d)); struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; @@ -208,7 +210,8 @@ static ssize_t cdc_ncm_show_rx_max(struct device *d, struct device_attribute *at return sprintf(buf, "%u\n", ctx->rx_max); } -static ssize_t cdc_ncm_show_tx_max(struct device *d, struct device_attribute *attr, char *buf) +static ssize_t tx_max_show(struct device *d, + struct device_attribute *attr, char *buf) { struct usbnet *dev = netdev_priv(to_net_dev(d)); struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; @@ -216,7 +219,8 @@ static ssize_t cdc_ncm_show_tx_max(struct device *d, struct device_attribute *at return sprintf(buf, "%u\n", ctx->tx_max); } -static ssize_t cdc_ncm_show_tx_timer_usecs(struct device *d, struct device_attribute *attr, char *buf) +static ssize_t tx_timer_usecs_show(struct device *d, + struct device_attribute *attr, char *buf) { struct usbnet *dev = netdev_priv(to_net_dev(d)); struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; @@ -224,7 +228,9 @@ static ssize_t cdc_ncm_show_tx_timer_usecs(struct device *d, struct device_attri return sprintf(buf, "%u\n", ctx->timer_interval / (u32)NSEC_PER_USEC); } -static ssize_t cdc_ncm_store_min_tx_pkt(struct device *d, struct device_attribute *attr, const char *buf, size_t len) +static ssize_t min_tx_pkt_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) { struct usbnet *dev = netdev_priv(to_net_dev(d)); struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; @@ -238,7 +244,9 @@ static ssize_t cdc_ncm_store_min_tx_pkt(struct device *d, struct device_attribu return len; } -static ssize_t cdc_ncm_store_rx_max(struct device *d, struct device_attribute *attr, const char *buf, size_t len) +static ssize_t rx_max_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) { struct usbnet *dev = netdev_priv(to_net_dev(d)); struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; @@ -251,7 +259,9 @@ static ssize_t cdc_ncm_store_rx_max(struct device *d, struct device_attribute * return len; } -static ssize_t cdc_ncm_store_tx_max(struct device *d, struct device_attribute *attr, const char *buf, size_t len) +static ssize_t tx_max_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) { struct usbnet *dev = netdev_priv(to_net_dev(d)); struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; @@ -264,7 +274,9 @@ static ssize_t cdc_ncm_store_tx_max(struct device *d, struct device_attribute * return len; } -static ssize_t cdc_ncm_store_tx_timer_usecs(struct device *d, struct device_attribute *attr, const char *buf, size_t len) +static ssize_t tx_timer_usecs_store(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) { struct usbnet *dev = netdev_priv(to_net_dev(d)); struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; @@ -285,10 +297,10 @@ static ssize_t cdc_ncm_store_tx_timer_usecs(struct device *d, struct device_att return len; } -static DEVICE_ATTR(min_tx_pkt, 0644, cdc_ncm_show_min_tx_pkt, cdc_ncm_store_min_tx_pkt); -static DEVICE_ATTR(rx_max, 0644, cdc_ncm_show_rx_max, cdc_ncm_store_rx_max); -static DEVICE_ATTR(tx_max, 0644, cdc_ncm_show_tx_max, cdc_ncm_store_tx_max); -static DEVICE_ATTR(tx_timer_usecs, 0644, cdc_ncm_show_tx_timer_usecs, cdc_ncm_store_tx_timer_usecs); +static DEVICE_ATTR_RW(min_tx_pkt); +static DEVICE_ATTR_RW(rx_max); +static DEVICE_ATTR_RW(tx_max); +static DEVICE_ATTR_RW(tx_timer_usecs); static ssize_t ndp_to_end_show(struct device *d, struct device_attribute *attr, char *buf) { @@ -628,7 +640,7 @@ out: /* set MTU to max supported by the device if necessary */ dev->net->mtu = min_t(int, dev->net->mtu, ctx->max_datagram_size - cdc_ncm_eth_hlen(dev)); - /* do not exceed operater preferred MTU */ + /* do not exceed operator preferred MTU */ if (ctx->mbim_extended_desc) { mbim_mtu = le16_to_cpu(ctx->mbim_extended_desc->wMTU); if (mbim_mtu != 0 && mbim_mtu < dev->net->mtu) @@ -685,7 +697,7 @@ static int cdc_ncm_setup(struct usbnet *dev) struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; u32 def_rx, def_tx; - /* be conservative when selecting intial buffer size to + /* be conservative when selecting initial buffer size to * increase the number of hosts this will work for */ def_rx = min_t(u32, CDC_NCM_NTB_DEF_SIZE_RX, diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 5c779cc0ea11..54ef8492ca01 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -457,9 +457,8 @@ static const struct usb_device_id hso_ids[] = { MODULE_DEVICE_TABLE(usb, hso_ids); /* Sysfs attribute */ -static ssize_t hso_sysfs_show_porttype(struct device *dev, - struct device_attribute *attr, - char *buf) +static ssize_t hsotype_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct hso_device *hso_dev = dev_get_drvdata(dev); char *port_name; @@ -505,7 +504,7 @@ static ssize_t hso_sysfs_show_porttype(struct device *dev, return sprintf(buf, "%s\n", port_name); } -static DEVICE_ATTR(hsotype, 0444, hso_sysfs_show_porttype, NULL); +static DEVICE_ATTR_RO(hsotype); static struct attribute *hso_serial_dev_attrs[] = { &dev_attr_hsotype.attr, diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c index a87f0dabcdb7..849b77330bf2 100644 --- a/drivers/net/usb/huawei_cdc_ncm.c +++ b/drivers/net/usb/huawei_cdc_ncm.c @@ -96,6 +96,7 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev, subdriver = usb_cdc_wdm_register(ctx->control, &usbnet_dev->status->desc, 1024, /* wMaxCommand */ + WWAN_PORT_AT, huawei_cdc_ncm_wdm_manage_power); if (IS_ERR(subdriver)) { ret = PTR_ERR(subdriver); diff --git a/drivers/net/usb/int51x1.c b/drivers/net/usb/int51x1.c index ed05f992c612..6fde41550de1 100644 --- a/drivers/net/usb/int51x1.c +++ b/drivers/net/usb/int51x1.c @@ -61,7 +61,7 @@ static struct sk_buff *int51x1_tx_fixup(struct usbnet *dev, int need_tail = 0; __le16 *len; - /* if packet and our header is smaler than 64 pad to 64 (+ ZLP) */ + /* if packet and our header is smaller than 64 pad to 64 (+ ZLP) */ if ((pack_with_header_len) < dev->maxpacket) need_tail = dev->maxpacket - pack_with_header_len + 1; /* diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 02bce40a67e5..25489389ea49 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -298,7 +298,7 @@ struct lan78xx_net; struct lan78xx_priv { struct lan78xx_net *dev; u32 rfe_ctl; - u32 mchash_table[DP_SEL_VHF_HASH_LEN]; /* multicat hash table */ + u32 mchash_table[DP_SEL_VHF_HASH_LEN]; /* multicast hash table */ u32 pfilter_table[NUM_OF_MAF][2]; /* perfect filter table */ u32 vlan_table[DP_SEL_VHF_VLAN_LEN]; struct mutex dataport_mutex; /* for dataport access */ diff --git a/drivers/net/usb/lg-vl600.c b/drivers/net/usb/lg-vl600.c index 217a2d8fa47b..b2495fa80171 100644 --- a/drivers/net/usb/lg-vl600.c +++ b/drivers/net/usb/lg-vl600.c @@ -31,7 +31,7 @@ * Windows/Mac drivers do send a couple of such frames to the device * during initialisation, with protocol set to 0x0906 or 0x0b06 and (what * seems to be) a flag in the .dummy_flags. This doesn't seem necessary - * for modem operation but can possibly be used for GPS or other funcitons. + * for modem operation but can possibly be used for GPS or other functions. */ struct vl600_frame_hdr { @@ -72,7 +72,7 @@ static int vl600_bind(struct usbnet *dev, struct usb_interface *intf) /* ARP packets don't go through, but they're also of no use. The * subnet has only two hosts anyway: us and the gateway / DHCP * server (probably simulated by modem firmware or network operator) - * whose address changes everytime we connect to the intarwebz and + * whose address changes every time we connect to the intarwebz and * who doesn't bother answering ARP requests either. So hardware * addresses have no meaning, the destination and the source of every * packet depend only on whether it is on the IN or OUT endpoint. */ diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c index 9f9352a4522f..2469bdcb1a04 100644 --- a/drivers/net/usb/mcs7830.c +++ b/drivers/net/usb/mcs7830.c @@ -601,7 +601,7 @@ MODULE_DEVICE_TABLE(usb, products); static int mcs7830_reset_resume (struct usb_interface *intf) { - /* YES, this function is successful enough that ethtool -d + /* YES, this function is successful enough that ethtool -d does show same output pre-/post-suspend */ struct usbnet *dev = usb_get_intfdata(intf); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index bc55ec739af9..6a2e4f884b12 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -710,7 +710,8 @@ static int qmi_wwan_register_subdriver(struct usbnet *dev) /* register subdriver */ subdriver = usb_cdc_wdm_register(info->control, &dev->status->desc, - 4096, &qmi_wwan_cdc_wdm_manage_power); + 4096, WWAN_PORT_QMI, + &qmi_wwan_cdc_wdm_manage_power); if (IS_ERR(subdriver)) { dev_err(&info->control->dev, "subdriver registration failed\n"); rv = PTR_ERR(subdriver); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index e25bfb7021ed..1692d3b1b6e1 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -931,6 +931,8 @@ struct r8152 { u32 rx_pending; u32 fc_pause_on, fc_pause_off; + unsigned int pipe_in, pipe_out, pipe_intr, pipe_ctrl_in, pipe_ctrl_out; + u32 support_2500full:1; u32 lenovo_macpassthru:1; u32 dell_tb_rx_agg_bug:1; @@ -1198,7 +1200,7 @@ int get_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data) if (!tmp) return -ENOMEM; - ret = usb_control_msg(tp->udev, usb_rcvctrlpipe(tp->udev, 0), + ret = usb_control_msg(tp->udev, tp->pipe_ctrl_in, RTL8152_REQ_GET_REGS, RTL8152_REQT_READ, value, index, tmp, size, 500); if (ret < 0) @@ -1221,7 +1223,7 @@ int set_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data) if (!tmp) return -ENOMEM; - ret = usb_control_msg(tp->udev, usb_sndctrlpipe(tp->udev, 0), + ret = usb_control_msg(tp->udev, tp->pipe_ctrl_out, RTL8152_REQ_SET_REGS, RTL8152_REQT_WRITE, value, index, tmp, size, 500); @@ -2041,7 +2043,7 @@ static int alloc_all_mem(struct r8152 *tp) goto err1; tp->intr_interval = (int)ep_intr->desc.bInterval; - usb_fill_int_urb(tp->intr_urb, tp->udev, usb_rcvintpipe(tp->udev, 3), + usb_fill_int_urb(tp->intr_urb, tp->udev, tp->pipe_intr, tp->intr_buff, INTBUFSIZE, intr_callback, tp, tp->intr_interval); @@ -2305,7 +2307,7 @@ static int r8152_tx_agg_fill(struct r8152 *tp, struct tx_agg *agg) if (ret < 0) goto out_tx_fill; - usb_fill_bulk_urb(agg->urb, tp->udev, usb_sndbulkpipe(tp->udev, 2), + usb_fill_bulk_urb(agg->urb, tp->udev, tp->pipe_out, agg->head, (int)(tx_data - (u8 *)agg->head), (usb_complete_t)write_bulk_callback, agg); @@ -2445,7 +2447,7 @@ static int rx_bottom(struct r8152 *tp, int budget) unsigned int pkt_len, rx_frag_head_sz; struct sk_buff *skb; - /* limite the skb numbers for rx_queue */ + /* limit the skb numbers for rx_queue */ if (unlikely(skb_queue_len(&tp->rx_queue) >= 1000)) break; @@ -2620,7 +2622,7 @@ int r8152_submit_rx(struct r8152 *tp, struct rx_agg *agg, gfp_t mem_flags) !test_bit(WORK_ENABLE, &tp->flags) || !netif_carrier_ok(tp->netdev)) return 0; - usb_fill_bulk_urb(agg->urb, tp->udev, usb_rcvbulkpipe(tp->udev, 1), + usb_fill_bulk_urb(agg->urb, tp->udev, tp->pipe_in, agg->buffer, tp->rx_buf_sz, (usb_complete_t)read_bulk_callback, agg); @@ -8211,7 +8213,7 @@ static int rtl8152_post_reset(struct usb_interface *intf) if (!tp) return 0; - /* reset the MAC adddress in case of policy change */ + /* reset the MAC address in case of policy change */ if (determine_ethernet_addr(tp, &sa) >= 0) { rtnl_lock(); dev_set_mac_address (tp->netdev, &sa, NULL); @@ -8967,6 +8969,79 @@ static int rtl8152_set_ringparam(struct net_device *netdev, return 0; } +static void rtl8152_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) +{ + struct r8152 *tp = netdev_priv(netdev); + u16 bmcr, lcladv, rmtadv; + u8 cap; + + if (usb_autopm_get_interface(tp->intf) < 0) + return; + + mutex_lock(&tp->control); + + bmcr = r8152_mdio_read(tp, MII_BMCR); + lcladv = r8152_mdio_read(tp, MII_ADVERTISE); + rmtadv = r8152_mdio_read(tp, MII_LPA); + + mutex_unlock(&tp->control); + + usb_autopm_put_interface(tp->intf); + + if (!(bmcr & BMCR_ANENABLE)) { + pause->autoneg = 0; + pause->rx_pause = 0; + pause->tx_pause = 0; + return; + } + + pause->autoneg = 1; + + cap = mii_resolve_flowctrl_fdx(lcladv, rmtadv); + + if (cap & FLOW_CTRL_RX) + pause->rx_pause = 1; + + if (cap & FLOW_CTRL_TX) + pause->tx_pause = 1; +} + +static int rtl8152_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) +{ + struct r8152 *tp = netdev_priv(netdev); + u16 old, new1; + u8 cap = 0; + int ret; + + ret = usb_autopm_get_interface(tp->intf); + if (ret < 0) + return ret; + + mutex_lock(&tp->control); + + if (pause->autoneg && !(r8152_mdio_read(tp, MII_BMCR) & BMCR_ANENABLE)) { + ret = -EINVAL; + goto out; + } + + if (pause->rx_pause) + cap |= FLOW_CTRL_RX; + + if (pause->tx_pause) + cap |= FLOW_CTRL_TX; + + old = r8152_mdio_read(tp, MII_ADVERTISE); + new1 = (old & ~(ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM)) | mii_advertise_flowctrl(cap); + if (old != new1) + r8152_mdio_write(tp, MII_ADVERTISE, new1); + +out: + mutex_unlock(&tp->control); + usb_autopm_put_interface(tp->intf); + + return ret; +} + static const struct ethtool_ops ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS, .get_drvinfo = rtl8152_get_drvinfo, @@ -8989,6 +9064,8 @@ static const struct ethtool_ops ops = { .set_tunable = rtl8152_set_tunable, .get_ringparam = rtl8152_get_ringparam, .set_ringparam = rtl8152_set_ringparam, + .get_pauseparam = rtl8152_get_pauseparam, + .set_pauseparam = rtl8152_set_pauseparam, }; static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) @@ -9432,6 +9509,12 @@ static int rtl8152_probe(struct usb_interface *intf, tp->intf = intf; tp->version = version; + tp->pipe_ctrl_in = usb_rcvctrlpipe(udev, 0); + tp->pipe_ctrl_out = usb_sndctrlpipe(udev, 0); + tp->pipe_in = usb_rcvbulkpipe(udev, 1); + tp->pipe_out = usb_sndbulkpipe(udev, 2); + tp->pipe_intr = usb_rcvintpipe(udev, 3); + switch (version) { case RTL_VER_01: case RTL_VER_02: diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index f813ca9dec53..85a8b96e39a6 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -324,7 +324,7 @@ generic_rndis_bind(struct usbnet *dev, struct usb_interface *intf, int flags) * For RX we handle drivers that zero-pad to end-of-packet. * Don't let userspace change these settings. * - * NOTE: there still seems to be wierdness here, as if we need + * NOTE: there still seems to be weirdness here, as if we need * to do some more things to make sure WinCE targets accept this. * They default to jumbograms of 8KB or 16KB, which is absurd * for such low data rates and which is also more than Linux diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index ecf62849f4c1..470e1c1e6353 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -74,6 +74,23 @@ MODULE_PARM_DESC (msg_level, "Override default message level"); /*-------------------------------------------------------------------------*/ +static const char * const usbnet_event_names[] = { + [EVENT_TX_HALT] = "EVENT_TX_HALT", + [EVENT_RX_HALT] = "EVENT_RX_HALT", + [EVENT_RX_MEMORY] = "EVENT_RX_MEMORY", + [EVENT_STS_SPLIT] = "EVENT_STS_SPLIT", + [EVENT_LINK_RESET] = "EVENT_LINK_RESET", + [EVENT_RX_PAUSED] = "EVENT_RX_PAUSED", + [EVENT_DEV_ASLEEP] = "EVENT_DEV_ASLEEP", + [EVENT_DEV_OPEN] = "EVENT_DEV_OPEN", + [EVENT_DEVICE_REPORT_IDLE] = "EVENT_DEVICE_REPORT_IDLE", + [EVENT_NO_RUNTIME_PM] = "EVENT_NO_RUNTIME_PM", + [EVENT_RX_KILL] = "EVENT_RX_KILL", + [EVENT_LINK_CHANGE] = "EVENT_LINK_CHANGE", + [EVENT_SET_RX_MODE] = "EVENT_SET_RX_MODE", + [EVENT_NO_IP_ALIGN] = "EVENT_NO_IP_ALIGN", +}; + /* handles CDC Ethernet and many other network "bulk data" interfaces */ int usbnet_get_endpoints(struct usbnet *dev, struct usb_interface *intf) { @@ -452,9 +469,9 @@ void usbnet_defer_kevent (struct usbnet *dev, int work) { set_bit (work, &dev->flags); if (!schedule_work (&dev->kevent)) - netdev_dbg(dev->net, "kevent %d may have been dropped\n", work); + netdev_dbg(dev->net, "kevent %s may have been dropped\n", usbnet_event_names[work]); else - netdev_dbg(dev->net, "kevent %d scheduled\n", work); + netdev_dbg(dev->net, "kevent %s scheduled\n", usbnet_event_names[work]); } EXPORT_SYMBOL_GPL(usbnet_defer_kevent); @@ -1597,6 +1614,9 @@ void usbnet_disconnect (struct usb_interface *intf) xdev->bus->bus_name, xdev->devpath, dev->driver_info->description); + if (dev->driver_info->unbind) + dev->driver_info->unbind(dev, intf); + net = dev->net; unregister_netdev (net); @@ -1604,9 +1624,6 @@ void usbnet_disconnect (struct usb_interface *intf) usb_scuttle_anchored_urbs(&dev->deferred); - if (dev->driver_info->unbind) - dev->driver_info->unbind (dev, intf); - usb_kill_urb(dev->interrupt); usb_free_urb(dev->interrupt); kfree(dev->padding_pkt); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d1ee546c15e3..f9e2d0114f7a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -380,7 +380,7 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, struct page *page, unsigned int offset, unsigned int len, unsigned int truesize, bool hdr_valid, unsigned int metasize, - unsigned int headroom) + bool whole_page) { struct sk_buff *skb; struct virtio_net_hdr_mrg_rxbuf *hdr; @@ -398,16 +398,28 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, else hdr_padded_len = sizeof(struct padded_vnet_hdr); - /* If headroom is not 0, there is an offset between the beginning of the + /* If whole_page, there is an offset between the beginning of the * data and the allocated space, otherwise the data and the allocated * space are aligned. * * Buffers with headroom use PAGE_SIZE as alloc size, see * add_recvbuf_mergeable() + get_mergeable_buf_len() */ - truesize = headroom ? PAGE_SIZE : truesize; - tailroom = truesize - len - headroom - (hdr_padded_len - hdr_len); - buf = p - headroom; + if (whole_page) { + /* Buffers with whole_page use PAGE_SIZE as alloc size, + * see add_recvbuf_mergeable() + get_mergeable_buf_len() + */ + truesize = PAGE_SIZE; + + /* page maybe head page, so we should get the buf by p, not the + * page + */ + tailroom = truesize - len - offset_in_page(p); + buf = (char *)((unsigned long)p & PAGE_MASK); + } else { + tailroom = truesize - len; + buf = p; + } len -= hdr_len; offset += hdr_padded_len; @@ -721,6 +733,12 @@ static struct sk_buff *receive_small(struct net_device *dev, len -= vi->hdr_len; stats->bytes += len; + if (unlikely(len > GOOD_PACKET_LEN)) { + pr_debug("%s: rx error: len %u exceeds max size %d\n", + dev->name, len, GOOD_PACKET_LEN); + dev->stats.rx_length_errors++; + goto err_len; + } rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { @@ -824,6 +842,7 @@ err: err_xdp: rcu_read_unlock(); stats->xdp_drops++; +err_len: stats->drops++; put_page(page); xdp_xmit: @@ -877,6 +896,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, head_skb = NULL; stats->bytes += len - vi->hdr_len; + if (unlikely(len > truesize)) { + pr_debug("%s: rx error: len %u exceeds truesize %lu\n", + dev->name, len, (unsigned long)ctx); + dev->stats.rx_length_errors++; + goto err_skb; + } rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { @@ -953,8 +978,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, put_page(page); head_skb = page_to_skb(vi, rq, xdp_page, offset, len, PAGE_SIZE, false, - metasize, - VIRTIO_XDP_HEADROOM); + metasize, true); return head_skb; } break; @@ -1004,15 +1028,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, } rcu_read_unlock(); - if (unlikely(len > truesize)) { - pr_debug("%s: rx error: len %u exceeds truesize %lu\n", - dev->name, len, (unsigned long)ctx); - dev->stats.rx_length_errors++; - goto err_skb; - } - head_skb = page_to_skb(vi, rq, page, offset, len, truesize, !xdp_prog, - metasize, headroom); + metasize, !!headroom); curr_skb = head_skb; if (unlikely(!curr_skb)) @@ -1619,7 +1636,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) if (virtio_net_hdr_from_skb(skb, &hdr->hdr, virtio_is_little_endian(vi->vdev), false, 0)) - BUG(); + return -EPROTO; if (vi->mergeable_rx_bufs) hdr->num_buffers = 0; @@ -2833,8 +2850,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi) ctx[rxq2vq(i)] = true; } - ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks, - names, ctx, NULL); + ret = virtio_find_vqs_ctx(vi->vdev, total_vqs, vqs, callbacks, + names, ctx, NULL); if (ret) goto err_find; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 28a6c4cfe9b8..2b1b944d4b28 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -274,7 +274,7 @@ vrf_map_register_dev(struct net_device *dev, struct netlink_ext_ack *extack) int res; /* we pre-allocate elements used in the spin-locked section (so that we - * keep the spinlock as short as possibile). + * keep the spinlock as short as possible). */ new_me = vrf_map_elem_alloc(GFP_KERNEL); if (!new_me) @@ -1366,22 +1366,22 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, int orig_iif = skb->skb_iif; bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr); bool is_ndisc = ipv6_ndisc_frame(skb); - bool is_ll_src; /* loopback, multicast & non-ND link-local traffic; do not push through * packet taps again. Reset pkt_type for upper layers to process skb. - * for packets with lladdr src, however, skip so that the dst can be - * determine at input using original ifindex in the case that daddr - * needs strict + * For strict packets with a source LLA, determine the dst using the + * original ifindex. */ - is_ll_src = ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL; - if (skb->pkt_type == PACKET_LOOPBACK || - (need_strict && !is_ndisc && !is_ll_src)) { + if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) { skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IP6CB(skb)->flags |= IP6SKB_L3SLAVE; + if (skb->pkt_type == PACKET_LOOPBACK) skb->pkt_type = PACKET_HOST; + else if (ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL) + vrf_ip6_input_dst(skb, vrf_dev, orig_iif); + goto out; } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 02a14f1b938a..5a8df5a195cb 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2164,6 +2164,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) struct neighbour *n; struct nd_msg *msg; + rcu_read_lock(); in6_dev = __in6_dev_get(dev); if (!in6_dev) goto out; @@ -2215,6 +2216,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) } out: + rcu_read_unlock(); consume_skb(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig index 83c9481995dd..473df2505c8e 100644 --- a/drivers/net/wan/Kconfig +++ b/drivers/net/wan/Kconfig @@ -49,7 +49,7 @@ config COSA network device. You will need user-space utilities COSA or SRP boards for downloading - the firmware to the cards and to set them up. Look at the + the firmware to the cards and to set them up. Look at the for more information. You can also read the comment at the top of the for details about the cards and the driver itself. @@ -108,7 +108,7 @@ config HDLC Generic HDLC driver currently supports raw HDLC, Cisco HDLC, Frame Relay, synchronous Point-to-Point Protocol (PPP) and X.25. - To compile this driver as a module, choose M here: the + To compile this driver as a module, choose M here: the module will be called hdlc. If unsure, say N. diff --git a/drivers/net/wan/c101.c b/drivers/net/wan/c101.c index c354a5143e99..059c2f7133be 100644 --- a/drivers/net/wan/c101.c +++ b/drivers/net/wan/c101.c @@ -28,9 +28,8 @@ #include "hd64570.h" - -static const char* version = "Moxa C101 driver version: 1.15"; -static const char* devname = "C101"; +static const char *version = "Moxa C101 driver version: 1.15"; +static const char *devname = "C101"; #undef DEBUG_PKT #define DEBUG_RINGS @@ -51,7 +50,6 @@ static const char* devname = "C101"; static char *hw; /* pointer to hw=xxx command line string */ - typedef struct card_s { struct net_device *dev; spinlock_t lock; /* TX lock */ @@ -72,14 +70,13 @@ typedef struct card_s { u8 page; struct card_s *next_card; -}card_t; +} card_t; typedef card_t port_t; static card_t *first_card; static card_t **new_card = &first_card; - #define sca_in(reg, card) readb((card)->win0base + C101_SCA + (reg)) #define sca_out(value, reg, card) writeb(value, (card)->win0base + C101_SCA + (reg)) #define sca_inw(reg, card) readw((card)->win0base + C101_SCA + (reg)) @@ -87,19 +84,18 @@ static card_t **new_card = &first_card; /* EDA address register must be set in EDAL, EDAH order - 8 bit ISA bus */ #define sca_outw(value, reg, card) do { \ writeb(value & 0xFF, (card)->win0base + C101_SCA + (reg)); \ - writeb((value >> 8 ) & 0xFF, (card)->win0base + C101_SCA + (reg + 1));\ -} while(0) + writeb((value >> 8) & 0xFF, (card)->win0base + C101_SCA + (reg + 1));\ +} while (0) #define port_to_card(port) (port) #define log_node(port) (0) #define phy_node(port) (0) #define winsize(card) (C101_WINDOW_SIZE) #define win0base(card) ((card)->win0base) -#define winbase(card) ((card)->win0base + 0x2000) +#define winbase(card) ((card)->win0base + 0x2000) #define get_port(card, port) (card) static void sca_msci_intr(port_t *port); - static inline u8 sca_get_page(card_t *card) { return card->page; @@ -111,10 +107,8 @@ static inline void openwin(card_t *card, u8 page) writeb(page, card->win0base + C101_PAGE); } - #include "hd64570.c" - static inline void set_carrier(port_t *port) { if (!(sca_in(MSCI1_OFFSET + ST3, port) & ST3_DCD)) @@ -123,7 +117,6 @@ static inline void set_carrier(port_t *port) netif_carrier_off(port_to_dev(port)); } - static void sca_msci_intr(port_t *port) { u8 stat = sca_in(MSCI0_OFFSET + ST1, port); /* read MSCI ST1 status */ @@ -145,13 +138,12 @@ static void sca_msci_intr(port_t *port) set_carrier(port); } - static void c101_set_iface(port_t *port) { u8 rxs = port->rxs & CLK_BRG_MASK; u8 txs = port->txs & CLK_BRG_MASK; - switch(port->settings.clock_type) { + switch (port->settings.clock_type) { case CLOCK_INT: rxs |= CLK_BRG_RX; /* TX clock */ txs |= CLK_RXCLK_TX; /* BRG output */ @@ -179,7 +171,6 @@ static void c101_set_iface(port_t *port) sca_set_port(port); } - static int c101_open(struct net_device *dev) { port_t *port = dev_to_port(dev); @@ -206,7 +197,6 @@ static int c101_open(struct net_device *dev) return 0; } - static int c101_close(struct net_device *dev) { port_t *port = dev_to_port(dev); @@ -218,7 +208,6 @@ static int c101_close(struct net_device *dev) return 0; } - static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { const size_t size = sizeof(sync_serial_settings); @@ -240,7 +229,7 @@ static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (cmd != SIOCWANDEV) return hdlc_ioctl(dev, ifr, cmd); - switch(ifr->ifr_settings.type) { + switch (ifr->ifr_settings.type) { case IF_GET_IFACE: ifr->ifr_settings.type = IF_IFACE_SYNC_SERIAL; if (ifr->ifr_settings.size < size) { @@ -252,7 +241,7 @@ static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return 0; case IF_IFACE_SYNC_SERIAL: - if(!capable(CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&new_line, line, size)) @@ -276,8 +265,6 @@ static int c101_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } } - - static void c101_destroy_card(card_t *card) { readb(card->win0base + C101_PAGE); /* Resets SCA? */ @@ -309,18 +296,18 @@ static int __init c101_run(unsigned long irq, unsigned long winbase) card_t *card; int result; - if (irq<3 || irq>15 || irq == 6) /* FIXME */ { + if (irq < 3 || irq > 15 || irq == 6) /* FIXME */ { pr_err("invalid IRQ value\n"); return -ENODEV; } - if (winbase < 0xC0000 || winbase > 0xDFFFF || (winbase & 0x3FFF) !=0) { + if (winbase < 0xC0000 || winbase > 0xDFFFF || (winbase & 0x3FFF) != 0) { pr_err("invalid RAM value\n"); return -ENODEV; } card = kzalloc(sizeof(card_t), GFP_KERNEL); - if (card == NULL) + if (!card) return -ENOBUFS; card->dev = alloc_hdlcdev(card); @@ -392,11 +379,9 @@ static int __init c101_run(unsigned long irq, unsigned long winbase) return 0; } - - static int __init c101_init(void) { - if (hw == NULL) { + if (!hw) { #ifdef MODULE pr_info("no card initialized\n"); #endif @@ -419,26 +404,25 @@ static int __init c101_init(void) if (*hw == '\x0') return first_card ? 0 : -EINVAL; - }while(*hw++ == ':'); + } while (*hw++ == ':'); pr_err("invalid hardware parameters\n"); return first_card ? 0 : -EINVAL; } - static void __exit c101_cleanup(void) { card_t *card = first_card; while (card) { card_t *ptr = card; + card = card->next_card; unregister_hdlc_device(port_to_dev(ptr)); c101_destroy_card(ptr); } } - module_init(c101_init); module_exit(c101_cleanup); diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index 2369ca250cd6..43caab0b7dee 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -1,13 +1,11 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* $Id: cosa.c,v 1.31 2000/03/08 17:47:16 kas Exp $ */ -/* - * Copyright (C) 1995-1997 Jan "Yenya" Kasprzak +/* Copyright (C) 1995-1997 Jan "Yenya" Kasprzak * Generic HDLC port Copyright (C) 2008 Krzysztof Halasa */ -/* - * The driver for the SRP and COSA synchronous serial cards. +/* The driver for the SRP and COSA synchronous serial cards. * * HARDWARE INFO * @@ -90,7 +88,7 @@ #define COSA_MAX_ID_STRING 128 /* Maximum length of the channel name */ -#define COSA_MAX_NAME (sizeof("cosaXXXcXXX")+1) +#define COSA_MAX_NAME (sizeof("cosaXXXcXXX") + 1) /* Per-channel data structure */ @@ -124,9 +122,9 @@ struct channel_data { }; /* cosa->firmware_status bits */ -#define COSA_FW_RESET (1<<0) /* Is the ROM monitor active? */ -#define COSA_FW_DOWNLOAD (1<<1) /* Is the microcode downloaded? */ -#define COSA_FW_START (1<<2) /* Is the microcode running? */ +#define COSA_FW_RESET BIT(0) /* Is the ROM monitor active? */ +#define COSA_FW_DOWNLOAD BIT(1) /* Is the microcode downloaded? */ +#define COSA_FW_START BIT(2) /* Is the microcode running? */ struct cosa_data { int num; /* Card number */ @@ -152,28 +150,25 @@ struct cosa_data { char *type; /* card type */ }; -/* - * Define this if you want all the possible ports to be autoprobed. +/* Define this if you want all the possible ports to be autoprobed. * It is here but it probably is not a good idea to use this. */ -/* #define COSA_ISA_AUTOPROBE 1 */ +/* #define COSA_ISA_AUTOPROBE 1*/ -/* - * Character device major number. 117 was allocated for us. +/* Character device major number. 117 was allocated for us. * The value of 0 means to allocate a first free one. */ static DEFINE_MUTEX(cosa_chardev_mutex); static int cosa_major = 117; -/* - * Encoding of the minor numbers: +/* Encoding of the minor numbers: * The lowest CARD_MINOR_BITS bits means the channel on the single card, * the highest bits means the card number. */ #define CARD_MINOR_BITS 4 /* How many bits in minor number are reserved - * for the single card */ -/* - * The following depends on CARD_MINOR_BITS. Unfortunately, the "MODULE_STRING" + * for the single card + */ +/* The following depends on CARD_MINOR_BITS. Unfortunately, the "MODULE_STRING" * macro doesn't like anything other than the raw number as an argument :-( */ #define MAX_CARDS 16 @@ -184,8 +179,7 @@ static int cosa_major = 117; #define DRIVER_TXMAP_SHIFT 2 #define DRIVER_TXMAP_MASK 0x0c /* FIXME: 0xfc for 8-channel version */ -/* - * for cosa->rxtx - indicates whether either transmit or receive is +/* for cosa->rxtx - indicates whether either transmit or receive is * in progress. These values are mean number of the bit. */ #define TXBIT 0 @@ -198,22 +192,22 @@ static int cosa_major = 117; #undef DEBUG_IRQS //1 /* Print the message when the IRQ is received */ #undef DEBUG_IO //1 /* Dump the I/O traffic */ -#define TX_TIMEOUT (5*HZ) +#define TX_TIMEOUT (5 * HZ) /* Maybe the following should be allocated dynamically */ static struct cosa_data cosa_cards[MAX_CARDS]; static int nr_cards; #ifdef COSA_ISA_AUTOPROBE -static int io[MAX_CARDS+1] = { 0x220, 0x228, 0x210, 0x218, 0, }; +static int io[MAX_CARDS + 1] = {0x220, 0x228, 0x210, 0x218, 0,}; /* NOTE: DMA is not autoprobed!!! */ -static int dma[MAX_CARDS+1] = { 1, 7, 1, 7, 1, 7, 1, 7, 0, }; +static int dma[MAX_CARDS + 1] = {1, 7, 1, 7, 1, 7, 1, 7, 0,}; #else -static int io[MAX_CARDS+1]; -static int dma[MAX_CARDS+1]; +static int io[MAX_CARDS + 1]; +static int dma[MAX_CARDS + 1]; #endif /* IRQ can be safely autoprobed */ -static int irq[MAX_CARDS+1] = { -1, -1, -1, -1, -1, -1, 0, }; +static int irq[MAX_CARDS + 1] = {-1, -1, -1, -1, -1, -1, 0,}; /* for class stuff*/ static struct class *cosa_class; @@ -244,14 +238,14 @@ MODULE_LICENSE("GPL"); #define cosa_inw inw #endif -#define is_8bit(cosa) (!(cosa->datareg & 0x08)) +#define is_8bit(cosa) (!((cosa)->datareg & 0x08)) -#define cosa_getstatus(cosa) (cosa_inb(cosa->statusreg)) -#define cosa_putstatus(cosa, stat) (cosa_outb(stat, cosa->statusreg)) -#define cosa_getdata16(cosa) (cosa_inw(cosa->datareg)) -#define cosa_getdata8(cosa) (cosa_inb(cosa->datareg)) -#define cosa_putdata16(cosa, dt) (cosa_outw(dt, cosa->datareg)) -#define cosa_putdata8(cosa, dt) (cosa_outb(dt, cosa->datareg)) +#define cosa_getstatus(cosa) (cosa_inb((cosa)->statusreg)) +#define cosa_putstatus(cosa, stat) (cosa_outb(stat, (cosa)->statusreg)) +#define cosa_getdata16(cosa) (cosa_inw((cosa)->datareg)) +#define cosa_getdata8(cosa) (cosa_inb((cosa)->datareg)) +#define cosa_putdata16(cosa, dt) (cosa_outw(dt, (cosa)->datareg)) +#define cosa_putdata8(cosa, dt) (cosa_outb(dt, (cosa)->datareg)) /* Initialization stuff */ static int cosa_probe(int ioaddr, int irq, int dma); @@ -280,14 +274,14 @@ static char *chrdev_setup_rx(struct channel_data *channel, int size); static int chrdev_rx_done(struct channel_data *channel); static int chrdev_tx_done(struct channel_data *channel, int size); static ssize_t cosa_read(struct file *file, - char __user *buf, size_t count, loff_t *ppos); + char __user *buf, size_t count, loff_t *ppos); static ssize_t cosa_write(struct file *file, - const char __user *buf, size_t count, loff_t *ppos); + const char __user *buf, size_t count, loff_t *ppos); static unsigned int cosa_poll(struct file *file, poll_table *poll); static int cosa_open(struct inode *inode, struct file *file); static int cosa_release(struct inode *inode, struct file *file); static long cosa_chardev_ioctl(struct file *file, unsigned int cmd, - unsigned long arg); + unsigned long arg); #ifdef COSA_FASYNC_WORKING static int cosa_fasync(struct inode *inode, struct file *file, int on); #endif @@ -337,7 +331,7 @@ static void debug_status_in(struct cosa_data *cosa, int status); static void debug_status_out(struct cosa_data *cosa, int status); #endif -static inline struct channel_data* dev_to_chan(struct net_device *dev) +static inline struct channel_data *dev_to_chan(struct net_device *dev) { return (struct channel_data *)dev_to_hdlc(dev)->priv; } @@ -355,15 +349,16 @@ static int __init cosa_init(void) goto out; } } else { - if (!(cosa_major=register_chrdev(0, "cosa", &cosa_fops))) { + cosa_major = register_chrdev(0, "cosa", &cosa_fops); + if (!cosa_major) { pr_warn("unable to register chardev\n"); err = -EIO; goto out; } } - for (i=0; i 0x3ff || base & 0x7) { pr_info("invalid I/O address 0x%x\n", base); return -1; @@ -448,8 +444,9 @@ static int cosa_probe(int base, int irq, int dma) pr_info("invalid DMA %d\n", dma); return -1; } - /* and finally, on 16-bit COSA DMA should be 4-7 and - * I/O base should not be multiple of 0x10 */ + /* and finally, on 16-bit COSA DMA should be 4-7 and + * I/O base should not be multiple of 0x10 + */ if (((base & 0x8) && dma < 4) || (!(base & 0x8) && dma > 3)) { pr_info("8/16 bit base and DMA mismatch (base=0x%x, dma=%d)\n", base, dma); @@ -458,12 +455,12 @@ static int cosa_probe(int base, int irq, int dma) cosa->dma = dma; cosa->datareg = base; - cosa->statusreg = is_8bit(cosa)?base+1:base+2; + cosa->statusreg = is_8bit(cosa) ? base + 1 : base + 2; spin_lock_init(&cosa->lock); - if (!request_region(base, is_8bit(cosa)?2:4,"cosa")) + if (!request_region(base, is_8bit(cosa) ? 2 : 4, "cosa")) return -1; - + if (cosa_reset_and_read_id(cosa, cosa->id_string) < 0) { printk(KERN_DEBUG "probe at 0x%x failed.\n", base); err = -1; @@ -471,11 +468,11 @@ static int cosa_probe(int base, int irq, int dma) } /* Test the validity of identification string */ - if (!strncmp(cosa->id_string, "SRP", 3)) + if (!strncmp(cosa->id_string, "SRP", 3)) { cosa->type = "srp"; - else if (!strncmp(cosa->id_string, "COSA", 4)) - cosa->type = is_8bit(cosa)? "cosa8": "cosa16"; - else { + } else if (!strncmp(cosa->id_string, "COSA", 4)) { + cosa->type = is_8bit(cosa) ? "cosa8" : "cosa16"; + } else { /* Print a warning only if we are not autoprobing */ #ifndef COSA_ISA_AUTOPROBE pr_info("valid signature not found at 0x%x\n", base); @@ -483,9 +480,9 @@ static int cosa_probe(int base, int irq, int dma) err = -1; goto err_out; } - /* Update the name of the region now we know the type of card */ - release_region(base, is_8bit(cosa)?2:4); - if (!request_region(base, is_8bit(cosa)?2:4, cosa->type)) { + /* Update the name of the region now we know the type of card */ + release_region(base, is_8bit(cosa) ? 2 : 4); + if (!request_region(base, is_8bit(cosa) ? 2 : 4, cosa->type)) { printk(KERN_DEBUG "changing name at 0x%x failed.\n", base); return -1; } @@ -495,8 +492,7 @@ static int cosa_probe(int base, int irq, int dma) unsigned long irqs; /* pr_info("IRQ autoprobe\n"); */ irqs = probe_irq_on(); - /* - * Enable interrupt on tx buffer empty (it sure is) + /* Enable interrupt on tx buffer empty (it sure is) * really sure ? * FIXME: When this code is not used as module, we should * probably call udelay() instead of the interruptible sleep. @@ -536,8 +532,8 @@ static int cosa_probe(int base, int irq, int dma) err = -1; goto err_out1; } - - cosa->bouncebuf = kmalloc(COSA_MTU, GFP_KERNEL|GFP_DMA); + + cosa->bouncebuf = kmalloc(COSA_MTU, GFP_KERNEL | GFP_DMA); if (!cosa->bouncebuf) { err = -ENOMEM; goto err_out2; @@ -563,7 +559,8 @@ static int cosa_probe(int base, int irq, int dma) sema_init(&chan->wsem, 1); /* Register the network interface */ - if (!(chan->netdev = alloc_hdlcdev(chan))) { + chan->netdev = alloc_hdlcdev(chan); + if (!chan->netdev) { pr_warn("%s: alloc_hdlcdev failed\n", chan->name); err = -ENOMEM; goto err_hdlcdev; @@ -603,12 +600,11 @@ err_out2: err_out1: free_irq(cosa->irq, cosa); err_out: - release_region(cosa->datareg,is_8bit(cosa)?2:4); + release_region(cosa->datareg, is_8bit(cosa) ? 2 : 4); pr_notice("cosa%d: allocating resources failed\n", cosa->num); return err; } - /*---------- network device ---------- */ static int cosa_net_attach(struct net_device *dev, unsigned short encoding, @@ -659,7 +655,7 @@ static int cosa_net_open(struct net_device *dev) } static netdev_tx_t cosa_net_tx(struct sk_buff *skb, - struct net_device *dev) + struct net_device *dev) { struct channel_data *chan = dev_to_chan(dev); @@ -714,13 +710,12 @@ static int cosa_net_close(struct net_device *dev) static char *cosa_net_setup_rx(struct channel_data *chan, int size) { - /* - * We can safely fall back to non-dma-able memory, because we have + /* We can safely fall back to non-dma-able memory, because we have * the cosa->bouncebuf pre-allocated. */ kfree_skb(chan->rx_skb); chan->rx_skb = dev_alloc_skb(size); - if (chan->rx_skb == NULL) { + if (!chan->rx_skb) { pr_notice("%s: Memory squeeze, dropping packet\n", chan->name); chan->netdev->stats.rx_dropped++; return NULL; @@ -767,7 +762,7 @@ static int cosa_net_tx_done(struct channel_data *chan, int size) /*---------- Character device ---------- */ static ssize_t cosa_read(struct file *file, - char __user *buf, size_t count, loff_t *ppos) + char __user *buf, size_t count, loff_t *ppos) { DECLARE_WAITQUEUE(wait, current); unsigned long flags; @@ -782,9 +777,9 @@ static ssize_t cosa_read(struct file *file, } if (mutex_lock_interruptible(&chan->rlock)) return -ERESTARTSYS; - - chan->rxdata = kmalloc(COSA_MTU, GFP_DMA|GFP_KERNEL); - if (chan->rxdata == NULL) { + + chan->rxdata = kmalloc(COSA_MTU, GFP_DMA | GFP_KERNEL); + if (!chan->rxdata) { mutex_unlock(&chan->rlock); return -ENOMEM; } @@ -840,9 +835,8 @@ static int chrdev_rx_done(struct channel_data *chan) return 1; } - static ssize_t cosa_write(struct file *file, - const char __user *buf, size_t count, loff_t *ppos) + const char __user *buf, size_t count, loff_t *ppos) { DECLARE_WAITQUEUE(wait, current); struct channel_data *chan = file->private_data; @@ -860,10 +854,10 @@ static ssize_t cosa_write(struct file *file, if (count > COSA_MTU) count = COSA_MTU; - + /* Allocate the buffer */ - kbuf = kmalloc(count, GFP_KERNEL|GFP_DMA); - if (kbuf == NULL) { + kbuf = kmalloc(count, GFP_KERNEL | GFP_DMA); + if (!kbuf) { up(&chan->wsem); return -ENOMEM; } @@ -872,7 +866,7 @@ static ssize_t cosa_write(struct file *file, kfree(kbuf); return -EFAULT; } - chan->tx_status=0; + chan->tx_status = 0; cosa_start_tx(chan, kbuf, count); spin_lock_irqsave(&cosa->lock, flags); @@ -927,20 +921,20 @@ static int cosa_open(struct inode *inode, struct file *file) int ret = 0; mutex_lock(&cosa_chardev_mutex); - if ((n=iminor(file_inode(file))>>CARD_MINOR_BITS) - >= nr_cards) { + n = iminor(file_inode(file)) >> CARD_MINOR_BITS; + if (n >= nr_cards) { ret = -ENODEV; goto out; } - cosa = cosa_cards+n; + cosa = cosa_cards + n; - if ((n=iminor(file_inode(file)) - & ((1<= cosa->nchannels) { + n = iminor(file_inode(file)) & ((1 << CARD_MINOR_BITS) - 1); + if (n >= cosa->nchannels) { ret = -ENODEV; goto out; } chan = cosa->chan + n; - + file->private_data = chan; spin_lock_irqsave(&cosa->lock, flags); @@ -982,26 +976,25 @@ static struct fasync_struct *fasync[256] = { NULL, }; /* To be done ... */ static int cosa_fasync(struct inode *inode, struct file *file, int on) { - int port = iminor(inode); + int port = iminor(inode); return fasync_helper(inode, file, on, &fasync[port]); } #endif - /* ---------- Ioctls ---------- */ -/* - * Ioctl subroutines can safely be made inline, because they are called +/* Ioctl subroutines can safely be made inline, because they are called * only from cosa_ioctl(). */ static inline int cosa_reset(struct cosa_data *cosa) { char idstring[COSA_MAX_ID_STRING]; + if (cosa->usage > 1) pr_info("cosa%d: WARNING: reset requested with cosa->usage > 1 (%d). Odd things may happen.\n", cosa->num, cosa->usage); - cosa->firmware_status &= ~(COSA_FW_RESET|COSA_FW_START); + cosa->firmware_status &= ~(COSA_FW_RESET | COSA_FW_START); if (cosa_reset_and_read_id(cosa, idstring) < 0) { pr_notice("cosa%d: reset failed\n", cosa->num); return -EIO; @@ -1025,7 +1018,7 @@ static inline int cosa_download(struct cosa_data *cosa, void __user *arg) cosa->name, cosa->firmware_status); return -EPERM; } - + if (copy_from_user(&d, arg, sizeof(d))) return -EFAULT; @@ -1034,9 +1027,8 @@ static inline int cosa_download(struct cosa_data *cosa, void __user *arg) if (d.len < 0 || d.len > COSA_MAX_FIRMWARE_SIZE) return -EINVAL; - /* If something fails, force the user to reset the card */ - cosa->firmware_status &= ~(COSA_FW_RESET|COSA_FW_DOWNLOAD); + cosa->firmware_status &= ~(COSA_FW_RESET | COSA_FW_DOWNLOAD); i = download(cosa, d.code, d.len, d.addr); if (i < 0) { @@ -1046,7 +1038,7 @@ static inline int cosa_download(struct cosa_data *cosa, void __user *arg) } pr_info("cosa%d: downloading microcode - 0x%04x bytes at 0x%04x\n", cosa->num, d.len, d.addr); - cosa->firmware_status |= COSA_FW_RESET|COSA_FW_DOWNLOAD; + cosa->firmware_status |= COSA_FW_RESET | COSA_FW_DOWNLOAD; return 0; } @@ -1091,14 +1083,15 @@ static inline int cosa_start(struct cosa_data *cosa, int address) pr_info("cosa%d: WARNING: start microcode requested with cosa->usage > 1 (%d). Odd things may happen.\n", cosa->num, cosa->usage); - if ((cosa->firmware_status & (COSA_FW_RESET|COSA_FW_DOWNLOAD)) - != (COSA_FW_RESET|COSA_FW_DOWNLOAD)) { + if ((cosa->firmware_status & (COSA_FW_RESET | COSA_FW_DOWNLOAD)) + != (COSA_FW_RESET | COSA_FW_DOWNLOAD)) { pr_notice("%s: download the microcode and/or reset the card first (status %d)\n", cosa->name, cosa->firmware_status); return -EPERM; } cosa->firmware_status &= ~COSA_FW_RESET; - if ((i=startmicrocode(cosa, address)) < 0) { + i = startmicrocode(cosa, address); + if (i < 0) { pr_notice("cosa%d: start microcode at 0x%04x failed: %d\n", cosa->num, address, i); return -EIO; @@ -1108,11 +1101,12 @@ static inline int cosa_start(struct cosa_data *cosa, int address) cosa->firmware_status |= COSA_FW_START; return 0; } - + /* Buffer of size at least COSA_MAX_ID_STRING is expected */ static inline int cosa_getidstr(struct cosa_data *cosa, char __user *string) { - int l = strlen(cosa->id_string)+1; + int l = strlen(cosa->id_string) + 1; + if (copy_to_user(string, cosa->id_string, l)) return -EFAULT; return l; @@ -1121,16 +1115,19 @@ static inline int cosa_getidstr(struct cosa_data *cosa, char __user *string) /* Buffer of size at least COSA_MAX_ID_STRING is expected */ static inline int cosa_gettype(struct cosa_data *cosa, char __user *string) { - int l = strlen(cosa->type)+1; + int l = strlen(cosa->type) + 1; + if (copy_to_user(string, cosa->type, l)) return -EFAULT; return l; } static int cosa_ioctl_common(struct cosa_data *cosa, - struct channel_data *channel, unsigned int cmd, unsigned long arg) + struct channel_data *channel, unsigned int cmd, + unsigned long arg) { void __user *argp = (void __user *)arg; + switch (cmd) { case COSAIORSET: /* Reset the device */ if (!capable(CAP_NET_ADMIN)) @@ -1143,7 +1140,7 @@ static int cosa_ioctl_common(struct cosa_data *cosa, case COSAIODOWNLD: /* Download the firmware */ if (!capable(CAP_SYS_RAWIO)) return -EACCES; - + return cosa_download(cosa, argp); case COSAIORMEM: if (!capable(CAP_SYS_RAWIO)) @@ -1176,6 +1173,7 @@ static int cosa_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { int rv; struct channel_data *chan = dev_to_chan(dev); + rv = cosa_ioctl_common(chan->cosa, chan, cmd, (unsigned long)ifr->ifr_data); if (rv != -ENOIOCTLCMD) @@ -1184,7 +1182,7 @@ static int cosa_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } static long cosa_chardev_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) + unsigned long arg) { struct channel_data *channel = file->private_data; struct cosa_data *cosa; @@ -1197,11 +1195,9 @@ static long cosa_chardev_ioctl(struct file *file, unsigned int cmd, return ret; } - /*---------- HW layer interface ---------- */ -/* - * The higher layer can bind itself to the HW layer by setting the callbacks +/* The higher layer can bind itself to the HW layer by setting the callbacks * in the channel_data structure and by using these routines. */ static void cosa_enable_rx(struct channel_data *chan) @@ -1220,8 +1216,7 @@ static void cosa_disable_rx(struct channel_data *chan) put_driver_status(cosa); } -/* - * FIXME: This routine probably should check for cosa_start_tx() called when +/* FIXME: This routine probably should check for cosa_start_tx() called when * the previous transmit is still unfinished. In this case the non-zero * return value should indicate to the caller that the queuing(sp?) up * the transmit has failed. @@ -1235,7 +1230,7 @@ static int cosa_start_tx(struct channel_data *chan, char *buf, int len) pr_info("cosa%dc%d: starting tx(0x%x)", chan->cosa->num, chan->num, len); - for (i=0; irxbitmap ? DRIVER_RX_READY : 0) | (cosa->txbitmap ? DRIVER_TX_READY : 0) - | (cosa->txbitmap? ~(cosa->txbitmap<txbitmap ? ~(cosa->txbitmap << DRIVER_TXMAP_SHIFT) + & DRIVER_TXMAP_MASK : 0); if (!cosa->rxtx) { - if (cosa->rxbitmap|cosa->txbitmap) { + if (cosa->rxbitmap | cosa->txbitmap) { if (!cosa->enabled) { cosa_putstatus(cosa, SR_RX_INT_ENA); #ifdef DEBUG_IO @@ -1294,10 +1289,10 @@ static void put_driver_status_nolock(struct cosa_data *cosa) status = (cosa->rxbitmap ? DRIVER_RX_READY : 0) | (cosa->txbitmap ? DRIVER_TX_READY : 0) - | (cosa->txbitmap? ~(cosa->txbitmap<txbitmap ? ~(cosa->txbitmap << DRIVER_TXMAP_SHIFT) + & DRIVER_TXMAP_MASK : 0); - if (cosa->rxbitmap|cosa->txbitmap) { + if (cosa->rxbitmap | cosa->txbitmap) { cosa_putstatus(cosa, SR_RX_INT_ENA); #ifdef DEBUG_IO debug_status_out(cosa, SR_RX_INT_ENA); @@ -1316,8 +1311,7 @@ static void put_driver_status_nolock(struct cosa_data *cosa) #endif } -/* - * The "kickme" function: When the DMA times out, this is called to +/* The "kickme" function: When the DMA times out, this is called to * clean up the driver status. * FIXME: Preliminary support, the interface is probably wrong. */ @@ -1344,7 +1338,7 @@ static void cosa_kick(struct cosa_data *cosa) udelay(100); cosa_putstatus(cosa, 0); udelay(100); - (void) cosa_getdata8(cosa); + (void)cosa_getdata8(cosa); udelay(100); cosa_putdata8(cosa, 0); udelay(100); @@ -1352,8 +1346,7 @@ static void cosa_kick(struct cosa_data *cosa) spin_unlock_irqrestore(&cosa->lock, flags); } -/* - * Check if the whole buffer is DMA-able. It means it is below the 16M of +/* Check if the whole buffer is DMA-able. It means it is below the 16M of * physical memory and doesn't span the 64k boundary. For now it seems * SKB's never do this, but we'll check this anyway. */ @@ -1361,9 +1354,10 @@ static int cosa_dma_able(struct channel_data *chan, char *buf, int len) { static int count; unsigned long b = (unsigned long)buf; - if (b+len >= MAX_DMA_ADDRESS) + + if (b + len >= MAX_DMA_ADDRESS) return 0; - if ((b^ (b+len)) & 0x10000) { + if ((b ^ (b + len)) & 0x10000) { if (count++ < 5) pr_info("%s: packet spanning a 64k boundary\n", chan->name); @@ -1372,11 +1366,9 @@ static int cosa_dma_able(struct channel_data *chan, char *buf, int len) return 1; } - /* ---------- The SRP/COSA ROM monitor functions ---------- */ -/* - * Downloading SRP microcode: say "w" to SRP monitor, it answers by "w=", +/* Downloading SRP microcode: say "w" to SRP monitor, it answers by "w=", * drivers need to say 4-digit hex number meaning start address of the microcode * separated by a single space. Monitor replies by saying " =". Now driver * has to write 4-digit hex number meaning the last byte address ended @@ -1387,18 +1379,27 @@ static int download(struct cosa_data *cosa, const char __user *microcode, int le { int i; - if (put_wait_data(cosa, 'w') == -1) return -1; + if (put_wait_data(cosa, 'w') == -1) + return -1; if ((i=get_wait_data(cosa)) != 'w') { printk("dnld: 0x%04x\n",i); return -2;} - if (get_wait_data(cosa) != '=') return -3; + if (get_wait_data(cosa) != '=') + return -3; - if (puthexnumber(cosa, address) < 0) return -4; - if (put_wait_data(cosa, ' ') == -1) return -10; - if (get_wait_data(cosa) != ' ') return -11; - if (get_wait_data(cosa) != '=') return -12; + if (puthexnumber(cosa, address) < 0) + return -4; + if (put_wait_data(cosa, ' ') == -1) + return -10; + if (get_wait_data(cosa) != ' ') + return -11; + if (get_wait_data(cosa) != '=') + return -12; - if (puthexnumber(cosa, address+length-1) < 0) return -13; - if (put_wait_data(cosa, ' ') == -1) return -18; - if (get_wait_data(cosa) != ' ') return -19; + if (puthexnumber(cosa, address + length - 1) < 0) + return -13; + if (put_wait_data(cosa, ' ') == -1) + return -18; + if (get_wait_data(cosa) != ' ') + return -19; while (length--) { char c; @@ -1413,43 +1414,53 @@ static int download(struct cosa_data *cosa, const char __user *microcode, int le microcode++; } - if (get_wait_data(cosa) != '\r') return -21; - if (get_wait_data(cosa) != '\n') return -22; - if (get_wait_data(cosa) != '.') return -23; + if (get_wait_data(cosa) != '\r') + return -21; + if (get_wait_data(cosa) != '\n') + return -22; + if (get_wait_data(cosa) != '.') + return -23; #if 0 printk(KERN_DEBUG "cosa%d: download completed.\n", cosa->num); #endif return 0; } - -/* - * Starting microcode is done via the "g" command of the SRP monitor. +/* Starting microcode is done via the "g" command of the SRP monitor. * The chat should be the following: "g" "g=" "" * "". */ static int startmicrocode(struct cosa_data *cosa, int address) { - if (put_wait_data(cosa, 'g') == -1) return -1; - if (get_wait_data(cosa) != 'g') return -2; - if (get_wait_data(cosa) != '=') return -3; + if (put_wait_data(cosa, 'g') == -1) + return -1; + if (get_wait_data(cosa) != 'g') + return -2; + if (get_wait_data(cosa) != '=') + return -3; - if (puthexnumber(cosa, address) < 0) return -4; - if (put_wait_data(cosa, '\r') == -1) return -5; - - if (get_wait_data(cosa) != '\r') return -6; - if (get_wait_data(cosa) != '\r') return -7; - if (get_wait_data(cosa) != '\n') return -8; - if (get_wait_data(cosa) != '\r') return -9; - if (get_wait_data(cosa) != '\n') return -10; + if (puthexnumber(cosa, address) < 0) + return -4; + if (put_wait_data(cosa, '\r') == -1) + return -5; + + if (get_wait_data(cosa) != '\r') + return -6; + if (get_wait_data(cosa) != '\r') + return -7; + if (get_wait_data(cosa) != '\n') + return -8; + if (get_wait_data(cosa) != '\r') + return -9; + if (get_wait_data(cosa) != '\n') + return -10; #if 0 printk(KERN_DEBUG "cosa%d: microcode started\n", cosa->num); #endif return 0; } -/* - * Reading memory is done via the "r" command of the SRP monitor. +/* Reading memory is done via the "r" command of the SRP monitor. * The chat is the following "r" "r=" " " " =" " " " " * Then driver can read the data and the conversation is finished * by SRP monitor sending "." (dot at the end). @@ -1459,27 +1470,39 @@ static int startmicrocode(struct cosa_data *cosa, int address) */ static int readmem(struct cosa_data *cosa, char __user *microcode, int length, int address) { - if (put_wait_data(cosa, 'r') == -1) return -1; - if ((get_wait_data(cosa)) != 'r') return -2; - if ((get_wait_data(cosa)) != '=') return -3; + if (put_wait_data(cosa, 'r') == -1) + return -1; + if ((get_wait_data(cosa)) != 'r') + return -2; + if ((get_wait_data(cosa)) != '=') + return -3; - if (puthexnumber(cosa, address) < 0) return -4; - if (put_wait_data(cosa, ' ') == -1) return -5; - if (get_wait_data(cosa) != ' ') return -6; - if (get_wait_data(cosa) != '=') return -7; + if (puthexnumber(cosa, address) < 0) + return -4; + if (put_wait_data(cosa, ' ') == -1) + return -5; + if (get_wait_data(cosa) != ' ') + return -6; + if (get_wait_data(cosa) != '=') + return -7; - if (puthexnumber(cosa, address+length-1) < 0) return -8; - if (put_wait_data(cosa, ' ') == -1) return -9; - if (get_wait_data(cosa) != ' ') return -10; + if (puthexnumber(cosa, address + length - 1) < 0) + return -8; + if (put_wait_data(cosa, ' ') == -1) + return -9; + if (get_wait_data(cosa) != ' ') + return -10; while (length--) { char c; int i; - if ((i=get_wait_data(cosa)) == -1) { + + i = get_wait_data(cosa); + if (i == -1) { pr_info("0x%04x bytes remaining\n", length); return -11; } - c=i; + c = i; #if 1 if (put_user(c, microcode)) return -23; /* ??? */ @@ -1489,22 +1512,24 @@ static int readmem(struct cosa_data *cosa, char __user *microcode, int length, i microcode++; } - if (get_wait_data(cosa) != '\r') return -21; - if (get_wait_data(cosa) != '\n') return -22; - if (get_wait_data(cosa) != '.') return -23; + if (get_wait_data(cosa) != '\r') + return -21; + if (get_wait_data(cosa) != '\n') + return -22; + if (get_wait_data(cosa) != '.') + return -23; #if 0 printk(KERN_DEBUG "cosa%d: readmem completed.\n", cosa->num); #endif return 0; } -/* - * This function resets the device and reads the initial prompt +/* This function resets the device and reads the initial prompt * of the device's ROM monitor. */ static int cosa_reset_and_read_id(struct cosa_data *cosa, char *idstring) { - int i=0, id=0, prev=0, curr=0; + int i = 0, id = 0, prev = 0, curr = 0; /* Reset the card ... */ cosa_putstatus(cosa, 0); @@ -1514,18 +1539,18 @@ static int cosa_reset_and_read_id(struct cosa_data *cosa, char *idstring) /* Disable all IRQs from the card */ cosa_putstatus(cosa, 0); - /* - * Try to read the ID string. The card then prints out the + /* Try to read the ID string. The card then prints out the * identification string ended by the "\n\x2e". * * The following loop is indexed through i (instead of id) * to avoid looping forever when for any reason * the port returns '\r', '\n' or '\x2e' permanently. */ - for (i=0; inum, cosa_getstatus(cosa)); return -1; } - -/* - * The following routine puts the hexadecimal number into the SRP monitor + +/* The following routine puts the hexadecimal number into the SRP monitor * and verifies the proper echo of the sent bytes. Returns 0 on success, * negative number on failure (-1,-3,-5,-7) means that put_wait_data() failed, * (-2,-4,-6,-8) means that reading echo failed. @@ -1608,26 +1631,24 @@ static int puthexnumber(struct cosa_data *cosa, int number) /* Well, I should probably replace this by something faster. */ sprintf(temp, "%04X", number); - for (i=0; i<4; i++) { + for (i = 0; i < 4; i++) { if (put_wait_data(cosa, temp[i]) == -1) { pr_notice("cosa%d: puthexnumber failed to write byte %d\n", cosa->num, i); - return -1-2*i; + return -1 - 2 * i; } if (get_wait_data(cosa) != temp[i]) { pr_notice("cosa%d: puthexhumber failed to read echo of byte %d\n", cosa->num, i); - return -2-2*i; + return -2 - 2 * i; } } return 0; } - /* ---------- Interrupt routines ---------- */ -/* - * There are three types of interrupt: +/* There are three types of interrupt: * At the beginning of transmit - this handled is in tx_interrupt(), * at the beginning of receive - it is in rx_interrupt() and * at the end of transmit/receive - it is the eot_interrupt() function. @@ -1635,14 +1656,13 @@ static int puthexnumber(struct cosa_data *cosa, int number) * COSA status byte. I have moved the rx/tx/eot interrupt handling into * separate functions to make it more readable. These functions are inline, * so there should be no overhead of function call. - * + * * In the COSA bus-master mode, we need to tell the card the address of a * buffer. Unfortunately, COSA may be too slow for us, so we must busy-wait. * It's time to use the bottom half :-( */ -/* - * Transmit interrupt routine - called when COSA is willing to obtain +/* Transmit interrupt routine - called when COSA is willing to obtain * data from the OS. The most tricky part of the routine is selection * of channel we (OS) want to send packet for. For SRP we should probably * use the round-robin approach. The newer COSA firmwares have a simple @@ -1667,7 +1687,8 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status) set_bit(TXBIT, &cosa->rxtx); if (!test_bit(IRQBIT, &cosa->rxtx)) { /* flow control, see the comment above */ - int i=0; + int i = 0; + if (!cosa->txbitmap) { pr_warn("%s: No channel wants data in TX IRQ. Expect DMA timeout.\n", cosa->name); @@ -1681,9 +1702,10 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status) i++; if (cosa->txchan >= cosa->nchannels) cosa->txchan = 0; - if (!(cosa->txbitmap & (1<txchan))) + if (!(cosa->txbitmap & (1 << cosa->txchan))) continue; - if (~status & (1 << (cosa->txchan+DRIVER_TXMAP_SHIFT))) + if (~status & + (1 << (cosa->txchan + DRIVER_TXMAP_SHIFT))) break; /* in second pass, accept first ready-to-TX channel */ if (i > cosa->nchannels) { @@ -1698,12 +1720,13 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status) } cosa->txsize = cosa->chan[cosa->txchan].txsize; - if (cosa_dma_able(cosa->chan+cosa->txchan, - cosa->chan[cosa->txchan].txbuf, cosa->txsize)) { + if (cosa_dma_able(cosa->chan + cosa->txchan, + cosa->chan[cosa->txchan].txbuf, + cosa->txsize)) { cosa->txbuf = cosa->chan[cosa->txchan].txbuf; } else { memcpy(cosa->bouncebuf, cosa->chan[cosa->txchan].txbuf, - cosa->txsize); + cosa->txsize); cosa->txbuf = cosa->bouncebuf; } } @@ -1711,12 +1734,12 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status) if (is_8bit(cosa)) { if (!test_bit(IRQBIT, &cosa->rxtx)) { cosa_putstatus(cosa, SR_TX_INT_ENA); - cosa_putdata8(cosa, ((cosa->txchan << 5) & 0xe0)| + cosa_putdata8(cosa, ((cosa->txchan << 5) & 0xe0) | ((cosa->txsize >> 8) & 0x1f)); #ifdef DEBUG_IO debug_status_out(cosa, SR_TX_INT_ENA); - debug_data_out(cosa, ((cosa->txchan << 5) & 0xe0)| - ((cosa->txsize >> 8) & 0x1f)); + debug_data_out(cosa, ((cosa->txchan << 5) & 0xe0) | + ((cosa->txsize >> 8) & 0x1f)); debug_data_in(cosa, cosa_getdata8(cosa)); #else cosa_getdata8(cosa); @@ -1727,20 +1750,20 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status) } else { clear_bit(IRQBIT, &cosa->rxtx); cosa_putstatus(cosa, 0); - cosa_putdata8(cosa, cosa->txsize&0xff); + cosa_putdata8(cosa, cosa->txsize & 0xff); #ifdef DEBUG_IO debug_status_out(cosa, 0); - debug_data_out(cosa, cosa->txsize&0xff); + debug_data_out(cosa, cosa->txsize & 0xff); #endif } } else { cosa_putstatus(cosa, SR_TX_INT_ENA); - cosa_putdata16(cosa, ((cosa->txchan<<13) & 0xe000) + cosa_putdata16(cosa, ((cosa->txchan << 13) & 0xe000) | (cosa->txsize & 0x1fff)); #ifdef DEBUG_IO debug_status_out(cosa, SR_TX_INT_ENA); - debug_data_out(cosa, ((cosa->txchan<<13) & 0xe000) - | (cosa->txsize & 0x1fff)); + debug_data_out(cosa, ((cosa->txchan << 13) & 0xe000) | + (cosa->txsize & 0x1fff)); debug_data_in(cosa, cosa_getdata8(cosa)); debug_status_out(cosa, 0); #else @@ -1751,25 +1774,28 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status) if (cosa->busmaster) { unsigned long addr = virt_to_bus(cosa->txbuf); - int count=0; + int count = 0; + pr_info("busmaster IRQ\n"); - while (!(cosa_getstatus(cosa)&SR_TX_RDY)) { + while (!(cosa_getstatus(cosa) & SR_TX_RDY)) { count++; udelay(10); - if (count > 1000) break; + if (count > 1000) + break; } pr_info("status %x\n", cosa_getstatus(cosa)); pr_info("ready after %d loops\n", count); - cosa_putdata16(cosa, (addr >> 16)&0xffff); + cosa_putdata16(cosa, (addr >> 16) & 0xffff); count = 0; - while (!(cosa_getstatus(cosa)&SR_TX_RDY)) { + while (!(cosa_getstatus(cosa) & SR_TX_RDY)) { count++; - if (count > 1000) break; + if (count > 1000) + break; udelay(10); } pr_info("ready after %d loops\n", count); - cosa_putdata16(cosa, addr &0xffff); + cosa_putdata16(cosa, addr & 0xffff); flags1 = claim_dma_lock(); set_dma_mode(cosa->dma, DMA_MODE_CASCADE); enable_dma(cosa->dma); @@ -1785,9 +1811,9 @@ static inline void tx_interrupt(struct cosa_data *cosa, int status) enable_dma(cosa->dma); release_dma_lock(flags1); } - cosa_putstatus(cosa, SR_TX_DMA_ENA|SR_USR_INT_ENA); + cosa_putstatus(cosa, SR_TX_DMA_ENA | SR_USR_INT_ENA); #ifdef DEBUG_IO - debug_status_out(cosa, SR_TX_DMA_ENA|SR_USR_INT_ENA); + debug_status_out(cosa, SR_TX_DMA_ENA | SR_USR_INT_ENA); #endif spin_unlock_irqrestore(&cosa->lock, flags); } @@ -1806,7 +1832,7 @@ static inline void rx_interrupt(struct cosa_data *cosa, int status) if (!test_bit(IRQBIT, &cosa->rxtx)) { set_bit(IRQBIT, &cosa->rxtx); put_driver_status_nolock(cosa); - cosa->rxsize = cosa_getdata8(cosa) <<8; + cosa->rxsize = cosa_getdata8(cosa) << 8; #ifdef DEBUG_IO debug_data_in(cosa, cosa->rxsize >> 8); #endif @@ -1859,20 +1885,20 @@ reject: /* Reject the packet */ disable_dma(cosa->dma); clear_dma_ff(cosa->dma); set_dma_mode(cosa->dma, DMA_MODE_READ); - if (cosa_dma_able(cosa->rxchan, cosa->rxbuf, cosa->rxsize & 0x1fff)) { + if (cosa_dma_able(cosa->rxchan, cosa->rxbuf, cosa->rxsize & 0x1fff)) set_dma_addr(cosa->dma, virt_to_bus(cosa->rxbuf)); - } else { + else set_dma_addr(cosa->dma, virt_to_bus(cosa->bouncebuf)); - } - set_dma_count(cosa->dma, (cosa->rxsize&0x1fff)); + + set_dma_count(cosa->dma, (cosa->rxsize & 0x1fff)); enable_dma(cosa->dma); release_dma_lock(flags); spin_lock_irqsave(&cosa->lock, flags); - cosa_putstatus(cosa, SR_RX_DMA_ENA|SR_USR_INT_ENA); + cosa_putstatus(cosa, SR_RX_DMA_ENA | SR_USR_INT_ENA); if (!is_8bit(cosa) && (status & SR_TX_RDY)) cosa_putdata8(cosa, DRIVER_RX_READY); #ifdef DEBUG_IO - debug_status_out(cosa, SR_RX_DMA_ENA|SR_USR_INT_ENA); + debug_status_out(cosa, SR_RX_DMA_ENA | SR_USR_INT_ENA); if (!is_8bit(cosa) && (status & SR_TX_RDY)) debug_data_cmd(cosa, DRIVER_RX_READY); #endif @@ -1882,13 +1908,15 @@ reject: /* Reject the packet */ static inline void eot_interrupt(struct cosa_data *cosa, int status) { unsigned long flags, flags1; + spin_lock_irqsave(&cosa->lock, flags); flags1 = claim_dma_lock(); disable_dma(cosa->dma); clear_dma_ff(cosa->dma); release_dma_lock(flags1); if (test_bit(TXBIT, &cosa->rxtx)) { - struct channel_data *chan = cosa->chan+cosa->txchan; + struct channel_data *chan = cosa->chan + cosa->txchan; + if (chan->tx_done) if (chan->tx_done(chan, cosa->txsize)) clear_bit(chan->num, &cosa->txbitmap); @@ -1896,9 +1924,10 @@ static inline void eot_interrupt(struct cosa_data *cosa, int status) #ifdef DEBUG_DATA { int i; + pr_info("cosa%dc%d: done rx(0x%x)", cosa->num, cosa->rxchan->num, cosa->rxsize); - for (i=0; irxsize; i++) + for (i = 0; i < cosa->rxsize; i++) pr_cont(" %02x", cosa->rxbuf[i]&0xff); pr_cont("\n"); } @@ -1914,8 +1943,7 @@ static inline void eot_interrupt(struct cosa_data *cosa, int status) } else { pr_notice("cosa%d: unexpected EOT interrupt\n", cosa->num); } - /* - * Clear the RXBIT, TXBIT and IRQBIT (the latest should be + /* Clear the RXBIT, TXBIT and IRQBIT (the latest should be * cleared anyway). We should do it as soon as possible * so that we can tell the COSA we are done and to give it a time * for recovery. @@ -1968,10 +1996,8 @@ again: return IRQ_HANDLED; } - /* ---------- I/O debugging routines ---------- */ -/* - * These routines can be used to monitor COSA/SRP I/O and to printk() +/* These routines can be used to monitor COSA/SRP I/O and to printk() * the data being transferred on the data and status I/O port in a * readable way. */ @@ -1980,6 +2006,7 @@ again: static void debug_status_in(struct cosa_data *cosa, int status) { char *s; + switch (status & SR_CMD_FROM_SRP_MASK) { case SR_UP_REQUEST: s = "RX_REQ"; diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index 5de71e44fc5a..b3466e084e84 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/* - * FarSync WAN driver for Linux (2.6.x kernel version) +/* FarSync WAN driver for Linux (2.6.x kernel version) * * Actually sync driver for X.21, V.35 and V.24 on FarSync T-series cards * @@ -30,8 +29,7 @@ #include "farsync.h" -/* - * Module info +/* Module info */ MODULE_AUTHOR("R.J.Dunlop "); MODULE_DESCRIPTION("FarSync T-Series WAN driver. FarSite Communications Ltd."); @@ -49,20 +47,23 @@ MODULE_LICENSE("GPL"); /* Default parameters for the link */ #define FST_TX_QUEUE_LEN 100 /* At 8Mbps a longer queue length is - * useful */ + * useful + */ #define FST_TXQ_DEPTH 16 /* This one is for the buffering * of frames on the way down to the card * so that we can keep the card busy * and maximise throughput */ #define FST_HIGH_WATER_MARK 12 /* Point at which we flow control - * network layer */ + * network layer + */ #define FST_LOW_WATER_MARK 8 /* Point at which we remove flow - * control from network layer */ + * control from network layer + */ #define FST_MAX_MTU 8000 /* Huge but possible */ #define FST_DEF_MTU 1500 /* Common sane value */ -#define FST_TX_TIMEOUT (2*HZ) +#define FST_TX_TIMEOUT (2 * HZ) #ifdef ARPHRD_RAWHDLC #define ARPHRD_MYTYPE ARPHRD_RAWHDLC /* Raw frames */ @@ -70,13 +71,12 @@ MODULE_LICENSE("GPL"); #define ARPHRD_MYTYPE ARPHRD_HDLC /* Cisco-HDLC (keepalives etc) */ #endif -/* - * Modules parameters and associated variables +/* Modules parameters and associated variables */ static int fst_txq_low = FST_LOW_WATER_MARK; static int fst_txq_high = FST_HIGH_WATER_MARK; static int fst_max_reads = 7; -static int fst_excluded_cards = 0; +static int fst_excluded_cards; static int fst_excluded_list[FST_MAX_CARDS]; module_param(fst_txq_low, int, 0); @@ -105,9 +105,11 @@ module_param_array(fst_excluded_list, int, NULL, 0); #define FST_MEMSIZE 0x100000 /* Size of card memory (1Mb) */ #define SMC_BASE 0x00002000L /* Base offset of the shared memory window main - * configuration structure */ + * configuration structure + */ #define BFM_BASE 0x00010000L /* Base offset of the shared memory window DMA - * buffers */ + * buffers + */ #define LEN_TX_BUFFER 8192 /* Size of packet buffers */ #define LEN_RX_BUFFER 8192 @@ -377,8 +379,7 @@ struct fst_shared { #define INTCSR_9054 0x68 /* Interrupt control/status register */ /* 9054 DMA Registers */ -/* - * Note that we will be using DMA Channel 0 for copying rx data +/* Note that we will be using DMA Channel 0 for copying rx data * and Channel 1 for copying tx data */ #define DMAMODE0 0x80 @@ -421,7 +422,7 @@ struct buf_window { /* Per port (line or channel) information */ struct fst_port_info { - struct net_device *dev; /* Device struct - must be first */ + struct net_device *dev; /* Device struct - must be first */ struct fst_card_info *card; /* Card we're associated with */ int index; /* Port index on the card */ int hwif; /* Line hardware (lineInterface copy) */ @@ -431,8 +432,7 @@ struct fst_port_info { int txpos; /* Next Tx buffer to use */ int txipos; /* Next Tx buffer to check for free */ int start; /* Indication of start/stop to network */ - /* - * A sixteen entry transmit queue + /* A sixteen entry transmit queue */ int txqs; /* index to get next buffer to tx */ int txqe; /* index to queue next packet */ @@ -479,9 +479,7 @@ struct fst_card_info { #define dev_to_port(D) (dev_to_hdlc(D)->priv) #define port_to_dev(P) ((P)->dev) - -/* - * Shared memory window access macros +/* Shared memory window access macros * * We have a nice memory based structure above, which could be directly * mapped on i386 but might not work on other architectures unless we use @@ -491,16 +489,15 @@ struct fst_card_info { */ #define WIN_OFFSET(X) ((long)&(((struct fst_shared *)SMC_BASE)->X)) -#define FST_RDB(C,E) readb ((C)->mem + WIN_OFFSET(E)) -#define FST_RDW(C,E) readw ((C)->mem + WIN_OFFSET(E)) -#define FST_RDL(C,E) readl ((C)->mem + WIN_OFFSET(E)) +#define FST_RDB(C, E) (readb((C)->mem + WIN_OFFSET(E))) +#define FST_RDW(C, E) (readw((C)->mem + WIN_OFFSET(E))) +#define FST_RDL(C, E) (readl((C)->mem + WIN_OFFSET(E))) -#define FST_WRB(C,E,B) writeb ((B), (C)->mem + WIN_OFFSET(E)) -#define FST_WRW(C,E,W) writew ((W), (C)->mem + WIN_OFFSET(E)) -#define FST_WRL(C,E,L) writel ((L), (C)->mem + WIN_OFFSET(E)) +#define FST_WRB(C, E, B) (writeb((B), (C)->mem + WIN_OFFSET(E))) +#define FST_WRW(C, E, W) (writew((W), (C)->mem + WIN_OFFSET(E))) +#define FST_WRL(C, E, L) (writel((L), (C)->mem + WIN_OFFSET(E))) -/* - * Debug support +/* Debug support */ #if FST_DEBUG @@ -524,43 +521,41 @@ do { \ } while (0) #endif -/* - * PCI ID lookup table +/* PCI ID lookup table */ static const struct pci_device_id fst_pci_dev_id[] = { - {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T2P, PCI_ANY_ID, + {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T2P, PCI_ANY_ID, PCI_ANY_ID, 0, 0, FST_TYPE_T2P}, - {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T4P, PCI_ANY_ID, + {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T4P, PCI_ANY_ID, PCI_ANY_ID, 0, 0, FST_TYPE_T4P}, - {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T1U, PCI_ANY_ID, + {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T1U, PCI_ANY_ID, PCI_ANY_ID, 0, 0, FST_TYPE_T1U}, - {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T2U, PCI_ANY_ID, + {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T2U, PCI_ANY_ID, PCI_ANY_ID, 0, 0, FST_TYPE_T2U}, - {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T4U, PCI_ANY_ID, + {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_T4U, PCI_ANY_ID, PCI_ANY_ID, 0, 0, FST_TYPE_T4U}, - {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_TE1, PCI_ANY_ID, + {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_TE1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, FST_TYPE_TE1}, - {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_TE1C, PCI_ANY_ID, + {PCI_VENDOR_ID_FARSITE, PCI_DEVICE_ID_FARSITE_TE1C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, FST_TYPE_TE1}, {0,} /* End */ }; MODULE_DEVICE_TABLE(pci, fst_pci_dev_id); -/* - * Device Driver Work Queues +/* Device Driver Work Queues * - * So that we don't spend too much time processing events in the - * Interrupt Service routine, we will declare a work queue per Card + * So that we don't spend too much time processing events in the + * Interrupt Service routine, we will declare a work queue per Card * and make the ISR schedule a task in the queue for later execution. * In the 2.4 Kernel we used to use the immediate queue for BH's - * Now that they are gone, tasklets seem to be much better than work + * Now that they are gone, tasklets seem to be much better than work * queues. */ @@ -578,18 +573,16 @@ static u64 fst_work_txq; static u64 fst_work_intq; static void -fst_q_work_item(u64 * queue, int card_index) +fst_q_work_item(u64 *queue, int card_index) { unsigned long flags; u64 mask; - /* - * Grab the queue exclusively + /* Grab the queue exclusively */ spin_lock_irqsave(&fst_work_q_lock, flags); - /* - * Making an entry in the queue is simply a matter of setting + /* Making an entry in the queue is simply a matter of setting * a bit for the card indicating that there is work to do in the * bottom half for the card. Note the limitation of 64 cards. * That ought to be enough @@ -606,8 +599,7 @@ fst_process_tx_work_q(struct tasklet_struct *unused) u64 work_txq; int i; - /* - * Grab the queue exclusively + /* Grab the queue exclusively */ dbg(DBG_TX, "fst_process_tx_work_q\n"); spin_lock_irqsave(&fst_work_q_lock, flags); @@ -615,12 +607,11 @@ fst_process_tx_work_q(struct tasklet_struct *unused) fst_work_txq = 0; spin_unlock_irqrestore(&fst_work_q_lock, flags); - /* - * Call the bottom half for each card with work waiting + /* Call the bottom half for each card with work waiting */ for (i = 0; i < FST_MAX_CARDS; i++) { if (work_txq & 0x01) { - if (fst_card_array[i] != NULL) { + if (fst_card_array[i]) { dbg(DBG_TX, "Calling tx bh for card %d\n", i); do_bottom_half_tx(fst_card_array[i]); } @@ -636,8 +627,7 @@ fst_process_int_work_q(struct tasklet_struct *unused) u64 work_intq; int i; - /* - * Grab the queue exclusively + /* Grab the queue exclusively */ dbg(DBG_INTR, "fst_process_int_work_q\n"); spin_lock_irqsave(&fst_work_q_lock, flags); @@ -645,12 +635,11 @@ fst_process_int_work_q(struct tasklet_struct *unused) fst_work_intq = 0; spin_unlock_irqrestore(&fst_work_q_lock, flags); - /* - * Call the bottom half for each card with work waiting + /* Call the bottom half for each card with work waiting */ for (i = 0; i < FST_MAX_CARDS; i++) { if (work_intq & 0x01) { - if (fst_card_array[i] != NULL) { + if (fst_card_array[i]) { dbg(DBG_INTR, "Calling rx & tx bh for card %d\n", i); do_bottom_half_rx(fst_card_array[i]); @@ -683,19 +672,16 @@ fst_cpureset(struct fst_card_info *card) dbg(DBG_ASS, "Error in reading interrupt line register\n"); } - /* - * Assert PLX software reset and Am186 hardware reset + /* Assert PLX software reset and Am186 hardware reset * and then deassert the PLX software reset but 186 still in reset */ outw(0x440f, card->pci_conf + CNTRL_9054 + 2); outw(0x040f, card->pci_conf + CNTRL_9054 + 2); - /* - * We are delaying here to allow the 9054 to reset itself + /* We are delaying here to allow the 9054 to reset itself */ usleep_range(10, 20); outw(0x240f, card->pci_conf + CNTRL_9054 + 2); - /* - * We are delaying here to allow the 9054 to reload its eeprom + /* We are delaying here to allow the 9054 to reload its eeprom */ usleep_range(10, 20); outw(0x040f, card->pci_conf + CNTRL_9054 + 2); @@ -720,19 +706,17 @@ static inline void fst_cpurelease(struct fst_card_info *card) { if (card->family == FST_FAMILY_TXU) { - /* - * Force posted writes to complete + /* Force posted writes to complete */ - (void) readb(card->mem); + (void)readb(card->mem); - /* - * Release LRESET DO = 1 + /* Release LRESET DO = 1 * Then release Local Hold, DO = 1 */ outw(0x040e, card->pci_conf + CNTRL_9054 + 2); outw(0x040f, card->pci_conf + CNTRL_9054 + 2); } else { - (void) readb(card->ctlmem); + (void)readb(card->ctlmem); } } @@ -742,7 +726,7 @@ static inline void fst_clear_intr(struct fst_card_info *card) { if (card->family == FST_FAMILY_TXU) { - (void) readb(card->ctlmem); + (void)readb(card->ctlmem); } else { /* Poke the appropriate PLX chip register (same as enabling interrupts) */ @@ -755,11 +739,10 @@ fst_clear_intr(struct fst_card_info *card) static inline void fst_enable_intr(struct fst_card_info *card) { - if (card->family == FST_FAMILY_TXU) { + if (card->family == FST_FAMILY_TXU) outl(0x0f0c0900, card->pci_conf + INTCSR_9054); - } else { + else outw(0x0543, card->pci_conf + INTCSR_9052); - } } /* Disable card interrupts @@ -767,11 +750,10 @@ fst_enable_intr(struct fst_card_info *card) static inline void fst_disable_intr(struct fst_card_info *card) { - if (card->family == FST_FAMILY_TXU) { + if (card->family == FST_FAMILY_TXU) outl(0x00000000, card->pci_conf + INTCSR_9054); - } else { + else outw(0x0000, card->pci_conf + INTCSR_9052); - } } /* Process the result of trying to pass a received frame up the stack @@ -782,8 +764,7 @@ fst_process_rx_status(int rx_status, char *name) switch (rx_status) { case NET_RX_SUCCESS: { - /* - * Nothing to do here + /* Nothing to do here */ break; } @@ -800,11 +781,10 @@ fst_process_rx_status(int rx_status, char *name) static inline void fst_init_dma(struct fst_card_info *card) { - /* - * This is only required for the PLX 9054 + /* This is only required for the PLX 9054 */ if (card->family == FST_FAMILY_TXU) { - pci_set_master(card->device); + pci_set_master(card->device); outl(0x00020441, card->pci_conf + DMAMODE0); outl(0x00020441, card->pci_conf + DMAMODE1); outl(0x0, card->pci_conf + DMATHR); @@ -819,8 +799,7 @@ fst_tx_dma_complete(struct fst_card_info *card, struct fst_port_info *port, { struct net_device *dev = port_to_dev(port); - /* - * Everything is now set, just tell the card to go + /* Everything is now set, just tell the card to go */ dbg(DBG_TX, "fst_tx_dma_complete\n"); FST_WRB(card, txDescrRing[port->index][txpos].bits, @@ -830,8 +809,7 @@ fst_tx_dma_complete(struct fst_card_info *card, struct fst_port_info *port, netif_trans_update(dev); } -/* - * Mark it for our own raw sockets interface +/* Mark it for our own raw sockets interface */ static __be16 farsync_type_trans(struct sk_buff *skb, struct net_device *dev) { @@ -874,55 +852,47 @@ fst_rx_dma_complete(struct fst_card_info *card, struct fst_port_info *port, dev->stats.rx_dropped++; } -/* - * Receive a frame through the DMA +/* Receive a frame through the DMA */ static inline void fst_rx_dma(struct fst_card_info *card, dma_addr_t dma, u32 mem, int len) { - /* - * This routine will setup the DMA and start it + /* This routine will setup the DMA and start it */ dbg(DBG_RX, "In fst_rx_dma %x %x %d\n", (u32)dma, mem, len); - if (card->dmarx_in_progress) { + if (card->dmarx_in_progress) dbg(DBG_ASS, "In fst_rx_dma while dma in progress\n"); - } outl(dma, card->pci_conf + DMAPADR0); /* Copy to here */ outl(mem, card->pci_conf + DMALADR0); /* from here */ outl(len, card->pci_conf + DMASIZ0); /* for this length */ outl(0x00000000c, card->pci_conf + DMADPR0); /* In this direction */ - /* - * We use the dmarx_in_progress flag to flag the channel as busy + /* We use the dmarx_in_progress flag to flag the channel as busy */ card->dmarx_in_progress = 1; outb(0x03, card->pci_conf + DMACSR0); /* Start the transfer */ } -/* - * Send a frame through the DMA +/* Send a frame through the DMA */ static inline void fst_tx_dma(struct fst_card_info *card, dma_addr_t dma, u32 mem, int len) { - /* - * This routine will setup the DMA and start it. + /* This routine will setup the DMA and start it. */ dbg(DBG_TX, "In fst_tx_dma %x %x %d\n", (u32)dma, mem, len); - if (card->dmatx_in_progress) { + if (card->dmatx_in_progress) dbg(DBG_ASS, "In fst_tx_dma while dma in progress\n"); - } outl(dma, card->pci_conf + DMAPADR1); /* Copy from here */ outl(mem, card->pci_conf + DMALADR1); /* to here */ outl(len, card->pci_conf + DMASIZ1); /* for this length */ outl(0x000000004, card->pci_conf + DMADPR1); /* In this direction */ - /* - * We use the dmatx_in_progress to flag the channel as busy + /* We use the dmatx_in_progress to flag the channel as busy */ card->dmatx_in_progress = 1; outb(0x03, card->pci_conf + DMACSR1); /* Start the transfer */ @@ -958,12 +928,11 @@ fst_issue_cmd(struct fst_port_info *port, unsigned short cmd) mbval = FST_RDW(card, portMailbox[port->index][0]); } - if (safety > 0) { + if (safety > 0) dbg(DBG_CMD, "Mailbox clear after %d jiffies\n", safety); - } - if (mbval == NAK) { + + if (mbval == NAK) dbg(DBG_CMD, "issue_cmd: previous command was NAK'd\n"); - } FST_WRW(card, portMailbox[port->index][0], cmd); @@ -998,8 +967,7 @@ fst_op_lower(struct fst_port_info *port, unsigned int outputs) fst_issue_cmd(port, SETV24O); } -/* - * Setup port Rx buffers +/* Setup port Rx buffers */ static void fst_rx_config(struct fst_port_info *port) @@ -1016,8 +984,8 @@ fst_rx_config(struct fst_port_info *port) for (i = 0; i < NUM_RX_BUFFER; i++) { offset = BUF_OFFSET(rxBuffer[pi][i][0]); - FST_WRW(card, rxDescrRing[pi][i].ladr, (u16) offset); - FST_WRB(card, rxDescrRing[pi][i].hadr, (u8) (offset >> 16)); + FST_WRW(card, rxDescrRing[pi][i].ladr, (u16)offset); + FST_WRB(card, rxDescrRing[pi][i].hadr, (u8)(offset >> 16)); FST_WRW(card, rxDescrRing[pi][i].bcnt, cnv_bcnt(LEN_RX_BUFFER)); FST_WRW(card, rxDescrRing[pi][i].mcnt, LEN_RX_BUFFER); FST_WRB(card, rxDescrRing[pi][i].bits, DMA_OWN); @@ -1026,8 +994,7 @@ fst_rx_config(struct fst_port_info *port) spin_unlock_irqrestore(&card->card_lock, flags); } -/* - * Setup port Tx buffers +/* Setup port Tx buffers */ static void fst_tx_config(struct fst_port_info *port) @@ -1044,8 +1011,8 @@ fst_tx_config(struct fst_port_info *port) for (i = 0; i < NUM_TX_BUFFER; i++) { offset = BUF_OFFSET(txBuffer[pi][i][0]); - FST_WRW(card, txDescrRing[pi][i].ladr, (u16) offset); - FST_WRB(card, txDescrRing[pi][i].hadr, (u8) (offset >> 16)); + FST_WRW(card, txDescrRing[pi][i].ladr, (u16)offset); + FST_WRB(card, txDescrRing[pi][i].hadr, (u8)(offset >> 16)); FST_WRW(card, txDescrRing[pi][i].bcnt, 0); FST_WRB(card, txDescrRing[pi][i].bits, 0); } @@ -1069,16 +1036,14 @@ fst_intr_te1_alarm(struct fst_card_info *card, struct fst_port_info *port) ais = FST_RDB(card, suStatus.alarmIndicationSignal); if (los) { - /* - * Lost the link + /* Lost the link */ if (netif_carrier_ok(port_to_dev(port))) { dbg(DBG_INTR, "Net carrier off\n"); netif_carrier_off(port_to_dev(port)); } } else { - /* - * Link available + /* Link available */ if (!netif_carrier_ok(port_to_dev(port))) { dbg(DBG_INTR, "Net carrier on\n"); @@ -1110,7 +1075,7 @@ fst_intr_ctlchg(struct fst_card_info *card, struct fst_port_info *port) signals = FST_RDL(card, v24DebouncedSts[port->index]); - if (signals & (((port->hwif == X21) || (port->hwif == X21D)) + if (signals & ((port->hwif == X21 || port->hwif == X21D) ? IPSTS_INDICATE : IPSTS_DCD)) { if (!netif_carrier_ok(port_to_dev(port))) { dbg(DBG_INTR, "DCD active\n"); @@ -1132,8 +1097,7 @@ fst_log_rx_error(struct fst_card_info *card, struct fst_port_info *port, { struct net_device *dev = port_to_dev(port); - /* - * Increment the appropriate error counter + /* Increment the appropriate error counter */ dev->stats.rx_errors++; if (dmabits & RX_OFLO) { @@ -1168,15 +1132,14 @@ fst_recover_rx_error(struct fst_card_info *card, struct fst_port_info *port, int pi; pi = port->index; - /* - * Discard buffer descriptors until we see the start of the + /* Discard buffer descriptors until we see the start of the * next frame. Note that for long frames this could be in - * a subsequent interrupt. + * a subsequent interrupt. */ i = 0; while ((dmabits & (DMA_OWN | RX_STP)) == 0) { FST_WRB(card, rxDescrRing[pi][rxp].bits, DMA_OWN); - rxp = (rxp+1) % NUM_RX_BUFFER; + rxp = (rxp + 1) % NUM_RX_BUFFER; if (++i > NUM_RX_BUFFER) { dbg(DBG_ASS, "intr_rx: Discarding more bufs" " than we have\n"); @@ -1190,11 +1153,9 @@ fst_recover_rx_error(struct fst_card_info *card, struct fst_port_info *port, /* Discard the terminal buffer */ if (!(dmabits & DMA_OWN)) { FST_WRB(card, rxDescrRing[pi][rxp].bits, DMA_OWN); - rxp = (rxp+1) % NUM_RX_BUFFER; + rxp = (rxp + 1) % NUM_RX_BUFFER; } port->rxpos = rxp; - return; - } /* Rx complete interrupt @@ -1219,17 +1180,15 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port) pi, rxp); return; } - if (card->dmarx_in_progress) { + if (card->dmarx_in_progress) return; - } /* Get buffer length */ len = FST_RDW(card, rxDescrRing[pi][rxp].mcnt); /* Discard the CRC */ len -= 2; if (len == 0) { - /* - * This seems to happen on the TE1 interface sometimes + /* This seems to happen on the TE1 interface sometimes * so throw the frame away and log the event. */ pr_err("Frame received with 0 length. Card %d Port %d\n", @@ -1237,7 +1196,7 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port) /* Return descriptor to card */ FST_WRB(card, rxDescrRing[pi][rxp].bits, DMA_OWN); - rxp = (rxp+1) % NUM_RX_BUFFER; + rxp = (rxp + 1) % NUM_RX_BUFFER; port->rxpos = rxp; return; } @@ -1254,7 +1213,8 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port) } /* Allocate SKB */ - if ((skb = dev_alloc_skb(len)) == NULL) { + skb = dev_alloc_skb(len); + if (!skb) { dbg(DBG_RX, "intr_rx: can't allocate buffer\n"); dev->stats.rx_dropped++; @@ -1262,18 +1222,17 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port) /* Return descriptor to card */ FST_WRB(card, rxDescrRing[pi][rxp].bits, DMA_OWN); - rxp = (rxp+1) % NUM_RX_BUFFER; + rxp = (rxp + 1) % NUM_RX_BUFFER; port->rxpos = rxp; return; } - /* - * We know the length we need to receive, len. + /* We know the length we need to receive, len. * It's not worth using the DMA for reads of less than * FST_MIN_DMA_LEN */ - if ((len < FST_MIN_DMA_LEN) || (card->family == FST_FAMILY_TXP)) { + if (len < FST_MIN_DMA_LEN || card->family == FST_FAMILY_TXP) { memcpy_fromio(skb_put(skb, len), card->mem + BUF_OFFSET(rxBuffer[pi][rxp][0]), len); @@ -1307,12 +1266,11 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port) dbg(DBG_ASS, "About to increment rxpos by more than 1\n"); dbg(DBG_ASS, "rxp = %d rxpos = %d\n", rxp, port->rxpos); } - rxp = (rxp+1) % NUM_RX_BUFFER; + rxp = (rxp + 1) % NUM_RX_BUFFER; port->rxpos = rxp; } -/* - * The bottom halfs to the ISR +/* The bottom half to the ISR * */ @@ -1326,8 +1284,7 @@ do_bottom_half_tx(struct fst_card_info *card) unsigned long flags; struct net_device *dev; - /* - * Find a free buffer for the transmit + /* Find a free buffer for the transmit * Step through each port on this card */ @@ -1340,39 +1297,36 @@ do_bottom_half_tx(struct fst_card_info *card) while (!(FST_RDB(card, txDescrRing[pi][port->txpos].bits) & DMA_OWN) && !(card->dmatx_in_progress)) { - /* - * There doesn't seem to be a txdone event per-se + /* There doesn't seem to be a txdone event per-se * We seem to have to deduce it, by checking the DMA_OWN * bit on the next buffer we think we can use */ spin_lock_irqsave(&card->card_lock, flags); - if ((txq_length = port->txqe - port->txqs) < 0) { - /* - * This is the case where one has wrapped and the + txq_length = port->txqe - port->txqs; + if (txq_length < 0) { + /* This is the case where one has wrapped and the * maths gives us a negative number */ txq_length = txq_length + FST_TXQ_DEPTH; } spin_unlock_irqrestore(&card->card_lock, flags); if (txq_length > 0) { - /* - * There is something to send + /* There is something to send */ spin_lock_irqsave(&card->card_lock, flags); skb = port->txq[port->txqs]; port->txqs++; - if (port->txqs == FST_TXQ_DEPTH) { + if (port->txqs == FST_TXQ_DEPTH) port->txqs = 0; - } + spin_unlock_irqrestore(&card->card_lock, flags); - /* - * copy the data and set the required indicators on the + /* copy the data and set the required indicators on the * card. */ FST_WRW(card, txDescrRing[pi][port->txpos].bcnt, cnv_bcnt(skb->len)); - if ((skb->len < FST_MIN_DMA_LEN) || - (card->family == FST_FAMILY_TXP)) { + if (skb->len < FST_MIN_DMA_LEN || + card->family == FST_FAMILY_TXP) { /* Enqueue the packet with normal io */ memcpy_toio(card->mem + BUF_OFFSET(txBuffer[pi] @@ -1401,8 +1355,7 @@ do_bottom_half_tx(struct fst_card_info *card) } if (++port->txpos >= NUM_TX_BUFFER) port->txpos = 0; - /* - * If we have flow control on, can we now release it? + /* If we have flow control on, can we now release it? */ if (port->start) { if (txq_length < fst_txq_low) { @@ -1413,8 +1366,7 @@ do_bottom_half_tx(struct fst_card_info *card) } dev_kfree_skb(skb); } else { - /* - * Nothing to send so break out of the while loop + /* Nothing to send so break out of the while loop */ break; } @@ -1438,8 +1390,7 @@ do_bottom_half_rx(struct fst_card_info *card) while (!(FST_RDB(card, rxDescrRing[pi][port->rxpos].bits) & DMA_OWN) && !(card->dmarx_in_progress)) { if (rx_count > fst_max_reads) { - /* - * Don't spend forever in receive processing + /* Don't spend forever in receive processing * Schedule another event */ fst_q_work_item(&fst_work_intq, card->card_no); @@ -1452,8 +1403,7 @@ do_bottom_half_rx(struct fst_card_info *card) } } -/* - * The interrupt service routine +/* The interrupt service routine * Dev_id is our fst_card_info pointer */ static irqreturn_t @@ -1468,8 +1418,7 @@ fst_intr(int dummy, void *dev_id) unsigned int do_card_interrupt; unsigned int int_retry_count; - /* - * Check to see if the interrupt was for this card + /* Check to see if the interrupt was for this card * return if not * Note that the call to clear the interrupt is important */ @@ -1478,10 +1427,9 @@ fst_intr(int dummy, void *dev_id) pr_err("Interrupt received for card %d in a non running state (%d)\n", card->card_no, card->state); - /* - * It is possible to really be running, i.e. we have re-loaded + /* It is possible to really be running, i.e. we have re-loaded * a running card - * Clear and reprime the interrupt source + * Clear and reprime the interrupt source */ fst_clear_intr(card); return IRQ_HANDLED; @@ -1490,8 +1438,7 @@ fst_intr(int dummy, void *dev_id) /* Clear and reprime the interrupt source */ fst_clear_intr(card); - /* - * Is the interrupt for this card (handshake == 1) + /* Is the interrupt for this card (handshake == 1) */ do_card_interrupt = 0; if (FST_RDB(card, interruptHandshake) == 1) { @@ -1500,13 +1447,11 @@ fst_intr(int dummy, void *dev_id) FST_WRB(card, interruptHandshake, 0xEE); } if (card->family == FST_FAMILY_TXU) { - /* - * Is it a DMA Interrupt + /* Is it a DMA Interrupt */ dma_intcsr = inl(card->pci_conf + INTCSR_9054); if (dma_intcsr & 0x00200000) { - /* - * DMA Channel 0 (Rx transfer complete) + /* DMA Channel 0 (Rx transfer complete) */ dbg(DBG_RX, "DMA Rx xfer complete\n"); outb(0x8, card->pci_conf + DMACSR0); @@ -1517,8 +1462,7 @@ fst_intr(int dummy, void *dev_id) do_card_interrupt += FST_RX_DMA_INT; } if (dma_intcsr & 0x00400000) { - /* - * DMA Channel 1 (Tx transfer complete) + /* DMA Channel 1 (Tx transfer complete) */ dbg(DBG_TX, "DMA Tx xfer complete\n"); outb(0x8, card->pci_conf + DMACSR1); @@ -1529,8 +1473,7 @@ fst_intr(int dummy, void *dev_id) } } - /* - * Have we been missing Interrupts + /* Have we been missing Interrupts */ int_retry_count = FST_RDL(card, interruptRetryCount); if (int_retry_count) { @@ -1539,9 +1482,8 @@ fst_intr(int dummy, void *dev_id) FST_WRL(card, interruptRetryCount, 0); } - if (!do_card_interrupt) { + if (!do_card_interrupt) return IRQ_HANDLED; - } /* Scehdule the bottom half of the ISR */ fst_q_work_item(&fst_work_intq, card->card_no); @@ -1611,7 +1553,7 @@ fst_intr(int dummy, void *dev_id) rdidx = 0; } FST_WRB(card, interruptEvent.rdindex, rdidx); - return IRQ_HANDLED; + return IRQ_HANDLED; } /* Check that the shared memory configuration is one that we can handle @@ -1635,7 +1577,8 @@ check_started_ok(struct fst_card_info *card) return; } /* Firmware status flag, 0x00 = initialising, 0x01 = OK, 0xFF = fail */ - if ((i = FST_RDB(card, taskStatus)) == 0x01) { + i = FST_RDB(card, taskStatus); + if (i == 0x01) { card->state = FST_RUNNING; } else if (i == 0xFF) { pr_err("Firmware initialisation failed. Card halted\n"); @@ -1665,8 +1608,8 @@ set_conf_from_info(struct fst_card_info *card, struct fst_port_info *port, int err; unsigned char my_framing; - /* Set things according to the user set valid flags - * Several of the old options have been invalidated/replaced by the + /* Set things according to the user set valid flags + * Several of the old options have been invalidated/replaced by the * generic hdlc package. */ err = 0; @@ -1740,9 +1683,8 @@ set_conf_from_info(struct fst_card_info *card, struct fst_port_info *port, #endif } #if FST_DEBUG - if (info->valid & FSTVAL_DEBUG) { + if (info->valid & FSTVAL_DEBUG) fst_debug_mask = info->debug; - } #endif return err; @@ -1754,7 +1696,7 @@ gather_conf_info(struct fst_card_info *card, struct fst_port_info *port, { int i; - memset(info, 0, sizeof (struct fstioc_info)); + memset(info, 0, sizeof(struct fstioc_info)); i = port->index; info->kernelVersion = LINUX_VERSION_CODE; @@ -1787,27 +1729,23 @@ gather_conf_info(struct fst_card_info *card, struct fst_port_info *port, info->cardMode = FST_RDW(card, cardMode); info->smcFirmwareVersion = FST_RDL(card, smcFirmwareVersion); - /* - * The T2U can report cable presence for both A or B - * in bits 0 and 1 of cableStatus. See which port we are and + /* The T2U can report cable presence for both A or B + * in bits 0 and 1 of cableStatus. See which port we are and * do the mapping. */ if (card->family == FST_FAMILY_TXU) { if (port->index == 0) { - /* - * Port A + /* Port A */ info->cableStatus = info->cableStatus & 1; } else { - /* - * Port B + /* Port B */ info->cableStatus = info->cableStatus >> 1; info->cableStatus = info->cableStatus & 1; } } - /* - * Some additional bits if we are TE1 + /* Some additional bits if we are TE1 */ if (card->type == FST_TYPE_TE1) { info->lineSpeed = FST_RDL(card, suConfig.dataRate); @@ -1851,14 +1789,12 @@ fst_set_iface(struct fst_card_info *card, struct fst_port_info *port, sync_serial_settings sync; int i; - if (ifr->ifr_settings.size != sizeof (sync)) { + if (ifr->ifr_settings.size != sizeof(sync)) return -ENOMEM; - } if (copy_from_user - (&sync, ifr->ifr_settings.ifs_ifsu.sync, sizeof (sync))) { + (&sync, ifr->ifr_settings.ifs_ifsu.sync, sizeof(sync))) return -EFAULT; - } if (sync.loopback) return -EINVAL; @@ -1951,12 +1887,11 @@ fst_get_iface(struct fst_card_info *card, struct fst_port_info *port, ifr->ifr_settings.type = IF_IFACE_X21; break; } - if (ifr->ifr_settings.size == 0) { + if (ifr->ifr_settings.size == 0) return 0; /* only type requested */ - } - if (ifr->ifr_settings.size < sizeof (sync)) { + + if (ifr->ifr_settings.size < sizeof(sync)) return -ENOMEM; - } i = port->index; memset(&sync, 0, sizeof(sync)); @@ -1966,11 +1901,10 @@ fst_get_iface(struct fst_card_info *card, struct fst_port_info *port, INTCLK ? CLOCK_INT : CLOCK_EXT; sync.loopback = 0; - if (copy_to_user(ifr->ifr_settings.ifs_ifsu.sync, &sync, sizeof (sync))) { + if (copy_to_user(ifr->ifr_settings.ifs_ifsu.sync, &sync, sizeof(sync))) return -EFAULT; - } - ifr->ifr_settings.size = sizeof (sync); + ifr->ifr_settings.size = sizeof(sync); return 0; } @@ -2008,21 +1942,19 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /* First copy in the header with the length and offset of data * to write */ - if (ifr->ifr_data == NULL) { + if (!ifr->ifr_data) return -EINVAL; - } + if (copy_from_user(&wrthdr, ifr->ifr_data, - sizeof (struct fstioc_write))) { + sizeof(struct fstioc_write))) return -EFAULT; - } /* Sanity check the parameters. We don't support partial writes * when going over the top */ if (wrthdr.size > FST_MEMSIZE || wrthdr.offset > FST_MEMSIZE || - wrthdr.size + wrthdr.offset > FST_MEMSIZE) { + wrthdr.size + wrthdr.offset > FST_MEMSIZE) return -ENXIO; - } /* Now copy the data to the card. */ @@ -2037,9 +1969,9 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /* Writes to the memory of a card in the reset state constitute * a download */ - if (card->state == FST_RESET) { + if (card->state == FST_RESET) card->state = FST_DOWNLOAD; - } + return 0; case FSTGETCONF: @@ -2059,21 +1991,18 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } } - if (ifr->ifr_data == NULL) { + if (!ifr->ifr_data) return -EINVAL; - } gather_conf_info(card, port, &info); - if (copy_to_user(ifr->ifr_data, &info, sizeof (info))) { + if (copy_to_user(ifr->ifr_data, &info, sizeof(info))) return -EFAULT; - } + return 0; case FSTSETCONF: - - /* - * Most of the settings have been moved to the generic ioctls + /* Most of the settings have been moved to the generic ioctls * this just covers debug and board ident now */ @@ -2082,9 +2011,8 @@ fst_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) card->card_no, card->state); return -EIO; } - if (copy_from_user(&info, ifr->ifr_data, sizeof (info))) { + if (copy_from_user(&info, ifr->ifr_data, sizeof(info))) return -EFAULT; - } return set_conf_from_info(card, port, &info); @@ -2150,7 +2078,7 @@ fst_openport(struct fst_port_info *port) port->run = 1; signals = FST_RDL(port->card, v24DebouncedSts[port->index]); - if (signals & (((port->hwif == X21) || (port->hwif == X21D)) + if (signals & ((port->hwif == X21 || port->hwif == X21D) ? IPSTS_INDICATE : IPSTS_DCD)) netif_carrier_on(port_to_dev(port)); else @@ -2159,7 +2087,6 @@ fst_openport(struct fst_port_info *port) port->txqe = 0; port->txqs = 0; } - } static void @@ -2185,7 +2112,7 @@ fst_open(struct net_device *dev) port = dev_to_port(dev); if (!try_module_get(THIS_MODULE)) - return -EBUSY; + return -EBUSY; if (port->mode != FST_RAW) { err = hdlc_open(dev); @@ -2220,9 +2147,9 @@ fst_close(struct net_device *dev) netif_stop_queue(dev); fst_closeport(dev_to_port(dev)); - if (port->mode != FST_RAW) { + if (port->mode != FST_RAW) hdlc_close(dev); - } + module_put(THIS_MODULE); return 0; } @@ -2230,8 +2157,7 @@ fst_close(struct net_device *dev) static int fst_attach(struct net_device *dev, unsigned short encoding, unsigned short parity) { - /* - * Setting currently fixed in FarSync card so we check and forget + /* Setting currently fixed in FarSync card so we check and forget */ if (encoding != ENCODING_NRZ || parity != PARITY_CRC16_PR1_CCITT) return -EINVAL; @@ -2289,23 +2215,21 @@ fst_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - /* - * We are always going to queue the packet + /* We are always going to queue the packet * so that the bottom half is the only place we tx from * Check there is room in the port txq */ spin_lock_irqsave(&card->card_lock, flags); - if ((txq_length = port->txqe - port->txqs) < 0) { - /* - * This is the case where the next free has wrapped but the + txq_length = port->txqe - port->txqs; + if (txq_length < 0) { + /* This is the case where the next free has wrapped but the * last used hasn't */ txq_length = txq_length + FST_TXQ_DEPTH; } spin_unlock_irqrestore(&card->card_lock, flags); if (txq_length > fst_txq_high) { - /* - * We have got enough buffers in the pipeline. Ask the network + /* We have got enough buffers in the pipeline. Ask the network * layer to stop sending frames down */ netif_stop_queue(dev); @@ -2313,8 +2237,7 @@ fst_start_xmit(struct sk_buff *skb, struct net_device *dev) } if (txq_length == FST_TXQ_DEPTH - 1) { - /* - * This shouldn't have happened but such is life + /* This shouldn't have happened but such is life */ dev_kfree_skb(skb); dev->stats.tx_errors++; @@ -2323,8 +2246,7 @@ fst_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - /* - * queue the buffer + /* queue the buffer */ spin_lock_irqsave(&card->card_lock, flags); port->txq[port->txqe] = skb; @@ -2340,8 +2262,7 @@ fst_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -/* - * Card setup having checked hardware resources. +/* Card setup having checked hardware resources. * Should be pretty bizarre if we get an error here (kernel memory * exhaustion is one possibility). If we do see a problem we report it * via a printk and leave the corresponding interface and all that follow @@ -2371,7 +2292,7 @@ fst_init_card(struct fst_card_info *card) err = register_hdlc_device(card->ports[i].dev); if (err < 0) { pr_err("Cannot register HDLC device for port %d (errno %d)\n", - i, -err); + i, -err); while (i--) unregister_hdlc_device(card->ports[i].dev); return err; @@ -2393,14 +2314,13 @@ static const struct net_device_ops fst_ops = { .ndo_tx_timeout = fst_tx_timeout, }; -/* - * Initialise card when detected. +/* Initialise card when detected. * Returns 0 to indicate success, or errno otherwise. */ static int fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent) { - static int no_of_cards_added = 0; + static int no_of_cards_added; struct fst_card_info *card; int err = 0; int i; @@ -2411,17 +2331,15 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent) #if FST_DEBUG dbg(DBG_ASS, "The value of debug mask is %x\n", fst_debug_mask); #endif - /* - * We are going to be clever and allow certain cards not to be + /* We are going to be clever and allow certain cards not to be * configured. An exclude list can be provided in /etc/modules.conf */ if (fst_excluded_cards != 0) { - /* - * There are cards to exclude + /* There are cards to exclude * */ for (i = 0; i < fst_excluded_cards; i++) { - if ((pdev->devfn) >> 3 == fst_excluded_list[i]) { + if (pdev->devfn >> 3 == fst_excluded_list[i]) { pr_info("FarSync PCI device %d not assigned\n", (pdev->devfn) >> 3); return -EBUSY; @@ -2431,16 +2349,18 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* Allocate driver private data */ card = kzalloc(sizeof(struct fst_card_info), GFP_KERNEL); - if (card == NULL) + if (!card) return -ENOMEM; /* Try to enable the device */ - if ((err = pci_enable_device(pdev)) != 0) { + err = pci_enable_device(pdev); + if (err) { pr_err("Failed to enable card. Err %d\n", -err); goto enable_fail; } - if ((err = pci_request_regions(pdev, "FarSync")) !=0) { + err = pci_request_regions(pdev, "FarSync"); + if (err) { pr_err("Failed to allocate regions. Err %d\n", -err); goto regions_fail; } @@ -2449,12 +2369,14 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent) card->pci_conf = pci_resource_start(pdev, 1); card->phys_mem = pci_resource_start(pdev, 2); card->phys_ctlmem = pci_resource_start(pdev, 3); - if ((card->mem = ioremap(card->phys_mem, FST_MEMSIZE)) == NULL) { + card->mem = ioremap(card->phys_mem, FST_MEMSIZE); + if (!card->mem) { pr_err("Physical memory remap failed\n"); err = -ENODEV; goto ioremap_physmem_fail; } - if ((card->ctlmem = ioremap(card->phys_ctlmem, 0x10)) == NULL) { + card->ctlmem = ioremap(card->phys_ctlmem, 0x10); + if (!card->ctlmem) { pr_err("Control memory remap failed\n"); err = -ENODEV; goto ioremap_ctlmem_fail; @@ -2474,19 +2396,20 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent) card->family = ((ent->driver_data == FST_TYPE_T2P) || (ent->driver_data == FST_TYPE_T4P)) ? FST_FAMILY_TXP : FST_FAMILY_TXU; - if ((ent->driver_data == FST_TYPE_T1U) || - (ent->driver_data == FST_TYPE_TE1)) + if (ent->driver_data == FST_TYPE_T1U || + ent->driver_data == FST_TYPE_TE1) card->nports = 1; else card->nports = ((ent->driver_data == FST_TYPE_T2P) || (ent->driver_data == FST_TYPE_T2U)) ? 2 : 4; card->state = FST_UNINIT; - spin_lock_init ( &card->card_lock ); + spin_lock_init(&card->card_lock); - for ( i = 0 ; i < card->nports ; i++ ) { + for (i = 0; i < card->nports; i++) { struct net_device *dev = alloc_hdlcdev(&card->ports[i]); hdlc_device *hdlc; + if (!dev) { while (i--) free_netdev(card->ports[i].dev); @@ -2495,29 +2418,29 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto hdlcdev_fail; } card->ports[i].dev = dev; - card->ports[i].card = card; - card->ports[i].index = i; - card->ports[i].run = 0; + card->ports[i].card = card; + card->ports[i].index = i; + card->ports[i].run = 0; hdlc = dev_to_hdlc(dev); - /* Fill in the net device info */ + /* Fill in the net device info */ /* Since this is a PCI setup this is purely * informational. Give them the buffer addresses * and basic card I/O. */ - dev->mem_start = card->phys_mem - + BUF_OFFSET ( txBuffer[i][0][0]); - dev->mem_end = card->phys_mem - + BUF_OFFSET ( txBuffer[i][NUM_TX_BUFFER - 1][LEN_RX_BUFFER - 1]); - dev->base_addr = card->pci_conf; - dev->irq = card->irq; + dev->mem_start = card->phys_mem + + BUF_OFFSET(txBuffer[i][0][0]); + dev->mem_end = card->phys_mem + + BUF_OFFSET(txBuffer[i][NUM_TX_BUFFER - 1][LEN_RX_BUFFER - 1]); + dev->base_addr = card->pci_conf; + dev->irq = card->irq; dev->netdev_ops = &fst_ops; dev->tx_queue_len = FST_TX_QUEUE_LEN; dev->watchdog_timeo = FST_TX_TIMEOUT; - hdlc->attach = fst_attach; - hdlc->xmit = fst_start_xmit; + hdlc->attach = fst_attach; + hdlc->xmit = fst_start_xmit; } card->device = pdev; @@ -2549,13 +2472,12 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto init_card_fail; if (card->family == FST_FAMILY_TXU) { - /* - * Allocate a dma buffer for transmit and receives + /* Allocate a dma buffer for transmit and receives */ card->rx_dma_handle_host = dma_alloc_coherent(&card->device->dev, FST_MAX_MTU, &card->rx_dma_handle_card, GFP_KERNEL); - if (card->rx_dma_handle_host == NULL) { + if (!card->rx_dma_handle_host) { pr_err("Could not allocate rx dma buffer\n"); err = -ENOMEM; goto rx_dma_fail; @@ -2563,7 +2485,7 @@ fst_add_one(struct pci_dev *pdev, const struct pci_device_id *ent) card->tx_dma_handle_host = dma_alloc_coherent(&card->device->dev, FST_MAX_MTU, &card->tx_dma_handle_card, GFP_KERNEL); - if (card->tx_dma_handle_host == NULL) { + if (!card->tx_dma_handle_host) { pr_err("Could not allocate tx dma buffer\n"); err = -ENOMEM; goto tx_dma_fail; @@ -2598,8 +2520,7 @@ enable_fail: return err; } -/* - * Cleanup and close down a card +/* Cleanup and close down a card */ static void fst_remove_one(struct pci_dev *pdev) @@ -2611,6 +2532,7 @@ fst_remove_one(struct pci_dev *pdev) for (i = 0; i < card->nports; i++) { struct net_device *dev = port_to_dev(&card->ports[i]); + unregister_hdlc_device(dev); } @@ -2621,8 +2543,7 @@ fst_remove_one(struct pci_dev *pdev) iounmap(card->mem); pci_release_regions(pdev); if (card->family == FST_FAMILY_TXU) { - /* - * Free dma buffers + /* Free dma buffers */ dma_free_coherent(&card->device->dev, FST_MAX_MTU, card->rx_dma_handle_host, diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 7eac6a3e1cde..39f05fabbfa4 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -1171,9 +1171,8 @@ static int ucc_hdlc_probe(struct platform_device *pdev) ut_info->uf_info.irq = irq_of_parse_and_map(np, 0); uhdlc_priv = kzalloc(sizeof(*uhdlc_priv), GFP_KERNEL); - if (!uhdlc_priv) { + if (!uhdlc_priv) return -ENOMEM; - } dev_set_drvdata(&pdev->dev, uhdlc_priv); uhdlc_priv->dev = &pdev->dev; diff --git a/drivers/net/wan/hd64570.c b/drivers/net/wan/hd64570.c index 058e48182838..0d19e39fec86 100644 --- a/drivers/net/wan/hd64570.c +++ b/drivers/net/wan/hd64570.c @@ -47,7 +47,6 @@ #define SCA_INTR_DMAC_RX(node) (node ? 0x20 : 0x02) #define SCA_INTR_DMAC_TX(node) (node ? 0x40 : 0x04) - static inline struct net_device *port_to_dev(port_t *port) { return port->dev; @@ -59,12 +58,18 @@ static inline int sca_intr_status(card_t *card) u8 isr0 = sca_in(ISR0, card); u8 isr1 = sca_in(ISR1, card); - if (isr1 & 0x03) result |= SCA_INTR_DMAC_RX(0); - if (isr1 & 0x0C) result |= SCA_INTR_DMAC_TX(0); - if (isr1 & 0x30) result |= SCA_INTR_DMAC_RX(1); - if (isr1 & 0xC0) result |= SCA_INTR_DMAC_TX(1); - if (isr0 & 0x0F) result |= SCA_INTR_MSCI(0); - if (isr0 & 0xF0) result |= SCA_INTR_MSCI(1); + if (isr1 & 0x03) + result |= SCA_INTR_DMAC_RX(0); + if (isr1 & 0x0C) + result |= SCA_INTR_DMAC_TX(0); + if (isr1 & 0x30) + result |= SCA_INTR_DMAC_RX(1); + if (isr1 & 0xC0) + result |= SCA_INTR_DMAC_TX(1); + if (isr0 & 0x0F) + result |= SCA_INTR_MSCI(0); + if (isr0 & 0xF0) + result |= SCA_INTR_MSCI(1); if (!(result & SCA_INTR_DMAC_TX(0))) if (sca_in(DSR_TX(0), card) & DSR_EOM) @@ -76,7 +81,7 @@ static inline int sca_intr_status(card_t *card) return result; } -static inline port_t* dev_to_port(struct net_device *dev) +static inline port_t *dev_to_port(struct net_device *dev) { return dev_to_hdlc(dev)->priv; } @@ -87,7 +92,6 @@ static inline u16 next_desc(port_t *port, u16 desc, int transmit) : port_to_card(port)->rx_ring_buffers); } - static inline u16 desc_abs_number(port_t *port, u16 desc, int transmit) { u16 rx_buffs = port_to_card(port)->rx_ring_buffers; @@ -98,14 +102,12 @@ static inline u16 desc_abs_number(port_t *port, u16 desc, int transmit) transmit * rx_buffs + desc; } - static inline u16 desc_offset(port_t *port, u16 desc, int transmit) { /* Descriptor offset always fits in 16 bits */ return desc_abs_number(port, desc, transmit) * sizeof(pkt_desc); } - static inline pkt_desc __iomem *desc_address(port_t *port, u16 desc, int transmit) { @@ -118,14 +120,12 @@ static inline pkt_desc __iomem *desc_address(port_t *port, u16 desc, #endif } - static inline u32 buffer_offset(port_t *port, u16 desc, int transmit) { return port_to_card(port)->buff_offset + desc_abs_number(port, desc, transmit) * (u32)HDLC_MAX_MRU; } - static inline void sca_set_carrier(port_t *port) { if (!(sca_in(get_msci(port) + ST3, port_to_card(port)) & ST3_DCD)) { @@ -143,7 +143,6 @@ static inline void sca_set_carrier(port_t *port) } } - static void sca_init_port(port_t *port) { card_t *card = port_to_card(port); @@ -213,13 +212,12 @@ static void sca_init_port(port_t *port) sca_set_carrier(port); } - #ifdef NEED_SCA_MSCI_INTR /* MSCI interrupt service */ static inline void sca_msci_intr(port_t *port) { u16 msci = get_msci(port); - card_t* card = port_to_card(port); + card_t *card = port_to_card(port); u8 stat = sca_in(msci + ST1, card); /* read MSCI ST1 status */ /* Reset MSCI TX underrun and CDCD status bit */ @@ -236,7 +234,6 @@ static inline void sca_msci_intr(port_t *port) } #endif - static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc, u16 rxin) { @@ -265,8 +262,9 @@ static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc, memcpy_fromio(skb->data, winbase(card) + buff, maxlen); openwin(card, page + 1); memcpy_fromio(skb->data + maxlen, winbase(card), len - maxlen); - } else + } else { memcpy_fromio(skb->data, winbase(card) + buff, len); + } #ifndef PAGE0_ALWAYS_MAPPED openwin(card, 0); /* select pkt_desc table page back */ @@ -282,7 +280,6 @@ static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc, netif_rx(skb); } - /* Receive DMA interrupt service */ static inline void sca_rx_intr(port_t *port) { @@ -304,7 +301,7 @@ static inline void sca_rx_intr(port_t *port) pkt_desc __iomem *desc; u32 cda = sca_inw(dmac + CDAL, card); - if ((cda >= desc_off) && (cda < desc_off + sizeof(pkt_desc))) + if (cda >= desc_off && (cda < desc_off + sizeof(pkt_desc))) break; /* No frame received */ desc = desc_address(port, port->rxin, 0); @@ -322,8 +319,9 @@ static inline void sca_rx_intr(port_t *port) dev->stats.rx_crc_errors++; if (stat & ST_RX_EOM) port->rxpart = 0; /* received last fragment */ - } else + } else { sca_rx(card, port, desc, port->rxin); + } /* Set new error descriptor address */ sca_outw(desc_off, dmac + EDAL, card); @@ -334,13 +332,12 @@ static inline void sca_rx_intr(port_t *port) sca_out(DSR_DE, DSR_RX(phy_node(port)), card); } - /* Transmit DMA interrupt service */ static inline void sca_tx_intr(port_t *port) { struct net_device *dev = port_to_dev(port); u16 dmac = get_dmac_tx(port); - card_t* card = port_to_card(port); + card_t *card = port_to_card(port); u8 stat; spin_lock(&port->lock); @@ -356,7 +353,8 @@ static inline void sca_tx_intr(port_t *port) u32 desc_off = desc_offset(port, port->txlast, 1); u32 cda = sca_inw(dmac + CDAL, card); - if ((cda >= desc_off) && (cda < desc_off + sizeof(pkt_desc))) + + if (cda >= desc_off && (cda < desc_off + sizeof(pkt_desc))) break; /* Transmitter is/will_be sending this frame */ desc = desc_address(port, port->txlast, 1); @@ -370,8 +368,7 @@ static inline void sca_tx_intr(port_t *port) spin_unlock(&port->lock); } - -static irqreturn_t sca_intr(int irq, void* dev_id) +static irqreturn_t sca_intr(int irq, void *dev_id) { card_t *card = dev_id; int i; @@ -379,10 +376,11 @@ static irqreturn_t sca_intr(int irq, void* dev_id) int handled = 0; u8 page = sca_get_page(card); - while((stat = sca_intr_status(card)) != 0) { + while ((stat = sca_intr_status(card)) != 0) { handled = 1; for (i = 0; i < 2; i++) { port_t *port = get_port(card, i); + if (port) { if (stat & SCA_INTR_MSCI(i)) sca_msci_intr(port); @@ -400,15 +398,13 @@ static irqreturn_t sca_intr(int irq, void* dev_id) return IRQ_RETVAL(handled); } - static void sca_set_port(port_t *port) { - card_t* card = port_to_card(port); + card_t *card = port_to_card(port); u16 msci = get_msci(port); u8 md2 = sca_in(msci + MD2, card); unsigned int tmc, br = 10, brv = 1024; - if (port->settings.clock_rate > 0) { /* Try lower br for better accuracy*/ do { @@ -417,14 +413,15 @@ static void sca_set_port(port_t *port) /* Baud Rate = CLOCK_BASE / TMC / 2^BR */ tmc = CLOCK_BASE / brv / port->settings.clock_rate; - }while (br > 1 && tmc <= 128); + } while (br > 1 && tmc <= 128); if (tmc < 1) { tmc = 1; br = 0; /* For baud=CLOCK_BASE we use tmc=1 br=0 */ brv = 1; - } else if (tmc > 255) + } else if (tmc > 255) { tmc = 256; /* tmc=0 means 256 - low baud rates */ + } port->settings.clock_rate = CLOCK_BASE / brv / tmc; } else { @@ -450,34 +447,50 @@ static void sca_set_port(port_t *port) md2 &= ~MD2_LOOPBACK; sca_out(md2, msci + MD2, card); - } - static void sca_open(struct net_device *dev) { port_t *port = dev_to_port(dev); - card_t* card = port_to_card(port); + card_t *card = port_to_card(port); u16 msci = get_msci(port); u8 md0, md2; - switch(port->encoding) { - case ENCODING_NRZ: md2 = MD2_NRZ; break; - case ENCODING_NRZI: md2 = MD2_NRZI; break; - case ENCODING_FM_MARK: md2 = MD2_FM_MARK; break; - case ENCODING_FM_SPACE: md2 = MD2_FM_SPACE; break; - default: md2 = MD2_MANCHESTER; + switch (port->encoding) { + case ENCODING_NRZ: + md2 = MD2_NRZ; + break; + case ENCODING_NRZI: + md2 = MD2_NRZI; + break; + case ENCODING_FM_MARK: + md2 = MD2_FM_MARK; + break; + case ENCODING_FM_SPACE: + md2 = MD2_FM_SPACE; + break; + default: + md2 = MD2_MANCHESTER; } if (port->settings.loopback) md2 |= MD2_LOOPBACK; - switch(port->parity) { - case PARITY_CRC16_PR0: md0 = MD0_HDLC | MD0_CRC_16_0; break; - case PARITY_CRC16_PR1: md0 = MD0_HDLC | MD0_CRC_16; break; - case PARITY_CRC16_PR0_CCITT: md0 = MD0_HDLC | MD0_CRC_ITU_0; break; - case PARITY_CRC16_PR1_CCITT: md0 = MD0_HDLC | MD0_CRC_ITU; break; - default: md0 = MD0_HDLC | MD0_CRC_NONE; + switch (port->parity) { + case PARITY_CRC16_PR0: + md0 = MD0_HDLC | MD0_CRC_16_0; + break; + case PARITY_CRC16_PR1: + md0 = MD0_HDLC | MD0_CRC_16; + break; + case PARITY_CRC16_PR0_CCITT: + md0 = MD0_HDLC | MD0_CRC_ITU_0; + break; + case PARITY_CRC16_PR1_CCITT: + md0 = MD0_HDLC | MD0_CRC_ITU; + break; + default: + md0 = MD0_HDLC | MD0_CRC_NONE; } sca_out(CMD_RESET, msci + CMD, card); @@ -494,9 +507,9 @@ static void sca_open(struct net_device *dev) sca_out(0x14, msci + TRC1, card); /* +1=TXRDY/DMA deactiv condition */ /* We're using the following interrupts: - - TXINT (DMAC completed all transmisions, underrun or DCD change) - - all DMA interrupts -*/ + * - TXINT (DMAC completed all transmisions, underrun or DCD change) + * - all DMA interrupts + */ sca_set_carrier(port); /* MSCI TX INT and RX INT A IRQ enable */ @@ -517,11 +530,10 @@ static void sca_open(struct net_device *dev) netif_start_queue(dev); } - static void sca_close(struct net_device *dev) { port_t *port = dev_to_port(dev); - card_t* card = port_to_card(port); + card_t *card = port_to_card(port); /* reset channel */ sca_out(CMD_RESET, get_msci(port) + CMD, port_to_card(port)); @@ -535,7 +547,6 @@ static void sca_close(struct net_device *dev) netif_stop_queue(dev); } - static int sca_attach(struct net_device *dev, unsigned short encoding, unsigned short parity) { @@ -558,7 +569,6 @@ static int sca_attach(struct net_device *dev, unsigned short encoding, return 0; } - #ifdef DEBUG_RINGS static void sca_dump_rings(struct net_device *dev) { @@ -613,7 +623,6 @@ static void sca_dump_rings(struct net_device *dev) } #endif /* DEBUG_RINGS */ - static netdev_tx_t sca_xmit(struct sk_buff *skb, struct net_device *dev) { port_t *port = dev_to_port(dev); @@ -645,8 +654,9 @@ static netdev_tx_t sca_xmit(struct sk_buff *skb, struct net_device *dev) memcpy_toio(winbase(card) + buff, skb->data, maxlen); openwin(card, page + 1); memcpy_toio(winbase(card), skb->data + maxlen, len - maxlen); - } else + } else { memcpy_toio(winbase(card) + buff, skb->data, len); + } #ifndef PAGE0_ALWAYS_MAPPED openwin(card, 0); /* select pkt_desc table page back */ @@ -670,7 +680,6 @@ static netdev_tx_t sca_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - #ifdef NEED_DETECT_RAM static u32 sca_detect_ram(card_t *card, u8 __iomem *rambase, u32 ramsize) { @@ -699,7 +708,6 @@ static u32 sca_detect_ram(card_t *card, u8 __iomem *rambase, u32 ramsize) } #endif /* NEED_DETECT_RAM */ - static void sca_init(card_t *card, int wait_states) { sca_out(wait_states, WCRL, card); /* Wait Control */ diff --git a/drivers/net/wan/hd64572.c b/drivers/net/wan/hd64572.c index 9f60e3969bf8..b89b03a6aba7 100644 --- a/drivers/net/wan/hd64572.c +++ b/drivers/net/wan/hd64572.c @@ -41,20 +41,20 @@ #define NAPI_WEIGHT 16 -#define get_msci(port) (port->chan ? MSCI1_OFFSET : MSCI0_OFFSET) -#define get_dmac_rx(port) (port->chan ? DMAC1RX_OFFSET : DMAC0RX_OFFSET) -#define get_dmac_tx(port) (port->chan ? DMAC1TX_OFFSET : DMAC0TX_OFFSET) +#define get_msci(port) ((port)->chan ? MSCI1_OFFSET : MSCI0_OFFSET) +#define get_dmac_rx(port) ((port)->chan ? DMAC1RX_OFFSET : DMAC0RX_OFFSET) +#define get_dmac_tx(port) ((port)->chan ? DMAC1TX_OFFSET : DMAC0TX_OFFSET) -#define sca_in(reg, card) readb(card->scabase + (reg)) -#define sca_out(value, reg, card) writeb(value, card->scabase + (reg)) -#define sca_inw(reg, card) readw(card->scabase + (reg)) -#define sca_outw(value, reg, card) writew(value, card->scabase + (reg)) -#define sca_inl(reg, card) readl(card->scabase + (reg)) -#define sca_outl(value, reg, card) writel(value, card->scabase + (reg)) +#define sca_in(reg, card) readb((card)->scabase + (reg)) +#define sca_out(value, reg, card) writeb(value, (card)->scabase + (reg)) +#define sca_inw(reg, card) readw((card)->scabase + (reg)) +#define sca_outw(value, reg, card) writew(value, (card)->scabase + (reg)) +#define sca_inl(reg, card) readl((card)->scabase + (reg)) +#define sca_outl(value, reg, card) writel(value, (card)->scabase + (reg)) static int sca_poll(struct napi_struct *napi, int budget); -static inline port_t* dev_to_port(struct net_device *dev) +static inline port_t *dev_to_port(struct net_device *dev) { return dev_to_hdlc(dev)->priv; } @@ -81,14 +81,12 @@ static inline u16 desc_abs_number(port_t *port, u16 desc, int transmit) return port->chan * (rx_buffs + tx_buffs) + transmit * rx_buffs + desc; } - static inline u16 desc_offset(port_t *port, u16 desc, int transmit) { /* Descriptor offset always fits in 16 bits */ return desc_abs_number(port, desc, transmit) * sizeof(pkt_desc); } - static inline pkt_desc __iomem *desc_address(port_t *port, u16 desc, int transmit) { @@ -96,14 +94,12 @@ static inline pkt_desc __iomem *desc_address(port_t *port, u16 desc, desc_offset(port, desc, transmit)); } - static inline u32 buffer_offset(port_t *port, u16 desc, int transmit) { return port->card->buff_offset + desc_abs_number(port, desc, transmit) * (u32)HDLC_MAX_MRU; } - static inline void sca_set_carrier(port_t *port) { if (!(sca_in(get_msci(port) + ST3, port->card) & ST3_DCD)) { @@ -121,7 +117,6 @@ static inline void sca_set_carrier(port_t *port) } } - static void sca_init_port(port_t *port) { card_t *card = port->card; @@ -181,12 +176,11 @@ static void sca_init_port(port_t *port) netif_napi_add(port->netdev, &port->napi, sca_poll, NAPI_WEIGHT); } - /* MSCI interrupt service */ static inline void sca_msci_intr(port_t *port) { u16 msci = get_msci(port); - card_t* card = port->card; + card_t *card = port->card; if (sca_in(msci + ST1, card) & ST1_CDCD) { /* Reset MSCI CDCD status bit */ @@ -195,7 +189,6 @@ static inline void sca_msci_intr(port_t *port) } } - static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc, u16 rxin) { @@ -225,7 +218,6 @@ static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc, netif_receive_skb(skb); } - /* Receive DMA service */ static inline int sca_rx_done(port_t *port, int budget) { @@ -281,12 +273,11 @@ static inline int sca_rx_done(port_t *port, int budget) return received; } - /* Transmit DMA service */ static inline void sca_tx_done(port_t *port) { struct net_device *dev = port->netdev; - card_t* card = port->card; + card_t *card = port->card; u8 stat; unsigned count = 0; @@ -321,7 +312,6 @@ static inline void sca_tx_done(port_t *port) spin_unlock(&port->lock); } - static int sca_poll(struct napi_struct *napi, int budget) { port_t *port = container_of(napi, port_t, napi); @@ -363,15 +353,13 @@ static irqreturn_t sca_intr(int irq, void *dev_id) return IRQ_RETVAL(handled); } - static void sca_set_port(port_t *port) { - card_t* card = port->card; + card_t *card = port->card; u16 msci = get_msci(port); u8 md2 = sca_in(msci + MD2, card); unsigned int tmc, br = 10, brv = 1024; - if (port->settings.clock_rate > 0) { /* Try lower br for better accuracy*/ do { @@ -380,14 +368,15 @@ static void sca_set_port(port_t *port) /* Baud Rate = CLOCK_BASE / TMC / 2^BR */ tmc = CLOCK_BASE / brv / port->settings.clock_rate; - }while (br > 1 && tmc <= 128); + } while (br > 1 && tmc <= 128); if (tmc < 1) { tmc = 1; br = 0; /* For baud=CLOCK_BASE we use tmc=1 br=0 */ brv = 1; - } else if (tmc > 255) + } else if (tmc > 255) { tmc = 256; /* tmc=0 means 256 - low baud rates */ + } port->settings.clock_rate = CLOCK_BASE / brv / tmc; } else { @@ -414,34 +403,50 @@ static void sca_set_port(port_t *port) md2 &= ~MD2_LOOPBACK; sca_out(md2, msci + MD2, card); - } - static void sca_open(struct net_device *dev) { port_t *port = dev_to_port(dev); - card_t* card = port->card; + card_t *card = port->card; u16 msci = get_msci(port); u8 md0, md2; - switch(port->encoding) { - case ENCODING_NRZ: md2 = MD2_NRZ; break; - case ENCODING_NRZI: md2 = MD2_NRZI; break; - case ENCODING_FM_MARK: md2 = MD2_FM_MARK; break; - case ENCODING_FM_SPACE: md2 = MD2_FM_SPACE; break; - default: md2 = MD2_MANCHESTER; + switch (port->encoding) { + case ENCODING_NRZ: + md2 = MD2_NRZ; + break; + case ENCODING_NRZI: + md2 = MD2_NRZI; + break; + case ENCODING_FM_MARK: + md2 = MD2_FM_MARK; + break; + case ENCODING_FM_SPACE: + md2 = MD2_FM_SPACE; + break; + default: + md2 = MD2_MANCHESTER; } if (port->settings.loopback) md2 |= MD2_LOOPBACK; - switch(port->parity) { - case PARITY_CRC16_PR0: md0 = MD0_HDLC | MD0_CRC_16_0; break; - case PARITY_CRC16_PR1: md0 = MD0_HDLC | MD0_CRC_16; break; - case PARITY_CRC32_PR1_CCITT: md0 = MD0_HDLC | MD0_CRC_ITU32; break; - case PARITY_CRC16_PR1_CCITT: md0 = MD0_HDLC | MD0_CRC_ITU; break; - default: md0 = MD0_HDLC | MD0_CRC_NONE; + switch (port->parity) { + case PARITY_CRC16_PR0: + md0 = MD0_HDLC | MD0_CRC_16_0; + break; + case PARITY_CRC16_PR1: + md0 = MD0_HDLC | MD0_CRC_16; + break; + case PARITY_CRC32_PR1_CCITT: + md0 = MD0_HDLC | MD0_CRC_ITU32; + break; + case PARITY_CRC16_PR1_CCITT: + md0 = MD0_HDLC | MD0_CRC_ITU; + break; + default: + md0 = MD0_HDLC | MD0_CRC_NONE; } sca_out(CMD_RESET, msci + CMD, card); @@ -476,7 +481,6 @@ static void sca_open(struct net_device *dev) netif_start_queue(dev); } - static void sca_close(struct net_device *dev) { port_t *port = dev_to_port(dev); @@ -488,7 +492,6 @@ static void sca_close(struct net_device *dev) netif_stop_queue(dev); } - static int sca_attach(struct net_device *dev, unsigned short encoding, unsigned short parity) { @@ -511,7 +514,6 @@ static int sca_attach(struct net_device *dev, unsigned short encoding, return 0; } - #ifdef DEBUG_RINGS static void sca_dump_rings(struct net_device *dev) { @@ -558,7 +560,6 @@ static void sca_dump_rings(struct net_device *dev) } #endif /* DEBUG_RINGS */ - static netdev_tx_t sca_xmit(struct sk_buff *skb, struct net_device *dev) { port_t *port = dev_to_port(dev); @@ -600,7 +601,6 @@ static netdev_tx_t sca_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - static u32 sca_detect_ram(card_t *card, u8 __iomem *rambase, u32 ramsize) { /* Round RAM size to 32 bits, fill from end to start */ @@ -619,7 +619,6 @@ static u32 sca_detect_ram(card_t *card, u8 __iomem *rambase, u32 ramsize) return i; } - static void sca_init(card_t *card, int wait_states) { sca_out(wait_states, WCRL, card); /* Wait Control */ diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c index 1bdd3df0867a..dd6312b69861 100644 --- a/drivers/net/wan/hdlc.c +++ b/drivers/net/wan/hdlc.c @@ -36,8 +36,7 @@ #include #include - -static const char* version = "HDLC support module revision 1.22"; +static const char *version = "HDLC support module revision 1.22"; #undef DEBUG_LINK @@ -74,25 +73,24 @@ netdev_tx_t hdlc_start_xmit(struct sk_buff *skb, struct net_device *dev) return hdlc->xmit(skb, dev); /* call hardware driver directly */ } +EXPORT_SYMBOL(hdlc_start_xmit); static inline void hdlc_proto_start(struct net_device *dev) { hdlc_device *hdlc = dev_to_hdlc(dev); + if (hdlc->proto->start) hdlc->proto->start(dev); } - - static inline void hdlc_proto_stop(struct net_device *dev) { hdlc_device *hdlc = dev_to_hdlc(dev); + if (hdlc->proto->stop) hdlc->proto->stop(dev); } - - static int hdlc_device_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -141,8 +139,6 @@ carrier_exit: return NOTIFY_DONE; } - - /* Must be called by hardware driver when HDLC device is being opened */ int hdlc_open(struct net_device *dev) { @@ -152,11 +148,12 @@ int hdlc_open(struct net_device *dev) hdlc->carrier, hdlc->open); #endif - if (hdlc->proto == NULL) + if (!hdlc->proto) return -ENOSYS; /* no protocol attached */ if (hdlc->proto->open) { int result = hdlc->proto->open(dev); + if (result) return result; } @@ -166,16 +163,16 @@ int hdlc_open(struct net_device *dev) if (hdlc->carrier) { netdev_info(dev, "Carrier detected\n"); hdlc_proto_start(dev); - } else + } else { netdev_info(dev, "No carrier\n"); + } hdlc->open = 1; spin_unlock_irq(&hdlc->state_lock); return 0; } - - +EXPORT_SYMBOL(hdlc_open); /* Must be called by hardware driver when HDLC device is being closed */ void hdlc_close(struct net_device *dev) @@ -197,8 +194,7 @@ void hdlc_close(struct net_device *dev) if (hdlc->proto->close) hdlc->proto->close(dev); } - - +EXPORT_SYMBOL(hdlc_close); int hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -217,12 +213,14 @@ int hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /* Not handled by currently attached protocol (if any) */ while (proto) { - if ((result = proto->ioctl(dev, ifr)) != -EINVAL) + result = proto->ioctl(dev, ifr); + if (result != -EINVAL) return result; proto = proto->next; } return -EINVAL; } +EXPORT_SYMBOL(hdlc_ioctl); static const struct header_ops hdlc_null_ops; @@ -256,12 +254,14 @@ static void hdlc_setup(struct net_device *dev) struct net_device *alloc_hdlcdev(void *priv) { struct net_device *dev; + dev = alloc_netdev(sizeof(struct hdlc_device), "hdlc%d", NET_NAME_UNKNOWN, hdlc_setup); if (dev) dev_to_hdlc(dev)->priv = priv; return dev; } +EXPORT_SYMBOL(alloc_hdlcdev); void unregister_hdlc_device(struct net_device *dev) { @@ -270,8 +270,7 @@ void unregister_hdlc_device(struct net_device *dev) unregister_netdevice(dev); rtnl_unlock(); } - - +EXPORT_SYMBOL(unregister_hdlc_device); int attach_hdlc_protocol(struct net_device *dev, struct hdlc_proto *proto, size_t size) @@ -287,7 +286,7 @@ int attach_hdlc_protocol(struct net_device *dev, struct hdlc_proto *proto, if (size) { dev_to_hdlc(dev)->state = kmalloc(size, GFP_KERNEL); - if (dev_to_hdlc(dev)->state == NULL) { + if (!dev_to_hdlc(dev)->state) { module_put(proto->module); return -ENOBUFS; } @@ -296,7 +295,7 @@ int attach_hdlc_protocol(struct net_device *dev, struct hdlc_proto *proto, return 0; } - +EXPORT_SYMBOL(attach_hdlc_protocol); int detach_hdlc_protocol(struct net_device *dev) { @@ -322,7 +321,7 @@ int detach_hdlc_protocol(struct net_device *dev) return 0; } - +EXPORT_SYMBOL(detach_hdlc_protocol); void register_hdlc_protocol(struct hdlc_proto *proto) { @@ -331,7 +330,7 @@ void register_hdlc_protocol(struct hdlc_proto *proto) first_proto = proto; rtnl_unlock(); } - +EXPORT_SYMBOL(register_hdlc_protocol); void unregister_hdlc_protocol(struct hdlc_proto *proto) { @@ -346,54 +345,38 @@ void unregister_hdlc_protocol(struct hdlc_proto *proto) *p = proto->next; rtnl_unlock(); } - - +EXPORT_SYMBOL(unregister_hdlc_protocol); MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("HDLC support module"); MODULE_LICENSE("GPL v2"); -EXPORT_SYMBOL(hdlc_start_xmit); -EXPORT_SYMBOL(hdlc_open); -EXPORT_SYMBOL(hdlc_close); -EXPORT_SYMBOL(hdlc_ioctl); -EXPORT_SYMBOL(alloc_hdlcdev); -EXPORT_SYMBOL(unregister_hdlc_device); -EXPORT_SYMBOL(register_hdlc_protocol); -EXPORT_SYMBOL(unregister_hdlc_protocol); -EXPORT_SYMBOL(attach_hdlc_protocol); -EXPORT_SYMBOL(detach_hdlc_protocol); - static struct packet_type hdlc_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_HDLC), .func = hdlc_rcv, }; - static struct notifier_block hdlc_notifier = { .notifier_call = hdlc_device_event, }; - static int __init hdlc_module_init(void) { int result; pr_info("%s\n", version); - if ((result = register_netdevice_notifier(&hdlc_notifier)) != 0) + result = register_netdevice_notifier(&hdlc_notifier); + if (result) return result; dev_add_pack(&hdlc_packet_type); return 0; } - - static void __exit hdlc_module_exit(void) { dev_remove_pack(&hdlc_packet_type); unregister_netdevice_notifier(&hdlc_notifier); } - module_init(hdlc_module_init); module_exit(hdlc_module_exit); diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c index cb5898f7d68c..349ca18088e8 100644 --- a/drivers/net/wan/hdlc_cisco.c +++ b/drivers/net/wan/hdlc_cisco.c @@ -28,13 +28,11 @@ #define CISCO_ADDR_REPLY 1 /* Cisco address reply */ #define CISCO_KEEPALIVE_REQ 2 /* Cisco keepalive request */ - struct hdlc_header { u8 address; u8 control; __be16 protocol; -}__packed; - +} __packed; struct cisco_packet { __be32 type; /* code */ @@ -42,11 +40,10 @@ struct cisco_packet { __be32 par2; __be16 rel; /* reliability */ __be32 time; -}__packed; +} __packed; #define CISCO_PACKET_LEN 18 #define CISCO_BIG_PACKET_LEN 20 - struct cisco_state { cisco_proto settings; @@ -59,16 +56,13 @@ struct cisco_state { u32 rxseq; /* RX sequence number */ }; - static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr); - -static inline struct cisco_state* state(hdlc_device *hdlc) +static inline struct cisco_state *state(hdlc_device *hdlc) { return (struct cisco_state *)hdlc->state; } - static int cisco_hard_header(struct sk_buff *skb, struct net_device *dev, u16 type, const void *daddr, const void *saddr, unsigned int len) @@ -79,7 +73,7 @@ static int cisco_hard_header(struct sk_buff *skb, struct net_device *dev, #endif skb_push(skb, sizeof(struct hdlc_header)); - data = (struct hdlc_header*)skb->data; + data = (struct hdlc_header *)skb->data; if (type == CISCO_KEEPALIVE) data->address = CISCO_MULTICAST; else @@ -90,8 +84,6 @@ static int cisco_hard_header(struct sk_buff *skb, struct net_device *dev, return sizeof(struct hdlc_header); } - - static void cisco_keepalive_send(struct net_device *dev, u32 type, __be32 par1, __be32 par2) { @@ -100,13 +92,12 @@ static void cisco_keepalive_send(struct net_device *dev, u32 type, skb = dev_alloc_skb(sizeof(struct hdlc_header) + sizeof(struct cisco_packet)); - if (!skb) { - netdev_warn(dev, "Memory squeeze on %s()\n", __func__); + if (!skb) return; - } + skb_reserve(skb, 4); cisco_hard_header(skb, dev, CISCO_KEEPALIVE, NULL, NULL, 0); - data = (struct cisco_packet*)(skb->data + 4); + data = (struct cisco_packet *)(skb->data + 4); data->type = htonl(type); data->par1 = par1; @@ -124,11 +115,9 @@ static void cisco_keepalive_send(struct net_device *dev, u32 type, dev_queue_xmit(skb); } - - static __be16 cisco_type_trans(struct sk_buff *skb, struct net_device *dev) { - struct hdlc_header *data = (struct hdlc_header*)skb->data; + struct hdlc_header *data = (struct hdlc_header *)skb->data; if (skb->len < sizeof(struct hdlc_header)) return cpu_to_be16(ETH_P_HDLC); @@ -148,13 +137,12 @@ static __be16 cisco_type_trans(struct sk_buff *skb, struct net_device *dev) } } - static int cisco_rx(struct sk_buff *skb) { struct net_device *dev = skb->dev; hdlc_device *hdlc = dev_to_hdlc(dev); struct cisco_state *st = state(hdlc); - struct hdlc_header *data = (struct hdlc_header*)skb->data; + struct hdlc_header *data = (struct hdlc_header *)skb->data; struct cisco_packet *cisco_data; struct in_device *in_dev; __be32 addr, mask; @@ -183,10 +171,10 @@ static int cisco_rx(struct sk_buff *skb) goto rx_error; } - cisco_data = (struct cisco_packet*)(skb->data + sizeof + cisco_data = (struct cisco_packet *)(skb->data + sizeof (struct hdlc_header)); - switch (ntohl (cisco_data->type)) { + switch (ntohl(cisco_data->type)) { case CISCO_ADDR_REQ: /* Stolen from syncppp.c :-) */ rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); @@ -226,6 +214,7 @@ static int cisco_rx(struct sk_buff *skb) st->last_poll = jiffies; if (!st->up) { u32 sec, min, hrs, days; + sec = ntohl(cisco_data->time) / 1000; min = sec / 60; sec -= min * 60; hrs = min / 60; min -= hrs * 60; @@ -253,8 +242,6 @@ rx_error: return NET_RX_DROP; } - - static void cisco_timer(struct timer_list *t) { struct cisco_state *st = from_timer(st, t, timer); @@ -276,8 +263,6 @@ static void cisco_timer(struct timer_list *t) add_timer(&st->timer); } - - static void cisco_start(struct net_device *dev) { hdlc_device *hdlc = dev_to_hdlc(dev); @@ -294,8 +279,6 @@ static void cisco_start(struct net_device *dev) add_timer(&st->timer); } - - static void cisco_stop(struct net_device *dev) { hdlc_device *hdlc = dev_to_hdlc(dev); @@ -310,7 +293,6 @@ static void cisco_stop(struct net_device *dev) spin_unlock_irqrestore(&st->lock, flags); } - static struct hdlc_proto proto = { .start = cisco_start, .stop = cisco_stop, @@ -359,7 +341,8 @@ static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr) new_settings.timeout < 2) return -EINVAL; - result = hdlc->attach(dev, ENCODING_NRZ,PARITY_CRC16_PR1_CCITT); + result = hdlc->attach(dev, ENCODING_NRZ, + PARITY_CRC16_PR1_CCITT); if (result) return result; @@ -381,21 +364,17 @@ static int cisco_ioctl(struct net_device *dev, struct ifreq *ifr) return -EINVAL; } - static int __init mod_init(void) { register_hdlc_protocol(&proto); return 0; } - - static void __exit mod_exit(void) { unregister_hdlc_protocol(&proto); } - module_init(mod_init); module_exit(mod_exit); diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 0720f5f92caa..72250fe0a1df 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -6,16 +6,16 @@ * Copyright (C) 1999 - 2006 Krzysztof Halasa * - Theory of PVC state + Theory of PVC state DCE mode: (exist,new) -> 0,0 when "PVC create" or if "link unreliable" - 0,x -> 1,1 if "link reliable" when sending FULL STATUS - 1,1 -> 1,0 if received FULL STATUS ACK + 0,x -> 1,1 if "link reliable" when sending FULL STATUS + 1,1 -> 1,0 if received FULL STATUS ACK (active) -> 0 when "ifconfig PVC down" or "link unreliable" or "PVC create" - -> 1 when "PVC up" and (exist,new) = 1,0 + -> 1 when "PVC up" and (exist,new) = 1,0 DTE mode: (exist,new,active) = FULL STATUS if "link reliable" @@ -60,7 +60,6 @@ #define NLPID_CCITT_ANSI_LMI 0x08 #define NLPID_CISCO_LMI 0x09 - #define LMI_CCITT_ANSI_DLCI 0 /* LMI DLCI */ #define LMI_CISCO_DLCI 1023 @@ -86,7 +85,6 @@ #define LMI_CCITT_CISCO_LENGTH 13 /* LMI frame lengths */ #define LMI_ANSI_LENGTH 14 - struct fr_hdr { #if defined(__LITTLE_ENDIAN_BITFIELD) unsigned ea1: 1; @@ -111,7 +109,6 @@ struct fr_hdr { #endif } __packed; - struct pvc_device { struct net_device *frad; struct net_device *main; @@ -128,7 +125,7 @@ struct pvc_device { unsigned int fecn: 1; unsigned int becn: 1; unsigned int bandwidth; /* Cisco LMI reporting only */ - }state; + } state; }; struct frad_state { @@ -149,29 +146,24 @@ struct frad_state { u8 rxseq; /* RX sequence number */ }; - static int fr_ioctl(struct net_device *dev, struct ifreq *ifr); - static inline u16 q922_to_dlci(u8 *hdr) { return ((hdr[0] & 0xFC) << 2) | ((hdr[1] & 0xF0) >> 4); } - static inline void dlci_to_q922(u8 *hdr, u16 dlci) { hdr[0] = (dlci >> 2) & 0xFC; hdr[1] = ((dlci << 4) & 0xF0) | 0x01; } - -static inline struct frad_state* state(hdlc_device *hdlc) +static inline struct frad_state *state(hdlc_device *hdlc) { - return(struct frad_state *)(hdlc->state); + return (struct frad_state *)(hdlc->state); } - static inline struct pvc_device *find_pvc(hdlc_device *hdlc, u16 dlci) { struct pvc_device *pvc = state(hdlc)->first_pvc; @@ -187,7 +179,6 @@ static inline struct pvc_device *find_pvc(hdlc_device *hdlc, u16 dlci) return NULL; } - static struct pvc_device *add_pvc(struct net_device *dev, u16 dlci) { hdlc_device *hdlc = dev_to_hdlc(dev); @@ -215,13 +206,11 @@ static struct pvc_device *add_pvc(struct net_device *dev, u16 dlci) return pvc; } - static inline int pvc_is_used(struct pvc_device *pvc) { return pvc->main || pvc->ether; } - static inline void pvc_carrier(int on, struct pvc_device *pvc) { if (on) { @@ -241,7 +230,6 @@ static inline void pvc_carrier(int on, struct pvc_device *pvc) } } - static inline void delete_unused_pvcs(hdlc_device *hdlc) { struct pvc_device **pvc_p = &state(hdlc)->first_pvc; @@ -260,7 +248,6 @@ static inline void delete_unused_pvcs(hdlc_device *hdlc) } } - static inline struct net_device **get_dev_p(struct pvc_device *pvc, int type) { @@ -270,7 +257,6 @@ static inline struct net_device **get_dev_p(struct pvc_device *pvc, return &pvc->main; } - static int fr_hard_header(struct sk_buff *skb, u16 dlci) { if (!skb->dev) { /* Control packets */ @@ -334,8 +320,6 @@ static int fr_hard_header(struct sk_buff *skb, u16 dlci) return 0; } - - static int pvc_open(struct net_device *dev) { struct pvc_device *pvc = dev->ml_priv; @@ -345,6 +329,7 @@ static int pvc_open(struct net_device *dev) if (pvc->open_count++ == 0) { hdlc_device *hdlc = dev_to_hdlc(pvc->frad); + if (state(hdlc)->settings.lmi == LMI_NONE) pvc->state.active = netif_carrier_ok(pvc->frad); @@ -354,14 +339,13 @@ static int pvc_open(struct net_device *dev) return 0; } - - static int pvc_close(struct net_device *dev) { struct pvc_device *pvc = dev->ml_priv; if (--pvc->open_count == 0) { hdlc_device *hdlc = dev_to_hdlc(pvc->frad); + if (state(hdlc)->settings.lmi == LMI_NONE) pvc->state.active = 0; @@ -373,8 +357,6 @@ static int pvc_close(struct net_device *dev) return 0; } - - static int pvc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct pvc_device *pvc = dev->ml_priv; @@ -465,15 +447,12 @@ static inline void fr_log_dlci_active(struct pvc_device *pvc) pvc->state.active ? "active" : "inactive"); } - - static inline u8 fr_lmi_nextseq(u8 x) { x++; return x ? x : 1; } - static void fr_lmi_send(struct net_device *dev, int fullrep) { hdlc_device *hdlc = dev_to_hdlc(dev); @@ -495,17 +474,16 @@ static void fr_lmi_send(struct net_device *dev, int fullrep) } skb = dev_alloc_skb(len); - if (!skb) { - netdev_warn(dev, "Memory squeeze on fr_lmi_send()\n"); + if (!skb) return; - } + memset(skb->data, 0, len); skb_reserve(skb, 4); - if (lmi == LMI_CISCO) { + if (lmi == LMI_CISCO) fr_hard_header(skb, LMI_CISCO_DLCI); - } else { + else fr_hard_header(skb, LMI_CCITT_ANSI_DLCI); - } + data = skb_tail_pointer(skb); data[i++] = LMI_CALLREF; data[i++] = dce ? LMI_STATUS : LMI_STATUS_ENQUIRY; @@ -569,8 +547,6 @@ static void fr_lmi_send(struct net_device *dev, int fullrep) dev_queue_xmit(skb); } - - static void fr_set_link_state(int reliable, struct net_device *dev) { hdlc_device *hdlc = dev_to_hdlc(dev); @@ -603,7 +579,6 @@ static void fr_set_link_state(int reliable, struct net_device *dev) } } - static void fr_timer(struct timer_list *t) { struct frad_state *st = from_timer(st, t, timer); @@ -637,10 +612,10 @@ static void fr_timer(struct timer_list *t) fr_set_link_state(reliable, dev); } - if (state(hdlc)->settings.dce) + if (state(hdlc)->settings.dce) { state(hdlc)->timer.expires = jiffies + state(hdlc)->settings.t392 * HZ; - else { + } else { if (state(hdlc)->n391cnt) state(hdlc)->n391cnt--; @@ -655,7 +630,6 @@ static void fr_timer(struct timer_list *t) add_timer(&state(hdlc)->timer); } - static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb) { hdlc_device *hdlc = dev_to_hdlc(dev); @@ -696,8 +670,9 @@ static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb) return 1; } i = 7; - } else + } else { i = 6; + } if (skb->data[i] != (lmi == LMI_CCITT ? LMI_CCITT_REPTYPE : LMI_ANSI_CISCO_REPTYPE)) { @@ -814,8 +789,8 @@ static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb) } i++; - new = !! (skb->data[i + 2] & 0x08); - active = !! (skb->data[i + 2] & 0x02); + new = !!(skb->data[i + 2] & 0x08); + active = !!(skb->data[i + 2] & 0x02); if (lmi == LMI_CISCO) { dlci = (skb->data[i] << 8) | skb->data[i + 1]; bw = (skb->data[i + 3] << 16) | @@ -962,8 +937,8 @@ static int fr_rx(struct sk_buff *skb) pvc->state.becn ^= 1; } - - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) { frad->stats.rx_dropped++; return NET_RX_DROP; } @@ -1018,8 +993,6 @@ rx_drop: return NET_RX_DROP; } - - static void fr_start(struct net_device *dev) { hdlc_device *hdlc = dev_to_hdlc(dev); @@ -1040,11 +1013,11 @@ static void fr_start(struct net_device *dev) /* First poll after 1 s */ state(hdlc)->timer.expires = jiffies + HZ; add_timer(&state(hdlc)->timer); - } else + } else { fr_set_link_state(1, dev); + } } - static void fr_stop(struct net_device *dev) { hdlc_device *hdlc = dev_to_hdlc(dev); @@ -1056,7 +1029,6 @@ static void fr_stop(struct net_device *dev) fr_set_link_state(0, dev); } - static void fr_close(struct net_device *dev) { hdlc_device *hdlc = dev_to_hdlc(dev); @@ -1071,7 +1043,6 @@ static void fr_close(struct net_device *dev) } } - static void pvc_setup(struct net_device *dev) { dev->type = ARPHRD_DLCI; @@ -1095,7 +1066,8 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type) struct net_device *dev; int used; - if ((pvc = add_pvc(frad, dlci)) == NULL) { + pvc = add_pvc(frad, dlci); + if (!pvc) { netdev_warn(frad, "Memory squeeze on fr_add_pvc()\n"); return -ENOBUFS; } @@ -1121,7 +1093,7 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type) dev->priv_flags &= ~IFF_TX_SKB_SHARING; eth_hw_addr_random(dev); } else { - *(__be16*)dev->dev_addr = htons(dlci); + *(__be16 *)dev->dev_addr = htons(dlci); dlci_to_q922(dev->broadcast, dlci); } dev->netdev_ops = &pvc_ops; @@ -1147,17 +1119,17 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type) return 0; } - - static int fr_del_pvc(hdlc_device *hdlc, unsigned int dlci, int type) { struct pvc_device *pvc; struct net_device *dev; - if ((pvc = find_pvc(hdlc, dlci)) == NULL) + pvc = find_pvc(hdlc, dlci); + if (!pvc) return -ENOENT; - if ((dev = *get_dev_p(pvc, type)) == NULL) + dev = *get_dev_p(pvc, type); + if (!dev) return -ENOENT; if (dev->flags & IFF_UP) @@ -1174,12 +1146,11 @@ static int fr_del_pvc(hdlc_device *hdlc, unsigned int dlci, int type) return 0; } - - static void fr_destroy(struct net_device *frad) { hdlc_device *hdlc = dev_to_hdlc(frad); struct pvc_device *pvc = state(hdlc)->first_pvc; + state(hdlc)->first_pvc = NULL; /* All PVCs destroyed */ state(hdlc)->dce_pvc_count = 0; state(hdlc)->dce_changed = 1; @@ -1198,7 +1169,6 @@ static void fr_destroy(struct net_device *frad) } } - static struct hdlc_proto proto = { .close = fr_close, .start = fr_start, @@ -1209,7 +1179,6 @@ static struct hdlc_proto proto = { .module = THIS_MODULE, }; - static int fr_ioctl(struct net_device *dev, struct ifreq *ifr) { fr_proto __user *fr_s = ifr->ifr_settings.ifs_ifsu.fr; @@ -1259,7 +1228,8 @@ static int fr_ioctl(struct net_device *dev, struct ifreq *ifr) new_settings.dce != 1)) return -EINVAL; - result=hdlc->attach(dev, ENCODING_NRZ,PARITY_CRC16_PR1_CCITT); + result = hdlc->attach(dev, ENCODING_NRZ, + PARITY_CRC16_PR1_CCITT); if (result) return result; @@ -1309,20 +1279,17 @@ static int fr_ioctl(struct net_device *dev, struct ifreq *ifr) return -EINVAL; } - static int __init mod_init(void) { register_hdlc_protocol(&proto); return 0; } - static void __exit mod_exit(void) { unregister_hdlc_protocol(&proto); } - module_init(mod_init); module_exit(mod_exit); diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index 261b53fc8e04..834be2ae3e9e 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -41,6 +41,7 @@ static const char *const code_names[CP_CODES] = { "0", "ConfReq", "ConfAck", "ConfNak", "ConfRej", "TermReq", "TermAck", "CodeRej", "ProtoRej", "EchoReq", "EchoReply", "Discard" }; + static char debug_buffer[64 + 3 * DEBUG_CP]; #endif @@ -58,7 +59,6 @@ struct cp_header { __be16 len; }; - struct proto { struct net_device *dev; struct timer_list timer; @@ -91,6 +91,7 @@ static const char *const state_names[STATES] = { "Closed", "Stopped", "Stopping", "ReqSent", "AckRecv", "AckSent", "Opened" }; + static const char *const event_names[EVENTS] = { "Start", "Stop", "TO+", "TO-", "RCR+", "RCR-", "RCA", "RCN", "RTR", "RTA", "RUC", "RXJ+", "RXJ-" @@ -101,12 +102,12 @@ static struct sk_buff_head tx_queue; /* used when holding the spin lock */ static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr); -static inline struct ppp* get_ppp(struct net_device *dev) +static inline struct ppp *get_ppp(struct net_device *dev) { return (struct ppp *)dev_to_hdlc(dev)->state; } -static inline struct proto* get_proto(struct net_device *dev, u16 pid) +static inline struct proto *get_proto(struct net_device *dev, u16 pid) { struct ppp *ppp = get_ppp(dev); @@ -122,7 +123,7 @@ static inline struct proto* get_proto(struct net_device *dev, u16 pid) } } -static inline const char* proto_name(u16 pid) +static inline const char *proto_name(u16 pid) { switch (pid) { case PID_LCP: @@ -138,7 +139,7 @@ static inline const char* proto_name(u16 pid) static __be16 ppp_type_trans(struct sk_buff *skb, struct net_device *dev) { - struct hdlc_header *data = (struct hdlc_header*)skb->data; + struct hdlc_header *data = (struct hdlc_header *)skb->data; if (skb->len < sizeof(struct hdlc_header)) return htons(ETH_P_HDLC); @@ -160,7 +161,6 @@ static __be16 ppp_type_trans(struct sk_buff *skb, struct net_device *dev) } } - static int ppp_hard_header(struct sk_buff *skb, struct net_device *dev, u16 type, const void *daddr, const void *saddr, unsigned int len) @@ -171,7 +171,7 @@ static int ppp_hard_header(struct sk_buff *skb, struct net_device *dev, #endif skb_push(skb, sizeof(struct hdlc_header)); - data = (struct hdlc_header*)skb->data; + data = (struct hdlc_header *)skb->data; data->address = HDLC_ADDR_ALLSTATIONS; data->control = HDLC_CTRL_UI; @@ -193,10 +193,10 @@ static int ppp_hard_header(struct sk_buff *skb, struct net_device *dev, return sizeof(struct hdlc_header); } - static void ppp_tx_flush(void) { struct sk_buff *skb; + while ((skb = skb_dequeue(&tx_queue)) != NULL) dev_queue_xmit(skb); } @@ -219,10 +219,9 @@ static void ppp_tx_cp(struct net_device *dev, u16 pid, u8 code, skb = dev_alloc_skb(sizeof(struct hdlc_header) + sizeof(struct cp_header) + magic_len + len); - if (!skb) { - netdev_warn(dev, "out of memory in ppp_tx_cp()\n"); + if (!skb) return; - } + skb_reserve(skb, sizeof(struct hdlc_header)); cp = skb_put(skb, sizeof(struct cp_header)); @@ -256,7 +255,6 @@ static void ppp_tx_cp(struct net_device *dev, u16 pid, u8 code, skb_queue_tail(&tx_queue, skb); } - /* State transition table (compare STD-51) Events Actions TO+ = Timeout with counter > 0 irc = Initialize-Restart-Count @@ -294,7 +292,6 @@ static int cp_table[EVENTS][STATES] = { { 0 , 1 , 1 , 1 , 1 , 1 ,IRC|STR|2}, /* RXJ- */ }; - /* SCA: RCR+ must supply id, len and data SCN: RCR- must supply code, id, len and data STA: RTR must supply id @@ -369,7 +366,6 @@ static void ppp_cp_event(struct net_device *dev, u16 pid, u16 event, u8 code, #endif } - static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id, unsigned int req_len, const u8 *data) { @@ -378,7 +374,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id, u8 *out; unsigned int len = req_len, nak_len = 0, rej_len = 0; - if (!(out = kmalloc(len, GFP_ATOMIC))) { + out = kmalloc(len, GFP_ATOMIC); + if (!out) { dev->stats.rx_dropped++; return; /* out of memory, ignore CR packet */ } @@ -435,7 +432,7 @@ err_out: static int ppp_rx(struct sk_buff *skb) { - struct hdlc_header *hdr = (struct hdlc_header*)skb->data; + struct hdlc_header *hdr = (struct hdlc_header *)skb->data; struct net_device *dev = skb->dev; struct ppp *ppp = get_ppp(dev); struct proto *proto; @@ -493,7 +490,7 @@ static int ppp_rx(struct sk_buff *skb) if (pid == PID_LCP) switch (cp->code) { case LCP_PROTO_REJ: - pid = ntohs(*(__be16*)skb->data); + pid = ntohs(*(__be16 *)skb->data); if (pid == PID_LCP || pid == PID_IPCP || pid == PID_IPV6CP) ppp_cp_event(dev, pid, RXJ_BAD, 0, 0, @@ -615,7 +612,6 @@ static void ppp_timer(struct timer_list *t) ppp_tx_flush(); } - static void ppp_start(struct net_device *dev) { struct ppp *ppp = get_ppp(dev); @@ -623,6 +619,7 @@ static void ppp_start(struct net_device *dev) for (i = 0; i < IDX_COUNT; i++) { struct proto *proto = &ppp->protos[i]; + proto->dev = dev; timer_setup(&proto->timer, ppp_timer, 0); proto->state = CLOSED; @@ -680,7 +677,8 @@ static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr) /* no settable parameters */ - result = hdlc->attach(dev, ENCODING_NRZ,PARITY_CRC16_PR1_CCITT); + result = hdlc->attach(dev, ENCODING_NRZ, + PARITY_CRC16_PR1_CCITT); if (result) return result; @@ -707,7 +705,6 @@ static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr) return -EINVAL; } - static int __init mod_init(void) { skb_queue_head_init(&tx_queue); @@ -720,7 +717,6 @@ static void __exit mod_exit(void) unregister_hdlc_protocol(&proto); } - module_init(mod_init); module_exit(mod_exit); diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index ba8c36c7ea91..d2bf72bf3bd7 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -56,10 +56,8 @@ static void x25_connect_disconnect(struct net_device *dev, int reason, int code) unsigned char *ptr; skb = __dev_alloc_skb(1, GFP_ATOMIC | __GFP_NOMEMALLOC); - if (!skb) { - netdev_err(dev, "out of memory\n"); + if (!skb) return; - } ptr = skb_put(skb, 1); *ptr = code; @@ -70,22 +68,16 @@ static void x25_connect_disconnect(struct net_device *dev, int reason, int code) tasklet_schedule(&x25st->rx_tasklet); } - - static void x25_connected(struct net_device *dev, int reason) { x25_connect_disconnect(dev, reason, X25_IFACE_CONNECT); } - - static void x25_disconnected(struct net_device *dev, int reason) { x25_connect_disconnect(dev, reason, X25_IFACE_DISCONNECT); } - - static int x25_data_indication(struct net_device *dev, struct sk_buff *skb) { struct x25_state *x25st = state(dev_to_hdlc(dev)); @@ -108,8 +100,6 @@ static int x25_data_indication(struct net_device *dev, struct sk_buff *skb) return NET_RX_SUCCESS; } - - static void x25_data_transmit(struct net_device *dev, struct sk_buff *skb) { hdlc_device *hdlc = dev_to_hdlc(dev); @@ -123,8 +113,6 @@ static void x25_data_transmit(struct net_device *dev, struct sk_buff *skb) hdlc->xmit(skb, dev); /* Ignore return value :-( */ } - - static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) { hdlc_device *hdlc = dev_to_hdlc(dev); @@ -149,13 +137,15 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) switch (skb->data[0]) { case X25_IFACE_DATA: /* Data to be transmitted */ skb_pull(skb, 1); - if ((result = lapb_data_request(dev, skb)) != LAPB_OK) + result = lapb_data_request(dev, skb); + if (result != LAPB_OK) dev_kfree_skb(skb); spin_unlock_bh(&x25st->up_lock); return NETDEV_TX_OK; case X25_IFACE_CONNECT: - if ((result = lapb_connect_request(dev))!= LAPB_OK) { + result = lapb_connect_request(dev); + if (result != LAPB_OK) { if (result == LAPB_CONNECTED) /* Send connect confirm. msg to level 3 */ x25_connected(dev, 0); @@ -166,7 +156,8 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) break; case X25_IFACE_DISCONNECT: - if ((result = lapb_disconnect_request(dev)) != LAPB_OK) { + result = lapb_disconnect_request(dev); + if (result != LAPB_OK) { if (result == LAPB_NOTCONNECTED) /* Send disconnect confirm. msg to level 3 */ x25_disconnected(dev, 0); @@ -185,8 +176,6 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - - static int x25_open(struct net_device *dev) { static const struct lapb_register_struct cb = { @@ -232,8 +221,6 @@ static int x25_open(struct net_device *dev) return 0; } - - static void x25_close(struct net_device *dev) { hdlc_device *hdlc = dev_to_hdlc(dev); @@ -247,15 +234,14 @@ static void x25_close(struct net_device *dev) tasklet_kill(&x25st->rx_tasklet); } - - static int x25_rx(struct sk_buff *skb) { struct net_device *dev = skb->dev; hdlc_device *hdlc = dev_to_hdlc(dev); struct x25_state *x25st = state(hdlc); - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) { dev->stats.rx_dropped++; return NET_RX_DROP; } @@ -279,7 +265,6 @@ static int x25_rx(struct sk_buff *skb) return NET_RX_DROP; } - static struct hdlc_proto proto = { .open = x25_open, .close = x25_close, @@ -289,7 +274,6 @@ static struct hdlc_proto proto = { .module = THIS_MODULE, }; - static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) { x25_hdlc_proto __user *x25_s = ifr->ifr_settings.ifs_ifsu.x25; @@ -326,35 +310,36 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) new_settings.t1 = 3; new_settings.t2 = 1; new_settings.n2 = 10; - } - else { + } else { if (copy_from_user(&new_settings, x25_s, size)) return -EFAULT; if ((new_settings.dce != 0 && - new_settings.dce != 1) || - (new_settings.modulo != 8 && - new_settings.modulo != 128) || - new_settings.window < 1 || - (new_settings.modulo == 8 && - new_settings.window > 7) || - (new_settings.modulo == 128 && - new_settings.window > 127) || - new_settings.t1 < 1 || - new_settings.t1 > 255 || - new_settings.t2 < 1 || - new_settings.t2 > 255 || - new_settings.n2 < 1 || - new_settings.n2 > 255) + new_settings.dce != 1) || + (new_settings.modulo != 8 && + new_settings.modulo != 128) || + new_settings.window < 1 || + (new_settings.modulo == 8 && + new_settings.window > 7) || + (new_settings.modulo == 128 && + new_settings.window > 127) || + new_settings.t1 < 1 || + new_settings.t1 > 255 || + new_settings.t2 < 1 || + new_settings.t2 > 255 || + new_settings.n2 < 1 || + new_settings.n2 > 255) return -EINVAL; } - result=hdlc->attach(dev, ENCODING_NRZ,PARITY_CRC16_PR1_CCITT); + result = hdlc->attach(dev, ENCODING_NRZ, + PARITY_CRC16_PR1_CCITT); if (result) return result; - if ((result = attach_hdlc_protocol(dev, &proto, - sizeof(struct x25_state)))) + result = attach_hdlc_protocol(dev, &proto, + sizeof(struct x25_state)); + if (result) return result; memcpy(&state(hdlc)->settings, &new_settings, size); @@ -380,21 +365,17 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) return -EINVAL; } - static int __init mod_init(void) { register_hdlc_protocol(&proto); return 0; } - - static void __exit mod_exit(void) { unregister_hdlc_protocol(&proto); } - module_init(mod_init); module_exit(mod_exit); diff --git a/drivers/net/wan/hostess_sv11.c b/drivers/net/wan/hostess_sv11.c index 6c05c4c8914a..fd61a7cc4fdf 100644 --- a/drivers/net/wan/hostess_sv11.c +++ b/drivers/net/wan/hostess_sv11.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/* - * Comtrol SV11 card driver +/* Comtrol SV11 card driver * * This is a slightly odd Z85230 synchronous driver. All you need to * know basically is @@ -9,7 +8,7 @@ * * It supports DMA using two DMA channels in SYNC mode. The driver doesn't * use these facilities - * + * * The control port is at io+1, the data at io+3 and turning off the DMA * is done by writing 0 to io+4 * @@ -44,17 +43,15 @@ static int dma; -/* - * Network driver support routines +/* Network driver support routines */ -static inline struct z8530_dev* dev_to_sv(struct net_device *dev) +static inline struct z8530_dev *dev_to_sv(struct net_device *dev) { return (struct z8530_dev *)dev_to_hdlc(dev)->priv; } -/* - * Frame receive. Simple for our card as we do HDLC and there +/* Frame receive. Simple for our card as we do HDLC and there * is no funny garbage involved */ @@ -65,15 +62,13 @@ static void hostess_input(struct z8530_channel *c, struct sk_buff *skb) skb->protocol = hdlc_type_trans(skb, c->netdevice); skb_reset_mac_header(skb); skb->dev = c->netdevice; - /* - * Send it to the PPP layer. We don't have time to process + /* Send it to the PPP layer. We don't have time to process * it right now. */ netif_rx(skb); } -/* - * We've been placed in the UP state +/* We've been placed in the UP state */ static int hostess_open(struct net_device *d) @@ -81,19 +76,18 @@ static int hostess_open(struct net_device *d) struct z8530_dev *sv11 = dev_to_sv(d); int err = -1; - /* - * Link layer up + /* Link layer up */ switch (dma) { - case 0: - err = z8530_sync_open(d, &sv11->chanA); - break; - case 1: - err = z8530_sync_dma_open(d, &sv11->chanA); - break; - case 2: - err = z8530_sync_txdma_open(d, &sv11->chanA); - break; + case 0: + err = z8530_sync_open(d, &sv11->chanA); + break; + case 1: + err = z8530_sync_dma_open(d, &sv11->chanA); + break; + case 2: + err = z8530_sync_txdma_open(d, &sv11->chanA); + break; } if (err) @@ -102,15 +96,15 @@ static int hostess_open(struct net_device *d) err = hdlc_open(d); if (err) { switch (dma) { - case 0: - z8530_sync_close(d, &sv11->chanA); - break; - case 1: - z8530_sync_dma_close(d, &sv11->chanA); - break; - case 2: - z8530_sync_txdma_close(d, &sv11->chanA); - break; + case 0: + z8530_sync_close(d, &sv11->chanA); + break; + case 1: + z8530_sync_dma_close(d, &sv11->chanA); + break; + case 2: + z8530_sync_txdma_close(d, &sv11->chanA); + break; } return err; } @@ -127,8 +121,7 @@ static int hostess_open(struct net_device *d) static int hostess_close(struct net_device *d) { struct z8530_dev *sv11 = dev_to_sv(d); - /* - * Discard new frames + /* Discard new frames */ sv11->chanA.rx_function = z8530_null_rx; @@ -136,32 +129,29 @@ static int hostess_close(struct net_device *d) netif_stop_queue(d); switch (dma) { - case 0: - z8530_sync_close(d, &sv11->chanA); - break; - case 1: - z8530_sync_dma_close(d, &sv11->chanA); - break; - case 2: - z8530_sync_txdma_close(d, &sv11->chanA); - break; + case 0: + z8530_sync_close(d, &sv11->chanA); + break; + case 1: + z8530_sync_dma_close(d, &sv11->chanA); + break; + case 2: + z8530_sync_txdma_close(d, &sv11->chanA); + break; } return 0; } static int hostess_ioctl(struct net_device *d, struct ifreq *ifr, int cmd) { - /* struct z8530_dev *sv11=dev_to_sv(d); - z8530_ioctl(d,&sv11->chanA,ifr,cmd) */ return hdlc_ioctl(d, ifr, cmd); } -/* - * Passed network frames, fire them downwind. +/* Passed network frames, fire them downwind. */ static netdev_tx_t hostess_queue_xmit(struct sk_buff *skb, - struct net_device *d) + struct net_device *d) { return z8530_queue_xmit(&dev_to_sv(d)->chanA, skb); } @@ -174,8 +164,7 @@ static int hostess_attach(struct net_device *dev, unsigned short encoding, return -EINVAL; } -/* - * Description block for a Comtrol Hostess SV11 card +/* Description block for a Comtrol Hostess SV11 card */ static const struct net_device_ops hostess_ops = { @@ -189,8 +178,7 @@ static struct z8530_dev *sv11_init(int iobase, int irq) { struct z8530_dev *sv; struct net_device *netdev; - /* - * Get the needed I/O space + /* Get the needed I/O space */ if (!request_region(iobase, 8, "Comtrol SV11")) { @@ -202,8 +190,7 @@ static struct z8530_dev *sv11_init(int iobase, int irq) if (!sv) goto err_kzalloc; - /* - * Stuff in the I/O addressing + /* Stuff in the I/O addressing */ sv->active = 0; @@ -218,7 +205,8 @@ static struct z8530_dev *sv11_init(int iobase, int irq) outb(0, iobase + 4); /* DMA off */ /* We want a fast IRQ for this device. Actually we'd like an even faster - IRQ ;) - This is one driver RtLinux is made for */ + * IRQ ;) - This is one driver RtLinux is made for + */ if (request_irq(irq, z8530_interrupt, 0, "Hostess SV11", sv) < 0) { @@ -232,8 +220,7 @@ static struct z8530_dev *sv11_init(int iobase, int irq) sv->chanB.dev = sv; if (dma) { - /* - * You can have DMA off or 1 and 3 thats the lot + /* You can have DMA off or 1 and 3 thats the lot * on the Comtrol. */ sv->chanA.txdma = 3; @@ -248,11 +235,11 @@ static struct z8530_dev *sv11_init(int iobase, int irq) } /* Kill our private IRQ line the hostess can end up chattering - until the configuration is set */ + * until the configuration is set + */ disable_irq(irq); - /* - * Begin normal initialise + /* Begin normal initialise */ if (z8530_init(sv)) { @@ -268,8 +255,7 @@ static struct z8530_dev *sv11_init(int iobase, int irq) enable_irq(irq); - /* - * Now we can take the IRQ + /* Now we can take the IRQ */ sv->chanA.netdevice = netdev = alloc_hdlcdev(sv); @@ -340,7 +326,8 @@ static struct z8530_dev *sv11_unit; int init_module(void) { - if ((sv11_unit = sv11_init(io, irq)) == NULL) + sv11_unit = sv11_init(io, irq); + if (!sv11_unit) return -ENODEV; return 0; } diff --git a/drivers/net/wan/ixp4xx_hss.c b/drivers/net/wan/ixp4xx_hss.c index ecea09fd21cb..e97521138f7e 100644 --- a/drivers/net/wan/ixp4xx_hss.c +++ b/drivers/net/wan/ixp4xx_hss.c @@ -83,7 +83,6 @@ #define PKT_HDLC_CRC_32 0x2 /* default = CRC-16 */ #define PKT_HDLC_MSB_ENDIAN 0x4 /* default = LE */ - /* hss_config, PCRs */ /* Frame sync sampling, default = active low */ #define PCR_FRM_SYNC_ACTIVE_HIGH 0x40000000 @@ -150,26 +149,24 @@ /* HSS number, default = 0 (first) */ #define CCR_SECOND_HSS 0x01000000 - /* hss_config, clkCR: main:10, num:10, denom:12 */ -#define CLK42X_SPEED_EXP ((0x3FF << 22) | ( 2 << 12) | 15) /*65 KHz*/ +#define CLK42X_SPEED_EXP ((0x3FF << 22) | (2 << 12) | 15) /*65 KHz*/ -#define CLK42X_SPEED_512KHZ (( 130 << 22) | ( 2 << 12) | 15) -#define CLK42X_SPEED_1536KHZ (( 43 << 22) | ( 18 << 12) | 47) -#define CLK42X_SPEED_1544KHZ (( 43 << 22) | ( 33 << 12) | 192) -#define CLK42X_SPEED_2048KHZ (( 32 << 22) | ( 34 << 12) | 63) -#define CLK42X_SPEED_4096KHZ (( 16 << 22) | ( 34 << 12) | 127) -#define CLK42X_SPEED_8192KHZ (( 8 << 22) | ( 34 << 12) | 255) +#define CLK42X_SPEED_512KHZ ((130 << 22) | (2 << 12) | 15) +#define CLK42X_SPEED_1536KHZ ((43 << 22) | (18 << 12) | 47) +#define CLK42X_SPEED_1544KHZ ((43 << 22) | (33 << 12) | 192) +#define CLK42X_SPEED_2048KHZ ((32 << 22) | (34 << 12) | 63) +#define CLK42X_SPEED_4096KHZ ((16 << 22) | (34 << 12) | 127) +#define CLK42X_SPEED_8192KHZ ((8 << 22) | (34 << 12) | 255) -#define CLK46X_SPEED_512KHZ (( 130 << 22) | ( 24 << 12) | 127) -#define CLK46X_SPEED_1536KHZ (( 43 << 22) | (152 << 12) | 383) -#define CLK46X_SPEED_1544KHZ (( 43 << 22) | ( 66 << 12) | 385) -#define CLK46X_SPEED_2048KHZ (( 32 << 22) | (280 << 12) | 511) -#define CLK46X_SPEED_4096KHZ (( 16 << 22) | (280 << 12) | 1023) -#define CLK46X_SPEED_8192KHZ (( 8 << 22) | (280 << 12) | 2047) +#define CLK46X_SPEED_512KHZ ((130 << 22) | (24 << 12) | 127) +#define CLK46X_SPEED_1536KHZ ((43 << 22) | (152 << 12) | 383) +#define CLK46X_SPEED_1544KHZ ((43 << 22) | (66 << 12) | 385) +#define CLK46X_SPEED_2048KHZ ((32 << 22) | (280 << 12) | 511) +#define CLK46X_SPEED_4096KHZ ((16 << 22) | (280 << 12) | 1023) +#define CLK46X_SPEED_8192KHZ ((8 << 22) | (280 << 12) | 2047) -/* - * HSS_CONFIG_CLOCK_CR register consists of 3 parts: +/* HSS_CONFIG_CLOCK_CR register consists of 3 parts: * A (10 bits), B (10 bits) and C (12 bits). * IXP42x HSS clock generator operation (verified with an oscilloscope): * Each clock bit takes 7.5 ns (1 / 133.xx MHz). @@ -208,7 +205,6 @@ #define HSS_CONFIG_TX_LUT 0x18 /* channel look-up tables */ #define HSS_CONFIG_RX_LUT 0x38 - /* NPE command codes */ /* writes the ConfigWord value to the location specified by offset */ #define PORT_CONFIG_WRITE 0x40 @@ -220,7 +216,8 @@ #define PORT_ERROR_READ 0x42 /* triggers the NPE to reset internal status and enable the HssPacketized - operation for the flow specified by pPipe */ + * operation for the flow specified by pPipe + */ #define PKT_PIPE_FLOW_ENABLE 0x50 #define PKT_PIPE_FLOW_DISABLE 0x51 #define PKT_NUM_PIPES_WRITE 0x52 @@ -235,12 +232,12 @@ #define ERR_HDLC_ALIGN 2 /* HDLC alignment error */ #define ERR_HDLC_FCS 3 /* HDLC Frame Check Sum error */ #define ERR_RXFREE_Q_EMPTY 4 /* RX-free queue became empty while receiving - this packet (if buf_len < pkt_len) */ + * this packet (if buf_len < pkt_len) + */ #define ERR_HDLC_TOO_LONG 5 /* HDLC frame size too long */ #define ERR_HDLC_ABORT 6 /* abort sequence received */ #define ERR_DISCONNECTING 7 /* disconnect is in progress */ - #ifdef __ARMEB__ typedef struct sk_buff buffer_t; #define free_buffer dev_kfree_skb @@ -308,7 +305,6 @@ struct desc { u32 __reserved1[4]; }; - #define rx_desc_phys(port, n) ((port)->desc_tab_phys + \ (n) * sizeof(struct desc)) #define rx_desc_ptr(port, n) (&(port)->desc_tab[n]) @@ -327,7 +323,7 @@ static DEFINE_SPINLOCK(npe_lock); static const struct { int tx, txdone, rx, rxfree; -}queue_ids[2] = {{HSS0_PKT_TX0_QUEUE, HSS0_PKT_TXDONE_QUEUE, HSS0_PKT_RX_QUEUE, +} queue_ids[2] = {{HSS0_PKT_TX0_QUEUE, HSS0_PKT_TXDONE_QUEUE, HSS0_PKT_RX_QUEUE, HSS0_PKT_RXFREE0_QUEUE}, {HSS1_PKT_TX0_QUEUE, HSS1_PKT_TXDONE_QUEUE, HSS1_PKT_RX_QUEUE, HSS1_PKT_RXFREE0_QUEUE}, @@ -337,7 +333,7 @@ static const struct { * utility functions ****************************************************************************/ -static inline struct port* dev_to_port(struct net_device *dev) +static inline struct port *dev_to_port(struct net_device *dev) { return dev_to_hdlc(dev)->priv; } @@ -346,6 +342,7 @@ static inline struct port* dev_to_port(struct net_device *dev) static inline void memcpy_swab32(u32 *dest, u32 *src, int cnt) { int i; + for (i = 0; i < cnt; i++) dest[i] = swab32(src[i]); } @@ -355,9 +352,10 @@ static inline void memcpy_swab32(u32 *dest, u32 *src, int cnt) * HSS access ****************************************************************************/ -static void hss_npe_send(struct port *port, struct msg *msg, const char* what) +static void hss_npe_send(struct port *port, struct msg *msg, const char *what) { - u32 *val = (u32*)msg; + u32 *val = (u32 *)msg; + if (npe_send_message(port->npe, msg, what)) { pr_crit("HSS-%i: unable to send command [%08X:%08X] to %s\n", port->id, val[0], val[1], npe_name(port->npe)); @@ -513,10 +511,12 @@ static int hss_load_firmware(struct port *port) if (port->initialized) return 0; - if (!npe_running(port->npe) && - (err = npe_load_firmware(port->npe, npe_name(port->npe), - port->dev))) - return err; + if (!npe_running(port->npe)) { + err = npe_load_firmware(port->npe, npe_name(port->npe), + port->dev); + if (err) + return err; + } /* HDLC mode configuration */ memset(&msg, 0, sizeof(msg)); @@ -567,7 +567,6 @@ static inline void debug_pkt(struct net_device *dev, const char *func, #endif } - static inline void debug_desc(u32 phys, struct desc *desc) { #if DEBUG_DESC @@ -583,7 +582,8 @@ static inline int queue_get_desc(unsigned int queue, struct port *port, u32 phys, tab_phys, n_desc; struct desc *tab; - if (!(phys = qmgr_get_entry(queue))) + phys = qmgr_get_entry(queue); + if (!phys) return -1; BUG_ON(phys & 0x1F); @@ -603,10 +603,10 @@ static inline void queue_put_desc(unsigned int queue, u32 phys, BUG_ON(phys & 0x1F); qmgr_put_entry(queue, phys); /* Don't check for queue overflow here, we've allocated sufficient - length and queues >= 32 don't support this check anyway. */ + * length and queues >= 32 don't support this check anyway. + */ } - static inline void dma_unmap_tx(struct port *port, struct desc *desc) { #ifdef __ARMEB__ @@ -619,7 +619,6 @@ static inline void dma_unmap_tx(struct port *port, struct desc *desc) #endif } - static void hss_hdlc_set_carrier(void *pdev, int carrier) { struct net_device *netdev = pdev; @@ -670,7 +669,8 @@ static int hss_hdlc_poll(struct napi_struct *napi, int budget) u32 phys; #endif - if ((n = queue_get_desc(rxq, port, 0)) < 0) { + n = queue_get_desc(rxq, port, 0); + if (n < 0) { #if DEBUG_RX printk(KERN_DEBUG "%s: hss_hdlc_poll" " napi_complete\n", dev->name); @@ -705,7 +705,8 @@ static int hss_hdlc_poll(struct napi_struct *napi, int budget) switch (desc->status) { case 0: #ifdef __ARMEB__ - if ((skb = netdev_alloc_skb(dev, RX_SIZE)) != NULL) { + skb = netdev_alloc_skb(dev, RX_SIZE); + if (skb) { phys = dma_map_single(&dev->dev, skb->data, RX_SIZE, DMA_FROM_DEVICE); @@ -784,7 +785,6 @@ static int hss_hdlc_poll(struct napi_struct *napi, int budget) return received; /* not all work done */ } - static void hss_hdlc_txdone_irq(void *pdev) { struct net_device *dev = pdev; @@ -854,7 +854,8 @@ static int hss_hdlc_xmit(struct sk_buff *skb, struct net_device *dev) #else offset = (int)skb->data & 3; /* keep 32-bit alignment */ bytes = ALIGN(offset + len, 4); - if (!(mem = kmalloc(bytes, GFP_ATOMIC))) { + mem = kmalloc(bytes, GFP_ATOMIC); + if (!mem) { dev_kfree_skb(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; @@ -910,7 +911,6 @@ static int hss_hdlc_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - static int request_hdlc_queues(struct port *port) { int err; @@ -974,8 +974,9 @@ static int init_hdlc_queues(struct port *port) return -ENOMEM; } - if (!(port->desc_tab = dma_pool_alloc(dma_pool, GFP_KERNEL, - &port->desc_tab_phys))) + port->desc_tab = dma_pool_alloc(dma_pool, GFP_KERNEL, + &port->desc_tab_phys); + if (!port->desc_tab) return -ENOMEM; memset(port->desc_tab, 0, POOL_ALLOC_SIZE); memset(port->rx_buff_tab, 0, sizeof(port->rx_buff_tab)); /* tables */ @@ -987,11 +988,13 @@ static int init_hdlc_queues(struct port *port) buffer_t *buff; void *data; #ifdef __ARMEB__ - if (!(buff = netdev_alloc_skb(port->netdev, RX_SIZE))) + buff = netdev_alloc_skb(port->netdev, RX_SIZE); + if (!buff) return -ENOMEM; data = buff->data; #else - if (!(buff = kmalloc(RX_SIZE, GFP_KERNEL))) + buff = kmalloc(RX_SIZE, GFP_KERNEL); + if (!buff) return -ENOMEM; data = buff; #endif @@ -1016,6 +1019,7 @@ static void destroy_hdlc_queues(struct port *port) for (i = 0; i < RX_DESCS; i++) { struct desc *desc = rx_desc_ptr(port, i); buffer_t *buff = port->rx_buff_tab[i]; + if (buff) { dma_unmap_single(&port->netdev->dev, desc->data, RX_SIZE, @@ -1026,6 +1030,7 @@ static void destroy_hdlc_queues(struct port *port) for (i = 0; i < TX_DESCS; i++) { struct desc *desc = tx_desc_ptr(port, i); buffer_t *buff = port->tx_buff_tab[i]; + if (buff) { dma_unmap_tx(port, desc); free_buffer(buff); @@ -1047,23 +1052,29 @@ static int hss_hdlc_open(struct net_device *dev) unsigned long flags; int i, err = 0; - if ((err = hdlc_open(dev))) + err = hdlc_open(dev); + if (err) return err; - if ((err = hss_load_firmware(port))) + err = hss_load_firmware(port); + if (err) goto err_hdlc_close; - if ((err = request_hdlc_queues(port))) + err = request_hdlc_queues(port); + if (err) goto err_hdlc_close; - if ((err = init_hdlc_queues(port))) + err = init_hdlc_queues(port); + if (err) goto err_destroy_queues; spin_lock_irqsave(&npe_lock, flags); - if (port->plat->open) - if ((err = port->plat->open(port->id, dev, - hss_hdlc_set_carrier))) + if (port->plat->open) { + err = port->plat->open(port->id, dev, hss_hdlc_set_carrier); + if (err) goto err_unlock; + } + spin_unlock_irqrestore(&npe_lock, flags); /* Populate queues with buffers, no failure after this point */ @@ -1160,7 +1171,6 @@ static int hss_hdlc_close(struct net_device *dev) return 0; } - static int hss_hdlc_attach(struct net_device *dev, unsigned short encoding, unsigned short parity) { @@ -1169,7 +1179,7 @@ static int hss_hdlc_attach(struct net_device *dev, unsigned short encoding, if (encoding != ENCODING_NRZ) return -EINVAL; - switch(parity) { + switch (parity) { case PARITY_CRC16_PR1_CCITT: port->hdlc_cfg = 0; return 0; @@ -1224,6 +1234,7 @@ static void find_best_clock(u32 timer_freq, u32 rate, u32 *best, u32 *reg) for (b = 0; b < 0x400; b++) { u64 c = (b + 1) * (u64)rate; + do_div(c, timer_freq - rate * a); c--; if (c >= 0xFFF) { /* 12-bit - no need to check more 'b's */ @@ -1255,7 +1266,7 @@ static int hss_hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (cmd != SIOCWANDEV) return hdlc_ioctl(dev, ifr, cmd); - switch(ifr->ifr_settings.type) { + switch (ifr->ifr_settings.type) { case IF_GET_IFACE: ifr->ifr_settings.type = IF_IFACE_V35; if (ifr->ifr_settings.size < size) { @@ -1272,7 +1283,7 @@ static int hss_hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case IF_IFACE_SYNC_SERIAL: case IF_IFACE_V35: - if(!capable(CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&new_line, line, size)) return -EFAULT; @@ -1288,11 +1299,11 @@ static int hss_hdlc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EINVAL; port->clock_type = clk; /* Update settings */ - if (clk == CLOCK_INT) + if (clk == CLOCK_INT) { find_best_clock(port->plat->timer_freq, new_line.clock_rate, &port->clock_rate, &port->clock_reg); - else { + } else { port->clock_rate = 0; port->clock_reg = CLK42X_SPEED_2048KHZ; } @@ -1334,15 +1345,19 @@ static int hss_init_one(struct platform_device *pdev) hdlc_device *hdlc; int err; - if ((port = kzalloc(sizeof(*port), GFP_KERNEL)) == NULL) + port = kzalloc(sizeof(*port), GFP_KERNEL); + if (!port) return -ENOMEM; - if ((port->npe = npe_request(0)) == NULL) { + port->npe = npe_request(0); + if (!port->npe) { err = -ENODEV; goto err_free; } - if ((port->netdev = dev = alloc_hdlcdev(port)) == NULL) { + dev = alloc_hdlcdev(port); + port->netdev = alloc_hdlcdev(port); + if (!port->netdev) { err = -ENOMEM; goto err_plat; } @@ -1361,7 +1376,8 @@ static int hss_init_one(struct platform_device *pdev) port->plat = pdev->dev.platform_data; netif_napi_add(dev, &port->napi, hss_hdlc_poll, NAPI_WEIGHT); - if ((err = register_hdlc_device(dev))) + err = register_hdlc_device(dev); + if (err) goto err_free_netdev; platform_set_drvdata(pdev, port); diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 59646865a3a4..89d31adc3809 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -6,7 +6,7 @@ * * This is a "pseudo" network driver to allow LAPB over Ethernet. * - * This driver can use any ethernet destination address, and can be + * This driver can use any ethernet destination address, and can be * limited to accept frames from one dedicated ethernet card only. * * History @@ -44,7 +44,8 @@ static const u8 bcast_addr[6] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; /* If this number is made larger, check that the temporary string buffer - * in lapbeth_new_device is large enough to store the probe device name.*/ + * in lapbeth_new_device is large enough to store the probe device name. + */ #define MAXLAPBDEV 100 struct lapbethdev { @@ -64,15 +65,14 @@ static void lapbeth_disconnected(struct net_device *dev, int reason); /* ------------------------------------------------------------------------ */ -/* - * Get the LAPB device for the ethernet device +/* Get the LAPB device for the ethernet device */ static struct lapbethdev *lapbeth_get_x25_dev(struct net_device *dev) { struct lapbethdev *lapbeth; list_for_each_entry_rcu(lapbeth, &lapbeth_devices, node, lockdep_rtnl_is_held()) { - if (lapbeth->ethdev == dev) + if (lapbeth->ethdev == dev) return lapbeth; } return NULL; @@ -105,10 +105,10 @@ static int lapbeth_napi_poll(struct napi_struct *napi, int budget) return processed; } -/* - * Receive a LAPB frame via an ethernet interface. +/* Receive a LAPB frame via an ethernet interface. */ -static int lapbeth_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) +static int lapbeth_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *ptype, struct net_device *orig_dev) { int len, err; struct lapbethdev *lapbeth; @@ -116,7 +116,8 @@ static int lapbeth_rcv(struct sk_buff *skb, struct net_device *dev, struct packe if (dev_net(dev) != &init_net) goto drop; - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) return NET_RX_DROP; if (!pskb_may_pull(skb, 2)) @@ -137,7 +138,8 @@ static int lapbeth_rcv(struct sk_buff *skb, struct net_device *dev, struct packe skb_pull(skb, 2); /* Remove the length bytes */ skb_trim(skb, len); /* Set the length of the data */ - if ((err = lapb_data_received(lapbeth->axdev, skb)) != LAPB_OK) { + err = lapb_data_received(lapbeth->axdev, skb); + if (err != LAPB_OK) { printk(KERN_DEBUG "lapbether: lapb_data_received err - %d\n", err); goto drop_unlock; } @@ -177,11 +179,10 @@ static int lapbeth_data_indication(struct net_device *dev, struct sk_buff *skb) return NET_RX_SUCCESS; } -/* - * Send a LAPB frame via an ethernet interface +/* Send a LAPB frame via an ethernet interface */ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb, - struct net_device *dev) + struct net_device *dev) { struct lapbethdev *lapbeth = netdev_priv(dev); int err; @@ -219,7 +220,8 @@ static netdev_tx_t lapbeth_xmit(struct sk_buff *skb, skb_pull(skb, 1); - if ((err = lapb_data_request(dev, skb)) != LAPB_OK) { + err = lapb_data_request(dev, skb); + if (err != LAPB_OK) { pr_err("lapb_data_request error - %d\n", err); goto drop; } @@ -263,10 +265,8 @@ static void lapbeth_connected(struct net_device *dev, int reason) unsigned char *ptr; struct sk_buff *skb = __dev_alloc_skb(1, GFP_ATOMIC | __GFP_NOMEMALLOC); - if (!skb) { - pr_err("out of memory\n"); + if (!skb) return; - } ptr = skb_put(skb, 1); *ptr = X25_IFACE_CONNECT; @@ -283,10 +283,8 @@ static void lapbeth_disconnected(struct net_device *dev, int reason) unsigned char *ptr; struct sk_buff *skb = __dev_alloc_skb(1, GFP_ATOMIC | __GFP_NOMEMALLOC); - if (!skb) { - pr_err("out of memory\n"); + if (!skb) return; - } ptr = skb_put(skb, 1); *ptr = X25_IFACE_DISCONNECT; @@ -297,17 +295,16 @@ static void lapbeth_disconnected(struct net_device *dev, int reason) napi_schedule(&lapbeth->napi); } -/* - * Set AX.25 callsign +/* Set AX.25 callsign */ static int lapbeth_set_mac_address(struct net_device *dev, void *addr) { struct sockaddr *sa = addr; + memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); return 0; } - static const struct lapb_register_struct lapbeth_callbacks = { .connect_confirmation = lapbeth_connected, .connect_indication = lapbeth_connected, @@ -317,8 +314,7 @@ static const struct lapb_register_struct lapbeth_callbacks = { .data_transmit = lapbeth_data_transmit, }; -/* - * open/close a device +/* open/close a device */ static int lapbeth_open(struct net_device *dev) { @@ -327,7 +323,8 @@ static int lapbeth_open(struct net_device *dev) napi_enable(&lapbeth->napi); - if ((err = lapb_register(dev, &lapbeth_callbacks)) != LAPB_OK) { + err = lapb_register(dev, &lapbeth_callbacks); + if (err != LAPB_OK) { pr_err("lapb_register error: %d\n", err); return -ENODEV; } @@ -348,7 +345,8 @@ static int lapbeth_close(struct net_device *dev) lapbeth->up = false; spin_unlock_bh(&lapbeth->up_lock); - if ((err = lapb_unregister(dev)) != LAPB_OK) + err = lapb_unregister(dev); + if (err != LAPB_OK) pr_err("lapb_unregister error: %d\n", err); napi_disable(&lapbeth->napi); @@ -375,8 +373,7 @@ static void lapbeth_setup(struct net_device *dev) dev->addr_len = 0; } -/* - * Setup a new device. +/* Setup a new device. */ static int lapbeth_new_device(struct net_device *dev) { @@ -427,8 +424,7 @@ fail: goto out; } -/* - * Free a lapb network device. +/* Free a lapb network device. */ static void lapbeth_free_device(struct lapbethdev *lapbeth) { @@ -437,8 +433,7 @@ static void lapbeth_free_device(struct lapbethdev *lapbeth) unregister_netdevice(lapbeth->axdev); } -/* - * Handle device status changes. +/* Handle device status changes. * * Called from notifier with RTNL held. */ @@ -457,13 +452,13 @@ static int lapbeth_device_event(struct notifier_block *this, switch (event) { case NETDEV_UP: /* New ethernet device -> new LAPB interface */ - if (lapbeth_get_x25_dev(dev) == NULL) + if (!lapbeth_get_x25_dev(dev)) lapbeth_new_device(dev); break; case NETDEV_GOING_DOWN: /* ethernet device closes -> close LAPB interface */ lapbeth = lapbeth_get_x25_dev(dev); - if (lapbeth) + if (lapbeth) dev_close(lapbeth->axdev); break; case NETDEV_UNREGISTER: diff --git a/drivers/net/wan/lmc/lmc.h b/drivers/net/wan/lmc/lmc.h index 38961793adad..3bd541c868d5 100644 --- a/drivers/net/wan/lmc/lmc.h +++ b/drivers/net/wan/lmc/lmc.h @@ -9,7 +9,7 @@ */ int lmc_probe(struct net_device * dev); unsigned lmc_mii_readreg(lmc_softc_t * const sc, unsigned - devaddr, unsigned regno); + devaddr, unsigned regno); void lmc_mii_writereg(lmc_softc_t * const sc, unsigned devaddr, unsigned regno, unsigned data); void lmc_led_on(lmc_softc_t * const, u32); diff --git a/drivers/net/wan/n2.c b/drivers/net/wan/n2.c index 5bf4463873b1..bdb6dc2409bc 100644 --- a/drivers/net/wan/n2.c +++ b/drivers/net/wan/n2.c @@ -32,9 +32,8 @@ #include #include "hd64570.h" - -static const char* version = "SDL RISCom/N2 driver version: 1.15"; -static const char* devname = "RISCom/N2"; +static const char *version = "SDL RISCom/N2 driver version: 1.15"; +static const char *devname = "RISCom/N2"; #undef DEBUG_PKT #define DEBUG_RINGS @@ -64,11 +63,9 @@ static char *hw; /* pointer to hw=xxx command line string */ #define PCR_ENWIN 4 /* Open window */ #define PCR_BUS16 8 /* 16-bit bus */ - /* Memory Base Address Register */ #define N2_BAR 2 - /* Page Scan Register */ #define N2_PSR 4 #define WIN16K 0x00 @@ -78,7 +75,6 @@ static char *hw; /* pointer to hw=xxx command line string */ #define PSR_DMAEN 0x80 #define PSR_PAGEBITS 0x0F - /* Modem Control Reg */ #define N2_MCR 6 #define CLOCK_OUT_PORT1 0x80 @@ -90,7 +86,6 @@ static char *hw; /* pointer to hw=xxx command line string */ #define DTR_PORT1 0x02 #define DTR_PORT0 0x01 - typedef struct port_s { struct net_device *dev; struct card_s *card; @@ -106,9 +101,7 @@ typedef struct port_s { u8 rxs, txs, tmc; /* SCA registers */ u8 phy_node; /* physical port # - 0 or 1 */ u8 log_node; /* logical port # */ -}port_t; - - +} port_t; typedef struct card_s { u8 __iomem *winbase; /* ISA window base address */ @@ -122,13 +115,11 @@ typedef struct card_s { port_t ports[2]; struct card_s *next_card; -}card_t; - +} card_t; static card_t *first_card; static card_t **new_card = &first_card; - #define sca_reg(reg, card) (0x8000 | (card)->io | \ ((reg) & 0x0F) | (((reg) & 0xF0) << 6)) #define sca_in(reg, card) inb(sca_reg(reg, card)) @@ -144,23 +135,20 @@ static card_t **new_card = &first_card; #define get_port(card, port) ((card)->ports[port].valid ? \ &(card)->ports[port] : NULL) - static __inline__ u8 sca_get_page(card_t *card) { return inb(card->io + N2_PSR) & PSR_PAGEBITS; } - static __inline__ void openwin(card_t *card, u8 page) { u8 psr = inb(card->io + N2_PSR); + outb((psr & ~PSR_PAGEBITS) | page, card->io + N2_PSR); } - #include "hd64570.c" - static void n2_set_iface(port_t *port) { card_t *card = port->card; @@ -170,7 +158,7 @@ static void n2_set_iface(port_t *port) u8 rxs = port->rxs & CLK_BRG_MASK; u8 txs = port->txs & CLK_BRG_MASK; - switch(port->settings.clock_type) { + switch (port->settings.clock_type) { case CLOCK_INT: mcr |= port->phy_node ? CLOCK_OUT_PORT1 : CLOCK_OUT_PORT0; rxs |= CLK_BRG_RX; /* BRG output */ @@ -203,13 +191,12 @@ static void n2_set_iface(port_t *port) sca_set_port(port); } - - static int n2_open(struct net_device *dev) { port_t *port = dev_to_port(dev); int io = port->card->io; - u8 mcr = inb(io + N2_MCR) | (port->phy_node ? TX422_PORT1:TX422_PORT0); + u8 mcr = inb(io + N2_MCR) | + (port->phy_node ? TX422_PORT1 : TX422_PORT0); int result; result = hdlc_open(dev); @@ -226,13 +213,12 @@ static int n2_open(struct net_device *dev) return 0; } - - static int n2_close(struct net_device *dev) { port_t *port = dev_to_port(dev); int io = port->card->io; - u8 mcr = inb(io+N2_MCR) | (port->phy_node ? TX422_PORT1 : TX422_PORT0); + u8 mcr = inb(io + N2_MCR) | + (port->phy_node ? TX422_PORT1 : TX422_PORT0); sca_close(dev); mcr |= port->phy_node ? DTR_PORT1 : DTR_PORT0; /* set DTR OFF */ @@ -241,8 +227,6 @@ static int n2_close(struct net_device *dev) return 0; } - - static int n2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { const size_t size = sizeof(sync_serial_settings); @@ -259,7 +243,7 @@ static int n2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (cmd != SIOCWANDEV) return hdlc_ioctl(dev, ifr, cmd); - switch(ifr->ifr_settings.type) { + switch (ifr->ifr_settings.type) { case IF_GET_IFACE: ifr->ifr_settings.type = IF_IFACE_SYNC_SERIAL; if (ifr->ifr_settings.size < size) { @@ -271,7 +255,7 @@ static int n2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return 0; case IF_IFACE_SYNC_SERIAL: - if(!capable(CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&new_line, line, size)) @@ -295,8 +279,6 @@ static int n2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } } - - static void n2_destroy_card(card_t *card) { int cnt; @@ -304,6 +286,7 @@ static void n2_destroy_card(card_t *card) for (cnt = 0; cnt < 2; cnt++) if (card->ports[cnt].card) { struct net_device *dev = port_to_dev(&card->ports[cnt]); + unregister_hdlc_device(dev); } @@ -354,7 +337,7 @@ static int __init n2_run(unsigned long io, unsigned long irq, } card = kzalloc(sizeof(card_t), GFP_KERNEL); - if (card == NULL) + if (!card) return -ENOBUFS; card->ports[0].dev = alloc_hdlcdev(&card->ports[0]); @@ -486,11 +469,9 @@ static int __init n2_run(unsigned long io, unsigned long irq, return 0; } - - static int __init n2_init(void) { - if (hw==NULL) { + if (!hw) { #ifdef MODULE pr_info("no card initialized\n"); #endif @@ -515,7 +496,7 @@ static int __init n2_init(void) if (*hw++ != ',') break; - while(1) { + while (1) { if (*hw == '0' && !valid[0]) valid[0] = 1; /* Port 0 enabled */ else if (*hw == '1' && !valid[1]) @@ -533,25 +514,24 @@ static int __init n2_init(void) if (*hw == '\x0') return first_card ? 0 : -EINVAL; - }while(*hw++ == ':'); + } while (*hw++ == ':'); pr_err("invalid hardware parameters\n"); return first_card ? 0 : -EINVAL; } - static void __exit n2_cleanup(void) { card_t *card = first_card; while (card) { card_t *ptr = card; + card = card->next_card; n2_destroy_card(ptr); } } - module_init(n2_init); module_exit(n2_cleanup); diff --git a/drivers/net/wan/pc300too.c b/drivers/net/wan/pc300too.c index 001fd378d417..7b123a771aa6 100644 --- a/drivers/net/wan/pc300too.c +++ b/drivers/net/wan/pc300too.c @@ -44,7 +44,7 @@ #define MAX_TX_BUFFERS 10 static int pci_clock_freq = 33000000; -static int use_crystal_clock = 0; +static int use_crystal_clock; static unsigned int CLOCK_BASE; /* Masks to access the init_ctrl PLX register */ @@ -52,11 +52,9 @@ static unsigned int CLOCK_BASE; #define PC300_CHMEDIA_MASK(port) (0x00000020UL << ((port) * 3)) #define PC300_CTYPE_MASK (0x00000800UL) - enum { PC300_RSV = 1, PC300_X21, PC300_TE }; /* card types */ -/* - * PLX PCI9050-1 local configuration and shared runtime registers. +/* PLX PCI9050-1 local configuration and shared runtime registers. * This structure can be used to access 9050 registers (memory mapped). */ typedef struct { @@ -69,9 +67,7 @@ typedef struct { u32 cs_base[4]; /* 3C-48h : Chip Select Base Addrs */ u32 intr_ctrl_stat; /* 4Ch : Interrupt Control/Status */ u32 init_ctrl; /* 50h : EEPROM ctrl, Init Ctrl, etc */ -}plx9050; - - +} plx9050; typedef struct port_s { struct napi_struct napi; @@ -88,9 +84,7 @@ typedef struct port_s { u16 txlast; u8 rxs, txs, tmc; /* SCA registers */ u8 chan; /* physical port # - 0 or 1 */ -}port_t; - - +} port_t; typedef struct card_s { int type; /* RSV, X21, etc. */ @@ -105,26 +99,24 @@ typedef struct card_s { u8 irq; /* interrupt request level */ port_t ports[2]; -}card_t; - +} card_t; #define get_port(card, port) ((port) < (card)->n_ports ? \ (&(card)->ports[port]) : (NULL)) #include "hd64572.c" - static void pc300_set_iface(port_t *port) { card_t *card = port->card; - u32 __iomem * init_ctrl = &card->plxbase->init_ctrl; + u32 __iomem *init_ctrl = &card->plxbase->init_ctrl; u16 msci = get_msci(port); u8 rxs = port->rxs & CLK_BRG_MASK; u8 txs = port->txs & CLK_BRG_MASK; sca_out(EXS_TES1, (port->chan ? MSCI1_OFFSET : MSCI0_OFFSET) + EXS, port->card); - switch(port->settings.clock_type) { + switch (port->settings.clock_type) { case CLOCK_INT: rxs |= CLK_BRG; /* BRG output */ txs |= CLK_PIN_OUT | CLK_TX_RXCLK; /* RX clock */ @@ -162,13 +154,11 @@ static void pc300_set_iface(port_t *port) } } - - static int pc300_open(struct net_device *dev) { port_t *port = dev_to_port(dev); - int result = hdlc_open(dev); + if (result) return result; @@ -177,8 +167,6 @@ static int pc300_open(struct net_device *dev) return 0; } - - static int pc300_close(struct net_device *dev) { sca_close(dev); @@ -186,8 +174,6 @@ static int pc300_close(struct net_device *dev) return 0; } - - static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { const size_t size = sizeof(sync_serial_settings); @@ -214,7 +200,6 @@ static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (copy_to_user(line, &port->settings, size)) return -EFAULT; return 0; - } if (port->card->type == PC300_X21 && @@ -255,8 +240,6 @@ static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return 0; } - - static void pc300_pci_remove_one(struct pci_dev *pdev) { int i; @@ -314,7 +297,7 @@ static int pc300_pci_init_one(struct pci_dev *pdev, } card = kzalloc(sizeof(card_t), GFP_KERNEL); - if (card == NULL) { + if (!card) { pci_release_regions(pdev); pci_disable_device(pdev); return -ENOBUFS; @@ -338,9 +321,7 @@ static int pc300_pci_init_one(struct pci_dev *pdev, ramphys = pci_resource_start(pdev, 3) & PCI_BASE_ADDRESS_MEM_MASK; card->rambase = pci_ioremap_bar(pdev, 3); - if (card->plxbase == NULL || - card->scabase == NULL || - card->rambase == NULL) { + if (!card->plxbase || !card->scabase || !card->rambase) { pr_err("ioremap() failed\n"); pc300_pci_remove_one(pdev); return -ENOMEM; @@ -365,12 +346,14 @@ static int pc300_pci_init_one(struct pci_dev *pdev, else card->n_ports = 2; - for (i = 0; i < card->n_ports; i++) - if (!(card->ports[i].netdev = alloc_hdlcdev(&card->ports[i]))) { + for (i = 0; i < card->n_ports; i++) { + card->ports[i].netdev = alloc_hdlcdev(&card->ports[i]); + if (!card->ports[i].netdev) { pr_err("unable to allocate memory\n"); pc300_pci_remove_one(pdev); return -ENOMEM; } + } /* Reset PLX */ p = &card->plxbase->init_ctrl; @@ -442,6 +425,7 @@ static int pc300_pci_init_one(struct pci_dev *pdev, port_t *port = &card->ports[i]; struct net_device *dev = port->netdev; hdlc_device *hdlc = dev_to_hdlc(dev); + port->chan = i; spin_lock_init(&port->lock); @@ -472,8 +456,6 @@ static int pc300_pci_init_one(struct pci_dev *pdev, return 0; } - - static const struct pci_device_id pc300_pci_tbl[] = { { PCI_VENDOR_ID_CYCLADES, PCI_DEVICE_ID_PC300_RX_1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, @@ -486,7 +468,6 @@ static const struct pci_device_id pc300_pci_tbl[] = { { 0, } }; - static struct pci_driver pc300_pci_driver = { .name = "PC300", .id_table = pc300_pci_tbl, @@ -494,7 +475,6 @@ static struct pci_driver pc300_pci_driver = { .remove = pc300_pci_remove_one, }; - static int __init pc300_init_module(void) { if (pci_clock_freq < 1000000 || pci_clock_freq > 80000000) { @@ -511,8 +491,6 @@ static int __init pc300_init_module(void) return pci_register_driver(&pc300_pci_driver); } - - static void __exit pc300_cleanup_module(void) { pci_unregister_driver(&pc300_pci_driver); diff --git a/drivers/net/wan/pci200syn.c b/drivers/net/wan/pci200syn.c index ba5cc0c53833..dee9c4e15eca 100644 --- a/drivers/net/wan/pci200syn.c +++ b/drivers/net/wan/pci200syn.c @@ -42,8 +42,7 @@ static int pci_clock_freq = 33000000; #define CLOCK_BASE pci_clock_freq -/* - * PLX PCI9052 local configuration and shared runtime registers. +/* PLX PCI9052 local configuration and shared runtime registers. * This structure can be used to access 9052 registers (memory mapped). */ typedef struct { @@ -56,9 +55,7 @@ typedef struct { u32 cs_base[4]; /* 3C-48h : Chip Select Base Addrs */ u32 intr_ctrl_stat; /* 4Ch : Interrupt Control/Status */ u32 init_ctrl; /* 50h : EEPROM ctrl, Init Ctrl, etc */ -}plx9052; - - +} plx9052; typedef struct port_s { struct napi_struct napi; @@ -74,9 +71,7 @@ typedef struct port_s { u16 txlast; u8 rxs, txs, tmc; /* SCA registers */ u8 chan; /* physical port # - 0 or 1 */ -}port_t; - - +} port_t; typedef struct card_s { u8 __iomem *rambase; /* buffer memory base (virtual) */ @@ -88,15 +83,15 @@ typedef struct card_s { u8 irq; /* interrupt request level */ port_t ports[2]; -}card_t; +} card_t; - -#define get_port(card, port) (&card->ports[port]) +#define get_port(card, port) (&(card)->ports[port]) #define sca_flush(card) (sca_in(IER0, card)) static inline void new_memcpy_toio(char __iomem *dest, char *src, int length) { int len; + do { len = length > 256 ? 256 : length; memcpy_toio(dest, src, len); @@ -112,7 +107,6 @@ static inline void new_memcpy_toio(char __iomem *dest, char *src, int length) #include "hd64572.c" - static void pci200_set_iface(port_t *port) { card_t *card = port->card; @@ -122,7 +116,7 @@ static void pci200_set_iface(port_t *port) sca_out(EXS_TES1, (port->chan ? MSCI1_OFFSET : MSCI0_OFFSET) + EXS, port->card); - switch(port->settings.clock_type) { + switch (port->settings.clock_type) { case CLOCK_INT: rxs |= CLK_BRG; /* BRG output */ txs |= CLK_PIN_OUT | CLK_TX_RXCLK; /* RX clock */ @@ -151,13 +145,11 @@ static void pci200_set_iface(port_t *port) sca_set_port(port); } - - static int pci200_open(struct net_device *dev) { port_t *port = dev_to_port(dev); - int result = hdlc_open(dev); + if (result) return result; @@ -167,8 +159,6 @@ static int pci200_open(struct net_device *dev) return 0; } - - static int pci200_close(struct net_device *dev) { sca_close(dev); @@ -177,8 +167,6 @@ static int pci200_close(struct net_device *dev) return 0; } - - static int pci200_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { const size_t size = sizeof(sync_serial_settings); @@ -195,7 +183,7 @@ static int pci200_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (cmd != SIOCWANDEV) return hdlc_ioctl(dev, ifr, cmd); - switch(ifr->ifr_settings.type) { + switch (ifr->ifr_settings.type) { case IF_GET_IFACE: ifr->ifr_settings.type = IF_IFACE_V35; if (ifr->ifr_settings.size < size) { @@ -233,8 +221,6 @@ static int pci200_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } } - - static void pci200_pci_remove_one(struct pci_dev *pdev) { int i; @@ -292,7 +278,7 @@ static int pci200_pci_init_one(struct pci_dev *pdev, } card = kzalloc(sizeof(card_t), GFP_KERNEL); - if (card == NULL) { + if (!card) { pci_release_regions(pdev); pci_disable_device(pdev); return -ENOBUFS; @@ -314,18 +300,16 @@ static int pci200_pci_init_one(struct pci_dev *pdev, return -EFAULT; } - plxphys = pci_resource_start(pdev,0) & PCI_BASE_ADDRESS_MEM_MASK; + plxphys = pci_resource_start(pdev, 0) & PCI_BASE_ADDRESS_MEM_MASK; card->plxbase = ioremap(plxphys, PCI200SYN_PLX_SIZE); - scaphys = pci_resource_start(pdev,2) & PCI_BASE_ADDRESS_MEM_MASK; + scaphys = pci_resource_start(pdev, 2) & PCI_BASE_ADDRESS_MEM_MASK; card->scabase = ioremap(scaphys, PCI200SYN_SCA_SIZE); - ramphys = pci_resource_start(pdev,3) & PCI_BASE_ADDRESS_MEM_MASK; + ramphys = pci_resource_start(pdev, 3) & PCI_BASE_ADDRESS_MEM_MASK; card->rambase = pci_ioremap_bar(pdev, 3); - if (card->plxbase == NULL || - card->scabase == NULL || - card->rambase == NULL) { + if (!card->plxbase || !card->scabase || !card->rambase) { pr_err("ioremap() failed\n"); pci200_pci_remove_one(pdev); return -EFAULT; @@ -380,6 +364,7 @@ static int pci200_pci_init_one(struct pci_dev *pdev, port_t *port = &card->ports[i]; struct net_device *dev = port->netdev; hdlc_device *hdlc = dev_to_hdlc(dev); + port->chan = i; spin_lock_init(&port->lock); @@ -407,15 +392,12 @@ static int pci200_pci_init_one(struct pci_dev *pdev, return 0; } - - static const struct pci_device_id pci200_pci_tbl[] = { { PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9050, PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_PCI200SYN, 0, 0, 0 }, { 0, } }; - static struct pci_driver pci200_pci_driver = { .name = "PCI200SYN", .id_table = pci200_pci_tbl, @@ -423,7 +405,6 @@ static struct pci_driver pci200_pci_driver = { .remove = pci200_pci_remove_one, }; - static int __init pci200_init_module(void) { if (pci_clock_freq < 1000000 || pci_clock_freq > 80000000) { @@ -433,8 +414,6 @@ static int __init pci200_init_module(void) return pci_register_driver(&pci200_pci_driver); } - - static void __exit pci200_cleanup_module(void) { pci_unregister_driver(&pci200_pci_driver); diff --git a/drivers/net/wan/sealevel.c b/drivers/net/wan/sealevel.c index 7dddc9dcbe23..4403e219ca03 100644 --- a/drivers/net/wan/sealevel.c +++ b/drivers/net/wan/sealevel.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/* - * Sealevel Systems 4021 driver. +/* Sealevel Systems 4021 driver. * * (c) Copyright 1999, 2001 Alan Cox * (c) Copyright 2001 Red Hat Inc. @@ -29,32 +28,25 @@ #include #include "z85230.h" - -struct slvl_device -{ +struct slvl_device { struct z8530_channel *chan; int channel; }; - -struct slvl_board -{ +struct slvl_board { struct slvl_device dev[2]; struct z8530_dev board; int iobase; }; -/* - * Network driver support routines - */ + /* Network driver support routines */ -static inline struct slvl_device* dev_to_chan(struct net_device *dev) +static inline struct slvl_device *dev_to_chan(struct net_device *dev) { return (struct slvl_device *)dev_to_hdlc(dev)->priv; } -/* - * Frame receive. Simple for our card as we do HDLC and there +/* Frame receive. Simple for our card as we do HDLC and there * is no funny garbage involved */ @@ -68,9 +60,7 @@ static void sealevel_input(struct z8530_channel *c, struct sk_buff *skb) netif_rx(skb); } -/* - * We've been placed in the UP state - */ + /* We've been placed in the UP state */ static int sealevel_open(struct net_device *d) { @@ -78,17 +68,15 @@ static int sealevel_open(struct net_device *d) int err = -1; int unit = slvl->channel; - /* - * Link layer up. - */ + /* Link layer up. */ switch (unit) { - case 0: - err = z8530_sync_dma_open(d, slvl->chan); - break; - case 1: - err = z8530_sync_open(d, slvl->chan); - break; + case 0: + err = z8530_sync_dma_open(d, slvl->chan); + break; + case 1: + err = z8530_sync_open(d, slvl->chan); + break; } if (err) @@ -97,21 +85,18 @@ static int sealevel_open(struct net_device *d) err = hdlc_open(d); if (err) { switch (unit) { - case 0: - z8530_sync_dma_close(d, slvl->chan); - break; - case 1: - z8530_sync_close(d, slvl->chan); - break; + case 0: + z8530_sync_dma_close(d, slvl->chan); + break; + case 1: + z8530_sync_close(d, slvl->chan); + break; } return err; } slvl->chan->rx_function = sealevel_input; - /* - * Go go go - */ netif_start_queue(d); return 0; } @@ -121,9 +106,7 @@ static int sealevel_close(struct net_device *d) struct slvl_device *slvl = dev_to_chan(d); int unit = slvl->channel; - /* - * Discard new frames - */ + /* Discard new frames */ slvl->chan->rx_function = z8530_null_rx; @@ -131,12 +114,12 @@ static int sealevel_close(struct net_device *d) netif_stop_queue(d); switch (unit) { - case 0: - z8530_sync_dma_close(d, slvl->chan); - break; - case 1: - z8530_sync_close(d, slvl->chan); - break; + case 0: + z8530_sync_dma_close(d, slvl->chan); + break; + case 1: + z8530_sync_close(d, slvl->chan); + break; } return 0; } @@ -144,16 +127,15 @@ static int sealevel_close(struct net_device *d) static int sealevel_ioctl(struct net_device *d, struct ifreq *ifr, int cmd) { /* struct slvl_device *slvl=dev_to_chan(d); - z8530_ioctl(d,&slvl->sync.chanA,ifr,cmd) */ + * z8530_ioctl(d,&slvl->sync.chanA,ifr,cmd) + */ return hdlc_ioctl(d, ifr, cmd); } -/* - * Passed network frames, fire them downwind. - */ +/* Passed network frames, fire them downwind. */ static netdev_tx_t sealevel_queue_xmit(struct sk_buff *skb, - struct net_device *d) + struct net_device *d) { return z8530_queue_xmit(dev_to_chan(d)->chan, skb); } @@ -176,6 +158,7 @@ static const struct net_device_ops sealevel_ops = { static int slvl_setup(struct slvl_device *sv, int iobase, int irq) { struct net_device *dev = alloc_hdlcdev(sv); + if (!dev) return -1; @@ -195,10 +178,7 @@ static int slvl_setup(struct slvl_device *sv, int iobase, int irq) return 0; } - -/* - * Allocate and setup Sealevel board. - */ +/* Allocate and setup Sealevel board. */ static __init struct slvl_board *slvl_init(int iobase, int irq, int txdma, int rxdma, int slow) @@ -206,9 +186,7 @@ static __init struct slvl_board *slvl_init(int iobase, int irq, struct z8530_dev *dev; struct slvl_board *b; - /* - * Get the needed I/O space - */ + /* Get the needed I/O space */ if (!request_region(iobase, 8, "Sealevel 4021")) { pr_warn("I/O 0x%X already in use\n", iobase); @@ -227,17 +205,13 @@ static __init struct slvl_board *slvl_init(int iobase, int irq, dev = &b->board; - /* - * Stuff in the I/O addressing - */ + /* Stuff in the I/O addressing */ dev->active = 0; b->iobase = iobase; - /* - * Select 8530 delays for the old board - */ + /* Select 8530 delays for the old board */ if (slow) iobase |= Z8530_PORT_SLEEP; @@ -250,15 +224,13 @@ static __init struct slvl_board *slvl_init(int iobase, int irq, dev->chanA.irqs = &z8530_nop; dev->chanB.irqs = &z8530_nop; - /* - * Assert DTR enable DMA - */ + /* Assert DTR enable DMA */ outb(3 | (1 << 7), b->iobase + 4); - /* We want a fast IRQ for this device. Actually we'd like an even faster - IRQ ;) - This is one driver RtLinux is made for */ + * IRQ ;) - This is one driver RtLinux is made for + */ if (request_irq(irq, z8530_interrupt, 0, "SeaLevel", dev) < 0) { @@ -282,9 +254,7 @@ static __init struct slvl_board *slvl_init(int iobase, int irq, disable_irq(irq); - /* - * Begin normal initialise - */ + /* Begin normal initialise */ if (z8530_init(dev) != 0) { pr_err("Z8530 series device not found\n"); @@ -299,9 +269,7 @@ static __init struct slvl_board *slvl_init(int iobase, int irq, z8530_channel_load(&dev->chanB, z8530_hdlc_kilostream_85230); } - /* - * Now we can take the IRQ - */ + /* Now we can take the IRQ */ enable_irq(irq); @@ -338,6 +306,7 @@ static void __exit slvl_shutdown(struct slvl_board *b) for (u = 0; u < 2; u++) { struct net_device *d = b->dev[u].chan->netdevice; + unregister_hdlc_device(d); free_netdev(d); } @@ -351,12 +320,11 @@ static void __exit slvl_shutdown(struct slvl_board *b) kfree(b); } - -static int io=0x238; -static int txdma=1; -static int rxdma=3; -static int irq=5; -static bool slow=false; +static int io = 0x238; +static int txdma = 1; +static int rxdma = 3; +static int irq = 5; +static bool slow; module_param_hw(io, int, ioport, 0); MODULE_PARM_DESC(io, "The I/O base of the Sealevel card"); diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c index a83133388de9..f22e48415e6f 100644 --- a/drivers/net/wan/wanxl.c +++ b/drivers/net/wan/wanxl.c @@ -32,7 +32,7 @@ #include "wanxl.h" -static const char* version = "wanXL serial card driver version: 0.48"; +static const char *version = "wanXL serial card driver version: 0.48"; #define PLX_CTL_RESET 0x40000000 /* adapter reset */ @@ -50,24 +50,21 @@ static const char* version = "wanXL serial card driver version: 0.48"; /* MAILBOX #2 - DRAM SIZE */ #define MBX2_MEMSZ_MASK 0xFFFF0000 /* PUTS Memory Size Register mask */ - struct port { struct net_device *dev; struct card *card; spinlock_t lock; /* for wanxl_xmit */ - int node; /* physical port #0 - 3 */ + int node; /* physical port #0 - 3 */ unsigned int clock_type; int tx_in, tx_out; struct sk_buff *tx_skbs[TX_BUFFERS]; }; - struct card_status { desc_t rx_descs[RX_QUEUE_LENGTH]; port_status_t port_status[4]; }; - struct card { int n_ports; /* 1, 2 or 4 ports */ u8 irq; @@ -81,25 +78,22 @@ struct card { struct port ports[]; /* 1 - 4 port structures follow */ }; - - static inline struct port *dev_to_port(struct net_device *dev) { return (struct port *)dev_to_hdlc(dev)->priv; } - static inline port_status_t *get_status(struct port *port) { return &port->card->status->port_status[port->node]; } - #ifdef DEBUG_PCI static inline dma_addr_t pci_map_single_debug(struct pci_dev *pdev, void *ptr, size_t size, int direction) { dma_addr_t addr = dma_map_single(&pdev->dev, ptr, size, direction); + if (addr + size > 0x100000000LL) pr_crit("%s: pci_map_single() returned memory at 0x%llx!\n", pci_name(pdev), (unsigned long long)addr); @@ -110,7 +104,6 @@ static inline dma_addr_t pci_map_single_debug(struct pci_dev *pdev, void *ptr, #define pci_map_single pci_map_single_debug #endif - /* Cable and/or personality module change interrupt service */ static inline void wanxl_cable_intr(struct port *port) { @@ -118,22 +111,46 @@ static inline void wanxl_cable_intr(struct port *port) int valid = 1; const char *cable, *pm, *dte = "", *dsr = "", *dcd = ""; - switch(value & 0x7) { - case STATUS_CABLE_V35: cable = "V.35"; break; - case STATUS_CABLE_X21: cable = "X.21"; break; - case STATUS_CABLE_V24: cable = "V.24"; break; - case STATUS_CABLE_EIA530: cable = "EIA530"; break; - case STATUS_CABLE_NONE: cable = "no"; break; - default: cable = "invalid"; + switch (value & 0x7) { + case STATUS_CABLE_V35: + cable = "V.35"; + break; + case STATUS_CABLE_X21: + cable = "X.21"; + break; + case STATUS_CABLE_V24: + cable = "V.24"; + break; + case STATUS_CABLE_EIA530: + cable = "EIA530"; + break; + case STATUS_CABLE_NONE: + cable = "no"; + break; + default: + cable = "invalid"; } - switch((value >> STATUS_CABLE_PM_SHIFT) & 0x7) { - case STATUS_CABLE_V35: pm = "V.35"; break; - case STATUS_CABLE_X21: pm = "X.21"; break; - case STATUS_CABLE_V24: pm = "V.24"; break; - case STATUS_CABLE_EIA530: pm = "EIA530"; break; - case STATUS_CABLE_NONE: pm = "no personality"; valid = 0; break; - default: pm = "invalid personality"; valid = 0; + switch ((value >> STATUS_CABLE_PM_SHIFT) & 0x7) { + case STATUS_CABLE_V35: + pm = "V.35"; + break; + case STATUS_CABLE_X21: + pm = "X.21"; + break; + case STATUS_CABLE_V24: + pm = "V.24"; + break; + case STATUS_CABLE_EIA530: + pm = "EIA530"; + break; + case STATUS_CABLE_NONE: + pm = "no personality"; + valid = 0; + break; + default: + pm = "invalid personality"; + valid = 0; } if (valid) { @@ -154,14 +171,13 @@ static inline void wanxl_cable_intr(struct port *port) netif_carrier_off(port->dev); } - - /* Transmit complete interrupt service */ static inline void wanxl_tx_intr(struct port *port) { struct net_device *dev = port->dev; + while (1) { - desc_t *desc = &get_status(port)->tx_descs[port->tx_in]; + desc_t *desc = &get_status(port)->tx_descs[port->tx_in]; struct sk_buff *skb = port->tx_skbs[port->tx_in]; switch (desc->stat) { @@ -179,34 +195,33 @@ static inline void wanxl_tx_intr(struct port *port) dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; } - desc->stat = PACKET_EMPTY; /* Free descriptor */ + desc->stat = PACKET_EMPTY; /* Free descriptor */ dma_unmap_single(&port->card->pdev->dev, desc->address, skb->len, DMA_TO_DEVICE); dev_consume_skb_irq(skb); - port->tx_in = (port->tx_in + 1) % TX_BUFFERS; - } + port->tx_in = (port->tx_in + 1) % TX_BUFFERS; + } } - - /* Receive complete interrupt service */ static inline void wanxl_rx_intr(struct card *card) { desc_t *desc; + while (desc = &card->status->rx_descs[card->rx_in], desc->stat != PACKET_EMPTY) { - if ((desc->stat & PACKET_PORT_MASK) > card->n_ports) + if ((desc->stat & PACKET_PORT_MASK) > card->n_ports) { pr_crit("%s: received packet for nonexistent port\n", pci_name(card->pdev)); - else { + } else { struct sk_buff *skb = card->rx_skbs[card->rx_in]; struct port *port = &card->ports[desc->stat & PACKET_PORT_MASK]; struct net_device *dev = port->dev; - if (!skb) + if (!skb) { dev->stats.rx_dropped++; - else { + } else { dma_unmap_single(&card->pdev->dev, desc->address, BUFFER_LENGTH, DMA_FROM_DEVICE); @@ -239,21 +254,18 @@ static inline void wanxl_rx_intr(struct card *card) } } - - -static irqreturn_t wanxl_intr(int irq, void* dev_id) +static irqreturn_t wanxl_intr(int irq, void *dev_id) { struct card *card = dev_id; - int i; - u32 stat; - int handled = 0; + int i; + u32 stat; + int handled = 0; - - while((stat = readl(card->plx + PLX_DOORBELL_FROM_CARD)) != 0) { - handled = 1; + while ((stat = readl(card->plx + PLX_DOORBELL_FROM_CARD)) != 0) { + handled = 1; writel(stat, card->plx + PLX_DOORBELL_FROM_CARD); - for (i = 0; i < card->n_ports; i++) { + for (i = 0; i < card->n_ports; i++) { if (stat & (1 << (DOORBELL_FROM_CARD_TX_0 + i))) wanxl_tx_intr(&card->ports[i]); if (stat & (1 << (DOORBELL_FROM_CARD_CABLE_0 + i))) @@ -261,23 +273,21 @@ static irqreturn_t wanxl_intr(int irq, void* dev_id) } if (stat & (1 << DOORBELL_FROM_CARD_RX)) wanxl_rx_intr(card); - } + } - return IRQ_RETVAL(handled); + return IRQ_RETVAL(handled); } - - static netdev_tx_t wanxl_xmit(struct sk_buff *skb, struct net_device *dev) { struct port *port = dev_to_port(dev); desc_t *desc; - spin_lock(&port->lock); + spin_lock(&port->lock); desc = &get_status(port)->tx_descs[port->tx_out]; - if (desc->stat != PACKET_EMPTY) { - /* should never happen - previous xmit should stop queue */ + if (desc->stat != PACKET_EMPTY) { + /* should never happen - previous xmit should stop queue */ #ifdef DEBUG_PKT printk(KERN_DEBUG "%s: transmitter buffer full\n", dev->name); #endif @@ -312,8 +322,6 @@ static netdev_tx_t wanxl_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - - static int wanxl_attach(struct net_device *dev, unsigned short encoding, unsigned short parity) { @@ -335,8 +343,6 @@ static int wanxl_attach(struct net_device *dev, unsigned short encoding, return 0; } - - static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { const size_t size = sizeof(sync_serial_settings); @@ -384,11 +390,9 @@ static int wanxl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) default: return hdlc_ioctl(dev, ifr, cmd); - } + } } - - static int wanxl_open(struct net_device *dev) { struct port *port = dev_to_port(dev); @@ -400,7 +404,9 @@ static int wanxl_open(struct net_device *dev) netdev_err(dev, "port already open\n"); return -EIO; } - if ((i = hdlc_open(dev)) != 0) + + i = hdlc_open(dev); + if (i) return i; port->tx_in = port->tx_out = 0; @@ -423,8 +429,6 @@ static int wanxl_open(struct net_device *dev) return -EFAULT; } - - static int wanxl_close(struct net_device *dev) { struct port *port = dev_to_port(dev); @@ -461,8 +465,6 @@ static int wanxl_close(struct net_device *dev) return 0; } - - static struct net_device_stats *wanxl_get_stats(struct net_device *dev) { struct port *port = dev_to_port(dev); @@ -474,8 +476,6 @@ static struct net_device_stats *wanxl_get_stats(struct net_device *dev) return &dev->stats; } - - static int wanxl_puts_command(struct card *card, u32 cmd) { unsigned long timeout = jiffies + 5 * HZ; @@ -486,13 +486,11 @@ static int wanxl_puts_command(struct card *card, u32 cmd) return 0; schedule(); - }while (time_after(timeout, jiffies)); + } while (time_after(timeout, jiffies)); return -1; } - - static void wanxl_reset(struct card *card) { u32 old_value = readl(card->plx + PLX_CONTROL) & ~PLX_CTL_RESET; @@ -505,8 +503,6 @@ static void wanxl_reset(struct card *card) readl(card->plx + PLX_CONTROL); /* wait for posted write */ } - - static void wanxl_pci_remove_one(struct pci_dev *pdev) { struct card *card = pci_get_drvdata(pdev); @@ -543,7 +539,6 @@ static void wanxl_pci_remove_one(struct pci_dev *pdev) kfree(card); } - #include "wanxlfw.inc" static const struct net_device_ops wanxl_ops = { @@ -574,12 +569,14 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, return i; /* QUICC can only access first 256 MB of host RAM directly, - but PLX9060 DMA does 32-bits for actual packet data transfers */ + * but PLX9060 DMA does 32-bits for actual packet data transfers + */ /* FIXME when PCI/DMA subsystems are fixed. - We set both dma_mask and consistent_dma_mask to 28 bits - and pray pci_alloc_consistent() will use this info. It should - work on most platforms */ + * We set both dma_mask and consistent_dma_mask to 28 bits + * and pray pci_alloc_consistent() will use this info. It should + * work on most platforms + */ if (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(28)) || dma_set_mask(&pdev->dev, DMA_BIT_MASK(28))) { pr_err("No usable DMA configuration\n"); @@ -594,13 +591,18 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, } switch (pdev->device) { - case PCI_DEVICE_ID_SBE_WANXL100: ports = 1; break; - case PCI_DEVICE_ID_SBE_WANXL200: ports = 2; break; - default: ports = 4; + case PCI_DEVICE_ID_SBE_WANXL100: + ports = 1; + break; + case PCI_DEVICE_ID_SBE_WANXL200: + ports = 2; + break; + default: + ports = 4; } card = kzalloc(struct_size(card, ports, ports), GFP_KERNEL); - if (card == NULL) { + if (!card) { pci_release_regions(pdev); pci_disable_device(pdev); return -ENOBUFS; @@ -612,7 +614,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, card->status = dma_alloc_coherent(&pdev->dev, sizeof(struct card_status), &card->status_address, GFP_KERNEL); - if (card->status == NULL) { + if (!card->status) { wanxl_pci_remove_one(pdev); return -ENOBUFS; } @@ -624,8 +626,9 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, #endif /* FIXME when PCI/DMA subsystems are fixed. - We set both dma_mask and consistent_dma_mask back to 32 bits - to indicate the card can do 32-bit DMA addressing */ + * We set both dma_mask and consistent_dma_mask back to 32 bits + * to indicate the card can do 32-bit DMA addressing + */ if (dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)) || dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) { pr_err("No usable DMA configuration\n"); @@ -639,7 +642,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, card->plx = ioremap(plx_phy, 0x70); if (!card->plx) { pr_err("ioremap() failed\n"); - wanxl_pci_remove_one(pdev); + wanxl_pci_remove_one(pdev); return -EFAULT; } @@ -656,7 +659,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, return -ENODEV; } - switch(stat & 0xC0) { + switch (stat & 0xC0) { case 0x00: /* hmm - PUTS completed with non-zero code? */ case 0x80: /* PUTS still testing the hardware */ break; @@ -677,7 +680,6 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, /* set up on-board RAM mapping */ mem_phy = pci_resource_start(pdev, 2); - /* sanity check the board's reported memory size */ if (ramsize < BUFFERS_ADDR + (TX_BUFFERS + RX_BUFFERS) * BUFFER_LENGTH * ports) { @@ -697,6 +699,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, for (i = 0; i < RX_QUEUE_LENGTH; i++) { struct sk_buff *skb = dev_alloc_skb(BUFFER_LENGTH); + card->rx_skbs[i] = skb; if (skb) card->status->rx_descs[i].address = @@ -707,12 +710,12 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, mem = ioremap(mem_phy, PDM_OFFSET + sizeof(firmware)); if (!mem) { pr_err("ioremap() failed\n"); - wanxl_pci_remove_one(pdev); + wanxl_pci_remove_one(pdev); return -EFAULT; } for (i = 0; i < sizeof(firmware); i += 4) - writel(ntohl(*(__be32*)(firmware + i)), mem + PDM_OFFSET + i); + writel(ntohl(*(__be32 *)(firmware + i)), mem + PDM_OFFSET + i); for (i = 0; i < ports; i++) writel(card->status_address + @@ -732,10 +735,11 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, timeout = jiffies + 5 * HZ; do { - if ((stat = readl(card->plx + PLX_MAILBOX_5)) != 0) + stat = readl(card->plx + PLX_MAILBOX_5); + if (stat) break; schedule(); - }while (time_after(timeout, jiffies)); + } while (time_after(timeout, jiffies)); if (!stat) { pr_warn("%s: timeout while initializing card firmware\n", @@ -764,6 +768,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, hdlc_device *hdlc; struct port *port = &card->ports[i]; struct net_device *dev = alloc_hdlcdev(port); + if (!dev) { pr_err("%s: unable to allocate memory\n", pci_name(pdev)); @@ -813,7 +818,6 @@ static const struct pci_device_id wanxl_pci_tbl[] = { { 0, } }; - static struct pci_driver wanxl_pci_driver = { .name = "wanXL", .id_table = wanxl_pci_tbl, @@ -821,7 +825,6 @@ static struct pci_driver wanxl_pci_driver = { .remove = wanxl_pci_remove_one, }; - static int __init wanxl_init_module(void) { #ifdef MODULE @@ -835,7 +838,6 @@ static void __exit wanxl_cleanup_module(void) pci_unregister_driver(&wanxl_pci_driver); } - MODULE_AUTHOR("Krzysztof Halasa "); MODULE_DESCRIPTION("SBE Inc. wanXL serial port driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/wan/z85230.c b/drivers/net/wan/z85230.c index 138930c66ad2..982a03488a00 100644 --- a/drivers/net/wan/z85230.c +++ b/drivers/net/wan/z85230.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/* - * - * (c) Copyright 1998 Alan Cox +/* (c) Copyright 1998 Alan Cox * (c) Copyright 2000, 2001 Red Hat Inc * * Development of this driver was funded by Equiinet Ltd @@ -12,7 +10,7 @@ * Asynchronous mode dropped for 2.2. For 2.5 we will attempt the * unification of all the Z85x30 asynchronous drivers for real. * - * DMA now uses get_free_page as kmalloc buffers may span a 64K + * DMA now uses get_free_page as kmalloc buffers may span a 64K * boundary. * * Modified for SMP safety and SMP locking by Alan Cox @@ -55,14 +53,13 @@ #include "z85230.h" - /** * z8530_read_port - Architecture specific interface function * @p: port to read * * Provided port access methods. The Comtrol SV11 requires no delays * between accesses and uses PC I/O. Some drivers may need a 5uS delay - * + * * In the longer term this should become an architecture specific * section so that this can become a generic driver interface for all * platforms. For now we only handle PC I/O ports with or without the @@ -74,8 +71,9 @@ static inline int z8530_read_port(unsigned long p) { - u8 r=inb(Z8530_PORT_OF(p)); - if(p&Z8530_PORT_SLEEP) /* gcc should figure this out efficiently ! */ + u8 r = inb(Z8530_PORT_OF(p)); + + if (p & Z8530_PORT_SLEEP) /* gcc should figure this out efficiently ! */ udelay(5); return r; } @@ -95,34 +93,30 @@ static inline int z8530_read_port(unsigned long p) * dread 5uS sanity delay. */ - static inline void z8530_write_port(unsigned long p, u8 d) { - outb(d,Z8530_PORT_OF(p)); - if(p&Z8530_PORT_SLEEP) + outb(d, Z8530_PORT_OF(p)); + if (p & Z8530_PORT_SLEEP) udelay(5); } - - static void z8530_rx_done(struct z8530_channel *c); static void z8530_tx_done(struct z8530_channel *c); - /** - * read_zsreg - Read a register from a Z85230 + * read_zsreg - Read a register from a Z85230 * @c: Z8530 channel to read from (2 per chip) * @reg: Register to read * FIXME: Use a spinlock. - * + * * Most of the Z8530 registers are indexed off the control registers. * A read is done by writing to the control register and reading the * register back. The caller must hold the lock */ - + static inline u8 read_zsreg(struct z8530_channel *c, u8 reg) { - if(reg) + if (reg) z8530_write_port(c->ctrlio, reg); return z8530_read_port(c->ctrlio); } @@ -138,7 +132,8 @@ static inline u8 read_zsreg(struct z8530_channel *c, u8 reg) static inline u8 read_zsdata(struct z8530_channel *c) { u8 r; - r=z8530_read_port(c->dataio); + + r = z8530_read_port(c->dataio); return r; } @@ -156,10 +151,9 @@ static inline u8 read_zsdata(struct z8530_channel *c) */ static inline void write_zsreg(struct z8530_channel *c, u8 reg, u8 val) { - if(reg) + if (reg) z8530_write_port(c->ctrlio, reg); z8530_write_port(c->ctrlio, val); - } /** @@ -182,108 +176,94 @@ static inline void write_zsctrl(struct z8530_channel *c, u8 val) * * Write directly to the data register on the Z8530 */ - - static inline void write_zsdata(struct z8530_channel *c, u8 val) { z8530_write_port(c->dataio, val); } -/* - * Register loading parameters for a dead port +/* Register loading parameters for a dead port */ - -u8 z8530_dead_port[]= -{ + +u8 z8530_dead_port[] = { 255 }; - EXPORT_SYMBOL(z8530_dead_port); -/* - * Register loading parameters for currently supported circuit types +/* Register loading parameters for currently supported circuit types */ - -/* - * Data clocked by telco end. This is the correct data for the UK +/* Data clocked by telco end. This is the correct data for the UK * "kilostream" service, and most other similar services. */ - -u8 z8530_hdlc_kilostream[]= -{ - 4, SYNC_ENAB|SDLC|X1CLK, + +u8 z8530_hdlc_kilostream[] = { + 4, SYNC_ENAB | SDLC | X1CLK, 2, 0, /* No vector */ 1, 0, - 3, ENT_HM|RxCRC_ENAB|Rx8, - 5, TxCRC_ENAB|RTS|TxENAB|Tx8|DTR, + 3, ENT_HM | RxCRC_ENAB | Rx8, + 5, TxCRC_ENAB | RTS | TxENAB | Tx8 | DTR, 9, 0, /* Disable interrupts */ 6, 0xFF, 7, FLAG, - 10, ABUNDER|NRZ|CRCPS,/*MARKIDLE ??*/ + 10, ABUNDER | NRZ | CRCPS,/*MARKIDLE ??*/ 11, TCTRxCP, 14, DISDPLL, - 15, DCDIE|SYNCIE|CTSIE|TxUIE|BRKIE, - 1, EXT_INT_ENAB|TxINT_ENAB|INT_ALL_Rx, - 9, NV|MIE|NORESET, + 15, DCDIE | SYNCIE | CTSIE | TxUIE | BRKIE, + 1, EXT_INT_ENAB | TxINT_ENAB | INT_ALL_Rx, + 9, NV | MIE | NORESET, 255 }; - EXPORT_SYMBOL(z8530_hdlc_kilostream); -/* - * As above but for enhanced chips. +/* As above but for enhanced chips. */ - -u8 z8530_hdlc_kilostream_85230[]= -{ - 4, SYNC_ENAB|SDLC|X1CLK, + +u8 z8530_hdlc_kilostream_85230[] = { + 4, SYNC_ENAB | SDLC | X1CLK, 2, 0, /* No vector */ 1, 0, - 3, ENT_HM|RxCRC_ENAB|Rx8, - 5, TxCRC_ENAB|RTS|TxENAB|Tx8|DTR, + 3, ENT_HM | RxCRC_ENAB | Rx8, + 5, TxCRC_ENAB | RTS | TxENAB | Tx8 | DTR, 9, 0, /* Disable interrupts */ 6, 0xFF, 7, FLAG, - 10, ABUNDER|NRZ|CRCPS, /* MARKIDLE?? */ + 10, ABUNDER | NRZ | CRCPS, /* MARKIDLE?? */ 11, TCTRxCP, 14, DISDPLL, - 15, DCDIE|SYNCIE|CTSIE|TxUIE|BRKIE, - 1, EXT_INT_ENAB|TxINT_ENAB|INT_ALL_Rx, - 9, NV|MIE|NORESET, + 15, DCDIE | SYNCIE | CTSIE | TxUIE | BRKIE, + 1, EXT_INT_ENAB | TxINT_ENAB | INT_ALL_Rx, + 9, NV | MIE | NORESET, 23, 3, /* Extended mode AUTO TX and EOM*/ - + 255 }; - EXPORT_SYMBOL(z8530_hdlc_kilostream_85230); /** * z8530_flush_fifo - Flush on chip RX FIFO * @c: Channel to flush * - * Flush the receive FIFO. There is no specific option for this, we + * Flush the receive FIFO. There is no specific option for this, we * blindly read bytes and discard them. Reading when there is no data * is harmless. The 8530 has a 4 byte FIFO, the 85230 has 8 bytes. - * + * * All locking is handled for the caller. On return data may still be * present if it arrived during the flush. */ - + static void z8530_flush_fifo(struct z8530_channel *c) { read_zsreg(c, R1); read_zsreg(c, R1); read_zsreg(c, R1); read_zsreg(c, R1); - if(c->dev->type==Z85230) - { + if (c->dev->type == Z85230) { read_zsreg(c, R1); read_zsreg(c, R1); read_zsreg(c, R1); read_zsreg(c, R1); } -} +} /** * z8530_rtsdtr - Control the outgoing DTS/RTS line @@ -309,7 +289,7 @@ static void z8530_rtsdtr(struct z8530_channel *c, int set) * z8530_rx - Handle a PIO receive event * @c: Z8530 channel to process * - * Receive handler for receiving in PIO mode. This is much like the + * Receive handler for receiving in PIO mode. This is much like the * async one but not quite the same or as complex * * Note: Its intended that this handler can easily be separated from @@ -322,77 +302,63 @@ static void z8530_rtsdtr(struct z8530_channel *c, int set) * other code - this is true in the RT case too. * * We only cover the sync cases for this. If you want 2Mbit async - * do it yourself but consider medical assistance first. This non DMA - * synchronous mode is portable code. The DMA mode assumes PCI like + * do it yourself but consider medical assistance first. This non DMA + * synchronous mode is portable code. The DMA mode assumes PCI like * ISA DMA * * Called with the device lock held */ - + static void z8530_rx(struct z8530_channel *c) { - u8 ch,stat; + u8 ch, stat; - while(1) - { + while (1) { /* FIFO empty ? */ - if(!(read_zsreg(c, R0)&1)) + if (!(read_zsreg(c, R0) & 1)) break; - ch=read_zsdata(c); - stat=read_zsreg(c, R1); - - /* - * Overrun ? + ch = read_zsdata(c); + stat = read_zsreg(c, R1); + + /* Overrun ? */ - if(c->count < c->max) - { - *c->dptr++=ch; + if (c->count < c->max) { + *c->dptr++ = ch; c->count++; } - if(stat&END_FR) - { - - /* - * Error ? + if (stat & END_FR) { + /* Error ? */ - if(stat&(Rx_OVR|CRC_ERR)) - { + if (stat & (Rx_OVR | CRC_ERR)) { /* Rewind the buffer and return */ - if(c->skb) - c->dptr=c->skb->data; - c->count=0; - if(stat&Rx_OVR) - { + if (c->skb) + c->dptr = c->skb->data; + c->count = 0; + if (stat & Rx_OVR) { pr_warn("%s: overrun\n", c->dev->name); c->rx_overrun++; } - if(stat&CRC_ERR) - { + if (stat & CRC_ERR) { c->rx_crc_err++; /* printk("crc error\n"); */ } /* Shove the frame upstream */ - } - else - { - /* - * Drop the lock for RX processing, or - * there are deadlocks - */ + } else { + /* Drop the lock for RX processing, or + * there are deadlocks + */ z8530_rx_done(c); write_zsctrl(c, RES_Rx_CRC); } } } - /* - * Clear irq + /* Clear irq */ write_zsctrl(c, ERR_RES); write_zsctrl(c, RES_H_IUS); } - /** * z8530_tx - Handle a PIO transmit event * @c: Z8530 channel to process @@ -402,35 +368,31 @@ static void z8530_rx(struct z8530_channel *c) * in as possible, its quite possible that we won't keep up with the * data rate otherwise. */ - + static void z8530_tx(struct z8530_channel *c) { - while(c->txcount) { + while (c->txcount) { /* FIFO full ? */ - if(!(read_zsreg(c, R0)&4)) + if (!(read_zsreg(c, R0) & 4)) return; c->txcount--; - /* - * Shovel out the byte + /* Shovel out the byte */ write_zsreg(c, R8, *c->tx_ptr++); write_zsctrl(c, RES_H_IUS); /* We are about to underflow */ - if(c->txcount==0) - { + if (c->txcount == 0) { write_zsctrl(c, RES_EOM_L); - write_zsreg(c, R10, c->regs[10]&~ABUNDER); + write_zsreg(c, R10, c->regs[10] & ~ABUNDER); } } - - /* - * End of frame TX - fire another one + /* End of frame TX - fire another one */ - + write_zsctrl(c, RES_Tx_P); - z8530_tx_done(c); + z8530_tx_done(c); write_zsctrl(c, RES_H_IUS); } @@ -460,8 +422,7 @@ static void z8530_status(struct z8530_channel *chan) z8530_tx_done(chan); } - if (altered & chan->dcdcheck) - { + if (altered & chan->dcdcheck) { if (status & chan->dcdcheck) { pr_info("%s: DCD raised\n", chan->dev->name); write_zsreg(chan, R3, chan->regs[3] | RxENABLE); @@ -474,7 +435,6 @@ static void z8530_status(struct z8530_channel *chan) if (chan->netdevice) netif_carrier_off(chan->netdevice); } - } write_zsctrl(chan, RES_EXT_INT); write_zsctrl(chan, RES_H_IUS); @@ -485,7 +445,6 @@ struct z8530_irqhandler z8530_sync = { .tx = z8530_tx, .status = z8530_status, }; - EXPORT_SYMBOL(z8530_sync); /** @@ -497,31 +456,27 @@ EXPORT_SYMBOL(z8530_sync); * events are handled by the DMA hardware. We get a kick here only if * a frame ended. */ - + static void z8530_dma_rx(struct z8530_channel *chan) { - if(chan->rxdma_on) - { + if (chan->rxdma_on) { /* Special condition check only */ u8 status; - + read_zsreg(chan, R7); read_zsreg(chan, R6); - - status=read_zsreg(chan, R1); - - if(status&END_FR) - { + + status = read_zsreg(chan, R1); + + if (status & END_FR) z8530_rx_done(chan); /* Fire up the next one */ - } + write_zsctrl(chan, ERR_RES); write_zsctrl(chan, RES_H_IUS); - } - else - { + } else { /* DMA is off right now, drain the slow way */ z8530_rx(chan); - } + } } /** @@ -531,11 +486,9 @@ static void z8530_dma_rx(struct z8530_channel *chan) * We have received an interrupt while doing DMA transmissions. It * shouldn't happen. Scream loudly if it does. */ - static void z8530_dma_tx(struct z8530_channel *chan) { - if(!chan->dma_tx) - { + if (!chan->dma_tx) { pr_warn("Hey who turned the DMA off?\n"); z8530_tx(chan); return; @@ -548,40 +501,35 @@ static void z8530_dma_tx(struct z8530_channel *chan) /** * z8530_dma_status - Handle a DMA status exception * @chan: Z8530 channel to process - * + * * A status event occurred on the Z8530. We receive these for two reasons * when in DMA mode. Firstly if we finished a packet transfer we get one * and kick the next packet out. Secondly we may see a DCD change. * */ - static void z8530_dma_status(struct z8530_channel *chan) { u8 status, altered; - status=read_zsreg(chan, R0); - altered=chan->status^status; - - chan->status=status; + status = read_zsreg(chan, R0); + altered = chan->status ^ status; + chan->status = status; - if(chan->dma_tx) - { - if(status&TxEOM) - { + if (chan->dma_tx) { + if (status & TxEOM) { unsigned long flags; - - flags=claim_dma_lock(); + + flags = claim_dma_lock(); disable_dma(chan->txdma); - clear_dma_ff(chan->txdma); - chan->txdma_on=0; + clear_dma_ff(chan->txdma); + chan->txdma_on = 0; release_dma_lock(flags); z8530_tx_done(chan); } } - if (altered & chan->dcdcheck) - { + if (altered & chan->dcdcheck) { if (status & chan->dcdcheck) { pr_info("%s: DCD raised\n", chan->dev->name); write_zsreg(chan, R3, chan->regs[3] | RxENABLE); @@ -621,21 +569,18 @@ static struct z8530_irqhandler z8530_txdma_sync = { * (eg the MacII) we must clear the interrupt cause or die. */ - static void z8530_rx_clear(struct z8530_channel *c) { - /* - * Data and status bytes + /* Data and status bytes */ u8 stat; read_zsdata(c); - stat=read_zsreg(c, R1); - - if(stat&END_FR) + stat = read_zsreg(c, R1); + + if (stat & END_FR) write_zsctrl(c, RES_Rx_CRC); - /* - * Clear irq + /* Clear irq */ write_zsctrl(c, ERR_RES); write_zsctrl(c, RES_H_IUS); @@ -667,8 +612,9 @@ static void z8530_tx_clear(struct z8530_channel *c) static void z8530_status_clear(struct z8530_channel *chan) { - u8 status=read_zsreg(chan, R0); - if(status&TxEOM) + u8 status = read_zsreg(chan, R0); + + if (status & TxEOM) write_zsctrl(chan, ERR_RES); write_zsctrl(chan, RES_EXT_INT); write_zsctrl(chan, RES_H_IUS); @@ -679,13 +625,11 @@ struct z8530_irqhandler z8530_nop = { .tx = z8530_tx_clear, .status = z8530_status_clear, }; - - EXPORT_SYMBOL(z8530_nop); /** * z8530_interrupt - Handle an interrupt from a Z8530 - * @irq: Interrupt number + * @irq: Interrupt number * @dev_id: The Z8530 device that is interrupting. * * A Z85[2]30 device has stuck its hand in the air for attention. @@ -701,78 +645,73 @@ EXPORT_SYMBOL(z8530_nop); irqreturn_t z8530_interrupt(int irq, void *dev_id) { - struct z8530_dev *dev=dev_id; + struct z8530_dev *dev = dev_id; u8 intr; static volatile int locker=0; - int work=0; + int work = 0; struct z8530_irqhandler *irqs; - - if(locker) - { + + if (locker) { pr_err("IRQ re-enter\n"); return IRQ_NONE; } - locker=1; + locker = 1; spin_lock(&dev->lock); - while(++work<5000) - { - + while (++work < 5000) { intr = read_zsreg(&dev->chanA, R3); - if(!(intr & (CHARxIP|CHATxIP|CHAEXT|CHBRxIP|CHBTxIP|CHBEXT))) + if (!(intr & + (CHARxIP | CHATxIP | CHAEXT | CHBRxIP | CHBTxIP | CHBEXT))) break; - - /* This holds the IRQ status. On the 8530 you must read it from chan - A even though it applies to the whole chip */ - - /* Now walk the chip and see what it is wanting - it may be - an IRQ for someone else remember */ - - irqs=dev->chanA.irqs; - if(intr & (CHARxIP|CHATxIP|CHAEXT)) - { - if(intr&CHARxIP) + /* This holds the IRQ status. On the 8530 you must read it + * from chan A even though it applies to the whole chip + */ + + /* Now walk the chip and see what it is wanting - it may be + * an IRQ for someone else remember + */ + + irqs = dev->chanA.irqs; + + if (intr & (CHARxIP | CHATxIP | CHAEXT)) { + if (intr & CHARxIP) irqs->rx(&dev->chanA); - if(intr&CHATxIP) + if (intr & CHATxIP) irqs->tx(&dev->chanA); - if(intr&CHAEXT) + if (intr & CHAEXT) irqs->status(&dev->chanA); } - irqs=dev->chanB.irqs; + irqs = dev->chanB.irqs; - if(intr & (CHBRxIP|CHBTxIP|CHBEXT)) - { - if(intr&CHBRxIP) + if (intr & (CHBRxIP | CHBTxIP | CHBEXT)) { + if (intr & CHBRxIP) irqs->rx(&dev->chanB); - if(intr&CHBTxIP) + if (intr & CHBTxIP) irqs->tx(&dev->chanB); - if(intr&CHBEXT) + if (intr & CHBEXT) irqs->status(&dev->chanB); } } spin_unlock(&dev->lock); - if(work==5000) + if (work == 5000) pr_err("%s: interrupt jammed - abort(0x%X)!\n", dev->name, intr); /* Ok all done */ - locker=0; + locker = 0; return IRQ_HANDLED; } - EXPORT_SYMBOL(z8530_interrupt); -static const u8 reg_init[16]= -{ - 0,0,0,0, - 0,0,0,0, - 0,0,0,0, - 0x55,0,0,0 +static const u8 reg_init[16] = { + 0, 0, 0, 0, + 0, 0, 0, 0, + 0, 0, 0, 0, + 0x55, 0, 0, 0 }; - /** * z8530_sync_open - Open a Z8530 channel for PIO * @dev: The network interface we are using @@ -781,7 +720,6 @@ static const u8 reg_init[16]= * Switch a Z8530 into synchronous mode without DMA assist. We * raise the RTS/DTR and commence network operation. */ - int z8530_sync_open(struct net_device *dev, struct z8530_channel *c) { unsigned long flags; @@ -789,7 +727,7 @@ int z8530_sync_open(struct net_device *dev, struct z8530_channel *c) spin_lock_irqsave(c->lock, flags); c->sync = 1; - c->mtu = dev->mtu+64; + c->mtu = dev->mtu + 64; c->count = 0; c->skb = NULL; c->skb2 = NULL; @@ -798,17 +736,15 @@ int z8530_sync_open(struct net_device *dev, struct z8530_channel *c) /* This loads the double buffer up */ z8530_rx_done(c); /* Load the frame ring */ z8530_rx_done(c); /* Load the backup frame */ - z8530_rtsdtr(c,1); + z8530_rtsdtr(c, 1); c->dma_tx = 0; - c->regs[R1]|=TxINT_ENAB; + c->regs[R1] |= TxINT_ENAB; write_zsreg(c, R1, c->regs[R1]); - write_zsreg(c, R3, c->regs[R3]|RxENABLE); + write_zsreg(c, R3, c->regs[R3] | RxENABLE); spin_unlock_irqrestore(c->lock, flags); return 0; } - - EXPORT_SYMBOL(z8530_sync_open); /** @@ -819,25 +755,23 @@ EXPORT_SYMBOL(z8530_sync_open); * Close down a Z8530 interface and switch its interrupt handlers * to discard future events. */ - int z8530_sync_close(struct net_device *dev, struct z8530_channel *c) { u8 chk; unsigned long flags; - + spin_lock_irqsave(c->lock, flags); c->irqs = &z8530_nop; c->max = 0; c->sync = 0; - - chk=read_zsreg(c,R0); + + chk = read_zsreg(c, R0); write_zsreg(c, R3, c->regs[R3]); - z8530_rtsdtr(c,0); + z8530_rtsdtr(c, 0); spin_unlock_irqrestore(c->lock, flags); return 0; } - EXPORT_SYMBOL(z8530_sync_close); /** @@ -849,91 +783,83 @@ EXPORT_SYMBOL(z8530_sync_close); * ISA DMA channels must be available for this to work. We assume ISA * DMA driven I/O and PC limits on access. */ - int z8530_sync_dma_open(struct net_device *dev, struct z8530_channel *c) { unsigned long cflags, dflags; - + c->sync = 1; - c->mtu = dev->mtu+64; + c->mtu = dev->mtu + 64; c->count = 0; c->skb = NULL; c->skb2 = NULL; - /* - * Load the DMA interfaces up + + /* Load the DMA interfaces up */ c->rxdma_on = 0; c->txdma_on = 0; - - /* - * Allocate the DMA flip buffers. Limit by page size. + + /* Allocate the DMA flip buffers. Limit by page size. * Everyone runs 1500 mtu or less on wan links so this * should be fine. */ - - if(c->mtu > PAGE_SIZE/2) + + if (c->mtu > PAGE_SIZE / 2) return -EMSGSIZE; - - c->rx_buf[0]=(void *)get_zeroed_page(GFP_KERNEL|GFP_DMA); - if(c->rx_buf[0]==NULL) + + c->rx_buf[0] = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + if (!c->rx_buf[0]) return -ENOBUFS; - c->rx_buf[1]=c->rx_buf[0]+PAGE_SIZE/2; - - c->tx_dma_buf[0]=(void *)get_zeroed_page(GFP_KERNEL|GFP_DMA); - if(c->tx_dma_buf[0]==NULL) - { + c->rx_buf[1] = c->rx_buf[0] + PAGE_SIZE / 2; + + c->tx_dma_buf[0] = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + if (!c->tx_dma_buf[0]) { free_page((unsigned long)c->rx_buf[0]); - c->rx_buf[0]=NULL; + c->rx_buf[0] = NULL; return -ENOBUFS; } - c->tx_dma_buf[1]=c->tx_dma_buf[0]+PAGE_SIZE/2; + c->tx_dma_buf[1] = c->tx_dma_buf[0] + PAGE_SIZE / 2; - c->tx_dma_used=0; + c->tx_dma_used = 0; c->dma_tx = 1; - c->dma_num=0; - c->dma_ready=1; - - /* - * Enable DMA control mode + c->dma_num = 0; + c->dma_ready = 1; + + /* Enable DMA control mode */ spin_lock_irqsave(c->lock, cflags); - - /* - * TX DMA via DIR/REQ - */ - - c->regs[R14]|= DTRREQ; - write_zsreg(c, R14, c->regs[R14]); - c->regs[R1]&= ~TxINT_ENAB; - write_zsreg(c, R1, c->regs[R1]); - - /* - * RX DMA via W/Req - */ - - c->regs[R1]|= WT_FN_RDYFN; - c->regs[R1]|= WT_RDY_RT; - c->regs[R1]|= INT_ERR_Rx; - c->regs[R1]&= ~TxINT_ENAB; - write_zsreg(c, R1, c->regs[R1]); - c->regs[R1]|= WT_RDY_ENAB; - write_zsreg(c, R1, c->regs[R1]); - - /* - * DMA interrupts + /* TX DMA via DIR/REQ */ - - /* - * Set up the DMA configuration - */ - - dflags=claim_dma_lock(); - + + c->regs[R14] |= DTRREQ; + write_zsreg(c, R14, c->regs[R14]); + + c->regs[R1] &= ~TxINT_ENAB; + write_zsreg(c, R1, c->regs[R1]); + + /* RX DMA via W/Req + */ + + c->regs[R1] |= WT_FN_RDYFN; + c->regs[R1] |= WT_RDY_RT; + c->regs[R1] |= INT_ERR_Rx; + c->regs[R1] &= ~TxINT_ENAB; + write_zsreg(c, R1, c->regs[R1]); + c->regs[R1] |= WT_RDY_ENAB; + write_zsreg(c, R1, c->regs[R1]); + + /* DMA interrupts + */ + + /* Set up the DMA configuration + */ + + dflags = claim_dma_lock(); + disable_dma(c->rxdma); clear_dma_ff(c->rxdma); - set_dma_mode(c->rxdma, DMA_MODE_READ|0x10); + set_dma_mode(c->rxdma, DMA_MODE_READ | 0x10); set_dma_addr(c->rxdma, virt_to_bus(c->rx_buf[0])); set_dma_count(c->rxdma, c->mtu); enable_dma(c->rxdma); @@ -942,26 +868,24 @@ int z8530_sync_dma_open(struct net_device *dev, struct z8530_channel *c) clear_dma_ff(c->txdma); set_dma_mode(c->txdma, DMA_MODE_WRITE); disable_dma(c->txdma); - + release_dma_lock(dflags); - - /* - * Select the DMA interrupt handlers + + /* Select the DMA interrupt handlers */ c->rxdma_on = 1; c->txdma_on = 1; c->tx_dma_used = 1; - + c->irqs = &z8530_dma_sync; - z8530_rtsdtr(c,1); - write_zsreg(c, R3, c->regs[R3]|RxENABLE); + z8530_rtsdtr(c, 1); + write_zsreg(c, R3, c->regs[R3] | RxENABLE); spin_unlock_irqrestore(c->lock, cflags); - + return 0; } - EXPORT_SYMBOL(z8530_sync_dma_open); /** @@ -972,66 +896,60 @@ EXPORT_SYMBOL(z8530_sync_dma_open); * Shut down a DMA mode synchronous interface. Halt the DMA, and * free the buffers. */ - int z8530_sync_dma_close(struct net_device *dev, struct z8530_channel *c) { u8 chk; unsigned long flags; - + c->irqs = &z8530_nop; c->max = 0; c->sync = 0; - - /* - * Disable the PC DMA channels + + /* Disable the PC DMA channels */ - - flags=claim_dma_lock(); + + flags = claim_dma_lock(); disable_dma(c->rxdma); clear_dma_ff(c->rxdma); - + c->rxdma_on = 0; - + disable_dma(c->txdma); clear_dma_ff(c->txdma); release_dma_lock(flags); - + c->txdma_on = 0; c->tx_dma_used = 0; spin_lock_irqsave(c->lock, flags); - /* - * Disable DMA control mode + /* Disable DMA control mode */ - - c->regs[R1]&= ~WT_RDY_ENAB; - write_zsreg(c, R1, c->regs[R1]); - c->regs[R1]&= ~(WT_RDY_RT|WT_FN_RDYFN|INT_ERR_Rx); - c->regs[R1]|= INT_ALL_Rx; + + c->regs[R1] &= ~WT_RDY_ENAB; write_zsreg(c, R1, c->regs[R1]); - c->regs[R14]&= ~DTRREQ; - write_zsreg(c, R14, c->regs[R14]); - - if(c->rx_buf[0]) - { + c->regs[R1] &= ~(WT_RDY_RT | WT_FN_RDYFN | INT_ERR_Rx); + c->regs[R1] |= INT_ALL_Rx; + write_zsreg(c, R1, c->regs[R1]); + c->regs[R14] &= ~DTRREQ; + write_zsreg(c, R14, c->regs[R14]); + + if (c->rx_buf[0]) { free_page((unsigned long)c->rx_buf[0]); - c->rx_buf[0]=NULL; + c->rx_buf[0] = NULL; } - if(c->tx_dma_buf[0]) - { + if (c->tx_dma_buf[0]) { free_page((unsigned long)c->tx_dma_buf[0]); - c->tx_dma_buf[0]=NULL; + c->tx_dma_buf[0] = NULL; } - chk=read_zsreg(c,R0); + chk = read_zsreg(c, R0); write_zsreg(c, R3, c->regs[R3]); - z8530_rtsdtr(c,0); + z8530_rtsdtr(c, 0); spin_unlock_irqrestore(c->lock, flags); return 0; } - EXPORT_SYMBOL(z8530_sync_dma_close); /** @@ -1050,65 +968,58 @@ int z8530_sync_txdma_open(struct net_device *dev, struct z8530_channel *c) printk("Opening sync interface for TX-DMA\n"); c->sync = 1; - c->mtu = dev->mtu+64; + c->mtu = dev->mtu + 64; c->count = 0; c->skb = NULL; c->skb2 = NULL; - - /* - * Allocate the DMA flip buffers. Limit by page size. + + /* Allocate the DMA flip buffers. Limit by page size. * Everyone runs 1500 mtu or less on wan links so this * should be fine. */ - - if(c->mtu > PAGE_SIZE/2) + + if (c->mtu > PAGE_SIZE / 2) return -EMSGSIZE; - - c->tx_dma_buf[0]=(void *)get_zeroed_page(GFP_KERNEL|GFP_DMA); - if(c->tx_dma_buf[0]==NULL) + + c->tx_dma_buf[0] = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + if (!c->tx_dma_buf[0]) return -ENOBUFS; - c->tx_dma_buf[1] = c->tx_dma_buf[0] + PAGE_SIZE/2; - + c->tx_dma_buf[1] = c->tx_dma_buf[0] + PAGE_SIZE / 2; spin_lock_irqsave(c->lock, cflags); - /* - * Load the PIO receive ring + /* Load the PIO receive ring */ z8530_rx_done(c); z8530_rx_done(c); - /* - * Load the DMA interfaces up + /* Load the DMA interfaces up */ c->rxdma_on = 0; c->txdma_on = 0; - - c->tx_dma_used=0; - c->dma_num=0; - c->dma_ready=1; + + c->tx_dma_used = 0; + c->dma_num = 0; + c->dma_ready = 1; c->dma_tx = 1; - /* - * Enable DMA control mode + /* Enable DMA control mode */ - /* - * TX DMA via DIR/REQ - */ - c->regs[R14]|= DTRREQ; - write_zsreg(c, R14, c->regs[R14]); - - c->regs[R1]&= ~TxINT_ENAB; + /* TX DMA via DIR/REQ + */ + c->regs[R14] |= DTRREQ; + write_zsreg(c, R14, c->regs[R14]); + + c->regs[R1] &= ~TxINT_ENAB; write_zsreg(c, R1, c->regs[R1]); - - /* - * Set up the DMA configuration - */ - + + /* Set up the DMA configuration + */ + dflags = claim_dma_lock(); disable_dma(c->txdma); @@ -1117,23 +1028,21 @@ int z8530_sync_txdma_open(struct net_device *dev, struct z8530_channel *c) disable_dma(c->txdma); release_dma_lock(dflags); - - /* - * Select the DMA interrupt handlers + + /* Select the DMA interrupt handlers */ c->rxdma_on = 0; c->txdma_on = 1; c->tx_dma_used = 1; - + c->irqs = &z8530_txdma_sync; - z8530_rtsdtr(c,1); - write_zsreg(c, R3, c->regs[R3]|RxENABLE); + z8530_rtsdtr(c, 1); + write_zsreg(c, R3, c->regs[R3] | RxENABLE); spin_unlock_irqrestore(c->lock, cflags); - + return 0; } - EXPORT_SYMBOL(z8530_sync_txdma_open); /** @@ -1141,7 +1050,7 @@ EXPORT_SYMBOL(z8530_sync_txdma_open); * @dev: Network device to detach * @c: Z8530 channel to move into discard mode * - * Shut down a DMA/PIO split mode synchronous interface. Halt the DMA, + * Shut down a DMA/PIO split mode synchronous interface. Halt the DMA, * and free the buffers. */ @@ -1150,17 +1059,15 @@ int z8530_sync_txdma_close(struct net_device *dev, struct z8530_channel *c) unsigned long dflags, cflags; u8 chk; - spin_lock_irqsave(c->lock, cflags); - + c->irqs = &z8530_nop; c->max = 0; c->sync = 0; - - /* - * Disable the PC DMA channels + + /* Disable the PC DMA channels */ - + dflags = claim_dma_lock(); disable_dma(c->txdma); @@ -1170,41 +1077,34 @@ int z8530_sync_txdma_close(struct net_device *dev, struct z8530_channel *c) release_dma_lock(dflags); - /* - * Disable DMA control mode + /* Disable DMA control mode */ - - c->regs[R1]&= ~WT_RDY_ENAB; - write_zsreg(c, R1, c->regs[R1]); - c->regs[R1]&= ~(WT_RDY_RT|WT_FN_RDYFN|INT_ERR_Rx); - c->regs[R1]|= INT_ALL_Rx; + + c->regs[R1] &= ~WT_RDY_ENAB; write_zsreg(c, R1, c->regs[R1]); - c->regs[R14]&= ~DTRREQ; - write_zsreg(c, R14, c->regs[R14]); - - if(c->tx_dma_buf[0]) - { + c->regs[R1] &= ~(WT_RDY_RT | WT_FN_RDYFN | INT_ERR_Rx); + c->regs[R1] |= INT_ALL_Rx; + write_zsreg(c, R1, c->regs[R1]); + c->regs[R14] &= ~DTRREQ; + write_zsreg(c, R14, c->regs[R14]); + + if (c->tx_dma_buf[0]) { free_page((unsigned long)c->tx_dma_buf[0]); - c->tx_dma_buf[0]=NULL; + c->tx_dma_buf[0] = NULL; } - chk=read_zsreg(c,R0); + chk = read_zsreg(c, R0); write_zsreg(c, R3, c->regs[R3]); - z8530_rtsdtr(c,0); + z8530_rtsdtr(c, 0); spin_unlock_irqrestore(c->lock, cflags); return 0; } - - EXPORT_SYMBOL(z8530_sync_txdma_close); - -/* - * Name strings for Z8530 chips. SGI claim to have a 130, Zilog deny +/* Name strings for Z8530 chips. SGI claim to have a 130, Zilog deny * it exists... */ - -static const char *z8530_type_name[]={ +static const char * const z8530_type_name[] = { "Z8530", "Z85C30", "Z85230" @@ -1224,78 +1124,71 @@ static const char *z8530_type_name[]={ void z8530_describe(struct z8530_dev *dev, char *mapping, unsigned long io) { pr_info("%s: %s found at %s 0x%lX, IRQ %d\n", - dev->name, + dev->name, z8530_type_name[dev->type], mapping, Z8530_PORT_OF(io), dev->irq); } - EXPORT_SYMBOL(z8530_describe); -/* - * Locked operation part of the z8530 init code +/* Locked operation part of the z8530 init code */ - static inline int do_z8530_init(struct z8530_dev *dev) { /* NOP the interrupt handlers first - we might get a - floating IRQ transition when we reset the chip */ - dev->chanA.irqs=&z8530_nop; - dev->chanB.irqs=&z8530_nop; - dev->chanA.dcdcheck=DCD; - dev->chanB.dcdcheck=DCD; + * floating IRQ transition when we reset the chip + */ + dev->chanA.irqs = &z8530_nop; + dev->chanB.irqs = &z8530_nop; + dev->chanA.dcdcheck = DCD; + dev->chanB.dcdcheck = DCD; /* Reset the chip */ write_zsreg(&dev->chanA, R9, 0xC0); udelay(200); /* Now check its valid */ write_zsreg(&dev->chanA, R12, 0xAA); - if(read_zsreg(&dev->chanA, R12)!=0xAA) + if (read_zsreg(&dev->chanA, R12) != 0xAA) return -ENODEV; write_zsreg(&dev->chanA, R12, 0x55); - if(read_zsreg(&dev->chanA, R12)!=0x55) + if (read_zsreg(&dev->chanA, R12) != 0x55) return -ENODEV; - - dev->type=Z8530; - - /* - * See the application note. + + dev->type = Z8530; + + /* See the application note. */ - + write_zsreg(&dev->chanA, R15, 0x01); - - /* - * If we can set the low bit of R15 then + + /* If we can set the low bit of R15 then * the chip is enhanced. */ - - if(read_zsreg(&dev->chanA, R15)==0x01) - { + + if (read_zsreg(&dev->chanA, R15) == 0x01) { /* This C30 versus 230 detect is from Klaus Kudielka's dmascc */ /* Put a char in the fifo */ write_zsreg(&dev->chanA, R8, 0); - if(read_zsreg(&dev->chanA, R0)&Tx_BUF_EMP) + if (read_zsreg(&dev->chanA, R0) & Tx_BUF_EMP) dev->type = Z85230; /* Has a FIFO */ else dev->type = Z85C30; /* Z85C30, 1 byte FIFO */ } - - /* - * The code assumes R7' and friends are + + /* The code assumes R7' and friends are * off. Use write_zsext() for these and keep * this bit clear. */ - + write_zsreg(&dev->chanA, R15, 0); - - /* - * At this point it looks like the chip is behaving + + /* At this point it looks like the chip is behaving */ - + memcpy(dev->chanA.regs, reg_init, 16); - memcpy(dev->chanB.regs, reg_init ,16); - + memcpy(dev->chanB.regs, reg_init, 16); + return 0; } @@ -1332,36 +1225,32 @@ int z8530_init(struct z8530_dev *dev) return ret; } - - EXPORT_SYMBOL(z8530_init); /** * z8530_shutdown - Shutdown a Z8530 device * @dev: The Z8530 chip to shutdown * - * We set the interrupt handlers to silence any interrupts. We then + * We set the interrupt handlers to silence any interrupts. We then * reset the chip and wait 100uS to be sure the reset completed. Just * in case the caller then tries to do stuff. * * This is called without the lock held */ - int z8530_shutdown(struct z8530_dev *dev) { unsigned long flags; /* Reset the chip */ spin_lock_irqsave(&dev->lock, flags); - dev->chanA.irqs=&z8530_nop; - dev->chanB.irqs=&z8530_nop; + dev->chanA.irqs = &z8530_nop; + dev->chanB.irqs = &z8530_nop; write_zsreg(&dev->chanA, R9, 0xC0); /* We must lock the udelay, the chip is offlimits here */ udelay(100); spin_unlock_irqrestore(&dev->lock, flags); return 0; } - EXPORT_SYMBOL(z8530_shutdown); /** @@ -1370,7 +1259,7 @@ EXPORT_SYMBOL(z8530_shutdown); * @rtable: table of register, value pairs * FIXME: ioctl to allow user uploaded tables * - * Load a Z8530 channel up from the system data. We use +16 to + * Load a Z8530 channel up from the system data. We use +16 to * indicate the "prime" registers. The value 255 terminates the * table. */ @@ -1381,41 +1270,39 @@ int z8530_channel_load(struct z8530_channel *c, u8 *rtable) spin_lock_irqsave(c->lock, flags); - while(*rtable!=255) - { - int reg=*rtable++; - if(reg>0x0F) - write_zsreg(c, R15, c->regs[15]|1); - write_zsreg(c, reg&0x0F, *rtable); - if(reg>0x0F) - write_zsreg(c, R15, c->regs[15]&~1); - c->regs[reg]=*rtable++; + while (*rtable != 255) { + int reg = *rtable++; + + if (reg > 0x0F) + write_zsreg(c, R15, c->regs[15] | 1); + write_zsreg(c, reg & 0x0F, *rtable); + if (reg > 0x0F) + write_zsreg(c, R15, c->regs[15] & ~1); + c->regs[reg] = *rtable++; } - c->rx_function=z8530_null_rx; - c->skb=NULL; - c->tx_skb=NULL; - c->tx_next_skb=NULL; - c->mtu=1500; - c->max=0; - c->count=0; - c->status=read_zsreg(c, R0); - c->sync=1; - write_zsreg(c, R3, c->regs[R3]|RxENABLE); + c->rx_function = z8530_null_rx; + c->skb = NULL; + c->tx_skb = NULL; + c->tx_next_skb = NULL; + c->mtu = 1500; + c->max = 0; + c->count = 0; + c->status = read_zsreg(c, R0); + c->sync = 1; + write_zsreg(c, R3, c->regs[R3] | RxENABLE); spin_unlock_irqrestore(c->lock, flags); return 0; } - EXPORT_SYMBOL(z8530_channel_load); - /** * z8530_tx_begin - Begin packet transmission * @c: The Z8530 channel to kick * * This is the speed sensitive side of transmission. If we are called * and no buffer is being transmitted we commence the next buffer. If - * nothing is queued we idle the sync. + * nothing is queued we idle the sync. * * Note: We are handling this code path in the interrupt path, keep it * fast or bad things will happen. @@ -1426,85 +1313,68 @@ EXPORT_SYMBOL(z8530_channel_load); static void z8530_tx_begin(struct z8530_channel *c) { unsigned long flags; - if(c->tx_skb) + + if (c->tx_skb) return; - - c->tx_skb=c->tx_next_skb; - c->tx_next_skb=NULL; - c->tx_ptr=c->tx_next_ptr; - - if(c->tx_skb==NULL) - { + + c->tx_skb = c->tx_next_skb; + c->tx_next_skb = NULL; + c->tx_ptr = c->tx_next_ptr; + + if (!c->tx_skb) { /* Idle on */ - if(c->dma_tx) - { - flags=claim_dma_lock(); + if (c->dma_tx) { + flags = claim_dma_lock(); disable_dma(c->txdma); - /* - * Check if we crapped out. + /* Check if we crapped out. */ - if (get_dma_residue(c->txdma)) - { + if (get_dma_residue(c->txdma)) { c->netdevice->stats.tx_dropped++; c->netdevice->stats.tx_fifo_errors++; } release_dma_lock(flags); } - c->txcount=0; - } - else - { - c->txcount=c->tx_skb->len; - - - if(c->dma_tx) - { - /* - * FIXME. DMA is broken for the original 8530, + c->txcount = 0; + } else { + c->txcount = c->tx_skb->len; + + if (c->dma_tx) { + /* FIXME. DMA is broken for the original 8530, * on the older parts we need to set a flag and * wait for a further TX interrupt to fire this - * stage off + * stage off */ - - flags=claim_dma_lock(); + + flags = claim_dma_lock(); disable_dma(c->txdma); - /* - * These two are needed by the 8530/85C30 + /* These two are needed by the 8530/85C30 * and must be issued when idling. */ - - if(c->dev->type!=Z85230) - { + if (c->dev->type != Z85230) { write_zsctrl(c, RES_Tx_CRC); write_zsctrl(c, RES_EOM_L); - } - write_zsreg(c, R10, c->regs[10]&~ABUNDER); + } + write_zsreg(c, R10, c->regs[10] & ~ABUNDER); clear_dma_ff(c->txdma); set_dma_addr(c->txdma, virt_to_bus(c->tx_ptr)); set_dma_count(c->txdma, c->txcount); enable_dma(c->txdma); release_dma_lock(flags); write_zsctrl(c, RES_EOM_L); - write_zsreg(c, R5, c->regs[R5]|TxENAB); - } - else - { - + write_zsreg(c, R5, c->regs[R5] | TxENAB); + } else { /* ABUNDER off */ write_zsreg(c, R10, c->regs[10]); write_zsctrl(c, RES_Tx_CRC); - - while(c->txcount && (read_zsreg(c,R0)&Tx_BUF_EMP)) - { + + while (c->txcount && (read_zsreg(c, R0) & Tx_BUF_EMP)) { write_zsreg(c, R8, *c->tx_ptr++); c->txcount--; } - } } - /* - * Since we emptied tx_skb we can ask for more + /* Since we emptied tx_skb we can ask for more */ netif_wake_queue(c->netdevice); } @@ -1525,7 +1395,7 @@ static void z8530_tx_done(struct z8530_channel *c) struct sk_buff *skb; /* Actually this can happen.*/ - if (c->tx_skb == NULL) + if (!c->tx_skb) return; skb = c->tx_skb; @@ -1544,12 +1414,10 @@ static void z8530_tx_done(struct z8530_channel *c) * We point the receive handler at this function when idle. Instead * of processing the frames we get to throw them away. */ - void z8530_null_rx(struct z8530_channel *c, struct sk_buff *skb) { dev_kfree_skb_any(skb); } - EXPORT_SYMBOL(z8530_null_rx); /** @@ -1564,67 +1432,58 @@ EXPORT_SYMBOL(z8530_null_rx); * * Called with the lock held */ - static void z8530_rx_done(struct z8530_channel *c) { struct sk_buff *skb; int ct; - - /* - * Is our receive engine in DMA mode + + /* Is our receive engine in DMA mode */ - - if(c->rxdma_on) - { - /* - * Save the ready state and the buffer currently + if (c->rxdma_on) { + /* Save the ready state and the buffer currently * being used as the DMA target */ - - int ready=c->dma_ready; - unsigned char *rxb=c->rx_buf[c->dma_num]; + int ready = c->dma_ready; + unsigned char *rxb = c->rx_buf[c->dma_num]; unsigned long flags; - - /* - * Complete this DMA. Necessary to find the length - */ - - flags=claim_dma_lock(); - + + /* Complete this DMA. Necessary to find the length + */ + flags = claim_dma_lock(); + disable_dma(c->rxdma); clear_dma_ff(c->rxdma); - c->rxdma_on=0; - ct=c->mtu-get_dma_residue(c->rxdma); - if(ct<0) - ct=2; /* Shit happens.. */ - c->dma_ready=0; - - /* - * Normal case: the other slot is free, start the next DMA + c->rxdma_on = 0; + ct = c->mtu - get_dma_residue(c->rxdma); + if (ct < 0) + ct = 2; /* Shit happens.. */ + c->dma_ready = 0; + + /* Normal case: the other slot is free, start the next DMA * into it immediately. */ - - if(ready) - { - c->dma_num^=1; - set_dma_mode(c->rxdma, DMA_MODE_READ|0x10); + + if (ready) { + c->dma_num ^= 1; + set_dma_mode(c->rxdma, DMA_MODE_READ | 0x10); set_dma_addr(c->rxdma, virt_to_bus(c->rx_buf[c->dma_num])); set_dma_count(c->rxdma, c->mtu); c->rxdma_on = 1; enable_dma(c->rxdma); - /* Stop any frames that we missed the head of - from passing */ + /* Stop any frames that we missed the head of + * from passing + */ write_zsreg(c, R0, RES_Rx_CRC); - } - else + } else { /* Can't occur as we dont reenable the DMA irq until - after the flip is done */ + * after the flip is done + */ netdev_warn(c->netdevice, "DMA flip overrun!\n"); + } release_dma_lock(flags); - /* - * Shove the old buffer into an sk_buff. We can't DMA + /* Shove the old buffer into an sk_buff. We can't DMA * directly into one on a PC - it might be above the 16Mb * boundary. Optimisation - we could check to see if we * can avoid the copy. Optimisation 2 - make the memcpy @@ -1632,7 +1491,7 @@ static void z8530_rx_done(struct z8530_channel *c) */ skb = dev_alloc_skb(ct); - if (skb == NULL) { + if (!skb) { c->netdevice->stats.rx_dropped++; netdev_warn(c->netdevice, "Memory squeeze\n"); } else { @@ -1646,8 +1505,7 @@ static void z8530_rx_done(struct z8530_channel *c) RT_LOCK; skb = c->skb; - /* - * The game we play for non DMA is similar. We want to + /* The game we play for non DMA is similar. We want to * get the controller set up for the next packet as fast * as possible. We potentially only have one byte + the * fifo length for this. Thus we want to flip to the new @@ -1658,7 +1516,7 @@ static void z8530_rx_done(struct z8530_channel *c) * sync IRQ for the RT_LOCK area. * */ - ct=c->count; + ct = c->count; c->skb = c->skb2; c->count = 0; @@ -1673,15 +1531,13 @@ static void z8530_rx_done(struct z8530_channel *c) RT_UNLOCK; c->skb2 = dev_alloc_skb(c->mtu); - if (c->skb2 == NULL) - netdev_warn(c->netdevice, "memory squeeze\n"); - else + if (c->skb2) skb_put(c->skb2, c->mtu); + c->netdevice->stats.rx_packets++; c->netdevice->stats.rx_bytes += ct; } - /* - * If we received a frame we must now process it. + /* If we received a frame we must now process it. */ if (skb) { skb_trim(skb, ct); @@ -1702,9 +1558,10 @@ static void z8530_rx_done(struct z8530_channel *c) static inline int spans_boundary(struct sk_buff *skb) { - unsigned long a=(unsigned long)skb->data; - a^=(a+skb->len); - if(a&0x00010000) /* If the 64K bit is different.. */ + unsigned long a = (unsigned long)skb->data; + + a ^= (a + skb->len); + if (a & 0x00010000) /* If the 64K bit is different.. */ return 1; return 0; } @@ -1715,60 +1572,54 @@ static inline int spans_boundary(struct sk_buff *skb) * @skb: The packet to kick down the channel * * Queue a packet for transmission. Because we have rather - * hard to hit interrupt latencies for the Z85230 per packet + * hard to hit interrupt latencies for the Z85230 per packet * even in DMA mode we do the flip to DMA buffer if needed here * not in the IRQ. * - * Called from the network code. The lock is not held at this + * Called from the network code. The lock is not held at this * point. */ - netdev_tx_t z8530_queue_xmit(struct z8530_channel *c, struct sk_buff *skb) { unsigned long flags; - + netif_stop_queue(c->netdevice); - if(c->tx_next_skb) + if (c->tx_next_skb) return NETDEV_TX_BUSY; - /* PC SPECIFIC - DMA limits */ - - /* - * If we will DMA the transmit and its gone over the ISA bus + /* If we will DMA the transmit and its gone over the ISA bus * limit, then copy to the flip buffer */ - - if(c->dma_tx && ((unsigned long)(virt_to_bus(skb->data+skb->len))>=16*1024*1024 || spans_boundary(skb))) - { - /* - * Send the flip buffer, and flip the flippy bit. + + if (c->dma_tx && + ((unsigned long)(virt_to_bus(skb->data + skb->len)) >= + 16 * 1024 * 1024 || spans_boundary(skb))) { + /* Send the flip buffer, and flip the flippy bit. * We don't care which is used when just so long as * we never use the same buffer twice in a row. Since * only one buffer can be going out at a time the other * has to be safe. */ - c->tx_next_ptr=c->tx_dma_buf[c->tx_dma_used]; - c->tx_dma_used^=1; /* Flip temp buffer */ + c->tx_next_ptr = c->tx_dma_buf[c->tx_dma_used]; + c->tx_dma_used ^= 1; /* Flip temp buffer */ skb_copy_from_linear_data(skb, c->tx_next_ptr, skb->len); + } else { + c->tx_next_ptr = skb->data; } - else - c->tx_next_ptr=skb->data; RT_LOCK; - c->tx_next_skb=skb; + c->tx_next_skb = skb; RT_UNLOCK; - + spin_lock_irqsave(c->lock, flags); z8530_tx_begin(c); spin_unlock_irqrestore(c->lock, flags); - + return NETDEV_TX_OK; } - EXPORT_SYMBOL(z8530_queue_xmit); -/* - * Module support +/* Module support */ static const char banner[] __initconst = KERN_INFO "Generic Z85C30/Z85230 interface driver v0.02\n"; diff --git a/drivers/net/wireless/ath/ath10k/ahb.c b/drivers/net/wireless/ath/ath10k/ahb.c index 869524852fba..ab8f77ae5e66 100644 --- a/drivers/net/wireless/ath/ath10k/ahb.c +++ b/drivers/net/wireless/ath/ath10k/ahb.c @@ -442,14 +442,7 @@ static int ath10k_ahb_resource_init(struct ath10k *ar) pdev = ar_ahb->pdev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) { - ath10k_err(ar, "failed to get memory resource\n"); - ret = -ENXIO; - goto out; - } - - ar_ahb->mem = devm_ioremap_resource(&pdev->dev, res); + ar_ahb->mem = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(ar_ahb->mem)) { ath10k_err(ar, "mem ioremap error\n"); ret = PTR_ERR(ar_ahb->mem); diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h index 648ed36f845f..5aeff2d9f6cf 100644 --- a/drivers/net/wireless/ath/ath10k/core.h +++ b/drivers/net/wireless/ath/ath10k/core.h @@ -301,7 +301,7 @@ struct ath10k_fw_stats_pdev { s32 underrun; u32 hw_paused; s32 tx_abort; - s32 mpdus_requed; + s32 mpdus_requeued; u32 tx_ko; u32 data_rc; u32 self_triggers; diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c index fd052f6ed019..39378e3f9b2b 100644 --- a/drivers/net/wireless/ath/ath10k/debug.c +++ b/drivers/net/wireless/ath/ath10k/debug.c @@ -1105,7 +1105,7 @@ static const char ath10k_gstrings_stats[][ETH_GSTRING_LEN] = { "d_tx_ppdu_reaped", "d_tx_fifo_underrun", "d_tx_ppdu_abort", - "d_tx_mpdu_requed", + "d_tx_mpdu_requeued", "d_tx_excessive_retries", "d_tx_hw_rate", "d_tx_dropped_sw_retries", @@ -1205,7 +1205,7 @@ void ath10k_debug_get_et_stats(struct ieee80211_hw *hw, data[i++] = pdev_stats->hw_reaped; data[i++] = pdev_stats->underrun; data[i++] = pdev_stats->tx_abort; - data[i++] = pdev_stats->mpdus_requed; + data[i++] = pdev_stats->mpdus_requeued; data[i++] = pdev_stats->tx_ko; data[i++] = pdev_stats->data_rc; data[i++] = pdev_stats->sw_retry_failure; diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h index dbc8aef82a65..ec689e3ce48a 100644 --- a/drivers/net/wireless/ath/ath10k/htt.h +++ b/drivers/net/wireless/ath/ath10k/htt.h @@ -1283,8 +1283,8 @@ struct htt_dbg_stats_wal_tx_stats { /* Num PPDUs cleaned up in TX abort */ __le32 tx_abort; - /* Num MPDUs requed by SW */ - __le32 mpdus_requed; + /* Num MPDUs requeued by SW */ + __le32 mpdus_requeued; /* excessive retries */ __le32 tx_ko; diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index 7ffb5d5b2a70..adbaeb67eedf 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -1787,7 +1787,6 @@ static bool ath10k_htt_rx_h_frag_pn_check(struct ath10k *ar, struct ath10k_peer *peer; union htt_rx_pn_t *last_pn, new_pn = {0}; struct ieee80211_hdr *hdr; - bool more_frags; u8 tid, frag_number; u32 seq; @@ -1805,7 +1804,6 @@ static bool ath10k_htt_rx_h_frag_pn_check(struct ath10k *ar, last_pn = &peer->frag_tids_last_pn[tid]; new_pn.pn48 = ath10k_htt_rx_h_get_pn(ar, skb, offset, enctype); - more_frags = ieee80211_has_morefrags(hdr->frame_control); frag_number = le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_FRAG; seq = (__le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_SEQ) >> 4; diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 5ce4f8d038b9..c272b290fa73 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -5592,6 +5592,7 @@ static int ath10k_add_interface(struct ieee80211_hw *hw, if (arvif->nohwcrypt && !test_bit(ATH10K_FLAG_RAW_MODE, &ar->dev_flags)) { + ret = -EINVAL; ath10k_warn(ar, "cryptmode module param needed for sw crypto\n"); goto err; } diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c index e7fde635e0ee..71878ab35b93 100644 --- a/drivers/net/wireless/ath/ath10k/pci.c +++ b/drivers/net/wireless/ath/ath10k/pci.c @@ -3685,8 +3685,10 @@ static int ath10k_pci_probe(struct pci_dev *pdev, ath10k_pci_soc_read32(ar, SOC_CHIP_ID_ADDRESS); if (bus_params.chip_id != 0xffffffff) { if (!ath10k_pci_chip_is_supported(pdev->device, - bus_params.chip_id)) + bus_params.chip_id)) { + ret = -ENODEV; goto err_unsupported; + } } } @@ -3697,11 +3699,15 @@ static int ath10k_pci_probe(struct pci_dev *pdev, } bus_params.chip_id = ath10k_pci_soc_read32(ar, SOC_CHIP_ID_ADDRESS); - if (bus_params.chip_id == 0xffffffff) + if (bus_params.chip_id == 0xffffffff) { + ret = -ENODEV; goto err_unsupported; + } - if (!ath10k_pci_chip_is_supported(pdev->device, bus_params.chip_id)) - goto err_free_irq; + if (!ath10k_pci_chip_is_supported(pdev->device, bus_params.chip_id)) { + ret = -ENODEV; + goto err_unsupported; + } ret = ath10k_core_register(ar, &bus_params); if (ret) { diff --git a/drivers/net/wireless/ath/ath10k/pci.h b/drivers/net/wireless/ath/ath10k/pci.h index 862d0901c5b8..cf64898b9447 100644 --- a/drivers/net/wireless/ath/ath10k/pci.h +++ b/drivers/net/wireless/ath/ath10k/pci.h @@ -235,7 +235,6 @@ u16 ath10k_pci_hif_get_free_queue_number(struct ath10k *ar, u8 pipe); void ath10k_pci_hif_power_down(struct ath10k *ar); int ath10k_pci_alloc_pipes(struct ath10k *ar); void ath10k_pci_free_pipes(struct ath10k *ar); -void ath10k_pci_free_pipes(struct ath10k *ar); void ath10k_pci_rx_replenish_retry(struct timer_list *t); void ath10k_pci_ce_deinit(struct ath10k *ar); void ath10k_pci_init_napi(struct ath10k *ar); diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index d48b922215eb..b8a4bbfe10b8 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -2795,7 +2795,7 @@ void ath10k_wmi_event_chan_info(struct ath10k *ar, struct sk_buff *skb) switch (ar->scan.state) { case ATH10K_SCAN_IDLE: case ATH10K_SCAN_STARTING: - ath10k_warn(ar, "received chan info event without a scan request, ignoring\n"); + ath10k_dbg(ar, ATH10K_DBG_WMI, "received chan info event without a scan request, ignoring\n"); goto exit; case ATH10K_SCAN_RUNNING: case ATH10K_SCAN_ABORTING: @@ -2867,7 +2867,7 @@ void ath10k_wmi_pull_pdev_stats_tx(const struct wmi_pdev_stats_tx *src, dst->hw_reaped = __le32_to_cpu(src->hw_reaped); dst->underrun = __le32_to_cpu(src->underrun); dst->tx_abort = __le32_to_cpu(src->tx_abort); - dst->mpdus_requed = __le32_to_cpu(src->mpdus_requed); + dst->mpdus_requeued = __le32_to_cpu(src->mpdus_requeued); dst->tx_ko = __le32_to_cpu(src->tx_ko); dst->data_rc = __le32_to_cpu(src->data_rc); dst->self_triggers = __le32_to_cpu(src->self_triggers); @@ -2895,7 +2895,7 @@ ath10k_wmi_10_4_pull_pdev_stats_tx(const struct wmi_10_4_pdev_stats_tx *src, dst->hw_reaped = __le32_to_cpu(src->hw_reaped); dst->underrun = __le32_to_cpu(src->underrun); dst->tx_abort = __le32_to_cpu(src->tx_abort); - dst->mpdus_requed = __le32_to_cpu(src->mpdus_requed); + dst->mpdus_requeued = __le32_to_cpu(src->mpdus_requeued); dst->tx_ko = __le32_to_cpu(src->tx_ko); dst->data_rc = __le32_to_cpu(src->data_rc); dst->self_triggers = __le32_to_cpu(src->self_triggers); @@ -8270,7 +8270,7 @@ ath10k_wmi_fw_pdev_tx_stats_fill(const struct ath10k_fw_stats_pdev *pdev, len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "PPDUs cleaned", pdev->tx_abort); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", - "MPDUs requed", pdev->mpdus_requed); + "MPDUs requeued", pdev->mpdus_requeued); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "Excessive retries", pdev->tx_ko); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h index d870f7067cb7..41c1a3d339c2 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.h +++ b/drivers/net/wireless/ath/ath10k/wmi.h @@ -4371,8 +4371,8 @@ struct wmi_pdev_stats_tx { /* Num PPDUs cleaned up in TX abort */ __le32 tx_abort; - /* Num MPDUs requed by SW */ - __le32 mpdus_requed; + /* Num MPDUs requeued by SW */ + __le32 mpdus_requeued; /* excessive retries */ __le32 tx_ko; @@ -4444,8 +4444,8 @@ struct wmi_10_4_pdev_stats_tx { /* Num PPDUs cleaned up in TX abort */ __le32 tx_abort; - /* Num MPDUs requed by SW */ - __le32 mpdus_requed; + /* Num MPDUs requeued by SW */ + __le32 mpdus_requeued; /* excessive retries */ __le32 tx_ko; @@ -7418,7 +7418,6 @@ int ath10k_wmi_wait_for_unified_ready(struct ath10k *ar); struct sk_buff *ath10k_wmi_alloc_skb(struct ath10k *ar, u32 len); int ath10k_wmi_connect(struct ath10k *ar); -struct sk_buff *ath10k_wmi_alloc_skb(struct ath10k *ar, u32 len); int ath10k_wmi_cmd_send(struct ath10k *ar, struct sk_buff *skb, u32 cmd_id); int ath10k_wmi_cmd_send_nowait(struct ath10k *ar, struct sk_buff *skb, u32 cmd_id); diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c index 77ce3347ab86..969bf1a590d9 100644 --- a/drivers/net/wireless/ath/ath11k/core.c +++ b/drivers/net/wireless/ath/ath11k/core.c @@ -70,6 +70,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .cold_boot_calib = true, .supports_suspend = false, .hal_desc_sz = sizeof(struct hal_rx_desc_ipq8074), + .fix_l1ss = true, }, { .hw_rev = ATH11K_HW_IPQ6018_HW10, @@ -110,6 +111,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .cold_boot_calib = true, .supports_suspend = false, .hal_desc_sz = sizeof(struct hal_rx_desc_ipq8074), + .fix_l1ss = true, }, { .name = "qca6390 hw2.0", @@ -149,6 +151,7 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .cold_boot_calib = false, .supports_suspend = true, .hal_desc_sz = sizeof(struct hal_rx_desc_ipq8074), + .fix_l1ss = true, }, { .name = "qcn9074 hw1.0", @@ -186,6 +189,47 @@ static const struct ath11k_hw_params ath11k_hw_params[] = { .cold_boot_calib = false, .supports_suspend = false, .hal_desc_sz = sizeof(struct hal_rx_desc_qcn9074), + .fix_l1ss = true, + }, + { + .name = "wcn6855 hw2.0", + .hw_rev = ATH11K_HW_WCN6855_HW20, + .fw = { + .dir = "WCN6855/hw2.0", + .board_size = 256 * 1024, + .cal_size = 256 * 1024, + }, + .max_radios = 3, + .bdf_addr = 0x4B0C0000, + .hw_ops = &wcn6855_ops, + .ring_mask = &ath11k_hw_ring_mask_qca6390, + .internal_sleep_clock = true, + .regs = &wcn6855_regs, + .qmi_service_ins_id = ATH11K_QMI_WLFW_SERVICE_INS_ID_V01_QCA6390, + .host_ce_config = ath11k_host_ce_config_qca6390, + .ce_count = 9, + .target_ce_config = ath11k_target_ce_config_wlan_qca6390, + .target_ce_count = 9, + .svc_to_ce_map = ath11k_target_service_to_ce_map_wlan_qca6390, + .svc_to_ce_map_len = 14, + .single_pdev_only = true, + .rxdma1_enable = false, + .num_rxmda_per_pdev = 2, + .rx_mac_buf_ring = true, + .vdev_start_delay = true, + .htt_peer_map_v2 = false, + .tcl_0_only = true, + .spectral_fft_sz = 0, + + .interface_modes = BIT(NL80211_IFTYPE_STATION) | + BIT(NL80211_IFTYPE_AP), + .supports_monitor = false, + .supports_shadow_regs = true, + .idle_ps = true, + .cold_boot_calib = false, + .supports_suspend = true, + .hal_desc_sz = sizeof(struct hal_rx_desc_wcn6855), + .fix_l1ss = false, }, }; @@ -488,7 +532,8 @@ static int ath11k_core_fetch_board_data_api_n(struct ath11k_base *ab, if (len < ALIGN(ie_len, 4)) { ath11k_err(ab, "invalid length for board ie_id %d ie_len %zu len %zu\n", ie_id, ie_len, len); - return -EINVAL; + ret = -EINVAL; + goto err; } switch (ie_id) { diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h index 55af982deca7..018fb2385f2a 100644 --- a/drivers/net/wireless/ath/ath11k/core.h +++ b/drivers/net/wireless/ath/ath11k/core.h @@ -107,6 +107,7 @@ enum ath11k_hw_rev { ATH11K_HW_QCA6390_HW20, ATH11K_HW_IPQ6018_HW10, ATH11K_HW_QCN9074_HW10, + ATH11K_HW_WCN6855_HW20, }; enum ath11k_firmware_mode { @@ -795,8 +796,8 @@ struct ath11k_fw_stats_pdev { s32 underrun; /* Num PPDUs cleaned up in TX abort */ s32 tx_abort; - /* Num MPDUs requed by SW */ - s32 mpdus_requed; + /* Num MPDUs requeued by SW */ + s32 mpdus_requeued; /* excessive retries */ u32 tx_ko; /* data hw rate code */ diff --git a/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c index ec93f14e6d2a..9e0c90da99d3 100644 --- a/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c +++ b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.c @@ -89,7 +89,7 @@ static inline void htt_print_tx_pdev_stats_cmn_tlv(const void *tag_buf, len += HTT_DBG_OUT(buf + len, buf_len - len, "tx_abort = %u", htt_stats_buf->tx_abort); len += HTT_DBG_OUT(buf + len, buf_len - len, "mpdu_requeued = %u", - htt_stats_buf->mpdu_requed); + htt_stats_buf->mpdu_requeued); len += HTT_DBG_OUT(buf + len, buf_len - len, "tx_xretry = %u", htt_stats_buf->tx_xretry); len += HTT_DBG_OUT(buf + len, buf_len - len, "data_rc = %u", diff --git a/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h index 567a26d485a9..d428f52003a4 100644 --- a/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h +++ b/drivers/net/wireless/ath/ath11k/debugfs_htt_stats.h @@ -147,7 +147,7 @@ struct htt_tx_pdev_stats_cmn_tlv { u32 hw_flush; u32 hw_filt; u32 tx_abort; - u32 mpdu_requed; + u32 mpdu_requeued; u32 tx_xretry; u32 data_rc; u32 mpdu_dropped_xretry; diff --git a/drivers/net/wireless/ath/ath11k/dp.c b/drivers/net/wireless/ath/ath11k/dp.c index 04f6c4e0658b..b0c8f6290099 100644 --- a/drivers/net/wireless/ath/ath11k/dp.c +++ b/drivers/net/wireless/ath/ath11k/dp.c @@ -342,7 +342,6 @@ static int ath11k_dp_srng_common_setup(struct ath11k_base *ab) struct ath11k_dp *dp = &ab->dp; struct hal_srng *srng; int i, ret; - u32 ring_hash_map; ret = ath11k_dp_srng_setup(ab, &dp->wbm_desc_rel_ring, HAL_SW2WBM_RELEASE, 0, 0, @@ -439,20 +438,9 @@ static int ath11k_dp_srng_common_setup(struct ath11k_base *ab) } /* When hash based routing of rx packet is enabled, 32 entries to map - * the hash values to the ring will be configured. Each hash entry uses - * three bits to map to a particular ring. The ring mapping will be - * 0:TCL, 1:SW1, 2:SW2, 3:SW3, 4:SW4, 5:Release, 6:FW and 7:Not used. + * the hash values to the ring will be configured. */ - ring_hash_map = HAL_HASH_ROUTING_RING_SW1 << 0 | - HAL_HASH_ROUTING_RING_SW2 << 3 | - HAL_HASH_ROUTING_RING_SW3 << 6 | - HAL_HASH_ROUTING_RING_SW4 << 9 | - HAL_HASH_ROUTING_RING_SW1 << 12 | - HAL_HASH_ROUTING_RING_SW2 << 15 | - HAL_HASH_ROUTING_RING_SW3 << 18 | - HAL_HASH_ROUTING_RING_SW4 << 21; - - ath11k_hal_reo_hw_setup(ab, ring_hash_map); + ab->hw_params.hw_ops->reo_setup(ab); return 0; diff --git a/drivers/net/wireless/ath/ath11k/hal.c b/drivers/net/wireless/ath/ath11k/hal.c index 08e3c72d9237..eaa0edca5576 100644 --- a/drivers/net/wireless/ath/ath11k/hal.c +++ b/drivers/net/wireless/ath/ath11k/hal.c @@ -382,6 +382,16 @@ static void ath11k_hal_srng_src_hw_init(struct ath11k_base *ab, val = FIELD_PREP(HAL_REO1_RING_ID_ENTRY_SIZE, srng->entry_size); ath11k_hif_write32(ab, reg_base + HAL_TCL1_RING_ID_OFFSET(ab), val); + if (srng->ring_id == HAL_SRNG_RING_ID_WBM_IDLE_LINK) { + ath11k_hif_write32(ab, reg_base, (u32)srng->ring_base_paddr); + val = FIELD_PREP(HAL_TCL1_RING_BASE_MSB_RING_BASE_ADDR_MSB, + ((u64)srng->ring_base_paddr >> + HAL_ADDR_MSB_REG_SHIFT)) | + FIELD_PREP(HAL_TCL1_RING_BASE_MSB_RING_SIZE, + (srng->entry_size * srng->num_entries)); + ath11k_hif_write32(ab, reg_base + HAL_TCL1_RING_BASE_MSB_OFFSET(ab), val); + } + /* interrupt setup */ /* NOTE: IPQ8074 v2 requires the interrupt timer threshold in the * unit of 8 usecs instead of 1 usec (as required by v1). diff --git a/drivers/net/wireless/ath/ath11k/hal.h b/drivers/net/wireless/ath/ath11k/hal.h index 91d1428b8b94..35ed3a14e200 100644 --- a/drivers/net/wireless/ath/ath11k/hal.h +++ b/drivers/net/wireless/ath/ath11k/hal.h @@ -120,6 +120,7 @@ struct ath11k_base; #define HAL_REO1_DEST_RING_CTRL_IX_1 0x00000008 #define HAL_REO1_DEST_RING_CTRL_IX_2 0x0000000c #define HAL_REO1_DEST_RING_CTRL_IX_3 0x00000010 +#define HAL_REO1_MISC_CTL 0x00000630 #define HAL_REO1_RING_BASE_LSB(ab) ab->hw_params.regs->hal_reo1_ring_base_lsb #define HAL_REO1_RING_BASE_MSB(ab) ab->hw_params.regs->hal_reo1_ring_base_msb #define HAL_REO1_RING_ID(ab) ab->hw_params.regs->hal_reo1_ring_id @@ -280,6 +281,7 @@ struct ath11k_base; #define HAL_REO1_GEN_ENABLE_FRAG_DST_RING GENMASK(25, 23) #define HAL_REO1_GEN_ENABLE_AGING_LIST_ENABLE BIT(2) #define HAL_REO1_GEN_ENABLE_AGING_FLUSH_ENABLE BIT(3) +#define HAL_REO1_MISC_CTL_FRAGMENT_DST_RING GENMASK(20, 17) /* CE ring bit field mask and shift */ #define HAL_CE_DST_R0_DEST_CTRL_MAX_LEN GENMASK(15, 0) @@ -906,7 +908,6 @@ void ath11k_hal_reo_qdesc_setup(void *vaddr, int tid, u32 ba_window_size, u32 start_seq, enum hal_pn_type type); void ath11k_hal_reo_init_cmd_ring(struct ath11k_base *ab, struct hal_srng *srng); -void ath11k_hal_reo_hw_setup(struct ath11k_base *ab, u32 ring_hash_map); void ath11k_hal_setup_link_idle_list(struct ath11k_base *ab, struct hal_wbm_idle_scatter_list *sbuf, u32 nsbufs, u32 tot_link_desc, diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.c b/drivers/net/wireless/ath/ath11k/hal_rx.c index fac2396edf32..325055ca41ab 100644 --- a/drivers/net/wireless/ath/ath11k/hal_rx.c +++ b/drivers/net/wireless/ath/ath11k/hal_rx.c @@ -801,43 +801,6 @@ void ath11k_hal_reo_init_cmd_ring(struct ath11k_base *ab, } } -void ath11k_hal_reo_hw_setup(struct ath11k_base *ab, u32 ring_hash_map) -{ - u32 reo_base = HAL_SEQ_WCSS_UMAC_REO_REG; - u32 val; - - val = ath11k_hif_read32(ab, reo_base + HAL_REO1_GEN_ENABLE); - - val &= ~HAL_REO1_GEN_ENABLE_FRAG_DST_RING; - val |= FIELD_PREP(HAL_REO1_GEN_ENABLE_FRAG_DST_RING, - HAL_SRNG_RING_ID_REO2SW1) | - FIELD_PREP(HAL_REO1_GEN_ENABLE_AGING_LIST_ENABLE, 1) | - FIELD_PREP(HAL_REO1_GEN_ENABLE_AGING_FLUSH_ENABLE, 1); - ath11k_hif_write32(ab, reo_base + HAL_REO1_GEN_ENABLE, val); - - ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_0(ab), - HAL_DEFAULT_REO_TIMEOUT_USEC); - ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_1(ab), - HAL_DEFAULT_REO_TIMEOUT_USEC); - ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_2(ab), - HAL_DEFAULT_REO_TIMEOUT_USEC); - ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_3(ab), - HAL_DEFAULT_REO_TIMEOUT_USEC); - - ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_0, - FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP, - ring_hash_map)); - ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_1, - FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP, - ring_hash_map)); - ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_2, - FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP, - ring_hash_map)); - ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_3, - FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP, - ring_hash_map)); -} - static enum hal_rx_mon_status ath11k_hal_rx_parse_mon_status_tlv(struct ath11k_base *ab, struct hal_rx_mon_ppdu_info *ppdu_info, @@ -1128,12 +1091,9 @@ ath11k_hal_rx_parse_mon_status_tlv(struct ath11k_base *ab, break; } case HAL_RX_MPDU_START: { - struct hal_rx_mpdu_info *mpdu_info = - (struct hal_rx_mpdu_info *)tlv_data; u16 peer_id; - peer_id = FIELD_GET(HAL_RX_MPDU_INFO_INFO0_PEERID, - __le32_to_cpu(mpdu_info->info0)); + peer_id = ab->hw_params.hw_ops->mpdu_info_get_peerid(tlv_data); if (peer_id) ppdu_info->peer_id = peer_id; break; diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.h b/drivers/net/wireless/ath/ath11k/hal_rx.h index d464a270c049..0f1f04b812b9 100644 --- a/drivers/net/wireless/ath/ath11k/hal_rx.h +++ b/drivers/net/wireless/ath/ath11k/hal_rx.h @@ -254,12 +254,20 @@ struct hal_rx_phyrx_rssi_legacy_info { } __packed; #define HAL_RX_MPDU_INFO_INFO0_PEERID GENMASK(31, 16) +#define HAL_RX_MPDU_INFO_INFO0_PEERID_WCN6855 GENMASK(15, 0) + struct hal_rx_mpdu_info { __le32 rsvd0; __le32 info0; __le32 rsvd1[21]; } __packed; +struct hal_rx_mpdu_info_wcn6855 { + __le32 rsvd0[8]; + __le32 info0; + __le32 rsvd1[14]; +} __packed; + #define HAL_RX_PPDU_END_DURATION GENMASK(23, 0) struct hal_rx_ppdu_end_duration { __le32 rsvd0[9]; diff --git a/drivers/net/wireless/ath/ath11k/hw.c b/drivers/net/wireless/ath/ath11k/hw.c index 377ae8d5b58f..d9596903b0a5 100644 --- a/drivers/net/wireless/ath/ath11k/hw.c +++ b/drivers/net/wireless/ath/ath11k/hw.c @@ -10,6 +10,7 @@ #include "hw.h" #include "core.h" #include "ce.h" +#include "hif.h" /* Map from pdev index to hw mac index */ static u8 ath11k_hw_ipq8074_mac_from_pdev_id(int pdev_idx) @@ -45,6 +46,13 @@ static void ath11k_hw_qcn9074_tx_mesh_enable(struct ath11k_base *ab, true); } +static void ath11k_hw_wcn6855_tx_mesh_enable(struct ath11k_base *ab, + struct hal_tcl_data_cmd *tcl_cmd) +{ + tcl_cmd->info3 |= FIELD_PREP(HAL_QCN9074_TCL_DATA_CMD_INFO3_MESH_ENABLE, + true); +} + static void ath11k_init_wmi_config_qca6390(struct ath11k_base *ab, struct target_resource_config *config) { @@ -91,6 +99,52 @@ static void ath11k_init_wmi_config_qca6390(struct ath11k_base *ab, config->num_keep_alive_pattern = 0; } +static void ath11k_hw_ipq8074_reo_setup(struct ath11k_base *ab) +{ + u32 reo_base = HAL_SEQ_WCSS_UMAC_REO_REG; + u32 val; + /* Each hash entry uses three bits to map to a particular ring. */ + u32 ring_hash_map = HAL_HASH_ROUTING_RING_SW1 << 0 | + HAL_HASH_ROUTING_RING_SW2 << 3 | + HAL_HASH_ROUTING_RING_SW3 << 6 | + HAL_HASH_ROUTING_RING_SW4 << 9 | + HAL_HASH_ROUTING_RING_SW1 << 12 | + HAL_HASH_ROUTING_RING_SW2 << 15 | + HAL_HASH_ROUTING_RING_SW3 << 18 | + HAL_HASH_ROUTING_RING_SW4 << 21; + + val = ath11k_hif_read32(ab, reo_base + HAL_REO1_GEN_ENABLE); + + val &= ~HAL_REO1_GEN_ENABLE_FRAG_DST_RING; + val |= FIELD_PREP(HAL_REO1_GEN_ENABLE_FRAG_DST_RING, + HAL_SRNG_RING_ID_REO2SW1) | + FIELD_PREP(HAL_REO1_GEN_ENABLE_AGING_LIST_ENABLE, 1) | + FIELD_PREP(HAL_REO1_GEN_ENABLE_AGING_FLUSH_ENABLE, 1); + ath11k_hif_write32(ab, reo_base + HAL_REO1_GEN_ENABLE, val); + + ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_0(ab), + HAL_DEFAULT_REO_TIMEOUT_USEC); + ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_1(ab), + HAL_DEFAULT_REO_TIMEOUT_USEC); + ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_2(ab), + HAL_DEFAULT_REO_TIMEOUT_USEC); + ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_3(ab), + HAL_DEFAULT_REO_TIMEOUT_USEC); + + ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_0, + FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP, + ring_hash_map)); + ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_1, + FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP, + ring_hash_map)); + ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_2, + FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP, + ring_hash_map)); + ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_3, + FIELD_PREP(HAL_REO_DEST_RING_CTRL_HASH_RING_MAP, + ring_hash_map)); +} + static void ath11k_init_wmi_config_ipq8074(struct ath11k_base *ab, struct target_resource_config *config) { @@ -489,6 +543,228 @@ static u8 *ath11k_hw_qcn9074_rx_desc_get_msdu_payload(struct hal_rx_desc *desc) return &desc->u.qcn9074.msdu_payload[0]; } +static bool ath11k_hw_wcn6855_rx_desc_get_first_msdu(struct hal_rx_desc *desc) +{ + return !!FIELD_GET(RX_MSDU_END_INFO2_FIRST_MSDU_WCN6855, + __le32_to_cpu(desc->u.wcn6855.msdu_end.info2)); +} + +static bool ath11k_hw_wcn6855_rx_desc_get_last_msdu(struct hal_rx_desc *desc) +{ + return !!FIELD_GET(RX_MSDU_END_INFO2_LAST_MSDU_WCN6855, + __le32_to_cpu(desc->u.wcn6855.msdu_end.info2)); +} + +static u8 ath11k_hw_wcn6855_rx_desc_get_l3_pad_bytes(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MSDU_END_INFO2_L3_HDR_PADDING, + __le32_to_cpu(desc->u.wcn6855.msdu_end.info2)); +} + +static u8 *ath11k_hw_wcn6855_rx_desc_get_hdr_status(struct hal_rx_desc *desc) +{ + return desc->u.wcn6855.hdr_status; +} + +static bool ath11k_hw_wcn6855_rx_desc_encrypt_valid(struct hal_rx_desc *desc) +{ + return __le32_to_cpu(desc->u.wcn6855.mpdu_start.info1) & + RX_MPDU_START_INFO1_ENCRYPT_INFO_VALID; +} + +static u32 ath11k_hw_wcn6855_rx_desc_get_encrypt_type(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MPDU_START_INFO2_ENC_TYPE, + __le32_to_cpu(desc->u.wcn6855.mpdu_start.info2)); +} + +static u8 ath11k_hw_wcn6855_rx_desc_get_decap_type(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MSDU_START_INFO2_DECAP_FORMAT, + __le32_to_cpu(desc->u.wcn6855.msdu_start.info2)); +} + +static u8 ath11k_hw_wcn6855_rx_desc_get_mesh_ctl(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MSDU_START_INFO2_MESH_CTRL_PRESENT, + __le32_to_cpu(desc->u.wcn6855.msdu_start.info2)); +} + +static bool ath11k_hw_wcn6855_rx_desc_get_mpdu_seq_ctl_vld(struct hal_rx_desc *desc) +{ + return !!FIELD_GET(RX_MPDU_START_INFO1_MPDU_SEQ_CTRL_VALID, + __le32_to_cpu(desc->u.wcn6855.mpdu_start.info1)); +} + +static bool ath11k_hw_wcn6855_rx_desc_get_mpdu_fc_valid(struct hal_rx_desc *desc) +{ + return !!FIELD_GET(RX_MPDU_START_INFO1_MPDU_FCTRL_VALID, + __le32_to_cpu(desc->u.wcn6855.mpdu_start.info1)); +} + +static u16 ath11k_hw_wcn6855_rx_desc_get_mpdu_start_seq_no(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MPDU_START_INFO1_MPDU_SEQ_NUM, + __le32_to_cpu(desc->u.wcn6855.mpdu_start.info1)); +} + +static u16 ath11k_hw_wcn6855_rx_desc_get_msdu_len(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MSDU_START_INFO1_MSDU_LENGTH, + __le32_to_cpu(desc->u.wcn6855.msdu_start.info1)); +} + +static u8 ath11k_hw_wcn6855_rx_desc_get_msdu_sgi(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MSDU_START_INFO3_SGI, + __le32_to_cpu(desc->u.wcn6855.msdu_start.info3)); +} + +static u8 ath11k_hw_wcn6855_rx_desc_get_msdu_rate_mcs(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MSDU_START_INFO3_RATE_MCS, + __le32_to_cpu(desc->u.wcn6855.msdu_start.info3)); +} + +static u8 ath11k_hw_wcn6855_rx_desc_get_msdu_rx_bw(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MSDU_START_INFO3_RECV_BW, + __le32_to_cpu(desc->u.wcn6855.msdu_start.info3)); +} + +static u32 ath11k_hw_wcn6855_rx_desc_get_msdu_freq(struct hal_rx_desc *desc) +{ + return __le32_to_cpu(desc->u.wcn6855.msdu_start.phy_meta_data); +} + +static u8 ath11k_hw_wcn6855_rx_desc_get_msdu_pkt_type(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MSDU_START_INFO3_PKT_TYPE, + __le32_to_cpu(desc->u.wcn6855.msdu_start.info3)); +} + +static u8 ath11k_hw_wcn6855_rx_desc_get_msdu_nss(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MSDU_START_INFO3_MIMO_SS_BITMAP, + __le32_to_cpu(desc->u.wcn6855.msdu_start.info3)); +} + +static u8 ath11k_hw_wcn6855_rx_desc_get_mpdu_tid(struct hal_rx_desc *desc) +{ + return FIELD_GET(RX_MPDU_START_INFO2_TID_WCN6855, + __le32_to_cpu(desc->u.wcn6855.mpdu_start.info2)); +} + +static u16 ath11k_hw_wcn6855_rx_desc_get_mpdu_peer_id(struct hal_rx_desc *desc) +{ + return __le16_to_cpu(desc->u.wcn6855.mpdu_start.sw_peer_id); +} + +static void ath11k_hw_wcn6855_rx_desc_copy_attn_end(struct hal_rx_desc *fdesc, + struct hal_rx_desc *ldesc) +{ + memcpy((u8 *)&fdesc->u.wcn6855.msdu_end, (u8 *)&ldesc->u.wcn6855.msdu_end, + sizeof(struct rx_msdu_end_wcn6855)); + memcpy((u8 *)&fdesc->u.wcn6855.attention, (u8 *)&ldesc->u.wcn6855.attention, + sizeof(struct rx_attention)); + memcpy((u8 *)&fdesc->u.wcn6855.mpdu_end, (u8 *)&ldesc->u.wcn6855.mpdu_end, + sizeof(struct rx_mpdu_end)); +} + +static u32 ath11k_hw_wcn6855_rx_desc_get_mpdu_start_tag(struct hal_rx_desc *desc) +{ + return FIELD_GET(HAL_TLV_HDR_TAG, + __le32_to_cpu(desc->u.wcn6855.mpdu_start_tag)); +} + +static u32 ath11k_hw_wcn6855_rx_desc_get_mpdu_ppdu_id(struct hal_rx_desc *desc) +{ + return __le16_to_cpu(desc->u.wcn6855.mpdu_start.phy_ppdu_id); +} + +static void ath11k_hw_wcn6855_rx_desc_set_msdu_len(struct hal_rx_desc *desc, u16 len) +{ + u32 info = __le32_to_cpu(desc->u.wcn6855.msdu_start.info1); + + info &= ~RX_MSDU_START_INFO1_MSDU_LENGTH; + info |= FIELD_PREP(RX_MSDU_START_INFO1_MSDU_LENGTH, len); + + desc->u.wcn6855.msdu_start.info1 = __cpu_to_le32(info); +} + +static +struct rx_attention *ath11k_hw_wcn6855_rx_desc_get_attention(struct hal_rx_desc *desc) +{ + return &desc->u.wcn6855.attention; +} + +static u8 *ath11k_hw_wcn6855_rx_desc_get_msdu_payload(struct hal_rx_desc *desc) +{ + return &desc->u.wcn6855.msdu_payload[0]; +} + +static void ath11k_hw_wcn6855_reo_setup(struct ath11k_base *ab) +{ + u32 reo_base = HAL_SEQ_WCSS_UMAC_REO_REG; + u32 val; + /* Each hash entry uses four bits to map to a particular ring. */ + u32 ring_hash_map = HAL_HASH_ROUTING_RING_SW1 << 0 | + HAL_HASH_ROUTING_RING_SW2 << 4 | + HAL_HASH_ROUTING_RING_SW3 << 8 | + HAL_HASH_ROUTING_RING_SW4 << 12 | + HAL_HASH_ROUTING_RING_SW1 << 16 | + HAL_HASH_ROUTING_RING_SW2 << 20 | + HAL_HASH_ROUTING_RING_SW3 << 24 | + HAL_HASH_ROUTING_RING_SW4 << 28; + + val = ath11k_hif_read32(ab, reo_base + HAL_REO1_GEN_ENABLE); + val |= FIELD_PREP(HAL_REO1_GEN_ENABLE_AGING_LIST_ENABLE, 1) | + FIELD_PREP(HAL_REO1_GEN_ENABLE_AGING_FLUSH_ENABLE, 1); + ath11k_hif_write32(ab, reo_base + HAL_REO1_GEN_ENABLE, val); + + val = ath11k_hif_read32(ab, reo_base + HAL_REO1_MISC_CTL); + val &= ~HAL_REO1_MISC_CTL_FRAGMENT_DST_RING; + val |= FIELD_PREP(HAL_REO1_MISC_CTL_FRAGMENT_DST_RING, HAL_SRNG_RING_ID_REO2SW1); + ath11k_hif_write32(ab, reo_base + HAL_REO1_MISC_CTL, val); + + ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_0(ab), + HAL_DEFAULT_REO_TIMEOUT_USEC); + ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_1(ab), + HAL_DEFAULT_REO_TIMEOUT_USEC); + ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_2(ab), + HAL_DEFAULT_REO_TIMEOUT_USEC); + ath11k_hif_write32(ab, reo_base + HAL_REO1_AGING_THRESH_IX_3(ab), + HAL_DEFAULT_REO_TIMEOUT_USEC); + + ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_2, + ring_hash_map); + ath11k_hif_write32(ab, reo_base + HAL_REO1_DEST_RING_CTRL_IX_3, + ring_hash_map); +} + +static u16 ath11k_hw_ipq8074_mpdu_info_get_peerid(u8 *tlv_data) +{ + u16 peer_id = 0; + struct hal_rx_mpdu_info *mpdu_info = + (struct hal_rx_mpdu_info *)tlv_data; + + peer_id = FIELD_GET(HAL_RX_MPDU_INFO_INFO0_PEERID, + __le32_to_cpu(mpdu_info->info0)); + + return peer_id; +} + +static u16 ath11k_hw_wcn6855_mpdu_info_get_peerid(u8 *tlv_data) +{ + u16 peer_id = 0; + struct hal_rx_mpdu_info_wcn6855 *mpdu_info = + (struct hal_rx_mpdu_info_wcn6855 *)tlv_data; + + peer_id = FIELD_GET(HAL_RX_MPDU_INFO_INFO0_PEERID_WCN6855, + __le32_to_cpu(mpdu_info->info0)); + return peer_id; +} + const struct ath11k_hw_ops ipq8074_ops = { .get_hw_mac_from_pdev_id = ath11k_hw_ipq8074_mac_from_pdev_id, .wmi_init_config = ath11k_init_wmi_config_ipq8074, @@ -521,6 +797,8 @@ const struct ath11k_hw_ops ipq8074_ops = { .rx_desc_set_msdu_len = ath11k_hw_ipq8074_rx_desc_set_msdu_len, .rx_desc_get_attention = ath11k_hw_ipq8074_rx_desc_get_attention, .rx_desc_get_msdu_payload = ath11k_hw_ipq8074_rx_desc_get_msdu_payload, + .reo_setup = ath11k_hw_ipq8074_reo_setup, + .mpdu_info_get_peerid = ath11k_hw_ipq8074_mpdu_info_get_peerid, }; const struct ath11k_hw_ops ipq6018_ops = { @@ -555,6 +833,8 @@ const struct ath11k_hw_ops ipq6018_ops = { .rx_desc_set_msdu_len = ath11k_hw_ipq8074_rx_desc_set_msdu_len, .rx_desc_get_attention = ath11k_hw_ipq8074_rx_desc_get_attention, .rx_desc_get_msdu_payload = ath11k_hw_ipq8074_rx_desc_get_msdu_payload, + .reo_setup = ath11k_hw_ipq8074_reo_setup, + .mpdu_info_get_peerid = ath11k_hw_ipq8074_mpdu_info_get_peerid, }; const struct ath11k_hw_ops qca6390_ops = { @@ -589,6 +869,8 @@ const struct ath11k_hw_ops qca6390_ops = { .rx_desc_set_msdu_len = ath11k_hw_ipq8074_rx_desc_set_msdu_len, .rx_desc_get_attention = ath11k_hw_ipq8074_rx_desc_get_attention, .rx_desc_get_msdu_payload = ath11k_hw_ipq8074_rx_desc_get_msdu_payload, + .reo_setup = ath11k_hw_ipq8074_reo_setup, + .mpdu_info_get_peerid = ath11k_hw_ipq8074_mpdu_info_get_peerid, }; const struct ath11k_hw_ops qcn9074_ops = { @@ -623,6 +905,44 @@ const struct ath11k_hw_ops qcn9074_ops = { .rx_desc_set_msdu_len = ath11k_hw_qcn9074_rx_desc_set_msdu_len, .rx_desc_get_attention = ath11k_hw_qcn9074_rx_desc_get_attention, .rx_desc_get_msdu_payload = ath11k_hw_qcn9074_rx_desc_get_msdu_payload, + .reo_setup = ath11k_hw_ipq8074_reo_setup, + .mpdu_info_get_peerid = ath11k_hw_ipq8074_mpdu_info_get_peerid, +}; + +const struct ath11k_hw_ops wcn6855_ops = { + .get_hw_mac_from_pdev_id = ath11k_hw_ipq8074_mac_from_pdev_id, + .wmi_init_config = ath11k_init_wmi_config_qca6390, + .mac_id_to_pdev_id = ath11k_hw_mac_id_to_pdev_id_qca6390, + .mac_id_to_srng_id = ath11k_hw_mac_id_to_srng_id_qca6390, + .tx_mesh_enable = ath11k_hw_wcn6855_tx_mesh_enable, + .rx_desc_get_first_msdu = ath11k_hw_wcn6855_rx_desc_get_first_msdu, + .rx_desc_get_last_msdu = ath11k_hw_wcn6855_rx_desc_get_last_msdu, + .rx_desc_get_l3_pad_bytes = ath11k_hw_wcn6855_rx_desc_get_l3_pad_bytes, + .rx_desc_get_hdr_status = ath11k_hw_wcn6855_rx_desc_get_hdr_status, + .rx_desc_encrypt_valid = ath11k_hw_wcn6855_rx_desc_encrypt_valid, + .rx_desc_get_encrypt_type = ath11k_hw_wcn6855_rx_desc_get_encrypt_type, + .rx_desc_get_decap_type = ath11k_hw_wcn6855_rx_desc_get_decap_type, + .rx_desc_get_mesh_ctl = ath11k_hw_wcn6855_rx_desc_get_mesh_ctl, + .rx_desc_get_mpdu_seq_ctl_vld = ath11k_hw_wcn6855_rx_desc_get_mpdu_seq_ctl_vld, + .rx_desc_get_mpdu_fc_valid = ath11k_hw_wcn6855_rx_desc_get_mpdu_fc_valid, + .rx_desc_get_mpdu_start_seq_no = ath11k_hw_wcn6855_rx_desc_get_mpdu_start_seq_no, + .rx_desc_get_msdu_len = ath11k_hw_wcn6855_rx_desc_get_msdu_len, + .rx_desc_get_msdu_sgi = ath11k_hw_wcn6855_rx_desc_get_msdu_sgi, + .rx_desc_get_msdu_rate_mcs = ath11k_hw_wcn6855_rx_desc_get_msdu_rate_mcs, + .rx_desc_get_msdu_rx_bw = ath11k_hw_wcn6855_rx_desc_get_msdu_rx_bw, + .rx_desc_get_msdu_freq = ath11k_hw_wcn6855_rx_desc_get_msdu_freq, + .rx_desc_get_msdu_pkt_type = ath11k_hw_wcn6855_rx_desc_get_msdu_pkt_type, + .rx_desc_get_msdu_nss = ath11k_hw_wcn6855_rx_desc_get_msdu_nss, + .rx_desc_get_mpdu_tid = ath11k_hw_wcn6855_rx_desc_get_mpdu_tid, + .rx_desc_get_mpdu_peer_id = ath11k_hw_wcn6855_rx_desc_get_mpdu_peer_id, + .rx_desc_copy_attn_end_tlv = ath11k_hw_wcn6855_rx_desc_copy_attn_end, + .rx_desc_get_mpdu_start_tag = ath11k_hw_wcn6855_rx_desc_get_mpdu_start_tag, + .rx_desc_get_mpdu_ppdu_id = ath11k_hw_wcn6855_rx_desc_get_mpdu_ppdu_id, + .rx_desc_set_msdu_len = ath11k_hw_wcn6855_rx_desc_set_msdu_len, + .rx_desc_get_attention = ath11k_hw_wcn6855_rx_desc_get_attention, + .rx_desc_get_msdu_payload = ath11k_hw_wcn6855_rx_desc_get_msdu_payload, + .reo_setup = ath11k_hw_wcn6855_reo_setup, + .mpdu_info_get_peerid = ath11k_hw_wcn6855_mpdu_info_get_peerid, }; #define ATH11K_TX_RING_MASK_0 0x1 @@ -1688,3 +2008,74 @@ const struct ath11k_hw_regs qcn9074_regs = { .pcie_qserdes_sysclk_en_sel = 0x01e0e0a8, .pcie_pcs_osc_dtct_config_base = 0x01e0f45c, }; + +const struct ath11k_hw_regs wcn6855_regs = { + /* SW2TCL(x) R0 ring configuration address */ + .hal_tcl1_ring_base_lsb = 0x00000690, + .hal_tcl1_ring_base_msb = 0x00000694, + .hal_tcl1_ring_id = 0x00000698, + .hal_tcl1_ring_misc = 0x000006a0, + .hal_tcl1_ring_tp_addr_lsb = 0x000006ac, + .hal_tcl1_ring_tp_addr_msb = 0x000006b0, + .hal_tcl1_ring_consumer_int_setup_ix0 = 0x000006c0, + .hal_tcl1_ring_consumer_int_setup_ix1 = 0x000006c4, + .hal_tcl1_ring_msi1_base_lsb = 0x000006d8, + .hal_tcl1_ring_msi1_base_msb = 0x000006dc, + .hal_tcl1_ring_msi1_data = 0x000006e0, + .hal_tcl2_ring_base_lsb = 0x000006e8, + .hal_tcl_ring_base_lsb = 0x00000798, + + /* TCL STATUS ring address */ + .hal_tcl_status_ring_base_lsb = 0x000008a0, + + /* REO2SW(x) R0 ring configuration address */ + .hal_reo1_ring_base_lsb = 0x00000244, + .hal_reo1_ring_base_msb = 0x00000248, + .hal_reo1_ring_id = 0x0000024c, + .hal_reo1_ring_misc = 0x00000254, + .hal_reo1_ring_hp_addr_lsb = 0x00000258, + .hal_reo1_ring_hp_addr_msb = 0x0000025c, + .hal_reo1_ring_producer_int_setup = 0x00000268, + .hal_reo1_ring_msi1_base_lsb = 0x0000028c, + .hal_reo1_ring_msi1_base_msb = 0x00000290, + .hal_reo1_ring_msi1_data = 0x00000294, + .hal_reo2_ring_base_lsb = 0x0000029c, + .hal_reo1_aging_thresh_ix_0 = 0x000005bc, + .hal_reo1_aging_thresh_ix_1 = 0x000005c0, + .hal_reo1_aging_thresh_ix_2 = 0x000005c4, + .hal_reo1_aging_thresh_ix_3 = 0x000005c8, + + /* REO2SW(x) R2 ring pointers (head/tail) address */ + .hal_reo1_ring_hp = 0x00003030, + .hal_reo1_ring_tp = 0x00003034, + .hal_reo2_ring_hp = 0x00003038, + + /* REO2TCL R0 ring configuration address */ + .hal_reo_tcl_ring_base_lsb = 0x00000454, + .hal_reo_tcl_ring_hp = 0x00003060, + + /* REO status address */ + .hal_reo_status_ring_base_lsb = 0x0000055c, + .hal_reo_status_hp = 0x00003078, + + /* WCSS relative address */ + .hal_seq_wcss_umac_ce0_src_reg = 0x1b80000, + .hal_seq_wcss_umac_ce0_dst_reg = 0x1b81000, + .hal_seq_wcss_umac_ce1_src_reg = 0x1b82000, + .hal_seq_wcss_umac_ce1_dst_reg = 0x1b83000, + + /* WBM Idle address */ + .hal_wbm_idle_link_ring_base_lsb = 0x00000870, + .hal_wbm_idle_link_ring_misc = 0x00000880, + + /* SW2WBM release address */ + .hal_wbm_release_ring_base_lsb = 0x000001e8, + + /* WBM2SW release address */ + .hal_wbm0_release_ring_base_lsb = 0x00000920, + .hal_wbm1_release_ring_base_lsb = 0x00000978, + + /* PCIe base address */ + .pcie_qserdes_sysclk_en_sel = 0x01e0c0ac, + .pcie_pcs_osc_dtct_config_base = 0x01e0c628, +}; diff --git a/drivers/net/wireless/ath/ath11k/hw.h b/drivers/net/wireless/ath/ath11k/hw.h index c81a6328361d..62f5978b3005 100644 --- a/drivers/net/wireless/ath/ath11k/hw.h +++ b/drivers/net/wireless/ath/ath11k/hw.h @@ -162,6 +162,7 @@ struct ath11k_hw_params { bool cold_boot_calib; bool supports_suspend; u32 hal_desc_sz; + bool fix_l1ss; }; struct ath11k_hw_ops { @@ -199,12 +200,15 @@ struct ath11k_hw_ops { void (*rx_desc_set_msdu_len)(struct hal_rx_desc *desc, u16 len); struct rx_attention *(*rx_desc_get_attention)(struct hal_rx_desc *desc); u8 *(*rx_desc_get_msdu_payload)(struct hal_rx_desc *desc); + void (*reo_setup)(struct ath11k_base *ab); + u16 (*mpdu_info_get_peerid)(u8 *tlv_data); }; extern const struct ath11k_hw_ops ipq8074_ops; extern const struct ath11k_hw_ops ipq6018_ops; extern const struct ath11k_hw_ops qca6390_ops; extern const struct ath11k_hw_ops qcn9074_ops; +extern const struct ath11k_hw_ops wcn6855_ops; extern const struct ath11k_hw_ring_mask ath11k_hw_ring_mask_ipq8074; extern const struct ath11k_hw_ring_mask ath11k_hw_ring_mask_qca6390; @@ -318,5 +322,6 @@ struct ath11k_hw_regs { extern const struct ath11k_hw_regs ipq8074_regs; extern const struct ath11k_hw_regs qca6390_regs; extern const struct ath11k_hw_regs qcn9074_regs; +extern const struct ath11k_hw_regs wcn6855_regs; #endif diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 9d0ff150ec30..e9b3689331ec 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -1314,10 +1314,16 @@ static void ath11k_peer_assoc_h_he(struct ath11k *ar, arg->he_flag = true; - memcpy(&arg->peer_he_cap_macinfo, he_cap->he_cap_elem.mac_cap_info, - sizeof(arg->peer_he_cap_macinfo)); - memcpy(&arg->peer_he_cap_phyinfo, he_cap->he_cap_elem.phy_cap_info, - sizeof(arg->peer_he_cap_phyinfo)); + memcpy_and_pad(&arg->peer_he_cap_macinfo, + sizeof(arg->peer_he_cap_macinfo), + he_cap->he_cap_elem.mac_cap_info, + sizeof(he_cap->he_cap_elem.mac_cap_info), + 0); + memcpy_and_pad(&arg->peer_he_cap_phyinfo, + sizeof(arg->peer_he_cap_phyinfo), + he_cap->he_cap_elem.phy_cap_info, + sizeof(he_cap->he_cap_elem.phy_cap_info), + 0); arg->peer_he_ops = vif->bss_conf.he_oper.params; /* the top most byte is used to indicate BSS color info */ @@ -5379,11 +5385,6 @@ ath11k_mac_update_vif_chan(struct ath11k *ar, if (WARN_ON(!arvif->is_up)) continue; - ret = ath11k_mac_setup_bcn_tmpl(arvif); - if (ret) - ath11k_warn(ab, "failed to update bcn tmpl during csa: %d\n", - ret); - ret = ath11k_mac_vdev_restart(arvif, &vifs[i].new_ctx->def); if (ret) { ath11k_warn(ab, "failed to restart vdev %d: %d\n", @@ -5391,6 +5392,11 @@ ath11k_mac_update_vif_chan(struct ath11k *ar, continue; } + ret = ath11k_mac_setup_bcn_tmpl(arvif); + if (ret) + ath11k_warn(ab, "failed to update bcn tmpl during csa: %d\n", + ret); + ret = ath11k_wmi_vdev_up(arvif->ar, arvif->vdev_id, arvif->aid, arvif->bssid); if (ret) { diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c index 27b394d115e2..75cc2d80fde8 100644 --- a/drivers/net/wireless/ath/ath11k/mhi.c +++ b/drivers/net/wireless/ath/ath11k/mhi.c @@ -354,6 +354,7 @@ int ath11k_mhi_register(struct ath11k_pci *ab_pci) ath11k_mhi_config = &ath11k_mhi_config_qcn9074; break; case ATH11K_HW_QCA6390_HW20: + case ATH11K_HW_WCN6855_HW20: ath11k_mhi_config = &ath11k_mhi_config_qca6390; break; default: diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c index 0f31eb566fb6..646ad79f309c 100644 --- a/drivers/net/wireless/ath/ath11k/pci.c +++ b/drivers/net/wireless/ath/ath11k/pci.c @@ -36,10 +36,12 @@ #define QCA6390_DEVICE_ID 0x1101 #define QCN9074_DEVICE_ID 0x1104 +#define WCN6855_DEVICE_ID 0x1103 static const struct pci_device_id ath11k_pci_id_table[] = { { PCI_VDEVICE(QCOM, QCA6390_DEVICE_ID) }, - /* TODO: add QCN9074_DEVICE_ID) once firmware issues are resolved */ + { PCI_VDEVICE(QCOM, WCN6855_DEVICE_ID) }, + { PCI_VDEVICE(QCOM, QCN9074_DEVICE_ID) }, {0} }; @@ -432,7 +434,8 @@ static void ath11k_pci_sw_reset(struct ath11k_base *ab, bool power_on) ath11k_pci_enable_ltssm(ab); ath11k_pci_clear_all_intrs(ab); ath11k_pci_set_wlaon_pwr_ctrl(ab); - ath11k_pci_fix_l1ss(ab); + if (ab->hw_params.fix_l1ss) + ath11k_pci_fix_l1ss(ab); } ath11k_mhi_clear_vector(ab); @@ -1176,12 +1179,26 @@ static const struct ath11k_hif_ops ath11k_pci_hif_ops = { .get_ce_msi_idx = ath11k_pci_get_ce_msi_idx, }; +static void ath11k_pci_read_hw_version(struct ath11k_base *ab, u32 *major, u32 *minor) +{ + u32 soc_hw_version; + + soc_hw_version = ath11k_pci_read32(ab, TCSR_SOC_HW_VERSION); + *major = FIELD_GET(TCSR_SOC_HW_VERSION_MAJOR_MASK, + soc_hw_version); + *minor = FIELD_GET(TCSR_SOC_HW_VERSION_MINOR_MASK, + soc_hw_version); + + ath11k_dbg(ab, ATH11K_DBG_PCI, "pci tcsr_soc_hw_version major %d minor %d\n", + *major, *minor); +} + static int ath11k_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pci_dev) { struct ath11k_base *ab; struct ath11k_pci *ab_pci; - u32 soc_hw_version, soc_hw_version_major, soc_hw_version_minor; + u32 soc_hw_version_major, soc_hw_version_minor; int ret; ab = ath11k_core_alloc(&pdev->dev, sizeof(*ab_pci), ATH11K_BUS_PCI, @@ -1209,15 +1226,8 @@ static int ath11k_pci_probe(struct pci_dev *pdev, switch (pci_dev->device) { case QCA6390_DEVICE_ID: - soc_hw_version = ath11k_pci_read32(ab, TCSR_SOC_HW_VERSION); - soc_hw_version_major = FIELD_GET(TCSR_SOC_HW_VERSION_MAJOR_MASK, - soc_hw_version); - soc_hw_version_minor = FIELD_GET(TCSR_SOC_HW_VERSION_MINOR_MASK, - soc_hw_version); - - ath11k_dbg(ab, ATH11K_DBG_PCI, "pci tcsr_soc_hw_version major %d minor %d\n", - soc_hw_version_major, soc_hw_version_minor); - + ath11k_pci_read_hw_version(ab, &soc_hw_version_major, + &soc_hw_version_minor); switch (soc_hw_version_major) { case 2: ab->hw_rev = ATH11K_HW_QCA6390_HW20; @@ -1235,6 +1245,21 @@ static int ath11k_pci_probe(struct pci_dev *pdev, ab->bus_params.static_window_map = true; ab->hw_rev = ATH11K_HW_QCN9074_HW10; break; + case WCN6855_DEVICE_ID: + ath11k_pci_read_hw_version(ab, &soc_hw_version_major, + &soc_hw_version_minor); + switch (soc_hw_version_major) { + case 2: + ab->hw_rev = ATH11K_HW_WCN6855_HW20; + break; + default: + dev_err(&pdev->dev, "Unsupported WCN6855 SOC hardware version: %d %d\n", + soc_hw_version_major, soc_hw_version_minor); + ret = -EOPNOTSUPP; + goto err_pci_free_region; + } + ab_pci->msi_config = &ath11k_msi_config[0]; + break; default: dev_err(&pdev->dev, "Unknown PCI device found: 0x%x\n", pci_dev->device); diff --git a/drivers/net/wireless/ath/ath11k/rx_desc.h b/drivers/net/wireless/ath/ath11k/rx_desc.h index 0cdb4a1f816e..79c50804d7dc 100644 --- a/drivers/net/wireless/ath/ath11k/rx_desc.h +++ b/drivers/net/wireless/ath/ath11k/rx_desc.h @@ -368,6 +368,7 @@ struct rx_attention { #define RX_MPDU_START_INFO2_BSSID_HIT BIT(9) #define RX_MPDU_START_INFO2_BSSID_NUM GENMASK(13, 10) #define RX_MPDU_START_INFO2_TID GENMASK(17, 14) +#define RX_MPDU_START_INFO2_TID_WCN6855 GENMASK(18, 15) #define RX_MPDU_START_INFO3_REO_DEST_IND GENMASK(4, 0) #define RX_MPDU_START_INFO3_FLOW_ID_TOEPLITZ BIT(7) @@ -546,6 +547,31 @@ struct rx_mpdu_start_qcn9074 { __le32 ht_ctrl; } __packed; +struct rx_mpdu_start_wcn6855 { + __le32 info3; + __le32 reo_queue_desc_lo; + __le32 info4; + __le32 pn[4]; + __le32 info2; + __le32 peer_meta_data; + __le16 info0; + __le16 phy_ppdu_id; + __le16 ast_index; + __le16 sw_peer_id; + __le32 info1; + __le32 info5; + __le32 info6; + __le16 frame_ctrl; + __le16 duration; + u8 addr1[ETH_ALEN]; + u8 addr2[ETH_ALEN]; + u8 addr3[ETH_ALEN]; + __le16 seq_ctrl; + u8 addr4[ETH_ALEN]; + __le16 qos_ctrl; + __le32 ht_ctrl; +} __packed; + /* rx_mpdu_start * * rxpcu_mpdu_filter_in_category @@ -804,6 +830,20 @@ struct rx_msdu_start_qcn9074 { __le16 vlan_stag_c1; } __packed; +struct rx_msdu_start_wcn6855 { + __le16 info0; + __le16 phy_ppdu_id; + __le32 info1; + __le32 info2; + __le32 toeplitz_hash; + __le32 flow_id_toeplitz; + __le32 info3; + __le32 ppdu_start_timestamp; + __le32 phy_meta_data; + __le16 vlan_ctag_ci; + __le16 vlan_stag_ci; +} __packed; + /* rx_msdu_start * * rxpcu_mpdu_filter_in_category @@ -988,7 +1028,9 @@ struct rx_msdu_start_qcn9074 { #define RX_MSDU_END_INFO2_REPORTED_MPDU_LEN GENMASK(13, 0) #define RX_MSDU_END_INFO2_FIRST_MSDU BIT(14) +#define RX_MSDU_END_INFO2_FIRST_MSDU_WCN6855 BIT(28) #define RX_MSDU_END_INFO2_LAST_MSDU BIT(15) +#define RX_MSDU_END_INFO2_LAST_MSDU_WCN6855 BIT(29) #define RX_MSDU_END_INFO2_SA_IDX_TIMEOUT BIT(16) #define RX_MSDU_END_INFO2_DA_IDX_TIMEOUT BIT(17) #define RX_MSDU_END_INFO2_MSDU_LIMIT_ERR BIT(18) @@ -1037,6 +1079,31 @@ struct rx_msdu_end_ipq8074 { __le16 sa_sw_peer_id; } __packed; +struct rx_msdu_end_wcn6855 { + __le16 info0; + __le16 phy_ppdu_id; + __le16 ip_hdr_cksum; + __le16 reported_mpdu_len; + __le32 info1; + __le32 ext_wapi_pn[2]; + __le32 info4; + __le32 ipv6_options_crc; + __le32 tcp_seq_num; + __le32 tcp_ack_num; + __le16 info3; + __le16 window_size; + __le32 info2; + __le16 sa_idx; + __le16 da_idx; + __le32 info5; + __le32 fse_metadata; + __le16 cce_metadata; + __le16 sa_sw_peer_id; + __le32 rule_indication[2]; + __le32 info6; + __le32 info7; +} __packed; + #define RX_MSDU_END_MPDU_LENGTH_INFO GENMASK(13, 0) #define RX_MSDU_END_INFO2_DA_OFFSET GENMASK(5, 0) @@ -1400,10 +1467,30 @@ struct hal_rx_desc_qcn9074 { u8 msdu_payload[0]; } __packed; +struct hal_rx_desc_wcn6855 { + __le32 msdu_end_tag; + struct rx_msdu_end_wcn6855 msdu_end; + __le32 rx_attn_tag; + struct rx_attention attention; + __le32 msdu_start_tag; + struct rx_msdu_start_wcn6855 msdu_start; + u8 rx_padding0[HAL_RX_DESC_PADDING0_BYTES]; + __le32 mpdu_start_tag; + struct rx_mpdu_start_wcn6855 mpdu_start; + __le32 mpdu_end_tag; + struct rx_mpdu_end mpdu_end; + u8 rx_padding1[HAL_RX_DESC_PADDING1_BYTES]; + __le32 hdr_status_tag; + __le32 phy_ppdu_id; + u8 hdr_status[HAL_RX_DESC_HDR_STATUS_LEN]; + u8 msdu_payload[0]; +} __packed; + struct hal_rx_desc { union { struct hal_rx_desc_ipq8074 ipq8074; struct hal_rx_desc_qcn9074 qcn9074; + struct hal_rx_desc_wcn6855 wcn6855; } u; } __packed; diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index 5ca2d80679b6..6c253eae9d06 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -5235,7 +5235,7 @@ ath11k_wmi_pull_pdev_stats_tx(const struct wmi_pdev_stats_tx *src, dst->hw_reaped = src->hw_reaped; dst->underrun = src->underrun; dst->tx_abort = src->tx_abort; - dst->mpdus_requed = src->mpdus_requed; + dst->mpdus_requeued = src->mpdus_requeued; dst->tx_ko = src->tx_ko; dst->data_rc = src->data_rc; dst->self_triggers = src->self_triggers; @@ -5505,7 +5505,7 @@ ath11k_wmi_fw_pdev_tx_stats_fill(const struct ath11k_fw_stats_pdev *pdev, len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", "PPDUs cleaned", pdev->tx_abort); len += scnprintf(buf + len, buf_len - len, "%30s %10d\n", - "MPDUs requed", pdev->mpdus_requed); + "MPDUs requeued", pdev->mpdus_requeued); len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", "Excessive retries", pdev->tx_ko); len += scnprintf(buf + len, buf_len - len, "%30s %10u\n", diff --git a/drivers/net/wireless/ath/ath11k/wmi.h b/drivers/net/wireless/ath/ath11k/wmi.h index 3ade1ddd35c9..d35c47e0b19d 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.h +++ b/drivers/net/wireless/ath/ath11k/wmi.h @@ -4171,8 +4171,8 @@ struct wmi_pdev_stats_tx { /* Num PPDUs cleaned up in TX abort */ s32 tx_abort; - /* Num MPDUs requed by SW */ - s32 mpdus_requed; + /* Num MPDUs requeued by SW */ + s32 mpdus_requeued; /* excessive retries */ u32 tx_ko; diff --git a/drivers/net/wireless/ath/ath5k/pcu.c b/drivers/net/wireless/ath/ath5k/pcu.c index f2db7cf16566..3f4ce4e9c532 100644 --- a/drivers/net/wireless/ath/ath5k/pcu.c +++ b/drivers/net/wireless/ath/ath5k/pcu.c @@ -855,7 +855,7 @@ ath5k_hw_start_rx_pcu(struct ath5k_hw *ah) } /** - * at5k_hw_stop_rx_pcu() - Stop RX engine + * ath5k_hw_stop_rx_pcu() - Stop RX engine * @ah: The &struct ath5k_hw * * Stops RX engine on PCU diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c index 29527e8dcced..fefdc6753acd 100644 --- a/drivers/net/wireless/ath/ath6kl/cfg80211.c +++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c @@ -3303,8 +3303,8 @@ static int ath6kl_cfg80211_sscan_start(struct wiphy *wiphy, if (ret < 0) return ret; } else { - ret = ath6kl_wmi_bssfilter_cmd(ar->wmi, vif->fw_vif_idx, - MATCHED_SSID_FILTER, 0); + ret = ath6kl_wmi_bssfilter_cmd(ar->wmi, vif->fw_vif_idx, + MATCHED_SSID_FILTER, 0); if (ret < 0) return ret; } diff --git a/drivers/net/wireless/ath/ath9k/ar9003_mac.c b/drivers/net/wireless/ath/ath9k/ar9003_mac.c index 76b538942a79..5184a0aacfe2 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_mac.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_mac.c @@ -522,6 +522,8 @@ int ath9k_hw_process_rxdesc_edma(struct ath_hw *ah, struct ath_rx_status *rxs, rxs->rs_moreaggr = (rxsp->status11 & AR_RxMoreAggr) ? 1 : 0; rxs->rs_antenna = (MS(rxsp->status4, AR_RxAntenna) & 0x7); rxs->enc_flags |= (rxsp->status4 & AR_GI) ? RX_ENC_FLAG_SHORT_GI : 0; + rxs->enc_flags |= + (rxsp->status4 & AR_STBC) ? (1 << RX_ENC_FLAG_STBC_SHIFT) : 0; rxs->bw = (rxsp->status4 & AR_2040) ? RATE_INFO_BW_40 : RATE_INFO_BW_20; rxs->evm0 = rxsp->status6; diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index 45f6402478b5..139831539da3 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -307,6 +307,11 @@ static int ath_reset_internal(struct ath_softc *sc, struct ath9k_channel *hchan) hchan = ah->curchan; } + if (!hchan) { + fastcc = false; + hchan = ath9k_cmn_get_channel(sc->hw, ah, &sc->cur_chan->chandef); + } + if (!ath_prepare_reset(sc)) fastcc = false; @@ -2649,7 +2654,7 @@ static void ath9k_unassign_vif_chanctx(struct ieee80211_hw *hw, static void ath9k_mgd_prepare_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - u16 duration) + struct ieee80211_prep_tx_info *info) { struct ath_softc *sc = hw->priv; struct ath_common *common = ath9k_hw_common(sc->sc_ah); diff --git a/drivers/net/wireless/ath/carl9170/Kconfig b/drivers/net/wireless/ath/carl9170/Kconfig index b2d760873992..ba9bea79381c 100644 --- a/drivers/net/wireless/ath/carl9170/Kconfig +++ b/drivers/net/wireless/ath/carl9170/Kconfig @@ -16,13 +16,11 @@ config CARL9170 config CARL9170_LEDS bool "SoftLED Support" - depends on CARL9170 - select MAC80211_LEDS - select LEDS_CLASS - select NEW_LEDS default y + depends on CARL9170 + depends on MAC80211_LEDS help - This option is necessary, if you want your device' LEDs to blink + This option is necessary, if you want your device's LEDs to blink. Say Y, unless you need the LEDs for firmware debugging. diff --git a/drivers/net/wireless/ath/hw.c b/drivers/net/wireless/ath/hw.c index eae9abf540a7..b53ebb3ac9a2 100644 --- a/drivers/net/wireless/ath/hw.c +++ b/drivers/net/wireless/ath/hw.c @@ -24,7 +24,7 @@ #define REG_WRITE(_ah, _reg, _val) (common->ops->write)(_ah, _val, _reg) /** - * ath_hw_set_bssid_mask - filter out bssids we listen + * ath_hw_setbssidmask - filter out bssids we listen * * @common: the ath_common struct for the device. * diff --git a/drivers/net/wireless/ath/wcn36xx/dxe.c b/drivers/net/wireless/ath/wcn36xx/dxe.c index 63079231e48e..8e1dbfda6538 100644 --- a/drivers/net/wireless/ath/wcn36xx/dxe.c +++ b/drivers/net/wireless/ath/wcn36xx/dxe.c @@ -800,7 +800,7 @@ int wcn36xx_dxe_tx_frame(struct wcn36xx *wcn, (char *)ctl_skb->skb->data, ctl_skb->skb->len); /* Move the head of the ring to the next empty descriptor */ - ch->head_blk_ctl = ctl_skb->next; + ch->head_blk_ctl = ctl_skb->next; /* Commit all previous writes and set descriptors to VALID */ wmb(); diff --git a/drivers/net/wireless/ath/wcn36xx/hal.h b/drivers/net/wireless/ath/wcn36xx/hal.h index 65ef893f2736..455143c4164e 100644 --- a/drivers/net/wireless/ath/wcn36xx/hal.h +++ b/drivers/net/wireless/ath/wcn36xx/hal.h @@ -3464,8 +3464,12 @@ struct wcn36xx_hal_rem_bcn_filter_req { #define WCN36XX_HAL_OFFLOAD_DISABLE 0 #define WCN36XX_HAL_OFFLOAD_ENABLE 1 #define WCN36XX_HAL_OFFLOAD_BCAST_FILTER_ENABLE 0x2 +#define WCN36XX_HAL_OFFLOAD_MCAST_FILTER_ENABLE 0x4 +#define WCN36XX_HAL_OFFLOAD_NS_AND_MCAST_FILTER_ENABLE \ + (WCN36XX_HAL_OFFLOAD_ENABLE | WCN36XX_HAL_OFFLOAD_MCAST_FILTER_ENABLE) #define WCN36XX_HAL_OFFLOAD_ARP_AND_BCAST_FILTER_ENABLE \ - (HAL_OFFLOAD_ENABLE|HAL_OFFLOAD_BCAST_FILTER_ENABLE) + (WCN36XX_HAL_OFFLOAD_ENABLE | WCN36XX_HAL_OFFLOAD_BCAST_FILTER_ENABLE) +#define WCN36XX_HAL_IPV6_OFFLOAD_ADDR_MAX 0x02 struct wcn36xx_hal_ns_offload_params { u8 src_ipv6_addr[WCN36XX_HAL_IPV6_ADDR_LEN]; @@ -3487,10 +3491,10 @@ struct wcn36xx_hal_ns_offload_params { /* slot index for this offload */ u32 slot_index; u8 bss_index; -}; +} __packed; struct wcn36xx_hal_host_offload_req { - u8 offload_Type; + u8 offload_type; /* enable or disable */ u8 enable; @@ -3499,13 +3503,13 @@ struct wcn36xx_hal_host_offload_req { u8 host_ipv4_addr[4]; u8 host_ipv6_addr[WCN36XX_HAL_IPV6_ADDR_LEN]; } u; -}; +} __packed; struct wcn36xx_hal_host_offload_req_msg { struct wcn36xx_hal_msg_header header; struct wcn36xx_hal_host_offload_req host_offload_params; struct wcn36xx_hal_ns_offload_params ns_offload_params; -}; +} __packed; /* Packet Types. */ #define WCN36XX_HAL_KEEP_ALIVE_NULL_PKT 1 @@ -4901,7 +4905,7 @@ struct wcn36xx_hal_gtk_offload_req_msg { u64 key_replay_counter; u8 bss_index; -}; +} __packed; struct wcn36xx_hal_gtk_offload_rsp_msg { struct wcn36xx_hal_msg_header header; @@ -4915,7 +4919,7 @@ struct wcn36xx_hal_gtk_offload_rsp_msg { struct wcn36xx_hal_gtk_offload_get_info_req_msg { struct wcn36xx_hal_msg_header header; u8 bss_index; -}; +} __packed; struct wcn36xx_hal_gtk_offload_get_info_rsp_msg { struct wcn36xx_hal_msg_header header; @@ -4939,7 +4943,7 @@ struct wcn36xx_hal_gtk_offload_get_info_rsp_msg { u32 igtk_rekey_count; u8 bss_index; -}; +} __packed; struct dhcp_info { /* Indicates the device mode which indicates about the DHCP activity */ diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c index afb4877eaad8..d202f2128df2 100644 --- a/drivers/net/wireless/ath/wcn36xx/main.c +++ b/drivers/net/wireless/ath/wcn36xx/main.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "wcn36xx.h" #include "testmode.h" @@ -172,7 +173,9 @@ static struct ieee80211_supported_band wcn_band_5ghz = { #ifdef CONFIG_PM static const struct wiphy_wowlan_support wowlan_support = { - .flags = WIPHY_WOWLAN_ANY + .flags = WIPHY_WOWLAN_ANY | + WIPHY_WOWLAN_MAGIC_PKT | + WIPHY_WOWLAN_SUPPORTS_GTK_REKEY }; #endif @@ -293,23 +296,16 @@ static int wcn36xx_start(struct ieee80211_hw *hw) goto out_free_dxe_pool; } - wcn->hal_buf = kmalloc(WCN36XX_HAL_BUF_SIZE, GFP_KERNEL); - if (!wcn->hal_buf) { - wcn36xx_err("Failed to allocate smd buf\n"); - ret = -ENOMEM; - goto out_free_dxe_ctl; - } - ret = wcn36xx_smd_load_nv(wcn); if (ret) { wcn36xx_err("Failed to push NV to chip\n"); - goto out_free_smd_buf; + goto out_free_dxe_ctl; } ret = wcn36xx_smd_start(wcn); if (ret) { wcn36xx_err("Failed to start chip\n"); - goto out_free_smd_buf; + goto out_free_dxe_ctl; } if (!wcn36xx_is_fw_version(wcn, 1, 2, 2, 24)) { @@ -336,8 +332,6 @@ static int wcn36xx_start(struct ieee80211_hw *hw) out_smd_stop: wcn36xx_smd_stop(wcn); -out_free_smd_buf: - kfree(wcn->hal_buf); out_free_dxe_ctl: wcn36xx_dxe_free_ctl_blks(wcn); out_free_dxe_pool: @@ -372,8 +366,6 @@ static void wcn36xx_stop(struct ieee80211_hw *hw) wcn36xx_dxe_free_mem_pools(wcn); wcn36xx_dxe_free_ctl_blks(wcn); - - kfree(wcn->hal_buf); } static void wcn36xx_change_ps(struct wcn36xx *wcn, bool enable) @@ -1088,28 +1080,91 @@ static int wcn36xx_sta_remove(struct ieee80211_hw *hw, #ifdef CONFIG_PM +static struct ieee80211_vif *wcn36xx_get_first_assoc_vif(struct wcn36xx *wcn) +{ + struct wcn36xx_vif *vif_priv = NULL; + struct ieee80211_vif *vif = NULL; + + list_for_each_entry(vif_priv, &wcn->vif_list, list) { + if (vif_priv->sta_assoc) { + vif = wcn36xx_priv_to_vif(vif_priv); + break; + } + } + return vif; +} + static int wcn36xx_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wow) { struct wcn36xx *wcn = hw->priv; + struct ieee80211_vif *vif = NULL; + int ret = 0; wcn36xx_dbg(WCN36XX_DBG_MAC, "mac suspend\n"); - flush_workqueue(wcn->hal_ind_wq); - wcn36xx_smd_set_power_params(wcn, true); - return 0; + mutex_lock(&wcn->conf_mutex); + + vif = wcn36xx_get_first_assoc_vif(wcn); + if (vif) { + ret = wcn36xx_smd_arp_offload(wcn, vif, true); + if (ret) + goto out; + ret = wcn36xx_smd_ipv6_ns_offload(wcn, vif, true); + if (ret) + goto out; + ret = wcn36xx_smd_gtk_offload(wcn, vif, true); + if (ret) + goto out; + ret = wcn36xx_smd_set_power_params(wcn, true); + if (ret) + goto out; + ret = wcn36xx_smd_wlan_host_suspend_ind(wcn); + } +out: + mutex_unlock(&wcn->conf_mutex); + return ret; } static int wcn36xx_resume(struct ieee80211_hw *hw) { struct wcn36xx *wcn = hw->priv; + struct ieee80211_vif *vif = NULL; wcn36xx_dbg(WCN36XX_DBG_MAC, "mac resume\n"); - flush_workqueue(wcn->hal_ind_wq); - wcn36xx_smd_set_power_params(wcn, false); + mutex_lock(&wcn->conf_mutex); + vif = wcn36xx_get_first_assoc_vif(wcn); + if (vif) { + wcn36xx_smd_host_resume(wcn); + wcn36xx_smd_set_power_params(wcn, false); + wcn36xx_smd_gtk_offload_get_info(wcn, vif); + wcn36xx_smd_gtk_offload(wcn, vif, false); + wcn36xx_smd_ipv6_ns_offload(wcn, vif, false); + wcn36xx_smd_arp_offload(wcn, vif, false); + } + mutex_unlock(&wcn->conf_mutex); + return 0; } +static void wcn36xx_set_rekey_data(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct cfg80211_gtk_rekey_data *data) +{ + struct wcn36xx *wcn = hw->priv; + struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif); + + mutex_lock(&wcn->conf_mutex); + + memcpy(vif_priv->rekey_data.kek, data->kek, NL80211_KEK_LEN); + memcpy(vif_priv->rekey_data.kck, data->kck, NL80211_KCK_LEN); + vif_priv->rekey_data.replay_ctr = + cpu_to_le64(be64_to_cpup((__be64 *)data->replay_ctr)); + vif_priv->rekey_data.valid = true; + + mutex_unlock(&wcn->conf_mutex); +} + #endif static int wcn36xx_ampdu_action(struct ieee80211_hw *hw, @@ -1176,6 +1231,34 @@ static int wcn36xx_ampdu_action(struct ieee80211_hw *hw, return ret; } +#if IS_ENABLED(CONFIG_IPV6) +static void wcn36xx_ipv6_addr_change(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct inet6_dev *idev) +{ + struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif); + struct inet6_ifaddr *ifa; + int idx = 0; + + memset(vif_priv->tentative_addrs, 0, sizeof(vif_priv->tentative_addrs)); + + read_lock_bh(&idev->lock); + list_for_each_entry(ifa, &idev->addr_list, if_list) { + vif_priv->target_ipv6_addrs[idx] = ifa->addr; + if (ifa->flags & IFA_F_TENTATIVE) + __set_bit(idx, vif_priv->tentative_addrs); + idx++; + if (idx >= WCN36XX_HAL_IPV6_OFFLOAD_ADDR_MAX) + break; + wcn36xx_dbg(WCN36XX_DBG_MAC, "%pI6 %s\n", &ifa->addr, + (ifa->flags & IFA_F_TENTATIVE) ? "tentative" : NULL); + } + read_unlock_bh(&idev->lock); + + vif_priv->num_target_ipv6_addrs = idx; +} +#endif + static const struct ieee80211_ops wcn36xx_ops = { .start = wcn36xx_start, .stop = wcn36xx_stop, @@ -1184,6 +1267,7 @@ static const struct ieee80211_ops wcn36xx_ops = { #ifdef CONFIG_PM .suspend = wcn36xx_suspend, .resume = wcn36xx_resume, + .set_rekey_data = wcn36xx_set_rekey_data, #endif .config = wcn36xx_config, .prepare_multicast = wcn36xx_prepare_multicast, @@ -1199,6 +1283,9 @@ static const struct ieee80211_ops wcn36xx_ops = { .sta_add = wcn36xx_sta_add, .sta_remove = wcn36xx_sta_remove, .ampdu_action = wcn36xx_ampdu_action, +#if IS_ENABLED(CONFIG_IPV6) + .ipv6_addr_change = wcn36xx_ipv6_addr_change, +#endif CFG80211_TESTMODE_CMD(wcn36xx_tm_cmd) }; @@ -1401,6 +1488,12 @@ static int wcn36xx_probe(struct platform_device *pdev) mutex_init(&wcn->hal_mutex); mutex_init(&wcn->scan_lock); + wcn->hal_buf = devm_kmalloc(wcn->dev, WCN36XX_HAL_BUF_SIZE, GFP_KERNEL); + if (!wcn->hal_buf) { + ret = -ENOMEM; + goto out_wq; + } + ret = dma_set_mask_and_coherent(wcn->dev, DMA_BIT_MASK(32)); if (ret < 0) { wcn36xx_err("failed to set DMA mask: %d\n", ret); diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c index d0c3a1557e8d..0e3be17d8cea 100644 --- a/drivers/net/wireless/ath/wcn36xx/smd.c +++ b/drivers/net/wireless/ath/wcn36xx/smd.c @@ -445,22 +445,12 @@ out: return ret; } -static void init_hal_msg(struct wcn36xx_hal_msg_header *hdr, - enum wcn36xx_hal_host_msg_type msg_type, - size_t msg_size) -{ - memset(hdr, 0, msg_size + sizeof(*hdr)); - hdr->msg_type = msg_type; - hdr->msg_version = WCN36XX_HAL_MSG_VERSION0; - hdr->len = msg_size + sizeof(*hdr); -} - #define __INIT_HAL_MSG(msg_body, type, version) \ do { \ - memset(&msg_body, 0, sizeof(msg_body)); \ - msg_body.header.msg_type = type; \ - msg_body.header.msg_version = version; \ - msg_body.header.len = sizeof(msg_body); \ + memset(&(msg_body), 0, sizeof(msg_body)); \ + (msg_body).header.msg_type = type; \ + (msg_body).header.msg_version = version; \ + (msg_body).header.len = sizeof(msg_body); \ } while (0) \ #define INIT_HAL_MSG(msg_body, type) \ @@ -2729,8 +2719,7 @@ int wcn36xx_smd_set_mc_list(struct wcn36xx *wcn, msg_body = (struct wcn36xx_hal_rcv_flt_pkt_set_mc_list_req_msg *) wcn->hal_buf; - init_hal_msg(&msg_body->header, WCN36XX_HAL_8023_MULTICAST_LIST_REQ, - sizeof(msg_body->mc_addr_list)); + INIT_HAL_MSG(*msg_body, WCN36XX_HAL_8023_MULTICAST_LIST_REQ); /* An empty list means all mc traffic will be received */ if (fp) @@ -2756,6 +2745,269 @@ out: return ret; } +int wcn36xx_smd_arp_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif, + bool enable) +{ + struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif); + struct wcn36xx_hal_host_offload_req_msg msg_body; + int ret; + + mutex_lock(&wcn->hal_mutex); + + INIT_HAL_MSG(msg_body, WCN36XX_HAL_HOST_OFFLOAD_REQ); + msg_body.host_offload_params.offload_type = + WCN36XX_HAL_IPV4_ARP_REPLY_OFFLOAD; + if (enable) { + msg_body.host_offload_params.enable = + WCN36XX_HAL_OFFLOAD_ARP_AND_BCAST_FILTER_ENABLE; + memcpy(&msg_body.host_offload_params.u, + &vif->bss_conf.arp_addr_list[0], sizeof(__be32)); + } + msg_body.ns_offload_params.bss_index = vif_priv->bss_index; + + PREPARE_HAL_BUF(wcn->hal_buf, msg_body); + + ret = wcn36xx_smd_send_and_wait(wcn, msg_body.header.len); + if (ret) { + wcn36xx_err("Sending host_offload_arp failed\n"); + goto out; + } + ret = wcn36xx_smd_rsp_status_check(wcn->hal_buf, wcn->hal_rsp_len); + if (ret) { + wcn36xx_err("host_offload_arp failed err=%d\n", ret); + goto out; + } +out: + mutex_unlock(&wcn->hal_mutex); + return ret; +} + +#if IS_ENABLED(CONFIG_IPV6) +int wcn36xx_smd_ipv6_ns_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif, + bool enable) +{ + struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif); + struct wcn36xx_hal_host_offload_req_msg msg_body; + struct wcn36xx_hal_ns_offload_params *ns_params; + struct wcn36xx_hal_host_offload_req *ho_params; + int ret; + + mutex_lock(&wcn->hal_mutex); + + INIT_HAL_MSG(msg_body, WCN36XX_HAL_HOST_OFFLOAD_REQ); + ho_params = &msg_body.host_offload_params; + ns_params = &msg_body.ns_offload_params; + + ho_params->offload_type = WCN36XX_HAL_IPV6_NS_OFFLOAD; + if (enable) { + ho_params->enable = + WCN36XX_HAL_OFFLOAD_NS_AND_MCAST_FILTER_ENABLE; + if (vif_priv->num_target_ipv6_addrs) { + memcpy(&ho_params->u, + &vif_priv->target_ipv6_addrs[0].in6_u, + sizeof(struct in6_addr)); + memcpy(&ns_params->target_ipv6_addr1, + &vif_priv->target_ipv6_addrs[0].in6_u, + sizeof(struct in6_addr)); + ns_params->target_ipv6_addr1_valid = 1; + } + if (vif_priv->num_target_ipv6_addrs > 1) { + memcpy(&ns_params->target_ipv6_addr2, + &vif_priv->target_ipv6_addrs[1].in6_u, + sizeof(struct in6_addr)); + ns_params->target_ipv6_addr2_valid = 1; + } + } + memcpy(&ns_params->self_addr, vif->addr, ETH_ALEN); + ns_params->bss_index = vif_priv->bss_index; + + PREPARE_HAL_BUF(wcn->hal_buf, msg_body); + + ret = wcn36xx_smd_send_and_wait(wcn, msg_body.header.len); + if (ret) { + wcn36xx_err("Sending host_offload_arp failed\n"); + goto out; + } + ret = wcn36xx_smd_rsp_status_check(wcn->hal_buf, wcn->hal_rsp_len); + if (ret) { + wcn36xx_err("host_offload_arp failed err=%d\n", ret); + goto out; + } +out: + mutex_unlock(&wcn->hal_mutex); + return ret; +} +#else +int wcn36xx_smd_ipv6_ns_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif, + bool enable) +{ + return 0; +} +#endif + +int wcn36xx_smd_gtk_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif, + bool enable) +{ + struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif); + struct wcn36xx_hal_gtk_offload_req_msg msg_body; + int ret; + + mutex_lock(&wcn->hal_mutex); + + INIT_HAL_MSG(msg_body, WCN36XX_HAL_GTK_OFFLOAD_REQ); + + if (enable) { + memcpy(&msg_body.kek, vif_priv->rekey_data.kek, NL80211_KEK_LEN); + memcpy(&msg_body.kck, vif_priv->rekey_data.kck, NL80211_KCK_LEN); + msg_body.key_replay_counter = + le64_to_cpu(vif_priv->rekey_data.replay_ctr); + msg_body.bss_index = vif_priv->bss_index; + } else { + msg_body.flags = WCN36XX_HAL_GTK_OFFLOAD_FLAGS_DISABLE; + } + + PREPARE_HAL_BUF(wcn->hal_buf, msg_body); + + ret = wcn36xx_smd_send_and_wait(wcn, msg_body.header.len); + if (ret) { + wcn36xx_err("Sending host_offload_arp failed\n"); + goto out; + } + ret = wcn36xx_smd_rsp_status_check(wcn->hal_buf, wcn->hal_rsp_len); + if (ret) { + wcn36xx_err("host_offload_arp failed err=%d\n", ret); + goto out; + } +out: + mutex_unlock(&wcn->hal_mutex); + return ret; +} + +static int wcn36xx_smd_gtk_offload_get_info_rsp(struct wcn36xx *wcn, + struct ieee80211_vif *vif) +{ + struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif); + struct wcn36xx_hal_gtk_offload_get_info_rsp_msg *rsp; + __be64 replay_ctr; + + if (wcn36xx_smd_rsp_status_check(wcn->hal_buf, wcn->hal_rsp_len)) + return -EIO; + + rsp = (struct wcn36xx_hal_gtk_offload_get_info_rsp_msg *)wcn->hal_buf; + + if (rsp->bss_index != vif_priv->bss_index) { + wcn36xx_err("gtk_offload_info invalid response bss index %d\n", + rsp->bss_index); + return -ENOENT; + } + + if (vif_priv->rekey_data.replay_ctr != cpu_to_le64(rsp->key_replay_counter)) { + replay_ctr = cpu_to_be64(rsp->key_replay_counter); + vif_priv->rekey_data.replay_ctr = + cpu_to_le64(rsp->key_replay_counter); + ieee80211_gtk_rekey_notify(vif, vif->bss_conf.bssid, + (void *)&replay_ctr, GFP_KERNEL); + wcn36xx_dbg(WCN36XX_DBG_HAL, + "GTK replay counter increment %llu\n", + rsp->key_replay_counter); + } + + wcn36xx_dbg(WCN36XX_DBG_HAL, + "gtk offload info status %d last_rekey_status %d " + "replay_counter %llu total_rekey_count %d gtk_rekey_count %d " + "igtk_rekey_count %d bss_index %d\n", + rsp->status, rsp->last_rekey_status, + rsp->key_replay_counter, rsp->total_rekey_count, + rsp->gtk_rekey_count, rsp->igtk_rekey_count, + rsp->bss_index); + + return 0; +} + +int wcn36xx_smd_gtk_offload_get_info(struct wcn36xx *wcn, + struct ieee80211_vif *vif) +{ + struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif); + struct wcn36xx_hal_gtk_offload_get_info_req_msg msg_body; + int ret; + + mutex_lock(&wcn->hal_mutex); + + INIT_HAL_MSG(msg_body, WCN36XX_HAL_GTK_OFFLOAD_GETINFO_REQ); + + msg_body.bss_index = vif_priv->bss_index; + + PREPARE_HAL_BUF(wcn->hal_buf, msg_body); + + ret = wcn36xx_smd_send_and_wait(wcn, msg_body.header.len); + if (ret) { + wcn36xx_err("Sending gtk_offload_get_info failed\n"); + goto out; + } + ret = wcn36xx_smd_rsp_status_check(wcn->hal_buf, wcn->hal_rsp_len); + if (ret) { + wcn36xx_err("gtk_offload_get_info failed err=%d\n", ret); + goto out; + } + ret = wcn36xx_smd_gtk_offload_get_info_rsp(wcn, vif); +out: + mutex_unlock(&wcn->hal_mutex); + return ret; +} + +int wcn36xx_smd_wlan_host_suspend_ind(struct wcn36xx *wcn) +{ + struct wcn36xx_hal_wlan_host_suspend_ind_msg msg_body; + int ret; + + mutex_lock(&wcn->hal_mutex); + + INIT_HAL_MSG(msg_body, WCN36XX_HAL_HOST_SUSPEND_IND); + msg_body.configured_mcst_bcst_filter_setting = 0; + msg_body.active_session_count = 1; + PREPARE_HAL_BUF(wcn->hal_buf, msg_body); + + ret = rpmsg_send(wcn->smd_channel, wcn->hal_buf, msg_body.header.len); + + mutex_unlock(&wcn->hal_mutex); + + return ret; +} + +int wcn36xx_smd_host_resume(struct wcn36xx *wcn) +{ + struct wcn36xx_hal_wlan_host_resume_req_msg msg_body; + struct wcn36xx_hal_host_resume_rsp_msg *rsp; + int ret; + + mutex_lock(&wcn->hal_mutex); + + INIT_HAL_MSG(msg_body, WCN36XX_HAL_HOST_RESUME_REQ); + msg_body.configured_mcst_bcst_filter_setting = 0; + + PREPARE_HAL_BUF(wcn->hal_buf, msg_body); + + ret = wcn36xx_smd_send_and_wait(wcn, msg_body.header.len); + if (ret) { + wcn36xx_err("Sending wlan_host_resume failed\n"); + goto out; + } + ret = wcn36xx_smd_rsp_status_check(wcn->hal_buf, wcn->hal_rsp_len); + if (ret) { + wcn36xx_err("wlan_host_resume err=%d\n", ret); + goto out; + } + + rsp = (struct wcn36xx_hal_host_resume_rsp_msg *)wcn->hal_buf; + if (rsp->status) + wcn36xx_warn("wlan_host_resume status=%d\n", rsp->status); + +out: + mutex_unlock(&wcn->hal_mutex); + + return ret; +} + int wcn36xx_smd_rsp_process(struct rpmsg_device *rpdev, void *buf, int len, void *priv, u32 addr) { @@ -2804,6 +3056,10 @@ int wcn36xx_smd_rsp_process(struct rpmsg_device *rpdev, case WCN36XX_HAL_8023_MULTICAST_LIST_RSP: case WCN36XX_HAL_START_SCAN_OFFLOAD_RSP: case WCN36XX_HAL_STOP_SCAN_OFFLOAD_RSP: + case WCN36XX_HAL_HOST_OFFLOAD_RSP: + case WCN36XX_HAL_GTK_OFFLOAD_RSP: + case WCN36XX_HAL_GTK_OFFLOAD_GETINFO_RSP: + case WCN36XX_HAL_HOST_RESUME_RSP: memcpy(wcn->hal_buf, buf, len); wcn->hal_rsp_len = len; complete(&wcn->hal_rsp_compl); diff --git a/drivers/net/wireless/ath/wcn36xx/smd.h b/drivers/net/wireless/ath/wcn36xx/smd.h index 462860572e1f..d8bded03945d 100644 --- a/drivers/net/wireless/ath/wcn36xx/smd.h +++ b/drivers/net/wireless/ath/wcn36xx/smd.h @@ -146,4 +146,21 @@ int wcn36xx_smd_rsp_process(struct rpmsg_device *rpdev, int wcn36xx_smd_set_mc_list(struct wcn36xx *wcn, struct ieee80211_vif *vif, struct wcn36xx_hal_rcv_flt_mc_addr_list_type *fp); + +int wcn36xx_smd_arp_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif, + bool enable); + +int wcn36xx_smd_ipv6_ns_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif, + bool enable); + +int wcn36xx_smd_gtk_offload(struct wcn36xx *wcn, struct ieee80211_vif *vif, + bool enable); + +int wcn36xx_smd_gtk_offload_get_info(struct wcn36xx *wcn, + struct ieee80211_vif *vif); + +int wcn36xx_smd_wlan_host_suspend_ind(struct wcn36xx *wcn); + +int wcn36xx_smd_host_resume(struct wcn36xx *wcn); + #endif /* _SMD_H_ */ diff --git a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h index 71fa9992b118..6121d8a5641a 100644 --- a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h +++ b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h @@ -18,6 +18,7 @@ #define _WCN36XX_H_ #include +#include #include #include #include @@ -136,6 +137,19 @@ struct wcn36xx_vif { u8 self_dpu_desc_index; u8 self_ucast_dpu_sign; +#if IS_ENABLED(CONFIG_IPV6) + /* IPv6 addresses for WoWLAN */ + struct in6_addr target_ipv6_addrs[WCN36XX_HAL_IPV6_OFFLOAD_ADDR_MAX]; + unsigned long tentative_addrs[BITS_TO_LONGS(WCN36XX_HAL_IPV6_OFFLOAD_ADDR_MAX)]; + int num_target_ipv6_addrs; +#endif + /* WoWLAN GTK rekey data */ + struct { + u8 kck[NL80211_KCK_LEN], kek[NL80211_KEK_LEN]; + __le64 replay_ctr; + bool valid; + } rekey_data; + struct list_head sta_list; }; diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c index 6746fd206d2a..1ff2679963f0 100644 --- a/drivers/net/wireless/ath/wil6210/cfg80211.c +++ b/drivers/net/wireless/ath/wil6210/cfg80211.c @@ -2842,9 +2842,7 @@ void wil_p2p_wdev_free(struct wil6210_priv *wil) wil->radio_wdev = wil->main_ndev->ieee80211_ptr; mutex_unlock(&wil->vif_mutex); if (p2p_wdev) { - wiphy_lock(wil->wiphy); cfg80211_unregister_wdev(p2p_wdev); - wiphy_unlock(wil->wiphy); kfree(p2p_wdev); } } diff --git a/drivers/net/wireless/ath/wil6210/interrupt.c b/drivers/net/wireless/ath/wil6210/interrupt.c index d13d081fdcc6..67172385a5d6 100644 --- a/drivers/net/wireless/ath/wil6210/interrupt.c +++ b/drivers/net/wireless/ath/wil6210/interrupt.c @@ -9,7 +9,7 @@ #include "wil6210.h" #include "trace.h" -/** +/* * Theory of operation: * * There is ISR pseudo-cause register, diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c index 02ad44997e87..2dc8406736f4 100644 --- a/drivers/net/wireless/ath/wil6210/wmi.c +++ b/drivers/net/wireless/ath/wil6210/wmi.c @@ -224,7 +224,7 @@ struct auth_no_hdr { u8 led_polarity = LED_POLARITY_LOW_ACTIVE; /** - * return AHB address for given firmware internal (linker) address + * wmi_addr_remap - return AHB address for given firmware internal (linker) address * @x: internal address * If address have no valid AHB mapping, return 0 */ @@ -242,7 +242,7 @@ static u32 wmi_addr_remap(u32 x) } /** - * find fw_mapping entry by section name + * wil_find_fw_mapping - find fw_mapping entry by section name * @section: section name * * Return pointer to section or NULL if not found @@ -260,7 +260,7 @@ struct fw_map *wil_find_fw_mapping(const char *section) } /** - * Check address validity for WMI buffer; remap if needed + * wmi_buffer_block - Check address validity for WMI buffer; remap if needed * @wil: driver data * @ptr_: internal (linker) fw/ucode address * @size: if non zero, validate the block does not diff --git a/drivers/net/wireless/broadcom/b43/phy_n.c b/drivers/net/wireless/broadcom/b43/phy_n.c index 665b737fbb0d..cf3ccf4ddfe7 100644 --- a/drivers/net/wireless/broadcom/b43/phy_n.c +++ b/drivers/net/wireless/broadcom/b43/phy_n.c @@ -4592,58 +4592,11 @@ static void b43_nphy_spur_workaround(struct b43_wldev *dev) { struct b43_phy_n *nphy = dev->phy.n; - u8 channel = dev->phy.channel; - int tone[2] = { 57, 58 }; - u32 noise[2] = { 0x3FF, 0x3FF }; - B43_WARN_ON(dev->phy.rev < 3); if (nphy->hang_avoid) b43_nphy_stay_in_carrier_search(dev, 1); - if (nphy->gband_spurwar_en) { - /* TODO: N PHY Adjust Analog Pfbw (7) */ - if (channel == 11 && b43_is_40mhz(dev)) { - ; /* TODO: N PHY Adjust Min Noise Var(2, tone, noise)*/ - } else { - ; /* TODO: N PHY Adjust Min Noise Var(0, NULL, NULL)*/ - } - /* TODO: N PHY Adjust CRS Min Power (0x1E) */ - } - - if (nphy->aband_spurwar_en) { - if (channel == 54) { - tone[0] = 0x20; - noise[0] = 0x25F; - } else if (channel == 38 || channel == 102 || channel == 118) { - if (0 /* FIXME */) { - tone[0] = 0x20; - noise[0] = 0x21F; - } else { - tone[0] = 0; - noise[0] = 0; - } - } else if (channel == 134) { - tone[0] = 0x20; - noise[0] = 0x21F; - } else if (channel == 151) { - tone[0] = 0x10; - noise[0] = 0x23F; - } else if (channel == 153 || channel == 161) { - tone[0] = 0x30; - noise[0] = 0x23F; - } else { - tone[0] = 0; - noise[0] = 0; - } - - if (!tone[0] && !noise[0]) { - ; /* TODO: N PHY Adjust Min Noise Var(1, tone, noise)*/ - } else { - ; /* TODO: N PHY Adjust Min Noise Var(0, NULL, NULL)*/ - } - } - if (nphy->hang_avoid) b43_nphy_stay_in_carrier_search(dev, 0); } diff --git a/drivers/net/wireless/broadcom/b43legacy/dma.c b/drivers/net/wireless/broadcom/b43legacy/dma.c index 7e2f70c4207c..6869f2bf1bae 100644 --- a/drivers/net/wireless/broadcom/b43legacy/dma.c +++ b/drivers/net/wireless/broadcom/b43legacy/dma.c @@ -213,19 +213,6 @@ return dev->dma.tx_ring1; return ring; } -/* Bcm4301-ring to mac80211-queue mapping */ -static inline int txring_to_priority(struct b43legacy_dmaring *ring) -{ - static const u8 idx_to_prio[] = - { 3, 2, 1, 0, 4, 5, }; - -/*FIXME: have only one queue, for now */ -return 0; - - return idx_to_prio[ring->index]; -} - - static u16 b43legacy_dmacontroller_base(enum b43legacy_dmatype type, int controller_idx) { diff --git a/drivers/net/wireless/broadcom/b43legacy/main.c b/drivers/net/wireless/broadcom/b43legacy/main.c index f64ebff68308..eec3af9c3745 100644 --- a/drivers/net/wireless/broadcom/b43legacy/main.c +++ b/drivers/net/wireless/broadcom/b43legacy/main.c @@ -391,7 +391,7 @@ void b43legacy_tsf_read(struct b43legacy_wldev *dev, u64 *tsf) * registers, we should take care of register overflows. * In theory, the whole tsf read process should be atomic. * We try to be atomic here, by restaring the read process, - * if any of the high registers changed (overflew). + * if any of the high registers changed (overflowed). */ if (dev->dev->id.revision >= 3) { u32 low; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index f4405d7861b6..cedba56fc448 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -2767,8 +2767,9 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev, struct brcmf_sta_info_le sta_info_le; u32 sta_flags; u32 is_tdls_peer; - s32 total_rssi; - s32 count_rssi; + s32 total_rssi_avg = 0; + s32 total_rssi = 0; + s32 count_rssi = 0; int rssi; u32 i; @@ -2834,25 +2835,27 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev, sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES); sinfo->rx_bytes = le64_to_cpu(sta_info_le.rx_tot_bytes); } - total_rssi = 0; - count_rssi = 0; for (i = 0; i < BRCMF_ANT_MAX; i++) { - if (sta_info_le.rssi[i]) { - sinfo->chain_signal_avg[count_rssi] = - sta_info_le.rssi[i]; - sinfo->chain_signal[count_rssi] = - sta_info_le.rssi[i]; - total_rssi += sta_info_le.rssi[i]; - count_rssi++; - } + if (sta_info_le.rssi[i] == 0 || + sta_info_le.rx_lastpkt_rssi[i] == 0) + continue; + sinfo->chains |= BIT(count_rssi); + sinfo->chain_signal[count_rssi] = + sta_info_le.rx_lastpkt_rssi[i]; + sinfo->chain_signal_avg[count_rssi] = + sta_info_le.rssi[i]; + total_rssi += sta_info_le.rx_lastpkt_rssi[i]; + total_rssi_avg += sta_info_le.rssi[i]; + count_rssi++; } if (count_rssi) { - sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL); - sinfo->chains = count_rssi; - sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL); - total_rssi /= count_rssi; - sinfo->signal = total_rssi; + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG); + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL); + sinfo->filled |= + BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG); + sinfo->signal = total_rssi / count_rssi; + sinfo->signal_avg = total_rssi_avg / count_rssi; } else if (test_bit(BRCMF_VIF_STATUS_CONNECTED, &ifp->vif->sme_state)) { memset(&scb_val, 0, sizeof(scb_val)); @@ -2892,8 +2895,13 @@ brcmf_cfg80211_dump_station(struct wiphy *wiphy, struct net_device *ndev, &cfg->assoclist, sizeof(cfg->assoclist)); if (err) { - bphy_err(drvr, "BRCMF_C_GET_ASSOCLIST unsupported, err=%d\n", - err); + /* GET_ASSOCLIST unsupported by firmware of older chips */ + if (err == -EBADE) + bphy_info_once(drvr, "BRCMF_C_GET_ASSOCLIST unsupported\n"); + else + bphy_err(drvr, "BRCMF_C_GET_ASSOCLIST failed, err=%d\n", + err); + cfg->assoclist.count = 0; return -EOPNOTSUPP; } @@ -6848,7 +6856,12 @@ static int brcmf_setup_wiphybands(struct brcmf_cfg80211_info *cfg) err = brcmf_fil_iovar_int_get(ifp, "rxchain", &rxchain); if (err) { - bphy_err(drvr, "rxchain error (%d)\n", err); + /* rxchain unsupported by firmware of older chips */ + if (err == -EBADE) + bphy_info_once(drvr, "rxchain unsupported\n"); + else + bphy_err(drvr, "rxchain error (%d)\n", err); + nchain = 1; } else { for (nchain = 0; rxchain; nchain++) @@ -7442,18 +7455,23 @@ static s32 brcmf_translate_country_code(struct brcmf_pub *drvr, char alpha2[2], s32 found_index; int i; - country_codes = drvr->settings->country_codes; - if (!country_codes) { - brcmf_dbg(TRACE, "No country codes configured for device\n"); - return -EINVAL; - } - if ((alpha2[0] == ccreq->country_abbrev[0]) && (alpha2[1] == ccreq->country_abbrev[1])) { brcmf_dbg(TRACE, "Country code already set\n"); return -EAGAIN; } + country_codes = drvr->settings->country_codes; + if (!country_codes) { + brcmf_dbg(TRACE, "No country codes configured for device, using ISO3166 code and 0 rev\n"); + memset(ccreq, 0, sizeof(*ccreq)); + ccreq->country_abbrev[0] = alpha2[0]; + ccreq->country_abbrev[1] = alpha2[1]; + ccreq->ccode[0] = alpha2[0]; + ccreq->ccode[1] = alpha2[1]; + return 0; + } + found_index = -1; for (i = 0; i < country_codes->table_size; i++) { cc = &country_codes->table[i]; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c index cee1682d2333..db5f8535fdb5 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c @@ -188,9 +188,14 @@ static void _brcmf_set_multicast_list(struct work_struct *work) /*Finally, pick up the PROMISC flag */ cmd_value = (ndev->flags & IFF_PROMISC) ? true : false; err = brcmf_fil_cmd_int_set(ifp, BRCMF_C_SET_PROMISC, cmd_value); - if (err < 0) - bphy_err(drvr, "Setting BRCMF_C_SET_PROMISC failed, %d\n", - err); + if (err < 0) { + /* PROMISC unsupported by firmware of older chips */ + if (err == -EBADE) + bphy_info_once(drvr, "BRCMF_C_SET_PROMISC unsupported\n"); + else + bphy_err(drvr, "Setting BRCMF_C_SET_PROMISC failed, err=%d\n", + err); + } brcmf_configure_arp_nd_offload(ifp, !cmd_value); } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.h index 44ba6f389fa9..9bb5f709d41a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/debug.h @@ -60,6 +60,10 @@ void __brcmf_err(struct brcmf_bus *bus, const char *func, const char *fmt, ...); ##__VA_ARGS__); \ } while (0) +#define bphy_info_once(drvr, fmt, ...) \ + wiphy_info_once((drvr)->wiphy, "%s: " fmt, __func__, \ + ##__VA_ARGS__) + #if defined(DEBUG) || defined(CONFIG_BRCM_TRACING) /* For debug/tracing purposes treat info messages as errors */ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h index 46c66415b4a6..e290dec9c53d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/firmware.h @@ -32,6 +32,13 @@ static const char BRCM_ ## fw_name ## _FIRMWARE_BASENAME[] = \ BRCMF_FW_DEFAULT_PATH fw_base; \ MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH fw_base ".bin") +/* Firmware and Country Local Matrix files */ +#define BRCMF_FW_CLM_DEF(fw_name, fw_base) \ +static const char BRCM_ ## fw_name ## _FIRMWARE_BASENAME[] = \ + BRCMF_FW_DEFAULT_PATH fw_base; \ +MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH fw_base ".bin"); \ +MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH fw_base ".clm_blob") + #define BRCMF_FW_ENTRY(chipid, mask, name) \ { chipid, mask, BRCM_ ## name ## _FIRMWARE_BASENAME } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c index a7554265f95f..2f7bc3a70c65 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c @@ -12,12 +12,59 @@ #include "common.h" #include "of.h" +static int brcmf_of_get_country_codes(struct device *dev, + struct brcmf_mp_device *settings) +{ + struct device_node *np = dev->of_node; + struct brcmfmac_pd_cc_entry *cce; + struct brcmfmac_pd_cc *cc; + int count; + int i; + + count = of_property_count_strings(np, "brcm,ccode-map"); + if (count < 0) { + /* The property is optional, so return success if it doesn't + * exist. Otherwise propagate the error code. + */ + return (count == -EINVAL) ? 0 : count; + } + + cc = devm_kzalloc(dev, sizeof(*cc) + count * sizeof(*cce), GFP_KERNEL); + if (!cc) + return -ENOMEM; + + cc->table_size = count; + + for (i = 0; i < count; i++) { + const char *map; + + cce = &cc->table[i]; + + if (of_property_read_string_index(np, "brcm,ccode-map", + i, &map)) + continue; + + /* String format e.g. US-Q2-86 */ + if (sscanf(map, "%2c-%2c-%d", cce->iso3166, cce->cc, + &cce->rev) != 3) + brcmf_err("failed to read country map %s\n", map); + else + brcmf_dbg(INFO, "%s-%s-%d\n", cce->iso3166, cce->cc, + cce->rev); + } + + settings->country_codes = cc; + + return 0; +} + void brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type, struct brcmf_mp_device *settings) { struct brcmfmac_sdio_pd *sdio = &settings->bus.sdio; struct device_node *root, *np = dev->of_node; int irq; + int err; u32 irqf; u32 val; @@ -43,8 +90,14 @@ void brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type, of_node_put(root); } - if (!np || bus_type != BRCMF_BUSTYPE_SDIO || - !of_device_is_compatible(np, "brcm,bcm4329-fmac")) + if (!np || !of_device_is_compatible(np, "brcm,bcm4329-fmac")) + return; + + err = brcmf_of_get_country_codes(dev, settings); + if (err) + brcmf_err("failed to get OF country code map (err=%d)\n", err); + + if (bus_type != BRCMF_BUSTYPE_SDIO) return; if (of_property_read_u32(np, "brcm,drive-strength", &val) == 0) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c index 34cd8a7401fe..9ac0d8c73d5a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c @@ -2037,7 +2037,7 @@ static void brcmf_p2p_get_current_chanspec(struct brcmf_p2p_info *p2p, } /** - * Change a P2P Role. + * brcmf_p2p_ifchange - Change a P2P Role. * @cfg: driver private data for cfg80211 interface. * @if_type: interface type. * Returns 0 if success. diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 143a705b5cb3..c49dd0c36ae4 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -48,8 +48,8 @@ enum brcmf_pcie_state { BRCMF_FW_DEF(43602, "brcmfmac43602-pcie"); BRCMF_FW_DEF(4350, "brcmfmac4350-pcie"); BRCMF_FW_DEF(4350C, "brcmfmac4350c2-pcie"); -BRCMF_FW_DEF(4356, "brcmfmac4356-pcie"); -BRCMF_FW_DEF(43570, "brcmfmac43570-pcie"); +BRCMF_FW_CLM_DEF(4356, "brcmfmac4356-pcie"); +BRCMF_FW_CLM_DEF(43570, "brcmfmac43570-pcie"); BRCMF_FW_DEF(4358, "brcmfmac4358-pcie"); BRCMF_FW_DEF(4359, "brcmfmac4359-pcie"); BRCMF_FW_DEF(4364, "brcmfmac4364-pcie"); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index 16ed325795a8..97ee9e2e2e35 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -616,18 +616,18 @@ BRCMF_FW_DEF(43362, "brcmfmac43362-sdio"); BRCMF_FW_DEF(4339, "brcmfmac4339-sdio"); BRCMF_FW_DEF(43430A0, "brcmfmac43430a0-sdio"); /* Note the names are not postfixed with a1 for backward compatibility */ -BRCMF_FW_DEF(43430A1, "brcmfmac43430-sdio"); -BRCMF_FW_DEF(43455, "brcmfmac43455-sdio"); +BRCMF_FW_CLM_DEF(43430A1, "brcmfmac43430-sdio"); +BRCMF_FW_CLM_DEF(43455, "brcmfmac43455-sdio"); BRCMF_FW_DEF(43456, "brcmfmac43456-sdio"); -BRCMF_FW_DEF(4354, "brcmfmac4354-sdio"); -BRCMF_FW_DEF(4356, "brcmfmac4356-sdio"); +BRCMF_FW_CLM_DEF(4354, "brcmfmac4354-sdio"); +BRCMF_FW_CLM_DEF(4356, "brcmfmac4356-sdio"); BRCMF_FW_DEF(4359, "brcmfmac4359-sdio"); -BRCMF_FW_DEF(4373, "brcmfmac4373-sdio"); -BRCMF_FW_DEF(43012, "brcmfmac43012-sdio"); +BRCMF_FW_CLM_DEF(4373, "brcmfmac4373-sdio"); +BRCMF_FW_CLM_DEF(43012, "brcmfmac43012-sdio"); /* firmware config files */ -MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcm/brcmfmac*-sdio.*.txt"); -MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcm/brcmfmac*-pcie.*.txt"); +MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-sdio.*.txt"); +MODULE_FIRMWARE(BRCMF_FW_DEFAULT_PATH "brcmfmac*-pcie.*.txt"); static const struct brcmf_firmware_mapping brcmf_sdio_fwnames[] = { BRCMF_FW_ENTRY(BRCM_CC_43143_CHIP_ID, 0xFFFFFFFF, 43143), @@ -1291,7 +1291,7 @@ static void brcmf_sdio_free_glom(struct brcmf_sdio *bus) } } -/** +/* * brcmfmac sdio bus specific header * This is the lowest layer header wrapped on the packets transmitted between * host and WiFi dongle which contains information needed for SDIO core and @@ -4162,7 +4162,6 @@ static int brcmf_sdio_bus_reset(struct device *dev) if (ret) { brcmf_err("Failed to probe after sdio device reset: ret %d\n", ret); - brcmf_sdiod_remove(sdiodev); } return ret; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c index 53365977bfd6..2084b506a450 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/aiutils.c @@ -531,9 +531,6 @@ void ai_detach(struct si_pub *sih) sii = container_of(sih, struct si_info, pub); - if (sii == NULL) - return; - kfree(sii); } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c index 39f3af2d0439..eadac0f5590f 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c @@ -1220,6 +1220,7 @@ static int brcms_bcma_probe(struct bcma_device *pdev) { struct brcms_info *wl; struct ieee80211_hw *hw; + int ret; dev_info(&pdev->dev, "mfg %x core %x rev %d class %d irq %d\n", pdev->id.manuf, pdev->id.id, pdev->id.rev, pdev->id.class, @@ -1244,11 +1245,16 @@ static int brcms_bcma_probe(struct bcma_device *pdev) wl = brcms_attach(pdev); if (!wl) { pr_err("%s: brcms_attach failed!\n", __func__); - return -ENODEV; + ret = -ENODEV; + goto err_free_ieee80211; } brcms_led_register(wl); return 0; + +err_free_ieee80211: + ieee80211_free_hw(hw); + return ret; } static int brcms_suspend(struct bcma_device *pdev) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c index 763e0ec583d7..26de1bd7fee9 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/main.c @@ -6607,7 +6607,8 @@ brcms_c_d11hdrs_mac80211(struct brcms_c_info *wlc, struct ieee80211_hw *hw, rts->frame_control = cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_RTS); - memcpy(&rts->ra, &h->addr1, 2 * ETH_ALEN); + memcpy(&rts->ra, &h->addr1, ETH_ALEN); + memcpy(&rts->ta, &h->addr2, ETH_ALEN); } /* mainrate diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/stf.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/stf.h index aa4ab53bf634..af86c7fc5112 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/stf.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/stf.h @@ -29,7 +29,6 @@ void brcms_c_stf_ss_update(struct brcms_c_info *wlc, struct brcms_band *band); void brcms_c_stf_phy_txant_upd(struct brcms_c_info *wlc); int brcms_c_stf_txchain_set(struct brcms_c_info *wlc, s32 int_val, bool force); bool brcms_c_stf_stbc_rx_set(struct brcms_c_info *wlc, s32 int_val); -void brcms_c_stf_phy_txant_upd(struct brcms_c_info *wlc); void brcms_c_stf_phy_chain_calc(struct brcms_c_info *wlc); u16 brcms_c_stf_phytxchain_sel(struct brcms_c_info *wlc, u32 rspec); u16 brcms_c_stf_d11hdrs_phyctl_txant(struct brcms_c_info *wlc, u32 rspec); diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c index 23fbddd0c1f8..47eb89b773cf 100644 --- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c @@ -5356,7 +5356,7 @@ struct ipw2100_wep_key { #define WEP_STR_128(x) x[0],x[1],x[2],x[3],x[4],x[5],x[6],x[7],x[8],x[9],x[10] /** - * Set a the wep key + * ipw2100_set_key() - Set a the wep key * * @priv: struct to work on * @idx: index of the key we want to set diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile index 14b0db28143b..d86918d162aa 100644 --- a/drivers/net/wireless/intel/iwlwifi/Makefile +++ b/drivers/net/wireless/intel/iwlwifi/Makefile @@ -16,9 +16,10 @@ iwlwifi-objs += iwl-trans.o iwlwifi-objs += queue/tx.o iwlwifi-objs += fw/img.o fw/notif-wait.o -iwlwifi-objs += fw/dbg.o fw/pnvm.o +iwlwifi-objs += fw/dbg.o fw/pnvm.o fw/dump.o iwlwifi-$(CONFIG_IWLMVM) += fw/paging.o fw/smem.o fw/init.o iwlwifi-$(CONFIG_ACPI) += fw/acpi.o +iwlwifi-$(CONFIG_EFI) += fw/uefi.o iwlwifi-$(CONFIG_IWLWIFI_DEBUGFS) += fw/debugfs.o iwlwifi-objs += $(iwlwifi-m) diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c index c2315dea9a23..7f1faa9d97b4 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include #include @@ -9,7 +9,7 @@ #include "iwl-prph.h" /* Highest firmware API version supported */ -#define IWL_22000_UCODE_API_MAX 63 +#define IWL_22000_UCODE_API_MAX 64 /* Lowest firmware API version supported */ #define IWL_22000_UCODE_API_MIN 39 @@ -47,6 +47,7 @@ #define IWL_MA_A_GF_A_FW_PRE "iwlwifi-ma-a0-gf-a0-" #define IWL_MA_A_GF4_A_FW_PRE "iwlwifi-ma-a0-gf4-a0-" #define IWL_MA_A_MR_A_FW_PRE "iwlwifi-ma-a0-mr-a0-" +#define IWL_MA_A_FM_A_FW_PRE "iwlwifi-ma-a0-fm-a0-" #define IWL_SNJ_A_MR_A_FW_PRE "iwlwifi-SoSnj-a0-mr-a0-" #define IWL_BZ_A_HR_B_FW_PRE "iwlwifi-bz-a0-hr-b0-" #define IWL_BZ_A_GF_A_FW_PRE "iwlwifi-bz-a0-gf-a0-" @@ -93,6 +94,8 @@ IWL_MA_A_GF4_A_FW_PRE __stringify(api) ".ucode" #define IWL_MA_A_MR_A_FW_MODULE_FIRMWARE(api) \ IWL_MA_A_MR_A_FW_PRE __stringify(api) ".ucode" +#define IWL_MA_A_FM_A_FW_MODULE_FIRMWARE(api) \ + IWL_MA_A_FM_A_FW_PRE __stringify(api) ".ucode" #define IWL_SNJ_A_MR_A_MODULE_FIRMWARE(api) \ IWL_SNJ_A_MR_A_FW_PRE __stringify(api) ".ucode" #define IWL_BZ_A_HR_B_MODULE_FIRMWARE(api) \ @@ -389,6 +392,7 @@ const char iwl_ax201_name[] = "Intel(R) Wi-Fi 6 AX201 160MHz"; const char iwl_ax203_name[] = "Intel(R) Wi-Fi 6 AX203"; const char iwl_ax211_name[] = "Intel(R) Wi-Fi 6E AX211 160MHz"; const char iwl_ax221_name[] = "Intel(R) Wi-Fi 6E AX221 160MHz"; +const char iwl_ax231_name[] = "Intel(R) Wi-Fi 6E AX231 160MHz"; const char iwl_ax411_name[] = "Intel(R) Wi-Fi 6E AX411 160MHz"; const char iwl_ax200_killer_1650w_name[] = @@ -724,6 +728,13 @@ const struct iwl_cfg iwl_cfg_ma_a0_mr_a0 = { .num_rbds = IWL_NUM_RBDS_AX210_HE, }; +const struct iwl_cfg iwl_cfg_ma_a0_fm_a0 = { + .fw_name_pre = IWL_MA_A_FM_A_FW_PRE, + .uhb_supported = true, + IWL_DEVICE_AX210, + .num_rbds = IWL_NUM_RBDS_AX210_HE, +}; + const struct iwl_cfg iwl_cfg_snj_a0_mr_a0 = { .fw_name_pre = IWL_SNJ_A_MR_A_FW_PRE, .uhb_supported = true, @@ -797,6 +808,7 @@ MODULE_FIRMWARE(IWL_MA_A_HR_B_FW_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_MA_A_GF_A_FW_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_MA_A_GF4_A_FW_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_MA_A_MR_A_FW_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL_MA_A_FM_A_FW_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_SNJ_A_MR_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_BZ_A_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_BZ_A_GF_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c index df1297358379..871533beff30 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include #include @@ -171,8 +171,12 @@ const char iwl9260_killer_1550_name[] = "Killer (R) Wireless-AC 1550 Wireless Network Adapter (9260NGW) 160MHz"; const char iwl9560_killer_1550i_name[] = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)"; +const char iwl9560_killer_1550i_160_name[] = + "Killer(R) Wireless-AC 1550i Wireless Network Adapter (9560NGW) 160MHz"; const char iwl9560_killer_1550s_name[] = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)"; +const char iwl9560_killer_1550s_160_name[] = + "Killer(R) Wireless-AC 1550s Wireless Network Adapter (9560D2W) 160MHz"; const struct iwl_cfg iwl9260_2ac_cfg = { .fw_name_pre = IWL9260_FW_PRE, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index e31bba836c6f..34933f133a0a 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -163,6 +163,27 @@ int iwl_acpi_get_dsm_u8(struct device *dev, int rev, int func, } IWL_EXPORT_SYMBOL(iwl_acpi_get_dsm_u8); +/* + * Evaluate a DSM with no arguments and a u32 return value, + */ +int iwl_acpi_get_dsm_u32(struct device *dev, int rev, int func, + const guid_t *guid, u32 *value) +{ + int ret; + u64 val; + + ret = iwl_acpi_get_dsm_integer(dev, rev, func, + guid, &val, sizeof(u32)); + + if (ret < 0) + return ret; + + /* cast val (u64) to be u32 */ + *value = (u32)val; + return 0; +} +IWL_EXPORT_SYMBOL(iwl_acpi_get_dsm_u32); + union acpi_object *iwl_acpi_get_wifi_pkg(struct device *dev, union acpi_object *data, int data_size, int *tbl_rev) @@ -696,68 +717,37 @@ int iwl_sar_geo_init(struct iwl_fw_runtime *fwrt, } IWL_EXPORT_SYMBOL(iwl_sar_geo_init); -static u32 iwl_acpi_eval_dsm_func(struct device *dev, enum iwl_dsm_funcs_rev_0 eval_func) -{ - union acpi_object *obj; - u32 ret; - - obj = iwl_acpi_get_dsm_object(dev, 0, - eval_func, NULL, - &iwl_guid); - - if (IS_ERR(obj)) { - IWL_DEBUG_DEV_RADIO(dev, - "ACPI: DSM func '%d': Got Error in obj = %ld\n", - eval_func, - PTR_ERR(obj)); - return 0; - } - - if (obj->type != ACPI_TYPE_INTEGER) { - IWL_DEBUG_DEV_RADIO(dev, - "ACPI: DSM func '%d' did not return a valid object, type=%d\n", - eval_func, - obj->type); - ret = 0; - goto out; - } - - ret = obj->integer.value; - IWL_DEBUG_DEV_RADIO(dev, - "ACPI: DSM method evaluated: func='%d', ret=%d\n", - eval_func, - ret); -out: - ACPI_FREE(obj); - return ret; -} - __le32 iwl_acpi_get_lari_config_bitmap(struct iwl_fw_runtime *fwrt) { - u32 ret; + int ret; + u8 value; __le32 config_bitmap = 0; /* ** Evaluate func 'DSM_FUNC_ENABLE_INDONESIA_5G2' */ - ret = iwl_acpi_eval_dsm_func(fwrt->dev, DSM_FUNC_ENABLE_INDONESIA_5G2); + ret = iwl_acpi_get_dsm_u8(fwrt->dev, 0, + DSM_FUNC_ENABLE_INDONESIA_5G2, + &iwl_guid, &value); - if (ret == DSM_VALUE_INDONESIA_ENABLE) + if (!ret && value == DSM_VALUE_INDONESIA_ENABLE) config_bitmap |= cpu_to_le32(LARI_CONFIG_ENABLE_5G2_IN_INDONESIA_MSK); /* ** Evaluate func 'DSM_FUNC_DISABLE_SRD' */ - ret = iwl_acpi_eval_dsm_func(fwrt->dev, DSM_FUNC_DISABLE_SRD); - - if (ret == DSM_VALUE_SRD_PASSIVE) - config_bitmap |= - cpu_to_le32(LARI_CONFIG_CHANGE_ETSI_TO_PASSIVE_MSK); - - else if (ret == DSM_VALUE_SRD_DISABLE) - config_bitmap |= - cpu_to_le32(LARI_CONFIG_CHANGE_ETSI_TO_DISABLED_MSK); + ret = iwl_acpi_get_dsm_u8(fwrt->dev, 0, + DSM_FUNC_DISABLE_SRD, + &iwl_guid, &value); + if (!ret) { + if (value == DSM_VALUE_SRD_PASSIVE) + config_bitmap |= + cpu_to_le32(LARI_CONFIG_CHANGE_ETSI_TO_PASSIVE_MSK); + else if (value == DSM_VALUE_SRD_DISABLE) + config_bitmap |= + cpu_to_le32(LARI_CONFIG_CHANGE_ETSI_TO_DISABLED_MSK); + } return config_bitmap; } diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h index d16e6ec08c9f..b858e998999c 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h @@ -78,6 +78,7 @@ enum iwl_dsm_funcs_rev_0 { DSM_FUNC_DISABLE_SRD = 1, DSM_FUNC_ENABLE_INDONESIA_5G2 = 2, DSM_FUNC_11AX_ENABLEMENT = 6, + DSM_FUNC_ENABLE_UNII4_CHAN = 7 }; enum iwl_dsm_values_srd { @@ -116,6 +117,9 @@ void *iwl_acpi_get_object(struct device *dev, acpi_string method); int iwl_acpi_get_dsm_u8(struct device *dev, int rev, int func, const guid_t *guid, u8 *value); +int iwl_acpi_get_dsm_u32(struct device *dev, int rev, int func, + const guid_t *guid, u32 *value); + union acpi_object *iwl_acpi_get_wifi_pkg(struct device *dev, union acpi_object *data, int data_size, int *tbl_rev); @@ -182,6 +186,12 @@ static inline int iwl_acpi_get_dsm_u8(struct device *dev, int rev, int func, return -ENOENT; } +static inline int iwl_acpi_get_dsm_u32(struct device *dev, int rev, int func, + const guid_t *guid, u32 *value) +{ + return -ENOENT; +} + static inline union acpi_object *iwl_acpi_get_wifi_pkg(struct device *dev, union acpi_object *data, int data_size, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h index c625d319142e..ce060c3dfd7b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h @@ -534,11 +534,6 @@ enum iwl_legacy_cmds { */ OFFLOADS_QUERY_CMD = 0xd5, - /** - * @REMOTE_WAKE_CONFIG_CMD: &struct iwl_wowlan_remote_wake_config - */ - REMOTE_WAKE_CONFIG_CMD = 0xd6, - /** * @D0I3_END_CMD: End D0i3/D3 state, no command data */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h b/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h index 758639084e0c..b2e7ef3ddc88 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2012-2014, 2018-2020 Intel Corporation + * Copyright (C) 2012-2014, 2018-2021 Intel Corporation * Copyright (C) 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH */ @@ -159,6 +159,22 @@ struct iwl_proto_offload_cmd_v3_large { struct iwl_ns_config ns_config[IWL_PROTO_OFFLOAD_NUM_NS_CONFIG_V3L]; } __packed; /* PROT_OFFLOAD_CONFIG_CMD_DB_S_VER_3 */ +/** + * struct iwl_proto_offload_cmd_v4 - ARP/NS offload configuration + * @sta_id: station id + * @common: common/IPv4 configuration + * @num_valid_ipv6_addrs: number of valid IPv6 addresses + * @targ_addrs: target IPv6 addresses + * @ns_config: NS offload configurations + */ +struct iwl_proto_offload_cmd_v4 { + __le32 sta_id; + struct iwl_proto_offload_cmd_common common; + __le32 num_valid_ipv6_addrs; + struct iwl_targ_addr targ_addrs[IWL_PROTO_OFFLOAD_NUM_IPV6_ADDRS_V3L]; + struct iwl_ns_config ns_config[IWL_PROTO_OFFLOAD_NUM_NS_CONFIG_V3L]; +} __packed; /* PROT_OFFLOAD_CONFIG_CMD_DB_S_VER_4 */ + /* * WOWLAN_PATTERNS */ @@ -302,13 +318,23 @@ struct iwl_wowlan_patterns_cmd { /** * @n_patterns: number of patterns */ - __le32 n_patterns; + u8 n_patterns; + + /** + * @n_patterns: sta_id + */ + u8 sta_id; + + /** + * @reserved: reserved for alignment + */ + __le16 reserved; /** * @patterns: the patterns, array length in @n_patterns */ struct iwl_wowlan_pattern_v2 patterns[]; -} __packed; /* WOWLAN_PATTERN_ARRAY_API_S_VER_2 */ +} __packed; /* WOWLAN_PATTERN_ARRAY_API_S_VER_3 */ enum iwl_wowlan_wakeup_filters { IWL_WOWLAN_WAKEUP_MAGIC_PACKET = BIT(0), @@ -339,9 +365,10 @@ enum iwl_wowlan_flags { }; /** - * struct iwl_wowlan_config_cmd - WoWLAN configuration + * struct iwl_wowlan_config_cmd - WoWLAN configuration (versions 5 and 6) * @wakeup_filter: filter from &enum iwl_wowlan_wakeup_filters - * @non_qos_seq: non-QoS sequence counter to use next + * @non_qos_seq: non-QoS sequence counter to use next. + * Reserved if the struct has version >= 6. * @qos_seq: QoS sequence counters to use next * @wowlan_ba_teardown_tids: bitmap of BA sessions to tear down * @is_11n_connection: indicates HT connection @@ -456,6 +483,23 @@ struct iwl_wowlan_kek_kck_material_cmd_v3 { __le32 bigtk_cipher; } __packed; /* KEK_KCK_MATERIAL_API_S_VER_3 */ +struct iwl_wowlan_kek_kck_material_cmd_v4 { + __le32 sta_id; + u8 kck[IWL_KCK_MAX_SIZE]; + u8 kek[IWL_KEK_MAX_SIZE]; + __le16 kck_len; + __le16 kek_len; + __le64 replay_ctr; + __le32 akm; + __le32 gtk_cipher; + __le32 igtk_cipher; + __le32 bigtk_cipher; +} __packed; /* KEK_KCK_MATERIAL_API_S_VER_4 */ + +struct iwl_wowlan_get_status_cmd { + __le32 sta_id; +} __packed; /* WOWLAN_GET_STATUSES_CMD_API_S_VER_1 */ + #define RF_KILL_INDICATOR_FOR_WOWLAN 0x87 enum iwl_wowlan_rekey_status { @@ -604,12 +648,13 @@ struct iwl_wowlan_status_v7 { } __packed; /* WOWLAN_STATUSES_API_S_VER_7 */ /** - * struct iwl_wowlan_status_v9 - WoWLAN status (version 9) + * struct iwl_wowlan_status_v9 - WoWLAN status (versions 9 and 10) * @gtk: GTK data * @igtk: IGTK data * @replay_ctr: GTK rekey replay counter * @pattern_number: number of the matched pattern - * @non_qos_seq_ctr: non-QoS sequence counter to use next + * @non_qos_seq_ctr: non-QoS sequence counter to use next. + * Reserved if the struct has version >= 10. * @qos_seq_ctr: QoS sequence counters to use next * @wakeup_reasons: wakeup reasons, see &enum iwl_wowlan_wakeup_reason * @num_of_gtk_rekeys: number of GTK rekeys @@ -638,7 +683,7 @@ struct iwl_wowlan_status_v9 { u8 tid_tear_down; u8 reserved[3]; u8 wake_packet[]; /* can be truncated from _length to _bufsize */ -} __packed; /* WOWLAN_STATUSES_API_S_VER_9 */ +} __packed; /* WOWLAN_STATUSES_RSP_API_S_VER_9 */ /** * struct iwl_wowlan_status - WoWLAN status @@ -683,55 +728,6 @@ static inline u8 iwlmvm_wowlan_gtk_idx(struct iwl_wowlan_gtk_status *gtk) return gtk->key_flags & IWL_WOWLAN_GTK_IDX_MASK; } -#define IWL_WOWLAN_TCP_MAX_PACKET_LEN 64 -#define IWL_WOWLAN_REMOTE_WAKE_MAX_PACKET_LEN 128 -#define IWL_WOWLAN_REMOTE_WAKE_MAX_TOKENS 2048 - -struct iwl_tcp_packet_info { - __le16 tcp_pseudo_header_checksum; - __le16 tcp_payload_length; -} __packed; /* TCP_PACKET_INFO_API_S_VER_2 */ - -struct iwl_tcp_packet { - struct iwl_tcp_packet_info info; - u8 rx_mask[IWL_WOWLAN_MAX_PATTERN_LEN / 8]; - u8 data[IWL_WOWLAN_TCP_MAX_PACKET_LEN]; -} __packed; /* TCP_PROTOCOL_PACKET_API_S_VER_1 */ - -struct iwl_remote_wake_packet { - struct iwl_tcp_packet_info info; - u8 rx_mask[IWL_WOWLAN_MAX_PATTERN_LEN / 8]; - u8 data[IWL_WOWLAN_REMOTE_WAKE_MAX_PACKET_LEN]; -} __packed; /* TCP_PROTOCOL_PACKET_API_S_VER_1 */ - -struct iwl_wowlan_remote_wake_config { - __le32 connection_max_time; /* unused */ - /* TCP_PROTOCOL_CONFIG_API_S_VER_1 */ - u8 max_syn_retries; - u8 max_data_retries; - u8 tcp_syn_ack_timeout; - u8 tcp_ack_timeout; - - struct iwl_tcp_packet syn_tx; - struct iwl_tcp_packet synack_rx; - struct iwl_tcp_packet keepalive_ack_rx; - struct iwl_tcp_packet fin_tx; - - struct iwl_remote_wake_packet keepalive_tx; - struct iwl_remote_wake_packet wake_rx; - - /* REMOTE_WAKE_OFFSET_INFO_API_S_VER_1 */ - u8 sequence_number_offset; - u8 sequence_number_length; - u8 token_offset; - u8 token_length; - /* REMOTE_WAKE_PROTOCOL_PARAMS_API_S_VER_1 */ - __le32 initial_sequence_number; - __le16 keepalive_interval; - __le16 num_tokens; - u8 tokens[IWL_WOWLAN_REMOTE_WAKE_MAX_TOKENS]; -} __packed; /* REMOTE_WAKE_CONFIG_API_S_VER_2 */ - /* TODO: NetDetect API */ #endif /* __iwl_fw_api_d3_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h index d299bba3aa54..985b0dc5b52a 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h @@ -63,6 +63,12 @@ enum iwl_data_path_subcmd_ids { */ RX_NO_DATA_NOTIF = 0xF5, + /** + * @THERMAL_DUAL_CHAIN_DISABLE_REQ: firmware request for SMPS mode, + * &struct iwl_thermal_dual_chain_request + */ + THERMAL_DUAL_CHAIN_REQUEST = 0xF6, + /** * @TLC_MNG_UPDATE_NOTIF: &struct iwl_tlc_update_notif */ @@ -169,4 +175,24 @@ struct iwl_datapath_monitor_notif { u8 reserved[3]; } __packed; /* MONITOR_NTF_API_S_VER_1 */ +/** + * enum iwl_thermal_dual_chain_req_events - firmware SMPS request event + * @THERMAL_DUAL_CHAIN_REQ_ENABLE: (re-)enable dual-chain operation + * (subject to other constraints) + * @THERMAL_DUAL_CHAIN_REQ_DISABLE: disable dual-chain operation + * (static SMPS) + */ +enum iwl_thermal_dual_chain_req_events { + THERMAL_DUAL_CHAIN_REQ_ENABLE, + THERMAL_DUAL_CHAIN_REQ_DISABLE, +}; /* THERMAL_DUAL_CHAIN_DISABLE_STATE_API_E_VER_1 */ + +/** + * struct iwl_thermal_dual_chain_request - SMPS request + * @event: the type of request, see &enum iwl_thermal_dual_chain_req_events + */ +struct iwl_thermal_dual_chain_request { + __le32 event; +} __packed; /* THERMAL_DUAL_CHAIN_DISABLE_REQ_NTFY_API_S_VER_1 */ + #endif /* __iwl_fw_api_datapath_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h index 996d5cc5bd9a..5a2d9a1f7e73 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #ifndef __iwl_fw_dbg_tlv_h__ #define __iwl_fw_dbg_tlv_h__ @@ -11,6 +11,7 @@ #define IWL_FW_INI_MAX_NAME 32 #define IWL_FW_INI_MAX_CFG_NAME 64 #define IWL_FW_INI_DOMAIN_ALWAYS_ON 0 +#define IWL_FW_INI_REGION_V2_MASK 0x0000FFFF /** * struct iwl_fw_ini_hcmd diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h index dc8f2777e944..cf48c6fa8f65 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h @@ -452,6 +452,25 @@ struct iwl_lari_config_change_cmd_v3 { __le32 oem_11ax_allow_bitmap; } __packed; /* LARI_CHANGE_CONF_CMD_S_VER_3 */ +/** + * struct iwl_lari_config_change_cmd_v4 - change LARI configuration + * @config_bitmap: Bitmap of the config commands. Each bit will trigger a + * different predefined FW config operation. + * @oem_uhb_allow_bitmap: Bitmap of UHB enabled MCC sets. + * @oem_11ax_allow_bitmap: Bitmap of 11ax allowed MCCs. There are two bits + * per country, one to indicate whether to override and the other to + * indicate the value to use. + * @oem_unii4_allow_bitmap: Bitmap of unii4 allowed MCCs.There are two bits + * per country, one to indicate whether to override and the other to + * indicate allow/disallow unii4 channels. + */ +struct iwl_lari_config_change_cmd_v4 { + __le32 config_bitmap; + __le32 oem_uhb_allow_bitmap; + __le32 oem_11ax_allow_bitmap; + __le32 oem_unii4_allow_bitmap; +} __packed; /* LARI_CHANGE_CONF_CMD_S_VER_4 */ + /** * struct iwl_pnvm_init_complete_ntfy - PNVM initialization complete * @status: PNVM image loading status diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index cc4e18ca9566..df7c55e06f54 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -1933,6 +1933,13 @@ static u32 iwl_dump_ini_mem(struct iwl_fw_runtime *fwrt, struct list_head *list, u32 num_of_ranges, i, size; void *range; + /* + * The higher part of the ID in version 2 is irrelevant for + * us, so mask it out. + */ + if (le32_to_cpu(reg->hdr.version) == 2) + id &= IWL_FW_INI_REGION_V2_MASK; + if (!ops->get_num_of_ranges || !ops->get_size || !ops->fill_mem_hdr || !ops->fill_range) return 0; @@ -1957,7 +1964,7 @@ static u32 iwl_dump_ini_mem(struct iwl_fw_runtime *fwrt, struct list_head *list, num_of_ranges = ops->get_num_of_ranges(fwrt, reg_data); header = (void *)tlv->data; - header->region_id = reg->id; + header->region_id = cpu_to_le32(id); header->num_of_ranges = cpu_to_le32(num_of_ranges); header->name_len = cpu_to_le32(IWL_FW_INI_MAX_NAME); memcpy(header->name, reg->name, IWL_FW_INI_MAX_NAME); @@ -2752,44 +2759,6 @@ void iwl_fw_dbg_stop_sync(struct iwl_fw_runtime *fwrt) } IWL_EXPORT_SYMBOL(iwl_fw_dbg_stop_sync); -#define FSEQ_REG(x) { .addr = (x), .str = #x, } - -void iwl_fw_error_print_fseq_regs(struct iwl_fw_runtime *fwrt) -{ - struct iwl_trans *trans = fwrt->trans; - int i; - struct { - u32 addr; - const char *str; - } fseq_regs[] = { - FSEQ_REG(FSEQ_ERROR_CODE), - FSEQ_REG(FSEQ_TOP_INIT_VERSION), - FSEQ_REG(FSEQ_CNVIO_INIT_VERSION), - FSEQ_REG(FSEQ_OTP_VERSION), - FSEQ_REG(FSEQ_TOP_CONTENT_VERSION), - FSEQ_REG(FSEQ_ALIVE_TOKEN), - FSEQ_REG(FSEQ_CNVI_ID), - FSEQ_REG(FSEQ_CNVR_ID), - FSEQ_REG(CNVI_AUX_MISC_CHIP), - FSEQ_REG(CNVR_AUX_MISC_CHIP), - FSEQ_REG(CNVR_SCU_SD_REGS_SD_REG_DIG_DCDC_VTRIM), - FSEQ_REG(CNVR_SCU_SD_REGS_SD_REG_ACTIVE_VDIG_MIRROR), - }; - - if (!iwl_trans_grab_nic_access(trans)) - return; - - IWL_ERR(fwrt, "Fseq Registers:\n"); - - for (i = 0; i < ARRAY_SIZE(fseq_regs); i++) - IWL_ERR(fwrt, "0x%08X | %s\n", - iwl_read_prph_no_grab(trans, fseq_regs[i].addr), - fseq_regs[i].str); - - iwl_trans_release_nic_access(trans); -} -IWL_EXPORT_SYMBOL(iwl_fw_error_print_fseq_regs); - static int iwl_fw_dbg_suspend_resume_hcmd(struct iwl_trans *trans, bool suspend) { struct iwl_dbg_suspend_resume_cmd cmd = { diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h index 49fa2f5f8c7e..c0e84ef84f5d 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2005-2014, 2018-2019 Intel Corporation + * Copyright (C) 2005-2014, 2018-2019, 2021 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH */ @@ -321,4 +321,6 @@ static inline void iwl_fwrt_update_fw_versions(struct iwl_fw_runtime *fwrt, fwrt->dump.fw_ver.umac_minor = le32_to_cpu(umac->umac_minor); } } + +void iwl_fwrt_dump_error_logs(struct iwl_fw_runtime *fwrt); #endif /* __iwl_fw_dbg_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dump.c b/drivers/net/wireless/intel/iwlwifi/fw/dump.c new file mode 100644 index 000000000000..a1842205e86a --- /dev/null +++ b/drivers/net/wireless/intel/iwlwifi/fw/dump.c @@ -0,0 +1,418 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Copyright (C) 2012-2014, 2018-2021 Intel Corporation + * Copyright (C) 2013-2014 Intel Mobile Communications GmbH + * Copyright (C) 2015-2017 Intel Deutschland GmbH + */ +#include +#include "iwl-drv.h" +#include "runtime.h" +#include "dbg.h" +#include "debugfs.h" +#include "iwl-io.h" +#include "iwl-prph.h" +#include "iwl-csr.h" + +/* + * Note: This structure is read from the device with IO accesses, + * and the reading already does the endian conversion. As it is + * read with u32-sized accesses, any members with a different size + * need to be ordered correctly though! + */ +struct iwl_error_event_table_v1 { + u32 valid; /* (nonzero) valid, (0) log is empty */ + u32 error_id; /* type of error */ + u32 pc; /* program counter */ + u32 blink1; /* branch link */ + u32 blink2; /* branch link */ + u32 ilink1; /* interrupt link */ + u32 ilink2; /* interrupt link */ + u32 data1; /* error-specific data */ + u32 data2; /* error-specific data */ + u32 data3; /* error-specific data */ + u32 bcon_time; /* beacon timer */ + u32 tsf_low; /* network timestamp function timer */ + u32 tsf_hi; /* network timestamp function timer */ + u32 gp1; /* GP1 timer register */ + u32 gp2; /* GP2 timer register */ + u32 gp3; /* GP3 timer register */ + u32 ucode_ver; /* uCode version */ + u32 hw_ver; /* HW Silicon version */ + u32 brd_ver; /* HW board version */ + u32 log_pc; /* log program counter */ + u32 frame_ptr; /* frame pointer */ + u32 stack_ptr; /* stack pointer */ + u32 hcmd; /* last host command header */ + u32 isr0; /* isr status register LMPM_NIC_ISR0: + * rxtx_flag */ + u32 isr1; /* isr status register LMPM_NIC_ISR1: + * host_flag */ + u32 isr2; /* isr status register LMPM_NIC_ISR2: + * enc_flag */ + u32 isr3; /* isr status register LMPM_NIC_ISR3: + * time_flag */ + u32 isr4; /* isr status register LMPM_NIC_ISR4: + * wico interrupt */ + u32 isr_pref; /* isr status register LMPM_NIC_PREF_STAT */ + u32 wait_event; /* wait event() caller address */ + u32 l2p_control; /* L2pControlField */ + u32 l2p_duration; /* L2pDurationField */ + u32 l2p_mhvalid; /* L2pMhValidBits */ + u32 l2p_addr_match; /* L2pAddrMatchStat */ + u32 lmpm_pmg_sel; /* indicate which clocks are turned on + * (LMPM_PMG_SEL) */ + u32 u_timestamp; /* indicate when the date and time of the + * compilation */ + u32 flow_handler; /* FH read/write pointers, RX credit */ +} __packed /* LOG_ERROR_TABLE_API_S_VER_1 */; + +struct iwl_error_event_table { + u32 valid; /* (nonzero) valid, (0) log is empty */ + u32 error_id; /* type of error */ + u32 trm_hw_status0; /* TRM HW status */ + u32 trm_hw_status1; /* TRM HW status */ + u32 blink2; /* branch link */ + u32 ilink1; /* interrupt link */ + u32 ilink2; /* interrupt link */ + u32 data1; /* error-specific data */ + u32 data2; /* error-specific data */ + u32 data3; /* error-specific data */ + u32 bcon_time; /* beacon timer */ + u32 tsf_low; /* network timestamp function timer */ + u32 tsf_hi; /* network timestamp function timer */ + u32 gp1; /* GP1 timer register */ + u32 gp2; /* GP2 timer register */ + u32 fw_rev_type; /* firmware revision type */ + u32 major; /* uCode version major */ + u32 minor; /* uCode version minor */ + u32 hw_ver; /* HW Silicon version */ + u32 brd_ver; /* HW board version */ + u32 log_pc; /* log program counter */ + u32 frame_ptr; /* frame pointer */ + u32 stack_ptr; /* stack pointer */ + u32 hcmd; /* last host command header */ + u32 isr0; /* isr status register LMPM_NIC_ISR0: + * rxtx_flag */ + u32 isr1; /* isr status register LMPM_NIC_ISR1: + * host_flag */ + u32 isr2; /* isr status register LMPM_NIC_ISR2: + * enc_flag */ + u32 isr3; /* isr status register LMPM_NIC_ISR3: + * time_flag */ + u32 isr4; /* isr status register LMPM_NIC_ISR4: + * wico interrupt */ + u32 last_cmd_id; /* last HCMD id handled by the firmware */ + u32 wait_event; /* wait event() caller address */ + u32 l2p_control; /* L2pControlField */ + u32 l2p_duration; /* L2pDurationField */ + u32 l2p_mhvalid; /* L2pMhValidBits */ + u32 l2p_addr_match; /* L2pAddrMatchStat */ + u32 lmpm_pmg_sel; /* indicate which clocks are turned on + * (LMPM_PMG_SEL) */ + u32 u_timestamp; /* indicate when the date and time of the + * compilation */ + u32 flow_handler; /* FH read/write pointers, RX credit */ +} __packed /* LOG_ERROR_TABLE_API_S_VER_3 */; + +/* + * UMAC error struct - relevant starting from family 8000 chip. + * Note: This structure is read from the device with IO accesses, + * and the reading already does the endian conversion. As it is + * read with u32-sized accesses, any members with a different size + * need to be ordered correctly though! + */ +struct iwl_umac_error_event_table { + u32 valid; /* (nonzero) valid, (0) log is empty */ + u32 error_id; /* type of error */ + u32 blink1; /* branch link */ + u32 blink2; /* branch link */ + u32 ilink1; /* interrupt link */ + u32 ilink2; /* interrupt link */ + u32 data1; /* error-specific data */ + u32 data2; /* error-specific data */ + u32 data3; /* error-specific data */ + u32 umac_major; + u32 umac_minor; + u32 frame_pointer; /* core register 27*/ + u32 stack_pointer; /* core register 28 */ + u32 cmd_header; /* latest host cmd sent to UMAC */ + u32 nic_isr_pref; /* ISR status register */ +} __packed; + +#define ERROR_START_OFFSET (1 * sizeof(u32)) +#define ERROR_ELEM_SIZE (7 * sizeof(u32)) + +static void iwl_fwrt_dump_umac_error_log(struct iwl_fw_runtime *fwrt) +{ + struct iwl_trans *trans = fwrt->trans; + struct iwl_umac_error_event_table table = {}; + u32 base = fwrt->trans->dbg.umac_error_event_table; + + if (!base && + !(fwrt->trans->dbg.error_event_table_tlv_status & + IWL_ERROR_EVENT_TABLE_UMAC)) + return; + + iwl_trans_read_mem_bytes(trans, base, &table, sizeof(table)); + + if (table.valid) + fwrt->dump.umac_err_id = table.error_id; + + if (ERROR_START_OFFSET <= table.valid * ERROR_ELEM_SIZE) { + IWL_ERR(trans, "Start IWL Error Log Dump:\n"); + IWL_ERR(trans, "Transport status: 0x%08lX, valid: %d\n", + fwrt->trans->status, table.valid); + } + + IWL_ERR(fwrt, "0x%08X | %s\n", table.error_id, + iwl_fw_lookup_assert_desc(table.error_id)); + IWL_ERR(fwrt, "0x%08X | umac branchlink1\n", table.blink1); + IWL_ERR(fwrt, "0x%08X | umac branchlink2\n", table.blink2); + IWL_ERR(fwrt, "0x%08X | umac interruptlink1\n", table.ilink1); + IWL_ERR(fwrt, "0x%08X | umac interruptlink2\n", table.ilink2); + IWL_ERR(fwrt, "0x%08X | umac data1\n", table.data1); + IWL_ERR(fwrt, "0x%08X | umac data2\n", table.data2); + IWL_ERR(fwrt, "0x%08X | umac data3\n", table.data3); + IWL_ERR(fwrt, "0x%08X | umac major\n", table.umac_major); + IWL_ERR(fwrt, "0x%08X | umac minor\n", table.umac_minor); + IWL_ERR(fwrt, "0x%08X | frame pointer\n", table.frame_pointer); + IWL_ERR(fwrt, "0x%08X | stack pointer\n", table.stack_pointer); + IWL_ERR(fwrt, "0x%08X | last host cmd\n", table.cmd_header); + IWL_ERR(fwrt, "0x%08X | isr status reg\n", table.nic_isr_pref); +} + +static void iwl_fwrt_dump_lmac_error_log(struct iwl_fw_runtime *fwrt, u8 lmac_num) +{ + struct iwl_trans *trans = fwrt->trans; + struct iwl_error_event_table table = {}; + u32 val, base = fwrt->trans->dbg.lmac_error_event_table[lmac_num]; + + if (fwrt->cur_fw_img == IWL_UCODE_INIT) { + if (!base) + base = fwrt->fw->init_errlog_ptr; + } else { + if (!base) + base = fwrt->fw->inst_errlog_ptr; + } + + if (base < 0x400000) { + IWL_ERR(fwrt, + "Not valid error log pointer 0x%08X for %s uCode\n", + base, + (fwrt->cur_fw_img == IWL_UCODE_INIT) + ? "Init" : "RT"); + return; + } + + /* check if there is a HW error */ + val = iwl_trans_read_mem32(trans, base); + if (((val & ~0xf) == 0xa5a5a5a0) || ((val & ~0xf) == 0x5a5a5a50)) { + int err; + + IWL_ERR(trans, "HW error, resetting before reading\n"); + + /* reset the device */ + iwl_trans_sw_reset(trans); + + err = iwl_finish_nic_init(trans, trans->trans_cfg); + if (err) + return; + } + + iwl_trans_read_mem_bytes(trans, base, &table, sizeof(table)); + + if (table.valid) + fwrt->dump.lmac_err_id[lmac_num] = table.error_id; + + if (ERROR_START_OFFSET <= table.valid * ERROR_ELEM_SIZE) { + IWL_ERR(trans, "Start IWL Error Log Dump:\n"); + IWL_ERR(trans, "Transport status: 0x%08lX, valid: %d\n", + fwrt->trans->status, table.valid); + } + + /* Do not change this output - scripts rely on it */ + + IWL_ERR(fwrt, "Loaded firmware version: %s\n", fwrt->fw->fw_version); + + IWL_ERR(fwrt, "0x%08X | %-28s\n", table.error_id, + iwl_fw_lookup_assert_desc(table.error_id)); + IWL_ERR(fwrt, "0x%08X | trm_hw_status0\n", table.trm_hw_status0); + IWL_ERR(fwrt, "0x%08X | trm_hw_status1\n", table.trm_hw_status1); + IWL_ERR(fwrt, "0x%08X | branchlink2\n", table.blink2); + IWL_ERR(fwrt, "0x%08X | interruptlink1\n", table.ilink1); + IWL_ERR(fwrt, "0x%08X | interruptlink2\n", table.ilink2); + IWL_ERR(fwrt, "0x%08X | data1\n", table.data1); + IWL_ERR(fwrt, "0x%08X | data2\n", table.data2); + IWL_ERR(fwrt, "0x%08X | data3\n", table.data3); + IWL_ERR(fwrt, "0x%08X | beacon time\n", table.bcon_time); + IWL_ERR(fwrt, "0x%08X | tsf low\n", table.tsf_low); + IWL_ERR(fwrt, "0x%08X | tsf hi\n", table.tsf_hi); + IWL_ERR(fwrt, "0x%08X | time gp1\n", table.gp1); + IWL_ERR(fwrt, "0x%08X | time gp2\n", table.gp2); + IWL_ERR(fwrt, "0x%08X | uCode revision type\n", table.fw_rev_type); + IWL_ERR(fwrt, "0x%08X | uCode version major\n", table.major); + IWL_ERR(fwrt, "0x%08X | uCode version minor\n", table.minor); + IWL_ERR(fwrt, "0x%08X | hw version\n", table.hw_ver); + IWL_ERR(fwrt, "0x%08X | board version\n", table.brd_ver); + IWL_ERR(fwrt, "0x%08X | hcmd\n", table.hcmd); + IWL_ERR(fwrt, "0x%08X | isr0\n", table.isr0); + IWL_ERR(fwrt, "0x%08X | isr1\n", table.isr1); + IWL_ERR(fwrt, "0x%08X | isr2\n", table.isr2); + IWL_ERR(fwrt, "0x%08X | isr3\n", table.isr3); + IWL_ERR(fwrt, "0x%08X | isr4\n", table.isr4); + IWL_ERR(fwrt, "0x%08X | last cmd Id\n", table.last_cmd_id); + IWL_ERR(fwrt, "0x%08X | wait_event\n", table.wait_event); + IWL_ERR(fwrt, "0x%08X | l2p_control\n", table.l2p_control); + IWL_ERR(fwrt, "0x%08X | l2p_duration\n", table.l2p_duration); + IWL_ERR(fwrt, "0x%08X | l2p_mhvalid\n", table.l2p_mhvalid); + IWL_ERR(fwrt, "0x%08X | l2p_addr_match\n", table.l2p_addr_match); + IWL_ERR(fwrt, "0x%08X | lmpm_pmg_sel\n", table.lmpm_pmg_sel); + IWL_ERR(fwrt, "0x%08X | timestamp\n", table.u_timestamp); + IWL_ERR(fwrt, "0x%08X | flow_handler\n", table.flow_handler); +} + +/* + * TCM error struct. + * Note: This structure is read from the device with IO accesses, + * and the reading already does the endian conversion. As it is + * read with u32-sized accesses, any members with a different size + * need to be ordered correctly though! + */ +struct iwl_tcm_error_event_table { + u32 valid; + u32 error_id; + u32 blink2; + u32 ilink1; + u32 ilink2; + u32 data1, data2, data3; + u32 logpc; + u32 frame_pointer; + u32 stack_pointer; + u32 msgid; + u32 isr; + u32 hw_status[5]; + u32 sw_status[1]; + u32 reserved[4]; +} __packed; /* TCM_LOG_ERROR_TABLE_API_S_VER_1 */ + +static void iwl_fwrt_dump_tcm_error_log(struct iwl_fw_runtime *fwrt) +{ + struct iwl_trans *trans = fwrt->trans; + struct iwl_tcm_error_event_table table = {}; + u32 base = fwrt->trans->dbg.tcm_error_event_table; + int i; + + if (!base || + !(fwrt->trans->dbg.error_event_table_tlv_status & + IWL_ERROR_EVENT_TABLE_TCM)) + return; + + iwl_trans_read_mem_bytes(trans, base, &table, sizeof(table)); + + IWL_ERR(fwrt, "TCM status:\n"); + IWL_ERR(fwrt, "0x%08X | error ID\n", table.error_id); + IWL_ERR(fwrt, "0x%08X | tcm branchlink2\n", table.blink2); + IWL_ERR(fwrt, "0x%08X | tcm interruptlink1\n", table.ilink1); + IWL_ERR(fwrt, "0x%08X | tcm interruptlink2\n", table.ilink2); + IWL_ERR(fwrt, "0x%08X | tcm data1\n", table.data1); + IWL_ERR(fwrt, "0x%08X | tcm data2\n", table.data2); + IWL_ERR(fwrt, "0x%08X | tcm data3\n", table.data3); + IWL_ERR(fwrt, "0x%08X | tcm log PC\n", table.logpc); + IWL_ERR(fwrt, "0x%08X | tcm frame pointer\n", table.frame_pointer); + IWL_ERR(fwrt, "0x%08X | tcm stack pointer\n", table.stack_pointer); + IWL_ERR(fwrt, "0x%08X | tcm msg ID\n", table.msgid); + IWL_ERR(fwrt, "0x%08X | tcm ISR status\n", table.isr); + for (i = 0; i < ARRAY_SIZE(table.hw_status); i++) + IWL_ERR(fwrt, "0x%08X | tcm HW status[%d]\n", + table.hw_status[i], i); + for (i = 0; i < ARRAY_SIZE(table.sw_status); i++) + IWL_ERR(fwrt, "0x%08X | tcm SW status[%d]\n", + table.sw_status[i], i); +} + +static void iwl_fwrt_dump_iml_error_log(struct iwl_fw_runtime *fwrt) +{ + struct iwl_trans *trans = fwrt->trans; + u32 error, data1; + + if (fwrt->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000) { + error = UMAG_SB_CPU_2_STATUS; + data1 = UMAG_SB_CPU_1_STATUS; + } else if (fwrt->trans->trans_cfg->device_family >= + IWL_DEVICE_FAMILY_8000) { + error = SB_CPU_2_STATUS; + data1 = SB_CPU_1_STATUS; + } else { + return; + } + + error = iwl_read_umac_prph(trans, UMAG_SB_CPU_2_STATUS); + + IWL_ERR(trans, "IML/ROM dump:\n"); + + if (error & 0xFFFF0000) + IWL_ERR(trans, "0x%04X | IML/ROM SYSASSERT\n", error >> 16); + + IWL_ERR(fwrt, "0x%08X | IML/ROM error/state\n", error); + IWL_ERR(fwrt, "0x%08X | IML/ROM data1\n", + iwl_read_umac_prph(trans, data1)); + + if (fwrt->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000) + IWL_ERR(fwrt, "0x%08X | IML/ROM WFPM_AUTH_KEY_0\n", + iwl_read_umac_prph(trans, SB_MODIFY_CFG_FLAG)); +} + +#define FSEQ_REG(x) { .addr = (x), .str = #x, } + +static void iwl_fwrt_dump_fseq_regs(struct iwl_fw_runtime *fwrt) +{ + struct iwl_trans *trans = fwrt->trans; + int i; + struct { + u32 addr; + const char *str; + } fseq_regs[] = { + FSEQ_REG(FSEQ_ERROR_CODE), + FSEQ_REG(FSEQ_TOP_INIT_VERSION), + FSEQ_REG(FSEQ_CNVIO_INIT_VERSION), + FSEQ_REG(FSEQ_OTP_VERSION), + FSEQ_REG(FSEQ_TOP_CONTENT_VERSION), + FSEQ_REG(FSEQ_ALIVE_TOKEN), + FSEQ_REG(FSEQ_CNVI_ID), + FSEQ_REG(FSEQ_CNVR_ID), + FSEQ_REG(CNVI_AUX_MISC_CHIP), + FSEQ_REG(CNVR_AUX_MISC_CHIP), + FSEQ_REG(CNVR_SCU_SD_REGS_SD_REG_DIG_DCDC_VTRIM), + FSEQ_REG(CNVR_SCU_SD_REGS_SD_REG_ACTIVE_VDIG_MIRROR), + }; + + if (!iwl_trans_grab_nic_access(trans)) + return; + + IWL_ERR(fwrt, "Fseq Registers:\n"); + + for (i = 0; i < ARRAY_SIZE(fseq_regs); i++) + IWL_ERR(fwrt, "0x%08X | %s\n", + iwl_read_prph_no_grab(trans, fseq_regs[i].addr), + fseq_regs[i].str); + + iwl_trans_release_nic_access(trans); +} + +void iwl_fwrt_dump_error_logs(struct iwl_fw_runtime *fwrt) +{ + if (!test_bit(STATUS_DEVICE_ENABLED, &fwrt->trans->status)) { + IWL_ERR(fwrt, + "DEVICE_ENABLED bit is not set. Aborting dump.\n"); + return; + } + + iwl_fwrt_dump_lmac_error_log(fwrt, 0); + if (fwrt->trans->dbg.lmac_error_event_table[1]) + iwl_fwrt_dump_lmac_error_log(fwrt, 1); + iwl_fwrt_dump_umac_error_log(fwrt); + iwl_fwrt_dump_tcm_error_log(fwrt); + iwl_fwrt_dump_iml_error_log(fwrt); + iwl_fwrt_dump_fseq_regs(fwrt); +} +IWL_EXPORT_SYMBOL(iwl_fwrt_dump_error_logs); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h index f9c5cf538ad1..9a8c7b7a0816 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/file.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2008-2014, 2018-2020 Intel Corporation + * Copyright (C) 2008-2014, 2018-2021 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -52,7 +52,8 @@ enum iwl_ucode_tlv_type { IWL_UCODE_TLV_INIT_DATA = 4, IWL_UCODE_TLV_BOOT = 5, IWL_UCODE_TLV_PROBE_MAX_LEN = 6, /* a u32 value */ - IWL_UCODE_TLV_PAN = 7, + IWL_UCODE_TLV_PAN = 7, /* deprecated -- only used in DVM */ + IWL_UCODE_TLV_MEM_DESC = 7, /* replaces PAN in non-DVM */ IWL_UCODE_TLV_RUNT_EVTLOG_PTR = 8, IWL_UCODE_TLV_RUNT_EVTLOG_SIZE = 9, IWL_UCODE_TLV_RUNT_ERRLOG_PTR = 10, @@ -97,6 +98,7 @@ enum iwl_ucode_tlv_type { IWL_UCODE_TLV_PNVM_VERSION = 62, IWL_UCODE_TLV_PNVM_SKU = 64, + IWL_UCODE_TLV_TCM_DEBUG_ADDRS = 65, IWL_UCODE_TLV_FW_NUM_STATIONS = IWL_UCODE_TLV_CONST_BASE + 0, @@ -277,10 +279,11 @@ enum iwl_ucode_tlv_api { IWL_UCODE_TLV_API_BAND_IN_RX_DATA = (__force iwl_ucode_tlv_api_t)59, - NUM_IWL_UCODE_TLV_API #ifdef __CHECKER__ - /* sparse says it cannot increment the previous enum member */ - = 128 + /* sparse says it cannot increment the previous enum member */ +#define NUM_IWL_UCODE_TLV_API 128 +#else + NUM_IWL_UCODE_TLV_API #endif }; @@ -411,6 +414,7 @@ enum iwl_ucode_tlv_capa { IWL_UCODE_TLV_CAPA_PROTECTED_TWT = (__force iwl_ucode_tlv_capa_t)56, IWL_UCODE_TLV_CAPA_FW_RESET_HANDSHAKE = (__force iwl_ucode_tlv_capa_t)57, IWL_UCODE_TLV_CAPA_PASSIVE_6GHZ_SCAN = (__force iwl_ucode_tlv_capa_t)58, + IWL_UCODE_TLV_CAPA_BROADCAST_TWT = (__force iwl_ucode_tlv_capa_t)60, /* set 2 */ IWL_UCODE_TLV_CAPA_EXTENDED_DTS_MEASURE = (__force iwl_ucode_tlv_capa_t)64, @@ -446,10 +450,11 @@ enum iwl_ucode_tlv_capa { IWL_UCODE_TLV_CAPA_BIGTK_SUPPORT = (__force iwl_ucode_tlv_capa_t)100, IWL_UCODE_TLV_CAPA_RFIM_SUPPORT = (__force iwl_ucode_tlv_capa_t)102, - NUM_IWL_UCODE_TLV_CAPA #ifdef __CHECKER__ - /* sparse says it cannot increment the previous enum member */ - = 128 + /* sparse says it cannot increment the previous enum member */ +#define NUM_IWL_UCODE_TLV_CAPA 128 +#else + NUM_IWL_UCODE_TLV_CAPA #endif }; @@ -946,6 +951,10 @@ struct iwl_fw_cmd_version { u8 notif_ver; } __packed; +struct iwl_fw_tcm_error_addr { + __le32 addr; +}; /* FW_TLV_TCM_ERROR_INFO_ADDRS_S */ + static inline size_t _iwl_tlv_array_len(const struct iwl_ucode_tlv *tlv, size_t fixed_size, size_t var_size) { diff --git a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c index 40f2109a097f..2403490cbc26 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.c @@ -10,7 +10,7 @@ #include "fw/api/commands.h" #include "fw/api/nvm-reg.h" #include "fw/api/alive.h" -#include +#include "fw/uefi.h" struct iwl_pnvm_section { __le32 offset; @@ -220,83 +220,6 @@ static int iwl_pnvm_parse(struct iwl_trans *trans, const u8 *data, return -ENOENT; } -#if defined(CONFIG_EFI) - -#define IWL_EFI_VAR_GUID EFI_GUID(0x92daaf2f, 0xc02b, 0x455b, \ - 0xb2, 0xec, 0xf5, 0xa3, \ - 0x59, 0x4f, 0x4a, 0xea) - -#define IWL_UEFI_OEM_PNVM_NAME L"UefiCnvWlanOemSignedPnvm" - -#define IWL_HARDCODED_PNVM_SIZE 4096 - -struct pnvm_sku_package { - u8 rev; - u8 reserved1[3]; - u32 total_size; - u8 n_skus; - u8 reserved2[11]; - u8 data[]; -}; - -static int iwl_pnvm_get_from_efi(struct iwl_trans *trans, - u8 **data, size_t *len) -{ - struct efivar_entry *pnvm_efivar; - struct pnvm_sku_package *package; - unsigned long package_size; - int err; - - pnvm_efivar = kzalloc(sizeof(*pnvm_efivar), GFP_KERNEL); - if (!pnvm_efivar) - return -ENOMEM; - - memcpy(&pnvm_efivar->var.VariableName, IWL_UEFI_OEM_PNVM_NAME, - sizeof(IWL_UEFI_OEM_PNVM_NAME)); - pnvm_efivar->var.VendorGuid = IWL_EFI_VAR_GUID; - - /* - * TODO: we hardcode a maximum length here, because reading - * from the UEFI is not working. To implement this properly, - * we have to call efivar_entry_size(). - */ - package_size = IWL_HARDCODED_PNVM_SIZE; - - package = kmalloc(package_size, GFP_KERNEL); - if (!package) { - err = -ENOMEM; - goto out; - } - - err = efivar_entry_get(pnvm_efivar, NULL, &package_size, package); - if (err) { - IWL_DEBUG_FW(trans, - "PNVM UEFI variable not found %d (len %lu)\n", - err, package_size); - goto out; - } - - IWL_DEBUG_FW(trans, "Read PNVM fro UEFI with size %lu\n", package_size); - - *data = kmemdup(package->data, *len, GFP_KERNEL); - if (!*data) - err = -ENOMEM; - *len = package_size - sizeof(*package); - -out: - kfree(package); - kfree(pnvm_efivar); - - return err; -} -#else /* CONFIG_EFI */ -static inline int iwl_pnvm_get_from_efi(struct iwl_trans *trans, - u8 **data, size_t *len) -{ - return -EOPNOTSUPP; -} -#endif /* CONFIG_EFI */ - static int iwl_pnvm_get_from_fs(struct iwl_trans *trans, u8 **data, size_t *len) { const struct firmware *pnvm; @@ -335,6 +258,7 @@ int iwl_pnvm_load(struct iwl_trans *trans, { u8 *data; size_t len; + struct pnvm_sku_package *package; struct iwl_notification_wait pnvm_wait; static const u16 ntf_cmds[] = { WIDE_ID(REGULATORY_AND_NVM_GROUP, PNVM_INIT_COMPLETE_NTFY) }; @@ -356,9 +280,19 @@ int iwl_pnvm_load(struct iwl_trans *trans, } /* First attempt to get the PNVM from BIOS */ - ret = iwl_pnvm_get_from_efi(trans, &data, &len); - if (!ret) - goto parse; + package = iwl_uefi_get_pnvm(trans, &len); + if (!IS_ERR_OR_NULL(package)) { + data = kmemdup(package->data, len, GFP_KERNEL); + + /* free package regardless of whether kmemdup succeeded */ + kfree(package); + + if (data) { + /* we need only the data size */ + len -= sizeof(*package); + goto parse; + } + } /* If it's not available, try from the filesystem */ ret = iwl_pnvm_get_from_fs(trans, &data, &len); @@ -379,6 +313,30 @@ parse: kfree(data); skip_parse: + data = NULL; + /* now try to get the reduce power table, if not loaded yet */ + if (!trans->reduce_power_loaded) { + data = iwl_uefi_get_reduced_power(trans, &len); + if (IS_ERR_OR_NULL(data)) { + /* + * Pretend we've loaded it - at least we've tried and + * couldn't load it at all, so there's no point in + * trying again over and over. + */ + trans->reduce_power_loaded = true; + + goto skip_reduce_power; + } + } + + ret = iwl_trans_set_reduce_power(trans, data, len); + if (ret) + IWL_DEBUG_FW(trans, + "Failed to set reduce power table %d\n", + ret); + kfree(data); + +skip_reduce_power: iwl_init_notification_wait(notif_wait, &pnvm_wait, ntf_cmds, ARRAY_SIZE(ntf_cmds), iwl_pnvm_complete_fn, trans); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.h b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.h index e4f91bce222d..61d3d4e0b7d9 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/pnvm.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/pnvm.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /****************************************************************************** * - * Copyright(c) 2020 Intel Corporation + * Copyright(c) 2020-2021 Intel Corporation * *****************************************************************************/ @@ -10,7 +10,7 @@ #include "fw/notif-wait.h" -#define MVM_UCODE_PNVM_TIMEOUT (HZ / 10) +#define MVM_UCODE_PNVM_TIMEOUT (HZ / 4) int iwl_pnvm_load(struct iwl_trans *trans, struct iwl_notif_wait_data *notif_wait); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c new file mode 100644 index 000000000000..a7c79d814aa4 --- /dev/null +++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c @@ -0,0 +1,262 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Copyright(c) 2021 Intel Corporation + */ + +#include "iwl-drv.h" +#include "pnvm.h" +#include "iwl-prph.h" +#include "iwl-io.h" + +#include "fw/uefi.h" +#include "fw/api/alive.h" +#include + +#define IWL_EFI_VAR_GUID EFI_GUID(0x92daaf2f, 0xc02b, 0x455b, \ + 0xb2, 0xec, 0xf5, 0xa3, \ + 0x59, 0x4f, 0x4a, 0xea) + +void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len) +{ + struct efivar_entry *pnvm_efivar; + void *data; + unsigned long package_size; + int err; + + *len = 0; + + pnvm_efivar = kzalloc(sizeof(*pnvm_efivar), GFP_KERNEL); + if (!pnvm_efivar) + return ERR_PTR(-ENOMEM); + + memcpy(&pnvm_efivar->var.VariableName, IWL_UEFI_OEM_PNVM_NAME, + sizeof(IWL_UEFI_OEM_PNVM_NAME)); + pnvm_efivar->var.VendorGuid = IWL_EFI_VAR_GUID; + + /* + * TODO: we hardcode a maximum length here, because reading + * from the UEFI is not working. To implement this properly, + * we have to call efivar_entry_size(). + */ + package_size = IWL_HARDCODED_PNVM_SIZE; + + data = kmalloc(package_size, GFP_KERNEL); + if (!data) { + data = ERR_PTR(-ENOMEM); + goto out; + } + + err = efivar_entry_get(pnvm_efivar, NULL, &package_size, data); + if (err) { + IWL_DEBUG_FW(trans, + "PNVM UEFI variable not found %d (len %zd)\n", + err, package_size); + kfree(data); + data = ERR_PTR(err); + goto out; + } + + IWL_DEBUG_FW(trans, "Read PNVM from UEFI with size %zd\n", package_size); + *len = package_size; + +out: + kfree(pnvm_efivar); + + return data; +} + +static void *iwl_uefi_reduce_power_section(struct iwl_trans *trans, + const u8 *data, size_t len) +{ + struct iwl_ucode_tlv *tlv; + u8 *reduce_power_data = NULL, *tmp; + u32 size = 0; + + IWL_DEBUG_FW(trans, "Handling REDUCE_POWER section\n"); + + while (len >= sizeof(*tlv)) { + u32 tlv_len, tlv_type; + + len -= sizeof(*tlv); + tlv = (void *)data; + + tlv_len = le32_to_cpu(tlv->length); + tlv_type = le32_to_cpu(tlv->type); + + if (len < tlv_len) { + IWL_ERR(trans, "invalid TLV len: %zd/%u\n", + len, tlv_len); + reduce_power_data = ERR_PTR(-EINVAL); + goto out; + } + + data += sizeof(*tlv); + + switch (tlv_type) { + case IWL_UCODE_TLV_MEM_DESC: { + IWL_DEBUG_FW(trans, + "Got IWL_UCODE_TLV_MEM_DESC len %d\n", + tlv_len); + + IWL_DEBUG_FW(trans, "Adding data (size %d)\n", tlv_len); + + tmp = krealloc(reduce_power_data, size + tlv_len, GFP_KERNEL); + if (!tmp) { + IWL_DEBUG_FW(trans, + "Couldn't allocate (more) reduce_power_data\n"); + + reduce_power_data = ERR_PTR(-ENOMEM); + goto out; + } + + reduce_power_data = tmp; + + memcpy(reduce_power_data + size, data, tlv_len); + + size += tlv_len; + + break; + } + case IWL_UCODE_TLV_PNVM_SKU: + IWL_DEBUG_FW(trans, + "New REDUCE_POWER section started, stop parsing.\n"); + goto done; + default: + IWL_DEBUG_FW(trans, "Found TLV 0x%0x, len %d\n", + tlv_type, tlv_len); + break; + } + + len -= ALIGN(tlv_len, 4); + data += ALIGN(tlv_len, 4); + } + +done: + if (!size) { + IWL_DEBUG_FW(trans, "Empty REDUCE_POWER, skipping.\n"); + reduce_power_data = ERR_PTR(-ENOENT); + goto out; + } + + IWL_INFO(trans, "loaded REDUCE_POWER\n"); + +out: + return reduce_power_data; +} + +static void *iwl_uefi_reduce_power_parse(struct iwl_trans *trans, + const u8 *data, size_t len) +{ + struct iwl_ucode_tlv *tlv; + void *sec_data; + + IWL_DEBUG_FW(trans, "Parsing REDUCE_POWER data\n"); + + while (len >= sizeof(*tlv)) { + u32 tlv_len, tlv_type; + + len -= sizeof(*tlv); + tlv = (void *)data; + + tlv_len = le32_to_cpu(tlv->length); + tlv_type = le32_to_cpu(tlv->type); + + if (len < tlv_len) { + IWL_ERR(trans, "invalid TLV len: %zd/%u\n", + len, tlv_len); + return ERR_PTR(-EINVAL); + } + + if (tlv_type == IWL_UCODE_TLV_PNVM_SKU) { + struct iwl_sku_id *sku_id = + (void *)(data + sizeof(*tlv)); + + IWL_DEBUG_FW(trans, + "Got IWL_UCODE_TLV_PNVM_SKU len %d\n", + tlv_len); + IWL_DEBUG_FW(trans, "sku_id 0x%0x 0x%0x 0x%0x\n", + le32_to_cpu(sku_id->data[0]), + le32_to_cpu(sku_id->data[1]), + le32_to_cpu(sku_id->data[2])); + + data += sizeof(*tlv) + ALIGN(tlv_len, 4); + len -= ALIGN(tlv_len, 4); + + if (trans->sku_id[0] == le32_to_cpu(sku_id->data[0]) && + trans->sku_id[1] == le32_to_cpu(sku_id->data[1]) && + trans->sku_id[2] == le32_to_cpu(sku_id->data[2])) { + sec_data = iwl_uefi_reduce_power_section(trans, + data, + len); + if (!IS_ERR(sec_data)) + return sec_data; + } else { + IWL_DEBUG_FW(trans, "SKU ID didn't match!\n"); + } + } else { + data += sizeof(*tlv) + ALIGN(tlv_len, 4); + len -= ALIGN(tlv_len, 4); + } + } + + return ERR_PTR(-ENOENT); +} + +void *iwl_uefi_get_reduced_power(struct iwl_trans *trans, size_t *len) +{ + struct efivar_entry *reduce_power_efivar; + struct pnvm_sku_package *package; + void *data = NULL; + unsigned long package_size; + int err; + + *len = 0; + + reduce_power_efivar = kzalloc(sizeof(*reduce_power_efivar), GFP_KERNEL); + if (!reduce_power_efivar) + return ERR_PTR(-ENOMEM); + + memcpy(&reduce_power_efivar->var.VariableName, IWL_UEFI_REDUCED_POWER_NAME, + sizeof(IWL_UEFI_REDUCED_POWER_NAME)); + reduce_power_efivar->var.VendorGuid = IWL_EFI_VAR_GUID; + + /* + * TODO: we hardcode a maximum length here, because reading + * from the UEFI is not working. To implement this properly, + * we have to call efivar_entry_size(). + */ + package_size = IWL_HARDCODED_REDUCE_POWER_SIZE; + + package = kmalloc(package_size, GFP_KERNEL); + if (!package) { + package = ERR_PTR(-ENOMEM); + goto out; + } + + err = efivar_entry_get(reduce_power_efivar, NULL, &package_size, package); + if (err) { + IWL_DEBUG_FW(trans, + "Reduced Power UEFI variable not found %d (len %lu)\n", + err, package_size); + kfree(package); + data = ERR_PTR(err); + goto out; + } + + IWL_DEBUG_FW(trans, "Read reduced power from UEFI with size %lu\n", + package_size); + *len = package_size; + + IWL_DEBUG_FW(trans, "rev %d, total_size %d, n_skus %d\n", + package->rev, package->total_size, package->n_skus); + + data = iwl_uefi_reduce_power_parse(trans, package->data, + *len - sizeof(*package)); + + kfree(package); + +out: + kfree(reduce_power_efivar); + + return data; +} diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h new file mode 100644 index 000000000000..45d0b36d79b5 --- /dev/null +++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* + * Copyright(c) 2021 Intel Corporation + */ + + +#define IWL_UEFI_OEM_PNVM_NAME L"UefiCnvWlanOemSignedPnvm" +#define IWL_UEFI_REDUCED_POWER_NAME L"UefiCnvWlanReducedPower" + +/* + * TODO: we have these hardcoded values that the caller must pass, + * because reading from the UEFI is not working. To implement this + * properly, we have to change iwl_pnvm_get_from_uefi() to call + * efivar_entry_size() and return the value to the caller instead. + */ +#define IWL_HARDCODED_PNVM_SIZE 4096 +#define IWL_HARDCODED_REDUCE_POWER_SIZE 32768 + +struct pnvm_sku_package { + u8 rev; + u32 total_size; + u8 n_skus; + u32 reserved[2]; + u8 data[]; +} __packed; + +#ifdef CONFIG_EFI +void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len); +void *iwl_uefi_get_reduced_power(struct iwl_trans *trans, size_t *len); +#else /* CONFIG_EFI */ +static inline +void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline +void *iwl_uefi_get_reduced_power(struct iwl_trans *trans, size_t *len) +{ + return ERR_PTR(-EOPNOTSUPP); +} +#endif /* CONFIG_EFI */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index b35ffdfdf14b..bf6ee56d4d96 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -426,6 +426,7 @@ struct iwl_cfg { #define IWL_CFG_RF_TYPE_HR1 0x10C #define IWL_CFG_RF_TYPE_GF 0x10D #define IWL_CFG_RF_TYPE_MR 0x110 +#define IWL_CFG_RF_TYPE_FM 0x112 #define IWL_CFG_RF_ID_TH 0x1 #define IWL_CFG_RF_ID_TH1 0x1 @@ -505,8 +506,11 @@ extern const char iwl_ax201_killer_1650s_name[]; extern const char iwl_ax201_killer_1650i_name[]; extern const char iwl_ax210_killer_1675w_name[]; extern const char iwl_ax210_killer_1675x_name[]; +extern const char iwl9560_killer_1550i_160_name[]; +extern const char iwl9560_killer_1550s_160_name[]; extern const char iwl_ax211_name[]; extern const char iwl_ax221_name[]; +extern const char iwl_ax231_name[]; extern const char iwl_ax411_name[]; #if IS_ENABLED(CONFIG_IWLDVM) extern const struct iwl_cfg iwl5300_agn_cfg; @@ -586,7 +590,6 @@ extern const struct iwl_cfg iwl_qu_b0_hr_b0; extern const struct iwl_cfg iwl_qu_c0_hr_b0; extern const struct iwl_cfg iwl_ax200_cfg_cc; extern const struct iwl_cfg iwl_ax201_cfg_qu_hr; -extern const struct iwl_cfg iwl_ax201_cfg_qu_hr; extern const struct iwl_cfg iwl_ax201_cfg_qu_c0_hr_b0; extern const struct iwl_cfg iwl_ax201_cfg_quz_hr; extern const struct iwl_cfg iwl_ax1650i_cfg_quz_hr; @@ -613,6 +616,7 @@ extern const struct iwl_cfg iwl_cfg_ma_a0_hr_b0; extern const struct iwl_cfg iwl_cfg_ma_a0_gf_a0; extern const struct iwl_cfg iwl_cfg_ma_a0_gf4_a0; extern const struct iwl_cfg iwl_cfg_ma_a0_mr_a0; +extern const struct iwl_cfg iwl_cfg_ma_a0_fm_a0; extern const struct iwl_cfg iwl_cfg_snj_a0_mr_a0; extern const struct iwl_cfg iwl_cfg_so_a0_hr_a0; extern const struct iwl_cfg iwl_cfg_quz_a0_hr_b0; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h index 2be605cc6fbf..e1fec23ac07f 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2018, 2020 Intel Corporation + * Copyright (C) 2018, 2020-2021 Intel Corporation */ #ifndef __iwl_context_info_file_gen3_h__ #define __iwl_context_info_file_gen3_h__ @@ -127,6 +127,17 @@ struct iwl_prph_scratch_rbd_cfg { __le32 reserved; } __packed; /* PERIPH_SCRATCH_RBD_CFG_S */ +/* + * struct iwl_prph_scratch_uefi_cfg - prph scratch reduce power table + * @base_addr: reduce power table address + * @size: table size in dwords + */ +struct iwl_prph_scratch_uefi_cfg { + __le64 base_addr; + __le32 size; + __le32 reserved; +} __packed; /* PERIPH_SCRATCH_UEFI_CFG_S */ + /* * struct iwl_prph_scratch_ctrl_cfg - prph scratch ctrl and config * @version: version information of context info and HW @@ -141,6 +152,7 @@ struct iwl_prph_scratch_ctrl_cfg { struct iwl_prph_scratch_pnvm_cfg pnvm_cfg; struct iwl_prph_scratch_hwm_cfg hwm_cfg; struct iwl_prph_scratch_rbd_cfg rbd_cfg; + struct iwl_prph_scratch_uefi_cfg reduce_power_cfg; } __packed; /* PERIPH_SCRATCH_CTRL_CFG_S */ /* @@ -151,7 +163,7 @@ struct iwl_prph_scratch_ctrl_cfg { */ struct iwl_prph_scratch { struct iwl_prph_scratch_ctrl_cfg ctrl_cfg; - __le32 reserved[16]; + __le32 reserved[12]; struct iwl_context_info_dram dram; } __packed; /* PERIPH_SCRATCH_S */ @@ -245,9 +257,11 @@ struct iwl_context_info_gen3 { int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, const struct fw_img *fw); -void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans); +void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans, bool alive); int iwl_trans_pcie_ctx_info_gen3_set_pnvm(struct iwl_trans *trans, const void *data, u32 len); +int iwl_trans_pcie_ctx_info_gen3_set_reduce_power(struct iwl_trans *trans, + const void *data, u32 len); #endif /* __iwl_context_info_file_gen3_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h index db312abd2e09..47e5a17c0f48 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2005-2014, 2018-2020 Intel Corporation + * Copyright (C) 2005-2014, 2018-2021 Intel Corporation * Copyright (C) 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2016 Intel Deutschland GmbH */ @@ -325,9 +325,6 @@ enum { #define CSR_HW_RF_ID_TYPE_GF (0x0010D000) #define CSR_HW_RF_ID_TYPE_GF4 (0x0010E000) -/* HW_RF CHIP ID */ -#define CSR_HW_RF_ID_TYPE_CHIP_ID(_val) (((_val) >> 12) & 0xFFF) - /* HW_RF CHIP STEP */ #define CSR_HW_RF_STEP(_val) (((_val) >> 8) & 0xF) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c index 4cd8c39cc3e9..0ddd255a8cc1 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c @@ -57,7 +57,7 @@ dbg_ver_table[IWL_DBG_TLV_TYPE_NUM] = { [IWL_DBG_TLV_TYPE_DEBUG_INFO] = {.min_ver = 1, .max_ver = 1,}, [IWL_DBG_TLV_TYPE_BUF_ALLOC] = {.min_ver = 1, .max_ver = 1,}, [IWL_DBG_TLV_TYPE_HCMD] = {.min_ver = 1, .max_ver = 1,}, - [IWL_DBG_TLV_TYPE_REGION] = {.min_ver = 1, .max_ver = 1,}, + [IWL_DBG_TLV_TYPE_REGION] = {.min_ver = 1, .max_ver = 2,}, [IWL_DBG_TLV_TYPE_TRIGGER] = {.min_ver = 1, .max_ver = 1,}, }; @@ -178,9 +178,20 @@ static int iwl_dbg_tlv_alloc_region(struct iwl_trans *trans, u32 type = le32_to_cpu(reg->type); u32 tlv_len = sizeof(*tlv) + le32_to_cpu(tlv->length); + /* + * The higher part of the ID in version 2 is irrelevant for + * us, so mask it out. + */ + if (le32_to_cpu(reg->hdr.version) == 2) + id &= IWL_FW_INI_REGION_V2_MASK; + if (le32_to_cpu(tlv->length) < sizeof(*reg)) return -EINVAL; + /* for safe use of a string from FW, limit it to IWL_FW_INI_MAX_NAME */ + IWL_DEBUG_FW(trans, "WRT: parsing region: %.*s\n", + IWL_FW_INI_MAX_NAME, reg->name); + if (id >= IWL_FW_INI_MAX_REGION_ID) { IWL_ERR(trans, "WRT: Invalid region id %u\n", id); return -EINVAL; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 884750bf7840..977dce686bdb 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1117,6 +1117,17 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, IWL_ERROR_EVENT_TABLE_LMAC1; break; } + case IWL_UCODE_TLV_TCM_DEBUG_ADDRS: { + struct iwl_fw_tcm_error_addr *ptr = (void *)tlv_data; + + if (tlv_len != sizeof(*ptr)) + goto invalid_tlv_len; + drv->trans->dbg.tcm_error_event_table = + le32_to_cpu(ptr->addr) & ~FW_ADDR_CACHE_CONTROL; + drv->trans->dbg.error_event_table_tlv_status |= + IWL_ERROR_EVENT_TABLE_TCM; + break; + } case IWL_UCODE_TLV_TYPE_DEBUG_INFO: case IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION: case IWL_UCODE_TLV_TYPE_HCMD: diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index fc75d049046d..850648ebd61c 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2005-2014, 2018-2020 Intel Corporation + * Copyright (C) 2005-2014, 2018-2021 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -549,8 +549,7 @@ static const struct ieee80211_sband_iftype_data iwl_he_capa[] = { .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP, .mac_cap_info[3] = - IEEE80211_HE_MAC_CAP3_OMI_CONTROL | - IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_2, + IEEE80211_HE_MAC_CAP3_OMI_CONTROL, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU | IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39, @@ -579,25 +578,20 @@ static const struct ieee80211_sband_iftype_data iwl_he_capa[] = { IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE | IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 | IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8, - .phy_cap_info[5] = - IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 | - IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2, .phy_cap_info[6] = IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMING_FB | IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB | IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT, .phy_cap_info[7] = IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_SUPP | - IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI | - IEEE80211_HE_PHY_CAP7_MAX_NC_1, + IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI, .phy_cap_info[8] = IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI | IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G | IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU | IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU | - IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996, + IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242, .phy_cap_info[9] = - IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK | IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB | IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB | IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED, @@ -632,19 +626,11 @@ static const struct ieee80211_sband_iftype_data iwl_he_capa[] = { .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, - .mac_cap_info[2] = - IEEE80211_HE_MAC_CAP2_BSR, .mac_cap_info[3] = - IEEE80211_HE_MAC_CAP3_OMI_CONTROL | - IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_2, - .mac_cap_info[4] = - IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU, - .mac_cap_info[5] = - IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU, + IEEE80211_HE_MAC_CAP3_OMI_CONTROL, .phy_cap_info[0] = IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G | - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G, + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G, .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD, .phy_cap_info[2] = @@ -654,27 +640,14 @@ static const struct ieee80211_sband_iftype_data iwl_he_capa[] = { IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 | IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM | IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1, - .phy_cap_info[4] = - IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE | - IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 | - IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8, - .phy_cap_info[5] = - IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 | - IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2, .phy_cap_info[6] = IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT, .phy_cap_info[7] = - IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI | - IEEE80211_HE_PHY_CAP7_MAX_NC_1, + IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI, .phy_cap_info[8] = IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI | - IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G | - IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU | - IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU | - IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996, + IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242, .phy_cap_info[9] = - IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB | - IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB | IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED, }, /* @@ -745,12 +718,72 @@ static void iwl_init_he_6ghz_capa(struct iwl_trans *trans, iftype_data[i].he_6ghz_capa.capa = cpu_to_le16(he_6ghz_capa); } +static void +iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans, + struct ieee80211_supported_band *sband, + struct ieee80211_sband_iftype_data *iftype_data, + u8 tx_chains, u8 rx_chains, + const struct iwl_fw *fw) +{ + bool is_ap = iftype_data->types_mask & BIT(NL80211_IFTYPE_AP); + + /* Advertise an A-MPDU exponent extension based on + * operating band + */ + if (sband->band != NL80211_BAND_2GHZ) + iftype_data->he_cap.he_cap_elem.mac_cap_info[3] |= + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_1; + else + iftype_data->he_cap.he_cap_elem.mac_cap_info[3] |= + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3; + + if (is_ap && iwlwifi_mod_params.nvm_file) + iftype_data->he_cap.he_cap_elem.phy_cap_info[0] |= + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G; + + if ((tx_chains & rx_chains) == ANT_AB) { + iftype_data->he_cap.he_cap_elem.phy_cap_info[5] |= + IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 | + IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2; + if (!is_ap) + iftype_data->he_cap.he_cap_elem.phy_cap_info[7] |= + IEEE80211_HE_PHY_CAP7_MAX_NC_2; + } else if (!is_ap) { + /* If not 2x2, we need to indicate 1x1 in the + * Midamble RX Max NSTS - but not for AP mode + */ + iftype_data->he_cap.he_cap_elem.phy_cap_info[1] &= + ~IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS; + iftype_data->he_cap.he_cap_elem.phy_cap_info[2] &= + ~IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS; + iftype_data->he_cap.he_cap_elem.phy_cap_info[7] |= + IEEE80211_HE_PHY_CAP7_MAX_NC_1; + } + + switch (CSR_HW_RFID_TYPE(trans->hw_rf_id)) { + case IWL_CFG_RF_TYPE_GF: + case IWL_CFG_RF_TYPE_MR: + iftype_data->he_cap.he_cap_elem.phy_cap_info[9] |= + IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU; + if (!is_ap) + iftype_data->he_cap.he_cap_elem.phy_cap_info[9] |= + IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU; + break; + } + + if (fw_has_capa(&fw->ucode_capa, IWL_UCODE_TLV_CAPA_BROADCAST_TWT)) + iftype_data->he_cap.he_cap_elem.mac_cap_info[2] |= + IEEE80211_HE_MAC_CAP2_BCAST_TWT; +} + static void iwl_init_he_hw_capab(struct iwl_trans *trans, struct iwl_nvm_data *data, struct ieee80211_supported_band *sband, - u8 tx_chains, u8 rx_chains) + u8 tx_chains, u8 rx_chains, + const struct iwl_fw *fw) { struct ieee80211_sband_iftype_data *iftype_data; + int i; /* should only initialize once */ if (WARN_ON(sband->iftype_data)) @@ -777,26 +810,18 @@ static void iwl_init_he_hw_capab(struct iwl_trans *trans, sband->iftype_data = iftype_data; sband->n_iftype_data = ARRAY_SIZE(iwl_he_capa); - /* If not 2x2, we need to indicate 1x1 in the Midamble RX Max NSTS */ - if ((tx_chains & rx_chains) != ANT_AB) { - int i; + for (i = 0; i < sband->n_iftype_data; i++) + iwl_nvm_fixup_sband_iftd(trans, sband, &iftype_data[i], + tx_chains, rx_chains, fw); - for (i = 0; i < sband->n_iftype_data; i++) { - iftype_data[i].he_cap.he_cap_elem.phy_cap_info[1] &= - ~IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS; - iftype_data[i].he_cap.he_cap_elem.phy_cap_info[2] &= - ~IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS; - iftype_data[i].he_cap.he_cap_elem.phy_cap_info[7] &= - ~IEEE80211_HE_PHY_CAP7_MAX_NC_MASK; - } - } iwl_init_he_6ghz_capa(trans, data, sband, tx_chains, rx_chains); } static void iwl_init_sbands(struct iwl_trans *trans, struct iwl_nvm_data *data, const void *nvm_ch_flags, u8 tx_chains, - u8 rx_chains, u32 sbands_flags, bool v4) + u8 rx_chains, u32 sbands_flags, bool v4, + const struct iwl_fw *fw) { struct device *dev = trans->dev; const struct iwl_cfg *cfg = trans->cfg; @@ -816,7 +841,8 @@ static void iwl_init_sbands(struct iwl_trans *trans, tx_chains, rx_chains); if (data->sku_cap_11ax_enable && !iwlwifi_mod_params.disable_11ax) - iwl_init_he_hw_capab(trans, data, sband, tx_chains, rx_chains); + iwl_init_he_hw_capab(trans, data, sband, tx_chains, rx_chains, + fw); sband = &data->bands[NL80211_BAND_5GHZ]; sband->band = NL80211_BAND_5GHZ; @@ -831,7 +857,8 @@ static void iwl_init_sbands(struct iwl_trans *trans, tx_chains, rx_chains); if (data->sku_cap_11ax_enable && !iwlwifi_mod_params.disable_11ax) - iwl_init_he_hw_capab(trans, data, sband, tx_chains, rx_chains); + iwl_init_he_hw_capab(trans, data, sband, tx_chains, rx_chains, + fw); /* 6GHz band. */ sband = &data->bands[NL80211_BAND_6GHZ]; @@ -843,7 +870,8 @@ static void iwl_init_sbands(struct iwl_trans *trans, NL80211_BAND_6GHZ); if (data->sku_cap_11ax_enable && !iwlwifi_mod_params.disable_11ax) - iwl_init_he_hw_capab(trans, data, sband, tx_chains, rx_chains); + iwl_init_he_hw_capab(trans, data, sband, tx_chains, rx_chains, + fw); else sband->n_channels = 0; if (n_channels != n_used) @@ -1154,7 +1182,7 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_cfg *cfg, sbands_flags |= IWL_NVM_SBANDS_FLAGS_NO_WIDE_IN_5GHZ; iwl_init_sbands(trans, data, ch_section, tx_chains, rx_chains, - sbands_flags, false); + sbands_flags, false, fw); data->calib_version = 255; return data; @@ -1661,7 +1689,7 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans, channel_profile, nvm->valid_tx_ant & fw->valid_tx_ant, nvm->valid_rx_ant & fw->valid_rx_ant, - sbands_flags, v4); + sbands_flags, v4, fw); iwl_free_resp(&hcmd); return nvm; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h index 3ce77e4eb7e3..9a9e714bf9af 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2005-2014, 2018-2020 Intel Corporation + * Copyright (C) 2005-2014, 2018-2021 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016 Intel Deutschland GmbH */ @@ -412,6 +412,8 @@ enum { #define UREG_DOORBELL_TO_ISR6_RESUME BIT(19) #define UREG_DOORBELL_TO_ISR6_PNVM BIT(20) +#define CNVI_MBOX_C 0xA3400C + #define FSEQ_ERROR_CODE 0xA340C8 #define FSEQ_TOP_INIT_VERSION 0xA34038 #define FSEQ_CNVIO_INIT_VERSION 0xA3403C diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h index bf569f856ad8..0199d7a5a648 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h @@ -193,6 +193,7 @@ enum iwl_error_event_table_status { IWL_ERROR_EVENT_TABLE_LMAC1 = BIT(0), IWL_ERROR_EVENT_TABLE_LMAC2 = BIT(1), IWL_ERROR_EVENT_TABLE_UMAC = BIT(2), + IWL_ERROR_EVENT_TABLE_TCM = BIT(3), }; /** @@ -589,6 +590,8 @@ struct iwl_trans_ops { void (*debugfs_cleanup)(struct iwl_trans *trans); void (*sync_nmi)(struct iwl_trans *trans); int (*set_pnvm)(struct iwl_trans *trans, const void *data, u32 len); + int (*set_reduce_power)(struct iwl_trans *trans, + const void *data, u32 len); void (*interrupts)(struct iwl_trans *trans, bool enable); }; @@ -706,6 +709,7 @@ struct iwl_self_init_dram { * @trigger_tlv: array of pointers to triggers TLVs for debug * @lmac_error_event_table: addrs of lmacs error tables * @umac_error_event_table: addr of umac error table + * @tcm_error_event_table: address of TCM error table * @error_event_table_tlv_status: bitmap that indicates what error table * pointers was recevied via TLV. uses enum &iwl_error_event_table_status * @internal_ini_cfg: internal debug cfg state. Uses &enum iwl_ini_cfg_state @@ -732,6 +736,7 @@ struct iwl_trans_debug { u32 lmac_error_event_table[2]; u32 umac_error_event_table; + u32 tcm_error_event_table; unsigned int error_event_table_tlv_status; enum iwl_ini_cfg_state internal_ini_cfg; @@ -957,6 +962,7 @@ struct iwl_trans { bool pm_support; bool ltr_enabled; u8 pnvm_loaded:1; + u8 reduce_power_loaded:1; const struct iwl_hcmd_arr *command_groups; int command_groups_size; @@ -1420,6 +1426,20 @@ static inline int iwl_trans_set_pnvm(struct iwl_trans *trans, return 0; } +static inline int iwl_trans_set_reduce_power(struct iwl_trans *trans, + const void *data, u32 len) +{ + if (trans->ops->set_reduce_power) { + int ret = trans->ops->set_reduce_power(trans, data, len); + + if (ret) + return ret; + } + + trans->reduce_power_loaded = true; + return 0; +} + static inline bool iwl_trans_dbg_ini_valid(struct iwl_trans *trans) { return trans->dbg.internal_ini_cfg != IWL_INI_CFG_STATE_NOT_LOADED || diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 2e28cf299ef4..6a259d867d90 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -104,7 +104,7 @@ static const u8 *iwl_mvm_find_max_pn(struct ieee80211_key_conf *key, struct wowlan_key_data { struct iwl_wowlan_rsc_tsc_params_cmd *rsc_tsc; struct iwl_wowlan_tkip_params_cmd *tkip; - struct iwl_wowlan_kek_kck_material_cmd_v3 *kek_kck_cmd; + struct iwl_wowlan_kek_kck_material_cmd_v4 *kek_kck_cmd; bool error, use_rsc_tsc, use_tkip, configure_keys; int wep_key_idx; }; @@ -393,14 +393,19 @@ static int iwl_mvm_send_patterns_v1(struct iwl_mvm *mvm, } static int iwl_mvm_send_patterns(struct iwl_mvm *mvm, + struct ieee80211_vif *vif, struct cfg80211_wowlan *wowlan) { + struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_wowlan_patterns_cmd *pattern_cmd; struct iwl_host_cmd cmd = { .id = WOWLAN_PATTERNS, .dataflags[0] = IWL_HCMD_DFL_NOCOPY, }; int i, err; + int ver = iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP, + WOWLAN_PATTERNS, + IWL_FW_CMD_VER_UNKNOWN); if (!wowlan->n_patterns) return 0; @@ -408,11 +413,13 @@ static int iwl_mvm_send_patterns(struct iwl_mvm *mvm, cmd.len[0] = sizeof(*pattern_cmd) + wowlan->n_patterns * sizeof(struct iwl_wowlan_pattern_v2); - pattern_cmd = kmalloc(cmd.len[0], GFP_KERNEL); + pattern_cmd = kzalloc(cmd.len[0], GFP_KERNEL); if (!pattern_cmd) return -ENOMEM; - pattern_cmd->n_patterns = cpu_to_le32(wowlan->n_patterns); + pattern_cmd->n_patterns = wowlan->n_patterns; + if (ver >= 3) + pattern_cmd->sta_id = mvmvif->ap_sta_id; for (i = 0; i < wowlan->n_patterns; i++) { int mask_len = DIV_ROUND_UP(wowlan->patterns[i].pattern_len, 8); @@ -636,7 +643,6 @@ iwl_mvm_get_wowlan_config(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct iwl_mvm_vif *mvmvif, struct ieee80211_sta *ap_sta) { - int ret; struct iwl_mvm_sta *mvm_ap_sta = iwl_mvm_sta_from_mac80211(ap_sta); /* TODO: wowlan_config_cmd->wowlan_ba_teardown_tids */ @@ -646,12 +652,16 @@ iwl_mvm_get_wowlan_config(struct iwl_mvm *mvm, wowlan_config_cmd->flags = ENABLE_L3_FILTERING | ENABLE_NBNS_FILTERING | ENABLE_DHCP_FILTERING; - /* Query the last used seqno and set it */ - ret = iwl_mvm_get_last_nonqos_seq(mvm, vif); - if (ret < 0) - return ret; + if (iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP, + WOWLAN_CONFIGURATION, 0) < 6) { + /* Query the last used seqno and set it */ + int ret = iwl_mvm_get_last_nonqos_seq(mvm, vif); - wowlan_config_cmd->non_qos_seq = cpu_to_le16(ret); + if (ret < 0) + return ret; + + wowlan_config_cmd->non_qos_seq = cpu_to_le16(ret); + } iwl_mvm_set_wowlan_qos_seq(mvm_ap_sta, wowlan_config_cmd); @@ -706,7 +716,8 @@ static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm, struct ieee80211_vif *vif, u32 cmd_flags) { - struct iwl_wowlan_kek_kck_material_cmd_v3 kek_kck_cmd = {}; + struct iwl_wowlan_kek_kck_material_cmd_v4 kek_kck_cmd = {}; + struct iwl_wowlan_kek_kck_material_cmd_v4 *_kek_kck_cmd = &kek_kck_cmd; struct iwl_wowlan_tkip_params_cmd tkip_cmd = {}; bool unified = fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_CNSLDTD_D3_D0_IMG); @@ -715,7 +726,7 @@ static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm, .use_rsc_tsc = false, .tkip = &tkip_cmd, .use_tkip = false, - .kek_kck_cmd = &kek_kck_cmd, + .kek_kck_cmd = _kek_kck_cmd, }; struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); int ret; @@ -809,13 +820,9 @@ static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm, IWL_ALWAYS_LONG_GROUP, WOWLAN_KEK_KCK_MATERIAL, IWL_FW_CMD_VER_UNKNOWN); - if (WARN_ON(cmd_ver != 2 && cmd_ver != 3 && + if (WARN_ON(cmd_ver != 2 && cmd_ver != 3 && cmd_ver != 4 && cmd_ver != IWL_FW_CMD_VER_UNKNOWN)) return -EINVAL; - if (cmd_ver == 3) - cmd_size = sizeof(struct iwl_wowlan_kek_kck_material_cmd_v3); - else - cmd_size = sizeof(struct iwl_wowlan_kek_kck_material_cmd_v2); memcpy(kek_kck_cmd.kck, mvmvif->rekey_data.kck, mvmvif->rekey_data.kck_len); @@ -825,6 +832,21 @@ static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm, kek_kck_cmd.kek_len = cpu_to_le16(mvmvif->rekey_data.kek_len); kek_kck_cmd.replay_ctr = mvmvif->rekey_data.replay_ctr; kek_kck_cmd.akm = cpu_to_le32(mvmvif->rekey_data.akm); + kek_kck_cmd.sta_id = cpu_to_le32(mvmvif->ap_sta_id); + + if (cmd_ver == 4) { + cmd_size = sizeof(struct iwl_wowlan_kek_kck_material_cmd_v4); + } else { + if (cmd_ver == 3) + cmd_size = + sizeof(struct iwl_wowlan_kek_kck_material_cmd_v3); + else + cmd_size = + sizeof(struct iwl_wowlan_kek_kck_material_cmd_v2); + /* skip the sta_id at the beginning */ + _kek_kck_cmd = (void *) + ((u8 *)_kek_kck_cmd) + sizeof(kek_kck_cmd.sta_id); + } IWL_DEBUG_WOWLAN(mvm, "setting akm %d\n", mvmvif->rekey_data.akm); @@ -832,7 +854,7 @@ static int iwl_mvm_wowlan_config_key_params(struct iwl_mvm *mvm, ret = iwl_mvm_send_cmd_pdu(mvm, WOWLAN_KEK_KCK_MATERIAL, cmd_flags, cmd_size, - &kek_kck_cmd); + _kek_kck_cmd); if (ret) goto out; } @@ -884,7 +906,7 @@ iwl_mvm_wowlan_config(struct iwl_mvm *mvm, if (fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_WOWLAN_TCP_SYN_WAKE)) - ret = iwl_mvm_send_patterns(mvm, wowlan); + ret = iwl_mvm_send_patterns(mvm, vif, wowlan); else ret = iwl_mvm_send_patterns_v1(mvm, wowlan); if (ret) @@ -1534,9 +1556,12 @@ static bool iwl_mvm_setup_connection_keep(struct iwl_mvm *mvm, } out: - mvmvif->seqno_valid = true; - /* +0x10 because the set API expects next-to-use, not last-used */ - mvmvif->seqno = le16_to_cpu(status->non_qos_seq_ctr) + 0x10; + if (iwl_fw_lookup_notif_ver(mvm->fw, LONG_GROUP, + WOWLAN_GET_STATUSES, 0) < 10) { + mvmvif->seqno_valid = true; + /* +0x10 because the set API expects next-to-use, not last-used */ + mvmvif->seqno = le16_to_cpu(status->non_qos_seq_ctr) + 0x10; + } return true; } @@ -1587,15 +1612,27 @@ iwl_mvm_parse_wowlan_status_common(v6) iwl_mvm_parse_wowlan_status_common(v7) iwl_mvm_parse_wowlan_status_common(v9) -struct iwl_wowlan_status *iwl_mvm_send_wowlan_get_status(struct iwl_mvm *mvm) +static struct iwl_wowlan_status * +iwl_mvm_send_wowlan_get_status(struct iwl_mvm *mvm, u8 sta_id) { struct iwl_wowlan_status *status; + struct iwl_wowlan_get_status_cmd get_status_cmd = { + .sta_id = cpu_to_le32(sta_id), + }; struct iwl_host_cmd cmd = { .id = WOWLAN_GET_STATUSES, .flags = CMD_WANT_SKB, + .data = { &get_status_cmd, }, + .len = { sizeof(get_status_cmd), }, }; int ret, len; u8 notif_ver; + u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP, + WOWLAN_GET_STATUSES, + IWL_FW_CMD_VER_UNKNOWN); + + if (cmd_ver == IWL_FW_CMD_VER_UNKNOWN) + cmd.len[0] = 0; lockdep_assert_held(&mvm->mutex); @@ -1608,8 +1645,11 @@ struct iwl_wowlan_status *iwl_mvm_send_wowlan_get_status(struct iwl_mvm *mvm) len = iwl_rx_packet_payload_len(cmd.resp_pkt); /* default to 7 (when we have IWL_UCODE_TLV_API_WOWLAN_KEY_MATERIAL) */ - notif_ver = iwl_fw_lookup_notif_ver(mvm->fw, LEGACY_GROUP, - WOWLAN_GET_STATUSES, 7); + notif_ver = iwl_fw_lookup_notif_ver(mvm->fw, LONG_GROUP, + WOWLAN_GET_STATUSES, 0); + if (!notif_ver) + notif_ver = iwl_fw_lookup_notif_ver(mvm->fw, LEGACY_GROUP, + WOWLAN_GET_STATUSES, 7); if (!fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_WOWLAN_KEY_MATERIAL)) { @@ -1654,7 +1694,7 @@ struct iwl_wowlan_status *iwl_mvm_send_wowlan_get_status(struct iwl_mvm *mvm) status->gtk[0] = v7->gtk[0]; status->igtk[0] = v7->igtk[0]; - } else if (notif_ver == 9) { + } else if (notif_ver == 9 || notif_ver == 10) { struct iwl_wowlan_status_v9 *v9 = (void *)cmd.resp_pkt->data; status = iwl_mvm_parse_wowlan_status_common_v9(mvm, @@ -1680,29 +1720,37 @@ out_free_resp: } static struct iwl_wowlan_status * -iwl_mvm_get_wakeup_status(struct iwl_mvm *mvm) +iwl_mvm_get_wakeup_status(struct iwl_mvm *mvm, u8 sta_id) { - int ret; + u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP, + OFFLOADS_QUERY_CMD, + IWL_FW_CMD_VER_UNKNOWN); + __le32 station_id = cpu_to_le32(sta_id); + u32 cmd_size = cmd_ver != IWL_FW_CMD_VER_UNKNOWN ? sizeof(station_id) : 0; - /* only for tracing for now */ - ret = iwl_mvm_send_cmd_pdu(mvm, OFFLOADS_QUERY_CMD, 0, 0, NULL); - if (ret) - IWL_ERR(mvm, "failed to query offload statistics (%d)\n", ret); + if (!mvm->net_detect) { + /* only for tracing for now */ + int ret = iwl_mvm_send_cmd_pdu(mvm, OFFLOADS_QUERY_CMD, 0, + cmd_size, &station_id); + if (ret) + IWL_ERR(mvm, "failed to query offload statistics (%d)\n", ret); + } - return iwl_mvm_send_wowlan_get_status(mvm); + return iwl_mvm_send_wowlan_get_status(mvm, sta_id); } /* releases the MVM mutex */ static bool iwl_mvm_query_wakeup_reasons(struct iwl_mvm *mvm, struct ieee80211_vif *vif) { + struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_wowlan_status_data status; struct iwl_wowlan_status *fw_status; int i; bool keep; struct iwl_mvm_sta *mvm_ap_sta; - fw_status = iwl_mvm_get_wakeup_status(mvm); + fw_status = iwl_mvm_get_wakeup_status(mvm, mvmvif->ap_sta_id); if (IS_ERR_OR_NULL(fw_status)) goto out_unlock; @@ -1880,7 +1928,7 @@ static void iwl_mvm_query_netdetect_reasons(struct iwl_mvm *mvm, u32 reasons = 0; int i, n_matches, ret; - fw_status = iwl_mvm_get_wakeup_status(mvm); + fw_status = iwl_mvm_get_wakeup_status(mvm, IWL_MVM_INVALID_STA); if (!IS_ERR_OR_NULL(fw_status)) { reasons = le32_to_cpu(fw_status->wakeup_reasons); kfree(fw_status); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c index 38d0bfb649cc..7d9faeffd154 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2020 Intel Corporation + * Copyright (C) 2012-2014, 2018-2021 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -460,7 +460,7 @@ static ssize_t iwl_dbgfs_os_device_timediff_read(struct file *file, int pos = 0; mutex_lock(&mvm->mutex); - iwl_mvm_get_sync_time(mvm, &curr_gp2, &curr_os); + iwl_mvm_get_sync_time(mvm, CLOCK_BOOTTIME, &curr_gp2, &curr_os, NULL); mutex_unlock(&mvm->mutex); do_div(curr_os, NSEC_PER_USEC); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c index 63d65018d098..95f883aba148 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c @@ -1023,7 +1023,9 @@ static ssize_t iwl_dbgfs_fw_restart_write(struct iwl_mvm *mvm, char *buf, mvm->fw_restart++; /* take the return value to make compiler happy - it will fail anyway */ - ret = iwl_mvm_send_cmd_pdu(mvm, REPLY_ERROR, 0, 0, NULL); + ret = iwl_mvm_send_cmd_pdu(mvm, + WIDE_ID(LONG_GROUP, REPLY_ERROR), + 0, 0, NULL); mutex_unlock(&mvm->mutex); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c index a456b8a0ae58..59cef0d89a6d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include #include @@ -430,6 +430,10 @@ iwl_mvm_ftm_put_target_common(struct iwl_mvm *mvm, FTM_PUT_FLAG(TB); else if (peer->ftm.non_trigger_based) FTM_PUT_FLAG(NON_TB); + + if ((peer->ftm.trigger_based || peer->ftm.non_trigger_based) && + peer->ftm.lmr_feedback) + FTM_PUT_FLAG(LMR_FEEDBACK); } static int @@ -879,7 +883,8 @@ static u64 iwl_mvm_ftm_get_host_time(struct iwl_mvm *mvm, __le32 fw_gp2_ts) u32 curr_gp2, diff; u64 now_from_boot_ns; - iwl_mvm_get_sync_time(mvm, &curr_gp2, &now_from_boot_ns); + iwl_mvm_get_sync_time(mvm, CLOCK_BOOTTIME, &curr_gp2, + &now_from_boot_ns, NULL); if (curr_gp2 >= gp2_ts) diff = curr_gp2 - gp2_ts; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 8aa5f1a2c58c..38fd5886af2d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -1139,19 +1139,34 @@ static u8 iwl_mvm_eval_dsm_rfi(struct iwl_mvm *mvm) static void iwl_mvm_lari_cfg(struct iwl_mvm *mvm) { - int cmd_ret; - struct iwl_lari_config_change_cmd_v3 cmd = {}; + int ret; + u32 value; + struct iwl_lari_config_change_cmd_v4 cmd = {}; cmd.config_bitmap = iwl_acpi_get_lari_config_bitmap(&mvm->fwrt); + ret = iwl_acpi_get_dsm_u32((&mvm->fwrt)->dev, 0, DSM_FUNC_11AX_ENABLEMENT, + &iwl_guid, &value); + if (!ret) + cmd.oem_11ax_allow_bitmap = cpu_to_le32(value); /* apply more config masks here */ - if (cmd.config_bitmap) { + ret = iwl_acpi_get_dsm_u32((&mvm->fwrt)->dev, 0, + DSM_FUNC_ENABLE_UNII4_CHAN, + &iwl_guid, &value); + if (!ret) + cmd.oem_unii4_allow_bitmap = cpu_to_le32(value); + + if (cmd.config_bitmap || + cmd.oem_11ax_allow_bitmap || + cmd.oem_unii4_allow_bitmap) { size_t cmd_size; u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw, REGULATORY_AND_NVM_GROUP, LARI_CONFIG_CHANGE, 1); - if (cmd_ver == 3) + if (cmd_ver == 4) + cmd_size = sizeof(struct iwl_lari_config_change_cmd_v4); + else if (cmd_ver == 3) cmd_size = sizeof(struct iwl_lari_config_change_cmd_v3); else if (cmd_ver == 2) cmd_size = sizeof(struct iwl_lari_config_change_cmd_v2); @@ -1159,16 +1174,21 @@ static void iwl_mvm_lari_cfg(struct iwl_mvm *mvm) cmd_size = sizeof(struct iwl_lari_config_change_cmd_v1); IWL_DEBUG_RADIO(mvm, - "sending LARI_CONFIG_CHANGE, config_bitmap=0x%x\n", - le32_to_cpu(cmd.config_bitmap)); - cmd_ret = iwl_mvm_send_cmd_pdu(mvm, - WIDE_ID(REGULATORY_AND_NVM_GROUP, - LARI_CONFIG_CHANGE), - 0, cmd_size, &cmd); - if (cmd_ret < 0) + "sending LARI_CONFIG_CHANGE, config_bitmap=0x%x, oem_11ax_allow_bitmap=0x%x\n", + le32_to_cpu(cmd.config_bitmap), + le32_to_cpu(cmd.oem_11ax_allow_bitmap)); + IWL_DEBUG_RADIO(mvm, + "sending LARI_CONFIG_CHANGE, oem_unii4_allow_bitmap=0x%x, cmd_ver=%d\n", + le32_to_cpu(cmd.oem_unii4_allow_bitmap), + cmd_ver); + ret = iwl_mvm_send_cmd_pdu(mvm, + WIDE_ID(REGULATORY_AND_NVM_GROUP, + LARI_CONFIG_CHANGE), + 0, cmd_size, &cmd); + if (ret < 0) IWL_DEBUG_RADIO(mvm, "Failed to send LARI_CONFIG_CHANGE (%d)\n", - cmd_ret); + ret); } } #else /* CONFIG_ACPI */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 607d5d564928..70ebecb73c24 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -3306,14 +3306,14 @@ static int iwl_mvm_mac_conf_tx(struct ieee80211_hw *hw, static void iwl_mvm_mac_mgd_prepare_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - u16 req_duration) + struct ieee80211_prep_tx_info *info) { struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); u32 duration = IWL_MVM_TE_SESSION_PROTECTION_MAX_TIME_MS; u32 min_duration = IWL_MVM_TE_SESSION_PROTECTION_MIN_TIME_MS; - if (req_duration > duration) - duration = req_duration; + if (info->duration > duration) + duration = info->duration; mutex_lock(&mvm->mutex); /* Try really hard to protect the session and hear a beacon @@ -3800,6 +3800,7 @@ static int iwl_mvm_roc(struct ieee80211_hw *hw, struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct cfg80211_chan_def chandef; struct iwl_mvm_phy_ctxt *phy_ctxt; + bool band_change_removal; int ret, i; IWL_DEBUG_MAC80211(mvm, "enter (%d, %d, %d)\n", channel->hw_value, @@ -3880,19 +3881,30 @@ static int iwl_mvm_roc(struct ieee80211_hw *hw, cfg80211_chandef_create(&chandef, channel, NL80211_CHAN_NO_HT); /* - * Change the PHY context configuration as it is currently referenced - * only by the P2P Device MAC + * Check if the remain-on-channel is on a different band and that + * requires context removal, see iwl_mvm_phy_ctxt_changed(). If + * so, we'll need to release and then re-configure here, since we + * must not remove a PHY context that's part of a binding. */ - if (mvmvif->phy_ctxt->ref == 1) { + band_change_removal = + fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_BINDING_CDB_SUPPORT) && + mvmvif->phy_ctxt->channel->band != chandef.chan->band; + + if (mvmvif->phy_ctxt->ref == 1 && !band_change_removal) { + /* + * Change the PHY context configuration as it is currently + * referenced only by the P2P Device MAC (and we can modify it) + */ ret = iwl_mvm_phy_ctxt_changed(mvm, mvmvif->phy_ctxt, &chandef, 1, 1); if (ret) goto out_unlock; } else { /* - * The PHY context is shared with other MACs. Need to remove the - * P2P Device from the binding, allocate an new PHY context and - * create a new binding + * The PHY context is shared with other MACs (or we're trying to + * switch bands), so remove the P2P Device from the binding, + * allocate an new PHY context and create a new binding. */ phy_ctxt = iwl_mvm_get_free_phy_ctxt(mvm); if (!phy_ctxt) { @@ -4211,7 +4223,6 @@ static void __iwl_mvm_unassign_vif_chanctx(struct iwl_mvm *mvm, struct ieee80211_vif *disabled_vif = NULL; lockdep_assert_held(&mvm->mutex); - iwl_mvm_remove_time_event(mvm, mvmvif, &mvmvif->time_event_data); switch (vif->type) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 4d9d4d6892fc..b50942f28bb7 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -16,6 +16,8 @@ #include #endif +#include + #include "iwl-op-mode.h" #include "iwl-trans.h" #include "fw/notif-wait.h" @@ -195,6 +197,7 @@ enum iwl_mvm_smps_type_request { IWL_MVM_SMPS_REQ_BT_COEX, IWL_MVM_SMPS_REQ_TT, IWL_MVM_SMPS_REQ_PROT, + IWL_MVM_SMPS_REQ_FW, NUM_IWL_MVM_SMPS_REQ, }; @@ -991,6 +994,8 @@ struct iwl_mvm { */ bool temperature_test; /* Debug test temperature is enabled */ + bool fw_static_smps_request; + unsigned long bt_coex_last_tcm_ts; struct iwl_mvm_tcm tcm; @@ -1447,10 +1452,16 @@ void iwl_mvm_hwrate_to_tx_rate(u32 rate_n_flags, struct ieee80211_tx_rate *r); u8 iwl_mvm_mac80211_idx_to_hwrate(int rate_idx); u8 iwl_mvm_mac80211_ac_to_ucode_ac(enum ieee80211_ac_numbers ac); -void iwl_mvm_dump_nic_error_log(struct iwl_mvm *mvm); + +static inline void iwl_mvm_dump_nic_error_log(struct iwl_mvm *mvm) +{ + iwl_fwrt_dump_error_logs(&mvm->fwrt); +} + u8 first_antenna(u8 mask); u8 iwl_mvm_next_antenna(struct iwl_mvm *mvm, u8 valid, u8 last_idx); -void iwl_mvm_get_sync_time(struct iwl_mvm *mvm, u32 *gp2, u64 *boottime); +void iwl_mvm_get_sync_time(struct iwl_mvm *mvm, int clock_type, u32 *gp2, + u64 *boottime, ktime_t *realtime); u32 iwl_mvm_get_systime(struct iwl_mvm *mvm); /* Tx / Host Commands */ @@ -1769,7 +1780,6 @@ void iwl_mvm_ipv6_addr_change(struct ieee80211_hw *hw, void iwl_mvm_set_default_unicast_key(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int idx); extern const struct file_operations iwl_dbgfs_d3_test_ops; -struct iwl_wowlan_status *iwl_mvm_send_wowlan_get_status(struct iwl_mvm *mvm); #ifdef CONFIG_PM void iwl_mvm_set_last_nonqos_seq(struct iwl_mvm *mvm, struct ieee80211_vif *vif); @@ -1827,7 +1837,9 @@ int iwl_mvm_disable_beacon_filter(struct iwl_mvm *mvm, void iwl_mvm_update_smps(struct iwl_mvm *mvm, struct ieee80211_vif *vif, enum iwl_mvm_smps_type_request req_type, enum ieee80211_smps_mode smps_request); -bool iwl_mvm_rx_diversity_allowed(struct iwl_mvm *mvm); +bool iwl_mvm_rx_diversity_allowed(struct iwl_mvm *mvm, + struct iwl_mvm_phy_ctxt *ctxt); +void iwl_mvm_apply_fw_smps_request(struct ieee80211_vif *vif); /* Low latency */ int iwl_mvm_update_low_latency(struct iwl_mvm *mvm, struct ieee80211_vif *vif, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/offloading.c b/drivers/net/wireless/intel/iwlwifi/mvm/offloading.c index 1cc90e61367b..41880517e8bb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/offloading.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/offloading.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014 Intel Corporation + * Copyright (C) 2012-2014, 2021 Intel Corporation * Copyright (C) 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 Intel Deutschland GmbH */ @@ -36,7 +36,7 @@ int iwl_mvm_send_proto_offload(struct iwl_mvm *mvm, struct iwl_proto_offload_cmd_v1 v1; struct iwl_proto_offload_cmd_v2 v2; struct iwl_proto_offload_cmd_v3_small v3s; - struct iwl_proto_offload_cmd_v3_large v3l; + struct iwl_proto_offload_cmd_v4 v4; } cmd = {}; struct iwl_host_cmd hcmd = { .id = PROT_OFFLOAD_CONFIG_CMD, @@ -47,6 +47,9 @@ int iwl_mvm_send_proto_offload(struct iwl_mvm *mvm, struct iwl_proto_offload_cmd_common *common; u32 enabled = 0, size; u32 capa_flags = mvm->fw->ucode_capa.flags; + int ver = iwl_fw_lookup_cmd_ver(mvm->fw, LONG_GROUP, + PROT_OFFLOAD_CONFIG_CMD, 0); + #if IS_ENABLED(CONFIG_IPV6) struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); int i; @@ -72,9 +75,9 @@ int iwl_mvm_send_proto_offload(struct iwl_mvm *mvm, addrs = cmd.v3s.targ_addrs; n_addrs = IWL_PROTO_OFFLOAD_NUM_IPV6_ADDRS_V3S; } else { - nsc = cmd.v3l.ns_config; + nsc = cmd.v4.ns_config; n_nsc = IWL_PROTO_OFFLOAD_NUM_NS_CONFIG_V3L; - addrs = cmd.v3l.targ_addrs; + addrs = cmd.v4.targ_addrs; n_addrs = IWL_PROTO_OFFLOAD_NUM_IPV6_ADDRS_V3L; } @@ -116,7 +119,7 @@ int iwl_mvm_send_proto_offload(struct iwl_mvm *mvm, cmd.v3s.num_valid_ipv6_addrs = cpu_to_le32(i - num_skipped); else - cmd.v3l.num_valid_ipv6_addrs = + cmd.v4.num_valid_ipv6_addrs = cpu_to_le32(i - num_skipped); } else if (capa_flags & IWL_UCODE_TLV_FLAGS_D3_6_IPV6_ADDRS) { bool found = false; @@ -171,8 +174,17 @@ int iwl_mvm_send_proto_offload(struct iwl_mvm *mvm, common = &cmd.v3s.common; size = sizeof(cmd.v3s); } else if (capa_flags & IWL_UCODE_TLV_FLAGS_NEW_NSOFFL_LARGE) { - common = &cmd.v3l.common; - size = sizeof(cmd.v3l); + common = &cmd.v4.common; + size = sizeof(cmd.v4); + if (ver < 4) { + /* + * This basically uses iwl_proto_offload_cmd_v3_large + * which doesn't have the sta_id parameter before the + * common part. + */ + size -= sizeof(cmd.v4.sta_id); + hcmd.data[0] = common; + } } else if (capa_flags & IWL_UCODE_TLV_FLAGS_D3_6_IPV6_ADDRS) { common = &cmd.v2.common; size = sizeof(cmd.v2); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index ebed82c590e5..20e8d343a950 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -210,6 +210,39 @@ static void iwl_mvm_rx_monitor_notif(struct iwl_mvm *mvm, ieee80211_disconnect(vif, true); } +void iwl_mvm_apply_fw_smps_request(struct ieee80211_vif *vif) +{ + struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); + struct iwl_mvm *mvm = mvmvif->mvm; + + iwl_mvm_update_smps(mvm, vif, IWL_MVM_SMPS_REQ_FW, + mvm->fw_static_smps_request ? + IEEE80211_SMPS_STATIC : + IEEE80211_SMPS_AUTOMATIC); +} + +static void iwl_mvm_intf_dual_chain_req(void *data, u8 *mac, + struct ieee80211_vif *vif) +{ + iwl_mvm_apply_fw_smps_request(vif); +} + +static void iwl_mvm_rx_thermal_dual_chain_req(struct iwl_mvm *mvm, + struct iwl_rx_cmd_buffer *rxb) +{ + struct iwl_rx_packet *pkt = rxb_addr(rxb); + struct iwl_thermal_dual_chain_request *req = (void *)pkt->data; + + /* + * We could pass it to the iterator data, but also need to remember + * it for new interfaces that are added while in this state. + */ + mvm->fw_static_smps_request = + req->event == cpu_to_le32(THERMAL_DUAL_CHAIN_REQ_DISABLE); + ieee80211_iterate_interfaces(mvm->hw, IEEE80211_IFACE_ITER_NORMAL, + iwl_mvm_intf_dual_chain_req, NULL); +} + /** * enum iwl_rx_handler_context context for Rx handler * @RX_HANDLER_SYNC : this means that it will be called in the Rx path @@ -358,6 +391,11 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = { RX_HANDLER_GRP(DATA_PATH_GROUP, MONITOR_NOTIF, iwl_mvm_rx_monitor_notif, RX_HANDLER_ASYNC_LOCKED, struct iwl_datapath_monitor_notif), + + RX_HANDLER_GRP(DATA_PATH_GROUP, THERMAL_DUAL_CHAIN_REQUEST, + iwl_mvm_rx_thermal_dual_chain_req, + RX_HANDLER_ASYNC_LOCKED, + struct iwl_thermal_dual_chain_request), }; #undef RX_HANDLER #undef RX_HANDLER_GRP @@ -445,7 +483,6 @@ static const struct iwl_hcmd_names iwl_mvm_legacy_names[] = { HCMD_NAME(D3_CONFIG_CMD), HCMD_NAME(PROT_OFFLOAD_CONFIG_CMD), HCMD_NAME(OFFLOADS_QUERY_CMD), - HCMD_NAME(REMOTE_WAKE_CONFIG_CMD), HCMD_NAME(MATCH_FOUND_NOTIFICATION), HCMD_NAME(DTS_MEASUREMENT_NOTIFICATION), HCMD_NAME(WOWLAN_PATTERNS), @@ -503,6 +540,7 @@ static const struct iwl_hcmd_names iwl_mvm_data_path_names[] = { HCMD_NAME(TLC_MNG_CONFIG_CMD), HCMD_NAME(CHEST_COLLECTOR_FILTER_CONFIG_CMD), HCMD_NAME(MONITOR_NOTIF), + HCMD_NAME(THERMAL_DUAL_CHAIN_REQUEST), HCMD_NAME(STA_PM_NOTIF), HCMD_NAME(MU_GROUP_MGMT_NOTIF), HCMD_NAME(RX_QUEUES_NOTIFICATION), diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c index 0fd51f6aa206..035336a9e755 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2020 Intel Corporation + * Copyright (C) 2012-2014, 2018-2021 Intel Corporation * Copyright (C) 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2017 Intel Deutschland GmbH */ @@ -76,6 +76,7 @@ static void iwl_mvm_phy_ctxt_cmd_hdr(struct iwl_mvm_phy_ctxt *ctxt, } static void iwl_mvm_phy_ctxt_set_rxchain(struct iwl_mvm *mvm, + struct iwl_mvm_phy_ctxt *ctxt, __le32 *rxchain_info, u8 chains_static, u8 chains_dynamic) @@ -93,11 +94,22 @@ static void iwl_mvm_phy_ctxt_set_rxchain(struct iwl_mvm *mvm, * between the two antennas is sufficiently different to impact * performance. */ - if (active_cnt == 1 && iwl_mvm_rx_diversity_allowed(mvm)) { + if (active_cnt == 1 && iwl_mvm_rx_diversity_allowed(mvm, ctxt)) { idle_cnt = 2; active_cnt = 2; } + /* + * If the firmware requested it, then we know that it supports + * getting zero for the values to indicate "use one, but pick + * which one yourself", which means it can dynamically pick one + * that e.g. has better RSSI. + */ + if (mvm->fw_static_smps_request && active_cnt == 1 && idle_cnt == 1) { + idle_cnt = 0; + active_cnt = 0; + } + *rxchain_info = cpu_to_le32(iwl_mvm_get_valid_rx_ant(mvm) << PHY_RX_CHAIN_VALID_POS); *rxchain_info |= cpu_to_le32(idle_cnt << PHY_RX_CHAIN_CNT_POS); @@ -113,6 +125,7 @@ static void iwl_mvm_phy_ctxt_set_rxchain(struct iwl_mvm *mvm, * Add the phy configuration to the PHY context command */ static void iwl_mvm_phy_ctxt_cmd_data_v1(struct iwl_mvm *mvm, + struct iwl_mvm_phy_ctxt *ctxt, struct iwl_phy_context_cmd_v1 *cmd, struct cfg80211_chan_def *chandef, u8 chains_static, u8 chains_dynamic) @@ -123,7 +136,7 @@ static void iwl_mvm_phy_ctxt_cmd_data_v1(struct iwl_mvm *mvm, /* Set the channel info data */ iwl_mvm_set_chan_info_chandef(mvm, &cmd->ci, chandef); - iwl_mvm_phy_ctxt_set_rxchain(mvm, &tail->rxchain_info, + iwl_mvm_phy_ctxt_set_rxchain(mvm, ctxt, &tail->rxchain_info, chains_static, chains_dynamic); tail->txchain_info = cpu_to_le32(iwl_mvm_get_valid_tx_ant(mvm)); @@ -133,6 +146,7 @@ static void iwl_mvm_phy_ctxt_cmd_data_v1(struct iwl_mvm *mvm, * Add the phy configuration to the PHY context command */ static void iwl_mvm_phy_ctxt_cmd_data(struct iwl_mvm *mvm, + struct iwl_mvm_phy_ctxt *ctxt, struct iwl_phy_context_cmd *cmd, struct cfg80211_chan_def *chandef, u8 chains_static, u8 chains_dynamic) @@ -143,7 +157,7 @@ static void iwl_mvm_phy_ctxt_cmd_data(struct iwl_mvm *mvm, /* Set the channel info data */ iwl_mvm_set_chan_info_chandef(mvm, &cmd->ci, chandef); - iwl_mvm_phy_ctxt_set_rxchain(mvm, &cmd->rxchain_info, + iwl_mvm_phy_ctxt_set_rxchain(mvm, ctxt, &cmd->rxchain_info, chains_static, chains_dynamic); } @@ -170,7 +184,7 @@ static int iwl_mvm_phy_ctxt_apply(struct iwl_mvm *mvm, iwl_mvm_phy_ctxt_cmd_hdr(ctxt, &cmd, action); /* Set the command data */ - iwl_mvm_phy_ctxt_cmd_data(mvm, &cmd, chandef, + iwl_mvm_phy_ctxt_cmd_data(mvm, ctxt, &cmd, chandef, chains_static, chains_dynamic); @@ -186,7 +200,7 @@ static int iwl_mvm_phy_ctxt_apply(struct iwl_mvm *mvm, action); /* Set the command data */ - iwl_mvm_phy_ctxt_cmd_data_v1(mvm, &cmd, chandef, + iwl_mvm_phy_ctxt_cmd_data_v1(mvm, ctxt, &cmd, chandef, chains_static, chains_dynamic); ret = iwl_mvm_send_cmd_pdu(mvm, PHY_CONTEXT_CMD, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 8e26422ca326..c0babb8d5b5c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2020 Intel Corporation + * Copyright (C) 2012-2014, 2018-2021 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH */ @@ -2001,8 +2001,10 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, struct sk_buff *skb; u8 channel, energy_a, energy_b; struct iwl_mvm_rx_phy_data phy_data = { + .info_type = le32_get_bits(desc->phy_info[1], + IWL_RX_PHY_DATA1_INFO_TYPE_MASK), .d0 = desc->phy_info[0], - .info_type = IWL_RX_PHY_INFO_TYPE_NONE, + .d1 = desc->phy_info[1], }; if (unlikely(iwl_rx_packet_payload_len(pkt) < sizeof(*desc))) @@ -2015,10 +2017,6 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, energy_b = (rssi & RX_NO_DATA_CHAIN_B_MSK) >> RX_NO_DATA_CHAIN_B_POS; channel = (rssi & RX_NO_DATA_CHANNEL_MSK) >> RX_NO_DATA_CHANNEL_POS; - phy_data.info_type = - le32_get_bits(desc->phy_info[1], - IWL_RX_PHY_DATA1_INFO_TYPE_MASK); - /* Dont use dev_alloc_skb(), we'll have enough headroom once * ieee80211_hdr pulled. */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 5a0696c44f6d..0368b7101222 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2020 Intel Corporation + * Copyright (C) 2012-2014, 2018-2021 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -2327,9 +2327,9 @@ static int iwl_mvm_scan_umac_v12(struct iwl_mvm *mvm, struct ieee80211_vif *vif, &scan_p->general_params, gen_flags); - ret = iwl_mvm_fill_scan_sched_params(params, - scan_p->periodic_params.schedule, - &scan_p->periodic_params.delay); + ret = iwl_mvm_fill_scan_sched_params(params, + scan_p->periodic_params.schedule, + &scan_p->periodic_params.delay); if (ret) return ret; @@ -2362,9 +2362,9 @@ static int iwl_mvm_scan_umac_v14(struct iwl_mvm *mvm, struct ieee80211_vif *vif, &scan_p->general_params, gen_flags); - ret = iwl_mvm_fill_scan_sched_params(params, - scan_p->periodic_params.schedule, - &scan_p->periodic_params.delay); + ret = iwl_mvm_fill_scan_sched_params(params, + scan_p->periodic_params.schedule, + &scan_p->periodic_params.delay); if (ret) return ret; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index f618368eda83..9c45a64c5009 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -3794,8 +3794,12 @@ void iwl_mvm_sta_modify_disable_tx_ap(struct iwl_mvm *mvm, mvm_sta->disable_tx = disable; - /* Tell mac80211 to start/stop queuing tx for this station */ - ieee80211_sta_block_awake(mvm->hw, sta, disable); + /* + * If sta PS state is handled by mac80211, tell it to start/stop + * queuing tx for this station. + */ + if (!ieee80211_hw_check(mvm->hw, AP_LINK_PS)) + ieee80211_sta_block_awake(mvm->hw, sta, disable); iwl_mvm_sta_modify_disable_tx(mvm, mvm_sta, disable); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 83342a6a6d5b..d3307a11fcac 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -31,6 +31,13 @@ void iwl_mvm_te_clear_data(struct iwl_mvm *mvm, return; list_del(&te_data->list); + + /* + * the list is only used for AUX ROC events so make sure it is always + * initialized + */ + INIT_LIST_HEAD(&te_data->list); + te_data->running = false; te_data->uid = 0; te_data->id = TE_MAX; @@ -310,6 +317,8 @@ static void iwl_mvm_te_handle_notif(struct iwl_mvm *mvm, * and know the dtim period. */ iwl_mvm_te_check_disconnect(mvm, te_data->vif, + !te_data->vif->bss_conf.assoc ? + "Not associated and the time event is over already..." : "No beacon heard and the time event is over already..."); break; default: @@ -607,14 +616,15 @@ void iwl_mvm_protect_session(struct iwl_mvm *mvm, } static void iwl_mvm_cancel_session_protection(struct iwl_mvm *mvm, - struct iwl_mvm_vif *mvmvif) + struct iwl_mvm_vif *mvmvif, + u32 id) { struct iwl_mvm_session_prot_cmd cmd = { .id_and_color = cpu_to_le32(FW_CMD_ID_AND_COLOR(mvmvif->id, mvmvif->color)), .action = cpu_to_le32(FW_CTXT_ACTION_REMOVE), - .conf_id = cpu_to_le32(mvmvif->time_event_data.id), + .conf_id = cpu_to_le32(id), }; int ret; @@ -632,6 +642,12 @@ static bool __iwl_mvm_remove_time_event(struct iwl_mvm *mvm, { u32 id; struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(te_data->vif); + enum nl80211_iftype iftype; + + if (!te_data->vif) + return false; + + iftype = te_data->vif->type; /* * It is possible that by the time we got to this point the time @@ -656,8 +672,8 @@ static bool __iwl_mvm_remove_time_event(struct iwl_mvm *mvm, IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD)) { if (mvmvif && id < SESSION_PROTECT_CONF_MAX_ID) { /* Session protection is still ongoing. Cancel it */ - iwl_mvm_cancel_session_protection(mvm, mvmvif); - if (te_data->vif->type == NL80211_IFTYPE_P2P_DEVICE) { + iwl_mvm_cancel_session_protection(mvm, mvmvif, id); + if (iftype == NL80211_IFTYPE_P2P_DEVICE) { set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status); iwl_mvm_roc_finished(mvm); } @@ -738,11 +754,6 @@ void iwl_mvm_remove_time_event(struct iwl_mvm *mvm, IWL_ERR(mvm, "Couldn't remove the time event\n"); } -/* - * When the firmware supports the session protection API, - * this is not needed since it'll automatically remove the - * session protection after association + beacon reception. - */ void iwl_mvm_stop_session_protection(struct iwl_mvm *mvm, struct ieee80211_vif *vif) { @@ -756,7 +767,15 @@ void iwl_mvm_stop_session_protection(struct iwl_mvm *mvm, id = te_data->id; spin_unlock_bh(&mvm->time_event_lock); - if (id != TE_BSS_STA_AGGRESSIVE_ASSOC) { + if (fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD)) { + if (id != SESSION_PROTECT_CONF_ASSOC) { + IWL_DEBUG_TE(mvm, + "don't remove session protection id=%u\n", + id); + return; + } + } else if (id != TE_BSS_STA_AGGRESSIVE_ASSOC) { IWL_DEBUG_TE(mvm, "don't remove TE with id=%u (not session protection)\n", id); @@ -808,6 +827,8 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm, * and know the dtim period. */ iwl_mvm_te_check_disconnect(mvm, vif, + !vif->bss_conf.assoc ? + "Not associated and the session protection is over already..." : "No beacon heard and the session protection is over already..."); spin_lock_bh(&mvm->time_event_lock); iwl_mvm_te_clear_data(mvm, te_data); @@ -981,7 +1002,8 @@ void iwl_mvm_stop_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif) mvmvif = iwl_mvm_vif_from_mac80211(vif); if (vif->type == NL80211_IFTYPE_P2P_DEVICE) { - iwl_mvm_cancel_session_protection(mvm, mvmvif); + iwl_mvm_cancel_session_protection(mvm, mvmvif, + mvmvif->time_event_data.id); set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status); } else { iwl_mvm_remove_aux_roc_te(mvm, mvmvif, @@ -1141,6 +1163,7 @@ void iwl_mvm_schedule_session_protection(struct iwl_mvm *mvm, iwl_mvm_te_clear_data(mvm, te_data); te_data->duration = le32_to_cpu(cmd.duration_tu); + te_data->vif = vif; spin_unlock_bh(&mvm->time_event_lock); IWL_DEBUG_TE(mvm, "Add new session protection, duration %d TU\n", diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 1ad621d13ad3..0a13c2bda2ee 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1032,6 +1032,9 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, if (WARN_ON_ONCE(mvmsta->sta_id == IWL_MVM_INVALID_STA)) return -1; + if (unlikely(ieee80211_is_any_nullfunc(fc)) && sta->he_cap.has_he) + return -1; + if (unlikely(ieee80211_is_probe_resp(fc))) iwl_mvm_probe_resp_set_noa(mvm, skb); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c index c566be99a4c7..4a3d2971a98b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2020 Intel Corporation + * Copyright (C) 2012-2014, 2018-2021 Intel Corporation * Copyright (C) 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH */ @@ -238,316 +238,6 @@ u8 iwl_mvm_next_antenna(struct iwl_mvm *mvm, u8 valid, u8 last_idx) return last_idx; } -/* - * Note: This structure is read from the device with IO accesses, - * and the reading already does the endian conversion. As it is - * read with u32-sized accesses, any members with a different size - * need to be ordered correctly though! - */ -struct iwl_error_event_table_v1 { - u32 valid; /* (nonzero) valid, (0) log is empty */ - u32 error_id; /* type of error */ - u32 pc; /* program counter */ - u32 blink1; /* branch link */ - u32 blink2; /* branch link */ - u32 ilink1; /* interrupt link */ - u32 ilink2; /* interrupt link */ - u32 data1; /* error-specific data */ - u32 data2; /* error-specific data */ - u32 data3; /* error-specific data */ - u32 bcon_time; /* beacon timer */ - u32 tsf_low; /* network timestamp function timer */ - u32 tsf_hi; /* network timestamp function timer */ - u32 gp1; /* GP1 timer register */ - u32 gp2; /* GP2 timer register */ - u32 gp3; /* GP3 timer register */ - u32 ucode_ver; /* uCode version */ - u32 hw_ver; /* HW Silicon version */ - u32 brd_ver; /* HW board version */ - u32 log_pc; /* log program counter */ - u32 frame_ptr; /* frame pointer */ - u32 stack_ptr; /* stack pointer */ - u32 hcmd; /* last host command header */ - u32 isr0; /* isr status register LMPM_NIC_ISR0: - * rxtx_flag */ - u32 isr1; /* isr status register LMPM_NIC_ISR1: - * host_flag */ - u32 isr2; /* isr status register LMPM_NIC_ISR2: - * enc_flag */ - u32 isr3; /* isr status register LMPM_NIC_ISR3: - * time_flag */ - u32 isr4; /* isr status register LMPM_NIC_ISR4: - * wico interrupt */ - u32 isr_pref; /* isr status register LMPM_NIC_PREF_STAT */ - u32 wait_event; /* wait event() caller address */ - u32 l2p_control; /* L2pControlField */ - u32 l2p_duration; /* L2pDurationField */ - u32 l2p_mhvalid; /* L2pMhValidBits */ - u32 l2p_addr_match; /* L2pAddrMatchStat */ - u32 lmpm_pmg_sel; /* indicate which clocks are turned on - * (LMPM_PMG_SEL) */ - u32 u_timestamp; /* indicate when the date and time of the - * compilation */ - u32 flow_handler; /* FH read/write pointers, RX credit */ -} __packed /* LOG_ERROR_TABLE_API_S_VER_1 */; - -struct iwl_error_event_table { - u32 valid; /* (nonzero) valid, (0) log is empty */ - u32 error_id; /* type of error */ - u32 trm_hw_status0; /* TRM HW status */ - u32 trm_hw_status1; /* TRM HW status */ - u32 blink2; /* branch link */ - u32 ilink1; /* interrupt link */ - u32 ilink2; /* interrupt link */ - u32 data1; /* error-specific data */ - u32 data2; /* error-specific data */ - u32 data3; /* error-specific data */ - u32 bcon_time; /* beacon timer */ - u32 tsf_low; /* network timestamp function timer */ - u32 tsf_hi; /* network timestamp function timer */ - u32 gp1; /* GP1 timer register */ - u32 gp2; /* GP2 timer register */ - u32 fw_rev_type; /* firmware revision type */ - u32 major; /* uCode version major */ - u32 minor; /* uCode version minor */ - u32 hw_ver; /* HW Silicon version */ - u32 brd_ver; /* HW board version */ - u32 log_pc; /* log program counter */ - u32 frame_ptr; /* frame pointer */ - u32 stack_ptr; /* stack pointer */ - u32 hcmd; /* last host command header */ - u32 isr0; /* isr status register LMPM_NIC_ISR0: - * rxtx_flag */ - u32 isr1; /* isr status register LMPM_NIC_ISR1: - * host_flag */ - u32 isr2; /* isr status register LMPM_NIC_ISR2: - * enc_flag */ - u32 isr3; /* isr status register LMPM_NIC_ISR3: - * time_flag */ - u32 isr4; /* isr status register LMPM_NIC_ISR4: - * wico interrupt */ - u32 last_cmd_id; /* last HCMD id handled by the firmware */ - u32 wait_event; /* wait event() caller address */ - u32 l2p_control; /* L2pControlField */ - u32 l2p_duration; /* L2pDurationField */ - u32 l2p_mhvalid; /* L2pMhValidBits */ - u32 l2p_addr_match; /* L2pAddrMatchStat */ - u32 lmpm_pmg_sel; /* indicate which clocks are turned on - * (LMPM_PMG_SEL) */ - u32 u_timestamp; /* indicate when the date and time of the - * compilation */ - u32 flow_handler; /* FH read/write pointers, RX credit */ -} __packed /* LOG_ERROR_TABLE_API_S_VER_3 */; - -/* - * UMAC error struct - relevant starting from family 8000 chip. - * Note: This structure is read from the device with IO accesses, - * and the reading already does the endian conversion. As it is - * read with u32-sized accesses, any members with a different size - * need to be ordered correctly though! - */ -struct iwl_umac_error_event_table { - u32 valid; /* (nonzero) valid, (0) log is empty */ - u32 error_id; /* type of error */ - u32 blink1; /* branch link */ - u32 blink2; /* branch link */ - u32 ilink1; /* interrupt link */ - u32 ilink2; /* interrupt link */ - u32 data1; /* error-specific data */ - u32 data2; /* error-specific data */ - u32 data3; /* error-specific data */ - u32 umac_major; - u32 umac_minor; - u32 frame_pointer; /* core register 27*/ - u32 stack_pointer; /* core register 28 */ - u32 cmd_header; /* latest host cmd sent to UMAC */ - u32 nic_isr_pref; /* ISR status register */ -} __packed; - -#define ERROR_START_OFFSET (1 * sizeof(u32)) -#define ERROR_ELEM_SIZE (7 * sizeof(u32)) - -static void iwl_mvm_dump_umac_error_log(struct iwl_mvm *mvm) -{ - struct iwl_trans *trans = mvm->trans; - struct iwl_umac_error_event_table table = {}; - u32 base = mvm->trans->dbg.umac_error_event_table; - - if (!base && - !(mvm->trans->dbg.error_event_table_tlv_status & - IWL_ERROR_EVENT_TABLE_UMAC)) - return; - - iwl_trans_read_mem_bytes(trans, base, &table, sizeof(table)); - - if (table.valid) - mvm->fwrt.dump.umac_err_id = table.error_id; - - if (ERROR_START_OFFSET <= table.valid * ERROR_ELEM_SIZE) { - IWL_ERR(trans, "Start IWL Error Log Dump:\n"); - IWL_ERR(trans, "Status: 0x%08lX, count: %d\n", - mvm->status, table.valid); - } - - IWL_ERR(mvm, "0x%08X | %s\n", table.error_id, - iwl_fw_lookup_assert_desc(table.error_id)); - IWL_ERR(mvm, "0x%08X | umac branchlink1\n", table.blink1); - IWL_ERR(mvm, "0x%08X | umac branchlink2\n", table.blink2); - IWL_ERR(mvm, "0x%08X | umac interruptlink1\n", table.ilink1); - IWL_ERR(mvm, "0x%08X | umac interruptlink2\n", table.ilink2); - IWL_ERR(mvm, "0x%08X | umac data1\n", table.data1); - IWL_ERR(mvm, "0x%08X | umac data2\n", table.data2); - IWL_ERR(mvm, "0x%08X | umac data3\n", table.data3); - IWL_ERR(mvm, "0x%08X | umac major\n", table.umac_major); - IWL_ERR(mvm, "0x%08X | umac minor\n", table.umac_minor); - IWL_ERR(mvm, "0x%08X | frame pointer\n", table.frame_pointer); - IWL_ERR(mvm, "0x%08X | stack pointer\n", table.stack_pointer); - IWL_ERR(mvm, "0x%08X | last host cmd\n", table.cmd_header); - IWL_ERR(mvm, "0x%08X | isr status reg\n", table.nic_isr_pref); -} - -static void iwl_mvm_dump_lmac_error_log(struct iwl_mvm *mvm, u8 lmac_num) -{ - struct iwl_trans *trans = mvm->trans; - struct iwl_error_event_table table = {}; - u32 val, base = mvm->trans->dbg.lmac_error_event_table[lmac_num]; - - if (mvm->fwrt.cur_fw_img == IWL_UCODE_INIT) { - if (!base) - base = mvm->fw->init_errlog_ptr; - } else { - if (!base) - base = mvm->fw->inst_errlog_ptr; - } - - if (base < 0x400000) { - IWL_ERR(mvm, - "Not valid error log pointer 0x%08X for %s uCode\n", - base, - (mvm->fwrt.cur_fw_img == IWL_UCODE_INIT) - ? "Init" : "RT"); - return; - } - - /* check if there is a HW error */ - val = iwl_trans_read_mem32(trans, base); - if (((val & ~0xf) == 0xa5a5a5a0) || ((val & ~0xf) == 0x5a5a5a50)) { - int err; - - IWL_ERR(trans, "HW error, resetting before reading\n"); - - /* reset the device */ - iwl_trans_sw_reset(trans); - - err = iwl_finish_nic_init(trans, trans->trans_cfg); - if (err) - return; - } - - iwl_trans_read_mem_bytes(trans, base, &table, sizeof(table)); - - if (table.valid) - mvm->fwrt.dump.lmac_err_id[lmac_num] = table.error_id; - - if (ERROR_START_OFFSET <= table.valid * ERROR_ELEM_SIZE) { - IWL_ERR(trans, "Start IWL Error Log Dump:\n"); - IWL_ERR(trans, "Status: 0x%08lX, count: %d\n", - mvm->status, table.valid); - } - - /* Do not change this output - scripts rely on it */ - - IWL_ERR(mvm, "Loaded firmware version: %s\n", mvm->fw->fw_version); - - IWL_ERR(mvm, "0x%08X | %-28s\n", table.error_id, - iwl_fw_lookup_assert_desc(table.error_id)); - IWL_ERR(mvm, "0x%08X | trm_hw_status0\n", table.trm_hw_status0); - IWL_ERR(mvm, "0x%08X | trm_hw_status1\n", table.trm_hw_status1); - IWL_ERR(mvm, "0x%08X | branchlink2\n", table.blink2); - IWL_ERR(mvm, "0x%08X | interruptlink1\n", table.ilink1); - IWL_ERR(mvm, "0x%08X | interruptlink2\n", table.ilink2); - IWL_ERR(mvm, "0x%08X | data1\n", table.data1); - IWL_ERR(mvm, "0x%08X | data2\n", table.data2); - IWL_ERR(mvm, "0x%08X | data3\n", table.data3); - IWL_ERR(mvm, "0x%08X | beacon time\n", table.bcon_time); - IWL_ERR(mvm, "0x%08X | tsf low\n", table.tsf_low); - IWL_ERR(mvm, "0x%08X | tsf hi\n", table.tsf_hi); - IWL_ERR(mvm, "0x%08X | time gp1\n", table.gp1); - IWL_ERR(mvm, "0x%08X | time gp2\n", table.gp2); - IWL_ERR(mvm, "0x%08X | uCode revision type\n", table.fw_rev_type); - IWL_ERR(mvm, "0x%08X | uCode version major\n", table.major); - IWL_ERR(mvm, "0x%08X | uCode version minor\n", table.minor); - IWL_ERR(mvm, "0x%08X | hw version\n", table.hw_ver); - IWL_ERR(mvm, "0x%08X | board version\n", table.brd_ver); - IWL_ERR(mvm, "0x%08X | hcmd\n", table.hcmd); - IWL_ERR(mvm, "0x%08X | isr0\n", table.isr0); - IWL_ERR(mvm, "0x%08X | isr1\n", table.isr1); - IWL_ERR(mvm, "0x%08X | isr2\n", table.isr2); - IWL_ERR(mvm, "0x%08X | isr3\n", table.isr3); - IWL_ERR(mvm, "0x%08X | isr4\n", table.isr4); - IWL_ERR(mvm, "0x%08X | last cmd Id\n", table.last_cmd_id); - IWL_ERR(mvm, "0x%08X | wait_event\n", table.wait_event); - IWL_ERR(mvm, "0x%08X | l2p_control\n", table.l2p_control); - IWL_ERR(mvm, "0x%08X | l2p_duration\n", table.l2p_duration); - IWL_ERR(mvm, "0x%08X | l2p_mhvalid\n", table.l2p_mhvalid); - IWL_ERR(mvm, "0x%08X | l2p_addr_match\n", table.l2p_addr_match); - IWL_ERR(mvm, "0x%08X | lmpm_pmg_sel\n", table.lmpm_pmg_sel); - IWL_ERR(mvm, "0x%08X | timestamp\n", table.u_timestamp); - IWL_ERR(mvm, "0x%08X | flow_handler\n", table.flow_handler); -} - -static void iwl_mvm_dump_iml_error_log(struct iwl_mvm *mvm) -{ - struct iwl_trans *trans = mvm->trans; - u32 error, data1; - - if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000) { - error = UMAG_SB_CPU_2_STATUS; - data1 = UMAG_SB_CPU_1_STATUS; - } else if (mvm->trans->trans_cfg->device_family >= - IWL_DEVICE_FAMILY_8000) { - error = SB_CPU_2_STATUS; - data1 = SB_CPU_1_STATUS; - } else { - return; - } - - error = iwl_read_umac_prph(trans, UMAG_SB_CPU_2_STATUS); - - IWL_ERR(trans, "IML/ROM dump:\n"); - - if (error & 0xFFFF0000) - IWL_ERR(trans, "0x%04X | IML/ROM SYSASSERT\n", error >> 16); - - IWL_ERR(mvm, "0x%08X | IML/ROM error/state\n", error); - IWL_ERR(mvm, "0x%08X | IML/ROM data1\n", - iwl_read_umac_prph(trans, data1)); - - if (mvm->trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_22000) - IWL_ERR(mvm, "0x%08X | IML/ROM WFPM_AUTH_KEY_0\n", - iwl_read_umac_prph(trans, SB_MODIFY_CFG_FLAG)); -} - -void iwl_mvm_dump_nic_error_log(struct iwl_mvm *mvm) -{ - if (!test_bit(STATUS_DEVICE_ENABLED, &mvm->trans->status)) { - IWL_ERR(mvm, - "DEVICE_ENABLED bit is not set. Aborting dump.\n"); - return; - } - - iwl_mvm_dump_lmac_error_log(mvm, 0); - - if (mvm->trans->dbg.lmac_error_event_table[1]) - iwl_mvm_dump_lmac_error_log(mvm, 1); - - iwl_mvm_dump_umac_error_log(mvm); - - iwl_mvm_dump_iml_error_log(mvm); - - iwl_fw_error_print_fseq_regs(&mvm->fwrt); -} - int iwl_mvm_reconfig_scd(struct iwl_mvm *mvm, int queue, int fifo, int sta_id, int tid, int frame_limit, u16 ssn) { @@ -621,7 +311,7 @@ void iwl_mvm_update_smps(struct iwl_mvm *mvm, struct ieee80211_vif *vif, enum ieee80211_smps_mode smps_request) { struct iwl_mvm_vif *mvmvif; - enum ieee80211_smps_mode smps_mode; + enum ieee80211_smps_mode smps_mode = IEEE80211_SMPS_AUTOMATIC; int i; lockdep_assert_held(&mvm->mutex); @@ -630,10 +320,8 @@ void iwl_mvm_update_smps(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (num_of_ant(iwl_mvm_get_valid_rx_ant(mvm)) == 1) return; - if (vif->type == NL80211_IFTYPE_AP) - smps_mode = IEEE80211_SMPS_OFF; - else - smps_mode = IEEE80211_SMPS_AUTOMATIC; + if (vif->type != NL80211_IFTYPE_STATION) + return; mvmvif = iwl_mvm_vif_from_mac80211(vif); mvmvif->smps_requests[req_type] = smps_request; @@ -683,23 +371,37 @@ void iwl_mvm_accu_radio_stats(struct iwl_mvm *mvm) mvm->accu_radio_stats.on_time_scan += mvm->radio_stats.on_time_scan; } +struct iwl_mvm_diversity_iter_data { + struct iwl_mvm_phy_ctxt *ctxt; + bool result; +}; + static void iwl_mvm_diversity_iter(void *_data, u8 *mac, struct ieee80211_vif *vif) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - bool *result = _data; + struct iwl_mvm_diversity_iter_data *data = _data; int i; + if (mvmvif->phy_ctxt != data->ctxt) + return; + for (i = 0; i < NUM_IWL_MVM_SMPS_REQ; i++) { if (mvmvif->smps_requests[i] == IEEE80211_SMPS_STATIC || - mvmvif->smps_requests[i] == IEEE80211_SMPS_DYNAMIC) - *result = false; + mvmvif->smps_requests[i] == IEEE80211_SMPS_DYNAMIC) { + data->result = false; + break; + } } } -bool iwl_mvm_rx_diversity_allowed(struct iwl_mvm *mvm) +bool iwl_mvm_rx_diversity_allowed(struct iwl_mvm *mvm, + struct iwl_mvm_phy_ctxt *ctxt) { - bool result = true; + struct iwl_mvm_diversity_iter_data data = { + .ctxt = ctxt, + .result = true, + }; lockdep_assert_held(&mvm->mutex); @@ -711,9 +413,9 @@ bool iwl_mvm_rx_diversity_allowed(struct iwl_mvm *mvm) ieee80211_iterate_active_interfaces_atomic( mvm->hw, IEEE80211_IFACE_ITER_NORMAL, - iwl_mvm_diversity_iter, &result); + iwl_mvm_diversity_iter, &data); - return result; + return data.result; } void iwl_mvm_send_low_latency_cmd(struct iwl_mvm *mvm, @@ -1398,7 +1100,8 @@ u32 iwl_mvm_get_systime(struct iwl_mvm *mvm) return iwl_read_prph(mvm->trans, reg_addr); } -void iwl_mvm_get_sync_time(struct iwl_mvm *mvm, u32 *gp2, u64 *boottime) +void iwl_mvm_get_sync_time(struct iwl_mvm *mvm, int clock_type, + u32 *gp2, u64 *boottime, ktime_t *realtime) { bool ps_disabled; @@ -1412,7 +1115,11 @@ void iwl_mvm_get_sync_time(struct iwl_mvm *mvm, u32 *gp2, u64 *boottime) } *gp2 = iwl_mvm_get_systime(mvm); - *boottime = ktime_get_boottime_ns(); + + if (clock_type == CLOCK_BOOTTIME && boottime) + *boottime = ktime_get_boottime_ns(); + else if (clock_type == CLOCK_REALTIME && realtime) + *realtime = ktime_get_real(); if (!ps_disabled) { mvm->ps_disabled = ps_disabled; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c index cecc32e7dbe8..239a722cd79d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c @@ -79,7 +79,6 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, struct iwl_prph_scratch *prph_scratch; struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl; struct iwl_prph_info *prph_info; - void *iml_img; u32 control_flags = 0; int ret; int cmdq_size = max_t(u32, IWL_CMD_QUEUE_SIZE, @@ -138,8 +137,15 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, /* Allocate prph information * currently we don't assign to the prph info anything, but it would get - * assigned later */ - prph_info = dma_alloc_coherent(trans->dev, sizeof(*prph_info), + * assigned later + * + * We also use the second half of this page to give the device some + * dummy TR/CR tail pointers - which shouldn't be necessary as we don't + * use this, but the hardware still reads/writes there and we can't let + * it go do that with a NULL pointer. + */ + BUILD_BUG_ON(sizeof(*prph_info) > PAGE_SIZE / 2); + prph_info = dma_alloc_coherent(trans->dev, PAGE_SIZE, &trans_pcie->prph_info_dma_addr, GFP_KERNEL); if (!prph_info) { @@ -166,13 +172,9 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, ctxt_info_gen3->cr_head_idx_arr_base_addr = cpu_to_le64(trans_pcie->rxq->rb_stts_dma); ctxt_info_gen3->tr_tail_idx_arr_base_addr = - cpu_to_le64(trans_pcie->rxq->tr_tail_dma); + cpu_to_le64(trans_pcie->prph_info_dma_addr + PAGE_SIZE / 2); ctxt_info_gen3->cr_tail_idx_arr_base_addr = - cpu_to_le64(trans_pcie->rxq->cr_tail_dma); - ctxt_info_gen3->cr_idx_arr_size = - cpu_to_le16(IWL_NUM_OF_COMPLETION_RINGS); - ctxt_info_gen3->tr_idx_arr_size = - cpu_to_le16(IWL_NUM_OF_TRANSFER_RINGS); + cpu_to_le64(trans_pcie->prph_info_dma_addr + 3 * PAGE_SIZE / 4); ctxt_info_gen3->mtr_base_addr = cpu_to_le64(trans->txqs.txq[trans->txqs.cmd.q_id]->dma_addr); ctxt_info_gen3->mcr_base_addr = @@ -187,14 +189,15 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, trans_pcie->prph_scratch = prph_scratch; /* Allocate IML */ - iml_img = dma_alloc_coherent(trans->dev, trans->iml_len, - &trans_pcie->iml_dma_addr, GFP_KERNEL); - if (!iml_img) { + trans_pcie->iml = dma_alloc_coherent(trans->dev, trans->iml_len, + &trans_pcie->iml_dma_addr, + GFP_KERNEL); + if (!trans_pcie->iml) { ret = -ENOMEM; goto err_free_ctxt_info; } - memcpy(iml_img, trans->iml, trans->iml_len); + memcpy(trans_pcie->iml, trans->iml, trans->iml_len); iwl_enable_fw_load_int_ctx_info(trans); @@ -216,10 +219,8 @@ err_free_ctxt_info: trans_pcie->ctxt_info_dma_addr); trans_pcie->ctxt_info_gen3 = NULL; err_free_prph_info: - dma_free_coherent(trans->dev, - sizeof(*prph_info), - prph_info, - trans_pcie->prph_info_dma_addr); + dma_free_coherent(trans->dev, PAGE_SIZE, prph_info, + trans_pcie->prph_info_dma_addr); err_free_prph_scratch: dma_free_coherent(trans->dev, @@ -230,29 +231,40 @@ err_free_prph_scratch: } -void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans) +void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans, bool alive) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); + if (trans_pcie->iml) { + dma_free_coherent(trans->dev, trans->iml_len, trans_pcie->iml, + trans_pcie->iml_dma_addr); + trans_pcie->iml_dma_addr = 0; + trans_pcie->iml = NULL; + } + + iwl_pcie_ctxt_info_free_fw_img(trans); + + if (alive) + return; + if (!trans_pcie->ctxt_info_gen3) return; + /* ctxt_info_gen3 and prph_scratch are still needed for PNVM load */ dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info_gen3), trans_pcie->ctxt_info_gen3, trans_pcie->ctxt_info_dma_addr); trans_pcie->ctxt_info_dma_addr = 0; trans_pcie->ctxt_info_gen3 = NULL; - iwl_pcie_ctxt_info_free_fw_img(trans); - dma_free_coherent(trans->dev, sizeof(*trans_pcie->prph_scratch), trans_pcie->prph_scratch, trans_pcie->prph_scratch_dma_addr); trans_pcie->prph_scratch_dma_addr = 0; trans_pcie->prph_scratch = NULL; - dma_free_coherent(trans->dev, sizeof(*trans_pcie->prph_info), - trans_pcie->prph_info, + /* this is needed for the entire lifetime */ + dma_free_coherent(trans->dev, PAGE_SIZE, trans_pcie->prph_info, trans_pcie->prph_info_dma_addr); trans_pcie->prph_info_dma_addr = 0; trans_pcie->prph_info = NULL; @@ -290,3 +302,37 @@ int iwl_trans_pcie_ctx_info_gen3_set_pnvm(struct iwl_trans *trans, return 0; } + +int iwl_trans_pcie_ctx_info_gen3_set_reduce_power(struct iwl_trans *trans, + const void *data, u32 len) +{ + struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); + struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl = + &trans_pcie->prph_scratch->ctrl_cfg; + int ret; + + if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210) + return 0; + + /* only allocate the DRAM if not allocated yet */ + if (!trans->reduce_power_loaded) { + if (WARN_ON(prph_sc_ctrl->reduce_power_cfg.size)) + return -EBUSY; + + ret = iwl_pcie_ctxt_info_alloc_dma(trans, data, len, + &trans_pcie->reduce_power_dram); + if (ret < 0) { + IWL_DEBUG_FW(trans, + "Failed to allocate reduce power DMA %d.\n", + ret); + return ret; + } + } + + prph_sc_ctrl->reduce_power_cfg.base_addr = + cpu_to_le64(trans_pcie->reduce_power_dram.physical); + prph_sc_ctrl->reduce_power_cfg.size = + cpu_to_le32(trans_pcie->reduce_power_dram.size); + + return 0; +} diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index d94bd8d732e9..16baee3d52ae 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -532,6 +532,8 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_DEV_INFO(0x31DC, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_name), IWL_DEV_INFO(0xA370, 0x1551, iwl9560_2ac_cfg_soc, iwl9560_killer_1550s_name), IWL_DEV_INFO(0xA370, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_name), + IWL_DEV_INFO(0x51F0, 0x1552, iwl9560_2ac_cfg_soc, iwl9560_killer_1550s_160_name), + IWL_DEV_INFO(0x51F0, 0x1551, iwl9560_2ac_cfg_soc, iwl9560_killer_1550i_160_name), IWL_DEV_INFO(0x271C, 0x0214, iwl9260_2ac_cfg, iwl9260_1_name), @@ -1029,6 +1031,11 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_CFG_RF_TYPE_MR, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB, iwl_cfg_ma_a0_mr_a0, iwl_ax221_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, + IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB, + iwl_cfg_ma_a0_fm_a0, iwl_ax231_name), _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_MAC_TYPE_SNJ, IWL_CFG_ANY, IWL_CFG_RF_TYPE_MR, IWL_CFG_ANY, @@ -1209,14 +1216,14 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (cfg == &iwlax210_2ax_cfg_so_hr_a0) { if (iwl_trans->hw_rev == CSR_HW_REV_TYPE_TY) { iwl_trans->cfg = &iwlax210_2ax_cfg_ty_gf_a0; - } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(iwl_trans->hw_rf_id) == - CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_JF)) { + } else if (CSR_HW_RFID_TYPE(iwl_trans->hw_rf_id) == + CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_JF)) { iwl_trans->cfg = &iwlax210_2ax_cfg_so_jf_b0; - } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(iwl_trans->hw_rf_id) == - CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_GF)) { + } else if (CSR_HW_RFID_TYPE(iwl_trans->hw_rf_id) == + CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_GF)) { iwl_trans->cfg = &iwlax211_2ax_cfg_so_gf_a0; - } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(iwl_trans->hw_rf_id) == - CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_GF4)) { + } else if (CSR_HW_RFID_TYPE(iwl_trans->hw_rf_id) == + CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_GF4)) { iwl_trans->cfg = &iwlax411_2ax_cfg_so_gf4_a0; } } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index 76a512cd2e5c..cc550f6ef957 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2003-2015, 2018-2020 Intel Corporation + * Copyright (C) 2003-2015, 2018-2021 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -109,12 +109,8 @@ struct iwl_rx_completion_desc { * Address size is 32 bit in pre-9000 devices and 64 bit in 9000 devices. * In AX210 devices it is a pointer to a list of iwl_rx_transfer_desc's * @bd_dma: bus address of buffer of receive buffer descriptors (rbd) - * @ubd: driver's pointer to buffer of used receive buffer descriptors (rbd) - * @ubd_dma: physical address of buffer of used receive buffer descriptors (rbd) - * @tr_tail: driver's pointer to the transmission ring tail buffer - * @tr_tail_dma: physical address of the buffer for the transmission ring tail - * @cr_tail: driver's pointer to the completion ring tail buffer - * @cr_tail_dma: physical address of the buffer for the completion ring tail + * @used_bd: driver's pointer to buffer of used receive buffer descriptors (rbd) + * @used_bd_dma: physical address of buffer of used receive buffer descriptors (rbd) * @read: Shared index to newest available Rx buffer * @write: Shared index to oldest written Rx packet * @free_count: Number of pre-allocated buffers in rx_free @@ -142,10 +138,6 @@ struct iwl_rxq { struct iwl_rx_completion_desc *cd; }; dma_addr_t used_bd_dma; - __le16 *tr_tail; - dma_addr_t tr_tail_dma; - __le16 *cr_tail; - dma_addr_t cr_tail_dma; u32 read; u32 write; u32 free_count; @@ -279,6 +271,8 @@ struct cont_rec { * Context information addresses will be taken from here. * This is driver's local copy for keeping track of size and * count for allocating and freeing the memory. + * @iml: image loader image virtual address + * @iml_dma_addr: image loader image DMA address * @trans: pointer to the generic transport area * @scd_base_addr: scheduler sram base address in SRAM * @kw: keep warm address @@ -317,6 +311,7 @@ struct cont_rec { * @alloc_page_lock: spinlock for the page allocator * @alloc_page: allocated page to still use parts of * @alloc_page_used: how much of the allocated page was already used (bytes) + * @rf_name: name/version of the CRF, if any */ struct iwl_trans_pcie { struct iwl_rxq *rxq; @@ -329,6 +324,7 @@ struct iwl_trans_pcie { }; struct iwl_prph_info *prph_info; struct iwl_prph_scratch *prph_scratch; + void *iml; dma_addr_t ctxt_info_dma_addr; dma_addr_t prph_info_dma_addr; dma_addr_t prph_scratch_dma_addr; @@ -353,6 +349,7 @@ struct iwl_trans_pcie { struct iwl_dma_ptr kw; struct iwl_dram_data pnvm_dram; + struct iwl_dram_data reduce_power_dram; struct iwl_txq *txq_memory; @@ -409,6 +406,8 @@ struct iwl_trans_pcie { bool fw_reset_handshake; bool fw_reset_done; wait_queue_head_t fw_reset_waitq; + + char rf_name[32]; }; static inline struct iwl_trans_pcie * @@ -530,9 +529,6 @@ static inline void _iwl_disable_interrupts(struct iwl_trans *trans) IWL_DEBUG_ISR(trans, "Disabled interrupts\n"); } -#define IWL_NUM_OF_COMPLETION_RINGS 31 -#define IWL_NUM_OF_TRANSFER_RINGS 527 - static inline int iwl_pcie_get_num_sections(const struct fw_img *fw, int start) { diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index fb8491412be4..4f6f4b2720f0 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -663,7 +663,6 @@ static int iwl_pcie_free_bd_size(struct iwl_trans *trans, bool use_rx_td) static void iwl_pcie_free_rxq_dma(struct iwl_trans *trans, struct iwl_rxq *rxq) { - struct device *dev = trans->dev; bool use_rx_td = (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210); int free_size = iwl_pcie_free_bd_size(trans, use_rx_td); @@ -685,21 +684,6 @@ static void iwl_pcie_free_rxq_dma(struct iwl_trans *trans, rxq->used_bd, rxq->used_bd_dma); rxq->used_bd_dma = 0; rxq->used_bd = NULL; - - if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210) - return; - - if (rxq->tr_tail) - dma_free_coherent(dev, sizeof(__le16), - rxq->tr_tail, rxq->tr_tail_dma); - rxq->tr_tail_dma = 0; - rxq->tr_tail = NULL; - - if (rxq->cr_tail) - dma_free_coherent(dev, sizeof(__le16), - rxq->cr_tail, rxq->cr_tail_dma); - rxq->cr_tail_dma = 0; - rxq->cr_tail = NULL; } static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans, @@ -744,21 +728,6 @@ static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans, rxq->rb_stts_dma = trans_pcie->base_rb_stts_dma + rxq->id * rb_stts_size; - if (!use_rx_td) - return 0; - - /* Allocate the driver's pointer to TR tail */ - rxq->tr_tail = dma_alloc_coherent(dev, sizeof(__le16), - &rxq->tr_tail_dma, GFP_KERNEL); - if (!rxq->tr_tail) - goto err; - - /* Allocate the driver's pointer to CR tail */ - rxq->cr_tail = dma_alloc_coherent(dev, sizeof(__le16), - &rxq->cr_tail_dma, GFP_KERNEL); - if (!rxq->cr_tail) - goto err; - return 0; err: @@ -1590,9 +1559,6 @@ restart: out: /* Backtrack one entry */ rxq->read = i; - /* update cr tail with the rxq read pointer */ - if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) - *rxq->cr_tail = cpu_to_le16(r); spin_unlock(&rxq->lock); /* diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c index 1bcd36e9e008..a34009357227 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c @@ -149,7 +149,7 @@ void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans) iwl_pcie_ctxt_info_free_paging(trans); if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) - iwl_pcie_ctxt_info_gen3_free(trans); + iwl_pcie_ctxt_info_gen3_free(trans, false); else iwl_pcie_ctxt_info_free(trans); @@ -240,6 +240,75 @@ static int iwl_pcie_gen2_nic_init(struct iwl_trans *trans) return 0; } +static void iwl_pcie_get_rf_name(struct iwl_trans *trans) +{ + struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); + char *buf = trans_pcie->rf_name; + size_t buflen = sizeof(trans_pcie->rf_name); + size_t pos; + u32 version; + + if (buf[0]) + return; + + switch (CSR_HW_RFID_TYPE(trans->hw_rf_id)) { + case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_JF): + pos = scnprintf(buf, buflen, "JF"); + break; + case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_GF): + pos = scnprintf(buf, buflen, "GF"); + break; + case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_GF4): + pos = scnprintf(buf, buflen, "GF4"); + break; + case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_HR): + pos = scnprintf(buf, buflen, "HR"); + break; + case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_HR1): + pos = scnprintf(buf, buflen, "HR1"); + break; + case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_HRCDB): + pos = scnprintf(buf, buflen, "HRCDB"); + break; + default: + return; + } + + switch (CSR_HW_RFID_TYPE(trans->hw_rf_id)) { + case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_HR): + case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_HR1): + case CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_HRCDB): + version = iwl_read_prph(trans, CNVI_MBOX_C); + switch (version) { + case 0x20000: + pos += scnprintf(buf + pos, buflen - pos, " B3"); + break; + case 0x120000: + pos += scnprintf(buf + pos, buflen - pos, " B5"); + break; + default: + pos += scnprintf(buf + pos, buflen - pos, + " (0x%x)", version); + break; + } + break; + default: + break; + } + + pos += scnprintf(buf + pos, buflen - pos, ", rfid=0x%x", + trans->hw_rf_id); + + IWL_INFO(trans, "Detected RF %s\n", buf); + + /* + * also add a \n for debugfs - need to do it after printing + * since our IWL_INFO machinery wants to see a static \n at + * the end of the string + */ + pos += scnprintf(buf + pos, buflen - pos, "\n"); +} + void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans, u32 scd_addr) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -254,7 +323,10 @@ void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans, u32 scd_addr) /* now that we got alive we can free the fw image & the context info. * paging memory cannot be freed included since FW will still use it */ - iwl_pcie_ctxt_info_free(trans); + if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) + iwl_pcie_ctxt_info_gen3_free(trans, true); + else + iwl_pcie_ctxt_info_free(trans); /* * Re-enable all the interrupts, including the RF-Kill one, now that @@ -263,6 +335,8 @@ void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans, u32 scd_addr) iwl_enable_interrupts(trans); mutex_lock(&trans_pcie->mutex); iwl_pcie_check_hw_rf_kill(trans); + + iwl_pcie_get_rf_name(trans); mutex_unlock(&trans_pcie->mutex); } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 239bc177a3e5..bee6b4574226 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -1648,7 +1648,7 @@ static void iwl_pcie_irq_set_affinity(struct iwl_trans *trans) if (ret) IWL_ERR(trans_pcie->trans, "Failed to set affinity mask for IRQ %d\n", - i); + trans_pcie->msix_entries[i].vector); } } @@ -1943,6 +1943,12 @@ void iwl_trans_pcie_free(struct iwl_trans *trans) trans_pcie->pnvm_dram.block, trans_pcie->pnvm_dram.physical); + if (trans_pcie->reduce_power_dram.size) + dma_free_coherent(trans->dev, + trans_pcie->reduce_power_dram.size, + trans_pcie->reduce_power_dram.block, + trans_pcie->reduce_power_dram.physical); + mutex_destroy(&trans_pcie->mutex); iwl_trans_free(trans); } @@ -2848,11 +2854,28 @@ static ssize_t iwl_dbgfs_monitor_data_read(struct file *file, return bytes_copied; } +static ssize_t iwl_dbgfs_rf_read(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct iwl_trans *trans = file->private_data; + struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); + + if (!trans_pcie->rf_name[0]) + return -ENODEV; + + return simple_read_from_buffer(user_buf, count, ppos, + trans_pcie->rf_name, + strlen(trans_pcie->rf_name)); +} + DEBUGFS_READ_WRITE_FILE_OPS(interrupt); DEBUGFS_READ_FILE_OPS(fh_reg); DEBUGFS_READ_FILE_OPS(rx_queue); DEBUGFS_WRITE_FILE_OPS(csr); DEBUGFS_READ_WRITE_FILE_OPS(rfkill); +DEBUGFS_READ_FILE_OPS(rf); + static const struct file_operations iwl_dbgfs_tx_queue_ops = { .owner = THIS_MODULE, .open = iwl_dbgfs_tx_queue_open, @@ -2879,6 +2902,7 @@ void iwl_trans_pcie_dbgfs_register(struct iwl_trans *trans) DEBUGFS_ADD_FILE(fh_reg, dir, 0400); DEBUGFS_ADD_FILE(rfkill, dir, 0600); DEBUGFS_ADD_FILE(monitor_data, dir, 0400); + DEBUGFS_ADD_FILE(rf, dir, 0400); } static void iwl_trans_pcie_debugfs_cleanup(struct iwl_trans *trans) @@ -3400,6 +3424,7 @@ static const struct iwl_trans_ops trans_ops_pcie_gen2 = { .wait_txq_empty = iwl_trans_pcie_wait_txq_empty, .rxq_dma_data = iwl_trans_pcie_rxq_dma_data, .set_pnvm = iwl_trans_pcie_ctx_info_gen3_set_pnvm, + .set_reduce_power = iwl_trans_pcie_ctx_info_gen3_set_reduce_power, #ifdef CONFIG_IWLWIFI_DEBUGFS .debugfs_cleanup = iwl_trans_pcie_debugfs_cleanup, #endif @@ -3413,6 +3438,7 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, struct iwl_trans *trans; int ret, addr_size; const struct iwl_trans_ops *ops = &trans_ops_pcie_gen2; + void __iomem * const *table; if (!cfg_trans->gen2) ops = &trans_ops_pcie; @@ -3485,9 +3511,16 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, goto out_no_pci; } - trans_pcie->hw_base = pcim_iomap_table(pdev)[0]; - if (!trans_pcie->hw_base) { + table = pcim_iomap_table(pdev); + if (!table) { dev_err(&pdev->dev, "pcim_iomap_table failed\n"); + ret = -ENOMEM; + goto out_no_pci; + } + + trans_pcie->hw_base = table[0]; + if (!trans_pcie->hw_base) { + dev_err(&pdev->dev, "couldn't find IO mem in first BAR\n"); ret = -ENODEV; goto out_no_pci; } diff --git a/drivers/net/wireless/intersil/orinoco/hw.c b/drivers/net/wireless/intersil/orinoco/hw.c index 2c7adb4be100..0aea35c9c11c 100644 --- a/drivers/net/wireless/intersil/orinoco/hw.c +++ b/drivers/net/wireless/intersil/orinoco/hw.c @@ -988,15 +988,18 @@ int __orinoco_hw_setup_enc(struct orinoco_private *priv) * tsc must be NULL or up to 8 bytes */ int __orinoco_hw_set_tkip_key(struct orinoco_private *priv, int key_idx, - int set_tx, const u8 *key, const u8 *rsc, - size_t rsc_len, const u8 *tsc, size_t tsc_len) + int set_tx, const u8 *key, size_t key_len, + const u8 *rsc, size_t rsc_len, + const u8 *tsc, size_t tsc_len) { struct { __le16 idx; u8 rsc[ORINOCO_SEQ_LEN]; - u8 key[TKIP_KEYLEN]; - u8 tx_mic[MIC_KEYLEN]; - u8 rx_mic[MIC_KEYLEN]; + struct { + u8 key[TKIP_KEYLEN]; + u8 tx_mic[MIC_KEYLEN]; + u8 rx_mic[MIC_KEYLEN]; + } tkip; u8 tsc[ORINOCO_SEQ_LEN]; } __packed buf; struct hermes *hw = &priv->hw; @@ -1011,8 +1014,9 @@ int __orinoco_hw_set_tkip_key(struct orinoco_private *priv, int key_idx, key_idx |= 0x8000; buf.idx = cpu_to_le16(key_idx); - memcpy(buf.key, key, - sizeof(buf.key) + sizeof(buf.tx_mic) + sizeof(buf.rx_mic)); + if (key_len != sizeof(buf.tkip)) + return -EINVAL; + memcpy(&buf.tkip, key, sizeof(buf.tkip)); if (rsc_len > sizeof(buf.rsc)) rsc_len = sizeof(buf.rsc); diff --git a/drivers/net/wireless/intersil/orinoco/hw.h b/drivers/net/wireless/intersil/orinoco/hw.h index 466d1ede76f1..da5804dbdf34 100644 --- a/drivers/net/wireless/intersil/orinoco/hw.h +++ b/drivers/net/wireless/intersil/orinoco/hw.h @@ -38,8 +38,9 @@ int __orinoco_hw_set_wap(struct orinoco_private *priv); int __orinoco_hw_setup_wepkeys(struct orinoco_private *priv); int __orinoco_hw_setup_enc(struct orinoco_private *priv); int __orinoco_hw_set_tkip_key(struct orinoco_private *priv, int key_idx, - int set_tx, const u8 *key, const u8 *rsc, - size_t rsc_len, const u8 *tsc, size_t tsc_len); + int set_tx, const u8 *key, size_t key_len, + const u8 *rsc, size_t rsc_len, + const u8 *tsc, size_t tsc_len); int orinoco_clear_tkip_key(struct orinoco_private *priv, int key_idx); int __orinoco_hw_set_multicast_list(struct orinoco_private *priv, struct net_device *dev, diff --git a/drivers/net/wireless/intersil/orinoco/wext.c b/drivers/net/wireless/intersil/orinoco/wext.c index 7b6c4ae8ddb3..4a01260027bc 100644 --- a/drivers/net/wireless/intersil/orinoco/wext.c +++ b/drivers/net/wireless/intersil/orinoco/wext.c @@ -791,7 +791,7 @@ static int orinoco_ioctl_set_encodeext(struct net_device *dev, err = __orinoco_hw_set_tkip_key(priv, idx, ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY, - priv->keys[idx].key, + priv->keys[idx].key, priv->keys[idx].key_len, tkip_iv, ORINOCO_SEQ_LEN, NULL, 0); if (err) printk(KERN_ERR "%s: Error %d setting TKIP key" diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 7a6fd46d0c6e..ffa894f7312a 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -626,6 +626,7 @@ struct mac80211_hwsim_data { u32 ciphers[ARRAY_SIZE(hwsim_ciphers)]; struct mac_address addresses[2]; + struct ieee80211_chanctx_conf *chanctx; int channels, idx; bool use_chanctx; bool destroy_on_close; @@ -1257,7 +1258,8 @@ static inline u16 trans_tx_rate_flags_ieee2hwsim(struct ieee80211_tx_rate *rate) static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, struct sk_buff *my_skb, - int dst_portid) + int dst_portid, + struct ieee80211_channel *channel) { struct sk_buff *skb; struct mac80211_hwsim_data *data = hw->priv; @@ -1312,7 +1314,7 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, if (nla_put_u32(skb, HWSIM_ATTR_FLAGS, hwsim_flags)) goto nla_put_failure; - if (nla_put_u32(skb, HWSIM_ATTR_FREQ, data->channel->center_freq)) + if (nla_put_u32(skb, HWSIM_ATTR_FREQ, channel->center_freq)) goto nla_put_failure; /* We get the tx control (rate and retries) info*/ @@ -1659,7 +1661,7 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw, _portid = READ_ONCE(data->wmediumd); if (_portid || hwsim_virtio_enabled) - return mac80211_hwsim_tx_frame_nl(hw, skb, _portid); + return mac80211_hwsim_tx_frame_nl(hw, skb, _portid, channel); /* NO wmediumd detected, perfect medium simulation */ data->tx_pkts++; @@ -1775,8 +1777,10 @@ static void mac80211_hwsim_tx_frame(struct ieee80211_hw *hw, mac80211_hwsim_monitor_rx(hw, skb, chan); if (_pid || hwsim_virtio_enabled) - return mac80211_hwsim_tx_frame_nl(hw, skb, _pid); + return mac80211_hwsim_tx_frame_nl(hw, skb, _pid, chan); + data->tx_pkts++; + data->tx_bytes += skb->len; mac80211_hwsim_tx_frame_no_nl(hw, skb, chan); dev_kfree_skb(skb); } @@ -2514,6 +2518,11 @@ static int mac80211_hwsim_croc(struct ieee80211_hw *hw, static int mac80211_hwsim_add_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx) { + struct mac80211_hwsim_data *hwsim = hw->priv; + + mutex_lock(&hwsim->mutex); + hwsim->chanctx = ctx; + mutex_unlock(&hwsim->mutex); hwsim_set_chanctx_magic(ctx); wiphy_dbg(hw->wiphy, "add channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", @@ -2525,6 +2534,11 @@ static int mac80211_hwsim_add_chanctx(struct ieee80211_hw *hw, static void mac80211_hwsim_remove_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx) { + struct mac80211_hwsim_data *hwsim = hw->priv; + + mutex_lock(&hwsim->mutex); + hwsim->chanctx = NULL; + mutex_unlock(&hwsim->mutex); wiphy_dbg(hw->wiphy, "remove channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", ctx->def.chan->center_freq, ctx->def.width, @@ -2537,6 +2551,11 @@ static void mac80211_hwsim_change_chanctx(struct ieee80211_hw *hw, struct ieee80211_chanctx_conf *ctx, u32 changed) { + struct mac80211_hwsim_data *hwsim = hw->priv; + + mutex_lock(&hwsim->mutex); + hwsim->chanctx = ctx; + mutex_unlock(&hwsim->mutex); hwsim_check_chanctx_magic(ctx); wiphy_dbg(hw->wiphy, "change channel context control: %d MHz/width: %d/cfreqs:%d/%d MHz\n", @@ -3129,6 +3148,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, hw->wiphy->max_remain_on_channel_duration = 1000; data->if_combination.radar_detect_widths = 0; data->if_combination.num_different_channels = data->channels; + data->chanctx = NULL; } else { data->if_combination.num_different_channels = 1; data->if_combination.radar_detect_widths = @@ -3638,6 +3658,7 @@ static int hwsim_cloned_frame_received_nl(struct sk_buff *skb_2, int frame_data_len; void *frame_data; struct sk_buff *skb = NULL; + struct ieee80211_channel *channel = NULL; if (!info->attrs[HWSIM_ATTR_ADDR_RECEIVER] || !info->attrs[HWSIM_ATTR_FRAME] || @@ -3664,6 +3685,17 @@ static int hwsim_cloned_frame_received_nl(struct sk_buff *skb_2, if (!data2) goto out; + if (data2->use_chanctx) { + if (data2->tmp_chan) + channel = data2->tmp_chan; + else if (data2->chanctx) + channel = data2->chanctx->def.chan; + } else { + channel = data2->channel; + } + if (!channel) + goto out; + if (!hwsim_virtio_enabled) { if (hwsim_net_get_netgroup(genl_info_net(info)) != data2->netgroup) @@ -3675,7 +3707,7 @@ static int hwsim_cloned_frame_received_nl(struct sk_buff *skb_2, /* check if radio is configured properly */ - if (data2->idle || !data2->started) + if ((data2->idle && !data2->tmp_chan) || !data2->started) goto out; /* A frame is received from user space */ @@ -3688,18 +3720,16 @@ static int hwsim_cloned_frame_received_nl(struct sk_buff *skb_2, mutex_lock(&data2->mutex); rx_status.freq = nla_get_u32(info->attrs[HWSIM_ATTR_FREQ]); - if (rx_status.freq != data2->channel->center_freq && - (!data2->tmp_chan || - rx_status.freq != data2->tmp_chan->center_freq)) { + if (rx_status.freq != channel->center_freq) { mutex_unlock(&data2->mutex); goto out; } mutex_unlock(&data2->mutex); } else { - rx_status.freq = data2->channel->center_freq; + rx_status.freq = channel->center_freq; } - rx_status.band = data2->channel->band; + rx_status.band = channel->band; rx_status.rate_idx = nla_get_u32(info->attrs[HWSIM_ATTR_RX_RATE]); rx_status.signal = nla_get_u32(info->attrs[HWSIM_ATTR_SIGNAL]); @@ -3796,11 +3826,6 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) return -EINVAL; } - if (param.channels > CFG80211_MAX_NUM_DIFFERENT_CHANNELS) { - GENL_SET_ERR_MSG(info, "too many channels specified"); - return -EINVAL; - } - if (info->attrs[HWSIM_ATTR_NO_VIF]) param.no_vif = true; diff --git a/drivers/net/wireless/marvell/libertas/main.c b/drivers/net/wireless/marvell/libertas/main.c index ee4cf3437e28..64fc5e410864 100644 --- a/drivers/net/wireless/marvell/libertas/main.c +++ b/drivers/net/wireless/marvell/libertas/main.c @@ -941,7 +941,7 @@ struct lbs_private *lbs_add_card(void *card, struct device *dmdev) wdev->netdev = dev; priv->dev = dev; - dev->netdev_ops = &lbs_netdev_ops; + dev->netdev_ops = &lbs_netdev_ops; dev->watchdog_timeo = 5 * HZ; dev->ethtool_ops = &lbs_ethtool_ops; dev->flags |= IFF_BROADCAST | IFF_MULTICAST; diff --git a/drivers/net/wireless/marvell/libertas/mesh.c b/drivers/net/wireless/marvell/libertas/mesh.c index c68814841583..6cbba84989b8 100644 --- a/drivers/net/wireless/marvell/libertas/mesh.c +++ b/drivers/net/wireless/marvell/libertas/mesh.c @@ -151,13 +151,13 @@ static uint16_t lbs_mesh_get_channel(struct lbs_private *priv) */ /** - * lbs_anycast_get - Get function for sysfs attribute anycast_mask + * anycast_mask_show - Get function for sysfs attribute anycast_mask * @dev: the &struct device * @attr: device attributes * @buf: buffer where data will be returned */ -static ssize_t lbs_anycast_get(struct device *dev, - struct device_attribute *attr, char * buf) +static ssize_t anycast_mask_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct lbs_private *priv = to_net_dev(dev)->ml_priv; struct cmd_ds_mesh_access mesh_access; @@ -173,14 +173,15 @@ static ssize_t lbs_anycast_get(struct device *dev, } /** - * lbs_anycast_set - Set function for sysfs attribute anycast_mask + * anycast_mask_store - Set function for sysfs attribute anycast_mask * @dev: the &struct device * @attr: device attributes * @buf: buffer that contains new attribute value * @count: size of buffer */ -static ssize_t lbs_anycast_set(struct device *dev, - struct device_attribute *attr, const char * buf, size_t count) +static ssize_t anycast_mask_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct lbs_private *priv = to_net_dev(dev)->ml_priv; struct cmd_ds_mesh_access mesh_access; @@ -199,13 +200,13 @@ static ssize_t lbs_anycast_set(struct device *dev, } /** - * lbs_prb_rsp_limit_get - Get function for sysfs attribute prb_rsp_limit + * prb_rsp_limit_show - Get function for sysfs attribute prb_rsp_limit * @dev: the &struct device * @attr: device attributes * @buf: buffer where data will be returned */ -static ssize_t lbs_prb_rsp_limit_get(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t prb_rsp_limit_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct lbs_private *priv = to_net_dev(dev)->ml_priv; struct cmd_ds_mesh_access mesh_access; @@ -225,14 +226,15 @@ static ssize_t lbs_prb_rsp_limit_get(struct device *dev, } /** - * lbs_prb_rsp_limit_set - Set function for sysfs attribute prb_rsp_limit + * prb_rsp_limit_store - Set function for sysfs attribute prb_rsp_limit * @dev: the &struct device * @attr: device attributes * @buf: buffer that contains new attribute value * @count: size of buffer */ -static ssize_t lbs_prb_rsp_limit_set(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) +static ssize_t prb_rsp_limit_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct lbs_private *priv = to_net_dev(dev)->ml_priv; struct cmd_ds_mesh_access mesh_access; @@ -259,27 +261,28 @@ static ssize_t lbs_prb_rsp_limit_set(struct device *dev, } /** - * lbs_mesh_get - Get function for sysfs attribute mesh + * lbs_mesh_show - Get function for sysfs attribute mesh * @dev: the &struct device * @attr: device attributes * @buf: buffer where data will be returned */ -static ssize_t lbs_mesh_get(struct device *dev, - struct device_attribute *attr, char * buf) +static ssize_t lbs_mesh_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct lbs_private *priv = to_net_dev(dev)->ml_priv; return snprintf(buf, 5, "0x%X\n", !!priv->mesh_dev); } /** - * lbs_mesh_set - Set function for sysfs attribute mesh + * lbs_mesh_store - Set function for sysfs attribute mesh * @dev: the &struct device * @attr: device attributes * @buf: buffer that contains new attribute value * @count: size of buffer */ -static ssize_t lbs_mesh_set(struct device *dev, - struct device_attribute *attr, const char * buf, size_t count) +static ssize_t lbs_mesh_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct lbs_private *priv = to_net_dev(dev)->ml_priv; int enable; @@ -301,20 +304,19 @@ static ssize_t lbs_mesh_set(struct device *dev, * lbs_mesh attribute to be exported per ethX interface * through sysfs (/sys/class/net/ethX/lbs_mesh) */ -static DEVICE_ATTR(lbs_mesh, 0644, lbs_mesh_get, lbs_mesh_set); +static DEVICE_ATTR_RW(lbs_mesh); /* * anycast_mask attribute to be exported per mshX interface * through sysfs (/sys/class/net/mshX/anycast_mask) */ -static DEVICE_ATTR(anycast_mask, 0644, lbs_anycast_get, lbs_anycast_set); +static DEVICE_ATTR_RW(anycast_mask); /* * prb_rsp_limit attribute to be exported per mshX interface * through sysfs (/sys/class/net/mshX/prb_rsp_limit) */ -static DEVICE_ATTR(prb_rsp_limit, 0644, lbs_prb_rsp_limit_get, - lbs_prb_rsp_limit_set); +static DEVICE_ATTR_RW(prb_rsp_limit); static struct attribute *lbs_mesh_sysfs_entries[] = { &dev_attr_anycast_mask.attr, @@ -351,13 +353,13 @@ static int mesh_get_default_parameters(struct device *dev, } /** - * bootflag_get - Get function for sysfs attribute bootflag + * bootflag_show - Get function for sysfs attribute bootflag * @dev: the &struct device * @attr: device attributes * @buf: buffer where data will be returned */ -static ssize_t bootflag_get(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t bootflag_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct mrvl_mesh_defaults defs; int ret; @@ -371,14 +373,14 @@ static ssize_t bootflag_get(struct device *dev, } /** - * bootflag_set - Set function for sysfs attribute bootflag + * bootflag_store - Set function for sysfs attribute bootflag * @dev: the &struct device * @attr: device attributes * @buf: buffer that contains new attribute value * @count: size of buffer */ -static ssize_t bootflag_set(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t bootflag_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct lbs_private *priv = to_net_dev(dev)->ml_priv; struct cmd_ds_mesh_config cmd; @@ -401,13 +403,13 @@ static ssize_t bootflag_set(struct device *dev, struct device_attribute *attr, } /** - * boottime_get - Get function for sysfs attribute boottime + * boottime_show - Get function for sysfs attribute boottime * @dev: the &struct device * @attr: device attributes * @buf: buffer where data will be returned */ -static ssize_t boottime_get(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t boottime_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct mrvl_mesh_defaults defs; int ret; @@ -421,14 +423,15 @@ static ssize_t boottime_get(struct device *dev, } /** - * boottime_set - Set function for sysfs attribute boottime + * boottime_store - Set function for sysfs attribute boottime * @dev: the &struct device * @attr: device attributes * @buf: buffer that contains new attribute value * @count: size of buffer */ -static ssize_t boottime_set(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) +static ssize_t boottime_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct lbs_private *priv = to_net_dev(dev)->ml_priv; struct cmd_ds_mesh_config cmd; @@ -460,13 +463,13 @@ static ssize_t boottime_set(struct device *dev, } /** - * channel_get - Get function for sysfs attribute channel + * channel_show - Get function for sysfs attribute channel * @dev: the &struct device * @attr: device attributes * @buf: buffer where data will be returned */ -static ssize_t channel_get(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t channel_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct mrvl_mesh_defaults defs; int ret; @@ -480,14 +483,14 @@ static ssize_t channel_get(struct device *dev, } /** - * channel_set - Set function for sysfs attribute channel + * channel_store - Set function for sysfs attribute channel * @dev: the &struct device * @attr: device attributes * @buf: buffer that contains new attribute value * @count: size of buffer */ -static ssize_t channel_set(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t channel_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct lbs_private *priv = to_net_dev(dev)->ml_priv; struct cmd_ds_mesh_config cmd; @@ -510,13 +513,13 @@ static ssize_t channel_set(struct device *dev, struct device_attribute *attr, } /** - * mesh_id_get - Get function for sysfs attribute mesh_id + * mesh_id_show - Get function for sysfs attribute mesh_id * @dev: the &struct device * @attr: device attributes * @buf: buffer where data will be returned */ -static ssize_t mesh_id_get(struct device *dev, struct device_attribute *attr, - char *buf) +static ssize_t mesh_id_show(struct device *dev, struct device_attribute *attr, + char *buf) { struct mrvl_mesh_defaults defs; int ret; @@ -539,14 +542,14 @@ static ssize_t mesh_id_get(struct device *dev, struct device_attribute *attr, } /** - * mesh_id_set - Set function for sysfs attribute mesh_id + * mesh_id_store - Set function for sysfs attribute mesh_id * @dev: the &struct device * @attr: device attributes * @buf: buffer that contains new attribute value * @count: size of buffer */ -static ssize_t mesh_id_set(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t mesh_id_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { struct cmd_ds_mesh_config cmd; struct mrvl_mesh_defaults defs; @@ -585,13 +588,14 @@ static ssize_t mesh_id_set(struct device *dev, struct device_attribute *attr, } /** - * protocol_id_get - Get function for sysfs attribute protocol_id + * protocol_id_show - Get function for sysfs attribute protocol_id * @dev: the &struct device * @attr: device attributes * @buf: buffer where data will be returned */ -static ssize_t protocol_id_get(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t protocol_id_show(struct device *dev, + struct device_attribute *attr, + char *buf) { struct mrvl_mesh_defaults defs; int ret; @@ -605,14 +609,15 @@ static ssize_t protocol_id_get(struct device *dev, } /** - * protocol_id_set - Set function for sysfs attribute protocol_id + * protocol_id_store - Set function for sysfs attribute protocol_id * @dev: the &struct device * @attr: device attributes * @buf: buffer that contains new attribute value * @count: size of buffer */ -static ssize_t protocol_id_set(struct device *dev, - struct device_attribute *attr, const char *buf, size_t count) +static ssize_t protocol_id_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct cmd_ds_mesh_config cmd; struct mrvl_mesh_defaults defs; @@ -646,13 +651,13 @@ static ssize_t protocol_id_set(struct device *dev, } /** - * metric_id_get - Get function for sysfs attribute metric_id + * metric_id_show - Get function for sysfs attribute metric_id * @dev: the &struct device * @attr: device attributes * @buf: buffer where data will be returned */ -static ssize_t metric_id_get(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t metric_id_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct mrvl_mesh_defaults defs; int ret; @@ -666,14 +671,15 @@ static ssize_t metric_id_get(struct device *dev, } /** - * metric_id_set - Set function for sysfs attribute metric_id + * metric_id_store - Set function for sysfs attribute metric_id * @dev: the &struct device * @attr: device attributes * @buf: buffer that contains new attribute value * @count: size of buffer */ -static ssize_t metric_id_set(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t metric_id_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct cmd_ds_mesh_config cmd; struct mrvl_mesh_defaults defs; @@ -707,13 +713,13 @@ static ssize_t metric_id_set(struct device *dev, struct device_attribute *attr, } /** - * capability_get - Get function for sysfs attribute capability + * capability_show - Get function for sysfs attribute capability * @dev: the &struct device * @attr: device attributes * @buf: buffer where data will be returned */ -static ssize_t capability_get(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t capability_show(struct device *dev, + struct device_attribute *attr, char *buf) { struct mrvl_mesh_defaults defs; int ret; @@ -727,14 +733,15 @@ static ssize_t capability_get(struct device *dev, } /** - * capability_set - Set function for sysfs attribute capability + * capability_store - Set function for sysfs attribute capability * @dev: the &struct device * @attr: device attributes * @buf: buffer that contains new attribute value * @count: size of buffer */ -static ssize_t capability_set(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t capability_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct cmd_ds_mesh_config cmd; struct mrvl_mesh_defaults defs; @@ -768,13 +775,13 @@ static ssize_t capability_set(struct device *dev, struct device_attribute *attr, } -static DEVICE_ATTR(bootflag, 0644, bootflag_get, bootflag_set); -static DEVICE_ATTR(boottime, 0644, boottime_get, boottime_set); -static DEVICE_ATTR(channel, 0644, channel_get, channel_set); -static DEVICE_ATTR(mesh_id, 0644, mesh_id_get, mesh_id_set); -static DEVICE_ATTR(protocol_id, 0644, protocol_id_get, protocol_id_set); -static DEVICE_ATTR(metric_id, 0644, metric_id_get, metric_id_set); -static DEVICE_ATTR(capability, 0644, capability_get, capability_set); +static DEVICE_ATTR_RW(bootflag); +static DEVICE_ATTR_RW(boottime); +static DEVICE_ATTR_RW(channel); +static DEVICE_ATTR_RW(mesh_id); +static DEVICE_ATTR_RW(protocol_id); +static DEVICE_ATTR_RW(metric_id); +static DEVICE_ATTR_RW(capability); static struct attribute *boot_opts_attrs[] = { &dev_attr_bootflag.attr, diff --git a/drivers/net/wireless/marvell/libertas_tf/if_usb.c b/drivers/net/wireless/marvell/libertas_tf/if_usb.c index a92916dc81a9..fe0a69e804d8 100644 --- a/drivers/net/wireless/marvell/libertas_tf/if_usb.c +++ b/drivers/net/wireless/marvell/libertas_tf/if_usb.c @@ -48,7 +48,7 @@ static int if_usb_submit_rx_urb(struct if_usb_card *cardp); static int if_usb_reset_device(struct lbtf_private *priv); /** - * if_usb_wrike_bulk_callback - call back to handle URB status + * if_usb_write_bulk_callback - call back to handle URB status * * @urb: pointer to urb structure */ diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h index 470d669c7f14..2ff23ab259ab 100644 --- a/drivers/net/wireless/marvell/mwifiex/fw.h +++ b/drivers/net/wireless/marvell/mwifiex/fw.h @@ -995,6 +995,11 @@ struct host_cmd_ds_802_11_key_material { struct mwifiex_ie_type_key_param_set key_param_set; } __packed; +struct host_cmd_ds_802_11_key_material_wep { + __le16 action; + struct mwifiex_ie_type_key_param_set key_param_set[NUM_WEP_KEYS]; +} __packed; + struct host_cmd_ds_gen { __le16 command; __le16 size; @@ -2347,6 +2352,7 @@ struct host_cmd_ds_command { struct host_cmd_ds_wmm_get_status get_wmm_status; struct host_cmd_ds_802_11_key_material key_material; struct host_cmd_ds_802_11_key_material_v2 key_material_v2; + struct host_cmd_ds_802_11_key_material_wep key_material_wep; struct host_cmd_ds_version_ext verext; struct host_cmd_ds_mgmt_frame_reg reg_mask; struct host_cmd_ds_remain_on_chan roc_cfg; diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c index 529dfd8b7ae8..17399d4aa129 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.c +++ b/drivers/net/wireless/marvell/mwifiex/main.c @@ -1445,11 +1445,18 @@ static void mwifiex_uninit_sw(struct mwifiex_adapter *adapter) if (!priv) continue; rtnl_lock(); - wiphy_lock(adapter->wiphy); if (priv->netdev && - priv->wdev.iftype != NL80211_IFTYPE_UNSPECIFIED) + priv->wdev.iftype != NL80211_IFTYPE_UNSPECIFIED) { + /* + * Close the netdev now, because if we do it later, the + * netdev notifiers will need to acquire the wiphy lock + * again --> deadlock. + */ + dev_close(priv->wdev.netdev); + wiphy_lock(adapter->wiphy); mwifiex_del_virtual_intf(adapter->wiphy, &priv->wdev); - wiphy_unlock(adapter->wiphy); + wiphy_unlock(adapter->wiphy); + } rtnl_unlock(); } diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c index d3a968ef21ef..48ea00da1fc9 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c @@ -840,14 +840,15 @@ mwifiex_cmd_802_11_key_material_v1(struct mwifiex_private *priv, } if (!enc_key) { - memset(&key_material->key_param_set, 0, - (NUM_WEP_KEYS * - sizeof(struct mwifiex_ie_type_key_param_set))); + struct host_cmd_ds_802_11_key_material_wep *key_material_wep = + (struct host_cmd_ds_802_11_key_material_wep *)key_material; + memset(key_material_wep->key_param_set, 0, + sizeof(key_material_wep->key_param_set)); ret = mwifiex_set_keyparamset_wep(priv, - &key_material->key_param_set, + &key_material_wep->key_param_set[0], &key_param_len); cmd->size = cpu_to_le16(key_param_len + - sizeof(key_material->action) + S_DS_GEN); + sizeof(key_material_wep->action) + S_DS_GEN); return ret; } else memset(&key_material->key_param_set, 0, diff --git a/drivers/net/wireless/marvell/mwl8k.c b/drivers/net/wireless/marvell/mwl8k.c index 84b32a5f01ee..3bf6571f4149 100644 --- a/drivers/net/wireless/marvell/mwl8k.c +++ b/drivers/net/wireless/marvell/mwl8k.c @@ -4552,7 +4552,7 @@ static int mwl8k_cmd_update_stadb_add(struct ieee80211_hw *hw, else rates = sta->supp_rates[NL80211_BAND_5GHZ] << 5; legacy_rate_mask_to_array(p->legacy_rates, rates); - memcpy(p->ht_rates, sta->ht_cap.mcs.rx_mask, 16); + memcpy(p->ht_rates, &sta->ht_cap.mcs, 16); p->interop = 1; p->amsdu_enabled = 0; @@ -5034,7 +5034,7 @@ mwl8k_bss_info_changed_sta(struct ieee80211_hw *hw, struct ieee80211_vif *vif, ap_legacy_rates = ap->supp_rates[NL80211_BAND_5GHZ] << 5; } - memcpy(ap_mcs_rates, ap->ht_cap.mcs.rx_mask, 16); + memcpy(ap_mcs_rates, &ap->ht_cap.mcs, 16); rcu_read_unlock(); diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 72b1cc0ecfda..5e1c1506a4c6 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -191,6 +191,7 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q, q->entry[idx].txwi = txwi; q->entry[idx].skb = skb; + q->entry[idx].wcid = 0xffff; return idx; } @@ -349,6 +350,9 @@ mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q, struct sk_buff *skb, struct mt76_wcid *wcid, struct ieee80211_sta *sta) { + struct ieee80211_tx_status status = { + .sta = sta, + }; struct mt76_tx_info tx_info = { .skb = skb, }; @@ -360,11 +364,9 @@ mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q, u8 *txwi; t = mt76_get_txwi(dev); - if (!t) { - hw = mt76_tx_status_get_hw(dev, skb); - ieee80211_free_txskb(hw, skb); - return -ENOMEM; - } + if (!t) + goto free_skb; + txwi = mt76_get_txwi_ptr(dev, t); skb->prev = skb->next = NULL; @@ -427,8 +429,13 @@ free: } #endif - dev_kfree_skb(tx_info.skb); mt76_put_txwi(dev, t); + +free_skb: + status.skb = tx_info.skb; + hw = mt76_tx_status_get_hw(dev, tx_info.skb); + ieee80211_tx_status_ext(hw, &status); + return ret; } diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 03fe62837557..d03aedc3286b 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -83,6 +83,22 @@ static const struct ieee80211_tpt_blink mt76_tpt_blink[] = { { .throughput = 300 * 1024, .blink_time = 50 }, }; +struct ieee80211_rate mt76_rates[] = { + CCK_RATE(0, 10), + CCK_RATE(1, 20), + CCK_RATE(2, 55), + CCK_RATE(3, 110), + OFDM_RATE(11, 60), + OFDM_RATE(15, 90), + OFDM_RATE(10, 120), + OFDM_RATE(14, 180), + OFDM_RATE(9, 240), + OFDM_RATE(13, 360), + OFDM_RATE(8, 480), + OFDM_RATE(12, 540), +}; +EXPORT_SYMBOL_GPL(mt76_rates); + static int mt76_led_init(struct mt76_dev *dev) { struct device_node *np = dev->dev->of_node; @@ -315,17 +331,6 @@ mt76_phy_init(struct mt76_phy *phy, struct ieee80211_hw *hw) ieee80211_hw_set(hw, MFP_CAPABLE); ieee80211_hw_set(hw, AP_LINK_PS); ieee80211_hw_set(hw, REPORTS_TX_ACK_STATUS); - - wiphy->flags |= WIPHY_FLAG_IBSS_RSN; - wiphy->interface_modes = - BIT(NL80211_IFTYPE_STATION) | - BIT(NL80211_IFTYPE_AP) | -#ifdef CONFIG_MAC80211_MESH - BIT(NL80211_IFTYPE_MESH_POINT) | -#endif - BIT(NL80211_IFTYPE_P2P_CLIENT) | - BIT(NL80211_IFTYPE_P2P_GO) | - BIT(NL80211_IFTYPE_ADHOC); } struct mt76_phy * @@ -346,6 +351,17 @@ mt76_alloc_phy(struct mt76_dev *dev, unsigned int size, phy->hw = hw; phy->priv = hw->priv + phy_size; + hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN; + hw->wiphy->interface_modes = + BIT(NL80211_IFTYPE_STATION) | + BIT(NL80211_IFTYPE_AP) | +#ifdef CONFIG_MAC80211_MESH + BIT(NL80211_IFTYPE_MESH_POINT) | +#endif + BIT(NL80211_IFTYPE_P2P_CLIENT) | + BIT(NL80211_IFTYPE_P2P_GO) | + BIT(NL80211_IFTYPE_ADHOC); + return phy; } EXPORT_SYMBOL_GPL(mt76_alloc_phy); @@ -428,6 +444,17 @@ mt76_alloc_device(struct device *pdev, unsigned int size, mutex_init(&dev->mcu.mutex); dev->tx_worker.fn = mt76_tx_worker; + hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN; + hw->wiphy->interface_modes = + BIT(NL80211_IFTYPE_STATION) | + BIT(NL80211_IFTYPE_AP) | +#ifdef CONFIG_MAC80211_MESH + BIT(NL80211_IFTYPE_MESH_POINT) | +#endif + BIT(NL80211_IFTYPE_P2P_CLIENT) | + BIT(NL80211_IFTYPE_P2P_GO) | + BIT(NL80211_IFTYPE_ADHOC); + spin_lock_init(&dev->token_lock); idr_init(&dev->token); @@ -632,20 +659,19 @@ void mt76_update_survey_active_time(struct mt76_phy *phy, ktime_t time) } EXPORT_SYMBOL_GPL(mt76_update_survey_active_time); -void mt76_update_survey(struct mt76_dev *dev) +void mt76_update_survey(struct mt76_phy *phy) { + struct mt76_dev *dev = phy->dev; ktime_t cur_time; if (dev->drv->update_survey) - dev->drv->update_survey(dev); + dev->drv->update_survey(phy); cur_time = ktime_get_boottime(); - mt76_update_survey_active_time(&dev->phy, cur_time); - if (dev->phy2) - mt76_update_survey_active_time(dev->phy2, cur_time); + mt76_update_survey_active_time(phy, cur_time); if (dev->drv->drv_flags & MT_DRV_SW_RX_AIRTIME) { - struct mt76_channel_state *state = dev->phy.chan_state; + struct mt76_channel_state *state = phy->chan_state; spin_lock_bh(&dev->cc_lock); state->cc_bss_rx += dev->cur_cc_bss_rx; @@ -664,7 +690,7 @@ void mt76_set_channel(struct mt76_phy *phy) int timeout = HZ / 5; wait_event_timeout(dev->tx_wait, !mt76_has_tx_pending(phy), timeout); - mt76_update_survey(dev); + mt76_update_survey(phy); phy->chandef = *chandef; phy->chan_state = mt76_channel_state(phy, chandef->chan); @@ -689,7 +715,7 @@ int mt76_get_survey(struct ieee80211_hw *hw, int idx, mutex_lock(&dev->mutex); if (idx == 0 && dev->drv->update_survey) - mt76_update_survey(dev); + mt76_update_survey(phy); sband = &phy->sband_2g; if (idx >= sband->sband.n_channels) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 36ede65919f8..25c5ceef5257 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -87,6 +87,22 @@ enum mt76_rxq_id { __MT_RXQ_MAX }; +enum mt76_cipher_type { + MT_CIPHER_NONE, + MT_CIPHER_WEP40, + MT_CIPHER_TKIP, + MT_CIPHER_TKIP_NO_MIC, + MT_CIPHER_AES_CCMP, + MT_CIPHER_WEP104, + MT_CIPHER_BIP_CMAC_128, + MT_CIPHER_WEP128, + MT_CIPHER_WAPI, + MT_CIPHER_CCMP_CCX, + MT_CIPHER_CCMP_256, + MT_CIPHER_GCMP, + MT_CIPHER_GCMP_256, +}; + struct mt76_queue_buf { dma_addr_t addr; u16 len; @@ -320,6 +336,7 @@ enum { struct mt76_hw_cap { bool has_2ghz; bool has_5ghz; + bool has_6ghz; }; #define MT_DRV_TXWI_NO_FREE BIT(0) @@ -336,7 +353,7 @@ struct mt76_driver_ops { u16 token_size; u8 mcs_rates; - void (*update_survey)(struct mt76_dev *dev); + void (*update_survey)(struct mt76_phy *phy); int (*tx_prepare_skb)(struct mt76_dev *dev, void *txwi_ptr, enum mt76_txq_id qid, struct mt76_wcid *wcid, @@ -738,6 +755,21 @@ enum mt76_phy_type { MT_PHY_TYPE_HE_MU, }; +#define CCK_RATE(_idx, _rate) { \ + .bitrate = _rate, \ + .flags = IEEE80211_RATE_SHORT_PREAMBLE, \ + .hw_value = (MT_PHY_TYPE_CCK << 8) | (_idx), \ + .hw_value_short = (MT_PHY_TYPE_CCK << 8) | (4 + _idx), \ +} + +#define OFDM_RATE(_idx, _rate) { \ + .bitrate = _rate, \ + .hw_value = (MT_PHY_TYPE_OFDM << 8) | (_idx), \ + .hw_value_short = (MT_PHY_TYPE_OFDM << 8) | (_idx), \ +} + +extern struct ieee80211_rate mt76_rates[12]; + #define __mt76_rr(dev, ...) (dev)->bus->rr((dev), __VA_ARGS__) #define __mt76_wr(dev, ...) (dev)->bus->wr((dev), __VA_ARGS__) #define __mt76_rmw(dev, ...) (dev)->bus->rmw((dev), __VA_ARGS__) @@ -1031,7 +1063,7 @@ void mt76_release_buffered_frames(struct ieee80211_hw *hw, bool more_data); bool mt76_has_tx_pending(struct mt76_phy *phy); void mt76_set_channel(struct mt76_phy *phy); -void mt76_update_survey(struct mt76_dev *dev); +void mt76_update_survey(struct mt76_phy *phy); void mt76_update_survey_active_time(struct mt76_phy *phy, ktime_t time); int mt76_get_survey(struct ieee80211_hw *hw, int idx, struct survey_info *survey); @@ -1056,7 +1088,14 @@ struct sk_buff *mt76_tx_status_skb_get(struct mt76_dev *dev, struct sk_buff_head *list); void mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb, struct sk_buff_head *list); -void mt76_tx_complete_skb(struct mt76_dev *dev, u16 wcid, struct sk_buff *skb); +void __mt76_tx_complete_skb(struct mt76_dev *dev, u16 wcid, struct sk_buff *skb, + struct list_head *free_list); +static inline void +mt76_tx_complete_skb(struct mt76_dev *dev, u16 wcid, struct sk_buff *skb) +{ + __mt76_tx_complete_skb(dev, wcid, skb, NULL); +} + void mt76_tx_status_check(struct mt76_dev *dev, struct mt76_wcid *wcid, bool flush); int mt76_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -1253,4 +1292,15 @@ mt76_token_put(struct mt76_dev *dev, int token) return txwi; } + +static inline int +mt76_get_next_pkt_id(struct mt76_wcid *wcid) +{ + wcid->packet_id = (wcid->packet_id + 1) & MT_PACKET_ID_MASK; + if (wcid->packet_id == MT_PACKET_ID_NO_ACK || + wcid->packet_id == MT_PACKET_ID_NO_SKB) + wcid->packet_id = MT_PACKET_ID_FIRST; + + return wcid->packet_id; +} #endif diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/init.c b/drivers/net/wireless/mediatek/mt76/mt7603/init.c index e1b2cfa56074..031d39a48a55 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/init.c @@ -304,34 +304,6 @@ mt7603_init_hardware(struct mt7603_dev *dev) return 0; } -#define CCK_RATE(_idx, _rate) { \ - .bitrate = _rate, \ - .flags = IEEE80211_RATE_SHORT_PREAMBLE, \ - .hw_value = (MT_PHY_TYPE_CCK << 8) | (_idx), \ - .hw_value_short = (MT_PHY_TYPE_CCK << 8) | (4 + _idx), \ -} - -#define OFDM_RATE(_idx, _rate) { \ - .bitrate = _rate, \ - .hw_value = (MT_PHY_TYPE_OFDM << 8) | (_idx), \ - .hw_value_short = (MT_PHY_TYPE_OFDM << 8) | (_idx), \ -} - -static struct ieee80211_rate mt7603_rates[] = { - CCK_RATE(0, 10), - CCK_RATE(1, 20), - CCK_RATE(2, 55), - CCK_RATE(3, 110), - OFDM_RATE(11, 60), - OFDM_RATE(15, 90), - OFDM_RATE(10, 120), - OFDM_RATE(14, 180), - OFDM_RATE(9, 240), - OFDM_RATE(13, 360), - OFDM_RATE(8, 480), - OFDM_RATE(12, 540), -}; - static const struct ieee80211_iface_limit if_limits[] = { { .max = 1, @@ -569,8 +541,8 @@ int mt7603_register_device(struct mt7603_dev *dev) wiphy->reg_notifier = mt7603_regd_notifier; - ret = mt76_register_device(&dev->mt76, true, mt7603_rates, - ARRAY_SIZE(mt7603_rates)); + ret = mt76_register_device(&dev->mt76, true, mt76_rates, + ARRAY_SIZE(mt76_rates)); if (ret) return ret; diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c index fbceb07c5f37..3972c56136a2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c @@ -550,14 +550,27 @@ mt7603_mac_fill_rx(struct mt7603_dev *dev, struct sk_buff *skb) u8 *data = (u8 *)rxd; if (status->flag & RX_FLAG_DECRYPTED) { - status->iv[0] = data[5]; - status->iv[1] = data[4]; - status->iv[2] = data[3]; - status->iv[3] = data[2]; - status->iv[4] = data[1]; - status->iv[5] = data[0]; - - insert_ccmp_hdr = FIELD_GET(MT_RXD2_NORMAL_FRAG, rxd2); + switch (FIELD_GET(MT_RXD2_NORMAL_SEC_MODE, rxd2)) { + case MT_CIPHER_AES_CCMP: + case MT_CIPHER_CCMP_CCX: + case MT_CIPHER_CCMP_256: + insert_ccmp_hdr = + FIELD_GET(MT_RXD2_NORMAL_FRAG, rxd2); + fallthrough; + case MT_CIPHER_TKIP: + case MT_CIPHER_TKIP_NO_MIC: + case MT_CIPHER_GCMP: + case MT_CIPHER_GCMP_256: + status->iv[0] = data[5]; + status->iv[1] = data[4]; + status->iv[2] = data[3]; + status->iv[3] = data[2]; + status->iv[4] = data[1]; + status->iv[5] = data[0]; + break; + default: + break; + } } rxd += 4; @@ -831,7 +844,7 @@ void mt7603_wtbl_set_rates(struct mt7603_dev *dev, struct mt7603_sta *sta, sta->wcid.tx_info |= MT_WCID_TX_INFO_SET; } -static enum mt7603_cipher_type +static enum mt76_cipher_type mt7603_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data) { memset(key_data, 0, 32); @@ -863,7 +876,7 @@ mt7603_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data) int mt7603_wtbl_set_key(struct mt7603_dev *dev, int wcid, struct ieee80211_key_conf *key) { - enum mt7603_cipher_type cipher; + enum mt76_cipher_type cipher; u32 addr = mt7603_wtbl3_addr(wcid); u8 key_data[32]; int key_len = sizeof(key_data); @@ -1213,7 +1226,7 @@ mt7603_mac_add_txs_skb(struct mt7603_dev *dev, struct mt7603_sta *sta, int pid, struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); if (!mt7603_fill_txs(dev, sta, info, txs_data)) { - ieee80211_tx_info_clear_status(info); + info->status.rates[0].count = 0; info->status.rates[0].idx = -1; } @@ -1584,12 +1597,12 @@ trigger: return true; } -void mt7603_update_channel(struct mt76_dev *mdev) +void mt7603_update_channel(struct mt76_phy *mphy) { - struct mt7603_dev *dev = container_of(mdev, struct mt7603_dev, mt76); + struct mt7603_dev *dev = container_of(mphy->dev, struct mt7603_dev, mt76); struct mt76_channel_state *state; - state = mdev->phy.chan_state; + state = mphy->chan_state; state->cc_busy += mt76_rr(dev, MT_MIB_STAT_CCA); } @@ -1806,7 +1819,7 @@ void mt7603_mac_work(struct work_struct *work) mutex_lock(&dev->mt76.mutex); dev->mphy.mac_work_count++; - mt76_update_survey(&dev->mt76); + mt76_update_survey(&dev->mphy); mt7603_edcca_check(dev); for (i = 0, idx = 0; i < 2; i++) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h index 1df5b9fed2bb..0fd46d907638 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h +++ b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h @@ -256,7 +256,7 @@ void mt7603_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif, void mt7603_pre_tbtt_tasklet(struct tasklet_struct *t); -void mt7603_update_channel(struct mt76_dev *mdev); +void mt7603_update_channel(struct mt76_phy *mphy); void mt7603_edcca_set_strict(struct mt7603_dev *dev, bool val); void mt7603_cca_stats_reset(struct mt7603_dev *dev); diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/regs.h b/drivers/net/wireless/mediatek/mt76/mt7603/regs.h index 6741e6907194..3b901090b29c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt7603/regs.h @@ -765,16 +765,4 @@ enum { #define MT_WTBL1_OR (MT_WTBL1_BASE + 0x2300) #define MT_WTBL1_OR_PSM_WRITE BIT(31) -enum mt7603_cipher_type { - MT_CIPHER_NONE, - MT_CIPHER_WEP40, - MT_CIPHER_TKIP, - MT_CIPHER_TKIP_NO_MIC, - MT_CIPHER_AES_CCMP, - MT_CIPHER_WEP104, - MT_CIPHER_BIP_CMAC_128, - MT_CIPHER_WEP128, - MT_CIPHER_WAPI, -}; - #endif diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/Makefile b/drivers/net/wireless/mediatek/mt76/mt7615/Makefile index e8fc4a7ae9bc..83f9861ff522 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/Makefile +++ b/drivers/net/wireless/mediatek/mt76/mt7615/Makefile @@ -1,4 +1,4 @@ -#SPDX-License-Identifier: ISC +# SPDX-License-Identifier: ISC obj-$(CONFIG_MT7615_COMMON) += mt7615-common.o obj-$(CONFIG_MT7615E) += mt7615e.o diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c index 676bb22726d6..cb4659771fd9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/debugfs.c @@ -75,7 +75,7 @@ mt7615_pm_set(void *data, u64 val) if (!mt7615_wait_for_mcu_init(dev)) return 0; - if (!mt7615_firmware_offload(dev) || !mt76_is_mmio(&dev->mt76)) + if (!mt7615_firmware_offload(dev) || mt76_is_usb(&dev->mt76)) return -EOPNOTSUPP; if (val == pm->enable) @@ -319,24 +319,6 @@ mt7615_radio_read(struct seq_file *s, void *data) return 0; } -static int mt7615_read_temperature(struct seq_file *s, void *data) -{ - struct mt7615_dev *dev = dev_get_drvdata(s->private); - int temp; - - if (!mt7615_wait_for_mcu_init(dev)) - return 0; - - /* cpu */ - mt7615_mutex_acquire(dev); - temp = mt7615_mcu_get_temperature(dev, 0); - mt7615_mutex_release(dev); - - seq_printf(s, "Temperature: %d\n", temp); - - return 0; -} - static int mt7615_queues_acq(struct seq_file *s, void *data) { @@ -566,8 +548,6 @@ int mt7615_init_debugfs(struct mt7615_dev *dev) debugfs_create_file("reset_test", 0200, dir, dev, &fops_reset_test); - debugfs_create_devm_seqfile(dev->mt76.dev, "temperature", dir, - mt7615_read_temperature); debugfs_create_file("ext_mac_addr", 0600, dir, dev, &fops_ext_mac_addr); debugfs_create_u32("rf_wfidx", 0600, dir, &dev->debugfs_rf_wf); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/dma.c b/drivers/net/wireless/mediatek/mt76/mt7615/dma.c index 8004ae5c16a9..00aefea1bf61 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/dma.c @@ -81,7 +81,7 @@ static int mt7615_poll_tx(struct napi_struct *napi, int budget) if (napi_complete(napi)) mt7615_irq_enable(dev, mt7615_tx_mcu_int_mask(dev)); - mt76_connac_pm_unref(&dev->pm); + mt76_connac_pm_unref(&dev->mphy, &dev->pm); return 0; } @@ -99,7 +99,7 @@ static int mt7615_poll_rx(struct napi_struct *napi, int budget) return 0; } done = mt76_dma_rx_poll(napi, budget); - mt76_connac_pm_unref(&dev->pm); + mt76_connac_pm_unref(&dev->mphy, &dev->pm); return done; } @@ -222,14 +222,9 @@ void mt7615_dma_start(struct mt7615_dev *dev) int mt7615_dma_init(struct mt7615_dev *dev) { int rx_ring_size = MT7615_RX_RING_SIZE; - int rx_buf_size = MT_RX_BUF_SIZE; u32 mask; int ret; - /* Increase buffer size to receive large VHT MPDUs */ - if (dev->mphy.cap.has_5ghz) - rx_buf_size *= 2; - mt76_dma_attach(&dev->mt76); mt76_wr(dev, MT_WPDMA_GLO_CFG, @@ -270,7 +265,7 @@ int mt7615_dma_init(struct mt7615_dev *dev) /* init rx queues */ ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU], 1, - MT7615_RX_MCU_RING_SIZE, rx_buf_size, + MT7615_RX_MCU_RING_SIZE, MT_RX_BUF_SIZE, MT_RX_RING_BASE); if (ret) return ret; @@ -279,7 +274,7 @@ int mt7615_dma_init(struct mt7615_dev *dev) rx_ring_size /= 2; ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MAIN], 0, - rx_ring_size, rx_buf_size, MT_RX_RING_BASE); + rx_ring_size, MT_RX_BUF_SIZE, MT_RX_RING_BASE); if (ret) return ret; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c index d20f05a7717d..2f1ac644e018 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c @@ -8,11 +8,61 @@ */ #include +#include +#include #include "mt7615.h" #include "mac.h" #include "mcu.h" #include "eeprom.h" +static ssize_t mt7615_thermal_show_temp(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mt7615_dev *mdev = dev_get_drvdata(dev); + int temperature; + + if (!mt7615_wait_for_mcu_init(mdev)) + return 0; + + mt7615_mutex_acquire(mdev); + temperature = mt7615_mcu_get_temperature(mdev); + mt7615_mutex_release(mdev); + + if (temperature < 0) + return temperature; + + /* display in millidegree celcius */ + return sprintf(buf, "%u\n", temperature * 1000); +} + +static SENSOR_DEVICE_ATTR(temp1_input, 0444, mt7615_thermal_show_temp, + NULL, 0); + +static struct attribute *mt7615_hwmon_attrs[] = { + &sensor_dev_attr_temp1_input.dev_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(mt7615_hwmon); + +int mt7615_thermal_init(struct mt7615_dev *dev) +{ + struct wiphy *wiphy = mt76_hw(dev)->wiphy; + struct device *hwmon; + + if (!IS_REACHABLE(CONFIG_HWMON)) + return 0; + + hwmon = devm_hwmon_device_register_with_groups(&wiphy->dev, + wiphy_name(wiphy), dev, + mt7615_hwmon_groups); + if (IS_ERR(hwmon)) + return PTR_ERR(hwmon); + + return 0; +} +EXPORT_SYMBOL_GPL(mt7615_thermal_init); + static void mt7615_phy_init(struct mt7615_dev *dev) { @@ -174,35 +224,6 @@ bool mt7615_wait_for_mcu_init(struct mt7615_dev *dev) } EXPORT_SYMBOL_GPL(mt7615_wait_for_mcu_init); -#define CCK_RATE(_idx, _rate) { \ - .bitrate = _rate, \ - .flags = IEEE80211_RATE_SHORT_PREAMBLE, \ - .hw_value = (MT_PHY_TYPE_CCK << 8) | (_idx), \ - .hw_value_short = (MT_PHY_TYPE_CCK << 8) | (4 + (_idx)), \ -} - -#define OFDM_RATE(_idx, _rate) { \ - .bitrate = _rate, \ - .hw_value = (MT_PHY_TYPE_OFDM << 8) | (_idx), \ - .hw_value_short = (MT_PHY_TYPE_OFDM << 8) | (_idx), \ -} - -struct ieee80211_rate mt7615_rates[] = { - CCK_RATE(0, 10), - CCK_RATE(1, 20), - CCK_RATE(2, 55), - CCK_RATE(3, 110), - OFDM_RATE(11, 60), - OFDM_RATE(15, 90), - OFDM_RATE(10, 120), - OFDM_RATE(14, 180), - OFDM_RATE(9, 240), - OFDM_RATE(13, 360), - OFDM_RATE(8, 480), - OFDM_RATE(12, 540), -}; -EXPORT_SYMBOL_GPL(mt7615_rates); - static const struct ieee80211_iface_limit if_limits[] = { { .max = 1, @@ -362,7 +383,7 @@ mt7615_init_wiphy(struct ieee80211_hw *hw) wiphy->reg_notifier = mt7615_regd_notifier; wiphy->max_sched_scan_plan_interval = - MT76_CONNAC_MAX_SCHED_SCAN_INTERVAL; + MT76_CONNAC_MAX_TIME_SCHED_SCAN_INTERVAL; wiphy->max_sched_scan_ie_len = IEEE80211_MAX_DATA_LEN; wiphy->max_scan_ie_len = MT76_CONNAC_SCAN_IE_LEN; wiphy->max_sched_scan_ssids = MT76_CONNAC_MAX_SCHED_SCAN_SSID; @@ -472,8 +493,8 @@ int mt7615_register_ext_phy(struct mt7615_dev *dev) for (i = 0; i <= MT_TXQ_PSD ; i++) mphy->q_tx[i] = dev->mphy.q_tx[i]; - ret = mt76_register_phy(mphy, true, mt7615_rates, - ARRAY_SIZE(mt7615_rates)); + ret = mt76_register_phy(mphy, true, mt76_rates, + ARRAY_SIZE(mt76_rates)); if (ret) ieee80211_free_hw(mphy->hw); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c index e2dcfee6be81..ff3f85e4087c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.c @@ -20,7 +20,7 @@ #define to_rssi(field, rxv) ((FIELD_GET(field, rxv) - 220) / 2) static const struct mt7615_dfs_radar_spec etsi_radar_specs = { - .pulse_th = { 40, -10, -80, 800, 3360, 128, 5200 }, + .pulse_th = { 110, -10, -80, 40, 5200, 128, 5200 }, .radar_pattern = { [5] = { 1, 0, 6, 32, 28, 0, 17, 990, 5010, 1, 1 }, [6] = { 1, 0, 9, 32, 28, 0, 27, 615, 5010, 1, 1 }, @@ -34,7 +34,7 @@ static const struct mt7615_dfs_radar_spec etsi_radar_specs = { }; static const struct mt7615_dfs_radar_spec fcc_radar_specs = { - .pulse_th = { 40, -10, -80, 800, 3360, 128, 5200 }, + .pulse_th = { 110, -10, -80, 40, 5200, 128, 5200 }, .radar_pattern = { [0] = { 1, 0, 9, 32, 28, 0, 13, 508, 3076, 1, 1 }, [1] = { 1, 0, 12, 32, 28, 0, 17, 140, 240, 1, 1 }, @@ -45,7 +45,7 @@ static const struct mt7615_dfs_radar_spec fcc_radar_specs = { }; static const struct mt7615_dfs_radar_spec jp_radar_specs = { - .pulse_th = { 40, -10, -80, 800, 3360, 128, 5200 }, + .pulse_th = { 110, -10, -80, 40, 5200, 128, 5200 }, .radar_pattern = { [0] = { 1, 0, 8, 32, 28, 0, 13, 508, 3076, 1, 1 }, [1] = { 1, 0, 12, 32, 28, 0, 17, 140, 240, 1, 1 }, @@ -57,6 +57,33 @@ static const struct mt7615_dfs_radar_spec jp_radar_specs = { }, }; +static enum mt76_cipher_type +mt7615_mac_get_cipher(int cipher) +{ + switch (cipher) { + case WLAN_CIPHER_SUITE_WEP40: + return MT_CIPHER_WEP40; + case WLAN_CIPHER_SUITE_WEP104: + return MT_CIPHER_WEP104; + case WLAN_CIPHER_SUITE_TKIP: + return MT_CIPHER_TKIP; + case WLAN_CIPHER_SUITE_AES_CMAC: + return MT_CIPHER_BIP_CMAC_128; + case WLAN_CIPHER_SUITE_CCMP: + return MT_CIPHER_AES_CCMP; + case WLAN_CIPHER_SUITE_CCMP_256: + return MT_CIPHER_CCMP_256; + case WLAN_CIPHER_SUITE_GCMP: + return MT_CIPHER_GCMP; + case WLAN_CIPHER_SUITE_GCMP_256: + return MT_CIPHER_GCMP_256; + case WLAN_CIPHER_SUITE_SMS4: + return MT_CIPHER_WAPI; + default: + return MT_CIPHER_NONE; + } +} + static struct mt76_wcid *mt7615_rx_get_wcid(struct mt7615_dev *dev, u8 idx, bool unicast) { @@ -313,14 +340,27 @@ static int mt7615_mac_fill_rx(struct mt7615_dev *dev, struct sk_buff *skb) u8 *data = (u8 *)rxd; if (status->flag & RX_FLAG_DECRYPTED) { - status->iv[0] = data[5]; - status->iv[1] = data[4]; - status->iv[2] = data[3]; - status->iv[3] = data[2]; - status->iv[4] = data[1]; - status->iv[5] = data[0]; - - insert_ccmp_hdr = FIELD_GET(MT_RXD2_NORMAL_FRAG, rxd2); + switch (FIELD_GET(MT_RXD2_NORMAL_SEC_MODE, rxd2)) { + case MT_CIPHER_AES_CCMP: + case MT_CIPHER_CCMP_CCX: + case MT_CIPHER_CCMP_256: + insert_ccmp_hdr = + FIELD_GET(MT_RXD2_NORMAL_FRAG, rxd2); + fallthrough; + case MT_CIPHER_TKIP: + case MT_CIPHER_TKIP_NO_MIC: + case MT_CIPHER_GCMP: + case MT_CIPHER_GCMP_256: + status->iv[0] = data[5]; + status->iv[1] = data[4]; + status->iv[2] = data[3]; + status->iv[3] = data[2]; + status->iv[4] = data[1]; + status->iv[5] = data[0]; + break; + default: + break; + } } rxd += 4; if ((u8 *)rxd - skb->data >= skb->len) @@ -1062,7 +1102,7 @@ void mt7615_mac_set_rates(struct mt7615_phy *phy, struct mt7615_sta *sta, idx = idx > HW_BSSID_MAX ? HW_BSSID_0 : idx; addr = idx > 1 ? MT_LPON_TCR2(idx): MT_LPON_TCR0(idx); - mt76_set(dev, addr, MT_LPON_TCR_MODE); /* TSF read */ + mt76_rmw(dev, addr, MT_LPON_TCR_MODE, MT_LPON_TCR_READ); /* TSF read */ sta->rate_set_tsf = mt76_rr(dev, MT_LPON_UTTR0) & ~BIT(0); sta->rate_set_tsf |= rd.rateset; @@ -1078,7 +1118,7 @@ EXPORT_SYMBOL_GPL(mt7615_mac_set_rates); static int mt7615_mac_wtbl_update_key(struct mt7615_dev *dev, struct mt76_wcid *wcid, struct ieee80211_key_conf *key, - enum mt7615_cipher_type cipher, u16 cipher_mask, + enum mt76_cipher_type cipher, u16 cipher_mask, enum set_key_cmd cmd) { u32 addr = mt7615_mac_wtbl_addr(dev, wcid->idx) + 30 * 4; @@ -1118,7 +1158,7 @@ mt7615_mac_wtbl_update_key(struct mt7615_dev *dev, struct mt76_wcid *wcid, static int mt7615_mac_wtbl_update_pk(struct mt7615_dev *dev, struct mt76_wcid *wcid, - enum mt7615_cipher_type cipher, u16 cipher_mask, + enum mt76_cipher_type cipher, u16 cipher_mask, int keyidx, enum set_key_cmd cmd) { u32 addr = mt7615_mac_wtbl_addr(dev, wcid->idx), w0, w1; @@ -1157,7 +1197,7 @@ mt7615_mac_wtbl_update_pk(struct mt7615_dev *dev, struct mt76_wcid *wcid, static void mt7615_mac_wtbl_update_cipher(struct mt7615_dev *dev, struct mt76_wcid *wcid, - enum mt7615_cipher_type cipher, u16 cipher_mask, + enum mt76_cipher_type cipher, u16 cipher_mask, enum set_key_cmd cmd) { u32 addr = mt7615_mac_wtbl_addr(dev, wcid->idx); @@ -1183,7 +1223,7 @@ int __mt7615_mac_wtbl_set_key(struct mt7615_dev *dev, struct ieee80211_key_conf *key, enum set_key_cmd cmd) { - enum mt7615_cipher_type cipher; + enum mt76_cipher_type cipher; u16 cipher_mask = wcid->cipher; int err; @@ -1235,22 +1275,20 @@ static bool mt7615_fill_txs(struct mt7615_dev *dev, struct mt7615_sta *sta, int first_idx = 0, last_idx; int i, idx, count; bool fixed_rate, ack_timeout; - bool probe, ampdu, cck = false; + bool ampdu, cck = false; bool rs_idx; u32 rate_set_tsf; u32 final_rate, final_rate_flags, final_nss, txs; - fixed_rate = info->status.rates[0].count; - probe = !!(info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE); - txs = le32_to_cpu(txs_data[1]); - ampdu = !fixed_rate && (txs & MT_TXS1_AMPDU); + ampdu = txs & MT_TXS1_AMPDU; txs = le32_to_cpu(txs_data[3]); count = FIELD_GET(MT_TXS3_TX_COUNT, txs); last_idx = FIELD_GET(MT_TXS3_LAST_TX_RATE, txs); txs = le32_to_cpu(txs_data[0]); + fixed_rate = txs & MT_TXS0_FIXED_RATE; final_rate = FIELD_GET(MT_TXS0_TX_RATE, txs); ack_timeout = txs & MT_TXS0_ACK_TIMEOUT; @@ -1272,7 +1310,7 @@ static bool mt7615_fill_txs(struct mt7615_dev *dev, struct mt7615_sta *sta, first_idx = max_t(int, 0, last_idx - (count - 1) / MT7615_RATE_RETRY); - if (fixed_rate && !probe) { + if (fixed_rate) { info->status.rates[0].count = count; i = 0; goto out; @@ -1391,7 +1429,7 @@ static bool mt7615_mac_add_txs_skb(struct mt7615_dev *dev, struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); if (!mt7615_fill_txs(dev, sta, info, txs_data)) { - ieee80211_tx_info_clear_status(info); + info->status.rates[0].count = 0; info->status.rates[0].idx = -1; } @@ -1821,43 +1859,41 @@ mt7615_phy_update_channel(struct mt76_phy *mphy, int idx) state->noise = -(phy->noise >> 4); } -static void __mt7615_update_channel(struct mt7615_dev *dev) -{ - struct mt76_dev *mdev = &dev->mt76; - - mt7615_phy_update_channel(&mdev->phy, 0); - if (mdev->phy2) - mt7615_phy_update_channel(mdev->phy2, 1); - - /* reset obss airtime */ - mt76_set(dev, MT_WF_RMAC_MIB_TIME0, MT_WF_RMAC_MIB_RXTIME_CLR); -} - -void mt7615_update_channel(struct mt76_dev *mdev) -{ - struct mt7615_dev *dev = container_of(mdev, struct mt7615_dev, mt76); - - if (mt76_connac_pm_wake(&dev->mphy, &dev->pm)) - return; - - __mt7615_update_channel(dev); - mt76_connac_power_save_sched(&dev->mphy, &dev->pm); -} -EXPORT_SYMBOL_GPL(mt7615_update_channel); - static void mt7615_update_survey(struct mt7615_dev *dev) { struct mt76_dev *mdev = &dev->mt76; ktime_t cur_time; - __mt7615_update_channel(dev); + /* MT7615 can only update both phys simultaneously + * since some reisters are shared across bands. + */ + + mt7615_phy_update_channel(&mdev->phy, 0); + if (mdev->phy2) + mt7615_phy_update_channel(mdev->phy2, 1); + cur_time = ktime_get_boottime(); mt76_update_survey_active_time(&mdev->phy, cur_time); if (mdev->phy2) mt76_update_survey_active_time(mdev->phy2, cur_time); + + /* reset obss airtime */ + mt76_set(dev, MT_WF_RMAC_MIB_TIME0, MT_WF_RMAC_MIB_RXTIME_CLR); } +void mt7615_update_channel(struct mt76_phy *mphy) +{ + struct mt7615_dev *dev = container_of(mphy->dev, struct mt7615_dev, mt76); + + if (mt76_connac_pm_wake(&dev->mphy, &dev->pm)) + return; + + mt7615_update_survey(dev); + mt76_connac_power_save_sched(&dev->mphy, &dev->pm); +} +EXPORT_SYMBOL_GPL(mt7615_update_channel); + static void mt7615_mac_update_mib_stats(struct mt7615_phy *phy) { @@ -1906,15 +1942,26 @@ void mt7615_pm_wake_work(struct work_struct *work) mphy = dev->phy.mt76; if (!mt7615_mcu_set_drv_ctrl(dev)) { + struct mt76_dev *mdev = &dev->mt76; int i; - mt76_for_each_q_rx(&dev->mt76, i) - napi_schedule(&dev->mt76.napi[i]); - mt76_connac_pm_dequeue_skbs(mphy, &dev->pm); - mt76_queue_tx_cleanup(dev, dev->mt76.q_mcu[MT_MCUQ_WM], false); - if (test_bit(MT76_STATE_RUNNING, &mphy->state)) + if (mt76_is_sdio(mdev)) { + mt76_worker_schedule(&mdev->sdio.txrx_worker); + } else { + mt76_for_each_q_rx(mdev, i) + napi_schedule(&mdev->napi[i]); + mt76_connac_pm_dequeue_skbs(mphy, &dev->pm); + mt76_queue_tx_cleanup(dev, mdev->q_mcu[MT_MCUQ_WM], + false); + } + + if (test_bit(MT76_STATE_RUNNING, &mphy->state)) { + unsigned long timeout; + + timeout = mt7615_get_macwork_timeout(dev); ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work, - MT7615_WATCHDOG_TIME); + timeout); + } } ieee80211_wake_queues(mphy->hw); @@ -1949,6 +1996,7 @@ void mt7615_mac_work(struct work_struct *work) { struct mt7615_phy *phy; struct mt76_phy *mphy; + unsigned long timeout; mphy = (struct mt76_phy *)container_of(work, struct mt76_phy, mac_work.work); @@ -1967,8 +2015,9 @@ void mt7615_mac_work(struct work_struct *work) mt7615_mutex_release(phy->dev); mt76_tx_status_check(mphy->dev, NULL, false); - ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work, - MT7615_WATCHDOG_TIME); + + timeout = mt7615_get_macwork_timeout(phy->dev); + ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work, timeout); } void mt7615_tx_token_put(struct mt7615_dev *dev) @@ -2049,14 +2098,12 @@ mt7615_dfs_init_radar_specs(struct mt7615_phy *phy) { const struct mt7615_dfs_radar_spec *radar_specs; struct mt7615_dev *dev = phy->dev; - int err, i; + int err, i, lpn = 500; switch (dev->mt76.region) { case NL80211_DFS_FCC: radar_specs = &fcc_radar_specs; - err = mt7615_mcu_set_fcc5_lpn(dev, 8); - if (err < 0) - return err; + lpn = 8; break; case NL80211_DFS_ETSI: radar_specs = &etsi_radar_specs; @@ -2068,6 +2115,11 @@ mt7615_dfs_init_radar_specs(struct mt7615_phy *phy) return -EINVAL; } + /* avoid FCC radar detection in non-FCC region */ + err = mt7615_mcu_set_fcc5_lpn(dev, lpn); + if (err < 0) + return err; + for (i = 0; i < ARRAY_SIZE(radar_specs->radar_pattern); i++) { err = mt7615_mcu_set_radar_th(dev, i, &radar_specs->radar_pattern[i]); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mac.h b/drivers/net/wireless/mediatek/mt76/mt7615/mac.h index 6bf9da040196..46f283eb8d0f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mac.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mac.h @@ -383,48 +383,6 @@ struct mt7615_dfs_radar_spec { struct mt7615_dfs_pattern radar_pattern[16]; }; -enum mt7615_cipher_type { - MT_CIPHER_NONE, - MT_CIPHER_WEP40, - MT_CIPHER_TKIP, - MT_CIPHER_TKIP_NO_MIC, - MT_CIPHER_AES_CCMP, - MT_CIPHER_WEP104, - MT_CIPHER_BIP_CMAC_128, - MT_CIPHER_WEP128, - MT_CIPHER_WAPI, - MT_CIPHER_CCMP_256 = 10, - MT_CIPHER_GCMP, - MT_CIPHER_GCMP_256, -}; - -static inline enum mt7615_cipher_type -mt7615_mac_get_cipher(int cipher) -{ - switch (cipher) { - case WLAN_CIPHER_SUITE_WEP40: - return MT_CIPHER_WEP40; - case WLAN_CIPHER_SUITE_WEP104: - return MT_CIPHER_WEP104; - case WLAN_CIPHER_SUITE_TKIP: - return MT_CIPHER_TKIP; - case WLAN_CIPHER_SUITE_AES_CMAC: - return MT_CIPHER_BIP_CMAC_128; - case WLAN_CIPHER_SUITE_CCMP: - return MT_CIPHER_AES_CCMP; - case WLAN_CIPHER_SUITE_CCMP_256: - return MT_CIPHER_CCMP_256; - case WLAN_CIPHER_SUITE_GCMP: - return MT_CIPHER_GCMP; - case WLAN_CIPHER_SUITE_GCMP_256: - return MT_CIPHER_GCMP_256; - case WLAN_CIPHER_SUITE_SMS4: - return MT_CIPHER_WAPI; - default: - return MT_CIPHER_NONE; - } -} - static inline struct mt7615_txp_common * mt7615_txwi_to_txp(struct mt76_dev *dev, struct mt76_txwi_cache *t) { diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c index 39733b351ac4..dada43d6d879 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c @@ -28,6 +28,7 @@ static int mt7615_start(struct ieee80211_hw *hw) { struct mt7615_dev *dev = mt7615_hw_dev(hw); struct mt7615_phy *phy = mt7615_hw_phy(hw); + unsigned long timeout; bool running; int ret; @@ -78,8 +79,8 @@ static int mt7615_start(struct ieee80211_hw *hw) set_bit(MT76_STATE_RUNNING, &phy->mt76->state); - ieee80211_queue_delayed_work(hw, &phy->mt76->mac_work, - MT7615_WATCHDOG_TIME); + timeout = mt7615_get_macwork_timeout(dev); + ieee80211_queue_delayed_work(hw, &phy->mt76->mac_work, timeout); if (!running) mt7615_mac_reset_counters(dev); @@ -240,8 +241,6 @@ static int mt7615_add_interface(struct ieee80211_hw *hw, } ret = mt7615_mcu_add_dev_info(phy, vif, true); - if (ret) - goto out; out: mt7615_mutex_release(dev); @@ -352,10 +351,12 @@ out: mt7615_mutex_release(dev); mt76_worker_schedule(&dev->mt76.tx_worker); - if (!mt76_testmode_enabled(phy->mt76)) + if (!mt76_testmode_enabled(phy->mt76)) { + unsigned long timeout = mt7615_get_macwork_timeout(dev); + ieee80211_queue_delayed_work(phy->mt76->hw, - &phy->mt76->mac_work, - MT7615_WATCHDOG_TIME); + &phy->mt76->mac_work, timeout); + } return ret; } @@ -695,7 +696,7 @@ static void mt7615_sta_rate_tbl_update(struct ieee80211_hw *hw, msta->n_rates = i; if (mt76_connac_pm_ref(phy->mt76, &dev->pm)) { mt7615_mac_set_rates(phy, msta, NULL, msta->rates); - mt76_connac_pm_unref(&dev->pm); + mt76_connac_pm_unref(phy->mt76, &dev->pm); } spin_unlock_bh(&dev->mt76.lock); } @@ -711,7 +712,7 @@ void mt7615_tx_worker(struct mt76_worker *w) } mt76_tx_worker_run(&dev->mt76); - mt76_connac_pm_unref(&dev->pm); + mt76_connac_pm_unref(&dev->mphy, &dev->pm); } static void mt7615_tx(struct ieee80211_hw *hw, @@ -741,7 +742,7 @@ static void mt7615_tx(struct ieee80211_hw *hw, if (mt76_connac_pm_ref(mphy, &dev->pm)) { mt76_tx(mphy, control->sta, wcid, skb); - mt76_connac_pm_unref(&dev->pm); + mt76_connac_pm_unref(mphy, &dev->pm); return; } @@ -881,7 +882,8 @@ mt7615_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) mt7615_mutex_acquire(dev); - mt76_set(dev, reg, MT_LPON_TCR_MODE); /* TSF read */ + /* TSF read */ + mt76_rmw(dev, reg, MT_LPON_TCR_MODE, MT_LPON_TCR_READ); tsf.t32[0] = mt76_rr(dev, MT_LPON_UTTR0); tsf.t32[1] = mt76_rr(dev, MT_LPON_UTTR1); @@ -911,7 +913,33 @@ mt7615_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif, mt76_wr(dev, MT_LPON_UTTR0, tsf.t32[0]); mt76_wr(dev, MT_LPON_UTTR1, tsf.t32[1]); /* TSF software overwrite */ - mt76_set(dev, reg, MT_LPON_TCR_WRITE); + mt76_rmw(dev, reg, MT_LPON_TCR_MODE, MT_LPON_TCR_WRITE); + + mt7615_mutex_release(dev); +} + +static void +mt7615_offset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + s64 timestamp) +{ + struct mt7615_vif *mvif = (struct mt7615_vif *)vif->drv_priv; + struct mt7615_dev *dev = mt7615_hw_dev(hw); + union { + u64 t64; + u32 t32[2]; + } tsf = { .t64 = timestamp, }; + u16 idx = mvif->mt76.omac_idx; + u32 reg; + + idx = idx > HW_BSSID_MAX ? HW_BSSID_0 : idx; + reg = idx > 1 ? MT_LPON_TCR2(idx): MT_LPON_TCR0(idx); + + mt7615_mutex_acquire(dev); + + mt76_wr(dev, MT_LPON_UTTR0, tsf.t32[0]); + mt76_wr(dev, MT_LPON_UTTR1, tsf.t32[1]); + /* TSF software adjust*/ + mt76_rmw(dev, reg, MT_LPON_TCR_MODE, MT_LPON_TCR_ADJUST); mt7615_mutex_release(dev); } @@ -1162,7 +1190,7 @@ static void mt7615_sta_set_decap_offload(struct ieee80211_hw *hw, else clear_bit(MT_WCID_FLAG_HDR_TRANS, &msta->wcid.flags); - mt7615_mcu_sta_update_hdr_trans(dev, vif, sta); + mt7615_mcu_set_sta_decap_offload(dev, vif, sta); } #ifdef CONFIG_PM @@ -1200,6 +1228,7 @@ static int mt7615_resume(struct ieee80211_hw *hw) { struct mt7615_phy *phy = mt7615_hw_phy(hw); struct mt7615_dev *dev = mt7615_hw_dev(hw); + unsigned long timeout; bool running; mt7615_mutex_acquire(dev); @@ -1223,8 +1252,8 @@ static int mt7615_resume(struct ieee80211_hw *hw) mt76_connac_mcu_set_suspend_iter, phy->mt76); - ieee80211_queue_delayed_work(hw, &phy->mt76->mac_work, - MT7615_WATCHDOG_TIME); + timeout = mt7615_get_macwork_timeout(dev); + ieee80211_queue_delayed_work(hw, &phy->mt76->mac_work, timeout); mt7615_mutex_release(dev); @@ -1278,6 +1307,7 @@ const struct ieee80211_ops mt7615_ops = { .get_stats = mt7615_get_stats, .get_tsf = mt7615_get_tsf, .set_tsf = mt7615_set_tsf, + .offset_tsf = mt7615_offset_tsf, .get_survey = mt76_get_survey, .get_antenna = mt76_get_antenna, .set_antenna = mt7615_set_antenna, diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c index aa42af9ebfd6..f8a09692d3e4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c @@ -411,6 +411,9 @@ mt7615_mcu_rx_csa_notify(struct mt7615_dev *dev, struct sk_buff *skb) c = (struct mt7615_mcu_csa_notify *)skb->data; + if (c->omac_idx > EXT_BSSID_MAX) + return; + if (ext_phy && ext_phy->omac_mask & BIT_ULL(c->omac_idx)) mphy = dev->mt76.phy2; @@ -427,6 +430,10 @@ mt7615_mcu_rx_radar_detected(struct mt7615_dev *dev, struct sk_buff *skb) r = (struct mt7615_mcu_rdd_report *)skb->data; + if (!dev->radar_pattern.n_pulses && !r->long_detected && + !r->constant_prf_detected && !r->staggered_prf_detected) + return; + if (r->band_idx && dev->mt76.phy2) mphy = dev->mt76.phy2; @@ -1021,9 +1028,10 @@ mt7615_mcu_wtbl_sta_add(struct mt7615_phy *phy, struct ieee80211_vif *vif, if (IS_ERR(sskb)) return PTR_ERR(sskb); - mt76_connac_mcu_sta_basic_tlv(sskb, vif, sta, enable); + mt76_connac_mcu_sta_basic_tlv(sskb, vif, sta, enable, true); if (enable && sta) - mt76_connac_mcu_sta_tlv(phy->mt76, sskb, sta, vif, 0); + mt76_connac_mcu_sta_tlv(phy->mt76, sskb, sta, vif, 0, + MT76_STA_INFO_STATE_ASSOC); wtbl_hdr = mt76_connac_mcu_alloc_wtbl_req(&dev->mt76, &msta->wcid, WTBL_RESET_AND_SET, NULL, @@ -1037,8 +1045,8 @@ mt7615_mcu_wtbl_sta_add(struct mt7615_phy *phy, struct ieee80211_vif *vif, if (sta) mt76_connac_mcu_wtbl_ht_tlv(&dev->mt76, wskb, sta, NULL, wtbl_hdr); - mt76_connac_mcu_wtbl_hdr_trans_tlv(wskb, &msta->wcid, NULL, - wtbl_hdr); + mt76_connac_mcu_wtbl_hdr_trans_tlv(wskb, vif, &msta->wcid, + NULL, wtbl_hdr); } cmd = enable ? MCU_EXT_CMD_WTBL_UPDATE : MCU_EXT_CMD_STA_REC_UPDATE; @@ -1058,6 +1066,26 @@ mt7615_mcu_wtbl_sta_add(struct mt7615_phy *phy, struct ieee80211_vif *vif, return mt76_mcu_skb_send_msg(&dev->mt76, skb, cmd, true); } +static int +mt7615_mcu_wtbl_update_hdr_trans(struct mt7615_dev *dev, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta) +{ + struct mt7615_sta *msta = (struct mt7615_sta *)sta->drv_priv; + struct wtbl_req_hdr *wtbl_hdr; + struct sk_buff *skb = NULL; + + wtbl_hdr = mt76_connac_mcu_alloc_wtbl_req(&dev->mt76, &msta->wcid, + WTBL_SET, NULL, &skb); + if (IS_ERR(wtbl_hdr)) + return PTR_ERR(wtbl_hdr); + + mt76_connac_mcu_wtbl_hdr_trans_tlv(skb, vif, &msta->wcid, NULL, + wtbl_hdr); + return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_EXT_CMD_WTBL_UPDATE, + true); +} + static const struct mt7615_mcu_ops wtbl_update_ops = { .add_beacon_offload = mt7615_mcu_add_beacon_offload, .set_pm_state = mt7615_mcu_ctrl_pm_state, @@ -1068,6 +1096,7 @@ static const struct mt7615_mcu_ops wtbl_update_ops = { .sta_add = mt7615_mcu_wtbl_sta_add, .set_drv_ctrl = mt7615_mcu_drv_pmctrl, .set_fw_ctrl = mt7615_mcu_fw_pmctrl, + .set_sta_decap_offload = mt7615_mcu_wtbl_update_hdr_trans, }; static int @@ -1120,18 +1149,21 @@ mt7615_mcu_sta_rx_ba(struct mt7615_dev *dev, static int __mt7615_mcu_add_sta(struct mt76_phy *phy, struct ieee80211_vif *vif, - struct ieee80211_sta *sta, bool enable, int cmd) + struct ieee80211_sta *sta, bool enable, int cmd, + bool offload_fw) { struct mt7615_vif *mvif = (struct mt7615_vif *)vif->drv_priv; struct mt76_sta_cmd_info info = { .sta = sta, .vif = vif, + .offload_fw = offload_fw, .enable = enable, + .newly = true, .cmd = cmd, }; info.wcid = sta ? (struct mt76_wcid *)sta->drv_priv : &mvif->sta.wcid; - return mt76_connac_mcu_add_sta_cmd(phy, &info); + return mt76_connac_mcu_sta_cmd(phy, &info); } static int @@ -1139,7 +1171,19 @@ mt7615_mcu_add_sta(struct mt7615_phy *phy, struct ieee80211_vif *vif, struct ieee80211_sta *sta, bool enable) { return __mt7615_mcu_add_sta(phy->mt76, vif, sta, enable, - MCU_EXT_CMD_STA_REC_UPDATE); + MCU_EXT_CMD_STA_REC_UPDATE, false); +} + +static int +mt7615_mcu_sta_update_hdr_trans(struct mt7615_dev *dev, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta) +{ + struct mt7615_sta *msta = (struct mt7615_sta *)sta->drv_priv; + + return mt76_connac_mcu_sta_update_hdr_trans(&dev->mt76, + vif, &msta->wcid, + MCU_EXT_CMD_STA_REC_UPDATE); } static const struct mt7615_mcu_ops sta_update_ops = { @@ -1152,27 +1196,9 @@ static const struct mt7615_mcu_ops sta_update_ops = { .sta_add = mt7615_mcu_add_sta, .set_drv_ctrl = mt7615_mcu_drv_pmctrl, .set_fw_ctrl = mt7615_mcu_fw_pmctrl, + .set_sta_decap_offload = mt7615_mcu_sta_update_hdr_trans, }; -int mt7615_mcu_sta_update_hdr_trans(struct mt7615_dev *dev, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta) -{ - struct mt7615_sta *msta = (struct mt7615_sta *)sta->drv_priv; - struct wtbl_req_hdr *wtbl_hdr; - struct sk_buff *skb = NULL; - - wtbl_hdr = mt76_connac_mcu_alloc_wtbl_req(&dev->mt76, &msta->wcid, - WTBL_SET, NULL, &skb); - if (IS_ERR(wtbl_hdr)) - return PTR_ERR(wtbl_hdr); - - mt76_connac_mcu_wtbl_hdr_trans_tlv(skb, &msta->wcid, NULL, wtbl_hdr); - - return mt76_mcu_skb_send_msg(&dev->mt76, skb, MCU_EXT_CMD_WTBL_UPDATE, - true); -} - static int mt7615_mcu_uni_ctrl_pm_state(struct mt7615_dev *dev, int band, int state) { @@ -1280,7 +1306,7 @@ mt7615_mcu_uni_add_sta(struct mt7615_phy *phy, struct ieee80211_vif *vif, struct ieee80211_sta *sta, bool enable) { return __mt7615_mcu_add_sta(phy->mt76, vif, sta, enable, - MCU_UNI_CMD_STA_REC_UPDATE); + MCU_UNI_CMD_STA_REC_UPDATE, true); } static int @@ -1338,6 +1364,18 @@ mt7615_mcu_uni_rx_ba(struct mt7615_dev *dev, MCU_UNI_CMD_STA_REC_UPDATE, true); } +static int +mt7615_mcu_sta_uni_update_hdr_trans(struct mt7615_dev *dev, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta) +{ + struct mt7615_sta *msta = (struct mt7615_sta *)sta->drv_priv; + + return mt76_connac_mcu_sta_update_hdr_trans(&dev->mt76, + vif, &msta->wcid, + MCU_UNI_CMD_STA_REC_UPDATE); +} + static const struct mt7615_mcu_ops uni_update_ops = { .add_beacon_offload = mt7615_mcu_uni_add_beacon_offload, .set_pm_state = mt7615_mcu_uni_ctrl_pm_state, @@ -1348,6 +1386,7 @@ static const struct mt7615_mcu_ops uni_update_ops = { .sta_add = mt7615_mcu_uni_add_sta, .set_drv_ctrl = mt7615_mcu_lp_drv_pmctrl, .set_fw_ctrl = mt7615_mcu_fw_pmctrl, + .set_sta_decap_offload = mt7615_mcu_sta_uni_update_hdr_trans, }; int mt7615_mcu_restart(struct mt76_dev *dev) @@ -2322,14 +2361,12 @@ int mt7615_mcu_set_chan_info(struct mt7615_phy *phy, int cmd) return mt76_mcu_send_msg(&dev->mt76, cmd, &req, sizeof(req), true); } -int mt7615_mcu_get_temperature(struct mt7615_dev *dev, int index) +int mt7615_mcu_get_temperature(struct mt7615_dev *dev) { struct { u8 action; u8 rsv[3]; - } req = { - .action = index, - }; + } req = {}; return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD_GET_TEMP, &req, sizeof(req), true); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c index 202ea235415e..71719c787511 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mmio.c @@ -229,7 +229,7 @@ int mt7615_mmio_probe(struct device *pdev, void __iomem *mem_base, GFP_KERNEL); if (!bus_ops) { ret = -ENOMEM; - goto error; + goto err_free_dev; } bus_ops->rr = mt7615_rr; @@ -242,17 +242,20 @@ int mt7615_mmio_probe(struct device *pdev, void __iomem *mem_base, ret = devm_request_irq(mdev->dev, irq, mt7615_irq_handler, IRQF_SHARED, KBUILD_MODNAME, dev); if (ret) - goto error; + goto err_free_dev; if (is_mt7663(mdev)) mt76_wr(dev, MT_PCIE_IRQ_ENABLE, 1); ret = mt7615_register_device(dev); if (ret) - goto error; + goto err_free_irq; return 0; -error: + +err_free_irq: + devm_free_irq(pdev, irq, dev); +err_free_dev: mt76_free_device(&dev->mt76); return ret; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h index 989f05ed4377..d0c64a9b09cf 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mt7615.h @@ -20,7 +20,6 @@ MT7615_MAX_INTERFACES) #define MT7615_PM_TIMEOUT (HZ / 12) -#define MT7615_WATCHDOG_TIME (HZ / 10) #define MT7615_HW_SCAN_TIMEOUT (HZ / 10) #define MT7615_RESET_TIMEOUT (30 * HZ) #define MT7615_RATE_RETRY 2 @@ -202,6 +201,7 @@ struct mt7615_phy { #define mt7615_mcu_set_pm(dev, ...) (dev)->mcu_ops->set_pm_state((dev), __VA_ARGS__) #define mt7615_mcu_set_drv_ctrl(dev) (dev)->mcu_ops->set_drv_ctrl((dev)) #define mt7615_mcu_set_fw_ctrl(dev) (dev)->mcu_ops->set_fw_ctrl((dev)) +#define mt7615_mcu_set_sta_decap_offload(dev, ...) (dev)->mcu_ops->set_sta_decap_offload((dev), __VA_ARGS__) struct mt7615_mcu_ops { int (*add_tx_ba)(struct mt7615_dev *dev, struct ieee80211_ampdu_params *params, @@ -221,6 +221,9 @@ struct mt7615_mcu_ops { int (*set_pm_state)(struct mt7615_dev *dev, int band, int state); int (*set_drv_ctrl)(struct mt7615_dev *dev); int (*set_fw_ctrl)(struct mt7615_dev *dev); + int (*set_sta_decap_offload)(struct mt7615_dev *dev, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta); }; struct mt7615_dev { @@ -356,6 +359,7 @@ static inline int mt7622_wmac_init(struct mt7615_dev *dev) } #endif +int mt7615_thermal_init(struct mt7615_dev *dev); int mt7615_mmio_probe(struct device *pdev, void __iomem *mem_base, int irq, const u32 *map); u32 mt7615_reg_map(struct mt7615_dev *dev, u32 addr); @@ -456,6 +460,12 @@ static inline u32 mt7615_tx_mcu_int_mask(struct mt7615_dev *dev) return MT_INT_TX_DONE(dev->mt76.q_mcu[MT_MCUQ_WM]->hw_idx); } +static inline unsigned long +mt7615_get_macwork_timeout(struct mt7615_dev *dev) +{ + return dev->pm.enable ? HZ / 3 : HZ / 10; +} + void mt7615_dma_reset(struct mt7615_dev *dev); void mt7615_scan_work(struct work_struct *work); void mt7615_roc_work(struct work_struct *work); @@ -466,7 +476,7 @@ int mt7615_set_channel(struct mt7615_phy *phy); void mt7615_init_work(struct mt7615_dev *dev); int mt7615_mcu_restart(struct mt76_dev *dev); -void mt7615_update_channel(struct mt76_dev *mdev); +void mt7615_update_channel(struct mt76_phy *mphy); bool mt7615_mac_wtbl_update(struct mt7615_dev *dev, int idx, u32 mask); void mt7615_mac_reset_counters(struct mt7615_dev *dev); void mt7615_mac_cca_stats_reset(struct mt7615_phy *phy); @@ -494,7 +504,7 @@ u32 mt7615_rf_rr(struct mt7615_dev *dev, u32 wf, u32 reg); int mt7615_rf_wr(struct mt7615_dev *dev, u32 wf, u32 reg, u32 val); int mt7615_mcu_set_dbdc(struct mt7615_dev *dev); int mt7615_mcu_set_eeprom(struct mt7615_dev *dev); -int mt7615_mcu_get_temperature(struct mt7615_dev *dev, int index); +int mt7615_mcu_get_temperature(struct mt7615_dev *dev); int mt7615_mcu_set_tx_power(struct mt7615_phy *phy); void mt7615_mcu_exit(struct mt7615_dev *dev); void mt7615_mcu_fill_msg(struct mt7615_dev *dev, struct sk_buff *skb, @@ -518,9 +528,6 @@ void mt7615_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif, void mt7615_mac_work(struct work_struct *work); void mt7615_txp_skb_unmap(struct mt76_dev *dev, struct mt76_txwi_cache *txwi); -int mt7615_mcu_sta_update_hdr_trans(struct mt7615_dev *dev, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta); int mt7615_mcu_set_rx_hdr_trans_blacklist(struct mt7615_dev *dev); int mt7615_mcu_set_fcc5_lpn(struct mt7615_dev *dev, int val); int mt7615_mcu_set_pulse_th(struct mt7615_dev *dev, diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci_init.c index ec8ec1a2033f..a2465b49ecd0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/pci_init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci_init.c @@ -98,7 +98,7 @@ mt7615_led_set_config(struct led_classdev *led_cdev, addr = mt7615_reg_map(dev, MT_LED_CTRL); mt76_wr(dev, addr, val); - mt76_connac_pm_unref(&dev->pm); + mt76_connac_pm_unref(&dev->mphy, &dev->pm); } static int @@ -147,8 +147,12 @@ int mt7615_register_device(struct mt7615_dev *dev) if (ret) return ret; - ret = mt76_register_device(&dev->mt76, true, mt7615_rates, - ARRAY_SIZE(mt7615_rates)); + ret = mt76_register_device(&dev->mt76, true, mt76_rates, + ARRAY_SIZE(mt76_rates)); + if (ret) + return ret; + + ret = mt7615_thermal_init(dev); if (ret) return ret; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c index d7cbef752f9f..da87c02a73eb 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c @@ -131,20 +131,21 @@ int mt7615_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, struct mt76_tx_info *tx_info) { struct mt7615_dev *dev = container_of(mdev, struct mt7615_dev, mt76); - struct mt7615_sta *msta = container_of(wcid, struct mt7615_sta, wcid); struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx_info->skb); struct ieee80211_key_conf *key = info->control.hw_key; int pid, id; u8 *txwi = (u8 *)txwi_ptr; struct mt76_txwi_cache *t; + struct mt7615_sta *msta; void *txp; + msta = wcid ? container_of(wcid, struct mt7615_sta, wcid) : NULL; if (!wcid) wcid = &dev->mt76.global_wcid; pid = mt76_tx_status_skb_add(mdev, wcid, tx_info->skb); - if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) { + if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) && msta) { struct mt7615_phy *phy = &dev->phy; if ((info->hw_queue & MT_TX_HW_QUEUE_EXT_PHY) && mdev->phy2) @@ -267,6 +268,7 @@ void mt7615_mac_reset_work(struct work_struct *work) struct mt7615_phy *phy2; struct mt76_phy *ext_phy; struct mt7615_dev *dev; + unsigned long timeout; dev = container_of(work, struct mt7615_dev, reset_work); ext_phy = dev->mt76.phy2; @@ -344,11 +346,11 @@ void mt7615_mac_reset_work(struct work_struct *work) mt7615_mutex_release(dev); + timeout = mt7615_get_macwork_timeout(dev); ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mphy.mac_work, - MT7615_WATCHDOG_TIME); + timeout); if (phy2) ieee80211_queue_delayed_work(ext_phy->hw, - &phy2->mt76->mac_work, - MT7615_WATCHDOG_TIME); + &phy2->mt76->mac_work, timeout); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/regs.h b/drivers/net/wireless/mediatek/mt76/mt7615/regs.h index 63c081bb04d0..6712ad9faeaa 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/regs.h @@ -463,7 +463,9 @@ enum mt7615_reg_base { #define MT_LPON_TCR0(_n) MT_LPON(0x010 + ((_n) * 4)) #define MT_LPON_TCR2(_n) MT_LPON(0x0f8 + ((_n) - 2) * 4) #define MT_LPON_TCR_MODE GENMASK(1, 0) +#define MT_LPON_TCR_READ GENMASK(1, 0) #define MT_LPON_TCR_WRITE BIT(0) +#define MT_LPON_TCR_ADJUST BIT(1) #define MT_LPON_UTTR0 MT_LPON(0x018) #define MT_LPON_UTTR1 MT_LPON(0x01c) diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.h b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.h index 05180971de84..03877d89e152 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio.h +++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: ISC +/* SPDX-License-Identifier: ISC */ /* Copyright (C) 2020 MediaTek Inc. * * Author: Sean Wang diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c index d1be78b0711c..45c1cd3b9f49 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_mcu.c @@ -55,6 +55,7 @@ static int __mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev) { struct sdio_func *func = dev->mt76.sdio.func; struct mt76_phy *mphy = &dev->mt76.phy; + struct mt76_connac_pm *pm = &dev->pm; u32 status; int ret; @@ -66,37 +67,45 @@ static int __mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev) status & WHLPCR_IS_DRIVER_OWN, 2000, 1000000); if (ret < 0) { dev_err(dev->mt76.dev, "Cannot get ownership from device"); - set_bit(MT76_STATE_PM, &mphy->state); - sdio_release_host(func); + } else { + clear_bit(MT76_STATE_PM, &mphy->state); - return ret; + pm->stats.last_wake_event = jiffies; + pm->stats.doze_time += pm->stats.last_wake_event - + pm->stats.last_doze_event; } - sdio_release_host(func); - dev->pm.last_activity = jiffies; - return 0; + return ret; } static int mt7663s_mcu_drv_pmctrl(struct mt7615_dev *dev) { struct mt76_phy *mphy = &dev->mt76.phy; + int ret = 0; - if (test_and_clear_bit(MT76_STATE_PM, &mphy->state)) - return __mt7663s_mcu_drv_pmctrl(dev); + mutex_lock(&dev->pm.mutex); - return 0; + if (test_bit(MT76_STATE_PM, &mphy->state)) + ret = __mt7663s_mcu_drv_pmctrl(dev); + + mutex_unlock(&dev->pm.mutex); + + return ret; } static int mt7663s_mcu_fw_pmctrl(struct mt7615_dev *dev) { struct sdio_func *func = dev->mt76.sdio.func; struct mt76_phy *mphy = &dev->mt76.phy; + struct mt76_connac_pm *pm = &dev->pm; + int ret = 0; u32 status; - int ret; - if (test_and_set_bit(MT76_STATE_PM, &mphy->state)) - return 0; + mutex_lock(&pm->mutex); + + if (mt76_connac_skip_fw_pmctrl(mphy, pm)) + goto out; sdio_claim_host(func); @@ -107,9 +116,15 @@ static int mt7663s_mcu_fw_pmctrl(struct mt7615_dev *dev) if (ret < 0) { dev_err(dev->mt76.dev, "Cannot set ownership to device"); clear_bit(MT76_STATE_PM, &mphy->state); + } else { + pm->stats.last_doze_event = jiffies; + pm->stats.awake_time += pm->stats.last_doze_event - + pm->stats.last_wake_event; } sdio_release_host(func); +out: + mutex_unlock(&pm->mutex); return ret; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_txrx.c b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_txrx.c index 4393dd21ebbb..04f4c89b7499 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/sdio_txrx.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/sdio_txrx.c @@ -283,9 +283,15 @@ void mt7663s_txrx_worker(struct mt76_worker *w) { struct mt76_sdio *sdio = container_of(w, struct mt76_sdio, txrx_worker); - struct mt76_dev *dev = container_of(sdio, struct mt76_dev, sdio); + struct mt76_dev *mdev = container_of(sdio, struct mt76_dev, sdio); + struct mt7615_dev *dev = container_of(mdev, struct mt7615_dev, mt76); int i, nframes, ret; + if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) { + queue_work(mdev->wq, &dev->pm.wake_work); + return; + } + /* disable interrupt */ sdio_claim_host(sdio->func); sdio_writel(sdio->func, WHLPCR_INT_EN_CLR, MCR_WHLPCR, NULL); @@ -295,16 +301,16 @@ void mt7663s_txrx_worker(struct mt76_worker *w) /* tx */ for (i = 0; i <= MT_TXQ_PSD; i++) { - ret = mt7663s_tx_run_queue(dev, dev->phy.q_tx[i]); + ret = mt7663s_tx_run_queue(mdev, mdev->phy.q_tx[i]); if (ret > 0) nframes += ret; } - ret = mt7663s_tx_run_queue(dev, dev->q_mcu[MT_MCUQ_WM]); + ret = mt7663s_tx_run_queue(mdev, mdev->q_mcu[MT_MCUQ_WM]); if (ret > 0) nframes += ret; /* rx */ - ret = mt7663s_rx_handler(dev); + ret = mt7663s_rx_handler(mdev); if (ret > 0) nframes += ret; } while (nframes > 0); @@ -312,6 +318,8 @@ void mt7663s_txrx_worker(struct mt76_worker *w) /* enable interrupt */ sdio_writel(sdio->func, WHLPCR_INT_EN_SET, MCR_WHLPCR, NULL); sdio_release_host(sdio->func); + + mt76_connac_pm_unref(&dev->mphy, &dev->pm); } void mt7663s_sdio_irq(struct sdio_func *func) diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/soc.c b/drivers/net/wireless/mediatek/mt76/mt7615/soc.c index be9a69fe1b38..f13d1b418742 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/soc.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/soc.c @@ -31,7 +31,6 @@ int mt7622_wmac_init(struct mt7615_dev *dev) static int mt7622_wmac_probe(struct platform_device *pdev) { - struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); void __iomem *mem_base; int irq; @@ -39,7 +38,7 @@ static int mt7622_wmac_probe(struct platform_device *pdev) if (irq < 0) return irq; - mem_base = devm_ioremap_resource(&pdev->dev, res); + mem_base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(mem_base)) return PTR_ERR(mem_base); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c index f8d3673c2cae..996d48cca18a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/usb_sdio.c @@ -123,7 +123,7 @@ static int mt7663_usb_sdio_set_rates(struct mt7615_dev *dev, idx = idx > HW_BSSID_MAX ? HW_BSSID_0 : idx; addr = idx > 1 ? MT_LPON_TCR2(idx): MT_LPON_TCR0(idx); - mt76_set(dev, addr, MT_LPON_TCR_MODE); /* TSF read */ + mt76_rmw(dev, addr, MT_LPON_TCR_MODE, MT_LPON_TCR_READ); /* TSF read */ val = mt76_rr(dev, MT_LPON_UTTR0); sta->rate_set_tsf = (val & ~BIT(0)) | rate->rateset; @@ -191,14 +191,15 @@ int mt7663_usb_sdio_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, struct ieee80211_sta *sta, struct mt76_tx_info *tx_info) { - struct mt7615_sta *msta = container_of(wcid, struct mt7615_sta, wcid); struct mt7615_dev *dev = container_of(mdev, struct mt7615_dev, mt76); struct sk_buff *skb = tx_info->skb; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct mt7615_sta *msta; int pad; + msta = wcid ? container_of(wcid, struct mt7615_sta, wcid) : NULL; if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) && - !msta->rate_probe) { + msta && !msta->rate_probe) { /* request to configure sampling rate */ spin_lock_bh(&dev->mt76.lock); mt7615_mac_set_rates(&dev->phy, msta, &info->control.rates[0], @@ -323,8 +324,8 @@ int mt7663_usb_sdio_register_device(struct mt7615_dev *dev) hw->max_tx_fragments = 1; } - err = mt76_register_device(&dev->mt76, true, mt7615_rates, - ARRAY_SIZE(mt7615_rates)); + err = mt76_register_device(&dev->mt76, true, mt76_rates, + ARRAY_SIZE(mt76_rates)); if (err < 0) return err; diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac.h index 6c889b90fd12..f49d97d0a1c5 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac.h @@ -7,12 +7,13 @@ #include "mt76.h" #define MT76_CONNAC_SCAN_IE_LEN 600 -#define MT76_CONNAC_MAX_SCHED_SCAN_INTERVAL 10 +#define MT76_CONNAC_MAX_NUM_SCHED_SCAN_INTERVAL 10 +#define MT76_CONNAC_MAX_TIME_SCHED_SCAN_INTERVAL U16_MAX #define MT76_CONNAC_MAX_SCHED_SCAN_SSID 10 #define MT76_CONNAC_MAX_SCAN_MATCH 16 #define MT76_CONNAC_COREDUMP_TIMEOUT (HZ / 20) -#define MT76_CONNAC_COREDUMP_SZ (128 * 1024) +#define MT76_CONNAC_COREDUMP_SZ (1300 * 1024) enum { CMD_CBW_20MHZ = IEEE80211_STA_RX_BW_20, @@ -45,6 +46,8 @@ enum { struct mt76_connac_pm { bool enable; + bool ds_enable; + bool suspended; spinlock_t txq_lock; struct { @@ -116,19 +119,27 @@ out: } static inline void -mt76_connac_pm_unref(struct mt76_connac_pm *pm) +mt76_connac_pm_unref(struct mt76_phy *phy, struct mt76_connac_pm *pm) { spin_lock_bh(&pm->wake.lock); - pm->wake.count--; + pm->last_activity = jiffies; + if (--pm->wake.count == 0 && + test_bit(MT76_STATE_MCU_RUNNING, &phy->state)) + mt76_connac_power_save_sched(phy, pm); + spin_unlock_bh(&pm->wake.lock); } static inline bool mt76_connac_skip_fw_pmctrl(struct mt76_phy *phy, struct mt76_connac_pm *pm) { + struct mt76_dev *dev = phy->dev; bool ret; + if (dev->token_count) + return true; + spin_lock_bh(&pm->wake.lock); ret = pm->wake.count || test_and_set_bit(MT76_STATE_PM, &phy->state); spin_unlock_bh(&pm->wake.lock); diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index 6f180c92d413..af43bcb54578 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -10,13 +10,16 @@ int mt76_connac_pm_wake(struct mt76_phy *phy, struct mt76_connac_pm *pm) if (!pm->enable) return 0; - if (!mt76_is_mmio(dev)) + if (mt76_is_usb(dev)) return 0; cancel_delayed_work_sync(&pm->ps_work); if (!test_bit(MT76_STATE_PM, &phy->state)) return 0; + if (pm->suspended) + return 0; + queue_work(dev->wq, &pm->wake_work); if (!wait_event_timeout(pm->wait, !test_bit(MT76_STATE_PM, &phy->state), @@ -34,12 +37,15 @@ void mt76_connac_power_save_sched(struct mt76_phy *phy, { struct mt76_dev *dev = phy->dev; - if (!mt76_is_mmio(dev)) + if (mt76_is_usb(dev)) return; if (!pm->enable) return; + if (pm->suspended) + return; + pm->last_activity = jiffies; if (!test_bit(MT76_STATE_PM, &phy->state)) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c index 619561606f96..5c3a81e5f559 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c @@ -304,7 +304,7 @@ EXPORT_SYMBOL_GPL(mt76_connac_mcu_alloc_wtbl_req); void mt76_connac_mcu_sta_basic_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, struct ieee80211_sta *sta, - bool enable) + bool enable, bool newly) { struct sta_rec_basic *basic; struct tlv *tlv; @@ -316,7 +316,8 @@ void mt76_connac_mcu_sta_basic_tlv(struct sk_buff *skb, basic->extra_info = cpu_to_le16(EXTRA_INFO_VER); if (enable) { - basic->extra_info |= cpu_to_le16(EXTRA_INFO_NEW); + if (newly) + basic->extra_info |= cpu_to_le16(EXTRA_INFO_NEW); basic->conn_state = CONN_STATE_PORT_SECURE; } else { basic->conn_state = CONN_STATE_DISCONNECT; @@ -393,6 +394,7 @@ mt76_connac_mcu_sta_uapsd(struct sk_buff *skb, struct ieee80211_vif *vif, } void mt76_connac_mcu_wtbl_hdr_trans_tlv(struct sk_buff *skb, + struct ieee80211_vif *vif, struct mt76_wcid *wcid, void *sta_wtbl, void *wtbl_tlv) { @@ -404,9 +406,46 @@ void mt76_connac_mcu_wtbl_hdr_trans_tlv(struct sk_buff *skb, wtbl_tlv, sta_wtbl); htr = (struct wtbl_hdr_trans *)tlv; htr->no_rx_trans = !test_bit(MT_WCID_FLAG_HDR_TRANS, &wcid->flags); + + if (vif->type == NL80211_IFTYPE_STATION) + htr->to_ds = true; + else + htr->from_ds = true; + + if (test_bit(MT_WCID_FLAG_4ADDR, &wcid->flags)) { + htr->to_ds = true; + htr->from_ds = true; + } } EXPORT_SYMBOL_GPL(mt76_connac_mcu_wtbl_hdr_trans_tlv); +int mt76_connac_mcu_sta_update_hdr_trans(struct mt76_dev *dev, + struct ieee80211_vif *vif, + struct mt76_wcid *wcid, int cmd) +{ + struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct wtbl_req_hdr *wtbl_hdr; + struct tlv *sta_wtbl; + struct sk_buff *skb; + + skb = mt76_connac_mcu_alloc_sta_req(dev, mvif, wcid); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + sta_wtbl = mt76_connac_mcu_add_tlv(skb, STA_REC_WTBL, + sizeof(struct tlv)); + + wtbl_hdr = mt76_connac_mcu_alloc_wtbl_req(dev, wcid, WTBL_SET, + sta_wtbl, &skb); + if (IS_ERR(wtbl_hdr)) + return PTR_ERR(wtbl_hdr); + + mt76_connac_mcu_wtbl_hdr_trans_tlv(skb, vif, wcid, sta_wtbl, wtbl_hdr); + + return mt76_mcu_skb_send_msg(dev, skb, cmd, true); +} +EXPORT_SYMBOL_GPL(mt76_connac_mcu_sta_update_hdr_trans); + void mt76_connac_mcu_wtbl_generic_tlv(struct mt76_dev *dev, struct sk_buff *skb, struct ieee80211_vif *vif, @@ -671,7 +710,7 @@ mt76_connac_get_phy_mode_v2(struct mt76_phy *mphy, struct ieee80211_vif *vif, void mt76_connac_mcu_sta_tlv(struct mt76_phy *mphy, struct sk_buff *skb, struct ieee80211_sta *sta, struct ieee80211_vif *vif, - u8 rcpi) + u8 rcpi, u8 sta_state) { struct cfg80211_chan_def *chandef = &mphy->chandef; enum nl80211_band band = chandef->chan->band; @@ -736,7 +775,7 @@ void mt76_connac_mcu_sta_tlv(struct mt76_phy *mphy, struct sk_buff *skb, tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_STATE, sizeof(*state)); state = (struct sta_rec_state *)tlv; - state->state = 2; + state->state = sta_state; if (sta->vht_cap.vht_supported) { state->vht_opmode = sta->bandwidth; @@ -828,8 +867,8 @@ void mt76_connac_mcu_wtbl_ht_tlv(struct mt76_dev *dev, struct sk_buff *skb, } EXPORT_SYMBOL_GPL(mt76_connac_mcu_wtbl_ht_tlv); -int mt76_connac_mcu_add_sta_cmd(struct mt76_phy *phy, - struct mt76_sta_cmd_info *info) +int mt76_connac_mcu_sta_cmd(struct mt76_phy *phy, + struct mt76_sta_cmd_info *info) { struct mt76_vif *mvif = (struct mt76_vif *)info->vif->drv_priv; struct mt76_dev *dev = phy->dev; @@ -841,10 +880,13 @@ int mt76_connac_mcu_add_sta_cmd(struct mt76_phy *phy, if (IS_ERR(skb)) return PTR_ERR(skb); - mt76_connac_mcu_sta_basic_tlv(skb, info->vif, info->sta, info->enable); - if (info->enable && info->sta) - mt76_connac_mcu_sta_tlv(phy, skb, info->sta, info->vif, - info->rcpi); + if (info->sta || !info->offload_fw) + mt76_connac_mcu_sta_basic_tlv(skb, info->vif, info->sta, + info->enable, info->newly); + if (info->sta && info->enable) + mt76_connac_mcu_sta_tlv(phy, skb, info->sta, + info->vif, info->rcpi, + info->state); sta_wtbl = mt76_connac_mcu_add_tlv(skb, STA_REC_WTBL, sizeof(struct tlv)); @@ -859,6 +901,8 @@ int mt76_connac_mcu_add_sta_cmd(struct mt76_phy *phy, mt76_connac_mcu_wtbl_generic_tlv(dev, skb, info->vif, info->sta, sta_wtbl, wtbl_hdr); + mt76_connac_mcu_wtbl_hdr_trans_tlv(skb, info->vif, info->wcid, + sta_wtbl, wtbl_hdr); if (info->sta) mt76_connac_mcu_wtbl_ht_tlv(dev, skb, info->sta, sta_wtbl, wtbl_hdr); @@ -866,7 +910,7 @@ int mt76_connac_mcu_add_sta_cmd(struct mt76_phy *phy, return mt76_mcu_skb_send_msg(dev, skb, info->cmd, true); } -EXPORT_SYMBOL_GPL(mt76_connac_mcu_add_sta_cmd); +EXPORT_SYMBOL_GPL(mt76_connac_mcu_sta_cmd); void mt76_connac_mcu_wtbl_ba_tlv(struct mt76_dev *dev, struct sk_buff *skb, struct ieee80211_ampdu_params *params, @@ -895,8 +939,10 @@ void mt76_connac_mcu_wtbl_ba_tlv(struct mt76_dev *dev, struct sk_buff *skb, ba->rst_ba_sb = 1; } - if (is_mt7921(dev)) + if (is_mt7921(dev)) { + ba->ba_winsize = enable ? cpu_to_le16(params->buf_size) : 0; return; + } if (enable && tx) { u8 ba_range[] = { 4, 8, 12, 24, 36, 48, 54, 64 }; @@ -1271,6 +1317,7 @@ int mt76_connac_mcu_uni_add_bss(struct mt76_phy *phy, u8 pad[3]; } __packed hdr; struct bss_info_uni_he he; + struct bss_info_uni_bss_color bss_color; } he_req = { .hdr = { .bss_idx = mvif->idx, @@ -1279,8 +1326,21 @@ int mt76_connac_mcu_uni_add_bss(struct mt76_phy *phy, .tag = cpu_to_le16(UNI_BSS_INFO_HE_BASIC), .len = cpu_to_le16(sizeof(struct bss_info_uni_he)), }, + .bss_color = { + .tag = cpu_to_le16(UNI_BSS_INFO_BSS_COLOR), + .len = cpu_to_le16(sizeof(struct bss_info_uni_bss_color)), + .enable = 0, + .bss_color = 0, + }, }; + if (enable) { + he_req.bss_color.enable = + vif->bss_conf.he_bss_color.enabled; + he_req.bss_color.bss_color = + vif->bss_conf.he_bss_color.color; + } + mt76_connac_mcu_uni_bss_he_tlv(phy, vif, (struct tlv *)&he_req.he); err = mt76_mcu_send_msg(mdev, MCU_UNI_CMD_BSS_INFO_UPDATE, @@ -1463,14 +1523,16 @@ int mt76_connac_mcu_sched_scan_req(struct mt76_phy *phy, req->version = 1; req->seq_num = mvif->scan_seq_num | ext_phy << 7; - if (is_mt7663(phy->dev) && - (sreq->flags & NL80211_SCAN_FLAG_RANDOM_ADDR)) { - get_random_mask_addr(req->mt7663.random_mac, sreq->mac_addr, - sreq->mac_addr_mask); + if (sreq->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) { + u8 *addr = is_mt7663(phy->dev) ? req->mt7663.random_mac + : req->mt7921.random_mac; + req->scan_func = 1; - } else if (is_mt7921(phy->dev)) { - req->mt7921.bss_idx = mvif->idx; + get_random_mask_addr(addr, sreq->mac_addr, + sreq->mac_addr_mask); } + if (is_mt7921(phy->dev)) + req->mt7921.bss_idx = mvif->idx; req->ssids_num = sreq->n_ssids; for (i = 0; i < req->ssids_num; i++) { @@ -1556,6 +1618,26 @@ int mt76_connac_mcu_set_deep_sleep(struct mt76_dev *dev, bool enable) } EXPORT_SYMBOL_GPL(mt76_connac_mcu_set_deep_sleep); +int mt76_connac_sta_state_dp(struct mt76_dev *dev, + enum ieee80211_sta_state old_state, + enum ieee80211_sta_state new_state) +{ + if ((old_state == IEEE80211_STA_ASSOC && + new_state == IEEE80211_STA_AUTHORIZED) || + (old_state == IEEE80211_STA_NONE && + new_state == IEEE80211_STA_NOTEXIST)) + mt76_connac_mcu_set_deep_sleep(dev, true); + + if ((old_state == IEEE80211_STA_NOTEXIST && + new_state == IEEE80211_STA_NONE) || + (old_state == IEEE80211_STA_AUTHORIZED && + new_state == IEEE80211_STA_ASSOC)) + mt76_connac_mcu_set_deep_sleep(dev, false); + + return 0; +} +EXPORT_SYMBOL_GPL(mt76_connac_sta_state_dp); + void mt76_connac_mcu_coredump_event(struct mt76_dev *dev, struct sk_buff *skb, struct mt76_connac_coredump *coredump) { @@ -1570,6 +1652,60 @@ void mt76_connac_mcu_coredump_event(struct mt76_dev *dev, struct sk_buff *skb, } EXPORT_SYMBOL_GPL(mt76_connac_mcu_coredump_event); +int mt76_connac_mcu_get_nic_capability(struct mt76_phy *phy) +{ + struct mt76_connac_cap_hdr { + __le16 n_element; + u8 rsv[2]; + } __packed * hdr; + struct sk_buff *skb; + int ret, i; + + ret = mt76_mcu_send_and_get_msg(phy->dev, MCU_CMD_GET_NIC_CAPAB, NULL, + 0, true, &skb); + if (ret) + return ret; + + hdr = (struct mt76_connac_cap_hdr *)skb->data; + if (skb->len < sizeof(*hdr)) { + ret = -EINVAL; + goto out; + } + + skb_pull(skb, sizeof(*hdr)); + + for (i = 0; i < le16_to_cpu(hdr->n_element); i++) { + struct tlv_hdr { + __le32 type; + __le32 len; + } __packed * tlv = (struct tlv_hdr *)skb->data; + int len; + + if (skb->len < sizeof(*tlv)) + break; + + skb_pull(skb, sizeof(*tlv)); + + len = le32_to_cpu(tlv->len); + if (skb->len < len) + break; + + switch (le32_to_cpu(tlv->type)) { + case MT_NIC_CAP_6G: + phy->cap.has_6ghz = skb->data[0]; + break; + default: + break; + } + skb_pull(skb, len); + } +out: + dev_kfree_skb(skb); + + return ret; +} +EXPORT_SYMBOL_GPL(mt76_connac_mcu_get_nic_capability); + static void mt76_connac_mcu_build_sku(struct mt76_dev *dev, s8 *sku, struct mt76_power_limits *limits, @@ -1632,12 +1768,15 @@ mt76_connac_mcu_rate_txpower_band(struct mt76_phy *phy, 142, 144, 149, 151, 153, 155, 157, 159, 161, 165 }; + int i, n_chan, batch_size, idx = 0, tx_power, last_ch; struct mt76_connac_sku_tlv sku_tlbv; - int i, n_chan, batch_size, idx = 0; struct mt76_power_limits limits; const u8 *ch_list; sku_len = is_mt7921(dev) ? sizeof(sku_tlbv) : sizeof(sku_tlbv) - 92; + tx_power = 2 * phy->hw->conf.power_level; + if (!tx_power) + tx_power = 127; if (band == NL80211_BAND_2GHZ) { n_chan = ARRAY_SIZE(chan_list_2ghz); @@ -1648,39 +1787,48 @@ mt76_connac_mcu_rate_txpower_band(struct mt76_phy *phy, } batch_size = DIV_ROUND_UP(n_chan, batch_len); + if (!phy->cap.has_5ghz) + last_ch = chan_list_2ghz[n_chan - 1]; + else + last_ch = chan_list_5ghz[n_chan - 1]; + for (i = 0; i < batch_size; i++) { - bool last_msg = i == batch_size - 1; - int num_ch = last_msg ? n_chan % batch_len : batch_len; struct mt76_connac_tx_power_limit_tlv tx_power_tlv = { .band = band == NL80211_BAND_2GHZ ? 1 : 2, - .n_chan = num_ch, - .last_msg = last_msg, }; + int j, err, msg_len, num_ch; struct sk_buff *skb; - int j, err, msg_len; + num_ch = i == batch_size - 1 ? n_chan % batch_len : batch_len; msg_len = sizeof(tx_power_tlv) + num_ch * sizeof(sku_tlbv); skb = mt76_mcu_msg_alloc(dev, NULL, msg_len); if (!skb) return -ENOMEM; + skb_reserve(skb, sizeof(tx_power_tlv)); + BUILD_BUG_ON(sizeof(dev->alpha2) > sizeof(tx_power_tlv.alpha2)); memcpy(tx_power_tlv.alpha2, dev->alpha2, sizeof(dev->alpha2)); + tx_power_tlv.n_chan = num_ch; - skb_put_data(skb, &tx_power_tlv, sizeof(tx_power_tlv)); for (j = 0; j < num_ch; j++, idx++) { struct ieee80211_channel chan = { .hw_value = ch_list[idx], .band = band, }; - mt76_get_rate_power_limits(phy, &chan, &limits, 127); + mt76_get_rate_power_limits(phy, &chan, &limits, + tx_power); + tx_power_tlv.last_msg = ch_list[idx] == last_ch; sku_tlbv.channel = ch_list[idx]; + mt76_connac_mcu_build_sku(dev, sku_tlbv.pwr_limit, &limits, band); skb_put_data(skb, &sku_tlbv, sku_len); } + __skb_push(skb, sizeof(tx_power_tlv)); + memcpy(skb->data, &tx_power_tlv, sizeof(tx_power_tlv)); err = mt76_mcu_skb_send_msg(dev, skb, MCU_CMD_SET_RATE_TX_POWER, false); @@ -1695,11 +1843,20 @@ int mt76_connac_mcu_set_rate_txpower(struct mt76_phy *phy) { int err; - err = mt76_connac_mcu_rate_txpower_band(phy, NL80211_BAND_2GHZ); - if (err < 0) - return err; + if (phy->cap.has_2ghz) { + err = mt76_connac_mcu_rate_txpower_band(phy, + NL80211_BAND_2GHZ); + if (err < 0) + return err; + } + if (phy->cap.has_5ghz) { + err = mt76_connac_mcu_rate_txpower_band(phy, + NL80211_BAND_5GHZ); + if (err < 0) + return err; + } - return mt76_connac_mcu_rate_txpower_band(phy, NL80211_BAND_5GHZ); + return 0; } EXPORT_SYMBOL_GPL(mt76_connac_mcu_set_rate_txpower); @@ -1939,7 +2096,7 @@ mt76_connac_mcu_set_wow_pattern(struct mt76_dev *dev, ptlv->index = index; memcpy(ptlv->pattern, pattern->pattern, pattern->pattern_len); - memcpy(ptlv->mask, pattern->mask, pattern->pattern_len / 8); + memcpy(ptlv->mask, pattern->mask, DIV_ROUND_UP(pattern->pattern_len, 8)); return mt76_mcu_skb_send_msg(dev, skb, MCU_UNI_CMD_SUSPEND, true); } @@ -1974,14 +2131,17 @@ mt76_connac_mcu_set_wow_ctrl(struct mt76_phy *phy, struct ieee80211_vif *vif, }; if (wowlan->magic_pkt) - req.wow_ctrl_tlv.trigger |= BIT(0); + req.wow_ctrl_tlv.trigger |= UNI_WOW_DETECT_TYPE_MAGIC; if (wowlan->disconnect) - req.wow_ctrl_tlv.trigger |= BIT(2); + req.wow_ctrl_tlv.trigger |= (UNI_WOW_DETECT_TYPE_DISCONNECT | + UNI_WOW_DETECT_TYPE_BCN_LOST); if (wowlan->nd_config) { mt76_connac_mcu_sched_scan_req(phy, vif, wowlan->nd_config); - req.wow_ctrl_tlv.trigger |= BIT(5); + req.wow_ctrl_tlv.trigger |= UNI_WOW_DETECT_TYPE_SCH_SCAN_HIT; mt76_connac_mcu_sched_scan_enable(phy, vif, suspend); } + if (wowlan->n_patterns) + req.wow_ctrl_tlv.trigger |= UNI_WOW_DETECT_TYPE_BITMAP; if (mt76_is_mmio(dev)) req.wow_ctrl_tlv.wakeup_hif = WOW_PCIE; diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h index a1096861d04a..1c73beb22677 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.h @@ -559,6 +559,7 @@ enum { MCU_CMD_SET_RATE_TX_POWER = MCU_CE_PREFIX | 0x5d, MCU_CMD_SCHED_SCAN_ENABLE = MCU_CE_PREFIX | 0x61, MCU_CMD_SCHED_SCAN_REQ = MCU_CE_PREFIX | 0x62, + MCU_CMD_GET_NIC_CAPAB = MCU_CE_PREFIX | 0x8a, MCU_CMD_REG_WRITE = MCU_CE_PREFIX | 0xc0, MCU_CMD_REG_READ = MCU_CE_PREFIX | MCU_QUERY_MASK | 0xc0, MCU_CMD_CHIP_CONFIG = MCU_CE_PREFIX | 0xca, @@ -575,6 +576,7 @@ enum { enum { UNI_BSS_INFO_BASIC = 0, UNI_BSS_INFO_RLM = 2, + UNI_BSS_INFO_BSS_COLOR = 4, UNI_BSS_INFO_HE_BASIC = 5, UNI_BSS_INFO_BCN_CONTENT = 7, UNI_BSS_INFO_QBSS = 15, @@ -590,6 +592,36 @@ enum { UNI_OFFLOAD_OFFLOAD_BMC_RPY_DETECT, }; +enum { + MT_NIC_CAP_TX_RESOURCE, + MT_NIC_CAP_TX_EFUSE_ADDR, + MT_NIC_CAP_COEX, + MT_NIC_CAP_SINGLE_SKU, + MT_NIC_CAP_CSUM_OFFLOAD, + MT_NIC_CAP_HW_VER, + MT_NIC_CAP_SW_VER, + MT_NIC_CAP_MAC_ADDR, + MT_NIC_CAP_PHY, + MT_NIC_CAP_MAC, + MT_NIC_CAP_FRAME_BUF, + MT_NIC_CAP_BEAM_FORM, + MT_NIC_CAP_LOCATION, + MT_NIC_CAP_MUMIMO, + MT_NIC_CAP_BUFFER_MODE_INFO, + MT_NIC_CAP_HW_ADIE_VERSION = 0x14, + MT_NIC_CAP_ANTSWP = 0x16, + MT_NIC_CAP_WFDMA_REALLOC, + MT_NIC_CAP_6G, +}; + +#define UNI_WOW_DETECT_TYPE_MAGIC BIT(0) +#define UNI_WOW_DETECT_TYPE_ANY BIT(1) +#define UNI_WOW_DETECT_TYPE_DISCONNECT BIT(2) +#define UNI_WOW_DETECT_TYPE_GTK_REKEY_FAIL BIT(3) +#define UNI_WOW_DETECT_TYPE_BCN_LOST BIT(4) +#define UNI_WOW_DETECT_TYPE_SCH_SCAN_HIT BIT(5) +#define UNI_WOW_DETECT_TYPE_BITMAP BIT(6) + enum { UNI_SUSPEND_MODE_SETTING, UNI_SUSPEND_WOW_CTRL, @@ -762,7 +794,7 @@ struct mt76_connac_sched_scan_req { u8 intervals_num; u8 scan_func; /* MT7663: BIT(0) eable random mac address */ struct mt76_connac_mcu_scan_channel channels[64]; - __le16 intervals[MT76_CONNAC_MAX_SCHED_SCAN_INTERVAL]; + __le16 intervals[MT76_CONNAC_MAX_NUM_SCHED_SCAN_INTERVAL]; union { struct { u8 random_mac[ETH_ALEN]; @@ -770,7 +802,9 @@ struct mt76_connac_sched_scan_req { } mt7663; struct { u8 bss_idx; - u8 pad2[63]; + u8 pad2[19]; + u8 random_mac[ETH_ALEN]; + u8 pad3[38]; } mt7921; }; } __packed; @@ -781,6 +815,14 @@ struct mt76_connac_sched_scan_done { __le16 pad; } __packed; +struct bss_info_uni_bss_color { + __le16 tag; + __le16 len; + u8 enable; + u8 bss_color; + u8 rsv[2]; +} __packed; + struct bss_info_uni_he { __le16 tag; __le16 len; @@ -885,15 +927,24 @@ struct mt76_connac_suspend_tlv { u8 pad[5]; } __packed; +enum mt76_sta_info_state { + MT76_STA_INFO_STATE_NONE, + MT76_STA_INFO_STATE_AUTH, + MT76_STA_INFO_STATE_ASSOC +}; + struct mt76_sta_cmd_info { struct ieee80211_sta *sta; struct mt76_wcid *wcid; struct ieee80211_vif *vif; + bool offload_fw; bool enable; + bool newly; int cmd; u8 rcpi; + u8 state; }; #define MT_SKU_POWER_LIMIT 161 @@ -963,18 +1014,23 @@ int mt76_connac_mcu_set_channel_domain(struct mt76_phy *phy); int mt76_connac_mcu_set_vif_ps(struct mt76_dev *dev, struct ieee80211_vif *vif); void mt76_connac_mcu_sta_basic_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, - struct ieee80211_sta *sta, bool enable); + struct ieee80211_sta *sta, bool enable, + bool newly); void mt76_connac_mcu_wtbl_generic_tlv(struct mt76_dev *dev, struct sk_buff *skb, struct ieee80211_vif *vif, struct ieee80211_sta *sta, void *sta_wtbl, void *wtbl_tlv); void mt76_connac_mcu_wtbl_hdr_trans_tlv(struct sk_buff *skb, + struct ieee80211_vif *vif, struct mt76_wcid *wcid, void *sta_wtbl, void *wtbl_tlv); +int mt76_connac_mcu_sta_update_hdr_trans(struct mt76_dev *dev, + struct ieee80211_vif *vif, + struct mt76_wcid *wcid, int cmd); void mt76_connac_mcu_sta_tlv(struct mt76_phy *mphy, struct sk_buff *skb, struct ieee80211_sta *sta, struct ieee80211_vif *vif, - u8 rcpi); + u8 rcpi, u8 state); void mt76_connac_mcu_wtbl_ht_tlv(struct mt76_dev *dev, struct sk_buff *skb, struct ieee80211_sta *sta, void *sta_wtbl, void *wtbl_tlv); @@ -996,8 +1052,8 @@ int mt76_connac_mcu_uni_add_bss(struct mt76_phy *phy, struct ieee80211_vif *vif, struct mt76_wcid *wcid, bool enable); -int mt76_connac_mcu_add_sta_cmd(struct mt76_phy *phy, - struct mt76_sta_cmd_info *info); +int mt76_connac_mcu_sta_cmd(struct mt76_phy *phy, + struct mt76_sta_cmd_info *info); void mt76_connac_mcu_beacon_loss_iter(void *priv, u8 *mac, struct ieee80211_vif *vif); int mt76_connac_mcu_set_rts_thresh(struct mt76_dev *dev, u32 val, u8 band); @@ -1008,6 +1064,7 @@ int mt76_connac_mcu_init_download(struct mt76_dev *dev, u32 addr, u32 len, int mt76_connac_mcu_start_patch(struct mt76_dev *dev); int mt76_connac_mcu_patch_sem_ctrl(struct mt76_dev *dev, bool get); int mt76_connac_mcu_start_firmware(struct mt76_dev *dev, u32 addr, u32 option); +int mt76_connac_mcu_get_nic_capability(struct mt76_phy *phy); int mt76_connac_mcu_hw_scan(struct mt76_phy *phy, struct ieee80211_vif *vif, struct ieee80211_scan_request *scan_req); @@ -1028,6 +1085,9 @@ int mt76_connac_mcu_update_gtk_rekey(struct ieee80211_hw *hw, int mt76_connac_mcu_set_hif_suspend(struct mt76_dev *dev, bool suspend); void mt76_connac_mcu_set_suspend_iter(void *priv, u8 *mac, struct ieee80211_vif *vif); +int mt76_connac_sta_state_dp(struct mt76_dev *dev, + enum ieee80211_sta_state old_state, + enum ieee80211_sta_state new_state); int mt76_connac_mcu_chip_config(struct mt76_dev *dev); int mt76_connac_mcu_set_deep_sleep(struct mt76_dev *dev, bool enable); void mt76_connac_mcu_coredump_event(struct mt76_dev *dev, struct sk_buff *skb, diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c index dd66fd12a2e6..cea24213186c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c @@ -68,7 +68,7 @@ static void mt76x0_set_chip_cap(struct mt76x02_dev *dev) nic_conf1 &= 0xff00; if (nic_conf1 & MT_EE_NIC_CONF_1_HW_RF_CTRL) - dev_err(dev->mt76.dev, + dev_dbg(dev->mt76.dev, "driver does not support HW RF ctrl\n"); if (!mt76x02_field_valid(nic_conf0 >> 8)) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c index 0da37867cb64..c32e6dc68773 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c @@ -34,24 +34,24 @@ mt76x02_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data) { memset(key_data, 0, 32); if (!key) - return MT_CIPHER_NONE; + return MT76X02_CIPHER_NONE; if (key->keylen > 32) - return MT_CIPHER_NONE; + return MT76X02_CIPHER_NONE; memcpy(key_data, key->key, key->keylen); switch (key->cipher) { case WLAN_CIPHER_SUITE_WEP40: - return MT_CIPHER_WEP40; + return MT76X02_CIPHER_WEP40; case WLAN_CIPHER_SUITE_WEP104: - return MT_CIPHER_WEP104; + return MT76X02_CIPHER_WEP104; case WLAN_CIPHER_SUITE_TKIP: - return MT_CIPHER_TKIP; + return MT76X02_CIPHER_TKIP; case WLAN_CIPHER_SUITE_CCMP: - return MT_CIPHER_AES_CCMP; + return MT76X02_CIPHER_AES_CCMP; default: - return MT_CIPHER_NONE; + return MT76X02_CIPHER_NONE; } } @@ -63,7 +63,7 @@ int mt76x02_mac_shared_key_setup(struct mt76x02_dev *dev, u8 vif_idx, u32 val; cipher = mt76x02_mac_get_key_info(key, key_data); - if (cipher == MT_CIPHER_NONE && key) + if (cipher == MT76X02_CIPHER_NONE && key) return -EOPNOTSUPP; val = mt76_rr(dev, MT_SKEY_MODE(vif_idx)); @@ -91,10 +91,10 @@ void mt76x02_mac_wcid_sync_pn(struct mt76x02_dev *dev, u8 idx, eiv = mt76_rr(dev, MT_WCID_IV(idx) + 4); pn = (u64)eiv << 16; - if (cipher == MT_CIPHER_TKIP) { + if (cipher == MT76X02_CIPHER_TKIP) { pn |= (iv >> 16) & 0xff; pn |= (iv & 0xff) << 8; - } else if (cipher >= MT_CIPHER_AES_CCMP) { + } else if (cipher >= MT76X02_CIPHER_AES_CCMP) { pn |= iv & 0xffff; } else { return; @@ -112,7 +112,7 @@ int mt76x02_mac_wcid_set_key(struct mt76x02_dev *dev, u8 idx, u64 pn; cipher = mt76x02_mac_get_key_info(key, key_data); - if (cipher == MT_CIPHER_NONE && key) + if (cipher == MT76X02_CIPHER_NONE && key) return -EOPNOTSUPP; mt76_wr_copy(dev, MT_WCID_KEY(idx), key_data, sizeof(key_data)); @@ -126,16 +126,16 @@ int mt76x02_mac_wcid_set_key(struct mt76x02_dev *dev, u8 idx, pn = atomic64_read(&key->tx_pn); iv_data[3] = key->keyidx << 6; - if (cipher >= MT_CIPHER_TKIP) { + if (cipher >= MT76X02_CIPHER_TKIP) { iv_data[3] |= 0x20; put_unaligned_le32(pn >> 16, &iv_data[4]); } - if (cipher == MT_CIPHER_TKIP) { + if (cipher == MT76X02_CIPHER_TKIP) { iv_data[0] = (pn >> 8) & 0xff; iv_data[1] = (iv_data[0] | 0x20) & 0x7f; iv_data[2] = pn & 0xff; - } else if (cipher >= MT_CIPHER_AES_CCMP) { + } else if (cipher >= MT76X02_CIPHER_AES_CCMP) { put_unaligned_le16((pn & 0xffff), &iv_data[0]); } } @@ -1022,12 +1022,12 @@ void mt76x02_mac_set_tx_protection(struct mt76x02_dev *dev, bool legacy_prot, mt76_wr(dev, MT_TX_PROT_CFG6 + i * 4, vht_prot[i]); } -void mt76x02_update_channel(struct mt76_dev *mdev) +void mt76x02_update_channel(struct mt76_phy *mphy) { - struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, mt76); + struct mt76x02_dev *dev = container_of(mphy->dev, struct mt76x02_dev, mt76); struct mt76_channel_state *state; - state = mdev->phy.chan_state; + state = mphy->chan_state; state->cc_busy += mt76_rr(dev, MT_CH_BUSY); spin_lock_bh(&dev->mt76.cc_lock); @@ -1169,7 +1169,7 @@ void mt76x02_mac_work(struct work_struct *work) mutex_lock(&dev->mt76.mutex); - mt76_update_survey(&dev->mt76); + mt76_update_survey(&dev->mphy); for (i = 0, idx = 0; i < 16; i++) { u32 val = mt76_rr(dev, MT_TX_AGG_CNT(i)); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h index 0cfbaca50210..5dc6c834111e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h @@ -195,7 +195,7 @@ void mt76x02_mac_write_txwi(struct mt76x02_dev *dev, struct mt76x02_txwi *txwi, struct ieee80211_sta *sta, int len); void mt76x02_mac_poll_tx_status(struct mt76x02_dev *dev, bool irq); void mt76x02_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e); -void mt76x02_update_channel(struct mt76_dev *mdev); +void mt76x02_update_channel(struct mt76_phy *mphy); void mt76x02_mac_work(struct work_struct *work); void mt76x02_mac_cc_reset(struct mt76x02_dev *dev); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_regs.h b/drivers/net/wireless/mediatek/mt76/mt76x02_regs.h index 3e722276b5c2..fa7872ac22bf 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_regs.h @@ -692,15 +692,15 @@ struct mt76_wcid_key { } __packed __aligned(4); enum mt76x02_cipher_type { - MT_CIPHER_NONE, - MT_CIPHER_WEP40, - MT_CIPHER_WEP104, - MT_CIPHER_TKIP, - MT_CIPHER_AES_CCMP, - MT_CIPHER_CKIP40, - MT_CIPHER_CKIP104, - MT_CIPHER_CKIP128, - MT_CIPHER_WAPI, + MT76X02_CIPHER_NONE, + MT76X02_CIPHER_WEP40, + MT76X02_CIPHER_WEP104, + MT76X02_CIPHER_TKIP, + MT76X02_CIPHER_AES_CCMP, + MT76X02_CIPHER_CKIP40, + MT76X02_CIPHER_CKIP104, + MT76X02_CIPHER_CKIP128, + MT76X02_CIPHER_WAPI, }; #endif diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c index 02db5d66735d..ccdbab341271 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c @@ -7,24 +7,18 @@ #include #include "mt76x02.h" -#define CCK_RATE(_idx, _rate) { \ +#define MT76x02_CCK_RATE(_idx, _rate) { \ .bitrate = _rate, \ .flags = IEEE80211_RATE_SHORT_PREAMBLE, \ .hw_value = (MT_PHY_TYPE_CCK << 8) | (_idx), \ .hw_value_short = (MT_PHY_TYPE_CCK << 8) | (8 + (_idx)), \ } -#define OFDM_RATE(_idx, _rate) { \ - .bitrate = _rate, \ - .hw_value = (MT_PHY_TYPE_OFDM << 8) | (_idx), \ - .hw_value_short = (MT_PHY_TYPE_OFDM << 8) | (_idx), \ -} - struct ieee80211_rate mt76x02_rates[] = { - CCK_RATE(0, 10), - CCK_RATE(1, 20), - CCK_RATE(2, 55), - CCK_RATE(3, 110), + MT76x02_CCK_RATE(0, 10), + MT76x02_CCK_RATE(1, 20), + MT76x02_CCK_RATE(2, 55), + MT76x02_CCK_RATE(3, 110), OFDM_RATE(0, 60), OFDM_RATE(1, 90), OFDM_RATE(2, 120), diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/Makefile b/drivers/net/wireless/mediatek/mt76/mt7915/Makefile index 40c8061787e9..80e49244348e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/Makefile +++ b/drivers/net/wireless/mediatek/mt76/mt7915/Makefile @@ -1,4 +1,4 @@ -#SPDX-License-Identifier: ISC +# SPDX-License-Identifier: ISC obj-$(CONFIG_MT7915E) += mt7915e.o diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c index 6a8ddeeecbe9..64048243e34b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c @@ -3,6 +3,7 @@ #include "mt7915.h" #include "eeprom.h" +#include "mcu.h" /** global debugfs **/ @@ -16,7 +17,7 @@ mt7915_implicit_txbf_set(void *data, u64 val) dev->ibf = !!val; - return mt7915_mcu_set_txbf_type(dev); + return mt7915_mcu_set_txbf(dev, MT_BF_TYPE_UPDATE); } static int @@ -147,6 +148,9 @@ mt7915_txbf_stat_read_phy(struct mt7915_phy *phy, struct seq_file *s) { struct mt7915_dev *dev = s->private; bool ext_phy = phy != &dev->phy; + static const char * const bw[] = { + "BW20", "BW40", "BW80", "BW160" + }; int cnt; if (!phy) @@ -164,11 +168,16 @@ mt7915_txbf_stat_read_phy(struct mt7915_phy *phy, struct seq_file *s) seq_puts(s, "Tx Beamformer Rx feedback statistics: "); cnt = mt76_rr(dev, MT_ETBF_RX_FB_CNT(ext_phy)); - seq_printf(s, "All: %ld, HE: %ld, VHT: %ld, HT: %ld\n", + seq_printf(s, "All: %ld, HE: %ld, VHT: %ld, HT: %ld, ", FIELD_GET(MT_ETBF_RX_FB_ALL, cnt), FIELD_GET(MT_ETBF_RX_FB_HE, cnt), FIELD_GET(MT_ETBF_RX_FB_VHT, cnt), FIELD_GET(MT_ETBF_RX_FB_HT, cnt)); + cnt = mt76_rr(dev, MT_ETBF_RX_FB_CONT(ext_phy)); + seq_printf(s, "%s, NC: %ld, NR: %ld\n", + bw[FIELD_GET(MT_ETBF_RX_FB_BW, cnt)], + FIELD_GET(MT_ETBF_RX_FB_NC, cnt), + FIELD_GET(MT_ETBF_RX_FB_NR, cnt)); /* Tx Beamformee Rx NDPA & Tx feedback report */ cnt = mt76_rr(dev, MT_ETBF_TX_NDP_BFRP(ext_phy)); @@ -204,7 +213,7 @@ mt7915_tx_stats_show(struct seq_file *file, void *data) mt7915_txbf_stat_read_phy(mt7915_ext_phy(dev), file); /* Tx amsdu info */ - seq_puts(file, "Tx MSDU stat:\n"); + seq_puts(file, "Tx MSDU statistics:\n"); for (i = 0, n = 0; i < ARRAY_SIZE(stat); i++) { stat[i] = mt76_rr(dev, MT_PLE_AMSDU_PACK_MSDU_CNT(i)); n += stat[i]; @@ -224,18 +233,6 @@ mt7915_tx_stats_show(struct seq_file *file, void *data) DEFINE_SHOW_ATTRIBUTE(mt7915_tx_stats); -static int mt7915_read_temperature(struct seq_file *s, void *data) -{ - struct mt7915_dev *dev = dev_get_drvdata(s->private); - int temp; - - /* cpu */ - temp = mt7915_mcu_get_temperature(dev, 0); - seq_printf(s, "Temperature: %d\n", temp); - - return 0; -} - static int mt7915_queues_acq(struct seq_file *s, void *data) { @@ -307,54 +304,23 @@ mt7915_puts_rate_txpower(struct seq_file *s, struct mt7915_phy *phy) "RU26", "RU52", "RU106", "RU242/SU20", "RU484/SU40", "RU996/SU80", "RU2x996/SU160" }; - struct mt7915_dev *dev = dev_get_drvdata(s->private); - bool ext_phy = phy != &dev->phy; - u32 reg_base; - int i, idx = 0; + s8 txpower[MT7915_SKU_RATE_NUM], *buf; + int i; if (!phy) return; - reg_base = MT_TMAC_FP0R0(ext_phy); - seq_printf(s, "\nBand %d\n", ext_phy); + seq_printf(s, "\nBand %d\n", phy != &phy->dev->phy); - for (i = 0; i < ARRAY_SIZE(mt7915_sku_group_len); i++) { - u8 cnt, mcs_num = mt7915_sku_group_len[i]; - s8 txpower[12]; - int j; + mt7915_mcu_get_txpower_sku(phy, txpower, sizeof(txpower)); + for (i = 0, buf = txpower; i < ARRAY_SIZE(mt7915_sku_group_len); i++) { + u8 mcs_num = mt7915_sku_group_len[i]; - if (i == SKU_HT_BW20 || i == SKU_HT_BW40) { - mcs_num = 8; - } else if (i >= SKU_VHT_BW20 && i <= SKU_VHT_BW160) { + if (i >= SKU_VHT_BW20 && i <= SKU_VHT_BW160) mcs_num = 10; - } else if (i == SKU_HE_RU26) { - reg_base = MT_TMAC_FP0R18(ext_phy); - idx = 0; - } - for (j = 0, cnt = 0; j < DIV_ROUND_UP(mcs_num, 4); j++) { - u32 val; - - if (i == SKU_VHT_BW160 && idx == 60) { - reg_base = MT_TMAC_FP0R15(ext_phy); - idx = 0; - } - - val = mt76_rr(dev, reg_base + (idx / 4) * 4); - - if (idx && idx % 4) - val >>= (idx % 4) * 8; - - while (val > 0 && cnt < mcs_num) { - s8 pwr = FIELD_GET(MT_TMAC_FP_MASK, val); - - txpower[cnt++] = pwr; - val >>= 8; - idx++; - } - } - - mt76_seq_puts_array(s, sku_group_name[i], txpower, mcs_num); + mt76_seq_puts_array(s, sku_group_name[i], buf, mcs_num); + buf += mt7915_sku_group_len[i]; } } @@ -390,8 +356,6 @@ int mt7915_init_debugfs(struct mt7915_dev *dev) debugfs_create_file("radar_trigger", 0200, dir, dev, &fops_radar_trigger); debugfs_create_file("ser_trigger", 0200, dir, dev, &fops_ser_trigger); - debugfs_create_devm_seqfile(dev->mt76.dev, "temperature", dir, - mt7915_read_temperature); debugfs_create_devm_seqfile(dev->mt76.dev, "txpower_sku", dir, mt7915_read_rate_txpower); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c index 11d0b760abd7..9182568f95c7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c @@ -19,39 +19,6 @@ int mt7915_init_tx_queues(struct mt7915_phy *phy, int idx, int n_desc) return 0; } -void mt7915_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, - struct sk_buff *skb) -{ - struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76); - __le32 *rxd = (__le32 *)skb->data; - enum rx_pkt_type type; - - type = FIELD_GET(MT_RXD0_PKT_TYPE, le32_to_cpu(rxd[0])); - - switch (type) { - case PKT_TYPE_TXRX_NOTIFY: - mt7915_mac_tx_free(dev, skb); - break; - case PKT_TYPE_RX_EVENT: - mt7915_mcu_rx_event(dev, skb); - break; -#ifdef CONFIG_NL80211_TESTMODE - case PKT_TYPE_TXRXV: - mt7915_mac_fill_rx_vector(dev, skb); - break; -#endif - case PKT_TYPE_NORMAL: - if (!mt7915_mac_fill_rx(dev, skb)) { - mt76_rx(&dev->mt76, q, skb); - return; - } - fallthrough; - default: - dev_kfree_skb(skb); - break; - } -} - static void mt7915_tx_cleanup(struct mt7915_dev *dev) { @@ -112,8 +79,6 @@ void mt7915_dma_prefetch(struct mt7915_dev *dev) int mt7915_dma_init(struct mt7915_dev *dev) { - /* Increase buffer size to receive large VHT/HE MPDUs */ - int rx_buf_size = MT_RX_BUF_SIZE * 2; u32 hif1_ofs = 0; int ret; @@ -177,28 +142,28 @@ int mt7915_dma_init(struct mt7915_dev *dev) /* event from WM */ ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU], MT7915_RXQ_MCU_WM, MT7915_RX_MCU_RING_SIZE, - rx_buf_size, MT_RX_EVENT_RING_BASE); + MT_RX_BUF_SIZE, MT_RX_EVENT_RING_BASE); if (ret) return ret; /* event from WA */ ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU_WA], MT7915_RXQ_MCU_WA, MT7915_RX_MCU_RING_SIZE, - rx_buf_size, MT_RX_EVENT_RING_BASE); + MT_RX_BUF_SIZE, MT_RX_EVENT_RING_BASE); if (ret) return ret; /* rx data queue */ ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MAIN], MT7915_RXQ_BAND0, MT7915_RX_RING_SIZE, - rx_buf_size, MT_RX_DATA_RING_BASE); + MT_RX_BUF_SIZE, MT_RX_DATA_RING_BASE); if (ret) return ret; if (dev->dbdc_support) { ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_EXT], MT7915_RXQ_BAND1, MT7915_RX_RING_SIZE, - rx_buf_size, + MT_RX_BUF_SIZE, MT_RX_DATA_RING_BASE + hif1_ofs); if (ret) return ret; @@ -207,7 +172,7 @@ int mt7915_dma_init(struct mt7915_dev *dev) ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_EXT_WA], MT7915_RXQ_MCU_WA_EXT, MT7915_RX_MCU_RING_SIZE, - rx_buf_size, + MT_RX_BUF_SIZE, MT_RX_EVENT_RING_BASE + hif1_ofs); if (ret) return ret; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c index 8ededf2e5279..ee3d64434821 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.c @@ -4,22 +4,12 @@ #include "mt7915.h" #include "eeprom.h" -static u32 mt7915_eeprom_read(struct mt7915_dev *dev, u32 offset) -{ - u8 *data = dev->mt76.eeprom.data; - - if (data[offset] == 0xff && !dev->flash_mode) - mt7915_mcu_get_eeprom(dev, offset); - - return data[offset]; -} - static int mt7915_eeprom_load_precal(struct mt7915_dev *dev) { struct mt76_dev *mdev = &dev->mt76; - u32 val; + u8 *eeprom = mdev->eeprom.data; + u32 val = eeprom[MT_EE_DO_PRE_CAL]; - val = mt7915_eeprom_read(dev, MT_EE_DO_PRE_CAL); if (val != (MT_EE_WIFI_CAL_DPD | MT_EE_WIFI_CAL_GROUP)) return 0; @@ -43,7 +33,13 @@ static int mt7915_eeprom_load(struct mt7915_dev *dev) dev->flash_mode = true; ret = mt7915_eeprom_load_precal(dev); } else { - memset(dev->mt76.eeprom.data, -1, MT7915_EEPROM_SIZE); + u32 block_num, i; + + block_num = DIV_ROUND_UP(MT7915_EEPROM_SIZE, + MT7915_EEPROM_BLOCK_SIZE); + for (i = 0; i < block_num; i++) + mt7915_mcu_get_eeprom(dev, + i * MT7915_EEPROM_BLOCK_SIZE); } return ret; @@ -52,10 +48,7 @@ static int mt7915_eeprom_load(struct mt7915_dev *dev) static int mt7915_check_eeprom(struct mt7915_dev *dev) { u8 *eeprom = dev->mt76.eeprom.data; - u16 val; - - mt7915_eeprom_read(dev, MT_EE_CHIP_ID); - val = get_unaligned_le16(eeprom); + u16 val = get_unaligned_le16(eeprom); switch (val) { case 0x7915: @@ -69,9 +62,10 @@ void mt7915_eeprom_parse_band_config(struct mt7915_phy *phy) { struct mt7915_dev *dev = phy->dev; bool ext_phy = phy != &dev->phy; + u8 *eeprom = dev->mt76.eeprom.data; u32 val; - val = mt7915_eeprom_read(dev, MT_EE_WIFI_CONF + ext_phy); + val = eeprom[MT_EE_WIFI_CONF + ext_phy]; val = FIELD_GET(MT_EE_WIFI_CONF0_BAND_SEL, val); if (val == MT_EE_BAND_SEL_DEFAULT && dev->dbdc_support) val = ext_phy ? MT_EE_BAND_SEL_5GHZ : MT_EE_BAND_SEL_2GHZ; @@ -143,6 +137,7 @@ int mt7915_eeprom_get_target_power(struct mt7915_dev *dev, struct ieee80211_channel *chan, u8 chain_idx) { + u8 *eeprom = dev->mt76.eeprom.data; int index, target_power; bool tssi_on; @@ -153,18 +148,18 @@ int mt7915_eeprom_get_target_power(struct mt7915_dev *dev, if (chan->band == NL80211_BAND_2GHZ) { index = MT_EE_TX0_POWER_2G + chain_idx * 3; - target_power = mt7915_eeprom_read(dev, index); + target_power = eeprom[index]; if (!tssi_on) - target_power += mt7915_eeprom_read(dev, index + 1); + target_power += eeprom[index + 1]; } else { int group = mt7915_get_channel_group(chan->hw_value); index = MT_EE_TX0_POWER_5G + chain_idx * 12; - target_power = mt7915_eeprom_read(dev, index + group); + target_power = eeprom[index + group]; if (!tssi_on) - target_power += mt7915_eeprom_read(dev, index + 8); + target_power += eeprom[index + 8]; } return target_power; @@ -172,13 +167,14 @@ int mt7915_eeprom_get_target_power(struct mt7915_dev *dev, s8 mt7915_eeprom_get_power_delta(struct mt7915_dev *dev, int band) { + u8 *eeprom = dev->mt76.eeprom.data; u32 val; s8 delta; if (band == NL80211_BAND_2GHZ) - val = mt7915_eeprom_read(dev, MT_EE_RATE_DELTA_2G); + val = eeprom[MT_EE_RATE_DELTA_2G]; else - val = mt7915_eeprom_read(dev, MT_EE_RATE_DELTA_5G); + val = eeprom[MT_EE_RATE_DELTA_5G]; if (!(val & MT_EE_RATE_DELTA_EN)) return 0; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h index 033fb592bdf0..a43389a41800 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/eeprom.h @@ -33,7 +33,7 @@ enum mt7915_eeprom_field { #define MT_EE_WIFI_CAL_GROUP BIT(0) #define MT_EE_WIFI_CAL_DPD GENMASK(2, 1) #define MT_EE_CAL_UNIT 1024 -#define MT_EE_CAL_GROUP_SIZE (44 * MT_EE_CAL_UNIT) +#define MT_EE_CAL_GROUP_SIZE (49 * MT_EE_CAL_UNIT + 16) #define MT_EE_CAL_DPD_SIZE (54 * MT_EE_CAL_UNIT) #define MT_EE_WIFI_CONF0_TX_PATH GENMASK(2, 0) @@ -99,12 +99,15 @@ static inline bool mt7915_tssi_enabled(struct mt7915_dev *dev, enum nl80211_band band) { u8 *eep = dev->mt76.eeprom.data; + u8 val = eep[MT_EE_WIFI_CONF + 7]; - /* TODO: DBDC */ - if (band == NL80211_BAND_5GHZ) - return eep[MT_EE_WIFI_CONF + 7] & MT_EE_WIFI_CONF7_TSSI0_5G; + if (band == NL80211_BAND_2GHZ) + return val & MT_EE_WIFI_CONF7_TSSI0_2G; + + if (dev->dbdc_support) + return val & MT_EE_WIFI_CONF7_TSSI1_5G; else - return eep[MT_EE_WIFI_CONF + 7] & MT_EE_WIFI_CONF7_TSSI0_2G; + return val & MT_EE_WIFI_CONF7_TSSI0_5G; } extern const u8 mt7915_sku_group_len[MAX_SKU_RATE_GROUP_NUM]; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c index 822f3aa6bb8b..4798d6344305 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c @@ -2,39 +2,14 @@ /* Copyright (C) 2020 MediaTek Inc. */ #include +#include +#include +#include #include "mt7915.h" #include "mac.h" #include "mcu.h" #include "eeprom.h" -#define CCK_RATE(_idx, _rate) { \ - .bitrate = _rate, \ - .flags = IEEE80211_RATE_SHORT_PREAMBLE, \ - .hw_value = (MT_PHY_TYPE_CCK << 8) | (_idx), \ - .hw_value_short = (MT_PHY_TYPE_CCK << 8) | (4 + (_idx)), \ -} - -#define OFDM_RATE(_idx, _rate) { \ - .bitrate = _rate, \ - .hw_value = (MT_PHY_TYPE_OFDM << 8) | (_idx), \ - .hw_value_short = (MT_PHY_TYPE_OFDM << 8) | (_idx), \ -} - -static struct ieee80211_rate mt7915_rates[] = { - CCK_RATE(0, 10), - CCK_RATE(1, 20), - CCK_RATE(2, 55), - CCK_RATE(3, 110), - OFDM_RATE(11, 60), - OFDM_RATE(15, 90), - OFDM_RATE(10, 120), - OFDM_RATE(14, 180), - OFDM_RATE(9, 240), - OFDM_RATE(13, 360), - OFDM_RATE(8, 480), - OFDM_RATE(12, 540), -}; - static const struct ieee80211_iface_limit if_limits[] = { { .max = 1, @@ -67,6 +42,117 @@ static const struct ieee80211_iface_combination if_comb[] = { } }; +static ssize_t mt7915_thermal_show_temp(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mt7915_phy *phy = dev_get_drvdata(dev); + int temperature; + + temperature = mt7915_mcu_get_temperature(phy); + if (temperature < 0) + return temperature; + + /* display in millidegree celcius */ + return sprintf(buf, "%u\n", temperature * 1000); +} + +static SENSOR_DEVICE_ATTR(temp1_input, 0444, mt7915_thermal_show_temp, + NULL, 0); + +static struct attribute *mt7915_hwmon_attrs[] = { + &sensor_dev_attr_temp1_input.dev_attr.attr, + NULL, +}; +ATTRIBUTE_GROUPS(mt7915_hwmon); + +static int +mt7915_thermal_get_max_throttle_state(struct thermal_cooling_device *cdev, + unsigned long *state) +{ + *state = MT7915_THERMAL_THROTTLE_MAX; + + return 0; +} + +static int +mt7915_thermal_get_cur_throttle_state(struct thermal_cooling_device *cdev, + unsigned long *state) +{ + struct mt7915_phy *phy = cdev->devdata; + + *state = phy->throttle_state; + + return 0; +} + +static int +mt7915_thermal_set_cur_throttle_state(struct thermal_cooling_device *cdev, + unsigned long state) +{ + struct mt7915_phy *phy = cdev->devdata; + int ret; + + if (state > MT7915_THERMAL_THROTTLE_MAX) + return -EINVAL; + + if (state == phy->throttle_state) + return 0; + + ret = mt7915_mcu_set_thermal_throttling(phy, state); + if (ret) + return ret; + + phy->throttle_state = state; + + return 0; +} + +static const struct thermal_cooling_device_ops mt7915_thermal_ops = { + .get_max_state = mt7915_thermal_get_max_throttle_state, + .get_cur_state = mt7915_thermal_get_cur_throttle_state, + .set_cur_state = mt7915_thermal_set_cur_throttle_state, +}; + +static void mt7915_unregister_thermal(struct mt7915_phy *phy) +{ + struct wiphy *wiphy = phy->mt76->hw->wiphy; + + if (!phy->cdev) + return; + + sysfs_remove_link(&wiphy->dev.kobj, "cooling_device"); + thermal_cooling_device_unregister(phy->cdev); +} + +static int mt7915_thermal_init(struct mt7915_phy *phy) +{ + struct wiphy *wiphy = phy->mt76->hw->wiphy; + struct thermal_cooling_device *cdev; + struct device *hwmon; + + cdev = thermal_cooling_device_register(wiphy_name(wiphy), phy, + &mt7915_thermal_ops); + if (!IS_ERR(cdev)) { + if (sysfs_create_link(&wiphy->dev.kobj, &cdev->device.kobj, + "cooling_device") < 0) + thermal_cooling_device_unregister(cdev); + else + phy->cdev = cdev; + } + + if (!IS_REACHABLE(CONFIG_HWMON)) + return 0; + + hwmon = devm_hwmon_device_register_with_groups(&wiphy->dev, + wiphy_name(wiphy), phy, + mt7915_hwmon_groups); + if (IS_ERR(hwmon)) + return PTR_ERR(hwmon); + + return 0; +} + static void mt7915_init_txpower(struct mt7915_dev *dev, struct ieee80211_supported_band *sband) @@ -201,7 +287,6 @@ mt7915_mac_init_band(struct mt7915_dev *dev, u8 band) FIELD_PREP(MT_MDP_RCFR1_RX_DROPPED_MCAST, MT_MDP_TO_HIF); mt76_rmw(dev, MT_MDP_BNRCFR1(band), mask, set); - mt76_set(dev, MT_WF_RMAC_MIB_TIME0(band), MT_WF_RMAC_MIB_RXTIME_EN); mt76_set(dev, MT_WF_RMAC_MIB_AIRTIME0(band), MT_WF_RMAC_MIB_RXTIME_EN); mt76_rmw_field(dev, MT_DMA_DCR0(band), MT_DMA_DCR0_MAX_RX_LEN, 1536); @@ -228,20 +313,19 @@ static int mt7915_txbf_init(struct mt7915_dev *dev) { int ret; - if (dev->dbdc_support) { - ret = mt7915_mcu_set_txbf_module(dev); + ret = mt7915_mcu_set_txbf(dev, MT_BF_MODULE_UPDATE); if (ret) return ret; } /* trigger sounding packets */ - ret = mt7915_mcu_set_txbf_sounding(dev); + ret = mt7915_mcu_set_txbf(dev, MT_BF_SOUNDING_ON); if (ret) return ret; /* enable eBF */ - return mt7915_mcu_set_txbf_type(dev); + return mt7915_mcu_set_txbf(dev, MT_BF_TYPE_UPDATE); } static int mt7915_register_ext_phy(struct mt7915_dev *dev) @@ -281,8 +365,12 @@ static int mt7915_register_ext_phy(struct mt7915_dev *dev) if (ret) goto error; - ret = mt76_register_phy(mphy, true, mt7915_rates, - ARRAY_SIZE(mt7915_rates)); + ret = mt76_register_phy(mphy, true, mt76_rates, + ARRAY_SIZE(mt76_rates)); + if (ret) + goto error; + + ret = mt7915_thermal_init(phy); if (ret) goto error; @@ -480,6 +568,9 @@ mt7915_set_stream_he_txbf_caps(struct ieee80211_sta_he_cap *he_cap, if (nss < 2) return; + /* the maximum cap is 4 x 3, (Nr, Nc) = (3, 2) */ + elem->phy_cap_info[7] |= min_t(int, nss - 1, 2) << 3; + if (vif != NL80211_IFTYPE_AP) return; @@ -493,9 +584,6 @@ mt7915_set_stream_he_txbf_caps(struct ieee80211_sta_he_cap *he_cap, c = IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMING_FB | IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB; elem->phy_cap_info[6] |= c; - - /* the maximum cap is 4 x 3, (Nr, Nc) = (3, 2) */ - elem->phy_cap_info[7] |= min_t(int, nss - 1, 2) << 3; } static void @@ -579,8 +667,6 @@ mt7915_init_he_caps(struct mt7915_phy *phy, enum nl80211_band band, switch (i) { case NL80211_IFTYPE_AP: - he_cap_elem->mac_cap_info[0] |= - IEEE80211_HE_MAC_CAP0_TWT_RES; he_cap_elem->mac_cap_info[2] |= IEEE80211_HE_MAC_CAP2_BSR; he_cap_elem->mac_cap_info[4] |= @@ -594,8 +680,6 @@ mt7915_init_he_caps(struct mt7915_phy *phy, enum nl80211_band band, IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT; break; case NL80211_IFTYPE_STATION: - he_cap_elem->mac_cap_info[0] |= - IEEE80211_HE_MAC_CAP0_TWT_REQ; he_cap_elem->mac_cap_info[1] |= IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US; @@ -690,6 +774,7 @@ static void mt7915_unregister_ext_phy(struct mt7915_dev *dev) if (!phy) return; + mt7915_unregister_thermal(phy); mt76_unregister_phy(mphy); ieee80211_free_hw(mphy->hw); } @@ -731,8 +816,12 @@ int mt7915_register_device(struct mt7915_dev *dev) dev->mt76.test_ops = &mt7915_testmode_ops; #endif - ret = mt76_register_device(&dev->mt76, true, mt7915_rates, - ARRAY_SIZE(mt7915_rates)); + ret = mt76_register_device(&dev->mt76, true, mt76_rates, + ARRAY_SIZE(mt76_rates)); + if (ret) + return ret; + + ret = mt7915_thermal_init(&dev->phy); if (ret) return ret; @@ -748,10 +837,12 @@ int mt7915_register_device(struct mt7915_dev *dev) void mt7915_unregister_device(struct mt7915_dev *dev) { mt7915_unregister_ext_phy(dev); + mt7915_unregister_thermal(&dev->phy); mt76_unregister_device(&dev->mt76); mt7915_mcu_exit(dev); mt7915_tx_token_put(dev); mt7915_dma_cleanup(dev); + tasklet_disable(&dev->irq_tasklet); mt76_free_device(&dev->mt76); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index 7a9759fb79d8..2462704094b0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -307,7 +307,8 @@ mt7915_mac_decode_he_radiotap(struct sk_buff *skb, } } -int mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb) +static int +mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb) { struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb; struct mt76_phy *mphy = &dev->mt76.phy; @@ -412,14 +413,27 @@ int mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb) u8 *data = (u8 *)rxd; if (status->flag & RX_FLAG_DECRYPTED) { - status->iv[0] = data[5]; - status->iv[1] = data[4]; - status->iv[2] = data[3]; - status->iv[3] = data[2]; - status->iv[4] = data[1]; - status->iv[5] = data[0]; - - insert_ccmp_hdr = FIELD_GET(MT_RXD2_NORMAL_FRAG, rxd2); + switch (FIELD_GET(MT_RXD1_NORMAL_SEC_MODE, rxd1)) { + case MT_CIPHER_AES_CCMP: + case MT_CIPHER_CCMP_CCX: + case MT_CIPHER_CCMP_256: + insert_ccmp_hdr = + FIELD_GET(MT_RXD2_NORMAL_FRAG, rxd2); + fallthrough; + case MT_CIPHER_TKIP: + case MT_CIPHER_TKIP_NO_MIC: + case MT_CIPHER_GCMP: + case MT_CIPHER_GCMP_256: + status->iv[0] = data[5]; + status->iv[1] = data[4]; + status->iv[2] = data[3]; + status->iv[3] = data[2]; + status->iv[4] = data[1]; + status->iv[5] = data[0]; + break; + default: + break; + } } rxd += 4; if ((u8 *)rxd - skb->data >= skb->len) @@ -610,9 +624,10 @@ int mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb) return 0; } -#ifdef CONFIG_NL80211_TESTMODE -void mt7915_mac_fill_rx_vector(struct mt7915_dev *dev, struct sk_buff *skb) +static void +mt7915_mac_fill_rx_vector(struct mt7915_dev *dev, struct sk_buff *skb) { +#ifdef CONFIG_NL80211_TESTMODE struct mt7915_phy *phy = &dev->phy; __le32 *rxd = (__le32 *)skb->data; __le32 *rxv_hdr = rxd + 2; @@ -650,10 +665,10 @@ void mt7915_mac_fill_rx_vector(struct mt7915_dev *dev, struct sk_buff *skb) phy->test.last_freq_offset = foe; phy->test.last_snr = snr; +#endif dev_kfree_skb(skb); } -#endif static void mt7915_mac_write_txwi_tm(struct mt7915_phy *phy, __le32 *txwi, @@ -885,7 +900,7 @@ mt7915_mac_write_txwi_80211(struct mt7915_dev *dev, __le32 *txwi, } void mt7915_mac_write_txwi(struct mt7915_dev *dev, __le32 *txwi, - struct sk_buff *skb, struct mt76_wcid *wcid, + struct sk_buff *skb, struct mt76_wcid *wcid, int pid, struct ieee80211_key_conf *key, bool beacon) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); @@ -944,7 +959,12 @@ void mt7915_mac_write_txwi(struct mt7915_dev *dev, __le32 *txwi, txwi[3] = cpu_to_le32(val); txwi[4] = 0; - txwi[5] = 0; + + val = FIELD_PREP(MT_TXD5_PID, pid); + if (pid >= MT_PACKET_ID_FIRST) + val |= MT_TXD5_TX_STATUS_HOST; + txwi[5] = cpu_to_le32(val); + txwi[6] = 0; txwi[7] = wcid->amsdu ? cpu_to_le32(MT_TXD7_HW_AMSDU) : 0; @@ -984,11 +1004,11 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx_info->skb); struct ieee80211_key_conf *key = info->control.hw_key; struct ieee80211_vif *vif = info->control.vif; - struct mt76_tx_cb *cb = mt76_tx_skb_cb(tx_info->skb); struct mt76_txwi_cache *t; struct mt7915_txp *txp; int id, i, nbuf = tx_info->nbuf - 1; u8 *txwi = (u8 *)txwi_ptr; + int pid; if (unlikely(tx_info->skb->len <= ETH_HLEN)) return -EINVAL; @@ -996,10 +1016,10 @@ int mt7915_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, if (!wcid) wcid = &dev->mt76.global_wcid; - mt7915_mac_write_txwi(dev, txwi_ptr, tx_info->skb, wcid, key, - false); + pid = mt76_tx_status_skb_add(mdev, wcid, tx_info->skb); - cb->wcid = wcid->idx; + mt7915_mac_write_txwi(dev, txwi_ptr, tx_info->skb, wcid, pid, key, + false); txp = (struct mt7915_txp *)(txwi + MT_TXD_SIZE); for (i = 0; i < nbuf; i++) { @@ -1071,54 +1091,7 @@ mt7915_tx_check_aggr(struct ieee80211_sta *sta, __le32 *txwi) } static void -mt7915_tx_complete_status(struct mt76_dev *mdev, struct sk_buff *skb, - struct ieee80211_sta *sta, u8 stat, - struct list_head *free_list) -{ - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_tx_status status = { - .sta = sta, - .info = info, - .skb = skb, - .free_list = free_list, - }; - struct ieee80211_hw *hw; - - if (sta) { - struct mt7915_sta *msta; - - msta = (struct mt7915_sta *)sta->drv_priv; - status.rate = &msta->stats.tx_rate; - } - -#ifdef CONFIG_NL80211_TESTMODE - if (mt76_is_testmode_skb(mdev, skb, &hw)) { - struct mt7915_phy *phy = mt7915_hw_phy(hw); - struct ieee80211_vif *vif = phy->monitor_vif; - struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; - - mt76_tx_complete_skb(mdev, mvif->sta.wcid.idx, skb); - return; - } -#endif - - hw = mt76_tx_status_get_hw(mdev, skb); - - if (info->flags & IEEE80211_TX_CTL_AMPDU) - info->flags |= IEEE80211_TX_STAT_AMPDU; - - if (stat) - ieee80211_tx_info_clear_status(info); - - if (!(info->flags & IEEE80211_TX_CTL_NO_ACK)) - info->flags |= IEEE80211_TX_STAT_ACK; - - info->status.tx_time = 0; - ieee80211_tx_status_ext(hw, &status); -} - -void mt7915_txp_skb_unmap(struct mt76_dev *dev, - struct mt76_txwi_cache *t) +mt7915_txp_skb_unmap(struct mt76_dev *dev, struct mt76_txwi_cache *t) { struct mt7915_txp *txp; int i; @@ -1129,7 +1102,39 @@ void mt7915_txp_skb_unmap(struct mt76_dev *dev, le16_to_cpu(txp->len[i]), DMA_TO_DEVICE); } -void mt7915_mac_tx_free(struct mt7915_dev *dev, struct sk_buff *skb) +static void +mt7915_txwi_free(struct mt7915_dev *dev, struct mt76_txwi_cache *t, + struct ieee80211_sta *sta, struct list_head *free_list) +{ + struct mt76_dev *mdev = &dev->mt76; + struct mt76_wcid *wcid; + __le32 *txwi; + u16 wcid_idx; + + mt7915_txp_skb_unmap(mdev, t); + if (!t->skb) + goto out; + + txwi = (__le32 *)mt76_get_txwi_ptr(mdev, t); + if (sta) { + wcid = (struct mt76_wcid *)sta->drv_priv; + wcid_idx = wcid->idx; + + if (likely(t->skb->protocol != cpu_to_be16(ETH_P_PAE))) + mt7915_tx_check_aggr(sta, txwi); + } else { + wcid_idx = FIELD_GET(MT_TXD1_WLAN_IDX, le32_to_cpu(txwi[1])); + } + + __mt76_tx_complete_skb(mdev, wcid_idx, t->skb, free_list); + +out: + t->skb = NULL; + mt76_put_txwi(mdev, t); +} + +static void +mt7915_mac_tx_free(struct mt7915_dev *dev, struct sk_buff *skb) { struct mt7915_tx_free *free = (struct mt7915_tx_free *)skb->data; struct mt76_dev *mdev = &dev->mt76; @@ -1194,28 +1199,7 @@ void mt7915_mac_tx_free(struct mt7915_dev *dev, struct sk_buff *skb) if (!txwi) continue; - mt7915_txp_skb_unmap(mdev, txwi); - if (txwi->skb) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(txwi->skb); - void *txwi_ptr = mt76_get_txwi_ptr(mdev, txwi); - - if (likely(txwi->skb->protocol != cpu_to_be16(ETH_P_PAE))) - mt7915_tx_check_aggr(sta, txwi_ptr); - - if (sta && !info->tx_time_est) { - struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv; - int pending; - - pending = atomic_dec_return(&wcid->non_aql_packets); - if (pending < 0) - atomic_cmpxchg(&wcid->non_aql_packets, pending, 0); - } - - mt7915_tx_complete_status(mdev, txwi->skb, sta, stat, &free_list); - txwi->skb = NULL; - } - - mt76_put_txwi(mdev, txwi); + mt7915_txwi_free(dev, txwi, sta, &free_list); } mt7915_mac_sta_poll(dev); @@ -1233,6 +1217,120 @@ void mt7915_mac_tx_free(struct mt7915_dev *dev, struct sk_buff *skb) } } +static bool +mt7915_mac_add_txs_skb(struct mt7915_dev *dev, struct mt76_wcid *wcid, int pid, + __le32 *txs_data) +{ + struct mt76_dev *mdev = &dev->mt76; + struct ieee80211_tx_info *info; + struct sk_buff_head list; + struct sk_buff *skb; + + mt76_tx_status_lock(mdev, &list); + skb = mt76_tx_status_skb_get(mdev, wcid, pid, &list); + if (!skb) + goto out; + + info = IEEE80211_SKB_CB(skb); + if (!(txs_data[0] & le32_to_cpu(MT_TXS0_ACK_ERROR_MASK))) + info->flags |= IEEE80211_TX_STAT_ACK; + + info->status.ampdu_len = 1; + info->status.ampdu_ack_len = !!(info->flags & + IEEE80211_TX_STAT_ACK); + + info->status.rates[0].idx = -1; + mt76_tx_status_skb_done(mdev, skb, &list); + +out: + mt76_tx_status_unlock(mdev, &list); + + return !!skb; +} + +static void mt7915_mac_add_txs(struct mt7915_dev *dev, void *data) +{ + struct mt7915_sta *msta = NULL; + struct mt76_wcid *wcid; + __le32 *txs_data = data; + u16 wcidx; + u32 txs; + u8 pid; + + txs = le32_to_cpu(txs_data[0]); + if (FIELD_GET(MT_TXS0_TXS_FORMAT, txs) > 1) + return; + + txs = le32_to_cpu(txs_data[2]); + wcidx = FIELD_GET(MT_TXS2_WCID, txs); + + txs = le32_to_cpu(txs_data[3]); + pid = FIELD_GET(MT_TXS3_PID, txs); + + if (pid < MT_PACKET_ID_FIRST) + return; + + if (wcidx >= MT7915_WTBL_SIZE) + return; + + rcu_read_lock(); + + wcid = rcu_dereference(dev->mt76.wcid[wcidx]); + if (!wcid) + goto out; + + mt7915_mac_add_txs_skb(dev, wcid, pid, txs_data); + + if (!wcid->sta) + goto out; + + msta = container_of(wcid, struct mt7915_sta, wcid); + spin_lock_bh(&dev->sta_poll_lock); + if (list_empty(&msta->poll_list)) + list_add_tail(&msta->poll_list, &dev->sta_poll_list); + spin_unlock_bh(&dev->sta_poll_lock); + +out: + rcu_read_unlock(); +} + +void mt7915_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, + struct sk_buff *skb) +{ + struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76); + __le32 *rxd = (__le32 *)skb->data; + __le32 *end = (__le32 *)&skb->data[skb->len]; + enum rx_pkt_type type; + + type = FIELD_GET(MT_RXD0_PKT_TYPE, le32_to_cpu(rxd[0])); + + switch (type) { + case PKT_TYPE_TXRX_NOTIFY: + mt7915_mac_tx_free(dev, skb); + break; + case PKT_TYPE_RX_EVENT: + mt7915_mcu_rx_event(dev, skb); + break; + case PKT_TYPE_TXRXV: + mt7915_mac_fill_rx_vector(dev, skb); + break; + case PKT_TYPE_TXS: + for (rxd += 2; rxd + 8 <= end; rxd += 8) + mt7915_mac_add_txs(dev, rxd); + dev_kfree_skb(skb); + break; + case PKT_TYPE_NORMAL: + if (!mt7915_mac_fill_rx(dev, skb)) { + mt76_rx(&dev->mt76, q, skb); + return; + } + fallthrough; + default: + dev_kfree_skb(skb); + break; + } +} + void mt7915_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e) { struct mt7915_dev *dev; @@ -1254,15 +1352,8 @@ void mt7915_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue_entry *e) e->skb = t ? t->skb : NULL; } - if (e->skb) { - struct mt76_tx_cb *cb = mt76_tx_skb_cb(e->skb); - struct mt76_wcid *wcid; - - wcid = rcu_dereference(dev->mt76.wcid[cb->wcid]); - - mt7915_tx_complete_status(mdev, e->skb, wcid_to_sta(wcid), 0, - NULL); - } + if (e->skb) + mt76_tx_complete_skb(mdev, e->wcid, e->skb); } void mt7915_mac_cca_stats_reset(struct mt7915_phy *phy) @@ -1296,14 +1387,10 @@ void mt7915_mac_reset_counters(struct mt7915_phy *phy) memset(&dev->mt76.aggr_stats[i], 0, sizeof(dev->mt76.aggr_stats) / 2); /* reset airtime counters */ - mt76_rr(dev, MT_MIB_SDR9(ext_phy)); - mt76_rr(dev, MT_MIB_SDR36(ext_phy)); - mt76_rr(dev, MT_MIB_SDR37(ext_phy)); - - mt76_set(dev, MT_WF_RMAC_MIB_TIME0(ext_phy), - MT_WF_RMAC_MIB_RXTIME_CLR); mt76_set(dev, MT_WF_RMAC_MIB_AIRTIME0(ext_phy), MT_WF_RMAC_MIB_RXTIME_CLR); + + mt7915_mcu_get_chan_mib_info(phy, true); } void mt7915_mac_set_timing(struct mt7915_phy *phy) @@ -1397,53 +1484,24 @@ mt7915_phy_get_nf(struct mt7915_phy *phy, int idx) return sum / n; } -static void -mt7915_phy_update_channel(struct mt76_phy *mphy, int idx) +void mt7915_update_channel(struct mt76_phy *mphy) { - struct mt7915_dev *dev = container_of(mphy->dev, struct mt7915_dev, mt76); struct mt7915_phy *phy = (struct mt7915_phy *)mphy->priv; - struct mt76_channel_state *state; - u64 busy_time, tx_time, rx_time, obss_time; + struct mt76_channel_state *state = mphy->chan_state; + bool ext_phy = phy != &phy->dev->phy; int nf; - busy_time = mt76_get_field(dev, MT_MIB_SDR9(idx), - MT_MIB_SDR9_BUSY_MASK); - tx_time = mt76_get_field(dev, MT_MIB_SDR36(idx), - MT_MIB_SDR36_TXTIME_MASK); - rx_time = mt76_get_field(dev, MT_MIB_SDR37(idx), - MT_MIB_SDR37_RXTIME_MASK); - obss_time = mt76_get_field(dev, MT_WF_RMAC_MIB_AIRTIME14(idx), - MT_MIB_OBSSTIME_MASK); + mt7915_mcu_get_chan_mib_info(phy, false); - nf = mt7915_phy_get_nf(phy, idx); + nf = mt7915_phy_get_nf(phy, ext_phy); if (!phy->noise) phy->noise = nf << 4; else if (nf) phy->noise += nf - (phy->noise >> 4); - state = mphy->chan_state; - state->cc_busy += busy_time; - state->cc_tx += tx_time; - state->cc_rx += rx_time + obss_time; - state->cc_bss_rx += rx_time; state->noise = -(phy->noise >> 4); } -void mt7915_update_channel(struct mt76_dev *mdev) -{ - struct mt7915_dev *dev = container_of(mdev, struct mt7915_dev, mt76); - - mt7915_phy_update_channel(&mdev->phy, 0); - if (mdev->phy2) - mt7915_phy_update_channel(mdev->phy2, 1); - - /* reset obss airtime */ - mt76_set(dev, MT_WF_RMAC_MIB_TIME0(0), MT_WF_RMAC_MIB_RXTIME_CLR); - if (mdev->phy2) - mt76_set(dev, MT_WF_RMAC_MIB_TIME0(1), - MT_WF_RMAC_MIB_RXTIME_CLR); -} - static bool mt7915_wait_reset_state(struct mt7915_dev *dev, u32 state) { @@ -1530,14 +1588,18 @@ mt7915_dma_reset(struct mt7915_dev *dev) mt76_set(dev, MT_WFDMA0_GLO_CFG, MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN); mt76_set(dev, MT_WFDMA1_GLO_CFG, - MT_WFDMA1_GLO_CFG_TX_DMA_EN | MT_WFDMA1_GLO_CFG_RX_DMA_EN); + MT_WFDMA1_GLO_CFG_TX_DMA_EN | MT_WFDMA1_GLO_CFG_RX_DMA_EN | + MT_WFDMA1_GLO_CFG_OMIT_TX_INFO | + MT_WFDMA1_GLO_CFG_OMIT_RX_INFO); if (dev->hif2) { mt76_set(dev, MT_WFDMA0_GLO_CFG + hif1_ofs, (MT_WFDMA0_GLO_CFG_TX_DMA_EN | MT_WFDMA0_GLO_CFG_RX_DMA_EN)); mt76_set(dev, MT_WFDMA1_GLO_CFG + hif1_ofs, (MT_WFDMA1_GLO_CFG_TX_DMA_EN | - MT_WFDMA1_GLO_CFG_RX_DMA_EN)); + MT_WFDMA1_GLO_CFG_RX_DMA_EN | + MT_WFDMA1_GLO_CFG_OMIT_TX_INFO | + MT_WFDMA1_GLO_CFG_OMIT_RX_INFO)); } } @@ -1548,14 +1610,7 @@ void mt7915_tx_token_put(struct mt7915_dev *dev) spin_lock_bh(&dev->mt76.token_lock); idr_for_each_entry(&dev->mt76.token, txwi, id) { - mt7915_txp_skb_unmap(&dev->mt76, txwi); - if (txwi->skb) { - struct ieee80211_hw *hw; - - hw = mt76_tx_status_get_hw(&dev->mt76, txwi->skb); - ieee80211_free_txskb(hw, txwi->skb); - } - mt76_put_txwi(&dev->mt76, txwi); + mt7915_txwi_free(dev, txwi, NULL, NULL); dev->mt76.token_count--; } spin_unlock_bh(&dev->mt76.token_lock); @@ -1588,11 +1643,6 @@ void mt7915_mac_reset_work(struct work_struct *work) set_bit(MT76_RESET, &phy2->mt76->state); cancel_delayed_work_sync(&phy2->mt76->mac_work); } - /* lock/unlock all queues to ensure that no tx is pending */ - mt76_txq_schedule_all(&dev->mphy); - if (ext_phy) - mt76_txq_schedule_all(ext_phy); - mt76_worker_disable(&dev->mt76.tx_worker); napi_disable(&dev->mt76.napi[0]); napi_disable(&dev->mt76.napi[1]); @@ -1618,10 +1668,6 @@ void mt7915_mac_reset_work(struct work_struct *work) if (phy2) clear_bit(MT76_RESET, &phy2->mt76->state); - mt76_worker_enable(&dev->mt76.tx_worker); - napi_enable(&dev->mt76.tx_napi); - napi_schedule(&dev->mt76.tx_napi); - napi_enable(&dev->mt76.napi[0]); napi_schedule(&dev->mt76.napi[0]); @@ -1630,14 +1676,20 @@ void mt7915_mac_reset_work(struct work_struct *work) napi_enable(&dev->mt76.napi[2]); napi_schedule(&dev->mt76.napi[2]); + tasklet_schedule(&dev->irq_tasklet); + + mt76_wr(dev, MT_MCU_INT_EVENT, MT_MCU_INT_EVENT_RESET_DONE); + mt7915_wait_reset_state(dev, MT_MCU_CMD_NORMAL_STATE); + + mt76_worker_enable(&dev->mt76.tx_worker); + + napi_enable(&dev->mt76.tx_napi); + napi_schedule(&dev->mt76.tx_napi); ieee80211_wake_queues(mt76_hw(dev)); if (ext_phy) ieee80211_wake_queues(ext_phy->hw); - mt76_wr(dev, MT_MCU_INT_EVENT, MT_MCU_INT_EVENT_RESET_DONE); - mt7915_wait_reset_state(dev, MT_MCU_CMD_NORMAL_STATE); - mutex_unlock(&dev->mt76.mutex); mt7915_update_beacons(dev); @@ -1651,7 +1703,7 @@ void mt7915_mac_reset_work(struct work_struct *work) } static void -mt7915_mac_update_mib_stats(struct mt7915_phy *phy) +mt7915_mac_update_stats(struct mt7915_phy *phy) { struct mt7915_dev *dev = phy->dev; struct mib_stats *mib = &phy->mib; @@ -1733,8 +1785,10 @@ void mt7915_mac_sta_rc_work(struct work_struct *work) if (changed & (IEEE80211_RC_SUPP_RATES_CHANGED | IEEE80211_RC_NSS_CHANGED | - IEEE80211_RC_BW_CHANGED)) + IEEE80211_RC_BW_CHANGED)) { + mt7915_mcu_add_he(dev, vif, sta); mt7915_mcu_add_rate_ctrl(dev, vif, sta); + } if (changed & IEEE80211_RC_SMPS_CHANGED) mt7915_mcu_add_smps(dev, vif, sta); @@ -1756,11 +1810,11 @@ void mt7915_mac_work(struct work_struct *work) mutex_lock(&mphy->dev->mutex); - mt76_update_survey(mphy->dev); + mt76_update_survey(mphy); if (++mphy->mac_work_count == 5) { mphy->mac_work_count = 0; - mt7915_mac_update_mib_stats(phy); + mt7915_mac_update_stats(phy); } if (++phy->sta_work_count == 10) { @@ -1770,6 +1824,8 @@ void mt7915_mac_work(struct work_struct *work) mutex_unlock(&mphy->dev->mutex); + mt76_tx_status_check(mphy->dev, NULL, false); + ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work, MT7915_WATCHDOG_TIME); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.h b/drivers/net/wireless/mediatek/mt76/mt7915/mac.h index 0f929fb53027..eb1885f4bd8e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.h @@ -304,6 +304,62 @@ struct mt7915_tx_free { /* will support this field in further revision */ #define MT_TX_FREE_RATE GENMASK(13, 0) +#define MT_TXS0_FIXED_RATE BIT(31) +#define MT_TXS0_BW GENMASK(30, 29) +#define MT_TXS0_TID GENMASK(28, 26) +#define MT_TXS0_AMPDU BIT(25) +#define MT_TXS0_TXS_FORMAT GENMASK(24, 23) +#define MT_TXS0_BA_ERROR BIT(22) +#define MT_TXS0_PS_FLAG BIT(21) +#define MT_TXS0_TXOP_TIMEOUT BIT(20) +#define MT_TXS0_BIP_ERROR BIT(19) + +#define MT_TXS0_QUEUE_TIMEOUT BIT(18) +#define MT_TXS0_RTS_TIMEOUT BIT(17) +#define MT_TXS0_ACK_TIMEOUT BIT(16) +#define MT_TXS0_ACK_ERROR_MASK GENMASK(18, 16) + +#define MT_TXS0_TX_STATUS_HOST BIT(15) +#define MT_TXS0_TX_STATUS_MCU BIT(14) +#define MT_TXS0_TX_RATE GENMASK(13, 0) + +#define MT_TXS1_SEQNO GENMASK(31, 20) +#define MT_TXS1_RESP_RATE GENMASK(19, 16) +#define MT_TXS1_RXV_SEQNO GENMASK(15, 8) +#define MT_TXS1_TX_POWER_DBM GENMASK(7, 0) + +#define MT_TXS2_BF_STATUS GENMASK(31, 30) +#define MT_TXS2_LAST_TX_RATE GENMASK(29, 27) +#define MT_TXS2_SHARED_ANTENNA BIT(26) +#define MT_TXS2_WCID GENMASK(25, 16) +#define MT_TXS2_TX_DELAY GENMASK(15, 0) + +#define MT_TXS3_PID GENMASK(31, 24) +#define MT_TXS3_ANT_ID GENMASK(23, 0) + +#define MT_TXS4_TIMESTAMP GENMASK(31, 0) + +#define MT_TXS5_F0_FINAL_MPDU BIT(31) +#define MT_TXS5_F0_QOS BIT(30) +#define MT_TXS5_F0_TX_COUNT GENMASK(29, 25) +#define MT_TXS5_F0_FRONT_TIME GENMASK(24, 0) +#define MT_TXS5_F1_MPDU_TX_COUNT GENMASK(31, 24) +#define MT_TXS5_F1_MPDU_TX_BYTES GENMASK(23, 0) + +#define MT_TXS6_F0_NOISE_3 GENMASK(31, 24) +#define MT_TXS6_F0_NOISE_2 GENMASK(23, 16) +#define MT_TXS6_F0_NOISE_1 GENMASK(15, 8) +#define MT_TXS6_F0_NOISE_0 GENMASK(7, 0) +#define MT_TXS6_F1_MPDU_FAIL_COUNT GENMASK(31, 24) +#define MT_TXS6_F1_MPDU_FAIL_BYTES GENMASK(23, 0) + +#define MT_TXS7_F0_RCPI_3 GENMASK(31, 24) +#define MT_TXS7_F0_RCPI_2 GENMASK(23, 16) +#define MT_TXS7_F0_RCPI_1 GENMASK(15, 8) +#define MT_TXS7_F0_RCPI_0 GENMASK(7, 0) +#define MT_TXS7_F1_MPDU_RETRY_COUNT GENMASK(31, 24) +#define MT_TXS7_F1_MPDU_RETRY_BYTES GENMASK(23, 0) + struct mt7915_dfs_pulse { u32 max_width; /* us */ int max_pwr; /* dbm */ diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c index e5bd687546b6..c25f8da590dd 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c @@ -139,12 +139,6 @@ static int get_omac_idx(enum nl80211_iftype type, u64 mask) if (type != NL80211_IFTYPE_STATION) break; - /* next, try to find a free repeater entry for the sta */ - i = get_free_idx(mask >> REPEATER_BSSID_START, 0, - REPEATER_BSSID_MAX - REPEATER_BSSID_START); - if (i) - return i + 32 - 1; - i = get_free_idx(mask, EXT_BSSID_1, EXT_BSSID_MAX); if (i) return i - 1; @@ -172,6 +166,22 @@ static int get_omac_idx(enum nl80211_iftype type, u64 mask) return -1; } +static void mt7915_init_bitrate_mask(struct ieee80211_vif *vif) +{ + struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; + int i; + + for (i = 0; i < ARRAY_SIZE(mvif->bitrate_mask.control); i++) { + mvif->bitrate_mask.control[i].legacy = GENMASK(31, 0); + memset(mvif->bitrate_mask.control[i].ht_mcs, GENMASK(7, 0), + sizeof(mvif->bitrate_mask.control[i].ht_mcs)); + memset(mvif->bitrate_mask.control[i].vht_mcs, GENMASK(15, 0), + sizeof(mvif->bitrate_mask.control[i].vht_mcs)); + memset(mvif->bitrate_mask.control[i].he_mcs, GENMASK(15, 0), + sizeof(mvif->bitrate_mask.control[i].he_mcs)); + } +} + static int mt7915_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { @@ -241,6 +251,8 @@ static int mt7915_add_interface(struct ieee80211_hw *hw, vif->offload_flags = 0; vif->offload_flags |= IEEE80211_OFFLOAD_ENCAP_4ADDR; + mt7915_init_bitrate_mask(vif); + out: mutex_unlock(&dev->mt76.mutex); @@ -798,7 +810,8 @@ mt7915_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif) n = mvif->omac_idx > HW_BSSID_MAX ? HW_BSSID_0 : mvif->omac_idx; /* TSF software read */ - mt76_set(dev, MT_LPON_TCR(band, n), MT_LPON_TCR_SW_MODE); + mt76_rmw(dev, MT_LPON_TCR(band, n), MT_LPON_TCR_SW_MODE, + MT_LPON_TCR_SW_READ); tsf.t32[0] = mt76_rr(dev, MT_LPON_UTTR0(band)); tsf.t32[1] = mt76_rr(dev, MT_LPON_UTTR1(band)); @@ -827,7 +840,34 @@ mt7915_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif, mt76_wr(dev, MT_LPON_UTTR0(band), tsf.t32[0]); mt76_wr(dev, MT_LPON_UTTR1(band), tsf.t32[1]); /* TSF software overwrite */ - mt76_set(dev, MT_LPON_TCR(band, n), MT_LPON_TCR_SW_WRITE); + mt76_rmw(dev, MT_LPON_TCR(band, n), MT_LPON_TCR_SW_MODE, + MT_LPON_TCR_SW_WRITE); + + mutex_unlock(&dev->mt76.mutex); +} + +static void +mt7915_offset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + s64 timestamp) +{ + struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; + struct mt7915_dev *dev = mt7915_hw_dev(hw); + struct mt7915_phy *phy = mt7915_hw_phy(hw); + bool band = phy != &dev->phy; + union { + u64 t64; + u32 t32[2]; + } tsf = { .t64 = timestamp, }; + u16 n; + + mutex_lock(&dev->mt76.mutex); + + n = mvif->omac_idx > HW_BSSID_MAX ? HW_BSSID_0 : mvif->omac_idx; + mt76_wr(dev, MT_LPON_UTTR0(band), tsf.t32[0]); + mt76_wr(dev, MT_LPON_UTTR1(band), tsf.t32[1]); + /* TSF software adjust*/ + mt76_rmw(dev, MT_LPON_TCR(band, n), MT_LPON_TCR_SW_MODE, + MT_LPON_TCR_SW_ADJUST); mutex_unlock(&dev->mt76.mutex); } @@ -911,17 +951,15 @@ static void mt7915_sta_statistics(struct ieee80211_hw *hw, sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE); } -static void -mt7915_sta_rc_update(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - struct ieee80211_sta *sta, - u32 changed) +static void mt7915_sta_rc_work(void *data, struct ieee80211_sta *sta) { - struct mt7915_dev *dev = mt7915_hw_dev(hw); struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv; + struct mt7915_dev *dev = msta->vif->phy->dev; + struct ieee80211_hw *hw = msta->vif->phy->mt76->hw; + u32 *changed = data; spin_lock_bh(&dev->sta_poll_lock); - msta->stats.changed |= changed; + msta->stats.changed |= *changed; if (list_empty(&msta->rc_list)) list_add_tail(&msta->rc_list, &dev->sta_rc_list); spin_unlock_bh(&dev->sta_poll_lock); @@ -929,6 +967,39 @@ mt7915_sta_rc_update(struct ieee80211_hw *hw, ieee80211_queue_work(hw, &dev->rc_work); } +static void mt7915_sta_rc_update(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + u32 changed) +{ + mt7915_sta_rc_work(&changed, sta); +} + +static int +mt7915_set_bitrate_mask(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + const struct cfg80211_bitrate_mask *mask) +{ + struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; + enum nl80211_band band = mvif->phy->mt76->chandef.chan->band; + u32 changed; + + if (mask->control[band].gi == NL80211_TXRATE_FORCE_LGI) + return -EINVAL; + + changed = IEEE80211_RC_SUPP_RATES_CHANGED; + mvif->bitrate_mask = *mask; + + /* Update firmware rate control to add a boundary on top of table + * to limit the rate selection for each peer, so when set bitrates + * vht-mcs-5 1:9, which actually means nss = 1 mcs = 0~9. This only + * applies to data frames as for the other mgmt, mcast, bcast still + * use legacy rates as it is. + */ + ieee80211_iterate_stations_atomic(hw, mt7915_sta_rc_work, &changed); + + return 0; +} + static void mt7915_sta_set_4addr(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, @@ -987,9 +1058,11 @@ const struct ieee80211_ops mt7915_ops = { .get_stats = mt7915_get_stats, .get_tsf = mt7915_get_tsf, .set_tsf = mt7915_set_tsf, + .offset_tsf = mt7915_offset_tsf, .get_survey = mt76_get_survey, .get_antenna = mt76_get_antenna, .set_antenna = mt7915_set_antenna, + .set_bitrate_mask = mt7915_set_bitrate_mask, .set_coverage_class = mt7915_set_coverage_class, .sta_statistics = mt7915_sta_statistics, .sta_set_4addr = mt7915_sta_set_4addr, diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c index b3f14ff67c5a..863aa18b3024 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c @@ -88,28 +88,28 @@ struct mt7915_fw_region { #define HE_PHY(p, c) u8_get_bits(c, IEEE80211_HE_PHY_##p) #define HE_MAC(m, c) u8_get_bits(c, IEEE80211_HE_MAC_##m) -static enum mt7915_cipher_type +static enum mcu_cipher_type mt7915_mcu_get_cipher(int cipher) { switch (cipher) { case WLAN_CIPHER_SUITE_WEP40: - return MT_CIPHER_WEP40; + return MCU_CIPHER_WEP40; case WLAN_CIPHER_SUITE_WEP104: - return MT_CIPHER_WEP104; + return MCU_CIPHER_WEP104; case WLAN_CIPHER_SUITE_TKIP: - return MT_CIPHER_TKIP; + return MCU_CIPHER_TKIP; case WLAN_CIPHER_SUITE_AES_CMAC: - return MT_CIPHER_BIP_CMAC_128; + return MCU_CIPHER_BIP_CMAC_128; case WLAN_CIPHER_SUITE_CCMP: - return MT_CIPHER_AES_CCMP; + return MCU_CIPHER_AES_CCMP; case WLAN_CIPHER_SUITE_CCMP_256: - return MT_CIPHER_CCMP_256; + return MCU_CIPHER_CCMP_256; case WLAN_CIPHER_SUITE_GCMP: - return MT_CIPHER_GCMP; + return MCU_CIPHER_GCMP; case WLAN_CIPHER_SUITE_GCMP_256: - return MT_CIPHER_GCMP_256; + return MCU_CIPHER_GCMP_256; case WLAN_CIPHER_SUITE_SMS4: - return MT_CIPHER_WAPI; + return MCU_CIPHER_WAPI; default: return MT_CIPHER_NONE; } @@ -147,10 +147,10 @@ mt7915_get_he_phy_cap(struct mt7915_phy *phy, struct ieee80211_vif *vif) } static u8 -mt7915_get_phy_mode(struct mt76_phy *mphy, struct ieee80211_vif *vif, - struct ieee80211_sta *sta) +mt7915_get_phy_mode(struct ieee80211_vif *vif, struct ieee80211_sta *sta) { - enum nl80211_band band = mphy->chandef.chan->band; + struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; + enum nl80211_band band = mvif->phy->mt76->chandef.chan->band; struct ieee80211_sta_ht_cap *ht_cap; struct ieee80211_sta_vht_cap *vht_cap; const struct ieee80211_sta_he_cap *he_cap; @@ -163,7 +163,7 @@ mt7915_get_phy_mode(struct mt76_phy *mphy, struct ieee80211_vif *vif, } else { struct ieee80211_supported_band *sband; - sband = mphy->hw->wiphy->bands[band]; + sband = mvif->phy->mt76->hw->wiphy->bands[band]; ht_cap = &sband->ht_cap; vht_cap = &sband->vht_cap; @@ -209,6 +209,112 @@ mt7915_mcu_get_sta_nss(u16 mcs_map) return nss - 1; } +static void +mt7915_mcu_set_sta_he_mcs(struct ieee80211_sta *sta, __le16 *he_mcs, + const u16 *mask) +{ + struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv; + struct cfg80211_chan_def *chandef = &msta->vif->phy->mt76->chandef; + int nss, max_nss = sta->rx_nss > 3 ? 4 : sta->rx_nss; + u16 mcs_map; + + switch (chandef->width) { + case NL80211_CHAN_WIDTH_80P80: + mcs_map = le16_to_cpu(sta->he_cap.he_mcs_nss_supp.rx_mcs_80p80); + break; + case NL80211_CHAN_WIDTH_160: + mcs_map = le16_to_cpu(sta->he_cap.he_mcs_nss_supp.rx_mcs_160); + break; + default: + mcs_map = le16_to_cpu(sta->he_cap.he_mcs_nss_supp.rx_mcs_80); + break; + } + + for (nss = 0; nss < max_nss; nss++) { + int mcs; + + switch ((mcs_map >> (2 * nss)) & 0x3) { + case IEEE80211_HE_MCS_SUPPORT_0_11: + mcs = GENMASK(11, 0); + break; + case IEEE80211_HE_MCS_SUPPORT_0_9: + mcs = GENMASK(9, 0); + break; + case IEEE80211_HE_MCS_SUPPORT_0_7: + mcs = GENMASK(7, 0); + break; + default: + mcs = 0; + } + + mcs = mcs ? fls(mcs & mask[nss]) - 1 : -1; + + switch (mcs) { + case 0 ... 7: + mcs = IEEE80211_HE_MCS_SUPPORT_0_7; + break; + case 8 ... 9: + mcs = IEEE80211_HE_MCS_SUPPORT_0_9; + break; + case 10 ... 11: + mcs = IEEE80211_HE_MCS_SUPPORT_0_11; + break; + default: + mcs = IEEE80211_HE_MCS_NOT_SUPPORTED; + break; + } + mcs_map &= ~(0x3 << (nss * 2)); + mcs_map |= mcs << (nss * 2); + + /* only support 2ss on 160MHz */ + if (nss > 1 && (sta->bandwidth == IEEE80211_STA_RX_BW_160)) + break; + } + + *he_mcs = cpu_to_le16(mcs_map); +} + +static void +mt7915_mcu_set_sta_vht_mcs(struct ieee80211_sta *sta, __le16 *vht_mcs, + const u16 *mask) +{ + u16 mcs_map = le16_to_cpu(sta->vht_cap.vht_mcs.rx_mcs_map); + int nss, max_nss = sta->rx_nss > 3 ? 4 : sta->rx_nss; + u16 mcs; + + for (nss = 0; nss < max_nss; nss++, mcs_map >>= 2) { + switch (mcs_map & 0x3) { + case IEEE80211_VHT_MCS_SUPPORT_0_9: + mcs = GENMASK(9, 0); + break; + case IEEE80211_VHT_MCS_SUPPORT_0_8: + mcs = GENMASK(8, 0); + break; + case IEEE80211_VHT_MCS_SUPPORT_0_7: + mcs = GENMASK(7, 0); + break; + default: + mcs = 0; + } + + vht_mcs[nss] = cpu_to_le16(mcs & mask[nss]); + + /* only support 2ss on 160MHz */ + if (nss > 1 && (sta->bandwidth == IEEE80211_STA_RX_BW_160)) + break; + } +} + +static void +mt7915_mcu_set_sta_ht_mcs(struct ieee80211_sta *sta, u8 *ht_mcs, + const u8 *mask) +{ + int nss, max_nss = sta->rx_nss > 3 ? 4 : sta->rx_nss; + + for (nss = 0; nss < max_nss; nss++) + ht_mcs[nss] = sta->ht_cap.mcs.rx_mask[nss] & mask[nss]; +} + static int mt7915_mcu_parse_response(struct mt76_dev *mdev, int cmd, struct sk_buff *skb, int seq) @@ -349,6 +455,24 @@ mt7915_mcu_rx_csa_notify(struct mt7915_dev *dev, struct sk_buff *skb) mt7915_mcu_csa_finish, mphy->hw); } +static void +mt7915_mcu_rx_thermal_notify(struct mt7915_dev *dev, struct sk_buff *skb) +{ + struct mt76_phy *mphy = &dev->mt76.phy; + struct mt7915_mcu_thermal_notify *t; + struct mt7915_phy *phy; + + t = (struct mt7915_mcu_thermal_notify *)skb->data; + if (t->ctrl.ctrl_id != THERMAL_PROTECT_ENABLE) + return; + + if (t->ctrl.band_idx && dev->mt76.phy2) + mphy = dev->mt76.phy2; + + phy = (struct mt7915_phy *)mphy->priv; + phy->throttle_state = t->ctrl.duty.duty_cycle; +} + static void mt7915_mcu_rx_radar_detected(struct mt7915_dev *dev, struct sk_buff *skb) { @@ -469,6 +593,7 @@ mt7915_mcu_tx_rate_report(struct mt7915_dev *dev, struct sk_buff *skb) u16 attempts = le16_to_cpu(ra->attempts); u16 curr = le16_to_cpu(ra->curr_rate); u16 wcidx = le16_to_cpu(ra->wlan_idx); + struct ieee80211_tx_status status = {}; struct mt76_phy *mphy = &dev->mphy; struct mt7915_sta_stats *stats; struct mt7915_sta *msta; @@ -500,6 +625,13 @@ mt7915_mcu_tx_rate_report(struct mt7915_dev *dev, struct sk_buff *skb) stats->per = 1000 * (attempts - success) / attempts; } + + status.sta = wcid_to_sta(wcid); + if (!status.sta) + return; + + status.rate = &stats->tx_rate; + ieee80211_tx_status_ext(mphy->hw, &status); } static void @@ -531,6 +663,9 @@ mt7915_mcu_rx_ext_event(struct mt7915_dev *dev, struct sk_buff *skb) struct mt7915_mcu_rxd *rxd = (struct mt7915_mcu_rxd *)skb->data; switch (rxd->ext_eid) { + case MCU_EXT_EVENT_THERMAL_PROTECT: + mt7915_mcu_rx_thermal_notify(dev, skb); + break; case MCU_EXT_EVENT_RDD_REPORT: mt7915_mcu_rx_radar_detected(dev, skb); break; @@ -733,7 +868,7 @@ mt7915_mcu_bss_basic_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, memcpy(bss->bssid, vif->bss_conf.bssid, ETH_ALEN); bss->bcn_interval = cpu_to_le16(vif->bss_conf.beacon_int); bss->dtim_period = vif->bss_conf.dtim_period; - bss->phy_mode = mt7915_get_phy_mode(phy->mt76, vif, NULL); + bss->phy_mode = mt7915_get_phy_mode(vif, NULL); } else { memcpy(bss->bssid, phy->mt76->macaddr, ETH_ALEN); } @@ -1072,14 +1207,14 @@ mt7915_mcu_sta_key_tlv(struct mt7915_sta *msta, struct sk_buff *skb, sec_key = &sec->key[0]; sec_key->cipher_len = sizeof(*sec_key); - if (cipher == MT_CIPHER_BIP_CMAC_128) { - sec_key->cipher_id = MT_CIPHER_AES_CCMP; + if (cipher == MCU_CIPHER_BIP_CMAC_128) { + sec_key->cipher_id = MCU_CIPHER_AES_CCMP; sec_key->key_id = bip->keyidx; sec_key->key_len = 16; memcpy(sec_key->key, bip->key, 16); sec_key = &sec->key[1]; - sec_key->cipher_id = MT_CIPHER_BIP_CMAC_128; + sec_key->cipher_id = MCU_CIPHER_BIP_CMAC_128; sec_key->cipher_len = sizeof(*sec_key); sec_key->key_len = 16; memcpy(sec_key->key, key->key, 16); @@ -1091,14 +1226,14 @@ mt7915_mcu_sta_key_tlv(struct mt7915_sta *msta, struct sk_buff *skb, sec_key->key_len = key->keylen; memcpy(sec_key->key, key->key, key->keylen); - if (cipher == MT_CIPHER_TKIP) { + if (cipher == MCU_CIPHER_TKIP) { /* Rx/Tx MIC keys are swapped */ memcpy(sec_key->key + 16, key->key + 24, 8); memcpy(sec_key->key + 24, key->key + 16, 8); } /* store key_conf for BIP batch update */ - if (cipher == MT_CIPHER_AES_CCMP) { + if (cipher == MCU_CIPHER_AES_CCMP) { memcpy(bip->key, key->key, key->keylen); bip->keyidx = key->keyidx; } @@ -1336,8 +1471,11 @@ mt7915_mcu_sta_basic_tlv(struct sk_buff *skb, struct ieee80211_vif *vif, static void mt7915_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) { + struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv; struct ieee80211_sta_he_cap *he_cap = &sta->he_cap; struct ieee80211_he_cap_elem *elem = &he_cap->he_cap_elem; + enum nl80211_band band = msta->vif->phy->mt76->chandef.chan->band; + const u16 *mcs_mask = msta->vif->bitrate_mask.control[band].he_mcs; struct sta_rec_he *he; struct tlv *tlv; u32 cap = 0; @@ -1428,15 +1566,18 @@ mt7915_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) case IEEE80211_STA_RX_BW_160: if (elem->phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) - he->max_nss_mcs[CMD_HE_MCS_BW8080] = - he_cap->he_mcs_nss_supp.rx_mcs_80p80; + mt7915_mcu_set_sta_he_mcs(sta, + &he->max_nss_mcs[CMD_HE_MCS_BW8080], + mcs_mask); - he->max_nss_mcs[CMD_HE_MCS_BW160] = - he_cap->he_mcs_nss_supp.rx_mcs_160; + mt7915_mcu_set_sta_he_mcs(sta, + &he->max_nss_mcs[CMD_HE_MCS_BW160], + mcs_mask); fallthrough; default: - he->max_nss_mcs[CMD_HE_MCS_BW80] = - he_cap->he_mcs_nss_supp.rx_mcs_80; + mt7915_mcu_set_sta_he_mcs(sta, + &he->max_nss_mcs[CMD_HE_MCS_BW80], + mcs_mask); break; } @@ -1544,27 +1685,18 @@ mt7915_mcu_sta_muru_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) HE_PHY(CAP2_UL_MU_PARTIAL_MU_MIMO, elem->phy_cap_info[2]); } -static int -mt7915_mcu_add_mu(struct mt7915_dev *dev, struct ieee80211_vif *vif, - struct ieee80211_sta *sta) +static void +mt7915_mcu_sta_vht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta) { - struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; - struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv; - struct sk_buff *skb; - int len = sizeof(struct sta_req_hdr) + sizeof(struct sta_rec_muru); + struct sta_rec_vht *vht; + struct tlv *tlv; - if (!sta->vht_cap.vht_supported && !sta->he_cap.has_he) - return 0; + tlv = mt7915_mcu_add_tlv(skb, STA_REC_VHT, sizeof(*vht)); - skb = mt7915_mcu_alloc_sta_req(dev, mvif, msta, len); - if (IS_ERR(skb)) - return PTR_ERR(skb); - - /* starec muru */ - mt7915_mcu_sta_muru_tlv(skb, sta); - - return mt76_mcu_skb_send_msg(&dev->mt76, skb, - MCU_EXT_CMD(STA_REC_UPDATE), true); + vht = (struct sta_rec_vht *)tlv; + vht->vht_cap = cpu_to_le32(sta->vht_cap.cap); + vht->vht_rx_mcs_map = sta->vht_cap.vht_mcs.rx_mcs_map; + vht->vht_tx_mcs_map = sta->vht_cap.vht_mcs.tx_mcs_map; } static void @@ -1616,17 +1748,6 @@ mt7915_mcu_sta_tlv(struct mt7915_dev *dev, struct sk_buff *skb, mt7915_mcu_sta_amsdu_tlv(skb, sta); } - /* starec vht */ - if (sta->vht_cap.vht_supported) { - struct sta_rec_vht *vht; - - tlv = mt7915_mcu_add_tlv(skb, STA_REC_VHT, sizeof(*vht)); - vht = (struct sta_rec_vht *)tlv; - vht->vht_cap = cpu_to_le32(sta->vht_cap.cap); - vht->vht_rx_mcs_map = sta->vht_cap.vht_mcs.rx_mcs_map; - vht->vht_tx_mcs_map = sta->vht_cap.vht_mcs.tx_mcs_map; - } - /* starec he */ if (sta->he_cap.has_he) mt7915_mcu_sta_he_tlv(skb, sta); @@ -2016,26 +2137,21 @@ mt7915_mcu_add_txbf(struct mt7915_dev *dev, struct ieee80211_vif *vif, vc = mt7915_get_he_phy_cap(phy, vif); ve = &vc->he_cap_elem; - ebfee = !!((HE_PHY(CAP3_SU_BEAMFORMER, pe->phy_cap_info[3]) || - HE_PHY(CAP4_MU_BEAMFORMER, pe->phy_cap_info[4])) && + ebfee = !!(HE_PHY(CAP3_SU_BEAMFORMER, pe->phy_cap_info[3]) && HE_PHY(CAP4_SU_BEAMFORMEE, ve->phy_cap_info[4])); - ebf = !!((HE_PHY(CAP3_SU_BEAMFORMER, ve->phy_cap_info[3]) || - HE_PHY(CAP4_MU_BEAMFORMER, ve->phy_cap_info[4])) && + ebf = !!(HE_PHY(CAP3_SU_BEAMFORMER, ve->phy_cap_info[3]) && HE_PHY(CAP4_SU_BEAMFORMEE, pe->phy_cap_info[4])); } else if (sta->vht_cap.vht_supported) { struct ieee80211_sta_vht_cap *pc; struct ieee80211_sta_vht_cap *vc; - u32 cr, ce; pc = &sta->vht_cap; vc = &phy->mt76->sband_5g.sband.vht_cap; - cr = IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE | - IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE; - ce = IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE | - IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE; - ebfee = !!((pc->cap & cr) && (vc->cap & ce)); - ebf = !!((vc->cap & cr) && (pc->cap & ce)); + ebfee = !!((pc->cap & IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE) && + (vc->cap & IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE)); + ebf = !!((vc->cap & IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE) && + (pc->cap & IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE)); } /* must keep each tag independent */ @@ -2079,57 +2195,47 @@ static void mt7915_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7915_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { - struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv; - struct mt76_phy *mphy = &dev->mphy; - enum nl80211_band band; + struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; + struct cfg80211_chan_def *chandef = &mvif->phy->mt76->chandef; + struct cfg80211_bitrate_mask *mask = &mvif->bitrate_mask; + enum nl80211_band band = chandef->chan->band; struct sta_rec_ra *ra; struct tlv *tlv; - u32 supp_rate, n_rates, cap = sta->wme ? STA_CAP_WMM : 0; - u8 i, nss = sta->rx_nss, mcs = 0; + u32 supp_rate = sta->supp_rates[band]; + u32 cap = sta->wme ? STA_CAP_WMM : 0; tlv = mt7915_mcu_add_tlv(skb, STA_REC_RA, sizeof(*ra)); ra = (struct sta_rec_ra *)tlv; - if (msta->wcid.ext_phy && dev->mt76.phy2) - mphy = dev->mt76.phy2; - - band = mphy->chandef.chan->band; - supp_rate = sta->supp_rates[band]; - n_rates = hweight32(supp_rate); - ra->valid = true; ra->auto_rate = true; - ra->phy_mode = mt7915_get_phy_mode(mphy, vif, sta); - ra->channel = mphy->chandef.chan->hw_value; + ra->phy_mode = mt7915_get_phy_mode(vif, sta); + ra->channel = chandef->chan->hw_value; ra->bw = sta->bandwidth; - ra->rate_len = n_rates; ra->phy.bw = sta->bandwidth; - if (n_rates) { + if (supp_rate) { + supp_rate &= mask->control[band].legacy; + ra->rate_len = hweight32(supp_rate); + if (band == NL80211_BAND_2GHZ) { ra->supp_mode = MODE_CCK; ra->supp_cck_rate = supp_rate & GENMASK(3, 0); - ra->phy.type = MT_PHY_TYPE_CCK; - if (n_rates > 4) { + if (ra->rate_len > 4) { ra->supp_mode |= MODE_OFDM; ra->supp_ofdm_rate = supp_rate >> 4; - ra->phy.type = MT_PHY_TYPE_OFDM; } } else { ra->supp_mode = MODE_OFDM; ra->supp_ofdm_rate = supp_rate; - ra->phy.type = MT_PHY_TYPE_OFDM; } } if (sta->ht_cap.ht_supported) { - for (i = 0; i < nss; i++) - ra->ht_mcs[i] = sta->ht_cap.mcs.rx_mask[i]; + const u8 *mcs_mask = mask->control[band].ht_mcs; - ra->supp_ht_mcs = *(__le32 *)ra->ht_mcs; ra->supp_mode |= MODE_HT; - mcs = hweight32(le32_to_cpu(ra->supp_ht_mcs)) - 1; ra->af = sta->ht_cap.ampdu_factor; ra->ht_gf = !!(sta->ht_cap.cap & IEEE80211_HT_CAP_GRN_FLD); @@ -2144,13 +2250,16 @@ mt7915_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7915_dev *dev, cap |= STA_CAP_RX_STBC; if (sta->ht_cap.cap & IEEE80211_HT_CAP_LDPC_CODING) cap |= STA_CAP_LDPC; + + mt7915_mcu_set_sta_ht_mcs(sta, ra->ht_mcs, mcs_mask); + ra->supp_ht_mcs = *(__le32 *)ra->ht_mcs; } if (sta->vht_cap.vht_supported) { - u16 mcs_map = le16_to_cpu(sta->vht_cap.vht_mcs.rx_mcs_map); - u16 vht_mcs; - u8 af, mcs_prev; + const u16 *mcs_mask = mask->control[band].vht_mcs; + u8 af; + ra->supp_mode |= MODE_VHT; af = FIELD_GET(IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK, sta->vht_cap.cap); ra->af = max_t(u8, ra->af, af); @@ -2167,33 +2276,7 @@ mt7915_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7915_dev *dev, if (sta->vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC) cap |= STA_CAP_VHT_LDPC; - ra->supp_mode |= MODE_VHT; - for (mcs = 0, i = 0; i < nss; i++, mcs_map >>= 2) { - switch (mcs_map & 0x3) { - case IEEE80211_VHT_MCS_SUPPORT_0_9: - vht_mcs = GENMASK(9, 0); - break; - case IEEE80211_VHT_MCS_SUPPORT_0_8: - vht_mcs = GENMASK(8, 0); - break; - case IEEE80211_VHT_MCS_SUPPORT_0_7: - vht_mcs = GENMASK(7, 0); - break; - default: - vht_mcs = 0; - } - - ra->supp_vht_mcs[i] = cpu_to_le16(vht_mcs); - - mcs_prev = hweight16(vht_mcs) - 1; - if (mcs_prev > mcs) - mcs = mcs_prev; - - /* only support 2ss on 160MHz */ - if (i > 1 && (ra->bw == CMD_CBW_160MHZ || - ra->bw == CMD_CBW_8080MHZ)) - break; - } + mt7915_mcu_set_sta_vht_mcs(sta, ra->supp_vht_mcs, mcs_mask); } if (sta->he_cap.has_he) { @@ -2201,28 +2284,7 @@ mt7915_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7915_dev *dev, cap |= STA_CAP_HE; } - ra->sta_status = cpu_to_le32(cap); - - switch (BIT(fls(ra->supp_mode) - 1)) { - case MODE_VHT: - ra->phy.type = MT_PHY_TYPE_VHT; - ra->phy.mcs = mcs; - ra->phy.nss = nss; - ra->phy.stbc = !!(sta->vht_cap.cap & IEEE80211_VHT_CAP_TXSTBC); - ra->phy.ldpc = !!(sta->vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC); - ra->phy.sgi = - !!(sta->vht_cap.cap & IEEE80211_VHT_CAP_SHORT_GI_80); - break; - case MODE_HT: - ra->phy.type = MT_PHY_TYPE_HT; - ra->phy.mcs = mcs; - ra->phy.ldpc = sta->ht_cap.cap & IEEE80211_HT_CAP_LDPC_CODING; - ra->phy.stbc = !!(sta->ht_cap.cap & IEEE80211_HT_CAP_TX_STBC); - ra->phy.sgi = !!(sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_20); - break; - default: - break; - } + ra->sta_cap = cpu_to_le32(cap); } int mt7915_mcu_add_rate_ctrl(struct mt7915_dev *dev, struct ieee80211_vif *vif, @@ -2243,6 +2305,87 @@ int mt7915_mcu_add_rate_ctrl(struct mt7915_dev *dev, struct ieee80211_vif *vif, MCU_EXT_CMD(STA_REC_UPDATE), true); } +int mt7915_mcu_add_he(struct mt7915_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta) +{ + struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; + struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv; + struct sk_buff *skb; + int len; + + if (!sta->he_cap.has_he) + return 0; + + len = sizeof(struct sta_req_hdr) + sizeof(struct sta_rec_he); + + skb = mt7915_mcu_alloc_sta_req(dev, mvif, msta, len); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + mt7915_mcu_sta_he_tlv(skb, sta); + + return mt76_mcu_skb_send_msg(&dev->mt76, skb, + MCU_EXT_CMD(STA_REC_UPDATE), true); +} + +static int +mt7915_mcu_add_group(struct mt7915_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta) +{ +#define MT_STA_BSS_GROUP 1 + struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; + struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv; + struct { + __le32 action; + u8 wlan_idx_lo; + u8 status; + u8 wlan_idx_hi; + u8 rsv0[5]; + __le32 val; + u8 rsv1[8]; + } __packed req = { + .action = cpu_to_le32(MT_STA_BSS_GROUP), + .wlan_idx_lo = to_wcid_lo(msta->wcid.idx), + .wlan_idx_hi = to_wcid_hi(msta->wcid.idx), + .val = cpu_to_le32(mvif->idx % 16), + }; + + return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(SET_DRR_CTRL), &req, + sizeof(req), true); +} + +static int +mt7915_mcu_add_mu(struct mt7915_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta) +{ + struct mt7915_vif *mvif = (struct mt7915_vif *)vif->drv_priv; + struct mt7915_sta *msta = (struct mt7915_sta *)sta->drv_priv; + struct sk_buff *skb; + int ret; + + if (!sta->vht_cap.vht_supported && !sta->he_cap.has_he) + return 0; + + ret = mt7915_mcu_add_group(dev, vif, sta); + if (ret) + return ret; + + skb = mt7915_mcu_alloc_sta_req(dev, mvif, msta, + MT7915_STA_UPDATE_MAX_SIZE); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + /* wait until TxBF and MU ready to update stare vht */ + + /* starec muru */ + mt7915_mcu_sta_muru_tlv(skb, sta); + /* starec vht */ + mt7915_mcu_sta_vht_tlv(skb, sta); + + return mt76_mcu_skb_send_msg(&dev->mt76, skb, + MCU_EXT_CMD(STA_REC_UPDATE), true); +} + int mt7915_mcu_add_sta_adv(struct mt7915_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta, bool enable) { @@ -2253,17 +2396,14 @@ int mt7915_mcu_add_sta_adv(struct mt7915_dev *dev, struct ieee80211_vif *vif, /* must keep the order */ ret = mt7915_mcu_add_txbf(dev, vif, sta, enable); - if (ret) + if (ret || !enable) return ret; ret = mt7915_mcu_add_mu(dev, vif, sta); if (ret) return ret; - if (enable) - return mt7915_mcu_add_rate_ctrl(dev, vif, sta); - - return 0; + return mt7915_mcu_add_rate_ctrl(dev, vif, sta); } int mt7915_mcu_add_sta(struct mt7915_dev *dev, struct ieee80211_vif *vif, @@ -2432,7 +2572,7 @@ mt7915_mcu_beacon_cont(struct mt7915_dev *dev, struct sk_buff *rskb, cont->csa_ofs = cpu_to_le16(offs->cntdwn_counter_offs[0] - 4); buf = (u8 *)tlv + sizeof(*cont); - mt7915_mac_write_txwi(dev, (__le32 *)buf, skb, wcid, NULL, + mt7915_mac_write_txwi(dev, (__le32 *)buf, skb, wcid, 0, NULL, true); memcpy(buf + MT_TXD_SIZE, skb->data, skb->len); } @@ -3307,7 +3447,8 @@ int mt7915_mcu_set_eeprom(struct mt7915_dev *dev) int mt7915_mcu_get_eeprom(struct mt7915_dev *dev, u32 offset) { struct mt7915_mcu_eeprom_info req = { - .addr = cpu_to_le32(round_down(offset, 16)), + .addr = cpu_to_le32(round_down(offset, + MT7915_EEPROM_BLOCK_SIZE)), }; struct mt7915_mcu_eeprom_info *res; struct sk_buff *skb; @@ -3321,7 +3462,7 @@ int mt7915_mcu_get_eeprom(struct mt7915_dev *dev, u32 offset) res = (struct mt7915_mcu_eeprom_info *)skb->data; buf = dev->mt76.eeprom.data + le32_to_cpu(res->addr); - memcpy(buf, res->data, 16); + memcpy(buf, res->data, MT7915_EEPROM_BLOCK_SIZE); dev_kfree_skb(skb); return 0; @@ -3440,8 +3581,9 @@ int mt7915_mcu_apply_tx_dpd(struct mt7915_phy *phy) { struct mt7915_dev *dev = phy->dev; struct cfg80211_chan_def *chandef = &phy->mt76->chandef; - u16 total = 2, idx, center_freq = chandef->center_freq1; + u16 total = 2, center_freq = chandef->center_freq1; u8 *cal = dev->cal, *eep = dev->mt76.eeprom.data; + int idx; if (!(eep[MT_EE_DO_PRE_CAL] & MT_EE_WIFI_CAL_DPD)) return 0; @@ -3469,22 +3611,128 @@ int mt7915_mcu_apply_tx_dpd(struct mt7915_phy *phy) return 0; } -int mt7915_mcu_get_temperature(struct mt7915_dev *dev, int index) +int mt7915_mcu_get_chan_mib_info(struct mt7915_phy *phy, bool chan_switch) { + /* strict order */ + static const enum mt7915_chan_mib_offs offs[] = { + MIB_BUSY_TIME, MIB_TX_TIME, MIB_RX_TIME, MIB_OBSS_AIRTIME + }; + struct mt76_channel_state *state = phy->mt76->chan_state; + struct mt76_channel_state *state_ts = &phy->state_ts; + struct mt7915_dev *dev = phy->dev; + struct mt7915_mcu_mib *res, req[4]; + struct sk_buff *skb; + int i, ret; + + for (i = 0; i < 4; i++) { + req[i].band = cpu_to_le32(phy != &dev->phy); + req[i].offs = cpu_to_le32(offs[i]); + } + + ret = mt76_mcu_send_and_get_msg(&dev->mt76, MCU_EXT_CMD(GET_MIB_INFO), + req, sizeof(req), true, &skb); + if (ret) + return ret; + + res = (struct mt7915_mcu_mib *)(skb->data + 20); + + if (chan_switch) + goto out; + +#define __res_u64(s) le64_to_cpu(res[s].data) + state->cc_busy += __res_u64(0) - state_ts->cc_busy; + state->cc_tx += __res_u64(1) - state_ts->cc_tx; + state->cc_bss_rx += __res_u64(2) - state_ts->cc_bss_rx; + state->cc_rx += __res_u64(2) + __res_u64(3) - state_ts->cc_rx; + +out: + state_ts->cc_busy = __res_u64(0); + state_ts->cc_tx = __res_u64(1); + state_ts->cc_bss_rx = __res_u64(2); + state_ts->cc_rx = __res_u64(2) + __res_u64(3); +#undef __res_u64 + + dev_kfree_skb(skb); + + return 0; +} + +int mt7915_mcu_get_temperature(struct mt7915_phy *phy) +{ + struct mt7915_dev *dev = phy->dev; struct { u8 ctrl_id; u8 action; - u8 band; + u8 dbdc_idx; u8 rsv[5]; } req = { .ctrl_id = THERMAL_SENSOR_TEMP_QUERY, - .action = index, + .dbdc_idx = phy != &dev->phy, }; return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(THERMAL_CTRL), &req, sizeof(req), true); } +int mt7915_mcu_set_thermal_throttling(struct mt7915_phy *phy, u8 state) +{ + struct mt7915_dev *dev = phy->dev; + struct { + struct mt7915_mcu_thermal_ctrl ctrl; + + __le32 trigger_temp; + __le32 restore_temp; + __le16 sustain_time; + u8 rsv[2]; + } __packed req = { + .ctrl = { + .band_idx = phy != &dev->phy, + }, + }; + int level; + +#define TRIGGER_TEMPERATURE 122 +#define RESTORE_TEMPERATURE 116 +#define SUSTAIN_PERIOD 10 + + if (!state) { + req.ctrl.ctrl_id = THERMAL_PROTECT_DISABLE; + goto out; + } + + /* set duty cycle and level */ + for (level = 0; level < 4; level++) { + int ret; + + req.ctrl.ctrl_id = THERMAL_PROTECT_DUTY_CONFIG; + req.ctrl.duty.duty_level = level; + req.ctrl.duty.duty_cycle = state; + state = state * 4 / 5; + + ret = mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(THERMAL_PROT), + &req, sizeof(req.ctrl), false); + if (ret) + return ret; + } + + /* currently use fixed values for throttling, and would be better + * to implement thermal zone for dynamic trip in the long run. + */ + + /* set high-temperature trigger threshold */ + req.ctrl.ctrl_id = THERMAL_PROTECT_ENABLE; + req.trigger_temp = cpu_to_le32(TRIGGER_TEMPERATURE); + req.restore_temp = cpu_to_le32(RESTORE_TEMPERATURE); + req.sustain_time = cpu_to_le16(SUSTAIN_PERIOD); + +out: + req.ctrl.type.protect_type = 1; + req.ctrl.type.trigger_type = 1; + + return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(THERMAL_PROT), + &req, sizeof(req), false); +} + int mt7915_mcu_get_tx_rate(struct mt7915_dev *dev, u32 cmd, u16 wlan_idx) { struct { @@ -3505,7 +3753,6 @@ int mt7915_mcu_get_tx_rate(struct mt7915_dev *dev, u32 cmd, u16 wlan_idx) int mt7915_mcu_set_txpower_sku(struct mt7915_phy *phy) { -#define MT7915_SKU_RATE_NUM 161 struct mt7915_dev *dev = phy->dev; struct mt76_phy *mphy = phy->mt76; struct ieee80211_hw *hw = mphy->hw; @@ -3555,6 +3802,39 @@ int mt7915_mcu_set_txpower_sku(struct mt7915_phy *phy) sizeof(req), true); } +int mt7915_mcu_get_txpower_sku(struct mt7915_phy *phy, s8 *txpower, int len) +{ +#define RATE_POWER_INFO 2 + struct mt7915_dev *dev = phy->dev; + struct { + u8 format_id; + u8 category; + u8 band; + u8 _rsv; + } __packed req = { + .format_id = 7, + .category = RATE_POWER_INFO, + .band = phy != &dev->phy, + }; + s8 res[MT7915_SKU_RATE_NUM][2]; + struct sk_buff *skb; + int ret, i; + + ret = mt76_mcu_send_and_get_msg(&dev->mt76, + MCU_EXT_CMD(TX_POWER_FEATURE_CTRL), + &req, sizeof(req), true, &skb); + if (ret) + return ret; + + memcpy(res, skb->data + 4, sizeof(res)); + for (i = 0; i < len; i++) + txpower[i] = res[i][req.band]; + + dev_kfree_skb(skb); + + return 0; +} + int mt7915_mcu_set_test_param(struct mt7915_dev *dev, u8 param, bool test_mode, u8 en) { @@ -3613,57 +3893,50 @@ int mt7915_mcu_set_ser(struct mt7915_dev *dev, u8 action, u8 set, u8 band) &req, sizeof(req), false); } -int mt7915_mcu_set_txbf_module(struct mt7915_dev *dev) +int mt7915_mcu_set_txbf(struct mt7915_dev *dev, u8 action) { -#define MT_BF_MODULE_UPDATE 25 struct { u8 action; - u8 bf_num; - u8 bf_bitmap; - u8 bf_sel[8]; - u8 rsv[8]; + union { + struct { + u8 snd_mode; + u8 sta_num; + u8 rsv; + u8 wlan_idx[4]; + __le32 snd_period; /* ms */ + } __packed snd; + struct { + bool ebf; + bool ibf; + u8 rsv; + } __packed type; + struct { + u8 bf_num; + u8 bf_bitmap; + u8 bf_sel[8]; + u8 rsv[5]; + } __packed mod; + }; } __packed req = { - .action = MT_BF_MODULE_UPDATE, - .bf_num = 2, - .bf_bitmap = GENMASK(1, 0), + .action = action, }; - return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(TXBF_ACTION), &req, - sizeof(req), true); -} - -int mt7915_mcu_set_txbf_type(struct mt7915_dev *dev) -{ -#define MT_BF_TYPE_UPDATE 20 - struct { - u8 action; - bool ebf; - bool ibf; - u8 rsv; - } __packed req = { - .action = MT_BF_TYPE_UPDATE, - .ebf = true, - .ibf = dev->ibf, - }; - - return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(TXBF_ACTION), &req, - sizeof(req), true); -} - -int mt7915_mcu_set_txbf_sounding(struct mt7915_dev *dev) -{ -#define MT_BF_PROCESSING 4 - struct { - u8 action; - u8 snd_mode; - u8 sta_num; - u8 rsv; - u8 wlan_idx[4]; - __le32 snd_period; /* ms */ - } __packed req = { - .action = true, - .snd_mode = MT_BF_PROCESSING, - }; +#define MT_BF_PROCESSING 4 + switch (action) { + case MT_BF_SOUNDING_ON: + req.snd.snd_mode = MT_BF_PROCESSING; + break; + case MT_BF_TYPE_UPDATE: + req.type.ebf = true; + req.type.ibf = dev->ibf; + break; + case MT_BF_MODULE_UPDATE: + req.mod.bf_num = 2; + req.mod.bf_bitmap = GENMASK(1, 0); + break; + default: + return -EINVAL; + } return mt76_mcu_send_msg(&dev->mt76, MCU_EXT_CMD(TXBF_ACTION), &req, sizeof(req), true); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h index 42582a66e42d..edd3ba3a0c2d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h @@ -68,6 +68,29 @@ struct mt7915_mcu_rxd { u8 s2d_index; }; +struct mt7915_mcu_thermal_ctrl { + u8 ctrl_id; + u8 band_idx; + union { + struct { + u8 protect_type; /* 1: duty admit, 2: radio off */ + u8 trigger_type; /* 0: low, 1: high */ + } __packed type; + struct { + u8 duty_level; /* level 0~3 */ + u8 duty_cycle; + } __packed duty; + }; +} __packed; + +struct mt7915_mcu_thermal_notify { + struct mt7915_mcu_rxd rxd; + + struct mt7915_mcu_thermal_ctrl ctrl; + __le32 temperature; + u8 rsv[8]; +} __packed; + struct mt7915_mcu_csa_notify { struct mt7915_mcu_rxd rxd; @@ -193,6 +216,19 @@ struct mt7915_mcu_phy_rx_info { #define MT_RA_RATE_DCM_EN BIT(4) #define MT_RA_RATE_BW GENMASK(14, 13) +struct mt7915_mcu_mib { + __le32 band; + __le32 offs; + __le64 data; +} __packed; + +enum mt7915_chan_mib_offs { + MIB_BUSY_TIME = 14, + MIB_TX_TIME = 81, + MIB_RX_TIME, + MIB_OBSS_AIRTIME = 86 +}; + struct edca { u8 queue; u8 set; @@ -262,6 +298,7 @@ enum { MCU_EXT_CMD_FW_LOG_2_HOST = 0x13, MCU_EXT_CMD_TXBF_ACTION = 0x1e, MCU_EXT_CMD_EFUSE_BUFFER_MODE = 0x21, + MCU_EXT_CMD_THERMAL_PROT = 0x23, MCU_EXT_CMD_STA_REC_UPDATE = 0x25, MCU_EXT_CMD_BSS_INFO_UPDATE = 0x26, MCU_EXT_CMD_EDCA_UPDATE = 0x27, @@ -277,6 +314,7 @@ enum { MCU_EXT_CMD_MUAR_UPDATE = 0x48, MCU_EXT_CMD_SET_RX_PATH = 0x4e, MCU_EXT_CMD_TX_POWER_FEATURE_CTRL = 0x58, + MCU_EXT_CMD_GET_MIB_INFO = 0x5a, MCU_EXT_CMD_MWDS_SUPPORT = 0x80, MCU_EXT_CMD_SET_SER_TRIGGER = 0x81, MCU_EXT_CMD_SCS_CTRL = 0x82, @@ -919,7 +957,7 @@ struct sta_rec_ra { u8 op_vht_rx_nss; u8 op_vht_rx_nss_type; - __le32 sta_status; + __le32 sta_cap; struct ra_phy phy; } __packed; @@ -1034,18 +1072,17 @@ enum { STA_REC_MAX_NUM }; -enum mt7915_cipher_type { - MT_CIPHER_NONE, - MT_CIPHER_WEP40, - MT_CIPHER_WEP104, - MT_CIPHER_WEP128, - MT_CIPHER_TKIP, - MT_CIPHER_AES_CCMP, - MT_CIPHER_CCMP_256, - MT_CIPHER_GCMP, - MT_CIPHER_GCMP_256, - MT_CIPHER_WAPI, - MT_CIPHER_BIP_CMAC_128, +enum mcu_cipher_type { + MCU_CIPHER_WEP40 = 1, + MCU_CIPHER_WEP104, + MCU_CIPHER_WEP128, + MCU_CIPHER_TKIP, + MCU_CIPHER_AES_CCMP, + MCU_CIPHER_CCMP_256, + MCU_CIPHER_GCMP, + MCU_CIPHER_GCMP_256, + MCU_CIPHER_WAPI, + MCU_CIPHER_BIP_CMAC_128, }; enum { @@ -1066,11 +1103,28 @@ enum { THERMAL_SENSOR_TASK_CTRL, }; +enum { + THERMAL_PROTECT_PARAMETER_CTRL, + THERMAL_PROTECT_BASIC_INFO, + THERMAL_PROTECT_ENABLE, + THERMAL_PROTECT_DISABLE, + THERMAL_PROTECT_DUTY_CONFIG, + THERMAL_PROTECT_MECH_INFO, + THERMAL_PROTECT_DUTY_INFO, + THERMAL_PROTECT_STATE_ACT, +}; + enum { MT_EBF = BIT(0), /* explicit beamforming */ MT_IBF = BIT(1) /* implicit beamforming */ }; +enum { + MT_BF_SOUNDING_ON = 1, + MT_BF_TYPE_UPDATE = 20, + MT_BF_MODULE_UPDATE = 25 +}; + #define MT7915_WTBL_UPDATE_MAX_SIZE (sizeof(struct wtbl_req_hdr) + \ sizeof(struct wtbl_generic) + \ sizeof(struct wtbl_rx) + \ diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h index 4ea8972d4e2f..3f613fae6218 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mt7915.h @@ -9,7 +9,7 @@ #include "../mt76.h" #include "regs.h" -#define MT7915_MAX_INTERFACES 32 +#define MT7915_MAX_INTERFACES 19 #define MT7915_MAX_WMM_SETS 4 #define MT7915_WTBL_SIZE 288 #define MT7915_WTBL_RESERVED (MT7915_WTBL_SIZE - 1) @@ -31,6 +31,7 @@ #define MT7915_ROM_PATCH "mediatek/mt7915_rom_patch.bin" #define MT7915_EEPROM_SIZE 3584 +#define MT7915_EEPROM_BLOCK_SIZE 16 #define MT7915_TOKEN_SIZE 8192 #define MT7915_CFEND_RATE_DEFAULT 0x49 /* OFDM 24M */ @@ -38,6 +39,10 @@ #define MT7915_5G_RATE_DEFAULT 0x4b /* OFDM 6M */ #define MT7915_2G_RATE_DEFAULT 0x0 /* CCK 1M */ +#define MT7915_THERMAL_THROTTLE_MAX 100 + +#define MT7915_SKU_RATE_NUM 161 + struct mt7915_vif; struct mt7915_sta; struct mt7915_dfs_pulse; @@ -100,6 +105,7 @@ struct mt7915_vif { struct mt7915_phy *phy; struct ieee80211_tx_queue_params queue_params[IEEE80211_NUM_ACS]; + struct cfg80211_bitrate_mask bitrate_mask; }; struct mib_stats { @@ -126,6 +132,9 @@ struct mt7915_phy { struct ieee80211_vif *monitor_vif; + struct thermal_cooling_device *cdev; + u8 throttle_state; + u32 rxfilter; u64 omac_mask; @@ -141,6 +150,7 @@ struct mt7915_phy { u32 ampdu_ref; struct mib_stats mib; + struct mt76_channel_state state_ts; struct list_head stats_list; u8 sta_work_count; @@ -169,6 +179,7 @@ struct mt7915_dev { struct mt7915_hif *hif2; const struct mt76_bus_ops *bus_ops; + struct tasklet_struct irq_tasklet; struct mt7915_phy phy; u16 chainmask; @@ -322,6 +333,8 @@ int mt7915_mcu_add_obss_spr(struct mt7915_dev *dev, struct ieee80211_vif *vif, bool enable); int mt7915_mcu_add_rate_ctrl(struct mt7915_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta); +int mt7915_mcu_add_he(struct mt7915_dev *dev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta); int mt7915_mcu_add_smps(struct mt7915_dev *dev, struct ieee80211_vif *vif, struct ieee80211_sta *sta); int mt7915_set_channel(struct mt7915_phy *phy); @@ -342,9 +355,8 @@ int mt7915_mcu_set_rts_thresh(struct mt7915_phy *phy, u32 val); int mt7915_mcu_set_pm(struct mt7915_dev *dev, int band, int enter); int mt7915_mcu_set_sku_en(struct mt7915_phy *phy, bool enable); int mt7915_mcu_set_txpower_sku(struct mt7915_phy *phy); -int mt7915_mcu_set_txbf_type(struct mt7915_dev *dev); -int mt7915_mcu_set_txbf_module(struct mt7915_dev *dev); -int mt7915_mcu_set_txbf_sounding(struct mt7915_dev *dev); +int mt7915_mcu_get_txpower_sku(struct mt7915_phy *phy, s8 *txpower, int len); +int mt7915_mcu_set_txbf(struct mt7915_dev *dev, u8 action); int mt7915_mcu_set_fcc5_lpn(struct mt7915_dev *dev, int val); int mt7915_mcu_set_pulse_th(struct mt7915_dev *dev, const struct mt7915_dfs_pulse *pulse); @@ -352,7 +364,9 @@ int mt7915_mcu_set_radar_th(struct mt7915_dev *dev, int index, const struct mt7915_dfs_pattern *pattern); int mt7915_mcu_apply_group_cal(struct mt7915_dev *dev); int mt7915_mcu_apply_tx_dpd(struct mt7915_phy *phy); -int mt7915_mcu_get_temperature(struct mt7915_dev *dev, int index); +int mt7915_mcu_get_chan_mib_info(struct mt7915_phy *phy, bool chan_switch); +int mt7915_mcu_get_temperature(struct mt7915_phy *phy); +int mt7915_mcu_set_thermal_throttling(struct mt7915_phy *phy, u8 state); int mt7915_mcu_get_tx_rate(struct mt7915_dev *dev, u32 cmd, u16 wlan_idx); int mt7915_mcu_get_rx_rate(struct mt7915_phy *phy, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct rate_info *rate); @@ -374,9 +388,11 @@ void mt7915_dual_hif_set_irq_mask(struct mt7915_dev *dev, bool write_reg, static inline void mt7915_irq_enable(struct mt7915_dev *dev, u32 mask) { if (dev->hif2) - mt7915_dual_hif_set_irq_mask(dev, true, 0, mask); + mt7915_dual_hif_set_irq_mask(dev, false, 0, mask); else - mt76_set_irq_mask(&dev->mt76, MT_INT_MASK_CSR, 0, mask); + mt76_set_irq_mask(&dev->mt76, 0, 0, mask); + + tasklet_schedule(&dev->irq_tasklet); } static inline void mt7915_irq_disable(struct mt7915_dev *dev, u32 mask) @@ -392,12 +408,9 @@ void mt7915_mac_reset_counters(struct mt7915_phy *phy); void mt7915_mac_cca_stats_reset(struct mt7915_phy *phy); void mt7915_mac_enable_nf(struct mt7915_dev *dev, bool ext_phy); void mt7915_mac_write_txwi(struct mt7915_dev *dev, __le32 *txwi, - struct sk_buff *skb, struct mt76_wcid *wcid, + struct sk_buff *skb, struct mt76_wcid *wcid, int pid, struct ieee80211_key_conf *key, bool beacon); void mt7915_mac_set_timing(struct mt7915_phy *phy); -int mt7915_mac_fill_rx(struct mt7915_dev *dev, struct sk_buff *skb); -void mt7915_mac_fill_rx_vector(struct mt7915_dev *dev, struct sk_buff *skb); -void mt7915_mac_tx_free(struct mt7915_dev *dev, struct sk_buff *skb); int mt7915_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void mt7915_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif, @@ -417,13 +430,11 @@ void mt7915_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q, struct sk_buff *skb); void mt7915_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps); void mt7915_stats_work(struct work_struct *work); -void mt7915_txp_skb_unmap(struct mt76_dev *dev, - struct mt76_txwi_cache *txwi); int mt76_dfs_start_rdd(struct mt7915_dev *dev, bool force); int mt7915_dfs_init_radar_detector(struct mt7915_phy *phy); void mt7915_set_stream_he_caps(struct mt7915_phy *phy); void mt7915_set_stream_vht_txbf_caps(struct mt7915_phy *phy); -void mt7915_update_channel(struct mt76_dev *mdev); +void mt7915_update_channel(struct mt76_phy *mphy); int mt7915_init_debugfs(struct mt7915_dev *dev); #ifdef CONFIG_MAC80211_DEBUGFS void mt7915_sta_add_debugfs(struct ieee80211_hw *hw, struct ieee80211_vif *vif, diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/pci.c b/drivers/net/wireless/mediatek/mt76/mt7915/pci.c index 643f171884cf..340b364da5f0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/pci.c @@ -94,11 +94,15 @@ mt7915_rx_poll_complete(struct mt76_dev *mdev, enum mt76_rxq_id q) } /* TODO: support 2/4/6/8 MSI-X vectors */ -static irqreturn_t mt7915_irq_handler(int irq, void *dev_instance) +static void mt7915_irq_tasklet(struct tasklet_struct *t) { - struct mt7915_dev *dev = dev_instance; + struct mt7915_dev *dev = from_tasklet(dev, t, irq_tasklet); u32 intr, intr1, mask; + mt76_wr(dev, MT_INT_MASK_CSR, 0); + if (dev->hif2) + mt76_wr(dev, MT_INT1_MASK_CSR, 0); + intr = mt76_rr(dev, MT_INT_SOURCE_CSR); intr &= dev->mt76.mmio.irqmask; mt76_wr(dev, MT_INT_SOURCE_CSR, intr); @@ -111,9 +115,6 @@ static irqreturn_t mt7915_irq_handler(int irq, void *dev_instance) intr |= intr1; } - if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state)) - return IRQ_NONE; - trace_dev_irq(&dev->mt76, intr, dev->mt76.mmio.irqmask); mask = intr & MT_INT_RX_DONE_ALL; @@ -150,6 +151,20 @@ static irqreturn_t mt7915_irq_handler(int irq, void *dev_instance) wake_up(&dev->reset_wait); } } +} + +static irqreturn_t mt7915_irq_handler(int irq, void *dev_instance) +{ + struct mt7915_dev *dev = dev_instance; + + mt76_wr(dev, MT_INT_MASK_CSR, 0); + if (dev->hif2) + mt76_wr(dev, MT_INT1_MASK_CSR, 0); + + if (!test_bit(MT76_STATE_INITIALIZED, &dev->mphy.state)) + return IRQ_NONE; + + tasklet_schedule(&dev->irq_tasklet); return IRQ_HANDLED; } @@ -240,6 +255,8 @@ static int mt7915_pci_probe(struct pci_dev *pdev, if (ret) return ret; + mt76_pci_disable_aspm(pdev); + if (id->device == 0x7916) return mt7915_pci_hif2_probe(pdev); @@ -250,10 +267,18 @@ static int mt7915_pci_probe(struct pci_dev *pdev, dev = container_of(mdev, struct mt7915_dev, mt76); + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); + if (ret < 0) + goto free; + ret = mt7915_mmio_init(mdev, pcim_iomap_table(pdev)[0], pdev->irq); if (ret) goto error; + tasklet_setup(&dev->irq_tasklet, mt7915_irq_tasklet); + + mt76_wr(dev, MT_INT_MASK_CSR, 0); + /* master switch of PCIe tnterrupt enable */ mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff); @@ -266,10 +291,14 @@ static int mt7915_pci_probe(struct pci_dev *pdev, ret = mt7915_register_device(dev); if (ret) - goto error; + goto free_irq; return 0; +free_irq: + devm_free_irq(mdev->dev, pdev->irq, dev); error: + pci_free_irq_vectors(pdev); +free: mt76_free_device(&dev->mt76); return ret; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/regs.h b/drivers/net/wireless/mediatek/mt76/mt7915/regs.h index efe0f2904c66..a213b5cb82f8 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/regs.h @@ -82,11 +82,6 @@ #define MT_TMAC_CTCR0_INS_DDLMT_EN BIT(17) #define MT_TMAC_CTCR0_INS_DDLMT_VHT_SMPDU_EN BIT(18) -#define MT_TMAC_FP0R0(_band) MT_WF_TMAC(_band, 0x020) -#define MT_TMAC_FP0R15(_band) MT_WF_TMAC(_band, 0x080) -#define MT_TMAC_FP0R18(_band) MT_WF_TMAC(_band, 0x270) -#define MT_TMAC_FP_MASK GENMASK(7, 0) - #define MT_TMAC_TFCR0(_band) MT_WF_TMAC(_band, 0x1e0) #define MT_WF_DMA_BASE(_band) ((_band) ? 0xa1e00 : 0x21e00) @@ -104,6 +99,11 @@ #define MT_ETBF_TX_FB_CPL GENMASK(31, 16) #define MT_ETBF_TX_FB_TRI GENMASK(15, 0) +#define MT_ETBF_RX_FB_CONT(_band) MT_WF_ETBF(_band, 0x068) +#define MT_ETBF_RX_FB_BW GENMASK(7, 6) +#define MT_ETBF_RX_FB_NC GENMASK(5, 3) +#define MT_ETBF_RX_FB_NR GENMASK(2, 0) + #define MT_ETBF_TX_APP_CNT(_band) MT_WF_ETBF(_band, 0x0f0) #define MT_ETBF_TX_IBF_CNT GENMASK(31, 16) #define MT_ETBF_TX_EBF_CNT GENMASK(15, 0) @@ -124,6 +124,8 @@ #define MT_LPON_TCR(_band, n) MT_WF_LPON(_band, 0x0a8 + (n) * 4) #define MT_LPON_TCR_SW_MODE GENMASK(1, 0) #define MT_LPON_TCR_SW_WRITE BIT(0) +#define MT_LPON_TCR_SW_ADJUST BIT(1) +#define MT_LPON_TCR_SW_READ GENMASK(1, 0) /* MIB: band 0(0x24800), band 1(0xa4800) */ #define MT_WF_MIB_BASE(_band) ((_band) ? 0xa4800 : 0x24800) @@ -132,20 +134,9 @@ #define MT_MIB_SDR3(_band) MT_WF_MIB(_band, 0x014) #define MT_MIB_SDR3_FCS_ERR_MASK GENMASK(15, 0) -#define MT_MIB_SDR9(_band) MT_WF_MIB(_band, 0x02c) -#define MT_MIB_SDR9_BUSY_MASK GENMASK(23, 0) - -#define MT_MIB_SDR16(_band) MT_WF_MIB(_band, 0x048) -#define MT_MIB_SDR16_BUSY_MASK GENMASK(23, 0) - #define MT_MIB_SDR34(_band) MT_WF_MIB(_band, 0x090) #define MT_MIB_MU_BF_TX_CNT GENMASK(15, 0) -#define MT_MIB_SDR36(_band) MT_WF_MIB(_band, 0x098) -#define MT_MIB_SDR36_TXTIME_MASK GENMASK(23, 0) -#define MT_MIB_SDR37(_band) MT_WF_MIB(_band, 0x09c) -#define MT_MIB_SDR37_RXTIME_MASK GENMASK(23, 0) - #define MT_MIB_DR8(_band) MT_WF_MIB(_band, 0x0c0) #define MT_MIB_DR9(_band) MT_WF_MIB(_band, 0x0c4) #define MT_MIB_DR11(_band) MT_WF_MIB(_band, 0x0cc) @@ -158,9 +149,6 @@ #define MT_MIB_BA_MISS_COUNT_MASK GENMASK(15, 0) #define MT_MIB_ACK_FAIL_COUNT_MASK GENMASK(31, 16) -#define MT_MIB_MB_SDR2(_band, n) MT_WF_MIB(_band, 0x108 + ((n) << 4)) -#define MT_MIB_FRAME_RETRIES_COUNT_MASK GENMASK(15, 0) - #define MT_TX_AGG_CNT(_band, n) MT_WF_MIB(_band, 0x0a8 + ((n) << 2)) #define MT_TX_AGG_CNT2(_band, n) MT_WF_MIB(_band, 0x164 + ((n) << 2)) #define MT_MIB_ARNG(_band, n) MT_WF_MIB(_band, 0x4b8 + ((n) << 2)) @@ -258,14 +246,10 @@ #define MT_WF_RFCR1_DROP_CFEND BIT(7) #define MT_WF_RFCR1_DROP_CFACK BIT(8) -#define MT_WF_RMAC_MIB_TIME0(_band) MT_WF_RMAC(_band, 0x03c4) +#define MT_WF_RMAC_MIB_AIRTIME0(_band) MT_WF_RMAC(_band, 0x0380) #define MT_WF_RMAC_MIB_RXTIME_CLR BIT(31) #define MT_WF_RMAC_MIB_RXTIME_EN BIT(30) -#define MT_WF_RMAC_MIB_AIRTIME14(_band) MT_WF_RMAC(_band, 0x03b8) -#define MT_MIB_OBSSTIME_MASK GENMASK(23, 0) -#define MT_WF_RMAC_MIB_AIRTIME0(_band) MT_WF_RMAC(_band, 0x0380) - /* WFDMA0 */ #define MT_WFDMA0_BASE 0xd4000 #define MT_WFDMA0(ofs) (MT_WFDMA0_BASE + (ofs)) diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c b/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c index f9d81e36ef09..b220b334906b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/testmode.c @@ -464,10 +464,17 @@ mt7915_tm_set_tx_frames(struct mt7915_phy *phy, bool en) static void mt7915_tm_set_rx_frames(struct mt7915_phy *phy, bool en) { - if (en) + mt7915_tm_set_trx(phy, TM_MAC_RX_RXV, false); + + if (en) { + struct mt7915_dev *dev = phy->dev; + mt7915_tm_update_channel(phy); - mt7915_tm_set_trx(phy, TM_MAC_RX_RXV, en); + /* read-clear */ + mt76_rr(dev, MT_MIB_SDR3(phy != &dev->phy)); + mt7915_tm_set_trx(phy, TM_MAC_RX_RXV, en); + } } static int @@ -690,7 +697,11 @@ static int mt7915_tm_dump_stats(struct mt76_phy *mphy, struct sk_buff *msg) { struct mt7915_phy *phy = mphy->priv; + struct mt7915_dev *dev = phy->dev; + bool ext_phy = phy != &dev->phy; + enum mt76_rxq_id q; void *rx, *rssi; + u16 fcs_err; int i; rx = nla_nest_start(msg, MT76_TM_STATS_ATTR_LAST_RX); @@ -735,6 +746,12 @@ mt7915_tm_dump_stats(struct mt76_phy *mphy, struct sk_buff *msg) nla_nest_end(msg, rx); + fcs_err = mt76_get_field(dev, MT_MIB_SDR3(ext_phy), + MT_MIB_SDR3_FCS_ERR_MASK); + q = ext_phy ? MT_RXQ_EXT : MT_RXQ_MAIN; + mphy->test.rx_stats.packets[q] += fcs_err; + mphy->test.rx_stats.fcs_error[q] += fcs_err; + return 0; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/testmode.h b/drivers/net/wireless/mediatek/mt76/mt7915/testmode.h index 8f8533ef9859..397a6b5532bc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/testmode.h +++ b/drivers/net/wireless/mediatek/mt76/mt7915/testmode.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: ISC +/* SPDX-License-Identifier: ISC */ /* Copyright (C) 2020 MediaTek Inc. */ #ifndef __MT7915_TESTMODE_H diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/Makefile b/drivers/net/wireless/mediatek/mt76/mt7921/Makefile index e531666f9fb4..0ebb59966a08 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/Makefile +++ b/drivers/net/wireless/mediatek/mt76/mt7921/Makefile @@ -1,4 +1,4 @@ -#SPDX-License-Identifier: ISC +# SPDX-License-Identifier: ISC obj-$(CONFIG_MT7921E) += mt7921e.o diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c index 6ee423dd4027..77468bdae460 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/debugfs.c @@ -184,7 +184,10 @@ mt7921_txpwr(struct seq_file *s, void *data) struct mt7921_txpwr txpwr; int ret; + mt7921_mutex_acquire(dev); ret = mt7921_get_txpwr_info(dev, &txpwr); + mt7921_mutex_release(dev); + if (ret) return ret; @@ -247,6 +250,9 @@ mt7921_pm_set(void *data, u64 val) ieee80211_iterate_active_interfaces(mphy->hw, IEEE80211_IFACE_ITER_RESUME_ALL, mt7921_pm_interface_iter, mphy->priv); + + mt76_connac_mcu_set_deep_sleep(&dev->mt76, pm->ds_enable); + mt7921_mutex_release(dev); return 0; @@ -264,6 +270,36 @@ mt7921_pm_get(void *data, u64 *val) DEFINE_DEBUGFS_ATTRIBUTE(fops_pm, mt7921_pm_get, mt7921_pm_set, "%lld\n"); +static int +mt7921_deep_sleep_set(void *data, u64 val) +{ + struct mt7921_dev *dev = data; + struct mt76_connac_pm *pm = &dev->pm; + bool enable = !!val; + + mt7921_mutex_acquire(dev); + if (pm->ds_enable != enable) { + mt76_connac_mcu_set_deep_sleep(&dev->mt76, enable); + pm->ds_enable = enable; + } + mt7921_mutex_release(dev); + + return 0; +} + +static int +mt7921_deep_sleep_get(void *data, u64 *val) +{ + struct mt7921_dev *dev = data; + + *val = dev->pm.ds_enable; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(fops_ds, mt7921_deep_sleep_get, + mt7921_deep_sleep_set, "%lld\n"); + static int mt7921_pm_stats(struct seq_file *s, void *data) { @@ -355,6 +391,7 @@ int mt7921_init_debugfs(struct mt7921_dev *dev) debugfs_create_file("chip_reset", 0600, dir, dev, &fops_reset); debugfs_create_devm_seqfile(dev->mt76.dev, "runtime_pm_stats", dir, mt7921_pm_stats); + debugfs_create_file("deep-sleep", 0600, dir, dev, &fops_ds); return 0; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c index 71e664ee7652..7d7d43a5422f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/dma.c @@ -74,7 +74,7 @@ static int mt7921_poll_tx(struct napi_struct *napi, int budget) mt7921_tx_cleanup(dev); if (napi_complete(napi)) mt7921_irq_enable(dev, MT_INT_TX_DONE_ALL); - mt76_connac_pm_unref(&dev->pm); + mt76_connac_pm_unref(&dev->mphy, &dev->pm); return 0; } @@ -92,7 +92,7 @@ static int mt7921_poll_rx(struct napi_struct *napi, int budget) return 0; } done = mt76_dma_rx_poll(napi, budget); - mt76_connac_pm_unref(&dev->pm); + mt76_connac_pm_unref(&dev->mphy, &dev->pm); return done; } @@ -313,9 +313,9 @@ static int mt7921_dma_reset(struct mt7921_dev *dev, bool force) int mt7921_wfsys_reset(struct mt7921_dev *dev) { - mt76_set(dev, 0x70002600, BIT(0)); - msleep(200); - mt76_clear(dev, 0x70002600, BIT(0)); + mt76_clear(dev, MT_WFSYS_SW_RST_B, WFSYS_SW_RST_B); + msleep(50); + mt76_set(dev, MT_WFSYS_SW_RST_B, WFSYS_SW_RST_B); if (!__mt76_poll_msec(&dev->mt76, MT_WFSYS_SW_RST_B, WFSYS_SW_INIT_DONE, WFSYS_SW_INIT_DONE, 500)) @@ -380,9 +380,7 @@ int mt7921_wpdma_reinit_cond(struct mt7921_dev *dev) int mt7921_dma_init(struct mt7921_dev *dev) { - /* Increase buffer size to receive large VHT/HE MPDUs */ struct mt76_bus_ops *bus_ops; - int rx_buf_size = MT_RX_BUF_SIZE * 2; int ret; dev->bus_ops = dev->mt76.bus; @@ -402,6 +400,10 @@ int mt7921_dma_init(struct mt7921_dev *dev) if (ret) return ret; + ret = mt7921_wfsys_reset(dev); + if (ret) + return ret; + /* init tx queue */ ret = mt7921_init_tx_queues(&dev->phy, MT7921_TXQ_BAND0, MT7921_TX_RING_SIZE); @@ -426,7 +428,7 @@ int mt7921_dma_init(struct mt7921_dev *dev) ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU], MT7921_RXQ_MCU_WM, MT7921_RX_MCU_RING_SIZE, - rx_buf_size, MT_RX_EVENT_RING_BASE); + MT_RX_BUF_SIZE, MT_RX_EVENT_RING_BASE); if (ret) return ret; @@ -434,14 +436,14 @@ int mt7921_dma_init(struct mt7921_dev *dev) ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MCU_WA], MT7921_RXQ_MCU_WM, MT7921_RX_MCU_RING_SIZE, - rx_buf_size, MT_WFDMA0(0x540)); + MT_RX_BUF_SIZE, MT_WFDMA0(0x540)); if (ret) return ret; /* rx data */ ret = mt76_queue_alloc(dev, &dev->mt76.q_rx[MT_RXQ_MAIN], MT7921_RXQ_BAND0, MT7921_RX_RING_SIZE, - rx_buf_size, MT_RX_DATA_RING_BASE); + MT_RX_BUF_SIZE, MT_RX_DATA_RING_BASE); if (ret) return ret; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c index 1763ea0614ce..a9ce10b98827 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c @@ -7,34 +7,6 @@ #include "mcu.h" #include "eeprom.h" -#define CCK_RATE(_idx, _rate) { \ - .bitrate = _rate, \ - .flags = IEEE80211_RATE_SHORT_PREAMBLE, \ - .hw_value = (MT_PHY_TYPE_CCK << 8) | (_idx), \ - .hw_value_short = (MT_PHY_TYPE_CCK << 8) | (4 + (_idx)), \ -} - -#define OFDM_RATE(_idx, _rate) { \ - .bitrate = _rate, \ - .hw_value = (MT_PHY_TYPE_OFDM << 8) | (_idx), \ - .hw_value_short = (MT_PHY_TYPE_OFDM << 8) | (_idx), \ -} - -static struct ieee80211_rate mt7921_rates[] = { - CCK_RATE(0, 10), - CCK_RATE(1, 20), - CCK_RATE(2, 55), - CCK_RATE(3, 110), - OFDM_RATE(11, 60), - OFDM_RATE(15, 90), - OFDM_RATE(10, 120), - OFDM_RATE(14, 180), - OFDM_RATE(9, 240), - OFDM_RATE(13, 360), - OFDM_RATE(8, 480), - OFDM_RATE(12, 540), -}; - static const struct ieee80211_iface_limit if_limits[] = { { .max = MT7921_MAX_INTERFACES, @@ -73,11 +45,13 @@ static void mt7921_init_wiphy(struct ieee80211_hw *hw) { struct mt7921_phy *phy = mt7921_hw_phy(hw); + struct mt7921_dev *dev = phy->dev; struct wiphy *wiphy = hw->wiphy; hw->queues = 4; hw->max_rx_aggregation_subframes = 64; hw->max_tx_aggregation_subframes = 128; + hw->netdev_features = NETIF_F_RXCSUM; hw->radiotap_timestamp.units_pos = IEEE80211_RADIOTAP_TIMESTAMP_UNIT_US; @@ -88,11 +62,13 @@ mt7921_init_wiphy(struct ieee80211_hw *hw) hw->vif_data_size = sizeof(struct mt7921_vif); wiphy->iface_combinations = if_comb; + wiphy->flags &= ~WIPHY_FLAG_IBSS_RSN; + wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION); wiphy->n_iface_combinations = ARRAY_SIZE(if_comb); wiphy->max_scan_ie_len = MT76_CONNAC_SCAN_IE_LEN; wiphy->max_scan_ssids = 4; wiphy->max_sched_scan_plan_interval = - MT76_CONNAC_MAX_SCHED_SCAN_INTERVAL; + MT76_CONNAC_MAX_TIME_SCHED_SCAN_INTERVAL; wiphy->max_sched_scan_ie_len = IEEE80211_MAX_DATA_LEN; wiphy->max_sched_scan_ssids = MT76_CONNAC_MAX_SCHED_SCAN_SSID; wiphy->max_match_sets = MT76_CONNAC_MAX_SCAN_MATCH; @@ -100,46 +76,33 @@ mt7921_init_wiphy(struct ieee80211_hw *hw) wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH; wiphy->reg_notifier = mt7921_regd_notifier; - wiphy->features |= NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR; + wiphy->features |= NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR | + NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR; wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_SET_SCAN_DWELL); ieee80211_hw_set(hw, SINGLE_SCAN_ON_ALL_BANDS); ieee80211_hw_set(hw, HAS_RATE_CONTROL); ieee80211_hw_set(hw, SUPPORTS_TX_ENCAP_OFFLOAD); + ieee80211_hw_set(hw, SUPPORTS_RX_DECAP_OFFLOAD); ieee80211_hw_set(hw, WANT_MONITOR_VIF); ieee80211_hw_set(hw, SUPPORTS_PS); ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS); + if (dev->pm.enable) + ieee80211_hw_set(hw, CONNECTION_MONITOR); + hw->max_tx_fragments = 4; } static void mt7921_mac_init_band(struct mt7921_dev *dev, u8 band) { - u32 mask, set; - mt76_rmw_field(dev, MT_TMAC_CTCR0(band), MT_TMAC_CTCR0_INS_DDLMT_REFTIME, 0x3f); mt76_set(dev, MT_TMAC_CTCR0(band), MT_TMAC_CTCR0_INS_DDLMT_VHT_SMPDU_EN | MT_TMAC_CTCR0_INS_DDLMT_EN); - mask = MT_MDP_RCFR0_MCU_RX_MGMT | - MT_MDP_RCFR0_MCU_RX_CTL_NON_BAR | - MT_MDP_RCFR0_MCU_RX_CTL_BAR; - set = FIELD_PREP(MT_MDP_RCFR0_MCU_RX_MGMT, MT_MDP_TO_HIF) | - FIELD_PREP(MT_MDP_RCFR0_MCU_RX_CTL_NON_BAR, MT_MDP_TO_HIF) | - FIELD_PREP(MT_MDP_RCFR0_MCU_RX_CTL_BAR, MT_MDP_TO_HIF); - mt76_rmw(dev, MT_MDP_BNRCFR0(band), mask, set); - - mask = MT_MDP_RCFR1_MCU_RX_BYPASS | - MT_MDP_RCFR1_RX_DROPPED_UCAST | - MT_MDP_RCFR1_RX_DROPPED_MCAST; - set = FIELD_PREP(MT_MDP_RCFR1_MCU_RX_BYPASS, MT_MDP_TO_HIF) | - FIELD_PREP(MT_MDP_RCFR1_RX_DROPPED_UCAST, MT_MDP_TO_HIF) | - FIELD_PREP(MT_MDP_RCFR1_RX_DROPPED_MCAST, MT_MDP_TO_HIF); - mt76_rmw(dev, MT_MDP_BNRCFR1(band), mask, set); - mt76_set(dev, MT_WF_RMAC_MIB_TIME0(band), MT_WF_RMAC_MIB_RXTIME_EN); mt76_set(dev, MT_WF_RMAC_MIB_AIRTIME0(band), MT_WF_RMAC_MIB_RXTIME_EN); @@ -148,14 +111,15 @@ mt7921_mac_init_band(struct mt7921_dev *dev, u8 band) mt76_clear(dev, MT_DMA_DCR0(band), MT_DMA_DCR0_RXD_G5_EN); } -void mt7921_mac_init(struct mt7921_dev *dev) +int mt7921_mac_init(struct mt7921_dev *dev) { int i; mt76_rmw_field(dev, MT_MDP_DCR1, MT_MDP_DCR1_MAX_RX_LEN, 1536); - /* disable hardware de-agg */ - mt76_clear(dev, MT_MDP_DCR0, MT_MDP_DCR0_DAMSDU_EN); - mt76_clear(dev, MT_MDP_DCR0, MT_MDP_DCR0_RX_HDR_TRANS_EN); + /* enable hardware de-agg */ + mt76_set(dev, MT_MDP_DCR0, MT_MDP_DCR0_DAMSDU_EN); + /* enable hardware rx header translation */ + mt76_set(dev, MT_MDP_DCR0, MT_MDP_DCR0_RX_HDR_TRANS_EN); for (i = 0; i < MT7921_WTBL_SIZE; i++) mt7921_mac_wtbl_update(dev, i, @@ -163,7 +127,7 @@ void mt7921_mac_init(struct mt7921_dev *dev) for (i = 0; i < 2; i++) mt7921_mac_init_band(dev, i); - mt76_connac_mcu_set_rts_thresh(&dev->mt76, 0x92b, 0); + return mt76_connac_mcu_set_rts_thresh(&dev->mt76, 0x92b, 0); } static int mt7921_init_hardware(struct mt7921_dev *dev) @@ -203,9 +167,7 @@ static int mt7921_init_hardware(struct mt7921_dev *dev) dev->mt76.global_wcid.tx_info |= MT_WCID_TX_INFO_SET; rcu_assign_pointer(dev->mt76.wcid[idx], &dev->mt76.global_wcid); - mt7921_mac_init(dev); - - return 0; + return mt7921_mac_init(dev); } int mt7921_register_device(struct mt7921_dev *dev) @@ -224,7 +186,6 @@ int mt7921_register_device(struct mt7921_dev *dev) mutex_init(&dev->pm.mutex); init_waitqueue_head(&dev->pm.wait); spin_lock_init(&dev->pm.txq_lock); - set_bit(MT76_STATE_PM, &dev->mphy.state); INIT_LIST_HEAD(&dev->phy.stats_list); INIT_DELAYED_WORK(&dev->mphy.mac_work, mt7921_mac_work); INIT_DELAYED_WORK(&dev->phy.scan_work, mt7921_scan_work); @@ -239,6 +200,8 @@ int mt7921_register_device(struct mt7921_dev *dev) dev->pm.idle_timeout = MT7921_PM_TIMEOUT; dev->pm.stats.last_wake_event = jiffies; dev->pm.stats.last_doze_event = jiffies; + dev->pm.enable = true; + dev->pm.ds_enable = true; ret = mt7921_init_hardware(dev); if (ret) @@ -253,19 +216,33 @@ int mt7921_register_device(struct mt7921_dev *dev) IEEE80211_HT_CAP_MAX_AMSDU; dev->mphy.sband_5g.sband.vht_cap.cap |= IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 | - IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; + IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK | + IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE | + IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE | + (3 << IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT); + dev->mphy.hw->wiphy->available_antennas_rx = dev->mphy.chainmask; dev->mphy.hw->wiphy->available_antennas_tx = dev->mphy.chainmask; mt76_set_stream_caps(&dev->mphy, true); mt7921_set_stream_he_caps(&dev->phy); - ret = mt76_register_device(&dev->mt76, true, mt7921_rates, - ARRAY_SIZE(mt7921_rates)); + ret = mt76_register_device(&dev->mt76, true, mt76_rates, + ARRAY_SIZE(mt76_rates)); if (ret) return ret; - return mt7921_init_debugfs(dev); + ret = mt7921_init_debugfs(dev); + if (ret) + return ret; + + ret = mt76_connac_mcu_set_deep_sleep(&dev->mt76, dev->pm.ds_enable); + if (ret) + return ret; + + dev->hw_init_done = true; + + return 0; } void mt7921_unregister_device(struct mt7921_dev *dev) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c index decf2d5f0ce3..7fe2e3a50428 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.c @@ -308,21 +308,24 @@ mt7921_mac_assoc_rssi(struct mt7921_dev *dev, struct sk_buff *skb) int mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb) { + u32 csum_mask = MT_RXD0_NORMAL_IP_SUM | MT_RXD0_NORMAL_UDP_TCP_SUM; struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb; + bool hdr_trans, unicast, insert_ccmp_hdr = false; + u8 chfreq, qos_ctl = 0, remove_pad, amsdu_info; + __le32 *rxv = NULL, *rxd = (__le32 *)skb->data; struct mt76_phy *mphy = &dev->mt76.phy; struct mt7921_phy *phy = &dev->phy; struct ieee80211_supported_band *sband; struct ieee80211_hdr *hdr; - __le32 *rxd = (__le32 *)skb->data; - __le32 *rxv = NULL; - u32 mode = 0; + u32 rxd0 = le32_to_cpu(rxd[0]); u32 rxd1 = le32_to_cpu(rxd[1]); u32 rxd2 = le32_to_cpu(rxd[2]); u32 rxd3 = le32_to_cpu(rxd[3]); - bool unicast, insert_ccmp_hdr = false; - u8 remove_pad; + u32 rxd4 = le32_to_cpu(rxd[4]); + u16 seq_ctrl = 0; + __le16 fc = 0; + u32 mode = 0; int i, idx; - u8 chfreq; memset(status, 0, sizeof(*status)); @@ -332,9 +335,13 @@ int mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb) if (!test_bit(MT76_STATE_RUNNING, &mphy->state)) return -EINVAL; + if (rxd2 & MT_RXD2_NORMAL_AMSDU_ERR) + return -EINVAL; + chfreq = FIELD_GET(MT_RXD3_NORMAL_CH_FREQ, rxd3); unicast = FIELD_GET(MT_RXD3_NORMAL_ADDR_TYPE, rxd3) == MT_RXD3_NORMAL_U2M; idx = FIELD_GET(MT_RXD1_NORMAL_WLAN_IDX, rxd1); + hdr_trans = rxd2 & MT_RXD2_NORMAL_HDR_TRANS; status->wcid = mt7921_rx_get_wcid(dev, idx, unicast); if (status->wcid) { @@ -357,6 +364,9 @@ int mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb) if (!sband->channels) return -EINVAL; + if ((rxd0 & csum_mask) == csum_mask) + skb->ip_summed = CHECKSUM_UNNECESSARY; + if (rxd1 & MT_RXD1_NORMAL_FCS_ERR) status->flag |= RX_FLAG_FAILED_FCS_CRC; @@ -377,6 +387,13 @@ int mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb) rxd += 6; if (rxd1 & MT_RXD1_NORMAL_GROUP_4) { + u32 v0 = le32_to_cpu(rxd[0]); + u32 v2 = le32_to_cpu(rxd[2]); + + fc = cpu_to_le16(FIELD_GET(MT_RXD6_FRAME_CONTROL, v0)); + seq_ctrl = FIELD_GET(MT_RXD8_SEQ_CTRL, v2); + qos_ctl = FIELD_GET(MT_RXD8_QOS_CTL, v2); + rxd += 4; if ((u8 *)rxd - skb->data >= skb->len) return -EINVAL; @@ -386,14 +403,27 @@ int mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb) u8 *data = (u8 *)rxd; if (status->flag & RX_FLAG_DECRYPTED) { - status->iv[0] = data[5]; - status->iv[1] = data[4]; - status->iv[2] = data[3]; - status->iv[3] = data[2]; - status->iv[4] = data[1]; - status->iv[5] = data[0]; - - insert_ccmp_hdr = FIELD_GET(MT_RXD2_NORMAL_FRAG, rxd2); + switch (FIELD_GET(MT_RXD1_NORMAL_SEC_MODE, rxd1)) { + case MT_CIPHER_AES_CCMP: + case MT_CIPHER_CCMP_CCX: + case MT_CIPHER_CCMP_256: + insert_ccmp_hdr = + FIELD_GET(MT_RXD2_NORMAL_FRAG, rxd2); + fallthrough; + case MT_CIPHER_TKIP: + case MT_CIPHER_TKIP_NO_MIC: + case MT_CIPHER_GCMP: + case MT_CIPHER_GCMP_256: + status->iv[0] = data[5]; + status->iv[1] = data[4]; + status->iv[2] = data[3]; + status->iv[3] = data[2]; + status->iv[4] = data[1]; + status->iv[5] = data[0]; + break; + default: + break; + } } rxd += 4; if ((u8 *)rxd - skb->data >= skb->len) @@ -444,16 +474,19 @@ int mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb) status->chain_signal[1] = to_rssi(MT_PRXV_RCPI1, v1); status->chain_signal[2] = to_rssi(MT_PRXV_RCPI2, v1); status->chain_signal[3] = to_rssi(MT_PRXV_RCPI3, v1); - status->signal = status->chain_signal[0]; - - for (i = 1; i < hweight8(mphy->antenna_mask); i++) { - if (!(status->chains & BIT(i))) + status->signal = -128; + for (i = 0; i < hweight8(mphy->antenna_mask); i++) { + if (!(status->chains & BIT(i)) || + status->chain_signal[i] >= 0) continue; status->signal = max(status->signal, status->chain_signal[i]); } + if (status->signal == -128) + status->flag |= RX_FLAG_NO_SIGNAL_VAL; + stbc = FIELD_GET(MT_PRXV_STBC, v0); gi = FIELD_GET(MT_PRXV_SGI, v0); cck = false; @@ -540,10 +573,35 @@ int mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb) skb_pull(skb, (u8 *)rxd - skb->data + 2 * remove_pad); - if (insert_ccmp_hdr) { - u8 key_id = FIELD_GET(MT_RXD1_NORMAL_KEY_ID, rxd1); + amsdu_info = FIELD_GET(MT_RXD4_NORMAL_PAYLOAD_FORMAT, rxd4); + status->amsdu = !!amsdu_info; + if (status->amsdu) { + status->first_amsdu = amsdu_info == MT_RXD4_FIRST_AMSDU_FRAME; + status->last_amsdu = amsdu_info == MT_RXD4_LAST_AMSDU_FRAME; + if (!hdr_trans) { + memmove(skb->data + 2, skb->data, + ieee80211_get_hdrlen_from_skb(skb)); + skb_pull(skb, 2); + } + } - mt76_insert_ccmp_hdr(skb, key_id); + if (!hdr_trans) { + if (insert_ccmp_hdr) { + u8 key_id = FIELD_GET(MT_RXD1_NORMAL_KEY_ID, rxd1); + + mt76_insert_ccmp_hdr(skb, key_id); + } + + hdr = mt76_skb_get_hdr(skb); + fc = hdr->frame_control; + if (ieee80211_is_data_qos(fc)) { + seq_ctrl = le16_to_cpu(hdr->seq_ctrl); + qos_ctl = *ieee80211_get_qos_ctl(hdr); + } + } else { + status->flag &= ~(RX_FLAG_RADIOTAP_HE | + RX_FLAG_RADIOTAP_HE_MU); + status->flag |= RX_FLAG_8023; } mt7921_mac_assoc_rssi(dev, skb); @@ -551,14 +609,12 @@ int mt7921_mac_fill_rx(struct mt7921_dev *dev, struct sk_buff *skb) if (rxv && status->flag & RX_FLAG_RADIOTAP_HE) mt7921_mac_decode_he_radiotap(skb, status, rxv, mode); - hdr = mt76_skb_get_hdr(skb); - if (!status->wcid || !ieee80211_is_data_qos(hdr->frame_control)) + if (!status->wcid || !ieee80211_is_data_qos(fc)) return 0; - status->aggr = unicast && - !ieee80211_is_qos_nullfunc(hdr->frame_control); - status->qos_ctl = *ieee80211_get_qos_ctl(hdr); - status->seqno = IEEE80211_SEQ_TO_SN(le16_to_cpu(hdr->seq_ctrl)); + status->aggr = unicast && !ieee80211_is_qos_nullfunc(fc); + status->seqno = IEEE80211_SEQ_TO_SN(seq_ctrl); + status->qos_ctl = qos_ctl; return 0; } @@ -676,6 +732,23 @@ mt7921_mac_write_txwi_80211(struct mt7921_dev *dev, __le32 *txwi, txwi[7] |= cpu_to_le32(val); } +static void mt7921_update_txs(struct mt76_wcid *wcid, __le32 *txwi) +{ + struct mt7921_sta *msta = container_of(wcid, struct mt7921_sta, wcid); + u32 pid, frame_type = FIELD_GET(MT_TXD2_FRAME_TYPE, txwi[2]); + + if (!(frame_type & (IEEE80211_FTYPE_DATA >> 2))) + return; + + if (time_is_after_eq_jiffies(msta->next_txs_ts)) + return; + + msta->next_txs_ts = jiffies + msecs_to_jiffies(250); + pid = mt76_get_next_pkt_id(wcid); + txwi[5] |= cpu_to_le32(MT_TXD5_TX_STATUS_MCU | + FIELD_PREP(MT_TXD5_PID, pid)); +} + void mt7921_mac_write_txwi(struct mt7921_dev *dev, __le32 *txwi, struct sk_buff *skb, struct mt76_wcid *wcid, struct ieee80211_key_conf *key, bool beacon) @@ -752,6 +825,8 @@ void mt7921_mac_write_txwi(struct mt7921_dev *dev, __le32 *txwi, txwi[6] |= cpu_to_le32(val); txwi[3] |= cpu_to_le32(MT_TXD3_BA_DISABLE); } + + mt7921_update_txs(wcid, txwi); } static void @@ -1154,18 +1229,18 @@ mt7921_phy_update_channel(struct mt76_phy *mphy, int idx) state->noise = -(phy->noise >> 4); } -void mt7921_update_channel(struct mt76_dev *mdev) +void mt7921_update_channel(struct mt76_phy *mphy) { - struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); + struct mt7921_dev *dev = container_of(mphy->dev, struct mt7921_dev, mt76); - if (mt76_connac_pm_wake(&dev->mphy, &dev->pm)) + if (mt76_connac_pm_wake(mphy, &dev->pm)) return; - mt7921_phy_update_channel(&mdev->phy, 0); + mt7921_phy_update_channel(mphy, 0); /* reset obss airtime */ mt76_set(dev, MT_WF_RMAC_MIB_TIME0(0), MT_WF_RMAC_MIB_RXTIME_CLR); - mt76_connac_power_save_sched(&dev->mphy, &dev->pm); + mt76_connac_power_save_sched(mphy, &dev->pm); } void mt7921_tx_token_put(struct mt7921_dev *dev) @@ -1196,7 +1271,8 @@ mt7921_vif_connect_iter(void *priv, u8 *mac, struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv; struct mt7921_dev *dev = mvif->phy->dev; - ieee80211_disconnect(vif, true); + if (vif->type == NL80211_IFTYPE_STATION) + ieee80211_disconnect(vif, true); mt76_connac_mcu_uni_add_dev(&dev->mphy, vif, &mvif->sta.wcid, true); mt7921_mcu_set_tx(dev, vif); @@ -1212,6 +1288,7 @@ mt7921_mac_reset(struct mt7921_dev *dev) mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0); mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0x0); + set_bit(MT76_RESET, &dev->mphy.state); set_bit(MT76_MCU_RESET, &dev->mphy.state); wake_up(&dev->mt76.mcu.wait); skb_queue_purge(&dev->mt76.mcu.res_q); @@ -1227,56 +1304,64 @@ mt7921_mac_reset(struct mt7921_dev *dev) mt7921_tx_token_put(dev); idr_init(&dev->mt76.token); - err = mt7921_wpdma_reset(dev, true); - if (err) - return err; + mt7921_wpdma_reset(dev, true); mt76_for_each_q_rx(&dev->mt76, i) { napi_enable(&dev->mt76.napi[i]); napi_schedule(&dev->mt76.napi[i]); } - napi_enable(&dev->mt76.tx_napi); - napi_schedule(&dev->mt76.tx_napi); - mt76_worker_enable(&dev->mt76.tx_worker); - clear_bit(MT76_MCU_RESET, &dev->mphy.state); - clear_bit(MT76_STATE_PM, &dev->mphy.state); - mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, 0); + mt76_wr(dev, MT_WFDMA0_HOST_INT_ENA, + MT_INT_RX_DONE_ALL | MT_INT_TX_DONE_ALL | + MT_INT_MCU_CMD); mt76_wr(dev, MT_PCIE_MAC_INT_ENABLE, 0xff); err = mt7921_run_firmware(dev); if (err) - return err; + goto out; err = mt7921_mcu_set_eeprom(dev); if (err) - return err; + goto out; - mt7921_mac_init(dev); - return __mt7921_start(&dev->phy); + err = mt7921_mac_init(dev); + if (err) + goto out; + + err = __mt7921_start(&dev->phy); +out: + clear_bit(MT76_RESET, &dev->mphy.state); + + napi_enable(&dev->mt76.tx_napi); + napi_schedule(&dev->mt76.tx_napi); + mt76_worker_enable(&dev->mt76.tx_worker); + + return err; } /* system error recovery */ void mt7921_mac_reset_work(struct work_struct *work) { - struct ieee80211_hw *hw; - struct mt7921_dev *dev; + struct mt7921_dev *dev = container_of(work, struct mt7921_dev, + reset_work); + struct ieee80211_hw *hw = mt76_hw(dev); + struct mt76_connac_pm *pm = &dev->pm; int i; - dev = container_of(work, struct mt7921_dev, reset_work); - hw = mt76_hw(dev); - dev_err(dev->mt76.dev, "chip reset\n"); + dev->hw_full_reset = true; ieee80211_stop_queues(hw); cancel_delayed_work_sync(&dev->mphy.mac_work); - cancel_delayed_work_sync(&dev->pm.ps_work); - cancel_work_sync(&dev->pm.wake_work); + cancel_delayed_work_sync(&pm->ps_work); + cancel_work_sync(&pm->wake_work); mutex_lock(&dev->mt76.mutex); for (i = 0; i < 10; i++) { + __mt7921_mcu_drv_pmctrl(dev); + if (!mt7921_mac_reset(dev)) break; } @@ -1293,16 +1378,24 @@ void mt7921_mac_reset_work(struct work_struct *work) ieee80211_scan_completed(dev->mphy.hw, &info); } + dev->hw_full_reset = false; ieee80211_wake_queues(hw); ieee80211_iterate_active_interfaces(hw, IEEE80211_IFACE_ITER_RESUME_ALL, mt7921_vif_connect_iter, NULL); + mt76_connac_power_save_sched(&dev->mt76.phy, pm); } void mt7921_reset(struct mt76_dev *mdev) { struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); + if (!dev->hw_init_done) + return; + + if (dev->hw_full_reset) + return; + queue_work(dev->mt76.wq, &dev->reset_work); } @@ -1337,30 +1430,6 @@ mt7921_mac_update_mib_stats(struct mt7921_phy *phy) } } -static void -mt7921_mac_sta_stats_work(struct mt7921_phy *phy) -{ - struct mt7921_dev *dev = phy->dev; - struct mt7921_sta *msta; - LIST_HEAD(list); - - spin_lock_bh(&dev->sta_poll_lock); - list_splice_init(&phy->stats_list, &list); - - while (!list_empty(&list)) { - msta = list_first_entry(&list, struct mt7921_sta, stats_list); - list_del_init(&msta->stats_list); - spin_unlock_bh(&dev->sta_poll_lock); - - /* query wtbl info to report tx rate for further devices */ - mt7921_get_wtbl_info(dev, msta->wcid.idx); - - spin_lock_bh(&dev->sta_poll_lock); - } - - spin_unlock_bh(&dev->sta_poll_lock); -} - void mt7921_mac_work(struct work_struct *work) { struct mt7921_phy *phy; @@ -1372,16 +1441,12 @@ void mt7921_mac_work(struct work_struct *work) mt7921_mutex_acquire(phy->dev); - mt76_update_survey(mphy->dev); + mt76_update_survey(mphy); if (++mphy->mac_work_count == 2) { mphy->mac_work_count = 0; mt7921_mac_update_mib_stats(phy); } - if (++phy->sta_work_count == 4) { - phy->sta_work_count = 0; - mt7921_mac_sta_stats_work(phy); - } mt7921_mutex_release(phy->dev); ieee80211_queue_delayed_work(phy->mt76->hw, &mphy->mac_work, @@ -1417,13 +1482,15 @@ void mt7921_pm_power_save_work(struct work_struct *work) { struct mt7921_dev *dev; unsigned long delta; + struct mt76_phy *mphy; dev = (struct mt7921_dev *)container_of(work, struct mt7921_dev, pm.ps_work.work); + mphy = dev->phy.mt76; delta = dev->pm.idle_timeout; - if (test_bit(MT76_HW_SCANNING, &dev->mphy.state) || - test_bit(MT76_HW_SCHED_SCANNING, &dev->mphy.state)) + if (test_bit(MT76_HW_SCANNING, &mphy->state) || + test_bit(MT76_HW_SCHED_SCANNING, &mphy->state)) goto out; if (time_is_after_jiffies(dev->pm.last_activity + delta)) { @@ -1431,8 +1498,10 @@ void mt7921_pm_power_save_work(struct work_struct *work) goto out; } - if (!mt7921_mcu_fw_pmctrl(dev)) + if (!mt7921_mcu_fw_pmctrl(dev)) { + cancel_delayed_work_sync(&mphy->mac_work); return; + } out: queue_delayed_work(dev->mt76.wq, &dev->pm.ps_work, delta); } @@ -1494,7 +1563,7 @@ void mt7921_coredump_work(struct work_struct *work) break; skb_pull(skb, sizeof(struct mt7921_mcu_rxd)); - if (data + skb->len - dump > MT76_CONNAC_COREDUMP_SZ) { + if (!dump || data + skb->len - dump > MT76_CONNAC_COREDUMP_SZ) { dev_kfree_skb(skb); continue; } @@ -1504,7 +1573,10 @@ void mt7921_coredump_work(struct work_struct *work) dev_kfree_skb(skb); } - dev_coredumpv(dev->mt76.dev, dump, MT76_CONNAC_COREDUMP_SZ, - GFP_KERNEL); + + if (dump) + dev_coredumpv(dev->mt76.dev, dump, MT76_CONNAC_COREDUMP_SZ, + GFP_KERNEL); + mt7921_reset(&dev->mt76); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mac.h b/drivers/net/wireless/mediatek/mt76/mt7921/mac.h index 109c8849d106..3af67fac213d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mac.h +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mac.h @@ -88,6 +88,9 @@ enum rx_pkt_type { /* RXD DW4 */ #define MT_RXD4_NORMAL_PAYLOAD_FORMAT GENMASK(1, 0) +#define MT_RXD4_FIRST_AMSDU_FRAME GENMASK(1, 0) +#define MT_RXD4_MID_AMSDU_FRAME BIT(1) +#define MT_RXD4_LAST_AMSDU_FRAME BIT(0) #define MT_RXD4_NORMAL_PATTERN_DROP BIT(9) #define MT_RXD4_NORMAL_CLS BIT(10) #define MT_RXD4_NORMAL_OFLD GENMASK(12, 11) @@ -97,6 +100,17 @@ enum rx_pkt_type { #define MT_RXD3_NORMAL_PF_MODE BIT(29) #define MT_RXD3_NORMAL_PF_STS GENMASK(31, 30) +/* RXD GROUP4 */ +#define MT_RXD6_FRAME_CONTROL GENMASK(15, 0) +#define MT_RXD6_TA_LO GENMASK(31, 16) + +#define MT_RXD7_TA_HI GENMASK(31, 0) + +#define MT_RXD8_SEQ_CTRL GENMASK(15, 0) +#define MT_RXD8_QOS_CTL GENMASK(31, 16) + +#define MT_RXD9_HT_CONTROL GENMASK(31, 0) + /* P-RXV DW0 */ #define MT_PRXV_TX_RATE GENMASK(6, 0) #define MT_PRXV_TX_DCM BIT(4) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 97a0ef331ac3..7fd21049ff5a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -79,13 +79,14 @@ mt7921_init_he_caps(struct mt7921_phy *phy, enum nl80211_band band, he_cap_elem->phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD; he_cap_elem->phy_cap_info[2] = + IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | - IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ; + IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ | + IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | + IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO; switch (i) { case NL80211_IFTYPE_STATION: - he_cap_elem->mac_cap_info[0] |= - IEEE80211_HE_MAC_CAP0_TWT_REQ; he_cap_elem->mac_cap_info[1] |= IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US; @@ -102,7 +103,15 @@ mt7921_init_he_caps(struct mt7921_phy *phy, enum nl80211_band band, he_cap_elem->phy_cap_info[3] |= IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK | IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK; + he_cap_elem->phy_cap_info[4] |= + IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE | + IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4; + he_cap_elem->phy_cap_info[5] |= + IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK | + IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK; he_cap_elem->phy_cap_info[6] |= + IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU | + IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU | IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB | IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE | IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT; @@ -223,54 +232,6 @@ static void mt7921_stop(struct ieee80211_hw *hw) mt7921_mutex_release(dev); } -static inline int get_free_idx(u32 mask, u8 start, u8 end) -{ - return ffs(~mask & GENMASK(end, start)); -} - -static int get_omac_idx(enum nl80211_iftype type, u64 mask) -{ - int i; - - switch (type) { - case NL80211_IFTYPE_STATION: - /* prefer hw bssid slot 1-3 */ - i = get_free_idx(mask, HW_BSSID_1, HW_BSSID_3); - if (i) - return i - 1; - - /* next, try to find a free repeater entry for the sta */ - i = get_free_idx(mask >> REPEATER_BSSID_START, 0, - REPEATER_BSSID_MAX - REPEATER_BSSID_START); - if (i) - return i + 32 - 1; - - i = get_free_idx(mask, EXT_BSSID_1, EXT_BSSID_MAX); - if (i) - return i - 1; - - if (~mask & BIT(HW_BSSID_0)) - return HW_BSSID_0; - - break; - case NL80211_IFTYPE_MONITOR: - /* ap uses hw bssid 0 and ext bssid */ - if (~mask & BIT(HW_BSSID_0)) - return HW_BSSID_0; - - i = get_free_idx(mask, EXT_BSSID_1, EXT_BSSID_MAX); - if (i) - return i - 1; - - break; - default: - WARN_ON(1); - break; - } - - return -1; -} - static int mt7921_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { @@ -292,12 +253,7 @@ static int mt7921_add_interface(struct ieee80211_hw *hw, goto out; } - idx = get_omac_idx(vif->type, phy->omac_mask); - if (idx < 0) { - ret = -ENOSPC; - goto out; - } - mvif->mt76.omac_idx = idx; + mvif->mt76.omac_idx = mvif->mt76.idx; mvif->phy = phy; mvif->mt76.band_idx = 0; mvif->mt76.wmm_idx = mvif->mt76.idx % MT7921_MAX_WMM_SETS; @@ -369,7 +325,7 @@ static void mt7921_remove_interface(struct ieee80211_hw *hw, spin_unlock_bh(&dev->sta_poll_lock); } -int mt7921_set_channel(struct mt7921_phy *phy) +static int mt7921_set_channel(struct mt7921_phy *phy) { struct mt7921_dev *dev = phy->dev; int ret; @@ -429,6 +385,10 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIE; wcid_keyidx = &wcid->hw_key_idx2; break; + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + if (!mvif->wep_sta) + return -EOPNOTSUPP; case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: @@ -436,8 +396,6 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, case WLAN_CIPHER_SUITE_GCMP_256: case WLAN_CIPHER_SUITE_SMS4: break; - case WLAN_CIPHER_SUITE_WEP40: - case WLAN_CIPHER_SUITE_WEP104: default: return -EOPNOTSUPP; } @@ -455,6 +413,12 @@ static int mt7921_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, cmd == SET_KEY ? key : NULL); err = mt7921_mcu_add_key(dev, vif, msta, key, cmd); + if (err) + goto out; + + if (key->cipher == WLAN_CIPHER_SUITE_WEP104 || + key->cipher == WLAN_CIPHER_SUITE_WEP40) + err = mt7921_mcu_add_key(dev, vif, mvif->wep_sta, key, cmd); out: mt7921_mutex_release(dev); @@ -477,6 +441,9 @@ static int mt7921_config(struct ieee80211_hw *hw, u32 changed) mt7921_mutex_acquire(dev); + if (changed & IEEE80211_CONF_CHANGE_POWER) + mt76_connac_mcu_set_rate_txpower(phy->mt76); + if (changed & IEEE80211_CONF_CHANGE_MONITOR) { bool enabled = !!(hw->conf.flags & IEEE80211_CONF_MONITOR); @@ -622,7 +589,8 @@ static void mt7921_bss_info_changed(struct ieee80211_hw *hw, mt7921_mcu_uni_bss_ps(dev, vif); if (changed & BSS_CHANGED_ASSOC) { - mt7921_mcu_sta_add(dev, NULL, vif, true); + mt7921_mcu_sta_update(dev, NULL, vif, true, + MT76_STA_INFO_STATE_ASSOC); mt7921_bss_bcnft_apply(dev, vif, info->assoc); } @@ -661,14 +629,14 @@ int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, if (ret) return ret; - if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls) - mt76_connac_mcu_uni_add_bss(&dev->mphy, vif, &mvif->sta.wcid, - true); + if (vif->type == NL80211_IFTYPE_STATION) + mvif->wep_sta = msta; mt7921_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); - ret = mt7921_mcu_sta_add(dev, sta, vif, true); + ret = mt7921_mcu_sta_update(dev, sta, vif, true, + MT76_STA_INFO_STATE_NONE); if (ret) return ret; @@ -677,6 +645,27 @@ int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, return 0; } +void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta) +{ + struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); + struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv; + struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv; + + mt7921_mutex_acquire(dev); + + if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls) + mt76_connac_mcu_uni_add_bss(&dev->mphy, vif, &mvif->sta.wcid, + true); + + mt7921_mac_wtbl_update(dev, msta->wcid.idx, + MT_WTBL_UPDATE_ADM_COUNT_CLEAR); + + mt7921_mcu_sta_update(dev, sta, vif, true, MT76_STA_INFO_STATE_ASSOC); + + mt7921_mutex_release(dev); +} + void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct ieee80211_sta *sta) { @@ -686,13 +675,14 @@ void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif, mt76_connac_free_pending_tx_skbs(&dev->pm, &msta->wcid); mt76_connac_pm_wake(&dev->mphy, &dev->pm); - mt7921_mcu_sta_add(dev, sta, vif, false); + mt7921_mcu_sta_update(dev, sta, vif, false, MT76_STA_INFO_STATE_NONE); mt7921_mac_wtbl_update(dev, msta->wcid.idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); if (vif->type == NL80211_IFTYPE_STATION) { struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv; + mvif->wep_sta = NULL; ewma_rssi_init(&mvif->rssi); if (!sta->tdls) mt76_connac_mcu_uni_add_bss(&dev->mphy, vif, @@ -720,7 +710,7 @@ void mt7921_tx_worker(struct mt76_worker *w) } mt76_txq_schedule_all(&dev->mphy); - mt76_connac_pm_unref(&dev->pm); + mt76_connac_pm_unref(&dev->mphy, &dev->pm); } static void mt7921_tx(struct ieee80211_hw *hw, @@ -750,7 +740,7 @@ static void mt7921_tx(struct ieee80211_hw *hw, if (mt76_connac_pm_ref(mphy, &dev->pm)) { mt76_tx(mphy, control->sta, wcid, skb); - mt76_connac_pm_unref(&dev->pm); + mt76_connac_pm_unref(mphy, &dev->pm); return; } @@ -831,20 +821,21 @@ mt7921_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, return ret; } -static int -mt7921_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - struct ieee80211_sta *sta) +static int mt7921_sta_state(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + enum ieee80211_sta_state old_state, + enum ieee80211_sta_state new_state) { - return mt76_sta_state(hw, vif, sta, IEEE80211_STA_NOTEXIST, - IEEE80211_STA_NONE); -} + struct mt7921_dev *dev = mt7921_hw_dev(hw); -static int -mt7921_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - struct ieee80211_sta *sta) -{ - return mt76_sta_state(hw, vif, sta, IEEE80211_STA_NONE, - IEEE80211_STA_NOTEXIST); + if (dev->pm.ds_enable) { + mt7921_mutex_acquire(dev); + mt76_connac_sta_state_dp(&dev->mt76, old_state, new_state); + mt7921_mutex_release(dev); + } + + return mt76_sta_state(hw, vif, sta, old_state, new_state); } static int @@ -1163,6 +1154,23 @@ static void mt7921_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif, HZ / 2); } +static void mt7921_sta_set_decap_offload(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + bool enabled) +{ + struct mt7921_sta *msta = (struct mt7921_sta *)sta->drv_priv; + struct mt7921_dev *dev = mt7921_hw_dev(hw); + + if (enabled) + set_bit(MT_WCID_FLAG_HDR_TRANS, &msta->wcid.flags); + else + clear_bit(MT_WCID_FLAG_HDR_TRANS, &msta->wcid.flags); + + mt76_connac_mcu_sta_update_hdr_trans(&dev->mt76, vif, &msta->wcid, + MCU_UNI_CMD_STA_REC_UPDATE); +} + const struct ieee80211_ops mt7921_ops = { .tx = mt7921_tx, .start = mt7921_start, @@ -1173,10 +1181,10 @@ const struct ieee80211_ops mt7921_ops = { .conf_tx = mt7921_conf_tx, .configure_filter = mt7921_configure_filter, .bss_info_changed = mt7921_bss_info_changed, - .sta_add = mt7921_sta_add, - .sta_remove = mt7921_sta_remove, + .sta_state = mt7921_sta_state, .sta_pre_rcu_remove = mt76_sta_pre_rcu_remove, .set_key = mt7921_set_key, + .sta_set_decap_offload = mt7921_sta_set_decap_offload, .ampdu_action = mt7921_ampdu_action, .set_rts_threshold = mt7921_set_rts_threshold, .wake_tx_queue = mt76_wake_tx_queue, diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c index 67dc4b4cc094..c2c4dc196802 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.c @@ -88,28 +88,28 @@ struct mt7921_fw_region { #define to_wcid_lo(id) FIELD_GET(GENMASK(7, 0), (u16)id) #define to_wcid_hi(id) FIELD_GET(GENMASK(9, 8), (u16)id) -static enum mt7921_cipher_type +static enum mcu_cipher_type mt7921_mcu_get_cipher(int cipher) { switch (cipher) { case WLAN_CIPHER_SUITE_WEP40: - return MT_CIPHER_WEP40; + return MCU_CIPHER_WEP40; case WLAN_CIPHER_SUITE_WEP104: - return MT_CIPHER_WEP104; + return MCU_CIPHER_WEP104; case WLAN_CIPHER_SUITE_TKIP: - return MT_CIPHER_TKIP; + return MCU_CIPHER_TKIP; case WLAN_CIPHER_SUITE_AES_CMAC: - return MT_CIPHER_BIP_CMAC_128; + return MCU_CIPHER_BIP_CMAC_128; case WLAN_CIPHER_SUITE_CCMP: - return MT_CIPHER_AES_CCMP; + return MCU_CIPHER_AES_CCMP; case WLAN_CIPHER_SUITE_CCMP_256: - return MT_CIPHER_CCMP_256; + return MCU_CIPHER_CCMP_256; case WLAN_CIPHER_SUITE_GCMP: - return MT_CIPHER_GCMP; + return MCU_CIPHER_GCMP; case WLAN_CIPHER_SUITE_GCMP_256: - return MT_CIPHER_GCMP_256; + return MCU_CIPHER_GCMP_256; case WLAN_CIPHER_SUITE_SMS4: - return MT_CIPHER_WAPI; + return MCU_CIPHER_WAPI; default: return MT_CIPHER_NONE; } @@ -398,43 +398,6 @@ mt7921_mcu_tx_rate_parse(struct mt76_phy *mphy, } } -static void -mt7921_mcu_tx_rate_report(struct mt7921_dev *dev, struct sk_buff *skb, - u16 wlan_idx) -{ - struct mt7921_mcu_wlan_info_event *wtbl_info; - struct mt76_phy *mphy = &dev->mphy; - struct mt7921_sta_stats *stats; - struct rate_info rate = {}; - struct mt7921_sta *msta; - struct mt76_wcid *wcid; - u8 idx; - - if (wlan_idx >= MT76_N_WCIDS) - return; - - wtbl_info = (struct mt7921_mcu_wlan_info_event *)skb->data; - idx = wtbl_info->rate_info.rate_idx; - if (idx >= ARRAY_SIZE(wtbl_info->rate_info.rate)) - return; - - rcu_read_lock(); - - wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]); - if (!wcid) - goto out; - - msta = container_of(wcid, struct mt7921_sta, wcid); - stats = &msta->stats; - - /* current rate */ - mt7921_mcu_tx_rate_parse(mphy, &wtbl_info->peer_cap, &rate, - le16_to_cpu(wtbl_info->rate_info.rate[idx])); - stats->tx_rate = rate; -out: - rcu_read_unlock(); -} - static void mt7921_mcu_scan_event(struct mt7921_dev *dev, struct sk_buff *skb) { @@ -450,22 +413,33 @@ mt7921_mcu_scan_event(struct mt7921_dev *dev, struct sk_buff *skb) } static void -mt7921_mcu_beacon_loss_event(struct mt7921_dev *dev, struct sk_buff *skb) +mt7921_mcu_connection_loss_iter(void *priv, u8 *mac, + struct ieee80211_vif *vif) +{ + struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv; + struct mt76_connac_beacon_loss_event *event = priv; + + if (mvif->idx != event->bss_idx) + return; + + if (!(vif->driver_flags & IEEE80211_VIF_BEACON_FILTER)) + return; + + ieee80211_connection_loss(vif); +} + +static void +mt7921_mcu_connection_loss_event(struct mt7921_dev *dev, struct sk_buff *skb) { struct mt76_connac_beacon_loss_event *event; - struct mt76_phy *mphy; - u8 band_idx = 0; /* DBDC support */ + struct mt76_phy *mphy = &dev->mt76.phy; skb_pull(skb, sizeof(struct mt7921_mcu_rxd)); event = (struct mt76_connac_beacon_loss_event *)skb->data; - if (band_idx && dev->mt76.phy2) - mphy = dev->mt76.phy2; - else - mphy = &dev->mt76.phy; ieee80211_iterate_active_interfaces_atomic(mphy->hw, IEEE80211_IFACE_ITER_RESUME_ALL, - mt76_connac_mcu_beacon_loss_iter, event); + mt7921_mcu_connection_loss_iter, event); } static void @@ -523,6 +497,49 @@ mt7921_mcu_low_power_event(struct mt7921_dev *dev, struct sk_buff *skb) trace_lp_event(dev, event->state); } +static void +mt7921_mcu_tx_done_event(struct mt7921_dev *dev, struct sk_buff *skb) +{ + struct mt7921_mcu_tx_done_event *event; + struct mt7921_sta *msta; + struct mt7921_phy *mphy = &dev->phy; + struct mt7921_mcu_peer_cap peer; + struct ieee80211_sta *sta; + LIST_HEAD(list); + + skb_pull(skb, sizeof(struct mt7921_mcu_rxd)); + event = (struct mt7921_mcu_tx_done_event *)skb->data; + + spin_lock_bh(&dev->sta_poll_lock); + list_splice_init(&mphy->stats_list, &list); + + while (!list_empty(&list)) { + msta = list_first_entry(&list, struct mt7921_sta, stats_list); + list_del_init(&msta->stats_list); + + if (msta->wcid.idx != event->wlan_idx) + continue; + + spin_unlock_bh(&dev->sta_poll_lock); + + sta = wcid_to_sta(&msta->wcid); + + /* peer config based on IEEE SPEC */ + memset(&peer, 0x0, sizeof(peer)); + peer.bw = event->bw; + peer.g2 = !!(sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_20); + peer.g4 = !!(sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_40); + peer.g8 = !!(sta->vht_cap.cap & IEEE80211_VHT_CAP_SHORT_GI_80); + peer.g16 = !!(sta->vht_cap.cap & IEEE80211_VHT_CAP_SHORT_GI_160); + mt7921_mcu_tx_rate_parse(mphy->mt76, &peer, + &msta->stats.tx_rate, event->tx_rate); + + spin_lock_bh(&dev->sta_poll_lock); + break; + } + spin_unlock_bh(&dev->sta_poll_lock); +} + static void mt7921_mcu_rx_unsolicited_event(struct mt7921_dev *dev, struct sk_buff *skb) { @@ -530,7 +547,7 @@ mt7921_mcu_rx_unsolicited_event(struct mt7921_dev *dev, struct sk_buff *skb) switch (rxd->eid) { case MCU_EVENT_BSS_BEACON_LOSS: - mt7921_mcu_beacon_loss_event(dev, skb); + mt7921_mcu_connection_loss_event(dev, skb); break; case MCU_EVENT_SCHED_SCAN_DONE: case MCU_EVENT_SCAN_DONE: @@ -549,6 +566,9 @@ mt7921_mcu_rx_unsolicited_event(struct mt7921_dev *dev, struct sk_buff *skb) case MCU_EVENT_LP_INFO: mt7921_mcu_low_power_event(dev, skb); break; + case MCU_EVENT_TX_DONE: + mt7921_mcu_tx_done_event(dev, skb); + break; default: break; } @@ -569,6 +589,7 @@ void mt7921_mcu_rx_event(struct mt7921_dev *dev, struct sk_buff *skb) rxd->eid == MCU_EVENT_SCHED_SCAN_DONE || rxd->eid == MCU_EVENT_BSS_ABSENCE || rxd->eid == MCU_EVENT_SCAN_DONE || + rxd->eid == MCU_EVENT_TX_DONE || rxd->eid == MCU_EVENT_DBG_MSG || rxd->eid == MCU_EVENT_COREDUMP || rxd->eid == MCU_EVENT_LP_INFO || @@ -604,14 +625,14 @@ mt7921_mcu_sta_key_tlv(struct mt7921_sta *msta, struct sk_buff *skb, sec_key = &sec->key[0]; sec_key->cipher_len = sizeof(*sec_key); - if (cipher == MT_CIPHER_BIP_CMAC_128) { - sec_key->cipher_id = MT_CIPHER_AES_CCMP; + if (cipher == MCU_CIPHER_BIP_CMAC_128) { + sec_key->cipher_id = MCU_CIPHER_AES_CCMP; sec_key->key_id = bip->keyidx; sec_key->key_len = 16; memcpy(sec_key->key, bip->key, 16); sec_key = &sec->key[1]; - sec_key->cipher_id = MT_CIPHER_BIP_CMAC_128; + sec_key->cipher_id = MCU_CIPHER_BIP_CMAC_128; sec_key->cipher_len = sizeof(*sec_key); sec_key->key_len = 16; memcpy(sec_key->key, key->key, 16); @@ -623,14 +644,14 @@ mt7921_mcu_sta_key_tlv(struct mt7921_sta *msta, struct sk_buff *skb, sec_key->key_len = key->keylen; memcpy(sec_key->key, key->key, key->keylen); - if (cipher == MT_CIPHER_TKIP) { + if (cipher == MCU_CIPHER_TKIP) { /* Rx/Tx MIC keys are swapped */ memcpy(sec_key->key + 16, key->key + 24, 8); memcpy(sec_key->key + 24, key->key + 16, 8); } /* store key_conf for BIP batch update */ - if (cipher == MT_CIPHER_AES_CCMP) { + if (cipher == MCU_CIPHER_AES_CCMP) { memcpy(bip->key, key->key, key->keylen); bip->keyidx = key->keyidx; } @@ -934,8 +955,6 @@ static int mt7921_load_firmware(struct mt7921_dev *dev) dev->mt76.hw->wiphy->wowlan = &mt76_connac_wowlan_support; #endif /* CONFIG_PM */ - clear_bit(MT76_STATE_PM, &dev->mphy.state); - dev_err(dev->mt76.dev, "Firmware init done\n"); return 0; @@ -969,7 +988,7 @@ int mt7921_run_firmware(struct mt7921_dev *dev) set_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state); mt7921_mcu_fw_log_2_host(dev, 1); - return 0; + return mt76_connac_mcu_get_nic_capability(&dev->mphy); } int mt7921_mcu_init(struct mt7921_dev *dev) @@ -1136,26 +1155,6 @@ int mt7921_mcu_get_eeprom(struct mt7921_dev *dev, u32 offset) return 0; } -u32 mt7921_get_wtbl_info(struct mt7921_dev *dev, u32 wlan_idx) -{ - struct mt7921_mcu_wlan_info wtbl_info = { - .wlan_idx = cpu_to_le32(wlan_idx), - }; - struct sk_buff *skb; - int ret; - - ret = mt76_mcu_send_and_get_msg(&dev->mt76, MCU_CMD_GET_WTBL, - &wtbl_info, sizeof(wtbl_info), true, - &skb); - if (ret) - return ret; - - mt7921_mcu_tx_rate_report(dev, skb, wlan_idx); - dev_kfree_skb(skb); - - return 0; -} - int mt7921_mcu_uni_bss_ps(struct mt7921_dev *dev, struct ieee80211_vif *vif) { struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv; @@ -1268,8 +1267,9 @@ int mt7921_mcu_set_bss_pm(struct mt7921_dev *dev, struct ieee80211_vif *vif, sizeof(req), false); } -int mt7921_mcu_sta_add(struct mt7921_dev *dev, struct ieee80211_sta *sta, - struct ieee80211_vif *vif, bool enable) +int mt7921_mcu_sta_update(struct mt7921_dev *dev, struct ieee80211_sta *sta, + struct ieee80211_vif *vif, bool enable, + enum mt76_sta_info_state state) { struct mt7921_vif *mvif = (struct mt7921_vif *)vif->drv_priv; int rssi = -ewma_rssi_read(&mvif->rssi); @@ -1278,27 +1278,25 @@ int mt7921_mcu_sta_add(struct mt7921_dev *dev, struct ieee80211_sta *sta, .vif = vif, .enable = enable, .cmd = MCU_UNI_CMD_STA_REC_UPDATE, + .state = state, + .offload_fw = true, .rcpi = to_rcpi(rssi), }; struct mt7921_sta *msta; msta = sta ? (struct mt7921_sta *)sta->drv_priv : NULL; info.wcid = msta ? &msta->wcid : &mvif->sta.wcid; + info.newly = msta ? state != MT76_STA_INFO_STATE_ASSOC : true; - return mt76_connac_mcu_add_sta_cmd(&dev->mphy, &info); + return mt76_connac_mcu_sta_cmd(&dev->mphy, &info); } -int mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev) +int __mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev) { struct mt76_phy *mphy = &dev->mt76.phy; struct mt76_connac_pm *pm = &dev->pm; int i, err = 0; - mutex_lock(&pm->mutex); - - if (!test_bit(MT76_STATE_PM, &mphy->state)) - goto out; - for (i = 0; i < MT7921_DRV_OWN_RETRY_COUNT; i++) { mt76_wr(dev, MT_CONN_ON_LPCTL, PCIE_LPCR_HOST_CLR_OWN); if (mt76_poll_msec(dev, MT_CONN_ON_LPCTL, @@ -1318,6 +1316,22 @@ int mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev) pm->stats.last_wake_event = jiffies; pm->stats.doze_time += pm->stats.last_wake_event - pm->stats.last_doze_event; +out: + return err; +} + +int mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev) +{ + struct mt76_phy *mphy = &dev->mt76.phy; + struct mt76_connac_pm *pm = &dev->pm; + int err = 0; + + mutex_lock(&pm->mutex); + + if (!test_bit(MT76_STATE_PM, &mphy->state)) + goto out; + + err = __mt7921_mcu_drv_pmctrl(dev); out: mutex_unlock(&pm->mutex); @@ -1368,6 +1382,7 @@ mt7921_pm_interface_iter(void *priv, u8 *mac, struct ieee80211_vif *vif) { struct mt7921_phy *phy = priv; struct mt7921_dev *dev = phy->dev; + struct ieee80211_hw *hw = mt76_hw(dev); int ret; if (dev->pm.enable) @@ -1380,9 +1395,11 @@ mt7921_pm_interface_iter(void *priv, u8 *mac, struct ieee80211_vif *vif) if (dev->pm.enable) { vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER; + ieee80211_hw_set(hw, CONNECTION_MONITOR); mt76_set(dev, MT_WF_RFCR(0), MT_WF_RFCR_DROP_OTHER_BEACON); } else { vif->driver_flags &= ~IEEE80211_VIF_BEACON_FILTER; + __clear_bit(IEEE80211_HW_CONNECTION_MONITOR, hw->flags); mt76_clear(dev, MT_WF_RFCR(0), MT_WF_RFCR_DROP_OTHER_BEACON); } } diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.h index 49823d0a3d0a..d76cf8f8dfdf 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mcu.h @@ -81,6 +81,7 @@ enum { MCU_EVENT_REG_ACCESS = 0x05, MCU_EVENT_LP_INFO = 0x07, MCU_EVENT_SCAN_DONE = 0x0d, + MCU_EVENT_TX_DONE = 0x0f, MCU_EVENT_BSS_ABSENCE = 0x11, MCU_EVENT_BSS_BEACON_LOSS = 0x13, MCU_EVENT_CH_PRIVILEGE = 0x18, @@ -197,18 +198,17 @@ struct sta_rec_sec { struct sec_key key[2]; } __packed; -enum mt7921_cipher_type { - MT_CIPHER_NONE, - MT_CIPHER_WEP40, - MT_CIPHER_WEP104, - MT_CIPHER_WEP128, - MT_CIPHER_TKIP, - MT_CIPHER_AES_CCMP, - MT_CIPHER_CCMP_256, - MT_CIPHER_GCMP, - MT_CIPHER_GCMP_256, - MT_CIPHER_WAPI, - MT_CIPHER_BIP_CMAC_128, +enum mcu_cipher_type { + MCU_CIPHER_WEP40 = 1, + MCU_CIPHER_WEP104, + MCU_CIPHER_WEP128, + MCU_CIPHER_TKIP, + MCU_CIPHER_AES_CCMP, + MCU_CIPHER_CCMP_256, + MCU_CIPHER_GCMP, + MCU_CIPHER_GCMP_256, + MCU_CIPHER_WAPI, + MCU_CIPHER_BIP_CMAC_128, }; enum { @@ -254,86 +254,6 @@ struct mt7921_mcu_reg_event { __le32 val; } __packed; -struct mt7921_mcu_tx_config { - u8 peer_addr[ETH_ALEN]; - u8 sw; - u8 dis_rx_hdr_tran; - - u8 aad_om; - u8 pfmu_idx; - __le16 partial_aid; - - u8 ibf; - u8 ebf; - u8 is_ht; - u8 is_vht; - - u8 mesh; - u8 baf_en; - u8 cf_ack; - u8 rdg_ba; - - u8 rdg; - u8 pm; - u8 rts; - u8 smps; - - u8 txop_ps; - u8 not_update_ipsm; - u8 skip_tx; - u8 ldpc; - - u8 qos; - u8 from_ds; - u8 to_ds; - u8 dyn_bw; - - u8 amdsu_cross_lg; - u8 check_per; - u8 gid_63; - u8 he; - - u8 vht_ibf; - u8 vht_ebf; - u8 vht_ldpc; - u8 he_ldpc; -} __packed; - -struct mt7921_mcu_sec_config { - u8 wpi_flag; - u8 rv; - u8 ikv; - u8 rkv; - - u8 rcid; - u8 rca1; - u8 rca2; - u8 even_pn; - - u8 key_id; - u8 muar_idx; - u8 cipher_suit; - u8 rsv[1]; -} __packed; - -struct mt7921_mcu_key_config { - u8 key[32]; -} __packed; - -struct mt7921_mcu_rate_info { - u8 mpdu_fail; - u8 mpdu_tx; - u8 rate_idx; - u8 rsv[1]; - __le16 rate[8]; -} __packed; - -struct mt7921_mcu_ba_config { - u8 ba_en; - u8 rsv[3]; - __le32 ba_winsize; -} __packed; - struct mt7921_mcu_ant_id_config { u8 ant_id[4]; } __packed; @@ -357,41 +277,6 @@ struct mt7921_mcu_peer_cap { u8 rsv[1]; } __packed; -struct mt7921_mcu_rx_cnt { - u8 rx_rcpi[4]; - u8 rx_cc[4]; - u8 rx_cc_sel; - u8 ce_rmsd; - u8 rsv[2]; -} __packed; - -struct mt7921_mcu_tx_cnt { - __le16 rate1_cnt; - __le16 rate1_fail_cnt; - __le16 rate2_cnt; - __le16 rate3_cnt; - __le16 cur_bw_tx_cnt; - __le16 cur_bw_tx_fail_cnt; - __le16 other_bw_tx_cnt; - __le16 other_bw_tx_fail_cnt; -} __packed; - -struct mt7921_mcu_wlan_info_event { - struct mt7921_mcu_tx_config tx_config; - struct mt7921_mcu_sec_config sec_config; - struct mt7921_mcu_key_config key_config; - struct mt7921_mcu_rate_info rate_info; - struct mt7921_mcu_ba_config ba_config; - struct mt7921_mcu_peer_cap peer_cap; - struct mt7921_mcu_rx_cnt rx_cnt; - struct mt7921_mcu_tx_cnt tx_cnt; -} __packed; - -struct mt7921_mcu_wlan_info { - __le32 wlan_idx; - struct mt7921_mcu_wlan_info_event event; -} __packed; - struct mt7921_txpwr_req { u8 ver; u8 action; @@ -407,4 +292,31 @@ struct mt7921_txpwr_event { struct mt7921_txpwr txpwr; } __packed; +struct mt7921_mcu_tx_done_event { + u8 pid; + u8 status; + u16 seq; + + u8 wlan_idx; + u8 tx_cnt; + u16 tx_rate; + + u8 flag; + u8 tid; + u8 rsp_rate; + u8 mcs; + + u8 bw; + u8 tx_pwr; + u8 reason; + u8 rsv0[1]; + + u32 delay; + u32 timestamp; + u32 applied_flag; + + u8 txs[28]; + + u8 rsv1[32]; +} __packed; #endif diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h index 59862ea4951c..2d8bd6bfc820 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h +++ b/drivers/net/wireless/mediatek/mt76/mt7921/mt7921.h @@ -92,6 +92,8 @@ struct mt7921_sta { unsigned long ampdu_state; struct mt7921_sta_key_conf bip; + + unsigned long next_txs_ts; }; DECLARE_EWMA(rssi, 10, 8); @@ -100,6 +102,8 @@ struct mt7921_vif { struct mt76_vif mt76; /* must be first */ struct mt7921_sta sta; + struct mt7921_sta *wep_sta; + struct mt7921_phy *phy; struct ewma_rssi rssi; @@ -156,6 +160,8 @@ struct mt7921_dev { u16 chainmask; struct work_struct reset_work; + bool hw_full_reset:1; + bool hw_init_done:1; struct list_head sta_poll_list; spinlock_t sta_poll_lock; @@ -256,9 +262,9 @@ int mt7921_mcu_init(struct mt7921_dev *dev); int mt7921_mcu_add_key(struct mt7921_dev *dev, struct ieee80211_vif *vif, struct mt7921_sta *msta, struct ieee80211_key_conf *key, enum set_key_cmd cmd); -int mt7921_set_channel(struct mt7921_phy *phy); -int mt7921_mcu_sta_add(struct mt7921_dev *dev, struct ieee80211_sta *sta, - struct ieee80211_vif *vif, bool enable); +int mt7921_mcu_sta_update(struct mt7921_dev *dev, struct ieee80211_sta *sta, + struct ieee80211_vif *vif, bool enable, + enum mt76_sta_info_state state); int mt7921_mcu_set_chan_info(struct mt7921_phy *phy, int cmd); int mt7921_mcu_set_tx(struct mt7921_dev *dev, struct ieee80211_vif *vif); int mt7921_mcu_set_eeprom(struct mt7921_dev *dev); @@ -318,7 +324,7 @@ static inline bool mt7921_dma_need_reinit(struct mt7921_dev *dev) return !mt76_get_field(dev, MT_WFDMA_DUMMY_CR, MT_WFDMA_NEED_REINIT); } -void mt7921_mac_init(struct mt7921_dev *dev); +int mt7921_mac_init(struct mt7921_dev *dev); bool mt7921_mac_wtbl_update(struct mt7921_dev *dev, int idx, u32 mask); void mt7921_mac_reset_counters(struct mt7921_phy *phy); void mt7921_mac_write_txwi(struct mt7921_dev *dev, __le32 *txwi, @@ -330,6 +336,8 @@ void mt7921_mac_fill_rx_vector(struct mt7921_dev *dev, struct sk_buff *skb); void mt7921_mac_tx_free(struct mt7921_dev *dev, struct sk_buff *skb); int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct ieee80211_sta *sta); +void mt7921_mac_sta_assoc(struct mt76_dev *mdev, struct ieee80211_vif *vif, + struct ieee80211_sta *sta); void mt7921_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif, struct ieee80211_sta *sta); void mt7921_mac_work(struct work_struct *work); @@ -352,7 +360,7 @@ void mt7921_stats_work(struct work_struct *work); void mt7921_txp_skb_unmap(struct mt76_dev *dev, struct mt76_txwi_cache *txwi); void mt7921_set_stream_he_caps(struct mt7921_phy *phy); -void mt7921_update_channel(struct mt76_dev *mdev); +void mt7921_update_channel(struct mt76_phy *mphy); int mt7921_init_debugfs(struct mt7921_dev *dev); int mt7921_mcu_uni_tx_ba(struct mt7921_dev *dev, @@ -362,12 +370,12 @@ int mt7921_mcu_uni_rx_ba(struct mt7921_dev *dev, struct ieee80211_ampdu_params *params, bool enable); void mt7921_scan_work(struct work_struct *work); -u32 mt7921_get_wtbl_info(struct mt7921_dev *dev, u32 wlan_idx); int mt7921_mcu_uni_bss_ps(struct mt7921_dev *dev, struct ieee80211_vif *vif); int mt7921_mcu_uni_bss_bcnft(struct mt7921_dev *dev, struct ieee80211_vif *vif, bool enable); int mt7921_mcu_set_bss_pm(struct mt7921_dev *dev, struct ieee80211_vif *vif, bool enable); +int __mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev); int mt7921_mcu_drv_pmctrl(struct mt7921_dev *dev); int mt7921_mcu_fw_pmctrl(struct mt7921_dev *dev); void mt7921_pm_wake_work(struct work_struct *work); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c index fa02d934f0bf..c3905bcab360 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c @@ -106,6 +106,7 @@ static int mt7921_pci_probe(struct pci_dev *pdev, .rx_poll_complete = mt7921_rx_poll_complete, .sta_ps = mt7921_sta_ps, .sta_add = mt7921_mac_sta_add, + .sta_assoc = mt7921_mac_sta_assoc, .sta_remove = mt7921_mac_sta_remove, .update_survey = mt7921_update_channel, }; @@ -188,22 +189,29 @@ static int mt7921_pci_suspend(struct pci_dev *pdev, pm_message_t state) { struct mt76_dev *mdev = pci_get_drvdata(pdev); struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); + struct mt76_connac_pm *pm = &dev->pm; bool hif_suspend; int i, err; - err = mt76_connac_pm_wake(&dev->mphy, &dev->pm); + pm->suspended = true; + cancel_delayed_work_sync(&pm->ps_work); + cancel_work_sync(&pm->wake_work); + + err = mt7921_mcu_drv_pmctrl(dev); if (err < 0) - return err; + goto restore_suspend; hif_suspend = !test_bit(MT76_STATE_SUSPEND, &dev->mphy.state); if (hif_suspend) { err = mt76_connac_mcu_set_hif_suspend(mdev, true); if (err) - return err; + goto restore_suspend; } - if (!dev->pm.enable) - mt76_connac_mcu_set_deep_sleep(&dev->mt76, true); + /* always enable deep sleep during suspend to reduce + * power consumption + */ + mt76_connac_mcu_set_deep_sleep(&dev->mt76, true); napi_disable(&mdev->tx_napi); mt76_worker_disable(&mdev->tx_worker); @@ -231,27 +239,30 @@ static int mt7921_pci_suspend(struct pci_dev *pdev, pm_message_t state) err = mt7921_mcu_fw_pmctrl(dev); if (err) - goto restore; + goto restore_napi; pci_save_state(pdev); err = pci_set_power_state(pdev, pci_choose_state(pdev, state)); if (err) - goto restore; + goto restore_napi; return 0; -restore: +restore_napi: mt76_for_each_q_rx(mdev, i) { napi_enable(&mdev->napi[i]); } napi_enable(&mdev->tx_napi); - if (!dev->pm.enable) + if (!pm->ds_enable) mt76_connac_mcu_set_deep_sleep(&dev->mt76, false); if (hif_suspend) mt76_connac_mcu_set_hif_suspend(mdev, false); +restore_suspend: + pm->suspended = false; + return err; } @@ -259,8 +270,10 @@ static int mt7921_pci_resume(struct pci_dev *pdev) { struct mt76_dev *mdev = pci_get_drvdata(pdev); struct mt7921_dev *dev = container_of(mdev, struct mt7921_dev, mt76); + struct mt76_connac_pm *pm = &dev->pm; int i, err; + pm->suspended = false; err = pci_set_power_state(pdev, PCI_D0); if (err) return err; @@ -291,7 +304,8 @@ static int mt7921_pci_resume(struct pci_dev *pdev) napi_enable(&mdev->tx_napi); napi_schedule(&mdev->tx_napi); - if (!dev->pm.enable) + /* restore previous ds setting */ + if (!pm->ds_enable) mt76_connac_mcu_set_deep_sleep(&dev->mt76, false); if (!test_bit(MT76_STATE_SUSPEND, &dev->mphy.state)) diff --git a/drivers/net/wireless/mediatek/mt76/sdio.c b/drivers/net/wireless/mediatek/mt76/sdio.c index a18d2896ee1f..783a15635ec5 100644 --- a/drivers/net/wireless/mediatek/mt76/sdio.c +++ b/drivers/net/wireless/mediatek/mt76/sdio.c @@ -184,9 +184,6 @@ static int mt76s_process_tx_queue(struct mt76_dev *dev, struct mt76_queue *q) if (!q->queued) wake_up(&dev->tx_wait); - if (!mcu) - mt76_txq_schedule(&dev->phy, q->qid); - return nframes; } @@ -195,19 +192,28 @@ static void mt76s_status_worker(struct mt76_worker *w) struct mt76_sdio *sdio = container_of(w, struct mt76_sdio, status_worker); struct mt76_dev *dev = container_of(sdio, struct mt76_dev, sdio); + bool resched = false; int i, nframes; do { + int ndata_frames = 0; + nframes = mt76s_process_tx_queue(dev, dev->q_mcu[MT_MCUQ_WM]); for (i = 0; i <= MT_TXQ_PSD; i++) - nframes += mt76s_process_tx_queue(dev, - dev->phy.q_tx[i]); + ndata_frames += mt76s_process_tx_queue(dev, + dev->phy.q_tx[i]); + nframes += ndata_frames; + if (ndata_frames > 0) + resched = true; if (dev->drv->tx_status_data && !test_and_set_bit(MT76_READING_STATS, &dev->phy.state)) queue_work(dev->wq, &dev->sdio.stat_work); } while (nframes > 0); + + if (resched) + mt76_worker_schedule(&dev->sdio.txrx_worker); } static void mt76s_tx_status_data(struct work_struct *work) @@ -256,6 +262,7 @@ mt76s_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q, q->entry[q->head].skb = tx_info.skb; q->entry[q->head].buf_sz = len; + q->entry[q->head].wcid = 0xffff; smp_wmb(); diff --git a/drivers/net/wireless/mediatek/mt76/testmode.c b/drivers/net/wireless/mediatek/mt76/testmode.c index 001d0ba5f73e..f73ffbd6e622 100644 --- a/drivers/net/wireless/mediatek/mt76/testmode.c +++ b/drivers/net/wireless/mediatek/mt76/testmode.c @@ -88,17 +88,8 @@ static void mt76_testmode_free_skb(struct mt76_phy *phy) { struct mt76_testmode_data *td = &phy->test; - struct sk_buff *skb = td->tx_skb; - if (!skb) - return; - - if (skb_has_frag_list(skb)) { - kfree_skb_list(skb_shinfo(skb)->frag_list); - skb_shinfo(skb)->frag_list = NULL; - } - - dev_kfree_skb(skb); + dev_kfree_skb(td->tx_skb); td->tx_skb = NULL; } @@ -158,19 +149,18 @@ int mt76_testmode_alloc_skb(struct mt76_phy *phy, u32 len) frag_len = MT_TXP_MAX_LEN; frag = alloc_skb(frag_len, GFP_KERNEL); - if (!frag) + if (!frag) { + mt76_testmode_free_skb(phy); + dev_kfree_skb(head); return -ENOMEM; + } __skb_put_zero(frag, frag_len); head->len += frag->len; head->data_len += frag->len; - if (*frag_tail) { - (*frag_tail)->next = frag; - frag_tail = &frag; - } else { - *frag_tail = frag; - } + *frag_tail = frag; + frag_tail = &(*frag_tail)->next; } mt76_testmode_free_skb(phy); @@ -531,6 +521,14 @@ mt76_testmode_dump_stats(struct mt76_phy *phy, struct sk_buff *msg) u64 rx_fcs_error = 0; int i; + if (dev->test_ops->dump_stats) { + int ret; + + ret = dev->test_ops->dump_stats(phy, msg); + if (ret) + return ret; + } + for (i = 0; i < ARRAY_SIZE(td->rx_stats.packets); i++) { rx_packets += td->rx_stats.packets[i]; rx_fcs_error += td->rx_stats.fcs_error[i]; @@ -545,9 +543,6 @@ mt76_testmode_dump_stats(struct mt76_phy *phy, struct sk_buff *msg) MT76_TM_STATS_ATTR_PAD)) return -EMSGSIZE; - if (dev->test_ops->dump_stats) - return dev->test_ops->dump_stats(phy, msg); - return 0; } diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c index 53ea8de82df0..f0f7a913eaab 100644 --- a/drivers/net/wireless/mediatek/mt76/tx.c +++ b/drivers/net/wireless/mediatek/mt76/tx.c @@ -54,11 +54,23 @@ mt76_tx_status_unlock(struct mt76_dev *dev, struct sk_buff_head *list) spin_unlock_bh(&dev->status_list.lock); + rcu_read_lock(); while ((skb = __skb_dequeue(list)) != NULL) { - hw = mt76_tx_status_get_hw(dev, skb); - ieee80211_tx_status(hw, skb); - } + struct ieee80211_tx_status status = { + .skb = skb, + .info = IEEE80211_SKB_CB(skb), + }; + struct mt76_tx_cb *cb = mt76_tx_skb_cb(skb); + struct mt76_wcid *wcid; + wcid = rcu_dereference(dev->wcid[cb->wcid]); + if (wcid) + status.sta = wcid_to_sta(wcid); + + hw = mt76_tx_status_get_hw(dev, skb); + ieee80211_tx_status_ext(hw, &status); + } + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(mt76_tx_status_unlock); @@ -80,7 +92,7 @@ __mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb, u8 flags, /* Tx status can be unreliable. if it fails, mark the frame as ACKed */ if (flags & MT_TX_CB_TXS_FAILED) { - ieee80211_tx_info_clear_status(info); + info->status.rates[0].count = 0; info->status.rates[0].idx = -1; info->flags |= IEEE80211_TX_STAT_ACK; } @@ -117,12 +129,7 @@ mt76_tx_status_skb_add(struct mt76_dev *dev, struct mt76_wcid *wcid, spin_lock_bh(&dev->status_list.lock); memset(cb, 0, sizeof(*cb)); - wcid->packet_id = (wcid->packet_id + 1) & MT_PACKET_ID_MASK; - if (wcid->packet_id == MT_PACKET_ID_NO_ACK || - wcid->packet_id == MT_PACKET_ID_NO_SKB) - wcid->packet_id = MT_PACKET_ID_FIRST; - - pid = wcid->packet_id; + pid = mt76_get_next_pkt_id(wcid); cb->wcid = wcid->idx; cb->pktid = pid; cb->jiffies = jiffies; @@ -173,36 +180,37 @@ mt76_tx_status_check(struct mt76_dev *dev, struct mt76_wcid *wcid, bool flush) EXPORT_SYMBOL_GPL(mt76_tx_status_check); static void -mt76_tx_check_non_aql(struct mt76_dev *dev, u16 wcid_idx, struct sk_buff *skb) +mt76_tx_check_non_aql(struct mt76_dev *dev, struct mt76_wcid *wcid, + struct sk_buff *skb) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct mt76_wcid *wcid; int pending; - if (info->tx_time_est) + if (!wcid || info->tx_time_est) return; - if (wcid_idx >= ARRAY_SIZE(dev->wcid)) - return; - - rcu_read_lock(); - - wcid = rcu_dereference(dev->wcid[wcid_idx]); - if (wcid) { - pending = atomic_dec_return(&wcid->non_aql_packets); - if (pending < 0) - atomic_cmpxchg(&wcid->non_aql_packets, pending, 0); - } - - rcu_read_unlock(); + pending = atomic_dec_return(&wcid->non_aql_packets); + if (pending < 0) + atomic_cmpxchg(&wcid->non_aql_packets, pending, 0); } -void mt76_tx_complete_skb(struct mt76_dev *dev, u16 wcid_idx, struct sk_buff *skb) +void __mt76_tx_complete_skb(struct mt76_dev *dev, u16 wcid_idx, struct sk_buff *skb, + struct list_head *free_list) { + struct ieee80211_tx_status status = { + .skb = skb, + .free_list = free_list, + }; + struct mt76_wcid *wcid = NULL; struct ieee80211_hw *hw; struct sk_buff_head list; - mt76_tx_check_non_aql(dev, wcid_idx, skb); + rcu_read_lock(); + + if (wcid_idx < ARRAY_SIZE(dev->wcid)) + wcid = rcu_dereference(dev->wcid[wcid_idx]); + + mt76_tx_check_non_aql(dev, wcid, skb); #ifdef CONFIG_NL80211_TESTMODE if (mt76_is_testmode_skb(dev, skb, &hw)) { @@ -214,21 +222,25 @@ void mt76_tx_complete_skb(struct mt76_dev *dev, u16 wcid_idx, struct sk_buff *sk wake_up(&dev->tx_wait); dev_kfree_skb_any(skb); - return; + goto out; } #endif if (!skb->prev) { hw = mt76_tx_status_get_hw(dev, skb); - ieee80211_free_txskb(hw, skb); - return; + status.sta = wcid_to_sta(wcid); + ieee80211_tx_status_ext(hw, &status); + goto out; } mt76_tx_status_lock(dev, &list); __mt76_tx_status_skb_done(dev, skb, MT_TX_CB_DMA_DONE, &list); mt76_tx_status_unlock(dev, &list); + +out: + rcu_read_unlock(); } -EXPORT_SYMBOL_GPL(mt76_tx_complete_skb); +EXPORT_SYMBOL_GPL(__mt76_tx_complete_skb); static int __mt76_tx_queue_skb(struct mt76_phy *phy, int qid, struct sk_buff *skb, @@ -244,11 +256,15 @@ __mt76_tx_queue_skb(struct mt76_phy *phy, int qid, struct sk_buff *skb, non_aql = !info->tx_time_est; idx = dev->queue_ops->tx_queue_skb(dev, q, skb, wcid, sta); - if (idx < 0 || !sta || !non_aql) + if (idx < 0 || !sta) return idx; wcid = (struct mt76_wcid *)sta->drv_priv; q->entry[idx].wcid = wcid->idx; + + if (!non_aql) + return idx; + pending = atomic_inc_return(&wcid->non_aql_packets); if (stop && pending >= MT_MAX_NON_AQL_PKT) *stop = true; @@ -285,7 +301,7 @@ mt76_tx(struct mt76_phy *phy, struct ieee80211_sta *sta, skb_set_queue_mapping(skb, qid); } - if (!(wcid->tx_info & MT_WCID_TX_INFO_SET)) + if (wcid && !(wcid->tx_info & MT_WCID_TX_INFO_SET)) ieee80211_get_tx_rates(info->control.vif, sta, skb, info->control.rates, 1); diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c index 30bc54e98c58..1e9f60bb811a 100644 --- a/drivers/net/wireless/mediatek/mt76/usb.c +++ b/drivers/net/wireless/mediatek/mt76/usb.c @@ -925,6 +925,7 @@ mt76u_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q, q->head = (q->head + 1) % q->ndesc; q->entry[idx].skb = tx_info.skb; + q->entry[idx].wcid = 0xffff; q->queued++; return idx; diff --git a/drivers/net/wireless/mediatek/mt7601u/usb.c b/drivers/net/wireless/mediatek/mt7601u/usb.c index 6bcc4a13ae6c..cc772045d526 100644 --- a/drivers/net/wireless/mediatek/mt7601u/usb.c +++ b/drivers/net/wireless/mediatek/mt7601u/usb.c @@ -26,6 +26,7 @@ static const struct usb_device_id mt7601u_device_table[] = { { USB_DEVICE(0x2717, 0x4106) }, { USB_DEVICE(0x2955, 0x0001) }, { USB_DEVICE(0x2955, 0x1001) }, + { USB_DEVICE(0x2955, 0x1003) }, { USB_DEVICE(0x2a5f, 0x1000) }, { USB_DEVICE(0x7392, 0x7710) }, { 0, } diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c index 1472e9843896..8e9aaf03a6fa 100644 --- a/drivers/net/wireless/microchip/wilc1000/spi.c +++ b/drivers/net/wireless/microchip/wilc1000/spi.c @@ -164,7 +164,7 @@ static int wilc_bus_probe(struct spi_device *spi) wilc->bus_data = spi_priv; wilc->dev_irq_num = spi->irq; - wilc->rtc_clk = devm_clk_get(&spi->dev, "rtc_clk"); + wilc->rtc_clk = devm_clk_get(&spi->dev, "rtc"); if (PTR_ERR_OR_ZERO(wilc->rtc_clk) == -EPROBE_DEFER) { kfree(spi_priv); return -EPROBE_DEFER; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index 5264b0a1f098..deddb0afd312 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -1037,7 +1037,7 @@ void rt2800_txdone_entry(struct queue_entry *entry, u32 status, __le32 *txwi, * FIXME: if we do not find matching entry, we tell that frame was * posted without any retries. We need to find a way to fix that * and provide retry count. - */ + */ if (unlikely((aggr == 1 && ampdu == 0 && real_mcs != mcs)) || !match) { rt2800_rate_from_status(skbdesc, status, rt2x00dev->curr_band); mcs = real_mcs; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c index d4d389e8f1b4..fb1d31b2d52a 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c @@ -446,8 +446,9 @@ static void rt2x00queue_create_tx_descriptor(struct rt2x00_dev *rt2x00dev, * Beacons and probe responses require the tsf timestamp * to be inserted into the frame. */ - if (ieee80211_is_beacon(hdr->frame_control) || - ieee80211_is_probe_resp(hdr->frame_control)) + if ((ieee80211_is_beacon(hdr->frame_control) || + ieee80211_is_probe_resp(hdr->frame_control)) && + !(tx_info->flags & IEEE80211_TX_CTL_INJECTED)) __set_bit(ENTRY_TXD_REQ_TIMESTAMP, &txdesc->flags); if ((tx_info->flags & IEEE80211_TX_CTL_FIRST_FRAGMENT) && diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h index d1a566cc0c9e..01735776345a 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu.h @@ -853,15 +853,10 @@ struct rtl8192eu_efuse { u8 usb_optional_function; u8 res9[2]; u8 mac_addr[ETH_ALEN]; /* 0xd7 */ - u8 res10[2]; - u8 vendor_name[7]; - u8 res11[2]; - u8 device_name[0x0b]; /* 0xe8 */ - u8 res12[2]; - u8 serial[0x0b]; /* 0xf5 */ - u8 res13[0x30]; + u8 device_info[80]; + u8 res11[3]; u8 unknown[0x0d]; /* 0x130 */ - u8 res14[0xc3]; + u8 res12[0xc3]; }; struct rtl8xxxu_reg8val { diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c index cfe2dfdae928..b06508d0cdf8 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c @@ -554,9 +554,43 @@ rtl8192e_set_tx_power(struct rtl8xxxu_priv *priv, int channel, bool ht40) } } +static void rtl8192eu_log_next_device_info(struct rtl8xxxu_priv *priv, + char *record_name, + char *device_info, + unsigned int *record_offset) +{ + char *record = device_info + *record_offset; + + /* A record is [ total length | 0x03 | value ] */ + unsigned char l = record[0]; + + /* + * The whole device info section seems to be 80 characters, make sure + * we don't read further. + */ + if (*record_offset + l > 80) { + dev_warn(&priv->udev->dev, + "invalid record length %d while parsing \"%s\" at offset %u.\n", + l, record_name, *record_offset); + return; + } + + if (l >= 2) { + char value[80]; + + memcpy(value, &record[2], l - 2); + value[l - 2] = '\0'; + dev_info(&priv->udev->dev, "%s: %s\n", record_name, value); + *record_offset = *record_offset + l; + } else { + dev_info(&priv->udev->dev, "%s not available.\n", record_name); + } +} + static int rtl8192eu_parse_efuse(struct rtl8xxxu_priv *priv) { struct rtl8192eu_efuse *efuse = &priv->efuse_wifi.efuse8192eu; + unsigned int record_offset; int i; if (efuse->rtl_id != cpu_to_le16(0x8129)) @@ -604,12 +638,25 @@ static int rtl8192eu_parse_efuse(struct rtl8xxxu_priv *priv) priv->has_xtalk = 1; priv->xtalk = priv->efuse_wifi.efuse8192eu.xtal_k & 0x3f; - dev_info(&priv->udev->dev, "Vendor: %.7s\n", efuse->vendor_name); - dev_info(&priv->udev->dev, "Product: %.11s\n", efuse->device_name); - if (memchr_inv(efuse->serial, 0xff, 11)) - dev_info(&priv->udev->dev, "Serial: %.11s\n", efuse->serial); - else - dev_info(&priv->udev->dev, "Serial not available.\n"); + /* + * device_info section seems to be laid out as records + * [ total length | 0x03 | value ] so: + * - vendor length + 2 + * - 0x03 + * - vendor string (not null terminated) + * - product length + 2 + * - 0x03 + * - product string (not null terminated) + * Then there is one or 2 0x00 on all the 4 devices I own or found + * dumped online. + * As previous version of the code handled an optional serial + * string, I now assume there may be a third record if the + * length is not 0. + */ + record_offset = 0; + rtl8192eu_log_next_device_info(priv, "Vendor", efuse->device_info, &record_offset); + rtl8192eu_log_next_device_info(priv, "Product", efuse->device_info, &record_offset); + rtl8192eu_log_next_device_info(priv, "Serial", efuse->device_info, &record_offset); if (rtl8xxxu_debug & RTL8XXXU_DEBUG_EFUSE) { unsigned char *raw = priv->efuse_wifi.raw; diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c index 9ff09cf7eb62..ac1061caacd6 100644 --- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c +++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_core.c @@ -5554,6 +5554,11 @@ int rtl8xxxu_parse_rxdesc16(struct rtl8xxxu_priv *priv, struct sk_buff *skb) urb_len = skb->len; pkt_cnt = 0; + if (urb_len < sizeof(struct rtl8xxxu_rxdesc16)) { + kfree_skb(skb); + return RX_TYPE_ERROR; + } + do { rx_desc = (struct rtl8xxxu_rxdesc16 *)skb->data; _rx_desc_le = (__le32 *)skb->data; @@ -5581,7 +5586,7 @@ int rtl8xxxu_parse_rxdesc16(struct rtl8xxxu_priv *priv, struct sk_buff *skb) * at least cover the rx descriptor */ if (pkt_cnt > 1 && - urb_len > (pkt_offset + sizeof(struct rtl8xxxu_rxdesc16))) + urb_len >= (pkt_offset + sizeof(struct rtl8xxxu_rxdesc16))) next_skb = skb_clone(skb, GFP_ATOMIC); rx_status = IEEE80211_SKB_RXCB(skb); @@ -5627,7 +5632,9 @@ int rtl8xxxu_parse_rxdesc16(struct rtl8xxxu_priv *priv, struct sk_buff *skb) pkt_cnt--; urb_len -= pkt_offset; - } while (skb && urb_len > 0 && pkt_cnt > 0); + next_skb = NULL; + } while (skb && pkt_cnt > 0 && + urb_len >= sizeof(struct rtl8xxxu_rxdesc16)); return RX_TYPE_DATA_PKT; } diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.c index 447caa4aad32..c5b8df58d4a2 100644 --- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.c +++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8821a2ant.c @@ -1721,10 +1721,6 @@ static void btc8821a2ant_tdma_duration_adjust(struct btc_coexist *btcoexist, btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 14); coex_dm->ps_tdma_du_adj_type = 14; - } else if (max_interval == 3) { - btc8821a2ant_ps_tdma(btcoexist, - NORMAL_EXEC, true, 15); - coex_dm->ps_tdma_du_adj_type = 15; } else { btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 15); @@ -1739,10 +1735,6 @@ static void btc8821a2ant_tdma_duration_adjust(struct btc_coexist *btcoexist, btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 10); coex_dm->ps_tdma_du_adj_type = 10; - } else if (max_interval == 3) { - btc8821a2ant_ps_tdma(btcoexist, - NORMAL_EXEC, true, 11); - coex_dm->ps_tdma_du_adj_type = 11; } else { btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 11); @@ -1759,10 +1751,6 @@ static void btc8821a2ant_tdma_duration_adjust(struct btc_coexist *btcoexist, btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 6); coex_dm->ps_tdma_du_adj_type = 6; - } else if (max_interval == 3) { - btc8821a2ant_ps_tdma(btcoexist, - NORMAL_EXEC, true, 7); - coex_dm->ps_tdma_du_adj_type = 7; } else { btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 7); @@ -1777,10 +1765,6 @@ static void btc8821a2ant_tdma_duration_adjust(struct btc_coexist *btcoexist, btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 2); coex_dm->ps_tdma_du_adj_type = 2; - } else if (max_interval == 3) { - btc8821a2ant_ps_tdma(btcoexist, - NORMAL_EXEC, true, 3); - coex_dm->ps_tdma_du_adj_type = 3; } else { btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 3); @@ -2810,6 +2794,7 @@ static void btc8821a2ant_action_a2dp(struct btc_coexist *btcoexist) 0x4); } + /* preserve identical branches for further fine-tuning */ if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) || (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) { btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 23); @@ -2944,6 +2929,7 @@ static void btc8821a2ant_action_pan_edr(struct btc_coexist *btcoexist) 0x4); } + /* preserve identical branches for further fine-tuning */ if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) || (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 26); @@ -3132,6 +3118,7 @@ static void btc8821a2ant_action_pan_edr_hid(struct btc_coexist *btcoexist) btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw); + /* preserve identical branches for further fine-tuning */ if (wifi_bw == BTC_WIFI_BW_LEGACY) { /* for HID at 11b/g mode */ btc8821a2ant_coex_table(btcoexist, NORMAL_EXEC, 0x55ff55ff, @@ -3321,6 +3308,7 @@ static void btc8821a2ant_action_hid_a2dp(struct btc_coexist *btcoexist) 0x4); } + /* preserve identical branches for further fine-tuning */ if ((bt_rssi_state == BTC_RSSI_STATE_HIGH) || (bt_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) { btc8821a2ant_ps_tdma(btcoexist, NORMAL_EXEC, true, 23); diff --git a/drivers/net/wireless/realtek/rtlwifi/cam.c b/drivers/net/wireless/realtek/rtlwifi/cam.c index 7aa28da39409..7a0355dc6bab 100644 --- a/drivers/net/wireless/realtek/rtlwifi/cam.c +++ b/drivers/net/wireless/realtek/rtlwifi/cam.c @@ -167,7 +167,7 @@ void rtl_cam_mark_invalid(struct ieee80211_hw *hw, u8 uc_index) u32 ul_command; u32 ul_content; - u32 ul_enc_algo = rtlpriv->cfg->maps[SEC_CAM_AES]; + u32 ul_enc_algo; switch (rtlpriv->sec.pairwise_enc_algorithm) { case WEP40_ENCRYPTION: diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/mac.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/mac.c index 8d2c6d8d32d9..4ff0d4118193 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/mac.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/mac.c @@ -112,7 +112,7 @@ void rtl92c_read_chip_version(struct ieee80211_hw *hw) } /** - * writeLLT - LLT table write access + * rtl92c_llt_write - LLT table write access * @hw: Pointer to the ieee80211_hw structure. * @address: LLT logical address. * @data: LLT data content @@ -144,7 +144,7 @@ bool rtl92c_llt_write(struct ieee80211_hw *hw, u32 address, u32 data) } /** - * rtl92c_init_LLT_table - Init LLT table + * rtl92c_init_llt_table - Init LLT table * @hw: Pointer to the ieee80211_hw structure. * @boundary: Page boundary. * diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c index 68ec009ea157..76dd881ef9bb 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c @@ -2574,7 +2574,7 @@ static void _rtl92d_phy_lc_calibrate_sw(struct ieee80211_hw *hw, bool is2t) RTPRINT(rtlpriv, FINIT, INIT_IQK, "path-B / 2.4G LCK\n"); } - memset(&curvecount_val[0], 0, CV_CURVE_CNT * 2); + memset(curvecount_val, 0, sizeof(curvecount_val)); /* Set LC calibration off */ rtl_set_rfreg(hw, (enum radio_path)index, RF_CHNLBW, 0x08000, 0x0); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c index 38034102aacb..e474b4ec17f3 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/trx.c @@ -513,7 +513,7 @@ void rtl92se_tx_fill_cmddesc(struct ieee80211_hw *hw, u8 *pdesc8, /* This bit indicate this packet is used for FW download. */ if (tcb_desc->cmd_or_init == DESC_PACKET_TYPE_INIT) { - /* For firmware downlaod we only need to set LINIP */ + /* For firmware download we only need to set LINIP */ set_tx_desc_linip(pdesc, tcb_desc->last_inipkt); /* 92SE must set as 1 for firmware download HW DMA error */ diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c index f8a1de6e9849..c98f2216734f 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c @@ -915,7 +915,7 @@ int rtl8723e_hw_init(struct ieee80211_hw *hw) struct rtl_phy *rtlphy = &(rtlpriv->phy); struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw)); struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); - bool rtstatus = true; + bool rtstatus; int err; u8 tmp_u1b; unsigned long flags; diff --git a/drivers/net/wireless/realtek/rtw88/coex.c b/drivers/net/wireless/realtek/rtw88/coex.c index cedbf3825848..2551e228b581 100644 --- a/drivers/net/wireless/realtek/rtw88/coex.c +++ b/drivers/net/wireless/realtek/rtw88/coex.c @@ -591,8 +591,10 @@ void rtw_coex_info_response(struct rtw_dev *rtwdev, struct sk_buff *skb) struct rtw_coex *coex = &rtwdev->coex; u8 *payload = get_payload_from_coex_resp(skb); - if (payload[0] != COEX_RESP_ACK_BY_WL_FW) + if (payload[0] != COEX_RESP_ACK_BY_WL_FW) { + dev_kfree_skb_any(skb); return; + } skb_queue_tail(&coex->queue, skb); wake_up(&coex->wait); @@ -630,20 +632,16 @@ static bool rtw_coex_get_bt_scan_type(struct rtw_dev *rtwdev, u8 *scan_type) struct rtw_coex_info_req req = {0}; struct sk_buff *skb; u8 *payload; - bool ret = false; req.op_code = BT_MP_INFO_OP_SCAN_TYPE; skb = rtw_coex_info_request(rtwdev, &req); if (!skb) - goto out; + return false; payload = get_payload_from_coex_resp(skb); *scan_type = GET_COEX_RESP_BT_SCAN_TYPE(payload); dev_kfree_skb_any(skb); - ret = true; - -out: - return ret; + return true; } static bool rtw_coex_set_lna_constrain_level(struct rtw_dev *rtwdev, @@ -651,19 +649,15 @@ static bool rtw_coex_set_lna_constrain_level(struct rtw_dev *rtwdev, { struct rtw_coex_info_req req = {0}; struct sk_buff *skb; - bool ret = false; req.op_code = BT_MP_INFO_OP_LNA_CONSTRAINT; req.para1 = lna_constrain_level; skb = rtw_coex_info_request(rtwdev, &req); if (!skb) - goto out; + return false; dev_kfree_skb_any(skb); - ret = true; - -out: - return ret; + return true; } #define case_BTSTATUS(src) \ @@ -3523,6 +3517,7 @@ static bool rtw_coex_get_bt_reg(struct rtw_dev *rtwdev, payload = get_payload_from_coex_resp(skb); *val = GET_COEX_RESP_BT_REG_VAL(payload); + dev_kfree_skb_any(skb); return true; } @@ -3533,19 +3528,17 @@ static bool rtw_coex_get_bt_patch_version(struct rtw_dev *rtwdev, struct rtw_coex_info_req req = {0}; struct sk_buff *skb; u8 *payload; - bool ret = false; req.op_code = BT_MP_INFO_OP_PATCH_VER; skb = rtw_coex_info_request(rtwdev, &req); if (!skb) - goto out; + return false; payload = get_payload_from_coex_resp(skb); *patch_version = GET_COEX_RESP_BT_PATCH_VER(payload); - ret = true; + dev_kfree_skb_any(skb); -out: - return ret; + return true; } static bool rtw_coex_get_bt_supported_version(struct rtw_dev *rtwdev, @@ -3554,19 +3547,17 @@ static bool rtw_coex_get_bt_supported_version(struct rtw_dev *rtwdev, struct rtw_coex_info_req req = {0}; struct sk_buff *skb; u8 *payload; - bool ret = false; req.op_code = BT_MP_INFO_OP_SUPP_VER; skb = rtw_coex_info_request(rtwdev, &req); if (!skb) - goto out; + return false; payload = get_payload_from_coex_resp(skb); *supported_version = GET_COEX_RESP_BT_SUPP_VER(payload); - ret = true; + dev_kfree_skb_any(skb); -out: - return ret; + return true; } static bool rtw_coex_get_bt_supported_feature(struct rtw_dev *rtwdev, @@ -3575,19 +3566,17 @@ static bool rtw_coex_get_bt_supported_feature(struct rtw_dev *rtwdev, struct rtw_coex_info_req req = {0}; struct sk_buff *skb; u8 *payload; - bool ret = false; req.op_code = BT_MP_INFO_OP_SUPP_FEAT; skb = rtw_coex_info_request(rtwdev, &req); if (!skb) - goto out; + return false; payload = get_payload_from_coex_resp(skb); *supported_feature = GET_COEX_RESP_BT_SUPP_FEAT(payload); - ret = true; + dev_kfree_skb_any(skb); -out: - return ret; + return true; } struct rtw_coex_sta_stat_iter_data { diff --git a/drivers/net/wireless/realtek/rtw88/debug.c b/drivers/net/wireless/realtek/rtw88/debug.c index 18ab472ea46c..dfd52cff5d02 100644 --- a/drivers/net/wireless/realtek/rtw88/debug.c +++ b/drivers/net/wireless/realtek/rtw88/debug.c @@ -11,6 +11,7 @@ #include "debug.h" #include "phy.h" #include "reg.h" +#include "ps.h" #ifdef CONFIG_RTW88_DEBUGFS @@ -847,7 +848,13 @@ static ssize_t rtw_debugfs_set_fw_crash(struct file *filp, if (!input) return -EINVAL; + if (test_bit(RTW_FLAG_RESTARTING, rtwdev->flags)) + return -EINPROGRESS; + + mutex_lock(&rtwdev->mutex); + rtw_leave_lps_deep(rtwdev); rtw_write8(rtwdev, REG_HRCV_MSG, 1); + mutex_unlock(&rtwdev->mutex); return count; } diff --git a/drivers/net/wireless/realtek/rtw88/debug.h b/drivers/net/wireless/realtek/rtw88/debug.h index c8efd1900a34..0dd3f9a88c8d 100644 --- a/drivers/net/wireless/realtek/rtw88/debug.h +++ b/drivers/net/wireless/realtek/rtw88/debug.h @@ -20,6 +20,7 @@ enum rtw_debug_mask { RTW_DBG_BF = 0x00000800, RTW_DBG_WOW = 0x00001000, RTW_DBG_CFO = 0x00002000, + RTW_DBG_PATH_DIV = 0x00004000, RTW_DBG_ALL = 0xffffffff }; diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c index ea2cd4db1d3c..3bfa5ecc0053 100644 --- a/drivers/net/wireless/realtek/rtw88/fw.c +++ b/drivers/net/wireless/realtek/rtw88/fw.c @@ -127,6 +127,62 @@ static void rtw_fw_ra_report_handle(struct rtw_dev *rtwdev, u8 *payload, rtw_iterate_stas_atomic(rtwdev, rtw_fw_ra_report_iter, &ra_data); } +struct rtw_beacon_filter_iter_data { + struct rtw_dev *rtwdev; + u8 *payload; +}; + +static void rtw_fw_bcn_filter_notify_vif_iter(void *data, u8 *mac, + struct ieee80211_vif *vif) +{ + struct rtw_beacon_filter_iter_data *iter_data = data; + struct rtw_dev *rtwdev = iter_data->rtwdev; + u8 *payload = iter_data->payload; + u8 type = GET_BCN_FILTER_NOTIFY_TYPE(payload); + u8 event = GET_BCN_FILTER_NOTIFY_EVENT(payload); + s8 sig = (s8)GET_BCN_FILTER_NOTIFY_RSSI(payload); + + switch (type) { + case BCN_FILTER_NOTIFY_SIGNAL_CHANGE: + event = event ? NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH : + NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW; + ieee80211_cqm_rssi_notify(vif, event, sig, GFP_KERNEL); + break; + case BCN_FILTER_CONNECTION_LOSS: + ieee80211_connection_loss(vif); + break; + case BCN_FILTER_CONNECTED: + rtwdev->beacon_loss = false; + break; + case BCN_FILTER_NOTIFY_BEACON_LOSS: + rtwdev->beacon_loss = true; + rtw_leave_lps(rtwdev); + break; + } +} + +static void rtw_fw_bcn_filter_notify(struct rtw_dev *rtwdev, u8 *payload, + u8 length) +{ + struct rtw_beacon_filter_iter_data dev_iter_data; + + dev_iter_data.rtwdev = rtwdev; + dev_iter_data.payload = payload; + rtw_iterate_vifs(rtwdev, rtw_fw_bcn_filter_notify_vif_iter, + &dev_iter_data); +} + +static void rtw_fw_scan_result(struct rtw_dev *rtwdev, u8 *payload, + u8 length) +{ + struct rtw_dm_info *dm_info = &rtwdev->dm_info; + + dm_info->scan_density = payload[0]; + + rtw_dbg(rtwdev, RTW_DBG_FW, "scan.density = %x\n", + dm_info->scan_density); +} + void rtw_fw_c2h_cmd_handle(struct rtw_dev *rtwdev, struct sk_buff *skb) { struct rtw_c2h_cmd *c2h; @@ -152,6 +208,9 @@ void rtw_fw_c2h_cmd_handle(struct rtw_dev *rtwdev, struct sk_buff *skb) case C2H_WLAN_INFO: rtw_coex_wl_fwdbginfo_notify(rtwdev, c2h->payload, len); break; + case C2H_BCN_FILTER_NOTIFY: + rtw_fw_bcn_filter_notify(rtwdev, c2h->payload, len); + break; case C2H_HALMAC: rtw_fw_c2h_cmd_handle_ext(rtwdev, skb); break; @@ -186,6 +245,12 @@ void rtw_fw_c2h_cmd_rx_irqsafe(struct rtw_dev *rtwdev, u32 pkt_offset, break; case C2H_WLAN_RFON: complete(&rtwdev->lps_leave_check); + dev_kfree_skb_any(skb); + break; + case C2H_SCAN_RESULT: + complete(&rtwdev->fw_scan_density); + rtw_fw_scan_result(rtwdev, c2h->payload, len); + dev_kfree_skb_any(skb); break; default: /* pass offset for further operation */ @@ -527,6 +592,45 @@ void rtw_fw_update_wl_phy_info(struct rtw_dev *rtwdev) rtw_fw_send_h2c_command(rtwdev, h2c_pkt); } +void rtw_fw_beacon_filter_config(struct rtw_dev *rtwdev, bool connect, + struct ieee80211_vif *vif) +{ + struct ieee80211_bss_conf *bss_conf = &vif->bss_conf; + struct ieee80211_sta *sta = ieee80211_find_sta(vif, bss_conf->bssid); + static const u8 rssi_min = 0, rssi_max = 100, rssi_offset = 100; + struct rtw_sta_info *si = + sta ? (struct rtw_sta_info *)sta->drv_priv : NULL; + s32 threshold = bss_conf->cqm_rssi_thold + rssi_offset; + u8 h2c_pkt[H2C_PKT_SIZE] = {0}; + + if (!rtw_fw_feature_check(&rtwdev->fw, FW_FEATURE_BCN_FILTER) || !si) + return; + + if (!connect) { + SET_H2C_CMD_ID_CLASS(h2c_pkt, H2C_CMD_BCN_FILTER_OFFLOAD_P1); + SET_BCN_FILTER_OFFLOAD_P1_ENABLE(h2c_pkt, connect); + rtw_fw_send_h2c_command(rtwdev, h2c_pkt); + + return; + } + SET_H2C_CMD_ID_CLASS(h2c_pkt, H2C_CMD_BCN_FILTER_OFFLOAD_P0); + ether_addr_copy(&h2c_pkt[1], bss_conf->bssid); + rtw_fw_send_h2c_command(rtwdev, h2c_pkt); + + memset(h2c_pkt, 0, sizeof(h2c_pkt)); + threshold = clamp_t(s32, threshold, rssi_min, rssi_max); + SET_H2C_CMD_ID_CLASS(h2c_pkt, H2C_CMD_BCN_FILTER_OFFLOAD_P1); + SET_BCN_FILTER_OFFLOAD_P1_ENABLE(h2c_pkt, connect); + SET_BCN_FILTER_OFFLOAD_P1_OFFLOAD_MODE(h2c_pkt, + BCN_FILTER_OFFLOAD_MODE_DEFAULT); + SET_BCN_FILTER_OFFLOAD_P1_THRESHOLD(h2c_pkt, (u8)threshold); + SET_BCN_FILTER_OFFLOAD_P1_BCN_LOSS_CNT(h2c_pkt, BCN_LOSS_CNT); + SET_BCN_FILTER_OFFLOAD_P1_MACID(h2c_pkt, si->mac_id); + SET_BCN_FILTER_OFFLOAD_P1_HYST(h2c_pkt, bss_conf->cqm_rssi_hyst); + SET_BCN_FILTER_OFFLOAD_P1_BCN_INTERVAL(h2c_pkt, bss_conf->beacon_int); + rtw_fw_send_h2c_command(rtwdev, h2c_pkt); +} + void rtw_fw_set_pwr_mode(struct rtw_dev *rtwdev) { struct rtw_lps_conf *conf = &rtwdev->lps_conf; @@ -1613,3 +1717,13 @@ void rtw_fw_channel_switch(struct rtw_dev *rtwdev, bool enable) rtw_fw_send_h2c_packet(rtwdev, h2c_pkt); } + +void rtw_fw_scan_notify(struct rtw_dev *rtwdev, bool start) +{ + u8 h2c_pkt[H2C_PKT_SIZE] = {0}; + + SET_H2C_CMD_ID_CLASS(h2c_pkt, H2C_CMD_SCAN); + SET_SCAN_START(h2c_pkt, start); + + rtw_fw_send_h2c_command(rtwdev, h2c_pkt); +} diff --git a/drivers/net/wireless/realtek/rtw88/fw.h b/drivers/net/wireless/realtek/rtw88/fw.h index 7c5b1d75e26f..a8a7162fbe64 100644 --- a/drivers/net/wireless/realtek/rtw88/fw.h +++ b/drivers/net/wireless/realtek/rtw88/fw.h @@ -24,6 +24,14 @@ #define DLFW_BLK_SIZE_LEGACY 4 #define FW_START_ADDR_LEGACY 0x1000 +#define BCN_LOSS_CNT 10 +#define BCN_FILTER_NOTIFY_SIGNAL_CHANGE 0 +#define BCN_FILTER_CONNECTION_LOSS 1 +#define BCN_FILTER_CONNECTED 2 +#define BCN_FILTER_NOTIFY_BEACON_LOSS 3 + +#define SCAN_NOTIFY_TIMEOUT msecs_to_jiffies(10) + enum rtw_c2h_cmd_id { C2H_CCX_TX_RPT = 0x03, C2H_BT_INFO = 0x09, @@ -32,6 +40,8 @@ enum rtw_c2h_cmd_id { C2H_HW_FEATURE_REPORT = 0x19, C2H_WLAN_INFO = 0x27, C2H_WLAN_RFON = 0x32, + C2H_BCN_FILTER_NOTIFY = 0x36, + C2H_SCAN_RESULT = 0x38, C2H_HW_FEATURE_DUMP = 0xfd, C2H_HALMAC = 0xff, }; @@ -78,9 +88,20 @@ enum rtw_fw_feature { FW_FEATURE_LPS_C2H = BIT(1), FW_FEATURE_LCLK = BIT(2), FW_FEATURE_PG = BIT(3), + FW_FEATURE_BCN_FILTER = BIT(5), + FW_FEATURE_NOTIFY_SCAN = BIT(6), FW_FEATURE_MAX = BIT(31), }; +enum rtw_beacon_filter_offload_mode { + BCN_FILTER_OFFLOAD_MODE_0 = 0, + BCN_FILTER_OFFLOAD_MODE_1, + BCN_FILTER_OFFLOAD_MODE_2, + BCN_FILTER_OFFLOAD_MODE_3, + + BCN_FILTER_OFFLOAD_MODE_DEFAULT = BCN_FILTER_OFFLOAD_MODE_1, +}; + struct rtw_coex_info_req { u8 seq; u8 op_code; @@ -237,6 +258,10 @@ struct rtw_fw_hdr_legacy { #define GET_RA_REPORT_BW(c2h_payload) (c2h_payload[6]) #define GET_RA_REPORT_MACID(c2h_payload) (c2h_payload[1]) +#define GET_BCN_FILTER_NOTIFY_TYPE(c2h_payload) (c2h_payload[1] & 0xf) +#define GET_BCN_FILTER_NOTIFY_EVENT(c2h_payload) (c2h_payload[1] & 0x10) +#define GET_BCN_FILTER_NOTIFY_RSSI(c2h_payload) (c2h_payload[2] - 100) + /* PKT H2C */ #define H2C_PKT_CMD_ID 0xFF #define H2C_PKT_CATEGORY 0x01 @@ -345,7 +370,10 @@ static inline void rtw_h2c_pkt_set_header(u8 *h2c_pkt, u8 sub_id) #define H2C_CMD_LPS_PG_INFO 0x2b #define H2C_CMD_RA_INFO 0x40 #define H2C_CMD_RSSI_MONITOR 0x42 +#define H2C_CMD_BCN_FILTER_OFFLOAD_P0 0x56 +#define H2C_CMD_BCN_FILTER_OFFLOAD_P1 0x57 #define H2C_CMD_WL_PHY_INFO 0x58 +#define H2C_CMD_SCAN 0x59 #define H2C_CMD_COEX_TDMA_TYPE 0x60 #define H2C_CMD_QUERY_BT_INFO 0x61 @@ -381,6 +409,23 @@ static inline void rtw_h2c_pkt_set_header(u8 *h2c_pkt, u8 sub_id) le32p_replace_bits((__le32 *)(h2c_pkt) + 0x01, value, GENMASK(15, 8)) #define SET_WL_PHY_INFO_RX_EVM(h2c_pkt, value) \ le32p_replace_bits((__le32 *)(h2c_pkt) + 0x01, value, GENMASK(23, 16)) +#define SET_BCN_FILTER_OFFLOAD_P1_MACID(h2c_pkt, value) \ + le32p_replace_bits((__le32 *)(h2c_pkt) + 0x00, value, GENMASK(15, 8)) +#define SET_BCN_FILTER_OFFLOAD_P1_ENABLE(h2c_pkt, value) \ + le32p_replace_bits((__le32 *)(h2c_pkt) + 0x00, value, BIT(16)) +#define SET_BCN_FILTER_OFFLOAD_P1_HYST(h2c_pkt, value) \ + le32p_replace_bits((__le32 *)(h2c_pkt) + 0x00, value, GENMASK(20, 17)) +#define SET_BCN_FILTER_OFFLOAD_P1_OFFLOAD_MODE(h2c_pkt, value) \ + le32p_replace_bits((__le32 *)(h2c_pkt) + 0x00, value, GENMASK(23, 21)) +#define SET_BCN_FILTER_OFFLOAD_P1_THRESHOLD(h2c_pkt, value) \ + le32p_replace_bits((__le32 *)(h2c_pkt) + 0x00, value, GENMASK(31, 24)) +#define SET_BCN_FILTER_OFFLOAD_P1_BCN_LOSS_CNT(h2c_pkt, value) \ + le32p_replace_bits((__le32 *)(h2c_pkt) + 0x01, value, GENMASK(3, 0)) +#define SET_BCN_FILTER_OFFLOAD_P1_BCN_INTERVAL(h2c_pkt, value) \ + le32p_replace_bits((__le32 *)(h2c_pkt) + 0x01, value, GENMASK(13, 4)) + +#define SET_SCAN_START(h2c_pkt, value) \ + le32p_replace_bits((__le32 *)(h2c_pkt) + 0x00, value, BIT(8)) #define SET_PWR_MODE_SET_MODE(h2c_pkt, value) \ le32p_replace_bits((__le32 *)(h2c_pkt) + 0x00, value, GENMASK(14, 8)) @@ -554,6 +599,12 @@ static inline struct rtw_c2h_cmd *get_c2h_from_skb(struct sk_buff *skb) return (struct rtw_c2h_cmd *)(skb->data + pkt_offset); } +static inline bool rtw_fw_feature_check(struct rtw_fw_state *fw, + enum rtw_fw_feature feature) +{ + return !!(fw->feature & feature); +} + void rtw_fw_c2h_cmd_rx_irqsafe(struct rtw_dev *rtwdev, u32 pkt_offset, struct sk_buff *skb); void rtw_fw_c2h_cmd_handle(struct rtw_dev *rtwdev, struct sk_buff *skb); @@ -577,6 +628,8 @@ void rtw_fw_send_rssi_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si); void rtw_fw_send_ra_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si); void rtw_fw_media_status_report(struct rtw_dev *rtwdev, u8 mac_id, bool conn); void rtw_fw_update_wl_phy_info(struct rtw_dev *rtwdev); +void rtw_fw_beacon_filter_config(struct rtw_dev *rtwdev, bool connect, + struct ieee80211_vif *vif); int rtw_fw_write_data_rsvd_page(struct rtw_dev *rtwdev, u16 pg_addr, u8 *buf, u32 size); void rtw_remove_rsvd_page(struct rtw_dev *rtwdev, @@ -607,5 +660,5 @@ void rtw_fw_h2c_cmd_dbg(struct rtw_dev *rtwdev, u8 *h2c); void rtw_fw_c2h_cmd_isr(struct rtw_dev *rtwdev); int rtw_fw_dump_fifo(struct rtw_dev *rtwdev, u8 fifo_sel, u32 addr, u32 size, u32 *buffer); - +void rtw_fw_scan_notify(struct rtw_dev *rtwdev, bool start); #endif diff --git a/drivers/net/wireless/realtek/rtw88/mac80211.c b/drivers/net/wireless/realtek/rtw88/mac80211.c index 333df6b38113..6f5629852416 100644 --- a/drivers/net/wireless/realtek/rtw88/mac80211.c +++ b/drivers/net/wireless/realtek/rtw88/mac80211.c @@ -153,6 +153,9 @@ static int rtw_ops_add_interface(struct ieee80211_hw *hw, u8 port = 0; u8 bcn_ctrl = 0; + if (rtw_fw_feature_check(&rtwdev->fw, FW_FEATURE_BCN_FILTER)) + vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER | + IEEE80211_VIF_SUPPORTS_CQM_RSSI; rtwvif->port = port; rtwvif->stats.tx_unicast = 0; rtwvif->stats.rx_unicast = 0; @@ -399,6 +402,8 @@ static void rtw_ops_bss_info_changed(struct ieee80211_hw *hw, rtw_write32_clr(rtwdev, REG_FWHW_TXQ_CTRL, BIT_EN_BCNQ_DL); } + if (changed & BSS_CHANGED_CQM) + rtw_fw_beacon_filter_config(rtwdev, true, vif); if (changed & BSS_CHANGED_MU_GROUPS) rtw_chip_set_gid_table(rtwdev, vif, conf); @@ -450,6 +455,7 @@ static int rtw_ops_sta_remove(struct ieee80211_hw *hw, { struct rtw_dev *rtwdev = hw->priv; + rtw_fw_beacon_filter_config(rtwdev, false, vif); mutex_lock(&rtwdev->mutex); rtw_sta_remove(rtwdev, sta, true); mutex_unlock(&rtwdev->mutex); @@ -599,6 +605,7 @@ static void rtw_ops_sw_scan_start(struct ieee80211_hw *hw, rtw_vif_port_config(rtwdev, rtwvif, config); rtw_coex_scan_notify(rtwdev, COEX_SCAN_START); + rtw_core_fw_scan_notify(rtwdev, true); set_bit(RTW_FLAG_DIG_DISABLE, rtwdev->flags); set_bit(RTW_FLAG_SCANNING, rtwdev->flags); @@ -618,6 +625,8 @@ static void rtw_ops_sw_scan_complete(struct ieee80211_hw *hw, clear_bit(RTW_FLAG_SCANNING, rtwdev->flags); clear_bit(RTW_FLAG_DIG_DISABLE, rtwdev->flags); + rtw_core_fw_scan_notify(rtwdev, false); + ether_addr_copy(rtwvif->mac_addr, vif->addr); config |= PORT_SET_MAC_ADDR; rtw_vif_port_config(rtwdev, rtwvif, config); @@ -629,7 +638,7 @@ static void rtw_ops_sw_scan_complete(struct ieee80211_hw *hw, static void rtw_ops_mgd_prepare_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - u16 duration) + struct ieee80211_prep_tx_info *info) { struct rtw_dev *rtwdev = hw->priv; diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index f3a3a86fa9b5..c6364837e83b 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -2,6 +2,8 @@ /* Copyright(c) 2018-2019 Realtek Corporation */ +#include + #include "main.h" #include "regd.h" #include "fw.h" @@ -239,7 +241,8 @@ static void rtw_watch_dog_work(struct work_struct *work) * get that vif and check if device is having traffic more than the * threshold. */ - if (rtwdev->ps_enabled && data.rtwvif && !ps_active) + if (rtwdev->ps_enabled && data.rtwvif && !ps_active && + !rtwdev->beacon_loss) rtw_enter_lps(rtwdev, data.rtwvif->port); rtwdev->watch_dog_cnt++; @@ -292,6 +295,7 @@ int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, rtw_fw_media_status_report(rtwdev, si->mac_id, true); rtwdev->sta_cnt++; + rtwdev->beacon_loss = false; rtw_info(rtwdev, "sta %pM joined with macid %d\n", sta->addr, si->mac_id); @@ -318,59 +322,131 @@ void rtw_sta_remove(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, sta->addr, si->mac_id); } -static bool rtw_fw_dump_crash_log(struct rtw_dev *rtwdev) +struct rtw_fwcd_hdr { + u32 item; + u32 size; + u32 padding1; + u32 padding2; +} __packed; + +static int rtw_fwcd_prep(struct rtw_dev *rtwdev) +{ + struct rtw_chip_info *chip = rtwdev->chip; + struct rtw_fwcd_desc *desc = &rtwdev->fw.fwcd_desc; + const struct rtw_fwcd_segs *segs = chip->fwcd_segs; + u32 prep_size = chip->fw_rxff_size + sizeof(struct rtw_fwcd_hdr); + u8 i; + + if (segs) { + prep_size += segs->num * sizeof(struct rtw_fwcd_hdr); + + for (i = 0; i < segs->num; i++) + prep_size += segs->segs[i]; + } + + desc->data = vmalloc(prep_size); + if (!desc->data) + return -ENOMEM; + + desc->size = prep_size; + desc->next = desc->data; + + return 0; +} + +static u8 *rtw_fwcd_next(struct rtw_dev *rtwdev, u32 item, u32 size) +{ + struct rtw_fwcd_desc *desc = &rtwdev->fw.fwcd_desc; + struct rtw_fwcd_hdr *hdr; + u8 *next; + + if (!desc->data) { + rtw_dbg(rtwdev, RTW_DBG_FW, "fwcd isn't prepared successfully\n"); + return NULL; + } + + next = desc->next + sizeof(struct rtw_fwcd_hdr); + if (next - desc->data + size > desc->size) { + rtw_dbg(rtwdev, RTW_DBG_FW, "fwcd isn't prepared enough\n"); + return NULL; + } + + hdr = (struct rtw_fwcd_hdr *)(desc->next); + hdr->item = item; + hdr->size = size; + hdr->padding1 = 0x01234567; + hdr->padding2 = 0x89abcdef; + desc->next = next + size; + + return next; +} + +static void rtw_fwcd_dump(struct rtw_dev *rtwdev) +{ + struct rtw_fwcd_desc *desc = &rtwdev->fw.fwcd_desc; + + rtw_dbg(rtwdev, RTW_DBG_FW, "dump fwcd\n"); + + /* Data will be freed after lifetime of device coredump. After calling + * dev_coredump, data is supposed to be handled by the device coredump + * framework. Note that a new dump will be discarded if a previous one + * hasn't been released yet. + */ + dev_coredumpv(rtwdev->dev, desc->data, desc->size, GFP_KERNEL); +} + +static void rtw_fwcd_free(struct rtw_dev *rtwdev, bool free_self) +{ + struct rtw_fwcd_desc *desc = &rtwdev->fw.fwcd_desc; + + if (free_self) { + rtw_dbg(rtwdev, RTW_DBG_FW, "free fwcd by self\n"); + vfree(desc->data); + } + + desc->data = NULL; + desc->next = NULL; +} + +static int rtw_fw_dump_crash_log(struct rtw_dev *rtwdev) { u32 size = rtwdev->chip->fw_rxff_size; u32 *buf; u8 seq; - bool ret = true; - buf = vmalloc(size); + buf = (u32 *)rtw_fwcd_next(rtwdev, RTW_FWCD_TLV, size); if (!buf) - goto exit; + return -ENOMEM; if (rtw_fw_dump_fifo(rtwdev, RTW_FW_FIFO_SEL_RXBUF_FW, 0, size, buf)) { rtw_dbg(rtwdev, RTW_DBG_FW, "dump fw fifo fail\n"); - goto free_buf; + return -EINVAL; } if (GET_FW_DUMP_LEN(buf) == 0) { rtw_dbg(rtwdev, RTW_DBG_FW, "fw crash dump's length is 0\n"); - goto free_buf; + return -EINVAL; } seq = GET_FW_DUMP_SEQ(buf); - if (seq > 0 && seq != (rtwdev->fw.prev_dump_seq + 1)) { + if (seq > 0) { rtw_dbg(rtwdev, RTW_DBG_FW, "fw crash dump's seq is wrong: %d\n", seq); - goto free_buf; + return -EINVAL; } - print_hex_dump(KERN_ERR, "rtw88 fw dump: ", DUMP_PREFIX_OFFSET, 16, 1, - buf, size, true); - - if (GET_FW_DUMP_MORE(buf) == 1) { - rtwdev->fw.prev_dump_seq = seq; - ret = false; - } - -free_buf: - vfree(buf); -exit: - rtw_write8(rtwdev, REG_MCU_TST_CFG, 0); - - return ret; + return 0; } int rtw_dump_fw(struct rtw_dev *rtwdev, const u32 ocp_src, u32 size, - const char *prefix_str) + u32 fwcd_item) { u32 rxff = rtwdev->chip->fw_rxff_size; u32 dump_size, done_size = 0; u8 *buf; int ret; - buf = vzalloc(size); + buf = rtw_fwcd_next(rtwdev, fwcd_item, size); if (!buf) return -ENOMEM; @@ -383,7 +459,7 @@ int rtw_dump_fw(struct rtw_dev *rtwdev, const u32 ocp_src, u32 size, rtw_err(rtwdev, "ddma fw 0x%x [+0x%x] to fw fifo fail\n", ocp_src, done_size); - goto exit; + return ret; } ret = rtw_fw_dump_fifo(rtwdev, RTW_FW_FIFO_SEL_RXBUF_FW, 0, @@ -392,24 +468,18 @@ int rtw_dump_fw(struct rtw_dev *rtwdev, const u32 ocp_src, u32 size, rtw_err(rtwdev, "dump fw 0x%x [+0x%x] from fw fifo fail\n", ocp_src, done_size); - goto exit; + return ret; } size -= dump_size; done_size += dump_size; } - print_hex_dump(KERN_ERR, prefix_str, DUMP_PREFIX_OFFSET, 16, 1, - buf, done_size, true); - -exit: - vfree(buf); - return ret; + return 0; } EXPORT_SYMBOL(rtw_dump_fw); -int rtw_dump_reg(struct rtw_dev *rtwdev, const u32 addr, const u32 size, - const char *prefix_str) +int rtw_dump_reg(struct rtw_dev *rtwdev, const u32 addr, const u32 size) { u8 *buf; u32 i; @@ -419,17 +489,13 @@ int rtw_dump_reg(struct rtw_dev *rtwdev, const u32 addr, const u32 size, return -EINVAL; } - buf = vzalloc(size); + buf = rtw_fwcd_next(rtwdev, RTW_FWCD_REG, size); if (!buf) return -ENOMEM; for (i = 0; i < size; i += 4) *(u32 *)(buf + i) = rtw_read32(rtwdev, addr + i); - print_hex_dump(KERN_ERR, prefix_str, DUMP_PREFIX_OFFSET, 16, 4, buf, - size, true); - - vfree(buf); return 0; } EXPORT_SYMBOL(rtw_dump_reg); @@ -487,20 +553,24 @@ void rtw_fw_recovery(struct rtw_dev *rtwdev) static void __fw_recovery_work(struct rtw_dev *rtwdev) { - - /* rtw_fw_dump_crash_log() returns false indicates that there are - * still more log to dump. Driver set 0x1cf[7:0] = 0x1 to tell firmware - * to dump the remaining part of the log, and firmware will trigger an - * IMR_C2HCMD interrupt to inform driver the log is ready. - */ - if (!rtw_fw_dump_crash_log(rtwdev)) { - rtw_write8(rtwdev, REG_HRCV_MSG, 1); - return; - } - rtwdev->fw.prev_dump_seq = 0; + int ret = 0; set_bit(RTW_FLAG_RESTARTING, rtwdev->flags); - rtw_chip_dump_fw_crash(rtwdev); + + ret = rtw_fwcd_prep(rtwdev); + if (ret) + goto free; + ret = rtw_fw_dump_crash_log(rtwdev); + if (ret) + goto free; + ret = rtw_chip_dump_fw_crash(rtwdev); + if (ret) + goto free; + + rtw_fwcd_dump(rtwdev); +free: + rtw_fwcd_free(rtwdev, !!ret); + rtw_write8(rtwdev, REG_MCU_TST_CFG, 0); WARN(1, "firmware crash, start reset and recover\n"); @@ -1109,11 +1179,11 @@ static enum rtw_lps_deep_mode rtw_update_lps_deep_mode(struct rtw_dev *rtwdev, return LPS_DEEP_MODE_NONE; if ((chip->lps_deep_mode_supported & BIT(LPS_DEEP_MODE_PG)) && - (fw->feature & FW_FEATURE_PG)) + rtw_fw_feature_check(fw, FW_FEATURE_PG)) return LPS_DEEP_MODE_PG; if ((chip->lps_deep_mode_supported & BIT(LPS_DEEP_MODE_LCLK)) && - (fw->feature & FW_FEATURE_LCLK)) + rtw_fw_feature_check(fw, FW_FEATURE_LCLK)) return LPS_DEEP_MODE_LCLK; return LPS_DEEP_MODE_NONE; @@ -1183,6 +1253,22 @@ err: return ret; } +void rtw_core_fw_scan_notify(struct rtw_dev *rtwdev, bool start) +{ + if (!rtw_fw_feature_check(&rtwdev->fw, FW_FEATURE_NOTIFY_SCAN)) + return; + + if (start) { + rtw_fw_scan_notify(rtwdev, true); + } else { + reinit_completion(&rtwdev->fw_scan_density); + rtw_fw_scan_notify(rtwdev, false); + if (!wait_for_completion_timeout(&rtwdev->fw_scan_density, + SCAN_NOTIFY_TIMEOUT)) + rtw_warn(rtwdev, "firmware failed to report density after scan\n"); + } +} + int rtw_core_start(struct rtw_dev *rtwdev) { int ret; @@ -1761,6 +1847,7 @@ int rtw_core_init(struct rtw_dev *rtwdev) init_waitqueue_head(&rtwdev->coex.wait); init_completion(&rtwdev->lps_leave_check); + init_completion(&rtwdev->fw_scan_density); rtwdev->sec.total_cam_num = 32; rtwdev->hal.current_channel = 1; @@ -1812,6 +1899,7 @@ void rtw_core_deinit(struct rtw_dev *rtwdev) destroy_workqueue(rtwdev->tx_wq); spin_lock_irqsave(&rtwdev->tx_report.q_lock, flags); skb_queue_purge(&rtwdev->tx_report.queue); + skb_queue_purge(&rtwdev->coex.queue); spin_unlock_irqrestore(&rtwdev->tx_report.q_lock, flags); list_for_each_entry_safe(rsvd_pkt, tmp, &rtwdev->rsvd_page_list, diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h index dc3744847ba9..e5af375b3dd0 100644 --- a/drivers/net/wireless/realtek/rtw88/main.h +++ b/drivers/net/wireless/realtek/rtw88/main.h @@ -806,7 +806,7 @@ struct rtw_regulatory { struct rtw_chip_ops { int (*mac_init)(struct rtw_dev *rtwdev); - void (*dump_fw_crash)(struct rtw_dev *rtwdev); + int (*dump_fw_crash)(struct rtw_dev *rtwdev); void (*shutdown)(struct rtw_dev *rtwdev); int (*read_efuse)(struct rtw_dev *rtwdev, u8 *map); void (*phy_set_param)(struct rtw_dev *rtwdev); @@ -841,6 +841,10 @@ struct rtw_chip_ops { u8 fixrate_en, u8 *new_rate); void (*cfo_init)(struct rtw_dev *rtwdev); void (*cfo_track)(struct rtw_dev *rtwdev); + void (*config_tx_path)(struct rtw_dev *rtwdev, u8 tx_path, + enum rtw_bb_path tx_path_1ss, + enum rtw_bb_path tx_path_cck, + bool is_tx2_path); /* for coex */ void (*coex_set_init)(struct rtw_dev *rtwdev); @@ -1108,6 +1112,15 @@ enum rtw_fw_fifo_sel { RTW_FW_FIFO_MAX, }; +enum rtw_fwcd_item { + RTW_FWCD_TLV, + RTW_FWCD_REG, + RTW_FWCD_ROM, + RTW_FWCD_IMEM, + RTW_FWCD_DMEM, + RTW_FWCD_EMEM, +}; + /* hardware configuration for each IC */ struct rtw_chip_info { struct rtw_chip_ops *ops; @@ -1136,7 +1149,11 @@ struct rtw_chip_info { u8 max_power_index; u16 fw_fifo_addr[RTW_FW_FIFO_MAX]; + const struct rtw_fwcd_segs *fwcd_segs; + u8 default_1ss_tx_path; + + bool path_div_supported; bool ht_supported; bool vht_supported; u8 lps_deep_mode_supported; @@ -1614,6 +1631,8 @@ struct rtw_dm_info { struct rtw_iqk_info iqk; struct rtw_gapk_info gapk; bool is_bt_iqk_timeout; + + u8 scan_density; }; struct rtw_efuse { @@ -1717,6 +1736,17 @@ struct rtw_fifo_conf { const struct rtw_rqpn *rqpn; }; +struct rtw_fwcd_desc { + u32 size; + u8 *next; + u8 *data; +}; + +struct rtw_fwcd_segs { + const u32 *segs; + u8 num; +}; + #define FW_CD_TYPE 0xffff #define FW_CD_LEN 4 #define FW_CD_VAL 0xaabbccdd @@ -1724,11 +1754,11 @@ struct rtw_fw_state { const struct firmware *firmware; struct rtw_dev *rtwdev; struct completion completion; + struct rtw_fwcd_desc fwcd_desc; u16 version; u8 sub_version; u8 sub_index; u16 h2c_version; - u8 prev_dump_seq; u32 feature; }; @@ -1781,6 +1811,14 @@ struct rtw_hal { [DESC_RATE_MAX]; }; +struct rtw_path_div { + enum rtw_bb_path current_tx_path; + u32 path_a_sum; + u32 path_b_sum; + u16 path_a_cnt; + u16 path_b_cnt; +}; + struct rtw_dev { struct ieee80211_hw *hw; struct device *dev; @@ -1837,6 +1875,7 @@ struct rtw_dev { /* lps power state & handler work */ struct rtw_lps_conf lps_conf; bool ps_enabled; + bool beacon_loss; struct completion lps_leave_check; struct dentry *debugfs; @@ -1848,11 +1887,13 @@ struct rtw_dev { DECLARE_BITMAP(flags, NUM_OF_RTW_FLAGS); u8 mp_mode; + struct rtw_path_div dm_path_div; struct rtw_fw_state wow_fw; struct rtw_wow_param wow; bool need_rfk; + struct completion fw_scan_density; /* hci related data, must be last */ u8 priv[] __aligned(sizeof(void *)); @@ -1923,10 +1964,12 @@ static inline void rtw_release_macid(struct rtw_dev *rtwdev, u8 mac_id) clear_bit(mac_id, rtwdev->mac_id_map); } -static inline void rtw_chip_dump_fw_crash(struct rtw_dev *rtwdev) +static inline int rtw_chip_dump_fw_crash(struct rtw_dev *rtwdev) { if (rtwdev->chip->ops->dump_fw_crash) - rtwdev->chip->ops->dump_fw_crash(rtwdev); + return rtwdev->chip->ops->dump_fw_crash(rtwdev); + + return 0; } void rtw_get_channel_params(struct cfg80211_chan_def *chandef, @@ -1958,9 +2001,9 @@ int rtw_sta_add(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, void rtw_sta_remove(struct rtw_dev *rtwdev, struct ieee80211_sta *sta, bool fw_exist); void rtw_fw_recovery(struct rtw_dev *rtwdev); +void rtw_core_fw_scan_notify(struct rtw_dev *rtwdev, bool start); int rtw_dump_fw(struct rtw_dev *rtwdev, const u32 ocp_src, u32 size, - const char *prefix_str); -int rtw_dump_reg(struct rtw_dev *rtwdev, const u32 addr, const u32 size, - const char *prefix_str); + u32 fwcd_item); +int rtw_dump_reg(struct rtw_dev *rtwdev, const u32 addr, const u32 size); #endif diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c index f59a4c462e3b..e7d17ab8f113 100644 --- a/drivers/net/wireless/realtek/rtw88/pci.c +++ b/drivers/net/wireless/realtek/rtw88/pci.c @@ -2,6 +2,7 @@ /* Copyright(c) 2018-2019 Realtek Corporation */ +#include #include #include #include "main.h" @@ -1673,6 +1674,36 @@ static void rtw_pci_napi_deinit(struct rtw_dev *rtwdev) netif_napi_del(&rtwpci->napi); } +enum rtw88_quirk_dis_pci_caps { + QUIRK_DIS_PCI_CAP_MSI, + QUIRK_DIS_PCI_CAP_ASPM, +}; + +static int disable_pci_caps(const struct dmi_system_id *dmi) +{ + uintptr_t dis_caps = (uintptr_t)dmi->driver_data; + + if (dis_caps & BIT(QUIRK_DIS_PCI_CAP_MSI)) + rtw_disable_msi = true; + if (dis_caps & BIT(QUIRK_DIS_PCI_CAP_ASPM)) + rtw_pci_disable_aspm = true; + + return 1; +} + +static const struct dmi_system_id rtw88_pci_quirks[] = { + { + .callback = disable_pci_caps, + .ident = "Protempo Ltd L116HTN6SPW", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Protempo Ltd"), + DMI_MATCH(DMI_PRODUCT_NAME, "L116HTN6SPW"), + }, + .driver_data = (void *)BIT(QUIRK_DIS_PCI_CAP_ASPM), + }, + {} +}; + int rtw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { @@ -1723,6 +1754,7 @@ int rtw_pci_probe(struct pci_dev *pdev, goto err_destroy_pci; } + dmi_check_system(rtw88_pci_quirks); rtw_pci_phy_cfg(rtwdev); ret = rtw_register_hw(rtwdev, hw); diff --git a/drivers/net/wireless/realtek/rtw88/phy.c b/drivers/net/wireless/realtek/rtw88/phy.c index 8146acaf1893..569dd3cfde35 100644 --- a/drivers/net/wireless/realtek/rtw88/phy.c +++ b/drivers/net/wireless/realtek/rtw88/phy.c @@ -127,6 +127,17 @@ static void rtw_phy_cfo_init(struct rtw_dev *rtwdev) chip->ops->cfo_init(rtwdev); } +static void rtw_phy_tx_path_div_init(struct rtw_dev *rtwdev) +{ + struct rtw_path_div *path_div = &rtwdev->dm_path_div; + + path_div->current_tx_path = rtwdev->chip->default_1ss_tx_path; + path_div->path_a_cnt = 0; + path_div->path_a_sum = 0; + path_div->path_b_cnt = 0; + path_div->path_b_sum = 0; +} + void rtw_phy_init(struct rtw_dev *rtwdev) { struct rtw_chip_info *chip = rtwdev->chip; @@ -149,6 +160,7 @@ void rtw_phy_init(struct rtw_dev *rtwdev) dm_info->iqk.done = false; rtw_phy_cfo_init(rtwdev); + rtw_phy_tx_path_div_init(rtwdev); } EXPORT_SYMBOL(rtw_phy_init); @@ -695,6 +707,7 @@ void rtw_phy_dynamic_mechanism(struct rtw_dev *rtwdev) rtw_phy_dig(rtwdev); rtw_phy_cck_pd(rtwdev); rtw_phy_ra_track(rtwdev); + rtw_phy_tx_path_diversity(rtwdev); rtw_phy_cfo_track(rtwdev); rtw_phy_dpk_track(rtwdev); rtw_phy_pwr_track(rtwdev); @@ -2315,3 +2328,71 @@ bool rtw_phy_pwrtrack_need_iqk(struct rtw_dev *rtwdev) return false; } EXPORT_SYMBOL(rtw_phy_pwrtrack_need_iqk); + +static void rtw_phy_set_tx_path_by_reg(struct rtw_dev *rtwdev, + enum rtw_bb_path tx_path_sel_1ss) +{ + struct rtw_path_div *path_div = &rtwdev->dm_path_div; + enum rtw_bb_path tx_path_sel_cck = tx_path_sel_1ss; + struct rtw_chip_info *chip = rtwdev->chip; + + if (tx_path_sel_1ss == path_div->current_tx_path) + return; + + path_div->current_tx_path = tx_path_sel_1ss; + rtw_dbg(rtwdev, RTW_DBG_PATH_DIV, "Switch TX path=%s\n", + tx_path_sel_1ss == BB_PATH_A ? "A" : "B"); + chip->ops->config_tx_path(rtwdev, rtwdev->hal.antenna_tx, + tx_path_sel_1ss, tx_path_sel_cck, false); +} + +static void rtw_phy_tx_path_div_select(struct rtw_dev *rtwdev) +{ + struct rtw_path_div *path_div = &rtwdev->dm_path_div; + enum rtw_bb_path path = path_div->current_tx_path; + s32 rssi_a = 0, rssi_b = 0; + + if (path_div->path_a_cnt) + rssi_a = path_div->path_a_sum / path_div->path_a_cnt; + else + rssi_a = 0; + if (path_div->path_b_cnt) + rssi_b = path_div->path_b_sum / path_div->path_b_cnt; + else + rssi_b = 0; + + if (rssi_a != rssi_b) + path = (rssi_a > rssi_b) ? BB_PATH_A : BB_PATH_B; + + path_div->path_a_cnt = 0; + path_div->path_a_sum = 0; + path_div->path_b_cnt = 0; + path_div->path_b_sum = 0; + rtw_phy_set_tx_path_by_reg(rtwdev, path); +} + +static void rtw_phy_tx_path_diversity_2ss(struct rtw_dev *rtwdev) +{ + if (rtwdev->hal.antenna_rx != BB_PATH_AB) { + rtw_dbg(rtwdev, RTW_DBG_PATH_DIV, + "[Return] tx_Path_en=%d, rx_Path_en=%d\n", + rtwdev->hal.antenna_tx, rtwdev->hal.antenna_rx); + return; + } + if (rtwdev->sta_cnt == 0) { + rtw_dbg(rtwdev, RTW_DBG_PATH_DIV, "No Link\n"); + return; + } + + rtw_phy_tx_path_div_select(rtwdev); +} + +void rtw_phy_tx_path_diversity(struct rtw_dev *rtwdev) +{ + struct rtw_chip_info *chip = rtwdev->chip; + + if (!chip->path_div_supported) + return; + + rtw_phy_tx_path_diversity_2ss(rtwdev); +} diff --git a/drivers/net/wireless/realtek/rtw88/phy.h b/drivers/net/wireless/realtek/rtw88/phy.h index 0b6f2fc8193c..112ed125970a 100644 --- a/drivers/net/wireless/realtek/rtw88/phy.h +++ b/drivers/net/wireless/realtek/rtw88/phy.h @@ -61,6 +61,7 @@ void rtw_phy_config_swing_table(struct rtw_dev *rtwdev, struct rtw_swing_table *swing_table); void rtw_phy_parsing_cfo(struct rtw_dev *rtwdev, struct rtw_rx_pkt_stat *pkt_stat); +void rtw_phy_tx_path_diversity(struct rtw_dev *rtwdev); struct rtw_txpwr_lmt_cfg_pair { u8 regd; diff --git a/drivers/net/wireless/realtek/rtw88/ps.c b/drivers/net/wireless/realtek/rtw88/ps.c index 3bead34c3d10..3f0ac33156d6 100644 --- a/drivers/net/wireless/realtek/rtw88/ps.c +++ b/drivers/net/wireless/realtek/rtw88/ps.c @@ -152,7 +152,7 @@ static void rtw_fw_leave_lps_check(struct rtw_dev *rtwdev) else fw = &rtwdev->fw; - if (fw->feature & FW_FEATURE_LPS_C2H) + if (rtw_fw_feature_check(fw, FW_FEATURE_LPS_C2H)) ret = __rtw_fw_leave_lps_check_c2h(rtwdev); else ret = __rtw_fw_leave_lps_check_reg(rtwdev); @@ -172,7 +172,7 @@ static void rtw_fw_leave_lps_check_prepare(struct rtw_dev *rtwdev) else fw = &rtwdev->fw; - if (fw->feature & FW_FEATURE_LPS_C2H) + if (rtw_fw_feature_check(fw, FW_FEATURE_LPS_C2H)) reinit_completion(&rtwdev->lps_leave_check); } diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c index 6cb593cc33c2..8bf3cd3a3678 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c @@ -17,7 +17,6 @@ #include "util.h" #include "bf.h" #include "efuse.h" -#include "coex.h" #define IQK_DONE_8822C 0xaa @@ -80,6 +79,13 @@ static void rtw8822c_header_file_init(struct rtw_dev *rtwdev, bool pre) rtw_write32_set(rtwdev, REG_ENCCK, BIT_CCK_OFDM_BLK_EN); } +static void rtw8822c_bb_reset(struct rtw_dev *rtwdev) +{ + rtw_write16_set(rtwdev, REG_SYS_FUNC_EN, BIT_FEN_BB_RSTB); + rtw_write16_clr(rtwdev, REG_SYS_FUNC_EN, BIT_FEN_BB_RSTB); + rtw_write16_set(rtwdev, REG_SYS_FUNC_EN, BIT_FEN_BB_RSTB); +} + static void rtw8822c_dac_backup_reg(struct rtw_dev *rtwdev, struct rtw_backup_info *backup, struct rtw_backup_info *backup_rf) @@ -2103,13 +2109,51 @@ static int rtw8822c_mac_init(struct rtw_dev *rtwdev) return 0; } -static void rtw8822c_dump_fw_crash(struct rtw_dev *rtwdev) +#define FWCD_SIZE_REG_8822C 0x2000 +#define FWCD_SIZE_DMEM_8822C 0x10000 +#define FWCD_SIZE_IMEM_8822C 0x10000 +#define FWCD_SIZE_EMEM_8822C 0x20000 +#define FWCD_SIZE_ROM_8822C 0x10000 + +static const u32 __fwcd_segs_8822c[] = { + FWCD_SIZE_REG_8822C, + FWCD_SIZE_DMEM_8822C, + FWCD_SIZE_IMEM_8822C, + FWCD_SIZE_EMEM_8822C, + FWCD_SIZE_ROM_8822C, +}; + +static const struct rtw_fwcd_segs rtw8822c_fwcd_segs = { + .segs = __fwcd_segs_8822c, + .num = ARRAY_SIZE(__fwcd_segs_8822c), +}; + +static int rtw8822c_dump_fw_crash(struct rtw_dev *rtwdev) { - rtw_dump_reg(rtwdev, 0x0, 0x2000, "rtw8822c reg_"); - rtw_dump_fw(rtwdev, OCPBASE_DMEM_88XX, 0x10000, "rtw8822c DMEM_"); - rtw_dump_fw(rtwdev, OCPBASE_IMEM_88XX, 0x10000, "rtw8822c IMEM_"); - rtw_dump_fw(rtwdev, OCPBASE_EMEM_88XX, 0x20000, "rtw8822c EMEM_"); - rtw_dump_fw(rtwdev, OCPBASE_ROM_88XX, 0x10000, "rtw8822c ROM_"); +#define __dump_fw_8822c(_dev, _mem) \ + rtw_dump_fw(_dev, OCPBASE_ ## _mem ## _88XX, \ + FWCD_SIZE_ ## _mem ## _8822C, RTW_FWCD_ ## _mem) + int ret; + + ret = rtw_dump_reg(rtwdev, 0x0, FWCD_SIZE_REG_8822C); + if (ret) + return ret; + ret = __dump_fw_8822c(rtwdev, DMEM); + if (ret) + return ret; + ret = __dump_fw_8822c(rtwdev, IMEM); + if (ret) + return ret; + ret = __dump_fw_8822c(rtwdev, EMEM); + if (ret) + return ret; + ret = __dump_fw_8822c(rtwdev, ROM); + if (ret) + return ret; + + return 0; + +#undef __dump_fw_8822c } static void rtw8822c_rstb_3wire(struct rtw_dev *rtwdev, bool enable) @@ -2424,10 +2468,11 @@ static void rtw8822c_config_cck_tx_path(struct rtw_dev *rtwdev, u8 tx_path, else rtw_write32_mask(rtwdev, REG_RXCCKSEL, 0xf0000000, 0x8); } + rtw8822c_bb_reset(rtwdev); } static void rtw8822c_config_ofdm_tx_path(struct rtw_dev *rtwdev, u8 tx_path, - bool is_tx2_path) + enum rtw_bb_path tx_path_sel_1ss) { if (tx_path == BB_PATH_A) { rtw_write32_mask(rtwdev, REG_ANTMAP0, 0xff, 0x11); @@ -2436,21 +2481,28 @@ static void rtw8822c_config_ofdm_tx_path(struct rtw_dev *rtwdev, u8 tx_path, rtw_write32_mask(rtwdev, REG_ANTMAP0, 0xff, 0x12); rtw_write32_mask(rtwdev, REG_TXLGMAP, 0xff, 0x0); } else { - if (is_tx2_path) { + if (tx_path_sel_1ss == BB_PATH_AB) { rtw_write32_mask(rtwdev, REG_ANTMAP0, 0xff, 0x33); rtw_write32_mask(rtwdev, REG_TXLGMAP, 0xffff, 0x0404); - } else { + } else if (tx_path_sel_1ss == BB_PATH_B) { + rtw_write32_mask(rtwdev, REG_ANTMAP0, 0xff, 0x32); + rtw_write32_mask(rtwdev, REG_TXLGMAP, 0xffff, 0x0400); + } else if (tx_path_sel_1ss == BB_PATH_A) { rtw_write32_mask(rtwdev, REG_ANTMAP0, 0xff, 0x31); rtw_write32_mask(rtwdev, REG_TXLGMAP, 0xffff, 0x0400); } } + rtw8822c_bb_reset(rtwdev); } static void rtw8822c_config_tx_path(struct rtw_dev *rtwdev, u8 tx_path, + enum rtw_bb_path tx_path_sel_1ss, + enum rtw_bb_path tx_path_cck, bool is_tx2_path) { - rtw8822c_config_cck_tx_path(rtwdev, tx_path, is_tx2_path); - rtw8822c_config_ofdm_tx_path(rtwdev, tx_path, is_tx2_path); + rtw8822c_config_cck_tx_path(rtwdev, tx_path_cck, is_tx2_path); + rtw8822c_config_ofdm_tx_path(rtwdev, tx_path, tx_path_sel_1ss); + rtw8822c_bb_reset(rtwdev); } static void rtw8822c_config_trx_mode(struct rtw_dev *rtwdev, u8 tx_path, @@ -2466,7 +2518,8 @@ static void rtw8822c_config_trx_mode(struct rtw_dev *rtwdev, u8 tx_path, rtw_write32_mask(rtwdev, REG_ORITXCODE2, MASK20BITS, 0x11111); rtw8822c_config_rx_path(rtwdev, rx_path); - rtw8822c_config_tx_path(rtwdev, tx_path, is_tx2_path); + rtw8822c_config_tx_path(rtwdev, tx_path, BB_PATH_A, BB_PATH_A, + is_tx2_path); rtw8822c_toggle_igi(rtwdev); } @@ -2517,6 +2570,7 @@ static void query_phy_status_page0(struct rtw_dev *rtwdev, u8 *phy_status, static void query_phy_status_page1(struct rtw_dev *rtwdev, u8 *phy_status, struct rtw_rx_pkt_stat *pkt_stat) { + struct rtw_path_div *p_div = &rtwdev->dm_path_div; struct rtw_dm_info *dm_info = &rtwdev->dm_info; u8 rxsc, bw; s8 min_rx_power = -120; @@ -2559,6 +2613,13 @@ static void query_phy_status_page1(struct rtw_dev *rtwdev, u8 *phy_status, for (path = 0; path <= rtwdev->hal.rf_path_num; path++) { rssi = rtw_phy_rf_power_2_rssi(&pkt_stat->rx_power[path], 1); dm_info->rssi[path] = rssi; + if (path == RF_PATH_A) { + p_div->path_a_sum += rssi; + p_div->path_a_cnt++; + } else if (path == RF_PATH_B) { + p_div->path_b_sum += rssi; + p_div->path_b_cnt++; + } dm_info->rx_snr[path] = pkt_stat->rx_snr[path] >> 1; dm_info->cfo_tail[path] = (pkt_stat->cfo_tail[path] * 5) >> 1; @@ -4371,26 +4432,28 @@ static void rtw8822c_pwrtrack_set(struct rtw_dev *rtwdev, u8 rf_path) } } -static void rtw8822c_pwr_track_path(struct rtw_dev *rtwdev, - struct rtw_swing_table *swing_table, - u8 path) +static void rtw8822c_pwr_track_stats(struct rtw_dev *rtwdev, u8 path) { - struct rtw_dm_info *dm_info = &rtwdev->dm_info; - u8 thermal_value, delta; + u8 thermal_value; if (rtwdev->efuse.thermal_meter[path] == 0xff) return; thermal_value = rtw_read_rf(rtwdev, path, RF_T_METER, 0x7e); - rtw_phy_pwrtrack_avg(rtwdev, thermal_value, path); +} + +static void rtw8822c_pwr_track_path(struct rtw_dev *rtwdev, + struct rtw_swing_table *swing_table, + u8 path) +{ + struct rtw_dm_info *dm_info = &rtwdev->dm_info; + u8 delta; delta = rtw_phy_pwrtrack_get_delta(rtwdev, path); - dm_info->delta_power_index[path] = rtw_phy_pwrtrack_get_pwridx(rtwdev, swing_table, path, path, delta); - rtw8822c_pwrtrack_set(rtwdev, path); } @@ -4401,12 +4464,12 @@ static void __rtw8822c_pwr_track(struct rtw_dev *rtwdev) rtw_phy_config_swing_table(rtwdev, &swing_table); + for (i = 0; i < rtwdev->hal.rf_path_num; i++) + rtw8822c_pwr_track_stats(rtwdev, i); if (rtw_phy_pwrtrack_need_lck(rtwdev)) rtw8822c_do_lck(rtwdev); - for (i = 0; i < rtwdev->hal.rf_path_num; i++) rtw8822c_pwr_track_path(rtwdev, &swing_table, i); - } static void rtw8822c_pwr_track(struct rtw_dev *rtwdev) @@ -4851,6 +4914,7 @@ static struct rtw_chip_ops rtw8822c_ops = { .cfg_csi_rate = rtw_bf_cfg_csi_rate, .cfo_init = rtw8822c_cfo_init, .cfo_track = rtw8822c_cfo_track, + .config_tx_path = rtw8822c_config_tx_path, .coex_set_init = rtw8822c_coex_cfg_init, .coex_set_ant_switch = NULL, @@ -5192,6 +5256,8 @@ struct rtw_chip_info rtw8822c_hw_spec = { .band = RTW_BAND_2G | RTW_BAND_5G, .page_size = 128, .dig_min = 0x20, + .default_1ss_tx_path = BB_PATH_A, + .path_div_supported = true, .ht_supported = true, .vht_supported = true, .lps_deep_mode_supported = BIT(LPS_DEEP_MODE_LCLK) | BIT(LPS_DEEP_MODE_PG), @@ -5259,6 +5325,7 @@ struct rtw_chip_info rtw8822c_hw_spec = { .coex_info_hw_regs = coex_info_hw_regs_8822c, .fw_fifo_addr = {0x780, 0x700, 0x780, 0x660, 0x650, 0x680}, + .fwcd_segs = &rtw8822c_fwcd_segs, }; EXPORT_SYMBOL(rtw8822c_hw_spec); diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c_table.c b/drivers/net/wireless/realtek/rtw88/rtw8822c_table.c index 822f3da91f1b..f9e3d0779c59 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822c_table.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8822c_table.c @@ -16812,53 +16812,53 @@ static const u32 rtw8822c_rf_a[] = { 0x92000002, 0x00000000, 0x40000000, 0x00000000, 0x03F, 0x00010E46, 0x93000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x93000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x93000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x93000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x93000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x93000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x93000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x93000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x94000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x94000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x94000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x94000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x94000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x94000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x94000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x94000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x95000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x95000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x95000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x95000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x95000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x95000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x95000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0x95000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00030246, + 0x03F, 0x0003D646, 0xA0000000, 0x00000000, 0x03F, 0x00002A46, 0xB0000000, 0x00000000, @@ -18762,53 +18762,53 @@ static const u32 rtw8822c_rf_a[] = { 0x92000002, 0x00000000, 0x40000000, 0x00000000, 0x03F, 0x0000EA46, 0x93000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0xA0000000, 0x00000000, 0x03F, 0x00002A46, 0xB0000000, 0x00000000, @@ -18957,53 +18957,53 @@ static const u32 rtw8822c_rf_a[] = { 0x92000002, 0x00000000, 0x40000000, 0x00000000, 0x03F, 0x0000EA46, 0x93000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0xA0000000, 0x00000000, 0x03F, 0x00002A46, 0xB0000000, 0x00000000, @@ -19152,53 +19152,53 @@ static const u32 rtw8822c_rf_a[] = { 0x92000002, 0x00000000, 0x40000000, 0x00000000, 0x03F, 0x0000EA46, 0x93000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0xA0000000, 0x00000000, 0x03F, 0x00002A46, 0xB0000000, 0x00000000, @@ -19347,53 +19347,53 @@ static const u32 rtw8822c_rf_a[] = { 0x92000002, 0x00000000, 0x40000000, 0x00000000, 0x03F, 0x0000EA46, 0x93000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x93000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x94000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000001, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000002, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000003, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000004, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000005, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000006, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000015, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0x95000016, 0x00000000, 0x40000000, 0x00000000, - 0x03F, 0x00031E46, + 0x03F, 0x0003D646, 0xA0000000, 0x00000000, 0x03F, 0x00002A46, 0xB0000000, 0x00000000, @@ -19610,21 +19610,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000002, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19633,21 +19633,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000003, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19656,21 +19656,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000004, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19679,21 +19679,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000005, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19702,21 +19702,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000006, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19725,21 +19725,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000015, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19748,21 +19748,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000016, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19771,21 +19771,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000001, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19794,21 +19794,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000002, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19817,21 +19817,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000003, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19840,21 +19840,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000004, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19863,21 +19863,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000005, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19886,21 +19886,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000006, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19909,21 +19909,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000015, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19932,21 +19932,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000016, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19955,21 +19955,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000001, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -19978,21 +19978,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000002, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -20001,21 +20001,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000003, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -20024,21 +20024,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000004, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -20047,21 +20047,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000005, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -20070,21 +20070,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000006, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -20093,21 +20093,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000015, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -20116,21 +20116,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000016, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -20139,21 +20139,21 @@ static const u32 rtw8822c_rf_a[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x000008C8, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x000008CB, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x000008CE, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x000008D1, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x000008D4, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000DD1, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0xA0000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000487, @@ -38484,21 +38484,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000002, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38507,21 +38507,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000003, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38530,21 +38530,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000004, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38553,21 +38553,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000005, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38576,21 +38576,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000006, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38599,21 +38599,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000015, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38622,21 +38622,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x93000016, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38645,21 +38645,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000001, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38668,21 +38668,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000002, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38691,21 +38691,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000003, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38714,21 +38714,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000004, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38737,21 +38737,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000005, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38760,21 +38760,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000006, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38783,21 +38783,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000015, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38806,21 +38806,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x94000016, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38829,21 +38829,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000001, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38852,21 +38852,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000002, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38875,21 +38875,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000003, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38898,21 +38898,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000004, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38921,21 +38921,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000005, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38944,21 +38944,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000006, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38967,21 +38967,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000015, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -38990,21 +38990,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0x95000016, 0x00000000, 0x40000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000467, @@ -39013,21 +39013,21 @@ static const u32 rtw8822c_rf_b[] = { 0x033, 0x00000062, 0x03F, 0x00000908, 0x033, 0x00000063, - 0x03F, 0x00000D09, + 0x03F, 0x00000CC6, 0x033, 0x00000064, - 0x03F, 0x00000D49, + 0x03F, 0x00000CC9, 0x033, 0x00000065, - 0x03F, 0x00000D8A, + 0x03F, 0x00000CCC, 0x033, 0x00000066, - 0x03F, 0x00000DEB, + 0x03F, 0x00000CCF, 0x033, 0x00000067, - 0x03F, 0x00000DEE, + 0x03F, 0x00000CD2, 0x033, 0x00000068, - 0x03F, 0x00000DF1, + 0x03F, 0x00000CD5, 0x033, 0x00000069, - 0x03F, 0x00000DF4, + 0x03F, 0x00000DD4, 0x033, 0x0000006A, - 0x03F, 0x00000DF7, + 0x03F, 0x00000DD7, 0xA0000000, 0x00000000, 0x033, 0x00000060, 0x03F, 0x00000487, diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index 9fe77556858e..63ce2443f136 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -1036,14 +1036,11 @@ static bool is_associated(struct usbnet *usbdev) { struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev); u8 bssid[ETH_ALEN]; - int ret; if (!priv->radio_on) return false; - ret = get_bssid(usbdev, bssid); - - return (ret == 0 && !is_zero_ether_addr(bssid)); + return (get_bssid(usbdev, bssid) == 0 && !is_zero_ether_addr(bssid)); } static int disassociate(struct usbnet *usbdev, bool reset_ssid) diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c index ce9892152f4d..99b21a2c8386 100644 --- a/drivers/net/wireless/rsi/rsi_91x_hal.c +++ b/drivers/net/wireless/rsi/rsi_91x_hal.c @@ -203,7 +203,7 @@ int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb) wh->frame_control |= cpu_to_le16(RSI_SET_PS_ENABLE); if ((!(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)) && - (common->secinfo.security_enable)) { + info->control.hw_key) { if (rsi_is_cipher_wep(common)) ieee80211_size += 4; else @@ -470,9 +470,9 @@ int rsi_prepare_beacon(struct rsi_common *common, struct sk_buff *skb) } if (common->band == NL80211_BAND_2GHZ) - bcn_frm->bbp_info |= cpu_to_le16(RSI_RATE_1); + bcn_frm->rate_info |= cpu_to_le16(RSI_RATE_1); else - bcn_frm->bbp_info |= cpu_to_le16(RSI_RATE_6); + bcn_frm->rate_info |= cpu_to_le16(RSI_RATE_6); if (mac_bcn->data[tim_offset + 2] == 0) bcn_frm->frame_info |= cpu_to_le16(RSI_DATA_DESC_DTIM_BEACON); diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index 16025300cddb..b66975f54567 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -837,6 +837,23 @@ static void rsi_mac80211_bss_info_changed(struct ieee80211_hw *hw, common->cqm_info.rssi_hyst); } + if (changed & BSS_CHANGED_BEACON_INT) { + rsi_dbg(INFO_ZONE, "%s: Changed Beacon interval: %d\n", + __func__, bss_conf->beacon_int); + if (common->beacon_interval != bss->beacon_int) { + common->beacon_interval = bss->beacon_int; + if (vif->type == NL80211_IFTYPE_AP) { + struct vif_priv *vif_info = (struct vif_priv *)vif->drv_priv; + + rsi_set_vap_capabilities(common, RSI_OPMODE_AP, + vif->addr, vif_info->vap_id, + VAP_UPDATE); + } + } + adapter->ps_info.listen_interval = + bss->beacon_int * adapter->ps_info.num_bcns_per_lis_int; + } + if ((changed & BSS_CHANGED_BEACON_ENABLED) && ((vif->type == NL80211_IFTYPE_AP) || (vif->type == NL80211_IFTYPE_P2P_GO))) { @@ -1028,7 +1045,6 @@ static int rsi_mac80211_set_key(struct ieee80211_hw *hw, mutex_lock(&common->mutex); switch (cmd) { case SET_KEY: - secinfo->security_enable = true; status = rsi_hal_key_config(hw, vif, key, sta); if (status) { mutex_unlock(&common->mutex); @@ -1047,8 +1063,6 @@ static int rsi_mac80211_set_key(struct ieee80211_hw *hw, break; case DISABLE_KEY: - if (vif->type == NL80211_IFTYPE_STATION) - secinfo->security_enable = false; rsi_dbg(ERR_ZONE, "%s: RSI del key\n", __func__); memset(key, 0, sizeof(struct ieee80211_key_conf)); status = rsi_hal_key_config(hw, vif, key, sta); diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c index 33c76d39a8e9..891fd5f0fa76 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c +++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c @@ -1547,8 +1547,8 @@ static int rsi_eeprom_read(struct rsi_common *common) } /** - * This function sends a frame to block/unblock - * data queues in the firmware + * rsi_send_block_unblock_frame() - This function sends a frame to block/unblock + * data queues in the firmware * * @common: Pointer to the driver private structure. * @block_event: Event block if true, unblock if false @@ -1803,8 +1803,7 @@ int rsi_send_wowlan_request(struct rsi_common *common, u16 flags, RSI_WIFI_MGMT_Q); cmd_frame->desc.desc_dword0.frame_type = WOWLAN_CONFIG_PARAMS; cmd_frame->host_sleep_status = sleep_status; - if (common->secinfo.security_enable && - common->secinfo.gtk_cipher) + if (common->secinfo.gtk_cipher) flags |= RSI_WOW_GTK_REKEY; if (sleep_status) cmd_frame->wow_flags = flags; diff --git a/drivers/net/wireless/rsi/rsi_main.h b/drivers/net/wireless/rsi/rsi_main.h index a1065e5a92b4..0f535850a383 100644 --- a/drivers/net/wireless/rsi/rsi_main.h +++ b/drivers/net/wireless/rsi/rsi_main.h @@ -151,7 +151,6 @@ enum edca_queue { }; struct security_info { - bool security_enable; u32 ptk_cipher; u32 gtk_cipher; }; diff --git a/drivers/net/wireless/st/cw1200/cw1200_sdio.c b/drivers/net/wireless/st/cw1200/cw1200_sdio.c index b65ec14136c7..4c30b5772ce0 100644 --- a/drivers/net/wireless/st/cw1200/cw1200_sdio.c +++ b/drivers/net/wireless/st/cw1200/cw1200_sdio.c @@ -53,6 +53,7 @@ static const struct sdio_device_id cw1200_sdio_ids[] = { { SDIO_DEVICE(SDIO_VENDOR_ID_STE, SDIO_DEVICE_ID_STE_CW1200) }, { /* end: all zeroes */ }, }; +MODULE_DEVICE_TABLE(sdio, cw1200_sdio_ids); /* hwbus_ops implemetation */ diff --git a/drivers/net/wireless/st/cw1200/scan.c b/drivers/net/wireless/st/cw1200/scan.c index 988581cc134b..1f856fbbc0ea 100644 --- a/drivers/net/wireless/st/cw1200/scan.c +++ b/drivers/net/wireless/st/cw1200/scan.c @@ -75,30 +75,27 @@ int cw1200_hw_scan(struct ieee80211_hw *hw, if (req->n_ssids > WSM_SCAN_MAX_NUM_OF_SSIDS) return -EINVAL; - /* will be unlocked in cw1200_scan_work() */ - down(&priv->scan.lock); - mutex_lock(&priv->conf_mutex); - frame.skb = ieee80211_probereq_get(hw, priv->vif->addr, NULL, 0, req->ie_len); - if (!frame.skb) { - mutex_unlock(&priv->conf_mutex); - up(&priv->scan.lock); + if (!frame.skb) return -ENOMEM; - } if (req->ie_len) skb_put_data(frame.skb, req->ie, req->ie_len); + /* will be unlocked in cw1200_scan_work() */ + down(&priv->scan.lock); + mutex_lock(&priv->conf_mutex); + ret = wsm_set_template_frame(priv, &frame); if (!ret) { /* Host want to be the probe responder. */ ret = wsm_set_probe_responder(priv, true); } if (ret) { - dev_kfree_skb(frame.skb); mutex_unlock(&priv->conf_mutex); up(&priv->scan.lock); + dev_kfree_skb(frame.skb); return ret; } @@ -120,8 +117,8 @@ int cw1200_hw_scan(struct ieee80211_hw *hw, ++priv->scan.n_ssids; } - dev_kfree_skb(frame.skb); mutex_unlock(&priv->conf_mutex); + dev_kfree_skb(frame.skb); queue_work(priv->workqueue, &priv->scan.work); return 0; } diff --git a/drivers/net/wireless/ti/wl1251/cmd.c b/drivers/net/wireless/ti/wl1251/cmd.c index 498c8db2eb48..c3be81dc7970 100644 --- a/drivers/net/wireless/ti/wl1251/cmd.c +++ b/drivers/net/wireless/ti/wl1251/cmd.c @@ -12,7 +12,7 @@ #include "acx.h" /** - * send command to firmware + * wl1251_cmd_send - Send command to firmware * * @wl: wl struct * @id: command id @@ -59,7 +59,7 @@ out: } /** - * send test command to firmware + * wl1251_cmd_test - Send test command to firmware * * @wl: wl struct * @buf: buffer containing the command, with all headers, must work with dma @@ -100,7 +100,7 @@ int wl1251_cmd_test(struct wl1251 *wl, void *buf, size_t buf_len, u8 answer) } /** - * read acx from firmware + * wl1251_cmd_interrogate - Read acx from firmware * * @wl: wl struct * @id: acx id @@ -138,7 +138,7 @@ out: } /** - * write acx value to firmware + * wl1251_cmd_configure - Write acx value to firmware * * @wl: wl struct * @id: acx id @@ -454,9 +454,12 @@ int wl1251_cmd_scan(struct wl1251 *wl, u8 *ssid, size_t ssid_len, cmd->channels[i].channel = channels[i]->hw_value; } - cmd->params.ssid_len = ssid_len; - if (ssid) - memcpy(cmd->params.ssid, ssid, ssid_len); + if (ssid) { + int len = clamp_val(ssid_len, 0, IEEE80211_MAX_SSID_LEN); + + cmd->params.ssid_len = len; + memcpy(cmd->params.ssid, ssid, len); + } ret = wl1251_cmd_send(wl, CMD_SCAN, cmd, sizeof(*cmd)); if (ret < 0) { diff --git a/drivers/net/wireless/ti/wl12xx/main.c b/drivers/net/wireless/ti/wl12xx/main.c index 9d7dbfe7fe0c..c6da0cfb4afb 100644 --- a/drivers/net/wireless/ti/wl12xx/main.c +++ b/drivers/net/wireless/ti/wl12xx/main.c @@ -1503,6 +1503,13 @@ static int wl12xx_get_fuse_mac(struct wl1271 *wl) u32 mac1, mac2; int ret; + /* Device may be in ELP from the bootloader or kexec */ + ret = wlcore_write32(wl, WL12XX_WELP_ARM_COMMAND, WELP_ARM_COMMAND_VAL); + if (ret < 0) + goto out; + + usleep_range(500000, 700000); + ret = wlcore_set_partition(wl, &wl->ptable[PART_DRPW]); if (ret < 0) goto out; diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c index 32a2e27cc561..8b798b5fcaf5 100644 --- a/drivers/net/wireless/ti/wlcore/cmd.c +++ b/drivers/net/wireless/ti/wlcore/cmd.c @@ -821,7 +821,7 @@ out: /** - * send test command to firmware + * wl1271_cmd_test - send test command to firmware * * @wl: wl struct * @buf: buffer containing the command, with all headers, must work with dma @@ -850,7 +850,7 @@ int wl1271_cmd_test(struct wl1271 *wl, void *buf, size_t buf_len, u8 answer) EXPORT_SYMBOL_GPL(wl1271_cmd_test); /** - * read acx from firmware + * wl1271_cmd_interrogate - read acx from firmware * * @wl: wl struct * @id: acx id @@ -879,7 +879,7 @@ int wl1271_cmd_interrogate(struct wl1271 *wl, u16 id, void *buf, } /** - * write acx value to firmware + * wlcore_cmd_configure_failsafe - write acx value to firmware * * @wl: wl struct * @id: acx id diff --git a/drivers/net/wireless/ti/wlcore/event.c b/drivers/net/wireless/ti/wlcore/event.c index a68bbadae043..46ab69eab26a 100644 --- a/drivers/net/wireless/ti/wlcore/event.c +++ b/drivers/net/wireless/ti/wlcore/event.c @@ -29,18 +29,20 @@ int wlcore_event_fw_logger(struct wl1271 *wl) u8 *buffer; u32 internal_fw_addrbase = WL18XX_DATA_RAM_BASE_ADDRESS; u32 addr = WL18XX_LOGGER_SDIO_BUFF_ADDR; - u32 end_buff_addr = WL18XX_LOGGER_SDIO_BUFF_ADDR + - WL18XX_LOGGER_BUFF_OFFSET; + u32 addr_ptr; + u32 buff_start_ptr; + u32 buff_read_ptr; + u32 buff_end_ptr; u32 available_len; u32 actual_len; - u32 clear_addr; + u32 clear_ptr; size_t len; u32 start_loc; buffer = kzalloc(WL18XX_LOGGER_SDIO_BUFF_MAX, GFP_KERNEL); if (!buffer) { wl1271_error("Fail to allocate fw logger memory"); - fw_log.actual_buff_size = cpu_to_le32(0); + actual_len = 0; goto out; } @@ -49,51 +51,58 @@ int wlcore_event_fw_logger(struct wl1271 *wl) if (ret < 0) { wl1271_error("Fail to read logger buffer, error_id = %d", ret); - fw_log.actual_buff_size = cpu_to_le32(0); + actual_len = 0; goto free_out; } memcpy(&fw_log, buffer, sizeof(fw_log)); - if (le32_to_cpu(fw_log.actual_buff_size) == 0) + actual_len = le32_to_cpu(fw_log.actual_buff_size); + if (actual_len == 0) goto free_out; - actual_len = le32_to_cpu(fw_log.actual_buff_size); - start_loc = (le32_to_cpu(fw_log.buff_read_ptr) - - internal_fw_addrbase) - addr; - end_buff_addr += le32_to_cpu(fw_log.max_buff_size); - available_len = end_buff_addr - - (le32_to_cpu(fw_log.buff_read_ptr) - - internal_fw_addrbase); - actual_len = min(actual_len, available_len); - len = actual_len; + /* Calculate the internal pointer to the fwlog structure */ + addr_ptr = internal_fw_addrbase + addr; + /* Calculate the internal pointers to the start and end of log buffer */ + buff_start_ptr = addr_ptr + WL18XX_LOGGER_BUFF_OFFSET; + buff_end_ptr = buff_start_ptr + le32_to_cpu(fw_log.max_buff_size); + + /* Read the read pointer and validate it */ + buff_read_ptr = le32_to_cpu(fw_log.buff_read_ptr); + if (buff_read_ptr < buff_start_ptr || + buff_read_ptr >= buff_end_ptr) { + wl1271_error("buffer read pointer out of bounds: %x not in (%x-%x)\n", + buff_read_ptr, buff_start_ptr, buff_end_ptr); + goto free_out; + } + + start_loc = buff_read_ptr - addr_ptr; + available_len = buff_end_ptr - buff_read_ptr; + + /* Copy initial part up to the end of ring buffer */ + len = min(actual_len, available_len); wl12xx_copy_fwlog(wl, &buffer[start_loc], len); - clear_addr = addr + start_loc + le32_to_cpu(fw_log.actual_buff_size) + - internal_fw_addrbase; + clear_ptr = addr_ptr + start_loc + actual_len; + if (clear_ptr == buff_end_ptr) + clear_ptr = buff_start_ptr; - len = le32_to_cpu(fw_log.actual_buff_size) - len; + /* Copy any remaining part from beginning of ring buffer */ + len = actual_len - len; if (len) { wl12xx_copy_fwlog(wl, &buffer[WL18XX_LOGGER_BUFF_OFFSET], len); - clear_addr = addr + WL18XX_LOGGER_BUFF_OFFSET + len + - internal_fw_addrbase; + clear_ptr = addr_ptr + WL18XX_LOGGER_BUFF_OFFSET + len; } - /* double check that clear address and write pointer are the same */ - if (clear_addr != le32_to_cpu(fw_log.buff_write_ptr)) { - wl1271_error("Calculate of clear addr Clear = %x, write = %x", - clear_addr, le32_to_cpu(fw_log.buff_write_ptr)); - } - - /* indicate FW about Clear buffer */ + /* Update the read pointer */ ret = wlcore_write32(wl, addr + WL18XX_LOGGER_READ_POINT_OFFSET, - fw_log.buff_write_ptr); + clear_ptr); free_out: kfree(buffer); out: - return le32_to_cpu(fw_log.actual_buff_size); + return actual_len; } EXPORT_SYMBOL_GPL(wlcore_event_fw_logger); diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 8509b989940c..e500b8405f8f 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -3242,8 +3242,8 @@ static void wl1271_op_configure_filter(struct ieee80211_hw *hw, * the firmware filters so that all multicast packets are passed * This is mandatory for MDNS based discovery protocols */ - if (wlvif->bss_type == BSS_TYPE_AP_BSS) { - if (*total & FIF_ALLMULTI) { + if (wlvif->bss_type == BSS_TYPE_AP_BSS) { + if (*total & FIF_ALLMULTI) { ret = wl1271_acx_group_address_tbl(wl, wlvif, false, NULL, 0); diff --git a/drivers/net/wireless/ti/wlcore/sysfs.c b/drivers/net/wireless/ti/wlcore/sysfs.c index 5cf0379b88b6..35b535c125b6 100644 --- a/drivers/net/wireless/ti/wlcore/sysfs.c +++ b/drivers/net/wireless/ti/wlcore/sysfs.c @@ -12,9 +12,9 @@ #include "debug.h" #include "sysfs.h" -static ssize_t wl1271_sysfs_show_bt_coex_state(struct device *dev, - struct device_attribute *attr, - char *buf) +static ssize_t bt_coex_state_show(struct device *dev, + struct device_attribute *attr, + char *buf) { struct wl1271 *wl = dev_get_drvdata(dev); ssize_t len; @@ -30,9 +30,9 @@ static ssize_t wl1271_sysfs_show_bt_coex_state(struct device *dev, } -static ssize_t wl1271_sysfs_store_bt_coex_state(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t bt_coex_state_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { struct wl1271 *wl = dev_get_drvdata(dev); unsigned long res; @@ -71,13 +71,11 @@ static ssize_t wl1271_sysfs_store_bt_coex_state(struct device *dev, return count; } -static DEVICE_ATTR(bt_coex_state, 0644, - wl1271_sysfs_show_bt_coex_state, - wl1271_sysfs_store_bt_coex_state); +static DEVICE_ATTR_RW(bt_coex_state); -static ssize_t wl1271_sysfs_show_hw_pg_ver(struct device *dev, - struct device_attribute *attr, - char *buf) +static ssize_t hw_pg_ver_show(struct device *dev, + struct device_attribute *attr, + char *buf) { struct wl1271 *wl = dev_get_drvdata(dev); ssize_t len; @@ -94,7 +92,7 @@ static ssize_t wl1271_sysfs_show_hw_pg_ver(struct device *dev, return len; } -static DEVICE_ATTR(hw_pg_ver, 0444, wl1271_sysfs_show_hw_pg_ver, NULL); +static DEVICE_ATTR_RO(hw_pg_ver); static ssize_t wl1271_sysfs_read_fwlog(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c index 5c4cd0e1adeb..a7ceef10bf6a 100644 --- a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c +++ b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c @@ -1544,14 +1544,14 @@ static int __init usb_init(void) zd_workqueue = create_singlethread_workqueue(driver.name); if (zd_workqueue == NULL) { - printk(KERN_ERR "%s couldn't create workqueue\n", driver.name); + pr_err("%s couldn't create workqueue\n", driver.name); return -ENOMEM; } r = usb_register(&driver); if (r) { destroy_workqueue(zd_workqueue); - printk(KERN_ERR "%s usb_register() failed. Error number %d\n", + pr_err("%s usb_register() failed. Error number %d\n", driver.name, r); return r; } diff --git a/drivers/net/wwan/Kconfig b/drivers/net/wwan/Kconfig index 7ad1920120bc..de9384326bc8 100644 --- a/drivers/net/wwan/Kconfig +++ b/drivers/net/wwan/Kconfig @@ -3,15 +3,9 @@ # Wireless WAN device configuration # -menuconfig WWAN - bool "Wireless WAN" - help - This section contains Wireless WAN configuration for WWAN framework - and drivers. +menu "Wireless WAN" -if WWAN - -config WWAN_CORE +config WWAN tristate "WWAN Driver Core" help Say Y here if you want to use the WWAN driver core. This driver @@ -20,9 +14,19 @@ config WWAN_CORE To compile this driver as a module, choose M here: the module will be called wwan. +if WWAN + +config WWAN_HWSIM + tristate "Simulated WWAN device" + help + This driver is a developer testing tool that can be used to test WWAN + framework. + + To compile this driver as a module, choose M here: the module will be + called wwan_hwsim. If unsure, say N. + config MHI_WWAN_CTRL tristate "MHI WWAN control driver for QCOM-based PCIe modems" - select WWAN_CORE depends on MHI_BUS help MHI WWAN CTRL allows QCOM-based PCIe modems to expose different modem @@ -34,4 +38,35 @@ config MHI_WWAN_CTRL To compile this driver as a module, choose M here: the module will be called mhi_wwan_ctrl. +config RPMSG_WWAN_CTRL + tristate "RPMSG WWAN control driver" + depends on RPMSG + help + RPMSG WWAN CTRL allows modems available via RPMSG channels to expose + different modem protocols/ports to userspace, including AT and QMI. + These protocols can be accessed directly from userspace + (e.g. AT commands) or via libraries/tools (e.g. libqmi, libqcdm...). + + This is mainly used for modems integrated into many Qualcomm SoCs, + e.g. for AT and QMI on Qualcomm MSM8916 or MSM8974. Note that many + newer Qualcomm SoCs (e.g. SDM845) still provide an AT port through + this driver but the QMI messages can only be sent through + QRTR network sockets (CONFIG_QRTR). + + To compile this driver as a module, choose M here: the module will be + called rpmsg_wwan_ctrl. + +config IOSM + tristate "IOSM Driver for Intel M.2 WWAN Device" + depends on INTEL_IOMMU + help + This driver enables Intel M.2 WWAN Device communication. + + If you have one of those Intel M.2 WWAN Modules and wish to use it in + Linux say Y/M here. + + If unsure, say N. + endif # WWAN + +endmenu diff --git a/drivers/net/wwan/Makefile b/drivers/net/wwan/Makefile index 556cd90958ca..d90ac33abaef 100644 --- a/drivers/net/wwan/Makefile +++ b/drivers/net/wwan/Makefile @@ -3,7 +3,11 @@ # Makefile for the Linux WWAN device drivers. # -obj-$(CONFIG_WWAN_CORE) += wwan.o +obj-$(CONFIG_WWAN) += wwan.o wwan-objs += wwan_core.o +obj-$(CONFIG_WWAN_HWSIM) += wwan_hwsim.o + obj-$(CONFIG_MHI_WWAN_CTRL) += mhi_wwan_ctrl.o +obj-$(CONFIG_RPMSG_WWAN_CTRL) += rpmsg_wwan_ctrl.o +obj-$(CONFIG_IOSM) += iosm/ diff --git a/drivers/net/wwan/iosm/Makefile b/drivers/net/wwan/iosm/Makefile new file mode 100644 index 000000000000..4f9f0ae398e1 --- /dev/null +++ b/drivers/net/wwan/iosm/Makefile @@ -0,0 +1,23 @@ +# SPDX-License-Identifier: (GPL-2.0-only) +# +# Copyright (C) 2020-21 Intel Corporation. +# + +iosm-y = \ + iosm_ipc_task_queue.o \ + iosm_ipc_imem.o \ + iosm_ipc_imem_ops.o \ + iosm_ipc_mmio.o \ + iosm_ipc_port.o \ + iosm_ipc_wwan.o \ + iosm_ipc_uevent.o \ + iosm_ipc_pm.o \ + iosm_ipc_pcie.o \ + iosm_ipc_irq.o \ + iosm_ipc_chnl_cfg.o \ + iosm_ipc_protocol.o \ + iosm_ipc_protocol_ops.o \ + iosm_ipc_mux.o \ + iosm_ipc_mux_codec.o + +obj-$(CONFIG_IOSM) := iosm.o diff --git a/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c new file mode 100644 index 000000000000..804e6c4f2c78 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include + +#include "iosm_ipc_chnl_cfg.h" + +/* Max. sizes of a downlink buffers */ +#define IPC_MEM_MAX_DL_FLASH_BUF_SIZE (16 * 1024) +#define IPC_MEM_MAX_DL_LOOPBACK_SIZE (1 * 1024 * 1024) +#define IPC_MEM_MAX_DL_AT_BUF_SIZE 2048 +#define IPC_MEM_MAX_DL_RPC_BUF_SIZE (32 * 1024) +#define IPC_MEM_MAX_DL_MBIM_BUF_SIZE IPC_MEM_MAX_DL_RPC_BUF_SIZE + +/* Max. transfer descriptors for a pipe. */ +#define IPC_MEM_MAX_TDS_FLASH_DL 3 +#define IPC_MEM_MAX_TDS_FLASH_UL 6 +#define IPC_MEM_MAX_TDS_AT 4 +#define IPC_MEM_MAX_TDS_RPC 4 +#define IPC_MEM_MAX_TDS_MBIM IPC_MEM_MAX_TDS_RPC +#define IPC_MEM_MAX_TDS_LOOPBACK 11 + +/* Accumulation backoff usec */ +#define IRQ_ACC_BACKOFF_OFF 0 + +/* MUX acc backoff 1ms */ +#define IRQ_ACC_BACKOFF_MUX 1000 + +/* Modem channel configuration table + * Always reserve element zero for flash channel. + */ +static struct ipc_chnl_cfg modem_cfg[] = { + /* IP Mux */ + { IPC_MEM_IP_CHL_ID_0, IPC_MEM_PIPE_0, IPC_MEM_PIPE_1, + IPC_MEM_MAX_TDS_MUX_LITE_UL, IPC_MEM_MAX_TDS_MUX_LITE_DL, + IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE, WWAN_PORT_UNKNOWN }, + /* RPC - 0 */ + { IPC_MEM_CTRL_CHL_ID_1, IPC_MEM_PIPE_2, IPC_MEM_PIPE_3, + IPC_MEM_MAX_TDS_RPC, IPC_MEM_MAX_TDS_RPC, + IPC_MEM_MAX_DL_RPC_BUF_SIZE, WWAN_PORT_UNKNOWN }, + /* IAT0 */ + { IPC_MEM_CTRL_CHL_ID_2, IPC_MEM_PIPE_4, IPC_MEM_PIPE_5, + IPC_MEM_MAX_TDS_AT, IPC_MEM_MAX_TDS_AT, IPC_MEM_MAX_DL_AT_BUF_SIZE, + WWAN_PORT_AT }, + /* Trace */ + { IPC_MEM_CTRL_CHL_ID_3, IPC_MEM_PIPE_6, IPC_MEM_PIPE_7, + IPC_MEM_TDS_TRC, IPC_MEM_TDS_TRC, IPC_MEM_MAX_DL_TRC_BUF_SIZE, + WWAN_PORT_UNKNOWN }, + /* IAT1 */ + { IPC_MEM_CTRL_CHL_ID_4, IPC_MEM_PIPE_8, IPC_MEM_PIPE_9, + IPC_MEM_MAX_TDS_AT, IPC_MEM_MAX_TDS_AT, IPC_MEM_MAX_DL_AT_BUF_SIZE, + WWAN_PORT_AT }, + /* Loopback */ + { IPC_MEM_CTRL_CHL_ID_5, IPC_MEM_PIPE_10, IPC_MEM_PIPE_11, + IPC_MEM_MAX_TDS_LOOPBACK, IPC_MEM_MAX_TDS_LOOPBACK, + IPC_MEM_MAX_DL_LOOPBACK_SIZE, WWAN_PORT_UNKNOWN }, + /* MBIM Channel */ + { IPC_MEM_CTRL_CHL_ID_6, IPC_MEM_PIPE_12, IPC_MEM_PIPE_13, + IPC_MEM_MAX_TDS_MBIM, IPC_MEM_MAX_TDS_MBIM, + IPC_MEM_MAX_DL_MBIM_BUF_SIZE, WWAN_PORT_MBIM }, +}; + +int ipc_chnl_cfg_get(struct ipc_chnl_cfg *chnl_cfg, int index) +{ + int array_size = ARRAY_SIZE(modem_cfg); + + if (index >= array_size) { + pr_err("index: %d and array_size %d", index, array_size); + return -ECHRNG; + } + + if (index == IPC_MEM_MUX_IP_CH_IF_ID) + chnl_cfg->accumulation_backoff = IRQ_ACC_BACKOFF_MUX; + else + chnl_cfg->accumulation_backoff = IRQ_ACC_BACKOFF_OFF; + + chnl_cfg->ul_nr_of_entries = modem_cfg[index].ul_nr_of_entries; + chnl_cfg->dl_nr_of_entries = modem_cfg[index].dl_nr_of_entries; + chnl_cfg->dl_buf_size = modem_cfg[index].dl_buf_size; + chnl_cfg->id = modem_cfg[index].id; + chnl_cfg->ul_pipe = modem_cfg[index].ul_pipe; + chnl_cfg->dl_pipe = modem_cfg[index].dl_pipe; + chnl_cfg->wwan_port_type = modem_cfg[index].wwan_port_type; + + return 0; +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h new file mode 100644 index 000000000000..422471367f78 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation + */ + +#ifndef IOSM_IPC_CHNL_CFG_H +#define IOSM_IPC_CHNL_CFG_H + +#include "iosm_ipc_mux.h" + +/* Number of TDs on the trace channel */ +#define IPC_MEM_TDS_TRC 32 + +/* Trace channel TD buffer size. */ +#define IPC_MEM_MAX_DL_TRC_BUF_SIZE 8192 + +/* Channel ID */ +enum ipc_channel_id { + IPC_MEM_IP_CHL_ID_0 = 0, + IPC_MEM_CTRL_CHL_ID_1, + IPC_MEM_CTRL_CHL_ID_2, + IPC_MEM_CTRL_CHL_ID_3, + IPC_MEM_CTRL_CHL_ID_4, + IPC_MEM_CTRL_CHL_ID_5, + IPC_MEM_CTRL_CHL_ID_6, +}; + +/** + * struct ipc_chnl_cfg - IPC channel configuration structure + * @id: Interface ID + * @ul_pipe: Uplink datastream + * @dl_pipe: Downlink datastream + * @ul_nr_of_entries: Number of Transfer descriptor uplink pipe + * @dl_nr_of_entries: Number of Transfer descriptor downlink pipe + * @dl_buf_size: Downlink buffer size + * @wwan_port_type: Wwan subsystem port type + * @accumulation_backoff: Time in usec for data accumalation + */ +struct ipc_chnl_cfg { + u32 id; + u32 ul_pipe; + u32 dl_pipe; + u32 ul_nr_of_entries; + u32 dl_nr_of_entries; + u32 dl_buf_size; + u32 wwan_port_type; + u32 accumulation_backoff; +}; + +/** + * ipc_chnl_cfg_get - Get pipe configuration. + * @chnl_cfg: Array of ipc_chnl_cfg struct + * @index: Channel index (upto MAX_CHANNELS) + * + * Return: 0 on success and failure value on error + */ +int ipc_chnl_cfg_get(struct ipc_chnl_cfg *chnl_cfg, int index); + +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c new file mode 100644 index 000000000000..9f00e36b7f79 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c @@ -0,0 +1,1363 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include + +#include "iosm_ipc_chnl_cfg.h" +#include "iosm_ipc_imem.h" +#include "iosm_ipc_port.h" + +/* Check the wwan ips if it is valid with Channel as input. */ +static int ipc_imem_check_wwan_ips(struct ipc_mem_channel *chnl) +{ + if (chnl) + return chnl->ctype == IPC_CTYPE_WWAN && + chnl->if_id == IPC_MEM_MUX_IP_CH_IF_ID; + return false; +} + +static int ipc_imem_msg_send_device_sleep(struct iosm_imem *ipc_imem, u32 state) +{ + union ipc_msg_prep_args prep_args = { + .sleep.target = 1, + .sleep.state = state, + }; + + ipc_imem->device_sleep = state; + + return ipc_protocol_tq_msg_send(ipc_imem->ipc_protocol, + IPC_MSG_PREP_SLEEP, &prep_args, NULL); +} + +static bool ipc_imem_dl_skb_alloc(struct iosm_imem *ipc_imem, + struct ipc_pipe *pipe) +{ + /* limit max. nr of entries */ + if (pipe->nr_of_queued_entries >= pipe->max_nr_of_queued_entries) + return false; + + return ipc_protocol_dl_td_prepare(ipc_imem->ipc_protocol, pipe); +} + +/* This timer handler will retry DL buff allocation if a pipe has no free buf + * and gives doorbell if TD is available + */ +static int ipc_imem_tq_td_alloc_timer(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size) +{ + bool new_buffers_available = false; + bool retry_allocation = false; + int i; + + for (i = 0; i < IPC_MEM_MAX_CHANNELS; i++) { + struct ipc_pipe *pipe = &ipc_imem->channels[i].dl_pipe; + + if (!pipe->is_open || pipe->nr_of_queued_entries > 0) + continue; + + while (ipc_imem_dl_skb_alloc(ipc_imem, pipe)) + new_buffers_available = true; + + if (pipe->nr_of_queued_entries == 0) + retry_allocation = true; + } + + if (new_buffers_available) + ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol, + IPC_HP_DL_PROCESS); + + if (retry_allocation) { + ipc_imem->hrtimer_period = + ktime_set(0, IPC_TD_ALLOC_TIMER_PERIOD_MS * 1000 * 1000ULL); + if (!hrtimer_active(&ipc_imem->td_alloc_timer)) + hrtimer_start(&ipc_imem->td_alloc_timer, + ipc_imem->hrtimer_period, + HRTIMER_MODE_REL); + } + return 0; +} + +static enum hrtimer_restart ipc_imem_td_alloc_timer_cb(struct hrtimer *hr_timer) +{ + struct iosm_imem *ipc_imem = + container_of(hr_timer, struct iosm_imem, td_alloc_timer); + /* Post an async tasklet event to trigger HP update Doorbell */ + ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_td_alloc_timer, 0, NULL, + 0, false); + return HRTIMER_NORESTART; +} + +/* Fast update timer tasklet handler to trigger HP update */ +static int ipc_imem_tq_fast_update_timer_cb(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size) +{ + ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol, + IPC_HP_FAST_TD_UPD_TMR); + + return 0; +} + +static enum hrtimer_restart +ipc_imem_fast_update_timer_cb(struct hrtimer *hr_timer) +{ + struct iosm_imem *ipc_imem = + container_of(hr_timer, struct iosm_imem, fast_update_timer); + /* Post an async tasklet event to trigger HP update Doorbell */ + ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_fast_update_timer_cb, 0, + NULL, 0, false); + return HRTIMER_NORESTART; +} + +static int ipc_imem_setup_cp_mux_cap_init(struct iosm_imem *ipc_imem, + struct ipc_mux_config *cfg) +{ + ipc_mmio_update_cp_capability(ipc_imem->mmio); + + if (!ipc_imem->mmio->has_mux_lite) { + dev_err(ipc_imem->dev, "Failed to get Mux capability."); + return -EINVAL; + } + + cfg->protocol = MUX_LITE; + + cfg->ul_flow = (ipc_imem->mmio->has_ul_flow_credit == 1) ? + MUX_UL_ON_CREDITS : + MUX_UL; + + /* The instance ID is same as channel ID because this is been reused + * for channel alloc function. + */ + cfg->instance_id = IPC_MEM_MUX_IP_CH_IF_ID; + cfg->nr_sessions = IPC_MEM_MUX_IP_SESSION_ENTRIES; + + return 0; +} + +void ipc_imem_msg_send_feature_set(struct iosm_imem *ipc_imem, + unsigned int reset_enable, bool atomic_ctx) +{ + union ipc_msg_prep_args prep_args = { .feature_set.reset_enable = + reset_enable }; + + if (atomic_ctx) + ipc_protocol_tq_msg_send(ipc_imem->ipc_protocol, + IPC_MSG_PREP_FEATURE_SET, &prep_args, + NULL); + else + ipc_protocol_msg_send(ipc_imem->ipc_protocol, + IPC_MSG_PREP_FEATURE_SET, &prep_args); +} + +void ipc_imem_td_update_timer_start(struct iosm_imem *ipc_imem) +{ + /* Use the TD update timer only in the runtime phase */ + if (!ipc_imem->enter_runtime || ipc_imem->td_update_timer_suspended) { + /* trigger the doorbell irq on CP directly. */ + ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol, + IPC_HP_TD_UPD_TMR_START); + return; + } + + if (!hrtimer_active(&ipc_imem->tdupdate_timer)) { + ipc_imem->hrtimer_period = + ktime_set(0, TD_UPDATE_DEFAULT_TIMEOUT_USEC * 1000ULL); + if (!hrtimer_active(&ipc_imem->tdupdate_timer)) + hrtimer_start(&ipc_imem->tdupdate_timer, + ipc_imem->hrtimer_period, + HRTIMER_MODE_REL); + } +} + +void ipc_imem_hrtimer_stop(struct hrtimer *hr_timer) +{ + if (hrtimer_active(hr_timer)) + hrtimer_cancel(hr_timer); +} + +bool ipc_imem_ul_write_td(struct iosm_imem *ipc_imem) +{ + struct ipc_mem_channel *channel; + struct sk_buff_head *ul_list; + bool hpda_pending = false; + bool forced_hpdu = false; + struct ipc_pipe *pipe; + int i; + + /* Analyze the uplink pipe of all active channels. */ + for (i = 0; i < ipc_imem->nr_of_channels; i++) { + channel = &ipc_imem->channels[i]; + + if (channel->state != IMEM_CHANNEL_ACTIVE) + continue; + + pipe = &channel->ul_pipe; + + /* Get the reference to the skbuf accumulator list. */ + ul_list = &channel->ul_list; + + /* Fill the transfer descriptor with the uplink buffer info. */ + hpda_pending |= ipc_protocol_ul_td_send(ipc_imem->ipc_protocol, + pipe, ul_list); + + /* forced HP update needed for non data channels */ + if (hpda_pending && !ipc_imem_check_wwan_ips(channel)) + forced_hpdu = true; + } + + if (forced_hpdu) { + hpda_pending = false; + ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol, + IPC_HP_UL_WRITE_TD); + } + + return hpda_pending; +} + +void ipc_imem_ipc_init_check(struct iosm_imem *ipc_imem) +{ + int timeout = IPC_MODEM_BOOT_TIMEOUT; + + ipc_imem->ipc_requested_state = IPC_MEM_DEVICE_IPC_INIT; + + /* Trigger the CP interrupt to enter the init state. */ + ipc_doorbell_fire(ipc_imem->pcie, IPC_DOORBELL_IRQ_IPC, + IPC_MEM_DEVICE_IPC_INIT); + /* Wait for the CP update. */ + do { + if (ipc_mmio_get_ipc_state(ipc_imem->mmio) == + ipc_imem->ipc_requested_state) { + /* Prepare the MMIO space */ + ipc_mmio_config(ipc_imem->mmio); + + /* Trigger the CP irq to enter the running state. */ + ipc_imem->ipc_requested_state = + IPC_MEM_DEVICE_IPC_RUNNING; + ipc_doorbell_fire(ipc_imem->pcie, IPC_DOORBELL_IRQ_IPC, + IPC_MEM_DEVICE_IPC_RUNNING); + + return; + } + msleep(20); + } while (--timeout); + + /* timeout */ + dev_err(ipc_imem->dev, "%s: ipc_status(%d) ne. IPC_MEM_DEVICE_IPC_INIT", + ipc_imem_phase_get_string(ipc_imem->phase), + ipc_mmio_get_ipc_state(ipc_imem->mmio)); + + ipc_uevent_send(ipc_imem->dev, UEVENT_MDM_TIMEOUT); +} + +/* Analyze the packet type and distribute it. */ +static void ipc_imem_dl_skb_process(struct iosm_imem *ipc_imem, + struct ipc_pipe *pipe, struct sk_buff *skb) +{ + u16 port_id; + + if (!skb) + return; + + /* An AT/control or IP packet is expected. */ + switch (pipe->channel->ctype) { + case IPC_CTYPE_CTRL: + port_id = pipe->channel->channel_id; + + /* Pass the packet to the wwan layer. */ + wwan_port_rx(ipc_imem->ipc_port[port_id]->iosm_port, skb); + break; + + case IPC_CTYPE_WWAN: + if (pipe->channel->if_id == IPC_MEM_MUX_IP_CH_IF_ID) + ipc_mux_dl_decode(ipc_imem->mux, skb); + break; + default: + dev_err(ipc_imem->dev, "Invalid channel type"); + break; + } +} + +/* Process the downlink data and pass them to the char or net layer. */ +static void ipc_imem_dl_pipe_process(struct iosm_imem *ipc_imem, + struct ipc_pipe *pipe) +{ + s32 cnt = 0, processed_td_cnt = 0; + struct ipc_mem_channel *channel; + u32 head = 0, tail = 0; + bool processed = false; + struct sk_buff *skb; + + channel = pipe->channel; + + ipc_protocol_get_head_tail_index(ipc_imem->ipc_protocol, pipe, &head, + &tail); + if (pipe->old_tail != tail) { + if (pipe->old_tail < tail) + cnt = tail - pipe->old_tail; + else + cnt = pipe->nr_of_entries - pipe->old_tail + tail; + } + + processed_td_cnt = cnt; + + /* Seek for pipes with pending DL data. */ + while (cnt--) { + skb = ipc_protocol_dl_td_process(ipc_imem->ipc_protocol, pipe); + + /* Analyze the packet type and distribute it. */ + ipc_imem_dl_skb_process(ipc_imem, pipe, skb); + } + + /* try to allocate new empty DL SKbs from head..tail - 1*/ + while (ipc_imem_dl_skb_alloc(ipc_imem, pipe)) + processed = true; + + if (processed && !ipc_imem_check_wwan_ips(channel)) { + /* Force HP update for non IP channels */ + ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol, + IPC_HP_DL_PROCESS); + processed = false; + + /* If Fast Update timer is already running then stop */ + ipc_imem_hrtimer_stop(&ipc_imem->fast_update_timer); + } + + /* Any control channel process will get immediate HP update. + * Start Fast update timer only for IP channel if all the TDs were + * used in last process. + */ + if (processed && (processed_td_cnt == pipe->nr_of_entries - 1)) { + ipc_imem->hrtimer_period = + ktime_set(0, FORCE_UPDATE_DEFAULT_TIMEOUT_USEC * 1000ULL); + hrtimer_start(&ipc_imem->fast_update_timer, + ipc_imem->hrtimer_period, HRTIMER_MODE_REL); + } + + if (ipc_imem->app_notify_dl_pend) + complete(&ipc_imem->dl_pend_sem); +} + +/* process open uplink pipe */ +static void ipc_imem_ul_pipe_process(struct iosm_imem *ipc_imem, + struct ipc_pipe *pipe) +{ + struct ipc_mem_channel *channel; + u32 tail = 0, head = 0; + struct sk_buff *skb; + s32 cnt = 0; + + channel = pipe->channel; + + /* Get the internal phase. */ + ipc_protocol_get_head_tail_index(ipc_imem->ipc_protocol, pipe, &head, + &tail); + + if (pipe->old_tail != tail) { + if (pipe->old_tail < tail) + cnt = tail - pipe->old_tail; + else + cnt = pipe->nr_of_entries - pipe->old_tail + tail; + } + + /* Free UL buffers. */ + while (cnt--) { + skb = ipc_protocol_ul_td_process(ipc_imem->ipc_protocol, pipe); + + if (!skb) + continue; + + /* If the user app was suspended in uplink direction - blocking + * write, resume it. + */ + if (IPC_CB(skb)->op_type == UL_USR_OP_BLOCKED) + complete(&channel->ul_sem); + + /* Free the skbuf element. */ + if (IPC_CB(skb)->op_type == UL_MUX_OP_ADB) { + if (channel->if_id == IPC_MEM_MUX_IP_CH_IF_ID) + ipc_mux_ul_encoded_process(ipc_imem->mux, skb); + else + dev_err(ipc_imem->dev, + "OP Type is UL_MUX, unknown if_id %d", + channel->if_id); + } else { + ipc_pcie_kfree_skb(ipc_imem->pcie, skb); + } + } + + /* Trace channel stats for IP UL pipe. */ + if (ipc_imem_check_wwan_ips(pipe->channel)) + ipc_mux_check_n_restart_tx(ipc_imem->mux); + + if (ipc_imem->app_notify_ul_pend) + complete(&ipc_imem->ul_pend_sem); +} + +/* Executes the irq. */ +static void ipc_imem_rom_irq_exec(struct iosm_imem *ipc_imem) +{ + struct ipc_mem_channel *channel; + + if (ipc_imem->flash_channel_id < 0) { + ipc_imem->rom_exit_code = IMEM_ROM_EXIT_FAIL; + dev_err(ipc_imem->dev, "Missing flash app:%d", + ipc_imem->flash_channel_id); + return; + } + + ipc_imem->rom_exit_code = ipc_mmio_get_rom_exit_code(ipc_imem->mmio); + + /* Wake up the flash app to continue or to terminate depending + * on the CP ROM exit code. + */ + channel = &ipc_imem->channels[ipc_imem->flash_channel_id]; + complete(&channel->ul_sem); +} + +/* Execute the UL bundle timer actions, generating the doorbell irq. */ +static int ipc_imem_tq_td_update_timer_cb(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size) +{ + ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol, + IPC_HP_TD_UPD_TMR); + return 0; +} + +/* Consider link power management in the runtime phase. */ +static void ipc_imem_slp_control_exec(struct iosm_imem *ipc_imem) +{ + /* link will go down, Test pending UL packets.*/ + if (ipc_protocol_pm_dev_sleep_handle(ipc_imem->ipc_protocol) && + hrtimer_active(&ipc_imem->tdupdate_timer)) { + /* Generate the doorbell irq. */ + ipc_imem_tq_td_update_timer_cb(ipc_imem, 0, NULL, 0); + /* Stop the TD update timer. */ + ipc_imem_hrtimer_stop(&ipc_imem->tdupdate_timer); + /* Stop the fast update timer. */ + ipc_imem_hrtimer_stop(&ipc_imem->fast_update_timer); + } +} + +/* Execute startup timer and wait for delayed start (e.g. NAND) */ +static int ipc_imem_tq_startup_timer_cb(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size) +{ + /* Update & check the current operation phase. */ + if (ipc_imem_phase_update(ipc_imem) != IPC_P_RUN) + return -EIO; + + if (ipc_mmio_get_ipc_state(ipc_imem->mmio) == + IPC_MEM_DEVICE_IPC_UNINIT) { + ipc_imem->ipc_requested_state = IPC_MEM_DEVICE_IPC_INIT; + + ipc_doorbell_fire(ipc_imem->pcie, IPC_DOORBELL_IRQ_IPC, + IPC_MEM_DEVICE_IPC_INIT); + + ipc_imem->hrtimer_period = ktime_set(0, 100 * 1000UL * 1000ULL); + /* reduce period to 100 ms to check for mmio init state */ + if (!hrtimer_active(&ipc_imem->startup_timer)) + hrtimer_start(&ipc_imem->startup_timer, + ipc_imem->hrtimer_period, + HRTIMER_MODE_REL); + } else if (ipc_mmio_get_ipc_state(ipc_imem->mmio) == + IPC_MEM_DEVICE_IPC_INIT) { + /* Startup complete - disable timer */ + ipc_imem_hrtimer_stop(&ipc_imem->startup_timer); + + /* Prepare the MMIO space */ + ipc_mmio_config(ipc_imem->mmio); + ipc_imem->ipc_requested_state = IPC_MEM_DEVICE_IPC_RUNNING; + ipc_doorbell_fire(ipc_imem->pcie, IPC_DOORBELL_IRQ_IPC, + IPC_MEM_DEVICE_IPC_RUNNING); + } + + return 0; +} + +static enum hrtimer_restart ipc_imem_startup_timer_cb(struct hrtimer *hr_timer) +{ + enum hrtimer_restart result = HRTIMER_NORESTART; + struct iosm_imem *ipc_imem = + container_of(hr_timer, struct iosm_imem, startup_timer); + + if (ktime_to_ns(ipc_imem->hrtimer_period)) { + hrtimer_forward(&ipc_imem->startup_timer, ktime_get(), + ipc_imem->hrtimer_period); + result = HRTIMER_RESTART; + } + + ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_startup_timer_cb, 0, + NULL, 0, false); + return result; +} + +/* Get the CP execution stage */ +static enum ipc_mem_exec_stage +ipc_imem_get_exec_stage_buffered(struct iosm_imem *ipc_imem) +{ + return (ipc_imem->phase == IPC_P_RUN && + ipc_imem->ipc_status == IPC_MEM_DEVICE_IPC_RUNNING) ? + ipc_protocol_get_ap_exec_stage(ipc_imem->ipc_protocol) : + ipc_mmio_get_exec_stage(ipc_imem->mmio); +} + +/* Callback to send the modem ready uevent */ +static int ipc_imem_send_mdm_rdy_cb(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size) +{ + enum ipc_mem_exec_stage exec_stage = + ipc_imem_get_exec_stage_buffered(ipc_imem); + + if (exec_stage == IPC_MEM_EXEC_STAGE_RUN) + ipc_uevent_send(ipc_imem->dev, UEVENT_MDM_READY); + + return 0; +} + +/* This function is executed in a task context via an ipc_worker object, + * as the creation or removal of device can't be done from tasklet. + */ +static void ipc_imem_run_state_worker(struct work_struct *instance) +{ + struct ipc_chnl_cfg chnl_cfg_port = { 0 }; + struct ipc_mux_config mux_cfg; + struct iosm_imem *ipc_imem; + u8 ctrl_chl_idx = 0; + + ipc_imem = container_of(instance, struct iosm_imem, run_state_worker); + + if (ipc_imem->phase != IPC_P_RUN) { + dev_err(ipc_imem->dev, + "Modem link down. Exit run state worker."); + return; + } + + if (!ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg)) + ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem); + + ipc_imem_wwan_channel_init(ipc_imem, mux_cfg.protocol); + if (ipc_imem->mux) + ipc_imem->mux->wwan = ipc_imem->wwan; + + while (ctrl_chl_idx < IPC_MEM_MAX_CHANNELS) { + if (!ipc_chnl_cfg_get(&chnl_cfg_port, ctrl_chl_idx)) { + ipc_imem->ipc_port[ctrl_chl_idx] = NULL; + if (chnl_cfg_port.wwan_port_type != WWAN_PORT_UNKNOWN) { + ipc_imem_channel_init(ipc_imem, IPC_CTYPE_CTRL, + chnl_cfg_port, + IRQ_MOD_OFF); + ipc_imem->ipc_port[ctrl_chl_idx] = + ipc_port_init(ipc_imem, chnl_cfg_port); + } + } + ctrl_chl_idx++; + } + + ipc_task_queue_send_task(ipc_imem, ipc_imem_send_mdm_rdy_cb, 0, NULL, 0, + false); + + /* Complete all memory stores before setting bit */ + smp_mb__before_atomic(); + + set_bit(FULLY_FUNCTIONAL, &ipc_imem->flag); + + /* Complete all memory stores after setting bit */ + smp_mb__after_atomic(); +} + +static void ipc_imem_handle_irq(struct iosm_imem *ipc_imem, int irq) +{ + enum ipc_mem_device_ipc_state curr_ipc_status; + enum ipc_phase old_phase, phase; + bool retry_allocation = false; + bool ul_pending = false; + int ch_id, i; + + if (irq != IMEM_IRQ_DONT_CARE) + ipc_imem->ev_irq_pending[irq] = false; + + /* Get the internal phase. */ + old_phase = ipc_imem->phase; + + if (old_phase == IPC_P_OFF_REQ) { + dev_dbg(ipc_imem->dev, + "[%s]: Ignoring MSI. Deinit sequence in progress!", + ipc_imem_phase_get_string(old_phase)); + return; + } + + /* Update the phase controlled by CP. */ + phase = ipc_imem_phase_update(ipc_imem); + + switch (phase) { + case IPC_P_RUN: + if (!ipc_imem->enter_runtime) { + /* Excute the transition from flash/boot to runtime. */ + ipc_imem->enter_runtime = 1; + + /* allow device to sleep, default value is + * IPC_HOST_SLEEP_ENTER_SLEEP + */ + ipc_imem_msg_send_device_sleep(ipc_imem, + ipc_imem->device_sleep); + + ipc_imem_msg_send_feature_set(ipc_imem, + IPC_MEM_INBAND_CRASH_SIG, + true); + } + + curr_ipc_status = + ipc_protocol_get_ipc_status(ipc_imem->ipc_protocol); + + /* check ipc_status change */ + if (ipc_imem->ipc_status != curr_ipc_status) { + ipc_imem->ipc_status = curr_ipc_status; + + if (ipc_imem->ipc_status == + IPC_MEM_DEVICE_IPC_RUNNING) { + schedule_work(&ipc_imem->run_state_worker); + } + } + + /* Consider power management in the runtime phase. */ + ipc_imem_slp_control_exec(ipc_imem); + break; /* Continue with skbuf processing. */ + + /* Unexpected phases. */ + case IPC_P_OFF: + case IPC_P_OFF_REQ: + dev_err(ipc_imem->dev, "confused phase %s", + ipc_imem_phase_get_string(phase)); + return; + + case IPC_P_PSI: + if (old_phase != IPC_P_ROM) + break; + + fallthrough; + /* On CP the PSI phase is already active. */ + + case IPC_P_ROM: + /* Before CP ROM driver starts the PSI image, it sets + * the exit_code field on the doorbell scratchpad and + * triggers the irq. + */ + ipc_imem_rom_irq_exec(ipc_imem); + return; + + default: + break; + } + + /* process message ring */ + ipc_protocol_msg_process(ipc_imem, irq); + + /* process all open pipes */ + for (i = 0; i < IPC_MEM_MAX_CHANNELS; i++) { + struct ipc_pipe *ul_pipe = &ipc_imem->channels[i].ul_pipe; + struct ipc_pipe *dl_pipe = &ipc_imem->channels[i].dl_pipe; + + if (dl_pipe->is_open && + (irq == IMEM_IRQ_DONT_CARE || irq == dl_pipe->irq)) { + ipc_imem_dl_pipe_process(ipc_imem, dl_pipe); + + if (dl_pipe->nr_of_queued_entries == 0) + retry_allocation = true; + } + + if (ul_pipe->is_open) + ipc_imem_ul_pipe_process(ipc_imem, ul_pipe); + } + + /* Try to generate new ADB or ADGH. */ + if (ipc_mux_ul_data_encode(ipc_imem->mux)) + ipc_imem_td_update_timer_start(ipc_imem); + + /* Continue the send procedure with accumulated SIO or NETIF packets. + * Reset the debounce flags. + */ + ul_pending |= ipc_imem_ul_write_td(ipc_imem); + + /* if UL data is pending restart TD update timer */ + if (ul_pending) { + ipc_imem->hrtimer_period = + ktime_set(0, TD_UPDATE_DEFAULT_TIMEOUT_USEC * 1000ULL); + if (!hrtimer_active(&ipc_imem->tdupdate_timer)) + hrtimer_start(&ipc_imem->tdupdate_timer, + ipc_imem->hrtimer_period, + HRTIMER_MODE_REL); + } + + /* If CP has executed the transition + * from IPC_INIT to IPC_RUNNING in the PSI + * phase, wake up the flash app to open the pipes. + */ + if ((phase == IPC_P_PSI || phase == IPC_P_EBL) && + ipc_imem->ipc_requested_state == IPC_MEM_DEVICE_IPC_RUNNING && + ipc_mmio_get_ipc_state(ipc_imem->mmio) == + IPC_MEM_DEVICE_IPC_RUNNING && + ipc_imem->flash_channel_id >= 0) { + /* Wake up the flash app to open the pipes. */ + ch_id = ipc_imem->flash_channel_id; + complete(&ipc_imem->channels[ch_id].ul_sem); + } + + /* Reset the expected CP state. */ + ipc_imem->ipc_requested_state = IPC_MEM_DEVICE_IPC_DONT_CARE; + + if (retry_allocation) { + ipc_imem->hrtimer_period = + ktime_set(0, IPC_TD_ALLOC_TIMER_PERIOD_MS * 1000 * 1000ULL); + if (!hrtimer_active(&ipc_imem->td_alloc_timer)) + hrtimer_start(&ipc_imem->td_alloc_timer, + ipc_imem->hrtimer_period, + HRTIMER_MODE_REL); + } +} + +/* Callback by tasklet for handling interrupt events. */ +static int ipc_imem_tq_irq_cb(struct iosm_imem *ipc_imem, int arg, void *msg, + size_t size) +{ + ipc_imem_handle_irq(ipc_imem, arg); + + return 0; +} + +void ipc_imem_ul_send(struct iosm_imem *ipc_imem) +{ + /* start doorbell irq delay timer if UL is pending */ + if (ipc_imem_ul_write_td(ipc_imem)) + ipc_imem_td_update_timer_start(ipc_imem); +} + +/* Check the execution stage and update the AP phase */ +static enum ipc_phase ipc_imem_phase_update_check(struct iosm_imem *ipc_imem, + enum ipc_mem_exec_stage stage) +{ + switch (stage) { + case IPC_MEM_EXEC_STAGE_BOOT: + if (ipc_imem->phase != IPC_P_ROM) { + /* Send this event only once */ + ipc_uevent_send(ipc_imem->dev, UEVENT_ROM_READY); + } + + ipc_imem->phase = IPC_P_ROM; + break; + + case IPC_MEM_EXEC_STAGE_PSI: + ipc_imem->phase = IPC_P_PSI; + break; + + case IPC_MEM_EXEC_STAGE_EBL: + ipc_imem->phase = IPC_P_EBL; + break; + + case IPC_MEM_EXEC_STAGE_RUN: + if (ipc_imem->phase != IPC_P_RUN && + ipc_imem->ipc_status == IPC_MEM_DEVICE_IPC_RUNNING) { + ipc_uevent_send(ipc_imem->dev, UEVENT_MDM_READY); + } + ipc_imem->phase = IPC_P_RUN; + break; + + case IPC_MEM_EXEC_STAGE_CRASH: + if (ipc_imem->phase != IPC_P_CRASH) + ipc_uevent_send(ipc_imem->dev, UEVENT_CRASH); + + ipc_imem->phase = IPC_P_CRASH; + break; + + case IPC_MEM_EXEC_STAGE_CD_READY: + if (ipc_imem->phase != IPC_P_CD_READY) + ipc_uevent_send(ipc_imem->dev, UEVENT_CD_READY); + ipc_imem->phase = IPC_P_CD_READY; + break; + + default: + /* unknown exec stage: + * assume that link is down and send info to listeners + */ + ipc_uevent_send(ipc_imem->dev, UEVENT_CD_READY_LINK_DOWN); + break; + } + + return ipc_imem->phase; +} + +/* Send msg to device to open pipe */ +static bool ipc_imem_pipe_open(struct iosm_imem *ipc_imem, + struct ipc_pipe *pipe) +{ + union ipc_msg_prep_args prep_args = { + .pipe_open.pipe = pipe, + }; + + if (ipc_protocol_msg_send(ipc_imem->ipc_protocol, + IPC_MSG_PREP_PIPE_OPEN, &prep_args) == 0) + pipe->is_open = true; + + return pipe->is_open; +} + +/* Allocates the TDs for the given pipe along with firing HP update DB. */ +static int ipc_imem_tq_pipe_td_alloc(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size) +{ + struct ipc_pipe *dl_pipe = msg; + bool processed = false; + int i; + + for (i = 0; i < dl_pipe->nr_of_entries - 1; i++) + processed |= ipc_imem_dl_skb_alloc(ipc_imem, dl_pipe); + + /* Trigger the doorbell irq to inform CP that new downlink buffers are + * available. + */ + if (processed) + ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol, arg); + + return 0; +} + +static enum hrtimer_restart +ipc_imem_td_update_timer_cb(struct hrtimer *hr_timer) +{ + struct iosm_imem *ipc_imem = + container_of(hr_timer, struct iosm_imem, tdupdate_timer); + + ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_td_update_timer_cb, 0, + NULL, 0, false); + return HRTIMER_NORESTART; +} + +/* Get the CP execution state and map it to the AP phase. */ +enum ipc_phase ipc_imem_phase_update(struct iosm_imem *ipc_imem) +{ + enum ipc_mem_exec_stage exec_stage = + ipc_imem_get_exec_stage_buffered(ipc_imem); + /* If the CP stage is undef, return the internal precalculated phase. */ + return ipc_imem->phase == IPC_P_OFF_REQ ? + ipc_imem->phase : + ipc_imem_phase_update_check(ipc_imem, exec_stage); +} + +const char *ipc_imem_phase_get_string(enum ipc_phase phase) +{ + switch (phase) { + case IPC_P_RUN: + return "A-RUN"; + + case IPC_P_OFF: + return "A-OFF"; + + case IPC_P_ROM: + return "A-ROM"; + + case IPC_P_PSI: + return "A-PSI"; + + case IPC_P_EBL: + return "A-EBL"; + + case IPC_P_CRASH: + return "A-CRASH"; + + case IPC_P_CD_READY: + return "A-CD_READY"; + + case IPC_P_OFF_REQ: + return "A-OFF_REQ"; + + default: + return "A-???"; + } +} + +void ipc_imem_pipe_close(struct iosm_imem *ipc_imem, struct ipc_pipe *pipe) +{ + union ipc_msg_prep_args prep_args = { .pipe_close.pipe = pipe }; + + pipe->is_open = false; + ipc_protocol_msg_send(ipc_imem->ipc_protocol, IPC_MSG_PREP_PIPE_CLOSE, + &prep_args); + + ipc_imem_pipe_cleanup(ipc_imem, pipe); +} + +void ipc_imem_channel_close(struct iosm_imem *ipc_imem, int channel_id) +{ + struct ipc_mem_channel *channel; + + if (channel_id < 0 || channel_id >= ipc_imem->nr_of_channels) { + dev_err(ipc_imem->dev, "invalid channel id %d", channel_id); + return; + } + + channel = &ipc_imem->channels[channel_id]; + + if (channel->state == IMEM_CHANNEL_FREE) { + dev_err(ipc_imem->dev, "ch[%d]: invalid channel state %d", + channel_id, channel->state); + return; + } + + /* Free only the channel id in the CP power off mode. */ + if (channel->state == IMEM_CHANNEL_RESERVED) + /* Release only the channel id. */ + goto channel_free; + + if (ipc_imem->phase == IPC_P_RUN) { + ipc_imem_pipe_close(ipc_imem, &channel->ul_pipe); + ipc_imem_pipe_close(ipc_imem, &channel->dl_pipe); + } + + ipc_imem_pipe_cleanup(ipc_imem, &channel->ul_pipe); + ipc_imem_pipe_cleanup(ipc_imem, &channel->dl_pipe); + +channel_free: + ipc_imem_channel_free(channel); +} + +struct ipc_mem_channel *ipc_imem_channel_open(struct iosm_imem *ipc_imem, + int channel_id, u32 db_id) +{ + struct ipc_mem_channel *channel; + + if (channel_id < 0 || channel_id >= IPC_MEM_MAX_CHANNELS) { + dev_err(ipc_imem->dev, "invalid channel ID: %d", channel_id); + return NULL; + } + + channel = &ipc_imem->channels[channel_id]; + + channel->state = IMEM_CHANNEL_ACTIVE; + + if (!ipc_imem_pipe_open(ipc_imem, &channel->ul_pipe)) + goto ul_pipe_err; + + if (!ipc_imem_pipe_open(ipc_imem, &channel->dl_pipe)) + goto dl_pipe_err; + + /* Allocate the downlink buffers in tasklet context. */ + if (ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_pipe_td_alloc, db_id, + &channel->dl_pipe, 0, false)) { + dev_err(ipc_imem->dev, "td allocation failed : %d", channel_id); + goto task_failed; + } + + /* Active channel. */ + return channel; +task_failed: + ipc_imem_pipe_close(ipc_imem, &channel->dl_pipe); +dl_pipe_err: + ipc_imem_pipe_close(ipc_imem, &channel->ul_pipe); +ul_pipe_err: + ipc_imem_channel_free(channel); + return NULL; +} + +void ipc_imem_pm_suspend(struct iosm_imem *ipc_imem) +{ + ipc_protocol_suspend(ipc_imem->ipc_protocol); +} + +void ipc_imem_pm_s2idle_sleep(struct iosm_imem *ipc_imem, bool sleep) +{ + ipc_protocol_s2idle_sleep(ipc_imem->ipc_protocol, sleep); +} + +void ipc_imem_pm_resume(struct iosm_imem *ipc_imem) +{ + enum ipc_mem_exec_stage stage; + + if (ipc_protocol_resume(ipc_imem->ipc_protocol)) { + stage = ipc_mmio_get_exec_stage(ipc_imem->mmio); + ipc_imem_phase_update_check(ipc_imem, stage); + } +} + +void ipc_imem_channel_free(struct ipc_mem_channel *channel) +{ + /* Reset dynamic channel elements. */ + channel->state = IMEM_CHANNEL_FREE; +} + +int ipc_imem_channel_alloc(struct iosm_imem *ipc_imem, int index, + enum ipc_ctype ctype) +{ + struct ipc_mem_channel *channel; + int i; + + /* Find channel of given type/index */ + for (i = 0; i < ipc_imem->nr_of_channels; i++) { + channel = &ipc_imem->channels[i]; + if (channel->ctype == ctype && channel->index == index) + break; + } + + if (i >= ipc_imem->nr_of_channels) { + dev_dbg(ipc_imem->dev, + "no channel definition for index=%d ctype=%d", index, + ctype); + return -ECHRNG; + } + + if (ipc_imem->channels[i].state != IMEM_CHANNEL_FREE) { + dev_dbg(ipc_imem->dev, "channel is in use"); + return -EBUSY; + } + + if (channel->ctype == IPC_CTYPE_WWAN && + index == IPC_MEM_MUX_IP_CH_IF_ID) + channel->if_id = index; + + channel->channel_id = index; + channel->state = IMEM_CHANNEL_RESERVED; + + return i; +} + +void ipc_imem_channel_init(struct iosm_imem *ipc_imem, enum ipc_ctype ctype, + struct ipc_chnl_cfg chnl_cfg, u32 irq_moderation) +{ + struct ipc_mem_channel *channel; + + if (chnl_cfg.ul_pipe >= IPC_MEM_MAX_PIPES || + chnl_cfg.dl_pipe >= IPC_MEM_MAX_PIPES) { + dev_err(ipc_imem->dev, "invalid pipe: ul_pipe=%d, dl_pipe=%d", + chnl_cfg.ul_pipe, chnl_cfg.dl_pipe); + return; + } + + if (ipc_imem->nr_of_channels >= IPC_MEM_MAX_CHANNELS) { + dev_err(ipc_imem->dev, "too many channels"); + return; + } + + channel = &ipc_imem->channels[ipc_imem->nr_of_channels]; + channel->channel_id = ipc_imem->nr_of_channels; + channel->ctype = ctype; + channel->index = chnl_cfg.id; + channel->net_err_count = 0; + channel->state = IMEM_CHANNEL_FREE; + ipc_imem->nr_of_channels++; + + ipc_imem_channel_update(ipc_imem, channel->channel_id, chnl_cfg, + IRQ_MOD_OFF); + + skb_queue_head_init(&channel->ul_list); + + init_completion(&channel->ul_sem); +} + +void ipc_imem_channel_update(struct iosm_imem *ipc_imem, int id, + struct ipc_chnl_cfg chnl_cfg, u32 irq_moderation) +{ + struct ipc_mem_channel *channel; + + if (id < 0 || id >= ipc_imem->nr_of_channels) { + dev_err(ipc_imem->dev, "invalid channel id %d", id); + return; + } + + channel = &ipc_imem->channels[id]; + + if (channel->state != IMEM_CHANNEL_FREE && + channel->state != IMEM_CHANNEL_RESERVED) { + dev_err(ipc_imem->dev, "invalid channel state %d", + channel->state); + return; + } + + channel->ul_pipe.nr_of_entries = chnl_cfg.ul_nr_of_entries; + channel->ul_pipe.pipe_nr = chnl_cfg.ul_pipe; + channel->ul_pipe.is_open = false; + channel->ul_pipe.irq = IPC_UL_PIPE_IRQ_VECTOR; + channel->ul_pipe.channel = channel; + channel->ul_pipe.dir = IPC_MEM_DIR_UL; + channel->ul_pipe.accumulation_backoff = chnl_cfg.accumulation_backoff; + channel->ul_pipe.irq_moderation = irq_moderation; + channel->ul_pipe.buf_size = 0; + + channel->dl_pipe.nr_of_entries = chnl_cfg.dl_nr_of_entries; + channel->dl_pipe.pipe_nr = chnl_cfg.dl_pipe; + channel->dl_pipe.is_open = false; + channel->dl_pipe.irq = IPC_DL_PIPE_IRQ_VECTOR; + channel->dl_pipe.channel = channel; + channel->dl_pipe.dir = IPC_MEM_DIR_DL; + channel->dl_pipe.accumulation_backoff = chnl_cfg.accumulation_backoff; + channel->dl_pipe.irq_moderation = irq_moderation; + channel->dl_pipe.buf_size = chnl_cfg.dl_buf_size; +} + +static void ipc_imem_channel_reset(struct iosm_imem *ipc_imem) +{ + int i; + + for (i = 0; i < ipc_imem->nr_of_channels; i++) { + struct ipc_mem_channel *channel; + + channel = &ipc_imem->channels[i]; + + ipc_imem_pipe_cleanup(ipc_imem, &channel->dl_pipe); + ipc_imem_pipe_cleanup(ipc_imem, &channel->ul_pipe); + + ipc_imem_channel_free(channel); + } +} + +void ipc_imem_pipe_cleanup(struct iosm_imem *ipc_imem, struct ipc_pipe *pipe) +{ + struct sk_buff *skb; + + /* Force pipe to closed state also when not explicitly closed through + * ipc_imem_pipe_close() + */ + pipe->is_open = false; + + /* Empty the uplink skb accumulator. */ + while ((skb = skb_dequeue(&pipe->channel->ul_list))) + ipc_pcie_kfree_skb(ipc_imem->pcie, skb); + + ipc_protocol_pipe_cleanup(ipc_imem->ipc_protocol, pipe); +} + +/* Send IPC protocol uninit to the modem when Link is active. */ +static void ipc_imem_device_ipc_uninit(struct iosm_imem *ipc_imem) +{ + int timeout = IPC_MODEM_UNINIT_TIMEOUT_MS; + enum ipc_mem_device_ipc_state ipc_state; + + /* When PCIe link is up set IPC_UNINIT + * of the modem otherwise ignore it when PCIe link down happens. + */ + if (ipc_pcie_check_data_link_active(ipc_imem->pcie)) { + /* set modem to UNINIT + * (in case we want to reload the AP driver without resetting + * the modem) + */ + ipc_doorbell_fire(ipc_imem->pcie, IPC_DOORBELL_IRQ_IPC, + IPC_MEM_DEVICE_IPC_UNINIT); + ipc_state = ipc_mmio_get_ipc_state(ipc_imem->mmio); + + /* Wait for maximum 30ms to allow the Modem to uninitialize the + * protocol. + */ + while ((ipc_state <= IPC_MEM_DEVICE_IPC_DONT_CARE) && + (ipc_state != IPC_MEM_DEVICE_IPC_UNINIT) && + (timeout > 0)) { + usleep_range(1000, 1250); + timeout--; + ipc_state = ipc_mmio_get_ipc_state(ipc_imem->mmio); + } + } +} + +void ipc_imem_cleanup(struct iosm_imem *ipc_imem) +{ + ipc_imem->phase = IPC_P_OFF_REQ; + + /* forward MDM_NOT_READY to listeners */ + ipc_uevent_send(ipc_imem->dev, UEVENT_MDM_NOT_READY); + + hrtimer_cancel(&ipc_imem->td_alloc_timer); + hrtimer_cancel(&ipc_imem->tdupdate_timer); + hrtimer_cancel(&ipc_imem->fast_update_timer); + hrtimer_cancel(&ipc_imem->startup_timer); + + /* cancel the workqueue */ + cancel_work_sync(&ipc_imem->run_state_worker); + + if (test_and_clear_bit(FULLY_FUNCTIONAL, &ipc_imem->flag)) { + ipc_mux_deinit(ipc_imem->mux); + ipc_wwan_deinit(ipc_imem->wwan); + ipc_port_deinit(ipc_imem->ipc_port); + } + + ipc_imem_device_ipc_uninit(ipc_imem); + ipc_imem_channel_reset(ipc_imem); + + ipc_protocol_deinit(ipc_imem->ipc_protocol); + ipc_task_deinit(ipc_imem->ipc_task); + + kfree(ipc_imem->ipc_task); + kfree(ipc_imem->mmio); + + ipc_imem->phase = IPC_P_OFF; +} + +/* After CP has unblocked the PCIe link, save the start address of the doorbell + * scratchpad and prepare the shared memory region. If the flashing to RAM + * procedure shall be executed, copy the chip information from the doorbell + * scratchtpad to the application buffer and wake up the flash app. + */ +static int ipc_imem_config(struct iosm_imem *ipc_imem) +{ + enum ipc_phase phase; + + /* Initialize the semaphore for the blocking read UL/DL transfer. */ + init_completion(&ipc_imem->ul_pend_sem); + + init_completion(&ipc_imem->dl_pend_sem); + + /* clear internal flags */ + ipc_imem->ipc_status = IPC_MEM_DEVICE_IPC_UNINIT; + ipc_imem->enter_runtime = 0; + + phase = ipc_imem_phase_update(ipc_imem); + + /* Either CP shall be in the power off or power on phase. */ + switch (phase) { + case IPC_P_ROM: + ipc_imem->hrtimer_period = ktime_set(0, 1000 * 1000 * 1000ULL); + /* poll execution stage (for delayed start, e.g. NAND) */ + if (!hrtimer_active(&ipc_imem->startup_timer)) + hrtimer_start(&ipc_imem->startup_timer, + ipc_imem->hrtimer_period, + HRTIMER_MODE_REL); + return 0; + + case IPC_P_PSI: + case IPC_P_EBL: + case IPC_P_RUN: + /* The initial IPC state is IPC_MEM_DEVICE_IPC_UNINIT. */ + ipc_imem->ipc_requested_state = IPC_MEM_DEVICE_IPC_UNINIT; + + /* Verify the exepected initial state. */ + if (ipc_imem->ipc_requested_state == + ipc_mmio_get_ipc_state(ipc_imem->mmio)) { + ipc_imem_ipc_init_check(ipc_imem); + + return 0; + } + dev_err(ipc_imem->dev, + "ipc_status(%d) != IPC_MEM_DEVICE_IPC_UNINIT", + ipc_mmio_get_ipc_state(ipc_imem->mmio)); + break; + case IPC_P_CRASH: + case IPC_P_CD_READY: + dev_dbg(ipc_imem->dev, + "Modem is in phase %d, reset Modem to collect CD", + phase); + return 0; + default: + dev_err(ipc_imem->dev, "unexpected operation phase %d", phase); + break; + } + + complete(&ipc_imem->dl_pend_sem); + complete(&ipc_imem->ul_pend_sem); + ipc_imem->phase = IPC_P_OFF; + return -EIO; +} + +/* Pass the dev ptr to the shared memory driver and request the entry points */ +struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id, + void __iomem *mmio, struct device *dev) +{ + struct iosm_imem *ipc_imem = kzalloc(sizeof(*pcie->imem), GFP_KERNEL); + + if (!ipc_imem) + return NULL; + + /* Save the device address. */ + ipc_imem->pcie = pcie; + ipc_imem->dev = dev; + + ipc_imem->pci_device_id = device_id; + + ipc_imem->ev_cdev_write_pending = false; + ipc_imem->cp_version = 0; + ipc_imem->device_sleep = IPC_HOST_SLEEP_ENTER_SLEEP; + + /* Reset the flash channel id. */ + ipc_imem->flash_channel_id = -1; + + /* Reset the max number of configured channels */ + ipc_imem->nr_of_channels = 0; + + /* allocate IPC MMIO */ + ipc_imem->mmio = ipc_mmio_init(mmio, ipc_imem->dev); + if (!ipc_imem->mmio) { + dev_err(ipc_imem->dev, "failed to initialize mmio region"); + goto mmio_init_fail; + } + + ipc_imem->ipc_task = kzalloc(sizeof(*ipc_imem->ipc_task), + GFP_KERNEL); + + /* Create tasklet for event handling*/ + if (!ipc_imem->ipc_task) + goto ipc_task_fail; + + if (ipc_task_init(ipc_imem->ipc_task)) + goto ipc_task_init_fail; + + ipc_imem->ipc_task->dev = ipc_imem->dev; + + INIT_WORK(&ipc_imem->run_state_worker, ipc_imem_run_state_worker); + + ipc_imem->ipc_protocol = ipc_protocol_init(ipc_imem); + + if (!ipc_imem->ipc_protocol) + goto protocol_init_fail; + + /* The phase is set to power off. */ + ipc_imem->phase = IPC_P_OFF; + + hrtimer_init(&ipc_imem->startup_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + ipc_imem->startup_timer.function = ipc_imem_startup_timer_cb; + + hrtimer_init(&ipc_imem->tdupdate_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + ipc_imem->tdupdate_timer.function = ipc_imem_td_update_timer_cb; + + hrtimer_init(&ipc_imem->fast_update_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + ipc_imem->fast_update_timer.function = ipc_imem_fast_update_timer_cb; + + hrtimer_init(&ipc_imem->td_alloc_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + ipc_imem->td_alloc_timer.function = ipc_imem_td_alloc_timer_cb; + + if (ipc_imem_config(ipc_imem)) { + dev_err(ipc_imem->dev, "failed to initialize the imem"); + goto imem_config_fail; + } + + return ipc_imem; + +imem_config_fail: + hrtimer_cancel(&ipc_imem->td_alloc_timer); + hrtimer_cancel(&ipc_imem->fast_update_timer); + hrtimer_cancel(&ipc_imem->tdupdate_timer); + hrtimer_cancel(&ipc_imem->startup_timer); +protocol_init_fail: + cancel_work_sync(&ipc_imem->run_state_worker); + ipc_task_deinit(ipc_imem->ipc_task); +ipc_task_init_fail: + kfree(ipc_imem->ipc_task); +ipc_task_fail: + kfree(ipc_imem->mmio); +mmio_init_fail: + kfree(ipc_imem); + return NULL; +} + +void ipc_imem_irq_process(struct iosm_imem *ipc_imem, int irq) +{ + /* Debounce IPC_EV_IRQ. */ + if (ipc_imem && !ipc_imem->ev_irq_pending[irq]) { + ipc_imem->ev_irq_pending[irq] = true; + ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_irq_cb, irq, + NULL, 0, false); + } +} + +void ipc_imem_td_update_timer_suspend(struct iosm_imem *ipc_imem, bool suspend) +{ + ipc_imem->td_update_timer_suspended = suspend; +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.h b/drivers/net/wwan/iosm/iosm_ipc_imem.h new file mode 100644 index 000000000000..0d2f10e4cbc8 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.h @@ -0,0 +1,579 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_IMEM_H +#define IOSM_IPC_IMEM_H + +#include +#include + +#include "iosm_ipc_mmio.h" +#include "iosm_ipc_pcie.h" +#include "iosm_ipc_uevent.h" +#include "iosm_ipc_wwan.h" +#include "iosm_ipc_task_queue.h" + +struct ipc_chnl_cfg; + +/* IRQ moderation in usec */ +#define IRQ_MOD_OFF 0 +#define IRQ_MOD_NET 1000 +#define IRQ_MOD_TRC 4000 + +/* Either the PSI image is accepted by CP or the suspended flash tool is waken, + * informed that the CP ROM driver is not ready to process the PSI image. + * unit : milliseconds + */ +#define IPC_PSI_TRANSFER_TIMEOUT 3000 + +/* Timeout in 20 msec to wait for the modem to boot up to + * IPC_MEM_DEVICE_IPC_INIT state. + * unit : milliseconds (500 * ipc_util_msleep(20)) + */ +#define IPC_MODEM_BOOT_TIMEOUT 500 + +/* Wait timeout for ipc status reflects IPC_MEM_DEVICE_IPC_UNINIT + * unit : milliseconds + */ +#define IPC_MODEM_UNINIT_TIMEOUT_MS 30 + +/* Pending time for processing data. + * unit : milliseconds + */ +#define IPC_PEND_DATA_TIMEOUT 500 + +/* The timeout in milliseconds for application to wait for remote time. */ +#define IPC_REMOTE_TS_TIMEOUT_MS 10 + +/* Timeout for TD allocation retry. + * unit : milliseconds + */ +#define IPC_TD_ALLOC_TIMER_PERIOD_MS 100 + +/* Host sleep target is host */ +#define IPC_HOST_SLEEP_HOST 0 + +/* Host sleep target is device */ +#define IPC_HOST_SLEEP_DEVICE 1 + +/* Sleep message, target host: AP enters sleep / target device: CP is + * allowed to enter sleep and shall use the host sleep protocol + */ +#define IPC_HOST_SLEEP_ENTER_SLEEP 0 + +/* Sleep_message, target host: AP exits sleep / target device: CP is + * NOT allowed to enter sleep + */ +#define IPC_HOST_SLEEP_EXIT_SLEEP 1 + +#define IMEM_IRQ_DONT_CARE (-1) + +#define IPC_MEM_MAX_CHANNELS 7 + +#define IPC_MEM_MUX_IP_SESSION_ENTRIES 8 + +#define IPC_MEM_MUX_IP_CH_IF_ID 0 + +#define TD_UPDATE_DEFAULT_TIMEOUT_USEC 1900 + +#define FORCE_UPDATE_DEFAULT_TIMEOUT_USEC 500 + +/* Sleep_message, target host: not applicable / target device: CP is + * allowed to enter sleep and shall NOT use the device sleep protocol + */ +#define IPC_HOST_SLEEP_ENTER_SLEEP_NO_PROTOCOL 2 + +/* in_band_crash_signal IPC_MEM_INBAND_CRASH_SIG + * Modem crash notification configuration. If this value is non-zero then + * FEATURE_SET message will be sent to the Modem as a result the Modem will + * signal Crash via Execution Stage register. If this value is zero then Modem + * will use out-of-band method to notify about it's Crash. + */ +#define IPC_MEM_INBAND_CRASH_SIG 1 + +/* Extra headroom to be allocated for DL SKBs to allow addition of Ethernet + * header + */ +#define IPC_MEM_DL_ETH_OFFSET 16 + +#define IPC_CB(skb) ((struct ipc_skb_cb *)((skb)->cb)) + +#define FULLY_FUNCTIONAL 0 + +/* List of the supported UL/DL pipes. */ +enum ipc_mem_pipes { + IPC_MEM_PIPE_0 = 0, + IPC_MEM_PIPE_1, + IPC_MEM_PIPE_2, + IPC_MEM_PIPE_3, + IPC_MEM_PIPE_4, + IPC_MEM_PIPE_5, + IPC_MEM_PIPE_6, + IPC_MEM_PIPE_7, + IPC_MEM_PIPE_8, + IPC_MEM_PIPE_9, + IPC_MEM_PIPE_10, + IPC_MEM_PIPE_11, + IPC_MEM_PIPE_12, + IPC_MEM_PIPE_13, + IPC_MEM_PIPE_14, + IPC_MEM_PIPE_15, + IPC_MEM_PIPE_16, + IPC_MEM_PIPE_17, + IPC_MEM_PIPE_18, + IPC_MEM_PIPE_19, + IPC_MEM_PIPE_20, + IPC_MEM_PIPE_21, + IPC_MEM_PIPE_22, + IPC_MEM_PIPE_23, + IPC_MEM_MAX_PIPES +}; + +/* Enum defining channel states. */ +enum ipc_channel_state { + IMEM_CHANNEL_FREE, + IMEM_CHANNEL_RESERVED, + IMEM_CHANNEL_ACTIVE, + IMEM_CHANNEL_CLOSING, +}; + +/* Time Unit */ +enum ipc_time_unit { + IPC_SEC = 0, + IPC_MILLI_SEC = 1, + IPC_MICRO_SEC = 2, + IPC_NANO_SEC = 3, + IPC_PICO_SEC = 4, + IPC_FEMTO_SEC = 5, + IPC_ATTO_SEC = 6, +}; + +/** + * enum ipc_ctype - Enum defining supported channel type needed for control + * /IP traffic. + * @IPC_CTYPE_WWAN: Used for IP traffic + * @IPC_CTYPE_CTRL: Used for Control Communication + */ +enum ipc_ctype { + IPC_CTYPE_WWAN, + IPC_CTYPE_CTRL, +}; + +/* Pipe direction. */ +enum ipc_mem_pipe_dir { + IPC_MEM_DIR_UL, + IPC_MEM_DIR_DL, +}; + +/* HP update identifier. To be used as data for ipc_cp_irq_hpda_update() */ +enum ipc_hp_identifier { + IPC_HP_MR = 0, + IPC_HP_PM_TRIGGER, + IPC_HP_WAKEUP_SPEC_TMR, + IPC_HP_TD_UPD_TMR_START, + IPC_HP_TD_UPD_TMR, + IPC_HP_FAST_TD_UPD_TMR, + IPC_HP_UL_WRITE_TD, + IPC_HP_DL_PROCESS, + IPC_HP_NET_CHANNEL_INIT, + IPC_HP_CDEV_OPEN, +}; + +/** + * struct ipc_pipe - Structure for Pipe. + * @tdr_start: Ipc private protocol Transfer Descriptor Ring + * @channel: Id of the sio device, set by imem_sio_open, + * needed to pass DL char to the user terminal + * @skbr_start: Circular buffer for skbuf and the buffer + * reference in a tdr_start entry. + * @phy_tdr_start: Transfer descriptor start address + * @old_head: last head pointer reported to CP. + * @old_tail: AP read position before CP moves the read + * position to write/head. If CP has consumed the + * buffers, AP has to freed the skbuf starting at + * tdr_start[old_tail]. + * @nr_of_entries: Number of elements of skb_start and tdr_start. + * @max_nr_of_queued_entries: Maximum number of queued entries in TDR + * @accumulation_backoff: Accumulation in usec for accumulation + * backoff (0 = no acc backoff) + * @irq_moderation: timer in usec for irq_moderation + * (0=no irq moderation) + * @pipe_nr: Pipe identification number + * @irq: Interrupt vector + * @dir: Direction of data stream in pipe + * @td_tag: Unique tag of the buffer queued + * @buf_size: Buffer size (in bytes) for preallocated + * buffers (for DL pipes) + * @nr_of_queued_entries: Aueued number of entries + * @is_open: Check for open pipe status + */ +struct ipc_pipe { + struct ipc_protocol_td *tdr_start; + struct ipc_mem_channel *channel; + struct sk_buff **skbr_start; + dma_addr_t phy_tdr_start; + u32 old_head; + u32 old_tail; + u32 nr_of_entries; + u32 max_nr_of_queued_entries; + u32 accumulation_backoff; + u32 irq_moderation; + u32 pipe_nr; + u32 irq; + enum ipc_mem_pipe_dir dir; + u32 td_tag; + u32 buf_size; + u16 nr_of_queued_entries; + u8 is_open:1; +}; + +/** + * struct ipc_mem_channel - Structure for Channel. + * @channel_id: Instance of the channel list and is return to the user + * at the end of the open operation. + * @ctype: Control or netif channel. + * @index: unique index per ctype + * @ul_pipe: pipe objects + * @dl_pipe: pipe objects + * @if_id: Interface ID + * @net_err_count: Number of downlink errors returned by ipc_wwan_receive + * interface at the entry point of the IP stack. + * @state: Free, reserved or busy (in use). + * @ul_sem: Needed for the blocking write or uplink transfer. + * @ul_list: Uplink accumulator which is filled by the uplink + * char app or IP stack. The socket buffer pointer are + * added to the descriptor list in the kthread context. + */ +struct ipc_mem_channel { + int channel_id; + enum ipc_ctype ctype; + int index; + struct ipc_pipe ul_pipe; + struct ipc_pipe dl_pipe; + int if_id; + u32 net_err_count; + enum ipc_channel_state state; + struct completion ul_sem; + struct sk_buff_head ul_list; +}; + +/** + * enum ipc_phase - Different AP and CP phases. + * The enums defined after "IPC_P_ROM" and before + * "IPC_P_RUN" indicates the operating state where CP can + * respond to any requests. So while introducing new phase + * this shall be taken into consideration. + * @IPC_P_OFF: On host PC, the PCIe device link settings are known + * about the combined power on. PC is running, the driver + * is loaded and CP is in power off mode. The PCIe bus + * driver call the device power mode D3hot. In this phase + * the driver the polls the device, until the device is in + * the power on state and signals the power mode D0. + * @IPC_P_OFF_REQ: The intermediate phase between cleanup activity starts + * and ends. + * @IPC_P_CRASH: The phase indicating CP crash + * @IPC_P_CD_READY: The phase indicating CP core dump is ready + * @IPC_P_ROM: After power on, CP starts in ROM mode and the IPC ROM + * driver is waiting 150 ms for the AP active notification + * saved in the PCI link status register. + * @IPC_P_PSI: Primary signed image download phase + * @IPC_P_EBL: Extended bootloader pahse + * @IPC_P_RUN: The phase after flashing to RAM is the RUNTIME phase. + */ +enum ipc_phase { + IPC_P_OFF, + IPC_P_OFF_REQ, + IPC_P_CRASH, + IPC_P_CD_READY, + IPC_P_ROM, + IPC_P_PSI, + IPC_P_EBL, + IPC_P_RUN, +}; + +/** + * struct iosm_imem - Current state of the IPC shared memory. + * @mmio: mmio instance to access CP MMIO area / + * doorbell scratchpad. + * @ipc_protocol: IPC Protocol instance + * @ipc_task: Task for entry into ipc task queue + * @wwan: WWAN device pointer + * @mux: IP Data multiplexing state. + * @sio: IPC SIO data structure pointer + * @ipc_port: IPC PORT data structure pointer + * @pcie: IPC PCIe + * @dev: Pointer to device structure + * @flash_channel_id: Reserved channel id for flashing to RAM. + * @ipc_requested_state: Expected IPC state on CP. + * @channels: Channel list with UL/DL pipe pairs. + * @ipc_status: local ipc_status + * @nr_of_channels: number of configured channels + * @startup_timer: startup timer for NAND support. + * @hrtimer_period: Hr timer period + * @tdupdate_timer: Delay the TD update doorbell. + * @fast_update_timer: forced head pointer update delay timer. + * @td_alloc_timer: Timer for DL pipe TD allocation retry + * @rom_exit_code: Mapped boot rom exit code. + * @enter_runtime: 1 means the transition to runtime phase was + * executed. + * @ul_pend_sem: Semaphore to wait/complete of UL TDs + * before closing pipe. + * @app_notify_ul_pend: Signal app if UL TD is pending + * @dl_pend_sem: Semaphore to wait/complete of DL TDs + * before closing pipe. + * @app_notify_dl_pend: Signal app if DL TD is pending + * @phase: Operating phase like runtime. + * @pci_device_id: Device ID + * @cp_version: CP version + * @device_sleep: Device sleep state + * @run_state_worker: Pointer to worker component for device + * setup operations to be called when modem + * reaches RUN state + * @ev_irq_pending: 0 means inform the IPC tasklet to + * process the irq actions. + * @flag: Flag to monitor the state of driver + * @td_update_timer_suspended: if true then td update timer suspend + * @ev_cdev_write_pending: 0 means inform the IPC tasklet to pass + * the accumulated uplink buffers to CP. + * @ev_mux_net_transmit_pending:0 means inform the IPC tasklet to pass + * @reset_det_n: Reset detect flag + * @pcie_wake_n: Pcie wake flag + */ +struct iosm_imem { + struct iosm_mmio *mmio; + struct iosm_protocol *ipc_protocol; + struct ipc_task *ipc_task; + struct iosm_wwan *wwan; + struct iosm_mux *mux; + struct iosm_cdev *ipc_port[IPC_MEM_MAX_CHANNELS]; + struct iosm_pcie *pcie; + struct device *dev; + int flash_channel_id; + enum ipc_mem_device_ipc_state ipc_requested_state; + struct ipc_mem_channel channels[IPC_MEM_MAX_CHANNELS]; + u32 ipc_status; + u32 nr_of_channels; + struct hrtimer startup_timer; + ktime_t hrtimer_period; + struct hrtimer tdupdate_timer; + struct hrtimer fast_update_timer; + struct hrtimer td_alloc_timer; + enum rom_exit_code rom_exit_code; + u32 enter_runtime; + struct completion ul_pend_sem; + u32 app_notify_ul_pend; + struct completion dl_pend_sem; + u32 app_notify_dl_pend; + enum ipc_phase phase; + u16 pci_device_id; + int cp_version; + int device_sleep; + struct work_struct run_state_worker; + u8 ev_irq_pending[IPC_IRQ_VECTORS]; + unsigned long flag; + u8 td_update_timer_suspended:1, + ev_cdev_write_pending:1, + ev_mux_net_transmit_pending:1, + reset_det_n:1, + pcie_wake_n:1; +}; + +/** + * ipc_imem_init - Initialize the shared memory region + * @pcie: Pointer to core driver data-struct + * @device_id: PCI device ID + * @mmio: Pointer to the mmio area + * @dev: Pointer to device structure + * + * Returns: Initialized imem pointer on success else NULL + */ +struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id, + void __iomem *mmio, struct device *dev); + +/** + * ipc_imem_pm_s2idle_sleep - Set PM variables to sleep/active for + * s2idle sleep/active + * @ipc_imem: Pointer to imem data-struct + * @sleep: Set PM Variable to sleep/active + */ +void ipc_imem_pm_s2idle_sleep(struct iosm_imem *ipc_imem, bool sleep); + +/** + * ipc_imem_pm_suspend - The HAL shall ask the shared memory layer + * whether D3 is allowed. + * @ipc_imem: Pointer to imem data-struct + */ +void ipc_imem_pm_suspend(struct iosm_imem *ipc_imem); + +/** + * ipc_imem_pm_resume - The HAL shall inform the shared memory layer + * that the device is active. + * @ipc_imem: Pointer to imem data-struct + */ +void ipc_imem_pm_resume(struct iosm_imem *ipc_imem); + +/** + * ipc_imem_cleanup - Inform CP and free the shared memory resources. + * @ipc_imem: Pointer to imem data-struct + */ +void ipc_imem_cleanup(struct iosm_imem *ipc_imem); + +/** + * ipc_imem_irq_process - Shift the IRQ actions to the IPC thread. + * @ipc_imem: Pointer to imem data-struct + * @irq: Irq number + */ +void ipc_imem_irq_process(struct iosm_imem *ipc_imem, int irq); + +/** + * imem_get_device_sleep_state - Get the device sleep state value. + * @ipc_imem: Pointer to imem instance + * + * Returns: device sleep state + */ +int imem_get_device_sleep_state(struct iosm_imem *ipc_imem); + +/** + * ipc_imem_td_update_timer_suspend - Updates the TD Update Timer suspend flag. + * @ipc_imem: Pointer to imem data-struct + * @suspend: Flag to update. If TRUE then HP update doorbell is triggered to + * device without any wait. If FALSE then HP update doorbell is + * delayed until timeout. + */ +void ipc_imem_td_update_timer_suspend(struct iosm_imem *ipc_imem, bool suspend); + +/** + * ipc_imem_channel_close - Release the channel resources. + * @ipc_imem: Pointer to imem data-struct + * @channel_id: Channel ID to be cleaned up. + */ +void ipc_imem_channel_close(struct iosm_imem *ipc_imem, int channel_id); + +/** + * ipc_imem_channel_alloc - Reserves a channel + * @ipc_imem: Pointer to imem data-struct + * @index: ID to lookup from the preallocated list. + * @ctype: Channel type. + * + * Returns: Index on success and failure value on error + */ +int ipc_imem_channel_alloc(struct iosm_imem *ipc_imem, int index, + enum ipc_ctype ctype); + +/** + * ipc_imem_channel_open - Establish the pipes. + * @ipc_imem: Pointer to imem data-struct + * @channel_id: Channel ID returned during alloc. + * @db_id: Doorbell ID for trigger identifier. + * + * Returns: Pointer of ipc_mem_channel on success and NULL on failure. + */ +struct ipc_mem_channel *ipc_imem_channel_open(struct iosm_imem *ipc_imem, + int channel_id, u32 db_id); + +/** + * ipc_imem_td_update_timer_start - Starts the TD Update Timer if not running. + * @ipc_imem: Pointer to imem data-struct + */ +void ipc_imem_td_update_timer_start(struct iosm_imem *ipc_imem); + +/** + * ipc_imem_ul_write_td - Pass the channel UL list to protocol layer for TD + * preparation and sending them to the device. + * @ipc_imem: Pointer to imem data-struct + * + * Returns: TRUE of HP Doorbell trigger is pending. FALSE otherwise. + */ +bool ipc_imem_ul_write_td(struct iosm_imem *ipc_imem); + +/** + * ipc_imem_ul_send - Dequeue SKB from channel list and start with + * the uplink transfer.If HP Doorbell is pending to be + * triggered then starts the TD Update Timer. + * @ipc_imem: Pointer to imem data-struct + */ +void ipc_imem_ul_send(struct iosm_imem *ipc_imem); + +/** + * ipc_imem_channel_update - Set or modify pipe config of an existing channel + * @ipc_imem: Pointer to imem data-struct + * @id: Channel config index + * @chnl_cfg: Channel config struct + * @irq_moderation: Timer in usec for irq_moderation + */ +void ipc_imem_channel_update(struct iosm_imem *ipc_imem, int id, + struct ipc_chnl_cfg chnl_cfg, u32 irq_moderation); + +/** + * ipc_imem_channel_free -Free an IPC channel. + * @channel: Channel to be freed + */ +void ipc_imem_channel_free(struct ipc_mem_channel *channel); + +/** + * ipc_imem_hrtimer_stop - Stop the hrtimer + * @hr_timer: Pointer to hrtimer instance + */ +void ipc_imem_hrtimer_stop(struct hrtimer *hr_timer); + +/** + * ipc_imem_pipe_cleanup - Reset volatile pipe content for all channels + * @ipc_imem: Pointer to imem data-struct + * @pipe: Pipe to cleaned up + */ +void ipc_imem_pipe_cleanup(struct iosm_imem *ipc_imem, struct ipc_pipe *pipe); + +/** + * ipc_imem_pipe_close - Send msg to device to close pipe + * @ipc_imem: Pointer to imem data-struct + * @pipe: Pipe to be closed + */ +void ipc_imem_pipe_close(struct iosm_imem *ipc_imem, struct ipc_pipe *pipe); + +/** + * ipc_imem_phase_update - Get the CP execution state + * and map it to the AP phase. + * @ipc_imem: Pointer to imem data-struct + * + * Returns: Current ap updated phase + */ +enum ipc_phase ipc_imem_phase_update(struct iosm_imem *ipc_imem); + +/** + * ipc_imem_phase_get_string - Return the current operation + * phase as string. + * @phase: AP phase + * + * Returns: AP phase string + */ +const char *ipc_imem_phase_get_string(enum ipc_phase phase); + +/** + * ipc_imem_msg_send_feature_set - Send feature set message to modem + * @ipc_imem: Pointer to imem data-struct + * @reset_enable: 0 = out-of-band, 1 = in-band-crash notification + * @atomic_ctx: if disabled call in tasklet context + * + */ +void ipc_imem_msg_send_feature_set(struct iosm_imem *ipc_imem, + unsigned int reset_enable, bool atomic_ctx); + +/** + * ipc_imem_ipc_init_check - Send the init event to CP, wait a certain time and + * set CP to runtime with the context information + * @ipc_imem: Pointer to imem data-struct + */ +void ipc_imem_ipc_init_check(struct iosm_imem *ipc_imem); + +/** + * ipc_imem_channel_init - Initialize the channel list with UL/DL pipe pairs. + * @ipc_imem: Pointer to imem data-struct + * @ctype: Channel type + * @chnl_cfg: Channel configuration struct + * @irq_moderation: Timer in usec for irq_moderation + */ +void ipc_imem_channel_init(struct iosm_imem *ipc_imem, enum ipc_ctype ctype, + struct ipc_chnl_cfg chnl_cfg, u32 irq_moderation); +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c new file mode 100644 index 000000000000..46f76e8aae92 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -0,0 +1,346 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include + +#include "iosm_ipc_chnl_cfg.h" +#include "iosm_ipc_imem.h" +#include "iosm_ipc_imem_ops.h" +#include "iosm_ipc_port.h" +#include "iosm_ipc_task_queue.h" + +/* Open a packet data online channel between the network layer and CP. */ +int ipc_imem_sys_wwan_open(struct iosm_imem *ipc_imem, int if_id) +{ + dev_dbg(ipc_imem->dev, "%s if id: %d", + ipc_imem_phase_get_string(ipc_imem->phase), if_id); + + /* The network interface is only supported in the runtime phase. */ + if (ipc_imem_phase_update(ipc_imem) != IPC_P_RUN) { + dev_err(ipc_imem->dev, "net:%d : refused phase %s", if_id, + ipc_imem_phase_get_string(ipc_imem->phase)); + return -EIO; + } + + /* check for the interafce id + * if if_id 1 to 8 then create IP MUX channel sessions. + * To start MUX session from 0 as network interface id would start + * from 1 so map it to if_id = if_id - 1 + */ + if (if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END) + return ipc_mux_open_session(ipc_imem->mux, if_id - 1); + + return -EINVAL; +} + +/* Release a net link to CP. */ +void ipc_imem_sys_wwan_close(struct iosm_imem *ipc_imem, int if_id, + int channel_id) +{ + if (ipc_imem->mux && if_id >= IP_MUX_SESSION_START && + if_id <= IP_MUX_SESSION_END) + ipc_mux_close_session(ipc_imem->mux, if_id - 1); +} + +/* Tasklet call to do uplink transfer. */ +static int ipc_imem_tq_cdev_write(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size) +{ + ipc_imem->ev_cdev_write_pending = false; + ipc_imem_ul_send(ipc_imem); + + return 0; +} + +/* Through tasklet to do sio write. */ +static int ipc_imem_call_cdev_write(struct iosm_imem *ipc_imem) +{ + if (ipc_imem->ev_cdev_write_pending) + return -1; + + ipc_imem->ev_cdev_write_pending = true; + + return ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_cdev_write, 0, + NULL, 0, false); +} + +/* Function for transfer UL data */ +int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, + int if_id, int channel_id, struct sk_buff *skb) +{ + int ret = -EINVAL; + + if (!ipc_imem || channel_id < 0) + goto out; + + /* Is CP Running? */ + if (ipc_imem->phase != IPC_P_RUN) { + dev_dbg(ipc_imem->dev, "phase %s transmit", + ipc_imem_phase_get_string(ipc_imem->phase)); + ret = -EIO; + goto out; + } + + if (if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END) + /* Route the UL packet through IP MUX Layer */ + ret = ipc_mux_ul_trigger_encode(ipc_imem->mux, + if_id - 1, skb); + else + dev_err(ipc_imem->dev, + "invalid if_id %d: ", if_id); +out: + return ret; +} + +/* Initialize wwan channel */ +void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, + enum ipc_mux_protocol mux_type) +{ + struct ipc_chnl_cfg chnl_cfg = { 0 }; + + ipc_imem->cp_version = ipc_mmio_get_cp_version(ipc_imem->mmio); + + /* If modem version is invalid (0xffffffff), do not initialize WWAN. */ + if (ipc_imem->cp_version == -1) { + dev_err(ipc_imem->dev, "invalid CP version"); + return; + } + + ipc_chnl_cfg_get(&chnl_cfg, ipc_imem->nr_of_channels); + ipc_imem_channel_init(ipc_imem, IPC_CTYPE_WWAN, chnl_cfg, + IRQ_MOD_OFF); + + /* WWAN registration. */ + ipc_imem->wwan = ipc_wwan_init(ipc_imem, ipc_imem->dev); + if (!ipc_imem->wwan) + dev_err(ipc_imem->dev, + "failed to register the ipc_wwan interfaces"); +} + +/* Map SKB to DMA for transfer */ +static int ipc_imem_map_skb_to_dma(struct iosm_imem *ipc_imem, + struct sk_buff *skb) +{ + struct iosm_pcie *ipc_pcie = ipc_imem->pcie; + char *buf = skb->data; + int len = skb->len; + dma_addr_t mapping; + int ret; + + ret = ipc_pcie_addr_map(ipc_pcie, buf, len, &mapping, DMA_TO_DEVICE); + + if (ret) + goto err; + + BUILD_BUG_ON(sizeof(*IPC_CB(skb)) > sizeof(skb->cb)); + + IPC_CB(skb)->mapping = mapping; + IPC_CB(skb)->direction = DMA_TO_DEVICE; + IPC_CB(skb)->len = len; + IPC_CB(skb)->op_type = (u8)UL_DEFAULT; + +err: + return ret; +} + +/* return true if channel is ready for use */ +static bool ipc_imem_is_channel_active(struct iosm_imem *ipc_imem, + struct ipc_mem_channel *channel) +{ + enum ipc_phase phase; + + /* Update the current operation phase. */ + phase = ipc_imem->phase; + + /* Select the operation depending on the execution stage. */ + switch (phase) { + case IPC_P_RUN: + case IPC_P_PSI: + case IPC_P_EBL: + break; + + case IPC_P_ROM: + /* Prepare the PSI image for the CP ROM driver and + * suspend the flash app. + */ + if (channel->state != IMEM_CHANNEL_RESERVED) { + dev_err(ipc_imem->dev, + "ch[%d]:invalid channel state %d,expected %d", + channel->channel_id, channel->state, + IMEM_CHANNEL_RESERVED); + goto channel_unavailable; + } + goto channel_available; + + default: + /* Ignore uplink actions in all other phases. */ + dev_err(ipc_imem->dev, "ch[%d]: confused phase %d", + channel->channel_id, phase); + goto channel_unavailable; + } + /* Check the full availability of the channel. */ + if (channel->state != IMEM_CHANNEL_ACTIVE) { + dev_err(ipc_imem->dev, "ch[%d]: confused channel state %d", + channel->channel_id, channel->state); + goto channel_unavailable; + } + +channel_available: + return true; + +channel_unavailable: + return false; +} + +/* Release a sio link to CP. */ +void ipc_imem_sys_cdev_close(struct iosm_cdev *ipc_cdev) +{ + struct iosm_imem *ipc_imem = ipc_cdev->ipc_imem; + struct ipc_mem_channel *channel = ipc_cdev->channel; + enum ipc_phase curr_phase; + int status = 0; + u32 tail = 0; + + curr_phase = ipc_imem->phase; + + /* If current phase is IPC_P_OFF or SIO ID is -ve then + * channel is already freed. Nothing to do. + */ + if (curr_phase == IPC_P_OFF) { + dev_err(ipc_imem->dev, + "nothing to do. Current Phase: %s", + ipc_imem_phase_get_string(curr_phase)); + return; + } + + if (channel->state == IMEM_CHANNEL_FREE) { + dev_err(ipc_imem->dev, "ch[%d]: invalid channel state %d", + channel->channel_id, channel->state); + return; + } + + /* If there are any pending TDs then wait for Timeout/Completion before + * closing pipe. + */ + if (channel->ul_pipe.old_tail != channel->ul_pipe.old_head) { + ipc_imem->app_notify_ul_pend = 1; + + /* Suspend the user app and wait a certain time for processing + * UL Data. + */ + status = wait_for_completion_interruptible_timeout + (&ipc_imem->ul_pend_sem, + msecs_to_jiffies(IPC_PEND_DATA_TIMEOUT)); + if (status == 0) { + dev_dbg(ipc_imem->dev, + "Pend data Timeout UL-Pipe:%d Head:%d Tail:%d", + channel->ul_pipe.pipe_nr, + channel->ul_pipe.old_head, + channel->ul_pipe.old_tail); + } + + ipc_imem->app_notify_ul_pend = 0; + } + + /* If there are any pending TDs then wait for Timeout/Completion before + * closing pipe. + */ + ipc_protocol_get_head_tail_index(ipc_imem->ipc_protocol, + &channel->dl_pipe, NULL, &tail); + + if (tail != channel->dl_pipe.old_tail) { + ipc_imem->app_notify_dl_pend = 1; + + /* Suspend the user app and wait a certain time for processing + * DL Data. + */ + status = wait_for_completion_interruptible_timeout + (&ipc_imem->dl_pend_sem, + msecs_to_jiffies(IPC_PEND_DATA_TIMEOUT)); + if (status == 0) { + dev_dbg(ipc_imem->dev, + "Pend data Timeout DL-Pipe:%d Head:%d Tail:%d", + channel->dl_pipe.pipe_nr, + channel->dl_pipe.old_head, + channel->dl_pipe.old_tail); + } + + ipc_imem->app_notify_dl_pend = 0; + } + + /* Due to wait for completion in messages, there is a small window + * between closing the pipe and updating the channel is closed. In this + * small window there could be HP update from Host Driver. Hence update + * the channel state as CLOSING to aviod unnecessary interrupt + * towards CP. + */ + channel->state = IMEM_CHANNEL_CLOSING; + + ipc_imem_pipe_close(ipc_imem, &channel->ul_pipe); + ipc_imem_pipe_close(ipc_imem, &channel->dl_pipe); + + ipc_imem_channel_free(channel); +} + +/* Open a PORT link to CP and return the channel */ +struct ipc_mem_channel *ipc_imem_sys_port_open(struct iosm_imem *ipc_imem, + int chl_id, int hp_id) +{ + struct ipc_mem_channel *channel; + int ch_id; + + /* The PORT interface is only supported in the runtime phase. */ + if (ipc_imem_phase_update(ipc_imem) != IPC_P_RUN) { + dev_err(ipc_imem->dev, "PORT open refused, phase %s", + ipc_imem_phase_get_string(ipc_imem->phase)); + return NULL; + } + + ch_id = ipc_imem_channel_alloc(ipc_imem, chl_id, IPC_CTYPE_CTRL); + + if (ch_id < 0) { + dev_err(ipc_imem->dev, "reservation of an PORT chnl id failed"); + return NULL; + } + + channel = ipc_imem_channel_open(ipc_imem, ch_id, hp_id); + + if (!channel) { + dev_err(ipc_imem->dev, "PORT channel id open failed"); + return NULL; + } + + return channel; +} + +/* transfer skb to modem */ +int ipc_imem_sys_cdev_write(struct iosm_cdev *ipc_cdev, struct sk_buff *skb) +{ + struct ipc_mem_channel *channel = ipc_cdev->channel; + struct iosm_imem *ipc_imem = ipc_cdev->ipc_imem; + int ret = -EIO; + + if (!ipc_imem_is_channel_active(ipc_imem, channel) || + ipc_imem->phase == IPC_P_OFF_REQ) + goto out; + + ret = ipc_imem_map_skb_to_dma(ipc_imem, skb); + + if (ret) + goto out; + + /* Add skb to the uplink skbuf accumulator. */ + skb_queue_tail(&channel->ul_list, skb); + + ret = ipc_imem_call_cdev_write(ipc_imem); + + if (ret) { + skb_dequeue_tail(&channel->ul_list); + dev_err(ipc_cdev->dev, "channel id[%d] write failed\n", + ipc_cdev->channel->channel_id); + } +out: + return ret; +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h new file mode 100644 index 000000000000..fd356dafbdd6 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_IMEM_OPS_H +#define IOSM_IPC_IMEM_OPS_H + +#include "iosm_ipc_mux_codec.h" + +/* Maximum wait time for blocking read */ +#define IPC_READ_TIMEOUT 500 + +/* The delay in ms for defering the unregister */ +#define SIO_UNREGISTER_DEFER_DELAY_MS 1 + +/* Default delay till CP PSI image is running and modem updates the + * execution stage. + * unit : milliseconds + */ +#define PSI_START_DEFAULT_TIMEOUT 3000 + +/* Default time out when closing SIO, till the modem is in + * running state. + * unit : milliseconds + */ +#define BOOT_CHECK_DEFAULT_TIMEOUT 400 + +/* IP MUX channel range */ +#define IP_MUX_SESSION_START 1 +#define IP_MUX_SESSION_END 8 + +/* Default IP MUX channel */ +#define IP_MUX_SESSION_DEFAULT 1 + +/** + * ipc_imem_sys_port_open - Open a port link to CP. + * @ipc_imem: Imem instance. + * @chl_id: Channel Indentifier. + * @hp_id: HP Indentifier. + * + * Return: channel instance on success, NULL for failure + */ +struct ipc_mem_channel *ipc_imem_sys_port_open(struct iosm_imem *ipc_imem, + int chl_id, int hp_id); + +/** + * ipc_imem_sys_cdev_close - Release a sio link to CP. + * @ipc_cdev: iosm sio instance. + */ +void ipc_imem_sys_cdev_close(struct iosm_cdev *ipc_cdev); + +/** + * ipc_imem_sys_cdev_write - Route the uplink buffer to CP. + * @ipc_cdev: iosm_cdev instance. + * @skb: Pointer to skb. + * + * Return: 0 on success and failure value on error + */ +int ipc_imem_sys_cdev_write(struct iosm_cdev *ipc_cdev, struct sk_buff *skb); + +/** + * ipc_imem_sys_wwan_open - Open packet data online channel between network + * layer and CP. + * @ipc_imem: Imem instance. + * @if_id: ip link tag of the net device. + * + * Return: Channel ID on success and failure value on error + */ +int ipc_imem_sys_wwan_open(struct iosm_imem *ipc_imem, int if_id); + +/** + * ipc_imem_sys_wwan_close - Close packet data online channel between network + * layer and CP. + * @ipc_imem: Imem instance. + * @if_id: IP link id net device. + * @channel_id: Channel ID to be closed. + */ +void ipc_imem_sys_wwan_close(struct iosm_imem *ipc_imem, int if_id, + int channel_id); + +/** + * ipc_imem_sys_wwan_transmit - Function for transfer UL data + * @ipc_imem: Imem instance. + * @if_id: link ID of the device. + * @channel_id: Channel ID used + * @skb: Pointer to sk buffer + * + * Return: 0 on success and failure value on error + */ +int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, int if_id, + int channel_id, struct sk_buff *skb); +/** + * ipc_imem_wwan_channel_init - Initializes WWAN channels and the channel for + * MUX. + * @ipc_imem: Pointer to iosm_imem struct. + * @mux_type: Type of mux protocol. + */ +void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, + enum ipc_mux_protocol mux_type); +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_irq.c b/drivers/net/wwan/iosm/iosm_ipc_irq.c new file mode 100644 index 000000000000..702f50a48151 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_irq.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include "iosm_ipc_pcie.h" +#include "iosm_ipc_protocol.h" + +static void ipc_write_dbell_reg(struct iosm_pcie *ipc_pcie, int irq_n, u32 data) +{ + void __iomem *write_reg; + + /* Select the first doorbell register, which is only currently needed + * by CP. + */ + write_reg = (void __iomem *)((u8 __iomem *)ipc_pcie->ipc_regs + + ipc_pcie->doorbell_write + + (irq_n * ipc_pcie->doorbell_reg_offset)); + + /* Fire the doorbell irq by writing data on the doorbell write pointer + * register. + */ + iowrite32(data, write_reg); +} + +void ipc_doorbell_fire(struct iosm_pcie *ipc_pcie, int irq_n, u32 data) +{ + ipc_write_dbell_reg(ipc_pcie, irq_n, data); +} + +/* Threaded Interrupt handler for MSI interrupts */ +static irqreturn_t ipc_msi_interrupt(int irq, void *dev_id) +{ + struct iosm_pcie *ipc_pcie = dev_id; + int instance = irq - ipc_pcie->pci->irq; + + /* Shift the MSI irq actions to the IPC tasklet. IRQ_NONE means the + * irq was not from the IPC device or could not be served. + */ + if (instance >= ipc_pcie->nvec) + return IRQ_NONE; + + if (!test_bit(0, &ipc_pcie->suspend)) + ipc_imem_irq_process(ipc_pcie->imem, instance); + + return IRQ_HANDLED; +} + +void ipc_release_irq(struct iosm_pcie *ipc_pcie) +{ + struct pci_dev *pdev = ipc_pcie->pci; + + if (pdev->msi_enabled) { + while (--ipc_pcie->nvec >= 0) + free_irq(pdev->irq + ipc_pcie->nvec, ipc_pcie); + } + pci_free_irq_vectors(pdev); +} + +int ipc_acquire_irq(struct iosm_pcie *ipc_pcie) +{ + struct pci_dev *pdev = ipc_pcie->pci; + int i, rc = -EINVAL; + + ipc_pcie->nvec = pci_alloc_irq_vectors(pdev, IPC_MSI_VECTORS, + IPC_MSI_VECTORS, PCI_IRQ_MSI); + + if (ipc_pcie->nvec < 0) { + rc = ipc_pcie->nvec; + goto error; + } + + if (!pdev->msi_enabled) + goto error; + + for (i = 0; i < ipc_pcie->nvec; ++i) { + rc = request_threaded_irq(pdev->irq + i, NULL, + ipc_msi_interrupt, IRQF_ONESHOT, + KBUILD_MODNAME, ipc_pcie); + if (rc) { + dev_err(ipc_pcie->dev, "unable to grab IRQ, rc=%d", rc); + ipc_pcie->nvec = i; + ipc_release_irq(ipc_pcie); + goto error; + } + } + +error: + return rc; +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_irq.h b/drivers/net/wwan/iosm/iosm_ipc_irq.h new file mode 100644 index 000000000000..a8ed596cb6a5 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_irq.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_IRQ_H +#define IOSM_IPC_IRQ_H + +struct iosm_pcie; + +/** + * ipc_doorbell_fire - fire doorbell to CP + * @ipc_pcie: Pointer to iosm_pcie + * @irq_n: Doorbell type + * @data: ipc state + */ +void ipc_doorbell_fire(struct iosm_pcie *ipc_pcie, int irq_n, u32 data); + +/** + * ipc_release_irq - Release the IRQ handler. + * @ipc_pcie: Pointer to iosm_pcie struct + */ +void ipc_release_irq(struct iosm_pcie *ipc_pcie); + +/** + * ipc_acquire_irq - acquire IRQ & register IRQ handler. + * @ipc_pcie: Pointer to iosm_pcie struct + * + * Return: 0 on success and failure value on error + */ +int ipc_acquire_irq(struct iosm_pcie *ipc_pcie); + +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_mmio.c b/drivers/net/wwan/iosm/iosm_ipc_mmio.c new file mode 100644 index 000000000000..06c94b1720b6 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_mmio.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include +#include +#include +#include +#include + +#include "iosm_ipc_mmio.h" + +/* Definition of MMIO offsets + * note that MMIO_CI offsets are relative to end of chip info structure + */ + +/* MMIO chip info size in bytes */ +#define MMIO_CHIP_INFO_SIZE 60 + +/* CP execution stage */ +#define MMIO_OFFSET_EXECUTION_STAGE 0x00 + +/* Boot ROM Chip Info struct */ +#define MMIO_OFFSET_CHIP_INFO 0x04 + +#define MMIO_OFFSET_ROM_EXIT_CODE 0x40 + +#define MMIO_OFFSET_PSI_ADDRESS 0x54 + +#define MMIO_OFFSET_PSI_SIZE 0x5C + +#define MMIO_OFFSET_IPC_STATUS 0x60 + +#define MMIO_OFFSET_CONTEXT_INFO 0x64 + +#define MMIO_OFFSET_BASE_ADDR 0x6C + +#define MMIO_OFFSET_END_ADDR 0x74 + +#define MMIO_OFFSET_CP_VERSION 0xF0 + +#define MMIO_OFFSET_CP_CAPABILITIES 0xF4 + +/* Timeout in 50 msec to wait for the modem boot code to write a valid + * execution stage into mmio area + */ +#define IPC_MMIO_EXEC_STAGE_TIMEOUT 50 + +/* check if exec stage has one of the valid values */ +static bool ipc_mmio_is_valid_exec_stage(enum ipc_mem_exec_stage stage) +{ + switch (stage) { + case IPC_MEM_EXEC_STAGE_BOOT: + case IPC_MEM_EXEC_STAGE_PSI: + case IPC_MEM_EXEC_STAGE_EBL: + case IPC_MEM_EXEC_STAGE_RUN: + case IPC_MEM_EXEC_STAGE_CRASH: + case IPC_MEM_EXEC_STAGE_CD_READY: + return true; + default: + return false; + } +} + +void ipc_mmio_update_cp_capability(struct iosm_mmio *ipc_mmio) +{ + u32 cp_cap; + unsigned int ver; + + ver = ipc_mmio_get_cp_version(ipc_mmio); + cp_cap = readl(ipc_mmio->base + ipc_mmio->offset.cp_capability); + + ipc_mmio->has_mux_lite = (ver >= IOSM_CP_VERSION) && + !(cp_cap & DL_AGGR) && !(cp_cap & UL_AGGR); + + ipc_mmio->has_ul_flow_credit = + (ver >= IOSM_CP_VERSION) && (cp_cap & UL_FLOW_CREDIT); +} + +struct iosm_mmio *ipc_mmio_init(void __iomem *mmio, struct device *dev) +{ + struct iosm_mmio *ipc_mmio = kzalloc(sizeof(*ipc_mmio), GFP_KERNEL); + int retries = IPC_MMIO_EXEC_STAGE_TIMEOUT; + enum ipc_mem_exec_stage stage; + + if (!ipc_mmio) + return NULL; + + ipc_mmio->dev = dev; + + ipc_mmio->base = mmio; + + ipc_mmio->offset.exec_stage = MMIO_OFFSET_EXECUTION_STAGE; + + /* Check for a valid execution stage to make sure that the boot code + * has correctly initialized the MMIO area. + */ + do { + stage = ipc_mmio_get_exec_stage(ipc_mmio); + if (ipc_mmio_is_valid_exec_stage(stage)) + break; + + msleep(20); + } while (retries-- > 0); + + if (!retries) { + dev_err(ipc_mmio->dev, "invalid exec stage %X", stage); + goto init_fail; + } + + ipc_mmio->offset.chip_info = MMIO_OFFSET_CHIP_INFO; + + /* read chip info size and version from chip info structure */ + ipc_mmio->chip_info_version = + ioread8(ipc_mmio->base + ipc_mmio->offset.chip_info); + + /* Increment of 2 is needed as the size value in the chip info + * excludes the version and size field, which are always present + */ + ipc_mmio->chip_info_size = + ioread8(ipc_mmio->base + ipc_mmio->offset.chip_info + 1) + 2; + + if (ipc_mmio->chip_info_size != MMIO_CHIP_INFO_SIZE) { + dev_err(ipc_mmio->dev, "Unexpected Chip Info"); + goto init_fail; + } + + ipc_mmio->offset.rom_exit_code = MMIO_OFFSET_ROM_EXIT_CODE; + + ipc_mmio->offset.psi_address = MMIO_OFFSET_PSI_ADDRESS; + ipc_mmio->offset.psi_size = MMIO_OFFSET_PSI_SIZE; + ipc_mmio->offset.ipc_status = MMIO_OFFSET_IPC_STATUS; + ipc_mmio->offset.context_info = MMIO_OFFSET_CONTEXT_INFO; + ipc_mmio->offset.ap_win_base = MMIO_OFFSET_BASE_ADDR; + ipc_mmio->offset.ap_win_end = MMIO_OFFSET_END_ADDR; + + ipc_mmio->offset.cp_version = MMIO_OFFSET_CP_VERSION; + ipc_mmio->offset.cp_capability = MMIO_OFFSET_CP_CAPABILITIES; + + return ipc_mmio; + +init_fail: + kfree(ipc_mmio); + return NULL; +} + +enum ipc_mem_exec_stage ipc_mmio_get_exec_stage(struct iosm_mmio *ipc_mmio) +{ + if (!ipc_mmio) + return IPC_MEM_EXEC_STAGE_INVALID; + + return (enum ipc_mem_exec_stage)readl(ipc_mmio->base + + ipc_mmio->offset.exec_stage); +} + +void ipc_mmio_copy_chip_info(struct iosm_mmio *ipc_mmio, void *dest, + size_t size) +{ + if (ipc_mmio && dest) + memcpy_fromio(dest, ipc_mmio->base + ipc_mmio->offset.chip_info, + size); +} + +enum ipc_mem_device_ipc_state ipc_mmio_get_ipc_state(struct iosm_mmio *ipc_mmio) +{ + if (!ipc_mmio) + return IPC_MEM_DEVICE_IPC_INVALID; + + return (enum ipc_mem_device_ipc_state) + readl(ipc_mmio->base + ipc_mmio->offset.ipc_status); +} + +enum rom_exit_code ipc_mmio_get_rom_exit_code(struct iosm_mmio *ipc_mmio) +{ + if (!ipc_mmio) + return IMEM_ROM_EXIT_FAIL; + + return (enum rom_exit_code)readl(ipc_mmio->base + + ipc_mmio->offset.rom_exit_code); +} + +void ipc_mmio_config(struct iosm_mmio *ipc_mmio) +{ + if (!ipc_mmio) + return; + + /* AP memory window (full window is open and active so that modem checks + * each AP address) 0 means don't check on modem side. + */ + iowrite64_lo_hi(0, ipc_mmio->base + ipc_mmio->offset.ap_win_base); + iowrite64_lo_hi(0, ipc_mmio->base + ipc_mmio->offset.ap_win_end); + + iowrite64_lo_hi(ipc_mmio->context_info_addr, + ipc_mmio->base + ipc_mmio->offset.context_info); +} + +void ipc_mmio_set_psi_addr_and_size(struct iosm_mmio *ipc_mmio, dma_addr_t addr, + u32 size) +{ + if (!ipc_mmio) + return; + + iowrite64_lo_hi(addr, ipc_mmio->base + ipc_mmio->offset.psi_address); + writel(size, ipc_mmio->base + ipc_mmio->offset.psi_size); +} + +void ipc_mmio_set_contex_info_addr(struct iosm_mmio *ipc_mmio, phys_addr_t addr) +{ + if (!ipc_mmio) + return; + + /* store context_info address. This will be stored in the mmio area + * during IPC_MEM_DEVICE_IPC_INIT state via ipc_mmio_config() + */ + ipc_mmio->context_info_addr = addr; +} + +int ipc_mmio_get_cp_version(struct iosm_mmio *ipc_mmio) +{ + return ipc_mmio ? readl(ipc_mmio->base + ipc_mmio->offset.cp_version) : + -EFAULT; +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_mmio.h b/drivers/net/wwan/iosm/iosm_ipc_mmio.h new file mode 100644 index 000000000000..45e6923da78f --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_mmio.h @@ -0,0 +1,183 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_MMIO_H +#define IOSM_IPC_MMIO_H + +/* Minimal IOSM CP VERSION which has valid CP_CAPABILITIES field */ +#define IOSM_CP_VERSION 0x0100UL + +/* DL dir Aggregation support mask */ +#define DL_AGGR BIT(23) + +/* UL dir Aggregation support mask */ +#define UL_AGGR BIT(22) + +/* UL flow credit support mask */ +#define UL_FLOW_CREDIT BIT(21) + +/* Possible states of the IPC finite state machine. */ +enum ipc_mem_device_ipc_state { + IPC_MEM_DEVICE_IPC_UNINIT, + IPC_MEM_DEVICE_IPC_INIT, + IPC_MEM_DEVICE_IPC_RUNNING, + IPC_MEM_DEVICE_IPC_RECOVERY, + IPC_MEM_DEVICE_IPC_ERROR, + IPC_MEM_DEVICE_IPC_DONT_CARE, + IPC_MEM_DEVICE_IPC_INVALID = -1 +}; + +/* Boot ROM exit status. */ +enum rom_exit_code { + IMEM_ROM_EXIT_OPEN_EXT = 0x01, + IMEM_ROM_EXIT_OPEN_MEM = 0x02, + IMEM_ROM_EXIT_CERT_EXT = 0x10, + IMEM_ROM_EXIT_CERT_MEM = 0x20, + IMEM_ROM_EXIT_FAIL = 0xFF +}; + +/* Boot stages */ +enum ipc_mem_exec_stage { + IPC_MEM_EXEC_STAGE_RUN = 0x600DF00D, + IPC_MEM_EXEC_STAGE_CRASH = 0x8BADF00D, + IPC_MEM_EXEC_STAGE_CD_READY = 0xBADC0DED, + IPC_MEM_EXEC_STAGE_BOOT = 0xFEEDB007, + IPC_MEM_EXEC_STAGE_PSI = 0xFEEDBEEF, + IPC_MEM_EXEC_STAGE_EBL = 0xFEEDCAFE, + IPC_MEM_EXEC_STAGE_INVALID = 0xFFFFFFFF +}; + +/* mmio scratchpad info */ +struct mmio_offset { + int exec_stage; + int chip_info; + int rom_exit_code; + int psi_address; + int psi_size; + int ipc_status; + int context_info; + int ap_win_base; + int ap_win_end; + int cp_version; + int cp_capability; +}; + +/** + * struct iosm_mmio - MMIO region mapped to the doorbell scratchpad. + * @base: Base address of MMIO region + * @dev: Pointer to device structure + * @offset: Start offset + * @context_info_addr: Physical base address of context info structure + * @chip_info_version: Version of chip info structure + * @chip_info_size: Size of chip info structure + * @has_mux_lite: It doesn't support mux aggergation + * @has_ul_flow_credit: Ul flow credit support + * @has_slp_no_prot: Device sleep no protocol support + * @has_mcr_support: Usage of mcr support + */ +struct iosm_mmio { + unsigned char __iomem *base; + struct device *dev; + struct mmio_offset offset; + phys_addr_t context_info_addr; + unsigned int chip_info_version; + unsigned int chip_info_size; + u8 has_mux_lite:1, + has_ul_flow_credit:1, + has_slp_no_prot:1, + has_mcr_support:1; +}; + +/** + * ipc_mmio_init - Allocate mmio instance data + * @mmio_addr: Mapped AP base address of the MMIO area. + * @dev: Pointer to device structure + * + * Returns: address of mmio instance data or NULL if fails. + */ +struct iosm_mmio *ipc_mmio_init(void __iomem *mmio_addr, struct device *dev); + +/** + * ipc_mmio_set_psi_addr_and_size - Set start address and size of the + * primary system image (PSI) for the + * FW dowload. + * @ipc_mmio: Pointer to mmio instance + * @addr: PSI address + * @size: PSI immage size + */ +void ipc_mmio_set_psi_addr_and_size(struct iosm_mmio *ipc_mmio, dma_addr_t addr, + u32 size); + +/** + * ipc_mmio_set_contex_info_addr - Stores the Context Info Address in + * MMIO instance to share it with CP during + * mmio_init. + * @ipc_mmio: Pointer to mmio instance + * @addr: 64-bit address of AP context information. + */ +void ipc_mmio_set_contex_info_addr(struct iosm_mmio *ipc_mmio, + phys_addr_t addr); + +/** + * ipc_mmio_get_cp_version - Get the CP IPC version + * @ipc_mmio: Pointer to mmio instance + * + * Returns: version number on success and failure value on error. + */ +int ipc_mmio_get_cp_version(struct iosm_mmio *ipc_mmio); + +/** + * ipc_mmio_get_rom_exit_code - Get exit code from CP boot rom download app + * @ipc_mmio: Pointer to mmio instance + * + * Returns: exit code from CP boot rom download APP + */ +enum rom_exit_code ipc_mmio_get_rom_exit_code(struct iosm_mmio *ipc_mmio); + +/** + * ipc_mmio_get_exec_stage - Query CP execution stage + * @ipc_mmio: Pointer to mmio instance + * + * Returns: CP execution stage + */ +enum ipc_mem_exec_stage ipc_mmio_get_exec_stage(struct iosm_mmio *ipc_mmio); + +/** + * ipc_mmio_get_ipc_state - Query CP IPC state + * @ipc_mmio: Pointer to mmio instance + * + * Returns: CP IPC state + */ +enum ipc_mem_device_ipc_state +ipc_mmio_get_ipc_state(struct iosm_mmio *ipc_mmio); + +/** + * ipc_mmio_copy_chip_info - Copy size bytes of CP chip info structure + * into caller provided buffer + * @ipc_mmio: Pointer to mmio instance + * @dest: Pointer to caller provided buff + * @size: Number of bytes to copy + */ +void ipc_mmio_copy_chip_info(struct iosm_mmio *ipc_mmio, void *dest, + size_t size); + +/** + * ipc_mmio_config - Write context info and AP memory range addresses. + * This needs to be called when CP is in + * IPC_MEM_DEVICE_IPC_INIT state + * + * @ipc_mmio: Pointer to mmio instance + */ +void ipc_mmio_config(struct iosm_mmio *ipc_mmio); + +/** + * ipc_mmio_update_cp_capability - Read and update modem capability, from mmio + * capability offset + * + * @ipc_mmio: Pointer to mmio instance + */ +void ipc_mmio_update_cp_capability(struct iosm_mmio *ipc_mmio); + +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.c b/drivers/net/wwan/iosm/iosm_ipc_mux.c new file mode 100644 index 000000000000..c1c77ce699da --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_mux.c @@ -0,0 +1,455 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include "iosm_ipc_mux_codec.h" + +/* At the begin of the runtime phase the IP MUX channel shall created. */ +static int ipc_mux_channel_create(struct iosm_mux *ipc_mux) +{ + int channel_id; + + channel_id = ipc_imem_channel_alloc(ipc_mux->imem, ipc_mux->instance_id, + IPC_CTYPE_WWAN); + + if (channel_id < 0) { + dev_err(ipc_mux->dev, + "allocation of the MUX channel id failed"); + ipc_mux->state = MUX_S_ERROR; + ipc_mux->event = MUX_E_NOT_APPLICABLE; + goto no_channel; + } + + /* Establish the MUX channel in blocking mode. */ + ipc_mux->channel = ipc_imem_channel_open(ipc_mux->imem, channel_id, + IPC_HP_NET_CHANNEL_INIT); + + if (!ipc_mux->channel) { + dev_err(ipc_mux->dev, "ipc_imem_channel_open failed"); + ipc_mux->state = MUX_S_ERROR; + ipc_mux->event = MUX_E_NOT_APPLICABLE; + return -ENODEV; /* MUX channel is not available. */ + } + + /* Define the MUX active state properties. */ + ipc_mux->state = MUX_S_ACTIVE; + ipc_mux->event = MUX_E_NO_ORDERS; + +no_channel: + return channel_id; +} + +/* Reset the session/if id state. */ +static void ipc_mux_session_free(struct iosm_mux *ipc_mux, int if_id) +{ + struct mux_session *if_entry; + + if_entry = &ipc_mux->session[if_id]; + /* Reset the session state. */ + if_entry->wwan = NULL; +} + +/* Create and send the session open command. */ +static struct mux_cmd_open_session_resp * +ipc_mux_session_open_send(struct iosm_mux *ipc_mux, int if_id) +{ + struct mux_cmd_open_session_resp *open_session_resp; + struct mux_acb *acb = &ipc_mux->acb; + union mux_cmd_param param; + + /* open_session commands to one ACB and start transmission. */ + param.open_session.flow_ctrl = 0; + param.open_session.ipv4v6_hints = 0; + param.open_session.reserved2 = 0; + param.open_session.dl_head_pad_len = cpu_to_le32(IPC_MEM_DL_ETH_OFFSET); + + /* Finish and transfer ACB. The user thread is suspended. + * It is a blocking function call, until CP responds or timeout. + */ + acb->wanted_response = MUX_CMD_OPEN_SESSION_RESP; + if (ipc_mux_dl_acb_send_cmds(ipc_mux, MUX_CMD_OPEN_SESSION, if_id, 0, + ¶m, sizeof(param.open_session), true, + false) || + acb->got_response != MUX_CMD_OPEN_SESSION_RESP) { + dev_err(ipc_mux->dev, "if_id %d: OPEN_SESSION send failed", + if_id); + return NULL; + } + + open_session_resp = &ipc_mux->acb.got_param.open_session_resp; + if (open_session_resp->response != cpu_to_le32(MUX_CMD_RESP_SUCCESS)) { + dev_err(ipc_mux->dev, + "if_id %d,session open failed,response=%d", if_id, + open_session_resp->response); + return NULL; + } + + return open_session_resp; +} + +/* Open the first IP session. */ +static bool ipc_mux_session_open(struct iosm_mux *ipc_mux, + struct mux_session_open *session_open) +{ + struct mux_cmd_open_session_resp *open_session_resp; + int if_id; + + /* Search for a free session interface id. */ + if_id = le32_to_cpu(session_open->if_id); + if (if_id < 0 || if_id >= ipc_mux->nr_sessions) { + dev_err(ipc_mux->dev, "invalid interface id=%d", if_id); + return false; + } + + /* Create and send the session open command. + * It is a blocking function call, until CP responds or timeout. + */ + open_session_resp = ipc_mux_session_open_send(ipc_mux, if_id); + if (!open_session_resp) { + ipc_mux_session_free(ipc_mux, if_id); + session_open->if_id = cpu_to_le32(-1); + return false; + } + + /* Initialize the uplink skb accumulator. */ + skb_queue_head_init(&ipc_mux->session[if_id].ul_list); + + ipc_mux->session[if_id].dl_head_pad_len = IPC_MEM_DL_ETH_OFFSET; + ipc_mux->session[if_id].ul_head_pad_len = + le32_to_cpu(open_session_resp->ul_head_pad_len); + ipc_mux->session[if_id].wwan = ipc_mux->wwan; + + /* Reset the flow ctrl stats of the session */ + ipc_mux->session[if_id].flow_ctl_en_cnt = 0; + ipc_mux->session[if_id].flow_ctl_dis_cnt = 0; + ipc_mux->session[if_id].ul_flow_credits = 0; + ipc_mux->session[if_id].net_tx_stop = false; + ipc_mux->session[if_id].flow_ctl_mask = 0; + + /* Save and return the assigned if id. */ + session_open->if_id = cpu_to_le32(if_id); + + return true; +} + +/* Free pending session UL packet. */ +static void ipc_mux_session_reset(struct iosm_mux *ipc_mux, int if_id) +{ + /* Reset the session/if id state. */ + ipc_mux_session_free(ipc_mux, if_id); + + /* Empty the uplink skb accumulator. */ + skb_queue_purge(&ipc_mux->session[if_id].ul_list); +} + +static void ipc_mux_session_close(struct iosm_mux *ipc_mux, + struct mux_session_close *msg) +{ + int if_id; + + /* Copy the session interface id. */ + if_id = le32_to_cpu(msg->if_id); + + if (if_id < 0 || if_id >= ipc_mux->nr_sessions) { + dev_err(ipc_mux->dev, "invalid session id %d", if_id); + return; + } + + /* Create and send the session close command. + * It is a blocking function call, until CP responds or timeout. + */ + if (ipc_mux_dl_acb_send_cmds(ipc_mux, MUX_CMD_CLOSE_SESSION, if_id, 0, + NULL, 0, true, false)) + dev_err(ipc_mux->dev, "if_id %d: CLOSE_SESSION send failed", + if_id); + + /* Reset the flow ctrl stats of the session */ + ipc_mux->session[if_id].flow_ctl_en_cnt = 0; + ipc_mux->session[if_id].flow_ctl_dis_cnt = 0; + ipc_mux->session[if_id].flow_ctl_mask = 0; + + ipc_mux_session_reset(ipc_mux, if_id); +} + +static void ipc_mux_channel_close(struct iosm_mux *ipc_mux, + struct mux_channel_close *channel_close_p) +{ + int i; + + /* Free pending session UL packet. */ + for (i = 0; i < ipc_mux->nr_sessions; i++) + if (ipc_mux->session[i].wwan) + ipc_mux_session_reset(ipc_mux, i); + + ipc_imem_channel_close(ipc_mux->imem, ipc_mux->channel_id); + + /* Reset the MUX object. */ + ipc_mux->state = MUX_S_INACTIVE; + ipc_mux->event = MUX_E_INACTIVE; +} + +/* CP has interrupted AP. If AP is in IP MUX mode, execute the pending ops. */ +static int ipc_mux_schedule(struct iosm_mux *ipc_mux, union mux_msg *msg) +{ + enum mux_event order; + bool success; + int ret = -EIO; + + if (!ipc_mux->initialized) { + ret = -EAGAIN; + goto out; + } + + order = msg->common.event; + + switch (ipc_mux->state) { + case MUX_S_INACTIVE: + if (order != MUX_E_MUX_SESSION_OPEN) + goto out; /* Wait for the request to open a session */ + + if (ipc_mux->event == MUX_E_INACTIVE) + /* Establish the MUX channel and the new state. */ + ipc_mux->channel_id = ipc_mux_channel_create(ipc_mux); + + if (ipc_mux->state != MUX_S_ACTIVE) { + ret = ipc_mux->channel_id; /* Missing the MUX channel */ + goto out; + } + + /* Disable the TD update timer and open the first IP session. */ + ipc_imem_td_update_timer_suspend(ipc_mux->imem, true); + ipc_mux->event = MUX_E_MUX_SESSION_OPEN; + success = ipc_mux_session_open(ipc_mux, &msg->session_open); + + ipc_imem_td_update_timer_suspend(ipc_mux->imem, false); + if (success) + ret = ipc_mux->channel_id; + goto out; + + case MUX_S_ACTIVE: + switch (order) { + case MUX_E_MUX_SESSION_OPEN: + /* Disable the TD update timer and open a session */ + ipc_imem_td_update_timer_suspend(ipc_mux->imem, true); + ipc_mux->event = MUX_E_MUX_SESSION_OPEN; + success = ipc_mux_session_open(ipc_mux, + &msg->session_open); + ipc_imem_td_update_timer_suspend(ipc_mux->imem, false); + if (success) + ret = ipc_mux->channel_id; + goto out; + + case MUX_E_MUX_SESSION_CLOSE: + /* Release an IP session. */ + ipc_mux->event = MUX_E_MUX_SESSION_CLOSE; + ipc_mux_session_close(ipc_mux, &msg->session_close); + ret = ipc_mux->channel_id; + goto out; + + case MUX_E_MUX_CHANNEL_CLOSE: + /* Close the MUX channel pipes. */ + ipc_mux->event = MUX_E_MUX_CHANNEL_CLOSE; + ipc_mux_channel_close(ipc_mux, &msg->channel_close); + ret = ipc_mux->channel_id; + goto out; + + default: + /* Invalid order. */ + goto out; + } + + default: + dev_err(ipc_mux->dev, + "unexpected MUX transition: state=%d, event=%d", + ipc_mux->state, ipc_mux->event); + } +out: + return ret; +} + +struct iosm_mux *ipc_mux_init(struct ipc_mux_config *mux_cfg, + struct iosm_imem *imem) +{ + struct iosm_mux *ipc_mux = kzalloc(sizeof(*ipc_mux), GFP_KERNEL); + int i, ul_tds, ul_td_size; + struct sk_buff_head *free_list; + struct sk_buff *skb; + + if (!ipc_mux) + return NULL; + + ipc_mux->protocol = mux_cfg->protocol; + ipc_mux->ul_flow = mux_cfg->ul_flow; + ipc_mux->nr_sessions = mux_cfg->nr_sessions; + ipc_mux->instance_id = mux_cfg->instance_id; + ipc_mux->wwan_q_offset = 0; + + ipc_mux->pcie = imem->pcie; + ipc_mux->imem = imem; + ipc_mux->ipc_protocol = imem->ipc_protocol; + ipc_mux->dev = imem->dev; + ipc_mux->wwan = imem->wwan; + + /* Get the reference to the UL ADB list. */ + free_list = &ipc_mux->ul_adb.free_list; + + /* Initialize the list with free ADB. */ + skb_queue_head_init(free_list); + + ul_td_size = IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE; + + ul_tds = IPC_MEM_MAX_TDS_MUX_LITE_UL; + + ipc_mux->ul_adb.dest_skb = NULL; + + ipc_mux->initialized = true; + ipc_mux->adb_prep_ongoing = false; + ipc_mux->size_needed = 0; + ipc_mux->ul_data_pend_bytes = 0; + ipc_mux->state = MUX_S_INACTIVE; + ipc_mux->ev_mux_net_transmit_pending = false; + ipc_mux->tx_transaction_id = 0; + ipc_mux->rr_next_session = 0; + ipc_mux->event = MUX_E_INACTIVE; + ipc_mux->channel_id = -1; + ipc_mux->channel = NULL; + + /* Allocate the list of UL ADB. */ + for (i = 0; i < ul_tds; i++) { + dma_addr_t mapping; + + skb = ipc_pcie_alloc_skb(ipc_mux->pcie, ul_td_size, GFP_ATOMIC, + &mapping, DMA_TO_DEVICE, 0); + if (!skb) { + ipc_mux_deinit(ipc_mux); + return NULL; + } + /* Extend the UL ADB list. */ + skb_queue_tail(free_list, skb); + } + + return ipc_mux; +} + +/* Informs the network stack to restart transmission for all opened session if + * Flow Control is not ON for that session. + */ +static void ipc_mux_restart_tx_for_all_sessions(struct iosm_mux *ipc_mux) +{ + struct mux_session *session; + int idx; + + for (idx = 0; idx < ipc_mux->nr_sessions; idx++) { + session = &ipc_mux->session[idx]; + + if (!session->wwan) + continue; + + /* If flow control of the session is OFF and if there was tx + * stop then restart. Inform the network interface to restart + * sending data. + */ + if (session->flow_ctl_mask == 0) { + session->net_tx_stop = false; + ipc_mux_netif_tx_flowctrl(session, idx, false); + } + } +} + +/* Informs the network stack to stop sending further pkt for all opened + * sessions + */ +static void ipc_mux_stop_netif_for_all_sessions(struct iosm_mux *ipc_mux) +{ + struct mux_session *session; + int idx; + + for (idx = 0; idx < ipc_mux->nr_sessions; idx++) { + session = &ipc_mux->session[idx]; + + if (!session->wwan) + continue; + + ipc_mux_netif_tx_flowctrl(session, session->if_id, true); + } +} + +void ipc_mux_check_n_restart_tx(struct iosm_mux *ipc_mux) +{ + if (ipc_mux->ul_flow == MUX_UL) { + int low_thresh = IPC_MEM_MUX_UL_FLOWCTRL_LOW_B; + + if (ipc_mux->ul_data_pend_bytes < low_thresh) + ipc_mux_restart_tx_for_all_sessions(ipc_mux); + } +} + +int ipc_mux_get_max_sessions(struct iosm_mux *ipc_mux) +{ + return ipc_mux ? ipc_mux->nr_sessions : -EFAULT; +} + +enum ipc_mux_protocol ipc_mux_get_active_protocol(struct iosm_mux *ipc_mux) +{ + return ipc_mux ? ipc_mux->protocol : MUX_UNKNOWN; +} + +int ipc_mux_open_session(struct iosm_mux *ipc_mux, int session_nr) +{ + struct mux_session_open *session_open; + union mux_msg mux_msg; + + session_open = &mux_msg.session_open; + session_open->event = MUX_E_MUX_SESSION_OPEN; + + session_open->if_id = cpu_to_le32(session_nr); + ipc_mux->session[session_nr].flags |= IPC_MEM_WWAN_MUX; + return ipc_mux_schedule(ipc_mux, &mux_msg); +} + +int ipc_mux_close_session(struct iosm_mux *ipc_mux, int session_nr) +{ + struct mux_session_close *session_close; + union mux_msg mux_msg; + int ret_val; + + session_close = &mux_msg.session_close; + session_close->event = MUX_E_MUX_SESSION_CLOSE; + + session_close->if_id = cpu_to_le32(session_nr); + ret_val = ipc_mux_schedule(ipc_mux, &mux_msg); + ipc_mux->session[session_nr].flags &= ~IPC_MEM_WWAN_MUX; + + return ret_val; +} + +void ipc_mux_deinit(struct iosm_mux *ipc_mux) +{ + struct mux_channel_close *channel_close; + struct sk_buff_head *free_list; + union mux_msg mux_msg; + struct sk_buff *skb; + + if (!ipc_mux->initialized) + return; + ipc_mux_stop_netif_for_all_sessions(ipc_mux); + + channel_close = &mux_msg.channel_close; + channel_close->event = MUX_E_MUX_CHANNEL_CLOSE; + ipc_mux_schedule(ipc_mux, &mux_msg); + + /* Empty the ADB free list. */ + free_list = &ipc_mux->ul_adb.free_list; + + /* Remove from the head of the downlink queue. */ + while ((skb = skb_dequeue(free_list))) + ipc_pcie_kfree_skb(ipc_mux->pcie, skb); + + if (ipc_mux->channel) { + ipc_mux->channel->ul_pipe.is_open = false; + ipc_mux->channel->dl_pipe.is_open = false; + } + + kfree(ipc_mux); +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.h b/drivers/net/wwan/iosm/iosm_ipc_mux.h new file mode 100644 index 000000000000..ddd2cd0bd911 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_mux.h @@ -0,0 +1,343 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_MUX_H +#define IOSM_IPC_MUX_H + +#include "iosm_ipc_protocol.h" + +/* Size of the buffer for the IP MUX data buffer. */ +#define IPC_MEM_MAX_DL_MUX_BUF_SIZE (16 * 1024) +#define IPC_MEM_MAX_UL_ADB_BUF_SIZE IPC_MEM_MAX_DL_MUX_BUF_SIZE + +/* Size of the buffer for the IP MUX Lite data buffer. */ +#define IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE (2 * 1024) + +/* TD counts for IP MUX Lite */ +#define IPC_MEM_MAX_TDS_MUX_LITE_UL 800 +#define IPC_MEM_MAX_TDS_MUX_LITE_DL 1200 + +/* open session request (AP->CP) */ +#define MUX_CMD_OPEN_SESSION 1 + +/* response to open session request (CP->AP) */ +#define MUX_CMD_OPEN_SESSION_RESP 2 + +/* close session request (AP->CP) */ +#define MUX_CMD_CLOSE_SESSION 3 + +/* response to close session request (CP->AP) */ +#define MUX_CMD_CLOSE_SESSION_RESP 4 + +/* Flow control command with mask of the flow per queue/flow. */ +#define MUX_LITE_CMD_FLOW_CTL 5 + +/* ACK the flow control command. Shall have the same Transaction ID as the + * matching FLOW_CTL command. + */ +#define MUX_LITE_CMD_FLOW_CTL_ACK 6 + +/* Command for report packet indicating link quality metrics. */ +#define MUX_LITE_CMD_LINK_STATUS_REPORT 7 + +/* Response to a report packet */ +#define MUX_LITE_CMD_LINK_STATUS_REPORT_RESP 8 + +/* Used to reset a command/response state. */ +#define MUX_CMD_INVALID 255 + +/* command response : command processed successfully */ +#define MUX_CMD_RESP_SUCCESS 0 + +/* MUX for route link devices */ +#define IPC_MEM_WWAN_MUX BIT(0) + +/* Initiated actions to change the state of the MUX object. */ +enum mux_event { + MUX_E_INACTIVE, /* No initiated actions. */ + MUX_E_MUX_SESSION_OPEN, /* Create the MUX channel and a session. */ + MUX_E_MUX_SESSION_CLOSE, /* Release a session. */ + MUX_E_MUX_CHANNEL_CLOSE, /* Release the MUX channel. */ + MUX_E_NO_ORDERS, /* No MUX order. */ + MUX_E_NOT_APPLICABLE, /* Defect IP MUX. */ +}; + +/* MUX session open command. */ +struct mux_session_open { + enum mux_event event; + __le32 if_id; +}; + +/* MUX session close command. */ +struct mux_session_close { + enum mux_event event; + __le32 if_id; +}; + +/* MUX channel close command. */ +struct mux_channel_close { + enum mux_event event; +}; + +/* Default message type to find out the right message type. */ +struct mux_common { + enum mux_event event; +}; + +/* List of ops in MUX mode. */ +union mux_msg { + struct mux_session_open session_open; + struct mux_session_close session_close; + struct mux_channel_close channel_close; + struct mux_common common; +}; + +/* Parameter definition of the open session command. */ +struct mux_cmd_open_session { + u8 flow_ctrl; /* 0: Flow control disabled (flow allowed). */ + /* 1: Flow control enabled (flow not allowed)*/ + u8 ipv4v6_hints; /* 0: IPv4/IPv6 hints not supported.*/ + /* 1: IPv4/IPv6 hints supported*/ + __le16 reserved2; /* Reserved. Set to zero. */ + __le32 dl_head_pad_len; /* Maximum length supported */ + /* for DL head padding on a datagram. */ +}; + +/* Parameter definition of the open session response. */ +struct mux_cmd_open_session_resp { + __le32 response; /* Response code */ + u8 flow_ctrl; /* 0: Flow control disabled (flow allowed). */ + /* 1: Flow control enabled (flow not allowed) */ + u8 ipv4v6_hints; /* 0: IPv4/IPv6 hints not supported */ + /* 1: IPv4/IPv6 hints supported */ + __le16 reserved2; /* Reserved. Set to zero. */ + __le32 ul_head_pad_len; /* Actual length supported for */ + /* UL head padding on adatagram.*/ +}; + +/* Parameter definition of the close session response code */ +struct mux_cmd_close_session_resp { + __le32 response; +}; + +/* Parameter definition of the flow control command. */ +struct mux_cmd_flow_ctl { + __le32 mask; /* indicating the desired flow control */ + /* state for various flows/queues */ +}; + +/* Parameter definition of the link status report code*/ +struct mux_cmd_link_status_report { + u8 payload; +}; + +/* Parameter definition of the link status report response code. */ +struct mux_cmd_link_status_report_resp { + __le32 response; +}; + +/** + * union mux_cmd_param - Union-definition of the command parameters. + * @open_session: Inband command for open session + * @open_session_resp: Inband command for open session response + * @close_session_resp: Inband command for close session response + * @flow_ctl: In-band flow control on the opened interfaces + * @link_status: In-band Link Status Report + * @link_status_resp: In-band command for link status report response + */ +union mux_cmd_param { + struct mux_cmd_open_session open_session; + struct mux_cmd_open_session_resp open_session_resp; + struct mux_cmd_close_session_resp close_session_resp; + struct mux_cmd_flow_ctl flow_ctl; + struct mux_cmd_link_status_report link_status; + struct mux_cmd_link_status_report_resp link_status_resp; +}; + +/* States of the MUX object.. */ +enum mux_state { + MUX_S_INACTIVE, /* IP MUX is unused. */ + MUX_S_ACTIVE, /* IP MUX channel is available. */ + MUX_S_ERROR, /* Defect IP MUX. */ +}; + +/* Supported MUX protocols. */ +enum ipc_mux_protocol { + MUX_UNKNOWN, + MUX_LITE, +}; + +/* Supported UL data transfer methods. */ +enum ipc_mux_ul_flow { + MUX_UL_UNKNOWN, + MUX_UL, /* Normal UL data transfer */ + MUX_UL_ON_CREDITS, /* UL data transfer will be based on credits */ +}; + +/* List of the MUX session. */ +struct mux_session { + struct iosm_wwan *wwan; /*Network i/f used for communication*/ + int if_id; /* i/f id for session open message.*/ + u32 flags; + u32 ul_head_pad_len; /* Nr of bytes for UL head padding. */ + u32 dl_head_pad_len; /* Nr of bytes for DL head padding. */ + struct sk_buff_head ul_list; /* skb entries for an ADT. */ + u32 flow_ctl_mask; /* UL flow control */ + u32 flow_ctl_en_cnt; /* Flow control Enable cmd count */ + u32 flow_ctl_dis_cnt; /* Flow Control Disable cmd count */ + int ul_flow_credits; /* UL flow credits */ + u8 net_tx_stop:1, + flush:1; /* flush net interface ? */ +}; + +/* State of a single UL data block. */ +struct mux_adb { + struct sk_buff *dest_skb; /* Current UL skb for the data block. */ + u8 *buf; /* ADB memory. */ + struct mux_adgh *adgh; /* ADGH pointer */ + struct sk_buff *qlth_skb; /* QLTH pointer */ + u32 *next_table_index; /* Pointer to next table index. */ + struct sk_buff_head free_list; /* List of alloc. ADB for the UL sess.*/ + int size; /* Size of the ADB memory. */ + u32 if_cnt; /* Statistic counter */ + u32 dg_cnt_total; + u32 payload_size; +}; + +/* Temporary ACB state. */ +struct mux_acb { + struct sk_buff *skb; /* Used UL skb. */ + int if_id; /* Session id. */ + u32 wanted_response; + u32 got_response; + u32 cmd; + union mux_cmd_param got_param; /* Received command/response parameter */ +}; + +/** + * struct iosm_mux - Structure of the data multiplexing over an IP channel. + * @dev: Pointer to device structure + * @session: Array of the MUX sessions. + * @channel: Reference to the IP MUX channel + * @pcie: Pointer to iosm_pcie struct + * @imem: Pointer to iosm_imem + * @wwan: Poinetr to iosm_wwan + * @ipc_protocol: Pointer to iosm_protocol + * @channel_id: Channel ID for MUX + * @protocol: Type of the MUX protocol + * @ul_flow: UL Flow type + * @nr_sessions: Number of sessions + * @instance_id: Instance ID + * @state: States of the MUX object + * @event: Initiated actions to change the state of the MUX object + * @tx_transaction_id: Transaction id for the ACB command. + * @rr_next_session: Next session number for round robin. + * @ul_adb: State of the UL ADB/ADGH. + * @size_needed: Variable to store the size needed during ADB preparation + * @ul_data_pend_bytes: Pending UL data to be processed in bytes + * @acb: Temporary ACB state + * @wwan_q_offset: This will hold the offset of the given instance + * Useful while passing or receiving packets from + * wwan/imem layer. + * @initialized: MUX object is initialized + * @ev_mux_net_transmit_pending: + * 0 means inform the IPC tasklet to pass the + * accumulated uplink ADB to CP. + * @adb_prep_ongoing: Flag for ADB preparation status + */ +struct iosm_mux { + struct device *dev; + struct mux_session session[IPC_MEM_MUX_IP_SESSION_ENTRIES]; + struct ipc_mem_channel *channel; + struct iosm_pcie *pcie; + struct iosm_imem *imem; + struct iosm_wwan *wwan; + struct iosm_protocol *ipc_protocol; + int channel_id; + enum ipc_mux_protocol protocol; + enum ipc_mux_ul_flow ul_flow; + int nr_sessions; + int instance_id; + enum mux_state state; + enum mux_event event; + u32 tx_transaction_id; + int rr_next_session; + struct mux_adb ul_adb; + int size_needed; + long long ul_data_pend_bytes; + struct mux_acb acb; + int wwan_q_offset; + u8 initialized:1, + ev_mux_net_transmit_pending:1, + adb_prep_ongoing:1; +}; + +/* MUX configuration structure */ +struct ipc_mux_config { + enum ipc_mux_protocol protocol; + enum ipc_mux_ul_flow ul_flow; + int nr_sessions; + int instance_id; +}; + +/** + * ipc_mux_init - Allocates and Init MUX instance + * @mux_cfg: Pointer to MUX configuration structure + * @ipc_imem: Pointer to imem data-struct + * + * Returns: Initialized mux pointer on success else NULL + */ +struct iosm_mux *ipc_mux_init(struct ipc_mux_config *mux_cfg, + struct iosm_imem *ipc_imem); + +/** + * ipc_mux_deinit - Deallocates MUX instance + * @ipc_mux: Pointer to the MUX instance. + */ +void ipc_mux_deinit(struct iosm_mux *ipc_mux); + +/** + * ipc_mux_check_n_restart_tx - Checks for pending UL date bytes and then + * it restarts the net interface tx queue if + * device has set flow control as off. + * @ipc_mux: Pointer to MUX data-struct + */ +void ipc_mux_check_n_restart_tx(struct iosm_mux *ipc_mux); + +/** + * ipc_mux_get_active_protocol - Returns the active MUX protocol type. + * @ipc_mux: Pointer to MUX data-struct + * + * Returns: enum of type ipc_mux_protocol + */ +enum ipc_mux_protocol ipc_mux_get_active_protocol(struct iosm_mux *ipc_mux); + +/** + * ipc_mux_open_session - Opens a MUX session for IP traffic. + * @ipc_mux: Pointer to MUX data-struct + * @session_nr: Interface ID or session number + * + * Returns: channel id on success, failure value on error + */ +int ipc_mux_open_session(struct iosm_mux *ipc_mux, int session_nr); + +/** + * ipc_mux_close_session - Closes a MUX session. + * @ipc_mux: Pointer to MUX data-struct + * @session_nr: Interface ID or session number + * + * Returns: channel id on success, failure value on error + */ +int ipc_mux_close_session(struct iosm_mux *ipc_mux, int session_nr); + +/** + * ipc_mux_get_max_sessions - Retuns the maximum sessions supported on the + * provided MUX instance.. + * @ipc_mux: Pointer to MUX data-struct + * + * Returns: Number of sessions supported on Success and failure value on error + */ +int ipc_mux_get_max_sessions(struct iosm_mux *ipc_mux); +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c new file mode 100644 index 000000000000..e634ffc6ec08 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c @@ -0,0 +1,910 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include + +#include "iosm_ipc_imem_ops.h" +#include "iosm_ipc_mux_codec.h" +#include "iosm_ipc_task_queue.h" + +/* Test the link power state and send a MUX command in blocking mode. */ +static int ipc_mux_tq_cmd_send(struct iosm_imem *ipc_imem, int arg, void *msg, + size_t size) +{ + struct iosm_mux *ipc_mux = ipc_imem->mux; + const struct mux_acb *acb = msg; + + skb_queue_tail(&ipc_mux->channel->ul_list, acb->skb); + ipc_imem_ul_send(ipc_mux->imem); + + return 0; +} + +static int ipc_mux_acb_send(struct iosm_mux *ipc_mux, bool blocking) +{ + struct completion *completion = &ipc_mux->channel->ul_sem; + int ret = ipc_task_queue_send_task(ipc_mux->imem, ipc_mux_tq_cmd_send, + 0, &ipc_mux->acb, + sizeof(ipc_mux->acb), false); + if (ret) { + dev_err(ipc_mux->dev, "unable to send mux command"); + return ret; + } + + /* if blocking, suspend the app and wait for irq in the flash or + * crash phase. return false on timeout to indicate failure. + */ + if (blocking) { + u32 wait_time_milliseconds = IPC_MUX_CMD_RUN_DEFAULT_TIMEOUT; + + reinit_completion(completion); + + if (wait_for_completion_interruptible_timeout + (completion, msecs_to_jiffies(wait_time_milliseconds)) == + 0) { + dev_err(ipc_mux->dev, "ch[%d] timeout", + ipc_mux->channel_id); + ipc_uevent_send(ipc_mux->imem->dev, UEVENT_MDM_TIMEOUT); + return -ETIMEDOUT; + } + } + + return 0; +} + +/* Prepare mux Command */ +static struct mux_lite_cmdh *ipc_mux_lite_add_cmd(struct iosm_mux *ipc_mux, + u32 cmd, struct mux_acb *acb, + void *param, u32 param_size) +{ + struct mux_lite_cmdh *cmdh = (struct mux_lite_cmdh *)acb->skb->data; + + cmdh->signature = cpu_to_le32(MUX_SIG_CMDH); + cmdh->command_type = cpu_to_le32(cmd); + cmdh->if_id = acb->if_id; + + acb->cmd = cmd; + + cmdh->cmd_len = cpu_to_le16(offsetof(struct mux_lite_cmdh, param) + + param_size); + cmdh->transaction_id = cpu_to_le32(ipc_mux->tx_transaction_id++); + + if (param) + memcpy(&cmdh->param, param, param_size); + + skb_put(acb->skb, le16_to_cpu(cmdh->cmd_len)); + + return cmdh; +} + +static int ipc_mux_acb_alloc(struct iosm_mux *ipc_mux) +{ + struct mux_acb *acb = &ipc_mux->acb; + struct sk_buff *skb; + dma_addr_t mapping; + + /* Allocate skb memory for the uplink buffer. */ + skb = ipc_pcie_alloc_skb(ipc_mux->pcie, MUX_MAX_UL_ACB_BUF_SIZE, + GFP_ATOMIC, &mapping, DMA_TO_DEVICE, 0); + if (!skb) + return -ENOMEM; + + /* Save the skb address. */ + acb->skb = skb; + + memset(skb->data, 0, MUX_MAX_UL_ACB_BUF_SIZE); + + return 0; +} + +int ipc_mux_dl_acb_send_cmds(struct iosm_mux *ipc_mux, u32 cmd_type, u8 if_id, + u32 transaction_id, union mux_cmd_param *param, + size_t res_size, bool blocking, bool respond) +{ + struct mux_acb *acb = &ipc_mux->acb; + struct mux_lite_cmdh *ack_lite; + int ret = 0; + + acb->if_id = if_id; + ret = ipc_mux_acb_alloc(ipc_mux); + if (ret) + return ret; + + ack_lite = ipc_mux_lite_add_cmd(ipc_mux, cmd_type, acb, param, + res_size); + if (respond) + ack_lite->transaction_id = cpu_to_le32(transaction_id); + + ret = ipc_mux_acb_send(ipc_mux, blocking); + + return ret; +} + +void ipc_mux_netif_tx_flowctrl(struct mux_session *session, int idx, bool on) +{ + /* Inform the network interface to start/stop flow ctrl */ + ipc_wwan_tx_flowctrl(session->wwan, idx, on); +} + +static int ipc_mux_dl_cmdresps_decode_process(struct iosm_mux *ipc_mux, + struct mux_lite_cmdh *cmdh) +{ + struct mux_acb *acb = &ipc_mux->acb; + + switch (le32_to_cpu(cmdh->command_type)) { + case MUX_CMD_OPEN_SESSION_RESP: + case MUX_CMD_CLOSE_SESSION_RESP: + /* Resume the control application. */ + acb->got_param = cmdh->param; + break; + + case MUX_LITE_CMD_FLOW_CTL_ACK: + /* This command type is not expected as response for + * Aggregation version of the protocol. So return non-zero. + */ + if (ipc_mux->protocol != MUX_LITE) + return -EINVAL; + + dev_dbg(ipc_mux->dev, "if %u FLOW_CTL_ACK %u received", + cmdh->if_id, le32_to_cpu(cmdh->transaction_id)); + break; + + default: + return -EINVAL; + } + + acb->wanted_response = MUX_CMD_INVALID; + acb->got_response = le32_to_cpu(cmdh->command_type); + complete(&ipc_mux->channel->ul_sem); + + return 0; +} + +static int ipc_mux_dl_dlcmds_decode_process(struct iosm_mux *ipc_mux, + struct mux_lite_cmdh *cmdh) +{ + union mux_cmd_param *param = &cmdh->param; + struct mux_session *session; + int new_size; + + dev_dbg(ipc_mux->dev, "if_id[%d]: dlcmds decode process %d", + cmdh->if_id, le32_to_cpu(cmdh->command_type)); + + switch (le32_to_cpu(cmdh->command_type)) { + case MUX_LITE_CMD_FLOW_CTL: + + if (cmdh->if_id >= ipc_mux->nr_sessions) { + dev_err(ipc_mux->dev, "if_id [%d] not valid", + cmdh->if_id); + return -EINVAL; /* No session interface id. */ + } + + session = &ipc_mux->session[cmdh->if_id]; + + new_size = offsetof(struct mux_lite_cmdh, param) + + sizeof(param->flow_ctl); + if (param->flow_ctl.mask == cpu_to_le32(0xFFFFFFFF)) { + /* Backward Compatibility */ + if (cmdh->cmd_len == cpu_to_le16(new_size)) + session->flow_ctl_mask = + le32_to_cpu(param->flow_ctl.mask); + else + session->flow_ctl_mask = ~0; + /* if CP asks for FLOW CTRL Enable + * then set our internal flow control Tx flag + * to limit uplink session queueing + */ + session->net_tx_stop = true; + /* Update the stats */ + session->flow_ctl_en_cnt++; + } else if (param->flow_ctl.mask == 0) { + /* Just reset the Flow control mask and let + * mux_flow_ctrl_low_thre_b take control on + * our internal Tx flag and enabling kernel + * flow control + */ + /* Backward Compatibility */ + if (cmdh->cmd_len == cpu_to_le16(new_size)) + session->flow_ctl_mask = + le32_to_cpu(param->flow_ctl.mask); + else + session->flow_ctl_mask = 0; + /* Update the stats */ + session->flow_ctl_dis_cnt++; + } else { + break; + } + + dev_dbg(ipc_mux->dev, "if[%u] FLOW CTRL 0x%08X", cmdh->if_id, + le32_to_cpu(param->flow_ctl.mask)); + break; + + case MUX_LITE_CMD_LINK_STATUS_REPORT: + break; + + default: + return -EINVAL; + } + return 0; +} + +/* Decode and Send appropriate response to a command block. */ +static void ipc_mux_dl_cmd_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb) +{ + struct mux_lite_cmdh *cmdh = (struct mux_lite_cmdh *)skb->data; + __le32 trans_id = cmdh->transaction_id; + + if (ipc_mux_dl_cmdresps_decode_process(ipc_mux, cmdh)) { + /* Unable to decode command response indicates the cmd_type + * may be a command instead of response. So try to decoding it. + */ + if (!ipc_mux_dl_dlcmds_decode_process(ipc_mux, cmdh)) { + /* Decoded command may need a response. Give the + * response according to the command type. + */ + union mux_cmd_param *mux_cmd = NULL; + size_t size = 0; + u32 cmd = MUX_LITE_CMD_LINK_STATUS_REPORT_RESP; + + if (cmdh->command_type == + cpu_to_le32(MUX_LITE_CMD_LINK_STATUS_REPORT)) { + mux_cmd = &cmdh->param; + mux_cmd->link_status_resp.response = + cpu_to_le32(MUX_CMD_RESP_SUCCESS); + /* response field is u32 */ + size = sizeof(u32); + } else if (cmdh->command_type == + cpu_to_le32(MUX_LITE_CMD_FLOW_CTL)) { + cmd = MUX_LITE_CMD_FLOW_CTL_ACK; + } else { + return; + } + + if (ipc_mux_dl_acb_send_cmds(ipc_mux, cmd, cmdh->if_id, + le32_to_cpu(trans_id), + mux_cmd, size, false, + true)) + dev_err(ipc_mux->dev, + "if_id %d: cmd send failed", + cmdh->if_id); + } + } +} + +/* Pass the DL packet to the netif layer. */ +static int ipc_mux_net_receive(struct iosm_mux *ipc_mux, int if_id, + struct iosm_wwan *wwan, u32 offset, + u8 service_class, struct sk_buff *skb) +{ + struct sk_buff *dest_skb = skb_clone(skb, GFP_ATOMIC); + + if (!dest_skb) + return -ENOMEM; + + skb_pull(dest_skb, offset); + skb_set_tail_pointer(dest_skb, dest_skb->len); + /* Pass the packet to the netif layer. */ + dest_skb->priority = service_class; + + return ipc_wwan_receive(wwan, dest_skb, false, if_id + 1); +} + +/* Decode Flow Credit Table in the block */ +static void ipc_mux_dl_fcth_decode(struct iosm_mux *ipc_mux, + unsigned char *block) +{ + struct ipc_mem_lite_gen_tbl *fct = (struct ipc_mem_lite_gen_tbl *)block; + struct iosm_wwan *wwan; + int ul_credits; + int if_id; + + if (fct->vfl_length != sizeof(fct->vfl.nr_of_bytes)) { + dev_err(ipc_mux->dev, "unexpected FCT length: %d", + fct->vfl_length); + return; + } + + if_id = fct->if_id; + if (if_id >= ipc_mux->nr_sessions) { + dev_err(ipc_mux->dev, "not supported if_id: %d", if_id); + return; + } + + /* Is the session active ? */ + if_id = array_index_nospec(if_id, ipc_mux->nr_sessions); + wwan = ipc_mux->session[if_id].wwan; + if (!wwan) { + dev_err(ipc_mux->dev, "session Net ID is NULL"); + return; + } + + ul_credits = fct->vfl.nr_of_bytes; + + dev_dbg(ipc_mux->dev, "Flow_Credit:: if_id[%d] Old: %d Grants: %d", + if_id, ipc_mux->session[if_id].ul_flow_credits, ul_credits); + + /* Update the Flow Credit information from ADB */ + ipc_mux->session[if_id].ul_flow_credits += ul_credits; + + /* Check whether the TX can be started */ + if (ipc_mux->session[if_id].ul_flow_credits > 0) { + ipc_mux->session[if_id].net_tx_stop = false; + ipc_mux_netif_tx_flowctrl(&ipc_mux->session[if_id], + ipc_mux->session[if_id].if_id, false); + } +} + +/* Decode non-aggregated datagram */ +static void ipc_mux_dl_adgh_decode(struct iosm_mux *ipc_mux, + struct sk_buff *skb) +{ + u32 pad_len, packet_offset; + struct iosm_wwan *wwan; + struct mux_adgh *adgh; + u8 *block = skb->data; + int rc = 0; + u8 if_id; + + adgh = (struct mux_adgh *)block; + + if (adgh->signature != cpu_to_le32(MUX_SIG_ADGH)) { + dev_err(ipc_mux->dev, "invalid ADGH signature received"); + return; + } + + if_id = adgh->if_id; + if (if_id >= ipc_mux->nr_sessions) { + dev_err(ipc_mux->dev, "invalid if_id while decoding %d", if_id); + return; + } + + /* Is the session active ? */ + if_id = array_index_nospec(if_id, ipc_mux->nr_sessions); + wwan = ipc_mux->session[if_id].wwan; + if (!wwan) { + dev_err(ipc_mux->dev, "session Net ID is NULL"); + return; + } + + /* Store the pad len for the corresponding session + * Pad bytes as negotiated in the open session less the header size + * (see session management chapter for details). + * If resulting padding is zero or less, the additional head padding is + * omitted. For e.g., if HEAD_PAD_LEN = 16 or less, this field is + * omitted if HEAD_PAD_LEN = 20, then this field will have 4 bytes + * set to zero + */ + pad_len = + ipc_mux->session[if_id].dl_head_pad_len - IPC_MEM_DL_ETH_OFFSET; + packet_offset = sizeof(*adgh) + pad_len; + + if_id += ipc_mux->wwan_q_offset; + + /* Pass the packet to the netif layer */ + rc = ipc_mux_net_receive(ipc_mux, if_id, wwan, packet_offset, + adgh->service_class, skb); + if (rc) { + dev_err(ipc_mux->dev, "mux adgh decoding error"); + return; + } + ipc_mux->session[if_id].flush = 1; +} + +void ipc_mux_dl_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb) +{ + u32 signature; + + if (!skb->data) + return; + + /* Decode the MUX header type. */ + signature = le32_to_cpup((__le32 *)skb->data); + + switch (signature) { + case MUX_SIG_ADGH: + ipc_mux_dl_adgh_decode(ipc_mux, skb); + break; + + case MUX_SIG_FCTH: + ipc_mux_dl_fcth_decode(ipc_mux, skb->data); + break; + + case MUX_SIG_CMDH: + ipc_mux_dl_cmd_decode(ipc_mux, skb); + break; + + default: + dev_err(ipc_mux->dev, "invalid ABH signature"); + } + + ipc_pcie_kfree_skb(ipc_mux->pcie, skb); +} + +static int ipc_mux_ul_skb_alloc(struct iosm_mux *ipc_mux, + struct mux_adb *ul_adb, u32 type) +{ + /* Take the first element of the free list. */ + struct sk_buff *skb = skb_dequeue(&ul_adb->free_list); + int qlt_size; + + if (!skb) + return -EBUSY; /* Wait for a free ADB skb. */ + + /* Mark it as UL ADB to select the right free operation. */ + IPC_CB(skb)->op_type = (u8)UL_MUX_OP_ADB; + + switch (type) { + case MUX_SIG_ADGH: + /* Save the ADB memory settings. */ + ul_adb->dest_skb = skb; + ul_adb->buf = skb->data; + ul_adb->size = IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE; + /* reset statistic counter */ + ul_adb->if_cnt = 0; + ul_adb->payload_size = 0; + ul_adb->dg_cnt_total = 0; + + ul_adb->adgh = (struct mux_adgh *)skb->data; + memset(ul_adb->adgh, 0, sizeof(struct mux_adgh)); + break; + + case MUX_SIG_QLTH: + qlt_size = offsetof(struct ipc_mem_lite_gen_tbl, vfl) + + (MUX_QUEUE_LEVEL * sizeof(struct mux_lite_vfl)); + + if (qlt_size > IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE) { + dev_err(ipc_mux->dev, + "can't support. QLT size:%d SKB size: %d", + qlt_size, IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE); + return -ERANGE; + } + + ul_adb->qlth_skb = skb; + memset((ul_adb->qlth_skb)->data, 0, qlt_size); + skb_put(skb, qlt_size); + break; + } + + return 0; +} + +static void ipc_mux_ul_adgh_finish(struct iosm_mux *ipc_mux) +{ + struct mux_adb *ul_adb = &ipc_mux->ul_adb; + u16 adgh_len; + long long bytes; + char *str; + + if (!ul_adb->dest_skb) { + dev_err(ipc_mux->dev, "no dest skb"); + return; + } + + adgh_len = le16_to_cpu(ul_adb->adgh->length); + skb_put(ul_adb->dest_skb, adgh_len); + skb_queue_tail(&ipc_mux->channel->ul_list, ul_adb->dest_skb); + ul_adb->dest_skb = NULL; + + if (ipc_mux->ul_flow == MUX_UL_ON_CREDITS) { + struct mux_session *session; + + session = &ipc_mux->session[ul_adb->adgh->if_id]; + str = "available_credits"; + bytes = (long long)session->ul_flow_credits; + + } else { + str = "pend_bytes"; + bytes = ipc_mux->ul_data_pend_bytes; + ipc_mux->ul_data_pend_bytes = ipc_mux->ul_data_pend_bytes + + adgh_len; + } + + dev_dbg(ipc_mux->dev, "UL ADGH: size=%u, if_id=%d, payload=%d, %s=%lld", + adgh_len, ul_adb->adgh->if_id, ul_adb->payload_size, + str, bytes); +} + +/* Allocates an ADB from the free list and initializes it with ADBH */ +static bool ipc_mux_ul_adb_allocate(struct iosm_mux *ipc_mux, + struct mux_adb *adb, int *size_needed, + u32 type) +{ + bool ret_val = false; + int status; + + if (!adb->dest_skb) { + /* Allocate memory for the ADB including of the + * datagram table header. + */ + status = ipc_mux_ul_skb_alloc(ipc_mux, adb, type); + if (status) + /* Is a pending ADB available ? */ + ret_val = true; /* None. */ + + /* Update size need to zero only for new ADB memory */ + *size_needed = 0; + } + + return ret_val; +} + +/* Informs the network stack to stop sending further packets for all opened + * sessions + */ +static void ipc_mux_stop_tx_for_all_sessions(struct iosm_mux *ipc_mux) +{ + struct mux_session *session; + int idx; + + for (idx = 0; idx < ipc_mux->nr_sessions; idx++) { + session = &ipc_mux->session[idx]; + + if (!session->wwan) + continue; + + session->net_tx_stop = true; + } +} + +/* Sends Queue Level Table of all opened sessions */ +static bool ipc_mux_lite_send_qlt(struct iosm_mux *ipc_mux) +{ + struct ipc_mem_lite_gen_tbl *qlt; + struct mux_session *session; + bool qlt_updated = false; + int i; + int qlt_size; + + if (!ipc_mux->initialized || ipc_mux->state != MUX_S_ACTIVE) + return qlt_updated; + + qlt_size = offsetof(struct ipc_mem_lite_gen_tbl, vfl) + + MUX_QUEUE_LEVEL * sizeof(struct mux_lite_vfl); + + for (i = 0; i < ipc_mux->nr_sessions; i++) { + session = &ipc_mux->session[i]; + + if (!session->wwan || session->flow_ctl_mask) + continue; + + if (ipc_mux_ul_skb_alloc(ipc_mux, &ipc_mux->ul_adb, + MUX_SIG_QLTH)) { + dev_err(ipc_mux->dev, + "no reserved mem to send QLT of if_id: %d", i); + break; + } + + /* Prepare QLT */ + qlt = (struct ipc_mem_lite_gen_tbl *)(ipc_mux->ul_adb.qlth_skb) + ->data; + qlt->signature = cpu_to_le32(MUX_SIG_QLTH); + qlt->length = cpu_to_le16(qlt_size); + qlt->if_id = i; + qlt->vfl_length = MUX_QUEUE_LEVEL * sizeof(struct mux_lite_vfl); + qlt->reserved[0] = 0; + qlt->reserved[1] = 0; + + qlt->vfl.nr_of_bytes = session->ul_list.qlen; + + /* Add QLT to the transfer list. */ + skb_queue_tail(&ipc_mux->channel->ul_list, + ipc_mux->ul_adb.qlth_skb); + + qlt_updated = true; + ipc_mux->ul_adb.qlth_skb = NULL; + } + + if (qlt_updated) + /* Updates the TDs with ul_list */ + (void)ipc_imem_ul_write_td(ipc_mux->imem); + + return qlt_updated; +} + +/* Checks the available credits for the specified session and returns + * number of packets for which credits are available. + */ +static int ipc_mux_ul_bytes_credits_check(struct iosm_mux *ipc_mux, + struct mux_session *session, + struct sk_buff_head *ul_list, + int max_nr_of_pkts) +{ + int pkts_to_send = 0; + struct sk_buff *skb; + int credits = 0; + + if (ipc_mux->ul_flow == MUX_UL_ON_CREDITS) { + credits = session->ul_flow_credits; + if (credits <= 0) { + dev_dbg(ipc_mux->dev, + "FC::if_id[%d] Insuff.Credits/Qlen:%d/%u", + session->if_id, session->ul_flow_credits, + session->ul_list.qlen); /* nr_of_bytes */ + return 0; + } + } else { + credits = IPC_MEM_MUX_UL_FLOWCTRL_HIGH_B - + ipc_mux->ul_data_pend_bytes; + if (credits <= 0) { + ipc_mux_stop_tx_for_all_sessions(ipc_mux); + + dev_dbg(ipc_mux->dev, + "if_id[%d] encod. fail Bytes: %llu, thresh: %d", + session->if_id, ipc_mux->ul_data_pend_bytes, + IPC_MEM_MUX_UL_FLOWCTRL_HIGH_B); + return 0; + } + } + + /* Check if there are enough credits/bytes available to send the + * requested max_nr_of_pkts. Otherwise restrict the nr_of_pkts + * depending on available credits. + */ + skb_queue_walk(ul_list, skb) + { + if (!(credits >= skb->len && pkts_to_send < max_nr_of_pkts)) + break; + credits -= skb->len; + pkts_to_send++; + } + + return pkts_to_send; +} + +/* Encode the UL IP packet according to Lite spec. */ +static int ipc_mux_ul_adgh_encode(struct iosm_mux *ipc_mux, int session_id, + struct mux_session *session, + struct sk_buff_head *ul_list, + struct mux_adb *adb, int nr_of_pkts) +{ + int offset = sizeof(struct mux_adgh); + int adb_updated = -EINVAL; + struct sk_buff *src_skb; + int aligned_size = 0; + int nr_of_skb = 0; + u32 pad_len = 0; + + /* Re-calculate the number of packets depending on number of bytes to be + * processed/available credits. + */ + nr_of_pkts = ipc_mux_ul_bytes_credits_check(ipc_mux, session, ul_list, + nr_of_pkts); + + /* If calculated nr_of_pkts from available credits is <= 0 + * then nothing to do. + */ + if (nr_of_pkts <= 0) + return 0; + + /* Read configured UL head_pad_length for session.*/ + if (session->ul_head_pad_len > IPC_MEM_DL_ETH_OFFSET) + pad_len = session->ul_head_pad_len - IPC_MEM_DL_ETH_OFFSET; + + /* Process all pending UL packets for this session + * depending on the allocated datagram table size. + */ + while (nr_of_pkts > 0) { + /* get destination skb allocated */ + if (ipc_mux_ul_adb_allocate(ipc_mux, adb, &ipc_mux->size_needed, + MUX_SIG_ADGH)) { + dev_err(ipc_mux->dev, "no reserved memory for ADGH"); + return -ENOMEM; + } + + /* Peek at the head of the list. */ + src_skb = skb_peek(ul_list); + if (!src_skb) { + dev_err(ipc_mux->dev, + "skb peek return NULL with count : %d", + nr_of_pkts); + break; + } + + /* Calculate the memory value. */ + aligned_size = ALIGN((pad_len + src_skb->len), 4); + + ipc_mux->size_needed = sizeof(struct mux_adgh) + aligned_size; + + if (ipc_mux->size_needed > adb->size) { + dev_dbg(ipc_mux->dev, "size needed %d, adgh size %d", + ipc_mux->size_needed, adb->size); + /* Return 1 if any IP packet is added to the transfer + * list. + */ + return nr_of_skb ? 1 : 0; + } + + /* Add buffer (without head padding to next pending transfer) */ + memcpy(adb->buf + offset + pad_len, src_skb->data, + src_skb->len); + + adb->adgh->signature = cpu_to_le32(MUX_SIG_ADGH); + adb->adgh->if_id = session_id; + adb->adgh->length = + cpu_to_le16(sizeof(struct mux_adgh) + pad_len + + src_skb->len); + adb->adgh->service_class = src_skb->priority; + adb->adgh->next_count = --nr_of_pkts; + adb->dg_cnt_total++; + adb->payload_size += src_skb->len; + + if (ipc_mux->ul_flow == MUX_UL_ON_CREDITS) + /* Decrement the credit value as we are processing the + * datagram from the UL list. + */ + session->ul_flow_credits -= src_skb->len; + + /* Remove the processed elements and free it. */ + src_skb = skb_dequeue(ul_list); + dev_kfree_skb(src_skb); + nr_of_skb++; + + ipc_mux_ul_adgh_finish(ipc_mux); + } + + if (nr_of_skb) { + /* Send QLT info to modem if pending bytes > high watermark + * in case of mux lite + */ + if (ipc_mux->ul_flow == MUX_UL_ON_CREDITS || + ipc_mux->ul_data_pend_bytes >= + IPC_MEM_MUX_UL_FLOWCTRL_LOW_B) + adb_updated = ipc_mux_lite_send_qlt(ipc_mux); + else + adb_updated = 1; + + /* Updates the TDs with ul_list */ + (void)ipc_imem_ul_write_td(ipc_mux->imem); + } + + return adb_updated; +} + +bool ipc_mux_ul_data_encode(struct iosm_mux *ipc_mux) +{ + struct sk_buff_head *ul_list; + struct mux_session *session; + int updated = 0; + int session_id; + int dg_n; + int i; + + if (!ipc_mux || ipc_mux->state != MUX_S_ACTIVE || + ipc_mux->adb_prep_ongoing) + return false; + + ipc_mux->adb_prep_ongoing = true; + + for (i = 0; i < ipc_mux->nr_sessions; i++) { + session_id = ipc_mux->rr_next_session; + session = &ipc_mux->session[session_id]; + + /* Go to next handle rr_next_session overflow */ + ipc_mux->rr_next_session++; + if (ipc_mux->rr_next_session >= ipc_mux->nr_sessions) + ipc_mux->rr_next_session = 0; + + if (!session->wwan || session->flow_ctl_mask || + session->net_tx_stop) + continue; + + ul_list = &session->ul_list; + + /* Is something pending in UL and flow ctrl off */ + dg_n = skb_queue_len(ul_list); + if (dg_n > MUX_MAX_UL_DG_ENTRIES) + dg_n = MUX_MAX_UL_DG_ENTRIES; + + if (dg_n == 0) + /* Nothing to do for ipc_mux session + * -> try next session id. + */ + continue; + + updated = ipc_mux_ul_adgh_encode(ipc_mux, session_id, session, + ul_list, &ipc_mux->ul_adb, + dg_n); + } + + ipc_mux->adb_prep_ongoing = false; + return updated == 1; +} + +void ipc_mux_ul_encoded_process(struct iosm_mux *ipc_mux, struct sk_buff *skb) +{ + struct mux_adgh *adgh; + u16 adgh_len; + + adgh = (struct mux_adgh *)skb->data; + adgh_len = le16_to_cpu(adgh->length); + + if (adgh->signature == cpu_to_le32(MUX_SIG_ADGH) && + ipc_mux->ul_flow == MUX_UL) + ipc_mux->ul_data_pend_bytes = ipc_mux->ul_data_pend_bytes - + adgh_len; + + if (ipc_mux->ul_flow == MUX_UL) + dev_dbg(ipc_mux->dev, "ul_data_pend_bytes: %lld", + ipc_mux->ul_data_pend_bytes); + + /* Reset the skb settings. */ + skb->tail = 0; + skb->len = 0; + + /* Add the consumed ADB to the free list. */ + skb_queue_tail((&ipc_mux->ul_adb.free_list), skb); +} + +/* Start the NETIF uplink send transfer in MUX mode. */ +static int ipc_mux_tq_ul_trigger_encode(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size) +{ + struct iosm_mux *ipc_mux = ipc_imem->mux; + bool ul_data_pend = false; + + /* Add session UL data to a ADB and ADGH */ + ul_data_pend = ipc_mux_ul_data_encode(ipc_mux); + if (ul_data_pend) + /* Delay the doorbell irq */ + ipc_imem_td_update_timer_start(ipc_mux->imem); + + /* reset the debounce flag */ + ipc_mux->ev_mux_net_transmit_pending = false; + + return 0; +} + +int ipc_mux_ul_trigger_encode(struct iosm_mux *ipc_mux, int if_id, + struct sk_buff *skb) +{ + struct mux_session *session = &ipc_mux->session[if_id]; + int ret = -EINVAL; + + if (ipc_mux->channel && + ipc_mux->channel->state != IMEM_CHANNEL_ACTIVE) { + dev_err(ipc_mux->dev, + "channel state is not IMEM_CHANNEL_ACTIVE"); + goto out; + } + + if (!session->wwan) { + dev_err(ipc_mux->dev, "session net ID is NULL"); + ret = -EFAULT; + goto out; + } + + /* Session is under flow control. + * Check if packet can be queued in session list, if not + * suspend net tx + */ + if (skb_queue_len(&session->ul_list) >= + (session->net_tx_stop ? + IPC_MEM_MUX_UL_SESS_FCON_THRESHOLD : + (IPC_MEM_MUX_UL_SESS_FCON_THRESHOLD * + IPC_MEM_MUX_UL_SESS_FCOFF_THRESHOLD_FACTOR))) { + ipc_mux_netif_tx_flowctrl(session, session->if_id, true); + ret = -EBUSY; + goto out; + } + + /* Add skb to the uplink skb accumulator. */ + skb_queue_tail(&session->ul_list, skb); + + /* Inform the IPC kthread to pass uplink IP packets to CP. */ + if (!ipc_mux->ev_mux_net_transmit_pending) { + ipc_mux->ev_mux_net_transmit_pending = true; + ret = ipc_task_queue_send_task(ipc_mux->imem, + ipc_mux_tq_ul_trigger_encode, 0, + NULL, 0, false); + if (ret) + goto out; + } + dev_dbg(ipc_mux->dev, "mux ul if[%d] qlen=%d/%u, len=%d/%d, prio=%d", + if_id, skb_queue_len(&session->ul_list), session->ul_list.qlen, + skb->len, skb->truesize, skb->priority); + ret = 0; +out: + return ret; +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h new file mode 100644 index 000000000000..4a74e3c9457f --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.h @@ -0,0 +1,193 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_MUX_CODEC_H +#define IOSM_IPC_MUX_CODEC_H + +#include "iosm_ipc_mux.h" + +/* Queue level size and reporting + * >1 is enable, 0 is disable + */ +#define MUX_QUEUE_LEVEL 1 + +/* Size of the buffer for the IP MUX commands. */ +#define MUX_MAX_UL_ACB_BUF_SIZE 256 + +/* Maximum number of packets in a go per session */ +#define MUX_MAX_UL_DG_ENTRIES 100 + +/* ADGH: Signature of the Datagram Header. */ +#define MUX_SIG_ADGH 0x48474441 + +/* CMDH: Signature of the Command Header. */ +#define MUX_SIG_CMDH 0x48444D43 + +/* QLTH: Signature of the Queue Level Table */ +#define MUX_SIG_QLTH 0x48544C51 + +/* FCTH: Signature of the Flow Credit Table */ +#define MUX_SIG_FCTH 0x48544346 + +/* MUX UL session threshold factor */ +#define IPC_MEM_MUX_UL_SESS_FCOFF_THRESHOLD_FACTOR (4) + +/* Size of the buffer for the IP MUX Lite data buffer. */ +#define IPC_MEM_MAX_DL_MUX_LITE_BUF_SIZE (2 * 1024) + +/* MUX UL session threshold in number of packets */ +#define IPC_MEM_MUX_UL_SESS_FCON_THRESHOLD (64) + +/* Default time out for sending IPC session commands like + * open session, close session etc + * unit : milliseconds + */ +#define IPC_MUX_CMD_RUN_DEFAULT_TIMEOUT 1000 /* 1 second */ + +/* MUX UL flow control lower threshold in bytes */ +#define IPC_MEM_MUX_UL_FLOWCTRL_LOW_B 10240 /* 10KB */ + +/* MUX UL flow control higher threshold in bytes (5ms worth of data)*/ +#define IPC_MEM_MUX_UL_FLOWCTRL_HIGH_B (110 * 1024) + +/** + * struct mux_adgh - Aggregated Datagram Header. + * @signature: Signature of the Aggregated Datagram Header(0x48474441) + * @length: Length (in bytes) of the datagram header. This length + * shall include the header size. Min value: 0x10 + * @if_id: ID of the interface the datagrams belong to + * @opt_ipv4v6: Indicates IPv4(=0)/IPv6(=1), It is optional if not + * used set it to zero. + * @reserved: Reserved bits. Set to zero. + * @service_class: Service class identifier for the datagram. + * @next_count: Count of the datagrams that shall be following this + * datagrams for this interface. A count of zero means + * the next datagram may not belong to this interface. + * @reserved1: Reserved bytes, Set to zero + */ +struct mux_adgh { + __le32 signature; + __le16 length; + u8 if_id; + u8 opt_ipv4v6; + u8 service_class; + u8 next_count; + u8 reserved1[6]; +}; + +/** + * struct mux_lite_cmdh - MUX Lite Command Header + * @signature: Signature of the Command Header(0x48444D43) + * @cmd_len: Length (in bytes) of the command. This length shall + * include the header size. Minimum value: 0x10 + * @if_id: ID of the interface the commands in the table belong to. + * @reserved: Reserved Set to zero. + * @command_type: Command Enum. + * @transaction_id: 4 byte value shall be generated and sent along with a + * command Responses and ACKs shall have the same + * Transaction ID as their commands. It shall be unique to + * the command transaction on the given interface. + * @param: Optional parameters used with the command. + */ +struct mux_lite_cmdh { + __le32 signature; + __le16 cmd_len; + u8 if_id; + u8 reserved; + __le32 command_type; + __le32 transaction_id; + union mux_cmd_param param; +}; + +/** + * struct mux_lite_vfl - value field in generic table + * @nr_of_bytes: Number of bytes available to transmit in the queue. + */ +struct mux_lite_vfl { + u32 nr_of_bytes; +}; + +/** + * struct ipc_mem_lite_gen_tbl - Generic table format for Queue Level + * and Flow Credit + * @signature: Signature of the table + * @length: Length of the table + * @if_id: ID of the interface the table belongs to + * @vfl_length: Value field length + * @reserved: Reserved + * @vfl: Value field of variable length + */ +struct ipc_mem_lite_gen_tbl { + __le32 signature; + __le16 length; + u8 if_id; + u8 vfl_length; + u32 reserved[2]; + struct mux_lite_vfl vfl; +}; + +/** + * ipc_mux_dl_decode -Route the DL packet through the IP MUX layer + * depending on Header. + * @ipc_mux: Pointer to MUX data-struct + * @skb: Pointer to ipc_skb. + */ +void ipc_mux_dl_decode(struct iosm_mux *ipc_mux, struct sk_buff *skb); + +/** + * ipc_mux_dl_acb_send_cmds - Respond to the Command blocks. + * @ipc_mux: Pointer to MUX data-struct + * @cmd_type: Command + * @if_id: Session interface id. + * @transaction_id: Command transaction id. + * @param: Pointer to command params. + * @res_size: Response size + * @blocking: True for blocking send + * @respond: If true return transaction ID + * + * Returns: 0 in success and failure value on error + */ +int ipc_mux_dl_acb_send_cmds(struct iosm_mux *ipc_mux, u32 cmd_type, u8 if_id, + u32 transaction_id, union mux_cmd_param *param, + size_t res_size, bool blocking, bool respond); + +/** + * ipc_mux_netif_tx_flowctrl - Enable/Disable TX flow control on MUX sessions. + * @session: Pointer to mux_session struct + * @idx: Session ID + * @on: true for Enable and false for disable flow control + */ +void ipc_mux_netif_tx_flowctrl(struct mux_session *session, int idx, bool on); + +/** + * ipc_mux_ul_trigger_encode - Route the UL packet through the IP MUX layer + * for encoding. + * @ipc_mux: Pointer to MUX data-struct + * @if_id: Session ID. + * @skb: Pointer to ipc_skb. + * + * Returns: 0 if successfully encoded + * failure value on error + * -EBUSY if packet has to be retransmitted. + */ +int ipc_mux_ul_trigger_encode(struct iosm_mux *ipc_mux, int if_id, + struct sk_buff *skb); +/** + * ipc_mux_ul_data_encode - UL encode function for calling from Tasklet context. + * @ipc_mux: Pointer to MUX data-struct + * + * Returns: TRUE if any packet of any session is encoded FALSE otherwise. + */ +bool ipc_mux_ul_data_encode(struct iosm_mux *ipc_mux); + +/** + * ipc_mux_ul_encoded_process - Handles the Modem processed UL data by adding + * the SKB to the UL free list. + * @ipc_mux: Pointer to MUX data-struct + * @skb: Pointer to ipc_skb. + */ +void ipc_mux_ul_encoded_process(struct iosm_mux *ipc_mux, struct sk_buff *skb); + +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c new file mode 100644 index 000000000000..7f7d364d3a51 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -0,0 +1,580 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include +#include +#include +#include + +#include "iosm_ipc_imem.h" +#include "iosm_ipc_pcie.h" +#include "iosm_ipc_protocol.h" + +MODULE_DESCRIPTION("IOSM Driver"); +MODULE_LICENSE("GPL v2"); + +/* WWAN GUID */ +static guid_t wwan_acpi_guid = GUID_INIT(0xbad01b75, 0x22a8, 0x4f48, 0x87, 0x92, + 0xbd, 0xde, 0x94, 0x67, 0x74, 0x7d); + +static void ipc_pcie_resources_release(struct iosm_pcie *ipc_pcie) +{ + /* Free the MSI resources. */ + ipc_release_irq(ipc_pcie); + + /* Free mapped doorbell scratchpad bus memory into CPU space. */ + iounmap(ipc_pcie->scratchpad); + + /* Free mapped IPC_REGS bus memory into CPU space. */ + iounmap(ipc_pcie->ipc_regs); + + /* Releases all PCI I/O and memory resources previously reserved by a + * successful call to pci_request_regions. Call this function only + * after all use of the PCI regions has ceased. + */ + pci_release_regions(ipc_pcie->pci); +} + +static void ipc_pcie_cleanup(struct iosm_pcie *ipc_pcie) +{ + /* Free the shared memory resources. */ + ipc_imem_cleanup(ipc_pcie->imem); + + ipc_pcie_resources_release(ipc_pcie); + + /* Signal to the system that the PCI device is not in use. */ + pci_disable_device(ipc_pcie->pci); +} + +static void ipc_pcie_deinit(struct iosm_pcie *ipc_pcie) +{ + kfree(ipc_pcie->imem); + kfree(ipc_pcie); +} + +static void ipc_pcie_remove(struct pci_dev *pci) +{ + struct iosm_pcie *ipc_pcie = pci_get_drvdata(pci); + + ipc_pcie_cleanup(ipc_pcie); + + ipc_pcie_deinit(ipc_pcie); +} + +static int ipc_pcie_resources_request(struct iosm_pcie *ipc_pcie) +{ + struct pci_dev *pci = ipc_pcie->pci; + u32 cap = 0; + u32 ret; + + /* Reserved PCI I/O and memory resources. + * Mark all PCI regions associated with PCI device pci as + * being reserved by owner IOSM_IPC. + */ + ret = pci_request_regions(pci, "IOSM_IPC"); + if (ret) { + dev_err(ipc_pcie->dev, "failed pci request regions"); + goto pci_request_region_fail; + } + + /* Reserve the doorbell IPC REGS memory resources. + * Remap the memory into CPU space. Arrange for the physical address + * (BAR) to be visible from this driver. + * pci_ioremap_bar() ensures that the memory is marked uncachable. + */ + ipc_pcie->ipc_regs = pci_ioremap_bar(pci, ipc_pcie->ipc_regs_bar_nr); + + if (!ipc_pcie->ipc_regs) { + dev_err(ipc_pcie->dev, "IPC REGS ioremap error"); + ret = -EBUSY; + goto ipc_regs_remap_fail; + } + + /* Reserve the MMIO scratchpad memory resources. + * Remap the memory into CPU space. Arrange for the physical address + * (BAR) to be visible from this driver. + * pci_ioremap_bar() ensures that the memory is marked uncachable. + */ + ipc_pcie->scratchpad = + pci_ioremap_bar(pci, ipc_pcie->scratchpad_bar_nr); + + if (!ipc_pcie->scratchpad) { + dev_err(ipc_pcie->dev, "doorbell scratchpad ioremap error"); + ret = -EBUSY; + goto scratch_remap_fail; + } + + /* Install the irq handler triggered by CP. */ + ret = ipc_acquire_irq(ipc_pcie); + if (ret) { + dev_err(ipc_pcie->dev, "acquiring MSI irq failed!"); + goto irq_acquire_fail; + } + + /* Enable bus-mastering for the IOSM IPC device. */ + pci_set_master(pci); + + /* Enable LTR if possible + * This is needed for L1.2! + */ + pcie_capability_read_dword(ipc_pcie->pci, PCI_EXP_DEVCAP2, &cap); + if (cap & PCI_EXP_DEVCAP2_LTR) + pcie_capability_set_word(ipc_pcie->pci, PCI_EXP_DEVCTL2, + PCI_EXP_DEVCTL2_LTR_EN); + + dev_dbg(ipc_pcie->dev, "link between AP and CP is fully on"); + + return ret; + +irq_acquire_fail: + iounmap(ipc_pcie->scratchpad); +scratch_remap_fail: + iounmap(ipc_pcie->ipc_regs); +ipc_regs_remap_fail: + pci_release_regions(pci); +pci_request_region_fail: + return ret; +} + +bool ipc_pcie_check_aspm_enabled(struct iosm_pcie *ipc_pcie, + bool parent) +{ + struct pci_dev *pdev; + u16 value = 0; + u32 enabled; + + if (parent) + pdev = ipc_pcie->pci->bus->self; + else + pdev = ipc_pcie->pci; + + pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &value); + enabled = value & PCI_EXP_LNKCTL_ASPMC; + dev_dbg(ipc_pcie->dev, "ASPM L1: 0x%04X 0x%03X", pdev->device, value); + + return (enabled == PCI_EXP_LNKCTL_ASPM_L1 || + enabled == PCI_EXP_LNKCTL_ASPMC); +} + +bool ipc_pcie_check_data_link_active(struct iosm_pcie *ipc_pcie) +{ + struct pci_dev *parent; + u16 link_status = 0; + + if (!ipc_pcie->pci->bus || !ipc_pcie->pci->bus->self) { + dev_err(ipc_pcie->dev, "root port not found"); + return false; + } + + parent = ipc_pcie->pci->bus->self; + + pcie_capability_read_word(parent, PCI_EXP_LNKSTA, &link_status); + dev_dbg(ipc_pcie->dev, "Link status: 0x%04X", link_status); + + return link_status & PCI_EXP_LNKSTA_DLLLA; +} + +static bool ipc_pcie_check_aspm_supported(struct iosm_pcie *ipc_pcie, + bool parent) +{ + struct pci_dev *pdev; + u32 support; + u32 cap = 0; + + if (parent) + pdev = ipc_pcie->pci->bus->self; + else + pdev = ipc_pcie->pci; + pcie_capability_read_dword(pdev, PCI_EXP_LNKCAP, &cap); + support = u32_get_bits(cap, PCI_EXP_LNKCAP_ASPMS); + if (support < PCI_EXP_LNKCTL_ASPM_L1) { + dev_dbg(ipc_pcie->dev, "ASPM L1 not supported: 0x%04X", + pdev->device); + return false; + } + return true; +} + +void ipc_pcie_config_aspm(struct iosm_pcie *ipc_pcie) +{ + bool parent_aspm_enabled, dev_aspm_enabled; + + /* check if both root port and child supports ASPM L1 */ + if (!ipc_pcie_check_aspm_supported(ipc_pcie, true) || + !ipc_pcie_check_aspm_supported(ipc_pcie, false)) + return; + + parent_aspm_enabled = ipc_pcie_check_aspm_enabled(ipc_pcie, true); + dev_aspm_enabled = ipc_pcie_check_aspm_enabled(ipc_pcie, false); + + dev_dbg(ipc_pcie->dev, "ASPM parent: %s device: %s", + parent_aspm_enabled ? "Enabled" : "Disabled", + dev_aspm_enabled ? "Enabled" : "Disabled"); +} + +/* Initializes PCIe endpoint configuration */ +static void ipc_pcie_config_init(struct iosm_pcie *ipc_pcie) +{ + /* BAR0 is used for doorbell */ + ipc_pcie->ipc_regs_bar_nr = IPC_DOORBELL_BAR0; + + /* update HW configuration */ + ipc_pcie->scratchpad_bar_nr = IPC_SCRATCHPAD_BAR2; + ipc_pcie->doorbell_reg_offset = IPC_DOORBELL_CH_OFFSET; + ipc_pcie->doorbell_write = IPC_WRITE_PTR_REG_0; + ipc_pcie->doorbell_capture = IPC_CAPTURE_PTR_REG_0; +} + +/* This will read the BIOS WWAN RTD3 settings: + * D0L1.2/D3L2/Disabled + */ +static enum ipc_pcie_sleep_state ipc_pcie_read_bios_cfg(struct device *dev) +{ + union acpi_object *object; + acpi_handle handle_acpi; + + handle_acpi = ACPI_HANDLE(dev); + if (!handle_acpi) { + pr_debug("pci device is NOT ACPI supporting device\n"); + goto default_ret; + } + + object = acpi_evaluate_dsm(handle_acpi, &wwan_acpi_guid, 0, 3, NULL); + + if (object && object->integer.value == 3) + return IPC_PCIE_D3L2; + +default_ret: + return IPC_PCIE_D0L12; +} + +static int ipc_pcie_probe(struct pci_dev *pci, + const struct pci_device_id *pci_id) +{ + struct iosm_pcie *ipc_pcie = kzalloc(sizeof(*ipc_pcie), GFP_KERNEL); + + pr_debug("Probing device 0x%X from the vendor 0x%X", pci_id->device, + pci_id->vendor); + + if (!ipc_pcie) + goto ret_fail; + + /* Initialize ipc dbg component for the PCIe device */ + ipc_pcie->dev = &pci->dev; + + /* Set the driver specific data. */ + pci_set_drvdata(pci, ipc_pcie); + + /* Save the address of the PCI device configuration. */ + ipc_pcie->pci = pci; + + /* Update platform configuration */ + ipc_pcie_config_init(ipc_pcie); + + /* Initialize the device before it is used. Ask low-level code + * to enable I/O and memory. Wake up the device if it was suspended. + */ + if (pci_enable_device(pci)) { + dev_err(ipc_pcie->dev, "failed to enable the AP PCIe device"); + /* If enable of PCIe device has failed then calling + * ipc_pcie_cleanup will panic the system. More over + * ipc_pcie_cleanup() is required to be called after + * ipc_imem_mount() + */ + goto pci_enable_fail; + } + + ipc_pcie_config_aspm(ipc_pcie); + dev_dbg(ipc_pcie->dev, "PCIe device enabled."); + + /* Read WWAN RTD3 BIOS Setting + */ + ipc_pcie->d3l2_support = ipc_pcie_read_bios_cfg(&pci->dev); + + ipc_pcie->suspend = 0; + + if (ipc_pcie_resources_request(ipc_pcie)) + goto resources_req_fail; + + /* Establish the link to the imem layer. */ + ipc_pcie->imem = ipc_imem_init(ipc_pcie, pci->device, + ipc_pcie->scratchpad, ipc_pcie->dev); + if (!ipc_pcie->imem) { + dev_err(ipc_pcie->dev, "failed to init imem"); + goto imem_init_fail; + } + + return 0; + +imem_init_fail: + ipc_pcie_resources_release(ipc_pcie); +resources_req_fail: + pci_disable_device(pci); +pci_enable_fail: + kfree(ipc_pcie); +ret_fail: + return -EIO; +} + +static const struct pci_device_id iosm_ipc_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, INTEL_CP_DEVICE_7560_ID) }, + {} +}; +MODULE_DEVICE_TABLE(pci, iosm_ipc_ids); + +/* Enter sleep in s2idle case + */ +static int __maybe_unused ipc_pcie_suspend_s2idle(struct iosm_pcie *ipc_pcie) +{ + ipc_cp_irq_sleep_control(ipc_pcie, IPC_MEM_DEV_PM_FORCE_SLEEP); + + /* Complete all memory stores before setting bit */ + smp_mb__before_atomic(); + + set_bit(0, &ipc_pcie->suspend); + + /* Complete all memory stores after setting bit */ + smp_mb__after_atomic(); + + ipc_imem_pm_s2idle_sleep(ipc_pcie->imem, true); + + return 0; +} + +/* Resume from sleep in s2idle case + */ +static int __maybe_unused ipc_pcie_resume_s2idle(struct iosm_pcie *ipc_pcie) +{ + ipc_cp_irq_sleep_control(ipc_pcie, IPC_MEM_DEV_PM_FORCE_ACTIVE); + + ipc_imem_pm_s2idle_sleep(ipc_pcie->imem, false); + + /* Complete all memory stores before clearing bit. */ + smp_mb__before_atomic(); + + clear_bit(0, &ipc_pcie->suspend); + + /* Complete all memory stores after clearing bit. */ + smp_mb__after_atomic(); + return 0; +} + +int __maybe_unused ipc_pcie_suspend(struct iosm_pcie *ipc_pcie) +{ + struct pci_dev *pdev; + int ret; + + pdev = ipc_pcie->pci; + + /* Execute D3 one time. */ + if (pdev->current_state != PCI_D0) { + dev_dbg(ipc_pcie->dev, "done for PM=%d", pdev->current_state); + return 0; + } + + /* The HAL shall ask the shared memory layer whether D3 is allowed. */ + ipc_imem_pm_suspend(ipc_pcie->imem); + + /* Save the PCI configuration space of a device before suspending. */ + ret = pci_save_state(pdev); + + if (ret) { + dev_err(ipc_pcie->dev, "pci_save_state error=%d", ret); + return ret; + } + + /* Set the power state of a PCI device. + * Transition a device to a new power state, using the device's PCI PM + * registers. + */ + ret = pci_set_power_state(pdev, PCI_D3cold); + + if (ret) { + dev_err(ipc_pcie->dev, "pci_set_power_state error=%d", ret); + return ret; + } + + dev_dbg(ipc_pcie->dev, "SUSPEND done"); + return ret; +} + +int __maybe_unused ipc_pcie_resume(struct iosm_pcie *ipc_pcie) +{ + int ret; + + /* Set the power state of a PCI device. + * Transition a device to a new power state, using the device's PCI PM + * registers. + */ + ret = pci_set_power_state(ipc_pcie->pci, PCI_D0); + + if (ret) { + dev_err(ipc_pcie->dev, "pci_set_power_state error=%d", ret); + return ret; + } + + pci_restore_state(ipc_pcie->pci); + + /* The HAL shall inform the shared memory layer that the device is + * active. + */ + ipc_imem_pm_resume(ipc_pcie->imem); + + dev_dbg(ipc_pcie->dev, "RESUME done"); + return ret; +} + +static int __maybe_unused ipc_pcie_suspend_cb(struct device *dev) +{ + struct iosm_pcie *ipc_pcie; + struct pci_dev *pdev; + + pdev = to_pci_dev(dev); + + ipc_pcie = pci_get_drvdata(pdev); + + switch (ipc_pcie->d3l2_support) { + case IPC_PCIE_D0L12: + ipc_pcie_suspend_s2idle(ipc_pcie); + break; + case IPC_PCIE_D3L2: + ipc_pcie_suspend(ipc_pcie); + break; + } + + return 0; +} + +static int __maybe_unused ipc_pcie_resume_cb(struct device *dev) +{ + struct iosm_pcie *ipc_pcie; + struct pci_dev *pdev; + + pdev = to_pci_dev(dev); + + ipc_pcie = pci_get_drvdata(pdev); + + switch (ipc_pcie->d3l2_support) { + case IPC_PCIE_D0L12: + ipc_pcie_resume_s2idle(ipc_pcie); + break; + case IPC_PCIE_D3L2: + ipc_pcie_resume(ipc_pcie); + break; + } + + return 0; +} + +static SIMPLE_DEV_PM_OPS(iosm_ipc_pm, ipc_pcie_suspend_cb, ipc_pcie_resume_cb); + +static struct pci_driver iosm_ipc_driver = { + .name = KBUILD_MODNAME, + .probe = ipc_pcie_probe, + .remove = ipc_pcie_remove, + .driver = { + .pm = &iosm_ipc_pm, + }, + .id_table = iosm_ipc_ids, +}; + +int ipc_pcie_addr_map(struct iosm_pcie *ipc_pcie, unsigned char *data, + size_t size, dma_addr_t *mapping, int direction) +{ + if (ipc_pcie->pci) { + *mapping = dma_map_single(&ipc_pcie->pci->dev, data, size, + direction); + if (dma_mapping_error(&ipc_pcie->pci->dev, *mapping)) { + dev_err(ipc_pcie->dev, "dma mapping failed"); + return -EINVAL; + } + } + return 0; +} + +void ipc_pcie_addr_unmap(struct iosm_pcie *ipc_pcie, size_t size, + dma_addr_t mapping, int direction) +{ + if (!mapping) + return; + if (ipc_pcie->pci) + dma_unmap_single(&ipc_pcie->pci->dev, mapping, size, direction); +} + +struct sk_buff *ipc_pcie_alloc_local_skb(struct iosm_pcie *ipc_pcie, + gfp_t flags, size_t size) +{ + struct sk_buff *skb; + + if (!ipc_pcie || !size) { + pr_err("invalid pcie object or size"); + return NULL; + } + + skb = __netdev_alloc_skb(NULL, size, flags); + if (!skb) + return NULL; + + IPC_CB(skb)->op_type = (u8)UL_DEFAULT; + IPC_CB(skb)->mapping = 0; + + return skb; +} + +struct sk_buff *ipc_pcie_alloc_skb(struct iosm_pcie *ipc_pcie, size_t size, + gfp_t flags, dma_addr_t *mapping, + int direction, size_t headroom) +{ + struct sk_buff *skb = ipc_pcie_alloc_local_skb(ipc_pcie, flags, + size + headroom); + if (!skb) + return NULL; + + if (headroom) + skb_reserve(skb, headroom); + + if (ipc_pcie_addr_map(ipc_pcie, skb->data, size, mapping, direction)) { + dev_kfree_skb(skb); + return NULL; + } + + BUILD_BUG_ON(sizeof(*IPC_CB(skb)) > sizeof(skb->cb)); + + /* Store the mapping address in skb scratch pad for later usage */ + IPC_CB(skb)->mapping = *mapping; + IPC_CB(skb)->direction = direction; + IPC_CB(skb)->len = size; + + return skb; +} + +void ipc_pcie_kfree_skb(struct iosm_pcie *ipc_pcie, struct sk_buff *skb) +{ + if (!skb) + return; + + ipc_pcie_addr_unmap(ipc_pcie, IPC_CB(skb)->len, IPC_CB(skb)->mapping, + IPC_CB(skb)->direction); + IPC_CB(skb)->mapping = 0; + dev_kfree_skb(skb); +} + +static int __init iosm_ipc_driver_init(void) +{ + if (pci_register_driver(&iosm_ipc_driver)) { + pr_err("registering of IOSM PCIe driver failed"); + return -1; + } + + return 0; +} + +static void __exit iosm_ipc_driver_exit(void) +{ + pci_unregister_driver(&iosm_ipc_driver); +} + +module_init(iosm_ipc_driver_init); +module_exit(iosm_ipc_driver_exit); diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.h b/drivers/net/wwan/iosm/iosm_ipc_pcie.h new file mode 100644 index 000000000000..7d1f0cd7364c --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.h @@ -0,0 +1,209 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_PCIE_H +#define IOSM_IPC_PCIE_H + +#include +#include +#include + +#include "iosm_ipc_irq.h" + +/* Device ID */ +#define INTEL_CP_DEVICE_7560_ID 0x7560 + +/* Define for BAR area usage */ +#define IPC_DOORBELL_BAR0 0 +#define IPC_SCRATCHPAD_BAR2 2 + +/* Defines for DOORBELL registers information */ +#define IPC_DOORBELL_CH_OFFSET BIT(5) +#define IPC_WRITE_PTR_REG_0 BIT(4) +#define IPC_CAPTURE_PTR_REG_0 BIT(3) + +/* Number of MSI used for IPC */ +#define IPC_MSI_VECTORS 1 + +/* Total number of Maximum IPC IRQ vectors used for IPC */ +#define IPC_IRQ_VECTORS IPC_MSI_VECTORS + +/** + * enum ipc_pcie_sleep_state - Enum type to different sleep state transitions + * @IPC_PCIE_D0L12: Put the sleep state in D0L12 + * @IPC_PCIE_D3L2: Put the sleep state in D3L2 + */ +enum ipc_pcie_sleep_state { + IPC_PCIE_D0L12, + IPC_PCIE_D3L2, +}; + +/** + * struct iosm_pcie - IPC_PCIE struct. + * @pci: Address of the device description + * @dev: Pointer to generic device structure + * @ipc_regs: Remapped CP doorbell address of the irq register + * set, to fire the doorbell irq. + * @scratchpad: Remapped CP scratchpad address, to send the + * configuration. tuple and the IPC descriptors + * to CP in the ROM phase. The config tuple + * information are saved on the MSI scratchpad. + * @imem: Pointer to imem data struct + * @ipc_regs_bar_nr: BAR number to be used for IPC doorbell + * @scratchpad_bar_nr: BAR number to be used for Scratchpad + * @nvec: number of requested irq vectors + * @doorbell_reg_offset: doorbell_reg_offset + * @doorbell_write: doorbell write register + * @doorbell_capture: doorbell capture resgister + * @suspend: S2IDLE sleep/active + * @d3l2_support: Read WWAN RTD3 BIOS setting for D3L2 support + */ +struct iosm_pcie { + struct pci_dev *pci; + struct device *dev; + void __iomem *ipc_regs; + void __iomem *scratchpad; + struct iosm_imem *imem; + int ipc_regs_bar_nr; + int scratchpad_bar_nr; + int nvec; + u32 doorbell_reg_offset; + u32 doorbell_write; + u32 doorbell_capture; + unsigned long suspend; + enum ipc_pcie_sleep_state d3l2_support; +}; + +/** + * struct ipc_skb_cb - Struct definition of the socket buffer which is mapped to + * the cb field of sbk + * @mapping: Store physical or IOVA mapped address of skb virtual add. + * @direction: DMA direction + * @len: Length of the DMA mapped region + * @op_type: Expected values are defined about enum ipc_ul_usr_op. + */ +struct ipc_skb_cb { + dma_addr_t mapping; + int direction; + int len; + u8 op_type; +}; + +/** + * enum ipc_ul_usr_op - Control operation to execute the right action on + * the user interface. + * @UL_USR_OP_BLOCKED: The uplink app was blocked until CP confirms that the + * uplink buffer was consumed triggered by the IRQ. + * @UL_MUX_OP_ADB: In MUX mode the UL ADB shall be addedd to the free list. + * @UL_DEFAULT: SKB in non muxing mode + */ +enum ipc_ul_usr_op { + UL_USR_OP_BLOCKED, + UL_MUX_OP_ADB, + UL_DEFAULT, +}; + +/** + * ipc_pcie_addr_map - Maps the kernel's virtual address to either IOVA + * address space or Physical address space, the mapping is + * stored in the skb's cb. + * @ipc_pcie: Pointer to struct iosm_pcie + * @data: Skb mem containing data + * @size: Data size + * @mapping: Dma mapping address + * @direction: Data direction + * + * Returns: 0 on success and failure value on error + */ +int ipc_pcie_addr_map(struct iosm_pcie *ipc_pcie, unsigned char *data, + size_t size, dma_addr_t *mapping, int direction); + +/** + * ipc_pcie_addr_unmap - Unmaps the skb memory region from IOVA address space + * @ipc_pcie: Pointer to struct iosm_pcie + * @size: Data size + * @mapping: Dma mapping address + * @direction: Data direction + */ +void ipc_pcie_addr_unmap(struct iosm_pcie *ipc_pcie, size_t size, + dma_addr_t mapping, int direction); + +/** + * ipc_pcie_alloc_skb - Allocate an uplink SKB for the given size. + * @ipc_pcie: Pointer to struct iosm_pcie + * @size: Size of the SKB required. + * @flags: Allocation flags + * @mapping: Copies either mapped IOVA add. or converted Phy address + * @direction: DMA data direction + * @headroom: Header data offset + * + * Returns: Pointer to ipc_skb on Success, NULL on failure. + */ +struct sk_buff *ipc_pcie_alloc_skb(struct iosm_pcie *ipc_pcie, size_t size, + gfp_t flags, dma_addr_t *mapping, + int direction, size_t headroom); + +/** + * ipc_pcie_alloc_local_skb - Allocate a local SKB for the given size. + * @ipc_pcie: Pointer to struct iosm_pcie + * @flags: Allocation flags + * @size: Size of the SKB required. + * + * Returns: Pointer to ipc_skb on Success, NULL on failure. + */ +struct sk_buff *ipc_pcie_alloc_local_skb(struct iosm_pcie *ipc_pcie, + gfp_t flags, size_t size); + +/** + * ipc_pcie_kfree_skb - Free skb allocated by ipc_pcie_alloc_*_skb(). + * @ipc_pcie: Pointer to struct iosm_pcie + * @skb: Pointer to the skb + */ +void ipc_pcie_kfree_skb(struct iosm_pcie *ipc_pcie, struct sk_buff *skb); + +/** + * ipc_pcie_check_data_link_active - Check Data Link Layer Active + * @ipc_pcie: Pointer to struct iosm_pcie + * + * Returns: true if active, otherwise false + */ +bool ipc_pcie_check_data_link_active(struct iosm_pcie *ipc_pcie); + +/** + * ipc_pcie_suspend - Callback invoked by pm_runtime_suspend. It decrements + * the device's usage count then, carry out a suspend, + * either synchronous or asynchronous. + * @ipc_pcie: Pointer to struct iosm_pcie + * + * Returns: 0 on success and failure value on error + */ +int ipc_pcie_suspend(struct iosm_pcie *ipc_pcie); + +/** + * ipc_pcie_resume - Callback invoked by pm_runtime_resume. It increments + * the device's usage count then, carry out a resume, + * either synchronous or asynchronous. + * @ipc_pcie: Pointer to struct iosm_pcie + * + * Returns: 0 on success and failure value on error + */ +int ipc_pcie_resume(struct iosm_pcie *ipc_pcie); + +/** + * ipc_pcie_check_aspm_enabled - Check if ASPM L1 is already enabled + * @ipc_pcie: Pointer to struct iosm_pcie + * @parent: True if checking ASPM L1 for parent else false + * + * Returns: true if ASPM is already enabled else false + */ +bool ipc_pcie_check_aspm_enabled(struct iosm_pcie *ipc_pcie, + bool parent); +/** + * ipc_pcie_config_aspm - Configure ASPM L1 + * @ipc_pcie: Pointer to struct iosm_pcie + */ +void ipc_pcie_config_aspm(struct iosm_pcie *ipc_pcie); + +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_pm.c b/drivers/net/wwan/iosm/iosm_ipc_pm.c new file mode 100644 index 000000000000..413601c72dcd --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_pm.c @@ -0,0 +1,333 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include "iosm_ipc_protocol.h" + +/* Timeout value in MS for the PM to wait for device to reach active state */ +#define IPC_PM_ACTIVE_TIMEOUT_MS (500) + +/* Note that here "active" has the value 1, as compared to the enums + * ipc_mem_host_pm_state or ipc_mem_dev_pm_state, where "active" is 0 + */ +#define IPC_PM_SLEEP (0) +#define CONSUME_STATE (0) +#define IPC_PM_ACTIVE (1) + +void ipc_pm_signal_hpda_doorbell(struct iosm_pm *ipc_pm, u32 identifier, + bool host_slp_check) +{ + if (host_slp_check && ipc_pm->host_pm_state != IPC_MEM_HOST_PM_ACTIVE && + ipc_pm->host_pm_state != IPC_MEM_HOST_PM_ACTIVE_WAIT) { + ipc_pm->pending_hpda_update = true; + dev_dbg(ipc_pm->dev, + "Pend HPDA update set. Host PM_State: %d identifier:%d", + ipc_pm->host_pm_state, identifier); + return; + } + + if (!ipc_pm_trigger(ipc_pm, IPC_PM_UNIT_IRQ, true)) { + ipc_pm->pending_hpda_update = true; + dev_dbg(ipc_pm->dev, "Pending HPDA update set. identifier:%d", + identifier); + return; + } + ipc_pm->pending_hpda_update = false; + + /* Trigger the irq towards CP */ + ipc_cp_irq_hpda_update(ipc_pm->pcie, identifier); + + ipc_pm_trigger(ipc_pm, IPC_PM_UNIT_IRQ, false); +} + +/* Wake up the device if it is in low power mode. */ +static bool ipc_pm_link_activate(struct iosm_pm *ipc_pm) +{ + if (ipc_pm->cp_state == IPC_MEM_DEV_PM_ACTIVE) + return true; + + if (ipc_pm->cp_state == IPC_MEM_DEV_PM_SLEEP) { + if (ipc_pm->ap_state == IPC_MEM_DEV_PM_SLEEP) { + /* Wake up the device. */ + ipc_cp_irq_sleep_control(ipc_pm->pcie, + IPC_MEM_DEV_PM_WAKEUP); + ipc_pm->ap_state = IPC_MEM_DEV_PM_ACTIVE_WAIT; + + goto not_active; + } + + if (ipc_pm->ap_state == IPC_MEM_DEV_PM_ACTIVE_WAIT) + goto not_active; + + return true; + } + +not_active: + /* link is not ready */ + return false; +} + +bool ipc_pm_wait_for_device_active(struct iosm_pm *ipc_pm) +{ + bool ret_val = false; + + if (ipc_pm->ap_state != IPC_MEM_DEV_PM_ACTIVE) { + /* Complete all memory stores before setting bit */ + smp_mb__before_atomic(); + + /* Wait for IPC_PM_ACTIVE_TIMEOUT_MS for Device sleep state + * machine to enter ACTIVE state. + */ + set_bit(0, &ipc_pm->host_sleep_pend); + + /* Complete all memory stores after setting bit */ + smp_mb__after_atomic(); + + if (!wait_for_completion_interruptible_timeout + (&ipc_pm->host_sleep_complete, + msecs_to_jiffies(IPC_PM_ACTIVE_TIMEOUT_MS))) { + dev_err(ipc_pm->dev, + "PM timeout. Expected State:%d. Actual: %d", + IPC_MEM_DEV_PM_ACTIVE, ipc_pm->ap_state); + goto active_timeout; + } + } + + ret_val = true; +active_timeout: + /* Complete all memory stores before clearing bit */ + smp_mb__before_atomic(); + + /* Reset the atomic variable in any case as device sleep + * state machine change is no longer of interest. + */ + clear_bit(0, &ipc_pm->host_sleep_pend); + + /* Complete all memory stores after clearing bit */ + smp_mb__after_atomic(); + + return ret_val; +} + +static void ipc_pm_on_link_sleep(struct iosm_pm *ipc_pm) +{ + /* pending sleep ack and all conditions are cleared + * -> signal SLEEP__ACK to CP + */ + ipc_pm->cp_state = IPC_MEM_DEV_PM_SLEEP; + ipc_pm->ap_state = IPC_MEM_DEV_PM_SLEEP; + + ipc_cp_irq_sleep_control(ipc_pm->pcie, IPC_MEM_DEV_PM_SLEEP); +} + +static void ipc_pm_on_link_wake(struct iosm_pm *ipc_pm, bool ack) +{ + ipc_pm->ap_state = IPC_MEM_DEV_PM_ACTIVE; + + if (ack) { + ipc_pm->cp_state = IPC_MEM_DEV_PM_ACTIVE; + + ipc_cp_irq_sleep_control(ipc_pm->pcie, IPC_MEM_DEV_PM_ACTIVE); + + /* check the consume state !!! */ + if (test_bit(CONSUME_STATE, &ipc_pm->host_sleep_pend)) + complete(&ipc_pm->host_sleep_complete); + } + + /* Check for pending HPDA update. + * Pending HP update could be because of sending message was + * put on hold due to Device sleep state or due to TD update + * which could be because of Device Sleep and Host Sleep + * states. + */ + if (ipc_pm->pending_hpda_update && + ipc_pm->host_pm_state == IPC_MEM_HOST_PM_ACTIVE) + ipc_pm_signal_hpda_doorbell(ipc_pm, IPC_HP_PM_TRIGGER, true); +} + +bool ipc_pm_trigger(struct iosm_pm *ipc_pm, enum ipc_pm_unit unit, bool active) +{ + union ipc_pm_cond old_cond; + union ipc_pm_cond new_cond; + bool link_active; + + /* Save the current D3 state. */ + new_cond = ipc_pm->pm_cond; + old_cond = ipc_pm->pm_cond; + + /* Calculate the power state only in the runtime phase. */ + switch (unit) { + case IPC_PM_UNIT_IRQ: /* CP irq */ + new_cond.irq = active; + break; + + case IPC_PM_UNIT_LINK: /* Device link state. */ + new_cond.link = active; + break; + + case IPC_PM_UNIT_HS: /* Host sleep trigger requires Link. */ + new_cond.hs = active; + break; + + default: + break; + } + + /* Something changed ? */ + if (old_cond.raw == new_cond.raw) { + /* Stay in the current PM state. */ + link_active = old_cond.link == IPC_PM_ACTIVE; + goto ret; + } + + ipc_pm->pm_cond = new_cond; + + if (new_cond.link) + ipc_pm_on_link_wake(ipc_pm, unit == IPC_PM_UNIT_LINK); + else if (unit == IPC_PM_UNIT_LINK) + ipc_pm_on_link_sleep(ipc_pm); + + if (old_cond.link == IPC_PM_SLEEP && new_cond.raw) { + link_active = ipc_pm_link_activate(ipc_pm); + goto ret; + } + + link_active = old_cond.link == IPC_PM_ACTIVE; + +ret: + return link_active; +} + +bool ipc_pm_prepare_host_sleep(struct iosm_pm *ipc_pm) +{ + /* suspend not allowed if host_pm_state is not IPC_MEM_HOST_PM_ACTIVE */ + if (ipc_pm->host_pm_state != IPC_MEM_HOST_PM_ACTIVE) { + dev_err(ipc_pm->dev, "host_pm_state=%d\tExpected to be: %d", + ipc_pm->host_pm_state, IPC_MEM_HOST_PM_ACTIVE); + return false; + } + + ipc_pm->host_pm_state = IPC_MEM_HOST_PM_SLEEP_WAIT_D3; + + return true; +} + +bool ipc_pm_prepare_host_active(struct iosm_pm *ipc_pm) +{ + if (ipc_pm->host_pm_state != IPC_MEM_HOST_PM_SLEEP) { + dev_err(ipc_pm->dev, "host_pm_state=%d\tExpected to be: %d", + ipc_pm->host_pm_state, IPC_MEM_HOST_PM_SLEEP); + return false; + } + + /* Sending Sleep Exit message to CP. Update the state */ + ipc_pm->host_pm_state = IPC_MEM_HOST_PM_ACTIVE_WAIT; + + return true; +} + +void ipc_pm_set_s2idle_sleep(struct iosm_pm *ipc_pm, bool sleep) +{ + if (sleep) { + ipc_pm->ap_state = IPC_MEM_DEV_PM_SLEEP; + ipc_pm->cp_state = IPC_MEM_DEV_PM_SLEEP; + ipc_pm->device_sleep_notification = IPC_MEM_DEV_PM_SLEEP; + } else { + ipc_pm->ap_state = IPC_MEM_DEV_PM_ACTIVE; + ipc_pm->cp_state = IPC_MEM_DEV_PM_ACTIVE; + ipc_pm->device_sleep_notification = IPC_MEM_DEV_PM_ACTIVE; + ipc_pm->pm_cond.link = IPC_PM_ACTIVE; + } +} + +bool ipc_pm_dev_slp_notification(struct iosm_pm *ipc_pm, u32 cp_pm_req) +{ + if (cp_pm_req == ipc_pm->device_sleep_notification) + return false; + + ipc_pm->device_sleep_notification = cp_pm_req; + + /* Evaluate the PM request. */ + switch (ipc_pm->cp_state) { + case IPC_MEM_DEV_PM_ACTIVE: + switch (cp_pm_req) { + case IPC_MEM_DEV_PM_ACTIVE: + break; + + case IPC_MEM_DEV_PM_SLEEP: + /* Inform the PM that the device link can go down. */ + ipc_pm_trigger(ipc_pm, IPC_PM_UNIT_LINK, false); + return true; + + default: + dev_err(ipc_pm->dev, + "loc-pm=%d active: confused req-pm=%d", + ipc_pm->cp_state, cp_pm_req); + break; + } + break; + + case IPC_MEM_DEV_PM_SLEEP: + switch (cp_pm_req) { + case IPC_MEM_DEV_PM_ACTIVE: + /* Inform the PM that the device link is active. */ + ipc_pm_trigger(ipc_pm, IPC_PM_UNIT_LINK, true); + break; + + case IPC_MEM_DEV_PM_SLEEP: + break; + + default: + dev_err(ipc_pm->dev, + "loc-pm=%d sleep: confused req-pm=%d", + ipc_pm->cp_state, cp_pm_req); + break; + } + break; + + default: + dev_err(ipc_pm->dev, "confused loc-pm=%d, req-pm=%d", + ipc_pm->cp_state, cp_pm_req); + break; + } + + return false; +} + +void ipc_pm_init(struct iosm_protocol *ipc_protocol) +{ + struct iosm_imem *ipc_imem = ipc_protocol->imem; + struct iosm_pm *ipc_pm = &ipc_protocol->pm; + + ipc_pm->pcie = ipc_imem->pcie; + ipc_pm->dev = ipc_imem->dev; + + ipc_pm->pm_cond.irq = IPC_PM_SLEEP; + ipc_pm->pm_cond.hs = IPC_PM_SLEEP; + ipc_pm->pm_cond.link = IPC_PM_ACTIVE; + + ipc_pm->cp_state = IPC_MEM_DEV_PM_ACTIVE; + ipc_pm->ap_state = IPC_MEM_DEV_PM_ACTIVE; + ipc_pm->host_pm_state = IPC_MEM_HOST_PM_ACTIVE; + + /* Create generic wait-for-completion handler for Host Sleep + * and device sleep coordination. + */ + init_completion(&ipc_pm->host_sleep_complete); + + /* Complete all memory stores before clearing bit */ + smp_mb__before_atomic(); + + clear_bit(0, &ipc_pm->host_sleep_pend); + + /* Complete all memory stores after clearing bit */ + smp_mb__after_atomic(); +} + +void ipc_pm_deinit(struct iosm_protocol *proto) +{ + struct iosm_pm *ipc_pm = &proto->pm; + + complete(&ipc_pm->host_sleep_complete); +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_pm.h b/drivers/net/wwan/iosm/iosm_ipc_pm.h new file mode 100644 index 000000000000..e7c00f388cb0 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_pm.h @@ -0,0 +1,207 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_PM_H +#define IOSM_IPC_PM_H + +/* Trigger the doorbell interrupt on cp to change the PM sleep/active status */ +#define ipc_cp_irq_sleep_control(ipc_pcie, data) \ + ipc_doorbell_fire(ipc_pcie, IPC_DOORBELL_IRQ_SLEEP, data) + +/* Trigger the doorbell interrupt on CP to do hpda update */ +#define ipc_cp_irq_hpda_update(ipc_pcie, data) \ + ipc_doorbell_fire(ipc_pcie, IPC_DOORBELL_IRQ_HPDA, 0xFF & (data)) + +/** + * union ipc_pm_cond - Conditions for D3 and the sleep message to CP. + * @raw: raw/combined value for faster check + * @irq: IRQ towards CP + * @hs: Host Sleep + * @link: Device link state. + */ +union ipc_pm_cond { + unsigned int raw; + + struct { + unsigned int irq:1, + hs:1, + link:1; + }; +}; + +/** + * enum ipc_mem_host_pm_state - Possible states of the HOST SLEEP finite state + * machine. + * @IPC_MEM_HOST_PM_ACTIVE: Host is active + * @IPC_MEM_HOST_PM_ACTIVE_WAIT: Intermediate state before going to + * active + * @IPC_MEM_HOST_PM_SLEEP_WAIT_IDLE: Intermediate state to wait for idle + * before going into sleep + * @IPC_MEM_HOST_PM_SLEEP_WAIT_D3: Intermediate state to wait for D3 + * before going to sleep + * @IPC_MEM_HOST_PM_SLEEP: after this state the interface is not + * accessible host is in suspend to RAM + * @IPC_MEM_HOST_PM_SLEEP_WAIT_EXIT_SLEEP: Intermediate state before exiting + * sleep + */ +enum ipc_mem_host_pm_state { + IPC_MEM_HOST_PM_ACTIVE, + IPC_MEM_HOST_PM_ACTIVE_WAIT, + IPC_MEM_HOST_PM_SLEEP_WAIT_IDLE, + IPC_MEM_HOST_PM_SLEEP_WAIT_D3, + IPC_MEM_HOST_PM_SLEEP, + IPC_MEM_HOST_PM_SLEEP_WAIT_EXIT_SLEEP, +}; + +/** + * enum ipc_mem_dev_pm_state - Possible states of the DEVICE SLEEP finite state + * machine. + * @IPC_MEM_DEV_PM_ACTIVE: IPC_MEM_DEV_PM_ACTIVE is the initial + * power management state. + * IRQ(struct ipc_mem_device_info: + * device_sleep_notification) + * and DOORBELL-IRQ-HPDA(data) values. + * @IPC_MEM_DEV_PM_SLEEP: IPC_MEM_DEV_PM_SLEEP is PM state for + * sleep. + * @IPC_MEM_DEV_PM_WAKEUP: DOORBELL-IRQ-DEVICE_WAKE(data). + * @IPC_MEM_DEV_PM_HOST_SLEEP: DOORBELL-IRQ-HOST_SLEEP(data). + * @IPC_MEM_DEV_PM_ACTIVE_WAIT: Local intermediate states. + * @IPC_MEM_DEV_PM_FORCE_SLEEP: DOORBELL-IRQ-FORCE_SLEEP. + * @IPC_MEM_DEV_PM_FORCE_ACTIVE: DOORBELL-IRQ-FORCE_ACTIVE. + */ +enum ipc_mem_dev_pm_state { + IPC_MEM_DEV_PM_ACTIVE, + IPC_MEM_DEV_PM_SLEEP, + IPC_MEM_DEV_PM_WAKEUP, + IPC_MEM_DEV_PM_HOST_SLEEP, + IPC_MEM_DEV_PM_ACTIVE_WAIT, + IPC_MEM_DEV_PM_FORCE_SLEEP = 7, + IPC_MEM_DEV_PM_FORCE_ACTIVE, +}; + +/** + * struct iosm_pm - Power management instance + * @pcie: Pointer to iosm_pcie structure + * @dev: Pointer to device structure + * @host_pm_state: PM states for host + * @host_sleep_pend: Variable to indicate Host Sleep Pending + * @host_sleep_complete: Generic wait-for-completion used in + * case of Host Sleep + * @pm_cond: Conditions for power management + * @ap_state: Current power management state, the + * initial state is IPC_MEM_DEV_PM_ACTIVE eq. 0. + * @cp_state: PM State of CP + * @device_sleep_notification: last handled device_sleep_notfication + * @pending_hpda_update: is a HPDA update pending? + */ +struct iosm_pm { + struct iosm_pcie *pcie; + struct device *dev; + enum ipc_mem_host_pm_state host_pm_state; + unsigned long host_sleep_pend; + struct completion host_sleep_complete; + union ipc_pm_cond pm_cond; + enum ipc_mem_dev_pm_state ap_state; + enum ipc_mem_dev_pm_state cp_state; + u32 device_sleep_notification; + u8 pending_hpda_update:1; +}; + +/** + * enum ipc_pm_unit - Power management units. + * @IPC_PM_UNIT_IRQ: IRQ towards CP + * @IPC_PM_UNIT_HS: Host Sleep for converged protocol + * @IPC_PM_UNIT_LINK: Link state controlled by CP. + */ +enum ipc_pm_unit { + IPC_PM_UNIT_IRQ, + IPC_PM_UNIT_HS, + IPC_PM_UNIT_LINK, +}; + +/** + * ipc_pm_init - Allocate power management component + * @ipc_protocol: Pointer to iosm_protocol structure + */ +void ipc_pm_init(struct iosm_protocol *ipc_protocol); + +/** + * ipc_pm_deinit - Free power management component, invalidating its pointer. + * @ipc_protocol: Pointer to iosm_protocol structure + */ +void ipc_pm_deinit(struct iosm_protocol *ipc_protocol); + +/** + * ipc_pm_dev_slp_notification - Handle a sleep notification message from the + * device. This can be called from interrupt state + * This function handles Host Sleep requests too + * if the Host Sleep protocol is register based. + * @ipc_pm: Pointer to power management component + * @sleep_notification: Actual notification from device + * + * Returns: true if dev sleep state has to be checked, false otherwise. + */ +bool ipc_pm_dev_slp_notification(struct iosm_pm *ipc_pm, + u32 sleep_notification); + +/** + * ipc_pm_set_s2idle_sleep - Set PM variables to sleep/active + * @ipc_pm: Pointer to power management component + * @sleep: true to enter sleep/false to exit sleep + */ +void ipc_pm_set_s2idle_sleep(struct iosm_pm *ipc_pm, bool sleep); + +/** + * ipc_pm_prepare_host_sleep - Prepare the PM for sleep by entering + * IPC_MEM_HOST_PM_SLEEP_WAIT_D3 state. + * @ipc_pm: Pointer to power management component + * + * Returns: true on success, false if the host was not active. + */ +bool ipc_pm_prepare_host_sleep(struct iosm_pm *ipc_pm); + +/** + * ipc_pm_prepare_host_active - Prepare the PM for wakeup by entering + * IPC_MEM_HOST_PM_ACTIVE_WAIT state. + * @ipc_pm: Pointer to power management component + * + * Returns: true on success, false if the host was not sleeping. + */ +bool ipc_pm_prepare_host_active(struct iosm_pm *ipc_pm); + +/** + * ipc_pm_wait_for_device_active - Wait upto IPC_PM_ACTIVE_TIMEOUT_MS ms + * for the device to reach active state + * @ipc_pm: Pointer to power management component + * + * Returns: true if device is active, false on timeout + */ +bool ipc_pm_wait_for_device_active(struct iosm_pm *ipc_pm); + +/** + * ipc_pm_signal_hpda_doorbell - Wake up the device if it is in low power mode + * and trigger a head pointer update interrupt. + * @ipc_pm: Pointer to power management component + * @identifier: specifies what component triggered hpda update irq + * @host_slp_check: if set to true then Host Sleep state machine check will + * be performed. If Host Sleep state machine allows HP + * update then only doorbell is triggered otherwise pending + * flag will be set. If set to false then Host Sleep check + * will not be performed. This is helpful for Host Sleep + * negotiation through message ring. + */ +void ipc_pm_signal_hpda_doorbell(struct iosm_pm *ipc_pm, u32 identifier, + bool host_slp_check); +/** + * ipc_pm_trigger - Update power manager and wake up the link if needed + * @ipc_pm: Pointer to power management component + * @unit: Power management units + * @active: Device link state + * + * Returns: true if link is unchanged or active, false otherwise + */ +bool ipc_pm_trigger(struct iosm_pm *ipc_pm, enum ipc_pm_unit unit, bool active); + +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_port.c b/drivers/net/wwan/iosm/iosm_ipc_port.c new file mode 100644 index 000000000000..beb944847398 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_port.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include "iosm_ipc_chnl_cfg.h" +#include "iosm_ipc_imem_ops.h" +#include "iosm_ipc_port.h" + +/* open logical channel for control communication */ +static int ipc_port_ctrl_start(struct wwan_port *port) +{ + struct iosm_cdev *ipc_port = wwan_port_get_drvdata(port); + int ret = 0; + + ipc_port->channel = ipc_imem_sys_port_open(ipc_port->ipc_imem, + ipc_port->chl_id, + IPC_HP_CDEV_OPEN); + if (!ipc_port->channel) + ret = -EIO; + + return ret; +} + +/* close logical channel */ +static void ipc_port_ctrl_stop(struct wwan_port *port) +{ + struct iosm_cdev *ipc_port = wwan_port_get_drvdata(port); + + ipc_imem_sys_cdev_close(ipc_port); +} + +/* transfer control data to modem */ +static int ipc_port_ctrl_tx(struct wwan_port *port, struct sk_buff *skb) +{ + struct iosm_cdev *ipc_port = wwan_port_get_drvdata(port); + + return ipc_imem_sys_cdev_write(ipc_port, skb); +} + +static const struct wwan_port_ops ipc_wwan_ctrl_ops = { + .start = ipc_port_ctrl_start, + .stop = ipc_port_ctrl_stop, + .tx = ipc_port_ctrl_tx, +}; + +/* Port init func */ +struct iosm_cdev *ipc_port_init(struct iosm_imem *ipc_imem, + struct ipc_chnl_cfg ipc_port_cfg) +{ + struct iosm_cdev *ipc_port = kzalloc(sizeof(*ipc_port), GFP_KERNEL); + enum wwan_port_type port_type = ipc_port_cfg.wwan_port_type; + enum ipc_channel_id chl_id = ipc_port_cfg.id; + + if (!ipc_port) + return NULL; + + ipc_port->dev = ipc_imem->dev; + ipc_port->pcie = ipc_imem->pcie; + + ipc_port->port_type = port_type; + ipc_port->chl_id = chl_id; + ipc_port->ipc_imem = ipc_imem; + + ipc_port->iosm_port = wwan_create_port(ipc_port->dev, port_type, + &ipc_wwan_ctrl_ops, ipc_port); + + return ipc_port; +} + +/* Port deinit func */ +void ipc_port_deinit(struct iosm_cdev *port[]) +{ + struct iosm_cdev *ipc_port; + u8 ctrl_chl_nr; + + for (ctrl_chl_nr = 0; ctrl_chl_nr < IPC_MEM_MAX_CHANNELS; + ctrl_chl_nr++) { + if (port[ctrl_chl_nr]) { + ipc_port = port[ctrl_chl_nr]; + wwan_remove_port(ipc_port->iosm_port); + kfree(ipc_port); + } + } +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_port.h b/drivers/net/wwan/iosm/iosm_ipc_port.h new file mode 100644 index 000000000000..11bc8ed21616 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_port.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_PORT_H +#define IOSM_IPC_PORT_H + +#include + +#include "iosm_ipc_imem_ops.h" + +/** + * struct iosm_cdev - State of the char driver layer. + * @iosm_port: Pointer of type wwan_port + * @ipc_imem: imem instance + * @dev: Pointer to device struct + * @pcie: PCIe component + * @port_type: WWAN port type + * @channel: Channel instance + * @chl_id: Channel Indentifier + */ +struct iosm_cdev { + struct wwan_port *iosm_port; + struct iosm_imem *ipc_imem; + struct device *dev; + struct iosm_pcie *pcie; + enum wwan_port_type port_type; + struct ipc_mem_channel *channel; + enum ipc_channel_id chl_id; +}; + +/** + * ipc_port_init - Allocate IPC port & register to wwan subsystem for AT/MBIM + * communication. + * @ipc_imem: Pointer to iosm_imem structure + * @ipc_port_cfg: IPC Port Config + * + * Returns: 0 on success & NULL on failure + */ +struct iosm_cdev *ipc_port_init(struct iosm_imem *ipc_imem, + struct ipc_chnl_cfg ipc_port_cfg); + +/** + * ipc_port_deinit - Free IPC port & unregister port with wwan subsystem. + * @ipc_port: Array of pointer to the ipc port data-struct + */ +void ipc_port_deinit(struct iosm_cdev *ipc_port[]); + +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol.c b/drivers/net/wwan/iosm/iosm_ipc_protocol.c new file mode 100644 index 000000000000..834d8b146a94 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_protocol.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include "iosm_ipc_imem.h" +#include "iosm_ipc_protocol.h" +#include "iosm_ipc_protocol_ops.h" +#include "iosm_ipc_pm.h" +#include "iosm_ipc_task_queue.h" + +int ipc_protocol_tq_msg_send(struct iosm_protocol *ipc_protocol, + enum ipc_msg_prep_type msg_type, + union ipc_msg_prep_args *prep_args, + struct ipc_rsp *response) +{ + int index = ipc_protocol_msg_prep(ipc_protocol->imem, msg_type, + prep_args); + + /* Store reference towards caller specified response in response ring + * and signal CP + */ + if (index >= 0 && index < IPC_MEM_MSG_ENTRIES) { + ipc_protocol->rsp_ring[index] = response; + ipc_protocol_msg_hp_update(ipc_protocol->imem); + } + + return index; +} + +/* Callback for message send */ +static int ipc_protocol_tq_msg_send_cb(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size) +{ + struct ipc_call_msg_send_args *send_args = msg; + struct iosm_protocol *ipc_protocol = ipc_imem->ipc_protocol; + + return ipc_protocol_tq_msg_send(ipc_protocol, send_args->msg_type, + send_args->prep_args, + send_args->response); +} + +/* Remove reference to a response. This is typically used when a requestor timed + * out and is no longer interested in the response. + */ +static int ipc_protocol_tq_msg_remove(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size) +{ + struct iosm_protocol *ipc_protocol = ipc_imem->ipc_protocol; + + ipc_protocol->rsp_ring[arg] = NULL; + return 0; +} + +int ipc_protocol_msg_send(struct iosm_protocol *ipc_protocol, + enum ipc_msg_prep_type prep, + union ipc_msg_prep_args *prep_args) +{ + struct ipc_call_msg_send_args send_args; + unsigned int exec_timeout; + struct ipc_rsp response; + int index; + + exec_timeout = (ipc_protocol_get_ap_exec_stage(ipc_protocol) == + IPC_MEM_EXEC_STAGE_RUN ? + IPC_MSG_COMPLETE_RUN_DEFAULT_TIMEOUT : + IPC_MSG_COMPLETE_BOOT_DEFAULT_TIMEOUT); + + /* Trap if called from non-preemptible context */ + might_sleep(); + + response.status = IPC_MEM_MSG_CS_INVALID; + init_completion(&response.completion); + + send_args.msg_type = prep; + send_args.prep_args = prep_args; + send_args.response = &response; + + /* Allocate and prepare message to be sent in tasklet context. + * A positive index returned form tasklet_call references the message + * in case it needs to be cancelled when there is a timeout. + */ + index = ipc_task_queue_send_task(ipc_protocol->imem, + ipc_protocol_tq_msg_send_cb, 0, + &send_args, 0, true); + + if (index < 0) { + dev_err(ipc_protocol->dev, "msg %d failed", prep); + return index; + } + + /* Wait for the device to respond to the message */ + switch (wait_for_completion_timeout(&response.completion, + msecs_to_jiffies(exec_timeout))) { + case 0: + /* Timeout, there was no response from the device. + * Remove the reference to the local response completion + * object as we are no longer interested in the response. + */ + ipc_task_queue_send_task(ipc_protocol->imem, + ipc_protocol_tq_msg_remove, index, + NULL, 0, true); + dev_err(ipc_protocol->dev, "msg timeout"); + ipc_uevent_send(ipc_protocol->pcie->dev, UEVENT_MDM_TIMEOUT); + break; + default: + /* We got a response in time; check completion status: */ + if (response.status != IPC_MEM_MSG_CS_SUCCESS) { + dev_err(ipc_protocol->dev, + "msg completion status error %d", + response.status); + return -EIO; + } + } + + return 0; +} + +static int ipc_protocol_msg_send_host_sleep(struct iosm_protocol *ipc_protocol, + u32 state) +{ + union ipc_msg_prep_args prep_args = { + .sleep.target = 0, + .sleep.state = state, + }; + + return ipc_protocol_msg_send(ipc_protocol, IPC_MSG_PREP_SLEEP, + &prep_args); +} + +void ipc_protocol_doorbell_trigger(struct iosm_protocol *ipc_protocol, + u32 identifier) +{ + ipc_pm_signal_hpda_doorbell(&ipc_protocol->pm, identifier, true); +} + +bool ipc_protocol_pm_dev_sleep_handle(struct iosm_protocol *ipc_protocol) +{ + u32 ipc_status = ipc_protocol_get_ipc_status(ipc_protocol); + u32 requested; + + if (ipc_status != IPC_MEM_DEVICE_IPC_RUNNING) { + dev_err(ipc_protocol->dev, + "irq ignored, CP IPC state is %d, should be RUNNING", + ipc_status); + + /* Stop further processing. */ + return false; + } + + /* Get a copy of the requested PM state by the device and the local + * device PM state. + */ + requested = ipc_protocol_pm_dev_get_sleep_notification(ipc_protocol); + + return ipc_pm_dev_slp_notification(&ipc_protocol->pm, requested); +} + +static int ipc_protocol_tq_wakeup_dev_slp(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size) +{ + struct iosm_pm *ipc_pm = &ipc_imem->ipc_protocol->pm; + + /* Wakeup from device sleep if it is not ACTIVE */ + ipc_pm_trigger(ipc_pm, IPC_PM_UNIT_HS, true); + + ipc_pm_trigger(ipc_pm, IPC_PM_UNIT_HS, false); + + return 0; +} + +void ipc_protocol_s2idle_sleep(struct iosm_protocol *ipc_protocol, bool sleep) +{ + ipc_pm_set_s2idle_sleep(&ipc_protocol->pm, sleep); +} + +bool ipc_protocol_suspend(struct iosm_protocol *ipc_protocol) +{ + if (!ipc_pm_prepare_host_sleep(&ipc_protocol->pm)) + goto err; + + ipc_task_queue_send_task(ipc_protocol->imem, + ipc_protocol_tq_wakeup_dev_slp, 0, NULL, 0, + true); + + if (!ipc_pm_wait_for_device_active(&ipc_protocol->pm)) { + ipc_uevent_send(ipc_protocol->pcie->dev, UEVENT_MDM_TIMEOUT); + goto err; + } + + /* Send the sleep message for sync sys calls. */ + dev_dbg(ipc_protocol->dev, "send TARGET_HOST, ENTER_SLEEP"); + if (ipc_protocol_msg_send_host_sleep(ipc_protocol, + IPC_HOST_SLEEP_ENTER_SLEEP)) { + /* Sending ENTER_SLEEP message failed, we are still active */ + ipc_protocol->pm.host_pm_state = IPC_MEM_HOST_PM_ACTIVE; + goto err; + } + + ipc_protocol->pm.host_pm_state = IPC_MEM_HOST_PM_SLEEP; + return true; +err: + return false; +} + +bool ipc_protocol_resume(struct iosm_protocol *ipc_protocol) +{ + if (!ipc_pm_prepare_host_active(&ipc_protocol->pm)) + return false; + + dev_dbg(ipc_protocol->dev, "send TARGET_HOST, EXIT_SLEEP"); + if (ipc_protocol_msg_send_host_sleep(ipc_protocol, + IPC_HOST_SLEEP_EXIT_SLEEP)) { + ipc_protocol->pm.host_pm_state = IPC_MEM_HOST_PM_SLEEP; + return false; + } + + ipc_protocol->pm.host_pm_state = IPC_MEM_HOST_PM_ACTIVE; + + return true; +} + +struct iosm_protocol *ipc_protocol_init(struct iosm_imem *ipc_imem) +{ + struct iosm_protocol *ipc_protocol = + kzalloc(sizeof(*ipc_protocol), GFP_KERNEL); + struct ipc_protocol_context_info *p_ci; + u64 addr; + + if (!ipc_protocol) + return NULL; + + ipc_protocol->dev = ipc_imem->dev; + ipc_protocol->pcie = ipc_imem->pcie; + ipc_protocol->imem = ipc_imem; + ipc_protocol->p_ap_shm = NULL; + ipc_protocol->phy_ap_shm = 0; + + ipc_protocol->old_msg_tail = 0; + + ipc_protocol->p_ap_shm = + pci_alloc_consistent(ipc_protocol->pcie->pci, + sizeof(*ipc_protocol->p_ap_shm), + &ipc_protocol->phy_ap_shm); + + if (!ipc_protocol->p_ap_shm) { + dev_err(ipc_protocol->dev, "pci shm alloc error"); + kfree(ipc_protocol); + return NULL; + } + + /* Prepare the context info for CP. */ + addr = ipc_protocol->phy_ap_shm; + p_ci = &ipc_protocol->p_ap_shm->ci; + p_ci->device_info_addr = + addr + offsetof(struct ipc_protocol_ap_shm, device_info); + p_ci->head_array = + addr + offsetof(struct ipc_protocol_ap_shm, head_array); + p_ci->tail_array = + addr + offsetof(struct ipc_protocol_ap_shm, tail_array); + p_ci->msg_head = addr + offsetof(struct ipc_protocol_ap_shm, msg_head); + p_ci->msg_tail = addr + offsetof(struct ipc_protocol_ap_shm, msg_tail); + p_ci->msg_ring_addr = + addr + offsetof(struct ipc_protocol_ap_shm, msg_ring); + p_ci->msg_ring_entries = cpu_to_le16(IPC_MEM_MSG_ENTRIES); + p_ci->msg_irq_vector = IPC_MSG_IRQ_VECTOR; + p_ci->device_info_irq_vector = IPC_DEVICE_IRQ_VECTOR; + + ipc_mmio_set_contex_info_addr(ipc_imem->mmio, addr); + + ipc_pm_init(ipc_protocol); + + return ipc_protocol; +} + +void ipc_protocol_deinit(struct iosm_protocol *proto) +{ + pci_free_consistent(proto->pcie->pci, sizeof(*proto->p_ap_shm), + proto->p_ap_shm, proto->phy_ap_shm); + + ipc_pm_deinit(proto); + kfree(proto); +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol.h b/drivers/net/wwan/iosm/iosm_ipc_protocol.h new file mode 100644 index 000000000000..9b3a6d86ece7 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_protocol.h @@ -0,0 +1,237 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_PROTOCOL_H +#define IOSM_IPC_PROTOCOL_H + +#include "iosm_ipc_imem.h" +#include "iosm_ipc_pm.h" +#include "iosm_ipc_protocol_ops.h" + +/* Trigger the doorbell interrupt on CP. */ +#define IPC_DOORBELL_IRQ_HPDA 0 +#define IPC_DOORBELL_IRQ_IPC 1 +#define IPC_DOORBELL_IRQ_SLEEP 2 + +/* IRQ vector number. */ +#define IPC_DEVICE_IRQ_VECTOR 0 +#define IPC_MSG_IRQ_VECTOR 0 +#define IPC_UL_PIPE_IRQ_VECTOR 0 +#define IPC_DL_PIPE_IRQ_VECTOR 0 + +#define IPC_MEM_MSG_ENTRIES 128 + +/* Default time out for sending IPC messages like open pipe, close pipe etc. + * during run mode. + * + * If the message interface lock to CP times out, the link to CP is broken. + * mode : run mode (IPC_MEM_EXEC_STAGE_RUN) + * unit : milliseconds + */ +#define IPC_MSG_COMPLETE_RUN_DEFAULT_TIMEOUT 500 /* 0.5 seconds */ + +/* Default time out for sending IPC messages like open pipe, close pipe etc. + * during boot mode. + * + * If the message interface lock to CP times out, the link to CP is broken. + * mode : boot mode + * (IPC_MEM_EXEC_STAGE_BOOT | IPC_MEM_EXEC_STAGE_PSI | IPC_MEM_EXEC_STAGE_EBL) + * unit : milliseconds + */ +#define IPC_MSG_COMPLETE_BOOT_DEFAULT_TIMEOUT 500 /* 0.5 seconds */ + +/** + * struct ipc_protocol_context_info - Structure of the context info + * @device_info_addr: 64 bit address to device info + * @head_array: 64 bit address to head pointer arr for the pipes + * @tail_array: 64 bit address to tail pointer arr for the pipes + * @msg_head: 64 bit address to message head pointer + * @msg_tail: 64 bit address to message tail pointer + * @msg_ring_addr: 64 bit pointer to the message ring buffer + * @msg_ring_entries: This field provides the number of entries which + * the MR can hold + * @msg_irq_vector: This field provides the IRQ which shall be + * generated by the EP device when generating + * completion for Messages. + * @device_info_irq_vector: This field provides the IRQ which shall be + * generated by the EP dev after updating Dev. Info + */ +struct ipc_protocol_context_info { + phys_addr_t device_info_addr; + phys_addr_t head_array; + phys_addr_t tail_array; + phys_addr_t msg_head; + phys_addr_t msg_tail; + phys_addr_t msg_ring_addr; + __le16 msg_ring_entries; + u8 msg_irq_vector; + u8 device_info_irq_vector; +}; + +/** + * struct ipc_protocol_device_info - Structure for the device information + * @execution_stage: CP execution stage + * @ipc_status: IPC states + * @device_sleep_notification: Requested device pm states + */ +struct ipc_protocol_device_info { + __le32 execution_stage; + __le32 ipc_status; + __le32 device_sleep_notification; +}; + +/** + * struct ipc_protocol_ap_shm - Protocol Shared Memory Structure + * @ci: Context information struct + * @device_info: Device information struct + * @msg_head: Point to msg head + * @head_array: Array of head pointer + * @msg_tail: Point to msg tail + * @tail_array: Array of tail pointer + * @msg_ring: Circular buffers for the read/tail and write/head + * indeces. + */ +struct ipc_protocol_ap_shm { + struct ipc_protocol_context_info ci; + struct ipc_protocol_device_info device_info; + __le32 msg_head; + __le32 head_array[IPC_MEM_MAX_PIPES]; + __le32 msg_tail; + __le32 tail_array[IPC_MEM_MAX_PIPES]; + union ipc_mem_msg_entry msg_ring[IPC_MEM_MSG_ENTRIES]; +}; + +/** + * struct iosm_protocol - Structure for IPC protocol. + * @p_ap_shm: Pointer to Protocol Shared Memory Structure + * @pm: Instance to struct iosm_pm + * @pcie: Pointer to struct iosm_pcie + * @imem: Pointer to struct iosm_imem + * @rsp_ring: Array of OS completion objects to be triggered once CP + * acknowledges a request in the message ring + * @dev: Pointer to device structure + * @phy_ap_shm: Physical/Mapped representation of the shared memory info + * @old_msg_tail: Old msg tail ptr, until AP has handled ACK's from CP + */ +struct iosm_protocol { + struct ipc_protocol_ap_shm *p_ap_shm; + struct iosm_pm pm; + struct iosm_pcie *pcie; + struct iosm_imem *imem; + struct ipc_rsp *rsp_ring[IPC_MEM_MSG_ENTRIES]; + struct device *dev; + phys_addr_t phy_ap_shm; + u32 old_msg_tail; +}; + +/** + * struct ipc_call_msg_send_args - Structure for message argument for + * tasklet function. + * @prep_args: Arguments for message preparation function + * @response: Can be NULL if result can be ignored + * @msg_type: Message Type + */ +struct ipc_call_msg_send_args { + union ipc_msg_prep_args *prep_args; + struct ipc_rsp *response; + enum ipc_msg_prep_type msg_type; +}; + +/** + * ipc_protocol_tq_msg_send - prepare the msg and send to CP + * @ipc_protocol: Pointer to ipc_protocol instance + * @msg_type: Message type + * @prep_args: Message arguments + * @response: Pointer to a response object which has a + * completion object and return code. + * + * Returns: 0 on success and failure value on error + */ +int ipc_protocol_tq_msg_send(struct iosm_protocol *ipc_protocol, + enum ipc_msg_prep_type msg_type, + union ipc_msg_prep_args *prep_args, + struct ipc_rsp *response); + +/** + * ipc_protocol_msg_send - Send ipc control message to CP and wait for response + * @ipc_protocol: Pointer to ipc_protocol instance + * @prep: Message type + * @prep_args: Message arguments + * + * Returns: 0 on success and failure value on error + */ +int ipc_protocol_msg_send(struct iosm_protocol *ipc_protocol, + enum ipc_msg_prep_type prep, + union ipc_msg_prep_args *prep_args); + +/** + * ipc_protocol_suspend - Signal to CP that host wants to go to sleep (suspend). + * @ipc_protocol: Pointer to ipc_protocol instance + * + * Returns: true if host can suspend, false if suspend must be aborted. + */ +bool ipc_protocol_suspend(struct iosm_protocol *ipc_protocol); + +/** + * ipc_protocol_s2idle_sleep - Call PM function to set PM variables in s2idle + * sleep/active case + * @ipc_protocol: Pointer to ipc_protocol instance + * @sleep: True for sleep/False for active + */ +void ipc_protocol_s2idle_sleep(struct iosm_protocol *ipc_protocol, bool sleep); + +/** + * ipc_protocol_resume - Signal to CP that host wants to resume operation. + * @ipc_protocol: Pointer to ipc_protocol instance + * + * Returns: true if host can resume, false if there is a problem. + */ +bool ipc_protocol_resume(struct iosm_protocol *ipc_protocol); + +/** + * ipc_protocol_pm_dev_sleep_handle - Handles the Device Sleep state change + * notification. + * @ipc_protocol: Pointer to ipc_protocol instance. + * + * Returns: true if sleep notification handled, false otherwise. + */ +bool ipc_protocol_pm_dev_sleep_handle(struct iosm_protocol *ipc_protocol); + +/** + * ipc_protocol_doorbell_trigger - Wrapper for PM function which wake up the + * device if it is in low power mode + * and trigger a head pointer update interrupt. + * @ipc_protocol: Pointer to ipc_protocol instance. + * @identifier: Specifies what component triggered hpda + * update irq + */ +void ipc_protocol_doorbell_trigger(struct iosm_protocol *ipc_protocol, + u32 identifier); + +/** + * ipc_protocol_sleep_notification_string - Returns last Sleep Notification as + * string. + * @ipc_protocol: Instance pointer of Protocol module. + * + * Returns: Pointer to string. + */ +const char * +ipc_protocol_sleep_notification_string(struct iosm_protocol *ipc_protocol); + +/** + * ipc_protocol_init - Allocates IPC protocol instance + * @ipc_imem: Pointer to iosm_imem structure + * + * Returns: Address of IPC protocol instance on success & NULL on failure. + */ +struct iosm_protocol *ipc_protocol_init(struct iosm_imem *ipc_imem); + +/** + * ipc_protocol_deinit - Deallocates IPC protocol instance + * @ipc_protocol: pointer to the IPC protocol instance + */ +void ipc_protocol_deinit(struct iosm_protocol *ipc_protocol); + +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c new file mode 100644 index 000000000000..91109e27efd3 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.c @@ -0,0 +1,552 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include "iosm_ipc_protocol.h" +#include "iosm_ipc_protocol_ops.h" + +/* Get the next free message element.*/ +static union ipc_mem_msg_entry * +ipc_protocol_free_msg_get(struct iosm_protocol *ipc_protocol, int *index) +{ + u32 head = le32_to_cpu(ipc_protocol->p_ap_shm->msg_head); + u32 new_head = (head + 1) % IPC_MEM_MSG_ENTRIES; + union ipc_mem_msg_entry *msg; + + if (new_head == le32_to_cpu(ipc_protocol->p_ap_shm->msg_tail)) { + dev_err(ipc_protocol->dev, "message ring is full"); + return NULL; + } + + /* Get the pointer to the next free message element, + * reset the fields and mark is as invalid. + */ + msg = &ipc_protocol->p_ap_shm->msg_ring[head]; + memset(msg, 0, sizeof(*msg)); + + /* return index in message ring */ + *index = head; + + return msg; +} + +/* Updates the message ring Head pointer */ +void ipc_protocol_msg_hp_update(struct iosm_imem *ipc_imem) +{ + struct iosm_protocol *ipc_protocol = ipc_imem->ipc_protocol; + u32 head = le32_to_cpu(ipc_protocol->p_ap_shm->msg_head); + u32 new_head = (head + 1) % IPC_MEM_MSG_ENTRIES; + + /* Update head pointer and fire doorbell. */ + ipc_protocol->p_ap_shm->msg_head = cpu_to_le32(new_head); + ipc_protocol->old_msg_tail = + le32_to_cpu(ipc_protocol->p_ap_shm->msg_tail); + + ipc_pm_signal_hpda_doorbell(&ipc_protocol->pm, IPC_HP_MR, false); +} + +/* Allocate and prepare a OPEN_PIPE message. + * This also allocates the memory for the new TDR structure and + * updates the pipe structure referenced in the preparation arguments. + */ +static int ipc_protocol_msg_prepipe_open(struct iosm_protocol *ipc_protocol, + union ipc_msg_prep_args *args) +{ + int index; + union ipc_mem_msg_entry *msg = + ipc_protocol_free_msg_get(ipc_protocol, &index); + struct ipc_pipe *pipe = args->pipe_open.pipe; + struct ipc_protocol_td *tdr; + struct sk_buff **skbr; + + if (!msg) { + dev_err(ipc_protocol->dev, "failed to get free message"); + return -EIO; + } + + /* Allocate the skbuf elements for the skbuf which are on the way. + * SKB ring is internal memory allocation for driver. No need to + * re-calculate the start and end addresses. + */ + skbr = kcalloc(pipe->nr_of_entries, sizeof(*skbr), GFP_ATOMIC); + if (!skbr) + return -ENOMEM; + + /* Allocate the transfer descriptors for the pipe. */ + tdr = pci_alloc_consistent(ipc_protocol->pcie->pci, + pipe->nr_of_entries * sizeof(*tdr), + &pipe->phy_tdr_start); + if (!tdr) { + kfree(skbr); + dev_err(ipc_protocol->dev, "tdr alloc error"); + return -ENOMEM; + } + + pipe->max_nr_of_queued_entries = pipe->nr_of_entries - 1; + pipe->nr_of_queued_entries = 0; + pipe->tdr_start = tdr; + pipe->skbr_start = skbr; + pipe->old_tail = 0; + + ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr] = 0; + + msg->open_pipe.type_of_message = IPC_MEM_MSG_OPEN_PIPE; + msg->open_pipe.pipe_nr = pipe->pipe_nr; + msg->open_pipe.tdr_addr = cpu_to_le64(pipe->phy_tdr_start); + msg->open_pipe.tdr_entries = cpu_to_le16(pipe->nr_of_entries); + msg->open_pipe.accumulation_backoff = + cpu_to_le32(pipe->accumulation_backoff); + msg->open_pipe.irq_vector = cpu_to_le32(pipe->irq); + + return index; +} + +static int ipc_protocol_msg_prepipe_close(struct iosm_protocol *ipc_protocol, + union ipc_msg_prep_args *args) +{ + int index = -1; + union ipc_mem_msg_entry *msg = + ipc_protocol_free_msg_get(ipc_protocol, &index); + struct ipc_pipe *pipe = args->pipe_close.pipe; + + if (!msg) + return -EIO; + + msg->close_pipe.type_of_message = IPC_MEM_MSG_CLOSE_PIPE; + msg->close_pipe.pipe_nr = pipe->pipe_nr; + + dev_dbg(ipc_protocol->dev, "IPC_MEM_MSG_CLOSE_PIPE(pipe_nr=%d)", + msg->close_pipe.pipe_nr); + + return index; +} + +static int ipc_protocol_msg_prep_sleep(struct iosm_protocol *ipc_protocol, + union ipc_msg_prep_args *args) +{ + int index = -1; + union ipc_mem_msg_entry *msg = + ipc_protocol_free_msg_get(ipc_protocol, &index); + + if (!msg) { + dev_err(ipc_protocol->dev, "failed to get free message"); + return -EIO; + } + + /* Prepare and send the host sleep message to CP to enter or exit D3. */ + msg->host_sleep.type_of_message = IPC_MEM_MSG_SLEEP; + msg->host_sleep.target = args->sleep.target; /* 0=host, 1=device */ + + /* state; 0=enter, 1=exit 2=enter w/o protocol */ + msg->host_sleep.state = args->sleep.state; + + dev_dbg(ipc_protocol->dev, "IPC_MEM_MSG_SLEEP(target=%d; state=%d)", + msg->host_sleep.target, msg->host_sleep.state); + + return index; +} + +static int ipc_protocol_msg_prep_feature_set(struct iosm_protocol *ipc_protocol, + union ipc_msg_prep_args *args) +{ + int index = -1; + union ipc_mem_msg_entry *msg = + ipc_protocol_free_msg_get(ipc_protocol, &index); + + if (!msg) { + dev_err(ipc_protocol->dev, "failed to get free message"); + return -EIO; + } + + msg->feature_set.type_of_message = IPC_MEM_MSG_FEATURE_SET; + msg->feature_set.reset_enable = args->feature_set.reset_enable << + RESET_BIT; + + dev_dbg(ipc_protocol->dev, "IPC_MEM_MSG_FEATURE_SET(reset_enable=%d)", + msg->feature_set.reset_enable >> RESET_BIT); + + return index; +} + +/* Processes the message consumed by CP. */ +bool ipc_protocol_msg_process(struct iosm_imem *ipc_imem, int irq) +{ + struct iosm_protocol *ipc_protocol = ipc_imem->ipc_protocol; + struct ipc_rsp **rsp_ring = ipc_protocol->rsp_ring; + bool msg_processed = false; + u32 i; + + if (le32_to_cpu(ipc_protocol->p_ap_shm->msg_tail) >= + IPC_MEM_MSG_ENTRIES) { + dev_err(ipc_protocol->dev, "msg_tail out of range: %d", + le32_to_cpu(ipc_protocol->p_ap_shm->msg_tail)); + return msg_processed; + } + + if (irq != IMEM_IRQ_DONT_CARE && + irq != ipc_protocol->p_ap_shm->ci.msg_irq_vector) + return msg_processed; + + for (i = ipc_protocol->old_msg_tail; + i != le32_to_cpu(ipc_protocol->p_ap_shm->msg_tail); + i = (i + 1) % IPC_MEM_MSG_ENTRIES) { + union ipc_mem_msg_entry *msg = + &ipc_protocol->p_ap_shm->msg_ring[i]; + + dev_dbg(ipc_protocol->dev, "msg[%d]: type=%u status=%d", i, + msg->common.type_of_message, + msg->common.completion_status); + + /* Update response with status and wake up waiting requestor */ + if (rsp_ring[i]) { + rsp_ring[i]->status = + le32_to_cpu(msg->common.completion_status); + complete(&rsp_ring[i]->completion); + rsp_ring[i] = NULL; + } + msg_processed = true; + } + + ipc_protocol->old_msg_tail = i; + return msg_processed; +} + +/* Sends data from UL list to CP for the provided pipe by updating the Head + * pointer of given pipe. + */ +bool ipc_protocol_ul_td_send(struct iosm_protocol *ipc_protocol, + struct ipc_pipe *pipe, + struct sk_buff_head *p_ul_list) +{ + struct ipc_protocol_td *td; + bool hpda_pending = false; + struct sk_buff *skb; + s32 free_elements; + u32 head; + u32 tail; + + if (!ipc_protocol->p_ap_shm) { + dev_err(ipc_protocol->dev, "driver is not initialized"); + return false; + } + + /* Get head and tail of the td list and calculate + * the number of free elements. + */ + head = le32_to_cpu(ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr]); + tail = pipe->old_tail; + + while (!skb_queue_empty(p_ul_list)) { + if (head < tail) + free_elements = tail - head - 1; + else + free_elements = + pipe->nr_of_entries - head + ((s32)tail - 1); + + if (free_elements <= 0) { + dev_dbg(ipc_protocol->dev, + "no free td elements for UL pipe %d", + pipe->pipe_nr); + break; + } + + /* Get the td address. */ + td = &pipe->tdr_start[head]; + + /* Take the first element of the uplink list and add it + * to the td list. + */ + skb = skb_dequeue(p_ul_list); + if (WARN_ON(!skb)) + break; + + /* Save the reference to the uplink skbuf. */ + pipe->skbr_start[head] = skb; + + td->buffer.address = IPC_CB(skb)->mapping; + td->scs = cpu_to_le32(skb->len) & cpu_to_le32(SIZE_MASK); + td->next = 0; + + pipe->nr_of_queued_entries++; + + /* Calculate the new head and save it. */ + head++; + if (head >= pipe->nr_of_entries) + head = 0; + + ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr] = + cpu_to_le32(head); + } + + if (pipe->old_head != head) { + dev_dbg(ipc_protocol->dev, "New UL TDs Pipe:%d", pipe->pipe_nr); + + pipe->old_head = head; + /* Trigger doorbell because of pending UL packets. */ + hpda_pending = true; + } + + return hpda_pending; +} + +/* Checks for Tail pointer update from CP and returns the data as SKB. */ +struct sk_buff *ipc_protocol_ul_td_process(struct iosm_protocol *ipc_protocol, + struct ipc_pipe *pipe) +{ + struct ipc_protocol_td *p_td = &pipe->tdr_start[pipe->old_tail]; + struct sk_buff *skb = pipe->skbr_start[pipe->old_tail]; + + pipe->nr_of_queued_entries--; + pipe->old_tail++; + if (pipe->old_tail >= pipe->nr_of_entries) + pipe->old_tail = 0; + + if (!p_td->buffer.address) { + dev_err(ipc_protocol->dev, "Td buffer address is NULL"); + return NULL; + } + + if (p_td->buffer.address != IPC_CB(skb)->mapping) { + dev_err(ipc_protocol->dev, + "pipe %d: invalid buf_addr or skb_data", + pipe->pipe_nr); + return NULL; + } + + return skb; +} + +/* Allocates an SKB for CP to send data and updates the Head Pointer + * of the given Pipe#. + */ +bool ipc_protocol_dl_td_prepare(struct iosm_protocol *ipc_protocol, + struct ipc_pipe *pipe) +{ + struct ipc_protocol_td *td; + dma_addr_t mapping = 0; + u32 head, new_head; + struct sk_buff *skb; + u32 tail; + + /* Get head and tail of the td list and calculate + * the number of free elements. + */ + head = le32_to_cpu(ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr]); + tail = le32_to_cpu(ipc_protocol->p_ap_shm->tail_array[pipe->pipe_nr]); + + new_head = head + 1; + if (new_head >= pipe->nr_of_entries) + new_head = 0; + + if (new_head == tail) + return false; + + /* Get the td address. */ + td = &pipe->tdr_start[head]; + + /* Allocate the skbuf for the descriptor. */ + skb = ipc_pcie_alloc_skb(ipc_protocol->pcie, pipe->buf_size, GFP_ATOMIC, + &mapping, DMA_FROM_DEVICE, + IPC_MEM_DL_ETH_OFFSET); + if (!skb) + return false; + + td->buffer.address = mapping; + td->scs = cpu_to_le32(pipe->buf_size) & cpu_to_le32(SIZE_MASK); + td->next = 0; + + /* store the new head value. */ + ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr] = + cpu_to_le32(new_head); + + /* Save the reference to the skbuf. */ + pipe->skbr_start[head] = skb; + + pipe->nr_of_queued_entries++; + + return true; +} + +/* Processes DL TD's */ +struct sk_buff *ipc_protocol_dl_td_process(struct iosm_protocol *ipc_protocol, + struct ipc_pipe *pipe) +{ + u32 tail = + le32_to_cpu(ipc_protocol->p_ap_shm->tail_array[pipe->pipe_nr]); + struct ipc_protocol_td *p_td; + struct sk_buff *skb; + + if (!pipe->tdr_start) + return NULL; + + /* Copy the reference to the downlink buffer. */ + p_td = &pipe->tdr_start[pipe->old_tail]; + skb = pipe->skbr_start[pipe->old_tail]; + + /* Reset the ring elements. */ + pipe->skbr_start[pipe->old_tail] = NULL; + + pipe->nr_of_queued_entries--; + + pipe->old_tail++; + if (pipe->old_tail >= pipe->nr_of_entries) + pipe->old_tail = 0; + + if (!skb) { + dev_err(ipc_protocol->dev, "skb is null"); + goto ret; + } else if (!p_td->buffer.address) { + dev_err(ipc_protocol->dev, "td/buffer address is null"); + ipc_pcie_kfree_skb(ipc_protocol->pcie, skb); + skb = NULL; + goto ret; + } + + if (!IPC_CB(skb)) { + dev_err(ipc_protocol->dev, "pipe# %d, tail: %d skb_cb is NULL", + pipe->pipe_nr, tail); + ipc_pcie_kfree_skb(ipc_protocol->pcie, skb); + skb = NULL; + goto ret; + } + + if (p_td->buffer.address != IPC_CB(skb)->mapping) { + dev_err(ipc_protocol->dev, "invalid buf=%p or skb=%p", + (void *)p_td->buffer.address, skb->data); + ipc_pcie_kfree_skb(ipc_protocol->pcie, skb); + skb = NULL; + goto ret; + } else if ((le32_to_cpu(p_td->scs) & SIZE_MASK) > pipe->buf_size) { + dev_err(ipc_protocol->dev, "invalid buffer size %d > %d", + le32_to_cpu(p_td->scs) & SIZE_MASK, + pipe->buf_size); + ipc_pcie_kfree_skb(ipc_protocol->pcie, skb); + skb = NULL; + goto ret; + } else if (le32_to_cpu(p_td->scs) >> COMPLETION_STATUS == + IPC_MEM_TD_CS_ABORT) { + /* Discard aborted buffers. */ + dev_dbg(ipc_protocol->dev, "discard 'aborted' buffers"); + ipc_pcie_kfree_skb(ipc_protocol->pcie, skb); + skb = NULL; + goto ret; + } + + /* Set the length field in skbuf. */ + skb_put(skb, le32_to_cpu(p_td->scs) & SIZE_MASK); + +ret: + return skb; +} + +void ipc_protocol_get_head_tail_index(struct iosm_protocol *ipc_protocol, + struct ipc_pipe *pipe, u32 *head, + u32 *tail) +{ + struct ipc_protocol_ap_shm *ipc_ap_shm = ipc_protocol->p_ap_shm; + + if (head) + *head = le32_to_cpu(ipc_ap_shm->head_array[pipe->pipe_nr]); + + if (tail) + *tail = le32_to_cpu(ipc_ap_shm->tail_array[pipe->pipe_nr]); +} + +/* Frees the TDs given to CP. */ +void ipc_protocol_pipe_cleanup(struct iosm_protocol *ipc_protocol, + struct ipc_pipe *pipe) +{ + struct sk_buff *skb; + u32 head; + u32 tail; + + /* Get the start and the end of the buffer list. */ + head = le32_to_cpu(ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr]); + tail = pipe->old_tail; + + /* Reset tail and head to 0. */ + ipc_protocol->p_ap_shm->tail_array[pipe->pipe_nr] = 0; + ipc_protocol->p_ap_shm->head_array[pipe->pipe_nr] = 0; + + /* Free pending uplink and downlink buffers. */ + if (pipe->skbr_start) { + while (head != tail) { + /* Get the reference to the skbuf, + * which is on the way and free it. + */ + skb = pipe->skbr_start[tail]; + if (skb) + ipc_pcie_kfree_skb(ipc_protocol->pcie, skb); + + tail++; + if (tail >= pipe->nr_of_entries) + tail = 0; + } + + kfree(pipe->skbr_start); + pipe->skbr_start = NULL; + } + + pipe->old_tail = 0; + + /* Free and reset the td and skbuf circular buffers. kfree is save! */ + if (pipe->tdr_start) { + pci_free_consistent(ipc_protocol->pcie->pci, + sizeof(*pipe->tdr_start) * + pipe->nr_of_entries, + pipe->tdr_start, pipe->phy_tdr_start); + + pipe->tdr_start = NULL; + } +} + +enum ipc_mem_device_ipc_state ipc_protocol_get_ipc_status(struct iosm_protocol + *ipc_protocol) +{ + return (enum ipc_mem_device_ipc_state) + le32_to_cpu(ipc_protocol->p_ap_shm->device_info.ipc_status); +} + +enum ipc_mem_exec_stage +ipc_protocol_get_ap_exec_stage(struct iosm_protocol *ipc_protocol) +{ + return le32_to_cpu(ipc_protocol->p_ap_shm->device_info.execution_stage); +} + +int ipc_protocol_msg_prep(struct iosm_imem *ipc_imem, + enum ipc_msg_prep_type msg_type, + union ipc_msg_prep_args *args) +{ + struct iosm_protocol *ipc_protocol = ipc_imem->ipc_protocol; + + switch (msg_type) { + case IPC_MSG_PREP_SLEEP: + return ipc_protocol_msg_prep_sleep(ipc_protocol, args); + + case IPC_MSG_PREP_PIPE_OPEN: + return ipc_protocol_msg_prepipe_open(ipc_protocol, args); + + case IPC_MSG_PREP_PIPE_CLOSE: + return ipc_protocol_msg_prepipe_close(ipc_protocol, args); + + case IPC_MSG_PREP_FEATURE_SET: + return ipc_protocol_msg_prep_feature_set(ipc_protocol, args); + + /* Unsupported messages in protocol */ + case IPC_MSG_PREP_MAP: + case IPC_MSG_PREP_UNMAP: + default: + dev_err(ipc_protocol->dev, + "unsupported message type: %d in protocol", msg_type); + return -EINVAL; + } +} + +u32 +ipc_protocol_pm_dev_get_sleep_notification(struct iosm_protocol *ipc_protocol) +{ + struct ipc_protocol_ap_shm *ipc_ap_shm = ipc_protocol->p_ap_shm; + + return le32_to_cpu(ipc_ap_shm->device_info.device_sleep_notification); +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.h b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.h new file mode 100644 index 000000000000..35aa1387306e --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_protocol_ops.h @@ -0,0 +1,444 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_PROTOCOL_OPS_H +#define IOSM_IPC_PROTOCOL_OPS_H + +#define SIZE_MASK 0x00FFFFFF +#define COMPLETION_STATUS 24 +#define RESET_BIT 7 + +/** + * enum ipc_mem_td_cs - Completion status of a TD + * @IPC_MEM_TD_CS_INVALID: Initial status - td not yet used. + * @IPC_MEM_TD_CS_PARTIAL_TRANSFER: More data pending -> next TD used for this + * @IPC_MEM_TD_CS_END_TRANSFER: IO transfer is complete. + * @IPC_MEM_TD_CS_OVERFLOW: IO transfer to small for the buff to write + * @IPC_MEM_TD_CS_ABORT: TD marked as abort and shall be discarded + * by AP. + * @IPC_MEM_TD_CS_ERROR: General error. + */ +enum ipc_mem_td_cs { + IPC_MEM_TD_CS_INVALID, + IPC_MEM_TD_CS_PARTIAL_TRANSFER, + IPC_MEM_TD_CS_END_TRANSFER, + IPC_MEM_TD_CS_OVERFLOW, + IPC_MEM_TD_CS_ABORT, + IPC_MEM_TD_CS_ERROR, +}; + +/** + * enum ipc_mem_msg_cs - Completion status of IPC Message + * @IPC_MEM_MSG_CS_INVALID: Initial status. + * @IPC_MEM_MSG_CS_SUCCESS: IPC Message completion success. + * @IPC_MEM_MSG_CS_ERROR: Message send error. + */ +enum ipc_mem_msg_cs { + IPC_MEM_MSG_CS_INVALID, + IPC_MEM_MSG_CS_SUCCESS, + IPC_MEM_MSG_CS_ERROR, +}; + +/** + * struct ipc_msg_prep_args_pipe - struct for pipe args for message preparation + * @pipe: Pipe to open/close + */ +struct ipc_msg_prep_args_pipe { + struct ipc_pipe *pipe; +}; + +/** + * struct ipc_msg_prep_args_sleep - struct for sleep args for message + * preparation + * @target: 0=host, 1=device + * @state: 0=enter sleep, 1=exit sleep + */ +struct ipc_msg_prep_args_sleep { + unsigned int target; + unsigned int state; +}; + +/** + * struct ipc_msg_prep_feature_set - struct for feature set argument for + * message preparation + * @reset_enable: 0=out-of-band, 1=in-band-crash notification + */ +struct ipc_msg_prep_feature_set { + u8 reset_enable; +}; + +/** + * struct ipc_msg_prep_map - struct for map argument for message preparation + * @region_id: Region to map + * @addr: Pcie addr of region to map + * @size: Size of the region to map + */ +struct ipc_msg_prep_map { + unsigned int region_id; + unsigned long addr; + size_t size; +}; + +/** + * struct ipc_msg_prep_unmap - struct for unmap argument for message preparation + * @region_id: Region to unmap + */ +struct ipc_msg_prep_unmap { + unsigned int region_id; +}; + +/** + * struct ipc_msg_prep_args - Union to handle different message types + * @pipe_open: Pipe open message preparation struct + * @pipe_close: Pipe close message preparation struct + * @sleep: Sleep message preparation struct + * @feature_set: Feature set message preparation struct + * @map: Memory map message preparation struct + * @unmap: Memory unmap message preparation struct + */ +union ipc_msg_prep_args { + struct ipc_msg_prep_args_pipe pipe_open; + struct ipc_msg_prep_args_pipe pipe_close; + struct ipc_msg_prep_args_sleep sleep; + struct ipc_msg_prep_feature_set feature_set; + struct ipc_msg_prep_map map; + struct ipc_msg_prep_unmap unmap; +}; + +/** + * enum ipc_msg_prep_type - Enum for message prepare actions + * @IPC_MSG_PREP_SLEEP: Sleep message preparation type + * @IPC_MSG_PREP_PIPE_OPEN: Pipe open message preparation type + * @IPC_MSG_PREP_PIPE_CLOSE: Pipe close message preparation type + * @IPC_MSG_PREP_FEATURE_SET: Feature set message preparation type + * @IPC_MSG_PREP_MAP: Memory map message preparation type + * @IPC_MSG_PREP_UNMAP: Memory unmap message preparation type + */ +enum ipc_msg_prep_type { + IPC_MSG_PREP_SLEEP, + IPC_MSG_PREP_PIPE_OPEN, + IPC_MSG_PREP_PIPE_CLOSE, + IPC_MSG_PREP_FEATURE_SET, + IPC_MSG_PREP_MAP, + IPC_MSG_PREP_UNMAP, +}; + +/** + * struct ipc_rsp - Response to sent message + * @completion: For waking up requestor + * @status: Completion status + */ +struct ipc_rsp { + struct completion completion; + enum ipc_mem_msg_cs status; +}; + +/** + * enum ipc_mem_msg - Type-definition of the messages. + * @IPC_MEM_MSG_OPEN_PIPE: AP ->CP: Open a pipe + * @IPC_MEM_MSG_CLOSE_PIPE: AP ->CP: Close a pipe + * @IPC_MEM_MSG_ABORT_PIPE: AP ->CP: wait for completion of the + * running transfer and abort all pending + * IO-transfers for the pipe + * @IPC_MEM_MSG_SLEEP: AP ->CP: host enter or exit sleep + * @IPC_MEM_MSG_FEATURE_SET: AP ->CP: Intel feature configuration + */ +enum ipc_mem_msg { + IPC_MEM_MSG_OPEN_PIPE = 0x01, + IPC_MEM_MSG_CLOSE_PIPE = 0x02, + IPC_MEM_MSG_ABORT_PIPE = 0x03, + IPC_MEM_MSG_SLEEP = 0x04, + IPC_MEM_MSG_FEATURE_SET = 0xF0, +}; + +/** + * struct ipc_mem_msg_open_pipe - Message structure for open pipe + * @tdr_addr: Tdr address + * @tdr_entries: Tdr entries + * @pipe_nr: Pipe number + * @type_of_message: Message type + * @irq_vector: MSI vector number + * @accumulation_backoff: Time in usec for data accumalation + * @completion_status: Message Completion Status + */ +struct ipc_mem_msg_open_pipe { + __le64 tdr_addr; + __le16 tdr_entries; + u8 pipe_nr; + u8 type_of_message; + __le32 irq_vector; + __le32 accumulation_backoff; + __le32 completion_status; +}; + +/** + * struct ipc_mem_msg_close_pipe - Message structure for close pipe + * @reserved1: Reserved + * @reserved2: Reserved + * @pipe_nr: Pipe number + * @type_of_message: Message type + * @reserved3: Reserved + * @reserved4: Reserved + * @completion_status: Message Completion Status + */ +struct ipc_mem_msg_close_pipe { + __le32 reserved1[2]; + __le16 reserved2; + u8 pipe_nr; + u8 type_of_message; + __le32 reserved3; + __le32 reserved4; + __le32 completion_status; +}; + +/** + * struct ipc_mem_msg_abort_pipe - Message structure for abort pipe + * @reserved1: Reserved + * @reserved2: Reserved + * @pipe_nr: Pipe number + * @type_of_message: Message type + * @reserved3: Reserved + * @reserved4: Reserved + * @completion_status: Message Completion Status + */ +struct ipc_mem_msg_abort_pipe { + __le32 reserved1[2]; + __le16 reserved2; + u8 pipe_nr; + u8 type_of_message; + __le32 reserved3; + __le32 reserved4; + __le32 completion_status; +}; + +/** + * struct ipc_mem_msg_host_sleep - Message structure for sleep message. + * @reserved1: Reserved + * @target: 0=host, 1=device, host or EP devie + * is the message target + * @state: 0=enter sleep, 1=exit sleep, + * 2=enter sleep no protocol + * @reserved2: Reserved + * @type_of_message: Message type + * @reserved3: Reserved + * @reserved4: Reserved + * @completion_status: Message Completion Status + */ +struct ipc_mem_msg_host_sleep { + __le32 reserved1[2]; + u8 target; + u8 state; + u8 reserved2; + u8 type_of_message; + __le32 reserved3; + __le32 reserved4; + __le32 completion_status; +}; + +/** + * struct ipc_mem_msg_feature_set - Message structure for feature_set message + * @reserved1: Reserved + * @reserved2: Reserved + * @reset_enable: 0=out-of-band, 1=in-band-crash notification + * @type_of_message: Message type + * @reserved3: Reserved + * @reserved4: Reserved + * @completion_status: Message Completion Status + */ +struct ipc_mem_msg_feature_set { + __le32 reserved1[2]; + __le16 reserved2; + u8 reset_enable; + u8 type_of_message; + __le32 reserved3; + __le32 reserved4; + __le32 completion_status; +}; + +/** + * struct ipc_mem_msg_common - Message structure for completion status update. + * @reserved1: Reserved + * @reserved2: Reserved + * @type_of_message: Message type + * @reserved3: Reserved + * @reserved4: Reserved + * @completion_status: Message Completion Status + */ +struct ipc_mem_msg_common { + __le32 reserved1[2]; + u8 reserved2[3]; + u8 type_of_message; + __le32 reserved3; + __le32 reserved4; + __le32 completion_status; +}; + +/** + * union ipc_mem_msg_entry - Union with all possible messages. + * @open_pipe: Open pipe message struct + * @close_pipe: Close pipe message struct + * @abort_pipe: Abort pipe message struct + * @host_sleep: Host sleep message struct + * @feature_set: Featuer set message struct + * @common: Used to access msg_type and to set the completion status + */ +union ipc_mem_msg_entry { + struct ipc_mem_msg_open_pipe open_pipe; + struct ipc_mem_msg_close_pipe close_pipe; + struct ipc_mem_msg_abort_pipe abort_pipe; + struct ipc_mem_msg_host_sleep host_sleep; + struct ipc_mem_msg_feature_set feature_set; + struct ipc_mem_msg_common common; +}; + +/* Transfer descriptor definition. */ +struct ipc_protocol_td { + union { + /* 0 : 63 - 64-bit address of a buffer in host memory. */ + dma_addr_t address; + struct { + /* 0 : 31 - 32 bit address */ + __le32 address; + /* 32 : 63 - corresponding descriptor */ + __le32 desc; + } __packed shm; + } buffer; + + /* 0 - 2nd byte - Size of the buffer. + * The host provides the size of the buffer queued. + * The EP device reads this value and shall update + * it for downlink transfers to indicate the + * amount of data written in buffer. + * 3rd byte - This field provides the completion status + * of the TD. When queuing the TD, the host sets + * the status to 0. The EP device updates this + * field when completing the TD. + */ + __le32 scs; + + /* 0th - nr of following descriptors + * 1 - 3rd byte - reserved + */ + __le32 next; +} __packed; + +/** + * ipc_protocol_msg_prep - Prepare message based upon message type + * @ipc_imem: iosm_protocol instance + * @msg_type: message prepare type + * @args: message arguments + * + * Return: 0 on success and failure value on error + */ +int ipc_protocol_msg_prep(struct iosm_imem *ipc_imem, + enum ipc_msg_prep_type msg_type, + union ipc_msg_prep_args *args); + +/** + * ipc_protocol_msg_hp_update - Function for head pointer update + * of message ring + * @ipc_imem: iosm_protocol instance + */ +void ipc_protocol_msg_hp_update(struct iosm_imem *ipc_imem); + +/** + * ipc_protocol_msg_process - Function for processing responses + * to IPC messages + * @ipc_imem: iosm_protocol instance + * @irq: IRQ vector + * + * Return: True on success, false if error + */ +bool ipc_protocol_msg_process(struct iosm_imem *ipc_imem, int irq); + +/** + * ipc_protocol_ul_td_send - Function for sending the data to CP + * @ipc_protocol: iosm_protocol instance + * @pipe: Pipe instance + * @p_ul_list: uplink sk_buff list + * + * Return: true in success, false in case of error + */ +bool ipc_protocol_ul_td_send(struct iosm_protocol *ipc_protocol, + struct ipc_pipe *pipe, + struct sk_buff_head *p_ul_list); + +/** + * ipc_protocol_ul_td_process - Function for processing the sent data + * @ipc_protocol: iosm_protocol instance + * @pipe: Pipe instance + * + * Return: sk_buff instance + */ +struct sk_buff *ipc_protocol_ul_td_process(struct iosm_protocol *ipc_protocol, + struct ipc_pipe *pipe); + +/** + * ipc_protocol_dl_td_prepare - Function for providing DL TDs to CP + * @ipc_protocol: iosm_protocol instance + * @pipe: Pipe instance + * + * Return: true in success, false in case of error + */ +bool ipc_protocol_dl_td_prepare(struct iosm_protocol *ipc_protocol, + struct ipc_pipe *pipe); + +/** + * ipc_protocol_dl_td_process - Function for processing the DL data + * @ipc_protocol: iosm_protocol instance + * @pipe: Pipe instance + * + * Return: sk_buff instance + */ +struct sk_buff *ipc_protocol_dl_td_process(struct iosm_protocol *ipc_protocol, + struct ipc_pipe *pipe); + +/** + * ipc_protocol_get_head_tail_index - Function for getting Head and Tail + * pointer index of given pipe + * @ipc_protocol: iosm_protocol instance + * @pipe: Pipe Instance + * @head: head pointer index of the given pipe + * @tail: tail pointer index of the given pipe + */ +void ipc_protocol_get_head_tail_index(struct iosm_protocol *ipc_protocol, + struct ipc_pipe *pipe, u32 *head, + u32 *tail); +/** + * ipc_protocol_get_ipc_status - Function for getting the IPC Status + * @ipc_protocol: iosm_protocol instance + * + * Return: Returns IPC State + */ +enum ipc_mem_device_ipc_state ipc_protocol_get_ipc_status(struct iosm_protocol + *ipc_protocol); + +/** + * ipc_protocol_pipe_cleanup - Function to cleanup pipe resources + * @ipc_protocol: iosm_protocol instance + * @pipe: Pipe instance + */ +void ipc_protocol_pipe_cleanup(struct iosm_protocol *ipc_protocol, + struct ipc_pipe *pipe); + +/** + * ipc_protocol_get_ap_exec_stage - Function for getting AP Exec Stage + * @ipc_protocol: pointer to struct iosm protocol + * + * Return: returns BOOT Stages + */ +enum ipc_mem_exec_stage +ipc_protocol_get_ap_exec_stage(struct iosm_protocol *ipc_protocol); + +/** + * ipc_protocol_pm_dev_get_sleep_notification - Function for getting Dev Sleep + * notification + * @ipc_protocol: iosm_protocol instance + * + * Return: Returns dev PM State + */ +u32 ipc_protocol_pm_dev_get_sleep_notification(struct iosm_protocol + *ipc_protocol); +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_task_queue.c b/drivers/net/wwan/iosm/iosm_ipc_task_queue.c new file mode 100644 index 000000000000..852a99166144 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_task_queue.c @@ -0,0 +1,202 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include "iosm_ipc_imem.h" +#include "iosm_ipc_task_queue.h" + +/* Actual tasklet function, will be called whenever tasklet is scheduled. + * Calls event handler involves callback for each element in the message queue + */ +static void ipc_task_queue_handler(unsigned long data) +{ + struct ipc_task_queue *ipc_task = (struct ipc_task_queue *)data; + unsigned int q_rpos = ipc_task->q_rpos; + + /* Loop over the input queue contents. */ + while (q_rpos != ipc_task->q_wpos) { + /* Get the current first queue element. */ + struct ipc_task_queue_args *args = &ipc_task->args[q_rpos]; + + /* Process the input message. */ + if (args->func) + args->response = args->func(args->ipc_imem, args->arg, + args->msg, args->size); + + /* Signal completion for synchronous calls */ + if (args->completion) + complete(args->completion); + + /* Free message if copy was allocated. */ + if (args->is_copy) + kfree(args->msg); + + /* Set invalid queue element. Technically + * spin_lock_irqsave is not required here as + * the array element has been processed already + * so we can assume that immediately after processing + * ipc_task element, queue will not rotate again to + * ipc_task same element within such short time. + */ + args->completion = NULL; + args->func = NULL; + args->msg = NULL; + args->size = 0; + args->is_copy = false; + + /* calculate the new read ptr and update the volatile read + * ptr + */ + q_rpos = (q_rpos + 1) % IPC_THREAD_QUEUE_SIZE; + ipc_task->q_rpos = q_rpos; + } +} + +/* Free memory alloc and trigger completions left in the queue during dealloc */ +static void ipc_task_queue_cleanup(struct ipc_task_queue *ipc_task) +{ + unsigned int q_rpos = ipc_task->q_rpos; + + while (q_rpos != ipc_task->q_wpos) { + struct ipc_task_queue_args *args = &ipc_task->args[q_rpos]; + + if (args->completion) + complete(args->completion); + + if (args->is_copy) + kfree(args->msg); + + q_rpos = (q_rpos + 1) % IPC_THREAD_QUEUE_SIZE; + ipc_task->q_rpos = q_rpos; + } +} + +/* Add a message to the queue and trigger the ipc_task. */ +static int +ipc_task_queue_add_task(struct iosm_imem *ipc_imem, + int arg, void *msg, + int (*func)(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size), + size_t size, bool is_copy, bool wait) +{ + struct tasklet_struct *ipc_tasklet = ipc_imem->ipc_task->ipc_tasklet; + struct ipc_task_queue *ipc_task = &ipc_imem->ipc_task->ipc_queue; + struct completion completion; + unsigned int pos, nextpos; + unsigned long flags; + int result = -EIO; + + init_completion(&completion); + + /* tasklet send may be called from both interrupt or thread + * context, therefore protect queue operation by spinlock + */ + spin_lock_irqsave(&ipc_task->q_lock, flags); + + pos = ipc_task->q_wpos; + nextpos = (pos + 1) % IPC_THREAD_QUEUE_SIZE; + + /* Get next queue position. */ + if (nextpos != ipc_task->q_rpos) { + /* Get the reference to the queue element and save the passed + * values. + */ + ipc_task->args[pos].arg = arg; + ipc_task->args[pos].msg = msg; + ipc_task->args[pos].func = func; + ipc_task->args[pos].ipc_imem = ipc_imem; + ipc_task->args[pos].size = size; + ipc_task->args[pos].is_copy = is_copy; + ipc_task->args[pos].completion = wait ? &completion : NULL; + ipc_task->args[pos].response = -1; + + /* apply write barrier so that ipc_task->q_rpos elements + * are updated before ipc_task->q_wpos is being updated. + */ + smp_wmb(); + + /* Update the status of the free queue space. */ + ipc_task->q_wpos = nextpos; + result = 0; + } + + spin_unlock_irqrestore(&ipc_task->q_lock, flags); + + if (result == 0) { + tasklet_schedule(ipc_tasklet); + + if (wait) { + wait_for_completion(&completion); + result = ipc_task->args[pos].response; + } + } else { + dev_err(ipc_imem->ipc_task->dev, "queue is full"); + } + + return result; +} + +int ipc_task_queue_send_task(struct iosm_imem *imem, + int (*func)(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size), + int arg, void *msg, size_t size, bool wait) +{ + bool is_copy = false; + void *copy = msg; + int ret = -ENOMEM; + + if (size > 0) { + copy = kmemdup(msg, size, GFP_ATOMIC); + if (!copy) + goto out; + + is_copy = true; + } + + ret = ipc_task_queue_add_task(imem, arg, copy, func, + size, is_copy, wait); + if (ret < 0) { + dev_err(imem->ipc_task->dev, + "add task failed for %ps %d, %p, %zu, %d", func, arg, + copy, size, is_copy); + if (is_copy) + kfree(copy); + goto out; + } + + ret = 0; +out: + return ret; +} + +int ipc_task_init(struct ipc_task *ipc_task) +{ + struct ipc_task_queue *ipc_queue = &ipc_task->ipc_queue; + + ipc_task->ipc_tasklet = kzalloc(sizeof(*ipc_task->ipc_tasklet), + GFP_KERNEL); + + if (!ipc_task->ipc_tasklet) + return -ENOMEM; + + /* Initialize the spinlock needed to protect the message queue of the + * ipc_task + */ + spin_lock_init(&ipc_queue->q_lock); + + tasklet_init(ipc_task->ipc_tasklet, ipc_task_queue_handler, + (unsigned long)ipc_queue); + return 0; +} + +void ipc_task_deinit(struct ipc_task *ipc_task) +{ + tasklet_kill(ipc_task->ipc_tasklet); + + kfree(ipc_task->ipc_tasklet); + /* This will free/complete any outstanding messages, + * without calling the actual handler + */ + ipc_task_queue_cleanup(&ipc_task->ipc_queue); +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_task_queue.h b/drivers/net/wwan/iosm/iosm_ipc_task_queue.h new file mode 100644 index 000000000000..df6e9cd925a9 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_task_queue.h @@ -0,0 +1,97 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_TASK_QUEUE_H +#define IOSM_IPC_TASK_QUEUE_H + +/* Number of available element for the input message queue of the IPC + * ipc_task + */ +#define IPC_THREAD_QUEUE_SIZE 256 + +/** + * struct ipc_task_queue_args - Struct for Task queue elements + * @ipc_imem: Pointer to struct iosm_imem + * @msg: Message argument for tasklet function. (optional, can be NULL) + * @completion: OS object used to wait for the tasklet function to finish for + * synchronous calls + * @func: Function to be called in tasklet (tl) context + * @arg: Generic integer argument for tasklet function (optional) + * @size: Message size argument for tasklet function (optional) + * @response: Return code of tasklet function for synchronous calls + * @is_copy: Is true if msg contains a pointer to a copy of the original msg + * for async. calls that needs to be freed once the tasklet returns + */ +struct ipc_task_queue_args { + struct iosm_imem *ipc_imem; + void *msg; + struct completion *completion; + int (*func)(struct iosm_imem *ipc_imem, int arg, void *msg, + size_t size); + int arg; + size_t size; + int response; + u8 is_copy:1; +}; + +/** + * struct ipc_task_queue - Struct for Task queue + * @q_lock: Protect the message queue of the ipc ipc_task + * @args: Message queue of the IPC ipc_task + * @q_rpos: First queue element to process. + * @q_wpos: First free element of the input queue. + */ +struct ipc_task_queue { + spinlock_t q_lock; /* for atomic operation on queue */ + struct ipc_task_queue_args args[IPC_THREAD_QUEUE_SIZE]; + unsigned int q_rpos; + unsigned int q_wpos; +}; + +/** + * struct ipc_task - Struct for Task + * @dev: Pointer to device structure + * @ipc_tasklet: Tasklet for serialized work offload + * from interrupts and OS callbacks + * @ipc_queue: Task for entry into ipc task queue + */ +struct ipc_task { + struct device *dev; + struct tasklet_struct *ipc_tasklet; + struct ipc_task_queue ipc_queue; +}; + +/** + * ipc_task_init - Allocate a tasklet + * @ipc_task: Pointer to ipc_task structure + * Returns: 0 on success and failure value on error. + */ +int ipc_task_init(struct ipc_task *ipc_task); + +/** + * ipc_task_deinit - Free a tasklet, invalidating its pointer. + * @ipc_task: Pointer to ipc_task structure + */ +void ipc_task_deinit(struct ipc_task *ipc_task); + +/** + * ipc_task_queue_send_task - Synchronously/Asynchronously call a function in + * tasklet context. + * @imem: Pointer to iosm_imem struct + * @func: Function to be called in tasklet context + * @arg: Integer argument for func + * @msg: Message pointer argument for func + * @size: Size argument for func + * @wait: if true wait for result + * + * Returns: Result value returned by func or failure value if func could not + * be called. + */ +int ipc_task_queue_send_task(struct iosm_imem *imem, + int (*func)(struct iosm_imem *ipc_imem, int arg, + void *msg, size_t size), + int arg, void *msg, size_t size, bool wait); + +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_uevent.c b/drivers/net/wwan/iosm/iosm_ipc_uevent.c new file mode 100644 index 000000000000..2229d752926c --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_uevent.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include +#include +#include + +#include "iosm_ipc_uevent.h" + +/* Update the uevent in work queue context */ +static void ipc_uevent_work(struct work_struct *data) +{ + struct ipc_uevent_info *info; + char *envp[2] = { NULL, NULL }; + + info = container_of(data, struct ipc_uevent_info, work); + + envp[0] = info->uevent; + + if (kobject_uevent_env(&info->dev->kobj, KOBJ_CHANGE, envp)) + pr_err("uevent %s failed to sent", info->uevent); + + kfree(info); +} + +void ipc_uevent_send(struct device *dev, char *uevent) +{ + struct ipc_uevent_info *info = kzalloc(sizeof(*info), GFP_ATOMIC); + + if (!info) + return; + + /* Initialize the kernel work queue */ + INIT_WORK(&info->work, ipc_uevent_work); + + /* Store the device and event information */ + info->dev = dev; + snprintf(info->uevent, MAX_UEVENT_LEN, "%s: %s", dev_name(dev), uevent); + + /* Schedule uevent in process context using work queue */ + schedule_work(&info->work); +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_uevent.h b/drivers/net/wwan/iosm/iosm_ipc_uevent.h new file mode 100644 index 000000000000..2e45c051b5f4 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_uevent.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_UEVENT_H +#define IOSM_IPC_UEVENT_H + +/* Baseband event strings */ +#define UEVENT_MDM_NOT_READY "MDM_NOT_READY" +#define UEVENT_ROM_READY "ROM_READY" +#define UEVENT_MDM_READY "MDM_READY" +#define UEVENT_CRASH "CRASH" +#define UEVENT_CD_READY "CD_READY" +#define UEVENT_CD_READY_LINK_DOWN "CD_READY_LINK_DOWN" +#define UEVENT_MDM_TIMEOUT "MDM_TIMEOUT" + +/* Maximum length of user events */ +#define MAX_UEVENT_LEN 64 + +/** + * struct ipc_uevent_info - Uevent information structure. + * @dev: Pointer to device structure + * @uevent: Uevent information + * @work: Uevent work struct + */ +struct ipc_uevent_info { + struct device *dev; + char uevent[MAX_UEVENT_LEN]; + struct work_struct work; +}; + +/** + * ipc_uevent_send - Send modem event to user space. + * @dev: Generic device pointer + * @uevent: Uevent information + * + */ +void ipc_uevent_send(struct device *dev, char *uevent); + +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c new file mode 100644 index 000000000000..c999c64001f4 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -0,0 +1,340 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-21 Intel Corporation. + */ + +#include +#include +#include +#include +#include + +#include "iosm_ipc_chnl_cfg.h" +#include "iosm_ipc_imem_ops.h" +#include "iosm_ipc_wwan.h" + +#define IOSM_IP_TYPE_MASK 0xF0 +#define IOSM_IP_TYPE_IPV4 0x40 +#define IOSM_IP_TYPE_IPV6 0x60 + +#define IOSM_IF_ID_PAYLOAD 2 + +/** + * struct iosm_netdev_priv - netdev WWAN driver specific private data + * @ipc_wwan: Pointer to iosm_wwan struct + * @netdev: Pointer to network interface device structure + * @if_id: Interface id for device. + * @ch_id: IPC channel number for which interface device is created. + */ +struct iosm_netdev_priv { + struct iosm_wwan *ipc_wwan; + struct net_device *netdev; + int if_id; + int ch_id; +}; + +/** + * struct iosm_wwan - This structure contains information about WWAN root device + * and interface to the IPC layer. + * @ipc_imem: Pointer to imem data-struct + * @sub_netlist: List of active netdevs + * @dev: Pointer device structure + * @if_mutex: Mutex used for add and remove interface id + */ +struct iosm_wwan { + struct iosm_imem *ipc_imem; + struct iosm_netdev_priv __rcu *sub_netlist[IP_MUX_SESSION_END + 1]; + struct device *dev; + struct mutex if_mutex; /* Mutex used for add and remove interface id */ +}; + +/* Bring-up the wwan net link */ +static int ipc_wwan_link_open(struct net_device *netdev) +{ + struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev); + struct iosm_wwan *ipc_wwan = priv->ipc_wwan; + int if_id = priv->if_id; + int ret; + + if (if_id < IP_MUX_SESSION_START || + if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist)) + return -EINVAL; + + mutex_lock(&ipc_wwan->if_mutex); + + /* get channel id */ + priv->ch_id = ipc_imem_sys_wwan_open(ipc_wwan->ipc_imem, if_id); + + if (priv->ch_id < 0) { + dev_err(ipc_wwan->dev, + "cannot connect wwan0 & id %d to the IPC mem layer", + if_id); + ret = -ENODEV; + goto out; + } + + /* enable tx path, DL data may follow */ + netif_start_queue(netdev); + + dev_dbg(ipc_wwan->dev, "Channel id %d allocated to if_id %d", + priv->ch_id, priv->if_id); + + ret = 0; +out: + mutex_unlock(&ipc_wwan->if_mutex); + return ret; +} + +/* Bring-down the wwan net link */ +static int ipc_wwan_link_stop(struct net_device *netdev) +{ + struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev); + + netif_stop_queue(netdev); + + mutex_lock(&priv->ipc_wwan->if_mutex); + ipc_imem_sys_wwan_close(priv->ipc_wwan->ipc_imem, priv->if_id, + priv->ch_id); + priv->ch_id = -1; + mutex_unlock(&priv->ipc_wwan->if_mutex); + + return 0; +} + +/* Transmit a packet */ +static int ipc_wwan_link_transmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev); + struct iosm_wwan *ipc_wwan = priv->ipc_wwan; + int if_id = priv->if_id; + int ret; + + /* Interface IDs from 1 to 8 are for IP data + * & from 257 to 261 are for non-IP data + */ + if (if_id < IP_MUX_SESSION_START || + if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist)) + return -EINVAL; + + /* Send the SKB to device for transmission */ + ret = ipc_imem_sys_wwan_transmit(ipc_wwan->ipc_imem, + if_id, priv->ch_id, skb); + + /* Return code of zero is success */ + if (ret == 0) { + ret = NETDEV_TX_OK; + } else if (ret == -EBUSY) { + ret = NETDEV_TX_BUSY; + dev_err(ipc_wwan->dev, "unable to push packets"); + } else { + goto exit; + } + + return ret; + +exit: + /* Log any skb drop */ + if (if_id) + dev_dbg(ipc_wwan->dev, "skb dropped. IF_ID: %d, ret: %d", if_id, + ret); + + dev_kfree_skb_any(skb); + return ret; +} + +/* Ops structure for wwan net link */ +static const struct net_device_ops ipc_inm_ops = { + .ndo_open = ipc_wwan_link_open, + .ndo_stop = ipc_wwan_link_stop, + .ndo_start_xmit = ipc_wwan_link_transmit, +}; + +/* Setup function for creating new net link */ +static void ipc_wwan_setup(struct net_device *iosm_dev) +{ + iosm_dev->header_ops = NULL; + iosm_dev->hard_header_len = 0; + iosm_dev->priv_flags |= IFF_NO_QUEUE; + + iosm_dev->type = ARPHRD_NONE; + iosm_dev->min_mtu = ETH_MIN_MTU; + iosm_dev->max_mtu = ETH_MAX_MTU; + + iosm_dev->flags = IFF_POINTOPOINT | IFF_NOARP; + + iosm_dev->netdev_ops = &ipc_inm_ops; +} + +/* Create new wwan net link */ +static int ipc_wwan_newlink(void *ctxt, struct net_device *dev, + u32 if_id, struct netlink_ext_ack *extack) +{ + struct iosm_wwan *ipc_wwan = ctxt; + struct iosm_netdev_priv *priv; + int err; + + if (if_id < IP_MUX_SESSION_START || + if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist)) + return -EINVAL; + + priv = wwan_netdev_drvpriv(dev); + priv->if_id = if_id; + priv->netdev = dev; + priv->ipc_wwan = ipc_wwan; + + mutex_lock(&ipc_wwan->if_mutex); + if (rcu_access_pointer(ipc_wwan->sub_netlist[if_id])) { + err = -EBUSY; + goto out_unlock; + } + + err = register_netdevice(dev); + if (err) + goto out_unlock; + + rcu_assign_pointer(ipc_wwan->sub_netlist[if_id], priv); + mutex_unlock(&ipc_wwan->if_mutex); + + netif_device_attach(dev); + + return 0; + +out_unlock: + mutex_unlock(&ipc_wwan->if_mutex); + return err; +} + +static void ipc_wwan_dellink(void *ctxt, struct net_device *dev, + struct list_head *head) +{ + struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(dev); + struct iosm_wwan *ipc_wwan = ctxt; + int if_id = priv->if_id; + + if (WARN_ON(if_id < IP_MUX_SESSION_START || + if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist))) + return; + + mutex_lock(&ipc_wwan->if_mutex); + + if (WARN_ON(rcu_access_pointer(ipc_wwan->sub_netlist[if_id]) != priv)) + goto unlock; + + RCU_INIT_POINTER(ipc_wwan->sub_netlist[if_id], NULL); + /* unregistering includes synchronize_net() */ + unregister_netdevice(dev); + +unlock: + mutex_unlock(&ipc_wwan->if_mutex); +} + +static const struct wwan_ops iosm_wwan_ops = { + .priv_size = sizeof(struct iosm_netdev_priv), + .setup = ipc_wwan_setup, + .newlink = ipc_wwan_newlink, + .dellink = ipc_wwan_dellink, +}; + +int ipc_wwan_receive(struct iosm_wwan *ipc_wwan, struct sk_buff *skb_arg, + bool dss, int if_id) +{ + struct sk_buff *skb = skb_arg; + struct net_device_stats *stats; + struct iosm_netdev_priv *priv; + int ret; + + if ((skb->data[0] & IOSM_IP_TYPE_MASK) == IOSM_IP_TYPE_IPV4) + skb->protocol = htons(ETH_P_IP); + else if ((skb->data[0] & IOSM_IP_TYPE_MASK) == + IOSM_IP_TYPE_IPV6) + skb->protocol = htons(ETH_P_IPV6); + + skb->pkt_type = PACKET_HOST; + + if (if_id < (IP_MUX_SESSION_START - 1) || + if_id > (IP_MUX_SESSION_END - 1)) { + ret = -EINVAL; + goto free; + } + + rcu_read_lock(); + priv = rcu_dereference(ipc_wwan->sub_netlist[if_id]); + if (!priv) { + ret = -EINVAL; + goto unlock; + } + skb->dev = priv->netdev; + stats = &priv->netdev->stats; + stats->rx_packets++; + stats->rx_bytes += skb->len; + + ret = netif_rx(skb); + skb = NULL; +unlock: + rcu_read_unlock(); +free: + dev_kfree_skb(skb); + return ret; +} + +void ipc_wwan_tx_flowctrl(struct iosm_wwan *ipc_wwan, int if_id, bool on) +{ + struct net_device *netdev; + struct iosm_netdev_priv *priv; + bool is_tx_blk; + + rcu_read_lock(); + priv = rcu_dereference(ipc_wwan->sub_netlist[if_id]); + if (!priv) { + rcu_read_unlock(); + return; + } + + netdev = priv->netdev; + + is_tx_blk = netif_queue_stopped(netdev); + + if (on) + dev_dbg(ipc_wwan->dev, "session id[%d]: flowctrl enable", + if_id); + + if (on && !is_tx_blk) + netif_stop_queue(netdev); + else if (!on && is_tx_blk) + netif_wake_queue(netdev); + rcu_read_unlock(); +} + +struct iosm_wwan *ipc_wwan_init(struct iosm_imem *ipc_imem, struct device *dev) +{ + struct iosm_wwan *ipc_wwan; + + ipc_wwan = kzalloc(sizeof(*ipc_wwan), GFP_KERNEL); + if (!ipc_wwan) + return NULL; + + ipc_wwan->dev = dev; + ipc_wwan->ipc_imem = ipc_imem; + + /* WWAN core will create a netdev for the default IP MUX channel */ + if (wwan_register_ops(ipc_wwan->dev, &iosm_wwan_ops, ipc_wwan, + IP_MUX_SESSION_DEFAULT)) { + kfree(ipc_wwan); + return NULL; + } + + mutex_init(&ipc_wwan->if_mutex); + + return ipc_wwan; +} + +void ipc_wwan_deinit(struct iosm_wwan *ipc_wwan) +{ + /* This call will remove all child netdev(s) */ + wwan_unregister_ops(ipc_wwan->dev); + + mutex_destroy(&ipc_wwan->if_mutex); + + kfree(ipc_wwan); +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.h b/drivers/net/wwan/iosm/iosm_ipc_wwan.h new file mode 100644 index 000000000000..4925f22dff0a --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-21 Intel Corporation. + */ + +#ifndef IOSM_IPC_WWAN_H +#define IOSM_IPC_WWAN_H + +/** + * ipc_wwan_init - Allocate, Init and register WWAN device + * @ipc_imem: Pointer to imem data-struct + * @dev: Pointer to device structure + * + * Returns: Pointer to instance on success else NULL + */ +struct iosm_wwan *ipc_wwan_init(struct iosm_imem *ipc_imem, struct device *dev); + +/** + * ipc_wwan_deinit - Unregister and free WWAN device, clear pointer + * @ipc_wwan: Pointer to wwan instance data + */ +void ipc_wwan_deinit(struct iosm_wwan *ipc_wwan); + +/** + * ipc_wwan_receive - Receive a downlink packet from CP. + * @ipc_wwan: Pointer to wwan instance + * @skb_arg: Pointer to struct sk_buff + * @dss: Set to true if interafce id is from 257 to 261, + * else false + * @if_id: Interface ID + * + * Return: 0 on success and failure value on error + */ +int ipc_wwan_receive(struct iosm_wwan *ipc_wwan, struct sk_buff *skb_arg, + bool dss, int if_id); + +/** + * ipc_wwan_tx_flowctrl - Enable/Disable TX flow control + * @ipc_wwan: Pointer to wwan instance + * @id: Ipc mux channel session id + * @on: if true then flow ctrl would be enabled else disable + * + */ +void ipc_wwan_tx_flowctrl(struct iosm_wwan *ipc_wwan, int id, bool on); + +/** + * ipc_wwan_is_tx_stopped - Checks if Tx stopped for a Interface id. + * @ipc_wwan: Pointer to wwan instance + * @id: Ipc mux channel session id + * + * Return: true if stopped, false otherwise + */ +bool ipc_wwan_is_tx_stopped(struct iosm_wwan *ipc_wwan, int id); + +#endif diff --git a/drivers/net/wwan/rpmsg_wwan_ctrl.c b/drivers/net/wwan/rpmsg_wwan_ctrl.c new file mode 100644 index 000000000000..31c24420ab2e --- /dev/null +++ b/drivers/net/wwan/rpmsg_wwan_ctrl.c @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2021, Stephan Gerhold */ +#include +#include +#include +#include +#include +#include + +struct rpmsg_wwan_dev { + /* Lower level is a rpmsg dev, upper level is a wwan port */ + struct rpmsg_device *rpdev; + struct wwan_port *wwan_port; + struct rpmsg_endpoint *ept; +}; + +static int rpmsg_wwan_ctrl_callback(struct rpmsg_device *rpdev, + void *buf, int len, void *priv, u32 src) +{ + struct rpmsg_wwan_dev *rpwwan = priv; + struct sk_buff *skb; + + skb = alloc_skb(len, GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + skb_put_data(skb, buf, len); + wwan_port_rx(rpwwan->wwan_port, skb); + return 0; +} + +static int rpmsg_wwan_ctrl_start(struct wwan_port *port) +{ + struct rpmsg_wwan_dev *rpwwan = wwan_port_get_drvdata(port); + struct rpmsg_channel_info chinfo = { + .src = rpwwan->rpdev->src, + .dst = RPMSG_ADDR_ANY, + }; + + strncpy(chinfo.name, rpwwan->rpdev->id.name, RPMSG_NAME_SIZE); + rpwwan->ept = rpmsg_create_ept(rpwwan->rpdev, rpmsg_wwan_ctrl_callback, + rpwwan, chinfo); + if (!rpwwan->ept) + return -EREMOTEIO; + + return 0; +} + +static void rpmsg_wwan_ctrl_stop(struct wwan_port *port) +{ + struct rpmsg_wwan_dev *rpwwan = wwan_port_get_drvdata(port); + + rpmsg_destroy_ept(rpwwan->ept); + rpwwan->ept = NULL; +} + +static int rpmsg_wwan_ctrl_tx(struct wwan_port *port, struct sk_buff *skb) +{ + struct rpmsg_wwan_dev *rpwwan = wwan_port_get_drvdata(port); + int ret; + + ret = rpmsg_trysend(rpwwan->ept, skb->data, skb->len); + if (ret) + return ret; + + consume_skb(skb); + return 0; +} + +static int rpmsg_wwan_ctrl_tx_blocking(struct wwan_port *port, struct sk_buff *skb) +{ + struct rpmsg_wwan_dev *rpwwan = wwan_port_get_drvdata(port); + int ret; + + ret = rpmsg_send(rpwwan->ept, skb->data, skb->len); + if (ret) + return ret; + + consume_skb(skb); + return 0; +} + +static __poll_t rpmsg_wwan_ctrl_tx_poll(struct wwan_port *port, + struct file *filp, poll_table *wait) +{ + struct rpmsg_wwan_dev *rpwwan = wwan_port_get_drvdata(port); + + return rpmsg_poll(rpwwan->ept, filp, wait); +} + +static const struct wwan_port_ops rpmsg_wwan_pops = { + .start = rpmsg_wwan_ctrl_start, + .stop = rpmsg_wwan_ctrl_stop, + .tx = rpmsg_wwan_ctrl_tx, + .tx_blocking = rpmsg_wwan_ctrl_tx_blocking, + .tx_poll = rpmsg_wwan_ctrl_tx_poll, +}; + +static struct device *rpmsg_wwan_find_parent(struct device *dev) +{ + /* Select first platform device as parent for the WWAN ports. + * On Qualcomm platforms this is usually the platform device that + * represents the modem remote processor. This might need to be + * adjusted when adding device IDs for other platforms. + */ + for (dev = dev->parent; dev; dev = dev->parent) { + if (dev_is_platform(dev)) + return dev; + } + return NULL; +} + +static int rpmsg_wwan_ctrl_probe(struct rpmsg_device *rpdev) +{ + struct rpmsg_wwan_dev *rpwwan; + struct wwan_port *port; + struct device *parent; + + parent = rpmsg_wwan_find_parent(&rpdev->dev); + if (!parent) + return -ENODEV; + + rpwwan = devm_kzalloc(&rpdev->dev, sizeof(*rpwwan), GFP_KERNEL); + if (!rpwwan) + return -ENOMEM; + + rpwwan->rpdev = rpdev; + dev_set_drvdata(&rpdev->dev, rpwwan); + + /* Register as a wwan port, id.driver_data contains wwan port type */ + port = wwan_create_port(parent, rpdev->id.driver_data, + &rpmsg_wwan_pops, rpwwan); + if (IS_ERR(port)) + return PTR_ERR(port); + + rpwwan->wwan_port = port; + + return 0; +}; + +static void rpmsg_wwan_ctrl_remove(struct rpmsg_device *rpdev) +{ + struct rpmsg_wwan_dev *rpwwan = dev_get_drvdata(&rpdev->dev); + + wwan_remove_port(rpwwan->wwan_port); +} + +static const struct rpmsg_device_id rpmsg_wwan_ctrl_id_table[] = { + /* RPMSG channels for Qualcomm SoCs with integrated modem */ + { .name = "DATA5_CNTL", .driver_data = WWAN_PORT_QMI }, + { .name = "DATA4", .driver_data = WWAN_PORT_AT }, + {}, +}; +MODULE_DEVICE_TABLE(rpmsg, rpmsg_wwan_ctrl_id_table); + +static struct rpmsg_driver rpmsg_wwan_ctrl_driver = { + .drv.name = "rpmsg_wwan_ctrl", + .id_table = rpmsg_wwan_ctrl_id_table, + .probe = rpmsg_wwan_ctrl_probe, + .remove = rpmsg_wwan_ctrl_remove, +}; +module_rpmsg_driver(rpmsg_wwan_ctrl_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("RPMSG WWAN CTRL Driver"); +MODULE_AUTHOR("Stephan Gerhold "); diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index cff04e532c1e..3e16c318e705 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -12,9 +12,13 @@ #include #include #include +#include #include +#include +#include -#define WWAN_MAX_MINORS 256 /* 256 minors allowed with register_chrdev() */ +/* Maximum number of minors in use */ +#define WWAN_MAX_MINORS (1 << MINORBITS) static DEFINE_MUTEX(wwan_register_lock); /* WWAN device create|remove lock */ static DEFINE_IDA(minors); /* minors for WWAN port chardevs */ @@ -34,11 +38,15 @@ static int wwan_major; * @id: WWAN device unique ID. * @dev: Underlying device. * @port_id: Current available port ID to pick. + * @ops: wwan device ops + * @ops_ctxt: context to pass to ops */ struct wwan_device { unsigned int id; struct device dev; atomic_t port_id; + const struct wwan_ops *ops; + void *ops_ctxt; }; /** @@ -51,6 +59,8 @@ struct wwan_device { * @dev: Underlying device * @rxq: Buffer inbound queue * @waitqueue: The waitqueue for port fops (read/write/poll) + * @data_lock: Port specific data access serialization + * @at_data: AT port specific data */ struct wwan_port { enum wwan_port_type type; @@ -61,8 +71,29 @@ struct wwan_port { struct device dev; struct sk_buff_head rxq; wait_queue_head_t waitqueue; + struct mutex data_lock; /* Port specific data access serialization */ + union { + struct { + struct ktermios termios; + int mdmbits; + } at_data; + }; }; +static ssize_t index_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct wwan_device *wwan = to_wwan_dev(dev); + + return sprintf(buf, "%d\n", wwan->id); +} +static DEVICE_ATTR_RO(index); + +static struct attribute *wwan_dev_attrs[] = { + &dev_attr_index.attr, + NULL, +}; +ATTRIBUTE_GROUPS(wwan_dev); + static void wwan_dev_destroy(struct device *dev) { struct wwan_device *wwandev = to_wwan_dev(dev); @@ -74,11 +105,13 @@ static void wwan_dev_destroy(struct device *dev) static const struct device_type wwan_dev_type = { .name = "wwan_dev", .release = wwan_dev_destroy, + .groups = wwan_dev_groups, }; static int wwan_dev_parent_match(struct device *dev, const void *parent) { - return (dev->type == &wwan_dev_type && dev->parent == parent); + return (dev->type == &wwan_dev_type && + (dev->parent == parent || dev == parent)); } static struct wwan_device *wwan_dev_get_by_parent(struct device *parent) @@ -92,6 +125,23 @@ static struct wwan_device *wwan_dev_get_by_parent(struct device *parent) return to_wwan_dev(dev); } +static int wwan_dev_name_match(struct device *dev, const void *name) +{ + return dev->type == &wwan_dev_type && + strcmp(dev_name(dev), name) == 0; +} + +static struct wwan_device *wwan_dev_get_by_name(const char *name) +{ + struct device *dev; + + dev = class_find_device(wwan_class, NULL, name, wwan_dev_name_match); + if (!dev) + return ERR_PTR(-ENODEV); + + return to_wwan_dev(dev); +} + /* This function allocates and registers a new WWAN device OR if a WWAN device * already exist for the given parent, it gets a reference and return it. * This function is not exported (for now), it is called indirectly via @@ -156,9 +206,14 @@ static void wwan_remove_dev(struct wwan_device *wwandev) /* WWAN device is created and registered (get+add) along with its first * child port, and subsequent port registrations only grab a reference * (get). The WWAN device must then be unregistered (del+put) along with - * its latest port, and reference simply dropped (put) otherwise. + * its last port, and reference simply dropped (put) otherwise. In the + * same fashion, we must not unregister it when the ops are still there. */ - ret = device_for_each_child(&wwandev->dev, NULL, is_wwan_child); + if (wwandev->ops) + ret = 1; + else + ret = device_for_each_child(&wwandev->dev, NULL, is_wwan_child); + if (!ret) device_unregister(&wwandev->dev); else @@ -169,12 +224,53 @@ static void wwan_remove_dev(struct wwan_device *wwandev) /* ------- WWAN port management ------- */ +static const struct { + const char * const name; /* Port type name */ + const char * const devsuf; /* Port devce name suffix */ +} wwan_port_types[WWAN_PORT_MAX + 1] = { + [WWAN_PORT_AT] = { + .name = "AT", + .devsuf = "at", + }, + [WWAN_PORT_MBIM] = { + .name = "MBIM", + .devsuf = "mbim", + }, + [WWAN_PORT_QMI] = { + .name = "QMI", + .devsuf = "qmi", + }, + [WWAN_PORT_QCDM] = { + .name = "QCDM", + .devsuf = "qcdm", + }, + [WWAN_PORT_FIREHOSE] = { + .name = "FIREHOSE", + .devsuf = "firehose", + }, +}; + +static ssize_t type_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct wwan_port *port = to_wwan_port(dev); + + return sprintf(buf, "%s\n", wwan_port_types[port->type].name); +} +static DEVICE_ATTR_RO(type); + +static struct attribute *wwan_port_attrs[] = { + &dev_attr_type.attr, + NULL, +}; +ATTRIBUTE_GROUPS(wwan_port); + static void wwan_port_destroy(struct device *dev) { struct wwan_port *port = to_wwan_port(dev); ida_free(&minors, MINOR(port->dev.devt)); - skb_queue_purge(&port->rxq); + mutex_destroy(&port->data_lock); mutex_destroy(&port->ops_lock); kfree(port); } @@ -182,6 +278,7 @@ static void wwan_port_destroy(struct device *dev) static const struct device_type wwan_port_dev_type = { .name = "wwan_port", .release = wwan_port_destroy, + .groups = wwan_port_groups, }; static int wwan_port_minor_match(struct device *dev, const void *minor) @@ -201,14 +298,55 @@ static struct wwan_port *wwan_port_get_by_minor(unsigned int minor) return to_wwan_port(dev); } -/* Keep aligned with wwan_port_type enum */ -static const char * const wwan_port_type_str[] = { - "AT", - "MBIM", - "QMI", - "QCDM", - "FIREHOSE" -}; +/* Allocate and set unique name based on passed format + * + * Name allocation approach is highly inspired by the __dev_alloc_name() + * function. + * + * To avoid names collision, the caller must prevent the new port device + * registration as well as concurrent invocation of this function. + */ +static int __wwan_port_dev_assign_name(struct wwan_port *port, const char *fmt) +{ + struct wwan_device *wwandev = to_wwan_dev(port->dev.parent); + const unsigned int max_ports = PAGE_SIZE * 8; + struct class_dev_iter iter; + unsigned long *idmap; + struct device *dev; + char buf[0x20]; + int id; + + idmap = (unsigned long *)get_zeroed_page(GFP_KERNEL); + if (!idmap) + return -ENOMEM; + + /* Collect ids of same name format ports */ + class_dev_iter_init(&iter, wwan_class, NULL, &wwan_port_dev_type); + while ((dev = class_dev_iter_next(&iter))) { + if (dev->parent != &wwandev->dev) + continue; + if (sscanf(dev_name(dev), fmt, &id) != 1) + continue; + if (id < 0 || id >= max_ports) + continue; + set_bit(id, idmap); + } + class_dev_iter_exit(&iter); + + /* Allocate unique id */ + id = find_first_zero_bit(idmap, max_ports); + free_page((unsigned long)idmap); + + snprintf(buf, sizeof(buf), fmt, id); /* Name generation */ + + dev = device_find_child_by_name(&wwandev->dev, buf); + if (dev) { + put_device(dev); + return -ENFILE; + } + + return dev_set_name(&port->dev, buf); +} struct wwan_port *wwan_create_port(struct device *parent, enum wwan_port_type type, @@ -218,8 +356,9 @@ struct wwan_port *wwan_create_port(struct device *parent, struct wwan_device *wwandev; struct wwan_port *port; int minor, err = -ENOMEM; + char namefmt[0x20]; - if (type >= WWAN_PORT_MAX || !ops) + if (type > WWAN_PORT_MAX || !ops) return ERR_PTR(-EINVAL); /* A port is always a child of a WWAN device, retrieve (allocate or @@ -245,6 +384,7 @@ struct wwan_port *wwan_create_port(struct device *parent, mutex_init(&port->ops_lock); skb_queue_head_init(&port->rxq); init_waitqueue_head(&port->waitqueue); + mutex_init(&port->data_lock); port->dev.parent = &wwandev->dev; port->dev.class = wwan_class; @@ -252,12 +392,18 @@ struct wwan_port *wwan_create_port(struct device *parent, port->dev.devt = MKDEV(wwan_major, minor); dev_set_drvdata(&port->dev, drvdata); - /* create unique name based on wwan device id, port index and type */ - dev_set_name(&port->dev, "wwan%up%u%s", wwandev->id, - atomic_inc_return(&wwandev->port_id), - wwan_port_type_str[port->type]); + /* allocate unique name based on wwan device id, port type and number */ + snprintf(namefmt, sizeof(namefmt), "wwan%u%s%%d", wwandev->id, + wwan_port_types[port->type].devsuf); + /* Serialize ports registration */ + mutex_lock(&wwan_register_lock); + + __wwan_port_dev_assign_name(port, namefmt); err = device_register(&port->dev); + + mutex_unlock(&wwan_register_lock); + if (err) goto error_put_device; @@ -346,12 +492,16 @@ static void wwan_port_op_stop(struct wwan_port *port) { mutex_lock(&port->ops_lock); port->start_count--; - if (port->ops && !port->start_count) - port->ops->stop(port); + if (!port->start_count) { + if (port->ops) + port->ops->stop(port); + skb_queue_purge(&port->rxq); + } mutex_unlock(&port->ops_lock); } -static int wwan_port_op_tx(struct wwan_port *port, struct sk_buff *skb) +static int wwan_port_op_tx(struct wwan_port *port, struct sk_buff *skb, + bool nonblock) { int ret; @@ -361,7 +511,10 @@ static int wwan_port_op_tx(struct wwan_port *port, struct sk_buff *skb) goto out_unlock; } - ret = port->ops->tx(port, skb); + if (nonblock || !port->ops->tx_blocking) + ret = port->ops->tx(port, skb); + else + ret = port->ops->tx_blocking(port, skb); out_unlock: mutex_unlock(&port->ops_lock); @@ -488,7 +641,7 @@ static ssize_t wwan_port_fops_write(struct file *filp, const char __user *buf, return -EFAULT; } - ret = wwan_port_op_tx(port, skb); + ret = wwan_port_op_tx(port, skb, !!(filp->f_flags & O_NONBLOCK)); if (ret) { kfree_skb(skb); return ret; @@ -504,16 +657,124 @@ static __poll_t wwan_port_fops_poll(struct file *filp, poll_table *wait) poll_wait(filp, &port->waitqueue, wait); - if (!is_write_blocked(port)) + mutex_lock(&port->ops_lock); + if (port->ops && port->ops->tx_poll) + mask |= port->ops->tx_poll(port, filp, wait); + else if (!is_write_blocked(port)) mask |= EPOLLOUT | EPOLLWRNORM; if (!is_read_blocked(port)) mask |= EPOLLIN | EPOLLRDNORM; if (!port->ops) mask |= EPOLLHUP | EPOLLERR; + mutex_unlock(&port->ops_lock); return mask; } +/* Implements minimalistic stub terminal IOCTLs support */ +static long wwan_port_fops_at_ioctl(struct wwan_port *port, unsigned int cmd, + unsigned long arg) +{ + int ret = 0; + + mutex_lock(&port->data_lock); + + switch (cmd) { + case TCFLSH: + break; + + case TCGETS: + if (copy_to_user((void __user *)arg, &port->at_data.termios, + sizeof(struct termios))) + ret = -EFAULT; + break; + + case TCSETS: + case TCSETSW: + case TCSETSF: + if (copy_from_user(&port->at_data.termios, (void __user *)arg, + sizeof(struct termios))) + ret = -EFAULT; + break; + +#ifdef TCGETS2 + case TCGETS2: + if (copy_to_user((void __user *)arg, &port->at_data.termios, + sizeof(struct termios2))) + ret = -EFAULT; + break; + + case TCSETS2: + case TCSETSW2: + case TCSETSF2: + if (copy_from_user(&port->at_data.termios, (void __user *)arg, + sizeof(struct termios2))) + ret = -EFAULT; + break; +#endif + + case TIOCMGET: + ret = put_user(port->at_data.mdmbits, (int __user *)arg); + break; + + case TIOCMSET: + case TIOCMBIC: + case TIOCMBIS: { + int mdmbits; + + if (copy_from_user(&mdmbits, (int __user *)arg, sizeof(int))) { + ret = -EFAULT; + break; + } + if (cmd == TIOCMBIC) + port->at_data.mdmbits &= ~mdmbits; + else if (cmd == TIOCMBIS) + port->at_data.mdmbits |= mdmbits; + else + port->at_data.mdmbits = mdmbits; + break; + } + + default: + ret = -ENOIOCTLCMD; + } + + mutex_unlock(&port->data_lock); + + return ret; +} + +static long wwan_port_fops_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + struct wwan_port *port = filp->private_data; + int res; + + if (port->type == WWAN_PORT_AT) { /* AT port specific IOCTLs */ + res = wwan_port_fops_at_ioctl(port, cmd, arg); + if (res != -ENOIOCTLCMD) + return res; + } + + switch (cmd) { + case TIOCINQ: { /* aka SIOCINQ aka FIONREAD */ + unsigned long flags; + struct sk_buff *skb; + int amount = 0; + + spin_lock_irqsave(&port->rxq.lock, flags); + skb_queue_walk(&port->rxq, skb) + amount += skb->len; + spin_unlock_irqrestore(&port->rxq.lock, flags); + + return put_user(amount, (int __user *)arg); + } + + default: + return -ENOIOCTLCMD; + } +} + static const struct file_operations wwan_port_fops = { .owner = THIS_MODULE, .open = wwan_port_fops_open, @@ -521,28 +782,345 @@ static const struct file_operations wwan_port_fops = { .read = wwan_port_fops_read, .write = wwan_port_fops_write, .poll = wwan_port_fops_poll, + .unlocked_ioctl = wwan_port_fops_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = compat_ptr_ioctl, +#endif .llseek = noop_llseek, }; -static int __init wwan_init(void) +static int wwan_rtnl_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) { - wwan_class = class_create(THIS_MODULE, "wwan"); - if (IS_ERR(wwan_class)) - return PTR_ERR(wwan_class); + if (!data) + return -EINVAL; - /* chrdev used for wwan ports */ - wwan_major = register_chrdev(0, "wwan_port", &wwan_port_fops); - if (wwan_major < 0) { - class_destroy(wwan_class); - return wwan_major; - } + if (!tb[IFLA_PARENT_DEV_NAME]) + return -EINVAL; + + if (!data[IFLA_WWAN_LINK_ID]) + return -EINVAL; return 0; } +static struct device_type wwan_type = { .name = "wwan" }; + +static struct net_device *wwan_rtnl_alloc(struct nlattr *tb[], + const char *ifname, + unsigned char name_assign_type, + unsigned int num_tx_queues, + unsigned int num_rx_queues) +{ + const char *devname = nla_data(tb[IFLA_PARENT_DEV_NAME]); + struct wwan_device *wwandev = wwan_dev_get_by_name(devname); + struct net_device *dev; + unsigned int priv_size; + + if (IS_ERR(wwandev)) + return ERR_CAST(wwandev); + + /* only supported if ops were registered (not just ports) */ + if (!wwandev->ops) { + dev = ERR_PTR(-EOPNOTSUPP); + goto out; + } + + priv_size = sizeof(struct wwan_netdev_priv) + wwandev->ops->priv_size; + dev = alloc_netdev_mqs(priv_size, ifname, name_assign_type, + wwandev->ops->setup, num_tx_queues, num_rx_queues); + + if (dev) { + SET_NETDEV_DEV(dev, &wwandev->dev); + SET_NETDEV_DEVTYPE(dev, &wwan_type); + } + +out: + /* release the reference */ + put_device(&wwandev->dev); + return dev; +} + +static int wwan_rtnl_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct wwan_device *wwandev = wwan_dev_get_by_parent(dev->dev.parent); + u32 link_id = nla_get_u32(data[IFLA_WWAN_LINK_ID]); + struct wwan_netdev_priv *priv = netdev_priv(dev); + int ret; + + if (IS_ERR(wwandev)) + return PTR_ERR(wwandev); + + /* shouldn't have a netdev (left) with us as parent so WARN */ + if (WARN_ON(!wwandev->ops)) { + ret = -EOPNOTSUPP; + goto out; + } + + priv->link_id = link_id; + if (wwandev->ops->newlink) + ret = wwandev->ops->newlink(wwandev->ops_ctxt, dev, + link_id, extack); + else + ret = register_netdevice(dev); + +out: + /* release the reference */ + put_device(&wwandev->dev); + return ret; +} + +static void wwan_rtnl_dellink(struct net_device *dev, struct list_head *head) +{ + struct wwan_device *wwandev = wwan_dev_get_by_parent(dev->dev.parent); + + if (IS_ERR(wwandev)) + return; + + /* shouldn't have a netdev (left) with us as parent so WARN */ + if (WARN_ON(!wwandev->ops)) + goto out; + + if (wwandev->ops->dellink) + wwandev->ops->dellink(wwandev->ops_ctxt, dev, head); + else + unregister_netdevice_queue(dev, head); + +out: + /* release the reference */ + put_device(&wwandev->dev); +} + +static size_t wwan_rtnl_get_size(const struct net_device *dev) +{ + return + nla_total_size(4) + /* IFLA_WWAN_LINK_ID */ + 0; +} + +static int wwan_rtnl_fill_info(struct sk_buff *skb, + const struct net_device *dev) +{ + struct wwan_netdev_priv *priv = netdev_priv(dev); + + if (nla_put_u32(skb, IFLA_WWAN_LINK_ID, priv->link_id)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static const struct nla_policy wwan_rtnl_policy[IFLA_WWAN_MAX + 1] = { + [IFLA_WWAN_LINK_ID] = { .type = NLA_U32 }, +}; + +static struct rtnl_link_ops wwan_rtnl_link_ops __read_mostly = { + .kind = "wwan", + .maxtype = __IFLA_WWAN_MAX, + .alloc = wwan_rtnl_alloc, + .validate = wwan_rtnl_validate, + .newlink = wwan_rtnl_newlink, + .dellink = wwan_rtnl_dellink, + .get_size = wwan_rtnl_get_size, + .fill_info = wwan_rtnl_fill_info, + .policy = wwan_rtnl_policy, +}; + +static void wwan_create_default_link(struct wwan_device *wwandev, + u32 def_link_id) +{ + struct nlattr *tb[IFLA_MAX + 1], *linkinfo[IFLA_INFO_MAX + 1]; + struct nlattr *data[IFLA_WWAN_MAX + 1]; + struct net_device *dev; + struct nlmsghdr *nlh; + struct sk_buff *msg; + + /* Forge attributes required to create a WWAN netdev. We first + * build a netlink message and then parse it. This looks + * odd, but such approach is less error prone. + */ + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (WARN_ON(!msg)) + return; + nlh = nlmsg_put(msg, 0, 0, RTM_NEWLINK, 0, 0); + if (WARN_ON(!nlh)) + goto free_attrs; + + if (nla_put_string(msg, IFLA_PARENT_DEV_NAME, dev_name(&wwandev->dev))) + goto free_attrs; + tb[IFLA_LINKINFO] = nla_nest_start(msg, IFLA_LINKINFO); + if (!tb[IFLA_LINKINFO]) + goto free_attrs; + linkinfo[IFLA_INFO_DATA] = nla_nest_start(msg, IFLA_INFO_DATA); + if (!linkinfo[IFLA_INFO_DATA]) + goto free_attrs; + if (nla_put_u32(msg, IFLA_WWAN_LINK_ID, def_link_id)) + goto free_attrs; + nla_nest_end(msg, linkinfo[IFLA_INFO_DATA]); + nla_nest_end(msg, tb[IFLA_LINKINFO]); + + nlmsg_end(msg, nlh); + + /* The next three parsing calls can not fail */ + nlmsg_parse_deprecated(nlh, 0, tb, IFLA_MAX, NULL, NULL); + nla_parse_nested_deprecated(linkinfo, IFLA_INFO_MAX, tb[IFLA_LINKINFO], + NULL, NULL); + nla_parse_nested_deprecated(data, IFLA_WWAN_MAX, + linkinfo[IFLA_INFO_DATA], NULL, NULL); + + rtnl_lock(); + + dev = rtnl_create_link(&init_net, "wwan%d", NET_NAME_ENUM, + &wwan_rtnl_link_ops, tb, NULL); + if (WARN_ON(IS_ERR(dev))) + goto unlock; + + if (WARN_ON(wwan_rtnl_newlink(&init_net, dev, tb, data, NULL))) { + free_netdev(dev); + goto unlock; + } + +unlock: + rtnl_unlock(); + +free_attrs: + nlmsg_free(msg); +} + +/** + * wwan_register_ops - register WWAN device ops + * @parent: Device to use as parent and shared by all WWAN ports and + * created netdevs + * @ops: operations to register + * @ctxt: context to pass to operations + * @def_link_id: id of the default link that will be automatically created by + * the WWAN core for the WWAN device. The default link will not be created + * if the passed value is WWAN_NO_DEFAULT_LINK. + * + * Returns: 0 on success, a negative error code on failure + */ +int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, + void *ctxt, u32 def_link_id) +{ + struct wwan_device *wwandev; + + if (WARN_ON(!parent || !ops || !ops->setup)) + return -EINVAL; + + wwandev = wwan_create_dev(parent); + if (!wwandev) + return -ENOMEM; + + if (WARN_ON(wwandev->ops)) { + wwan_remove_dev(wwandev); + return -EBUSY; + } + + wwandev->ops = ops; + wwandev->ops_ctxt = ctxt; + + /* NB: we do not abort ops registration in case of default link + * creation failure. Link ops is the management interface, while the + * default link creation is a service option. And we should not prevent + * a user from manually creating a link latter if service option failed + * now. + */ + if (def_link_id != WWAN_NO_DEFAULT_LINK) + wwan_create_default_link(wwandev, def_link_id); + + return 0; +} +EXPORT_SYMBOL_GPL(wwan_register_ops); + +/* Enqueue child netdev deletion */ +static int wwan_child_dellink(struct device *dev, void *data) +{ + struct list_head *kill_list = data; + + if (dev->type == &wwan_type) + wwan_rtnl_dellink(to_net_dev(dev), kill_list); + + return 0; +} + +/** + * wwan_unregister_ops - remove WWAN device ops + * @parent: Device to use as parent and shared by all WWAN ports and + * created netdevs + */ +void wwan_unregister_ops(struct device *parent) +{ + struct wwan_device *wwandev = wwan_dev_get_by_parent(parent); + LIST_HEAD(kill_list); + + if (WARN_ON(IS_ERR(wwandev))) + return; + if (WARN_ON(!wwandev->ops)) { + put_device(&wwandev->dev); + return; + } + + /* put the reference obtained by wwan_dev_get_by_parent(), + * we should still have one (that the owner is giving back + * now) due to the ops being assigned. + */ + put_device(&wwandev->dev); + + rtnl_lock(); /* Prevent concurent netdev(s) creation/destroying */ + + /* Remove all child netdev(s), using batch removing */ + device_for_each_child(&wwandev->dev, &kill_list, + wwan_child_dellink); + unregister_netdevice_many(&kill_list); + + wwandev->ops = NULL; /* Finally remove ops */ + + rtnl_unlock(); + + wwandev->ops_ctxt = NULL; + wwan_remove_dev(wwandev); +} +EXPORT_SYMBOL_GPL(wwan_unregister_ops); + +static int __init wwan_init(void) +{ + int err; + + err = rtnl_link_register(&wwan_rtnl_link_ops); + if (err) + return err; + + wwan_class = class_create(THIS_MODULE, "wwan"); + if (IS_ERR(wwan_class)) { + err = PTR_ERR(wwan_class); + goto unregister; + } + + /* chrdev used for wwan ports */ + wwan_major = __register_chrdev(0, 0, WWAN_MAX_MINORS, "wwan_port", + &wwan_port_fops); + if (wwan_major < 0) { + err = wwan_major; + goto destroy; + } + + return 0; + +destroy: + class_destroy(wwan_class); +unregister: + rtnl_link_unregister(&wwan_rtnl_link_ops); + return err; +} + static void __exit wwan_exit(void) { - unregister_chrdev(wwan_major, "wwan_port"); + __unregister_chrdev(wwan_major, 0, WWAN_MAX_MINORS, "wwan_port"); + rtnl_link_unregister(&wwan_rtnl_link_ops); class_destroy(wwan_class); } diff --git a/drivers/net/wwan/wwan_hwsim.c b/drivers/net/wwan/wwan_hwsim.c new file mode 100644 index 000000000000..5b62cf3b3c42 --- /dev/null +++ b/drivers/net/wwan/wwan_hwsim.c @@ -0,0 +1,547 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * WWAN device simulator for WWAN framework testing. + * + * Copyright (c) 2021, Sergey Ryazanov + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +static int wwan_hwsim_devsnum = 2; +module_param_named(devices, wwan_hwsim_devsnum, int, 0444); +MODULE_PARM_DESC(devices, "Number of simulated devices"); + +static struct class *wwan_hwsim_class; + +static struct dentry *wwan_hwsim_debugfs_topdir; +static struct dentry *wwan_hwsim_debugfs_devcreate; + +static DEFINE_SPINLOCK(wwan_hwsim_devs_lock); +static LIST_HEAD(wwan_hwsim_devs); +static unsigned int wwan_hwsim_dev_idx; + +struct wwan_hwsim_dev { + struct list_head list; + unsigned int id; + struct device dev; + struct work_struct del_work; + struct dentry *debugfs_topdir; + struct dentry *debugfs_portcreate; + spinlock_t ports_lock; /* Serialize ports creation/deletion */ + unsigned int port_idx; + struct list_head ports; +}; + +struct wwan_hwsim_port { + struct list_head list; + unsigned int id; + struct wwan_hwsim_dev *dev; + struct wwan_port *wwan; + struct work_struct del_work; + struct dentry *debugfs_topdir; + enum { /* AT command parser state */ + AT_PARSER_WAIT_A, + AT_PARSER_WAIT_T, + AT_PARSER_WAIT_TERM, + AT_PARSER_SKIP_LINE, + } pstate; +}; + +static const struct file_operations wwan_hwsim_debugfs_portdestroy_fops; +static const struct file_operations wwan_hwsim_debugfs_portcreate_fops; +static const struct file_operations wwan_hwsim_debugfs_devdestroy_fops; +static void wwan_hwsim_port_del_work(struct work_struct *work); +static void wwan_hwsim_dev_del_work(struct work_struct *work); + +static netdev_tx_t wwan_hwsim_netdev_xmit(struct sk_buff *skb, + struct net_device *ndev) +{ + ndev->stats.tx_packets++; + ndev->stats.tx_bytes += skb->len; + consume_skb(skb); + return NETDEV_TX_OK; +} + +static const struct net_device_ops wwan_hwsim_netdev_ops = { + .ndo_start_xmit = wwan_hwsim_netdev_xmit, +}; + +static void wwan_hwsim_netdev_setup(struct net_device *ndev) +{ + ndev->netdev_ops = &wwan_hwsim_netdev_ops; + ndev->needs_free_netdev = true; + + ndev->mtu = ETH_DATA_LEN; + ndev->min_mtu = ETH_MIN_MTU; + ndev->max_mtu = ETH_MAX_MTU; + + ndev->type = ARPHRD_NONE; + ndev->flags = IFF_POINTOPOINT | IFF_NOARP; +} + +static const struct wwan_ops wwan_hwsim_wwan_rtnl_ops = { + .priv_size = 0, /* No private data */ + .setup = wwan_hwsim_netdev_setup, +}; + +static int wwan_hwsim_port_start(struct wwan_port *wport) +{ + struct wwan_hwsim_port *port = wwan_port_get_drvdata(wport); + + port->pstate = AT_PARSER_WAIT_A; + + return 0; +} + +static void wwan_hwsim_port_stop(struct wwan_port *wport) +{ +} + +/* Implements a minimalistic AT commands parser that echo input back and + * reply with 'OK' to each input command. See AT command protocol details in the + * ITU-T V.250 recomendations document. + * + * Be aware that this processor is not fully V.250 compliant. + */ +static int wwan_hwsim_port_tx(struct wwan_port *wport, struct sk_buff *in) +{ + struct wwan_hwsim_port *port = wwan_port_get_drvdata(wport); + struct sk_buff *out; + int i, n, s; + + /* Estimate a max possible number of commands by counting the number of + * termination chars (S3 param, CR by default). And then allocate the + * output buffer that will be enough to fit the echo and result codes of + * all commands. + */ + for (i = 0, n = 0; i < in->len; ++i) + if (in->data[i] == '\r') + n++; + n = in->len + n * (2 + 2 + 2); /* Output buffer size */ + out = alloc_skb(n, GFP_KERNEL); + if (!out) + return -ENOMEM; + + for (i = 0, s = 0; i < in->len; ++i) { + char c = in->data[i]; + + if (port->pstate == AT_PARSER_WAIT_A) { + if (c == 'A' || c == 'a') + port->pstate = AT_PARSER_WAIT_T; + else if (c != '\n') /* Ignore formating char */ + port->pstate = AT_PARSER_SKIP_LINE; + } else if (port->pstate == AT_PARSER_WAIT_T) { + if (c == 'T' || c == 't') + port->pstate = AT_PARSER_WAIT_TERM; + else + port->pstate = AT_PARSER_SKIP_LINE; + } else if (port->pstate == AT_PARSER_WAIT_TERM) { + if (c != '\r') + continue; + /* Consume the trailing formatting char as well */ + if ((i + 1) < in->len && in->data[i + 1] == '\n') + i++; + n = i - s + 1; + memcpy(skb_put(out, n), &in->data[s], n);/* Echo */ + memcpy(skb_put(out, 6), "\r\nOK\r\n", 6); + s = i + 1; + port->pstate = AT_PARSER_WAIT_A; + } else if (port->pstate == AT_PARSER_SKIP_LINE) { + if (c != '\r') + continue; + port->pstate = AT_PARSER_WAIT_A; + } + } + + if (i > s) { + /* Echo the processed portion of a not yet completed command */ + n = i - s; + memcpy(skb_put(out, n), &in->data[s], n); + } + + consume_skb(in); + + wwan_port_rx(wport, out); + + return 0; +} + +static const struct wwan_port_ops wwan_hwsim_port_ops = { + .start = wwan_hwsim_port_start, + .stop = wwan_hwsim_port_stop, + .tx = wwan_hwsim_port_tx, +}; + +static struct wwan_hwsim_port *wwan_hwsim_port_new(struct wwan_hwsim_dev *dev) +{ + struct wwan_hwsim_port *port; + char name[0x10]; + int err; + + port = kzalloc(sizeof(*port), GFP_KERNEL); + if (!port) + return ERR_PTR(-ENOMEM); + + port->dev = dev; + + spin_lock(&dev->ports_lock); + port->id = dev->port_idx++; + spin_unlock(&dev->ports_lock); + + port->wwan = wwan_create_port(&dev->dev, WWAN_PORT_AT, + &wwan_hwsim_port_ops, + port); + if (IS_ERR(port->wwan)) { + err = PTR_ERR(port->wwan); + goto err_free_port; + } + + INIT_WORK(&port->del_work, wwan_hwsim_port_del_work); + + snprintf(name, sizeof(name), "port%u", port->id); + port->debugfs_topdir = debugfs_create_dir(name, dev->debugfs_topdir); + debugfs_create_file("destroy", 0200, port->debugfs_topdir, port, + &wwan_hwsim_debugfs_portdestroy_fops); + + return port; + +err_free_port: + kfree(port); + + return ERR_PTR(err); +} + +static void wwan_hwsim_port_del(struct wwan_hwsim_port *port) +{ + debugfs_remove(port->debugfs_topdir); + + /* Make sure that there is no pending deletion work */ + if (current_work() != &port->del_work) + cancel_work_sync(&port->del_work); + + wwan_remove_port(port->wwan); + kfree(port); +} + +static void wwan_hwsim_port_del_work(struct work_struct *work) +{ + struct wwan_hwsim_port *port = + container_of(work, typeof(*port), del_work); + struct wwan_hwsim_dev *dev = port->dev; + + spin_lock(&dev->ports_lock); + if (list_empty(&port->list)) { + /* Someone else deleting port at the moment */ + spin_unlock(&dev->ports_lock); + return; + } + list_del_init(&port->list); + spin_unlock(&dev->ports_lock); + + wwan_hwsim_port_del(port); +} + +static void wwan_hwsim_dev_release(struct device *sysdev) +{ + struct wwan_hwsim_dev *dev = container_of(sysdev, typeof(*dev), dev); + + kfree(dev); +} + +static struct wwan_hwsim_dev *wwan_hwsim_dev_new(void) +{ + struct wwan_hwsim_dev *dev; + int err; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return ERR_PTR(-ENOMEM); + + spin_lock(&wwan_hwsim_devs_lock); + dev->id = wwan_hwsim_dev_idx++; + spin_unlock(&wwan_hwsim_devs_lock); + + dev->dev.release = wwan_hwsim_dev_release; + dev->dev.class = wwan_hwsim_class; + dev_set_name(&dev->dev, "hwsim%u", dev->id); + + spin_lock_init(&dev->ports_lock); + INIT_LIST_HEAD(&dev->ports); + + err = device_register(&dev->dev); + if (err) + goto err_free_dev; + + INIT_WORK(&dev->del_work, wwan_hwsim_dev_del_work); + + err = wwan_register_ops(&dev->dev, &wwan_hwsim_wwan_rtnl_ops, dev, 1); + if (err) + goto err_unreg_dev; + + dev->debugfs_topdir = debugfs_create_dir(dev_name(&dev->dev), + wwan_hwsim_debugfs_topdir); + debugfs_create_file("destroy", 0200, dev->debugfs_topdir, dev, + &wwan_hwsim_debugfs_devdestroy_fops); + dev->debugfs_portcreate = + debugfs_create_file("portcreate", 0200, + dev->debugfs_topdir, dev, + &wwan_hwsim_debugfs_portcreate_fops); + + return dev; + +err_unreg_dev: + device_unregister(&dev->dev); + /* Memory will be freed in the device release callback */ + + return ERR_PTR(err); + +err_free_dev: + kfree(dev); + + return ERR_PTR(err); +} + +static void wwan_hwsim_dev_del(struct wwan_hwsim_dev *dev) +{ + debugfs_remove(dev->debugfs_portcreate); /* Avoid new ports */ + + spin_lock(&dev->ports_lock); + while (!list_empty(&dev->ports)) { + struct wwan_hwsim_port *port; + + port = list_first_entry(&dev->ports, struct wwan_hwsim_port, + list); + list_del_init(&port->list); + spin_unlock(&dev->ports_lock); + wwan_hwsim_port_del(port); + spin_lock(&dev->ports_lock); + } + spin_unlock(&dev->ports_lock); + + debugfs_remove(dev->debugfs_topdir); + + /* This will remove all child netdev(s) */ + wwan_unregister_ops(&dev->dev); + + /* Make sure that there is no pending deletion work */ + if (current_work() != &dev->del_work) + cancel_work_sync(&dev->del_work); + + device_unregister(&dev->dev); + /* Memory will be freed in the device release callback */ +} + +static void wwan_hwsim_dev_del_work(struct work_struct *work) +{ + struct wwan_hwsim_dev *dev = container_of(work, typeof(*dev), del_work); + + spin_lock(&wwan_hwsim_devs_lock); + if (list_empty(&dev->list)) { + /* Someone else deleting device at the moment */ + spin_unlock(&wwan_hwsim_devs_lock); + return; + } + list_del_init(&dev->list); + spin_unlock(&wwan_hwsim_devs_lock); + + wwan_hwsim_dev_del(dev); +} + +static ssize_t wwan_hwsim_debugfs_portdestroy_write(struct file *file, + const char __user *usrbuf, + size_t count, loff_t *ppos) +{ + struct wwan_hwsim_port *port = file->private_data; + + /* We can not delete port here since it will cause a deadlock due to + * waiting this callback to finish in the debugfs_remove() call. So, + * use workqueue. + */ + schedule_work(&port->del_work); + + return count; +} + +static const struct file_operations wwan_hwsim_debugfs_portdestroy_fops = { + .write = wwan_hwsim_debugfs_portdestroy_write, + .open = simple_open, + .llseek = noop_llseek, +}; + +static ssize_t wwan_hwsim_debugfs_portcreate_write(struct file *file, + const char __user *usrbuf, + size_t count, loff_t *ppos) +{ + struct wwan_hwsim_dev *dev = file->private_data; + struct wwan_hwsim_port *port; + + port = wwan_hwsim_port_new(dev); + if (IS_ERR(port)) + return PTR_ERR(port); + + spin_lock(&dev->ports_lock); + list_add_tail(&port->list, &dev->ports); + spin_unlock(&dev->ports_lock); + + return count; +} + +static const struct file_operations wwan_hwsim_debugfs_portcreate_fops = { + .write = wwan_hwsim_debugfs_portcreate_write, + .open = simple_open, + .llseek = noop_llseek, +}; + +static ssize_t wwan_hwsim_debugfs_devdestroy_write(struct file *file, + const char __user *usrbuf, + size_t count, loff_t *ppos) +{ + struct wwan_hwsim_dev *dev = file->private_data; + + /* We can not delete device here since it will cause a deadlock due to + * waiting this callback to finish in the debugfs_remove() call. So, + * use workqueue. + */ + schedule_work(&dev->del_work); + + return count; +} + +static const struct file_operations wwan_hwsim_debugfs_devdestroy_fops = { + .write = wwan_hwsim_debugfs_devdestroy_write, + .open = simple_open, + .llseek = noop_llseek, +}; + +static ssize_t wwan_hwsim_debugfs_devcreate_write(struct file *file, + const char __user *usrbuf, + size_t count, loff_t *ppos) +{ + struct wwan_hwsim_dev *dev; + + dev = wwan_hwsim_dev_new(); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + spin_lock(&wwan_hwsim_devs_lock); + list_add_tail(&dev->list, &wwan_hwsim_devs); + spin_unlock(&wwan_hwsim_devs_lock); + + return count; +} + +static const struct file_operations wwan_hwsim_debugfs_devcreate_fops = { + .write = wwan_hwsim_debugfs_devcreate_write, + .open = simple_open, + .llseek = noop_llseek, +}; + +static int __init wwan_hwsim_init_devs(void) +{ + struct wwan_hwsim_dev *dev; + int i, j; + + for (i = 0; i < wwan_hwsim_devsnum; ++i) { + dev = wwan_hwsim_dev_new(); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + spin_lock(&wwan_hwsim_devs_lock); + list_add_tail(&dev->list, &wwan_hwsim_devs); + spin_unlock(&wwan_hwsim_devs_lock); + + /* Create a couple of ports per each device to accelerate + * the simulator readiness time. + */ + for (j = 0; j < 2; ++j) { + struct wwan_hwsim_port *port; + + port = wwan_hwsim_port_new(dev); + if (IS_ERR(port)) + return PTR_ERR(port); + + spin_lock(&dev->ports_lock); + list_add_tail(&port->list, &dev->ports); + spin_unlock(&dev->ports_lock); + } + } + + return 0; +} + +static void wwan_hwsim_free_devs(void) +{ + struct wwan_hwsim_dev *dev; + + spin_lock(&wwan_hwsim_devs_lock); + while (!list_empty(&wwan_hwsim_devs)) { + dev = list_first_entry(&wwan_hwsim_devs, struct wwan_hwsim_dev, + list); + list_del_init(&dev->list); + spin_unlock(&wwan_hwsim_devs_lock); + wwan_hwsim_dev_del(dev); + spin_lock(&wwan_hwsim_devs_lock); + } + spin_unlock(&wwan_hwsim_devs_lock); +} + +static int __init wwan_hwsim_init(void) +{ + int err; + + if (wwan_hwsim_devsnum < 0 || wwan_hwsim_devsnum > 128) + return -EINVAL; + + wwan_hwsim_class = class_create(THIS_MODULE, "wwan_hwsim"); + if (IS_ERR(wwan_hwsim_class)) + return PTR_ERR(wwan_hwsim_class); + + wwan_hwsim_debugfs_topdir = debugfs_create_dir("wwan_hwsim", NULL); + wwan_hwsim_debugfs_devcreate = + debugfs_create_file("devcreate", 0200, + wwan_hwsim_debugfs_topdir, NULL, + &wwan_hwsim_debugfs_devcreate_fops); + + err = wwan_hwsim_init_devs(); + if (err) + goto err_clean_devs; + + return 0; + +err_clean_devs: + wwan_hwsim_free_devs(); + debugfs_remove(wwan_hwsim_debugfs_topdir); + class_destroy(wwan_hwsim_class); + + return err; +} + +static void __exit wwan_hwsim_exit(void) +{ + debugfs_remove(wwan_hwsim_debugfs_devcreate); /* Avoid new devs */ + wwan_hwsim_free_devs(); + flush_scheduled_work(); /* Wait deletion works completion */ + debugfs_remove(wwan_hwsim_debugfs_topdir); + class_destroy(wwan_hwsim_class); +} + +module_init(wwan_hwsim_init); +module_exit(wwan_hwsim_exit); + +MODULE_AUTHOR("Sergey Ryazanov"); +MODULE_DESCRIPTION("Device simulator for WWAN framework"); +MODULE_LICENSE("GPL"); diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c index fe0719ed81a0..528745862738 100644 --- a/drivers/nfc/fdp/fdp.c +++ b/drivers/nfc/fdp/fdp.c @@ -149,7 +149,7 @@ static void fdp_nci_send_patch_cb(struct nci_dev *ndev) wake_up(&info->setup_wq); } -/** +/* * Register a packet sent counter and a callback * * We have no other way of knowing when all firmware packets were sent out @@ -167,7 +167,7 @@ static void fdp_nci_set_data_pkt_counter(struct nci_dev *ndev, info->data_pkt_counter_cb = cb; } -/** +/* * The device is expecting a stream of packets. All packets need to * have the PBF flag set to 0x0 (last packet) even if the firmware * file is segmented and there are multiple packets. If we give the @@ -237,28 +237,18 @@ static int fdp_nci_send_patch(struct nci_dev *ndev, u8 conn_id, u8 type) static int fdp_nci_open(struct nci_dev *ndev) { struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - - dev_dbg(dev, "%s\n", __func__); return info->phy_ops->enable(info->phy); } static int fdp_nci_close(struct nci_dev *ndev) { - struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - - dev_dbg(dev, "%s\n", __func__); return 0; } static int fdp_nci_send(struct nci_dev *ndev, struct sk_buff *skb) { struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - - dev_dbg(dev, "%s\n", __func__); if (atomic_dec_and_test(&info->data_pkt_counter)) info->data_pkt_counter_cb(ndev); @@ -266,16 +256,6 @@ static int fdp_nci_send(struct nci_dev *ndev, struct sk_buff *skb) return info->phy_ops->write(info->phy, skb); } -int fdp_nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb) -{ - struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - - dev_dbg(dev, "%s\n", __func__); - return nci_recv_frame(ndev, skb); -} -EXPORT_SYMBOL(fdp_nci_recv_frame); - static int fdp_nci_request_firmware(struct nci_dev *ndev) { struct fdp_nci_info *info = nci_get_drvdata(ndev); @@ -286,7 +266,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev) r = request_firmware(&info->ram_patch, FDP_RAM_PATCH_NAME, dev); if (r < 0) { nfc_err(dev, "RAM patch request error\n"); - goto error; + return r; } data = (u8 *) info->ram_patch->data; @@ -303,7 +283,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev) r = request_firmware(&info->otp_patch, FDP_OTP_PATCH_NAME, dev); if (r < 0) { nfc_err(dev, "OTP patch request error\n"); - goto out; + return 0; } data = (u8 *) info->otp_patch->data; @@ -315,10 +295,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev) dev_dbg(dev, "OTP patch version: %d, size: %d\n", info->otp_patch_version, (int) info->otp_patch->size); -out: return 0; -error: - return r; } static void fdp_nci_release_firmware(struct nci_dev *ndev) @@ -476,8 +453,6 @@ static int fdp_nci_setup(struct nci_dev *ndev) int r; u8 patched = 0; - dev_dbg(dev, "%s\n", __func__); - r = nci_core_init(ndev); if (r) goto error; @@ -585,9 +560,7 @@ static int fdp_nci_core_reset_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) { struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - dev_dbg(dev, "%s\n", __func__); info->setup_reset_ntf = 1; wake_up(&info->setup_wq); @@ -598,9 +571,7 @@ static int fdp_nci_prop_patch_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb) { struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - dev_dbg(dev, "%s\n", __func__); info->setup_patch_ntf = 1; info->setup_patch_status = skb->data[0]; wake_up(&info->setup_wq); @@ -773,11 +744,6 @@ EXPORT_SYMBOL(fdp_nci_probe); void fdp_nci_remove(struct nci_dev *ndev) { - struct fdp_nci_info *info = nci_get_drvdata(ndev); - struct device *dev = &info->phy->i2c_dev->dev; - - dev_dbg(dev, "%s\n", __func__); - nci_unregister_device(ndev); nci_free_device(ndev); } diff --git a/drivers/nfc/fdp/fdp.h b/drivers/nfc/fdp/fdp.h index 9bd1f3f23e2d..ead3b21ccae6 100644 --- a/drivers/nfc/fdp/fdp.h +++ b/drivers/nfc/fdp/fdp.h @@ -25,6 +25,5 @@ int fdp_nci_probe(struct fdp_i2c_phy *phy, struct nfc_phy_ops *phy_ops, struct nci_dev **ndev, int tx_headroom, int tx_tailroom, u8 clock_type, u32 clock_freq, u8 *fw_vsc_cfg); void fdp_nci_remove(struct nci_dev *ndev); -int fdp_nci_recv_frame(struct nci_dev *ndev, struct sk_buff *skb); #endif /* __LOCAL_FDP_H_ */ diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c index adaa1a7147f9..c5596e514648 100644 --- a/drivers/nfc/fdp/i2c.c +++ b/drivers/nfc/fdp/i2c.c @@ -49,7 +49,6 @@ static int fdp_nci_i2c_enable(void *phy_id) { struct fdp_i2c_phy *phy = phy_id; - dev_dbg(&phy->i2c_dev->dev, "%s\n", __func__); fdp_nci_i2c_reset(phy); return 0; @@ -59,7 +58,6 @@ static void fdp_nci_i2c_disable(void *phy_id) { struct fdp_i2c_phy *phy = phy_id; - dev_dbg(&phy->i2c_dev->dev, "%s\n", __func__); fdp_nci_i2c_reset(phy); } @@ -197,7 +195,6 @@ flush: static irqreturn_t fdp_nci_i2c_irq_thread_fn(int irq, void *phy_id) { struct fdp_i2c_phy *phy = phy_id; - struct i2c_client *client; struct sk_buff *skb; int r; @@ -206,9 +203,6 @@ static irqreturn_t fdp_nci_i2c_irq_thread_fn(int irq, void *phy_id) return IRQ_NONE; } - client = phy->i2c_dev; - dev_dbg(&client->dev, "%s\n", __func__); - r = fdp_nci_i2c_read(phy, &skb); if (r == -EREMOTEIO) @@ -217,7 +211,7 @@ static irqreturn_t fdp_nci_i2c_irq_thread_fn(int irq, void *phy_id) return IRQ_HANDLED; if (skb != NULL) - fdp_nci_recv_frame(phy->ndev, skb); + nci_recv_frame(phy->ndev, skb); return IRQ_HANDLED; } @@ -288,8 +282,6 @@ static int fdp_nci_i2c_probe(struct i2c_client *client) u32 clock_freq; int r = 0; - dev_dbg(dev, "%s\n", __func__); - if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { nfc_err(dev, "No I2C_FUNC_I2C support\n"); return -ENODEV; @@ -351,8 +343,6 @@ static int fdp_nci_i2c_remove(struct i2c_client *client) { struct fdp_i2c_phy *phy = i2c_get_clientdata(client); - dev_dbg(&client->dev, "%s\n", __func__); - fdp_nci_remove(phy->ndev); fdp_nci_i2c_disable(phy); @@ -368,7 +358,7 @@ MODULE_DEVICE_TABLE(acpi, fdp_nci_i2c_acpi_match); static struct i2c_driver fdp_nci_i2c_driver = { .driver = { .name = FDP_I2C_DRIVER_NAME, - .acpi_match_table = ACPI_PTR(fdp_nci_i2c_acpi_match), + .acpi_match_table = fdp_nci_i2c_acpi_match, }, .probe_new = fdp_nci_i2c_probe, .remove = fdp_nci_i2c_remove, diff --git a/drivers/nfc/mei_phy.c b/drivers/nfc/mei_phy.c index 0f43bb389566..e56cea716cd2 100644 --- a/drivers/nfc/mei_phy.c +++ b/drivers/nfc/mei_phy.c @@ -98,8 +98,6 @@ static int mei_nfc_if_version(struct nfc_mei_phy *phy) size_t if_version_length; int bytes_recv, r; - pr_info("%s\n", __func__); - memset(&cmd, 0, sizeof(struct mei_nfc_cmd)); cmd.hdr.cmd = MEI_NFC_CMD_MAINTENANCE; cmd.hdr.data_size = 1; @@ -146,8 +144,6 @@ static int mei_nfc_connect(struct nfc_mei_phy *phy) size_t connect_length, connect_resp_length; int bytes_recv, r; - pr_info("%s\n", __func__); - connect_length = sizeof(struct mei_nfc_cmd) + sizeof(struct mei_nfc_connect); @@ -320,8 +316,6 @@ static int nfc_mei_phy_enable(void *phy_id) int r; struct nfc_mei_phy *phy = phy_id; - pr_info("%s\n", __func__); - if (phy->powered == 1) return 0; @@ -363,8 +357,6 @@ static void nfc_mei_phy_disable(void *phy_id) { struct nfc_mei_phy *phy = phy_id; - pr_info("%s\n", __func__); - mei_cldev_disable(phy->cldev); phy->powered = 0; diff --git a/drivers/nfc/microread/microread.c b/drivers/nfc/microread/microread.c index 8d3988457c58..b1d3975e8a81 100644 --- a/drivers/nfc/microread/microread.c +++ b/drivers/nfc/microread/microread.c @@ -364,7 +364,6 @@ static void microread_im_transceive_cb(void *context, struct sk_buff *skb, case MICROREAD_CB_TYPE_READER_ALL: if (err == 0) { if (skb->len == 0) { - err = -EPROTO; kfree_skb(skb); info->async_cb(info->async_cb_context, NULL, -EPROTO); diff --git a/drivers/nfc/nfcmrvl/fw_dnld.c b/drivers/nfc/nfcmrvl/fw_dnld.c index 52c8ae504e32..aaccb8b76b3e 100644 --- a/drivers/nfc/nfcmrvl/fw_dnld.c +++ b/drivers/nfc/nfcmrvl/fw_dnld.c @@ -1,19 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Marvell NFC driver: Firmware downloader * * Copyright (C) 2015, Marvell International Ltd. - * - * This software file (the "File") is distributed by Marvell International - * Ltd. under the terms of the GNU General Public License Version 2, June 1991 - * (the "License"). You may use, redistribute and/or modify this File in - * accordance with the terms and conditions of the License, a copy of which - * is available on the worldwide web at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. - * - * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE - * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE - * ARE EXPRESSLY DISCLAIMED. The License provides additional details about - * this warranty disclaimer. */ #include @@ -50,8 +39,8 @@ enum { }; /* -** Patterns for responses -*/ + * Patterns for responses + */ static const uint8_t nci_pattern_core_reset_ntf[] = { 0x60, 0x00, 0x02, 0xA0, 0x01 @@ -451,7 +440,7 @@ static void fw_dnld_rx_work(struct work_struct *work) } } -int nfcmrvl_fw_dnld_init(struct nfcmrvl_private *priv) +int nfcmrvl_fw_dnld_init(struct nfcmrvl_private *priv) { char name[32]; @@ -465,13 +454,13 @@ int nfcmrvl_fw_dnld_init(struct nfcmrvl_private *priv) return 0; } -void nfcmrvl_fw_dnld_deinit(struct nfcmrvl_private *priv) +void nfcmrvl_fw_dnld_deinit(struct nfcmrvl_private *priv) { destroy_workqueue(priv->fw_dnld.rx_wq); } -void nfcmrvl_fw_dnld_recv_frame(struct nfcmrvl_private *priv, - struct sk_buff *skb) +void nfcmrvl_fw_dnld_recv_frame(struct nfcmrvl_private *priv, + struct sk_buff *skb) { /* Discard command timer */ if (timer_pending(&priv->ndev->cmd_timer)) diff --git a/drivers/nfc/nfcmrvl/fw_dnld.h b/drivers/nfc/nfcmrvl/fw_dnld.h index 058ce77b3cbc..7c4d91b01910 100644 --- a/drivers/nfc/nfcmrvl/fw_dnld.h +++ b/drivers/nfc/nfcmrvl/fw_dnld.h @@ -1,20 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Marvell NFC driver: Firmware downloader * * Copyright (C) 2015, Marvell International Ltd. - * - * This software file (the "File") is distributed by Marvell International - * Ltd. under the terms of the GNU General Public License Version 2, June 1991 - * (the "License"). You may use, redistribute and/or modify this File in - * accordance with the terms and conditions of the License, a copy of which - * is available on the worldwide web at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. - * - * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE - * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE - * ARE EXPRESSLY DISCLAIMED. The License provides additional details about - * this warranty disclaimer. - **/ + */ #ifndef __NFCMRVL_FW_DNLD_H__ #define __NFCMRVL_FW_DNLD_H__ diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index c5420616b7bc..59a529e72d96 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -1,20 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Marvell NFC-over-I2C driver: I2C interface related functions * * Copyright (C) 2015, Marvell International Ltd. - * - * This software file (the "File") is distributed by Marvell International - * Ltd. under the terms of the GNU General Public License Version 2, June 1991 - * (the "License"). You may use, redistribute and/or modify this File in - * accordance with the terms and conditions of the License, a copy of which - * is available on the worldwide web at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. - * - * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE - * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE - * ARE EXPRESSLY DISCLAIMED. The License provides additional details about - * this warranty disclaimer. - **/ + */ #include #include @@ -49,11 +38,6 @@ static int nfcmrvl_i2c_read(struct nfcmrvl_i2c_drv_data *drv_data, return -EBADMSG; } - if (nci_hdr.plen > NCI_MAX_PAYLOAD_SIZE) { - nfc_err(&drv_data->i2c->dev, "invalid packet payload size\n"); - return -EBADMSG; - } - *skb = nci_skb_alloc(drv_data->priv->ndev, nci_hdr.plen + NCI_CTRL_HDR_SIZE, GFP_KERNEL); if (!*skb) @@ -260,7 +244,7 @@ static int nfcmrvl_i2c_remove(struct i2c_client *client) } -static const struct of_device_id of_nfcmrvl_i2c_match[] = { +static const struct of_device_id of_nfcmrvl_i2c_match[] __maybe_unused = { { .compatible = "marvell,nfc-i2c", }, {}, }; diff --git a/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c index 529be35ac178..a4620b480c4f 100644 --- a/drivers/nfc/nfcmrvl/main.c +++ b/drivers/nfc/nfcmrvl/main.c @@ -1,19 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Marvell NFC driver: major functions * * Copyright (C) 2014-2015 Marvell International Ltd. - * - * This software file (the "File") is distributed by Marvell International - * Ltd. under the terms of the GNU General Public License Version 2, June 1991 - * (the "License"). You may use, redistribute and/or modify this File in - * accordance with the terms and conditions of the License, a copy of which - * is available on the worldwide web at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. - * - * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE - * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE - * ARE EXPRESSLY DISCLAIMED. The License provides additional details about - * this warranty disclaimer. */ #include diff --git a/drivers/nfc/nfcmrvl/nfcmrvl.h b/drivers/nfc/nfcmrvl/nfcmrvl.h index e84ee18c73ae..a715543bc9bf 100644 --- a/drivers/nfc/nfcmrvl/nfcmrvl.h +++ b/drivers/nfc/nfcmrvl/nfcmrvl.h @@ -1,20 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Marvell NFC driver * * Copyright (C) 2014-2015, Marvell International Ltd. - * - * This software file (the "File") is distributed by Marvell International - * Ltd. under the terms of the GNU General Public License Version 2, June 1991 - * (the "License"). You may use, redistribute and/or modify this File in - * accordance with the terms and conditions of the License, a copy of which - * is available on the worldwide web at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. - * - * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE - * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE - * ARE EXPRESSLY DISCLAIMED. The License provides additional details about - * this warranty disclaimer. - **/ + */ #ifndef _NFCMRVL_H_ #define _NFCMRVL_H_ @@ -36,16 +25,16 @@ #define NFCMRVL_NCI_MAX_EVENT_SIZE 260 /* -** NCI FW Parmaters -*/ + * NCI FW Parameters + */ #define NFCMRVL_PB_BAIL_OUT 0x11 #define NFCMRVL_PROP_REF_CLOCK 0xF0 #define NFCMRVL_PROP_SET_HI_CONFIG 0xF1 /* -** HCI defines -*/ + * HCI defines + */ #define NFCMRVL_HCI_EVENT_HEADER_SIZE 0x04 #define NFCMRVL_HCI_EVENT_CODE 0x04 @@ -78,8 +67,8 @@ struct nfcmrvl_private { bool support_fw_dnld; /* - ** PHY related information - */ + * PHY related information + */ /* PHY driver context */ void *drv_data; diff --git a/drivers/nfc/nfcmrvl/spi.c b/drivers/nfc/nfcmrvl/spi.c index dec0d3eb3648..66696321c645 100644 --- a/drivers/nfc/nfcmrvl/spi.c +++ b/drivers/nfc/nfcmrvl/spi.c @@ -1,20 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Marvell NFC-over-SPI driver: SPI interface related functions * * Copyright (C) 2015, Marvell International Ltd. - * - * This software file (the "File") is distributed by Marvell International - * Ltd. under the terms of the GNU General Public License Version 2, June 1991 - * (the "License"). You may use, redistribute and/or modify this File in - * accordance with the terms and conditions of the License, a copy of which - * is available on the worldwide web at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. - * - * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE - * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE - * ARE EXPRESSLY DISCLAIMED. The License provides additional details about - * this warranty disclaimer. - **/ + */ #include #include @@ -196,7 +185,7 @@ static int nfcmrvl_spi_remove(struct spi_device *spi) return 0; } -static const struct of_device_id of_nfcmrvl_spi_match[] = { +static const struct of_device_id of_nfcmrvl_spi_match[] __maybe_unused = { { .compatible = "marvell,nfc-spi", }, {}, }; diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c index 7194dd7ef0f1..50d86c90b9dd 100644 --- a/drivers/nfc/nfcmrvl/uart.c +++ b/drivers/nfc/nfcmrvl/uart.c @@ -1,19 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Marvell NFC-over-UART driver * * Copyright (C) 2015, Marvell International Ltd. - * - * This software file (the "File") is distributed by Marvell International - * Ltd. under the terms of the GNU General Public License Version 2, June 1991 - * (the "License"). You may use, redistribute and/or modify this File in - * accordance with the terms and conditions of the License, a copy of which - * is available on the worldwide web at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. - * - * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE - * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE - * ARE EXPRESSLY DISCLAIMED. The License provides additional details about - * this warranty disclaimer. */ #include @@ -29,8 +18,8 @@ static unsigned int break_control; static int reset_n_io = -EINVAL; /* -** NFCMRVL NCI OPS -*/ + * NFCMRVL NCI OPS + */ static int nfcmrvl_uart_nci_open(struct nfcmrvl_private *priv) { @@ -103,8 +92,8 @@ static int nfcmrvl_uart_parse_dt(struct device_node *node, } /* -** NCI UART OPS -*/ + * NCI UART OPS + */ static int nfcmrvl_nci_uart_open(struct nci_uart *nu) { @@ -178,10 +167,10 @@ static void nfcmrvl_nci_uart_tx_done(struct nci_uart *nu) return; /* - ** To ensure that if the NFCC goes in DEEP SLEEP sate we can wake him - ** up. we set BREAK. Once we will be ready to send again we will remove - ** it. - */ + * To ensure that if the NFCC goes in DEEP SLEEP sate we can wake him + * up. we set BREAK. Once we will be ready to send again we will remove + * it. + */ if (priv->config.break_control && nu->tty->ops->break_ctl) { nu->tty->ops->break_ctl(nu->tty, -1); usleep_range(1000, 3000); @@ -200,23 +189,7 @@ static struct nci_uart nfcmrvl_nci_uart = { .tx_done = nfcmrvl_nci_uart_tx_done, } }; - -/* -** Module init -*/ - -static int nfcmrvl_uart_init_module(void) -{ - return nci_uart_register(&nfcmrvl_nci_uart); -} - -static void nfcmrvl_uart_exit_module(void) -{ - nci_uart_unregister(&nfcmrvl_nci_uart); -} - -module_init(nfcmrvl_uart_init_module); -module_exit(nfcmrvl_uart_exit_module); +module_driver(nfcmrvl_nci_uart, nci_uart_register, nci_uart_unregister); MODULE_AUTHOR("Marvell International Ltd."); MODULE_DESCRIPTION("Marvell NFC-over-UART"); diff --git a/drivers/nfc/nfcmrvl/usb.c b/drivers/nfc/nfcmrvl/usb.c index bcd563cb556c..9d649b45300b 100644 --- a/drivers/nfc/nfcmrvl/usb.c +++ b/drivers/nfc/nfcmrvl/usb.c @@ -1,20 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Marvell NFC-over-USB driver: USB interface related functions * * Copyright (C) 2014, Marvell International Ltd. - * - * This software file (the "File") is distributed by Marvell International - * Ltd. under the terms of the GNU General Public License Version 2, June 1991 - * (the "License"). You may use, redistribute and/or modify this File in - * accordance with the terms and conditions of the License, a copy of which - * is available on the worldwide web at - * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. - * - * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE - * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE - * ARE EXPRESSLY DISCLAIMED. The License provides additional details about - * this warranty disclaimer. - **/ + */ #include #include @@ -68,7 +57,6 @@ static int nfcmrvl_inc_tx(struct nfcmrvl_usb_drv_data *drv_data) static void nfcmrvl_bulk_complete(struct urb *urb) { struct nfcmrvl_usb_drv_data *drv_data = urb->context; - struct sk_buff *skb; int err; dev_dbg(&drv_data->udev->dev, "urb %p status %d count %d\n", @@ -78,6 +66,8 @@ static void nfcmrvl_bulk_complete(struct urb *urb) return; if (!urb->status) { + struct sk_buff *skb; + skb = nci_skb_alloc(drv_data->priv->ndev, urb->actual_length, GFP_ATOMIC); if (!skb) { @@ -296,7 +286,6 @@ static void nfcmrvl_waker(struct work_struct *work) static int nfcmrvl_probe(struct usb_interface *intf, const struct usb_device_id *id) { - struct usb_endpoint_descriptor *ep_desc; struct nfcmrvl_usb_drv_data *drv_data; struct nfcmrvl_private *priv; int i; @@ -314,18 +303,16 @@ static int nfcmrvl_probe(struct usb_interface *intf, return -ENOMEM; for (i = 0; i < intf->cur_altsetting->desc.bNumEndpoints; i++) { + struct usb_endpoint_descriptor *ep_desc; + ep_desc = &intf->cur_altsetting->endpoint[i].desc; if (!drv_data->bulk_tx_ep && usb_endpoint_is_bulk_out(ep_desc)) { drv_data->bulk_tx_ep = ep_desc; - continue; - } - - if (!drv_data->bulk_rx_ep && - usb_endpoint_is_bulk_in(ep_desc)) { + } else if (!drv_data->bulk_rx_ep && + usb_endpoint_is_bulk_in(ep_desc)) { drv_data->bulk_rx_ep = ep_desc; - continue; } } diff --git a/drivers/nfc/nxp-nci/core.c b/drivers/nfc/nxp-nci/core.c index a0ce95a287c5..2b0c7232e91f 100644 --- a/drivers/nfc/nxp-nci/core.c +++ b/drivers/nfc/nxp-nci/core.c @@ -70,21 +70,16 @@ static int nxp_nci_send(struct nci_dev *ndev, struct sk_buff *skb) struct nxp_nci_info *info = nci_get_drvdata(ndev); int r; - if (!info->phy_ops->write) { - r = -ENOTSUPP; - goto send_exit; - } + if (!info->phy_ops->write) + return -EOPNOTSUPP; - if (info->mode != NXP_NCI_MODE_NCI) { - r = -EINVAL; - goto send_exit; - } + if (info->mode != NXP_NCI_MODE_NCI) + return -EINVAL; r = info->phy_ops->write(info->phy_id, skb); if (r < 0) kfree_skb(skb); -send_exit: return r; } @@ -104,10 +99,8 @@ int nxp_nci_probe(void *phy_id, struct device *pdev, int r; info = devm_kzalloc(pdev, sizeof(struct nxp_nci_info), GFP_KERNEL); - if (!info) { - r = -ENOMEM; - goto probe_exit; - } + if (!info) + return -ENOMEM; info->phy_id = phy_id; info->pdev = pdev; @@ -120,31 +113,25 @@ int nxp_nci_probe(void *phy_id, struct device *pdev, if (info->phy_ops->set_mode) { r = info->phy_ops->set_mode(info->phy_id, NXP_NCI_MODE_COLD); if (r < 0) - goto probe_exit; + return r; } info->mode = NXP_NCI_MODE_COLD; info->ndev = nci_allocate_device(&nxp_nci_ops, NXP_NCI_NFC_PROTOCOLS, NXP_NCI_HDR_LEN, 0); - if (!info->ndev) { - r = -ENOMEM; - goto probe_exit; - } + if (!info->ndev) + return -ENOMEM; nci_set_parent_dev(info->ndev, pdev); nci_set_drvdata(info->ndev, info); r = nci_register_device(info->ndev); - if (r < 0) - goto probe_exit_free_nci; + if (r < 0) { + nci_free_device(info->ndev); + return r; + } *ndev = info->ndev; - - goto probe_exit; - -probe_exit_free_nci: - nci_free_device(info->ndev); -probe_exit: return r; } EXPORT_SYMBOL(nxp_nci_probe); diff --git a/drivers/nfc/nxp-nci/firmware.c b/drivers/nfc/nxp-nci/firmware.c index dae0c8030e95..119bf305c642 100644 --- a/drivers/nfc/nxp-nci/firmware.c +++ b/drivers/nfc/nxp-nci/firmware.c @@ -95,10 +95,8 @@ static int nxp_nci_fw_send_chunk(struct nxp_nci_info *info) int r; skb = nci_skb_alloc(info->ndev, info->max_payload, GFP_KERNEL); - if (!skb) { - r = -ENOMEM; - goto chunk_exit; - } + if (!skb) + return -ENOMEM; chunk_len = info->max_payload - NXP_NCI_FW_HDR_LEN - NXP_NCI_FW_CRC_LEN; remaining_len = fw_info->frame_size - fw_info->written; @@ -124,7 +122,6 @@ static int nxp_nci_fw_send_chunk(struct nxp_nci_info *info) kfree_skb(skb); -chunk_exit: return r; } diff --git a/drivers/nfc/pn533/i2c.c b/drivers/nfc/pn533/i2c.c index 795da9b85d56..e6bf8cfe3aa7 100644 --- a/drivers/nfc/pn533/i2c.c +++ b/drivers/nfc/pn533/i2c.c @@ -174,9 +174,6 @@ static int pn533_i2c_probe(struct i2c_client *client, struct pn533 *priv; int r = 0; - dev_dbg(&client->dev, "%s\n", __func__); - dev_dbg(&client->dev, "IRQ: %d\n", client->irq); - if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { nfc_err(&client->dev, "Need I2C_FUNC_I2C\n"); return -ENODEV; @@ -195,9 +192,8 @@ static int pn533_i2c_probe(struct i2c_client *client, phy, &i2c_phy_ops, NULL, &phy->i2c_dev->dev); - if (IS_ERR(priv)) { + if (IS_ERR(priv)) return PTR_ERR(priv); - } phy->priv = priv; r = pn532_i2c_nfc_alloc(priv, PN533_NO_TYPE_B_PROTOCOLS, &client->dev); @@ -239,8 +235,6 @@ static int pn533_i2c_remove(struct i2c_client *client) { struct pn533_i2c_phy *phy = i2c_get_clientdata(client); - dev_dbg(&client->dev, "%s\n", __func__); - free_irq(client->irq, phy); pn53x_unregister_nfc(phy->priv); @@ -249,7 +243,7 @@ static int pn533_i2c_remove(struct i2c_client *client) return 0; } -static const struct of_device_id of_pn533_i2c_match[] = { +static const struct of_device_id of_pn533_i2c_match[] __maybe_unused = { { .compatible = "nxp,pn532", }, /* * NOTE: The use of the compatibles with the trailing "...-i2c" is diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c index 2c7f9916f206..cd64bfe20402 100644 --- a/drivers/nfc/pn533/pn533.c +++ b/drivers/nfc/pn533/pn533.c @@ -1075,8 +1075,6 @@ static int pn533_tm_get_data_complete(struct pn533 *dev, void *arg, u8 status, ret, mi; int rc; - dev_dbg(dev->dev, "%s\n", __func__); - if (IS_ERR(resp)) { skb_queue_purge(&dev->resp_q); return PTR_ERR(resp); @@ -1124,8 +1122,6 @@ static void pn533_wq_tm_mi_recv(struct work_struct *work) struct sk_buff *skb; int rc; - dev_dbg(dev->dev, "%s\n", __func__); - skb = pn533_alloc_skb(dev, 0); if (!skb) return; @@ -1148,8 +1144,6 @@ static void pn533_wq_tm_mi_send(struct work_struct *work) struct sk_buff *skb; int rc; - dev_dbg(dev->dev, "%s\n", __func__); - /* Grab the first skb in the queue */ skb = skb_dequeue(&dev->fragment_skb); if (skb == NULL) { /* No more data */ @@ -1186,8 +1180,6 @@ static void pn533_wq_tg_get_data(struct work_struct *work) struct sk_buff *skb; int rc; - dev_dbg(dev->dev, "%s\n", __func__); - skb = pn533_alloc_skb(dev, 0); if (!skb) return; @@ -1206,8 +1198,6 @@ static int pn533_init_target_complete(struct pn533 *dev, struct sk_buff *resp) size_t gb_len; int rc; - dev_dbg(dev->dev, "%s\n", __func__); - if (resp->len < ATR_REQ_GB_OFFSET + 1) return -EINVAL; @@ -1260,8 +1250,6 @@ static int pn533_rf_complete(struct pn533 *dev, void *arg, { int rc = 0; - dev_dbg(dev->dev, "%s\n", __func__); - if (IS_ERR(resp)) { rc = PTR_ERR(resp); @@ -1283,8 +1271,6 @@ static void pn533_wq_rf(struct work_struct *work) struct sk_buff *skb; int rc; - dev_dbg(dev->dev, "%s\n", __func__); - skb = pn533_alloc_skb(dev, 2); if (!skb) return; @@ -1360,8 +1346,6 @@ static int pn533_poll_dep(struct nfc_dev *nfc_dev) u8 *next, nfcid3[NFC_NFCID3_MAXSIZE]; u8 passive_data[PASSIVE_DATA_LEN] = {0x00, 0xff, 0xff, 0x00, 0x3}; - dev_dbg(dev->dev, "%s", __func__); - if (!dev->gb) { dev->gb = nfc_get_local_general_bytes(nfc_dev, &dev->gb_len); @@ -1511,8 +1495,6 @@ static int pn533_poll_complete(struct pn533 *dev, void *arg, struct pn533_poll_modulations *cur_mod; int rc; - dev_dbg(dev->dev, "%s\n", __func__); - if (IS_ERR(resp)) { rc = PTR_ERR(resp); @@ -1783,8 +1765,6 @@ static int pn533_activate_target_nfcdep(struct pn533 *dev) struct sk_buff *skb; struct sk_buff *resp; - dev_dbg(dev->dev, "%s\n", __func__); - skb = pn533_alloc_skb(dev, sizeof(u8) * 2); /*TG + Next*/ if (!skb) return -ENOMEM; @@ -1866,8 +1846,6 @@ static int pn533_deactivate_target_complete(struct pn533 *dev, void *arg, { int rc = 0; - dev_dbg(dev->dev, "%s\n", __func__); - if (IS_ERR(resp)) { rc = PTR_ERR(resp); @@ -1892,8 +1870,6 @@ static void pn533_deactivate_target(struct nfc_dev *nfc_dev, struct sk_buff *skb; int rc; - dev_dbg(dev->dev, "%s\n", __func__); - if (!dev->tgt_active_prot) { nfc_err(dev->dev, "There is no active target\n"); return; @@ -1988,8 +1964,6 @@ static int pn533_dep_link_up(struct nfc_dev *nfc_dev, struct nfc_target *target, u8 *next, *arg, nfcid3[NFC_NFCID3_MAXSIZE]; u8 passive_data[PASSIVE_DATA_LEN] = {0x00, 0xff, 0xff, 0x00, 0x3}; - dev_dbg(dev->dev, "%s\n", __func__); - if (dev->poll_mod_count) { nfc_err(dev->dev, "Cannot bring the DEP link up while polling\n"); @@ -2067,8 +2041,6 @@ static int pn533_dep_link_down(struct nfc_dev *nfc_dev) { struct pn533 *dev = nfc_get_drvdata(nfc_dev); - dev_dbg(dev->dev, "%s\n", __func__); - pn533_poll_reset_mod_list(dev); if (dev->tgt_mode || dev->tgt_active_prot) @@ -2092,8 +2064,6 @@ static struct sk_buff *pn533_build_response(struct pn533 *dev) struct sk_buff *skb, *tmp, *t; unsigned int skb_len = 0, tmp_len = 0; - dev_dbg(dev->dev, "%s\n", __func__); - if (skb_queue_empty(&dev->resp_q)) return NULL; @@ -2133,8 +2103,6 @@ static int pn533_data_exchange_complete(struct pn533 *dev, void *_arg, int rc = 0; u8 status, ret, mi; - dev_dbg(dev->dev, "%s\n", __func__); - if (IS_ERR(resp)) { rc = PTR_ERR(resp); goto _error; @@ -2288,8 +2256,6 @@ static int pn533_transceive(struct nfc_dev *nfc_dev, struct pn533_data_exchange_arg *arg = NULL; int rc; - dev_dbg(dev->dev, "%s\n", __func__); - if (!dev->tgt_active_prot) { nfc_err(dev->dev, "Can't exchange data if there is no active target\n"); @@ -2356,8 +2322,6 @@ static int pn533_tm_send_complete(struct pn533 *dev, void *arg, { u8 status; - dev_dbg(dev->dev, "%s\n", __func__); - if (IS_ERR(resp)) return PTR_ERR(resp); @@ -2388,8 +2352,6 @@ static int pn533_tm_send(struct nfc_dev *nfc_dev, struct sk_buff *skb) struct pn533 *dev = nfc_get_drvdata(nfc_dev); int rc; - dev_dbg(dev->dev, "%s\n", __func__); - /* let's split in multiple chunks if size's too big */ if (skb->len > PN533_CMD_DATAEXCH_DATA_MAXLEN) { rc = pn533_fill_fragment_skbs(dev, skb); @@ -2426,8 +2388,6 @@ static void pn533_wq_mi_recv(struct work_struct *work) struct sk_buff *skb; int rc; - dev_dbg(dev->dev, "%s\n", __func__); - skb = pn533_alloc_skb(dev, PN533_CMD_DATAEXCH_HEAD_LEN); if (!skb) goto error; @@ -2476,8 +2436,6 @@ static void pn533_wq_mi_send(struct work_struct *work) struct sk_buff *skb; int rc; - dev_dbg(dev->dev, "%s\n", __func__); - /* Grab the first skb in the queue */ skb = skb_dequeue(&dev->fragment_skb); @@ -2533,8 +2491,6 @@ static int pn533_set_configuration(struct pn533 *dev, u8 cfgitem, u8 *cfgdata, struct sk_buff *resp; int skb_len; - dev_dbg(dev->dev, "%s\n", __func__); - skb_len = sizeof(cfgitem) + cfgdata_len; /* cfgitem + cfgdata */ skb = pn533_alloc_skb(dev, skb_len); @@ -2580,8 +2536,6 @@ static int pn533_pasori_fw_reset(struct pn533 *dev) struct sk_buff *skb; struct sk_buff *resp; - dev_dbg(dev->dev, "%s\n", __func__); - skb = pn533_alloc_skb(dev, sizeof(u8)); if (!skb) return -ENOMEM; diff --git a/drivers/nfc/pn533/uart.c b/drivers/nfc/pn533/uart.c index a0665d8ea85b..7bdaf8263070 100644 --- a/drivers/nfc/pn533/uart.c +++ b/drivers/nfc/pn533/uart.c @@ -319,7 +319,7 @@ static struct serdev_device_driver pn532_uart_driver = { .remove = pn532_uart_remove, .driver = { .name = "pn532_uart", - .of_match_table = of_match_ptr(pn532_uart_of_match), + .of_match_table = pn532_uart_of_match, }, }; diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index 84d2bfabf42b..bd7f7478d189 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -354,8 +354,6 @@ static void pn533_acr122_poweron_rdr_resp(struct urb *urb) { struct pn533_acr122_poweron_rdr_arg *arg = urb->context; - dev_dbg(&urb->dev->dev, "%s\n", __func__); - print_hex_dump_debug("ACR122 RX: ", DUMP_PREFIX_NONE, 16, 1, urb->transfer_buffer, urb->transfer_buffer_length, false); @@ -375,8 +373,6 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy) void *cntx; struct pn533_acr122_poweron_rdr_arg arg; - dev_dbg(&phy->udev->dev, "%s\n", __func__); - buffer = kmemdup(cmd, sizeof(cmd), GFP_KERNEL); if (!buffer) return -ENOMEM; diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index 4ac8cb262559..de59e439c369 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -50,7 +50,7 @@ static const struct i2c_device_id pn544_hci_i2c_id_table[] = { MODULE_DEVICE_TABLE(i2c, pn544_hci_i2c_id_table); -static const struct acpi_device_id pn544_hci_i2c_acpi_match[] = { +static const struct acpi_device_id pn544_hci_i2c_acpi_match[] __maybe_unused = { {"NXP5440", 0}, {} }; @@ -241,8 +241,6 @@ static int pn544_hci_i2c_enable(void *phy_id) { struct pn544_i2c_phy *phy = phy_id; - pr_info("%s\n", __func__); - pn544_hci_i2c_enable_mode(phy, PN544_HCI_MODE); phy->powered = 1; @@ -875,9 +873,6 @@ static int pn544_hci_i2c_probe(struct i2c_client *client, struct pn544_i2c_phy *phy; int r = 0; - dev_dbg(&client->dev, "%s\n", __func__); - dev_dbg(&client->dev, "IRQ: %d\n", client->irq); - if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { nfc_err(&client->dev, "Need I2C_FUNC_I2C\n"); return -ENODEV; @@ -937,8 +932,6 @@ static int pn544_hci_i2c_remove(struct i2c_client *client) { struct pn544_i2c_phy *phy = i2c_get_clientdata(client); - dev_dbg(&client->dev, "%s\n", __func__); - cancel_work_sync(&phy->fw_work); if (phy->fw_work_state != FW_WORK_STATE_IDLE) pn544_hci_i2c_fw_work_complete(phy, -ENODEV); @@ -951,7 +944,7 @@ static int pn544_hci_i2c_remove(struct i2c_client *client) return 0; } -static const struct of_device_id of_pn544_i2c_match[] = { +static const struct of_device_id of_pn544_i2c_match[] __maybe_unused = { { .compatible = "nxp,pn544-i2c", }, {}, }; diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c index 8e4d355dc3ae..4df926cc37d0 100644 --- a/drivers/nfc/port100.c +++ b/drivers/nfc/port100.c @@ -94,7 +94,7 @@ struct port100; typedef void (*port100_send_async_complete_t)(struct port100 *dev, void *arg, struct sk_buff *resp); -/** +/* * Setting sets structure for in_set_rf command * * @in_*_set_number: Represent the entry indexes in the port-100 RF Base Table. @@ -145,7 +145,7 @@ static const struct port100_in_rf_setting in_rf_settings[] = { }; /** - * Setting sets structure for tg_set_rf command + * struct port100_tg_rf_setting - Setting sets structure for tg_set_rf command * * @tg_set_number: Represents the entry index in the port-100 RF Base Table. * This table contains multiple RF setting sets required for RF diff --git a/drivers/nfc/s3fwrn5/i2c.c b/drivers/nfc/s3fwrn5/i2c.c index 897394167522..4d1cf1bb55b0 100644 --- a/drivers/nfc/s3fwrn5/i2c.c +++ b/drivers/nfc/s3fwrn5/i2c.c @@ -6,6 +6,7 @@ * Robert Baldyga */ +#include #include #include #include @@ -22,6 +23,7 @@ struct s3fwrn5_i2c_phy { struct phy_common common; struct i2c_client *i2c_dev; + struct clk *clk; unsigned int irq_skip:1; }; @@ -207,17 +209,40 @@ static int s3fwrn5_i2c_probe(struct i2c_client *client, if (ret < 0) return ret; + phy->clk = devm_clk_get_optional(&client->dev, NULL); + if (IS_ERR(phy->clk)) + return dev_err_probe(&client->dev, PTR_ERR(phy->clk), + "failed to get clock\n"); + + /* + * S3FWRN5 depends on a clock input ("XI" pin) to function properly. + * Depending on the hardware configuration this could be an always-on + * oscillator or some external clock that must be explicitly enabled. + * Make sure the clock is running before starting S3FWRN5. + */ + ret = clk_prepare_enable(phy->clk); + if (ret < 0) { + dev_err(&client->dev, "failed to enable clock: %d\n", ret); + return ret; + } + ret = s3fwrn5_probe(&phy->common.ndev, phy, &phy->i2c_dev->dev, &i2c_phy_ops); if (ret < 0) - return ret; + goto disable_clk; ret = devm_request_threaded_irq(&client->dev, phy->i2c_dev->irq, NULL, s3fwrn5_i2c_irq_thread_fn, IRQF_ONESHOT, S3FWRN5_I2C_DRIVER_NAME, phy); if (ret) - s3fwrn5_remove(phy->common.ndev); + goto s3fwrn5_remove; + return 0; + +s3fwrn5_remove: + s3fwrn5_remove(phy->common.ndev); +disable_clk: + clk_disable_unprepare(phy->clk); return ret; } @@ -226,6 +251,7 @@ static int s3fwrn5_i2c_remove(struct i2c_client *client) struct s3fwrn5_i2c_phy *phy = i2c_get_clientdata(client); s3fwrn5_remove(phy->common.ndev); + clk_disable_unprepare(phy->clk); return 0; } @@ -236,7 +262,7 @@ static const struct i2c_device_id s3fwrn5_i2c_id_table[] = { }; MODULE_DEVICE_TABLE(i2c, s3fwrn5_i2c_id_table); -static const struct of_device_id of_s3fwrn5_i2c_match[] = { +static const struct of_device_id of_s3fwrn5_i2c_match[] __maybe_unused = { { .compatible = "samsung,s3fwrn5-i2c", }, {} }; diff --git a/drivers/nfc/st-nci/i2c.c b/drivers/nfc/st-nci/i2c.c index 55d600cd3861..46981405e8b1 100644 --- a/drivers/nfc/st-nci/i2c.c +++ b/drivers/nfc/st-nci/i2c.c @@ -206,9 +206,6 @@ static int st_nci_i2c_probe(struct i2c_client *client, struct st_nci_i2c_phy *phy; int r; - dev_dbg(&client->dev, "%s\n", __func__); - dev_dbg(&client->dev, "IRQ: %d\n", client->irq); - if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { nfc_err(&client->dev, "Need I2C_FUNC_I2C\n"); return -ENODEV; @@ -261,8 +258,6 @@ static int st_nci_i2c_remove(struct i2c_client *client) { struct st_nci_i2c_phy *phy = i2c_get_clientdata(client); - dev_dbg(&client->dev, "%s\n", __func__); - ndlc_remove(phy->ndlc); return 0; @@ -274,14 +269,14 @@ static const struct i2c_device_id st_nci_i2c_id_table[] = { }; MODULE_DEVICE_TABLE(i2c, st_nci_i2c_id_table); -static const struct acpi_device_id st_nci_i2c_acpi_match[] = { +static const struct acpi_device_id st_nci_i2c_acpi_match[] __maybe_unused = { {"SMO2101"}, {"SMO2102"}, {} }; MODULE_DEVICE_TABLE(acpi, st_nci_i2c_acpi_match); -static const struct of_device_id of_st_nci_i2c_match[] = { +static const struct of_device_id of_st_nci_i2c_match[] __maybe_unused = { { .compatible = "st,st21nfcb-i2c", }, { .compatible = "st,st21nfcb_i2c", }, { .compatible = "st,st21nfcc-i2c", }, diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index 1cba8f69d3ae..5fd89f72969d 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -470,8 +470,6 @@ int st_nci_disable_se(struct nci_dev *ndev, u32 se_idx) { int r; - pr_debug("st_nci_disable_se\n"); - /* * According to upper layer, se_idx == NFC_SE_UICC when * info->se_info.se_status->is_uicc_enable is true should never happen @@ -496,8 +494,6 @@ int st_nci_enable_se(struct nci_dev *ndev, u32 se_idx) { int r; - pr_debug("st_nci_enable_se\n"); - /* * According to upper layer, se_idx == NFC_SE_UICC when * info->se_info.se_status->is_uicc_enable is true should never happen. @@ -534,10 +530,8 @@ static int st_nci_hci_network_init(struct nci_dev *ndev) dest_params = kzalloc(sizeof(struct core_conn_create_dest_spec_params) + sizeof(struct dest_spec_params), GFP_KERNEL); - if (dest_params == NULL) { - r = -ENOMEM; - goto exit; - } + if (dest_params == NULL) + return -ENOMEM; dest_params->type = NCI_DESTINATION_SPECIFIC_PARAM_NFCEE_TYPE; dest_params->length = sizeof(struct dest_spec_params); @@ -594,8 +588,6 @@ static int st_nci_hci_network_init(struct nci_dev *ndev) free_dest_params: kfree(dest_params); - -exit: return r; } @@ -606,8 +598,6 @@ int st_nci_discover_se(struct nci_dev *ndev) int se_count = 0; struct st_nci_info *info = nci_get_drvdata(ndev); - pr_debug("st_nci_discover_se\n"); - r = st_nci_hci_network_init(ndev); if (r != 0) return r; diff --git a/drivers/nfc/st-nci/spi.c b/drivers/nfc/st-nci/spi.c index 09df6ea65840..250d56f204c3 100644 --- a/drivers/nfc/st-nci/spi.c +++ b/drivers/nfc/st-nci/spi.c @@ -216,9 +216,6 @@ static int st_nci_spi_probe(struct spi_device *dev) struct st_nci_spi_phy *phy; int r; - dev_dbg(&dev->dev, "%s\n", __func__); - dev_dbg(&dev->dev, "IRQ: %d\n", dev->irq); - /* Check SPI platform functionnalities */ if (!dev) { pr_debug("%s: dev is NULL. Device is not accessible.\n", @@ -274,8 +271,6 @@ static int st_nci_spi_remove(struct spi_device *dev) { struct st_nci_spi_phy *phy = spi_get_drvdata(dev); - dev_dbg(&dev->dev, "%s\n", __func__); - ndlc_remove(phy->ndlc); return 0; @@ -287,13 +282,13 @@ static struct spi_device_id st_nci_spi_id_table[] = { }; MODULE_DEVICE_TABLE(spi, st_nci_spi_id_table); -static const struct acpi_device_id st_nci_spi_acpi_match[] = { +static const struct acpi_device_id st_nci_spi_acpi_match[] __maybe_unused = { {"SMO2101", 0}, {} }; MODULE_DEVICE_TABLE(acpi, st_nci_spi_acpi_match); -static const struct of_device_id of_st_nci_spi_match[] = { +static const struct of_device_id of_st_nci_spi_match[] __maybe_unused = { { .compatible = "st,st21nfcb-spi", }, {} }; diff --git a/drivers/nfc/st-nci/vendor_cmds.c b/drivers/nfc/st-nci/vendor_cmds.c index c6a9d30a4dba..94b600029a2a 100644 --- a/drivers/nfc/st-nci/vendor_cmds.c +++ b/drivers/nfc/st-nci/vendor_cmds.c @@ -98,7 +98,7 @@ static int st_nci_hci_dm_get_info(struct nfc_dev *dev, void *data, r = nci_hci_send_cmd(ndev, ST_NCI_DEVICE_MGNT_GATE, ST_NCI_HCI_DM_GETINFO, data, data_len, &skb); if (r) - goto exit; + return r; msg = nfc_vendor_cmd_alloc_reply_skb(dev, ST_NCI_VENDOR_OUI, HCI_DM_GET_INFO, skb->len); @@ -117,7 +117,6 @@ static int st_nci_hci_dm_get_info(struct nfc_dev *dev, void *data, free_skb: kfree_skb(skb); -exit: return r; } @@ -131,7 +130,7 @@ static int st_nci_hci_dm_get_data(struct nfc_dev *dev, void *data, r = nci_hci_send_cmd(ndev, ST_NCI_DEVICE_MGNT_GATE, ST_NCI_HCI_DM_GETDATA, data, data_len, &skb); if (r) - goto exit; + return r; msg = nfc_vendor_cmd_alloc_reply_skb(dev, ST_NCI_VENDOR_OUI, HCI_DM_GET_DATA, skb->len); @@ -150,7 +149,6 @@ static int st_nci_hci_dm_get_data(struct nfc_dev *dev, void *data, free_skb: kfree_skb(skb); -exit: return r; } @@ -216,7 +214,7 @@ static int st_nci_hci_get_param(struct nfc_dev *dev, void *data, r = nci_hci_get_param(ndev, param->gate, param->data, &skb); if (r) - goto exit; + return r; msg = nfc_vendor_cmd_alloc_reply_skb(dev, ST_NCI_VENDOR_OUI, HCI_GET_PARAM, skb->len); @@ -235,7 +233,6 @@ static int st_nci_hci_get_param(struct nfc_dev *dev, void *data, free_skb: kfree_skb(skb); -exit: return r; } @@ -262,7 +259,7 @@ static int st_nci_hci_dm_vdc_measurement_value(struct nfc_dev *dev, void *data, ST_NCI_HCI_DM_VDC_MEASUREMENT_VALUE, data, data_len, &skb); if (r) - goto exit; + return r; msg = nfc_vendor_cmd_alloc_reply_skb(dev, ST_NCI_VENDOR_OUI, HCI_DM_VDC_MEASUREMENT_VALUE, skb->len); @@ -281,7 +278,6 @@ static int st_nci_hci_dm_vdc_measurement_value(struct nfc_dev *dev, void *data, free_skb: kfree_skb(skb); -exit: return r; } @@ -299,7 +295,7 @@ static int st_nci_hci_dm_vdc_value_comparison(struct nfc_dev *dev, void *data, ST_NCI_HCI_DM_VDC_VALUE_COMPARISON, data, data_len, &skb); if (r) - goto exit; + return r; msg = nfc_vendor_cmd_alloc_reply_skb(dev, ST_NCI_VENDOR_OUI, HCI_DM_VDC_VALUE_COMPARISON, skb->len); @@ -318,7 +314,6 @@ static int st_nci_hci_dm_vdc_value_comparison(struct nfc_dev *dev, void *data, free_skb: kfree_skb(skb); -exit: return r; } diff --git a/drivers/nfc/st21nfca/dep.c b/drivers/nfc/st21nfca/dep.c index 8874d605b14f..1ec651e31064 100644 --- a/drivers/nfc/st21nfca/dep.c +++ b/drivers/nfc/st21nfca/dep.c @@ -196,38 +196,29 @@ static int st21nfca_tm_recv_atr_req(struct nfc_hci_dev *hdev, skb_trim(skb, skb->len - 1); - if (!skb->len) { - r = -EIO; - goto exit; - } + if (!skb->len) + return -EIO; - if (skb->len < ST21NFCA_ATR_REQ_MIN_SIZE) { - r = -EPROTO; - goto exit; - } + if (skb->len < ST21NFCA_ATR_REQ_MIN_SIZE) + return -EPROTO; atr_req = (struct st21nfca_atr_req *)skb->data; - if (atr_req->length < sizeof(struct st21nfca_atr_req)) { - r = -EPROTO; - goto exit; - } + if (atr_req->length < sizeof(struct st21nfca_atr_req)) + return -EPROTO; r = st21nfca_tm_send_atr_res(hdev, atr_req); if (r) - goto exit; + return r; gb_len = skb->len - sizeof(struct st21nfca_atr_req); r = nfc_tm_activated(hdev->ndev, NFC_PROTO_NFC_DEP_MASK, NFC_COMM_PASSIVE, atr_req->gbi, gb_len); if (r) - goto exit; + return r; - r = 0; - -exit: - return r; + return 0; } static int st21nfca_tm_send_psl_res(struct nfc_hci_dev *hdev, @@ -280,25 +271,18 @@ static int st21nfca_tm_recv_psl_req(struct nfc_hci_dev *hdev, struct sk_buff *skb) { struct st21nfca_psl_req *psl_req; - int r; skb_trim(skb, skb->len - 1); - if (!skb->len) { - r = -EIO; - goto exit; - } + if (!skb->len) + return -EIO; psl_req = (struct st21nfca_psl_req *)skb->data; - if (skb->len < sizeof(struct st21nfca_psl_req)) { - r = -EIO; - goto exit; - } + if (skb->len < sizeof(struct st21nfca_psl_req)) + return -EIO; - r = st21nfca_tm_send_psl_res(hdev, psl_req); -exit: - return r; + return st21nfca_tm_send_psl_res(hdev, psl_req); } int st21nfca_tm_send_dep_res(struct nfc_hci_dev *hdev, struct sk_buff *skb) @@ -324,7 +308,6 @@ static int st21nfca_tm_recv_dep_req(struct nfc_hci_dev *hdev, { struct st21nfca_dep_req_res *dep_req; u8 size; - int r; struct st21nfca_hci_info *info = nfc_hci_get_clientdata(hdev); skb_trim(skb, skb->len - 1); @@ -332,20 +315,16 @@ static int st21nfca_tm_recv_dep_req(struct nfc_hci_dev *hdev, size = 4; dep_req = (struct st21nfca_dep_req_res *)skb->data; - if (skb->len < size) { - r = -EIO; - goto exit; - } + if (skb->len < size) + return -EIO; if (ST21NFCA_NFC_DEP_DID_BIT_SET(dep_req->pfb)) size++; if (ST21NFCA_NFC_DEP_NAD_BIT_SET(dep_req->pfb)) size++; - if (skb->len < size) { - r = -EIO; - goto exit; - } + if (skb->len < size) + return -EIO; /* Receiving DEP_REQ - Decoding */ switch (ST21NFCA_NFC_DEP_PFB_TYPE(dep_req->pfb)) { @@ -364,8 +343,6 @@ static int st21nfca_tm_recv_dep_req(struct nfc_hci_dev *hdev, skb_pull(skb, size); return nfc_tm_data_received(hdev->ndev, skb); -exit: - return r; } static int st21nfca_tm_event_send_data(struct nfc_hci_dev *hdev, diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c index 23ed11f91213..7a9f4d71707e 100644 --- a/drivers/nfc/st21nfca/i2c.c +++ b/drivers/nfc/st21nfca/i2c.c @@ -502,9 +502,6 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client, struct st21nfca_i2c_phy *phy; int r; - dev_dbg(&client->dev, "%s\n", __func__); - dev_dbg(&client->dev, "IRQ: %d\n", client->irq); - if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { nfc_err(&client->dev, "Need I2C_FUNC_I2C\n"); return -ENODEV; @@ -568,8 +565,6 @@ static int st21nfca_hci_i2c_remove(struct i2c_client *client) { struct st21nfca_i2c_phy *phy = i2c_get_clientdata(client); - dev_dbg(&client->dev, "%s\n", __func__); - st21nfca_hci_remove(phy->hdev); if (phy->powered) @@ -584,13 +579,13 @@ static const struct i2c_device_id st21nfca_hci_i2c_id_table[] = { }; MODULE_DEVICE_TABLE(i2c, st21nfca_hci_i2c_id_table); -static const struct acpi_device_id st21nfca_hci_i2c_acpi_match[] = { +static const struct acpi_device_id st21nfca_hci_i2c_acpi_match[] __maybe_unused = { {"SMO2100", 0}, {} }; MODULE_DEVICE_TABLE(acpi, st21nfca_hci_i2c_acpi_match); -static const struct of_device_id of_st21nfca_i2c_match[] = { +static const struct of_device_id of_st21nfca_i2c_match[] __maybe_unused = { { .compatible = "st,st21nfca-i2c", }, { .compatible = "st,st21nfca_i2c", }, {} diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c index 457854765983..2dc788c363fd 100644 --- a/drivers/nfc/st95hf/core.c +++ b/drivers/nfc/st95hf/core.c @@ -926,10 +926,8 @@ static int st95hf_in_send_cmd(struct nfc_digital_dev *ddev, int len_data_to_tag = 0; skb_resp = nfc_alloc_recv_skb(MAX_RESPONSE_BUFFER_SIZE, GFP_KERNEL); - if (!skb_resp) { - rc = -ENOMEM; - goto error; - } + if (!skb_resp) + return -ENOMEM; switch (stcontext->current_rf_tech) { case NFC_DIGITAL_RF_TECH_106A: @@ -986,7 +984,6 @@ static int st95hf_in_send_cmd(struct nfc_digital_dev *ddev, free_skb_resp: kfree_skb(skb_resp); -error: return rc; } @@ -1059,9 +1056,9 @@ static const struct spi_device_id st95hf_id[] = { }; MODULE_DEVICE_TABLE(spi, st95hf_id); -static const struct of_device_id st95hf_spi_of_match[] = { - { .compatible = "st,st95hf" }, - { }, +static const struct of_device_id st95hf_spi_of_match[] __maybe_unused = { + { .compatible = "st,st95hf" }, + {}, }; MODULE_DEVICE_TABLE(of, st95hf_spi_of_match); diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c index 7b9556291eb1..088d3dd6f6fa 100644 --- a/drivers/nvdimm/blk.c +++ b/drivers/nvdimm/blk.c @@ -228,49 +228,34 @@ static const struct block_device_operations nd_blk_fops = { .submit_bio = nd_blk_submit_bio, }; -static void nd_blk_release_queue(void *q) -{ - blk_cleanup_queue(q); -} - static void nd_blk_release_disk(void *disk) { del_gendisk(disk); - put_disk(disk); + blk_cleanup_disk(disk); } static int nsblk_attach_disk(struct nd_namespace_blk *nsblk) { struct device *dev = &nsblk->common.dev; resource_size_t available_disk_size; - struct request_queue *q; struct gendisk *disk; u64 internal_nlba; internal_nlba = div_u64(nsblk->size, nsblk_internal_lbasize(nsblk)); available_disk_size = internal_nlba * nsblk_sector_size(nsblk); - q = blk_alloc_queue(NUMA_NO_NODE); - if (!q) - return -ENOMEM; - if (devm_add_action_or_reset(dev, nd_blk_release_queue, q)) - return -ENOMEM; - - blk_queue_max_hw_sectors(q, UINT_MAX); - blk_queue_logical_block_size(q, nsblk_sector_size(nsblk)); - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - - disk = alloc_disk(0); + disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) return -ENOMEM; - disk->first_minor = 0; disk->fops = &nd_blk_fops; - disk->queue = q; - disk->flags = GENHD_FL_EXT_DEVT; disk->private_data = nsblk; nvdimm_namespace_disk_name(&nsblk->common, disk->disk_name); + blk_queue_max_hw_sectors(disk->queue, UINT_MAX); + blk_queue_logical_block_size(disk->queue, nsblk_sector_size(nsblk)); + blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); + if (devm_add_action_or_reset(dev, nd_blk_release_disk, disk)) return -ENOMEM; diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 18a267d5073f..92dec4952297 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1521,35 +1521,25 @@ static int btt_blk_init(struct btt *btt) struct nd_btt *nd_btt = btt->nd_btt; struct nd_namespace_common *ndns = nd_btt->ndns; - /* create a new disk and request queue for btt */ - btt->btt_queue = blk_alloc_queue(NUMA_NO_NODE); - if (!btt->btt_queue) + btt->btt_disk = blk_alloc_disk(NUMA_NO_NODE); + if (!btt->btt_disk) return -ENOMEM; - btt->btt_disk = alloc_disk(0); - if (!btt->btt_disk) { - blk_cleanup_queue(btt->btt_queue); - return -ENOMEM; - } - nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name); btt->btt_disk->first_minor = 0; btt->btt_disk->fops = &btt_fops; btt->btt_disk->private_data = btt; - btt->btt_disk->queue = btt->btt_queue; - btt->btt_disk->flags = GENHD_FL_EXT_DEVT; - blk_queue_logical_block_size(btt->btt_queue, btt->sector_size); - blk_queue_max_hw_sectors(btt->btt_queue, UINT_MAX); - blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_queue); + blk_queue_logical_block_size(btt->btt_disk->queue, btt->sector_size); + blk_queue_max_hw_sectors(btt->btt_disk->queue, UINT_MAX); + blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_disk->queue); if (btt_meta_size(btt)) { int rc = nd_integrity_init(btt->btt_disk, btt_meta_size(btt)); if (rc) { del_gendisk(btt->btt_disk); - put_disk(btt->btt_disk); - blk_cleanup_queue(btt->btt_queue); + blk_cleanup_disk(btt->btt_disk); return rc; } } @@ -1564,8 +1554,7 @@ static int btt_blk_init(struct btt *btt) static void btt_blk_cleanup(struct btt *btt) { del_gendisk(btt->btt_disk); - put_disk(btt->btt_disk); - blk_cleanup_queue(btt->btt_queue); + blk_cleanup_disk(btt->btt_disk); } /** diff --git a/drivers/nvdimm/btt.h b/drivers/nvdimm/btt.h index aa53e0b769bd..0c76c0333f6e 100644 --- a/drivers/nvdimm/btt.h +++ b/drivers/nvdimm/btt.h @@ -201,7 +201,6 @@ struct badblocks; /** * struct btt - handle for a BTT instance * @btt_disk: Pointer to the gendisk for BTT device - * @btt_queue: Pointer to the request queue for the BTT device * @arena_list: Head of the list of arenas * @debugfs_dir: Debugfs dentry * @nd_btt: Parent nd_btt struct @@ -219,7 +218,6 @@ struct badblocks; */ struct btt { struct gendisk *btt_disk; - struct request_queue *btt_queue; struct list_head arena_list; struct dentry *debugfs_dir; struct nd_btt *nd_btt; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index ed10a8b66068..1e0615b8565e 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -335,10 +335,9 @@ static const struct attribute_group *pmem_attribute_groups[] = { static void pmem_pagemap_cleanup(struct dev_pagemap *pgmap) { - struct request_queue *q = - container_of(pgmap->ref, struct request_queue, q_usage_counter); + struct pmem_device *pmem = pgmap->owner; - blk_cleanup_queue(q); + blk_cleanup_disk(pmem->disk); } static void pmem_release_queue(void *pgmap) @@ -361,7 +360,6 @@ static void pmem_release_disk(void *__pmem) kill_dax(pmem->dax_dev); put_dax(pmem->dax_dev); del_gendisk(pmem->disk); - put_disk(pmem->disk); } static const struct dev_pagemap_ops fsdax_pagemap_ops = { @@ -422,10 +420,13 @@ static int pmem_attach_disk(struct device *dev, return -EBUSY; } - q = blk_alloc_queue(dev_to_node(dev)); - if (!q) + disk = blk_alloc_disk(nid); + if (!disk) return -ENOMEM; + q = disk->queue; + pmem->disk = disk; + pmem->pgmap.owner = pmem; pmem->pfn_flags = PFN_DEV; pmem->pgmap.ref = &q->q_usage_counter; if (is_nd_pfn(dev)) { @@ -470,14 +471,7 @@ static int pmem_attach_disk(struct device *dev, if (pmem->pfn_flags & PFN_MAP) blk_queue_flag_set(QUEUE_FLAG_DAX, q); - disk = alloc_disk_node(0, nid); - if (!disk) - return -ENOMEM; - pmem->disk = disk; - disk->fops = &pmem_fops; - disk->queue = q; - disk->flags = GENHD_FL_EXT_DEVT; disk->private_data = pmem; nvdimm_namespace_disk_name(ndns, disk->disk_name); set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset) @@ -491,7 +485,6 @@ static int pmem_attach_disk(struct device *dev, flags = DAXDEV_F_SYNC; dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops, flags); if (IS_ERR(dax_dev)) { - put_disk(disk); return PTR_ERR(dax_dev); } dax_write_cache(dax_dev, nvdimm_has_cache(nd_region)); diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 494675aeaaad..c3f3d77f1aac 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -21,7 +21,7 @@ config NVME_MULTIPATH help This option enables support for multipath access to NVMe subsystems. If this option is enabled only a single - /dev/nvmeXnY device will show up for each NVMe namespaces, + /dev/nvmeXnY device will show up for each NVMe namespace, even if it is accessible through multiple controllers. config NVME_HWMON diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 66973bb56305..80c656dcbbac 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -57,6 +57,26 @@ static bool force_apst; module_param(force_apst, bool, 0644); MODULE_PARM_DESC(force_apst, "allow APST for newly enumerated devices even if quirked off"); +static unsigned long apst_primary_timeout_ms = 100; +module_param(apst_primary_timeout_ms, ulong, 0644); +MODULE_PARM_DESC(apst_primary_timeout_ms, + "primary APST timeout in ms"); + +static unsigned long apst_secondary_timeout_ms = 2000; +module_param(apst_secondary_timeout_ms, ulong, 0644); +MODULE_PARM_DESC(apst_secondary_timeout_ms, + "secondary APST timeout in ms"); + +static unsigned long apst_primary_latency_tol_us = 15000; +module_param(apst_primary_latency_tol_us, ulong, 0644); +MODULE_PARM_DESC(apst_primary_latency_tol_us, + "primary APST latency tolerance in us"); + +static unsigned long apst_secondary_latency_tol_us = 100000; +module_param(apst_secondary_latency_tol_us, ulong, 0644); +MODULE_PARM_DESC(apst_secondary_latency_tol_us, + "secondary APST latency tolerance in us"); + static bool streams; module_param(streams, bool, 0644); MODULE_PARM_DESC(streams, "turn on support for Streams write directives"); @@ -701,9 +721,7 @@ EXPORT_SYMBOL_GPL(__nvme_check_ready); static int nvme_toggle_streams(struct nvme_ctrl *ctrl, bool enable) { - struct nvme_command c; - - memset(&c, 0, sizeof(c)); + struct nvme_command c = { }; c.directive.opcode = nvme_admin_directive_send; c.directive.nsid = cpu_to_le32(NVME_NSID_ALL); @@ -728,9 +746,8 @@ static int nvme_enable_streams(struct nvme_ctrl *ctrl) static int nvme_get_stream_params(struct nvme_ctrl *ctrl, struct streams_directive_params *s, u32 nsid) { - struct nvme_command c; + struct nvme_command c = { }; - memset(&c, 0, sizeof(c)); memset(s, 0, sizeof(*s)); c.directive.opcode = nvme_admin_directive_recv; @@ -1440,10 +1457,9 @@ static int nvme_features(struct nvme_ctrl *dev, u8 op, unsigned int fid, unsigned int dword11, void *buffer, size_t buflen, u32 *result) { union nvme_result res = { 0 }; - struct nvme_command c; + struct nvme_command c = { }; int ret; - memset(&c, 0, sizeof(c)); c.features.opcode = op; c.features.fid = cpu_to_le32(fid); c.features.dword11 = cpu_to_le32(dword11); @@ -1522,36 +1538,6 @@ static void nvme_enable_aen(struct nvme_ctrl *ctrl) queue_work(nvme_wq, &ctrl->async_event_work); } -/* - * Issue ioctl requests on the first available path. Note that unlike normal - * block layer requests we will not retry failed request on another controller. - */ -struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk, - struct nvme_ns_head **head, int *srcu_idx) -{ -#ifdef CONFIG_NVME_MULTIPATH - if (disk->fops == &nvme_ns_head_ops) { - struct nvme_ns *ns; - - *head = disk->private_data; - *srcu_idx = srcu_read_lock(&(*head)->srcu); - ns = nvme_find_path(*head); - if (!ns) - srcu_read_unlock(&(*head)->srcu, *srcu_idx); - return ns; - } -#endif - *head = NULL; - *srcu_idx = -1; - return disk->private_data; -} - -void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx) -{ - if (head) - srcu_read_unlock(&head->srcu, idx); -} - static int nvme_ns_open(struct nvme_ns *ns) { @@ -1601,9 +1587,8 @@ int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo) static void nvme_init_integrity(struct gendisk *disk, u16 ms, u8 pi_type, u32 max_integrity_segments) { - struct blk_integrity integrity; + struct blk_integrity integrity = { }; - memset(&integrity, 0, sizeof(integrity)); switch (pi_type) { case NVME_NS_DPS_PI_TYPE3: integrity.profile = &t10_pi_type3_crc; @@ -1948,30 +1933,45 @@ static char nvme_pr_type(enum pr_type type) } }; +static int nvme_send_ns_head_pr_command(struct block_device *bdev, + struct nvme_command *c, u8 data[16]) +{ + struct nvme_ns_head *head = bdev->bd_disk->private_data; + int srcu_idx = srcu_read_lock(&head->srcu); + struct nvme_ns *ns = nvme_find_path(head); + int ret = -EWOULDBLOCK; + + if (ns) { + c->common.nsid = cpu_to_le32(ns->head->ns_id); + ret = nvme_submit_sync_cmd(ns->queue, c, data, 16); + } + srcu_read_unlock(&head->srcu, srcu_idx); + return ret; +} + +static int nvme_send_ns_pr_command(struct nvme_ns *ns, struct nvme_command *c, + u8 data[16]) +{ + c->common.nsid = cpu_to_le32(ns->head->ns_id); + return nvme_submit_sync_cmd(ns->queue, c, data, 16); +} + static int nvme_pr_command(struct block_device *bdev, u32 cdw10, u64 key, u64 sa_key, u8 op) { - struct nvme_ns_head *head = NULL; - struct nvme_ns *ns; - struct nvme_command c; - int srcu_idx, ret; + struct nvme_command c = { }; u8 data[16] = { 0, }; - ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx); - if (unlikely(!ns)) - return -EWOULDBLOCK; - put_unaligned_le64(key, &data[0]); put_unaligned_le64(sa_key, &data[8]); - memset(&c, 0, sizeof(c)); c.common.opcode = op; - c.common.nsid = cpu_to_le32(ns->head->ns_id); c.common.cdw10 = cpu_to_le32(cdw10); - ret = nvme_submit_sync_cmd(ns->queue, &c, data, 16); - nvme_put_ns_from_disk(head, srcu_idx); - return ret; + if (IS_ENABLED(CONFIG_NVME_MULTIPATH) && + bdev->bd_disk->fops == &nvme_ns_head_ops) + return nvme_send_ns_head_pr_command(bdev, &c, data); + return nvme_send_ns_pr_command(bdev->bd_disk->private_data, &c, data); } static int nvme_pr_register(struct block_device *bdev, u64 old, @@ -2036,9 +2036,8 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len, bool send) { struct nvme_ctrl *ctrl = data; - struct nvme_command cmd; + struct nvme_command cmd = { }; - memset(&cmd, 0, sizeof(cmd)); if (send) cmd.common.opcode = nvme_admin_security_send; else @@ -2053,6 +2052,17 @@ int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len, EXPORT_SYMBOL_GPL(nvme_sec_submit); #endif /* CONFIG_BLK_SED_OPAL */ +#ifdef CONFIG_BLK_DEV_ZONED +static int nvme_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data) +{ + return nvme_ns_report_zones(disk->private_data, sector, nr_zones, cb, + data); +} +#else +#define nvme_report_zones NULL +#endif /* CONFIG_BLK_DEV_ZONED */ + static const struct block_device_operations nvme_bdev_ops = { .owner = THIS_MODULE, .ioctl = nvme_ioctl, @@ -2217,14 +2227,54 @@ static int nvme_configure_acre(struct nvme_ctrl *ctrl) return ret; } +/* + * The function checks whether the given total (exlat + enlat) latency of + * a power state allows the latter to be used as an APST transition target. + * It does so by comparing the latency to the primary and secondary latency + * tolerances defined by module params. If there's a match, the corresponding + * timeout value is returned and the matching tolerance index (1 or 2) is + * reported. + */ +static bool nvme_apst_get_transition_time(u64 total_latency, + u64 *transition_time, unsigned *last_index) +{ + if (total_latency <= apst_primary_latency_tol_us) { + if (*last_index == 1) + return false; + *last_index = 1; + *transition_time = apst_primary_timeout_ms; + return true; + } + if (apst_secondary_timeout_ms && + total_latency <= apst_secondary_latency_tol_us) { + if (*last_index <= 2) + return false; + *last_index = 2; + *transition_time = apst_secondary_timeout_ms; + return true; + } + return false; +} + /* * APST (Autonomous Power State Transition) lets us program a table of power * state transitions that the controller will perform automatically. - * We configure it with a simple heuristic: we are willing to spend at most 2% - * of the time transitioning between power states. Therefore, when running in - * any given state, we will enter the next lower-power non-operational state - * after waiting 50 * (enlat + exlat) microseconds, as long as that state's exit - * latency is under the requested maximum latency. + * + * Depending on module params, one of the two supported techniques will be used: + * + * - If the parameters provide explicit timeouts and tolerances, they will be + * used to build a table with up to 2 non-operational states to transition to. + * The default parameter values were selected based on the values used by + * Microsoft's and Intel's NVMe drivers. Yet, since we don't implement dynamic + * regeneration of the APST table in the event of switching between external + * and battery power, the timeouts and tolerances reflect a compromise + * between values used by Microsoft for AC and battery scenarios. + * - If not, we'll configure the table with a simple heuristic: we are willing + * to spend at most 2% of the time transitioning between power states. + * Therefore, when running in any given state, we will enter the next + * lower-power non-operational state after waiting 50 * (enlat + exlat) + * microseconds, as long as that state's exit latency is under the requested + * maximum latency. * * We will not autonomously enter any non-operational state for which the total * latency exceeds ps_max_latency_us. @@ -2240,6 +2290,7 @@ static int nvme_configure_apst(struct nvme_ctrl *ctrl) int max_ps = -1; int state; int ret; + unsigned last_lt_index = UINT_MAX; /* * If APST isn't supported or if we haven't been initialized yet, @@ -2298,13 +2349,19 @@ static int nvme_configure_apst(struct nvme_ctrl *ctrl) le32_to_cpu(ctrl->psd[state].entry_lat); /* - * This state is good. Use it as the APST idle target for - * higher power states. + * This state is good. It can be used as the APST idle target + * for higher power states. */ - transition_ms = total_latency_us + 19; - do_div(transition_ms, 20); - if (transition_ms > (1 << 24) - 1) - transition_ms = (1 << 24) - 1; + if (apst_primary_timeout_ms && apst_primary_latency_tol_us) { + if (!nvme_apst_get_transition_time(total_latency_us, + &transition_ms, &last_lt_index)) + continue; + } else { + transition_ms = total_latency_us + 19; + do_div(transition_ms, 20); + if (transition_ms > (1 << 24) - 1) + transition_ms = (1 << 24) - 1; + } target = cpu_to_le64((state << 3) | (transition_ms << 8)); if (max_ps == -1) @@ -3701,7 +3758,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid, disk->fops = &nvme_bdev_ops; disk->private_data = ns; disk->queue = ns->queue; - disk->flags = GENHD_FL_EXT_DEVT; /* * Without the multipath code enabled, multiple controller per * subsystems are visible as devices and thus we cannot use the @@ -4069,6 +4125,11 @@ static int nvme_class_uevent(struct device *dev, struct kobj_uevent_env *env) ret = add_uevent_var(env, "NVME_HOST_TRADDR=%s", opts->host_traddr ?: "none"); + if (ret) + return ret; + + ret = add_uevent_var(env, "NVME_HOST_IFACE=%s", + opts->host_iface ?: "none"); } return ret; } diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 34a84d2086c7..1e6a7cc056ca 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -112,6 +112,9 @@ int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size) if (ctrl->opts->mask & NVMF_OPT_HOST_TRADDR) len += scnprintf(buf + len, size - len, "%shost_traddr=%s", (len) ? "," : "", ctrl->opts->host_traddr); + if (ctrl->opts->mask & NVMF_OPT_HOST_IFACE) + len += scnprintf(buf + len, size - len, "%shost_iface=%s", + (len) ? "," : "", ctrl->opts->host_iface); len += scnprintf(buf + len, size - len, "\n"); return len; @@ -187,11 +190,10 @@ EXPORT_SYMBOL_GPL(nvmf_reg_read32); */ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val) { - struct nvme_command cmd; + struct nvme_command cmd = { }; union nvme_result res; int ret; - memset(&cmd, 0, sizeof(cmd)); cmd.prop_get.opcode = nvme_fabrics_command; cmd.prop_get.fctype = nvme_fabrics_type_property_get; cmd.prop_get.attrib = 1; @@ -233,10 +235,9 @@ EXPORT_SYMBOL_GPL(nvmf_reg_read64); */ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val) { - struct nvme_command cmd; + struct nvme_command cmd = { }; int ret; - memset(&cmd, 0, sizeof(cmd)); cmd.prop_set.opcode = nvme_fabrics_command; cmd.prop_set.fctype = nvme_fabrics_type_property_set; cmd.prop_set.attrib = 0; @@ -254,28 +255,23 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val) EXPORT_SYMBOL_GPL(nvmf_reg_write32); /** - * nvmf_log_connect_error() - Error-parsing-diagnostic print - * out function for connect() errors. - * - * @ctrl: the specific /dev/nvmeX device that had the error. - * - * @errval: Error code to be decoded in a more human-friendly - * printout. - * - * @offset: For use with the NVMe error code NVME_SC_CONNECT_INVALID_PARAM. - * - * @cmd: This is the SQE portion of a submission capsule. - * - * @data: This is the "Data" portion of a submission capsule. + * nvmf_log_connect_error() - Error-parsing-diagnostic print out function for + * connect() errors. + * @ctrl: The specific /dev/nvmeX device that had the error. + * @errval: Error code to be decoded in a more human-friendly + * printout. + * @offset: For use with the NVMe error code + * NVME_SC_CONNECT_INVALID_PARAM. + * @cmd: This is the SQE portion of a submission capsule. + * @data: This is the "Data" portion of a submission capsule. */ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl, int errval, int offset, struct nvme_command *cmd, struct nvmf_connect_data *data) { - int err_sctype = errval & (~NVME_SC_DNR); + int err_sctype = errval & ~NVME_SC_DNR; switch (err_sctype) { - case (NVME_SC_CONNECT_INVALID_PARAM): if (offset >> 16) { char *inv_data = "Connect Invalid Data Parameter"; @@ -318,35 +314,30 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl, } } break; - case NVME_SC_CONNECT_INVALID_HOST: dev_err(ctrl->device, "Connect for subsystem %s is not allowed, hostnqn: %s\n", data->subsysnqn, data->hostnqn); break; - case NVME_SC_CONNECT_CTRL_BUSY: dev_err(ctrl->device, "Connect command failed: controller is busy or not available\n"); break; - case NVME_SC_CONNECT_FORMAT: dev_err(ctrl->device, "Connect incompatible format: %d", cmd->connect.recfmt); break; - case NVME_SC_HOST_PATH_ERROR: dev_err(ctrl->device, "Connect command failed: host path error\n"); break; - default: dev_err(ctrl->device, "Connect command failed, error wo/DNR bit: %d\n", err_sctype); break; - } /* switch (err_sctype) */ + } } /** @@ -371,12 +362,11 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl, */ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) { - struct nvme_command cmd; + struct nvme_command cmd = { }; union nvme_result res; struct nvmf_connect_data *data; int ret; - memset(&cmd, 0, sizeof(cmd)); cmd.connect.opcode = nvme_fabrics_command; cmd.connect.fctype = nvme_fabrics_type_connect; cmd.connect.qid = 0; @@ -439,12 +429,11 @@ EXPORT_SYMBOL_GPL(nvmf_connect_admin_queue); */ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid, bool poll) { - struct nvme_command cmd; + struct nvme_command cmd = { }; struct nvmf_connect_data *data; union nvme_result res; int ret; - memset(&cmd, 0, sizeof(cmd)); cmd.connect.opcode = nvme_fabrics_command; cmd.connect.fctype = nvme_fabrics_type_connect; cmd.connect.qid = cpu_to_le16(qid); @@ -550,6 +539,7 @@ static const match_table_t opt_tokens = { { NVMF_OPT_KATO, "keep_alive_tmo=%d" }, { NVMF_OPT_HOSTNQN, "hostnqn=%s" }, { NVMF_OPT_HOST_TRADDR, "host_traddr=%s" }, + { NVMF_OPT_HOST_IFACE, "host_iface=%s" }, { NVMF_OPT_HOST_ID, "hostid=%s" }, { NVMF_OPT_DUP_CONNECT, "duplicate_connect" }, { NVMF_OPT_DISABLE_SQFLOW, "disable_sqflow" }, @@ -759,6 +749,15 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, kfree(opts->host_traddr); opts->host_traddr = p; break; + case NVMF_OPT_HOST_IFACE: + p = match_strdup(args); + if (!p) { + ret = -ENOMEM; + goto out; + } + kfree(opts->host_iface); + opts->host_iface = p; + break; case NVMF_OPT_HOST_ID: p = match_strdup(args); if (!p) { @@ -943,6 +942,7 @@ void nvmf_free_options(struct nvmf_ctrl_options *opts) kfree(opts->trsvcid); kfree(opts->subsysnqn); kfree(opts->host_traddr); + kfree(opts->host_iface); kfree(opts); } EXPORT_SYMBOL_GPL(nvmf_free_options); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index d7f7974dc208..c31dad69a773 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -66,6 +66,7 @@ enum { NVMF_OPT_NR_POLL_QUEUES = 1 << 18, NVMF_OPT_TOS = 1 << 19, NVMF_OPT_FAIL_FAST_TMO = 1 << 20, + NVMF_OPT_HOST_IFACE = 1 << 21, }; /** @@ -83,7 +84,9 @@ enum { * @trsvcid: The transport-specific TRSVCID field for a port on the * subsystem which is adding a controller. * @host_traddr: A transport-specific field identifying the NVME host port - * to use for the connection to the controller. + * to use for the connection to the controller. + * @host_iface: A transport-specific field identifying the NVME host + * interface to use for the connection to the controller. * @queue_size: Number of IO queue elements. * @nr_io_queues: Number of controller IO queues that will be established. * @reconnect_delay: Time between two consecutive reconnect attempts. @@ -108,6 +111,7 @@ struct nvmf_ctrl_options { char *traddr; char *trsvcid; char *host_traddr; + char *host_iface; size_t queue_size; unsigned int nr_io_queues; unsigned int reconnect_delay; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index f183f9fa03d0..7600863f7752 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3112,7 +3112,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) } /* FC-NVME supports normal SGL Data Block Descriptors */ - if (!(ctrl->ctrl.sgls & ((1 << 0) | (1 << 1)))) { + if (!nvme_ctrl_sgl_supported(&ctrl->ctrl)) { dev_err(ctrl->ctrl.device, "Mandatory sgls are not supported!\n"); ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR; diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 9557ead02de1..d93928d1e5bd 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -177,6 +177,20 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) metadata, meta_len, lower_32_bits(io.slba), NULL, 0); } +static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl, + struct nvme_ns *ns, __u32 nsid) +{ + if (ns && nsid != ns->head->ns_id) { + dev_err(ctrl->device, + "%s: nsid (%u) in cmd does not match nsid (%u)" + "of namespace\n", + current->comm, nsid, ns->head->ns_id); + return false; + } + + return true; +} + static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, struct nvme_passthru_cmd __user *ucmd) { @@ -192,12 +206,8 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return -EFAULT; if (cmd.flags) return -EINVAL; - if (ns && cmd.nsid != ns->head->ns_id) { - dev_err(ctrl->device, - "%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n", - current->comm, cmd.nsid, ns->head->ns_id); + if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid)) return -EINVAL; - } memset(&c, 0, sizeof(c)); c.common.opcode = cmd.opcode; @@ -242,12 +252,8 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return -EFAULT; if (cmd.flags) return -EINVAL; - if (ns && cmd.nsid != ns->head->ns_id) { - dev_err(ctrl->device, - "%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n", - current->comm, cmd.nsid, ns->head->ns_id); + if (!nvme_validate_passthru_nsid(ctrl, ns, cmd.nsid)) return -EINVAL; - } memset(&c, 0, sizeof(c)); c.common.opcode = cmd.opcode; @@ -372,12 +378,13 @@ long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) #ifdef CONFIG_NVME_MULTIPATH static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *argp, struct nvme_ns_head *head, int srcu_idx) + __releases(&head->srcu) { struct nvme_ctrl *ctrl = ns->ctrl; int ret; nvme_get_ctrl(ns->ctrl); - nvme_put_ns_from_disk(head, srcu_idx); + srcu_read_unlock(&head->srcu, srcu_idx); ret = nvme_ctrl_ioctl(ns->ctrl, cmd, argp); nvme_put_ctrl(ctrl); @@ -387,14 +394,15 @@ static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd, int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { - struct nvme_ns_head *head = NULL; + struct nvme_ns_head *head = bdev->bd_disk->private_data; void __user *argp = (void __user *)arg; struct nvme_ns *ns; - int srcu_idx, ret; + int srcu_idx, ret = -EWOULDBLOCK; - ns = nvme_get_ns_from_disk(bdev->bd_disk, &head, &srcu_idx); - if (unlikely(!ns)) - return -EWOULDBLOCK; + srcu_idx = srcu_read_lock(&head->srcu); + ns = nvme_find_path(head); + if (!ns) + goto out_unlock; /* * Handle ioctls that apply to the controller instead of the namespace @@ -402,12 +410,11 @@ int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode, * deadlock when deleting namespaces using the passthrough interface. */ if (is_ctrl_ioctl(cmd)) - ret = nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx); - else { - ret = nvme_ns_ioctl(ns, cmd, argp); - nvme_put_ns_from_disk(head, srcu_idx); - } + return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx); + ret = nvme_ns_ioctl(ns, cmd, argp); +out_unlock: + srcu_read_unlock(&head->srcu, srcu_idx); return ret; } @@ -419,21 +426,19 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd, container_of(cdev, struct nvme_ns_head, cdev); void __user *argp = (void __user *)arg; struct nvme_ns *ns; - int srcu_idx, ret; + int srcu_idx, ret = -EWOULDBLOCK; srcu_idx = srcu_read_lock(&head->srcu); ns = nvme_find_path(head); - if (!ns) { - srcu_read_unlock(&head->srcu, srcu_idx); - return -EWOULDBLOCK; - } + if (!ns) + goto out_unlock; if (is_ctrl_ioctl(cmd)) return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx); ret = nvme_ns_ioctl(ns, cmd, argp); - nvme_put_ns_from_disk(head, srcu_idx); - +out_unlock: + srcu_read_unlock(&head->srcu, srcu_idx); return ret; } #endif /* CONFIG_NVME_MULTIPATH */ diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index f81871c7128a..0ea5298469c3 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -349,6 +349,25 @@ static void nvme_ns_head_release(struct gendisk *disk, fmode_t mode) nvme_put_ns_head(disk->private_data); } +#ifdef CONFIG_BLK_DEV_ZONED +static int nvme_ns_head_report_zones(struct gendisk *disk, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data) +{ + struct nvme_ns_head *head = disk->private_data; + struct nvme_ns *ns; + int srcu_idx, ret = -EWOULDBLOCK; + + srcu_idx = srcu_read_lock(&head->srcu); + ns = nvme_find_path(head); + if (ns) + ret = nvme_ns_report_zones(ns, sector, nr_zones, cb, data); + srcu_read_unlock(&head->srcu, srcu_idx); + return ret; +} +#else +#define nvme_ns_head_report_zones NULL +#endif /* CONFIG_BLK_DEV_ZONED */ + const struct block_device_operations nvme_ns_head_ops = { .owner = THIS_MODULE, .submit_bio = nvme_ns_head_submit_bio, @@ -356,7 +375,7 @@ const struct block_device_operations nvme_ns_head_ops = { .release = nvme_ns_head_release, .ioctl = nvme_ns_head_ioctl, .getgeo = nvme_getgeo, - .report_zones = nvme_report_zones, + .report_zones = nvme_ns_head_report_zones, .pr_ops = &nvme_pr_ops, }; @@ -416,18 +435,12 @@ static void nvme_requeue_work(struct work_struct *work) next = bio->bi_next; bio->bi_next = NULL; - /* - * Reset disk to the mpath node and resubmit to select a new - * path. - */ - bio_set_dev(bio, head->disk->part0); submit_bio_noacct(bio); } } int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) { - struct request_queue *q; bool vwc = false; mutex_init(&head->lock); @@ -443,34 +456,24 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) if (!(ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || !multipath) return 0; - q = blk_alloc_queue(ctrl->numa_node); - if (!q) - goto out; - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - /* set to a default value for 512 until disk is validated */ - blk_queue_logical_block_size(q, 512); - blk_set_stacking_limits(&q->limits); + head->disk = blk_alloc_disk(ctrl->numa_node); + if (!head->disk) + return -ENOMEM; + head->disk->fops = &nvme_ns_head_ops; + head->disk->private_data = head; + sprintf(head->disk->disk_name, "nvme%dn%d", + ctrl->subsys->instance, head->instance); + + blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue); + /* set to a default value of 512 until the disk is validated */ + blk_queue_logical_block_size(head->disk->queue, 512); + blk_set_stacking_limits(&head->disk->queue->limits); /* we need to propagate up the VMC settings */ if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) vwc = true; - blk_queue_write_cache(q, vwc, vwc); - - head->disk = alloc_disk(0); - if (!head->disk) - goto out_cleanup_queue; - head->disk->fops = &nvme_ns_head_ops; - head->disk->private_data = head; - head->disk->queue = q; - head->disk->flags = GENHD_FL_EXT_DEVT; - sprintf(head->disk->disk_name, "nvme%dn%d", - ctrl->subsys->instance, head->instance); + blk_queue_write_cache(head->disk->queue, vwc, vwc); return 0; - -out_cleanup_queue: - blk_cleanup_queue(q); -out: - return -ENOMEM; } static void nvme_mpath_set_live(struct nvme_ns *ns) @@ -769,16 +772,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head) /* make sure all pending bios are cleaned up */ kblockd_schedule_work(&head->requeue_work); flush_work(&head->requeue_work); - blk_cleanup_queue(head->disk->queue); - if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) { - /* - * if device_add_disk wasn't called, prevent - * disk release to put a bogus reference on the - * request queue - */ - head->disk->queue = NULL; - } - put_disk(head->disk); + blk_cleanup_disk(head->disk); } void nvme_mpath_init_ctrl(struct nvme_ctrl *ctrl) @@ -799,6 +793,13 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) !(ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA)) return 0; + if (!ctrl->max_namespaces || + ctrl->max_namespaces > le32_to_cpu(id->nn)) { + dev_err(ctrl->device, + "Invalid MNAN value %u\n", ctrl->max_namespaces); + return -EINVAL; + } + ctrl->anacap = id->anacap; ctrl->anatt = id->anatt; ctrl->nanagrpid = le32_to_cpu(id->nanagrpid); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 0015860ec12b..75420ceacc10 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -674,9 +674,6 @@ int nvme_delete_ctrl(struct nvme_ctrl *ctrl); void nvme_queue_scan(struct nvme_ctrl *ctrl); int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi, void *log, size_t size, u64 offset); -struct nvme_ns *nvme_get_ns_from_disk(struct gendisk *disk, - struct nvme_ns_head **head, int *srcu_idx); -void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx); bool nvme_tryget_ns_head(struct nvme_ns_head *head); void nvme_put_ns_head(struct nvme_ns_head *head); int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device, @@ -697,6 +694,7 @@ extern const struct attribute_group *nvme_ns_id_attr_groups[]; extern const struct pr_ops nvme_pr_ops; extern const struct block_device_operations nvme_ns_head_ops; +struct nvme_ns *nvme_find_path(struct nvme_ns_head *head); #ifdef CONFIG_NVME_MULTIPATH static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) { @@ -718,7 +716,6 @@ void nvme_mpath_uninit(struct nvme_ctrl *ctrl); void nvme_mpath_stop(struct nvme_ctrl *ctrl); bool nvme_mpath_clear_current_path(struct nvme_ns *ns); void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl); -struct nvme_ns *nvme_find_path(struct nvme_ns_head *head); static inline void nvme_mpath_check_last_path(struct nvme_ns *ns) { @@ -810,17 +807,14 @@ static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys) #endif /* CONFIG_NVME_MULTIPATH */ int nvme_revalidate_zones(struct nvme_ns *ns); +int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data); #ifdef CONFIG_BLK_DEV_ZONED int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf); -int nvme_report_zones(struct gendisk *disk, sector_t sector, - unsigned int nr_zones, report_zones_cb cb, void *data); - blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd, enum nvme_zone_mgmt_action action); #else -#define nvme_report_zones NULL - static inline blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd, enum nvme_zone_mgmt_action action) @@ -875,6 +869,11 @@ static inline void nvme_hwmon_exit(struct nvme_ctrl *ctrl) } #endif +static inline bool nvme_ctrl_sgl_supported(struct nvme_ctrl *ctrl) +{ + return ctrl->sgls & ((1 << 0) | (1 << 1)); +} + u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode); void nvme_execute_passthru_rq(struct request *rq); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index a29b170701fc..d3c5086673bc 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -307,13 +307,12 @@ static void nvme_dbbuf_free(struct nvme_queue *nvmeq) static void nvme_dbbuf_set(struct nvme_dev *dev) { - struct nvme_command c; + struct nvme_command c = { }; unsigned int i; if (!dev->dbbuf_dbs) return; - memset(&c, 0, sizeof(c)); c.dbbuf.opcode = nvme_admin_dbbuf; c.dbbuf.prp1 = cpu_to_le64(dev->dbbuf_dbs_dma_addr); c.dbbuf.prp2 = cpu_to_le64(dev->dbbuf_eis_dma_addr); @@ -536,7 +535,7 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req) avg_seg_size = DIV_ROUND_UP(blk_rq_payload_bytes(req), nseg); - if (!(dev->ctrl.sgls & ((1 << 0) | (1 << 1)))) + if (!nvme_ctrl_sgl_supported(&dev->ctrl)) return false; if (!iod->nvmeq->qid) return false; @@ -559,7 +558,6 @@ static void nvme_free_prps(struct nvme_dev *dev, struct request *req) dma_pool_free(dev->prp_page_pool, prp_list, dma_addr); dma_addr = next_dma_addr; } - } static void nvme_free_sgls(struct nvme_dev *dev, struct request *req) @@ -576,7 +574,6 @@ static void nvme_free_sgls(struct nvme_dev *dev, struct request *req) dma_pool_free(dev->prp_page_pool, sg_list, dma_addr); dma_addr = next_dma_addr; } - } static void nvme_unmap_sg(struct nvme_dev *dev, struct request *req) @@ -855,7 +852,7 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, &cmnd->rw, &bv); if (iod->nvmeq->qid && sgl_threshold && - dev->ctrl.sgls & ((1 << 0) | (1 << 1))) + nvme_ctrl_sgl_supported(&dev->ctrl)) return nvme_setup_sgl_simple(dev, req, &cmnd->rw, &bv); } @@ -1032,7 +1029,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) static inline void nvme_update_cq_head(struct nvme_queue *nvmeq) { - u16 tmp = nvmeq->cq_head + 1; + u32 tmp = nvmeq->cq_head + 1; if (tmp == nvmeq->q_depth) { nvmeq->cq_head = 0; @@ -1114,9 +1111,8 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl) { struct nvme_dev *dev = to_nvme_dev(ctrl); struct nvme_queue *nvmeq = &dev->queues[0]; - struct nvme_command c; + struct nvme_command c = { }; - memset(&c, 0, sizeof(c)); c.common.opcode = nvme_admin_async_event; c.common.command_id = NVME_AQ_BLK_MQ_DEPTH; nvme_submit_cmd(nvmeq, &c, true); @@ -1124,9 +1120,8 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl) static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id) { - struct nvme_command c; + struct nvme_command c = { }; - memset(&c, 0, sizeof(c)); c.delete_queue.opcode = opcode; c.delete_queue.qid = cpu_to_le16(id); @@ -1136,7 +1131,7 @@ static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id) static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid, struct nvme_queue *nvmeq, s16 vector) { - struct nvme_command c; + struct nvme_command c = { }; int flags = NVME_QUEUE_PHYS_CONTIG; if (!test_bit(NVMEQ_POLLED, &nvmeq->flags)) @@ -1146,7 +1141,6 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid, * Note: we (ab)use the fact that the prp fields survive if no data * is attached to the request. */ - memset(&c, 0, sizeof(c)); c.create_cq.opcode = nvme_admin_create_cq; c.create_cq.prp1 = cpu_to_le64(nvmeq->cq_dma_addr); c.create_cq.cqid = cpu_to_le16(qid); @@ -1161,7 +1155,7 @@ static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid, struct nvme_queue *nvmeq) { struct nvme_ctrl *ctrl = &dev->ctrl; - struct nvme_command c; + struct nvme_command c = { }; int flags = NVME_QUEUE_PHYS_CONTIG; /* @@ -1176,7 +1170,6 @@ static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid, * Note: we (ab)use the fact that the prp fields survive if no data * is attached to the request. */ - memset(&c, 0, sizeof(c)); c.create_sq.opcode = nvme_admin_create_sq; c.create_sq.prp1 = cpu_to_le64(nvmeq->sq_dma_addr); c.create_sq.sqid = cpu_to_le16(qid); @@ -1257,7 +1250,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) struct nvme_queue *nvmeq = iod->nvmeq; struct nvme_dev *dev = nvmeq->dev; struct request *abort_req; - struct nvme_command cmd; + struct nvme_command cmd = { }; u32 csts = readl(dev->bar + NVME_REG_CSTS); /* If PCI error recovery process is happening, we cannot reset or @@ -1337,7 +1330,6 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) } iod->aborted = 1; - memset(&cmd, 0, sizeof(cmd)); cmd.abort.opcode = nvme_admin_abort_cmd; cmd.abort.cid = req->tag; cmd.abort.sqid = cpu_to_le16(nvmeq->qid); @@ -1888,10 +1880,9 @@ static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits) { u32 host_mem_size = dev->host_mem_size >> NVME_CTRL_PAGE_SHIFT; u64 dma_addr = dev->host_mem_descs_dma; - struct nvme_command c; + struct nvme_command c = { }; int ret; - memset(&c, 0, sizeof(c)); c.features.opcode = nvme_admin_set_features; c.features.fid = cpu_to_le32(NVME_FEAT_HOST_MEM_BUF); c.features.dword11 = cpu_to_le32(bits); @@ -2265,9 +2256,8 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode) { struct request_queue *q = nvmeq->dev->ctrl.admin_q; struct request *req; - struct nvme_command cmd; + struct nvme_command cmd = { }; - memset(&cmd, 0, sizeof(cmd)); cmd.delete_queue.opcode = opcode; cmd.delete_queue.qid = cpu_to_le16(nvmeq->qid); @@ -2828,54 +2818,6 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev) return 0; } -#ifdef CONFIG_ACPI -static bool nvme_acpi_storage_d3(struct pci_dev *dev) -{ - struct acpi_device *adev; - struct pci_dev *root; - acpi_handle handle; - acpi_status status; - u8 val; - - /* - * Look for _DSD property specifying that the storage device on the port - * must use D3 to support deep platform power savings during - * suspend-to-idle. - */ - root = pcie_find_root_port(dev); - if (!root) - return false; - - adev = ACPI_COMPANION(&root->dev); - if (!adev) - return false; - - /* - * The property is defined in the PXSX device for South complex ports - * and in the PEGP device for North complex ports. - */ - status = acpi_get_handle(adev->handle, "PXSX", &handle); - if (ACPI_FAILURE(status)) { - status = acpi_get_handle(adev->handle, "PEGP", &handle); - if (ACPI_FAILURE(status)) - return false; - } - - if (acpi_bus_get_device(handle, &adev)) - return false; - - if (fwnode_property_read_u8(acpi_fwnode_handle(adev), "StorageD3Enable", - &val)) - return false; - return val == 1; -} -#else -static inline bool nvme_acpi_storage_d3(struct pci_dev *dev) -{ - return false; -} -#endif /* CONFIG_ACPI */ - static void nvme_async_probe(void *data, async_cookie_t cookie) { struct nvme_dev *dev = data; @@ -2925,7 +2867,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) quirks |= check_vendor_combination_bug(pdev); - if (!noacpi && nvme_acpi_storage_d3(pdev)) { + if (!noacpi && acpi_storage_d3(&pdev->dev)) { /* * Some systems use a bios work around to ask for D3 on * platforms that support kernel managed suspend. diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 4697a94c0945..a9e70cefd7ed 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1088,7 +1088,7 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl) static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new) { - int ret = -EINVAL; + int ret; bool changed; ret = nvme_rdma_configure_admin_queue(ctrl, new); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 34f4b3402f7c..c7bd37103cf4 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -123,6 +123,7 @@ struct nvme_tcp_ctrl { struct blk_mq_tag_set admin_tag_set; struct sockaddr_storage addr; struct sockaddr_storage src_addr; + struct net_device *ndev; struct nvme_ctrl ctrl; struct work_struct err_work; @@ -1455,6 +1456,20 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, } } + if (nctrl->opts->mask & NVMF_OPT_HOST_IFACE) { + char *iface = nctrl->opts->host_iface; + sockptr_t optval = KERNEL_SOCKPTR(iface); + + ret = sock_setsockopt(queue->sock, SOL_SOCKET, SO_BINDTODEVICE, + optval, strlen(iface)); + if (ret) { + dev_err(nctrl->device, + "failed to bind to interface %s queue %d err %d\n", + iface, qid, ret); + goto err_sock; + } + } + queue->hdr_digest = nctrl->opts->hdr_digest; queue->data_digest = nctrl->opts->data_digest; if (queue->hdr_digest || queue->data_digest) { @@ -1973,11 +1988,13 @@ static int nvme_tcp_setup_ctrl(struct nvme_ctrl *ctrl, bool new) return ret; if (ctrl->icdoff) { + ret = -EOPNOTSUPP; dev_err(ctrl->device, "icdoff is not supported!\n"); goto destroy_admin; } - if (!(ctrl->sgls & ((1 << 0) | (1 << 1)))) { + if (!nvme_ctrl_sgl_supported(ctrl)) { + ret = -EOPNOTSUPP; dev_err(ctrl->device, "Mandatory sgls are not supported!\n"); goto destroy_admin; } @@ -2515,6 +2532,16 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, } } + if (opts->mask & NVMF_OPT_HOST_IFACE) { + ctrl->ndev = dev_get_by_name(&init_net, opts->host_iface); + if (!ctrl->ndev) { + pr_err("invalid interface passed: %s\n", + opts->host_iface); + ret = -ENODEV; + goto out_free_ctrl; + } + } + if (!opts->duplicate_connect && nvme_tcp_existing_controller(opts)) { ret = -EALREADY; goto out_free_ctrl; @@ -2571,7 +2598,7 @@ static struct nvmf_transport_ops nvme_tcp_transport = { NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO | NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST | NVMF_OPT_NR_WRITE_QUEUES | NVMF_OPT_NR_POLL_QUEUES | - NVMF_OPT_TOS, + NVMF_OPT_TOS | NVMF_OPT_HOST_IFACE, .create_ctrl = nvme_tcp_create_ctrl, }; diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index 475dd45c3db4..d95010481fce 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -171,8 +171,8 @@ static int nvme_zone_parse_entry(struct nvme_ns *ns, return cb(&zone, idx, data); } -static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector, - unsigned int nr_zones, report_zones_cb cb, void *data) +int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data) { struct nvme_zone_report *report; struct nvme_command c = { }; @@ -180,6 +180,9 @@ static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector, unsigned int nz, i; size_t buflen; + if (ns->head->ids.csi != NVME_CSI_ZNS) + return -EINVAL; + report = nvme_zns_alloc_report_buffer(ns, nr_zones, &buflen); if (!report) return -ENOMEM; @@ -227,26 +230,6 @@ out_free: return ret; } -int nvme_report_zones(struct gendisk *disk, sector_t sector, - unsigned int nr_zones, report_zones_cb cb, void *data) -{ - struct nvme_ns_head *head = NULL; - struct nvme_ns *ns; - int srcu_idx, ret; - - ns = nvme_get_ns_from_disk(disk, &head, &srcu_idx); - if (unlikely(!ns)) - return -EWOULDBLOCK; - - if (ns->head->ids.csi == NVME_CSI_ZNS) - ret = nvme_ns_report_zones(ns, sector, nr_zones, cb, data); - else - ret = -EINVAL; - nvme_put_ns_from_disk(head, srcu_idx); - - return ret; -} - blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req, struct nvme_command *c, enum nvme_zone_mgmt_action action) { diff --git a/drivers/nvme/target/Makefile b/drivers/nvme/target/Makefile index ebf91fc4c72e..9837e580fa7e 100644 --- a/drivers/nvme/target/Makefile +++ b/drivers/nvme/target/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_NVME_TARGET_TCP) += nvmet-tcp.o nvmet-y += core.o configfs.o admin-cmd.o fabrics-cmd.o \ discovery.o io-cmd-file.o io-cmd-bdev.o nvmet-$(CONFIG_NVME_TARGET_PASSTHRU) += passthru.o +nvmet-$(CONFIG_BLK_DEV_ZONED) += zns.o nvme-loop-y += loop.o nvmet-rdma-y += rdma.o nvmet-fc-y += fc.o diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index dcd49a72f2f3..0cb98f2bbc8c 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -162,15 +162,8 @@ out: nvmet_req_complete(req, status); } -static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req) +static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log) { - u16 status = NVME_SC_INTERNAL; - struct nvme_effects_log *log; - - log = kzalloc(sizeof(*log), GFP_KERNEL); - if (!log) - goto out; - log->acs[nvme_admin_get_log_page] = cpu_to_le32(1 << 0); log->acs[nvme_admin_identify] = cpu_to_le32(1 << 0); log->acs[nvme_admin_abort_cmd] = cpu_to_le32(1 << 0); @@ -184,9 +177,45 @@ static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req) log->iocs[nvme_cmd_flush] = cpu_to_le32(1 << 0); log->iocs[nvme_cmd_dsm] = cpu_to_le32(1 << 0); log->iocs[nvme_cmd_write_zeroes] = cpu_to_le32(1 << 0); +} + +static void nvmet_get_cmd_effects_zns(struct nvme_effects_log *log) +{ + log->iocs[nvme_cmd_zone_append] = cpu_to_le32(1 << 0); + log->iocs[nvme_cmd_zone_mgmt_send] = cpu_to_le32(1 << 0); + log->iocs[nvme_cmd_zone_mgmt_recv] = cpu_to_le32(1 << 0); +} + +static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req) +{ + struct nvme_effects_log *log; + u16 status = NVME_SC_SUCCESS; + + log = kzalloc(sizeof(*log), GFP_KERNEL); + if (!log) { + status = NVME_SC_INTERNAL; + goto out; + } + + switch (req->cmd->get_log_page.csi) { + case NVME_CSI_NVM: + nvmet_get_cmd_effects_nvm(log); + break; + case NVME_CSI_ZNS: + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED)) { + status = NVME_SC_INVALID_IO_CMD_SET; + goto free; + } + nvmet_get_cmd_effects_nvm(log); + nvmet_get_cmd_effects_zns(log); + break; + default: + status = NVME_SC_INVALID_LOG_PAGE; + goto free; + } status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log)); - +free: kfree(log); out: nvmet_req_complete(req, status); @@ -313,22 +342,6 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req) nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR); } -static u16 nvmet_set_model_number(struct nvmet_subsys *subsys) -{ - u16 status = 0; - - mutex_lock(&subsys->lock); - if (!subsys->model_number) { - subsys->model_number = - kstrdup(NVMET_DEFAULT_CTRL_MODEL, GFP_KERNEL); - if (!subsys->model_number) - status = NVME_SC_INTERNAL; - } - mutex_unlock(&subsys->lock); - - return status; -} - static void nvmet_execute_identify_ctrl(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; @@ -337,14 +350,10 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) u32 cmd_capsule_size; u16 status = 0; - /* - * If there is no model number yet, set it now. It will then remain - * stable for the life time of the subsystem. - */ - if (!subsys->model_number) { - status = nvmet_set_model_number(subsys); - if (status) - goto out; + if (!subsys->subsys_discovered) { + mutex_lock(&subsys->lock); + subsys->subsys_discovered = true; + mutex_unlock(&subsys->lock); } id = kzalloc(sizeof(*id), GFP_KERNEL); @@ -357,9 +366,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) id->vid = 0; id->ssvid = 0; - memset(id->sn, ' ', sizeof(id->sn)); - bin2hex(id->sn, &ctrl->subsys->serial, - min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2)); + memcpy(id->sn, ctrl->subsys->serial, NVMET_SN_MAX_SIZE); memcpy_and_pad(id->mn, sizeof(id->mn), subsys->model_number, strlen(subsys->model_number), ' '); memcpy_and_pad(id->fr, sizeof(id->fr), @@ -415,7 +422,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) /* no enforcement soft-limit for maxcmd - pick arbitrary high value */ id->maxcmd = cpu_to_le16(NVMET_MAX_CMD); - id->nn = cpu_to_le32(ctrl->subsys->max_nsid); + id->nn = cpu_to_le32(NVMET_MAX_NAMESPACES); id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES); id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM | NVME_CTRL_ONCS_WRITE_ZEROES); @@ -635,6 +642,12 @@ static void nvmet_execute_identify_desclist(struct nvmet_req *req) goto out; } + status = nvmet_copy_ns_identifier(req, NVME_NIDT_CSI, + NVME_NIDT_CSI_LEN, + &req->ns->csi, &off); + if (status) + goto out; + if (sg_zero_buffer(req->sg, req->sg_cnt, NVME_IDENTIFY_DATA_SIZE - off, off) != NVME_IDENTIFY_DATA_SIZE - off) status = NVME_SC_INTERNAL | NVME_SC_DNR; @@ -643,6 +656,23 @@ out: nvmet_req_complete(req, status); } +static bool nvmet_handle_identify_desclist(struct nvmet_req *req) +{ + switch (req->cmd->identify.csi) { + case NVME_CSI_NVM: + nvmet_execute_identify_desclist(req); + return true; + case NVME_CSI_ZNS: + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) { + nvmet_execute_identify_desclist(req); + return true; + } + return false; + default: + return false; + } +} + static void nvmet_execute_identify(struct nvmet_req *req) { if (!nvmet_check_transfer_len(req, NVME_IDENTIFY_DATA_SIZE)) @@ -650,19 +680,54 @@ static void nvmet_execute_identify(struct nvmet_req *req) switch (req->cmd->identify.cns) { case NVME_ID_CNS_NS: - return nvmet_execute_identify_ns(req); + switch (req->cmd->identify.csi) { + case NVME_CSI_NVM: + return nvmet_execute_identify_ns(req); + default: + break; + } + break; + case NVME_ID_CNS_CS_NS: + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) { + switch (req->cmd->identify.csi) { + case NVME_CSI_ZNS: + return nvmet_execute_identify_cns_cs_ns(req); + default: + break; + } + } + break; case NVME_ID_CNS_CTRL: - return nvmet_execute_identify_ctrl(req); + switch (req->cmd->identify.csi) { + case NVME_CSI_NVM: + return nvmet_execute_identify_ctrl(req); + } + break; + case NVME_ID_CNS_CS_CTRL: + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) { + switch (req->cmd->identify.csi) { + case NVME_CSI_ZNS: + return nvmet_execute_identify_cns_cs_ctrl(req); + default: + break; + } + } + break; case NVME_ID_CNS_NS_ACTIVE_LIST: - return nvmet_execute_identify_nslist(req); + switch (req->cmd->identify.csi) { + case NVME_CSI_NVM: + return nvmet_execute_identify_nslist(req); + default: + break; + } + break; case NVME_ID_CNS_NS_DESC_LIST: - return nvmet_execute_identify_desclist(req); + if (nvmet_handle_identify_desclist(req) == true) + return; + break; } - pr_debug("unhandled identify cns %d on qid %d\n", - req->cmd->identify.cns, req->sq->qid); - req->error_loc = offsetof(struct nvme_identify, cns); - nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR); + nvmet_req_cns_error_complete(req); } /* diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 65a0cf99f557..273555127188 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -1007,13 +1007,26 @@ static ssize_t nvmet_subsys_attr_version_show(struct config_item *item, NVME_MINOR(subsys->ver)); } -static ssize_t nvmet_subsys_attr_version_store(struct config_item *item, - const char *page, size_t count) +static ssize_t +nvmet_subsys_attr_version_store_locked(struct nvmet_subsys *subsys, + const char *page, size_t count) { - struct nvmet_subsys *subsys = to_subsys(item); int major, minor, tertiary = 0; int ret; + if (subsys->subsys_discovered) { + if (NVME_TERTIARY(subsys->ver)) + pr_err("Can't set version number. %llu.%llu.%llu is already assigned\n", + NVME_MAJOR(subsys->ver), + NVME_MINOR(subsys->ver), + NVME_TERTIARY(subsys->ver)); + else + pr_err("Can't set version number. %llu.%llu is already assigned\n", + NVME_MAJOR(subsys->ver), + NVME_MINOR(subsys->ver)); + return -EINVAL; + } + /* passthru subsystems use the underlying controller's version */ if (nvmet_passthru_ctrl(subsys)) return -EINVAL; @@ -1022,35 +1035,84 @@ static ssize_t nvmet_subsys_attr_version_store(struct config_item *item, if (ret != 2 && ret != 3) return -EINVAL; - down_write(&nvmet_config_sem); subsys->ver = NVME_VS(major, minor, tertiary); - up_write(&nvmet_config_sem); return count; } + +static ssize_t nvmet_subsys_attr_version_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_subsys *subsys = to_subsys(item); + ssize_t ret; + + down_write(&nvmet_config_sem); + mutex_lock(&subsys->lock); + ret = nvmet_subsys_attr_version_store_locked(subsys, page, count); + mutex_unlock(&subsys->lock); + up_write(&nvmet_config_sem); + + return ret; +} CONFIGFS_ATTR(nvmet_subsys_, attr_version); +/* See Section 1.5 of NVMe 1.4 */ +static bool nvmet_is_ascii(const char c) +{ + return c >= 0x20 && c <= 0x7e; +} + static ssize_t nvmet_subsys_attr_serial_show(struct config_item *item, char *page) { struct nvmet_subsys *subsys = to_subsys(item); - return snprintf(page, PAGE_SIZE, "%llx\n", subsys->serial); + return snprintf(page, PAGE_SIZE, "%s\n", subsys->serial); +} + +static ssize_t +nvmet_subsys_attr_serial_store_locked(struct nvmet_subsys *subsys, + const char *page, size_t count) +{ + int pos, len = strcspn(page, "\n"); + + if (subsys->subsys_discovered) { + pr_err("Can't set serial number. %s is already assigned\n", + subsys->serial); + return -EINVAL; + } + + if (!len || len > NVMET_SN_MAX_SIZE) { + pr_err("Serial Number can not be empty or exceed %d Bytes\n", + NVMET_SN_MAX_SIZE); + return -EINVAL; + } + + for (pos = 0; pos < len; pos++) { + if (!nvmet_is_ascii(page[pos])) { + pr_err("Serial Number must contain only ASCII strings\n"); + return -EINVAL; + } + } + + memcpy_and_pad(subsys->serial, NVMET_SN_MAX_SIZE, page, len, ' '); + + return count; } static ssize_t nvmet_subsys_attr_serial_store(struct config_item *item, const char *page, size_t count) { - u64 serial; - - if (sscanf(page, "%llx\n", &serial) != 1) - return -EINVAL; + struct nvmet_subsys *subsys = to_subsys(item); + ssize_t ret; down_write(&nvmet_config_sem); - to_subsys(item)->serial = serial; + mutex_lock(&subsys->lock); + ret = nvmet_subsys_attr_serial_store_locked(subsys, page, count); + mutex_unlock(&subsys->lock); up_write(&nvmet_config_sem); - return count; + return ret; } CONFIGFS_ATTR(nvmet_subsys_, attr_serial); @@ -1118,20 +1180,8 @@ static ssize_t nvmet_subsys_attr_model_show(struct config_item *item, char *page) { struct nvmet_subsys *subsys = to_subsys(item); - int ret; - mutex_lock(&subsys->lock); - ret = snprintf(page, PAGE_SIZE, "%s\n", subsys->model_number ? - subsys->model_number : NVMET_DEFAULT_CTRL_MODEL); - mutex_unlock(&subsys->lock); - - return ret; -} - -/* See Section 1.5 of NVMe 1.4 */ -static bool nvmet_is_ascii(const char c) -{ - return c >= 0x20 && c <= 0x7e; + return snprintf(page, PAGE_SIZE, "%s\n", subsys->model_number); } static ssize_t nvmet_subsys_attr_model_store_locked(struct nvmet_subsys *subsys, @@ -1139,7 +1189,7 @@ static ssize_t nvmet_subsys_attr_model_store_locked(struct nvmet_subsys *subsys, { int pos = 0, len; - if (subsys->model_number) { + if (subsys->subsys_discovered) { pr_err("Can't set model number. %s is already assigned\n", subsys->model_number); return -EINVAL; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index b20b8d0a1144..ac7210a3ea1c 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -16,6 +16,7 @@ #include "nvmet.h" struct workqueue_struct *buffered_io_wq; +struct workqueue_struct *zbd_wq; static const struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX]; static DEFINE_IDA(cntlid_ida); @@ -43,43 +44,34 @@ DECLARE_RWSEM(nvmet_ana_sem); inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno) { - u16 status; - switch (errno) { case 0: - status = NVME_SC_SUCCESS; - break; + return NVME_SC_SUCCESS; case -ENOSPC: req->error_loc = offsetof(struct nvme_rw_command, length); - status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR; - break; + return NVME_SC_CAP_EXCEEDED | NVME_SC_DNR; case -EREMOTEIO: req->error_loc = offsetof(struct nvme_rw_command, slba); - status = NVME_SC_LBA_RANGE | NVME_SC_DNR; - break; + return NVME_SC_LBA_RANGE | NVME_SC_DNR; case -EOPNOTSUPP: req->error_loc = offsetof(struct nvme_common_command, opcode); switch (req->cmd->common.opcode) { case nvme_cmd_dsm: case nvme_cmd_write_zeroes: - status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR; - break; + return NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR; default: - status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } break; case -ENODATA: req->error_loc = offsetof(struct nvme_rw_command, nsid); - status = NVME_SC_ACCESS_DENIED; - break; + return NVME_SC_ACCESS_DENIED; case -EIO: fallthrough; default: req->error_loc = offsetof(struct nvme_common_command, opcode); - status = NVME_SC_INTERNAL | NVME_SC_DNR; + return NVME_SC_INTERNAL | NVME_SC_DNR; } - - return status; } u16 nvmet_report_invalid_opcode(struct nvmet_req *req) @@ -122,11 +114,11 @@ u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len) return 0; } -static unsigned int nvmet_max_nsid(struct nvmet_subsys *subsys) +static u32 nvmet_max_nsid(struct nvmet_subsys *subsys) { - unsigned long nsid = 0; struct nvmet_ns *cur; unsigned long idx; + u32 nsid = 0; xa_for_each(&subsys->namespaces, idx, cur) nsid = cur->nsid; @@ -141,14 +133,13 @@ static u32 nvmet_async_event_result(struct nvmet_async_event *aen) static void nvmet_async_events_failall(struct nvmet_ctrl *ctrl) { - u16 status = NVME_SC_INTERNAL | NVME_SC_DNR; struct nvmet_req *req; mutex_lock(&ctrl->lock); while (ctrl->nr_async_event_cmds) { req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds]; mutex_unlock(&ctrl->lock); - nvmet_req_complete(req, status); + nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_SC_DNR); mutex_lock(&ctrl->lock); } mutex_unlock(&ctrl->lock); @@ -412,7 +403,6 @@ void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl) pr_debug("ctrl %d start keep-alive timer for %d secs\n", ctrl->cntlid, ctrl->kato); - INIT_DELAYED_WORK(&ctrl->ka_work, nvmet_keep_alive_timer); schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ); } @@ -693,6 +683,7 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid) uuid_gen(&ns->uuid); ns->buffered_io = false; + ns->csi = NVME_CSI_NVM; return ns; } @@ -895,10 +886,18 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req) return ret; } - if (req->ns->file) - return nvmet_file_parse_io_cmd(req); - - return nvmet_bdev_parse_io_cmd(req); + switch (req->ns->csi) { + case NVME_CSI_NVM: + if (req->ns->file) + return nvmet_file_parse_io_cmd(req); + return nvmet_bdev_parse_io_cmd(req); + case NVME_CSI_ZNS: + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) + return nvmet_bdev_zns_parse_io_cmd(req); + return NVME_SC_INVALID_IO_CMD_SET; + default: + return NVME_SC_INVALID_IO_CMD_SET; + } } bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, @@ -1119,6 +1118,17 @@ static inline u8 nvmet_cc_iocqes(u32 cc) return (cc >> NVME_CC_IOCQES_SHIFT) & 0xf; } +static inline bool nvmet_css_supported(u8 cc_css) +{ + switch (cc_css <<= NVME_CC_CSS_SHIFT) { + case NVME_CC_CSS_NVM: + case NVME_CC_CSS_CSI: + return true; + default: + return false; + } +} + static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl) { lockdep_assert_held(&ctrl->lock); @@ -1138,7 +1148,7 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl) if (nvmet_cc_mps(ctrl->cc) != 0 || nvmet_cc_ams(ctrl->cc) != 0 || - nvmet_cc_css(ctrl->cc) != 0) { + !nvmet_css_supported(nvmet_cc_css(ctrl->cc))) { ctrl->csts = NVME_CSTS_CFS; return; } @@ -1189,6 +1199,8 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl) { /* command sets supported: NVMe command set: */ ctrl->cap = (1ULL << 37); + /* Controller supports one or more I/O Command Sets */ + ctrl->cap |= (1ULL << 43); /* CC.EN timeout in 500msec units: */ ctrl->cap |= (15ULL << 24); /* maximum queue entries supported: */ @@ -1358,6 +1370,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, INIT_LIST_HEAD(&ctrl->async_events); INIT_RADIX_TREE(&ctrl->p2p_ns_map, GFP_KERNEL); INIT_WORK(&ctrl->fatal_err_work, nvmet_fatal_error_handler); + INIT_DELAYED_WORK(&ctrl->ka_work, nvmet_keep_alive_timer); memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE); memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE); @@ -1499,6 +1512,8 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, enum nvme_subsys_type type) { struct nvmet_subsys *subsys; + char serial[NVMET_SN_MAX_SIZE / 2]; + int ret; subsys = kzalloc(sizeof(*subsys), GFP_KERNEL); if (!subsys) @@ -1506,7 +1521,14 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, subsys->ver = NVMET_DEFAULT_VS; /* generate a random serial number as our controllers are ephemeral: */ - get_random_bytes(&subsys->serial, sizeof(subsys->serial)); + get_random_bytes(&serial, sizeof(serial)); + bin2hex(subsys->serial, &serial, sizeof(serial)); + + subsys->model_number = kstrdup(NVMET_DEFAULT_CTRL_MODEL, GFP_KERNEL); + if (!subsys->model_number) { + ret = -ENOMEM; + goto free_subsys; + } switch (type) { case NVME_NQN_NVME: @@ -1517,15 +1539,15 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, break; default: pr_err("%s: Unknown Subsystem type - %d\n", __func__, type); - kfree(subsys); - return ERR_PTR(-EINVAL); + ret = -EINVAL; + goto free_mn; } subsys->type = type; subsys->subsysnqn = kstrndup(subsysnqn, NVMF_NQN_SIZE, GFP_KERNEL); if (!subsys->subsysnqn) { - kfree(subsys); - return ERR_PTR(-ENOMEM); + ret = -ENOMEM; + goto free_mn; } subsys->cntlid_min = NVME_CNTLID_MIN; subsys->cntlid_max = NVME_CNTLID_MAX; @@ -1537,6 +1559,12 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, INIT_LIST_HEAD(&subsys->hosts); return subsys; + +free_mn: + kfree(subsys->model_number); +free_subsys: + kfree(subsys); + return ERR_PTR(ret); } static void nvmet_subsys_free(struct kref *ref) @@ -1575,11 +1603,15 @@ static int __init nvmet_init(void) nvmet_ana_group_enabled[NVMET_DEFAULT_ANA_GRPID] = 1; + zbd_wq = alloc_workqueue("nvmet-zbd-wq", WQ_MEM_RECLAIM, 0); + if (!zbd_wq) + return -ENOMEM; + buffered_io_wq = alloc_workqueue("nvmet-buffered-io-wq", WQ_MEM_RECLAIM, 0); if (!buffered_io_wq) { error = -ENOMEM; - goto out; + goto out_free_zbd_work_queue; } error = nvmet_init_discovery(); @@ -1595,7 +1627,8 @@ out_exit_discovery: nvmet_exit_discovery(); out_free_work_queue: destroy_workqueue(buffered_io_wq); -out: +out_free_zbd_work_queue: + destroy_workqueue(zbd_wq); return error; } @@ -1605,6 +1638,7 @@ static void __exit nvmet_exit(void) nvmet_exit_discovery(); ida_destroy(&cntlid_ida); destroy_workqueue(buffered_io_wq); + destroy_workqueue(zbd_wq); BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_entry) != 1024); BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_hdr) != 1024); diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index fc3645fc2c24..7aa62bc6ae84 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -244,7 +244,6 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvme_id_ctrl *id; - const char model[] = "Linux"; u16 status = 0; if (!nvmet_check_transfer_len(req, NVME_IDENTIFY_DATA_SIZE)) @@ -262,11 +261,10 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req) goto out; } - memset(id->sn, ' ', sizeof(id->sn)); - bin2hex(id->sn, &ctrl->subsys->serial, - min(sizeof(ctrl->subsys->serial), sizeof(id->sn) / 2)); + memcpy(id->sn, ctrl->subsys->serial, NVMET_SN_MAX_SIZE); memset(id->fr, ' ', sizeof(id->fr)); - memcpy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1, ' '); + memcpy_and_pad(id->mn, sizeof(id->mn), ctrl->subsys->model_number, + strlen(ctrl->subsys->model_number), ' '); memcpy_and_pad(id->fr, sizeof(id->fr), UTS_RELEASE, strlen(UTS_RELEASE), ' '); diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 19e113240fff..22b5108168a6 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -2510,13 +2510,6 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, u32 xfrlen = be32_to_cpu(cmdiu->data_len); int ret; - /* - * if there is no nvmet mapping to the targetport there - * shouldn't be requests. just terminate them. - */ - if (!tgtport->pe) - goto transport_error; - /* * Fused commands are currently not supported in the linux * implementation. @@ -2544,7 +2537,8 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, fod->req.cmd = &fod->cmdiubuf.sqe; fod->req.cqe = &fod->rspiubuf.cqe; - fod->req.port = tgtport->pe->port; + if (tgtport->pe) + fod->req.port = tgtport->pe->port; /* clear any response payload */ memset(&fod->rspiubuf, 0, sizeof(fod->rspiubuf)); diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 429263ca9b97..0fc2781ab970 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -47,6 +47,14 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) id->nows = to0based(ql->io_opt / ql->logical_block_size); } +void nvmet_bdev_ns_disable(struct nvmet_ns *ns) +{ + if (ns->bdev) { + blkdev_put(ns->bdev, FMODE_WRITE | FMODE_READ); + ns->bdev = NULL; + } +} + static void nvmet_bdev_ns_enable_integrity(struct nvmet_ns *ns) { struct blk_integrity *bi = bdev_get_integrity(ns->bdev); @@ -86,15 +94,15 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns) if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY_T10)) nvmet_bdev_ns_enable_integrity(ns); - return 0; -} - -void nvmet_bdev_ns_disable(struct nvmet_ns *ns) -{ - if (ns->bdev) { - blkdev_put(ns->bdev, FMODE_WRITE | FMODE_READ); - ns->bdev = NULL; + if (bdev_is_zoned(ns->bdev)) { + if (!nvmet_bdev_zns_enable(ns)) { + nvmet_bdev_ns_disable(ns); + return -EINVAL; + } + ns->csi = NVME_CSI_ZNS; } + + return 0; } void nvmet_bdev_ns_revalidate(struct nvmet_ns *ns) @@ -102,7 +110,7 @@ void nvmet_bdev_ns_revalidate(struct nvmet_ns *ns) ns->size = i_size_read(ns->bdev->bd_inode); } -static u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts) +u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts) { u16 status = NVME_SC_SUCCESS; @@ -164,8 +172,7 @@ static void nvmet_bio_done(struct bio *bio) struct nvmet_req *req = bio->bi_private; nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status)); - if (bio != &req->b.inline_bio) - bio_put(bio); + nvmet_req_bio_put(req, bio); } #ifdef CONFIG_BLK_DEV_INTEGRITY @@ -174,11 +181,10 @@ static int nvmet_bdev_alloc_bip(struct nvmet_req *req, struct bio *bio, { struct blk_integrity *bi; struct bio_integrity_payload *bip; - struct block_device *bdev = req->ns->bdev; int rc; size_t resid, len; - bi = bdev_get_integrity(bdev); + bi = bdev_get_integrity(req->ns->bdev); if (unlikely(!bi)) { pr_err("Unable to locate bio_integrity\n"); return -ENODEV; @@ -430,9 +436,7 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req) u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req) { - struct nvme_command *cmd = req->cmd; - - switch (cmd->common.opcode) { + switch (req->cmd->common.opcode) { case nvme_cmd_read: case nvme_cmd_write: req->execute = nvmet_bdev_execute_rw; diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 7fdbdc496597..1dd1a0fe2e81 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -385,9 +385,7 @@ static void nvmet_file_execute_write_zeroes(struct nvmet_req *req) u16 nvmet_file_parse_io_cmd(struct nvmet_req *req) { - struct nvme_command *cmd = req->cmd; - - switch (cmd->common.opcode) { + switch (req->cmd->common.opcode) { case nvme_cmd_read: case nvme_cmd_write: req->execute = nvmet_file_execute_rw; diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 53aea9a8056e..06dd3d537f07 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -28,6 +28,7 @@ #define NVMET_NO_ERROR_LOC ((u16)-1) #define NVMET_DEFAULT_CTRL_MODEL "Linux" #define NVMET_MN_MAX_SIZE 40 +#define NVMET_SN_MAX_SIZE 20 /* * Supported optional AENs: @@ -82,6 +83,7 @@ struct nvmet_ns { struct pci_dev *p2p_dev; int pi_type; int metadata_size; + u8 csi; }; static inline struct nvmet_ns *to_nvmet_ns(struct config_item *item) @@ -217,7 +219,7 @@ struct nvmet_subsys { struct xarray namespaces; unsigned int nr_namespaces; - unsigned int max_nsid; + u32 max_nsid; u16 cntlid_min; u16 cntlid_max; @@ -229,7 +231,8 @@ struct nvmet_subsys { u16 max_qid; u64 ver; - u64 serial; + char serial[NVMET_SN_MAX_SIZE]; + bool subsys_discovered; char *subsysnqn; bool pi_support; @@ -247,6 +250,10 @@ struct nvmet_subsys { unsigned int admin_timeout; unsigned int io_timeout; #endif /* CONFIG_NVME_TARGET_PASSTHRU */ + +#ifdef CONFIG_BLK_DEV_ZONED + u8 zasl; +#endif /* CONFIG_BLK_DEV_ZONED */ }; static inline struct nvmet_subsys *to_subsys(struct config_item *item) @@ -332,6 +339,12 @@ struct nvmet_req { struct work_struct work; bool use_workqueue; } p; +#ifdef CONFIG_BLK_DEV_ZONED + struct { + struct bio inline_bio; + struct work_struct zmgmt_work; + } z; +#endif /* CONFIG_BLK_DEV_ZONED */ }; int sg_cnt; int metadata_sg_cnt; @@ -351,6 +364,7 @@ struct nvmet_req { }; extern struct workqueue_struct *buffered_io_wq; +extern struct workqueue_struct *zbd_wq; static inline void nvmet_set_result(struct nvmet_req *req, u32 result) { @@ -400,6 +414,7 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req); void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id); u16 nvmet_bdev_parse_io_cmd(struct nvmet_req *req); u16 nvmet_file_parse_io_cmd(struct nvmet_req *req); +u16 nvmet_bdev_zns_parse_io_cmd(struct nvmet_req *req); u16 nvmet_parse_admin_cmd(struct nvmet_req *req); u16 nvmet_parse_discovery_cmd(struct nvmet_req *req); u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req); @@ -527,6 +542,14 @@ void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid); void nvmet_bdev_ns_revalidate(struct nvmet_ns *ns); int nvmet_file_ns_revalidate(struct nvmet_ns *ns); void nvmet_ns_revalidate(struct nvmet_ns *ns); +u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts); + +bool nvmet_bdev_zns_enable(struct nvmet_ns *ns); +void nvmet_execute_identify_cns_cs_ctrl(struct nvmet_req *req); +void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req); +void nvmet_bdev_execute_zone_mgmt_recv(struct nvmet_req *req); +void nvmet_bdev_execute_zone_mgmt_send(struct nvmet_req *req); +void nvmet_bdev_execute_zone_append(struct nvmet_req *req); static inline u32 nvmet_rw_data_len(struct nvmet_req *req) { @@ -622,4 +645,18 @@ static inline bool nvmet_use_inline_bvec(struct nvmet_req *req) req->sg_cnt <= NVMET_MAX_INLINE_BIOVEC; } +static inline void nvmet_req_cns_error_complete(struct nvmet_req *req) +{ + pr_debug("unhandled identify cns %d on qid %d\n", + req->cmd->identify.cns, req->sq->qid); + req->error_loc = offsetof(struct nvme_identify, cns); + nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR); +} + +static inline void nvmet_req_bio_put(struct nvmet_req *req, struct bio *bio) +{ + if (bio != &req->b.inline_bio) + bio_put(bio); +} + #endif /* _NVMET_H */ diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 39b1473f7204..fced52de33ce 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -206,8 +206,7 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq) for_each_sg(req->sg, sg, req->sg_cnt, i) { if (bio_add_pc_page(rq->q, bio, sg_page(sg), sg->length, sg->offset) < sg->length) { - if (bio != &req->p.inline_bio) - bio_put(bio); + nvmet_req_bio_put(req, bio); return -EINVAL; } } diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 7d607f435e36..891174ccd44b 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1257,7 +1257,7 @@ out_err: static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue) { - struct ib_qp_init_attr qp_attr; + struct ib_qp_init_attr qp_attr = { }; struct nvmet_rdma_device *ndev = queue->dev; int nr_cqe, ret, i, factor; @@ -1275,7 +1275,6 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue) goto out; } - memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.qp_context = queue; qp_attr.event_handler = nvmet_rdma_qp_event; qp_attr.send_cq = queue->cq; diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c new file mode 100644 index 000000000000..17f8b7a45f21 --- /dev/null +++ b/drivers/nvme/target/zns.c @@ -0,0 +1,615 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVMe ZNS-ZBD command implementation. + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include +#include +#include "nvmet.h" + +/* + * We set the Memory Page Size Minimum (MPSMIN) for target controller to 0 + * which gets added by 12 in the nvme_enable_ctrl() which results in 2^12 = 4k + * as page_shift value. When calculating the ZASL use shift by 12. + */ +#define NVMET_MPSMIN_SHIFT 12 + +static inline u8 nvmet_zasl(unsigned int zone_append_sects) +{ + /* + * Zone Append Size Limit (zasl) is expressed as a power of 2 value + * with the minimum memory page size (i.e. 12) as unit. + */ + return ilog2(zone_append_sects >> (NVMET_MPSMIN_SHIFT - 9)); +} + +static int validate_conv_zones_cb(struct blk_zone *z, + unsigned int i, void *data) +{ + if (z->type == BLK_ZONE_TYPE_CONVENTIONAL) + return -EOPNOTSUPP; + return 0; +} + +bool nvmet_bdev_zns_enable(struct nvmet_ns *ns) +{ + struct request_queue *q = ns->bdev->bd_disk->queue; + u8 zasl = nvmet_zasl(queue_max_zone_append_sectors(q)); + struct gendisk *bd_disk = ns->bdev->bd_disk; + int ret; + + if (ns->subsys->zasl) { + if (ns->subsys->zasl > zasl) + return false; + } + ns->subsys->zasl = zasl; + + /* + * Generic zoned block devices may have a smaller last zone which is + * not supported by ZNS. Exclude zoned drives that have such smaller + * last zone. + */ + if (get_capacity(bd_disk) & (bdev_zone_sectors(ns->bdev) - 1)) + return false; + /* + * ZNS does not define a conventional zone type. If the underlying + * device has a bitmap set indicating the existence of conventional + * zones, reject the device. Otherwise, use report zones to detect if + * the device has conventional zones. + */ + if (ns->bdev->bd_disk->queue->conv_zones_bitmap) + return false; + + ret = blkdev_report_zones(ns->bdev, 0, blkdev_nr_zones(bd_disk), + validate_conv_zones_cb, NULL); + if (ret < 0) + return false; + + ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev)); + + return true; +} + +void nvmet_execute_identify_cns_cs_ctrl(struct nvmet_req *req) +{ + u8 zasl = req->sq->ctrl->subsys->zasl; + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvme_id_ctrl_zns *id; + u16 status; + + id = kzalloc(sizeof(*id), GFP_KERNEL); + if (!id) { + status = NVME_SC_INTERNAL; + goto out; + } + + if (ctrl->ops->get_mdts) + id->zasl = min_t(u8, ctrl->ops->get_mdts(ctrl), zasl); + else + id->zasl = zasl; + + status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id)); + + kfree(id); +out: + nvmet_req_complete(req, status); +} + +void nvmet_execute_identify_cns_cs_ns(struct nvmet_req *req) +{ + struct nvme_id_ns_zns *id_zns; + u64 zsze; + u16 status; + + if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) { + req->error_loc = offsetof(struct nvme_identify, nsid); + status = NVME_SC_INVALID_NS | NVME_SC_DNR; + goto out; + } + + id_zns = kzalloc(sizeof(*id_zns), GFP_KERNEL); + if (!id_zns) { + status = NVME_SC_INTERNAL; + goto out; + } + + status = nvmet_req_find_ns(req); + if (status) { + status = NVME_SC_INTERNAL; + goto done; + } + + if (!bdev_is_zoned(req->ns->bdev)) { + req->error_loc = offsetof(struct nvme_identify, nsid); + status = NVME_SC_INVALID_NS | NVME_SC_DNR; + goto done; + } + + nvmet_ns_revalidate(req->ns); + zsze = (bdev_zone_sectors(req->ns->bdev) << 9) >> + req->ns->blksize_shift; + id_zns->lbafe[0].zsze = cpu_to_le64(zsze); + id_zns->mor = cpu_to_le32(bdev_max_open_zones(req->ns->bdev)); + id_zns->mar = cpu_to_le32(bdev_max_active_zones(req->ns->bdev)); + +done: + status = nvmet_copy_to_sgl(req, 0, id_zns, sizeof(*id_zns)); + kfree(id_zns); +out: + nvmet_req_complete(req, status); +} + +static u16 nvmet_bdev_validate_zone_mgmt_recv(struct nvmet_req *req) +{ + sector_t sect = nvmet_lba_to_sect(req->ns, req->cmd->zmr.slba); + u32 out_bufsize = (le32_to_cpu(req->cmd->zmr.numd) + 1) << 2; + + if (sect >= get_capacity(req->ns->bdev->bd_disk)) { + req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, slba); + return NVME_SC_LBA_RANGE | NVME_SC_DNR; + } + + if (out_bufsize < sizeof(struct nvme_zone_report)) { + req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, numd); + return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + } + + if (req->cmd->zmr.zra != NVME_ZRA_ZONE_REPORT) { + req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, zra); + return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + } + + switch (req->cmd->zmr.pr) { + case 0: + case 1: + break; + default: + req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, pr); + return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + } + + switch (req->cmd->zmr.zrasf) { + case NVME_ZRASF_ZONE_REPORT_ALL: + case NVME_ZRASF_ZONE_STATE_EMPTY: + case NVME_ZRASF_ZONE_STATE_IMP_OPEN: + case NVME_ZRASF_ZONE_STATE_EXP_OPEN: + case NVME_ZRASF_ZONE_STATE_CLOSED: + case NVME_ZRASF_ZONE_STATE_FULL: + case NVME_ZRASF_ZONE_STATE_READONLY: + case NVME_ZRASF_ZONE_STATE_OFFLINE: + break; + default: + req->error_loc = + offsetof(struct nvme_zone_mgmt_recv_cmd, zrasf); + return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + } + + return NVME_SC_SUCCESS; +} + +struct nvmet_report_zone_data { + struct nvmet_req *req; + u64 out_buf_offset; + u64 out_nr_zones; + u64 nr_zones; + u8 zrasf; +}; + +static int nvmet_bdev_report_zone_cb(struct blk_zone *z, unsigned i, void *d) +{ + static const unsigned int nvme_zrasf_to_blk_zcond[] = { + [NVME_ZRASF_ZONE_STATE_EMPTY] = BLK_ZONE_COND_EMPTY, + [NVME_ZRASF_ZONE_STATE_IMP_OPEN] = BLK_ZONE_COND_IMP_OPEN, + [NVME_ZRASF_ZONE_STATE_EXP_OPEN] = BLK_ZONE_COND_EXP_OPEN, + [NVME_ZRASF_ZONE_STATE_CLOSED] = BLK_ZONE_COND_CLOSED, + [NVME_ZRASF_ZONE_STATE_READONLY] = BLK_ZONE_COND_READONLY, + [NVME_ZRASF_ZONE_STATE_FULL] = BLK_ZONE_COND_FULL, + [NVME_ZRASF_ZONE_STATE_OFFLINE] = BLK_ZONE_COND_OFFLINE, + }; + struct nvmet_report_zone_data *rz = d; + + if (rz->zrasf != NVME_ZRASF_ZONE_REPORT_ALL && + z->cond != nvme_zrasf_to_blk_zcond[rz->zrasf]) + return 0; + + if (rz->nr_zones < rz->out_nr_zones) { + struct nvme_zone_descriptor zdesc = { }; + u16 status; + + zdesc.zcap = nvmet_sect_to_lba(rz->req->ns, z->capacity); + zdesc.zslba = nvmet_sect_to_lba(rz->req->ns, z->start); + zdesc.wp = nvmet_sect_to_lba(rz->req->ns, z->wp); + zdesc.za = z->reset ? 1 << 2 : 0; + zdesc.zs = z->cond << 4; + zdesc.zt = z->type; + + status = nvmet_copy_to_sgl(rz->req, rz->out_buf_offset, &zdesc, + sizeof(zdesc)); + if (status) + return -EINVAL; + + rz->out_buf_offset += sizeof(zdesc); + } + + rz->nr_zones++; + + return 0; +} + +static unsigned long nvmet_req_nr_zones_from_slba(struct nvmet_req *req) +{ + unsigned int sect = nvmet_lba_to_sect(req->ns, req->cmd->zmr.slba); + + return blkdev_nr_zones(req->ns->bdev->bd_disk) - + (sect >> ilog2(bdev_zone_sectors(req->ns->bdev))); +} + +static unsigned long get_nr_zones_from_buf(struct nvmet_req *req, u32 bufsize) +{ + if (bufsize <= sizeof(struct nvme_zone_report)) + return 0; + + return (bufsize - sizeof(struct nvme_zone_report)) / + sizeof(struct nvme_zone_descriptor); +} + +static void nvmet_bdev_zone_zmgmt_recv_work(struct work_struct *w) +{ + struct nvmet_req *req = container_of(w, struct nvmet_req, z.zmgmt_work); + sector_t start_sect = nvmet_lba_to_sect(req->ns, req->cmd->zmr.slba); + unsigned long req_slba_nr_zones = nvmet_req_nr_zones_from_slba(req); + u32 out_bufsize = (le32_to_cpu(req->cmd->zmr.numd) + 1) << 2; + __le64 nr_zones; + u16 status; + int ret; + struct nvmet_report_zone_data rz_data = { + .out_nr_zones = get_nr_zones_from_buf(req, out_bufsize), + /* leave the place for report zone header */ + .out_buf_offset = sizeof(struct nvme_zone_report), + .zrasf = req->cmd->zmr.zrasf, + .nr_zones = 0, + .req = req, + }; + + status = nvmet_bdev_validate_zone_mgmt_recv(req); + if (status) + goto out; + + if (!req_slba_nr_zones) { + status = NVME_SC_SUCCESS; + goto out; + } + + ret = blkdev_report_zones(req->ns->bdev, start_sect, req_slba_nr_zones, + nvmet_bdev_report_zone_cb, &rz_data); + if (ret < 0) { + status = NVME_SC_INTERNAL; + goto out; + } + + /* + * When partial bit is set nr_zones must indicate the number of zone + * descriptors actually transferred. + */ + if (req->cmd->zmr.pr) + rz_data.nr_zones = min(rz_data.nr_zones, rz_data.out_nr_zones); + + nr_zones = cpu_to_le64(rz_data.nr_zones); + status = nvmet_copy_to_sgl(req, 0, &nr_zones, sizeof(nr_zones)); + +out: + nvmet_req_complete(req, status); +} + +void nvmet_bdev_execute_zone_mgmt_recv(struct nvmet_req *req) +{ + INIT_WORK(&req->z.zmgmt_work, nvmet_bdev_zone_zmgmt_recv_work); + queue_work(zbd_wq, &req->z.zmgmt_work); +} + +static inline enum req_opf zsa_req_op(u8 zsa) +{ + switch (zsa) { + case NVME_ZONE_OPEN: + return REQ_OP_ZONE_OPEN; + case NVME_ZONE_CLOSE: + return REQ_OP_ZONE_CLOSE; + case NVME_ZONE_FINISH: + return REQ_OP_ZONE_FINISH; + case NVME_ZONE_RESET: + return REQ_OP_ZONE_RESET; + default: + return REQ_OP_LAST; + } +} + +static u16 blkdev_zone_mgmt_errno_to_nvme_status(int ret) +{ + switch (ret) { + case 0: + return NVME_SC_SUCCESS; + case -EINVAL: + case -EIO: + return NVME_SC_ZONE_INVALID_TRANSITION | NVME_SC_DNR; + default: + return NVME_SC_INTERNAL; + } +} + +struct nvmet_zone_mgmt_send_all_data { + unsigned long *zbitmap; + struct nvmet_req *req; +}; + +static int zmgmt_send_scan_cb(struct blk_zone *z, unsigned i, void *d) +{ + struct nvmet_zone_mgmt_send_all_data *data = d; + + switch (zsa_req_op(data->req->cmd->zms.zsa)) { + case REQ_OP_ZONE_OPEN: + switch (z->cond) { + case BLK_ZONE_COND_CLOSED: + break; + default: + return 0; + } + break; + case REQ_OP_ZONE_CLOSE: + switch (z->cond) { + case BLK_ZONE_COND_IMP_OPEN: + case BLK_ZONE_COND_EXP_OPEN: + break; + default: + return 0; + } + break; + case REQ_OP_ZONE_FINISH: + switch (z->cond) { + case BLK_ZONE_COND_IMP_OPEN: + case BLK_ZONE_COND_EXP_OPEN: + case BLK_ZONE_COND_CLOSED: + break; + default: + return 0; + } + break; + default: + return -EINVAL; + } + + set_bit(i, data->zbitmap); + + return 0; +} + +static u16 nvmet_bdev_zone_mgmt_emulate_all(struct nvmet_req *req) +{ + struct block_device *bdev = req->ns->bdev; + unsigned int nr_zones = blkdev_nr_zones(bdev->bd_disk); + struct request_queue *q = bdev_get_queue(bdev); + struct bio *bio = NULL; + sector_t sector = 0; + int ret; + struct nvmet_zone_mgmt_send_all_data d = { + .req = req, + }; + + d.zbitmap = kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(*(d.zbitmap)), + GFP_NOIO, q->node); + if (!d.zbitmap) { + ret = -ENOMEM; + goto out; + } + + /* Scan and build bitmap of the eligible zones */ + ret = blkdev_report_zones(bdev, 0, nr_zones, zmgmt_send_scan_cb, &d); + if (ret != nr_zones) { + if (ret > 0) + ret = -EIO; + goto out; + } else { + /* We scanned all the zones */ + ret = 0; + } + + while (sector < get_capacity(bdev->bd_disk)) { + if (test_bit(blk_queue_zone_no(q, sector), d.zbitmap)) { + bio = blk_next_bio(bio, 0, GFP_KERNEL); + bio->bi_opf = zsa_req_op(req->cmd->zms.zsa) | REQ_SYNC; + bio->bi_iter.bi_sector = sector; + bio_set_dev(bio, bdev); + /* This may take a while, so be nice to others */ + cond_resched(); + } + sector += blk_queue_zone_sectors(q); + } + + if (bio) { + ret = submit_bio_wait(bio); + bio_put(bio); + } + +out: + kfree(d.zbitmap); + + return blkdev_zone_mgmt_errno_to_nvme_status(ret); +} + +static u16 nvmet_bdev_execute_zmgmt_send_all(struct nvmet_req *req) +{ + int ret; + + switch (zsa_req_op(req->cmd->zms.zsa)) { + case REQ_OP_ZONE_RESET: + ret = blkdev_zone_mgmt(req->ns->bdev, REQ_OP_ZONE_RESET, 0, + get_capacity(req->ns->bdev->bd_disk), + GFP_KERNEL); + if (ret < 0) + return blkdev_zone_mgmt_errno_to_nvme_status(ret); + break; + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: + return nvmet_bdev_zone_mgmt_emulate_all(req); + default: + /* this is needed to quiet compiler warning */ + req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, zsa); + return NVME_SC_INVALID_FIELD | NVME_SC_DNR; + } + + return NVME_SC_SUCCESS; +} + +static void nvmet_bdev_zmgmt_send_work(struct work_struct *w) +{ + struct nvmet_req *req = container_of(w, struct nvmet_req, z.zmgmt_work); + sector_t sect = nvmet_lba_to_sect(req->ns, req->cmd->zms.slba); + enum req_opf op = zsa_req_op(req->cmd->zms.zsa); + struct block_device *bdev = req->ns->bdev; + sector_t zone_sectors = bdev_zone_sectors(bdev); + u16 status = NVME_SC_SUCCESS; + int ret; + + if (op == REQ_OP_LAST) { + req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, zsa); + status = NVME_SC_ZONE_INVALID_TRANSITION | NVME_SC_DNR; + goto out; + } + + /* when select all bit is set slba field is ignored */ + if (req->cmd->zms.select_all) { + status = nvmet_bdev_execute_zmgmt_send_all(req); + goto out; + } + + if (sect >= get_capacity(bdev->bd_disk)) { + req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, slba); + status = NVME_SC_LBA_RANGE | NVME_SC_DNR; + goto out; + } + + if (sect & (zone_sectors - 1)) { + req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, slba); + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + goto out; + } + + ret = blkdev_zone_mgmt(bdev, op, sect, zone_sectors, GFP_KERNEL); + if (ret < 0) + status = blkdev_zone_mgmt_errno_to_nvme_status(ret); + +out: + nvmet_req_complete(req, status); +} + +void nvmet_bdev_execute_zone_mgmt_send(struct nvmet_req *req) +{ + INIT_WORK(&req->z.zmgmt_work, nvmet_bdev_zmgmt_send_work); + queue_work(zbd_wq, &req->z.zmgmt_work); +} + +static void nvmet_bdev_zone_append_bio_done(struct bio *bio) +{ + struct nvmet_req *req = bio->bi_private; + + if (bio->bi_status == BLK_STS_OK) { + req->cqe->result.u64 = + nvmet_sect_to_lba(req->ns, bio->bi_iter.bi_sector); + } + + nvmet_req_complete(req, blk_to_nvme_status(req, bio->bi_status)); + nvmet_req_bio_put(req, bio); +} + +void nvmet_bdev_execute_zone_append(struct nvmet_req *req) +{ + sector_t sect = nvmet_lba_to_sect(req->ns, req->cmd->rw.slba); + u16 status = NVME_SC_SUCCESS; + unsigned int total_len = 0; + struct scatterlist *sg; + struct bio *bio; + int sg_cnt; + + /* Request is completed on len mismatch in nvmet_check_transter_len() */ + if (!nvmet_check_transfer_len(req, nvmet_rw_data_len(req))) + return; + + if (!req->sg_cnt) { + nvmet_req_complete(req, 0); + return; + } + + if (sect >= get_capacity(req->ns->bdev->bd_disk)) { + req->error_loc = offsetof(struct nvme_rw_command, slba); + status = NVME_SC_LBA_RANGE | NVME_SC_DNR; + goto out; + } + + if (sect & (bdev_zone_sectors(req->ns->bdev) - 1)) { + req->error_loc = offsetof(struct nvme_rw_command, slba); + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + goto out; + } + + if (nvmet_use_inline_bvec(req)) { + bio = &req->z.inline_bio; + bio_init(bio, req->inline_bvec, ARRAY_SIZE(req->inline_bvec)); + } else { + bio = bio_alloc(GFP_KERNEL, req->sg_cnt); + } + + bio->bi_opf = REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE; + bio->bi_end_io = nvmet_bdev_zone_append_bio_done; + bio_set_dev(bio, req->ns->bdev); + bio->bi_iter.bi_sector = sect; + bio->bi_private = req; + if (req->cmd->rw.control & cpu_to_le16(NVME_RW_FUA)) + bio->bi_opf |= REQ_FUA; + + for_each_sg(req->sg, sg, req->sg_cnt, sg_cnt) { + struct page *p = sg_page(sg); + unsigned int l = sg->length; + unsigned int o = sg->offset; + unsigned int ret; + + ret = bio_add_zone_append_page(bio, p, l, o); + if (ret != sg->length) { + status = NVME_SC_INTERNAL; + goto out_put_bio; + } + total_len += sg->length; + } + + if (total_len != nvmet_rw_data_len(req)) { + status = NVME_SC_INTERNAL | NVME_SC_DNR; + goto out_put_bio; + } + + submit_bio(bio); + return; + +out_put_bio: + nvmet_req_bio_put(req, bio); +out: + nvmet_req_complete(req, status); +} + +u16 nvmet_bdev_zns_parse_io_cmd(struct nvmet_req *req) +{ + struct nvme_command *cmd = req->cmd; + + switch (cmd->common.opcode) { + case nvme_cmd_zone_append: + req->execute = nvmet_bdev_execute_zone_append; + return 0; + case nvme_cmd_zone_mgmt_recv: + req->execute = nvmet_bdev_execute_zone_mgmt_recv; + return 0; + case nvme_cmd_zone_mgmt_send: + req->execute = nvmet_bdev_execute_zone_mgmt_send; + return 0; + default: + return nvmet_bdev_parse_io_cmd(req); + } +} diff --git a/drivers/opp/core.c b/drivers/opp/core.c index e366218d6736..b335c077f215 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -893,6 +893,16 @@ static int _set_required_opps(struct device *dev, if (!required_opp_tables) return 0; + /* + * We only support genpd's OPPs in the "required-opps" for now, as we + * don't know much about other use cases. Error out if the required OPP + * doesn't belong to a genpd. + */ + if (unlikely(!required_opp_tables[0]->is_genpd)) { + dev_err(dev, "required-opps don't belong to a genpd\n"); + return -ENOENT; + } + /* required-opps not fully initialized yet */ if (lazy_linking_pending(opp_table)) return -EBUSY; diff --git a/drivers/opp/of.c b/drivers/opp/of.c index c582a9ca397b..d298e38aaf7e 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -197,21 +197,8 @@ static void _opp_table_alloc_required_tables(struct opp_table *opp_table, required_opp_tables[i] = _find_table_of_opp_np(required_np); of_node_put(required_np); - if (IS_ERR(required_opp_tables[i])) { + if (IS_ERR(required_opp_tables[i])) lazy = true; - continue; - } - - /* - * We only support genpd's OPPs in the "required-opps" for now, - * as we don't know how much about other cases. Error out if the - * required OPP doesn't belong to a genpd. - */ - if (!required_opp_tables[i]->is_genpd) { - dev_err(dev, "required-opp doesn't belong to genpd: %pOF\n", - required_np); - goto free_required_tables; - } } /* Let's do the linking later on */ @@ -379,13 +366,6 @@ static void lazy_link_required_opp_table(struct opp_table *new_table) struct dev_pm_opp *opp; int i, ret; - /* - * We only support genpd's OPPs in the "required-opps" for now, - * as we don't know much about other cases. - */ - if (!new_table->is_genpd) - return; - mutex_lock(&opp_table_lock); list_for_each_entry_safe(opp_table, temp, &lazy_opp_tables, lazy) { @@ -433,8 +413,7 @@ static void lazy_link_required_opp_table(struct opp_table *new_table) /* All required opp-tables found, remove from lazy list */ if (!lazy) { - list_del(&opp_table->lazy); - INIT_LIST_HEAD(&opp_table->lazy); + list_del_init(&opp_table->lazy); list_for_each_entry(opp, &opp_table->opp_list, node) _required_opps_available(opp, opp_table->required_opp_count); @@ -874,7 +853,7 @@ static struct dev_pm_opp *_opp_add_static_v2(struct opp_table *opp_table, return ERR_PTR(-ENOMEM); ret = _read_opp_key(new_opp, opp_table, np, &rate_not_available); - if (ret < 0 && !opp_table->is_genpd) { + if (ret < 0) { dev_err(dev, "%s: opp key field not found\n", __func__); goto free_opp; } diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 6511648271b2..bebe3eeebc4e 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3476,6 +3476,9 @@ static void __exit exit_hv_pci_drv(void) static int __init init_hv_pci_drv(void) { + if (!hv_is_hyperv_initialized()) + return -ENODEV; + /* Set the invalid domain number's bit, so it will not be used */ set_bit(HVPCI_DOM_INVALID, hvpci_dom_map); diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c index f00107017318..9d1e7e03628e 100644 --- a/drivers/platform/chrome/cros_ec_ishtp.c +++ b/drivers/platform/chrome/cros_ec_ishtp.c @@ -703,7 +703,7 @@ end_ishtp_cl_alloc_error: * * Return: 0 */ -static int cros_ec_ishtp_remove(struct ishtp_cl_device *cl_device) +static void cros_ec_ishtp_remove(struct ishtp_cl_device *cl_device) { struct ishtp_cl *cros_ish_cl = ishtp_get_drvdata(cl_device); struct ishtp_cl_data *client_data = ishtp_get_client_data(cros_ish_cl); @@ -712,8 +712,6 @@ static int cros_ec_ishtp_remove(struct ishtp_cl_device *cl_device) cancel_work_sync(&client_data->work_ec_evt); cros_ish_deinit(cros_ish_cl); ishtp_put_device(cl_device); - - return 0; } /** diff --git a/drivers/platform/surface/aggregator/Kconfig b/drivers/platform/surface/aggregator/Kconfig index 3aaeea9f0433..fd6dc452f3e8 100644 --- a/drivers/platform/surface/aggregator/Kconfig +++ b/drivers/platform/surface/aggregator/Kconfig @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0+ -# Copyright (C) 2019-2020 Maximilian Luz +# Copyright (C) 2019-2021 Maximilian Luz menuconfig SURFACE_AGGREGATOR tristate "Microsoft Surface System Aggregator Module Subsystem and Drivers" diff --git a/drivers/platform/surface/aggregator/Makefile b/drivers/platform/surface/aggregator/Makefile index c112e2c7112b..c8498c41e758 100644 --- a/drivers/platform/surface/aggregator/Makefile +++ b/drivers/platform/surface/aggregator/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0+ -# Copyright (C) 2019-2020 Maximilian Luz +# Copyright (C) 2019-2021 Maximilian Luz # For include/trace/define_trace.h to include trace.h CFLAGS_core.o = -I$(src) diff --git a/drivers/platform/surface/aggregator/bus.c b/drivers/platform/surface/aggregator/bus.c index a9b660af0917..0169677c243e 100644 --- a/drivers/platform/surface/aggregator/bus.c +++ b/drivers/platform/surface/aggregator/bus.c @@ -2,7 +2,7 @@ /* * Surface System Aggregator Module bus and device integration. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #include diff --git a/drivers/platform/surface/aggregator/bus.h b/drivers/platform/surface/aggregator/bus.h index 7712baaed6a5..ed032c2cbdb2 100644 --- a/drivers/platform/surface/aggregator/bus.h +++ b/drivers/platform/surface/aggregator/bus.h @@ -2,7 +2,7 @@ /* * Surface System Aggregator Module bus and device integration. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #ifndef _SURFACE_AGGREGATOR_BUS_H diff --git a/drivers/platform/surface/aggregator/controller.c b/drivers/platform/surface/aggregator/controller.c index a06964aa96e7..b8c377b3f932 100644 --- a/drivers/platform/surface/aggregator/controller.c +++ b/drivers/platform/surface/aggregator/controller.c @@ -2,7 +2,7 @@ /* * Main SSAM/SSH controller structure and functionality. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #include @@ -407,6 +407,31 @@ ssam_nf_refcount_dec(struct ssam_nf *nf, struct ssam_event_registry reg, return NULL; } +/** + * ssam_nf_refcount_dec_free() - Decrement reference-/activation-count of the + * given event and free its entry if the reference count reaches zero. + * @nf: The notifier system reference. + * @reg: The registry used to enable/disable the event. + * @id: The event ID. + * + * Decrements the reference-/activation-count of the specified event, freeing + * its entry if it reaches zero. + * + * Note: ``nf->lock`` must be held when calling this function. + */ +static void ssam_nf_refcount_dec_free(struct ssam_nf *nf, + struct ssam_event_registry reg, + struct ssam_event_id id) +{ + struct ssam_nf_refcount_entry *entry; + + lockdep_assert_held(&nf->lock); + + entry = ssam_nf_refcount_dec(nf, reg, id); + if (entry && entry->refcount == 0) + kfree(entry); +} + /** * ssam_nf_refcount_empty() - Test if the notification system has any * enabled/active events. @@ -2122,14 +2147,123 @@ int ssam_ctrl_notif_d0_entry(struct ssam_controller *ctrl) /* -- Top-level event registry interface. ----------------------------------- */ +/** + * ssam_nf_refcount_enable() - Enable event for reference count entry if it has + * not already been enabled. + * @ctrl: The controller to enable the event on. + * @entry: The reference count entry for the event to be enabled. + * @flags: The flags used for enabling the event on the EC. + * + * Enable the event associated with the given reference count entry if the + * reference count equals one, i.e. the event has not previously been enabled. + * If the event has already been enabled (i.e. reference count not equal to + * one), check that the flags used for enabling match and warn about this if + * they do not. + * + * This does not modify the reference count itself, which is done with + * ssam_nf_refcount_inc() / ssam_nf_refcount_dec(). + * + * Note: ``nf->lock`` must be held when calling this function. + * + * Return: Returns zero on success. If the event is enabled by this call, + * returns the status of the event-enable EC command. + */ +static int ssam_nf_refcount_enable(struct ssam_controller *ctrl, + struct ssam_nf_refcount_entry *entry, u8 flags) +{ + const struct ssam_event_registry reg = entry->key.reg; + const struct ssam_event_id id = entry->key.id; + struct ssam_nf *nf = &ctrl->cplt.event.notif; + int status; + + lockdep_assert_held(&nf->lock); + + ssam_dbg(ctrl, "enabling event (reg: %#04x, tc: %#04x, iid: %#04x, rc: %d)\n", + reg.target_category, id.target_category, id.instance, entry->refcount); + + if (entry->refcount == 1) { + status = ssam_ssh_event_enable(ctrl, reg, id, flags); + if (status) + return status; + + entry->flags = flags; + + } else if (entry->flags != flags) { + ssam_warn(ctrl, + "inconsistent flags when enabling event: got %#04x, expected %#04x (reg: %#04x, tc: %#04x, iid: %#04x)\n", + flags, entry->flags, reg.target_category, id.target_category, + id.instance); + } + + return 0; +} + +/** + * ssam_nf_refcount_disable_free() - Disable event for reference count entry if it is + * no longer in use and free the corresponding entry. + * @ctrl: The controller to disable the event on. + * @entry: The reference count entry for the event to be disabled. + * @flags: The flags used for enabling the event on the EC. + * + * If the reference count equals zero, i.e. the event is no longer requested by + * any client, the event will be disabled and the corresponding reference count + * entry freed. The reference count entry must not be used any more after a + * call to this function. + * + * Also checks if the flags used for disabling the event match the flags used + * for enabling the event and warns if they do not (regardless of reference + * count). + * + * This does not modify the reference count itself, which is done with + * ssam_nf_refcount_inc() / ssam_nf_refcount_dec(). + * + * Note: ``nf->lock`` must be held when calling this function. + * + * Return: Returns zero on success. If the event is disabled by this call, + * returns the status of the event-enable EC command. + */ +static int ssam_nf_refcount_disable_free(struct ssam_controller *ctrl, + struct ssam_nf_refcount_entry *entry, u8 flags) +{ + const struct ssam_event_registry reg = entry->key.reg; + const struct ssam_event_id id = entry->key.id; + struct ssam_nf *nf = &ctrl->cplt.event.notif; + int status = 0; + + lockdep_assert_held(&nf->lock); + + ssam_dbg(ctrl, "disabling event (reg: %#04x, tc: %#04x, iid: %#04x, rc: %d)\n", + reg.target_category, id.target_category, id.instance, entry->refcount); + + if (entry->flags != flags) { + ssam_warn(ctrl, + "inconsistent flags when disabling event: got %#04x, expected %#04x (reg: %#04x, tc: %#04x, iid: %#04x)\n", + flags, entry->flags, reg.target_category, id.target_category, + id.instance); + } + + if (entry->refcount == 0) { + status = ssam_ssh_event_disable(ctrl, reg, id, flags); + kfree(entry); + } + + return status; +} + /** * ssam_notifier_register() - Register an event notifier. * @ctrl: The controller to register the notifier on. * @n: The event notifier to register. * - * Register an event notifier and increment the usage counter of the - * associated SAM event. If the event was previously not enabled, it will be - * enabled during this call. + * Register an event notifier. Increment the usage counter of the associated + * SAM event if the notifier is not marked as an observer. If the event is not + * marked as an observer and is currently not enabled, it will be enabled + * during this call. If the notifier is marked as an observer, no attempt will + * be made at enabling any event and no reference count will be modified. + * + * Notifiers marked as observers do not need to be associated with one specific + * event, i.e. as long as no event matching is performed, only the event target + * category needs to be set. * * Return: Returns zero on success, %-ENOSPC if there have already been * %INT_MAX notifiers for the event ID/type associated with the notifier block @@ -2138,11 +2272,10 @@ int ssam_ctrl_notif_d0_entry(struct ssam_controller *ctrl) * for the specific associated event, returns the status of the event-enable * EC-command. */ -int ssam_notifier_register(struct ssam_controller *ctrl, - struct ssam_event_notifier *n) +int ssam_notifier_register(struct ssam_controller *ctrl, struct ssam_event_notifier *n) { u16 rqid = ssh_tc_to_rqid(n->event.id.target_category); - struct ssam_nf_refcount_entry *entry; + struct ssam_nf_refcount_entry *entry = NULL; struct ssam_nf_head *nf_head; struct ssam_nf *nf; int status; @@ -2155,44 +2288,32 @@ int ssam_notifier_register(struct ssam_controller *ctrl, mutex_lock(&nf->lock); - entry = ssam_nf_refcount_inc(nf, n->event.reg, n->event.id); - if (IS_ERR(entry)) { - mutex_unlock(&nf->lock); - return PTR_ERR(entry); + if (!(n->flags & SSAM_EVENT_NOTIFIER_OBSERVER)) { + entry = ssam_nf_refcount_inc(nf, n->event.reg, n->event.id); + if (IS_ERR(entry)) { + mutex_unlock(&nf->lock); + return PTR_ERR(entry); + } } - ssam_dbg(ctrl, "enabling event (reg: %#04x, tc: %#04x, iid: %#04x, rc: %d)\n", - n->event.reg.target_category, n->event.id.target_category, - n->event.id.instance, entry->refcount); - status = ssam_nfblk_insert(nf_head, &n->base); if (status) { - entry = ssam_nf_refcount_dec(nf, n->event.reg, n->event.id); - if (entry->refcount == 0) - kfree(entry); + if (entry) + ssam_nf_refcount_dec_free(nf, n->event.reg, n->event.id); mutex_unlock(&nf->lock); return status; } - if (entry->refcount == 1) { - status = ssam_ssh_event_enable(ctrl, n->event.reg, n->event.id, - n->event.flags); + if (entry) { + status = ssam_nf_refcount_enable(ctrl, entry, n->event.flags); if (status) { ssam_nfblk_remove(&n->base); - kfree(ssam_nf_refcount_dec(nf, n->event.reg, n->event.id)); + ssam_nf_refcount_dec_free(nf, n->event.reg, n->event.id); mutex_unlock(&nf->lock); synchronize_srcu(&nf_head->srcu); return status; } - - entry->flags = n->event.flags; - - } else if (entry->flags != n->event.flags) { - ssam_warn(ctrl, - "inconsistent flags when enabling event: got %#04x, expected %#04x (reg: %#04x, tc: %#04x, iid: %#04x)\n", - n->event.flags, entry->flags, n->event.reg.target_category, - n->event.id.target_category, n->event.id.instance); } mutex_unlock(&nf->lock); @@ -2205,17 +2326,16 @@ EXPORT_SYMBOL_GPL(ssam_notifier_register); * @ctrl: The controller the notifier has been registered on. * @n: The event notifier to unregister. * - * Unregister an event notifier and decrement the usage counter of the - * associated SAM event. If the usage counter reaches zero, the event will be - * disabled. + * Unregister an event notifier. Decrement the usage counter of the associated + * SAM event if the notifier is not marked as an observer. If the usage counter + * reaches zero, the event will be disabled. * * Return: Returns zero on success, %-ENOENT if the given notifier block has * not been registered on the controller. If the given notifier block was the * last one associated with its specific event, returns the status of the * event-disable EC-command. */ -int ssam_notifier_unregister(struct ssam_controller *ctrl, - struct ssam_event_notifier *n) +int ssam_notifier_unregister(struct ssam_controller *ctrl, struct ssam_event_notifier *n) { u16 rqid = ssh_tc_to_rqid(n->event.id.target_category); struct ssam_nf_refcount_entry *entry; @@ -2236,33 +2356,24 @@ int ssam_notifier_unregister(struct ssam_controller *ctrl, return -ENOENT; } - entry = ssam_nf_refcount_dec(nf, n->event.reg, n->event.id); - if (WARN_ON(!entry)) { - /* - * If this does not return an entry, there's a logic error - * somewhere: The notifier block is registered, but the event - * refcount entry is not there. Remove the notifier block - * anyways. - */ - status = -ENOENT; - goto remove; - } + /* + * If this is an observer notifier, do not attempt to disable the + * event, just remove it. + */ + if (!(n->flags & SSAM_EVENT_NOTIFIER_OBSERVER)) { + entry = ssam_nf_refcount_dec(nf, n->event.reg, n->event.id); + if (WARN_ON(!entry)) { + /* + * If this does not return an entry, there's a logic + * error somewhere: The notifier block is registered, + * but the event refcount entry is not there. Remove + * the notifier block anyways. + */ + status = -ENOENT; + goto remove; + } - ssam_dbg(ctrl, "disabling event (reg: %#04x, tc: %#04x, iid: %#04x, rc: %d)\n", - n->event.reg.target_category, n->event.id.target_category, - n->event.id.instance, entry->refcount); - - if (entry->flags != n->event.flags) { - ssam_warn(ctrl, - "inconsistent flags when disabling event: got %#04x, expected %#04x (reg: %#04x, tc: %#04x, iid: %#04x)\n", - n->event.flags, entry->flags, n->event.reg.target_category, - n->event.id.target_category, n->event.id.instance); - } - - if (entry->refcount == 0) { - status = ssam_ssh_event_disable(ctrl, n->event.reg, n->event.id, - n->event.flags); - kfree(entry); + status = ssam_nf_refcount_disable_free(ctrl, entry, n->event.flags); } remove: @@ -2274,6 +2385,105 @@ remove: } EXPORT_SYMBOL_GPL(ssam_notifier_unregister); +/** + * ssam_controller_event_enable() - Enable the specified event. + * @ctrl: The controller to enable the event for. + * @reg: The event registry to use for enabling the event. + * @id: The event ID specifying the event to be enabled. + * @flags: The SAM event flags used for enabling the event. + * + * Increment the event reference count of the specified event. If the event has + * not been enabled previously, it will be enabled by this call. + * + * Note: In general, ssam_notifier_register() with a non-observer notifier + * should be preferred for enabling/disabling events, as this will guarantee + * proper ordering and event forwarding in case of errors during event + * enabling/disabling. + * + * Return: Returns zero on success, %-ENOSPC if the reference count for the + * specified event has reached its maximum, %-ENOMEM if the corresponding event + * entry could not be allocated. If this is the first time that this event has + * been enabled (i.e. the reference count was incremented from zero to one by + * this call), returns the status of the event-enable EC-command. + */ +int ssam_controller_event_enable(struct ssam_controller *ctrl, + struct ssam_event_registry reg, + struct ssam_event_id id, u8 flags) +{ + u16 rqid = ssh_tc_to_rqid(id.target_category); + struct ssam_nf *nf = &ctrl->cplt.event.notif; + struct ssam_nf_refcount_entry *entry; + int status; + + if (!ssh_rqid_is_event(rqid)) + return -EINVAL; + + mutex_lock(&nf->lock); + + entry = ssam_nf_refcount_inc(nf, reg, id); + if (IS_ERR(entry)) { + mutex_unlock(&nf->lock); + return PTR_ERR(entry); + } + + status = ssam_nf_refcount_enable(ctrl, entry, flags); + if (status) { + ssam_nf_refcount_dec_free(nf, reg, id); + mutex_unlock(&nf->lock); + return status; + } + + mutex_unlock(&nf->lock); + return 0; +} +EXPORT_SYMBOL_GPL(ssam_controller_event_enable); + +/** + * ssam_controller_event_disable() - Disable the specified event. + * @ctrl: The controller to disable the event for. + * @reg: The event registry to use for disabling the event. + * @id: The event ID specifying the event to be disabled. + * @flags: The flags used when enabling the event. + * + * Decrement the reference count of the specified event. If the reference count + * reaches zero, the event will be disabled. + * + * Note: In general, ssam_notifier_register()/ssam_notifier_unregister() with a + * non-observer notifier should be preferred for enabling/disabling events, as + * this will guarantee proper ordering and event forwarding in case of errors + * during event enabling/disabling. + * + * Return: Returns zero on success, %-ENOENT if the given event has not been + * enabled on the controller. If the reference count of the event reaches zero + * during this call, returns the status of the event-disable EC-command. + */ +int ssam_controller_event_disable(struct ssam_controller *ctrl, + struct ssam_event_registry reg, + struct ssam_event_id id, u8 flags) +{ + u16 rqid = ssh_tc_to_rqid(id.target_category); + struct ssam_nf *nf = &ctrl->cplt.event.notif; + struct ssam_nf_refcount_entry *entry; + int status; + + if (!ssh_rqid_is_event(rqid)) + return -EINVAL; + + mutex_lock(&nf->lock); + + entry = ssam_nf_refcount_dec(nf, reg, id); + if (!entry) { + mutex_unlock(&nf->lock); + return -ENOENT; + } + + status = ssam_nf_refcount_disable_free(ctrl, entry, flags); + + mutex_unlock(&nf->lock); + return status; +} +EXPORT_SYMBOL_GPL(ssam_controller_event_disable); + /** * ssam_notifier_disable_registered() - Disable events for all registered * notifiers. diff --git a/drivers/platform/surface/aggregator/controller.h b/drivers/platform/surface/aggregator/controller.h index 8297d34e7489..a0963c3562ff 100644 --- a/drivers/platform/surface/aggregator/controller.h +++ b/drivers/platform/surface/aggregator/controller.h @@ -2,7 +2,7 @@ /* * Main SSAM/SSH controller structure and functionality. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #ifndef _SURFACE_AGGREGATOR_CONTROLLER_H diff --git a/drivers/platform/surface/aggregator/core.c b/drivers/platform/surface/aggregator/core.c index 8dc2c267bcd6..279d9df19c01 100644 --- a/drivers/platform/surface/aggregator/core.c +++ b/drivers/platform/surface/aggregator/core.c @@ -7,7 +7,7 @@ * Handles communication via requests as well as enabling, disabling, and * relaying of events. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #include @@ -621,8 +621,8 @@ static const struct acpi_gpio_mapping ssam_acpi_gpios[] = { static int ssam_serial_hub_probe(struct serdev_device *serdev) { + struct acpi_device *ssh = ACPI_COMPANION(&serdev->dev); struct ssam_controller *ctrl; - acpi_handle *ssh = ACPI_HANDLE(&serdev->dev); acpi_status astatus; int status; @@ -652,7 +652,7 @@ static int ssam_serial_hub_probe(struct serdev_device *serdev) if (status) goto err_devopen; - astatus = ssam_serdev_setup_via_acpi(ssh, serdev); + astatus = ssam_serdev_setup_via_acpi(ssh->handle, serdev); if (ACPI_FAILURE(astatus)) { status = -ENXIO; goto err_devinit; @@ -706,7 +706,7 @@ static int ssam_serial_hub_probe(struct serdev_device *serdev) * For now let's thus default power/wakeup to false. */ device_set_wakeup_capable(&serdev->dev, true); - acpi_walk_dep_device_list(ssh); + acpi_dev_clear_dependencies(ssh); return 0; diff --git a/drivers/platform/surface/aggregator/ssh_msgb.h b/drivers/platform/surface/aggregator/ssh_msgb.h index 1221f642dda1..e562958ffdf0 100644 --- a/drivers/platform/surface/aggregator/ssh_msgb.h +++ b/drivers/platform/surface/aggregator/ssh_msgb.h @@ -2,7 +2,7 @@ /* * SSH message builder functions. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #ifndef _SURFACE_AGGREGATOR_SSH_MSGB_H diff --git a/drivers/platform/surface/aggregator/ssh_packet_layer.c b/drivers/platform/surface/aggregator/ssh_packet_layer.c index 15d96eac6811..8a4451c1ffe5 100644 --- a/drivers/platform/surface/aggregator/ssh_packet_layer.c +++ b/drivers/platform/surface/aggregator/ssh_packet_layer.c @@ -2,7 +2,7 @@ /* * SSH packet transport layer. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #include @@ -1567,9 +1567,7 @@ static void ssh_ptl_timeout_reap(struct work_struct *work) clear_bit(SSH_PACKET_SF_PENDING_BIT, &p->state); atomic_dec(&ptl->pending.count); - list_del(&p->pending_node); - - list_add_tail(&p->pending_node, &claimed); + list_move_tail(&p->pending_node, &claimed); } spin_unlock(&ptl->pending.lock); @@ -1957,8 +1955,7 @@ void ssh_ptl_shutdown(struct ssh_ptl *ptl) smp_mb__before_atomic(); clear_bit(SSH_PACKET_SF_QUEUED_BIT, &p->state); - list_del(&p->queue_node); - list_add_tail(&p->queue_node, &complete_q); + list_move_tail(&p->queue_node, &complete_q); } spin_unlock(&ptl->queue.lock); @@ -1970,8 +1967,7 @@ void ssh_ptl_shutdown(struct ssh_ptl *ptl) smp_mb__before_atomic(); clear_bit(SSH_PACKET_SF_PENDING_BIT, &p->state); - list_del(&p->pending_node); - list_add_tail(&p->pending_node, &complete_q); + list_move_tail(&p->pending_node, &complete_q); } atomic_set(&ptl->pending.count, 0); spin_unlock(&ptl->pending.lock); diff --git a/drivers/platform/surface/aggregator/ssh_packet_layer.h b/drivers/platform/surface/aggregator/ssh_packet_layer.h index e8757d03f279..2eb329f0b91a 100644 --- a/drivers/platform/surface/aggregator/ssh_packet_layer.h +++ b/drivers/platform/surface/aggregator/ssh_packet_layer.h @@ -2,7 +2,7 @@ /* * SSH packet transport layer. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #ifndef _SURFACE_AGGREGATOR_SSH_PACKET_LAYER_H diff --git a/drivers/platform/surface/aggregator/ssh_parser.c b/drivers/platform/surface/aggregator/ssh_parser.c index e2dead8de94a..b77912f8f13b 100644 --- a/drivers/platform/surface/aggregator/ssh_parser.c +++ b/drivers/platform/surface/aggregator/ssh_parser.c @@ -2,7 +2,7 @@ /* * SSH message parser. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #include diff --git a/drivers/platform/surface/aggregator/ssh_parser.h b/drivers/platform/surface/aggregator/ssh_parser.h index 63c38d350988..3bd6e180fd16 100644 --- a/drivers/platform/surface/aggregator/ssh_parser.h +++ b/drivers/platform/surface/aggregator/ssh_parser.h @@ -2,7 +2,7 @@ /* * SSH message parser. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #ifndef _SURFACE_AGGREGATOR_SSH_PARSER_H diff --git a/drivers/platform/surface/aggregator/ssh_request_layer.c b/drivers/platform/surface/aggregator/ssh_request_layer.c index 52a83a8fcf82..790f7f0eee98 100644 --- a/drivers/platform/surface/aggregator/ssh_request_layer.c +++ b/drivers/platform/surface/aggregator/ssh_request_layer.c @@ -2,7 +2,7 @@ /* * SSH request transport layer. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #include @@ -863,9 +863,7 @@ static void ssh_rtl_timeout_reap(struct work_struct *work) clear_bit(SSH_REQUEST_SF_PENDING_BIT, &r->state); atomic_dec(&rtl->pending.count); - list_del(&r->node); - - list_add_tail(&r->node, &claimed); + list_move_tail(&r->node, &claimed); } spin_unlock(&rtl->pending.lock); @@ -1204,8 +1202,7 @@ void ssh_rtl_shutdown(struct ssh_rtl *rtl) smp_mb__before_atomic(); clear_bit(SSH_REQUEST_SF_QUEUED_BIT, &r->state); - list_del(&r->node); - list_add_tail(&r->node, &claimed); + list_move_tail(&r->node, &claimed); } spin_unlock(&rtl->queue.lock); @@ -1238,8 +1235,7 @@ void ssh_rtl_shutdown(struct ssh_rtl *rtl) smp_mb__before_atomic(); clear_bit(SSH_REQUEST_SF_PENDING_BIT, &r->state); - list_del(&r->node); - list_add_tail(&r->node, &claimed); + list_move_tail(&r->node, &claimed); } spin_unlock(&rtl->pending.lock); } diff --git a/drivers/platform/surface/aggregator/ssh_request_layer.h b/drivers/platform/surface/aggregator/ssh_request_layer.h index cb35815858d1..9c3cbae2d4bd 100644 --- a/drivers/platform/surface/aggregator/ssh_request_layer.h +++ b/drivers/platform/surface/aggregator/ssh_request_layer.h @@ -2,7 +2,7 @@ /* * SSH request transport layer. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #ifndef _SURFACE_AGGREGATOR_SSH_REQUEST_LAYER_H diff --git a/drivers/platform/surface/aggregator/trace.h b/drivers/platform/surface/aggregator/trace.h index eb332bb53ae4..de64cf169060 100644 --- a/drivers/platform/surface/aggregator/trace.h +++ b/drivers/platform/surface/aggregator/trace.h @@ -2,7 +2,7 @@ /* * Trace points for SSAM/SSH. * - * Copyright (C) 2020 Maximilian Luz + * Copyright (C) 2020-2021 Maximilian Luz */ #undef TRACE_SYSTEM diff --git a/drivers/platform/surface/surface3_power.c b/drivers/platform/surface/surface3_power.c index cc4f9cba6856..dea82aa1abd4 100644 --- a/drivers/platform/surface/surface3_power.c +++ b/drivers/platform/surface/surface3_power.c @@ -446,12 +446,12 @@ mshw0011_space_handler(u32 function, acpi_physical_address command, static int mshw0011_install_space_handler(struct i2c_client *client) { - acpi_handle handle; + struct acpi_device *adev; struct mshw0011_handler_data *data; acpi_status status; - handle = ACPI_HANDLE(&client->dev); - if (!handle) + adev = ACPI_COMPANION(&client->dev); + if (!adev) return -ENODEV; data = kzalloc(sizeof(struct mshw0011_handler_data), @@ -460,25 +460,25 @@ static int mshw0011_install_space_handler(struct i2c_client *client) return -ENOMEM; data->client = client; - status = acpi_bus_attach_private_data(handle, (void *)data); + status = acpi_bus_attach_private_data(adev->handle, (void *)data); if (ACPI_FAILURE(status)) { kfree(data); return -ENOMEM; } - status = acpi_install_address_space_handler(handle, - ACPI_ADR_SPACE_GSBUS, - &mshw0011_space_handler, - NULL, - data); + status = acpi_install_address_space_handler(adev->handle, + ACPI_ADR_SPACE_GSBUS, + &mshw0011_space_handler, + NULL, + data); if (ACPI_FAILURE(status)) { dev_err(&client->dev, "Error installing i2c space handler\n"); - acpi_bus_detach_private_data(handle); + acpi_bus_detach_private_data(adev->handle); kfree(data); return -ENOMEM; } - acpi_walk_dep_device_list(handle); + acpi_dev_clear_dependencies(adev); return 0; } diff --git a/drivers/platform/surface/surface_acpi_notify.c b/drivers/platform/surface/surface_acpi_notify.c index ef9c1f8e8336..8339988d95c1 100644 --- a/drivers/platform/surface/surface_acpi_notify.c +++ b/drivers/platform/surface/surface_acpi_notify.c @@ -798,7 +798,7 @@ static int san_consumer_links_setup(struct platform_device *pdev) static int san_probe(struct platform_device *pdev) { - acpi_handle san = ACPI_HANDLE(&pdev->dev); + struct acpi_device *san = ACPI_COMPANION(&pdev->dev); struct ssam_controller *ctrl; struct san_data *data; acpi_status astatus; @@ -821,7 +821,8 @@ static int san_probe(struct platform_device *pdev) platform_set_drvdata(pdev, data); - astatus = acpi_install_address_space_handler(san, ACPI_ADR_SPACE_GSBUS, + astatus = acpi_install_address_space_handler(san->handle, + ACPI_ADR_SPACE_GSBUS, &san_opreg_handler, NULL, &data->info); if (ACPI_FAILURE(astatus)) @@ -835,7 +836,7 @@ static int san_probe(struct platform_device *pdev) if (status) goto err_install_dev; - acpi_walk_dep_device_list(san); + acpi_dev_clear_dependencies(san); return 0; err_install_dev: diff --git a/drivers/platform/surface/surface_aggregator_cdev.c b/drivers/platform/surface/surface_aggregator_cdev.c index 79e28fab7e40..30fb50fde450 100644 --- a/drivers/platform/surface/surface_aggregator_cdev.c +++ b/drivers/platform/surface/surface_aggregator_cdev.c @@ -3,29 +3,69 @@ * Provides user-space access to the SSAM EC via the /dev/surface/aggregator * misc device. Intended for debugging and development. * - * Copyright (C) 2020 Maximilian Luz + * Copyright (C) 2020-2021 Maximilian Luz */ #include +#include #include +#include #include #include #include #include +#include #include #include #include +#include #include #include +#include #define SSAM_CDEV_DEVICE_NAME "surface_aggregator_cdev" + +/* -- Main structures. ------------------------------------------------------ */ + +enum ssam_cdev_device_state { + SSAM_CDEV_DEVICE_SHUTDOWN_BIT = BIT(0), +}; + struct ssam_cdev { struct kref kref; struct rw_semaphore lock; + + struct device *dev; struct ssam_controller *ctrl; struct miscdevice mdev; + unsigned long flags; + + struct rw_semaphore client_lock; /* Guards client list. */ + struct list_head client_list; +}; + +struct ssam_cdev_client; + +struct ssam_cdev_notifier { + struct ssam_cdev_client *client; + struct ssam_event_notifier nf; +}; + +struct ssam_cdev_client { + struct ssam_cdev *cdev; + struct list_head node; + + struct mutex notifier_lock; /* Guards notifier access for registration */ + struct ssam_cdev_notifier *notifier[SSH_NUM_EVENTS]; + + struct mutex read_lock; /* Guards FIFO buffer read access */ + struct mutex write_lock; /* Guards FIFO buffer write access */ + DECLARE_KFIFO(buffer, u8, 4096); + + wait_queue_head_t waitq; + struct fasync_struct *fasync; }; static void __ssam_cdev_release(struct kref *kref) @@ -47,24 +87,173 @@ static void ssam_cdev_put(struct ssam_cdev *cdev) kref_put(&cdev->kref, __ssam_cdev_release); } -static int ssam_cdev_device_open(struct inode *inode, struct file *filp) -{ - struct miscdevice *mdev = filp->private_data; - struct ssam_cdev *cdev = container_of(mdev, struct ssam_cdev, mdev); - filp->private_data = ssam_cdev_get(cdev); - return stream_open(inode, filp); -} +/* -- Notifier handling. ---------------------------------------------------- */ -static int ssam_cdev_device_release(struct inode *inode, struct file *filp) +static u32 ssam_cdev_notifier(struct ssam_event_notifier *nf, const struct ssam_event *in) { - ssam_cdev_put(filp->private_data); + struct ssam_cdev_notifier *cdev_nf = container_of(nf, struct ssam_cdev_notifier, nf); + struct ssam_cdev_client *client = cdev_nf->client; + struct ssam_cdev_event event; + size_t n = struct_size(&event, data, in->length); + + /* Translate event. */ + event.target_category = in->target_category; + event.target_id = in->target_id; + event.command_id = in->command_id; + event.instance_id = in->instance_id; + event.length = in->length; + + mutex_lock(&client->write_lock); + + /* Make sure we have enough space. */ + if (kfifo_avail(&client->buffer) < n) { + dev_warn(client->cdev->dev, + "buffer full, dropping event (tc: %#04x, tid: %#04x, cid: %#04x, iid: %#04x)\n", + in->target_category, in->target_id, in->command_id, in->instance_id); + mutex_unlock(&client->write_lock); + return 0; + } + + /* Copy event header and payload. */ + kfifo_in(&client->buffer, (const u8 *)&event, struct_size(&event, data, 0)); + kfifo_in(&client->buffer, &in->data[0], in->length); + + mutex_unlock(&client->write_lock); + + /* Notify waiting readers. */ + kill_fasync(&client->fasync, SIGIO, POLL_IN); + wake_up_interruptible(&client->waitq); + + /* + * Don't mark events as handled, this is the job of a proper driver and + * not the debugging interface. + */ return 0; } -static long ssam_cdev_request(struct ssam_cdev *cdev, unsigned long arg) +static int ssam_cdev_notifier_register(struct ssam_cdev_client *client, u8 tc, int priority) +{ + const u16 rqid = ssh_tc_to_rqid(tc); + const u16 event = ssh_rqid_to_event(rqid); + struct ssam_cdev_notifier *nf; + int status; + + lockdep_assert_held_read(&client->cdev->lock); + + /* Validate notifier target category. */ + if (!ssh_rqid_is_event(rqid)) + return -EINVAL; + + mutex_lock(&client->notifier_lock); + + /* Check if the notifier has already been registered. */ + if (client->notifier[event]) { + mutex_unlock(&client->notifier_lock); + return -EEXIST; + } + + /* Allocate new notifier. */ + nf = kzalloc(sizeof(*nf), GFP_KERNEL); + if (!nf) { + mutex_unlock(&client->notifier_lock); + return -ENOMEM; + } + + /* + * Create a dummy notifier with the minimal required fields for + * observer registration. Note that we can skip fully specifying event + * and registry here as we do not need any matching and use silent + * registration, which does not enable the corresponding event. + */ + nf->client = client; + nf->nf.base.fn = ssam_cdev_notifier; + nf->nf.base.priority = priority; + nf->nf.event.id.target_category = tc; + nf->nf.event.mask = 0; /* Do not do any matching. */ + nf->nf.flags = SSAM_EVENT_NOTIFIER_OBSERVER; + + /* Register notifier. */ + status = ssam_notifier_register(client->cdev->ctrl, &nf->nf); + if (status) + kfree(nf); + else + client->notifier[event] = nf; + + mutex_unlock(&client->notifier_lock); + return status; +} + +static int ssam_cdev_notifier_unregister(struct ssam_cdev_client *client, u8 tc) +{ + const u16 rqid = ssh_tc_to_rqid(tc); + const u16 event = ssh_rqid_to_event(rqid); + int status; + + lockdep_assert_held_read(&client->cdev->lock); + + /* Validate notifier target category. */ + if (!ssh_rqid_is_event(rqid)) + return -EINVAL; + + mutex_lock(&client->notifier_lock); + + /* Check if the notifier is currently registered. */ + if (!client->notifier[event]) { + mutex_unlock(&client->notifier_lock); + return -ENOENT; + } + + /* Unregister and free notifier. */ + status = ssam_notifier_unregister(client->cdev->ctrl, &client->notifier[event]->nf); + kfree(client->notifier[event]); + client->notifier[event] = NULL; + + mutex_unlock(&client->notifier_lock); + return status; +} + +static void ssam_cdev_notifier_unregister_all(struct ssam_cdev_client *client) +{ + int i; + + down_read(&client->cdev->lock); + + /* + * This function may be used during shutdown, thus we need to test for + * cdev->ctrl instead of the SSAM_CDEV_DEVICE_SHUTDOWN_BIT bit. + */ + if (client->cdev->ctrl) { + for (i = 0; i < SSH_NUM_EVENTS; i++) + ssam_cdev_notifier_unregister(client, i + 1); + + } else { + int count = 0; + + /* + * Device has been shut down. Any notifier remaining is a bug, + * so warn about that as this would otherwise hardly be + * noticeable. Nevertheless, free them as well. + */ + mutex_lock(&client->notifier_lock); + for (i = 0; i < SSH_NUM_EVENTS; i++) { + count += !!(client->notifier[i]); + kfree(client->notifier[i]); + client->notifier[i] = NULL; + } + mutex_unlock(&client->notifier_lock); + + WARN_ON(count > 0); + } + + up_read(&client->cdev->lock); +} + + +/* -- IOCTL functions. ------------------------------------------------------ */ + +static long ssam_cdev_request(struct ssam_cdev_client *client, struct ssam_cdev_request __user *r) { - struct ssam_cdev_request __user *r; struct ssam_cdev_request rqst; struct ssam_request spec = {}; struct ssam_response rsp = {}; @@ -72,7 +261,8 @@ static long ssam_cdev_request(struct ssam_cdev *cdev, unsigned long arg) void __user *rspdata; int status = 0, ret = 0, tmp; - r = (struct ssam_cdev_request __user *)arg; + lockdep_assert_held_read(&client->cdev->lock); + ret = copy_struct_from_user(&rqst, sizeof(rqst), r, sizeof(*r)); if (ret) goto out; @@ -152,7 +342,7 @@ static long ssam_cdev_request(struct ssam_cdev *cdev, unsigned long arg) } /* Perform request. */ - status = ssam_request_sync(cdev->ctrl, &spec, &rsp); + status = ssam_request_sync(client->cdev->ctrl, &spec, &rsp); if (status) goto out; @@ -177,48 +367,315 @@ out: return ret; } -static long __ssam_cdev_device_ioctl(struct ssam_cdev *cdev, unsigned int cmd, +static long ssam_cdev_notif_register(struct ssam_cdev_client *client, + const struct ssam_cdev_notifier_desc __user *d) +{ + struct ssam_cdev_notifier_desc desc; + long ret; + + lockdep_assert_held_read(&client->cdev->lock); + + ret = copy_struct_from_user(&desc, sizeof(desc), d, sizeof(*d)); + if (ret) + return ret; + + return ssam_cdev_notifier_register(client, desc.target_category, desc.priority); +} + +static long ssam_cdev_notif_unregister(struct ssam_cdev_client *client, + const struct ssam_cdev_notifier_desc __user *d) +{ + struct ssam_cdev_notifier_desc desc; + long ret; + + lockdep_assert_held_read(&client->cdev->lock); + + ret = copy_struct_from_user(&desc, sizeof(desc), d, sizeof(*d)); + if (ret) + return ret; + + return ssam_cdev_notifier_unregister(client, desc.target_category); +} + +static long ssam_cdev_event_enable(struct ssam_cdev_client *client, + const struct ssam_cdev_event_desc __user *d) +{ + struct ssam_cdev_event_desc desc; + struct ssam_event_registry reg; + struct ssam_event_id id; + long ret; + + lockdep_assert_held_read(&client->cdev->lock); + + /* Read descriptor from user-space. */ + ret = copy_struct_from_user(&desc, sizeof(desc), d, sizeof(*d)); + if (ret) + return ret; + + /* Translate descriptor. */ + reg.target_category = desc.reg.target_category; + reg.target_id = desc.reg.target_id; + reg.cid_enable = desc.reg.cid_enable; + reg.cid_disable = desc.reg.cid_disable; + + id.target_category = desc.id.target_category; + id.instance = desc.id.instance; + + /* Disable event. */ + return ssam_controller_event_enable(client->cdev->ctrl, reg, id, desc.flags); +} + +static long ssam_cdev_event_disable(struct ssam_cdev_client *client, + const struct ssam_cdev_event_desc __user *d) +{ + struct ssam_cdev_event_desc desc; + struct ssam_event_registry reg; + struct ssam_event_id id; + long ret; + + lockdep_assert_held_read(&client->cdev->lock); + + /* Read descriptor from user-space. */ + ret = copy_struct_from_user(&desc, sizeof(desc), d, sizeof(*d)); + if (ret) + return ret; + + /* Translate descriptor. */ + reg.target_category = desc.reg.target_category; + reg.target_id = desc.reg.target_id; + reg.cid_enable = desc.reg.cid_enable; + reg.cid_disable = desc.reg.cid_disable; + + id.target_category = desc.id.target_category; + id.instance = desc.id.instance; + + /* Disable event. */ + return ssam_controller_event_disable(client->cdev->ctrl, reg, id, desc.flags); +} + + +/* -- File operations. ------------------------------------------------------ */ + +static int ssam_cdev_device_open(struct inode *inode, struct file *filp) +{ + struct miscdevice *mdev = filp->private_data; + struct ssam_cdev_client *client; + struct ssam_cdev *cdev = container_of(mdev, struct ssam_cdev, mdev); + + /* Initialize client */ + client = vzalloc(sizeof(*client)); + if (!client) + return -ENOMEM; + + client->cdev = ssam_cdev_get(cdev); + + INIT_LIST_HEAD(&client->node); + + mutex_init(&client->notifier_lock); + + mutex_init(&client->read_lock); + mutex_init(&client->write_lock); + INIT_KFIFO(client->buffer); + init_waitqueue_head(&client->waitq); + + filp->private_data = client; + + /* Attach client. */ + down_write(&cdev->client_lock); + + if (test_bit(SSAM_CDEV_DEVICE_SHUTDOWN_BIT, &cdev->flags)) { + up_write(&cdev->client_lock); + mutex_destroy(&client->write_lock); + mutex_destroy(&client->read_lock); + mutex_destroy(&client->notifier_lock); + ssam_cdev_put(client->cdev); + vfree(client); + return -ENODEV; + } + list_add_tail(&client->node, &cdev->client_list); + + up_write(&cdev->client_lock); + + stream_open(inode, filp); + return 0; +} + +static int ssam_cdev_device_release(struct inode *inode, struct file *filp) +{ + struct ssam_cdev_client *client = filp->private_data; + + /* Force-unregister all remaining notifiers of this client. */ + ssam_cdev_notifier_unregister_all(client); + + /* Detach client. */ + down_write(&client->cdev->client_lock); + list_del(&client->node); + up_write(&client->cdev->client_lock); + + /* Free client. */ + mutex_destroy(&client->write_lock); + mutex_destroy(&client->read_lock); + + mutex_destroy(&client->notifier_lock); + + ssam_cdev_put(client->cdev); + vfree(client); + + return 0; +} + +static long __ssam_cdev_device_ioctl(struct ssam_cdev_client *client, unsigned int cmd, unsigned long arg) { + lockdep_assert_held_read(&client->cdev->lock); + switch (cmd) { case SSAM_CDEV_REQUEST: - return ssam_cdev_request(cdev, arg); + return ssam_cdev_request(client, (struct ssam_cdev_request __user *)arg); + + case SSAM_CDEV_NOTIF_REGISTER: + return ssam_cdev_notif_register(client, + (struct ssam_cdev_notifier_desc __user *)arg); + + case SSAM_CDEV_NOTIF_UNREGISTER: + return ssam_cdev_notif_unregister(client, + (struct ssam_cdev_notifier_desc __user *)arg); + + case SSAM_CDEV_EVENT_ENABLE: + return ssam_cdev_event_enable(client, (struct ssam_cdev_event_desc __user *)arg); + + case SSAM_CDEV_EVENT_DISABLE: + return ssam_cdev_event_disable(client, (struct ssam_cdev_event_desc __user *)arg); default: return -ENOTTY; } } -static long ssam_cdev_device_ioctl(struct file *file, unsigned int cmd, - unsigned long arg) +static long ssam_cdev_device_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct ssam_cdev *cdev = file->private_data; + struct ssam_cdev_client *client = file->private_data; long status; /* Ensure that controller is valid for as long as we need it. */ + if (down_read_killable(&client->cdev->lock)) + return -ERESTARTSYS; + + if (test_bit(SSAM_CDEV_DEVICE_SHUTDOWN_BIT, &client->cdev->flags)) { + up_read(&client->cdev->lock); + return -ENODEV; + } + + status = __ssam_cdev_device_ioctl(client, cmd, arg); + + up_read(&client->cdev->lock); + return status; +} + +static ssize_t ssam_cdev_read(struct file *file, char __user *buf, size_t count, loff_t *offs) +{ + struct ssam_cdev_client *client = file->private_data; + struct ssam_cdev *cdev = client->cdev; + unsigned int copied; + int status = 0; + if (down_read_killable(&cdev->lock)) return -ERESTARTSYS; - if (!cdev->ctrl) { + /* Make sure we're not shut down. */ + if (test_bit(SSAM_CDEV_DEVICE_SHUTDOWN_BIT, &cdev->flags)) { up_read(&cdev->lock); return -ENODEV; } - status = __ssam_cdev_device_ioctl(cdev, cmd, arg); + do { + /* Check availability, wait if necessary. */ + if (kfifo_is_empty(&client->buffer)) { + up_read(&cdev->lock); + + if (file->f_flags & O_NONBLOCK) + return -EAGAIN; + + status = wait_event_interruptible(client->waitq, + !kfifo_is_empty(&client->buffer) || + test_bit(SSAM_CDEV_DEVICE_SHUTDOWN_BIT, + &cdev->flags)); + if (status < 0) + return status; + + if (down_read_killable(&cdev->lock)) + return -ERESTARTSYS; + + /* Need to check that we're not shut down again. */ + if (test_bit(SSAM_CDEV_DEVICE_SHUTDOWN_BIT, &cdev->flags)) { + up_read(&cdev->lock); + return -ENODEV; + } + } + + /* Try to read from FIFO. */ + if (mutex_lock_interruptible(&client->read_lock)) { + up_read(&cdev->lock); + return -ERESTARTSYS; + } + + status = kfifo_to_user(&client->buffer, buf, count, &copied); + mutex_unlock(&client->read_lock); + + if (status < 0) { + up_read(&cdev->lock); + return status; + } + + /* We might not have gotten anything, check this here. */ + if (copied == 0 && (file->f_flags & O_NONBLOCK)) { + up_read(&cdev->lock); + return -EAGAIN; + } + } while (copied == 0); up_read(&cdev->lock); - return status; + return copied; +} + +static __poll_t ssam_cdev_poll(struct file *file, struct poll_table_struct *pt) +{ + struct ssam_cdev_client *client = file->private_data; + __poll_t events = 0; + + if (test_bit(SSAM_CDEV_DEVICE_SHUTDOWN_BIT, &client->cdev->flags)) + return EPOLLHUP | EPOLLERR; + + poll_wait(file, &client->waitq, pt); + + if (!kfifo_is_empty(&client->buffer)) + events |= EPOLLIN | EPOLLRDNORM; + + return events; +} + +static int ssam_cdev_fasync(int fd, struct file *file, int on) +{ + struct ssam_cdev_client *client = file->private_data; + + return fasync_helper(fd, file, on, &client->fasync); } static const struct file_operations ssam_controller_fops = { .owner = THIS_MODULE, .open = ssam_cdev_device_open, .release = ssam_cdev_device_release, + .read = ssam_cdev_read, + .poll = ssam_cdev_poll, + .fasync = ssam_cdev_fasync, .unlocked_ioctl = ssam_cdev_device_ioctl, .compat_ioctl = ssam_cdev_device_ioctl, - .llseek = noop_llseek, + .llseek = no_llseek, }; + +/* -- Device and driver setup ----------------------------------------------- */ + static int ssam_dbg_device_probe(struct platform_device *pdev) { struct ssam_controller *ctrl; @@ -236,6 +693,7 @@ static int ssam_dbg_device_probe(struct platform_device *pdev) kref_init(&cdev->kref); init_rwsem(&cdev->lock); cdev->ctrl = ctrl; + cdev->dev = &pdev->dev; cdev->mdev.parent = &pdev->dev; cdev->mdev.minor = MISC_DYNAMIC_MINOR; @@ -243,6 +701,9 @@ static int ssam_dbg_device_probe(struct platform_device *pdev) cdev->mdev.nodename = "surface/aggregator"; cdev->mdev.fops = &ssam_controller_fops; + init_rwsem(&cdev->client_lock); + INIT_LIST_HEAD(&cdev->client_list); + status = misc_register(&cdev->mdev); if (status) { kfree(cdev); @@ -256,8 +717,32 @@ static int ssam_dbg_device_probe(struct platform_device *pdev) static int ssam_dbg_device_remove(struct platform_device *pdev) { struct ssam_cdev *cdev = platform_get_drvdata(pdev); + struct ssam_cdev_client *client; - misc_deregister(&cdev->mdev); + /* + * Mark device as shut-down. Prevent new clients from being added and + * new operations from being executed. + */ + set_bit(SSAM_CDEV_DEVICE_SHUTDOWN_BIT, &cdev->flags); + + down_write(&cdev->client_lock); + + /* Remove all notifiers registered by us. */ + list_for_each_entry(client, &cdev->client_list, node) { + ssam_cdev_notifier_unregister_all(client); + } + + /* Wake up async clients. */ + list_for_each_entry(client, &cdev->client_list, node) { + kill_fasync(&client->fasync, SIGIO, POLL_HUP); + } + + /* Wake up blocking clients. */ + list_for_each_entry(client, &cdev->client_list, node) { + wake_up_interruptible(&client->waitq); + } + + up_write(&cdev->client_lock); /* * The controller is only guaranteed to be valid for as long as the @@ -266,8 +751,11 @@ static int ssam_dbg_device_remove(struct platform_device *pdev) */ down_write(&cdev->lock); cdev->ctrl = NULL; + cdev->dev = NULL; up_write(&cdev->lock); + misc_deregister(&cdev->mdev); + ssam_cdev_put(cdev); return 0; } diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c index ef83461fa536..4428c4330229 100644 --- a/drivers/platform/surface/surface_aggregator_registry.c +++ b/drivers/platform/surface/surface_aggregator_registry.c @@ -119,8 +119,13 @@ static const struct software_node ssam_node_hid_base_iid6 = { .parent = &ssam_node_hub_base, }; -/* Devices for Surface Book 2. */ -static const struct software_node *ssam_node_group_sb2[] = { +/* + * Devices for 5th- and 6th-generations models: + * - Surface Book 2, + * - Surface Laptop 1 and 2, + * - Surface Pro 5 and 6. + */ +static const struct software_node *ssam_node_group_gen5[] = { &ssam_node_root, &ssam_node_tmp_pprof, NULL, @@ -142,20 +147,6 @@ static const struct software_node *ssam_node_group_sb3[] = { NULL, }; -/* Devices for Surface Laptop 1. */ -static const struct software_node *ssam_node_group_sl1[] = { - &ssam_node_root, - &ssam_node_tmp_pprof, - NULL, -}; - -/* Devices for Surface Laptop 2. */ -static const struct software_node *ssam_node_group_sl2[] = { - &ssam_node_root, - &ssam_node_tmp_pprof, - NULL, -}; - /* Devices for Surface Laptop 3 and 4. */ static const struct software_node *ssam_node_group_sl3[] = { &ssam_node_root, @@ -177,20 +168,6 @@ static const struct software_node *ssam_node_group_slg1[] = { NULL, }; -/* Devices for Surface Pro 5. */ -static const struct software_node *ssam_node_group_sp5[] = { - &ssam_node_root, - &ssam_node_tmp_pprof, - NULL, -}; - -/* Devices for Surface Pro 6. */ -static const struct software_node *ssam_node_group_sp6[] = { - &ssam_node_root, - &ssam_node_tmp_pprof, - NULL, -}; - /* Devices for Surface Pro 7 and Surface Pro 7+. */ static const struct software_node *ssam_node_group_sp7[] = { &ssam_node_root, @@ -495,10 +472,10 @@ static struct ssam_device_driver ssam_base_hub_driver = { static const struct acpi_device_id ssam_platform_hub_match[] = { /* Surface Pro 4, 5, and 6 (OMBR < 0x10) */ - { "MSHW0081", (unsigned long)ssam_node_group_sp5 }, + { "MSHW0081", (unsigned long)ssam_node_group_gen5 }, /* Surface Pro 6 (OMBR >= 0x10) */ - { "MSHW0111", (unsigned long)ssam_node_group_sp6 }, + { "MSHW0111", (unsigned long)ssam_node_group_gen5 }, /* Surface Pro 7 */ { "MSHW0116", (unsigned long)ssam_node_group_sp7 }, @@ -507,16 +484,16 @@ static const struct acpi_device_id ssam_platform_hub_match[] = { { "MSHW0119", (unsigned long)ssam_node_group_sp7 }, /* Surface Book 2 */ - { "MSHW0107", (unsigned long)ssam_node_group_sb2 }, + { "MSHW0107", (unsigned long)ssam_node_group_gen5 }, /* Surface Book 3 */ { "MSHW0117", (unsigned long)ssam_node_group_sb3 }, /* Surface Laptop 1 */ - { "MSHW0086", (unsigned long)ssam_node_group_sl1 }, + { "MSHW0086", (unsigned long)ssam_node_group_gen5 }, /* Surface Laptop 2 */ - { "MSHW0112", (unsigned long)ssam_node_group_sl2 }, + { "MSHW0112", (unsigned long)ssam_node_group_gen5 }, /* Surface Laptop 3 (13", Intel) */ { "MSHW0114", (unsigned long)ssam_node_group_sl3 }, diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 60592fb88e7a..7d385c3b2239 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -415,16 +415,17 @@ config HP_ACCEL To compile this driver as a module, choose M here: the module will be called hp_accel. -config HP_WIRELESS - tristate "HP wireless button" +config WIRELESS_HOTKEY + tristate "Wireless hotkey button" depends on ACPI depends on INPUT help - This driver provides supports for new HP wireless button for Windows 8. + This driver provides supports for the wireless buttons found on some AMD, + HP, & Xioami laptops. On such systems the driver should load automatically (via ACPI alias). To compile this driver as a module, choose M here: the module will - be called hp-wireless. + be called wireless-hotkey. config HP_WMI tristate "HP WMI extras" @@ -639,6 +640,19 @@ config THINKPAD_ACPI_HOTKEY_POLL If you are not sure, say Y here. The driver enables polling only if it is strictly necessary to do so. +config THINKPAD_LMI + tristate "Lenovo WMI-based systems management driver" + depends on ACPI_WMI + select FW_ATTR_CLASS + help + This driver allows changing BIOS settings on Lenovo machines whose + BIOS support the WMI interface. + + To compile this driver as a module, choose M here: the module will + be called think-lmi. + +source "drivers/platform/x86/intel/Kconfig" + config INTEL_ATOMISP2_LED tristate "Intel AtomISP2 camera LED driver" depends on GPIOLIB && LEDS_GPIO @@ -673,30 +687,6 @@ config INTEL_ATOMISP2_PM To compile this driver as a module, choose M here: the module will be called intel_atomisp2_pm. -config INTEL_CHT_INT33FE - tristate "Intel Cherry Trail ACPI INT33FE Driver" - depends on X86 && ACPI && I2C && REGULATOR - depends on CHARGER_BQ24190=y || (CHARGER_BQ24190=m && m) - depends on USB_ROLES_INTEL_XHCI=y || (USB_ROLES_INTEL_XHCI=m && m) - depends on TYPEC_MUX_PI3USB30532=y || (TYPEC_MUX_PI3USB30532=m && m) - help - This driver add support for the INT33FE ACPI device found on - some Intel Cherry Trail devices. - - There are two kinds of INT33FE ACPI device possible: for hardware - with USB Type-C and Micro-B connectors. This driver supports both. - - The INT33FE ACPI device has a CRS table with I2cSerialBusV2 - resources for Fuel Gauge Controller and (in the Type-C variant) - FUSB302 USB Type-C Controller and PI3USB30532 USB switch. - This driver instantiates i2c-clients for these, so that standard - i2c drivers for these chips can bind to the them. - - If you enable this driver it is advised to also select - CONFIG_BATTERY_BQ27XXX=m or CONFIG_BATTERY_BQ27XXX_I2C=m for Micro-B - device and CONFIG_TYPEC_FUSB302=m and CONFIG_BATTERY_MAX17042=m - for Type-C device. - config INTEL_HID_EVENT tristate "INTEL HID Event" depends on ACPI @@ -1076,6 +1066,9 @@ config TOUCHSCREEN_DMI the OS-image for the device. This option supplies the missing info. Enable this for x86 tablets with Silead or Chipone touchscreens. +config FW_ATTR_CLASS + tristate + config INTEL_IMR bool "Intel Isolated Memory Region support" depends on X86_INTEL_QUARK && IOSF_MBI diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile index dcc8cdb95b4d..7ee369aab10d 100644 --- a/drivers/platform/x86/Makefile +++ b/drivers/platform/x86/Makefile @@ -52,7 +52,6 @@ obj-$(CONFIG_GPD_POCKET_FAN) += gpd-pocket-fan.o # Hewlett Packard obj-$(CONFIG_HP_ACCEL) += hp_accel.o -obj-$(CONFIG_HP_WIRELESS) += hp-wireless.o obj-$(CONFIG_HP_WMI) += hp-wmi.o obj-$(CONFIG_TC1100_WMI) += tc1100-wmi.o @@ -64,14 +63,13 @@ obj-$(CONFIG_IBM_RTL) += ibm_rtl.o obj-$(CONFIG_IDEAPAD_LAPTOP) += ideapad-laptop.o obj-$(CONFIG_SENSORS_HDAPS) += hdaps.o obj-$(CONFIG_THINKPAD_ACPI) += thinkpad_acpi.o +obj-$(CONFIG_THINKPAD_LMI) += think-lmi.o # Intel +obj-$(CONFIG_X86_PLATFORM_DRIVERS_INTEL) += intel/ + obj-$(CONFIG_INTEL_ATOMISP2_LED) += intel_atomisp2_led.o obj-$(CONFIG_INTEL_ATOMISP2_PM) += intel_atomisp2_pm.o -obj-$(CONFIG_INTEL_CHT_INT33FE) += intel_cht_int33fe.o -intel_cht_int33fe-objs := intel_cht_int33fe_common.o \ - intel_cht_int33fe_typec.o \ - intel_cht_int33fe_microb.o obj-$(CONFIG_INTEL_HID_EVENT) += intel-hid.o obj-$(CONFIG_INTEL_INT0002_VGPIO) += intel_int0002_vgpio.o obj-$(CONFIG_INTEL_MENLOW) += intel_menlow.o @@ -112,9 +110,11 @@ obj-$(CONFIG_SYSTEM76_ACPI) += system76_acpi.o obj-$(CONFIG_TOPSTAR_LAPTOP) += topstar-laptop.o # Platform drivers +obj-$(CONFIG_FW_ATTR_CLASS) += firmware_attributes_class.o obj-$(CONFIG_I2C_MULTI_INSTANTIATE) += i2c-multi-instantiate.o obj-$(CONFIG_MLX_PLATFORM) += mlx-platform.o obj-$(CONFIG_TOUCHSCREEN_DMI) += touchscreen_dmi.o +obj-$(CONFIG_WIRELESS_HOTKEY) += wireless-hotkey.o # Intel uncore drivers obj-$(CONFIG_INTEL_IPS) += intel_ips.o diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index d41d7ad14be0..0cb927f0f301 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -110,11 +110,6 @@ static struct quirk_entry quirk_asus_forceals = { .wmi_force_als_set = true, }; -static struct quirk_entry quirk_asus_vendor_backlight = { - .wmi_backlight_power = true, - .wmi_backlight_set_devstate = true, -}; - static struct quirk_entry quirk_asus_use_kbd_dock_devid = { .use_kbd_dock_devid = true, }; @@ -425,78 +420,6 @@ static const struct dmi_system_id asus_quirks[] = { }, .driver_data = &quirk_asus_forceals, }, - { - .callback = dmi_matched, - .ident = "ASUSTeK COMPUTER INC. GA401IH", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "GA401IH"), - }, - .driver_data = &quirk_asus_vendor_backlight, - }, - { - .callback = dmi_matched, - .ident = "ASUSTeK COMPUTER INC. GA401II", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "GA401II"), - }, - .driver_data = &quirk_asus_vendor_backlight, - }, - { - .callback = dmi_matched, - .ident = "ASUSTeK COMPUTER INC. GA401IU", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "GA401IU"), - }, - .driver_data = &quirk_asus_vendor_backlight, - }, - { - .callback = dmi_matched, - .ident = "ASUSTeK COMPUTER INC. GA401IV", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "GA401IV"), - }, - .driver_data = &quirk_asus_vendor_backlight, - }, - { - .callback = dmi_matched, - .ident = "ASUSTeK COMPUTER INC. GA401IVC", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "GA401IVC"), - }, - .driver_data = &quirk_asus_vendor_backlight, - }, - { - .callback = dmi_matched, - .ident = "ASUSTeK COMPUTER INC. GA502II", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "GA502II"), - }, - .driver_data = &quirk_asus_vendor_backlight, - }, - { - .callback = dmi_matched, - .ident = "ASUSTeK COMPUTER INC. GA502IU", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "GA502IU"), - }, - .driver_data = &quirk_asus_vendor_backlight, - }, - { - .callback = dmi_matched, - .ident = "ASUSTeK COMPUTER INC. GA502IV", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), - DMI_MATCH(DMI_PRODUCT_NAME, "GA502IV"), - }, - .driver_data = &quirk_asus_vendor_backlight, - }, { .callback = dmi_matched, .ident = "Asus Transformer T100TA / T100HA / T100CHI", diff --git a/drivers/platform/x86/dell/Kconfig b/drivers/platform/x86/dell/Kconfig index e0a55337f51a..9e7314d90bea 100644 --- a/drivers/platform/x86/dell/Kconfig +++ b/drivers/platform/x86/dell/Kconfig @@ -5,7 +5,6 @@ menuconfig X86_PLATFORM_DRIVERS_DELL bool "Dell X86 Platform Specific Device Drivers" - default n depends on X86_PLATFORM_DEVICES help Say Y here to get to see options for device drivers for various @@ -53,6 +52,7 @@ config DELL_LAPTOP depends on BACKLIGHT_CLASS_DEVICE depends on ACPI_VIDEO || ACPI_VIDEO = n depends on RFKILL || RFKILL = n + depends on DELL_WMI || DELL_WMI = n depends on SERIO_I8042 depends on DELL_SMBIOS select POWER_SUPPLY @@ -164,6 +164,14 @@ config DELL_WMI To compile this driver as a module, choose M here: the module will be called dell-wmi. +config DELL_WMI_PRIVACY + bool "Dell WMI Hardware Privacy Support" + depends on DELL_WMI + depends on LEDS_TRIGGER_AUDIO + help + This option adds integration with the "Dell Hardware Privacy" + feature of Dell laptops to the dell-wmi driver. + config DELL_WMI_AIO tristate "WMI Hotkeys for Dell All-In-One series" default m @@ -197,6 +205,7 @@ config DELL_WMI_SYSMAN depends on ACPI_WMI depends on DMI select NLS + select FW_ATTR_CLASS help This driver allows changing BIOS settings on many Dell machines from 2018 and newer without the use of any additional software. diff --git a/drivers/platform/x86/dell/Makefile b/drivers/platform/x86/dell/Makefile index d720a3e42ae3..ddba1df71e80 100644 --- a/drivers/platform/x86/dell/Makefile +++ b/drivers/platform/x86/dell/Makefile @@ -15,6 +15,8 @@ dell-smbios-$(CONFIG_DELL_SMBIOS_WMI) += dell-smbios-wmi.o dell-smbios-$(CONFIG_DELL_SMBIOS_SMM) += dell-smbios-smm.o obj-$(CONFIG_DELL_SMO8800) += dell-smo8800.o obj-$(CONFIG_DELL_WMI) += dell-wmi.o +dell-wmi-objs := dell-wmi-base.o +dell-wmi-$(CONFIG_DELL_WMI_PRIVACY) += dell-wmi-privacy.o obj-$(CONFIG_DELL_WMI_AIO) += dell-wmi-aio.o obj-$(CONFIG_DELL_WMI_DESCRIPTOR) += dell-wmi-descriptor.o obj-$(CONFIG_DELL_WMI_LED) += dell-wmi-led.o diff --git a/drivers/platform/x86/dell/dcdbas.c b/drivers/platform/x86/dell/dcdbas.c index d513a59a5d47..28447c180be8 100644 --- a/drivers/platform/x86/dell/dcdbas.c +++ b/drivers/platform/x86/dell/dcdbas.c @@ -394,8 +394,7 @@ static int host_control_smi(void) /* wait a few to see if it executed */ num_ticks = TIMEOUT_USEC_SHORT_SEMA_BLOCKING; - while ((cmd_status = inb(PCAT_APM_STATUS_PORT)) - == ESM_STATUS_CMD_UNSUCCESSFUL) { + while ((s8)inb(PCAT_APM_STATUS_PORT) == ESM_STATUS_CMD_UNSUCCESSFUL) { num_ticks--; if (num_ticks == EXPIRED_TIMER) return -ETIME; diff --git a/drivers/platform/x86/dell/dell-laptop.c b/drivers/platform/x86/dell/dell-laptop.c index 70edc5bb3a14..8230e7a68a5e 100644 --- a/drivers/platform/x86/dell/dell-laptop.c +++ b/drivers/platform/x86/dell/dell-laptop.c @@ -31,6 +31,8 @@ #include "dell-rbtn.h" #include "dell-smbios.h" +#include "dell-wmi-privacy.h" + struct quirk_entry { bool touchpad_led; bool kbd_led_not_present; @@ -90,6 +92,7 @@ static struct rfkill *wifi_rfkill; static struct rfkill *bluetooth_rfkill; static struct rfkill *wwan_rfkill; static bool force_rfkill; +static bool micmute_led_registered; module_param(force_rfkill, bool, 0444); MODULE_PARM_DESC(force_rfkill, "enable rfkill on non whitelisted models"); @@ -2205,11 +2208,13 @@ static int __init dell_init(void) dell_laptop_register_notifier(&dell_laptop_notifier); if (dell_smbios_find_token(GLOBAL_MIC_MUTE_DISABLE) && - dell_smbios_find_token(GLOBAL_MIC_MUTE_ENABLE)) { + dell_smbios_find_token(GLOBAL_MIC_MUTE_ENABLE) && + !dell_privacy_has_mic_mute()) { micmute_led_cdev.brightness = ledtrig_audio_get(LED_AUDIO_MICMUTE); ret = led_classdev_register(&platform_device->dev, &micmute_led_cdev); if (ret < 0) goto fail_led; + micmute_led_registered = true; } if (acpi_video_get_backlight_type() != acpi_backlight_vendor) @@ -2257,7 +2262,8 @@ static int __init dell_init(void) fail_get_brightness: backlight_device_unregister(dell_backlight_device); fail_backlight: - led_classdev_unregister(&micmute_led_cdev); + if (micmute_led_registered) + led_classdev_unregister(&micmute_led_cdev); fail_led: dell_cleanup_rfkill(); fail_rfkill: @@ -2278,7 +2284,8 @@ static void __exit dell_exit(void) touchpad_led_exit(); kbd_led_exit(); backlight_device_unregister(dell_backlight_device); - led_classdev_unregister(&micmute_led_cdev); + if (micmute_led_registered) + led_classdev_unregister(&micmute_led_cdev); dell_cleanup_rfkill(); if (platform_device) { platform_device_unregister(platform_device); diff --git a/drivers/platform/x86/dell/dell-wmi.c b/drivers/platform/x86/dell/dell-wmi-base.c similarity index 98% rename from drivers/platform/x86/dell/dell-wmi.c rename to drivers/platform/x86/dell/dell-wmi-base.c index 5e1b7f897df5..089c125e18f7 100644 --- a/drivers/platform/x86/dell/dell-wmi.c +++ b/drivers/platform/x86/dell/dell-wmi-base.c @@ -27,6 +27,7 @@ #include #include "dell-smbios.h" #include "dell-wmi-descriptor.h" +#include "dell-wmi-privacy.h" MODULE_AUTHOR("Matthew Garrett "); MODULE_AUTHOR("Pali Rohár "); @@ -427,7 +428,6 @@ static void dell_wmi_notify(struct wmi_device *wdev, switch (buffer_entry[1]) { case 0x0000: /* One key pressed or event occurred */ - case 0x0012: /* Event with extended data occurred */ if (len > 2) dell_wmi_process_key(wdev, buffer_entry[1], buffer_entry[2]); @@ -439,6 +439,13 @@ static void dell_wmi_notify(struct wmi_device *wdev, dell_wmi_process_key(wdev, buffer_entry[1], buffer_entry[i]); break; + case 0x0012: + if ((len > 4) && dell_privacy_process_event(buffer_entry[1], buffer_entry[3], + buffer_entry[4])) + /* dell_privacy_process_event has handled the event */; + else if (len > 2) + dell_wmi_process_key(wdev, buffer_entry[1], buffer_entry[2]); + break; default: /* Unknown event */ pr_info("Unknown WMI event type 0x%x\n", (int)buffer_entry[1]); @@ -747,6 +754,10 @@ static int __init dell_wmi_init(void) } } + err = dell_privacy_register_driver(); + if (err) + return err; + return wmi_driver_register(&dell_wmi_driver); } late_initcall(dell_wmi_init); @@ -757,6 +768,7 @@ static void __exit dell_wmi_exit(void) dell_wmi_events_set_enabled(false); wmi_driver_unregister(&dell_wmi_driver); + dell_privacy_unregister_driver(); } module_exit(dell_wmi_exit); diff --git a/drivers/platform/x86/dell/dell-wmi-privacy.c b/drivers/platform/x86/dell/dell-wmi-privacy.c new file mode 100644 index 000000000000..074b7e68c227 --- /dev/null +++ b/drivers/platform/x86/dell/dell-wmi-privacy.c @@ -0,0 +1,391 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Dell privacy notification driver + * + * Copyright (C) 2021 Dell Inc. All Rights Reserved. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "dell-wmi-privacy.h" + +#define DELL_PRIVACY_GUID "6932965F-1671-4CEB-B988-D3AB0A901919" +#define MICROPHONE_STATUS BIT(0) +#define CAMERA_STATUS BIT(1) +#define DELL_PRIVACY_AUDIO_EVENT 0x1 +#define DELL_PRIVACY_CAMERA_EVENT 0x2 +#define led_to_priv(c) container_of(c, struct privacy_wmi_data, cdev) + +/* + * The wmi_list is used to store the privacy_priv struct with mutex protecting + */ +static LIST_HEAD(wmi_list); +static DEFINE_MUTEX(list_mutex); + +struct privacy_wmi_data { + struct input_dev *input_dev; + struct wmi_device *wdev; + struct list_head list; + struct led_classdev cdev; + u32 features_present; + u32 last_status; +}; + +/* DELL Privacy Type */ +enum dell_hardware_privacy_type { + DELL_PRIVACY_TYPE_AUDIO = 0, + DELL_PRIVACY_TYPE_CAMERA, + DELL_PRIVACY_TYPE_SCREEN, + DELL_PRIVACY_TYPE_MAX, +}; + +static const char * const privacy_types[DELL_PRIVACY_TYPE_MAX] = { + [DELL_PRIVACY_TYPE_AUDIO] = "Microphone", + [DELL_PRIVACY_TYPE_CAMERA] = "Camera Shutter", + [DELL_PRIVACY_TYPE_SCREEN] = "ePrivacy Screen", +}; + +/* + * Keymap for WMI privacy events of type 0x0012 + */ +static const struct key_entry dell_wmi_keymap_type_0012[] = { + /* privacy mic mute */ + { KE_KEY, 0x0001, { KEY_MICMUTE } }, + /* privacy camera mute */ + { KE_SW, 0x0002, { SW_CAMERA_LENS_COVER } }, + { KE_END, 0}, +}; + +bool dell_privacy_has_mic_mute(void) +{ + struct privacy_wmi_data *priv; + + mutex_lock(&list_mutex); + priv = list_first_entry_or_null(&wmi_list, + struct privacy_wmi_data, + list); + mutex_unlock(&list_mutex); + + return priv && (priv->features_present & BIT(DELL_PRIVACY_TYPE_AUDIO)); +} +EXPORT_SYMBOL_GPL(dell_privacy_has_mic_mute); + +/* + * The flow of privacy event: + * 1) User presses key. HW does stuff with this key (timeout is started) + * 2) WMI event is emitted from BIOS + * 3) WMI event is received by dell-privacy + * 4) KEY_MICMUTE emitted from dell-privacy + * 5) Userland picks up key and modifies kcontrol for SW mute + * 6) Codec kernel driver catches and calls ledtrig_audio_set which will call + * led_set_brightness() on the LED registered by dell_privacy_leds_setup() + * 7) dell-privacy notifies EC, the timeout is cancelled and the HW mute activates. + * If the EC is not notified then the HW mic mute will activate when the timeout + * triggers, just a bit later than with the active ack. + */ +bool dell_privacy_process_event(int type, int code, int status) +{ + struct privacy_wmi_data *priv; + const struct key_entry *key; + bool ret = false; + + mutex_lock(&list_mutex); + priv = list_first_entry_or_null(&wmi_list, + struct privacy_wmi_data, + list); + if (!priv) + goto error; + + key = sparse_keymap_entry_from_scancode(priv->input_dev, (type << 16) | code); + if (!key) { + dev_warn(&priv->wdev->dev, "Unknown key with type 0x%04x and code 0x%04x pressed\n", + type, code); + goto error; + } + dev_dbg(&priv->wdev->dev, "Key with type 0x%04x and code 0x%04x pressed\n", type, code); + + switch (code) { + case DELL_PRIVACY_AUDIO_EVENT: /* Mic mute */ + case DELL_PRIVACY_CAMERA_EVENT: /* Camera mute */ + priv->last_status = status; + sparse_keymap_report_entry(priv->input_dev, key, 1, true); + ret = true; + break; + default: + dev_dbg(&priv->wdev->dev, "unknown event type 0x%04x 0x%04x\n", type, code); + } + +error: + mutex_unlock(&list_mutex); + return ret; +} + +static ssize_t dell_privacy_supported_type_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct privacy_wmi_data *priv = dev_get_drvdata(dev); + enum dell_hardware_privacy_type type; + u32 privacy_list; + int len = 0; + + privacy_list = priv->features_present; + for (type = DELL_PRIVACY_TYPE_AUDIO; type < DELL_PRIVACY_TYPE_MAX; type++) { + if (privacy_list & BIT(type)) + len += sysfs_emit_at(buf, len, "[%s] [supported]\n", privacy_types[type]); + else + len += sysfs_emit_at(buf, len, "[%s] [unsupported]\n", privacy_types[type]); + } + + return len; +} + +static ssize_t dell_privacy_current_state_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct privacy_wmi_data *priv = dev_get_drvdata(dev); + u32 privacy_supported = priv->features_present; + enum dell_hardware_privacy_type type; + u32 privacy_state = priv->last_status; + int len = 0; + + for (type = DELL_PRIVACY_TYPE_AUDIO; type < DELL_PRIVACY_TYPE_MAX; type++) { + if (privacy_supported & BIT(type)) { + if (privacy_state & BIT(type)) + len += sysfs_emit_at(buf, len, "[%s] [unmuted]\n", privacy_types[type]); + else + len += sysfs_emit_at(buf, len, "[%s] [muted]\n", privacy_types[type]); + } + } + + return len; +} + +static DEVICE_ATTR_RO(dell_privacy_supported_type); +static DEVICE_ATTR_RO(dell_privacy_current_state); + +static struct attribute *privacy_attributes[] = { + &dev_attr_dell_privacy_supported_type.attr, + &dev_attr_dell_privacy_current_state.attr, + NULL, +}; + +static const struct attribute_group privacy_attribute_group = { + .attrs = privacy_attributes +}; + +/* + * Describes the Device State class exposed by BIOS which can be consumed by + * various applications interested in knowing the Privacy feature capabilities. + * class DeviceState + * { + * [key, read] string InstanceName; + * [read] boolean ReadOnly; + * + * [WmiDataId(1), read] uint32 DevicesSupported; + * 0 - None; 0x1 - Microphone; 0x2 - Camera; 0x4 - ePrivacy Screen + * + * [WmiDataId(2), read] uint32 CurrentState; + * 0 - Off; 1 - On; Bit0 - Microphone; Bit1 - Camera; Bit2 - ePrivacyScreen + * }; + */ +static int get_current_status(struct wmi_device *wdev) +{ + struct privacy_wmi_data *priv = dev_get_drvdata(&wdev->dev); + union acpi_object *obj_present; + u32 *buffer; + int ret = 0; + + if (!priv) { + dev_err(&wdev->dev, "dell privacy priv is NULL\n"); + return -EINVAL; + } + /* check privacy support features and device states */ + obj_present = wmidev_block_query(wdev, 0); + if (!obj_present) { + dev_err(&wdev->dev, "failed to read Binary MOF\n"); + return -EIO; + } + + if (obj_present->type != ACPI_TYPE_BUFFER) { + dev_err(&wdev->dev, "Binary MOF is not a buffer!\n"); + ret = -EIO; + goto obj_free; + } + /* Although it's not technically a failure, this would lead to + * unexpected behavior + */ + if (obj_present->buffer.length != 8) { + dev_err(&wdev->dev, "Dell privacy buffer has unexpected length (%d)!\n", + obj_present->buffer.length); + ret = -EINVAL; + goto obj_free; + } + buffer = (u32 *)obj_present->buffer.pointer; + priv->features_present = buffer[0]; + priv->last_status = buffer[1]; + +obj_free: + kfree(obj_present); + return ret; +} + +static int dell_privacy_micmute_led_set(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + struct privacy_wmi_data *priv = led_to_priv(led_cdev); + static char *acpi_method = (char *)"ECAK"; + acpi_status status; + acpi_handle handle; + + handle = ec_get_handle(); + if (!handle) + return -EIO; + + if (!acpi_has_method(handle, acpi_method)) + return -EIO; + + status = acpi_evaluate_object(handle, acpi_method, NULL, NULL); + if (ACPI_FAILURE(status)) { + dev_err(&priv->wdev->dev, "Error setting privacy EC ack value: %s\n", + acpi_format_exception(status)); + return -EIO; + } + + return 0; +} + +/* + * Pressing the mute key activates a time delayed circuit to physically cut + * off the mute. The LED is in the same circuit, so it reflects the true + * state of the HW mute. The reason for the EC "ack" is so that software + * can first invoke a SW mute before the HW circuit is cut off. Without SW + * cutting this off first does not affect the time delayed muting or status + * of the LED but there is a possibility of a "popping" noise. + * + * If the EC receives the SW ack, the circuit will be activated before the + * delay completed. + * + * Exposing as an LED device allows the codec drivers notification path to + * EC ACK to work + */ +static int dell_privacy_leds_setup(struct device *dev) +{ + struct privacy_wmi_data *priv = dev_get_drvdata(dev); + + priv->cdev.name = "dell-privacy::micmute"; + priv->cdev.max_brightness = 1; + priv->cdev.brightness_set_blocking = dell_privacy_micmute_led_set; + priv->cdev.default_trigger = "audio-micmute"; + priv->cdev.brightness = ledtrig_audio_get(LED_AUDIO_MICMUTE); + return devm_led_classdev_register(dev, &priv->cdev); +} + +static int dell_privacy_wmi_probe(struct wmi_device *wdev, const void *context) +{ + struct privacy_wmi_data *priv; + struct key_entry *keymap; + int ret, i; + + ret = wmi_has_guid(DELL_PRIVACY_GUID); + if (!ret) + pr_debug("Unable to detect available Dell privacy devices!\n"); + + priv = devm_kzalloc(&wdev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + dev_set_drvdata(&wdev->dev, priv); + priv->wdev = wdev; + /* create evdev passing interface */ + priv->input_dev = devm_input_allocate_device(&wdev->dev); + if (!priv->input_dev) + return -ENOMEM; + + /* remap the wmi keymap event to new keymap */ + keymap = kcalloc(ARRAY_SIZE(dell_wmi_keymap_type_0012), + sizeof(struct key_entry), GFP_KERNEL); + if (!keymap) + return -ENOMEM; + + /* remap the keymap code with Dell privacy key type 0x12 as prefix + * KEY_MICMUTE scancode will be reported as 0x120001 + */ + for (i = 0; i < ARRAY_SIZE(dell_wmi_keymap_type_0012); i++) { + keymap[i] = dell_wmi_keymap_type_0012[i]; + keymap[i].code |= (0x0012 << 16); + } + ret = sparse_keymap_setup(priv->input_dev, keymap, NULL); + kfree(keymap); + if (ret) + return ret; + + priv->input_dev->dev.parent = &wdev->dev; + priv->input_dev->name = "Dell Privacy Driver"; + priv->input_dev->id.bustype = BUS_HOST; + + ret = input_register_device(priv->input_dev); + if (ret) + return ret; + + ret = get_current_status(priv->wdev); + if (ret) + return ret; + + ret = devm_device_add_group(&wdev->dev, &privacy_attribute_group); + if (ret) + return ret; + + if (priv->features_present & BIT(DELL_PRIVACY_TYPE_AUDIO)) { + ret = dell_privacy_leds_setup(&priv->wdev->dev); + if (ret) + return ret; + } + mutex_lock(&list_mutex); + list_add_tail(&priv->list, &wmi_list); + mutex_unlock(&list_mutex); + return 0; +} + +static void dell_privacy_wmi_remove(struct wmi_device *wdev) +{ + struct privacy_wmi_data *priv = dev_get_drvdata(&wdev->dev); + + mutex_lock(&list_mutex); + list_del(&priv->list); + mutex_unlock(&list_mutex); +} + +static const struct wmi_device_id dell_wmi_privacy_wmi_id_table[] = { + { .guid_string = DELL_PRIVACY_GUID }, + { }, +}; + +static struct wmi_driver dell_privacy_wmi_driver = { + .driver = { + .name = "dell-privacy", + }, + .probe = dell_privacy_wmi_probe, + .remove = dell_privacy_wmi_remove, + .id_table = dell_wmi_privacy_wmi_id_table, +}; + +int dell_privacy_register_driver(void) +{ + return wmi_driver_register(&dell_privacy_wmi_driver); +} + +void dell_privacy_unregister_driver(void) +{ + wmi_driver_unregister(&dell_privacy_wmi_driver); +} diff --git a/drivers/platform/x86/dell/dell-wmi-privacy.h b/drivers/platform/x86/dell/dell-wmi-privacy.h new file mode 100644 index 000000000000..50c9b943dd47 --- /dev/null +++ b/drivers/platform/x86/dell/dell-wmi-privacy.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Dell privacy notification driver + * + * Copyright (C) 2021 Dell Inc. All Rights Reserved. + */ + +#ifndef _DELL_PRIVACY_WMI_H_ +#define _DELL_PRIVACY_WMI_H_ + +#if IS_ENABLED(CONFIG_DELL_WMI_PRIVACY) +bool dell_privacy_has_mic_mute(void); +bool dell_privacy_process_event(int type, int code, int status); +int dell_privacy_register_driver(void); +void dell_privacy_unregister_driver(void); +#else /* CONFIG_DELL_PRIVACY */ +static inline bool dell_privacy_has_mic_mute(void) +{ + return false; +} + +static inline bool dell_privacy_process_event(int type, int code, int status) +{ + return false; +} + +static inline int dell_privacy_register_driver(void) +{ + return 0; +} + +static inline void dell_privacy_unregister_driver(void) +{ +} +#endif /* CONFIG_DELL_PRIVACY */ +#endif diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h b/drivers/platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h index b80f2a62ea3f..3ad33a094588 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h +++ b/drivers/platform/x86/dell/dell-wmi-sysman/dell-wmi-sysman.h @@ -152,12 +152,15 @@ static ssize_t curr_val##_store(struct kobject *kobj, \ return ret ? ret : count; \ } +#define check_property_type(attr, prop, valuetype) \ + (attr##_obj[prop].type != valuetype) + union acpi_object *get_wmiobj_pointer(int instance_id, const char *guid_string); int get_instance_count(const char *guid_string); void strlcpy_attr(char *dest, char *src); int populate_enum_data(union acpi_object *enumeration_obj, int instance_id, - struct kobject *attr_name_kobj); + struct kobject *attr_name_kobj, u32 enum_property_count); int alloc_enum_data(void); void exit_enum_attributes(void); diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c index 091e48c217ed..8cc212c85266 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c @@ -132,39 +132,68 @@ int alloc_enum_data(void) * @enumeration_obj: ACPI object with enumeration data * @instance_id: The instance to enumerate * @attr_name_kobj: The parent kernel object + * @enum_property_count: Total properties count under enumeration type */ int populate_enum_data(union acpi_object *enumeration_obj, int instance_id, - struct kobject *attr_name_kobj) + struct kobject *attr_name_kobj, u32 enum_property_count) { int i, next_obj, value_modifier_count, possible_values_count; wmi_priv.enumeration_data[instance_id].attr_name_kobj = attr_name_kobj; + if (check_property_type(enumeration, ATTR_NAME, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.enumeration_data[instance_id].attribute_name, enumeration_obj[ATTR_NAME].string.pointer); + if (check_property_type(enumeration, DISPL_NAME_LANG_CODE, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.enumeration_data[instance_id].display_name_language_code, enumeration_obj[DISPL_NAME_LANG_CODE].string.pointer); + if (check_property_type(enumeration, DISPLAY_NAME, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.enumeration_data[instance_id].display_name, enumeration_obj[DISPLAY_NAME].string.pointer); + if (check_property_type(enumeration, DEFAULT_VAL, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.enumeration_data[instance_id].default_value, enumeration_obj[DEFAULT_VAL].string.pointer); + if (check_property_type(enumeration, MODIFIER, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.enumeration_data[instance_id].dell_modifier, enumeration_obj[MODIFIER].string.pointer); next_obj = MODIFIER + 1; - value_modifier_count = (uintptr_t)enumeration_obj[next_obj].string.pointer; + if (next_obj >= enum_property_count) + return -EINVAL; + + if (check_property_type(enumeration, next_obj, ACPI_TYPE_INTEGER)) + return -EINVAL; + value_modifier_count = (uintptr_t)enumeration_obj[next_obj++].string.pointer; for (i = 0; i < value_modifier_count; i++) { + if (next_obj >= enum_property_count) + return -EINVAL; + if (check_property_type(enumeration, next_obj, ACPI_TYPE_STRING)) + return -EINVAL; strcat(wmi_priv.enumeration_data[instance_id].dell_value_modifier, - enumeration_obj[++next_obj].string.pointer); + enumeration_obj[next_obj++].string.pointer); strcat(wmi_priv.enumeration_data[instance_id].dell_value_modifier, ";"); } - possible_values_count = (uintptr_t) enumeration_obj[++next_obj].string.pointer; + if (next_obj >= enum_property_count) + return -EINVAL; + + if (check_property_type(enumeration, next_obj, ACPI_TYPE_INTEGER)) + return -EINVAL; + possible_values_count = (uintptr_t) enumeration_obj[next_obj++].string.pointer; for (i = 0; i < possible_values_count; i++) { + if (next_obj >= enum_property_count) + return -EINVAL; + if (check_property_type(enumeration, next_obj, ACPI_TYPE_STRING)) + return -EINVAL; strcat(wmi_priv.enumeration_data[instance_id].possible_values, - enumeration_obj[++next_obj].string.pointer); + enumeration_obj[next_obj++].string.pointer); strcat(wmi_priv.enumeration_data[instance_id].possible_values, ";"); } diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c index 8a49ba6e44f9..951e75b538fa 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c @@ -141,20 +141,36 @@ int populate_int_data(union acpi_object *integer_obj, int instance_id, struct kobject *attr_name_kobj) { wmi_priv.integer_data[instance_id].attr_name_kobj = attr_name_kobj; + if (check_property_type(integer, ATTR_NAME, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.integer_data[instance_id].attribute_name, integer_obj[ATTR_NAME].string.pointer); + if (check_property_type(integer, DISPL_NAME_LANG_CODE, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.integer_data[instance_id].display_name_language_code, integer_obj[DISPL_NAME_LANG_CODE].string.pointer); + if (check_property_type(integer, DISPLAY_NAME, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.integer_data[instance_id].display_name, integer_obj[DISPLAY_NAME].string.pointer); + if (check_property_type(integer, DEFAULT_VAL, ACPI_TYPE_INTEGER)) + return -EINVAL; wmi_priv.integer_data[instance_id].default_value = (uintptr_t)integer_obj[DEFAULT_VAL].string.pointer; + if (check_property_type(integer, MODIFIER, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.integer_data[instance_id].dell_modifier, integer_obj[MODIFIER].string.pointer); + if (check_property_type(integer, MIN_VALUE, ACPI_TYPE_INTEGER)) + return -EINVAL; wmi_priv.integer_data[instance_id].min_value = (uintptr_t)integer_obj[MIN_VALUE].string.pointer; + if (check_property_type(integer, MAX_VALUE, ACPI_TYPE_INTEGER)) + return -EINVAL; wmi_priv.integer_data[instance_id].max_value = (uintptr_t)integer_obj[MAX_VALUE].string.pointer; + if (check_property_type(integer, SCALAR_INCR, ACPI_TYPE_INTEGER)) + return -EINVAL; wmi_priv.integer_data[instance_id].scalar_increment = (uintptr_t)integer_obj[SCALAR_INCR].string.pointer; diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c index 834b3e82ad9f..230e6ee96636 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c @@ -159,10 +159,16 @@ int alloc_po_data(void) int populate_po_data(union acpi_object *po_obj, int instance_id, struct kobject *attr_name_kobj) { wmi_priv.po_data[instance_id].attr_name_kobj = attr_name_kobj; + if (check_property_type(po, ATTR_NAME, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.po_data[instance_id].attribute_name, po_obj[ATTR_NAME].string.pointer); + if (check_property_type(po, MIN_PASS_LEN, ACPI_TYPE_INTEGER)) + return -EINVAL; wmi_priv.po_data[instance_id].min_password_length = (uintptr_t)po_obj[MIN_PASS_LEN].string.pointer; + if (check_property_type(po, MAX_PASS_LEN, ACPI_TYPE_INTEGER)) + return -EINVAL; wmi_priv.po_data[instance_id].max_password_length = (uintptr_t) po_obj[MAX_PASS_LEN].string.pointer; diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c b/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c index 339a082d6c18..86ec962aace9 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/passwordattr-interface.c @@ -95,9 +95,9 @@ int set_new_password(const char *password_type, const char *new) print_hex_dump_bytes("set new password data: ", DUMP_PREFIX_NONE, buffer, buffer_size); ret = call_password_interface(wmi_priv.password_attr_wdev, buffer, buffer_size); - /* clear current_password here and use user input from wmi_priv.current_password */ + /* on success copy the new password to current password */ if (!ret) - memset(current_password, 0, MAX_BUFF); + strscpy(current_password, new, MAX_BUFF); /* explain to user the detailed failure reason */ else if (ret == -EOPNOTSUPP) dev_err(&wmi_priv.password_attr_wdev->dev, "admin password must be configured\n"); diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c index 552537852459..c392f0ecf8b5 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c @@ -118,24 +118,38 @@ int alloc_str_data(void) /** * populate_str_data() - Populate all properties of an instance under string attribute - * @str_obj: ACPI object with integer data + * @str_obj: ACPI object with string data * @instance_id: The instance to enumerate * @attr_name_kobj: The parent kernel object */ int populate_str_data(union acpi_object *str_obj, int instance_id, struct kobject *attr_name_kobj) { wmi_priv.str_data[instance_id].attr_name_kobj = attr_name_kobj; + if (check_property_type(str, ATTR_NAME, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.str_data[instance_id].attribute_name, str_obj[ATTR_NAME].string.pointer); + if (check_property_type(str, DISPL_NAME_LANG_CODE, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.str_data[instance_id].display_name_language_code, str_obj[DISPL_NAME_LANG_CODE].string.pointer); + if (check_property_type(str, DISPLAY_NAME, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.str_data[instance_id].display_name, str_obj[DISPLAY_NAME].string.pointer); + if (check_property_type(str, DEFAULT_VAL, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.str_data[instance_id].default_value, str_obj[DEFAULT_VAL].string.pointer); + if (check_property_type(str, MODIFIER, ACPI_TYPE_STRING)) + return -EINVAL; strlcpy_attr(wmi_priv.str_data[instance_id].dell_modifier, str_obj[MODIFIER].string.pointer); + if (check_property_type(str, MIN_LEN, ACPI_TYPE_INTEGER)) + return -EINVAL; wmi_priv.str_data[instance_id].min_length = (uintptr_t)str_obj[MIN_LEN].string.pointer; + if (check_property_type(str, MAX_LEN, ACPI_TYPE_INTEGER)) + return -EINVAL; wmi_priv.str_data[instance_id].max_length = (uintptr_t) str_obj[MAX_LEN].string.pointer; return sysfs_create_group(attr_name_kobj, &str_attr_group); diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c index c8d276d78e92..636bdfa83284 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c @@ -13,14 +13,11 @@ #include #include #include "dell-wmi-sysman.h" +#include "../../firmware_attributes_class.h" #define MAX_TYPES 4 #include -static struct class firmware_attributes_class = { - .name = "firmware-attributes", -}; - struct wmi_sysman_priv wmi_priv = { .mutex = __MUTEX_INITIALIZER(wmi_priv.mutex), }; @@ -28,6 +25,7 @@ struct wmi_sysman_priv wmi_priv = { /* reset bios to defaults */ static const char * const reset_types[] = {"builtinsafe", "lastknowngood", "factory", "custom"}; static int reset_option = -1; +static struct class *fw_attr_class; /** @@ -481,7 +479,8 @@ static int init_bios_attributes(int attr_type, const char *guid) /* enumerate all of this attribute */ switch (attr_type) { case ENUM: - retval = populate_enum_data(elements, instance_id, attr_name_kobj); + retval = populate_enum_data(elements, instance_id, attr_name_kobj, + obj->package.count); break; case INT: retval = populate_int_data(elements, instance_id, attr_name_kobj); @@ -541,11 +540,11 @@ static int __init sysman_init(void) goto err_exit_bios_attr_pass_interface; } - ret = class_register(&firmware_attributes_class); + ret = fw_attributes_class_get(&fw_attr_class); if (ret) goto err_exit_bios_attr_pass_interface; - wmi_priv.class_dev = device_create(&firmware_attributes_class, NULL, MKDEV(0, 0), + wmi_priv.class_dev = device_create(fw_attr_class, NULL, MKDEV(0, 0), NULL, "%s", DRIVER_NAME); if (IS_ERR(wmi_priv.class_dev)) { ret = PTR_ERR(wmi_priv.class_dev); @@ -602,10 +601,10 @@ err_release_attributes_data: release_attributes_data(); err_destroy_classdev: - device_destroy(&firmware_attributes_class, MKDEV(0, 0)); + device_destroy(fw_attr_class, MKDEV(0, 0)); err_unregister_class: - class_unregister(&firmware_attributes_class); + fw_attributes_class_put(); err_exit_bios_attr_pass_interface: exit_bios_attr_pass_interface(); @@ -619,8 +618,8 @@ err_exit_bios_attr_set_interface: static void __exit sysman_exit(void) { release_attributes_data(); - device_destroy(&firmware_attributes_class, MKDEV(0, 0)); - class_unregister(&firmware_attributes_class); + device_destroy(fw_attr_class, MKDEV(0, 0)); + fw_attributes_class_put(); exit_bios_attr_set_interface(); exit_bios_attr_pass_interface(); } diff --git a/drivers/platform/x86/firmware_attributes_class.c b/drivers/platform/x86/firmware_attributes_class.c new file mode 100644 index 000000000000..fafe8eaf6e3e --- /dev/null +++ b/drivers/platform/x86/firmware_attributes_class.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +/* Firmware attributes class helper module */ + +#include +#include +#include +#include "firmware_attributes_class.h" + +static DEFINE_MUTEX(fw_attr_lock); +static int fw_attr_inuse; + +static struct class firmware_attributes_class = { + .name = "firmware-attributes", +}; + +int fw_attributes_class_get(struct class **fw_attr_class) +{ + int err; + + mutex_lock(&fw_attr_lock); + if (!fw_attr_inuse) { /*first time class is being used*/ + err = class_register(&firmware_attributes_class); + if (err) { + mutex_unlock(&fw_attr_lock); + return err; + } + } + fw_attr_inuse++; + *fw_attr_class = &firmware_attributes_class; + mutex_unlock(&fw_attr_lock); + return 0; +} +EXPORT_SYMBOL_GPL(fw_attributes_class_get); + +int fw_attributes_class_put(void) +{ + mutex_lock(&fw_attr_lock); + if (!fw_attr_inuse) { + mutex_unlock(&fw_attr_lock); + return -EINVAL; + } + fw_attr_inuse--; + if (!fw_attr_inuse) /* No more consumers */ + class_unregister(&firmware_attributes_class); + mutex_unlock(&fw_attr_lock); + return 0; +} +EXPORT_SYMBOL_GPL(fw_attributes_class_put); + +MODULE_AUTHOR("Mark Pearson "); +MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/firmware_attributes_class.h b/drivers/platform/x86/firmware_attributes_class.h new file mode 100644 index 000000000000..486485cb1f54 --- /dev/null +++ b/drivers/platform/x86/firmware_attributes_class.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Firmware attributes class helper module */ + +#ifndef FW_ATTR_CLASS_H +#define FW_ATTR_CLASS_H + +int fw_attributes_class_get(struct class **fw_attr_class); +int fw_attributes_class_put(void); + +#endif /* FW_ATTR_CLASS_H */ diff --git a/drivers/platform/x86/hdaps.c b/drivers/platform/x86/hdaps.c index a72270932ec3..9996485f5295 100644 --- a/drivers/platform/x86/hdaps.c +++ b/drivers/platform/x86/hdaps.c @@ -462,7 +462,7 @@ static struct attribute *hdaps_attributes[] = { NULL, }; -static struct attribute_group hdaps_attribute_group = { +static const struct attribute_group hdaps_attribute_group = { .attrs = hdaps_attributes, }; diff --git a/drivers/platform/x86/hp-wireless.c b/drivers/platform/x86/hp-wireless.c deleted file mode 100644 index 0753ef18e721..000000000000 --- a/drivers/platform/x86/hp-wireless.c +++ /dev/null @@ -1,102 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Airplane mode button for HP & Xiaomi laptops - * - * Copyright (C) 2014-2017 Alex Hung - */ - -#include -#include -#include -#include -#include -#include -#include - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Alex Hung"); -MODULE_ALIAS("acpi*:HPQ6001:*"); -MODULE_ALIAS("acpi*:WSTADEF:*"); -MODULE_ALIAS("acpi*:AMDI0051:*"); - -static struct input_dev *hpwl_input_dev; - -static const struct acpi_device_id hpwl_ids[] = { - {"HPQ6001", 0}, - {"WSTADEF", 0}, - {"AMDI0051", 0}, - {"", 0}, -}; - -static int hp_wireless_input_setup(void) -{ - int err; - - hpwl_input_dev = input_allocate_device(); - if (!hpwl_input_dev) - return -ENOMEM; - - hpwl_input_dev->name = "HP Wireless hotkeys"; - hpwl_input_dev->phys = "hpq6001/input0"; - hpwl_input_dev->id.bustype = BUS_HOST; - hpwl_input_dev->evbit[0] = BIT(EV_KEY); - set_bit(KEY_RFKILL, hpwl_input_dev->keybit); - - err = input_register_device(hpwl_input_dev); - if (err) - goto err_free_dev; - - return 0; - -err_free_dev: - input_free_device(hpwl_input_dev); - return err; -} - -static void hp_wireless_input_destroy(void) -{ - input_unregister_device(hpwl_input_dev); -} - -static void hpwl_notify(struct acpi_device *acpi_dev, u32 event) -{ - if (event != 0x80) { - pr_info("Received unknown event (0x%x)\n", event); - return; - } - - input_report_key(hpwl_input_dev, KEY_RFKILL, 1); - input_sync(hpwl_input_dev); - input_report_key(hpwl_input_dev, KEY_RFKILL, 0); - input_sync(hpwl_input_dev); -} - -static int hpwl_add(struct acpi_device *device) -{ - int err; - - err = hp_wireless_input_setup(); - if (err) - pr_err("Failed to setup hp wireless hotkeys\n"); - - return err; -} - -static int hpwl_remove(struct acpi_device *device) -{ - hp_wireless_input_destroy(); - return 0; -} - -static struct acpi_driver hpwl_driver = { - .name = "hp-wireless", - .owner = THIS_MODULE, - .ids = hpwl_ids, - .ops = { - .add = hpwl_add, - .remove = hpwl_remove, - .notify = hpwl_notify, - }, -}; - -module_acpi_driver(hpwl_driver); diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 387817290921..784326bd72f0 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1408,6 +1408,18 @@ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data) case 6: ideapad_input_report(priv, bit); break; + case 10: + /* + * This event gets send on a Yoga 300-11IBR when the EC + * believes that the device has changed between laptop/ + * tent/stand/tablet mode. The EC relies on getting + * angle info from 2 accelerometers through a special + * windows service calling a DSM on the DUAL250E ACPI- + * device. Linux does not do this, making the laptop/ + * tent/stand/tablet mode info unreliable, so we simply + * ignore these events. + */ + break; case 9: ideapad_sync_rfk_state(priv); break; diff --git a/drivers/platform/x86/intel/Kconfig b/drivers/platform/x86/intel/Kconfig new file mode 100644 index 000000000000..f2eef337eb98 --- /dev/null +++ b/drivers/platform/x86/intel/Kconfig @@ -0,0 +1,22 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Intel x86 Platform Specific Drivers +# + +menuconfig X86_PLATFORM_DRIVERS_INTEL + bool "Intel x86 Platform Specific Device Drivers" + default y + help + Say Y here to get to see options for device drivers for + various Intel x86 platforms, including vendor-specific + drivers. This option alone does not add any kernel code. + + If you say N, all options in this submenu will be skipped + and disabled. + +if X86_PLATFORM_DRIVERS_INTEL + +source "drivers/platform/x86/intel/int33fe/Kconfig" +source "drivers/platform/x86/intel/int3472/Kconfig" + +endif # X86_PLATFORM_DRIVERS_INTEL diff --git a/drivers/platform/x86/intel/Makefile b/drivers/platform/x86/intel/Makefile new file mode 100644 index 000000000000..0653055942d5 --- /dev/null +++ b/drivers/platform/x86/intel/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for drivers/platform/x86/intel +# Intel x86 Platform-Specific Drivers +# + +obj-$(CONFIG_INTEL_CHT_INT33FE) += int33fe/ +obj-$(CONFIG_INTEL_SKL_INT3472) += int3472/ diff --git a/drivers/platform/x86/intel/int33fe/Kconfig b/drivers/platform/x86/intel/int33fe/Kconfig new file mode 100644 index 000000000000..2f7329a2e399 --- /dev/null +++ b/drivers/platform/x86/intel/int33fe/Kconfig @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: GPL-2.0-only +config INTEL_CHT_INT33FE + tristate "Intel Cherry Trail ACPI INT33FE Driver" + depends on X86 && ACPI && I2C && REGULATOR + depends on CHARGER_BQ24190=y || (CHARGER_BQ24190=m && m) + depends on USB_ROLES_INTEL_XHCI=y || (USB_ROLES_INTEL_XHCI=m && m) + depends on TYPEC_MUX_PI3USB30532=y || (TYPEC_MUX_PI3USB30532=m && m) + help + This driver add support for the INT33FE ACPI device found on + some Intel Cherry Trail devices. + + There are two kinds of INT33FE ACPI device possible: for hardware + with USB Type-C and Micro-B connectors. This driver supports both. + + The INT33FE ACPI device has a CRS table with I2cSerialBusV2 + resources for Fuel Gauge Controller and (in the Type-C variant) + FUSB302 USB Type-C Controller and PI3USB30532 USB switch. + This driver instantiates i2c-clients for these, so that standard + i2c drivers for these chips can bind to the them. + + If you enable this driver it is advised to also select + CONFIG_BATTERY_BQ27XXX=m or CONFIG_BATTERY_BQ27XXX_I2C=m for Micro-B + device and CONFIG_TYPEC_FUSB302=m and CONFIG_BATTERY_MAX17042=m + for Type-C device. diff --git a/drivers/platform/x86/intel/int33fe/Makefile b/drivers/platform/x86/intel/int33fe/Makefile new file mode 100644 index 000000000000..cc11183ce179 --- /dev/null +++ b/drivers/platform/x86/intel/int33fe/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_INTEL_CHT_INT33FE) += intel_cht_int33fe.o +intel_cht_int33fe-objs := intel_cht_int33fe_common.o \ + intel_cht_int33fe_typec.o \ + intel_cht_int33fe_microb.o diff --git a/drivers/platform/x86/intel_cht_int33fe_common.c b/drivers/platform/x86/intel/int33fe/intel_cht_int33fe_common.c similarity index 100% rename from drivers/platform/x86/intel_cht_int33fe_common.c rename to drivers/platform/x86/intel/int33fe/intel_cht_int33fe_common.c diff --git a/drivers/platform/x86/intel_cht_int33fe_common.h b/drivers/platform/x86/intel/int33fe/intel_cht_int33fe_common.h similarity index 100% rename from drivers/platform/x86/intel_cht_int33fe_common.h rename to drivers/platform/x86/intel/int33fe/intel_cht_int33fe_common.h diff --git a/drivers/platform/x86/intel_cht_int33fe_microb.c b/drivers/platform/x86/intel/int33fe/intel_cht_int33fe_microb.c similarity index 100% rename from drivers/platform/x86/intel_cht_int33fe_microb.c rename to drivers/platform/x86/intel/int33fe/intel_cht_int33fe_microb.c diff --git a/drivers/platform/x86/intel_cht_int33fe_typec.c b/drivers/platform/x86/intel/int33fe/intel_cht_int33fe_typec.c similarity index 99% rename from drivers/platform/x86/intel_cht_int33fe_typec.c rename to drivers/platform/x86/intel/int33fe/intel_cht_int33fe_typec.c index b61bad9cc8d2..d59544167430 100644 --- a/drivers/platform/x86/intel_cht_int33fe_typec.c +++ b/drivers/platform/x86/intel/int33fe/intel_cht_int33fe_typec.c @@ -168,8 +168,8 @@ static int cht_int33fe_setup_dp(struct cht_int33fe_data *data) return -ENODEV; } - /* Then the DP child device node */ - data->dp = device_get_named_child_node(&pdev->dev, "DD02"); + /* Then the DP-2 child device node */ + data->dp = device_get_named_child_node(&pdev->dev, "DD04"); pci_dev_put(pdev); if (!data->dp) return -ENODEV; diff --git a/drivers/platform/x86/intel/int3472/Kconfig b/drivers/platform/x86/intel/int3472/Kconfig new file mode 100644 index 000000000000..62e5d4cf9ee5 --- /dev/null +++ b/drivers/platform/x86/intel/int3472/Kconfig @@ -0,0 +1,30 @@ +config INTEL_SKL_INT3472 + tristate "Intel SkyLake ACPI INT3472 Driver" + depends on ACPI + depends on COMMON_CLK + depends on I2C + depends on GPIOLIB + depends on REGULATOR + select MFD_CORE + select REGMAP_I2C + help + This driver adds power controller support for the Intel SkyCam + devices found on the Intel SkyLake platforms. + + The INT3472 is a camera power controller, a logical device found on + Intel Skylake-based systems that can map to different hardware + devices depending on the platform. On machines designed for Chrome OS + it maps to a TPS68470 camera PMIC. On machines designed for Windows, + it maps to either a TP68470 camera PMIC, a uP6641Q sensor PMIC, or a + set of discrete GPIOs and power gates. + + If your device was designed for Chrome OS, this driver will provide + an ACPI OpRegion, which must be available before any of the devices + using it are probed. For this reason, you should select Y if your + device was designed for ChromeOS. For the same reason the + I2C_DESIGNWARE_PLATFORM option must be set to Y too. + + Say Y or M here if you have a SkyLake device designed for use + with Windows or ChromeOS. Say N here if you are not sure. + + The module will be named "intel-skl-int3472". diff --git a/drivers/platform/x86/intel/int3472/Makefile b/drivers/platform/x86/intel/int3472/Makefile new file mode 100644 index 000000000000..48bd97f0a04e --- /dev/null +++ b/drivers/platform/x86/intel/int3472/Makefile @@ -0,0 +1,5 @@ +obj-$(CONFIG_INTEL_SKL_INT3472) += intel_skl_int3472.o +intel_skl_int3472-objs := intel_skl_int3472_common.o \ + intel_skl_int3472_discrete.o \ + intel_skl_int3472_tps68470.o \ + intel_skl_int3472_clk_and_regulator.o diff --git a/drivers/platform/x86/intel/int3472/intel_skl_int3472_clk_and_regulator.c b/drivers/platform/x86/intel/int3472/intel_skl_int3472_clk_and_regulator.c new file mode 100644 index 000000000000..1700e7557a82 --- /dev/null +++ b/drivers/platform/x86/intel/int3472/intel_skl_int3472_clk_and_regulator.c @@ -0,0 +1,207 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Author: Dan Scally */ + +#include +#include +#include +#include +#include +#include +#include + +#include "intel_skl_int3472_common.h" + +/* + * The regulators have to have .ops to be valid, but the only ops we actually + * support are .enable and .disable which are handled via .ena_gpiod. Pass an + * empty struct to clear the check without lying about capabilities. + */ +static const struct regulator_ops int3472_gpio_regulator_ops; + +static int skl_int3472_clk_prepare(struct clk_hw *hw) +{ + struct int3472_gpio_clock *clk = to_int3472_clk(hw); + + gpiod_set_value_cansleep(clk->ena_gpio, 1); + gpiod_set_value_cansleep(clk->led_gpio, 1); + + return 0; +} + +static void skl_int3472_clk_unprepare(struct clk_hw *hw) +{ + struct int3472_gpio_clock *clk = to_int3472_clk(hw); + + gpiod_set_value_cansleep(clk->ena_gpio, 0); + gpiod_set_value_cansleep(clk->led_gpio, 0); +} + +static int skl_int3472_clk_enable(struct clk_hw *hw) +{ + /* + * We're just turning a GPIO on to enable the clock, which operation + * has the potential to sleep. Given .enable() cannot sleep, but + * .prepare() can, we toggle the GPIO in .prepare() instead. Thus, + * nothing to do here. + */ + return 0; +} + +static void skl_int3472_clk_disable(struct clk_hw *hw) +{ + /* Likewise, nothing to do here... */ +} + +static unsigned int skl_int3472_get_clk_frequency(struct int3472_discrete_device *int3472) +{ + union acpi_object *obj; + unsigned int freq; + + obj = skl_int3472_get_acpi_buffer(int3472->sensor, "SSDB"); + if (IS_ERR(obj)) + return 0; /* report rate as 0 on error */ + + if (obj->buffer.length < CIO2_SENSOR_SSDB_MCLKSPEED_OFFSET + sizeof(u32)) { + dev_err(int3472->dev, "The buffer is too small\n"); + kfree(obj); + return 0; + } + + freq = *(u32 *)(obj->buffer.pointer + CIO2_SENSOR_SSDB_MCLKSPEED_OFFSET); + + kfree(obj); + return freq; +} + +static unsigned long skl_int3472_clk_recalc_rate(struct clk_hw *hw, + unsigned long parent_rate) +{ + struct int3472_gpio_clock *clk = to_int3472_clk(hw); + + return clk->frequency; +} + +static const struct clk_ops skl_int3472_clock_ops = { + .prepare = skl_int3472_clk_prepare, + .unprepare = skl_int3472_clk_unprepare, + .enable = skl_int3472_clk_enable, + .disable = skl_int3472_clk_disable, + .recalc_rate = skl_int3472_clk_recalc_rate, +}; + +int skl_int3472_register_clock(struct int3472_discrete_device *int3472) +{ + struct clk_init_data init = { + .ops = &skl_int3472_clock_ops, + .flags = CLK_GET_RATE_NOCACHE, + }; + int ret; + + init.name = kasprintf(GFP_KERNEL, "%s-clk", + acpi_dev_name(int3472->adev)); + if (!init.name) + return -ENOMEM; + + int3472->clock.frequency = skl_int3472_get_clk_frequency(int3472); + + int3472->clock.clk_hw.init = &init; + int3472->clock.clk = clk_register(&int3472->adev->dev, + &int3472->clock.clk_hw); + if (IS_ERR(int3472->clock.clk)) { + ret = PTR_ERR(int3472->clock.clk); + goto out_free_init_name; + } + + int3472->clock.cl = clkdev_create(int3472->clock.clk, NULL, + int3472->sensor_name); + if (!int3472->clock.cl) { + ret = -ENOMEM; + goto err_unregister_clk; + } + + kfree(init.name); + return 0; + +err_unregister_clk: + clk_unregister(int3472->clock.clk); +out_free_init_name: + kfree(init.name); + + return ret; +} + +void skl_int3472_unregister_clock(struct int3472_discrete_device *int3472) +{ + clkdev_drop(int3472->clock.cl); + clk_unregister(int3472->clock.clk); +} + +int skl_int3472_register_regulator(struct int3472_discrete_device *int3472, + struct acpi_resource_gpio *agpio) +{ + const struct int3472_sensor_config *sensor_config; + char *path = agpio->resource_source.string_ptr; + struct regulator_consumer_supply supply_map; + struct regulator_init_data init_data = { }; + struct regulator_config cfg = { }; + int ret; + + sensor_config = int3472->sensor_config; + if (IS_ERR(sensor_config)) { + dev_err(int3472->dev, "No sensor module config\n"); + return PTR_ERR(sensor_config); + } + + if (!sensor_config->supply_map.supply) { + dev_err(int3472->dev, "No supply name defined\n"); + return -ENODEV; + } + + init_data.constraints.valid_ops_mask = REGULATOR_CHANGE_STATUS; + init_data.num_consumer_supplies = 1; + supply_map = sensor_config->supply_map; + supply_map.dev_name = int3472->sensor_name; + init_data.consumer_supplies = &supply_map; + + snprintf(int3472->regulator.regulator_name, + sizeof(int3472->regulator.regulator_name), "%s-regulator", + acpi_dev_name(int3472->adev)); + snprintf(int3472->regulator.supply_name, + GPIO_REGULATOR_SUPPLY_NAME_LENGTH, "supply-0"); + + int3472->regulator.rdesc = INT3472_REGULATOR( + int3472->regulator.regulator_name, + int3472->regulator.supply_name, + &int3472_gpio_regulator_ops); + + int3472->regulator.gpio = acpi_get_and_request_gpiod(path, agpio->pin_table[0], + "int3472,regulator"); + if (IS_ERR(int3472->regulator.gpio)) { + dev_err(int3472->dev, "Failed to get regulator GPIO line\n"); + return PTR_ERR(int3472->regulator.gpio); + } + + cfg.dev = &int3472->adev->dev; + cfg.init_data = &init_data; + cfg.ena_gpiod = int3472->regulator.gpio; + + int3472->regulator.rdev = regulator_register(&int3472->regulator.rdesc, + &cfg); + if (IS_ERR(int3472->regulator.rdev)) { + ret = PTR_ERR(int3472->regulator.rdev); + goto err_free_gpio; + } + + return 0; + +err_free_gpio: + gpiod_put(int3472->regulator.gpio); + + return ret; +} + +void skl_int3472_unregister_regulator(struct int3472_discrete_device *int3472) +{ + regulator_unregister(int3472->regulator.rdev); + gpiod_put(int3472->regulator.gpio); +} diff --git a/drivers/platform/x86/intel/int3472/intel_skl_int3472_common.c b/drivers/platform/x86/intel/int3472/intel_skl_int3472_common.c new file mode 100644 index 000000000000..497e74fba75f --- /dev/null +++ b/drivers/platform/x86/intel/int3472/intel_skl_int3472_common.c @@ -0,0 +1,106 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Author: Dan Scally */ + +#include +#include +#include +#include + +#include "intel_skl_int3472_common.h" + +union acpi_object *skl_int3472_get_acpi_buffer(struct acpi_device *adev, char *id) +{ + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + acpi_handle handle = adev->handle; + union acpi_object *obj; + acpi_status status; + + status = acpi_evaluate_object(handle, id, NULL, &buffer); + if (ACPI_FAILURE(status)) + return ERR_PTR(-ENODEV); + + obj = buffer.pointer; + if (!obj) + return ERR_PTR(-ENODEV); + + if (obj->type != ACPI_TYPE_BUFFER) { + acpi_handle_err(handle, "%s object is not an ACPI buffer\n", id); + kfree(obj); + return ERR_PTR(-EINVAL); + } + + return obj; +} + +int skl_int3472_fill_cldb(struct acpi_device *adev, struct int3472_cldb *cldb) +{ + union acpi_object *obj; + int ret; + + obj = skl_int3472_get_acpi_buffer(adev, "CLDB"); + if (IS_ERR(obj)) + return PTR_ERR(obj); + + if (obj->buffer.length > sizeof(*cldb)) { + acpi_handle_err(adev->handle, "The CLDB buffer is too large\n"); + ret = -EINVAL; + goto out_free_obj; + } + + memcpy(cldb, obj->buffer.pointer, obj->buffer.length); + ret = 0; + +out_free_obj: + kfree(obj); + return ret; +} + +static const struct acpi_device_id int3472_device_id[] = { + { "INT3472", 0 }, + { } +}; +MODULE_DEVICE_TABLE(acpi, int3472_device_id); + +static struct platform_driver int3472_discrete = { + .driver = { + .name = "int3472-discrete", + .acpi_match_table = int3472_device_id, + }, + .probe = skl_int3472_discrete_probe, + .remove = skl_int3472_discrete_remove, +}; + +static struct i2c_driver int3472_tps68470 = { + .driver = { + .name = "int3472-tps68470", + .acpi_match_table = int3472_device_id, + }, + .probe_new = skl_int3472_tps68470_probe, +}; + +static int skl_int3472_init(void) +{ + int ret; + + ret = platform_driver_register(&int3472_discrete); + if (ret) + return ret; + + ret = i2c_register_driver(THIS_MODULE, &int3472_tps68470); + if (ret) + platform_driver_unregister(&int3472_discrete); + + return ret; +} +module_init(skl_int3472_init); + +static void skl_int3472_exit(void) +{ + platform_driver_unregister(&int3472_discrete); + i2c_del_driver(&int3472_tps68470); +} +module_exit(skl_int3472_exit); + +MODULE_DESCRIPTION("Intel SkyLake INT3472 ACPI Device Driver"); +MODULE_AUTHOR("Daniel Scally "); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/platform/x86/intel/int3472/intel_skl_int3472_common.h b/drivers/platform/x86/intel/int3472/intel_skl_int3472_common.h new file mode 100644 index 000000000000..714fde73b524 --- /dev/null +++ b/drivers/platform/x86/intel/int3472/intel_skl_int3472_common.h @@ -0,0 +1,122 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Author: Dan Scally */ + +#ifndef _INTEL_SKL_INT3472_H +#define _INTEL_SKL_INT3472_H + +#include +#include +#include +#include +#include + +/* FIXME drop this once the I2C_DEV_NAME_FORMAT macro has been added to include/linux/i2c.h */ +#ifndef I2C_DEV_NAME_FORMAT +#define I2C_DEV_NAME_FORMAT "i2c-%s" +#endif + +/* PMIC GPIO Types */ +#define INT3472_GPIO_TYPE_RESET 0x00 +#define INT3472_GPIO_TYPE_POWERDOWN 0x01 +#define INT3472_GPIO_TYPE_POWER_ENABLE 0x0b +#define INT3472_GPIO_TYPE_CLK_ENABLE 0x0c +#define INT3472_GPIO_TYPE_PRIVACY_LED 0x0d + +#define INT3472_PDEV_MAX_NAME_LEN 23 +#define INT3472_MAX_SENSOR_GPIOS 3 + +#define GPIO_REGULATOR_NAME_LENGTH 21 +#define GPIO_REGULATOR_SUPPLY_NAME_LENGTH 9 + +#define CIO2_SENSOR_SSDB_MCLKSPEED_OFFSET 86 + +#define INT3472_REGULATOR(_name, _supply, _ops) \ + (const struct regulator_desc) { \ + .name = _name, \ + .supply_name = _supply, \ + .type = REGULATOR_VOLTAGE, \ + .ops = _ops, \ + .owner = THIS_MODULE, \ + } + +#define to_int3472_clk(hw) \ + container_of(hw, struct int3472_gpio_clock, clk_hw) + +#define to_int3472_device(clk) \ + container_of(clk, struct int3472_discrete_device, clock) + +struct acpi_device; +struct i2c_client; +struct platform_device; + +struct int3472_cldb { + u8 version; + /* + * control logic type + * 0: UNKNOWN + * 1: DISCRETE(CRD-D) + * 2: PMIC TPS68470 + * 3: PMIC uP6641 + */ + u8 control_logic_type; + u8 control_logic_id; + u8 sensor_card_sku; + u8 reserved[28]; +}; + +struct int3472_gpio_function_remap { + const char *documented; + const char *actual; +}; + +struct int3472_sensor_config { + const char *sensor_module_name; + struct regulator_consumer_supply supply_map; + const struct int3472_gpio_function_remap *function_maps; +}; + +struct int3472_discrete_device { + struct acpi_device *adev; + struct device *dev; + struct acpi_device *sensor; + const char *sensor_name; + + const struct int3472_sensor_config *sensor_config; + + struct int3472_gpio_regulator { + char regulator_name[GPIO_REGULATOR_NAME_LENGTH]; + char supply_name[GPIO_REGULATOR_SUPPLY_NAME_LENGTH]; + struct gpio_desc *gpio; + struct regulator_dev *rdev; + struct regulator_desc rdesc; + } regulator; + + struct int3472_gpio_clock { + struct clk *clk; + struct clk_hw clk_hw; + struct clk_lookup *cl; + struct gpio_desc *ena_gpio; + struct gpio_desc *led_gpio; + u32 frequency; + } clock; + + unsigned int ngpios; /* how many GPIOs have we seen */ + unsigned int n_sensor_gpios; /* how many have we mapped to sensor */ + struct gpiod_lookup_table gpios; +}; + +int skl_int3472_discrete_probe(struct platform_device *pdev); +int skl_int3472_discrete_remove(struct platform_device *pdev); +int skl_int3472_tps68470_probe(struct i2c_client *client); +union acpi_object *skl_int3472_get_acpi_buffer(struct acpi_device *adev, + char *id); +int skl_int3472_fill_cldb(struct acpi_device *adev, struct int3472_cldb *cldb); + +int skl_int3472_register_clock(struct int3472_discrete_device *int3472); +void skl_int3472_unregister_clock(struct int3472_discrete_device *int3472); + +int skl_int3472_register_regulator(struct int3472_discrete_device *int3472, + struct acpi_resource_gpio *agpio); +void skl_int3472_unregister_regulator(struct int3472_discrete_device *int3472); + +#endif diff --git a/drivers/platform/x86/intel/int3472/intel_skl_int3472_discrete.c b/drivers/platform/x86/intel/int3472/intel_skl_int3472_discrete.c new file mode 100644 index 000000000000..9fe0a2527e1c --- /dev/null +++ b/drivers/platform/x86/intel/int3472/intel_skl_int3472_discrete.c @@ -0,0 +1,413 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Author: Dan Scally */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "intel_skl_int3472_common.h" + +/* + * 79234640-9e10-4fea-a5c1-b5aa8b19756f + * This _DSM GUID returns information about the GPIO lines mapped to a + * discrete INT3472 device. Function number 1 returns a count of the GPIO + * lines that are mapped. Subsequent functions return 32 bit ints encoding + * information about the GPIO line, including its purpose. + */ +static const guid_t int3472_gpio_guid = + GUID_INIT(0x79234640, 0x9e10, 0x4fea, + 0xa5, 0xc1, 0xb5, 0xaa, 0x8b, 0x19, 0x75, 0x6f); + +/* + * 822ace8f-2814-4174-a56b-5f029fe079ee + * This _DSM GUID returns a string from the sensor device, which acts as a + * module identifier. + */ +static const guid_t cio2_sensor_module_guid = + GUID_INIT(0x822ace8f, 0x2814, 0x4174, + 0xa5, 0x6b, 0x5f, 0x02, 0x9f, 0xe0, 0x79, 0xee); + +/* + * Here follows platform specific mapping information that we can pass to + * the functions mapping resources to the sensors. Where the sensors have + * a power enable pin defined in DSDT we need to provide a supply name so + * the sensor drivers can find the regulator. The device name will be derived + * from the sensor's ACPI device within the code. Optionally, we can provide a + * NULL terminated array of function name mappings to deal with any platform + * specific deviations from the documented behaviour of GPIOs. + * + * Map a GPIO function name to NULL to prevent the driver from mapping that + * GPIO at all. + */ + +static const struct int3472_gpio_function_remap ov2680_gpio_function_remaps[] = { + { "reset", NULL }, + { "powerdown", "reset" }, + { } +}; + +static const struct int3472_sensor_config int3472_sensor_configs[] = { + /* Lenovo Miix 510-12ISK - OV2680, Front */ + { "GNDF140809R", { 0 }, ov2680_gpio_function_remaps }, + /* Lenovo Miix 510-12ISK - OV5648, Rear */ + { "GEFF150023R", REGULATOR_SUPPLY("avdd", NULL), NULL }, + /* Surface Go 1&2 - OV5693, Front */ + { "YHCU", REGULATOR_SUPPLY("avdd", NULL), NULL }, +}; + +static const struct int3472_sensor_config * +skl_int3472_get_sensor_module_config(struct int3472_discrete_device *int3472) +{ + union acpi_object *obj; + unsigned int i; + + obj = acpi_evaluate_dsm_typed(int3472->sensor->handle, + &cio2_sensor_module_guid, 0x00, + 0x01, NULL, ACPI_TYPE_STRING); + + if (!obj) { + dev_err(int3472->dev, + "Failed to get sensor module string from _DSM\n"); + return ERR_PTR(-ENODEV); + } + + if (obj->string.type != ACPI_TYPE_STRING) { + dev_err(int3472->dev, + "Sensor _DSM returned a non-string value\n"); + + ACPI_FREE(obj); + return ERR_PTR(-EINVAL); + } + + for (i = 0; i < ARRAY_SIZE(int3472_sensor_configs); i++) { + if (!strcmp(int3472_sensor_configs[i].sensor_module_name, + obj->string.pointer)) + break; + } + + ACPI_FREE(obj); + + if (i >= ARRAY_SIZE(int3472_sensor_configs)) + return ERR_PTR(-EINVAL); + + return &int3472_sensor_configs[i]; +} + +static int skl_int3472_map_gpio_to_sensor(struct int3472_discrete_device *int3472, + struct acpi_resource_gpio *agpio, + const char *func, u32 polarity) +{ + const struct int3472_sensor_config *sensor_config; + char *path = agpio->resource_source.string_ptr; + struct gpiod_lookup *table_entry; + struct acpi_device *adev; + acpi_handle handle; + acpi_status status; + int ret; + + if (int3472->n_sensor_gpios >= INT3472_MAX_SENSOR_GPIOS) { + dev_warn(int3472->dev, "Too many GPIOs mapped\n"); + return -EINVAL; + } + + sensor_config = int3472->sensor_config; + if (!IS_ERR(sensor_config) && sensor_config->function_maps) { + const struct int3472_gpio_function_remap *remap; + + for (remap = sensor_config->function_maps; remap->documented; remap++) { + if (!strcmp(func, remap->documented)) { + func = remap->actual; + break; + } + } + } + + /* Functions mapped to NULL should not be mapped to the sensor */ + if (!func) + return 0; + + status = acpi_get_handle(NULL, path, &handle); + if (ACPI_FAILURE(status)) + return -EINVAL; + + ret = acpi_bus_get_device(handle, &adev); + if (ret) + return -ENODEV; + + table_entry = &int3472->gpios.table[int3472->n_sensor_gpios]; + table_entry->key = acpi_dev_name(adev); + table_entry->chip_hwnum = agpio->pin_table[0]; + table_entry->con_id = func; + table_entry->idx = 0; + table_entry->flags = polarity; + + int3472->n_sensor_gpios++; + + return 0; +} + +static int skl_int3472_map_gpio_to_clk(struct int3472_discrete_device *int3472, + struct acpi_resource_gpio *agpio, u8 type) +{ + char *path = agpio->resource_source.string_ptr; + u16 pin = agpio->pin_table[0]; + struct gpio_desc *gpio; + + switch (type) { + case INT3472_GPIO_TYPE_CLK_ENABLE: + gpio = acpi_get_and_request_gpiod(path, pin, "int3472,clk-enable"); + if (IS_ERR(gpio)) + return (PTR_ERR(gpio)); + + int3472->clock.ena_gpio = gpio; + break; + case INT3472_GPIO_TYPE_PRIVACY_LED: + gpio = acpi_get_and_request_gpiod(path, pin, "int3472,privacy-led"); + if (IS_ERR(gpio)) + return (PTR_ERR(gpio)); + + int3472->clock.led_gpio = gpio; + break; + default: + dev_err(int3472->dev, "Invalid GPIO type 0x%02x for clock\n", type); + break; + } + + return 0; +} + +/** + * skl_int3472_handle_gpio_resources: Map PMIC resources to consuming sensor + * @ares: A pointer to a &struct acpi_resource + * @data: A pointer to a &struct int3472_discrete_device + * + * This function handles GPIO resources that are against an INT3472 + * ACPI device, by checking the value of the corresponding _DSM entry. + * This will return a 32bit int, where the lowest byte represents the + * function of the GPIO pin: + * + * 0x00 Reset + * 0x01 Power down + * 0x0b Power enable + * 0x0c Clock enable + * 0x0d Privacy LED + * + * There are some known platform specific quirks where that does not quite + * hold up; for example where a pin with type 0x01 (Power down) is mapped to + * a sensor pin that performs a reset function or entries in _CRS and _DSM that + * do not actually correspond to a physical connection. These will be handled + * by the mapping sub-functions. + * + * GPIOs will either be mapped directly to the sensor device or else used + * to create clocks and regulators via the usual frameworks. + * + * Return: + * * 1 - To continue the loop + * * 0 - When all resources found are handled properly. + * * -EINVAL - If the resource is not a GPIO IO resource + * * -ENODEV - If the resource has no corresponding _DSM entry + * * -Other - Errors propagated from one of the sub-functions. + */ +static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares, + void *data) +{ + struct int3472_discrete_device *int3472 = data; + struct acpi_resource_gpio *agpio; + union acpi_object *obj; + const char *err_msg; + int ret; + u8 type; + + if (!acpi_gpio_get_io_resource(ares, &agpio)) + return 1; + + /* + * ngpios + 2 because the index of this _DSM function is 1-based and + * the first function is just a count. + */ + obj = acpi_evaluate_dsm_typed(int3472->adev->handle, + &int3472_gpio_guid, 0x00, + int3472->ngpios + 2, + NULL, ACPI_TYPE_INTEGER); + + if (!obj) { + dev_warn(int3472->dev, "No _DSM entry for GPIO pin %u\n", + agpio->pin_table[0]); + return 1; + } + + type = obj->integer.value & 0xff; + + switch (type) { + case INT3472_GPIO_TYPE_RESET: + ret = skl_int3472_map_gpio_to_sensor(int3472, agpio, "reset", + GPIO_ACTIVE_LOW); + if (ret) + err_msg = "Failed to map reset pin to sensor\n"; + + break; + case INT3472_GPIO_TYPE_POWERDOWN: + ret = skl_int3472_map_gpio_to_sensor(int3472, agpio, "powerdown", + GPIO_ACTIVE_LOW); + if (ret) + err_msg = "Failed to map powerdown pin to sensor\n"; + + break; + case INT3472_GPIO_TYPE_CLK_ENABLE: + case INT3472_GPIO_TYPE_PRIVACY_LED: + ret = skl_int3472_map_gpio_to_clk(int3472, agpio, type); + if (ret) + err_msg = "Failed to map GPIO to clock\n"; + + break; + case INT3472_GPIO_TYPE_POWER_ENABLE: + ret = skl_int3472_register_regulator(int3472, agpio); + if (ret) + err_msg = "Failed to map regulator to sensor\n"; + + break; + default: + dev_warn(int3472->dev, + "GPIO type 0x%02x unknown; the sensor may not work\n", + type); + ret = 1; + break; + } + + int3472->ngpios++; + ACPI_FREE(obj); + + if (ret < 0) + return dev_err_probe(int3472->dev, ret, err_msg); + + return ret; +} + +static int skl_int3472_parse_crs(struct int3472_discrete_device *int3472) +{ + LIST_HEAD(resource_list); + int ret; + + /* + * No error check, because not having a sensor config is not necessarily + * a failure mode. + */ + int3472->sensor_config = skl_int3472_get_sensor_module_config(int3472); + + ret = acpi_dev_get_resources(int3472->adev, &resource_list, + skl_int3472_handle_gpio_resources, + int3472); + if (ret < 0) + return ret; + + acpi_dev_free_resource_list(&resource_list); + + /* + * If we find no clock enable GPIO pin then the privacy LED won't work. + * We've never seen that situation, but it's possible. Warn the user so + * it's clear what's happened. + */ + if (int3472->clock.ena_gpio) { + ret = skl_int3472_register_clock(int3472); + if (ret) + return ret; + } else { + if (int3472->clock.led_gpio) + dev_warn(int3472->dev, + "No clk GPIO. The privacy LED won't work\n"); + } + + int3472->gpios.dev_id = int3472->sensor_name; + gpiod_add_lookup_table(&int3472->gpios); + + return 0; +} + +int skl_int3472_discrete_probe(struct platform_device *pdev) +{ + struct acpi_device *adev = ACPI_COMPANION(&pdev->dev); + struct int3472_discrete_device *int3472; + struct int3472_cldb cldb; + int ret; + + ret = skl_int3472_fill_cldb(adev, &cldb); + if (ret) { + dev_err(&pdev->dev, "Couldn't fill CLDB structure\n"); + return ret; + } + + if (cldb.control_logic_type != 1) { + dev_err(&pdev->dev, "Unsupported control logic type %u\n", + cldb.control_logic_type); + return -EINVAL; + } + + /* Max num GPIOs we've seen plus a terminator */ + int3472 = devm_kzalloc(&pdev->dev, struct_size(int3472, gpios.table, + INT3472_MAX_SENSOR_GPIOS + 1), GFP_KERNEL); + if (!int3472) + return -ENOMEM; + + int3472->adev = adev; + int3472->dev = &pdev->dev; + platform_set_drvdata(pdev, int3472); + + int3472->sensor = acpi_dev_get_first_consumer_dev(adev); + if (!int3472->sensor) { + dev_err(&pdev->dev, "INT3472 seems to have no dependents.\n"); + return -ENODEV; + } + + int3472->sensor_name = devm_kasprintf(int3472->dev, GFP_KERNEL, + I2C_DEV_NAME_FORMAT, + acpi_dev_name(int3472->sensor)); + if (!int3472->sensor_name) { + ret = -ENOMEM; + goto err_put_sensor; + } + + /* + * Initialising this list means we can call gpiod_remove_lookup_table() + * in failure paths without issue. + */ + INIT_LIST_HEAD(&int3472->gpios.list); + + ret = skl_int3472_parse_crs(int3472); + if (ret) { + skl_int3472_discrete_remove(pdev); + return ret; + } + + return 0; + +err_put_sensor: + acpi_dev_put(int3472->sensor); + + return ret; +} + +int skl_int3472_discrete_remove(struct platform_device *pdev) +{ + struct int3472_discrete_device *int3472 = platform_get_drvdata(pdev); + + gpiod_remove_lookup_table(&int3472->gpios); + + if (int3472->clock.ena_gpio) + skl_int3472_unregister_clock(int3472); + + gpiod_put(int3472->clock.ena_gpio); + gpiod_put(int3472->clock.led_gpio); + + skl_int3472_unregister_regulator(int3472); + + return 0; +} diff --git a/drivers/platform/x86/intel/int3472/intel_skl_int3472_tps68470.c b/drivers/platform/x86/intel/int3472/intel_skl_int3472_tps68470.c new file mode 100644 index 000000000000..c05b4cf502fe --- /dev/null +++ b/drivers/platform/x86/intel/int3472/intel_skl_int3472_tps68470.c @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Author: Dan Scally */ + +#include +#include +#include +#include +#include + +#include "intel_skl_int3472_common.h" + +#define DESIGNED_FOR_CHROMEOS 1 +#define DESIGNED_FOR_WINDOWS 2 + +static const struct mfd_cell tps68470_cros[] = { + { .name = "tps68470-gpio" }, + { .name = "tps68470_pmic_opregion" }, +}; + +static const struct mfd_cell tps68470_win[] = { + { .name = "tps68470-gpio" }, + { .name = "tps68470-clk" }, + { .name = "tps68470-regulator" }, +}; + +static const struct regmap_config tps68470_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = TPS68470_REG_MAX, +}; + +static int tps68470_chip_init(struct device *dev, struct regmap *regmap) +{ + unsigned int version; + int ret; + + /* Force software reset */ + ret = regmap_write(regmap, TPS68470_REG_RESET, TPS68470_REG_RESET_MASK); + if (ret) + return ret; + + ret = regmap_read(regmap, TPS68470_REG_REVID, &version); + if (ret) { + dev_err(dev, "Failed to read revision register: %d\n", ret); + return ret; + } + + dev_info(dev, "TPS68470 REVID: 0x%02x\n", version); + + return 0; +} + +/** skl_int3472_tps68470_calc_type: Check what platform a device is designed for + * @adev: A pointer to a &struct acpi_device + * + * Check CLDB buffer against the PMIC's adev. If present, then we check + * the value of control_logic_type field and follow one of the + * following scenarios: + * + * 1. No CLDB - likely ACPI tables designed for ChromeOS. We + * create platform devices for the GPIOs and OpRegion drivers. + * + * 2. CLDB, with control_logic_type = 2 - probably ACPI tables + * made for Windows 2-in-1 platforms. Register pdevs for GPIO, + * Clock and Regulator drivers to bind to. + * + * 3. Any other value in control_logic_type, we should never have + * gotten to this point; fail probe and return. + * + * Return: + * * 1 Device intended for ChromeOS + * * 2 Device intended for Windows + * * -EINVAL Where @adev has an object named CLDB but it does not conform to + * our expectations + */ +static int skl_int3472_tps68470_calc_type(struct acpi_device *adev) +{ + struct int3472_cldb cldb = { 0 }; + int ret; + + /* + * A CLDB buffer that exists, but which does not match our expectations + * should trigger an error so we don't blindly continue. + */ + ret = skl_int3472_fill_cldb(adev, &cldb); + if (ret && ret != -ENODEV) + return ret; + + if (ret) + return DESIGNED_FOR_CHROMEOS; + + if (cldb.control_logic_type != 2) + return -EINVAL; + + return DESIGNED_FOR_WINDOWS; +} + +int skl_int3472_tps68470_probe(struct i2c_client *client) +{ + struct acpi_device *adev = ACPI_COMPANION(&client->dev); + struct regmap *regmap; + int device_type; + int ret; + + regmap = devm_regmap_init_i2c(client, &tps68470_regmap_config); + if (IS_ERR(regmap)) { + dev_err(&client->dev, "Failed to create regmap: %ld\n", PTR_ERR(regmap)); + return PTR_ERR(regmap); + } + + i2c_set_clientdata(client, regmap); + + ret = tps68470_chip_init(&client->dev, regmap); + if (ret < 0) { + dev_err(&client->dev, "TPS68470 init error %d\n", ret); + return ret; + } + + device_type = skl_int3472_tps68470_calc_type(adev); + switch (device_type) { + case DESIGNED_FOR_WINDOWS: + ret = devm_mfd_add_devices(&client->dev, PLATFORM_DEVID_NONE, + tps68470_win, ARRAY_SIZE(tps68470_win), + NULL, 0, NULL); + break; + case DESIGNED_FOR_CHROMEOS: + ret = devm_mfd_add_devices(&client->dev, PLATFORM_DEVID_NONE, + tps68470_cros, ARRAY_SIZE(tps68470_cros), + NULL, 0, NULL); + break; + default: + dev_err(&client->dev, "Failed to add MFD devices\n"); + return device_type; + } + + return ret; +} diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c index bffe548187ee..4dfdbfca6841 100644 --- a/drivers/platform/x86/intel_ips.c +++ b/drivers/platform/x86/intel_ips.c @@ -829,7 +829,7 @@ static u16 calc_avg_temp(struct ips_driver *ips, u16 *array) static u16 read_mgtv(struct ips_driver *ips) { - u16 ret; + u16 __maybe_unused ret; u64 slope, offset; u64 val; diff --git a/drivers/platform/x86/intel_pmt_crashlog.c b/drivers/platform/x86/intel_pmt_crashlog.c index 92d315a16cfd..56963ceb6345 100644 --- a/drivers/platform/x86/intel_pmt_crashlog.c +++ b/drivers/platform/x86/intel_pmt_crashlog.c @@ -218,7 +218,7 @@ static struct attribute *pmt_crashlog_attrs[] = { NULL }; -static struct attribute_group pmt_crashlog_group = { +static const struct attribute_group pmt_crashlog_group = { .attrs = pmt_crashlog_attrs, }; diff --git a/drivers/platform/x86/intel_speed_select_if/isst_if_common.c b/drivers/platform/x86/intel_speed_select_if/isst_if_common.c index 0c2aa22c7a12..6f0cc679c8e5 100644 --- a/drivers/platform/x86/intel_speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel_speed_select_if/isst_if_common.c @@ -281,10 +281,69 @@ static int isst_if_get_platform_info(void __user *argp) struct isst_if_cpu_info { /* For BUS 0 and BUS 1 only, which we need for PUNIT interface */ int bus_info[2]; + struct pci_dev *pci_dev[2]; int punit_cpu_id; + int numa_node; }; static struct isst_if_cpu_info *isst_cpu_info; +#define ISST_MAX_PCI_DOMAINS 8 + +static struct pci_dev *_isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn) +{ + struct pci_dev *matched_pci_dev = NULL; + struct pci_dev *pci_dev = NULL; + int no_matches = 0; + int i, bus_number; + + if (bus_no < 0 || bus_no > 1 || cpu < 0 || cpu >= nr_cpu_ids || + cpu >= num_possible_cpus()) + return NULL; + + bus_number = isst_cpu_info[cpu].bus_info[bus_no]; + if (bus_number < 0) + return NULL; + + for (i = 0; i < ISST_MAX_PCI_DOMAINS; ++i) { + struct pci_dev *_pci_dev; + int node; + + _pci_dev = pci_get_domain_bus_and_slot(i, bus_number, PCI_DEVFN(dev, fn)); + if (!_pci_dev) + continue; + + ++no_matches; + if (!matched_pci_dev) + matched_pci_dev = _pci_dev; + + node = dev_to_node(&_pci_dev->dev); + if (node == NUMA_NO_NODE) { + pr_info("Fail to get numa node for CPU:%d bus:%d dev:%d fn:%d\n", + cpu, bus_no, dev, fn); + continue; + } + + if (node == isst_cpu_info[cpu].numa_node) { + pci_dev = _pci_dev; + break; + } + } + + /* + * If there is no numa matched pci_dev, then there can be following cases: + * 1. CONFIG_NUMA is not defined: In this case if there is only single device + * match, then we don't need numa information. Simply return last match. + * Othewise return NULL. + * 2. NUMA information is not exposed via _SEG method. In this case it is similar + * to case 1. + * 3. Numa information doesn't match with CPU numa node and more than one match + * return NULL. + */ + if (!pci_dev && no_matches == 1) + pci_dev = matched_pci_dev; + + return pci_dev; +} /** * isst_if_get_pci_dev() - Get the PCI device instance for a CPU @@ -300,17 +359,18 @@ static struct isst_if_cpu_info *isst_cpu_info; */ struct pci_dev *isst_if_get_pci_dev(int cpu, int bus_no, int dev, int fn) { - int bus_number; + struct pci_dev *pci_dev; if (bus_no < 0 || bus_no > 1 || cpu < 0 || cpu >= nr_cpu_ids || cpu >= num_possible_cpus()) return NULL; - bus_number = isst_cpu_info[cpu].bus_info[bus_no]; - if (bus_number < 0) - return NULL; + pci_dev = isst_cpu_info[cpu].pci_dev[bus_no]; - return pci_get_domain_bus_and_slot(0, bus_number, PCI_DEVFN(dev, fn)); + if (pci_dev && pci_dev->devfn == PCI_DEVFN(dev, fn)) + return pci_dev; + + return _isst_if_get_pci_dev(cpu, bus_no, dev, fn); } EXPORT_SYMBOL_GPL(isst_if_get_pci_dev); @@ -327,6 +387,8 @@ static int isst_if_cpu_online(unsigned int cpu) } else { isst_cpu_info[cpu].bus_info[0] = data & 0xff; isst_cpu_info[cpu].bus_info[1] = (data >> 8) & 0xff; + isst_cpu_info[cpu].pci_dev[0] = _isst_if_get_pci_dev(cpu, 0, 0, 1); + isst_cpu_info[cpu].pci_dev[1] = _isst_if_get_pci_dev(cpu, 1, 30, 1); } ret = rdmsrl_safe(MSR_THREAD_ID_INFO, &data); @@ -335,6 +397,7 @@ static int isst_if_cpu_online(unsigned int cpu) return ret; } isst_cpu_info[cpu].punit_cpu_id = data; + isst_cpu_info[cpu].numa_node = cpu_to_node(cpu); isst_restore_msr_local(cpu); diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c index d5cec6e35bb8..7ee010aa740a 100644 --- a/drivers/platform/x86/samsung-laptop.c +++ b/drivers/platform/x86/samsung-laptop.c @@ -388,7 +388,7 @@ MODULE_PARM_DESC(force, "Disable the DMI check and forces the driver to be loaded"); static bool debug; -module_param(debug, bool, S_IRUGO | S_IWUSR); +module_param(debug, bool, 0644); MODULE_PARM_DESC(debug, "Debug enabled or not"); static int sabi_command(struct samsung_laptop *samsung, u16 command, @@ -705,7 +705,7 @@ static ssize_t set_performance_level(struct device *dev, return count; } -static DEVICE_ATTR(performance_level, S_IWUSR | S_IRUGO, +static DEVICE_ATTR(performance_level, 0644, get_performance_level, set_performance_level); static int read_battery_life_extender(struct samsung_laptop *samsung) @@ -774,7 +774,7 @@ static ssize_t set_battery_life_extender(struct device *dev, return count; } -static DEVICE_ATTR(battery_life_extender, S_IWUSR | S_IRUGO, +static DEVICE_ATTR(battery_life_extender, 0644, get_battery_life_extender, set_battery_life_extender); static int read_usb_charge(struct samsung_laptop *samsung) @@ -843,7 +843,7 @@ static ssize_t set_usb_charge(struct device *dev, return count; } -static DEVICE_ATTR(usb_charge, S_IWUSR | S_IRUGO, +static DEVICE_ATTR(usb_charge, 0644, get_usb_charge, set_usb_charge); static int read_lid_handling(struct samsung_laptop *samsung) @@ -908,7 +908,7 @@ static ssize_t set_lid_handling(struct device *dev, return count; } -static DEVICE_ATTR(lid_handling, S_IWUSR | S_IRUGO, +static DEVICE_ATTR(lid_handling, 0644, get_lid_handling, set_lid_handling); static struct attribute *platform_attributes[] = { @@ -1291,24 +1291,17 @@ static void samsung_debugfs_init(struct samsung_laptop *samsung) samsung->debug.sdiag_wrapper.data = samsung->sdiag; samsung->debug.sdiag_wrapper.size = strlen(samsung->sdiag); - debugfs_create_u16("command", S_IRUGO | S_IWUSR, root, - &samsung->debug.command); - debugfs_create_u32("d0", S_IRUGO | S_IWUSR, root, - &samsung->debug.data.d0); - debugfs_create_u32("d1", S_IRUGO | S_IWUSR, root, - &samsung->debug.data.d1); - debugfs_create_u16("d2", S_IRUGO | S_IWUSR, root, - &samsung->debug.data.d2); - debugfs_create_u8("d3", S_IRUGO | S_IWUSR, root, - &samsung->debug.data.d3); - debugfs_create_blob("data", S_IRUGO | S_IWUSR, root, - &samsung->debug.data_wrapper); - debugfs_create_blob("f0000_segment", S_IRUSR | S_IWUSR, root, + debugfs_create_u16("command", 0644, root, &samsung->debug.command); + debugfs_create_u32("d0", 0644, root, &samsung->debug.data.d0); + debugfs_create_u32("d1", 0644, root, &samsung->debug.data.d1); + debugfs_create_u16("d2", 0644, root, &samsung->debug.data.d2); + debugfs_create_u8("d3", 0644, root, &samsung->debug.data.d3); + debugfs_create_blob("data", 0444, root, &samsung->debug.data_wrapper); + debugfs_create_blob("f0000_segment", 0400, root, &samsung->debug.f0000_wrapper); - debugfs_create_file("call", S_IFREG | S_IRUGO, root, samsung, + debugfs_create_file("call", 0444, root, samsung, &samsung_laptop_call_fops); - debugfs_create_blob("sdiag", S_IRUGO | S_IWUSR, root, - &samsung->debug.sdiag_wrapper); + debugfs_create_blob("sdiag", 0444, root, &samsung->debug.sdiag_wrapper); } static void samsung_sabi_exit(struct samsung_laptop *samsung) diff --git a/drivers/platform/x86/tc1100-wmi.c b/drivers/platform/x86/tc1100-wmi.c index 803920b6f01d..9072eb302618 100644 --- a/drivers/platform/x86/tc1100-wmi.c +++ b/drivers/platform/x86/tc1100-wmi.c @@ -156,7 +156,7 @@ static struct attribute *tc1100_attributes[] = { NULL }; -static struct attribute_group tc1100_attribute_group = { +static const struct attribute_group tc1100_attribute_group = { .attrs = tc1100_attributes, }; diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c new file mode 100644 index 000000000000..3671b5d20613 --- /dev/null +++ b/drivers/platform/x86/think-lmi.c @@ -0,0 +1,904 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Think LMI BIOS configuration driver + * + * Copyright(C) 2019-2021 Lenovo + * + * Original code from Thinkpad-wmi project https://github.com/iksaif/thinkpad-wmi + * Copyright(C) 2017 Corentin Chary + * Distributed under the GPL-2.0 license + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include "firmware_attributes_class.h" +#include "think-lmi.h" + +/* + * Name: + * Lenovo_BiosSetting + * Description: + * Get item name and settings for current LMI instance. + * Type: + * Query + * Returns: + * "Item,Value" + * Example: + * "WakeOnLAN,Enable" + */ +#define LENOVO_BIOS_SETTING_GUID "51F5230E-9677-46CD-A1CF-C0B23EE34DB7" + +/* + * Name: + * Lenovo_SetBiosSetting + * Description: + * Change the BIOS setting to the desired value using the Lenovo_SetBiosSetting + * class. To save the settings, use the Lenovo_SaveBiosSetting class. + * BIOS settings and values are case sensitive. + * After making changes to the BIOS settings, you must reboot the computer + * before the changes will take effect. + * Type: + * Method + * Arguments: + * "Item,Value,Password,Encoding,KbdLang;" + * Example: + * "WakeOnLAN,Disable,pa55w0rd,ascii,us;" + */ +#define LENOVO_SET_BIOS_SETTINGS_GUID "98479A64-33F5-4E33-A707-8E251EBBC3A1" + +/* + * Name: + * Lenovo_SaveBiosSettings + * Description: + * Save any pending changes in settings. + * Type: + * Method + * Arguments: + * "Password,Encoding,KbdLang;" + * Example: + * "pa55w0rd,ascii,us;" + */ +#define LENOVO_SAVE_BIOS_SETTINGS_GUID "6A4B54EF-A5ED-4D33-9455-B0D9B48DF4B3" + +/* + * Name: + * Lenovo_BiosPasswordSettings + * Description: + * Return BIOS Password settings + * Type: + * Query + * Returns: + * PasswordMode, PasswordState, MinLength, MaxLength, + * SupportedEncoding, SupportedKeyboard + */ +#define LENOVO_BIOS_PASSWORD_SETTINGS_GUID "8ADB159E-1E32-455C-BC93-308A7ED98246" + +/* + * Name: + * Lenovo_SetBiosPassword + * Description: + * Change a specific password. + * - BIOS settings cannot be changed at the same boot as power-on + * passwords (POP) and hard disk passwords (HDP). If you want to change + * BIOS settings and POP or HDP, you must reboot the system after changing + * one of them. + * - A password cannot be set using this method when one does not already + * exist. Passwords can only be updated or cleared. + * Type: + * Method + * Arguments: + * "PasswordType,CurrentPassword,NewPassword,Encoding,KbdLang;" + * Example: + * "pop,pa55w0rd,newpa55w0rd,ascii,us;” + */ +#define LENOVO_SET_BIOS_PASSWORD_GUID "2651D9FD-911C-4B69-B94E-D0DED5963BD7" + +/* + * Name: + * Lenovo_GetBiosSelections + * Description: + * Return a list of valid settings for a given item. + * Type: + * Method + * Arguments: + * "Item" + * Returns: + * "Value1,Value2,Value3,..." + * Example: + * -> "FlashOverLAN" + * <- "Enabled,Disabled" + */ +#define LENOVO_GET_BIOS_SELECTIONS_GUID "7364651A-132F-4FE7-ADAA-40C6C7EE2E3B" + +#define TLMI_POP_PWD (1 << 0) +#define TLMI_PAP_PWD (1 << 1) +#define to_tlmi_pwd_setting(kobj) container_of(kobj, struct tlmi_pwd_setting, kobj) +#define to_tlmi_attr_setting(kobj) container_of(kobj, struct tlmi_attr_setting, kobj) + +static const struct tlmi_err_codes tlmi_errs[] = { + {"Success", 0}, + {"Not Supported", -EOPNOTSUPP}, + {"Invalid Parameter", -EINVAL}, + {"Access Denied", -EACCES}, + {"System Busy", -EBUSY}, +}; + +static const char * const encoding_options[] = { + [TLMI_ENCODING_ASCII] = "ascii", + [TLMI_ENCODING_SCANCODE] = "scancode", +}; +static struct think_lmi tlmi_priv; +static struct class *fw_attr_class; + +/* ------ Utility functions ------------*/ +/* Convert BIOS WMI error string to suitable error code */ +static int tlmi_errstr_to_err(const char *errstr) +{ + int i; + + for (i = 0; i < sizeof(tlmi_errs)/sizeof(struct tlmi_err_codes); i++) { + if (!strcmp(tlmi_errs[i].err_str, errstr)) + return tlmi_errs[i].err_code; + } + return -EPERM; +} + +/* Extract error string from WMI return buffer */ +static int tlmi_extract_error(const struct acpi_buffer *output) +{ + const union acpi_object *obj; + + obj = output->pointer; + if (!obj) + return -ENOMEM; + if (obj->type != ACPI_TYPE_STRING || !obj->string.pointer) + return -EIO; + + return tlmi_errstr_to_err(obj->string.pointer); +} + +/* Utility function to execute WMI call to BIOS */ +static int tlmi_simple_call(const char *guid, const char *arg) +{ + const struct acpi_buffer input = { strlen(arg), (char *)arg }; + struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; + acpi_status status; + int i, err; + + /* + * Duplicated call required to match BIOS workaround for behavior + * seen when WMI accessed via scripting on other OS. + */ + for (i = 0; i < 2; i++) { + /* (re)initialize output buffer to default state */ + output.length = ACPI_ALLOCATE_BUFFER; + output.pointer = NULL; + + status = wmi_evaluate_method(guid, 0, 0, &input, &output); + if (ACPI_FAILURE(status)) { + kfree(output.pointer); + return -EIO; + } + err = tlmi_extract_error(&output); + kfree(output.pointer); + if (err) + return err; + } + return 0; +} + +/* Extract output string from WMI return buffer */ +static int tlmi_extract_output_string(const struct acpi_buffer *output, + char **string) +{ + const union acpi_object *obj; + char *s; + + obj = output->pointer; + if (!obj) + return -ENOMEM; + if (obj->type != ACPI_TYPE_STRING || !obj->string.pointer) + return -EIO; + + s = kstrdup(obj->string.pointer, GFP_KERNEL); + if (!s) + return -ENOMEM; + *string = s; + return 0; +} + +/* ------ Core interface functions ------------*/ + +/* Get password settings from BIOS */ +static int tlmi_get_pwd_settings(struct tlmi_pwdcfg *pwdcfg) +{ + struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; + const union acpi_object *obj; + acpi_status status; + + if (!tlmi_priv.can_get_password_settings) + return -EOPNOTSUPP; + + status = wmi_query_block(LENOVO_BIOS_PASSWORD_SETTINGS_GUID, 0, + &output); + if (ACPI_FAILURE(status)) + return -EIO; + + obj = output.pointer; + if (!obj) + return -ENOMEM; + if (obj->type != ACPI_TYPE_BUFFER || !obj->buffer.pointer) { + kfree(obj); + return -EIO; + } + /* + * The size of thinkpad_wmi_pcfg on ThinkStation is larger than ThinkPad. + * To make the driver compatible on different brands, we permit it to get + * the data in below case. + */ + if (obj->buffer.length < sizeof(struct tlmi_pwdcfg)) { + pr_warn("Unknown pwdcfg buffer length %d\n", obj->buffer.length); + kfree(obj); + return -EIO; + } + memcpy(pwdcfg, obj->buffer.pointer, sizeof(struct tlmi_pwdcfg)); + kfree(obj); + return 0; +} + +static int tlmi_save_bios_settings(const char *password) +{ + return tlmi_simple_call(LENOVO_SAVE_BIOS_SETTINGS_GUID, + password); +} + +static int tlmi_setting(int item, char **value, const char *guid_string) +{ + struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; + acpi_status status; + int ret; + + status = wmi_query_block(guid_string, item, &output); + if (ACPI_FAILURE(status)) { + kfree(output.pointer); + return -EIO; + } + + ret = tlmi_extract_output_string(&output, value); + kfree(output.pointer); + return ret; +} + +static int tlmi_get_bios_selections(const char *item, char **value) +{ + const struct acpi_buffer input = { strlen(item), (char *)item }; + struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; + acpi_status status; + int ret; + + status = wmi_evaluate_method(LENOVO_GET_BIOS_SELECTIONS_GUID, + 0, 0, &input, &output); + + if (ACPI_FAILURE(status)) { + kfree(output.pointer); + return -EIO; + } + + ret = tlmi_extract_output_string(&output, value); + kfree(output.pointer); + return ret; +} + +/* ---- Authentication sysfs --------------------------------------------------------- */ +static ssize_t is_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct tlmi_pwd_setting *setting = to_tlmi_pwd_setting(kobj); + + return sysfs_emit(buf, "%d\n", setting->valid); +} + +static struct kobj_attribute auth_is_pass_set = __ATTR_RO(is_enabled); + +static ssize_t current_password_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct tlmi_pwd_setting *setting = to_tlmi_pwd_setting(kobj); + size_t pwdlen; + char *p; + + pwdlen = strlen(buf); + /* pwdlen == 0 is allowed to clear the password */ + if (pwdlen && ((pwdlen < setting->minlen) || (pwdlen > setting->maxlen))) + return -EINVAL; + + strscpy(setting->password, buf, setting->maxlen); + /* Strip out CR if one is present, setting password won't work if it is present */ + p = strchrnul(setting->password, '\n'); + *p = '\0'; + return count; +} + +static struct kobj_attribute auth_current_password = __ATTR_WO(current_password); + +static ssize_t new_password_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct tlmi_pwd_setting *setting = to_tlmi_pwd_setting(kobj); + char *auth_str, *new_pwd, *p; + size_t pwdlen; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!tlmi_priv.can_set_bios_password) + return -EOPNOTSUPP; + + new_pwd = kstrdup(buf, GFP_KERNEL); + if (!new_pwd) + return -ENOMEM; + + /* Strip out CR if one is present, setting password won't work if it is present */ + p = strchrnul(new_pwd, '\n'); + *p = '\0'; + + pwdlen = strlen(new_pwd); + /* pwdlen == 0 is allowed to clear the password */ + if (pwdlen && ((pwdlen < setting->minlen) || (pwdlen > setting->maxlen))) { + ret = -EINVAL; + goto out; + } + + /* Format: 'PasswordType,CurrentPw,NewPw,Encoding,KbdLang;' */ + auth_str = kasprintf(GFP_KERNEL, "%s,%s,%s,%s,%s;", + setting->pwd_type, setting->password, new_pwd, + encoding_options[setting->encoding], setting->kbdlang); + if (!auth_str) { + ret = -ENOMEM; + goto out; + } + ret = tlmi_simple_call(LENOVO_SET_BIOS_PASSWORD_GUID, auth_str); + kfree(auth_str); +out: + kfree(new_pwd); + return ret ?: count; +} + +static struct kobj_attribute auth_new_password = __ATTR_WO(new_password); + +static ssize_t min_password_length_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct tlmi_pwd_setting *setting = to_tlmi_pwd_setting(kobj); + + return sysfs_emit(buf, "%d\n", setting->minlen); +} + +static struct kobj_attribute auth_min_pass_length = __ATTR_RO(min_password_length); + +static ssize_t max_password_length_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct tlmi_pwd_setting *setting = to_tlmi_pwd_setting(kobj); + + return sysfs_emit(buf, "%d\n", setting->maxlen); +} +static struct kobj_attribute auth_max_pass_length = __ATTR_RO(max_password_length); + +static ssize_t mechanism_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "password\n"); +} +static struct kobj_attribute auth_mechanism = __ATTR_RO(mechanism); + +static ssize_t encoding_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct tlmi_pwd_setting *setting = to_tlmi_pwd_setting(kobj); + + return sysfs_emit(buf, "%s\n", encoding_options[setting->encoding]); +} + +static ssize_t encoding_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct tlmi_pwd_setting *setting = to_tlmi_pwd_setting(kobj); + int i; + + /* Scan for a matching profile */ + i = sysfs_match_string(encoding_options, buf); + if (i < 0) + return -EINVAL; + + setting->encoding = i; + return count; +} + +static struct kobj_attribute auth_encoding = __ATTR_RW(encoding); + +static ssize_t kbdlang_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct tlmi_pwd_setting *setting = to_tlmi_pwd_setting(kobj); + + return sysfs_emit(buf, "%s\n", setting->kbdlang); +} + +static ssize_t kbdlang_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct tlmi_pwd_setting *setting = to_tlmi_pwd_setting(kobj); + int length; + + /* Calculate length till '\n' or terminating 0 */ + length = strchrnul(buf, '\n') - buf; + if (!length || length >= TLMI_LANG_MAXLEN) + return -EINVAL; + + memcpy(setting->kbdlang, buf, length); + setting->kbdlang[length] = '\0'; + return count; +} + +static struct kobj_attribute auth_kbdlang = __ATTR_RW(kbdlang); + +static ssize_t role_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct tlmi_pwd_setting *setting = to_tlmi_pwd_setting(kobj); + + return sysfs_emit(buf, "%s\n", setting->role); +} +static struct kobj_attribute auth_role = __ATTR_RO(role); + +static struct attribute *auth_attrs[] = { + &auth_is_pass_set.attr, + &auth_min_pass_length.attr, + &auth_max_pass_length.attr, + &auth_current_password.attr, + &auth_new_password.attr, + &auth_role.attr, + &auth_mechanism.attr, + &auth_encoding.attr, + &auth_kbdlang.attr, + NULL +}; + +static const struct attribute_group auth_attr_group = { + .attrs = auth_attrs, +}; + +/* ---- Attributes sysfs --------------------------------------------------------- */ +static ssize_t display_name_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct tlmi_attr_setting *setting = to_tlmi_attr_setting(kobj); + + return sysfs_emit(buf, "%s\n", setting->display_name); +} + +static ssize_t current_value_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + struct tlmi_attr_setting *setting = to_tlmi_attr_setting(kobj); + char *item, *value; + int ret; + + ret = tlmi_setting(setting->index, &item, LENOVO_BIOS_SETTING_GUID); + if (ret) + return ret; + + /* validate and split from `item,value` -> `value` */ + value = strpbrk(item, ","); + if (!value || value == item || !strlen(value + 1)) + return -EINVAL; + + ret = sysfs_emit(buf, "%s\n", value + 1); + kfree(item); + return ret; +} + +static ssize_t possible_values_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) +{ + struct tlmi_attr_setting *setting = to_tlmi_attr_setting(kobj); + + if (!tlmi_priv.can_get_bios_selections) + return -EOPNOTSUPP; + + return sysfs_emit(buf, "%s\n", setting->possible_values); +} + +static ssize_t current_value_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct tlmi_attr_setting *setting = to_tlmi_attr_setting(kobj); + char *set_str = NULL, *new_setting = NULL; + char *auth_str = NULL; + char *p; + int ret; + + if (!tlmi_priv.can_set_bios_settings) + return -EOPNOTSUPP; + + new_setting = kstrdup(buf, GFP_KERNEL); + if (!new_setting) + return -ENOMEM; + + /* Strip out CR if one is present */ + p = strchrnul(new_setting, '\n'); + *p = '\0'; + + if (tlmi_priv.pwd_admin->valid && tlmi_priv.pwd_admin->password[0]) { + auth_str = kasprintf(GFP_KERNEL, "%s,%s,%s;", + tlmi_priv.pwd_admin->password, + encoding_options[tlmi_priv.pwd_admin->encoding], + tlmi_priv.pwd_admin->kbdlang); + if (!auth_str) { + ret = -ENOMEM; + goto out; + } + } + + if (auth_str) + set_str = kasprintf(GFP_KERNEL, "%s,%s,%s", setting->display_name, + new_setting, auth_str); + else + set_str = kasprintf(GFP_KERNEL, "%s,%s;", setting->display_name, + new_setting); + if (!set_str) { + ret = -ENOMEM; + goto out; + } + + ret = tlmi_simple_call(LENOVO_SET_BIOS_SETTINGS_GUID, set_str); + if (ret) + goto out; + + if (auth_str) + ret = tlmi_save_bios_settings(auth_str); + else + ret = tlmi_save_bios_settings(""); + +out: + kfree(auth_str); + kfree(set_str); + kfree(new_setting); + return ret ?: count; +} + +static struct kobj_attribute attr_displ_name = __ATTR_RO(display_name); + +static struct kobj_attribute attr_possible_values = __ATTR_RO(possible_values); + +static struct kobj_attribute attr_current_val = __ATTR_RW_MODE(current_value, 0600); + +static struct attribute *tlmi_attrs[] = { + &attr_displ_name.attr, + &attr_current_val.attr, + &attr_possible_values.attr, + NULL +}; + +static const struct attribute_group tlmi_attr_group = { + .attrs = tlmi_attrs, +}; + +static ssize_t tlmi_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct kobj_attribute *kattr; + + kattr = container_of(attr, struct kobj_attribute, attr); + if (kattr->show) + return kattr->show(kobj, kattr, buf); + return -EIO; +} + +static ssize_t tlmi_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct kobj_attribute *kattr; + + kattr = container_of(attr, struct kobj_attribute, attr); + if (kattr->store) + return kattr->store(kobj, kattr, buf, count); + return -EIO; +} + +static const struct sysfs_ops tlmi_kobj_sysfs_ops = { + .show = tlmi_attr_show, + .store = tlmi_attr_store, +}; + +static void tlmi_attr_setting_release(struct kobject *kobj) +{ + struct tlmi_attr_setting *setting = to_tlmi_attr_setting(kobj); + + kfree(setting->possible_values); + kfree(setting); +} + +static void tlmi_pwd_setting_release(struct kobject *kobj) +{ + struct tlmi_pwd_setting *setting = to_tlmi_pwd_setting(kobj); + + kfree(setting); +} + +static struct kobj_type tlmi_attr_setting_ktype = { + .release = &tlmi_attr_setting_release, + .sysfs_ops = &tlmi_kobj_sysfs_ops, +}; + +static struct kobj_type tlmi_pwd_setting_ktype = { + .release = &tlmi_pwd_setting_release, + .sysfs_ops = &tlmi_kobj_sysfs_ops, +}; + +/* ---- Initialisation --------------------------------------------------------- */ +static void tlmi_release_attr(void) +{ + int i; + + /* Attribute structures */ + for (i = 0; i < TLMI_SETTINGS_COUNT; i++) { + if (tlmi_priv.setting[i]) { + sysfs_remove_group(&tlmi_priv.setting[i]->kobj, &tlmi_attr_group); + kobject_put(&tlmi_priv.setting[i]->kobj); + } + } + kset_unregister(tlmi_priv.attribute_kset); + + /* Authentication structures */ + sysfs_remove_group(&tlmi_priv.pwd_admin->kobj, &auth_attr_group); + kobject_put(&tlmi_priv.pwd_admin->kobj); + sysfs_remove_group(&tlmi_priv.pwd_power->kobj, &auth_attr_group); + kobject_put(&tlmi_priv.pwd_power->kobj); + kset_unregister(tlmi_priv.authentication_kset); +} + +static int tlmi_sysfs_init(void) +{ + int i, ret; + + ret = fw_attributes_class_get(&fw_attr_class); + if (ret) + return ret; + + tlmi_priv.class_dev = device_create(fw_attr_class, NULL, MKDEV(0, 0), + NULL, "%s", "thinklmi"); + if (IS_ERR(tlmi_priv.class_dev)) { + ret = PTR_ERR(tlmi_priv.class_dev); + goto fail_class_created; + } + + tlmi_priv.attribute_kset = kset_create_and_add("attributes", NULL, + &tlmi_priv.class_dev->kobj); + if (!tlmi_priv.attribute_kset) { + ret = -ENOMEM; + goto fail_device_created; + } + + for (i = 0; i < TLMI_SETTINGS_COUNT; i++) { + /* Check if index is a valid setting - skip if it isn't */ + if (!tlmi_priv.setting[i]) + continue; + + /* check for duplicate or reserved values */ + if (kset_find_obj(tlmi_priv.attribute_kset, tlmi_priv.setting[i]->display_name) || + !strcmp(tlmi_priv.setting[i]->display_name, "Reserved")) { + pr_debug("duplicate or reserved attribute name found - %s\n", + tlmi_priv.setting[i]->display_name); + kfree(tlmi_priv.setting[i]->possible_values); + kfree(tlmi_priv.setting[i]); + tlmi_priv.setting[i] = NULL; + continue; + } + + /* Build attribute */ + tlmi_priv.setting[i]->kobj.kset = tlmi_priv.attribute_kset; + ret = kobject_init_and_add(&tlmi_priv.setting[i]->kobj, &tlmi_attr_setting_ktype, + NULL, "%s", tlmi_priv.setting[i]->display_name); + if (ret) + goto fail_create_attr; + + ret = sysfs_create_group(&tlmi_priv.setting[i]->kobj, &tlmi_attr_group); + if (ret) + goto fail_create_attr; + } + + /* Create authentication entries */ + tlmi_priv.authentication_kset = kset_create_and_add("authentication", NULL, + &tlmi_priv.class_dev->kobj); + if (!tlmi_priv.authentication_kset) { + ret = -ENOMEM; + goto fail_create_attr; + } + tlmi_priv.pwd_admin->kobj.kset = tlmi_priv.authentication_kset; + ret = kobject_init_and_add(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype, + NULL, "%s", "Admin"); + if (ret) + goto fail_create_attr; + + ret = sysfs_create_group(&tlmi_priv.pwd_admin->kobj, &auth_attr_group); + if (ret) + goto fail_create_attr; + + tlmi_priv.pwd_power->kobj.kset = tlmi_priv.authentication_kset; + ret = kobject_init_and_add(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype, + NULL, "%s", "System"); + if (ret) + goto fail_create_attr; + + ret = sysfs_create_group(&tlmi_priv.pwd_power->kobj, &auth_attr_group); + if (ret) + goto fail_create_attr; + + return ret; + +fail_create_attr: + tlmi_release_attr(); +fail_device_created: + device_destroy(fw_attr_class, MKDEV(0, 0)); +fail_class_created: + fw_attributes_class_put(); + return ret; +} + +/* ---- Base Driver -------------------------------------------------------- */ +static int tlmi_analyze(void) +{ + struct tlmi_pwdcfg pwdcfg; + acpi_status status; + int i, ret; + + if (wmi_has_guid(LENOVO_SET_BIOS_SETTINGS_GUID) && + wmi_has_guid(LENOVO_SAVE_BIOS_SETTINGS_GUID)) + tlmi_priv.can_set_bios_settings = true; + + if (wmi_has_guid(LENOVO_GET_BIOS_SELECTIONS_GUID)) + tlmi_priv.can_get_bios_selections = true; + + if (wmi_has_guid(LENOVO_SET_BIOS_PASSWORD_GUID)) + tlmi_priv.can_set_bios_password = true; + + if (wmi_has_guid(LENOVO_BIOS_PASSWORD_SETTINGS_GUID)) + tlmi_priv.can_get_password_settings = true; + + /* + * Try to find the number of valid settings of this machine + * and use it to create sysfs attributes. + */ + for (i = 0; i < TLMI_SETTINGS_COUNT; ++i) { + struct tlmi_attr_setting *setting; + char *item = NULL; + char *p; + + tlmi_priv.setting[i] = NULL; + status = tlmi_setting(i, &item, LENOVO_BIOS_SETTING_GUID); + if (ACPI_FAILURE(status)) + break; + if (!item) + break; + if (!*item) + continue; + + /* It is not allowed to have '/' for file name. Convert it into '\'. */ + strreplace(item, '/', '\\'); + + /* Remove the value part */ + p = strchrnul(item, ','); + *p = '\0'; + + /* Create a setting entry */ + setting = kzalloc(sizeof(*setting), GFP_KERNEL); + if (!setting) { + ret = -ENOMEM; + goto fail_clear_attr; + } + setting->index = i; + strscpy(setting->display_name, item, TLMI_SETTINGS_MAXLEN); + /* If BIOS selections supported, load those */ + if (tlmi_priv.can_get_bios_selections) { + ret = tlmi_get_bios_selections(setting->display_name, + &setting->possible_values); + if (ret || !setting->possible_values) + pr_info("Error retrieving possible values for %d : %s\n", + i, setting->display_name); + } + tlmi_priv.setting[i] = setting; + tlmi_priv.settings_count++; + kfree(item); + } + + /* Create password setting structure */ + ret = tlmi_get_pwd_settings(&pwdcfg); + if (ret) + goto fail_clear_attr; + + tlmi_priv.pwd_admin = kzalloc(sizeof(struct tlmi_pwd_setting), GFP_KERNEL); + if (!tlmi_priv.pwd_admin) { + ret = -ENOMEM; + goto fail_clear_attr; + } + strscpy(tlmi_priv.pwd_admin->kbdlang, "us", TLMI_LANG_MAXLEN); + tlmi_priv.pwd_admin->encoding = TLMI_ENCODING_ASCII; + tlmi_priv.pwd_admin->pwd_type = "pap"; + tlmi_priv.pwd_admin->role = "bios-admin"; + tlmi_priv.pwd_admin->minlen = pwdcfg.min_length; + if (WARN_ON(pwdcfg.max_length >= TLMI_PWD_BUFSIZE)) + pwdcfg.max_length = TLMI_PWD_BUFSIZE - 1; + tlmi_priv.pwd_admin->maxlen = pwdcfg.max_length; + if (pwdcfg.password_state & TLMI_PAP_PWD) + tlmi_priv.pwd_admin->valid = true; + + tlmi_priv.pwd_power = kzalloc(sizeof(struct tlmi_pwd_setting), GFP_KERNEL); + if (!tlmi_priv.pwd_power) { + ret = -ENOMEM; + goto fail_clear_attr; + } + strscpy(tlmi_priv.pwd_power->kbdlang, "us", TLMI_LANG_MAXLEN); + tlmi_priv.pwd_power->encoding = TLMI_ENCODING_ASCII; + tlmi_priv.pwd_power->pwd_type = "pop"; + tlmi_priv.pwd_power->role = "power-on"; + tlmi_priv.pwd_power->minlen = pwdcfg.min_length; + tlmi_priv.pwd_power->maxlen = pwdcfg.max_length; + + if (pwdcfg.password_state & TLMI_POP_PWD) + tlmi_priv.pwd_power->valid = true; + + return 0; + +fail_clear_attr: + for (i = 0; i < TLMI_SETTINGS_COUNT; ++i) + kfree(tlmi_priv.setting[i]); + return ret; +} + +static void tlmi_remove(struct wmi_device *wdev) +{ + tlmi_release_attr(); + device_destroy(fw_attr_class, MKDEV(0, 0)); + fw_attributes_class_put(); +} + +static int tlmi_probe(struct wmi_device *wdev, const void *context) +{ + tlmi_analyze(); + return tlmi_sysfs_init(); +} + +static const struct wmi_device_id tlmi_id_table[] = { + { .guid_string = LENOVO_BIOS_SETTING_GUID }, + { } +}; +MODULE_DEVICE_TABLE(wmi, tlmi_id_table); + +static struct wmi_driver tlmi_driver = { + .driver = { + .name = "think-lmi", + }, + .id_table = tlmi_id_table, + .probe = tlmi_probe, + .remove = tlmi_remove, +}; + +MODULE_AUTHOR("Sugumaran L "); +MODULE_AUTHOR("Mark Pearson "); +MODULE_AUTHOR("Corentin Chary "); +MODULE_DESCRIPTION("ThinkLMI Driver"); +MODULE_LICENSE("GPL"); + +module_wmi_driver(tlmi_driver); diff --git a/drivers/platform/x86/think-lmi.h b/drivers/platform/x86/think-lmi.h new file mode 100644 index 000000000000..6fa8da7af6c7 --- /dev/null +++ b/drivers/platform/x86/think-lmi.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _THINK_LMI_H_ +#define _THINK_LMI_H_ + +#include + +#define TLMI_SETTINGS_COUNT 256 +#define TLMI_SETTINGS_MAXLEN 512 +#define TLMI_PWD_BUFSIZE 129 +#define TLMI_LANG_MAXLEN 4 + +/* Possible error values */ +struct tlmi_err_codes { + const char *err_str; + int err_code; +}; + +enum encoding_option { + TLMI_ENCODING_ASCII, + TLMI_ENCODING_SCANCODE, +}; + +/* password configuration details */ +struct tlmi_pwdcfg { + uint32_t password_mode; + uint32_t password_state; + uint32_t min_length; + uint32_t max_length; + uint32_t supported_encodings; + uint32_t supported_keyboard; +}; + +/* password setting details */ +struct tlmi_pwd_setting { + struct kobject kobj; + bool valid; + char password[TLMI_PWD_BUFSIZE]; + const char *pwd_type; + const char *role; + int minlen; + int maxlen; + enum encoding_option encoding; + char kbdlang[TLMI_LANG_MAXLEN]; +}; + +/* Attribute setting details */ +struct tlmi_attr_setting { + struct kobject kobj; + int index; + char display_name[TLMI_SETTINGS_MAXLEN]; + char *possible_values; +}; + +struct think_lmi { + struct wmi_device *wmi_device; + + int settings_count; + bool can_set_bios_settings; + bool can_get_bios_selections; + bool can_set_bios_password; + bool can_get_password_settings; + + struct tlmi_attr_setting *setting[TLMI_SETTINGS_COUNT]; + struct device *class_dev; + struct kset *attribute_kset; + struct kset *authentication_kset; + struct tlmi_pwd_setting *pwd_admin; + struct tlmi_pwd_setting *pwd_power; +}; + +#endif /* !_THINK_LMI_H_ */ diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index edd71e744d27..603156a6e3ed 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -7938,7 +7938,7 @@ static int volume_write(char *buf) continue; } else if (sscanf(cmd, "level %u", &l) == 1 && l >= 0 && l <= TP_EC_VOLUME_MAX) { - new_level = l; + new_level = l; continue; } } diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index fa7232ad8c39..352508d30467 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -2831,6 +2831,7 @@ static int toshiba_acpi_setup_keyboard(struct toshiba_acpi_dev *dev) if (!dev->info_supported && !dev->system_event_supported) { pr_warn("No hotkey query interface found\n"); + error = -EINVAL; goto err_remove_filter; } diff --git a/drivers/platform/x86/toshiba_haps.c b/drivers/platform/x86/toshiba_haps.c index b237bd6b1ee5..49e84095bb01 100644 --- a/drivers/platform/x86/toshiba_haps.c +++ b/drivers/platform/x86/toshiba_haps.c @@ -131,7 +131,7 @@ static const struct attribute_group haps_attr_group = { */ static void toshiba_haps_notify(struct acpi_device *device, u32 event) { - pr_debug("Received event: 0x%x", event); + pr_debug("Received event: 0x%x\n", event); acpi_bus_generate_netlink_event(device->pnp.device_class, dev_name(&device->dev), diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index bde740d6120e..0e1451b1d9c6 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -299,6 +299,35 @@ static const struct ts_dmi_data estar_beauty_hd_data = { .properties = estar_beauty_hd_props, }; +/* Generic props + data for upside-down mounted GDIX1001 touchscreens */ +static const struct property_entry gdix1001_upside_down_props[] = { + PROPERTY_ENTRY_BOOL("touchscreen-inverted-x"), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + { } +}; + +static const struct ts_dmi_data gdix1001_00_upside_down_data = { + .acpi_name = "GDIX1001:00", + .properties = gdix1001_upside_down_props, +}; + +static const struct ts_dmi_data gdix1001_01_upside_down_data = { + .acpi_name = "GDIX1001:01", + .properties = gdix1001_upside_down_props, +}; + +static const struct property_entry glavey_tm800a550l_props[] = { + PROPERTY_ENTRY_STRING("firmware-name", "gt912-glavey-tm800a550l.fw"), + PROPERTY_ENTRY_STRING("goodix,config-name", "gt912-glavey-tm800a550l.cfg"), + PROPERTY_ENTRY_U32("goodix,main-clk", 54), + { } +}; + +static const struct ts_dmi_data glavey_tm800a550l_data = { + .acpi_name = "GDIX1001:00", + .properties = glavey_tm800a550l_props, +}; + static const struct property_entry gp_electronic_t701_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 960), PROPERTY_ENTRY_U32("touchscreen-size-y", 640), @@ -942,7 +971,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { - /* Chuwi Hi10 Prus (CWI597) */ + /* Chuwi Hi10 Pro (CWI529) */ .driver_data = (void *)&chuwi_hi10_pro_data, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"), @@ -1038,6 +1067,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "eSTAR BEAUTY HD Intel Quad core"), }, }, + { /* Glavey TM800A550L */ + .driver_data = (void *)&glavey_tm800a550l_data, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), + DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"), + /* Above strings are too generic, also match on BIOS version */ + DMI_MATCH(DMI_BIOS_VERSION, "ZY-8-BI-PX4S70VTR400-X423B-005-D"), + }, + }, { /* GP-electronic T701 */ .driver_data = (void *)&gp_electronic_t701_data, @@ -1330,6 +1368,24 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_BOARD_NAME, "X3 Plus"), }, }, + { + /* Teclast X89 (Android version / BIOS) */ + .driver_data = (void *)&gdix1001_00_upside_down_data, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "WISKY"), + DMI_MATCH(DMI_BOARD_NAME, "3G062i"), + }, + }, + { + /* Teclast X89 (Windows version / BIOS) */ + .driver_data = (void *)&gdix1001_01_upside_down_data, + .matches = { + /* tPAD is too generic, also match on bios date */ + DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"), + DMI_MATCH(DMI_BOARD_NAME, "tPAD"), + DMI_MATCH(DMI_BIOS_DATE, "12/19/2014"), + }, + }, { /* Teclast X98 Plus II */ .driver_data = (void *)&teclast_x98plus2_data, @@ -1338,6 +1394,19 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "X98 Plus II"), }, }, + { + /* Teclast X98 Pro */ + .driver_data = (void *)&gdix1001_00_upside_down_data, + .matches = { + /* + * Only match BIOS date, because the manufacturers + * BIOS does not report the board name at all + * (sometimes)... + */ + DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"), + DMI_MATCH(DMI_BIOS_DATE, "10/28/2015"), + }, + }, { /* Trekstor Primebook C11 */ .driver_data = (void *)&trekstor_primebook_c11_data, @@ -1413,6 +1482,22 @@ const struct dmi_system_id touchscreen_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "VINGA Twizzle J116"), }, }, + { + /* "WinBook TW100" */ + .driver_data = (void *)&gdix1001_00_upside_down_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "WinBook"), + DMI_MATCH(DMI_PRODUCT_NAME, "TW100") + } + }, + { + /* WinBook TW700 */ + .driver_data = (void *)&gdix1001_00_upside_down_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "WinBook"), + DMI_MATCH(DMI_PRODUCT_NAME, "TW700") + }, + }, { /* Yours Y8W81, same case and touchscreen as Chuwi Vi8 */ .driver_data = (void *)&chuwi_vi8_data, diff --git a/drivers/platform/x86/uv_sysfs.c b/drivers/platform/x86/uv_sysfs.c index 7badcfa3f384..956a354b57c1 100644 --- a/drivers/platform/x86/uv_sysfs.c +++ b/drivers/platform/x86/uv_sysfs.c @@ -778,7 +778,7 @@ static struct attribute *base_attrs[] = { NULL, }; -static struct attribute_group base_attr_group = { +static const struct attribute_group base_attr_group = { .attrs = base_attrs }; @@ -823,7 +823,7 @@ static struct attribute *hubless_base_attrs[] = { NULL, }; -static struct attribute_group hubless_base_attr_group = { +static const struct attribute_group hubless_base_attr_group = { .attrs = hubless_base_attrs }; diff --git a/drivers/platform/x86/wireless-hotkey.c b/drivers/platform/x86/wireless-hotkey.c new file mode 100644 index 000000000000..b010e4ca3383 --- /dev/null +++ b/drivers/platform/x86/wireless-hotkey.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Airplane mode button for AMD, HP & Xiaomi laptops + * + * Copyright (C) 2014-2017 Alex Hung + * Copyright (C) 2021 Advanced Micro Devices + */ + +#include +#include +#include +#include +#include +#include +#include + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Alex Hung"); +MODULE_ALIAS("acpi*:HPQ6001:*"); +MODULE_ALIAS("acpi*:WSTADEF:*"); +MODULE_ALIAS("acpi*:AMDI0051:*"); + +static struct input_dev *wl_input_dev; + +static const struct acpi_device_id wl_ids[] = { + {"HPQ6001", 0}, + {"WSTADEF", 0}, + {"AMDI0051", 0}, + {"", 0}, +}; + +static int wireless_input_setup(void) +{ + int err; + + wl_input_dev = input_allocate_device(); + if (!wl_input_dev) + return -ENOMEM; + + wl_input_dev->name = "Wireless hotkeys"; + wl_input_dev->phys = "hpq6001/input0"; + wl_input_dev->id.bustype = BUS_HOST; + wl_input_dev->evbit[0] = BIT(EV_KEY); + set_bit(KEY_RFKILL, wl_input_dev->keybit); + + err = input_register_device(wl_input_dev); + if (err) + goto err_free_dev; + + return 0; + +err_free_dev: + input_free_device(wl_input_dev); + return err; +} + +static void wireless_input_destroy(void) +{ + input_unregister_device(wl_input_dev); +} + +static void wl_notify(struct acpi_device *acpi_dev, u32 event) +{ + if (event != 0x80) { + pr_info("Received unknown event (0x%x)\n", event); + return; + } + + input_report_key(wl_input_dev, KEY_RFKILL, 1); + input_sync(wl_input_dev); + input_report_key(wl_input_dev, KEY_RFKILL, 0); + input_sync(wl_input_dev); +} + +static int wl_add(struct acpi_device *device) +{ + int err; + + err = wireless_input_setup(); + if (err) + pr_err("Failed to setup hp wireless hotkeys\n"); + + return err; +} + +static int wl_remove(struct acpi_device *device) +{ + wireless_input_destroy(); + return 0; +} + +static struct acpi_driver wl_driver = { + .name = "wireless-hotkey", + .owner = THIS_MODULE, + .ids = wl_ids, + .ops = { + .add = wl_add, + .remove = wl_remove, + .notify = wl_notify, + }, +}; + +module_acpi_driver(wl_driver); diff --git a/drivers/pnp/base.h b/drivers/pnp/base.h index cdcfa39cf167..e74a0f6a3157 100644 --- a/drivers/pnp/base.h +++ b/drivers/pnp/base.h @@ -6,7 +6,6 @@ extern struct mutex pnp_lock; extern const struct attribute_group *pnp_dev_groups[]; -void *pnp_alloc(long size); int pnp_register_protocol(struct pnp_protocol *protocol); void pnp_unregister_protocol(struct pnp_protocol *protocol); diff --git a/drivers/pnp/card.c b/drivers/pnp/card.c index c2464ee08e4a..d40ed8621571 100644 --- a/drivers/pnp/card.c +++ b/drivers/pnp/card.c @@ -80,7 +80,7 @@ static int card_probe(struct pnp_card *card, struct pnp_card_driver *drv) if (!id) return 0; - clink = pnp_alloc(sizeof(*clink)); + clink = kzalloc(sizeof(*clink), GFP_KERNEL); if (!clink) return 0; clink->card = card; @@ -181,8 +181,8 @@ struct pnp_card *pnp_alloc_card(struct pnp_protocol *protocol, int id, char *pnp return card; } -static ssize_t pnp_show_card_name(struct device *dmdev, - struct device_attribute *attr, char *buf) +static ssize_t name_show(struct device *dmdev, + struct device_attribute *attr, char *buf) { char *str = buf; struct pnp_card *card = to_pnp_card(dmdev); @@ -191,10 +191,10 @@ static ssize_t pnp_show_card_name(struct device *dmdev, return (str - buf); } -static DEVICE_ATTR(name, S_IRUGO, pnp_show_card_name, NULL); +static DEVICE_ATTR_RO(name); -static ssize_t pnp_show_card_ids(struct device *dmdev, - struct device_attribute *attr, char *buf) +static ssize_t card_id_show(struct device *dmdev, + struct device_attribute *attr, char *buf) { char *str = buf; struct pnp_card *card = to_pnp_card(dmdev); @@ -207,7 +207,7 @@ static ssize_t pnp_show_card_ids(struct device *dmdev, return (str - buf); } -static DEVICE_ATTR(card_id, S_IRUGO, pnp_show_card_ids, NULL); +static DEVICE_ATTR_RO(card_id); static int pnp_interface_attach_card(struct pnp_card *card) { diff --git a/drivers/pnp/core.c b/drivers/pnp/core.c index a50ab002e9e4..4df5aa6a309c 100644 --- a/drivers/pnp/core.c +++ b/drivers/pnp/core.c @@ -31,18 +31,6 @@ DEFINE_MUTEX(pnp_lock); int pnp_platform_devices; EXPORT_SYMBOL(pnp_platform_devices); -void *pnp_alloc(long size) -{ - void *result; - - result = kzalloc(size, GFP_KERNEL); - if (!result) { - printk(KERN_ERR "pnp: Out of Memory\n"); - return NULL; - } - return result; -} - static void pnp_remove_protocol(struct pnp_protocol *protocol) { mutex_lock(&pnp_lock); @@ -227,9 +215,8 @@ int pnp_add_device(struct pnp_dev *dev) for (id = dev->id; id; id = id->next) len += scnprintf(buf + len, sizeof(buf) - len, " %s", id->id); - dev_printk(KERN_DEBUG, &dev->dev, "%s device, IDs%s (%s)\n", - dev->protocol->name, buf, - dev->active ? "active" : "disabled"); + dev_dbg(&dev->dev, "%s device, IDs%s (%s)\n", dev->protocol->name, buf, + dev->active ? "active" : "disabled"); return 0; } diff --git a/drivers/pnp/interface.c b/drivers/pnp/interface.c index 602c46893e83..44efcdb87e6f 100644 --- a/drivers/pnp/interface.c +++ b/drivers/pnp/interface.c @@ -214,7 +214,7 @@ static ssize_t options_show(struct device *dmdev, struct device_attribute *attr, int ret, dep = 0, set = 0; char *indent; - buffer = pnp_alloc(sizeof(pnp_info_buffer_t)); + buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); if (!buffer) return -ENOMEM; @@ -257,7 +257,7 @@ static ssize_t resources_show(struct device *dmdev, if (!dev) return -EINVAL; - buffer = pnp_alloc(sizeof(pnp_info_buffer_t)); + buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); if (!buffer) return -ENOMEM; diff --git a/drivers/pnp/isapnp/proc.c b/drivers/pnp/isapnp/proc.c index 785a796430fa..1ae458c02656 100644 --- a/drivers/pnp/isapnp/proc.c +++ b/drivers/pnp/isapnp/proc.c @@ -57,21 +57,20 @@ static const struct proc_ops isapnp_proc_bus_proc_ops = { static int isapnp_proc_attach_device(struct pnp_dev *dev) { struct pnp_card *bus = dev->card; - struct proc_dir_entry *de, *e; char name[16]; - if (!(de = bus->procdir)) { + if (!bus->procdir) { sprintf(name, "%02x", bus->number); - de = bus->procdir = proc_mkdir(name, isapnp_proc_bus_dir); - if (!de) + bus->procdir = proc_mkdir(name, isapnp_proc_bus_dir); + if (!bus->procdir) return -ENOMEM; } sprintf(name, "%02x", dev->number); - e = dev->procent = proc_create_data(name, S_IFREG | S_IRUGO, de, + dev->procent = proc_create_data(name, S_IFREG | S_IRUGO, bus->procdir, &isapnp_proc_bus_proc_ops, dev); - if (!e) + if (!dev->procent) return -ENOMEM; - proc_set_size(e, 256); + proc_set_size(dev->procent, 256); return 0; } diff --git a/drivers/pnp/pnpbios/core.c b/drivers/pnp/pnpbios/core.c index 9b760e73ee8f..669ef4700c1a 100644 --- a/drivers/pnp/pnpbios/core.c +++ b/drivers/pnp/pnpbios/core.c @@ -298,14 +298,12 @@ struct pnp_protocol pnpbios_protocol = { static int __init insert_device(struct pnp_bios_node *node) { - struct list_head *pos; struct pnp_dev *dev; char id[8]; int error; /* check if the device is already added */ - list_for_each(pos, &pnpbios_protocol.devices) { - dev = list_entry(pos, struct pnp_dev, protocol_list); + list_for_each_entry(dev, &pnpbios_protocol.devices, protocol_list) { if (dev->number == node->handle) return -EEXIST; } diff --git a/drivers/pnp/resource.c b/drivers/pnp/resource.c index 70d4ba95735a..2fa0f7d55259 100644 --- a/drivers/pnp/resource.c +++ b/drivers/pnp/resource.c @@ -540,7 +540,7 @@ struct pnp_resource *pnp_add_irq_resource(struct pnp_dev *dev, int irq, res->start = irq; res->end = irq; - dev_printk(KERN_DEBUG, &dev->dev, "%pR\n", res); + dev_dbg(&dev->dev, "%pR\n", res); return pnp_res; } diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 21c4c34c52d8..a23a37a4d5dc 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -63,27 +63,6 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue, spin_unlock_irqrestore(&queue->lock, flags); } -long scaled_ppm_to_ppb(long ppm) -{ - /* - * The 'freq' field in the 'struct timex' is in parts per - * million, but with a 16 bit binary fractional field. - * - * We want to calculate - * - * ppb = scaled_ppm * 1000 / 2^16 - * - * which simplifies to - * - * ppb = scaled_ppm * 125 / 2^13 - */ - s64 ppb = 1 + ppm; - ppb *= 125; - ppb >>= 13; - return (long) ppb; -} -EXPORT_SYMBOL(scaled_ppm_to_ppb); - /* posix clock implementation */ static int ptp_clock_getres(struct posix_clock *pc, struct timespec64 *tp) @@ -239,6 +218,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, pr_err("failed to create ptp aux_worker %d\n", err); goto kworker_err; } + ptp->pps_source->lookup_cookie = ptp; } err = ptp_populate_pin_groups(ptp); diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c index 13bc78e5c1bc..c43fb9ec2fea 100644 --- a/drivers/rpmsg/rpmsg_core.c +++ b/drivers/rpmsg/rpmsg_core.c @@ -495,8 +495,10 @@ static int rpmsg_dev_match(struct device *dev, struct device_driver *drv) if (ids) for (i = 0; ids[i].name[0]; i++) - if (rpmsg_id_match(rpdev, &ids[i])) + if (rpmsg_id_match(rpdev, &ids[i])) { + rpdev->id.driver_data = ids[i].driver_data; return 1; + } return of_driver_match_device(dev, drv); } diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index 8d6587ec73e2..493e8469893c 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -109,9 +109,9 @@ int dasd_scan_partitions(struct dasd_block *block) return -ENODEV; } - mutex_lock(&bdev->bd_mutex); - rc = bdev_disk_changed(bdev, false); - mutex_unlock(&bdev->bd_mutex); + mutex_lock(&block->gdp->open_mutex); + rc = bdev_disk_changed(block->gdp, false); + mutex_unlock(&block->gdp->open_mutex); if (rc) DBF_DEV_EVENT(DBF_ERR, block->base, "scan partitions error, rc %d", rc); @@ -145,9 +145,9 @@ void dasd_destroy_partitions(struct dasd_block *block) bdev = block->bdev; block->bdev = NULL; - mutex_lock(&bdev->bd_mutex); - bdev_disk_changed(bdev, true); - mutex_unlock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); + bdev_disk_changed(bdev->bd_disk, true); + mutex_unlock(&bdev->bd_disk->open_mutex); /* Matching blkdev_put to the blkdev_get in dasd_scan_partitions. */ blkdev_put(bdev, FMODE_READ); diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index da33cb4cba28..7faa56399999 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -90,7 +90,6 @@ struct dcssblk_dev_info { int segment_type; unsigned char save_pending; unsigned char is_shared; - struct request_queue *dcssblk_queue; int num_of_segments; struct list_head seg_list; struct dax_device *dax_dev; @@ -429,9 +428,7 @@ removeseg: kill_dax(dev_info->dax_dev); put_dax(dev_info->dax_dev); del_gendisk(dev_info->gd); - blk_cleanup_queue(dev_info->dcssblk_queue); - dev_info->gd->queue = NULL; - put_disk(dev_info->gd); + blk_cleanup_disk(dev_info->gd); up_write(&dcssblk_devices_sem); if (device_remove_file_self(dev, attr)) { @@ -644,18 +641,17 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char dev_info->dev.release = dcssblk_release_segment; dev_info->dev.groups = dcssblk_dev_attr_groups; INIT_LIST_HEAD(&dev_info->lh); - dev_info->gd = alloc_disk(DCSSBLK_MINORS_PER_DISK); + dev_info->gd = blk_alloc_disk(NUMA_NO_NODE); if (dev_info->gd == NULL) { rc = -ENOMEM; goto seg_list_del; } dev_info->gd->major = dcssblk_major; + dev_info->gd->minors = DCSSBLK_MINORS_PER_DISK; dev_info->gd->fops = &dcssblk_devops; - dev_info->dcssblk_queue = blk_alloc_queue(NUMA_NO_NODE); - dev_info->gd->queue = dev_info->dcssblk_queue; dev_info->gd->private_data = dev_info; - blk_queue_logical_block_size(dev_info->dcssblk_queue, 4096); - blk_queue_flag_set(QUEUE_FLAG_DAX, dev_info->dcssblk_queue); + blk_queue_logical_block_size(dev_info->gd->queue, 4096); + blk_queue_flag_set(QUEUE_FLAG_DAX, dev_info->gd->queue); seg_byte_size = (dev_info->end - dev_info->start + 1); set_capacity(dev_info->gd, seg_byte_size >> 9); // size in sectors @@ -719,9 +715,7 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char put_dev: list_del(&dev_info->lh); - blk_cleanup_queue(dev_info->dcssblk_queue); - dev_info->gd->queue = NULL; - put_disk(dev_info->gd); + blk_cleanup_disk(dev_info->gd); list_for_each_entry(seg_info, &dev_info->seg_list, lh) { segment_unload(seg_info->segment_name); } @@ -731,9 +725,7 @@ put_dev: dev_list_del: list_del(&dev_info->lh); release_gd: - blk_cleanup_queue(dev_info->dcssblk_queue); - dev_info->gd->queue = NULL; - put_disk(dev_info->gd); + blk_cleanup_disk(dev_info->gd); up_write(&dcssblk_devices_sem); seg_list_del: if (dev_info == NULL) @@ -801,9 +793,7 @@ dcssblk_remove_store(struct device *dev, struct device_attribute *attr, const ch kill_dax(dev_info->dax_dev); put_dax(dev_info->dax_dev); del_gendisk(dev_info->gd); - blk_cleanup_queue(dev_info->dcssblk_queue); - dev_info->gd->queue = NULL; - put_disk(dev_info->gd); + blk_cleanup_disk(dev_info->gd); /* unload all related segments */ list_for_each_entry(entry, &dev_info->seg_list, lh) diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c index a4f6f2e62b1d..88cba6212ee2 100644 --- a/drivers/s390/block/scm_blk.c +++ b/drivers/s390/block/scm_blk.c @@ -462,12 +462,12 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) if (ret) goto out; - rq = blk_mq_init_queue(&bdev->tag_set); - if (IS_ERR(rq)) { - ret = PTR_ERR(rq); + bdev->gendisk = blk_mq_alloc_disk(&bdev->tag_set, scmdev); + if (IS_ERR(bdev->gendisk)) { + ret = PTR_ERR(bdev->gendisk); goto out_tag; } - bdev->rq = rq; + rq = bdev->rq = bdev->gendisk->queue; nr_max_blk = min(scmdev->nr_max_block, (unsigned int) (PAGE_SIZE / sizeof(struct aidaw))); @@ -477,17 +477,11 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) blk_queue_flag_set(QUEUE_FLAG_NONROT, rq); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, rq); - bdev->gendisk = alloc_disk(SCM_NR_PARTS); - if (!bdev->gendisk) { - ret = -ENOMEM; - goto out_queue; - } - rq->queuedata = scmdev; bdev->gendisk->private_data = scmdev; bdev->gendisk->fops = &scm_blk_devops; - bdev->gendisk->queue = rq; bdev->gendisk->major = scm_major; bdev->gendisk->first_minor = devindex * SCM_NR_PARTS; + bdev->gendisk->minors = SCM_NR_PARTS; len = snprintf(bdev->gendisk->disk_name, DISK_NAME_LEN, "scm"); if (devindex > 25) { @@ -504,8 +498,6 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev) device_add_disk(&scmdev->dev, bdev->gendisk, NULL); return 0; -out_queue: - blk_cleanup_queue(rq); out_tag: blk_mq_free_tag_set(&bdev->tag_set); out: @@ -516,9 +508,8 @@ out: void scm_blk_dev_cleanup(struct scm_blk_dev *bdev) { del_gendisk(bdev->gendisk); - blk_cleanup_queue(bdev->gendisk->queue); + blk_cleanup_disk(bdev->gendisk); blk_mq_free_tag_set(&bdev->tag_set); - put_disk(bdev->gendisk); } void scm_blk_set_available(struct scm_blk_dev *bdev) diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c index d1ed39162943..91ef710edfd2 100644 --- a/drivers/s390/block/xpram.c +++ b/drivers/s390/block/xpram.c @@ -56,7 +56,6 @@ typedef struct { static xpram_device_t xpram_devices[XPRAM_MAX_DEVS]; static unsigned int xpram_sizes[XPRAM_MAX_DEVS]; static struct gendisk *xpram_disks[XPRAM_MAX_DEVS]; -static struct request_queue *xpram_queues[XPRAM_MAX_DEVS]; static unsigned int xpram_pages; static int xpram_devs; @@ -341,17 +340,13 @@ static int __init xpram_setup_blkdev(void) int i, rc = -ENOMEM; for (i = 0; i < xpram_devs; i++) { - xpram_disks[i] = alloc_disk(1); + xpram_disks[i] = blk_alloc_disk(NUMA_NO_NODE); if (!xpram_disks[i]) goto out; - xpram_queues[i] = blk_alloc_queue(NUMA_NO_NODE); - if (!xpram_queues[i]) { - put_disk(xpram_disks[i]); - goto out; - } - blk_queue_flag_set(QUEUE_FLAG_NONROT, xpram_queues[i]); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, xpram_queues[i]); - blk_queue_logical_block_size(xpram_queues[i], 4096); + blk_queue_flag_set(QUEUE_FLAG_NONROT, xpram_disks[i]->queue); + blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, + xpram_disks[i]->queue); + blk_queue_logical_block_size(xpram_disks[i]->queue, 4096); } /* @@ -373,9 +368,9 @@ static int __init xpram_setup_blkdev(void) offset += xpram_devices[i].size; disk->major = XPRAM_MAJOR; disk->first_minor = i; + disk->minors = 1; disk->fops = &xpram_devops; disk->private_data = &xpram_devices[i]; - disk->queue = xpram_queues[i]; sprintf(disk->disk_name, "slram%d", i); set_capacity(disk, xpram_sizes[i] << 1); add_disk(disk); @@ -383,10 +378,8 @@ static int __init xpram_setup_blkdev(void) return 0; out: - while (i--) { - blk_cleanup_queue(xpram_queues[i]); - put_disk(xpram_disks[i]); - } + while (i--) + blk_cleanup_disk(xpram_disks[i]); return rc; } @@ -434,8 +427,7 @@ static void __exit xpram_exit(void) int i; for (i = 0; i < xpram_devs; i++) { del_gendisk(xpram_disks[i]); - blk_cleanup_queue(xpram_queues[i]); - put_disk(xpram_disks[i]); + blk_cleanup_disk(xpram_disks[i]); } unregister_blkdev(XPRAM_MAJOR, XPRAM_NAME); platform_device_unregister(xpram_pdev); diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c index 260860cf3aa1..5a0c2f07a3a2 100644 --- a/drivers/s390/net/netiucv.c +++ b/drivers/s390/net/netiucv.c @@ -118,24 +118,6 @@ static struct device_driver netiucv_driver = { .bus = &iucv_bus, }; -static int netiucv_callback_connreq(struct iucv_path *, u8 *, u8 *); -static void netiucv_callback_connack(struct iucv_path *, u8 *); -static void netiucv_callback_connrej(struct iucv_path *, u8 *); -static void netiucv_callback_connsusp(struct iucv_path *, u8 *); -static void netiucv_callback_connres(struct iucv_path *, u8 *); -static void netiucv_callback_rx(struct iucv_path *, struct iucv_message *); -static void netiucv_callback_txdone(struct iucv_path *, struct iucv_message *); - -static struct iucv_handler netiucv_handler = { - .path_pending = netiucv_callback_connreq, - .path_complete = netiucv_callback_connack, - .path_severed = netiucv_callback_connrej, - .path_quiesced = netiucv_callback_connsusp, - .path_resumed = netiucv_callback_connres, - .message_pending = netiucv_callback_rx, - .message_complete = netiucv_callback_txdone -}; - /** * Per connection profiling data */ @@ -774,6 +756,16 @@ static void conn_action_txdone(fsm_instance *fi, int event, void *arg) } } +static struct iucv_handler netiucv_handler = { + .path_pending = netiucv_callback_connreq, + .path_complete = netiucv_callback_connack, + .path_severed = netiucv_callback_connrej, + .path_quiesced = netiucv_callback_connsusp, + .path_resumed = netiucv_callback_connres, + .message_pending = netiucv_callback_rx, + .message_complete = netiucv_callback_txdone, +}; + static void conn_action_connaccept(fsm_instance *fi, int event, void *arg) { struct iucv_event *ev = arg; diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index fd9b869d278e..f4d554ea0c93 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -417,13 +417,17 @@ enum qeth_qdio_out_buffer_state { QETH_QDIO_BUF_EMPTY, /* Filled by driver; owned by hardware in order to be sent. */ QETH_QDIO_BUF_PRIMED, - /* Discovered by the TX completion code: */ - QETH_QDIO_BUF_PENDING, - /* Finished by the TX completion code: */ - QETH_QDIO_BUF_NEED_QAOB, - /* Received QAOB notification on CQ: */ - QETH_QDIO_BUF_QAOB_OK, - QETH_QDIO_BUF_QAOB_ERROR, +}; + +enum qeth_qaob_state { + QETH_QAOB_ISSUED, + QETH_QAOB_PENDING, + QETH_QAOB_DONE, +}; + +struct qeth_qaob_priv1 { + unsigned int state; + u8 queue_no; }; struct qeth_qdio_out_buffer { @@ -433,9 +437,8 @@ struct qeth_qdio_out_buffer { unsigned int frames; unsigned int bytes; struct sk_buff_head skb_list; - int is_header[QDIO_MAX_ELEMENTS_PER_BUFFER]; + DECLARE_BITMAP(from_kmem_cache, QDIO_MAX_ELEMENTS_PER_BUFFER); - struct qeth_qdio_out_q *q; struct list_head list_entry; struct qaob *aob; }; @@ -483,6 +486,7 @@ struct qeth_out_q_stats { u64 stopped; u64 doorbell; u64 coal_frames; + u64 completion_irq; u64 completion_yield; u64 completion_timer; @@ -526,6 +530,7 @@ struct qeth_qdio_out_q { unsigned int coalesce_usecs; unsigned int max_coalesced_frames; + unsigned int rescan_usecs; }; #define qeth_for_each_output_queue(card, q, i) \ @@ -612,7 +617,6 @@ struct qeth_channel { struct ccw_device *ccwdev; struct qeth_cmd_buffer *active_cmd; enum qeth_channel_states state; - atomic_t irq_pending; }; struct qeth_reply { @@ -662,11 +666,6 @@ static inline struct ccw1 *__ccw_from_cmd(struct qeth_cmd_buffer *iob) return (struct ccw1 *)(iob->data + ALIGN(iob->length, 8)); } -static inline bool qeth_trylock_channel(struct qeth_channel *channel) -{ - return atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0; -} - /** * OSA card related definitions */ @@ -886,13 +885,24 @@ static inline bool qeth_card_hw_is_reachable(struct qeth_card *card) return card->state == CARD_STATE_SOFTSETUP; } +static inline bool qeth_use_tx_irqs(struct qeth_card *card) +{ + return !IS_IQD(card); +} + static inline void qeth_unlock_channel(struct qeth_card *card, struct qeth_channel *channel) { - atomic_set(&channel->irq_pending, 0); + xchg(&channel->active_cmd, NULL); wake_up(&card->wait_q); } +static inline bool qeth_trylock_channel(struct qeth_channel *channel, + struct qeth_cmd_buffer *cmd) +{ + return cmpxchg(&channel->active_cmd, NULL, cmd) == NULL; +} + struct qeth_trap_id { __u16 lparnr; char vmname[8]; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index a1f08e9aa064..62f88ccbd03f 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -70,9 +70,6 @@ static void qeth_issue_next_read_cb(struct qeth_card *card, unsigned int data_length); static int qeth_qdio_establish(struct qeth_card *); static void qeth_free_qdio_queues(struct qeth_card *card); -static void qeth_notify_skbs(struct qeth_qdio_out_q *queue, - struct qeth_qdio_out_buffer *buf, - enum iucv_tx_notify notification); static void qeth_close_dev_handler(struct work_struct *work) { @@ -434,65 +431,6 @@ static enum iucv_tx_notify qeth_compute_cq_notification(int sbalf15, return n; } -static void qeth_qdio_handle_aob(struct qeth_card *card, - unsigned long phys_aob_addr) -{ - enum qeth_qdio_out_buffer_state new_state = QETH_QDIO_BUF_QAOB_OK; - struct qaob *aob; - struct qeth_qdio_out_buffer *buffer; - enum iucv_tx_notify notification; - struct qeth_qdio_out_q *queue; - unsigned int i; - - aob = (struct qaob *) phys_to_virt(phys_aob_addr); - QETH_CARD_TEXT(card, 5, "haob"); - QETH_CARD_TEXT_(card, 5, "%lx", phys_aob_addr); - buffer = (struct qeth_qdio_out_buffer *) aob->user1; - QETH_CARD_TEXT_(card, 5, "%lx", aob->user1); - - if (aob->aorc) { - QETH_CARD_TEXT_(card, 2, "aorc%02X", aob->aorc); - new_state = QETH_QDIO_BUF_QAOB_ERROR; - } - - switch (atomic_xchg(&buffer->state, new_state)) { - case QETH_QDIO_BUF_PRIMED: - /* Faster than TX completion code, let it handle the async - * completion for us. It will also recycle the QAOB. - */ - break; - case QETH_QDIO_BUF_PENDING: - /* TX completion code is active and will handle the async - * completion for us. It will also recycle the QAOB. - */ - break; - case QETH_QDIO_BUF_NEED_QAOB: - /* TX completion code is already finished. */ - notification = qeth_compute_cq_notification(aob->aorc, 1); - qeth_notify_skbs(buffer->q, buffer, notification); - - /* Free dangling allocations. The attached skbs are handled by - * qeth_tx_complete_pending_bufs(), and so is the QAOB. - */ - for (i = 0; - i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card); - i++) { - void *data = phys_to_virt(aob->sba[i]); - - if (data && buffer->is_header[i]) - kmem_cache_free(qeth_core_header_cache, data); - buffer->is_header[i] = 0; - } - - queue = buffer->q; - atomic_set(&buffer->state, QETH_QDIO_BUF_EMPTY); - napi_schedule(&queue->napi); - break; - default: - WARN_ON_ONCE(1); - } -} - static void qeth_setup_ccw(struct ccw1 *ccw, u8 cmd_code, u8 flags, u32 len, void *data) { @@ -1268,7 +1206,6 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, iob = (struct qeth_cmd_buffer *) (addr_t)intparm; } - channel->active_cmd = NULL; qeth_unlock_channel(card, channel); rc = qeth_check_irb_error(card, cdev, irb); @@ -1353,10 +1290,10 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *q, } } -static void qeth_tx_complete_buf(struct qeth_qdio_out_buffer *buf, bool error, +static void qeth_tx_complete_buf(struct qeth_qdio_out_q *queue, + struct qeth_qdio_out_buffer *buf, bool error, int budget) { - struct qeth_qdio_out_q *queue = buf->q; struct sk_buff *skb; /* Empty buffer? */ @@ -1400,17 +1337,18 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue, int i; /* is PCI flag set on buffer? */ - if (buf->buffer->element[0].sflags & SBAL_SFLAGS0_PCI_REQ) + if (buf->buffer->element[0].sflags & SBAL_SFLAGS0_PCI_REQ) { atomic_dec(&queue->set_pci_flags_count); + QETH_TXQ_STAT_INC(queue, completion_irq); + } - qeth_tx_complete_buf(buf, error, budget); + qeth_tx_complete_buf(queue, buf, error, budget); for (i = 0; i < queue->max_elements; ++i) { void *data = phys_to_virt(buf->buffer->element[i].addr); - if (data && buf->is_header[i]) + if (__test_and_clear_bit(i, buf->from_kmem_cache) && data) kmem_cache_free(qeth_core_header_cache, data); - buf->is_header[i] = 0; } qeth_scrub_qdio_buffer(buf->buffer, queue->max_elements); @@ -1434,14 +1372,30 @@ static void qeth_tx_complete_pending_bufs(struct qeth_card *card, struct qeth_qdio_out_buffer *buf, *tmp; list_for_each_entry_safe(buf, tmp, &queue->pending_bufs, list_entry) { - if (drain || atomic_read(&buf->state) == QETH_QDIO_BUF_EMPTY) { + struct qeth_qaob_priv1 *priv; + struct qaob *aob = buf->aob; + enum iucv_tx_notify notify; + unsigned int i; + + priv = (struct qeth_qaob_priv1 *)&aob->user1; + if (drain || READ_ONCE(priv->state) == QETH_QAOB_DONE) { QETH_CARD_TEXT(card, 5, "fp"); QETH_CARD_TEXT_(card, 5, "%lx", (long) buf); - if (drain) - qeth_notify_skbs(queue, buf, - TX_NOTIFY_GENERALERROR); - qeth_tx_complete_buf(buf, drain, budget); + notify = drain ? TX_NOTIFY_GENERALERROR : + qeth_compute_cq_notification(aob->aorc, 1); + qeth_notify_skbs(queue, buf, notify); + qeth_tx_complete_buf(queue, buf, drain, budget); + + for (i = 0; + i < aob->sb_count && i < queue->max_elements; + i++) { + void *data = phys_to_virt(aob->sba[i]); + + if (test_bit(i, buf->from_kmem_cache) && data) + kmem_cache_free(qeth_core_header_cache, + data); + } list_del(&buf->list_entry); qeth_free_out_buf(buf); @@ -1713,11 +1667,10 @@ static int qeth_stop_channel(struct qeth_channel *channel) rc = ccw_device_set_offline(cdev); spin_lock_irq(get_ccwdev_lock(cdev)); - if (channel->active_cmd) { + if (channel->active_cmd) dev_err(&cdev->dev, "Stopped channel while cmd %px was still active\n", channel->active_cmd); - channel->active_cmd = NULL; - } + cdev->handler = NULL; spin_unlock_irq(get_ccwdev_lock(cdev)); @@ -1730,7 +1683,7 @@ static int qeth_start_channel(struct qeth_channel *channel) int rc; channel->state = CH_STATE_DOWN; - atomic_set(&channel->irq_pending, 0); + xchg(&channel->active_cmd, NULL); spin_lock_irq(get_ccwdev_lock(cdev)); cdev->handler = qeth_irq; @@ -2037,7 +1990,7 @@ static int qeth_send_control_data(struct qeth_card *card, reply->param = reply_param; timeout = wait_event_interruptible_timeout(card->wait_q, - qeth_trylock_channel(channel), + qeth_trylock_channel(channel, iob), timeout); if (timeout <= 0) { qeth_put_cmd(iob); @@ -2057,8 +2010,6 @@ static int qeth_send_control_data(struct qeth_card *card, spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_start_timeout(channel->ccwdev, __ccw_from_cmd(iob), (addr_t) iob, 0, 0, timeout); - if (!rc) - channel->active_cmd = iob; spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { QETH_DBF_MESSAGE(2, "qeth_send_control_data on device %x: ccw_device_start rc = %i\n", @@ -2578,7 +2529,6 @@ static int qeth_alloc_out_buf(struct qeth_qdio_out_q *q, unsigned int bidx, newbuf->buffer = q->qdio_bufs[bidx]; skb_queue_head_init(&newbuf->skb_list); lockdep_set_class(&newbuf->skb_list.lock, &qdio_out_skb_queue_key); - newbuf->q = q; atomic_set(&newbuf->state, QETH_QDIO_BUF_EMPTY); q->bufs[bidx] = newbuf; return 0; @@ -2663,8 +2613,15 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) INIT_LIST_HEAD(&queue->pending_bufs); spin_lock_init(&queue->lock); timer_setup(&queue->timer, qeth_tx_completion_timer, 0); - queue->coalesce_usecs = QETH_TX_COALESCE_USECS; - queue->max_coalesced_frames = QETH_TX_MAX_COALESCED_FRAMES; + if (IS_IQD(card)) { + queue->coalesce_usecs = QETH_TX_COALESCE_USECS; + queue->max_coalesced_frames = QETH_TX_MAX_COALESCED_FRAMES; + queue->rescan_usecs = QETH_TX_TIMER_USECS; + } else { + queue->coalesce_usecs = USEC_PER_SEC; + queue->max_coalesced_frames = 0; + queue->rescan_usecs = 10 * USEC_PER_SEC; + } queue->priority = QETH_QIB_PQUE_PRIO_DEFAULT; } @@ -3601,8 +3558,8 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, int count) { struct qeth_qdio_out_buffer *buf = queue->bufs[index]; - unsigned int qdio_flags = QDIO_FLAG_SYNC_OUTPUT; struct qeth_card *card = queue->card; + unsigned int frames, usecs; struct qaob *aob = NULL; int rc; int i; @@ -3629,8 +3586,12 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, if (!buf->aob) buf->aob = qdio_allocate_aob(); if (buf->aob) { + struct qeth_qaob_priv1 *priv; + aob = buf->aob; - aob->user1 = (u64) buf; + priv = (struct qeth_qaob_priv1 *)&aob->user1; + priv->state = QETH_QAOB_ISSUED; + priv->queue_no = queue->queue_no; } } } else { @@ -3658,14 +3619,11 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, buf->buffer->element[0].sflags |= SBAL_SFLAGS0_PCI_REQ; } } - - if (atomic_read(&queue->set_pci_flags_count)) - qdio_flags |= QDIO_FLAG_PCI_OUT; } QETH_TXQ_STAT_INC(queue, doorbell); - rc = do_QDIO(CARD_DDEV(card), qdio_flags, queue->queue_no, index, count, - aob); + rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_OUTPUT, queue->queue_no, + index, count, aob); switch (rc) { case 0: @@ -3673,17 +3631,20 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, /* ignore temporary SIGA errors without busy condition */ /* Fake the TX completion interrupt: */ - if (IS_IQD(card)) { - unsigned int frames = READ_ONCE(queue->max_coalesced_frames); - unsigned int usecs = READ_ONCE(queue->coalesce_usecs); + frames = READ_ONCE(queue->max_coalesced_frames); + usecs = READ_ONCE(queue->coalesce_usecs); - if (frames && queue->coalesced_frames >= frames) { - napi_schedule(&queue->napi); - queue->coalesced_frames = 0; - QETH_TXQ_STAT_INC(queue, coal_frames); - } else if (usecs) { - qeth_tx_arm_timer(queue, usecs); - } + if (frames && queue->coalesced_frames >= frames) { + napi_schedule(&queue->napi); + queue->coalesced_frames = 0; + QETH_TXQ_STAT_INC(queue, coal_frames); + } else if (qeth_use_tx_irqs(card) && + atomic_read(&queue->used_buffers) >= 32) { + /* Old behaviour carried over from the qdio layer: */ + napi_schedule(&queue->napi); + QETH_TXQ_STAT_INC(queue, coal_frames); + } else if (usecs) { + qeth_tx_arm_timer(queue, usecs); } break; @@ -3769,6 +3730,18 @@ out: } EXPORT_SYMBOL_GPL(qeth_configure_cq); +static void qeth_qdio_handle_aob(struct qeth_card *card, struct qaob *aob) +{ + struct qeth_qaob_priv1 *priv = (struct qeth_qaob_priv1 *)&aob->user1; + unsigned int queue_no = priv->queue_no; + + BUILD_BUG_ON(sizeof(*priv) > ARRAY_SIZE(aob->user1)); + + if (xchg(&priv->state, QETH_QAOB_DONE) == QETH_QAOB_PENDING && + queue_no < card->qdio.no_out_queues) + napi_schedule(&card->qdio.out_qs[queue_no]->napi); +} + static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err, unsigned int queue, int first_element, int count) @@ -3795,7 +3768,7 @@ static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err, buffer->element[e].addr) { unsigned long phys_aob_addr = buffer->element[e].addr; - qeth_qdio_handle_aob(card, phys_aob_addr); + qeth_qdio_handle_aob(card, phys_to_virt(phys_aob_addr)); ++e; } qeth_scrub_qdio_buffer(buffer, QDIO_MAX_ELEMENTS_PER_BUFFER); @@ -3831,36 +3804,14 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev, unsigned long card_ptr) { struct qeth_card *card = (struct qeth_card *) card_ptr; - struct qeth_qdio_out_q *queue = card->qdio.out_qs[__queue]; struct net_device *dev = card->dev; - struct netdev_queue *txq; - int i; QETH_CARD_TEXT(card, 6, "qdouhdl"); if (qdio_error & QDIO_ERROR_FATAL) { QETH_CARD_TEXT(card, 2, "achkcond"); netif_tx_stop_all_queues(dev); qeth_schedule_recovery(card); - return; } - - for (i = first_element; i < (first_element + count); ++i) { - struct qeth_qdio_out_buffer *buf = queue->bufs[QDIO_BUFNR(i)]; - - qeth_handle_send_error(card, buf, qdio_error); - qeth_clear_output_buffer(queue, buf, qdio_error, 0); - } - - atomic_sub(count, &queue->used_buffers); - qeth_check_outbound_queue(queue); - - txq = netdev_get_tx_queue(dev, __queue); - /* xmit may have observed the full-condition, but not yet stopped the - * txq. In which case the code below won't trigger. So before returning, - * xmit will re-check the txq's fill level and wake it up if needed. - */ - if (netif_tx_queue_stopped(txq) && !qeth_out_queue_is_full(queue)) - netif_tx_wake_queue(txq); } /** @@ -4101,7 +4052,7 @@ static unsigned int qeth_fill_buffer(struct qeth_qdio_out_buffer *buf, /* HW header is allocated from cache: */ if ((void *)hdr != skb->data) - buf->is_header[element] = 1; + __set_bit(element, buf->from_kmem_cache); /* HW header was pushed and is contiguous with linear part: */ else if (length > 0 && !PAGE_ALIGNED(data) && (data == (char *)hdr + hd_len)) @@ -5256,7 +5207,6 @@ static int qeth_qdio_establish(struct qeth_card *card) init_data.int_parm = (unsigned long) card; init_data.input_sbal_addr_array = in_sbal_ptrs; init_data.output_sbal_addr_array = out_sbal_ptrs; - init_data.scan_threshold = IS_IQD(card) ? 0 : 32; if (atomic_cmpxchg(&card->qdio.state, QETH_QDIO_ALLOCATED, QETH_QDIO_ESTABLISHED) == QETH_QDIO_ALLOCATED) { @@ -5956,9 +5906,10 @@ static unsigned int qeth_rx_poll(struct qeth_card *card, int budget) /* Fetch completed RX buffers: */ if (!card->rx.b_count) { card->rx.qdio_err = 0; - card->rx.b_count = qdio_get_next_buffers( - card->data.ccwdev, 0, &card->rx.b_index, - &card->rx.qdio_err); + card->rx.b_count = qdio_inspect_queue(CARD_DDEV(card), + 0, true, + &card->rx.b_index, + &card->rx.qdio_err); if (card->rx.b_count <= 0) { card->rx.b_count = 0; break; @@ -6022,6 +5973,16 @@ int qeth_poll(struct napi_struct *napi, int budget) work_done = qeth_rx_poll(card, budget); + if (qeth_use_tx_irqs(card)) { + struct qeth_qdio_out_q *queue; + unsigned int i; + + qeth_for_each_output_queue(card, queue, i) { + if (!qeth_out_queue_is_empty(queue)) + napi_schedule(&queue->napi); + } + } + if (card->options.cq == QETH_CQ_ENABLED) qeth_cq_poll(card); @@ -6055,6 +6016,8 @@ static void qeth_iqd_tx_complete(struct qeth_qdio_out_q *queue, if (qdio_error == QDIO_ERROR_SLSB_PENDING) { struct qaob *aob = buffer->aob; + struct qeth_qaob_priv1 *priv; + enum iucv_tx_notify notify; if (!aob) { netdev_WARN_ONCE(card->dev, @@ -6066,60 +6029,27 @@ static void qeth_iqd_tx_complete(struct qeth_qdio_out_q *queue, QETH_CARD_TEXT_(card, 5, "pel%u", bidx); - switch (atomic_cmpxchg(&buffer->state, - QETH_QDIO_BUF_PRIMED, - QETH_QDIO_BUF_PENDING)) { - case QETH_QDIO_BUF_PRIMED: - /* We have initial ownership, no QAOB (yet): */ + priv = (struct qeth_qaob_priv1 *)&aob->user1; + /* QAOB hasn't completed yet: */ + if (xchg(&priv->state, QETH_QAOB_PENDING) != QETH_QAOB_DONE) { qeth_notify_skbs(queue, buffer, TX_NOTIFY_PENDING); - /* Handle race with qeth_qdio_handle_aob(): */ - switch (atomic_xchg(&buffer->state, - QETH_QDIO_BUF_NEED_QAOB)) { - case QETH_QDIO_BUF_PENDING: - /* No concurrent QAOB notification. */ - - /* Prepare the queue slot for immediate re-use: */ - qeth_scrub_qdio_buffer(buffer->buffer, queue->max_elements); - if (qeth_alloc_out_buf(queue, bidx, - GFP_ATOMIC)) { - QETH_CARD_TEXT(card, 2, "outofbuf"); - qeth_schedule_recovery(card); - } - - list_add(&buffer->list_entry, - &queue->pending_bufs); - /* Skip clearing the buffer: */ - return; - case QETH_QDIO_BUF_QAOB_OK: - qeth_notify_skbs(queue, buffer, - TX_NOTIFY_DELAYED_OK); - error = false; - break; - case QETH_QDIO_BUF_QAOB_ERROR: - qeth_notify_skbs(queue, buffer, - TX_NOTIFY_DELAYED_GENERALERROR); - error = true; - break; - default: - WARN_ON_ONCE(1); + /* Prepare the queue slot for immediate re-use: */ + qeth_scrub_qdio_buffer(buffer->buffer, queue->max_elements); + if (qeth_alloc_out_buf(queue, bidx, GFP_ATOMIC)) { + QETH_CARD_TEXT(card, 2, "outofbuf"); + qeth_schedule_recovery(card); } - break; - case QETH_QDIO_BUF_QAOB_OK: - /* qeth_qdio_handle_aob() already received a QAOB: */ - qeth_notify_skbs(queue, buffer, TX_NOTIFY_OK); - error = false; - break; - case QETH_QDIO_BUF_QAOB_ERROR: - /* qeth_qdio_handle_aob() already received a QAOB: */ - qeth_notify_skbs(queue, buffer, TX_NOTIFY_GENERALERROR); - error = true; - break; - default: - WARN_ON_ONCE(1); + list_add(&buffer->list_entry, &queue->pending_bufs); + /* Skip clearing the buffer: */ + return; } + /* QAOB already completed: */ + notify = qeth_compute_cq_notification(aob->aorc, 0); + qeth_notify_skbs(queue, buffer, notify); + error = !!aob->aorc; memset(aob, 0, sizeof(*aob)); } else if (card->options.cq == QETH_CQ_ENABLED) { qeth_notify_skbs(queue, buffer, @@ -6138,7 +6068,10 @@ static int qeth_tx_poll(struct napi_struct *napi, int budget) unsigned int work_done = 0; struct netdev_queue *txq; - txq = netdev_get_tx_queue(dev, qeth_iqd_translate_txq(dev, queue_no)); + if (IS_IQD(card)) + txq = netdev_get_tx_queue(dev, qeth_iqd_translate_txq(dev, queue_no)); + else + txq = netdev_get_tx_queue(dev, queue_no); while (1) { unsigned int start, error, i; @@ -6165,8 +6098,9 @@ static int qeth_tx_poll(struct napi_struct *napi, int budget) &start, &error); if (completed <= 0) { /* Ensure we see TX completion for pending work: */ - if (napi_complete_done(napi, 0)) - qeth_tx_arm_timer(queue, QETH_TX_TIMER_USECS); + if (napi_complete_done(napi, 0) && + !atomic_read(&queue->set_pci_flags_count)) + qeth_tx_arm_timer(queue, queue->rescan_usecs); return 0; } @@ -6179,12 +6113,19 @@ static int qeth_tx_poll(struct napi_struct *napi, int budget) bytes += buffer->bytes; qeth_handle_send_error(card, buffer, error); - qeth_iqd_tx_complete(queue, bidx, error, budget); + if (IS_IQD(card)) + qeth_iqd_tx_complete(queue, bidx, error, budget); + else + qeth_clear_output_buffer(queue, buffer, error, + budget); } - netdev_tx_completed_queue(txq, packets, bytes); atomic_sub(completed, &queue->used_buffers); work_done += completed; + if (IS_IQD(card)) + netdev_tx_completed_queue(txq, packets, bytes); + else + qeth_check_outbound_queue(queue); /* xmit may have observed the full-condition, but not yet * stopped the txq. In which case the code below won't trigger. @@ -7228,6 +7169,8 @@ EXPORT_SYMBOL_GPL(qeth_iqd_select_queue); int qeth_open(struct net_device *dev) { struct qeth_card *card = dev->ml_priv; + struct qeth_qdio_out_q *queue; + unsigned int i; QETH_CARD_TEXT(card, 4, "qethopen"); @@ -7235,16 +7178,11 @@ int qeth_open(struct net_device *dev) netif_tx_start_all_queues(dev); local_bh_disable(); - if (IS_IQD(card)) { - struct qeth_qdio_out_q *queue; - unsigned int i; - - qeth_for_each_output_queue(card, queue, i) { - netif_tx_napi_add(dev, &queue->napi, qeth_tx_poll, - QETH_NAPI_WEIGHT); - napi_enable(&queue->napi); - napi_schedule(&queue->napi); - } + qeth_for_each_output_queue(card, queue, i) { + netif_tx_napi_add(dev, &queue->napi, qeth_tx_poll, + QETH_NAPI_WEIGHT); + napi_enable(&queue->napi); + napi_schedule(&queue->napi); } napi_enable(&card->napi); @@ -7259,6 +7197,8 @@ EXPORT_SYMBOL_GPL(qeth_open); int qeth_stop(struct net_device *dev) { struct qeth_card *card = dev->ml_priv; + struct qeth_qdio_out_q *queue; + unsigned int i; QETH_CARD_TEXT(card, 4, "qethstop"); @@ -7266,24 +7206,17 @@ int qeth_stop(struct net_device *dev) cancel_delayed_work_sync(&card->buffer_reclaim_work); qdio_stop_irq(CARD_DDEV(card)); - if (IS_IQD(card)) { - struct qeth_qdio_out_q *queue; - unsigned int i; + /* Quiesce the NAPI instances: */ + qeth_for_each_output_queue(card, queue, i) + napi_disable(&queue->napi); - /* Quiesce the NAPI instances: */ - qeth_for_each_output_queue(card, queue, i) - napi_disable(&queue->napi); + /* Stop .ndo_start_xmit, might still access queue->napi. */ + netif_tx_disable(dev); - /* Stop .ndo_start_xmit, might still access queue->napi. */ - netif_tx_disable(dev); - - qeth_for_each_output_queue(card, queue, i) { - del_timer_sync(&queue->timer); - /* Queues may get re-allocated, so remove the NAPIs. */ - netif_napi_del(&queue->napi); - } - } else { - netif_tx_disable(dev); + qeth_for_each_output_queue(card, queue, i) { + del_timer_sync(&queue->timer); + /* Queues may get re-allocated, so remove the NAPIs. */ + netif_napi_del(&queue->napi); } return 0; diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c index 3a51bbff0ffe..2c4cb300a8fc 100644 --- a/drivers/s390/net/qeth_ethtool.c +++ b/drivers/s390/net/qeth_ethtool.c @@ -41,6 +41,7 @@ static const struct qeth_stats txq_stats[] = { QETH_TXQ_STAT("Queue stopped", stopped), QETH_TXQ_STAT("Doorbell", doorbell), QETH_TXQ_STAT("IRQ for frames", coal_frames), + QETH_TXQ_STAT("Completion IRQ", completion_irq), QETH_TXQ_STAT("Completion yield", completion_yield), QETH_TXQ_STAT("Completion timer", completion_timer), }; @@ -79,10 +80,8 @@ static void qeth_add_stat_strings(u8 **data, const char *prefix, { unsigned int i; - for (i = 0; i < size; i++) { - snprintf(*data, ETH_GSTRING_LEN, "%s%s", prefix, stats[i].name); - *data += ETH_GSTRING_LEN; - } + for (i = 0; i < size; i++) + ethtool_sprintf(data, "%s%s", prefix, stats[i].name); } static int qeth_get_sset_count(struct net_device *dev, int stringset) diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index ca44421a6d6e..2abf86c104d5 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -805,8 +805,6 @@ static int qeth_l2_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, if (!netif_device_present(dev)) return -ENODEV; - if (!(priv->brport_hw_features)) - return -EOPNOTSUPP; nlmsg_for_each_attr(attr, nlh, sizeof(struct ifinfomsg), rem1) { if (nla_type(attr) == IFLA_PROTINFO) { @@ -832,6 +830,16 @@ static int qeth_l2_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, return 0; if (!bp_tb[IFLA_BRPORT_LEARNING_SYNC]) return -EINVAL; + if (!(priv->brport_hw_features & BR_LEARNING_SYNC)) { + NL_SET_ERR_MSG_ATTR(extack, bp_tb[IFLA_BRPORT_LEARNING_SYNC], + "Operation not supported by HW"); + return -EOPNOTSUPP; + } + if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) { + NL_SET_ERR_MSG_ATTR(extack, bp_tb[IFLA_BRPORT_LEARNING_SYNC], + "Requires NET_SWITCHDEV"); + return -EOPNOTSUPP; + } enable = !!nla_get_u8(bp_tb[IFLA_BRPORT_LEARNING_SYNC]); if (enable == !!(priv->brport_features & BR_LEARNING_SYNC)) diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 6540d48eb0e8..715c34904e3e 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index 41ac9477df7a..10b6c6daaacd 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index a2c3d9ad9ee4..746a7def2825 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1416,7 +1416,7 @@ static bool sd_need_revalidate(struct block_device *bdev, * In the latter case @inode and @filp carry an abridged amount * of information as noted above. * - * Locking: called with bdev->bd_mutex held. + * Locking: called with bdev->bd_disk->open_mutex held. **/ static int sd_open(struct block_device *bdev, fmode_t mode) { @@ -1490,7 +1490,7 @@ error_out: * Note: may block (uninterruptible) if error recovery is underway * on this disk. * - * Locking: called with bdev->bd_mutex held. + * Locking: called with bdev->bd_disk->open_mutex held. **/ static void sd_release(struct gendisk *disk, fmode_t mode) { diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index e6718a74e5da..403753929320 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -406,6 +406,14 @@ static void storvsc_on_channel_callback(void *context); #define STORVSC_IDE_MAX_TARGETS 1 #define STORVSC_IDE_MAX_CHANNELS 1 +/* + * Upper bound on the size of a storvsc packet. vmscsi_size_delta is not + * included in the calculation because it is set after STORVSC_MAX_PKT_SIZE + * is used in storvsc_connect_to_vsp + */ +#define STORVSC_MAX_PKT_SIZE (sizeof(struct vmpacket_descriptor) +\ + sizeof(struct vstor_packet)) + struct storvsc_cmd_request { struct scsi_cmnd *cmd; @@ -688,6 +696,23 @@ old_is_alloced: spin_unlock_irqrestore(&stor_device->lock, flags); } +static u64 storvsc_next_request_id(struct vmbus_channel *channel, u64 rqst_addr) +{ + struct storvsc_cmd_request *request = + (struct storvsc_cmd_request *)(unsigned long)rqst_addr; + + if (rqst_addr == VMBUS_RQST_INIT) + return VMBUS_RQST_INIT; + if (rqst_addr == VMBUS_RQST_RESET) + return VMBUS_RQST_RESET; + + /* + * Cannot return an ID of 0, which is reserved for an unsolicited + * message from Hyper-V. + */ + return (u64)blk_mq_unique_tag(request->cmd->request) + 1; +} + static void handle_sc_creation(struct vmbus_channel *new_sc) { struct hv_device *device = new_sc->primary_channel->device_obj; @@ -701,12 +726,9 @@ static void handle_sc_creation(struct vmbus_channel *new_sc) return; memset(&props, 0, sizeof(struct vmstorage_channel_properties)); + new_sc->max_pkt_size = STORVSC_MAX_PKT_SIZE; - /* - * The size of vmbus_requestor is an upper bound on the number of requests - * that can be in-progress at any one time across all channels. - */ - new_sc->rqstor_size = scsi_driver.can_queue; + new_sc->next_request_id_callback = storvsc_next_request_id; ret = vmbus_open(new_sc, storvsc_ringbuffer_size, @@ -773,7 +795,7 @@ static void handle_multichannel_storage(struct hv_device *device, int max_chns) ret = vmbus_sendpacket(device->channel, vstor_packet, (sizeof(struct vstor_packet) - stor_device->vmscsi_size_delta), - (unsigned long)request, + VMBUS_RQST_INIT, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); @@ -842,7 +864,7 @@ static int storvsc_execute_vstor_op(struct hv_device *device, ret = vmbus_sendpacket(device->channel, vstor_packet, (sizeof(struct vstor_packet) - stor_device->vmscsi_size_delta), - (unsigned long)request, + VMBUS_RQST_INIT, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret != 0) @@ -1244,6 +1266,7 @@ static void storvsc_on_channel_callback(void *context) const struct vmpacket_descriptor *desc; struct hv_device *device; struct storvsc_device *stor_device; + struct Scsi_Host *shost; if (channel->primary_channel != NULL) device = channel->primary_channel->device_obj; @@ -1254,20 +1277,12 @@ static void storvsc_on_channel_callback(void *context) if (!stor_device) return; + shost = stor_device->host; + foreach_vmbus_pkt(desc, channel) { - void *packet = hv_pkt_data(desc); - struct storvsc_cmd_request *request; - u64 cmd_rqst; - - cmd_rqst = vmbus_request_addr(&channel->requestor, - desc->trans_id); - if (cmd_rqst == VMBUS_RQST_ERROR) { - dev_err(&device->device, - "Incorrect transaction id\n"); - continue; - } - - request = (struct storvsc_cmd_request *)(unsigned long)cmd_rqst; + struct vstor_packet *packet = hv_pkt_data(desc); + struct storvsc_cmd_request *request = NULL; + u64 rqst_id = desc->trans_id; if (hv_pkt_datalen(desc) < sizeof(struct vstor_packet) - stor_device->vmscsi_size_delta) { @@ -1275,14 +1290,44 @@ static void storvsc_on_channel_callback(void *context) continue; } - if (request == &stor_device->init_request || - request == &stor_device->reset_request) { - memcpy(&request->vstor_packet, packet, - (sizeof(struct vstor_packet) - stor_device->vmscsi_size_delta)); - complete(&request->wait_event); + if (rqst_id == VMBUS_RQST_INIT) { + request = &stor_device->init_request; + } else if (rqst_id == VMBUS_RQST_RESET) { + request = &stor_device->reset_request; } else { + /* Hyper-V can send an unsolicited message with ID of 0 */ + if (rqst_id == 0) { + /* + * storvsc_on_receive() looks at the vstor_packet in the message + * from the ring buffer. If the operation in the vstor_packet is + * COMPLETE_IO, then we call storvsc_on_io_completion(), and + * dereference the guest memory address. Make sure we don't call + * storvsc_on_io_completion() with a guest memory address that is + * zero if Hyper-V were to construct and send such a bogus packet. + */ + if (packet->operation == VSTOR_OPERATION_COMPLETE_IO) { + dev_err(&device->device, "Invalid packet with ID of 0\n"); + continue; + } + } else { + struct scsi_cmnd *scmnd; + + /* Transaction 'rqst_id' corresponds to tag 'rqst_id - 1' */ + scmnd = scsi_host_find_tag(shost, rqst_id - 1); + if (scmnd == NULL) { + dev_err(&device->device, "Incorrect transaction ID\n"); + continue; + } + request = (struct storvsc_cmd_request *)scsi_cmd_priv(scmnd); + } + storvsc_on_receive(stor_device, packet, request); + continue; } + + memcpy(&request->vstor_packet, packet, + (sizeof(struct vstor_packet) - stor_device->vmscsi_size_delta)); + complete(&request->wait_event); } } @@ -1294,11 +1339,8 @@ static int storvsc_connect_to_vsp(struct hv_device *device, u32 ring_size, memset(&props, 0, sizeof(struct vmstorage_channel_properties)); - /* - * The size of vmbus_requestor is an upper bound on the number of requests - * that can be in-progress at any one time across all channels. - */ - device->channel->rqstor_size = scsi_driver.can_queue; + device->channel->max_pkt_size = STORVSC_MAX_PKT_SIZE; + device->channel->next_request_id_callback = storvsc_next_request_id; ret = vmbus_open(device->channel, ring_size, @@ -1624,7 +1666,7 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd) ret = vmbus_sendpacket(device->channel, vstor_packet, (sizeof(struct vstor_packet) - stor_device->vmscsi_size_delta), - (unsigned long)&stor_device->reset_request, + VMBUS_RQST_RESET, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret != 0) diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c index 66a76fd83248..2de3896489c8 100644 --- a/drivers/ssb/driver_gpio.c +++ b/drivers/ssb/driver_gpio.c @@ -231,7 +231,8 @@ static int ssb_gpio_chipco_init(struct ssb_bus *bus) chip->ngpio = 16; /* There is just one SoC in one device and its GPIO addresses should be * deterministic to address them more easily. The other buses could get - * a random base number. */ + * a random base number. + */ if (bus->bustype == SSB_BUSTYPE_SSB) chip->base = 0; else @@ -424,7 +425,8 @@ static int ssb_gpio_extif_init(struct ssb_bus *bus) chip->ngpio = 5; /* There is just one SoC in one device and its GPIO addresses should be * deterministic to address them more easily. The other buses could get - * a random base number. */ + * a random base number. + */ if (bus->bustype == SSB_BUSTYPE_SSB) chip->base = 0; else diff --git a/drivers/ssb/driver_pcicore.c b/drivers/ssb/driver_pcicore.c index c1186415896b..d11b4242b6d2 100644 --- a/drivers/ssb/driver_pcicore.c +++ b/drivers/ssb/driver_pcicore.c @@ -55,7 +55,8 @@ void pcicore_write16(struct ssb_pcicore *pc, u16 offset, u16 value) #include /* Probe a 32bit value on the bus and catch bus exceptions. * Returns nonzero on a bus exception. - * This is MIPS specific */ + * This is MIPS specific + */ #define mips_busprobe32(val, addr) get_dbe((val), ((u32 *)(addr))) /* Assume one-hot slot wiring */ @@ -255,7 +256,8 @@ static struct pci_controller ssb_pcicore_controller = { }; /* This function is called when doing a pci_enable_device(). - * We must first check if the device is a device on the PCI-core bridge. */ + * We must first check if the device is a device on the PCI-core bridge. + */ int ssb_pcicore_plat_dev_init(struct pci_dev *d) { if (d->bus->ops != &ssb_pcicore_pciops) { @@ -381,11 +383,13 @@ static void ssb_pcicore_init_hostmode(struct ssb_pcicore *pc) /* Ok, ready to run, register it to the system. * The following needs change, if we want to port hostmode - * to non-MIPS platform. */ + * to non-MIPS platform. + */ ssb_pcicore_controller.io_map_base = (unsigned long)ioremap(SSB_PCI_MEM, 0x04000000); set_io_port_base(ssb_pcicore_controller.io_map_base); /* Give some time to the PCI controller to configure itself with the new - * values. Not waiting at this point causes crashes of the machine. */ + * values. Not waiting at this point causes crashes of the machine. + */ mdelay(10); register_pci_controller(&ssb_pcicore_controller); } @@ -405,7 +409,8 @@ static int pcicore_is_in_hostmode(struct ssb_pcicore *pc) return 0; /* The 200-pin BCM4712 package does not bond out PCI. Even when - * PCI is bonded out, some boards may leave the pins floating. */ + * PCI is bonded out, some boards may leave the pins floating. + */ if (bus->chip_id == 0x4712) { if (bus->chip_package == SSB_CHIPPACK_BCM4712S) return 0; @@ -685,7 +690,8 @@ int ssb_pcicore_dev_irqvecs_enable(struct ssb_pcicore *pc, if (dev->bus->bustype != SSB_BUSTYPE_PCI) { /* This SSB device is not on a PCI host-bus. So the IRQs are * not routed through the PCI core. - * So we must not enable routing through the PCI core. */ + * So we must not enable routing through the PCI core. + */ goto out; } diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c index 0a26984acb2c..3a29b5570f9f 100644 --- a/drivers/ssb/main.c +++ b/drivers/ssb/main.c @@ -37,7 +37,8 @@ static LIST_HEAD(buses); /* Software ID counter */ static unsigned int next_busnumber; /* buses_mutes locks the two buslists and the next_busnumber. - * Don't lock this directly, but use ssb_buses_[un]lock() below. */ + * Don't lock this directly, but use ssb_buses_[un]lock() below. + */ static DEFINE_MUTEX(buses_mutex); /* There are differences in the codeflow, if the bus is @@ -45,7 +46,8 @@ static DEFINE_MUTEX(buses_mutex); * are not available early. This is a mechanism to delay * these initializations to after early boot has finished. * It's also used to avoid mutex locking, as that's not - * available and needed early. */ + * available and needed early. + */ static bool ssb_is_early_boot = 1; static void ssb_buses_lock(void); @@ -161,7 +163,8 @@ int ssb_bus_resume(struct ssb_bus *bus) int err; /* Reset HW state information in memory, so that HW is - * completely reinitialized. */ + * completely reinitialized. + */ bus->mapped_device = NULL; #ifdef CONFIG_SSB_DRIVER_PCICORE bus->pcicore.setup_done = 0; @@ -431,9 +434,7 @@ void ssb_bus_unregister(struct ssb_bus *bus) int err; err = ssb_gpio_unregister(bus); - if (err == -EBUSY) - pr_debug("Some GPIOs are still in use\n"); - else if (err) + if (err) pr_debug("Can not unregister GPIO driver: %i\n", err); ssb_buses_lock(); @@ -467,7 +468,8 @@ static int ssb_devices_register(struct ssb_bus *bus) sdev = &(bus->devices[i]); /* We don't register SSB-system devices to the kernel, - * as the drivers for them are built into SSB. */ + * as the drivers for them are built into SSB. + */ switch (sdev->id.coreid) { case SSB_DEV_CHIPCOMMON: case SSB_DEV_PCI: @@ -521,7 +523,8 @@ static int ssb_devices_register(struct ssb_bus *bus) if (err) { pr_err("Could not register %s\n", dev_name(dev)); /* Set dev to NULL to not unregister - * dev on error unwinding. */ + * dev on error unwinding. + */ sdev->dev = NULL; put_device(dev); goto error; @@ -667,7 +670,8 @@ ssb_bus_register(struct ssb_bus *bus, ssb_bus_may_powerdown(bus); /* Queue it for attach. - * See the comment at the ssb_is_early_boot definition. */ + * See the comment at the ssb_is_early_boot definition. + */ list_add_tail(&bus->list, &attach_queue); if (!ssb_is_early_boot) { /* This is not early boot, so we must attach the bus now */ @@ -1007,7 +1011,8 @@ static void ssb_flush_tmslow(struct ssb_device *dev) * a machine check exception otherwise. * Do this by reading the register back to commit the * PCI write and delay an additional usec for the device - * to react to the change. */ + * to react to the change. + */ ssb_read32(dev, SSB_TMSLOW); udelay(1); } @@ -1044,7 +1049,8 @@ void ssb_device_enable(struct ssb_device *dev, u32 core_specific_flags) EXPORT_SYMBOL(ssb_device_enable); /* Wait for bitmask in a register to get set or cleared. - * timeout is in units of ten-microseconds */ + * timeout is in units of ten-microseconds + */ static int ssb_wait_bits(struct ssb_device *dev, u16 reg, u32 bitmask, int timeout, int set) { @@ -1153,7 +1159,8 @@ int ssb_bus_may_powerdown(struct ssb_bus *bus) /* On buses where more than one core may be working * at a time, we must not powerdown stuff if there are - * still cores that may want to run. */ + * still cores that may want to run. + */ if (bus->bustype == SSB_BUSTYPE_SSB) goto out; @@ -1303,13 +1310,11 @@ static int __init ssb_modinit(void) if (err) { pr_err("Broadcom 43xx PCI-SSB-bridge initialization failed\n"); /* don't fail SSB init because of this */ - err = 0; } err = ssb_host_pcmcia_init(); if (err) { pr_err("PCMCIA host initialization failed\n"); /* don't fail SSB init because of this */ - err = 0; } err = ssb_gige_init(); if (err) { @@ -1322,7 +1327,8 @@ out: } /* ssb must be initialized after PCI but before the ssb drivers. * That means we must use some initcall between subsys_initcall - * and device_initcall. */ + * and device_initcall. + */ fs_initcall(ssb_modinit); static void __exit ssb_modexit(void) diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c index dac54041ad8d..148bcb99c212 100644 --- a/drivers/ssb/pci.c +++ b/drivers/ssb/pci.c @@ -1117,9 +1117,9 @@ const struct ssb_bus_ops ssb_pci_ops = { #endif }; -static ssize_t ssb_pci_attr_sprom_show(struct device *pcidev, - struct device_attribute *attr, - char *buf) +static ssize_t ssb_sprom_show(struct device *pcidev, + struct device_attribute *attr, + char *buf) { struct pci_dev *pdev = container_of(pcidev, struct pci_dev, dev); struct ssb_bus *bus; @@ -1131,9 +1131,9 @@ static ssize_t ssb_pci_attr_sprom_show(struct device *pcidev, return ssb_attr_sprom_show(bus, buf, sprom_do_read); } -static ssize_t ssb_pci_attr_sprom_store(struct device *pcidev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t ssb_sprom_store(struct device *pcidev, + struct device_attribute *attr, + const char *buf, size_t count) { struct pci_dev *pdev = container_of(pcidev, struct pci_dev, dev); struct ssb_bus *bus; @@ -1146,9 +1146,7 @@ static ssize_t ssb_pci_attr_sprom_store(struct device *pcidev, sprom_check_crc, sprom_do_write); } -static DEVICE_ATTR(ssb_sprom, 0600, - ssb_pci_attr_sprom_show, - ssb_pci_attr_sprom_store); +static DEVICE_ATTR_ADMIN_RW(ssb_sprom); void ssb_pci_exit(struct ssb_bus *bus) { diff --git a/drivers/ssb/pcmcia.c b/drivers/ssb/pcmcia.c index d7d730c245c5..45502098e0c7 100644 --- a/drivers/ssb/pcmcia.c +++ b/drivers/ssb/pcmcia.c @@ -723,9 +723,9 @@ int ssb_pcmcia_get_invariants(struct ssb_bus *bus, return -ENODEV; } -static ssize_t ssb_pcmcia_attr_sprom_show(struct device *pcmciadev, - struct device_attribute *attr, - char *buf) +static ssize_t ssb_sprom_show(struct device *pcmciadev, + struct device_attribute *attr, + char *buf) { struct pcmcia_device *pdev = container_of(pcmciadev, struct pcmcia_device, dev); @@ -739,9 +739,9 @@ static ssize_t ssb_pcmcia_attr_sprom_show(struct device *pcmciadev, ssb_pcmcia_sprom_read_all); } -static ssize_t ssb_pcmcia_attr_sprom_store(struct device *pcmciadev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t ssb_sprom_store(struct device *pcmciadev, + struct device_attribute *attr, + const char *buf, size_t count) { struct pcmcia_device *pdev = container_of(pcmciadev, struct pcmcia_device, dev); @@ -756,9 +756,7 @@ static ssize_t ssb_pcmcia_attr_sprom_store(struct device *pcmciadev, ssb_pcmcia_sprom_write_all); } -static DEVICE_ATTR(ssb_sprom, 0600, - ssb_pcmcia_attr_sprom_show, - ssb_pcmcia_attr_sprom_store); +static DEVICE_ATTR_ADMIN_RW(ssb_sprom); static int ssb_pcmcia_cor_setup(struct ssb_bus *bus, u8 cor) { diff --git a/drivers/ssb/scan.c b/drivers/ssb/scan.c index f49ab1aa2149..4161e5d1f276 100644 --- a/drivers/ssb/scan.c +++ b/drivers/ssb/scan.c @@ -325,6 +325,7 @@ int ssb_bus_scan(struct ssb_bus *bus, if (bus->nr_devices > ARRAY_SIZE(bus->devices)) { pr_err("More than %d ssb cores found (%d)\n", SSB_MAX_NR_CORES, bus->nr_devices); + err = -EINVAL; goto err_unmap; } if (bus->bustype == SSB_BUSTYPE_SSB) { diff --git a/drivers/ssb/sdio.c b/drivers/ssb/sdio.c index 7fe0afb42234..66c5c2169704 100644 --- a/drivers/ssb/sdio.c +++ b/drivers/ssb/sdio.c @@ -411,7 +411,6 @@ static void ssb_sdio_block_write(struct ssb_device *dev, const void *buffer, sdio_claim_host(bus->host_sdio); if (unlikely(ssb_sdio_switch_core(bus, dev))) { error = -EIO; - memset((void *)buffer, 0xff, count); goto err_out; } offset |= bus->sdio_sbaddr & 0xffff; diff --git a/drivers/staging/mt7621-dts/mt7621.dtsi b/drivers/staging/mt7621-dts/mt7621.dtsi index f0c9ae757bcd..093a7f8091b5 100644 --- a/drivers/staging/mt7621-dts/mt7621.dtsi +++ b/drivers/staging/mt7621-dts/mt7621.dtsi @@ -437,6 +437,10 @@ mediatek,mcm; resets = <&rstctrl 2>; reset-names = "mcm"; + interrupt-controller; + #interrupt-cells = <1>; + interrupt-parent = <&gic>; + interrupts = ; ports { #address-cells = <1>; diff --git a/drivers/staging/octeon-usb/octeon-hcd.c b/drivers/staging/octeon-usb/octeon-hcd.c index f27f20a4aa2d..a1cd81d4a114 100644 --- a/drivers/staging/octeon-usb/octeon-hcd.c +++ b/drivers/staging/octeon-usb/octeon-hcd.c @@ -50,8 +50,10 @@ #include #include #include +#include #include #include +#include #include diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index d1e4a7379beb..8e5490ac13a2 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -21,8 +21,10 @@ #include #include #include +#include #include #include +#include #include #include #include @@ -55,6 +57,7 @@ MODULE_DEVICE_TABLE (usb, wdm_ids); #define WDM_SUSPENDING 8 #define WDM_RESETTING 9 #define WDM_OVERFLOW 10 +#define WDM_WWAN_IN_USE 11 #define WDM_MAX 16 @@ -106,6 +109,9 @@ struct wdm_device { struct list_head device_list; int (*manage_power)(struct usb_interface *, int); + + enum wwan_port_type wwanp_type; + struct wwan_port *wwanp; }; static struct usb_driver wdm_driver; @@ -157,6 +163,8 @@ static void wdm_out_callback(struct urb *urb) wake_up_all(&desc->wait); } +static void wdm_wwan_rx(struct wdm_device *desc, int length); + static void wdm_in_callback(struct urb *urb) { unsigned long flags; @@ -192,6 +200,11 @@ static void wdm_in_callback(struct urb *urb) } } + if (test_bit(WDM_WWAN_IN_USE, &desc->flags)) { + wdm_wwan_rx(desc, length); + goto out; + } + /* * only set a new error if there is no previous error. * Errors are only cleared during read/open @@ -226,6 +239,7 @@ skip_error: set_bit(WDM_READ, &desc->flags); wake_up(&desc->wait); } +out: spin_unlock_irqrestore(&desc->iuspin, flags); } @@ -708,6 +722,11 @@ static int wdm_open(struct inode *inode, struct file *file) goto out; file->private_data = desc; + if (test_bit(WDM_WWAN_IN_USE, &desc->flags)) { + rv = -EBUSY; + goto out; + } + rv = usb_autopm_get_interface(desc->intf); if (rv < 0) { dev_err(&desc->intf->dev, "Error autopm - %d\n", rv); @@ -804,6 +823,152 @@ static struct usb_class_driver wdm_class = { .minor_base = WDM_MINOR_BASE, }; +/* --- WWAN framework integration --- */ +#ifdef CONFIG_WWAN +static int wdm_wwan_port_start(struct wwan_port *port) +{ + struct wdm_device *desc = wwan_port_get_drvdata(port); + + /* The interface is both exposed via the WWAN framework and as a + * legacy usbmisc chardev. If chardev is already open, just fail + * to prevent concurrent usage. Otherwise, switch to WWAN mode. + */ + mutex_lock(&wdm_mutex); + if (desc->count) { + mutex_unlock(&wdm_mutex); + return -EBUSY; + } + set_bit(WDM_WWAN_IN_USE, &desc->flags); + mutex_unlock(&wdm_mutex); + + desc->manage_power(desc->intf, 1); + + /* tx is allowed */ + wwan_port_txon(port); + + /* Start getting events */ + return usb_submit_urb(desc->validity, GFP_KERNEL); +} + +static void wdm_wwan_port_stop(struct wwan_port *port) +{ + struct wdm_device *desc = wwan_port_get_drvdata(port); + + /* Stop all transfers and disable WWAN mode */ + poison_urbs(desc); + desc->manage_power(desc->intf, 0); + clear_bit(WDM_READ, &desc->flags); + clear_bit(WDM_WWAN_IN_USE, &desc->flags); + unpoison_urbs(desc); +} + +static void wdm_wwan_port_tx_complete(struct urb *urb) +{ + struct sk_buff *skb = urb->context; + struct wdm_device *desc = skb_shinfo(skb)->destructor_arg; + + usb_autopm_put_interface(desc->intf); + wwan_port_txon(desc->wwanp); + kfree_skb(skb); +} + +static int wdm_wwan_port_tx(struct wwan_port *port, struct sk_buff *skb) +{ + struct wdm_device *desc = wwan_port_get_drvdata(port); + struct usb_interface *intf = desc->intf; + struct usb_ctrlrequest *req = desc->orq; + int rv; + + rv = usb_autopm_get_interface(intf); + if (rv) + return rv; + + usb_fill_control_urb( + desc->command, + interface_to_usbdev(intf), + usb_sndctrlpipe(interface_to_usbdev(intf), 0), + (unsigned char *)req, + skb->data, + skb->len, + wdm_wwan_port_tx_complete, + skb + ); + + req->bRequestType = (USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE); + req->bRequest = USB_CDC_SEND_ENCAPSULATED_COMMAND; + req->wValue = 0; + req->wIndex = desc->inum; + req->wLength = cpu_to_le16(skb->len); + + skb_shinfo(skb)->destructor_arg = desc; + + rv = usb_submit_urb(desc->command, GFP_KERNEL); + if (rv) + usb_autopm_put_interface(intf); + else /* One transfer at a time, stop TX until URB completion */ + wwan_port_txoff(port); + + return rv; +} + +static struct wwan_port_ops wdm_wwan_port_ops = { + .start = wdm_wwan_port_start, + .stop = wdm_wwan_port_stop, + .tx = wdm_wwan_port_tx, +}; + +static void wdm_wwan_init(struct wdm_device *desc) +{ + struct usb_interface *intf = desc->intf; + struct wwan_port *port; + + /* Only register to WWAN core if protocol/type is known */ + if (desc->wwanp_type == WWAN_PORT_UNKNOWN) { + dev_info(&intf->dev, "Unknown control protocol\n"); + return; + } + + port = wwan_create_port(&intf->dev, desc->wwanp_type, &wdm_wwan_port_ops, desc); + if (IS_ERR(port)) { + dev_err(&intf->dev, "%s: Unable to create WWAN port\n", + dev_name(intf->usb_dev)); + return; + } + + desc->wwanp = port; +} + +static void wdm_wwan_deinit(struct wdm_device *desc) +{ + if (!desc->wwanp) + return; + + wwan_remove_port(desc->wwanp); + desc->wwanp = NULL; +} + +static void wdm_wwan_rx(struct wdm_device *desc, int length) +{ + struct wwan_port *port = desc->wwanp; + struct sk_buff *skb; + + /* Forward data to WWAN port */ + skb = alloc_skb(length, GFP_ATOMIC); + if (!skb) + return; + + memcpy(skb_put(skb, length), desc->inbuf, length); + wwan_port_rx(port, skb); + + /* inbuf has been copied, it is safe to check for outstanding data */ + schedule_work(&desc->service_outs_intr); +} +#else /* CONFIG_WWAN */ +static void wdm_wwan_init(struct wdm_device *desc) {} +static void wdm_wwan_deinit(struct wdm_device *desc) {} +static void wdm_wwan_rx(struct wdm_device *desc, int length) {} +#endif /* CONFIG_WWAN */ + /* --- error handling --- */ static void wdm_rxwork(struct work_struct *work) { @@ -848,7 +1013,8 @@ static void service_interrupt_work(struct work_struct *work) /* --- hotplug --- */ static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor *ep, - u16 bufsize, int (*manage_power)(struct usb_interface *, int)) + u16 bufsize, enum wwan_port_type type, + int (*manage_power)(struct usb_interface *, int)) { int rv = -ENOMEM; struct wdm_device *desc; @@ -865,6 +1031,7 @@ static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor /* this will be expanded and needed in hardware endianness */ desc->inum = cpu_to_le16((u16)intf->cur_altsetting->desc.bInterfaceNumber); desc->intf = intf; + desc->wwanp_type = type; INIT_WORK(&desc->rxwork, wdm_rxwork); INIT_WORK(&desc->service_outs_intr, service_interrupt_work); @@ -945,6 +1112,9 @@ static int wdm_create(struct usb_interface *intf, struct usb_endpoint_descriptor goto err; else dev_info(&intf->dev, "%s: USB WDM device\n", dev_name(intf->usb_dev)); + + wdm_wwan_init(desc); + out: return rv; err: @@ -989,7 +1159,7 @@ static int wdm_probe(struct usb_interface *intf, const struct usb_device_id *id) goto err; ep = &iface->endpoint[0].desc; - rv = wdm_create(intf, ep, maxcom, &wdm_manage_power); + rv = wdm_create(intf, ep, maxcom, WWAN_PORT_UNKNOWN, &wdm_manage_power); err: return rv; @@ -1000,6 +1170,7 @@ err: * @intf: usb interface the subdriver will associate with * @ep: interrupt endpoint to monitor for notifications * @bufsize: maximum message size to support for read/write + * @type: Type/protocol of the transported data (MBIM, QMI...) * @manage_power: call-back invoked during open and release to * manage the device's power * Create WDM usb class character device and associate it with intf @@ -1017,12 +1188,12 @@ err: */ struct usb_driver *usb_cdc_wdm_register(struct usb_interface *intf, struct usb_endpoint_descriptor *ep, - int bufsize, + int bufsize, enum wwan_port_type type, int (*manage_power)(struct usb_interface *, int)) { int rv; - rv = wdm_create(intf, ep, bufsize, manage_power); + rv = wdm_create(intf, ep, bufsize, type, manage_power); if (rv < 0) goto err; @@ -1041,6 +1212,8 @@ static void wdm_disconnect(struct usb_interface *intf) desc = wdm_find_device(intf); mutex_lock(&wdm_mutex); + wdm_wwan_deinit(desc); + /* the spinlock makes sure no new urbs are generated in the callbacks */ spin_lock_irqsave(&desc->iuspin, flags); set_bit(WDM_DISCONNECTING, &desc->flags); diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index 50bb91b6a4b8..c7387677a26a 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -917,7 +917,6 @@ static int tegra_xusb_load_firmware(struct tegra_xusb *tegra) struct xhci_op_regs __iomem *op; unsigned long timeout; time64_t timestamp; - struct tm time; u64 address; u32 value; int err; @@ -1014,11 +1013,8 @@ static int tegra_xusb_load_firmware(struct tegra_xusb *tegra) } timestamp = le32_to_cpu(header->fwimg_created_time); - time64_to_tm(timestamp, 0, &time); - dev_info(dev, "Firmware timestamp: %ld-%02d-%02d %02d:%02d:%02d UTC\n", - time.tm_year + 1900, time.tm_mon + 1, time.tm_mday, - time.tm_hour, time.tm_min, time.tm_sec); + dev_info(dev, "Firmware timestamp: %ptTs UTC\n", ×tamp); return 0; } diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index a3e925a41b0d..4fce73a8a650 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -567,7 +567,7 @@ static int vaddr_get_pfns(struct mm_struct *mm, unsigned long vaddr, vaddr = untagged_addr(vaddr); retry: - vma = find_vma_intersection(mm, vaddr, vaddr + 1); + vma = vma_lookup(mm, vaddr); if (vma && vma->vm_flags & VM_PFNMAP) { ret = follow_fault_pfn(vma, mm, vaddr, pfn, prot & IOMMU_WRITE); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index df82b124170e..6414bd5741b8 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -744,11 +744,9 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, if (copied != len) return -EFAULT; - xdp->data_hard_start = buf; - xdp->data = buf + pad; - xdp->data_end = xdp->data + len; + xdp_init_buff(xdp, buflen, NULL); + xdp_prepare_buff(xdp, buf, pad, len, true); hdr->buflen = buflen; - xdp->frame_sz = buflen; --net->refcnt_bias; alloc_frag->offset += buflen; diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 5e78fb719602..d38c996b4f46 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -31,7 +31,8 @@ enum { VHOST_VSOCK_FEATURES = VHOST_FEATURES | - (1ULL << VIRTIO_F_ACCESS_PLATFORM) + (1ULL << VIRTIO_F_ACCESS_PLATFORM) | + (1ULL << VIRTIO_VSOCK_F_SEQPACKET) }; enum { @@ -56,6 +57,7 @@ struct vhost_vsock { atomic_t queued_replies; u32 guest_cid; + bool seqpacket_allow; }; static u32 vhost_transport_get_local_cid(void) @@ -112,6 +114,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, size_t nbytes; size_t iov_len, payload_len; int head; + bool restore_flag = false; spin_lock_bh(&vsock->send_pkt_list_lock); if (list_empty(&vsock->send_pkt_list)) { @@ -168,9 +171,26 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, /* If the packet is greater than the space available in the * buffer, we split it using multiple buffers. */ - if (payload_len > iov_len - sizeof(pkt->hdr)) + if (payload_len > iov_len - sizeof(pkt->hdr)) { payload_len = iov_len - sizeof(pkt->hdr); + /* As we are copying pieces of large packet's buffer to + * small rx buffers, headers of packets in rx queue are + * created dynamically and are initialized with header + * of current packet(except length). But in case of + * SOCK_SEQPACKET, we also must clear record delimeter + * bit(VIRTIO_VSOCK_SEQ_EOR). Otherwise, instead of one + * packet with delimeter(which marks end of record), + * there will be sequence of packets with delimeter + * bit set. After initialized header will be copied to + * rx buffer, this bit will be restored. + */ + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) { + pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); + restore_flag = true; + } + } + /* Set the correct length in the header */ pkt->hdr.len = cpu_to_le32(payload_len); @@ -204,6 +224,9 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, * to send it with the next available buffer. */ if (pkt->off < pkt->len) { + if (restore_flag) + pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); + /* We are queueing the same virtio_vsock_pkt to handle * the remaining bytes, and we want to deliver it * to monitoring devices in the next iteration. @@ -354,8 +377,7 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq, return NULL; } - if (le16_to_cpu(pkt->hdr.type) == VIRTIO_VSOCK_TYPE_STREAM) - pkt->len = le32_to_cpu(pkt->hdr.len); + pkt->len = le32_to_cpu(pkt->hdr.len); /* No payload */ if (!pkt->len) @@ -398,6 +420,8 @@ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock) return val < vq->num; } +static bool vhost_transport_seqpacket_allow(u32 remote_cid); + static struct virtio_transport vhost_transport = { .transport = { .module = THIS_MODULE, @@ -424,6 +448,11 @@ static struct virtio_transport vhost_transport = { .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, + .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, + .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, + .seqpacket_allow = vhost_transport_seqpacket_allow, + .seqpacket_has_data = virtio_transport_seqpacket_has_data, + .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, @@ -441,6 +470,22 @@ static struct virtio_transport vhost_transport = { .send_pkt = vhost_transport_send_pkt, }; +static bool vhost_transport_seqpacket_allow(u32 remote_cid) +{ + struct vhost_vsock *vsock; + bool seqpacket_allow = false; + + rcu_read_lock(); + vsock = vhost_vsock_get(remote_cid); + + if (vsock) + seqpacket_allow = vsock->seqpacket_allow; + + rcu_read_unlock(); + + return seqpacket_allow; +} + static void vhost_vsock_handle_tx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, @@ -689,7 +734,7 @@ static void vhost_vsock_reset_orphans(struct sock *sk) vsk->peer_shutdown = SHUTDOWN_MASK; sk->sk_state = SS_UNCONNECTED; sk->sk_err = ECONNRESET; - sk->sk_error_report(sk); + sk_error_report(sk); } static int vhost_vsock_dev_release(struct inode *inode, struct file *file) @@ -785,6 +830,9 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features) goto err; } + if (features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET)) + vsock->seqpacket_allow = true; + for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 510e9318854d..47dce91f788c 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -993,6 +993,23 @@ static int virtballoon_probe(struct virtio_device *vdev) goto out_unregister_oom; } + /* + * The default page reporting order is @pageblock_order, which + * corresponds to 512MB in size on ARM64 when 64KB base page + * size is used. The page reporting won't be triggered if the + * freeing page can't come up with a free area like that huge. + * So we specify the page reporting order to 5, corresponding + * to 2MB. It helps to avoid THP splitting if 4KB base page + * size is used by host. + * + * Ideally, the page reporting order is selected based on the + * host's base page size. However, it needs more work to report + * that value. The hard-coded order would be fine currently. + */ +#if defined(CONFIG_ARM64) && defined(CONFIG_ARM64_64K_PAGES) + vb->pr_dev_info.order = 5; +#endif + err = page_reporting_register(&vb->pr_dev_info); if (err) goto out_unregister_oom; diff --git a/drivers/watchdog/octeon-wdt-main.c b/drivers/watchdog/octeon-wdt-main.c index fde9e739b436..391c774a1f67 100644 --- a/drivers/watchdog/octeon-wdt-main.c +++ b/drivers/watchdog/octeon-wdt-main.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index fb7ee026d101..adbb3a1edcbf 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -73,6 +73,7 @@ static sector_t _adfs_bmap(struct address_space *mapping, sector_t block) } static const struct address_space_operations adfs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = adfs_readpage, .writepage = adfs_writepage, .write_begin = adfs_write_begin, diff --git a/fs/affs/file.c b/fs/affs/file.c index d91b0133d95d..75ebd2b576ca 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -453,6 +453,7 @@ static sector_t _affs_bmap(struct address_space *mapping, sector_t block) } const struct address_space_operations affs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = affs_readpage, .writepage = affs_writepage, .write_begin = affs_write_begin, @@ -833,6 +834,7 @@ err_bh: } const struct address_space_operations affs_aops_ofs = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = affs_readpage_ofs, //.writepage = affs_writepage_ofs, .write_begin = affs_write_begin_ofs, diff --git a/fs/bfs/file.c b/fs/bfs/file.c index 0dceefc54b48..7f8544abf636 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -188,6 +188,7 @@ static sector_t bfs_bmap(struct address_space *mapping, sector_t block) } const struct address_space_operations bfs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = bfs_readpage, .writepage = bfs_writepage, .write_begin = bfs_write_begin, diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 3e84e9bb9084..145917f734fe 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -222,7 +222,7 @@ static int load_aout_binary(struct linux_binprm * bprm) error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text, PROT_READ | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE, + MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE, fd_offset); if (error != N_TXTADDR(ex)) @@ -230,7 +230,7 @@ static int load_aout_binary(struct linux_binprm * bprm) error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data, PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE, + MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE, fd_offset + ex.a_text); if (error != N_DATADDR(ex)) return error; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 3d73cbb439fa..439ed81e755a 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1070,7 +1070,7 @@ out_free_interp: elf_prot = make_prot(elf_ppnt->p_flags, &arch_state, !!interpreter, false); - elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE; + elf_flags = MAP_PRIVATE | MAP_DENYWRITE; vaddr = elf_ppnt->p_vaddr; /* diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index ab9c31ddffda..cf4028487dcc 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -928,7 +928,7 @@ static int elf_fdpic_map_file_constdisp_on_uclinux( { struct elf32_fdpic_loadseg *seg; struct elf32_phdr *phdr; - unsigned long load_addr, base = ULONG_MAX, top = 0, maddr = 0, mflags; + unsigned long load_addr, base = ULONG_MAX, top = 0, maddr = 0; int loop, ret; load_addr = params->load_addr; @@ -948,12 +948,8 @@ static int elf_fdpic_map_file_constdisp_on_uclinux( } /* allocate one big anon block for everything */ - mflags = MAP_PRIVATE; - if (params->flags & ELF_FDPIC_FLAG_EXECUTABLE) - mflags |= MAP_EXECUTABLE; - maddr = vm_mmap(NULL, load_addr, top - base, - PROT_READ | PROT_WRITE | PROT_EXEC, mflags, 0); + PROT_READ | PROT_WRITE | PROT_EXEC, MAP_PRIVATE, 0); if (IS_ERR_VALUE(maddr)) return (int) maddr; @@ -1046,9 +1042,6 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, if (phdr->p_flags & PF_X) prot |= PROT_EXEC; flags = MAP_PRIVATE | MAP_DENYWRITE; - if (params->flags & ELF_FDPIC_FLAG_EXECUTABLE) - flags |= MAP_EXECUTABLE; - maddr = 0; switch (params->flags & ELF_FDPIC_FLAG_ARRANGEMENT) { diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index a1072c6a2341..5d776f80ee50 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -573,7 +573,7 @@ static int load_flat_file(struct linux_binprm *bprm, pr_debug("ROM mapping of file (we hope)\n"); textpos = vm_mmap(bprm->file, 0, text_len, PROT_READ|PROT_EXEC, - MAP_PRIVATE|MAP_EXECUTABLE, 0); + MAP_PRIVATE, 0); if (!textpos || IS_ERR_VALUE(textpos)) { ret = textpos; if (!textpos) diff --git a/fs/block_dev.c b/fs/block_dev.c index 6cc4d4cfe0c2..7e83c3e71504 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -895,7 +895,6 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) mapping_set_gfp_mask(&inode->i_data, GFP_USER); bdev = I_BDEV(inode); - mutex_init(&bdev->bd_mutex); mutex_init(&bdev->bd_fsfreeze_mutex); spin_lock_init(&bdev->bd_size_lock); bdev->bd_disk = disk; @@ -1154,7 +1153,7 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) struct bd_holder_disk *holder; int ret = 0; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); WARN_ON_ONCE(!bdev->bd_holder); @@ -1199,7 +1198,7 @@ out_del: out_free: kfree(holder); out_unlock: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); return ret; } EXPORT_SYMBOL_GPL(bd_link_disk_holder); @@ -1218,7 +1217,7 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) { struct bd_holder_disk *holder; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); holder = bd_find_holder_disk(bdev, disk); @@ -1230,138 +1229,97 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) kfree(holder); } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); } EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); #endif -static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); - -int bdev_disk_changed(struct block_device *bdev, bool invalidate) +static void blkdev_flush_mapping(struct block_device *bdev) { - struct gendisk *disk = bdev->bd_disk; - int ret = 0; - - lockdep_assert_held(&bdev->bd_mutex); - - if (!(disk->flags & GENHD_FL_UP)) - return -ENXIO; - -rescan: - if (bdev->bd_part_count) - return -EBUSY; + WARN_ON_ONCE(bdev->bd_holders); sync_blockdev(bdev); - invalidate_bdev(bdev); - blk_drop_partitions(disk); - - clear_bit(GD_NEED_PART_SCAN, &disk->state); - - /* - * Historically we only set the capacity to zero for devices that - * support partitions (independ of actually having partitions created). - * Doing that is rather inconsistent, but changing it broke legacy - * udisks polling for legacy ide-cdrom devices. Use the crude check - * below to get the sane behavior for most device while not breaking - * userspace for this particular setup. - */ - if (invalidate) { - if (disk_part_scan_enabled(disk) || - !(disk->flags & GENHD_FL_REMOVABLE)) - set_capacity(disk, 0); - } - - if (get_capacity(disk)) { - ret = blk_add_partitions(disk, bdev); - if (ret == -EAGAIN) - goto rescan; - } else if (invalidate) { - /* - * Tell userspace that the media / partition table may have - * changed. - */ - kobject_uevent(&disk_to_dev(disk)->kobj, KOBJ_CHANGE); - } - - return ret; + kill_bdev(bdev); + bdev_write_inode(bdev); } -/* - * Only exported for loop and dasd for historic reasons. Don't use in new - * code! - */ -EXPORT_SYMBOL_GPL(bdev_disk_changed); -/* - * bd_mutex locking: - * - * mutex_lock(part->bd_mutex) - * mutex_lock_nested(whole->bd_mutex, 1) - */ -static int __blkdev_get(struct block_device *bdev, fmode_t mode) +static int blkdev_get_whole(struct block_device *bdev, fmode_t mode) { struct gendisk *disk = bdev->bd_disk; int ret = 0; - if (!(disk->flags & GENHD_FL_UP)) - return -ENXIO; + if (disk->fops->open) { + ret = disk->fops->open(bdev, mode); + if (ret) { + /* avoid ghost partitions on a removed medium */ + if (ret == -ENOMEDIUM && + test_bit(GD_NEED_PART_SCAN, &disk->state)) + bdev_disk_changed(disk, true); + return ret; + } + } if (!bdev->bd_openers) { - if (!bdev_is_partition(bdev)) { - ret = 0; - if (disk->fops->open) - ret = disk->fops->open(bdev, mode); - - if (!ret) - set_init_blocksize(bdev); - - /* - * If the device is invalidated, rescan partition - * if open succeeded or failed with -ENOMEDIUM. - * The latter is necessary to prevent ghost - * partitions on a removed medium. - */ - if (test_bit(GD_NEED_PART_SCAN, &disk->state) && - (!ret || ret == -ENOMEDIUM)) - bdev_disk_changed(bdev, ret == -ENOMEDIUM); - - if (ret) - return ret; - } else { - struct block_device *whole = bdgrab(disk->part0); - - mutex_lock_nested(&whole->bd_mutex, 1); - ret = __blkdev_get(whole, mode); - if (ret) { - mutex_unlock(&whole->bd_mutex); - bdput(whole); - return ret; - } - whole->bd_part_count++; - mutex_unlock(&whole->bd_mutex); - - if (!bdev_nr_sectors(bdev)) { - __blkdev_put(whole, mode, 1); - bdput(whole); - return -ENXIO; - } - set_init_blocksize(bdev); - } - + set_init_blocksize(bdev); if (bdev->bd_bdi == &noop_backing_dev_info) bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info); - } else { - if (!bdev_is_partition(bdev)) { - if (bdev->bd_disk->fops->open) - ret = bdev->bd_disk->fops->open(bdev, mode); - /* the same as first opener case, read comment there */ - if (test_bit(GD_NEED_PART_SCAN, &disk->state) && - (!ret || ret == -ENOMEDIUM)) - bdev_disk_changed(bdev, ret == -ENOMEDIUM); - if (ret) - return ret; - } } + if (test_bit(GD_NEED_PART_SCAN, &disk->state)) + bdev_disk_changed(disk, false); bdev->bd_openers++; + return 0;; +} + +static void blkdev_put_whole(struct block_device *bdev, fmode_t mode) +{ + if (!--bdev->bd_openers) + blkdev_flush_mapping(bdev); + if (bdev->bd_disk->fops->release) + bdev->bd_disk->fops->release(bdev->bd_disk, mode); +} + +static int blkdev_get_part(struct block_device *part, fmode_t mode) +{ + struct gendisk *disk = part->bd_disk; + struct block_device *whole; + int ret; + + if (part->bd_openers) + goto done; + + whole = bdgrab(disk->part0); + ret = blkdev_get_whole(whole, mode); + if (ret) + goto out_put_whole; + + ret = -ENXIO; + if (!bdev_nr_sectors(part)) + goto out_blkdev_put; + + disk->open_partitions++; + set_init_blocksize(part); + if (part->bd_bdi == &noop_backing_dev_info) + part->bd_bdi = bdi_get(disk->queue->backing_dev_info); +done: + part->bd_openers++; return 0; + +out_blkdev_put: + blkdev_put_whole(whole, mode); +out_put_whole: + bdput(whole); + return ret; +} + +static void blkdev_put_part(struct block_device *part, fmode_t mode) +{ + struct block_device *whole = bdev_whole(part); + + if (--part->bd_openers) + return; + blkdev_flush_mapping(part); + whole->bd_disk->open_partitions--; + blkdev_put_whole(whole, mode); + bdput(whole); } struct block_device *blkdev_get_no_open(dev_t dev) @@ -1447,8 +1405,14 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) disk_block_events(disk); - mutex_lock(&bdev->bd_mutex); - ret =__blkdev_get(bdev, mode); + mutex_lock(&disk->open_mutex); + ret = -ENXIO; + if (!(disk->flags & GENHD_FL_UP)) + goto abort_claiming; + if (bdev_is_partition(bdev)) + ret = blkdev_get_part(bdev, mode); + else + ret = blkdev_get_whole(bdev, mode); if (ret) goto abort_claiming; if (mode & FMODE_EXCL) { @@ -1467,7 +1431,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) unblock_events = false; } } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&disk->open_mutex); if (unblock_events) disk_unblock_events(disk); @@ -1476,7 +1440,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) abort_claiming: if (mode & FMODE_EXCL) bd_abort_claiming(bdev, holder); - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&disk->open_mutex); disk_unblock_events(disk); put_blkdev: blkdev_put_no_open(bdev); @@ -1551,10 +1515,9 @@ static int blkdev_open(struct inode * inode, struct file * filp) return 0; } -static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) +void blkdev_put(struct block_device *bdev, fmode_t mode) { struct gendisk *disk = bdev->bd_disk; - struct block_device *victim = NULL; /* * Sync early if it looks like we're the last one. If someone else @@ -1566,41 +1529,14 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part) if (bdev->bd_openers == 1) sync_blockdev(bdev); - mutex_lock_nested(&bdev->bd_mutex, for_part); - if (for_part) - bdev->bd_part_count--; - - if (!--bdev->bd_openers) { - WARN_ON_ONCE(bdev->bd_holders); - sync_blockdev(bdev); - kill_bdev(bdev); - bdev_write_inode(bdev); - if (bdev_is_partition(bdev)) - victim = bdev_whole(bdev); - } - - if (!bdev_is_partition(bdev) && disk->fops->release) - disk->fops->release(disk, mode); - mutex_unlock(&bdev->bd_mutex); - if (victim) { - __blkdev_put(victim, mode, 1); - bdput(victim); - } -} - -void blkdev_put(struct block_device *bdev, fmode_t mode) -{ - struct gendisk *disk = bdev->bd_disk; - - mutex_lock(&bdev->bd_mutex); - + mutex_lock(&disk->open_mutex); if (mode & FMODE_EXCL) { struct block_device *whole = bdev_whole(bdev); bool bdev_free; /* * Release a claim on the device. The holder fields - * are protected with bdev_lock. bd_mutex is to + * are protected with bdev_lock. open_mutex is to * synchronize disk_holder unlinking. */ spin_lock(&bdev_lock); @@ -1631,9 +1567,13 @@ void blkdev_put(struct block_device *bdev, fmode_t mode) * from userland - e.g. eject(1). */ disk_flush_events(disk, DISK_EVENT_MEDIA_CHANGE); - mutex_unlock(&bdev->bd_mutex); - __blkdev_put(bdev, mode, 0); + if (bdev_is_partition(bdev)) + blkdev_put_part(bdev, mode); + else + blkdev_put_whole(bdev, mode); + mutex_unlock(&disk->open_mutex); + blkdev_put_no_open(bdev); } EXPORT_SYMBOL(blkdev_put); @@ -1733,20 +1673,6 @@ ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) } EXPORT_SYMBOL_GPL(blkdev_read_iter); -/* - * Try to release a page associated with block device when the system - * is under memory pressure. - */ -static int blkdev_releasepage(struct page *page, gfp_t wait) -{ - struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super; - - if (super && super->s_op->bdev_try_to_free_page) - return super->s_op->bdev_try_to_free_page(super, page, wait); - - return try_to_free_buffers(page); -} - static int blkdev_writepages(struct address_space *mapping, struct writeback_control *wbc) { @@ -1754,13 +1680,13 @@ static int blkdev_writepages(struct address_space *mapping, } static const struct address_space_operations def_blk_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = blkdev_readpage, .readahead = blkdev_readahead, .writepage = blkdev_writepage, .write_begin = blkdev_write_begin, .write_end = blkdev_write_end, .writepages = blkdev_writepages, - .releasepage = blkdev_releasepage, .direct_IO = blkdev_direct_IO, .migratepage = buffer_migrate_page_norefs, .is_dirty_writeback = buffer_check_dirty_writeback, @@ -1940,10 +1866,10 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) old_inode = inode; bdev = I_BDEV(inode); - mutex_lock(&bdev->bd_mutex); + mutex_lock(&bdev->bd_disk->open_mutex); if (bdev->bd_openers) func(bdev, arg); - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&bdev->bd_disk->open_mutex); spin_lock(&blockdev_superblock->s_inode_list_lock); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 782e16795bc4..807502cd6510 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1247,7 +1247,7 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, lockdep_assert_held(&uuid_mutex); /* * The device_list_mutex cannot be taken here in case opening the - * underlying device takes further locks like bd_mutex. + * underlying device takes further locks like open_mutex. * * We also don't need the lock here as this is called during mount and * exclusion is provided by uuid_mutex diff --git a/fs/buffer.c b/fs/buffer.c index ea48c01fb76b..6290c3afdba4 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -588,31 +588,6 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) } EXPORT_SYMBOL(mark_buffer_dirty_inode); -/* - * Mark the page dirty, and set it dirty in the page cache, and mark the inode - * dirty. - * - * If warn is true, then emit a warning if the page is not uptodate and has - * not been truncated. - * - * The caller must hold lock_page_memcg(). - */ -void __set_page_dirty(struct page *page, struct address_space *mapping, - int warn) -{ - unsigned long flags; - - xa_lock_irqsave(&mapping->i_pages, flags); - if (page->mapping) { /* Race with truncate? */ - WARN_ON_ONCE(warn && !PageUptodate(page)); - account_page_dirtied(page, mapping); - __xa_set_mark(&mapping->i_pages, page_index(page), - PAGECACHE_TAG_DIRTY); - } - xa_unlock_irqrestore(&mapping->i_pages, flags); -} -EXPORT_SYMBOL_GPL(__set_page_dirty); - /* * Add a page to the dirty page list. * diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index bf52e9326ebe..7364950a9ef4 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -19,6 +19,8 @@ config CIFS select CRYPTO_LIB_DES select KEYS select DNS_RESOLVER + select ASN1 + select OID_REGISTRY help This is the client VFS module for the SMB3 family of NAS protocols, (including support for the most recent, most secure dialect SMB3.1.1) @@ -57,6 +59,7 @@ config CIFS config CIFS_STATS2 bool "Extended statistics" depends on CIFS + default y help Enabling this option will allow more detailed statistics on SMB request timing to be displayed in /proc/fs/cifs/DebugData and also @@ -65,8 +68,7 @@ config CIFS_STATS2 for more details. These additional statistics may have a minor effect on performance and memory utilization. - Unless you are a developer or are doing network performance analysis - or tuning, say N. + If unsure, say Y. config CIFS_ALLOW_INSECURE_LEGACY bool "Support legacy servers which use less secure dialects" diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile index 3ee3b7de4ded..87fcacdf3de7 100644 --- a/fs/cifs/Makefile +++ b/fs/cifs/Makefile @@ -6,12 +6,16 @@ ccflags-y += -I$(src) # needed for trace events obj-$(CONFIG_CIFS) += cifs.o cifs-y := trace.o cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o \ - inode.o link.o misc.o netmisc.o smbencrypt.o transport.o asn1.o \ + inode.o link.o misc.o netmisc.o smbencrypt.o transport.o \ cifs_unicode.o nterr.o cifsencrypt.o \ readdir.o ioctl.o sess.o export.o smb1ops.o unc.o winucase.o \ smb2ops.o smb2maperror.o smb2transport.o \ smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o \ - dns_resolve.o + dns_resolve.o cifs_spnego_negtokeninit.asn1.o asn1.o + +$(obj)/asn1.o: $(obj)/cifs_spnego_negtokeninit.asn1.h + +$(obj)/cifs_spnego_negtokeninit.asn1.o: $(obj)/cifs_spnego_negtokeninit.asn1.c $(obj)/cifs_spnego_negtokeninit.asn1.h cifs-$(CONFIG_CIFS_XATTR) += xattr.o diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c index 3150c19cdc2f..b5724ef9f182 100644 --- a/fs/cifs/asn1.c +++ b/fs/cifs/asn1.c @@ -1,612 +1,63 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/* - * The ASB.1/BER parsing code is derived from ip_nat_snmp_basic.c which was in - * turn derived from the gxsnmp package by Gregory McLean & Jochen Friedrich - * - * Copyright (c) 2000 RP Internet (www.rpi.net.au). - */ #include -#include #include -#include -#include -#include "cifspdu.h" +#include #include "cifsglob.h" #include "cifs_debug.h" #include "cifsproto.h" - -/***************************************************************************** - * - * Basic ASN.1 decoding routines (gxsnmp author Dirk Wisse) - * - *****************************************************************************/ - -/* Class */ -#define ASN1_UNI 0 /* Universal */ -#define ASN1_APL 1 /* Application */ -#define ASN1_CTX 2 /* Context */ -#define ASN1_PRV 3 /* Private */ - -/* Tag */ -#define ASN1_EOC 0 /* End Of Contents or N/A */ -#define ASN1_BOL 1 /* Boolean */ -#define ASN1_INT 2 /* Integer */ -#define ASN1_BTS 3 /* Bit String */ -#define ASN1_OTS 4 /* Octet String */ -#define ASN1_NUL 5 /* Null */ -#define ASN1_OJI 6 /* Object Identifier */ -#define ASN1_OJD 7 /* Object Description */ -#define ASN1_EXT 8 /* External */ -#define ASN1_ENUM 10 /* Enumerated */ -#define ASN1_SEQ 16 /* Sequence */ -#define ASN1_SET 17 /* Set */ -#define ASN1_NUMSTR 18 /* Numerical String */ -#define ASN1_PRNSTR 19 /* Printable String */ -#define ASN1_TEXSTR 20 /* Teletext String */ -#define ASN1_VIDSTR 21 /* Video String */ -#define ASN1_IA5STR 22 /* IA5 String */ -#define ASN1_UNITIM 23 /* Universal Time */ -#define ASN1_GENTIM 24 /* General Time */ -#define ASN1_GRASTR 25 /* Graphical String */ -#define ASN1_VISSTR 26 /* Visible String */ -#define ASN1_GENSTR 27 /* General String */ - -/* Primitive / Constructed methods*/ -#define ASN1_PRI 0 /* Primitive */ -#define ASN1_CON 1 /* Constructed */ - -/* - * Error codes. - */ -#define ASN1_ERR_NOERROR 0 -#define ASN1_ERR_DEC_EMPTY 2 -#define ASN1_ERR_DEC_EOC_MISMATCH 3 -#define ASN1_ERR_DEC_LENGTH_MISMATCH 4 -#define ASN1_ERR_DEC_BADVALUE 5 - -#define SPNEGO_OID_LEN 7 -#define NTLMSSP_OID_LEN 10 -#define KRB5_OID_LEN 7 -#define KRB5U2U_OID_LEN 8 -#define MSKRB5_OID_LEN 7 -static unsigned long SPNEGO_OID[7] = { 1, 3, 6, 1, 5, 5, 2 }; -static unsigned long NTLMSSP_OID[10] = { 1, 3, 6, 1, 4, 1, 311, 2, 2, 10 }; -static unsigned long KRB5_OID[7] = { 1, 2, 840, 113554, 1, 2, 2 }; -static unsigned long KRB5U2U_OID[8] = { 1, 2, 840, 113554, 1, 2, 2, 3 }; -static unsigned long MSKRB5_OID[7] = { 1, 2, 840, 48018, 1, 2, 2 }; - -/* - * ASN.1 context. - */ -struct asn1_ctx { - int error; /* Error condition */ - unsigned char *pointer; /* Octet just to be decoded */ - unsigned char *begin; /* First octet */ - unsigned char *end; /* Octet after last octet */ -}; - -/* - * Octet string (not null terminated) - */ -struct asn1_octstr { - unsigned char *data; - unsigned int len; -}; - -static void -asn1_open(struct asn1_ctx *ctx, unsigned char *buf, unsigned int len) -{ - ctx->begin = buf; - ctx->end = buf + len; - ctx->pointer = buf; - ctx->error = ASN1_ERR_NOERROR; -} - -static unsigned char -asn1_octet_decode(struct asn1_ctx *ctx, unsigned char *ch) -{ - if (ctx->pointer >= ctx->end) { - ctx->error = ASN1_ERR_DEC_EMPTY; - return 0; - } - *ch = *(ctx->pointer)++; - return 1; -} - -#if 0 /* will be needed later by spnego decoding/encoding of ntlmssp */ -static unsigned char -asn1_enum_decode(struct asn1_ctx *ctx, __le32 *val) -{ - unsigned char ch; - - if (ctx->pointer >= ctx->end) { - ctx->error = ASN1_ERR_DEC_EMPTY; - return 0; - } - - ch = *(ctx->pointer)++; /* ch has 0xa, ptr points to length octet */ - if ((ch) == ASN1_ENUM) /* if ch value is ENUM, 0xa */ - *val = *(++(ctx->pointer)); /* value has enum value */ - else - return 0; - - ctx->pointer++; - return 1; -} -#endif - -static unsigned char -asn1_tag_decode(struct asn1_ctx *ctx, unsigned int *tag) -{ - unsigned char ch; - - *tag = 0; - - do { - if (!asn1_octet_decode(ctx, &ch)) - return 0; - *tag <<= 7; - *tag |= ch & 0x7F; - } while ((ch & 0x80) == 0x80); - return 1; -} - -static unsigned char -asn1_id_decode(struct asn1_ctx *ctx, - unsigned int *cls, unsigned int *con, unsigned int *tag) -{ - unsigned char ch; - - if (!asn1_octet_decode(ctx, &ch)) - return 0; - - *cls = (ch & 0xC0) >> 6; - *con = (ch & 0x20) >> 5; - *tag = (ch & 0x1F); - - if (*tag == 0x1F) { - if (!asn1_tag_decode(ctx, tag)) - return 0; - } - return 1; -} - -static unsigned char -asn1_length_decode(struct asn1_ctx *ctx, unsigned int *def, unsigned int *len) -{ - unsigned char ch, cnt; - - if (!asn1_octet_decode(ctx, &ch)) - return 0; - - if (ch == 0x80) - *def = 0; - else { - *def = 1; - - if (ch < 0x80) - *len = ch; - else { - cnt = (unsigned char) (ch & 0x7F); - *len = 0; - - while (cnt > 0) { - if (!asn1_octet_decode(ctx, &ch)) - return 0; - *len <<= 8; - *len |= ch; - cnt--; - } - } - } - - /* don't trust len bigger than ctx buffer */ - if (*len > ctx->end - ctx->pointer) - return 0; - - return 1; -} - -static unsigned char -asn1_header_decode(struct asn1_ctx *ctx, - unsigned char **eoc, - unsigned int *cls, unsigned int *con, unsigned int *tag) -{ - unsigned int def = 0; - unsigned int len = 0; - - if (!asn1_id_decode(ctx, cls, con, tag)) - return 0; - - if (!asn1_length_decode(ctx, &def, &len)) - return 0; - - /* primitive shall be definite, indefinite shall be constructed */ - if (*con == ASN1_PRI && !def) - return 0; - - if (def) - *eoc = ctx->pointer + len; - else - *eoc = NULL; - return 1; -} - -static unsigned char -asn1_eoc_decode(struct asn1_ctx *ctx, unsigned char *eoc) -{ - unsigned char ch; - - if (eoc == NULL) { - if (!asn1_octet_decode(ctx, &ch)) - return 0; - - if (ch != 0x00) { - ctx->error = ASN1_ERR_DEC_EOC_MISMATCH; - return 0; - } - - if (!asn1_octet_decode(ctx, &ch)) - return 0; - - if (ch != 0x00) { - ctx->error = ASN1_ERR_DEC_EOC_MISMATCH; - return 0; - } - return 1; - } else { - if (ctx->pointer != eoc) { - ctx->error = ASN1_ERR_DEC_LENGTH_MISMATCH; - return 0; - } - return 1; - } -} - -/* static unsigned char asn1_null_decode(struct asn1_ctx *ctx, - unsigned char *eoc) -{ - ctx->pointer = eoc; - return 1; -} - -static unsigned char asn1_long_decode(struct asn1_ctx *ctx, - unsigned char *eoc, long *integer) -{ - unsigned char ch; - unsigned int len; - - if (!asn1_octet_decode(ctx, &ch)) - return 0; - - *integer = (signed char) ch; - len = 1; - - while (ctx->pointer < eoc) { - if (++len > sizeof(long)) { - ctx->error = ASN1_ERR_DEC_BADVALUE; - return 0; - } - - if (!asn1_octet_decode(ctx, &ch)) - return 0; - - *integer <<= 8; - *integer |= ch; - } - return 1; -} - -static unsigned char asn1_uint_decode(struct asn1_ctx *ctx, - unsigned char *eoc, - unsigned int *integer) -{ - unsigned char ch; - unsigned int len; - - if (!asn1_octet_decode(ctx, &ch)) - return 0; - - *integer = ch; - if (ch == 0) - len = 0; - else - len = 1; - - while (ctx->pointer < eoc) { - if (++len > sizeof(unsigned int)) { - ctx->error = ASN1_ERR_DEC_BADVALUE; - return 0; - } - - if (!asn1_octet_decode(ctx, &ch)) - return 0; - - *integer <<= 8; - *integer |= ch; - } - return 1; -} - -static unsigned char asn1_ulong_decode(struct asn1_ctx *ctx, - unsigned char *eoc, - unsigned long *integer) -{ - unsigned char ch; - unsigned int len; - - if (!asn1_octet_decode(ctx, &ch)) - return 0; - - *integer = ch; - if (ch == 0) - len = 0; - else - len = 1; - - while (ctx->pointer < eoc) { - if (++len > sizeof(unsigned long)) { - ctx->error = ASN1_ERR_DEC_BADVALUE; - return 0; - } - - if (!asn1_octet_decode(ctx, &ch)) - return 0; - - *integer <<= 8; - *integer |= ch; - } - return 1; -} - -static unsigned char -asn1_octets_decode(struct asn1_ctx *ctx, - unsigned char *eoc, - unsigned char **octets, unsigned int *len) -{ - unsigned char *ptr; - - *len = 0; - - *octets = kmalloc(eoc - ctx->pointer, GFP_ATOMIC); - if (*octets == NULL) { - return 0; - } - - ptr = *octets; - while (ctx->pointer < eoc) { - if (!asn1_octet_decode(ctx, (unsigned char *) ptr++)) { - kfree(*octets); - *octets = NULL; - return 0; - } - (*len)++; - } - return 1; -} */ - -static unsigned char -asn1_subid_decode(struct asn1_ctx *ctx, unsigned long *subid) -{ - unsigned char ch; - - *subid = 0; - - do { - if (!asn1_octet_decode(ctx, &ch)) - return 0; - - *subid <<= 7; - *subid |= ch & 0x7F; - } while ((ch & 0x80) == 0x80); - return 1; -} - -static int -asn1_oid_decode(struct asn1_ctx *ctx, - unsigned char *eoc, unsigned long **oid, unsigned int *len) -{ - unsigned long subid; - unsigned int size; - unsigned long *optr; - - size = eoc - ctx->pointer + 1; - - /* first subid actually encodes first two subids */ - if (size < 2 || size > UINT_MAX/sizeof(unsigned long)) - return 0; - - *oid = kmalloc_array(size, sizeof(unsigned long), GFP_ATOMIC); - if (*oid == NULL) - return 0; - - optr = *oid; - - if (!asn1_subid_decode(ctx, &subid)) { - kfree(*oid); - *oid = NULL; - return 0; - } - - if (subid < 40) { - optr[0] = 0; - optr[1] = subid; - } else if (subid < 80) { - optr[0] = 1; - optr[1] = subid - 40; - } else { - optr[0] = 2; - optr[1] = subid - 80; - } - - *len = 2; - optr += 2; - - while (ctx->pointer < eoc) { - if (++(*len) > size) { - ctx->error = ASN1_ERR_DEC_BADVALUE; - kfree(*oid); - *oid = NULL; - return 0; - } - - if (!asn1_subid_decode(ctx, optr++)) { - kfree(*oid); - *oid = NULL; - return 0; - } - } - return 1; -} - -static int -compare_oid(unsigned long *oid1, unsigned int oid1len, - unsigned long *oid2, unsigned int oid2len) -{ - unsigned int i; - - if (oid1len != oid2len) - return 0; - else { - for (i = 0; i < oid1len; i++) { - if (oid1[i] != oid2[i]) - return 0; - } - return 1; - } -} - - /* BB check for endian conversion issues here */ +#include "cifs_spnego_negtokeninit.asn1.h" int decode_negTokenInit(unsigned char *security_blob, int length, struct TCP_Server_Info *server) { - struct asn1_ctx ctx; - unsigned char *end; - unsigned char *sequence_end; - unsigned long *oid = NULL; - unsigned int cls, con, tag, oidlen, rc; - - /* cifs_dump_mem(" Received SecBlob ", security_blob, length); */ - - asn1_open(&ctx, security_blob, length); - - /* GSSAPI header */ - if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) { - cifs_dbg(FYI, "Error decoding negTokenInit header\n"); + if (asn1_ber_decoder(&cifs_spnego_negtokeninit_decoder, server, + security_blob, length) == 0) + return 1; + else return 0; - } else if ((cls != ASN1_APL) || (con != ASN1_CON) - || (tag != ASN1_EOC)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d\n", cls, con, tag); - return 0; - } - - /* Check for SPNEGO OID -- remember to free obj->oid */ - rc = asn1_header_decode(&ctx, &end, &cls, &con, &tag); - if (rc) { - if ((tag == ASN1_OJI) && (con == ASN1_PRI) && - (cls == ASN1_UNI)) { - rc = asn1_oid_decode(&ctx, end, &oid, &oidlen); - if (rc) { - rc = compare_oid(oid, oidlen, SPNEGO_OID, - SPNEGO_OID_LEN); - kfree(oid); - } - } else - rc = 0; - } - - /* SPNEGO OID not present or garbled -- bail out */ - if (!rc) { - cifs_dbg(FYI, "Error decoding negTokenInit header\n"); - return 0; - } - - /* SPNEGO */ - if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) { - cifs_dbg(FYI, "Error decoding negTokenInit\n"); - return 0; - } else if ((cls != ASN1_CTX) || (con != ASN1_CON) - || (tag != ASN1_EOC)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p exit 0\n", - cls, con, tag, end); - return 0; - } - - /* negTokenInit */ - if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) { - cifs_dbg(FYI, "Error decoding negTokenInit\n"); - return 0; - } else if ((cls != ASN1_UNI) || (con != ASN1_CON) - || (tag != ASN1_SEQ)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p exit 1\n", - cls, con, tag, end); - return 0; - } - - /* sequence */ - if (asn1_header_decode(&ctx, &end, &cls, &con, &tag) == 0) { - cifs_dbg(FYI, "Error decoding 2nd part of negTokenInit\n"); - return 0; - } else if ((cls != ASN1_CTX) || (con != ASN1_CON) - || (tag != ASN1_EOC)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d end = %p exit 0\n", - cls, con, tag, end); - return 0; - } - - /* sequence of */ - if (asn1_header_decode - (&ctx, &sequence_end, &cls, &con, &tag) == 0) { - cifs_dbg(FYI, "Error decoding 2nd part of negTokenInit\n"); - return 0; - } else if ((cls != ASN1_UNI) || (con != ASN1_CON) - || (tag != ASN1_SEQ)) { - cifs_dbg(FYI, "cls = %d con = %d tag = %d sequence_end = %p exit 1\n", - cls, con, tag, sequence_end); - return 0; - } - - /* list of security mechanisms */ - while (!asn1_eoc_decode(&ctx, sequence_end)) { - rc = asn1_header_decode(&ctx, &end, &cls, &con, &tag); - if (!rc) { - cifs_dbg(FYI, "Error decoding negTokenInit hdr exit2\n"); - return 0; - } - if ((tag == ASN1_OJI) && (con == ASN1_PRI)) { - if (asn1_oid_decode(&ctx, end, &oid, &oidlen)) { - - cifs_dbg(FYI, "OID len = %d oid = 0x%lx 0x%lx 0x%lx 0x%lx\n", - oidlen, *oid, *(oid + 1), *(oid + 2), - *(oid + 3)); - - if (compare_oid(oid, oidlen, MSKRB5_OID, - MSKRB5_OID_LEN)) - server->sec_mskerberos = true; - else if (compare_oid(oid, oidlen, KRB5U2U_OID, - KRB5U2U_OID_LEN)) - server->sec_kerberosu2u = true; - else if (compare_oid(oid, oidlen, KRB5_OID, - KRB5_OID_LEN)) - server->sec_kerberos = true; - else if (compare_oid(oid, oidlen, NTLMSSP_OID, - NTLMSSP_OID_LEN)) - server->sec_ntlmssp = true; - - kfree(oid); - } - } else { - cifs_dbg(FYI, "Should be an oid what is going on?\n"); - } - } - - /* - * We currently ignore anything at the end of the SPNEGO blob after - * the mechTypes have been parsed, since none of that info is - * used at the moment. - */ - return 1; +} + +int cifs_gssapi_this_mech(void *context, size_t hdrlen, + unsigned char tag, const void *value, size_t vlen) +{ + enum OID oid; + + oid = look_up_OID(value, vlen); + if (oid != OID_spnego) { + char buf[50]; + + sprint_oid(value, vlen, buf, sizeof(buf)); + cifs_dbg(FYI, "Error decoding negTokenInit header: unexpected OID %s\n", + buf); + return -EBADMSG; + } + return 0; +} + +int cifs_neg_token_init_mech_type(void *context, size_t hdrlen, + unsigned char tag, + const void *value, size_t vlen) +{ + struct TCP_Server_Info *server = context; + enum OID oid; + + oid = look_up_OID(value, vlen); + if (oid == OID_mskrb5) + server->sec_mskerberos = true; + else if (oid == OID_krb5u2u) + server->sec_kerberosu2u = true; + else if (oid == OID_krb5) + server->sec_kerberos = true; + else if (oid == OID_ntlmssp) + server->sec_ntlmssp = true; + else { + char buf[50]; + + sprint_oid(value, vlen, buf, sizeof(buf)); + cifs_dbg(FYI, "Decoding negTokenInit: unsupported OID %s\n", + buf); + } + return 0; } diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c index 488fe0ffc1ef..8a3b30ec860c 100644 --- a/fs/cifs/cache.c +++ b/fs/cifs/cache.c @@ -1,22 +1,10 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/cache.c - CIFS filesystem cache index structure definitions * * Copyright (c) 2010 Novell, Inc. * Authors(s): Suresh Jayaraman (sjayaraman@suse.de> * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include "fscache.h" #include "cifs_debug.h" diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 68e8e5b27841..8857ac7e7a14 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -50,7 +50,6 @@ void cifs_dump_detail(void *buf, struct TCP_Server_Info *server) void cifs_dump_mids(struct TCP_Server_Info *server) { #ifdef CONFIG_CIFS_DEBUG2 - struct list_head *tmp; struct mid_q_entry *mid_entry; if (server == NULL) @@ -58,8 +57,7 @@ void cifs_dump_mids(struct TCP_Server_Info *server) cifs_dbg(VFS, "Dump pending requests:\n"); spin_lock(&GlobalMid_Lock); - list_for_each(tmp, &server->pending_mid_q) { - mid_entry = list_entry(tmp, struct mid_q_entry, qhead); + list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) { cifs_dbg(VFS, "State: %d Cmd: %d Pid: %d Cbdata: %p Mid %llu\n", mid_entry->mid_state, le16_to_cpu(mid_entry->command), @@ -168,7 +166,7 @@ cifs_dump_iface(struct seq_file *m, struct cifs_server_iface *iface) static int cifs_debug_files_proc_show(struct seq_file *m, void *v) { - struct list_head *stmp, *tmp, *tmp1, *tmp2; + struct list_head *tmp, *tmp1, *tmp2; struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; @@ -183,9 +181,7 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) seq_printf(m, " \n"); #endif /* CIFS_DEBUG2 */ spin_lock(&cifs_tcp_ses_lock); - list_for_each(stmp, &cifs_tcp_ses_list) { - server = list_entry(stmp, struct TCP_Server_Info, - tcp_ses_list); + list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each(tmp, &server->smb_ses_list) { ses = list_entry(tmp, struct cifs_ses, smb_ses_list); list_for_each(tmp1, &ses->tcon_list) { @@ -220,7 +216,7 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v) static int cifs_debug_data_proc_show(struct seq_file *m, void *v) { - struct list_head *tmp1, *tmp2, *tmp3; + struct list_head *tmp2, *tmp3; struct mid_q_entry *mid_entry; struct TCP_Server_Info *server; struct cifs_ses *ses; @@ -278,11 +274,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) c = 0; spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp1, &cifs_tcp_ses_list) { - server = list_entry(tmp1, struct TCP_Server_Info, - tcp_ses_list); - - /* channel info will be printed as a part of sessions below */ + list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { if (server->is_channel) continue; @@ -563,7 +555,7 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) #ifdef CONFIG_CIFS_STATS2 int j; #endif /* STATS2 */ - struct list_head *tmp1, *tmp2, *tmp3; + struct list_head *tmp2, *tmp3; struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; @@ -594,9 +586,7 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v) i = 0; spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp1, &cifs_tcp_ses_list) { - server = list_entry(tmp1, struct TCP_Server_Info, - tcp_ses_list); + list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { seq_printf(m, "\nMax requests in flight: %d", server->max_in_flight); #ifdef CONFIG_CIFS_STATS2 seq_puts(m, "\nTotal time spent processing by command. Time "); diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h index 5e66dab712d0..ee4ea2b60c0f 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/cifs/cifs_debug.h @@ -3,7 +3,7 @@ * * Copyright (c) International Business Machines Corp., 2000,2002 * Modified by Steve French (sfrench@us.ibm.com) -*/ + */ #ifndef _H_CIFS_DEBUG #define _H_CIFS_DEBUG diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index c87c37cf2914..ec57cdb1590f 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -125,7 +125,7 @@ cifs_build_devname(char *nodename, const char *prepath) * @sb_mountdata: parent/root DFS mount options (template) * @fullpath: full path in UNC format * @ref: optional server's referral - * + * @devname: return the built cifs device name if passed pointer not NULL * creates mount options for submount based on template options sb_mountdata * and replacing unc,ip,prefixpath options with ones we've got form ref_unc. * diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index 9c45b3a82ad9..4fd788586399 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -1,19 +1,10 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/cifs_fs_sb.h * * Copyright (c) International Business Machines Corp., 2002,2004 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * */ #include @@ -72,11 +63,12 @@ struct cifs_sb_info { char *prepath; /* - * Path initially provided by the mount call. We might connect - * to something different via DFS but we want to keep it to do - * failover properly. + * Canonical DFS path initially provided by the mount call. We might connect to something + * different via DFS but we want to keep it to do failover properly. */ char *origin_fullpath; /* \\HOST\SHARE\[OPTIONAL PATH] */ + /* randomly generated 128-bit number for indexing dfs mount groups in referral cache */ + uuid_t dfs_mount_id; /* * Indicate whether serverino option was turned off later * (cifs_autodisable_serverino) in order to match new mounts. diff --git a/fs/cifs/cifs_ioctl.h b/fs/cifs/cifs_ioctl.h index 37fc7d6ac457..ef723be358af 100644 --- a/fs/cifs/cifs_ioctl.h +++ b/fs/cifs/cifs_ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/cifs_ioctl.h * @@ -5,16 +6,6 @@ * * Copyright (c) 2015 Steve French * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * */ struct smb_mnt_fs_info { diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index 7b9b876b513b..8fa26a8530f8 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -1,22 +1,10 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/cifs_spnego.c -- SPNEGO upcall management for CIFS * * Copyright (c) 2007 Red Hat, Inc. * Author(s): Jeff Layton (jlayton@redhat.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include diff --git a/fs/cifs/cifs_spnego.h b/fs/cifs/cifs_spnego.h index 31bef9ee078b..31387d0ea32e 100644 --- a/fs/cifs/cifs_spnego.h +++ b/fs/cifs/cifs_spnego.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/cifs_spnego.h -- SPNEGO upcall management for CIFS * @@ -5,19 +6,6 @@ * Author(s): Jeff Layton (jlayton@redhat.com) * Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _CIFS_SPNEGO_H diff --git a/fs/cifs/cifs_spnego_negtokeninit.asn1 b/fs/cifs/cifs_spnego_negtokeninit.asn1 new file mode 100644 index 000000000000..181c083887d5 --- /dev/null +++ b/fs/cifs/cifs_spnego_negtokeninit.asn1 @@ -0,0 +1,40 @@ +GSSAPI ::= + [APPLICATION 0] IMPLICIT SEQUENCE { + thisMech + OBJECT IDENTIFIER ({cifs_gssapi_this_mech}), + negotiationToken + NegotiationToken + } + +MechType ::= OBJECT IDENTIFIER ({cifs_neg_token_init_mech_type}) + +MechTypeList ::= SEQUENCE OF MechType + +NegHints ::= SEQUENCE { + hintName + [0] GeneralString OPTIONAL, + hintAddress + [1] OCTET STRING OPTIONAL + } + +NegTokenInit2 ::= + SEQUENCE { + mechTypes + [0] MechTypeList OPTIONAL, + reqFlags + [1] BIT STRING OPTIONAL, + mechToken + [2] OCTET STRING OPTIONAL, + negHints + [3] NegHints OPTIONAL, + mechListMIC + [3] OCTET STRING OPTIONAL + } + +NegotiationToken ::= + CHOICE { + negTokenInit + [0] NegTokenInit2, + negTokenTarg + [1] ANY + } diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c index d829b8bf833e..93b47818c6c2 100644 --- a/fs/cifs/cifs_swn.c +++ b/fs/cifs/cifs_swn.c @@ -447,15 +447,13 @@ static int cifs_swn_store_swn_addr(const struct sockaddr_storage *new, const struct sockaddr_storage *old, struct sockaddr_storage *dst) { - __be16 port; + __be16 port = cpu_to_be16(CIFS_PORT); if (old->ss_family == AF_INET) { struct sockaddr_in *ipv4 = (struct sockaddr_in *)old; port = ipv4->sin_port; - } - - if (old->ss_family == AF_INET6) { + } else if (old->ss_family == AF_INET6) { struct sockaddr_in6 *ipv6 = (struct sockaddr_in6 *)old; port = ipv6->sin6_port; @@ -465,9 +463,7 @@ static int cifs_swn_store_swn_addr(const struct sockaddr_storage *new, struct sockaddr_in *ipv4 = (struct sockaddr_in *)new; ipv4->sin_port = port; - } - - if (new->ss_family == AF_INET6) { + } else if (new->ss_family == AF_INET6) { struct sockaddr_in6 *ipv6 = (struct sockaddr_in6 *)new; ipv6->sin6_port = port; diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 784407f9280f..388eb536cff1 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/cifsacl.c * @@ -6,19 +7,6 @@ * * Contains the routines for mapping CIFS/NTFS ACLs * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include @@ -409,7 +397,6 @@ try_upcall_to_get_id: saved_cred = override_creds(root_cred); sidkey = request_key(&cifs_idmap_key_type, sidstr, ""); if (IS_ERR(sidkey)) { - rc = -EINVAL; cifs_dbg(FYI, "%s: Can't map SID %s to a %cid\n", __func__, sidstr, sidtype == SIDOWNER ? 'u' : 'g'); goto out_revert_creds; @@ -422,7 +409,6 @@ try_upcall_to_get_id: */ BUILD_BUG_ON(sizeof(uid_t) != sizeof(gid_t)); if (sidkey->datalen != sizeof(uid_t)) { - rc = -EIO; cifs_dbg(FYI, "%s: Downcall contained malformed key (datalen=%hu)\n", __func__, sidkey->datalen); key_invalidate(sidkey); @@ -1308,7 +1294,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd, ndacl_ptr = (struct cifs_acl *)((char *)pnntsd + ndacloffset); ndacl_ptr->revision = dacloffset ? dacl_ptr->revision : cpu_to_le16(ACL_REVISION); - ndacl_ptr->num_aces = dacl_ptr->num_aces; + ndacl_ptr->num_aces = dacl_ptr ? dacl_ptr->num_aces : 0; if (uid_valid(uid)) { /* chown */ uid_t id; diff --git a/fs/cifs/cifsacl.h b/fs/cifs/cifsacl.h index d9e704979d99..f8292bcf8594 100644 --- a/fs/cifs/cifsacl.h +++ b/fs/cifs/cifsacl.h @@ -1,28 +1,15 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/cifsacl.h * * Copyright (c) International Business Machines Corp., 2007 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _CIFSACL_H #define _CIFSACL_H - #define NUM_AUTHS (6) /* number of authority fields */ #define SID_MAX_SUB_AUTHORITIES (15) /* max number of sub authority fields */ diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index b8f1ff9a83f3..ecf15d845dbd 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/cifsencrypt.c * @@ -7,19 +8,6 @@ * Copyright (C) International Business Machines Corp., 2005,2013 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 2ffcb29d5c8f..9fb874dd8d24 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/cifsfs.c * @@ -6,19 +7,6 @@ * * Common Internet FileSystem (CIFS) client * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* Note that BB means BUGBUG (ie something to fix eventually) */ diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 6beddb108ba0..177f3e7ab86d 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -1,22 +1,10 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/cifsfs.h * * Copyright (c) International Business Machines Corp., 2002, 2007 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _CIFSFS_H diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 8488d7024462..3100f8b66e60 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/cifsglob.h * @@ -5,16 +6,6 @@ * Author(s): Steve French (sfrench@us.ibm.com) * Jeremy Allison (jra@samba.org) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * */ #ifndef _CIFS_GLOB_H #define _CIFS_GLOB_H @@ -630,7 +621,7 @@ struct TCP_Server_Info { /* SMB_COM_WRITE_RAW or SMB_COM_READ_RAW. */ unsigned int capabilities; /* selective disabling of caps by smb sess */ int timeAdj; /* Adjust for difference in server time zone in sec */ - __u64 CurrentMid; /* multiplex id - rotating counter */ + __u64 CurrentMid; /* multiplex id - rotating counter, protected by GlobalMid_Lock */ char cryptkey[CIFS_CRYPTO_KEY_SIZE]; /* used by ntlm, ntlmv2 etc */ /* 16th byte of RFC1001 workstation name is always null */ char workstation_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL]; @@ -896,7 +887,7 @@ struct cifs_ses { struct mutex session_mutex; struct TCP_Server_Info *server; /* pointer to server info */ int ses_count; /* reference counter */ - enum statusEnum status; + enum statusEnum status; /* updates protected by GlobalMid_Lock */ unsigned overrideSecFlg; /* if non-zero override global sec flags */ char *serverOS; /* name of operating system underlying server */ char *serverNOS; /* name of network operating system of server */ @@ -1093,8 +1084,7 @@ struct cifs_tcon { struct cached_fid crfid; /* Cached root fid */ /* BB add field for back pointer to sb struct(s)? */ #ifdef CONFIG_CIFS_DFS_UPCALL - char *dfs_path; - int remap:2; + char *dfs_path; /* canonical DFS path */ struct list_head ulist; /* cache update list */ #endif }; @@ -1795,6 +1785,8 @@ require use of the stronger protocol */ * list operations on pending_mid_q and oplockQ * updates to XID counters, multiplex id and SMB sequence numbers * list operations on global DnotifyReqList + * updates to ses->status + * updates to server->CurrentMid * tcp_ses_lock protects: * list operations on tcp and SMB session lists * tcon->open_file_lock protects the list of open files hanging off the tcon diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 554d64fe171e..0923f72d27e9 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -1,22 +1,10 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/cifspdu.h * * Copyright (c) International Business Machines Corp., 2002,2009 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _CIFSPDU_H diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index d30cba44ba29..e0def0f0714b 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -1,22 +1,10 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/cifsproto.h * * Copyright (c) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _CIFSPROTO_H #define _CIFSPROTO_H diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 41f74163cc1c..58ebec4d4413 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/cifssmb.c * @@ -6,19 +7,6 @@ * * Contains the routines for constructing the SMB PDUs themselves * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* SMB/CIFS PDU handling routines here - except for leftovers in connect.c */ @@ -1220,7 +1208,7 @@ SMBLegacyOpen(const unsigned int xid, struct cifs_tcon *tcon, int *pOplock, FILE_ALL_INFO *pfile_info, const struct nls_table *nls_codepage, int remap) { - int rc = -EACCES; + int rc; OPENX_REQ *pSMB = NULL; OPENX_RSP *pSMBr = NULL; int bytes_returned; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 495c395f9def..5d269f583dac 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1,22 +1,10 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/connect.c * * Copyright (C) International Business Machines Corp., 2002,2011 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include #include @@ -368,13 +356,7 @@ cifs_reconnect(struct TCP_Server_Info *server) cifs_server_dbg(VFS, "%s: failed to update DFS target hint: rc = %d\n", __func__, rc); } - rc = dfs_cache_update_vol(cifs_sb->origin_fullpath, server); - if (rc) { - cifs_server_dbg(VFS, "%s: failed to update vol info in DFS cache: rc = %d\n", - __func__, rc); - } dfs_cache_free_tgts(&tgt_list); - } cifs_put_tcp_super(sb); @@ -1557,29 +1539,25 @@ out: /** * cifs_free_ipc - helper to release the session IPC tcon * - * Needs to be called everytime a session is destroyed + * Needs to be called everytime a session is destroyed. + * + * On session close, the IPC is closed and the server must release all tcons of the session. + * No need to send a tree disconnect here. + * + * Besides, it will make the server to not close durable and resilient files on session close, as + * specified in MS-SMB2 3.3.5.6 Receiving an SMB2 LOGOFF Request. */ static int cifs_free_ipc(struct cifs_ses *ses) { - int rc = 0, xid; struct cifs_tcon *tcon = ses->tcon_ipc; if (tcon == NULL) return 0; - if (ses->server->ops->tree_disconnect) { - xid = get_xid(); - rc = ses->server->ops->tree_disconnect(xid, tcon); - free_xid(xid); - } - - if (rc) - cifs_dbg(FYI, "failed to disconnect IPC tcon (rc=%d)\n", rc); - tconInfoFree(tcon); ses->tcon_ipc = NULL; - return rc; + return 0; } static struct cifs_ses * @@ -1605,7 +1583,6 @@ void cifs_put_smb_ses(struct cifs_ses *ses) { unsigned int rc, xid; struct TCP_Server_Info *server = ses->server; - cifs_dbg(FYI, "%s: ses_count=%d\n", __func__, ses->ses_count); spin_lock(&cifs_tcp_ses_lock); @@ -1613,13 +1590,20 @@ void cifs_put_smb_ses(struct cifs_ses *ses) spin_unlock(&cifs_tcp_ses_lock); return; } + + cifs_dbg(FYI, "%s: ses_count=%d\n", __func__, ses->ses_count); + cifs_dbg(FYI, "%s: ses ipc: %s\n", __func__, ses->tcon_ipc ? ses->tcon_ipc->treeName : "NONE"); + if (--ses->ses_count > 0) { spin_unlock(&cifs_tcp_ses_lock); return; } + spin_unlock(&cifs_tcp_ses_lock); + + spin_lock(&GlobalMid_Lock); if (ses->status == CifsGood) ses->status = CifsExiting; - spin_unlock(&cifs_tcp_ses_lock); + spin_unlock(&GlobalMid_Lock); cifs_free_ipc(ses); @@ -1951,10 +1935,7 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) spin_lock(&cifs_tcp_ses_lock); list_for_each(tmp, &ses->tcon_list) { tcon = list_entry(tmp, struct cifs_tcon, tcon_list); -#ifdef CONFIG_CIFS_DFS_UPCALL - if (tcon->dfs_path) - continue; -#endif + if (!match_tcon(tcon, ctx)) continue; ++tcon->tc_count; @@ -3017,9 +2998,8 @@ expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses, return rc; } -static inline int get_next_dfs_tgt(const char *path, - struct dfs_cache_tgt_list *tgt_list, - struct dfs_cache_tgt_iterator **tgt_it) +static int get_next_dfs_tgt(struct dfs_cache_tgt_list *tgt_list, + struct dfs_cache_tgt_iterator **tgt_it) { if (!*tgt_it) *tgt_it = dfs_cache_get_tgt_iterator(tgt_list); @@ -3059,6 +3039,7 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_ struct cifs_ses **ses, struct cifs_tcon **tcon) { int rc; + char *npath = NULL; struct dfs_cache_tgt_list tgt_list = {0}; struct dfs_cache_tgt_iterator *tgt_it = NULL; struct smb3_fs_context tmp_ctx = {NULL}; @@ -3066,11 +3047,15 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) return -EOPNOTSUPP; - cifs_dbg(FYI, "%s: path=%s full_path=%s\n", __func__, path, full_path); + npath = dfs_cache_canonical_path(path, cifs_sb->local_nls, cifs_remap(cifs_sb)); + if (IS_ERR(npath)) + return PTR_ERR(npath); - rc = dfs_cache_noreq_find(path, NULL, &tgt_list); + cifs_dbg(FYI, "%s: path=%s full_path=%s\n", __func__, npath, full_path); + + rc = dfs_cache_noreq_find(npath, NULL, &tgt_list); if (rc) - return rc; + goto out; /* * We use a 'tmp_ctx' here because we need pass it down to the mount_{get,put} functions to * test connection against new DFS targets. @@ -3084,11 +3069,11 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_ char *fake_devname = NULL, *mdata = NULL; /* Get next DFS target server - if any */ - rc = get_next_dfs_tgt(path, &tgt_list, &tgt_it); + rc = get_next_dfs_tgt(&tgt_list, &tgt_it); if (rc) break; - rc = dfs_cache_get_tgt_referral(path, tgt_it, &ref); + rc = dfs_cache_get_tgt_referral(npath, tgt_it, &ref); if (rc) break; @@ -3137,6 +3122,7 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_ } out: + kfree(npath); smb3_cleanup_fs_context_contents(&tmp_ctx); dfs_cache_free_tgts(&tgt_list); return rc; @@ -3288,25 +3274,18 @@ static int is_path_remote(struct cifs_sb_info *cifs_sb, struct smb3_fs_context * } #ifdef CONFIG_CIFS_DFS_UPCALL -static void set_root_ses(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, +static void set_root_ses(struct cifs_sb_info *cifs_sb, const uuid_t *mount_id, struct cifs_ses *ses, struct cifs_ses **root_ses) { if (ses) { spin_lock(&cifs_tcp_ses_lock); ses->ses_count++; - if (ses->tcon_ipc) - ses->tcon_ipc->remap = cifs_remap(cifs_sb); spin_unlock(&cifs_tcp_ses_lock); + dfs_cache_add_refsrv_session(mount_id, ses); } *root_ses = ses; } -static void put_root_ses(struct cifs_ses *ses) -{ - if (ses) - cifs_put_smb_ses(ses); -} - /* Set up next dfs prefix path in @dfs_path */ static int next_dfs_prepath(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx, const unsigned int xid, struct TCP_Server_Info *server, @@ -3352,17 +3331,25 @@ out: } /* Check if resolved targets can handle any DFS referrals */ -static int is_referral_server(const char *ref_path, struct cifs_tcon *tcon, bool *ref_server) +static int is_referral_server(const char *ref_path, struct cifs_sb_info *cifs_sb, + struct cifs_tcon *tcon, bool *ref_server) { int rc; struct dfs_info3_param ref = {0}; + cifs_dbg(FYI, "%s: ref_path=%s\n", __func__, ref_path); + if (is_tcon_dfs(tcon)) { *ref_server = true; } else { - cifs_dbg(FYI, "%s: ref_path=%s\n", __func__, ref_path); + char *npath; - rc = dfs_cache_noreq_find(ref_path, &ref, NULL); + npath = dfs_cache_canonical_path(ref_path, cifs_sb->local_nls, cifs_remap(cifs_sb)); + if (IS_ERR(npath)) + return PTR_ERR(npath); + + rc = dfs_cache_noreq_find(npath, &ref, NULL); + kfree(npath); if (rc) { cifs_dbg(VFS, "%s: dfs_cache_noreq_find: failed (rc=%d)\n", __func__, rc); return rc; @@ -3386,9 +3373,9 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) struct cifs_ses *ses = NULL, *root_ses = NULL; struct cifs_tcon *tcon = NULL; int count = 0; + uuid_t mount_id = {0}; char *ref_path = NULL, *full_path = NULL; char *oldmnt = NULL; - char *mntdata = NULL; bool ref_server = false; rc = mount_get_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon); @@ -3411,12 +3398,9 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) if (rc != -EREMOTE) goto error; } - /* Save mount options */ - mntdata = kstrdup(cifs_sb->ctx->mount_options, GFP_KERNEL); - if (!mntdata) { - rc = -ENOMEM; - goto error; - } + + ctx->nosharesock = true; + /* Get path of DFS root */ ref_path = build_unc_path_to_root(ctx, cifs_sb, false); if (IS_ERR(ref_path)) { @@ -3425,7 +3409,8 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) goto error; } - set_root_ses(cifs_sb, ses, &root_ses); + uuid_gen(&mount_id); + set_root_ses(cifs_sb, &mount_id, ses, &root_ses); do { /* Save full path of last DFS path we used to resolve final target server */ kfree(full_path); @@ -3456,13 +3441,11 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) continue; /* Make sure that requests go through new root servers */ - rc = is_referral_server(ref_path + 1, tcon, &ref_server); + rc = is_referral_server(ref_path + 1, cifs_sb, tcon, &ref_server); if (rc) break; - if (ref_server) { - put_root_ses(root_ses); - set_root_ses(cifs_sb, ses, &root_ses); - } + if (ref_server) + set_root_ses(cifs_sb, &mount_id, ses, &root_ses); /* Get next dfs path and then continue chasing them if -EREMOTE */ rc = next_dfs_prepath(cifs_sb, ctx, xid, server, tcon, &ref_path); @@ -3471,12 +3454,10 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) rc = -ELOOP; } while (rc == -EREMOTE); - if (rc) + if (rc || !tcon) goto error; - put_root_ses(root_ses); - root_ses = NULL; + kfree(ref_path); - ref_path = NULL; /* * Store DFS full path in both superblock and tree connect structures. * @@ -3485,21 +3466,27 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) * links, the prefix path is included in both and may be changed during reconnect. See * cifs_tree_connect(). */ - cifs_sb->origin_fullpath = kstrdup(full_path, GFP_KERNEL); - if (!cifs_sb->origin_fullpath) { + ref_path = dfs_cache_canonical_path(full_path, cifs_sb->local_nls, cifs_remap(cifs_sb)); + kfree(full_path); + full_path = NULL; + + if (IS_ERR(ref_path)) { + rc = PTR_ERR(ref_path); + ref_path = NULL; + goto error; + } + cifs_sb->origin_fullpath = ref_path; + + ref_path = kstrdup(cifs_sb->origin_fullpath, GFP_KERNEL); + if (!ref_path) { rc = -ENOMEM; goto error; } spin_lock(&cifs_tcp_ses_lock); - tcon->dfs_path = full_path; - full_path = NULL; - tcon->remap = cifs_remap(cifs_sb); + tcon->dfs_path = ref_path; + ref_path = NULL; spin_unlock(&cifs_tcp_ses_lock); - /* Add original context for DFS cache to be used when refreshing referrals */ - rc = dfs_cache_add_vol(mntdata, ctx, cifs_sb->origin_fullpath); - if (rc) - goto error; /* * After reconnecting to a different server, unique ids won't * match anymore, so we disable serverino. This prevents @@ -3514,6 +3501,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) kfree(cifs_sb->prepath); cifs_sb->prepath = ctx->prepath; ctx->prepath = NULL; + uuid_copy(&cifs_sb->dfs_mount_id, &mount_id); out: free_xid(xid); @@ -3523,9 +3511,8 @@ out: error: kfree(ref_path); kfree(full_path); - kfree(mntdata); kfree(cifs_sb->origin_fullpath); - put_root_ses(root_ses); + dfs_cache_put_refsrv_sessions(&mount_id); mount_put_conns(cifs_sb, xid, server, ses, tcon); return rc; } @@ -3755,7 +3742,7 @@ cifs_umount(struct cifs_sb_info *cifs_sb) kfree(cifs_sb->prepath); #ifdef CONFIG_CIFS_DFS_UPCALL - dfs_cache_del_vol(cifs_sb->origin_fullpath); + dfs_cache_put_refsrv_sessions(&cifs_sb->dfs_mount_id); kfree(cifs_sb->origin_fullpath); #endif call_rcu(&cifs_sb->rcu, delayed_free); diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index b1fa30fefe1f..7c1769714609 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "cifsglob.h" #include "smb2pdu.h" #include "smb2proto.h" @@ -18,15 +19,14 @@ #include "cifs_debug.h" #include "cifs_unicode.h" #include "smb2glob.h" -#include "fs_context.h" #include "dfs_cache.h" #define CACHE_HTABLE_SIZE 32 #define CACHE_MAX_ENTRIES 64 +#define CACHE_MIN_TTL 120 /* 2 minutes */ -#define IS_INTERLINK_SET(v) ((v) & (DFSREF_REFERRAL_SERVER | \ - DFSREF_STORAGE_SERVER)) +#define IS_DFS_INTERLINK(v) (((v) & DFSREF_REFERRAL_SERVER) && !((v) & DFSREF_STORAGE_SERVER)) struct cache_dfs_tgt { char *name; @@ -48,14 +48,15 @@ struct cache_entry { struct cache_dfs_tgt *tgthint; }; -struct vol_info { - char *fullpath; - spinlock_t ctx_lock; - struct smb3_fs_context ctx; - char *mntdata; +/* List of referral server sessions per dfs mount */ +struct mount_group { struct list_head list; - struct list_head rlist; - struct kref refcnt; + uuid_t id; + struct cifs_ses *sessions[CACHE_MAX_ENTRIES]; + int num_sessions; + spinlock_t lock; + struct list_head refresh_list; + struct kref refcount; }; static struct kmem_cache *cache_slab __read_mostly; @@ -64,7 +65,7 @@ static struct workqueue_struct *dfscache_wq __read_mostly; static int cache_ttl; static DEFINE_SPINLOCK(cache_ttl_lock); -static struct nls_table *cache_nlsc; +static struct nls_table *cache_cp; /* * Number of entries in the cache @@ -74,34 +75,145 @@ static atomic_t cache_count; static struct hlist_head cache_htable[CACHE_HTABLE_SIZE]; static DECLARE_RWSEM(htable_rw_lock); -static LIST_HEAD(vol_list); -static DEFINE_SPINLOCK(vol_list_lock); +static LIST_HEAD(mount_group_list); +static DEFINE_MUTEX(mount_group_list_lock); static void refresh_cache_worker(struct work_struct *work); static DECLARE_DELAYED_WORK(refresh_task, refresh_cache_worker); -static int get_normalized_path(const char *path, const char **npath) +static void get_ipc_unc(const char *ref_path, char *ipc, size_t ipclen) { - if (!path || strlen(path) < 3 || (*path != '\\' && *path != '/')) - return -EINVAL; + const char *host; + size_t len; - if (*path == '\\') { - *npath = path; - } else { - char *s = kstrdup(path, GFP_KERNEL); - if (!s) - return -ENOMEM; - convert_delimiter(s, '\\'); - *npath = s; - } - return 0; + extract_unc_hostname(ref_path, &host, &len); + scnprintf(ipc, ipclen, "\\\\%.*s\\IPC$", (int)len, host); } -static inline void free_normalized_path(const char *path, const char *npath) +static struct cifs_ses *find_ipc_from_server_path(struct cifs_ses **ses, const char *path) { - if (path != npath) - kfree(npath); + char unc[SERVER_NAME_LENGTH + sizeof("//x/IPC$")] = {0}; + + get_ipc_unc(path, unc, sizeof(unc)); + for (; *ses; ses++) { + if (!strcasecmp(unc, (*ses)->tcon_ipc->treeName)) + return *ses; + } + return ERR_PTR(-ENOENT); +} + +static void __mount_group_release(struct mount_group *mg) +{ + int i; + + for (i = 0; i < mg->num_sessions; i++) + cifs_put_smb_ses(mg->sessions[i]); + kfree(mg); +} + +static void mount_group_release(struct kref *kref) +{ + struct mount_group *mg = container_of(kref, struct mount_group, refcount); + + mutex_lock(&mount_group_list_lock); + list_del(&mg->list); + mutex_unlock(&mount_group_list_lock); + __mount_group_release(mg); +} + +static struct mount_group *find_mount_group_locked(const uuid_t *id) +{ + struct mount_group *mg; + + list_for_each_entry(mg, &mount_group_list, list) { + if (uuid_equal(&mg->id, id)) + return mg; + } + return ERR_PTR(-ENOENT); +} + +static struct mount_group *__get_mount_group_locked(const uuid_t *id) +{ + struct mount_group *mg; + + mg = find_mount_group_locked(id); + if (!IS_ERR(mg)) + return mg; + + mg = kmalloc(sizeof(*mg), GFP_KERNEL); + if (!mg) + return ERR_PTR(-ENOMEM); + kref_init(&mg->refcount); + uuid_copy(&mg->id, id); + mg->num_sessions = 0; + spin_lock_init(&mg->lock); + list_add(&mg->list, &mount_group_list); + return mg; +} + +static struct mount_group *get_mount_group(const uuid_t *id) +{ + struct mount_group *mg; + + mutex_lock(&mount_group_list_lock); + mg = __get_mount_group_locked(id); + if (!IS_ERR(mg)) + kref_get(&mg->refcount); + mutex_unlock(&mount_group_list_lock); + + return mg; +} + +static void free_mount_group_list(void) +{ + struct mount_group *mg, *tmp_mg; + + list_for_each_entry_safe(mg, tmp_mg, &mount_group_list, list) { + list_del_init(&mg->list); + __mount_group_release(mg); + } +} + +/** + * dfs_cache_canonical_path - get a canonical DFS path + * + * @path: DFS path + * @cp: codepage + * @remap: mapping type + * + * Return canonical path if success, otherwise error. + */ +char *dfs_cache_canonical_path(const char *path, const struct nls_table *cp, int remap) +{ + char *tmp; + int plen = 0; + char *npath; + + if (!path || strlen(path) < 3 || (*path != '\\' && *path != '/')) + return ERR_PTR(-EINVAL); + + if (unlikely(strcmp(cp->charset, cache_cp->charset))) { + tmp = (char *)cifs_strndup_to_utf16(path, strlen(path), &plen, cp, remap); + if (!tmp) { + cifs_dbg(VFS, "%s: failed to convert path to utf16\n", __func__); + return ERR_PTR(-EINVAL); + } + + npath = cifs_strndup_from_utf16(tmp, plen, true, cache_cp); + kfree(tmp); + + if (!npath) { + cifs_dbg(VFS, "%s: failed to convert path from utf16\n", __func__); + return ERR_PTR(-EINVAL); + } + } else { + npath = kstrdup(path, GFP_KERNEL); + if (!npath) + return ERR_PTR(-ENOMEM); + } + convert_delimiter(npath, '\\'); + return npath; } static inline bool cache_entry_expired(const struct cache_entry *ce) @@ -171,7 +283,7 @@ static int dfscache_proc_show(struct seq_file *m, void *v) "cache entry: path=%s,type=%s,ttl=%d,etime=%ld,hdr_flags=0x%x,ref_flags=0x%x,interlink=%s,path_consumed=%d,expired=%s\n", ce->path, ce->srvtype == DFS_TYPE_ROOT ? "root" : "link", ce->ttl, ce->etime.tv_nsec, ce->ref_flags, ce->hdr_flags, - IS_INTERLINK_SET(ce->hdr_flags) ? "yes" : "no", + IS_DFS_INTERLINK(ce->hdr_flags) ? "yes" : "no", ce->path_consumed, cache_entry_expired(ce) ? "yes" : "no"); list_for_each_entry(t, &ce->tlist, list) { @@ -240,7 +352,7 @@ static inline void dump_ce(const struct cache_entry *ce) ce->srvtype == DFS_TYPE_ROOT ? "root" : "link", ce->ttl, ce->etime.tv_nsec, ce->hdr_flags, ce->ref_flags, - IS_INTERLINK_SET(ce->hdr_flags) ? "yes" : "no", + IS_DFS_INTERLINK(ce->hdr_flags) ? "yes" : "no", ce->path_consumed, cache_entry_expired(ce) ? "yes" : "no"); dump_tgts(ce); @@ -284,8 +396,7 @@ int dfs_cache_init(void) int rc; int i; - dfscache_wq = alloc_workqueue("cifs-dfscache", - WQ_FREEZABLE | WQ_MEM_RECLAIM, 1); + dfscache_wq = alloc_workqueue("cifs-dfscache", WQ_FREEZABLE | WQ_UNBOUND, 1); if (!dfscache_wq) return -ENOMEM; @@ -301,7 +412,9 @@ int dfs_cache_init(void) INIT_HLIST_HEAD(&cache_htable[i]); atomic_set(&cache_count, 0); - cache_nlsc = load_nls_default(); + cache_cp = load_nls("utf8"); + if (!cache_cp) + cache_cp = load_nls_default(); cifs_dbg(FYI, "%s: initialized DFS referral cache\n", __func__); return 0; @@ -311,23 +424,24 @@ out_destroy_wq: return rc; } -static inline unsigned int cache_entry_hash(const void *data, int size) +static int cache_entry_hash(const void *data, int size, unsigned int *hash) { - unsigned int h; + int i, clen; + const unsigned char *s = data; + wchar_t c; + unsigned int h = 0; - h = jhash(data, size, 0); - return h & (CACHE_HTABLE_SIZE - 1); -} - -/* Check whether second path component of @path is SYSVOL or NETLOGON */ -static inline bool is_sysvol_or_netlogon(const char *path) -{ - const char *s; - char sep = path[0]; - - s = strchr(path + 1, sep) + 1; - return !strncasecmp(s, "sysvol", strlen("sysvol")) || - !strncasecmp(s, "netlogon", strlen("netlogon")); + for (i = 0; i < size; i += clen) { + clen = cache_cp->char2uni(&s[i], size - i, &c); + if (unlikely(clen < 0)) { + cifs_dbg(VFS, "%s: can't convert char\n", __func__); + return clen; + } + c = cifs_toupper(c); + h = jhash(&c, sizeof(c), h); + } + *hash = h % CACHE_HTABLE_SIZE; + return 0; } /* Return target hint of a DFS cache entry */ @@ -378,7 +492,7 @@ static int copy_ref_data(const struct dfs_info3_param *refs, int numrefs, { int i; - ce->ttl = refs[0].ttl; + ce->ttl = max_t(int, refs[0].ttl, CACHE_MIN_TTL); ce->etime = get_expire_time(ce->ttl); ce->srvtype = refs[0].server_type; ce->hdr_flags = refs[0].flags; @@ -409,9 +523,7 @@ static int copy_ref_data(const struct dfs_info3_param *refs, int numrefs, } /* Allocate a new cache entry */ -static struct cache_entry *alloc_cache_entry(const char *path, - const struct dfs_info3_param *refs, - int numrefs) +static struct cache_entry *alloc_cache_entry(struct dfs_info3_param *refs, int numrefs) { struct cache_entry *ce; int rc; @@ -420,11 +532,9 @@ static struct cache_entry *alloc_cache_entry(const char *path, if (!ce) return ERR_PTR(-ENOMEM); - ce->path = kstrdup(path, GFP_KERNEL); - if (!ce->path) { - kmem_cache_free(cache_slab, ce); - return ERR_PTR(-ENOMEM); - } + ce->path = refs[0].path_name; + refs[0].path_name = NULL; + INIT_HLIST_NODE(&ce->hlist); INIT_LIST_HEAD(&ce->tlist); @@ -437,13 +547,14 @@ static struct cache_entry *alloc_cache_entry(const char *path, return ce; } -/* Must be called with htable_rw_lock held */ -static void remove_oldest_entry(void) +static void remove_oldest_entry_locked(void) { int i; struct cache_entry *ce; struct cache_entry *to_del = NULL; + WARN_ON(!rwsem_is_locked(&htable_rw_lock)); + for (i = 0; i < CACHE_HTABLE_SIZE; i++) { struct hlist_head *l = &cache_htable[i]; @@ -467,12 +578,24 @@ static void remove_oldest_entry(void) } /* Add a new DFS cache entry */ -static int add_cache_entry(const char *path, unsigned int hash, - struct dfs_info3_param *refs, int numrefs) +static int add_cache_entry_locked(struct dfs_info3_param *refs, int numrefs) { + int rc; struct cache_entry *ce; + unsigned int hash; - ce = alloc_cache_entry(path, refs, numrefs); + WARN_ON(!rwsem_is_locked(&htable_rw_lock)); + + if (atomic_read(&cache_count) >= CACHE_MAX_ENTRIES) { + cifs_dbg(FYI, "%s: reached max cache size (%d)\n", __func__, CACHE_MAX_ENTRIES); + remove_oldest_entry_locked(); + } + + rc = cache_entry_hash(refs[0].path_name, strlen(refs[0].path_name), &hash); + if (rc) + return rc; + + ce = alloc_cache_entry(refs, numrefs); if (IS_ERR(ce)) return PTR_ERR(ce); @@ -486,65 +609,77 @@ static int add_cache_entry(const char *path, unsigned int hash, } spin_unlock(&cache_ttl_lock); - down_write(&htable_rw_lock); hlist_add_head(&ce->hlist, &cache_htable[hash]); dump_ce(ce); - up_write(&htable_rw_lock); + + atomic_inc(&cache_count); return 0; } -static struct cache_entry *__lookup_cache_entry(const char *path) +/* Check if two DFS paths are equal. @s1 and @s2 are expected to be in @cache_cp's charset */ +static bool dfs_path_equal(const char *s1, int len1, const char *s2, int len2) +{ + int i, l1, l2; + wchar_t c1, c2; + + if (len1 != len2) + return false; + + for (i = 0; i < len1; i += l1) { + l1 = cache_cp->char2uni(&s1[i], len1 - i, &c1); + l2 = cache_cp->char2uni(&s2[i], len2 - i, &c2); + if (unlikely(l1 < 0 && l2 < 0)) { + if (s1[i] != s2[i]) + return false; + l1 = 1; + continue; + } + if (l1 != l2) + return false; + if (cifs_toupper(c1) != cifs_toupper(c2)) + return false; + } + return true; +} + +static struct cache_entry *__lookup_cache_entry(const char *path, unsigned int hash, int len) { struct cache_entry *ce; - unsigned int h; - bool found = false; - h = cache_entry_hash(path, strlen(path)); - - hlist_for_each_entry(ce, &cache_htable[h], hlist) { - if (!strcasecmp(path, ce->path)) { - found = true; + hlist_for_each_entry(ce, &cache_htable[hash], hlist) { + if (dfs_path_equal(ce->path, strlen(ce->path), path, len)) { dump_ce(ce); - break; + return ce; } } - - if (!found) - ce = ERR_PTR(-ENOENT); - return ce; + return ERR_PTR(-EEXIST); } /* - * Find a DFS cache entry in hash table and optionally check prefix path against - * @path. - * Use whole path components in the match. - * Must be called with htable_rw_lock held. + * Find a DFS cache entry in hash table and optionally check prefix path against normalized @path. * - * Return ERR_PTR(-ENOENT) if the entry is not found. + * Use whole path components in the match. Must be called with htable_rw_lock held. + * + * Return ERR_PTR(-EEXIST) if the entry is not found. */ -static struct cache_entry *lookup_cache_entry(const char *path, unsigned int *hash) +static struct cache_entry *lookup_cache_entry(const char *path) { - struct cache_entry *ce = ERR_PTR(-ENOENT); - unsigned int h; + struct cache_entry *ce; int cnt = 0; - char *npath; - char *s, *e; - char sep; + const char *s = path, *e; + char sep = *s; + unsigned int hash; + int rc; - npath = kstrdup(path, GFP_KERNEL); - if (!npath) - return ERR_PTR(-ENOMEM); - - s = npath; - sep = *npath; while ((s = strchr(s, sep)) && ++cnt < 3) s++; if (cnt < 3) { - h = cache_entry_hash(path, strlen(path)); - ce = __lookup_cache_entry(path); - goto out; + rc = cache_entry_hash(path, strlen(path), &hash); + if (rc) + return ERR_PTR(rc); + return __lookup_cache_entry(path, hash, strlen(path)); } /* * Handle paths that have more than two path components and are a complete prefix of the DFS @@ -552,64 +687,29 @@ static struct cache_entry *lookup_cache_entry(const char *path, unsigned int *ha * * See MS-DFSC 3.2.5.5 "Receiving a Root Referral Request or Link Referral Request". */ - h = cache_entry_hash(npath, strlen(npath)); - e = npath + strlen(npath) - 1; + e = path + strlen(path) - 1; while (e > s) { - char tmp; + int len; /* skip separators */ while (e > s && *e == sep) e--; if (e == s) - goto out; - - tmp = *(e+1); - *(e+1) = 0; - - ce = __lookup_cache_entry(npath); - if (!IS_ERR(ce)) { - h = cache_entry_hash(npath, strlen(npath)); break; - } - *(e+1) = tmp; + len = e + 1 - path; + rc = cache_entry_hash(path, len, &hash); + if (rc) + return ERR_PTR(rc); + ce = __lookup_cache_entry(path, hash, len); + if (!IS_ERR(ce)) + return ce; + /* backward until separator */ while (e > s && *e != sep) e--; } -out: - if (hash) - *hash = h; - kfree(npath); - return ce; -} - -static void __vol_release(struct vol_info *vi) -{ - kfree(vi->fullpath); - kfree(vi->mntdata); - smb3_cleanup_fs_context_contents(&vi->ctx); - kfree(vi); -} - -static void vol_release(struct kref *kref) -{ - struct vol_info *vi = container_of(kref, struct vol_info, refcnt); - - spin_lock(&vol_list_lock); - list_del(&vi->list); - spin_unlock(&vol_list_lock); - __vol_release(vi); -} - -static inline void free_vol_list(void) -{ - struct vol_info *vi, *nvi; - - list_for_each_entry_safe(vi, nvi, &vol_list, list) { - list_del_init(&vi->list); - __vol_release(vi); - } + return ERR_PTR(-EEXIST); } /** @@ -618,8 +718,8 @@ static inline void free_vol_list(void) void dfs_cache_destroy(void) { cancel_delayed_work_sync(&refresh_task); - unload_nls(cache_nlsc); - free_vol_list(); + unload_nls(cache_cp); + free_mount_group_list(); flush_cache_ents(); kmem_cache_destroy(cache_slab); destroy_workqueue(dfscache_wq); @@ -627,18 +727,14 @@ void dfs_cache_destroy(void) cifs_dbg(FYI, "%s: destroyed DFS referral cache\n", __func__); } -/* Must be called with htable_rw_lock held */ -static int __update_cache_entry(const char *path, - const struct dfs_info3_param *refs, - int numrefs) +/* Update a cache entry with the new referral in @refs */ +static int update_cache_entry_locked(struct cache_entry *ce, const struct dfs_info3_param *refs, + int numrefs) { int rc; - struct cache_entry *ce; char *s, *th = NULL; - ce = lookup_cache_entry(path, NULL); - if (IS_ERR(ce)) - return PTR_ERR(ce); + WARN_ON(!rwsem_is_locked(&htable_rw_lock)); if (ce->tgthint) { s = ce->tgthint->name; @@ -657,37 +753,30 @@ static int __update_cache_entry(const char *path, return rc; } -static int get_dfs_referral(const unsigned int xid, struct cifs_ses *ses, - const struct nls_table *nls_codepage, int remap, - const char *path, struct dfs_info3_param **refs, - int *numrefs) +static int get_dfs_referral(const unsigned int xid, struct cifs_ses *ses, const char *path, + struct dfs_info3_param **refs, int *numrefs) { - cifs_dbg(FYI, "%s: get an DFS referral for %s\n", __func__, path); + int rc; + int i; - if (!ses || !ses->server || !ses->server->ops->get_dfs_refer) - return -EOPNOTSUPP; - if (unlikely(!nls_codepage)) - return -EINVAL; + cifs_dbg(FYI, "%s: get an DFS referral for %s\n", __func__, path); *refs = NULL; *numrefs = 0; - return ses->server->ops->get_dfs_refer(xid, ses, path, refs, numrefs, - nls_codepage, remap); -} + if (!ses || !ses->server || !ses->server->ops->get_dfs_refer) + return -EOPNOTSUPP; + if (unlikely(!cache_cp)) + return -EINVAL; -/* Update an expired cache entry by getting a new DFS referral from server */ -static int update_cache_entry(const char *path, - const struct dfs_info3_param *refs, - int numrefs) -{ - - int rc; - - down_write(&htable_rw_lock); - rc = __update_cache_entry(path, refs, numrefs); - up_write(&htable_rw_lock); + rc = ses->server->ops->get_dfs_refer(xid, ses, path, refs, numrefs, cache_cp, + NO_MAP_UNI_RSVD); + if (!rc) { + struct dfs_info3_param *ref = *refs; + for (i = 0; i < *numrefs; i++) + convert_delimiter(ref[i].path_name, '\\'); + } return rc; } @@ -697,15 +786,12 @@ static int update_cache_entry(const char *path, * If the entry wasn't found, it will create a new one. Or if it was found but * expired, then it will update the entry accordingly. * - * For interlinks, __cifs_dfs_mount() and expand_dfs_referral() are supposed to + * For interlinks, cifs_mount() and expand_dfs_referral() are supposed to * handle them properly. */ -static int __dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, - const struct nls_table *nls_codepage, int remap, - const char *path, bool noreq) +static int cache_refresh_path(const unsigned int xid, struct cifs_ses *ses, const char *path) { int rc; - unsigned int hash; struct cache_entry *ce; struct dfs_info3_param *refs = NULL; int numrefs = 0; @@ -713,62 +799,38 @@ static int __dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, cifs_dbg(FYI, "%s: search path: %s\n", __func__, path); - down_read(&htable_rw_lock); - - ce = lookup_cache_entry(path, &hash); - - /* - * If @noreq is set, no requests will be sent to the server. Just return - * the cache entry. - */ - if (noreq) { - up_read(&htable_rw_lock); - return PTR_ERR_OR_ZERO(ce); - } + down_write(&htable_rw_lock); + ce = lookup_cache_entry(path); if (!IS_ERR(ce)) { if (!cache_entry_expired(ce)) { dump_ce(ce); - up_read(&htable_rw_lock); + up_write(&htable_rw_lock); return 0; } } else { newent = true; } - up_read(&htable_rw_lock); - /* - * No entry was found. - * - * Request a new DFS referral in order to create a new cache entry, or - * updating an existing one. + * Either the entry was not found, or it is expired. + * Request a new DFS referral in order to create or update a cache entry. */ - rc = get_dfs_referral(xid, ses, nls_codepage, remap, path, - &refs, &numrefs); + rc = get_dfs_referral(xid, ses, path, &refs, &numrefs); if (rc) - return rc; + goto out_unlock; dump_refs(refs, numrefs); if (!newent) { - rc = update_cache_entry(path, refs, numrefs); - goto out_free_refs; + rc = update_cache_entry_locked(ce, refs, numrefs); + goto out_unlock; } - if (atomic_read(&cache_count) >= CACHE_MAX_ENTRIES) { - cifs_dbg(FYI, "%s: reached max cache size (%d)\n", - __func__, CACHE_MAX_ENTRIES); - down_write(&htable_rw_lock); - remove_oldest_entry(); - up_write(&htable_rw_lock); - } + rc = add_cache_entry_locked(refs, numrefs); - rc = add_cache_entry(path, hash, refs, numrefs); - if (!rc) - atomic_inc(&cache_count); - -out_free_refs: +out_unlock: + up_write(&htable_rw_lock); free_dfs_info_array(refs, numrefs); return rc; } @@ -868,7 +930,7 @@ err_free_it: * needs to be issued: * @xid: syscall xid * @ses: smb session to issue the request on - * @nls_codepage: charset conversion + * @cp: codepage * @remap: path character remapping type * @path: path to lookup in DFS referral cache. * @@ -877,26 +939,25 @@ err_free_it: * * Return zero if the target was found, otherwise non-zero. */ -int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, - const struct nls_table *nls_codepage, int remap, - const char *path, struct dfs_info3_param *ref, +int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, const struct nls_table *cp, + int remap, const char *path, struct dfs_info3_param *ref, struct dfs_cache_tgt_list *tgt_list) { int rc; const char *npath; struct cache_entry *ce; - rc = get_normalized_path(path, &npath); - if (rc) - return rc; + npath = dfs_cache_canonical_path(path, cp, remap); + if (IS_ERR(npath)) + return PTR_ERR(npath); - rc = __dfs_cache_find(xid, ses, nls_codepage, remap, npath, false); + rc = cache_refresh_path(xid, ses, npath); if (rc) goto out_free_path; down_read(&htable_rw_lock); - ce = lookup_cache_entry(npath, NULL); + ce = lookup_cache_entry(npath); if (IS_ERR(ce)) { up_read(&htable_rw_lock); rc = PTR_ERR(ce); @@ -913,7 +974,7 @@ int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, up_read(&htable_rw_lock); out_free_path: - free_normalized_path(path, npath); + kfree(npath); return rc; } @@ -925,7 +986,7 @@ out_free_path: * expired, nor create a new cache entry if @path hasn't been found. It heavily * relies on an existing cache entry. * - * @path: path to lookup in the DFS referral cache. + * @path: canonical DFS path to lookup in the DFS referral cache. * @ref: when non-NULL, store single DFS referral result in it. * @tgt_list: when non-NULL, store complete DFS target list in it. * @@ -937,18 +998,13 @@ int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref, struct dfs_cache_tgt_list *tgt_list) { int rc; - const char *npath; struct cache_entry *ce; - rc = get_normalized_path(path, &npath); - if (rc) - return rc; - - cifs_dbg(FYI, "%s: path: %s\n", __func__, npath); + cifs_dbg(FYI, "%s: path: %s\n", __func__, path); down_read(&htable_rw_lock); - ce = lookup_cache_entry(npath, NULL); + ce = lookup_cache_entry(path); if (IS_ERR(ce)) { rc = PTR_ERR(ce); goto out_unlock; @@ -963,8 +1019,6 @@ int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref, out_unlock: up_read(&htable_rw_lock); - free_normalized_path(path, npath); - return rc; } @@ -979,16 +1033,15 @@ out_unlock: * * @xid: syscall id * @ses: smb session - * @nls_codepage: charset conversion + * @cp: codepage * @remap: type of character remapping for paths - * @path: path to lookup in DFS referral cache. + * @path: path to lookup in DFS referral cache * @it: DFS target iterator * * Return zero if the target hint was updated successfully, otherwise non-zero. */ int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses, - const struct nls_table *nls_codepage, int remap, - const char *path, + const struct nls_table *cp, int remap, const char *path, const struct dfs_cache_tgt_iterator *it) { int rc; @@ -996,19 +1049,19 @@ int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses, struct cache_entry *ce; struct cache_dfs_tgt *t; - rc = get_normalized_path(path, &npath); - if (rc) - return rc; + npath = dfs_cache_canonical_path(path, cp, remap); + if (IS_ERR(npath)) + return PTR_ERR(npath); cifs_dbg(FYI, "%s: update target hint - path: %s\n", __func__, npath); - rc = __dfs_cache_find(xid, ses, nls_codepage, remap, npath, false); + rc = cache_refresh_path(xid, ses, npath); if (rc) goto out_free_path; down_write(&htable_rw_lock); - ce = lookup_cache_entry(npath, NULL); + ce = lookup_cache_entry(npath); if (IS_ERR(ce)) { rc = PTR_ERR(ce); goto out_unlock; @@ -1031,8 +1084,7 @@ int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses, out_unlock: up_write(&htable_rw_lock); out_free_path: - free_normalized_path(path, npath); - + kfree(npath); return rc; } @@ -1044,32 +1096,26 @@ out_free_path: * expired, nor create a new cache entry if @path hasn't been found. It heavily * relies on an existing cache entry. * - * @path: path to lookup in DFS referral cache. + * @path: canonical DFS path to lookup in DFS referral cache. * @it: target iterator which contains the target hint to update the cache * entry with. * * Return zero if the target hint was updated successfully, otherwise non-zero. */ -int dfs_cache_noreq_update_tgthint(const char *path, - const struct dfs_cache_tgt_iterator *it) +int dfs_cache_noreq_update_tgthint(const char *path, const struct dfs_cache_tgt_iterator *it) { int rc; - const char *npath; struct cache_entry *ce; struct cache_dfs_tgt *t; if (!it) return -EINVAL; - rc = get_normalized_path(path, &npath); - if (rc) - return rc; - - cifs_dbg(FYI, "%s: path: %s\n", __func__, npath); + cifs_dbg(FYI, "%s: path: %s\n", __func__, path); down_write(&htable_rw_lock); - ce = lookup_cache_entry(npath, NULL); + ce = lookup_cache_entry(path); if (IS_ERR(ce)) { rc = PTR_ERR(ce); goto out_unlock; @@ -1092,8 +1138,6 @@ int dfs_cache_noreq_update_tgthint(const char *path, out_unlock: up_write(&htable_rw_lock); - free_normalized_path(path, npath); - return rc; } @@ -1101,32 +1145,26 @@ out_unlock: * dfs_cache_get_tgt_referral - returns a DFS referral (@ref) from a given * target iterator (@it). * - * @path: path to lookup in DFS referral cache. + * @path: canonical DFS path to lookup in DFS referral cache. * @it: DFS target iterator. * @ref: DFS referral pointer to set up the gathered information. * * Return zero if the DFS referral was set up correctly, otherwise non-zero. */ -int dfs_cache_get_tgt_referral(const char *path, - const struct dfs_cache_tgt_iterator *it, +int dfs_cache_get_tgt_referral(const char *path, const struct dfs_cache_tgt_iterator *it, struct dfs_info3_param *ref) { int rc; - const char *npath; struct cache_entry *ce; if (!it || !ref) return -EINVAL; - rc = get_normalized_path(path, &npath); - if (rc) - return rc; - - cifs_dbg(FYI, "%s: path: %s\n", __func__, npath); + cifs_dbg(FYI, "%s: path: %s\n", __func__, path); down_read(&htable_rw_lock); - ce = lookup_cache_entry(npath, NULL); + ce = lookup_cache_entry(path); if (IS_ERR(ce)) { rc = PTR_ERR(ce); goto out_unlock; @@ -1138,132 +1176,55 @@ int dfs_cache_get_tgt_referral(const char *path, out_unlock: up_read(&htable_rw_lock); - free_normalized_path(path, npath); - return rc; } /** - * dfs_cache_add_vol - add a cifs context during mount() that will be handled by - * DFS cache refresh worker. + * dfs_cache_add_refsrv_session - add SMB session of referral server * - * @mntdata: mount data. - * @ctx: cifs context. - * @fullpath: origin full path. - * - * Return zero if context was set up correctly, otherwise non-zero. + * @mount_id: mount group uuid to lookup. + * @ses: reference counted SMB session of referral server. */ -int dfs_cache_add_vol(char *mntdata, struct smb3_fs_context *ctx, const char *fullpath) +void dfs_cache_add_refsrv_session(const uuid_t *mount_id, struct cifs_ses *ses) { - int rc; - struct vol_info *vi; + struct mount_group *mg; - if (!ctx || !fullpath || !mntdata) - return -EINVAL; - - cifs_dbg(FYI, "%s: fullpath: %s\n", __func__, fullpath); - - vi = kzalloc(sizeof(*vi), GFP_KERNEL); - if (!vi) - return -ENOMEM; - - vi->fullpath = kstrdup(fullpath, GFP_KERNEL); - if (!vi->fullpath) { - rc = -ENOMEM; - goto err_free_vi; - } - - rc = smb3_fs_context_dup(&vi->ctx, ctx); - if (rc) - goto err_free_fullpath; - - vi->mntdata = mntdata; - spin_lock_init(&vi->ctx_lock); - kref_init(&vi->refcnt); - - spin_lock(&vol_list_lock); - list_add_tail(&vi->list, &vol_list); - spin_unlock(&vol_list_lock); - - return 0; - -err_free_fullpath: - kfree(vi->fullpath); -err_free_vi: - kfree(vi); - return rc; -} - -/* Must be called with vol_list_lock held */ -static struct vol_info *find_vol(const char *fullpath) -{ - struct vol_info *vi; - - list_for_each_entry(vi, &vol_list, list) { - cifs_dbg(FYI, "%s: vi->fullpath: %s\n", __func__, vi->fullpath); - if (!strcasecmp(vi->fullpath, fullpath)) - return vi; - } - return ERR_PTR(-ENOENT); -} - -/** - * dfs_cache_update_vol - update vol info in DFS cache after failover - * - * @fullpath: fullpath to look up in volume list. - * @server: TCP ses pointer. - * - * Return zero if volume was updated, otherwise non-zero. - */ -int dfs_cache_update_vol(const char *fullpath, struct TCP_Server_Info *server) -{ - struct vol_info *vi; - - if (!fullpath || !server) - return -EINVAL; - - cifs_dbg(FYI, "%s: fullpath: %s\n", __func__, fullpath); - - spin_lock(&vol_list_lock); - vi = find_vol(fullpath); - if (IS_ERR(vi)) { - spin_unlock(&vol_list_lock); - return PTR_ERR(vi); - } - kref_get(&vi->refcnt); - spin_unlock(&vol_list_lock); - - cifs_dbg(FYI, "%s: updating volume info\n", __func__); - spin_lock(&vi->ctx_lock); - memcpy(&vi->ctx.dstaddr, &server->dstaddr, - sizeof(vi->ctx.dstaddr)); - spin_unlock(&vi->ctx_lock); - - kref_put(&vi->refcnt, vol_release); - - return 0; -} - -/** - * dfs_cache_del_vol - remove volume info in DFS cache during umount() - * - * @fullpath: fullpath to look up in volume list. - */ -void dfs_cache_del_vol(const char *fullpath) -{ - struct vol_info *vi; - - if (!fullpath || !*fullpath) + if (WARN_ON_ONCE(!mount_id || uuid_is_null(mount_id) || !ses)) return; - cifs_dbg(FYI, "%s: fullpath: %s\n", __func__, fullpath); + mg = get_mount_group(mount_id); + if (WARN_ON_ONCE(IS_ERR(mg))) + return; - spin_lock(&vol_list_lock); - vi = find_vol(fullpath); - spin_unlock(&vol_list_lock); + spin_lock(&mg->lock); + if (mg->num_sessions < ARRAY_SIZE(mg->sessions)) + mg->sessions[mg->num_sessions++] = ses; + spin_unlock(&mg->lock); + kref_put(&mg->refcount, mount_group_release); +} - if (!IS_ERR(vi)) - kref_put(&vi->refcnt, vol_release); +/** + * dfs_cache_put_refsrv_sessions - put all referral server sessions + * + * Put all SMB sessions from the given mount group id. + * + * @mount_id: mount group uuid to lookup. + */ +void dfs_cache_put_refsrv_sessions(const uuid_t *mount_id) +{ + struct mount_group *mg; + + if (!mount_id || uuid_is_null(mount_id)) + return; + + mutex_lock(&mount_group_list_lock); + mg = find_mount_group_locked(mount_id); + if (IS_ERR(mg)) { + mutex_unlock(&mount_group_list_lock); + return; + } + mutex_unlock(&mount_group_list_lock); + kref_put(&mg->refcount, mount_group_release); } /** @@ -1276,8 +1237,8 @@ void dfs_cache_del_vol(const char *fullpath) * * Return zero if target was parsed correctly, otherwise non-zero. */ -int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it, - char **share, char **prefix) +int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it, char **share, + char **prefix) { char *s, sep, *p; size_t len; @@ -1332,278 +1293,190 @@ int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it, return 0; } -/* Get all tcons that are within a DFS namespace and can be refreshed */ -static void get_tcons(struct TCP_Server_Info *server, struct list_head *head) +/* + * Refresh all active dfs mounts regardless of whether they are in cache or not. + * (cache can be cleared) + */ +static void refresh_mounts(struct cifs_ses **sessions) { + struct TCP_Server_Info *server; struct cifs_ses *ses; - struct cifs_tcon *tcon; + struct cifs_tcon *tcon, *ntcon; + struct list_head tcons; + unsigned int xid; - INIT_LIST_HEAD(head); + INIT_LIST_HEAD(&tcons); spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { - list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { - if (!tcon->need_reconnect && !tcon->need_reopen_files && - tcon->dfs_path) { - tcon->tc_count++; - list_add_tail(&tcon->ulist, head); + list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { + if (tcon->dfs_path) { + tcon->tc_count++; + list_add_tail(&tcon->ulist, &tcons); + } } } - if (ses->tcon_ipc && !ses->tcon_ipc->need_reconnect && - ses->tcon_ipc->dfs_path) { - list_add_tail(&ses->tcon_ipc->ulist, head); - } } spin_unlock(&cifs_tcp_ses_lock); -} -static bool is_dfs_link(const char *path) -{ - char *s; + list_for_each_entry_safe(tcon, ntcon, &tcons, ulist) { + const char *path = tcon->dfs_path + 1; + struct cache_entry *ce; + struct dfs_info3_param *refs = NULL; + int numrefs = 0; + bool needs_refresh = false; + int rc = 0; - s = strchr(path + 1, '\\'); - if (!s) - return false; - return !!strchr(s + 1, '\\'); -} + list_del_init(&tcon->ulist); -static char *get_dfs_root(const char *path) -{ - char *s, *npath; + ses = find_ipc_from_server_path(sessions, path); + if (IS_ERR(ses)) + goto next_tcon; - s = strchr(path + 1, '\\'); - if (!s) - return ERR_PTR(-EINVAL); - - s = strchr(s + 1, '\\'); - if (!s) - return ERR_PTR(-EINVAL); - - npath = kstrndup(path, s - path, GFP_KERNEL); - if (!npath) - return ERR_PTR(-ENOMEM); - - return npath; -} - -static inline void put_tcp_server(struct TCP_Server_Info *server) -{ - cifs_put_tcp_session(server, 0); -} - -static struct TCP_Server_Info *get_tcp_server(struct smb3_fs_context *ctx) -{ - struct TCP_Server_Info *server; - - server = cifs_find_tcp_session(ctx); - if (IS_ERR_OR_NULL(server)) - return NULL; - - spin_lock(&GlobalMid_Lock); - if (server->tcpStatus != CifsGood) { - spin_unlock(&GlobalMid_Lock); - put_tcp_server(server); - return NULL; - } - spin_unlock(&GlobalMid_Lock); - - return server; -} - -/* Find root SMB session out of a DFS link path */ -static struct cifs_ses *find_root_ses(struct vol_info *vi, - struct cifs_tcon *tcon, - const char *path) -{ - char *rpath; - int rc; - struct cache_entry *ce; - struct dfs_info3_param ref = {0}; - char *mdata = NULL, *devname = NULL; - struct TCP_Server_Info *server; - struct cifs_ses *ses; - struct smb3_fs_context ctx = {NULL}; - - rpath = get_dfs_root(path); - if (IS_ERR(rpath)) - return ERR_CAST(rpath); - - down_read(&htable_rw_lock); - - ce = lookup_cache_entry(rpath, NULL); - if (IS_ERR(ce)) { + down_read(&htable_rw_lock); + ce = lookup_cache_entry(path); + needs_refresh = IS_ERR(ce) || cache_entry_expired(ce); up_read(&htable_rw_lock); - ses = ERR_CAST(ce); - goto out; - } - rc = setup_referral(path, ce, &ref, get_tgt_name(ce)); - if (rc) { - up_read(&htable_rw_lock); - ses = ERR_PTR(rc); - goto out; - } + if (!needs_refresh) + goto next_tcon; - up_read(&htable_rw_lock); + xid = get_xid(); + rc = get_dfs_referral(xid, ses, path, &refs, &numrefs); + free_xid(xid); - mdata = cifs_compose_mount_options(vi->mntdata, rpath, &ref, - &devname); - free_dfs_info_param(&ref); - - if (IS_ERR(mdata)) { - ses = ERR_CAST(mdata); - mdata = NULL; - goto out; - } - - rc = cifs_setup_volume_info(&ctx, NULL, devname); - - if (rc) { - ses = ERR_PTR(rc); - goto out; - } - - server = get_tcp_server(&ctx); - if (!server) { - ses = ERR_PTR(-EHOSTDOWN); - goto out; - } - - ses = cifs_get_smb_ses(server, &ctx); - -out: - smb3_cleanup_fs_context_contents(&ctx); - kfree(mdata); - kfree(rpath); - kfree(devname); - - return ses; -} - -/* Refresh DFS cache entry from a given tcon */ -static int refresh_tcon(struct vol_info *vi, struct cifs_tcon *tcon) -{ - int rc = 0; - unsigned int xid; - const char *path, *npath; - struct cache_entry *ce; - struct cifs_ses *root_ses = NULL, *ses; - struct dfs_info3_param *refs = NULL; - int numrefs = 0; - - xid = get_xid(); - - path = tcon->dfs_path + 1; - - rc = get_normalized_path(path, &npath); - if (rc) - goto out_free_xid; - - down_read(&htable_rw_lock); - - ce = lookup_cache_entry(npath, NULL); - if (IS_ERR(ce)) { - rc = PTR_ERR(ce); - up_read(&htable_rw_lock); - goto out_free_path; - } - - if (!cache_entry_expired(ce)) { - up_read(&htable_rw_lock); - goto out_free_path; - } - - up_read(&htable_rw_lock); - - /* If it's a DFS Link, then use root SMB session for refreshing it */ - if (is_dfs_link(npath)) { - ses = root_ses = find_root_ses(vi, tcon, npath); - if (IS_ERR(ses)) { - rc = PTR_ERR(ses); - root_ses = NULL; - goto out_free_path; + /* Create or update a cache entry with the new referral */ + if (!rc) { + down_write(&htable_rw_lock); + ce = lookup_cache_entry(path); + if (IS_ERR(ce)) + add_cache_entry_locked(refs, numrefs); + else if (cache_entry_expired(ce)) + update_cache_entry_locked(ce, refs, numrefs); + up_write(&htable_rw_lock); + } + +next_tcon: + free_dfs_info_array(refs, numrefs); + cifs_put_tcon(tcon); + } +} + +static void refresh_cache(struct cifs_ses **sessions) +{ + int i; + struct cifs_ses *ses; + unsigned int xid; + char *ref_paths[CACHE_MAX_ENTRIES]; + int count = 0; + struct cache_entry *ce; + + /* + * Refresh all cached entries. Get all new referrals outside critical section to avoid + * starvation while performing SMB2 IOCTL on broken or slow connections. + + * The cache entries may cover more paths than the active mounts + * (e.g. domain-based DFS referrals or multi tier DFS setups). + */ + down_read(&htable_rw_lock); + for (i = 0; i < CACHE_HTABLE_SIZE; i++) { + struct hlist_head *l = &cache_htable[i]; + + hlist_for_each_entry(ce, l, hlist) { + if (count == ARRAY_SIZE(ref_paths)) + goto out_unlock; + if (hlist_unhashed(&ce->hlist) || !cache_entry_expired(ce) || + IS_ERR(find_ipc_from_server_path(sessions, ce->path))) + continue; + ref_paths[count++] = kstrdup(ce->path, GFP_ATOMIC); } - } else { - ses = tcon->ses; } - rc = get_dfs_referral(xid, ses, cache_nlsc, tcon->remap, npath, &refs, - &numrefs); - if (!rc) { - dump_refs(refs, numrefs); - rc = update_cache_entry(npath, refs, numrefs); +out_unlock: + up_read(&htable_rw_lock); + + for (i = 0; i < count; i++) { + char *path = ref_paths[i]; + struct dfs_info3_param *refs = NULL; + int numrefs = 0; + int rc = 0; + + if (!path) + continue; + + ses = find_ipc_from_server_path(sessions, path); + if (IS_ERR(ses)) + goto next_referral; + + xid = get_xid(); + rc = get_dfs_referral(xid, ses, path, &refs, &numrefs); + free_xid(xid); + + if (!rc) { + down_write(&htable_rw_lock); + ce = lookup_cache_entry(path); + /* + * We need to re-check it because other tasks might have it deleted or + * updated. + */ + if (!IS_ERR(ce) && cache_entry_expired(ce)) + update_cache_entry_locked(ce, refs, numrefs); + up_write(&htable_rw_lock); + } + +next_referral: + kfree(path); free_dfs_info_array(refs, numrefs); } - - if (root_ses) - cifs_put_smb_ses(root_ses); - -out_free_path: - free_normalized_path(path, npath); - -out_free_xid: - free_xid(xid); - return rc; } /* - * Worker that will refresh DFS cache based on lowest TTL value from a DFS + * Worker that will refresh DFS cache and active mounts based on lowest TTL value from a DFS * referral. */ static void refresh_cache_worker(struct work_struct *work) { - struct vol_info *vi, *nvi; - struct TCP_Server_Info *server; - LIST_HEAD(vols); - LIST_HEAD(tcons); - struct cifs_tcon *tcon, *ntcon; - int rc; + struct list_head mglist; + struct mount_group *mg, *tmp_mg; + struct cifs_ses *sessions[CACHE_MAX_ENTRIES + 1] = {NULL}; + int max_sessions = ARRAY_SIZE(sessions) - 1; + int i = 0, count; - /* - * Find SMB volumes that are eligible (server->tcpStatus == CifsGood) - * for refreshing. - */ - spin_lock(&vol_list_lock); - list_for_each_entry(vi, &vol_list, list) { - server = get_tcp_server(&vi->ctx); - if (!server) - continue; + INIT_LIST_HEAD(&mglist); - kref_get(&vi->refcnt); - list_add_tail(&vi->rlist, &vols); - put_tcp_server(server); + /* Get refereces of mount groups */ + mutex_lock(&mount_group_list_lock); + list_for_each_entry(mg, &mount_group_list, list) { + kref_get(&mg->refcount); + list_add(&mg->refresh_list, &mglist); } - spin_unlock(&vol_list_lock); + mutex_unlock(&mount_group_list_lock); - /* Walk through all TCONs and refresh any expired cache entry */ - list_for_each_entry_safe(vi, nvi, &vols, rlist) { - spin_lock(&vi->ctx_lock); - server = get_tcp_server(&vi->ctx); - spin_unlock(&vi->ctx_lock); + /* Fill in local array with an NULL-terminated list of all referral server sessions */ + list_for_each_entry(mg, &mglist, refresh_list) { + if (i >= max_sessions) + break; - if (!server) - goto next_vol; + spin_lock(&mg->lock); + if (i + mg->num_sessions > max_sessions) + count = max_sessions - i; + else + count = mg->num_sessions; + memcpy(&sessions[i], mg->sessions, count * sizeof(mg->sessions[0])); + spin_unlock(&mg->lock); + i += count; + } - get_tcons(server, &tcons); - rc = 0; + if (sessions[0]) { + /* Refresh all active mounts and cached entries */ + refresh_mounts(sessions); + refresh_cache(sessions); + } - list_for_each_entry_safe(tcon, ntcon, &tcons, ulist) { - /* - * Skip tcp server if any of its tcons failed to refresh - * (possibily due to reconnects). - */ - if (!rc) - rc = refresh_tcon(vi, tcon); - - list_del_init(&tcon->ulist); - cifs_put_tcon(tcon); - } - - put_tcp_server(server); - -next_vol: - list_del_init(&vi->rlist); - kref_put(&vi->refcnt, vol_release); + list_for_each_entry_safe(mg, tmp_mg, &mglist, refresh_list) { + list_del_init(&mg->refresh_list); + kref_put(&mg->refcount, mount_group_release); } spin_lock(&cache_ttl_lock); diff --git a/fs/cifs/dfs_cache.h b/fs/cifs/dfs_cache.h index 1afc4f590c47..b29d3ae64829 100644 --- a/fs/cifs/dfs_cache.h +++ b/fs/cifs/dfs_cache.h @@ -10,6 +10,7 @@ #include #include +#include #include "cifsglob.h" struct dfs_cache_tgt_list { @@ -23,34 +24,26 @@ struct dfs_cache_tgt_iterator { struct list_head it_list; }; -extern int dfs_cache_init(void); -extern void dfs_cache_destroy(void); +int dfs_cache_init(void); +void dfs_cache_destroy(void); extern const struct proc_ops dfscache_proc_ops; -extern int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, - const struct nls_table *nls_codepage, int remap, - const char *path, struct dfs_info3_param *ref, - struct dfs_cache_tgt_list *tgt_list); -extern int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref, - struct dfs_cache_tgt_list *tgt_list); -extern int dfs_cache_update_tgthint(const unsigned int xid, - struct cifs_ses *ses, - const struct nls_table *nls_codepage, - int remap, const char *path, - const struct dfs_cache_tgt_iterator *it); -extern int -dfs_cache_noreq_update_tgthint(const char *path, - const struct dfs_cache_tgt_iterator *it); -extern int dfs_cache_get_tgt_referral(const char *path, - const struct dfs_cache_tgt_iterator *it, - struct dfs_info3_param *ref); -extern int dfs_cache_add_vol(char *mntdata, struct smb3_fs_context *ctx, - const char *fullpath); -extern int dfs_cache_update_vol(const char *fullpath, - struct TCP_Server_Info *server); -extern void dfs_cache_del_vol(const char *fullpath); -extern int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it, - char **share, char **prefix); +int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, const struct nls_table *cp, + int remap, const char *path, struct dfs_info3_param *ref, + struct dfs_cache_tgt_list *tgt_list); +int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref, + struct dfs_cache_tgt_list *tgt_list); +int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses, + const struct nls_table *cp, int remap, const char *path, + const struct dfs_cache_tgt_iterator *it); +int dfs_cache_noreq_update_tgthint(const char *path, const struct dfs_cache_tgt_iterator *it); +int dfs_cache_get_tgt_referral(const char *path, const struct dfs_cache_tgt_iterator *it, + struct dfs_info3_param *ref); +int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it, char **share, + char **prefix); +void dfs_cache_put_refsrv_sessions(const uuid_t *mount_id); +void dfs_cache_add_refsrv_session(const uuid_t *mount_id, struct cifs_ses *ses); +char *dfs_cache_canonical_path(const char *path, const struct nls_table *cp, int remap); static inline struct dfs_cache_tgt_iterator * dfs_cache_get_next_tgt(struct dfs_cache_tgt_list *tl, diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 6bcd3e8f7cda..79402ca0ddfa 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/dir.c * @@ -6,19 +7,6 @@ * Copyright (C) International Business Machines Corp., 2002,2009 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include #include @@ -396,10 +384,11 @@ cifs_create_set_dentry: goto out_err; } - if (S_ISDIR(newinode->i_mode)) { - rc = -EISDIR; - goto out_err; - } + if (newinode) + if (S_ISDIR(newinode->i_mode)) { + rc = -EISDIR; + goto out_err; + } d_drop(direntry); d_add(direntry, newinode); @@ -630,6 +619,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, struct inode *newInode = NULL; const char *full_path; void *page; + int retry_count = 0; xid = get_xid(); @@ -673,6 +663,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, cifs_dbg(FYI, "Full path: %s inode = 0x%p\n", full_path, d_inode(direntry)); +again: if (pTcon->posix_extensions) rc = smb311_posix_get_inode_info(&newInode, full_path, parent_dir_inode->i_sb, xid); else if (pTcon->unix_ext) { @@ -687,6 +678,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, /* since paths are not looked up by component - the parent directories are presumed to be good here */ renew_parental_timestamps(direntry); + } else if (rc == -EAGAIN && retry_count++ < 10) { + goto again; } else if (rc == -ENOENT) { cifs_set_time(direntry, jiffies); newInode = NULL; diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index 534cbba72789..d15b82d569ef 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/dns_resolve.c * @@ -10,19 +11,6 @@ * Contains the CIFS DFS upcall routines used for hostname to * IP address translation. * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include diff --git a/fs/cifs/dns_resolve.h b/fs/cifs/dns_resolve.h index d3f5d27f4d06..5be060b82b13 100644 --- a/fs/cifs/dns_resolve.h +++ b/fs/cifs/dns_resolve.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/dns_resolve.h -- DNS Resolver upcall management for CIFS DFS * Handles host name to IP address resolution @@ -5,19 +6,6 @@ * Copyright (c) International Business Machines Corp., 2008 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _DNS_RESOLVE_H diff --git a/fs/cifs/export.c b/fs/cifs/export.c index eb0bb8ca8e63..747a540db954 100644 --- a/fs/cifs/export.c +++ b/fs/cifs/export.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/export.c * @@ -8,19 +9,6 @@ * * Operations related to support for exporting files via NFSD * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 379a427f3c2f..cd108607a070 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/file.c * @@ -7,19 +8,6 @@ * Author(s): Steve French (sfrench@us.ibm.com) * Jeremy Allison (jra@samba.org) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include #include diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 20d24af33ee2..dd625033cd6b 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -1,22 +1,10 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/fscache.c - CIFS filesystem cache interface * * Copyright (c) 2010 Novell, Inc. * Author(s): Suresh Jayaraman * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include "fscache.h" #include "cifsglob.h" diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h index e811f2dd7619..3d55cb2ef055 100644 --- a/fs/cifs/fscache.h +++ b/fs/cifs/fscache.h @@ -1,22 +1,10 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/fscache.h - CIFS filesystem cache interface definitions * * Copyright (c) 2010 Novell, Inc. * Authors(s): Suresh Jayaraman (sjayaraman@suse.de> * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _CIFS_FSCACHE_H #define _CIFS_FSCACHE_H diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 1dfa57982522..b96b253e7635 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1,22 +1,10 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/inode.c * * Copyright (C) International Business Machines Corp., 2002,2010 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include #include @@ -367,9 +355,12 @@ cifs_get_file_info_unix(struct file *filp) } else if (rc == -EREMOTE) { cifs_create_dfs_fattr(&fattr, inode->i_sb); rc = 0; - } + } else + goto cifs_gfiunix_out; rc = cifs_fattr_to_inode(inode, &fattr); + +cifs_gfiunix_out: free_xid(xid); return rc; } diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index d67d281ab863..42c6a0bac6c8 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/ioctl.c * @@ -6,19 +7,6 @@ * Copyright (C) International Business Machines Corp., 2005,2013 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 970fcf2adb08..f0a6d63bc08c 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -1,22 +1,10 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/link.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include #include diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 7207a63819cb..184138b4eb8c 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -1,22 +1,10 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/misc.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include diff --git a/fs/cifs/netlink.c b/fs/cifs/netlink.c index 5aaabe4cc0a7..291cb606f149 100644 --- a/fs/cifs/netlink.c +++ b/fs/cifs/netlink.c @@ -30,7 +30,7 @@ static const struct nla_policy cifs_genl_policy[CIFS_GENL_ATTR_MAX + 1] = { [CIFS_GENL_ATTR_SWN_RESOURCE_NAME] = { .type = NLA_STRING}, }; -static struct genl_ops cifs_genl_ops[] = { +static const struct genl_ops cifs_genl_ops[] = { { .cmd = CIFS_GENL_CMD_SWN_NOTIFY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h index 3079b38f0afb..378133ce8869 100644 --- a/fs/cifs/ntlmssp.h +++ b/fs/cifs/ntlmssp.h @@ -1,22 +1,10 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/ntlmssp.h * * Copyright (c) International Business Machines Corp., 2002,2007 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #define NTLMSSP_SIGNATURE "NTLMSSP" diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 63bfc533c9fb..bfee176b901d 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/readdir.c * @@ -7,19 +8,6 @@ * Copyright (C) Red Hat, Inc., 2011 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include #include @@ -321,7 +309,7 @@ static void cifs_fulldir_info_to_fattr(struct cifs_fattr *fattr, { __dir_info_to_fattr(fattr, info); - /* See MS-FSCC 2.4.18 FileIdFullDirectoryInformation */ + /* See MS-FSCC 2.4.19 FileIdFullDirectoryInformation */ if (fattr->cf_cifsattrs & ATTR_REPARSE) fattr->cf_cifstag = le32_to_cpu(info->EaSize); cifs_fill_common_info(fattr, cifs_sb); diff --git a/fs/cifs/rfc1002pdu.h b/fs/cifs/rfc1002pdu.h index 8b69fcceb597..137f7c95afd6 100644 --- a/fs/cifs/rfc1002pdu.h +++ b/fs/cifs/rfc1002pdu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/rfc1002pdu.h * @@ -6,19 +7,6 @@ * Copyright (c) International Business Machines Corp., 2004 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* NB: unlike smb/cifs packets, the RFC1002 structures are big endian */ diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index a92a1fb7cb52..c5785fd3f52e 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/sess.c * @@ -6,19 +7,6 @@ * Copyright (c) International Business Machines Corp., 2006, 2009 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include "cifspdu.h" @@ -195,7 +183,7 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, ses, iface->speed, iface->rdma_capable ? "yes" : "no", &ipv4->sin_addr); else - cifs_dbg(FYI, "adding channel to ses %p (speed:%zu bps rdma:%s ip:%pI4)\n", + cifs_dbg(FYI, "adding channel to ses %p (speed:%zu bps rdma:%s ip:%pI6)\n", ses, iface->speed, iface->rdma_capable ? "yes" : "no", &ipv6->sin6_addr); diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 2fa3ba354cc9..c9d8a50062b8 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/smb2file.c * @@ -5,19 +6,6 @@ * Author(s): Steve French (sfrench@us.ibm.com), * Pavel Shilovsky ((pshilovsky@samba.org) 2012 * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include #include diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index d9a990c99121..d0e9f3782bd9 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/smb2glob.h * @@ -9,16 +10,6 @@ * Jeremy Allison (jra@samba.org) * Pavel Shilovsky (pshilovsky@samba.org) 2012 * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * */ #ifndef _SMB2_GLOB_H #define _SMB2_GLOB_H diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 9a61209a283e..957b2594f02e 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/smb2inode.c * @@ -6,19 +7,6 @@ * Author(s): Pavel Shilovsky (pshilovsky@samba.org), * Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include #include diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index c775682ee973..cea39bcecbab 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/smb2/smb2maperror.c * @@ -6,19 +7,6 @@ * Copyright (C) International Business Machines Corp., 2009 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include #include "cifsglob.h" diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 06d555d4da9a..668f77108831 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/smb2misc.c * @@ -6,19 +7,6 @@ * Author(s): Steve French (sfrench@us.ibm.com) * Pavel Shilovsky (pshilovsky@samba.org) 2012 * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include #include "smb2pdu.h" @@ -164,19 +152,16 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) struct smb2_transform_hdr *thdr = (struct smb2_transform_hdr *)buf; struct cifs_ses *ses = NULL; - struct list_head *tmp; /* decrypt frame now that it is completely read in */ spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp, &srvr->smb_ses_list) { - ses = list_entry(tmp, struct cifs_ses, smb_ses_list); + list_for_each_entry(ses, &srvr->smb_ses_list, smb_ses_list) { if (ses->Suid == thdr->SessionId) break; - - ses = NULL; } spin_unlock(&cifs_tcp_ses_lock); - if (ses == NULL) { + if (list_entry_is_head(ses, &srvr->smb_ses_list, + smb_ses_list)) { cifs_dbg(VFS, "no decryption - session id not found\n"); return 1; } @@ -548,7 +533,6 @@ static bool smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp) { __u8 lease_state; - struct list_head *tmp; struct cifsFileInfo *cfile; struct cifsInodeInfo *cinode; int ack_req = le32_to_cpu(rsp->Flags & @@ -556,8 +540,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp) lease_state = le32_to_cpu(rsp->NewLeaseState); - list_for_each(tmp, &tcon->openFileList) { - cfile = list_entry(tmp, struct cifsFileInfo, tlist); + list_for_each_entry(cfile, &tcon->openFileList, tlist) { cinode = CIFS_I(d_inode(cfile->dentry)); if (memcmp(cinode->lease_key, rsp->LeaseKey, @@ -618,7 +601,6 @@ static bool smb2_is_valid_lease_break(char *buffer) { struct smb2_lease_break *rsp = (struct smb2_lease_break *)buffer; - struct list_head *tmp, *tmp1, *tmp2; struct TCP_Server_Info *server; struct cifs_ses *ses; struct cifs_tcon *tcon; @@ -628,15 +610,9 @@ smb2_is_valid_lease_break(char *buffer) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp, &cifs_tcp_ses_list) { - server = list_entry(tmp, struct TCP_Server_Info, tcp_ses_list); - - list_for_each(tmp1, &server->smb_ses_list) { - ses = list_entry(tmp1, struct cifs_ses, smb_ses_list); - - list_for_each(tmp2, &ses->tcon_list) { - tcon = list_entry(tmp2, struct cifs_tcon, - tcon_list); + list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); cifs_stats_inc( &tcon->stats.cifs_stats.num_oplock_brks); @@ -687,7 +663,6 @@ bool smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) { struct smb2_oplock_break *rsp = (struct smb2_oplock_break *)buffer; - struct list_head *tmp, *tmp1, *tmp2; struct cifs_ses *ses; struct cifs_tcon *tcon; struct cifsInodeInfo *cinode; @@ -710,16 +685,11 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); - list_for_each(tmp, &server->smb_ses_list) { - ses = list_entry(tmp, struct cifs_ses, smb_ses_list); - - list_for_each(tmp1, &ses->tcon_list) { - tcon = list_entry(tmp1, struct cifs_tcon, tcon_list); + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); - list_for_each(tmp2, &tcon->openFileList) { - cfile = list_entry(tmp2, struct cifsFileInfo, - tlist); + list_for_each_entry(cfile, &tcon->openFileList, tlist) { if (rsp->PersistentFid != cfile->fid.persistent_fid || rsp->VolatileFid != diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 21ef51d338e0..e4c8f603dd58 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -388,7 +388,9 @@ smb2_negotiate(const unsigned int xid, struct cifs_ses *ses) { int rc; + spin_lock(&GlobalMid_Lock); cifs_ses_server(ses)->CurrentMid = 0; + spin_unlock(&GlobalMid_Lock); rc = SMB2_negotiate(xid, ses); /* BB we probably don't need to retry with modern servers */ if (rc == -EAGAIN) @@ -2325,6 +2327,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, struct smb2_query_directory_rsp *qd_rsp = NULL; struct smb2_create_rsp *op_rsp = NULL; struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses); + int retry_count = 0; utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); if (!utf16_path) @@ -2372,10 +2375,14 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, smb2_set_related(&rqst[1]); +again: rc = compound_send_recv(xid, tcon->ses, server, flags, 2, rqst, resp_buftype, rsp_iov); + if (rc == -EAGAIN && retry_count++ < 10) + goto again; + /* If the open failed there is nothing to do */ op_rsp = (struct smb2_create_rsp *)rsp_iov[0].iov_base; if (op_rsp == NULL || op_rsp->sync_hdr.Status != STATUS_SUCCESS) { @@ -3601,6 +3608,119 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, return rc; } +static int smb3_simple_fallocate_write_range(unsigned int xid, + struct cifs_tcon *tcon, + struct cifsFileInfo *cfile, + loff_t off, loff_t len, + char *buf) +{ + struct cifs_io_parms io_parms = {0}; + int nbytes; + struct kvec iov[2]; + + io_parms.netfid = cfile->fid.netfid; + io_parms.pid = current->tgid; + io_parms.tcon = tcon; + io_parms.persistent_fid = cfile->fid.persistent_fid; + io_parms.volatile_fid = cfile->fid.volatile_fid; + io_parms.offset = off; + io_parms.length = len; + + /* iov[0] is reserved for smb header */ + iov[1].iov_base = buf; + iov[1].iov_len = io_parms.length; + return SMB2_write(xid, &io_parms, &nbytes, iov, 1); +} + +static int smb3_simple_fallocate_range(unsigned int xid, + struct cifs_tcon *tcon, + struct cifsFileInfo *cfile, + loff_t off, loff_t len) +{ + struct file_allocated_range_buffer in_data, *out_data = NULL, *tmp_data; + u32 out_data_len; + char *buf = NULL; + loff_t l; + int rc; + + in_data.file_offset = cpu_to_le64(off); + in_data.length = cpu_to_le64(len); + rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + FSCTL_QUERY_ALLOCATED_RANGES, true, + (char *)&in_data, sizeof(in_data), + 1024 * sizeof(struct file_allocated_range_buffer), + (char **)&out_data, &out_data_len); + if (rc) + goto out; + /* + * It is already all allocated + */ + if (out_data_len == 0) + goto out; + + buf = kzalloc(1024 * 1024, GFP_KERNEL); + if (buf == NULL) { + rc = -ENOMEM; + goto out; + } + + tmp_data = out_data; + while (len) { + /* + * The rest of the region is unmapped so write it all. + */ + if (out_data_len == 0) { + rc = smb3_simple_fallocate_write_range(xid, tcon, + cfile, off, len, buf); + goto out; + } + + if (out_data_len < sizeof(struct file_allocated_range_buffer)) { + rc = -EINVAL; + goto out; + } + + if (off < le64_to_cpu(tmp_data->file_offset)) { + /* + * We are at a hole. Write until the end of the region + * or until the next allocated data, + * whichever comes next. + */ + l = le64_to_cpu(tmp_data->file_offset) - off; + if (len < l) + l = len; + rc = smb3_simple_fallocate_write_range(xid, tcon, + cfile, off, l, buf); + if (rc) + goto out; + off = off + l; + len = len - l; + if (len == 0) + goto out; + } + /* + * We are at a section of allocated data, just skip forward + * until the end of the data or the end of the region + * we are supposed to fallocate, whichever comes first. + */ + l = le64_to_cpu(tmp_data->length); + if (len < l) + l = len; + off += l; + len -= l; + + tmp_data = &tmp_data[1]; + out_data_len -= sizeof(struct file_allocated_range_buffer); + } + + out: + kfree(out_data); + kfree(buf); + return rc; +} + + static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, loff_t off, loff_t len, bool keep_size) { @@ -3661,6 +3781,26 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, } if ((keep_size == true) || (i_size_read(inode) >= off + len)) { + /* + * At this point, we are trying to fallocate an internal + * regions of a sparse file. Since smb2 does not have a + * fallocate command we have two otions on how to emulate this. + * We can either turn the entire file to become non-sparse + * which we only do if the fallocate is for virtually + * the whole file, or we can overwrite the region with zeroes + * using SMB2_write, which could be prohibitevly expensive + * if len is large. + */ + /* + * We are only trying to fallocate a small region so + * just write it with zero. + */ + if (len <= 1024 * 1024) { + rc = smb3_simple_fallocate_range(xid, tcon, cfile, + off, len); + goto out; + } + /* * Check if falloc starts within first few pages of file * and ends within a few pages of the end of file to diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index c205f93e0a10..962826dc3316 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/smb2pdu.c * @@ -8,19 +9,6 @@ * * Contains the routines for constructing the SMB2 PDUs themselves * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* SMB2 PDU handling routines here - except for leftovers (eg session setup) */ @@ -1791,10 +1779,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, rsp = (struct smb2_tree_connect_rsp *)rsp_iov.iov_base; trace_smb3_tcon(xid, tcon->tid, ses->Suid, tree, rc); if (rc != 0) { - if (tcon) { - cifs_stats_fail_inc(tcon, SMB2_TREE_CONNECT_HE); - tcon->need_reconnect = true; - } + cifs_stats_fail_inc(tcon, SMB2_TREE_CONNECT_HE); + tcon->need_reconnect = true; goto tcon_error_exit; } @@ -2906,7 +2892,10 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, #endif /* CIFS_DEBUG2 */ if (buf) { - memcpy(buf, &rsp->CreationTime, 32); + buf->CreationTime = rsp->CreationTime; + buf->LastAccessTime = rsp->LastAccessTime; + buf->LastWriteTime = rsp->LastWriteTime; + buf->ChangeTime = rsp->ChangeTime; buf->AllocationSize = rsp->AllocationSize; buf->EndOfFile = rsp->EndofFile; buf->Attributes = rsp->FileAttributes; @@ -3484,6 +3473,8 @@ int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, NULL); } +#if 0 +/* currently unused, as now we are doing compounding instead (see smb311_posix_query_path_info) */ int SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, struct smb311_posix_qinfo *data, u32 *plen) @@ -3495,7 +3486,9 @@ SMB311_posix_query_info(const unsigned int xid, struct cifs_tcon *tcon, return query_info(xid, tcon, persistent_fid, volatile_fid, SMB_FIND_FILE_POSIX_INFO, SMB2_O_INFO_FILE, 0, output_len, sizeof(struct smb311_posix_qinfo), (void **)&data, plen); + /* Note caller must free "data" (passed in above). It may be allocated in query_info call */ } +#endif int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon, @@ -4498,7 +4491,7 @@ int posix_info_parse(const void *beg, const void *end, { int total_len = 0; - int sid_len; + int owner_len, group_len; int name_len; const void *owner_sid; const void *group_sid; @@ -4521,17 +4514,17 @@ int posix_info_parse(const void *beg, const void *end, /* check owner sid */ owner_sid = beg + total_len; - sid_len = posix_info_sid_size(owner_sid, end); - if (sid_len < 0) + owner_len = posix_info_sid_size(owner_sid, end); + if (owner_len < 0) return -1; - total_len += sid_len; + total_len += owner_len; /* check group sid */ group_sid = beg + total_len; - sid_len = posix_info_sid_size(group_sid, end); - if (sid_len < 0) + group_len = posix_info_sid_size(group_sid, end); + if (group_len < 0) return -1; - total_len += sid_len; + total_len += group_len; /* check name len */ if (beg + total_len + 4 > end) @@ -4552,10 +4545,8 @@ int posix_info_parse(const void *beg, const void *end, out->size = total_len; out->name_len = name_len; out->name = name; - memcpy(&out->owner, owner_sid, - posix_info_sid_size(owner_sid, end)); - memcpy(&out->group, group_sid, - posix_info_sid_size(group_sid, end)); + memcpy(&out->owner, owner_sid, owner_len); + memcpy(&out->group, group_sid, group_len); } return total_len; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 6442dc1c292b..a5c48b85549a 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/smb2pdu.h * @@ -6,19 +7,6 @@ * Author(s): Steve French (sfrench@us.ibm.com) * Pavel Shilovsky (pshilovsky@samba.org) 2012 * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _SMB2PDU_H @@ -276,7 +264,7 @@ struct share_redirect_error_context_rsp { __le32 NotificationType; __le32 ResourceNameOffset; __le32 ResourceNameLength; - __le16 Flags; + __le16 Reserved; __le16 TargetType; __le32 IPAddrCount; struct move_dst_ipaddr IpAddrMoveList[]; @@ -1460,6 +1448,22 @@ struct smb2_echo_rsp { #define SMB2_QUERY_DIRECTORY_IOV_SIZE 2 +/* + * Valid FileInformation classes. + * + * Note that these are a subset of the (file) QUERY_INFO levels defined + * later in this file (but since QUERY_DIRECTORY uses equivalent numbers + * we do not redefine them here) + * + * FileDirectoryInfomation 0x01 + * FileFullDirectoryInformation 0x02 + * FileIdFullDirectoryInformation 0x26 + * FileBothDirectoryInformation 0x03 + * FileIdBothDirectoryInformation 0x25 + * FileNamesInformation 0x0C + * FileIdExtdDirectoryInformation 0x3C + */ + struct smb2_query_directory_req { struct smb2_sync_hdr sync_hdr; __le16 StructureSize; /* Must be 33 */ @@ -1696,6 +1700,7 @@ struct smb3_fs_vol_info { #define FILEID_GLOBAL_TX_DIRECTORY_INFORMATION 50 #define FILE_STANDARD_LINK_INFORMATION 54 #define FILE_ID_INFORMATION 59 +#define FILE_ID_EXTD_DIRECTORY_INFORMATION 60 struct smb2_file_internal_info { __le64 IndexNumber; @@ -1776,13 +1781,31 @@ struct smb2_file_network_open_info { __le32 Reserved; } __packed; /* level 34 Query also similar returned in close rsp and open rsp */ -/* See MS-FSCC 2.4.43 */ +/* See MS-FSCC 2.4.21 */ struct smb2_file_id_information { __le64 VolumeSerialNumber; __u64 PersistentFileId; /* opaque endianness */ __u64 VolatileFileId; /* opaque endianness */ } __packed; /* level 59 */ +/* See MS-FSCC 2.4.18 */ +struct smb2_file_id_extd_directory_info { + __le32 NextEntryOffset; + __u32 FileIndex; + __le64 CreationTime; + __le64 LastAccessTime; + __le64 LastWriteTime; + __le64 ChangeTime; + __le64 EndOfFile; + __le64 AllocationSize; + __le32 FileAttributes; + __le32 FileNameLength; + __le32 EaSize; /* EA size */ + __le32 ReparsePointTag; /* valid if FILE_ATTR_REPARSE_POINT set in FileAttributes */ + __le64 UniqueId; /* inode num - le since Samba puts ino in low 32 bit */ + char FileName[1]; +} __packed; /* level 60 */ + extern char smb2_padding[7]; /* equivalent of the contents of SMB3.1.1 POSIX open context response */ diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index a5f87b02cfaf..263767f644f8 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/smb2proto.h * @@ -6,19 +7,6 @@ * Author(s): Steve French (sfrench@us.ibm.com) * Pavel Shilovsky (pshilovsky@samba.org) 2012 * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _SMB2PROTO_H #define _SMB2PROTO_H @@ -64,8 +52,6 @@ extern void smb2_echo_request(struct work_struct *work); extern __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode); extern bool smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv); -extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server, - __u64 ses_id); extern int smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid); diff --git a/fs/cifs/smb2status.h b/fs/cifs/smb2status.h index 7505056e9580..0215ef36e240 100644 --- a/fs/cifs/smb2status.h +++ b/fs/cifs/smb2status.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/smb2status.h * @@ -7,19 +8,6 @@ * Copyright (c) International Business Machines Corp., 2009,2011 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index e6fa76ab70be..6f7952ea4941 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/smb2transport.c * @@ -7,19 +8,6 @@ * Jeremy Allison (jra@samba.org) 2006 * Pavel Shilovsky (pshilovsky@samba.org) 2012 * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include @@ -154,6 +142,7 @@ smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id) list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { if (ses->Suid != ses_id) continue; + ++ses->ses_count; return ses; } @@ -205,7 +194,14 @@ smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid) return NULL; } tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid); + if (!tcon) { + cifs_put_smb_ses(ses); + spin_unlock(&cifs_tcp_ses_lock); + return NULL; + } spin_unlock(&cifs_tcp_ses_lock); + /* tcon already has a ref to ses, so we don't need ses anymore */ + cifs_put_smb_ses(ses); return tcon; } @@ -239,7 +235,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, if (rc) { cifs_server_dbg(VFS, "%s: sha256 alloc failed\n", __func__); - return rc; + goto out; } shash = &sdesc->shash; } else { @@ -290,6 +286,8 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, out: if (allocate_crypto) cifs_free_hash(&hash, &sdesc); + if (ses) + cifs_put_smb_ses(ses); return rc; } diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 10dfe5006792..31ef64eb7fbb 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -572,8 +572,13 @@ static struct rdma_cm_id *smbd_create_id( log_rdma_event(ERR, "rdma_resolve_addr() failed %i\n", rc); goto out; } - wait_for_completion_interruptible_timeout( + rc = wait_for_completion_interruptible_timeout( &info->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT)); + /* e.g. if interrupted returns -ERESTARTSYS */ + if (rc < 0) { + log_rdma_event(ERR, "rdma_resolve_addr timeout rc: %i\n", rc); + goto out; + } rc = info->ri_rc; if (rc) { log_rdma_event(ERR, "rdma_resolve_addr() completed %i\n", rc); @@ -586,8 +591,13 @@ static struct rdma_cm_id *smbd_create_id( log_rdma_event(ERR, "rdma_resolve_route() failed %i\n", rc); goto out; } - wait_for_completion_interruptible_timeout( + rc = wait_for_completion_interruptible_timeout( &info->ri_done, msecs_to_jiffies(RDMA_RESOLVE_TIMEOUT)); + /* e.g. if interrupted returns -ERESTARTSYS */ + if (rc < 0) { + log_rdma_event(ERR, "rdma_resolve_addr timeout rc: %i\n", rc); + goto out; + } rc = info->ri_rc; if (rc) { log_rdma_event(ERR, "rdma_resolve_route() completed %i\n", rc); diff --git a/fs/cifs/smberr.h b/fs/cifs/smberr.h index 7f16cb825fe5..60189efb3236 100644 --- a/fs/cifs/smberr.h +++ b/fs/cifs/smberr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/smberr.h * @@ -7,19 +8,6 @@ * See Error Codes section of the SNIA CIFS Specification * for more information * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #define SUCCESS 0x00 /* The request was successful. */ diff --git a/fs/cifs/smbfsctl.h b/fs/cifs/smbfsctl.h index a0e84747f567..d0fc42061f49 100644 --- a/fs/cifs/smbfsctl.h +++ b/fs/cifs/smbfsctl.h @@ -1,22 +1,10 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ /* * fs/cifs/smbfsctl.h: SMB, CIFS, SMB2 FSCTL definitions * * Copyright (c) International Business Machines Corp., 2002,2013 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* IOCTL information */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index c1725b55f364..f65f9a692ca2 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/transport.c * @@ -5,19 +6,6 @@ * Author(s): Steve French (sfrench@us.ibm.com) * Jeremy Allison (jra@samba.org) 2006. * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index aa3e8ca0457c..9ed481e79ce0 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -1,22 +1,10 @@ +// SPDX-License-Identifier: LGPL-2.1 /* * fs/cifs/xattr.c * * Copyright (c) International Business Machines Corp., 2003, 2007 * Author(s): Steve French (sfrench@us.ibm.com) * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU Lesser General Public License as published - * by the Free Software Foundation; either version 2.1 of the License, or - * (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index eb5ec3e46283..b601610e9907 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -28,12 +28,6 @@ static struct lock_class_key default_group_class[MAX_LOCK_DEPTH]; #endif -static const struct address_space_operations configfs_aops = { - .readpage = simple_readpage, - .write_begin = simple_write_begin, - .write_end = simple_write_end, -}; - static const struct inode_operations configfs_inode_operations ={ .setattr = configfs_setattr, }; @@ -114,7 +108,7 @@ struct inode *configfs_new_inode(umode_t mode, struct configfs_dirent *sd, struct inode * inode = new_inode(s); if (inode) { inode->i_ino = get_next_ino(); - inode->i_mapping->a_ops = &configfs_aops; + inode->i_mapping->a_ops = &ram_aops; inode->i_op = &configfs_inode_operations; if (sd->s_iattr) { diff --git a/fs/dax.c b/fs/dax.c index 62352cbcf0f4..da41f9363568 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -488,10 +488,11 @@ static void *grab_mapping_entry(struct xa_state *xas, struct address_space *mapping, unsigned int order) { unsigned long index = xas->xa_index; - bool pmd_downgrade = false; /* splitting PMD entry into PTE entries? */ + bool pmd_downgrade; /* splitting PMD entry into PTE entries? */ void *entry; retry: + pmd_downgrade = false; xas_lock_irq(xas); entry = get_unlocked_entry(xas, order); diff --git a/fs/dlm/config.c b/fs/dlm/config.c index 88d95d96e36c..42eee2783756 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -20,6 +20,7 @@ #include #include "config.h" +#include "midcomms.h" #include "lowcomms.h" /* @@ -79,6 +80,9 @@ struct dlm_cluster { unsigned int cl_new_rsb_count; unsigned int cl_recover_callbacks; char cl_cluster_name[DLM_LOCKSPACE_LEN]; + + struct dlm_spaces *sps; + struct dlm_comms *cms; }; static struct dlm_cluster *config_item_to_cluster(struct config_item *i) @@ -204,7 +208,7 @@ static int dlm_check_zero(unsigned int x) static int dlm_check_buffer_size(unsigned int x) { - if (x < DEFAULT_BUFFER_SIZE) + if (x < DLM_MAX_SOCKET_BUFSIZE) return -EINVAL; return 0; @@ -409,6 +413,9 @@ static struct config_group *make_cluster(struct config_group *g, if (!cl || !sps || !cms) goto fail; + cl->sps = sps; + cl->cms = cms; + config_group_init_type_name(&cl->group, name, &cluster_type); config_group_init_type_name(&sps->ss_group, "spaces", &spaces_type); config_group_init_type_name(&cms->cs_group, "comms", &comms_type); @@ -458,6 +465,9 @@ static void drop_cluster(struct config_group *g, struct config_item *i) static void release_cluster(struct config_item *i) { struct dlm_cluster *cl = config_item_to_cluster(i); + + kfree(cl->sps); + kfree(cl->cms); kfree(cl); } @@ -532,7 +542,7 @@ static void drop_comm(struct config_group *g, struct config_item *i) struct dlm_comm *cm = config_item_to_comm(i); if (local_comm == cm) local_comm = NULL; - dlm_lowcomms_close(cm->nodeid); + dlm_midcomms_close(cm->nodeid); while (cm->addr_count--) kfree(cm->addr[cm->addr_count]); config_item_put(i); @@ -942,7 +952,7 @@ int dlm_our_addr(struct sockaddr_storage *addr, int num) #define DEFAULT_SCAN_SECS 5 #define DEFAULT_LOG_DEBUG 0 #define DEFAULT_LOG_INFO 1 -#define DEFAULT_PROTOCOL 0 +#define DEFAULT_PROTOCOL DLM_PROTO_TCP #define DEFAULT_MARK 0 #define DEFAULT_TIMEWARN_CS 500 /* 5 sec = 500 centiseconds */ #define DEFAULT_WAITWARN_US 0 @@ -952,7 +962,7 @@ int dlm_our_addr(struct sockaddr_storage *addr, int num) struct dlm_config_info dlm_config = { .ci_tcp_port = DEFAULT_TCP_PORT, - .ci_buffer_size = DEFAULT_BUFFER_SIZE, + .ci_buffer_size = DLM_MAX_SOCKET_BUFSIZE, .ci_rsbtbl_size = DEFAULT_RSBTBL_SIZE, .ci_recover_timer = DEFAULT_RECOVER_TIMER, .ci_toss_secs = DEFAULT_TOSS_SECS, diff --git a/fs/dlm/config.h b/fs/dlm/config.h index d2cd4bd20313..df92b0a07fc6 100644 --- a/fs/dlm/config.h +++ b/fs/dlm/config.h @@ -12,7 +12,7 @@ #ifndef __CONFIG_DOT_H__ #define __CONFIG_DOT_H__ -#define DEFAULT_BUFFER_SIZE 4096 +#define DLM_MAX_SOCKET_BUFSIZE 4096 struct dlm_config_node { int nodeid; @@ -23,6 +23,9 @@ struct dlm_config_node { #define DLM_MAX_ADDR_COUNT 3 +#define DLM_PROTO_TCP 0 +#define DLM_PROTO_SCTP 1 + struct dlm_config_info { int ci_tcp_port; int ci_buffer_size; diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index d5bd990bcab8..47e9d57e4cae 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -16,6 +16,7 @@ #include #include "dlm_internal.h" +#include "midcomms.h" #include "lock.h" #define DLM_DEBUG_BUF_LEN 4096 @@ -23,6 +24,7 @@ static char debug_buf[DLM_DEBUG_BUF_LEN]; static struct mutex debug_buf_lock; static struct dentry *dlm_root; +static struct dentry *dlm_comms; static char *print_lockmode(int mode) { @@ -738,6 +740,57 @@ void dlm_delete_debug_file(struct dlm_ls *ls) debugfs_remove(ls->ls_debug_toss_dentry); } +static int dlm_state_show(struct seq_file *file, void *offset) +{ + seq_printf(file, "%s\n", dlm_midcomms_state(file->private)); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(dlm_state); + +static int dlm_flags_show(struct seq_file *file, void *offset) +{ + seq_printf(file, "%lu\n", dlm_midcomms_flags(file->private)); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(dlm_flags); + +static int dlm_send_queue_cnt_show(struct seq_file *file, void *offset) +{ + seq_printf(file, "%d\n", dlm_midcomms_send_queue_cnt(file->private)); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(dlm_send_queue_cnt); + +static int dlm_version_show(struct seq_file *file, void *offset) +{ + seq_printf(file, "0x%08x\n", dlm_midcomms_version(file->private)); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(dlm_version); + +void *dlm_create_debug_comms_file(int nodeid, void *data) +{ + struct dentry *d_node; + char name[256]; + + memset(name, 0, sizeof(name)); + snprintf(name, 256, "%d", nodeid); + + d_node = debugfs_create_dir(name, dlm_comms); + debugfs_create_file("state", 0444, d_node, data, &dlm_state_fops); + debugfs_create_file("flags", 0444, d_node, data, &dlm_flags_fops); + debugfs_create_file("send_queue_count", 0444, d_node, data, + &dlm_send_queue_cnt_fops); + debugfs_create_file("version", 0444, d_node, data, &dlm_version_fops); + + return d_node; +} + +void dlm_delete_debug_comms_file(void *ctx) +{ + debugfs_remove(ctx); +} + void dlm_create_debug_file(struct dlm_ls *ls) { char name[DLM_LOCKSPACE_LEN + 8]; @@ -797,6 +850,7 @@ void __init dlm_register_debugfs(void) { mutex_init(&debug_buf_lock); dlm_root = debugfs_create_dir("dlm", NULL); + dlm_comms = debugfs_create_dir("comms", dlm_root); } void dlm_unregister_debugfs(void) diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index 04fe9f525ac7..91d1ca3a121a 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -57,9 +57,12 @@ struct dlm_header; struct dlm_message; struct dlm_rcom; struct dlm_mhandle; +struct dlm_msg; #define log_print(fmt, args...) \ printk(KERN_ERR "dlm: "fmt"\n" , ##args) +#define log_print_ratelimited(fmt, args...) \ + printk_ratelimited(KERN_ERR "dlm: "fmt"\n", ##args) #define log_error(ls, fmt, args...) \ printk(KERN_ERR "dlm: %s: " fmt "\n", (ls)->ls_name , ##args) @@ -368,23 +371,33 @@ static inline int rsb_flag(struct dlm_rsb *r, enum rsb_flags flag) /* dlm_header is first element of all structs sent between nodes */ #define DLM_HEADER_MAJOR 0x00030000 -#define DLM_HEADER_MINOR 0x00000001 +#define DLM_HEADER_MINOR 0x00000002 + +#define DLM_VERSION_3_1 0x00030001 +#define DLM_VERSION_3_2 0x00030002 #define DLM_HEADER_SLOTS 0x00000001 #define DLM_MSG 1 #define DLM_RCOM 2 +#define DLM_OPTS 3 +#define DLM_ACK 4 +#define DLM_FIN 5 struct dlm_header { uint32_t h_version; - uint32_t h_lockspace; + union { + /* for DLM_MSG and DLM_RCOM */ + uint32_t h_lockspace; + /* for DLM_ACK and DLM_OPTS */ + uint32_t h_seq; + } u; uint32_t h_nodeid; /* nodeid of sender */ uint16_t h_length; uint8_t h_cmd; /* DLM_MSG, DLM_RCOM */ uint8_t h_pad; }; - #define DLM_MSG_REQUEST 1 #define DLM_MSG_CONVERT 2 #define DLM_MSG_UNLOCK 3 @@ -452,10 +465,29 @@ struct dlm_rcom { char rc_buf[]; }; +struct dlm_opt_header { + uint16_t t_type; + uint16_t t_length; + uint32_t o_pad; + /* need to be 8 byte aligned */ + char t_value[]; +}; + +/* encapsulation header */ +struct dlm_opts { + struct dlm_header o_header; + uint8_t o_nextcmd; + uint8_t o_pad; + uint16_t o_optlen; + uint32_t o_pad2; + char o_opts[]; +}; + union dlm_packet { struct dlm_header header; /* common to other two */ struct dlm_message message; struct dlm_rcom rcom; + struct dlm_opts opts; }; #define DLM_RSF_NEED_SLOTS 0x00000001 @@ -722,11 +754,15 @@ void dlm_register_debugfs(void); void dlm_unregister_debugfs(void); void dlm_create_debug_file(struct dlm_ls *ls); void dlm_delete_debug_file(struct dlm_ls *ls); +void *dlm_create_debug_comms_file(int nodeid, void *data); +void dlm_delete_debug_comms_file(void *ctx); #else static inline void dlm_register_debugfs(void) { } static inline void dlm_unregister_debugfs(void) { } static inline void dlm_create_debug_file(struct dlm_ls *ls) { } static inline void dlm_delete_debug_file(struct dlm_ls *ls) { } +static inline void *dlm_create_debug_comms_file(int nodeid, void *data) { return NULL; } +static inline void dlm_delete_debug_comms_file(void *ctx) { } #endif #endif /* __DLM_INTERNAL_DOT_H__ */ diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index b93df39d0915..c502c065d007 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -59,7 +59,7 @@ #include "dlm_internal.h" #include #include "memory.h" -#include "lowcomms.h" +#include "midcomms.h" #include "requestqueue.h" #include "util.h" #include "dir.h" @@ -3534,17 +3534,17 @@ static int _create_message(struct dlm_ls *ls, int mb_len, char *mb; /* get_buffer gives us a message handle (mh) that we need to - pass into lowcomms_commit and a message buffer (mb) that we + pass into midcomms_commit and a message buffer (mb) that we write our data into */ - mh = dlm_lowcomms_get_buffer(to_nodeid, mb_len, GFP_NOFS, &mb); + mh = dlm_midcomms_get_mhandle(to_nodeid, mb_len, GFP_NOFS, &mb); if (!mh) return -ENOBUFS; ms = (struct dlm_message *) mb; ms->m_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR); - ms->m_header.h_lockspace = ls->ls_global_id; + ms->m_header.u.h_lockspace = ls->ls_global_id; ms->m_header.h_nodeid = dlm_our_nodeid(); ms->m_header.h_length = mb_len; ms->m_header.h_cmd = DLM_MSG; @@ -3589,7 +3589,7 @@ static int create_message(struct dlm_rsb *r, struct dlm_lkb *lkb, static int send_message(struct dlm_mhandle *mh, struct dlm_message *ms) { dlm_message_out(ms); - dlm_lowcomms_commit_buffer(mh); + dlm_midcomms_commit_mhandle(mh); return 0; } @@ -5038,16 +5038,16 @@ void dlm_receive_buffer(union dlm_packet *p, int nodeid) if (hd->h_nodeid != nodeid) { log_print("invalid h_nodeid %d from %d lockspace %x", - hd->h_nodeid, nodeid, hd->h_lockspace); + hd->h_nodeid, nodeid, hd->u.h_lockspace); return; } - ls = dlm_find_lockspace_global(hd->h_lockspace); + ls = dlm_find_lockspace_global(hd->u.h_lockspace); if (!ls) { if (dlm_config.ci_log_debug) { printk_ratelimited(KERN_DEBUG "dlm: invalid lockspace " "%u from %d cmd %d type %d\n", - hd->h_lockspace, nodeid, hd->h_cmd, type); + hd->u.h_lockspace, nodeid, hd->h_cmd, type); } if (hd->h_cmd == DLM_RCOM && type == DLM_RCOM_STATUS) diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index c14cf2b7faab..d71aba8c3e64 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -16,6 +16,7 @@ #include "member.h" #include "recoverd.h" #include "dir.h" +#include "midcomms.h" #include "lowcomms.h" #include "config.h" #include "memory.h" @@ -390,7 +391,7 @@ static int threads_start(void) } /* Thread for sending/receiving messages for all lockspace's */ - error = dlm_lowcomms_start(); + error = dlm_midcomms_start(); if (error) { log_print("cannot start dlm lowcomms %d", error); goto scand_fail; @@ -566,7 +567,12 @@ static int new_lockspace(const char *name, const char *cluster, mutex_init(&ls->ls_requestqueue_mutex); mutex_init(&ls->ls_clear_proc_locks); - ls->ls_recover_buf = kmalloc(LOWCOMMS_MAX_TX_BUFFER_LEN, GFP_NOFS); + /* Due backwards compatibility with 3.1 we need to use maximum + * possible dlm message size to be sure the message will fit and + * not having out of bounds issues. However on sending side 3.2 + * might send less. + */ + ls->ls_recover_buf = kmalloc(DLM_MAX_SOCKET_BUFSIZE, GFP_NOFS); if (!ls->ls_recover_buf) goto out_lkbidr; @@ -698,7 +704,7 @@ int dlm_new_lockspace(const char *name, const char *cluster, error = 0; if (!ls_count) { dlm_scand_stop(); - dlm_lowcomms_shutdown(); + dlm_midcomms_shutdown(); dlm_lowcomms_stop(); } out: @@ -787,7 +793,7 @@ static int release_lockspace(struct dlm_ls *ls, int force) if (ls_count == 1) { dlm_scand_stop(); - dlm_lowcomms_shutdown(); + dlm_midcomms_shutdown(); } dlm_callback_stop(ls); diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 166e36fcf3e4..0ea9ae35da0b 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -59,7 +59,6 @@ #include "config.h" #define NEEDED_RMEM (4*1024*1024) -#define CONN_HASH_SIZE 32 /* Number of messages to send before rescheduling */ #define MAX_SEND_MSG_COUNT 25 @@ -79,14 +78,20 @@ struct connection { #define CF_CLOSING 8 #define CF_SHUTDOWN 9 #define CF_CONNECTED 10 +#define CF_RECONNECT 11 +#define CF_DELAY_CONNECT 12 +#define CF_EOF 13 struct list_head writequeue; /* List of outgoing writequeue_entries */ spinlock_t writequeue_lock; + atomic_t writequeue_cnt; void (*connect_action) (struct connection *); /* What to do to connect */ void (*shutdown_action)(struct connection *con); /* What to do to shutdown */ + bool (*eof_condition)(struct connection *con); /* What to do to eof check */ int retries; #define MAX_CONNECT_RETRIES 3 struct hlist_node list; struct connection *othercon; + struct connection *sendcon; struct work_struct rwork; /* Receive workqueue */ struct work_struct swork; /* Send workqueue */ wait_queue_head_t shutdown_wait; /* wait for graceful shutdown */ @@ -113,7 +118,22 @@ struct writequeue_entry { int len; int end; int users; + bool dirty; struct connection *con; + struct list_head msgs; + struct kref ref; +}; + +struct dlm_msg { + struct writequeue_entry *entry; + struct dlm_msg *orig_msg; + bool retransmit; + void *ppc; + int len; + int idx; /* new()/commit() idx exchange */ + + struct list_head list; + struct kref ref; }; struct dlm_node_addr { @@ -155,33 +175,23 @@ static void sctp_connect_to_sock(struct connection *con); static void tcp_connect_to_sock(struct connection *con); static void dlm_tcp_shutdown(struct connection *con); -/* This is deliberately very simple because most clusters have simple - sequential nodeids, so we should be able to go straight to a connection - struct in the array */ -static inline int nodeid_hash(int nodeid) +static struct connection *__find_con(int nodeid, int r) { - return nodeid & (CONN_HASH_SIZE-1); -} - -static struct connection *__find_con(int nodeid) -{ - int r, idx; struct connection *con; - r = nodeid_hash(nodeid); - - idx = srcu_read_lock(&connections_srcu); hlist_for_each_entry_rcu(con, &connection_hash[r], list) { - if (con->nodeid == nodeid) { - srcu_read_unlock(&connections_srcu, idx); + if (con->nodeid == nodeid) return con; - } } - srcu_read_unlock(&connections_srcu, idx); return NULL; } +static bool tcp_eof_condition(struct connection *con) +{ + return atomic_read(&con->writequeue_cnt); +} + static int dlm_con_init(struct connection *con, int nodeid) { con->rx_buflen = dlm_config.ci_buffer_size; @@ -193,15 +203,23 @@ static int dlm_con_init(struct connection *con, int nodeid) mutex_init(&con->sock_mutex); INIT_LIST_HEAD(&con->writequeue); spin_lock_init(&con->writequeue_lock); + atomic_set(&con->writequeue_cnt, 0); INIT_WORK(&con->swork, process_send_sockets); INIT_WORK(&con->rwork, process_recv_sockets); init_waitqueue_head(&con->shutdown_wait); - if (dlm_config.ci_protocol == 0) { + switch (dlm_config.ci_protocol) { + case DLM_PROTO_TCP: con->connect_action = tcp_connect_to_sock; con->shutdown_action = dlm_tcp_shutdown; - } else { + con->eof_condition = tcp_eof_condition; + break; + case DLM_PROTO_SCTP: con->connect_action = sctp_connect_to_sock; + break; + default: + kfree(con->rx_buf); + return -EINVAL; } return 0; @@ -216,7 +234,8 @@ static struct connection *nodeid2con(int nodeid, gfp_t alloc) struct connection *con, *tmp; int r, ret; - con = __find_con(nodeid); + r = nodeid_hash(nodeid); + con = __find_con(nodeid, r); if (con || !alloc) return con; @@ -230,8 +249,6 @@ static struct connection *nodeid2con(int nodeid, gfp_t alloc) return NULL; } - r = nodeid_hash(nodeid); - spin_lock(&connections_lock); /* Because multiple workqueues/threads calls this function it can * race on multiple cpu's. Instead of locking hot path __find_con() @@ -239,7 +256,7 @@ static struct connection *nodeid2con(int nodeid, gfp_t alloc) * under protection of connections_lock. If this is the case we * abort our connection creation and return the existing connection. */ - tmp = __find_con(nodeid); + tmp = __find_con(nodeid, r); if (tmp) { spin_unlock(&connections_lock); kfree(con->rx_buf); @@ -256,15 +273,13 @@ static struct connection *nodeid2con(int nodeid, gfp_t alloc) /* Loop round all connections */ static void foreach_conn(void (*conn_func)(struct connection *c)) { - int i, idx; + int i; struct connection *con; - idx = srcu_read_lock(&connections_srcu); for (i = 0; i < CONN_HASH_SIZE; i++) { hlist_for_each_entry_rcu(con, &connection_hash[i], list) conn_func(con); } - srcu_read_unlock(&connections_srcu, idx); } static struct dlm_node_addr *find_node_addr(int nodeid) @@ -462,6 +477,9 @@ static void lowcomms_data_ready(struct sock *sk) static void lowcomms_listen_data_ready(struct sock *sk) { + if (!dlm_allow_conn) + return; + queue_work(recv_workqueue, &listen_con.rwork); } @@ -518,14 +536,21 @@ static void lowcomms_state_change(struct sock *sk) int dlm_lowcomms_connect_node(int nodeid) { struct connection *con; + int idx; if (nodeid == dlm_our_nodeid()) return 0; + idx = srcu_read_lock(&connections_srcu); con = nodeid2con(nodeid, GFP_NOFS); - if (!con) + if (!con) { + srcu_read_unlock(&connections_srcu, idx); return -ENOMEM; + } + lowcomms_connect_sock(con); + srcu_read_unlock(&connections_srcu, idx); + return 0; } @@ -587,6 +612,22 @@ static void lowcomms_error_report(struct sock *sk) dlm_config.ci_tcp_port, sk->sk_err, sk->sk_err_soft); } + + /* below sendcon only handling */ + if (test_bit(CF_IS_OTHERCON, &con->flags)) + con = con->sendcon; + + switch (sk->sk_err) { + case ECONNREFUSED: + set_bit(CF_DELAY_CONNECT, &con->flags); + break; + default: + break; + } + + if (!test_and_set_bit(CF_RECONNECT, &con->flags)) + queue_work(send_workqueue, &con->swork); + out: read_unlock_bh(&sk->sk_callback_lock); if (orig_report) @@ -669,6 +710,42 @@ static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port, memset((char *)saddr + *addr_len, 0, sizeof(struct sockaddr_storage) - *addr_len); } +static void dlm_page_release(struct kref *kref) +{ + struct writequeue_entry *e = container_of(kref, struct writequeue_entry, + ref); + + __free_page(e->page); + kfree(e); +} + +static void dlm_msg_release(struct kref *kref) +{ + struct dlm_msg *msg = container_of(kref, struct dlm_msg, ref); + + kref_put(&msg->entry->ref, dlm_page_release); + kfree(msg); +} + +static void free_entry(struct writequeue_entry *e) +{ + struct dlm_msg *msg, *tmp; + + list_for_each_entry_safe(msg, tmp, &e->msgs, list) { + if (msg->orig_msg) { + msg->orig_msg->retransmit = false; + kref_put(&msg->orig_msg->ref, dlm_msg_release); + } + + list_del(&msg->list); + kref_put(&msg->ref, dlm_msg_release); + } + + list_del(&e->list); + atomic_dec(&e->con->writequeue_cnt); + kref_put(&e->ref, dlm_page_release); +} + static void dlm_close_sock(struct socket **sock) { if (*sock) { @@ -683,6 +760,7 @@ static void close_connection(struct connection *con, bool and_other, bool tx, bool rx) { bool closing = test_and_set_bit(CF_CLOSING, &con->flags); + struct writequeue_entry *e; if (tx && !closing && cancel_work_sync(&con->swork)) { log_print("canceled swork for node %d", con->nodeid); @@ -698,12 +776,35 @@ static void close_connection(struct connection *con, bool and_other, if (con->othercon && and_other) { /* Will only re-enter once. */ - close_connection(con->othercon, false, true, true); + close_connection(con->othercon, false, tx, rx); } + /* if we send a writequeue entry only a half way, we drop the + * whole entry because reconnection and that we not start of the + * middle of a msg which will confuse the other end. + * + * we can always drop messages because retransmits, but what we + * cannot allow is to transmit half messages which may be processed + * at the other side. + * + * our policy is to start on a clean state when disconnects, we don't + * know what's send/received on transport layer in this case. + */ + spin_lock(&con->writequeue_lock); + if (!list_empty(&con->writequeue)) { + e = list_first_entry(&con->writequeue, struct writequeue_entry, + list); + if (e->dirty) + free_entry(e); + } + spin_unlock(&con->writequeue_lock); + con->rx_leftover = 0; con->retries = 0; clear_bit(CF_CONNECTED, &con->flags); + clear_bit(CF_DELAY_CONNECT, &con->flags); + clear_bit(CF_RECONNECT, &con->flags); + clear_bit(CF_EOF, &con->flags); mutex_unlock(&con->sock_mutex); clear_bit(CF_CLOSING, &con->flags); } @@ -841,19 +942,26 @@ out_resched: return -EAGAIN; out_close: - mutex_unlock(&con->sock_mutex); - if (ret != -EAGAIN) { - /* Reconnect when there is something to send */ - close_connection(con, false, true, false); - if (ret == 0) { - log_print("connection %p got EOF from %d", - con, con->nodeid); + if (ret == 0) { + log_print("connection %p got EOF from %d", + con, con->nodeid); + + if (con->eof_condition && con->eof_condition(con)) { + set_bit(CF_EOF, &con->flags); + mutex_unlock(&con->sock_mutex); + } else { + mutex_unlock(&con->sock_mutex); + close_connection(con, false, true, false); + /* handling for tcp shutdown */ clear_bit(CF_SHUTDOWN, &con->flags); wake_up(&con->shutdown_wait); - /* signal to breaking receive worker */ - ret = -1; } + + /* signal to breaking receive worker */ + ret = -1; + } else { + mutex_unlock(&con->sock_mutex); } return ret; } @@ -864,16 +972,12 @@ static int accept_from_sock(struct listen_connection *con) int result; struct sockaddr_storage peeraddr; struct socket *newsock; - int len; + int len, idx; int nodeid; struct connection *newcon; struct connection *addcon; unsigned int mark; - if (!dlm_allow_conn) { - return -1; - } - if (!con->sock) return -ENOTCONN; @@ -907,8 +1011,10 @@ static int accept_from_sock(struct listen_connection *con) * the same time and the connections cross on the wire. * In this case we store the incoming one in "othercon" */ + idx = srcu_read_lock(&connections_srcu); newcon = nodeid2con(nodeid, GFP_NOFS); if (!newcon) { + srcu_read_unlock(&connections_srcu, idx); result = -ENOMEM; goto accept_err; } @@ -924,6 +1030,7 @@ static int accept_from_sock(struct listen_connection *con) if (!othercon) { log_print("failed to allocate incoming socket"); mutex_unlock(&newcon->sock_mutex); + srcu_read_unlock(&connections_srcu, idx); result = -ENOMEM; goto accept_err; } @@ -932,11 +1039,14 @@ static int accept_from_sock(struct listen_connection *con) if (result < 0) { kfree(othercon); mutex_unlock(&newcon->sock_mutex); + srcu_read_unlock(&connections_srcu, idx); goto accept_err; } lockdep_set_subclass(&othercon->sock_mutex, 1); + set_bit(CF_IS_OTHERCON, &othercon->flags); newcon->othercon = othercon; + othercon->sendcon = newcon; } else { /* close other sock con if we have something new */ close_connection(othercon, false, true, false); @@ -966,6 +1076,8 @@ static int accept_from_sock(struct listen_connection *con) if (!test_and_set_bit(CF_READ_PENDING, &addcon->flags)) queue_work(recv_workqueue, &addcon->rwork); + srcu_read_unlock(&connections_srcu, idx); + return 0; accept_err: @@ -977,12 +1089,6 @@ accept_err: return result; } -static void free_entry(struct writequeue_entry *e) -{ - __free_page(e->page); - kfree(e); -} - /* * writequeue_entry_complete - try to delete and free write queue entry * @e: write queue entry to try to delete @@ -994,11 +1100,11 @@ static void writequeue_entry_complete(struct writequeue_entry *e, int completed) { e->offset += completed; e->len -= completed; + /* signal that page was half way transmitted */ + e->dirty = true; - if (e->len == 0 && e->users == 0) { - list_del(&e->list); + if (e->len == 0 && e->users == 0) free_entry(e); - } } /* @@ -1075,7 +1181,7 @@ static void sctp_connect_to_sock(struct connection *con) make_sockaddr(&daddr, dlm_config.ci_tcp_port, &addr_len); - log_print("connecting to %d", con->nodeid); + log_print_ratelimited("connecting to %d", con->nodeid); /* Turn off Nagle's algorithm */ sctp_sock_set_nodelay(sock->sk); @@ -1171,7 +1277,7 @@ static void tcp_connect_to_sock(struct connection *con) make_sockaddr(&saddr, dlm_config.ci_tcp_port, &addr_len); - log_print("connecting to %d", con->nodeid); + log_print_ratelimited("connecting to %d", con->nodeid); /* Turn off Nagle's algorithm */ tcp_sock_set_nodelay(sock->sk); @@ -1364,12 +1470,16 @@ static struct writequeue_entry *new_writequeue_entry(struct connection *con, entry->con = con; entry->users = 1; + kref_init(&entry->ref); + INIT_LIST_HEAD(&entry->msgs); return entry; } static struct writequeue_entry *new_wq_entry(struct connection *con, int len, - gfp_t allocation, char **ppc) + gfp_t allocation, char **ppc, + void (*cb)(struct dlm_mhandle *mh), + struct dlm_mhandle *mh) { struct writequeue_entry *e; @@ -1377,7 +1487,12 @@ static struct writequeue_entry *new_wq_entry(struct connection *con, int len, if (!list_empty(&con->writequeue)) { e = list_last_entry(&con->writequeue, struct writequeue_entry, list); if (DLM_WQ_REMAIN_BYTES(e) >= len) { + kref_get(&e->ref); + *ppc = page_address(e->page) + e->end; + if (cb) + cb(mh); + e->end += len; e->users++; spin_unlock(&con->writequeue_lock); @@ -1391,42 +1506,92 @@ static struct writequeue_entry *new_wq_entry(struct connection *con, int len, if (!e) return NULL; + kref_get(&e->ref); *ppc = page_address(e->page); e->end += len; + atomic_inc(&con->writequeue_cnt); spin_lock(&con->writequeue_lock); + if (cb) + cb(mh); + list_add_tail(&e->list, &con->writequeue); spin_unlock(&con->writequeue_lock); return e; }; -void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc) +static struct dlm_msg *dlm_lowcomms_new_msg_con(struct connection *con, int len, + gfp_t allocation, char **ppc, + void (*cb)(struct dlm_mhandle *mh), + struct dlm_mhandle *mh) +{ + struct writequeue_entry *e; + struct dlm_msg *msg; + + msg = kzalloc(sizeof(*msg), allocation); + if (!msg) + return NULL; + + kref_init(&msg->ref); + + e = new_wq_entry(con, len, allocation, ppc, cb, mh); + if (!e) { + kfree(msg); + return NULL; + } + + msg->ppc = *ppc; + msg->len = len; + msg->entry = e; + + return msg; +} + +struct dlm_msg *dlm_lowcomms_new_msg(int nodeid, int len, gfp_t allocation, + char **ppc, void (*cb)(struct dlm_mhandle *mh), + struct dlm_mhandle *mh) { struct connection *con; + struct dlm_msg *msg; + int idx; - if (len > DEFAULT_BUFFER_SIZE || + if (len > DLM_MAX_SOCKET_BUFSIZE || len < sizeof(struct dlm_header)) { - BUILD_BUG_ON(PAGE_SIZE < DEFAULT_BUFFER_SIZE); + BUILD_BUG_ON(PAGE_SIZE < DLM_MAX_SOCKET_BUFSIZE); log_print("failed to allocate a buffer of size %d", len); WARN_ON(1); return NULL; } + idx = srcu_read_lock(&connections_srcu); con = nodeid2con(nodeid, allocation); - if (!con) + if (!con) { + srcu_read_unlock(&connections_srcu, idx); return NULL; + } - return new_wq_entry(con, len, allocation, ppc); + msg = dlm_lowcomms_new_msg_con(con, len, allocation, ppc, cb, mh); + if (!msg) { + srcu_read_unlock(&connections_srcu, idx); + return NULL; + } + + /* we assume if successful commit must called */ + msg->idx = idx; + return msg; } -void dlm_lowcomms_commit_buffer(void *mh) +static void _dlm_lowcomms_commit_msg(struct dlm_msg *msg) { - struct writequeue_entry *e = (struct writequeue_entry *)mh; + struct writequeue_entry *e = msg->entry; struct connection *con = e->con; int users; spin_lock(&con->writequeue_lock); + kref_get(&msg->ref); + list_add(&msg->list, &e->msgs); + users = --e->users; if (users) goto out; @@ -1442,6 +1607,42 @@ out: return; } +void dlm_lowcomms_commit_msg(struct dlm_msg *msg) +{ + _dlm_lowcomms_commit_msg(msg); + srcu_read_unlock(&connections_srcu, msg->idx); +} + +void dlm_lowcomms_put_msg(struct dlm_msg *msg) +{ + kref_put(&msg->ref, dlm_msg_release); +} + +/* does not held connections_srcu, usage workqueue only */ +int dlm_lowcomms_resend_msg(struct dlm_msg *msg) +{ + struct dlm_msg *msg_resend; + char *ppc; + + if (msg->retransmit) + return 1; + + msg_resend = dlm_lowcomms_new_msg_con(msg->entry->con, msg->len, + GFP_ATOMIC, &ppc, NULL, NULL); + if (!msg_resend) + return -ENOMEM; + + msg->retransmit = true; + kref_get(&msg->ref); + msg_resend->orig_msg = msg; + + memcpy(ppc, msg->ppc, msg->len); + _dlm_lowcomms_commit_msg(msg_resend); + dlm_lowcomms_put_msg(msg_resend); + + return 0; +} + /* Send a message */ static void send_to_sock(struct connection *con) { @@ -1483,7 +1684,7 @@ static void send_to_sock(struct connection *con) cond_resched(); goto out; } else if (ret < 0) - goto send_error; + goto out; } /* Don't starve people filling buffers */ @@ -1496,16 +1697,23 @@ static void send_to_sock(struct connection *con) writequeue_entry_complete(e, ret); } spin_unlock(&con->writequeue_lock); -out: - mutex_unlock(&con->sock_mutex); + + /* close if we got EOF */ + if (test_and_clear_bit(CF_EOF, &con->flags)) { + mutex_unlock(&con->sock_mutex); + close_connection(con, false, false, true); + + /* handling for tcp shutdown */ + clear_bit(CF_SHUTDOWN, &con->flags); + wake_up(&con->shutdown_wait); + } else { + mutex_unlock(&con->sock_mutex); + } + return; -send_error: +out: mutex_unlock(&con->sock_mutex); - close_connection(con, false, false, true); - /* Requeue the send work. When the work daemon runs again, it will try - a new connection, then call this function again. */ - queue_work(send_workqueue, &con->swork); return; out_connect: @@ -1520,7 +1728,6 @@ static void clean_one_writequeue(struct connection *con) spin_lock(&con->writequeue_lock); list_for_each_entry_safe(e, safe, &con->writequeue, list) { - list_del(&e->list); free_entry(e); } spin_unlock(&con->writequeue_lock); @@ -1532,8 +1739,10 @@ int dlm_lowcomms_close(int nodeid) { struct connection *con; struct dlm_node_addr *na; + int idx; log_print("closing connection to node %d", nodeid); + idx = srcu_read_lock(&connections_srcu); con = nodeid2con(nodeid, 0); if (con) { set_bit(CF_CLOSE, &con->flags); @@ -1542,6 +1751,7 @@ int dlm_lowcomms_close(int nodeid) if (con->othercon) clean_one_writequeue(con->othercon); } + srcu_read_unlock(&connections_srcu, idx); spin_lock(&dlm_node_addrs_spin); na = find_node_addr(nodeid); @@ -1578,35 +1788,50 @@ static void process_send_sockets(struct work_struct *work) { struct connection *con = container_of(work, struct connection, swork); + WARN_ON(test_bit(CF_IS_OTHERCON, &con->flags)); + clear_bit(CF_WRITE_PENDING, &con->flags); - if (con->sock == NULL) /* not mutex protected so check it inside too */ + + if (test_and_clear_bit(CF_RECONNECT, &con->flags)) { + close_connection(con, false, false, true); + dlm_midcomms_unack_msg_resend(con->nodeid); + } + + if (con->sock == NULL) { /* not mutex protected so check it inside too */ + if (test_and_clear_bit(CF_DELAY_CONNECT, &con->flags)) + msleep(1000); con->connect_action(con); + } if (!list_empty(&con->writequeue)) send_to_sock(con); } static void work_stop(void) { - if (recv_workqueue) + if (recv_workqueue) { destroy_workqueue(recv_workqueue); - if (send_workqueue) + recv_workqueue = NULL; + } + + if (send_workqueue) { destroy_workqueue(send_workqueue); + send_workqueue = NULL; + } } static int work_start(void) { - recv_workqueue = alloc_workqueue("dlm_recv", - WQ_UNBOUND | WQ_MEM_RECLAIM, 1); + recv_workqueue = alloc_ordered_workqueue("dlm_recv", WQ_MEM_RECLAIM); if (!recv_workqueue) { log_print("can't start dlm_recv"); return -ENOMEM; } - send_workqueue = alloc_workqueue("dlm_send", - WQ_UNBOUND | WQ_MEM_RECLAIM, 1); + send_workqueue = alloc_ordered_workqueue("dlm_send", WQ_MEM_RECLAIM); if (!send_workqueue) { log_print("can't start dlm_send"); destroy_workqueue(recv_workqueue); + recv_workqueue = NULL; return -ENOMEM; } @@ -1621,6 +1846,8 @@ static void shutdown_conn(struct connection *con) void dlm_lowcomms_shutdown(void) { + int idx; + /* Set all the flags to prevent any * socket activity. */ @@ -1633,7 +1860,9 @@ void dlm_lowcomms_shutdown(void) dlm_close_sock(&listen_con.sock); + idx = srcu_read_lock(&connections_srcu); foreach_conn(shutdown_conn); + srcu_read_unlock(&connections_srcu, idx); } static void _stop_conn(struct connection *con, bool and_other) @@ -1682,7 +1911,7 @@ static void free_conn(struct connection *con) static void work_flush(void) { - int ok, idx; + int ok; int i; struct connection *con; @@ -1693,7 +1922,6 @@ static void work_flush(void) flush_workqueue(recv_workqueue); if (send_workqueue) flush_workqueue(send_workqueue); - idx = srcu_read_lock(&connections_srcu); for (i = 0; i < CONN_HASH_SIZE && ok; i++) { hlist_for_each_entry_rcu(con, &connection_hash[i], list) { @@ -1707,14 +1935,17 @@ static void work_flush(void) } } } - srcu_read_unlock(&connections_srcu, idx); } while (!ok); } void dlm_lowcomms_stop(void) { + int idx; + + idx = srcu_read_lock(&connections_srcu); work_flush(); foreach_conn(free_conn); + srcu_read_unlock(&connections_srcu, idx); work_stop(); deinit_local(); } @@ -1738,15 +1969,24 @@ int dlm_lowcomms_start(void) error = work_start(); if (error) - goto fail; + goto fail_local; dlm_allow_conn = 1; /* Start listening */ - if (dlm_config.ci_protocol == 0) + switch (dlm_config.ci_protocol) { + case DLM_PROTO_TCP: error = tcp_listen_for_all(); - else + break; + case DLM_PROTO_SCTP: error = sctp_listen_for_all(&listen_con); + break; + default: + log_print("Invalid protocol identifier %d set", + dlm_config.ci_protocol); + error = -EINVAL; + break; + } if (error) goto fail_unlisten; @@ -1755,6 +1995,9 @@ int dlm_lowcomms_start(void) fail_unlisten: dlm_allow_conn = 0; dlm_close_sock(&listen_con.sock); + work_stop(); +fail_local: + deinit_local(); fail: return error; } diff --git a/fs/dlm/lowcomms.h b/fs/dlm/lowcomms.h index 48bbc4e18761..aaae7115c00d 100644 --- a/fs/dlm/lowcomms.h +++ b/fs/dlm/lowcomms.h @@ -12,7 +12,22 @@ #ifndef __LOWCOMMS_DOT_H__ #define __LOWCOMMS_DOT_H__ -#define LOWCOMMS_MAX_TX_BUFFER_LEN 4096 +#include "dlm_internal.h" + +#define DLM_MIDCOMMS_OPT_LEN sizeof(struct dlm_opts) +#define DLM_MAX_APP_BUFSIZE (DLM_MAX_SOCKET_BUFSIZE - \ + DLM_MIDCOMMS_OPT_LEN) + +#define CONN_HASH_SIZE 32 + +/* This is deliberately very simple because most clusters have simple + * sequential nodeids, so we should be able to go straight to a connection + * struct in the array + */ +static inline int nodeid_hash(int nodeid) +{ + return nodeid & (CONN_HASH_SIZE-1); +} /* switch to check if dlm is running */ extern int dlm_allow_conn; @@ -22,8 +37,12 @@ void dlm_lowcomms_shutdown(void); void dlm_lowcomms_stop(void); void dlm_lowcomms_exit(void); int dlm_lowcomms_close(int nodeid); -void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc); -void dlm_lowcomms_commit_buffer(void *mh); +struct dlm_msg *dlm_lowcomms_new_msg(int nodeid, int len, gfp_t allocation, + char **ppc, void (*cb)(struct dlm_mhandle *mh), + struct dlm_mhandle *mh); +void dlm_lowcomms_commit_msg(struct dlm_msg *msg); +void dlm_lowcomms_put_msg(struct dlm_msg *msg); +int dlm_lowcomms_resend_msg(struct dlm_msg *msg); int dlm_lowcomms_connect_node(int nodeid); int dlm_lowcomms_nodes_set_mark(int nodeid, unsigned int mark); int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len); diff --git a/fs/dlm/member.c b/fs/dlm/member.c index ceef3f2074ff..d9e1e4170eb1 100644 --- a/fs/dlm/member.c +++ b/fs/dlm/member.c @@ -15,6 +15,7 @@ #include "recover.h" #include "rcom.h" #include "config.h" +#include "midcomms.h" #include "lowcomms.h" int dlm_slots_version(struct dlm_header *h) @@ -270,7 +271,7 @@ int dlm_slots_assign(struct dlm_ls *ls, int *num_slots, int *slots_size, log_slots(ls, gen, num, NULL, array, array_size); - max_slots = (LOWCOMMS_MAX_TX_BUFFER_LEN - sizeof(struct dlm_rcom) - + max_slots = (DLM_MAX_APP_BUFSIZE - sizeof(struct dlm_rcom) - sizeof(struct rcom_config)) / sizeof(struct rcom_slot); if (num > max_slots) { @@ -329,6 +330,7 @@ static int dlm_add_member(struct dlm_ls *ls, struct dlm_config_node *node) memb->nodeid = node->nodeid; memb->weight = node->weight; memb->comm_seq = node->comm_seq; + dlm_midcomms_add_member(node->nodeid); add_ordered_member(ls, memb); ls->ls_num_nodes++; return 0; @@ -359,26 +361,34 @@ int dlm_is_removed(struct dlm_ls *ls, int nodeid) return 0; } -static void clear_memb_list(struct list_head *head) +static void clear_memb_list(struct list_head *head, + void (*after_del)(int nodeid)) { struct dlm_member *memb; while (!list_empty(head)) { memb = list_entry(head->next, struct dlm_member, list); list_del(&memb->list); + if (after_del) + after_del(memb->nodeid); kfree(memb); } } +static void clear_members_cb(int nodeid) +{ + dlm_midcomms_remove_member(nodeid); +} + void dlm_clear_members(struct dlm_ls *ls) { - clear_memb_list(&ls->ls_nodes); + clear_memb_list(&ls->ls_nodes, clear_members_cb); ls->ls_num_nodes = 0; } void dlm_clear_members_gone(struct dlm_ls *ls) { - clear_memb_list(&ls->ls_nodes_gone); + clear_memb_list(&ls->ls_nodes_gone, NULL); } static void make_member_array(struct dlm_ls *ls) @@ -552,6 +562,7 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out) neg++; list_move(&memb->list, &ls->ls_nodes_gone); + dlm_midcomms_remove_member(memb->nodeid); ls->ls_num_nodes--; dlm_lsop_recover_slot(ls, memb); } @@ -576,12 +587,18 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out) *neg_out = neg; error = ping_members(ls); - if (!error || error == -EPROTO) { - /* new_lockspace() may be waiting to know if the config - is good or bad */ - ls->ls_members_result = error; - complete(&ls->ls_members_done); - } + /* error -EINTR means that a new recovery action is triggered. + * We ignore this recovery action and let run the new one which might + * have new member configuration. + */ + if (error == -EINTR) + error = 0; + + /* new_lockspace() may be waiting to know if the config + * is good or bad + */ + ls->ls_members_result = error; + complete(&ls->ls_members_done); log_rinfo(ls, "dlm_recover_members %d nodes", ls->ls_num_nodes); return error; diff --git a/fs/dlm/midcomms.c b/fs/dlm/midcomms.c index 1c6654a21ec4..e3de268898ed 100644 --- a/fs/dlm/midcomms.c +++ b/fs/dlm/midcomms.c @@ -3,7 +3,7 @@ ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. -** Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. +** Copyright (C) 2004-2021 Red Hat, Inc. All rights reserved. ** ** ******************************************************************************* @@ -12,22 +12,866 @@ /* * midcomms.c * - * This is the appallingly named "mid-level" comms layer. + * This is the appallingly named "mid-level" comms layer. It takes care about + * deliver an on application layer "reliable" communication above the used + * lowcomms transport layer. * - * Its purpose is to take packets from the "real" comms layer, - * split them up into packets and pass them to the interested - * part of the locking mechanism. + * How it works: * - * It also takes messages from the locking layer, formats them - * into packets and sends them to the comms layer. + * Each nodes keeps track of all send DLM messages in send_queue with a sequence + * number. The receive will send an DLM_ACK message back for every DLM message + * received at the other side. If a reconnect happens in lowcomms we will send + * all unacknowledged dlm messages again. The receiving side might drop any already + * received message by comparing sequence numbers. + * + * How version detection works: + * + * Due the fact that dlm has pre-configured node addresses on every side + * it is in it's nature that every side connects at starts to transmit + * dlm messages which ends in a race. However DLM_RCOM_NAMES, DLM_RCOM_STATUS + * and their replies are the first messages which are exchanges. Due backwards + * compatibility these messages are not covered by the midcomms re-transmission + * layer. These messages have their own re-transmission handling in the dlm + * application layer. The version field of every node will be set on these RCOM + * messages as soon as they arrived and the node isn't yet part of the nodes + * hash. There exists also logic to detect version mismatched if something weird + * going on or the first messages isn't an expected one. + * + * Termination: + * + * The midcomms layer does a 4 way handshake for termination on DLM protocol + * like TCP supports it with half-closed socket support. SCTP doesn't support + * half-closed socket, so we do it on DLM layer. Also socket shutdown() can be + * interrupted by .e.g. tcp reset itself. Additional there exists the othercon + * paradigm in lowcomms which cannot be easily without breaking backwards + * compatibility. A node cannot send anything to another node when a DLM_FIN + * message was send. There exists additional logic to print a warning if + * DLM wants to do it. There exists a state handling like RFC 793 but reduced + * to termination only. The event "member removal event" describes the cluster + * manager removed the node from internal lists, at this point DLM does not + * send any message to the other node. There exists two cases: + * + * 1. The cluster member was removed and we received a FIN + * OR + * 2. We received a FIN but the member was not removed yet + * + * One of these cases will do the CLOSE_WAIT to LAST_ACK change. + * + * + * +---------+ + * | CLOSED | + * +---------+ + * | add member/receive RCOM version + * | detection msg + * V + * +---------+ + * | ESTAB | + * +---------+ + * CLOSE | | rcv FIN + * ------- | | ------- + * +---------+ snd FIN / \ snd ACK +---------+ + * | FIN |<----------------- ------------------>| CLOSE | + * | WAIT-1 |------------------ | WAIT | + * +---------+ rcv FIN \ +---------+ + * | rcv ACK of FIN ------- | CLOSE | member + * | -------------- snd ACK | ------- | removal + * V x V snd FIN V event + * +---------+ +---------+ +---------+ + * |FINWAIT-2| | CLOSING | | LAST-ACK| + * +---------+ +---------+ +---------+ + * | rcv ACK of FIN | rcv ACK of FIN | + * | rcv FIN -------------- | -------------- | + * | ------- x V x V + * \ snd ACK +---------+ +---------+ + * ------------------------>| CLOSED | | CLOSED | + * +---------+ +---------+ + * + * NOTE: any state can interrupted by midcomms_close() and state will be + * switched to CLOSED in case of fencing. There exists also some timeout + * handling when we receive the version detection RCOM messages which is + * made by observation. + * + * Future improvements: + * + * There exists some known issues/improvements of the dlm handling. Some + * of them should be done in a next major dlm version bump which makes + * it incompatible with previous versions. + * + * Unaligned memory access: + * + * There exists cases when the dlm message buffer length is not aligned + * to 8 byte. However seems nobody detected any problem with it. This + * can be fixed in the next major version bump of dlm. + * + * Version detection: + * + * The version detection and how it's done is related to backwards + * compatibility. There exists better ways to make a better handling. + * However this should be changed in the next major version bump of dlm. + * + * Ack handling: + * + * Currently we send an ack message for every dlm message. However we + * can ack multiple dlm messages with one ack by just delaying the ack + * message. Will reduce some traffic but makes the drop detection slower. + * + * Tail Size checking: + * + * There exists a message tail payload in e.g. DLM_MSG however we don't + * check it against the message length yet regarding to the receive buffer + * length. That need to be validated. + * + * Fencing bad nodes: + * + * At timeout places or weird sequence number behaviours we should send + * a fencing request to the cluster manager. */ +/* Debug switch to enable a 5 seconds sleep waiting of a termination. + * This can be useful to test fencing while termination is running. + * This requires a setup with only gfs2 as dlm user, so that the + * last umount will terminate the connection. + * + * However it became useful to test, while the 5 seconds block in umount + * just press the reset button. In a lot of dropping the termination + * process can could take several seconds. + */ +#define DLM_DEBUG_FENCE_TERMINATION 0 + +#include + #include "dlm_internal.h" #include "lowcomms.h" #include "config.h" #include "lock.h" +#include "util.h" #include "midcomms.h" +/* init value for sequence numbers for testing purpose only e.g. overflows */ +#define DLM_SEQ_INIT 0 +/* 3 minutes wait to sync ending of dlm */ +#define DLM_SHUTDOWN_TIMEOUT msecs_to_jiffies(3 * 60 * 1000) +#define DLM_VERSION_NOT_SET 0 + +struct midcomms_node { + int nodeid; + uint32_t version; + uint32_t seq_send; + uint32_t seq_next; + /* These queues are unbound because we cannot drop any message in dlm. + * We could send a fence signal for a specific node to the cluster + * manager if queues hits some maximum value, however this handling + * not supported yet. + */ + struct list_head send_queue; + spinlock_t send_queue_lock; + atomic_t send_queue_cnt; +#define DLM_NODE_FLAG_CLOSE 1 +#define DLM_NODE_FLAG_STOP_TX 2 +#define DLM_NODE_FLAG_STOP_RX 3 + unsigned long flags; + wait_queue_head_t shutdown_wait; + + /* dlm tcp termination state */ +#define DLM_CLOSED 1 +#define DLM_ESTABLISHED 2 +#define DLM_FIN_WAIT1 3 +#define DLM_FIN_WAIT2 4 +#define DLM_CLOSE_WAIT 5 +#define DLM_LAST_ACK 6 +#define DLM_CLOSING 7 + int state; + spinlock_t state_lock; + + /* counts how many lockspaces are using this node + * this refcount is necessary to determine if the + * node wants to disconnect. + */ + int users; + + /* not protected by srcu, node_hash lifetime */ + void *debugfs; + + struct hlist_node hlist; + struct rcu_head rcu; +}; + +struct dlm_mhandle { + const struct dlm_header *inner_hd; + struct midcomms_node *node; + struct dlm_opts *opts; + struct dlm_msg *msg; + bool committed; + uint32_t seq; + + void (*ack_rcv)(struct midcomms_node *node); + + /* get_mhandle/commit srcu idx exchange */ + int idx; + + struct list_head list; + struct rcu_head rcu; +}; + +static struct hlist_head node_hash[CONN_HASH_SIZE]; +static DEFINE_SPINLOCK(nodes_lock); +DEFINE_STATIC_SRCU(nodes_srcu); + +/* This mutex prevents that midcomms_close() is running while + * stop() or remove(). As I experienced invalid memory access + * behaviours when DLM_DEBUG_FENCE_TERMINATION is enabled and + * resetting machines. I will end in some double deletion in nodes + * datastructure. + */ +static DEFINE_MUTEX(close_lock); + +static inline const char *dlm_state_str(int state) +{ + switch (state) { + case DLM_CLOSED: + return "CLOSED"; + case DLM_ESTABLISHED: + return "ESTABLISHED"; + case DLM_FIN_WAIT1: + return "FIN_WAIT1"; + case DLM_FIN_WAIT2: + return "FIN_WAIT2"; + case DLM_CLOSE_WAIT: + return "CLOSE_WAIT"; + case DLM_LAST_ACK: + return "LAST_ACK"; + case DLM_CLOSING: + return "CLOSING"; + default: + return "UNKNOWN"; + } +} + +const char *dlm_midcomms_state(struct midcomms_node *node) +{ + return dlm_state_str(node->state); +} + +unsigned long dlm_midcomms_flags(struct midcomms_node *node) +{ + return node->flags; +} + +int dlm_midcomms_send_queue_cnt(struct midcomms_node *node) +{ + return atomic_read(&node->send_queue_cnt); +} + +uint32_t dlm_midcomms_version(struct midcomms_node *node) +{ + return node->version; +} + +static struct midcomms_node *__find_node(int nodeid, int r) +{ + struct midcomms_node *node; + + hlist_for_each_entry_rcu(node, &node_hash[r], hlist) { + if (node->nodeid == nodeid) + return node; + } + + return NULL; +} + +static void dlm_mhandle_release(struct rcu_head *rcu) +{ + struct dlm_mhandle *mh = container_of(rcu, struct dlm_mhandle, rcu); + + dlm_lowcomms_put_msg(mh->msg); + kfree(mh); +} + +static void dlm_mhandle_delete(struct midcomms_node *node, + struct dlm_mhandle *mh) +{ + list_del_rcu(&mh->list); + atomic_dec(&node->send_queue_cnt); + call_rcu(&mh->rcu, dlm_mhandle_release); +} + +static void dlm_send_queue_flush(struct midcomms_node *node) +{ + struct dlm_mhandle *mh; + + pr_debug("flush midcomms send queue of node %d\n", node->nodeid); + + rcu_read_lock(); + spin_lock(&node->send_queue_lock); + list_for_each_entry_rcu(mh, &node->send_queue, list) { + dlm_mhandle_delete(node, mh); + } + spin_unlock(&node->send_queue_lock); + rcu_read_unlock(); +} + +static void midcomms_node_reset(struct midcomms_node *node) +{ + pr_debug("reset node %d\n", node->nodeid); + + node->seq_next = DLM_SEQ_INIT; + node->seq_send = DLM_SEQ_INIT; + node->version = DLM_VERSION_NOT_SET; + node->flags = 0; + + dlm_send_queue_flush(node); + node->state = DLM_CLOSED; + wake_up(&node->shutdown_wait); +} + +static struct midcomms_node *nodeid2node(int nodeid, gfp_t alloc) +{ + struct midcomms_node *node, *tmp; + int r = nodeid_hash(nodeid); + + node = __find_node(nodeid, r); + if (node || !alloc) + return node; + + node = kmalloc(sizeof(*node), alloc); + if (!node) + return NULL; + + node->nodeid = nodeid; + spin_lock_init(&node->state_lock); + spin_lock_init(&node->send_queue_lock); + atomic_set(&node->send_queue_cnt, 0); + INIT_LIST_HEAD(&node->send_queue); + init_waitqueue_head(&node->shutdown_wait); + node->users = 0; + midcomms_node_reset(node); + + spin_lock(&nodes_lock); + /* check again if there was somebody else + * earlier here to add the node + */ + tmp = __find_node(nodeid, r); + if (tmp) { + spin_unlock(&nodes_lock); + kfree(node); + return tmp; + } + + hlist_add_head_rcu(&node->hlist, &node_hash[r]); + spin_unlock(&nodes_lock); + + node->debugfs = dlm_create_debug_comms_file(nodeid, node); + return node; +} + +static int dlm_send_ack(int nodeid, uint32_t seq) +{ + int mb_len = sizeof(struct dlm_header); + struct dlm_header *m_header; + struct dlm_msg *msg; + char *ppc; + + msg = dlm_lowcomms_new_msg(nodeid, mb_len, GFP_NOFS, &ppc, + NULL, NULL); + if (!msg) + return -ENOMEM; + + m_header = (struct dlm_header *)ppc; + + m_header->h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR); + m_header->h_nodeid = dlm_our_nodeid(); + m_header->h_length = mb_len; + m_header->h_cmd = DLM_ACK; + m_header->u.h_seq = seq; + + header_out(m_header); + dlm_lowcomms_commit_msg(msg); + dlm_lowcomms_put_msg(msg); + + return 0; +} + +static int dlm_send_fin(struct midcomms_node *node, + void (*ack_rcv)(struct midcomms_node *node)) +{ + int mb_len = sizeof(struct dlm_header); + struct dlm_header *m_header; + struct dlm_mhandle *mh; + char *ppc; + + mh = dlm_midcomms_get_mhandle(node->nodeid, mb_len, GFP_NOFS, &ppc); + if (!mh) + return -ENOMEM; + + mh->ack_rcv = ack_rcv; + + m_header = (struct dlm_header *)ppc; + + m_header->h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR); + m_header->h_nodeid = dlm_our_nodeid(); + m_header->h_length = mb_len; + m_header->h_cmd = DLM_FIN; + + header_out(m_header); + + pr_debug("sending fin msg to node %d\n", node->nodeid); + dlm_midcomms_commit_mhandle(mh); + set_bit(DLM_NODE_FLAG_STOP_TX, &node->flags); + + return 0; +} + +static void dlm_receive_ack(struct midcomms_node *node, uint32_t seq) +{ + struct dlm_mhandle *mh; + + rcu_read_lock(); + list_for_each_entry_rcu(mh, &node->send_queue, list) { + if (before(mh->seq, seq)) { + if (mh->ack_rcv) + mh->ack_rcv(node); + } else { + /* send queue should be ordered */ + break; + } + } + + spin_lock(&node->send_queue_lock); + list_for_each_entry_rcu(mh, &node->send_queue, list) { + if (before(mh->seq, seq)) { + dlm_mhandle_delete(node, mh); + } else { + /* send queue should be ordered */ + break; + } + } + spin_unlock(&node->send_queue_lock); + rcu_read_unlock(); +} + +static void dlm_pas_fin_ack_rcv(struct midcomms_node *node) +{ + spin_lock(&node->state_lock); + pr_debug("receive passive fin ack from node %d with state %s\n", + node->nodeid, dlm_state_str(node->state)); + + switch (node->state) { + case DLM_LAST_ACK: + /* DLM_CLOSED */ + midcomms_node_reset(node); + break; + case DLM_CLOSED: + /* not valid but somehow we got what we want */ + wake_up(&node->shutdown_wait); + break; + default: + spin_unlock(&node->state_lock); + log_print("%s: unexpected state: %d\n", + __func__, node->state); + WARN_ON(1); + return; + } + spin_unlock(&node->state_lock); +} + +static void dlm_midcomms_receive_buffer(union dlm_packet *p, + struct midcomms_node *node, + uint32_t seq) +{ + if (seq == node->seq_next) { + node->seq_next++; + /* send ack before fin */ + dlm_send_ack(node->nodeid, node->seq_next); + + switch (p->header.h_cmd) { + case DLM_FIN: + spin_lock(&node->state_lock); + pr_debug("receive fin msg from node %d with state %s\n", + node->nodeid, dlm_state_str(node->state)); + + switch (node->state) { + case DLM_ESTABLISHED: + node->state = DLM_CLOSE_WAIT; + pr_debug("switch node %d to state %s\n", + node->nodeid, dlm_state_str(node->state)); + /* passive shutdown DLM_LAST_ACK case 1 + * additional we check if the node is used by + * cluster manager events at all. + */ + if (node->users == 0) { + node->state = DLM_LAST_ACK; + pr_debug("switch node %d to state %s case 1\n", + node->nodeid, dlm_state_str(node->state)); + spin_unlock(&node->state_lock); + goto send_fin; + } + break; + case DLM_FIN_WAIT1: + node->state = DLM_CLOSING; + pr_debug("switch node %d to state %s\n", + node->nodeid, dlm_state_str(node->state)); + break; + case DLM_FIN_WAIT2: + midcomms_node_reset(node); + pr_debug("switch node %d to state %s\n", + node->nodeid, dlm_state_str(node->state)); + wake_up(&node->shutdown_wait); + break; + case DLM_LAST_ACK: + /* probably remove_member caught it, do nothing */ + break; + default: + spin_unlock(&node->state_lock); + log_print("%s: unexpected state: %d\n", + __func__, node->state); + WARN_ON(1); + return; + } + spin_unlock(&node->state_lock); + + set_bit(DLM_NODE_FLAG_STOP_RX, &node->flags); + break; + default: + WARN_ON(test_bit(DLM_NODE_FLAG_STOP_RX, &node->flags)); + dlm_receive_buffer(p, node->nodeid); + break; + } + } else { + /* retry to ack message which we already have by sending back + * current node->seq_next number as ack. + */ + if (seq < node->seq_next) + dlm_send_ack(node->nodeid, node->seq_next); + + log_print_ratelimited("ignore dlm msg because seq mismatch, seq: %u, expected: %u, nodeid: %d", + seq, node->seq_next, node->nodeid); + } + + return; + +send_fin: + set_bit(DLM_NODE_FLAG_STOP_RX, &node->flags); + dlm_send_fin(node, dlm_pas_fin_ack_rcv); +} + +static struct midcomms_node * +dlm_midcomms_recv_node_lookup(int nodeid, const union dlm_packet *p, + uint16_t msglen, int (*cb)(struct midcomms_node *node)) +{ + struct midcomms_node *node = NULL; + gfp_t allocation = 0; + int ret; + + switch (p->header.h_cmd) { + case DLM_RCOM: + if (msglen < sizeof(struct dlm_rcom)) { + log_print("rcom msg too small: %u, will skip this message from node %d", + msglen, nodeid); + return NULL; + } + + switch (le32_to_cpu(p->rcom.rc_type)) { + case DLM_RCOM_NAMES: + fallthrough; + case DLM_RCOM_NAMES_REPLY: + fallthrough; + case DLM_RCOM_STATUS: + fallthrough; + case DLM_RCOM_STATUS_REPLY: + node = nodeid2node(nodeid, 0); + if (node) { + spin_lock(&node->state_lock); + if (node->state != DLM_ESTABLISHED) + pr_debug("receive begin RCOM msg from node %d with state %s\n", + node->nodeid, dlm_state_str(node->state)); + + switch (node->state) { + case DLM_CLOSED: + node->state = DLM_ESTABLISHED; + pr_debug("switch node %d to state %s\n", + node->nodeid, dlm_state_str(node->state)); + break; + case DLM_ESTABLISHED: + break; + default: + /* some invalid state passive shutdown + * was failed, we try to reset and + * hope it will go on. + */ + log_print("reset node %d because shutdown stuck", + node->nodeid); + + midcomms_node_reset(node); + node->state = DLM_ESTABLISHED; + break; + } + spin_unlock(&node->state_lock); + } + + allocation = GFP_NOFS; + break; + default: + break; + } + + break; + default: + break; + } + + node = nodeid2node(nodeid, allocation); + if (!node) { + switch (p->header.h_cmd) { + case DLM_OPTS: + if (msglen < sizeof(struct dlm_opts)) { + log_print("opts msg too small: %u, will skip this message from node %d", + msglen, nodeid); + return NULL; + } + + log_print_ratelimited("received dlm opts message nextcmd %d from node %d in an invalid sequence", + p->opts.o_nextcmd, nodeid); + break; + default: + log_print_ratelimited("received dlm message cmd %d from node %d in an invalid sequence", + p->header.h_cmd, nodeid); + break; + } + + return NULL; + } + + ret = cb(node); + if (ret < 0) + return NULL; + + return node; +} + +static int dlm_midcomms_version_check_3_2(struct midcomms_node *node) +{ + switch (node->version) { + case DLM_VERSION_NOT_SET: + node->version = DLM_VERSION_3_2; + log_print("version 0x%08x for node %d detected", DLM_VERSION_3_2, + node->nodeid); + break; + case DLM_VERSION_3_2: + break; + default: + log_print_ratelimited("version mismatch detected, assumed 0x%08x but node %d has 0x%08x", + DLM_VERSION_3_2, node->nodeid, node->version); + return -1; + } + + return 0; +} + +static int dlm_opts_check_msglen(union dlm_packet *p, uint16_t msglen, int nodeid) +{ + int len = msglen; + + /* we only trust outer header msglen because + * it's checked against receive buffer length. + */ + if (len < sizeof(struct dlm_opts)) + return -1; + len -= sizeof(struct dlm_opts); + + if (len < le16_to_cpu(p->opts.o_optlen)) + return -1; + len -= le16_to_cpu(p->opts.o_optlen); + + switch (p->opts.o_nextcmd) { + case DLM_FIN: + if (len < sizeof(struct dlm_header)) { + log_print("fin too small: %d, will skip this message from node %d", + len, nodeid); + return -1; + } + + break; + case DLM_MSG: + if (len < sizeof(struct dlm_message)) { + log_print("msg too small: %d, will skip this message from node %d", + msglen, nodeid); + return -1; + } + + break; + case DLM_RCOM: + if (len < sizeof(struct dlm_rcom)) { + log_print("rcom msg too small: %d, will skip this message from node %d", + len, nodeid); + return -1; + } + + break; + default: + log_print("unsupported o_nextcmd received: %u, will skip this message from node %d", + p->opts.o_nextcmd, nodeid); + return -1; + } + + return 0; +} + +static void dlm_midcomms_receive_buffer_3_2(union dlm_packet *p, int nodeid) +{ + uint16_t msglen = le16_to_cpu(p->header.h_length); + struct midcomms_node *node; + uint32_t seq; + int ret, idx; + + idx = srcu_read_lock(&nodes_srcu); + node = dlm_midcomms_recv_node_lookup(nodeid, p, msglen, + dlm_midcomms_version_check_3_2); + if (!node) + goto out; + + switch (p->header.h_cmd) { + case DLM_RCOM: + /* these rcom message we use to determine version. + * they have their own retransmission handling and + * are the first messages of dlm. + * + * length already checked. + */ + switch (le32_to_cpu(p->rcom.rc_type)) { + case DLM_RCOM_NAMES: + fallthrough; + case DLM_RCOM_NAMES_REPLY: + fallthrough; + case DLM_RCOM_STATUS: + fallthrough; + case DLM_RCOM_STATUS_REPLY: + break; + default: + log_print("unsupported rcom type received: %u, will skip this message from node %d", + le32_to_cpu(p->rcom.rc_type), nodeid); + goto out; + } + + WARN_ON(test_bit(DLM_NODE_FLAG_STOP_RX, &node->flags)); + dlm_receive_buffer(p, nodeid); + break; + case DLM_OPTS: + seq = le32_to_cpu(p->header.u.h_seq); + + ret = dlm_opts_check_msglen(p, msglen, nodeid); + if (ret < 0) { + log_print("opts msg too small: %u, will skip this message from node %d", + msglen, nodeid); + goto out; + } + + p = (union dlm_packet *)((unsigned char *)p->opts.o_opts + + le16_to_cpu(p->opts.o_optlen)); + + /* recheck inner msglen just if it's not garbage */ + msglen = le16_to_cpu(p->header.h_length); + switch (p->header.h_cmd) { + case DLM_RCOM: + if (msglen < sizeof(struct dlm_rcom)) { + log_print("inner rcom msg too small: %u, will skip this message from node %d", + msglen, nodeid); + goto out; + } + + break; + case DLM_MSG: + if (msglen < sizeof(struct dlm_message)) { + log_print("inner msg too small: %u, will skip this message from node %d", + msglen, nodeid); + goto out; + } + + break; + case DLM_FIN: + if (msglen < sizeof(struct dlm_header)) { + log_print("inner fin too small: %u, will skip this message from node %d", + msglen, nodeid); + goto out; + } + + break; + default: + log_print("unsupported inner h_cmd received: %u, will skip this message from node %d", + msglen, nodeid); + goto out; + } + + dlm_midcomms_receive_buffer(p, node, seq); + break; + case DLM_ACK: + seq = le32_to_cpu(p->header.u.h_seq); + dlm_receive_ack(node, seq); + break; + default: + log_print("unsupported h_cmd received: %u, will skip this message from node %d", + p->header.h_cmd, nodeid); + break; + } + +out: + srcu_read_unlock(&nodes_srcu, idx); +} + +static int dlm_midcomms_version_check_3_1(struct midcomms_node *node) +{ + switch (node->version) { + case DLM_VERSION_NOT_SET: + node->version = DLM_VERSION_3_1; + log_print("version 0x%08x for node %d detected", DLM_VERSION_3_1, + node->nodeid); + break; + case DLM_VERSION_3_1: + break; + default: + log_print_ratelimited("version mismatch detected, assumed 0x%08x but node %d has 0x%08x", + DLM_VERSION_3_1, node->nodeid, node->version); + return -1; + } + + return 0; +} + +static void dlm_midcomms_receive_buffer_3_1(union dlm_packet *p, int nodeid) +{ + uint16_t msglen = le16_to_cpu(p->header.h_length); + struct midcomms_node *node; + int idx; + + idx = srcu_read_lock(&nodes_srcu); + node = dlm_midcomms_recv_node_lookup(nodeid, p, msglen, + dlm_midcomms_version_check_3_1); + if (!node) { + srcu_read_unlock(&nodes_srcu, idx); + return; + } + srcu_read_unlock(&nodes_srcu, idx); + + switch (p->header.h_cmd) { + case DLM_RCOM: + /* length already checked */ + break; + case DLM_MSG: + if (msglen < sizeof(struct dlm_message)) { + log_print("msg too small: %u, will skip this message from node %d", + msglen, nodeid); + return; + } + + break; + default: + log_print("unsupported h_cmd received: %u, will skip this message from node %d", + p->header.h_cmd, nodeid); + return; + } + + dlm_receive_buffer(p, nodeid); +} + /* * Called from the low-level comms layer to process a buffer of * commands. @@ -43,7 +887,7 @@ int dlm_process_incoming_buffer(int nodeid, unsigned char *buf, int len) while (len >= sizeof(struct dlm_header)) { hd = (struct dlm_header *)ptr; - /* no message should be more than DEFAULT_BUFFER_SIZE or + /* no message should be more than DLM_MAX_SOCKET_BUFSIZE or * less than dlm_header size. * * Some messages does not have a 8 byte length boundary yet @@ -55,7 +899,7 @@ int dlm_process_incoming_buffer(int nodeid, unsigned char *buf, int len) * the next major version bump. */ msglen = le16_to_cpu(hd->h_length); - if (msglen > DEFAULT_BUFFER_SIZE || + if (msglen > DLM_MAX_SOCKET_BUFSIZE || msglen < sizeof(struct dlm_header)) { log_print("received invalid length header: %u from node %d, will abort message parsing", msglen, nodeid); @@ -68,32 +912,19 @@ int dlm_process_incoming_buffer(int nodeid, unsigned char *buf, int len) if (msglen > len) break; - switch (hd->h_cmd) { - case DLM_MSG: - if (msglen < sizeof(struct dlm_message)) { - log_print("dlm msg too small: %u, will skip this message", - msglen); - goto skip; - } - + switch (le32_to_cpu(hd->h_version)) { + case DLM_VERSION_3_1: + dlm_midcomms_receive_buffer_3_1((union dlm_packet *)ptr, nodeid); break; - case DLM_RCOM: - if (msglen < sizeof(struct dlm_rcom)) { - log_print("dlm rcom msg too small: %u, will skip this message", - msglen); - goto skip; - } - + case DLM_VERSION_3_2: + dlm_midcomms_receive_buffer_3_2((union dlm_packet *)ptr, nodeid); break; default: - log_print("unsupported h_cmd received: %u, will skip this message", - hd->h_cmd); - goto skip; + log_print("received invalid version header: %u from node %d, will skip this message", + le32_to_cpu(hd->h_version), nodeid); + break; } - dlm_receive_buffer((union dlm_packet *)ptr, nodeid); - -skip: ret += msglen; len -= msglen; ptr += msglen; @@ -102,3 +933,455 @@ skip: return ret; } +void dlm_midcomms_unack_msg_resend(int nodeid) +{ + struct midcomms_node *node; + struct dlm_mhandle *mh; + int idx, ret; + + idx = srcu_read_lock(&nodes_srcu); + node = nodeid2node(nodeid, 0); + if (!node) { + srcu_read_unlock(&nodes_srcu, idx); + return; + } + + /* old protocol, we don't support to retransmit on failure */ + switch (node->version) { + case DLM_VERSION_3_2: + break; + default: + srcu_read_unlock(&nodes_srcu, idx); + return; + } + + rcu_read_lock(); + list_for_each_entry_rcu(mh, &node->send_queue, list) { + if (!mh->committed) + continue; + + ret = dlm_lowcomms_resend_msg(mh->msg); + if (!ret) + log_print_ratelimited("retransmit dlm msg, seq %u, nodeid %d", + mh->seq, node->nodeid); + } + rcu_read_unlock(); + srcu_read_unlock(&nodes_srcu, idx); +} + +static void dlm_fill_opts_header(struct dlm_opts *opts, uint16_t inner_len, + uint32_t seq) +{ + opts->o_header.h_cmd = DLM_OPTS; + opts->o_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR); + opts->o_header.h_nodeid = dlm_our_nodeid(); + opts->o_header.h_length = DLM_MIDCOMMS_OPT_LEN + inner_len; + opts->o_header.u.h_seq = seq; + header_out(&opts->o_header); +} + +static void midcomms_new_msg_cb(struct dlm_mhandle *mh) +{ + atomic_inc(&mh->node->send_queue_cnt); + + spin_lock(&mh->node->send_queue_lock); + list_add_tail_rcu(&mh->list, &mh->node->send_queue); + spin_unlock(&mh->node->send_queue_lock); + + mh->seq = mh->node->seq_send++; +} + +static struct dlm_msg *dlm_midcomms_get_msg_3_2(struct dlm_mhandle *mh, int nodeid, + int len, gfp_t allocation, char **ppc) +{ + struct dlm_opts *opts; + struct dlm_msg *msg; + + msg = dlm_lowcomms_new_msg(nodeid, len + DLM_MIDCOMMS_OPT_LEN, + allocation, ppc, midcomms_new_msg_cb, mh); + if (!msg) + return NULL; + + opts = (struct dlm_opts *)*ppc; + mh->opts = opts; + + /* add possible options here */ + dlm_fill_opts_header(opts, len, mh->seq); + + *ppc += sizeof(*opts); + mh->inner_hd = (const struct dlm_header *)*ppc; + return msg; +} + +struct dlm_mhandle *dlm_midcomms_get_mhandle(int nodeid, int len, + gfp_t allocation, char **ppc) +{ + struct midcomms_node *node; + struct dlm_mhandle *mh; + struct dlm_msg *msg; + int idx; + + idx = srcu_read_lock(&nodes_srcu); + node = nodeid2node(nodeid, 0); + if (!node) { + WARN_ON_ONCE(1); + goto err; + } + + /* this is a bug, however we going on and hope it will be resolved */ + WARN_ON(test_bit(DLM_NODE_FLAG_STOP_TX, &node->flags)); + + mh = kzalloc(sizeof(*mh), GFP_NOFS); + if (!mh) + goto err; + + mh->idx = idx; + mh->node = node; + + switch (node->version) { + case DLM_VERSION_3_1: + msg = dlm_lowcomms_new_msg(nodeid, len, allocation, ppc, + NULL, NULL); + if (!msg) { + kfree(mh); + goto err; + } + + break; + case DLM_VERSION_3_2: + msg = dlm_midcomms_get_msg_3_2(mh, nodeid, len, allocation, + ppc); + if (!msg) { + kfree(mh); + goto err; + } + + break; + default: + kfree(mh); + WARN_ON(1); + goto err; + } + + mh->msg = msg; + + /* keep in mind that is a must to call + * dlm_midcomms_commit_msg() which releases + * nodes_srcu using mh->idx which is assumed + * here that the application will call it. + */ + return mh; + +err: + srcu_read_unlock(&nodes_srcu, idx); + return NULL; +} + +static void dlm_midcomms_commit_msg_3_2(struct dlm_mhandle *mh) +{ + /* nexthdr chain for fast lookup */ + mh->opts->o_nextcmd = mh->inner_hd->h_cmd; + mh->committed = true; + dlm_lowcomms_commit_msg(mh->msg); +} + +void dlm_midcomms_commit_mhandle(struct dlm_mhandle *mh) +{ + switch (mh->node->version) { + case DLM_VERSION_3_1: + srcu_read_unlock(&nodes_srcu, mh->idx); + + dlm_lowcomms_commit_msg(mh->msg); + dlm_lowcomms_put_msg(mh->msg); + /* mh is not part of rcu list in this case */ + kfree(mh); + break; + case DLM_VERSION_3_2: + dlm_midcomms_commit_msg_3_2(mh); + srcu_read_unlock(&nodes_srcu, mh->idx); + break; + default: + srcu_read_unlock(&nodes_srcu, mh->idx); + WARN_ON(1); + break; + } +} + +int dlm_midcomms_start(void) +{ + int i; + + for (i = 0; i < CONN_HASH_SIZE; i++) + INIT_HLIST_HEAD(&node_hash[i]); + + return dlm_lowcomms_start(); +} + +static void dlm_act_fin_ack_rcv(struct midcomms_node *node) +{ + spin_lock(&node->state_lock); + pr_debug("receive active fin ack from node %d with state %s\n", + node->nodeid, dlm_state_str(node->state)); + + switch (node->state) { + case DLM_FIN_WAIT1: + node->state = DLM_FIN_WAIT2; + pr_debug("switch node %d to state %s\n", + node->nodeid, dlm_state_str(node->state)); + break; + case DLM_CLOSING: + midcomms_node_reset(node); + pr_debug("switch node %d to state %s\n", + node->nodeid, dlm_state_str(node->state)); + wake_up(&node->shutdown_wait); + break; + case DLM_CLOSED: + /* not valid but somehow we got what we want */ + wake_up(&node->shutdown_wait); + break; + default: + spin_unlock(&node->state_lock); + log_print("%s: unexpected state: %d\n", + __func__, node->state); + WARN_ON(1); + return; + } + spin_unlock(&node->state_lock); +} + +void dlm_midcomms_add_member(int nodeid) +{ + struct midcomms_node *node; + int idx; + + if (nodeid == dlm_our_nodeid()) + return; + + idx = srcu_read_lock(&nodes_srcu); + node = nodeid2node(nodeid, GFP_NOFS); + if (!node) { + srcu_read_unlock(&nodes_srcu, idx); + return; + } + + spin_lock(&node->state_lock); + if (!node->users) { + pr_debug("receive add member from node %d with state %s\n", + node->nodeid, dlm_state_str(node->state)); + switch (node->state) { + case DLM_ESTABLISHED: + break; + case DLM_CLOSED: + node->state = DLM_ESTABLISHED; + pr_debug("switch node %d to state %s\n", + node->nodeid, dlm_state_str(node->state)); + break; + default: + /* some invalid state passive shutdown + * was failed, we try to reset and + * hope it will go on. + */ + log_print("reset node %d because shutdown stuck", + node->nodeid); + + midcomms_node_reset(node); + node->state = DLM_ESTABLISHED; + break; + } + } + + node->users++; + pr_debug("users inc count %d\n", node->users); + spin_unlock(&node->state_lock); + + srcu_read_unlock(&nodes_srcu, idx); +} + +void dlm_midcomms_remove_member(int nodeid) +{ + struct midcomms_node *node; + int idx; + + if (nodeid == dlm_our_nodeid()) + return; + + idx = srcu_read_lock(&nodes_srcu); + node = nodeid2node(nodeid, 0); + if (!node) { + srcu_read_unlock(&nodes_srcu, idx); + return; + } + + spin_lock(&node->state_lock); + node->users--; + pr_debug("users dec count %d\n", node->users); + + /* hitting users count to zero means the + * other side is running dlm_midcomms_stop() + * we meet us to have a clean disconnect. + */ + if (node->users == 0) { + pr_debug("receive remove member from node %d with state %s\n", + node->nodeid, dlm_state_str(node->state)); + switch (node->state) { + case DLM_ESTABLISHED: + break; + case DLM_CLOSE_WAIT: + /* passive shutdown DLM_LAST_ACK case 2 */ + node->state = DLM_LAST_ACK; + spin_unlock(&node->state_lock); + + pr_debug("switch node %d to state %s case 2\n", + node->nodeid, dlm_state_str(node->state)); + goto send_fin; + case DLM_LAST_ACK: + /* probably receive fin caught it, do nothing */ + break; + case DLM_CLOSED: + /* already gone, do nothing */ + break; + default: + log_print("%s: unexpected state: %d\n", + __func__, node->state); + break; + } + } + spin_unlock(&node->state_lock); + + srcu_read_unlock(&nodes_srcu, idx); + return; + +send_fin: + set_bit(DLM_NODE_FLAG_STOP_RX, &node->flags); + dlm_send_fin(node, dlm_pas_fin_ack_rcv); + srcu_read_unlock(&nodes_srcu, idx); +} + +static void midcomms_node_release(struct rcu_head *rcu) +{ + struct midcomms_node *node = container_of(rcu, struct midcomms_node, rcu); + + WARN_ON(atomic_read(&node->send_queue_cnt)); + kfree(node); +} + +static void midcomms_shutdown(struct midcomms_node *node) +{ + int ret; + + /* old protocol, we don't wait for pending operations */ + switch (node->version) { + case DLM_VERSION_3_2: + break; + default: + return; + } + + spin_lock(&node->state_lock); + pr_debug("receive active shutdown for node %d with state %s\n", + node->nodeid, dlm_state_str(node->state)); + switch (node->state) { + case DLM_ESTABLISHED: + node->state = DLM_FIN_WAIT1; + pr_debug("switch node %d to state %s case 2\n", + node->nodeid, dlm_state_str(node->state)); + break; + case DLM_CLOSED: + /* we have what we want */ + spin_unlock(&node->state_lock); + return; + default: + /* busy to enter DLM_FIN_WAIT1, wait until passive + * done in shutdown_wait to enter DLM_CLOSED. + */ + break; + } + spin_unlock(&node->state_lock); + + if (node->state == DLM_FIN_WAIT1) { + dlm_send_fin(node, dlm_act_fin_ack_rcv); + + if (DLM_DEBUG_FENCE_TERMINATION) + msleep(5000); + } + + /* wait for other side dlm + fin */ + ret = wait_event_timeout(node->shutdown_wait, + node->state == DLM_CLOSED || + test_bit(DLM_NODE_FLAG_CLOSE, &node->flags), + DLM_SHUTDOWN_TIMEOUT); + if (!ret || test_bit(DLM_NODE_FLAG_CLOSE, &node->flags)) { + pr_debug("active shutdown timed out for node %d with state %s\n", + node->nodeid, dlm_state_str(node->state)); + midcomms_node_reset(node); + return; + } + + pr_debug("active shutdown done for node %d with state %s\n", + node->nodeid, dlm_state_str(node->state)); +} + +void dlm_midcomms_shutdown(void) +{ + struct midcomms_node *node; + int i, idx; + + mutex_lock(&close_lock); + idx = srcu_read_lock(&nodes_srcu); + for (i = 0; i < CONN_HASH_SIZE; i++) { + hlist_for_each_entry_rcu(node, &node_hash[i], hlist) { + midcomms_shutdown(node); + + dlm_delete_debug_comms_file(node->debugfs); + + spin_lock(&nodes_lock); + hlist_del_rcu(&node->hlist); + spin_unlock(&nodes_lock); + + call_srcu(&nodes_srcu, &node->rcu, midcomms_node_release); + } + } + srcu_read_unlock(&nodes_srcu, idx); + mutex_unlock(&close_lock); + + dlm_lowcomms_shutdown(); +} + +int dlm_midcomms_close(int nodeid) +{ + struct midcomms_node *node; + int idx, ret; + + if (nodeid == dlm_our_nodeid()) + return 0; + + idx = srcu_read_lock(&nodes_srcu); + /* Abort pending close/remove operation */ + node = nodeid2node(nodeid, 0); + if (node) { + /* let shutdown waiters leave */ + set_bit(DLM_NODE_FLAG_CLOSE, &node->flags); + wake_up(&node->shutdown_wait); + } + srcu_read_unlock(&nodes_srcu, idx); + + synchronize_srcu(&nodes_srcu); + + idx = srcu_read_lock(&nodes_srcu); + mutex_lock(&close_lock); + node = nodeid2node(nodeid, 0); + if (!node) { + mutex_unlock(&close_lock); + srcu_read_unlock(&nodes_srcu, idx); + return dlm_lowcomms_close(nodeid); + } + + ret = dlm_lowcomms_close(nodeid); + spin_lock(&node->state_lock); + midcomms_node_reset(node); + spin_unlock(&node->state_lock); + srcu_read_unlock(&nodes_srcu, idx); + mutex_unlock(&close_lock); + + return ret; +} diff --git a/fs/dlm/midcomms.h b/fs/dlm/midcomms.h index 61e90a921849..579abc6929be 100644 --- a/fs/dlm/midcomms.h +++ b/fs/dlm/midcomms.h @@ -12,7 +12,22 @@ #ifndef __MIDCOMMS_DOT_H__ #define __MIDCOMMS_DOT_H__ +struct midcomms_node; + int dlm_process_incoming_buffer(int nodeid, unsigned char *buf, int buflen); +struct dlm_mhandle *dlm_midcomms_get_mhandle(int nodeid, int len, + gfp_t allocation, char **ppc); +void dlm_midcomms_commit_mhandle(struct dlm_mhandle *mh); +int dlm_midcomms_close(int nodeid); +int dlm_midcomms_start(void); +void dlm_midcomms_shutdown(void); +void dlm_midcomms_add_member(int nodeid); +void dlm_midcomms_remove_member(int nodeid); +void dlm_midcomms_unack_msg_resend(int nodeid); +const char *dlm_midcomms_state(struct midcomms_node *node); +unsigned long dlm_midcomms_flags(struct midcomms_node *node); +int dlm_midcomms_send_queue_cnt(struct midcomms_node *node); +uint32_t dlm_midcomms_version(struct midcomms_node *node); #endif /* __MIDCOMMS_DOT_H__ */ diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c index f5b1bd65728d..5651933f54a4 100644 --- a/fs/dlm/rcom.c +++ b/fs/dlm/rcom.c @@ -27,25 +27,15 @@ static int rcom_response(struct dlm_ls *ls) return test_bit(LSFL_RCOM_READY, &ls->ls_flags); } -static int create_rcom(struct dlm_ls *ls, int to_nodeid, int type, int len, - struct dlm_rcom **rc_ret, struct dlm_mhandle **mh_ret) +static void _create_rcom(struct dlm_ls *ls, int to_nodeid, int type, int len, + struct dlm_rcom **rc_ret, char *mb, int mb_len) { struct dlm_rcom *rc; - struct dlm_mhandle *mh; - char *mb; - int mb_len = sizeof(struct dlm_rcom) + len; - - mh = dlm_lowcomms_get_buffer(to_nodeid, mb_len, GFP_NOFS, &mb); - if (!mh) { - log_print("create_rcom to %d type %d len %d ENOBUFS", - to_nodeid, type, len); - return -ENOBUFS; - } rc = (struct dlm_rcom *) mb; rc->rc_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR); - rc->rc_header.h_lockspace = ls->ls_global_id; + rc->rc_header.u.h_lockspace = ls->ls_global_id; rc->rc_header.h_nodeid = dlm_our_nodeid(); rc->rc_header.h_length = mb_len; rc->rc_header.h_cmd = DLM_RCOM; @@ -56,16 +46,67 @@ static int create_rcom(struct dlm_ls *ls, int to_nodeid, int type, int len, rc->rc_seq = ls->ls_recover_seq; spin_unlock(&ls->ls_recover_lock); - *mh_ret = mh; *rc_ret = rc; +} + +static int create_rcom(struct dlm_ls *ls, int to_nodeid, int type, int len, + struct dlm_rcom **rc_ret, struct dlm_mhandle **mh_ret) +{ + int mb_len = sizeof(struct dlm_rcom) + len; + struct dlm_mhandle *mh; + char *mb; + + mh = dlm_midcomms_get_mhandle(to_nodeid, mb_len, GFP_NOFS, &mb); + if (!mh) { + log_print("%s to %d type %d len %d ENOBUFS", + __func__, to_nodeid, type, len); + return -ENOBUFS; + } + + _create_rcom(ls, to_nodeid, type, len, rc_ret, mb, mb_len); + *mh_ret = mh; return 0; } +static int create_rcom_stateless(struct dlm_ls *ls, int to_nodeid, int type, + int len, struct dlm_rcom **rc_ret, + struct dlm_msg **msg_ret) +{ + int mb_len = sizeof(struct dlm_rcom) + len; + struct dlm_msg *msg; + char *mb; + + msg = dlm_lowcomms_new_msg(to_nodeid, mb_len, GFP_NOFS, &mb, + NULL, NULL); + if (!msg) { + log_print("create_rcom to %d type %d len %d ENOBUFS", + to_nodeid, type, len); + return -ENOBUFS; + } + + _create_rcom(ls, to_nodeid, type, len, rc_ret, mb, mb_len); + *msg_ret = msg; + return 0; +} + +static void _send_rcom(struct dlm_ls *ls, struct dlm_rcom *rc) +{ + dlm_rcom_out(rc); +} + static void send_rcom(struct dlm_ls *ls, struct dlm_mhandle *mh, struct dlm_rcom *rc) { - dlm_rcom_out(rc); - dlm_lowcomms_commit_buffer(mh); + _send_rcom(ls, rc); + dlm_midcomms_commit_mhandle(mh); +} + +static void send_rcom_stateless(struct dlm_ls *ls, struct dlm_msg *msg, + struct dlm_rcom *rc) +{ + _send_rcom(ls, rc); + dlm_lowcomms_commit_msg(msg); + dlm_lowcomms_put_msg(msg); } static void set_rcom_status(struct dlm_ls *ls, struct rcom_status *rs, @@ -141,7 +182,7 @@ static void disallow_sync_reply(struct dlm_ls *ls) int dlm_rcom_status(struct dlm_ls *ls, int nodeid, uint32_t status_flags) { struct dlm_rcom *rc; - struct dlm_mhandle *mh; + struct dlm_msg *msg; int error = 0; ls->ls_recover_nodeid = nodeid; @@ -153,17 +194,17 @@ int dlm_rcom_status(struct dlm_ls *ls, int nodeid, uint32_t status_flags) } retry: - error = create_rcom(ls, nodeid, DLM_RCOM_STATUS, - sizeof(struct rcom_status), &rc, &mh); + error = create_rcom_stateless(ls, nodeid, DLM_RCOM_STATUS, + sizeof(struct rcom_status), &rc, &msg); if (error) goto out; set_rcom_status(ls, (struct rcom_status *)rc->rc_buf, status_flags); allow_sync_reply(ls, &rc->rc_id); - memset(ls->ls_recover_buf, 0, LOWCOMMS_MAX_TX_BUFFER_LEN); + memset(ls->ls_recover_buf, 0, DLM_MAX_SOCKET_BUFSIZE); - send_rcom(ls, mh, rc); + send_rcom_stateless(ls, msg, rc); error = dlm_wait_function(ls, &rcom_response); disallow_sync_reply(ls); @@ -191,11 +232,11 @@ retry: static void receive_rcom_status(struct dlm_ls *ls, struct dlm_rcom *rc_in) { struct dlm_rcom *rc; - struct dlm_mhandle *mh; struct rcom_status *rs; uint32_t status; int nodeid = rc_in->rc_header.h_nodeid; int len = sizeof(struct rcom_config); + struct dlm_msg *msg; int num_slots = 0; int error; @@ -218,8 +259,8 @@ static void receive_rcom_status(struct dlm_ls *ls, struct dlm_rcom *rc_in) len += num_slots * sizeof(struct rcom_slot); do_create: - error = create_rcom(ls, nodeid, DLM_RCOM_STATUS_REPLY, - len, &rc, &mh); + error = create_rcom_stateless(ls, nodeid, DLM_RCOM_STATUS_REPLY, + len, &rc, &msg); if (error) return; @@ -246,7 +287,7 @@ static void receive_rcom_status(struct dlm_ls *ls, struct dlm_rcom *rc_in) spin_unlock(&ls->ls_recover_lock); do_send: - send_rcom(ls, mh, rc); + send_rcom_stateless(ls, msg, rc); } static void receive_sync_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in) @@ -271,21 +312,22 @@ static void receive_sync_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in) int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len) { struct dlm_rcom *rc; - struct dlm_mhandle *mh; + struct dlm_msg *msg; int error = 0; ls->ls_recover_nodeid = nodeid; retry: - error = create_rcom(ls, nodeid, DLM_RCOM_NAMES, last_len, &rc, &mh); + error = create_rcom_stateless(ls, nodeid, DLM_RCOM_NAMES, last_len, + &rc, &msg); if (error) goto out; memcpy(rc->rc_buf, last_name, last_len); allow_sync_reply(ls, &rc->rc_id); - memset(ls->ls_recover_buf, 0, LOWCOMMS_MAX_TX_BUFFER_LEN); + memset(ls->ls_recover_buf, 0, DLM_MAX_SOCKET_BUFSIZE); - send_rcom(ls, mh, rc); + send_rcom_stateless(ls, msg, rc); error = dlm_wait_function(ls, &rcom_response); disallow_sync_reply(ls); @@ -298,14 +340,15 @@ retry: static void receive_rcom_names(struct dlm_ls *ls, struct dlm_rcom *rc_in) { struct dlm_rcom *rc; - struct dlm_mhandle *mh; int error, inlen, outlen, nodeid; + struct dlm_msg *msg; nodeid = rc_in->rc_header.h_nodeid; inlen = rc_in->rc_header.h_length - sizeof(struct dlm_rcom); - outlen = LOWCOMMS_MAX_TX_BUFFER_LEN - sizeof(struct dlm_rcom); + outlen = DLM_MAX_APP_BUFSIZE - sizeof(struct dlm_rcom); - error = create_rcom(ls, nodeid, DLM_RCOM_NAMES_REPLY, outlen, &rc, &mh); + error = create_rcom_stateless(ls, nodeid, DLM_RCOM_NAMES_REPLY, outlen, + &rc, &msg); if (error) return; rc->rc_id = rc_in->rc_id; @@ -313,7 +356,7 @@ static void receive_rcom_names(struct dlm_ls *ls, struct dlm_rcom *rc_in) dlm_copy_master_names(ls, rc_in->rc_buf, inlen, rc->rc_buf, outlen, nodeid); - send_rcom(ls, mh, rc); + send_rcom_stateless(ls, msg, rc); } int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid) @@ -342,10 +385,6 @@ static void receive_rcom_lookup(struct dlm_ls *ls, struct dlm_rcom *rc_in) int error, ret_nodeid, nodeid = rc_in->rc_header.h_nodeid; int len = rc_in->rc_header.h_length - sizeof(struct dlm_rcom); - error = create_rcom(ls, nodeid, DLM_RCOM_LOOKUP_REPLY, 0, &rc, &mh); - if (error) - return; - /* Old code would send this special id to trigger a debug dump. */ if (rc_in->rc_id == 0xFFFFFFFF) { log_error(ls, "receive_rcom_lookup dump from %d", nodeid); @@ -353,6 +392,10 @@ static void receive_rcom_lookup(struct dlm_ls *ls, struct dlm_rcom *rc_in) return; } + error = create_rcom(ls, nodeid, DLM_RCOM_LOOKUP_REPLY, 0, &rc, &mh); + if (error) + return; + error = dlm_master_lookup(ls, nodeid, rc_in->rc_buf, len, DLM_LU_RECOVER_MASTER, &ret_nodeid, NULL); if (error) @@ -458,14 +501,14 @@ int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in) char *mb; int mb_len = sizeof(struct dlm_rcom) + sizeof(struct rcom_config); - mh = dlm_lowcomms_get_buffer(nodeid, mb_len, GFP_NOFS, &mb); + mh = dlm_midcomms_get_mhandle(nodeid, mb_len, GFP_NOFS, &mb); if (!mh) return -ENOBUFS; rc = (struct dlm_rcom *) mb; rc->rc_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR); - rc->rc_header.h_lockspace = rc_in->rc_header.h_lockspace; + rc->rc_header.u.h_lockspace = rc_in->rc_header.u.h_lockspace; rc->rc_header.h_nodeid = dlm_our_nodeid(); rc->rc_header.h_length = mb_len; rc->rc_header.h_cmd = DLM_RCOM; @@ -479,7 +522,7 @@ int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in) rf->rf_lvblen = cpu_to_le32(~0U); dlm_rcom_out(rc); - dlm_lowcomms_commit_buffer(mh); + dlm_midcomms_commit_mhandle(mh); return 0; } diff --git a/fs/dlm/util.c b/fs/dlm/util.c index cfd0d00b19ae..58acbcc2081a 100644 --- a/fs/dlm/util.c +++ b/fs/dlm/util.c @@ -20,18 +20,20 @@ #define DLM_ERRNO_ETIMEDOUT 110 #define DLM_ERRNO_EINPROGRESS 115 -static void header_out(struct dlm_header *hd) +void header_out(struct dlm_header *hd) { hd->h_version = cpu_to_le32(hd->h_version); - hd->h_lockspace = cpu_to_le32(hd->h_lockspace); + /* does it for others u32 in union as well */ + hd->u.h_lockspace = cpu_to_le32(hd->u.h_lockspace); hd->h_nodeid = cpu_to_le32(hd->h_nodeid); hd->h_length = cpu_to_le16(hd->h_length); } -static void header_in(struct dlm_header *hd) +void header_in(struct dlm_header *hd) { hd->h_version = le32_to_cpu(hd->h_version); - hd->h_lockspace = le32_to_cpu(hd->h_lockspace); + /* does it for others u32 in union as well */ + hd->u.h_lockspace = le32_to_cpu(hd->u.h_lockspace); hd->h_nodeid = le32_to_cpu(hd->h_nodeid); hd->h_length = le16_to_cpu(hd->h_length); } diff --git a/fs/dlm/util.h b/fs/dlm/util.h index cc719ca9397e..d46f23c7a6a0 100644 --- a/fs/dlm/util.h +++ b/fs/dlm/util.h @@ -15,6 +15,8 @@ void dlm_message_out(struct dlm_message *ms); void dlm_message_in(struct dlm_message *ms); void dlm_rcom_out(struct dlm_rcom *rc); void dlm_rcom_in(struct dlm_rcom *rc); +void header_out(struct dlm_header *hd); +void header_in(struct dlm_header *hd); #endif diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index 392e721b50a3..7d85e64ea62f 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -533,7 +533,20 @@ static sector_t ecryptfs_bmap(struct address_space *mapping, sector_t block) return block; } +#include + const struct address_space_operations ecryptfs_aops = { + /* + * XXX: This is pretty broken for multiple reasons: ecryptfs does not + * actually use buffer_heads, and ecryptfs will crash without + * CONFIG_BLOCK. But it matches the behavior before the default for + * address_space_operations without the ->set_page_dirty method was + * cleaned up, so this is the best we can do without maintainer + * feedback. + */ +#ifdef CONFIG_BLOCK + .set_page_dirty = __set_page_dirty_buffers, +#endif .writepage = ecryptfs_writepage, .readpage = ecryptfs_readpage, .write_begin = ecryptfs_write_begin, diff --git a/fs/exec.c b/fs/exec.c index 18594f11c31f..f2bcdbeb3afb 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1360,6 +1360,10 @@ int begin_new_exec(struct linux_binprm * bprm) WRITE_ONCE(me->self_exec_id, me->self_exec_id + 1); flush_signal_handlers(me, 0); + retval = set_cred_ucounts(bprm->cred); + if (retval < 0) + goto out_unlock; + /* * install the new credentials for this executable */ @@ -1874,7 +1878,7 @@ static int do_execveat_common(int fd, struct filename *filename, * whether NPROC limit is still exceeded. */ if ((current->flags & PF_NPROC_EXCEEDED) && - atomic_read(¤t_user()->processes) > rlimit(RLIMIT_NPROC)) { + is_ucounts_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { retval = -EAGAIN; goto out_ret; } diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index 1803ef3220fd..ca37d4344361 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -491,6 +491,7 @@ int exfat_block_truncate_page(struct inode *inode, loff_t from) } static const struct address_space_operations exfat_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = exfat_readpage, .readahead = exfat_readahead, .writepage = exfat_writepage, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 68178b2234bd..dadb121beb22 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -961,6 +961,7 @@ ext2_dax_writepages(struct address_space *mapping, struct writeback_control *wbc } const struct address_space_operations ext2_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = ext2_readpage, .readahead = ext2_readahead, .writepage = ext2_writepage, @@ -975,6 +976,7 @@ const struct address_space_operations ext2_aops = { }; const struct address_space_operations ext2_nobh_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = ext2_readpage, .readahead = ext2_readahead, .writepage = ext2_nobh_writepage, @@ -990,7 +992,7 @@ const struct address_space_operations ext2_nobh_aops = { static const struct address_space_operations ext2_dax_aops = { .writepages = ext2_dax_writepages, .direct_IO = noop_direct_IO, - .set_page_dirty = noop_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, .invalidatepage = noop_invalidatepage, }; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 37002663d521..3c51e243450d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -720,6 +720,7 @@ enum { #define EXT4_IOC_CLEAR_ES_CACHE _IO('f', 40) #define EXT4_IOC_GETSTATE _IOW('f', 41, __u32) #define EXT4_IOC_GET_ES_CACHE _IOWR('f', 42, struct fiemap) +#define EXT4_IOC_CHECKPOINT _IOW('f', 43, __u32) #define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32) @@ -741,6 +742,14 @@ enum { #define EXT4_STATE_FLAG_NEWENTRY 0x00000004 #define EXT4_STATE_FLAG_DA_ALLOC_CLOSE 0x00000008 +/* flags for ioctl EXT4_IOC_CHECKPOINT */ +#define EXT4_IOC_CHECKPOINT_FLAG_DISCARD 0x1 +#define EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT 0x2 +#define EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN 0x4 +#define EXT4_IOC_CHECKPOINT_FLAG_VALID (EXT4_IOC_CHECKPOINT_FLAG_DISCARD | \ + EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT | \ + EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN) + #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* * ioctl commands in 32 bit emulation @@ -1477,7 +1486,7 @@ struct ext4_sb_info { unsigned int s_inode_goal; u32 s_hash_seed[4]; int s_def_hash_version; - int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */ + int s_hash_unsigned; /* 3 if hash should be unsigned, 0 if not */ struct percpu_counter s_freeclusters_counter; struct percpu_counter s_freeinodes_counter; struct percpu_counter s_dirs_counter; @@ -1488,6 +1497,7 @@ struct ext4_sb_info { struct kobject s_kobj; struct completion s_kobj_unregister; struct super_block *s_sb; + struct buffer_head *s_mmp_bh; /* Journaling */ struct journal_s *s_journal; @@ -3614,6 +3624,7 @@ extern const struct inode_operations ext4_symlink_inode_operations; extern const struct inode_operations ext4_fast_symlink_inode_operations; /* sysfs.c */ +extern void ext4_notify_error_sysfs(struct ext4_sb_info *sbi); extern int ext4_register_sysfs(struct super_block *sb); extern void ext4_unregister_sysfs(struct super_block *sb); extern int __init ext4_init_sysfs(void); @@ -3720,6 +3731,9 @@ extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end); /* mmp.c */ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t); +/* mmp.c */ +extern void ext4_stop_mmpd(struct ext4_sb_info *sbi); + /* verity.c */ extern const struct fsverity_operations ext4_verityops; @@ -3784,7 +3798,7 @@ static inline int ext4_buffer_uptodate(struct buffer_head *bh) * have to read the block because we may read the old data * successfully. */ - if (!buffer_uptodate(bh) && buffer_write_io_error(bh)) + if (buffer_write_io_error(bh)) set_buffer_uptodate(bh); return buffer_uptodate(bh); } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index cbf37b2cf871..92ad64b89d9b 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -825,6 +825,7 @@ void ext4_ext_tree_init(handle_t *handle, struct inode *inode) eh->eh_entries = 0; eh->eh_magic = EXT4_EXT_MAGIC; eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); + eh->eh_generation = 0; ext4_mark_inode_dirty(handle, inode); } @@ -1090,6 +1091,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_depth = 0; + neh->eh_generation = 0; /* move remainder of path[depth] to the new leaf */ if (unlikely(path[depth].p_hdr->eh_entries != @@ -1167,6 +1169,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); neh->eh_depth = cpu_to_le16(depth - i); + neh->eh_generation = 0; fidx = EXT_FIRST_INDEX(neh); fidx->ei_block = border; ext4_idx_store_pblock(fidx, oldblock); @@ -1306,6 +1309,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, neh->eh_magic = EXT4_EXT_MAGIC; ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); + set_buffer_verified(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 0a729027322d..9a3a8996aacf 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -1574,11 +1574,9 @@ static unsigned long ext4_es_scan(struct shrinker *shrink, ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_enter(sbi->s_sb, nr_to_scan, ret); - if (!nr_to_scan) - return ret; - nr_shrunk = __es_shrink(sbi, nr_to_scan, NULL); + ret = percpu_counter_read_positive(&sbi->s_es_stats.es_stats_shk_cnt); trace_ext4_es_shrink_scan_exit(sbi->s_sb, nr_shrunk, ret); return nr_shrunk; } diff --git a/fs/ext4/fsmap.h b/fs/ext4/fsmap.h index 68c8001fee85..ac642be2302e 100644 --- a/fs/ext4/fsmap.h +++ b/fs/ext4/fsmap.h @@ -50,7 +50,7 @@ int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head, #define EXT4_FMR_OWN_INODES FMR_OWNER('X', 5) /* inodes */ #define EXT4_FMR_OWN_GDT FMR_OWNER('f', 1) /* group descriptors */ #define EXT4_FMR_OWN_RESV_GDT FMR_OWNER('f', 2) /* reserved gdt blocks */ -#define EXT4_FMR_OWN_BLKBM FMR_OWNER('f', 3) /* inode bitmap */ -#define EXT4_FMR_OWN_INOBM FMR_OWNER('f', 4) /* block bitmap */ +#define EXT4_FMR_OWN_BLKBM FMR_OWNER('f', 3) /* block bitmap */ +#define EXT4_FMR_OWN_INOBM FMR_OWNER('f', 4) /* inode bitmap */ #endif /* __EXT4_FSMAP_H__ */ diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 9bab7fd4ccd5..e89fc0f770b0 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -402,7 +402,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g, * * We always try to spread first-level directories. * - * If there are blockgroups with both free inodes and free blocks counts + * If there are blockgroups with both free inodes and free clusters counts * not worse than average we return one with smallest directory count. * Otherwise we simply return a random group. * @@ -411,7 +411,7 @@ static void get_orlov_stats(struct super_block *sb, ext4_group_t g, * It's OK to put directory into a group unless * it has too many directories already (max_dirs) or * it has too few free inodes left (min_inodes) or - * it has too few free blocks left (min_blocks) or + * it has too few free clusters left (min_clusters) or * Parent's group is preferred, if it doesn't satisfy these * conditions we search cyclically through the rest. If none * of the groups look good we just look for a group with more @@ -427,7 +427,7 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, ext4_group_t real_ngroups = ext4_get_groups_count(sb); int inodes_per_group = EXT4_INODES_PER_GROUP(sb); unsigned int freei, avefreei, grp_free; - ext4_fsblk_t freeb, avefreec; + ext4_fsblk_t freec, avefreec; unsigned int ndirs; int max_dirs, min_inodes; ext4_grpblk_t min_clusters; @@ -446,9 +446,8 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); avefreei = freei / ngroups; - freeb = EXT4_C2B(sbi, - percpu_counter_read_positive(&sbi->s_freeclusters_counter)); - avefreec = freeb; + freec = percpu_counter_read_positive(&sbi->s_freeclusters_counter); + avefreec = freec; do_div(avefreec, ngroups); ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index f2b08b356a23..6166e7bec39d 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -205,7 +205,7 @@ out: /* * write the buffer to the inline inode. * If 'create' is set, we don't need to do the extra copy in the xattr - * value since it is already handled by ext4_xattr_ibody_inline_set. + * value since it is already handled by ext4_xattr_ibody_set. * That saves us one memcpy. */ static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc, @@ -287,7 +287,7 @@ static int ext4_create_inline_data(handle_t *handle, BUG_ON(!is.s.not_found); - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) { if (error == -ENOSPC) ext4_clear_inode_state(inode, @@ -359,7 +359,7 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode, i.value = value; i.value_len = len; - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; @@ -432,7 +432,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle, if (error) goto out; - error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (error) goto out; @@ -1939,8 +1939,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) i.value = value; i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ? i_size - EXT4_MIN_INLINE_DATA_SIZE : 0; - err = ext4_xattr_ibody_inline_set(handle, inode, - &i, &is); + err = ext4_xattr_ibody_set(handle, inode, &i, &is); if (err) goto out_error; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e986ed0e9099..13516eefcb94 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -375,7 +375,7 @@ void ext4_da_update_reserve_space(struct inode *inode, ei->i_reserved_data_blocks -= used; percpu_counter_sub(&sbi->s_dirtyclusters_counter, used); - spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); + spin_unlock(&ei->i_block_reservation_lock); /* Update quota subsystem for data blocks */ if (quota_claim) @@ -3247,7 +3247,7 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) ext4_clear_inode_state(inode, EXT4_STATE_JDATA); journal = EXT4_JOURNAL(inode); jbd2_journal_lock_updates(journal); - err = jbd2_journal_flush(journal); + err = jbd2_journal_flush(journal, 0); jbd2_journal_unlock_updates(journal); if (err) @@ -3442,7 +3442,7 @@ retry: * i_disksize out to i_size. This could be beyond where direct I/O is * happening and thus expose allocated blocks to direct I/O reads. */ - else if ((map->m_lblk * (1 << blkbits)) >= i_size_read(inode)) + else if (((loff_t)map->m_lblk << blkbits) >= i_size_read(inode)) m_flags = EXT4_GET_BLOCKS_CREATE; else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) m_flags = EXT4_GET_BLOCKS_IO_CREATE_EXT; @@ -3733,7 +3733,7 @@ static const struct address_space_operations ext4_da_aops = { static const struct address_space_operations ext4_dax_aops = { .writepages = ext4_dax_writepages, .direct_IO = noop_direct_IO, - .set_page_dirty = noop_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, .bmap = ext4_bmap, .invalidatepage = noop_invalidatepage, .swap_activate = ext4_iomap_swap_activate, @@ -6037,7 +6037,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) if (val) ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); else { - err = jbd2_journal_flush(journal); + err = jbd2_journal_flush(journal, 0); if (err < 0) { jbd2_journal_unlock_updates(journal); percpu_up_write(&sbi->s_writepages_rwsem); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 31627f7dc5cd..e27f34bceb8d 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -659,10 +659,9 @@ static int ext4_ioc_getfsmap(struct super_block *sb, info.gi_sb = sb; info.gi_data = arg; error = ext4_getfsmap(sb, &xhead, ext4_getfsmap_format, &info); - if (error == EXT4_QUERY_RANGE_ABORT) { - error = 0; + if (error == EXT4_QUERY_RANGE_ABORT) aborted = true; - } else if (error) + else if (error) return error; /* If we didn't abort, set the "last" flag in the last fmx */ @@ -693,13 +692,6 @@ static long ext4_ioctl_group_add(struct file *file, if (err) return err; - if (ext4_has_feature_bigalloc(sb)) { - ext4_msg(sb, KERN_ERR, - "Online resizing not supported with bigalloc"); - err = -EOPNOTSUPP; - goto group_add_out; - } - err = mnt_want_write_file(file); if (err) goto group_add_out; @@ -707,7 +699,7 @@ static long ext4_ioctl_group_add(struct file *file, err = ext4_group_add(sb, input); if (EXT4_SB(sb)->s_journal) { jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); - err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal); + err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) @@ -800,6 +792,57 @@ static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg) return error; } +static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg) +{ + int err = 0; + __u32 flags = 0; + unsigned int flush_flags = 0; + struct super_block *sb = file_inode(filp)->i_sb; + struct request_queue *q; + + if (copy_from_user(&flags, (__u32 __user *)arg, + sizeof(__u32))) + return -EFAULT; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* check for invalid bits set */ + if ((flags & ~EXT4_IOC_CHECKPOINT_FLAG_VALID) || + ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && + (flags & JBD2_JOURNAL_FLUSH_ZEROOUT))) + return -EINVAL; + + if (!EXT4_SB(sb)->s_journal) + return -ENODEV; + + if (flags & ~JBD2_JOURNAL_FLUSH_VALID) + return -EINVAL; + + q = bdev_get_queue(EXT4_SB(sb)->s_journal->j_dev); + if (!q) + return -ENXIO; + if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q)) + return -EOPNOTSUPP; + + if (flags & EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN) + return 0; + + if (flags & EXT4_IOC_CHECKPOINT_FLAG_DISCARD) + flush_flags |= JBD2_JOURNAL_FLUSH_DISCARD; + + if (flags & EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT) { + flush_flags |= JBD2_JOURNAL_FLUSH_ZEROOUT; + pr_info_ratelimited("warning: checkpointing journal with EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT can be slow"); + } + + jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); + err = jbd2_journal_flush(EXT4_SB(sb)->s_journal, flush_flags); + jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); + + return err; +} + static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -871,13 +914,6 @@ setversion_out: goto group_extend_out; } - if (ext4_has_feature_bigalloc(sb)) { - ext4_msg(sb, KERN_ERR, - "Online resizing not supported with bigalloc"); - err = -EOPNOTSUPP; - goto group_extend_out; - } - err = mnt_want_write_file(filp); if (err) goto group_extend_out; @@ -885,7 +921,7 @@ setversion_out: err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count); if (EXT4_SB(sb)->s_journal) { jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); - err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal); + err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) @@ -1028,7 +1064,7 @@ mext_out: if (EXT4_SB(sb)->s_journal) { ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE); jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); - err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal); + err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) @@ -1211,6 +1247,9 @@ resizefs_out: return fsverity_ioctl_read_metadata(filp, (const void __user *)arg); + case EXT4_IOC_CHECKPOINT: + return ext4_ioctl_checkpoint(filp, arg); + default: return -ENOTTY; } @@ -1291,6 +1330,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case EXT4_IOC_CLEAR_ES_CACHE: case EXT4_IOC_GETSTATE: case EXT4_IOC_GET_ES_CACHE: + case EXT4_IOC_CHECKPOINT: break; default: return -ENOIOCTLCMD; diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 68fbeedd627b..6cb598b549ca 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -127,9 +127,9 @@ void __dump_mmp_msg(struct super_block *sb, struct mmp_struct *mmp, */ static int kmmpd(void *data) { - struct super_block *sb = ((struct mmpd_data *) data)->sb; - struct buffer_head *bh = ((struct mmpd_data *) data)->bh; + struct super_block *sb = (struct super_block *) data; struct ext4_super_block *es = EXT4_SB(sb)->s_es; + struct buffer_head *bh = EXT4_SB(sb)->s_mmp_bh; struct mmp_struct *mmp; ext4_fsblk_t mmp_block; u32 seq = 0; @@ -245,12 +245,18 @@ static int kmmpd(void *data) retval = write_mmp_block(sb, bh); exit_thread: - EXT4_SB(sb)->s_mmp_tsk = NULL; - kfree(data); - brelse(bh); return retval; } +void ext4_stop_mmpd(struct ext4_sb_info *sbi) +{ + if (sbi->s_mmp_tsk) { + kthread_stop(sbi->s_mmp_tsk); + brelse(sbi->s_mmp_bh); + sbi->s_mmp_tsk = NULL; + } +} + /* * Get a random new sequence number but make sure it is not greater than * EXT4_MMP_SEQ_MAX. @@ -275,7 +281,6 @@ int ext4_multi_mount_protect(struct super_block *sb, struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct buffer_head *bh = NULL; struct mmp_struct *mmp = NULL; - struct mmpd_data *mmpd_data; u32 seq; unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval); unsigned int wait_time = 0; @@ -364,24 +369,17 @@ skip: goto failed; } - mmpd_data = kmalloc(sizeof(*mmpd_data), GFP_KERNEL); - if (!mmpd_data) { - ext4_warning(sb, "not enough memory for mmpd_data"); - goto failed; - } - mmpd_data->sb = sb; - mmpd_data->bh = bh; + EXT4_SB(sb)->s_mmp_bh = bh; /* * Start a kernel thread to update the MMP block periodically. */ - EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%.*s", + EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, sb, "kmmpd-%.*s", (int)sizeof(mmp->mmp_bdevname), bdevname(bh->b_bdev, mmp->mmp_bdevname)); if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) { EXT4_SB(sb)->s_mmp_tsk = NULL; - kfree(mmpd_data); ext4_warning(sb, "Unable to create kmmpd thread for %s.", sb->s_id); goto failed; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 2354426fa14f..664cdc0ef15d 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2499,7 +2499,7 @@ again: /* Which index block gets the new entry? */ if (at - entries >= icount1) { - frame->at = at = at - entries - icount1 + entries2; + frame->at = at - entries - icount1 + entries2; frame->entries = entries = entries2; swap(frame->bh, bh2); } diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index bd0d185654f3..fc885914c88a 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -74,6 +74,15 @@ int ext4_resize_begin(struct super_block *sb) return -EPERM; } + if (ext4_has_feature_bigalloc(sb)) { + ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc"); + return -EOPNOTSUPP; + } + if (ext4_has_feature_sparse_super2(sb)) { + ext4_msg(sb, KERN_ERR, "Online resizing not supported with sparse_super2"); + return -EOPNOTSUPP; + } + if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING, &EXT4_SB(sb)->s_ext4_flags)) ret = -EBUSY; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d29f6aa7d96e..20344633bdd9 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -718,6 +718,7 @@ static void flush_stashed_error_work(struct work_struct *work) goto write_directly; } jbd2_journal_stop(handle); + ext4_notify_error_sysfs(sbi); return; } write_directly: @@ -726,6 +727,7 @@ write_directly: * out and hope for the best. */ ext4_commit_super(sbi->s_sb); + ext4_notify_error_sysfs(sbi); } #define ext4_error_ratelimit(sb) \ @@ -1174,6 +1176,7 @@ static void ext4_put_super(struct super_block *sb) ext4_unregister_sysfs(sb); if (sbi->s_journal) { + jbd2_journal_unregister_shrinker(sbi->s_journal); aborted = is_journal_aborted(sbi->s_journal); err = jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; @@ -1245,8 +1248,8 @@ static void ext4_put_super(struct super_block *sb) ext4_xattr_destroy_cache(sbi->s_ea_block_cache); sbi->s_ea_block_cache = NULL; - if (sbi->s_mmp_tsk) - kthread_stop(sbi->s_mmp_tsk); + ext4_stop_mmpd(sbi); + brelse(sbi->s_sbh); sb->s_fs_info = NULL; /* @@ -1441,26 +1444,6 @@ static int ext4_nfs_commit_metadata(struct inode *inode) return ext4_write_inode(inode, &wbc); } -/* - * Try to release metadata pages (indirect blocks, directories) which are - * mapped via the block device. Since these pages could have journal heads - * which would prevent try_to_free_buffers() from freeing them, we must use - * jbd2 layer's try_to_free_buffers() function to release them. - */ -static int bdev_try_to_free_page(struct super_block *sb, struct page *page, - gfp_t wait) -{ - journal_t *journal = EXT4_SB(sb)->s_journal; - - WARN_ON(PageChecked(page)); - if (!page_has_buffers(page)) - return 0; - if (journal) - return jbd2_journal_try_to_free_buffers(journal, page); - - return try_to_free_buffers(page); -} - #ifdef CONFIG_FS_ENCRYPTION static int ext4_get_context(struct inode *inode, void *ctx, size_t len) { @@ -1655,7 +1638,6 @@ static const struct super_operations ext4_sops = { .quota_write = ext4_quota_write, .get_dquots = ext4_get_dquots, #endif - .bdev_try_to_free_page = bdev_try_to_free_page, }; static const struct export_operations ext4_export_ops = { @@ -3101,8 +3083,15 @@ static void ext4_orphan_cleanup(struct super_block *sb, inode_lock(inode); truncate_inode_pages(inode->i_mapping, inode->i_size); ret = ext4_truncate(inode); - if (ret) + if (ret) { + /* + * We need to clean up the in-core orphan list + * manually if ext4_truncate() failed to get a + * transaction handle. + */ + ext4_orphan_del(NULL, inode); ext4_std_error(inode->i_sb, ret); + } inode_unlock(inode); nr_truncates++; } else { @@ -5058,6 +5047,7 @@ no_journal: ext4_msg(sb, KERN_ERR, "unable to initialize " "flex_bg meta info!"); + ret = -ENOMEM; goto failed_mount6; } @@ -5178,6 +5168,7 @@ failed_mount_wq: sbi->s_ea_block_cache = NULL; if (sbi->s_journal) { + jbd2_journal_unregister_shrinker(sbi->s_journal); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; } @@ -5186,8 +5177,7 @@ failed_mount3a: failed_mount3: flush_work(&sbi->s_error_work); del_timer_sync(&sbi->s_err_report); - if (sbi->s_mmp_tsk) - kthread_stop(sbi->s_mmp_tsk); + ext4_stop_mmpd(sbi); failed_mount2: rcu_read_lock(); group_desc = rcu_dereference(sbi->s_group_desc); @@ -5504,6 +5494,12 @@ static int ext4_load_journal(struct super_block *sb, ext4_commit_super(sb); } + err = jbd2_journal_register_shrinker(journal); + if (err) { + EXT4_SB(sb)->s_journal = NULL; + goto err_out; + } + return 0; err_out: @@ -5646,7 +5642,7 @@ static int ext4_mark_recovery_complete(struct super_block *sb, return 0; } jbd2_journal_lock_updates(journal); - err = jbd2_journal_flush(journal); + err = jbd2_journal_flush(journal, 0); if (err < 0) goto out; @@ -5788,7 +5784,7 @@ static int ext4_freeze(struct super_block *sb) * Don't clear the needs_recovery flag if we failed to * flush the journal. */ - error = jbd2_journal_flush(journal); + error = jbd2_journal_flush(journal, 0); if (error < 0) goto out; @@ -5989,8 +5985,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) */ ext4_mark_recovery_complete(sb, es); } - if (sbi->s_mmp_tsk) - kthread_stop(sbi->s_mmp_tsk); + ext4_stop_mmpd(sbi); } else { /* Make sure we can mount this feature set readwrite */ if (ext4_has_feature_readonly(sb) || @@ -6383,7 +6378,7 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, * otherwise be livelocked... */ jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); - err = jbd2_journal_flush(EXT4_SB(sb)->s_journal); + err = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); if (err) return err; diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 55fcab60a59a..2314f7446592 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -506,6 +506,11 @@ static struct kobj_type ext4_feat_ktype = { .release = (void (*)(struct kobject *))kfree, }; +void ext4_notify_error_sysfs(struct ext4_sb_info *sbi) +{ + sysfs_notify(&sbi->s_kobj, NULL, "errors_count"); +} + static struct kobject *ext4_root; static struct kobject *ext4_feat; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 10ba4b24a0aa..6dd5c05c444a 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2190,31 +2190,7 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, return 0; } -int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, - struct ext4_xattr_info *i, - struct ext4_xattr_ibody_find *is) -{ - struct ext4_xattr_ibody_header *header; - struct ext4_xattr_search *s = &is->s; - int error; - - if (EXT4_I(inode)->i_extra_isize == 0) - return -ENOSPC; - error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); - if (error) - return error; - header = IHDR(inode, ext4_raw_inode(&is->iloc)); - if (!IS_LAST_ENTRY(s->first)) { - header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); - ext4_set_inode_state(inode, EXT4_STATE_XATTR); - } else { - header->h_magic = cpu_to_le32(0); - ext4_clear_inode_state(inode, EXT4_STATE_XATTR); - } - return 0; -} - -static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, +int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 730b91fa0dd7..77efb9a627ad 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -186,9 +186,9 @@ extern int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, extern int ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size); -extern int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, - struct ext4_xattr_info *i, - struct ext4_xattr_ibody_find *is); +extern int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, + struct ext4_xattr_info *i, + struct ext4_xattr_ibody_find *is); extern struct mb_cache *ext4_xattr_create_cache(void); extern void ext4_xattr_destroy_cache(struct mb_cache *); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index bab9b202b496..de0c9b013a85 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -342,6 +342,7 @@ int fat_block_truncate_page(struct inode *inode, loff_t from) } static const struct address_space_operations fat_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = fat_readpage, .readahead = fat_readahead, .writepage = fat_writepage, diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e91980f49388..06d04a74ab6c 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -131,25 +131,6 @@ static bool inode_io_list_move_locked(struct inode *inode, return false; } -/** - * inode_io_list_del_locked - remove an inode from its bdi_writeback IO list - * @inode: inode to be removed - * @wb: bdi_writeback @inode is being removed from - * - * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and - * clear %WB_has_dirty_io if all are empty afterwards. - */ -static void inode_io_list_del_locked(struct inode *inode, - struct bdi_writeback *wb) -{ - assert_spin_locked(&wb->list_lock); - assert_spin_locked(&inode->i_lock); - - inode->i_state &= ~I_SYNC_QUEUED; - list_del_init(&inode->i_io_list); - wb_io_lists_depopulated(wb); -} - static void wb_wakeup(struct bdi_writeback *wb) { spin_lock_bh(&wb->work_lock); @@ -244,6 +225,13 @@ void wb_wait_for_completion(struct wb_completion *done) /* one round can affect upto 5 slots */ #define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ +/* + * Maximum inodes per isw. A specific value has been chosen to make + * struct inode_switch_wbs_context fit into 1024 bytes kmalloc. + */ +#define WB_MAX_INODES_PER_ISW ((1024UL - sizeof(struct inode_switch_wbs_context)) \ + / sizeof(struct inode *)) + static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; @@ -278,6 +266,28 @@ void __inode_attach_wb(struct inode *inode, struct page *page) } EXPORT_SYMBOL_GPL(__inode_attach_wb); +/** + * inode_cgwb_move_to_attached - put the inode onto wb->b_attached list + * @inode: inode of interest with i_lock held + * @wb: target bdi_writeback + * + * Remove the inode from wb's io lists and if necessarily put onto b_attached + * list. Only inodes attached to cgwb's are kept on this list. + */ +static void inode_cgwb_move_to_attached(struct inode *inode, + struct bdi_writeback *wb) +{ + assert_spin_locked(&wb->list_lock); + assert_spin_locked(&inode->i_lock); + + inode->i_state &= ~I_SYNC_QUEUED; + if (wb != &wb->bdi->wb) + list_move(&inode->i_io_list, &wb->b_attached); + else + list_del_init(&inode->i_io_list); + wb_io_lists_depopulated(wb); +} + /** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it * @inode: inode of interest with i_lock held @@ -332,11 +342,18 @@ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) } struct inode_switch_wbs_context { - struct inode *inode; - struct bdi_writeback *new_wb; + struct rcu_work work; - struct rcu_head rcu_head; - struct work_struct work; + /* + * Multiple inodes can be switched at once. The switching procedure + * consists of two parts, separated by a RCU grace period. To make + * sure that the second part is executed for each inode gone through + * the first part, all inode pointers are placed into a NULL-terminated + * array embedded into struct inode_switch_wbs_context. Otherwise + * an inode could be left in a non-consistent state. + */ + struct bdi_writeback *new_wb; + struct inode *inodes[]; }; static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) @@ -349,50 +366,23 @@ static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) up_write(&bdi->wb_switch_rwsem); } -static void inode_switch_wbs_work_fn(struct work_struct *work) +static bool inode_do_switch_wbs(struct inode *inode, + struct bdi_writeback *old_wb, + struct bdi_writeback *new_wb) { - struct inode_switch_wbs_context *isw = - container_of(work, struct inode_switch_wbs_context, work); - struct inode *inode = isw->inode; - struct backing_dev_info *bdi = inode_to_bdi(inode); struct address_space *mapping = inode->i_mapping; - struct bdi_writeback *old_wb = inode->i_wb; - struct bdi_writeback *new_wb = isw->new_wb; XA_STATE(xas, &mapping->i_pages, 0); struct page *page; bool switched = false; - /* - * If @inode switches cgwb membership while sync_inodes_sb() is - * being issued, sync_inodes_sb() might miss it. Synchronize. - */ - down_read(&bdi->wb_switch_rwsem); - - /* - * By the time control reaches here, RCU grace period has passed - * since I_WB_SWITCH assertion and all wb stat update transactions - * between unlocked_inode_to_wb_begin/end() are guaranteed to be - * synchronizing against the i_pages lock. - * - * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock - * gives us exclusion against all wb related operations on @inode - * including IO list manipulations and stat updates. - */ - if (old_wb < new_wb) { - spin_lock(&old_wb->list_lock); - spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); - } else { - spin_lock(&new_wb->list_lock); - spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); - } spin_lock(&inode->i_lock); xa_lock_irq(&mapping->i_pages); /* - * Once I_FREEING is visible under i_lock, the eviction path owns - * the inode and we shouldn't modify ->i_io_list. + * Once I_FREEING or I_WILL_FREE are visible under i_lock, the eviction + * path owns the inode and we shouldn't modify ->i_io_list. */ - if (unlikely(inode->i_state & I_FREEING)) + if (unlikely(inode->i_state & (I_FREEING | I_WILL_FREE))) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); @@ -419,21 +409,28 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) wb_get(new_wb); /* - * Transfer to @new_wb's IO list if necessary. The specific list - * @inode was on is ignored and the inode is put on ->b_dirty which - * is always correct including from ->b_dirty_time. The transfer - * preserves @inode->dirtied_when ordering. + * Transfer to @new_wb's IO list if necessary. If the @inode is dirty, + * the specific list @inode was on is ignored and the @inode is put on + * ->b_dirty which is always correct including from ->b_dirty_time. + * The transfer preserves @inode->dirtied_when ordering. If the @inode + * was clean, it means it was on the b_attached list, so move it onto + * the b_attached list of @new_wb. */ if (!list_empty(&inode->i_io_list)) { - struct inode *pos; - - inode_io_list_del_locked(inode, old_wb); inode->i_wb = new_wb; - list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) - if (time_after_eq(inode->dirtied_when, - pos->dirtied_when)) - break; - inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev); + + if (inode->i_state & I_DIRTY_ALL) { + struct inode *pos; + + list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) + if (time_after_eq(inode->dirtied_when, + pos->dirtied_when)) + break; + inode_io_list_move_locked(inode, new_wb, + pos->i_io_list.prev); + } else { + inode_cgwb_move_to_attached(inode, new_wb); + } } else { inode->i_wb = new_wb; } @@ -452,31 +449,91 @@ skip_switch: xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); + + return switched; +} + +static void inode_switch_wbs_work_fn(struct work_struct *work) +{ + struct inode_switch_wbs_context *isw = + container_of(to_rcu_work(work), struct inode_switch_wbs_context, work); + struct backing_dev_info *bdi = inode_to_bdi(isw->inodes[0]); + struct bdi_writeback *old_wb = isw->inodes[0]->i_wb; + struct bdi_writeback *new_wb = isw->new_wb; + unsigned long nr_switched = 0; + struct inode **inodep; + + /* + * If @inode switches cgwb membership while sync_inodes_sb() is + * being issued, sync_inodes_sb() might miss it. Synchronize. + */ + down_read(&bdi->wb_switch_rwsem); + + /* + * By the time control reaches here, RCU grace period has passed + * since I_WB_SWITCH assertion and all wb stat update transactions + * between unlocked_inode_to_wb_begin/end() are guaranteed to be + * synchronizing against the i_pages lock. + * + * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock + * gives us exclusion against all wb related operations on @inode + * including IO list manipulations and stat updates. + */ + if (old_wb < new_wb) { + spin_lock(&old_wb->list_lock); + spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock(&new_wb->list_lock); + spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); + } + + for (inodep = isw->inodes; *inodep; inodep++) { + WARN_ON_ONCE((*inodep)->i_wb != old_wb); + if (inode_do_switch_wbs(*inodep, old_wb, new_wb)) + nr_switched++; + } + spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); up_read(&bdi->wb_switch_rwsem); - if (switched) { + if (nr_switched) { wb_wakeup(new_wb); - wb_put(old_wb); + wb_put_many(old_wb, nr_switched); } + + for (inodep = isw->inodes; *inodep; inodep++) + iput(*inodep); wb_put(new_wb); - - iput(inode); kfree(isw); - atomic_dec(&isw_nr_in_flight); } -static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) +static bool inode_prepare_wbs_switch(struct inode *inode, + struct bdi_writeback *new_wb) { - struct inode_switch_wbs_context *isw = container_of(rcu_head, - struct inode_switch_wbs_context, rcu_head); + /* + * Paired with smp_mb() in cgroup_writeback_umount(). + * isw_nr_in_flight must be increased before checking SB_ACTIVE and + * grabbing an inode, otherwise isw_nr_in_flight can be observed as 0 + * in cgroup_writeback_umount() and the isw_wq will be not flushed. + */ + smp_mb(); - /* needs to grab bh-unsafe locks, bounce to work item */ - INIT_WORK(&isw->work, inode_switch_wbs_work_fn); - queue_work(isw_wq, &isw->work); + /* while holding I_WB_SWITCH, no one else can update the association */ + spin_lock(&inode->i_lock); + if (!(inode->i_sb->s_flags & SB_ACTIVE) || + inode->i_state & (I_WB_SWITCH | I_FREEING | I_WILL_FREE) || + inode_to_wb(inode) == new_wb) { + spin_unlock(&inode->i_lock); + return false; + } + inode->i_state |= I_WB_SWITCH; + __iget(inode); + spin_unlock(&inode->i_lock); + + return true; } /** @@ -501,32 +558,30 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) return; - isw = kzalloc(sizeof(*isw), GFP_ATOMIC); + isw = kzalloc(sizeof(*isw) + 2 * sizeof(struct inode *), GFP_ATOMIC); if (!isw) return; + atomic_inc(&isw_nr_in_flight); + /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); - if (memcg_css) - isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); + if (memcg_css && !css_tryget(memcg_css)) + memcg_css = NULL; rcu_read_unlock(); + if (!memcg_css) + goto out_free; + + isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); + css_put(memcg_css); if (!isw->new_wb) goto out_free; - /* while holding I_WB_SWITCH, no one else can update the association */ - spin_lock(&inode->i_lock); - if (!(inode->i_sb->s_flags & SB_ACTIVE) || - inode->i_state & (I_WB_SWITCH | I_FREEING) || - inode_to_wb(inode) == isw->new_wb) { - spin_unlock(&inode->i_lock); + if (!inode_prepare_wbs_switch(inode, isw->new_wb)) goto out_free; - } - inode->i_state |= I_WB_SWITCH; - __iget(inode); - spin_unlock(&inode->i_lock); - isw->inode = inode; + isw->inodes[0] = inode; /* * In addition to synchronizing among switchers, I_WB_SWITCH tells @@ -534,17 +589,84 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ - call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); - - atomic_inc(&isw_nr_in_flight); + INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); + queue_rcu_work(isw_wq, &isw->work); return; out_free: + atomic_dec(&isw_nr_in_flight); if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); } +/** + * cleanup_offline_cgwb - detach associated inodes + * @wb: target wb + * + * Switch all inodes attached to @wb to a nearest living ancestor's wb in order + * to eventually release the dying @wb. Returns %true if not all inodes were + * switched and the function has to be restarted. + */ +bool cleanup_offline_cgwb(struct bdi_writeback *wb) +{ + struct cgroup_subsys_state *memcg_css; + struct inode_switch_wbs_context *isw; + struct inode *inode; + int nr; + bool restart = false; + + isw = kzalloc(sizeof(*isw) + WB_MAX_INODES_PER_ISW * + sizeof(struct inode *), GFP_KERNEL); + if (!isw) + return restart; + + atomic_inc(&isw_nr_in_flight); + + for (memcg_css = wb->memcg_css->parent; memcg_css; + memcg_css = memcg_css->parent) { + isw->new_wb = wb_get_create(wb->bdi, memcg_css, GFP_KERNEL); + if (isw->new_wb) + break; + } + if (unlikely(!isw->new_wb)) + isw->new_wb = &wb->bdi->wb; /* wb_get() is noop for bdi's wb */ + + nr = 0; + spin_lock(&wb->list_lock); + list_for_each_entry(inode, &wb->b_attached, i_io_list) { + if (!inode_prepare_wbs_switch(inode, isw->new_wb)) + continue; + + isw->inodes[nr++] = inode; + + if (nr >= WB_MAX_INODES_PER_ISW - 1) { + restart = true; + break; + } + } + spin_unlock(&wb->list_lock); + + /* no attached inodes? bail out */ + if (nr == 0) { + atomic_dec(&isw_nr_in_flight); + wb_put(isw->new_wb); + kfree(isw); + return restart; + } + + /* + * In addition to synchronizing among switchers, I_WB_SWITCH tells + * the RCU protected stat update paths to grab the i_page + * lock so that stat transfer can synchronize against them. + * Let's continue after I_WB_SWITCH is guaranteed to be visible. + */ + INIT_RCU_WORK(&isw->work, inode_switch_wbs_work_fn); + queue_rcu_work(isw_wq, &isw->work); + + return restart; +} + /** * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it * @wbc: writeback_control of interest @@ -1000,6 +1122,12 @@ out_bdi_put: */ void cgroup_writeback_umount(void) { + /* + * SB_ACTIVE should be reliably cleared before checking + * isw_nr_in_flight, see generic_shutdown_super(). + */ + smp_mb(); + if (atomic_read(&isw_nr_in_flight)) { /* * Use rcu_barrier() to wait for all pending callbacks to @@ -1024,6 +1152,17 @@ fs_initcall(cgroup_writeback_init); static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } +static void inode_cgwb_move_to_attached(struct inode *inode, + struct bdi_writeback *wb) +{ + assert_spin_locked(&wb->list_lock); + assert_spin_locked(&inode->i_lock); + + inode->i_state &= ~I_SYNC_QUEUED; + list_del_init(&inode->i_io_list); + wb_io_lists_depopulated(wb); +} + static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) @@ -1124,7 +1263,11 @@ void inode_io_list_del(struct inode *inode) wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); - inode_io_list_del_locked(inode, wb); + + inode->i_state &= ~I_SYNC_QUEUED; + list_del_init(&inode->i_io_list); + wb_io_lists_depopulated(wb); + spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } @@ -1437,7 +1580,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ - inode_io_list_del_locked(inode, wb); + inode_cgwb_move_to_attached(inode, wb); } } @@ -1589,7 +1732,7 @@ static int writeback_single_inode(struct inode *inode, * responsible for the writeback lists. */ if (!(inode->i_state & I_DIRTY_ALL)) - inode_io_list_del_locked(inode, wb); + inode_cgwb_move_to_attached(inode, wb); spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: @@ -2205,28 +2348,6 @@ int dirtytime_interval_handler(struct ctl_table *table, int write, return ret; } -static noinline void block_dump___mark_inode_dirty(struct inode *inode) -{ - if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) { - struct dentry *dentry; - const char *name = "?"; - - dentry = d_find_alias(inode); - if (dentry) { - spin_lock(&dentry->d_lock); - name = (const char *) dentry->d_name.name; - } - printk(KERN_DEBUG - "%s(%d): dirtied inode %lu (%s) on %s\n", - current->comm, task_pid_nr(current), inode->i_ino, - name, inode->i_sb->s_id); - if (dentry) { - spin_unlock(&dentry->d_lock); - dput(dentry); - } - } -} - /** * __mark_inode_dirty - internal function to mark an inode dirty * @@ -2296,9 +2417,6 @@ void __mark_inode_dirty(struct inode *inode, int flags) (dirtytime && (inode->i_state & I_DIRTY_INODE))) return; - if (unlikely(block_dump)) - block_dump___mark_inode_dirty(inode); - spin_lock(&inode->i_lock); if (dirtytime && (inode->i_state & I_DIRTY_INODE)) goto out_unlock_inode; diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index ff99ab2a3c43..fb733eb5aead 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -1329,7 +1330,7 @@ bool fuse_dax_inode_alloc(struct super_block *sb, struct fuse_inode *fi) static const struct address_space_operations fuse_dax_file_aops = { .writepages = fuse_dax_writepages, .direct_IO = noop_direct_IO, - .set_page_dirty = noop_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, .invalidatepage = noop_invalidatepage, }; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 23b5be3db044..81d8f064126e 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -784,7 +784,7 @@ static const struct address_space_operations gfs2_aops = { .writepages = gfs2_writepages, .readpage = gfs2_readpage, .readahead = gfs2_readahead, - .set_page_dirty = iomap_set_page_dirty, + .set_page_dirty = __set_page_dirty_nobuffers, .releasepage = iomap_releasepage, .invalidatepage = iomap_invalidatepage, .bmap = gfs2_bmap, diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 0bcf11a9987b..ed8b67b21718 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -56,14 +56,6 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh, u64 block, struct page *page) { struct inode *inode = &ip->i_inode; - int release = 0; - - if (!page || page->index) { - page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS); - if (!page) - return -ENOMEM; - release = 1; - } if (!PageUptodate(page)) { void *kaddr = kmap(page); @@ -97,26 +89,10 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh, gfs2_ordered_add_inode(ip); } - if (release) { - unlock_page(page); - put_page(page); - } - return 0; } -/** - * gfs2_unstuff_dinode - Unstuff a dinode when the data has grown too big - * @ip: The GFS2 inode to unstuff - * @page: The (optional) page. This is looked up if the @page is NULL - * - * This routine unstuffs a dinode and returns it to a "normal" state such - * that the height can be grown in the traditional way. - * - * Returns: errno - */ - -int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page) +static int __gfs2_unstuff_inode(struct gfs2_inode *ip, struct page *page) { struct buffer_head *bh, *dibh; struct gfs2_dinode *di; @@ -124,11 +100,9 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page) int isdir = gfs2_is_dir(ip); int error; - down_write(&ip->i_rw_mutex); - error = gfs2_meta_inode_buffer(ip, &dibh); if (error) - goto out; + return error; if (i_size_read(&ip->i_inode)) { /* Get a free block, fill it with the stuffed data, @@ -170,12 +144,38 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page) out_brelse: brelse(dibh); + return error; +} + +/** + * gfs2_unstuff_dinode - Unstuff a dinode when the data has grown too big + * @ip: The GFS2 inode to unstuff + * + * This routine unstuffs a dinode and returns it to a "normal" state such + * that the height can be grown in the traditional way. + * + * Returns: errno + */ + +int gfs2_unstuff_dinode(struct gfs2_inode *ip) +{ + struct inode *inode = &ip->i_inode; + struct page *page; + int error; + + down_write(&ip->i_rw_mutex); + page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS); + error = -ENOMEM; + if (!page) + goto out; + error = __gfs2_unstuff_inode(ip, page); + unlock_page(page); + put_page(page); out: up_write(&ip->i_rw_mutex); return error; } - /** * find_metapath - Find path through the metadata tree * @sdp: The superblock @@ -1079,7 +1079,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, goto out_trans_fail; if (unstuff) { - ret = gfs2_unstuff_dinode(ip, NULL); + ret = gfs2_unstuff_dinode(ip); if (ret) goto out_trans_end; release_metapath(mp); @@ -2143,7 +2143,7 @@ static int do_grow(struct inode *inode, u64 size) goto do_grow_release; if (unstuff) { - error = gfs2_unstuff_dinode(ip, NULL); + error = gfs2_unstuff_dinode(ip); if (error) goto do_end_trans; } diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h index 6676d863faef..53cce6c08e81 100644 --- a/fs/gfs2/bmap.h +++ b/fs/gfs2/bmap.h @@ -46,7 +46,7 @@ static inline void gfs2_write_calc_reserv(const struct gfs2_inode *ip, extern const struct iomap_ops gfs2_iomap_ops; extern const struct iomap_writeback_ops gfs2_writeback_ops; -extern int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page); +extern int gfs2_unstuff_dinode(struct gfs2_inode *ip); extern int gfs2_block_map(struct inode *inode, sector_t lblock, struct buffer_head *bh, int create); extern int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length, diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 18f67b37d6f8..42b7dfffb5e7 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -172,7 +172,7 @@ static int gfs2_dir_write_data(struct gfs2_inode *ip, const char *buf, return -EINVAL; if (gfs2_is_stuffed(ip)) { - error = gfs2_unstuff_dinode(ip, NULL); + error = gfs2_unstuff_dinode(ip); if (error) return error; } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 493a83e3f590..84ec053d43b4 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -210,7 +210,7 @@ void gfs2_set_inode_flags(struct inode *inode) /** * do_gfs2_set_flags - set flags on an inode - * @filp: file pointer + * @inode: The inode * @reqflags: The flags to set * @mask: Indicates which flags are valid * @fsflags: The FS_* inode flags passed in @@ -427,22 +427,25 @@ static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf) struct gfs2_alloc_parms ap = { .aflags = 0, }; u64 offset = page_offset(page); unsigned int data_blocks, ind_blocks, rblocks; + vm_fault_t ret = VM_FAULT_LOCKED; struct gfs2_holder gh; unsigned int length; loff_t size; - int ret; + int err; sb_start_pagefault(inode->i_sb); gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); - ret = gfs2_glock_nq(&gh); - if (ret) + err = gfs2_glock_nq(&gh); + if (err) { + ret = block_page_mkwrite_return(err); goto out_uninit; + } /* Check page index against inode size */ size = i_size_read(inode); if (offset >= size) { - ret = -EINVAL; + ret = VM_FAULT_SIGBUS; goto out_unlock; } @@ -450,8 +453,8 @@ static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf) file_update_time(vmf->vma->vm_file); /* page is wholly or partially inside EOF */ - if (offset > size - PAGE_SIZE) - length = offset_in_page(size); + if (size - offset < PAGE_SIZE) + length = size - offset; else length = PAGE_SIZE; @@ -469,24 +472,30 @@ static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf) !gfs2_write_alloc_required(ip, offset, length)) { lock_page(page); if (!PageUptodate(page) || page->mapping != inode->i_mapping) { - ret = -EAGAIN; + ret = VM_FAULT_NOPAGE; unlock_page(page); } goto out_unlock; } - ret = gfs2_rindex_update(sdp); - if (ret) + err = gfs2_rindex_update(sdp); + if (err) { + ret = block_page_mkwrite_return(err); goto out_unlock; + } gfs2_write_calc_reserv(ip, length, &data_blocks, &ind_blocks); ap.target = data_blocks + ind_blocks; - ret = gfs2_quota_lock_check(ip, &ap); - if (ret) + err = gfs2_quota_lock_check(ip, &ap); + if (err) { + ret = block_page_mkwrite_return(err); goto out_unlock; - ret = gfs2_inplace_reserve(ip, &ap); - if (ret) + } + err = gfs2_inplace_reserve(ip, &ap); + if (err) { + ret = block_page_mkwrite_return(err); goto out_quota_unlock; + } rblocks = RES_DINODE + ind_blocks; if (gfs2_is_jdata(ip)) @@ -495,28 +504,38 @@ static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf) rblocks += RES_STATFS + RES_QUOTA; rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks); } - ret = gfs2_trans_begin(sdp, rblocks, 0); - if (ret) + err = gfs2_trans_begin(sdp, rblocks, 0); + if (err) { + ret = block_page_mkwrite_return(err); goto out_trans_fail; + } + + /* Unstuff, if required, and allocate backing blocks for page */ + if (gfs2_is_stuffed(ip)) { + err = gfs2_unstuff_dinode(ip); + if (err) { + ret = block_page_mkwrite_return(err); + goto out_trans_end; + } + } lock_page(page); - ret = -EAGAIN; /* If truncated, we must retry the operation, we may have raced * with the glock demotion code. */ - if (!PageUptodate(page) || page->mapping != inode->i_mapping) - goto out_trans_end; + if (!PageUptodate(page) || page->mapping != inode->i_mapping) { + ret = VM_FAULT_NOPAGE; + goto out_page_locked; + } - /* Unstuff, if required, and allocate backing blocks for page */ - ret = 0; - if (gfs2_is_stuffed(ip)) - ret = gfs2_unstuff_dinode(ip, page); - if (ret == 0) - ret = gfs2_allocate_page_backing(page, length); + err = gfs2_allocate_page_backing(page, length); + if (err) + ret = block_page_mkwrite_return(err); -out_trans_end: - if (ret) +out_page_locked: + if (ret != VM_FAULT_LOCKED) unlock_page(page); +out_trans_end: gfs2_trans_end(sdp); out_trans_fail: gfs2_inplace_release(ip); @@ -526,12 +545,12 @@ out_unlock: gfs2_glock_dq(&gh); out_uninit: gfs2_holder_uninit(&gh); - if (ret == 0) { + if (ret == VM_FAULT_LOCKED) { set_page_dirty(page); wait_for_stable_page(page); } sb_end_pagefault(inode->i_sb); - return block_page_mkwrite_return(ret); + return ret; } static vm_fault_t gfs2_fault(struct vm_fault *vmf) @@ -962,7 +981,7 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len, gfs2_trans_add_meta(ip->i_gl, dibh); if (gfs2_is_stuffed(ip)) { - error = gfs2_unstuff_dinode(ip, NULL); + error = gfs2_unstuff_dinode(ip); if (unlikely(error)) goto out; } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index d9cb261f55b0..1f3902ecdded 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -212,8 +212,7 @@ void gfs2_glock_add_to_lru(struct gfs2_glock *gl) spin_lock(&lru_lock); - list_del(&gl->gl_lru); - list_add_tail(&gl->gl_lru, &lru_list); + list_move_tail(&gl->gl_lru, &lru_list); if (!test_bit(GLF_LRU, &gl->gl_flags)) { set_bit(GLF_LRU, &gl->gl_flags); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index d68184ebbfdd..7c9619997355 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -89,11 +89,13 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb } const struct address_space_operations gfs2_meta_aops = { + .set_page_dirty = __set_page_dirty_buffers, .writepage = gfs2_aspace_writepage, .releasepage = gfs2_releasepage, }; const struct address_space_operations gfs2_rgrp_aops = { + .set_page_dirty = __set_page_dirty_buffers, .writepage = gfs2_aspace_writepage, .releasepage = gfs2_releasepage, }; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 826f77d9cff5..5f4504dd0875 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -687,6 +687,7 @@ static int init_statfs(struct gfs2_sbd *sdp) } iput(pn); + pn = NULL; ip = GFS2_I(sdp->sd_sc_inode); error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &sdp->sd_sc_gh); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 94637c307cc8..be0997e24d60 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -825,7 +825,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, u64 size; if (gfs2_is_stuffed(ip)) { - err = gfs2_unstuff_dinode(ip, NULL); + err = gfs2_unstuff_dinode(ip); if (err) return err; } diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 3fc5cb346586..4a95a92546a0 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -159,6 +159,7 @@ static int hfs_writepages(struct address_space *mapping, } const struct address_space_operations hfs_btree_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = hfs_readpage, .writepage = hfs_writepage, .write_begin = hfs_write_begin, @@ -168,6 +169,7 @@ const struct address_space_operations hfs_btree_aops = { }; const struct address_space_operations hfs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = hfs_readpage, .writepage = hfs_writepage, .write_begin = hfs_write_begin, diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 8ea447e5c470..70e8374ddac4 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -156,6 +156,7 @@ static int hfsplus_writepages(struct address_space *mapping, } const struct address_space_operations hfsplus_btree_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = hfsplus_readpage, .writepage = hfsplus_writepage, .write_begin = hfsplus_write_begin, @@ -165,6 +166,7 @@ const struct address_space_operations hfsplus_btree_aops = { }; const struct address_space_operations hfsplus_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = hfsplus_readpage, .writepage = hfsplus_writepage, .write_begin = hfsplus_write_begin, diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 077c25128eb7..c3a49aacf20a 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -196,6 +196,7 @@ static int hpfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } const struct address_space_operations hpfs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = hpfs_readpage, .writepage = hpfs_writepage, .readahead = hpfs_readahead, diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 30dee68458c7..926eeb9bf4eb 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1446,7 +1446,7 @@ static int get_hstate_idx(int page_size_log) * otherwise hugetlb_reserve_pages reserves one less hugepages than intended. */ struct file *hugetlb_file_setup(const char *name, size_t size, - vm_flags_t acctflag, struct user_struct **user, + vm_flags_t acctflag, struct ucounts **ucounts, int creat_flags, int page_size_log) { struct inode *inode; @@ -1458,20 +1458,20 @@ struct file *hugetlb_file_setup(const char *name, size_t size, if (hstate_idx < 0) return ERR_PTR(-ENODEV); - *user = NULL; + *ucounts = NULL; mnt = hugetlbfs_vfsmount[hstate_idx]; if (!mnt) return ERR_PTR(-ENOENT); if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) { - *user = current_user(); - if (user_shm_lock(size, *user)) { + *ucounts = current_ucounts(); + if (user_shm_lock(size, *ucounts)) { task_lock(current); pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n", current->comm, current->pid); task_unlock(current); } else { - *user = NULL; + *ucounts = NULL; return ERR_PTR(-EPERM); } } @@ -1498,9 +1498,9 @@ struct file *hugetlb_file_setup(const char *name, size_t size, iput(inode); out: - if (*user) { - user_shm_unlock(size, *user); - *user = NULL; + if (*ucounts) { + user_shm_unlock(size, *ucounts); + *ucounts = NULL; } return file; } diff --git a/fs/io-wq.c b/fs/io-wq.c index b3e8624a37d0..843d4a7bcd6e 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -9,8 +9,6 @@ #include #include #include -#include -#include #include #include #include @@ -96,13 +94,14 @@ struct io_wqe { struct io_wq *wq; struct io_wq_work *hash_tail[IO_WQ_NR_HASH_BUCKETS]; + + cpumask_var_t cpu_mask; }; /* * Per io_wq state */ struct io_wq { - struct io_wqe **wqes; unsigned long state; free_work_fn *free_work; @@ -110,14 +109,14 @@ struct io_wq { struct io_wq_hash *hash; - refcount_t refs; - atomic_t worker_refs; struct completion worker_done; struct hlist_node cpuhp_node; struct task_struct *task; + + struct io_wqe *wqes[]; }; static enum cpuhp_state io_wq_online; @@ -241,7 +240,8 @@ static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) * Most likely an attempt to queue unbounded work on an io_wq that * wasn't setup with any unbounded workers. */ - WARN_ON_ONCE(!acct->max_workers); + if (unlikely(!acct->max_workers)) + pr_warn_once("io-wq is not configured for unbound workers"); rcu_read_lock(); ret = io_wqe_activate_free_worker(wqe); @@ -560,17 +560,13 @@ loop: if (ret) continue; /* timed out, exit unless we're the fixed worker */ - if (test_bit(IO_WQ_BIT_EXIT, &wq->state) || - !(worker->flags & IO_WORKER_F_FIXED)) + if (!(worker->flags & IO_WORKER_F_FIXED)) break; } if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) { raw_spin_lock_irq(&wqe->lock); - if (!wq_list_empty(&wqe->work_list)) - io_worker_handle_work(worker); - else - raw_spin_unlock_irq(&wqe->lock); + io_worker_handle_work(worker); } io_worker_exit(worker); @@ -645,7 +641,7 @@ fail: tsk->pf_io_worker = worker; worker->task = tsk; - set_cpus_allowed_ptr(tsk, cpumask_of_node(wqe->node)); + set_cpus_allowed_ptr(tsk, wqe->cpu_mask); tsk->flags |= PF_NO_SETAFFINITY; raw_spin_lock_irq(&wqe->lock); @@ -901,23 +897,20 @@ static int io_wqe_hash_wake(struct wait_queue_entry *wait, unsigned mode, struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) { - int ret = -ENOMEM, node; + int ret, node; struct io_wq *wq; if (WARN_ON_ONCE(!data->free_work || !data->do_work)) return ERR_PTR(-EINVAL); + if (WARN_ON_ONCE(!bounded)) + return ERR_PTR(-EINVAL); - wq = kzalloc(sizeof(*wq), GFP_KERNEL); + wq = kzalloc(struct_size(wq, wqes, nr_node_ids), GFP_KERNEL); if (!wq) return ERR_PTR(-ENOMEM); - - wq->wqes = kcalloc(nr_node_ids, sizeof(struct io_wqe *), GFP_KERNEL); - if (!wq->wqes) - goto err_wq; - ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node); if (ret) - goto err_wqes; + goto err_wq; refcount_inc(&data->hash->refs); wq->hash = data->hash; @@ -934,6 +927,9 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node); if (!wqe) goto err; + if (!alloc_cpumask_var(&wqe->cpu_mask, GFP_KERNEL)) + goto err; + cpumask_copy(wqe->cpu_mask, cpumask_of_node(node)); wq->wqes[node] = wqe; wqe->node = alloc_node; wqe->acct[IO_WQ_ACCT_BOUND].index = IO_WQ_ACCT_BOUND; @@ -953,17 +949,18 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data) } wq->task = get_task_struct(data->task); - refcount_set(&wq->refs, 1); atomic_set(&wq->worker_refs, 1); init_completion(&wq->worker_done); return wq; err: io_wq_put_hash(data->hash); cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node); - for_each_node(node) + for_each_node(node) { + if (!wq->wqes[node]) + continue; + free_cpumask_var(wq->wqes[node]->cpu_mask); kfree(wq->wqes[node]); -err_wqes: - kfree(wq->wqes); + } err_wq: kfree(wq); return ERR_PTR(ret); @@ -1033,10 +1030,10 @@ static void io_wq_destroy(struct io_wq *wq) .cancel_all = true, }; io_wqe_cancel_pending_work(wqe, &match); + free_cpumask_var(wqe->cpu_mask); kfree(wqe); } io_wq_put_hash(wq->hash); - kfree(wq->wqes); kfree(wq); } @@ -1045,25 +1042,67 @@ void io_wq_put_and_exit(struct io_wq *wq) WARN_ON_ONCE(!test_bit(IO_WQ_BIT_EXIT, &wq->state)); io_wq_exit_workers(wq); - if (refcount_dec_and_test(&wq->refs)) - io_wq_destroy(wq); + io_wq_destroy(wq); } +struct online_data { + unsigned int cpu; + bool online; +}; + static bool io_wq_worker_affinity(struct io_worker *worker, void *data) { - set_cpus_allowed_ptr(worker->task, cpumask_of_node(worker->wqe->node)); + struct online_data *od = data; + if (od->online) + cpumask_set_cpu(od->cpu, worker->wqe->cpu_mask); + else + cpumask_clear_cpu(od->cpu, worker->wqe->cpu_mask); return false; } +static int __io_wq_cpu_online(struct io_wq *wq, unsigned int cpu, bool online) +{ + struct online_data od = { + .cpu = cpu, + .online = online + }; + int i; + + rcu_read_lock(); + for_each_node(i) + io_wq_for_each_worker(wq->wqes[i], io_wq_worker_affinity, &od); + rcu_read_unlock(); + return 0; +} + static int io_wq_cpu_online(unsigned int cpu, struct hlist_node *node) { struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node); + + return __io_wq_cpu_online(wq, cpu, true); +} + +static int io_wq_cpu_offline(unsigned int cpu, struct hlist_node *node) +{ + struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node); + + return __io_wq_cpu_online(wq, cpu, false); +} + +int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask) +{ int i; rcu_read_lock(); - for_each_node(i) - io_wq_for_each_worker(wq->wqes[i], io_wq_worker_affinity, NULL); + for_each_node(i) { + struct io_wqe *wqe = wq->wqes[i]; + + if (mask) + cpumask_copy(wqe->cpu_mask, mask); + else + cpumask_copy(wqe->cpu_mask, cpumask_of_node(i)); + } rcu_read_unlock(); return 0; } @@ -1073,7 +1112,7 @@ static __init int io_wq_init(void) int ret; ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "io-wq/online", - io_wq_cpu_online, NULL); + io_wq_cpu_online, io_wq_cpu_offline); if (ret < 0) return ret; io_wq_online = ret; diff --git a/fs/io-wq.h b/fs/io-wq.h index af2df0680ee2..3999ee58ff26 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -87,7 +87,6 @@ static inline void wq_list_del(struct io_wq_work_list *list, struct io_wq_work { struct io_wq_work_node list; - const struct cred *creds; unsigned flags; }; @@ -128,6 +127,8 @@ void io_wq_put_and_exit(struct io_wq *wq); void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work); void io_wq_hash_work(struct io_wq_work *work, void *val); +int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask); + static inline bool io_wq_is_hashed(struct io_wq_work *work) { return work->flags & IO_WQ_WORK_HASHED; diff --git a/fs/io_uring.c b/fs/io_uring.c index fa8794c61af7..e55b21fc0ab2 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -11,7 +11,7 @@ * before writing the tail (using smp_load_acquire to read the tail will * do). It also needs a smp_mb() before updating CQ head (ordering the * entry load(s) with the head store), pairing with an implicit barrier - * through a control-dependency in io_get_cqring (smp_store_release to + * through a control-dependency in io_get_cqe (smp_store_release to * store head will do). Failure to do so could lead to reading invalid * CQ entries. * @@ -89,6 +89,7 @@ #define IORING_MAX_ENTRIES 32768 #define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES) +#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8 /* * Shift of 9 is 512 entries, or exactly one page on 64-bit archs @@ -100,11 +101,19 @@ #define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \ IORING_REGISTER_LAST + IORING_OP_LAST) +#define IO_RSRC_TAG_TABLE_SHIFT 9 +#define IO_RSRC_TAG_TABLE_MAX (1U << IO_RSRC_TAG_TABLE_SHIFT) +#define IO_RSRC_TAG_TABLE_MASK (IO_RSRC_TAG_TABLE_MAX - 1) + #define IORING_MAX_REG_BUFFERS (1U << 14) #define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ IOSQE_BUFFER_SELECT) +#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ + REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS) + +#define IO_TCTX_REFS_CACHE_NR (1U << 10) struct io_uring { u32 head ____cacheline_aligned_in_smp; @@ -164,7 +173,7 @@ struct io_rings { * Written by the application, shouldn't be modified by the * kernel. */ - u32 cq_flags; + u32 cq_flags; /* * Number of completion events lost because the queue was full; * this should be avoided by the application by making sure @@ -243,7 +252,8 @@ typedef void (rsrc_put_fn)(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc); struct io_rsrc_data { struct io_ring_ctx *ctx; - u64 *tags; + u64 **tags; + unsigned int nr; rsrc_put_fn *do_put; atomic_t refs; struct completion done; @@ -288,7 +298,6 @@ struct io_sq_data { unsigned long state; struct completion exited; - struct callback_head *park_task_work; }; #define IO_IOPOLL_BATCH 8 @@ -299,11 +308,8 @@ struct io_sq_data { struct io_comp_state { struct io_kiocb *reqs[IO_COMPL_BATCH]; unsigned int nr; - unsigned int locked_free_nr; /* inline/task_work completion list, under ->uring_lock */ struct list_head free_list; - /* IRQ completion list, under ->completion_lock */ - struct list_head locked_free_list; }; struct io_submit_link { @@ -338,16 +344,23 @@ struct io_submit_state { }; struct io_ring_ctx { + /* const or read-mostly hot data */ struct { struct percpu_ref refs; - } ____cacheline_aligned_in_smp; - struct { + struct io_rings *rings; unsigned int flags; unsigned int compat: 1; unsigned int drain_next: 1; unsigned int eventfd_async: 1; unsigned int restricted: 1; + unsigned int off_timeout_used: 1; + unsigned int drain_active: 1; + } ____cacheline_aligned_in_smp; + + /* submission data */ + struct { + struct mutex uring_lock; /* * Ring buffer of indices into array of io_uring_sqe, which is @@ -361,35 +374,33 @@ struct io_ring_ctx { * array. */ u32 *sq_array; + struct io_uring_sqe *sq_sqes; unsigned cached_sq_head; unsigned sq_entries; - unsigned sq_mask; - unsigned sq_thread_idle; - unsigned cached_sq_dropped; - unsigned cached_cq_overflow; - unsigned long sq_check_overflow; - - /* hashed buffered write serialization */ - struct io_wq_hash *hash_map; - struct list_head defer_list; + + /* + * Fixed resources fast path, should be accessed only under + * uring_lock, and updated through io_uring_register(2) + */ + struct io_rsrc_node *rsrc_node; + struct io_file_table file_table; + unsigned nr_user_files; + unsigned nr_user_bufs; + struct io_mapped_ubuf **user_bufs; + + struct io_submit_state submit_state; struct list_head timeout_list; struct list_head cq_overflow_list; - - struct io_uring_sqe *sq_sqes; + struct xarray io_buffers; + struct xarray personalities; + u32 pers_next; + unsigned sq_thread_idle; } ____cacheline_aligned_in_smp; - struct { - struct mutex uring_lock; - wait_queue_head_t wait; - } ____cacheline_aligned_in_smp; - - struct io_submit_state submit_state; - - struct io_rings *rings; - - /* Only used for accounting purposes */ - struct mm_struct *mm_account; + /* IRQ completion list, under ->completion_lock */ + struct list_head locked_free_list; + unsigned int locked_free_nr; const struct cred *sq_creds; /* cred used for __io_sq_thread() */ struct io_sq_data *sq_data; /* if using sq thread polling */ @@ -397,44 +408,18 @@ struct io_ring_ctx { struct wait_queue_head sqo_sq_wait; struct list_head sqd_list; - /* - * If used, fixed file set. Writers must ensure that ->refs is dead, - * readers must ensure that ->refs is alive as long as the file* is - * used. Only updated through io_uring_register(2). - */ - struct io_rsrc_data *file_data; - struct io_file_table file_table; - unsigned nr_user_files; - - /* if used, fixed mapped user buffers */ - struct io_rsrc_data *buf_data; - unsigned nr_user_bufs; - struct io_mapped_ubuf **user_bufs; - - struct user_struct *user; - - struct completion ref_comp; - -#if defined(CONFIG_UNIX) - struct socket *ring_sock; -#endif - - struct xarray io_buffers; - - struct xarray personalities; - u32 pers_next; + unsigned long check_cq_overflow; struct { unsigned cached_cq_tail; unsigned cq_entries; - unsigned cq_mask; - atomic_t cq_timeouts; - unsigned cq_last_tm_flush; - unsigned cq_extra; - unsigned long cq_check_overflow; - struct wait_queue_head cq_wait; - struct fasync_struct *cq_fasync; struct eventfd_ctx *cq_ev_fd; + struct wait_queue_head poll_wait; + struct wait_queue_head cq_wait; + unsigned cq_extra; + atomic_t cq_timeouts; + struct fasync_struct *cq_fasync; + unsigned cq_last_tm_flush; } ____cacheline_aligned_in_smp; struct { @@ -449,29 +434,47 @@ struct io_ring_ctx { struct list_head iopoll_list; struct hlist_head *cancel_hash; unsigned cancel_hash_bits; - bool poll_multi_file; + bool poll_multi_queue; } ____cacheline_aligned_in_smp; - struct delayed_work rsrc_put_work; - struct llist_head rsrc_put_llist; - struct list_head rsrc_ref_list; - spinlock_t rsrc_ref_lock; - struct io_rsrc_node *rsrc_node; - struct io_rsrc_node *rsrc_backup_node; - struct io_mapped_ubuf *dummy_ubuf; - struct io_restriction restrictions; - /* exit task_work */ - struct callback_head *exit_task_work; + /* slow path rsrc auxilary data, used by update/register */ + struct { + struct io_rsrc_node *rsrc_backup_node; + struct io_mapped_ubuf *dummy_ubuf; + struct io_rsrc_data *file_data; + struct io_rsrc_data *buf_data; + + struct delayed_work rsrc_put_work; + struct llist_head rsrc_put_llist; + struct list_head rsrc_ref_list; + spinlock_t rsrc_ref_lock; + }; /* Keep this last, we don't need it for the fast path */ - struct work_struct exit_work; - struct list_head tctx_list; + struct { + #if defined(CONFIG_UNIX) + struct socket *ring_sock; + #endif + /* hashed buffered write serialization */ + struct io_wq_hash *hash_map; + + /* Only used for accounting purposes */ + struct user_struct *user; + struct mm_struct *mm_account; + + /* ctx exit and cancelation */ + struct callback_head *exit_task_work; + struct work_struct exit_work; + struct list_head tctx_list; + struct completion ref_comp; + }; }; struct io_uring_task { /* submission side */ + int cached_refs; struct xarray xa; struct wait_queue_head wait; const struct io_ring_ctx *last; @@ -706,7 +709,7 @@ enum { REQ_F_BUFFER_SELECT_BIT = IOSQE_BUFFER_SELECT_BIT, /* first byte is taken by user flags, shift it to not overlap */ - REQ_F_FAIL_LINK_BIT = 8, + REQ_F_FAIL_BIT = 8, REQ_F_INFLIGHT_BIT, REQ_F_CUR_POS_BIT, REQ_F_NOWAIT_BIT, @@ -718,6 +721,7 @@ enum { REQ_F_COMPLETE_INLINE_BIT, REQ_F_REISSUE_BIT, REQ_F_DONT_REISSUE_BIT, + REQ_F_CREDS_BIT, /* keep async read/write and isreg together and in order */ REQ_F_ASYNC_READ_BIT, REQ_F_ASYNC_WRITE_BIT, @@ -742,7 +746,7 @@ enum { REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT), /* fail rest of links */ - REQ_F_FAIL_LINK = BIT(REQ_F_FAIL_LINK_BIT), + REQ_F_FAIL = BIT(REQ_F_FAIL_BIT), /* on inflight list, should be cancelled and waited on exit reliably */ REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT), /* read/write uses file position */ @@ -771,6 +775,8 @@ enum { REQ_F_ASYNC_WRITE = BIT(REQ_F_ASYNC_WRITE_BIT), /* regular file */ REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), + /* has creds assigned */ + REQ_F_CREDS = BIT(REQ_F_CREDS_BIT), }; struct async_poll { @@ -851,6 +857,8 @@ struct io_kiocb { struct hlist_node hash_node; struct async_poll *apoll; struct io_wq_work work; + const struct cred *creds; + /* store used ubuf, so we can prevent reloading */ struct io_mapped_ubuf *imu; }; @@ -1034,11 +1042,11 @@ static const struct io_op_def io_op_defs[] = { }; static bool io_disarm_next(struct io_kiocb *req); -static void io_uring_del_task_file(unsigned long index); +static void io_uring_del_tctx_node(unsigned long index); static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct task_struct *task, - struct files_struct *files); -static void io_uring_cancel_sqpoll(struct io_sq_data *sqd); + bool cancel_all); +static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx); static bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data, @@ -1059,8 +1067,7 @@ static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); static void io_req_task_queue(struct io_kiocb *req); -static void io_submit_flush_completions(struct io_comp_state *cs, - struct io_ring_ctx *ctx); +static void io_submit_flush_completions(struct io_ring_ctx *ctx); static bool io_poll_remove_waitqs(struct io_kiocb *req); static int io_req_prep_async(struct io_kiocb *req); @@ -1106,15 +1113,14 @@ static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl) percpu_ref_put(ref); } -static bool io_match_task(struct io_kiocb *head, - struct task_struct *task, - struct files_struct *files) +static bool io_match_task(struct io_kiocb *head, struct task_struct *task, + bool cancel_all) { struct io_kiocb *req; if (task && head->task != task) return false; - if (!files) + if (cancel_all) return true; io_for_each_link(req, head) { @@ -1124,10 +1130,9 @@ static bool io_match_task(struct io_kiocb *head, return false; } -static inline void req_set_fail_links(struct io_kiocb *req) +static inline void req_set_fail(struct io_kiocb *req) { - if (req->flags & REQ_F_LINK) - req->flags |= REQ_F_FAIL_LINK; + req->flags |= REQ_F_FAIL; } static void io_ring_ctx_ref_free(struct percpu_ref *ref) @@ -1179,13 +1184,13 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) ctx->flags = p->flags; init_waitqueue_head(&ctx->sqo_sq_wait); INIT_LIST_HEAD(&ctx->sqd_list); - init_waitqueue_head(&ctx->cq_wait); + init_waitqueue_head(&ctx->poll_wait); INIT_LIST_HEAD(&ctx->cq_overflow_list); init_completion(&ctx->ref_comp); xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1); xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); mutex_init(&ctx->uring_lock); - init_waitqueue_head(&ctx->wait); + init_waitqueue_head(&ctx->cq_wait); spin_lock_init(&ctx->completion_lock); INIT_LIST_HEAD(&ctx->iopoll_list); INIT_LIST_HEAD(&ctx->defer_list); @@ -1196,7 +1201,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) init_llist_head(&ctx->rsrc_put_llist); INIT_LIST_HEAD(&ctx->tctx_list); INIT_LIST_HEAD(&ctx->submit_state.comp.free_list); - INIT_LIST_HEAD(&ctx->submit_state.comp.locked_free_list); + INIT_LIST_HEAD(&ctx->locked_free_list); return ctx; err: kfree(ctx->dummy_ubuf); @@ -1205,13 +1210,20 @@ err: return NULL; } +static void io_account_cq_overflow(struct io_ring_ctx *ctx) +{ + struct io_rings *r = ctx->rings; + + WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1); + ctx->cq_extra--; +} + static bool req_need_defer(struct io_kiocb *req, u32 seq) { if (unlikely(req->flags & REQ_F_IO_DRAIN)) { struct io_ring_ctx *ctx = req->ctx; - return seq + ctx->cq_extra != ctx->cached_cq_tail - + READ_ONCE(ctx->cached_cq_overflow); + return seq + READ_ONCE(ctx->cq_extra) != ctx->cached_cq_tail; } return false; @@ -1230,8 +1242,10 @@ static void io_prep_async_work(struct io_kiocb *req) const struct io_op_def *def = &io_op_defs[req->opcode]; struct io_ring_ctx *ctx = req->ctx; - if (!req->work.creds) - req->work.creds = get_current_cred(); + if (!(req->flags & REQ_F_CREDS)) { + req->flags |= REQ_F_CREDS; + req->creds = get_current_cred(); + } req->work.list.next = NULL; req->work.flags = 0; @@ -1295,9 +1309,9 @@ static void io_kill_timeout(struct io_kiocb *req, int status) } } -static void __io_queue_deferred(struct io_ring_ctx *ctx) +static void io_queue_deferred(struct io_ring_ctx *ctx) { - do { + while (!list_empty(&ctx->defer_list)) { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, struct io_defer_entry, list); @@ -1306,19 +1320,14 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx) list_del_init(&de->list); io_req_task_queue(de->req); kfree(de); - } while (!list_empty(&ctx->defer_list)); + } } static void io_flush_timeouts(struct io_ring_ctx *ctx) { - u32 seq; + u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); - if (list_empty(&ctx->timeout_list)) - return; - - seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); - - do { + while (!list_empty(&ctx->timeout_list)) { u32 events_needed, events_got; struct io_kiocb *req = list_first_entry(&ctx->timeout_list, struct io_kiocb, timeout.list); @@ -1340,27 +1349,31 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx) list_del_init(&req->timeout.list); io_kill_timeout(req, 0); - } while (!list_empty(&ctx->timeout_list)); - + } ctx->cq_last_tm_flush = seq; } -static void io_commit_cqring(struct io_ring_ctx *ctx) +static void __io_commit_cqring_flush(struct io_ring_ctx *ctx) { - io_flush_timeouts(ctx); + if (ctx->off_timeout_used) + io_flush_timeouts(ctx); + if (ctx->drain_active) + io_queue_deferred(ctx); +} +static inline void io_commit_cqring(struct io_ring_ctx *ctx) +{ + if (unlikely(ctx->off_timeout_used || ctx->drain_active)) + __io_commit_cqring_flush(ctx); /* order cqe stores with ring update */ smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail); - - if (unlikely(!list_empty(&ctx->defer_list))) - __io_queue_deferred(ctx); } static inline bool io_sqring_full(struct io_ring_ctx *ctx) { struct io_rings *r = ctx->rings; - return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == r->sq_ring_entries; + return READ_ONCE(r->sq.tail) - ctx->cached_sq_head == ctx->sq_entries; } static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) @@ -1368,21 +1381,21 @@ static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx) return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head); } -static inline struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) +static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx) { struct io_rings *rings = ctx->rings; - unsigned tail; + unsigned tail, mask = ctx->cq_entries - 1; /* * writes to the cq entry need to come after reading head; the * control dependency is enough as we're using WRITE_ONCE to * fill the cq entry */ - if (__io_cqring_events(ctx) == rings->cq_ring_entries) + if (__io_cqring_events(ctx) == ctx->cq_entries) return NULL; tail = ctx->cached_cq_tail++; - return &rings->cqes[tail & ctx->cq_mask]; + return &rings->cqes[tail & mask]; } static inline bool io_should_trigger_evfd(struct io_ring_ctx *ctx) @@ -1399,14 +1412,14 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) /* see waitqueue_active() comment */ smp_mb(); - if (waitqueue_active(&ctx->wait)) - wake_up(&ctx->wait); + if (waitqueue_active(&ctx->cq_wait)) + wake_up(&ctx->cq_wait); if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait)) wake_up(&ctx->sq_data->wait); if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); - if (waitqueue_active(&ctx->cq_wait)) { - wake_up_interruptible(&ctx->cq_wait); + if (waitqueue_active(&ctx->poll_wait)) { + wake_up_interruptible(&ctx->poll_wait); kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); } } @@ -1417,13 +1430,13 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) smp_mb(); if (ctx->flags & IORING_SETUP_SQPOLL) { - if (waitqueue_active(&ctx->wait)) - wake_up(&ctx->wait); + if (waitqueue_active(&ctx->cq_wait)) + wake_up(&ctx->cq_wait); } if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); - if (waitqueue_active(&ctx->cq_wait)) { - wake_up_interruptible(&ctx->cq_wait); + if (waitqueue_active(&ctx->poll_wait)) { + wake_up_interruptible(&ctx->poll_wait); kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); } } @@ -1431,17 +1444,16 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) /* Returns true if there are no backlogged entries after the flush */ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) { - struct io_rings *rings = ctx->rings; unsigned long flags; bool all_flushed, posted; - if (!force && __io_cqring_events(ctx) == rings->cq_ring_entries) + if (!force && __io_cqring_events(ctx) == ctx->cq_entries) return false; posted = false; spin_lock_irqsave(&ctx->completion_lock, flags); while (!list_empty(&ctx->cq_overflow_list)) { - struct io_uring_cqe *cqe = io_get_cqring(ctx); + struct io_uring_cqe *cqe = io_get_cqe(ctx); struct io_overflow_cqe *ocqe; if (!cqe && !force) @@ -1451,8 +1463,8 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) if (cqe) memcpy(cqe, &ocqe->cqe, sizeof(*cqe)); else - WRITE_ONCE(ctx->rings->cq_overflow, - ++ctx->cached_cq_overflow); + io_account_cq_overflow(ctx); + posted = true; list_del(&ocqe->list); kfree(ocqe); @@ -1460,8 +1472,7 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) all_flushed = list_empty(&ctx->cq_overflow_list); if (all_flushed) { - clear_bit(0, &ctx->sq_check_overflow); - clear_bit(0, &ctx->cq_check_overflow); + clear_bit(0, &ctx->check_cq_overflow); ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; } @@ -1477,7 +1488,7 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) { bool ret = true; - if (test_bit(0, &ctx->cq_check_overflow)) { + if (test_bit(0, &ctx->check_cq_overflow)) { /* iopoll syncs against uring_lock, not completion_lock */ if (ctx->flags & IORING_SETUP_IOPOLL) mutex_lock(&ctx->uring_lock); @@ -1536,12 +1547,11 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, * or cannot allocate an overflow entry, then we need to drop it * on the floor. */ - WRITE_ONCE(ctx->rings->cq_overflow, ++ctx->cached_cq_overflow); + io_account_cq_overflow(ctx); return false; } if (list_empty(&ctx->cq_overflow_list)) { - set_bit(0, &ctx->sq_check_overflow); - set_bit(0, &ctx->cq_check_overflow); + set_bit(0, &ctx->check_cq_overflow); ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW; } ocqe->cqe.user_data = user_data; @@ -1563,7 +1573,7 @@ static inline bool __io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data * submission (by quite a lot). Increment the overflow count in * the ring. */ - cqe = io_get_cqring(ctx); + cqe = io_get_cqe(ctx); if (likely(cqe)) { WRITE_ONCE(cqe->user_data, user_data); WRITE_ONCE(cqe->res, res); @@ -1593,10 +1603,8 @@ static void io_req_complete_post(struct io_kiocb *req, long res, * free_list cache. */ if (req_ref_put_and_test(req)) { - struct io_comp_state *cs = &ctx->submit_state.comp; - if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { - if (req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_FAIL_LINK)) + if (req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_FAIL)) io_disarm_next(req); if (req->link) { io_req_task_queue(req->link); @@ -1605,8 +1613,8 @@ static void io_req_complete_post(struct io_kiocb *req, long res, } io_dismantle_req(req); io_put_task(req->task, 1); - list_add(&req->compl.list, &cs->locked_free_list); - cs->locked_free_nr++; + list_add(&req->compl.list, &ctx->locked_free_list); + ctx->locked_free_nr++; } else { if (!percpu_ref_tryget(&ctx->refs)) req = NULL; @@ -1622,8 +1630,7 @@ static void io_req_complete_post(struct io_kiocb *req, long res, static inline bool io_req_needs_clean(struct io_kiocb *req) { - return req->flags & (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | - REQ_F_POLLED | REQ_F_INFLIGHT); + return req->flags & IO_REQ_CLEAN_FLAGS; } static void io_req_complete_state(struct io_kiocb *req, long res, @@ -1652,7 +1659,7 @@ static inline void io_req_complete(struct io_kiocb *req, long res) static void io_req_complete_failed(struct io_kiocb *req, long res) { - req_set_fail_links(req); + req_set_fail(req); io_put_req(req); io_req_complete_post(req, res, 0); } @@ -1661,8 +1668,8 @@ static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, struct io_comp_state *cs) { spin_lock_irq(&ctx->completion_lock); - list_splice_init(&cs->locked_free_list, &cs->free_list); - cs->locked_free_nr = 0; + list_splice_init(&ctx->locked_free_list, &cs->free_list); + ctx->locked_free_nr = 0; spin_unlock_irq(&ctx->completion_lock); } @@ -1678,7 +1685,7 @@ static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) * locked cache, grab the lock and move them over to our submission * side cache. */ - if (READ_ONCE(cs->locked_free_nr) > IO_COMPL_BATCH) + if (READ_ONCE(ctx->locked_free_nr) > IO_COMPL_BATCH) io_flush_cached_locked_reqs(ctx, cs); nr = state->free_reqs; @@ -1700,11 +1707,11 @@ static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx) { struct io_submit_state *state = &ctx->submit_state; - BUILD_BUG_ON(IO_REQ_ALLOC_BATCH > ARRAY_SIZE(state->reqs)); + BUILD_BUG_ON(ARRAY_SIZE(state->reqs) < IO_REQ_ALLOC_BATCH); if (!state->free_reqs) { gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; - int ret; + int ret, i; if (io_flush_cached_reqs(ctx)) goto got_req; @@ -1722,6 +1729,20 @@ static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx) return NULL; ret = 1; } + + /* + * Don't initialise the fields below on every allocation, but + * do that in advance and keep valid on free. + */ + for (i = 0; i < ret; i++) { + struct io_kiocb *req = state->reqs[i]; + + req->ctx = ctx; + req->link = NULL; + req->async_data = NULL; + /* not necessary, but safer to zero */ + req->result = 0; + } state->free_reqs = ret; } got_req: @@ -1745,11 +1766,9 @@ static void io_dismantle_req(struct io_kiocb *req) io_put_file(req->file); if (req->fixed_rsrc_refs) percpu_ref_put(req->fixed_rsrc_refs); - if (req->async_data) + if (req->async_data) { kfree(req->async_data); - if (req->work.creds) { - put_cred(req->work.creds); - req->work.creds = NULL; + req->async_data = NULL; } } @@ -1831,7 +1850,7 @@ static bool io_disarm_next(struct io_kiocb *req) if (likely(req->flags & REQ_F_LINK_TIMEOUT)) posted = io_kill_linked_timeout(req); - if (unlikely((req->flags & REQ_F_FAIL_LINK) && + if (unlikely((req->flags & REQ_F_FAIL) && !(req->flags & REQ_F_HARDLINK))) { posted |= (req->link != NULL); io_fail_links(req); @@ -1849,7 +1868,7 @@ static struct io_kiocb *__io_req_find_next(struct io_kiocb *req) * dependencies to the next request. In case of failure, fail the rest * of the chain. */ - if (req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_FAIL_LINK)) { + if (req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_FAIL)) { struct io_ring_ctx *ctx = req->ctx; unsigned long flags; bool posted; @@ -1880,54 +1899,51 @@ static void ctx_flush_and_put(struct io_ring_ctx *ctx) return; if (ctx->submit_state.comp.nr) { mutex_lock(&ctx->uring_lock); - io_submit_flush_completions(&ctx->submit_state.comp, ctx); + io_submit_flush_completions(ctx); mutex_unlock(&ctx->uring_lock); } percpu_ref_put(&ctx->refs); } -static bool __tctx_task_work(struct io_uring_task *tctx) +static void tctx_task_work(struct callback_head *cb) { struct io_ring_ctx *ctx = NULL; - struct io_wq_work_list list; - struct io_wq_work_node *node; + struct io_uring_task *tctx = container_of(cb, struct io_uring_task, + task_work); - if (wq_list_empty(&tctx->task_list)) - return false; + while (1) { + struct io_wq_work_node *node; - spin_lock_irq(&tctx->task_lock); - list = tctx->task_list; - INIT_WQ_LIST(&tctx->task_list); - spin_unlock_irq(&tctx->task_lock); + spin_lock_irq(&tctx->task_lock); + node = tctx->task_list.first; + INIT_WQ_LIST(&tctx->task_list); + spin_unlock_irq(&tctx->task_lock); - node = list.first; - while (node) { - struct io_wq_work_node *next = node->next; - struct io_kiocb *req; + while (node) { + struct io_wq_work_node *next = node->next; + struct io_kiocb *req = container_of(node, struct io_kiocb, + io_task_work.node); - req = container_of(node, struct io_kiocb, io_task_work.node); - if (req->ctx != ctx) { - ctx_flush_and_put(ctx); - ctx = req->ctx; - percpu_ref_get(&ctx->refs); + if (req->ctx != ctx) { + ctx_flush_and_put(ctx); + ctx = req->ctx; + percpu_ref_get(&ctx->refs); + } + req->task_work.func(&req->task_work); + node = next; } - - req->task_work.func(&req->task_work); - node = next; + if (wq_list_empty(&tctx->task_list)) { + clear_bit(0, &tctx->task_state); + if (wq_list_empty(&tctx->task_list)) + break; + /* another tctx_task_work() is enqueued, yield */ + if (test_and_set_bit(0, &tctx->task_state)) + break; + } + cond_resched(); } ctx_flush_and_put(ctx); - return list.first != NULL; -} - -static void tctx_task_work(struct callback_head *cb) -{ - struct io_uring_task *tctx = container_of(cb, struct io_uring_task, task_work); - - clear_bit(0, &tctx->task_state); - - while (__tctx_task_work(tctx)) - cond_resched(); } static int io_req_task_work_add(struct io_kiocb *req) @@ -2128,26 +2144,26 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req, list_add(&req->compl.list, &state->comp.free_list); } -static void io_submit_flush_completions(struct io_comp_state *cs, - struct io_ring_ctx *ctx) +static void io_submit_flush_completions(struct io_ring_ctx *ctx) { + struct io_comp_state *cs = &ctx->submit_state.comp; int i, nr = cs->nr; - struct io_kiocb *req; struct req_batch rb; - io_init_req_batch(&rb); spin_lock_irq(&ctx->completion_lock); for (i = 0; i < nr; i++) { - req = cs->reqs[i]; + struct io_kiocb *req = cs->reqs[i]; + __io_cqring_fill_event(ctx, req->user_data, req->result, req->compl.cflags); } io_commit_cqring(ctx); spin_unlock_irq(&ctx->completion_lock); - io_cqring_ev_posted(ctx); + + io_init_req_batch(&rb); for (i = 0; i < nr; i++) { - req = cs->reqs[i]; + struct io_kiocb *req = cs->reqs[i]; /* submission and completion refs */ if (req_ref_sub_and_test(req, 2)) @@ -2235,12 +2251,6 @@ static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req) static inline bool io_run_task_work(void) { - /* - * Not safe to run on exiting task, and the task_work handling will - * not add work to such a task. - */ - if (unlikely(current->flags & PF_EXITING)) - return false; if (current->task_works) { __set_current_state(TASK_RUNNING); task_work_run(); @@ -2304,7 +2314,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, * Only spin for completions if we don't have multiple devices hanging * off our complete list, and we're under the requested amount. */ - spin = !ctx->poll_multi_file && *nr_events < min; + spin = !ctx->poll_multi_queue && *nr_events < min; ret = 0; list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, inflight_entry) { @@ -2389,7 +2399,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) * If we do, we can potentially be spinning for commands that * already triggered a CQE (eg in error). */ - if (test_bit(0, &ctx->cq_check_overflow)) + if (test_bit(0, &ctx->check_cq_overflow)) __io_cqring_overflow_flush(ctx, false); if (io_cqring_events(ctx)) goto out; @@ -2488,7 +2498,7 @@ static void __io_complete_rw(struct io_kiocb *req, long res, long res2, req->flags |= REQ_F_REISSUE; return; } - req_set_fail_links(req); + req_set_fail(req); } if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_rw_kbuf(req); @@ -2511,7 +2521,7 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) if (unlikely(res != req->result)) { if (!(res == -EAGAIN && io_rw_should_reissue(req) && io_resubmit_prep(req))) { - req_set_fail_links(req); + req_set_fail(req); req->flags |= REQ_F_DONT_REISSUE; } } @@ -2528,9 +2538,14 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) * find it from a io_do_iopoll() thread before the issuer is done * accessing the kiocb cookie. */ -static void io_iopoll_req_issued(struct io_kiocb *req, bool in_async) +static void io_iopoll_req_issued(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; + const bool in_async = io_wq_current_is_worker(); + + /* workqueue context doesn't hold uring_lock, grab it now */ + if (unlikely(in_async)) + mutex_lock(&ctx->uring_lock); /* * Track whether we have multiple files in our lists. This will impact @@ -2538,14 +2553,22 @@ static void io_iopoll_req_issued(struct io_kiocb *req, bool in_async) * different devices. */ if (list_empty(&ctx->iopoll_list)) { - ctx->poll_multi_file = false; - } else if (!ctx->poll_multi_file) { + ctx->poll_multi_queue = false; + } else if (!ctx->poll_multi_queue) { struct io_kiocb *list_req; + unsigned int queue_num0, queue_num1; list_req = list_first_entry(&ctx->iopoll_list, struct io_kiocb, inflight_entry); - if (list_req->file != req->file) - ctx->poll_multi_file = true; + + if (list_req->file != req->file) { + ctx->poll_multi_queue = true; + } else { + queue_num0 = blk_qc_t_to_queue_num(list_req->rw.kiocb.ki_cookie); + queue_num1 = blk_qc_t_to_queue_num(req->rw.kiocb.ki_cookie); + if (queue_num0 != queue_num1) + ctx->poll_multi_queue = true; + } } /* @@ -2557,14 +2580,19 @@ static void io_iopoll_req_issued(struct io_kiocb *req, bool in_async) else list_add_tail(&req->inflight_entry, &ctx->iopoll_list); - /* - * If IORING_SETUP_SQPOLL is enabled, sqes are either handled in sq thread - * task context or in io worker task context. If current task context is - * sq thread, we don't need to check whether should wake up sq thread. - */ - if (in_async && (ctx->flags & IORING_SETUP_SQPOLL) && - wq_has_sleeper(&ctx->sq_data->wait)) - wake_up(&ctx->sq_data->wait); + if (unlikely(in_async)) { + /* + * If IORING_SETUP_SQPOLL is enabled, sqes are either handle + * in sq thread task context or in io worker task context. If + * current task context is sq thread, we don't need to check + * whether should wake up sq thread. + */ + if ((ctx->flags & IORING_SETUP_SQPOLL) && + wq_has_sleeper(&ctx->sq_data->wait)) + wake_up(&ctx->sq_data->wait); + + mutex_unlock(&ctx->uring_lock); + } } static inline void io_state_file_put(struct io_submit_state *state) @@ -2621,7 +2649,7 @@ static bool __io_file_supports_async(struct file *file, int rw) return true; return false; } - if (S_ISCHR(mode) || S_ISSOCK(mode)) + if (S_ISSOCK(mode)) return true; if (S_ISREG(mode)) { if (IS_ENABLED(CONFIG_BLOCK) && @@ -2754,12 +2782,12 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, if (req->flags & REQ_F_CUR_POS) req->file->f_pos = kiocb->ki_pos; - if (ret >= 0 && kiocb->ki_complete == io_complete_rw) + if (ret >= 0 && check_reissue) __io_complete_rw(req, ret, 0, issue_flags); else io_rw_done(kiocb, ret); - if (check_reissue && req->flags & REQ_F_REISSUE) { + if (check_reissue && (req->flags & REQ_F_REISSUE)) { req->flags &= ~REQ_F_REISSUE; if (io_resubmit_prep(req)) { req_ref_get(req); @@ -2767,7 +2795,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, } else { int cflags = 0; - req_set_fail_links(req); + req_set_fail(req); if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_rw_kbuf(req); __io_req_complete(req, issue_flags, ret, cflags); @@ -3238,7 +3266,7 @@ static bool io_rw_should_retry(struct io_kiocb *req) return true; } -static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) +static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) { if (req->file->f_op->read_iter) return call_read_iter(req->file, &req->rw.kiocb, iter); @@ -3453,6 +3481,10 @@ static int io_renameat_prep(struct io_kiocb *req, struct io_rename *ren = &req->rename; const char __user *oldf, *newf; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->buf_index) + return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -3489,7 +3521,7 @@ static int io_renameat(struct io_kiocb *req, unsigned int issue_flags) req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -3500,6 +3532,10 @@ static int io_unlinkat_prep(struct io_kiocb *req, struct io_unlink *un = &req->unlink; const char __user *fname; + if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + return -EINVAL; + if (sqe->ioprio || sqe->off || sqe->len || sqe->buf_index) + return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; @@ -3533,7 +3569,7 @@ static int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags) req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -3570,7 +3606,7 @@ static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags) ret = __sys_shutdown_sock(sock, req->shutdown.how); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; #else @@ -3581,7 +3617,7 @@ static int io_shutdown(struct io_kiocb *req, unsigned int issue_flags) static int __io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_splice* sp = &req->splice; + struct io_splice *sp = &req->splice; unsigned int valid_flags = SPLICE_F_FD_IN_FIXED | SPLICE_F_ALL; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) @@ -3628,14 +3664,14 @@ static int io_tee(struct io_kiocb *req, unsigned int issue_flags) req->flags &= ~REQ_F_NEED_CLEANUP; if (ret != sp->len) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_splice* sp = &req->splice; + struct io_splice *sp = &req->splice; sp->off_in = READ_ONCE(sqe->splice_off_in); sp->off_out = READ_ONCE(sqe->off); @@ -3665,7 +3701,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) req->flags &= ~REQ_F_NEED_CLEANUP; if (ret != sp->len) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -3718,7 +3754,7 @@ static int io_fsync(struct io_kiocb *req, unsigned int issue_flags) end > 0 ? end : LLONG_MAX, req->sync.flags & IORING_FSYNC_DATASYNC); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -3747,7 +3783,7 @@ static int io_fallocate(struct io_kiocb *req, unsigned int issue_flags) ret = vfs_fallocate(req->file, req->sync.mode, req->sync.off, req->sync.len); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -3841,32 +3877,31 @@ static int io_openat2(struct io_kiocb *req, unsigned int issue_flags) goto err; file = do_filp_open(req->open.dfd, req->open.filename, &op); - /* only retry if RESOLVE_CACHED wasn't already set by application */ - if ((!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK)) && - file == ERR_PTR(-EAGAIN)) { + if (IS_ERR(file)) { /* - * We could hang on to this 'fd', but seems like marginal - * gain for something that is now known to be a slower path. - * So just put it, and we'll get a new one when we retry. + * We could hang on to this 'fd' on retrying, but seems like + * marginal gain for something that is now known to be a slower + * path. So just put it, and we'll get a new one when we retry. */ put_unused_fd(ret); - return -EAGAIN; + + ret = PTR_ERR(file); + /* only retry if RESOLVE_CACHED wasn't already set by application */ + if (ret == -EAGAIN && + (!resolve_nonblock && (issue_flags & IO_URING_F_NONBLOCK))) + return -EAGAIN; + goto err; } - if (IS_ERR(file)) { - put_unused_fd(ret); - ret = PTR_ERR(file); - } else { - if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set) - file->f_flags &= ~O_NONBLOCK; - fsnotify_open(file); - fd_install(ret, file); - } + if ((issue_flags & IO_URING_F_NONBLOCK) && !nonblock_set) + file->f_flags &= ~O_NONBLOCK; + fsnotify_open(file); + fd_install(ret, file); err: putname(req->open.filename); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -3938,7 +3973,7 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) if (head) ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); /* complete before unlock, IOPOLL may need the lock */ __io_req_complete(req, issue_flags, ret, 0); @@ -4029,7 +4064,7 @@ static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) __io_remove_buffers(ctx, head, p->bgid, -1U); } if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); /* complete before unlock, IOPOLL may need the lock */ __io_req_complete(req, issue_flags, ret, 0); io_ring_submit_unlock(ctx, !force_nonblock); @@ -4075,7 +4110,7 @@ static int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; #else @@ -4111,7 +4146,7 @@ static int io_madvise(struct io_kiocb *req, unsigned int issue_flags) ret = do_madvise(current->mm, ma->addr, ma->len, ma->advice); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; #else @@ -4150,7 +4185,7 @@ static int io_fadvise(struct io_kiocb *req, unsigned int issue_flags) ret = vfs_fadvise(req->file, fa->offset, fa->len, fa->advice); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4185,7 +4220,7 @@ static int io_statx(struct io_kiocb *req, unsigned int issue_flags) ctx->buffer); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -4243,7 +4278,7 @@ static int io_close(struct io_kiocb *req, unsigned int issue_flags) ret = filp_close(file, current->files); err: if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); if (file) fput(file); __io_req_complete(req, issue_flags, ret, 0); @@ -4276,7 +4311,7 @@ static int io_sync_file_range(struct io_kiocb *req, unsigned int issue_flags) ret = sync_file_range(req->file, req->sync.off, req->sync.len, req->sync.flags); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -4380,7 +4415,7 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < min_ret) - req_set_fail_links(req); + req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4422,7 +4457,7 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) ret = -EINTR; if (ret < min_ret) - req_set_fail_links(req); + req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -4617,7 +4652,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; if (ret < min_ret || ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)))) - req_set_fail_links(req); + req_set_fail(req); __io_req_complete(req, issue_flags, ret, cflags); return 0; } @@ -4672,7 +4707,7 @@ out_free: if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); if (ret < min_ret || ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)))) - req_set_fail_links(req); + req_set_fail(req); __io_req_complete(req, issue_flags, ret, cflags); return 0; } @@ -4711,7 +4746,7 @@ static int io_accept(struct io_kiocb *req, unsigned int issue_flags) if (ret < 0) { if (ret == -ERESTARTSYS) ret = -EINTR; - req_set_fail_links(req); + req_set_fail(req); } __io_req_complete(req, issue_flags, ret, 0); return 0; @@ -4775,7 +4810,7 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags) ret = -EINTR; out: if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -5064,7 +5099,7 @@ static void io_async_task_func(struct callback_head *cb) struct async_poll *apoll = req->apoll; struct io_ring_ctx *ctx = req->ctx; - trace_io_uring_task_run(req->ctx, req->opcode, req->user_data); + trace_io_uring_task_run(req->ctx, req, req->opcode, req->user_data); if (io_poll_rewait(req, &apoll->poll)) { spin_unlock_irq(&ctx->completion_lock); @@ -5143,50 +5178,51 @@ static __poll_t __io_arm_poll_handler(struct io_kiocb *req, return mask; } -static bool io_arm_poll_handler(struct io_kiocb *req) +enum { + IO_APOLL_OK, + IO_APOLL_ABORTED, + IO_APOLL_READY +}; + +static int io_arm_poll_handler(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; struct io_ring_ctx *ctx = req->ctx; struct async_poll *apoll; struct io_poll_table ipt; - __poll_t mask, ret; + __poll_t ret, mask = EPOLLONESHOT | POLLERR | POLLPRI; int rw; if (!req->file || !file_can_poll(req->file)) - return false; + return IO_APOLL_ABORTED; if (req->flags & REQ_F_POLLED) - return false; - if (def->pollin) + return IO_APOLL_ABORTED; + if (!def->pollin && !def->pollout) + return IO_APOLL_ABORTED; + + if (def->pollin) { rw = READ; - else if (def->pollout) + mask |= POLLIN | POLLRDNORM; + + /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ + if ((req->opcode == IORING_OP_RECVMSG) && + (req->sr_msg.msg_flags & MSG_ERRQUEUE)) + mask &= ~POLLIN; + } else { rw = WRITE; - else - return false; + mask |= POLLOUT | POLLWRNORM; + } + /* if we can't nonblock try, then no point in arming a poll handler */ if (!io_file_supports_async(req, rw)) - return false; + return IO_APOLL_ABORTED; apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); if (unlikely(!apoll)) - return false; + return IO_APOLL_ABORTED; apoll->double_poll = NULL; - - req->flags |= REQ_F_POLLED; req->apoll = apoll; - - mask = EPOLLONESHOT; - if (def->pollin) - mask |= POLLIN | POLLRDNORM; - if (def->pollout) - mask |= POLLOUT | POLLWRNORM; - - /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ - if ((req->opcode == IORING_OP_RECVMSG) && - (req->sr_msg.msg_flags & MSG_ERRQUEUE)) - mask &= ~POLLIN; - - mask |= POLLERR | POLLPRI; - + req->flags |= REQ_F_POLLED; ipt.pt._qproc = io_async_queue_proc; ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask, @@ -5194,12 +5230,14 @@ static bool io_arm_poll_handler(struct io_kiocb *req) if (ret || ipt.error) { io_poll_remove_double(req); spin_unlock_irq(&ctx->completion_lock); - return false; + if (ret) + return IO_APOLL_READY; + return IO_APOLL_ABORTED; } spin_unlock_irq(&ctx->completion_lock); - trace_io_uring_poll_arm(ctx, req->opcode, req->user_data, mask, - apoll->poll.events); - return true; + trace_io_uring_poll_arm(ctx, req, req->opcode, req->user_data, + mask, apoll->poll.events); + return IO_APOLL_OK; } static bool __io_poll_remove_one(struct io_kiocb *req, @@ -5246,7 +5284,7 @@ static bool io_poll_remove_one(struct io_kiocb *req) if (do_complete) { io_cqring_fill_event(req->ctx, req->user_data, -ECANCELED, 0); io_commit_cqring(req->ctx); - req_set_fail_links(req); + req_set_fail(req); io_put_req_deferred(req, 1); } @@ -5257,7 +5295,7 @@ static bool io_poll_remove_one(struct io_kiocb *req) * Returns true if we found and killed one or more poll requests */ static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk, - struct files_struct *files) + bool cancel_all) { struct hlist_node *tmp; struct io_kiocb *req; @@ -5269,7 +5307,7 @@ static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk, list = &ctx->cancel_hash[i]; hlist_for_each_entry_safe(req, tmp, list, hash_node) { - if (io_match_task(req, tsk, files)) + if (io_match_task(req, tsk, cancel_all)) posted += io_poll_remove_one(req); } } @@ -5456,7 +5494,7 @@ static int io_poll_update(struct io_kiocb *req, unsigned int issue_flags) err: if (ret < 0) { spin_unlock_irq(&ctx->completion_lock); - req_set_fail_links(req); + req_set_fail(req); io_req_complete(req, ret); return 0; } @@ -5476,7 +5514,7 @@ err: if (!completing) { ret = io_poll_add(preq, issue_flags); if (ret < 0) { - req_set_fail_links(preq); + req_set_fail(preq); io_req_complete(preq, ret); } } @@ -5501,7 +5539,7 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer) spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); - req_set_fail_links(req); + req_set_fail(req); io_put_req(req); return HRTIMER_NORESTART; } @@ -5537,7 +5575,7 @@ static int io_timeout_cancel(struct io_ring_ctx *ctx, __u64 user_data) if (IS_ERR(req)) return PTR_ERR(req); - req_set_fail_links(req); + req_set_fail(req); io_cqring_fill_event(ctx, req->user_data, -ECANCELED, 0); io_put_req_deferred(req, 1); return 0; @@ -5616,7 +5654,7 @@ static int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags) spin_unlock_irq(&ctx->completion_lock); io_cqring_ev_posted(ctx); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_put_req(req); return 0; } @@ -5639,6 +5677,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, return -EINVAL; req->timeout.off = off; + if (unlikely(off && !req->ctx->off_timeout_used)) + req->ctx->off_timeout_used = true; if (!req->async_data && io_alloc_async_data(req)) return -ENOMEM; @@ -5769,7 +5809,7 @@ done: io_cqring_ev_posted(ctx); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); } static int io_async_cancel_prep(struct io_kiocb *req, @@ -5826,7 +5866,7 @@ done: io_cqring_ev_posted(ctx); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); io_put_req(req); return 0; } @@ -5868,7 +5908,7 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) mutex_unlock(&ctx->uring_lock); if (ret < 0) - req_set_fail_links(req); + req_set_fail(req); __io_req_complete(req, issue_flags, ret, 0); return 0; } @@ -5979,48 +6019,69 @@ static int io_req_prep_async(struct io_kiocb *req) static u32 io_get_sequence(struct io_kiocb *req) { - struct io_kiocb *pos; - struct io_ring_ctx *ctx = req->ctx; - u32 total_submitted, nr_reqs = 0; + u32 seq = req->ctx->cached_sq_head; - io_for_each_link(pos, req) - nr_reqs++; - - total_submitted = ctx->cached_sq_head - ctx->cached_sq_dropped; - return total_submitted - nr_reqs; + /* need original cached_sq_head, but it was increased for each req */ + io_for_each_link(req, req) + seq--; + return seq; } -static int io_req_defer(struct io_kiocb *req) +static bool io_drain_req(struct io_kiocb *req) { + struct io_kiocb *pos; struct io_ring_ctx *ctx = req->ctx; struct io_defer_entry *de; int ret; u32 seq; + /* + * If we need to drain a request in the middle of a link, drain the + * head request and the next request/link after the current link. + * Considering sequential execution of links, IOSQE_IO_DRAIN will be + * maintained for every request of our link. + */ + if (ctx->drain_next) { + req->flags |= REQ_F_IO_DRAIN; + ctx->drain_next = false; + } + /* not interested in head, start from the first linked */ + io_for_each_link(pos, req->link) { + if (pos->flags & REQ_F_IO_DRAIN) { + ctx->drain_next = true; + req->flags |= REQ_F_IO_DRAIN; + break; + } + } + /* Still need defer if there is pending req in defer list. */ if (likely(list_empty_careful(&ctx->defer_list) && - !(req->flags & REQ_F_IO_DRAIN))) - return 0; + !(req->flags & REQ_F_IO_DRAIN))) { + ctx->drain_active = false; + return false; + } seq = io_get_sequence(req); /* Still a chance to pass the sequence check */ if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) - return 0; + return false; ret = io_req_prep_async(req); if (ret) return ret; io_prep_async_link(req); de = kmalloc(sizeof(*de), GFP_KERNEL); - if (!de) - return -ENOMEM; + if (!de) { + io_req_complete_failed(req, ret); + return true; + } spin_lock_irq(&ctx->completion_lock); if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) { spin_unlock_irq(&ctx->completion_lock); kfree(de); io_queue_async_work(req); - return -EIOCBQUEUED; + return true; } trace_io_uring_defer(ctx, req, req->user_data); @@ -6028,7 +6089,7 @@ static int io_req_defer(struct io_kiocb *req) de->seq = seq; list_add_tail(&de->list, &ctx->defer_list); spin_unlock_irq(&ctx->completion_lock); - return -EIOCBQUEUED; + return true; } static void io_clean_op(struct io_kiocb *req) @@ -6045,7 +6106,6 @@ static void io_clean_op(struct io_kiocb *req) kfree(req->sr_msg.kbuf); break; } - req->flags &= ~REQ_F_BUFFER_SELECTED; } if (req->flags & REQ_F_NEED_CLEANUP) { @@ -6057,8 +6117,8 @@ static void io_clean_op(struct io_kiocb *req) case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: { struct io_async_rw *io = req->async_data; - if (io->free_iovec) - kfree(io->free_iovec); + + kfree(io->free_iovec); break; } case IORING_OP_RECVMSG: @@ -6086,7 +6146,6 @@ static void io_clean_op(struct io_kiocb *req) putname(req->unlink.filename); break; } - req->flags &= ~REQ_F_NEED_CLEANUP; } if ((req->flags & REQ_F_POLLED) && req->apoll) { kfree(req->apoll->double_poll); @@ -6097,8 +6156,11 @@ static void io_clean_op(struct io_kiocb *req) struct io_uring_task *tctx = req->task->io_uring; atomic_dec(&tctx->inflight_tracked); - req->flags &= ~REQ_F_INFLIGHT; } + if (req->flags & REQ_F_CREDS) + put_cred(req->creds); + + req->flags &= ~IO_REQ_CLEAN_FLAGS; } static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) @@ -6107,8 +6169,8 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) const struct cred *creds = NULL; int ret; - if (req->work.creds && req->work.creds != current_cred()) - creds = override_creds(req->work.creds); + if ((req->flags & REQ_F_CREDS) && req->creds != current_cred()) + creds = override_creds(req->creds); switch (req->opcode) { case IORING_OP_NOP: @@ -6218,23 +6280,11 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) if (creds) revert_creds(creds); - if (ret) return ret; - /* If the op doesn't have a file, we're not polling for it */ - if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) { - const bool in_async = io_wq_current_is_worker(); - - /* workqueue context doesn't hold uring_lock, grab it now */ - if (in_async) - mutex_lock(&ctx->uring_lock); - - io_iopoll_req_issued(req, in_async); - - if (in_async) - mutex_unlock(&ctx->uring_lock); - } + if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) + io_iopoll_req_issued(req); return 0; } @@ -6416,6 +6466,7 @@ static void __io_queue_sqe(struct io_kiocb *req) struct io_kiocb *linked_timeout = io_prep_linked_timeout(req); int ret; +issue_sqe: ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); /* @@ -6430,17 +6481,21 @@ static void __io_queue_sqe(struct io_kiocb *req) cs->reqs[cs->nr++] = req; if (cs->nr == ARRAY_SIZE(cs->reqs)) - io_submit_flush_completions(cs, ctx); + io_submit_flush_completions(ctx); } else { io_put_req(req); } } else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { - if (!io_arm_poll_handler(req)) { + switch (io_arm_poll_handler(req)) { + case IO_APOLL_READY: + goto issue_sqe; + case IO_APOLL_ABORTED: /* * Queued up for async execution, worker will release * submit reference when the iocb is actually submitted. */ io_queue_async_work(req); + break; } } else { io_req_complete_failed(req, ret); @@ -6449,23 +6504,20 @@ static void __io_queue_sqe(struct io_kiocb *req) io_queue_linked_timeout(linked_timeout); } -static void io_queue_sqe(struct io_kiocb *req) +static inline void io_queue_sqe(struct io_kiocb *req) { - int ret; + if (unlikely(req->ctx->drain_active) && io_drain_req(req)) + return; - ret = io_req_defer(req); - if (ret) { - if (ret != -EIOCBQUEUED) { -fail_req: - io_req_complete_failed(req, ret); - } - } else if (req->flags & REQ_F_FORCE_ASYNC) { - ret = io_req_prep_async(req); - if (unlikely(ret)) - goto fail_req; - io_queue_async_work(req); - } else { + if (likely(!(req->flags & REQ_F_FORCE_ASYNC))) { __io_queue_sqe(req); + } else { + int ret = io_req_prep_async(req); + + if (unlikely(ret)) + io_req_complete_failed(req, ret); + else + io_queue_async_work(req); } } @@ -6478,7 +6530,7 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx, struct io_kiocb *req, unsigned int sqe_flags) { - if (!ctx->restricted) + if (likely(!ctx->restricted)) return true; if (!test_bit(req->opcode, ctx->restrictions.sqe_op)) @@ -6506,35 +6558,33 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, /* same numerical values with corresponding REQ_F_*, safe to copy */ req->flags = sqe_flags = READ_ONCE(sqe->flags); req->user_data = READ_ONCE(sqe->user_data); - req->async_data = NULL; req->file = NULL; - req->ctx = ctx; - req->link = NULL; req->fixed_rsrc_refs = NULL; /* one is dropped after submission, the other at completion */ atomic_set(&req->refs, 2); req->task = current; - req->result = 0; - req->work.creds = NULL; /* enforce forwards compatibility on users */ if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) return -EINVAL; if (unlikely(req->opcode >= IORING_OP_LAST)) return -EINVAL; - if (unlikely(!io_check_restriction(ctx, req, sqe_flags))) + if (!io_check_restriction(ctx, req, sqe_flags)) return -EACCES; if ((sqe_flags & IOSQE_BUFFER_SELECT) && !io_op_defs[req->opcode].buffer_select) return -EOPNOTSUPP; + if (unlikely(sqe_flags & IOSQE_IO_DRAIN)) + ctx->drain_active = true; personality = READ_ONCE(sqe->personality); if (personality) { - req->work.creds = xa_load(&ctx->personalities, personality); - if (!req->work.creds) + req->creds = xa_load(&ctx->personalities, personality); + if (!req->creds) return -EINVAL; - get_cred(req->work.creds); + get_cred(req->creds); + req->flags |= REQ_F_CREDS; } state = &ctx->submit_state; @@ -6571,20 +6621,22 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, fail_req: if (link->head) { /* fail even hard links since we don't submit */ - link->head->flags |= REQ_F_FAIL_LINK; + req_set_fail(link->head); io_req_complete_failed(link->head, -ECANCELED); link->head = NULL; } io_req_complete_failed(req, ret); return ret; } + ret = io_req_prep(req, sqe); if (unlikely(ret)) goto fail_req; /* don't need @sqe from now on */ - trace_io_uring_submit_sqe(ctx, req->opcode, req->user_data, - true, ctx->flags & IORING_SETUP_SQPOLL); + trace_io_uring_submit_sqe(ctx, req, req->opcode, req->user_data, + req->flags, true, + ctx->flags & IORING_SETUP_SQPOLL); /* * If we already have a head request, queue this one for async @@ -6596,17 +6648,6 @@ fail_req: if (link->head) { struct io_kiocb *head = link->head; - /* - * Taking sequential execution of a link, draining both sides - * of the link also fullfils IOSQE_IO_DRAIN semantics for all - * requests in the link. So, it drains the head and the - * next after the link request. The last one is done via - * drain_next flag to persist the effect across calls. - */ - if (req->flags & REQ_F_IO_DRAIN) { - head->flags |= REQ_F_IO_DRAIN; - ctx->drain_next = 1; - } ret = io_req_prep_async(req); if (unlikely(ret)) goto fail_req; @@ -6616,14 +6657,10 @@ fail_req: /* last request of a link, enqueue the link */ if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { - io_queue_sqe(head); link->head = NULL; + io_queue_sqe(head); } } else { - if (unlikely(ctx->drain_next)) { - req->flags |= REQ_F_IO_DRAIN; - ctx->drain_next = 0; - } if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { link->head = req; link->last = req; @@ -6644,7 +6681,7 @@ static void io_submit_state_end(struct io_submit_state *state, if (state->link.head) io_queue_sqe(state->link.head); if (state->comp.nr) - io_submit_flush_completions(&state->comp, ctx); + io_submit_flush_completions(ctx); if (state->plug_started) blk_finish_plug(&state->plug); io_state_file_put(state); @@ -6675,7 +6712,7 @@ static void io_commit_sqring(struct io_ring_ctx *ctx) } /* - * Fetch an sqe, if one is available. Note that sqe_ptr will point to memory + * Fetch an sqe, if one is available. Note this returns a pointer to memory * that is mapped by userspace. This means that care needs to be taken to * ensure that reads are stable, as we cannot rely on userspace always * being a good citizen. If members of the sqe are validated and then later @@ -6684,8 +6721,8 @@ static void io_commit_sqring(struct io_ring_ctx *ctx) */ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) { - u32 *sq_array = ctx->sq_array; - unsigned head; + unsigned head, mask = ctx->sq_entries - 1; + unsigned sq_idx = ctx->cached_sq_head++ & mask; /* * The cached sq head (or cq tail) serves two purposes: @@ -6695,28 +6732,36 @@ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) * 2) allows the kernel side to track the head on its own, even * though the application is the one updating it. */ - head = READ_ONCE(sq_array[ctx->cached_sq_head++ & ctx->sq_mask]); + head = READ_ONCE(ctx->sq_array[sq_idx]); if (likely(head < ctx->sq_entries)) return &ctx->sq_sqes[head]; /* drop invalid entries */ - ctx->cached_sq_dropped++; - WRITE_ONCE(ctx->rings->sq_dropped, ctx->cached_sq_dropped); + ctx->cq_extra--; + WRITE_ONCE(ctx->rings->sq_dropped, + READ_ONCE(ctx->rings->sq_dropped) + 1); return NULL; } static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) { + struct io_uring_task *tctx; int submitted = 0; /* make sure SQ entry isn't read before tail */ nr = min3(nr, ctx->sq_entries, io_sqring_entries(ctx)); - if (!percpu_ref_tryget_many(&ctx->refs, nr)) return -EAGAIN; - percpu_counter_add(¤t->io_uring->inflight, nr); - refcount_add(nr, ¤t->usage); + tctx = current->io_uring; + tctx->cached_refs -= nr; + if (unlikely(tctx->cached_refs < 0)) { + unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR; + + percpu_counter_add(&tctx->inflight, refill); + refcount_add(refill, ¤t->usage); + tctx->cached_refs += refill; + } io_submit_state_start(&ctx->submit_state, nr); while (submitted < nr) { @@ -6742,12 +6787,10 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) if (unlikely(submitted != nr)) { int ref_used = (submitted == -EAGAIN) ? 0 : submitted; - struct io_uring_task *tctx = current->io_uring; int unused = nr - ref_used; + current->io_uring->cached_refs += unused; percpu_ref_put_many(&ctx->refs, unused); - percpu_counter_sub(&tctx->inflight, unused); - put_task_struct_many(current, unused); } io_submit_state_end(&ctx->submit_state, ctx); @@ -6757,6 +6800,11 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) return submitted; } +static inline bool io_sqd_events_pending(struct io_sq_data *sqd) +{ + return READ_ONCE(sqd->state); +} + static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx) { /* Tell userspace we may need a wakeup call */ @@ -6779,11 +6827,15 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) to_submit = io_sqring_entries(ctx); /* if we're handling multiple rings, cap submit size for fairness */ - if (cap_entries && to_submit > 8) - to_submit = 8; + if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE) + to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE; if (!list_empty(&ctx->iopoll_list) || to_submit) { unsigned nr_events = 0; + const struct cred *creds = NULL; + + if (ctx->sq_creds != current_cred()) + creds = override_creds(ctx->sq_creds); mutex_lock(&ctx->uring_lock); if (!list_empty(&ctx->iopoll_list)) @@ -6797,10 +6849,12 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) !(ctx->flags & IORING_SETUP_R_DISABLED)) ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); - } - if (!io_sqring_full(ctx) && wq_has_sleeper(&ctx->sqo_sq_wait)) - wake_up(&ctx->sqo_sq_wait); + if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) + wake_up(&ctx->sqo_sq_wait); + if (creds) + revert_creds(creds); + } return ret; } @@ -6815,6 +6869,22 @@ static void io_sqd_update_thread_idle(struct io_sq_data *sqd) sqd->sq_thread_idle = sq_thread_idle; } +static bool io_sqd_handle_event(struct io_sq_data *sqd) +{ + bool did_sig = false; + struct ksignal ksig; + + if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) || + signal_pending(current)) { + mutex_unlock(&sqd->lock); + if (signal_pending(current)) + did_sig = get_signal(&ksig); + cond_resched(); + mutex_lock(&sqd->lock); + } + return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); +} + static int io_sq_thread(void *data) { struct io_sq_data *sqd = data; @@ -6833,48 +6903,26 @@ static int io_sq_thread(void *data) current->flags |= PF_NO_SETAFFINITY; mutex_lock(&sqd->lock); - /* a user may had exited before the thread started */ - io_run_task_work_head(&sqd->park_task_work); + while (1) { + bool cap_entries, sqt_spin = false; - while (!test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)) { - int ret; - bool cap_entries, sqt_spin, needs_sched; - - if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) || - signal_pending(current)) { - bool did_sig = false; - - mutex_unlock(&sqd->lock); - if (signal_pending(current)) { - struct ksignal ksig; - - did_sig = get_signal(&ksig); - } - cond_resched(); - mutex_lock(&sqd->lock); - io_run_task_work(); - io_run_task_work_head(&sqd->park_task_work); - if (did_sig) + if (io_sqd_events_pending(sqd) || signal_pending(current)) { + if (io_sqd_handle_event(sqd)) break; timeout = jiffies + sqd->sq_thread_idle; - continue; } - sqt_spin = false; + cap_entries = !list_is_singular(&sqd->ctx_list); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { - const struct cred *creds = NULL; + int ret = __io_sq_thread(ctx, cap_entries); - if (ctx->sq_creds != current_cred()) - creds = override_creds(ctx->sq_creds); - ret = __io_sq_thread(ctx, cap_entries); - if (creds) - revert_creds(creds); if (!sqt_spin && (ret > 0 || !list_empty(&ctx->iopoll_list))) sqt_spin = true; } + if (io_run_task_work()) + sqt_spin = true; if (sqt_spin || !time_after(jiffies, timeout)) { - io_run_task_work(); cond_resched(); if (sqt_spin) timeout = jiffies + sqd->sq_thread_idle; @@ -6882,12 +6930,12 @@ static int io_sq_thread(void *data) } prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE); - if (!test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) { - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + if (!io_sqd_events_pending(sqd) && !current->task_works) { + bool needs_sched = true; + + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { io_ring_set_wakeup_flag(ctx); - needs_sched = true; - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { if ((ctx->flags & IORING_SETUP_IOPOLL) && !list_empty_careful(&ctx->iopoll_list)) { needs_sched = false; @@ -6909,16 +6957,14 @@ static int io_sq_thread(void *data) } finish_wait(&sqd->wait, &wait); - io_run_task_work_head(&sqd->park_task_work); timeout = jiffies + sqd->sq_thread_idle; } - io_uring_cancel_sqpoll(sqd); + io_uring_cancel_generic(true, sqd); sqd->thread = NULL; list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_ring_set_wakeup_flag(ctx); io_run_task_work(); - io_run_task_work_head(&sqd->park_task_work); mutex_unlock(&sqd->lock); complete(&sqd->exited); @@ -6955,7 +7001,7 @@ static int io_wake_function(struct wait_queue_entry *curr, unsigned int mode, * Cannot safely flush overflowed CQEs from here, ensure we wake up * the task, and the next invocation will do it. */ - if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->cq_check_overflow)) + if (io_should_wake(iowq) || test_bit(0, &iowq->ctx->check_cq_overflow)) return autoremove_wake_function(curr, mode, wake_flags, key); return -1; } @@ -6983,7 +7029,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, if (ret || io_should_wake(iowq)) return ret; /* let the caller flush overflows, retry */ - if (test_bit(0, &ctx->cq_check_overflow)) + if (test_bit(0, &ctx->check_cq_overflow)) return 1; *timeout = schedule_timeout(*timeout); @@ -7048,10 +7094,10 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, ret = -EBUSY; break; } - prepare_to_wait_exclusive(&ctx->wait, &iowq.wq, + prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); ret = io_cqring_wait_schedule(ctx, &iowq, &timeout); - finish_wait(&ctx->wait, &iowq.wq); + finish_wait(&ctx->cq_wait, &iowq.wq); cond_resched(); } while (ret > 0); @@ -7060,14 +7106,36 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; } -static void io_free_file_tables(struct io_file_table *table, unsigned nr_files) +static void io_free_page_table(void **table, size_t size) { - unsigned i, nr_tables = DIV_ROUND_UP(nr_files, IORING_MAX_FILES_TABLE); + unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); for (i = 0; i < nr_tables; i++) - kfree(table->files[i]); - kfree(table->files); - table->files = NULL; + kfree(table[i]); + kfree(table); +} + +static void **io_alloc_page_table(size_t size) +{ + unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); + size_t init_size = size; + void **table; + + table = kcalloc(nr_tables, sizeof(*table), GFP_KERNEL); + if (!table) + return NULL; + + for (i = 0; i < nr_tables; i++) { + unsigned int this_size = min_t(size_t, size, PAGE_SIZE); + + table[i] = kzalloc(this_size, GFP_KERNEL); + if (!table[i]) { + io_free_page_table(table, init_size); + return NULL; + } + size -= this_size; + } + return table; } static inline void io_rsrc_ref_lock(struct io_ring_ctx *ctx) @@ -7156,33 +7224,77 @@ static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, struct io_ring_ctx *ct return ret; } +static u64 *io_get_tag_slot(struct io_rsrc_data *data, unsigned int idx) +{ + unsigned int off = idx & IO_RSRC_TAG_TABLE_MASK; + unsigned int table_idx = idx >> IO_RSRC_TAG_TABLE_SHIFT; + + return &data->tags[table_idx][off]; +} + static void io_rsrc_data_free(struct io_rsrc_data *data) { - kvfree(data->tags); + size_t size = data->nr * sizeof(data->tags[0][0]); + + if (data->tags) + io_free_page_table((void **)data->tags, size); kfree(data); } -static struct io_rsrc_data *io_rsrc_data_alloc(struct io_ring_ctx *ctx, - rsrc_put_fn *do_put, - unsigned nr) +static int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put, + u64 __user *utags, unsigned nr, + struct io_rsrc_data **pdata) { struct io_rsrc_data *data; + int ret = -ENOMEM; + unsigned i; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) - return NULL; - - data->tags = kvcalloc(nr, sizeof(*data->tags), GFP_KERNEL); + return -ENOMEM; + data->tags = (u64 **)io_alloc_page_table(nr * sizeof(data->tags[0][0])); if (!data->tags) { kfree(data); - return NULL; + return -ENOMEM; + } + + data->nr = nr; + data->ctx = ctx; + data->do_put = do_put; + if (utags) { + ret = -EFAULT; + for (i = 0; i < nr; i++) { + u64 *tag_slot = io_get_tag_slot(data, i); + + if (copy_from_user(tag_slot, &utags[i], + sizeof(*tag_slot))) + goto fail; + } } atomic_set(&data->refs, 1); - data->ctx = ctx; - data->do_put = do_put; init_completion(&data->done); - return data; + *pdata = data; + return 0; +fail: + io_rsrc_data_free(data); + return ret; +} + +static bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) +{ + size_t size = nr_files * sizeof(struct io_fixed_file); + + table->files = (struct io_fixed_file **)io_alloc_page_table(size); + return !!table->files; +} + +static void io_free_file_tables(struct io_file_table *table, unsigned nr_files) +{ + size_t size = nr_files * sizeof(struct io_fixed_file); + + io_free_page_table((void **)table->files, size); + table->files = NULL; } static void __io_sqe_files_unregister(struct io_ring_ctx *ctx) @@ -7446,31 +7558,6 @@ static int io_sqe_files_scm(struct io_ring_ctx *ctx) } #endif -static bool io_alloc_file_tables(struct io_file_table *table, unsigned nr_files) -{ - unsigned i, nr_tables = DIV_ROUND_UP(nr_files, IORING_MAX_FILES_TABLE); - - table->files = kcalloc(nr_tables, sizeof(*table->files), GFP_KERNEL); - if (!table->files) - return false; - - for (i = 0; i < nr_tables; i++) { - unsigned int this_files = min(nr_files, IORING_MAX_FILES_TABLE); - - table->files[i] = kcalloc(this_files, sizeof(*table->files[i]), - GFP_KERNEL); - if (!table->files[i]) - break; - nr_files -= this_files; - } - - if (i == nr_tables) - return true; - - io_free_file_tables(table, nr_tables * IORING_MAX_FILES_TABLE); - return false; -} - static void io_rsrc_file_put(struct io_ring_ctx *ctx, struct io_rsrc_put *prsrc) { struct file *file = prsrc->file; @@ -7545,14 +7632,13 @@ static void __io_rsrc_put_work(struct io_rsrc_node *ref_node) if (prsrc->tag) { bool lock_ring = ctx->flags & IORING_SETUP_IOPOLL; - unsigned long flags; io_ring_submit_lock(ctx, lock_ring); - spin_lock_irqsave(&ctx->completion_lock, flags); + spin_lock_irq(&ctx->completion_lock); io_cqring_fill_event(ctx, prsrc->tag, 0, 0); ctx->cq_extra++; io_commit_cqring(ctx); - spin_unlock_irqrestore(&ctx->completion_lock, flags); + spin_unlock_irq(&ctx->completion_lock); io_cqring_ev_posted(ctx); io_ring_submit_unlock(ctx, lock_ring); } @@ -7634,7 +7720,6 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, struct file *file; int fd, ret; unsigned i; - struct io_rsrc_data *file_data; if (ctx->file_data) return -EBUSY; @@ -7645,27 +7730,24 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, ret = io_rsrc_node_switch_start(ctx); if (ret) return ret; + ret = io_rsrc_data_alloc(ctx, io_rsrc_file_put, tags, nr_args, + &ctx->file_data); + if (ret) + return ret; - file_data = io_rsrc_data_alloc(ctx, io_rsrc_file_put, nr_args); - if (!file_data) - return -ENOMEM; - ctx->file_data = file_data; ret = -ENOMEM; if (!io_alloc_file_tables(&ctx->file_table, nr_args)) goto out_free; for (i = 0; i < nr_args; i++, ctx->nr_user_files++) { - u64 tag = 0; - - if ((tags && copy_from_user(&tag, &tags[i], sizeof(tag))) || - copy_from_user(&fd, &fds[i], sizeof(fd))) { + if (copy_from_user(&fd, &fds[i], sizeof(fd))) { ret = -EFAULT; goto out_fput; } /* allow sparse sets */ if (fd == -1) { ret = -EINVAL; - if (unlikely(tag)) + if (unlikely(*io_get_tag_slot(ctx->file_data, i))) goto out_fput; continue; } @@ -7686,7 +7768,6 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, fput(file); goto out_fput; } - ctx->file_data->tags[i] = tag; io_fixed_file_set(io_fixed_file_slot(&ctx->file_table, i), file); } @@ -7764,7 +7845,7 @@ static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, if (!prsrc) return -ENOMEM; - prsrc->tag = data->tags[idx]; + prsrc->tag = *io_get_tag_slot(data, idx); prsrc->rsrc = rsrc; list_add(&prsrc->list, &node->rsrc_list); return 0; @@ -7834,7 +7915,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - data->tags[up->offset + done] = tag; + *io_get_tag_slot(data, up->offset + done) = tag; io_fixed_file_set(file_slot, file); err = io_sqe_file_register(ctx, file, i); if (err) { @@ -7892,7 +7973,7 @@ static int io_uring_alloc_task_context(struct task_struct *task, struct io_uring_task *tctx; int ret; - tctx = kmalloc(sizeof(*tctx), GFP_KERNEL); + tctx = kzalloc(sizeof(*tctx), GFP_KERNEL); if (unlikely(!tctx)) return -ENOMEM; @@ -7912,13 +7993,11 @@ static int io_uring_alloc_task_context(struct task_struct *task, xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); - tctx->last = NULL; atomic_set(&tctx->in_idle, 0); atomic_set(&tctx->inflight_tracked, 0); task->io_uring = tctx; spin_lock_init(&tctx->task_lock); INIT_WQ_LIST(&tctx->task_list); - tctx->task_state = 0; init_task_work(&tctx->task_work, tctx_task_work); return 0; } @@ -7929,6 +8008,7 @@ void __io_uring_free(struct task_struct *tsk) WARN_ON_ONCE(!xa_empty(&tctx->xa)); WARN_ON_ONCE(tctx->io_wq); + WARN_ON_ONCE(tctx->cached_refs); percpu_counter_destroy(&tctx->inflight); kfree(tctx); @@ -8305,6 +8385,8 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, struct iovec *iov, for (i = 0; i < nr_pages; i++) { struct vm_area_struct *vma = vmas[i]; + if (vma_is_shmem(vma)) + continue; if (vma->vm_file && !is_file_hugepages(vma->vm_file)) { ret = -EOPNOTSUPP; @@ -8402,9 +8484,9 @@ static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, ret = io_rsrc_node_switch_start(ctx); if (ret) return ret; - data = io_rsrc_data_alloc(ctx, io_rsrc_buf_put, nr_args); - if (!data) - return -ENOMEM; + ret = io_rsrc_data_alloc(ctx, io_rsrc_buf_put, tags, nr_args, &data); + if (ret) + return ret; ret = io_buffers_map_alloc(ctx, nr_args); if (ret) { io_rsrc_data_free(data); @@ -8412,19 +8494,13 @@ static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, } for (i = 0; i < nr_args; i++, ctx->nr_user_bufs++) { - u64 tag = 0; - - if (tags && copy_from_user(&tag, &tags[i], sizeof(tag))) { - ret = -EFAULT; - break; - } ret = io_copy_iov(ctx, &iov, arg, i); if (ret) break; ret = io_buffer_validate(&iov); if (ret) break; - if (!iov.iov_base && tag) { + if (!iov.iov_base && *io_get_tag_slot(data, i)) { ret = -EINVAL; break; } @@ -8433,7 +8509,6 @@ static int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg, &last_hpage); if (ret) break; - data->tags[i] = tag; } WARN_ON_ONCE(ctx->buf_data); @@ -8498,7 +8573,7 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, } ctx->user_bufs[i] = imu; - ctx->buf_data->tags[offset] = tag; + *io_get_tag_slot(ctx->buf_data, offset) = tag; } if (needs_switch) @@ -8520,6 +8595,7 @@ static int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg) ctx->cq_ev_fd = eventfd_ctx_fdget(fd); if (IS_ERR(ctx->cq_ev_fd)) { int ret = PTR_ERR(ctx->cq_ev_fd); + ctx->cq_ev_fd = NULL; return ret; } @@ -8643,7 +8719,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) struct io_ring_ctx *ctx = file->private_data; __poll_t mask = 0; - poll_wait(file, &ctx->cq_wait, wait); + poll_wait(file, &ctx->poll_wait, wait); /* * synchronizes with barrier from wq_has_sleeper call in * io_commit_cqring @@ -8665,7 +8741,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) * Users may get EPOLLIN meanwhile seeing nothing in cqring, this * pushs them to do the flush. */ - if (io_cqring_events(ctx) || test_bit(0, &ctx->cq_check_overflow)) + if (io_cqring_events(ctx) || test_bit(0, &ctx->check_cq_overflow)) mask |= EPOLLIN | EPOLLRDNORM; return mask; @@ -8713,7 +8789,7 @@ static void io_tctx_exit_cb(struct callback_head *cb) * node. It'll be removed by the end of cancellation, just ignore it. */ if (!atomic_read(&tctx->in_idle)) - io_uring_del_task_file((unsigned long)work->ctx); + io_uring_del_tctx_node((unsigned long)work->ctx); complete(&work->completion); } @@ -8739,7 +8815,7 @@ static void io_ring_exit_work(struct work_struct *work) * as nobody else will be looking for them. */ do { - io_uring_try_cancel_requests(ctx, NULL, NULL); + io_uring_try_cancel_requests(ctx, NULL, true); if (ctx->sq_data) { struct io_sq_data *sqd = ctx->sq_data; struct task_struct *tsk; @@ -8790,14 +8866,14 @@ static void io_ring_exit_work(struct work_struct *work) /* Returns true if we found and killed one or more timeouts */ static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, - struct files_struct *files) + bool cancel_all) { struct io_kiocb *req, *tmp; int canceled = 0; spin_lock_irq(&ctx->completion_lock); list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { - if (io_match_task(req, tsk, files)) { + if (io_match_task(req, tsk, cancel_all)) { io_kill_timeout(req, -ECANCELED); canceled++; } @@ -8823,8 +8899,8 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) io_unregister_personality(ctx, index); mutex_unlock(&ctx->uring_lock); - io_kill_timeouts(ctx, NULL, NULL); - io_poll_remove_all(ctx, NULL, NULL); + io_kill_timeouts(ctx, NULL, true); + io_poll_remove_all(ctx, NULL, true); /* if we failed setting up the ctx, we might not have any rings */ io_iopoll_try_reap_events(ctx); @@ -8850,7 +8926,7 @@ static int io_uring_release(struct inode *inode, struct file *file) struct io_task_cancel { struct task_struct *task; - struct files_struct *files; + bool all; }; static bool io_cancel_task_cb(struct io_wq_work *work, void *data) @@ -8859,30 +8935,29 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data) struct io_task_cancel *cancel = data; bool ret; - if (cancel->files && (req->flags & REQ_F_LINK_TIMEOUT)) { + if (!cancel->all && (req->flags & REQ_F_LINK_TIMEOUT)) { unsigned long flags; struct io_ring_ctx *ctx = req->ctx; /* protect against races with linked timeouts */ spin_lock_irqsave(&ctx->completion_lock, flags); - ret = io_match_task(req, cancel->task, cancel->files); + ret = io_match_task(req, cancel->task, cancel->all); spin_unlock_irqrestore(&ctx->completion_lock, flags); } else { - ret = io_match_task(req, cancel->task, cancel->files); + ret = io_match_task(req, cancel->task, cancel->all); } return ret; } static bool io_cancel_defer_files(struct io_ring_ctx *ctx, - struct task_struct *task, - struct files_struct *files) + struct task_struct *task, bool cancel_all) { struct io_defer_entry *de; LIST_HEAD(list); spin_lock_irq(&ctx->completion_lock); list_for_each_entry_reverse(de, &ctx->defer_list, list) { - if (io_match_task(de->req, task, files)) { + if (io_match_task(de->req, task, cancel_all)) { list_cut_position(&list, &ctx->defer_list, &de->list); break; } @@ -8926,9 +9001,9 @@ static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, struct task_struct *task, - struct files_struct *files) + bool cancel_all) { - struct io_task_cancel cancel = { .task = task, .files = files, }; + struct io_task_cancel cancel = { .task = task, .all = cancel_all, }; struct io_uring_task *tctx = task ? task->io_uring : NULL; while (1) { @@ -8948,7 +9023,7 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, } /* SQPOLL thread does its own polling */ - if ((!(ctx->flags & IORING_SETUP_SQPOLL) && !files) || + if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) || (ctx->sq_data && ctx->sq_data->thread == current)) { while (!list_empty_careful(&ctx->iopoll_list)) { io_iopoll_try_reap_events(ctx); @@ -8956,10 +9031,11 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, } } - ret |= io_cancel_defer_files(ctx, task, files); - ret |= io_poll_remove_all(ctx, task, files); - ret |= io_kill_timeouts(ctx, task, files); - ret |= io_run_task_work(); + ret |= io_cancel_defer_files(ctx, task, cancel_all); + ret |= io_poll_remove_all(ctx, task, cancel_all); + ret |= io_kill_timeouts(ctx, task, cancel_all); + if (task) + ret |= io_run_task_work(); ret |= io_run_ctx_fallback(ctx); if (!ret) break; @@ -8967,7 +9043,7 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, } } -static int __io_uring_add_task_file(struct io_ring_ctx *ctx) +static int __io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_node *node; @@ -9004,19 +9080,19 @@ static int __io_uring_add_task_file(struct io_ring_ctx *ctx) /* * Note that this task has used io_uring. We use it for cancelation purposes. */ -static inline int io_uring_add_task_file(struct io_ring_ctx *ctx) +static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; if (likely(tctx && tctx->last == ctx)) return 0; - return __io_uring_add_task_file(ctx); + return __io_uring_add_tctx_node(ctx); } /* * Remove this io_uring_file -> task mapping. */ -static void io_uring_del_task_file(unsigned long index) +static void io_uring_del_tctx_node(unsigned long index) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_node *node; @@ -9046,7 +9122,7 @@ static void io_uring_clean_tctx(struct io_uring_task *tctx) unsigned long index; xa_for_each(&tctx->xa, index, node) - io_uring_del_task_file(index); + io_uring_del_tctx_node(index); if (wq) { /* * Must be after io_uring_del_task_file() (removes nodes under @@ -9064,44 +9140,58 @@ static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) return percpu_counter_sum(&tctx->inflight); } -static void io_uring_try_cancel(struct files_struct *files) +static void io_uring_drop_tctx_refs(struct task_struct *task) { - struct io_uring_task *tctx = current->io_uring; - struct io_tctx_node *node; - unsigned long index; + struct io_uring_task *tctx = task->io_uring; + unsigned int refs = tctx->cached_refs; - xa_for_each(&tctx->xa, index, node) { - struct io_ring_ctx *ctx = node->ctx; - - /* sqpoll task will cancel all its requests */ - if (!ctx->sq_data) - io_uring_try_cancel_requests(ctx, current, files); - } + tctx->cached_refs = 0; + percpu_counter_sub(&tctx->inflight, refs); + put_task_struct_many(task, refs); } -/* should only be called by SQPOLL task */ -static void io_uring_cancel_sqpoll(struct io_sq_data *sqd) +/* + * Find any io_uring ctx that this task has registered or done IO on, and cancel + * requests. @sqd should be not-null IIF it's an SQPOLL thread cancellation. + */ +static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) { struct io_uring_task *tctx = current->io_uring; struct io_ring_ctx *ctx; s64 inflight; DEFINE_WAIT(wait); + WARN_ON_ONCE(sqd && sqd->thread != current); + if (!current->io_uring) return; if (tctx->io_wq) io_wq_exit_start(tctx->io_wq); - WARN_ON_ONCE(!sqd || sqd->thread != current); - + io_uring_drop_tctx_refs(current); atomic_inc(&tctx->in_idle); do { /* read completions before cancelations */ - inflight = tctx_inflight(tctx, false); + inflight = tctx_inflight(tctx, !cancel_all); if (!inflight) break; - list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) - io_uring_try_cancel_requests(ctx, current, NULL); + + if (!sqd) { + struct io_tctx_node *node; + unsigned long index; + + xa_for_each(&tctx->xa, index, node) { + /* sqpoll task will cancel all its requests */ + if (node->ctx->sq_data) + continue; + io_uring_try_cancel_requests(node->ctx, current, + cancel_all); + } + } else { + list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) + io_uring_try_cancel_requests(ctx, current, + cancel_all); + } prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); /* @@ -9109,54 +9199,24 @@ static void io_uring_cancel_sqpoll(struct io_sq_data *sqd) * avoids a race where a completion comes in before we did * prepare_to_wait(). */ - if (inflight == tctx_inflight(tctx, false)) - schedule(); - finish_wait(&tctx->wait, &wait); - } while (1); - atomic_dec(&tctx->in_idle); -} - -/* - * Find any io_uring fd that this task has registered or done IO on, and cancel - * requests. - */ -void __io_uring_cancel(struct files_struct *files) -{ - struct io_uring_task *tctx = current->io_uring; - DEFINE_WAIT(wait); - s64 inflight; - - if (tctx->io_wq) - io_wq_exit_start(tctx->io_wq); - - /* make sure overflow events are dropped */ - atomic_inc(&tctx->in_idle); - do { - /* read completions before cancelations */ - inflight = tctx_inflight(tctx, !!files); - if (!inflight) - break; - io_uring_try_cancel(files); - prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); - - /* - * If we've seen completions, retry without waiting. This - * avoids a race where a completion comes in before we did - * prepare_to_wait(). - */ - if (inflight == tctx_inflight(tctx, !!files)) + if (inflight == tctx_inflight(tctx, !cancel_all)) schedule(); finish_wait(&tctx->wait, &wait); } while (1); atomic_dec(&tctx->in_idle); io_uring_clean_tctx(tctx); - if (!files) { + if (cancel_all) { /* for exec all current's requests should be gone, kill tctx */ __io_uring_free(current); } } +void __io_uring_cancel(struct files_struct *files) +{ + io_uring_cancel_generic(!files, NULL); +} + static void *io_uring_validate_mmap_request(struct file *file, loff_t pgoff, size_t sz) { @@ -9317,9 +9377,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, io_cqring_overflow_flush(ctx, false); ret = -EOWNERDEAD; - if (unlikely(ctx->sq_data->thread == NULL)) { + if (unlikely(ctx->sq_data->thread == NULL)) goto out; - } if (flags & IORING_ENTER_SQ_WAKEUP) wake_up(&ctx->sq_data->wait); if (flags & IORING_ENTER_SQ_WAIT) { @@ -9329,7 +9388,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, } submitted = to_submit; } else if (to_submit) { - ret = io_uring_add_task_file(ctx); + ret = io_uring_add_tctx_node(ctx); if (unlikely(ret)) goto out; mutex_lock(&ctx->uring_lock); @@ -9513,8 +9572,6 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx, rings->cq_ring_mask = p->cq_entries - 1; rings->sq_ring_entries = p->sq_entries; rings->cq_ring_entries = p->cq_entries; - ctx->sq_mask = rings->sq_ring_mask; - ctx->cq_mask = rings->cq_ring_mask; size = array_size(sizeof(struct io_uring_sqe), p->sq_entries); if (size == SIZE_MAX) { @@ -9541,7 +9598,7 @@ static int io_uring_install_fd(struct io_ring_ctx *ctx, struct file *file) if (fd < 0) return fd; - ret = io_uring_add_task_file(ctx); + ret = io_uring_add_tctx_node(ctx); if (ret) { put_unused_fd(fd); return ret; @@ -9956,6 +10013,43 @@ static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; } +static int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg, + unsigned len) +{ + struct io_uring_task *tctx = current->io_uring; + cpumask_var_t new_mask; + int ret; + + if (!tctx || !tctx->io_wq) + return -EINVAL; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_clear(new_mask); + if (len > cpumask_size()) + len = cpumask_size(); + + if (copy_from_user(new_mask, arg, len)) { + free_cpumask_var(new_mask); + return -EFAULT; + } + + ret = io_wq_cpu_affinity(tctx->io_wq, new_mask); + free_cpumask_var(new_mask); + return ret; +} + +static int io_unregister_iowq_aff(struct io_ring_ctx *ctx) +{ + struct io_uring_task *tctx = current->io_uring; + + if (!tctx || !tctx->io_wq) + return -EINVAL; + + return io_wq_cpu_affinity(tctx->io_wq, NULL); +} + static bool io_register_op_must_quiesce(int op) { switch (op) { @@ -9971,6 +10065,8 @@ static bool io_register_op_must_quiesce(int op) case IORING_REGISTER_FILES_UPDATE2: case IORING_REGISTER_BUFFERS2: case IORING_REGISTER_BUFFERS_UPDATE: + case IORING_REGISTER_IOWQ_AFF: + case IORING_UNREGISTER_IOWQ_AFF: return false; default: return true; @@ -10110,6 +10206,18 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, ret = io_register_rsrc_update(ctx, arg, nr_args, IORING_RSRC_BUFFER); break; + case IORING_REGISTER_IOWQ_AFF: + ret = -EINVAL; + if (!arg || !nr_args) + break; + ret = io_register_iowq_aff(ctx, arg, nr_args); + break; + case IORING_UNREGISTER_IOWQ_AFF: + ret = -EINVAL; + if (arg || nr_args) + break; + ret = io_unregister_iowq_aff(ctx); + break; default: ret = -EINVAL; break; @@ -10188,6 +10296,7 @@ static int __init io_uring_init(void) BUILD_BUG_SQE_ELEM(28, __u32, splice_flags); BUILD_BUG_SQE_ELEM(32, __u64, user_data); BUILD_BUG_SQE_ELEM(40, __u16, buf_index); + BUILD_BUG_SQE_ELEM(40, __u16, buf_group); BUILD_BUG_SQE_ELEM(42, __u16, personality); BUILD_BUG_SQE_ELEM(44, __s32, splice_fd_in); @@ -10200,6 +10309,7 @@ static int __init io_uring_init(void) BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); BUILD_BUG_ON(__REQ_F_LAST_BIT >= 8 * sizeof(int)); + req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); return 0; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 9023717c5188..0065781935c7 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -640,31 +640,6 @@ out_no_page: return status; } -int -iomap_set_page_dirty(struct page *page) -{ - struct address_space *mapping = page_mapping(page); - int newly_dirty; - - if (unlikely(!mapping)) - return !TestSetPageDirty(page); - - /* - * Lock out page's memcg migration to keep PageDirty - * synchronized with per-memcg dirty page counters. - */ - lock_page_memcg(page); - newly_dirty = !TestSetPageDirty(page); - if (newly_dirty) - __set_page_dirty(page, mapping, 0); - unlock_page_memcg(page); - - if (newly_dirty) - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - return newly_dirty; -} -EXPORT_SYMBOL_GPL(iomap_set_page_dirty); - static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len, size_t copied, struct page *page) { @@ -684,7 +659,7 @@ static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len, if (unlikely(copied < len && !PageUptodate(page))) return 0; iomap_set_range_uptodate(page, offset_in_page(pos), len); - iomap_set_page_dirty(page); + __set_page_dirty_nobuffers(page); return copied; } diff --git a/fs/isofs/dir.c b/fs/isofs/dir.c index b9e6a7ec78be..eb2f8273e6f1 100644 --- a/fs/isofs/dir.c +++ b/fs/isofs/dir.c @@ -235,8 +235,6 @@ static int do_isofs_readdir(struct inode *inode, struct file *file, break; } ctx->pos += de_len; - - continue; } if (bh) brelse(bh); diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 63b526d44886..51d1eb2ffeb9 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -80,23 +80,15 @@ static inline void __buffer_relink_io(struct journal_head *jh) } /* - * Try to release a checkpointed buffer from its transaction. - * Returns 1 if we released it and 2 if we also released the - * whole transaction. + * Check a checkpoint buffer could be release or not. * * Requires j_list_lock */ -static int __try_to_free_cp_buf(struct journal_head *jh) +static inline bool __cp_buffer_busy(struct journal_head *jh) { - int ret = 0; struct buffer_head *bh = jh2bh(jh); - if (jh->b_transaction == NULL && !buffer_locked(bh) && - !buffer_dirty(bh) && !buffer_write_io_error(bh)) { - JBUFFER_TRACE(jh, "remove from checkpoint list"); - ret = __jbd2_journal_remove_checkpoint(jh) + 1; - } - return ret; + return (jh->b_transaction || buffer_locked(bh) || buffer_dirty(bh)); } /* @@ -228,7 +220,6 @@ int jbd2_log_do_checkpoint(journal_t *journal) * OK, we need to start writing disk blocks. Take one transaction * and write it. */ - result = 0; spin_lock(&journal->j_list_lock); if (!journal->j_checkpoint_transactions) goto out; @@ -295,8 +286,6 @@ restart: goto restart; } if (!buffer_dirty(bh)) { - if (unlikely(buffer_write_io_error(bh)) && !result) - result = -EIO; BUFFER_TRACE(bh, "remove from checkpoint"); if (__jbd2_journal_remove_checkpoint(jh)) /* The transaction was released; we're done */ @@ -356,8 +345,6 @@ restart2: spin_lock(&journal->j_list_lock); goto restart2; } - if (unlikely(buffer_write_io_error(bh)) && !result) - result = -EIO; /* * Now in whatever state the buffer currently is, we @@ -369,10 +356,7 @@ restart2: } out: spin_unlock(&journal->j_list_lock); - if (result < 0) - jbd2_journal_abort(journal, result); - else - result = jbd2_cleanup_journal_tail(journal); + result = jbd2_cleanup_journal_tail(journal); return (result < 0) ? result : 0; } @@ -437,7 +421,6 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) { struct journal_head *last_jh; struct journal_head *next_jh = jh; - int ret; if (!jh) return 0; @@ -446,13 +429,11 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) do { jh = next_jh; next_jh = jh->b_cpnext; - if (!destroy) - ret = __try_to_free_cp_buf(jh); - else - ret = __jbd2_journal_remove_checkpoint(jh) + 1; - if (!ret) + + if (!destroy && __cp_buffer_busy(jh)) return 0; - if (ret == 2) + + if (__jbd2_journal_remove_checkpoint(jh)) return 1; /* * This function only frees up some memory @@ -467,6 +448,137 @@ static int journal_clean_one_cp_list(struct journal_head *jh, bool destroy) return 0; } +/* + * journal_shrink_one_cp_list + * + * Find 'nr_to_scan' written-back checkpoint buffers in the given list + * and try to release them. If the whole transaction is released, set + * the 'released' parameter. Return the number of released checkpointed + * buffers. + * + * Called with j_list_lock held. + */ +static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, + unsigned long *nr_to_scan, + bool *released) +{ + struct journal_head *last_jh; + struct journal_head *next_jh = jh; + unsigned long nr_freed = 0; + int ret; + + if (!jh || *nr_to_scan == 0) + return 0; + + last_jh = jh->b_cpprev; + do { + jh = next_jh; + next_jh = jh->b_cpnext; + + (*nr_to_scan)--; + if (__cp_buffer_busy(jh)) + continue; + + nr_freed++; + ret = __jbd2_journal_remove_checkpoint(jh); + if (ret) { + *released = true; + break; + } + + if (need_resched()) + break; + } while (jh != last_jh && *nr_to_scan); + + return nr_freed; +} + +/* + * jbd2_journal_shrink_checkpoint_list + * + * Find 'nr_to_scan' written-back checkpoint buffers in the journal + * and try to release them. Return the number of released checkpointed + * buffers. + * + * Called with j_list_lock held. + */ +unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, + unsigned long *nr_to_scan) +{ + transaction_t *transaction, *last_transaction, *next_transaction; + bool released; + tid_t first_tid = 0, last_tid = 0, next_tid = 0; + tid_t tid = 0; + unsigned long nr_freed = 0; + unsigned long nr_scanned = *nr_to_scan; + +again: + spin_lock(&journal->j_list_lock); + if (!journal->j_checkpoint_transactions) { + spin_unlock(&journal->j_list_lock); + goto out; + } + + /* + * Get next shrink transaction, resume previous scan or start + * over again. If some others do checkpoint and drop transaction + * from the checkpoint list, we ignore saved j_shrink_transaction + * and start over unconditionally. + */ + if (journal->j_shrink_transaction) + transaction = journal->j_shrink_transaction; + else + transaction = journal->j_checkpoint_transactions; + + if (!first_tid) + first_tid = transaction->t_tid; + last_transaction = journal->j_checkpoint_transactions->t_cpprev; + next_transaction = transaction; + last_tid = last_transaction->t_tid; + do { + transaction = next_transaction; + next_transaction = transaction->t_cpnext; + tid = transaction->t_tid; + released = false; + + nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_list, + nr_to_scan, &released); + if (*nr_to_scan == 0) + break; + if (need_resched() || spin_needbreak(&journal->j_list_lock)) + break; + if (released) + continue; + + nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_io_list, + nr_to_scan, &released); + if (*nr_to_scan == 0) + break; + if (need_resched() || spin_needbreak(&journal->j_list_lock)) + break; + } while (transaction != last_transaction); + + if (transaction != last_transaction) { + journal->j_shrink_transaction = next_transaction; + next_tid = next_transaction->t_tid; + } else { + journal->j_shrink_transaction = NULL; + next_tid = 0; + } + + spin_unlock(&journal->j_list_lock); + cond_resched(); + + if (*nr_to_scan && next_tid) + goto again; +out: + nr_scanned -= *nr_to_scan; + trace_jbd2_shrink_checkpoint_list(journal, first_tid, tid, last_tid, + nr_freed, nr_scanned, next_tid); + + return nr_freed; +} + /* * journal_clean_checkpoint_list * @@ -564,24 +676,37 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) struct transaction_chp_stats_s *stats; transaction_t *transaction; journal_t *journal; - int ret = 0; + struct buffer_head *bh = jh2bh(jh); JBUFFER_TRACE(jh, "entry"); - if ((transaction = jh->b_cp_transaction) == NULL) { + transaction = jh->b_cp_transaction; + if (!transaction) { JBUFFER_TRACE(jh, "not on transaction"); - goto out; + return 0; } journal = transaction->t_journal; JBUFFER_TRACE(jh, "removing from transaction"); + + /* + * If we have failed to write the buffer out to disk, the filesystem + * may become inconsistent. We cannot abort the journal here since + * we hold j_list_lock and we have to be careful about races with + * jbd2_journal_destroy(). So mark the writeback IO error in the + * journal here and we abort the journal later from a better context. + */ + if (buffer_write_io_error(bh)) + set_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags); + __buffer_unlink(jh); jh->b_cp_transaction = NULL; + percpu_counter_dec(&journal->j_jh_shrink_count); jbd2_journal_put_journal_head(jh); - if (transaction->t_checkpoint_list != NULL || - transaction->t_checkpoint_io_list != NULL) - goto out; + /* Is this transaction empty? */ + if (transaction->t_checkpoint_list || transaction->t_checkpoint_io_list) + return 0; /* * There is one special case to worry about: if we have just pulled the @@ -593,10 +718,12 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) * See the comment at the end of jbd2_journal_commit_transaction(). */ if (transaction->t_state != T_FINISHED) - goto out; + return 0; - /* OK, that was the last buffer for the transaction: we can now - safely remove this transaction from the log */ + /* + * OK, that was the last buffer for the transaction, we can now + * safely remove this transaction from the log. + */ stats = &transaction->t_chp_stats; if (stats->cs_chp_time) stats->cs_chp_time = jbd2_time_diff(stats->cs_chp_time, @@ -606,9 +733,7 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) __jbd2_journal_drop_transaction(journal, transaction); jbd2_journal_free_transaction(transaction); - ret = 1; -out: - return ret; + return 1; } /* @@ -639,6 +764,7 @@ void __jbd2_journal_insert_checkpoint(struct journal_head *jh, jh->b_cpnext->b_cpprev = jh; } transaction->t_checkpoint_list = jh; + percpu_counter_inc(&transaction->t_journal->j_jh_shrink_count); } /* @@ -654,6 +780,8 @@ void __jbd2_journal_insert_checkpoint(struct journal_head *jh, void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transaction) { assert_spin_locked(&journal->j_list_lock); + + journal->j_shrink_transaction = NULL; if (transaction->t_cpnext) { transaction->t_cpnext->t_cpprev = transaction->t_cpprev; transaction->t_cpprev->t_cpnext = transaction->t_cpnext; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 2dc944442802..152880c298ca 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -934,10 +934,6 @@ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks) } EXPORT_SYMBOL(jbd2_fc_wait_bufs); -/* - * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf - * for completion. - */ int jbd2_fc_release_bufs(journal_t *journal) { struct buffer_head *bh; @@ -945,10 +941,6 @@ int jbd2_fc_release_bufs(journal_t *journal) j_fc_off = journal->j_fc_off; - /* - * Wait in reverse order to minimize chances of us being woken up before - * all IOs have completed - */ for (i = j_fc_off - 1; i >= 0; i--) { bh = journal->j_fc_wbuf[i]; if (!bh) @@ -1618,6 +1610,10 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, if (is_journal_aborted(journal)) return -EIO; + if (test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) { + jbd2_journal_abort(journal, -EIO); + return -EIO; + } BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", @@ -1686,6 +1682,110 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op) write_unlock(&journal->j_state_lock); } +/** + * __jbd2_journal_erase() - Discard or zeroout journal blocks (excluding superblock) + * @journal: The journal to erase. + * @flags: A discard/zeroout request is sent for each physically contigous + * region of the journal. Either JBD2_JOURNAL_FLUSH_DISCARD or + * JBD2_JOURNAL_FLUSH_ZEROOUT must be set to determine which operation + * to perform. + * + * Note: JBD2_JOURNAL_FLUSH_ZEROOUT attempts to use hardware offload. Zeroes + * will be explicitly written if no hardware offload is available, see + * blkdev_issue_zeroout for more details. + */ +static int __jbd2_journal_erase(journal_t *journal, unsigned int flags) +{ + int err = 0; + unsigned long block, log_offset; /* logical */ + unsigned long long phys_block, block_start, block_stop; /* physical */ + loff_t byte_start, byte_stop, byte_count; + struct request_queue *q = bdev_get_queue(journal->j_dev); + + /* flags must be set to either discard or zeroout */ + if ((flags & ~JBD2_JOURNAL_FLUSH_VALID) || !flags || + ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && + (flags & JBD2_JOURNAL_FLUSH_ZEROOUT))) + return -EINVAL; + + if (!q) + return -ENXIO; + + if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !blk_queue_discard(q)) + return -EOPNOTSUPP; + + /* + * lookup block mapping and issue discard/zeroout for each + * contiguous region + */ + log_offset = be32_to_cpu(journal->j_superblock->s_first); + block_start = ~0ULL; + for (block = log_offset; block < journal->j_total_len; block++) { + err = jbd2_journal_bmap(journal, block, &phys_block); + if (err) { + pr_err("JBD2: bad block at offset %lu", block); + return err; + } + + if (block_start == ~0ULL) { + block_start = phys_block; + block_stop = block_start - 1; + } + + /* + * last block not contiguous with current block, + * process last contiguous region and return to this block on + * next loop + */ + if (phys_block != block_stop + 1) { + block--; + } else { + block_stop++; + /* + * if this isn't the last block of journal, + * no need to process now because next block may also + * be part of this contiguous region + */ + if (block != journal->j_total_len - 1) + continue; + } + + /* + * end of contiguous region or this is last block of journal, + * take care of the region + */ + byte_start = block_start * journal->j_blocksize; + byte_stop = block_stop * journal->j_blocksize; + byte_count = (block_stop - block_start + 1) * + journal->j_blocksize; + + truncate_inode_pages_range(journal->j_dev->bd_inode->i_mapping, + byte_start, byte_stop); + + if (flags & JBD2_JOURNAL_FLUSH_DISCARD) { + err = blkdev_issue_discard(journal->j_dev, + byte_start >> SECTOR_SHIFT, + byte_count >> SECTOR_SHIFT, + GFP_NOFS, 0); + } else if (flags & JBD2_JOURNAL_FLUSH_ZEROOUT) { + err = blkdev_issue_zeroout(journal->j_dev, + byte_start >> SECTOR_SHIFT, + byte_count >> SECTOR_SHIFT, + GFP_NOFS, 0); + } + + if (unlikely(err != 0)) { + pr_err("JBD2: (error %d) unable to wipe journal at physical blocks %llu - %llu", + err, block_start, block_stop); + return err; + } + + /* reset start and stop after processing a region */ + block_start = ~0ULL; + } + + return blkdev_issue_flush(journal->j_dev); +} /** * jbd2_journal_update_sb_errno() - Update error in the journal. @@ -1950,6 +2050,93 @@ recovery_error: return -EIO; } +/** + * jbd2_journal_shrink_scan() + * + * Scan the checkpointed buffer on the checkpoint list and release the + * journal_head. + */ +static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) +{ + journal_t *journal = container_of(shrink, journal_t, j_shrinker); + unsigned long nr_to_scan = sc->nr_to_scan; + unsigned long nr_shrunk; + unsigned long count; + + count = percpu_counter_read_positive(&journal->j_jh_shrink_count); + trace_jbd2_shrink_scan_enter(journal, sc->nr_to_scan, count); + + nr_shrunk = jbd2_journal_shrink_checkpoint_list(journal, &nr_to_scan); + + count = percpu_counter_read_positive(&journal->j_jh_shrink_count); + trace_jbd2_shrink_scan_exit(journal, nr_to_scan, nr_shrunk, count); + + return nr_shrunk; +} + +/** + * jbd2_journal_shrink_count() + * + * Count the number of checkpoint buffers on the checkpoint list. + */ +static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) +{ + journal_t *journal = container_of(shrink, journal_t, j_shrinker); + unsigned long count; + + count = percpu_counter_read_positive(&journal->j_jh_shrink_count); + trace_jbd2_shrink_count(journal, sc->nr_to_scan, count); + + return count; +} + +/** + * jbd2_journal_register_shrinker() + * @journal: Journal to act on. + * + * Init a percpu counter to record the checkpointed buffers on the checkpoint + * list and register a shrinker to release their journal_head. + */ +int jbd2_journal_register_shrinker(journal_t *journal) +{ + int err; + + journal->j_shrink_transaction = NULL; + + err = percpu_counter_init(&journal->j_jh_shrink_count, 0, GFP_KERNEL); + if (err) + return err; + + journal->j_shrinker.scan_objects = jbd2_journal_shrink_scan; + journal->j_shrinker.count_objects = jbd2_journal_shrink_count; + journal->j_shrinker.seeks = DEFAULT_SEEKS; + journal->j_shrinker.batch = journal->j_max_transaction_buffers; + + err = register_shrinker(&journal->j_shrinker); + if (err) { + percpu_counter_destroy(&journal->j_jh_shrink_count); + return err; + } + + return 0; +} +EXPORT_SYMBOL(jbd2_journal_register_shrinker); + +/** + * jbd2_journal_unregister_shrinker() + * @journal: Journal to act on. + * + * Unregister the checkpointed buffer shrinker and destroy the percpu counter. + */ +void jbd2_journal_unregister_shrinker(journal_t *journal) +{ + percpu_counter_destroy(&journal->j_jh_shrink_count); + unregister_shrinker(&journal->j_shrinker); +} +EXPORT_SYMBOL(jbd2_journal_unregister_shrinker); + /** * jbd2_journal_destroy() - Release a journal_t structure. * @journal: Journal to act on. @@ -1995,6 +2182,16 @@ int jbd2_journal_destroy(journal_t *journal) J_ASSERT(journal->j_checkpoint_transactions == NULL); spin_unlock(&journal->j_list_lock); + /* + * OK, all checkpoint transactions have been checked, now check the + * write out io error flag and abort the journal if some buffer failed + * to write back to the original location, otherwise the filesystem + * may become inconsistent. + */ + if (!is_journal_aborted(journal) && + test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) + jbd2_journal_abort(journal, -EIO); + if (journal->j_sb_buffer) { if (!is_journal_aborted(journal)) { mutex_lock_io(&journal->j_checkpoint_mutex); @@ -2012,6 +2209,8 @@ int jbd2_journal_destroy(journal_t *journal) brelse(journal->j_sb_buffer); } + jbd2_journal_unregister_shrinker(journal); + if (journal->j_proc_entry) jbd2_stats_proc_exit(journal); iput(journal->j_inode); @@ -2246,13 +2445,18 @@ EXPORT_SYMBOL(jbd2_journal_clear_features); /** * jbd2_journal_flush() - Flush journal * @journal: Journal to act on. + * @flags: optional operation on the journal blocks after the flush (see below) * * Flush all data for a given journal to disk and empty the journal. * Filesystems can use this when remounting readonly to ensure that - * recovery does not need to happen on remount. + * recovery does not need to happen on remount. Optionally, a discard or zeroout + * can be issued on the journal blocks after flushing. + * + * flags: + * JBD2_JOURNAL_FLUSH_DISCARD: issues discards for the journal blocks + * JBD2_JOURNAL_FLUSH_ZEROOUT: issues zeroouts for the journal blocks */ - -int jbd2_journal_flush(journal_t *journal) +int jbd2_journal_flush(journal_t *journal, unsigned int flags) { int err = 0; transaction_t *transaction = NULL; @@ -2306,6 +2510,10 @@ int jbd2_journal_flush(journal_t *journal) * commits of data to the journal will restore the current * s_start value. */ jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); + + if (flags) + err = __jbd2_journal_erase(journal, flags); + mutex_unlock(&journal->j_checkpoint_mutex); write_lock(&journal->j_state_lock); J_ASSERT(!journal->j_running_transaction); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index e8fc45fd751f..8804e126805f 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2123,7 +2123,6 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page) { struct buffer_head *head; struct buffer_head *bh; - bool has_write_io_error = false; int ret = 0; J_ASSERT(PageLocked(page)); @@ -2148,26 +2147,10 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page) jbd2_journal_put_journal_head(jh); if (buffer_jbd(bh)) goto busy; - - /* - * If we free a metadata buffer which has been failed to - * write out, the jbd2 checkpoint procedure will not detect - * this failure and may lead to filesystem inconsistency - * after cleanup journal tail. - */ - if (buffer_write_io_error(bh)) { - pr_err("JBD2: Error while async write back metadata bh %llu.", - (unsigned long long)bh->b_blocknr); - has_write_io_error = true; - } } while ((bh = bh->b_this_page) != head); ret = try_to_free_buffers(page); - busy: - if (has_write_io_error) - jbd2_journal_abort(journal, -EIO); - return ret; } diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 6f65bfa9f18d..3663dd5a23bc 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -356,6 +356,7 @@ static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } const struct address_space_operations jfs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = jfs_readpage, .readahead = jfs_readahead, .writepage = jfs_writepage, diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index d73950fc3d57..26f2aa3586f9 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -17,12 +17,6 @@ #include "kernfs-internal.h" -static const struct address_space_operations kernfs_aops = { - .readpage = simple_readpage, - .write_begin = simple_write_begin, - .write_end = simple_write_end, -}; - static const struct inode_operations kernfs_iops = { .permission = kernfs_iop_permission, .setattr = kernfs_iop_setattr, @@ -203,7 +197,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode) { kernfs_get(kn); inode->i_private = kn; - inode->i_mapping->a_ops = &kernfs_aops; + inode->i_mapping->a_ops = &ram_aops; inode->i_op = &kernfs_iops; inode->i_generation = kernfs_gen(kn); diff --git a/fs/libfs.c b/fs/libfs.c index e9b29c6ffccb..51b4de3b3447 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -512,7 +512,7 @@ int simple_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, } EXPORT_SYMBOL(simple_setattr); -int simple_readpage(struct file *file, struct page *page) +static int simple_readpage(struct file *file, struct page *page) { clear_highpage(page); flush_dcache_page(page); @@ -520,7 +520,6 @@ int simple_readpage(struct file *file, struct page *page) unlock_page(page); return 0; } -EXPORT_SYMBOL(simple_readpage); int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, @@ -568,7 +567,7 @@ EXPORT_SYMBOL(simple_write_begin); * * Use *ONLY* with simple_readpage() */ -int simple_write_end(struct file *file, struct address_space *mapping, +static int simple_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { @@ -597,7 +596,17 @@ int simple_write_end(struct file *file, struct address_space *mapping, return copied; } -EXPORT_SYMBOL(simple_write_end); + +/* + * Provides ramfs-style behavior: data in the pagecache, but no writeback. + */ +const struct address_space_operations ram_aops = { + .readpage = simple_readpage, + .write_begin = simple_write_begin, + .write_end = simple_write_end, + .set_page_dirty = __set_page_dirty_no_writeback, +}; +EXPORT_SYMBOL(ram_aops); /* * the inodes created here are not hashed. If you use iunique to generate @@ -1162,22 +1171,6 @@ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync) } EXPORT_SYMBOL(noop_fsync); -int noop_set_page_dirty(struct page *page) -{ - /* - * Unlike __set_page_dirty_no_writeback that handles dirty page - * tracking in the page object, dax does all dirty tracking in - * the inode address_space in response to mkwrite faults. In the - * dax case we only need to worry about potentially dirty CPU - * caches, not dirty page cache pages to write back. - * - * This callback is defined to prevent fallback to - * __set_page_dirty_buffers() in set_page_dirty(). - */ - return 0; -} -EXPORT_SYMBOL_GPL(noop_set_page_dirty); - void noop_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { @@ -1208,19 +1201,10 @@ void kfree_link(void *p) } EXPORT_SYMBOL(kfree_link); -/* - * nop .set_page_dirty method so that people can use .page_mkwrite on - * anon inodes. - */ -static int anon_set_page_dirty(struct page *page) -{ - return 0; -}; - struct inode *alloc_anon_inode(struct super_block *s) { static const struct address_space_operations anon_aops = { - .set_page_dirty = anon_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, }; struct inode *inode = new_inode_pseudo(s); diff --git a/fs/minix/inode.c b/fs/minix/inode.c index a532a99bbe81..a71f1cf894b9 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -442,6 +442,7 @@ static sector_t minix_bmap(struct address_space *mapping, sector_t block) } static const struct address_space_operations minix_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = minix_readpage, .writepage = minix_writepage, .write_begin = minix_write_begin, diff --git a/fs/namespace.c b/fs/namespace.c index c3f1a78ba369..ab4174a3c802 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -3464,9 +3464,10 @@ out_type: return ret; } -#define FSMOUNT_VALID_FLAGS \ - (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \ - MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME) +#define FSMOUNT_VALID_FLAGS \ + (MOUNT_ATTR_RDONLY | MOUNT_ATTR_NOSUID | MOUNT_ATTR_NODEV | \ + MOUNT_ATTR_NOEXEC | MOUNT_ATTR__ATIME | MOUNT_ATTR_NODIRATIME | \ + MOUNT_ATTR_NOSYMFOLLOW) #define MOUNT_SETATTR_VALID_FLAGS (FSMOUNT_VALID_FLAGS | MOUNT_ATTR_IDMAP) @@ -3487,6 +3488,8 @@ static unsigned int attr_flags_to_mnt_flags(u64 attr_flags) mnt_flags |= MNT_NOEXEC; if (attr_flags & MOUNT_ATTR_NODIRATIME) mnt_flags |= MNT_NODIRATIME; + if (attr_flags & MOUNT_ATTR_NOSYMFOLLOW) + mnt_flags |= MNT_NOSYMFOLLOW; return mnt_flags; } diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index c0361ce45f62..97769fe4d588 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -434,6 +434,7 @@ nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc) static const struct address_space_operations def_mdt_aops = { + .set_page_dirty = __set_page_dirty_buffers, .writepage = nilfs_mdt_write_page, }; diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index 9c6c0e2e5880..68e8d61e28dd 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -19,19 +19,6 @@ /* /sys/fs// */ static struct kset *nilfs_kset; -#define NILFS_SHOW_TIME(time_t_val, buf) ({ \ - struct tm res; \ - int count = 0; \ - time64_to_tm(time_t_val, 0, &res); \ - res.tm_year += 1900; \ - res.tm_mon += 1; \ - count = scnprintf(buf, PAGE_SIZE, \ - "%ld-%.2d-%.2d %.2d:%.2d:%.2d\n", \ - res.tm_year, res.tm_mon, res.tm_mday, \ - res.tm_hour, res.tm_min, res.tm_sec);\ - count; \ -}) - #define NILFS_DEV_INT_GROUP_OPS(name, parent_name) \ static ssize_t nilfs_##name##_attr_show(struct kobject *kobj, \ struct attribute *attr, char *buf) \ @@ -576,7 +563,7 @@ nilfs_segctor_last_seg_write_time_show(struct nilfs_segctor_attr *attr, ctime = nilfs->ns_ctime; up_read(&nilfs->ns_segctor_sem); - return NILFS_SHOW_TIME(ctime, buf); + return sysfs_emit(buf, "%ptTs\n", &ctime); } static ssize_t @@ -604,7 +591,7 @@ nilfs_segctor_last_nongc_write_time_show(struct nilfs_segctor_attr *attr, nongc_ctime = nilfs->ns_nongc_ctime; up_read(&nilfs->ns_segctor_sem); - return NILFS_SHOW_TIME(nongc_ctime, buf); + return sysfs_emit(buf, "%ptTs\n", &nongc_ctime); } static ssize_t @@ -724,7 +711,7 @@ nilfs_superblock_sb_write_time_show(struct nilfs_superblock_attr *attr, sbwtime = nilfs->ns_sbwtime; up_read(&nilfs->ns_sem); - return NILFS_SHOW_TIME(sbwtime, buf); + return sysfs_emit(buf, "%ptTs\n", &sbwtime); } static ssize_t diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index f5c058b3192c..4474adb393ca 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -477,7 +477,7 @@ err_corrupt_attr: } file_name_attr = (FILE_NAME_ATTR*)((u8*)attr + le16_to_cpu(attr->data.resident.value_offset)); - p2 = (u8*)attr + le32_to_cpu(attr->data.resident.value_length); + p2 = (u8 *)file_name_attr + le32_to_cpu(attr->data.resident.value_length); if (p2 < (u8*)attr || p2 > p) goto err_corrupt_attr; /* This attribute is ok, but is it in the $Extend directory? */ diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index e032f2e2c2c5..f1cc8258d34a 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -6018,7 +6018,7 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb) * Then truncate log will be replayed resulting in cluster double free. */ jbd2_journal_lock_updates(journal->j_journal); - status = jbd2_journal_flush(journal->j_journal); + status = jbd2_journal_flush(journal->j_journal, 0); jbd2_journal_unlock_updates(journal->j_journal); if (status < 0) { mlog_errno(status); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 1294925ac94a..68d11c295dd3 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -632,8 +632,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno, } if (PageUptodate(page)) { - if (!buffer_uptodate(bh)) - set_buffer_uptodate(bh); + set_buffer_uptodate(bh); } else if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_new(bh) && ocfs2_should_read_blk(inode, page, block_start) && @@ -2454,6 +2453,7 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } const struct address_space_operations ocfs2_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = ocfs2_readpage, .readahead = ocfs2_readahead, .writepage = ocfs2_writepage, diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index e829c2595543..f89ffcbd585f 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1442,8 +1442,6 @@ void o2hb_init(void) for (i = 0; i < ARRAY_SIZE(o2hb_live_slots); i++) INIT_LIST_HEAD(&o2hb_live_slots[i]); - INIT_LIST_HEAD(&o2hb_node_events); - memset(o2hb_live_node_bitmap, 0, sizeof(o2hb_live_node_bitmap)); memset(o2hb_region_bitmap, 0, sizeof(o2hb_region_bitmap)); memset(o2hb_live_region_bitmap, 0, sizeof(o2hb_live_region_bitmap)); @@ -1598,12 +1596,13 @@ static ssize_t o2hb_region_start_block_store(struct config_item *item, struct o2hb_region *reg = to_o2hb_region(item); unsigned long long tmp; char *p = (char *)page; + ssize_t ret; if (reg->hr_bdev) return -EINVAL; - tmp = simple_strtoull(p, &p, 0); - if (!p || (*p && (*p != '\n'))) + ret = kstrtoull(p, 0, &tmp); + if (ret) return -EINVAL; reg->hr_start_block = tmp; diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index bb82e6b1ff4e..625c92521416 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -824,7 +824,7 @@ static void __exit exit_o2nm(void) static int __init init_o2nm(void) { - int ret = -1; + int ret; o2hb_init(); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 4960a6de768d..9b88219febb5 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2977,7 +2977,7 @@ static u8 dlm_pick_migration_target(struct dlm_ctxt *dlm, struct dlm_lock_resource *res) { enum dlm_lockres_list idx; - struct list_head *queue = &res->granted; + struct list_head *queue; struct dlm_lock *lock; int noderef; u8 nodenum = O2NM_MAX_NODES; diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c index 90b8d300c1ee..de56e6231af8 100644 --- a/fs/ocfs2/filecheck.c +++ b/fs/ocfs2/filecheck.c @@ -326,11 +326,7 @@ static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj, ret = snprintf(buf + total, remain, "%lu\t\t%u\t%s\n", p->fe_ino, p->fe_done, ocfs2_filecheck_error(p->fe_status)); - if (ret < 0) { - total = ret; - break; - } - if (ret == remain) { + if (ret >= remain) { /* snprintf() didn't fit */ total = -E2BIG; break; diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 4e589ce2fce6..4f15750aac5d 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -308,7 +308,7 @@ static int ocfs2_commit_cache(struct ocfs2_super *osb) } jbd2_journal_lock_updates(journal->j_journal); - status = jbd2_journal_flush(journal->j_journal); + status = jbd2_journal_flush(journal->j_journal, 0); jbd2_journal_unlock_updates(journal->j_journal); if (status < 0) { up_write(&journal->j_trans_barrier); @@ -1000,7 +1000,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb) if (ocfs2_mount_local(osb)) { jbd2_journal_lock_updates(journal->j_journal); - status = jbd2_journal_flush(journal->j_journal); + status = jbd2_journal_flush(journal->j_journal, 0); jbd2_journal_unlock_updates(journal->j_journal); if (status < 0) mlog_errno(status); @@ -1070,7 +1070,7 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed) if (replayed) { jbd2_journal_lock_updates(journal->j_journal); - status = jbd2_journal_flush(journal->j_journal); + status = jbd2_journal_flush(journal->j_journal, 0); jbd2_journal_unlock_updates(journal->j_journal); if (status < 0) mlog_errno(status); @@ -1666,7 +1666,7 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb, /* wipe the journal */ jbd2_journal_lock_updates(journal); - status = jbd2_journal_flush(journal); + status = jbd2_journal_flush(journal, 0); jbd2_journal_unlock_updates(journal); if (status < 0) mlog_errno(status); diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index d50e8b8dfea4..16f1bfc407f2 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -500,11 +500,7 @@ static ssize_t ocfs2_loaded_cluster_plugins_show(struct kobject *kobj, list_for_each_entry(p, &ocfs2_stack_list, sp_list) { ret = snprintf(buf, remain, "%s\n", p->sp_name); - if (ret < 0) { - total = ret; - break; - } - if (ret == remain) { + if (ret >= remain) { /* snprintf() didn't fit */ total = -E2BIG; break; @@ -531,7 +527,7 @@ static ssize_t ocfs2_active_cluster_plugin_show(struct kobject *kobj, if (active_stack) { ret = snprintf(buf, PAGE_SIZE, "%s\n", active_stack->sp_name); - if (ret == PAGE_SIZE) + if (ret >= PAGE_SIZE) ret = -E2BIG; } spin_unlock(&ocfs2_stack_lock); diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 11e733aab25d..89725b15a64b 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -372,6 +372,7 @@ const struct inode_operations omfs_file_inops = { }; const struct address_space_operations omfs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = omfs_readpage, .readahead = omfs_readahead, .writepage = omfs_writepage, diff --git a/fs/open.c b/fs/open.c index e53af13b5835..53bc0573c0ec 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1002,12 +1002,20 @@ inline struct open_how build_open_how(int flags, umode_t mode) inline int build_open_flags(const struct open_how *how, struct open_flags *op) { - int flags = how->flags; + u64 flags = how->flags; + u64 strip = FMODE_NONOTIFY | O_CLOEXEC; int lookup_flags = 0; int acc_mode = ACC_MODE(flags); - /* Must never be set by userspace */ - flags &= ~(FMODE_NONOTIFY | O_CLOEXEC); + BUILD_BUG_ON_MSG(upper_32_bits(VALID_OPEN_FLAGS), + "struct open_flags doesn't yet handle flags > 32 bits"); + + /* + * Strip flags that either shouldn't be set by userspace like + * FMODE_NONOTIFY or that aren't relevant in determining struct + * open_flags like O_CLOEXEC. + */ + flags &= ~strip; /* * Older syscalls implicitly clear all of the invalid flags or argument diff --git a/fs/proc/array.c b/fs/proc/array.c index 7ec59171f197..ee0ce8cecc4a 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -284,7 +284,7 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p) collect_sigign_sigcatch(p, &ignored, &caught); num_threads = get_nr_threads(p); rcu_read_lock(); /* FIXME: is this correct? */ - qsize = atomic_read(&__task_cred(p)->user->sigpending); + qsize = get_ucounts_value(task_ucounts(p), UCOUNT_RLIMIT_SIGPENDING); rcu_read_unlock(); qlim = task_rlimit(p, RLIMIT_SIGPENDING); unlock_task_sighand(p, &flags); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 2a26ed67c820..dcad3ab9f0c2 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1109,7 +1109,7 @@ static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, return false; if (!is_cow_mapping(vma->vm_flags)) return false; - if (likely(!atomic_read(&vma->vm_mm->has_pinned))) + if (likely(!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))) return false; page = vm_normal_page(vma, addr, pte); if (!page) diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 8adabde685f1..328da35da390 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -173,6 +173,7 @@ config PSTORE_BLK tristate "Log panic/oops to a block device" depends on PSTORE depends on BLOCK + depends on BROKEN select PSTORE_ZONE default n help diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 05e4bd9ab6d6..2bcc9a6f1bfc 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -968,31 +968,30 @@ out: return ret; } -SYSCALL_DEFINE4(quotactl_path, unsigned int, cmd, const char __user *, - mountpoint, qid_t, id, void __user *, addr) +SYSCALL_DEFINE4(quotactl_fd, unsigned int, fd, unsigned int, cmd, + qid_t, id, void __user *, addr) { struct super_block *sb; - struct path mountpath; unsigned int cmds = cmd >> SUBCMDSHIFT; unsigned int type = cmd & SUBCMDMASK; + struct fd f; int ret; + f = fdget_raw(fd); + if (!f.file) + return -EBADF; + + ret = -EINVAL; if (type >= MAXQUOTAS) - return -EINVAL; - - ret = user_path_at(AT_FDCWD, mountpoint, - LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT, &mountpath); - if (ret) - return ret; - - sb = mountpath.mnt->mnt_sb; + goto out; if (quotactl_cmd_write(cmds)) { - ret = mnt_want_write(mountpath.mnt); + ret = mnt_want_write(f.file->f_path.mnt); if (ret) goto out; } + sb = f.file->f_path.mnt->mnt_sb; if (quotactl_cmd_onoff(cmds)) down_write(&sb->s_umount); else @@ -1006,9 +1005,8 @@ SYSCALL_DEFINE4(quotactl_path, unsigned int, cmd, const char __user *, up_read(&sb->s_umount); if (quotactl_cmd_write(cmds)) - mnt_drop_write(mountpath.mnt); + mnt_drop_write(f.file->f_path.mnt); out: - path_put(&mountpath); - + fdput(f); return ret; } diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c index c5562c871c8b..d3e995e1046f 100644 --- a/fs/quota/quota_tree.c +++ b/fs/quota/quota_tree.c @@ -47,15 +47,6 @@ static int qtree_dqstr_in_blk(struct qtree_mem_dqinfo *info) / info->dqi_entry_size; } -static char *getdqbuf(size_t size) -{ - char *buf = kmalloc(size, GFP_NOFS); - if (!buf) - printk(KERN_WARNING - "VFS: Not enough memory for quota buffers.\n"); - return buf; -} - static ssize_t read_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) { struct super_block *sb = info->dqi_sb; @@ -83,7 +74,7 @@ static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf) /* Remove empty block from list and return it */ static int get_free_dqblk(struct qtree_mem_dqinfo *info) { - char *buf = getdqbuf(info->dqi_usable_bs); + char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS); struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf; int ret, blk; @@ -132,7 +123,7 @@ static int put_free_dqblk(struct qtree_mem_dqinfo *info, char *buf, uint blk) static int remove_free_dqentry(struct qtree_mem_dqinfo *info, char *buf, uint blk) { - char *tmpbuf = getdqbuf(info->dqi_usable_bs); + char *tmpbuf = kmalloc(info->dqi_usable_bs, GFP_NOFS); struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf; uint nextblk = le32_to_cpu(dh->dqdh_next_free); uint prevblk = le32_to_cpu(dh->dqdh_prev_free); @@ -179,7 +170,7 @@ out_buf: static int insert_free_dqentry(struct qtree_mem_dqinfo *info, char *buf, uint blk) { - char *tmpbuf = getdqbuf(info->dqi_usable_bs); + char *tmpbuf = kmalloc(info->dqi_usable_bs, GFP_NOFS); struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf; int err; @@ -227,7 +218,7 @@ static uint find_free_dqentry(struct qtree_mem_dqinfo *info, { uint blk, i; struct qt_disk_dqdbheader *dh; - char *buf = getdqbuf(info->dqi_usable_bs); + char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS); char *ddquot; *err = 0; @@ -298,7 +289,7 @@ out_buf: static int do_insert_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot, uint *treeblk, int depth) { - char *buf = getdqbuf(info->dqi_usable_bs); + char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS); int ret = 0, newson = 0, newact = 0; __le32 *ref; uint newblk; @@ -375,7 +366,7 @@ int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot) int type = dquot->dq_id.type; struct super_block *sb = dquot->dq_sb; ssize_t ret; - char *ddquot = getdqbuf(info->dqi_entry_size); + char *ddquot = kmalloc(info->dqi_entry_size, GFP_NOFS); if (!ddquot) return -ENOMEM; @@ -414,7 +405,7 @@ static int free_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot, uint blk) { struct qt_disk_dqdbheader *dh; - char *buf = getdqbuf(info->dqi_usable_bs); + char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS); int ret = 0; if (!buf) @@ -474,7 +465,7 @@ out_buf: static int remove_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot, uint *blk, int depth) { - char *buf = getdqbuf(info->dqi_usable_bs); + char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS); int ret = 0; uint newblk; __le32 *ref = (__le32 *)buf; @@ -533,7 +524,7 @@ EXPORT_SYMBOL(qtree_delete_dquot); static loff_t find_block_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot, uint blk) { - char *buf = getdqbuf(info->dqi_usable_bs); + char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS); loff_t ret = 0; int i; char *ddquot; @@ -571,7 +562,7 @@ out_buf: static loff_t find_tree_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot, uint blk, int depth) { - char *buf = getdqbuf(info->dqi_usable_bs); + char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS); loff_t ret = 0; __le32 *ref = (__le32 *)buf; @@ -635,7 +626,7 @@ int qtree_read_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot) } dquot->dq_off = offset; } - ddquot = getdqbuf(info->dqi_entry_size); + ddquot = kmalloc(info->dqi_entry_size, GFP_NOFS); if (!ddquot) return -ENOMEM; ret = sb->s_op->quota_read(sb, type, ddquot, info->dqi_entry_size, @@ -679,7 +670,7 @@ EXPORT_SYMBOL(qtree_release_dquot); static int find_next_id(struct qtree_mem_dqinfo *info, qid_t *id, unsigned int blk, int depth) { - char *buf = getdqbuf(info->dqi_usable_bs); + char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS); __le32 *ref = (__le32 *)buf; ssize_t ret; unsigned int epb = info->dqi_usable_bs >> 2; diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 9ebd17d7befb..65e7e56005b8 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -53,13 +53,6 @@ struct ramfs_fs_info { static const struct super_operations ramfs_ops; static const struct inode_operations ramfs_dir_inode_operations; -static const struct address_space_operations ramfs_aops = { - .readpage = simple_readpage, - .write_begin = simple_write_begin, - .write_end = simple_write_end, - .set_page_dirty = __set_page_dirty_no_writeback, -}; - struct inode *ramfs_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode, dev_t dev) { @@ -68,7 +61,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, if (inode) { inode->i_ino = get_next_ino(); inode_init_owner(&init_user_ns, inode, dir, mode); - inode->i_mapping->a_ops = &ramfs_aops; + inode->i_mapping->a_ops = &ram_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_unevictable(inode->i_mapping); inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 780bb90c1804..f49b72ccac4c 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2584,9 +2584,7 @@ static int reiserfs_write_full_page(struct page *page, clear_buffer_dirty(bh); set_buffer_uptodate(bh); } else if ((checked || buffer_dirty(bh)) && - (!buffer_mapped(bh) || (buffer_mapped(bh) - && bh->b_blocknr == - 0))) { + (!buffer_mapped(bh) || bh->b_blocknr == 0)) { /* * not mapped yet, or it points to a direct item, search * the btree for the mapping info, and log any direct diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 9edc8e2b154e..0834b101c316 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2758,6 +2758,20 @@ int journal_init(struct super_block *sb, const char *j_dev_name, goto free_and_return; } + /* + * Sanity check to see if journal first block is correct. + * If journal first block is invalid it can cause + * zeroing important superblock members. + */ + if (!SB_ONDISK_JOURNAL_DEVICE(sb) && + SB_ONDISK_JOURNAL_1st_BLOCK(sb) < SB_JOURNAL_1st_RESERVED_BLOCK(sb)) { + reiserfs_warning(sb, "journal-1393", + "journal 1st super block is invalid: 1st reserved block %d, but actual 1st block is %d", + SB_JOURNAL_1st_RESERVED_BLOCK(sb), + SB_ONDISK_JOURNAL_1st_BLOCK(sb)); + goto free_and_return; + } + if (journal_init_dev(sb, journal, j_dev_name) != 0) { reiserfs_warning(sb, "sh-462", "unable to initialize journal device"); diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index b9e87ebb1060..855f0e87066d 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -226,8 +226,11 @@ out_free_bio: bio_free_pages(bio); bio_put(bio); out: - if (res < 0) + if (res < 0) { ERROR("Failed to read block 0x%llx: %d\n", index, res); + if (msblk->panic_on_errors) + panic("squashfs read failed"); + } return res; } diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 166e98806265..1e90c2575f9b 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -65,5 +65,6 @@ struct squashfs_sb_info { unsigned int fragments; int xattr_ids; unsigned int ids; + bool panic_on_errors; }; #endif diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 88cc94be1076..60d6951915f4 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -18,9 +18,11 @@ #include #include +#include #include #include #include +#include #include #include #include @@ -37,6 +39,51 @@ static struct file_system_type squashfs_fs_type; static const struct super_operations squashfs_super_ops; +enum Opt_errors { + Opt_errors_continue, + Opt_errors_panic, +}; + +enum squashfs_param { + Opt_errors, +}; + +struct squashfs_mount_opts { + enum Opt_errors errors; +}; + +static const struct constant_table squashfs_param_errors[] = { + {"continue", Opt_errors_continue }, + {"panic", Opt_errors_panic }, + {} +}; + +static const struct fs_parameter_spec squashfs_fs_parameters[] = { + fsparam_enum("errors", Opt_errors, squashfs_param_errors), + {} +}; + +static int squashfs_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct squashfs_mount_opts *opts = fc->fs_private; + struct fs_parse_result result; + int opt; + + opt = fs_parse(fc, squashfs_fs_parameters, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_errors: + opts->errors = result.uint_32; + break; + default: + return -EINVAL; + } + + return 0; +} + static const struct squashfs_decompressor *supported_squashfs_filesystem( struct fs_context *fc, short major, short minor, short id) @@ -67,6 +114,7 @@ static const struct squashfs_decompressor *supported_squashfs_filesystem( static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) { + struct squashfs_mount_opts *opts = fc->fs_private; struct squashfs_sb_info *msblk; struct squashfs_super_block *sblk = NULL; struct inode *root; @@ -85,6 +133,8 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) } msblk = sb->s_fs_info; + msblk->panic_on_errors = (opts->errors == Opt_errors_panic); + msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE); msblk->devblksize_log2 = ffz(~msblk->devblksize); @@ -350,18 +400,52 @@ static int squashfs_get_tree(struct fs_context *fc) static int squashfs_reconfigure(struct fs_context *fc) { + struct super_block *sb = fc->root->d_sb; + struct squashfs_sb_info *msblk = sb->s_fs_info; + struct squashfs_mount_opts *opts = fc->fs_private; + sync_filesystem(fc->root->d_sb); fc->sb_flags |= SB_RDONLY; + + msblk->panic_on_errors = (opts->errors == Opt_errors_panic); + return 0; } +static void squashfs_free_fs_context(struct fs_context *fc) +{ + kfree(fc->fs_private); +} + static const struct fs_context_operations squashfs_context_ops = { .get_tree = squashfs_get_tree, + .free = squashfs_free_fs_context, + .parse_param = squashfs_parse_param, .reconfigure = squashfs_reconfigure, }; +static int squashfs_show_options(struct seq_file *s, struct dentry *root) +{ + struct super_block *sb = root->d_sb; + struct squashfs_sb_info *msblk = sb->s_fs_info; + + if (msblk->panic_on_errors) + seq_puts(s, ",errors=panic"); + else + seq_puts(s, ",errors=continue"); + + return 0; +} + static int squashfs_init_fs_context(struct fs_context *fc) { + struct squashfs_mount_opts *opts; + + opts = kzalloc(sizeof(*opts), GFP_KERNEL); + if (!opts) + return -ENOMEM; + + fc->fs_private = opts; fc->ops = &squashfs_context_ops; return 0; } @@ -481,6 +565,7 @@ static struct file_system_type squashfs_fs_type = { .owner = THIS_MODULE, .name = "squashfs", .init_fs_context = squashfs_init_fs_context, + .parameters = squashfs_fs_parameters, .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV }; @@ -491,6 +576,7 @@ static const struct super_operations squashfs_super_ops = { .free_inode = squashfs_free_inode, .statfs = squashfs_statfs, .put_super = squashfs_put_super, + .show_options = squashfs_show_options, }; module_init(init_squashfs_fs); diff --git a/fs/super.c b/fs/super.c index 11b7e7213fd1..91b7f156735b 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1277,9 +1277,9 @@ int get_tree_bdev(struct fs_context *fc, } /* - * s_umount nests inside bd_mutex during + * s_umount nests inside open_mutex during * __invalidate_device(). blkdev_put() acquires - * bd_mutex and can't be called under s_umount. Drop + * open_mutex and can't be called under s_umount. Drop * s_umount temporarily. This is safe as we're * holding an active reference. */ @@ -1352,9 +1352,9 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, } /* - * s_umount nests inside bd_mutex during + * s_umount nests inside open_mutex during * __invalidate_device(). blkdev_put() acquires - * bd_mutex and can't be called under s_umount. Drop + * open_mutex and can't be called under s_umount. Drop * s_umount temporarily. This is safe as we're * holding an active reference. */ diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c index 8b2e99b7bc9f..749385015a8d 100644 --- a/fs/sysv/itree.c +++ b/fs/sysv/itree.c @@ -495,6 +495,7 @@ static sector_t sysv_bmap(struct address_space *mapping, sector_t block) } const struct address_space_operations sysv_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = sysv_readpage, .writepage = sysv_writepage, .write_begin = sysv_write_begin, diff --git a/fs/udf/file.c b/fs/udf/file.c index 2846dcd92197..1baff8ddb754 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -125,6 +125,7 @@ static int udf_adinicb_write_end(struct file *file, struct address_space *mappin } const struct address_space_operations udf_adinicb_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = udf_adinicb_readpage, .writepage = udf_adinicb_writepage, .write_begin = udf_adinicb_write_begin, diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 0dd2f93ac048..4917670860a0 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -235,6 +235,7 @@ static sector_t udf_bmap(struct address_space *mapping, sector_t block) } const struct address_space_operations udf_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = udf_readpage, .readahead = udf_readahead, .writepage = udf_writepage, diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 3ae9f1e91984..7c7c9bbbfa57 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -934,6 +934,10 @@ static int udf_symlink(struct user_namespace *mnt_userns, struct inode *dir, iinfo->i_location.partitionReferenceNum, 0); epos.bh = udf_tgetblk(sb, block); + if (unlikely(!epos.bh)) { + err = -ENOMEM; + goto out_no_entry; + } lock_buffer(epos.bh); memset(epos.bh->b_data, 0x00, bsize); set_buffer_uptodate(epos.bh); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index debc282c1bb4..ac628de69601 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -526,6 +526,7 @@ static sector_t ufs_bmap(struct address_space *mapping, sector_t block) } const struct address_space_operations ufs_aops = { + .set_page_dirty = __set_page_dirty_buffers, .readpage = ufs_readpage, .writepage = ufs_writepage, .write_begin = ufs_write_begin, diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 826caa6b4a5a..cb4e0fcf4c76 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -561,7 +561,7 @@ const struct address_space_operations xfs_address_space_operations = { .readahead = xfs_vm_readahead, .writepage = xfs_vm_writepage, .writepages = xfs_vm_writepages, - .set_page_dirty = iomap_set_page_dirty, + .set_page_dirty = __set_page_dirty_nobuffers, .releasepage = iomap_releasepage, .invalidatepage = iomap_invalidatepage, .bmap = xfs_vm_bmap, @@ -575,7 +575,7 @@ const struct address_space_operations xfs_address_space_operations = { const struct address_space_operations xfs_dax_aops = { .writepages = xfs_dax_writepages, .direct_IO = noop_direct_IO, - .set_page_dirty = noop_set_page_dirty, + .set_page_dirty = __set_page_dirty_no_writeback, .invalidatepage = noop_invalidatepage, .swap_activate = xfs_iomap_swapfile_activate, }; diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h index 7ec1a9207517..bb9860ec9a93 100644 --- a/fs/xfs/xfs_message.h +++ b/fs/xfs/xfs_message.h @@ -2,6 +2,8 @@ #ifndef __XFS_MESSAGE_H #define __XFS_MESSAGE_H 1 +#include + struct xfs_mount; extern __printf(2, 3) @@ -41,16 +43,7 @@ do { \ } while (0) #define xfs_printk_once(func, dev, fmt, ...) \ -({ \ - static bool __section(".data.once") __print_once; \ - bool __ret_print_once = !__print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - func(dev, fmt, ##__VA_ARGS__); \ - } \ - unlikely(__ret_print_once); \ -}) + DO_ONCE_LITE(func, dev, fmt, ##__VA_ARGS__) #define xfs_emerg_ratelimited(dev, fmt, ...) \ xfs_printk_ratelimited(xfs_emerg, dev, fmt, ##__VA_ARGS__) diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index cd145d318b17..dbf03635869c 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -5,7 +5,7 @@ * Copyright (C) 2019 Western Digital Corporation or its affiliates. */ #include -#include +#include #include #include #include @@ -185,7 +185,7 @@ static const struct address_space_operations zonefs_file_aops = { .readahead = zonefs_readahead, .writepage = zonefs_writepage, .writepages = zonefs_writepages, - .set_page_dirty = iomap_set_page_dirty, + .set_page_dirty = __set_page_dirty_nobuffers, .releasepage = iomap_releasepage, .invalidatepage = iomap_invalidatepage, .migratepage = iomap_migrate_page, diff --git a/include/acpi/acbuffer.h b/include/acpi/acbuffer.h index 18197c16149f..3e8d969b22fe 100644 --- a/include/acpi/acbuffer.h +++ b/include/acpi/acbuffer.h @@ -207,4 +207,14 @@ struct acpi_pld_info { #define ACPI_PLD_GET_HORIZ_OFFSET(dword) ACPI_GET_BITS (dword, 16, ACPI_16BIT_MASK) #define ACPI_PLD_SET_HORIZ_OFFSET(dword,value) ACPI_SET_BITS (dword, 16, ACPI_16BIT_MASK, value) /* Offset 128+16=144, Len 16 */ +/* Panel position defined in _PLD section of ACPI Specification 6.3 */ + +#define ACPI_PLD_PANEL_TOP 0 +#define ACPI_PLD_PANEL_BOTTOM 1 +#define ACPI_PLD_PANEL_LEFT 2 +#define ACPI_PLD_PANEL_RIGHT 3 +#define ACPI_PLD_PANEL_FRONT 4 +#define ACPI_PLD_PANEL_BACK 5 +#define ACPI_PLD_PANEL_UNKNOWN 6 + #endif /* ACBUFFER_H */ diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h index e92f84fa8c68..0362cbb72359 100644 --- a/include/acpi/acconfig.h +++ b/include/acpi/acconfig.h @@ -188,6 +188,8 @@ #define ACPI_MAX_GSBUS_DATA_SIZE 255 #define ACPI_MAX_GSBUS_BUFFER_SIZE ACPI_SERIAL_HEADER_SIZE + ACPI_MAX_GSBUS_DATA_SIZE +#define ACPI_PRM_INPUT_BUFFER_SIZE 26 + /* _sx_d and _sx_w control methods */ #define ACPI_NUM_sx_d_METHODS 4 diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 3a82faac5767..c6bd4f9a80ba 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -280,6 +280,12 @@ struct acpi_device_power { struct acpi_device_power_state states[ACPI_D_STATE_COUNT]; /* Power states (D0-D3Cold) */ }; +struct acpi_dep_data { + struct list_head node; + acpi_handle supplier; + acpi_handle consumer; +}; + /* Performance Management */ struct acpi_device_perf_flags { @@ -498,8 +504,6 @@ extern int unregister_acpi_notifier(struct notifier_block *); */ int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device); -struct acpi_device *acpi_bus_get_acpi_device(acpi_handle handle); -void acpi_bus_put_acpi_device(struct acpi_device *adev); acpi_status acpi_bus_get_status_handle(acpi_handle handle, unsigned long long *sta); int acpi_bus_get_status(struct acpi_device *device); @@ -586,7 +590,7 @@ struct acpi_pci_root { /* helper */ -bool acpi_dma_supported(struct acpi_device *adev); +bool acpi_dma_supported(const struct acpi_device *adev); enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev); int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset, u64 *size); @@ -685,6 +689,8 @@ static inline bool acpi_device_can_poweroff(struct acpi_device *adev) bool acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2); +void acpi_dev_clear_dependencies(struct acpi_device *supplier); +struct acpi_device *acpi_dev_get_first_consumer_dev(struct acpi_device *supplier); struct acpi_device * acpi_dev_get_next_match_dev(struct acpi_device *adev, const char *hid, const char *uid, s64 hrv); struct acpi_device * @@ -718,6 +724,13 @@ static inline void acpi_dev_put(struct acpi_device *adev) { put_device(&adev->dev); } + +struct acpi_device *acpi_bus_get_acpi_device(acpi_handle handle); + +static inline void acpi_bus_put_acpi_device(struct acpi_device *adev) +{ + acpi_dev_put(adev); +} #else /* CONFIG_ACPI */ static inline int register_acpi_bus_type(void *bus) { return 0; } diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h index 40a91ce87e04..68e4d80c1b32 100644 --- a/include/acpi/acpi_numa.h +++ b/include/acpi/acpi_numa.h @@ -43,4 +43,4 @@ static inline void disable_hmat(void) { } #endif /* CONFIG_ACPI_HMAT */ -#endif /* __ACP_NUMA_H */ +#endif /* __ACPI_NUMA_H */ diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index f8d44b06f3e3..a43335961e30 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -12,7 +12,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20210331 +#define ACPI_CA_VERSION 0x20210604 #include #include diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index ce59903c2695..ef2872dea01c 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -327,9 +327,20 @@ struct acpi_cedt_header { enum acpi_cedt_type { ACPI_CEDT_TYPE_CHBS = 0, - ACPI_CEDT_TYPE_RESERVED = 1 + ACPI_CEDT_TYPE_CFMWS = 1, + ACPI_CEDT_TYPE_RESERVED = 2, }; +/* Values for version field above */ + +#define ACPI_CEDT_CHBS_VERSION_CXL11 (0) +#define ACPI_CEDT_CHBS_VERSION_CXL20 (1) + +/* Values for length field above */ + +#define ACPI_CEDT_CHBS_LENGTH_CXL11 (0x2000) +#define ACPI_CEDT_CHBS_LENGTH_CXL20 (0x10000) + /* * CEDT subtables */ @@ -345,6 +356,34 @@ struct acpi_cedt_chbs { u64 length; }; +/* 1: CXL Fixed Memory Window Structure */ + +struct acpi_cedt_cfmws { + struct acpi_cedt_header header; + u32 reserved1; + u64 base_hpa; + u64 window_size; + u8 interleave_ways; + u8 interleave_arithmetic; + u16 reserved2; + u32 granularity; + u16 restrictions; + u16 qtg_id; + u32 interleave_targets[]; +}; + +/* Values for Interleave Arithmetic field above */ + +#define ACPI_CEDT_CFMWS_ARITHMETIC_MODULO (0) + +/* Values for Restrictions field above */ + +#define ACPI_CEDT_CFMWS_RESTRICT_TYPE2 (1) +#define ACPI_CEDT_CFMWS_RESTRICT_TYPE3 (1<<1) +#define ACPI_CEDT_CFMWS_RESTRICT_VOLATILE (1<<2) +#define ACPI_CEDT_CFMWS_RESTRICT_PMEM (1<<3) +#define ACPI_CEDT_CFMWS_RESTRICT_FIXED (1<<4) + /******************************************************************************* * * CPEP - Corrected Platform Error Polling table (ACPI 4.0) diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 18cafe3ebddc..2069ac38a4e2 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -24,6 +24,7 @@ * file. Useful because they make it more difficult to inadvertently type in * the wrong signature. */ +#define ACPI_SIG_BDAT "BDAT" /* BIOS Data ACPI Table */ #define ACPI_SIG_IORT "IORT" /* IO Remapping Table */ #define ACPI_SIG_IVRS "IVRS" /* I/O Virtualization Reporting Structure */ #define ACPI_SIG_LPIT "LPIT" /* Low Power Idle Table */ @@ -39,11 +40,14 @@ #define ACPI_SIG_PHAT "PHAT" /* Platform Health Assessment Table */ #define ACPI_SIG_PMTT "PMTT" /* Platform Memory Topology Table */ #define ACPI_SIG_PPTT "PPTT" /* Processor Properties Topology Table */ +#define ACPI_SIG_PRMT "PRMT" /* Platform Runtime Mechanism Table */ #define ACPI_SIG_RASF "RASF" /* RAS Feature table */ +#define ACPI_SIG_RGRT "RGRT" /* Regulatory Graphics Resource Table */ #define ACPI_SIG_SBST "SBST" /* Smart Battery Specification Table */ #define ACPI_SIG_SDEI "SDEI" /* Software Delegated Exception Interface Table */ #define ACPI_SIG_SDEV "SDEV" /* Secure Devices table */ #define ACPI_SIG_NHLT "NHLT" /* Non-HDAudio Link Table */ +#define ACPI_SIG_SVKL "SVKL" /* Storage Volume Key Location Table */ /* * All tables must be byte-packed to match the ACPI specification, since @@ -63,6 +67,20 @@ * See http://stackoverflow.com/a/1053662/41661 */ +/******************************************************************************* + * + * BDAT - BIOS Data ACPI Table + * + * Conforms to "BIOS Data ACPI Table", Interface Specification v4.0 Draft 5 + * Nov 2020 + * + ******************************************************************************/ + +struct acpi_table_bdat { + struct acpi_table_header header; + struct acpi_generic_address gas; +}; + /******************************************************************************* * * IORT - IO Remapping Table @@ -446,6 +464,12 @@ struct acpi_ivrs_device_hid { u8 uid_length; }; +/* Values for uid_type above */ + +#define ACPI_IVRS_UID_NOT_PRESENT 0 +#define ACPI_IVRS_UID_IS_INTEGER 1 +#define ACPI_IVRS_UID_IS_STRING 2 + /* 0x20, 0x21, 0x22: I/O Virtualization Memory Definition Block (IVMD) */ struct acpi_ivrs_memory { @@ -763,6 +787,20 @@ struct acpi_madt_multiproc_wakeup { u64 base_address; }; +#define ACPI_MULTIPROC_WAKEUP_MB_OS_SIZE 2032 +#define ACPI_MULTIPROC_WAKEUP_MB_FIRMWARE_SIZE 2048 + +struct acpi_madt_multiproc_wakeup_mailbox { + u16 command; + u16 reserved; /* reserved - must be zero */ + u32 apic_id; + u64 wakeup_vector; + u8 reserved_os[ACPI_MULTIPROC_WAKEUP_MB_OS_SIZE]; /* reserved for OS use */ + u8 reserved_firmware[ACPI_MULTIPROC_WAKEUP_MB_FIRMWARE_SIZE]; /* reserved for firmware use */ +}; + +#define ACPI_MP_WAKE_COMMAND_WAKEUP 1 + /* * Common flags fields for MADT subtables */ @@ -1673,6 +1711,48 @@ struct acpi_pptt_id { u16 spin_rev; }; +/******************************************************************************* + * + * PRMT - Platform Runtime Mechanism Table + * Version 1 + * + ******************************************************************************/ + +struct acpi_table_prmt { + struct acpi_table_header header; /* Common ACPI table header */ +}; + +struct acpi_table_prmt_header { + u8 platform_guid[16]; + u32 module_info_offset; + u32 module_info_count; +}; + +struct acpi_prmt_module_header { + u16 revision; + u16 length; +}; + +struct acpi_prmt_module_info { + u16 revision; + u16 length; + u8 module_guid[16]; + u16 major_rev; + u16 minor_rev; + u16 handler_info_count; + u32 handler_info_offset; + u64 mmio_list_pointer; +}; + +struct acpi_prmt_handler_info { + u16 revision; + u16 length; + u8 handler_guid[16]; + u64 handler_address; + u64 static_data_buffer_address; + u64 acpi_param_buffer_address; +}; + /******************************************************************************* * * RASF - RAS Feature Table (ACPI 5.0) @@ -1769,6 +1849,32 @@ enum acpi_rasf_status { #define ACPI_RASF_ERROR (1<<2) #define ACPI_RASF_STATUS (0x1F<<3) +/******************************************************************************* + * + * RGRT - Regulatory Graphics Resource Table + * Version 1 + * + * Conforms to "ACPI RGRT" available at: + * https://microsoft.github.io/mu/dyn/mu_plus/ms_core_pkg/acpi_RGRT/feature_acpi_rgrt/ + * + ******************************************************************************/ + +struct acpi_table_rgrt { + struct acpi_table_header header; /* Common ACPI table header */ + u16 version; + u8 image_type; + u8 reserved; + u8 image[0]; +}; + +/* image_type values */ + +enum acpi_rgrt_image_type { + ACPI_RGRT_TYPE_RESERVED0 = 0, + ACPI_RGRT_IMAGE_TYPE_PNG = 1, + ACPI_RGRT_TYPE_RESERVED = 2 /* 2 and greater are reserved */ +}; + /******************************************************************************* * * SBST - Smart Battery Specification Table @@ -1899,6 +2005,37 @@ struct acpi_sdev_pcie_path { u8 function; }; +/******************************************************************************* + * + * SVKL - Storage Volume Key Location Table (ACPI 6.4) + * From: "Guest-Host-Communication Interface (GHCI) for Intel + * Trust Domain Extensions (Intel TDX)". + * Version 1 + * + ******************************************************************************/ + +struct acpi_table_svkl { + struct acpi_table_header header; /* Common ACPI table header */ + u32 count; +}; + +struct acpi_svkl_key { + u16 type; + u16 format; + u32 size; + u64 address; +}; + +enum acpi_svkl_type { + ACPI_SVKL_TYPE_MAIN_STORAGE = 0, + ACPI_SVKL_TYPE_RESERVED = 1 /* 1 and greater are reserved */ +}; + +enum acpi_svkl_format { + ACPI_SVKL_FORMAT_RAW_BINARY = 0, + ACPI_SVKL_FORMAT_RESERVED = 1 /* 1 and greater are reserved */ +}; + /* Reset to default packing */ #pragma pack() diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index b402494883b6..bafc51f483c4 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -4,6 +4,7 @@ #include #include +#include #define CUT_HERE "------------[ cut here ]------------\n" @@ -140,39 +141,15 @@ void __warn(const char *file, int line, void *caller, unsigned taint, }) #ifndef WARN_ON_ONCE -#define WARN_ON_ONCE(condition) ({ \ - static bool __section(".data.once") __warned; \ - int __ret_warn_once = !!(condition); \ - \ - if (unlikely(__ret_warn_once && !__warned)) { \ - __warned = true; \ - WARN_ON(1); \ - } \ - unlikely(__ret_warn_once); \ -}) +#define WARN_ON_ONCE(condition) \ + DO_ONCE_LITE_IF(condition, WARN_ON, 1) #endif -#define WARN_ONCE(condition, format...) ({ \ - static bool __section(".data.once") __warned; \ - int __ret_warn_once = !!(condition); \ - \ - if (unlikely(__ret_warn_once && !__warned)) { \ - __warned = true; \ - WARN(1, format); \ - } \ - unlikely(__ret_warn_once); \ -}) +#define WARN_ONCE(condition, format...) \ + DO_ONCE_LITE_IF(condition, WARN, 1, format) -#define WARN_TAINT_ONCE(condition, taint, format...) ({ \ - static bool __section(".data.once") __warned; \ - int __ret_warn_once = !!(condition); \ - \ - if (unlikely(__ret_warn_once && !__warned)) { \ - __warned = true; \ - WARN_TAINT(1, taint, format); \ - } \ - unlikely(__ret_warn_once); \ -}) +#define WARN_TAINT_ONCE(condition, taint, format...) \ + DO_ONCE_LITE_IF(condition, WARN_TAINT, 1, taint, format) #else /* !CONFIG_BUG */ #ifndef HAVE_ARCH_BUG diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h index 7637fb46ba4f..a2c8ed60233a 100644 --- a/include/asm-generic/memory_model.h +++ b/include/asm-generic/memory_model.h @@ -6,47 +6,18 @@ #ifndef __ASSEMBLY__ +/* + * supports 3 memory models. + */ #if defined(CONFIG_FLATMEM) #ifndef ARCH_PFN_OFFSET #define ARCH_PFN_OFFSET (0UL) #endif -#elif defined(CONFIG_DISCONTIGMEM) - -#ifndef arch_pfn_to_nid -#define arch_pfn_to_nid(pfn) pfn_to_nid(pfn) -#endif - -#ifndef arch_local_page_offset -#define arch_local_page_offset(pfn, nid) \ - ((pfn) - NODE_DATA(nid)->node_start_pfn) -#endif - -#endif /* CONFIG_DISCONTIGMEM */ - -/* - * supports 3 memory models. - */ -#if defined(CONFIG_FLATMEM) - #define __pfn_to_page(pfn) (mem_map + ((pfn) - ARCH_PFN_OFFSET)) #define __page_to_pfn(page) ((unsigned long)((page) - mem_map) + \ ARCH_PFN_OFFSET) -#elif defined(CONFIG_DISCONTIGMEM) - -#define __pfn_to_page(pfn) \ -({ unsigned long __pfn = (pfn); \ - unsigned long __nid = arch_pfn_to_nid(__pfn); \ - NODE_DATA(__nid)->node_mem_map + arch_local_page_offset(__pfn, __nid);\ -}) - -#define __page_to_pfn(pg) \ -({ const struct page *__pg = (pg); \ - struct pglist_data *__pgdat = NODE_DATA(page_to_nid(__pg)); \ - (unsigned long)(__pg - __pgdat->node_mem_map) + \ - __pgdat->node_start_pfn; \ -}) #elif defined(CONFIG_SPARSEMEM_VMEMMAP) @@ -70,7 +41,7 @@ struct mem_section *__sec = __pfn_to_section(__pfn); \ __section_mem_map_addr(__sec) + __pfn; \ }) -#endif /* CONFIG_FLATMEM/DISCONTIGMEM/SPARSEMEM */ +#endif /* CONFIG_FLATMEM/SPARSEMEM */ /* * Convert a physical address to a Page Frame Number and back diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h index ce2cbb3c380f..2f6b1befb129 100644 --- a/include/asm-generic/pgtable-nop4d.h +++ b/include/asm-generic/pgtable-nop4d.h @@ -9,7 +9,6 @@ typedef struct { pgd_t pgd; } p4d_t; #define P4D_SHIFT PGDIR_SHIFT -#define MAX_PTRS_PER_P4D 1 #define PTRS_PER_P4D 1 #define P4D_SIZE (1UL << P4D_SHIFT) #define P4D_MASK (~(P4D_SIZE-1)) diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h index 5aa8705df87e..4dbe715be65b 100644 --- a/include/asm-generic/topology.h +++ b/include/asm-generic/topology.h @@ -45,7 +45,7 @@ #endif #ifndef cpumask_of_node - #ifdef CONFIG_NEED_MULTIPLE_NODES + #ifdef CONFIG_NUMA #define cpumask_of_node(node) ((node) == 0 ? cpu_online_mask : cpu_none_mask) #else #define cpumask_of_node(node) ((void)(node), cpu_online_mask) diff --git a/include/clocksource/samsung_pwm.h b/include/clocksource/samsung_pwm.h index c395238d0922..9b435caa95fe 100644 --- a/include/clocksource/samsung_pwm.h +++ b/include/clocksource/samsung_pwm.h @@ -27,6 +27,7 @@ struct samsung_pwm_variant { }; void samsung_pwm_clocksource_init(void __iomem *base, - unsigned int *irqs, struct samsung_pwm_variant *variant); + unsigned int *irqs, + const struct samsung_pwm_variant *variant); #endif /* __CLOCKSOURCE_SAMSUNG_PWM_H */ diff --git a/include/clocksource/timer-ti-dm.h b/include/clocksource/timer-ti-dm.h index 4c61dade8835..f6da8a132639 100644 --- a/include/clocksource/timer-ti-dm.h +++ b/include/clocksource/timer-ti-dm.h @@ -74,6 +74,7 @@ #define OMAP_TIMER_ERRATA_I103_I767 0x80000000 struct timer_regs { + u32 ocp_cfg; u32 tidr; u32 tier; u32 twer; diff --git a/include/kunit/test.h b/include/kunit/test.h index 49601c4b98b8..524d4789af22 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -515,8 +515,9 @@ kunit_find_resource(struct kunit *test, void *match_data) { struct kunit_resource *res, *found = NULL; + unsigned long flags; - spin_lock(&test->lock); + spin_lock_irqsave(&test->lock, flags); list_for_each_entry_reverse(res, &test->resources, node) { if (match(test, res, (void *)match_data)) { @@ -526,7 +527,7 @@ kunit_find_resource(struct kunit *test, } } - spin_unlock(&test->lock); + spin_unlock_irqrestore(&test->lock, flags); return found; } diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c60745f657e9..b338613fb536 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -132,6 +132,7 @@ enum acpi_address_range_id { union acpi_subtable_headers { struct acpi_subtable_header common; struct acpi_hmat_structure hmat; + struct acpi_prmt_module_header prmt; }; typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); @@ -550,6 +551,7 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 +#define OSC_SB_PRM_SUPPORT 0x00020000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 extern bool osc_sb_apei_support_acked; @@ -666,7 +668,6 @@ extern bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv); int acpi_device_uevent_modalias(struct device *, struct kobj_uevent_env *); int acpi_device_modalias(struct device *, char *, int); -void acpi_walk_dep_device_list(acpi_handle handle); struct platform_device *acpi_create_platform_device(struct acpi_device *, struct property_entry *); @@ -710,6 +711,8 @@ static inline u64 acpi_arch_get_root_pointer(void) } #endif +int acpi_get_local_address(acpi_handle handle, u32 *addr); + #else /* !CONFIG_ACPI */ #define acpi_disabled 1 @@ -765,7 +768,7 @@ static inline bool is_acpi_device_node(const struct fwnode_handle *fwnode) return false; } -static inline struct acpi_device *to_acpi_device_node(struct fwnode_handle *fwnode) +static inline struct acpi_device *to_acpi_device_node(const struct fwnode_handle *fwnode) { return NULL; } @@ -775,12 +778,12 @@ static inline bool is_acpi_data_node(const struct fwnode_handle *fwnode) return false; } -static inline struct acpi_data_node *to_acpi_data_node(struct fwnode_handle *fwnode) +static inline struct acpi_data_node *to_acpi_data_node(const struct fwnode_handle *fwnode) { return NULL; } -static inline bool acpi_data_node_match(struct fwnode_handle *fwnode, +static inline bool acpi_data_node_match(const struct fwnode_handle *fwnode, const char *name) { return false; @@ -911,7 +914,7 @@ acpi_create_platform_device(struct acpi_device *adev, return NULL; } -static inline bool acpi_dma_supported(struct acpi_device *adev) +static inline bool acpi_dma_supported(const struct acpi_device *adev) { return false; } @@ -965,6 +968,11 @@ static inline struct acpi_device *acpi_resource_consumer(struct resource *res) return NULL; } +static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) +{ + return -ENODEV; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC @@ -1004,6 +1012,7 @@ int acpi_dev_resume(struct device *dev); int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); +bool acpi_storage_d3(struct device *dev); #else static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } @@ -1011,6 +1020,10 @@ static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) { return 0; } +static inline bool acpi_storage_d3(struct device *dev) +{ + return false; +} #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) @@ -1096,6 +1109,8 @@ void __acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, const c #if defined(CONFIG_ACPI) && defined(CONFIG_GPIOLIB) bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); +bool acpi_gpio_get_io_resource(struct acpi_resource *ares, + struct acpi_resource_gpio **agpio); int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, @@ -1103,6 +1118,11 @@ static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, { return false; } +static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, + struct acpi_resource_gpio **agpio) +{ + return false; +} static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index) { diff --git a/include/linux/acpi_mdio.h b/include/linux/acpi_mdio.h new file mode 100644 index 000000000000..0a24ab7cb66f --- /dev/null +++ b/include/linux/acpi_mdio.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * ACPI helper for the MDIO (Ethernet PHY) API + */ + +#ifndef __LINUX_ACPI_MDIO_H +#define __LINUX_ACPI_MDIO_H + +#include + +#if IS_ENABLED(CONFIG_ACPI_MDIO) +int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode); +#else /* CONFIG_ACPI_MDIO */ +static inline int +acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) +{ + /* + * Fall back to mdiobus_register() function to register a bus. + * This way, we don't have to keep compat bits around in drivers. + */ + + return mdiobus_register(mdio); +} +#endif + +#endif /* __LINUX_ACPI_MDIO_H */ diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 8612f8fc86c1..db0e099c2399 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -412,9 +412,36 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_queue_select); * PF removes the filters and returns status. */ +/* VIRTCHNL_ETHER_ADDR_LEGACY + * Prior to adding the @type member to virtchnl_ether_addr, there were 2 pad + * bytes. Moving forward all VF drivers should not set type to + * VIRTCHNL_ETHER_ADDR_LEGACY. This is only here to not break previous/legacy + * behavior. The control plane function (i.e. PF) can use a best effort method + * of tracking the primary/device unicast in this case, but there is no + * guarantee and functionality depends on the implementation of the PF. + */ + +/* VIRTCHNL_ETHER_ADDR_PRIMARY + * All VF drivers should set @type to VIRTCHNL_ETHER_ADDR_PRIMARY for the + * primary/device unicast MAC address filter for VIRTCHNL_OP_ADD_ETH_ADDR and + * VIRTCHNL_OP_DEL_ETH_ADDR. This allows for the underlying control plane + * function (i.e. PF) to accurately track and use this MAC address for + * displaying on the host and for VM/function reset. + */ + +/* VIRTCHNL_ETHER_ADDR_EXTRA + * All VF drivers should set @type to VIRTCHNL_ETHER_ADDR_EXTRA for any extra + * unicast and/or multicast filters that are being added/deleted via + * VIRTCHNL_OP_DEL_ETH_ADDR/VIRTCHNL_OP_ADD_ETH_ADDR respectively. + */ struct virtchnl_ether_addr { u8 addr[ETH_ALEN]; - u8 pad[2]; + u8 type; +#define VIRTCHNL_ETHER_ADDR_LEGACY 0 +#define VIRTCHNL_ETHER_ADDR_PRIMARY 1 +#define VIRTCHNL_ETHER_ADDR_EXTRA 2 +#define VIRTCHNL_ETHER_ADDR_TYPE_MASK 3 /* first two bits of type are valid */ + u8 pad; }; VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_ether_addr); diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index fff9367a6348..1d7edad9914f 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -154,6 +154,8 @@ struct bdi_writeback { struct cgroup_subsys_state *blkcg_css; /* and blkcg */ struct list_head memcg_node; /* anchored at memcg->cgwb_list */ struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ + struct list_head b_attached; /* attached inodes, protected by list_lock */ + struct list_head offline_node; /* anchored at offline_cgwbs */ union { struct work_struct release_work; @@ -239,8 +241,9 @@ static inline void wb_get(struct bdi_writeback *wb) /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put + * @nr: number of references to put */ -static inline void wb_put(struct bdi_writeback *wb) +static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { if (WARN_ON_ONCE(!wb->bdi)) { /* @@ -251,7 +254,16 @@ static inline void wb_put(struct bdi_writeback *wb) } if (wb != &wb->bdi->wb) - percpu_ref_put(&wb->refcnt); + percpu_ref_put_many(&wb->refcnt, nr); +} + +/** + * wb_put - decrement a wb's refcount + * @wb: bdi_writeback to put + */ +static inline void wb_put(struct bdi_writeback *wb) +{ + wb_put_many(wb, 1); } /** @@ -280,6 +292,10 @@ static inline void wb_put(struct bdi_writeback *wb) { } +static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) +{ +} + static inline bool wb_dying(struct bdi_writeback *wb) { return false; diff --git a/include/linux/bio.h b/include/linux/bio.h index a0b4cfdf62a4..2203b686e1f0 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -44,9 +44,6 @@ static inline unsigned int bio_max_segs(unsigned int nr_segs) #define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter) #define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter) -#define bio_multiple_segments(bio) \ - ((bio)->bi_iter.bi_size != bio_iovec(bio).bv_len) - #define bvec_iter_sectors(iter) ((iter).bi_size >> 9) #define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter))) @@ -271,7 +268,7 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit) static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) { - *bv = bio_iovec(bio); + *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) @@ -279,10 +276,9 @@ static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) struct bvec_iter iter = bio->bi_iter; int idx; - if (unlikely(!bio_multiple_segments(bio))) { - *bv = bio_iovec(bio); - return; - } + bio_get_first_bvec(bio, bv); + if (bv->bv_len == bio->bi_iter.bi_size) + return; /* this bio only has a single bvec */ bio_advance_iter(bio, &iter, iter.bi_size); @@ -822,4 +818,6 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } +struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp); + #endif /* __LINUX_BIO_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 359486940fa0..fd2de2b422ed 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -426,19 +426,29 @@ enum { ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ << BLK_MQ_F_ALLOC_POLICY_START_BIT) +#define blk_mq_alloc_disk(set, queuedata) \ +({ \ + static struct lock_class_key __key; \ + struct gendisk *__disk = __blk_mq_alloc_disk(set, queuedata); \ + \ + if (!IS_ERR(__disk)) \ + lockdep_init_map(&__disk->lockdep_map, \ + "(bio completion)", &__key, 0); \ + __disk; \ +}) +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, + void *queuedata); struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, void *queuedata); -struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, - struct request_queue *q, - bool elevator_init); -struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, - const struct blk_mq_ops *ops, - unsigned int queue_depth, - unsigned int set_flags); +int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, + struct request_queue *q); void blk_mq_unregister_dev(struct device *, struct request_queue *); int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set); +int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, unsigned int queue_depth, + unsigned int set_flags); void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 9ec28fcd3bcc..550d485cfec2 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -29,7 +29,6 @@ struct block_device { int bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; - struct mutex bd_mutex; /* open/close mutex */ void * bd_claiming; struct device bd_device; void * bd_holder; @@ -40,9 +39,6 @@ struct block_device { #endif struct kobject *bd_holder_dir; u8 bd_partno; - /* number of times partitions within this device have been opened. */ - unsigned bd_part_count; - spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; @@ -307,6 +303,7 @@ enum { BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ BIO_TRACKED, /* set if bio goes through the rq_qos path */ BIO_REMAPPED, + BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ BIO_FLAG_LAST }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f69c75bd6d27..103acc5228e7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -25,6 +25,7 @@ #include #include #include +#include struct module; struct scsi_ioctl_command; @@ -493,6 +494,9 @@ struct request_queue { atomic_t nr_active_requests_shared_sbitmap; + struct sbitmap_queue sched_bitmap_tags; + struct sbitmap_queue sched_breserved_tags; + struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); @@ -1008,6 +1012,18 @@ static inline unsigned int blk_rq_stats_sectors(const struct request *rq) /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond); +static inline unsigned int bio_zone_no(struct bio *bio) +{ + return blk_queue_zone_no(bdev_get_queue(bio->bi_bdev), + bio->bi_iter.bi_sector); +} + +static inline unsigned int bio_zone_is_seq(struct bio *bio) +{ + return blk_queue_zone_is_seq(bdev_get_queue(bio->bi_bdev), + bio->bi_iter.bi_sector); +} + static inline unsigned int blk_rq_zone_no(struct request *rq) { return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); @@ -1209,7 +1225,6 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, extern void blk_dump_rq_flags(struct request *, char *); bool __must_check blk_get_queue(struct request_queue *); -struct request_queue *blk_alloc_queue(int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 02b02cb29ce2..f309fc1509f2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -22,6 +22,7 @@ #include #include #include +#include struct bpf_verifier_env; struct bpf_verifier_log; @@ -69,6 +70,8 @@ struct bpf_map_ops { void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); + int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key, + void *value, u64 flags); int (*map_lookup_and_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); @@ -1428,7 +1431,7 @@ struct bpf_iter__bpf_map_elem { int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); -int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); @@ -1459,7 +1462,7 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_get_file_flag(int flags); -int bpf_check_uarg_tail_zero(void __user *uaddr, size_t expected_size, +int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and @@ -1479,8 +1482,7 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) } /* verify correctness of eBPF program */ -int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, - union bpf_attr __user *uattr); +int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr); #ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); @@ -1499,8 +1501,13 @@ int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, + struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); +int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog, struct bpf_map *map, + bool exclude_ingress); bool dev_map_can_have_prog(struct bpf_map *map); void __cpu_map_flush(void); @@ -1668,6 +1675,13 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, return 0; } +static inline +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, + struct bpf_map *map, bool exclude_ingress) +{ + return 0; +} + struct sk_buff; static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, @@ -1677,6 +1691,14 @@ static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, return 0; } +static inline +int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog, struct bpf_map *map, + bool exclude_ingress) +{ + return 0; +} + static inline void __cpu_map_flush(void) { } @@ -1826,6 +1848,9 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map) struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); +int bpf_prog_test_run_syscall(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -1851,6 +1876,13 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) static inline void bpf_map_offload_map_free(struct bpf_map *map) { } + +static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) @@ -1964,6 +1996,7 @@ extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; +extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); @@ -2015,6 +2048,7 @@ struct sk_reuseport_kern { struct sk_buff *skb; struct sock *sk; struct sock *selected_sk; + struct sock *migrating_sk; void *data_end; u32 hash; u32 reuseport_id; diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index b902c580c48d..24496bc28e7b 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -58,7 +58,7 @@ struct bpf_local_storage_data { * from the object's bpf_local_storage. * * Put it in the same cacheline as the data to minimize - * the number of cachelines access during the cache hit case. + * the number of cachelines accessed during the cache hit case. */ struct bpf_local_storage_map __rcu *smap; u8 data[] __aligned(8); @@ -71,7 +71,7 @@ struct bpf_local_storage_elem { struct bpf_local_storage __rcu *local_storage; struct rcu_head rcu; /* 8 bytes hole */ - /* The data is stored in aother cacheline to minimize + /* The data is stored in another cacheline to minimize * the number of cachelines access during a cache hit. */ struct bpf_local_storage_data sdata ____cacheline_aligned; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index f883f01a5061..a9db1eae6796 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -77,6 +77,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LSM, lsm, void *, void *) #endif /* CONFIG_BPF_LSM */ #endif +BPF_PROG_TYPE(BPF_PROG_TYPE_SYSCALL, bpf_syscall, + void *, void *) BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 06841517ab1e..e774ecc1cd1f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -215,6 +215,13 @@ struct bpf_idx_pair { u32 idx; }; +struct bpf_id_pair { + u32 old; + u32 cur; +}; + +/* Maximum number of register states that can exist at once */ +#define BPF_ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) #define MAX_CALL_FRAMES 8 struct bpf_verifier_state { /* call stack tracking */ @@ -418,6 +425,7 @@ struct bpf_verifier_env { const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; + struct bpf_id_pair idmap_scratch[BPF_ID_MAP_SIZE]; struct { int *insn_state; int *insn_stack; @@ -442,6 +450,7 @@ struct bpf_verifier_env { u32 peak_states; /* longest register parentage chain walked for liveness marking */ u32 longest_mark_read_walk; + bpfptr_t fd_array; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h new file mode 100644 index 000000000000..5cdeab497cb3 --- /dev/null +++ b/include/linux/bpfptr.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* A pointer that can point to either kernel or userspace memory. */ +#ifndef _LINUX_BPFPTR_H +#define _LINUX_BPFPTR_H + +#include + +typedef sockptr_t bpfptr_t; + +static inline bool bpfptr_is_kernel(bpfptr_t bpfptr) +{ + return bpfptr.is_kernel; +} + +static inline bpfptr_t KERNEL_BPFPTR(void *p) +{ + return (bpfptr_t) { .kernel = p, .is_kernel = true }; +} + +static inline bpfptr_t USER_BPFPTR(void __user *p) +{ + return (bpfptr_t) { .user = p }; +} + +static inline bpfptr_t make_bpfptr(u64 addr, bool is_kernel) +{ + if (is_kernel) + return KERNEL_BPFPTR((void*) (uintptr_t) addr); + else + return USER_BPFPTR(u64_to_user_ptr(addr)); +} + +static inline bool bpfptr_is_null(bpfptr_t bpfptr) +{ + if (bpfptr_is_kernel(bpfptr)) + return !bpfptr.kernel; + return !bpfptr.user; +} + +static inline void bpfptr_add(bpfptr_t *bpfptr, size_t val) +{ + if (bpfptr_is_kernel(*bpfptr)) + bpfptr->kernel += val; + else + bpfptr->user += val; +} + +static inline int copy_from_bpfptr_offset(void *dst, bpfptr_t src, + size_t offset, size_t size) +{ + return copy_from_sockptr_offset(dst, (sockptr_t) src, offset, size); +} + +static inline int copy_from_bpfptr(void *dst, bpfptr_t src, size_t size) +{ + return copy_from_bpfptr_offset(dst, src, 0, size); +} + +static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, + const void *src, size_t size) +{ + return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size); +} + +static inline void *memdup_bpfptr(bpfptr_t src, size_t len) +{ + return memdup_sockptr((sockptr_t) src, len); +} + +static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) +{ + return strncpy_from_sockptr(dst, (sockptr_t) src, count); +} + +#endif /* _LINUX_BPFPTR_H */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 3bac66e0183a..94a0c976c90f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -21,7 +21,7 @@ extern const struct file_operations btf_fops; void btf_get(struct btf *btf); void btf_put(struct btf *btf); -int btf_new_fd(const union bpf_attr *attr); +int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr); struct btf *btf_get_by_fd(int fd); int btf_get_info_by_fd(const struct btf *btf, const union bpf_attr *attr, diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index d6ab416ee2d2..1d42d4b17327 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -43,6 +43,8 @@ struct module; * @shift: Cycle to nanosecond divisor (power of two) * @max_idle_ns: Maximum idle time permitted by the clocksource (nsecs) * @maxadj: Maximum adjustment value to mult (~11%) + * @uncertainty_margin: Maximum uncertainty in nanoseconds per half second. + * Zero says to use default WATCHDOG_THRESHOLD. * @archdata: Optional arch-specific data * @max_cycles: Maximum safe cycle value which won't overflow on * multiplication @@ -98,6 +100,7 @@ struct clocksource { u32 shift; u64 max_idle_ns; u32 maxadj; + u32 uncertainty_margin; #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA struct arch_clocksource_data archdata; #endif @@ -137,7 +140,7 @@ struct clocksource { #define CLOCK_SOURCE_UNSTABLE 0x40 #define CLOCK_SOURCE_SUSPEND_NONSTOP 0x80 #define CLOCK_SOURCE_RESELECT 0x100 - +#define CLOCK_SOURCE_VERIFY_PERCPU 0x200 /* simplify initialization of mask field */ #define CLOCKSOURCE_MASK(bits) GENMASK_ULL((bits) - 1, 0) @@ -288,4 +291,7 @@ static inline void timer_probe(void) {} #define TIMER_ACPI_DECLARE(name, table_id, fn) \ ACPI_DECLARE_PROBE_ENTRY(timer, name, table_id, 0, NULL, 0, fn) +extern ulong max_cswd_read_retries; +void clocksource_verify_percpu(struct clocksource *cs); + #endif /* _LINUX_CLOCKSOURCE_H */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 77047904cf70..b67261a1e3e9 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -219,6 +219,16 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, __v; \ }) +/* + * With CONFIG_CFI_CLANG, the compiler replaces function addresses in + * instrumented C code with jump table addresses. Architectures that + * support CFI can define this macro to return the actual function address + * when needed. + */ +#ifndef function_nocfi +#define function_nocfi(x) (x) +#endif + #endif /* __KERNEL__ */ /* diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 183ddd5fd072..2487be0e7199 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -27,15 +27,16 @@ */ #ifndef __has_attribute # define __has_attribute(x) __GCC4_has_attribute_##x -# define __GCC4_has_attribute___assume_aligned__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___assume_aligned__ 1 # define __GCC4_has_attribute___copy__ 0 # define __GCC4_has_attribute___designated_init__ 0 # define __GCC4_has_attribute___externally_visible__ 1 # define __GCC4_has_attribute___no_caller_saved_registers__ 0 # define __GCC4_has_attribute___noclone__ 1 +# define __GCC4_has_attribute___no_profile_instrument_function__ 0 # define __GCC4_has_attribute___nonstring__ 0 -# define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) -# define __GCC4_has_attribute___no_sanitize_undefined__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___no_sanitize_address__ 1 +# define __GCC4_has_attribute___no_sanitize_undefined__ 1 # define __GCC4_has_attribute___fallthrough__ 0 #endif @@ -238,6 +239,18 @@ # define __nonstring #endif +/* + * Optional: only supported since GCC >= 7.1, clang >= 13.0. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-no_005fprofile_005finstrument_005ffunction-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#no-profile-instrument-function + */ +#if __has_attribute(__no_profile_instrument_function__) +# define __no_profile __attribute__((__no_profile_instrument_function__)) +#else +# define __no_profile +#endif + /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noreturn-function-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#noreturn diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index d29bda7f6ebd..d509169860f1 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -210,7 +210,7 @@ struct ftrace_likely_data { /* Section for code which can't be instrumented at all */ #define noinstr \ noinline notrace __attribute((__section__(".noinstr.text"))) \ - __no_kcsan __no_sanitize_address + __no_kcsan __no_sanitize_address __no_profile #endif /* __KERNEL__ */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 4a62b3980642..47e13582d9fc 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -54,7 +54,7 @@ enum cpuhp_state { CPUHP_MM_MEMCQ_DEAD, CPUHP_PERCPU_CNT_DEAD, CPUHP_RADIX_DEAD, - CPUHP_PAGE_ALLOC_DEAD, + CPUHP_PAGE_ALLOC, CPUHP_NET_DEV_DEAD, CPUHP_PCI_XGENE_DEAD, CPUHP_IOMMU_IOVA_DEAD, diff --git a/include/linux/cred.h b/include/linux/cred.h index 14971322e1a0..fcbc6885cc09 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -143,6 +143,7 @@ struct cred { #endif struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ + struct ucounts *ucounts; struct group_info *group_info; /* supplementary groups for euid/fsgid */ /* RCU deletion */ union { @@ -169,6 +170,7 @@ extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); +extern int set_cred_ucounts(struct cred *); /* * check for validity of credentials @@ -369,6 +371,7 @@ static inline void put_cred(const struct cred *_cred) #define task_uid(task) (task_cred_xxx((task), uid)) #define task_euid(task) (task_cred_xxx((task), euid)) +#define task_ucounts(task) (task_cred_xxx((task), ucounts)) #define current_cred_xxx(xxx) \ ({ \ @@ -385,6 +388,7 @@ static inline void put_cred(const struct cred *_cred) #define current_fsgid() (current_cred_xxx(fsgid)) #define current_cap() (current_cred_xxx(cap_effective)) #define current_user() (current_cred_xxx(user)) +#define current_ucounts() (current_cred_xxx(ucounts)) extern struct user_namespace init_user_ns; #ifdef CONFIG_USER_NS diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 6f009559ee54..82d3d46005a1 100644 --- a/include/linux/dev_printk.h +++ b/include/linux/dev_printk.h @@ -236,7 +236,7 @@ do { \ * using WARN/WARN_ONCE to include file/line information and a backtrace. */ #define dev_WARN(dev, format, arg...) \ - WARN(1, "%s %s: " format, dev_driver_string(dev), dev_name(dev), ## arg); + WARN(1, "%s %s: " format, dev_driver_string(dev), dev_name(dev), ## arg) #define dev_WARN_ONCE(dev, condition, format, arg...) \ WARN_ONCE(condition, "%s %s: " format, \ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index ff700fb6ce1d..7457d49acf9a 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -361,6 +361,12 @@ struct dm_target { * Set if we need to limit the number of in-flight bios when swapping. */ bool limit_swap_bios:1; + + /* + * Set if this target implements a a zoned device and needs emulation of + * zone append operations using regular writes. + */ + bool emulate_zone_append:1; }; void *dm_per_bio_data(struct bio *bio, size_t data_size); @@ -478,7 +484,8 @@ struct dm_report_zones_args { /* must be filled by ->report_zones before calling dm_report_zones_cb */ sector_t start; }; -int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data); +int dm_report_zones(struct block_device *bdev, sector_t start, sector_t sector, + struct dm_report_zones_args *args, unsigned int nr_zones); #endif /* CONFIG_BLK_DEV_ZONED */ /* diff --git a/include/linux/device.h b/include/linux/device.h index 959cb9d2c9ab..4cd200f8b47a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -817,6 +817,7 @@ int device_online(struct device *dev); void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); +void device_set_node(struct device *dev, struct fwnode_handle *fwnode); static inline int dev_num_vf(struct device *dev) { diff --git a/include/linux/devm-helpers.h b/include/linux/devm-helpers.h index f40f77717a24..74891802200d 100644 --- a/include/linux/devm-helpers.h +++ b/include/linux/devm-helpers.h @@ -51,4 +51,29 @@ static inline int devm_delayed_work_autocancel(struct device *dev, return devm_add_action(dev, devm_delayed_work_drop, w); } +static inline void devm_work_drop(void *res) +{ + cancel_work_sync(res); +} + +/** + * devm_work_autocancel - Resource-managed work allocation + * @dev: Device which lifetime work is bound to + * @w: Work to be added (and automatically cancelled) + * @worker: Worker function + * + * Initialize work which is automatically cancelled when driver is detached. + * A few drivers need to queue work which must be cancelled before driver + * is detached to avoid accessing removed resources. + * devm_work_autocancel() can be used to omit the explicit + * cancelleation when driver is detached. + */ +static inline int devm_work_autocancel(struct device *dev, + struct work_struct *w, + work_func_t worker) +{ + INIT_WORK(w, worker); + return devm_add_action(dev, devm_work_drop, w); +} + #endif diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index e42de7750c88..c1707ee5b540 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -51,6 +51,7 @@ MODULE_PARM_DESC(name, description) struct dm_kcopyd_client; struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *throttle); void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc); +void dm_kcopyd_client_flush(struct dm_kcopyd_client *kc); /* * Submit a copy job to kcopyd. This is built on top of the diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index b12b05f1c8b4..1587961f1a7b 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -37,8 +37,6 @@ struct dsa_8021q_context { #define DSA_8021Q_N_SUBVLAN 8 -#if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) - int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, @@ -52,6 +50,9 @@ int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *subvlan); + u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); @@ -70,78 +71,4 @@ bool vid_is_dsa_8021q_txvlan(u16 vid); bool vid_is_dsa_8021q(u16 vid); -#else - -int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled) -{ - return 0; -} - -int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) -{ - return 0; -} - -int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) -{ - return 0; -} - -struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, - u16 tpid, u16 tci) -{ - return NULL; -} - -u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) -{ - return 0; -} - -u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) -{ - return 0; -} - -u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan) -{ - return 0; -} - -int dsa_8021q_rx_switch_id(u16 vid) -{ - return 0; -} - -int dsa_8021q_rx_source_port(u16 vid) -{ - return 0; -} - -u16 dsa_8021q_rx_subvlan(u16 vid) -{ - return 0; -} - -bool vid_is_dsa_8021q_rxvlan(u16 vid) -{ - return false; -} - -bool vid_is_dsa_8021q_txvlan(u16 vid) -{ - return false; -} - -bool vid_is_dsa_8021q(u16 vid) -{ - return false; -} - -#endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */ - #endif /* _NET_DSA_8021Q_H */ diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 1eb84562b311..b6089b88314c 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -14,6 +14,7 @@ #define ETH_P_SJA1105 ETH_P_DSA_8021Q #define ETH_P_SJA1105_META 0x0008 +#define ETH_P_SJA1110 0xdadc /* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */ #define SJA1105_LINKLOCAL_FILTER_A 0x0180C2000000ull @@ -44,11 +45,14 @@ struct sja1105_tagger_data { */ spinlock_t meta_lock; unsigned long state; + u8 ts_id; }; struct sja1105_skb_cb { struct sk_buff *clone; - u32 meta_tstamp; + u64 tstamp; + /* Only valid for packets cloned for 2-step TX timestamping */ + u8 ts_id; }; #define SJA1105_SKB_CB(skb) \ @@ -65,4 +69,24 @@ struct sja1105_port { u16 xmit_tpid; }; +enum sja1110_meta_tstamp { + SJA1110_META_TSTAMP_TX = 0, + SJA1110_META_TSTAMP_RX = 1, +}; + +#if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) + +void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp); + +#else + +static inline void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, + u8 ts_id, enum sja1110_meta_tstamp dir, + u64 tstamp) +{ +} + +#endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ + #endif /* _NET_DSA_SJA1105_H */ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index dcb2f9022c1d..ef9ceead3db1 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -117,9 +117,11 @@ extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); extern void elv_merged_request(struct request_queue *, struct request *, enum elv_merge); -extern bool elv_attempt_insert_merge(struct request_queue *, struct request *); +extern bool elv_attempt_insert_merge(struct request_queue *, struct request *, + struct list_head *); extern struct request *elv_former_request(struct request_queue *, struct request *); extern struct request *elv_latter_request(struct request_queue *, struct request *); +void elevator_init_mq(struct request_queue *q); /* * io scheduler registration diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e030f7510cd3..29dbb603bc91 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -401,12 +401,12 @@ struct ethtool_rmon_stats { * required information to the driver. */ struct ethtool_module_eeprom { - __u32 offset; - __u32 length; - __u8 page; - __u8 bank; - __u8 i2c_address; - __u8 *data; + u32 offset; + u32 length; + u8 page; + u8 bank; + u8 i2c_address; + u8 *data; }; /** diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h index 766fcd973beb..a332e79b3207 100644 --- a/include/linux/fcntl.h +++ b/include/linux/fcntl.h @@ -12,10 +12,6 @@ FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \ O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE) -/* List of all valid flags for the how->upgrade_mask argument: */ -#define VALID_UPGRADE_FLAGS \ - (UPGRADE_NOWRITE | UPGRADE_NOREAD) - /* List of all valid flags for the how->resolve argument: */ #define VALID_RESOLVE_FLAGS \ (RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \ diff --git a/include/linux/filter.h b/include/linux/filter.h index 9a09547bc7ba..472f97074da0 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -646,6 +646,7 @@ struct bpf_redirect_info { u32 flags; u32 tgt_index; void *tgt_value; + struct bpf_map *map; u32 map_id; enum bpf_map_type map_type; u32 kern_flags; @@ -762,11 +763,9 @@ DECLARE_BPF_DISPATCHER(xdp) static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { - /* Caller needs to hold rcu_read_lock() (!), otherwise program - * can be released while still running, or map elements could be - * freed early while still having concurrent users. XDP fastpath - * already takes rcu_read_lock() when fetching the program, so - * it's not necessary here anymore. + /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus + * under local_bh_disable(), which provides the needed RCU protection + * for accessing map entries. */ return __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); } @@ -995,11 +994,13 @@ void bpf_warn_invalid_xdp_action(u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash); #else static inline struct sock * bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { return NULL; @@ -1464,17 +1465,19 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, } #endif /* IS_ENABLED(CONFIG_IPV6) */ -static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, u64 flags, +static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, + u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; /* Lower bits of the flags are used as return code on lookup failure */ - if (unlikely(flags > XDP_TX)) + if (unlikely(flags & ~(action_mask | flag_mask))) return XDP_ABORTED; ri->tgt_value = lookup_elem(map, ifindex); - if (unlikely(!ri->tgt_value)) { + if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) { /* If the lookup fails we want to clear out the state in the * redirect_info struct completely, so that if an eBPF program * performs multiple lookups, the last one always takes @@ -1482,13 +1485,21 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind */ ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; - return flags; + return flags & action_mask; } ri->tgt_index = ifindex; ri->map_id = map->id; ri->map_type = map->map_type; + if (flags & BPF_F_BROADCAST) { + WRITE_ONCE(ri->map, map); + ri->flags = flags; + } else { + WRITE_ONCE(ri->map, NULL); + ri->flags = 0; + } + return XDP_REDIRECT; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 506d205a8ce6..ecb723adafc6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2171,7 +2171,6 @@ struct super_operations { ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot **(*get_dquots)(struct inode *); #endif - int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, @@ -3417,18 +3416,14 @@ extern int simple_rename(struct user_namespace *, struct inode *, extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); -extern int noop_set_page_dirty(struct page *page); extern void noop_invalidatepage(struct page *page, unsigned int offset, unsigned int length); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); -extern int simple_readpage(struct file *file, struct page *page); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); -extern int simple_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); +extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); extern int simple_nosetlease(struct file *, long, struct file_lock **, void **); diff --git a/include/linux/fwnode_mdio.h b/include/linux/fwnode_mdio.h new file mode 100644 index 000000000000..faf603c48c86 --- /dev/null +++ b/include/linux/fwnode_mdio.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * FWNODE helper for the MDIO (Ethernet PHY) API + */ + +#ifndef __LINUX_FWNODE_MDIO_H +#define __LINUX_FWNODE_MDIO_H + +#include + +#if IS_ENABLED(CONFIG_FWNODE_MDIO) +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr); + +int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, u32 addr); + +#else /* CONFIG_FWNODE_MDIO */ +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr) +{ + return -EINVAL; +} + +static inline int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, + u32 addr) +{ + return -EINVAL; +} +#endif + +#endif /* __LINUX_FWNODE_MDIO_H */ diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6fc26f7bdf71..13b34177cc85 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -153,6 +153,11 @@ struct gendisk { unsigned long state; #define GD_NEED_PART_SCAN 0 #define GD_READ_ONLY 1 +#define GD_QUEUE_REF 2 + + struct mutex open_mutex; /* open/close mutex */ + unsigned open_partitions; /* number of open partitions */ + struct kobject *slave_dir; struct timer_rand_state *random; @@ -218,7 +223,6 @@ static inline void add_disk_no_queue_reg(struct gendisk *disk) } extern void del_gendisk(struct gendisk *gp); -extern struct block_device *bdget_disk(struct gendisk *disk, int partno); void set_disk_ro(struct gendisk *disk, bool read_only); @@ -252,8 +256,7 @@ static inline sector_t get_capacity(struct gendisk *disk) return bdev_nr_sectors(disk->part0); } -int bdev_disk_changed(struct block_device *bdev, bool invalidate); -int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); +int bdev_disk_changed(struct gendisk *disk, bool invalidate); void blk_drop_partitions(struct gendisk *disk); extern struct gendisk *__alloc_disk_node(int minors, int node_id); @@ -277,6 +280,28 @@ extern void put_disk(struct gendisk *disk); #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) +/** + * blk_alloc_disk - allocate a gendisk structure + * @node_id: numa node to allocate on + * + * Allocate and pre-initialize a gendisk structure for use with BIO based + * drivers. + * + * Context: can sleep + */ +#define blk_alloc_disk(node_id) \ +({ \ + struct gendisk *__disk = __blk_alloc_disk(node_id); \ + static struct lock_class_key __key; \ + \ + if (__disk) \ + lockdep_init_map(&__disk->lockdep_map, \ + "(bio completion)", &__key, 0); \ + __disk; \ +}) +struct gendisk *__blk_alloc_disk(int node); +void blk_cleanup_disk(struct gendisk *disk); + int __register_blkdev(unsigned int major, const char *name, void (*probe)(dev_t devt)); #define register_blkdev(major, name) \ @@ -306,6 +331,7 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, } #endif /* CONFIG_SYSFS */ +dev_t part_devt(struct gendisk *disk, u8 partno); dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); #ifdef CONFIG_BLOCK diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 8eca80fe154d..be56885a22bd 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -497,8 +497,8 @@ static inline int gfp_zonelist(gfp_t flags) * There are two zonelists per node, one for all zones with memory and * one containing just zones from the node the zonelist belongs to. * - * For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets - * optimized to &contig_page_data at compile-time. + * For the case of non-NUMA systems the NODE_DATA() gets optimized to + * &contig_page_data at compile-time. */ static inline struct zonelist *node_zonelist(int nid, gfp_t flags) { @@ -539,6 +539,15 @@ alloc_pages_bulk_array(gfp_t gfp, unsigned long nr_pages, struct page **page_arr return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, NULL, page_array); } +static inline unsigned long +alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array) +{ + if (nid == NUMA_NO_NODE) + nid = numa_mem_id(); + + return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array); +} + /* * Allocate pages, preferring the node given as nid. The node must be valid and * online. For more general interface, see alloc_pages_node(). diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index c73b25bc9213..566feb56601f 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -692,6 +692,8 @@ int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); void devm_acpi_dev_remove_driver_gpios(struct device *dev); +struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label); + #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ struct acpi_device; diff --git a/include/linux/hid.h b/include/linux/hid.h index 10e922cee4eb..9e067f937dbc 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -102,6 +102,7 @@ struct hid_item { #define HID_COLLECTION_PHYSICAL 0 #define HID_COLLECTION_APPLICATION 1 #define HID_COLLECTION_LOGICAL 2 +#define HID_COLLECTION_NAMED_ARRAY 4 /* * HID report descriptor global item tags @@ -800,6 +801,7 @@ struct hid_driver { * @raw_request: send raw report request to device (e.g. feature report) * @output_report: send output report to device * @idle: send idle request to device + * @may_wakeup: return if device may act as a wakeup source during system-suspend */ struct hid_ll_driver { int (*start)(struct hid_device *hdev); @@ -824,6 +826,7 @@ struct hid_ll_driver { int (*output_report) (struct hid_device *hdev, __u8 *buf, size_t len); int (*idle)(struct hid_device *hdev, int report, int idle, int reqtype); + bool (*may_wakeup)(struct hid_device *hdev); }; extern struct hid_ll_driver i2c_hid_ll_driver; @@ -1149,6 +1152,22 @@ static inline int hid_hw_idle(struct hid_device *hdev, int report, int idle, return 0; } +/** + * hid_may_wakeup - return if the hid device may act as a wakeup source during system-suspend + * + * @hdev: hid device + */ +static inline bool hid_hw_may_wakeup(struct hid_device *hdev) +{ + if (hdev->ll_driver->may_wakeup) + return hdev->ll_driver->may_wakeup(hdev); + + if (hdev->dev.parent) + return device_may_wakeup(hdev->dev.parent); + + return false; +} + /** * hid_hw_wait - wait for buffered io to complete * diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3c0117656745..8ba79dc64ab8 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -451,7 +451,7 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, - struct user_struct **user, int creat_flags, + struct ucounts **ucounts, int creat_flags, int page_size_log); static inline bool is_file_hugepages(struct file *file) @@ -471,7 +471,7 @@ static inline struct hstate *hstate_inode(struct inode *i) #define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, - struct user_struct **user, int creat_flags, + struct ucounts **ucounts, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index d1e59dbef1dd..2e859d2f9609 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -181,6 +181,10 @@ struct hv_ring_buffer_info { * being freed while the ring buffer is being accessed. */ struct mutex ring_buffer_mutex; + + /* Buffer that holds a copy of an incoming host packet */ + void *pkt_buffer; + u32 pkt_buffer_size; }; @@ -790,7 +794,11 @@ struct vmbus_requestor { #define VMBUS_NO_RQSTOR U64_MAX #define VMBUS_RQST_ERROR (U64_MAX - 1) +/* NetVSC-specific */ #define VMBUS_RQST_ID_NO_RESPONSE (U64_MAX - 2) +/* StorVSC-specific */ +#define VMBUS_RQST_INIT (U64_MAX - 2) +#define VMBUS_RQST_RESET (U64_MAX - 3) struct vmbus_device { u16 dev_type; @@ -799,6 +807,8 @@ struct vmbus_device { bool allowed_in_isolated; }; +#define VMBUS_DEFAULT_MAX_PKT_SIZE 4096 + struct vmbus_channel { struct list_head listentry; @@ -1018,13 +1028,21 @@ struct vmbus_channel { u32 fuzz_testing_interrupt_delay; u32 fuzz_testing_message_delay; + /* callback to generate a request ID from a request address */ + u64 (*next_request_id_callback)(struct vmbus_channel *channel, u64 rqst_addr); + /* callback to retrieve a request address from a request ID */ + u64 (*request_addr_callback)(struct vmbus_channel *channel, u64 rqst_id); + /* request/transaction ids for VMBus */ struct vmbus_requestor requestor; u32 rqstor_size; + + /* The max size of a packet on this channel */ + u32 max_pkt_size; }; -u64 vmbus_next_request_id(struct vmbus_requestor *rqstor, u64 rqst_addr); -u64 vmbus_request_addr(struct vmbus_requestor *rqstor, u64 trans_id); +u64 vmbus_next_request_id(struct vmbus_channel *channel, u64 rqst_addr); +u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id); static inline bool is_hvsock_channel(const struct vmbus_channel *c) { @@ -1662,15 +1680,44 @@ static inline u32 hv_pkt_datalen(const struct vmpacket_descriptor *desc) } +struct vmpacket_descriptor * +hv_pkt_iter_first_raw(struct vmbus_channel *channel); + struct vmpacket_descriptor * hv_pkt_iter_first(struct vmbus_channel *channel); struct vmpacket_descriptor * __hv_pkt_iter_next(struct vmbus_channel *channel, - const struct vmpacket_descriptor *pkt); + const struct vmpacket_descriptor *pkt, + bool copy); void hv_pkt_iter_close(struct vmbus_channel *channel); +static inline struct vmpacket_descriptor * +hv_pkt_iter_next_pkt(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt, + bool copy) +{ + struct vmpacket_descriptor *nxt; + + nxt = __hv_pkt_iter_next(channel, pkt, copy); + if (!nxt) + hv_pkt_iter_close(channel); + + return nxt; +} + +/* + * Get next packet descriptor without copying it out of the ring buffer + * If at end of list, return NULL and update host. + */ +static inline struct vmpacket_descriptor * +hv_pkt_iter_next_raw(struct vmbus_channel *channel, + const struct vmpacket_descriptor *pkt) +{ + return hv_pkt_iter_next_pkt(channel, pkt, false); +} + /* * Get next packet descriptor from iterator * If at end of list, return NULL and update host. @@ -1679,13 +1726,7 @@ static inline struct vmpacket_descriptor * hv_pkt_iter_next(struct vmbus_channel *channel, const struct vmpacket_descriptor *pkt) { - struct vmpacket_descriptor *nxt; - - nxt = __hv_pkt_iter_next(channel, pkt); - if (!nxt) - hv_pkt_iter_close(channel); - - return nxt; + return hv_pkt_iter_next_pkt(channel, pkt, true); } #define foreach_vmbus_pkt(pkt, channel) \ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2967437f1b11..a6730072d13a 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -9,7 +9,7 @@ * Copyright (c) 2006, Michael Wu * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH - * Copyright (c) 2018 - 2020 Intel Corporation + * Copyright (c) 2018 - 2021 Intel Corporation */ #ifndef LINUX_IEEE80211_H @@ -2179,6 +2179,8 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED 0xc0 #define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK 0xc0 +#define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF 0x01 + /* 802.11ax HE TX/RX MCS NSS Support */ #define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) #define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6) @@ -2933,6 +2935,7 @@ enum ieee80211_category { WLAN_CATEGORY_BACK = 3, WLAN_CATEGORY_PUBLIC = 4, WLAN_CATEGORY_RADIO_MEASUREMENT = 5, + WLAN_CATEGORY_FAST_BBS_TRANSITION = 6, WLAN_CATEGORY_HT = 7, WLAN_CATEGORY_SA_QUERY = 8, WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION = 9, @@ -3110,6 +3113,11 @@ enum ieee80211_tdls_actioncode { */ #define WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT BIT(6) +/* Timing Measurement protocol for time sync is set in the 7th bit of 3rd byte + * of the @WLAN_EID_EXT_CAPABILITY information element + */ +#define WLAN_EXT_CAPA3_TIMING_MEASUREMENT_SUPPORT BIT(7) + /* TDLS capabilities in the 4th byte of @WLAN_EID_EXT_CAPABILITY */ #define WLAN_EXT_CAPA4_TDLS_BUFFER_STA BIT(4) #define WLAN_EXT_CAPA4_TDLS_PEER_PSM BIT(5) diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index bf5c5f32c65e..b712217f7030 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -48,6 +48,7 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: + case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: case ARPHRD_RAWIP: diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 2cc35038a8ca..b651c5e32a28 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -67,10 +67,12 @@ int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list); bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto); bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto); +bool br_multicast_has_router_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); bool br_multicast_router(const struct net_device *dev); int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack); + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack); #else static inline int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) @@ -87,6 +89,13 @@ static inline bool br_multicast_has_querier_adjacent(struct net_device *dev, { return false; } + +static inline bool br_multicast_has_router_adjacent(struct net_device *dev, + int proto) +{ + return true; +} + static inline bool br_multicast_enabled(const struct net_device *dev) { return false; @@ -95,9 +104,9 @@ static inline bool br_multicast_router(const struct net_device *dev) { return false; } -static inline int br_mdb_replay(struct net_device *br_dev, - struct net_device *dev, - struct notifier_block *nb, +static inline int br_mdb_replay(const struct net_device *br_dev, + const struct net_device *dev, const void *ctx, + bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; @@ -112,7 +121,8 @@ int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto); int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack); + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack); #else static inline bool br_vlan_enabled(const struct net_device *dev) { @@ -141,8 +151,8 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, } static inline int br_vlan_replay(struct net_device *br_dev, - struct net_device *dev, - struct notifier_block *nb, + struct net_device *dev, const void *ctx, + bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; @@ -156,9 +166,9 @@ struct net_device *br_fdb_find_port(const struct net_device *br_dev, void br_fdb_clear_offload(const struct net_device *dev, u16 vid); bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); u8 br_port_get_stp_state(const struct net_device *dev); -clock_t br_get_ageing_time(struct net_device *br_dev); -int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb); +clock_t br_get_ageing_time(const struct net_device *br_dev); +int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, + const void *ctx, bool adding, struct notifier_block *nb); #else static inline struct net_device * br_fdb_find_port(const struct net_device *br_dev, @@ -183,14 +193,14 @@ static inline u8 br_port_get_stp_state(const struct net_device *dev) return BR_STATE_DISABLED; } -static inline clock_t br_get_ageing_time(struct net_device *br_dev) +static inline clock_t br_get_ageing_time(const struct net_device *br_dev) { return 0; } -static inline int br_fdb_replay(struct net_device *br_dev, - struct net_device *dev, - struct notifier_block *nb) +static inline int br_fdb_replay(const struct net_device *br_dev, + const struct net_device *dev, const void *ctx, + bool adding, struct notifier_block *nb) { return -EOPNOTSUPP; } diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index 4efb537f57f3..10e7521ecb6c 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only - * Copyright (c) 2013-2019, The Linux Foundation. All rights reserved. + * Copyright (c) 2013-2019, 2021 The Linux Foundation. All rights reserved. */ #ifndef _LINUX_IF_RMNET_H_ @@ -12,10 +12,12 @@ struct rmnet_map_header { } __aligned(1); /* rmnet_map_header flags field: - * PAD_LEN: number of pad bytes following packet data - * CMD: 1 = packet contains a MAP command; 0 = packet contains data + * PAD_LEN: number of pad bytes following packet data + * CMD: 1 = packet contains a MAP command; 0 = packet contains data + * NEXT_HEADER: 1 = packet contains V5 CSUM header 0 = no V5 CSUM header */ #define MAP_PAD_LEN_MASK GENMASK(5, 0) +#define MAP_NEXT_HEADER_FLAG BIT(6) #define MAP_CMD_FLAG BIT(7) struct rmnet_map_dl_csum_trailer { @@ -23,7 +25,7 @@ struct rmnet_map_dl_csum_trailer { u8 flags; /* MAP_CSUM_DL_VALID_FLAG */ __be16 csum_start_offset; __be16 csum_length; - __be16 csum_value; + __sum16 csum_value; } __aligned(1); /* rmnet_map_dl_csum_trailer flags field: @@ -45,4 +47,26 @@ struct rmnet_map_ul_csum_header { #define MAP_CSUM_UL_UDP_FLAG BIT(14) #define MAP_CSUM_UL_ENABLED_FLAG BIT(15) +/* MAP CSUM headers */ +struct rmnet_map_v5_csum_header { + u8 header_info; + u8 csum_info; + __be16 reserved; +} __aligned(1); + +/* v5 header_info field + * NEXT_HEADER: represents whether there is any next header + * HEADER_TYPE: represents the type of this header + * + * csum_info field + * CSUM_VALID_OR_REQ: + * 1 = for UL, checksum computation is requested. + * 1 = for DL, validated the checksum and has found it valid + */ + +#define MAPV5_HDRINFO_NXT_HDR_FLAG BIT(0) +#define MAPV5_HDRINFO_HDR_TYPE_FMASK GENMASK(7, 1) +#define MAPV5_CSUMINFO_VALID_FLAG BIT(7) + +#define RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD 2 #endif /* !(_LINUX_IF_RMNET_H_) */ diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 0d6b4bc191c5..25e2b4e80502 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -8,11 +8,17 @@ #ifndef _INTEL_ISH_CLIENT_IF_H_ #define _INTEL_ISH_CLIENT_IF_H_ +#include +#include + struct ishtp_cl_device; struct ishtp_device; struct ishtp_cl; struct ishtp_fw_client; +typedef __printf(2, 3) void (*ishtp_print_log)(struct ishtp_device *dev, + const char *format, ...); + /* Client state */ enum cl_state { ISHTP_CL_INITIALIZING = 0, @@ -36,7 +42,7 @@ struct ishtp_cl_driver { const char *name; const guid_t *guid; int (*probe)(struct ishtp_cl_device *dev); - int (*remove)(struct ishtp_cl_device *dev); + void (*remove)(struct ishtp_cl_device *dev); int (*reset)(struct ishtp_cl_device *dev); const struct dev_pm_ops *pm; }; @@ -76,7 +82,7 @@ int ishtp_register_event_cb(struct ishtp_cl_device *device, /* Get the device * from ishtp device instance */ struct device *ishtp_device(struct ishtp_cl_device *cl_device); /* Trace interface for clients */ -void *ishtp_trace_callback(struct ishtp_cl_device *cl_device); +ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device); /* Get device pointer of PCI device for DMA acces */ struct device *ishtp_get_pci_device(struct ishtp_cl_device *cl_device); diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 35a374241515..2ed65b01c961 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -64,6 +64,8 @@ * IRQF_NO_AUTOEN - Don't enable IRQ or NMI automatically when users request it. * Users will enable it explicitly by enable_irq() or enable_nmi() * later. + * IRQF_NO_DEBUG - Exclude from runnaway detection for IPI and similar handlers, + * depends on IRQF_PERCPU. */ #define IRQF_SHARED 0x00000080 #define IRQF_PROBE_SHARED 0x00000100 @@ -78,6 +80,7 @@ #define IRQF_EARLY_RESUME 0x00020000 #define IRQF_COND_SUSPEND 0x00040000 #define IRQF_NO_AUTOEN 0x00080000 +#define IRQF_NO_DEBUG 0x00100000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) diff --git a/include/linux/iomap.h b/include/linux/iomap.h index c87d0cb0de6d..479c1da3e221 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -159,7 +159,6 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops); int iomap_readpage(struct page *page, const struct iomap_ops *ops); void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); -int iomap_set_page_dirty(struct page *page); int iomap_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count); int iomap_releasepage(struct page *page, gfp_t gfp_mask); diff --git a/include/linux/irq.h b/include/linux/irq.h index 31b347c9f8dd..8e9a9ae471a6 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -72,6 +72,7 @@ enum irqchip_irq_state; * mechanism and from core side polling. * IRQ_DISABLE_UNLAZY - Disable lazy irq disable * IRQ_HIDDEN - Don't show up in /proc/interrupts + * IRQ_NO_DEBUG - Exclude from note_interrupt() debugging */ enum { IRQ_TYPE_NONE = 0x00000000, @@ -99,6 +100,7 @@ enum { IRQ_IS_POLLED = (1 << 18), IRQ_DISABLE_UNLAZY = (1 << 19), IRQ_HIDDEN = (1 << 20), + IRQ_NO_DEBUG = (1 << 21), }; #define IRQF_MODIFY_MASK \ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index df4651250785..59aea39785bf 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -158,25 +158,21 @@ static inline void generic_handle_irq_desc(struct irq_desc *desc) desc->handle_irq(desc); } +int handle_irq_desc(struct irq_desc *desc); int generic_handle_irq(unsigned int irq); -#ifdef CONFIG_HANDLE_DOMAIN_IRQ +#ifdef CONFIG_IRQ_DOMAIN /* * Convert a HW interrupt number to a logical one using a IRQ domain, * and handle the result interrupt number. Return -EINVAL if - * conversion failed. Providing a NULL domain indicates that the - * conversion has already been done. + * conversion failed. */ -int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq, - bool lookup, struct pt_regs *regs); +int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq); -static inline int handle_domain_irq(struct irq_domain *domain, - unsigned int hwirq, struct pt_regs *regs) -{ - return __handle_domain_irq(domain, hwirq, true, regs); -} +#ifdef CONFIG_HANDLE_DOMAIN_IRQ +int handle_domain_irq(struct irq_domain *domain, + unsigned int hwirq, struct pt_regs *regs); -#ifdef CONFIG_IRQ_DOMAIN int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq, struct pt_regs *regs); #endif diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 62a8e3d23829..23e4ee523576 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -41,13 +41,11 @@ struct fwnode_handle; struct irq_domain; struct irq_chip; struct irq_data; +struct irq_desc; struct cpumask; struct seq_file; struct irq_affinity_desc; -/* Number of irqs reserved for a legacy isa controller */ -#define NUM_ISA_INTERRUPTS 16 - #define IRQ_DOMAIN_IRQ_SPEC_PARAMS 16 /** @@ -152,11 +150,10 @@ struct irq_domain_chip_generic; * @parent: Pointer to parent irq_domain to support hierarchy irq_domains * * Revmap data, used internally by irq_domain - * @revmap_direct_max_irq: The largest hwirq that can be set for controllers that - * support direct mapping - * @revmap_size: Size of the linear map table @linear_revmap[] + * @revmap_size: Size of the linear map table @revmap[] * @revmap_tree: Radix map tree for hwirqs that don't fit in the linear map - * @linear_revmap: Linear table of hwirq->virq reverse mappings + * @revmap_mutex: Lock for the revmap + * @revmap: Linear table of irq_data pointers */ struct irq_domain { struct list_head link; @@ -176,11 +173,10 @@ struct irq_domain { /* reverse map data. The linear map gets appended to the irq_domain */ irq_hw_number_t hwirq_max; - unsigned int revmap_direct_max_irq; unsigned int revmap_size; struct radix_tree_root revmap_tree; - struct mutex revmap_tree_mutex; - unsigned int linear_revmap[]; + struct mutex revmap_mutex; + struct irq_data __rcu *revmap[]; }; /* Irq domain flags */ @@ -210,6 +206,9 @@ enum { */ IRQ_DOMAIN_MSI_NOMASK_QUIRK = (1 << 6), + /* Irq domain doesn't translate anything */ + IRQ_DOMAIN_FLAG_NO_MAP = (1 << 7), + /* * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved * for implementation specific purposes and ignored by the @@ -348,6 +347,8 @@ static inline struct irq_domain *irq_domain_add_linear(struct device_node *of_no { return __irq_domain_add(of_node_to_fwnode(of_node), size, size, 0, ops, host_data); } + +#ifdef CONFIG_IRQ_DOMAIN_NOMAP static inline struct irq_domain *irq_domain_add_nomap(struct device_node *of_node, unsigned int max_irq, const struct irq_domain_ops *ops, @@ -355,14 +356,10 @@ static inline struct irq_domain *irq_domain_add_nomap(struct device_node *of_nod { return __irq_domain_add(of_node_to_fwnode(of_node), 0, max_irq, max_irq, ops, host_data); } -static inline struct irq_domain *irq_domain_add_legacy_isa( - struct device_node *of_node, - const struct irq_domain_ops *ops, - void *host_data) -{ - return irq_domain_add_legacy(of_node, NUM_ISA_INTERRUPTS, 0, 0, ops, - host_data); -} + +extern unsigned int irq_create_direct_mapping(struct irq_domain *host); +#endif + static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node, const struct irq_domain_ops *ops, void *host_data) @@ -405,25 +402,37 @@ static inline unsigned int irq_create_mapping(struct irq_domain *host, return irq_create_mapping_affinity(host, hwirq, NULL); } +extern struct irq_desc *__irq_resolve_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq, + unsigned int *irq); + +static inline struct irq_desc *irq_resolve_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq) +{ + return __irq_resolve_mapping(domain, hwirq, NULL); +} /** - * irq_linear_revmap() - Find a linux irq from a hw irq number. + * irq_find_mapping() - Find a linux irq from a hw irq number. * @domain: domain owning this hardware interrupt * @hwirq: hardware irq number in that domain space - * - * This is a fast path alternative to irq_find_mapping() that can be - * called directly by irq controller code to save a handful of - * instructions. It is always safe to call, but won't find irqs mapped - * using the radix tree. */ +static inline unsigned int irq_find_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq) +{ + unsigned int irq; + + if (__irq_resolve_mapping(domain, hwirq, &irq)) + return irq; + + return 0; +} + static inline unsigned int irq_linear_revmap(struct irq_domain *domain, irq_hw_number_t hwirq) { - return hwirq < domain->revmap_size ? domain->linear_revmap[hwirq] : 0; + return irq_find_mapping(domain, hwirq); } -extern unsigned int irq_find_mapping(struct irq_domain *host, - irq_hw_number_t hwirq); -extern unsigned int irq_create_direct_mapping(struct irq_domain *host); extern const struct irq_domain_ops irq_domain_simple_ops; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index db0e1920cb12..6cc035321562 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -779,6 +779,11 @@ struct journal_s */ unsigned long j_flags; + /** + * @j_atomic_flags: Atomic journaling state flags. + */ + unsigned long j_atomic_flags; + /** * @j_errno: * @@ -904,6 +909,29 @@ struct journal_s */ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; + /** + * @j_shrinker: + * + * Journal head shrinker, reclaim buffer's journal head which + * has been written back. + */ + struct shrinker j_shrinker; + + /** + * @j_jh_shrink_count: + * + * Number of journal buffers on the checkpoint list. [j_list_lock] + */ + struct percpu_counter j_jh_shrink_count; + + /** + * @j_shrink_transaction: + * + * Record next transaction will shrink on the checkpoint list. + * [j_list_lock] + */ + transaction_t *j_shrink_transaction; + /** * @j_head: * @@ -1370,6 +1398,16 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) * mode */ #define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ #define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ +#define JBD2_JOURNAL_FLUSH_DISCARD 0x0001 +#define JBD2_JOURNAL_FLUSH_ZEROOUT 0x0002 +#define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \ + JBD2_JOURNAL_FLUSH_ZEROOUT) + +/* + * Journal atomic flag definitions + */ +#define JBD2_CHECKPOINT_IO_ERROR 0x001 /* Detect io error while writing + * buffer back to disk */ /* * Function declarations for the journaling transaction and buffer @@ -1407,6 +1445,7 @@ extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy); +unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); @@ -1500,7 +1539,7 @@ extern int jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned int, unsigned int); extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); extern int jbd2_journal_stop(handle_t *); -extern int jbd2_journal_flush (journal_t *); +extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); @@ -1517,6 +1556,8 @@ extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); +extern int jbd2_journal_register_shrinker(journal_t *journal); +extern void jbd2_journal_unregister_shrinker(journal_t *journal); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); diff --git a/include/linux/kasan.h b/include/linux/kasan.h index a1c7ce5f3e4f..5310e217bd74 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -18,7 +18,6 @@ struct task_struct; /* kasan_data struct is used in KUnit tests for KASAN expected failures */ struct kunit_kasan_expectation { - bool report_expected; bool report_found; }; @@ -42,9 +41,9 @@ struct kunit_kasan_expectation { #endif extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; -extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS]; -extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD]; -extern pud_t kasan_early_shadow_pud[PTRS_PER_PUD]; +extern pte_t kasan_early_shadow_pte[MAX_PTRS_PER_PTE + PTE_HWTABLE_PTRS]; +extern pmd_t kasan_early_shadow_pmd[MAX_PTRS_PER_PMD]; +extern pud_t kasan_early_shadow_pud[MAX_PTRS_PER_PUD]; extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D]; int kasan_populate_early_shadow(const void *shadow_start, diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 15d8bad3d2f2..f2ad8a53f71f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -71,6 +71,18 @@ */ #define lower_32_bits(n) ((u32)((n) & 0xffffffff)) +/** + * upper_16_bits - return bits 16-31 of a number + * @n: the number we're accessing + */ +#define upper_16_bits(n) ((u16)((n) >> 16)) + +/** + * lower_16_bits - return bits 0-15 of a number + * @n: the number we're accessing + */ +#define lower_16_bits(n) ((u16)((n) & 0xffff)) + struct completion; struct pt_regs; struct user; @@ -357,6 +369,8 @@ int sscanf(const char *, const char *, ...); extern __scanf(2, 0) int vsscanf(const char *, const char *, va_list); +extern int no_hash_pointers_enable(char *str); + extern int get_option(char **str, int *pint); extern char *get_options(const char *str, int nints, int *ints); extern unsigned long long memparse(const char *ptr, char **retptr); diff --git a/include/linux/kthread.h b/include/linux/kthread.h index d9133d6db308..346b0f269161 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -18,7 +18,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), * @threadfn: the function to run in the thread * @data: data pointer for @threadfn() * @namefmt: printf-style format string for the thread name - * @arg...: arguments for @namefmt. + * @arg: arguments for @namefmt. * * This macro will create a kthread on the current node, leaving it in * the stopped state. This is just a helper for kthread_create_on_node(); diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index cd23355d2271..17d02eda9538 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -48,13 +48,13 @@ struct lsm_ioctlop_audit { }; struct lsm_ibpkey_audit { - u64 subnet_prefix; - u16 pkey; + u64 subnet_prefix; + u16 pkey; }; struct lsm_ibendport_audit { - char dev_name[IB_DEVICE_NAME_MAX]; - u8 port; + const char *dev_name; + u8 port; }; /* Auxiliary data to use in generating the audit record. */ diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 04c01794de83..2adeea44c0d5 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -358,8 +358,7 @@ LSM_HOOK(int, 0, xfrm_state_alloc_acquire, struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid) LSM_HOOK(void, LSM_RET_VOID, xfrm_state_free_security, struct xfrm_state *x) LSM_HOOK(int, 0, xfrm_state_delete_security, struct xfrm_state *x) -LSM_HOOK(int, 0, xfrm_policy_lookup, struct xfrm_sec_ctx *ctx, u32 fl_secid, - u8 dir) +LSM_HOOK(int, 0, xfrm_policy_lookup, struct xfrm_sec_ctx *ctx, u32 fl_secid) LSM_HOOK(int, 1, xfrm_state_pol_flow_match, struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) LSM_HOOK(int, 0, xfrm_decode_session, struct sk_buff *skb, u32 *secid, diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index d5a983d65f05..44365aab043c 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -65,14 +65,10 @@ enum cmdq_code { CMDQ_CODE_LOGIC = 0xa0, }; -enum cmdq_cb_status { - CMDQ_CB_NORMAL = 0, - CMDQ_CB_ERROR -}; - struct cmdq_cb_data { - enum cmdq_cb_status sta; + int sta; void *data; + struct cmdq_pkt *pkt; }; typedef void (*cmdq_async_flush_cb)(struct cmdq_cb_data data); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 5984fff3f175..552309342c38 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -50,7 +50,7 @@ struct memblock_region { phys_addr_t base; phys_addr_t size; enum memblock_flags flags; -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA int nid; #endif }; @@ -347,7 +347,7 @@ int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask); int memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid); -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA static inline void memblock_set_region_node(struct memblock_region *r, int nid) { r->nid = nid; @@ -366,7 +366,7 @@ static inline int memblock_get_region_node(const struct memblock_region *r) { return 0; } -#endif /* CONFIG_NEED_MULTIPLE_NODES */ +#endif /* CONFIG_NUMA */ /* Flags for memblock allocation APIs */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c193be760709..6d66037be646 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -192,7 +192,7 @@ enum memcg_kmem_state { struct memcg_padding { char x[0]; } ____cacheline_internodealigned_in_smp; -#define MEMCG_PADDING(name) struct memcg_padding name; +#define MEMCG_PADDING(name) struct memcg_padding name #else #define MEMCG_PADDING(name) #endif @@ -349,8 +349,7 @@ struct mem_cgroup { struct deferred_split deferred_split_queue; #endif - struct mem_cgroup_per_node *nodeinfo[0]; - /* WARNING: nodeinfo must be the last member here */ + struct mem_cgroup_per_node *nodeinfo[]; }; /* @@ -743,35 +742,18 @@ out: /** * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page * @page: the page - * @pgdat: pgdat of the page * * This function relies on page->mem_cgroup being stable. */ -static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, - struct pglist_data *pgdat) +static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page) { + pg_data_t *pgdat = page_pgdat(page); struct mem_cgroup *memcg = page_memcg(page); VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page); return mem_cgroup_lruvec(memcg, pgdat); } -static inline bool lruvec_holds_page_lru_lock(struct page *page, - struct lruvec *lruvec) -{ - pg_data_t *pgdat = page_pgdat(page); - const struct mem_cgroup *memcg; - struct mem_cgroup_per_node *mz; - - if (mem_cgroup_disabled()) - return lruvec == &pgdat->__lruvec; - - mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - memcg = page_memcg(page) ? : root_mem_cgroup; - - return lruvec->pgdat == pgdat && mz->memcg == memcg; -} - struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); @@ -1221,18 +1203,11 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, return &pgdat->__lruvec; } -static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, - struct pglist_data *pgdat) -{ - return &pgdat->__lruvec; -} - -static inline bool lruvec_holds_page_lru_lock(struct page *page, - struct lruvec *lruvec) +static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page) { pg_data_t *pgdat = page_pgdat(page); - return lruvec == &pgdat->__lruvec; + return &pgdat->__lruvec; } static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) @@ -1255,6 +1230,12 @@ static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) return NULL; } +static inline +struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) +{ + return NULL; +} + static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } @@ -1516,12 +1497,19 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, spin_unlock_irqrestore(&lruvec->lru_lock, flags); } +/* Test requires a stable page->memcg binding, see page_memcg() */ +static inline bool page_matches_lruvec(struct page *page, struct lruvec *lruvec) +{ + return lruvec_pgdat(lruvec) == page_pgdat(page) && + lruvec_memcg(lruvec) == page_memcg(page); +} + /* Don't lock again iff page's lruvec locked */ static inline struct lruvec *relock_page_lruvec_irq(struct page *page, struct lruvec *locked_lruvec) { if (locked_lruvec) { - if (lruvec_holds_page_lru_lock(page, locked_lruvec)) + if (page_matches_lruvec(page, locked_lruvec)) return locked_lruvec; unlock_page_lruvec_irq(locked_lruvec); @@ -1535,7 +1523,7 @@ static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page, struct lruvec *locked_lruvec, unsigned long *flags) { if (locked_lruvec) { - if (lruvec_holds_page_lru_lock(page, locked_lruvec)) + if (page_matches_lruvec(page, locked_lruvec)) return locked_lruvec; unlock_page_lruvec_irqrestore(locked_lruvec, *flags); diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 416ee6dd2574..3d43c60b49fa 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -39,10 +39,26 @@ /* struct phy_device dev_flags definitions */ #define MICREL_PHY_50MHZ_CLK 0x00000001 #define MICREL_PHY_FXEN 0x00000002 +#define MICREL_KSZ8_P1_ERRATA 0x00000003 #define MICREL_KSZ9021_EXTREG_CTRL 0xB #define MICREL_KSZ9021_EXTREG_DATA_WRITE 0xC #define MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW 0x104 #define MICREL_KSZ9021_RGMII_RX_DATA_PAD_SCEW 0x105 +/* Device specific MII_BMCR (Reg 0) bits */ +/* 1 = HP Auto MDI/MDI-X mode, 0 = Microchip Auto MDI/MDI-X mode */ +#define KSZ886X_BMCR_HP_MDIX BIT(5) +/* 1 = Force MDI (transmit on RXP/RXM pins), 0 = Normal operation + * (transmit on TXP/TXM pins) + */ +#define KSZ886X_BMCR_FORCE_MDI BIT(4) +/* 1 = Disable auto MDI-X */ +#define KSZ886X_BMCR_DISABLE_AUTO_MDIX BIT(3) +#define KSZ886X_BMCR_DISABLE_FAR_END_FAULT BIT(2) +#define KSZ886X_BMCR_DISABLE_TRANSMIT BIT(1) +#define KSZ886X_BMCR_DISABLE_LED BIT(0) + +#define KSZ886X_CTRL_MDIX_STAT BIT(4) + #endif /* _MICREL_PHY_H */ diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 578c4ccae91c..0025913505ab 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1179,6 +1179,7 @@ enum mlx5_cap_type { MLX5_CAP_VDPA_EMULATION = 0x13, MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, + MLX5_CAP_GENERAL_2 = 0x20, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1220,6 +1221,15 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_GEN_MAX(mdev, cap) \ MLX5_GET(cmd_hca_cap, mdev->caps.hca_max[MLX5_CAP_GENERAL], cap) +#define MLX5_CAP_GEN_2(mdev, cap) \ + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap) + +#define MLX5_CAP_GEN_2_64(mdev, cap) \ + MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap) + +#define MLX5_CAP_GEN_2_MAX(mdev, cap) \ + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_max[MLX5_CAP_GENERAL_2], cap) + #define MLX5_CAP_ETH(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ mdev->caps.hca_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f8902bcd91e2..1efe37466969 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -554,6 +554,7 @@ struct mlx5_adev { int idx; }; +struct mlx5_ft_pool; struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ struct mlx5_irq_table *irq_table; @@ -606,6 +607,7 @@ struct mlx5_priv { struct mlx5_core_roce roce; struct mlx5_fc_stats fc_stats; struct mlx5_rl_table rl_table; + struct mlx5_ft_pool *ft_pool; struct mlx5_bfreg_data bfregs; struct mlx5_uars_page *uar; diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index e49d8c0d4f26..cea6ecb4b73e 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -16,6 +16,7 @@ struct mlx5_eq_param { u8 irq_index; int nent; u64 mask[4]; + cpumask_var_t affinity; }; struct mlx5_eq * diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 17109b65c1ac..bc7db2e059eb 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -98,10 +98,11 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, u16 vport_num); /* Reg C1 usage: - * Reg C1 = < ESW_TUN_ID(12) | ESW_TUN_OPTS(12) | ESW_ZONE_ID(8) > + * Reg C1 = < Reserved(1) | ESW_TUN_ID(12) | ESW_TUN_OPTS(11) | ESW_ZONE_ID(8) > * - * Highest 12 bits of reg c1 is the encapsulation tunnel id, next 12 bits is - * encapsulation tunnel options, and the lowest 8 bits are used for zone id. + * Highest bit is reserved for other offloads as marker bit, next 12 bits of reg c1 + * is the encapsulation tunnel id, next 11 bits is encapsulation tunnel options, + * and the lowest 8 bits are used for zone id. * * Zone id is used to restore CT flow when packet misses on chain. * @@ -109,16 +110,18 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, * on miss and to support inner header rewrite by means of implicit chain 0 * flows. */ +#define ESW_RESERVED_BITS 1 #define ESW_ZONE_ID_BITS 8 -#define ESW_TUN_OPTS_BITS 12 +#define ESW_TUN_OPTS_BITS 11 #define ESW_TUN_ID_BITS 12 #define ESW_TUN_OPTS_OFFSET ESW_ZONE_ID_BITS #define ESW_TUN_OFFSET ESW_TUN_OPTS_OFFSET #define ESW_ZONE_ID_MASK GENMASK(ESW_ZONE_ID_BITS - 1, 0) -#define ESW_TUN_OPTS_MASK GENMASK(32 - ESW_TUN_ID_BITS - 1, ESW_TUN_OPTS_OFFSET) -#define ESW_TUN_MASK GENMASK(31, ESW_TUN_OFFSET) +#define ESW_TUN_OPTS_MASK GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, ESW_TUN_OPTS_OFFSET) +#define ESW_TUN_MASK GENMASK(31 - ESW_RESERVED_BITS, ESW_TUN_OFFSET) #define ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT 0 /* 0 is not a valid tunnel id */ -#define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT 0xFFF /* 0xFFF is a reserved mapping */ +/* 0x7FF is a reserved mapping */ +#define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT GENMASK(ESW_TUN_OPTS_BITS - 1, 0) #define ESW_TUN_SLOW_TABLE_GOTO_VPORT ((ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT << ESW_TUN_OPTS_BITS) | \ ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT) #define ESW_TUN_SLOW_TABLE_GOTO_VPORT_MARK ESW_TUN_OPTS_MASK diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 1f51f4c3b1af..77746f7e35b8 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -87,6 +87,8 @@ enum { FDB_BYPASS_PATH, FDB_TC_OFFLOAD, FDB_FT_OFFLOAD, + FDB_TC_MISS, + FDB_BR_OFFLOAD, FDB_SLOW_PATH, FDB_PER_VPORT, }; @@ -254,10 +256,16 @@ struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev, void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, struct mlx5_modify_hdr *modify_hdr); +struct mlx5_pkt_reformat_params { + int type; + u8 param_0; + u8 param_1; + size_t size; + void *data; +}; + struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type ns_type); void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, struct mlx5_pkt_reformat *reformat); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index eb86e80e4643..e32a0d61929b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -435,7 +435,10 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_40[0x20]; - u8 reserved_at_60[0x18]; + u8 reserved_at_60[0x2]; + u8 reformat_insert[0x1]; + u8 reformat_remove[0x1]; + u8 reserver_at_64[0x14]; u8 log_max_ft_num[0x8]; u8 reserved_at_80[0x10]; @@ -1312,7 +1315,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x1f]; u8 vhca_resource_manager[0x1]; - u8 reserved_at_20[0x3]; + u8 hca_cap_2[0x1]; + u8 reserved_at_21[0x2]; u8 event_on_vhca_state_teardown_request[0x1]; u8 event_on_vhca_state_in_use[0x1]; u8 event_on_vhca_state_active[0x1]; @@ -1732,6 +1736,17 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_7c0[0x40]; }; +struct mlx5_ifc_cmd_hca_cap_2_bits { + u8 reserved_at_0[0xa0]; + + u8 max_reformat_insert_size[0x8]; + u8 max_reformat_insert_offset[0x8]; + u8 max_reformat_remove_size[0x8]; + u8 max_reformat_remove_offset[0x8]; + + u8 reserved_at_c0[0x740]; +}; + enum mlx5_flow_destination_type { MLX5_FLOW_DESTINATION_TYPE_VPORT = 0x0, MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, @@ -3105,6 +3120,7 @@ struct mlx5_ifc_roce_addr_layout_bits { union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap; + struct mlx5_ifc_cmd_hca_cap_2_bits cmd_hca_cap_2; struct mlx5_ifc_odp_cap_bits odp_cap; struct mlx5_ifc_atomic_caps_bits atomic_caps; struct mlx5_ifc_roce_cap_bits roce_cap; @@ -3790,8 +3806,8 @@ struct mlx5_ifc_eqc_bits { u8 reserved_at_80[0x20]; - u8 reserved_at_a0[0x18]; - u8 intr[0x8]; + u8 reserved_at_a0[0x14]; + u8 intr[0xc]; u8 reserved_at_c0[0x3]; u8 log_page_size[0x5]; @@ -5785,12 +5801,14 @@ struct mlx5_ifc_query_eq_in_bits { }; struct mlx5_ifc_packet_reformat_context_in_bits { - u8 reserved_at_0[0x5]; - u8 reformat_type[0x3]; - u8 reserved_at_8[0xe]; + u8 reformat_type[0x8]; + u8 reserved_at_8[0x4]; + u8 reformat_param_0[0x4]; + u8 reserved_at_10[0x6]; u8 reformat_data_size[0xa]; - u8 reserved_at_20[0x10]; + u8 reformat_param_1[0x8]; + u8 reserved_at_28[0x8]; u8 reformat_data[2][0x8]; u8 more_reformat_data[][0x8]; @@ -5830,12 +5848,20 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits { u8 reserved_at_60[0x20]; }; +enum { + MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START = 0x1, + MLX5_REFORMAT_CONTEXT_ANCHOR_IP_START = 0x7, + MLX5_REFORMAT_CONTEXT_ANCHOR_TCP_UDP_START = 0x9, +}; + enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0, MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1, MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2, MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x3, MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, + MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf, + MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10, }; struct mlx5_ifc_alloc_packet_reformat_context_in_bits { @@ -5956,6 +5982,8 @@ enum { MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM = 0x59, MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM = 0x5B, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME = 0x5D, + MLX5_ACTION_IN_FIELD_OUT_EMD_47_32 = 0x6F, + MLX5_ACTION_IN_FIELD_OUT_EMD_31_0 = 0x70, }; struct mlx5_ifc_alloc_modify_header_context_out_bits { @@ -11055,6 +11083,11 @@ struct mlx5_ifc_create_sampler_obj_in_bits { struct mlx5_ifc_sampler_obj_bits sampler_object; }; +struct mlx5_ifc_query_sampler_obj_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; + struct mlx5_ifc_sampler_obj_bits sampler_object; +}; + enum { MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128 = 0x0, MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_256 = 0x1, diff --git a/include/linux/mm.h b/include/linux/mm.h index 889b4006b1db..265f4859a7f3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -46,7 +46,7 @@ extern int sysctl_page_lock_unfairness; void init_mm_internals(void); -#ifndef CONFIG_NEED_MULTIPLE_NODES /* Don't use mapnrs, do it properly */ +#ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; static inline void set_max_mapnr(unsigned long limit) @@ -124,16 +124,6 @@ extern int mmap_rnd_compat_bits __read_mostly; #define lm_alias(x) __va(__pa_symbol(x)) #endif -/* - * With CONFIG_CFI_CLANG, the compiler replaces function addresses in - * instrumented C code with jump table addresses. Architectures that - * support CFI can define this macro to return the actual function address - * when needed. - */ -#ifndef function_nocfi -#define function_nocfi(x) (x) -#endif - /* * To prevent common memory management code establishing * a zero page mapping on a read fault. @@ -234,7 +224,11 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp, void **shadowp); +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) +#else +#define nth_page(page,n) ((page) + (n)) +#endif /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) @@ -1341,7 +1335,7 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, if (!is_cow_mapping(vma->vm_flags)) return false; - if (!atomic_read(&vma->vm_mm->has_pinned)) + if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)) return false; return page_maybe_dma_pinned(page); @@ -1668,10 +1662,11 @@ struct address_space *page_mapping(struct page *page); static inline bool page_is_pfmemalloc(const struct page *page) { /* - * Page index cannot be this large so this must be - * a pfmemalloc page. + * lru.next has bit 1 set if the page is allocated from the + * pfmemalloc reserves. Callers may simply overwrite it if + * they do not need to preserve that information. */ - return page->index == -1UL; + return (uintptr_t)page->lru.next & BIT(1); } /* @@ -1680,12 +1675,12 @@ static inline bool page_is_pfmemalloc(const struct page *page) */ static inline void set_page_pfmemalloc(struct page *page) { - page->index = -1UL; + page->lru.next = (void *)BIT(1); } static inline void clear_page_pfmemalloc(struct page *page) { - page->index = 0; + page->lru.next = NULL; } /* @@ -1709,8 +1704,8 @@ extern bool can_do_mlock(void); #else static inline bool can_do_mlock(void) { return false; } #endif -extern int user_shm_lock(size_t, struct user_struct *); -extern void user_shm_unlock(size_t, struct user_struct *); +extern int user_shm_lock(size_t, struct ucounts *); +extern void user_shm_unlock(size_t, struct ucounts *); /* * Parameter block passed down to zap_pte_range in exceptional cases. @@ -1850,12 +1845,8 @@ extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length); -void __set_page_dirty(struct page *, struct address_space *, int warn); -int __set_page_dirty_nobuffers(struct page *page); -int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); -void account_page_dirtied(struct page *page, struct address_space *mapping); void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb); int set_page_dirty(struct page *page); @@ -2421,7 +2412,7 @@ static inline unsigned long free_initmem_default(int poison) extern char __init_begin[], __init_end[]; return free_reserved_area(&__init_begin, &__init_end, - poison, "unused kernel"); + poison, "unused kernel image (initmem)"); } static inline unsigned long get_num_physpages(void) @@ -2461,7 +2452,7 @@ extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA static inline int early_pfn_to_nid(unsigned long pfn) { return 0; @@ -2475,7 +2466,6 @@ extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); -extern void memmap_init_zone(struct zone *zone); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); @@ -2682,17 +2672,45 @@ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long add extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, struct vm_area_struct **pprev); -/* Look up the first VMA which intersects the interval start_addr..end_addr-1, - NULL if none. Assume start_addr < end_addr. */ -static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * mm, unsigned long start_addr, unsigned long end_addr) +/** + * find_vma_intersection() - Look up the first VMA which intersects the interval + * @mm: The process address space. + * @start_addr: The inclusive start user address. + * @end_addr: The exclusive end user address. + * + * Returns: The first VMA within the provided range, %NULL otherwise. Assumes + * start_addr < end_addr. + */ +static inline +struct vm_area_struct *find_vma_intersection(struct mm_struct *mm, + unsigned long start_addr, + unsigned long end_addr) { - struct vm_area_struct * vma = find_vma(mm,start_addr); + struct vm_area_struct *vma = find_vma(mm, start_addr); if (vma && end_addr <= vma->vm_start) vma = NULL; return vma; } +/** + * vma_lookup() - Find a VMA at a specific address + * @mm: The process address space. + * @addr: The user address. + * + * Return: The vm_area_struct at the given address, %NULL otherwise. + */ +static inline +struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma = find_vma(mm, addr); + + if (vma && addr < vma->vm_start) + vma = NULL; + + return vma; +} + static inline unsigned long vm_start_gap(struct vm_area_struct *vma) { unsigned long vm_start = vma->vm_start; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3732f7d62eef..b31ea9b4fffd 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -96,6 +96,13 @@ struct page { unsigned long private; }; struct { /* page_pool used by netstack */ + /** + * @pp_magic: magic value to avoid recycling non + * page_pool allocated pages. + */ + unsigned long pp_magic; + struct page_pool *pp; + unsigned long _pp_mapping_pad; /** * @dma_addr: might require a 64-bit value on * 32-bit architectures. @@ -442,16 +449,6 @@ struct mm_struct { */ atomic_t mm_count; - /** - * @has_pinned: Whether this mm has pinned any pages. This can - * be either replaced in the future by @pinned_vm when it - * becomes stable, or grow into a counter on its own. We're - * aggresive on this bit now - even if the pinned pages were - * unpinned later on, we'll still keep this bit set for the - * lifecycle of this mm just for simplicity. - */ - atomic_t has_pinned; - #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif diff --git a/include/linux/mman.h b/include/linux/mman.h index 629cefc4ecba..ebb09a964272 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -31,6 +31,8 @@ /* * The historical set of flags that all mmap implementations implicitly * support when a ->mmap_validate() op is not provided in file_operations. + * + * MAP_EXECUTABLE is completely ignored throughout the kernel. */ #define LEGACY_MAP_MASK (MAP_SHARED \ | MAP_PRIVATE \ diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 5d0767cb424a..1935d4c72d10 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -9,8 +9,7 @@ struct page; struct vm_area_struct; struct mm_struct; -extern void dump_page(struct page *page, const char *reason); -extern void __dump_page(struct page *page, const char *reason); +void dump_page(struct page *page, const char *reason); void dump_vma(const struct vm_area_struct *vma); void dump_mm(const struct mm_struct *mm); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1bbd158f781f..68077a9185e5 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -20,6 +20,7 @@ #include #include #include +#include #include /* Free memory management - zoned buddy allocator. */ @@ -134,10 +135,10 @@ enum numa_stat_item { NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ - NR_VM_NUMA_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS }; #else -#define NR_VM_NUMA_STAT_ITEMS 0 +#define NR_VM_NUMA_EVENT_ITEMS 0 #endif enum zone_stat_item { @@ -330,29 +331,55 @@ enum zone_watermarks { NR_WMARK }; +/* + * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER plus one additional + * for pageblock size for THP if configured. + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define NR_PCP_THP 1 +#else +#define NR_PCP_THP 0 +#endif +#define NR_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1 + NR_PCP_THP)) + +/* + * Shift to encode migratetype and order in the same integer, with order + * in the least significant bits. + */ +#define NR_PCP_ORDER_WIDTH 8 +#define NR_PCP_ORDER_MASK ((1<_watermark[WMARK_MIN] + z->watermark_boost) #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost) #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost) #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost) +/* Fields and list protected by pagesets local_lock in page_alloc.c */ struct per_cpu_pages { int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ int batch; /* chunk size for buddy add/remove */ + short free_factor; /* batch scaling factor during free */ +#ifdef CONFIG_NUMA + short expire; /* When 0, remote pagesets are drained */ +#endif /* Lists of pages, one per migrate type stored on the pcp-lists */ - struct list_head lists[MIGRATE_PCPTYPES]; + struct list_head lists[NR_PCP_LISTS]; }; -struct per_cpu_pageset { - struct per_cpu_pages pcp; -#ifdef CONFIG_NUMA - s8 expire; - u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; -#endif +struct per_cpu_zonestat { #ifdef CONFIG_SMP - s8 stat_threshold; s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS]; + s8 stat_threshold; +#endif +#ifdef CONFIG_NUMA + /* + * Low priority inaccurate counters that are only folded + * on demand. Use a large type to avoid the overhead of + * folding during refresh_cpu_vm_stats. + */ + unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #endif }; @@ -482,7 +509,8 @@ struct zone { int node; #endif struct pglist_data *zone_pgdat; - struct per_cpu_pageset __percpu *pageset; + struct per_cpu_pages __percpu *per_cpu_pageset; + struct per_cpu_zonestat __percpu *per_cpu_zonestats; /* * the high and batch values are copied to individual pagesets for * faster access @@ -617,7 +645,7 @@ struct zone { ZONE_PADDING(_pad3_) /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; - atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; + atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { @@ -635,6 +663,7 @@ enum zone_flags { ZONE_BOOSTED_WATERMARK, /* zone recently boosted watermarks. * Cleared when kswapd is woken. */ + ZONE_RECLAIM_ACTIVE, /* kswapd may be scanning the zone. */ }; static inline unsigned long zone_managed_pages(struct zone *zone) @@ -736,10 +765,12 @@ struct zonelist { struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1]; }; -#ifndef CONFIG_DISCONTIGMEM -/* The array of struct pages - for discontigmem use pgdat->lmem_map */ +/* + * The array of struct pages for flatmem. + * It must be declared for SPARSEMEM as well because there are configurations + * that rely on that. + */ extern struct page *mem_map; -#endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split { @@ -773,7 +804,7 @@ typedef struct pglist_data { struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; /* number of populated zones in this node */ -#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */ +#ifdef CONFIG_FLATMEM /* means !SPARSEMEM */ struct page *node_mem_map; #ifdef CONFIG_PAGE_EXTENSION struct page_ext *node_page_ext; @@ -863,7 +894,7 @@ typedef struct pglist_data { #define node_present_pages(nid) (NODE_DATA(nid)->node_present_pages) #define node_spanned_pages(nid) (NODE_DATA(nid)->node_spanned_pages) -#ifdef CONFIG_FLAT_NODE_MEM_MAP +#ifdef CONFIG_FLATMEM #define pgdat_page_nr(pgdat, pagenr) ((pgdat)->node_mem_map + (pagenr)) #else #define pgdat_page_nr(pgdat, pagenr) pfn_to_page((pgdat)->node_start_pfn + (pagenr)) @@ -980,22 +1011,11 @@ static inline void zone_set_nid(struct zone *zone, int nid) {} extern int movable_zone; -#ifdef CONFIG_HIGHMEM -static inline int zone_movable_is_highmem(void) -{ -#ifdef CONFIG_NEED_MULTIPLE_NODES - return movable_zone == ZONE_HIGHMEM; -#else - return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM; -#endif -} -#endif - static inline int is_highmem_idx(enum zone_type idx) { #ifdef CONFIG_HIGHMEM return (idx == ZONE_HIGHMEM || - (idx == ZONE_MOVABLE && zone_movable_is_highmem())); + (idx == ZONE_MOVABLE && movable_zone == ZONE_HIGHMEM)); #else return 0; #endif @@ -1027,7 +1047,7 @@ int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *, extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, +int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); @@ -1035,21 +1055,21 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int numa_zonelist_order_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -extern int percpu_pagelist_fraction; +extern int percpu_pagelist_high_fraction; extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; #define NODE_DATA(nid) (&contig_page_data) #define NODE_MEM_MAP(nid) mem_map -#else /* CONFIG_NEED_MULTIPLE_NODES */ +#else /* CONFIG_NUMA */ #include -#endif /* !CONFIG_NEED_MULTIPLE_NODES */ +#endif /* !CONFIG_NUMA */ extern struct pglist_data *first_online_pgdat(void); extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat); @@ -1198,8 +1218,6 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #ifdef CONFIG_SPARSEMEM /* - * SECTION_SHIFT #bits space required to store a section # - * * PA_SECTION_SHIFT physical address to/from section number * PFN_SECTION_SHIFT pfn to/from section number */ diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 7d45b5f989b0..8e291cfdaf06 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -447,6 +447,7 @@ struct hv_vmbus_device_id { struct rpmsg_device_id { char name[RPMSG_NAME_SIZE]; + kernel_ulong_t driver_data; }; /* i2c */ diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index f41387a8969f..41f24b5241ab 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -4,6 +4,8 @@ #ifndef _I40E_CLIENT_H_ #define _I40E_CLIENT_H_ +#include + #define I40E_CLIENT_STR_LENGTH 10 /* Client interface version should be updated anytime there is a change in the @@ -48,7 +50,7 @@ struct i40e_qv_info { struct i40e_qvlist_info { u32 num_vectors; - struct i40e_qv_info qv_info[1]; + struct i40e_qv_info qv_info[]; }; @@ -78,6 +80,7 @@ struct i40e_info { u8 lanmac[6]; struct net_device *netdev; struct pci_dev *pcidev; + struct auxiliary_device *aux_dev; u8 __iomem *hw_addr; u8 fid; /* function id, PF id or VF id */ #define I40E_CLIENT_FTYPE_PF 0 @@ -100,6 +103,11 @@ struct i40e_info { u32 fw_build; /* firmware build number */ }; +struct i40e_auxiliary_device { + struct auxiliary_device aux_dev; + struct i40e_info *ldev; +}; + #define I40E_CLIENT_RESET_LEVEL_PF 1 #define I40E_CLIENT_RESET_LEVEL_CORE 2 #define I40E_CLIENT_VSI_FLAG_TCP_ENABLE BIT(1) @@ -187,6 +195,8 @@ static inline bool i40e_client_is_registered(struct i40e_client *client) return test_bit(__I40E_CLIENT_REGISTERED, &client->state); } +void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client); +void i40e_client_device_unregister(struct i40e_info *ldev); /* used by clients */ int i40e_register_client(struct i40e_client *client); int i40e_unregister_client(struct i40e_client *client); diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h new file mode 100644 index 000000000000..e32f6712aee0 --- /dev/null +++ b/include/linux/net/intel/iidc.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021, Intel Corporation. */ + +#ifndef _IIDC_H_ +#define _IIDC_H_ + +#include +#include +#include +#include +#include +#include + +enum iidc_event_type { + IIDC_EVENT_BEFORE_MTU_CHANGE, + IIDC_EVENT_AFTER_MTU_CHANGE, + IIDC_EVENT_BEFORE_TC_CHANGE, + IIDC_EVENT_AFTER_TC_CHANGE, + IIDC_EVENT_CRIT_ERR, + IIDC_EVENT_NBITS /* must be last */ +}; + +enum iidc_reset_type { + IIDC_PFR, + IIDC_CORER, + IIDC_GLOBR, +}; + +#define IIDC_MAX_USER_PRIORITY 8 + +/* Struct to hold per RDMA Qset info */ +struct iidc_rdma_qset_params { + /* Qset TEID returned to the RDMA driver in + * ice_add_rdma_qset and used by RDMA driver + * for calls to ice_del_rdma_qset + */ + u32 teid; /* Qset TEID */ + u16 qs_handle; /* RDMA driver provides this */ + u16 vport_id; /* VSI index */ + u8 tc; /* TC branch the Qset should belong to */ +}; + +struct iidc_qos_info { + u64 tc_ctx; + u8 rel_bw; + u8 prio_type; + u8 egress_virt_up; + u8 ingress_virt_up; +}; + +/* Struct to pass QoS info */ +struct iidc_qos_params { + struct iidc_qos_info tc_info[IEEE_8021QAZ_MAX_TCS]; + u8 up2tc[IIDC_MAX_USER_PRIORITY]; + u8 vport_relative_bw; + u8 vport_priority_type; + u8 num_tc; +}; + +struct iidc_event { + DECLARE_BITMAP(type, IIDC_EVENT_NBITS); + u32 reg; +}; + +struct ice_pf; + +int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset); +int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset); +int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type); +int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable); +void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos); + +#define IIDC_RDMA_ROCE_NAME "roce" + +/* Structure representing auxiliary driver tailored information about the core + * PCI dev, each auxiliary driver using the IIDC interface will have an + * instance of this struct dedicated to it. + */ + +struct iidc_auxiliary_dev { + struct auxiliary_device adev; + struct ice_pf *pf; +}; + +/* structure representing the auxiliary driver. This struct is to be + * allocated and populated by the auxiliary driver's owner. The core PCI + * driver will access these ops by performing a container_of on the + * auxiliary_device->dev.driver. + */ +struct iidc_auxiliary_drv { + struct auxiliary_driver adrv; + /* This event_handler is meant to be a blocking call. For instance, + * when a BEFORE_MTU_CHANGE event comes in, the event_handler will not + * return until the auxiliary driver is ready for the MTU change to + * happen. + */ + void (*event_handler)(struct ice_pf *pf, struct iidc_event *event); +}; + +#endif /* _IIDC_H_*/ diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 3de38d6a0aea..2c6b9e416225 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -93,7 +93,7 @@ enum { /* * Add your fresh new feature above and remember to update - * netdev_features_strings[] in net/core/ethtool.c and maybe + * netdev_features_strings[] in net/ethtool/common.c and maybe * some feature mask #defines below. Please also describe it * in Documentation/networking/netdev-features.rst. */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5cbc950b34df..eaf5bb008aa9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4114,7 +4114,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, return NET_RX_DROP; } - skb_scrub_packet(skb, true); + skb_scrub_packet(skb, !net_eq(dev_net(dev), dev_net(skb->dev))); skb->priority = 0; return 0; } @@ -4187,8 +4187,8 @@ unsigned long dev_trans_start(struct net_device *dev); void __netdev_watchdog_up(struct net_device *dev); void netif_carrier_on(struct net_device *dev); - void netif_carrier_off(struct net_device *dev); +void netif_carrier_event(struct net_device *dev); /** * netif_dormant_on - mark device as dormant. diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index f0f3a8354c3c..3fda1a508733 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -65,8 +65,8 @@ struct nf_hook_ops; struct sock; struct nf_hook_state { - unsigned int hook; - u_int8_t pf; + u8 hook; + u8 pf; struct net_device *in; struct net_device *out; struct sock *sk; @@ -77,12 +77,18 @@ struct nf_hook_state { typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); +enum nf_hook_ops_type { + NF_HOOK_OP_UNDEFINED, + NF_HOOK_OP_NF_TABLES, +}; + struct nf_hook_ops { /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; void *priv; - u_int8_t pf; + u8 pf; + enum nf_hook_ops_type hook_ops_type:8; unsigned int hooknum; /* Hooks are ordered in ascending priority. */ int priority; diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 515ce53aa20d..241e005f290a 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -11,6 +11,7 @@ struct nfnl_info { struct net *net; struct sock *sk; const struct nlmsghdr *nlh; + const struct nfgenmsg *nfmsg; struct netlink_ext_ack *extack; }; diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 07c6ad8f2a02..28d7027cd460 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -36,8 +36,8 @@ struct xt_action_param { const void *matchinfo, *targinfo; }; const struct nf_hook_state *state; - int fragoff; unsigned int thoff; + u16 fragoff; bool hotdrop; }; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index edcbd60b88b9..b7c4c4130b65 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -636,8 +636,8 @@ struct nvme_lba_range_type { __u8 type; __u8 attributes; __u8 rsvd2[14]; - __u64 slba; - __u64 nlb; + __le64 slba; + __le64 nlb; __u8 guid[16]; __u8 rsvd48[16]; }; @@ -944,6 +944,13 @@ struct nvme_zone_mgmt_recv_cmd { enum { NVME_ZRA_ZONE_REPORT = 0, NVME_ZRASF_ZONE_REPORT_ALL = 0, + NVME_ZRASF_ZONE_STATE_EMPTY = 0x01, + NVME_ZRASF_ZONE_STATE_IMP_OPEN = 0x02, + NVME_ZRASF_ZONE_STATE_EXP_OPEN = 0x03, + NVME_ZRASF_ZONE_STATE_CLOSED = 0x04, + NVME_ZRASF_ZONE_STATE_READONLY = 0x05, + NVME_ZRASF_ZONE_STATE_FULL = 0x06, + NVME_ZRASF_ZONE_STATE_OFFLINE = 0x07, NVME_REPORT_ZONE_PARTIAL = 1, }; @@ -1504,6 +1511,7 @@ enum { NVME_SC_NS_WRITE_PROTECTED = 0x20, NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_TRANSIENT_TR_ERR = 0x22, + NVME_SC_INVALID_IO_CMD_SET = 0x2C, NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 2b05e7f7c238..da633d34ab86 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -72,6 +72,13 @@ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node * return mdiobus_register(mdio); } +static inline int devm_of_mdiobus_register(struct device *dev, + struct mii_bus *mdio, + struct device_node *np) +{ + return devm_mdiobus_register(dev, mdio); +} + static inline struct mdio_device *of_mdio_find_device(struct device_node *np) { return NULL; diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 461b7aa587ba..3d8db1f6a5db 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -54,6 +54,10 @@ enum OID { OID_md4, /* 1.2.840.113549.2.4 */ OID_md5, /* 1.2.840.113549.2.5 */ + OID_mskrb5, /* 1.2.840.48018.1.2.2 */ + OID_krb5, /* 1.2.840.113554.1.2.2 */ + OID_krb5u2u, /* 1.2.840.113554.1.2.2.3 */ + /* Microsoft Authenticode & Software Publishing */ OID_msIndirectData, /* 1.3.6.1.4.1.311.2.1.4 */ OID_msStatementType, /* 1.3.6.1.4.1.311.2.1.11 */ @@ -62,6 +66,10 @@ enum OID { OID_msIndividualSPKeyPurpose, /* 1.3.6.1.4.1.311.2.1.21 */ OID_msOutlookExpress, /* 1.3.6.1.4.1.311.16.4 */ + OID_ntlmssp, /* 1.3.6.1.4.1.311.2.2.10 */ + + OID_spnego, /* 1.3.6.1.5.5.2 */ + OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ OID_sha1, /* 1.3.14.3.2.26 */ OID_id_ansip384r1, /* 1.3.132.0.34 */ diff --git a/include/linux/once_lite.h b/include/linux/once_lite.h new file mode 100644 index 000000000000..861e606b820f --- /dev/null +++ b/include/linux/once_lite.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ONCE_LITE_H +#define _LINUX_ONCE_LITE_H + +#include + +/* Call a function once. Similar to DO_ONCE(), but does not use jump label + * patching via static keys. + */ +#define DO_ONCE_LITE(func, ...) \ + DO_ONCE_LITE_IF(true, func, ##__VA_ARGS__) +#define DO_ONCE_LITE_IF(condition, func, ...) \ + ({ \ + static bool __section(".data.once") __already_done; \ + bool __ret_do_once = !!(condition); \ + \ + if (unlikely(__ret_do_once && !__already_done)) { \ + __already_done = true; \ + func(__VA_ARGS__); \ + } \ + unlikely(__ret_do_once); \ + }) + +#endif /* _LINUX_ONCE_LITE_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 40e2c5000585..458696550028 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -180,17 +180,17 @@ enum pageflags { #ifndef __GENERATING_BOUNDS_H -struct page; /* forward declaration */ - -static inline struct page *compound_head(struct page *page) +static inline unsigned long _compound_head(const struct page *page) { unsigned long head = READ_ONCE(page->compound_head); if (unlikely(head & 1)) - return (struct page *) (head - 1); - return page; + return head - 1; + return (unsigned long)page; } +#define compound_head(page) ((typeof(page))_compound_head(page)) + static __always_inline int PageTail(struct page *page) { return READ_ONCE(page->compound_head) & 1; diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 3468794f83d2..719bfe5108c5 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -14,7 +14,7 @@ extern void __set_page_owner(struct page *page, extern void __split_page_owner(struct page *page, unsigned int nr); extern void __copy_page_owner(struct page *oldpage, struct page *newpage); extern void __set_page_owner_migrate_reason(struct page *page, int reason); -extern void __dump_page_owner(struct page *page); +extern void __dump_page_owner(const struct page *page); extern void pagetypeinfo_showmixedcount_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone); @@ -46,7 +46,7 @@ static inline void set_page_owner_migrate_reason(struct page *page, int reason) if (static_branch_unlikely(&page_owner_inited)) __set_page_owner_migrate_reason(page, reason); } -static inline void dump_page_owner(struct page *page) +static inline void dump_page_owner(const struct page *page) { if (static_branch_unlikely(&page_owner_inited)) __dump_page_owner(page); @@ -69,7 +69,7 @@ static inline void copy_page_owner(struct page *oldpage, struct page *newpage) static inline void set_page_owner_migrate_reason(struct page *page, int reason) { } -static inline void dump_page_owner(struct page *page) +static inline void dump_page_owner(const struct page *page) { } #endif /* CONFIG_PAGE_OWNER */ diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index f3318f34fc54..7ad46f45df39 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -62,12 +62,12 @@ static inline void __page_ref_unfreeze(struct page *page, int v) #endif -static inline int page_ref_count(struct page *page) +static inline int page_ref_count(const struct page *page) { return atomic_read(&page->_refcount); } -static inline int page_count(struct page *page) +static inline int page_count(const struct page *page) { return atomic_read(&compound_head(page)->_refcount); } diff --git a/include/linux/page_reporting.h b/include/linux/page_reporting.h index 3b99e0ec24f2..fe648dfa3a7c 100644 --- a/include/linux/page_reporting.h +++ b/include/linux/page_reporting.h @@ -18,6 +18,9 @@ struct page_reporting_dev_info { /* Current state of page reporting */ atomic_t state; + + /* Minimal order of page reporting */ + unsigned int order; }; /* Tear-down and bring-up for page reporting devices */ diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index fff52ad370c1..973fd731a520 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -54,7 +54,7 @@ extern unsigned int pageblock_order; /* Forward declaration */ struct page; -unsigned long get_pfnblock_flags_mask(struct page *page, +unsigned long get_pfnblock_flags_mask(const struct page *page, unsigned long pfn, unsigned long mask); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0b512d3854ad..a7d0fa7e593b 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -700,6 +700,10 @@ int wait_on_page_writeback_killable(struct page *page); extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); +void __set_page_dirty(struct page *, struct address_space *, int warn); +int __set_page_dirty_nobuffers(struct page *page); +int __set_page_dirty_no_writeback(struct page *page); + void page_endio(struct page *page, bool is_write, int err); /** diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 2cb5188a7ef1..add077a81b21 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -10,37 +10,33 @@ #include #include +#define NXP_SJA1105_XPCS_ID 0x00000010 +#define NXP_SJA1110_XPCS_ID 0x00000020 + /* AN mode */ #define DW_AN_C73 1 #define DW_AN_C37_SGMII 2 +#define DW_2500BASEX 3 -struct mdio_xpcs_args { - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); - struct mii_bus *bus; - int addr; - int an_mode; +struct xpcs_id; + +struct dw_xpcs { + struct mdio_device *mdiodev; + const struct xpcs_id *id; + struct phylink_pcs pcs; }; -struct mdio_xpcs_ops { - int (*validate)(struct mdio_xpcs_args *xpcs, - unsigned long *supported, - struct phylink_link_state *state); - int (*config)(struct mdio_xpcs_args *xpcs, - const struct phylink_link_state *state); - int (*get_state)(struct mdio_xpcs_args *xpcs, - struct phylink_link_state *state); - int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, - phy_interface_t interface); - int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); -}; - -#if IS_ENABLED(CONFIG_PCS_XPCS) -struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); -#else -static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) -{ - return NULL; -} -#endif +int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); +void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, int speed, int duplex); +int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, + unsigned int mode); +void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, + struct phylink_link_state *state); +int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, + int enable); +struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, + phy_interface_t interface); +void xpcs_destroy(struct dw_xpcs *xpcs); #endif /* __LINUX_PCS_XPCS_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index a43047b1030d..c32600c9e1ad 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1592,4 +1592,26 @@ typedef unsigned int pgtbl_mod_mask; #define pte_leaf_size(x) PAGE_SIZE #endif +/* + * Some architectures have MMUs that are configurable or selectable at boot + * time. These lead to variable PTRS_PER_x. For statically allocated arrays it + * helps to have a static maximum value. + */ + +#ifndef MAX_PTRS_PER_PTE +#define MAX_PTRS_PER_PTE PTRS_PER_PTE +#endif + +#ifndef MAX_PTRS_PER_PMD +#define MAX_PTRS_PER_PMD PTRS_PER_PMD +#endif + +#ifndef MAX_PTRS_PER_PUD +#define MAX_PTRS_PER_PUD PTRS_PER_PUD +#endif + +#ifndef MAX_PTRS_PER_P4D +#define MAX_PTRS_PER_P4D PTRS_PER_P4D +#endif + #endif /* _LINUX_PGTABLE_H */ diff --git a/include/linux/phy.h b/include/linux/phy.h index 852743f07e3e..3b80dc3ed68b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -93,6 +93,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface + * @PHY_INTERFACE_MODE_REVRMII: Reduced Media Independent Interface in PHY role * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay @@ -111,6 +112,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR + * @PHY_INTERFACE_MODE_25GBASER: 25G BaseR * @PHY_INTERFACE_MODE_USXGMII: Universal Serial 10GE MII * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN * @PHY_INTERFACE_MODE_MAX: Book keeping @@ -126,6 +128,7 @@ typedef enum { PHY_INTERFACE_MODE_TBI, PHY_INTERFACE_MODE_REVMII, PHY_INTERFACE_MODE_RMII, + PHY_INTERFACE_MODE_REVRMII, PHY_INTERFACE_MODE_RGMII, PHY_INTERFACE_MODE_RGMII_ID, PHY_INTERFACE_MODE_RGMII_RXID, @@ -145,6 +148,7 @@ typedef enum { PHY_INTERFACE_MODE_XAUI, /* 10GBASE-R, XFI, SFI - single lane 10G Serdes */ PHY_INTERFACE_MODE_10GBASER, + PHY_INTERFACE_MODE_25GBASER, PHY_INTERFACE_MODE_USXGMII, /* 10GBASE-KR - with Clause 73 AN */ PHY_INTERFACE_MODE_10GKR, @@ -185,6 +189,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "rev-mii"; case PHY_INTERFACE_MODE_RMII: return "rmii"; + case PHY_INTERFACE_MODE_REVRMII: + return "rev-rmii"; case PHY_INTERFACE_MODE_RGMII: return "rgmii"; case PHY_INTERFACE_MODE_RGMII_ID: @@ -219,6 +225,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "xaui"; case PHY_INTERFACE_MODE_10GBASER: return "10gbase-r"; + case PHY_INTERFACE_MODE_25GBASER: + return "25gbase-r"; case PHY_INTERFACE_MODE_USXGMII: return "usxgmii"; case PHY_INTERFACE_MODE_10GKR: @@ -1373,10 +1381,42 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) +int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); +struct phy_device *device_phy_find_device(struct device *dev); +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); #else +static inline int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id) +{ + return 0; +} +static inline +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) +{ + return 0; +} + +static inline +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode) +{ + return NULL; +} + +static inline struct phy_device *device_phy_find_device(struct device *dev) +{ + return NULL; +} + +static inline +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) +{ + return NULL; +} + static inline struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { diff --git a/include/linux/phylink.h b/include/linux/phylink.h index fd2acfd9b597..afb3ded0b691 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -441,6 +441,9 @@ void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); +int phylink_fwnode_phy_connect(struct phylink *pl, + struct fwnode_handle *fwnode, + u32 flags); void phylink_disconnect_phy(struct phylink *); void phylink_mac_change(struct phylink *, bool up); diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index dfcfbcecc34b..21a0577305ef 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -198,6 +198,7 @@ struct generic_pm_domain_data { struct notifier_block *power_nb; int cpu; unsigned int performance_state; + unsigned int rpm_pstate; ktime_t next_wakeup; void *data; }; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 6c08a085367b..aab8b35e9f8a 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -380,6 +380,9 @@ static inline int pm_runtime_get(struct device *dev) * The possible return values of this function are the same as for * pm_runtime_resume() and the runtime PM usage counter of @dev remains * incremented in all cases, even if it returns an error code. + * Consider using pm_runtime_resume_and_get() instead of it, especially + * if its return value is checked by the caller, as this is likely to result + * in cleaner code. */ static inline int pm_runtime_get_sync(struct device *dev) { diff --git a/include/linux/poison.h b/include/linux/poison.h index aff1c9250c82..d62ef5a6b4e9 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -78,4 +78,7 @@ /********** security/ **********/ #define KEY_DESTROY 0xbd +/********** net/core/page_pool.c **********/ +#define PP_SIGNATURE (0x40 + POISON_POINTER_DELTA) + #endif diff --git a/include/linux/prandom.h b/include/linux/prandom.h index bbf4b4ad61df..056d31317e49 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -111,7 +111,7 @@ static inline u32 __seed(u32 x, u32 m) */ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) { - u32 i = (seed >> 32) ^ (seed << 10) ^ seed; + u32 i = ((seed >> 32) ^ (seed << 10) ^ seed) & 0xffffffffUL; state->s1 = __seed(i, 2U); state->s2 = __seed(i, 8U); diff --git a/include/linux/printk.h b/include/linux/printk.h index fe7eb2351610..e834d78f0478 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -8,6 +8,7 @@ #include #include #include +#include extern const char linux_banner[]; extern const char linux_proc_banner[]; @@ -206,6 +207,7 @@ void __init setup_log_buf(int early); __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...); void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); +extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; extern void printk_safe_flush(void); extern void printk_safe_flush_on_panic(void); @@ -269,6 +271,10 @@ static inline void show_regs_print_info(const char *log_lvl) { } +static inline void dump_stack_lvl(const char *log_lvl) +{ +} + static inline void dump_stack(void) { } @@ -282,6 +288,47 @@ static inline void printk_safe_flush_on_panic(void) } #endif +#ifdef CONFIG_SMP +extern int __printk_cpu_trylock(void); +extern void __printk_wait_on_cpu_lock(void); +extern void __printk_cpu_unlock(void); + +/** + * printk_cpu_lock_irqsave() - Acquire the printk cpu-reentrant spinning + * lock and disable interrupts. + * @flags: Stack-allocated storage for saving local interrupt state, + * to be passed to printk_cpu_unlock_irqrestore(). + * + * If the lock is owned by another CPU, spin until it becomes available. + * Interrupts are restored while spinning. + */ +#define printk_cpu_lock_irqsave(flags) \ + for (;;) { \ + local_irq_save(flags); \ + if (__printk_cpu_trylock()) \ + break; \ + local_irq_restore(flags); \ + __printk_wait_on_cpu_lock(); \ + } + +/** + * printk_cpu_unlock_irqrestore() - Release the printk cpu-reentrant spinning + * lock and restore interrupts. + * @flags: Caller's saved interrupt state, from printk_cpu_lock_irqsave(). + */ +#define printk_cpu_unlock_irqrestore(flags) \ + do { \ + __printk_cpu_unlock(); \ + local_irq_restore(flags); \ + } while (0) \ + +#else + +#define printk_cpu_lock_irqsave(flags) ((void)flags) +#define printk_cpu_unlock_irqrestore(flags) ((void)flags) + +#endif /* CONFIG_SMP */ + extern int kptr_restrict; /** @@ -436,27 +483,9 @@ extern int kptr_restrict; #ifdef CONFIG_PRINTK #define printk_once(fmt, ...) \ -({ \ - static bool __section(".data.once") __print_once; \ - bool __ret_print_once = !__print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - printk(fmt, ##__VA_ARGS__); \ - } \ - unlikely(__ret_print_once); \ -}) + DO_ONCE_LITE(printk, fmt, ##__VA_ARGS__) #define printk_deferred_once(fmt, ...) \ -({ \ - static bool __section(".data.once") __print_once; \ - bool __ret_print_once = !__print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - printk_deferred(fmt, ##__VA_ARGS__); \ - } \ - unlikely(__ret_print_once); \ -}) + DO_ONCE_LITE(printk_deferred, fmt, ##__VA_ARGS__) #else #define printk_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) diff --git a/include/linux/prmt.h b/include/linux/prmt.h new file mode 100644 index 000000000000..24da8364b919 --- /dev/null +++ b/include/linux/prmt.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifdef CONFIG_ACPI_PRMT +void init_prmt(void); +#else +static inline void init_prmt(void) { } +#endif diff --git a/include/linux/property.h b/include/linux/property.h index 0d876316e61d..073e680c35e2 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -119,7 +119,7 @@ struct fwnode_handle *device_get_named_child_node(struct device *dev, struct fwnode_handle *fwnode_handle_get(struct fwnode_handle *fwnode); void fwnode_handle_put(struct fwnode_handle *fwnode); -int fwnode_irq_get(struct fwnode_handle *fwnode, unsigned int index); +int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index); unsigned int device_get_child_node_count(struct device *dev); diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 51d7f1b8b32a..aba237c0b3a2 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -186,6 +186,32 @@ struct ptp_clock_event { }; }; +/** + * scaled_ppm_to_ppb() - convert scaled ppm to ppb + * + * @ppm: Parts per million, but with a 16 bit binary fractional field + */ +static inline long scaled_ppm_to_ppb(long ppm) +{ + /* + * The 'freq' field in the 'struct timex' is in parts per + * million, but with a 16 bit binary fractional field. + * + * We want to calculate + * + * ppb = scaled_ppm * 1000 / 2^16 + * + * which simplifies to + * + * ppb = scaled_ppm * 125 / 2^13 + */ + s64 ppb = 1 + ppm; + + ppb *= 125; + ppb >>= 13; + return (long)ppb; +} + #if IS_REACHABLE(CONFIG_PTP_1588_CLOCK) /** @@ -229,14 +255,6 @@ extern void ptp_clock_event(struct ptp_clock *ptp, extern int ptp_clock_index(struct ptp_clock *ptp); -/** - * scaled_ppm_to_ppb() - convert scaled ppm to ppb - * - * @ppm: Parts per million, but with a 16 bit binary fractional field - */ - -extern long scaled_ppm_to_ppb(long ppm); - /** * ptp_find_pin() - obtain the pin index of a given auxiliary function * diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 977807e1be53..0a3807e927c5 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -702,7 +702,7 @@ enum mf_mode { /* Per-protocol connection types */ enum protocol_type { - PROTOCOLID_ISCSI, + PROTOCOLID_TCP_ULP, PROTOCOLID_FCOE, PROTOCOLID_ROCE, PROTOCOLID_CORE, diff --git a/include/linux/qed/nvmetcp_common.h b/include/linux/qed/nvmetcp_common.h new file mode 100644 index 000000000000..5a2ab0606308 --- /dev/null +++ b/include/linux/qed/nvmetcp_common.h @@ -0,0 +1,531 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright 2021 Marvell. All rights reserved. */ + +#ifndef __NVMETCP_COMMON__ +#define __NVMETCP_COMMON__ + +#include "tcp_common.h" +#include + +#define NVMETCP_SLOW_PATH_LAYER_CODE (6) +#define NVMETCP_WQE_NUM_SGES_SLOWIO (0xf) + +/* NVMeTCP firmware function init parameters */ +struct nvmetcp_spe_func_init { + __le16 half_way_close_timeout; + u8 num_sq_pages_in_ring; + u8 num_r2tq_pages_in_ring; + u8 num_uhq_pages_in_ring; + u8 ll2_rx_queue_id; + u8 flags; +#define NVMETCP_SPE_FUNC_INIT_COUNTERS_EN_MASK 0x1 +#define NVMETCP_SPE_FUNC_INIT_COUNTERS_EN_SHIFT 0 +#define NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE_MASK 0x1 +#define NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE_SHIFT 1 +#define NVMETCP_SPE_FUNC_INIT_RESERVED0_MASK 0x3F +#define NVMETCP_SPE_FUNC_INIT_RESERVED0_SHIFT 2 + u8 debug_flags; + __le16 reserved1; + u8 params; +#define NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT_MASK 0xF +#define NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT_SHIFT 0 +#define NVMETCP_SPE_FUNC_INIT_RESERVED1_MASK 0xF +#define NVMETCP_SPE_FUNC_INIT_RESERVED1_SHIFT 4 + u8 reserved2[5]; + struct scsi_init_func_params func_params; + struct scsi_init_func_queues q_params; +}; + +/* NVMeTCP init params passed by driver to FW in NVMeTCP init ramrod. */ +struct nvmetcp_init_ramrod_params { + struct nvmetcp_spe_func_init nvmetcp_init_spe; + struct tcp_init_params tcp_init; +}; + +/* NVMeTCP Ramrod Command IDs */ +enum nvmetcp_ramrod_cmd_id { + NVMETCP_RAMROD_CMD_ID_UNUSED = 0, + NVMETCP_RAMROD_CMD_ID_INIT_FUNC = 1, + NVMETCP_RAMROD_CMD_ID_DESTROY_FUNC = 2, + NVMETCP_RAMROD_CMD_ID_OFFLOAD_CONN = 3, + NVMETCP_RAMROD_CMD_ID_UPDATE_CONN = 4, + NVMETCP_RAMROD_CMD_ID_TERMINATION_CONN = 5, + NVMETCP_RAMROD_CMD_ID_CLEAR_SQ = 6, + MAX_NVMETCP_RAMROD_CMD_ID +}; + +struct nvmetcp_glbl_queue_entry { + struct regpair cq_pbl_addr; + struct regpair reserved; +}; + +/* NVMeTCP conn level EQEs */ +enum nvmetcp_eqe_opcode { + NVMETCP_EVENT_TYPE_INIT_FUNC = 0, /* Response after init Ramrod */ + NVMETCP_EVENT_TYPE_DESTROY_FUNC, /* Response after destroy Ramrod */ + NVMETCP_EVENT_TYPE_OFFLOAD_CONN,/* Response after option 2 offload Ramrod */ + NVMETCP_EVENT_TYPE_UPDATE_CONN, /* Response after update Ramrod */ + NVMETCP_EVENT_TYPE_CLEAR_SQ, /* Response after clear sq Ramrod */ + NVMETCP_EVENT_TYPE_TERMINATE_CONN, /* Response after termination Ramrod */ + NVMETCP_EVENT_TYPE_RESERVED0, + NVMETCP_EVENT_TYPE_RESERVED1, + NVMETCP_EVENT_TYPE_ASYN_CONNECT_COMPLETE, /* Connect completed (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_TERMINATE_DONE, /* Termination completed (A-syn EQE) */ + NVMETCP_EVENT_TYPE_START_OF_ERROR_TYPES = 10, /* Separate EQs from err EQs */ + NVMETCP_EVENT_TYPE_ASYN_ABORT_RCVD, /* TCP RST packet receive (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_CLOSE_RCVD, /* TCP FIN packet receive (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_SYN_RCVD, /* TCP SYN+ACK packet receive (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_MAX_RT_TIME, /* TCP max retransmit time (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_MAX_RT_CNT, /* TCP max retransmit count (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_MAX_KA_PROBES_CNT, /* TCP ka probes count (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_FIN_WAIT2, /* TCP fin wait 2 (A-syn EQE) */ + NVMETCP_EVENT_TYPE_NVMETCP_CONN_ERROR, /* NVMeTCP error response (A-syn EQE) */ + NVMETCP_EVENT_TYPE_TCP_CONN_ERROR, /* NVMeTCP error - tcp error (A-syn EQE) */ + MAX_NVMETCP_EQE_OPCODE +}; + +struct nvmetcp_conn_offload_section { + struct regpair cccid_itid_table_addr; /* CCCID to iTID table address */ + __le16 cccid_max_range; /* CCCID max value - used for validation */ + __le16 reserved[3]; +}; + +/* NVMe TCP connection offload params passed by driver to FW in NVMeTCP offload ramrod */ +struct nvmetcp_conn_offload_params { + struct regpair sq_pbl_addr; + struct regpair r2tq_pbl_addr; + struct regpair xhq_pbl_addr; + struct regpair uhq_pbl_addr; + __le16 physical_q0; + __le16 physical_q1; + u8 flags; +#define NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_SHIFT 0 +#define NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE_SHIFT 1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_SHIFT 2 +#define NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE_SHIFT 3 +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0xF +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 4 + u8 default_cq; + __le16 reserved0; + __le32 reserved1; + __le32 initial_ack; + + struct nvmetcp_conn_offload_section nvmetcp; /* NVMe/TCP section */ +}; + +/* NVMe TCP and TCP connection offload params passed by driver to FW in NVMeTCP offload ramrod. */ +struct nvmetcp_spe_conn_offload { + __le16 reserved; + __le16 conn_id; + __le32 fw_cid; + struct nvmetcp_conn_offload_params nvmetcp; + struct tcp_offload_params_opt2 tcp; +}; + +/* NVMeTCP connection update params passed by driver to FW in NVMETCP update ramrod. */ +struct nvmetcp_conn_update_ramrod_params { + __le16 reserved0; + __le16 conn_id; + __le32 reserved1; + u8 flags; +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_HD_EN_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_HD_EN_SHIFT 0 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_DD_EN_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_DD_EN_SHIFT 1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED0_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED0_SHIFT 2 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_DATA_SHIFT 3 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED2_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED2_SHIFT 4 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED3_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED3_SHIFT 5 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED4_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED4_SHIFT 6 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED5_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED5_SHIFT 7 + u8 reserved3[3]; + __le32 max_seq_size; + __le32 max_send_pdu_length; + __le32 max_recv_pdu_length; + __le32 first_seq_length; + __le32 reserved4[5]; +}; + +/* NVMeTCP connection termination request */ +struct nvmetcp_spe_conn_termination { + __le16 reserved0; + __le16 conn_id; + __le32 reserved1; + u8 abortive; + u8 reserved2[7]; + struct regpair reserved3; + struct regpair reserved4; +}; + +struct nvmetcp_dif_flags { + u8 flags; +}; + +enum nvmetcp_wqe_type { + NVMETCP_WQE_TYPE_NORMAL, + NVMETCP_WQE_TYPE_TASK_CLEANUP, + NVMETCP_WQE_TYPE_MIDDLE_PATH, + NVMETCP_WQE_TYPE_IC, + MAX_NVMETCP_WQE_TYPE +}; + +struct nvmetcp_wqe { + __le16 task_id; + u8 flags; +#define NVMETCP_WQE_WQE_TYPE_MASK 0x7 /* [use nvmetcp_wqe_type] */ +#define NVMETCP_WQE_WQE_TYPE_SHIFT 0 +#define NVMETCP_WQE_NUM_SGES_MASK 0xF +#define NVMETCP_WQE_NUM_SGES_SHIFT 3 +#define NVMETCP_WQE_RESPONSE_MASK 0x1 +#define NVMETCP_WQE_RESPONSE_SHIFT 7 + struct nvmetcp_dif_flags prot_flags; + __le32 contlen_cdbsize; +#define NVMETCP_WQE_CONT_LEN_MASK 0xFFFFFF +#define NVMETCP_WQE_CONT_LEN_SHIFT 0 +#define NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD_MASK 0xFF +#define NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD_SHIFT 24 +}; + +struct nvmetcp_host_cccid_itid_entry { + __le16 itid; +}; + +struct nvmetcp_connect_done_results { + __le16 icid; + __le16 conn_id; + struct tcp_ulp_connect_done_params params; +}; + +struct nvmetcp_eqe_data { + __le16 icid; + __le16 conn_id; + __le16 reserved; + u8 error_code; + u8 error_pdu_opcode_reserved; +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_MASK 0x3F +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_SHIFT 0 +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_VALID_MASK 0x1 +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_VALID_SHIFT 6 +#define NVMETCP_EQE_DATA_RESERVED0_MASK 0x1 +#define NVMETCP_EQE_DATA_RESERVED0_SHIFT 7 +}; + +enum nvmetcp_task_type { + NVMETCP_TASK_TYPE_HOST_WRITE, + NVMETCP_TASK_TYPE_HOST_READ, + NVMETCP_TASK_TYPE_INIT_CONN_REQUEST, + NVMETCP_TASK_TYPE_RESERVED0, + NVMETCP_TASK_TYPE_CLEANUP, + NVMETCP_TASK_TYPE_HOST_READ_NO_CQE, + MAX_NVMETCP_TASK_TYPE +}; + +struct nvmetcp_db_data { + u8 params; +#define NVMETCP_DB_DATA_DEST_MASK 0x3 /* destination of doorbell (use enum db_dest) */ +#define NVMETCP_DB_DATA_DEST_SHIFT 0 +#define NVMETCP_DB_DATA_AGG_CMD_MASK 0x3 /* aggregative command to CM (use enum db_agg_cmd_sel) */ +#define NVMETCP_DB_DATA_AGG_CMD_SHIFT 2 +#define NVMETCP_DB_DATA_BYPASS_EN_MASK 0x1 /* enable QM bypass */ +#define NVMETCP_DB_DATA_BYPASS_EN_SHIFT 4 +#define NVMETCP_DB_DATA_RESERVED_MASK 0x1 +#define NVMETCP_DB_DATA_RESERVED_SHIFT 5 +#define NVMETCP_DB_DATA_AGG_VAL_SEL_MASK 0x3 /* aggregative value selection */ +#define NVMETCP_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; /* bit for every DQ counter flags in CM context that DQ can increment */ + __le16 sq_prod; +}; + +struct nvmetcp_fw_nvmf_cqe { + __le32 reserved[4]; +}; + +struct nvmetcp_icresp_mdata { + u8 digest; + u8 cpda; + __le16 pfv; + __le32 maxdata; + __le16 rsvd[4]; +}; + +union nvmetcp_fw_cqe_data { + struct nvmetcp_fw_nvmf_cqe nvme_cqe; + struct nvmetcp_icresp_mdata icresp_mdata; +}; + +struct nvmetcp_fw_cqe { + __le16 conn_id; + u8 cqe_type; + u8 cqe_error_status_bits; +#define CQE_ERROR_BITMAP_DIF_ERR_BITS_MASK 0x7 +#define CQE_ERROR_BITMAP_DIF_ERR_BITS_SHIFT 0 +#define CQE_ERROR_BITMAP_DATA_DIGEST_ERR_MASK 0x1 +#define CQE_ERROR_BITMAP_DATA_DIGEST_ERR_SHIFT 3 +#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN_MASK 0x1 +#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN_SHIFT 4 + __le16 itid; + u8 task_type; + u8 fw_dbg_field; + u8 caused_conn_err; + u8 reserved0[3]; + __le32 reserved1; + union nvmetcp_fw_cqe_data cqe_data; + struct regpair task_opaque; + __le32 reserved[6]; +}; + +enum nvmetcp_fw_cqes_type { + NVMETCP_FW_CQE_TYPE_NORMAL = 1, + NVMETCP_FW_CQE_TYPE_RESERVED0, + NVMETCP_FW_CQE_TYPE_RESERVED1, + NVMETCP_FW_CQE_TYPE_CLEANUP, + NVMETCP_FW_CQE_TYPE_DUMMY, + MAX_NVMETCP_FW_CQES_TYPE +}; + +struct ystorm_nvmetcp_task_state { + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; + __le32 resrved0; + __le32 buffer_offset; + __le16 cccid; + struct nvmetcp_dif_flags dif_flags; + u8 flags; +#define YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP_SHIFT 0 +#define YSTORM_NVMETCP_TASK_STATE_SLOW_IO_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_SLOW_IO_SHIFT 1 +#define YSTORM_NVMETCP_TASK_STATE_SET_DIF_OFFSET_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_SET_DIF_OFFSET_SHIFT 2 +#define YSTORM_NVMETCP_TASK_STATE_SEND_W_RSP_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_SEND_W_RSP_SHIFT 3 +}; + +struct ystorm_nvmetcp_task_rxmit_opt { + __le32 reserved[4]; +}; + +struct nvmetcp_task_hdr { + __le32 reg[18]; +}; + +struct nvmetcp_task_hdr_aligned { + struct nvmetcp_task_hdr task_hdr; + __le32 reserved[2]; /* HSI_COMMENT: Align to QREG */ +}; + +struct e5_tdif_task_context { + __le32 reserved[16]; +}; + +struct e5_rdif_task_context { + __le32 reserved[12]; +}; + +struct ystorm_nvmetcp_task_st_ctx { + struct ystorm_nvmetcp_task_state state; + struct ystorm_nvmetcp_task_rxmit_opt rxmit_opt; + struct nvmetcp_task_hdr_aligned pdu_hdr; +}; + +struct mstorm_nvmetcp_task_st_ctx { + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; + __le32 rem_task_size; + __le32 data_buffer_offset; + u8 task_type; + struct nvmetcp_dif_flags dif_flags; + __le16 dif_task_icid; + struct regpair reserved0; + __le32 expected_itt; + __le32 reserved1; +}; + +struct ustorm_nvmetcp_task_st_ctx { + __le32 rem_rcv_len; + __le32 exp_data_transfer_len; + __le32 exp_data_sn; + struct regpair reserved0; + __le32 reg1_map; +#define REG1_NUM_SGES_MASK 0xF +#define REG1_NUM_SGES_SHIFT 0 +#define REG1_RESERVED1_MASK 0xFFFFFFF +#define REG1_RESERVED1_SHIFT 4 + u8 flags2; +#define USTORM_NVMETCP_TASK_ST_CTX_AHS_EXIST_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_AHS_EXIST_SHIFT 0 +#define USTORM_NVMETCP_TASK_ST_CTX_RESERVED1_MASK 0x7F +#define USTORM_NVMETCP_TASK_ST_CTX_RESERVED1_SHIFT 1 + struct nvmetcp_dif_flags dif_flags; + __le16 reserved3; + __le16 tqe_opaque[2]; + __le32 reserved5; + __le32 nvme_tcp_opaque_lo; + __le32 nvme_tcp_opaque_hi; + u8 task_type; + u8 error_flags; +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_DIGEST_ERROR_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_DIGEST_ERROR_SHIFT 0 +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_TRUNCATED_ERROR_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_TRUNCATED_ERROR_SHIFT 1 +#define USTORM_NVMETCP_TASK_ST_CTX_UNDER_RUN_ERROR_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_UNDER_RUN_ERROR_SHIFT 2 +#define USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP_SHIFT 3 + u8 flags; +#define USTORM_NVMETCP_TASK_ST_CTX_CQE_WRITE_MASK 0x3 +#define USTORM_NVMETCP_TASK_ST_CTX_CQE_WRITE_SHIFT 0 +#define USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP_SHIFT 2 +#define USTORM_NVMETCP_TASK_ST_CTX_Q0_R2TQE_WRITE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_Q0_R2TQE_WRITE_SHIFT 3 +#define USTORM_NVMETCP_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_SHIFT 4 +#define USTORM_NVMETCP_TASK_ST_CTX_HQ_SCANNED_DONE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_HQ_SCANNED_DONE_SHIFT 5 +#define USTORM_NVMETCP_TASK_ST_CTX_R2T2RECV_DONE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_R2T2RECV_DONE_SHIFT 6 + u8 cq_rss_number; +}; + +struct e5_ystorm_nvmetcp_task_ag_ctx { + u8 reserved /* cdu_validation */; + u8 byte1 /* state_and_core_id */; + __le16 word0 /* icid */; + u8 flags0; + u8 flags1; + u8 flags2; + u8 flags3; + __le32 TTT; + u8 byte2; + u8 byte3; + u8 byte4; + u8 e4_reserved7; +}; + +struct e5_mstorm_nvmetcp_task_ag_ctx { + u8 cdu_validation; + u8 byte1; + __le16 task_cid; + u8 flags0; +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_VALID_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_VALID_SHIFT 6 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_FLAG_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_FLAG_SHIFT 7 + u8 flags1; +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_MASK 0x3 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_SHIFT 0 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1_MASK 0x3 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1_SHIFT 2 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF2_MASK 0x3 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF2_SHIFT 4 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_EN_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_EN_SHIFT 6 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1EN_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1EN_SHIFT 7 + u8 flags2; + u8 flags3; + __le32 reg0; + u8 byte2; + u8 byte3; + u8 byte4; + u8 e4_reserved7; +}; + +struct e5_ustorm_nvmetcp_task_ag_ctx { + u8 reserved; + u8 state_and_core_id; + __le16 icid; + u8 flags0; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_SHIFT 6 + u8 flags1; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED1_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED1_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3_SHIFT 4 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6 + u8 flags2; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_EN_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DISABLE_DATA_ACKED_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DISABLE_DATA_ACKED_SHIFT 1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_EN_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3EN_SHIFT 3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_SHIFT 5 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RULE1EN_SHIFT 6 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_SHIFT 7 + u8 flags3; + u8 flags4; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED5_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED5_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED6_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED6_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED7_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED7_SHIFT 3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 + u8 byte2; + u8 byte3; + u8 e4_reserved8; + __le32 dif_err_intervals; + __le32 dif_error_1st_interval; + __le32 rcv_cont_len; + __le32 exp_cont_len; + __le32 total_data_acked; + __le32 exp_data_acked; + __le16 word1; + __le16 next_tid; + __le32 hdr_residual_count; + __le32 exp_r2t_sn; +}; + +struct e5_nvmetcp_task_context { + struct ystorm_nvmetcp_task_st_ctx ystorm_st_context; + struct e5_ystorm_nvmetcp_task_ag_ctx ystorm_ag_context; + struct regpair ystorm_ag_padding[2]; + struct e5_tdif_task_context tdif_context; + struct e5_mstorm_nvmetcp_task_ag_ctx mstorm_ag_context; + struct regpair mstorm_ag_padding[2]; + struct e5_ustorm_nvmetcp_task_ag_ctx ustorm_ag_context; + struct regpair ustorm_ag_padding[2]; + struct mstorm_nvmetcp_task_st_ctx mstorm_st_context; + struct regpair mstorm_st_padding[2]; + struct ustorm_nvmetcp_task_st_ctx ustorm_st_context; + struct regpair ustorm_st_padding[2]; + struct e5_rdif_task_context rdif_context; +}; + +#endif /* __NVMETCP_COMMON__*/ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 68d17a4fbf20..850b98991670 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -542,6 +542,22 @@ struct qed_iscsi_pf_params { u8 bdq_pbl_num_entries[3]; }; +struct qed_nvmetcp_pf_params { + u64 glbl_q_params_addr; + u16 cq_num_entries; + u16 num_cons; + u16 num_tasks; + u8 num_sq_pages_in_ring; + u8 num_r2tq_pages_in_ring; + u8 num_uhq_pages_in_ring; + u8 num_queues; + u8 gl_rq_pi; + u8 gl_cmd_pi; + u8 debug_mode; + u8 ll2_ooo_queue_id; + u16 min_rto; +}; + struct qed_rdma_pf_params { /* Supplied to QED during resource allocation (may affect the ILT and * the doorbell BAR). @@ -560,6 +576,7 @@ struct qed_pf_params { struct qed_eth_pf_params eth_pf_params; struct qed_fcoe_pf_params fcoe_pf_params; struct qed_iscsi_pf_params iscsi_pf_params; + struct qed_nvmetcp_pf_params nvmetcp_pf_params; struct qed_rdma_pf_params rdma_pf_params; }; @@ -662,6 +679,7 @@ enum qed_sb_type { enum qed_protocol { QED_PROTOCOL_ETH, QED_PROTOCOL_ISCSI, + QED_PROTOCOL_NVMETCP = QED_PROTOCOL_ISCSI, QED_PROTOCOL_FCOE, }; diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index ea273ba1c991..ff808d248883 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -18,7 +18,7 @@ enum qed_ll2_conn_type { QED_LL2_TYPE_FCOE, - QED_LL2_TYPE_ISCSI, + QED_LL2_TYPE_TCP_ULP, QED_LL2_TYPE_TEST, QED_LL2_TYPE_OOO, QED_LL2_TYPE_RESERVED2, diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h new file mode 100644 index 000000000000..14671bc19ed1 --- /dev/null +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -0,0 +1,240 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright 2021 Marvell. All rights reserved. */ + +#ifndef _QED_NVMETCP_IF_H +#define _QED_NVMETCP_IF_H +#include +#include +#include +#include + +#define QED_NVMETCP_MAX_IO_SIZE 0x800000 +#define QED_NVMETCP_CMN_HDR_SIZE (sizeof(struct nvme_tcp_hdr)) +#define QED_NVMETCP_CMD_HDR_SIZE (sizeof(struct nvme_tcp_cmd_pdu)) +#define QED_NVMETCP_NON_IO_HDR_SIZE ((QED_NVMETCP_CMN_HDR_SIZE + 16)) + +typedef int (*nvmetcp_event_cb_t) (void *context, + u8 fw_event_code, void *fw_handle); + +struct qed_dev_nvmetcp_info { + struct qed_dev_info common; + u8 port_id; /* Physical port */ + u8 num_cqs; +}; + +#define MAX_TID_BLOCKS_NVMETCP (512) +struct qed_nvmetcp_tid { + u32 size; /* In bytes per task */ + u32 num_tids_per_block; + u8 *blocks[MAX_TID_BLOCKS_NVMETCP]; +}; + +struct qed_nvmetcp_id_params { + u8 mac[ETH_ALEN]; + u32 ip[4]; + u16 port; +}; + +struct qed_nvmetcp_params_offload { + /* FW initializations */ + dma_addr_t sq_pbl_addr; + dma_addr_t nvmetcp_cccid_itid_table_addr; + u16 nvmetcp_cccid_max_range; + u8 default_cq; + + /* Networking and TCP stack initializations */ + struct qed_nvmetcp_id_params src; + struct qed_nvmetcp_id_params dst; + u32 ka_timeout; + u32 ka_interval; + u32 max_rt_time; + u32 cwnd; + u16 mss; + u16 vlan_id; + bool timestamp_en; + bool delayed_ack_en; + bool tcp_keep_alive_en; + bool ecn_en; + u8 ip_version; + u8 ka_max_probe_cnt; + u8 ttl; + u8 tos_or_tc; + u8 rcv_wnd_scale; +}; + +struct qed_nvmetcp_params_update { + u32 max_io_size; + u32 max_recv_pdu_length; + u32 max_send_pdu_length; + + /* Placeholder: pfv, cpda, hpda */ + + bool hdr_digest_en; + bool data_digest_en; +}; + +struct qed_nvmetcp_cb_ops { + struct qed_common_cb_ops common; +}; + +struct nvmetcp_sge { + struct regpair sge_addr; /* SGE address */ + __le32 sge_len; /* SGE length */ + __le32 reserved; +}; + +/* IO path HSI function SGL params */ +struct storage_sgl_task_params { + struct nvmetcp_sge *sgl; + struct regpair sgl_phys_addr; + u32 total_buffer_size; + u16 num_sges; + bool small_mid_sge; +}; + +/* IO path HSI function FW task context params */ +struct nvmetcp_task_params { + void *context; /* Output parameter - set/filled by the HSI function */ + struct nvmetcp_wqe *sqe; + u32 tx_io_size; /* in bytes (Without DIF, if exists) */ + u32 rx_io_size; /* in bytes (Without DIF, if exists) */ + u16 conn_icid; + u16 itid; + struct regpair opq; /* qedn_task_ctx address */ + u16 host_cccid; + u8 cq_rss_number; + bool send_write_incapsule; +}; + +/** + * struct qed_nvmetcp_ops - qed NVMeTCP operations. + * @common: common operations pointer + * @ll2: light L2 operations pointer + * @fill_dev_info: fills NVMeTCP specific information + * @param cdev + * @param info + * @return 0 on success, otherwise error value. + * @register_ops: register nvmetcp operations + * @param cdev + * @param ops - specified using qed_nvmetcp_cb_ops + * @param cookie - driver private + * @start: nvmetcp in FW + * @param cdev + * @param tasks - qed will fill information about tasks + * return 0 on success, otherwise error value. + * @stop: nvmetcp in FW + * @param cdev + * return 0 on success, otherwise error value. + * @acquire_conn: acquire a new nvmetcp connection + * @param cdev + * @param handle - qed will fill handle that should be + * used henceforth as identifier of the + * connection. + * @param p_doorbell - qed will fill the address of the + * doorbell. + * @return 0 on sucesss, otherwise error value. + * @release_conn: release a previously acquired nvmetcp connection + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @offload_conn: configures an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @param conn_info - the configuration to use for the + * offload. + * @return 0 on success, otherwise error value. + * @update_conn: updates an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @param conn_info - the configuration to use for the + * offload. + * @return 0 on success, otherwise error value. + * @destroy_conn: stops an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @clear_sq: clear all task in sq + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @add_src_tcp_port_filter: Add source tcp port filter + * @param cdev + * @param src_port + * @remove_src_tcp_port_filter: Remove source tcp port filter + * @param cdev + * @param src_port + * @add_dst_tcp_port_filter: Add destination tcp port filter + * @param cdev + * @param dest_port + * @remove_dst_tcp_port_filter: Remove destination tcp port filter + * @param cdev + * @param dest_port + * @clear_all_filters: Clear all filters. + * @param cdev + */ +struct qed_nvmetcp_ops { + const struct qed_common_ops *common; + + const struct qed_ll2_ops *ll2; + + int (*fill_dev_info)(struct qed_dev *cdev, + struct qed_dev_nvmetcp_info *info); + + void (*register_ops)(struct qed_dev *cdev, + struct qed_nvmetcp_cb_ops *ops, void *cookie); + + int (*start)(struct qed_dev *cdev, + struct qed_nvmetcp_tid *tasks, + void *event_context, nvmetcp_event_cb_t async_event_cb); + + int (*stop)(struct qed_dev *cdev); + + int (*acquire_conn)(struct qed_dev *cdev, + u32 *handle, + u32 *fw_cid, void __iomem **p_doorbell); + + int (*release_conn)(struct qed_dev *cdev, u32 handle); + + int (*offload_conn)(struct qed_dev *cdev, + u32 handle, + struct qed_nvmetcp_params_offload *conn_info); + + int (*update_conn)(struct qed_dev *cdev, + u32 handle, + struct qed_nvmetcp_params_update *conn_info); + + int (*destroy_conn)(struct qed_dev *cdev, u32 handle, u8 abrt_conn); + + int (*clear_sq)(struct qed_dev *cdev, u32 handle); + + int (*add_src_tcp_port_filter)(struct qed_dev *cdev, u16 src_port); + + void (*remove_src_tcp_port_filter)(struct qed_dev *cdev, u16 src_port); + + int (*add_dst_tcp_port_filter)(struct qed_dev *cdev, u16 dest_port); + + void (*remove_dst_tcp_port_filter)(struct qed_dev *cdev, u16 dest_port); + + void (*clear_all_filters)(struct qed_dev *cdev); + + void (*init_read_io)(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params); + + void (*init_write_io)(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params); + + void (*init_icreq_exchange)(struct nvmetcp_task_params *task_params, + struct nvme_tcp_icreq_pdu *init_conn_req_pdu_hdr, + struct storage_sgl_task_params *tx_sgl_task_params, + struct storage_sgl_task_params *rx_sgl_task_params); + + void (*init_task_cleanup)(struct nvmetcp_task_params *task_params); +}; + +const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void); +void qed_put_nvmetcp_ops(void); +#endif diff --git a/include/linux/qed/qed_nvmetcp_ip_services_if.h b/include/linux/qed/qed_nvmetcp_ip_services_if.h new file mode 100644 index 000000000000..3604aee53796 --- /dev/null +++ b/include/linux/qed/qed_nvmetcp_ip_services_if.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* + * Copyright 2021 Marvell. All rights reserved. + */ + +#ifndef _QED_IP_SERVICES_IF_H +#define _QED_IP_SERVICES_IF_H + +#include +#include +#include +#include + +int qed_route_ipv4(struct sockaddr_storage *local_addr, + struct sockaddr_storage *remote_addr, + struct sockaddr *hardware_address, + struct net_device **ndev); +int qed_route_ipv6(struct sockaddr_storage *local_addr, + struct sockaddr_storage *remote_addr, + struct sockaddr *hardware_address, + struct net_device **ndev); +void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id); +struct pci_dev *qed_validate_ndev(struct net_device *ndev); +void qed_return_tcp_port(struct socket *sock); +int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr, + struct socket **sock, u16 *port); +__be16 qed_get_in_port(struct sockaddr_storage *sa); + +#endif /* _QED_IP_SERVICES_IF_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9455476c5ba2..d7895b81264e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -363,6 +363,20 @@ static inline void rcu_preempt_sleep_check(void) { } #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ +/** + * unrcu_pointer - mark a pointer as not being RCU protected + * @p: pointer needing to lose its __rcu property + * + * Converts @p from an __rcu pointer to a __kernel pointer. + * This allows an __rcu pointer to be used with xchg() and friends. + */ +#define unrcu_pointer(p) \ +({ \ + typeof(*p) *_________p1 = (typeof(*p) *__force)(p); \ + rcu_check_sparse(p, __rcu); \ + ((typeof(*p) __force __kernel *)(_________p1)); \ +}) + #define __rcu_access_pointer(p, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index dfd82eab2902..4d9e3a656875 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -73,6 +73,14 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_OOM_VICTIM 25 /* mm is the oom victim */ #define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ #define MMF_MULTIPROCESS 27 /* mm is shared between processes */ +/* + * MMF_HAS_PINNED: Whether this mm has pinned any pages. This can be either + * replaced in the future by mm.pinned_vm when it becomes stable, or grow into + * a counter on its own. We're aggresive on this bit for now: even if the + * pinned pages were unpinned later on, we'll still keep this bit set for the + * lifecycle of this mm, just for simplicity. + */ +#define MMF_HAS_PINNED 28 /* FOLL_PIN has run, never cleared */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 3632c5d6ec55..2462f7d07695 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -12,16 +12,9 @@ */ struct user_struct { refcount_t __count; /* reference count */ - atomic_t processes; /* How many processes does this user have? */ - atomic_t sigpending; /* How many pending signals does this user have? */ #ifdef CONFIG_EPOLL atomic_long_t epoll_watches; /* The number of file descriptors currently watched */ #endif -#ifdef CONFIG_POSIX_MQUEUE - /* protected by mq_lock */ - unsigned long mq_bytes; /* How many bytes can be allocated to mqueue? */ -#endif - unsigned long locked_shm; /* How many pages of mlocked shm ? */ unsigned long unix_inflight; /* How many files in flight in unix sockets */ atomic_long_t pipe_bufs; /* how many pages are allocated in pipe buffers */ diff --git a/include/linux/sctp.h b/include/linux/sctp.h index bb1926589693..a86e852507b3 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -98,6 +98,7 @@ enum sctp_cid { SCTP_CID_I_FWD_TSN = 0xC2, SCTP_CID_ASCONF_ACK = 0x80, SCTP_CID_RECONF = 0x82, + SCTP_CID_PAD = 0x84, }; /* enum */ @@ -410,6 +411,12 @@ struct sctp_heartbeat_chunk { }; +/* PAD chunk could be bundled with heartbeat chunk to probe pmtu */ +struct sctp_pad_chunk { + struct sctp_chunkhdr uh; +}; + + /* For the abort and shutdown ACK we must carry the init tag in the * common header. Just the common header is all that is needed with a * chunk descriptor. diff --git a/include/linux/security.h b/include/linux/security.h index 06f7c50ce77f..24eda04221e9 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1681,7 +1681,7 @@ int security_xfrm_state_alloc_acquire(struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid); int security_xfrm_state_delete(struct xfrm_state *x); void security_xfrm_state_free(struct xfrm_state *x); -int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir); +int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid); int security_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic); @@ -1732,7 +1732,7 @@ static inline int security_xfrm_state_delete(struct xfrm_state *x) return 0; } -static inline int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir) +static inline int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid) { return 0; } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index d82b6f396588..aa77dcd1646f 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -65,7 +65,7 @@ extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt, extern int shmem_zero_setup(struct vm_area_struct *); extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); -extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern int shmem_lock(struct file *file, int lock, struct ucounts *ucounts); #ifdef CONFIG_SHMEM extern const struct address_space_operations shmem_aops; static inline bool shmem_mapping(struct address_space *mapping) diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index 68e06c75c5b2..34cb28b8f16c 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -13,6 +13,8 @@ typedef struct kernel_siginfo { __SIGINFO; } kernel_siginfo_t; +struct ucounts; + /* * Real Time signals may be queued. */ @@ -21,7 +23,7 @@ struct sigqueue { struct list_head list; int flags; kernel_siginfo_t info; - struct user_struct *user; + struct ucounts *ucounts; }; /* flags values. */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dbf820a50a39..b2db9cd9a73f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -37,6 +37,7 @@ #include #include #include +#include #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include #endif @@ -667,6 +668,8 @@ typedef unsigned char *sk_buff_data_t; * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves + * @pp_recycle: mark the packet for recycling instead of freeing (implies + * page_pool support on driver) * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed @@ -791,10 +794,12 @@ struct sk_buff { fclone:2, peeked:1, head_frag:1, - pfmemalloc:1; + pfmemalloc:1, + pp_recycle:1; /* page_pool recycle indicator */ #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif + /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() */ @@ -3081,12 +3086,20 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) /** * __skb_frag_unref - release a reference on a paged fragment. * @frag: the paged fragment + * @recycle: recycle the page if allocated via page_pool * - * Releases a reference on the paged fragment @frag. + * Releases a reference on the paged fragment @frag + * or recycles the page via the page_pool API. */ -static inline void __skb_frag_unref(skb_frag_t *frag) +static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { - put_page(skb_frag_page(frag)); + struct page *page = skb_frag_page(frag); + +#ifdef CONFIG_PAGE_POOL + if (recycle && page_pool_return_skb_page(page)) + return; +#endif + put_page(page); } /** @@ -3098,7 +3111,7 @@ static inline void __skb_frag_unref(skb_frag_t *frag) */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { - __skb_frag_unref(&skb_shinfo(skb)->frags[f]); + __skb_frag_unref(&skb_shinfo(skb)->frags[f], skb->pp_recycle); } /** @@ -4697,5 +4710,21 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb) #endif } +#ifdef CONFIG_PAGE_POOL +static inline void skb_mark_for_recycle(struct sk_buff *skb, struct page *page, + struct page_pool *pp) +{ + skb->pp_recycle = 1; + page_pool_store_mem_info(page, pp); +} +#endif + +static inline bool skb_pp_recycle(struct sk_buff *skb, void *data) +{ + if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) + return false; + return page_pool_return_skb_page(virt_to_page(data)); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index aba0f0f429be..96f319099744 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -126,8 +126,6 @@ int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); -int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, - long timeo, int *err); int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); @@ -348,7 +346,7 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err) struct sock *sk = psock->sk; sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } struct sk_psock *sk_psock_init(struct sock *sk, int node); diff --git a/include/linux/slab.h b/include/linux/slab.h index 0c97d788762c..083f3ce550bc 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -305,9 +305,21 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, /* * Whenever changing this, take care of that kmalloc_type() and * create_kmalloc_caches() still work as intended. + * + * KMALLOC_NORMAL can contain only unaccounted objects whereas KMALLOC_CGROUP + * is for accounted but unreclaimable and non-dma objects. All the other + * kmem caches can have both accounted and unaccounted objects. */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, +#ifndef CONFIG_ZONE_DMA + KMALLOC_DMA = KMALLOC_NORMAL, +#endif +#ifndef CONFIG_MEMCG_KMEM + KMALLOC_CGROUP = KMALLOC_NORMAL, +#else + KMALLOC_CGROUP, +#endif KMALLOC_RECLAIM, #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, @@ -319,24 +331,36 @@ enum kmalloc_cache_type { extern struct kmem_cache * kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; +/* + * Define gfp bits that should not be set for KMALLOC_NORMAL. + */ +#define KMALLOC_NOT_NORMAL_BITS \ + (__GFP_RECLAIMABLE | \ + (IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \ + (IS_ENABLED(CONFIG_MEMCG_KMEM) ? __GFP_ACCOUNT : 0)) + static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) { -#ifdef CONFIG_ZONE_DMA /* * The most common case is KMALLOC_NORMAL, so test for it - * with a single branch for both flags. + * with a single branch for all the relevant flags. */ - if (likely((flags & (__GFP_DMA | __GFP_RECLAIMABLE)) == 0)) + if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0)) return KMALLOC_NORMAL; /* - * At least one of the flags has to be set. If both are, __GFP_DMA - * is more important. + * At least one of the flags has to be set. Their priorities in + * decreasing order are: + * 1) __GFP_DMA + * 2) __GFP_RECLAIMABLE + * 3) __GFP_ACCOUNT */ - return flags & __GFP_DMA ? KMALLOC_DMA : KMALLOC_RECLAIM; -#else - return flags & __GFP_RECLAIMABLE ? KMALLOC_RECLAIM : KMALLOC_NORMAL; -#endif + if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA)) + return KMALLOC_DMA; + if (!IS_ENABLED(CONFIG_MEMCG_KMEM) || (flags & __GFP_RECLAIMABLE)) + return KMALLOC_RECLAIM; + else + return KMALLOC_CGROUP; } /* @@ -346,8 +370,14 @@ static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) * 1 = 65 .. 96 bytes * 2 = 129 .. 192 bytes * n = 2^(n-1)+1 .. 2^n + * + * Note: __kmalloc_index() is compile-time optimized, and not runtime optimized; + * typical usage is via kmalloc_index() and therefore evaluated at compile-time. + * Callers where !size_is_constant should only be test modules, where runtime + * overheads of __kmalloc_index() can be tolerated. Also see kmalloc_slab(). */ -static __always_inline unsigned int kmalloc_index(size_t size) +static __always_inline unsigned int __kmalloc_index(size_t size, + bool size_is_constant) { if (!size) return 0; @@ -382,12 +412,17 @@ static __always_inline unsigned int kmalloc_index(size_t size) if (size <= 8 * 1024 * 1024) return 23; if (size <= 16 * 1024 * 1024) return 24; if (size <= 32 * 1024 * 1024) return 25; - if (size <= 64 * 1024 * 1024) return 26; - BUG(); + + if ((IS_ENABLED(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 110000) + && !IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) + BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()"); + else + BUG(); /* Will never be reached. Needed because the compiler may complain */ return -1; } +#define kmalloc_index(s) __kmalloc_index(s, true) #endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 0db36360ef21..d5ae621d66ba 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -172,6 +172,18 @@ struct stmmac_fpe_cfg { enum stmmac_fpe_state lo_fpe_state; /* Local station FPE state */ }; +struct stmmac_safety_feature_cfg { + u32 tsoee; + u32 mrxpee; + u32 mestee; + u32 mrxee; + u32 mtxee; + u32 epsi; + u32 edpp; + u32 prtyen; + u32 tmouten; +}; + struct plat_stmmacenet_data { int bus_id; int phy_addr; @@ -184,6 +196,7 @@ struct plat_stmmacenet_data { struct stmmac_dma_cfg *dma_cfg; struct stmmac_est *est; struct stmmac_fpe_cfg *fpe_cfg; + struct stmmac_safety_feature_cfg *safety_feat_cfg; int clk_csr; int has_gmac; int enh_desc; @@ -210,6 +223,7 @@ struct plat_stmmacenet_data { void (*fix_mac_speed)(void *priv, unsigned int speed); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); + void (*speed_mode_2500)(struct net_device *ndev, void *priv); void (*ptp_clk_freq_config)(void *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); @@ -223,8 +237,10 @@ struct plat_stmmacenet_data { struct clk *clk_ptp_ref; unsigned int clk_ptp_rate; unsigned int clk_ref_rate; + unsigned int mult_fact_100ns; s32 ptp_max_adj; struct reset_control *stmmac_rst; + struct reset_control *stmmac_ahb_rst; struct stmmac_axi *axi; int has_gmac4; bool has_sun8i; @@ -249,5 +265,6 @@ struct plat_stmmacenet_data { int msi_sfty_ue_vec; int msi_rx_base_vec; int msi_tx_base_vec; + bool use_phy_wol; }; #endif diff --git a/include/linux/surface_aggregator/controller.h b/include/linux/surface_aggregator/controller.h index 0806796eabcb..068e1982ad37 100644 --- a/include/linux/surface_aggregator/controller.h +++ b/include/linux/surface_aggregator/controller.h @@ -6,7 +6,7 @@ * managing access and communication to and from the SSAM EC, as well as main * communication structures and definitions. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #ifndef _LINUX_SURFACE_AGGREGATOR_CONTROLLER_H @@ -795,6 +795,20 @@ enum ssam_event_mask { #define SSAM_EVENT_REGISTRY_REG \ SSAM_EVENT_REGISTRY(SSAM_SSH_TC_REG, 0x02, 0x01, 0x02) +/** + * enum ssam_event_notifier_flags - Flags for event notifiers. + * @SSAM_EVENT_NOTIFIER_OBSERVER: + * The corresponding notifier acts as observer. Registering a notifier + * with this flag set will not attempt to enable any event. Equally, + * unregistering will not attempt to disable any event. Note that a + * notifier with this flag may not even correspond to a certain event at + * all, only to a specific event target category. Event matching will not + * be influenced by this flag. + */ +enum ssam_event_notifier_flags { + SSAM_EVENT_NOTIFIER_OBSERVER = BIT(0), +}; + /** * struct ssam_event_notifier - Notifier block for SSAM events. * @base: The base notifier block with callback function and priority. @@ -803,6 +817,7 @@ enum ssam_event_mask { * @event.id: ID specifying the event. * @event.mask: Flags determining how events are matched to the notifier. * @event.flags: Flags used for enabling the event. + * @flags: Notifier flags (see &enum ssam_event_notifier_flags). */ struct ssam_event_notifier { struct ssam_notifier_block base; @@ -813,6 +828,8 @@ struct ssam_event_notifier { enum ssam_event_mask mask; u8 flags; } event; + + unsigned long flags; }; int ssam_notifier_register(struct ssam_controller *ctrl, @@ -821,4 +838,12 @@ int ssam_notifier_register(struct ssam_controller *ctrl, int ssam_notifier_unregister(struct ssam_controller *ctrl, struct ssam_event_notifier *n); +int ssam_controller_event_enable(struct ssam_controller *ctrl, + struct ssam_event_registry reg, + struct ssam_event_id id, u8 flags); + +int ssam_controller_event_disable(struct ssam_controller *ctrl, + struct ssam_event_registry reg, + struct ssam_event_id id, u8 flags); + #endif /* _LINUX_SURFACE_AGGREGATOR_CONTROLLER_H */ diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index 6ff9c58b3e17..f636c5310321 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -7,7 +7,7 @@ * Provides support for non-platform/non-ACPI SSAM clients via dedicated * subsystem. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #ifndef _LINUX_SURFACE_AGGREGATOR_DEVICE_H diff --git a/include/linux/surface_aggregator/serial_hub.h b/include/linux/surface_aggregator/serial_hub.h index 64276fbfa1d5..c3de43edcffa 100644 --- a/include/linux/surface_aggregator/serial_hub.h +++ b/include/linux/surface_aggregator/serial_hub.h @@ -6,7 +6,7 @@ * Surface System Aggregator Module (SSAM). Provides the interface for basic * packet- and request-based communication with the SSAM EC via SSH. * - * Copyright (C) 2019-2020 Maximilian Luz + * Copyright (C) 2019-2021 Maximilian Luz */ #ifndef _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H diff --git a/include/linux/swap.h b/include/linux/swap.h index 144727041e78..49b1dd2c100b 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -177,7 +177,6 @@ enum { SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ - SWP_VALID = (1 << 13), /* swap is valid to be operated on? */ /* add others here before... */ SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */ }; @@ -240,6 +239,7 @@ struct swap_cluster_list { * The in-memory structure used to track swap areas. */ struct swap_info_struct { + struct percpu_ref users; /* indicate and keep swap device valid. */ unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ @@ -260,6 +260,7 @@ struct swap_info_struct { struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ unsigned int old_block_size; /* seldom referenced */ + struct completion comp; /* seldom referenced */ #ifdef CONFIG_FRONTSWAP unsigned long *frontswap_map; /* frontswap in-use, one bit per page */ atomic_t frontswap_pages; /* frontswap pages in-use counter */ @@ -445,6 +446,7 @@ extern void __delete_from_swap_cache(struct page *page, extern void delete_from_swap_cache(struct page *); extern void clear_shadow_from_swap_cache(int type, unsigned long begin, unsigned long end); +extern void free_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); extern struct page *lookup_swap_cache(swp_entry_t entry, @@ -511,7 +513,7 @@ sector_t swap_page_sector(struct page *page); static inline void put_swap_device(struct swap_info_struct *si) { - rcu_read_unlock(); + percpu_ref_put(&si->users); } #else /* CONFIG_SWAP */ @@ -526,6 +528,15 @@ static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) return NULL; } +static inline struct swap_info_struct *get_swap_device(swp_entry_t entry) +{ + return NULL; +} + +static inline void put_swap_device(struct swap_info_struct *si) +{ +} + #define swap_address_space(entry) (NULL) #define get_nr_swap_pages() 0L #define total_swap_pages 0L @@ -541,6 +552,10 @@ static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); +static inline void free_swap_cache(struct page *page) +{ +} + static inline void show_swap_cache_info(void) { } diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 6430a94c6981..5907205c712c 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -330,6 +330,11 @@ static inline int is_hwpoison_entry(swp_entry_t entry) return swp_type(entry) == SWP_HWPOISON; } +static inline unsigned long hwpoison_entry_to_pfn(swp_entry_t entry) +{ + return swp_offset(entry); +} + static inline void num_poisoned_pages_inc(void) { atomic_long_inc(&num_poisoned_pages); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 050511e8f1f8..586128d5c3b8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -485,8 +485,8 @@ asmlinkage long sys_pipe2(int __user *fildes, int flags); /* fs/quota.c */ asmlinkage long sys_quotactl(unsigned int cmd, const char __user *special, qid_t id, void __user *addr); -asmlinkage long sys_quotactl_path(unsigned int cmd, const char __user *mountpoint, - qid_t id, void __user *addr); +asmlinkage long sys_quotactl_fd(unsigned int fd, unsigned int cmd, qid_t id, + void __user *addr); /* fs/readdir.c */ asmlinkage long sys_getdents64(unsigned int fd, diff --git a/include/linux/usb/cdc-wdm.h b/include/linux/usb/cdc-wdm.h index 9b895f93d8de..9f5a51f79ba5 100644 --- a/include/linux/usb/cdc-wdm.h +++ b/include/linux/usb/cdc-wdm.h @@ -12,11 +12,12 @@ #ifndef __LINUX_USB_CDC_WDM_H #define __LINUX_USB_CDC_WDM_H +#include #include extern struct usb_driver *usb_cdc_wdm_register(struct usb_interface *intf, struct usb_endpoint_descriptor *ep, - int bufsize, + int bufsize, enum wwan_port_type type, int (*manage_power)(struct usb_interface *, int)); #endif /* __LINUX_USB_CDC_WDM_H */ diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 1d08dbbcfe32..eb70cabe6e7f 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -54,9 +54,15 @@ enum ucount_type { UCOUNT_FANOTIFY_GROUPS, UCOUNT_FANOTIFY_MARKS, #endif + UCOUNT_RLIMIT_NPROC, + UCOUNT_RLIMIT_MSGQUEUE, + UCOUNT_RLIMIT_SIGPENDING, + UCOUNT_RLIMIT_MEMLOCK, UCOUNT_COUNTS, }; +#define MAX_PER_NAMESPACE_UCOUNTS UCOUNT_RLIMIT_NPROC + struct user_namespace { struct uid_gid_map uid_map; struct uid_gid_map gid_map; @@ -92,23 +98,42 @@ struct user_namespace { struct ctl_table_header *sysctls; #endif struct ucounts *ucounts; - int ucount_max[UCOUNT_COUNTS]; + long ucount_max[UCOUNT_COUNTS]; } __randomize_layout; struct ucounts { struct hlist_node node; struct user_namespace *ns; kuid_t uid; - int count; - atomic_t ucount[UCOUNT_COUNTS]; + atomic_t count; + atomic_long_t ucount[UCOUNT_COUNTS]; }; extern struct user_namespace init_user_ns; +extern struct ucounts init_ucounts; bool setup_userns_sysctls(struct user_namespace *ns); void retire_userns_sysctls(struct user_namespace *ns); struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type); void dec_ucount(struct ucounts *ucounts, enum ucount_type type); +struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); +struct ucounts * __must_check get_ucounts(struct ucounts *ucounts); +void put_ucounts(struct ucounts *ucounts); + +static inline long get_ucounts_value(struct ucounts *ucounts, enum ucount_type type) +{ + return atomic_long_read(&ucounts->ucount[type]); +} + +long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); +bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v); +bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max); + +static inline void set_rlimit_ucount_max(struct user_namespace *ns, + enum ucount_type type, unsigned long max) +{ + ns->ucount_max[type] = max <= LONG_MAX ? max : LONG_MAX; +} #ifdef CONFIG_USER_NS diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 778639fc347e..de584a776908 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -37,6 +37,7 @@ struct virtio_vsock_sock { u32 rx_bytes; u32 buf_alloc; struct list_head rx_queue; + u32 msg_count; }; struct virtio_vsock_pkt { @@ -81,8 +82,17 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags); +int +virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len); +ssize_t +virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags); s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); +u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk); int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 3299cd69e4ca..d6a6cf53b127 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -138,34 +138,27 @@ static inline void vm_events_fold_cpu(int cpu) * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; -extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; +extern atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; #ifdef CONFIG_NUMA -static inline void zone_numa_state_add(long x, struct zone *zone, - enum numa_stat_item item) +static inline void zone_numa_event_add(long x, struct zone *zone, + enum numa_stat_item item) { - atomic_long_add(x, &zone->vm_numa_stat[item]); - atomic_long_add(x, &vm_numa_stat[item]); + atomic_long_add(x, &zone->vm_numa_event[item]); + atomic_long_add(x, &vm_numa_event[item]); } -static inline unsigned long global_numa_state(enum numa_stat_item item) -{ - long x = atomic_long_read(&vm_numa_stat[item]); - - return x; -} - -static inline unsigned long zone_numa_state_snapshot(struct zone *zone, +static inline unsigned long zone_numa_event_state(struct zone *zone, enum numa_stat_item item) { - long x = atomic_long_read(&zone->vm_numa_stat[item]); - int cpu; + return atomic_long_read(&zone->vm_numa_event[item]); +} - for_each_online_cpu(cpu) - x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item]; - - return x; +static inline unsigned long +global_numa_event_state(enum numa_stat_item item) +{ + return atomic_long_read(&vm_numa_event[item]); } #endif /* CONFIG_NUMA */ @@ -236,7 +229,7 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) - x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item]; + x += per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; @@ -245,18 +238,38 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, } #ifdef CONFIG_NUMA -extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item); +/* See __count_vm_event comment on why raw_cpu_inc is used. */ +static inline void +__count_numa_event(struct zone *zone, enum numa_stat_item item) +{ + struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; + + raw_cpu_inc(pzstats->vm_numa_event[item]); +} + +static inline void +__count_numa_events(struct zone *zone, enum numa_stat_item item, long delta) +{ + struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; + + raw_cpu_add(pzstats->vm_numa_event[item], delta); +} + extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); -extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item); +extern unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); extern unsigned long node_page_state_pages(struct pglist_data *pgdat, enum node_stat_item item); +extern void fold_vm_numa_events(void); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #define node_page_state_pages(node, item) global_node_page_state_pages(item) +static inline void fold_vm_numa_events(void) +{ +} #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP @@ -291,7 +304,7 @@ struct ctl_table; int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); -void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); +void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); @@ -399,7 +412,7 @@ static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, - struct per_cpu_pageset *pset) { } + struct per_cpu_zonestat *pzstats) { } #endif /* CONFIG_SMP */ static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, @@ -428,7 +441,7 @@ static inline const char *numa_stat_name(enum numa_stat_item item) static inline const char *node_stat_name(enum node_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS + + NR_VM_NUMA_EVENT_ITEMS + item]; } @@ -440,7 +453,7 @@ static inline const char *lru_list_name(enum lru_list lru) static inline const char *writeback_stat_name(enum writeback_stat_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS + + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + item]; } @@ -449,7 +462,7 @@ static inline const char *writeback_stat_name(enum writeback_stat_item item) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS + + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + NR_VM_WRITEBACK_STAT_ITEMS + item]; diff --git a/include/linux/wait.h b/include/linux/wait.h index fe10e8570a52..6598ae35e1b5 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -1136,7 +1136,7 @@ do { \ * Waitqueues which are removed from the waitqueue_head at wakeup time */ void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); -void prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 8e5c5bb16e2d..667e86cfbdcf 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -221,6 +221,7 @@ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr_pages, enum wb_reason reason, struct wb_completion *done); void cgroup_writeback_umount(void); +bool cleanup_offline_cgwb(struct bdi_writeback *wb); /** * inode_attach_wb - associate an inode with its wb @@ -360,7 +361,6 @@ extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; extern int vm_highmem_is_dirtyable; -extern int block_dump; extern int laptop_mode; int dirty_background_ratio_handler(struct ctl_table *table, int write, diff --git a/include/linux/wwan.h b/include/linux/wwan.h index aa05a253dcf9..9fac819f92e3 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -6,7 +6,10 @@ #include #include +#include #include +#include +#include /** * enum wwan_port_type - WWAN port types @@ -15,7 +18,10 @@ * @WWAN_PORT_QMI: Qcom modem/MSM interface for modem control * @WWAN_PORT_QCDM: Qcom Modem diagnostic interface * @WWAN_PORT_FIREHOSE: XML based command protocol - * @WWAN_PORT_MAX: Number of supported port types + * + * @WWAN_PORT_MAX: Highest supported port types + * @WWAN_PORT_UNKNOWN: Special value to indicate an unknown port type + * @__WWAN_PORT_MAX: Internal use */ enum wwan_port_type { WWAN_PORT_AT, @@ -23,7 +29,12 @@ enum wwan_port_type { WWAN_PORT_QMI, WWAN_PORT_QCDM, WWAN_PORT_FIREHOSE, - WWAN_PORT_MAX, + + /* Add new port types above this line */ + + __WWAN_PORT_MAX, + WWAN_PORT_MAX = __WWAN_PORT_MAX - 1, + WWAN_PORT_UNKNOWN, }; struct wwan_port; @@ -31,15 +42,23 @@ struct wwan_port; /** struct wwan_port_ops - The WWAN port operations * @start: The routine for starting the WWAN port device. * @stop: The routine for stopping the WWAN port device. - * @tx: The routine that sends WWAN port protocol data to the device. + * @tx: Non-blocking routine that sends WWAN port protocol data to the device. + * @tx_blocking: Optional blocking routine that sends WWAN port protocol data + * to the device. + * @tx_poll: Optional routine that sets additional TX poll flags. * * The wwan_port_ops structure contains a list of low-level operations - * that control a WWAN port device. All functions are mandatory. + * that control a WWAN port device. All functions are mandatory unless specified. */ struct wwan_port_ops { int (*start)(struct wwan_port *port); void (*stop)(struct wwan_port *port); int (*tx)(struct wwan_port *port, struct sk_buff *skb); + + /* Optional operations */ + int (*tx_blocking)(struct wwan_port *port, struct sk_buff *skb); + __poll_t (*tx_poll)(struct wwan_port *port, struct file *filp, + poll_table *wait); }; /** @@ -108,4 +127,48 @@ void wwan_port_txon(struct wwan_port *port); */ void *wwan_port_get_drvdata(struct wwan_port *port); +/** + * struct wwan_netdev_priv - WWAN core network device private data + * @link_id: WWAN device data link id + * @drv_priv: driver private data area, size is determined in &wwan_ops + */ +struct wwan_netdev_priv { + u32 link_id; + + /* must be last */ + u8 drv_priv[] __aligned(sizeof(void *)); +}; + +static inline void *wwan_netdev_drvpriv(struct net_device *dev) +{ + return ((struct wwan_netdev_priv *)netdev_priv(dev))->drv_priv; +} + +/* + * Used to indicate that the WWAN core should not create a default network + * link. + */ +#define WWAN_NO_DEFAULT_LINK U32_MAX + +/** + * struct wwan_ops - WWAN device ops + * @priv_size: size of private netdev data area + * @setup: set up a new netdev + * @newlink: register the new netdev + * @dellink: remove the given netdev + */ +struct wwan_ops { + unsigned int priv_size; + void (*setup)(struct net_device *dev); + int (*newlink)(void *ctxt, struct net_device *dev, + u32 if_id, struct netlink_ext_ack *extack); + void (*dellink)(void *ctxt, struct net_device *dev, + struct list_head *head); +}; + +int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, + void *ctxt, u32 def_link_id); + +void wwan_unregister_ops(struct device *parent); + #endif /* __WWAN_H */ diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index b1c717286993..ab207677e0a8 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -135,6 +135,14 @@ struct vsock_transport { bool (*stream_is_active)(struct vsock_sock *); bool (*stream_allow)(u32 cid, u32 port); + /* SEQ_PACKET. */ + ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, + int flags); + int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg, + size_t len); + bool (*seqpacket_allow)(u32 remote_cid); + u32 (*seqpacket_has_data)(struct vsock_sock *vsk); + /* Notification. */ int (*notify_poll_in)(struct vsock_sock *, size_t, bool *); int (*notify_poll_out)(struct vsock_sock *, size_t, bool *); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index ea4ae551c426..b80415011dcd 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -36,7 +36,7 @@ #define HCI_MAX_AMP_ASSOC_SIZE 672 -#define HCI_MAX_CSB_DATA_SIZE 252 +#define HCI_MAX_CPB_DATA_SIZE 252 /* HCI dev events */ #define HCI_DEV_REG 1 @@ -339,6 +339,7 @@ enum { #define HCI_PAIRING_TIMEOUT msecs_to_jiffies(60000) /* 60 seconds */ #define HCI_INIT_TIMEOUT msecs_to_jiffies(10000) /* 10 seconds */ #define HCI_CMD_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ +#define HCI_NCMD_TIMEOUT msecs_to_jiffies(4000) /* 4 seconds */ #define HCI_ACL_TX_TIMEOUT msecs_to_jiffies(45000) /* 45 seconds */ #define HCI_AUTO_OFF_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ #define HCI_POWER_OFF_TIMEOUT msecs_to_jiffies(5000) /* 5 seconds */ @@ -471,10 +472,10 @@ enum { #define LMP_EXTFEATURES 0x80 /* Extended LMP features */ -#define LMP_CSB_MASTER 0x01 -#define LMP_CSB_SLAVE 0x02 -#define LMP_SYNC_TRAIN 0x04 -#define LMP_SYNC_SCAN 0x08 +#define LMP_CPB_CENTRAL 0x01 +#define LMP_CPB_PERIPHERAL 0x02 +#define LMP_SYNC_TRAIN 0x04 +#define LMP_SYNC_SCAN 0x08 #define LMP_SC 0x01 #define LMP_PING 0x02 @@ -488,7 +489,7 @@ enum { /* LE features */ #define HCI_LE_ENCRYPTION 0x01 #define HCI_LE_CONN_PARAM_REQ_PROC 0x02 -#define HCI_LE_SLAVE_FEATURES 0x08 +#define HCI_LE_PERIPHERAL_FEATURES 0x08 #define HCI_LE_PING 0x10 #define HCI_LE_DATA_LEN_EXT 0x20 #define HCI_LE_LL_PRIVACY 0x40 @@ -497,8 +498,8 @@ enum { #define HCI_LE_PHY_CODED 0x08 #define HCI_LE_EXT_ADV 0x10 #define HCI_LE_CHAN_SEL_ALG2 0x40 -#define HCI_LE_CIS_MASTER 0x10 -#define HCI_LE_CIS_SLAVE 0x20 +#define HCI_LE_CIS_CENTRAL 0x10 +#define HCI_LE_CIS_PERIPHERAL 0x20 /* Connection modes */ #define HCI_CM_ACTIVE 0x0000 @@ -876,17 +877,17 @@ struct hci_rp_logical_link_cancel { __u8 flow_spec_id; } __packed; -#define HCI_OP_SET_CSB 0x0441 -struct hci_cp_set_csb { +#define HCI_OP_SET_CPB 0x0441 +struct hci_cp_set_cpb { __u8 enable; __u8 lt_addr; __u8 lpo_allowed; __le16 packet_type; __le16 interval_min; __le16 interval_max; - __le16 csb_sv_tout; + __le16 cpb_sv_tout; } __packed; -struct hci_rp_set_csb { +struct hci_rp_set_cpb { __u8 status; __u8 lt_addr; __le16 interval; @@ -1183,14 +1184,14 @@ struct hci_rp_delete_reserved_lt_addr { __u8 lt_addr; } __packed; -#define HCI_OP_SET_CSB_DATA 0x0c76 -struct hci_cp_set_csb_data { +#define HCI_OP_SET_CPB_DATA 0x0c76 +struct hci_cp_set_cpb_data { __u8 lt_addr; __u8 fragment; __u8 data_length; - __u8 data[HCI_MAX_CSB_DATA_SIZE]; + __u8 data[HCI_MAX_CPB_DATA_SIZE]; } __packed; -struct hci_rp_set_csb_data { +struct hci_rp_set_cpb_data { __u8 status; __u8 lt_addr; } __packed; @@ -1504,7 +1505,7 @@ struct hci_cp_le_set_scan_enable { } __packed; #define HCI_LE_USE_PEER_ADDR 0x00 -#define HCI_LE_USE_WHITELIST 0x01 +#define HCI_LE_USE_ACCEPT_LIST 0x01 #define HCI_OP_LE_CREATE_CONN 0x200d struct hci_cp_le_create_conn { @@ -1524,22 +1525,22 @@ struct hci_cp_le_create_conn { #define HCI_OP_LE_CREATE_CONN_CANCEL 0x200e -#define HCI_OP_LE_READ_WHITE_LIST_SIZE 0x200f -struct hci_rp_le_read_white_list_size { +#define HCI_OP_LE_READ_ACCEPT_LIST_SIZE 0x200f +struct hci_rp_le_read_accept_list_size { __u8 status; __u8 size; } __packed; -#define HCI_OP_LE_CLEAR_WHITE_LIST 0x2010 +#define HCI_OP_LE_CLEAR_ACCEPT_LIST 0x2010 -#define HCI_OP_LE_ADD_TO_WHITE_LIST 0x2011 -struct hci_cp_le_add_to_white_list { +#define HCI_OP_LE_ADD_TO_ACCEPT_LIST 0x2011 +struct hci_cp_le_add_to_accept_list { __u8 bdaddr_type; bdaddr_t bdaddr; } __packed; -#define HCI_OP_LE_DEL_FROM_WHITE_LIST 0x2012 -struct hci_cp_le_del_from_white_list { +#define HCI_OP_LE_DEL_FROM_ACCEPT_LIST 0x2012 +struct hci_cp_le_del_from_accept_list { __u8 bdaddr_type; bdaddr_t bdaddr; } __packed; @@ -1774,13 +1775,15 @@ struct hci_cp_ext_adv_set { __u8 max_events; } __packed; +#define HCI_MAX_EXT_AD_LENGTH 251 + #define HCI_OP_LE_SET_EXT_ADV_DATA 0x2037 struct hci_cp_le_set_ext_adv_data { __u8 handle; __u8 operation; __u8 frag_pref; __u8 length; - __u8 data[HCI_MAX_AD_LENGTH]; + __u8 data[]; } __packed; #define HCI_OP_LE_SET_EXT_SCAN_RSP_DATA 0x2038 @@ -1789,7 +1792,7 @@ struct hci_cp_le_set_ext_scan_rsp_data { __u8 operation; __u8 frag_pref; __u8 length; - __u8 data[HCI_MAX_AD_LENGTH]; + __u8 data[]; } __packed; #define LE_SET_ADV_DATA_OP_COMPLETE 0x03 @@ -1838,23 +1841,23 @@ struct hci_rp_le_read_iso_tx_sync { #define HCI_OP_LE_SET_CIG_PARAMS 0x2062 struct hci_cis_params { __u8 cis_id; - __le16 m_sdu; - __le16 s_sdu; - __u8 m_phy; - __u8 s_phy; - __u8 m_rtn; - __u8 s_rtn; + __le16 c_sdu; + __le16 p_pdu; + __u8 c_phy; + __u8 p_phy; + __u8 c_rtn; + __u8 p_rtn; } __packed; struct hci_cp_le_set_cig_params { __u8 cig_id; - __u8 m_interval[3]; - __u8 s_interval[3]; - __u8 sca; + __u8 c_interval[3]; + __u8 p_interval[3]; + __u8 wc_sca; __u8 packing; __u8 framing; - __le16 m_latency; - __le16 s_latency; + __le16 c_latency; + __le16 p_latency; __u8 num_cis; struct hci_cis_params cis[]; } __packed; @@ -2259,7 +2262,7 @@ struct hci_ev_sync_train_complete { __u8 status; } __packed; -#define HCI_EV_SLAVE_PAGE_RESP_TIMEOUT 0x54 +#define HCI_EV_PERIPHERAL_PAGE_RESP_TIMEOUT 0x54 #define HCI_EV_LE_CONN_COMPLETE 0x01 struct hci_ev_le_conn_complete { @@ -2417,17 +2420,17 @@ struct hci_evt_le_cis_established { __le16 handle; __u8 cig_sync_delay[3]; __u8 cis_sync_delay[3]; - __u8 m_latency[3]; - __u8 s_latency[3]; - __u8 m_phy; - __u8 s_phy; + __u8 c_latency[3]; + __u8 p_latency[3]; + __u8 c_phy; + __u8 p_phy; __u8 nse; - __u8 m_bn; - __u8 s_bn; - __u8 m_ft; - __u8 s_ft; - __le16 m_mtu; - __le16 s_mtu; + __u8 c_bn; + __u8 p_bn; + __u8 c_ft; + __u8 p_ft; + __le16 c_mtu; + __le16 p_mtu; __le16 interval; } __packed; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index c73ac52af186..a53e94459ecd 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -122,7 +122,7 @@ struct hci_conn_hash { unsigned int amp_num; unsigned int sco_num; unsigned int le_num; - unsigned int le_num_slave; + unsigned int le_num_peripheral; }; struct bdaddr_list { @@ -228,9 +228,9 @@ struct adv_info { __u16 remaining_time; __u16 duration; __u16 adv_data_len; - __u8 adv_data[HCI_MAX_AD_LENGTH]; + __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; __u16 scan_rsp_len; - __u8 scan_rsp_data[HCI_MAX_AD_LENGTH]; + __u8 scan_rsp_data[HCI_MAX_EXT_AD_LENGTH]; __s8 tx_power; __u32 min_interval; __u32 max_interval; @@ -327,7 +327,7 @@ struct hci_dev { __u8 max_page; __u8 features[HCI_MAX_PAGES][8]; __u8 le_features[8]; - __u8 le_white_list_size; + __u8 le_accept_list_size; __u8 le_resolv_list_size; __u8 le_num_of_adv_sets; __u8 le_states[8]; @@ -470,6 +470,7 @@ struct hci_dev { struct delayed_work service_cache; struct delayed_work cmd_timer; + struct delayed_work ncmd_timer; struct work_struct rx_work; struct work_struct cmd_work; @@ -521,14 +522,14 @@ struct hci_dev { struct hci_conn_hash conn_hash; struct list_head mgmt_pending; - struct list_head blacklist; - struct list_head whitelist; + struct list_head reject_list; + struct list_head accept_list; struct list_head uuids; struct list_head link_keys; struct list_head long_term_keys; struct list_head identity_resolving_keys; struct list_head remote_oob_data; - struct list_head le_white_list; + struct list_head le_accept_list; struct list_head le_resolv_list; struct list_head le_conn_params; struct list_head pend_le_conns; @@ -550,9 +551,9 @@ struct hci_dev { DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); __s8 adv_tx_power; - __u8 adv_data[HCI_MAX_AD_LENGTH]; + __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; __u8 adv_data_len; - __u8 scan_rsp_data[HCI_MAX_AD_LENGTH]; + __u8 scan_rsp_data[HCI_MAX_EXT_AD_LENGTH]; __u8 scan_rsp_data_len; struct list_head adv_instances; @@ -893,7 +894,7 @@ static inline void hci_conn_hash_add(struct hci_dev *hdev, struct hci_conn *c) case LE_LINK: h->le_num++; if (c->role == HCI_ROLE_SLAVE) - h->le_num_slave++; + h->le_num_peripheral++; break; case SCO_LINK: case ESCO_LINK: @@ -919,7 +920,7 @@ static inline void hci_conn_hash_del(struct hci_dev *hdev, struct hci_conn *c) case LE_LINK: h->le_num--; if (c->role == HCI_ROLE_SLAVE) - h->le_num_slave--; + h->le_num_peripheral--; break; case SCO_LINK: case ESCO_LINK: @@ -1393,8 +1394,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define lmp_edr_5slot_capable(dev) ((dev)->features[0][5] & LMP_EDR_5SLOT) /* ----- Extended LMP capabilities ----- */ -#define lmp_csb_master_capable(dev) ((dev)->features[2][0] & LMP_CSB_MASTER) -#define lmp_csb_slave_capable(dev) ((dev)->features[2][0] & LMP_CSB_SLAVE) +#define lmp_cpb_central_capable(dev) ((dev)->features[2][0] & LMP_CPB_CENTRAL) +#define lmp_cpb_peripheral_capable(dev) ((dev)->features[2][0] & LMP_CPB_PERIPHERAL) #define lmp_sync_train_capable(dev) ((dev)->features[2][0] & LMP_SYNC_TRAIN) #define lmp_sync_scan_capable(dev) ((dev)->features[2][0] & LMP_SYNC_SCAN) #define lmp_sc_capable(dev) ((dev)->features[2][1] & LMP_SC) @@ -1768,7 +1769,7 @@ void __mgmt_power_off(struct hci_dev *hdev); void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, bool persistent); void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, - u32 flags, u8 *name, u8 name_len); + u8 *name, u8 name_len); void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, u8 addr_type, u8 reason, bool mgmt_connected); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index a7cffb069565..23a0524061b7 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -202,7 +202,7 @@ struct mgmt_cp_load_link_keys { struct mgmt_ltk_info { struct mgmt_addr_info addr; __u8 type; - __u8 master; + __u8 initiator; __u8 enc_size; __le16 ediv; __le64 rand; @@ -939,6 +939,7 @@ struct mgmt_ev_auth_failed { #define MGMT_DEV_FOUND_CONFIRM_NAME 0x01 #define MGMT_DEV_FOUND_LEGACY_PAIRING 0x02 #define MGMT_DEV_FOUND_NOT_CONNECTABLE 0x04 +#define MGMT_DEV_FOUND_INITIATED_CONN 0x08 #define MGMT_EV_DEVICE_FOUND 0x0012 struct mgmt_ev_device_found { diff --git a/include/net/bonding.h b/include/net/bonding.h index 019e998d944a..15335732e166 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -232,7 +232,7 @@ struct bonding { char proc_file_name[IFNAMSIZ]; #endif /* CONFIG_PROC_FS */ struct list_head bond_list; - u32 rr_tx_counter; + u32 __percpu *rr_tx_counter; struct ad_bond_info ad_info; struct alb_bond_info alb_info; struct bond_params params; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 58c2cd417e89..161cdf7df1a0 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7,7 +7,7 @@ * Copyright 2006-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include @@ -22,6 +22,7 @@ #include #include #include +#include #include /** @@ -370,11 +371,18 @@ struct ieee80211_sta_he_cap { * @he_cap: holds the HE capabilities * @he_6ghz_capa: HE 6 GHz capabilities, must be filled in for a * 6 GHz band channel (and 0 may be valid value). + * @vendor_elems: vendor element(s) to advertise + * @vendor_elems.data: vendor element(s) data + * @vendor_elems.len: vendor element(s) length */ struct ieee80211_sband_iftype_data { u16 types_mask; struct ieee80211_sta_he_cap he_cap; struct ieee80211_he_6ghz_capa he_6ghz_capa; + struct { + const u8 *data; + unsigned int len; + } vendor_elems; }; /** @@ -533,18 +541,6 @@ ieee80211_get_he_iftype_cap(const struct ieee80211_supported_band *sband, return NULL; } -/** - * ieee80211_get_he_sta_cap - return HE capabilities for an sband's STA - * @sband: the sband to search for the STA on - * - * Return: pointer to the struct ieee80211_sta_he_cap, or NULL is none found - */ -static inline const struct ieee80211_sta_he_cap * -ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband) -{ - return ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_STATION); -} - /** * ieee80211_get_he_6ghz_capa - return HE 6 GHz capabilities * @sband: the sband to search for the STA on @@ -905,6 +901,17 @@ ieee80211_chandef_max_power(struct cfg80211_chan_def *chandef) return chandef->chan->max_power; } +/** + * cfg80211_any_usable_channels - check for usable channels + * @wiphy: the wiphy to check for + * @band_mask: which bands to check on + * @prohibited_flags: which channels to not consider usable, + * %IEEE80211_CHAN_DISABLED is always taken into account + */ +bool cfg80211_any_usable_channels(struct wiphy *wiphy, + unsigned long band_mask, + u32 prohibited_flags); + /** * enum survey_info_flags - survey information flags * @@ -1245,8 +1252,6 @@ struct cfg80211_csa_settings { u8 count; }; -#define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 - /** * struct iface_combination_params - input parameters for interface combinations * @@ -3522,7 +3527,10 @@ struct cfg80211_pmsr_result { * If neither @trigger_based nor @non_trigger_based is set, * EDCA based ranging will be used. * @lmr_feedback: negotiate for I2R LMR feedback. Only valid if either - * @trigger_based or @non_trigger_based is set. + * @trigger_based or @non_trigger_based is set. + * @bss_color: the bss color of the responder. Optional. Set to zero to + * indicate the driver should set the BSS color. Only valid if + * @non_trigger_based or @trigger_based is set. * * See also nl80211 for the respective attribute documentation. */ @@ -3540,6 +3548,7 @@ struct cfg80211_pmsr_ftm_request_peer { u8 burst_duration; u8 ftms_per_burst; u8 ftmr_retries; + u8 bss_color; }; /** @@ -4945,6 +4954,7 @@ struct wiphy_iftype_akm_suites { * configuration through the %NL80211_TID_CONFIG_ATTR_RETRY_SHORT and * %NL80211_TID_CONFIG_ATTR_RETRY_LONG attributes * @sar_capa: SAR control capabilities + * @rfkill: a pointer to the rfkill structure */ struct wiphy { struct mutex mtx; @@ -5087,6 +5097,8 @@ struct wiphy { const struct cfg80211_sar_capa *sar_capa; + struct rfkill *rfkill; + char priv[] __aligned(NETDEV_ALIGN); }; @@ -6661,7 +6673,10 @@ void wiphy_rfkill_start_polling(struct wiphy *wiphy); * wiphy_rfkill_stop_polling - stop polling rfkill * @wiphy: the wiphy */ -void wiphy_rfkill_stop_polling(struct wiphy *wiphy); +static inline void wiphy_rfkill_stop_polling(struct wiphy *wiphy) +{ + rfkill_pause_polling(wiphy->rfkill); +} /** * DOC: Vendor commands @@ -8154,6 +8169,8 @@ bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, dev_notice(&(wiphy)->dev, format, ##args) #define wiphy_info(wiphy, format, args...) \ dev_info(&(wiphy)->dev, format, ##args) +#define wiphy_info_once(wiphy, format, args...) \ + dev_info_once(&(wiphy)->dev, format, ##args) #define wiphy_err_ratelimited(wiphy, format, args...) \ dev_err_ratelimited(&(wiphy)->dev, format, ##args) diff --git a/include/net/devlink.h b/include/net/devlink.h index 7c984cadfec4..57b738b78073 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -34,6 +34,7 @@ struct devlink_ops; struct devlink { struct list_head list; struct list_head port_list; + struct list_head rate_list; struct list_head sb_list; struct list_head dpipe_table_list; struct list_head resource_list; @@ -133,6 +134,24 @@ struct devlink_port_attrs { }; }; +struct devlink_rate { + struct list_head list; + enum devlink_rate_type type; + struct devlink *devlink; + void *priv; + u64 tx_share; + u64 tx_max; + + struct devlink_rate *parent; + union { + struct devlink_port *devlink_port; + struct { + char *name; + refcount_t refcnt; + }; + }; +}; + struct devlink_port { struct list_head list; struct list_head param_list; @@ -152,6 +171,8 @@ struct devlink_port { struct delayed_work type_warn_dw; struct list_head reporter_list; struct mutex reporters_lock; /* Protects reporter_list */ + + struct devlink_rate *devlink_rate; }; struct devlink_port_new_attrs { @@ -1326,6 +1347,16 @@ struct devlink_ops { const struct devlink_trap_group *group, enum devlink_trap_action action, struct netlink_ext_ack *extack); + /** + * @trap_drop_counter_get: Trap drop counter get function. + * + * Should be used by device drivers to report number of packets + * that have been dropped, and cannot be passed to the devlink + * subsystem by the underlying device. + */ + int (*trap_drop_counter_get)(struct devlink *devlink, + const struct devlink_trap *trap, + u64 *p_drops); /** * @trap_policer_init: Trap policer initialization function. * @@ -1453,6 +1484,30 @@ struct devlink_ops { struct devlink_port *port, enum devlink_port_fn_state state, struct netlink_ext_ack *extack); + + /** + * Rate control callbacks. + */ + int (*rate_leaf_tx_share_set)(struct devlink_rate *devlink_rate, void *priv, + u64 tx_share, struct netlink_ext_ack *extack); + int (*rate_leaf_tx_max_set)(struct devlink_rate *devlink_rate, void *priv, + u64 tx_max, struct netlink_ext_ack *extack); + int (*rate_node_tx_share_set)(struct devlink_rate *devlink_rate, void *priv, + u64 tx_share, struct netlink_ext_ack *extack); + int (*rate_node_tx_max_set)(struct devlink_rate *devlink_rate, void *priv, + u64 tx_max, struct netlink_ext_ack *extack); + int (*rate_node_new)(struct devlink_rate *rate_node, void **priv, + struct netlink_ext_ack *extack); + int (*rate_node_del)(struct devlink_rate *rate_node, void *priv, + struct netlink_ext_ack *extack); + int (*rate_leaf_parent_set)(struct devlink_rate *child, + struct devlink_rate *parent, + void *priv_child, void *priv_parent, + struct netlink_ext_ack *extack); + int (*rate_node_parent_set)(struct devlink_rate *child, + struct devlink_rate *parent, + void *priv_child, void *priv_parent, + struct netlink_ext_ack *extack); }; static inline void *devlink_priv(struct devlink *devlink) @@ -1512,6 +1567,9 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u32 sf, bool external); +int devlink_rate_leaf_create(struct devlink_port *port, void *priv); +void devlink_rate_leaf_destroy(struct devlink_port *devlink_port); +void devlink_rate_nodes_destroy(struct devlink *devlink); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/net/dsa.h b/include/net/dsa.h index e1a2610a0e06..33f40c1ec379 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -50,6 +50,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 +#define DSA_TAG_PROTO_SJA1110_VALUE 23 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -75,6 +76,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, + DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, }; struct packet_type; @@ -91,7 +93,8 @@ struct dsa_device_ops { * as regular on the master net device. */ bool (*filter)(const struct sk_buff *skb, struct net_device *dev); - unsigned int overhead; + unsigned int needed_headroom; + unsigned int needed_tailroom; const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC @@ -100,7 +103,6 @@ struct dsa_device_ops { * its RX filter. */ bool promisc_on_master; - bool tail_tag; }; /* This structure defines the control interfaces that are overlayed by the @@ -283,6 +285,12 @@ struct dsa_port { */ const struct dsa_netdevice_ops *netdev_ops; + /* List of MAC addresses that must be forwarded on this port. + * These are only valid on CPU ports and DSA links. + */ + struct list_head fdbs; + struct list_head mdbs; + bool setup; }; @@ -297,6 +305,13 @@ struct dsa_link { struct list_head list; }; +struct dsa_mac_addr { + unsigned char addr[ETH_ALEN]; + u16 vid; + refcount_t refcount; + struct list_head list; +}; + struct dsa_switch { bool setup; @@ -407,6 +422,21 @@ static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) return NULL; } +static inline bool dsa_port_is_dsa(struct dsa_port *port) +{ + return port->type == DSA_PORT_TYPE_DSA; +} + +static inline bool dsa_port_is_cpu(struct dsa_port *port) +{ + return port->type == DSA_PORT_TYPE_CPU; +} + +static inline bool dsa_port_is_user(struct dsa_port *dp) +{ + return dp->type == DSA_PORT_TYPE_USER; +} + static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; @@ -474,6 +504,32 @@ static inline unsigned int dsa_upstream_port(struct dsa_switch *ds, int port) return dsa_towards_port(ds, cpu_dp->ds->index, cpu_dp->index); } +/* Return true if this is the local port used to reach the CPU port */ +static inline bool dsa_is_upstream_port(struct dsa_switch *ds, int port) +{ + if (dsa_is_unused_port(ds, port)) + return false; + + return port == dsa_upstream_port(ds, port); +} + +/* Return true if @upstream_ds is an upstream switch of @downstream_ds, meaning + * that the routing port from @downstream_ds to @upstream_ds is also the port + * which @downstream_ds uses to reach its dedicated CPU. + */ +static inline bool dsa_switch_is_upstream_of(struct dsa_switch *upstream_ds, + struct dsa_switch *downstream_ds) +{ + int routing_port; + + if (upstream_ds == downstream_ds) + return true; + + routing_port = dsa_routing_port(downstream_ds, upstream_ds->index); + + return dsa_is_upstream_port(downstream_ds, routing_port); +} + static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) { const struct dsa_switch *ds = dp->ds; @@ -926,7 +982,7 @@ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, { #if IS_ENABLED(CONFIG_NET_DSA) const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; - int tag_len = ops->overhead; + int tag_len = ops->needed_headroom; *offset = tag_len; *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index dc5c1e69cd9f..69c9eabf8325 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -319,12 +319,14 @@ flow_action_mixed_hw_stats_check(const struct flow_action *action, if (flow_offload_has_one_action(action)) return true; - flow_action_for_each(i, action_entry, action) { - if (i && action_entry->hw_stats != last_hw_stats) { - NL_SET_ERR_MSG_MOD(extack, "Mixing HW stats types for actions is not supported"); - return false; + if (action) { + flow_action_for_each(i, action_entry, action) { + if (i && action_entry->hw_stats != last_hw_stats) { + NL_SET_ERR_MSG_MOD(extack, "Mixing HW stats types for actions is not supported"); + return false; + } + last_hw_stats = action_entry->hw_stats; } - last_hw_stats = action_entry->hw_stats; } return true; } diff --git a/include/net/icmp.h b/include/net/icmp.h index fd84adc47963..caddf4a59ad1 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -57,5 +57,6 @@ int icmp_rcv(struct sk_buff *skb); int icmp_err(struct sk_buff *skb, u32 info); int icmp_init(void); void icmp_out_count(struct net *net, unsigned char type); +bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr); #endif /* _ICMP_H */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 3c8c59471bc1..b06c2d02ec84 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -135,7 +135,7 @@ struct inet_connection_sock { u32 icsk_user_timeout; u64 icsk_ca_priv[104 / sizeof(u64)]; -#define ICSK_CA_PRIV_SIZE (13 * sizeof(u64)) +#define ICSK_CA_PRIV_SIZE sizeof_field(struct inet_connection_sock, icsk_ca_priv) }; #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ diff --git a/include/net/ip.h b/include/net/ip.h index e20874059f82..d9683bef8684 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -31,6 +31,7 @@ #include #include #include +#include #define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */ #define IPV4_MIN_MTU 68 /* RFC 791 */ @@ -445,22 +446,25 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, /* 'forwarding = true' case should always honour route mtu */ mtu = dst_metric_raw(dst, RTAX_MTU); - if (mtu) - return mtu; + if (!mtu) + mtu = min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU); - return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU); + return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } static inline unsigned int ip_skb_dst_mtu(struct sock *sk, const struct sk_buff *skb) { + unsigned int mtu; + if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) { bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding); } - return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU); + mtu = min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU); + return mtu - lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu); } struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx, diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index f51a118bfce8..f14149df5a65 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -265,11 +265,18 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, static inline int ip6_skb_dst_mtu(struct sk_buff *skb) { + int mtu; + struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; - return (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) ? - skb_dst(skb)->dev->mtu : dst_mtu(skb_dst(skb)); + if (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) { + mtu = READ_ONCE(skb_dst(skb)->dev->mtu); + mtu -= lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu); + } else + mtu = dst_mtu(skb_dst(skb)); + + return mtu; } static inline bool ip6_sk_accept_pmtu(const struct sock *sk) @@ -317,7 +324,7 @@ static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) if (dst_metric_locked(dst, RTAX_MTU)) { mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) - return mtu; + goto out; } mtu = IPV6_MIN_MTU; @@ -327,7 +334,8 @@ static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) mtu = idev->cnf.mtu6; rcu_read_unlock(); - return mtu; +out: + return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } u32 ip6_mtu_from_fib6(const struct fib6_result *res, diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index a914f33f3ed5..3ab2563b1a23 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -466,6 +466,49 @@ int fib_sync_up(struct net_device *dev, unsigned char nh_flags); void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); +/* Fields used for sysctl_fib_multipath_hash_fields. + * Common to IPv4 and IPv6. + * + * Add new fields at the end. This is user API. + */ +#define FIB_MULTIPATH_HASH_FIELD_SRC_IP BIT(0) +#define FIB_MULTIPATH_HASH_FIELD_DST_IP BIT(1) +#define FIB_MULTIPATH_HASH_FIELD_IP_PROTO BIT(2) +#define FIB_MULTIPATH_HASH_FIELD_FLOWLABEL BIT(3) +#define FIB_MULTIPATH_HASH_FIELD_SRC_PORT BIT(4) +#define FIB_MULTIPATH_HASH_FIELD_DST_PORT BIT(5) +#define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP BIT(6) +#define FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP BIT(7) +#define FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO BIT(8) +#define FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL BIT(9) +#define FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT BIT(10) +#define FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT BIT(11) + +#define FIB_MULTIPATH_HASH_FIELD_OUTER_MASK \ + (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ + FIB_MULTIPATH_HASH_FIELD_DST_IP | \ + FIB_MULTIPATH_HASH_FIELD_IP_PROTO | \ + FIB_MULTIPATH_HASH_FIELD_FLOWLABEL | \ + FIB_MULTIPATH_HASH_FIELD_SRC_PORT | \ + FIB_MULTIPATH_HASH_FIELD_DST_PORT) + +#define FIB_MULTIPATH_HASH_FIELD_INNER_MASK \ + (FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP | \ + FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP | \ + FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO | \ + FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL | \ + FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT | \ + FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) + +#define FIB_MULTIPATH_HASH_FIELD_ALL_MASK \ + (FIB_MULTIPATH_HASH_FIELD_OUTER_MASK | \ + FIB_MULTIPATH_HASH_FIELD_INNER_MASK) + +#define FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK \ + (FIB_MULTIPATH_HASH_FIELD_SRC_IP | \ + FIB_MULTIPATH_HASH_FIELD_DST_IP | \ + FIB_MULTIPATH_HASH_FIELD_IP_PROTO) + #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 448bf2b34759..f2d0ecc257bb 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -926,11 +926,19 @@ static inline int ip6_multipath_hash_policy(const struct net *net) { return net->ipv6.sysctl.multipath_hash_policy; } +static inline u32 ip6_multipath_hash_fields(const struct net *net) +{ + return net->ipv6.sysctl.multipath_hash_fields; +} #else static inline int ip6_multipath_hash_policy(const struct net *net) { return 0; } +static inline u32 ip6_multipath_hash_fields(const struct net *net) +{ + return 0; +} #endif /* diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e89530d0d9c6..d8a1d09a2141 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -7,7 +7,7 @@ * Copyright 2007-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2020 Intel Corporation + * Copyright (C) 2018 - 2021 Intel Corporation */ #ifndef MAC80211_H @@ -526,6 +526,7 @@ struct ieee80211_fils_discovery { * @twt_responder: does this BSS support TWT requester (relevant for managed * mode only, set if the AP advertises TWT responder role) * @twt_protected: does this BSS support protected TWT frames + * @twt_broadcast: does this BSS support broadcast TWT * @assoc: association status * @ibss_joined: indicates whether this station is part of an IBSS * or not @@ -642,6 +643,7 @@ struct ieee80211_bss_conf { bool twt_requester; bool twt_responder; bool twt_protected; + bool twt_broadcast; /* association related data */ bool assoc, ibss_joined; bool ibss_creator; @@ -3344,6 +3346,21 @@ enum ieee80211_reconfig_type { IEEE80211_RECONFIG_TYPE_SUSPEND, }; +/** + * struct ieee80211_prep_tx_info - prepare TX information + * @duration: if non-zero, hint about the required duration, + * only used with the mgd_prepare_tx() method. + * @subtype: frame subtype (auth, (re)assoc, deauth, disassoc) + * @success: whether the frame exchange was successful, only + * used with the mgd_complete_tx() method, and then only + * valid for auth and (re)assoc. + */ +struct ieee80211_prep_tx_info { + u16 duration; + u16 subtype; + u8 success:1; +}; + /** * struct ieee80211_ops - callbacks from mac80211 to the driver * @@ -3756,9 +3773,13 @@ enum ieee80211_reconfig_type { * frame in case that no beacon was heard from the AP/P2P GO. * The callback will be called before each transmission and upon return * mac80211 will transmit the frame right away. - * If duration is greater than zero, mac80211 hints to the driver the - * duration for which the operation is requested. + * Additional information is passed in the &struct ieee80211_prep_tx_info + * data. If duration there is greater than zero, mac80211 hints to the + * driver the duration for which the operation is requested. * The callback is optional and can (should!) sleep. + * @mgd_complete_tx: Notify the driver that the response frame for a previously + * transmitted frame announced with @mgd_prepare_tx was received, the data + * is filled similarly to @mgd_prepare_tx though the duration is not used. * * @mgd_protect_tdls_discover: Protect a TDLS discovery session. After sending * a TDLS discovery-request, we expect a reply to arrive on the AP's @@ -4109,7 +4130,10 @@ struct ieee80211_ops { void (*mgd_prepare_tx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - u16 duration); + struct ieee80211_prep_tx_info *info); + void (*mgd_complete_tx)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_prep_tx_info *info); void (*mgd_protect_tdls_discover)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); @@ -6184,6 +6208,11 @@ enum rate_control_capabilities { * otherwise the NSS difference doesn't bother us. */ RATE_CTRL_CAPA_VHT_EXT_NSS_BW = BIT(0), + /** + * @RATE_CTRL_CAPA_AMPDU_TRIGGER: + * mac80211 should start A-MPDU sessions on tx + */ + RATE_CTRL_CAPA_AMPDU_TRIGGER = BIT(1), }; struct rate_control_ops { @@ -6576,9 +6605,6 @@ static inline void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) { } -void __ieee80211_schedule_txq(struct ieee80211_hw *hw, - struct ieee80211_txq *txq, bool force); - /** * ieee80211_schedule_txq - schedule a TXQ for transmission * @@ -6591,11 +6617,7 @@ void __ieee80211_schedule_txq(struct ieee80211_hw *hw, * The driver may call this function if it has buffered packets for * this TXQ internally. */ -static inline void -ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) -{ - __ieee80211_schedule_txq(hw, txq, true); -} +void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq); /** * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq() @@ -6607,12 +6629,8 @@ ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) * The driver may set force=true if it has buffered packets for this TXQ * internally. */ -static inline void -ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, - bool force) -{ - __ieee80211_schedule_txq(hw, txq, force); -} +void ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, + bool force); /** * ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit @@ -6752,4 +6770,22 @@ struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw, struct sk_buff * ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw, struct ieee80211_vif *vif); + +/** + * ieee80211_is_tx_data - check if frame is a data frame + * + * The function is used to check if a frame is a data frame. Frames with + * hardware encapsulation enabled are data frames. + * + * @skb: the frame to be transmitted. + */ +static inline bool ieee80211_is_tx_data(struct sk_buff *skb) +{ + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_hdr *hdr = (void *) skb->data; + + return info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP || + ieee80211_is_data(hdr->frame_control); +} + #endif /* MAC80211_H */ diff --git a/include/net/macsec.h b/include/net/macsec.h index 52874cdfe226..d6fa6b97f6ef 100644 --- a/include/net/macsec.h +++ b/include/net/macsec.h @@ -241,7 +241,7 @@ struct macsec_context { struct macsec_rx_sc *rx_sc; struct { unsigned char assoc_num; - u8 key[MACSEC_KEYID_LEN]; + u8 key[MACSEC_MAX_KEY_LEN]; union { struct macsec_rx_sa *rx_sa; struct macsec_tx_sa *tx_sa; diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 83f23774b908..cb580b06152f 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -23,6 +23,7 @@ struct mptcp_ext { u64 data_seq; u32 subflow_seq; u16 data_len; + __sum16 csum; u8 use_map:1, dsn64:1, data_fin:1, @@ -31,7 +32,8 @@ struct mptcp_ext { mpc_map:1, frozen:1, reset_transient:1; - u8 reset_reason:4; + u8 reset_reason:4, + csum_reqd:1; }; #define MPTCP_RM_IDS_MAX 8 @@ -63,8 +65,10 @@ struct mptcp_out_options { struct mptcp_rm_list rm_list; u8 join_id; u8 backup; - u8 reset_reason:4; - u8 reset_transient:1; + u8 reset_reason:4, + reset_transient:1, + csum_reqd:1, + allow_join_id0:1; u32 nonce; u64 thmac; u32 token; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index bdc0459a595e..12cf6d7ea62c 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -32,6 +32,7 @@ #include #include #include +#include #include #include #include @@ -170,6 +171,9 @@ struct net { struct sock *crypto_nlsk; #endif struct sock *diag_nlsk; +#if IS_ENABLED(CONFIG_SMC) + struct netns_smc smc; +#endif } __randomize_layout; #include diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 06dc6db70d18..cc663c68ddc4 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -346,6 +346,13 @@ nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info) skb_set_nfct(skb, (unsigned long)ct | info); } +extern unsigned int nf_conntrack_net_id; + +static inline struct nf_conntrack_net *nf_ct_pernet(const struct net *net) +{ + return net_generic(net, nf_conntrack_net_id); +} + #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_ADD_ATOMIC(net, count, v) this_cpu_add((net)->ct.stat->count, (v)) diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 96f9cf81f46b..1f47bef51722 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -159,22 +159,26 @@ unsigned int nf_ct_port_nlattr_tuple_size(void); extern const struct nla_policy nf_ct_port_nla_policy[]; #ifdef CONFIG_SYSCTL -__printf(3, 4) __cold +__printf(4, 5) __cold void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_conn *ct, + const struct nf_hook_state *state, const char *fmt, ...); -__printf(5, 6) __cold +__printf(4, 5) __cold void nf_l4proto_log_invalid(const struct sk_buff *skb, - struct net *net, - u16 pf, u8 protonum, + const struct nf_hook_state *state, + u8 protonum, const char *fmt, ...); #else -static inline __printf(5, 6) __cold -void nf_l4proto_log_invalid(const struct sk_buff *skb, struct net *net, - u16 pf, u8 protonum, const char *fmt, ...) {} -static inline __printf(3, 4) __cold +static inline __printf(4, 5) __cold +void nf_l4proto_log_invalid(const struct sk_buff *skb, + const struct nf_hook_state *state, + u8 protonum, + const char *fmt, ...) {} +static inline __printf(4, 5) __cold void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_conn *ct, + const struct nf_hook_state *state, const char *fmt, ...) { } #endif /* CONFIG_SYSCTL */ diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 48ef7460ff30..a3647fadf1cc 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -177,6 +177,8 @@ struct flow_offload { #define NF_FLOW_TIMEOUT (30 * HZ) #define nf_flowtable_time_stamp (u32)jiffies +unsigned long flow_offload_get_timeout(struct flow_offload *flow); + static inline __s32 nf_flow_timeout_delta(unsigned int timeout) { return (__s32)(timeout - nf_flowtable_time_stamp); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 0a5655e300b5..148f5d8ee5ab 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -23,35 +23,46 @@ struct module; struct nft_pktinfo { struct sk_buff *skb; + const struct nf_hook_state *state; bool tprot_set; u8 tprot; - /* for x_tables compatibility */ - struct xt_action_param xt; + u16 fragoff; + unsigned int thoff; }; +static inline struct sock *nft_sk(const struct nft_pktinfo *pkt) +{ + return pkt->state->sk; +} + +static inline unsigned int nft_thoff(const struct nft_pktinfo *pkt) +{ + return pkt->thoff; +} + static inline struct net *nft_net(const struct nft_pktinfo *pkt) { - return pkt->xt.state->net; + return pkt->state->net; } static inline unsigned int nft_hook(const struct nft_pktinfo *pkt) { - return pkt->xt.state->hook; + return pkt->state->hook; } static inline u8 nft_pf(const struct nft_pktinfo *pkt) { - return pkt->xt.state->pf; + return pkt->state->pf; } static inline const struct net_device *nft_in(const struct nft_pktinfo *pkt) { - return pkt->xt.state->in; + return pkt->state->in; } static inline const struct net_device *nft_out(const struct nft_pktinfo *pkt) { - return pkt->xt.state->out; + return pkt->state->out; } static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, @@ -59,16 +70,15 @@ static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, const struct nf_hook_state *state) { pkt->skb = skb; - pkt->xt.state = state; + pkt->state = state; } -static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline void nft_set_pktinfo_unspec(struct nft_pktinfo *pkt) { pkt->tprot_set = false; pkt->tprot = 0; - pkt->xt.thoff = 0; - pkt->xt.fragoff = 0; + pkt->thoff = 0; + pkt->fragoff = 0; } /** diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index fd10a7862fdc..0fa5a6d98a00 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -3,6 +3,7 @@ #define _NET_NF_TABLES_CORE_H #include +#include extern struct nft_expr_type nft_imm_type; extern struct nft_expr_type nft_cmp_type; @@ -15,6 +16,7 @@ extern struct nft_expr_type nft_range_type; extern struct nft_expr_type nft_meta_type; extern struct nft_expr_type nft_rt_type; extern struct nft_expr_type nft_exthdr_type; +extern struct nft_expr_type nft_last_type; #ifdef CONFIG_NETWORK_SECMARK extern struct nft_object_type nft_secmark_obj_type; @@ -88,6 +90,36 @@ extern const struct nft_set_type nft_set_bitmap_type; extern const struct nft_set_type nft_set_pipapo_type; extern const struct nft_set_type nft_set_pipapo_avx2_type; +#ifdef CONFIG_RETPOLINE +bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +bool nft_hash_lookup_fast(const struct net *net, + const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +bool nft_hash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +bool nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +#else +static inline bool +nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) +{ + return set->ops->lookup(net, set, key, ext); +} +#endif + +/* called from nft_pipapo_avx2.c */ +bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); +/* called from nft_set_pipapo.c */ +bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext); + struct nft_expr; struct nft_regs; struct nft_pktinfo; diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index 1f7bea39ad1b..eb4c094cd54d 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -5,26 +5,24 @@ #include #include -static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt) { struct iphdr *ip; ip = ip_hdr(pkt->skb); pkt->tprot_set = true; pkt->tprot = ip->protocol; - pkt->xt.thoff = ip_hdrlen(pkt->skb); - pkt->xt.fragoff = ntohs(ip->frag_off) & IP_OFFSET; + pkt->thoff = ip_hdrlen(pkt->skb); + pkt->fragoff = ntohs(ip->frag_off) & IP_OFFSET; } -static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) { struct iphdr *iph, _iph; u32 len, thoff; - iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph), - &_iph); + iph = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb), + sizeof(*iph), &_iph); if (!iph) return -1; @@ -33,42 +31,40 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, len = ntohs(iph->tot_len); thoff = iph->ihl * 4; - if (skb->len < len) + if (pkt->skb->len < len) return -1; else if (len < thoff) return -1; pkt->tprot_set = true; pkt->tprot = iph->protocol; - pkt->xt.thoff = thoff; - pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET; + pkt->thoff = thoff; + pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET; return 0; } -static inline void nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline void nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt) { - if (__nft_set_pktinfo_ipv4_validate(pkt, skb) < 0) - nft_set_pktinfo_unspec(pkt, skb); + if (__nft_set_pktinfo_ipv4_validate(pkt) < 0) + nft_set_pktinfo_unspec(pkt); } -static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt) { struct iphdr *iph; u32 len, thoff; - if (!pskb_may_pull(skb, sizeof(*iph))) + if (!pskb_may_pull(pkt->skb, sizeof(*iph))) return -1; - iph = ip_hdr(skb); + iph = ip_hdr(pkt->skb); if (iph->ihl < 5 || iph->version != 4) goto inhdr_error; len = ntohs(iph->tot_len); thoff = iph->ihl * 4; - if (skb->len < len) { + if (pkt->skb->len < len) { __IP_INC_STATS(nft_net(pkt), IPSTATS_MIB_INTRUNCATEDPKTS); return -1; } else if (len < thoff) { @@ -77,8 +73,8 @@ static inline int nft_set_pktinfo_ipv4_ingress(struct nft_pktinfo *pkt, pkt->tprot_set = true; pkt->tprot = iph->protocol; - pkt->xt.thoff = thoff; - pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET; + pkt->thoff = thoff; + pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET; return 0; diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index 867de29f3f7a..7595e02b00ba 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -6,8 +6,7 @@ #include #include -static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt) { unsigned int flags = IP6_FH_F_AUTH; int protohdr, thoff = 0; @@ -15,18 +14,17 @@ static inline void nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); if (protohdr < 0) { - nft_set_pktinfo_unspec(pkt, skb); + nft_set_pktinfo_unspec(pkt); return; } pkt->tprot_set = true; pkt->tprot = protohdr; - pkt->xt.thoff = thoff; - pkt->xt.fragoff = frag_off; + pkt->thoff = thoff; + pkt->fragoff = frag_off; } -static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) { #if IS_ENABLED(CONFIG_IPV6) unsigned int flags = IP6_FH_F_AUTH; @@ -36,8 +34,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, int protohdr; u32 pkt_len; - ip6h = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*ip6h), - &_ip6h); + ip6h = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb), + sizeof(*ip6h), &_ip6h); if (!ip6h) return -1; @@ -45,7 +43,7 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, return -1; pkt_len = ntohs(ip6h->payload_len); - if (pkt_len + sizeof(*ip6h) > skb->len) + if (pkt_len + sizeof(*ip6h) > pkt->skb->len) return -1; protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags); @@ -54,8 +52,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, pkt->tprot_set = true; pkt->tprot = protohdr; - pkt->xt.thoff = thoff; - pkt->xt.fragoff = frag_off; + pkt->thoff = thoff; + pkt->fragoff = frag_off; return 0; #else @@ -63,15 +61,13 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, #endif } -static inline void nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline void nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) { - if (__nft_set_pktinfo_ipv6_validate(pkt, skb) < 0) - nft_set_pktinfo_unspec(pkt, skb); + if (__nft_set_pktinfo_ipv6_validate(pkt) < 0) + nft_set_pktinfo_unspec(pkt); } -static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt, - struct sk_buff *skb) +static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt) { #if IS_ENABLED(CONFIG_IPV6) unsigned int flags = IP6_FH_F_AUTH; @@ -82,15 +78,15 @@ static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt, int protohdr; u32 pkt_len; - if (!pskb_may_pull(skb, sizeof(*ip6h))) + if (!pskb_may_pull(pkt->skb, sizeof(*ip6h))) return -1; - ip6h = ipv6_hdr(skb); + ip6h = ipv6_hdr(pkt->skb); if (ip6h->version != 6) goto inhdr_error; pkt_len = ntohs(ip6h->payload_len); - if (pkt_len + sizeof(*ip6h) > skb->len) { + if (pkt_len + sizeof(*ip6h) > pkt->skb->len) { idev = __in6_dev_get(nft_in(pkt)); __IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INTRUNCATEDPKTS); return -1; @@ -102,8 +98,8 @@ static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt, pkt->tprot_set = true; pkt->tprot = protohdr; - pkt->xt.thoff = thoff; - pkt->xt.fragoff = frag_off; + pkt->thoff = thoff; + pkt->fragoff = frag_off; return 0; diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index ad0a95c2335e..c3094b83a525 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -27,6 +27,10 @@ struct nf_tcp_net { u8 tcp_loose; u8 tcp_be_liberal; u8 tcp_max_retrans; +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + unsigned int offload_timeout; + unsigned int offload_pickup; +#endif }; enum udp_conntrack { @@ -37,6 +41,10 @@ enum udp_conntrack { struct nf_udp_net { unsigned int timeouts[UDP_CT_MAX]; +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + unsigned int offload_timeout; + unsigned int offload_pickup; +#endif }; struct nf_icmp_net { diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index f6af8d96d3c6..b8620519eace 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -126,6 +126,7 @@ struct netns_ipv4 { u8 sysctl_tcp_syn_retries; u8 sysctl_tcp_synack_retries; u8 sysctl_tcp_syncookies; + u8 sysctl_tcp_migrate_req; int sysctl_tcp_reordering; u8 sysctl_tcp_retries1; u8 sysctl_tcp_retries2; @@ -210,6 +211,7 @@ struct netns_ipv4 { #endif #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH + u32 sysctl_fib_multipath_hash_fields; u8 sysctl_fib_multipath_use_neigh; u8 sysctl_fib_multipath_hash_policy; #endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 6153c8067009..bde0b7adb4a3 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -28,8 +28,9 @@ struct netns_sysctl_ipv6 { int ip6_rt_gc_elasticity; int ip6_rt_mtu_expires; int ip6_rt_min_advmss; - u8 bindv6only; + u32 multipath_hash_fields; u8 multipath_hash_policy; + u8 bindv6only; u8 flowlabel_consistency; u8 auto_flowlabels; int icmpv6_time; diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index a0f315effa94..40240722cdca 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -84,6 +84,9 @@ struct netns_sctp { /* HB.interval - 30 seconds */ unsigned int hb_interval; + /* The interval for PLPMTUD probe timer */ + unsigned int probe_interval; + /* Association.Max.Retrans - 10 attempts * Path.Max.Retrans - 5 attempts (per destination address) * Max.Init.Retransmits - 8 attempts diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h new file mode 100644 index 000000000000..ea8a9cf2619b --- /dev/null +++ b/include/net/netns/smc.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NETNS_SMC_H__ +#define __NETNS_SMC_H__ +#include +#include + +struct smc_stats_rsn; +struct smc_stats; +struct netns_smc { + /* per cpu counters for SMC */ + struct smc_stats __percpu *smc_stats; + /* protect fback_rsn */ + struct mutex mutex_fback_rsn; + struct smc_stats_rsn *fback_rsn; +}; +#endif diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index e816b6a3ef2b..e946366e8ba5 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -42,6 +42,7 @@ struct netns_xfrm { struct hlist_head __rcu *state_bydst; struct hlist_head __rcu *state_bysrc; struct hlist_head __rcu *state_byspi; + struct hlist_head __rcu *state_byseq; unsigned int state_hmask; unsigned int state_num; struct work_struct state_hash_work; diff --git a/include/net/page_pool.h b/include/net/page_pool.h index b4b6de909c93..3dd62dd73027 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -146,6 +146,8 @@ inline enum dma_data_direction page_pool_get_dma_dir(struct page_pool *pool) return pool->p.dma_dir; } +bool page_pool_return_skb_page(struct page *page); + struct page_pool *page_pool_create(const struct page_pool_params *params); #ifdef CONFIG_PAGE_POOL @@ -251,4 +253,11 @@ static inline void page_pool_ring_unlock(struct page_pool *pool) spin_unlock_bh(&pool->ring.producer_lock); } +/* Store mem_info on struct page and use it while recycling skb frags */ +static inline +void page_pool_store_mem_info(struct page *page, struct page_pool *pp) +{ + page->pp = pp; +} + #endif /* _NET_PAGE_POOL_H */ diff --git a/include/net/protocol.h b/include/net/protocol.h index 2b778e1d2d8f..f51c06ae365f 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -43,7 +43,6 @@ struct net_protocol { int (*err_handler)(struct sk_buff *skb, u32 info); unsigned int no_policy:1, - netns_ok:1, /* does the protocol do more stringent * icmp tag validation than simple * socket lookup? diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 479f60ef54c0..384e800665f2 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -37,6 +37,9 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters + * @alloc: netdev allocation function, can be %NULL and is then used + * in place of alloc_netdev_mqs(), in this case @priv_size + * and @setup are unused. Returns a netdev or ERR_PTR(). * @priv_size: sizeof net_device private space * @setup: net_device setup function * @newlink: Function for configuring and registering a new device @@ -63,6 +66,11 @@ struct rtnl_link_ops { const char *kind; size_t priv_size; + struct net_device *(*alloc)(struct nlattr *tb[], + const char *ifname, + unsigned char name_assign_type, + unsigned int num_tx_queues, + unsigned int num_rx_queues); void (*setup)(struct net_device *dev); bool netns_refund; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 1e625519ae96..9ed33e6840bd 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -37,8 +37,15 @@ enum qdisc_state_t { __QDISC_STATE_SCHED, __QDISC_STATE_DEACTIVATED, __QDISC_STATE_MISSED, + __QDISC_STATE_DRAINING, }; +#define QDISC_STATE_MISSED BIT(__QDISC_STATE_MISSED) +#define QDISC_STATE_DRAINING BIT(__QDISC_STATE_DRAINING) + +#define QDISC_STATE_NON_EMPTY (QDISC_STATE_MISSED | \ + QDISC_STATE_DRAINING) + struct qdisc_size_table { struct rcu_head rcu; struct list_head list; @@ -110,8 +117,6 @@ struct Qdisc { spinlock_t busylock ____cacheline_aligned_in_smp; spinlock_t seqlock; - /* for NOLOCK qdisc, true if there are no enqueued skbs */ - bool empty; struct rcu_head rcu; /* private data */ @@ -145,6 +150,11 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc) return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; } +static inline bool nolock_qdisc_is_empty(const struct Qdisc *qdisc) +{ + return !(READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY); +} + static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) { return q->flags & TCQ_F_CPUSTATS; @@ -153,7 +163,7 @@ static inline bool qdisc_is_percpu_stats(const struct Qdisc *q) static inline bool qdisc_is_empty(const struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) - return READ_ONCE(qdisc->empty); + return nolock_qdisc_is_empty(qdisc); return !READ_ONCE(qdisc->q.qlen); } @@ -161,7 +171,13 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { if (spin_trylock(&qdisc->seqlock)) - goto nolock_empty; + return true; + + /* Paired with smp_mb__after_atomic() to make sure + * STATE_MISSED checking is synchronized with clearing + * in pfifo_fast_dequeue(). + */ + smp_mb__before_atomic(); /* If the MISSED flag is set, it means other thread has * set the MISSED flag before second spin_trylock(), so @@ -180,14 +196,16 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) */ set_bit(__QDISC_STATE_MISSED, &qdisc->state); + /* spin_trylock() only has load-acquire semantic, so use + * smp_mb__after_atomic() to ensure STATE_MISSED is set + * before doing the second spin_trylock(). + */ + smp_mb__after_atomic(); + /* Retry again in case other CPU may not see the new flag * after it releases the lock at the end of qdisc_run_end(). */ - if (!spin_trylock(&qdisc->seqlock)) - return false; - -nolock_empty: - WRITE_ONCE(qdisc->empty, false); + return spin_trylock(&qdisc->seqlock); } else if (qdisc_is_running(qdisc)) { return false; } @@ -201,15 +219,14 @@ nolock_empty: static inline void qdisc_run_end(struct Qdisc *qdisc) { - write_seqcount_end(&qdisc->running); if (qdisc->flags & TCQ_F_NOLOCK) { spin_unlock(&qdisc->seqlock); if (unlikely(test_bit(__QDISC_STATE_MISSED, - &qdisc->state))) { - clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + &qdisc->state))) __netif_schedule(qdisc); - } + } else { + write_seqcount_end(&qdisc->running); } } diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h index 5e848884ff61..2058fabffbf6 100644 --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -59,6 +59,7 @@ enum sctp_verb { SCTP_CMD_HB_TIMERS_START, /* Start the heartbeat timers. */ SCTP_CMD_HB_TIMER_UPDATE, /* Update a heartbeat timers. */ SCTP_CMD_HB_TIMERS_STOP, /* Stop the heartbeat timers. */ + SCTP_CMD_PROBE_TIMER_UPDATE, /* Update a probe timer. */ SCTP_CMD_TRANSPORT_HB_SENT, /* Reset the status of a transport. */ SCTP_CMD_TRANSPORT_IDLE, /* Do manipulations on idle transport */ SCTP_CMD_TRANSPORT_ON, /* Mark the transport as active. */ diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 14a0d22c9113..265fffa33dad 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -77,6 +77,7 @@ enum sctp_event_timeout { SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD, SCTP_EVENT_TIMEOUT_HEARTBEAT, SCTP_EVENT_TIMEOUT_RECONF, + SCTP_EVENT_TIMEOUT_PROBE, SCTP_EVENT_TIMEOUT_SACK, SCTP_EVENT_TIMEOUT_AUTOCLOSE, }; @@ -200,6 +201,23 @@ enum sctp_sock_state { SCTP_SS_CLOSING = TCP_CLOSE_WAIT, }; +enum sctp_plpmtud_state { + SCTP_PL_DISABLED, + SCTP_PL_BASE, + SCTP_PL_SEARCH, + SCTP_PL_COMPLETE, + SCTP_PL_ERROR, +}; + +#define SCTP_BASE_PLPMTU 1200 +#define SCTP_MAX_PLPMTU 9000 +#define SCTP_MIN_PLPMTU 512 + +#define SCTP_MAX_PROBES 3 + +#define SCTP_PL_BIG_STEP 32 +#define SCTP_PL_MIN_STEP 4 + /* These functions map various type to printable names. */ const char *sctp_cname(const union sctp_subtype id); /* chunk types */ const char *sctp_oname(const union sctp_subtype id); /* other events */ @@ -424,4 +442,6 @@ enum { */ #define SCTP_AUTH_RANDOM_LENGTH 32 +#define SCTP_PROBE_TIMER_MIN 5000 + #endif /* __sctp_constants_h__ */ diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 86f74f2fe6de..69bab88ad66b 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -145,6 +145,8 @@ struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *, struct sctphdr *, struct sctp_association **, struct sctp_transport **); void sctp_err_finish(struct sock *, struct sctp_transport *); +int sctp_udp_v4_err(struct sock *sk, struct sk_buff *skb); +int sctp_udp_v6_err(struct sock *sk, struct sk_buff *skb); void sctp_icmp_frag_needed(struct sock *, struct sctp_association *, struct sctp_transport *t, __u32 pmtu); void sctp_icmp_redirect(struct sock *, struct sctp_transport *, @@ -573,14 +575,15 @@ static inline struct dst_entry *sctp_transport_dst_check(struct sctp_transport * /* Calculate max payload size given a MTU, or the total overhead if * given MTU is zero */ -static inline __u32 sctp_mtu_payload(const struct sctp_sock *sp, - __u32 mtu, __u32 extra) +static inline __u32 __sctp_mtu_payload(const struct sctp_sock *sp, + const struct sctp_transport *t, + __u32 mtu, __u32 extra) { __u32 overhead = sizeof(struct sctphdr) + extra; if (sp) { overhead += sp->pf->af->net_header_len; - if (sp->udp_port) + if (sp->udp_port && (!t || t->encap_port)) overhead += sizeof(struct udphdr); } else { overhead += sizeof(struct ipv6hdr); @@ -592,6 +595,12 @@ static inline __u32 sctp_mtu_payload(const struct sctp_sock *sp, return mtu ? mtu - overhead : overhead; } +static inline __u32 sctp_mtu_payload(const struct sctp_sock *sp, + __u32 mtu, __u32 extra) +{ + return __sctp_mtu_payload(sp, NULL, mtu, extra); +} + static inline __u32 sctp_dst_mtu(const struct dst_entry *dst) { return SCTP_TRUNC4(max_t(__u32, dst_mtu(dst), @@ -615,6 +624,48 @@ static inline __u32 sctp_min_frag_point(struct sctp_sock *sp, __u16 datasize) return sctp_mtu_payload(sp, SCTP_DEFAULT_MINSEGMENT, datasize); } +static inline int sctp_transport_pl_hlen(struct sctp_transport *t) +{ + return __sctp_mtu_payload(sctp_sk(t->asoc->base.sk), t, 0, 0); +} + +static inline void sctp_transport_pl_reset(struct sctp_transport *t) +{ + if (t->probe_interval && (t->param_flags & SPP_PMTUD_ENABLE) && + (t->state == SCTP_ACTIVE || t->state == SCTP_UNKNOWN)) { + if (t->pl.state == SCTP_PL_DISABLED) { + t->pl.state = SCTP_PL_BASE; + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pl.probe_size = SCTP_BASE_PLPMTU; + sctp_transport_reset_probe_timer(t); + } + } else { + if (t->pl.state != SCTP_PL_DISABLED) { + if (del_timer(&t->probe_timer)) + sctp_transport_put(t); + t->pl.state = SCTP_PL_DISABLED; + } + } +} + +static inline void sctp_transport_pl_update(struct sctp_transport *t) +{ + if (t->pl.state == SCTP_PL_DISABLED) + return; + + if (del_timer(&t->probe_timer)) + sctp_transport_put(t); + + t->pl.state = SCTP_PL_BASE; + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pl.probe_size = SCTP_BASE_PLPMTU; +} + +static inline bool sctp_transport_pl_enabled(struct sctp_transport *t) +{ + return t->pl.state != SCTP_PL_DISABLED; +} + static inline bool sctp_newsk_ready(const struct sock *sk) { return sock_flag(sk, SOCK_DEAD) || sk->sk_socket; diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index fd223c94589a..2eb6d7c2c931 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -151,6 +151,7 @@ sctp_state_fn_t sctp_sf_cookie_wait_icmp_abort; /* Prototypes for timeout event state functions. */ sctp_state_fn_t sctp_sf_do_6_3_3_rtx; sctp_state_fn_t sctp_sf_send_reconf; +sctp_state_fn_t sctp_sf_send_probe; sctp_state_fn_t sctp_sf_do_6_2_sack; sctp_state_fn_t sctp_sf_autoclose_timer_expire; @@ -225,11 +226,13 @@ struct sctp_chunk *sctp_make_new_encap_port( const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, - const struct sctp_transport *transport); + const struct sctp_transport *transport, + __u32 probe_size); struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const void *payload, const size_t paylen); +struct sctp_chunk *sctp_make_pad(const struct sctp_association *asoc, int len); struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, const struct sctp_chunk *chunk, __be16 cause_code, const void *payload, @@ -310,6 +313,7 @@ int sctp_do_sm(struct net *net, enum sctp_event_type event_type, void sctp_generate_t3_rtx_event(struct timer_list *t); void sctp_generate_heartbeat_event(struct timer_list *t); void sctp_generate_reconf_event(struct timer_list *t); +void sctp_generate_probe_event(struct timer_list *t); void sctp_generate_proto_unreach_event(struct timer_list *t); void sctp_ootb_pkt_free(struct sctp_packet *packet); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 1aa585216f34..32fc4a309df5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -177,6 +177,7 @@ struct sctp_sock { * will be inherited by all new associations. */ __u32 hbinterval; + __u32 probe_interval; __be16 udp_port; __be16 encap_port; @@ -385,6 +386,7 @@ struct sctp_sender_hb_info { union sctp_addr daddr; unsigned long sent_at; __u64 hb_nonce; + __u32 probe_size; }; int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, @@ -461,7 +463,7 @@ struct sctp_af { int saddr); void (*from_sk) (union sctp_addr *, struct sock *sk); - void (*from_addr_param) (union sctp_addr *, + bool (*from_addr_param) (union sctp_addr *, union sctp_addr_param *, __be16 port, int iif); int (*to_addr_param) (const union sctp_addr *, @@ -656,6 +658,7 @@ struct sctp_chunk { data_accepted:1, /* At least 1 chunk accepted */ auth:1, /* IN: was auth'ed | OUT: needs auth */ has_asconf:1, /* IN: have seen an asconf before */ + pmtu_probe:1, /* Used by PLPMTUD, can be set in s HB chunk */ tsn_missing_report:2, /* Data chunk missing counter. */ fast_retransmit:2; /* Is this chunk fast retransmitted? */ }; @@ -858,6 +861,7 @@ struct sctp_transport { * the destination address every heartbeat interval. */ unsigned long hbinterval; + unsigned long probe_interval; /* SACK delay timeout */ unsigned long sackdelay; @@ -934,6 +938,9 @@ struct sctp_transport { /* Timer to handler reconf chunk rtx */ struct timer_list reconf_timer; + /* Timer to send a probe HB packet for PLPMTUD */ + struct timer_list probe_timer; + /* Since we're using per-destination retransmission timers * (see above), we're also using per-destination "transmitted" * queues. This probably ought to be a private struct @@ -976,6 +983,15 @@ struct sctp_transport { char cacc_saw_newack; } cacc; + struct { + __u16 pmtu; + __u16 probe_size; + __u16 probe_high; + __u8 probe_count:3; + __u8 raise_count:5; + __u8 state; + } pl; /* plpmtud related */ + /* 64-bit random number sent with heartbeat. */ __u64 hb_nonce; @@ -993,6 +1009,7 @@ void sctp_transport_free(struct sctp_transport *); void sctp_transport_reset_t3_rtx(struct sctp_transport *); void sctp_transport_reset_hb_timer(struct sctp_transport *); void sctp_transport_reset_reconf_timer(struct sctp_transport *transport); +void sctp_transport_reset_probe_timer(struct sctp_transport *transport); int sctp_transport_hold(struct sctp_transport *); void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); @@ -1007,6 +1024,8 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); void sctp_transport_immediate_rtx(struct sctp_transport *); void sctp_transport_dst_release(struct sctp_transport *t); void sctp_transport_dst_confirm(struct sctp_transport *t); +void sctp_transport_pl_send(struct sctp_transport *t); +void sctp_transport_pl_recv(struct sctp_transport *t); /* This is the structure we use to queue packets as they come into @@ -1795,6 +1814,7 @@ struct sctp_association { * will be inherited by all new transports. */ unsigned long hbinterval; + unsigned long probe_interval; __be16 encap_port; diff --git a/include/net/sock.h b/include/net/sock.h index 7a7058f4f265..8bdd80027ffb 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2281,6 +2281,8 @@ static inline int sock_error(struct sock *sk) return -err; } +void sk_error_report(struct sock *sk); + static inline unsigned long sock_wspace(struct sock *sk) { int amt = 0; @@ -2752,6 +2754,9 @@ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) void sock_def_readable(struct sock *sk); int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk); +void sock_set_timestamp(struct sock *sk, int optname, bool valbool); +int sock_set_timestamping(struct sock *sk, int optname, int val); + void sock_enable_timestamps(struct sock *sk); void sock_no_linger(struct sock *sk); void sock_set_keepalive(struct sock *sk); diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 505f1e18e9bf..473b0b0fa4ab 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -13,8 +13,9 @@ extern spinlock_t reuseport_lock; struct sock_reuseport { struct rcu_head rcu; - u16 max_socks; /* length of socks */ - u16 num_socks; /* elements in socks */ + u16 max_socks; /* length of socks */ + u16 num_socks; /* elements in socks */ + u16 num_closed_socks; /* closed elements in socks */ /* The last synq overflow event timestamp of this * reuse->socks[] group. */ @@ -31,10 +32,14 @@ extern int reuseport_alloc(struct sock *sk, bool bind_inany); extern int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany); extern void reuseport_detach_sock(struct sock *sk); +void reuseport_stop_listen_sock(struct sock *sk); extern struct sock *reuseport_select_sock(struct sock *sk, u32 hash, struct sk_buff *skb, int hdr_len); +struct sock *reuseport_migrate_sock(struct sock *sk, + struct sock *migrating_sk, + struct sk_buff *skb); extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); extern int reuseport_detach_prog(struct sock *sk); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index f1a5a9a3634d..e4cac9218ce1 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -202,6 +202,7 @@ enum switchdev_notifier_type { struct switchdev_notifier_info { struct net_device *dev; struct netlink_ext_ack *extack; + const void *ctx; }; struct switchdev_notifier_fdb_info { @@ -268,19 +269,19 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*add_cb)(struct net_device *dev, + int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)); int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*del_cb)(struct net_device *dev, + int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)); int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), - int (*set_cb)(struct net_device *dev, + int (*set_cb)(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack)); #else @@ -352,7 +353,7 @@ static inline int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*add_cb)(struct net_device *dev, + int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)) { @@ -363,7 +364,7 @@ static inline int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*del_cb)(struct net_device *dev, + int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)) { return 0; @@ -373,7 +374,7 @@ static inline int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), - int (*set_cb)(struct net_device *dev, + int (*set_cb)(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack)) { diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index f051046ba034..f94b8bc26f9e 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -16,6 +16,7 @@ struct tcf_vlan_params { u16 tcfv_push_vid; __be16 tcfv_push_proto; u8 tcfv_push_prio; + bool tcfv_push_prio_exists; struct rcu_head rcu; }; diff --git a/include/net/tcp.h b/include/net/tcp.h index d05193cb0d99..e668f1bf780d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -412,6 +412,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); int tcp_set_window_clamp(struct sock *sk, int val); +void tcp_update_recv_tstamps(struct sk_buff *skb, + struct scm_timestamping_internal *tss); +void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, + struct scm_timestamping_internal *tss); void tcp_data_ready(struct sock *sk); #ifdef CONFIG_MMU int tcp_mmap(struct file *file, struct socket *sock, diff --git a/include/net/tls.h b/include/net/tls.h index 8341a8d1e807..be4b3e1cac46 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -79,8 +79,6 @@ __SNMP_INC_STATS((net)->mib.tls_statistics, field) #define TLS_INC_STATS(net, field) \ SNMP_INC_STATS((net)->mib.tls_statistics, field) -#define __TLS_DEC_STATS(net, field) \ - __SNMP_DEC_STATS((net)->mib.tls_statistics, field) #define TLS_DEC_STATS(net, field) \ SNMP_DEC_STATS((net)->mib.tls_statistics, field) @@ -471,7 +469,7 @@ static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) static inline void tls_err_abort(struct sock *sk, int err) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } static inline bool tls_bigint_increment(unsigned char *seq, int len) diff --git a/include/net/xdp.h b/include/net/xdp.h index a5bc214a49d9..5533f0ab2afc 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -170,6 +170,7 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, struct net_device *dev); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp); +struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf); static inline void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp) diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 9c0722c6d7ac..fff069d2ed1b 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -37,7 +37,7 @@ struct xdp_umem { struct xsk_map { struct bpf_map map; spinlock_t lock; /* Synchronize map updates */ - struct xdp_sock *xsk_map[]; + struct xdp_sock __rcu *xsk_map[]; }; struct xdp_sock { diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 687022b39896..75f8a256fd48 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -145,6 +145,12 @@ enum { XFRM_MODE_FLAG_TUNNEL = 1, }; +enum xfrm_replay_mode { + XFRM_REPLAY_MODE_LEGACY, + XFRM_REPLAY_MODE_BMP, + XFRM_REPLAY_MODE_ESN, +}; + /* Full description of state of transformer. */ struct xfrm_state { possible_net_t xs_net; @@ -154,6 +160,7 @@ struct xfrm_state { }; struct hlist_node bysrc; struct hlist_node byspi; + struct hlist_node byseq; refcount_t refcnt; spinlock_t lock; @@ -214,9 +221,8 @@ struct xfrm_state { struct xfrm_replay_state preplay; struct xfrm_replay_state_esn *preplay_esn; - /* The functions for replay detection. */ - const struct xfrm_replay *repl; - + /* replay detection mode */ + enum xfrm_replay_mode repl_mode; /* internal flag that only holds state for delayed aevent at the * moment */ @@ -296,18 +302,6 @@ struct km_event { struct net *net; }; -struct xfrm_replay { - void (*advance)(struct xfrm_state *x, __be32 net_seq); - int (*check)(struct xfrm_state *x, - struct sk_buff *skb, - __be32 net_seq); - int (*recheck)(struct xfrm_state *x, - struct sk_buff *skb, - __be32 net_seq); - void (*notify)(struct xfrm_state *x, int event); - int (*overflow)(struct xfrm_state *x, struct sk_buff *skb); -}; - struct xfrm_if_cb { struct xfrm_if *(*decode_session)(struct sk_buff *skb, unsigned short family); @@ -387,7 +381,6 @@ void xfrm_flush_gc(void); void xfrm_state_delete_tunnel(struct xfrm_state *x); struct xfrm_type { - char *description; struct module *owner; u8 proto; u8 flags; @@ -402,14 +395,12 @@ struct xfrm_type { int (*output)(struct xfrm_state *, struct sk_buff *pskb); int (*reject)(struct xfrm_state *, struct sk_buff *, const struct flowi *); - int (*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **); }; int xfrm_register_type(const struct xfrm_type *type, unsigned short family); void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family); struct xfrm_type_offload { - char *description; struct module *owner; u8 proto; void (*encap)(struct xfrm_state *, struct sk_buff *pskb); @@ -1024,6 +1015,7 @@ struct xfrm_offload { #define CRYPTO_INVALID_PROTOCOL 128 __u8 proto; + __u8 inner_ipproto; }; struct sec_path { @@ -1546,6 +1538,7 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); int xfrm_init_replay(struct xfrm_state *x); +u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload); int xfrm_init_state(struct xfrm_state *x); @@ -1568,7 +1561,6 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm4_transport_finish(struct sk_buff *skb, int async); int xfrm4_rcv(struct sk_buff *skb); -int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq); static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) { @@ -1579,7 +1571,6 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) } int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb); -int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family); @@ -1603,9 +1594,6 @@ int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family) __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr); __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr); int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb); -int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb); -int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, - u8 **prevhdr); #ifdef CONFIG_XFRM void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu); @@ -1719,6 +1707,12 @@ static inline int xfrm_policy_id2dir(u32 index) } #ifdef CONFIG_XFRM +void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq); +int xfrm_replay_check(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); +void xfrm_replay_notify(struct xfrm_state *x, int event); +int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb); +int xfrm_replay_recheck(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); + static inline int xfrm_aevent_is_on(struct net *net) { struct sock *nlsk; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index eaa8386dbc63..7a9a23e7a604 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -147,11 +147,16 @@ static inline bool xp_desc_crosses_non_contig_pg(struct xsk_buff_pool *pool, { bool cross_pg = (addr & (PAGE_SIZE - 1)) + len > PAGE_SIZE; - if (pool->dma_pages_cnt && cross_pg) { + if (likely(!cross_pg)) + return false; + + if (pool->dma_pages_cnt) { return !(pool->dma_pages[addr >> PAGE_SHIFT] & XSK_NEXT_PG_CONTIG_MASK); } - return false; + + /* skb path */ + return addr + len > pool->addrs_cnt; } static inline u64 xp_aligned_extract_addr(struct xsk_buff_pool *pool, u64 addr) diff --git a/include/soc/microchip/mpfs.h b/include/soc/microchip/mpfs.h new file mode 100644 index 000000000000..2b64c95f3be5 --- /dev/null +++ b/include/soc/microchip/mpfs.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * + * Microchip PolarFire SoC (MPFS) + * + * Copyright (c) 2020 Microchip Corporation. All rights reserved. + * + * Author: Conor Dooley + * + */ + +#ifndef __SOC_MPFS_H__ +#define __SOC_MPFS_H__ + +#include +#include + +struct mpfs_sys_controller; + +struct mpfs_mss_msg { + u8 cmd_opcode; + u16 cmd_data_size; + struct mpfs_mss_response *response; + u8 *cmd_data; + u16 mbox_offset; + u16 resp_offset; +}; + +struct mpfs_mss_response { + u32 resp_status; + u32 *resp_msg; + u16 resp_size; +}; + +#if IS_ENABLED(CONFIG_POLARFIRE_SOC_SYS_CTRL) + +int mpfs_blocking_transaction(struct mpfs_sys_controller *mpfs_client, void *msg); + +struct mpfs_sys_controller *mpfs_sys_controller_get(struct device_node *mailbox_node); + +#endif /* if IS_ENABLED(CONFIG_POLARFIRE_SOC_SYS_CTRL) */ + +#endif /* __SOC_MPFS_H__ */ diff --git a/include/trace/events/cma.h b/include/trace/events/cma.h index c3d354702cb0..3d708dae1542 100644 --- a/include/trace/events/cma.h +++ b/include/trace/events/cma.h @@ -31,7 +31,7 @@ DECLARE_EVENT_CLASS(cma_alloc_class, __entry->align = align; ), - TP_printk("name=%s pfn=%lx page=%p count=%lu align=%u", + TP_printk("name=%s pfn=0x%lx page=%p count=%lu align=%u", __get_str(name), __entry->pfn, __entry->page, @@ -60,7 +60,7 @@ TRACE_EVENT(cma_release, __entry->count = count; ), - TP_printk("name=%s pfn=%lx page=%p count=%lu", + TP_printk("name=%s pfn=0x%lx page=%p count=%lu", __get_str(name), __entry->pfn, __entry->page, diff --git a/include/trace/events/filemap.h b/include/trace/events/filemap.h index 796053e162d2..c47b63db124e 100644 --- a/include/trace/events/filemap.h +++ b/include/trace/events/filemap.h @@ -36,7 +36,7 @@ DECLARE_EVENT_CLASS(mm_filemap_op_page_cache, __entry->s_dev = page->mapping->host->i_rdev; ), - TP_printk("dev %d:%d ino %lx page=%p pfn=%lu ofs=%lu", + TP_printk("dev %d:%d ino %lx page=%p pfn=0x%lx ofs=%lu", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, pfn_to_page(__entry->pfn), diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index abb8b24744fd..e4e44a2b4aa9 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -12,11 +12,11 @@ struct io_wq_work; /** * io_uring_create - called after a new io_uring context was prepared * - * @fd: corresponding file descriptor - * @ctx: pointer to a ring context structure + * @fd: corresponding file descriptor + * @ctx: pointer to a ring context structure * @sq_entries: actual SQ size * @cq_entries: actual CQ size - * @flags: SQ ring flags, provided to io_uring_setup(2) + * @flags: SQ ring flags, provided to io_uring_setup(2) * * Allows to trace io_uring creation and provide pointer to a context, that can * be used later to find correlated events. @@ -52,12 +52,12 @@ TRACE_EVENT(io_uring_create, * io_uring_register - called after a buffer/file/eventfd was successfully * registered for a ring * - * @ctx: pointer to a ring context structure - * @opcode: describes which operation to perform + * @ctx: pointer to a ring context structure + * @opcode: describes which operation to perform * @nr_user_files: number of registered files * @nr_user_bufs: number of registered buffers * @cq_ev_fd: whether eventfs registered or not - * @ret: return code + * @ret: return code * * Allows to trace fixed files/buffers/eventfds, that could be registered to * avoid an overhead of getting references to them for every operation. This @@ -142,16 +142,16 @@ TRACE_EVENT(io_uring_queue_async_work, TP_ARGS(ctx, rw, req, work, flags), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( int, rw ) - __field( void *, req ) + __field( void *, ctx ) + __field( int, rw ) + __field( void *, req ) __field( struct io_wq_work *, work ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->ctx = ctx; - __entry->rw = rw; + __entry->rw = rw; __entry->req = req; __entry->work = work; __entry->flags = flags; @@ -196,10 +196,10 @@ TRACE_EVENT(io_uring_defer, /** * io_uring_link - called before the io_uring request added into link_list of - * another request + * another request * - * @ctx: pointer to a ring context structure - * @req: pointer to a linked request + * @ctx: pointer to a ring context structure + * @req: pointer to a linked request * @target_req: pointer to a previous request, that would contain @req * * Allows to track linked requests, to understand dependencies between requests @@ -212,8 +212,8 @@ TRACE_EVENT(io_uring_link, TP_ARGS(ctx, req, target_req), TP_STRUCT__entry ( - __field( void *, ctx ) - __field( void *, req ) + __field( void *, ctx ) + __field( void *, req ) __field( void *, target_req ) ), @@ -244,7 +244,7 @@ TRACE_EVENT(io_uring_cqring_wait, TP_ARGS(ctx, min_events), TP_STRUCT__entry ( - __field( void *, ctx ) + __field( void *, ctx ) __field( int, min_events ) ), @@ -272,7 +272,7 @@ TRACE_EVENT(io_uring_fail_link, TP_ARGS(req, link), TP_STRUCT__entry ( - __field( void *, req ) + __field( void *, req ) __field( void *, link ) ), @@ -318,13 +318,14 @@ TRACE_EVENT(io_uring_complete, __entry->res, __entry->cflags) ); - /** * io_uring_submit_sqe - called before submitting one SQE * * @ctx: pointer to a ring context structure + * @req: pointer to a submitted request * @opcode: opcode of request * @user_data: user data associated with the request + * @flags request flags * @force_nonblock: whether a context blocking or not * @sq_thread: true if sq_thread has submitted this SQE * @@ -333,41 +334,60 @@ TRACE_EVENT(io_uring_complete, */ TRACE_EVENT(io_uring_submit_sqe, - TP_PROTO(void *ctx, u8 opcode, u64 user_data, bool force_nonblock, - bool sq_thread), + TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data, u32 flags, + bool force_nonblock, bool sq_thread), - TP_ARGS(ctx, opcode, user_data, force_nonblock, sq_thread), + TP_ARGS(ctx, req, opcode, user_data, flags, force_nonblock, sq_thread), TP_STRUCT__entry ( __field( void *, ctx ) + __field( void *, req ) __field( u8, opcode ) __field( u64, user_data ) + __field( u32, flags ) __field( bool, force_nonblock ) __field( bool, sq_thread ) ), TP_fast_assign( __entry->ctx = ctx; + __entry->req = req; __entry->opcode = opcode; __entry->user_data = user_data; + __entry->flags = flags; __entry->force_nonblock = force_nonblock; __entry->sq_thread = sq_thread; ), - TP_printk("ring %p, op %d, data 0x%llx, non block %d, sq_thread %d", - __entry->ctx, __entry->opcode, - (unsigned long long) __entry->user_data, - __entry->force_nonblock, __entry->sq_thread) + TP_printk("ring %p, req %p, op %d, data 0x%llx, flags %u, " + "non block %d, sq_thread %d", __entry->ctx, __entry->req, + __entry->opcode, (unsigned long long)__entry->user_data, + __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); +/* + * io_uring_poll_arm - called after arming a poll wait if successful + * + * @ctx: pointer to a ring context structure + * @req: pointer to the armed request + * @opcode: opcode of request + * @user_data: user data associated with the request + * @mask: request poll events mask + * @events: registered events of interest + * + * Allows to track which fds are waiting for and what are the events of + * interest. + */ TRACE_EVENT(io_uring_poll_arm, - TP_PROTO(void *ctx, u8 opcode, u64 user_data, int mask, int events), + TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data, + int mask, int events), - TP_ARGS(ctx, opcode, user_data, mask, events), + TP_ARGS(ctx, req, opcode, user_data, mask, events), TP_STRUCT__entry ( __field( void *, ctx ) + __field( void *, req ) __field( u8, opcode ) __field( u64, user_data ) __field( int, mask ) @@ -376,16 +396,17 @@ TRACE_EVENT(io_uring_poll_arm, TP_fast_assign( __entry->ctx = ctx; + __entry->req = req; __entry->opcode = opcode; __entry->user_data = user_data; __entry->mask = mask; __entry->events = events; ), - TP_printk("ring %p, op %d, data 0x%llx, mask 0x%x, events 0x%x", - __entry->ctx, __entry->opcode, - (unsigned long long) __entry->user_data, - __entry->mask, __entry->events) + TP_printk("ring %p, req %p, op %d, data 0x%llx, mask 0x%x, events 0x%x", + __entry->ctx, __entry->req, __entry->opcode, + (unsigned long long) __entry->user_data, + __entry->mask, __entry->events) ); TRACE_EVENT(io_uring_poll_wake, @@ -440,27 +461,40 @@ TRACE_EVENT(io_uring_task_add, __entry->mask) ); +/* + * io_uring_task_run - called when task_work_run() executes the poll events + * notification callbacks + * + * @ctx: pointer to a ring context structure + * @req: pointer to the armed request + * @opcode: opcode of request + * @user_data: user data associated with the request + * + * Allows to track when notified poll events are processed + */ TRACE_EVENT(io_uring_task_run, - TP_PROTO(void *ctx, u8 opcode, u64 user_data), + TP_PROTO(void *ctx, void *req, u8 opcode, u64 user_data), - TP_ARGS(ctx, opcode, user_data), + TP_ARGS(ctx, req, opcode, user_data), TP_STRUCT__entry ( __field( void *, ctx ) + __field( void *, req ) __field( u8, opcode ) __field( u64, user_data ) ), TP_fast_assign( __entry->ctx = ctx; + __entry->req = req; __entry->opcode = opcode; __entry->user_data = user_data; ), - TP_printk("ring %p, op %d, data 0x%llx", - __entry->ctx, __entry->opcode, - (unsigned long long) __entry->user_data) + TP_printk("ring %p, req %p, op %d, data 0x%llx", + __entry->ctx, __entry->req, __entry->opcode, + (unsigned long long) __entry->user_data) ); #endif /* _TRACE_IO_URING_H */ diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h index d16a32867f3a..a4dfe005983d 100644 --- a/include/trace/events/jbd2.h +++ b/include/trace/events/jbd2.h @@ -394,6 +394,107 @@ TRACE_EVENT(jbd2_lock_buffer_stall, __entry->stall_ms) ); +DECLARE_EVENT_CLASS(jbd2_journal_shrink, + + TP_PROTO(journal_t *journal, unsigned long nr_to_scan, + unsigned long count), + + TP_ARGS(journal, nr_to_scan, count), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned long, nr_to_scan) + __field(unsigned long, count) + ), + + TP_fast_assign( + __entry->dev = journal->j_fs_dev->bd_dev; + __entry->nr_to_scan = nr_to_scan; + __entry->count = count; + ), + + TP_printk("dev %d,%d nr_to_scan %lu count %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->nr_to_scan, __entry->count) +); + +DEFINE_EVENT(jbd2_journal_shrink, jbd2_shrink_count, + + TP_PROTO(journal_t *journal, unsigned long nr_to_scan, unsigned long count), + + TP_ARGS(journal, nr_to_scan, count) +); + +DEFINE_EVENT(jbd2_journal_shrink, jbd2_shrink_scan_enter, + + TP_PROTO(journal_t *journal, unsigned long nr_to_scan, unsigned long count), + + TP_ARGS(journal, nr_to_scan, count) +); + +TRACE_EVENT(jbd2_shrink_scan_exit, + + TP_PROTO(journal_t *journal, unsigned long nr_to_scan, + unsigned long nr_shrunk, unsigned long count), + + TP_ARGS(journal, nr_to_scan, nr_shrunk, count), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned long, nr_to_scan) + __field(unsigned long, nr_shrunk) + __field(unsigned long, count) + ), + + TP_fast_assign( + __entry->dev = journal->j_fs_dev->bd_dev; + __entry->nr_to_scan = nr_to_scan; + __entry->nr_shrunk = nr_shrunk; + __entry->count = count; + ), + + TP_printk("dev %d,%d nr_to_scan %lu nr_shrunk %lu count %lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->nr_to_scan, __entry->nr_shrunk, + __entry->count) +); + +TRACE_EVENT(jbd2_shrink_checkpoint_list, + + TP_PROTO(journal_t *journal, tid_t first_tid, tid_t tid, tid_t last_tid, + unsigned long nr_freed, unsigned long nr_scanned, + tid_t next_tid), + + TP_ARGS(journal, first_tid, tid, last_tid, nr_freed, + nr_scanned, next_tid), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(tid_t, first_tid) + __field(tid_t, tid) + __field(tid_t, last_tid) + __field(unsigned long, nr_freed) + __field(unsigned long, nr_scanned) + __field(tid_t, next_tid) + ), + + TP_fast_assign( + __entry->dev = journal->j_fs_dev->bd_dev; + __entry->first_tid = first_tid; + __entry->tid = tid; + __entry->last_tid = last_tid; + __entry->nr_freed = nr_freed; + __entry->nr_scanned = nr_scanned; + __entry->next_tid = next_tid; + ), + + TP_printk("dev %d,%d shrink transaction %u-%u(%u) freed %lu " + "scanned %lu next transaction %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->first_tid, __entry->tid, __entry->last_tid, + __entry->nr_freed, __entry->nr_scanned, __entry->next_tid) +); + #endif /* _TRACE_JBD2_H */ /* This part must be outside protection */ diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 829a75692cc0..ddc8c944f417 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -173,7 +173,7 @@ TRACE_EVENT(mm_page_free, __entry->order = order; ), - TP_printk("page=%p pfn=%lu order=%d", + TP_printk("page=%p pfn=0x%lx order=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order) @@ -193,7 +193,7 @@ TRACE_EVENT(mm_page_free_batched, __entry->pfn = page_to_pfn(page); ), - TP_printk("page=%p pfn=%lu order=0", + TP_printk("page=%p pfn=0x%lx order=0", pfn_to_page(__entry->pfn), __entry->pfn) ); @@ -219,7 +219,7 @@ TRACE_EVENT(mm_page_alloc, __entry->migratetype = migratetype; ), - TP_printk("page=%p pfn=%lu order=%d migratetype=%d gfp_flags=%s", + TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, @@ -245,7 +245,7 @@ DECLARE_EVENT_CLASS(mm_page, __entry->migratetype = migratetype; ), - TP_printk("page=%p pfn=%lu order=%u migratetype=%d percpu_refill=%d", + TP_printk("page=%p pfn=0x%lx order=%u migratetype=%d percpu_refill=%d", __entry->pfn != -1UL ? pfn_to_page(__entry->pfn) : NULL, __entry->pfn != -1UL ? __entry->pfn : 0, __entry->order, @@ -278,7 +278,7 @@ TRACE_EVENT(mm_page_pcpu_drain, __entry->migratetype = migratetype; ), - TP_printk("page=%p pfn=%lu order=%d migratetype=%d", + TP_printk("page=%p pfn=0x%lx order=%d migratetype=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->order, __entry->migratetype) ); @@ -312,7 +312,7 @@ TRACE_EVENT(mm_page_alloc_extfrag, get_pageblock_migratetype(page)); ), - TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", + TP_printk("page=%p pfn=0x%lx alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", pfn_to_page(__entry->pfn), __entry->pfn, __entry->alloc_order, diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h index 775a46d0b0f0..6bf43176f14c 100644 --- a/include/trace/events/mptcp.h +++ b/include/trace/events/mptcp.h @@ -73,6 +73,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __field(u64, data_seq) __field(u32, subflow_seq) __field(u16, data_len) + __field(u16, csum) __field(u8, use_map) __field(u8, dsn64) __field(u8, data_fin) @@ -82,6 +83,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __field(u8, frozen) __field(u8, reset_transient) __field(u8, reset_reason) + __field(u8, csum_reqd) ), TP_fast_assign( @@ -89,6 +91,7 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __entry->data_seq = mpext->data_seq; __entry->subflow_seq = mpext->subflow_seq; __entry->data_len = mpext->data_len; + __entry->csum = (__force u16)mpext->csum; __entry->use_map = mpext->use_map; __entry->dsn64 = mpext->dsn64; __entry->data_fin = mpext->data_fin; @@ -98,16 +101,18 @@ DECLARE_EVENT_CLASS(mptcp_dump_mpext, __entry->frozen = mpext->frozen; __entry->reset_transient = mpext->reset_transient; __entry->reset_reason = mpext->reset_reason; + __entry->csum_reqd = mpext->csum_reqd; ), - TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u", + TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u", __entry->data_ack, __entry->data_seq, __entry->subflow_seq, __entry->data_len, - __entry->use_map, __entry->dsn64, - __entry->data_fin, __entry->use_ack, - __entry->ack64, __entry->mpc_map, - __entry->frozen, __entry->reset_transient, - __entry->reset_reason) + __entry->csum, __entry->use_map, + __entry->dsn64, __entry->data_fin, + __entry->use_ack, __entry->ack64, + __entry->mpc_map, __entry->frozen, + __entry->reset_transient, __entry->reset_reason, + __entry->csum_reqd) ); DEFINE_EVENT(mptcp_dump_mpext, get_mapping_status, diff --git a/include/trace/events/page_pool.h b/include/trace/events/page_pool.h index ad0aa7f31675..ca534501158b 100644 --- a/include/trace/events/page_pool.h +++ b/include/trace/events/page_pool.h @@ -60,7 +60,7 @@ TRACE_EVENT(page_pool_state_release, __entry->pfn = page_to_pfn(page); ), - TP_printk("page_pool=%p page=%p pfn=%lu release=%u", + TP_printk("page_pool=%p page=%p pfn=0x%lx release=%u", __entry->pool, __entry->page, __entry->pfn, __entry->release) ); @@ -85,7 +85,7 @@ TRACE_EVENT(page_pool_state_hold, __entry->pfn = page_to_pfn(page); ), - TP_printk("page_pool=%p page=%p pfn=%lu hold=%u", + TP_printk("page_pool=%p page=%p pfn=0x%lx hold=%u", __entry->pool, __entry->page, __entry->pfn, __entry->hold) ); diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h index e1735fe7c76a..1d28431e85bd 100644 --- a/include/trace/events/pagemap.h +++ b/include/trace/events/pagemap.h @@ -46,7 +46,7 @@ TRACE_EVENT(mm_lru_insertion, ), /* Flag format is based on page-types.c formatting for pagemap */ - TP_printk("page=%p pfn=%lu lru=%d flags=%s%s%s%s%s%s", + TP_printk("page=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s", __entry->page, __entry->pfn, __entry->lru, @@ -75,7 +75,7 @@ TRACE_EVENT(mm_lru_activate, ), /* Flag format is based on page-types.c formatting for pagemap */ - TP_printk("page=%p pfn=%lu", __entry->page, __entry->pfn) + TP_printk("page=%p pfn=0x%lx", __entry->page, __entry->pfn) ); diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h index a966d4b5ab37..12c315782766 100644 --- a/include/trace/events/sock.h +++ b/include/trace/events/sock.h @@ -201,6 +201,66 @@ TRACE_EVENT(inet_sock_set_state, show_tcp_state_name(__entry->newstate)) ); +TRACE_EVENT(inet_sk_error_report, + + TP_PROTO(const struct sock *sk), + + TP_ARGS(sk), + + TP_STRUCT__entry( + __field(int, error) + __field(__u16, sport) + __field(__u16, dport) + __field(__u16, family) + __field(__u16, protocol) + __array(__u8, saddr, 4) + __array(__u8, daddr, 4) + __array(__u8, saddr_v6, 16) + __array(__u8, daddr_v6, 16) + ), + + TP_fast_assign( + struct inet_sock *inet = inet_sk(sk); + struct in6_addr *pin6; + __be32 *p32; + + __entry->error = sk->sk_err; + __entry->family = sk->sk_family; + __entry->protocol = sk->sk_protocol; + __entry->sport = ntohs(inet->inet_sport); + __entry->dport = ntohs(inet->inet_dport); + + p32 = (__be32 *) __entry->saddr; + *p32 = inet->inet_saddr; + + p32 = (__be32 *) __entry->daddr; + *p32 = inet->inet_daddr; + +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) { + pin6 = (struct in6_addr *)__entry->saddr_v6; + *pin6 = sk->sk_v6_rcv_saddr; + pin6 = (struct in6_addr *)__entry->daddr_v6; + *pin6 = sk->sk_v6_daddr; + } else +#endif + { + pin6 = (struct in6_addr *)__entry->saddr_v6; + ipv6_addr_set_v4mapped(inet->inet_saddr, pin6); + pin6 = (struct in6_addr *)__entry->daddr_v6; + ipv6_addr_set_v4mapped(inet->inet_daddr, pin6); + } + ), + + TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c error=%d", + show_family_name(__entry->family), + show_inet_protocol_name(__entry->protocol), + __entry->sport, __entry->dport, + __entry->saddr, __entry->daddr, + __entry->saddr_v6, __entry->daddr_v6, + __entry->error) +); + #endif /* _TRACE_SOCK_H */ /* This part must be outside protection */ diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index ba94857eea11..521059d8dc0a 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -295,6 +295,82 @@ TRACE_EVENT(tcp_probe, __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie) ); +#define TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb) \ + do { \ + const struct tcphdr *th = (const struct tcphdr *)skb->data; \ + struct sockaddr_in *v4 = (void *)__entry->saddr; \ + \ + v4->sin_family = AF_INET; \ + v4->sin_port = th->source; \ + v4->sin_addr.s_addr = ip_hdr(skb)->saddr; \ + v4 = (void *)__entry->daddr; \ + v4->sin_family = AF_INET; \ + v4->sin_port = th->dest; \ + v4->sin_addr.s_addr = ip_hdr(skb)->daddr; \ + } while (0) + +#if IS_ENABLED(CONFIG_IPV6) + +#define TP_STORE_ADDR_PORTS_SKB(__entry, skb) \ + do { \ + const struct iphdr *iph = ip_hdr(skb); \ + \ + if (iph->version == 6) { \ + const struct tcphdr *th = (const struct tcphdr *)skb->data; \ + struct sockaddr_in6 *v6 = (void *)__entry->saddr; \ + \ + v6->sin6_family = AF_INET6; \ + v6->sin6_port = th->source; \ + v6->sin6_addr = ipv6_hdr(skb)->saddr; \ + v6 = (void *)__entry->daddr; \ + v6->sin6_family = AF_INET6; \ + v6->sin6_port = th->dest; \ + v6->sin6_addr = ipv6_hdr(skb)->daddr; \ + } else \ + TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb); \ + } while (0) + +#else + +#define TP_STORE_ADDR_PORTS_SKB(__entry, skb) \ + TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb) + +#endif + +/* + * tcp event with only skb + */ +DECLARE_EVENT_CLASS(tcp_event_skb, + + TP_PROTO(const struct sk_buff *skb), + + TP_ARGS(skb), + + TP_STRUCT__entry( + __field(const void *, skbaddr) + __array(__u8, saddr, sizeof(struct sockaddr_in6)) + __array(__u8, daddr, sizeof(struct sockaddr_in6)) + ), + + TP_fast_assign( + __entry->skbaddr = skb; + + memset(__entry->saddr, 0, sizeof(struct sockaddr_in6)); + memset(__entry->daddr, 0, sizeof(struct sockaddr_in6)); + + TP_STORE_ADDR_PORTS_SKB(__entry, skb); + ), + + TP_printk("src=%pISpc dest=%pISpc", __entry->saddr, __entry->daddr) +); + +DEFINE_EVENT(tcp_event_skb, tcp_bad_csum, + + TP_PROTO(const struct sk_buff *skb), + + TP_ARGS(skb) +); + #endif /* _TRACE_TCP_H */ /* This part must be outside protection */ diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 2070df64958e..00d1180527d8 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -330,7 +330,7 @@ TRACE_EVENT(mm_vmscan_writepage, page_is_file_lru(page)); ), - TP_printk("page=%p pfn=%lu flags=%s", + TP_printk("page=%p pfn=0x%lx flags=%s", pfn_to_page(__entry->pfn), __entry->pfn, show_reclaim_flags(__entry->reclaim_flags)) diff --git a/include/trace/events/vsock_virtio_transport_common.h b/include/trace/events/vsock_virtio_transport_common.h index 6782213778be..d0b3f0ea9ba1 100644 --- a/include/trace/events/vsock_virtio_transport_common.h +++ b/include/trace/events/vsock_virtio_transport_common.h @@ -9,9 +9,12 @@ #include TRACE_DEFINE_ENUM(VIRTIO_VSOCK_TYPE_STREAM); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_TYPE_SEQPACKET); #define show_type(val) \ - __print_symbolic(val, { VIRTIO_VSOCK_TYPE_STREAM, "STREAM" }) + __print_symbolic(val, \ + { VIRTIO_VSOCK_TYPE_STREAM, "STREAM" }, \ + { VIRTIO_VSOCK_TYPE_SEQPACKET, "SEQPACKET" }) TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_INVALID); TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_REQUEST); diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index fcad3645a70b..c40fc97f9417 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -110,7 +110,11 @@ DECLARE_EVENT_CLASS(xdp_redirect_template, u32 ifindex = 0, map_index = index; if (map_type == BPF_MAP_TYPE_DEVMAP || map_type == BPF_MAP_TYPE_DEVMAP_HASH) { - ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex; + /* Just leave to_ifindex to 0 if do broadcast redirect, + * as tgt will be NULL. + */ + if (tgt) + ifindex = ((struct _bpf_dtab_netdev *)tgt)->dev->ifindex; } else if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { ifindex = index; map_index = 0; diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 4dcd13d097a9..d588c244ec2f 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -122,6 +122,8 @@ #define SO_PREFER_BUSY_POLL 69 #define SO_BUSY_POLL_BUDGET 70 +#define SO_NETNS_COOKIE 71 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index d2a942086fcb..f211961ce1da 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -863,7 +863,8 @@ __SYSCALL(__NR_process_madvise, sys_process_madvise) __SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) #define __NR_mount_setattr 442 __SYSCALL(__NR_mount_setattr, sys_mount_setattr) -/* 443 is reserved for quotactl_path */ +#define __NR_quotactl_fd 443 +__SYSCALL(__NR_quotactl_fd, sys_quotactl_fd) #define __NR_landlock_create_ruleset 444 __SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset) diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index cd2d8279a5e4..daa481729e9b 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -48,7 +48,7 @@ * 2500 - 2999 future user space (maybe integrity labels and related events) * * Messages from 1000-1199 are bi-directional. 1200-1299 & 2100 - 2999 are - * exclusively user space. 1300-2099 is kernel --> user space + * exclusively user space. 1300-2099 is kernel --> user space * communication. */ #define AUDIT_GET 1000 /* Get status */ @@ -78,7 +78,7 @@ #define AUDIT_LAST_USER_MSG 1199 #define AUDIT_FIRST_USER_MSG2 2100 /* More user space messages */ #define AUDIT_LAST_USER_MSG2 2999 - + #define AUDIT_DAEMON_START 1200 /* Daemon startup record */ #define AUDIT_DAEMON_END 1201 /* Daemon normal stop record */ #define AUDIT_DAEMON_ABORT 1202 /* Daemon error stop record */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ec6d85a81744..bf9252c7381e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -527,6 +527,15 @@ union bpf_iter_link_info { * Look up an element with the given *key* in the map referred to * by the file descriptor *fd*, and if found, delete the element. * + * For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map + * types, the *flags* argument needs to be set to 0, but for other + * map types, it may be specified as: + * + * **BPF_F_LOCK** + * Look up and delete the value of a spin-locked map + * without returning the lock. This must be specified if + * the elements contain a spinlock. + * * The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types * implement this command as a "pop" operation, deleting the top * element rather than one corresponding to *key*. @@ -536,6 +545,10 @@ union bpf_iter_link_info { * This command is only valid for the following map types: * * **BPF_MAP_TYPE_QUEUE** * * **BPF_MAP_TYPE_STACK** + * * **BPF_MAP_TYPE_HASH** + * * **BPF_MAP_TYPE_PERCPU_HASH** + * * **BPF_MAP_TYPE_LRU_HASH** + * * **BPF_MAP_TYPE_LRU_PERCPU_HASH** * * Return * Returns zero on success. On error, -1 is returned and *errno* @@ -837,6 +850,7 @@ enum bpf_cmd { BPF_PROG_ATTACH, BPF_PROG_DETACH, BPF_PROG_TEST_RUN, + BPF_PROG_RUN = BPF_PROG_TEST_RUN, BPF_PROG_GET_NEXT_ID, BPF_MAP_GET_NEXT_ID, BPF_PROG_GET_FD_BY_ID, @@ -937,6 +951,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_EXT, BPF_PROG_TYPE_LSM, BPF_PROG_TYPE_SK_LOOKUP, + BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ }; enum bpf_attach_type { @@ -979,6 +994,8 @@ enum bpf_attach_type { BPF_SK_LOOKUP, BPF_XDP, BPF_SK_SKB_VERDICT, + BPF_SK_REUSEPORT_SELECT, + BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, __MAX_BPF_ATTACH_TYPE }; @@ -1097,8 +1114,8 @@ enum bpf_link_type { /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * - * insn[0].src_reg: BPF_PSEUDO_MAP_FD - * insn[0].imm: map fd + * insn[0].src_reg: BPF_PSEUDO_MAP_[FD|IDX] + * insn[0].imm: map fd or fd_idx * insn[1].imm: 0 * insn[0].off: 0 * insn[1].off: 0 @@ -1106,15 +1123,19 @@ enum bpf_link_type { * verifier type: CONST_PTR_TO_MAP */ #define BPF_PSEUDO_MAP_FD 1 -/* insn[0].src_reg: BPF_PSEUDO_MAP_VALUE - * insn[0].imm: map fd +#define BPF_PSEUDO_MAP_IDX 5 + +/* insn[0].src_reg: BPF_PSEUDO_MAP_[IDX_]VALUE + * insn[0].imm: map fd or fd_idx * insn[1].imm: offset into value * insn[0].off: 0 * insn[1].off: 0 * ldimm64 rewrite: address of map[0]+offset * verifier type: PTR_TO_MAP_VALUE */ -#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_IDX_VALUE 6 + /* insn[0].src_reg: BPF_PSEUDO_BTF_ID * insn[0].imm: kernel btd id of VAR * insn[1].imm: 0 @@ -1314,6 +1335,8 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; + __u32 :32; /* pad */ + __aligned_u64 fd_array; /* array of FDs */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -2534,8 +2557,12 @@ union bpf_attr { * The lower two bits of *flags* are used as the return code if * the map lookup fails. This is so that the return value can be * one of the XDP program return codes up to **XDP_TX**, as chosen - * by the caller. Any higher bits in the *flags* argument must be - * unset. + * by the caller. The higher bits of *flags* can be set to + * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below. + * + * With BPF_F_BROADCAST the packet will be broadcasted to all the + * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress + * interface will be excluded when do broadcasting. * * See also **bpf_redirect**\ (), which only supports redirecting * to an ifindex, but doesn't require a map to do so. @@ -4735,6 +4762,24 @@ union bpf_attr { * be zero-terminated except when **str_size** is 0. * * Or **-EBUSY** if the per-CPU memory copy buffer is busy. + * + * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size) + * Description + * Execute bpf syscall with given arguments. + * Return + * A syscall result. + * + * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags) + * Description + * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs. + * Return + * Returns btf_id and btf_obj_fd in lower and upper 32 bits. + * + * long bpf_sys_close(u32 fd) + * Description + * Execute close syscall for given FD. + * Return + * A syscall result. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4903,6 +4948,9 @@ union bpf_attr { FN(check_mtu), \ FN(for_each_map_elem), \ FN(snprintf), \ + FN(sys_bpf), \ + FN(btf_find_by_name_kind), \ + FN(sys_close), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5080,6 +5128,12 @@ enum { BPF_F_BPRM_SECUREEXEC = (1ULL << 0), }; +/* Flags for bpf_redirect_map helper */ +enum { + BPF_F_BROADCAST = (1ULL << 3), + BPF_F_EXCLUDE_INGRESS = (1ULL << 4), +}; + #define __bpf_md_ptr(type, name) \ union { \ type name; \ @@ -5364,6 +5418,20 @@ struct sk_reuseport_md { __u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */ __u32 bind_inany; /* Is sock bound to an INANY address? */ __u32 hash; /* A hash of the packet 4 tuples */ + /* When reuse->migrating_sk is NULL, it is selecting a sk for the + * new incoming connection request (e.g. selecting a listen sk for + * the received SYN in the TCP case). reuse->sk is one of the sk + * in the reuseport group. The bpf prog can use reuse->sk to learn + * the local listening ip/port without looking into the skb. + * + * When reuse->migrating_sk is not NULL, reuse->sk is closed and + * reuse->migrating_sk is the socket that needs to be migrated + * to another listening socket. migrating_sk could be a fullsock + * sk that is fully established or a reqsk that is in-the-middle + * of 3-way handshake. + */ + __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(struct bpf_sock *, migrating_sk); }; #define BPF_TAG_SIZE 8 diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index c7535352fef6..90801ada2bbe 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -123,8 +123,8 @@ struct can_frame { /* * defined bits for canfd_frame.flags * - * The use of struct canfd_frame implies the Extended Data Length (EDL) bit to - * be set in the CAN frame bitstream on the wire. The EDL bit switch turns + * The use of struct canfd_frame implies the FD Frame (FDF) bit to + * be set in the CAN frame bitstream on the wire. The FDF bit switch turns * the CAN controllers bitstream processor into the CAN FD mode which creates * two new options within the CAN FD frame specification: * @@ -135,9 +135,18 @@ struct can_frame { * controller only the CANFD_BRS bit is relevant for real CAN controllers when * building a CAN FD frame for transmission. Setting the CANFD_ESI bit can make * sense for virtual CAN interfaces to test applications with echoed frames. + * + * The struct can_frame and struct canfd_frame intentionally share the same + * layout to be able to write CAN frame content into a CAN FD frame structure. + * When this is done the former differentiation via CAN_MTU / CANFD_MTU gets + * lost. CANFD_FDF allows programmers to mark CAN FD frames in the case of + * using struct canfd_frame for mixed CAN / CAN FD content (dual use). + * N.B. the Kernel APIs do NOT provide mixed CAN / CAN FD content inside of + * struct canfd_frame therefore the CANFD_FDF flag is disregarded by Linux. */ #define CANFD_BRS 0x01 /* bit rate switch (second bitrate for payload data) */ #define CANFD_ESI 0x02 /* error state indicator of the transmitting node */ +#define CANFD_FDF 0x04 /* mark CAN FD for dual use of struct canfd_frame */ /** * struct canfd_frame - CAN flexible data rate frame structure diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index f6008b2fa60f..32f53a0069d6 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -126,6 +126,11 @@ enum devlink_command { DEVLINK_CMD_HEALTH_REPORTER_TEST, + DEVLINK_CMD_RATE_GET, /* can dump */ + DEVLINK_CMD_RATE_SET, + DEVLINK_CMD_RATE_NEW, + DEVLINK_CMD_RATE_DEL, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -206,6 +211,11 @@ enum devlink_port_flavour { */ }; +enum devlink_rate_type { + DEVLINK_RATE_TYPE_LEAF, + DEVLINK_RATE_TYPE_NODE, +}; + enum devlink_param_cmode { DEVLINK_PARAM_CMODE_RUNTIME, DEVLINK_PARAM_CMODE_DRIVERINIT, @@ -534,6 +544,13 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_ACTION_STATS, /* nested */ DEVLINK_ATTR_PORT_PCI_SF_NUMBER, /* u32 */ + + DEVLINK_ATTR_RATE_TYPE, /* u16 */ + DEVLINK_ATTR_RATE_TX_SHARE, /* u64 */ + DEVLINK_ATTR_RATE_TX_MAX, /* u64 */ + DEVLINK_ATTR_RATE_NODE_NAME, /* string */ + DEVLINK_ATTR_RATE_PARENT_NODE_NAME, /* string */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index cfef6b08169a..67aa7134b301 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -233,7 +233,7 @@ enum tunable_id { ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */ /* * Add your fresh new tunable attribute above and remember to update - * tunable_strings[] in net/core/ethtool.c + * tunable_strings[] in net/ethtool/common.c */ __ETHTOOL_TUNABLE_COUNT, }; @@ -297,7 +297,7 @@ enum phy_tunable_id { ETHTOOL_PHY_EDPD, /* * Add your fresh new phy tunable attribute above and remember to update - * phy_tunable_strings[] in net/core/ethtool.c + * phy_tunable_strings[] in net/ethtool/common.c */ __ETHTOOL_PHY_TUNABLE_COUNT, }; diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 825cfda1c5d5..c7135c9c37a5 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -675,7 +675,7 @@ enum { ETHTOOL_A_MODULE_EEPROM_PAGE, /* u8 */ ETHTOOL_A_MODULE_EEPROM_BANK, /* u8 */ ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS, /* u8 */ - ETHTOOL_A_MODULE_EEPROM_DATA, /* nested */ + ETHTOOL_A_MODULE_EEPROM_DATA, /* binary */ __ETHTOOL_A_MODULE_EEPROM_CNT, ETHTOOL_A_MODULE_EEPROM_MAX = (__ETHTOOL_A_MODULE_EEPROM_CNT - 1) diff --git a/include/uapi/linux/icmp.h b/include/uapi/linux/icmp.h index c1da8244c5e1..163c0998aec9 100644 --- a/include/uapi/linux/icmp.h +++ b/include/uapi/linux/icmp.h @@ -20,7 +20,6 @@ #include #include -#include #include #include @@ -154,7 +153,7 @@ struct icmp_ext_echo_iio { struct { struct icmp_ext_echo_ctype3_hdr ctype3_hdr; union { - struct in_addr ipv4_addr; + __be32 ipv4_addr; struct in6_addr ipv6_addr; } ip_addr; } addr; diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 13d59c51ef5b..6b56a7549531 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -627,6 +627,8 @@ enum { MDBA_ROUTER_PATTR_UNSPEC, MDBA_ROUTER_PATTR_TIMER, MDBA_ROUTER_PATTR_TYPE, + MDBA_ROUTER_PATTR_INET_TIMER, + MDBA_ROUTER_PATTR_INET6_TIMER, __MDBA_ROUTER_PATTR_MAX }; #define MDBA_ROUTER_PATTR_MAX (__MDBA_ROUTER_PATTR_MAX - 1) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index cd5b382a4138..4882e81514b6 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -341,6 +341,13 @@ enum { IFLA_ALT_IFNAME, /* Alternative ifname */ IFLA_PERM_ADDRESS, IFLA_PROTO_DOWN_REASON, + + /* device (sysfs) name as parent, used instead + * of IFLA_LINK where there's no parent netdev + */ + IFLA_PARENT_DEV_NAME, + IFLA_PARENT_DEV_BUS_NAME, + __IFLA_MAX }; @@ -1236,6 +1243,8 @@ enum { #define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1) #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2) #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3) +#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5 (1U << 4) +#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5 (1U << 5) enum { IFLA_RMNET_UNSPEC, diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 162ff99ed2cb..79126d5cd289 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -46,21 +46,17 @@ struct io_uring_sqe { __u32 unlink_flags; }; __u64 user_data; /* data to be passed back at completion time */ + /* pack this to avoid bogus arm OABI complaints */ union { - struct { - /* pack this to avoid bogus arm OABI complaints */ - union { - /* index into fixed buffers, if used */ - __u16 buf_index; - /* for grouped buffer selection */ - __u16 buf_group; - } __attribute__((packed)); - /* personality to use, if used */ - __u16 personality; - __s32 splice_fd_in; - }; - __u64 __pad2[3]; - }; + /* index into fixed buffers, if used */ + __u16 buf_index; + /* for grouped buffer selection */ + __u16 buf_group; + } __attribute__((packed)); + /* personality to use, if used */ + __u16 personality; + __s32 splice_fd_in; + __u64 __pad2[2]; }; enum { @@ -306,6 +302,10 @@ enum { IORING_REGISTER_BUFFERS2 = 15, IORING_REGISTER_BUFFERS_UPDATE = 16, + /* set/clear io-wq thread affinities */ + IORING_REGISTER_IOWQ_AFF = 17, + IORING_UNREGISTER_IOWQ_AFF = 18, + /* this goes last */ IORING_REGISTER_LAST }; diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index e6524ead2b7b..dd7a166fdf9c 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -120,6 +120,7 @@ enum fsconfig_command { #define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */ #define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */ #define MOUNT_ATTR_IDMAP 0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */ +#define MOUNT_ATTR_NOSYMFOLLOW 0x00200000 /* Do not follow symlinks */ /* * mount_setattr() diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 8eb3c0844bff..7b05f7102321 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -105,6 +105,7 @@ struct mptcp_info { __u64 mptcpi_rcv_nxt; __u8 mptcpi_local_addr_used; __u8 mptcpi_local_addr_max; + __u8 mptcpi_csum_enabled; }; /* diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 1fb4ca18ffbb..e94d1fa554cb 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -813,11 +813,13 @@ enum nft_exthdr_flags { * @NFT_EXTHDR_OP_IPV6: match against ipv6 extension headers * @NFT_EXTHDR_OP_TCP: match against tcp options * @NFT_EXTHDR_OP_IPV4: match against ipv4 options + * @NFT_EXTHDR_OP_SCTP: match against sctp chunks */ enum nft_exthdr_op { NFT_EXTHDR_OP_IPV6, NFT_EXTHDR_OP_TCPOPT, NFT_EXTHDR_OP_IPV4, + NFT_EXTHDR_OP_SCTP, __NFT_EXTHDR_OP_MAX }; #define NFT_EXTHDR_OP_MAX (__NFT_EXTHDR_OP_MAX - 1) @@ -1193,6 +1195,21 @@ enum nft_counter_attributes { }; #define NFTA_COUNTER_MAX (__NFTA_COUNTER_MAX - 1) +/** + * enum nft_last_attributes - nf_tables last expression netlink attributes + * + * @NFTA_LAST_SET: last update has been set, zero means never updated (NLA_U32) + * @NFTA_LAST_MSECS: milliseconds since last update (NLA_U64) + */ +enum nft_last_attributes { + NFTA_LAST_UNSPEC, + NFTA_LAST_SET, + NFTA_LAST_MSECS, + NFTA_LAST_PAD, + __NFTA_LAST_MAX +}; +#define NFTA_LAST_MAX (__NFTA_LAST_MAX - 1) + /** * enum nft_log_attributes - nf_tables log expression netlink attributes * diff --git a/include/uapi/linux/netfilter/nfnetlink.h b/include/uapi/linux/netfilter/nfnetlink.h index 5bc960f220b3..6cd58cd2a6f0 100644 --- a/include/uapi/linux/netfilter/nfnetlink.h +++ b/include/uapi/linux/netfilter/nfnetlink.h @@ -60,7 +60,8 @@ struct nfgenmsg { #define NFNL_SUBSYS_CTHELPER 9 #define NFNL_SUBSYS_NFTABLES 10 #define NFNL_SUBSYS_NFT_COMPAT 11 -#define NFNL_SUBSYS_COUNT 12 +#define NFNL_SUBSYS_HOOK 12 +#define NFNL_SUBSYS_COUNT 13 /* Reserved control nfnetlink messages */ #define NFNL_MSG_BATCH_BEGIN NLMSG_MIN_TYPE diff --git a/include/uapi/linux/netfilter/nfnetlink_hook.h b/include/uapi/linux/netfilter/nfnetlink_hook.h new file mode 100644 index 000000000000..912ec60b26b0 --- /dev/null +++ b/include/uapi/linux/netfilter/nfnetlink_hook.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _NFNL_HOOK_H_ +#define _NFNL_HOOK_H_ + +enum nfnl_hook_msg_types { + NFNL_MSG_HOOK_GET, + NFNL_MSG_HOOK_MAX, +}; + +/** + * enum nfnl_hook_attributes - netfilter hook netlink attributes + * + * @NFNLA_HOOK_HOOKNUM: netfilter hook number (NLA_U32) + * @NFNLA_HOOK_PRIORITY: netfilter hook priority (NLA_U32) + * @NFNLA_HOOK_DEV: netdevice name (NLA_STRING) + * @NFNLA_HOOK_FUNCTION_NAME: hook function name (NLA_STRING) + * @NFNLA_HOOK_MODULE_NAME: kernel module that registered this hook (NLA_STRING) + * @NFNLA_HOOK_CHAIN_INFO: basechain hook metadata (NLA_NESTED) + */ +enum nfnl_hook_attributes { + NFNLA_HOOK_UNSPEC, + NFNLA_HOOK_HOOKNUM, + NFNLA_HOOK_PRIORITY, + NFNLA_HOOK_DEV, + NFNLA_HOOK_FUNCTION_NAME, + NFNLA_HOOK_MODULE_NAME, + NFNLA_HOOK_CHAIN_INFO, + __NFNLA_HOOK_MAX +}; +#define NFNLA_HOOK_MAX (__NFNLA_HOOK_MAX - 1) + +/** + * enum nfnl_hook_chain_info_attributes - chain description + * + * NFNLA_HOOK_INFO_DESC: nft chain and table name (enum nft_table_attributes) (NLA_NESTED) + * NFNLA_HOOK_INFO_TYPE: chain type (enum nfnl_hook_chaintype) (NLA_U32) + */ +enum nfnl_hook_chain_info_attributes { + NFNLA_HOOK_INFO_UNSPEC, + NFNLA_HOOK_INFO_DESC, + NFNLA_HOOK_INFO_TYPE, + __NFNLA_HOOK_INFO_MAX, +}; +#define NFNLA_HOOK_INFO_MAX (__NFNLA_HOOK_INFO_MAX - 1) + +/** + * enum nfnl_hook_chaintype - chain type + * + * @NFNL_HOOK_TYPE_NFTABLES nf_tables base chain + */ +enum nfnl_hook_chaintype { + NFNL_HOOK_TYPE_NFTABLES = 0x1, +}; + +#endif /* _NFNL_HOOK_H */ diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 3d94269bbfa8..4c0cde075c27 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -91,9 +91,10 @@ struct nlmsghdr { #define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr))) #define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN) #define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len)) -#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0))) +#define NLMSG_DATA(nlh) ((void *)(((char *)nlh) + NLMSG_HDRLEN)) #define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \ - (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len))) + (struct nlmsghdr *)(((char *)(nlh)) + \ + NLMSG_ALIGN((nlh)->nlmsg_len))) #define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \ (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \ (nlh)->nlmsg_len <= (len)) diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index f962c06e9818..db474994fa73 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -11,7 +11,7 @@ * Copyright 2008 Jouni Malinen * Copyright 2008 Colin McCabe * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -3654,6 +3654,8 @@ enum nl80211_mpath_info { * defined * @NL80211_BAND_IFTYPE_ATTR_HE_6GHZ_CAPA: HE 6GHz band capabilities (__le16), * given for all 6 GHz band channels + * @NL80211_BAND_IFTYPE_ATTR_VENDOR_ELEMS: vendor element capabilities that are + * advertised on this band/for this iftype (binary) * @__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST: internal use */ enum nl80211_band_iftype_attr { @@ -3665,6 +3667,7 @@ enum nl80211_band_iftype_attr { NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET, NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE, NL80211_BAND_IFTYPE_ATTR_HE_6GHZ_CAPA, + NL80211_BAND_IFTYPE_ATTR_VENDOR_ELEMS, /* keep last */ __NL80211_BAND_IFTYPE_ATTR_AFTER_LAST, @@ -6912,6 +6915,9 @@ enum nl80211_peer_measurement_ftm_capa { * @NL80211_PMSR_FTM_REQ_ATTR_LMR_FEEDBACK: negotiate for LMR feedback. Only * valid if either %NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED or * %NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED is set. + * @NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR: optional. The BSS color of the + * responder. Only valid if %NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED + * or %NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED is set. * * @NUM_NL80211_PMSR_FTM_REQ_ATTR: internal * @NL80211_PMSR_FTM_REQ_ATTR_MAX: highest attribute number @@ -6931,6 +6937,7 @@ enum nl80211_peer_measurement_ftm_req { NL80211_PMSR_FTM_REQ_ATTR_TRIGGER_BASED, NL80211_PMSR_FTM_REQ_ATTR_NON_TRIGGER_BASED, NL80211_PMSR_FTM_REQ_ATTR_LMR_FEEDBACK, + NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR, /* keep last */ NUM_NL80211_PMSR_FTM_REQ_ATTR, diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index cb78e7a739da..c4ff1ebd8bcc 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -141,6 +141,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_EXPOSE_POTENTIALLY_FAILED_STATE 131 #define SCTP_EXPOSE_PF_STATE SCTP_EXPOSE_POTENTIALLY_FAILED_STATE #define SCTP_REMOTE_UDP_ENCAPS_PORT 132 +#define SCTP_PLPMTUD_PROBE_INTERVAL 133 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 @@ -1213,4 +1214,11 @@ enum sctp_sched_type { SCTP_SS_MAX = SCTP_SS_RR }; +/* Probe Interval socket option */ +struct sctp_probeinterval { + sctp_assoc_t spi_assoc_id; + struct sockaddr_storage spi_address; + __u32 spi_interval; +}; + #endif /* _UAPI_SCTP_H */ diff --git a/include/uapi/linux/seg6_local.h b/include/uapi/linux/seg6_local.h index 5ae3ace84de0..332b18f318f8 100644 --- a/include/uapi/linux/seg6_local.h +++ b/include/uapi/linux/seg6_local.h @@ -64,6 +64,8 @@ enum { SEG6_LOCAL_ACTION_END_AM = 14, /* custom BPF action */ SEG6_LOCAL_ACTION_END_BPF = 15, + /* decap and lookup of DA in v4 or v6 table */ + SEG6_LOCAL_ACTION_END_DT46 = 16, __SEG6_LOCAL_ACTION_MAX, }; diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 3e68da07fba2..0f7f87c70baf 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -47,6 +47,8 @@ enum { SMC_NETLINK_GET_LGR_SMCD, SMC_NETLINK_GET_DEV_SMCD, SMC_NETLINK_GET_DEV_SMCR, + SMC_NETLINK_GET_STATS, + SMC_NETLINK_GET_FBACK_STATS, }; /* SMC_GENL_FAMILY top level attributes */ @@ -58,6 +60,8 @@ enum { SMC_GEN_LGR_SMCD, /* nest */ SMC_GEN_DEV_SMCD, /* nest */ SMC_GEN_DEV_SMCR, /* nest */ + SMC_GEN_STATS, /* nest */ + SMC_GEN_FBACK_STATS, /* nest */ __SMC_GEN_MAX, SMC_GEN_MAX = __SMC_GEN_MAX - 1 }; @@ -159,4 +163,83 @@ enum { SMC_NLA_DEV_MAX = __SMC_NLA_DEV_MAX - 1 }; +/* SMC_NLA_STATS_T_TX(RX)_RMB_SIZE nested attributes */ +/* SMC_NLA_STATS_TX(RX)PLOAD_SIZE nested attributes */ +enum { + SMC_NLA_STATS_PLOAD_PAD, + SMC_NLA_STATS_PLOAD_8K, /* u64 */ + SMC_NLA_STATS_PLOAD_16K, /* u64 */ + SMC_NLA_STATS_PLOAD_32K, /* u64 */ + SMC_NLA_STATS_PLOAD_64K, /* u64 */ + SMC_NLA_STATS_PLOAD_128K, /* u64 */ + SMC_NLA_STATS_PLOAD_256K, /* u64 */ + SMC_NLA_STATS_PLOAD_512K, /* u64 */ + SMC_NLA_STATS_PLOAD_1024K, /* u64 */ + SMC_NLA_STATS_PLOAD_G_1024K, /* u64 */ + __SMC_NLA_STATS_PLOAD_MAX, + SMC_NLA_STATS_PLOAD_MAX = __SMC_NLA_STATS_PLOAD_MAX - 1 +}; + +/* SMC_NLA_STATS_T_TX(RX)_RMB_STATS nested attributes */ +enum { + SMC_NLA_STATS_RMB_PAD, + SMC_NLA_STATS_RMB_SIZE_SM_PEER_CNT, /* u64 */ + SMC_NLA_STATS_RMB_SIZE_SM_CNT, /* u64 */ + SMC_NLA_STATS_RMB_FULL_PEER_CNT, /* u64 */ + SMC_NLA_STATS_RMB_FULL_CNT, /* u64 */ + SMC_NLA_STATS_RMB_REUSE_CNT, /* u64 */ + SMC_NLA_STATS_RMB_ALLOC_CNT, /* u64 */ + SMC_NLA_STATS_RMB_DGRADE_CNT, /* u64 */ + __SMC_NLA_STATS_RMB_MAX, + SMC_NLA_STATS_RMB_MAX = __SMC_NLA_STATS_RMB_MAX - 1 +}; + +/* SMC_NLA_STATS_SMCD_TECH and _SMCR_TECH nested attributes */ +enum { + SMC_NLA_STATS_T_PAD, + SMC_NLA_STATS_T_TX_RMB_SIZE, /* nest */ + SMC_NLA_STATS_T_RX_RMB_SIZE, /* nest */ + SMC_NLA_STATS_T_TXPLOAD_SIZE, /* nest */ + SMC_NLA_STATS_T_RXPLOAD_SIZE, /* nest */ + SMC_NLA_STATS_T_TX_RMB_STATS, /* nest */ + SMC_NLA_STATS_T_RX_RMB_STATS, /* nest */ + SMC_NLA_STATS_T_CLNT_V1_SUCC, /* u64 */ + SMC_NLA_STATS_T_CLNT_V2_SUCC, /* u64 */ + SMC_NLA_STATS_T_SRV_V1_SUCC, /* u64 */ + SMC_NLA_STATS_T_SRV_V2_SUCC, /* u64 */ + SMC_NLA_STATS_T_SENDPAGE_CNT, /* u64 */ + SMC_NLA_STATS_T_SPLICE_CNT, /* u64 */ + SMC_NLA_STATS_T_CORK_CNT, /* u64 */ + SMC_NLA_STATS_T_NDLY_CNT, /* u64 */ + SMC_NLA_STATS_T_URG_DATA_CNT, /* u64 */ + SMC_NLA_STATS_T_RX_BYTES, /* u64 */ + SMC_NLA_STATS_T_TX_BYTES, /* u64 */ + SMC_NLA_STATS_T_RX_CNT, /* u64 */ + SMC_NLA_STATS_T_TX_CNT, /* u64 */ + __SMC_NLA_STATS_T_MAX, + SMC_NLA_STATS_T_MAX = __SMC_NLA_STATS_T_MAX - 1 +}; + +/* SMC_GEN_STATS attributes */ +enum { + SMC_NLA_STATS_PAD, + SMC_NLA_STATS_SMCD_TECH, /* nest */ + SMC_NLA_STATS_SMCR_TECH, /* nest */ + SMC_NLA_STATS_CLNT_HS_ERR_CNT, /* u64 */ + SMC_NLA_STATS_SRV_HS_ERR_CNT, /* u64 */ + __SMC_NLA_STATS_MAX, + SMC_NLA_STATS_MAX = __SMC_NLA_STATS_MAX - 1 +}; + +/* SMC_GEN_FBACK_STATS attributes */ +enum { + SMC_NLA_FBACK_STATS_PAD, + SMC_NLA_FBACK_STATS_TYPE, /* u8 */ + SMC_NLA_FBACK_STATS_SRV_CNT, /* u64 */ + SMC_NLA_FBACK_STATS_CLNT_CNT, /* u64 */ + SMC_NLA_FBACK_STATS_RSN_CODE, /* u32 */ + SMC_NLA_FBACK_STATS_RSN_CNT, /* u16 */ + __SMC_NLA_FBACK_STATS_MAX, + SMC_NLA_FBACK_STATS_MAX = __SMC_NLA_FBACK_STATS_MAX - 1 +}; #endif /* _UAPI_LINUX_SMC_H */ diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 26fc60ce9298..904909d020e2 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -290,6 +290,8 @@ enum LINUX_MIB_TCPDUPLICATEDATAREHASH, /* TCPDuplicateDataRehash */ LINUX_MIB_TCPDSACKRECVSEGS, /* TCPDSACKRecvSegs */ LINUX_MIB_TCPDSACKIGNOREDDUBIOUS, /* TCPDSACKIgnoredDubious */ + LINUX_MIB_TCPMIGRATEREQSUCCESS, /* TCPMigrateReqSuccess */ + LINUX_MIB_TCPMIGRATEREQFAILURE, /* TCPMigrateReqFailure */ __LINUX_MIB_MAX }; diff --git a/include/uapi/linux/surface_aggregator/cdev.h b/include/uapi/linux/surface_aggregator/cdev.h index fbcce04abfe9..08f46b60b151 100644 --- a/include/uapi/linux/surface_aggregator/cdev.h +++ b/include/uapi/linux/surface_aggregator/cdev.h @@ -6,7 +6,7 @@ * device. This device provides direct user-space access to the SSAM EC. * Intended for debugging and development. * - * Copyright (C) 2020 Maximilian Luz + * Copyright (C) 2020-2021 Maximilian Luz */ #ifndef _UAPI_LINUX_SURFACE_AGGREGATOR_CDEV_H @@ -73,6 +73,75 @@ struct ssam_cdev_request { } response; } __attribute__((__packed__)); -#define SSAM_CDEV_REQUEST _IOWR(0xA5, 1, struct ssam_cdev_request) +/** + * struct ssam_cdev_notifier_desc - Notifier descriptor. + * @priority: Priority value determining the order in which notifier + * callbacks will be called. A higher value means higher + * priority, i.e. the associated callback will be executed + * earlier than other (lower priority) callbacks. + * @target_category: The event target category for which this notifier should + * receive events. + * + * Specifies the notifier that should be registered or unregistered, + * specifically with which priority and for which target category of events. + */ +struct ssam_cdev_notifier_desc { + __s32 priority; + __u8 target_category; +} __attribute__((__packed__)); + +/** + * struct ssam_cdev_event_desc - Event descriptor. + * @reg: Registry via which the event will be enabled/disabled. + * @reg.target_category: Target category for the event registry requests. + * @reg.target_id: Target ID for the event registry requests. + * @reg.cid_enable: Command ID for the event-enable request. + * @reg.cid_disable: Command ID for the event-disable request. + * @id: ID specifying the event. + * @id.target_category: Target category of the event source. + * @id.instance: Instance ID of the event source. + * @flags: Flags used for enabling the event. + * + * Specifies which event should be enabled/disabled and how to do that. + */ +struct ssam_cdev_event_desc { + struct { + __u8 target_category; + __u8 target_id; + __u8 cid_enable; + __u8 cid_disable; + } reg; + + struct { + __u8 target_category; + __u8 instance; + } id; + + __u8 flags; +} __attribute__((__packed__)); + +/** + * struct ssam_cdev_event - SSAM event sent by the EC. + * @target_category: Target category of the event source. See &enum ssam_ssh_tc. + * @target_id: Target ID of the event source. + * @command_id: Command ID of the event. + * @instance_id: Instance ID of the event source. + * @length: Length of the event payload in bytes. + * @data: Event payload data. + */ +struct ssam_cdev_event { + __u8 target_category; + __u8 target_id; + __u8 command_id; + __u8 instance_id; + __u16 length; + __u8 data[]; +} __attribute__((__packed__)); + +#define SSAM_CDEV_REQUEST _IOWR(0xA5, 1, struct ssam_cdev_request) +#define SSAM_CDEV_NOTIF_REGISTER _IOW(0xA5, 2, struct ssam_cdev_notifier_desc) +#define SSAM_CDEV_NOTIF_UNREGISTER _IOW(0xA5, 3, struct ssam_cdev_notifier_desc) +#define SSAM_CDEV_EVENT_ENABLE _IOW(0xA5, 4, struct ssam_cdev_event_desc) +#define SSAM_CDEV_EVENT_DISABLE _IOW(0xA5, 5, struct ssam_cdev_event_desc) #endif /* _UAPI_LINUX_SURFACE_AGGREGATOR_CDEV_H */ diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h index 1d57ed3d84d2..3dd3555b2740 100644 --- a/include/uapi/linux/virtio_vsock.h +++ b/include/uapi/linux/virtio_vsock.h @@ -38,6 +38,9 @@ #include #include +/* The feature bitmap for virtio vsock */ +#define VIRTIO_VSOCK_F_SEQPACKET 1 /* SOCK_SEQPACKET supported */ + struct virtio_vsock_config { __le64 guest_cid; } __attribute__((packed)); @@ -65,6 +68,7 @@ struct virtio_vsock_hdr { enum virtio_vsock_type { VIRTIO_VSOCK_TYPE_STREAM = 1, + VIRTIO_VSOCK_TYPE_SEQPACKET = 2, }; enum virtio_vsock_op { @@ -91,4 +95,9 @@ enum virtio_vsock_shutdown { VIRTIO_VSOCK_SHUTDOWN_SEND = 2, }; +/* VIRTIO_VSOCK_OP_RW flags values */ +enum virtio_vsock_rw { + VIRTIO_VSOCK_SEQ_EOR = 1, +}; + #endif /* _UAPI_LINUX_VIRTIO_VSOCK_H */ diff --git a/include/uapi/linux/wwan.h b/include/uapi/linux/wwan.h new file mode 100644 index 000000000000..32a2720b4d11 --- /dev/null +++ b/include/uapi/linux/wwan.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (C) 2021 Intel Corporation. + */ +#ifndef _UAPI_WWAN_H_ +#define _UAPI_WWAN_H_ + +enum { + IFLA_WWAN_UNSPEC, + IFLA_WWAN_LINK_ID, /* u32 */ + + __IFLA_WWAN_MAX +}; +#define IFLA_WWAN_MAX (__IFLA_WWAN_MAX - 1) + +#endif /* _UAPI_WWAN_H_ */ diff --git a/init/Kconfig b/init/Kconfig index b2e59e06dc79..3892833bb972 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -83,6 +83,9 @@ config TOOLS_SUPPORT_RELR config CC_HAS_ASM_INLINE def_bool $(success,echo 'void foo(void) { asm inline (""); }' | $(CC) -x c - -c -o /dev/null) +config CC_HAS_NO_PROFILE_FN_ATTR + def_bool $(success,echo '__attribute__((no_profile_instrument_function)) int x();' | $(CC) -x c - -c -o /dev/null -Werror) + config CONSTRUCTORS bool diff --git a/init/do_mounts.c b/init/do_mounts.c index a78e44ee6adb..74aede860de7 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -133,14 +133,8 @@ static dev_t devt_from_partuuid(const char *uuid_str) * Attempt to find the requested partition by adding an offset * to the partition number found by UUID. */ - struct block_device *part; - - part = bdget_disk(dev_to_disk(dev), - dev_to_bdev(dev)->bd_partno + offset); - if (part) { - devt = part->bd_dev; - bdput(part); - } + devt = part_devt(dev_to_disk(dev), + dev_to_bdev(dev)->bd_partno + offset); } else { devt = dev->devt; } diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 4e4e61111500..5becca9be867 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -144,7 +144,7 @@ struct mqueue_inode_info { struct pid *notify_owner; u32 notify_self_exec_id; struct user_namespace *notify_user_ns; - struct user_struct *user; /* user who created, for accounting */ + struct ucounts *ucounts; /* user who created, for accounting */ struct sock *notify_sock; struct sk_buff *notify_cookie; @@ -292,7 +292,6 @@ static struct inode *mqueue_get_inode(struct super_block *sb, struct ipc_namespace *ipc_ns, umode_t mode, struct mq_attr *attr) { - struct user_struct *u = current_user(); struct inode *inode; int ret = -ENOMEM; @@ -321,7 +320,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb, info->notify_owner = NULL; info->notify_user_ns = NULL; info->qsize = 0; - info->user = NULL; /* set when all is ok */ + info->ucounts = NULL; /* set when all is ok */ info->msg_tree = RB_ROOT; info->msg_tree_rightmost = NULL; info->node_cache = NULL; @@ -371,19 +370,23 @@ static struct inode *mqueue_get_inode(struct super_block *sb, if (mq_bytes + mq_treesize < mq_bytes) goto out_inode; mq_bytes += mq_treesize; - spin_lock(&mq_lock); - if (u->mq_bytes + mq_bytes < u->mq_bytes || - u->mq_bytes + mq_bytes > rlimit(RLIMIT_MSGQUEUE)) { - spin_unlock(&mq_lock); - /* mqueue_evict_inode() releases info->messages */ - ret = -EMFILE; - goto out_inode; - } - u->mq_bytes += mq_bytes; - spin_unlock(&mq_lock); + info->ucounts = get_ucounts(current_ucounts()); + if (info->ucounts) { + long msgqueue; - /* all is ok */ - info->user = get_uid(u); + spin_lock(&mq_lock); + msgqueue = inc_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes); + if (msgqueue == LONG_MAX || msgqueue > rlimit(RLIMIT_MSGQUEUE)) { + dec_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes); + spin_unlock(&mq_lock); + put_ucounts(info->ucounts); + info->ucounts = NULL; + /* mqueue_evict_inode() releases info->messages */ + ret = -EMFILE; + goto out_inode; + } + spin_unlock(&mq_lock); + } } else if (S_ISDIR(mode)) { inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ @@ -497,7 +500,6 @@ static void mqueue_free_inode(struct inode *inode) static void mqueue_evict_inode(struct inode *inode) { struct mqueue_inode_info *info; - struct user_struct *user; struct ipc_namespace *ipc_ns; struct msg_msg *msg, *nmsg; LIST_HEAD(tmp_msg); @@ -520,8 +522,7 @@ static void mqueue_evict_inode(struct inode *inode) free_msg(msg); } - user = info->user; - if (user) { + if (info->ucounts) { unsigned long mq_bytes, mq_treesize; /* Total amount of bytes accounted for the mqueue */ @@ -533,7 +534,7 @@ static void mqueue_evict_inode(struct inode *inode) info->attr.mq_msgsize); spin_lock(&mq_lock); - user->mq_bytes -= mq_bytes; + dec_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes); /* * get_ns_from_inode() ensures that the * (ipc_ns = sb->s_fs_info) is either a valid ipc_ns @@ -543,7 +544,8 @@ static void mqueue_evict_inode(struct inode *inode) if (ipc_ns) ipc_ns->mq_queues_count--; spin_unlock(&mq_lock); - free_uid(user); + put_ucounts(info->ucounts); + info->ucounts = NULL; } if (ipc_ns) put_ipc_ns(ipc_ns); diff --git a/ipc/shm.c b/ipc/shm.c index febd88daba8c..003234fbbd17 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -60,7 +60,7 @@ struct shmid_kernel /* private to the kernel */ time64_t shm_ctim; struct pid *shm_cprid; struct pid *shm_lprid; - struct user_struct *mlock_user; + struct ucounts *mlock_ucounts; /* The task created the shm object. NULL if the task is dead. */ struct task_struct *shm_creator; @@ -286,10 +286,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) shm_rmid(ns, shp); shm_unlock(shp); if (!is_file_hugepages(shm_file)) - shmem_lock(shm_file, 0, shp->mlock_user); - else if (shp->mlock_user) + shmem_lock(shm_file, 0, shp->mlock_ucounts); + else if (shp->mlock_ucounts) user_shm_unlock(i_size_read(file_inode(shm_file)), - shp->mlock_user); + shp->mlock_ucounts); fput(shm_file); ipc_update_pid(&shp->shm_cprid, NULL); ipc_update_pid(&shp->shm_lprid, NULL); @@ -625,7 +625,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) shp->shm_perm.key = key; shp->shm_perm.mode = (shmflg & S_IRWXUGO); - shp->mlock_user = NULL; + shp->mlock_ucounts = NULL; shp->shm_perm.security = NULL; error = security_shm_alloc(&shp->shm_perm); @@ -650,7 +650,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) if (shmflg & SHM_NORESERVE) acctflag = VM_NORESERVE; file = hugetlb_file_setup(name, hugesize, acctflag, - &shp->mlock_user, HUGETLB_SHMFS_INODE, + &shp->mlock_ucounts, HUGETLB_SHMFS_INODE, (shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); } else { /* @@ -698,8 +698,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) no_id: ipc_update_pid(&shp->shm_cprid, NULL); ipc_update_pid(&shp->shm_lprid, NULL); - if (is_file_hugepages(file) && shp->mlock_user) - user_shm_unlock(size, shp->mlock_user); + if (is_file_hugepages(file) && shp->mlock_ucounts) + user_shm_unlock(size, shp->mlock_ucounts); fput(file); ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); return error; @@ -1105,12 +1105,12 @@ static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd) goto out_unlock0; if (cmd == SHM_LOCK) { - struct user_struct *user = current_user(); + struct ucounts *ucounts = current_ucounts(); - err = shmem_lock(shm_file, 1, user); + err = shmem_lock(shm_file, 1, ucounts); if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) { shp->shm_perm.mode |= SHM_LOCKED; - shp->mlock_user = user; + shp->mlock_ucounts = ucounts; } goto out_unlock0; } @@ -1118,9 +1118,9 @@ static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd) /* SHM_UNLOCK */ if (!(shp->shm_perm.mode & SHM_LOCKED)) goto out_unlock0; - shmem_lock(shm_file, 0, shp->mlock_user); + shmem_lock(shm_file, 0, shp->mlock_ucounts); shp->shm_perm.mode &= ~SHM_LOCKED; - shp->mlock_user = NULL; + shp->mlock_ucounts = NULL; get_file(shm_file); ipc_unlock_object(&shp->shm_perm); rcu_read_unlock(); diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index bd7c4147b9a8..5876e30c5740 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -102,7 +102,6 @@ config PREEMPT_DYNAMIC config SCHED_CORE bool "Core Scheduling for SMT" - default y depends on SCHED_SMT help This option permits Core Scheduling, a means of coordinated task @@ -115,7 +114,8 @@ config SCHED_CORE - mitigation of some (not all) SMT side channels; - limiting SMT interference to improve determinism and/or performance. - SCHED_CORE is default enabled when SCHED_SMT is enabled -- when - unused there should be no impact on performance. + SCHED_CORE is default disabled. When it is enabled and unused, + which is the likely usage by Linux distributions, there should + be no measurable impact on performance. diff --git a/kernel/audit.h b/kernel/audit.h index 1522e100fd17..b565ea16c0a5 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ -/* audit -- definition of audit_context structure and supporting types +/* audit -- definition of audit_context structure and supporting types * * Copyright 2003-2004 Red Hat, Inc. * Copyright 2005 Hewlett-Packard Development Company, L.P. @@ -21,16 +21,16 @@ a per-task filter. At syscall entry, the audit_state is augmented by the syscall filter. */ enum audit_state { - AUDIT_DISABLED, /* Do not create per-task audit_context. + AUDIT_STATE_DISABLED, /* Do not create per-task audit_context. * No syscall-specific audit records can * be generated. */ - AUDIT_BUILD_CONTEXT, /* Create the per-task audit_context, + AUDIT_STATE_BUILD, /* Create the per-task audit_context, * and fill it in at syscall * entry time. This makes a full * syscall record available if some * other part of the kernel decides it * should be recorded. */ - AUDIT_RECORD_CONTEXT /* Create the per-task audit_context, + AUDIT_STATE_RECORD /* Create the per-task audit_context, * always fill it in at syscall entry * time, and always write out the audit * record at syscall exit time. */ @@ -322,7 +322,7 @@ static inline int audit_signal_info_syscall(struct task_struct *t) return 0; } -#define audit_filter_inodes(t, c) AUDIT_DISABLED +#define audit_filter_inodes(t, c) AUDIT_STATE_DISABLED #endif /* CONFIG_AUDITSYSCALL */ extern char *audit_unpack_string(void **bufp, size_t *remain, size_t len); diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 6c91902f4f45..b2be4e978ba3 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -689,8 +689,7 @@ void audit_trim_trees(void) tree = container_of(cursor.next, struct audit_tree, list); get_tree(tree); - list_del(&cursor); - list_add(&cursor, &tree->list); + list_move(&cursor, &tree->list); mutex_unlock(&audit_filter_mutex); err = kern_path(tree->pathname, 0, &path); @@ -899,8 +898,7 @@ int audit_tag_tree(char *old, char *new) tree = container_of(cursor.next, struct audit_tree, list); get_tree(tree); - list_del(&cursor); - list_add(&cursor, &tree->list); + list_move(&cursor, &tree->list); mutex_unlock(&audit_filter_mutex); err = kern_path(tree->pathname, 0, &path2); @@ -925,8 +923,7 @@ int audit_tag_tree(char *old, char *new) mutex_lock(&audit_filter_mutex); spin_lock(&hash_lock); if (!tree->goner) { - list_del(&tree->list); - list_add(&tree->list, &tree_list); + list_move(&tree->list, &tree_list); } spin_unlock(&hash_lock); put_tree(tree); @@ -937,8 +934,7 @@ int audit_tag_tree(char *old, char *new) tree = container_of(barrier.prev, struct audit_tree, list); get_tree(tree); - list_del(&tree->list); - list_add(&tree->list, &barrier); + list_move(&tree->list, &barrier); mutex_unlock(&audit_filter_mutex); if (!failed) { diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 175ef6f3ea4e..8dd73a64f921 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -160,6 +160,7 @@ static const struct audit_nfcfgop_tab audit_nfcfgs[] = { static int audit_match_perm(struct audit_context *ctx, int mask) { unsigned n; + if (unlikely(!ctx)) return 0; n = ctx->major; @@ -231,7 +232,7 @@ static void audit_set_auditable(struct audit_context *ctx) { if (!ctx->prio) { ctx->prio = 1; - ctx->current_state = AUDIT_RECORD_CONTEXT; + ctx->current_state = AUDIT_STATE_RECORD; } } @@ -239,6 +240,7 @@ static int put_tree_ref(struct audit_context *ctx, struct audit_chunk *chunk) { struct audit_tree_refs *p = ctx->trees; int left = ctx->tree_count; + if (likely(left)) { p->c[--left] = chunk; ctx->tree_count = left; @@ -259,6 +261,7 @@ static int put_tree_ref(struct audit_context *ctx, struct audit_chunk *chunk) static int grow_tree_refs(struct audit_context *ctx) { struct audit_tree_refs *p = ctx->trees; + ctx->trees = kzalloc(sizeof(struct audit_tree_refs), GFP_KERNEL); if (!ctx->trees) { ctx->trees = p; @@ -277,6 +280,7 @@ static void unroll_tree_refs(struct audit_context *ctx, { struct audit_tree_refs *q; int n; + if (!p) { /* we started with empty chain */ p = ctx->first_trees; @@ -303,6 +307,7 @@ static void unroll_tree_refs(struct audit_context *ctx, static void free_tree_refs(struct audit_context *ctx) { struct audit_tree_refs *p, *q; + for (p = ctx->first_trees; p; p = q) { q = p->next; kfree(p); @@ -313,6 +318,7 @@ static int match_tree_refs(struct audit_context *ctx, struct audit_tree *tree) { struct audit_tree_refs *p; int n; + if (!tree) return 0; /* full ones */ @@ -337,13 +343,13 @@ static int audit_compare_uid(kuid_t uid, { struct audit_names *n; int rc; - + if (name) { rc = audit_uid_comparator(uid, f->op, name->uid); if (rc) return rc; } - + if (ctx) { list_for_each_entry(n, &ctx->names_list, list) { rc = audit_uid_comparator(uid, f->op, n->uid); @@ -361,13 +367,13 @@ static int audit_compare_gid(kgid_t gid, { struct audit_names *n; int rc; - + if (name) { rc = audit_gid_comparator(gid, f->op, name->gid); if (rc) return rc; } - + if (ctx) { list_for_each_entry(n, &ctx->names_list, list) { rc = audit_gid_comparator(gid, f->op, n->gid); @@ -751,10 +757,10 @@ static int audit_filter_rules(struct task_struct *tsk, } switch (rule->action) { case AUDIT_NEVER: - *state = AUDIT_DISABLED; + *state = AUDIT_STATE_DISABLED; break; case AUDIT_ALWAYS: - *state = AUDIT_RECORD_CONTEXT; + *state = AUDIT_STATE_RECORD; break; } return 1; @@ -773,14 +779,14 @@ static enum audit_state audit_filter_task(struct task_struct *tsk, char **key) list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_TASK], list) { if (audit_filter_rules(tsk, &e->rule, NULL, NULL, &state, true)) { - if (state == AUDIT_RECORD_CONTEXT) + if (state == AUDIT_STATE_RECORD) *key = kstrdup(e->rule.filterkey, GFP_ATOMIC); rcu_read_unlock(); return state; } } rcu_read_unlock(); - return AUDIT_BUILD_CONTEXT; + return AUDIT_STATE_BUILD; } static int audit_in_mask(const struct audit_krule *rule, unsigned long val) @@ -802,7 +808,7 @@ static int audit_in_mask(const struct audit_krule *rule, unsigned long val) /* At syscall exit time, this filter is called if the audit_state is * not low enough that auditing cannot take place, but is also not * high enough that we already know we have to write an audit record - * (i.e., the state is AUDIT_SETUP_CONTEXT or AUDIT_BUILD_CONTEXT). + * (i.e., the state is AUDIT_STATE_BUILD). */ static void audit_filter_syscall(struct task_struct *tsk, struct audit_context *ctx) @@ -923,7 +929,7 @@ static inline struct audit_context *audit_alloc_context(enum audit_state state) if (!context) return NULL; context->state = state; - context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0; + context->prio = state == AUDIT_STATE_RECORD ? ~0ULL : 0; INIT_LIST_HEAD(&context->killed_trees); INIT_LIST_HEAD(&context->names_list); context->fds[0] = -1; @@ -950,7 +956,7 @@ int audit_alloc(struct task_struct *tsk) return 0; /* Return if not auditing. */ state = audit_filter_task(tsk, &key); - if (state == AUDIT_DISABLED) { + if (state == AUDIT_STATE_DISABLED) { clear_task_syscall_work(tsk, SYSCALL_AUDIT); return 0; } @@ -1225,6 +1231,7 @@ static void show_special(struct audit_context *context, int *call_panic) switch (context->type) { case AUDIT_SOCKETCALL: { int nargs = context->socketcall.nargs; + audit_log_format(ab, "nargs=%d", nargs); for (i = 0; i < nargs; i++) audit_log_format(ab, " a%d=%lx", i, @@ -1240,6 +1247,7 @@ static void show_special(struct audit_context *context, int *call_panic) if (osid) { char *ctx = NULL; u32 len; + if (security_secid_to_secctx(osid, &ctx, &len)) { audit_log_format(ab, " osid=%u", osid); *call_panic = 1; @@ -1289,6 +1297,7 @@ static void show_special(struct audit_context *context, int *call_panic) break; case AUDIT_MQ_GETSETATTR: { struct mq_attr *attr = &context->mq_getsetattr.mqstat; + audit_log_format(ab, "mqdes=%d mq_flags=0x%lx mq_maxmsg=%ld mq_msgsize=%ld " "mq_curmsgs=%ld ", @@ -1325,6 +1334,7 @@ static void show_special(struct audit_context *context, int *call_panic) static inline int audit_proctitle_rtrim(char *proctitle, int len) { char *end = proctitle + len - 1; + while (end > proctitle && !isprint(*end)) end--; @@ -1513,6 +1523,7 @@ static void audit_log_exit(void) case AUDIT_BPRM_FCAPS: { struct audit_aux_data_bprm_fcaps *axs = (void *)aux; + audit_log_format(ab, "fver=%x", axs->fcap_ver); audit_log_cap(ab, "fp", &axs->fcap.permitted); audit_log_cap(ab, "fi", &axs->fcap.inheritable); @@ -1628,7 +1639,7 @@ void __audit_free(struct task_struct *tsk) audit_filter_syscall(tsk, context); audit_filter_inodes(tsk, context); - if (context->current_state == AUDIT_RECORD_CONTEXT) + if (context->current_state == AUDIT_STATE_RECORD) audit_log_exit(); } @@ -1647,7 +1658,7 @@ void __audit_free(struct task_struct *tsk) * Fill in audit context at syscall entry. This only happens if the * audit context was created when the task was created and the state or * filters demand the audit context be built. If the state from the - * per-task filter or from the per-syscall filter is AUDIT_RECORD_CONTEXT, + * per-task filter or from the per-syscall filter is AUDIT_STATE_RECORD, * then the record will be written at syscall exit time (otherwise, it * will only be written if another part of the kernel requests that it * be written). @@ -1664,11 +1675,11 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2, BUG_ON(context->in_syscall || context->name_count); state = context->state; - if (state == AUDIT_DISABLED) + if (state == AUDIT_STATE_DISABLED) return; context->dummy = !audit_n_rules; - if (!context->dummy && state == AUDIT_BUILD_CONTEXT) { + if (!context->dummy && state == AUDIT_STATE_BUILD) { context->prio = 0; if (auditd_test_task(current)) return; @@ -1693,7 +1704,7 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2, * @return_code: return value of the syscall * * Tear down after system call. If the audit context has been marked as - * auditable (either because of the AUDIT_RECORD_CONTEXT state from + * auditable (either because of the AUDIT_STATE_RECORD state from * filtering, or because some other part of the kernel wrote an audit * message), then write out the syscall information. In call cases, * free the names stored from getname(). @@ -1735,12 +1746,12 @@ void __audit_syscall_exit(int success, long return_code) audit_filter_syscall(current, context); audit_filter_inodes(current, context); - if (context->current_state == AUDIT_RECORD_CONTEXT) + if (context->current_state == AUDIT_STATE_RECORD) audit_log_exit(); } context->in_syscall = 0; - context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0; + context->prio = context->state == AUDIT_STATE_RECORD ? ~0ULL : 0; audit_free_module(context); audit_free_names(context); @@ -1753,7 +1764,7 @@ void __audit_syscall_exit(int success, long return_code) context->sockaddr_len = 0; context->type = 0; context->fds[0] = -1; - if (context->state != AUDIT_RECORD_CONTEXT) { + if (context->state != AUDIT_STATE_RECORD) { kfree(context->filterkey); context->filterkey = NULL; } @@ -1765,6 +1776,7 @@ static inline void handle_one(const struct inode *inode) struct audit_tree_refs *p; struct audit_chunk *chunk; int count; + if (likely(!inode->i_fsnotify_marks)) return; context = audit_context(); @@ -1806,8 +1818,10 @@ retry: seq = read_seqbegin(&rename_lock); for(;;) { struct inode *inode = d_backing_inode(d); + if (inode && unlikely(inode->i_fsnotify_marks)) { struct audit_chunk *chunk; + chunk = audit_tree_lookup(inode); if (chunk) { if (unlikely(!put_tree_ref(context, chunk))) { @@ -2203,7 +2217,7 @@ int auditsc_get_stamp(struct audit_context *ctx, *serial = ctx->serial; if (!ctx->prio) { ctx->prio = 1; - ctx->current_state = AUDIT_RECORD_CONTEXT; + ctx->current_state = AUDIT_STATE_RECORD; } return 1; } @@ -2285,6 +2299,7 @@ void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { struct audit_context *context = audit_context(); + context->mq_getsetattr.mqdes = mqdes; context->mq_getsetattr.mqstat = *mqstat; context->type = AUDIT_MQ_GETSETATTR; @@ -2298,6 +2313,7 @@ void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) void __audit_ipc_obj(struct kern_ipc_perm *ipcp) { struct audit_context *context = audit_context(); + context->ipc.uid = ipcp->uid; context->ipc.gid = ipcp->gid; context->ipc.mode = ipcp->mode; @@ -2362,6 +2378,7 @@ int __audit_socketcall(int nargs, unsigned long *args) void __audit_fd_pair(int fd1, int fd2) { struct audit_context *context = audit_context(); + context->fds[0] = fd1; context->fds[1] = fd2; } @@ -2379,6 +2396,7 @@ int __audit_sockaddr(int len, void *a) if (!context->sockaddr) { void *p = kmalloc(sizeof(struct sockaddr_storage), GFP_KERNEL); + if (!p) return -ENOMEM; context->sockaddr = p; @@ -2510,6 +2528,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, void __audit_log_capset(const struct cred *new, const struct cred *old) { struct audit_context *context = audit_context(); + context->capset.pid = task_tgid_nr(current); context->capset.cap.effective = new->cap_effective; context->capset.cap.inheritable = new->cap_effective; @@ -2521,6 +2540,7 @@ void __audit_log_capset(const struct cred *new, const struct cred *old) void __audit_mmap_fd(int fd, int flags) { struct audit_context *context = audit_context(); + context->mmap.fd = fd; context->mmap.flags = flags; context->type = AUDIT_MMAP; @@ -2686,6 +2706,7 @@ void audit_seccomp_actions_logged(const char *names, const char *old_names, struct list_head *audit_killed_trees(void) { struct audit_context *ctx = audit_context(); + if (likely(!ctx || !ctx->in_syscall)) return NULL; return &ctx->killed_trees; diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 2921ca39a93e..96ceed0e0fb5 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -72,7 +72,7 @@ void bpf_inode_storage_free(struct inode *inode) return; } - /* Netiher the bpf_prog nor the bpf-map's syscall + /* Neither the bpf_prog nor the bpf-map's syscall * could be modifying the local_storage->list now. * Thus, no elem can be added-to or deleted-from the * local_storage->list by the bpf_prog or by the bpf-map's syscall. diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 931870f9cf56..2d4fbdbb194e 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -473,15 +473,16 @@ bool bpf_link_is_iter(struct bpf_link *link) return link->ops == &bpf_iter_link_lops; } -int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, + struct bpf_prog *prog) { - union bpf_iter_link_info __user *ulinfo; struct bpf_link_primer link_primer; struct bpf_iter_target_info *tinfo; union bpf_iter_link_info linfo; struct bpf_iter_link *link; u32 prog_btf_id, linfo_len; bool existed = false; + bpfptr_t ulinfo; int err; if (attr->link_create.target_fd || attr->link_create.flags) @@ -489,18 +490,18 @@ int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) memset(&linfo, 0, sizeof(union bpf_iter_link_info)); - ulinfo = u64_to_user_ptr(attr->link_create.iter_info); + ulinfo = make_bpfptr(attr->link_create.iter_info, uattr.is_kernel); linfo_len = attr->link_create.iter_info_len; - if (!ulinfo ^ !linfo_len) + if (bpfptr_is_null(ulinfo) ^ !linfo_len) return -EINVAL; - if (ulinfo) { + if (!bpfptr_is_null(ulinfo)) { err = bpf_check_uarg_tail_zero(ulinfo, sizeof(linfo), linfo_len); if (err) return err; linfo_len = min_t(u32, linfo_len, sizeof(linfo)); - if (copy_from_user(&linfo, ulinfo, linfo_len)) + if (copy_from_bpfptr(&linfo, ulinfo, linfo_len)) return -EFAULT; } diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index da471bf01b97..06062370c3b8 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -127,7 +127,7 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } /* The set of hooks which are called without pagefaults disabled and are allowed - * to "sleep" and thus can be used for sleeable BPF programs. + * to "sleep" and thus can be used for sleepable BPF programs. */ BTF_SET_START(sleepable_lsm_hooks) BTF_ID(func, bpf_lsm_bpf) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index f982a9f0dbc4..cb4b72997d9b 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -51,7 +51,7 @@ * The BTF type section contains a list of 'struct btf_type' objects. * Each one describes a C type. Recall from the above section * that a 'struct btf_type' object could be immediately followed by extra - * data in order to desribe some particular C types. + * data in order to describe some particular C types. * * type_id: * ~~~~~~~ @@ -1143,7 +1143,7 @@ static void *btf_show_obj_safe(struct btf_show *show, /* * We need a new copy to our safe object, either because we haven't - * yet copied and are intializing safe data, or because the data + * yet copied and are initializing safe data, or because the data * we want falls outside the boundaries of the safe object. */ if (!safe) { @@ -3417,7 +3417,7 @@ static struct btf_kind_operations func_proto_ops = { * BTF_KIND_FUNC_PROTO cannot be directly referred by * a struct's member. * - * It should be a funciton pointer instead. + * It should be a function pointer instead. * (i.e. struct's member -> BTF_KIND_PTR -> BTF_KIND_FUNC_PROTO) * * Hence, there is no btf_func_check_member(). @@ -4257,7 +4257,7 @@ static int btf_parse_hdr(struct btf_verifier_env *env) return 0; } -static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, +static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, u32 log_level, char __user *log_ubuf, u32 log_size) { struct btf_verifier_env *env = NULL; @@ -4306,7 +4306,7 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, btf->data = data; btf->data_size = btf_data_size; - if (copy_from_user(data, btf_data, btf_data_size)) { + if (copy_from_bpfptr(data, btf_data, btf_data_size)) { err = -EFAULT; goto errout; } @@ -5792,12 +5792,12 @@ static int __btf_new_fd(struct btf *btf) return anon_inode_getfd("btf", &btf_fops, btf, O_RDONLY | O_CLOEXEC); } -int btf_new_fd(const union bpf_attr *attr) +int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr) { struct btf *btf; int ret; - btf = btf_parse(u64_to_user_ptr(attr->btf), + btf = btf_parse(make_bpfptr(attr->btf, uattr.is_kernel), attr->btf_size, attr->btf_log_level, u64_to_user_ptr(attr->btf_log_buf), attr->btf_log_size); @@ -6097,3 +6097,65 @@ struct module *btf_try_get_module(const struct btf *btf) return res; } + +BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags) +{ + struct btf *btf; + long ret; + + if (flags) + return -EINVAL; + + if (name_sz <= 1 || name[name_sz - 1]) + return -EINVAL; + + btf = bpf_get_btf_vmlinux(); + if (IS_ERR(btf)) + return PTR_ERR(btf); + + ret = btf_find_by_name_kind(btf, name, kind); + /* ret is never zero, since btf_find_by_name_kind returns + * positive btf_id or negative error. + */ + if (ret < 0) { + struct btf *mod_btf; + int id; + + /* If name is not found in vmlinux's BTF then search in module's BTFs */ + spin_lock_bh(&btf_idr_lock); + idr_for_each_entry(&btf_idr, mod_btf, id) { + if (!btf_is_module(mod_btf)) + continue; + /* linear search could be slow hence unlock/lock + * the IDR to avoiding holding it for too long + */ + btf_get(mod_btf); + spin_unlock_bh(&btf_idr_lock); + ret = btf_find_by_name_kind(mod_btf, name, kind); + if (ret > 0) { + int btf_obj_fd; + + btf_obj_fd = __btf_new_fd(mod_btf); + if (btf_obj_fd < 0) { + btf_put(mod_btf); + return btf_obj_fd; + } + return ret | (((u64)btf_obj_fd) << 32); + } + spin_lock_bh(&btf_idr_lock); + btf_put(mod_btf); + } + spin_unlock_bh(&btf_idr_lock); + } + return ret; +} + +const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { + .func = bpf_btf_find_by_name_kind, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 5e31ee9f7512..034ad93a1ad7 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1392,29 +1392,54 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn) select_insn: goto *jumptable[insn->code]; - /* ALU */ -#define ALU(OPCODE, OP) \ - ALU64_##OPCODE##_X: \ - DST = DST OP SRC; \ - CONT; \ - ALU_##OPCODE##_X: \ - DST = (u32) DST OP (u32) SRC; \ - CONT; \ - ALU64_##OPCODE##_K: \ - DST = DST OP IMM; \ - CONT; \ - ALU_##OPCODE##_K: \ - DST = (u32) DST OP (u32) IMM; \ + /* Explicitly mask the register-based shift amounts with 63 or 31 + * to avoid undefined behavior. Normally this won't affect the + * generated code, for example, in case of native 64 bit archs such + * as x86-64 or arm64, the compiler is optimizing the AND away for + * the interpreter. In case of JITs, each of the JIT backends compiles + * the BPF shift operations to machine instructions which produce + * implementation-defined results in such a case; the resulting + * contents of the register may be arbitrary, but program behaviour + * as a whole remains defined. In other words, in case of JIT backends, + * the AND must /not/ be added to the emitted LSH/RSH/ARSH translation. + */ + /* ALU (shifts) */ +#define SHT(OPCODE, OP) \ + ALU64_##OPCODE##_X: \ + DST = DST OP (SRC & 63); \ + CONT; \ + ALU_##OPCODE##_X: \ + DST = (u32) DST OP ((u32) SRC & 31); \ + CONT; \ + ALU64_##OPCODE##_K: \ + DST = DST OP IMM; \ + CONT; \ + ALU_##OPCODE##_K: \ + DST = (u32) DST OP (u32) IMM; \ + CONT; + /* ALU (rest) */ +#define ALU(OPCODE, OP) \ + ALU64_##OPCODE##_X: \ + DST = DST OP SRC; \ + CONT; \ + ALU_##OPCODE##_X: \ + DST = (u32) DST OP (u32) SRC; \ + CONT; \ + ALU64_##OPCODE##_K: \ + DST = DST OP IMM; \ + CONT; \ + ALU_##OPCODE##_K: \ + DST = (u32) DST OP (u32) IMM; \ CONT; - ALU(ADD, +) ALU(SUB, -) ALU(AND, &) ALU(OR, |) - ALU(LSH, <<) - ALU(RSH, >>) ALU(XOR, ^) ALU(MUL, *) + SHT(LSH, <<) + SHT(RSH, >>) +#undef SHT #undef ALU ALU_NEG: DST = (u32) -DST; @@ -1439,13 +1464,13 @@ select_insn: insn++; CONT; ALU_ARSH_X: - DST = (u64) (u32) (((s32) DST) >> SRC); + DST = (u64) (u32) (((s32) DST) >> (SRC & 31)); CONT; ALU_ARSH_K: DST = (u64) (u32) (((s32) DST) >> IMM); CONT; ALU64_ARSH_X: - (*(s64 *) &DST) >>= SRC; + (*(s64 *) &DST) >>= (SRC & 63); CONT; ALU64_ARSH_K: (*(s64 *) &DST) >>= IMM; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 5dd3e866599a..480e936c54d0 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -74,7 +74,7 @@ struct bpf_cpu_map_entry { struct bpf_cpu_map { struct bpf_map map; /* Below members specific for map type */ - struct bpf_cpu_map_entry **cpu_map; + struct bpf_cpu_map_entry __rcu **cpu_map; }; static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list); @@ -469,7 +469,7 @@ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, { struct bpf_cpu_map_entry *old_rcpu; - old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu); + old_rcpu = unrcu_pointer(xchg(&cmap->cpu_map[key_cpu], RCU_INITIALIZER(rcpu))); if (old_rcpu) { call_rcu(&old_rcpu->rcu, __cpu_map_entry_free); INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop); @@ -551,7 +551,7 @@ static void cpu_map_free(struct bpf_map *map) for (i = 0; i < cmap->map.max_entries; i++) { struct bpf_cpu_map_entry *rcpu; - rcpu = READ_ONCE(cmap->cpu_map[i]); + rcpu = rcu_dereference_raw(cmap->cpu_map[i]); if (!rcpu) continue; @@ -562,6 +562,10 @@ static void cpu_map_free(struct bpf_map *map) kfree(cmap); } +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. + */ static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); @@ -570,7 +574,8 @@ static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) if (key >= map->max_entries) return NULL; - rcpu = READ_ONCE(cmap->cpu_map[key]); + rcpu = rcu_dereference_check(cmap->cpu_map[key], + rcu_read_lock_bh_held()); return rcpu; } @@ -601,7 +606,8 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, __cpu_map_lookup_elem); + return __bpf_xdp_redirect_map(map, ifindex, flags, 0, + __cpu_map_lookup_elem); } static int cpu_map_btf_id; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index aa516472ce46..2546dafd6672 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -57,6 +57,7 @@ struct xdp_dev_bulk_queue { struct list_head flush_node; struct net_device *dev; struct net_device *dev_rx; + struct bpf_prog *xdp_prog; unsigned int count; }; @@ -72,7 +73,7 @@ struct bpf_dtab_netdev { struct bpf_dtab { struct bpf_map map; - struct bpf_dtab_netdev **netdev_map; /* DEVMAP type only */ + struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */ struct list_head list; /* these are only used for DEVMAP_HASH type maps */ @@ -92,7 +93,7 @@ static struct hlist_head *dev_map_create_hash(unsigned int entries, int i; struct hlist_head *hash; - hash = bpf_map_area_alloc(entries * sizeof(*hash), numa_node); + hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node); if (hash != NULL) for (i = 0; i < entries; i++) INIT_HLIST_HEAD(&hash[i]); @@ -143,7 +144,7 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) spin_lock_init(&dtab->index_lock); } else { - dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries * + dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) @@ -197,6 +198,7 @@ static void dev_map_free(struct bpf_map *map) list_del_rcu(&dtab->list); spin_unlock(&dev_map_lock); + bpf_clear_redirect_map(map); synchronize_rcu(); /* Make sure prior __dev_map_entry_free() have completed. */ @@ -224,7 +226,7 @@ static void dev_map_free(struct bpf_map *map) for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev; - dev = dtab->netdev_map[i]; + dev = rcu_dereference_raw(dtab->netdev_map[i]); if (!dev) continue; @@ -257,6 +259,10 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. + */ static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); @@ -326,22 +332,69 @@ bool dev_map_can_have_prog(struct bpf_map *map) return false; } +static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, + struct xdp_frame **frames, int n, + struct net_device *dev) +{ + struct xdp_txq_info txq = { .dev = dev }; + struct xdp_buff xdp; + int i, nframes = 0; + + for (i = 0; i < n; i++) { + struct xdp_frame *xdpf = frames[i]; + u32 act; + int err; + + xdp_convert_frame_to_buff(xdpf, &xdp); + xdp.txq = &txq; + + act = bpf_prog_run_xdp(xdp_prog, &xdp); + switch (act) { + case XDP_PASS: + err = xdp_update_frame_from_buff(&xdp, xdpf); + if (unlikely(err < 0)) + xdp_return_frame_rx_napi(xdpf); + else + frames[nframes++] = xdpf; + break; + default: + bpf_warn_invalid_xdp_action(act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(dev, xdp_prog, act); + fallthrough; + case XDP_DROP: + xdp_return_frame_rx_napi(xdpf); + break; + } + } + return nframes; /* sent frames count */ +} + static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { struct net_device *dev = bq->dev; + unsigned int cnt = bq->count; int sent = 0, err = 0; + int to_send = cnt; int i; - if (unlikely(!bq->count)) + if (unlikely(!cnt)) return; - for (i = 0; i < bq->count; i++) { + for (i = 0; i < cnt; i++) { struct xdp_frame *xdpf = bq->q[i]; prefetch(xdpf); } - sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags); + if (bq->xdp_prog) { + to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev); + if (!to_send) + goto out; + } + + sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags); if (sent < 0) { /* If ndo_xdp_xmit fails with an errno, no frames have * been xmit'ed. @@ -353,37 +406,34 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) /* If not all frames have been transmitted, it is our * responsibility to free them */ - for (i = sent; unlikely(i < bq->count); i++) + for (i = sent; unlikely(i < to_send); i++) xdp_return_frame_rx_napi(bq->q[i]); - trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, bq->count - sent, err); - bq->dev_rx = NULL; +out: bq->count = 0; - __list_del_clearprev(&bq->flush_node); + trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err); } -/* __dev_flush is called from xdp_do_flush() which _must_ be signaled - * from the driver before returning from its napi->poll() routine. The poll() - * routine is called either from busy_poll context or net_rx_action signaled - * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the - * net device can be torn down. On devmap tear down we ensure the flush list - * is empty before completing to ensure all flush operations have completed. - * When drivers update the bpf program they may need to ensure any flush ops - * are also complete. Using synchronize_rcu or call_rcu will suffice for this - * because both wait for napi context to exit. +/* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the + * driver before returning from its napi->poll() routine. See the comment above + * xdp_do_flush() in filter.c. */ void __dev_flush(void) { struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); struct xdp_dev_bulk_queue *bq, *tmp; - list_for_each_entry_safe(bq, tmp, flush_list, flush_node) + list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { bq_xmit_all(bq, XDP_XMIT_FLUSH); + bq->dev_rx = NULL; + bq->xdp_prog = NULL; + __list_del_clearprev(&bq->flush_node); + } } -/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or - * update happens in parallel here a dev_put wont happen until after reading the - * ifindex. +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. */ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { @@ -393,15 +443,17 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) if (key >= map->max_entries) return NULL; - obj = READ_ONCE(dtab->netdev_map[key]); + obj = rcu_dereference_check(dtab->netdev_map[key], + rcu_read_lock_bh_held()); return obj; } -/* Runs under RCU-read-side, plus in softirq under NAPI protection. - * Thus, safe percpu variable access. +/* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu + * variable access, and map elements stick around. See comment above + * xdp_do_flush() in filter.c. */ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, - struct net_device *dev_rx) + struct net_device *dev_rx, struct bpf_prog *xdp_prog) { struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); @@ -412,18 +464,22 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed * from net_device drivers NAPI func end. + * + * Do the same with xdp_prog and flush_list since these fields + * are only ever modified together. */ - if (!bq->dev_rx) + if (!bq->dev_rx) { bq->dev_rx = dev_rx; + bq->xdp_prog = xdp_prog; + list_add(&bq->flush_node, flush_list); + } bq->q[bq->count++] = xdpf; - - if (!bq->flush_node.prev) - list_add(&bq->flush_node, flush_list); } static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, - struct net_device *dev_rx) + struct net_device *dev_rx, + struct bpf_prog *xdp_prog) { struct xdp_frame *xdpf; int err; @@ -439,42 +495,14 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, if (unlikely(!xdpf)) return -EOVERFLOW; - bq_enqueue(dev, xdpf, dev_rx); + bq_enqueue(dev, xdpf, dev_rx, xdp_prog); return 0; } -static struct xdp_buff *dev_map_run_prog(struct net_device *dev, - struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) -{ - struct xdp_txq_info txq = { .dev = dev }; - u32 act; - - xdp_set_data_meta_invalid(xdp); - xdp->txq = &txq; - - act = bpf_prog_run_xdp(xdp_prog, xdp); - switch (act) { - case XDP_PASS: - return xdp; - case XDP_DROP: - break; - default: - bpf_warn_invalid_xdp_action(act); - fallthrough; - case XDP_ABORTED: - trace_xdp_exception(dev, xdp_prog, act); - break; - } - - xdp_return_buff(xdp); - return NULL; -} - int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, struct net_device *dev_rx) { - return __xdp_enqueue(dev, xdp, dev_rx); + return __xdp_enqueue(dev, xdp, dev_rx, NULL); } int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, @@ -482,12 +510,100 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, { struct net_device *dev = dst->dev; - if (dst->xdp_prog) { - xdp = dev_map_run_prog(dev, xdp, dst->xdp_prog); - if (!xdp) - return 0; + return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog); +} + +static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp, + int exclude_ifindex) +{ + if (!obj || obj->dev->ifindex == exclude_ifindex || + !obj->dev->netdev_ops->ndo_xdp_xmit) + return false; + + if (xdp_ok_fwd_dev(obj->dev, xdp->data_end - xdp->data)) + return false; + + return true; +} + +static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj, + struct net_device *dev_rx, + struct xdp_frame *xdpf) +{ + struct xdp_frame *nxdpf; + + nxdpf = xdpf_clone(xdpf); + if (!nxdpf) + return -ENOMEM; + + bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog); + + return 0; +} + +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, + struct bpf_map *map, bool exclude_ingress) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + int exclude_ifindex = exclude_ingress ? dev_rx->ifindex : 0; + struct bpf_dtab_netdev *dst, *last_dst = NULL; + struct hlist_head *head; + struct xdp_frame *xdpf; + unsigned int i; + int err; + + xdpf = xdp_convert_buff_to_frame(xdp); + if (unlikely(!xdpf)) + return -EOVERFLOW; + + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + for (i = 0; i < map->max_entries; i++) { + dst = READ_ONCE(dtab->netdev_map[i]); + if (!is_valid_dst(dst, xdp, exclude_ifindex)) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); + if (err) + return err; + + last_dst = dst; + } + } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ + for (i = 0; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + hlist_for_each_entry_rcu(dst, head, index_hlist, + lockdep_is_held(&dtab->index_lock)) { + if (!is_valid_dst(dst, xdp, exclude_ifindex)) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); + if (err) + return err; + + last_dst = dst; + } + } } - return __xdp_enqueue(dev, xdp, dev_rx); + + /* consume the last copy of the frame */ + if (last_dst) + bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog); + else + xdp_return_frame_rx_napi(xdpf); /* dtab is empty */ + + return 0; } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, @@ -504,6 +620,87 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, return 0; } +static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, + struct sk_buff *skb, + struct bpf_prog *xdp_prog) +{ + struct sk_buff *nskb; + int err; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return -ENOMEM; + + err = dev_map_generic_redirect(dst, nskb, xdp_prog); + if (unlikely(err)) { + consume_skb(nskb); + return err; + } + + return 0; +} + +int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog, struct bpf_map *map, + bool exclude_ingress) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + int exclude_ifindex = exclude_ingress ? dev->ifindex : 0; + struct bpf_dtab_netdev *dst, *last_dst = NULL; + struct hlist_head *head; + struct hlist_node *next; + unsigned int i; + int err; + + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + for (i = 0; i < map->max_entries; i++) { + dst = READ_ONCE(dtab->netdev_map[i]); + if (!dst || dst->dev->ifindex == exclude_ifindex) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_redirect_clone(last_dst, skb, xdp_prog); + if (err) + return err; + + last_dst = dst; + } + } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ + for (i = 0; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + hlist_for_each_entry_safe(dst, next, head, index_hlist) { + if (!dst || dst->dev->ifindex == exclude_ifindex) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_redirect_clone(last_dst, skb, xdp_prog); + if (err) + return err; + + last_dst = dst; + } + } + } + + /* consume the first skb and return */ + if (last_dst) + return dev_map_generic_redirect(last_dst, skb, xdp_prog); + + /* dtab is empty */ + consume_skb(skb); + return 0; +} + static void *dev_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); @@ -538,14 +735,7 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) if (k >= map->max_entries) return -EINVAL; - /* Use call_rcu() here to ensure any rcu critical sections have - * completed as well as any flush operations because call_rcu - * will wait for preempt-disable region to complete, NAPI in this - * context. And additionally, the driver tear down ensures all - * soft irqs are complete before removing the net device in the - * case of dev_put equals zero. - */ - old_dev = xchg(&dtab->netdev_map[k], NULL); + old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; @@ -654,7 +844,7 @@ static int __dev_map_update_elem(struct net *net, struct bpf_map *map, * Remembering the driver side flush operation will happen before the * net device is removed. */ - old_dev = xchg(&dtab->netdev_map[i], dev); + old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev))); if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); @@ -730,12 +920,16 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, static int dev_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_lookup_elem); + return __bpf_xdp_redirect_map(map, ifindex, flags, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, + __dev_map_lookup_elem); } static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, __dev_map_hash_lookup_elem); + return __bpf_xdp_redirect_map(map, ifindex, flags, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, + __dev_map_hash_lookup_elem); } static int dev_map_btf_id; @@ -830,10 +1024,10 @@ static int dev_map_notification(struct notifier_block *notifier, for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; - dev = READ_ONCE(dtab->netdev_map[i]); + dev = rcu_dereference(dtab->netdev_map[i]); if (!dev || netdev != dev->dev) continue; - odev = cmpxchg(&dtab->netdev_map[i], dev, NULL); + odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); if (dev == odev) call_rcu(&dev->rcu, __dev_map_entry_free); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index d7ebb12ffffc..72c58cc516a3 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -46,12 +46,12 @@ * events, kprobes and tracing to be invoked before the prior invocation * from one of these contexts completed. sys_bpf() uses the same mechanism * by pinning the task to the current CPU and incrementing the recursion - * protection accross the map operation. + * protection across the map operation. * * This has subtle implications on PREEMPT_RT. PREEMPT_RT forbids certain * operations like memory allocations (even with GFP_ATOMIC) from atomic * contexts. This is required because even with GFP_ATOMIC the memory - * allocator calls into code pathes which acquire locks with long held lock + * allocator calls into code paths which acquire locks with long held lock * sections. To ensure the deterministic behaviour these locks are regular * spinlocks, which are converted to 'sleepable' spinlocks on RT. The only * true atomic contexts on an RT kernel are the low level hardware @@ -596,7 +596,8 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) struct htab_elem *l; u32 hash, key_size; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -989,7 +990,8 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, /* unknown flags */ return -EINVAL; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -1082,7 +1084,8 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, /* unknown flags */ return -EINVAL; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -1148,7 +1151,8 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, /* unknown flags */ return -EINVAL; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -1202,7 +1206,8 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, /* unknown flags */ return -EINVAL; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -1276,7 +1281,8 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) u32 hash, key_size; int ret; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -1311,7 +1317,8 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) u32 hash, key_size; int ret; - WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held() && + !rcu_read_lock_bh_held()); key_size = map->key_size; @@ -1401,6 +1408,100 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } +static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, + void *value, bool is_lru_map, + bool is_percpu, u64 flags) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + struct hlist_nulls_head *head; + unsigned long bflags; + struct htab_elem *l; + u32 hash, key_size; + struct bucket *b; + int ret; + + key_size = map->key_size; + + hash = htab_map_hash(key, key_size, htab->hashrnd); + b = __select_bucket(htab, hash); + head = &b->head; + + ret = htab_lock_bucket(htab, b, hash, &bflags); + if (ret) + return ret; + + l = lookup_elem_raw(head, hash, key, key_size); + if (!l) { + ret = -ENOENT; + } else { + if (is_percpu) { + u32 roundup_value_size = round_up(map->value_size, 8); + void __percpu *pptr; + int off = 0, cpu; + + pptr = htab_elem_get_ptr(l, key_size); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(value + off, + per_cpu_ptr(pptr, cpu), + roundup_value_size); + off += roundup_value_size; + } + } else { + u32 roundup_key_size = round_up(map->key_size, 8); + + if (flags & BPF_F_LOCK) + copy_map_value_locked(map, value, l->key + + roundup_key_size, + true); + else + copy_map_value(map, value, l->key + + roundup_key_size); + check_and_init_map_lock(map, value); + } + + hlist_nulls_del_rcu(&l->hash_node); + if (!is_lru_map) + free_htab_elem(htab, l); + } + + htab_unlock_bucket(htab, b, hash, bflags); + + if (is_lru_map && l) + bpf_lru_push_free(&htab->lru, &l->lru_node); + + return ret; +} + +static int htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return __htab_map_lookup_and_delete_elem(map, key, value, false, false, + flags); +} + +static int htab_percpu_map_lookup_and_delete_elem(struct bpf_map *map, + void *key, void *value, + u64 flags) +{ + return __htab_map_lookup_and_delete_elem(map, key, value, false, true, + flags); +} + +static int htab_lru_map_lookup_and_delete_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return __htab_map_lookup_and_delete_elem(map, key, value, true, false, + flags); +} + +static int htab_lru_percpu_map_lookup_and_delete_elem(struct bpf_map *map, + void *key, void *value, + u64 flags) +{ + return __htab_map_lookup_and_delete_elem(map, key, value, true, true, + flags); +} + static int __htab_map_lookup_and_delete_batch(struct bpf_map *map, const union bpf_attr *attr, @@ -1934,6 +2035,7 @@ const struct bpf_map_ops htab_map_ops = { .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_map_lookup_elem, + .map_lookup_and_delete_elem = htab_map_lookup_and_delete_elem, .map_update_elem = htab_map_update_elem, .map_delete_elem = htab_map_delete_elem, .map_gen_lookup = htab_map_gen_lookup, @@ -1954,6 +2056,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_lru_map_lookup_elem, + .map_lookup_and_delete_elem = htab_lru_map_lookup_and_delete_elem, .map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys, .map_update_elem = htab_lru_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, @@ -2077,6 +2180,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_percpu_map_lookup_elem, + .map_lookup_and_delete_elem = htab_percpu_map_lookup_and_delete_elem, .map_update_elem = htab_percpu_map_update_elem, .map_delete_elem = htab_map_delete_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, @@ -2096,6 +2200,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_lru_percpu_map_lookup_elem, + .map_lookup_and_delete_elem = htab_lru_percpu_map_lookup_and_delete_elem, .map_update_elem = htab_lru_percpu_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a2f1f15ce432..62cf00383910 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -29,7 +29,7 @@ */ BPF_CALL_2(bpf_map_lookup_elem, struct bpf_map *, map, void *, key) { - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); return (unsigned long) map->ops->map_lookup_elem(map, key); } @@ -45,7 +45,7 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto = { BPF_CALL_4(bpf_map_update_elem, struct bpf_map *, map, void *, key, void *, value, u64, flags) { - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); return map->ops->map_update_elem(map, key, value, flags); } @@ -62,7 +62,7 @@ const struct bpf_func_proto bpf_map_update_elem_proto = { BPF_CALL_2(bpf_map_delete_elem, struct bpf_map *, map, void *, key) { - WARN_ON_ONCE(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); return map->ops->map_delete_elem(map, key); } diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 1b7b8a6f34ee..423549d2c52e 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -232,7 +232,8 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) /* Start walking the trie from the root node ... */ - for (node = rcu_dereference(trie->root); node;) { + for (node = rcu_dereference_check(trie->root, rcu_read_lock_bh_held()); + node;) { unsigned int next_bit; size_t matchlen; @@ -264,7 +265,8 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) * traverse down. */ next_bit = extract_bit(key->data, node->prefixlen); - node = rcu_dereference(node->child[next_bit]); + node = rcu_dereference_check(node->child[next_bit], + rcu_read_lock_bh_held()); } if (!found) diff --git a/kernel/bpf/preload/iterators/iterators.bpf.c b/kernel/bpf/preload/iterators/iterators.bpf.c index 52aa7b38e8b8..03af863314ea 100644 --- a/kernel/bpf/preload/iterators/iterators.bpf.c +++ b/kernel/bpf/preload/iterators/iterators.bpf.c @@ -2,7 +2,6 @@ /* Copyright (c) 2020 Facebook */ #include #include -#include #include #pragma clang attribute push (__attribute__((preserve_access_index)), apply_to = record) diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 4838922f723d..93a55391791a 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -102,7 +102,7 @@ static void reuseport_array_free(struct bpf_map *map) /* * ops->map_*_elem() will not be able to access this * array now. Hence, this function only races with - * bpf_sk_reuseport_detach() which was triggerred by + * bpf_sk_reuseport_detach() which was triggered by * close() or disconnect(). * * This function and bpf_sk_reuseport_detach() are diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 84b3b35fc0d0..9e0c10c6892a 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #define RINGBUF_CREATE_FLAG_MASK (BPF_F_NUMA_NODE) @@ -105,6 +106,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages, VM_ALLOC | VM_USERMAP, PAGE_KERNEL); if (rb) { + kmemleak_not_leak(pages); rb->pages = pages; rb->nr_pages = nr_pages; return rb; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ea04b0deb5ce..e343f158e556 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -73,11 +73,10 @@ static const struct bpf_map_ops * const bpf_map_types[] = { * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ -int bpf_check_uarg_tail_zero(void __user *uaddr, +int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size) { - unsigned char __user *addr = uaddr + expected_size; int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ @@ -86,7 +85,12 @@ int bpf_check_uarg_tail_zero(void __user *uaddr, if (actual_size <= expected_size) return 0; - res = check_zeroed_user(addr, actual_size - expected_size); + if (uaddr.is_kernel) + res = memchr_inv(uaddr.kernel + expected_size, 0, + actual_size - expected_size) == NULL; + else + res = check_zeroed_user(uaddr.user + expected_size, + actual_size - expected_size); if (res < 0) return res; return res ? 0 : -E2BIG; @@ -1005,6 +1009,17 @@ static void *__bpf_copy_key(void __user *ukey, u64 key_size) return NULL; } +static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size) +{ + if (key_size) + return memdup_bpfptr(ukey, key_size); + + if (!bpfptr_is_null(ukey)) + return ERR_PTR(-EINVAL); + + return NULL; +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags @@ -1075,10 +1090,10 @@ err_put: #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags -static int map_update_elem(union bpf_attr *attr) +static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) { - void __user *ukey = u64_to_user_ptr(attr->key); - void __user *uvalue = u64_to_user_ptr(attr->value); + bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); + bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel); int ufd = attr->map_fd; struct bpf_map *map; void *key, *value; @@ -1104,7 +1119,7 @@ static int map_update_elem(union bpf_attr *attr) goto err_put; } - key = __bpf_copy_key(ukey, map->key_size); + key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -1124,7 +1139,7 @@ static int map_update_elem(union bpf_attr *attr) goto free_key; err = -EFAULT; - if (copy_from_user(value, uvalue, value_size) != 0) + if (copy_from_bpfptr(value, uvalue, value_size) != 0) goto free_value; err = bpf_map_update_value(map, f, key, value, attr->flags); @@ -1469,7 +1484,7 @@ free_buf: return err; } -#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value +#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags static int map_lookup_and_delete_elem(union bpf_attr *attr) { @@ -1485,6 +1500,9 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) return -EINVAL; + if (attr->flags & ~BPF_F_LOCK) + return -EINVAL; + f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) @@ -1495,24 +1513,47 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) goto err_put; } + if (attr->flags && + (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK)) { + err = -EINVAL; + goto err_put; + } + + if ((attr->flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + err = -EINVAL; + goto err_put; + } + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } - value_size = map->value_size; + value_size = bpf_map_value_size(map); err = -ENOMEM; value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; + err = -ENOTSUPP; if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK) { err = map->ops->map_pop_elem(map, value); - } else { - err = -ENOTSUPP; + } else if (map->map_type == BPF_MAP_TYPE_HASH || + map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + if (!bpf_map_is_dev_bound(map)) { + bpf_disable_instrumentation(); + rcu_read_lock(); + err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags); + rcu_read_unlock(); + bpf_enable_instrumentation(); + } } if (err) @@ -1932,6 +1973,11 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) attr->expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; break; + case BPF_PROG_TYPE_SK_REUSEPORT: + if (!attr->expected_attach_type) + attr->expected_attach_type = + BPF_SK_REUSEPORT_SELECT; + break; } } @@ -2015,6 +2061,15 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, if (expected_attach_type == BPF_SK_LOOKUP) return 0; return -EINVAL; + case BPF_PROG_TYPE_SK_REUSEPORT: + switch (expected_attach_type) { + case BPF_SK_REUSEPORT_SELECT: + case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: + return 0; + default: + return -EINVAL; + } + case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: if (expected_attach_type) return -EINVAL; @@ -2074,9 +2129,9 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD attach_prog_fd +#define BPF_PROG_LOAD_LAST_FIELD fd_array -static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) +static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; @@ -2101,8 +2156,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) return -EPERM; /* copy eBPF program license from user space */ - if (strncpy_from_user(license, u64_to_user_ptr(attr->license), - sizeof(license) - 1) < 0) + if (strncpy_from_bpfptr(license, + make_bpfptr(attr->license, uattr.is_kernel), + sizeof(license) - 1) < 0) return -EFAULT; license[sizeof(license) - 1] = 0; @@ -2186,8 +2242,9 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) prog->len = attr->insn_cnt; err = -EFAULT; - if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns), - bpf_prog_insn_size(prog)) != 0) + if (copy_from_bpfptr(prog->insns, + make_bpfptr(attr->insns, uattr.is_kernel), + bpf_prog_insn_size(prog)) != 0) goto free_prog_sec; prog->orig_prog = NULL; @@ -3423,7 +3480,7 @@ static int bpf_prog_get_info_by_fd(struct file *file, u32 ulen; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -3702,7 +3759,7 @@ static int bpf_map_get_info_by_fd(struct file *file, u32 info_len = attr->info.info_len; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -3745,7 +3802,7 @@ static int bpf_btf_get_info_by_fd(struct file *file, u32 info_len = attr->info.info_len; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(*uinfo), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len); if (err) return err; @@ -3762,7 +3819,7 @@ static int bpf_link_get_info_by_fd(struct file *file, u32 info_len = attr->info.info_len; int err; - err = bpf_check_uarg_tail_zero(uinfo, sizeof(info), info_len); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); @@ -3825,7 +3882,7 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, #define BPF_BTF_LOAD_LAST_FIELD btf_log_level -static int bpf_btf_load(const union bpf_attr *attr) +static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr) { if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; @@ -3833,7 +3890,7 @@ static int bpf_btf_load(const union bpf_attr *attr) if (!bpf_capable()) return -EPERM; - return btf_new_fd(attr); + return btf_new_fd(attr, uattr); } #define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id @@ -4023,13 +4080,14 @@ err_put: return err; } -static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +static int tracing_bpf_link_attach(const union bpf_attr *attr, bpfptr_t uattr, + struct bpf_prog *prog) { if (attr->link_create.attach_type != prog->expected_attach_type) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_ITER) - return bpf_iter_link_attach(attr, prog); + return bpf_iter_link_attach(attr, uattr, prog); else if (prog->type == BPF_PROG_TYPE_EXT) return bpf_tracing_prog_attach(prog, attr->link_create.target_fd, @@ -4038,7 +4096,7 @@ static int tracing_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog * } #define BPF_LINK_CREATE_LAST_FIELD link_create.iter_info_len -static int link_create(union bpf_attr *attr) +static int link_create(union bpf_attr *attr, bpfptr_t uattr) { enum bpf_prog_type ptype; struct bpf_prog *prog; @@ -4057,7 +4115,7 @@ static int link_create(union bpf_attr *attr) goto out; if (prog->type == BPF_PROG_TYPE_EXT) { - ret = tracing_bpf_link_attach(attr, prog); + ret = tracing_bpf_link_attach(attr, uattr, prog); goto out; } @@ -4078,7 +4136,7 @@ static int link_create(union bpf_attr *attr) ret = cgroup_bpf_link_attach(attr, prog); break; case BPF_PROG_TYPE_TRACING: - ret = tracing_bpf_link_attach(attr, prog); + ret = tracing_bpf_link_attach(attr, uattr, prog); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_SK_LOOKUP: @@ -4366,7 +4424,7 @@ out_prog_put: return ret; } -SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) +static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; int err; @@ -4381,7 +4439,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz /* copy attributes from user space, may be less than sizeof(bpf_attr) */ memset(&attr, 0, sizeof(attr)); - if (copy_from_user(&attr, uattr, size) != 0) + if (copy_from_bpfptr(&attr, uattr, size) != 0) return -EFAULT; err = security_bpf(cmd, &attr, size); @@ -4396,7 +4454,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = map_lookup_elem(&attr); break; case BPF_MAP_UPDATE_ELEM: - err = map_update_elem(&attr); + err = map_update_elem(&attr, uattr); break; case BPF_MAP_DELETE_ELEM: err = map_delete_elem(&attr); @@ -4423,21 +4481,21 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_prog_detach(&attr); break; case BPF_PROG_QUERY: - err = bpf_prog_query(&attr, uattr); + err = bpf_prog_query(&attr, uattr.user); break; case BPF_PROG_TEST_RUN: - err = bpf_prog_test_run(&attr, uattr); + err = bpf_prog_test_run(&attr, uattr.user); break; case BPF_PROG_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &prog_idr, &prog_idr_lock); break; case BPF_MAP_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &map_idr, &map_idr_lock); break; case BPF_BTF_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &btf_idr, &btf_idr_lock); break; case BPF_PROG_GET_FD_BY_ID: @@ -4447,38 +4505,38 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_map_get_fd_by_id(&attr); break; case BPF_OBJ_GET_INFO_BY_FD: - err = bpf_obj_get_info_by_fd(&attr, uattr); + err = bpf_obj_get_info_by_fd(&attr, uattr.user); break; case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); break; case BPF_BTF_LOAD: - err = bpf_btf_load(&attr); + err = bpf_btf_load(&attr, uattr); break; case BPF_BTF_GET_FD_BY_ID: err = bpf_btf_get_fd_by_id(&attr); break; case BPF_TASK_FD_QUERY: - err = bpf_task_fd_query(&attr, uattr); + err = bpf_task_fd_query(&attr, uattr.user); break; case BPF_MAP_LOOKUP_AND_DELETE_ELEM: err = map_lookup_and_delete_elem(&attr); break; case BPF_MAP_LOOKUP_BATCH: - err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH); + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_BATCH); break; case BPF_MAP_LOOKUP_AND_DELETE_BATCH: - err = bpf_map_do_batch(&attr, uattr, + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_AND_DELETE_BATCH); break; case BPF_MAP_UPDATE_BATCH: - err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH); + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_UPDATE_BATCH); break; case BPF_MAP_DELETE_BATCH: - err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH); + err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_DELETE_BATCH); break; case BPF_LINK_CREATE: - err = link_create(&attr); + err = link_create(&attr, uattr); break; case BPF_LINK_UPDATE: err = link_update(&attr); @@ -4487,7 +4545,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz err = bpf_link_get_fd_by_id(&attr); break; case BPF_LINK_GET_NEXT_ID: - err = bpf_obj_get_next_id(&attr, uattr, + err = bpf_obj_get_next_id(&attr, uattr.user, &link_idr, &link_idr_lock); break; case BPF_ENABLE_STATS: @@ -4509,3 +4567,94 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz return err; } + +SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) +{ + return __sys_bpf(cmd, USER_BPFPTR(uattr), size); +} + +static bool syscall_prog_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (off < 0 || off >= U16_MAX) + return false; + if (off % size != 0) + return false; + return true; +} + +BPF_CALL_3(bpf_sys_bpf, int, cmd, void *, attr, u32, attr_size) +{ + switch (cmd) { + case BPF_MAP_CREATE: + case BPF_MAP_UPDATE_ELEM: + case BPF_MAP_FREEZE: + case BPF_PROG_LOAD: + case BPF_BTF_LOAD: + break; + /* case BPF_PROG_TEST_RUN: + * is not part of this list to prevent recursive test_run + */ + default: + return -EINVAL; + } + return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size); +} + +static const struct bpf_func_proto bpf_sys_bpf_proto = { + .func = bpf_sys_bpf, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + +const struct bpf_func_proto * __weak +tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return bpf_base_func_proto(func_id); +} + +BPF_CALL_1(bpf_sys_close, u32, fd) +{ + /* When bpf program calls this helper there should not be + * an fdget() without matching completed fdput(). + * This helper is allowed in the following callchain only: + * sys_bpf->prog_test_run->bpf_prog->bpf_sys_close + */ + return close_fd(fd); +} + +static const struct bpf_func_proto bpf_sys_close_proto = { + .func = bpf_sys_close, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + +static const struct bpf_func_proto * +syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_sys_bpf: + return &bpf_sys_bpf_proto; + case BPF_FUNC_btf_find_by_name_kind: + return &bpf_btf_find_by_name_kind_proto; + case BPF_FUNC_sys_close: + return &bpf_sys_close_proto; + default: + return tracing_prog_func_proto(func_id, prog); + } +} + +const struct bpf_verifier_ops bpf_syscall_verifier_ops = { + .get_func_proto = syscall_prog_func_proto, + .is_valid_access = syscall_prog_is_valid_access, +}; + +const struct bpf_prog_ops bpf_syscall_prog_ops = { + .test_run = bpf_prog_test_run_syscall, +}; diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index ceac5281bd31..3d7127f439a1 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -111,28 +111,31 @@ struct tnum tnum_xor(struct tnum a, struct tnum b) return TNUM(v & ~mu, mu); } -/* half-multiply add: acc += (unknown * mask * value). - * An intermediate step in the multiply algorithm. +/* Generate partial products by multiplying each bit in the multiplier (tnum a) + * with the multiplicand (tnum b), and add the partial products after + * appropriately bit-shifting them. Instead of directly performing tnum addition + * on the generated partial products, equivalenty, decompose each partial + * product into two tnums, consisting of the value-sum (acc_v) and the + * mask-sum (acc_m) and then perform tnum addition on them. The following paper + * explains the algorithm in more detail: https://arxiv.org/abs/2105.05398. */ -static struct tnum hma(struct tnum acc, u64 value, u64 mask) -{ - while (mask) { - if (mask & 1) - acc = tnum_add(acc, TNUM(0, value)); - mask >>= 1; - value <<= 1; - } - return acc; -} - struct tnum tnum_mul(struct tnum a, struct tnum b) { - struct tnum acc; - u64 pi; + u64 acc_v = a.value * b.value; + struct tnum acc_m = TNUM(0, 0); - pi = a.value * b.value; - acc = hma(TNUM(pi, 0), a.mask, b.mask | b.value); - return hma(acc, b.mask, a.value); + while (a.value || a.mask) { + /* LSB of tnum a is a certain 1 */ + if (a.value & 1) + acc_m = tnum_add(acc_m, TNUM(0, b.mask)); + /* LSB of tnum a is uncertain */ + else if (a.mask & 1) + acc_m = tnum_add(acc_m, TNUM(0, b.value | b.mask)); + /* Note: no case for LSB is certain 0 */ + a = tnum_rshift(a, 1); + b = tnum_lshift(b, 1); + } + return tnum_add(TNUM(acc_v, 0), acc_m); } /* Note that if a and b disagree - i.e. one has a 'known 1' where the other has diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 2d44b5aa0057..28a3630c48ee 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -552,7 +552,7 @@ static void notrace inc_misses_counter(struct bpf_prog *prog) * __bpf_prog_enter returns: * 0 - skip execution of the bpf prog * 1 - execute bpf prog - * [2..MAX_U64] - excute bpf prog and record execution time. + * [2..MAX_U64] - execute bpf prog and record execution time. * This is start time. */ u64 notrace __bpf_prog_enter(struct bpf_prog *prog) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c6a27574242d..be38bb930bf1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -47,7 +47,7 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * - unreachable insns exist (shouldn't be a forest. program = one function) * - out of bounds or malformed jumps * The second pass is all possible path descent from the 1st insn. - * Since it's analyzing all pathes through the program, the length of the + * Since it's analyzing all paths through the program, the length of the * analysis is limited to 64k insn, which may be hit even if total number of * insn is less then 4K, but there are too many branches that change stack/regs. * Number of 'branches to be analyzed' is limited to 1k @@ -132,7 +132,7 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * If it's ok, then verifier allows this BPF_CALL insn and looks at * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function - * returns ether pointer to map value or NULL. + * returns either pointer to map value or NULL. * * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off' * insn, the register holding that pointer in the true branch changes state to @@ -737,81 +737,104 @@ static void print_verifier_state(struct bpf_verifier_env *env, verbose(env, "\n"); } -#define COPY_STATE_FN(NAME, COUNT, FIELD, SIZE) \ -static int copy_##NAME##_state(struct bpf_func_state *dst, \ - const struct bpf_func_state *src) \ -{ \ - if (!src->FIELD) \ - return 0; \ - if (WARN_ON_ONCE(dst->COUNT < src->COUNT)) { \ - /* internal bug, make state invalid to reject the program */ \ - memset(dst, 0, sizeof(*dst)); \ - return -EFAULT; \ - } \ - memcpy(dst->FIELD, src->FIELD, \ - sizeof(*src->FIELD) * (src->COUNT / SIZE)); \ - return 0; \ -} -/* copy_reference_state() */ -COPY_STATE_FN(reference, acquired_refs, refs, 1) -/* copy_stack_state() */ -COPY_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) -#undef COPY_STATE_FN - -#define REALLOC_STATE_FN(NAME, COUNT, FIELD, SIZE) \ -static int realloc_##NAME##_state(struct bpf_func_state *state, int size, \ - bool copy_old) \ -{ \ - u32 old_size = state->COUNT; \ - struct bpf_##NAME##_state *new_##FIELD; \ - int slot = size / SIZE; \ - \ - if (size <= old_size || !size) { \ - if (copy_old) \ - return 0; \ - state->COUNT = slot * SIZE; \ - if (!size && old_size) { \ - kfree(state->FIELD); \ - state->FIELD = NULL; \ - } \ - return 0; \ - } \ - new_##FIELD = kmalloc_array(slot, sizeof(struct bpf_##NAME##_state), \ - GFP_KERNEL); \ - if (!new_##FIELD) \ - return -ENOMEM; \ - if (copy_old) { \ - if (state->FIELD) \ - memcpy(new_##FIELD, state->FIELD, \ - sizeof(*new_##FIELD) * (old_size / SIZE)); \ - memset(new_##FIELD + old_size / SIZE, 0, \ - sizeof(*new_##FIELD) * (size - old_size) / SIZE); \ - } \ - state->COUNT = slot * SIZE; \ - kfree(state->FIELD); \ - state->FIELD = new_##FIELD; \ - return 0; \ -} -/* realloc_reference_state() */ -REALLOC_STATE_FN(reference, acquired_refs, refs, 1) -/* realloc_stack_state() */ -REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) -#undef REALLOC_STATE_FN - -/* do_check() starts with zero-sized stack in struct bpf_verifier_state to - * make it consume minimal amount of memory. check_stack_write() access from - * the program calls into realloc_func_state() to grow the stack size. - * Note there is a non-zero 'parent' pointer inside bpf_verifier_state - * which realloc_stack_state() copies over. It points to previous - * bpf_verifier_state which is never reallocated. +/* copy array src of length n * size bytes to dst. dst is reallocated if it's too + * small to hold src. This is different from krealloc since we don't want to preserve + * the contents of dst. + * + * Leaves dst untouched if src is NULL or length is zero. Returns NULL if memory could + * not be allocated. */ -static int realloc_func_state(struct bpf_func_state *state, int stack_size, - int refs_size, bool copy_old) +static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags) { - int err = realloc_reference_state(state, refs_size, copy_old); - if (err) - return err; - return realloc_stack_state(state, stack_size, copy_old); + size_t bytes; + + if (ZERO_OR_NULL_PTR(src)) + goto out; + + if (unlikely(check_mul_overflow(n, size, &bytes))) + return NULL; + + if (ksize(dst) < bytes) { + kfree(dst); + dst = kmalloc_track_caller(bytes, flags); + if (!dst) + return NULL; + } + + memcpy(dst, src, bytes); +out: + return dst ? dst : ZERO_SIZE_PTR; +} + +/* resize an array from old_n items to new_n items. the array is reallocated if it's too + * small to hold new_n items. new items are zeroed out if the array grows. + * + * Contrary to krealloc_array, does not free arr if new_n is zero. + */ +static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size) +{ + if (!new_n || old_n == new_n) + goto out; + + arr = krealloc_array(arr, new_n, size, GFP_KERNEL); + if (!arr) + return NULL; + + if (new_n > old_n) + memset(arr + old_n * size, 0, (new_n - old_n) * size); + +out: + return arr ? arr : ZERO_SIZE_PTR; +} + +static int copy_reference_state(struct bpf_func_state *dst, const struct bpf_func_state *src) +{ + dst->refs = copy_array(dst->refs, src->refs, src->acquired_refs, + sizeof(struct bpf_reference_state), GFP_KERNEL); + if (!dst->refs) + return -ENOMEM; + + dst->acquired_refs = src->acquired_refs; + return 0; +} + +static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_state *src) +{ + size_t n = src->allocated_stack / BPF_REG_SIZE; + + dst->stack = copy_array(dst->stack, src->stack, n, sizeof(struct bpf_stack_state), + GFP_KERNEL); + if (!dst->stack) + return -ENOMEM; + + dst->allocated_stack = src->allocated_stack; + return 0; +} + +static int resize_reference_state(struct bpf_func_state *state, size_t n) +{ + state->refs = realloc_array(state->refs, state->acquired_refs, n, + sizeof(struct bpf_reference_state)); + if (!state->refs) + return -ENOMEM; + + state->acquired_refs = n; + return 0; +} + +static int grow_stack_state(struct bpf_func_state *state, int size) +{ + size_t old_n = state->allocated_stack / BPF_REG_SIZE, n = size / BPF_REG_SIZE; + + if (old_n >= n) + return 0; + + state->stack = realloc_array(state->stack, old_n, n, sizeof(struct bpf_stack_state)); + if (!state->stack) + return -ENOMEM; + + state->allocated_stack = size; + return 0; } /* Acquire a pointer id from the env and update the state->refs to include @@ -825,7 +848,7 @@ static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) int new_ofs = state->acquired_refs; int id, err; - err = realloc_reference_state(state, state->acquired_refs + 1, true); + err = resize_reference_state(state, state->acquired_refs + 1); if (err) return err; id = ++env->id_gen; @@ -854,18 +877,6 @@ static int release_reference_state(struct bpf_func_state *state, int ptr_id) return -EINVAL; } -static int transfer_reference_state(struct bpf_func_state *dst, - struct bpf_func_state *src) -{ - int err = realloc_reference_state(dst, src->acquired_refs, false); - if (err) - return err; - err = copy_reference_state(dst, src); - if (err) - return err; - return 0; -} - static void free_func_state(struct bpf_func_state *state) { if (!state) @@ -904,10 +915,6 @@ static int copy_func_state(struct bpf_func_state *dst, { int err; - err = realloc_func_state(dst, src->allocated_stack, src->acquired_refs, - false); - if (err) - return err; memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs)); err = copy_reference_state(dst, src); if (err) @@ -919,16 +926,13 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, const struct bpf_verifier_state *src) { struct bpf_func_state *dst; - u32 jmp_sz = sizeof(struct bpf_idx_pair) * src->jmp_history_cnt; int i, err; - if (dst_state->jmp_history_cnt < src->jmp_history_cnt) { - kfree(dst_state->jmp_history); - dst_state->jmp_history = kmalloc(jmp_sz, GFP_USER); - if (!dst_state->jmp_history) - return -ENOMEM; - } - memcpy(dst_state->jmp_history, src->jmp_history, jmp_sz); + dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history, + src->jmp_history_cnt, sizeof(struct bpf_idx_pair), + GFP_USER); + if (!dst_state->jmp_history) + return -ENOMEM; dst_state->jmp_history_cnt = src->jmp_history_cnt; /* if dst has more stack frames then src frame, free them */ @@ -2590,8 +2594,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, u32 dst_reg = env->prog->insnsi[insn_idx].dst_reg; struct bpf_reg_state *reg = NULL; - err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE), - state->acquired_refs, true); + err = grow_stack_state(state, round_up(slot + 1, BPF_REG_SIZE)); if (err) return err; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, @@ -2613,7 +2616,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, if (dst_reg != BPF_REG_FP) { /* The backtracking logic can only recognize explicit * stack slot address like [fp - 8]. Other spill of - * scalar via different register has to be conervative. + * scalar via different register has to be conservative. * Backtrack from here and mark all registers as precise * that contributed into 'reg' being a constant. */ @@ -2753,8 +2756,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, if (value_reg && register_is_null(value_reg)) writing_zero = true; - err = realloc_func_state(state, round_up(-min_off, BPF_REG_SIZE), - state->acquired_refs, true); + err = grow_stack_state(state, round_up(-min_off, BPF_REG_SIZE)); if (err) return err; @@ -5629,7 +5631,7 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn subprog /* subprog number within this prog */); /* Transfer references to the callee */ - err = transfer_reference_state(callee, caller); + err = copy_reference_state(callee, caller); if (err) return err; @@ -5780,7 +5782,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) } /* Transfer references to the caller */ - err = transfer_reference_state(caller, callee); + err = copy_reference_state(caller, callee); if (err) return err; @@ -8968,12 +8970,14 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) mark_reg_known_zero(env, regs, insn->dst_reg); dst_reg->map_ptr = map; - if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) { + if (insn->src_reg == BPF_PSEUDO_MAP_VALUE || + insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { dst_reg->type = PTR_TO_MAP_VALUE; dst_reg->off = aux->map_off; if (map_value_has_spin_lock(map)) dst_reg->id = ++env->id_gen; - } else if (insn->src_reg == BPF_PSEUDO_MAP_FD) { + } else if (insn->src_reg == BPF_PSEUDO_MAP_FD || + insn->src_reg == BPF_PSEUDO_MAP_IDX) { dst_reg->type = CONST_PTR_TO_MAP; } else { verbose(env, "bpf verifier is misconfigured\n"); @@ -9104,7 +9108,7 @@ static int check_return_code(struct bpf_verifier_env *env) !prog->aux->attach_func_proto->type) return 0; - /* eBPF calling convetion is such that R0 is used + /* eBPF calling convention is such that R0 is used * to return the value from eBPF program. * Make sure that it's readable at this time * of bpf_exit, which means that program wrote @@ -9489,7 +9493,7 @@ static int check_abnormal_return(struct bpf_verifier_env *env) static int check_btf_func(struct bpf_verifier_env *env, const union bpf_attr *attr, - union bpf_attr __user *uattr) + bpfptr_t uattr) { const struct btf_type *type, *func_proto, *ret_type; u32 i, nfuncs, urec_size, min_size; @@ -9498,7 +9502,7 @@ static int check_btf_func(struct bpf_verifier_env *env, struct bpf_func_info_aux *info_aux = NULL; struct bpf_prog *prog; const struct btf *btf; - void __user *urecord; + bpfptr_t urecord; u32 prev_offset = 0; bool scalar_return; int ret = -ENOMEM; @@ -9526,7 +9530,7 @@ static int check_btf_func(struct bpf_verifier_env *env, prog = env->prog; btf = prog->aux->btf; - urecord = u64_to_user_ptr(attr->func_info); + urecord = make_bpfptr(attr->func_info, uattr.is_kernel); min_size = min_t(u32, krec_size, urec_size); krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN); @@ -9544,13 +9548,15 @@ static int check_btf_func(struct bpf_verifier_env *env, /* set the size kernel expects so loader can zero * out the rest of the record. */ - if (put_user(min_size, &uattr->func_info_rec_size)) + if (copy_to_bpfptr_offset(uattr, + offsetof(union bpf_attr, func_info_rec_size), + &min_size, sizeof(min_size))) ret = -EFAULT; } goto err_free; } - if (copy_from_user(&krecord[i], urecord, min_size)) { + if (copy_from_bpfptr(&krecord[i], urecord, min_size)) { ret = -EFAULT; goto err_free; } @@ -9602,7 +9608,7 @@ static int check_btf_func(struct bpf_verifier_env *env, } prev_offset = krecord[i].insn_off; - urecord += urec_size; + bpfptr_add(&urecord, urec_size); } prog->aux->func_info = krecord; @@ -9634,14 +9640,14 @@ static void adjust_btf_func(struct bpf_verifier_env *env) static int check_btf_line(struct bpf_verifier_env *env, const union bpf_attr *attr, - union bpf_attr __user *uattr) + bpfptr_t uattr) { u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0; struct bpf_subprog_info *sub; struct bpf_line_info *linfo; struct bpf_prog *prog; const struct btf *btf; - void __user *ulinfo; + bpfptr_t ulinfo; int err; nr_linfo = attr->line_info_cnt; @@ -9667,7 +9673,7 @@ static int check_btf_line(struct bpf_verifier_env *env, s = 0; sub = env->subprog_info; - ulinfo = u64_to_user_ptr(attr->line_info); + ulinfo = make_bpfptr(attr->line_info, uattr.is_kernel); expected_size = sizeof(struct bpf_line_info); ncopy = min_t(u32, expected_size, rec_size); for (i = 0; i < nr_linfo; i++) { @@ -9675,14 +9681,15 @@ static int check_btf_line(struct bpf_verifier_env *env, if (err) { if (err == -E2BIG) { verbose(env, "nonzero tailing record in line_info"); - if (put_user(expected_size, - &uattr->line_info_rec_size)) + if (copy_to_bpfptr_offset(uattr, + offsetof(union bpf_attr, line_info_rec_size), + &expected_size, sizeof(expected_size))) err = -EFAULT; } goto err_free; } - if (copy_from_user(&linfo[i], ulinfo, ncopy)) { + if (copy_from_bpfptr(&linfo[i], ulinfo, ncopy)) { err = -EFAULT; goto err_free; } @@ -9734,7 +9741,7 @@ static int check_btf_line(struct bpf_verifier_env *env, } prev_offset = linfo[i].insn_off; - ulinfo += rec_size; + bpfptr_add(&ulinfo, rec_size); } if (s != env->subprog_cnt) { @@ -9756,7 +9763,7 @@ err_free: static int check_btf_info(struct bpf_verifier_env *env, const union bpf_attr *attr, - union bpf_attr __user *uattr) + bpfptr_t uattr) { struct btf *btf; int err; @@ -9801,13 +9808,6 @@ static bool range_within(struct bpf_reg_state *old, old->s32_max_value >= cur->s32_max_value; } -/* Maximum number of register states that can exist at once */ -#define ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) -struct idpair { - u32 old; - u32 cur; -}; - /* If in the old state two registers had the same id, then they need to have * the same id in the new state as well. But that id could be different from * the old state, so we need to track the mapping from old to new ids. @@ -9818,11 +9818,11 @@ struct idpair { * So we look through our idmap to see if this old id has been seen before. If * so, we require the new id to match; otherwise, we add the id pair to the map. */ -static bool check_ids(u32 old_id, u32 cur_id, struct idpair *idmap) +static bool check_ids(u32 old_id, u32 cur_id, struct bpf_id_pair *idmap) { unsigned int i; - for (i = 0; i < ID_MAP_SIZE; i++) { + for (i = 0; i < BPF_ID_MAP_SIZE; i++) { if (!idmap[i].old) { /* Reached an empty slot; haven't seen this id before */ idmap[i].old = old_id; @@ -9899,7 +9899,7 @@ static void clean_verifier_state(struct bpf_verifier_env *env, * Since the verifier pushes the branch states as it sees them while exploring * the program the condition of walking the branch instruction for the second * time means that all states below this branch were already explored and - * their final liveness markes are already propagated. + * their final liveness marks are already propagated. * Hence when the verifier completes the search of state list in is_state_visited() * we can call this clean_live_states() function to mark all liveness states * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state' @@ -9935,7 +9935,7 @@ next: /* Returns true if (rold safe implies rcur safe) */ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, - struct idpair *idmap) + struct bpf_id_pair *idmap) { bool equal; @@ -10053,7 +10053,7 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, static bool stacksafe(struct bpf_func_state *old, struct bpf_func_state *cur, - struct idpair *idmap) + struct bpf_id_pair *idmap) { int i, spi; @@ -10150,32 +10150,23 @@ static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur) * whereas register type in current state is meaningful, it means that * the current state will reach 'bpf_exit' instruction safely */ -static bool func_states_equal(struct bpf_func_state *old, +static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old, struct bpf_func_state *cur) { - struct idpair *idmap; - bool ret = false; int i; - idmap = kcalloc(ID_MAP_SIZE, sizeof(struct idpair), GFP_KERNEL); - /* If we failed to allocate the idmap, just say it's not safe */ - if (!idmap) + memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch)); + for (i = 0; i < MAX_BPF_REG; i++) + if (!regsafe(&old->regs[i], &cur->regs[i], env->idmap_scratch)) + return false; + + if (!stacksafe(old, cur, env->idmap_scratch)) return false; - for (i = 0; i < MAX_BPF_REG; i++) { - if (!regsafe(&old->regs[i], &cur->regs[i], idmap)) - goto out_free; - } - - if (!stacksafe(old, cur, idmap)) - goto out_free; - if (!refsafe(old, cur)) - goto out_free; - ret = true; -out_free: - kfree(idmap); - return ret; + return false; + + return true; } static bool states_equal(struct bpf_verifier_env *env, @@ -10202,7 +10193,7 @@ static bool states_equal(struct bpf_verifier_env *env, for (i = 0; i <= old->curframe; i++) { if (old->frame[i]->callsite != cur->frame[i]->callsite) return false; - if (!func_states_equal(old->frame[i], cur->frame[i])) + if (!func_states_equal(env, old->frame[i], cur->frame[i])) return false; } return true; @@ -11239,6 +11230,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) struct bpf_map *map; struct fd f; u64 addr; + u32 fd; if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || @@ -11268,16 +11260,38 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) /* In final convert_pseudo_ld_imm64() step, this is * converted into regular 64-bit imm load insn. */ - if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD && - insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) || - (insn[0].src_reg == BPF_PSEUDO_MAP_FD && - insn[1].imm != 0)) { - verbose(env, - "unrecognized bpf_ld_imm64 insn\n"); + switch (insn[0].src_reg) { + case BPF_PSEUDO_MAP_VALUE: + case BPF_PSEUDO_MAP_IDX_VALUE: + break; + case BPF_PSEUDO_MAP_FD: + case BPF_PSEUDO_MAP_IDX: + if (insn[1].imm == 0) + break; + fallthrough; + default: + verbose(env, "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } - f = fdget(insn[0].imm); + switch (insn[0].src_reg) { + case BPF_PSEUDO_MAP_IDX_VALUE: + case BPF_PSEUDO_MAP_IDX: + if (bpfptr_is_null(env->fd_array)) { + verbose(env, "fd_idx without fd_array is invalid\n"); + return -EPROTO; + } + if (copy_from_bpfptr_offset(&fd, env->fd_array, + insn[0].imm * sizeof(fd), + sizeof(fd))) + return -EFAULT; + break; + default: + fd = insn[0].imm; + break; + } + + f = fdget(fd); map = __bpf_map_get(f); if (IS_ERR(map)) { verbose(env, "fd %d is not pointing to valid bpf_map\n", @@ -11292,7 +11306,8 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) } aux = &env->insn_aux_data[i]; - if (insn->src_reg == BPF_PSEUDO_MAP_FD) { + if (insn[0].src_reg == BPF_PSEUDO_MAP_FD || + insn[0].src_reg == BPF_PSEUDO_MAP_IDX) { addr = (unsigned long)map; } else { u32 off = insn[1].imm; @@ -11459,7 +11474,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len } } -static void adjust_poke_descs(struct bpf_prog *prog, u32 len) +static void adjust_poke_descs(struct bpf_prog *prog, u32 off, u32 len) { struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab; int i, sz = prog->aux->size_poke_tab; @@ -11467,6 +11482,8 @@ static void adjust_poke_descs(struct bpf_prog *prog, u32 len) for (i = 0; i < sz; i++) { desc = &tab[i]; + if (desc->insn_idx <= off) + continue; desc->insn_idx += len - 1; } } @@ -11487,7 +11504,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of if (adjust_insn_aux_data(env, new_prog, off, len)) return NULL; adjust_subprog_starts(env, off, len); - adjust_poke_descs(new_prog, len); + adjust_poke_descs(new_prog, off, len); return new_prog; } @@ -12506,7 +12523,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) prog->aux->max_pkt_offset = MAX_PACKET_OFF; /* mark bpf_tail_call as different opcode to avoid - * conditional branch in the interpeter for every normal + * conditional branch in the interpreter for every normal * call and to prevent accidental JITing by JIT compiler * that doesn't support bpf_tail_call yet */ @@ -13281,6 +13298,14 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) int ret; u64 key; + if (prog->type == BPF_PROG_TYPE_SYSCALL) { + if (prog->aux->sleepable) + /* attach_btf_id checked to be zero already */ + return 0; + verbose(env, "Syscall programs can only be sleepable\n"); + return -EINVAL; + } + if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM) { verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n"); @@ -13355,8 +13380,7 @@ struct btf *bpf_get_btf_vmlinux(void) return btf_vmlinux; } -int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, - union bpf_attr __user *uattr) +int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) { u64 start_time = ktime_get_ns(); struct bpf_verifier_env *env; @@ -13386,6 +13410,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, env->insn_aux_data[i].orig_idx = i; env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; + env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); is_priv = bpf_capable(); bpf_get_btf_vmlinux(); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index a446e7e5aaf9..d99c71a52246 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -596,6 +596,7 @@ out_unlock: rcu_read_unlock(); return css; } +EXPORT_SYMBOL_GPL(cgroup_get_e_css); static void cgroup_get_live(struct cgroup *cgrp) { diff --git a/kernel/cpu.c b/kernel/cpu.c index 5128fccdd5b7..6bdbebc15186 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include @@ -874,6 +875,52 @@ void __init cpuhp_threads_init(void) kthread_unpark(this_cpu_read(cpuhp_state.thread)); } +/* + * + * Serialize hotplug trainwrecks outside of the cpu_hotplug_lock + * protected region. + * + * The operation is still serialized against concurrent CPU hotplug via + * cpu_add_remove_lock, i.e. CPU map protection. But it is _not_ + * serialized against other hotplug related activity like adding or + * removing of state callbacks and state instances, which invoke either the + * startup or the teardown callback of the affected state. + * + * This is required for subsystems which are unfixable vs. CPU hotplug and + * evade lock inversion problems by scheduling work which has to be + * completed _before_ cpu_up()/_cpu_down() returns. + * + * Don't even think about adding anything to this for any new code or even + * drivers. It's only purpose is to keep existing lock order trainwrecks + * working. + * + * For cpu_down() there might be valid reasons to finish cleanups which are + * not required to be done under cpu_hotplug_lock, but that's a different + * story and would be not invoked via this. + */ +static void cpu_up_down_serialize_trainwrecks(bool tasks_frozen) +{ + /* + * cpusets delegate hotplug operations to a worker to "solve" the + * lock order problems. Wait for the worker, but only if tasks are + * _not_ frozen (suspend, hibernate) as that would wait forever. + * + * The wait is required because otherwise the hotplug operation + * returns with inconsistent state, which could even be observed in + * user space when a new CPU is brought up. The CPU plug uevent + * would be delivered and user space reacting on it would fail to + * move tasks to the newly plugged CPU up to the point where the + * work has finished because up to that point the newly plugged CPU + * is not assignable in cpusets/cgroups. On unplug that's not + * necessarily a visible issue, but it is still inconsistent state, + * which is the real problem which needs to be "fixed". This can't + * prevent the transient state between scheduling the work and + * returning from waiting for it. + */ + if (!tasks_frozen) + cpuset_wait_for_hotplug(); +} + #ifdef CONFIG_HOTPLUG_CPU #ifndef arch_clear_mm_cpumask_cpu #define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) @@ -962,7 +1009,7 @@ static int takedown_cpu(unsigned int cpu) int err; /* Park the smpboot threads */ - kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread); + kthread_park(st->thread); /* * Prevent irq alloc/free while the dying cpu reorganizes the @@ -978,7 +1025,7 @@ static int takedown_cpu(unsigned int cpu) /* CPU refused to die */ irq_unlock_sparse(); /* Unpark the hotplug thread so we can rollback there */ - kthread_unpark(per_cpu_ptr(&cpuhp_state, cpu)->thread); + kthread_unpark(st->thread); return err; } BUG_ON(cpu_online(cpu)); @@ -1109,6 +1156,7 @@ out: */ lockup_detector_cleanup(); arch_smt_update(); + cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } @@ -1322,6 +1370,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) out: cpus_write_unlock(); arch_smt_update(); + cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 684a6061a13a..da449c1cdca7 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -455,7 +455,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_SYMBOL(_stext); VMCOREINFO_SYMBOL(vmap_area_list); -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA VMCOREINFO_SYMBOL(mem_map); VMCOREINFO_SYMBOL(contig_page_data); #endif @@ -484,7 +484,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(page, compound_head); VMCOREINFO_OFFSET(pglist_data, node_zones); VMCOREINFO_OFFSET(pglist_data, nr_zones); -#ifdef CONFIG_FLAT_NODE_MEM_MAP +#ifdef CONFIG_FLATMEM VMCOREINFO_OFFSET(pglist_data, node_mem_map); #endif VMCOREINFO_OFFSET(pglist_data, node_start_pfn); diff --git a/kernel/cred.c b/kernel/cred.c index e1d274cd741b..e6fd2b3fc31f 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -60,6 +60,7 @@ struct cred init_cred = { .user = INIT_USER, .user_ns = &init_user_ns, .group_info = &init_groups, + .ucounts = &init_ucounts, }; static inline void set_cred_subscribers(struct cred *cred, int n) @@ -119,6 +120,8 @@ static void put_cred_rcu(struct rcu_head *rcu) if (cred->group_info) put_group_info(cred->group_info); free_uid(cred->user); + if (cred->ucounts) + put_ucounts(cred->ucounts); put_user_ns(cred->user_ns); kmem_cache_free(cred_jar, cred); } @@ -222,6 +225,7 @@ struct cred *cred_alloc_blank(void) #ifdef CONFIG_DEBUG_CREDENTIALS new->magic = CRED_MAGIC; #endif + new->ucounts = get_ucounts(&init_ucounts); if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; @@ -284,6 +288,11 @@ struct cred *prepare_creds(void) if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; + + new->ucounts = get_ucounts(new->ucounts); + if (!new->ucounts) + goto error; + validate_creds(new); return new; @@ -351,7 +360,7 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) kdebug("share_creds(%p{%d,%d})", p->cred, atomic_read(&p->cred->usage), read_cred_subscribers(p->cred)); - atomic_inc(&p->cred->user->processes); + inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); return 0; } @@ -363,6 +372,9 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) ret = create_user_ns(new); if (ret < 0) goto error_put; + ret = set_cred_ucounts(new); + if (ret < 0) + goto error_put; } #ifdef CONFIG_KEYS @@ -384,8 +396,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) } #endif - atomic_inc(&new->user->processes); p->cred = p->real_cred = get_cred(new); + inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); alter_cred_subscribers(new, 2); validate_creds(new); return 0; @@ -485,12 +497,12 @@ int commit_creds(struct cred *new) * in set_user(). */ alter_cred_subscribers(new, 2); - if (new->user != old->user) - atomic_inc(&new->user->processes); + if (new->user != old->user || new->user_ns != old->user_ns) + inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1); rcu_assign_pointer(task->real_cred, new); rcu_assign_pointer(task->cred, new); if (new->user != old->user) - atomic_dec(&old->user->processes); + dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1); alter_cred_subscribers(old, -2); /* send notifications */ @@ -653,6 +665,31 @@ int cred_fscmp(const struct cred *a, const struct cred *b) } EXPORT_SYMBOL(cred_fscmp); +int set_cred_ucounts(struct cred *new) +{ + struct task_struct *task = current; + const struct cred *old = task->real_cred; + struct ucounts *old_ucounts = new->ucounts; + + if (new->user == old->user && new->user_ns == old->user_ns) + return 0; + + /* + * This optimization is needed because alloc_ucounts() uses locks + * for table lookups. + */ + if (old_ucounts && old_ucounts->ns == new->user_ns && uid_eq(old_ucounts->uid, new->euid)) + return 0; + + if (!(new->ucounts = alloc_ucounts(new->user_ns, new->euid))) + return -EAGAIN; + + if (old_ucounts) + put_ucounts(old_ucounts); + + return 0; +} + /* * initialise the credentials stuff */ @@ -719,6 +756,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; + new->ucounts = get_ucounts(new->ucounts); + if (!new->ucounts) + goto error; + put_cred(old); validate_creds(new); return new; diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 1baa96a2ecb8..622410c45da1 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2488,7 +2488,6 @@ static void kdb_sysinfo(struct sysinfo *val) static int kdb_summary(int argc, const char **argv) { time64_t now; - struct tm tm; struct sysinfo val; if (argc) @@ -2502,13 +2501,7 @@ static int kdb_summary(int argc, const char **argv) kdb_printf("domainname %s\n", init_uts_ns.name.domainname); now = __ktime_get_real_seconds(); - time64_to_tm(now, 0, &tm); - kdb_printf("date %04ld-%02d-%02d %02d:%02d:%02d " - "tz_minuteswest %d\n", - 1900+tm.tm_year, tm.tm_mon+1, tm.tm_mday, - tm.tm_hour, tm.tm_min, tm.tm_sec, - sys_tz.tz_minuteswest); - + kdb_printf("date %ptTs tz_minuteswest %d\n", &now, sys_tz.tz_minuteswest); kdb_sysinfo(&val); kdb_printf("uptime "); if (val.uptime > (24*60*60)) { diff --git a/kernel/events/core.c b/kernel/events/core.c index b28cf21b1df5..c43ffdd68c59 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8310,8 +8310,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) if (vma->vm_flags & VM_DENYWRITE) flags |= MAP_DENYWRITE; - if (vma->vm_flags & VM_MAYEXEC) - flags |= MAP_EXECUTABLE; if (vma->vm_flags & VM_LOCKED) flags |= MAP_LOCKED; if (is_vm_hugetlb_page(vma)) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index a481ef696143..af24dc3febbe 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -2047,8 +2047,8 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) struct vm_area_struct *vma; mmap_read_lock(mm); - vma = find_vma(mm, bp_vaddr); - if (vma && vma->vm_start <= bp_vaddr) { + vma = vma_lookup(mm, bp_vaddr); + if (vma) { if (valid_vma(vma, false)) { struct inode *inode = file_inode(vma->vm_file); loff_t offset = vaddr_to_offset(vma, bp_vaddr); diff --git a/kernel/exit.c b/kernel/exit.c index 65809fac3038..9a89e7f36acb 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -188,7 +188,7 @@ repeat: /* don't need to get the RCU readlock here - the process is dead and * can't be modifying its own credentials. But shut RCU-lockdep up */ rcu_read_lock(); - atomic_dec(&__task_cred(p)->user->processes); + dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); rcu_read_unlock(); cgroup_release(p); diff --git a/kernel/fork.c b/kernel/fork.c index fe538ce7cfb6..100a5ce6959c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -830,9 +830,14 @@ void __init fork_init(void) init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; - for (i = 0; i < UCOUNT_COUNTS; i++) + for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; + set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, task_rlimit(&init_task, RLIMIT_NPROC)); + set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, task_rlimit(&init_task, RLIMIT_MSGQUEUE)); + set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, task_rlimit(&init_task, RLIMIT_SIGPENDING)); + set_rlimit_ucount_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, task_rlimit(&init_task, RLIMIT_MEMLOCK)); + #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", NULL, free_vm_stack_cache); @@ -1035,7 +1040,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; - atomic_set(&mm->has_pinned, 0); atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); @@ -1985,8 +1989,7 @@ static __latent_entropy struct task_struct *copy_process( DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = -EAGAIN; - if (atomic_read(&p->real_cred->user->processes) >= - task_rlimit(p, RLIMIT_NPROC)) { + if (is_ucounts_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_free; @@ -2395,7 +2398,7 @@ bad_fork_cleanup_threadgroup_lock: #endif delayacct_tsk_free(p); bad_fork_cleanup_count: - atomic_dec(&p->cred->user->processes); + dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); @@ -3010,6 +3013,12 @@ int ksys_unshare(unsigned long unshare_flags) if (err) goto bad_unshare_cleanup_cred; + if (new_cred) { + err = set_cred_ucounts(new_cred); + if (err) + goto bad_unshare_cleanup_cred; + } + if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index 58f87a3092f3..053447183ac5 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -5,6 +5,7 @@ config GCOV_KERNEL bool "Enable gcov-based kernel profiling" depends on DEBUG_FS depends on !CC_IS_CLANG || CLANG_VERSION >= 110000 + depends on !ARCH_WANTS_NO_INSTR || CC_HAS_NO_PROFILE_FN_ATTR select CONSTRUCTORS default n help diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index d79ef2493a28..fbc54c2a7f23 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -70,6 +70,11 @@ config IRQ_DOMAIN_HIERARCHY bool select IRQ_DOMAIN +# Support for obsolete non-mapping irq domains +config IRQ_DOMAIN_NOMAP + bool + select IRQ_DOMAIN + # Support for hierarchical fasteoi+edge and fasteoi+level handlers config IRQ_FASTEOI_HIERARCHY_HANDLERS bool diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 1d48bae8f84c..055ecb10447b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -482,7 +482,7 @@ void handle_nested_irq(unsigned int irq) for_each_action_of_desc(desc, action) action_ret |= action->thread_fn(action->irq, action->dev_id); - if (!noirqdebug) + if (!irq_settings_no_debug(desc)) note_interrupt(desc, action_ret); raw_spin_lock_irq(&desc->lock); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 762a928e18f9..221d80c31e94 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -197,7 +197,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) add_interrupt_randomness(desc->irq_data.irq, flags); - if (!noirqdebug) + if (!irq_settings_no_debug(desc)) note_interrupt(desc, retval); return retval; } diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 4383d16e3068..6db413a3fd15 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -632,14 +632,8 @@ void irq_init_desc(unsigned int irq) #endif /* !CONFIG_SPARSE_IRQ */ -/** - * generic_handle_irq - Invoke the handler for a particular irq - * @irq: The irq number to handle - * - */ -int generic_handle_irq(unsigned int irq) +int handle_irq_desc(struct irq_desc *desc) { - struct irq_desc *desc = irq_to_desc(irq); struct irq_data *data; if (!desc) @@ -652,11 +646,40 @@ int generic_handle_irq(unsigned int irq) generic_handle_irq_desc(desc); return 0; } +EXPORT_SYMBOL_GPL(handle_irq_desc); + +/** + * generic_handle_irq - Invoke the handler for a particular irq + * @irq: The irq number to handle + * + */ +int generic_handle_irq(unsigned int irq) +{ + return handle_irq_desc(irq_to_desc(irq)); +} EXPORT_SYMBOL_GPL(generic_handle_irq); +#ifdef CONFIG_IRQ_DOMAIN +/** + * generic_handle_domain_irq - Invoke the handler for a HW irq belonging + * to a domain, usually for a non-root interrupt + * controller + * @domain: The domain where to perform the lookup + * @hwirq: The HW irq number to convert to a logical one + * + * Returns: 0 on success, or -EINVAL if conversion has failed + * + */ +int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq) +{ + return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); +} +EXPORT_SYMBOL_GPL(generic_handle_domain_irq); + #ifdef CONFIG_HANDLE_DOMAIN_IRQ /** - * __handle_domain_irq - Invoke the handler for a HW irq belonging to a domain + * handle_domain_irq - Invoke the handler for a HW irq belonging to a domain, + * usually for a root interrupt controller * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * @lookup: Whether to perform the domain lookup or not @@ -664,37 +687,27 @@ EXPORT_SYMBOL_GPL(generic_handle_irq); * * Returns: 0 on success, or -EINVAL if conversion has failed */ -int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq, - bool lookup, struct pt_regs *regs) +int handle_domain_irq(struct irq_domain *domain, + unsigned int hwirq, struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - unsigned int irq = hwirq; + struct irq_desc *desc; int ret = 0; irq_enter(); -#ifdef CONFIG_IRQ_DOMAIN - if (lookup) - irq = irq_find_mapping(domain, hwirq); -#endif - - /* - * Some hardware gives randomly wrong interrupts. Rather - * than crashing, do something sensible. - */ - if (unlikely(!irq || irq >= nr_irqs)) { - ack_bad_irq(irq); + /* The irqdomain code provides boundary checks */ + desc = irq_resolve_mapping(domain, hwirq); + if (likely(desc)) + handle_irq_desc(desc); + else ret = -EINVAL; - } else { - generic_handle_irq(irq); - } irq_exit(); set_irq_regs(old_regs); return ret; } -#ifdef CONFIG_IRQ_DOMAIN /** * handle_domain_nmi - Invoke the handler for a HW irq belonging to a domain * @domain: The domain where to perform the lookup @@ -709,7 +722,7 @@ int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq, struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - unsigned int irq; + struct irq_desc *desc; int ret = 0; /* @@ -717,14 +730,14 @@ int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq, */ WARN_ON(!in_nmi()); - irq = irq_find_mapping(domain, hwirq); + desc = irq_resolve_mapping(domain, hwirq); /* * ack_bad_irq is not NMI-safe, just report * an invalid interrupt. */ - if (likely(irq)) - generic_handle_irq(irq); + if (likely(desc)) + handle_irq_desc(desc); else ret = -EINVAL; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 6284443b87ec..51c483ce2447 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -146,7 +146,11 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, static atomic_t unknown_domains; - domain = kzalloc_node(sizeof(*domain) + (sizeof(unsigned int) * size), + if (WARN_ON((size && direct_max) || + (!IS_ENABLED(CONFIG_IRQ_DOMAIN_NOMAP) && direct_max))) + return NULL; + + domain = kzalloc_node(struct_size(domain, revmap, size), GFP_KERNEL, of_node_to_nid(to_of_node(fwnode))); if (!domain) return NULL; @@ -209,12 +213,18 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, /* Fill structure */ INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL); - mutex_init(&domain->revmap_tree_mutex); + mutex_init(&domain->revmap_mutex); domain->ops = ops; domain->host_data = host_data; domain->hwirq_max = hwirq_max; + + if (direct_max) { + size = direct_max; + domain->flags |= IRQ_DOMAIN_FLAG_NO_MAP; + } + domain->revmap_size = size; - domain->revmap_direct_max_irq = direct_max; + irq_domain_check_hierarchy(domain); mutex_lock(&irq_domain_mutex); @@ -482,29 +492,39 @@ struct irq_domain *irq_get_default_host(void) return irq_default_domain; } +static bool irq_domain_is_nomap(struct irq_domain *domain) +{ + return IS_ENABLED(CONFIG_IRQ_DOMAIN_NOMAP) && + (domain->flags & IRQ_DOMAIN_FLAG_NO_MAP); +} + static void irq_domain_clear_mapping(struct irq_domain *domain, irq_hw_number_t hwirq) { - if (hwirq < domain->revmap_size) { - domain->linear_revmap[hwirq] = 0; - } else { - mutex_lock(&domain->revmap_tree_mutex); + if (irq_domain_is_nomap(domain)) + return; + + mutex_lock(&domain->revmap_mutex); + if (hwirq < domain->revmap_size) + rcu_assign_pointer(domain->revmap[hwirq], NULL); + else radix_tree_delete(&domain->revmap_tree, hwirq); - mutex_unlock(&domain->revmap_tree_mutex); - } + mutex_unlock(&domain->revmap_mutex); } static void irq_domain_set_mapping(struct irq_domain *domain, irq_hw_number_t hwirq, struct irq_data *irq_data) { - if (hwirq < domain->revmap_size) { - domain->linear_revmap[hwirq] = irq_data->irq; - } else { - mutex_lock(&domain->revmap_tree_mutex); + if (irq_domain_is_nomap(domain)) + return; + + mutex_lock(&domain->revmap_mutex); + if (hwirq < domain->revmap_size) + rcu_assign_pointer(domain->revmap[hwirq], irq_data); + else radix_tree_insert(&domain->revmap_tree, hwirq, irq_data); - mutex_unlock(&domain->revmap_tree_mutex); - } + mutex_unlock(&domain->revmap_mutex); } static void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) @@ -604,6 +624,7 @@ void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, } EXPORT_SYMBOL_GPL(irq_domain_associate_many); +#ifdef CONFIG_IRQ_DOMAIN_NOMAP /** * irq_create_direct_mapping() - Allocate an irq for direct mapping * @domain: domain to allocate the irq for or NULL for default domain @@ -628,9 +649,9 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain) pr_debug("create_direct virq allocation failed\n"); return 0; } - if (virq >= domain->revmap_direct_max_irq) { + if (virq >= domain->revmap_size) { pr_err("ERROR: no free irqs available below %i maximum\n", - domain->revmap_direct_max_irq); + domain->revmap_size); irq_free_desc(virq); return 0; } @@ -644,6 +665,7 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain) return virq; } EXPORT_SYMBOL_GPL(irq_create_direct_mapping); +#endif /** * irq_create_mapping_affinity() - Map a hardware interrupt into linux irq space @@ -862,37 +884,53 @@ void irq_dispose_mapping(unsigned int virq) EXPORT_SYMBOL_GPL(irq_dispose_mapping); /** - * irq_find_mapping() - Find a linux irq from a hw irq number. + * __irq_resolve_mapping() - Find a linux irq from a hw irq number. * @domain: domain owning this hardware interrupt * @hwirq: hardware irq number in that domain space + * @irq: optional pointer to return the Linux irq if required + * + * Returns the interrupt descriptor. */ -unsigned int irq_find_mapping(struct irq_domain *domain, - irq_hw_number_t hwirq) +struct irq_desc *__irq_resolve_mapping(struct irq_domain *domain, + irq_hw_number_t hwirq, + unsigned int *irq) { + struct irq_desc *desc = NULL; struct irq_data *data; /* Look for default domain if necessary */ if (domain == NULL) domain = irq_default_domain; if (domain == NULL) - return 0; + return desc; - if (hwirq < domain->revmap_direct_max_irq) { - data = irq_domain_get_irq_data(domain, hwirq); - if (data && data->hwirq == hwirq) - return hwirq; + if (irq_domain_is_nomap(domain)) { + if (hwirq < domain->revmap_size) { + data = irq_domain_get_irq_data(domain, hwirq); + if (data && data->hwirq == hwirq) + desc = irq_data_to_desc(data); + } + + return desc; } + rcu_read_lock(); /* Check if the hwirq is in the linear revmap. */ if (hwirq < domain->revmap_size) - return domain->linear_revmap[hwirq]; + data = rcu_dereference(domain->revmap[hwirq]); + else + data = radix_tree_lookup(&domain->revmap_tree, hwirq); + + if (likely(data)) { + desc = irq_data_to_desc(data); + if (irq) + *irq = data->irq; + } - rcu_read_lock(); - data = radix_tree_lookup(&domain->revmap_tree, hwirq); rcu_read_unlock(); - return data ? data->irq : 0; + return desc; } -EXPORT_SYMBOL_GPL(irq_find_mapping); +EXPORT_SYMBOL_GPL(__irq_resolve_mapping); /** * irq_domain_xlate_onecell() - Generic xlate for direct one cell bindings @@ -1468,15 +1506,20 @@ static void irq_domain_fix_revmap(struct irq_data *d) { void __rcu **slot; - if (d->hwirq < d->domain->revmap_size) - return; /* Not using radix tree. */ + if (irq_domain_is_nomap(d->domain)) + return; /* Fix up the revmap. */ - mutex_lock(&d->domain->revmap_tree_mutex); - slot = radix_tree_lookup_slot(&d->domain->revmap_tree, d->hwirq); - if (slot) - radix_tree_replace_slot(&d->domain->revmap_tree, slot, d); - mutex_unlock(&d->domain->revmap_tree_mutex); + mutex_lock(&d->domain->revmap_mutex); + if (d->hwirq < d->domain->revmap_size) { + /* Not using radix tree */ + rcu_assign_pointer(d->domain->revmap[d->hwirq], d); + } else { + slot = radix_tree_lookup_slot(&d->domain->revmap_tree, d->hwirq); + if (slot) + radix_tree_replace_slot(&d->domain->revmap_tree, slot, d); + } + mutex_unlock(&d->domain->revmap_mutex); } /** @@ -1828,8 +1871,7 @@ static void irq_domain_debug_show_one(struct seq_file *m, struct irq_domain *d, int ind) { seq_printf(m, "%*sname: %s\n", ind, "", d->name); - seq_printf(m, "%*ssize: %u\n", ind + 1, "", - d->revmap_size + d->revmap_direct_max_irq); + seq_printf(m, "%*ssize: %u\n", ind + 1, "", d->revmap_size); seq_printf(m, "%*smapped: %u\n", ind + 1, "", d->mapcount); seq_printf(m, "%*sflags: 0x%08x\n", ind +1 , "", d->flags); if (d->ops && d->ops->debug_show) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index a847dd2044c8..ef30b4762947 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1717,8 +1717,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) if (new->flags & IRQF_PERCPU) { irqd_set(&desc->irq_data, IRQD_PER_CPU); irq_settings_set_per_cpu(desc); + if (new->flags & IRQF_NO_DEBUG) + irq_settings_set_no_debug(desc); } + if (noirqdebug) + irq_settings_set_no_debug(desc); + if (new->flags & IRQF_ONESHOT) desc->istate |= IRQS_ONESHOT; diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h index 403378b9947b..7b7efb1a114b 100644 --- a/kernel/irq/settings.h +++ b/kernel/irq/settings.h @@ -18,6 +18,7 @@ enum { _IRQ_IS_POLLED = IRQ_IS_POLLED, _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY, _IRQ_HIDDEN = IRQ_HIDDEN, + _IRQ_NO_DEBUG = IRQ_NO_DEBUG, _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, }; @@ -33,6 +34,7 @@ enum { #define IRQ_IS_POLLED GOT_YOU_MORON #define IRQ_DISABLE_UNLAZY GOT_YOU_MORON #define IRQ_HIDDEN GOT_YOU_MORON +#define IRQ_NO_DEBUG GOT_YOU_MORON #undef IRQF_MODIFY_MASK #define IRQF_MODIFY_MASK GOT_YOU_MORON @@ -174,3 +176,13 @@ static inline bool irq_settings_is_hidden(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_HIDDEN; } + +static inline void irq_settings_set_no_debug(struct irq_desc *desc) +{ + desc->status_use_accessors |= _IRQ_NO_DEBUG; +} + +static inline bool irq_settings_no_debug(struct irq_desc *desc) +{ + return desc->status_use_accessors & _IRQ_NO_DEBUG; +} diff --git a/kernel/kthread.c b/kernel/kthread.c index 5df5330d0d8f..31278089674c 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1163,14 +1163,14 @@ static bool __kthread_cancel_work(struct kthread_work *work) * modify @dwork's timer so that it expires after @delay. If @delay is zero, * @work is guaranteed to be queued immediately. * - * Return: %true if @dwork was pending and its timer was modified, - * %false otherwise. + * Return: %false if @dwork was idle and queued, %true otherwise. * * A special case is when the work is being canceled in parallel. * It might be caused either by the real kthread_cancel_delayed_work_sync() * or yet another kthread_mod_delayed_work() call. We let the other command - * win and return %false here. The caller is supposed to synchronize these - * operations a reasonable way. + * win and return %true here. The return value can be used for reference + * counting and the number of queued works stays the same. Anyway, the caller + * is supposed to synchronize these operations a reasonable way. * * This function is safe to call from any context including IRQ handler. * See __kthread_cancel_work() and kthread_delayed_work_timer_fn() @@ -1182,13 +1182,15 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker, { struct kthread_work *work = &dwork->work; unsigned long flags; - int ret = false; + int ret; raw_spin_lock_irqsave(&worker->lock, flags); /* Do not bother with canceling when never queued. */ - if (!work->worker) + if (!work->worker) { + ret = false; goto fast_queue; + } /* Work must not be used with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker != worker); @@ -1206,8 +1208,11 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker, * be used for reference counting. */ kthread_cancel_delayed_work_timer(work, &flags); - if (work->canceling) + if (work->canceling) { + /* The number of works in the queue does not change. */ + ret = true; goto out; + } ret = __kthread_cancel_work(work); fast_queue: diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 6bfe3ead10ad..a12779650f15 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -98,20 +98,20 @@ config PM_STD_PARTITION default "" help The default resume partition is the partition that the suspend- - to-disk implementation will look for a suspended disk image. + to-disk implementation will look for a suspended disk image. - The partition specified here will be different for almost every user. + The partition specified here will be different for almost every user. It should be a valid swap partition (at least for now) that is turned - on before suspending. + on before suspending. The partition specified can be overridden by specifying: - resume=/dev/ + resume=/dev/ - which will set the resume partition to the device specified. + which will set the resume partition to the device specified. Note there is currently not a way to specify which device to save the - suspended image to. It will simply pick the first available swap + suspended image to. It will simply pick the first available swap device. config PM_SLEEP diff --git a/kernel/power/process.c b/kernel/power/process.c index 8bd2bcc09392..c828dace30d9 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * drivers/power/process.c - Functions for starting/stopping processes on + * drivers/power/process.c - Functions for starting/stopping processes on * suspend transitions. * * Originally from swsusp. diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 1a221dcb3c01..f7a986078213 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -331,7 +331,7 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size) * * Memory bitmap is a structure consisting of many linked lists of * objects. The main list's elements are of type struct zone_bitmap - * and each of them corresonds to one zone. For each zone bitmap + * and each of them corresponds to one zone. For each zone bitmap * object there is a list of objects of type struct bm_block that * represent each blocks of bitmap in which information is stored. * @@ -1146,7 +1146,7 @@ int create_basic_memory_bitmaps(void) Free_second_object: kfree(bm2); Free_first_bitmap: - memory_bm_free(bm1, PG_UNSAFE_CLEAR); + memory_bm_free(bm1, PG_UNSAFE_CLEAR); Free_first_object: kfree(bm1); return -ENOMEM; @@ -1500,7 +1500,7 @@ static struct memory_bitmap copy_bm; /** * swsusp_free - Free pages allocated for hibernation image. * - * Image pages are alocated before snapshot creation, so they need to be + * Image pages are allocated before snapshot creation, so they need to be * released after resume. */ void swsusp_free(void) @@ -2326,7 +2326,7 @@ static struct memory_bitmap *safe_highmem_bm; * (@nr_highmem_p points to the variable containing the number of highmem image * pages). The pages that are "safe" (ie. will not be overwritten when the * hibernation image is restored entirely) have the corresponding bits set in - * @bm (it must be unitialized). + * @bm (it must be uninitialized). * * NOTE: This function should not be called if there are no highmem image pages. */ @@ -2483,7 +2483,7 @@ static inline void free_highmem_data(void) {} /** * prepare_image - Make room for loading hibernation image. - * @new_bm: Unitialized memory bitmap structure. + * @new_bm: Uninitialized memory bitmap structure. * @bm: Memory bitmap with unsafe pages marked. * * Use @bm to mark the pages that will be overwritten in the process of diff --git a/kernel/power/swap.c b/kernel/power/swap.c index bea3cb8afa11..3cb89baebc79 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -1125,7 +1125,7 @@ struct dec_data { }; /** - * Deompression function that runs in its own thread. + * Decompression function that runs in its own thread. */ static int lzo_decompress_threadfn(void *data) { diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index d789ba5fa054..479278f37e26 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3540,3 +3540,119 @@ void kmsg_dump_rewind(struct kmsg_dump_iter *iter) EXPORT_SYMBOL_GPL(kmsg_dump_rewind); #endif + +#ifdef CONFIG_SMP +static atomic_t printk_cpulock_owner = ATOMIC_INIT(-1); +static atomic_t printk_cpulock_nested = ATOMIC_INIT(0); + +/** + * __printk_wait_on_cpu_lock() - Busy wait until the printk cpu-reentrant + * spinning lock is not owned by any CPU. + * + * Context: Any context. + */ +void __printk_wait_on_cpu_lock(void) +{ + do { + cpu_relax(); + } while (atomic_read(&printk_cpulock_owner) != -1); +} +EXPORT_SYMBOL(__printk_wait_on_cpu_lock); + +/** + * __printk_cpu_trylock() - Try to acquire the printk cpu-reentrant + * spinning lock. + * + * If no processor has the lock, the calling processor takes the lock and + * becomes the owner. If the calling processor is already the owner of the + * lock, this function succeeds immediately. + * + * Context: Any context. Expects interrupts to be disabled. + * Return: 1 on success, otherwise 0. + */ +int __printk_cpu_trylock(void) +{ + int cpu; + int old; + + cpu = smp_processor_id(); + + /* + * Guarantee loads and stores from this CPU when it is the lock owner + * are _not_ visible to the previous lock owner. This pairs with + * __printk_cpu_unlock:B. + * + * Memory barrier involvement: + * + * If __printk_cpu_trylock:A reads from __printk_cpu_unlock:B, then + * __printk_cpu_unlock:A can never read from __printk_cpu_trylock:B. + * + * Relies on: + * + * RELEASE from __printk_cpu_unlock:A to __printk_cpu_unlock:B + * of the previous CPU + * matching + * ACQUIRE from __printk_cpu_trylock:A to __printk_cpu_trylock:B + * of this CPU + */ + old = atomic_cmpxchg_acquire(&printk_cpulock_owner, -1, + cpu); /* LMM(__printk_cpu_trylock:A) */ + if (old == -1) { + /* + * This CPU is now the owner and begins loading/storing + * data: LMM(__printk_cpu_trylock:B) + */ + return 1; + + } else if (old == cpu) { + /* This CPU is already the owner. */ + atomic_inc(&printk_cpulock_nested); + return 1; + } + + return 0; +} +EXPORT_SYMBOL(__printk_cpu_trylock); + +/** + * __printk_cpu_unlock() - Release the printk cpu-reentrant spinning lock. + * + * The calling processor must be the owner of the lock. + * + * Context: Any context. Expects interrupts to be disabled. + */ +void __printk_cpu_unlock(void) +{ + if (atomic_read(&printk_cpulock_nested)) { + atomic_dec(&printk_cpulock_nested); + return; + } + + /* + * This CPU is finished loading/storing data: + * LMM(__printk_cpu_unlock:A) + */ + + /* + * Guarantee loads and stores from this CPU when it was the + * lock owner are visible to the next lock owner. This pairs + * with __printk_cpu_trylock:A. + * + * Memory barrier involvement: + * + * If __printk_cpu_trylock:A reads from __printk_cpu_unlock:B, + * then __printk_cpu_trylock:B reads from __printk_cpu_unlock:A. + * + * Relies on: + * + * RELEASE from __printk_cpu_unlock:A to __printk_cpu_unlock:B + * of this CPU + * matching + * ACQUIRE from __printk_cpu_trylock:A to __printk_cpu_trylock:B + * of the next CPU + */ + atomic_set_release(&printk_cpulock_owner, + -1); /* LMM(__printk_cpu_unlock:B) */ +} +EXPORT_SYMBOL(__printk_cpu_unlock); +#endif /* CONFIG_SMP */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index da526e034b5e..e344a3147824 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3688,15 +3688,15 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) r = removed_load; sub_positive(&sa->load_avg, r); - sub_positive(&sa->load_sum, r * divider); + sa->load_sum = sa->load_avg * divider; r = removed_util; sub_positive(&sa->util_avg, r); - sub_positive(&sa->util_sum, r * divider); + sa->util_sum = sa->util_avg * divider; r = removed_runnable; sub_positive(&sa->runnable_avg, r); - sub_positive(&sa->runnable_sum, r * divider); + sa->runnable_sum = sa->runnable_avg * divider; /* * removed_runnable is the unweighted version of removed_load so we diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 3e9e1e109cf2..a5975579a741 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -264,17 +264,22 @@ prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_ent } EXPORT_SYMBOL(prepare_to_wait); -void +/* Returns true if we are the first waiter in the queue, false otherwise. */ +bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state) { unsigned long flags; + bool was_empty = false; wq_entry->flags |= WQ_FLAG_EXCLUSIVE; spin_lock_irqsave(&wq_head->lock, flags); - if (list_empty(&wq_entry->entry)) + if (list_empty(&wq_entry->entry)) { + was_empty = list_empty(&wq_head->head); __add_wait_queue_entry_tail(wq_head, wq_entry); + } set_current_state(state); spin_unlock_irqrestore(&wq_head->lock, flags); + return was_empty; } EXPORT_SYMBOL(prepare_to_wait_exclusive); diff --git a/kernel/signal.c b/kernel/signal.c index 68a371fdf54e..df75640169a0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -412,8 +412,8 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, int override_rlimit, const unsigned int sigqueue_flags) { struct sigqueue *q = NULL; - struct user_struct *user; - int sigpending; + struct ucounts *ucounts = NULL; + long sigpending; /* * Protect access to @t credentials. This can go away when all @@ -424,27 +424,26 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, * changes from/to zero. */ rcu_read_lock(); - user = __task_cred(t)->user; - sigpending = atomic_inc_return(&user->sigpending); + ucounts = task_ucounts(t); + sigpending = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1); if (sigpending == 1) - get_uid(user); + ucounts = get_ucounts(ucounts); rcu_read_unlock(); - if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { + if (override_rlimit || (sigpending < LONG_MAX && sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { q = kmem_cache_alloc(sigqueue_cachep, gfp_flags); } else { print_dropped_signal(sig); } if (unlikely(q == NULL)) { - if (atomic_dec_and_test(&user->sigpending)) - free_uid(user); + if (ucounts && dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1)) + put_ucounts(ucounts); } else { INIT_LIST_HEAD(&q->list); q->flags = sigqueue_flags; - q->user = user; + q->ucounts = ucounts; } - return q; } @@ -452,8 +451,10 @@ static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) return; - if (atomic_dec_and_test(&q->user->sigpending)) - free_uid(q->user); + if (q->ucounts && dec_rlimit_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING, 1)) { + put_ucounts(q->ucounts); + q->ucounts = NULL; + } kmem_cache_free(sigqueue_cachep, q); } diff --git a/kernel/sys.c b/kernel/sys.c index 4db66d26146c..99d31641acf9 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -483,7 +483,7 @@ static int set_user(struct cred *new) * for programs doing set*uid()+execve() by harmlessly deferring the * failure to the execve() stage. */ - if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) && + if (is_ucounts_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) && new_user != INIT_USER) current->flags |= PF_NPROC_EXCEEDED; else @@ -562,6 +562,10 @@ long __sys_setreuid(uid_t ruid, uid_t euid) if (retval < 0) goto error; + retval = set_cred_ucounts(new); + if (retval < 0) + goto error; + return commit_creds(new); error: @@ -620,6 +624,10 @@ long __sys_setuid(uid_t uid) if (retval < 0) goto error; + retval = set_cred_ucounts(new); + if (retval < 0) + goto error; + return commit_creds(new); error: @@ -695,6 +703,10 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) if (retval < 0) goto error; + retval = set_cred_ucounts(new); + if (retval < 0) + goto error; + return commit_creds(new); error: diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 0ea8128468c3..dad4d994641e 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -99,7 +99,7 @@ COND_SYSCALL(flock); /* fs/quota.c */ COND_SYSCALL(quotactl); -COND_SYSCALL(quotactl_path); +COND_SYSCALL(quotactl_fd); /* fs/readdir.c */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b919560d041e..2935fe97db37 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2932,11 +2932,11 @@ static struct ctl_table vm_table[] = { .extra1 = SYSCTL_ZERO, }, { - .procname = "percpu_pagelist_fraction", - .data = &percpu_pagelist_fraction, - .maxlen = sizeof(percpu_pagelist_fraction), + .procname = "percpu_pagelist_high_fraction", + .data = &percpu_pagelist_high_fraction, + .maxlen = sizeof(percpu_pagelist_high_fraction), .mode = 0644, - .proc_handler = percpu_pagelist_fraction_sysctl_handler, + .proc_handler = percpu_pagelist_high_fraction_sysctl_handler, .extra1 = SYSCTL_ZERO, }, { @@ -2973,14 +2973,6 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { - .procname = "block_dump", - .data = &block_dump, - .maxlen = sizeof(block_dump), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, { .procname = "vfs_cache_pressure", .data = &sysctl_vfs_cache_pressure, diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 7df71ef0e1fd..04bfd62f5e5c 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -64,6 +64,15 @@ config LEGACY_TIMER_TICK lack support for the generic clockevent framework. New platforms should use generic clockevents instead. +config TIME_KUNIT_TEST + tristate "KUnit test for kernel/time functions" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + Enable this option to test RTC library functions. + + If unsure, say N. + if GENERIC_CLOCKEVENTS menu "Timers subsystem" diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 1fb1c1ef6a19..7e875e63ff3b 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -21,3 +21,5 @@ obj-$(CONFIG_HAVE_GENERIC_VDSO) += vsyscall.o obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o obj-$(CONFIG_TEST_UDELAY) += test_udelay.o obj-$(CONFIG_TIME_NS) += namespace.o +obj-$(CONFIG_TEST_CLOCKSOURCE_WATCHDOG) += clocksource-wdtest.o +obj-$(CONFIG_TIME_KUNIT_TEST) += time_test.o diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index f5490222e134..003ccf338d20 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -347,8 +347,7 @@ static void clockevents_notify_released(void) while (!list_empty(&clockevents_released)) { dev = list_entry(clockevents_released.next, struct clock_event_device, list); - list_del(&dev->list); - list_add(&dev->list, &clockevent_devices); + list_move(&dev->list, &clockevent_devices); tick_check_new_device(dev); } } @@ -576,8 +575,7 @@ void clockevents_exchange_device(struct clock_event_device *old, if (old) { module_put(old->owner); clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED); - list_del(&old->list); - list_add(&old->list, &clockevents_released); + list_move(&old->list, &clockevents_released); } if (new) { @@ -629,6 +627,7 @@ void tick_offline_cpu(unsigned int cpu) /** * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu + * @cpu: The dead CPU */ void tick_cleanup_dead_cpu(int cpu) { @@ -668,9 +667,9 @@ static struct bus_type clockevents_subsys = { static DEFINE_PER_CPU(struct device, tick_percpu_dev); static struct tick_device *tick_get_tick_dev(struct device *dev); -static ssize_t sysfs_show_current_tick_dev(struct device *dev, - struct device_attribute *attr, - char *buf) +static ssize_t current_device_show(struct device *dev, + struct device_attribute *attr, + char *buf) { struct tick_device *td; ssize_t count = 0; @@ -682,12 +681,12 @@ static ssize_t sysfs_show_current_tick_dev(struct device *dev, raw_spin_unlock_irq(&clockevents_lock); return count; } -static DEVICE_ATTR(current_device, 0444, sysfs_show_current_tick_dev, NULL); +static DEVICE_ATTR_RO(current_device); /* We don't support the abomination of removable broadcast devices */ -static ssize_t sysfs_unbind_tick_dev(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static ssize_t unbind_device_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { char name[CS_NAME_LEN]; ssize_t ret = sysfs_get_uname(buf, name, count); @@ -714,7 +713,7 @@ static ssize_t sysfs_unbind_tick_dev(struct device *dev, mutex_unlock(&clockevents_mutex); return ret ? ret : count; } -static DEVICE_ATTR(unbind_device, 0200, NULL, sysfs_unbind_tick_dev); +static DEVICE_ATTR_WO(unbind_device); #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST static struct device tick_bc_dev = { diff --git a/kernel/time/clocksource-wdtest.c b/kernel/time/clocksource-wdtest.c new file mode 100644 index 000000000000..01df12395c0e --- /dev/null +++ b/kernel/time/clocksource-wdtest.c @@ -0,0 +1,202 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Unit test for the clocksource watchdog. + * + * Copyright (C) 2021 Facebook, Inc. + * + * Author: Paul E. McKenney + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include /* for spin_unlock_irq() using preempt_count() m68k */ +#include +#include +#include +#include +#include + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Paul E. McKenney "); + +static int holdoff = IS_BUILTIN(CONFIG_TEST_CLOCKSOURCE_WATCHDOG) ? 10 : 0; +module_param(holdoff, int, 0444); +MODULE_PARM_DESC(holdoff, "Time to wait to start test (s)."); + +/* Watchdog kthread's task_struct pointer for debug purposes. */ +static struct task_struct *wdtest_task; + +static u64 wdtest_jiffies_read(struct clocksource *cs) +{ + return (u64)jiffies; +} + +/* Assume HZ > 100. */ +#define JIFFIES_SHIFT 8 + +static struct clocksource clocksource_wdtest_jiffies = { + .name = "wdtest-jiffies", + .rating = 1, /* lowest valid rating*/ + .uncertainty_margin = TICK_NSEC, + .read = wdtest_jiffies_read, + .mask = CLOCKSOURCE_MASK(32), + .flags = CLOCK_SOURCE_MUST_VERIFY, + .mult = TICK_NSEC << JIFFIES_SHIFT, /* details above */ + .shift = JIFFIES_SHIFT, + .max_cycles = 10, +}; + +static int wdtest_ktime_read_ndelays; +static bool wdtest_ktime_read_fuzz; + +static u64 wdtest_ktime_read(struct clocksource *cs) +{ + int wkrn = READ_ONCE(wdtest_ktime_read_ndelays); + static int sign = 1; + u64 ret; + + if (wkrn) { + udelay(cs->uncertainty_margin / 250); + WRITE_ONCE(wdtest_ktime_read_ndelays, wkrn - 1); + } + ret = ktime_get_real_fast_ns(); + if (READ_ONCE(wdtest_ktime_read_fuzz)) { + sign = -sign; + ret = ret + sign * 100 * NSEC_PER_MSEC; + } + return ret; +} + +static void wdtest_ktime_cs_mark_unstable(struct clocksource *cs) +{ + pr_info("--- Marking %s unstable due to clocksource watchdog.\n", cs->name); +} + +#define KTIME_FLAGS (CLOCK_SOURCE_IS_CONTINUOUS | \ + CLOCK_SOURCE_VALID_FOR_HRES | \ + CLOCK_SOURCE_MUST_VERIFY | \ + CLOCK_SOURCE_VERIFY_PERCPU) + +static struct clocksource clocksource_wdtest_ktime = { + .name = "wdtest-ktime", + .rating = 300, + .read = wdtest_ktime_read, + .mask = CLOCKSOURCE_MASK(64), + .flags = KTIME_FLAGS, + .mark_unstable = wdtest_ktime_cs_mark_unstable, + .list = LIST_HEAD_INIT(clocksource_wdtest_ktime.list), +}; + +/* Reset the clocksource if needed. */ +static void wdtest_ktime_clocksource_reset(void) +{ + if (clocksource_wdtest_ktime.flags & CLOCK_SOURCE_UNSTABLE) { + clocksource_unregister(&clocksource_wdtest_ktime); + clocksource_wdtest_ktime.flags = KTIME_FLAGS; + schedule_timeout_uninterruptible(HZ / 10); + clocksource_register_khz(&clocksource_wdtest_ktime, 1000 * 1000); + } +} + +/* Run the specified series of watchdog tests. */ +static int wdtest_func(void *arg) +{ + unsigned long j1, j2; + char *s; + int i; + + schedule_timeout_uninterruptible(holdoff * HZ); + + /* + * Verify that jiffies-like clocksources get the manually + * specified uncertainty margin. + */ + pr_info("--- Verify jiffies-like uncertainty margin.\n"); + __clocksource_register(&clocksource_wdtest_jiffies); + WARN_ON_ONCE(clocksource_wdtest_jiffies.uncertainty_margin != TICK_NSEC); + + j1 = clocksource_wdtest_jiffies.read(&clocksource_wdtest_jiffies); + schedule_timeout_uninterruptible(HZ); + j2 = clocksource_wdtest_jiffies.read(&clocksource_wdtest_jiffies); + WARN_ON_ONCE(j1 == j2); + + clocksource_unregister(&clocksource_wdtest_jiffies); + + /* + * Verify that tsc-like clocksources are assigned a reasonable + * uncertainty margin. + */ + pr_info("--- Verify tsc-like uncertainty margin.\n"); + clocksource_register_khz(&clocksource_wdtest_ktime, 1000 * 1000); + WARN_ON_ONCE(clocksource_wdtest_ktime.uncertainty_margin < NSEC_PER_USEC); + + j1 = clocksource_wdtest_ktime.read(&clocksource_wdtest_ktime); + udelay(1); + j2 = clocksource_wdtest_ktime.read(&clocksource_wdtest_ktime); + pr_info("--- tsc-like times: %lu - %lu = %lu.\n", j2, j1, j2 - j1); + WARN_ON_ONCE(time_before(j2, j1 + NSEC_PER_USEC)); + + /* Verify tsc-like stability with various numbers of errors injected. */ + for (i = 0; i <= max_cswd_read_retries + 1; i++) { + if (i <= 1 && i < max_cswd_read_retries) + s = ""; + else if (i <= max_cswd_read_retries) + s = ", expect message"; + else + s = ", expect clock skew"; + pr_info("--- Watchdog with %dx error injection, %lu retries%s.\n", i, max_cswd_read_retries, s); + WRITE_ONCE(wdtest_ktime_read_ndelays, i); + schedule_timeout_uninterruptible(2 * HZ); + WARN_ON_ONCE(READ_ONCE(wdtest_ktime_read_ndelays)); + WARN_ON_ONCE((i <= max_cswd_read_retries) != + !(clocksource_wdtest_ktime.flags & CLOCK_SOURCE_UNSTABLE)); + wdtest_ktime_clocksource_reset(); + } + + /* Verify tsc-like stability with clock-value-fuzz error injection. */ + pr_info("--- Watchdog clock-value-fuzz error injection, expect clock skew and per-CPU mismatches.\n"); + WRITE_ONCE(wdtest_ktime_read_fuzz, true); + schedule_timeout_uninterruptible(2 * HZ); + WARN_ON_ONCE(!(clocksource_wdtest_ktime.flags & CLOCK_SOURCE_UNSTABLE)); + clocksource_verify_percpu(&clocksource_wdtest_ktime); + WRITE_ONCE(wdtest_ktime_read_fuzz, false); + + clocksource_unregister(&clocksource_wdtest_ktime); + + pr_info("--- Done with test.\n"); + return 0; +} + +static void wdtest_print_module_parms(void) +{ + pr_alert("--- holdoff=%d\n", holdoff); +} + +/* Cleanup function. */ +static void clocksource_wdtest_cleanup(void) +{ +} + +static int __init clocksource_wdtest_init(void) +{ + int ret = 0; + + wdtest_print_module_parms(); + + /* Create watchdog-test task. */ + wdtest_task = kthread_run(wdtest_func, NULL, "wdtest"); + if (IS_ERR(wdtest_task)) { + ret = PTR_ERR(wdtest_task); + pr_warn("%s: Failed to create wdtest kthread.\n", __func__); + wdtest_task = NULL; + return ret; + } + + return 0; +} + +module_init(clocksource_wdtest_init); +module_exit(clocksource_wdtest_cleanup); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 2cd902592fc1..b89c76e1c02c 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -14,6 +14,8 @@ #include /* for spin_unlock_irq() using preempt_count() m68k */ #include #include +#include +#include #include "tick-internal.h" #include "timekeeping_internal.h" @@ -93,6 +95,20 @@ static char override_name[CS_NAME_LEN]; static int finished_booting; static u64 suspend_start; +/* + * Threshold: 0.0312s, when doubled: 0.0625s. + * Also a default for cs->uncertainty_margin when registering clocks. + */ +#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 5) + +/* + * Maximum permissible delay between two readouts of the watchdog + * clocksource surrounding a read of the clocksource being validated. + * This delay could be due to SMIs, NMIs, or to VCPU preemptions. Used as + * a lower bound for cs->uncertainty_margin values when registering clocks. + */ +#define WATCHDOG_MAX_SKEW (50 * NSEC_PER_USEC) + #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); static void clocksource_select(void); @@ -119,10 +135,9 @@ static int clocksource_watchdog_kthread(void *data); static void __clocksource_change_rating(struct clocksource *cs, int rating); /* - * Interval: 0.5sec Threshold: 0.0625s + * Interval: 0.5sec. */ #define WATCHDOG_INTERVAL (HZ >> 1) -#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4) static void clocksource_watchdog_work(struct work_struct *work) { @@ -184,12 +199,164 @@ void clocksource_mark_unstable(struct clocksource *cs) spin_unlock_irqrestore(&watchdog_lock, flags); } +ulong max_cswd_read_retries = 3; +module_param(max_cswd_read_retries, ulong, 0644); +EXPORT_SYMBOL_GPL(max_cswd_read_retries); +static int verify_n_cpus = 8; +module_param(verify_n_cpus, int, 0644); + +static bool cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) +{ + unsigned int nretries; + u64 wd_end, wd_delta; + int64_t wd_delay; + + for (nretries = 0; nretries <= max_cswd_read_retries; nretries++) { + local_irq_disable(); + *wdnow = watchdog->read(watchdog); + *csnow = cs->read(cs); + wd_end = watchdog->read(watchdog); + local_irq_enable(); + + wd_delta = clocksource_delta(wd_end, *wdnow, watchdog->mask); + wd_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, + watchdog->shift); + if (wd_delay <= WATCHDOG_MAX_SKEW) { + if (nretries > 1 || nretries >= max_cswd_read_retries) { + pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n", + smp_processor_id(), watchdog->name, nretries); + } + return true; + } + } + + pr_warn("timekeeping watchdog on CPU%d: %s read-back delay of %lldns, attempt %d, marking unstable\n", + smp_processor_id(), watchdog->name, wd_delay, nretries); + return false; +} + +static u64 csnow_mid; +static cpumask_t cpus_ahead; +static cpumask_t cpus_behind; +static cpumask_t cpus_chosen; + +static void clocksource_verify_choose_cpus(void) +{ + int cpu, i, n = verify_n_cpus; + + if (n < 0) { + /* Check all of the CPUs. */ + cpumask_copy(&cpus_chosen, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &cpus_chosen); + return; + } + + /* If no checking desired, or no other CPU to check, leave. */ + cpumask_clear(&cpus_chosen); + if (n == 0 || num_online_cpus() <= 1) + return; + + /* Make sure to select at least one CPU other than the current CPU. */ + cpu = cpumask_next(-1, cpu_online_mask); + if (cpu == smp_processor_id()) + cpu = cpumask_next(cpu, cpu_online_mask); + if (WARN_ON_ONCE(cpu >= nr_cpu_ids)) + return; + cpumask_set_cpu(cpu, &cpus_chosen); + + /* Force a sane value for the boot parameter. */ + if (n > nr_cpu_ids) + n = nr_cpu_ids; + + /* + * Randomly select the specified number of CPUs. If the same + * CPU is selected multiple times, that CPU is checked only once, + * and no replacement CPU is selected. This gracefully handles + * situations where verify_n_cpus is greater than the number of + * CPUs that are currently online. + */ + for (i = 1; i < n; i++) { + cpu = prandom_u32() % nr_cpu_ids; + cpu = cpumask_next(cpu - 1, cpu_online_mask); + if (cpu >= nr_cpu_ids) + cpu = cpumask_next(-1, cpu_online_mask); + if (!WARN_ON_ONCE(cpu >= nr_cpu_ids)) + cpumask_set_cpu(cpu, &cpus_chosen); + } + + /* Don't verify ourselves. */ + cpumask_clear_cpu(smp_processor_id(), &cpus_chosen); +} + +static void clocksource_verify_one_cpu(void *csin) +{ + struct clocksource *cs = (struct clocksource *)csin; + + csnow_mid = cs->read(cs); +} + +void clocksource_verify_percpu(struct clocksource *cs) +{ + int64_t cs_nsec, cs_nsec_max = 0, cs_nsec_min = LLONG_MAX; + u64 csnow_begin, csnow_end; + int cpu, testcpu; + s64 delta; + + if (verify_n_cpus == 0) + return; + cpumask_clear(&cpus_ahead); + cpumask_clear(&cpus_behind); + get_online_cpus(); + preempt_disable(); + clocksource_verify_choose_cpus(); + if (cpumask_weight(&cpus_chosen) == 0) { + preempt_enable(); + put_online_cpus(); + pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name); + return; + } + testcpu = smp_processor_id(); + pr_warn("Checking clocksource %s synchronization from CPU %d to CPUs %*pbl.\n", cs->name, testcpu, cpumask_pr_args(&cpus_chosen)); + for_each_cpu(cpu, &cpus_chosen) { + if (cpu == testcpu) + continue; + csnow_begin = cs->read(cs); + smp_call_function_single(cpu, clocksource_verify_one_cpu, cs, 1); + csnow_end = cs->read(cs); + delta = (s64)((csnow_mid - csnow_begin) & cs->mask); + if (delta < 0) + cpumask_set_cpu(cpu, &cpus_behind); + delta = (csnow_end - csnow_mid) & cs->mask; + if (delta < 0) + cpumask_set_cpu(cpu, &cpus_ahead); + delta = clocksource_delta(csnow_end, csnow_begin, cs->mask); + cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift); + if (cs_nsec > cs_nsec_max) + cs_nsec_max = cs_nsec; + if (cs_nsec < cs_nsec_min) + cs_nsec_min = cs_nsec; + } + preempt_enable(); + put_online_cpus(); + if (!cpumask_empty(&cpus_ahead)) + pr_warn(" CPUs %*pbl ahead of CPU %d for clocksource %s.\n", + cpumask_pr_args(&cpus_ahead), testcpu, cs->name); + if (!cpumask_empty(&cpus_behind)) + pr_warn(" CPUs %*pbl behind CPU %d for clocksource %s.\n", + cpumask_pr_args(&cpus_behind), testcpu, cs->name); + if (!cpumask_empty(&cpus_ahead) || !cpumask_empty(&cpus_behind)) + pr_warn(" CPU %d check durations %lldns - %lldns for clocksource %s.\n", + testcpu, cs_nsec_min, cs_nsec_max, cs->name); +} +EXPORT_SYMBOL_GPL(clocksource_verify_percpu); + static void clocksource_watchdog(struct timer_list *unused) { - struct clocksource *cs; u64 csnow, wdnow, cslast, wdlast, delta; - int64_t wd_nsec, cs_nsec; int next_cpu, reset_pending; + int64_t wd_nsec, cs_nsec; + struct clocksource *cs; + u32 md; spin_lock(&watchdog_lock); if (!watchdog_running) @@ -206,10 +373,11 @@ static void clocksource_watchdog(struct timer_list *unused) continue; } - local_irq_disable(); - csnow = cs->read(cs); - wdnow = watchdog->read(watchdog); - local_irq_enable(); + if (!cs_watchdog_read(cs, &csnow, &wdnow)) { + /* Clock readout unreliable, so give it up. */ + __clocksource_unstable(cs); + continue; + } /* Clocksource initialized ? */ if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) || @@ -235,13 +403,20 @@ static void clocksource_watchdog(struct timer_list *unused) continue; /* Check the deviation from the watchdog clocksource. */ - if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) { + md = cs->uncertainty_margin + watchdog->uncertainty_margin; + if (abs(cs_nsec - wd_nsec) > md) { pr_warn("timekeeping watchdog on CPU%d: Marking clocksource '%s' as unstable because the skew is too large:\n", smp_processor_id(), cs->name); - pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n", - watchdog->name, wdnow, wdlast, watchdog->mask); - pr_warn(" '%s' cs_now: %llx cs_last: %llx mask: %llx\n", - cs->name, csnow, cslast, cs->mask); + pr_warn(" '%s' wd_nsec: %lld wd_now: %llx wd_last: %llx mask: %llx\n", + watchdog->name, wd_nsec, wdnow, wdlast, watchdog->mask); + pr_warn(" '%s' cs_nsec: %lld cs_now: %llx cs_last: %llx mask: %llx\n", + cs->name, cs_nsec, csnow, cslast, cs->mask); + if (curr_clocksource == cs) + pr_warn(" '%s' is current clocksource.\n", cs->name); + else if (curr_clocksource) + pr_warn(" '%s' (not '%s') is current clocksource.\n", curr_clocksource->name, cs->name); + else + pr_warn(" No current clocksource.\n"); __clocksource_unstable(cs); continue; } @@ -407,6 +582,12 @@ static int __clocksource_watchdog_kthread(void) unsigned long flags; int select = 0; + /* Do any required per-CPU skew verification. */ + if (curr_clocksource && + curr_clocksource->flags & CLOCK_SOURCE_UNSTABLE && + curr_clocksource->flags & CLOCK_SOURCE_VERIFY_PERCPU) + clocksource_verify_percpu(curr_clocksource); + spin_lock_irqsave(&watchdog_lock, flags); list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) { if (cs->flags & CLOCK_SOURCE_UNSTABLE) { @@ -876,6 +1057,26 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, NSEC_PER_SEC / scale, sec * scale); } + + /* + * If the uncertainty margin is not specified, calculate it. + * If both scale and freq are non-zero, calculate the clock + * period, but bound below at 2*WATCHDOG_MAX_SKEW. However, + * if either of scale or freq is zero, be very conservative and + * take the tens-of-milliseconds WATCHDOG_THRESHOLD value for the + * uncertainty margin. Allow stupidly small uncertainty margins + * to be specified by the caller for testing purposes, but warn + * to discourage production use of this capability. + */ + if (scale && freq && !cs->uncertainty_margin) { + cs->uncertainty_margin = NSEC_PER_SEC / (scale * freq); + if (cs->uncertainty_margin < 2 * WATCHDOG_MAX_SKEW) + cs->uncertainty_margin = 2 * WATCHDOG_MAX_SKEW; + } else if (!cs->uncertainty_margin) { + cs->uncertainty_margin = WATCHDOG_THRESHOLD; + } + WARN_ON_ONCE(cs->uncertainty_margin < 2 * WATCHDOG_MAX_SKEW); + /* * Ensure clocksources that have large 'mult' values don't overflow * when adjusted. diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index a492e4da69ba..01935aafdb46 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -49,13 +49,14 @@ static u64 jiffies_read(struct clocksource *cs) * for "tick-less" systems. */ static struct clocksource clocksource_jiffies = { - .name = "jiffies", - .rating = 1, /* lowest valid rating*/ - .read = jiffies_read, - .mask = CLOCKSOURCE_MASK(32), - .mult = TICK_NSEC << JIFFIES_SHIFT, /* details above */ - .shift = JIFFIES_SHIFT, - .max_cycles = 10, + .name = "jiffies", + .rating = 1, /* lowest valid rating*/ + .uncertainty_margin = 32 * NSEC_PER_MSEC, + .read = jiffies_read, + .mask = CLOCKSOURCE_MASK(32), + .mult = TICK_NSEC << JIFFIES_SHIFT, /* details above */ + .shift = JIFFIES_SHIFT, + .max_cycles = 10, }; __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index a44055228796..f7fe6fe36173 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -33,6 +33,8 @@ static int tick_broadcast_forced; static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock); #ifdef CONFIG_TICK_ONESHOT +static DEFINE_PER_CPU(struct clock_event_device *, tick_oneshot_wakeup_device); + static void tick_broadcast_setup_oneshot(struct clock_event_device *bc); static void tick_broadcast_clear_oneshot(int cpu); static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); @@ -61,6 +63,13 @@ struct cpumask *tick_get_broadcast_mask(void) return tick_broadcast_mask; } +static struct clock_event_device *tick_get_oneshot_wakeup_device(int cpu); + +const struct clock_event_device *tick_get_wakeup_device(int cpu) +{ + return tick_get_oneshot_wakeup_device(cpu); +} + /* * Start the device in periodic mode */ @@ -88,13 +97,75 @@ static bool tick_check_broadcast_device(struct clock_event_device *curdev, return !curdev || newdev->rating > curdev->rating; } +#ifdef CONFIG_TICK_ONESHOT +static struct clock_event_device *tick_get_oneshot_wakeup_device(int cpu) +{ + return per_cpu(tick_oneshot_wakeup_device, cpu); +} + +static void tick_oneshot_wakeup_handler(struct clock_event_device *wd) +{ + /* + * If we woke up early and the tick was reprogrammed in the + * meantime then this may be spurious but harmless. + */ + tick_receive_broadcast(); +} + +static bool tick_set_oneshot_wakeup_device(struct clock_event_device *newdev, + int cpu) +{ + struct clock_event_device *curdev = tick_get_oneshot_wakeup_device(cpu); + + if (!newdev) + goto set_device; + + if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) || + (newdev->features & CLOCK_EVT_FEAT_C3STOP)) + return false; + + if (!(newdev->features & CLOCK_EVT_FEAT_PERCPU) || + !(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) + return false; + + if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) + return false; + + if (curdev && newdev->rating <= curdev->rating) + return false; + + if (!try_module_get(newdev->owner)) + return false; + + newdev->event_handler = tick_oneshot_wakeup_handler; +set_device: + clockevents_exchange_device(curdev, newdev); + per_cpu(tick_oneshot_wakeup_device, cpu) = newdev; + return true; +} +#else +static struct clock_event_device *tick_get_oneshot_wakeup_device(int cpu) +{ + return NULL; +} + +static bool tick_set_oneshot_wakeup_device(struct clock_event_device *newdev, + int cpu) +{ + return false; +} +#endif + /* * Conditionally install/replace broadcast device */ -void tick_install_broadcast_device(struct clock_event_device *dev) +void tick_install_broadcast_device(struct clock_event_device *dev, int cpu) { struct clock_event_device *cur = tick_broadcast_device.evtdev; + if (tick_set_oneshot_wakeup_device(dev, cpu)) + return; + if (!tick_check_broadcast_device(cur, dev)) return; @@ -253,7 +324,6 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) return ret; } -#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST int tick_receive_broadcast(void) { struct tick_device *td = this_cpu_ptr(&tick_cpu_device); @@ -268,7 +338,6 @@ int tick_receive_broadcast(void) evt->event_handler(evt); return 0; } -#endif /* * Broadcast the event to the cpus, which are set in the mask (mangled). @@ -719,24 +788,16 @@ static void broadcast_shutdown_local(struct clock_event_device *bc, clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN); } -int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) +static int ___tick_broadcast_oneshot_control(enum tick_broadcast_state state, + struct tick_device *td, + int cpu) { - struct clock_event_device *bc, *dev; - int cpu, ret = 0; + struct clock_event_device *bc, *dev = td->evtdev; + int ret = 0; ktime_t now; - /* - * If there is no broadcast device, tell the caller not to go - * into deep idle. - */ - if (!tick_broadcast_device.evtdev) - return -EBUSY; - - dev = this_cpu_ptr(&tick_cpu_device)->evtdev; - raw_spin_lock(&tick_broadcast_lock); bc = tick_broadcast_device.evtdev; - cpu = smp_processor_id(); if (state == TICK_BROADCAST_ENTER) { /* @@ -865,6 +926,53 @@ out: return ret; } +static int tick_oneshot_wakeup_control(enum tick_broadcast_state state, + struct tick_device *td, + int cpu) +{ + struct clock_event_device *dev, *wd; + + dev = td->evtdev; + if (td->mode != TICKDEV_MODE_ONESHOT) + return -EINVAL; + + wd = tick_get_oneshot_wakeup_device(cpu); + if (!wd) + return -ENODEV; + + switch (state) { + case TICK_BROADCAST_ENTER: + clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED); + clockevents_switch_state(wd, CLOCK_EVT_STATE_ONESHOT); + clockevents_program_event(wd, dev->next_event, 1); + break; + case TICK_BROADCAST_EXIT: + /* We may have transitioned to oneshot mode while idle */ + if (clockevent_get_state(wd) != CLOCK_EVT_STATE_ONESHOT) + return -ENODEV; + } + + return 0; +} + +int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) +{ + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + int cpu = smp_processor_id(); + + if (!tick_oneshot_wakeup_control(state, td, cpu)) + return 0; + + if (tick_broadcast_device.evtdev) + return ___tick_broadcast_oneshot_control(state, td, cpu); + + /* + * If there is no broadcast or wakeup device, tell the caller not + * to go into deep idle. + */ + return -EBUSY; +} + /* * Reset the one shot broadcast for a cpu * @@ -991,6 +1099,9 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu) */ static void tick_broadcast_oneshot_offline(unsigned int cpu) { + if (tick_get_oneshot_wakeup_device(cpu)) + tick_set_oneshot_wakeup_device(NULL, cpu); + /* * Clear the broadcast masks for the dead cpu, but do not stop * the broadcast device! diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index aecc371f61fe..52414eb5823c 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -375,7 +375,7 @@ out_bc: /* * Can the new device be used as a broadcast device ? */ - tick_install_broadcast_device(newdev); + tick_install_broadcast_device(newdev, cpu); } /** diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 7a981c9e87a4..6a742a29e545 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -61,7 +61,7 @@ extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); /* Broadcasting support */ # ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); -extern void tick_install_broadcast_device(struct clock_event_device *dev); +extern void tick_install_broadcast_device(struct clock_event_device *dev, int cpu); extern int tick_is_broadcast_device(struct clock_event_device *dev); extern void tick_suspend_broadcast(void); extern void tick_resume_broadcast(void); @@ -71,8 +71,9 @@ extern void tick_set_periodic_handler(struct clock_event_device *dev, int broadc extern int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq); extern struct tick_device *tick_get_broadcast_device(void); extern struct cpumask *tick_get_broadcast_mask(void); +extern const struct clock_event_device *tick_get_wakeup_device(int cpu); # else /* !CONFIG_GENERIC_CLOCKEVENTS_BROADCAST: */ -static inline void tick_install_broadcast_device(struct clock_event_device *dev) { } +static inline void tick_install_broadcast_device(struct clock_event_device *dev, int cpu) { } static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; } static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; } static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { } diff --git a/kernel/time/time_test.c b/kernel/time/time_test.c new file mode 100644 index 000000000000..831e8e779ace --- /dev/null +++ b/kernel/time/time_test.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: LGPL-2.1+ + +#include +#include + +/* + * Traditional implementation of leap year evaluation. + */ +static bool is_leap(long year) +{ + return year % 4 == 0 && (year % 100 != 0 || year % 400 == 0); +} + +/* + * Gets the last day of a month. + */ +static int last_day_of_month(long year, int month) +{ + if (month == 2) + return 28 + is_leap(year); + if (month == 4 || month == 6 || month == 9 || month == 11) + return 30; + return 31; +} + +/* + * Advances a date by one day. + */ +static void advance_date(long *year, int *month, int *mday, int *yday) +{ + if (*mday != last_day_of_month(*year, *month)) { + ++*mday; + ++*yday; + return; + } + + *mday = 1; + if (*month != 12) { + ++*month; + ++*yday; + return; + } + + *month = 1; + *yday = 0; + ++*year; +} + +/* + * Checks every day in a 160000 years interval centered at 1970-01-01 + * against the expected result. + */ +static void time64_to_tm_test_date_range(struct kunit *test) +{ + /* + * 80000 years = (80000 / 400) * 400 years + * = (80000 / 400) * 146097 days + * = (80000 / 400) * 146097 * 86400 seconds + */ + time64_t total_secs = ((time64_t) 80000) / 400 * 146097 * 86400; + long year = 1970 - 80000; + int month = 1; + int mdday = 1; + int yday = 0; + + struct tm result; + time64_t secs; + s64 days; + + for (secs = -total_secs; secs <= total_secs; secs += 86400) { + + time64_to_tm(secs, 0, &result); + + days = div_s64(secs, 86400); + + #define FAIL_MSG "%05ld/%02d/%02d (%2d) : %ld", \ + year, month, mdday, yday, days + + KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG); + KUNIT_ASSERT_EQ_MSG(test, month - 1, result.tm_mon, FAIL_MSG); + KUNIT_ASSERT_EQ_MSG(test, mdday, result.tm_mday, FAIL_MSG); + KUNIT_ASSERT_EQ_MSG(test, yday, result.tm_yday, FAIL_MSG); + + advance_date(&year, &month, &mdday, &yday); + } +} + +static struct kunit_case time_test_cases[] = { + KUNIT_CASE(time64_to_tm_test_date_range), + {} +}; + +static struct kunit_suite time_test_suite = { + .name = "time_test_cases", + .test_cases = time_test_cases, +}; + +kunit_test_suite(time_test_suite); +MODULE_LICENSE("GPL"); diff --git a/kernel/time/timeconv.c b/kernel/time/timeconv.c index 62e3b46717a6..59b922c826e7 100644 --- a/kernel/time/timeconv.c +++ b/kernel/time/timeconv.c @@ -22,47 +22,16 @@ /* * Converts the calendar time to broken-down time representation - * Based on code from glibc-2.6 * * 2009-7-14: * Moved from glibc-2.6 to kernel by Zhaolei + * 2021-06-02: + * Reimplemented by Cassio Neri */ #include #include - -/* - * Nonzero if YEAR is a leap year (every 4 years, - * except every 100th isn't, and every 400th is). - */ -static int __isleap(long year) -{ - return (year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0); -} - -/* do a mathdiv for long type */ -static long math_div(long a, long b) -{ - return a / b - (a % b < 0); -} - -/* How many leap years between y1 and y2, y1 must less or equal to y2 */ -static long leaps_between(long y1, long y2) -{ - long leaps1 = math_div(y1 - 1, 4) - math_div(y1 - 1, 100) - + math_div(y1 - 1, 400); - long leaps2 = math_div(y2 - 1, 4) - math_div(y2 - 1, 100) - + math_div(y2 - 1, 400); - return leaps2 - leaps1; -} - -/* How many days come before each month (0-12). */ -static const unsigned short __mon_yday[2][13] = { - /* Normal years. */ - {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365}, - /* Leap years. */ - {0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366} -}; +#include #define SECS_PER_HOUR (60 * 60) #define SECS_PER_DAY (SECS_PER_HOUR * 24) @@ -77,9 +46,11 @@ static const unsigned short __mon_yday[2][13] = { */ void time64_to_tm(time64_t totalsecs, int offset, struct tm *result) { - long days, rem, y; + u32 u32tmp, day_of_century, year_of_century, day_of_year, month, day; + u64 u64tmp, udays, century, year; + bool is_Jan_or_Feb, is_leap_year; + long days, rem; int remainder; - const unsigned short *ip; days = div_s64_rem(totalsecs, SECS_PER_DAY, &remainder); rem = remainder; @@ -103,27 +74,68 @@ void time64_to_tm(time64_t totalsecs, int offset, struct tm *result) if (result->tm_wday < 0) result->tm_wday += 7; - y = 1970; + /* + * The following algorithm is, basically, Proposition 6.3 of Neri + * and Schneider [1]. In a few words: it works on the computational + * (fictitious) calendar where the year starts in March, month = 2 + * (*), and finishes in February, month = 13. This calendar is + * mathematically convenient because the day of the year does not + * depend on whether the year is leap or not. For instance: + * + * March 1st 0-th day of the year; + * ... + * April 1st 31-st day of the year; + * ... + * January 1st 306-th day of the year; (Important!) + * ... + * February 28th 364-th day of the year; + * February 29th 365-th day of the year (if it exists). + * + * After having worked out the date in the computational calendar + * (using just arithmetics) it's easy to convert it to the + * corresponding date in the Gregorian calendar. + * + * [1] "Euclidean Affine Functions and Applications to Calendar + * Algorithms". https://arxiv.org/abs/2102.06959 + * + * (*) The numbering of months follows tm more closely and thus, + * is slightly different from [1]. + */ - while (days < 0 || days >= (__isleap(y) ? 366 : 365)) { - /* Guess a corrected year, assuming 365 days per year. */ - long yg = y + math_div(days, 365); + udays = ((u64) days) + 2305843009213814918ULL; - /* Adjust DAYS and Y to match the guessed year. */ - days -= (yg - y) * 365 + leaps_between(y, yg); - y = yg; - } + u64tmp = 4 * udays + 3; + century = div64_u64_rem(u64tmp, 146097, &u64tmp); + day_of_century = (u32) (u64tmp / 4); - result->tm_year = y - 1900; + u32tmp = 4 * day_of_century + 3; + u64tmp = 2939745ULL * u32tmp; + year_of_century = upper_32_bits(u64tmp); + day_of_year = lower_32_bits(u64tmp) / 2939745 / 4; - result->tm_yday = days; + year = 100 * century + year_of_century; + is_leap_year = year_of_century ? !(year_of_century % 4) : !(century % 4); - ip = __mon_yday[__isleap(y)]; - for (y = 11; days < ip[y]; y--) - continue; - days -= ip[y]; + u32tmp = 2141 * day_of_year + 132377; + month = u32tmp >> 16; + day = ((u16) u32tmp) / 2141; - result->tm_mon = y; - result->tm_mday = days + 1; + /* + * Recall that January 1st is the 306-th day of the year in the + * computational (not Gregorian) calendar. + */ + is_Jan_or_Feb = day_of_year >= 306; + + /* Convert to the Gregorian calendar and adjust to Unix time. */ + year = year + is_Jan_or_Feb - 6313183731940000ULL; + month = is_Jan_or_Feb ? month - 12 : month; + day = day + 1; + day_of_year += is_Jan_or_Feb ? -306 : 31 + 28 + is_leap_year; + + /* Convert to tm's format. */ + result->tm_year = (long) (year - 1900); + result->tm_mon = (int) month; + result->tm_mday = (int) day; + result->tm_yday = (int) day_of_year; } EXPORT_SYMBOL(time64_to_tm); diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 6939140ab7c5..ed7d6ad694fb 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -228,6 +228,14 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) SEQ_printf(m, " event_handler: %ps\n", dev->event_handler); SEQ_printf(m, "\n"); SEQ_printf(m, " retries: %lu\n", dev->retries); + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST + if (cpu >= 0) { + const struct clock_event_device *wd = tick_get_wakeup_device(cpu); + + SEQ_printf(m, "Wakeup Device: %s\n", wd ? wd->name : ""); + } +#endif SEQ_printf(m, "\n"); } @@ -248,7 +256,7 @@ static void timer_list_show_tickdevices_header(struct seq_file *m) static inline void timer_list_header(struct seq_file *m, u64 now) { - SEQ_printf(m, "Timer List Version: v0.8\n"); + SEQ_printf(m, "Timer List Version: v0.9\n"); SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES); SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); SEQ_printf(m, "\n"); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7a52bc172841..64bd2d84367f 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1017,6 +1017,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; + case BPF_FUNC_get_current_ancestor_cgroup_id: + return &bpf_get_current_ancestor_cgroup_id_proto; #endif case BPF_FUNC_send_signal: return &bpf_send_signal_proto; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index cd80d046c7a5..d5d8c088a55d 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -20,6 +20,7 @@ #include #include #include +#include #ifdef CONFIG_FTRACE_SYSCALLS #include /* For NR_SYSCALLS */ @@ -99,16 +100,8 @@ enum trace_type { #include "trace_entries.h" /* Use this for memory failure errors */ -#define MEM_FAIL(condition, fmt, ...) ({ \ - static bool __section(".data.once") __warned; \ - int __ret_warn_once = !!(condition); \ - \ - if (unlikely(__ret_warn_once && !__warned)) { \ - __warned = true; \ - pr_err("ERROR: " fmt, ##__VA_ARGS__); \ - } \ - unlikely(__ret_warn_once); \ -}) +#define MEM_FAIL(condition, fmt, ...) \ + DO_ONCE_LITE_IF(condition, pr_err, "ERROR: " fmt, ##__VA_ARGS__) /* * syscalls are special, and need special handling, this is why diff --git a/kernel/ucount.c b/kernel/ucount.c index 8d8874f1c35e..87799e2379bd 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -8,6 +8,12 @@ #include #include +struct ucounts init_ucounts = { + .ns = &init_user_ns, + .uid = GLOBAL_ROOT_UID, + .count = ATOMIC_INIT(1), +}; + #define UCOUNTS_HASHTABLE_BITS 10 static struct hlist_head ucounts_hashtable[(1 << UCOUNTS_HASHTABLE_BITS)]; static DEFINE_SPINLOCK(ucounts_lock); @@ -78,6 +84,10 @@ static struct ctl_table user_table[] = { UCOUNT_ENTRY("max_fanotify_groups"), UCOUNT_ENTRY("max_fanotify_marks"), #endif + { }, + { }, + { }, + { }, { } }; #endif /* CONFIG_SYSCTL */ @@ -129,7 +139,24 @@ static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struc return NULL; } -static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) +static void hlist_add_ucounts(struct ucounts *ucounts) +{ + struct hlist_head *hashent = ucounts_hashentry(ucounts->ns, ucounts->uid); + spin_lock_irq(&ucounts_lock); + hlist_add_head(&ucounts->node, hashent); + spin_unlock_irq(&ucounts_lock); +} + +struct ucounts *get_ucounts(struct ucounts *ucounts) +{ + if (ucounts && atomic_add_negative(1, &ucounts->count)) { + put_ucounts(ucounts); + ucounts = NULL; + } + return ucounts; +} + +struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) { struct hlist_head *hashent = ucounts_hashentry(ns, uid); struct ucounts *ucounts, *new; @@ -145,7 +172,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) new->ns = ns; new->uid = uid; - new->count = 0; + atomic_set(&new->count, 1); spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); @@ -153,40 +180,35 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) kfree(new); } else { hlist_add_head(&new->node, hashent); - ucounts = new; + spin_unlock_irq(&ucounts_lock); + return new; } } - if (ucounts->count == INT_MAX) - ucounts = NULL; - else - ucounts->count += 1; spin_unlock_irq(&ucounts_lock); + ucounts = get_ucounts(ucounts); return ucounts; } -static void put_ucounts(struct ucounts *ucounts) +void put_ucounts(struct ucounts *ucounts) { unsigned long flags; - spin_lock_irqsave(&ucounts_lock, flags); - ucounts->count -= 1; - if (!ucounts->count) + if (atomic_dec_and_test(&ucounts->count)) { + spin_lock_irqsave(&ucounts_lock, flags); hlist_del_init(&ucounts->node); - else - ucounts = NULL; - spin_unlock_irqrestore(&ucounts_lock, flags); - - kfree(ucounts); + spin_unlock_irqrestore(&ucounts_lock, flags); + kfree(ucounts); + } } -static inline bool atomic_inc_below(atomic_t *v, int u) +static inline bool atomic_long_inc_below(atomic_long_t *v, int u) { - int c, old; - c = atomic_read(v); + long c, old; + c = atomic_long_read(v); for (;;) { if (unlikely(c >= u)) return false; - old = atomic_cmpxchg(v, c, c+1); + old = atomic_long_cmpxchg(v, c, c+1); if (likely(old == c)) return true; c = old; @@ -198,19 +220,19 @@ struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, { struct ucounts *ucounts, *iter, *bad; struct user_namespace *tns; - ucounts = get_ucounts(ns, uid); + ucounts = alloc_ucounts(ns, uid); for (iter = ucounts; iter; iter = tns->ucounts) { - int max; + long max; tns = iter->ns; max = READ_ONCE(tns->ucount_max[type]); - if (!atomic_inc_below(&iter->ucount[type], max)) + if (!atomic_long_inc_below(&iter->ucount[type], max)) goto fail; } return ucounts; fail: bad = iter; for (iter = ucounts; iter != bad; iter = iter->ns->ucounts) - atomic_dec(&iter->ucount[type]); + atomic_long_dec(&iter->ucount[type]); put_ucounts(ucounts); return NULL; @@ -220,12 +242,54 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type) { struct ucounts *iter; for (iter = ucounts; iter; iter = iter->ns->ucounts) { - int dec = atomic_dec_if_positive(&iter->ucount[type]); + long dec = atomic_long_dec_if_positive(&iter->ucount[type]); WARN_ON_ONCE(dec < 0); } put_ucounts(ucounts); } +long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v) +{ + struct ucounts *iter; + long ret = 0; + + for (iter = ucounts; iter; iter = iter->ns->ucounts) { + long max = READ_ONCE(iter->ns->ucount_max[type]); + long new = atomic_long_add_return(v, &iter->ucount[type]); + if (new < 0 || new > max) + ret = LONG_MAX; + else if (iter == ucounts) + ret = new; + } + return ret; +} + +bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v) +{ + struct ucounts *iter; + long new = -1; /* Silence compiler warning */ + for (iter = ucounts; iter; iter = iter->ns->ucounts) { + long dec = atomic_long_add_return(-v, &iter->ucount[type]); + WARN_ON_ONCE(dec < 0); + if (iter == ucounts) + new = dec; + } + return (new == 0); +} + +bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max) +{ + struct ucounts *iter; + if (get_ucounts_value(ucounts, type) > max) + return true; + for (iter = ucounts; iter; iter = iter->ns->ucounts) { + max = READ_ONCE(iter->ns->ucount_max[type]); + if (get_ucounts_value(iter, type) > max) + return true; + } + return false; +} + static __init int user_namespace_sysctl_init(void) { #ifdef CONFIG_SYSCTL @@ -241,6 +305,8 @@ static __init int user_namespace_sysctl_init(void) BUG_ON(!user_header); BUG_ON(!setup_userns_sysctls(&init_user_ns)); #endif + hlist_add_ucounts(&init_ucounts); + inc_rlimit_ucounts(&init_ucounts, UCOUNT_RLIMIT_NPROC, 1); return 0; } subsys_initcall(user_namespace_sysctl_init); diff --git a/kernel/user.c b/kernel/user.c index a2478cddf536..c82399c1618a 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -98,9 +98,6 @@ static DEFINE_SPINLOCK(uidhash_lock); /* root_user.__count is 1, for init task cred */ struct user_struct root_user = { .__count = REFCOUNT_INIT(1), - .processes = ATOMIC_INIT(1), - .sigpending = ATOMIC_INIT(0), - .locked_shm = 0, .uid = GLOBAL_ROOT_UID, .ratelimit = RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0), }; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 8d62863721b0..ef82d401dde8 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -119,9 +119,13 @@ int create_user_ns(struct cred *new) ns->owner = owner; ns->group = group; INIT_WORK(&ns->work, free_user_ns); - for (i = 0; i < UCOUNT_COUNTS; i++) { + for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) { ns->ucount_max[i] = INT_MAX; } + set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)); + set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE)); + set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING)); + set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK)); ns->ucounts = ucounts; /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ @@ -1340,6 +1344,9 @@ static int userns_install(struct nsset *nsset, struct ns_common *ns) put_user_ns(cred->user_ns); set_cred_user_ns(cred, get_user_ns(user_ns)); + if (set_cred_ucounts(cred) < 0) + return -EINVAL; + return 0; } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 92d3bcc5a5e0..ad912511a0c0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -92,7 +92,7 @@ __setup("nmi_watchdog=", hardlockup_panic_setup); * own hardlockup detector. * * watchdog_nmi_enable/disable can be implemented to start and stop when - * softlockup watchdog threads start and stop. The arch must select the + * softlockup watchdog start and stop. The arch must select the * SOFTLOCKUP_DETECTOR Kconfig. */ int __weak watchdog_nmi_enable(unsigned int cpu) @@ -335,7 +335,7 @@ static DEFINE_PER_CPU(struct completion, softlockup_completion); static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); /* - * The watchdog thread function - touches the timestamp. + * The watchdog feed function - touches the timestamp. * * It only runs once every sample_period seconds (4 seconds by * default) to reset the softlockup timestamp. If this gets delayed @@ -558,11 +558,7 @@ static void lockup_detector_reconfigure(void) } /* - * Create the watchdog thread infrastructure and configure the detector(s). - * - * The threads are not unparked as watchdog_allowed_mask is empty. When - * the threads are successfully initialized, take the proper locks and - * unpark the threads in the watchdog_cpumask if the watchdog is enabled. + * Create the watchdog infrastructure and configure the detector(s). */ static __init void lockup_detector_setup(void) { @@ -628,7 +624,7 @@ void lockup_detector_soft_poweroff(void) #ifdef CONFIG_SYSCTL -/* Propagate any changes to the watchdog threads */ +/* Propagate any changes to the watchdog infrastructure */ static void proc_watchdog_update(void) { /* Remove impossible cpus to keep sysctl output clean. */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1e1bd6f4a13d..1c9857fdb1a0 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -313,6 +313,9 @@ config DEBUG_INFO_BTF config PAHOLE_HAS_SPLIT_BTF def_bool $(success, test `$(PAHOLE) --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/'` -ge "119") +config PAHOLE_HAS_ZEROSIZE_PERCPU_SUPPORT + def_bool $(success, test `$(PAHOLE) --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/'` -ge "122") + config DEBUG_INFO_BTF_MODULES def_bool y depends on DEBUG_INFO_BTF && MODULES && PAHOLE_HAS_SPLIT_BTF @@ -2180,6 +2183,9 @@ config TEST_KSTRTOX config TEST_PRINTF tristate "Test printf() family of functions at runtime" +config TEST_SCANF + tristate "Test scanf() family of functions at runtime" + config TEST_BITMAP tristate "Test bitmap_*() family of functions at runtime" help @@ -2428,6 +2434,18 @@ config BITS_TEST If unsure, say N. +config SLUB_KUNIT_TEST + tristate "KUnit test for SLUB cache error detection" if !KUNIT_ALL_TESTS + depends on SLUB_DEBUG && KUNIT + default KUNIT_ALL_TESTS + help + This builds SLUB allocator unit test. + Tests SLUB cache debugging functionality. + For more information on KUnit and unit tests in general please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. + + If unsure, say N. + config TEST_UDELAY tristate "udelay test driver" help @@ -2570,6 +2588,18 @@ config TEST_FPU If unsure, say N. +config TEST_CLOCKSOURCE_WATCHDOG + tristate "Test clocksource watchdog in kernel space" + depends on CLOCKSOURCE_WATCHDOG + help + Enable this option to create a kernel module that will trigger + a test of the clocksource watchdog. This module may be loaded + via modprobe or insmod in which case it will run upon being + loaded, or it may be built in, in which case it will run + shortly after boot. + + If unsure, say N. + endif # RUNTIME_TESTING_MENU config ARCH_USE_MEMTEST diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index cffc2ebbf185..1e2d10f86011 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -12,6 +12,13 @@ config HAVE_ARCH_KASAN_HW_TAGS config HAVE_ARCH_KASAN_VMALLOC bool +config ARCH_DISABLE_KASAN_INLINE + bool + help + An architecture might not support inline instrumentation. + When this option is selected, inline and stack instrumentation are + disabled. + config CC_HAS_KASAN_GENERIC def_bool $(cc-option, -fsanitize=kernel-address) @@ -130,6 +137,7 @@ config KASAN_OUTLINE config KASAN_INLINE bool "Inline instrumentation" + depends on !ARCH_DISABLE_KASAN_INLINE help Compiler directly inserts code checking shadow memory before memory accesses. This is faster than outline (in some workloads @@ -141,6 +149,7 @@ endchoice config KASAN_STACK bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST depends on KASAN_GENERIC || KASAN_SW_TAGS + depends on !ARCH_DISABLE_KASAN_INLINE default y if CC_IS_GCC help The LLVM stack address sanitizer has a know problem that @@ -154,10 +163,13 @@ config KASAN_STACK but clang users can still enable it for builds without CONFIG_COMPILE_TEST. On gcc it is assumed to always be safe to use and enabled by default. + If the architecture disables inline instrumentation, stack + instrumentation is also disabled as it adds inline-style + instrumentation that is run unconditionally. -config KASAN_SW_TAGS_IDENTIFY +config KASAN_TAGS_IDENTIFY bool "Enable memory corruption identification" - depends on KASAN_SW_TAGS + depends on KASAN_SW_TAGS || KASAN_HW_TAGS help This option enables best-effort identification of bug type (use-after-free or out-of-bounds) at the cost of increased diff --git a/lib/Makefile b/lib/Makefile index 2cc359ec1fdd..6d765d5fb8ac 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -83,6 +83,7 @@ obj-$(CONFIG_TEST_USER_COPY) += test_user_copy.o obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_keys.o obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o obj-$(CONFIG_TEST_PRINTF) += test_printf.o +obj-$(CONFIG_TEST_SCANF) += test_scanf.o obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o obj-$(CONFIG_TEST_STRSCPY) += test_strscpy.o obj-$(CONFIG_TEST_UUID) += test_uuid.o @@ -354,5 +355,6 @@ obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o obj-$(CONFIG_BITS_TEST) += test_bits.o obj-$(CONFIG_CMDLINE_KUNIT_TEST) += cmdline_kunit.o +obj-$(CONFIG_SLUB_KUNIT_TEST) += slub_kunit.o obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o diff --git a/lib/dump_stack.c b/lib/dump_stack.c index f5a33b6f773f..27f16872320d 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -73,10 +73,10 @@ void show_regs_print_info(const char *log_lvl) dump_stack_print_info(log_lvl); } -static void __dump_stack(void) +static void __dump_stack(const char *log_lvl) { - dump_stack_print_info(KERN_DEFAULT); - show_stack(NULL, NULL, KERN_DEFAULT); + dump_stack_print_info(log_lvl); + show_stack(NULL, NULL, log_lvl); } /** @@ -84,50 +84,22 @@ static void __dump_stack(void) * * Architectures can override this implementation by implementing its own. */ -#ifdef CONFIG_SMP -static atomic_t dump_lock = ATOMIC_INIT(-1); - -asmlinkage __visible void dump_stack(void) +asmlinkage __visible void dump_stack_lvl(const char *log_lvl) { unsigned long flags; - int was_locked; - int old; - int cpu; /* * Permit this cpu to perform nested stack dumps while serialising * against other CPUs */ -retry: - local_irq_save(flags); - cpu = smp_processor_id(); - old = atomic_cmpxchg(&dump_lock, -1, cpu); - if (old == -1) { - was_locked = 0; - } else if (old == cpu) { - was_locked = 1; - } else { - local_irq_restore(flags); - /* - * Wait for the lock to release before jumping to - * atomic_cmpxchg() in order to mitigate the thundering herd - * problem. - */ - do { cpu_relax(); } while (atomic_read(&dump_lock) != -1); - goto retry; - } - - __dump_stack(); - - if (!was_locked) - atomic_set(&dump_lock, -1); - - local_irq_restore(flags); + printk_cpu_lock_irqsave(flags); + __dump_stack(log_lvl); + printk_cpu_unlock_irqrestore(flags); } -#else +EXPORT_SYMBOL(dump_stack_lvl); + asmlinkage __visible void dump_stack(void) { - __dump_stack(); + dump_stack_lvl(KERN_DEFAULT); } -#endif EXPORT_SYMBOL(dump_stack); diff --git a/lib/kstrtox.c b/lib/kstrtox.c index a118b0b1e9b2..0b5fe8b41173 100644 --- a/lib/kstrtox.c +++ b/lib/kstrtox.c @@ -39,20 +39,22 @@ const char *_parse_integer_fixup_radix(const char *s, unsigned int *base) /* * Convert non-negative integer string representation in explicitly given radix - * to an integer. + * to an integer. A maximum of max_chars characters will be converted. + * * Return number of characters consumed maybe or-ed with overflow bit. * If overflow occurs, result integer (incorrect) is still returned. * * Don't you dare use this function. */ -unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p) +unsigned int _parse_integer_limit(const char *s, unsigned int base, unsigned long long *p, + size_t max_chars) { unsigned long long res; unsigned int rv; res = 0; rv = 0; - while (1) { + while (max_chars--) { unsigned int c = *s; unsigned int lc = c | 0x20; /* don't tolower() this line */ unsigned int val; @@ -82,6 +84,11 @@ unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long return rv; } +unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p) +{ + return _parse_integer_limit(s, base, p, INT_MAX); +} + static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res) { unsigned long long _res; diff --git a/lib/kstrtox.h b/lib/kstrtox.h index 3b4637bcd254..158c400ca865 100644 --- a/lib/kstrtox.h +++ b/lib/kstrtox.h @@ -4,6 +4,8 @@ #define KSTRTOX_OVERFLOW (1U << 31) const char *_parse_integer_fixup_radix(const char *s, unsigned int *base); +unsigned int _parse_integer_limit(const char *s, unsigned int base, unsigned long long *res, + size_t max_chars); unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *res); #endif diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 2f6cc0123232..45f068864d76 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -475,6 +475,7 @@ int kunit_add_resource(struct kunit *test, void *data) { int ret = 0; + unsigned long flags; res->free = free; kref_init(&res->refcount); @@ -487,10 +488,10 @@ int kunit_add_resource(struct kunit *test, res->data = data; } - spin_lock(&test->lock); + spin_lock_irqsave(&test->lock, flags); list_add_tail(&res->node, &test->resources); /* refcount for list is established by kref_init() */ - spin_unlock(&test->lock); + spin_unlock_irqrestore(&test->lock, flags); return ret; } @@ -548,9 +549,11 @@ EXPORT_SYMBOL_GPL(kunit_alloc_and_get_resource); void kunit_remove_resource(struct kunit *test, struct kunit_resource *res) { - spin_lock(&test->lock); + unsigned long flags; + + spin_lock_irqsave(&test->lock, flags); list_del(&res->node); - spin_unlock(&test->lock); + spin_unlock_irqrestore(&test->lock, flags); kunit_put_resource(res); } EXPORT_SYMBOL_GPL(kunit_remove_resource); @@ -630,6 +633,7 @@ EXPORT_SYMBOL_GPL(kunit_kfree); void kunit_cleanup(struct kunit *test) { struct kunit_resource *res; + unsigned long flags; /* * test->resources is a stack - each allocation must be freed in the @@ -641,9 +645,9 @@ void kunit_cleanup(struct kunit *test) * protect against the current node being deleted, not the next. */ while (true) { - spin_lock(&test->lock); + spin_lock_irqsave(&test->lock, flags); if (list_empty(&test->resources)) { - spin_unlock(&test->lock); + spin_unlock_irqrestore(&test->lock, flags); break; } res = list_last_entry(&test->resources, @@ -654,7 +658,7 @@ void kunit_cleanup(struct kunit *test) * resource, and this can't happen if the test->lock * is held. */ - spin_unlock(&test->lock); + spin_unlock_irqrestore(&test->lock, flags); kunit_remove_resource(test, res); } current->kunit_test = NULL; diff --git a/lib/slub_kunit.c b/lib/slub_kunit.c new file mode 100644 index 000000000000..8662dc6cb509 --- /dev/null +++ b/lib/slub_kunit.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include "../mm/slab.h" + +static struct kunit_resource resource; +static int slab_errors; + +static void test_clobber_zone(struct kunit *test) +{ + struct kmem_cache *s = kmem_cache_create("TestSlub_RZ_alloc", 64, 0, + SLAB_RED_ZONE, NULL); + u8 *p = kmem_cache_alloc(s, GFP_KERNEL); + + kasan_disable_current(); + p[64] = 0x12; + + validate_slab_cache(s); + KUNIT_EXPECT_EQ(test, 2, slab_errors); + + kasan_enable_current(); + kmem_cache_free(s, p); + kmem_cache_destroy(s); +} + +#ifndef CONFIG_KASAN +static void test_next_pointer(struct kunit *test) +{ + struct kmem_cache *s = kmem_cache_create("TestSlub_next_ptr_free", 64, 0, + SLAB_POISON, NULL); + u8 *p = kmem_cache_alloc(s, GFP_KERNEL); + unsigned long tmp; + unsigned long *ptr_addr; + + kmem_cache_free(s, p); + + ptr_addr = (unsigned long *)(p + s->offset); + tmp = *ptr_addr; + p[s->offset] = 0x12; + + /* + * Expecting three errors. + * One for the corrupted freechain and the other one for the wrong + * count of objects in use. The third error is fixing broken cache. + */ + validate_slab_cache(s); + KUNIT_EXPECT_EQ(test, 3, slab_errors); + + /* + * Try to repair corrupted freepointer. + * Still expecting two errors. The first for the wrong count + * of objects in use. + * The second error is for fixing broken cache. + */ + *ptr_addr = tmp; + slab_errors = 0; + + validate_slab_cache(s); + KUNIT_EXPECT_EQ(test, 2, slab_errors); + + /* + * Previous validation repaired the count of objects in use. + * Now expecting no error. + */ + slab_errors = 0; + validate_slab_cache(s); + KUNIT_EXPECT_EQ(test, 0, slab_errors); + + kmem_cache_destroy(s); +} + +static void test_first_word(struct kunit *test) +{ + struct kmem_cache *s = kmem_cache_create("TestSlub_1th_word_free", 64, 0, + SLAB_POISON, NULL); + u8 *p = kmem_cache_alloc(s, GFP_KERNEL); + + kmem_cache_free(s, p); + *p = 0x78; + + validate_slab_cache(s); + KUNIT_EXPECT_EQ(test, 2, slab_errors); + + kmem_cache_destroy(s); +} + +static void test_clobber_50th_byte(struct kunit *test) +{ + struct kmem_cache *s = kmem_cache_create("TestSlub_50th_word_free", 64, 0, + SLAB_POISON, NULL); + u8 *p = kmem_cache_alloc(s, GFP_KERNEL); + + kmem_cache_free(s, p); + p[50] = 0x9a; + + validate_slab_cache(s); + KUNIT_EXPECT_EQ(test, 2, slab_errors); + + kmem_cache_destroy(s); +} +#endif + +static void test_clobber_redzone_free(struct kunit *test) +{ + struct kmem_cache *s = kmem_cache_create("TestSlub_RZ_free", 64, 0, + SLAB_RED_ZONE, NULL); + u8 *p = kmem_cache_alloc(s, GFP_KERNEL); + + kasan_disable_current(); + kmem_cache_free(s, p); + p[64] = 0xab; + + validate_slab_cache(s); + KUNIT_EXPECT_EQ(test, 2, slab_errors); + + kasan_enable_current(); + kmem_cache_destroy(s); +} + +static int test_init(struct kunit *test) +{ + slab_errors = 0; + + kunit_add_named_resource(test, NULL, NULL, &resource, + "slab_errors", &slab_errors); + return 0; +} + +static struct kunit_case test_cases[] = { + KUNIT_CASE(test_clobber_zone), + +#ifndef CONFIG_KASAN + KUNIT_CASE(test_next_pointer), + KUNIT_CASE(test_first_word), + KUNIT_CASE(test_clobber_50th_byte), +#endif + + KUNIT_CASE(test_clobber_redzone_free), + {} +}; + +static struct kunit_suite test_suite = { + .name = "slub_test", + .init = test_init, + .test_cases = test_cases, +}; +kunit_test_suite(test_suite); + +MODULE_LICENSE("GPL"); diff --git a/lib/test_hmm.c b/lib/test_hmm.c index 80a78877bd93..15f2e2db77bc 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -686,9 +686,8 @@ static int dmirror_migrate(struct dmirror *dmirror, mmap_read_lock(mm); for (addr = start; addr < end; addr = next) { - vma = find_vma(mm, addr); - if (!vma || addr < vma->vm_start || - !(vma->vm_flags & VM_READ)) { + vma = vma_lookup(mm, addr); + if (!vma || !(vma->vm_flags & VM_READ)) { ret = -EINVAL; goto out; } diff --git a/lib/test_kasan.c b/lib/test_kasan.c index cacbbbdef768..44e08f4d9c52 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -55,7 +55,6 @@ static int kasan_test_init(struct kunit *test) multishot = kasan_save_enable_multi_shot(); kasan_set_tagging_report_once(false); fail_data.report_found = false; - fail_data.report_expected = false; kunit_add_named_resource(test, NULL, NULL, &resource, "kasan_data", &fail_data); return 0; @@ -94,20 +93,20 @@ static void kasan_test_exit(struct kunit *test) !kasan_async_mode_enabled()) \ migrate_disable(); \ KUNIT_EXPECT_FALSE(test, READ_ONCE(fail_data.report_found)); \ - WRITE_ONCE(fail_data.report_expected, true); \ barrier(); \ expression; \ barrier(); \ - KUNIT_EXPECT_EQ(test, \ - READ_ONCE(fail_data.report_expected), \ - READ_ONCE(fail_data.report_found)); \ + if (!READ_ONCE(fail_data.report_found)) { \ + KUNIT_FAIL(test, KUNIT_SUBTEST_INDENT "KASAN failure " \ + "expected in \"" #expression \ + "\", but none occurred"); \ + } \ if (IS_ENABLED(CONFIG_KASAN_HW_TAGS)) { \ if (READ_ONCE(fail_data.report_found)) \ kasan_enable_tagging_sync(); \ migrate_enable(); \ } \ WRITE_ONCE(fail_data.report_found, false); \ - WRITE_ONCE(fail_data.report_expected, false); \ } while (0) #define KASAN_TEST_NEEDS_CONFIG_ON(test, config) do { \ diff --git a/lib/test_printf.c b/lib/test_printf.c index ec0d5976bb69..8ac71aee46af 100644 --- a/lib/test_printf.c +++ b/lib/test_printf.c @@ -528,6 +528,11 @@ time_and_date(void) test("0119-00-04T15:32:23", "%ptTr", &t); test("15:32:23|2019-01-04", "%ptTt|%ptTd", &t, &t); test("15:32:23|0119-00-04", "%ptTtr|%ptTdr", &t, &t); + + test("2019-01-04 15:32:23", "%ptTs", &t); + test("0119-00-04 15:32:23", "%ptTsr", &t); + test("15:32:23|2019-01-04", "%ptTts|%ptTds", &t, &t); + test("15:32:23|0119-00-04", "%ptTtrs|%ptTdrs", &t, &t); } static void __init diff --git a/lib/test_scanf.c b/lib/test_scanf.c new file mode 100644 index 000000000000..48ff5747a4da --- /dev/null +++ b/lib/test_scanf.c @@ -0,0 +1,750 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test cases for sscanf facility. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../tools/testing/selftests/kselftest_module.h" + +#define BUF_SIZE 1024 + +KSTM_MODULE_GLOBALS(); +static char *test_buffer __initdata; +static char *fmt_buffer __initdata; +static struct rnd_state rnd_state __initdata; + +typedef int (*check_fn)(const void *check_data, const char *string, + const char *fmt, int n_args, va_list ap); + +static void __scanf(4, 6) __init +_test(check_fn fn, const void *check_data, const char *string, const char *fmt, + int n_args, ...) +{ + va_list ap, ap_copy; + int ret; + + total_tests++; + + va_start(ap, n_args); + va_copy(ap_copy, ap); + ret = vsscanf(string, fmt, ap_copy); + va_end(ap_copy); + + if (ret != n_args) { + pr_warn("vsscanf(\"%s\", \"%s\", ...) returned %d expected %d\n", + string, fmt, ret, n_args); + goto fail; + } + + ret = (*fn)(check_data, string, fmt, n_args, ap); + if (ret) + goto fail; + + va_end(ap); + + return; + +fail: + failed_tests++; + va_end(ap); +} + +#define _check_numbers_template(arg_fmt, expect, str, fmt, n_args, ap) \ +do { \ + pr_debug("\"%s\", \"%s\" ->\n", str, fmt); \ + for (; n_args > 0; n_args--, expect++) { \ + typeof(*expect) got = *va_arg(ap, typeof(expect)); \ + pr_debug("\t" arg_fmt "\n", got); \ + if (got != *expect) { \ + pr_warn("vsscanf(\"%s\", \"%s\", ...) expected " arg_fmt " got " arg_fmt "\n", \ + str, fmt, *expect, got); \ + return 1; \ + } \ + } \ + return 0; \ +} while (0) + +static int __init check_ull(const void *check_data, const char *string, + const char *fmt, int n_args, va_list ap) +{ + const unsigned long long *pval = check_data; + + _check_numbers_template("%llu", pval, string, fmt, n_args, ap); +} + +static int __init check_ll(const void *check_data, const char *string, + const char *fmt, int n_args, va_list ap) +{ + const long long *pval = check_data; + + _check_numbers_template("%lld", pval, string, fmt, n_args, ap); +} + +static int __init check_ulong(const void *check_data, const char *string, + const char *fmt, int n_args, va_list ap) +{ + const unsigned long *pval = check_data; + + _check_numbers_template("%lu", pval, string, fmt, n_args, ap); +} + +static int __init check_long(const void *check_data, const char *string, + const char *fmt, int n_args, va_list ap) +{ + const long *pval = check_data; + + _check_numbers_template("%ld", pval, string, fmt, n_args, ap); +} + +static int __init check_uint(const void *check_data, const char *string, + const char *fmt, int n_args, va_list ap) +{ + const unsigned int *pval = check_data; + + _check_numbers_template("%u", pval, string, fmt, n_args, ap); +} + +static int __init check_int(const void *check_data, const char *string, + const char *fmt, int n_args, va_list ap) +{ + const int *pval = check_data; + + _check_numbers_template("%d", pval, string, fmt, n_args, ap); +} + +static int __init check_ushort(const void *check_data, const char *string, + const char *fmt, int n_args, va_list ap) +{ + const unsigned short *pval = check_data; + + _check_numbers_template("%hu", pval, string, fmt, n_args, ap); +} + +static int __init check_short(const void *check_data, const char *string, + const char *fmt, int n_args, va_list ap) +{ + const short *pval = check_data; + + _check_numbers_template("%hd", pval, string, fmt, n_args, ap); +} + +static int __init check_uchar(const void *check_data, const char *string, + const char *fmt, int n_args, va_list ap) +{ + const unsigned char *pval = check_data; + + _check_numbers_template("%hhu", pval, string, fmt, n_args, ap); +} + +static int __init check_char(const void *check_data, const char *string, + const char *fmt, int n_args, va_list ap) +{ + const signed char *pval = check_data; + + _check_numbers_template("%hhd", pval, string, fmt, n_args, ap); +} + +/* Selection of interesting numbers to test, copied from test-kstrtox.c */ +static const unsigned long long numbers[] __initconst = { + 0x0ULL, + 0x1ULL, + 0x7fULL, + 0x80ULL, + 0x81ULL, + 0xffULL, + 0x100ULL, + 0x101ULL, + 0x7fffULL, + 0x8000ULL, + 0x8001ULL, + 0xffffULL, + 0x10000ULL, + 0x10001ULL, + 0x7fffffffULL, + 0x80000000ULL, + 0x80000001ULL, + 0xffffffffULL, + 0x100000000ULL, + 0x100000001ULL, + 0x7fffffffffffffffULL, + 0x8000000000000000ULL, + 0x8000000000000001ULL, + 0xfffffffffffffffeULL, + 0xffffffffffffffffULL, +}; + +#define value_representable_in_type(T, val) \ +(is_signed_type(T) \ + ? ((long long)(val) >= type_min(T)) && ((long long)(val) <= type_max(T)) \ + : ((unsigned long long)(val) <= type_max(T))) + + +#define test_one_number(T, gen_fmt, scan_fmt, val, fn) \ +do { \ + const T expect_val = (T)(val); \ + T result = ~expect_val; /* should be overwritten */ \ + \ + snprintf(test_buffer, BUF_SIZE, gen_fmt, expect_val); \ + _test(fn, &expect_val, test_buffer, "%" scan_fmt, 1, &result); \ +} while (0) + +#define simple_numbers_loop(T, gen_fmt, scan_fmt, fn) \ +do { \ + int i; \ + \ + for (i = 0; i < ARRAY_SIZE(numbers); i++) { \ + if (value_representable_in_type(T, numbers[i])) \ + test_one_number(T, gen_fmt, scan_fmt, \ + numbers[i], fn); \ + \ + if (value_representable_in_type(T, -numbers[i])) \ + test_one_number(T, gen_fmt, scan_fmt, \ + -numbers[i], fn); \ + } \ +} while (0) + +static void __init numbers_simple(void) +{ + simple_numbers_loop(unsigned long long, "%llu", "llu", check_ull); + simple_numbers_loop(long long, "%lld", "lld", check_ll); + simple_numbers_loop(long long, "%lld", "lli", check_ll); + simple_numbers_loop(unsigned long long, "%llx", "llx", check_ull); + simple_numbers_loop(long long, "%llx", "llx", check_ll); + simple_numbers_loop(long long, "0x%llx", "lli", check_ll); + simple_numbers_loop(unsigned long long, "0x%llx", "llx", check_ull); + simple_numbers_loop(long long, "0x%llx", "llx", check_ll); + + simple_numbers_loop(unsigned long, "%lu", "lu", check_ulong); + simple_numbers_loop(long, "%ld", "ld", check_long); + simple_numbers_loop(long, "%ld", "li", check_long); + simple_numbers_loop(unsigned long, "%lx", "lx", check_ulong); + simple_numbers_loop(long, "%lx", "lx", check_long); + simple_numbers_loop(long, "0x%lx", "li", check_long); + simple_numbers_loop(unsigned long, "0x%lx", "lx", check_ulong); + simple_numbers_loop(long, "0x%lx", "lx", check_long); + + simple_numbers_loop(unsigned int, "%u", "u", check_uint); + simple_numbers_loop(int, "%d", "d", check_int); + simple_numbers_loop(int, "%d", "i", check_int); + simple_numbers_loop(unsigned int, "%x", "x", check_uint); + simple_numbers_loop(int, "%x", "x", check_int); + simple_numbers_loop(int, "0x%x", "i", check_int); + simple_numbers_loop(unsigned int, "0x%x", "x", check_uint); + simple_numbers_loop(int, "0x%x", "x", check_int); + + simple_numbers_loop(unsigned short, "%hu", "hu", check_ushort); + simple_numbers_loop(short, "%hd", "hd", check_short); + simple_numbers_loop(short, "%hd", "hi", check_short); + simple_numbers_loop(unsigned short, "%hx", "hx", check_ushort); + simple_numbers_loop(short, "%hx", "hx", check_short); + simple_numbers_loop(short, "0x%hx", "hi", check_short); + simple_numbers_loop(unsigned short, "0x%hx", "hx", check_ushort); + simple_numbers_loop(short, "0x%hx", "hx", check_short); + + simple_numbers_loop(unsigned char, "%hhu", "hhu", check_uchar); + simple_numbers_loop(signed char, "%hhd", "hhd", check_char); + simple_numbers_loop(signed char, "%hhd", "hhi", check_char); + simple_numbers_loop(unsigned char, "%hhx", "hhx", check_uchar); + simple_numbers_loop(signed char, "%hhx", "hhx", check_char); + simple_numbers_loop(signed char, "0x%hhx", "hhi", check_char); + simple_numbers_loop(unsigned char, "0x%hhx", "hhx", check_uchar); + simple_numbers_loop(signed char, "0x%hhx", "hhx", check_char); +} + +/* + * This gives a better variety of number "lengths" in a small sample than + * the raw prandom*() functions (Not mathematically rigorous!!). + * Variabilty of length and value is more important than perfect randomness. + */ +static u32 __init next_test_random(u32 max_bits) +{ + u32 n_bits = hweight32(prandom_u32_state(&rnd_state)) % (max_bits + 1); + + return prandom_u32_state(&rnd_state) & (UINT_MAX >> (32 - n_bits)); +} + +static unsigned long long __init next_test_random_ull(void) +{ + u32 rand1 = prandom_u32_state(&rnd_state); + u32 n_bits = (hweight32(rand1) * 3) % 64; + u64 val = (u64)prandom_u32_state(&rnd_state) * rand1; + + return val & (ULLONG_MAX >> (64 - n_bits)); +} + +#define random_for_type(T) \ + ((T)(sizeof(T) <= sizeof(u32) \ + ? next_test_random(BITS_PER_TYPE(T)) \ + : next_test_random_ull())) + +/* + * Define a pattern of negative and positive numbers to ensure we get + * some of both within the small number of samples in a test string. + */ +#define NEGATIVES_PATTERN 0x3246 /* 00110010 01000110 */ + +#define fill_random_array(arr) \ +do { \ + unsigned int neg_pattern = NEGATIVES_PATTERN; \ + int i; \ + \ + for (i = 0; i < ARRAY_SIZE(arr); i++, neg_pattern >>= 1) { \ + (arr)[i] = random_for_type(typeof((arr)[0])); \ + if (is_signed_type(typeof((arr)[0])) && (neg_pattern & 1)) \ + (arr)[i] = -(arr)[i]; \ + } \ +} while (0) + +/* + * Convenience wrapper around snprintf() to append at buf_pos in buf, + * updating buf_pos and returning the number of characters appended. + * On error buf_pos is not changed and return value is 0. + */ +static int __init __printf(4, 5) +append_fmt(char *buf, int *buf_pos, int buf_len, const char *val_fmt, ...) +{ + va_list ap; + int field_len; + + va_start(ap, val_fmt); + field_len = vsnprintf(buf + *buf_pos, buf_len - *buf_pos, val_fmt, ap); + va_end(ap); + + if (field_len < 0) + field_len = 0; + + *buf_pos += field_len; + + return field_len; +} + +/* + * Convenience function to append the field delimiter string + * to both the value string and format string buffers. + */ +static void __init append_delim(char *str_buf, int *str_buf_pos, int str_buf_len, + char *fmt_buf, int *fmt_buf_pos, int fmt_buf_len, + const char *delim_str) +{ + append_fmt(str_buf, str_buf_pos, str_buf_len, delim_str); + append_fmt(fmt_buf, fmt_buf_pos, fmt_buf_len, delim_str); +} + +#define test_array_8(fn, check_data, string, fmt, arr) \ +do { \ + BUILD_BUG_ON(ARRAY_SIZE(arr) != 8); \ + _test(fn, check_data, string, fmt, 8, \ + &(arr)[0], &(arr)[1], &(arr)[2], &(arr)[3], \ + &(arr)[4], &(arr)[5], &(arr)[6], &(arr)[7]); \ +} while (0) + +#define numbers_list_8(T, gen_fmt, field_sep, scan_fmt, fn) \ +do { \ + int i, pos = 0, fmt_pos = 0; \ + T expect[8], result[8]; \ + \ + fill_random_array(expect); \ + \ + for (i = 0; i < ARRAY_SIZE(expect); i++) { \ + if (i != 0) \ + append_delim(test_buffer, &pos, BUF_SIZE, \ + fmt_buffer, &fmt_pos, BUF_SIZE, \ + field_sep); \ + \ + append_fmt(test_buffer, &pos, BUF_SIZE, gen_fmt, expect[i]); \ + append_fmt(fmt_buffer, &fmt_pos, BUF_SIZE, "%%%s", scan_fmt); \ + } \ + \ + test_array_8(fn, expect, test_buffer, fmt_buffer, result); \ +} while (0) + +#define numbers_list_fix_width(T, gen_fmt, field_sep, width, scan_fmt, fn) \ +do { \ + char full_fmt[16]; \ + \ + snprintf(full_fmt, sizeof(full_fmt), "%u%s", width, scan_fmt); \ + numbers_list_8(T, gen_fmt, field_sep, full_fmt, fn); \ +} while (0) + +#define numbers_list_val_width(T, gen_fmt, field_sep, scan_fmt, fn) \ +do { \ + int i, val_len, pos = 0, fmt_pos = 0; \ + T expect[8], result[8]; \ + \ + fill_random_array(expect); \ + \ + for (i = 0; i < ARRAY_SIZE(expect); i++) { \ + if (i != 0) \ + append_delim(test_buffer, &pos, BUF_SIZE, \ + fmt_buffer, &fmt_pos, BUF_SIZE, field_sep);\ + \ + val_len = append_fmt(test_buffer, &pos, BUF_SIZE, gen_fmt, \ + expect[i]); \ + append_fmt(fmt_buffer, &fmt_pos, BUF_SIZE, \ + "%%%u%s", val_len, scan_fmt); \ + } \ + \ + test_array_8(fn, expect, test_buffer, fmt_buffer, result); \ +} while (0) + +static void __init numbers_list(const char *delim) +{ + numbers_list_8(unsigned long long, "%llu", delim, "llu", check_ull); + numbers_list_8(long long, "%lld", delim, "lld", check_ll); + numbers_list_8(long long, "%lld", delim, "lli", check_ll); + numbers_list_8(unsigned long long, "%llx", delim, "llx", check_ull); + numbers_list_8(unsigned long long, "0x%llx", delim, "llx", check_ull); + numbers_list_8(long long, "0x%llx", delim, "lli", check_ll); + + numbers_list_8(unsigned long, "%lu", delim, "lu", check_ulong); + numbers_list_8(long, "%ld", delim, "ld", check_long); + numbers_list_8(long, "%ld", delim, "li", check_long); + numbers_list_8(unsigned long, "%lx", delim, "lx", check_ulong); + numbers_list_8(unsigned long, "0x%lx", delim, "lx", check_ulong); + numbers_list_8(long, "0x%lx", delim, "li", check_long); + + numbers_list_8(unsigned int, "%u", delim, "u", check_uint); + numbers_list_8(int, "%d", delim, "d", check_int); + numbers_list_8(int, "%d", delim, "i", check_int); + numbers_list_8(unsigned int, "%x", delim, "x", check_uint); + numbers_list_8(unsigned int, "0x%x", delim, "x", check_uint); + numbers_list_8(int, "0x%x", delim, "i", check_int); + + numbers_list_8(unsigned short, "%hu", delim, "hu", check_ushort); + numbers_list_8(short, "%hd", delim, "hd", check_short); + numbers_list_8(short, "%hd", delim, "hi", check_short); + numbers_list_8(unsigned short, "%hx", delim, "hx", check_ushort); + numbers_list_8(unsigned short, "0x%hx", delim, "hx", check_ushort); + numbers_list_8(short, "0x%hx", delim, "hi", check_short); + + numbers_list_8(unsigned char, "%hhu", delim, "hhu", check_uchar); + numbers_list_8(signed char, "%hhd", delim, "hhd", check_char); + numbers_list_8(signed char, "%hhd", delim, "hhi", check_char); + numbers_list_8(unsigned char, "%hhx", delim, "hhx", check_uchar); + numbers_list_8(unsigned char, "0x%hhx", delim, "hhx", check_uchar); + numbers_list_8(signed char, "0x%hhx", delim, "hhi", check_char); +} + +/* + * List of numbers separated by delim. Each field width specifier is the + * maximum possible digits for the given type and base. + */ +static void __init numbers_list_field_width_typemax(const char *delim) +{ + numbers_list_fix_width(unsigned long long, "%llu", delim, 20, "llu", check_ull); + numbers_list_fix_width(long long, "%lld", delim, 20, "lld", check_ll); + numbers_list_fix_width(long long, "%lld", delim, 20, "lli", check_ll); + numbers_list_fix_width(unsigned long long, "%llx", delim, 16, "llx", check_ull); + numbers_list_fix_width(unsigned long long, "0x%llx", delim, 18, "llx", check_ull); + numbers_list_fix_width(long long, "0x%llx", delim, 18, "lli", check_ll); + +#if BITS_PER_LONG == 64 + numbers_list_fix_width(unsigned long, "%lu", delim, 20, "lu", check_ulong); + numbers_list_fix_width(long, "%ld", delim, 20, "ld", check_long); + numbers_list_fix_width(long, "%ld", delim, 20, "li", check_long); + numbers_list_fix_width(unsigned long, "%lx", delim, 16, "lx", check_ulong); + numbers_list_fix_width(unsigned long, "0x%lx", delim, 18, "lx", check_ulong); + numbers_list_fix_width(long, "0x%lx", delim, 18, "li", check_long); +#else + numbers_list_fix_width(unsigned long, "%lu", delim, 10, "lu", check_ulong); + numbers_list_fix_width(long, "%ld", delim, 11, "ld", check_long); + numbers_list_fix_width(long, "%ld", delim, 11, "li", check_long); + numbers_list_fix_width(unsigned long, "%lx", delim, 8, "lx", check_ulong); + numbers_list_fix_width(unsigned long, "0x%lx", delim, 10, "lx", check_ulong); + numbers_list_fix_width(long, "0x%lx", delim, 10, "li", check_long); +#endif + + numbers_list_fix_width(unsigned int, "%u", delim, 10, "u", check_uint); + numbers_list_fix_width(int, "%d", delim, 11, "d", check_int); + numbers_list_fix_width(int, "%d", delim, 11, "i", check_int); + numbers_list_fix_width(unsigned int, "%x", delim, 8, "x", check_uint); + numbers_list_fix_width(unsigned int, "0x%x", delim, 10, "x", check_uint); + numbers_list_fix_width(int, "0x%x", delim, 10, "i", check_int); + + numbers_list_fix_width(unsigned short, "%hu", delim, 5, "hu", check_ushort); + numbers_list_fix_width(short, "%hd", delim, 6, "hd", check_short); + numbers_list_fix_width(short, "%hd", delim, 6, "hi", check_short); + numbers_list_fix_width(unsigned short, "%hx", delim, 4, "hx", check_ushort); + numbers_list_fix_width(unsigned short, "0x%hx", delim, 6, "hx", check_ushort); + numbers_list_fix_width(short, "0x%hx", delim, 6, "hi", check_short); + + numbers_list_fix_width(unsigned char, "%hhu", delim, 3, "hhu", check_uchar); + numbers_list_fix_width(signed char, "%hhd", delim, 4, "hhd", check_char); + numbers_list_fix_width(signed char, "%hhd", delim, 4, "hhi", check_char); + numbers_list_fix_width(unsigned char, "%hhx", delim, 2, "hhx", check_uchar); + numbers_list_fix_width(unsigned char, "0x%hhx", delim, 4, "hhx", check_uchar); + numbers_list_fix_width(signed char, "0x%hhx", delim, 4, "hhi", check_char); +} + +/* + * List of numbers separated by delim. Each field width specifier is the + * exact length of the corresponding value digits in the string being scanned. + */ +static void __init numbers_list_field_width_val_width(const char *delim) +{ + numbers_list_val_width(unsigned long long, "%llu", delim, "llu", check_ull); + numbers_list_val_width(long long, "%lld", delim, "lld", check_ll); + numbers_list_val_width(long long, "%lld", delim, "lli", check_ll); + numbers_list_val_width(unsigned long long, "%llx", delim, "llx", check_ull); + numbers_list_val_width(unsigned long long, "0x%llx", delim, "llx", check_ull); + numbers_list_val_width(long long, "0x%llx", delim, "lli", check_ll); + + numbers_list_val_width(unsigned long, "%lu", delim, "lu", check_ulong); + numbers_list_val_width(long, "%ld", delim, "ld", check_long); + numbers_list_val_width(long, "%ld", delim, "li", check_long); + numbers_list_val_width(unsigned long, "%lx", delim, "lx", check_ulong); + numbers_list_val_width(unsigned long, "0x%lx", delim, "lx", check_ulong); + numbers_list_val_width(long, "0x%lx", delim, "li", check_long); + + numbers_list_val_width(unsigned int, "%u", delim, "u", check_uint); + numbers_list_val_width(int, "%d", delim, "d", check_int); + numbers_list_val_width(int, "%d", delim, "i", check_int); + numbers_list_val_width(unsigned int, "%x", delim, "x", check_uint); + numbers_list_val_width(unsigned int, "0x%x", delim, "x", check_uint); + numbers_list_val_width(int, "0x%x", delim, "i", check_int); + + numbers_list_val_width(unsigned short, "%hu", delim, "hu", check_ushort); + numbers_list_val_width(short, "%hd", delim, "hd", check_short); + numbers_list_val_width(short, "%hd", delim, "hi", check_short); + numbers_list_val_width(unsigned short, "%hx", delim, "hx", check_ushort); + numbers_list_val_width(unsigned short, "0x%hx", delim, "hx", check_ushort); + numbers_list_val_width(short, "0x%hx", delim, "hi", check_short); + + numbers_list_val_width(unsigned char, "%hhu", delim, "hhu", check_uchar); + numbers_list_val_width(signed char, "%hhd", delim, "hhd", check_char); + numbers_list_val_width(signed char, "%hhd", delim, "hhi", check_char); + numbers_list_val_width(unsigned char, "%hhx", delim, "hhx", check_uchar); + numbers_list_val_width(unsigned char, "0x%hhx", delim, "hhx", check_uchar); + numbers_list_val_width(signed char, "0x%hhx", delim, "hhi", check_char); +} + +/* + * Slice a continuous string of digits without field delimiters, containing + * numbers of varying length, using the field width to extract each group + * of digits. For example the hex values c0,3,bf01,303 would have a + * string representation of "c03bf01303" and extracted with "%2x%1x%4x%3x". + */ +static void __init numbers_slice(void) +{ + numbers_list_field_width_val_width(""); +} + +#define test_number_prefix(T, str, scan_fmt, expect0, expect1, n_args, fn) \ +do { \ + const T expect[2] = { expect0, expect1 }; \ + T result[2] = {~expect[0], ~expect[1]}; \ + \ + _test(fn, &expect, str, scan_fmt, n_args, &result[0], &result[1]); \ +} while (0) + +/* + * Number prefix is >= field width. + * Expected behaviour is derived from testing userland sscanf. + */ +static void __init numbers_prefix_overflow(void) +{ + /* + * Negative decimal with a field of width 1, should quit scanning + * and return 0. + */ + test_number_prefix(long long, "-1 1", "%1lld %lld", 0, 0, 0, check_ll); + test_number_prefix(long, "-1 1", "%1ld %ld", 0, 0, 0, check_long); + test_number_prefix(int, "-1 1", "%1d %d", 0, 0, 0, check_int); + test_number_prefix(short, "-1 1", "%1hd %hd", 0, 0, 0, check_short); + test_number_prefix(signed char, "-1 1", "%1hhd %hhd", 0, 0, 0, check_char); + + test_number_prefix(long long, "-1 1", "%1lli %lli", 0, 0, 0, check_ll); + test_number_prefix(long, "-1 1", "%1li %li", 0, 0, 0, check_long); + test_number_prefix(int, "-1 1", "%1i %i", 0, 0, 0, check_int); + test_number_prefix(short, "-1 1", "%1hi %hi", 0, 0, 0, check_short); + test_number_prefix(signed char, "-1 1", "%1hhi %hhi", 0, 0, 0, check_char); + + /* + * 0x prefix in a field of width 1: 0 is a valid digit so should + * convert. Next field scan starts at the 'x' which isn't a digit so + * scan quits with one field converted. + */ + test_number_prefix(unsigned long long, "0xA7", "%1llx%llx", 0, 0, 1, check_ull); + test_number_prefix(unsigned long, "0xA7", "%1lx%lx", 0, 0, 1, check_ulong); + test_number_prefix(unsigned int, "0xA7", "%1x%x", 0, 0, 1, check_uint); + test_number_prefix(unsigned short, "0xA7", "%1hx%hx", 0, 0, 1, check_ushort); + test_number_prefix(unsigned char, "0xA7", "%1hhx%hhx", 0, 0, 1, check_uchar); + test_number_prefix(long long, "0xA7", "%1lli%llx", 0, 0, 1, check_ll); + test_number_prefix(long, "0xA7", "%1li%lx", 0, 0, 1, check_long); + test_number_prefix(int, "0xA7", "%1i%x", 0, 0, 1, check_int); + test_number_prefix(short, "0xA7", "%1hi%hx", 0, 0, 1, check_short); + test_number_prefix(char, "0xA7", "%1hhi%hhx", 0, 0, 1, check_char); + + /* + * 0x prefix in a field of width 2 using %x conversion: first field + * converts to 0. Next field scan starts at the character after "0x". + * Both fields will convert. + */ + test_number_prefix(unsigned long long, "0xA7", "%2llx%llx", 0, 0xa7, 2, check_ull); + test_number_prefix(unsigned long, "0xA7", "%2lx%lx", 0, 0xa7, 2, check_ulong); + test_number_prefix(unsigned int, "0xA7", "%2x%x", 0, 0xa7, 2, check_uint); + test_number_prefix(unsigned short, "0xA7", "%2hx%hx", 0, 0xa7, 2, check_ushort); + test_number_prefix(unsigned char, "0xA7", "%2hhx%hhx", 0, 0xa7, 2, check_uchar); + + /* + * 0x prefix in a field of width 2 using %i conversion: first field + * converts to 0. Next field scan starts at the character after "0x", + * which will convert if can be intepreted as decimal but will fail + * if it contains any hex digits (since no 0x prefix). + */ + test_number_prefix(long long, "0x67", "%2lli%lli", 0, 67, 2, check_ll); + test_number_prefix(long, "0x67", "%2li%li", 0, 67, 2, check_long); + test_number_prefix(int, "0x67", "%2i%i", 0, 67, 2, check_int); + test_number_prefix(short, "0x67", "%2hi%hi", 0, 67, 2, check_short); + test_number_prefix(char, "0x67", "%2hhi%hhi", 0, 67, 2, check_char); + + test_number_prefix(long long, "0xA7", "%2lli%lli", 0, 0, 1, check_ll); + test_number_prefix(long, "0xA7", "%2li%li", 0, 0, 1, check_long); + test_number_prefix(int, "0xA7", "%2i%i", 0, 0, 1, check_int); + test_number_prefix(short, "0xA7", "%2hi%hi", 0, 0, 1, check_short); + test_number_prefix(char, "0xA7", "%2hhi%hhi", 0, 0, 1, check_char); +} + +#define _test_simple_strtoxx(T, fn, gen_fmt, expect, base) \ +do { \ + T got; \ + char *endp; \ + int len; \ + bool fail = false; \ + \ + total_tests++; \ + len = snprintf(test_buffer, BUF_SIZE, gen_fmt, expect); \ + got = (fn)(test_buffer, &endp, base); \ + pr_debug(#fn "(\"%s\", %d) -> " gen_fmt "\n", test_buffer, base, got); \ + if (got != (expect)) { \ + fail = true; \ + pr_warn(#fn "(\"%s\", %d): got " gen_fmt " expected " gen_fmt "\n", \ + test_buffer, base, got, expect); \ + } else if (endp != test_buffer + len) { \ + fail = true; \ + pr_warn(#fn "(\"%s\", %d) startp=0x%px got endp=0x%px expected 0x%px\n", \ + test_buffer, base, test_buffer, \ + test_buffer + len, endp); \ + } \ + \ + if (fail) \ + failed_tests++; \ +} while (0) + +#define test_simple_strtoxx(T, fn, gen_fmt, base) \ +do { \ + int i; \ + \ + for (i = 0; i < ARRAY_SIZE(numbers); i++) { \ + _test_simple_strtoxx(T, fn, gen_fmt, (T)numbers[i], base); \ + \ + if (is_signed_type(T)) \ + _test_simple_strtoxx(T, fn, gen_fmt, \ + -(T)numbers[i], base); \ + } \ +} while (0) + +static void __init test_simple_strtoull(void) +{ + test_simple_strtoxx(unsigned long long, simple_strtoull, "%llu", 10); + test_simple_strtoxx(unsigned long long, simple_strtoull, "%llu", 0); + test_simple_strtoxx(unsigned long long, simple_strtoull, "%llx", 16); + test_simple_strtoxx(unsigned long long, simple_strtoull, "0x%llx", 16); + test_simple_strtoxx(unsigned long long, simple_strtoull, "0x%llx", 0); +} + +static void __init test_simple_strtoll(void) +{ + test_simple_strtoxx(long long, simple_strtoll, "%lld", 10); + test_simple_strtoxx(long long, simple_strtoll, "%lld", 0); + test_simple_strtoxx(long long, simple_strtoll, "%llx", 16); + test_simple_strtoxx(long long, simple_strtoll, "0x%llx", 16); + test_simple_strtoxx(long long, simple_strtoll, "0x%llx", 0); +} + +static void __init test_simple_strtoul(void) +{ + test_simple_strtoxx(unsigned long, simple_strtoul, "%lu", 10); + test_simple_strtoxx(unsigned long, simple_strtoul, "%lu", 0); + test_simple_strtoxx(unsigned long, simple_strtoul, "%lx", 16); + test_simple_strtoxx(unsigned long, simple_strtoul, "0x%lx", 16); + test_simple_strtoxx(unsigned long, simple_strtoul, "0x%lx", 0); +} + +static void __init test_simple_strtol(void) +{ + test_simple_strtoxx(long, simple_strtol, "%ld", 10); + test_simple_strtoxx(long, simple_strtol, "%ld", 0); + test_simple_strtoxx(long, simple_strtol, "%lx", 16); + test_simple_strtoxx(long, simple_strtol, "0x%lx", 16); + test_simple_strtoxx(long, simple_strtol, "0x%lx", 0); +} + +/* Selection of common delimiters/separators between numbers in a string. */ +static const char * const number_delimiters[] __initconst = { + " ", ":", ",", "-", "/", +}; + +static void __init test_numbers(void) +{ + int i; + + /* String containing only one number. */ + numbers_simple(); + + /* String with multiple numbers separated by delimiter. */ + for (i = 0; i < ARRAY_SIZE(number_delimiters); i++) { + numbers_list(number_delimiters[i]); + + /* Field width may be longer than actual field digits. */ + numbers_list_field_width_typemax(number_delimiters[i]); + + /* Each field width exactly length of actual field digits. */ + numbers_list_field_width_val_width(number_delimiters[i]); + } + + /* Slice continuous sequence of digits using field widths. */ + numbers_slice(); + + numbers_prefix_overflow(); +} + +static void __init selftest(void) +{ + test_buffer = kmalloc(BUF_SIZE, GFP_KERNEL); + if (!test_buffer) + return; + + fmt_buffer = kmalloc(BUF_SIZE, GFP_KERNEL); + if (!fmt_buffer) { + kfree(test_buffer); + return; + } + + prandom_seed_state(&rnd_state, 3141592653589793238ULL); + + test_numbers(); + + test_simple_strtoull(); + test_simple_strtoll(); + test_simple_strtoul(); + test_simple_strtol(); + + kfree(fmt_buffer); + kfree(test_buffer); +} + +KSTM_MODULE_LOADERS(test_scanf); +MODULE_AUTHOR("Richard Fitzgerald "); +MODULE_LICENSE("GPL v2"); diff --git a/lib/vsprintf.c b/lib/vsprintf.c index f0c35d9b65bf..e5c7afbf7405 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -53,6 +53,31 @@ #include #include "kstrtox.h" +static unsigned long long simple_strntoull(const char *startp, size_t max_chars, + char **endp, unsigned int base) +{ + const char *cp; + unsigned long long result = 0ULL; + size_t prefix_chars; + unsigned int rv; + + cp = _parse_integer_fixup_radix(startp, &base); + prefix_chars = cp - startp; + if (prefix_chars < max_chars) { + rv = _parse_integer_limit(cp, base, &result, max_chars - prefix_chars); + /* FIXME */ + cp += (rv & ~KSTRTOX_OVERFLOW); + } else { + /* Field too short for prefix + digit, skip over without converting */ + cp = startp + max_chars; + } + + if (endp) + *endp = (char *)cp; + + return result; +} + /** * simple_strtoull - convert a string to an unsigned long long * @cp: The start of the string @@ -63,18 +88,7 @@ */ unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) { - unsigned long long result; - unsigned int rv; - - cp = _parse_integer_fixup_radix(cp, &base); - rv = _parse_integer(cp, base, &result); - /* FIXME */ - cp += (rv & ~KSTRTOX_OVERFLOW); - - if (endp) - *endp = (char *)cp; - - return result; + return simple_strntoull(cp, INT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoull); @@ -109,6 +123,21 @@ long simple_strtol(const char *cp, char **endp, unsigned int base) } EXPORT_SYMBOL(simple_strtol); +static long long simple_strntoll(const char *cp, size_t max_chars, char **endp, + unsigned int base) +{ + /* + * simple_strntoull() safely handles receiving max_chars==0 in the + * case cp[0] == '-' && max_chars == 1. + * If max_chars == 0 we can drop through and pass it to simple_strntoull() + * and the content of *cp is irrelevant. + */ + if (*cp == '-' && max_chars > 0) + return -simple_strntoull(cp + 1, max_chars - 1, endp, base); + + return simple_strntoull(cp, max_chars, endp, base); +} + /** * simple_strtoll - convert a string to a signed long long * @cp: The start of the string @@ -119,10 +148,7 @@ EXPORT_SYMBOL(simple_strtol); */ long long simple_strtoll(const char *cp, char **endp, unsigned int base) { - if (*cp == '-') - return -simple_strtoull(cp + 1, endp, base); - - return simple_strtoull(cp, endp, base); + return simple_strntoll(cp, INT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoll); @@ -1834,7 +1860,8 @@ char *rtc_str(char *buf, char *end, const struct rtc_time *tm, struct printf_spec spec, const char *fmt) { bool have_t = true, have_d = true; - bool raw = false; + bool raw = false, iso8601_separator = true; + bool found = true; int count = 2; if (check_pointer(&buf, end, tm, spec)) @@ -1851,14 +1878,25 @@ char *rtc_str(char *buf, char *end, const struct rtc_time *tm, break; } - raw = fmt[count] == 'r'; + do { + switch (fmt[count++]) { + case 'r': + raw = true; + break; + case 's': + iso8601_separator = false; + break; + default: + found = false; + break; + } + } while (found); if (have_d) buf = date_str(buf, end, tm, raw); if (have_d && have_t) { - /* Respect ISO 8601 */ if (buf < end) - *buf = 'T'; + *buf = iso8601_separator ? 'T' : ' '; buf++; } if (have_t) @@ -2186,7 +2224,7 @@ char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, bool no_hash_pointers __ro_after_init; EXPORT_SYMBOL_GPL(no_hash_pointers); -static int __init no_hash_pointers_enable(char *str) +int __init no_hash_pointers_enable(char *str) { if (no_hash_pointers) return 0; @@ -2298,7 +2336,7 @@ early_param("no_hash_pointers", no_hash_pointers_enable); * - 'd[234]' For a dentry name (optionally 2-4 last components) * - 'D[234]' Same as 'd' but for a struct file * - 'g' For block_device name (gendisk + partition number) - * - 't[RT][dt][r]' For time and date as represented by: + * - 't[RT][dt][r][s]' For time and date as represented by: * R struct rtc_time * T time64_t * - 'C' For a clock, it prints the name (Common Clock Framework) or address @@ -3565,8 +3603,12 @@ int vsscanf(const char *buf, const char *fmt, va_list args) str = skip_spaces(str); digit = *str; - if (is_sign && digit == '-') + if (is_sign && digit == '-') { + if (field_width == 1) + break; + digit = *(str + 1); + } if (!digit || (base == 16 && !isxdigit(digit)) @@ -3576,25 +3618,13 @@ int vsscanf(const char *buf, const char *fmt, va_list args) break; if (is_sign) - val.s = qualifier != 'L' ? - simple_strtol(str, &next, base) : - simple_strtoll(str, &next, base); + val.s = simple_strntoll(str, + field_width >= 0 ? field_width : INT_MAX, + &next, base); else - val.u = qualifier != 'L' ? - simple_strtoul(str, &next, base) : - simple_strtoull(str, &next, base); - - if (field_width > 0 && next - str > field_width) { - if (base == 0) - _parse_integer_fixup_radix(str, &base); - while (next - str > field_width) { - if (is_sign) - val.s = div_s64(val.s, base); - else - val.u = div_u64(val.u, base); - --next; - } - } + val.u = simple_strntoull(str, + field_width >= 0 ? field_width : INT_MAX, + &next, base); switch (qualifier) { case 'H': /* that's 'hh' in format */ diff --git a/mm/Kconfig b/mm/Kconfig index 02d44e3420f5..ded98fb859ab 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -19,7 +19,7 @@ choice config FLATMEM_MANUAL bool "Flat Memory" - depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE + depends on !ARCH_SPARSEMEM_ENABLE || ARCH_FLATMEM_ENABLE help This option is best suited for non-NUMA systems with flat address space. The FLATMEM is the most efficient @@ -32,21 +32,6 @@ config FLATMEM_MANUAL If unsure, choose this option (Flat Memory) over any other. -config DISCONTIGMEM_MANUAL - bool "Discontiguous Memory" - depends on ARCH_DISCONTIGMEM_ENABLE - help - This option provides enhanced support for discontiguous - memory systems, over FLATMEM. These systems have holes - in their physical address spaces, and this option provides - more efficient handling of these holes. - - Although "Discontiguous Memory" is still used by several - architectures, it is considered deprecated in favor of - "Sparse Memory". - - If unsure, choose "Sparse Memory" over this option. - config SPARSEMEM_MANUAL bool "Sparse Memory" depends on ARCH_SPARSEMEM_ENABLE @@ -62,30 +47,13 @@ config SPARSEMEM_MANUAL endchoice -config DISCONTIGMEM - def_bool y - depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL - config SPARSEMEM def_bool y depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL config FLATMEM def_bool y - depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL - -config FLAT_NODE_MEM_MAP - def_bool y - depends on !SPARSEMEM - -# -# Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's -# to represent different areas of memory. This variable allows -# those dependencies to exist individually. -# -config NEED_MULTIPLE_NODES - def_bool y - depends on DISCONTIGMEM || NUMA + depends on !SPARSEMEM || FLATMEM_MANUAL # # SPARSEMEM_EXTREME (which is the default) does some bootmem diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 576220acd686..271f2ca862c8 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -371,12 +371,16 @@ static void wb_exit(struct bdi_writeback *wb) #include /* - * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, and memcg->cgwb_list. - * bdi->cgwb_tree is also RCU protected. + * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, offline_cgwbs and + * memcg->cgwb_list. bdi->cgwb_tree is also RCU protected. */ static DEFINE_SPINLOCK(cgwb_lock); static struct workqueue_struct *cgwb_release_wq; +static LIST_HEAD(offline_cgwbs); +static void cleanup_offline_cgwbs_workfn(struct work_struct *work); +static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn); + static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, @@ -395,7 +399,13 @@ static void cgwb_release_workfn(struct work_struct *work) fprop_local_destroy_percpu(&wb->memcg_completions); percpu_ref_exit(&wb->refcnt); + + spin_lock_irq(&cgwb_lock); + list_del(&wb->offline_node); + spin_unlock_irq(&cgwb_lock); + wb_exit(wb); + WARN_ON_ONCE(!list_empty(&wb->b_attached)); kfree_rcu(wb, rcu); } @@ -413,6 +423,7 @@ static void cgwb_kill(struct bdi_writeback *wb) WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id)); list_del(&wb->memcg_node); list_del(&wb->blkcg_node); + list_add(&wb->offline_node, &offline_cgwbs); percpu_ref_kill(&wb->refcnt); } @@ -472,6 +483,7 @@ static int cgwb_create(struct backing_dev_info *bdi, wb->memcg_css = memcg_css; wb->blkcg_css = blkcg_css; + INIT_LIST_HEAD(&wb->b_attached); INIT_WORK(&wb->release_work, cgwb_release_workfn); set_bit(WB_registered, &wb->state); @@ -633,6 +645,54 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi) mutex_unlock(&bdi->cgwb_release_mutex); } +/* + * cleanup_offline_cgwbs_workfn - try to release dying cgwbs + * + * Try to release dying cgwbs by switching attached inodes to the nearest + * living ancestor's writeback. Processed wbs are placed at the end + * of the list to guarantee the forward progress. + */ +static void cleanup_offline_cgwbs_workfn(struct work_struct *work) +{ + struct bdi_writeback *wb; + LIST_HEAD(processed); + + spin_lock_irq(&cgwb_lock); + + while (!list_empty(&offline_cgwbs)) { + wb = list_first_entry(&offline_cgwbs, struct bdi_writeback, + offline_node); + list_move(&wb->offline_node, &processed); + + /* + * If wb is dirty, cleaning up the writeback by switching + * attached inodes will result in an effective removal of any + * bandwidth restrictions, which isn't the goal. Instead, + * it can be postponed until the next time, when all io + * will be likely completed. If in the meantime some inodes + * will get re-dirtied, they should be eventually switched to + * a new cgwb. + */ + if (wb_has_dirty_io(wb)) + continue; + + if (!wb_tryget(wb)) + continue; + + spin_unlock_irq(&cgwb_lock); + while (cleanup_offline_cgwb(wb)) + cond_resched(); + spin_lock_irq(&cgwb_lock); + + wb_put(wb); + } + + if (!list_empty(&processed)) + list_splice_tail(&processed, &offline_cgwbs); + + spin_unlock_irq(&cgwb_lock); +} + /** * wb_memcg_offline - kill all wb's associated with a memcg being offlined * @memcg: memcg being offlined @@ -649,6 +709,8 @@ void wb_memcg_offline(struct mem_cgroup *memcg) cgwb_kill(wb); memcg_cgwb_list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); + + queue_work(system_unbound_wq, &cleanup_offline_cgwbs_work); } /** diff --git a/mm/compaction.c b/mm/compaction.c index 725f564a5664..3a509fbf2bea 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1028,7 +1028,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (!TestClearPageLRU(page)) goto isolate_fail_put; - lruvec = mem_cgroup_page_lruvec(page, pgdat); + lruvec = mem_cgroup_page_lruvec(page); /* If we already hold the lock, we can skip some rechecking */ if (lruvec != locked) { diff --git a/mm/debug.c b/mm/debug.c index 0bdda8407f71..e73fe0a8ec3d 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -42,11 +42,10 @@ const struct trace_print_flags vmaflag_names[] = { {0, NULL} }; -void __dump_page(struct page *page, const char *reason) +static void __dump_page(struct page *page) { struct page *head = compound_head(page); struct address_space *mapping; - bool page_poisoned = PagePoisoned(page); bool compound = PageCompound(page); /* * Accessing the pageblock without the zone lock. It could change to @@ -58,16 +57,6 @@ void __dump_page(struct page *page, const char *reason) int mapcount; char *type = ""; - /* - * If struct page is poisoned don't access Page*() functions as that - * leads to recursive loop. Page*() check for poisoned pages, and calls - * dump_page() when detected. - */ - if (page_poisoned) { - pr_warn("page:%px is uninitialized and poisoned", page); - goto hex_only; - } - if (page < head || (page >= head + MAX_ORDER_NR_PAGES)) { /* * Corrupt page, so we cannot call page_mapping. Instead, do a @@ -173,8 +162,6 @@ out_mapping: pr_warn("%sflags: %#lx(%pGp)%s\n", type, head->flags, &head->flags, page_cma ? " CMA" : ""); - -hex_only: print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32, sizeof(unsigned long), page, sizeof(struct page), false); @@ -182,14 +169,16 @@ hex_only: print_hex_dump(KERN_WARNING, "head: ", DUMP_PREFIX_NONE, 32, sizeof(unsigned long), head, sizeof(struct page), false); - - if (reason) - pr_warn("page dumped because: %s\n", reason); } void dump_page(struct page *page, const char *reason) { - __dump_page(page, reason); + if (PagePoisoned(page)) + pr_warn("page:%p is uninitialized and poisoned", page); + else + __dump_page(page); + if (reason) + pr_warn("page dumped because: %s\n", reason); dump_page_owner(page); } EXPORT_SYMBOL(dump_page); diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 297d1b349c19..92bfc37300df 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -146,13 +146,14 @@ static void __init pte_savedwrite_tests(unsigned long pfn, pgprot_t prot) static void __init pmd_basic_tests(unsigned long pfn, int idx) { pgprot_t prot = protection_map[idx]; - pmd_t pmd = pfn_pmd(pfn, prot); unsigned long val = idx, *ptr = &val; + pmd_t pmd; if (!has_transparent_hugepage()) return; pr_debug("Validating PMD basic (%pGv)\n", ptr); + pmd = pfn_pmd(pfn, prot); /* * This test needs to be executed after the given page table entry @@ -185,7 +186,7 @@ static void __init pmd_advanced_tests(struct mm_struct *mm, unsigned long pfn, unsigned long vaddr, pgprot_t prot, pgtable_t pgtable) { - pmd_t pmd = pfn_pmd(pfn, prot); + pmd_t pmd; if (!has_transparent_hugepage()) return; @@ -232,9 +233,14 @@ static void __init pmd_advanced_tests(struct mm_struct *mm, static void __init pmd_leaf_tests(unsigned long pfn, pgprot_t prot) { - pmd_t pmd = pfn_pmd(pfn, prot); + pmd_t pmd; + + if (!has_transparent_hugepage()) + return; pr_debug("Validating PMD leaf\n"); + pmd = pfn_pmd(pfn, prot); + /* * PMD based THP is a leaf entry. */ @@ -267,12 +273,16 @@ static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot) static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) { - pmd_t pmd = pfn_pmd(pfn, prot); + pmd_t pmd; if (!IS_ENABLED(CONFIG_NUMA_BALANCING)) return; + if (!has_transparent_hugepage()) + return; + pr_debug("Validating PMD saved write\n"); + pmd = pfn_pmd(pfn, prot); WARN_ON(!pmd_savedwrite(pmd_mk_savedwrite(pmd_clear_savedwrite(pmd)))); WARN_ON(pmd_savedwrite(pmd_clear_savedwrite(pmd_mk_savedwrite(pmd)))); } @@ -281,13 +291,14 @@ static void __init pmd_savedwrite_tests(unsigned long pfn, pgprot_t prot) static void __init pud_basic_tests(struct mm_struct *mm, unsigned long pfn, int idx) { pgprot_t prot = protection_map[idx]; - pud_t pud = pfn_pud(pfn, prot); unsigned long val = idx, *ptr = &val; + pud_t pud; if (!has_transparent_hugepage()) return; pr_debug("Validating PUD basic (%pGv)\n", ptr); + pud = pfn_pud(pfn, prot); /* * This test needs to be executed after the given page table entry @@ -323,7 +334,7 @@ static void __init pud_advanced_tests(struct mm_struct *mm, unsigned long pfn, unsigned long vaddr, pgprot_t prot) { - pud_t pud = pfn_pud(pfn, prot); + pud_t pud; if (!has_transparent_hugepage()) return; @@ -332,6 +343,7 @@ static void __init pud_advanced_tests(struct mm_struct *mm, /* Align the address wrt HPAGE_PUD_SIZE */ vaddr &= HPAGE_PUD_MASK; + pud = pfn_pud(pfn, prot); set_pud_at(mm, vaddr, pudp, pud); pudp_set_wrprotect(mm, vaddr, pudp); pud = READ_ONCE(*pudp); @@ -370,9 +382,13 @@ static void __init pud_advanced_tests(struct mm_struct *mm, static void __init pud_leaf_tests(unsigned long pfn, pgprot_t prot) { - pud_t pud = pfn_pud(pfn, prot); + pud_t pud; + + if (!has_transparent_hugepage()) + return; pr_debug("Validating PUD leaf\n"); + pud = pfn_pud(pfn, prot); /* * PUD based THP is a leaf entry. */ @@ -654,12 +670,16 @@ static void __init pte_protnone_tests(unsigned long pfn, pgprot_t prot) #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void __init pmd_protnone_tests(unsigned long pfn, pgprot_t prot) { - pmd_t pmd = pmd_mkhuge(pfn_pmd(pfn, prot)); + pmd_t pmd; if (!IS_ENABLED(CONFIG_NUMA_BALANCING)) return; + if (!has_transparent_hugepage()) + return; + pr_debug("Validating PMD protnone\n"); + pmd = pmd_mkhuge(pfn_pmd(pfn, prot)); WARN_ON(!pmd_protnone(pmd)); WARN_ON(!pmd_present(pmd)); } @@ -679,18 +699,26 @@ static void __init pte_devmap_tests(unsigned long pfn, pgprot_t prot) #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void __init pmd_devmap_tests(unsigned long pfn, pgprot_t prot) { - pmd_t pmd = pfn_pmd(pfn, prot); + pmd_t pmd; + + if (!has_transparent_hugepage()) + return; pr_debug("Validating PMD devmap\n"); + pmd = pfn_pmd(pfn, prot); WARN_ON(!pmd_devmap(pmd_mkdevmap(pmd))); } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static void __init pud_devmap_tests(unsigned long pfn, pgprot_t prot) { - pud_t pud = pfn_pud(pfn, prot); + pud_t pud; + + if (!has_transparent_hugepage()) + return; pr_debug("Validating PUD devmap\n"); + pud = pfn_pud(pfn, prot); WARN_ON(!pud_devmap(pud_mkdevmap(pud))); } #else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ @@ -733,25 +761,33 @@ static void __init pte_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void __init pmd_soft_dirty_tests(unsigned long pfn, pgprot_t prot) { - pmd_t pmd = pfn_pmd(pfn, prot); + pmd_t pmd; if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) return; + if (!has_transparent_hugepage()) + return; + pr_debug("Validating PMD soft dirty\n"); + pmd = pfn_pmd(pfn, prot); WARN_ON(!pmd_soft_dirty(pmd_mksoft_dirty(pmd))); WARN_ON(pmd_soft_dirty(pmd_clear_soft_dirty(pmd))); } static void __init pmd_swap_soft_dirty_tests(unsigned long pfn, pgprot_t prot) { - pmd_t pmd = pfn_pmd(pfn, prot); + pmd_t pmd; if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) || !IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION)) return; + if (!has_transparent_hugepage()) + return; + pr_debug("Validating PMD swap soft dirty\n"); + pmd = pfn_pmd(pfn, prot); WARN_ON(!pmd_swp_soft_dirty(pmd_swp_mksoft_dirty(pmd))); WARN_ON(pmd_swp_soft_dirty(pmd_swp_clear_soft_dirty(pmd))); } @@ -780,6 +816,9 @@ static void __init pmd_swap_tests(unsigned long pfn, pgprot_t prot) swp_entry_t swp; pmd_t pmd; + if (!has_transparent_hugepage()) + return; + pr_debug("Validating PMD swap\n"); pmd = pfn_pmd(pfn, prot); swp = __pmd_to_swp_entry(pmd); diff --git a/mm/dmapool.c b/mm/dmapool.c index 16483f86360e..64b537b3ccb0 100644 --- a/mm/dmapool.c +++ b/mm/dmapool.c @@ -62,8 +62,7 @@ struct dma_page { /* cacheable header for 'allocation' bytes */ static DEFINE_MUTEX(pools_lock); static DEFINE_MUTEX(pools_reg_lock); -static ssize_t -show_pools(struct device *dev, struct device_attribute *attr, char *buf) +static ssize_t pools_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned temp; unsigned size; @@ -103,7 +102,7 @@ show_pools(struct device *dev, struct device_attribute *attr, char *buf) return PAGE_SIZE - size; } -static DEVICE_ATTR(pools, 0444, show_pools, NULL); +static DEVICE_ATTR_RO(pools); /** * dma_pool_create - Creates a pool of consistent memory blocks, for dma. diff --git a/mm/filemap.c b/mm/filemap.c index aa7d12c41907..23a3d0898351 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -872,7 +872,7 @@ noinline int __add_to_page_cache_locked(struct page *page, page->index = offset; if (!huge) { - error = mem_cgroup_charge(page, current->mm, gfp); + error = mem_cgroup_charge(page, NULL, gfp); if (error) goto error; charged = true; diff --git a/mm/gup.c b/mm/gup.c index 3ded6a5f26b2..8651309f8ec3 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -44,6 +44,23 @@ static void hpage_pincount_sub(struct page *page, int refs) atomic_sub(refs, compound_pincount_ptr(page)); } +/* Equivalent to calling put_page() @refs times. */ +static void put_page_refs(struct page *page, int refs) +{ +#ifdef CONFIG_DEBUG_VM + if (VM_WARN_ON_ONCE_PAGE(page_ref_count(page) < refs, page)) + return; +#endif + + /* + * Calling put_page() for each ref is unnecessarily slow. Only the last + * ref needs a put_page(). + */ + if (refs > 1) + page_ref_sub(page, refs - 1); + put_page(page); +} + /* * Return the compound head page with ref appropriately incremented, * or NULL if that failed. @@ -56,6 +73,21 @@ static inline struct page *try_get_compound_head(struct page *page, int refs) return NULL; if (unlikely(!page_cache_add_speculative(head, refs))) return NULL; + + /* + * At this point we have a stable reference to the head page; but it + * could be that between the compound_head() lookup and the refcount + * increment, the compound page was split, in which case we'd end up + * holding a reference on a page that has nothing to do with the page + * we were given anymore. + * So now that the head page is stable, recheck that the pages still + * belong together. + */ + if (unlikely(compound_head(page) != head)) { + put_page_refs(head, refs); + return NULL; + } + return head; } @@ -95,6 +127,14 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page, !is_pinnable_page(page))) return NULL; + /* + * CAUTION: Don't use compound_head() on the page before this + * point, the result won't be stable. + */ + page = try_get_compound_head(page, refs); + if (!page) + return NULL; + /* * When pinning a compound page of order > 1 (which is what * hpage_pincount_available() checks for), use an exact count to @@ -103,15 +143,10 @@ __maybe_unused struct page *try_grab_compound_head(struct page *page, * However, be sure to *also* increment the normal page refcount * field at least once, so that the page really is pinned. */ - if (!hpage_pincount_available(page)) - refs *= GUP_PIN_COUNTING_BIAS; - - page = try_get_compound_head(page, refs); - if (!page) - return NULL; - if (hpage_pincount_available(page)) hpage_pincount_add(page, refs); + else + page_ref_add(page, refs * (GUP_PIN_COUNTING_BIAS - 1)); mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, orig_refs); @@ -135,14 +170,7 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags) refs *= GUP_PIN_COUNTING_BIAS; } - VM_BUG_ON_PAGE(page_ref_count(page) < refs, page); - /* - * Calling put_page() for each ref is unnecessarily slow. Only the last - * ref needs a put_page(). - */ - if (refs > 1) - page_ref_sub(page, refs - 1); - put_page(page); + put_page_refs(page, refs); } /** @@ -392,6 +420,17 @@ void unpin_user_pages(struct page **pages, unsigned long npages) } EXPORT_SYMBOL(unpin_user_pages); +/* + * Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's + * lifecycle. Avoid setting the bit unless necessary, or it might cause write + * cache bouncing on large SMP machines for concurrent pinned gups. + */ +static inline void mm_set_has_pinned_flag(unsigned long *mm_flags) +{ + if (!test_bit(MMF_HAS_PINNED, mm_flags)) + set_bit(MMF_HAS_PINNED, mm_flags); +} + #ifdef CONFIG_MMU static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags) @@ -1293,7 +1332,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, } if (flags & FOLL_PIN) - atomic_set(&mm->has_pinned, 1); + mm_set_has_pinned_flag(&mm->flags); /* * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior @@ -2614,7 +2653,7 @@ static int internal_get_user_pages_fast(unsigned long start, return -EINVAL; if (gup_flags & FOLL_PIN) - atomic_set(¤t->mm->has_pinned, 1); + mm_set_has_pinned_flag(¤t->mm->flags); if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(¤t->mm->mmap_lock); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5ba5a0da6d57..103f1187043f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5938,6 +5938,8 @@ int get_hwpoison_huge_page(struct page *page, bool *hugetlb) *hugetlb = true; if (HPageFreed(page) || HPageMigratable(page)) ret = get_page_unless_zero(page); + else + ret = -EBUSY; } spin_unlock_irq(&hugetlb_lock); return ret; diff --git a/mm/internal.h b/mm/internal.h index e8fdb531f887..6ec2cea9926b 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -115,6 +115,11 @@ extern void putback_lru_page(struct page *page); */ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); +/* + * in mm/memcontrol.c: + */ +extern bool cgroup_memory_nokmem; + /* * in mm/page_alloc.c */ @@ -198,10 +203,10 @@ extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern int user_min_free_kbytes; -extern void free_unref_page(struct page *page); +extern void free_unref_page(struct page *page, unsigned int order); extern void free_unref_page_list(struct list_head *list); -extern void zone_pcp_update(struct zone *zone); +extern void zone_pcp_update(struct zone *zone, int cpu_online); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 9fe39a66388a..adcd9acaef61 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -37,5 +37,5 @@ CFLAGS_sw_tags.o := $(CC_FLAGS_KASAN_RUNTIME) obj-$(CONFIG_KASAN) := common.o report.o obj-$(CONFIG_KASAN_GENERIC) += init.o generic.o report_generic.o shadow.o quarantine.o -obj-$(CONFIG_KASAN_HW_TAGS) += hw_tags.o report_hw_tags.o -obj-$(CONFIG_KASAN_SW_TAGS) += init.o report_sw_tags.o shadow.o sw_tags.o +obj-$(CONFIG_KASAN_HW_TAGS) += hw_tags.o report_hw_tags.o tags.o report_tags.o +obj-$(CONFIG_KASAN_SW_TAGS) += init.o report_sw_tags.o shadow.o sw_tags.o tags.o report_tags.o diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 0ecd293af344..2baf121fb8c5 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -51,11 +51,14 @@ void kasan_enable_current(void) { current->kasan_depth++; } +EXPORT_SYMBOL(kasan_enable_current); void kasan_disable_current(void) { current->kasan_depth--; } +EXPORT_SYMBOL(kasan_disable_current); + #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ void __kasan_unpoison_range(const void *address, size_t size) @@ -328,6 +331,9 @@ static inline bool ____kasan_slab_free(struct kmem_cache *cache, void *object, u8 tag; void *tagged_object; + if (!kasan_arch_is_ready()) + return false; + tag = get_tag(object); tagged_object = object; object = kasan_reset_tag(object); diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index 53cbf28859b5..c3f5ba7a294a 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -163,6 +163,9 @@ static __always_inline bool check_region_inline(unsigned long addr, size_t size, bool write, unsigned long ret_ip) { + if (!kasan_arch_is_ready()) + return true; + if (unlikely(size == 0)) return true; diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c index ed5e5b833d61..4ea8c368b5b8 100644 --- a/mm/kasan/hw_tags.c +++ b/mm/kasan/hw_tags.c @@ -216,28 +216,6 @@ void __init kasan_init_hw_tags(void) pr_info("KernelAddressSanitizer initialized\n"); } -void kasan_set_free_info(struct kmem_cache *cache, - void *object, u8 tag) -{ - struct kasan_alloc_meta *alloc_meta; - - alloc_meta = kasan_get_alloc_meta(cache, object); - if (alloc_meta) - kasan_set_track(&alloc_meta->free_track[0], GFP_NOWAIT); -} - -struct kasan_track *kasan_get_free_track(struct kmem_cache *cache, - void *object, u8 tag) -{ - struct kasan_alloc_meta *alloc_meta; - - alloc_meta = kasan_get_alloc_meta(cache, object); - if (!alloc_meta) - return NULL; - - return &alloc_meta->free_track[0]; -} - void kasan_alloc_pages(struct page *page, unsigned int order, gfp_t flags) { /* diff --git a/mm/kasan/init.c b/mm/kasan/init.c index 348f31d15a97..cc64ed6858c6 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -41,7 +41,7 @@ static inline bool kasan_p4d_table(pgd_t pgd) } #endif #if CONFIG_PGTABLE_LEVELS > 3 -pud_t kasan_early_shadow_pud[PTRS_PER_PUD] __page_aligned_bss; +pud_t kasan_early_shadow_pud[MAX_PTRS_PER_PUD] __page_aligned_bss; static inline bool kasan_pud_table(p4d_t p4d) { return p4d_page(p4d) == virt_to_page(lm_alias(kasan_early_shadow_pud)); @@ -53,7 +53,7 @@ static inline bool kasan_pud_table(p4d_t p4d) } #endif #if CONFIG_PGTABLE_LEVELS > 2 -pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD] __page_aligned_bss; +pmd_t kasan_early_shadow_pmd[MAX_PTRS_PER_PMD] __page_aligned_bss; static inline bool kasan_pmd_table(pud_t pud) { return pud_page(pud) == virt_to_page(lm_alias(kasan_early_shadow_pmd)); @@ -64,7 +64,7 @@ static inline bool kasan_pmd_table(pud_t pud) return false; } #endif -pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS] +pte_t kasan_early_shadow_pte[MAX_PTRS_PER_PTE + PTE_HWTABLE_PTRS] __page_aligned_bss; static inline bool kasan_pte_table(pmd_t pmd) diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 8f450bc28045..98e3059bfea4 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -153,7 +153,7 @@ struct kasan_track { depot_stack_handle_t stack; }; -#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY +#if defined(CONFIG_KASAN_TAGS_IDENTIFY) && defined(CONFIG_KASAN_SW_TAGS) #define KASAN_NR_FREE_STACKS 5 #else #define KASAN_NR_FREE_STACKS 1 @@ -170,7 +170,7 @@ struct kasan_alloc_meta { #else struct kasan_track free_track[KASAN_NR_FREE_STACKS]; #endif -#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY +#ifdef CONFIG_KASAN_TAGS_IDENTIFY u8 free_pointer_tag[KASAN_NR_FREE_STACKS]; u8 free_track_idx; #endif @@ -449,6 +449,12 @@ static inline void kasan_poison_last_granule(const void *address, size_t size) { #endif /* CONFIG_KASAN_GENERIC */ +#ifndef kasan_arch_is_ready +static inline bool kasan_arch_is_ready(void) { return true; } +#elif !defined(CONFIG_KASAN_GENERIC) || !defined(CONFIG_KASAN_OUTLINE) +#error kasan_arch_is_ready only works in KASAN generic outline mode! +#endif + /* * Exported functions for interfaces called from assembly or from generated * code. Declarations here to avoid warning about missing declarations. diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 14bd51ea2348..8fff1825b22c 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -230,7 +230,7 @@ static void print_address_description(void *addr, u8 tag) { struct page *page = kasan_addr_to_page(addr); - dump_stack(); + dump_stack_lvl(KERN_ERR); pr_err("\n"); if (page && PageSlab(page)) { @@ -375,7 +375,7 @@ void kasan_report_async(void) pr_err("BUG: KASAN: invalid-access\n"); pr_err("Asynchronous mode enabled: no access details available\n"); pr_err("\n"); - dump_stack(); + dump_stack_lvl(KERN_ERR); end_report(&flags, 0); } #endif /* CONFIG_KASAN_HW_TAGS */ @@ -420,7 +420,7 @@ static void __kasan_report(unsigned long addr, size_t size, bool is_write, pr_err("\n"); print_memory_metadata(info.first_bad_addr); } else { - dump_stack(); + dump_stack_lvl(KERN_ERR); } end_report(&flags, addr); diff --git a/mm/kasan/report_hw_tags.c b/mm/kasan/report_hw_tags.c index 42b2168755d6..5dbbbb930e7a 100644 --- a/mm/kasan/report_hw_tags.c +++ b/mm/kasan/report_hw_tags.c @@ -15,11 +15,6 @@ #include "kasan.h" -const char *kasan_get_bug_type(struct kasan_access_info *info) -{ - return "invalid-access"; -} - void *kasan_find_first_bad_addr(void *addr, size_t size) { return kasan_reset_tag(addr); diff --git a/mm/kasan/report_sw_tags.c b/mm/kasan/report_sw_tags.c index 3d20d3451d9e..d2298c357834 100644 --- a/mm/kasan/report_sw_tags.c +++ b/mm/kasan/report_sw_tags.c @@ -29,49 +29,6 @@ #include "kasan.h" #include "../slab.h" -const char *kasan_get_bug_type(struct kasan_access_info *info) -{ -#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY - struct kasan_alloc_meta *alloc_meta; - struct kmem_cache *cache; - struct page *page; - const void *addr; - void *object; - u8 tag; - int i; - - tag = get_tag(info->access_addr); - addr = kasan_reset_tag(info->access_addr); - page = kasan_addr_to_page(addr); - if (page && PageSlab(page)) { - cache = page->slab_cache; - object = nearest_obj(cache, page, (void *)addr); - alloc_meta = kasan_get_alloc_meta(cache, object); - - if (alloc_meta) { - for (i = 0; i < KASAN_NR_FREE_STACKS; i++) { - if (alloc_meta->free_pointer_tag[i] == tag) - return "use-after-free"; - } - } - return "out-of-bounds"; - } - -#endif - /* - * If access_size is a negative number, then it has reason to be - * defined as out-of-bounds bug type. - * - * Casting negative numbers to size_t would indeed turn up as - * a large size_t and its value will be larger than ULONG_MAX/2, - * so that this can qualify as out-of-bounds. - */ - if (info->access_addr + info->access_size < info->access_addr) - return "out-of-bounds"; - - return "invalid-access"; -} - void *kasan_find_first_bad_addr(void *addr, size_t size) { u8 tag = get_tag(addr); diff --git a/mm/kasan/report_tags.c b/mm/kasan/report_tags.c new file mode 100644 index 000000000000..8a319fc16dab --- /dev/null +++ b/mm/kasan/report_tags.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Copyright (c) 2020 Google, Inc. + */ + +#include "kasan.h" +#include "../slab.h" + +const char *kasan_get_bug_type(struct kasan_access_info *info) +{ +#ifdef CONFIG_KASAN_TAGS_IDENTIFY + struct kasan_alloc_meta *alloc_meta; + struct kmem_cache *cache; + struct page *page; + const void *addr; + void *object; + u8 tag; + int i; + + tag = get_tag(info->access_addr); + addr = kasan_reset_tag(info->access_addr); + page = kasan_addr_to_page(addr); + if (page && PageSlab(page)) { + cache = page->slab_cache; + object = nearest_obj(cache, page, (void *)addr); + alloc_meta = kasan_get_alloc_meta(cache, object); + + if (alloc_meta) { + for (i = 0; i < KASAN_NR_FREE_STACKS; i++) { + if (alloc_meta->free_pointer_tag[i] == tag) + return "use-after-free"; + } + } + return "out-of-bounds"; + } +#endif + + /* + * If access_size is a negative number, then it has reason to be + * defined as out-of-bounds bug type. + * + * Casting negative numbers to size_t would indeed turn up as + * a large size_t and its value will be larger than ULONG_MAX/2, + * so that this can qualify as out-of-bounds. + */ + if (info->access_addr + info->access_size < info->access_addr) + return "out-of-bounds"; + + return "invalid-access"; +} diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 082ee5b6d9a1..8d95ee52d019 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -73,6 +73,9 @@ void kasan_poison(const void *addr, size_t size, u8 value, bool init) { void *shadow_start, *shadow_end; + if (!kasan_arch_is_ready()) + return; + /* * Perform shadow offset calculation based on untagged address, as * some of the callers (e.g. kasan_poison_object_data) pass tagged @@ -99,6 +102,9 @@ EXPORT_SYMBOL(kasan_poison); #ifdef CONFIG_KASAN_GENERIC void kasan_poison_last_granule(const void *addr, size_t size) { + if (!kasan_arch_is_ready()) + return; + if (size & KASAN_GRANULE_MASK) { u8 *shadow = (u8 *)kasan_mem_to_shadow(addr + size); *shadow = size & KASAN_GRANULE_MASK; diff --git a/mm/kasan/sw_tags.c b/mm/kasan/sw_tags.c index 9362938abbfa..bd3f540feb47 100644 --- a/mm/kasan/sw_tags.c +++ b/mm/kasan/sw_tags.c @@ -167,47 +167,6 @@ void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size) } EXPORT_SYMBOL(__hwasan_tag_memory); -void kasan_set_free_info(struct kmem_cache *cache, - void *object, u8 tag) -{ - struct kasan_alloc_meta *alloc_meta; - u8 idx = 0; - - alloc_meta = kasan_get_alloc_meta(cache, object); - if (!alloc_meta) - return; - -#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY - idx = alloc_meta->free_track_idx; - alloc_meta->free_pointer_tag[idx] = tag; - alloc_meta->free_track_idx = (idx + 1) % KASAN_NR_FREE_STACKS; -#endif - - kasan_set_track(&alloc_meta->free_track[idx], GFP_NOWAIT); -} - -struct kasan_track *kasan_get_free_track(struct kmem_cache *cache, - void *object, u8 tag) -{ - struct kasan_alloc_meta *alloc_meta; - int i = 0; - - alloc_meta = kasan_get_alloc_meta(cache, object); - if (!alloc_meta) - return NULL; - -#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY - for (i = 0; i < KASAN_NR_FREE_STACKS; i++) { - if (alloc_meta->free_pointer_tag[i] == tag) - break; - } - if (i == KASAN_NR_FREE_STACKS) - i = alloc_meta->free_track_idx; -#endif - - return &alloc_meta->free_track[i]; -} - void kasan_tag_mismatch(unsigned long addr, unsigned long access_info, unsigned long ret_ip) { diff --git a/mm/kasan/tags.c b/mm/kasan/tags.c new file mode 100644 index 000000000000..8f48b9502a17 --- /dev/null +++ b/mm/kasan/tags.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains common tag-based KASAN code. + * + * Copyright (c) 2018 Google, Inc. + * Copyright (c) 2020 Google, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "kasan.h" + +void kasan_set_free_info(struct kmem_cache *cache, + void *object, u8 tag) +{ + struct kasan_alloc_meta *alloc_meta; + u8 idx = 0; + + alloc_meta = kasan_get_alloc_meta(cache, object); + if (!alloc_meta) + return; + +#ifdef CONFIG_KASAN_TAGS_IDENTIFY + idx = alloc_meta->free_track_idx; + alloc_meta->free_pointer_tag[idx] = tag; + alloc_meta->free_track_idx = (idx + 1) % KASAN_NR_FREE_STACKS; +#endif + + kasan_set_track(&alloc_meta->free_track[idx], GFP_NOWAIT); +} + +struct kasan_track *kasan_get_free_track(struct kmem_cache *cache, + void *object, u8 tag) +{ + struct kasan_alloc_meta *alloc_meta; + int i = 0; + + alloc_meta = kasan_get_alloc_meta(cache, object); + if (!alloc_meta) + return NULL; + +#ifdef CONFIG_KASAN_TAGS_IDENTIFY + for (i = 0; i < KASAN_NR_FREE_STACKS; i++) { + if (alloc_meta->free_pointer_tag[i] == tag) + break; + } + if (i == KASAN_NR_FREE_STACKS) + i = alloc_meta->free_track_idx; +#endif + + return &alloc_meta->free_track[i]; +} diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index 4acf4251ee04..7f24b9bcb2ec 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -197,7 +197,7 @@ static void test_cache_destroy(void) static inline size_t kmalloc_cache_alignment(size_t size) { - return kmalloc_caches[kmalloc_type(GFP_KERNEL)][kmalloc_index(size)]->align; + return kmalloc_caches[kmalloc_type(GFP_KERNEL)][__kmalloc_index(size, false)]->align; } /* Must always inline to match stack trace against caller. */ @@ -267,7 +267,8 @@ static void *test_alloc(struct kunit *test, size_t size, gfp_t gfp, enum allocat if (is_kfence_address(alloc)) { struct page *page = virt_to_head_page(alloc); - struct kmem_cache *s = test_cache ?: kmalloc_caches[kmalloc_type(GFP_KERNEL)][kmalloc_index(size)]; + struct kmem_cache *s = test_cache ?: + kmalloc_caches[kmalloc_type(GFP_KERNEL)][__kmalloc_index(size, false)]; /* * Verify that various helpers return the right values diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 92a2d4885808..228a2fbe0657 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -219,7 +219,7 @@ static struct task_struct *scan_thread; static unsigned long jiffies_min_age; static unsigned long jiffies_last_scan; /* delay between automatic memory scannings */ -static signed long jiffies_scan_wait; +static unsigned long jiffies_scan_wait; /* enables or disables the task stacks scanning */ static int kmemleak_stack_scan = 1; /* protects the memory scanning, parameters and debug/kmemleak file access */ @@ -1567,7 +1567,7 @@ static int kmemleak_scan_thread(void *arg) } while (!kthread_should_stop()) { - signed long timeout = jiffies_scan_wait; + signed long timeout = READ_ONCE(jiffies_scan_wait); mutex_lock(&scan_mutex); kmemleak_scan(); @@ -1807,14 +1807,20 @@ static ssize_t kmemleak_write(struct file *file, const char __user *user_buf, else if (strncmp(buf, "scan=off", 8) == 0) stop_scan_thread(); else if (strncmp(buf, "scan=", 5) == 0) { - unsigned long secs; + unsigned secs; + unsigned long msecs; - ret = kstrtoul(buf + 5, 0, &secs); + ret = kstrtouint(buf + 5, 0, &secs); if (ret < 0) goto out; + + msecs = secs * MSEC_PER_SEC; + if (msecs > UINT_MAX) + msecs = UINT_MAX; + stop_scan_thread(); - if (secs) { - jiffies_scan_wait = msecs_to_jiffies(secs * 1000); + if (msecs) { + WRITE_ONCE(jiffies_scan_wait, msecs_to_jiffies(msecs)); start_scan_thread(); } } else if (strncmp(buf, "scan", 4) == 0) diff --git a/mm/ksm.c b/mm/ksm.c index 2f3aaeb34a42..3fa9bc8a67cf 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -521,10 +521,8 @@ static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm, struct vm_area_struct *vma; if (ksm_test_exit(mm)) return NULL; - vma = find_vma(mm, addr); - if (!vma || vma->vm_start > addr) - return NULL; - if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) + vma = vma_lookup(mm, addr); + if (!vma || !(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) return NULL; return vma; } diff --git a/mm/memblock.c b/mm/memblock.c index ab267a3316ac..ab54f0a49ff2 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -92,7 +92,7 @@ * system initialization completes. */ -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA struct pglist_data __refdata contig_page_data; EXPORT_SYMBOL(contig_page_data); #endif @@ -607,7 +607,7 @@ repeat: * area, insert that portion. */ if (rbase > base) { -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA WARN_ON(nid != memblock_get_region_node(rgn)); #endif WARN_ON(flags != rgn->flags); @@ -1205,7 +1205,7 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid, int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid) { -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA int start_rgn, end_rgn; int i, ret; @@ -1850,7 +1850,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type) size = rgn->size; end = base + size - 1; flags = rgn->flags; -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA if (memblock_get_region_node(rgn) != MAX_NUMNODES) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 64ada9e650a5..4ee243ce6135 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -78,12 +78,13 @@ struct mem_cgroup *root_mem_cgroup __read_mostly; /* Active memory cgroup to use from an interrupt context */ DEFINE_PER_CPU(struct mem_cgroup *, int_active_memcg); +EXPORT_PER_CPU_SYMBOL_GPL(int_active_memcg); /* Socket memory accounting disabled? */ static bool cgroup_memory_nosocket; /* Kernel memory accounting disabled? */ -static bool cgroup_memory_nokmem; +bool cgroup_memory_nokmem; /* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP @@ -261,7 +262,6 @@ static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg, static void obj_cgroup_release(struct percpu_ref *ref) { struct obj_cgroup *objcg = container_of(ref, struct obj_cgroup, refcnt); - struct mem_cgroup *memcg; unsigned int nr_bytes; unsigned int nr_pages; unsigned long flags; @@ -290,12 +290,11 @@ static void obj_cgroup_release(struct percpu_ref *ref) WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1)); nr_pages = nr_bytes >> PAGE_SHIFT; - spin_lock_irqsave(&css_set_lock, flags); - memcg = obj_cgroup_memcg(objcg); if (nr_pages) obj_cgroup_uncharge_pages(objcg, nr_pages); + + spin_lock_irqsave(&css_set_lock, flags); list_del(&objcg->list); - mem_cgroup_put(memcg); spin_unlock_irqrestore(&css_set_lock, flags); percpu_ref_exit(ref); @@ -330,17 +329,12 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg, spin_lock_irq(&css_set_lock); - /* Move active objcg to the parent's list */ - xchg(&objcg->memcg, parent); - css_get(&parent->css); - list_add(&objcg->list, &parent->objcg_list); - - /* Move already reparented objcgs to the parent's list */ - list_for_each_entry(iter, &memcg->objcg_list, list) { - css_get(&parent->css); - xchg(&iter->memcg, parent); - css_put(&memcg->css); - } + /* 1) Ready to reparent active objcg. */ + list_add(&objcg->list, &memcg->objcg_list); + /* 2) Reparent active objcg and already reparented objcgs to parent. */ + list_for_each_entry(iter, &memcg->objcg_list, list) + WRITE_ONCE(iter->memcg, parent); + /* 3) Move already reparented objcgs to the parent's list */ list_splice(&memcg->objcg_list, &parent->objcg_list); spin_unlock_irq(&css_set_lock); @@ -782,6 +776,24 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) rcu_read_unlock(); } +/* + * mod_objcg_mlstate() may be called with irq enabled, so + * mod_memcg_lruvec_state() should be used. + */ +static inline void mod_objcg_mlstate(struct obj_cgroup *objcg, + struct pglist_data *pgdat, + enum node_stat_item idx, int nr) +{ + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + lruvec = mem_cgroup_lruvec(memcg, pgdat); + mod_memcg_lruvec_state(lruvec, idx, nr); + rcu_read_unlock(); +} + /** * __count_memcg_events - account VM events in a cgroup * @memcg: the memory cgroup @@ -886,13 +898,24 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) } EXPORT_SYMBOL(mem_cgroup_from_task); +static __always_inline struct mem_cgroup *active_memcg(void) +{ + if (in_interrupt()) + return this_cpu_read(int_active_memcg); + else + return current->active_memcg; +} + /** * get_mem_cgroup_from_mm: Obtain a reference on given mm_struct's memcg. * @mm: mm from which memcg should be extracted. It can be NULL. * - * Obtain a reference on mm->memcg and returns it if successful. Otherwise - * root_mem_cgroup is returned. However if mem_cgroup is disabled, NULL is - * returned. + * Obtain a reference on mm->memcg and returns it if successful. If mm + * is NULL, then the memcg is chosen as follows: + * 1) The active memcg, if set. + * 2) current->mm->memcg, if available + * 3) root memcg + * If mem_cgroup is disabled, NULL is returned. */ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { @@ -901,34 +924,38 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) if (mem_cgroup_disabled()) return NULL; + /* + * Page cache insertions can happen without an + * actual mm context, e.g. during disk probing + * on boot, loopback IO, acct() writes etc. + * + * No need to css_get on root memcg as the reference + * counting is disabled on the root level in the + * cgroup core. See CSS_NO_REF. + */ + if (unlikely(!mm)) { + memcg = active_memcg(); + if (unlikely(memcg)) { + /* remote memcg must hold a ref */ + css_get(&memcg->css); + return memcg; + } + mm = current->mm; + if (unlikely(!mm)) + return root_mem_cgroup; + } + rcu_read_lock(); do { - /* - * Page cache insertions can happen without an - * actual mm context, e.g. during disk probing - * on boot, loopback IO, acct() writes etc. - */ - if (unlikely(!mm)) + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) memcg = root_mem_cgroup; - else { - memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (unlikely(!memcg)) - memcg = root_mem_cgroup; - } } while (!css_tryget(&memcg->css)); rcu_read_unlock(); return memcg; } EXPORT_SYMBOL(get_mem_cgroup_from_mm); -static __always_inline struct mem_cgroup *active_memcg(void) -{ - if (in_interrupt()) - return this_cpu_read(int_active_memcg); - else - return current->active_memcg; -} - static __always_inline bool memcg_kmem_bypass(void) { /* Allow remote memcg charging from any context. */ @@ -1178,9 +1205,8 @@ void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) struct lruvec *lock_page_lruvec(struct page *page) { struct lruvec *lruvec; - struct pglist_data *pgdat = page_pgdat(page); - lruvec = mem_cgroup_page_lruvec(page, pgdat); + lruvec = mem_cgroup_page_lruvec(page); spin_lock(&lruvec->lru_lock); lruvec_memcg_debug(lruvec, page); @@ -1191,9 +1217,8 @@ struct lruvec *lock_page_lruvec(struct page *page) struct lruvec *lock_page_lruvec_irq(struct page *page) { struct lruvec *lruvec; - struct pglist_data *pgdat = page_pgdat(page); - lruvec = mem_cgroup_page_lruvec(page, pgdat); + lruvec = mem_cgroup_page_lruvec(page); spin_lock_irq(&lruvec->lru_lock); lruvec_memcg_debug(lruvec, page); @@ -1204,9 +1229,8 @@ struct lruvec *lock_page_lruvec_irq(struct page *page) struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags) { struct lruvec *lruvec; - struct pglist_data *pgdat = page_pgdat(page); - lruvec = mem_cgroup_page_lruvec(page, pgdat); + lruvec = mem_cgroup_page_lruvec(page); spin_lock_irqsave(&lruvec->lru_lock, *flags); lruvec_memcg_debug(lruvec, page); @@ -2040,14 +2064,23 @@ void unlock_page_memcg(struct page *page) } EXPORT_SYMBOL(unlock_page_memcg); +struct obj_stock { +#ifdef CONFIG_MEMCG_KMEM + struct obj_cgroup *cached_objcg; + struct pglist_data *cached_pgdat; + unsigned int nr_bytes; + int nr_slab_reclaimable_b; + int nr_slab_unreclaimable_b; +#else + int dummy[0]; +#endif +}; + struct memcg_stock_pcp { struct mem_cgroup *cached; /* this never be root cgroup */ unsigned int nr_pages; - -#ifdef CONFIG_MEMCG_KMEM - struct obj_cgroup *cached_objcg; - unsigned int nr_bytes; -#endif + struct obj_stock task_obj; + struct obj_stock irq_obj; struct work_struct work; unsigned long flags; @@ -2057,12 +2090,12 @@ static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock); static DEFINE_MUTEX(percpu_charge_mutex); #ifdef CONFIG_MEMCG_KMEM -static void drain_obj_stock(struct memcg_stock_pcp *stock); +static void drain_obj_stock(struct obj_stock *stock); static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, struct mem_cgroup *root_memcg); #else -static inline void drain_obj_stock(struct memcg_stock_pcp *stock) +static inline void drain_obj_stock(struct obj_stock *stock) { } static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, @@ -2072,6 +2105,41 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, } #endif +/* + * Most kmem_cache_alloc() calls are from user context. The irq disable/enable + * sequence used in this case to access content from object stock is slow. + * To optimize for user context access, there are now two object stocks for + * task context and interrupt context access respectively. + * + * The task context object stock can be accessed by disabling preemption only + * which is cheap in non-preempt kernel. The interrupt context object stock + * can only be accessed after disabling interrupt. User context code can + * access interrupt object stock, but not vice versa. + */ +static inline struct obj_stock *get_obj_stock(unsigned long *pflags) +{ + struct memcg_stock_pcp *stock; + + if (likely(in_task())) { + *pflags = 0UL; + preempt_disable(); + stock = this_cpu_ptr(&memcg_stock); + return &stock->task_obj; + } + + local_irq_save(*pflags); + stock = this_cpu_ptr(&memcg_stock); + return &stock->irq_obj; +} + +static inline void put_obj_stock(unsigned long flags) +{ + if (likely(in_task())) + preempt_enable(); + else + local_irq_restore(flags); +} + /** * consume_stock: Try to consume stocked charge on this cpu. * @memcg: memcg to consume from. @@ -2138,7 +2206,9 @@ static void drain_local_stock(struct work_struct *dummy) local_irq_save(flags); stock = this_cpu_ptr(&memcg_stock); - drain_obj_stock(stock); + drain_obj_stock(&stock->irq_obj); + if (in_task()) + drain_obj_stock(&stock->task_obj); drain_stock(stock); clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); @@ -2504,8 +2574,8 @@ out: css_put(&memcg->css); } -static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, - unsigned int nr_pages) +static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask, + unsigned int nr_pages) { unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages); int nr_retries = MAX_RECLAIM_RETRIES; @@ -2517,8 +2587,6 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, bool drained = false; unsigned long pflags; - if (mem_cgroup_is_root(memcg)) - return 0; retry: if (consume_stock(memcg, nr_pages)) return 0; @@ -2698,6 +2766,15 @@ done_restock: return 0; } +static inline int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, + unsigned int nr_pages) +{ + if (mem_cgroup_is_root(memcg)) + return 0; + + return try_charge_memcg(memcg, gfp_mask, nr_pages); +} + #if defined(CONFIG_MEMCG_KMEM) || defined(CONFIG_MMU) static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) { @@ -2739,6 +2816,13 @@ retry: } #ifdef CONFIG_MEMCG_KMEM +/* + * The allocated objcg pointers array is not accounted directly. + * Moreover, it should not come from DMA buffer and is not readily + * reclaimable. So those GFP bits should be masked off. + */ +#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT) + int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, gfp_t gfp, bool new_page) { @@ -2746,6 +2830,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, unsigned long memcg_data; void *vec; + gfp &= ~OBJCGS_CLEAR_MASK; vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp, page_to_nid(page)); if (!vec) @@ -2925,7 +3010,7 @@ static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp, memcg = get_mem_cgroup_from_objcg(objcg); - ret = try_charge(memcg, gfp, nr_pages); + ret = try_charge_memcg(memcg, gfp, nr_pages); if (ret) goto out; @@ -2995,26 +3080,81 @@ void __memcg_kmem_uncharge_page(struct page *page, int order) obj_cgroup_put(objcg); } +void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, + enum node_stat_item idx, int nr) +{ + unsigned long flags; + struct obj_stock *stock = get_obj_stock(&flags); + int *bytes; + + /* + * Save vmstat data in stock and skip vmstat array update unless + * accumulating over a page of vmstat data or when pgdat or idx + * changes. + */ + if (stock->cached_objcg != objcg) { + drain_obj_stock(stock); + obj_cgroup_get(objcg); + stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes) + ? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0; + stock->cached_objcg = objcg; + stock->cached_pgdat = pgdat; + } else if (stock->cached_pgdat != pgdat) { + /* Flush the existing cached vmstat data */ + if (stock->nr_slab_reclaimable_b) { + mod_objcg_mlstate(objcg, pgdat, NR_SLAB_RECLAIMABLE_B, + stock->nr_slab_reclaimable_b); + stock->nr_slab_reclaimable_b = 0; + } + if (stock->nr_slab_unreclaimable_b) { + mod_objcg_mlstate(objcg, pgdat, NR_SLAB_UNRECLAIMABLE_B, + stock->nr_slab_unreclaimable_b); + stock->nr_slab_unreclaimable_b = 0; + } + stock->cached_pgdat = pgdat; + } + + bytes = (idx == NR_SLAB_RECLAIMABLE_B) ? &stock->nr_slab_reclaimable_b + : &stock->nr_slab_unreclaimable_b; + /* + * Even for large object >= PAGE_SIZE, the vmstat data will still be + * cached locally at least once before pushing it out. + */ + if (!*bytes) { + *bytes = nr; + nr = 0; + } else { + *bytes += nr; + if (abs(*bytes) > PAGE_SIZE) { + nr = *bytes; + *bytes = 0; + } else { + nr = 0; + } + } + if (nr) + mod_objcg_mlstate(objcg, pgdat, idx, nr); + + put_obj_stock(flags); +} + static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) { - struct memcg_stock_pcp *stock; unsigned long flags; + struct obj_stock *stock = get_obj_stock(&flags); bool ret = false; - local_irq_save(flags); - - stock = this_cpu_ptr(&memcg_stock); if (objcg == stock->cached_objcg && stock->nr_bytes >= nr_bytes) { stock->nr_bytes -= nr_bytes; ret = true; } - local_irq_restore(flags); + put_obj_stock(flags); return ret; } -static void drain_obj_stock(struct memcg_stock_pcp *stock) +static void drain_obj_stock(struct obj_stock *stock) { struct obj_cgroup *old = stock->cached_objcg; @@ -3042,6 +3182,25 @@ static void drain_obj_stock(struct memcg_stock_pcp *stock) stock->nr_bytes = 0; } + /* + * Flush the vmstat data in current stock + */ + if (stock->nr_slab_reclaimable_b || stock->nr_slab_unreclaimable_b) { + if (stock->nr_slab_reclaimable_b) { + mod_objcg_mlstate(old, stock->cached_pgdat, + NR_SLAB_RECLAIMABLE_B, + stock->nr_slab_reclaimable_b); + stock->nr_slab_reclaimable_b = 0; + } + if (stock->nr_slab_unreclaimable_b) { + mod_objcg_mlstate(old, stock->cached_pgdat, + NR_SLAB_UNRECLAIMABLE_B, + stock->nr_slab_unreclaimable_b); + stock->nr_slab_unreclaimable_b = 0; + } + stock->cached_pgdat = NULL; + } + obj_cgroup_put(old); stock->cached_objcg = NULL; } @@ -3051,8 +3210,13 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, { struct mem_cgroup *memcg; - if (stock->cached_objcg) { - memcg = obj_cgroup_memcg(stock->cached_objcg); + if (in_task() && stock->task_obj.cached_objcg) { + memcg = obj_cgroup_memcg(stock->task_obj.cached_objcg); + if (memcg && mem_cgroup_is_descendant(memcg, root_memcg)) + return true; + } + if (stock->irq_obj.cached_objcg) { + memcg = obj_cgroup_memcg(stock->irq_obj.cached_objcg); if (memcg && mem_cgroup_is_descendant(memcg, root_memcg)) return true; } @@ -3060,26 +3224,32 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, return false; } -static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) +static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, + bool allow_uncharge) { - struct memcg_stock_pcp *stock; unsigned long flags; + struct obj_stock *stock = get_obj_stock(&flags); + unsigned int nr_pages = 0; - local_irq_save(flags); - - stock = this_cpu_ptr(&memcg_stock); if (stock->cached_objcg != objcg) { /* reset if necessary */ drain_obj_stock(stock); obj_cgroup_get(objcg); stock->cached_objcg = objcg; - stock->nr_bytes = atomic_xchg(&objcg->nr_charged_bytes, 0); + stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes) + ? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0; + allow_uncharge = true; /* Allow uncharge when objcg changes */ } stock->nr_bytes += nr_bytes; - if (stock->nr_bytes > PAGE_SIZE) - drain_obj_stock(stock); + if (allow_uncharge && (stock->nr_bytes > PAGE_SIZE)) { + nr_pages = stock->nr_bytes >> PAGE_SHIFT; + stock->nr_bytes &= (PAGE_SIZE - 1); + } - local_irq_restore(flags); + put_obj_stock(flags); + + if (nr_pages) + obj_cgroup_uncharge_pages(objcg, nr_pages); } int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) @@ -3091,14 +3261,27 @@ int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) return 0; /* - * In theory, memcg->nr_charged_bytes can have enough + * In theory, objcg->nr_charged_bytes can have enough * pre-charged bytes to satisfy the allocation. However, - * flushing memcg->nr_charged_bytes requires two atomic - * operations, and memcg->nr_charged_bytes can't be big, - * so it's better to ignore it and try grab some new pages. - * memcg->nr_charged_bytes will be flushed in - * refill_obj_stock(), called from this function or - * independently later. + * flushing objcg->nr_charged_bytes requires two atomic + * operations, and objcg->nr_charged_bytes can't be big. + * The shared objcg->nr_charged_bytes can also become a + * performance bottleneck if all tasks of the same memcg are + * trying to update it. So it's better to ignore it and try + * grab some new pages. The stock's nr_bytes will be flushed to + * objcg->nr_charged_bytes later on when objcg changes. + * + * The stock's nr_bytes may contain enough pre-charged bytes + * to allow one less page from being charged, but we can't rely + * on the pre-charged bytes not being changed outside of + * consume_obj_stock() or refill_obj_stock(). So ignore those + * pre-charged bytes as well when charging pages. To avoid a + * page uncharge right after a page charge, we set the + * allow_uncharge flag to false when calling refill_obj_stock() + * to temporarily allow the pre-charged bytes to exceed the page + * size limit. The maximum reachable value of the pre-charged + * bytes is (sizeof(object) + PAGE_SIZE - 2) if there is no data + * race. */ nr_pages = size >> PAGE_SHIFT; nr_bytes = size & (PAGE_SIZE - 1); @@ -3108,14 +3291,14 @@ int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) ret = obj_cgroup_charge_pages(objcg, gfp, nr_pages); if (!ret && nr_bytes) - refill_obj_stock(objcg, PAGE_SIZE - nr_bytes); + refill_obj_stock(objcg, PAGE_SIZE - nr_bytes, false); return ret; } void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) { - refill_obj_stock(objcg, size); + refill_obj_stock(objcg, size, true); } #endif /* CONFIG_MEMCG_KMEM */ @@ -6541,7 +6724,8 @@ out: * @gfp_mask: reclaim mode * * Try to charge @page to the memcg that @mm belongs to, reclaiming - * pages according to @gfp_mask if necessary. + * pages according to @gfp_mask if necessary. if @mm is NULL, try to + * charge to the active memcg. * * Do not use this for pages allocated for swapin. * @@ -6671,6 +6855,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) unsigned long nr_pages; struct mem_cgroup *memcg; struct obj_cgroup *objcg; + bool use_objcg = PageMemcgKmem(page); VM_BUG_ON_PAGE(PageLRU(page), page); @@ -6679,7 +6864,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) * page memcg or objcg at this point, we have fully * exclusive access to the page. */ - if (PageMemcgKmem(page)) { + if (use_objcg) { objcg = __page_objcg(page); /* * This get matches the put at the end of the function and @@ -6707,7 +6892,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) nr_pages = compound_nr(page); - if (PageMemcgKmem(page)) { + if (use_objcg) { ug->nr_memory += nr_pages; ug->nr_kmem += nr_pages; @@ -6806,9 +6991,11 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) /* Force-charge the new page. The old one will be freed soon */ nr_pages = thp_nr_pages(newpage); - page_counter_charge(&memcg->memory, nr_pages); - if (do_memsw_account()) - page_counter_charge(&memcg->memsw, nr_pages); + if (!mem_cgroup_is_root(memcg)) { + page_counter_charge(&memcg->memory, nr_pages); + if (do_memsw_account()) + page_counter_charge(&memcg->memsw, nr_pages); + } css_get(&memcg->css); commit_charge(newpage, memcg); diff --git a/mm/memfd.c b/mm/memfd.c index 2647c898990c..081dd33e6a61 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -297,9 +297,9 @@ SYSCALL_DEFINE2(memfd_create, } if (flags & MFD_HUGETLB) { - struct user_struct *user = NULL; + struct ucounts *ucounts = NULL; - file = hugetlb_file_setup(name, 0, VM_NORESERVE, &user, + file = hugetlb_file_setup(name, 0, VM_NORESERVE, &ucounts, HUGETLB_ANONHUGE_INODE, (flags >> MFD_HUGE_SHIFT) & MFD_HUGE_MASK); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 6f5f78885ab4..e5a1531f7f4e 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -56,6 +56,7 @@ #include #include #include +#include #include "internal.h" #include "ras/ras_event.h" @@ -554,6 +555,148 @@ static void collect_procs(struct page *page, struct list_head *tokill, collect_procs_file(page, tokill, force_early); } +struct hwp_walk { + struct to_kill tk; + unsigned long pfn; + int flags; +}; + +static void set_to_kill(struct to_kill *tk, unsigned long addr, short shift) +{ + tk->addr = addr; + tk->size_shift = shift; +} + +static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift, + unsigned long poisoned_pfn, struct to_kill *tk) +{ + unsigned long pfn = 0; + + if (pte_present(pte)) { + pfn = pte_pfn(pte); + } else { + swp_entry_t swp = pte_to_swp_entry(pte); + + if (is_hwpoison_entry(swp)) + pfn = hwpoison_entry_to_pfn(swp); + } + + if (!pfn || pfn != poisoned_pfn) + return 0; + + set_to_kill(tk, addr, shift); + return 1; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, + struct hwp_walk *hwp) +{ + pmd_t pmd = *pmdp; + unsigned long pfn; + unsigned long hwpoison_vaddr; + + if (!pmd_present(pmd)) + return 0; + pfn = pmd_pfn(pmd); + if (pfn <= hwp->pfn && hwp->pfn < pfn + HPAGE_PMD_NR) { + hwpoison_vaddr = addr + ((hwp->pfn - pfn) << PAGE_SHIFT); + set_to_kill(&hwp->tk, hwpoison_vaddr, PAGE_SHIFT); + return 1; + } + return 0; +} +#else +static int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, + struct hwp_walk *hwp) +{ + return 0; +} +#endif + +static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + struct hwp_walk *hwp = (struct hwp_walk *)walk->private; + int ret = 0; + pte_t *ptep; + spinlock_t *ptl; + + ptl = pmd_trans_huge_lock(pmdp, walk->vma); + if (ptl) { + ret = check_hwpoisoned_pmd_entry(pmdp, addr, hwp); + spin_unlock(ptl); + goto out; + } + + if (pmd_trans_unstable(pmdp)) + goto out; + + ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp, addr, &ptl); + for (; addr != end; ptep++, addr += PAGE_SIZE) { + ret = check_hwpoisoned_entry(*ptep, addr, PAGE_SHIFT, + hwp->pfn, &hwp->tk); + if (ret == 1) + break; + } + pte_unmap_unlock(ptep - 1, ptl); +out: + cond_resched(); + return ret; +} + +#ifdef CONFIG_HUGETLB_PAGE +static int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask, + unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct hwp_walk *hwp = (struct hwp_walk *)walk->private; + pte_t pte = huge_ptep_get(ptep); + struct hstate *h = hstate_vma(walk->vma); + + return check_hwpoisoned_entry(pte, addr, huge_page_shift(h), + hwp->pfn, &hwp->tk); +} +#else +#define hwpoison_hugetlb_range NULL +#endif + +static struct mm_walk_ops hwp_walk_ops = { + .pmd_entry = hwpoison_pte_range, + .hugetlb_entry = hwpoison_hugetlb_range, +}; + +/* + * Sends SIGBUS to the current process with error info. + * + * This function is intended to handle "Action Required" MCEs on already + * hardware poisoned pages. They could happen, for example, when + * memory_failure() failed to unmap the error page at the first call, or + * when multiple local machine checks happened on different CPUs. + * + * MCE handler currently has no easy access to the error virtual address, + * so this function walks page table to find it. The returned virtual address + * is proper in most cases, but it could be wrong when the application + * process has multiple entries mapping the error page. + */ +static int kill_accessing_process(struct task_struct *p, unsigned long pfn, + int flags) +{ + int ret; + struct hwp_walk priv = { + .pfn = pfn, + }; + priv.tk.tsk = p; + + mmap_read_lock(p->mm); + ret = walk_page_range(p->mm, 0, TASK_SIZE, &hwp_walk_ops, + (void *)&priv); + if (ret == 1 && priv.tk.addr) + kill_proc(&priv.tk, pfn, flags); + mmap_read_unlock(p->mm); + return ret ? -EFAULT : -EHWPOISON; +} + static const char *action_name[] = { [MF_IGNORED] = "Ignored", [MF_FAILED] = "Failed", @@ -974,13 +1117,6 @@ static inline bool HWPoisonHandlable(struct page *page) return PageLRU(page) || __PageMovable(page); } -/** - * __get_hwpoison_page() - Get refcount for memory error handling: - * @page: raw error page (hit by memory error) - * - * Return: return 0 if failed to grab the refcount, otherwise true (some - * non-zero value.) - */ static int __get_hwpoison_page(struct page *page) { struct page *head = compound_head(page); @@ -1025,15 +1161,6 @@ static int __get_hwpoison_page(struct page *page) return 0; } -/* - * Safely get reference count of an arbitrary page. - * - * Returns 0 for a free page, 1 for an in-use page, - * -EIO for a page-type we cannot handle and -EBUSY if we raced with an - * allocation. - * We only incremented refcount in case the page was already in-use and it - * is a known type we can handle. - */ static int get_any_page(struct page *p, unsigned long flags) { int ret = 0, pass = 0; @@ -1043,50 +1170,77 @@ static int get_any_page(struct page *p, unsigned long flags) count_increased = true; try_again: - if (!count_increased && !__get_hwpoison_page(p)) { - if (page_count(p)) { - /* We raced with an allocation, retry. */ - if (pass++ < 3) - goto try_again; - ret = -EBUSY; - } else if (!PageHuge(p) && !is_free_buddy_page(p)) { - /* We raced with put_page, retry. */ - if (pass++ < 3) - goto try_again; - ret = -EIO; - } - } else { - if (PageHuge(p) || HWPoisonHandlable(p)) { - ret = 1; - } else { - /* - * A page we cannot handle. Check whether we can turn - * it into something we can handle. - */ - if (pass++ < 3) { - put_page(p); - shake_page(p, 1); - count_increased = false; - goto try_again; + if (!count_increased) { + ret = __get_hwpoison_page(p); + if (!ret) { + if (page_count(p)) { + /* We raced with an allocation, retry. */ + if (pass++ < 3) + goto try_again; + ret = -EBUSY; + } else if (!PageHuge(p) && !is_free_buddy_page(p)) { + /* We raced with put_page, retry. */ + if (pass++ < 3) + goto try_again; + ret = -EIO; } - put_page(p); - ret = -EIO; + goto out; + } else if (ret == -EBUSY) { + /* We raced with freeing huge page to buddy, retry. */ + if (pass++ < 3) + goto try_again; + goto out; } } + if (PageHuge(p) || HWPoisonHandlable(p)) { + ret = 1; + } else { + /* + * A page we cannot handle. Check whether we can turn + * it into something we can handle. + */ + if (pass++ < 3) { + put_page(p); + shake_page(p, 1); + count_increased = false; + goto try_again; + } + put_page(p); + ret = -EIO; + } +out: return ret; } -static int get_hwpoison_page(struct page *p, unsigned long flags, - enum mf_flags ctxt) +/** + * get_hwpoison_page() - Get refcount for memory error handling + * @p: Raw error page (hit by memory error) + * @flags: Flags controlling behavior of error handling + * + * get_hwpoison_page() takes a page refcount of an error page to handle memory + * error on it, after checking that the error page is in a well-defined state + * (defined as a page-type we can successfully handle the memor error on it, + * such as LRU page and hugetlb page). + * + * Memory error handling could be triggered at any time on any type of page, + * so it's prone to race with typical memory management lifecycle (like + * allocation and free). So to avoid such races, get_hwpoison_page() takes + * extra care for the error page's state (as done in __get_hwpoison_page()), + * and has some retry logic in get_any_page(). + * + * Return: 0 on failure, + * 1 on success for in-use pages in a well-defined state, + * -EIO for pages on which we can not handle memory errors, + * -EBUSY when get_hwpoison_page() has raced with page lifecycle + * operations like allocation and free. + */ +static int get_hwpoison_page(struct page *p, unsigned long flags) { int ret; zone_pcp_disable(page_zone(p)); - if (ctxt == MF_SOFT_OFFLINE) - ret = get_any_page(p, flags); - else - ret = __get_hwpoison_page(p); + ret = get_any_page(p, flags); zone_pcp_enable(page_zone(p)); return ret; @@ -1267,32 +1421,41 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags) if (TestSetPageHWPoison(head)) { pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); - return -EHWPOISON; + res = -EHWPOISON; + if (flags & MF_ACTION_REQUIRED) + res = kill_accessing_process(current, page_to_pfn(head), flags); + return res; } num_poisoned_pages_inc(); - if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p, flags, 0)) { - /* - * Check "filter hit" and "race with other subpage." - */ - lock_page(head); - if (PageHWPoison(head)) { - if ((hwpoison_filter(p) && TestClearPageHWPoison(p)) - || (p != head && TestSetPageHWPoison(head))) { - num_poisoned_pages_dec(); - unlock_page(head); - return 0; + if (!(flags & MF_COUNT_INCREASED)) { + res = get_hwpoison_page(p, flags); + if (!res) { + /* + * Check "filter hit" and "race with other subpage." + */ + lock_page(head); + if (PageHWPoison(head)) { + if ((hwpoison_filter(p) && TestClearPageHWPoison(p)) + || (p != head && TestSetPageHWPoison(head))) { + num_poisoned_pages_dec(); + unlock_page(head); + return 0; + } } + unlock_page(head); + res = MF_FAILED; + if (!dissolve_free_huge_page(p) && take_page_off_buddy(p)) { + page_ref_inc(p); + res = MF_RECOVERED; + } + action_result(pfn, MF_MSG_FREE_HUGE, res); + return res == MF_RECOVERED ? 0 : -EBUSY; + } else if (res < 0) { + action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED); + return -EBUSY; } - unlock_page(head); - res = MF_FAILED; - if (!dissolve_free_huge_page(p) && take_page_off_buddy(p)) { - page_ref_inc(p); - res = MF_RECOVERED; - } - action_result(pfn, MF_MSG_FREE_HUGE, res); - return res == MF_RECOVERED ? 0 : -EBUSY; } lock_page(head); @@ -1476,6 +1639,8 @@ try_again: pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); res = -EHWPOISON; + if (flags & MF_ACTION_REQUIRED) + res = kill_accessing_process(current, pfn, flags); goto unlock_mutex; } @@ -1493,28 +1658,35 @@ try_again: * In fact it's dangerous to directly bump up page count from 0, * that may make page_ref_freeze()/page_ref_unfreeze() mismatch. */ - if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p, flags, 0)) { - if (is_free_buddy_page(p)) { - if (take_page_off_buddy(p)) { - page_ref_inc(p); - res = MF_RECOVERED; - } else { - /* We lost the race, try again */ - if (retry) { - ClearPageHWPoison(p); - num_poisoned_pages_dec(); - retry = false; - goto try_again; + if (!(flags & MF_COUNT_INCREASED)) { + res = get_hwpoison_page(p, flags); + if (!res) { + if (is_free_buddy_page(p)) { + if (take_page_off_buddy(p)) { + page_ref_inc(p); + res = MF_RECOVERED; + } else { + /* We lost the race, try again */ + if (retry) { + ClearPageHWPoison(p); + num_poisoned_pages_dec(); + retry = false; + goto try_again; + } + res = MF_FAILED; } - res = MF_FAILED; + action_result(pfn, MF_MSG_BUDDY, res); + res = res == MF_RECOVERED ? 0 : -EBUSY; + } else { + action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED); + res = -EBUSY; } - action_result(pfn, MF_MSG_BUDDY, res); - res = res == MF_RECOVERED ? 0 : -EBUSY; - } else { - action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED); + goto unlock_mutex; + } else if (res < 0) { + action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED); res = -EBUSY; + goto unlock_mutex; } - goto unlock_mutex; } if (PageTransHuge(hpage)) { @@ -1792,7 +1964,7 @@ int unpoison_memory(unsigned long pfn) return 0; } - if (!get_hwpoison_page(p, flags, 0)) { + if (!get_hwpoison_page(p, flags)) { if (TestClearPageHWPoison(p)) num_poisoned_pages_dec(); unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n", @@ -2008,7 +2180,7 @@ int soft_offline_page(unsigned long pfn, int flags) retry: get_online_mems(); - ret = get_hwpoison_page(page, flags, MF_SOFT_OFFLINE); + ret = get_hwpoison_page(page, flags); put_online_mems(); if (ret > 0) { diff --git a/mm/memory.c b/mm/memory.c index 3ed48ff60ff7..186b87bc74dd 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -91,8 +91,7 @@ #warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid. #endif -#ifndef CONFIG_NEED_MULTIPLE_NODES -/* use the per-pgdat data instead for discontigmem - mbligh */ +#ifndef CONFIG_NUMA unsigned long max_mapnr; EXPORT_SYMBOL(max_mapnr); @@ -3037,6 +3036,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) munlock_vma_page(old_page); unlock_page(old_page); } + if (page_copied) + free_swap_cache(old_page); put_page(old_page); } return page_copied ? VM_FAULT_WRITE : 0; @@ -3061,7 +3062,7 @@ oom: * The function expects the page to be locked or other protection against * concurrent faults / writeback (such as DAX radix tree locks). * - * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before + * Return: %0 on success, %VM_FAULT_NOPAGE when PTE got changed before * we acquired PTE lock. */ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf) @@ -3367,6 +3368,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL, *swapcache; + struct swap_info_struct *si = NULL; swp_entry_t entry; pte_t pte; int locked; @@ -3394,14 +3396,16 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) goto out; } + /* Prevent swapoff from happening to us. */ + si = get_swap_device(entry); + if (unlikely(!si)) + goto out; delayacct_set_flag(current, DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry, vma, vmf->address); swapcache = page; if (!page) { - struct swap_info_struct *si = swp_swap_info(entry); - if (data_race(si->flags & SWP_SYNCHRONOUS_IO) && __swap_count(entry) == 1) { /* skip swapcache */ @@ -3572,6 +3576,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); out: + if (si) + put_swap_device(si); return ret; out_nomap: pte_unmap_unlock(vmf->pte, vmf->ptl); @@ -3583,6 +3589,8 @@ out_release: unlock_page(swapcache); put_page(swapcache); } + if (si) + put_swap_device(si); return ret; } @@ -5001,8 +5009,8 @@ int __access_remote_vm(struct mm_struct *mm, unsigned long addr, void *buf, * Check if this is a VM_IO | VM_PFNMAP VMA, which * we can access using slightly different code. */ - vma = find_vma(mm, addr); - if (!vma || vma->vm_start > addr) + vma = vma_lookup(mm, addr); + if (!vma) break; if (vma->vm_ops && vma->vm_ops->access) ret = vma->vm_ops->access(vma, addr, buf, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 70620d0dd923..974a565797d8 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -961,7 +961,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z node_states_set_node(nid, &arg); if (need_zonelists_rebuild) build_all_zonelists(NULL); - zone_pcp_update(zone); /* Basic onlining is complete, allow allocation of onlined pages. */ undo_isolate_page_range(pfn, pfn + nr_pages, MIGRATE_MOVABLE); @@ -974,6 +973,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *z */ shuffle_zone(zone); + /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); kswapd_run(nid); @@ -1829,13 +1829,13 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages) adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages); adjust_present_page_count(zone, -nr_pages); + /* reinitialise watermarks and update pcp limits */ init_per_zone_wmark_min(); if (!populated_zone(zone)) { zone_pcp_reset(zone); build_all_zonelists(NULL); - } else - zone_pcp_update(zone); + } node_states_clear_node(node, &arg); if (arg.status_change_nid >= 0) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4ce15411f77a..0913e8185195 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -976,7 +976,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); - vma = find_vma_intersection(mm, addr, addr+1); + vma = vma_lookup(mm, addr); if (!vma) { mmap_read_unlock(mm); return -EFAULT; @@ -2151,7 +2151,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, return page; if (page && page_to_nid(page) == nid) { preempt_disable(); - __inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT); + __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } return page; diff --git a/mm/migrate.c b/mm/migrate.c index 41ff2c9896c4..380ca57b9031 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1834,8 +1834,8 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, struct page *page; int err = -EFAULT; - vma = find_vma(mm, addr); - if (!vma || addr < vma->vm_start) + vma = vma_lookup(mm, addr); + if (!vma) goto set_status; /* FOLL_DUMP to ignore special (like zero) pages */ diff --git a/mm/mlock.c b/mm/mlock.c index 9cc6928821ab..41c676a9dc43 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -817,9 +817,10 @@ SYSCALL_DEFINE0(munlockall) */ static DEFINE_SPINLOCK(shmlock_user_lock); -int user_shm_lock(size_t size, struct user_struct *user) +int user_shm_lock(size_t size, struct ucounts *ucounts) { unsigned long lock_limit, locked; + long memlock; int allowed = 0; locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; @@ -828,21 +829,26 @@ int user_shm_lock(size_t size, struct user_struct *user) allowed = 1; lock_limit >>= PAGE_SHIFT; spin_lock(&shmlock_user_lock); - if (!allowed && - locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK)) + memlock = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); + + if (!allowed && (memlock == LONG_MAX || memlock > lock_limit) && !capable(CAP_IPC_LOCK)) { + dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); goto out; - get_uid(user); - user->locked_shm += locked; + } + if (!get_ucounts(ucounts)) { + dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked); + goto out; + } allowed = 1; out: spin_unlock(&shmlock_user_lock); return allowed; } -void user_shm_unlock(size_t size, struct user_struct *user) +void user_shm_unlock(size_t size, struct ucounts *ucounts) { spin_lock(&shmlock_user_lock); - user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, (size + PAGE_SIZE - 1) >> PAGE_SHIFT); spin_unlock(&shmlock_user_lock); - free_uid(user); + put_ucounts(ucounts); } diff --git a/mm/mmap.c b/mm/mmap.c index 3215d3ed19a1..00d9e4b653be 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1466,9 +1466,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, return addr; if (flags & MAP_FIXED_NOREPLACE) { - struct vm_area_struct *vma = find_vma(mm, addr); - - if (vma && vma->vm_start < addr + len) + if (find_vma_intersection(mm, addr, addr + len)) return -EEXIST; } @@ -1620,7 +1618,7 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, goto out_fput; } } else if (flags & MAP_HUGETLB) { - struct user_struct *user = NULL; + struct ucounts *ucounts = NULL; struct hstate *hs; hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); @@ -1636,13 +1634,13 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, */ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, - &user, HUGETLB_ANONHUGE_INODE, + &ucounts, HUGETLB_ANONHUGE_INODE, (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (IS_ERR(file)) return PTR_ERR(file); } - flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); + flags &= ~MAP_DENYWRITE; retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); out_fput: @@ -2812,6 +2810,22 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, return __split_vma(mm, vma, addr, new_below); } +static inline void +unlock_range(struct vm_area_struct *start, unsigned long limit) +{ + struct mm_struct *mm = start->vm_mm; + struct vm_area_struct *tmp = start; + + while (tmp && tmp->vm_start < limit) { + if (tmp->vm_flags & VM_LOCKED) { + mm->locked_vm -= vma_pages(tmp); + munlock_vma_pages_all(tmp); + } + + tmp = tmp->vm_next; + } +} + /* Munmap is split into 2 main parts -- this part which finds * what needs doing, and the areas themselves, which do the * work. This now handles partial unmappings. @@ -2838,16 +2852,11 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, */ arch_unmap(mm, start, end); - /* Find the first overlapping VMA */ - vma = find_vma(mm, start); + /* Find the first overlapping VMA where start < vma->vm_end */ + vma = find_vma_intersection(mm, start, end); if (!vma) return 0; prev = vma->vm_prev; - /* we have start < vma->vm_end */ - - /* if it doesn't overlap, we have nothing.. */ - if (vma->vm_start >= end) - return 0; /* * If we need to split any vma, do it now to save pain later. @@ -2900,17 +2909,8 @@ int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, /* * unlock any mlock()ed ranges before detaching vmas */ - if (mm->locked_vm) { - struct vm_area_struct *tmp = vma; - while (tmp && tmp->vm_start < end) { - if (tmp->vm_flags & VM_LOCKED) { - mm->locked_vm -= vma_pages(tmp); - munlock_vma_pages_all(tmp); - } - - tmp = tmp->vm_next; - } - } + if (mm->locked_vm) + unlock_range(vma, end); /* Detach vmas from rbtree */ if (!detach_vmas_to_be_unmapped(mm, vma, prev, end)) @@ -3195,14 +3195,8 @@ void exit_mmap(struct mm_struct *mm) mmap_write_unlock(mm); } - if (mm->locked_vm) { - vma = mm->mmap; - while (vma) { - if (vma->vm_flags & VM_LOCKED) - munlock_vma_pages_all(vma); - vma = vma->vm_next; - } - } + if (mm->locked_vm) + unlock_range(mm->mmap, ULONG_MAX); arch_exit_mmap(mm); diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c index dcdde4f722a4..2ae3f33b85b1 100644 --- a/mm/mmap_lock.c +++ b/mm/mmap_lock.c @@ -11,6 +11,7 @@ #include #include #include +#include EXPORT_TRACEPOINT_SYMBOL(mmap_lock_start_locking); EXPORT_TRACEPOINT_SYMBOL(mmap_lock_acquire_returned); @@ -39,21 +40,30 @@ static int reg_refcount; /* Protected by reg_lock. */ */ #define CONTEXT_COUNT 4 -static DEFINE_PER_CPU(char __rcu *, memcg_path_buf); +struct memcg_path { + local_lock_t lock; + char __rcu *buf; + local_t buf_idx; +}; +static DEFINE_PER_CPU(struct memcg_path, memcg_paths) = { + .lock = INIT_LOCAL_LOCK(lock), + .buf_idx = LOCAL_INIT(0), +}; + static char **tmp_bufs; -static DEFINE_PER_CPU(int, memcg_path_buf_idx); /* Called with reg_lock held. */ static void free_memcg_path_bufs(void) { + struct memcg_path *memcg_path; int cpu; char **old = tmp_bufs; for_each_possible_cpu(cpu) { - *(old++) = rcu_dereference_protected( - per_cpu(memcg_path_buf, cpu), + memcg_path = per_cpu_ptr(&memcg_paths, cpu); + *(old++) = rcu_dereference_protected(memcg_path->buf, lockdep_is_held(®_lock)); - rcu_assign_pointer(per_cpu(memcg_path_buf, cpu), NULL); + rcu_assign_pointer(memcg_path->buf, NULL); } /* Wait for inflight memcg_path_buf users to finish. */ @@ -88,7 +98,7 @@ int trace_mmap_lock_reg(void) new = kmalloc(MEMCG_PATH_BUF_SIZE * CONTEXT_COUNT, GFP_KERNEL); if (new == NULL) goto out_fail_free; - rcu_assign_pointer(per_cpu(memcg_path_buf, cpu), new); + rcu_assign_pointer(per_cpu_ptr(&memcg_paths, cpu)->buf, new); /* Don't need to wait for inflights, they'd have gotten NULL. */ } @@ -122,23 +132,24 @@ out: static inline char *get_memcg_path_buf(void) { + struct memcg_path *memcg_path = this_cpu_ptr(&memcg_paths); char *buf; int idx; rcu_read_lock(); - buf = rcu_dereference(*this_cpu_ptr(&memcg_path_buf)); + buf = rcu_dereference(memcg_path->buf); if (buf == NULL) { rcu_read_unlock(); return NULL; } - idx = this_cpu_add_return(memcg_path_buf_idx, MEMCG_PATH_BUF_SIZE) - + idx = local_add_return(MEMCG_PATH_BUF_SIZE, &memcg_path->buf_idx) - MEMCG_PATH_BUF_SIZE; return &buf[idx]; } static inline void put_memcg_path_buf(void) { - this_cpu_sub(memcg_path_buf_idx, MEMCG_PATH_BUF_SIZE); + local_sub(MEMCG_PATH_BUF_SIZE, &this_cpu_ptr(&memcg_paths)->buf_idx); rcu_read_unlock(); } @@ -179,14 +190,14 @@ out: #define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \ do { \ const char *memcg_path; \ - preempt_disable(); \ + local_lock(&memcg_paths.lock); \ memcg_path = get_mm_memcg_path(mm); \ trace_mmap_lock_##type(mm, \ memcg_path != NULL ? memcg_path : "", \ ##__VA_ARGS__); \ if (likely(memcg_path != NULL)) \ put_memcg_path_buf(); \ - preempt_enable(); \ + local_unlock(&memcg_paths.lock); \ } while (0) #else /* !CONFIG_MEMCG */ diff --git a/mm/mremap.c b/mm/mremap.c index 47c255b60150..a369a6100698 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -634,10 +634,11 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, unsigned long *p) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma = find_vma(mm, addr); + struct vm_area_struct *vma; unsigned long pgoff; - if (!vma || vma->vm_start > addr) + vma = vma_lookup(mm, addr); + if (!vma) return ERR_PTR(-EFAULT); /* diff --git a/mm/nommu.c b/mm/nommu.c index 85a3a68dffb6..affda71641ca 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1296,7 +1296,7 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, goto out; } - flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE); + flags &= ~MAP_DENYWRITE; retval = vm_mmap_pgoff(file, addr, len, prot, flags, pgoff); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0062d5c57d41..9f63548f247c 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -32,7 +32,6 @@ #include #include #include -#include /* __set_page_dirty_buffers */ #include #include #include @@ -108,11 +107,6 @@ EXPORT_SYMBOL_GPL(dirty_writeback_interval); */ unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ -/* - * Flag that makes the machine dump writes/reads and block dirtyings. - */ -int block_dump; - /* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. @@ -845,7 +839,7 @@ static long long pos_ratio_polynom(unsigned long setpoint, * ^ pos_ratio * | * | |<===== global dirty control scope ======>| - * 2.0 .............* + * 2.0 * * * * * * * * | .* * | . * * | . * @@ -1869,10 +1863,9 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * - * On really big machines, get_writeback_state is expensive, so try to avoid - * calling it too often (ratelimiting). But once we're over the dirty memory - * limit we decrease the ratelimiting by a lot, to prevent individual processes - * from overshooting the limit by (ratelimit_pages) each. + * Once we're over the dirty memory limit we decrease the ratelimiting + * by a lot, to prevent individual processes from overshooting the limit + * by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { @@ -1945,6 +1938,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; + unsigned long reclaimable; + unsigned long thresh; /* * Similar to balance_dirty_pages() but ignores pages being written @@ -1957,8 +1952,13 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (gdtc->dirty > gdtc->bg_thresh) return true; - if (wb_stat(wb, WB_RECLAIMABLE) > - wb_calc_thresh(gdtc->wb, gdtc->bg_thresh)) + thresh = wb_calc_thresh(gdtc->wb, gdtc->bg_thresh); + if (thresh < 2 * wb_stat_error()) + reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); + else + reclaimable = wb_stat(wb, WB_RECLAIMABLE); + + if (reclaimable > thresh) return true; if (mdtc) { @@ -1972,8 +1972,13 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (mdtc->dirty > mdtc->bg_thresh) return true; - if (wb_stat(wb, WB_RECLAIMABLE) > - wb_calc_thresh(mdtc->wb, mdtc->bg_thresh)) + thresh = wb_calc_thresh(mdtc->wb, mdtc->bg_thresh); + if (thresh < 2 * wb_stat_error()) + reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); + else + reclaimable = wb_stat(wb, WB_RECLAIMABLE); + + if (reclaimable > thresh) return true; } @@ -2045,8 +2050,6 @@ void laptop_sync_completion(void) /* * If ratelimit_pages is too high then we can get into dirty-data overload * if a large number of processes all perform writes at the same time. - * If it is too low then SMP machines will call the (expensive) - * get_writeback_state too often. * * Here we set ratelimit_pages to a level which ensures that when all CPUs are * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory @@ -2409,6 +2412,7 @@ int __set_page_dirty_no_writeback(struct page *page) return !TestSetPageDirty(page); return 0; } +EXPORT_SYMBOL(__set_page_dirty_no_writeback); /* * Helper function for set_page_dirty family. @@ -2417,7 +2421,8 @@ int __set_page_dirty_no_writeback(struct page *page) * * NOTE: This relies on being atomic wrt interrupts. */ -void account_page_dirtied(struct page *page, struct address_space *mapping) +static void account_page_dirtied(struct page *page, + struct address_space *mapping) { struct inode *inode = mapping->host; @@ -2436,7 +2441,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) inc_wb_stat(wb, WB_DIRTIED); task_io_account_write(PAGE_SIZE); current->nr_dirtied++; - this_cpu_inc(bdp_ratelimits); + __this_cpu_inc(bdp_ratelimits); mem_cgroup_track_foreign_dirty(page, wb); } @@ -2458,6 +2463,30 @@ void account_page_cleaned(struct page *page, struct address_space *mapping, } } +/* + * Mark the page dirty, and set it dirty in the page cache, and mark the inode + * dirty. + * + * If warn is true, then emit a warning if the page is not uptodate and has + * not been truncated. + * + * The caller must hold lock_page_memcg(). + */ +void __set_page_dirty(struct page *page, struct address_space *mapping, + int warn) +{ + unsigned long flags; + + xa_lock_irqsave(&mapping->i_pages, flags); + if (page->mapping) { /* Race with truncate? */ + WARN_ON_ONCE(warn && !PageUptodate(page)); + account_page_dirtied(page, mapping); + __xa_set_mark(&mapping->i_pages, page_index(page), + PAGECACHE_TAG_DIRTY); + } + xa_unlock_irqrestore(&mapping->i_pages, flags); +} + /* * For address_spaces which do not use buffers. Just tag the page as dirty in * the xarray. @@ -2475,20 +2504,12 @@ int __set_page_dirty_nobuffers(struct page *page) lock_page_memcg(page); if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); - unsigned long flags; if (!mapping) { unlock_page_memcg(page); return 1; } - - xa_lock_irqsave(&mapping->i_pages, flags); - BUG_ON(page_mapping(page) != mapping); - WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); - account_page_dirtied(page, mapping); - __xa_set_mark(&mapping->i_pages, page_index(page), - PAGECACHE_TAG_DIRTY); - xa_unlock_irqrestore(&mapping->i_pages, flags); + __set_page_dirty(page, mapping, !PagePrivate(page)); unlock_page_memcg(page); if (mapping->host) { @@ -2546,13 +2567,9 @@ EXPORT_SYMBOL(redirty_page_for_writepage); /* * Dirty a page. * - * For pages with a mapping this should be done under the page lock - * for the benefit of asynchronous memory errors who prefer a consistent - * dirty state. This rule can be broken in some special cases, - * but should be better not to. - * - * If the mapping doesn't provide a set_page_dirty a_op, then - * just fall through and assume that it wants buffer_heads. + * For pages with a mapping this should be done under the page lock for the + * benefit of asynchronous memory errors who prefer a consistent dirty state. + * This rule can be broken in some special cases, but should be better not to. */ int set_page_dirty(struct page *page) { @@ -2560,7 +2577,6 @@ int set_page_dirty(struct page *page) page = compound_head(page); if (likely(mapping)) { - int (*spd)(struct page *) = mapping->a_ops->set_page_dirty; /* * readahead/lru_deactivate_page could remain * PG_readahead/PG_reclaim due to race with end_page_writeback @@ -2573,11 +2589,7 @@ int set_page_dirty(struct page *page) */ if (PageReclaim(page)) ClearPageReclaim(page); -#ifdef CONFIG_BLOCK - if (!spd) - spd = __set_page_dirty_buffers; -#endif - return (*spd)(page); + return mapping->a_ops->set_page_dirty(page); } if (!PageDirty(page)) { if (!TestSetPageDirty(page)) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b09d61589f61..4e1d6803fda4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -120,7 +120,25 @@ typedef int __bitwise fpi_t; /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */ static DEFINE_MUTEX(pcp_batch_high_lock); -#define MIN_PERCPU_PAGELIST_FRACTION (8) +#define MIN_PERCPU_PAGELIST_HIGH_FRACTION (8) + +struct pagesets { + local_lock_t lock; +#if defined(CONFIG_DEBUG_INFO_BTF) && \ + !defined(CONFIG_DEBUG_LOCK_ALLOC) && \ + !defined(CONFIG_PAHOLE_HAS_ZEROSIZE_PERCPU_SUPPORT) + /* + * pahole 1.21 and earlier gets confused by zero-sized per-CPU + * variables and produces invalid BTF. Ensure that + * sizeof(struct pagesets) != 0 for older versions of pahole. + */ + char __pahole_hack; + #warning "pahole too old to support zero-sized struct pagesets" +#endif +}; +static DEFINE_PER_CPU(struct pagesets, pagesets) = { + .lock = INIT_LOCAL_LOCK(lock), +}; #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DEFINE_PER_CPU(int, numa_node); @@ -175,7 +193,7 @@ EXPORT_SYMBOL(_totalram_pages); unsigned long totalreserve_pages __read_mostly; unsigned long totalcma_pages __read_mostly; -int percpu_pagelist_fraction; +int percpu_pagelist_high_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc); EXPORT_SYMBOL(init_on_alloc); @@ -336,20 +354,7 @@ compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS] = { */ int min_free_kbytes = 1024; int user_min_free_kbytes = -1; -#ifdef CONFIG_DISCONTIGMEM -/* - * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges - * are not on separate NUMA nodes. Functionally this works but with - * watermark_boost_factor, it can reclaim prematurely as the ranges can be - * quite small. By default, do not boost watermarks on discontigmem as in - * many cases very high-order allocations like THP are likely to be - * unsupported and the premature reclaim offsets the advantage of long-term - * fragmentation avoidance. - */ -int watermark_boost_factor __read_mostly; -#else int watermark_boost_factor __read_mostly = 15000; -#endif int watermark_scale_factor = 10; /* @@ -481,7 +486,7 @@ static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn) #endif /* Return a pointer to the bitmap storing bits affecting a block of pages */ -static inline unsigned long *get_pageblock_bitmap(struct page *page, +static inline unsigned long *get_pageblock_bitmap(const struct page *page, unsigned long pfn) { #ifdef CONFIG_SPARSEMEM @@ -491,7 +496,7 @@ static inline unsigned long *get_pageblock_bitmap(struct page *page, #endif /* CONFIG_SPARSEMEM */ } -static inline int pfn_to_bitidx(struct page *page, unsigned long pfn) +static inline int pfn_to_bitidx(const struct page *page, unsigned long pfn) { #ifdef CONFIG_SPARSEMEM pfn &= (PAGES_PER_SECTION-1); @@ -502,7 +507,7 @@ static inline int pfn_to_bitidx(struct page *page, unsigned long pfn) } static __always_inline -unsigned long __get_pfnblock_flags_mask(struct page *page, +unsigned long __get_pfnblock_flags_mask(const struct page *page, unsigned long pfn, unsigned long mask) { @@ -527,13 +532,14 @@ unsigned long __get_pfnblock_flags_mask(struct page *page, * * Return: pageblock_bits flags */ -unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn, - unsigned long mask) +unsigned long get_pfnblock_flags_mask(const struct page *page, + unsigned long pfn, unsigned long mask) { return __get_pfnblock_flags_mask(page, pfn, mask); } -static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn) +static __always_inline int get_pfnblock_migratetype(const struct page *page, + unsigned long pfn) { return __get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK); } @@ -665,8 +671,7 @@ static void bad_page(struct page *page, const char *reason) pr_alert("BUG: Bad page state in process %s pfn:%05lx\n", current->comm, page_to_pfn(page)); - __dump_page(page, reason); - dump_page_owner(page); + dump_page(page, reason); print_modules(); dump_stack(); @@ -676,6 +681,57 @@ out: add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } +static inline unsigned int order_to_pindex(int migratetype, int order) +{ + int base = order; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (order > PAGE_ALLOC_COSTLY_ORDER) { + VM_BUG_ON(order != pageblock_order); + base = PAGE_ALLOC_COSTLY_ORDER + 1; + } +#else + VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); +#endif + + return (MIGRATE_PCPTYPES * base) + migratetype; +} + +static inline int pindex_to_order(unsigned int pindex) +{ + int order = pindex / MIGRATE_PCPTYPES; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (order > PAGE_ALLOC_COSTLY_ORDER) { + order = pageblock_order; + VM_BUG_ON(order != pageblock_order); + } +#else + VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER); +#endif + + return order; +} + +static inline bool pcp_allowed_order(unsigned int order) +{ + if (order <= PAGE_ALLOC_COSTLY_ORDER) + return true; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (order == pageblock_order) + return true; +#endif + return false; +} + +static inline void free_the_page(struct page *page, unsigned int order) +{ + if (pcp_allowed_order(order)) /* Via pcp? */ + free_unref_page(page, order); + else + __free_pages_ok(page, order, FPI_NONE); +} + /* * Higher-order pages are called "compound pages". They are structured thusly: * @@ -694,7 +750,7 @@ out: void free_compound_page(struct page *page) { mem_cgroup_uncharge(page); - __free_pages_ok(page, compound_order(page), FPI_NONE); + free_the_page(page, compound_order(page)); } void prep_compound_page(struct page *page, unsigned int order) @@ -1357,9 +1413,9 @@ static __always_inline bool free_pages_prepare(struct page *page, * to pcp lists. With debug_pagealloc also enabled, they are also rechecked when * moved from pcp lists to free lists. */ -static bool free_pcp_prepare(struct page *page) +static bool free_pcp_prepare(struct page *page, unsigned int order) { - return free_pages_prepare(page, 0, true, FPI_NONE); + return free_pages_prepare(page, order, true, FPI_NONE); } static bool bulkfree_pcp_prepare(struct page *page) @@ -1376,12 +1432,12 @@ static bool bulkfree_pcp_prepare(struct page *page) * debug_pagealloc enabled, they are checked also immediately when being freed * to the pcp lists. */ -static bool free_pcp_prepare(struct page *page) +static bool free_pcp_prepare(struct page *page, unsigned int order) { if (debug_pagealloc_enabled_static()) - return free_pages_prepare(page, 0, true, FPI_NONE); + return free_pages_prepare(page, order, true, FPI_NONE); else - return free_pages_prepare(page, 0, false, FPI_NONE); + return free_pages_prepare(page, order, false, FPI_NONE); } static bool bulkfree_pcp_prepare(struct page *page) @@ -1413,8 +1469,10 @@ static inline void prefetch_buddy(struct page *page) static void free_pcppages_bulk(struct zone *zone, int count, struct per_cpu_pages *pcp) { - int migratetype = 0; + int pindex = 0; int batch_free = 0; + int nr_freed = 0; + unsigned int order; int prefetch_nr = READ_ONCE(pcp->batch); bool isolated_pageblocks; struct page *page, *tmp; @@ -1425,7 +1483,7 @@ static void free_pcppages_bulk(struct zone *zone, int count, * below while (list_empty(list)) loop. */ count = min(pcp->count, count); - while (count) { + while (count > 0) { struct list_head *list; /* @@ -1437,24 +1495,31 @@ static void free_pcppages_bulk(struct zone *zone, int count, */ do { batch_free++; - if (++migratetype == MIGRATE_PCPTYPES) - migratetype = 0; - list = &pcp->lists[migratetype]; + if (++pindex == NR_PCP_LISTS) + pindex = 0; + list = &pcp->lists[pindex]; } while (list_empty(list)); /* This is the only non-empty list. Free them all. */ - if (batch_free == MIGRATE_PCPTYPES) + if (batch_free == NR_PCP_LISTS) batch_free = count; + order = pindex_to_order(pindex); + BUILD_BUG_ON(MAX_ORDER >= (1<lru); - pcp->count--; + nr_freed += 1 << order; + count -= 1 << order; if (bulkfree_pcp_prepare(page)) continue; + /* Encode order with the migratetype */ + page->index <<= NR_PCP_ORDER_WIDTH; + page->index |= order; + list_add_tail(&page->lru, &head); /* @@ -1470,9 +1535,14 @@ static void free_pcppages_bulk(struct zone *zone, int count, prefetch_buddy(page); prefetch_nr--; } - } while (--count && --batch_free && !list_empty(list)); + } while (count > 0 && --batch_free && !list_empty(list)); } + pcp->count -= nr_freed; + /* + * local_lock_irq held so equivalent to spin_lock_irqsave for + * both PREEMPT_RT and non-PREEMPT_RT configurations. + */ spin_lock(&zone->lock); isolated_pageblocks = has_isolate_pageblock(zone); @@ -1482,14 +1552,19 @@ static void free_pcppages_bulk(struct zone *zone, int count, */ list_for_each_entry_safe(page, tmp, &head, lru) { int mt = get_pcppage_migratetype(page); + + /* mt has been encoded with the order (see above) */ + order = mt & NR_PCP_ORDER_MASK; + mt >>= NR_PCP_ORDER_WIDTH; + /* MIGRATE_ISOLATE page should not go to pcplists */ VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); /* Pageblock could have been isolated meanwhile */ if (unlikely(isolated_pageblocks)) mt = get_pageblock_migratetype(page); - __free_one_page(page, page_to_pfn(page), zone, 0, mt, FPI_NONE); - trace_mm_page_pcpu_drain(page, 0, mt); + __free_one_page(page, page_to_pfn(page), zone, order, mt, FPI_NONE); + trace_mm_page_pcpu_drain(page, order, mt); } spin_unlock(&zone->lock); } @@ -1499,13 +1574,15 @@ static void free_one_page(struct zone *zone, unsigned int order, int migratetype, fpi_t fpi_flags) { - spin_lock(&zone->lock); + unsigned long flags; + + spin_lock_irqsave(&zone->lock, flags); if (unlikely(has_isolate_pageblock(zone) || is_migrate_isolate(migratetype))) { migratetype = get_pfnblock_migratetype(page, pfn); } __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); - spin_unlock(&zone->lock); + spin_unlock_irqrestore(&zone->lock, flags); } static void __meminit __init_single_page(struct page *page, unsigned long pfn, @@ -1588,16 +1665,22 @@ static void __free_pages_ok(struct page *page, unsigned int order, unsigned long flags; int migratetype; unsigned long pfn = page_to_pfn(page); + struct zone *zone = page_zone(page); if (!free_pages_prepare(page, order, true, fpi_flags)) return; migratetype = get_pfnblock_migratetype(page, pfn); - local_irq_save(flags); + + spin_lock_irqsave(&zone->lock, flags); + if (unlikely(has_isolate_pageblock(zone) || + is_migrate_isolate(migratetype))) { + migratetype = get_pfnblock_migratetype(page, pfn); + } + __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); + spin_unlock_irqrestore(&zone->lock, flags); + __count_vm_events(PGFREE, 1 << order); - free_one_page(page_zone(page), page, pfn, order, migratetype, - fpi_flags); - local_irq_restore(flags); } void __free_pages_core(struct page *page, unsigned int order) @@ -1629,7 +1712,7 @@ void __free_pages_core(struct page *page, unsigned int order) __free_pages_ok(page, order, FPI_TO_TAIL | FPI_SKIP_KASAN_POISON); } -#ifdef CONFIG_NEED_MULTIPLE_NODES +#ifdef CONFIG_NUMA /* * During memory init memblocks map pfns to nids. The search is expensive and @@ -1679,7 +1762,7 @@ int __meminit early_pfn_to_nid(unsigned long pfn) return nid; } -#endif /* CONFIG_NEED_MULTIPLE_NODES */ +#endif /* CONFIG_NUMA */ void __init memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order) @@ -2166,14 +2249,6 @@ void __init page_alloc_init_late(void) /* Block until all are initialised */ wait_for_completion(&pgdat_init_all_done_comp); - /* - * The number of managed pages has changed due to the initialisation - * so the pcpu batch and high limits needs to be updated or the limits - * will be artificially small. - */ - for_each_populated_zone(zone) - zone_pcp_update(zone); - /* * We initialized the rest of the deferred pages. Permanently disable * on-demand struct page initialization. @@ -2979,6 +3054,10 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, { int i, allocated = 0; + /* + * local_lock_irq held so equivalent to spin_lock_irqsave for + * both PREEMPT_RT and non-PREEMPT_RT configurations. + */ spin_lock(&zone->lock); for (i = 0; i < count; ++i) { struct page *page = __rmqueue(zone, order, migratetype, @@ -3031,12 +3110,12 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) unsigned long flags; int to_drain, batch; - local_irq_save(flags); + local_lock_irqsave(&pagesets.lock, flags); batch = READ_ONCE(pcp->batch); to_drain = min(pcp->count, batch); if (to_drain > 0) free_pcppages_bulk(zone, to_drain, pcp); - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); } #endif @@ -3050,16 +3129,15 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) static void drain_pages_zone(unsigned int cpu, struct zone *zone) { unsigned long flags; - struct per_cpu_pageset *pset; struct per_cpu_pages *pcp; - local_irq_save(flags); - pset = per_cpu_ptr(zone->pageset, cpu); + local_lock_irqsave(&pagesets.lock, flags); - pcp = &pset->pcp; + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); if (pcp->count) free_pcppages_bulk(zone, pcp->count, pcp); - local_irq_restore(flags); + + local_unlock_irqrestore(&pagesets.lock, flags); } /* @@ -3157,7 +3235,7 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) * disables preemption as part of its processing */ for_each_online_cpu(cpu) { - struct per_cpu_pageset *pcp; + struct per_cpu_pages *pcp; struct zone *z; bool has_pcps = false; @@ -3168,13 +3246,13 @@ static void __drain_all_pages(struct zone *zone, bool force_all_cpus) */ has_pcps = true; } else if (zone) { - pcp = per_cpu_ptr(zone->pageset, cpu); - if (pcp->pcp.count) + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + if (pcp->count) has_pcps = true; } else { for_each_populated_zone(z) { - pcp = per_cpu_ptr(z->pageset, cpu); - if (pcp->pcp.count) { + pcp = per_cpu_ptr(z->per_cpu_pageset, cpu); + if (pcp->count) { has_pcps = true; break; } @@ -3267,11 +3345,12 @@ void mark_free_pages(struct zone *zone) } #endif /* CONFIG_PM */ -static bool free_unref_page_prepare(struct page *page, unsigned long pfn) +static bool free_unref_page_prepare(struct page *page, unsigned long pfn, + unsigned int order) { int migratetype; - if (!free_pcp_prepare(page)) + if (!free_pcp_prepare(page, order)) return false; migratetype = get_pfnblock_migratetype(page, pfn); @@ -3279,52 +3358,99 @@ static bool free_unref_page_prepare(struct page *page, unsigned long pfn) return true; } -static void free_unref_page_commit(struct page *page, unsigned long pfn) +static int nr_pcp_free(struct per_cpu_pages *pcp, int high, int batch) +{ + int min_nr_free, max_nr_free; + + /* Check for PCP disabled or boot pageset */ + if (unlikely(high < batch)) + return 1; + + /* Leave at least pcp->batch pages on the list */ + min_nr_free = batch; + max_nr_free = high - batch; + + /* + * Double the number of pages freed each time there is subsequent + * freeing of pages without any allocation. + */ + batch <<= pcp->free_factor; + if (batch < max_nr_free) + pcp->free_factor++; + batch = clamp(batch, min_nr_free, max_nr_free); + + return batch; +} + +static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone) +{ + int high = READ_ONCE(pcp->high); + + if (unlikely(!high)) + return 0; + + if (!test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags)) + return high; + + /* + * If reclaim is active, limit the number of pages that can be + * stored on pcp lists + */ + return min(READ_ONCE(pcp->batch) << 2, high); +} + +static void free_unref_page_commit(struct page *page, unsigned long pfn, + int migratetype, unsigned int order) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; + int high; + int pindex; + + __count_vm_event(PGFREE); + pcp = this_cpu_ptr(zone->per_cpu_pageset); + pindex = order_to_pindex(migratetype, order); + list_add(&page->lru, &pcp->lists[pindex]); + pcp->count += 1 << order; + high = nr_pcp_high(pcp, zone); + if (pcp->count >= high) { + int batch = READ_ONCE(pcp->batch); + + free_pcppages_bulk(zone, nr_pcp_free(pcp, high, batch), pcp); + } +} + +/* + * Free a pcp page + */ +void free_unref_page(struct page *page, unsigned int order) +{ + unsigned long flags; + unsigned long pfn = page_to_pfn(page); int migratetype; - migratetype = get_pcppage_migratetype(page); - __count_vm_event(PGFREE); + if (!free_unref_page_prepare(page, pfn, order)) + return; /* * We only track unmovable, reclaimable and movable on pcp lists. - * Free ISOLATE pages back to the allocator because they are being + * Place ISOLATE pages on the isolated list because they are being * offlined but treat HIGHATOMIC as movable pages so we can get those * areas back if necessary. Otherwise, we may have to free * excessively into the page allocator */ - if (migratetype >= MIGRATE_PCPTYPES) { + migratetype = get_pcppage_migratetype(page); + if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(zone, page, pfn, 0, migratetype, - FPI_NONE); + free_one_page(page_zone(page), page, pfn, order, migratetype, FPI_NONE); return; } migratetype = MIGRATE_MOVABLE; } - pcp = &this_cpu_ptr(zone->pageset)->pcp; - list_add(&page->lru, &pcp->lists[migratetype]); - pcp->count++; - if (pcp->count >= READ_ONCE(pcp->high)) - free_pcppages_bulk(zone, READ_ONCE(pcp->batch), pcp); -} - -/* - * Free a 0-order page - */ -void free_unref_page(struct page *page) -{ - unsigned long flags; - unsigned long pfn = page_to_pfn(page); - - if (!free_unref_page_prepare(page, pfn)) - return; - - local_irq_save(flags); - free_unref_page_commit(page, pfn); - local_irq_restore(flags); + local_lock_irqsave(&pagesets.lock, flags); + free_unref_page_commit(page, pfn, migratetype, order); + local_unlock_irqrestore(&pagesets.lock, flags); } /* @@ -3335,34 +3461,56 @@ void free_unref_page_list(struct list_head *list) struct page *page, *next; unsigned long flags, pfn; int batch_count = 0; + int migratetype; /* Prepare pages for freeing */ list_for_each_entry_safe(page, next, list, lru) { pfn = page_to_pfn(page); - if (!free_unref_page_prepare(page, pfn)) + if (!free_unref_page_prepare(page, pfn, 0)) list_del(&page->lru); + + /* + * Free isolated pages directly to the allocator, see + * comment in free_unref_page. + */ + migratetype = get_pcppage_migratetype(page); + if (unlikely(migratetype >= MIGRATE_PCPTYPES)) { + if (unlikely(is_migrate_isolate(migratetype))) { + list_del(&page->lru); + free_one_page(page_zone(page), page, pfn, 0, + migratetype, FPI_NONE); + continue; + } + + /* + * Non-isolated types over MIGRATE_PCPTYPES get added + * to the MIGRATE_MOVABLE pcp list. + */ + set_pcppage_migratetype(page, MIGRATE_MOVABLE); + } + set_page_private(page, pfn); } - local_irq_save(flags); + local_lock_irqsave(&pagesets.lock, flags); list_for_each_entry_safe(page, next, list, lru) { - unsigned long pfn = page_private(page); - + pfn = page_private(page); set_page_private(page, 0); + migratetype = get_pcppage_migratetype(page); trace_mm_page_free_batched(page); - free_unref_page_commit(page, pfn); + free_unref_page_commit(page, pfn, migratetype, 0); /* * Guard against excessive IRQ disabled times when we get * a large list of pages to free. */ if (++batch_count == SWAP_CLUSTER_MAX) { - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); batch_count = 0; - local_irq_save(flags); + local_lock_irqsave(&pagesets.lock, flags); } } - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); } /* @@ -3461,7 +3609,8 @@ void __putback_isolated_page(struct page *page, unsigned int order, int mt) * * Must be called with interrupts disabled. */ -static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) +static inline void zone_statistics(struct zone *preferred_zone, struct zone *z, + long nr_account) { #ifdef CONFIG_NUMA enum numa_stat_item local_stat = NUMA_LOCAL; @@ -3474,18 +3623,19 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) local_stat = NUMA_OTHER; if (zone_to_nid(z) == zone_to_nid(preferred_zone)) - __inc_numa_state(z, NUMA_HIT); + __count_numa_events(z, NUMA_HIT, nr_account); else { - __inc_numa_state(z, NUMA_MISS); - __inc_numa_state(preferred_zone, NUMA_FOREIGN); + __count_numa_events(z, NUMA_MISS, nr_account); + __count_numa_events(preferred_zone, NUMA_FOREIGN, nr_account); } - __inc_numa_state(z, local_stat); + __count_numa_events(z, local_stat, nr_account); #endif } /* Remove page from the per-cpu list, caller must protect the list */ static inline -struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, +struct page *__rmqueue_pcplist(struct zone *zone, unsigned int order, + int migratetype, unsigned int alloc_flags, struct per_cpu_pages *pcp, struct list_head *list) @@ -3494,16 +3644,30 @@ struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, do { if (list_empty(list)) { - pcp->count += rmqueue_bulk(zone, 0, - READ_ONCE(pcp->batch), list, + int batch = READ_ONCE(pcp->batch); + int alloced; + + /* + * Scale batch relative to order if batch implies + * free pages can be stored on the PCP. Batch can + * be 1 for small zones or for boot pagesets which + * should never store free pages as the pages may + * belong to arbitrary zones. + */ + if (batch > 1) + batch = max(batch >> order, 2); + alloced = rmqueue_bulk(zone, order, + batch, list, migratetype, alloc_flags); + + pcp->count += alloced << order; if (unlikely(list_empty(list))) return NULL; } page = list_first_entry(list, struct page, lru); list_del(&page->lru); - pcp->count--; + pcp->count -= 1 << order; } while (check_new_pcp(page)); return page; @@ -3511,23 +3675,31 @@ struct page *__rmqueue_pcplist(struct zone *zone, int migratetype, /* Lock and remove page from the per-cpu list */ static struct page *rmqueue_pcplist(struct zone *preferred_zone, - struct zone *zone, gfp_t gfp_flags, - int migratetype, unsigned int alloc_flags) + struct zone *zone, unsigned int order, + gfp_t gfp_flags, int migratetype, + unsigned int alloc_flags) { struct per_cpu_pages *pcp; struct list_head *list; struct page *page; unsigned long flags; - local_irq_save(flags); - pcp = &this_cpu_ptr(zone->pageset)->pcp; - list = &pcp->lists[migratetype]; - page = __rmqueue_pcplist(zone, migratetype, alloc_flags, pcp, list); + local_lock_irqsave(&pagesets.lock, flags); + + /* + * On allocation, reduce the number of pages that are batch freed. + * See nr_pcp_free() where free_factor is increased for subsequent + * frees. + */ + pcp = this_cpu_ptr(zone->per_cpu_pageset); + pcp->free_factor >>= 1; + list = &pcp->lists[order_to_pindex(migratetype, order)]; + page = __rmqueue_pcplist(zone, order, migratetype, alloc_flags, pcp, list); + local_unlock_irqrestore(&pagesets.lock, flags); if (page) { __count_zid_vm_events(PGALLOC, page_zonenum(page), 1); - zone_statistics(preferred_zone, zone); + zone_statistics(preferred_zone, zone, 1); } - local_irq_restore(flags); return page; } @@ -3543,15 +3715,15 @@ struct page *rmqueue(struct zone *preferred_zone, unsigned long flags; struct page *page; - if (likely(order == 0)) { + if (likely(pcp_allowed_order(order))) { /* * MIGRATE_MOVABLE pcplist could have the pages on CMA area and * we need to skip it when CMA area isn't allowed. */ if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA || migratetype != MIGRATE_MOVABLE) { - page = rmqueue_pcplist(preferred_zone, zone, gfp_flags, - migratetype, alloc_flags); + page = rmqueue_pcplist(preferred_zone, zone, order, + gfp_flags, migratetype, alloc_flags); goto out; } } @@ -3579,15 +3751,15 @@ struct page *rmqueue(struct zone *preferred_zone, if (!page) page = __rmqueue(zone, order, migratetype, alloc_flags); } while (page && check_new_pages(page, order)); - spin_unlock(&zone->lock); if (!page) goto failed; + __mod_zone_freepage_state(zone, -(1 << order), get_pcppage_migratetype(page)); + spin_unlock_irqrestore(&zone->lock, flags); __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); - zone_statistics(preferred_zone, zone); - local_irq_restore(flags); + zone_statistics(preferred_zone, zone, 1); out: /* Separate test+clear to avoid unnecessary atomics */ @@ -3600,7 +3772,7 @@ out: return page; failed: - local_irq_restore(flags); + spin_unlock_irqrestore(&zone->lock, flags); return NULL; } @@ -4276,6 +4448,9 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, if (!order) return false; + if (fatal_signal_pending(current)) + return false; + if (compaction_made_progress(compact_result)) (*compaction_retries)++; @@ -5068,7 +5243,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, struct alloc_context ac; gfp_t alloc_gfp; unsigned int alloc_flags = ALLOC_WMARK_LOW; - int nr_populated = 0; + int nr_populated = 0, nr_account = 0; if (unlikely(nr_pages <= 0)) return 0; @@ -5125,9 +5300,9 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, goto failed; /* Attempt the batch allocation */ - local_irq_save(flags); - pcp = &this_cpu_ptr(zone->pageset)->pcp; - pcp_list = &pcp->lists[ac.migratetype]; + local_lock_irqsave(&pagesets.lock, flags); + pcp = this_cpu_ptr(zone->per_cpu_pageset); + pcp_list = &pcp->lists[order_to_pindex(ac.migratetype, 0)]; while (nr_populated < nr_pages) { @@ -5137,7 +5312,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, continue; } - page = __rmqueue_pcplist(zone, ac.migratetype, alloc_flags, + page = __rmqueue_pcplist(zone, 0, ac.migratetype, alloc_flags, pcp, pcp_list); if (unlikely(!page)) { /* Try and get at least one page */ @@ -5145,15 +5320,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, goto failed_irq; break; } - - /* - * Ideally this would be batched but the best way to do - * that cheaply is to first convert zone_statistics to - * be inaccurate per-cpu counter like vm_events to avoid - * a RMW cycle then do the accounting with IRQs enabled. - */ - __count_zid_vm_events(PGALLOC, zone_idx(zone), 1); - zone_statistics(ac.preferred_zoneref->zone, zone); + nr_account++; prep_new_page(page, 0, gfp, 0); if (page_list) @@ -5163,12 +5330,15 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, nr_populated++; } - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); + + __count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account); + zone_statistics(ac.preferred_zoneref->zone, zone, nr_account); return nr_populated; failed_irq: - local_irq_restore(flags); + local_unlock_irqrestore(&pagesets.lock, flags); failed: page = __alloc_pages(gfp, 0, preferred_nid, nodemask); @@ -5275,14 +5445,6 @@ unsigned long get_zeroed_page(gfp_t gfp_mask) } EXPORT_SYMBOL(get_zeroed_page); -static inline void free_the_page(struct page *page, unsigned int order) -{ - if (order == 0) /* Via pcp? */ - free_unref_page(page); - else - __free_pages_ok(page, order, FPI_NONE); -} - /** * __free_pages - Free pages allocated with alloc_pages(). * @page: The page pointer returned from alloc_pages(). @@ -5741,7 +5903,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) continue; for_each_online_cpu(cpu) - free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count; + free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count; } printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n" @@ -5833,7 +5995,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) free_pcp = 0; for_each_online_cpu(cpu) - free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count; + free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count; show_node(zone); printk(KERN_CONT @@ -5874,7 +6036,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(zone_page_state(zone, NR_MLOCK)), K(zone_page_state(zone, NR_BOUNCE)), K(free_pcp), - K(this_cpu_read(zone->pageset->pcp.count)), + K(this_cpu_read(zone->per_cpu_pageset->count)), K(zone_page_state(zone, NR_FREE_CMA_PAGES))); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) @@ -6201,11 +6363,12 @@ static void build_zonelists(pg_data_t *pgdat) * not check if the processor is online before following the pageset pointer. * Other parts of the kernel may not check if the zone is available. */ -static void pageset_init(struct per_cpu_pageset *p); +static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats); /* These effectively disable the pcplists in the boot pageset completely */ #define BOOT_PAGESET_HIGH 0 #define BOOT_PAGESET_BATCH 1 -static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset); +static DEFINE_PER_CPU(struct per_cpu_pages, boot_pageset); +static DEFINE_PER_CPU(struct per_cpu_zonestat, boot_zonestats); static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats); static void __build_all_zonelists(void *data) @@ -6272,7 +6435,7 @@ build_all_zonelists_init(void) * (a chicken-egg dilemma). */ for_each_possible_cpu(cpu) - pageset_init(&per_cpu(boot_pageset, cpu)); + per_cpu_pages_init(&per_cpu(boot_pageset, cpu), &per_cpu(boot_zonestats, cpu)); mminit_verify_zonelist(); cpuset_init_current_mems_allowed(); @@ -6424,7 +6587,7 @@ void __ref memmap_init_zone_device(struct zone *zone, return; /* - * The call to memmap_init_zone should have already taken care + * The call to memmap_init should have already taken care * of the pages reserved for the memmap, so we can just jump to * the end of that region and start processing the device pages. */ @@ -6485,11 +6648,11 @@ static void __meminit zone_init_free_lists(struct zone *zone) } } -#if !defined(CONFIG_FLAT_NODE_MEM_MAP) +#if !defined(CONFIG_FLATMEM) /* * Only struct pages that correspond to ranges defined by memblock.memory * are zeroed and initialized by going through __init_single_page() during - * memmap_init_zone(). + * memmap_init_zone_range(). * * But, there could be struct pages that correspond to holes in * memblock.memory. This can happen because of the following reasons: @@ -6508,9 +6671,9 @@ static void __meminit zone_init_free_lists(struct zone *zone) * zone/node above the hole except for the trailing pages in the last * section that will be appended to the zone/node below. */ -static u64 __meminit init_unavailable_range(unsigned long spfn, - unsigned long epfn, - int zone, int node) +static void __init init_unavailable_range(unsigned long spfn, + unsigned long epfn, + int zone, int node) { unsigned long pfn; u64 pgcnt = 0; @@ -6526,56 +6689,77 @@ static u64 __meminit init_unavailable_range(unsigned long spfn, pgcnt++; } - return pgcnt; + if (pgcnt) + pr_info("On node %d, zone %s: %lld pages in unavailable ranges", + node, zone_names[zone], pgcnt); } #else -static inline u64 init_unavailable_range(unsigned long spfn, unsigned long epfn, - int zone, int node) +static inline void init_unavailable_range(unsigned long spfn, + unsigned long epfn, + int zone, int node) { - return 0; } #endif -void __meminit __weak memmap_init_zone(struct zone *zone) +static void __init memmap_init_zone_range(struct zone *zone, + unsigned long start_pfn, + unsigned long end_pfn, + unsigned long *hole_pfn) { unsigned long zone_start_pfn = zone->zone_start_pfn; unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages; - int i, nid = zone_to_nid(zone), zone_id = zone_idx(zone); - static unsigned long hole_pfn; + int nid = zone_to_nid(zone), zone_id = zone_idx(zone); + + start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn); + end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn); + + if (start_pfn >= end_pfn) + return; + + memmap_init_range(end_pfn - start_pfn, nid, zone_id, start_pfn, + zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); + + if (*hole_pfn < start_pfn) + init_unavailable_range(*hole_pfn, start_pfn, zone_id, nid); + + *hole_pfn = end_pfn; +} + +static void __init memmap_init(void) +{ unsigned long start_pfn, end_pfn; - u64 pgcnt = 0; + unsigned long hole_pfn = 0; + int i, j, zone_id, nid; - for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { - start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn); - end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + struct pglist_data *node = NODE_DATA(nid); - if (end_pfn > start_pfn) - memmap_init_range(end_pfn - start_pfn, nid, - zone_id, start_pfn, zone_end_pfn, - MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); + for (j = 0; j < MAX_NR_ZONES; j++) { + struct zone *zone = node->node_zones + j; - if (hole_pfn < start_pfn) - pgcnt += init_unavailable_range(hole_pfn, start_pfn, - zone_id, nid); - hole_pfn = end_pfn; + if (!populated_zone(zone)) + continue; + + memmap_init_zone_range(zone, start_pfn, end_pfn, + &hole_pfn); + zone_id = j; + } } #ifdef CONFIG_SPARSEMEM /* - * Initialize the hole in the range [zone_end_pfn, section_end]. - * If zone boundary falls in the middle of a section, this hole - * will be re-initialized during the call to this function for the - * higher zone. + * Initialize the memory map for hole in the range [memory_end, + * section_end]. + * Append the pages in this hole to the highest zone in the last + * node. + * The call to init_unavailable_range() is outside the ifdef to + * silence the compiler warining about zone_id set but not used; + * for FLATMEM it is a nop anyway */ - end_pfn = round_up(zone_end_pfn, PAGES_PER_SECTION); + end_pfn = round_up(end_pfn, PAGES_PER_SECTION); if (hole_pfn < end_pfn) - pgcnt += init_unavailable_range(hole_pfn, end_pfn, - zone_id, nid); #endif - - if (pgcnt) - pr_info(" %s zone: %llu pages in unavailable ranges\n", - zone->name, pgcnt); + init_unavailable_range(hole_pfn, end_pfn, zone_id, nid); } static int zone_batchsize(struct zone *zone) @@ -6584,13 +6768,12 @@ static int zone_batchsize(struct zone *zone) int batch; /* - * The per-cpu-pages pools are set to around 1000th of the - * size of the zone. + * The number of pages to batch allocate is either ~0.1% + * of the zone or 1MB, whichever is smaller. The batch + * size is striking a balance between allocation latency + * and zone lock contention. */ - batch = zone_managed_pages(zone) / 1024; - /* But no more than a meg. */ - if (batch * PAGE_SIZE > 1024 * 1024) - batch = (1024 * 1024) / PAGE_SIZE; + batch = min(zone_managed_pages(zone) >> 10, (1024 * 1024) / PAGE_SIZE); batch /= 4; /* We effectively *= 4 below */ if (batch < 1) batch = 1; @@ -6627,6 +6810,54 @@ static int zone_batchsize(struct zone *zone) #endif } +static int zone_highsize(struct zone *zone, int batch, int cpu_online) +{ +#ifdef CONFIG_MMU + int high; + int nr_split_cpus; + unsigned long total_pages; + + if (!percpu_pagelist_high_fraction) { + /* + * By default, the high value of the pcp is based on the zone + * low watermark so that if they are full then background + * reclaim will not be started prematurely. + */ + total_pages = low_wmark_pages(zone); + } else { + /* + * If percpu_pagelist_high_fraction is configured, the high + * value is based on a fraction of the managed pages in the + * zone. + */ + total_pages = zone_managed_pages(zone) / percpu_pagelist_high_fraction; + } + + /* + * Split the high value across all online CPUs local to the zone. Note + * that early in boot that CPUs may not be online yet and that during + * CPU hotplug that the cpumask is not yet updated when a CPU is being + * onlined. For memory nodes that have no CPUs, split pcp->high across + * all online CPUs to mitigate the risk that reclaim is triggered + * prematurely due to pages stored on pcp lists. + */ + nr_split_cpus = cpumask_weight(cpumask_of_node(zone_to_nid(zone))) + cpu_online; + if (!nr_split_cpus) + nr_split_cpus = num_online_cpus(); + high = total_pages / nr_split_cpus; + + /* + * Ensure high is at least batch*4. The multiple is based on the + * historical relationship between high and batch. + */ + high = max(high, batch << 2); + + return high; +#else + return 0; +#endif +} + /* * pcp->high and pcp->batch values are related and generally batch is lower * than high. They are also related to pcp->count such that count is lower @@ -6650,16 +6881,15 @@ static void pageset_update(struct per_cpu_pages *pcp, unsigned long high, WRITE_ONCE(pcp->high, high); } -static void pageset_init(struct per_cpu_pageset *p) +static void per_cpu_pages_init(struct per_cpu_pages *pcp, struct per_cpu_zonestat *pzstats) { - struct per_cpu_pages *pcp; - int migratetype; + int pindex; - memset(p, 0, sizeof(*p)); + memset(pcp, 0, sizeof(*pcp)); + memset(pzstats, 0, sizeof(*pzstats)); - pcp = &p->pcp; - for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++) - INIT_LIST_HEAD(&pcp->lists[migratetype]); + for (pindex = 0; pindex < NR_PCP_LISTS; pindex++) + INIT_LIST_HEAD(&pcp->lists[pindex]); /* * Set batch and high values safe for a boot pageset. A true percpu @@ -6669,38 +6899,31 @@ static void pageset_init(struct per_cpu_pageset *p) */ pcp->high = BOOT_PAGESET_HIGH; pcp->batch = BOOT_PAGESET_BATCH; + pcp->free_factor = 0; } static void __zone_set_pageset_high_and_batch(struct zone *zone, unsigned long high, unsigned long batch) { - struct per_cpu_pageset *p; + struct per_cpu_pages *pcp; int cpu; for_each_possible_cpu(cpu) { - p = per_cpu_ptr(zone->pageset, cpu); - pageset_update(&p->pcp, high, batch); + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + pageset_update(pcp, high, batch); } } /* * Calculate and set new high and batch values for all per-cpu pagesets of a - * zone, based on the zone's size and the percpu_pagelist_fraction sysctl. + * zone based on the zone's size. */ -static void zone_set_pageset_high_and_batch(struct zone *zone) +static void zone_set_pageset_high_and_batch(struct zone *zone, int cpu_online) { - unsigned long new_high, new_batch; + int new_high, new_batch; - if (percpu_pagelist_fraction) { - new_high = zone_managed_pages(zone) / percpu_pagelist_fraction; - new_batch = max(1UL, new_high / 4); - if ((new_high / 4) > (PAGE_SHIFT * 8)) - new_batch = PAGE_SHIFT * 8; - } else { - new_batch = zone_batchsize(zone); - new_high = 6 * new_batch; - new_batch = max(1UL, 1 * new_batch); - } + new_batch = max(1, zone_batchsize(zone)); + new_high = zone_highsize(zone, new_batch, cpu_online); if (zone->pageset_high == new_high && zone->pageset_batch == new_batch) @@ -6714,16 +6937,23 @@ static void zone_set_pageset_high_and_batch(struct zone *zone) void __meminit setup_zone_pageset(struct zone *zone) { - struct per_cpu_pageset *p; int cpu; - zone->pageset = alloc_percpu(struct per_cpu_pageset); + /* Size may be 0 on !SMP && !NUMA */ + if (sizeof(struct per_cpu_zonestat) > 0) + zone->per_cpu_zonestats = alloc_percpu(struct per_cpu_zonestat); + + zone->per_cpu_pageset = alloc_percpu(struct per_cpu_pages); for_each_possible_cpu(cpu) { - p = per_cpu_ptr(zone->pageset, cpu); - pageset_init(p); + struct per_cpu_pages *pcp; + struct per_cpu_zonestat *pzstats; + + pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + per_cpu_pages_init(pcp, pzstats); } - zone_set_pageset_high_and_batch(zone); + zone_set_pageset_high_and_batch(zone, 0); } /* @@ -6747,9 +6977,9 @@ void __init setup_per_cpu_pageset(void) * the nodes these zones are associated with. */ for_each_possible_cpu(cpu) { - struct per_cpu_pageset *pcp = &per_cpu(boot_pageset, cpu); - memset(pcp->vm_numa_stat_diff, 0, - sizeof(pcp->vm_numa_stat_diff)); + struct per_cpu_zonestat *pzstats = &per_cpu(boot_zonestats, cpu); + memset(pzstats->vm_numa_event, 0, + sizeof(pzstats->vm_numa_event)); } #endif @@ -6765,14 +6995,14 @@ static __meminit void zone_pcp_init(struct zone *zone) * relies on the ability of the linker to provide the * offset of a (static) per cpu variable into the per cpu area. */ - zone->pageset = &boot_pageset; + zone->per_cpu_pageset = &boot_pageset; + zone->per_cpu_zonestats = &boot_zonestats; zone->pageset_high = BOOT_PAGESET_HIGH; zone->pageset_batch = BOOT_PAGESET_BATCH; if (populated_zone(zone)) - printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%u\n", - zone->name, zone->present_pages, - zone_batchsize(zone)); + pr_debug(" %s zone: %lu pages, LIFO batch:%u\n", zone->name, + zone->present_pages, zone_batchsize(zone)); } void __meminit init_currently_empty_zone(struct zone *zone, @@ -7042,8 +7272,7 @@ static void __init calculate_node_totalpages(struct pglist_data *pgdat, pgdat->node_spanned_pages = totalpages; pgdat->node_present_pages = realtotalpages; - printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, - realtotalpages); + pr_debug("On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); } #ifndef CONFIG_SPARSEMEM @@ -7243,19 +7472,17 @@ static void __init free_area_init_core(struct pglist_data *pgdat) if (freesize >= memmap_pages) { freesize -= memmap_pages; if (memmap_pages) - printk(KERN_DEBUG - " %s zone: %lu pages used for memmap\n", - zone_names[j], memmap_pages); + pr_debug(" %s zone: %lu pages used for memmap\n", + zone_names[j], memmap_pages); } else - pr_warn(" %s zone: %lu pages exceeds freesize %lu\n", + pr_warn(" %s zone: %lu memmap pages exceeds freesize %lu\n", zone_names[j], memmap_pages, freesize); } /* Account for reserved pages */ if (j == 0 && freesize > dma_reserve) { freesize -= dma_reserve; - printk(KERN_DEBUG " %s zone: %lu pages reserved\n", - zone_names[0], dma_reserve); + pr_debug(" %s zone: %lu pages reserved\n", zone_names[0], dma_reserve); } if (!is_highmem_idx(j)) @@ -7278,11 +7505,10 @@ static void __init free_area_init_core(struct pglist_data *pgdat) set_pageblock_order(); setup_usemap(zone); init_currently_empty_zone(zone, zone->zone_start_pfn, size); - memmap_init_zone(zone); } } -#ifdef CONFIG_FLAT_NODE_MEM_MAP +#ifdef CONFIG_FLATMEM static void __ref alloc_node_mem_map(struct pglist_data *pgdat) { unsigned long __maybe_unused start = 0; @@ -7317,7 +7543,7 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat) pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", __func__, pgdat->node_id, (unsigned long)pgdat, (unsigned long)pgdat->node_mem_map); -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA /* * With no DISCONTIG, the global mem_map is just set as node 0's */ @@ -7330,7 +7556,7 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat) } #else static void __ref alloc_node_mem_map(struct pglist_data *pgdat) { } -#endif /* CONFIG_FLAT_NODE_MEM_MAP */ +#endif /* CONFIG_FLATMEM */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT static inline void pgdat_set_deferred_range(pg_data_t *pgdat) @@ -7804,6 +8030,8 @@ void __init free_area_init(unsigned long *max_zone_pfn) node_set_state(nid, N_MEMORY); check_for_memory(pgdat, nid); } + + memmap_init(); } static int __init cmdline_parse_core(char *p, unsigned long *core, @@ -7980,6 +8208,7 @@ void __init set_dma_reserve(unsigned long new_dma_reserve) static int page_alloc_cpu_dead(unsigned int cpu) { + struct zone *zone; lru_add_drain_cpu(cpu); drain_pages(cpu); @@ -8000,6 +8229,19 @@ static int page_alloc_cpu_dead(unsigned int cpu) * race with what we are doing. */ cpu_vm_stats_fold(cpu); + + for_each_populated_zone(zone) + zone_pcp_update(zone, 0); + + return 0; +} + +static int page_alloc_cpu_online(unsigned int cpu) +{ + struct zone *zone; + + for_each_populated_zone(zone) + zone_pcp_update(zone, 1); return 0; } @@ -8025,8 +8267,9 @@ void __init page_alloc_init(void) hashdist = 0; #endif - ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC_DEAD, - "mm/page_alloc:dead", NULL, + ret = cpuhp_setup_state_nocalls(CPUHP_PAGE_ALLOC, + "mm/page_alloc:pcp", + page_alloc_cpu_online, page_alloc_cpu_dead); WARN_ON(ret < 0); } @@ -8089,14 +8332,14 @@ static void setup_per_zone_lowmem_reserve(void) unsigned long managed_pages = 0; for (j = i + 1; j < MAX_NR_ZONES; j++) { - if (clear) { - zone->lowmem_reserve[j] = 0; - } else { - struct zone *upper_zone = &pgdat->node_zones[j]; + struct zone *upper_zone = &pgdat->node_zones[j]; - managed_pages += zone_managed_pages(upper_zone); + managed_pages += zone_managed_pages(upper_zone); + + if (clear) + zone->lowmem_reserve[j] = 0; + else zone->lowmem_reserve[j] = managed_pages / ratio; - } } } } @@ -8179,11 +8422,19 @@ static void __setup_per_zone_wmarks(void) */ void setup_per_zone_wmarks(void) { + struct zone *zone; static DEFINE_SPINLOCK(lock); spin_lock(&lock); __setup_per_zone_wmarks(); spin_unlock(&lock); + + /* + * The watermark size have changed so update the pcpu batch + * and high limits or the limits may be inappropriate. + */ + for_each_zone(zone) + zone_pcp_update(zone, 0); } /* @@ -8362,38 +8613,38 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write, } /* - * percpu_pagelist_fraction - changes the pcp->high for each zone on each - * cpu. It is the fraction of total pages in each zone that a hot per cpu + * percpu_pagelist_high_fraction - changes the pcp->high for each zone on each + * cpu. It is the fraction of total pages in each zone that a hot per cpu * pagelist can have before it gets flushed back to buddy allocator. */ -int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write, - void *buffer, size_t *length, loff_t *ppos) +int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *table, + int write, void *buffer, size_t *length, loff_t *ppos) { struct zone *zone; - int old_percpu_pagelist_fraction; + int old_percpu_pagelist_high_fraction; int ret; mutex_lock(&pcp_batch_high_lock); - old_percpu_pagelist_fraction = percpu_pagelist_fraction; + old_percpu_pagelist_high_fraction = percpu_pagelist_high_fraction; ret = proc_dointvec_minmax(table, write, buffer, length, ppos); if (!write || ret < 0) goto out; /* Sanity checking to avoid pcp imbalance */ - if (percpu_pagelist_fraction && - percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) { - percpu_pagelist_fraction = old_percpu_pagelist_fraction; + if (percpu_pagelist_high_fraction && + percpu_pagelist_high_fraction < MIN_PERCPU_PAGELIST_HIGH_FRACTION) { + percpu_pagelist_high_fraction = old_percpu_pagelist_high_fraction; ret = -EINVAL; goto out; } /* No change? */ - if (percpu_pagelist_fraction == old_percpu_pagelist_fraction) + if (percpu_pagelist_high_fraction == old_percpu_pagelist_high_fraction) goto out; for_each_populated_zone(zone) - zone_set_pageset_high_and_batch(zone); + zone_set_pageset_high_and_batch(zone, 0); out: mutex_unlock(&pcp_batch_high_lock); return ret; @@ -8748,7 +8999,8 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, lru_cache_enable(); if (ret < 0) { - alloc_contig_dump_pages(&cc->migratepages); + if (ret == -EBUSY) + alloc_contig_dump_pages(&cc->migratepages); putback_movable_pages(&cc->migratepages); return ret; } @@ -9021,10 +9273,10 @@ EXPORT_SYMBOL(free_contig_range); * The zone indicated has a new number of managed_pages; batch sizes and percpu * page high values need to be recalculated. */ -void __meminit zone_pcp_update(struct zone *zone) +void zone_pcp_update(struct zone *zone, int cpu_online) { mutex_lock(&pcp_batch_high_lock); - zone_set_pageset_high_and_batch(zone); + zone_set_pageset_high_and_batch(zone, cpu_online); mutex_unlock(&pcp_batch_high_lock); } @@ -9052,15 +9304,17 @@ void zone_pcp_enable(struct zone *zone) void zone_pcp_reset(struct zone *zone) { int cpu; - struct per_cpu_pageset *pset; + struct per_cpu_zonestat *pzstats; - if (zone->pageset != &boot_pageset) { + if (zone->per_cpu_pageset != &boot_pageset) { for_each_online_cpu(cpu) { - pset = per_cpu_ptr(zone->pageset, cpu); - drain_zonestat(zone, pset); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + drain_zonestat(zone, pzstats); } - free_percpu(zone->pageset); - zone->pageset = &boot_pageset; + free_percpu(zone->per_cpu_pageset); + free_percpu(zone->per_cpu_zonestats); + zone->per_cpu_pageset = &boot_pageset; + zone->per_cpu_zonestats = &boot_zonestats; } } diff --git a/mm/page_ext.c b/mm/page_ext.c index df6f74aac8e1..293b2685fc48 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -191,7 +191,7 @@ fail: panic("Out of memory"); } -#else /* CONFIG_FLAT_NODE_MEM_MAP */ +#else /* CONFIG_FLATMEM */ struct page_ext *lookup_page_ext(const struct page *page) { diff --git a/mm/page_owner.c b/mm/page_owner.c index adfabb560eb9..f51a57e92aa3 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -392,7 +392,7 @@ err: return -ENOMEM; } -void __dump_page_owner(struct page *page) +void __dump_page_owner(const struct page *page) { struct page_ext *page_ext = lookup_page_ext(page); struct page_owner *page_owner; diff --git a/mm/page_reporting.c b/mm/page_reporting.c index c50d93ffa252..382958eef8a9 100644 --- a/mm/page_reporting.c +++ b/mm/page_reporting.c @@ -4,12 +4,17 @@ #include #include #include +#include #include #include #include "page_reporting.h" #include "internal.h" +unsigned int page_reporting_order = MAX_ORDER; +module_param(page_reporting_order, uint, 0644); +MODULE_PARM_DESC(page_reporting_order, "Set page reporting order"); + #define PAGE_REPORTING_DELAY (2 * HZ) static struct page_reporting_dev_info __rcu *pr_dev_info __read_mostly; @@ -31,8 +36,8 @@ __page_reporting_request(struct page_reporting_dev_info *prdev) return; /* - * If reporting is already active there is nothing we need to do. - * Test against 0 as that represents PAGE_REPORTING_IDLE. + * If reporting is already active there is nothing we need to do. + * Test against 0 as that represents PAGE_REPORTING_IDLE. */ state = atomic_xchg(&prdev->state, PAGE_REPORTING_REQUESTED); if (state != PAGE_REPORTING_IDLE) @@ -229,7 +234,7 @@ page_reporting_process_zone(struct page_reporting_dev_info *prdev, /* Generate minimum watermark to be able to guarantee progress */ watermark = low_wmark_pages(zone) + - (PAGE_REPORTING_CAPACITY << PAGE_REPORTING_MIN_ORDER); + (PAGE_REPORTING_CAPACITY << page_reporting_order); /* * Cancel request if insufficient free memory or if we failed @@ -239,7 +244,7 @@ page_reporting_process_zone(struct page_reporting_dev_info *prdev, return err; /* Process each free list starting from lowest order/mt */ - for (order = PAGE_REPORTING_MIN_ORDER; order < MAX_ORDER; order++) { + for (order = page_reporting_order; order < MAX_ORDER; order++) { for (mt = 0; mt < MIGRATE_TYPES; mt++) { /* We do not pull pages from the isolate free list */ if (is_migrate_isolate(mt)) @@ -324,6 +329,12 @@ int page_reporting_register(struct page_reporting_dev_info *prdev) goto err_out; } + /* + * Update the page reporting order if it's specified by driver. + * Otherwise, it falls back to @pageblock_order. + */ + page_reporting_order = prdev->order ? : pageblock_order; + /* initialize state and work structures */ atomic_set(&prdev->state, PAGE_REPORTING_IDLE); INIT_DELAYED_WORK(&prdev->work, &page_reporting_process); diff --git a/mm/page_reporting.h b/mm/page_reporting.h index 2c385dd4ddbd..c51dbc228b94 100644 --- a/mm/page_reporting.h +++ b/mm/page_reporting.h @@ -10,10 +10,9 @@ #include #include -#define PAGE_REPORTING_MIN_ORDER pageblock_order - #ifdef CONFIG_PAGE_REPORTING DECLARE_STATIC_KEY_FALSE(page_reporting_enabled); +extern unsigned int page_reporting_order; void __page_reporting_notify(void); static inline bool page_reported(struct page *page) @@ -38,7 +37,7 @@ static inline void page_reporting_notify_free(unsigned int order) return; /* Determine if we have crossed reporting threshold */ - if (order < PAGE_REPORTING_MIN_ORDER) + if (order < page_reporting_order) return; /* This will add a few cycles, but should be called infrequently */ diff --git a/mm/pagewalk.c b/mm/pagewalk.c index e81640d9f177..9b3db11a4d1d 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -58,6 +58,45 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, return err; } +#ifdef CONFIG_ARCH_HAS_HUGEPD +static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr, + unsigned long end, struct mm_walk *walk, int pdshift) +{ + int err = 0; + const struct mm_walk_ops *ops = walk->ops; + int shift = hugepd_shift(*phpd); + int page_size = 1 << shift; + + if (!ops->pte_entry) + return 0; + + if (addr & (page_size - 1)) + return 0; + + for (;;) { + pte_t *pte; + + spin_lock(&walk->mm->page_table_lock); + pte = hugepte_offset(*phpd, addr, pdshift); + err = ops->pte_entry(pte, addr, addr + page_size, walk); + spin_unlock(&walk->mm->page_table_lock); + + if (err) + break; + if (addr >= end - page_size) + break; + addr += page_size; + } + return err; +} +#else +static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr, + unsigned long end, struct mm_walk *walk, int pdshift) +{ + return 0; +} +#endif + static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -108,7 +147,10 @@ again: goto again; } - err = walk_pte_range(pmd, addr, next, walk); + if (is_hugepd(__hugepd(pmd_val(*pmd)))) + err = walk_hugepd_range((hugepd_t *)pmd, addr, next, walk, PMD_SHIFT); + else + err = walk_pte_range(pmd, addr, next, walk); if (err) break; } while (pmd++, addr = next, addr != end); @@ -157,7 +199,10 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, if (pud_none(*pud)) goto again; - err = walk_pmd_range(pud, addr, next, walk); + if (is_hugepd(__hugepd(pud_val(*pud)))) + err = walk_hugepd_range((hugepd_t *)pud, addr, next, walk, PUD_SHIFT); + else + err = walk_pmd_range(pud, addr, next, walk); if (err) break; } while (pud++, addr = next, addr != end); @@ -189,7 +234,9 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, if (err) break; } - if (ops->pud_entry || ops->pmd_entry || ops->pte_entry) + if (is_hugepd(__hugepd(p4d_val(*p4d)))) + err = walk_hugepd_range((hugepd_t *)p4d, addr, next, walk, P4D_SHIFT); + else if (ops->pud_entry || ops->pmd_entry || ops->pte_entry) err = walk_pud_range(p4d, addr, next, walk); if (err) break; @@ -224,8 +271,9 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, if (err) break; } - if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || - ops->pte_entry) + if (is_hugepd(__hugepd(pgd_val(*pgd)))) + err = walk_hugepd_range((hugepd_t *)pgd, addr, next, walk, PGDIR_SHIFT); + else if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || ops->pte_entry) err = walk_p4d_range(pgd, addr, next, walk); if (err) break; diff --git a/mm/shmem.c b/mm/shmem.c index 5d46611cba8d..6268b9b4e41a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1695,8 +1695,9 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); - struct mm_struct *charge_mm = vma ? vma->vm_mm : current->mm; - struct page *page; + struct mm_struct *charge_mm = vma ? vma->vm_mm : NULL; + struct swap_info_struct *si; + struct page *page = NULL; swp_entry_t swap; int error; @@ -1704,6 +1705,12 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, swap = radix_to_swp_entry(*pagep); *pagep = NULL; + /* Prevent swapoff from happening to us. */ + si = get_swap_device(swap); + if (!si) { + error = EINVAL; + goto failed; + } /* Look it up and read it in.. */ page = lookup_swap_cache(swap, NULL, 0); if (!page) { @@ -1765,6 +1772,8 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index, swap_free(swap); *pagep = page; + if (si) + put_swap_device(si); return 0; failed: if (!shmem_confirm_swap(mapping, index, swap)) @@ -1775,6 +1784,9 @@ unlock: put_page(page); } + if (si) + put_swap_device(si); + return error; } @@ -1816,7 +1828,7 @@ repeat: } sbinfo = SHMEM_SB(inode->i_sb); - charge_mm = vma ? vma->vm_mm : current->mm; + charge_mm = vma ? vma->vm_mm : NULL; page = pagecache_get_page(mapping, index, FGP_ENTRY | FGP_HEAD | FGP_LOCK, 0); @@ -2227,7 +2239,7 @@ static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, } #endif -int shmem_lock(struct file *file, int lock, struct user_struct *user) +int shmem_lock(struct file *file, int lock, struct ucounts *ucounts) { struct inode *inode = file_inode(file); struct shmem_inode_info *info = SHMEM_I(inode); @@ -2239,13 +2251,13 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) * no serialization needed when called from shm_destroy(). */ if (lock && !(info->flags & VM_LOCKED)) { - if (!user_shm_lock(inode->i_size, user)) + if (!user_shm_lock(inode->i_size, ucounts)) goto out_nomem; info->flags |= VM_LOCKED; mapping_set_unevictable(file->f_mapping); } - if (!lock && (info->flags & VM_LOCKED) && user) { - user_shm_unlock(inode->i_size, user); + if (!lock && (info->flags & VM_LOCKED) && ucounts) { + user_shm_unlock(inode->i_size, ucounts); info->flags &= ~VM_LOCKED; mapping_clear_unevictable(file->f_mapping); } @@ -4092,7 +4104,7 @@ int shmem_unuse(unsigned int type, bool frontswap, return 0; } -int shmem_lock(struct file *file, int lock, struct user_struct *user) +int shmem_lock(struct file *file, int lock, struct ucounts *ucounts) { return 0; } diff --git a/mm/slab.h b/mm/slab.h index 47cc272e46ff..7824114aa896 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -233,6 +233,7 @@ DECLARE_STATIC_KEY_TRUE(slub_debug_enabled); DECLARE_STATIC_KEY_FALSE(slub_debug_enabled); #endif extern void print_tracking(struct kmem_cache *s, void *object); +long validate_slab_cache(struct kmem_cache *s); extern unsigned long get_each_object_track(struct kmem_cache *s, struct page *page, enum track_item alloc, int (*fn)(const struct kmem_cache *, const void *, @@ -270,6 +271,8 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla #ifdef CONFIG_MEMCG_KMEM int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, gfp_t gfp, bool new_page); +void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, + enum node_stat_item idx, int nr); static inline void memcg_free_page_obj_cgroups(struct page *page) { @@ -314,20 +317,6 @@ static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, return true; } -static inline void mod_objcg_state(struct obj_cgroup *objcg, - struct pglist_data *pgdat, - enum node_stat_item idx, int nr) -{ - struct mem_cgroup *memcg; - struct lruvec *lruvec; - - rcu_read_lock(); - memcg = obj_cgroup_memcg(objcg); - lruvec = mem_cgroup_lruvec(memcg, pgdat); - mod_memcg_lruvec_state(lruvec, idx, nr); - rcu_read_unlock(); -} - static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, struct obj_cgroup *objcg, gfp_t flags, size_t size, @@ -340,7 +329,6 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, if (!memcg_kmem_enabled() || !objcg) return; - flags &= ~__GFP_ACCOUNT; for (i = 0; i < size; i++) { if (likely(p[i])) { page = virt_to_head_page(p[i]); @@ -661,6 +649,12 @@ static inline bool slab_want_init_on_free(struct kmem_cache *c) return false; } +#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_SLUB_DEBUG) +void debugfs_slab_release(struct kmem_cache *); +#else +static inline void debugfs_slab_release(struct kmem_cache *s) { } +#endif + #ifdef CONFIG_PRINTK #define KS_ADDRS_COUNT 16 struct kmem_obj_info { diff --git a/mm/slab_common.c b/mm/slab_common.c index 7cab77655f11..c126e6f6b5a5 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -377,11 +377,11 @@ out_unlock: if (err) { if (flags & SLAB_PANIC) - panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n", - name, err); + panic("%s: Failed to create slab '%s'. Error %d\n", + __func__, name, err); else { - pr_warn("kmem_cache_create(%s) failed with error %d\n", - name, err); + pr_warn("%s(%s) failed with error %d\n", + __func__, name, err); dump_stack(); } return NULL; @@ -448,6 +448,7 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work) rcu_barrier(); list_for_each_entry_safe(s, s2, &to_destroy, list) { + debugfs_slab_release(s); kfence_shutdown_cache(s); #ifdef SLAB_SUPPORTS_SYSFS sysfs_slab_release(s); @@ -475,6 +476,7 @@ static int shutdown_cache(struct kmem_cache *s) schedule_work(&slab_caches_to_rcu_destroy_work); } else { kfence_shutdown_cache(s); + debugfs_slab_release(s); #ifdef SLAB_SUPPORTS_SYSFS sysfs_slab_unlink(s); sysfs_slab_release(s); @@ -508,8 +510,8 @@ void kmem_cache_destroy(struct kmem_cache *s) err = shutdown_cache(s); if (err) { - pr_err("kmem_cache_destroy %s: Slab cache still has objects\n", - s->name); + pr_err("%s %s: Slab cache still has objects\n", + __func__, s->name); dump_stack(); } out_unlock: @@ -736,26 +738,30 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) } #ifdef CONFIG_ZONE_DMA -#define INIT_KMALLOC_INFO(__size, __short_size) \ -{ \ - .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \ - .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \ - .name[KMALLOC_DMA] = "dma-kmalloc-" #__short_size, \ - .size = __size, \ -} +#define KMALLOC_DMA_NAME(sz) .name[KMALLOC_DMA] = "dma-kmalloc-" #sz, #else +#define KMALLOC_DMA_NAME(sz) +#endif + +#ifdef CONFIG_MEMCG_KMEM +#define KMALLOC_CGROUP_NAME(sz) .name[KMALLOC_CGROUP] = "kmalloc-cg-" #sz, +#else +#define KMALLOC_CGROUP_NAME(sz) +#endif + #define INIT_KMALLOC_INFO(__size, __short_size) \ { \ .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \ .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \ + KMALLOC_CGROUP_NAME(__short_size) \ + KMALLOC_DMA_NAME(__short_size) \ .size = __size, \ } -#endif /* * kmalloc_info[] is to make slub_debug=,kmalloc-xx option work at boot time. - * kmalloc_index() supports up to 2^26=64MB, so the final entry of the table is - * kmalloc-67108864. + * kmalloc_index() supports up to 2^25=32MB, so the final entry of the table is + * kmalloc-32M. */ const struct kmalloc_info_struct kmalloc_info[] __initconst = { INIT_KMALLOC_INFO(0, 0), @@ -783,8 +789,7 @@ const struct kmalloc_info_struct kmalloc_info[] __initconst = { INIT_KMALLOC_INFO(4194304, 4M), INIT_KMALLOC_INFO(8388608, 8M), INIT_KMALLOC_INFO(16777216, 16M), - INIT_KMALLOC_INFO(33554432, 32M), - INIT_KMALLOC_INFO(67108864, 64M) + INIT_KMALLOC_INFO(33554432, 32M) }; /* @@ -837,13 +842,27 @@ void __init setup_kmalloc_cache_index_table(void) static void __init new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags) { - if (type == KMALLOC_RECLAIM) + if (type == KMALLOC_RECLAIM) { flags |= SLAB_RECLAIM_ACCOUNT; + } else if (IS_ENABLED(CONFIG_MEMCG_KMEM) && (type == KMALLOC_CGROUP)) { + if (cgroup_memory_nokmem) { + kmalloc_caches[type][idx] = kmalloc_caches[KMALLOC_NORMAL][idx]; + return; + } + flags |= SLAB_ACCOUNT; + } kmalloc_caches[type][idx] = create_kmalloc_cache( kmalloc_info[idx].name[type], kmalloc_info[idx].size, flags, 0, kmalloc_info[idx].size); + + /* + * If CONFIG_MEMCG_KMEM is enabled, disable cache merging for + * KMALLOC_NORMAL caches. + */ + if (IS_ENABLED(CONFIG_MEMCG_KMEM) && (type == KMALLOC_NORMAL)) + kmalloc_caches[type][idx]->refcount = -1; } /* @@ -856,6 +875,9 @@ void __init create_kmalloc_caches(slab_flags_t flags) int i; enum kmalloc_cache_type type; + /* + * Including KMALLOC_CGROUP if CONFIG_MEMCG_KMEM defined + */ for (type = KMALLOC_NORMAL; type <= KMALLOC_RECLAIM; type++) { for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { if (!kmalloc_caches[type][i]) diff --git a/mm/slub.c b/mm/slub.c index 2ac8facae5a7..7cdf54a0d8a5 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -36,7 +36,9 @@ #include #include #include +#include +#include #include #include "internal.h" @@ -117,12 +119,26 @@ */ #ifdef CONFIG_SLUB_DEBUG + #ifdef CONFIG_SLUB_DEBUG_ON DEFINE_STATIC_KEY_TRUE(slub_debug_enabled); #else DEFINE_STATIC_KEY_FALSE(slub_debug_enabled); #endif -#endif + +static inline bool __slub_debug_enabled(void) +{ + return static_branch_unlikely(&slub_debug_enabled); +} + +#else /* CONFIG_SLUB_DEBUG */ + +static inline bool __slub_debug_enabled(void) +{ + return false; +} + +#endif /* CONFIG_SLUB_DEBUG */ static inline bool kmem_cache_debug(struct kmem_cache *s) { @@ -154,9 +170,6 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s) * - Variable sizing of the per node arrays */ -/* Enable to test recovery from slab corruption on boot */ -#undef SLUB_RESILIENCY_TEST - /* Enable to log cmpxchg failures */ #undef SLUB_DEBUG_CMPXCHG @@ -210,6 +223,12 @@ static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p) { return 0; } #endif +#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_SLUB_DEBUG) +static void debugfs_slab_add(struct kmem_cache *); +#else +static inline void debugfs_slab_add(struct kmem_cache *s) { } +#endif + static inline void stat(const struct kmem_cache *s, enum stat_item si) { #ifdef CONFIG_SLUB_STATS @@ -433,6 +452,26 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)]; static DEFINE_SPINLOCK(object_map_lock); +#if IS_ENABLED(CONFIG_KUNIT) +static bool slab_add_kunit_errors(void) +{ + struct kunit_resource *resource; + + if (likely(!current->kunit_test)) + return false; + + resource = kunit_find_named_resource(current->kunit_test, "slab_errors"); + if (!resource) + return false; + + (*(int *)resource->data)++; + kunit_put_resource(resource); + return true; +} +#else +static inline bool slab_add_kunit_errors(void) { return false; } +#endif + /* * Determine a map of object in use on a page. * @@ -686,16 +725,18 @@ static void slab_bug(struct kmem_cache *s, char *fmt, ...) pr_err("=============================================================================\n"); pr_err("BUG %s (%s): %pV\n", s->name, print_tainted(), &vaf); pr_err("-----------------------------------------------------------------------------\n\n"); - - add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); va_end(args); } +__printf(2, 3) static void slab_fix(struct kmem_cache *s, char *fmt, ...) { struct va_format vaf; va_list args; + if (slab_add_kunit_errors()) + return; + va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; @@ -759,8 +800,12 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) void object_err(struct kmem_cache *s, struct page *page, u8 *object, char *reason) { + if (slab_add_kunit_errors()) + return; + slab_bug(s, "%s", reason); print_trailer(s, page, object); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page, @@ -769,12 +814,16 @@ static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page, va_list args; char buf[100]; + if (slab_add_kunit_errors()) + return; + va_start(args, fmt); vsnprintf(buf, sizeof(buf), fmt, args); va_end(args); slab_bug(s, "%s", buf); print_page_info(page); dump_stack(); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } static void init_object(struct kmem_cache *s, void *object, u8 val) @@ -796,7 +845,7 @@ static void init_object(struct kmem_cache *s, void *object, u8 val) static void restore_bytes(struct kmem_cache *s, char *message, u8 data, void *from, void *to) { - slab_fix(s, "Restoring 0x%p-0x%p=0x%x\n", from, to - 1, data); + slab_fix(s, "Restoring %s 0x%p-0x%p=0x%x", message, from, to - 1, data); memset(from, data, to - from); } @@ -818,12 +867,17 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, while (end > fault && end[-1] == value) end--; + if (slab_add_kunit_errors()) + goto skip_bug_print; + slab_bug(s, "%s overwritten", what); pr_err("0x%p-0x%p @offset=%tu. First byte 0x%x instead of 0x%x\n", fault, end - 1, fault - addr, fault[0], value); print_trailer(s, page, object); + add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); +skip_bug_print: restore_bytes(s, what, value, fault, end); return 0; } @@ -1045,13 +1099,13 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search) slab_err(s, page, "Wrong number of objects. Found %d but should be %d", page->objects, max_objects); page->objects = max_objects; - slab_fix(s, "Number of objects adjusted."); + slab_fix(s, "Number of objects adjusted"); } if (page->inuse != page->objects - nr) { slab_err(s, page, "Wrong object count. Counter is %d but counted were %d", page->inuse, page->objects - nr); page->inuse = page->objects - nr; - slab_fix(s, "Object count adjusted."); + slab_fix(s, "Object count adjusted"); } return search == NULL; } @@ -1415,6 +1469,8 @@ static int __init setup_slub_debug(char *str) out: if (slub_debug != 0 || slub_debug_string) static_branch_enable(&slub_debug_enabled); + else + static_branch_disable(&slub_debug_enabled); if ((static_branch_unlikely(&init_on_alloc) || static_branch_unlikely(&init_on_free)) && (slub_debug & SLAB_POISON)) @@ -4470,6 +4526,10 @@ void __init kmem_cache_init(void) if (debug_guardpage_minorder()) slub_max_order = 0; + /* Print slub debugging pointers without hashing */ + if (__slub_debug_enabled()) + no_hash_pointers_enable(NULL); + kmem_cache_node = &boot_kmem_cache_node; kmem_cache = &boot_kmem_cache; @@ -4558,6 +4618,9 @@ int __kmem_cache_create(struct kmem_cache *s, slab_flags_t flags) if (err) __kmem_cache_release(s); + if (s->flags & SLAB_STORE_USER) + debugfs_slab_add(s); + return err; } @@ -4666,9 +4729,11 @@ static int validate_slab_node(struct kmem_cache *s, validate_slab(s, page); count++; } - if (count != n->nr_partial) + if (count != n->nr_partial) { pr_err("SLUB %s: %ld partial slabs counted but counter=%ld\n", s->name, count, n->nr_partial); + slab_add_kunit_errors(); + } if (!(s->flags & SLAB_STORE_USER)) goto out; @@ -4677,16 +4742,18 @@ static int validate_slab_node(struct kmem_cache *s, validate_slab(s, page); count++; } - if (count != atomic_long_read(&n->nr_slabs)) + if (count != atomic_long_read(&n->nr_slabs)) { pr_err("SLUB: %s %ld slabs counted but counter=%ld\n", s->name, count, atomic_long_read(&n->nr_slabs)); + slab_add_kunit_errors(); + } out: spin_unlock_irqrestore(&n->list_lock, flags); return count; } -static long validate_slab_cache(struct kmem_cache *s) +long validate_slab_cache(struct kmem_cache *s) { int node; unsigned long count = 0; @@ -4698,6 +4765,9 @@ static long validate_slab_cache(struct kmem_cache *s) return count; } +EXPORT_SYMBOL(validate_slab_cache); + +#ifdef CONFIG_DEBUG_FS /* * Generate lists of code addresses where slabcache objects are allocated * and freed. @@ -4721,6 +4791,8 @@ struct loc_track { struct location *loc; }; +static struct dentry *slab_debugfs_root; + static void free_loc_track(struct loc_track *t) { if (t->max) @@ -4837,144 +4909,9 @@ static void process_slab(struct loc_track *t, struct kmem_cache *s, add_location(t, s, get_track(s, p, alloc)); put_map(map); } - -static int list_locations(struct kmem_cache *s, char *buf, - enum track_item alloc) -{ - int len = 0; - unsigned long i; - struct loc_track t = { 0, 0, NULL }; - int node; - struct kmem_cache_node *n; - - if (!alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location), - GFP_KERNEL)) { - return sysfs_emit(buf, "Out of memory\n"); - } - /* Push back cpu slabs */ - flush_all(s); - - for_each_kmem_cache_node(s, node, n) { - unsigned long flags; - struct page *page; - - if (!atomic_long_read(&n->nr_slabs)) - continue; - - spin_lock_irqsave(&n->list_lock, flags); - list_for_each_entry(page, &n->partial, slab_list) - process_slab(&t, s, page, alloc); - list_for_each_entry(page, &n->full, slab_list) - process_slab(&t, s, page, alloc); - spin_unlock_irqrestore(&n->list_lock, flags); - } - - for (i = 0; i < t.count; i++) { - struct location *l = &t.loc[i]; - - len += sysfs_emit_at(buf, len, "%7ld ", l->count); - - if (l->addr) - len += sysfs_emit_at(buf, len, "%pS", (void *)l->addr); - else - len += sysfs_emit_at(buf, len, ""); - - if (l->sum_time != l->min_time) - len += sysfs_emit_at(buf, len, " age=%ld/%ld/%ld", - l->min_time, - (long)div_u64(l->sum_time, - l->count), - l->max_time); - else - len += sysfs_emit_at(buf, len, " age=%ld", l->min_time); - - if (l->min_pid != l->max_pid) - len += sysfs_emit_at(buf, len, " pid=%ld-%ld", - l->min_pid, l->max_pid); - else - len += sysfs_emit_at(buf, len, " pid=%ld", - l->min_pid); - - if (num_online_cpus() > 1 && - !cpumask_empty(to_cpumask(l->cpus))) - len += sysfs_emit_at(buf, len, " cpus=%*pbl", - cpumask_pr_args(to_cpumask(l->cpus))); - - if (nr_online_nodes > 1 && !nodes_empty(l->nodes)) - len += sysfs_emit_at(buf, len, " nodes=%*pbl", - nodemask_pr_args(&l->nodes)); - - len += sysfs_emit_at(buf, len, "\n"); - } - - free_loc_track(&t); - if (!t.count) - len += sysfs_emit_at(buf, len, "No data\n"); - - return len; -} +#endif /* CONFIG_DEBUG_FS */ #endif /* CONFIG_SLUB_DEBUG */ -#ifdef SLUB_RESILIENCY_TEST -static void __init resiliency_test(void) -{ - u8 *p; - int type = KMALLOC_NORMAL; - - BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || KMALLOC_SHIFT_HIGH < 10); - - pr_err("SLUB resiliency testing\n"); - pr_err("-----------------------\n"); - pr_err("A. Corruption after allocation\n"); - - p = kzalloc(16, GFP_KERNEL); - p[16] = 0x12; - pr_err("\n1. kmalloc-16: Clobber Redzone/next pointer 0x12->0x%p\n\n", - p + 16); - - validate_slab_cache(kmalloc_caches[type][4]); - - /* Hmmm... The next two are dangerous */ - p = kzalloc(32, GFP_KERNEL); - p[32 + sizeof(void *)] = 0x34; - pr_err("\n2. kmalloc-32: Clobber next pointer/next slab 0x34 -> -0x%p\n", - p); - pr_err("If allocated object is overwritten then not detectable\n\n"); - - validate_slab_cache(kmalloc_caches[type][5]); - p = kzalloc(64, GFP_KERNEL); - p += 64 + (get_cycles() & 0xff) * sizeof(void *); - *p = 0x56; - pr_err("\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n", - p); - pr_err("If allocated object is overwritten then not detectable\n\n"); - validate_slab_cache(kmalloc_caches[type][6]); - - pr_err("\nB. Corruption after free\n"); - p = kzalloc(128, GFP_KERNEL); - kfree(p); - *p = 0x78; - pr_err("1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p); - validate_slab_cache(kmalloc_caches[type][7]); - - p = kzalloc(256, GFP_KERNEL); - kfree(p); - p[50] = 0x9a; - pr_err("\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p); - validate_slab_cache(kmalloc_caches[type][8]); - - p = kzalloc(512, GFP_KERNEL); - kfree(p); - p[512] = 0xab; - pr_err("\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p); - validate_slab_cache(kmalloc_caches[type][9]); -} -#else -#ifdef CONFIG_SYSFS -static void resiliency_test(void) {}; -#endif -#endif /* SLUB_RESILIENCY_TEST */ - #ifdef CONFIG_SYSFS enum slab_stat_type { SL_ALL, /* All slabs */ @@ -5362,21 +5299,6 @@ static ssize_t validate_store(struct kmem_cache *s, } SLAB_ATTR(validate); -static ssize_t alloc_calls_show(struct kmem_cache *s, char *buf) -{ - if (!(s->flags & SLAB_STORE_USER)) - return -ENOSYS; - return list_locations(s, buf, TRACK_ALLOC); -} -SLAB_ATTR_RO(alloc_calls); - -static ssize_t free_calls_show(struct kmem_cache *s, char *buf) -{ - if (!(s->flags & SLAB_STORE_USER)) - return -ENOSYS; - return list_locations(s, buf, TRACK_FREE); -} -SLAB_ATTR_RO(free_calls); #endif /* CONFIG_SLUB_DEBUG */ #ifdef CONFIG_FAILSLAB @@ -5540,8 +5462,6 @@ static struct attribute *slab_attrs[] = { &poison_attr.attr, &store_user_attr.attr, &validate_attr.attr, - &alloc_calls_attr.attr, - &free_calls_attr.attr, #endif #ifdef CONFIG_ZONE_DMA &cache_dma_attr.attr, @@ -5823,13 +5743,179 @@ static int __init slab_sysfs_init(void) } mutex_unlock(&slab_mutex); - resiliency_test(); return 0; } __initcall(slab_sysfs_init); #endif /* CONFIG_SYSFS */ +#if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS) +static int slab_debugfs_show(struct seq_file *seq, void *v) +{ + + struct location *l; + unsigned int idx = *(unsigned int *)v; + struct loc_track *t = seq->private; + + if (idx < t->count) { + l = &t->loc[idx]; + + seq_printf(seq, "%7ld ", l->count); + + if (l->addr) + seq_printf(seq, "%pS", (void *)l->addr); + else + seq_puts(seq, ""); + + if (l->sum_time != l->min_time) { + seq_printf(seq, " age=%ld/%llu/%ld", + l->min_time, div_u64(l->sum_time, l->count), + l->max_time); + } else + seq_printf(seq, " age=%ld", l->min_time); + + if (l->min_pid != l->max_pid) + seq_printf(seq, " pid=%ld-%ld", l->min_pid, l->max_pid); + else + seq_printf(seq, " pid=%ld", + l->min_pid); + + if (num_online_cpus() > 1 && !cpumask_empty(to_cpumask(l->cpus))) + seq_printf(seq, " cpus=%*pbl", + cpumask_pr_args(to_cpumask(l->cpus))); + + if (nr_online_nodes > 1 && !nodes_empty(l->nodes)) + seq_printf(seq, " nodes=%*pbl", + nodemask_pr_args(&l->nodes)); + + seq_puts(seq, "\n"); + } + + if (!idx && !t->count) + seq_puts(seq, "No data\n"); + + return 0; +} + +static void slab_debugfs_stop(struct seq_file *seq, void *v) +{ +} + +static void *slab_debugfs_next(struct seq_file *seq, void *v, loff_t *ppos) +{ + struct loc_track *t = seq->private; + + v = ppos; + ++*ppos; + if (*ppos <= t->count) + return v; + + return NULL; +} + +static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos) +{ + return ppos; +} + +static const struct seq_operations slab_debugfs_sops = { + .start = slab_debugfs_start, + .next = slab_debugfs_next, + .stop = slab_debugfs_stop, + .show = slab_debugfs_show, +}; + +static int slab_debug_trace_open(struct inode *inode, struct file *filep) +{ + + struct kmem_cache_node *n; + enum track_item alloc; + int node; + struct loc_track *t = __seq_open_private(filep, &slab_debugfs_sops, + sizeof(struct loc_track)); + struct kmem_cache *s = file_inode(filep)->i_private; + + if (strcmp(filep->f_path.dentry->d_name.name, "alloc_traces") == 0) + alloc = TRACK_ALLOC; + else + alloc = TRACK_FREE; + + if (!alloc_loc_track(t, PAGE_SIZE / sizeof(struct location), GFP_KERNEL)) + return -ENOMEM; + + /* Push back cpu slabs */ + flush_all(s); + + for_each_kmem_cache_node(s, node, n) { + unsigned long flags; + struct page *page; + + if (!atomic_long_read(&n->nr_slabs)) + continue; + + spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, slab_list) + process_slab(t, s, page, alloc); + list_for_each_entry(page, &n->full, slab_list) + process_slab(t, s, page, alloc); + spin_unlock_irqrestore(&n->list_lock, flags); + } + + return 0; +} + +static int slab_debug_trace_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct loc_track *t = seq->private; + + free_loc_track(t); + return seq_release_private(inode, file); +} + +static const struct file_operations slab_debugfs_fops = { + .open = slab_debug_trace_open, + .read = seq_read, + .llseek = seq_lseek, + .release = slab_debug_trace_release, +}; + +static void debugfs_slab_add(struct kmem_cache *s) +{ + struct dentry *slab_cache_dir; + + if (unlikely(!slab_debugfs_root)) + return; + + slab_cache_dir = debugfs_create_dir(s->name, slab_debugfs_root); + + debugfs_create_file("alloc_traces", 0400, + slab_cache_dir, s, &slab_debugfs_fops); + + debugfs_create_file("free_traces", 0400, + slab_cache_dir, s, &slab_debugfs_fops); +} + +void debugfs_slab_release(struct kmem_cache *s) +{ + debugfs_remove_recursive(debugfs_lookup(s->name, slab_debugfs_root)); +} + +static int __init slab_debugfs_init(void) +{ + struct kmem_cache *s; + + slab_debugfs_root = debugfs_create_dir("slab", NULL); + + list_for_each_entry(s, &slab_caches, list) + if (s->flags & SLAB_STORE_USER) + debugfs_slab_add(s); + + return 0; + +} +__initcall(slab_debugfs_init); +#endif /* * The /proc/slabinfo ABI */ diff --git a/mm/sparse.c b/mm/sparse.c index 55c18aff3e42..7272f7a1449d 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -346,7 +346,7 @@ size_t mem_section_usage_size(void) static inline phys_addr_t pgdat_to_phys(struct pglist_data *pgdat) { -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA return __pa_symbol(pgdat); #else return __pa(pgdat); diff --git a/mm/swap.c b/mm/swap.c index dfb48cf9c2c9..6c11db780467 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -95,7 +95,7 @@ static void __put_single_page(struct page *page) { __page_cache_release(page); mem_cgroup_uncharge(page); - free_unref_page(page); + free_unref_page(page, 0); } static void __put_compound_page(struct page *page) @@ -313,7 +313,7 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) void lru_note_cost_page(struct page *page) { - lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)), + lru_note_cost(mem_cgroup_page_lruvec(page), page_is_file_lru(page), thp_nr_pages(page)); } diff --git a/mm/swap_slots.c b/mm/swap_slots.c index 6248d1030a9b..a66f3e0ec973 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -43,8 +43,6 @@ static DEFINE_MUTEX(swap_slots_cache_mutex); static DEFINE_MUTEX(swap_slots_cache_enable_mutex); static void __drain_swap_slots_cache(unsigned int type); -static void deactivate_swap_slots_cache(void); -static void reactivate_swap_slots_cache(void); #define use_swap_slot_cache (swap_slot_cache_active && swap_slot_cache_enabled) #define SLOTS_CACHE 0x1 diff --git a/mm/swap_state.c b/mm/swap_state.c index 272ea2108c9d..c56aa9ac050d 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -114,8 +114,6 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, SetPageSwapCache(page); do { - unsigned long nr_shadows = 0; - xas_lock_irq(&xas); xas_create_range(&xas); if (xas_error(&xas)) @@ -124,7 +122,6 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, VM_BUG_ON_PAGE(xas.xa_index != idx + i, page); old = xas_load(&xas); if (xa_is_value(old)) { - nr_shadows++; if (shadowp) *shadowp = old; } @@ -260,7 +257,6 @@ void clear_shadow_from_swap_cache(int type, unsigned long begin, void *old; for (;;) { - unsigned long nr_shadows = 0; swp_entry_t entry = swp_entry(type, curr); struct address_space *address_space = swap_address_space(entry); XA_STATE(xas, &address_space->i_pages, curr); @@ -270,7 +266,6 @@ void clear_shadow_from_swap_cache(int type, unsigned long begin, if (!xa_is_value(old)) continue; xas_store(&xas, NULL); - nr_shadows++; } xa_unlock_irq(&address_space->i_pages); @@ -291,7 +286,7 @@ void clear_shadow_from_swap_cache(int type, unsigned long begin, * try_to_free_swap() _with_ the lock. * - Marcelo */ -static inline void free_swap_cache(struct page *page) +void free_swap_cache(struct page *page) { if (PageSwapCache(page) && !page_mapped(page) && trylock_page(page)) { try_to_free_swap(page); @@ -698,7 +693,12 @@ int init_swap_address_space(unsigned int type, unsigned long nr_pages) void exit_swap_address_space(unsigned int type) { - kvfree(swapper_spaces[type]); + int i; + struct address_space *spaces = swapper_spaces[type]; + + for (i = 0; i < nr_swapper_spaces[type]; i++) + VM_WARN_ON_ONCE(!mapping_empty(&spaces[i])); + kvfree(spaces); nr_swapper_spaces[type] = 0; swapper_spaces[type] = NULL; } @@ -721,7 +721,6 @@ static void swap_ra_info(struct vm_fault *vmf, { struct vm_area_struct *vma = vmf->vma; unsigned long ra_val; - swp_entry_t entry; unsigned long faddr, pfn, fpfn; unsigned long start, end; pte_t *pte, *orig_pte; @@ -739,11 +738,6 @@ static void swap_ra_info(struct vm_fault *vmf, faddr = vmf->address; orig_pte = pte = pte_offset_map(vmf->pmd, faddr); - entry = pte_to_swp_entry(*pte); - if ((unlikely(non_swap_entry(entry)))) { - pte_unmap(orig_pte); - return; - } fpfn = PFN_DOWN(faddr); ra_val = GET_SWAP_RA_VAL(vma); diff --git a/mm/swapfile.c b/mm/swapfile.c index 996afa8131c8..e898c879a434 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -99,11 +100,10 @@ atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { - if (type >= READ_ONCE(nr_swapfiles)) + if (type >= MAX_SWAPFILES) return NULL; - smp_rmb(); /* Pairs with smp_wmb in alloc_swap_info. */ - return READ_ONCE(swap_info[type]); + return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } static inline unsigned char swap_count(unsigned char ent) @@ -452,10 +452,10 @@ static void swap_cluster_schedule_discard(struct swap_info_struct *si, unsigned int idx) { /* - * If scan_swap_map() can't find a free cluster, it will check + * If scan_swap_map_slots() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't - * taken by scan_swap_map(), mark the swap entries bad (occupied). It - * will be cleared after discard + * taken by scan_swap_map_slots(), mark the swap entries bad (occupied). + * It will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); @@ -511,6 +511,14 @@ static void swap_discard_work(struct work_struct *work) spin_unlock(&si->lock); } +static void swap_users_ref_free(struct percpu_ref *ref) +{ + struct swap_info_struct *si; + + si = container_of(ref, struct swap_info_struct, users); + complete(&si->comp); +} + static void alloc_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; @@ -580,7 +588,7 @@ static void dec_cluster_info_page(struct swap_info_struct *p, } /* - * It's possible scan_swap_map() uses a free cluster in the middle of free + * It's possible scan_swap_map_slots() uses a free cluster in the middle of free * cluster list. Avoiding such abuse to avoid list corruption. */ static bool @@ -1028,21 +1036,6 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) swap_range_free(si, offset, SWAPFILE_CLUSTER); } -static unsigned long scan_swap_map(struct swap_info_struct *si, - unsigned char usage) -{ - swp_entry_t entry; - int n_ret; - - n_ret = scan_swap_map_slots(si, usage, 1, &entry); - - if (n_ret) - return swp_offset(entry); - else - return 0; - -} - int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) { unsigned long size = swap_entry_size(entry_size); @@ -1105,14 +1098,14 @@ start_over: nextsi: /* * if we got here, it's likely that si was almost full before, - * and since scan_swap_map() can drop the si->lock, multiple - * callers probably all tried to get a page from the same si - * and it filled up before we could get one; or, the si filled - * up between us dropping swap_avail_lock and taking si->lock. - * Since we dropped the swap_avail_lock, the swap_avail_head - * list may have been modified; so if next is still in the - * swap_avail_head list then try it, otherwise start over - * if we have not gotten any slots. + * and since scan_swap_map_slots() can drop the si->lock, + * multiple callers probably all tried to get a page from the + * same si and it filled up before we could get one; or, the si + * filled up between us dropping swap_avail_lock and taking + * si->lock. Since we dropped the swap_avail_lock, the + * swap_avail_head list may have been modified; so if next is + * still in the swap_avail_head list then try it, otherwise + * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; @@ -1128,30 +1121,6 @@ noswap: return n_ret; } -/* The only caller of this function is now suspend routine */ -swp_entry_t get_swap_page_of_type(int type) -{ - struct swap_info_struct *si = swap_type_to_swap_info(type); - pgoff_t offset; - - if (!si) - goto fail; - - spin_lock(&si->lock); - if (si->flags & SWP_WRITEOK) { - /* This is called for allocating swap entry, not cache */ - offset = scan_swap_map(si, 1); - if (offset) { - atomic_long_dec(&nr_swap_pages); - spin_unlock(&si->lock); - return swp_entry(type, offset); - } - } - spin_unlock(&si->lock); -fail: - return (swp_entry_t) {0}; -} - static struct swap_info_struct *__swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; @@ -1270,18 +1239,12 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * - * The entirety of the RCU read critical section must come before the - * return from or after the call to synchronize_rcu() in - * enable_swap_info() or swapoff(). So if "si->flags & SWP_VALID" is - * true, the si->map, si->cluster_info, etc. must be valid in the - * critical section. - * * Notice that swapoff or swapoff+swapon can still happen before the - * rcu_read_lock() in get_swap_device() or after the rcu_read_unlock() - * in put_swap_device() if there isn't any other way to prevent - * swapoff, such as page lock, page table lock, etc. The caller must - * be prepared for that. For example, the following situation is - * possible. + * percpu_ref_tryget_live() in get_swap_device() or after the + * percpu_ref_put() in put_swap_device() if there isn't any other way + * to prevent swapoff, such as page lock, page table lock, etc. The + * caller must be prepared for that. For example, the following + * situation is possible. * * CPU1 CPU2 * do_swap_page() @@ -1309,21 +1272,27 @@ struct swap_info_struct *get_swap_device(swp_entry_t entry) si = swp_swap_info(entry); if (!si) goto bad_nofile; - - rcu_read_lock(); - if (data_race(!(si->flags & SWP_VALID))) - goto unlock_out; + if (!percpu_ref_tryget_live(&si->users)) + goto out; + /* + * Guarantee the si->users are checked before accessing other + * fields of swap_info_struct. + * + * Paired with the spin_unlock() after setup_swap_info() in + * enable_swap_info(). + */ + smp_rmb(); offset = swp_offset(entry); if (offset >= si->max) - goto unlock_out; + goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; -unlock_out: - rcu_read_unlock(); +put_out: + percpu_ref_put(&si->users); return NULL; } @@ -1803,6 +1772,24 @@ int free_swap_and_cache(swp_entry_t entry) } #ifdef CONFIG_HIBERNATION + +swp_entry_t get_swap_page_of_type(int type) +{ + struct swap_info_struct *si = swap_type_to_swap_info(type); + swp_entry_t entry = {0}; + + if (!si) + goto fail; + + /* This is called for allocating swap entry, not cache */ + spin_lock(&si->lock); + if ((si->flags & SWP_WRITEOK) && scan_swap_map_slots(si, 1, 1, &entry)) + atomic_long_dec(&nr_swap_pages); + spin_unlock(&si->lock); +fail: + return entry; +} + /* * Find the swap type that corresponds to given device (if any). * @@ -2466,7 +2453,7 @@ static void setup_swap_info(struct swap_info_struct *p, int prio, static void _enable_swap_info(struct swap_info_struct *p) { - p->flags |= SWP_WRITEOK | SWP_VALID; + p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; @@ -2497,10 +2484,9 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, spin_unlock(&p->lock); spin_unlock(&swap_lock); /* - * Guarantee swap_map, cluster_info, etc. fields are valid - * between get/put_swap_device() if SWP_VALID bit is set + * Finished initializing swap device, now it's safe to reference it. */ - synchronize_rcu(); + percpu_ref_resurrect(&p->users); spin_lock(&swap_lock); spin_lock(&p->lock); _enable_swap_info(p); @@ -2616,16 +2602,16 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) reenable_swap_slots_cache_unlock(); - spin_lock(&swap_lock); - spin_lock(&p->lock); - p->flags &= ~SWP_VALID; /* mark swap device as invalid */ - spin_unlock(&p->lock); - spin_unlock(&swap_lock); /* - * wait for swap operations protected by get/put_swap_device() - * to complete + * Wait for swap operations protected by get/put_swap_device() + * to complete. + * + * We need synchronize_rcu() here to protect the accessing to + * the swap cache data structure. */ + percpu_ref_kill(&p->users); synchronize_rcu(); + wait_for_completion(&p->comp); flush_work(&p->discard_work); @@ -2641,7 +2627,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_lock(&p->lock); drain_mmlist(); - /* wait for anyone still in scan_swap_map */ + /* wait for anyone still in scan_swap_map_slots */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); @@ -2857,6 +2843,12 @@ static struct swap_info_struct *alloc_swap_info(void) if (!p) return ERR_PTR(-ENOMEM); + if (percpu_ref_init(&p->users, swap_users_ref_free, + PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { + kvfree(p); + return ERR_PTR(-ENOMEM); + } + spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) @@ -2864,19 +2856,18 @@ static struct swap_info_struct *alloc_swap_info(void) } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); + percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; - WRITE_ONCE(swap_info[type], p); /* - * Write swap_info[type] before nr_swapfiles, in case a - * racing procfs swap_start() or swap_next() is reading them. - * (We never shrink nr_swapfiles, we never free this entry.) + * Publish the swap_info_struct after initializing it. + * Note that kvzalloc() above zeroes all its fields. */ - smp_wmb(); - WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1); + smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ + nr_swapfiles++; } else { defer = p; p = swap_info[type]; @@ -2891,9 +2882,13 @@ static struct swap_info_struct *alloc_swap_info(void) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); - kvfree(defer); + if (defer) { + percpu_ref_exit(&defer->users); + kvfree(defer); + } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); + init_completion(&p->comp); return p; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d0a7d89be091..b2ec7f751bd0 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2567,6 +2567,7 @@ static void __vunmap(const void *addr, int deallocate_pages) BUG_ON(!page); __free_pages(page, page_order); + cond_resched(); } atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); @@ -2758,6 +2759,54 @@ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) EXPORT_SYMBOL_GPL(vmap_pfn); #endif /* CONFIG_VMAP_PFN */ +static inline unsigned int +vm_area_alloc_pages(gfp_t gfp, int nid, + unsigned int order, unsigned long nr_pages, struct page **pages) +{ + unsigned int nr_allocated = 0; + + /* + * For order-0 pages we make use of bulk allocator, if + * the page array is partly or not at all populated due + * to fails, fallback to a single page allocator that is + * more permissive. + */ + if (!order) + nr_allocated = alloc_pages_bulk_array_node( + gfp, nid, nr_pages, pages); + else + /* + * Compound pages required for remap_vmalloc_page if + * high-order pages. + */ + gfp |= __GFP_COMP; + + /* High-order pages or fallback path if "bulk" fails. */ + while (nr_allocated < nr_pages) { + struct page *page; + int i; + + page = alloc_pages_node(nid, gfp, order); + if (unlikely(!page)) + break; + + /* + * Careful, we allocate and map page-order pages, but + * tracking is done per PAGE_SIZE page so as to keep the + * vm_struct APIs independent of the physical/mapped size. + */ + for (i = 0; i < (1U << order); i++) + pages[nr_allocated + i] = page + i; + + if (gfpflags_allow_blocking(gfp)) + cond_resched(); + + nr_allocated += 1U << order; + } + + return nr_allocated; +} + static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot, unsigned int page_shift, int node) @@ -2768,8 +2817,6 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, unsigned long array_size; unsigned int nr_small_pages = size >> PAGE_SHIFT; unsigned int page_order; - struct page **pages; - unsigned int i; array_size = (unsigned long)nr_small_pages * sizeof(struct page *); gfp_mask |= __GFP_NOWARN; @@ -2778,62 +2825,44 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { - pages = __vmalloc_node(array_size, 1, nested_gfp, node, + area->pages = __vmalloc_node(array_size, 1, nested_gfp, node, area->caller); } else { - pages = kmalloc_node(array_size, nested_gfp, node); + area->pages = kmalloc_node(array_size, nested_gfp, node); } - if (!pages) { - free_vm_area(area); + if (!area->pages) { warn_alloc(gfp_mask, NULL, - "vmalloc size %lu allocation failure: " - "page array size %lu allocation failed", - nr_small_pages * PAGE_SIZE, array_size); + "vmalloc error: size %lu, failed to allocated page array size %lu", + nr_small_pages * PAGE_SIZE, array_size); + free_vm_area(area); return NULL; } - area->pages = pages; - area->nr_pages = nr_small_pages; set_vm_area_page_order(area, page_shift - PAGE_SHIFT); - page_order = vm_area_page_order(area); - /* - * Careful, we allocate and map page_order pages, but tracking is done - * per PAGE_SIZE page so as to keep the vm_struct APIs independent of - * the physical/mapped size. - */ - for (i = 0; i < area->nr_pages; i += 1U << page_order) { - struct page *page; - int p; + area->nr_pages = vm_area_alloc_pages(gfp_mask, node, + page_order, nr_small_pages, area->pages); - /* Compound pages required for remap_vmalloc_page */ - page = alloc_pages_node(node, gfp_mask | __GFP_COMP, page_order); - if (unlikely(!page)) { - /* Successfully allocated i pages, free them in __vfree() */ - area->nr_pages = i; - atomic_long_add(area->nr_pages, &nr_vmalloc_pages); - warn_alloc(gfp_mask, NULL, - "vmalloc size %lu allocation failure: " - "page order %u allocation failed", - area->nr_pages * PAGE_SIZE, page_order); - goto fail; - } - - for (p = 0; p < (1U << page_order); p++) - area->pages[i + p] = page + p; - - if (gfpflags_allow_blocking(gfp_mask)) - cond_resched(); - } atomic_long_add(area->nr_pages, &nr_vmalloc_pages); - if (vmap_pages_range(addr, addr + size, prot, pages, page_shift) < 0) { + /* + * If not enough pages were obtained to accomplish an + * allocation request, free them via __vfree() if any. + */ + if (area->nr_pages != nr_small_pages) { warn_alloc(gfp_mask, NULL, - "vmalloc size %lu allocation failure: " - "failed to map pages", - area->nr_pages * PAGE_SIZE); + "vmalloc error: size %lu, page order %u, failed to allocate pages", + area->nr_pages * PAGE_SIZE, page_order); + goto fail; + } + + if (vmap_pages_range(addr, addr + size, prot, area->pages, + page_shift) < 0) { + warn_alloc(gfp_mask, NULL, + "vmalloc error: size %lu, failed to map pages", + area->nr_pages * PAGE_SIZE); goto fail; } @@ -2878,8 +2907,8 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, if ((size >> PAGE_SHIFT) > totalram_pages()) { warn_alloc(gfp_mask, NULL, - "vmalloc size %lu allocation failure: " - "exceeds total pages", real_size); + "vmalloc error: size %lu, exceeds total pages", + real_size); return NULL; } @@ -2910,8 +2939,8 @@ again: gfp_mask, caller); if (!area) { warn_alloc(gfp_mask, NULL, - "vmalloc size %lu allocation failure: " - "vm_struct allocation failed", real_size); + "vmalloc error: size %lu, vm_struct allocation failed", + real_size); goto fail; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 5199b9696bab..d7c3cb8688dd 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2015,8 +2015,8 @@ static int too_many_isolated(struct pglist_data *pgdat, int file, * * Returns the number of pages moved to the given lruvec. */ -static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, - struct list_head *list) +static unsigned int move_pages_to_lru(struct lruvec *lruvec, + struct list_head *list) { int nr_pages, nr_moved = 0; LIST_HEAD(pages_to_free); @@ -2063,7 +2063,7 @@ static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec, * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ - VM_BUG_ON_PAGE(!lruvec_holds_page_lru_lock(page, lruvec), page); + VM_BUG_ON_PAGE(!page_matches_lruvec(page, lruvec), page); add_page_to_lru_list(page, lruvec); nr_pages = thp_nr_pages(page); nr_moved += nr_pages; @@ -2096,7 +2096,7 @@ static int current_may_throttle(void) * shrink_inactive_list() is a helper for shrink_node(). It returns the number * of reclaimed pages */ -static noinline_for_stack unsigned long +static unsigned long shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, struct scan_control *sc, enum lru_list lru) { @@ -3722,6 +3722,38 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, return sc->nr_scanned >= sc->nr_to_reclaim; } +/* Page allocator PCP high watermark is lowered if reclaim is active. */ +static inline void +update_reclaim_active(pg_data_t *pgdat, int highest_zoneidx, bool active) +{ + int i; + struct zone *zone; + + for (i = 0; i <= highest_zoneidx; i++) { + zone = pgdat->node_zones + i; + + if (!managed_zone(zone)) + continue; + + if (active) + set_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); + else + clear_bit(ZONE_RECLAIM_ACTIVE, &zone->flags); + } +} + +static inline void +set_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) +{ + update_reclaim_active(pgdat, highest_zoneidx, true); +} + +static inline void +clear_reclaim_active(pg_data_t *pgdat, int highest_zoneidx) +{ + update_reclaim_active(pgdat, highest_zoneidx, false); +} + /* * For kswapd, balance_pgdat() will reclaim pages across a node from zones * that are eligible for use by the caller until at least one zone is @@ -3774,6 +3806,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx) boosted = nr_boost_reclaim; restart: + set_reclaim_active(pgdat, highest_zoneidx); sc.priority = DEF_PRIORITY; do { unsigned long nr_reclaimed = sc.nr_reclaimed; @@ -3907,6 +3940,8 @@ restart: pgdat->kswapd_failures++; out: + clear_reclaim_active(pgdat, highest_zoneidx); + /* If reclaim was boosted, account for the reclaim done in this pass */ if (boosted) { unsigned long flags; diff --git a/mm/vmstat.c b/mm/vmstat.c index 8285ac2c62c7..2d0050da3b55 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -31,8 +31,6 @@ #include "internal.h" -#define NUMA_STATS_THRESHOLD (U16_MAX - 2) - #ifdef CONFIG_NUMA int sysctl_vm_numa_stat = ENABLE_NUMA_STAT; @@ -41,11 +39,12 @@ static void zero_zone_numa_counters(struct zone *zone) { int item, cpu; - for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) { - atomic_long_set(&zone->vm_numa_stat[item], 0); - for_each_online_cpu(cpu) - per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item] + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) { + atomic_long_set(&zone->vm_numa_event[item], 0); + for_each_online_cpu(cpu) { + per_cpu_ptr(zone->per_cpu_zonestats, cpu)->vm_numa_event[item] = 0; + } } } @@ -63,8 +62,8 @@ static void zero_global_numa_counters(void) { int item; - for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) - atomic_long_set(&vm_numa_stat[item], 0); + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + atomic_long_set(&vm_numa_event[item], 0); } static void invalid_numa_statistics(void) @@ -161,10 +160,9 @@ void vm_events_fold_cpu(int cpu) * vm_stat contains the global counters */ atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp; -atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS] __cacheline_aligned_in_smp; atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS] __cacheline_aligned_in_smp; +atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS] __cacheline_aligned_in_smp; EXPORT_SYMBOL(vm_zone_stat); -EXPORT_SYMBOL(vm_numa_stat); EXPORT_SYMBOL(vm_node_stat); #ifdef CONFIG_SMP @@ -266,7 +264,7 @@ void refresh_zone_stat_thresholds(void) for_each_online_cpu(cpu) { int pgdat_threshold; - per_cpu_ptr(zone->pageset, cpu)->stat_threshold + per_cpu_ptr(zone->per_cpu_zonestats, cpu)->stat_threshold = threshold; /* Base nodestat threshold on the largest populated zone. */ @@ -303,7 +301,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, threshold = (*calculate_pressure)(zone); for_each_online_cpu(cpu) - per_cpu_ptr(zone->pageset, cpu)->stat_threshold + per_cpu_ptr(zone->per_cpu_zonestats, cpu)->stat_threshold = threshold; } } @@ -316,7 +314,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { - struct per_cpu_pageset __percpu *pcp = zone->pageset; + struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; s8 __percpu *p = pcp->vm_stat_diff + item; long x; long t; @@ -389,7 +387,7 @@ EXPORT_SYMBOL(__mod_node_page_state); */ void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { - struct per_cpu_pageset __percpu *pcp = zone->pageset; + struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; @@ -435,7 +433,7 @@ EXPORT_SYMBOL(__inc_node_page_state); void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { - struct per_cpu_pageset __percpu *pcp = zone->pageset; + struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; s8 __percpu *p = pcp->vm_stat_diff + item; s8 v, t; @@ -495,7 +493,7 @@ EXPORT_SYMBOL(__dec_node_page_state); static inline void mod_zone_state(struct zone *zone, enum zone_stat_item item, long delta, int overstep_mode) { - struct per_cpu_pageset __percpu *pcp = zone->pageset; + struct per_cpu_zonestat __percpu *pcp = zone->per_cpu_zonestats; s8 __percpu *p = pcp->vm_stat_diff + item; long o, n, t, z; @@ -706,32 +704,6 @@ EXPORT_SYMBOL(dec_node_page_state); * Fold a differential into the global counters. * Returns the number of counters updated. */ -#ifdef CONFIG_NUMA -static int fold_diff(int *zone_diff, int *numa_diff, int *node_diff) -{ - int i; - int changes = 0; - - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (zone_diff[i]) { - atomic_long_add(zone_diff[i], &vm_zone_stat[i]); - changes++; - } - - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - if (numa_diff[i]) { - atomic_long_add(numa_diff[i], &vm_numa_stat[i]); - changes++; - } - - for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) - if (node_diff[i]) { - atomic_long_add(node_diff[i], &vm_node_stat[i]); - changes++; - } - return changes; -} -#else static int fold_diff(int *zone_diff, int *node_diff) { int i; @@ -750,7 +722,34 @@ static int fold_diff(int *zone_diff, int *node_diff) } return changes; } -#endif /* CONFIG_NUMA */ + +#ifdef CONFIG_NUMA +static void fold_vm_zone_numa_events(struct zone *zone) +{ + unsigned long zone_numa_events[NR_VM_NUMA_EVENT_ITEMS] = { 0, }; + int cpu; + enum numa_stat_item item; + + for_each_online_cpu(cpu) { + struct per_cpu_zonestat *pzstats; + + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + zone_numa_events[item] += xchg(&pzstats->vm_numa_event[item], 0); + } + + for (item = 0; item < NR_VM_NUMA_EVENT_ITEMS; item++) + zone_numa_event_add(zone_numa_events[item], zone, item); +} + +void fold_vm_numa_events(void) +{ + struct zone *zone; + + for_each_populated_zone(zone) + fold_vm_zone_numa_events(zone); +} +#endif /* * Update the zone counters for the current cpu. @@ -774,41 +773,30 @@ static int refresh_cpu_vm_stats(bool do_pagesets) struct zone *zone; int i; int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; -#ifdef CONFIG_NUMA - int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, }; -#endif int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; int changes = 0; for_each_populated_zone(zone) { - struct per_cpu_pageset __percpu *p = zone->pageset; + struct per_cpu_zonestat __percpu *pzstats = zone->per_cpu_zonestats; +#ifdef CONFIG_NUMA + struct per_cpu_pages __percpu *pcp = zone->per_cpu_pageset; +#endif for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { int v; - v = this_cpu_xchg(p->vm_stat_diff[i], 0); + v = this_cpu_xchg(pzstats->vm_stat_diff[i], 0); if (v) { atomic_long_add(v, &zone->vm_stat[i]); global_zone_diff[i] += v; #ifdef CONFIG_NUMA /* 3 seconds idle till flush */ - __this_cpu_write(p->expire, 3); + __this_cpu_write(pcp->expire, 3); #endif } } #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) { - int v; - - v = this_cpu_xchg(p->vm_numa_stat_diff[i], 0); - if (v) { - - atomic_long_add(v, &zone->vm_numa_stat[i]); - global_numa_diff[i] += v; - __this_cpu_write(p->expire, 3); - } - } if (do_pagesets) { cond_resched(); @@ -819,23 +807,23 @@ static int refresh_cpu_vm_stats(bool do_pagesets) * Check if there are pages remaining in this pageset * if not then there is nothing to expire. */ - if (!__this_cpu_read(p->expire) || - !__this_cpu_read(p->pcp.count)) + if (!__this_cpu_read(pcp->expire) || + !__this_cpu_read(pcp->count)) continue; /* * We never drain zones local to this processor. */ if (zone_to_nid(zone) == numa_node_id()) { - __this_cpu_write(p->expire, 0); + __this_cpu_write(pcp->expire, 0); continue; } - if (__this_cpu_dec_return(p->expire)) + if (__this_cpu_dec_return(pcp->expire)) continue; - if (__this_cpu_read(p->pcp.count)) { - drain_zone_pages(zone, this_cpu_ptr(&p->pcp)); + if (__this_cpu_read(pcp->count)) { + drain_zone_pages(zone, this_cpu_ptr(pcp)); changes++; } } @@ -856,12 +844,7 @@ static int refresh_cpu_vm_stats(bool do_pagesets) } } -#ifdef CONFIG_NUMA - changes += fold_diff(global_zone_diff, global_numa_diff, - global_node_diff); -#else changes += fold_diff(global_zone_diff, global_node_diff); -#endif return changes; } @@ -876,36 +859,33 @@ void cpu_vm_stats_fold(int cpu) struct zone *zone; int i; int global_zone_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; -#ifdef CONFIG_NUMA - int global_numa_diff[NR_VM_NUMA_STAT_ITEMS] = { 0, }; -#endif int global_node_diff[NR_VM_NODE_STAT_ITEMS] = { 0, }; for_each_populated_zone(zone) { - struct per_cpu_pageset *p; + struct per_cpu_zonestat *pzstats; - p = per_cpu_ptr(zone->pageset, cpu); + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (p->vm_stat_diff[i]) { + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { + if (pzstats->vm_stat_diff[i]) { int v; - v = p->vm_stat_diff[i]; - p->vm_stat_diff[i] = 0; + v = pzstats->vm_stat_diff[i]; + pzstats->vm_stat_diff[i] = 0; atomic_long_add(v, &zone->vm_stat[i]); global_zone_diff[i] += v; } - + } #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - if (p->vm_numa_stat_diff[i]) { - int v; + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) { + if (pzstats->vm_numa_event[i]) { + unsigned long v; - v = p->vm_numa_stat_diff[i]; - p->vm_numa_stat_diff[i] = 0; - atomic_long_add(v, &zone->vm_numa_stat[i]); - global_numa_diff[i] += v; + v = pzstats->vm_numa_event[i]; + pzstats->vm_numa_event[i] = 0; + zone_numa_event_add(v, zone, i); } + } #endif } @@ -925,58 +905,39 @@ void cpu_vm_stats_fold(int cpu) } } -#ifdef CONFIG_NUMA - fold_diff(global_zone_diff, global_numa_diff, global_node_diff); -#else fold_diff(global_zone_diff, global_node_diff); -#endif } /* * this is only called if !populated_zone(zone), which implies no other users of * pset->vm_stat_diff[] exist. */ -void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) +void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *pzstats) { + unsigned long v; int i; - for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - if (pset->vm_stat_diff[i]) { - int v = pset->vm_stat_diff[i]; - pset->vm_stat_diff[i] = 0; - atomic_long_add(v, &zone->vm_stat[i]); - atomic_long_add(v, &vm_zone_stat[i]); + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) { + if (pzstats->vm_stat_diff[i]) { + v = pzstats->vm_stat_diff[i]; + pzstats->vm_stat_diff[i] = 0; + zone_page_state_add(v, zone, i); } - -#ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - if (pset->vm_numa_stat_diff[i]) { - int v = pset->vm_numa_stat_diff[i]; - - pset->vm_numa_stat_diff[i] = 0; - atomic_long_add(v, &zone->vm_numa_stat[i]); - atomic_long_add(v, &vm_numa_stat[i]); - } -#endif -} -#endif - -#ifdef CONFIG_NUMA -void __inc_numa_state(struct zone *zone, - enum numa_stat_item item) -{ - struct per_cpu_pageset __percpu *pcp = zone->pageset; - u16 __percpu *p = pcp->vm_numa_stat_diff + item; - u16 v; - - v = __this_cpu_inc_return(*p); - - if (unlikely(v > NUMA_STATS_THRESHOLD)) { - zone_numa_state_add(v, zone, item); - __this_cpu_write(*p, 0); } -} +#ifdef CONFIG_NUMA + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) { + if (pzstats->vm_numa_event[i]) { + v = pzstats->vm_numa_event[i]; + pzstats->vm_numa_event[i] = 0; + zone_numa_event_add(v, zone, i); + } + } +#endif +} +#endif + +#ifdef CONFIG_NUMA /* * Determine the per node value of a stat item. This function * is called frequently in a NUMA machine, so try to be as @@ -995,19 +956,16 @@ unsigned long sum_zone_node_page_state(int node, return count; } -/* - * Determine the per node value of a numa stat item. To avoid deviation, - * the per cpu stat number in vm_numa_stat_diff[] is also included. - */ -unsigned long sum_zone_numa_state(int node, +/* Determine the per node value of a numa stat item. */ +unsigned long sum_zone_numa_event_state(int node, enum numa_stat_item item) { struct zone *zones = NODE_DATA(node)->node_zones; - int i; unsigned long count = 0; + int i; for (i = 0; i < MAX_NR_ZONES; i++) - count += zone_numa_state_snapshot(zones + i, item); + count += zone_numa_event_state(zones + i, item); return count; } @@ -1684,28 +1642,30 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, zone_page_state(zone, i)); #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) seq_printf(m, "\n %-12s %lu", numa_stat_name(i), - zone_numa_state_snapshot(zone, i)); + zone_numa_event_state(zone, i)); #endif seq_printf(m, "\n pagesets"); for_each_online_cpu(i) { - struct per_cpu_pageset *pageset; + struct per_cpu_pages *pcp; + struct per_cpu_zonestat __maybe_unused *pzstats; - pageset = per_cpu_ptr(zone->pageset, i); + pcp = per_cpu_ptr(zone->per_cpu_pageset, i); seq_printf(m, "\n cpu: %i" "\n count: %i" "\n high: %i" "\n batch: %i", i, - pageset->pcp.count, - pageset->pcp.high, - pageset->pcp.batch); + pcp->count, + pcp->high, + pcp->batch); #ifdef CONFIG_SMP + pzstats = per_cpu_ptr(zone->per_cpu_zonestats, i); seq_printf(m, "\n vm stats threshold: %d", - pageset->stat_threshold); + pzstats->stat_threshold); #endif } seq_printf(m, @@ -1738,7 +1698,7 @@ static const struct seq_operations zoneinfo_op = { }; #define NR_VMSTAT_ITEMS (NR_VM_ZONE_STAT_ITEMS + \ - NR_VM_NUMA_STAT_ITEMS + \ + NR_VM_NUMA_EVENT_ITEMS + \ NR_VM_NODE_STAT_ITEMS + \ NR_VM_WRITEBACK_STAT_ITEMS + \ (IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \ @@ -1753,6 +1713,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) return NULL; BUILD_BUG_ON(ARRAY_SIZE(vmstat_text) < NR_VMSTAT_ITEMS); + fold_vm_numa_events(); v = kmalloc_array(NR_VMSTAT_ITEMS, sizeof(unsigned long), GFP_KERNEL); m->private = v; if (!v) @@ -1762,9 +1723,9 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) v += NR_VM_ZONE_STAT_ITEMS; #ifdef CONFIG_NUMA - for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - v[i] = global_numa_state(i); - v += NR_VM_NUMA_STAT_ITEMS; + for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++) + v[i] = global_numa_event_state(i); + v += NR_VM_NUMA_EVENT_ITEMS; #endif for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { @@ -1925,19 +1886,16 @@ static bool need_update(int cpu) struct zone *zone; for_each_populated_zone(zone) { - struct per_cpu_pageset *p = per_cpu_ptr(zone->pageset, cpu); + struct per_cpu_zonestat *pzstats = per_cpu_ptr(zone->per_cpu_zonestats, cpu); struct per_cpu_nodestat *n; + /* * The fast way of checking if there are any vmstat diffs. */ - if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS * - sizeof(p->vm_stat_diff[0]))) + if (memchr_inv(pzstats->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS * + sizeof(pzstats->vm_stat_diff[0]))) return true; -#ifdef CONFIG_NUMA - if (memchr_inv(p->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS * - sizeof(p->vm_numa_stat_diff[0]))) - return true; -#endif + if (last_pgdat == zone->zone_pgdat) continue; last_pgdat = zone->zone_pgdat; diff --git a/mm/workingset.c b/mm/workingset.c index b7cdeca5a76d..4f7a306ce75a 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -408,7 +408,7 @@ void workingset_activation(struct page *page) memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); + lruvec = mem_cgroup_page_lruvec(page); workingset_age_nonresident(lruvec, thp_nr_pages(page)); out: rcu_read_unlock(); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index fb3d3262dc1a..4cdf8416869d 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -638,7 +638,8 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg) case GET_VLAN_REALDEV_NAME_CMD: err = 0; - vlan_dev_get_realdev_name(dev, args.u.device2); + vlan_dev_get_realdev_name(dev, args.u.device2, + sizeof(args.u.device2)); if (copy_to_user(arg, &args, sizeof(struct vlan_ioctl_args))) err = -EFAULT; diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index fa3ad3d4d58c..1a705a4ef7fa 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -108,7 +108,8 @@ static inline netdev_features_t vlan_tnl_features(struct net_device *real_dev) netdev_features_t ret; ret = real_dev->hw_enc_features & - (NETIF_F_CSUM_MASK | NETIF_F_ALL_TSO | NETIF_F_GSO_ENCAP_ALL); + (NETIF_F_CSUM_MASK | NETIF_F_GSO_SOFTWARE | + NETIF_F_GSO_ENCAP_ALL); if ((ret & NETIF_F_GSO_ENCAP_ALL) && (ret & NETIF_F_CSUM_MASK)) return (ret & ~NETIF_F_CSUM_MASK) | NETIF_F_HW_CSUM; @@ -129,7 +130,8 @@ void vlan_dev_set_ingress_priority(const struct net_device *dev, int vlan_dev_set_egress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); int vlan_dev_change_flags(const struct net_device *dev, u32 flag, u32 mask); -void vlan_dev_get_realdev_name(const struct net_device *dev, char *result); +void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, + size_t size); int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id, diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 4db3f0621959..a0367b37512d 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -239,9 +239,9 @@ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask) return 0; } -void vlan_dev_get_realdev_name(const struct net_device *dev, char *result) +void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, size_t size) { - strncpy(result, vlan_dev_priv(dev)->real_dev->name, 23); + strscpy_pad(result, vlan_dev_priv(dev)->real_dev->name, size); } bool vlan_dev_inherit_address(struct net_device *dev, @@ -360,7 +360,7 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) struct ifreq ifrr; int err = -EOPNOTSUPP; - strncpy(ifrr.ifr_name, real_dev->name, IFNAMSIZ); + strscpy_pad(ifrr.ifr_name, real_dev->name, IFNAMSIZ); ifrr.ifr_ifru = ifr->ifr_ifru; switch (cmd) { diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 93f2f8654882..2bbd7dce0f1d 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -99,7 +99,7 @@ static unsigned int rest_of_page(void *data) * @client: client instance * * This reclaims a channel by freeing its resources and - * reseting its inuse flag. + * resetting its inuse flag. * */ @@ -463,7 +463,7 @@ req_retry_pinned: * For example TREAD have 11. * 11 is the read/write header = PDU Header(7) + IO Size (4). * Arrange in such a way that server places header in the - * alloced memory and payload onto the user buffer. + * allocated memory and payload onto the user buffer. */ in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM, req->rc.sdata, in_hdr_len); @@ -760,7 +760,7 @@ static struct p9_trans_module p9_virtio_trans = { .cancelled = p9_virtio_cancelled, /* * We leave one entry for input and one entry for response - * headers. We also skip one more entry to accomodate, address + * headers. We also skip one more entry to accommodate, address * that are not at page boundary, that can result in an extra * page in zero copy. */ diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index ebda397fa95a..8ade5a4ceaf5 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -707,7 +707,7 @@ static int atif_ioctl(int cmd, void __user *arg) /* * Phase 1 is fine on LocalTalk but we don't do - * EtherTalk phase 1. Anyone wanting to add it go ahead. + * EtherTalk phase 1. Anyone wanting to add it, go ahead. */ if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2) return -EPROTONOSUPPORT; @@ -828,7 +828,7 @@ static int atif_ioctl(int cmd, void __user *arg) nr = (struct atalk_netrange *)&(atif->nets); /* * Phase 1 is fine on Localtalk but we don't do - * Ethertalk phase 1. Anyone wanting to add it go ahead. + * Ethertalk phase 1. Anyone wanting to add it, go ahead. */ if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2) return -EPROTONOSUPPORT; @@ -2018,7 +2018,7 @@ module_init(atalk_init); * by the network device layer. * * Ergo, before the AppleTalk module can be removed, all AppleTalk - * sockets be closed from user space. + * sockets should be closed from user space. */ static void __exit atalk_exit(void) { diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c index aa1b57161f3b..0fdbdfd19474 100644 --- a/net/atm/atm_sysfs.c +++ b/net/atm/atm_sysfs.c @@ -11,7 +11,7 @@ #define to_atm_dev(cldev) container_of(cldev, struct atm_dev, class_dev) -static ssize_t show_type(struct device *cdev, +static ssize_t type_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct atm_dev *adev = to_atm_dev(cdev); @@ -19,7 +19,7 @@ static ssize_t show_type(struct device *cdev, return scnprintf(buf, PAGE_SIZE, "%s\n", adev->type); } -static ssize_t show_address(struct device *cdev, +static ssize_t address_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct atm_dev *adev = to_atm_dev(cdev); @@ -27,7 +27,7 @@ static ssize_t show_address(struct device *cdev, return scnprintf(buf, PAGE_SIZE, "%pM\n", adev->esi); } -static ssize_t show_atmaddress(struct device *cdev, +static ssize_t atmaddress_show(struct device *cdev, struct device_attribute *attr, char *buf) { unsigned long flags; @@ -50,7 +50,7 @@ static ssize_t show_atmaddress(struct device *cdev, return count; } -static ssize_t show_atmindex(struct device *cdev, +static ssize_t atmindex_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct atm_dev *adev = to_atm_dev(cdev); @@ -58,7 +58,7 @@ static ssize_t show_atmindex(struct device *cdev, return scnprintf(buf, PAGE_SIZE, "%d\n", adev->number); } -static ssize_t show_carrier(struct device *cdev, +static ssize_t carrier_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct atm_dev *adev = to_atm_dev(cdev); @@ -67,7 +67,7 @@ static ssize_t show_carrier(struct device *cdev, adev->signal == ATM_PHY_SIG_LOST ? 0 : 1); } -static ssize_t show_link_rate(struct device *cdev, +static ssize_t link_rate_show(struct device *cdev, struct device_attribute *attr, char *buf) { struct atm_dev *adev = to_atm_dev(cdev); @@ -90,12 +90,12 @@ static ssize_t show_link_rate(struct device *cdev, return scnprintf(buf, PAGE_SIZE, "%d\n", link_rate); } -static DEVICE_ATTR(address, 0444, show_address, NULL); -static DEVICE_ATTR(atmaddress, 0444, show_atmaddress, NULL); -static DEVICE_ATTR(atmindex, 0444, show_atmindex, NULL); -static DEVICE_ATTR(carrier, 0444, show_carrier, NULL); -static DEVICE_ATTR(type, 0444, show_type, NULL); -static DEVICE_ATTR(link_rate, 0444, show_link_rate, NULL); +static DEVICE_ATTR_RO(address); +static DEVICE_ATTR_RO(atmaddress); +static DEVICE_ATTR_RO(atmindex); +static DEVICE_ATTR_RO(carrier); +static DEVICE_ATTR_RO(type); +static DEVICE_ATTR_RO(link_rate); static struct device_attribute *atm_attrs[] = { &dev_attr_atmaddress, diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 3e17a5ecaa94..dd2a8dabed84 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -93,8 +93,8 @@ struct br2684_dev { * This lock should be held for writing any time the list of devices or * their attached vcc's could be altered. It should be held for reading * any time these are being queried. Note that we sometimes need to - * do read-locking under interrupt context, so write locking must block - * the current CPU's interrupts + * do read-locking under interrupting context, so write locking must block + * the current CPU's interrupts. */ static DEFINE_RWLOCK(devs_lock); diff --git a/net/atm/resources.c b/net/atm/resources.c index 53236986dfe0..2b2d33eeaf20 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -52,10 +52,8 @@ static struct atm_dev *__alloc_atm_dev(const char *type) static struct atm_dev *__atm_dev_lookup(int number) { struct atm_dev *dev; - struct list_head *p; - list_for_each(p, &atm_devs) { - dev = list_entry(p, struct atm_dev, dev_list); + list_for_each_entry(dev, &atm_devs, dev_list) { if (dev->number == number) { atm_dev_hold(dev); return dev; @@ -215,8 +213,7 @@ int atm_getnames(void __user *buf, int __user *iobuf_len) return -ENOMEM; } tmp_p = tmp_buf; - list_for_each(p, &atm_devs) { - dev = list_entry(p, struct atm_dev, dev_list); + list_for_each_entry(dev, &atm_devs, dev_list) { *tmp_p++ = dev->number; } mutex_unlock(&atm_dev_mutex); diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index fc8be49010b9..12022378f892 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1851,6 +1851,8 @@ batadv_iv_ogm_orig_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, orig_node->orig) || nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, neigh_node->addr) || + nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, + neigh_node->if_incoming->net_dev->name) || nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, neigh_node->if_incoming->net_dev->ifindex) || nla_put_u8(msg, BATADV_ATTR_TQ, tq_avg) || @@ -2080,6 +2082,8 @@ batadv_iv_ogm_neigh_dump_neigh(struct sk_buff *msg, u32 portid, u32 seq, if (nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, hardif_neigh->addr) || + nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, + hardif_neigh->if_incoming->net_dev->name) || nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, hardif_neigh->if_incoming->net_dev->ifindex) || nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, @@ -2461,6 +2465,8 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, router->addr) || nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, router->if_incoming->net_dev->name) || + nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + router->if_incoming->net_dev->ifindex) || nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_DOWN, gw_node->bandwidth_down) || nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_UP, diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index e1ca2b8c3152..b98aea958e3d 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -146,6 +146,8 @@ batadv_v_neigh_dump_neigh(struct sk_buff *msg, u32 portid, u32 seq, if (nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, hardif_neigh->addr) || + nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, + hardif_neigh->if_incoming->net_dev->name) || nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, hardif_neigh->if_incoming->net_dev->ifindex) || nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, @@ -298,6 +300,8 @@ batadv_v_orig_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq, if (nla_put(msg, BATADV_ATTR_ORIG_ADDRESS, ETH_ALEN, orig_node->orig) || nla_put(msg, BATADV_ATTR_NEIGH_ADDRESS, ETH_ALEN, neigh_node->addr) || + nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, + neigh_node->if_incoming->net_dev->name) || nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, neigh_node->if_incoming->net_dev->ifindex) || nla_put_u32(msg, BATADV_ATTR_THROUGHPUT, throughput) || @@ -739,6 +743,12 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, goto out; } + if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, + router->if_incoming->net_dev->ifindex)) { + genlmsg_cancel(msg, hdr); + goto out; + } + if (nla_put_u32(msg, BATADV_ATTR_BANDWIDTH_DOWN, gw_node->bandwidth_down)) { genlmsg_cancel(msg, hdr); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 7dc133cfc363..63d42dcc9324 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -395,7 +395,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, break; case BATADV_CLAIM_TYPE_ANNOUNCE: /* announcement frame - * set HW SRC to the special mac containg the crc + * set HW SRC to the special mac containing the crc */ ether_addr_copy(hw_src, mac); batadv_dbg(BATADV_DBG_BLA, bat_priv, @@ -1040,7 +1040,7 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv, /* lets see if this originator is in our mesh */ orig_node = batadv_orig_hash_find(bat_priv, backbone_addr); - /* dont accept claims from gateways which are not in + /* don't accept claims from gateways which are not in * the same mesh or group. */ if (!orig_node) diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 5c22955bb9d5..8673a265995f 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -52,7 +52,6 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, void batadv_bla_status_update(struct net_device *net_dev); int batadv_bla_init(struct batadv_priv *bat_priv); void batadv_bla_free(struct batadv_priv *bat_priv); -int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb); #ifdef CONFIG_BATMAN_ADV_DAT bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr, unsigned short vid); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 4a6a25d551a8..55d97e18aa4a 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -9,7 +9,6 @@ #include #include -#include #include #include #include @@ -403,7 +402,7 @@ int batadv_hardif_no_broadcast(struct batadv_hard_iface *if_outgoing, goto out; } - /* >1 neighbors -> (re)brodcast */ + /* >1 neighbors -> (re)broadcast */ if (rcu_dereference(hlist_next_rcu(first))) goto out; @@ -677,44 +676,17 @@ batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface) batadv_update_min_mtu(hard_iface->soft_iface); } -/** - * batadv_master_del_slave() - remove hard_iface from the current master iface - * @slave: the interface enslaved in another master - * @master: the master from which slave has to be removed - * - * Invoke ndo_del_slave on master passing slave as argument. In this way the - * slave is free'd and the master can correctly change its internal state. - * - * Return: 0 on success, a negative value representing the error otherwise - */ -static int batadv_master_del_slave(struct batadv_hard_iface *slave, - struct net_device *master) -{ - int ret; - - if (!master) - return 0; - - ret = -EBUSY; - if (master->netdev_ops->ndo_del_slave) - ret = master->netdev_ops->ndo_del_slave(master, slave->net_dev); - - return ret; -} - /** * batadv_hardif_enable_interface() - Enslave hard interface to soft interface * @hard_iface: hard interface to add to soft interface - * @net: the applicable net namespace - * @iface_name: name of the soft interface + * @soft_iface: netdev struct of the mesh interface * * Return: 0 on success or negative error number in case of failure */ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, - struct net *net, const char *iface_name) + struct net_device *soft_iface) { struct batadv_priv *bat_priv; - struct net_device *soft_iface, *master; __be16 ethertype = htons(ETH_P_BATMAN); int max_header_len = batadv_max_header_len(); int ret; @@ -724,35 +696,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, kref_get(&hard_iface->refcount); - soft_iface = dev_get_by_name(net, iface_name); - - if (!soft_iface) { - soft_iface = batadv_softif_create(net, iface_name); - - if (!soft_iface) { - ret = -ENOMEM; - goto err; - } - - /* dev_get_by_name() increases the reference counter for us */ - dev_hold(soft_iface); - } - - if (!batadv_softif_is_valid(soft_iface)) { - pr_err("Can't create batman mesh interface %s: already exists as regular interface\n", - soft_iface->name); - ret = -EINVAL; - goto err_dev; - } - - /* check if the interface is enslaved in another virtual one and - * in that case unlink it first - */ - master = netdev_master_upper_dev_get(hard_iface->net_dev); - ret = batadv_master_del_slave(hard_iface, master); - if (ret) - goto err_dev; - + dev_hold(soft_iface); hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface); @@ -810,7 +754,6 @@ err_upper: err_dev: hard_iface->soft_iface = NULL; dev_put(soft_iface); -err: batadv_hardif_put(hard_iface); return ret; } diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 83d11b46a9d8..8cb2a1f10080 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -16,7 +16,6 @@ #include #include #include -#include /** * enum batadv_hard_if_state - State of a hard interface @@ -75,7 +74,7 @@ bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface); struct batadv_hard_iface* batadv_hardif_get_by_netdev(const struct net_device *net_dev); int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, - struct net *net, const char *iface_name); + struct net_device *soft_iface); void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface); int batadv_hardif_min_mtu(struct net_device *soft_iface); void batadv_update_min_mtu(struct net_device *soft_iface); diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 46696759f194..fb251c385a1b 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -18,7 +18,7 @@ #include #include -/* callback to a compare function. should compare 2 element datas for their +/* callback to a compare function. should compare 2 element data for their * keys * * Return: true if same and false if not same diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 8f0102b71656..014235fd4681 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2021.1" +#define BATADV_SOURCE_VERSION "2021.2" #endif /* B.A.T.M.A.N. parameters */ @@ -88,7 +88,6 @@ /* number of packets to send for broadcasts on different interface types */ #define BATADV_NUM_BCASTS_DEFAULT 1 #define BATADV_NUM_BCASTS_WIRELESS 3 -#define BATADV_NUM_BCASTS_MAX 3 /* length of the single packet used by the TP meter */ #define BATADV_TP_PACKET_LEN ETH_DATA_LEN diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 1d63c8cbbfe7..923e2197c2db 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -193,53 +193,22 @@ static u8 batadv_mcast_mla_rtr_flags_softif_get(struct batadv_priv *bat_priv, * BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present * The former two OR'd: no multicast router is present */ -#if IS_ENABLED(CONFIG_IPV6) static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv, struct net_device *bridge) { - struct list_head bridge_mcast_list = LIST_HEAD_INIT(bridge_mcast_list); struct net_device *dev = bat_priv->soft_iface; - struct br_ip_list *br_ip_entry, *tmp; - u8 flags = BATADV_MCAST_WANT_NO_RTR6; - int ret; + u8 flags = BATADV_NO_FLAGS; if (!bridge) return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6; - /* TODO: ask the bridge if a multicast router is present (the bridge - * is capable of performing proper RFC4286 multicast router - * discovery) instead of searching for a ff02::2 listener here - */ - ret = br_multicast_list_adjacent(dev, &bridge_mcast_list); - if (ret < 0) - return BATADV_NO_FLAGS; - - list_for_each_entry_safe(br_ip_entry, tmp, &bridge_mcast_list, list) { - /* the bridge snooping does not maintain IPv4 link-local - * addresses - therefore we won't find any IPv4 multicast router - * address here, only IPv6 ones - */ - if (br_ip_entry->addr.proto == htons(ETH_P_IPV6) && - ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.dst.ip6)) - flags &= ~BATADV_MCAST_WANT_NO_RTR6; - - list_del(&br_ip_entry->list); - kfree(br_ip_entry); - } + if (!br_multicast_has_router_adjacent(dev, ETH_P_IP)) + flags |= BATADV_MCAST_WANT_NO_RTR4; + if (!br_multicast_has_router_adjacent(dev, ETH_P_IPV6)) + flags |= BATADV_MCAST_WANT_NO_RTR6; return flags; } -#else -static inline u8 -batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv, - struct net_device *bridge) -{ - if (bridge) - return BATADV_NO_FLAGS; - else - return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6; -} -#endif /** * batadv_mcast_mla_rtr_flags_get() - get multicast router flags diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index f317d206b411..b6cc746e01a6 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -814,6 +814,10 @@ static int batadv_netlink_hardif_fill(struct sk_buff *msg, bat_priv->soft_iface->ifindex)) goto nla_put_failure; + if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, + bat_priv->soft_iface->name)) + goto nla_put_failure; + if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, net_dev->ifindex) || nla_put_string(msg, BATADV_ATTR_HARD_IFNAME, @@ -1045,6 +1049,10 @@ static int batadv_netlink_vlan_fill(struct sk_buff *msg, bat_priv->soft_iface->ifindex)) goto nla_put_failure; + if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, + bat_priv->soft_iface->name)) + goto nla_put_failure; + if (nla_put_u32(msg, BATADV_ATTR_VLANID, vlan->vid & VLAN_VID_MASK)) goto nla_put_failure; diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 40f5cffde6a3..bb9e93e3d98c 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1182,9 +1182,9 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, struct batadv_bcast_packet *bcast_packet; struct ethhdr *ethhdr; int hdr_size = sizeof(*bcast_packet); - int ret = NET_RX_DROP; s32 seq_diff; u32 seqno; + int ret; /* drop packet if it has not necessary minimum size */ if (unlikely(!pskb_may_pull(skb, hdr_size))) @@ -1210,7 +1210,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, if (batadv_is_my_mac(bat_priv, bcast_packet->orig)) goto free_skb; - if (bcast_packet->ttl < 2) + if (bcast_packet->ttl-- < 2) goto free_skb; orig_node = batadv_orig_hash_find(bat_priv, bcast_packet->orig); @@ -1249,7 +1249,9 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, batadv_skb_set_priority(skb, sizeof(struct batadv_bcast_packet)); /* rebroadcast packet */ - batadv_add_bcast_packet_to_list(bat_priv, skb, 1, false); + ret = batadv_forw_bcast_packet(bat_priv, skb, 0, false); + if (ret == NETDEV_TX_BUSY) + goto free_skb; /* don't hand the broadcast up if it is from an originator * from the same backbone. @@ -1275,6 +1277,7 @@ spin_unlock: spin_unlock_bh(&orig_node->bcast_seqno_lock); free_skb: kfree_skb(skb); + ret = NET_RX_DROP; out: if (orig_node) batadv_orig_node_put(orig_node); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 157abe92d827..0b9dd29d3b6a 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -737,57 +737,48 @@ void batadv_forw_packet_ogmv1_queue(struct batadv_priv *bat_priv, } /** - * batadv_add_bcast_packet_to_list() - queue broadcast packet for multiple sends + * batadv_forw_bcast_packet_to_list() - queue broadcast packet for transmissions * @bat_priv: the bat priv with all the soft interface information * @skb: broadcast packet to add * @delay: number of jiffies to wait before sending * @own_packet: true if it is a self-generated broadcast packet + * @if_in: the interface where the packet was received on + * @if_out: the outgoing interface to queue on * - * add a broadcast packet to the queue and setup timers. broadcast packets + * Adds a broadcast packet to the queue and sets up timers. Broadcast packets * are sent multiple times to increase probability for being received. * - * The skb is not consumed, so the caller should make sure that the - * skb is freed. - * * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. */ -int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, - const struct sk_buff *skb, - unsigned long delay, - bool own_packet) +static int batadv_forw_bcast_packet_to_list(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet, + struct batadv_hard_iface *if_in, + struct batadv_hard_iface *if_out) { - struct batadv_hard_iface *primary_if; struct batadv_forw_packet *forw_packet; - struct batadv_bcast_packet *bcast_packet; + unsigned long send_time = jiffies; struct sk_buff *newskb; - primary_if = batadv_primary_if_get_selected(bat_priv); - if (!primary_if) - goto err; - newskb = skb_copy(skb, GFP_ATOMIC); - if (!newskb) { - batadv_hardif_put(primary_if); + if (!newskb) goto err; - } - forw_packet = batadv_forw_packet_alloc(primary_if, NULL, + forw_packet = batadv_forw_packet_alloc(if_in, if_out, &bat_priv->bcast_queue_left, bat_priv, newskb); - batadv_hardif_put(primary_if); if (!forw_packet) goto err_packet_free; - /* as we have a copy now, it is safe to decrease the TTL */ - bcast_packet = (struct batadv_bcast_packet *)newskb->data; - bcast_packet->ttl--; - forw_packet->own = own_packet; INIT_DELAYED_WORK(&forw_packet->delayed_work, batadv_send_outstanding_bcast_packet); - batadv_forw_packet_bcast_queue(bat_priv, forw_packet, jiffies + delay); + send_time += delay ? delay : msecs_to_jiffies(5); + + batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return NETDEV_TX_OK; err_packet_free: @@ -796,10 +787,220 @@ err: return NETDEV_TX_BUSY; } +/** + * batadv_forw_bcast_packet_if() - forward and queue a broadcast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: broadcast packet to add + * @delay: number of jiffies to wait before sending + * @own_packet: true if it is a self-generated broadcast packet + * @if_in: the interface where the packet was received on + * @if_out: the outgoing interface to forward to + * + * Transmits a broadcast packet on the specified interface either immediately + * or if a delay is given after that. Furthermore, queues additional + * retransmissions if this interface is a wireless one. + * + * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. + */ +static int batadv_forw_bcast_packet_if(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet, + struct batadv_hard_iface *if_in, + struct batadv_hard_iface *if_out) +{ + unsigned int num_bcasts = if_out->num_bcasts; + struct sk_buff *newskb; + int ret = NETDEV_TX_OK; + + if (!delay) { + newskb = skb_copy(skb, GFP_ATOMIC); + if (!newskb) + return NETDEV_TX_BUSY; + + batadv_send_broadcast_skb(newskb, if_out); + num_bcasts--; + } + + /* delayed broadcast or rebroadcasts? */ + if (num_bcasts >= 1) { + BATADV_SKB_CB(skb)->num_bcasts = num_bcasts; + + ret = batadv_forw_bcast_packet_to_list(bat_priv, skb, delay, + own_packet, if_in, + if_out); + } + + return ret; +} + +/** + * batadv_send_no_broadcast() - check whether (re)broadcast is necessary + * @bat_priv: the bat priv with all the soft interface information + * @skb: broadcast packet to check + * @own_packet: true if it is a self-generated broadcast packet + * @if_out: the outgoing interface checked and considered for (re)broadcast + * + * Return: False if a packet needs to be (re)broadcasted on the given interface, + * true otherwise. + */ +static bool batadv_send_no_broadcast(struct batadv_priv *bat_priv, + struct sk_buff *skb, bool own_packet, + struct batadv_hard_iface *if_out) +{ + struct batadv_hardif_neigh_node *neigh_node = NULL; + struct batadv_bcast_packet *bcast_packet; + u8 *orig_neigh; + u8 *neigh_addr; + char *type; + int ret; + + if (!own_packet) { + neigh_addr = eth_hdr(skb)->h_source; + neigh_node = batadv_hardif_neigh_get(if_out, + neigh_addr); + } + + bcast_packet = (struct batadv_bcast_packet *)skb->data; + orig_neigh = neigh_node ? neigh_node->orig : NULL; + + ret = batadv_hardif_no_broadcast(if_out, bcast_packet->orig, + orig_neigh); + + if (neigh_node) + batadv_hardif_neigh_put(neigh_node); + + /* ok, may broadcast */ + if (!ret) + return false; + + /* no broadcast */ + switch (ret) { + case BATADV_HARDIF_BCAST_NORECIPIENT: + type = "no neighbor"; + break; + case BATADV_HARDIF_BCAST_DUPFWD: + type = "single neighbor is source"; + break; + case BATADV_HARDIF_BCAST_DUPORIG: + type = "single neighbor is originator"; + break; + default: + type = "unknown"; + } + + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "BCAST packet from orig %pM on %s suppressed: %s\n", + bcast_packet->orig, + if_out->net_dev->name, type); + + return true; +} + +/** + * __batadv_forw_bcast_packet() - forward and queue a broadcast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: broadcast packet to add + * @delay: number of jiffies to wait before sending + * @own_packet: true if it is a self-generated broadcast packet + * + * Transmits a broadcast packet either immediately or if a delay is given + * after that. Furthermore, queues additional retransmissions on wireless + * interfaces. + * + * This call clones the given skb, hence the caller needs to take into + * account that the data segment of the given skb might not be + * modifiable anymore. + * + * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. + */ +static int __batadv_forw_bcast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet) +{ + struct batadv_hard_iface *hard_iface; + struct batadv_hard_iface *primary_if; + int ret = NETDEV_TX_OK; + + primary_if = batadv_primary_if_get_selected(bat_priv); + if (!primary_if) + return NETDEV_TX_BUSY; + + rcu_read_lock(); + list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { + if (hard_iface->soft_iface != bat_priv->soft_iface) + continue; + + if (!kref_get_unless_zero(&hard_iface->refcount)) + continue; + + if (batadv_send_no_broadcast(bat_priv, skb, own_packet, + hard_iface)) { + batadv_hardif_put(hard_iface); + continue; + } + + ret = batadv_forw_bcast_packet_if(bat_priv, skb, delay, + own_packet, primary_if, + hard_iface); + batadv_hardif_put(hard_iface); + + if (ret == NETDEV_TX_BUSY) + break; + } + rcu_read_unlock(); + + batadv_hardif_put(primary_if); + return ret; +} + +/** + * batadv_forw_bcast_packet() - forward and queue a broadcast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: broadcast packet to add + * @delay: number of jiffies to wait before sending + * @own_packet: true if it is a self-generated broadcast packet + * + * Transmits a broadcast packet either immediately or if a delay is given + * after that. Furthermore, queues additional retransmissions on wireless + * interfaces. + * + * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors. + */ +int batadv_forw_bcast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet) +{ + return __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); +} + +/** + * batadv_send_bcast_packet() - send and queue a broadcast packet + * @bat_priv: the bat priv with all the soft interface information + * @skb: broadcast packet to add + * @delay: number of jiffies to wait before sending + * @own_packet: true if it is a self-generated broadcast packet + * + * Transmits a broadcast packet either immediately or if a delay is given + * after that. Furthermore, queues additional retransmissions on wireless + * interfaces. + * + * Consumes the provided skb. + */ +void batadv_send_bcast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet) +{ + __batadv_forw_bcast_packet(bat_priv, skb, delay, own_packet); + consume_skb(skb); +} + /** * batadv_forw_packet_bcasts_left() - check if a retransmission is necessary * @forw_packet: the forwarding packet to check - * @hard_iface: the interface to check on * * Checks whether a given packet has any (re)transmissions left on the provided * interface. @@ -811,28 +1012,20 @@ err: * Return: True if (re)transmissions are left, false otherwise. */ static bool -batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet, - struct batadv_hard_iface *hard_iface) +batadv_forw_packet_bcasts_left(struct batadv_forw_packet *forw_packet) { - unsigned int max; - - if (hard_iface) - max = hard_iface->num_bcasts; - else - max = BATADV_NUM_BCASTS_MAX; - - return BATADV_SKB_CB(forw_packet->skb)->num_bcasts < max; + return BATADV_SKB_CB(forw_packet->skb)->num_bcasts; } /** - * batadv_forw_packet_bcasts_inc() - increment retransmission counter of a + * batadv_forw_packet_bcasts_dec() - decrement retransmission counter of a * packet - * @forw_packet: the packet to increase the counter for + * @forw_packet: the packet to decrease the counter for */ static void -batadv_forw_packet_bcasts_inc(struct batadv_forw_packet *forw_packet) +batadv_forw_packet_bcasts_dec(struct batadv_forw_packet *forw_packet) { - BATADV_SKB_CB(forw_packet->skb)->num_bcasts++; + BATADV_SKB_CB(forw_packet->skb)->num_bcasts--; } /** @@ -843,30 +1036,30 @@ batadv_forw_packet_bcasts_inc(struct batadv_forw_packet *forw_packet) */ bool batadv_forw_packet_is_rebroadcast(struct batadv_forw_packet *forw_packet) { - return BATADV_SKB_CB(forw_packet->skb)->num_bcasts > 0; + unsigned char num_bcasts = BATADV_SKB_CB(forw_packet->skb)->num_bcasts; + + return num_bcasts != forw_packet->if_outgoing->num_bcasts; } +/** + * batadv_send_outstanding_bcast_packet() - transmit a queued broadcast packet + * @work: work queue item + * + * Transmits a queued broadcast packet and if necessary reschedules it. + */ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) { - struct batadv_hard_iface *hard_iface; - struct batadv_hardif_neigh_node *neigh_node; - struct delayed_work *delayed_work; - struct batadv_forw_packet *forw_packet; - struct batadv_bcast_packet *bcast_packet; - struct sk_buff *skb1; - struct net_device *soft_iface; - struct batadv_priv *bat_priv; unsigned long send_time = jiffies + msecs_to_jiffies(5); + struct batadv_forw_packet *forw_packet; + struct delayed_work *delayed_work; + struct batadv_priv *bat_priv; + struct sk_buff *skb1; bool dropped = false; - u8 *neigh_addr; - u8 *orig_neigh; - int ret = 0; delayed_work = to_delayed_work(work); forw_packet = container_of(delayed_work, struct batadv_forw_packet, delayed_work); - soft_iface = forw_packet->if_incoming->soft_iface; - bat_priv = netdev_priv(soft_iface); + bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface); if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) { dropped = true; @@ -878,76 +1071,15 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work) goto out; } - bcast_packet = (struct batadv_bcast_packet *)forw_packet->skb->data; + /* send a copy of the saved skb */ + skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC); + if (!skb1) + goto out; - /* rebroadcast packet */ - rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { - if (hard_iface->soft_iface != soft_iface) - continue; + batadv_send_broadcast_skb(skb1, forw_packet->if_outgoing); + batadv_forw_packet_bcasts_dec(forw_packet); - if (!batadv_forw_packet_bcasts_left(forw_packet, hard_iface)) - continue; - - if (forw_packet->own) { - neigh_node = NULL; - } else { - neigh_addr = eth_hdr(forw_packet->skb)->h_source; - neigh_node = batadv_hardif_neigh_get(hard_iface, - neigh_addr); - } - - orig_neigh = neigh_node ? neigh_node->orig : NULL; - - ret = batadv_hardif_no_broadcast(hard_iface, bcast_packet->orig, - orig_neigh); - - if (ret) { - char *type; - - switch (ret) { - case BATADV_HARDIF_BCAST_NORECIPIENT: - type = "no neighbor"; - break; - case BATADV_HARDIF_BCAST_DUPFWD: - type = "single neighbor is source"; - break; - case BATADV_HARDIF_BCAST_DUPORIG: - type = "single neighbor is originator"; - break; - default: - type = "unknown"; - } - - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "BCAST packet from orig %pM on %s suppressed: %s\n", - bcast_packet->orig, - hard_iface->net_dev->name, type); - - if (neigh_node) - batadv_hardif_neigh_put(neigh_node); - - continue; - } - - if (neigh_node) - batadv_hardif_neigh_put(neigh_node); - - if (!kref_get_unless_zero(&hard_iface->refcount)) - continue; - - /* send a copy of the saved skb */ - skb1 = skb_clone(forw_packet->skb, GFP_ATOMIC); - if (skb1) - batadv_send_broadcast_skb(skb1, hard_iface); - - batadv_hardif_put(hard_iface); - } - rcu_read_unlock(); - - batadv_forw_packet_bcasts_inc(forw_packet); - - /* if we still have some more bcasts to send */ - if (batadv_forw_packet_bcasts_left(forw_packet, NULL)) { + if (batadv_forw_packet_bcasts_left(forw_packet)) { batadv_forw_packet_bcast_queue(bat_priv, forw_packet, send_time); return; diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 2b0daf8b2bc4..08af251b765c 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -39,10 +39,14 @@ int batadv_send_broadcast_skb(struct sk_buff *skb, struct batadv_hard_iface *hard_iface); int batadv_send_unicast_skb(struct sk_buff *skb, struct batadv_neigh_node *neigh_node); -int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, - const struct sk_buff *skb, - unsigned long delay, - bool own_packet); +int batadv_forw_bcast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet); +void batadv_send_bcast_packet(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned long delay, + bool own_packet); void batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, const struct batadv_hard_iface *hard_iface); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 6b8181bc3122..ae368a42a4ad 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include @@ -37,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -191,7 +191,7 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, struct vlan_ethhdr *vhdr; unsigned int header_len = 0; int data_len = skb->len, ret; - unsigned long brd_delay = 1; + unsigned long brd_delay = 0; bool do_bcast = false, client_added; unsigned short vid; u32 seqno; @@ -330,7 +330,7 @@ send: bcast_packet = (struct batadv_bcast_packet *)skb->data; bcast_packet->version = BATADV_COMPAT_VERSION; - bcast_packet->ttl = BATADV_TTL; + bcast_packet->ttl = BATADV_TTL - 1; /* batman packet type: broadcast */ bcast_packet->packet_type = BATADV_BCAST; @@ -346,13 +346,7 @@ send: seqno = atomic_inc_return(&bat_priv->bcast_seqno); bcast_packet->seqno = htonl(seqno); - batadv_add_bcast_packet_to_list(bat_priv, skb, brd_delay, true); - - /* a copy is stored in the bcast list, therefore removing - * the original skb. - */ - consume_skb(skb); - + batadv_send_bcast_packet(bat_priv, skb, brd_delay, true); /* unicast packet */ } else { /* DHCP packets going to a server will use the GW feature */ @@ -848,14 +842,13 @@ static int batadv_softif_slave_add(struct net_device *dev, struct netlink_ext_ack *extack) { struct batadv_hard_iface *hard_iface; - struct net *net = dev_net(dev); int ret = -EINVAL; hard_iface = batadv_hardif_get_by_netdev(slave_dev); if (!hard_iface || hard_iface->soft_iface) goto out; - ret = batadv_hardif_enable_interface(hard_iface, net, dev->name); + ret = batadv_hardif_enable_interface(hard_iface, dev); out: if (hard_iface) @@ -1092,38 +1085,6 @@ static int batadv_softif_newlink(struct net *src_net, struct net_device *dev, return register_netdevice(dev); } -/** - * batadv_softif_create() - Create and register soft interface - * @net: the applicable net namespace - * @name: name of the new soft interface - * - * Return: newly allocated soft_interface, NULL on errors - */ -struct net_device *batadv_softif_create(struct net *net, const char *name) -{ - struct net_device *soft_iface; - int ret; - - soft_iface = alloc_netdev(sizeof(struct batadv_priv), name, - NET_NAME_UNKNOWN, batadv_softif_init_early); - if (!soft_iface) - return NULL; - - dev_net_set(soft_iface, net); - - soft_iface->rtnl_link_ops = &batadv_link_ops; - - ret = register_netdevice(soft_iface); - if (ret < 0) { - pr_err("Unable to register the batman interface '%s': %i\n", - name, ret); - free_netdev(soft_iface); - return NULL; - } - - return soft_iface; -} - /** * batadv_softif_destroy_netlink() - deletion of batadv_soft_interface via * netlink diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 38b0ad182584..67a2ddd6832f 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -12,14 +12,12 @@ #include #include #include -#include #include int batadv_skb_head_push(struct sk_buff *skb, unsigned int len); void batadv_interface_rx(struct net_device *soft_iface, struct sk_buff *skb, int hdr_size, struct batadv_orig_node *orig_node); -struct net_device *batadv_softif_create(struct net *net, const char *name); bool batadv_softif_is_valid(const struct net_device *net_dev); extern struct rtnl_link_ops batadv_link_ops; int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 97617d02c8f9..fd164a248569 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -103,34 +103,6 @@ static inline bool peer_del(struct lowpan_btle_dev *dev, return false; } -static inline struct lowpan_peer *peer_lookup_ba(struct lowpan_btle_dev *dev, - bdaddr_t *ba, __u8 type) -{ - struct lowpan_peer *peer; - - BT_DBG("peers %d addr %pMR type %d", atomic_read(&dev->peer_count), - ba, type); - - rcu_read_lock(); - - list_for_each_entry_rcu(peer, &dev->peers, list) { - BT_DBG("dst addr %pMR dst type %d", - &peer->chan->dst, peer->chan->dst_type); - - if (bacmp(&peer->chan->dst, ba)) - continue; - - if (type == peer->chan->dst_type) { - rcu_read_unlock(); - return peer; - } - } - - rcu_read_unlock(); - - return NULL; -} - static inline struct lowpan_peer * __peer_lookup_chan(struct lowpan_btle_dev *dev, struct l2cap_chan *chan) { @@ -195,7 +167,7 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_btle_dev *dev, rcu_read_lock(); list_for_each_entry_rcu(peer, &dev->peers, list) { - BT_DBG("dst addr %pMR dst type %d ip %pI6c", + BT_DBG("dst addr %pMR dst type %u ip %pI6c", &peer->chan->dst, peer->chan->dst_type, &peer->peer_addr); @@ -506,7 +478,7 @@ static int send_mcast_pkt(struct sk_buff *skb, struct net_device *netdev) local_skb = skb_clone(skb, GFP_ATOMIC); - BT_DBG("xmit %s to %pMR type %d IP %pI6c chan %p", + BT_DBG("xmit %s to %pMR type %u IP %pI6c chan %p", netdev->name, &pentry->chan->dst, pentry->chan->dst_type, &pentry->peer_addr, pentry->chan); @@ -549,7 +521,7 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) if (err) { if (lowpan_cb(skb)->chan) { - BT_DBG("xmit %s to %pMR type %d IP %pI6c chan %p", + BT_DBG("xmit %s to %pMR type %u IP %pI6c chan %p", netdev->name, &addr, addr_type, &lowpan_cb(skb)->addr, lowpan_cb(skb)->chan); err = send_pkt(lowpan_cb(skb)->chan, skb, netdev); @@ -691,7 +663,7 @@ static struct l2cap_chan *add_peer_chan(struct l2cap_chan *chan, static int setup_netdev(struct l2cap_chan *chan, struct lowpan_btle_dev **dev) { struct net_device *netdev; - int err = 0; + int err; netdev = alloc_netdev(LOWPAN_PRIV_SIZE(sizeof(struct lowpan_btle_dev)), IFACE_NAME_TEMPLATE, NET_NAME_UNKNOWN, @@ -818,7 +790,7 @@ static void chan_close_cb(struct l2cap_chan *chan) BT_DBG("dev %p removing %speer %p", dev, last ? "last " : "1 ", peer); - BT_DBG("chan %p orig refcnt %d", chan, + BT_DBG("chan %p orig refcnt %u", chan, kref_read(&chan->kref)); l2cap_chan_put(chan); @@ -907,14 +879,6 @@ static const struct l2cap_ops bt_6lowpan_chan_ops = { .set_shutdown = l2cap_chan_no_set_shutdown, }; -static inline __u8 bdaddr_type(__u8 type) -{ - if (type == ADDR_LE_DEV_PUBLIC) - return BDADDR_LE_PUBLIC; - else - return BDADDR_LE_RANDOM; -} - static int bt_6lowpan_connect(bdaddr_t *addr, u8 dst_type) { struct l2cap_chan *chan; @@ -940,7 +904,7 @@ static int bt_6lowpan_disconnect(struct l2cap_conn *conn, u8 dst_type) { struct lowpan_peer *peer; - BT_DBG("conn %p dst type %d", conn, dst_type); + BT_DBG("conn %p dst type %u", conn, dst_type); peer = lookup_peer(conn); if (!peer) @@ -972,7 +936,7 @@ static struct l2cap_chan *bt_6lowpan_listen(void) atomic_set(&chan->nesting, L2CAP_NESTING_PARENT); - BT_DBG("chan %p src type %d", chan, chan->src_type); + BT_DBG("chan %p src type %u", chan, chan->src_type); err = l2cap_add_psm(chan, addr, cpu_to_le16(L2CAP_PSM_IPSP)); if (err) { @@ -1013,7 +977,7 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, *conn = (struct l2cap_conn *)hcon->l2cap_data; - BT_DBG("conn %p dst %pMR type %d", *conn, &hcon->dst, hcon->dst_type); + BT_DBG("conn %p dst %pMR type %u", *conn, &hcon->dst, hcon->dst_type); return 0; } @@ -1155,7 +1119,7 @@ static ssize_t lowpan_control_write(struct file *fp, return -EALREADY; } - BT_DBG("conn %p dst %pMR type %d user %d", conn, + BT_DBG("conn %p dst %pMR type %d user %u", conn, &conn->hcon->dst, conn->hcon->dst_type, addr_type); } diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 463bad58478b..1fcc482397c3 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -120,7 +120,7 @@ static int a2mp_command_rej(struct amp_mgr *mgr, struct sk_buff *skb, if (le16_to_cpu(hdr->len) < sizeof(*rej)) return -EINVAL; - BT_DBG("ident %d reason %d", hdr->ident, le16_to_cpu(rej->reason)); + BT_DBG("ident %u reason %d", hdr->ident, le16_to_cpu(rej->reason)); skb_pull(skb, sizeof(*rej)); @@ -219,7 +219,7 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb, cl = (void *) skb->data; while (len >= sizeof(*cl)) { - BT_DBG("Remote AMP id %d type %d status %d", cl->id, cl->type, + BT_DBG("Remote AMP id %u type %u status %u", cl->id, cl->type, cl->status); if (cl->id != AMP_ID_BREDR && cl->type != AMP_TYPE_BREDR) { @@ -273,7 +273,7 @@ static int a2mp_change_notify(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cl *cl = (void *) skb->data; while (skb->len >= sizeof(*cl)) { - BT_DBG("Controller id %d type %d status %d", cl->id, cl->type, + BT_DBG("Controller id %u type %u status %u", cl->id, cl->type, cl->status); cl = skb_pull(skb, sizeof(*cl)); } @@ -302,7 +302,7 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb, if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; - BT_DBG("id %d", req->id); + BT_DBG("id %u", req->id); hdev = hci_dev_get(req->id); if (!hdev || hdev->dev_type != HCI_AMP) { @@ -344,7 +344,7 @@ static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb, if (le16_to_cpu(hdr->len) < sizeof(*rsp)) return -EINVAL; - BT_DBG("id %d status 0x%2.2x", rsp->id, rsp->status); + BT_DBG("id %u status 0x%2.2x", rsp->id, rsp->status); if (rsp->status) return -EINVAL; @@ -373,7 +373,7 @@ static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb, if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; - BT_DBG("id %d", req->id); + BT_DBG("id %u", req->id); /* Make sure that other request is not processed */ tmp = amp_mgr_lookup_by_state(READ_LOC_AMP_ASSOC); @@ -423,7 +423,7 @@ static int a2mp_getampassoc_rsp(struct amp_mgr *mgr, struct sk_buff *skb, assoc_len = len - sizeof(*rsp); - BT_DBG("id %d status 0x%2.2x assoc len %zu", rsp->id, rsp->status, + BT_DBG("id %u status 0x%2.2x assoc len %zu", rsp->id, rsp->status, assoc_len); if (rsp->status) @@ -457,7 +457,7 @@ static int a2mp_getampassoc_rsp(struct amp_mgr *mgr, struct sk_buff *skb, if (!hcon) goto done; - BT_DBG("Created hcon %p: loc:%d -> rem:%d", hcon, hdev->id, rsp->id); + BT_DBG("Created hcon %p: loc:%u -> rem:%u", hcon, hdev->id, rsp->id); mgr->bredr_chan->remote_amp_id = rsp->id; @@ -481,7 +481,7 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; - BT_DBG("local_id %d, remote_id %d", req->local_id, req->remote_id); + BT_DBG("local_id %u, remote_id %u", req->local_id, req->remote_id); memset(&rsp, 0, sizeof(rsp)); @@ -562,7 +562,7 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb, if (le16_to_cpu(hdr->len) < sizeof(*req)) return -EINVAL; - BT_DBG("local_id %d remote_id %d", req->local_id, req->remote_id); + BT_DBG("local_id %u remote_id %u", req->local_id, req->remote_id); memset(&rsp, 0, sizeof(rsp)); @@ -599,7 +599,7 @@ send_rsp: static inline int a2mp_cmd_rsp(struct amp_mgr *mgr, struct sk_buff *skb, struct a2mp_cmd *hdr) { - BT_DBG("ident %d code 0x%2.2x", hdr->ident, hdr->code); + BT_DBG("ident %u code 0x%2.2x", hdr->ident, hdr->code); skb_pull(skb, le16_to_cpu(hdr->len)); return 0; @@ -620,7 +620,7 @@ static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) hdr = (void *) skb->data; len = le16_to_cpu(hdr->len); - BT_DBG("code 0x%2.2x id %d len %u", hdr->code, hdr->ident, len); + BT_DBG("code 0x%2.2x id %u len %u", hdr->code, hdr->ident, len); skb_pull(skb, sizeof(*hdr)); diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c index be2d469d6369..2134f92bd7ac 100644 --- a/net/bluetooth/amp.c +++ b/net/bluetooth/amp.c @@ -78,7 +78,7 @@ struct amp_ctrl *amp_ctrl_lookup(struct amp_mgr *mgr, u8 id) { struct amp_ctrl *ctrl; - BT_DBG("mgr %p id %d", mgr, id); + BT_DBG("mgr %p id %u", mgr, id); mutex_lock(&mgr->amp_ctrls_lock); list_for_each_entry(ctrl, &mgr->amp_ctrls, list) { @@ -179,7 +179,7 @@ int phylink_gen_key(struct hci_conn *conn, u8 *data, u8 *len, u8 *type) /* Legacy key */ if (conn->key_type < 3) { - bt_dev_err(hdev, "legacy key type %d", conn->key_type); + bt_dev_err(hdev, "legacy key type %u", conn->key_type); return -EACCES; } @@ -257,7 +257,7 @@ void amp_read_loc_assoc_frag(struct hci_dev *hdev, u8 phy_handle) struct hci_request req; int err; - BT_DBG("%s handle %d", hdev->name, phy_handle); + BT_DBG("%s handle %u", hdev->name, phy_handle); cp.phy_handle = phy_handle; cp.max_len = cpu_to_le16(hdev->amp_assoc_size); diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 43c284158f63..72f47b372705 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -126,8 +126,8 @@ static int bnep_ctrl_set_netfilter(struct bnep_session *s, __be16 *data, int len f[i].start = get_unaligned_be16(data++); f[i].end = get_unaligned_be16(data++); - BT_DBG("proto filter start %d end %d", - f[i].start, f[i].end); + BT_DBG("proto filter start %u end %u", + f[i].start, f[i].end); } if (i < BNEP_MAX_PROTO_FILTERS) @@ -266,7 +266,7 @@ static int bnep_rx_extension(struct bnep_session *s, struct sk_buff *skb) break; } - BT_DBG("type 0x%x len %d", h->type, h->len); + BT_DBG("type 0x%x len %u", h->type, h->len); switch (h->type & BNEP_TYPE_MASK) { case BNEP_EXT_CONTROL: @@ -424,7 +424,7 @@ static int bnep_tx_frame(struct bnep_session *s, struct sk_buff *skb) int len = 0, il = 0; u8 type = 0; - BT_DBG("skb %p dev %p type %d", skb, skb->dev, skb->pkt_type); + BT_DBG("skb %p dev %p type %u", skb, skb->dev, skb->pkt_type); if (!skb->dev) { /* Control frame sent by us */ diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index eb41556002e3..f3bedc3b613a 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -74,7 +74,7 @@ static struct cmtp_application *cmtp_application_add(struct cmtp_session *sessio { struct cmtp_application *app = kzalloc(sizeof(*app), GFP_KERNEL); - BT_DBG("session %p application %p appl %d", session, app, appl); + BT_DBG("session %p application %p appl %u", session, app, appl); if (!app) return NULL; @@ -135,7 +135,7 @@ static void cmtp_send_capimsg(struct cmtp_session *session, struct sk_buff *skb) { struct cmtp_scb *scb = (void *) skb->cb; - BT_DBG("session %p skb %p len %d", session, skb, skb->len); + BT_DBG("session %p skb %p len %u", session, skb, skb->len); scb->id = -1; scb->data = (CAPIMSG_COMMAND(skb->data) == CAPI_DATA_B3); @@ -152,7 +152,7 @@ static void cmtp_send_interopmsg(struct cmtp_session *session, struct sk_buff *skb; unsigned char *s; - BT_DBG("session %p subcmd 0x%02x appl %d msgnum %d", session, subcmd, appl, msgnum); + BT_DBG("session %p subcmd 0x%02x appl %u msgnum %u", session, subcmd, appl, msgnum); skb = alloc_skb(CAPI_MSG_BASELEN + 6 + len, GFP_ATOMIC); if (!skb) { @@ -188,7 +188,7 @@ static void cmtp_recv_interopmsg(struct cmtp_session *session, struct sk_buff *s __u16 appl, msgnum, func, info; __u32 controller; - BT_DBG("session %p skb %p len %d", session, skb, skb->len); + BT_DBG("session %p skb %p len %u", session, skb, skb->len); switch (CAPIMSG_SUBCOMMAND(skb->data)) { case CAPI_CONF: @@ -321,7 +321,7 @@ void cmtp_recv_capimsg(struct cmtp_session *session, struct sk_buff *skb) __u16 appl; __u32 contr; - BT_DBG("session %p skb %p len %d", session, skb, skb->len); + BT_DBG("session %p skb %p len %u", session, skb, skb->len); if (skb->len < CAPI_MSG_BASELEN) return; @@ -344,7 +344,7 @@ void cmtp_recv_capimsg(struct cmtp_session *session, struct sk_buff *skb) appl = application->appl; CAPIMSG_SETAPPID(skb->data, appl); } else { - BT_ERR("Can't find application with id %d", appl); + BT_ERR("Can't find application with id %u", appl); kfree_skb(skb); return; } @@ -385,8 +385,8 @@ static void cmtp_register_appl(struct capi_ctr *ctrl, __u16 appl, capi_register_ unsigned char buf[8]; int err = 0, nconn, want = rp->level3cnt; - BT_DBG("ctrl %p appl %d level3cnt %d datablkcnt %d datablklen %d", - ctrl, appl, rp->level3cnt, rp->datablkcnt, rp->datablklen); + BT_DBG("ctrl %p appl %u level3cnt %u datablkcnt %u datablklen %u", + ctrl, appl, rp->level3cnt, rp->datablkcnt, rp->datablklen); application = cmtp_application_add(session, appl); if (!application) { @@ -450,7 +450,7 @@ static void cmtp_release_appl(struct capi_ctr *ctrl, __u16 appl) struct cmtp_session *session = ctrl->driverdata; struct cmtp_application *application; - BT_DBG("ctrl %p appl %d", ctrl, appl); + BT_DBG("ctrl %p appl %u", ctrl, appl); application = cmtp_application_get(session, CMTP_APPLID, appl); if (!application) { @@ -483,7 +483,7 @@ static u16 cmtp_send_message(struct capi_ctr *ctrl, struct sk_buff *skb) application = cmtp_application_get(session, CMTP_APPLID, appl); if ((!application) || (application->state != BT_CONNECTED)) { - BT_ERR("Can't find application with id %d", appl); + BT_ERR("Can't find application with id %u", appl); return CAPI_ILLAPPNR; } @@ -515,7 +515,7 @@ static int cmtp_proc_show(struct seq_file *m, void *v) seq_printf(m, "ctrl %d\n", session->num); list_for_each_entry(app, &session->applications, list) { - seq_printf(m, "appl %d -> %d\n", app->appl, app->mapping); + seq_printf(m, "appl %u -> %u\n", app->appl, app->mapping); } return 0; diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 07cfa3249f83..0a2d78e811cf 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -392,6 +392,11 @@ int cmtp_add_connection(struct cmtp_connadd_req *req, struct socket *sock) if (!(session->flags & BIT(CMTP_LOOPBACK))) { err = cmtp_attach_device(session); if (err < 0) { + /* Caller will call fput in case of failure, and so + * will cmtp_session kthread. + */ + get_file(session->sock->file); + atomic_inc(&session->terminate); wake_up_interruptible(sk_sleep(session->sock->sk)); up_write(&cmtp_session_sem); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 88ec08978ff4..2b5059a56cda 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -257,7 +257,7 @@ int hci_disconnect(struct hci_conn *conn, __u8 reason) { BT_DBG("hcon %p", conn); - /* When we are master of an established connection and it enters + /* When we are central of an established connection and it enters * the disconnect timeout, then go ahead and try to read the * current clock offset. Processing of the result is done * within the event handling and hci_clock_offset_evt function. @@ -758,7 +758,7 @@ void hci_le_conn_failed(struct hci_conn *conn, u8 status) conn->state = BT_CLOSED; /* If the status indicates successful cancellation of - * the attempt (i.e. Unkown Connection Id) there's no point of + * the attempt (i.e. Unknown Connection Id) there's no point of * notifying failure since we'll go back to keep trying to * connect. The only exception is explicit connect requests * where a timeout + cancel does indicate an actual failure. @@ -1109,9 +1109,9 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, hci_req_init(&req, hdev); - /* Disable advertising if we're active. For master role + /* Disable advertising if we're active. For central role * connections most controllers will refuse to connect if - * advertising is enabled, and for slave role connections we + * advertising is enabled, and for peripheral role connections we * anyway have to disable it in order to start directed * advertising. Any registered advertisements will be * re-enabled after the connection attempt is finished. @@ -1119,7 +1119,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, if (hci_dev_test_flag(hdev, HCI_LE_ADV)) __hci_req_pause_adv_instances(&req); - /* If requested to connect as slave use directed advertising */ + /* If requested to connect as peripheral use directed advertising */ if (conn->role == HCI_ROLE_SLAVE) { /* If we're active scanning most controllers are unable * to initiate advertising. Simply reject the attempt. @@ -1842,7 +1842,7 @@ u32 hci_conn_get_phy(struct hci_conn *conn) /* BLUETOOTH CORE SPECIFICATION Version 5.2 | Vol 2, Part B page 471: * Table 6.2: Packets defined for synchronous, asynchronous, and - * CSB logical transport types. + * CPB logical transport types. */ switch (conn->type) { case SCO_LINK: diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 7d71d104fdfd..2560ed2f144d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -545,24 +545,24 @@ static void hci_set_event_mask_page_2(struct hci_request *req) u8 events[8] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; bool changed = false; - /* If Connectionless Slave Broadcast master role is supported + /* If Connectionless Peripheral Broadcast central role is supported * enable all necessary events for it. */ - if (lmp_csb_master_capable(hdev)) { + if (lmp_cpb_central_capable(hdev)) { events[1] |= 0x40; /* Triggered Clock Capture */ events[1] |= 0x80; /* Synchronization Train Complete */ - events[2] |= 0x10; /* Slave Page Response Timeout */ - events[2] |= 0x20; /* CSB Channel Map Change */ + events[2] |= 0x10; /* Peripheral Page Response Timeout */ + events[2] |= 0x20; /* CPB Channel Map Change */ changed = true; } - /* If Connectionless Slave Broadcast slave role is supported + /* If Connectionless Peripheral Broadcast peripheral role is supported * enable all necessary events for it. */ - if (lmp_csb_slave_capable(hdev)) { + if (lmp_cpb_peripheral_capable(hdev)) { events[2] |= 0x01; /* Synchronization Train Received */ - events[2] |= 0x02; /* CSB Receive */ - events[2] |= 0x04; /* CSB Timeout */ + events[2] |= 0x02; /* CPB Receive */ + events[2] |= 0x04; /* CPB Timeout */ events[2] |= 0x08; /* Truncated Page Complete */ changed = true; } @@ -648,7 +648,7 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) */ /* If the controller supports Extended Scanner Filter - * Policies, enable the correspondig event. + * Policies, enable the corresponding event. */ if (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY) events[1] |= 0x04; /* LE Direct Advertising @@ -749,14 +749,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt) } if (hdev->commands[26] & 0x40) { - /* Read LE White List Size */ - hci_req_add(req, HCI_OP_LE_READ_WHITE_LIST_SIZE, + /* Read LE Accept List Size */ + hci_req_add(req, HCI_OP_LE_READ_ACCEPT_LIST_SIZE, 0, NULL); } if (hdev->commands[26] & 0x80) { - /* Clear LE White List */ - hci_req_add(req, HCI_OP_LE_CLEAR_WHITE_LIST, 0, NULL); + /* Clear LE Accept List */ + hci_req_add(req, HCI_OP_LE_CLEAR_ACCEPT_LIST, 0, NULL); } if (hdev->commands[34] & 0x40) { @@ -1454,7 +1454,7 @@ static int hci_dev_do_open(struct hci_dev *hdev) } /* Check for valid public address or a configured static - * random adddress, but let the HCI setup proceed to + * random address, but let the HCI setup proceed to * be able to determine if there is a public address * or not. * @@ -1721,15 +1721,8 @@ int hci_dev_do_close(struct hci_dev *hdev) BT_DBG("%s %p", hdev->name, hdev); - if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) && - !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && - test_bit(HCI_UP, &hdev->flags)) { - /* Execute vendor specific shutdown routine */ - if (hdev->shutdown) - hdev->shutdown(hdev); - } - cancel_delayed_work(&hdev->power_off); + cancel_delayed_work(&hdev->ncmd_timer); hci_request_cancel_all(hdev); hci_req_sync_lock(hdev); @@ -1805,6 +1798,14 @@ int hci_dev_do_close(struct hci_dev *hdev) clear_bit(HCI_INIT, &hdev->flags); } + if (!hci_dev_test_flag(hdev, HCI_UNREGISTER) && + !hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + test_bit(HCI_UP, &hdev->flags)) { + /* Execute vendor specific shutdown routine */ + if (hdev->shutdown) + hdev->shutdown(hdev); + } + /* flush cmd work */ flush_work(&hdev->cmd_work); @@ -2777,6 +2778,24 @@ static void hci_cmd_timeout(struct work_struct *work) queue_work(hdev->workqueue, &hdev->cmd_work); } +/* HCI ncmd timer function */ +static void hci_ncmd_timeout(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, + ncmd_timer.work); + + bt_dev_err(hdev, "Controller not accepting commands anymore: ncmd = 0"); + + /* During HCI_INIT phase no events can be injected if the ncmd timer + * triggers since the procedure has its own timeout handling. + */ + if (test_bit(HCI_INIT, &hdev->flags)) + return; + + /* This is an irrecoverable state, inject hardware error event */ + hci_reset_dev(hdev); +} + struct oob_data *hci_find_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 bdaddr_type) { @@ -3549,7 +3568,7 @@ void hci_conn_params_clear_disabled(struct hci_dev *hdev) if (params->auto_connect != HCI_AUTO_CONN_DISABLED) continue; - /* If trying to estabilish one time connection to disabled + /* If trying to establish one time connection to disabled * device, leave the params, but mark them as just once. */ if (params->explicit_connect) { @@ -3694,13 +3713,13 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, /* Suspend consists of two actions: * - First, disconnect everything and make the controller not * connectable (disabling scanning) - * - Second, program event filter/whitelist and enable scan + * - Second, program event filter/accept list and enable scan */ ret = hci_change_suspend_state(hdev, BT_SUSPEND_DISCONNECT); if (!ret) state = BT_SUSPEND_DISCONNECT; - /* Only configure whitelist if disconnect succeeded and wake + /* Only configure accept list if disconnect succeeded and wake * isn't being prevented. */ if (!ret && !(hdev->prevent_wake && hdev->prevent_wake(hdev))) { @@ -3808,14 +3827,14 @@ struct hci_dev *hci_alloc_dev(void) mutex_init(&hdev->req_lock); INIT_LIST_HEAD(&hdev->mgmt_pending); - INIT_LIST_HEAD(&hdev->blacklist); - INIT_LIST_HEAD(&hdev->whitelist); + INIT_LIST_HEAD(&hdev->reject_list); + INIT_LIST_HEAD(&hdev->accept_list); INIT_LIST_HEAD(&hdev->uuids); INIT_LIST_HEAD(&hdev->link_keys); INIT_LIST_HEAD(&hdev->long_term_keys); INIT_LIST_HEAD(&hdev->identity_resolving_keys); INIT_LIST_HEAD(&hdev->remote_oob_data); - INIT_LIST_HEAD(&hdev->le_white_list); + INIT_LIST_HEAD(&hdev->le_accept_list); INIT_LIST_HEAD(&hdev->le_resolv_list); INIT_LIST_HEAD(&hdev->le_conn_params); INIT_LIST_HEAD(&hdev->pend_le_conns); @@ -3841,6 +3860,7 @@ struct hci_dev *hci_alloc_dev(void) init_waitqueue_head(&hdev->suspend_wait_q); INIT_DELAYED_WORK(&hdev->cmd_timer, hci_cmd_timeout); + INIT_DELAYED_WORK(&hdev->ncmd_timer, hci_ncmd_timeout); hci_request_setup(hdev); @@ -4027,8 +4047,8 @@ void hci_unregister_dev(struct hci_dev *hdev) destroy_workqueue(hdev->req_workqueue); hci_dev_lock(hdev); - hci_bdaddr_list_clear(&hdev->blacklist); - hci_bdaddr_list_clear(&hdev->whitelist); + hci_bdaddr_list_clear(&hdev->reject_list); + hci_bdaddr_list_clear(&hdev->accept_list); hci_uuids_clear(hdev); hci_link_keys_clear(hdev); hci_smp_ltks_clear(hdev); @@ -4036,7 +4056,7 @@ void hci_unregister_dev(struct hci_dev *hdev) hci_remote_oob_data_clear(hdev); hci_adv_instances_clear(hdev); hci_adv_monitors_clear(hdev); - hci_bdaddr_list_clear(&hdev->le_white_list); + hci_bdaddr_list_clear(&hdev->le_accept_list); hci_bdaddr_list_clear(&hdev->le_resolv_list); hci_conn_params_clear_all(hdev); hci_discovery_filter_clear(hdev); @@ -4078,6 +4098,8 @@ int hci_reset_dev(struct hci_dev *hdev) hci_skb_pkt_type(skb) = HCI_EVENT_PKT; skb_put_data(skb, hw_err, 3); + bt_dev_err(hdev, "Injecting HCI hardware error event"); + /* Send Hardware Error to upper stack */ return hci_recv_frame(hdev, skb); } @@ -4284,7 +4306,7 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode) return hdev->sent_cmd->data + HCI_COMMAND_HDR_SIZE; } -/* Send HCI command and wait for command commplete event */ +/* Send HCI command and wait for command complete event */ struct sk_buff *hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param, u32 timeout) { diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index 47f4f21fbc1a..841393389f7b 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -125,7 +125,7 @@ static int device_list_show(struct seq_file *f, void *ptr) struct bdaddr_list *b; hci_dev_lock(hdev); - list_for_each_entry(b, &hdev->whitelist, list) + list_for_each_entry(b, &hdev->accept_list, list) seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type); list_for_each_entry(p, &hdev->le_conn_params, list) { seq_printf(f, "%pMR (type %u) %u\n", &p->addr, p->addr_type, @@ -144,7 +144,7 @@ static int blacklist_show(struct seq_file *f, void *p) struct bdaddr_list *b; hci_dev_lock(hdev); - list_for_each_entry(b, &hdev->blacklist, list) + list_for_each_entry(b, &hdev->reject_list, list) seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type); hci_dev_unlock(hdev); @@ -784,7 +784,7 @@ static int white_list_show(struct seq_file *f, void *ptr) struct bdaddr_list *b; hci_dev_lock(hdev); - list_for_each_entry(b, &hdev->le_white_list, list) + list_for_each_entry(b, &hdev->le_accept_list, list) seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type); hci_dev_unlock(hdev); @@ -1195,7 +1195,7 @@ void hci_debugfs_create_le(struct hci_dev *hdev) &force_static_address_fops); debugfs_create_u8("white_list_size", 0444, hdev->debugfs, - &hdev->le_white_list_size); + &hdev->le_accept_list_size); debugfs_create_file("white_list", 0444, hdev->debugfs, hdev, &white_list_fops); debugfs_create_u8("resolv_list_size", 0444, hdev->debugfs, diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 016b2999f219..1c3018202564 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -236,7 +236,7 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb) hdev->ssp_debug_mode = 0; - hci_bdaddr_list_clear(&hdev->le_white_list); + hci_bdaddr_list_clear(&hdev->le_accept_list); hci_bdaddr_list_clear(&hdev->le_resolv_list); } @@ -1492,36 +1492,22 @@ static void hci_cc_le_read_num_adv_sets(struct hci_dev *hdev, hdev->le_num_of_adv_sets = rp->num_of_sets; } -static void hci_cc_le_read_white_list_size(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_cc_le_read_accept_list_size(struct hci_dev *hdev, + struct sk_buff *skb) { - struct hci_rp_le_read_white_list_size *rp = (void *) skb->data; + struct hci_rp_le_read_accept_list_size *rp = (void *)skb->data; BT_DBG("%s status 0x%2.2x size %u", hdev->name, rp->status, rp->size); if (rp->status) return; - hdev->le_white_list_size = rp->size; + hdev->le_accept_list_size = rp->size; } -static void hci_cc_le_clear_white_list(struct hci_dev *hdev, - struct sk_buff *skb) -{ - __u8 status = *((__u8 *) skb->data); - - BT_DBG("%s status 0x%2.2x", hdev->name, status); - - if (status) - return; - - hci_bdaddr_list_clear(&hdev->le_white_list); -} - -static void hci_cc_le_add_to_white_list(struct hci_dev *hdev, +static void hci_cc_le_clear_accept_list(struct hci_dev *hdev, struct sk_buff *skb) { - struct hci_cp_le_add_to_white_list *sent; __u8 status = *((__u8 *) skb->data); BT_DBG("%s status 0x%2.2x", hdev->name, status); @@ -1529,18 +1515,13 @@ static void hci_cc_le_add_to_white_list(struct hci_dev *hdev, if (status) return; - sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_WHITE_LIST); - if (!sent) - return; - - hci_bdaddr_list_add(&hdev->le_white_list, &sent->bdaddr, - sent->bdaddr_type); + hci_bdaddr_list_clear(&hdev->le_accept_list); } -static void hci_cc_le_del_from_white_list(struct hci_dev *hdev, - struct sk_buff *skb) +static void hci_cc_le_add_to_accept_list(struct hci_dev *hdev, + struct sk_buff *skb) { - struct hci_cp_le_del_from_white_list *sent; + struct hci_cp_le_add_to_accept_list *sent; __u8 status = *((__u8 *) skb->data); BT_DBG("%s status 0x%2.2x", hdev->name, status); @@ -1548,11 +1529,30 @@ static void hci_cc_le_del_from_white_list(struct hci_dev *hdev, if (status) return; - sent = hci_sent_cmd_data(hdev, HCI_OP_LE_DEL_FROM_WHITE_LIST); + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_ADD_TO_ACCEPT_LIST); if (!sent) return; - hci_bdaddr_list_del(&hdev->le_white_list, &sent->bdaddr, + hci_bdaddr_list_add(&hdev->le_accept_list, &sent->bdaddr, + sent->bdaddr_type); +} + +static void hci_cc_le_del_from_accept_list(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_del_from_accept_list *sent; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%2.2x", hdev->name, status); + + if (status) + return; + + sent = hci_sent_cmd_data(hdev, HCI_OP_LE_DEL_FROM_ACCEPT_LIST); + if (!sent) + return; + + hci_bdaddr_list_del(&hdev->le_accept_list, &sent->bdaddr, sent->bdaddr_type); } @@ -2069,7 +2069,7 @@ static void hci_check_pending_name(struct hci_dev *hdev, struct hci_conn *conn, if (conn && (conn->state == BT_CONFIG || conn->state == BT_CONNECTED) && !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, conn, 0, name, name_len); + mgmt_device_connected(hdev, conn, name, name_len); if (discov->state == DISCOVERY_STOPPED) return; @@ -2367,7 +2367,7 @@ static void cs_le_create_conn(struct hci_dev *hdev, bdaddr_t *peer_addr, /* We don't want the connection attempt to stick around * indefinitely since LE doesn't have a page timeout concept * like BR/EDR. Set a timer for any connection that doesn't use - * the white list for connecting. + * the accept list for connecting. */ if (filter_policy == HCI_LE_USE_PEER_ADDR) queue_delayed_work(conn->hdev->workqueue, @@ -2623,7 +2623,7 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) * only used during suspend. */ if (ev->link_type == ACL_LINK && - hci_bdaddr_list_lookup_with_flags(&hdev->whitelist, + hci_bdaddr_list_lookup_with_flags(&hdev->accept_list, &ev->bdaddr, BDADDR_BREDR)) { conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr, @@ -2745,19 +2745,19 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) return; } - if (hci_bdaddr_list_lookup(&hdev->blacklist, &ev->bdaddr, + if (hci_bdaddr_list_lookup(&hdev->reject_list, &ev->bdaddr, BDADDR_BREDR)) { hci_reject_conn(hdev, &ev->bdaddr); return; } - /* Require HCI_CONNECTABLE or a whitelist entry to accept the + /* Require HCI_CONNECTABLE or an accept list entry to accept the * connection. These features are only touched through mgmt so * only do the checks if HCI_MGMT is set. */ if (hci_dev_test_flag(hdev, HCI_MGMT) && !hci_dev_test_flag(hdev, HCI_CONNECTABLE) && - !hci_bdaddr_list_lookup_with_flags(&hdev->whitelist, &ev->bdaddr, + !hci_bdaddr_list_lookup_with_flags(&hdev->accept_list, &ev->bdaddr, BDADDR_BREDR)) { hci_reject_conn(hdev, &ev->bdaddr); return; @@ -2795,9 +2795,9 @@ static void hci_conn_request_evt(struct hci_dev *hdev, struct sk_buff *skb) bacpy(&cp.bdaddr, &ev->bdaddr); if (lmp_rswitch_capable(hdev) && (mask & HCI_LM_MASTER)) - cp.role = 0x00; /* Become master */ + cp.role = 0x00; /* Become central */ else - cp.role = 0x01; /* Remain slave */ + cp.role = 0x01; /* Remain peripheral */ hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp), &cp); } else if (!(flags & HCI_PROTO_DEFER)) { @@ -3256,7 +3256,7 @@ static void hci_remote_features_evt(struct hci_dev *hdev, cp.pscan_rep_mode = 0x02; hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp); } else if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, conn, 0, NULL, 0); + mgmt_device_connected(hdev, conn, NULL, 0); if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; @@ -3268,6 +3268,23 @@ unlock: hci_dev_unlock(hdev); } +static inline void handle_cmd_cnt_and_timer(struct hci_dev *hdev, + u16 opcode, u8 ncmd) +{ + if (opcode != HCI_OP_NOP) + cancel_delayed_work(&hdev->cmd_timer); + + if (!test_bit(HCI_RESET, &hdev->flags)) { + if (ncmd) { + cancel_delayed_work(&hdev->ncmd_timer); + atomic_set(&hdev->cmd_cnt, 1); + } else { + schedule_delayed_work(&hdev->ncmd_timer, + HCI_NCMD_TIMEOUT); + } + } +} + static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, u16 *opcode, u8 *status, hci_req_complete_t *req_complete, @@ -3521,20 +3538,20 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, hci_cc_le_set_scan_enable(hdev, skb); break; - case HCI_OP_LE_READ_WHITE_LIST_SIZE: - hci_cc_le_read_white_list_size(hdev, skb); + case HCI_OP_LE_READ_ACCEPT_LIST_SIZE: + hci_cc_le_read_accept_list_size(hdev, skb); break; - case HCI_OP_LE_CLEAR_WHITE_LIST: - hci_cc_le_clear_white_list(hdev, skb); + case HCI_OP_LE_CLEAR_ACCEPT_LIST: + hci_cc_le_clear_accept_list(hdev, skb); break; - case HCI_OP_LE_ADD_TO_WHITE_LIST: - hci_cc_le_add_to_white_list(hdev, skb); + case HCI_OP_LE_ADD_TO_ACCEPT_LIST: + hci_cc_le_add_to_accept_list(hdev, skb); break; - case HCI_OP_LE_DEL_FROM_WHITE_LIST: - hci_cc_le_del_from_white_list(hdev, skb); + case HCI_OP_LE_DEL_FROM_ACCEPT_LIST: + hci_cc_le_del_from_accept_list(hdev, skb); break; case HCI_OP_LE_READ_SUPPORTED_STATES: @@ -3630,11 +3647,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb, break; } - if (*opcode != HCI_OP_NOP) - cancel_delayed_work(&hdev->cmd_timer); - - if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) - atomic_set(&hdev->cmd_cnt, 1); + handle_cmd_cnt_and_timer(hdev, *opcode, ev->ncmd); hci_req_cmd_complete(hdev, *opcode, *status, req_complete, req_complete_skb); @@ -3735,11 +3748,7 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb, break; } - if (*opcode != HCI_OP_NOP) - cancel_delayed_work(&hdev->cmd_timer); - - if (ev->ncmd && !test_bit(HCI_RESET, &hdev->flags)) - atomic_set(&hdev->cmd_cnt, 1); + handle_cmd_cnt_and_timer(hdev, *opcode, ev->ncmd); /* Indicate request completion if the command failed. Also, if * we're not waiting for a special event and we get a success @@ -4330,7 +4339,7 @@ static void hci_remote_ext_features_evt(struct hci_dev *hdev, cp.pscan_rep_mode = 0x02; hci_send_cmd(hdev, HCI_OP_REMOTE_NAME_REQ, sizeof(cp), &cp); } else if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, conn, 0, NULL, 0); + mgmt_device_connected(hdev, conn, NULL, 0); if (!hci_outgoing_auth_needed(hdev, conn)) { conn->state = BT_CONNECTED; @@ -4404,12 +4413,12 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, bt_dev_dbg(hdev, "SCO connected with air mode: %02x", ev->air_mode); - switch (conn->setting & SCO_AIRMODE_MASK) { - case SCO_AIRMODE_CVSD: + switch (ev->air_mode) { + case 0x02: if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_ENABLE_SCO_CVSD); break; - case SCO_AIRMODE_TRANSP: + case 0x03: if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_ENABLE_SCO_TRANSP); break; @@ -5122,8 +5131,8 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn->dst_type = bdaddr_type; /* If we didn't have a hci_conn object previously - * but we're in master role this must be something - * initiated using a white list. Since white list based + * but we're in central role this must be something + * initiated using an accept list. Since accept list based * connections are not "first class citizens" we don't * have full tracking of them. Therefore, we go ahead * with a "best effort" approach of determining the @@ -5187,6 +5196,23 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn->dst_type = irk->addr_type; } + /* When using controller based address resolution, then the new + * address types 0x02 and 0x03 are used. These types need to be + * converted back into either public address or random address type + */ + if (use_ll_privacy(hdev) && + hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) && + hci_dev_test_flag(hdev, HCI_LL_RPA_RESOLUTION)) { + switch (conn->dst_type) { + case ADDR_LE_DEV_PUBLIC_RESOLVED: + conn->dst_type = ADDR_LE_DEV_PUBLIC; + break; + case ADDR_LE_DEV_RANDOM_RESOLVED: + conn->dst_type = ADDR_LE_DEV_RANDOM; + break; + } + } + if (status) { hci_le_conn_failed(conn, status); goto unlock; @@ -5198,13 +5224,13 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, addr_type = BDADDR_LE_RANDOM; /* Drop the connection if the device is blocked */ - if (hci_bdaddr_list_lookup(&hdev->blacklist, &conn->dst, addr_type)) { + if (hci_bdaddr_list_lookup(&hdev->reject_list, &conn->dst, addr_type)) { hci_conn_drop(conn); goto unlock; } if (!test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) - mgmt_device_connected(hdev, conn, 0, NULL, 0); + mgmt_device_connected(hdev, conn, NULL, 0); conn->sec_level = BT_SECURITY_LOW; conn->handle = handle; @@ -5217,17 +5243,17 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, hci_debugfs_create_conn(conn); hci_conn_add_sysfs(conn); - /* The remote features procedure is defined for master + /* The remote features procedure is defined for central * role only. So only in case of an initiated connection * request the remote features. * - * If the local controller supports slave-initiated features - * exchange, then requesting the remote features in slave + * If the local controller supports peripheral-initiated features + * exchange, then requesting the remote features in peripheral * role is possible. Otherwise just transition into the * connected state without requesting the remote features. */ if (conn->out || - (hdev->le_features[0] & HCI_LE_SLAVE_FEATURES)) { + (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) { struct hci_cp_le_read_remote_features cp; cp.handle = __cpu_to_le16(conn->handle); @@ -5296,8 +5322,19 @@ static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s status 0x%2.2x", hdev->name, ev->status); - if (ev->status) + if (ev->status) { + struct adv_info *adv; + + adv = hci_find_adv_instance(hdev, ev->handle); + if (!adv) + return; + + /* Remove advertising as it has been terminated */ + hci_remove_adv_instance(hdev, ev->handle); + mgmt_advertising_removed(NULL, hdev, ev->handle); + return; + } conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->conn_handle)); if (conn) { @@ -5354,13 +5391,13 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, return NULL; /* Ignore if the device is blocked */ - if (hci_bdaddr_list_lookup(&hdev->blacklist, addr, addr_type)) + if (hci_bdaddr_list_lookup(&hdev->reject_list, addr, addr_type)) return NULL; /* Most controller will fail if we try to create new connections - * while we have an existing one in slave role. + * while we have an existing one in peripheral role. */ - if (hdev->conn_hash.le_num_slave > 0 && + if (hdev->conn_hash.le_num_peripheral > 0 && (!test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) || !(hdev->le_states[3] & 0x10))) return NULL; @@ -5378,7 +5415,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, case HCI_AUTO_CONN_DIRECT: /* Only devices advertising with ADV_DIRECT_IND are * triggering a connection attempt. This is allowing - * incoming connections from slave devices. + * incoming connections from peripheral devices. */ if (adv_type != LE_ADV_DIRECT_IND) return NULL; @@ -5386,8 +5423,8 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, case HCI_AUTO_CONN_ALWAYS: /* Devices advertising with ADV_IND or ADV_DIRECT_IND * are triggering a connection attempt. This means - * that incoming connections from slave device are - * accepted and also outgoing connections to slave + * that incoming connections from peripheral device are + * accepted and also outgoing connections to peripheral * devices are established when found. */ break; @@ -5441,7 +5478,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, struct hci_conn *conn; bool match; u32 flags; - u8 *ptr, real_len; + u8 *ptr; switch (type) { case LE_ADV_IND: @@ -5472,14 +5509,10 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, break; } - real_len = ptr - data; - - /* Adjust for actual length */ - if (len != real_len) { - bt_dev_err_ratelimited(hdev, "advertising data len corrected %u -> %u", - len, real_len); - len = real_len; - } + /* Adjust for actual length. This handles the case when remote + * device is advertising with incorrect data length. + */ + len = ptr - data; /* If the direct address is present, then this report is from * a LE Direct Advertising Report event. In that case it is @@ -5752,7 +5785,7 @@ static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, if (conn->state == BT_CONFIG) { __u8 status; - /* If the local controller supports slave-initiated + /* If the local controller supports peripheral-initiated * features exchange, but the remote controller does * not, then it is possible that the error code 0x1a * for unsupported remote feature gets returned. @@ -5761,8 +5794,8 @@ static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev, * transition into connected state and mark it as * successful. */ - if ((hdev->le_features[0] & HCI_LE_SLAVE_FEATURES) && - !conn->out && ev->status == 0x1a) + if (!conn->out && ev->status == 0x1a && + (hdev->le_features[0] & HCI_LE_PERIPHERAL_FEATURES)) status = 0x00; else status = ev->status; @@ -6032,7 +6065,7 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode, return true; } - /* Check if request ended in Command Status - no way to retreive + /* Check if request ended in Command Status - no way to retrieve * any extra parameters in this case. */ if (hdr->evt == HCI_EV_CMD_STATUS) diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index fa9125b782f8..1d14adc023e9 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -745,17 +745,17 @@ void hci_req_add_le_scan_disable(struct hci_request *req, bool rpa_le_conn) } } -static void del_from_white_list(struct hci_request *req, bdaddr_t *bdaddr, - u8 bdaddr_type) +static void del_from_accept_list(struct hci_request *req, bdaddr_t *bdaddr, + u8 bdaddr_type) { - struct hci_cp_le_del_from_white_list cp; + struct hci_cp_le_del_from_accept_list cp; cp.bdaddr_type = bdaddr_type; bacpy(&cp.bdaddr, bdaddr); - bt_dev_dbg(req->hdev, "Remove %pMR (0x%x) from whitelist", &cp.bdaddr, + bt_dev_dbg(req->hdev, "Remove %pMR (0x%x) from accept list", &cp.bdaddr, cp.bdaddr_type); - hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, sizeof(cp), &cp); + hci_req_add(req, HCI_OP_LE_DEL_FROM_ACCEPT_LIST, sizeof(cp), &cp); if (use_ll_privacy(req->hdev) && hci_dev_test_flag(req->hdev, HCI_ENABLE_LL_PRIVACY)) { @@ -774,31 +774,31 @@ static void del_from_white_list(struct hci_request *req, bdaddr_t *bdaddr, } } -/* Adds connection to white list if needed. On error, returns -1. */ -static int add_to_white_list(struct hci_request *req, - struct hci_conn_params *params, u8 *num_entries, - bool allow_rpa) +/* Adds connection to accept list if needed. On error, returns -1. */ +static int add_to_accept_list(struct hci_request *req, + struct hci_conn_params *params, u8 *num_entries, + bool allow_rpa) { - struct hci_cp_le_add_to_white_list cp; + struct hci_cp_le_add_to_accept_list cp; struct hci_dev *hdev = req->hdev; - /* Already in white list */ - if (hci_bdaddr_list_lookup(&hdev->le_white_list, ¶ms->addr, + /* Already in accept list */ + if (hci_bdaddr_list_lookup(&hdev->le_accept_list, ¶ms->addr, params->addr_type)) return 0; /* Select filter policy to accept all advertising */ - if (*num_entries >= hdev->le_white_list_size) + if (*num_entries >= hdev->le_accept_list_size) return -1; - /* White list can not be used with RPAs */ + /* Accept list can not be used with RPAs */ if (!allow_rpa && !hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) && hci_find_irk_by_addr(hdev, ¶ms->addr, params->addr_type)) { return -1; } - /* During suspend, only wakeable devices can be in whitelist */ + /* During suspend, only wakeable devices can be in accept list */ if (hdev->suspended && !hci_conn_test_flag(HCI_CONN_FLAG_REMOTE_WAKEUP, params->current_flags)) return 0; @@ -807,9 +807,9 @@ static int add_to_white_list(struct hci_request *req, cp.bdaddr_type = params->addr_type; bacpy(&cp.bdaddr, ¶ms->addr); - bt_dev_dbg(hdev, "Add %pMR (0x%x) to whitelist", &cp.bdaddr, + bt_dev_dbg(hdev, "Add %pMR (0x%x) to accept list", &cp.bdaddr, cp.bdaddr_type); - hci_req_add(req, HCI_OP_LE_ADD_TO_WHITE_LIST, sizeof(cp), &cp); + hci_req_add(req, HCI_OP_LE_ADD_TO_ACCEPT_LIST, sizeof(cp), &cp); if (use_ll_privacy(hdev) && hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) { @@ -837,15 +837,15 @@ static int add_to_white_list(struct hci_request *req, return 0; } -static u8 update_white_list(struct hci_request *req) +static u8 update_accept_list(struct hci_request *req) { struct hci_dev *hdev = req->hdev; struct hci_conn_params *params; struct bdaddr_list *b; u8 num_entries = 0; bool pend_conn, pend_report; - /* We allow whitelisting even with RPAs in suspend. In the worst case, - * we won't be able to wake from devices that use the privacy1.2 + /* We allow usage of accept list even with RPAs in suspend. In the worst + * case, we won't be able to wake from devices that use the privacy1.2 * features. Additionally, once we support privacy1.2 and IRK * offloading, we can update this to also check for those conditions. */ @@ -855,13 +855,13 @@ static u8 update_white_list(struct hci_request *req) hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) allow_rpa = true; - /* Go through the current white list programmed into the + /* Go through the current accept list programmed into the * controller one by one and check if that address is still * in the list of pending connections or list of devices to * report. If not present in either list, then queue the * command to remove it from the controller. */ - list_for_each_entry(b, &hdev->le_white_list, list) { + list_for_each_entry(b, &hdev->le_accept_list, list) { pend_conn = hci_pend_le_action_lookup(&hdev->pend_le_conns, &b->bdaddr, b->bdaddr_type); @@ -870,14 +870,14 @@ static u8 update_white_list(struct hci_request *req) b->bdaddr_type); /* If the device is not likely to connect or report, - * remove it from the whitelist. + * remove it from the accept list. */ if (!pend_conn && !pend_report) { - del_from_white_list(req, &b->bdaddr, b->bdaddr_type); + del_from_accept_list(req, &b->bdaddr, b->bdaddr_type); continue; } - /* White list can not be used with RPAs */ + /* Accept list can not be used with RPAs */ if (!allow_rpa && !hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) && hci_find_irk_by_addr(hdev, &b->bdaddr, b->bdaddr_type)) { @@ -887,27 +887,27 @@ static u8 update_white_list(struct hci_request *req) num_entries++; } - /* Since all no longer valid white list entries have been + /* Since all no longer valid accept list entries have been * removed, walk through the list of pending connections * and ensure that any new device gets programmed into * the controller. * * If the list of the devices is larger than the list of - * available white list entries in the controller, then + * available accept list entries in the controller, then * just abort and return filer policy value to not use the - * white list. + * accept list. */ list_for_each_entry(params, &hdev->pend_le_conns, action) { - if (add_to_white_list(req, params, &num_entries, allow_rpa)) + if (add_to_accept_list(req, params, &num_entries, allow_rpa)) return 0x00; } /* After adding all new pending connections, walk through * the list of pending reports and also add these to the - * white list if there is still space. Abort if space runs out. + * accept list if there is still space. Abort if space runs out. */ list_for_each_entry(params, &hdev->pend_le_reports, action) { - if (add_to_white_list(req, params, &num_entries, allow_rpa)) + if (add_to_accept_list(req, params, &num_entries, allow_rpa)) return 0x00; } @@ -921,7 +921,7 @@ static u8 update_white_list(struct hci_request *req) hdev->interleave_scan_state != INTERLEAVE_SCAN_ALLOWLIST) return 0x00; - /* Select filter policy to use white list */ + /* Select filter policy to use accept list */ return 0x01; } @@ -932,7 +932,7 @@ static bool scan_use_rpa(struct hci_dev *hdev) static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, u16 window, u8 own_addr_type, u8 filter_policy, - bool addr_resolv) + bool filter_dup, bool addr_resolv) { struct hci_dev *hdev = req->hdev; @@ -997,7 +997,7 @@ static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, memset(&ext_enable_cp, 0, sizeof(ext_enable_cp)); ext_enable_cp.enable = LE_SCAN_ENABLE; - ext_enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + ext_enable_cp.filter_dup = filter_dup; hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE, sizeof(ext_enable_cp), &ext_enable_cp); @@ -1016,7 +1016,7 @@ static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, memset(&enable_cp, 0, sizeof(enable_cp)); enable_cp.enable = LE_SCAN_ENABLE; - enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE; + enable_cp.filter_dup = filter_dup; hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp), &enable_cp); } @@ -1053,6 +1053,8 @@ void hci_req_add_le_passive_scan(struct hci_request *req) u8 own_addr_type; u8 filter_policy; u16 window, interval; + /* Default is to enable duplicates filter */ + u8 filter_dup = LE_SCAN_FILTER_DUP_ENABLE; /* Background scanning should run with address resolution */ bool addr_resolv = true; @@ -1076,20 +1078,20 @@ void hci_req_add_le_passive_scan(struct hci_request *req) return; bt_dev_dbg(hdev, "interleave state %d", hdev->interleave_scan_state); - /* Adding or removing entries from the white list must + /* Adding or removing entries from the accept list must * happen before enabling scanning. The controller does - * not allow white list modification while scanning. + * not allow accept list modification while scanning. */ - filter_policy = update_white_list(req); + filter_policy = update_accept_list(req); /* When the controller is using random resolvable addresses and * with that having LE privacy enabled, then controllers with * Extended Scanner Filter Policies support can now enable support * for handling directed advertising. * - * So instead of using filter polices 0x00 (no whitelist) - * and 0x01 (whitelist enabled) use the new filter policies - * 0x02 (no whitelist) and 0x03 (whitelist enabled). + * So instead of using filter polices 0x00 (no accept list) + * and 0x01 (accept list enabled) use the new filter policies + * 0x02 (no accept list) and 0x03 (accept list enabled). */ if (hci_dev_test_flag(hdev, HCI_PRIVACY) && (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY)) @@ -1106,14 +1108,30 @@ void hci_req_add_le_passive_scan(struct hci_request *req) } else if (hci_is_adv_monitoring(hdev)) { window = hdev->le_scan_window_adv_monitor; interval = hdev->le_scan_int_adv_monitor; + + /* Disable duplicates filter when scanning for advertisement + * monitor for the following reasons. + * + * For HW pattern filtering (ex. MSFT), Realtek and Qualcomm + * controllers ignore RSSI_Sampling_Period when the duplicates + * filter is enabled. + * + * For SW pattern filtering, when we're not doing interleaved + * scanning, it is necessary to disable duplicates filter, + * otherwise hosts can only receive one advertisement and it's + * impossible to know if a peer is still in range. + */ + filter_dup = LE_SCAN_FILTER_DUP_DISABLE; } else { window = hdev->le_scan_window; interval = hdev->le_scan_interval; } - bt_dev_dbg(hdev, "LE passive scan with whitelist = %d", filter_policy); + bt_dev_dbg(hdev, "LE passive scan with accept list = %d", + filter_policy); hci_req_start_scan(req, LE_SCAN_PASSIVE, interval, window, - own_addr_type, filter_policy, addr_resolv); + own_addr_type, filter_policy, filter_dup, + addr_resolv); } static bool adv_instance_is_scannable(struct hci_dev *hdev, u8 instance) @@ -1163,7 +1181,7 @@ static void hci_req_set_event_filter(struct hci_request *req) /* Always clear event filter when starting */ hci_req_clear_event_filter(req); - list_for_each_entry(b, &hdev->whitelist, list) { + list_for_each_entry(b, &hdev->accept_list, list) { if (!hci_conn_test_flag(HCI_CONN_FLAG_REMOTE_WAKEUP, b->current_flags)) continue; @@ -1502,13 +1520,14 @@ static bool is_advertising_allowed(struct hci_dev *hdev, bool connectable) if (hci_conn_num(hdev, LE_LINK) == 0) return true; - /* Check le_states if there is any connection in slave role. */ - if (hdev->conn_hash.le_num_slave > 0) { - /* Slave connection state and non connectable mode bit 20. */ + /* Check le_states if there is any connection in peripheral role. */ + if (hdev->conn_hash.le_num_peripheral > 0) { + /* Peripheral connection state and non connectable mode bit 20. + */ if (!connectable && !(hdev->le_states[2] & 0x10)) return false; - /* Slave connection state and connectable mode bit 38 + /* Peripheral connection state and connectable mode bit 38 * and scannable bit 21. */ if (connectable && (!(hdev->le_states[4] & 0x40) || @@ -1516,13 +1535,13 @@ static bool is_advertising_allowed(struct hci_dev *hdev, bool connectable) return false; } - /* Check le_states if there is any connection in master role. */ - if (hci_conn_num(hdev, LE_LINK) != hdev->conn_hash.le_num_slave) { - /* Master connection state and non connectable mode bit 18. */ + /* Check le_states if there is any connection in central role. */ + if (hci_conn_num(hdev, LE_LINK) != hdev->conn_hash.le_num_peripheral) { + /* Central connection state and non connectable mode bit 18. */ if (!connectable && !(hdev->le_states[2] & 0x02)) return false; - /* Master connection state and connectable mode bit 35 and + /* Central connection state and connectable mode bit 35 and * scannable 19. */ if (connectable && (!(hdev->le_states[4] & 0x08) || @@ -1697,30 +1716,33 @@ void __hci_req_update_scan_rsp_data(struct hci_request *req, u8 instance) return; if (ext_adv_capable(hdev)) { - struct hci_cp_le_set_ext_scan_rsp_data cp; + struct { + struct hci_cp_le_set_ext_scan_rsp_data cp; + u8 data[HCI_MAX_EXT_AD_LENGTH]; + } pdu; - memset(&cp, 0, sizeof(cp)); + memset(&pdu, 0, sizeof(pdu)); if (instance) len = create_instance_scan_rsp_data(hdev, instance, - cp.data); + pdu.data); else - len = create_default_scan_rsp_data(hdev, cp.data); + len = create_default_scan_rsp_data(hdev, pdu.data); if (hdev->scan_rsp_data_len == len && - !memcmp(cp.data, hdev->scan_rsp_data, len)) + !memcmp(pdu.data, hdev->scan_rsp_data, len)) return; - memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data)); + memcpy(hdev->scan_rsp_data, pdu.data, len); hdev->scan_rsp_data_len = len; - cp.handle = instance; - cp.length = len; - cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; - cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; + pdu.cp.handle = instance; + pdu.cp.length = len; + pdu.cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; + pdu.cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; - hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_RSP_DATA, sizeof(cp), - &cp); + hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_RSP_DATA, + sizeof(pdu.cp) + len, &pdu.cp); } else { struct hci_cp_le_set_scan_rsp_data cp; @@ -1843,26 +1865,30 @@ void __hci_req_update_adv_data(struct hci_request *req, u8 instance) return; if (ext_adv_capable(hdev)) { - struct hci_cp_le_set_ext_adv_data cp; + struct { + struct hci_cp_le_set_ext_adv_data cp; + u8 data[HCI_MAX_EXT_AD_LENGTH]; + } pdu; - memset(&cp, 0, sizeof(cp)); + memset(&pdu, 0, sizeof(pdu)); - len = create_instance_adv_data(hdev, instance, cp.data); + len = create_instance_adv_data(hdev, instance, pdu.data); /* There's nothing to do if the data hasn't changed */ if (hdev->adv_data_len == len && - memcmp(cp.data, hdev->adv_data, len) == 0) + memcmp(pdu.data, hdev->adv_data, len) == 0) return; - memcpy(hdev->adv_data, cp.data, sizeof(cp.data)); + memcpy(hdev->adv_data, pdu.data, len); hdev->adv_data_len = len; - cp.length = len; - cp.handle = instance; - cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; - cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; + pdu.cp.length = len; + pdu.cp.handle = instance; + pdu.cp.operation = LE_SET_ADV_DATA_OP_COMPLETE; + pdu.cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG; - hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_DATA, sizeof(cp), &cp); + hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_DATA, + sizeof(pdu.cp) + len, &pdu.cp); } else { struct hci_cp_le_set_adv_data cp; @@ -2605,11 +2631,11 @@ int hci_update_random_address(struct hci_request *req, bool require_privacy, return 0; } -static bool disconnected_whitelist_entries(struct hci_dev *hdev) +static bool disconnected_accept_list_entries(struct hci_dev *hdev) { struct bdaddr_list *b; - list_for_each_entry(b, &hdev->whitelist, list) { + list_for_each_entry(b, &hdev->accept_list, list) { struct hci_conn *conn; conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &b->bdaddr); @@ -2641,7 +2667,7 @@ void __hci_req_update_scan(struct hci_request *req) return; if (hci_dev_test_flag(hdev, HCI_CONNECTABLE) || - disconnected_whitelist_entries(hdev)) + disconnected_accept_list_entries(hdev)) scan = SCAN_PAGE; else scan = SCAN_DISABLED; @@ -3133,8 +3159,10 @@ static int active_scan(struct hci_request *req, unsigned long opt) uint16_t interval = opt; struct hci_dev *hdev = req->hdev; u8 own_addr_type; - /* White list is not used for discovery */ + /* Accept list is not used for discovery */ u8 filter_policy = 0x00; + /* Default is to enable duplicates filter */ + u8 filter_dup = LE_SCAN_FILTER_DUP_ENABLE; /* Discovery doesn't require controller address resolution */ bool addr_resolv = false; int err; @@ -3159,9 +3187,26 @@ static int active_scan(struct hci_request *req, unsigned long opt) if (err < 0) own_addr_type = ADDR_LE_DEV_PUBLIC; + if (hci_is_adv_monitoring(hdev)) { + /* Duplicate filter should be disabled when some advertisement + * monitor is activated, otherwise AdvMon can only receive one + * advertisement for one peer(*) during active scanning, and + * might report loss to these peers. + * + * Note that different controllers have different meanings of + * |duplicate|. Some of them consider packets with the same + * address as duplicate, and others consider packets with the + * same address and the same RSSI as duplicate. Although in the + * latter case we don't need to disable duplicate filter, but + * it is common to have active scanning for a short period of + * time, the power impact should be neglectable. + */ + filter_dup = LE_SCAN_FILTER_DUP_DISABLE; + } + hci_req_start_scan(req, LE_SCAN_ACTIVE, interval, hdev->le_scan_window_discovery, own_addr_type, - filter_policy, addr_resolv); + filter_policy, filter_dup, addr_resolv); return 0; } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index eed0dd066e12..b04a5a02ecf3 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -892,7 +892,7 @@ static int hci_sock_release(struct socket *sock) return 0; } -static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg) +static int hci_sock_reject_list_add(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; int err; @@ -902,14 +902,14 @@ static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg) hci_dev_lock(hdev); - err = hci_bdaddr_list_add(&hdev->blacklist, &bdaddr, BDADDR_BREDR); + err = hci_bdaddr_list_add(&hdev->reject_list, &bdaddr, BDADDR_BREDR); hci_dev_unlock(hdev); return err; } -static int hci_sock_blacklist_del(struct hci_dev *hdev, void __user *arg) +static int hci_sock_reject_list_del(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; int err; @@ -919,7 +919,7 @@ static int hci_sock_blacklist_del(struct hci_dev *hdev, void __user *arg) hci_dev_lock(hdev); - err = hci_bdaddr_list_del(&hdev->blacklist, &bdaddr, BDADDR_BREDR); + err = hci_bdaddr_list_del(&hdev->reject_list, &bdaddr, BDADDR_BREDR); hci_dev_unlock(hdev); @@ -959,12 +959,12 @@ static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, case HCIBLOCKADDR: if (!capable(CAP_NET_ADMIN)) return -EPERM; - return hci_sock_blacklist_add(hdev, (void __user *)arg); + return hci_sock_reject_list_add(hdev, (void __user *)arg); case HCIUNBLOCKADDR: if (!capable(CAP_NET_ADMIN)) return -EPERM; - return hci_sock_blacklist_del(hdev, (void __user *)arg); + return hci_sock_reject_list_del(hdev, (void __user *)arg); } return -ENOIOCTLCMD; @@ -1130,7 +1130,7 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, if (!hci_sock_gen_cookie(sk)) { /* In the case when a cookie has already been assigned, * then there has been already an ioctl issued against - * an unbound socket and with that triggerd an open + * an unbound socket and with that triggered an open * notification. Send a close notification first to * allow the state transition to bounded. */ @@ -1326,9 +1326,9 @@ static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, if (hci_pi(sk)->channel == HCI_CHANNEL_CONTROL) { if (!hci_sock_gen_cookie(sk)) { /* In the case when a cookie has already been - * assigned, this socket will transtion from + * assigned, this socket will transition from * a raw socket into a control socket. To - * allow for a clean transtion, send the + * allow for a clean transition, send the * close notification first. */ skb = create_monitor_ctrl_close(sk); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 0db48c812662..80848dfc01db 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -508,7 +508,7 @@ static int hidp_process_data(struct hidp_session *session, struct sk_buff *skb, unsigned char param) { int done_with_skb = 1; - BT_DBG("session %p skb %p len %d param 0x%02x", session, skb, skb->len, param); + BT_DBG("session %p skb %p len %u param 0x%02x", session, skb, skb->len, param); switch (param) { case HIDP_DATA_RTYPE_INPUT: @@ -553,7 +553,7 @@ static void hidp_recv_ctrl_frame(struct hidp_session *session, unsigned char hdr, type, param; int free_skb = 1; - BT_DBG("session %p skb %p len %d", session, skb, skb->len); + BT_DBG("session %p skb %p len %u", session, skb, skb->len); hdr = skb->data[0]; skb_pull(skb, 1); @@ -589,7 +589,7 @@ static void hidp_recv_intr_frame(struct hidp_session *session, { unsigned char hdr; - BT_DBG("session %p skb %p len %d", session, skb, skb->len); + BT_DBG("session %p skb %p len %u", session, skb, skb->len); hdr = skb->data[0]; skb_pull(skb, 1); @@ -794,7 +794,7 @@ static int hidp_setup_hid(struct hidp_session *session, hid->dev.parent = &session->conn->hcon->dev; hid->ll_driver = &hidp_hid_driver; - /* True if device is blacklisted in drivers/hid/hid-quirks.c */ + /* True if device is blocked in drivers/hid/hid-quirks.c */ if (hid_ignore(hid)) { hid_destroy_device(session->hid); session->hid = NULL; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b6a88b8256c7..77ba68209dbd 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1691,7 +1691,7 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn) if (hcon->out) smp_conn_security(hcon, hcon->pending_sec_level); - /* For LE slave connections, make sure the connection interval + /* For LE peripheral connections, make sure the connection interval * is in the range of the minimum and maximum interval that has * been configured for this connection. If not, then trigger * the connection update procedure. @@ -4237,7 +4237,7 @@ static int l2cap_connect_req(struct l2cap_conn *conn, hci_dev_lock(hdev); if (hci_dev_test_flag(hdev, HCI_MGMT) && !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &hcon->flags)) - mgmt_device_connected(hdev, hcon, 0, NULL, 0); + mgmt_device_connected(hdev, hcon, NULL, 0); hci_dev_unlock(hdev); l2cap_connect(conn, cmd, data, L2CAP_CONN_RSP, 0); @@ -6066,7 +6066,7 @@ static inline int l2cap_ecred_conn_rsp(struct l2cap_conn *conn, struct l2cap_ecred_conn_rsp *rsp = (void *) data; struct hci_conn *hcon = conn->hcon; u16 mtu, mps, credits, result; - struct l2cap_chan *chan; + struct l2cap_chan *chan, *tmp; int err = 0, sec_level; int i = 0; @@ -6085,7 +6085,7 @@ static inline int l2cap_ecred_conn_rsp(struct l2cap_conn *conn, cmd_len -= sizeof(*rsp); - list_for_each_entry(chan, &conn->chan_l, list) { + list_for_each_entry_safe(chan, tmp, &conn->chan_l, list) { u16 dcid; if (chan->ident != cmd->ident || @@ -6248,7 +6248,7 @@ static inline int l2cap_ecred_reconf_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u16 cmd_len, u8 *data) { - struct l2cap_chan *chan; + struct l2cap_chan *chan, *tmp; struct l2cap_ecred_conn_rsp *rsp = (void *) data; u16 result; @@ -6262,7 +6262,7 @@ static inline int l2cap_ecred_reconf_rsp(struct l2cap_conn *conn, if (!result) return 0; - list_for_each_entry(chan, &conn->chan_l, list) { + list_for_each_entry_safe(chan, tmp, &conn->chan_l, list) { if (chan->ident != cmd->ident) continue; @@ -7662,7 +7662,7 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) * at least ensure that we ignore incoming data from them. */ if (hcon->type == LE_LINK && - hci_bdaddr_list_lookup(&hcon->hdev->blacklist, &hcon->dst, + hci_bdaddr_list_lookup(&hcon->hdev->reject_list, &hcon->dst, bdaddr_dst_type(hcon))) { kfree_skb(skb); return; @@ -8119,7 +8119,7 @@ static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status) dst_type = bdaddr_dst_type(hcon); /* If device is blocked, do not create channels for it */ - if (hci_bdaddr_list_lookup(&hdev->blacklist, &hcon->dst, dst_type)) + if (hci_bdaddr_list_lookup(&hdev->reject_list, &hcon->dst, dst_type)) return; /* Find fixed channels and notify them of the new connection. We diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index f9be7f9084d6..3663f880df11 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -40,7 +40,7 @@ #include "msft.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 20 +#define MGMT_REVISION 21 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -252,12 +252,15 @@ static const u8 mgmt_status_table[] = { MGMT_STATUS_TIMEOUT, /* Instant Passed */ MGMT_STATUS_NOT_SUPPORTED, /* Pairing Not Supported */ MGMT_STATUS_FAILED, /* Transaction Collision */ + MGMT_STATUS_FAILED, /* Reserved for future use */ MGMT_STATUS_INVALID_PARAMS, /* Unacceptable Parameter */ MGMT_STATUS_REJECTED, /* QoS Rejected */ MGMT_STATUS_NOT_SUPPORTED, /* Classification Not Supported */ MGMT_STATUS_REJECTED, /* Insufficient Security */ MGMT_STATUS_INVALID_PARAMS, /* Parameter Out Of Range */ + MGMT_STATUS_FAILED, /* Reserved for future use */ MGMT_STATUS_BUSY, /* Role Switch Pending */ + MGMT_STATUS_FAILED, /* Reserved for future use */ MGMT_STATUS_FAILED, /* Slot Violation */ MGMT_STATUS_FAILED, /* Role Switch Failed */ MGMT_STATUS_INVALID_PARAMS, /* EIR Too Large */ @@ -2956,7 +2959,7 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, /* When pairing a new device, it is expected to remember * this device for future connections. Adding the connection * parameter information ahead of time allows tracking - * of the slave preferred values and will speed up any + * of the peripheral preferred values and will speed up any * further connection establishment. * * If connection parameters already exist, then they @@ -3341,7 +3344,7 @@ static int set_local_name(struct sock *sk, struct hci_dev *hdev, void *data, } /* The name is stored in the scan response data and so - * no need to udpate the advertising data here. + * no need to update the advertising data here. */ if (lmp_le_capable(hdev) && hci_dev_test_flag(hdev, HCI_ADVERTISING)) __hci_req_update_scan_rsp_data(&req, hdev->cur_adv_instance); @@ -4058,8 +4061,10 @@ static int get_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); + memset(&rp, 0, sizeof(rp)); + if (cp->addr.type == BDADDR_BREDR) { - br_params = hci_bdaddr_list_lookup_with_flags(&hdev->whitelist, + br_params = hci_bdaddr_list_lookup_with_flags(&hdev->accept_list, &cp->addr.bdaddr, cp->addr.type); if (!br_params) @@ -4127,7 +4132,7 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); if (cp->addr.type == BDADDR_BREDR) { - br_params = hci_bdaddr_list_lookup_with_flags(&hdev->whitelist, + br_params = hci_bdaddr_list_lookup_with_flags(&hdev->accept_list, &cp->addr.bdaddr, cp->addr.type); @@ -4274,7 +4279,7 @@ int mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev, u8 status) done: hci_dev_unlock(hdev); - bt_dev_dbg(hdev, "add monitor %d complete, status %d", + bt_dev_dbg(hdev, "add monitor %d complete, status %u", rp.monitor_handle, status); return err; @@ -4499,7 +4504,7 @@ int mgmt_remove_adv_monitor_complete(struct hci_dev *hdev, u8 status) done: hci_dev_unlock(hdev); - bt_dev_dbg(hdev, "remove monitor %d complete, status %d", + bt_dev_dbg(hdev, "remove monitor %d complete, status %u", rp.monitor_handle, status); return err; @@ -4829,7 +4834,7 @@ void mgmt_start_discovery_complete(struct hci_dev *hdev, u8 status) { struct mgmt_pending_cmd *cmd; - bt_dev_dbg(hdev, "status %d", status); + bt_dev_dbg(hdev, "status %u", status); hci_dev_lock(hdev); @@ -5085,7 +5090,7 @@ void mgmt_stop_discovery_complete(struct hci_dev *hdev, u8 status) { struct mgmt_pending_cmd *cmd; - bt_dev_dbg(hdev, "status %d", status); + bt_dev_dbg(hdev, "status %u", status); hci_dev_lock(hdev); @@ -5204,7 +5209,7 @@ static int block_device(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); - err = hci_bdaddr_list_add(&hdev->blacklist, &cp->addr.bdaddr, + err = hci_bdaddr_list_add(&hdev->reject_list, &cp->addr.bdaddr, cp->addr.type); if (err < 0) { status = MGMT_STATUS_FAILED; @@ -5240,7 +5245,7 @@ static int unblock_device(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); - err = hci_bdaddr_list_del(&hdev->blacklist, &cp->addr.bdaddr, + err = hci_bdaddr_list_del(&hdev->reject_list, &cp->addr.bdaddr, cp->addr.type); if (err < 0) { status = MGMT_STATUS_INVALID_PARAMS; @@ -5298,7 +5303,7 @@ static int set_device_id(struct sock *sk, struct hci_dev *hdev, void *data, static void enable_advertising_instance(struct hci_dev *hdev, u8 status, u16 opcode) { - bt_dev_dbg(hdev, "status %d", status); + bt_dev_dbg(hdev, "status %u", status); } static void set_advertising_complete(struct hci_dev *hdev, u8 status, @@ -6164,7 +6169,7 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, static bool ltk_is_valid(struct mgmt_ltk_info *key) { - if (key->master != 0x00 && key->master != 0x01) + if (key->initiator != 0x00 && key->initiator != 0x01) return false; switch (key->addr.type) { @@ -6242,11 +6247,11 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, switch (key->type) { case MGMT_LTK_UNAUTHENTICATED: authenticated = 0x00; - type = key->master ? SMP_LTK : SMP_LTK_SLAVE; + type = key->initiator ? SMP_LTK : SMP_LTK_RESPONDER; break; case MGMT_LTK_AUTHENTICATED: authenticated = 0x01; - type = key->master ? SMP_LTK : SMP_LTK_SLAVE; + type = key->initiator ? SMP_LTK : SMP_LTK_RESPONDER; break; case MGMT_LTK_P256_UNAUTH: authenticated = 0x00; @@ -6342,7 +6347,7 @@ static void conn_info_refresh_complete(struct hci_dev *hdev, u8 hci_status, handle = __le16_to_cpu(cp->handle); conn = hci_conn_hash_lookup_handle(hdev, handle); if (!conn) { - bt_dev_err(hdev, "unknown handle (%d) in conn_info response", + bt_dev_err(hdev, "unknown handle (%u) in conn_info response", handle); goto unlock; } @@ -6731,7 +6736,7 @@ static int add_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - err = hci_bdaddr_list_add_with_flags(&hdev->whitelist, + err = hci_bdaddr_list_add_with_flags(&hdev->accept_list, &cp->addr.bdaddr, cp->addr.type, 0); if (err) @@ -6829,7 +6834,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, } if (cp->addr.type == BDADDR_BREDR) { - err = hci_bdaddr_list_del(&hdev->whitelist, + err = hci_bdaddr_list_del(&hdev->accept_list, &cp->addr.bdaddr, cp->addr.type); if (err) { @@ -6900,7 +6905,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - list_for_each_entry_safe(b, btmp, &hdev->whitelist, list) { + list_for_each_entry_safe(b, btmp, &hdev->accept_list, list) { device_removed(sk, hdev, &b->bdaddr, b->bdaddr_type); list_del(&b->list); kfree(b); @@ -7585,6 +7590,9 @@ static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data, for (i = 0, cur_len = 0; i < len; i += (cur_len + 1)) { cur_len = data[i]; + if (!cur_len) + continue; + if (data[i + 1] == EIR_FLAGS && (!is_adv_data || flags_managed(adv_flags))) return false; @@ -7646,7 +7654,7 @@ static void add_advertising_complete(struct hci_dev *hdev, u8 status, struct adv_info *adv_instance, *n; u8 instance; - bt_dev_dbg(hdev, "status %d", status); + bt_dev_dbg(hdev, "status %u", status); hci_dev_lock(hdev); @@ -8176,7 +8184,7 @@ static void remove_advertising_complete(struct hci_dev *hdev, u8 status, struct mgmt_cp_remove_advertising *cp; struct mgmt_rp_remove_advertising rp; - bt_dev_dbg(hdev, "status %d", status); + bt_dev_dbg(hdev, "status %u", status); hci_dev_lock(hdev); @@ -8641,7 +8649,7 @@ static u8 mgmt_ltk_type(struct smp_ltk *ltk) { switch (ltk->type) { case SMP_LTK: - case SMP_LTK_SLAVE: + case SMP_LTK_RESPONDER: if (ltk->authenticated) return MGMT_LTK_AUTHENTICATED; return MGMT_LTK_UNAUTHENTICATED; @@ -8687,7 +8695,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) ev.key.rand = key->rand; if (key->type == SMP_LTK) - ev.key.master = 1; + ev.key.initiator = 1; /* Make sure we copy only the significant bytes based on the * encryption key size, and set the rest of the value to zeroes. @@ -8767,15 +8775,19 @@ void mgmt_new_conn_param(struct hci_dev *hdev, bdaddr_t *bdaddr, } void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, - u32 flags, u8 *name, u8 name_len) + u8 *name, u8 name_len) { char buf[512]; struct mgmt_ev_device_connected *ev = (void *) buf; u16 eir_len = 0; + u32 flags = 0; bacpy(&ev->addr.bdaddr, &conn->dst); ev->addr.type = link_to_bdaddr(conn->type, conn->dst_type); + if (conn->out) + flags |= MGMT_DEV_FOUND_INITIATED_CONN; + ev->flags = __cpu_to_le32(flags); /* We must ensure that the EIR Data fields are ordered and diff --git a/net/bluetooth/mgmt_config.c b/net/bluetooth/mgmt_config.c index 1deb0ca7a929..6ef701c27da4 100644 --- a/net/bluetooth/mgmt_config.c +++ b/net/bluetooth/mgmt_config.c @@ -146,7 +146,7 @@ int set_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data, const u16 type = le16_to_cpu(TO_TLV(buffer)->type); if (buffer_left < exp_len) { - bt_dev_warn(hdev, "invalid len left %d, exp >= %d", + bt_dev_warn(hdev, "invalid len left %u, exp >= %u", buffer_left, exp_len); return mgmt_cmd_status(sk, hdev->id, @@ -198,7 +198,7 @@ int set_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data, } if (exp_type_len && len != exp_type_len) { - bt_dev_warn(hdev, "invalid length %d, exp %zu for type %d", + bt_dev_warn(hdev, "invalid length %d, exp %zu for type %u", len, exp_type_len, type); return mgmt_cmd_status(sk, hdev->id, diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index e28f15439ce4..b4bfae41e8a5 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -34,12 +34,12 @@ struct msft_le_monitor_advertisement_pattern { __u8 length; __u8 data_type; __u8 start_byte; - __u8 pattern[0]; + __u8 pattern[]; }; struct msft_le_monitor_advertisement_pattern_data { __u8 count; - __u8 data[0]; + __u8 data[]; }; struct msft_cp_le_monitor_advertisement { @@ -49,7 +49,7 @@ struct msft_cp_le_monitor_advertisement { __u8 rssi_low_interval; __u8 rssi_sampling_period; __u8 cond_type; - __u8 data[0]; + __u8 data[]; } __packed; struct msft_rp_le_monitor_advertisement { @@ -311,7 +311,7 @@ static void msft_le_monitor_advertisement_cb(struct hci_dev *hdev, monitor = idr_find(&hdev->adv_monitors_idr, msft->pending_add_handle); if (!monitor) { - bt_dev_err(hdev, "msft add advmon: monitor %d is not found!", + bt_dev_err(hdev, "msft add advmon: monitor %u is not found!", msft->pending_add_handle); status = HCI_ERROR_UNSPECIFIED; goto unlock; diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index a58584949a95..8cb53e10a985 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -198,20 +198,22 @@ static void rfcomm_reparent_device(struct rfcomm_dev *dev) hci_dev_put(hdev); } -static ssize_t show_address(struct device *tty_dev, struct device_attribute *attr, char *buf) +static ssize_t address_show(struct device *tty_dev, + struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); return sprintf(buf, "%pMR\n", &dev->dst); } -static ssize_t show_channel(struct device *tty_dev, struct device_attribute *attr, char *buf) +static ssize_t channel_show(struct device *tty_dev, + struct device_attribute *attr, char *buf) { struct rfcomm_dev *dev = dev_get_drvdata(tty_dev); return sprintf(buf, "%d\n", dev->channel); } -static DEVICE_ATTR(address, 0444, show_address, NULL); -static DEVICE_ATTR(channel, 0444, show_channel, NULL); +static DEVICE_ATTR_RO(address); +static DEVICE_ATTR_RO(channel); static struct rfcomm_dev *__rfcomm_dev_add(struct rfcomm_dev_req *req, struct rfcomm_dlc *dlc) diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 3bd41563f118..d9a4e88dacbb 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -310,7 +310,7 @@ static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) if (!sk) goto drop; - BT_DBG("sk %p len %d", sk, skb->len); + BT_DBG("sk %p len %u", sk, skb->len); if (sk->sk_state != BT_CONNECTED) goto drop; @@ -905,7 +905,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, opts.mtu = sco_pi(sk)->conn->mtu; - BT_DBG("mtu %d", opts.mtu); + BT_DBG("mtu %u", opts.mtu); len = min_t(unsigned int, len, sizeof(opts)); if (copy_to_user(optval, (char *)&opts, len)) @@ -1167,7 +1167,7 @@ static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) return; - BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); + BT_DBG("hcon %p bdaddr %pMR status %u", hcon, &hcon->dst, status); if (!status) { struct sco_conn *conn; @@ -1196,7 +1196,7 @@ void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) if (!conn) goto drop; - BT_DBG("conn %p len %d", conn, skb->len); + BT_DBG("conn %p len %u", conn, skb->len); if (skb->len) { sco_recv_frame(conn, skb); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 7dd51da73845..11f853d0500f 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -40,7 +40,7 @@ ((struct smp_dev *)((struct l2cap_chan *)((hdev)->smp_data))->data) /* Low-level debug macros to be used for stuff that we don't want - * accidentially in dmesg, i.e. the values of the various crypto keys + * accidentally in dmesg, i.e. the values of the various crypto keys * and the inputs & outputs of crypto functions. */ #ifdef DEBUG @@ -111,9 +111,9 @@ struct smp_chan { u8 id_addr_type; u8 irk[16]; struct smp_csrk *csrk; - struct smp_csrk *slave_csrk; + struct smp_csrk *responder_csrk; struct smp_ltk *ltk; - struct smp_ltk *slave_ltk; + struct smp_ltk *responder_ltk; struct smp_irk *remote_irk; u8 *link_key; unsigned long flags; @@ -560,7 +560,7 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]) return err; /* This is unlikely, but we need to check that - * we didn't accidentially generate a debug key. + * we didn't accidentally generate a debug key. */ if (crypto_memneq(smp->local_pk, debug_pk, 64)) break; @@ -753,7 +753,7 @@ static void smp_chan_destroy(struct l2cap_conn *conn) mgmt_smp_complete(hcon, complete); kfree_sensitive(smp->csrk); - kfree_sensitive(smp->slave_csrk); + kfree_sensitive(smp->responder_csrk); kfree_sensitive(smp->link_key); crypto_free_shash(smp->tfm_cmac); @@ -776,9 +776,9 @@ static void smp_chan_destroy(struct l2cap_conn *conn) kfree_rcu(smp->ltk, rcu); } - if (smp->slave_ltk) { - list_del_rcu(&smp->slave_ltk->list); - kfree_rcu(smp->slave_ltk, rcu); + if (smp->responder_ltk) { + list_del_rcu(&smp->responder_ltk->list); + kfree_rcu(smp->responder_ltk, rcu); } if (smp->remote_irk) { @@ -859,7 +859,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, memset(smp->tk, 0, sizeof(smp->tk)); clear_bit(SMP_FLAG_TK_VALID, &smp->flags); - bt_dev_dbg(hcon->hdev, "auth:%d lcl:%d rem:%d", auth, local_io, + bt_dev_dbg(hcon->hdev, "auth:%u lcl:%u rem:%u", auth, local_io, remote_io); /* If neither side wants MITM, either "just" confirm an incoming @@ -909,8 +909,8 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, hcon->pending_sec_level = BT_SECURITY_HIGH; } - /* If both devices have Keyoard-Display I/O, the master - * Confirms and the slave Enters the passkey. + /* If both devices have Keyboard-Display I/O, the initiator + * Confirms and the responder Enters the passkey. */ if (smp->method == OVERLAP) { if (hcon->role == HCI_ROLE_MASTER) @@ -925,7 +925,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, get_random_bytes(&passkey, sizeof(passkey)); passkey %= 1000000; put_unaligned_le32(passkey, smp->tk); - bt_dev_dbg(hcon->hdev, "PassKey: %d", passkey); + bt_dev_dbg(hcon->hdev, "PassKey: %u", passkey); set_bit(SMP_FLAG_TK_VALID, &smp->flags); } @@ -979,7 +979,7 @@ static u8 smp_random(struct smp_chan *smp) int ret; bt_dev_dbg(conn->hcon->hdev, "conn %p %s", conn, - conn->hcon->out ? "master" : "slave"); + conn->hcon->out ? "initiator" : "responder"); ret = smp_c1(smp->tk, smp->rrnd, smp->preq, smp->prsp, hcon->init_addr_type, &hcon->init_addr, @@ -1021,8 +1021,8 @@ static u8 smp_random(struct smp_chan *smp) else auth = 0; - /* Even though there's no _SLAVE suffix this is the - * slave STK we're adding for later lookup (the master + /* Even though there's no _RESPONDER suffix this is the + * responder STK we're adding for later lookup (the initiator * STK never needs to be stored). */ hci_add_ltk(hcon->hdev, &hcon->dst, hcon->dst_type, @@ -1077,10 +1077,10 @@ static void smp_notify_keys(struct l2cap_conn *conn) mgmt_new_csrk(hdev, smp->csrk, persistent); } - if (smp->slave_csrk) { - smp->slave_csrk->bdaddr_type = hcon->dst_type; - bacpy(&smp->slave_csrk->bdaddr, &hcon->dst); - mgmt_new_csrk(hdev, smp->slave_csrk, persistent); + if (smp->responder_csrk) { + smp->responder_csrk->bdaddr_type = hcon->dst_type; + bacpy(&smp->responder_csrk->bdaddr, &hcon->dst); + mgmt_new_csrk(hdev, smp->responder_csrk, persistent); } if (smp->ltk) { @@ -1089,10 +1089,10 @@ static void smp_notify_keys(struct l2cap_conn *conn) mgmt_new_ltk(hdev, smp->ltk, persistent); } - if (smp->slave_ltk) { - smp->slave_ltk->bdaddr_type = hcon->dst_type; - bacpy(&smp->slave_ltk->bdaddr, &hcon->dst); - mgmt_new_ltk(hdev, smp->slave_ltk, persistent); + if (smp->responder_ltk) { + smp->responder_ltk->bdaddr_type = hcon->dst_type; + bacpy(&smp->responder_ltk->bdaddr, &hcon->dst); + mgmt_new_ltk(hdev, smp->responder_ltk, persistent); } if (smp->link_key) { @@ -1272,7 +1272,7 @@ static void smp_distribute_keys(struct smp_chan *smp) if (*keydist & SMP_DIST_ENC_KEY) { struct smp_cmd_encrypt_info enc; - struct smp_cmd_master_ident ident; + struct smp_cmd_initiator_ident ident; struct smp_ltk *ltk; u8 authenticated; __le16 ediv; @@ -1293,14 +1293,15 @@ static void smp_distribute_keys(struct smp_chan *smp) authenticated = hcon->sec_level == BT_SECURITY_HIGH; ltk = hci_add_ltk(hdev, &hcon->dst, hcon->dst_type, - SMP_LTK_SLAVE, authenticated, enc.ltk, + SMP_LTK_RESPONDER, authenticated, enc.ltk, smp->enc_key_size, ediv, rand); - smp->slave_ltk = ltk; + smp->responder_ltk = ltk; ident.ediv = ediv; ident.rand = rand; - smp_send_cmd(conn, SMP_CMD_MASTER_IDENT, sizeof(ident), &ident); + smp_send_cmd(conn, SMP_CMD_INITIATOR_IDENT, sizeof(ident), + &ident); *keydist &= ~SMP_DIST_ENC_KEY; } @@ -1343,7 +1344,7 @@ static void smp_distribute_keys(struct smp_chan *smp) csrk->type = MGMT_CSRK_LOCAL_UNAUTHENTICATED; memcpy(csrk->val, sign.csrk, sizeof(csrk->val)); } - smp->slave_csrk = csrk; + smp->responder_csrk = csrk; smp_send_cmd(conn, SMP_CMD_SIGN_INFO, sizeof(sign), &sign); @@ -1654,7 +1655,7 @@ int smp_user_confirm_reply(struct hci_conn *hcon, u16 mgmt_op, __le32 passkey) case MGMT_OP_USER_PASSKEY_REPLY: value = le32_to_cpu(passkey); memset(smp->tk, 0, sizeof(smp->tk)); - bt_dev_dbg(conn->hcon->hdev, "PassKey: %d", value); + bt_dev_dbg(conn->hcon->hdev, "PassKey: %u", value); put_unaligned_le32(value, smp->tk); fallthrough; case MGMT_OP_USER_CONFIRM_REPLY: @@ -1902,7 +1903,7 @@ static u8 sc_send_public_key(struct smp_chan *smp) return SMP_UNSPECIFIED; /* This is unlikely, but we need to check that - * we didn't accidentially generate a debug key. + * we didn't accidentally generate a debug key. */ if (crypto_memneq(smp->local_pk, debug_pk, 64)) break; @@ -2048,7 +2049,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp) struct smp_cmd_pairing *req, *rsp; u8 auth; - /* The issue is only observed when we're in slave role */ + /* The issue is only observed when we're in responder role */ if (hcon->out) return SMP_UNSPECIFIED; @@ -2084,7 +2085,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; - bt_dev_dbg(hdev, "conn %p %s", conn, hcon->out ? "master" : "slave"); + bt_dev_dbg(hdev, "conn %p %s", conn, + hcon->out ? "initiator" : "responder"); if (skb->len < sizeof(smp->pcnf)) return SMP_INVALID_PARAMS; @@ -2251,7 +2253,7 @@ static bool smp_ltk_encrypt(struct l2cap_conn *conn, u8 sec_level) hci_le_start_enc(hcon, key->ediv, key->rand, key->val, key->enc_size); hcon->enc_key_size = key->enc_size; - /* We never store STKs for master role, so clear this flag */ + /* We never store STKs for initiator role, so clear this flag */ clear_bit(HCI_CONN_STK_ENCRYPT, &hcon->flags); return true; @@ -2467,7 +2469,7 @@ int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr, /* Set keys to NULL to make sure smp_failure() does not try to * remove and free already invalidated rcu list entries. */ smp->ltk = NULL; - smp->slave_ltk = NULL; + smp->responder_ltk = NULL; smp->remote_irk = NULL; if (test_bit(SMP_FLAG_COMPLETE, &smp->flags)) @@ -2503,7 +2505,7 @@ static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) return SMP_INVALID_PARAMS; } - SMP_ALLOW_CMD(smp, SMP_CMD_MASTER_IDENT); + SMP_ALLOW_CMD(smp, SMP_CMD_INITIATOR_IDENT); skb_pull(skb, sizeof(*rp)); @@ -2512,9 +2514,9 @@ static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) return 0; } -static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb) +static int smp_cmd_initiator_ident(struct l2cap_conn *conn, struct sk_buff *skb) { - struct smp_cmd_master_ident *rp = (void *) skb->data; + struct smp_cmd_initiator_ident *rp = (void *)skb->data; struct l2cap_chan *chan = conn->smp; struct smp_chan *smp = chan->data; struct hci_dev *hdev = conn->hcon->hdev; @@ -2913,7 +2915,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) return 0; } - /* Slave sends DHKey check as response to master */ + /* Responder sends DHKey check as response to initiator */ sc_dhkey_check(smp); } @@ -3000,8 +3002,8 @@ static int smp_sig_channel(struct l2cap_chan *chan, struct sk_buff *skb) reason = smp_cmd_encrypt_info(conn, skb); break; - case SMP_CMD_MASTER_IDENT: - reason = smp_cmd_master_ident(conn, skb); + case SMP_CMD_INITIATOR_IDENT: + reason = smp_cmd_initiator_ident(conn, skb); break; case SMP_CMD_IDENT_INFO: @@ -3081,7 +3083,7 @@ static void bredr_pairing(struct l2cap_chan *chan) if (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags)) return; - /* Only master may initiate SMP over BR/EDR */ + /* Only initiator may initiate SMP over BR/EDR */ if (hcon->role != HCI_ROLE_MASTER) return; diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h index fc35a8bf358e..87a59ec2c9f0 100644 --- a/net/bluetooth/smp.h +++ b/net/bluetooth/smp.h @@ -79,8 +79,8 @@ struct smp_cmd_encrypt_info { __u8 ltk[16]; } __packed; -#define SMP_CMD_MASTER_IDENT 0x07 -struct smp_cmd_master_ident { +#define SMP_CMD_INITIATOR_IDENT 0x07 +struct smp_cmd_initiator_ident { __le16 ediv; __le64 rand; } __packed; @@ -146,7 +146,7 @@ struct smp_cmd_keypress_notify { enum { SMP_STK, SMP_LTK, - SMP_LTK_SLAVE, + SMP_LTK_RESPONDER, SMP_LTK_P256, SMP_LTK_P256_DEBUG, }; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index a5d72c48fb66..aa47af349ba8 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -409,7 +409,7 @@ static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size) return ERR_PTR(-ENOMEM); if (data_in) { - err = bpf_check_uarg_tail_zero(data_in, max_size, size); + err = bpf_check_uarg_tail_zero(USER_BPFPTR(data_in), max_size, size); if (err) { kfree(data); return ERR_PTR(err); @@ -918,3 +918,46 @@ out: kfree(user_ctx); return ret; } + +int bpf_prog_test_run_syscall(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in); + __u32 ctx_size_in = kattr->test.ctx_size_in; + void *ctx = NULL; + u32 retval; + int err = 0; + + /* doesn't support data_in/out, ctx_out, duration, or repeat or flags */ + if (kattr->test.data_in || kattr->test.data_out || + kattr->test.ctx_out || kattr->test.duration || + kattr->test.repeat || kattr->test.flags) + return -EINVAL; + + if (ctx_size_in < prog->aux->max_ctx_offset || + ctx_size_in > U16_MAX) + return -EINVAL; + + if (ctx_size_in) { + ctx = kzalloc(ctx_size_in, GFP_USER); + if (!ctx) + return -ENOMEM; + if (copy_from_user(ctx, ctx_in, ctx_size_in)) { + err = -EFAULT; + goto out; + } + } + retval = bpf_prog_run_pin_on_cpu(prog, ctx); + + if (copy_to_user(&uattr->test.retval, &retval, sizeof(u32))) { + err = -EFAULT; + goto out; + } + if (ctx_size_in) + if (copy_to_user(ctx_in, ctx, ctx_size_in)) + err = -EFAULT; +out: + kfree(ctx); + return err; +} diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c index 05e1cfc1e5cd..291a92546246 100644 --- a/net/bpfilter/main.c +++ b/net/bpfilter/main.c @@ -57,7 +57,7 @@ int main(void) { debug_f = fopen("/dev/kmsg", "w"); setvbuf(debug_f, 0, _IOLBF, 0); - fprintf(debug_f, "Started bpfilter\n"); + fprintf(debug_f, "<5>Started bpfilter\n"); loop(); fclose(debug_f); return 0; diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c index 001064f7583d..a3c755d0a09d 100644 --- a/net/bridge/br_cfm.c +++ b/net/bridge/br_cfm.c @@ -142,7 +142,7 @@ static void br_cfm_notify(int event, const struct net_bridge_port *port) { u32 filter = RTEXT_FILTER_CFM_STATUS; - return br_info_notify(event, port->br, NULL, filter); + br_info_notify(event, port->br, NULL, filter); } static void cc_peer_enable(struct br_cfm_peer_mep *peer_mep) diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 698b79747d32..2b862cffc03a 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -440,9 +440,14 @@ int br_fdb_test_addr(struct net_device *dev, unsigned char *addr) if (!port) ret = 0; else { + const struct net_bridge_port *dst = NULL; + fdb = br_fdb_find_rcu(port->br, addr, 0); - ret = fdb && fdb->dst && fdb->dst->dev != dev && - fdb->dst->state == BR_STATE_FORWARDING; + if (fdb) + dst = READ_ONCE(fdb->dst); + + ret = dst && dst->dev != dev && + dst->state == BR_STATE_FORWARDING; } rcu_read_unlock(); @@ -509,7 +514,7 @@ static struct net_bridge_fdb_entry *fdb_create(struct net_bridge *br, fdb = kmem_cache_alloc(br_fdb_cache, GFP_ATOMIC); if (fdb) { memcpy(fdb->key.addr.addr, addr, ETH_ALEN); - fdb->dst = source; + WRITE_ONCE(fdb->dst, source); fdb->key.vlan_id = vid; fdb->flags = flags; fdb->updated = fdb->used = jiffies; @@ -600,10 +605,10 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, } /* fastpath: update of existing entry */ - if (unlikely(source != fdb->dst && + if (unlikely(source != READ_ONCE(fdb->dst) && !test_bit(BR_FDB_STICKY, &fdb->flags))) { - br_switchdev_fdb_notify(fdb, RTM_DELNEIGH); - fdb->dst = source; + br_switchdev_fdb_notify(br, fdb, RTM_DELNEIGH); + WRITE_ONCE(fdb->dst, source); fdb_modified = true; /* Take over HW learned entry */ if (unlikely(test_bit(BR_FDB_ADDED_BY_EXT_LEARN, @@ -650,6 +655,7 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, const struct net_bridge_fdb_entry *fdb, u32 portid, u32 seq, int type, unsigned int flags) { + const struct net_bridge_port *dst = READ_ONCE(fdb->dst); unsigned long now = jiffies; struct nda_cacheinfo ci; struct nlmsghdr *nlh; @@ -665,7 +671,7 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ndm->ndm_pad2 = 0; ndm->ndm_flags = 0; ndm->ndm_type = 0; - ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex; + ndm->ndm_ifindex = dst ? dst->dev->ifindex : br->dev->ifindex; ndm->ndm_state = fdb_to_nud(br, fdb); if (test_bit(BR_FDB_OFFLOADED, &fdb->flags)) @@ -727,8 +733,9 @@ static inline size_t fdb_nlmsg_size(void) } static int br_fdb_replay_one(struct notifier_block *nb, - struct net_bridge_fdb_entry *fdb, - struct net_device *dev) + const struct net_bridge_fdb_entry *fdb, + struct net_device *dev, unsigned long action, + const void *ctx) { struct switchdev_notifier_fdb_info item; int err; @@ -737,35 +744,46 @@ static int br_fdb_replay_one(struct notifier_block *nb, item.vid = fdb->key.vlan_id; item.added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); item.offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags); + item.is_local = test_bit(BR_FDB_LOCAL, &fdb->flags); item.info.dev = dev; + item.info.ctx = ctx; - err = nb->notifier_call(nb, SWITCHDEV_FDB_ADD_TO_DEVICE, &item); + err = nb->notifier_call(nb, action, &item); return notifier_to_errno(err); } -int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb) +int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, + const void *ctx, bool adding, struct notifier_block *nb) { struct net_bridge_fdb_entry *fdb; struct net_bridge *br; + unsigned long action; int err = 0; - if (!netif_is_bridge_master(br_dev) || !netif_is_bridge_port(dev)) + if (!netif_is_bridge_master(br_dev)) + return -EINVAL; + + if (!netif_is_bridge_port(dev) && !netif_is_bridge_master(dev)) return -EINVAL; br = netdev_priv(br_dev); + if (adding) + action = SWITCHDEV_FDB_ADD_TO_DEVICE; + else + action = SWITCHDEV_FDB_DEL_TO_DEVICE; + rcu_read_lock(); hlist_for_each_entry_rcu(fdb, &br->fdb_list, fdb_node) { - struct net_bridge_port *dst = READ_ONCE(fdb->dst); + const struct net_bridge_port *dst = READ_ONCE(fdb->dst); struct net_device *dst_dev; dst_dev = dst ? dst->dev : br->dev; if (dst_dev != br_dev && dst_dev != dev) continue; - err = br_fdb_replay_one(nb, fdb, dst_dev); + err = br_fdb_replay_one(nb, fdb, dst_dev, action, ctx); if (err) break; } @@ -785,7 +803,7 @@ static void fdb_notify(struct net_bridge *br, int err = -ENOBUFS; if (swdev_notify) - br_switchdev_fdb_notify(fdb, type); + br_switchdev_fdb_notify(br, fdb, type); skb = nlmsg_new(fdb_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) @@ -955,8 +973,8 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, if (flags & NLM_F_EXCL) return -EEXIST; - if (fdb->dst != source) { - fdb->dst = source; + if (READ_ONCE(fdb->dst) != source) { + WRITE_ONCE(fdb->dst, source); modified = true; } } @@ -1123,7 +1141,7 @@ static int fdb_delete_by_addr_and_port(struct net_bridge *br, struct net_bridge_fdb_entry *fdb; fdb = br_fdb_find(br, addr, vlan); - if (!fdb || fdb->dst != p) + if (!fdb || READ_ONCE(fdb->dst) != p) return -ENOENT; fdb_delete(br, fdb, true); @@ -1272,8 +1290,8 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, } else { fdb->updated = jiffies; - if (fdb->dst != p) { - fdb->dst = p; + if (READ_ONCE(fdb->dst) != p) { + WRITE_ONCE(fdb->dst, p); modified = true; } diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 6e9b049ae521..07856362538f 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -276,7 +276,8 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, bool allow_mode_include = true; struct hlist_node *rp; - rp = rcu_dereference(hlist_first_rcu(&br->router_list)); + rp = br_multicast_get_first_rport_node(br, skb); + if (mdst) { p = rcu_dereference(mdst->ports); if (br_multicast_should_handle_mode(br, mdst->addr.proto) && @@ -290,7 +291,7 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, struct net_bridge_port *port, *lport, *rport; lport = p ? p->key.port : NULL; - rport = hlist_entry_safe(rp, struct net_bridge_port, rlist); + rport = br_multicast_rport_from_node_skb(rp, skb); if ((unsigned long)lport > (unsigned long)rport) { port = lport; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 8875e953ac53..1f506309efa8 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -132,7 +132,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && br_multicast_querier_exists(br, eth_hdr(skb), mdst)) { if ((mdst && mdst->host_joined) || - br_multicast_is_router(br)) { + br_multicast_is_router(br, skb)) { local_rcv = true; br->dev->stats.multicast++; } diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 95fa4af0e8dd..17a720b4473f 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -16,31 +16,76 @@ #include "br_private.h" +static bool br_rports_have_mc_router(struct net_bridge *br) +{ +#if IS_ENABLED(CONFIG_IPV6) + return !hlist_empty(&br->ip4_mc_router_list) || + !hlist_empty(&br->ip6_mc_router_list); +#else + return !hlist_empty(&br->ip4_mc_router_list); +#endif +} + +static bool +br_ip4_rports_get_timer(struct net_bridge_port *port, unsigned long *timer) +{ + *timer = br_timer_value(&port->ip4_mc_router_timer); + return !hlist_unhashed(&port->ip4_rlist); +} + +static bool +br_ip6_rports_get_timer(struct net_bridge_port *port, unsigned long *timer) +{ +#if IS_ENABLED(CONFIG_IPV6) + *timer = br_timer_value(&port->ip6_mc_router_timer); + return !hlist_unhashed(&port->ip6_rlist); +#else + *timer = 0; + return false; +#endif +} + static int br_rports_fill_info(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - struct net_bridge_port *p; + bool have_ip4_mc_rtr, have_ip6_mc_rtr; + unsigned long ip4_timer, ip6_timer; struct nlattr *nest, *port_nest; + struct net_bridge_port *p; - if (!br->multicast_router || hlist_empty(&br->router_list)) + if (!br->multicast_router) + return 0; + + if (!br_rports_have_mc_router(br)) return 0; nest = nla_nest_start_noflag(skb, MDBA_ROUTER); if (nest == NULL) return -EMSGSIZE; - hlist_for_each_entry_rcu(p, &br->router_list, rlist) { - if (!p) + list_for_each_entry_rcu(p, &br->port_list, list) { + have_ip4_mc_rtr = br_ip4_rports_get_timer(p, &ip4_timer); + have_ip6_mc_rtr = br_ip6_rports_get_timer(p, &ip6_timer); + + if (!have_ip4_mc_rtr && !have_ip6_mc_rtr) continue; + port_nest = nla_nest_start_noflag(skb, MDBA_ROUTER_PORT); if (!port_nest) goto fail; + if (nla_put_nohdr(skb, sizeof(u32), &p->dev->ifindex) || nla_put_u32(skb, MDBA_ROUTER_PATTR_TIMER, - br_timer_value(&p->multicast_router_timer)) || + max(ip4_timer, ip6_timer)) || nla_put_u8(skb, MDBA_ROUTER_PATTR_TYPE, - p->multicast_router)) { + p->multicast_router) || + (have_ip4_mc_rtr && + nla_put_u32(skb, MDBA_ROUTER_PATTR_INET_TIMER, + ip4_timer)) || + (have_ip6_mc_rtr && + nla_put_u32(skb, MDBA_ROUTER_PATTR_INET6_TIMER, + ip6_timer))) { nla_nest_cancel(skb, port_nest); goto fail; } @@ -522,19 +567,21 @@ static void br_switchdev_mdb_populate(struct switchdev_obj_port_mdb *mdb, } static int br_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, - struct switchdev_obj_port_mdb *mdb, + const struct switchdev_obj_port_mdb *mdb, + unsigned long action, const void *ctx, struct netlink_ext_ack *extack) { struct switchdev_notifier_port_obj_info obj_info = { .info = { .dev = dev, .extack = extack, + .ctx = ctx, }, .obj = &mdb->obj, }; int err; - err = nb->notifier_call(nb, SWITCHDEV_PORT_OBJ_ADD, &obj_info); + err = nb->notifier_call(nb, action, &obj_info); return notifier_to_errno(err); } @@ -558,11 +605,13 @@ static int br_mdb_queue_one(struct list_head *mdb_list, } int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack) + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - struct net_bridge_mdb_entry *mp; + const struct net_bridge_mdb_entry *mp; struct switchdev_obj *obj, *tmp; struct net_bridge *br; + unsigned long action; LIST_HEAD(mdb_list); int err = 0; @@ -587,8 +636,8 @@ int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, rcu_read_lock(); hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { - struct net_bridge_port_group __rcu **pp; - struct net_bridge_port_group *p; + struct net_bridge_port_group __rcu * const *pp; + const struct net_bridge_port_group *p; if (mp->host_joined) { err = br_mdb_queue_one(&mdb_list, @@ -617,9 +666,14 @@ int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, rcu_read_unlock(); + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + list_for_each_entry(obj, &mdb_list, list) { err = br_mdb_replay_one(nb, dev, SWITCHDEV_OBJ_PORT_MDB(obj), - extack); + action, ctx, extack); if (err) goto out_free_mdb; } diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index cd2b1e424e54..fd2de35ffb3c 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -204,6 +204,33 @@ static struct sk_buff *br_mrp_alloc_test_skb(struct br_mrp *mrp, hdr->timestamp = cpu_to_be32(jiffies_to_msecs(jiffies)); br_mrp_skb_common(skb, mrp); + + /* In case the node behaves as MRA then the Test frame needs to have + * an Option TLV which includes eventually a sub-option TLV that has + * the type AUTO_MGR + */ + if (mrp->ring_role == BR_MRP_RING_ROLE_MRA) { + struct br_mrp_sub_option1_hdr *sub_opt = NULL; + struct br_mrp_tlv_hdr *sub_tlv = NULL; + struct br_mrp_oui_hdr *oui = NULL; + u8 length; + + length = sizeof(*sub_opt) + sizeof(*sub_tlv) + sizeof(oui) + + MRP_OPT_PADDING; + br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_OPTION, length); + + oui = skb_put(skb, sizeof(*oui)); + memset(oui, 0x0, sizeof(*oui)); + sub_opt = skb_put(skb, sizeof(*sub_opt)); + memset(sub_opt, 0x0, sizeof(*sub_opt)); + + sub_tlv = skb_put(skb, sizeof(*sub_tlv)); + sub_tlv->type = BR_MRP_SUB_TLV_HEADER_TEST_AUTO_MGR; + + /* 32 bit alligment shall be ensured therefore add 2 bytes */ + skb_put(skb, MRP_OPT_PADDING); + } + br_mrp_skb_tlv(skb, BR_MRP_TLV_HEADER_END, 0x0); return skb; @@ -627,8 +654,7 @@ int br_mrp_set_ring_state(struct net_bridge *br, if (!mrp) return -EINVAL; - if (mrp->ring_state == BR_MRP_RING_STATE_CLOSED && - state->ring_state != BR_MRP_RING_STATE_CLOSED) + if (mrp->ring_state != state->ring_state) mrp->ring_transitions++; mrp->ring_state = state->ring_state; @@ -715,8 +741,7 @@ int br_mrp_set_in_state(struct net_bridge *br, struct br_mrp_in_state *state) if (!mrp) return -EINVAL; - if (mrp->in_state == BR_MRP_IN_STATE_CLOSED && - state->in_state != BR_MRP_IN_STATE_CLOSED) + if (mrp->in_state != state->in_state) mrp->in_transitions++; mrp->in_state = state->in_state; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 226bb05c3b42..53c3a9d80d9c 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -51,8 +51,8 @@ static const struct rhashtable_params br_sg_port_rht_params = { static void br_multicast_start_querier(struct net_bridge *br, struct bridge_mcast_own_query *query); -static void br_multicast_add_router(struct net_bridge *br, - struct net_bridge_port *port); +static void br_ip4_multicast_add_router(struct net_bridge *br, + struct net_bridge_port *port); static void br_ip4_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, @@ -60,7 +60,10 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br, const unsigned char *src); static void br_multicast_port_group_rexmit(struct timer_list *t); -static void __del_port_router(struct net_bridge_port *p); +static void +br_multicast_rport_del_notify(struct net_bridge_port *p, bool deleted); +static void br_ip6_multicast_add_router(struct net_bridge *br, + struct net_bridge_port *port); #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, @@ -1354,23 +1357,64 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, } #endif -static void br_multicast_router_expired(struct timer_list *t) +static bool br_multicast_rport_del(struct hlist_node *rlist) +{ + if (hlist_unhashed(rlist)) + return false; + + hlist_del_init_rcu(rlist); + return true; +} + +static bool br_ip4_multicast_rport_del(struct net_bridge_port *p) +{ + return br_multicast_rport_del(&p->ip4_rlist); +} + +static bool br_ip6_multicast_rport_del(struct net_bridge_port *p) +{ +#if IS_ENABLED(CONFIG_IPV6) + return br_multicast_rport_del(&p->ip6_rlist); +#else + return false; +#endif +} + +static void br_multicast_router_expired(struct net_bridge_port *port, + struct timer_list *t, + struct hlist_node *rlist) { - struct net_bridge_port *port = - from_timer(port, t, multicast_router_timer); struct net_bridge *br = port->br; + bool del; spin_lock(&br->multicast_lock); if (port->multicast_router == MDB_RTR_TYPE_DISABLED || port->multicast_router == MDB_RTR_TYPE_PERM || - timer_pending(&port->multicast_router_timer)) + timer_pending(t)) goto out; - __del_port_router(port); + del = br_multicast_rport_del(rlist); + br_multicast_rport_del_notify(port, del); out: spin_unlock(&br->multicast_lock); } +static void br_ip4_multicast_router_expired(struct timer_list *t) +{ + struct net_bridge_port *port = from_timer(port, t, ip4_mc_router_timer); + + br_multicast_router_expired(port, t, &port->ip4_rlist); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_router_expired(struct timer_list *t) +{ + struct net_bridge_port *port = from_timer(port, t, ip6_mc_router_timer); + + br_multicast_router_expired(port, t, &port->ip6_rlist); +} +#endif + static void br_mc_router_state_change(struct net_bridge *p, bool is_mc_router) { @@ -1384,14 +1428,14 @@ static void br_mc_router_state_change(struct net_bridge *p, switchdev_port_attr_set(p->dev, &attr, NULL); } -static void br_multicast_local_router_expired(struct timer_list *t) +static void br_multicast_local_router_expired(struct net_bridge *br, + struct timer_list *timer) { - struct net_bridge *br = from_timer(br, t, multicast_router_timer); - spin_lock(&br->multicast_lock); if (br->multicast_router == MDB_RTR_TYPE_DISABLED || br->multicast_router == MDB_RTR_TYPE_PERM || - timer_pending(&br->multicast_router_timer)) + br_ip4_multicast_is_router(br) || + br_ip6_multicast_is_router(br)) goto out; br_mc_router_state_change(br, false); @@ -1399,6 +1443,22 @@ out: spin_unlock(&br->multicast_lock); } +static void br_ip4_multicast_local_router_expired(struct timer_list *t) +{ + struct net_bridge *br = from_timer(br, t, ip4_mc_router_timer); + + br_multicast_local_router_expired(br, t); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_local_router_expired(struct timer_list *t) +{ + struct net_bridge *br = from_timer(br, t, ip6_mc_router_timer); + + br_multicast_local_router_expired(br, t); +} +#endif + static void br_multicast_querier_expired(struct net_bridge *br, struct bridge_mcast_own_query *query) { @@ -1613,11 +1673,13 @@ int br_multicast_add_port(struct net_bridge_port *port) port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; port->multicast_eht_hosts_limit = BR_MCAST_DEFAULT_EHT_HOSTS_LIMIT; - timer_setup(&port->multicast_router_timer, - br_multicast_router_expired, 0); + timer_setup(&port->ip4_mc_router_timer, + br_ip4_multicast_router_expired, 0); timer_setup(&port->ip4_own_query.timer, br_ip4_multicast_port_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) + timer_setup(&port->ip6_mc_router_timer, + br_ip6_multicast_router_expired, 0); timer_setup(&port->ip6_own_query.timer, br_ip6_multicast_port_query_expired, 0); #endif @@ -1649,7 +1711,10 @@ void br_multicast_del_port(struct net_bridge_port *port) hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); br_multicast_gc(&deleted_head); - del_timer_sync(&port->multicast_router_timer); + del_timer_sync(&port->ip4_mc_router_timer); +#if IS_ENABLED(CONFIG_IPV6) + del_timer_sync(&port->ip6_mc_router_timer); +#endif free_percpu(port->mcast_stats); } @@ -1673,9 +1738,10 @@ static void __br_multicast_enable_port(struct net_bridge_port *port) #if IS_ENABLED(CONFIG_IPV6) br_multicast_enable(&port->ip6_own_query); #endif - if (port->multicast_router == MDB_RTR_TYPE_PERM && - hlist_unhashed(&port->rlist)) - br_multicast_add_router(br, port); + if (port->multicast_router == MDB_RTR_TYPE_PERM) { + br_ip4_multicast_add_router(br, port); + br_ip6_multicast_add_router(br, port); + } } void br_multicast_enable_port(struct net_bridge_port *port) @@ -1692,19 +1758,22 @@ void br_multicast_disable_port(struct net_bridge_port *port) struct net_bridge *br = port->br; struct net_bridge_port_group *pg; struct hlist_node *n; + bool del = false; spin_lock(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) if (!(pg->flags & MDB_PG_FLAGS_PERMANENT)) br_multicast_find_del_pg(br, pg); - __del_port_router(port); - - del_timer(&port->multicast_router_timer); + del |= br_ip4_multicast_rport_del(port); + del_timer(&port->ip4_mc_router_timer); del_timer(&port->ip4_own_query.timer); + del |= br_ip6_multicast_rport_del(port); #if IS_ENABLED(CONFIG_IPV6) + del_timer(&port->ip6_mc_router_timer); del_timer(&port->ip6_own_query.timer); #endif + br_multicast_rport_del_notify(port, del); spin_unlock(&br->multicast_lock); } @@ -2615,22 +2684,6 @@ update: } #endif -static bool br_multicast_select_querier(struct net_bridge *br, - struct net_bridge_port *port, - struct br_ip *saddr) -{ - switch (saddr->proto) { - case htons(ETH_P_IP): - return br_ip4_multicast_select_querier(br, port, saddr->src.ip4); -#if IS_ENABLED(CONFIG_IPV6) - case htons(ETH_P_IPV6): - return br_ip6_multicast_select_querier(br, port, &saddr->src.ip6); -#endif - } - - return false; -} - static void br_multicast_update_query_timer(struct net_bridge *br, struct bridge_mcast_other_query *query, @@ -2655,45 +2708,122 @@ static void br_port_mc_router_state_change(struct net_bridge_port *p, switchdev_port_attr_set(p->dev, &attr, NULL); } -/* - * Add port to router_list +static struct net_bridge_port * +br_multicast_rport_from_node(struct net_bridge *br, + struct hlist_head *mc_router_list, + struct hlist_node *rlist) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (mc_router_list == &br->ip6_mc_router_list) + return hlist_entry(rlist, struct net_bridge_port, ip6_rlist); +#endif + return hlist_entry(rlist, struct net_bridge_port, ip4_rlist); +} + +static struct hlist_node * +br_multicast_get_rport_slot(struct net_bridge *br, + struct net_bridge_port *port, + struct hlist_head *mc_router_list) + +{ + struct hlist_node *slot = NULL; + struct net_bridge_port *p; + struct hlist_node *rlist; + + hlist_for_each(rlist, mc_router_list) { + p = br_multicast_rport_from_node(br, mc_router_list, rlist); + + if ((unsigned long)port >= (unsigned long)p) + break; + + slot = rlist; + } + + return slot; +} + +static bool br_multicast_no_router_otherpf(struct net_bridge_port *port, + struct hlist_node *rnode) +{ +#if IS_ENABLED(CONFIG_IPV6) + if (rnode != &port->ip6_rlist) + return hlist_unhashed(&port->ip6_rlist); + else + return hlist_unhashed(&port->ip4_rlist); +#else + return true; +#endif +} + +/* Add port to router_list * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ static void br_multicast_add_router(struct net_bridge *br, - struct net_bridge_port *port) + struct net_bridge_port *port, + struct hlist_node *rlist, + struct hlist_head *mc_router_list) { - struct net_bridge_port *p; - struct hlist_node *slot = NULL; + struct hlist_node *slot; - if (!hlist_unhashed(&port->rlist)) + if (!hlist_unhashed(rlist)) return; - hlist_for_each_entry(p, &br->router_list, rlist) { - if ((unsigned long) port >= (unsigned long) p) - break; - slot = &p->rlist; - } + slot = br_multicast_get_rport_slot(br, port, mc_router_list); if (slot) - hlist_add_behind_rcu(&port->rlist, slot); + hlist_add_behind_rcu(rlist, slot); else - hlist_add_head_rcu(&port->rlist, &br->router_list); - br_rtr_notify(br->dev, port, RTM_NEWMDB); - br_port_mc_router_state_change(port, true); + hlist_add_head_rcu(rlist, mc_router_list); + + /* For backwards compatibility for now, only notify if we + * switched from no IPv4/IPv6 multicast router to a new + * IPv4 or IPv6 multicast router. + */ + if (br_multicast_no_router_otherpf(port, rlist)) { + br_rtr_notify(br->dev, port, RTM_NEWMDB); + br_port_mc_router_state_change(port, true); + } +} + +/* Add port to router_list + * list is maintained ordered by pointer value + * and locked by br->multicast_lock and RCU + */ +static void br_ip4_multicast_add_router(struct net_bridge *br, + struct net_bridge_port *port) +{ + br_multicast_add_router(br, port, &port->ip4_rlist, + &br->ip4_mc_router_list); +} + +/* Add port to router_list + * list is maintained ordered by pointer value + * and locked by br->multicast_lock and RCU + */ +static void br_ip6_multicast_add_router(struct net_bridge *br, + struct net_bridge_port *port) +{ +#if IS_ENABLED(CONFIG_IPV6) + br_multicast_add_router(br, port, &port->ip6_rlist, + &br->ip6_mc_router_list); +#endif } static void br_multicast_mark_router(struct net_bridge *br, - struct net_bridge_port *port) + struct net_bridge_port *port, + struct timer_list *timer, + struct hlist_node *rlist, + struct hlist_head *mc_router_list) { unsigned long now = jiffies; if (!port) { if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) { - if (!timer_pending(&br->multicast_router_timer)) + if (!br_ip4_multicast_is_router(br) && + !br_ip6_multicast_is_router(br)) br_mc_router_state_change(br, true); - mod_timer(&br->multicast_router_timer, - now + br->multicast_querier_interval); + mod_timer(timer, now + br->multicast_querier_interval); } return; } @@ -2702,25 +2832,72 @@ static void br_multicast_mark_router(struct net_bridge *br, port->multicast_router == MDB_RTR_TYPE_PERM) return; - br_multicast_add_router(br, port); - - mod_timer(&port->multicast_router_timer, - now + br->multicast_querier_interval); + br_multicast_add_router(br, port, rlist, mc_router_list); + mod_timer(timer, now + br->multicast_querier_interval); } -static void br_multicast_query_received(struct net_bridge *br, - struct net_bridge_port *port, - struct bridge_mcast_other_query *query, - struct br_ip *saddr, - unsigned long max_delay) +static void br_ip4_multicast_mark_router(struct net_bridge *br, + struct net_bridge_port *port) { - if (!br_multicast_select_querier(br, port, saddr)) + struct timer_list *timer = &br->ip4_mc_router_timer; + struct hlist_node *rlist = NULL; + + if (port) { + timer = &port->ip4_mc_router_timer; + rlist = &port->ip4_rlist; + } + + br_multicast_mark_router(br, port, timer, rlist, + &br->ip4_mc_router_list); +} + +static void br_ip6_multicast_mark_router(struct net_bridge *br, + struct net_bridge_port *port) +{ +#if IS_ENABLED(CONFIG_IPV6) + struct timer_list *timer = &br->ip6_mc_router_timer; + struct hlist_node *rlist = NULL; + + if (port) { + timer = &port->ip6_mc_router_timer; + rlist = &port->ip6_rlist; + } + + br_multicast_mark_router(br, port, timer, rlist, + &br->ip6_mc_router_list); +#endif +} + +static void +br_ip4_multicast_query_received(struct net_bridge *br, + struct net_bridge_port *port, + struct bridge_mcast_other_query *query, + struct br_ip *saddr, + unsigned long max_delay) +{ + if (!br_ip4_multicast_select_querier(br, port, saddr->src.ip4)) return; br_multicast_update_query_timer(br, query, max_delay); - br_multicast_mark_router(br, port); + br_ip4_multicast_mark_router(br, port); } +#if IS_ENABLED(CONFIG_IPV6) +static void +br_ip6_multicast_query_received(struct net_bridge *br, + struct net_bridge_port *port, + struct bridge_mcast_other_query *query, + struct br_ip *saddr, + unsigned long max_delay) +{ + if (!br_ip6_multicast_select_querier(br, port, &saddr->src.ip6)) + return; + + br_multicast_update_query_timer(br, query, max_delay); + br_ip6_multicast_mark_router(br, port); +} +#endif + static void br_ip4_multicast_query(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, @@ -2768,8 +2945,8 @@ static void br_ip4_multicast_query(struct net_bridge *br, saddr.proto = htons(ETH_P_IP); saddr.src.ip4 = iph->saddr; - br_multicast_query_received(br, port, &br->ip4_other_query, - &saddr, max_delay); + br_ip4_multicast_query_received(br, port, &br->ip4_other_query, + &saddr, max_delay); goto out; } @@ -2856,8 +3033,8 @@ static int br_ip6_multicast_query(struct net_bridge *br, saddr.proto = htons(ETH_P_IPV6); saddr.src.ip6 = ipv6_hdr(skb)->saddr; - br_multicast_query_received(br, port, &br->ip6_other_query, - &saddr, max_delay); + br_ip6_multicast_query_received(br, port, &br->ip6_other_query, + &saddr, max_delay); goto out; } else if (!group) { goto out; @@ -3087,7 +3264,7 @@ static void br_multicast_pim(struct net_bridge *br, pim_hdr_type(pimhdr) != PIM_TYPE_HELLO) return; - br_multicast_mark_router(br, port); + br_ip4_multicast_mark_router(br, port); } static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, @@ -3098,7 +3275,7 @@ static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, igmp_hdr(skb)->type != IGMP_MRDISC_ADV) return -ENOMSG; - br_multicast_mark_router(br, port); + br_ip4_multicast_mark_router(br, port); return 0; } @@ -3166,7 +3343,7 @@ static void br_ip6_multicast_mrd_rcv(struct net_bridge *br, if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV) return; - br_multicast_mark_router(br, port); + br_ip6_multicast_mark_router(br, port); } static int br_multicast_ipv6_rcv(struct net_bridge *br, @@ -3316,13 +3493,15 @@ void br_multicast_init(struct net_bridge *br) br_opt_toggle(br, BROPT_HAS_IPV6_ADDR, true); spin_lock_init(&br->multicast_lock); - timer_setup(&br->multicast_router_timer, - br_multicast_local_router_expired, 0); + timer_setup(&br->ip4_mc_router_timer, + br_ip4_multicast_local_router_expired, 0); timer_setup(&br->ip4_other_query.timer, br_ip4_multicast_querier_expired, 0); timer_setup(&br->ip4_own_query.timer, br_ip4_multicast_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) + timer_setup(&br->ip6_mc_router_timer, + br_ip6_multicast_local_router_expired, 0); timer_setup(&br->ip6_other_query.timer, br_ip6_multicast_querier_expired, 0); timer_setup(&br->ip6_own_query.timer, @@ -3416,10 +3595,11 @@ void br_multicast_open(struct net_bridge *br) void br_multicast_stop(struct net_bridge *br) { - del_timer_sync(&br->multicast_router_timer); + del_timer_sync(&br->ip4_mc_router_timer); del_timer_sync(&br->ip4_other_query.timer); del_timer_sync(&br->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) + del_timer_sync(&br->ip6_mc_router_timer); del_timer_sync(&br->ip6_other_query.timer); del_timer_sync(&br->ip6_own_query.timer); #endif @@ -3453,7 +3633,10 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val) case MDB_RTR_TYPE_DISABLED: case MDB_RTR_TYPE_PERM: br_mc_router_state_change(br, val == MDB_RTR_TYPE_PERM); - del_timer(&br->multicast_router_timer); + del_timer(&br->ip4_mc_router_timer); +#if IS_ENABLED(CONFIG_IPV6) + del_timer(&br->ip6_mc_router_timer); +#endif br->multicast_router = val; err = 0; break; @@ -3470,11 +3653,22 @@ int br_multicast_set_router(struct net_bridge *br, unsigned long val) return err; } -static void __del_port_router(struct net_bridge_port *p) +static void +br_multicast_rport_del_notify(struct net_bridge_port *p, bool deleted) { - if (hlist_unhashed(&p->rlist)) + if (!deleted) return; - hlist_del_init_rcu(&p->rlist); + + /* For backwards compatibility for now, only notify if there is + * no multicast router anymore for both IPv4 and IPv6. + */ + if (!hlist_unhashed(&p->ip4_rlist)) + return; +#if IS_ENABLED(CONFIG_IPV6) + if (!hlist_unhashed(&p->ip6_rlist)) + return; +#endif + br_rtr_notify(p->br->dev, p, RTM_DELMDB); br_port_mc_router_state_change(p, false); @@ -3488,34 +3682,52 @@ int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) struct net_bridge *br = p->br; unsigned long now = jiffies; int err = -EINVAL; + bool del = false; spin_lock(&br->multicast_lock); if (p->multicast_router == val) { /* Refresh the temp router port timer */ - if (p->multicast_router == MDB_RTR_TYPE_TEMP) - mod_timer(&p->multicast_router_timer, + if (p->multicast_router == MDB_RTR_TYPE_TEMP) { + mod_timer(&p->ip4_mc_router_timer, now + br->multicast_querier_interval); +#if IS_ENABLED(CONFIG_IPV6) + mod_timer(&p->ip6_mc_router_timer, + now + br->multicast_querier_interval); +#endif + } err = 0; goto unlock; } switch (val) { case MDB_RTR_TYPE_DISABLED: p->multicast_router = MDB_RTR_TYPE_DISABLED; - __del_port_router(p); - del_timer(&p->multicast_router_timer); + del |= br_ip4_multicast_rport_del(p); + del_timer(&p->ip4_mc_router_timer); + del |= br_ip6_multicast_rport_del(p); +#if IS_ENABLED(CONFIG_IPV6) + del_timer(&p->ip6_mc_router_timer); +#endif + br_multicast_rport_del_notify(p, del); break; case MDB_RTR_TYPE_TEMP_QUERY: p->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; - __del_port_router(p); + del |= br_ip4_multicast_rport_del(p); + del |= br_ip6_multicast_rport_del(p); + br_multicast_rport_del_notify(p, del); break; case MDB_RTR_TYPE_PERM: p->multicast_router = MDB_RTR_TYPE_PERM; - del_timer(&p->multicast_router_timer); - br_multicast_add_router(br, p); + del_timer(&p->ip4_mc_router_timer); + br_ip4_multicast_add_router(br, p); +#if IS_ENABLED(CONFIG_IPV6) + del_timer(&p->ip6_mc_router_timer); +#endif + br_ip6_multicast_add_router(br, p); break; case MDB_RTR_TYPE_TEMP: p->multicast_router = MDB_RTR_TYPE_TEMP; - br_multicast_mark_router(br, p); + br_ip4_multicast_mark_router(br, p); + br_ip6_multicast_mark_router(br, p); break; default: goto unlock; @@ -3621,7 +3833,7 @@ bool br_multicast_router(const struct net_device *dev) bool is_router; spin_lock_bh(&br->multicast_lock); - is_router = br_multicast_is_router(br); + is_router = br_multicast_is_router(br, NULL); spin_unlock_bh(&br->multicast_lock); return is_router; } @@ -3842,6 +4054,61 @@ unlock: } EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent); +/** + * br_multicast_has_router_adjacent - Checks for a router behind a bridge port + * @dev: The bridge port adjacent to which to check for a multicast router + * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 + * + * Checks whether the given interface has a bridge on top and if so returns + * true if a multicast router is behind one of the other ports of this + * bridge. Otherwise returns false. + */ +bool br_multicast_has_router_adjacent(struct net_device *dev, int proto) +{ + struct net_bridge_port *port, *p; + bool ret = false; + + rcu_read_lock(); + port = br_port_get_check_rcu(dev); + if (!port) + goto unlock; + + switch (proto) { + case ETH_P_IP: + hlist_for_each_entry_rcu(p, &port->br->ip4_mc_router_list, + ip4_rlist) { + if (p == port) + continue; + + ret = true; + goto unlock; + } + break; +#if IS_ENABLED(CONFIG_IPV6) + case ETH_P_IPV6: + hlist_for_each_entry_rcu(p, &port->br->ip6_mc_router_list, + ip6_rlist) { + if (p == port) + continue; + + ret = true; + goto unlock; + } + break; +#endif + default: + /* when compiled without IPv6 support, be conservative and + * always assume presence of an IPv6 multicast router + */ + ret = true; + } + +unlock: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(br_multicast_has_router_adjacent); + static void br_mcast_stats_add(struct bridge_mcast_stats __percpu *stats, const struct sk_buff *skb, u8 type, u8 dir) { diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e4e6e991313e..8642e56059fb 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1644,7 +1644,6 @@ static size_t br_get_linkxstats_size(const struct net_device *dev, int attr) p = br_port_get_rtnl(dev); if (!p) return 0; - br = p->br; vg = nbp_vlan_group(p); break; default: diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index e013d33f1c7c..2b48b204205e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -307,16 +307,18 @@ struct net_bridge_port { #ifdef CONFIG_BRIDGE_IGMP_SNOOPING struct bridge_mcast_own_query ip4_own_query; + struct timer_list ip4_mc_router_timer; + struct hlist_node ip4_rlist; #if IS_ENABLED(CONFIG_IPV6) struct bridge_mcast_own_query ip6_own_query; + struct timer_list ip6_mc_router_timer; + struct hlist_node ip6_rlist; #endif /* IS_ENABLED(CONFIG_IPV6) */ u32 multicast_eht_hosts_limit; u32 multicast_eht_hosts_cnt; unsigned char multicast_router; struct bridge_mcast_stats __percpu *mcast_stats; - struct timer_list multicast_router_timer; struct hlist_head mglist; - struct hlist_node rlist; #endif #ifdef CONFIG_SYSFS @@ -449,14 +451,16 @@ struct net_bridge { struct hlist_head mcast_gc_list; struct hlist_head mdb_list; - struct hlist_head router_list; - struct timer_list multicast_router_timer; + struct hlist_head ip4_mc_router_list; + struct timer_list ip4_mc_router_timer; struct bridge_mcast_other_query ip4_other_query; struct bridge_mcast_own_query ip4_own_query; struct bridge_mcast_querier ip4_querier; struct bridge_mcast_stats __percpu *mcast_stats; #if IS_ENABLED(CONFIG_IPV6) + struct hlist_head ip6_mc_router_list; + struct timer_list ip6_mc_router_timer; struct bridge_mcast_other_query ip6_other_query; struct bridge_mcast_own_query ip6_own_query; struct bridge_mcast_querier ip6_querier; @@ -864,11 +868,58 @@ static inline bool br_group_is_l2(const struct br_ip *group) #define mlock_dereference(X, br) \ rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) -static inline bool br_multicast_is_router(struct net_bridge *br) +static inline struct hlist_node * +br_multicast_get_first_rport_node(struct net_bridge *b, struct sk_buff *skb) { +#if IS_ENABLED(CONFIG_IPV6) + if (skb->protocol == htons(ETH_P_IPV6)) + return rcu_dereference(hlist_first_rcu(&b->ip6_mc_router_list)); +#endif + return rcu_dereference(hlist_first_rcu(&b->ip4_mc_router_list)); +} + +static inline struct net_bridge_port * +br_multicast_rport_from_node_skb(struct hlist_node *rp, struct sk_buff *skb) { +#if IS_ENABLED(CONFIG_IPV6) + if (skb->protocol == htons(ETH_P_IPV6)) + return hlist_entry_safe(rp, struct net_bridge_port, ip6_rlist); +#endif + return hlist_entry_safe(rp, struct net_bridge_port, ip4_rlist); +} + +static inline bool br_ip4_multicast_is_router(struct net_bridge *br) { - return br->multicast_router == 2 || - (br->multicast_router == 1 && - timer_pending(&br->multicast_router_timer)); + return timer_pending(&br->ip4_mc_router_timer); +} + +static inline bool br_ip6_multicast_is_router(struct net_bridge *br) +{ +#if IS_ENABLED(CONFIG_IPV6) + return timer_pending(&br->ip6_mc_router_timer); +#else + return false; +#endif +} + +static inline bool +br_multicast_is_router(struct net_bridge *br, struct sk_buff *skb) +{ + switch (br->multicast_router) { + case MDB_RTR_TYPE_PERM: + return true; + case MDB_RTR_TYPE_TEMP_QUERY: + if (skb) { + if (skb->protocol == htons(ETH_P_IP)) + return br_ip4_multicast_is_router(br); + else if (skb->protocol == htons(ETH_P_IPV6)) + return br_ip6_multicast_is_router(br); + } else { + return br_ip4_multicast_is_router(br) || + br_ip6_multicast_is_router(br); + } + fallthrough; + default: + return false; + } } static inline bool @@ -1017,7 +1068,8 @@ static inline void br_multicast_flood(struct net_bridge_mdb_entry *mdst, { } -static inline bool br_multicast_is_router(struct net_bridge *br) +static inline bool br_multicast_is_router(struct net_bridge *br, + struct sk_buff *skb) { return false; } @@ -1602,8 +1654,8 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p, unsigned long flags, unsigned long mask, struct netlink_ext_ack *extack); -void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, - int type); +void br_switchdev_fdb_notify(struct net_bridge *br, + const struct net_bridge_fdb_entry *fdb, int type); int br_switchdev_port_vlan_add(struct net_device *dev, u16 vid, u16 flags, struct netlink_ext_ack *extack); int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid); @@ -1650,7 +1702,8 @@ static inline int br_switchdev_port_vlan_del(struct net_device *dev, u16 vid) } static inline void -br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) +br_switchdev_fdb_notify(struct net_bridge *br, + const struct net_bridge_fdb_entry *fdb, int type) { } diff --git a/net/bridge/br_private_mrp.h b/net/bridge/br_private_mrp.h index 9559aa2750fb..bda8e1896712 100644 --- a/net/bridge/br_private_mrp.h +++ b/net/bridge/br_private_mrp.h @@ -6,6 +6,8 @@ #include "br_private.h" #include +#define MRP_OPT_PADDING 0x2 + struct br_mrp { /* list of mrp instances */ struct hlist_node list; @@ -134,4 +136,13 @@ struct br_mrp_in_test_hdr { __be32 timestamp; } __attribute__((__packed__)); +struct br_mrp_oui_hdr { + __u8 oui[MRP_OUI_LENGTH]; +}; + +struct br_mrp_sub_option1_hdr { + __u8 type; + __u8 data[MRP_MANUFACTURE_DATA_LENGTH]; +}; + #endif /* _BR_PRIVATE_MRP_H */ diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 3dafb6143cff..1d80f34a139c 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -639,9 +639,9 @@ int br_set_ageing_time(struct net_bridge *br, clock_t ageing_time) return 0; } -clock_t br_get_ageing_time(struct net_device *br_dev) +clock_t br_get_ageing_time(const struct net_device *br_dev) { - struct net_bridge *br; + const struct net_bridge *br; if (!netif_is_bridge_master(br_dev)) return 0; diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index a5e601e41cb9..d3adee0f91f9 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -108,8 +108,11 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p, } void -br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) +br_switchdev_fdb_notify(struct net_bridge *br, + const struct net_bridge_fdb_entry *fdb, int type) { + const struct net_bridge_port *dst = READ_ONCE(fdb->dst); + struct net_device *dev = dst ? dst->dev : br->dev; struct switchdev_notifier_fdb_info info = { .addr = fdb->key.addr.addr, .vid = fdb->key.vlan_id, @@ -118,17 +121,14 @@ br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) .offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags), }; - if (!fdb->dst) - return; - switch (type) { case RTM_DELNEIGH: call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_DEVICE, - fdb->dst->dev, &info.info, NULL); + dev, &info.info, NULL); break; case RTM_NEWNEIGH: call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_DEVICE, - fdb->dst->dev, &info.info, NULL); + dev, &info.info, NULL); break; } } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index da3256a3eed0..a08e9f193009 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -113,9 +113,7 @@ static void __vlan_add_list(struct net_bridge_vlan *v) headp = &vg->vlan_list; list_for_each_prev(hpos, headp) { vent = list_entry(hpos, struct net_bridge_vlan, vlist); - if (v->vid < vent->vid) - continue; - else + if (v->vid >= vent->vid) break; } list_add_rcu(&v->vlist, hpos); @@ -1809,28 +1807,32 @@ out_kfree: static int br_vlan_replay_one(struct notifier_block *nb, struct net_device *dev, struct switchdev_obj_port_vlan *vlan, + const void *ctx, unsigned long action, struct netlink_ext_ack *extack) { struct switchdev_notifier_port_obj_info obj_info = { .info = { .dev = dev, .extack = extack, + .ctx = ctx, }, .obj = &vlan->obj, }; int err; - err = nb->notifier_call(nb, SWITCHDEV_PORT_OBJ_ADD, &obj_info); + err = nb->notifier_call(nb, action, &obj_info); return notifier_to_errno(err); } int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack) + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge_port *p; struct net_bridge *br; + unsigned long action; int err = 0; u16 pvid; @@ -1857,6 +1859,11 @@ int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, if (!vg) return 0; + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + pvid = br_get_pvid(vg); list_for_each_entry(v, &vg->vlan_list, vlist) { @@ -1870,7 +1877,7 @@ int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, if (!br_vlan_should_use(v)) continue; - err = br_vlan_replay_one(nb, dev, &vlan, extack); + err = br_vlan_replay_one(nb, dev, &vlan, ctx, action, extack); if (err) return err; } diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 3ad0a1df6712..647554c9813b 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -243,7 +243,7 @@ static void caif_ctrl_cb(struct cflayer *layr, cf_sk->sk.sk_shutdown = SHUTDOWN_MASK; cf_sk->sk.sk_err = ECONNRESET; set_rx_flow_on(cf_sk); - cf_sk->sk.sk_error_report(&cf_sk->sk); + sk_error_report(&cf_sk->sk); break; default: diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index cac30e676ac9..23267c8db7c4 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -480,7 +480,7 @@ got_phyid: phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC); if (!phyinfo) { res = -ENOMEM; - goto out_err; + goto out; } phy_layer->id = phyid; diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index fadc7c8a3107..37b67194c0df 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -76,8 +76,6 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) u8 buf; priv = container_of(layr, struct chnl_net, chnl); - if (!priv) - return -EINVAL; skb = (struct sk_buff *) cfpkt_tonative(pkt); diff --git a/net/can/bcm.c b/net/can/bcm.c index f3e4d9528fa3..508f67de0b80 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -785,6 +785,7 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, bcm_rx_handler, op); list_del(&op->list); + synchronize_rcu(); bcm_remove_op(op); return 1; /* done */ } @@ -1417,7 +1418,7 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, if (notify_enodev) { sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } break; @@ -1425,7 +1426,7 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, if (bo->bound && bo->ifindex == dev->ifindex) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } } } @@ -1533,9 +1534,13 @@ static int bcm_release(struct socket *sock) REGMASK(op->can_id), bcm_rx_handler, op); - bcm_remove_op(op); } + synchronize_rcu(); + + list_for_each_entry_safe(op, next, &bo->rx_ops, list) + bcm_remove_op(op); + #if IS_ENABLED(CONFIG_PROC_FS) /* remove procfs entry */ if (net->can.bcmproc_dir && bo->bcm_proc_read) diff --git a/net/can/gw.c b/net/can/gw.c index ba4124805602..d8861e862f15 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -596,6 +596,7 @@ static int cgw_notifier(struct notifier_block *nb, if (gwj->src.dev == dev || gwj->dst.dev == dev) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); + synchronize_rcu(); kmem_cache_free(cgw_cache, gwj); } } @@ -1154,6 +1155,7 @@ static void cgw_remove_all_jobs(struct net *net) hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) { hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); + synchronize_rcu(); kmem_cache_free(cgw_cache, gwj); } } @@ -1222,6 +1224,7 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, hlist_del(&gwj->list); cgw_unregister_filter(net, gwj); + synchronize_rcu(); kmem_cache_free(cgw_cache, gwj); err = 0; break; diff --git a/net/can/isotp.c b/net/can/isotp.c index be6183f8ca11..caaa532ece94 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -168,7 +168,7 @@ static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer) /* report 'connection timed out' */ sk->sk_err = ETIMEDOUT; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); /* reset rx state */ so->rx.state = ISOTP_IDLE; @@ -225,8 +225,8 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus) can_send_ret = can_send(nskb, 1); if (can_send_ret) - pr_notice_once("can-isotp: %s: can_send_ret %d\n", - __func__, can_send_ret); + pr_notice_once("can-isotp: %s: can_send_ret %pe\n", + __func__, ERR_PTR(can_send_ret)); dev_put(dev); @@ -339,7 +339,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); so->tx.state = ISOTP_IDLE; wake_up_interruptible(&so->wait); @@ -392,7 +392,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) /* overflow on receiver side - report 'message too long' */ sk->sk_err = EMSGSIZE; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); fallthrough; default: @@ -420,7 +420,7 @@ static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen, /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); return 1; } @@ -535,7 +535,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, /* wrong sn detected - report 'illegal byte sequence' */ sk->sk_err = EILSEQ; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); /* reset rx state */ so->rx.state = ISOTP_IDLE; @@ -559,7 +559,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, /* malformed PDU - report 'not a data message' */ sk->sk_err = EBADMSG; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); return 1; } @@ -758,7 +758,7 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) /* report 'communication error on send' */ sk->sk_err = ECOMM; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); /* reset tx state */ so->tx.state = ISOTP_IDLE; @@ -801,10 +801,12 @@ isotp_tx_burst: can_skb_set_owner(skb, sk); can_send_ret = can_send(skb, 1); - if (can_send_ret) - pr_notice_once("can-isotp: %s: can_send_ret %d\n", - __func__, can_send_ret); - + if (can_send_ret) { + pr_notice_once("can-isotp: %s: can_send_ret %pe\n", + __func__, ERR_PTR(can_send_ret)); + if (can_send_ret == -ENOBUFS) + pr_notice_once("can-isotp: tx queue is full, increasing txqueuelen may prevent this error\n"); + } if (so->tx.idx >= so->tx.len) { /* we are done */ so->tx.state = ISOTP_IDLE; @@ -950,8 +952,8 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) err = can_send(skb, 1); dev_put(dev); if (err) { - pr_notice_once("can-isotp: %s: can_send_ret %d\n", - __func__, err); + pr_notice_once("can-isotp: %s: can_send_ret %pe\n", + __func__, ERR_PTR(err)); return err; } @@ -1028,9 +1030,6 @@ static int isotp_release(struct socket *sock) lock_sock(sk); - hrtimer_cancel(&so->txtimer); - hrtimer_cancel(&so->rxtimer); - /* remove current filters & unregister */ if (so->bound && (!(so->opt.flags & CAN_ISOTP_SF_BROADCAST))) { if (so->ifindex) { @@ -1042,10 +1041,14 @@ static int isotp_release(struct socket *sock) SINGLE_MASK(so->rxid), isotp_rcv, sk); dev_put(dev); + synchronize_rcu(); } } } + hrtimer_cancel(&so->txtimer); + hrtimer_cancel(&so->rxtimer); + so->ifindex = 0; so->bound = 0; @@ -1155,7 +1158,7 @@ out: if (notify_enetdown) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } return err; @@ -1354,13 +1357,13 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg, sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); break; case NETDEV_DOWN: sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); break; } } @@ -1482,7 +1485,7 @@ static __init int isotp_module_init(void) err = can_proto_register(&isotp_can_proto); if (err < 0) - pr_err("can: registration of isotp protocol failed\n"); + pr_err("can: registration of isotp protocol failed %pe\n", ERR_PTR(err)); else register_netdevice_notifier(&canisotp_notifier); diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index da3a7a7bcff2..08c8606cfd9c 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -193,6 +193,10 @@ static void j1939_can_rx_unregister(struct j1939_priv *priv) can_rx_unregister(dev_net(ndev), ndev, J1939_CAN_ID, J1939_CAN_MASK, j1939_can_recv, priv); + /* The last reference of priv is dropped by the RCU deferred + * j1939_sk_sock_destruct() of the last socket, so we can + * safely drop this reference here. + */ j1939_priv_put(priv); } diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 56aa66147d5a..54f6d521492f 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -398,6 +398,9 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + + /* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */ + sock_set_flag(sk, SOCK_RCU_FREE); sk->sk_destruct = j1939_sk_sock_destruct; sk->sk_protocol = CAN_J1939; @@ -673,7 +676,7 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname, switch (optname) { case SO_J1939_FILTER: - if (!sockptr_is_null(optval)) { + if (!sockptr_is_null(optval) && optlen != 0) { struct j1939_filter *f; int c; @@ -1009,7 +1012,7 @@ void j1939_sk_send_loop_abort(struct sock *sk, int err) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } static int j1939_sk_send_loop(struct j1939_priv *priv, struct sock *sk, @@ -1189,7 +1192,7 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) list_for_each_entry(jsk, &priv->j1939_socks, list) { jsk->sk.sk_err = error_code; if (!sock_flag(&jsk->sk, SOCK_DEAD)) - jsk->sk.sk_error_report(&jsk->sk); + sk_error_report(&jsk->sk); j1939_sk_queue_drop_all(priv, jsk, error_code); } diff --git a/net/can/proc.c b/net/can/proc.c index d1fe49e6f16d..b3099f0a3cb8 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -99,8 +99,6 @@ static void can_init_stats(struct net *net) static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif, unsigned long count) { - unsigned long rate; - if (oldjif == newjif) return 0; @@ -111,9 +109,7 @@ static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif, return 99999999; } - rate = (count * HZ) / (newjif - oldjif); - - return rate; + return (count * HZ) / (newjif - oldjif); } void can_stat_update(struct timer_list *t) diff --git a/net/can/raw.c b/net/can/raw.c index ac96fc210025..ed4fcb7ab0c3 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -295,13 +295,13 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); break; case NETDEV_DOWN: sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); break; } } @@ -488,7 +488,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (notify_enetdown) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } return err; diff --git a/net/ceph/auth_x_protocol.h b/net/ceph/auth_x_protocol.h index 792fcb974dc3..9c60feeb1bcb 100644 --- a/net/ceph/auth_x_protocol.h +++ b/net/ceph/auth_x_protocol.h @@ -87,7 +87,7 @@ struct ceph_x_authorize_reply { /* - * encyption bundle + * encryption bundle */ #define CEPHX_ENC_MAGIC 0xff009cad8826aa55ull diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 195ceb8afb06..013cbdb6cfe2 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1508,7 +1508,7 @@ static struct ceph_msg *mon_alloc_msg(struct ceph_connection *con, return get_generic_reply(con, hdr, skip); /* - * Older OSDs don't set reply tid even if the orignal + * Older OSDs don't set reply tid even if the original * request had a non-zero tid. Work around this weirdness * by allocating a new message. */ diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index c959320c4775..75b738083523 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -1309,7 +1309,7 @@ static int get_osdmap_client_data_v(void **p, void *end, return -EINVAL; } - /* old osdmap enconding */ + /* old osdmap encoding */ struct_v = 0; } @@ -3010,7 +3010,7 @@ static bool is_valid_crush_name(const char *name) * parent, returns 0. * * Does a linear search, as there are no parent pointers of any - * kind. Note that the result is ambigous for items that occur + * kind. Note that the result is ambiguous for items that occur * multiple times in the map. */ static int get_immediate_parent(struct crush_map *c, int id, diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index cc3712ad8716..f564f82e91d9 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -524,8 +524,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) nr_maps++; } - diag = kzalloc(sizeof(*diag) + sizeof(diag->maps[0]) * nr_maps, - GFP_KERNEL); + diag = kzalloc(struct_size(diag, maps, nr_maps), GFP_KERNEL); if (!diag) return ERR_PTR(-ENOMEM); diff --git a/net/core/dev.c b/net/core/dev.c index bb7d6e98bcba..fe0055566102 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -148,6 +148,7 @@ #include #include #include +#include #include #include "net-sysfs.h" @@ -3494,13 +3495,16 @@ EXPORT_SYMBOL(__skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG +static void do_netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) +{ + pr_err("%s: hw csum failure\n", dev ? dev->name : ""); + skb_dump(KERN_ERR, skb, true); + dump_stack(); +} + void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { - if (net_ratelimit()) { - pr_err("%s: hw csum failure\n", dev ? dev->name : ""); - skb_dump(KERN_ERR, skb, true); - dump_stack(); - } + DO_ONCE_LITE(do_netdev_rx_csum_fault, dev, skb); } EXPORT_SYMBOL(netdev_rx_csum_fault); #endif @@ -3859,10 +3863,33 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - if (likely(!netif_xmit_frozen_or_stopped(txq))) - qdisc_run(q); + if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) && + qdisc_run_begin(q)) { + /* Retest nolock_qdisc_is_empty() within the protection + * of q->seqlock to protect from racing with requeuing. + */ + if (unlikely(!nolock_qdisc_is_empty(q))) { + rc = q->enqueue(skb, q, &to_free) & + NET_XMIT_MASK; + __qdisc_run(q); + qdisc_run_end(q); + goto no_lock_out; + } + + qdisc_bstats_cpu_update(q, skb); + if (sch_direct_xmit(skb, q, dev, txq, NULL, true) && + !nolock_qdisc_is_empty(q)) + __qdisc_run(q); + + qdisc_run_end(q); + return NET_XMIT_SUCCESS; + } + + rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + qdisc_run(q); + +no_lock_out: if (unlikely(to_free)) kfree_skb_list(to_free); return rc; @@ -5284,9 +5311,9 @@ another_round: if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret2; - preempt_disable(); + migrate_disable(); ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb); - preempt_enable(); + migrate_enable(); if (ret2 != XDP_PASS) { ret = NET_RX_DROP; @@ -6527,11 +6554,18 @@ EXPORT_SYMBOL(napi_schedule_prep); * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule * - * Variant of __napi_schedule() assuming hard irqs are masked + * Variant of __napi_schedule() assuming hard irqs are masked. + * + * On PREEMPT_RT enabled kernels this maps to __napi_schedule() + * because the interrupt disabled assumption might not be true + * due to force-threaded interrupts and spinlock substitution. */ void __napi_schedule_irqoff(struct napi_struct *n) { - ____napi_schedule(this_cpu_ptr(&softnet_data), n); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + ____napi_schedule(this_cpu_ptr(&softnet_data), n); + else + __napi_schedule(n); } EXPORT_SYMBOL(__napi_schedule_irqoff); diff --git a/net/core/devlink.c b/net/core/devlink.c index 051432ea4f69..8fdd04f00fd7 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -190,6 +190,80 @@ static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, return devlink_port_get_from_attrs(devlink, info->attrs); } +static inline bool +devlink_rate_is_leaf(struct devlink_rate *devlink_rate) +{ + return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF; +} + +static inline bool +devlink_rate_is_node(struct devlink_rate *devlink_rate) +{ + return devlink_rate->type == DEVLINK_RATE_TYPE_NODE; +} + +static struct devlink_rate * +devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info) +{ + struct devlink_rate *devlink_rate; + struct devlink_port *devlink_port; + + devlink_port = devlink_port_get_from_attrs(devlink, info->attrs); + if (IS_ERR(devlink_port)) + return ERR_CAST(devlink_port); + devlink_rate = devlink_port->devlink_rate; + return devlink_rate ?: ERR_PTR(-ENODEV); +} + +static struct devlink_rate * +devlink_rate_node_get_by_name(struct devlink *devlink, const char *node_name) +{ + static struct devlink_rate *devlink_rate; + + list_for_each_entry(devlink_rate, &devlink->rate_list, list) { + if (devlink_rate_is_node(devlink_rate) && + !strcmp(node_name, devlink_rate->name)) + return devlink_rate; + } + return ERR_PTR(-ENODEV); +} + +static struct devlink_rate * +devlink_rate_node_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) +{ + const char *rate_node_name; + size_t len; + + if (!attrs[DEVLINK_ATTR_RATE_NODE_NAME]) + return ERR_PTR(-EINVAL); + rate_node_name = nla_data(attrs[DEVLINK_ATTR_RATE_NODE_NAME]); + len = strlen(rate_node_name); + /* Name cannot be empty or decimal number */ + if (!len || strspn(rate_node_name, "0123456789") == len) + return ERR_PTR(-EINVAL); + + return devlink_rate_node_get_by_name(devlink, rate_node_name); +} + +static struct devlink_rate * +devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info) +{ + return devlink_rate_node_get_from_attrs(devlink, info->attrs); +} + +static struct devlink_rate * +devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info) +{ + struct nlattr **attrs = info->attrs; + + if (attrs[DEVLINK_ATTR_PORT_INDEX]) + return devlink_rate_leaf_get_from_info(devlink, info); + else if (attrs[DEVLINK_ATTR_RATE_NODE_NAME]) + return devlink_rate_node_get_from_info(devlink, info); + else + return ERR_PTR(-EINVAL); +} + struct devlink_sb { struct list_head list; unsigned int index; @@ -408,12 +482,14 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) #define DEVLINK_NL_FLAG_NEED_PORT BIT(0) #define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT BIT(1) +#define DEVLINK_NL_FLAG_NEED_RATE BIT(2) +#define DEVLINK_NL_FLAG_NEED_RATE_NODE BIT(3) /* The per devlink instance lock is taken by default in the pre-doit * operation, yet several commands do not require this. The global * devlink lock is taken and protects from disruption by user-calls. */ -#define DEVLINK_NL_FLAG_NO_LOCK BIT(2) +#define DEVLINK_NL_FLAG_NO_LOCK BIT(4) static int devlink_nl_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) @@ -442,6 +518,24 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops, devlink_port = devlink_port_get_from_info(devlink, info); if (!IS_ERR(devlink_port)) info->user_ptr[1] = devlink_port; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) { + struct devlink_rate *devlink_rate; + + devlink_rate = devlink_rate_get_from_info(devlink, info); + if (IS_ERR(devlink_rate)) { + err = PTR_ERR(devlink_rate); + goto unlock; + } + info->user_ptr[1] = devlink_rate; + } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE_NODE) { + struct devlink_rate *rate_node; + + rate_node = devlink_rate_node_get_from_info(devlink, info); + if (IS_ERR(rate_node)) { + err = PTR_ERR(rate_node); + goto unlock; + } + info->user_ptr[1] = rate_node; } return 0; @@ -748,6 +842,56 @@ devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops * return 0; } +static int devlink_nl_rate_fill(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_rate *devlink_rate, + enum devlink_command cmd, u32 portid, + u32 seq, int flags, + struct netlink_ext_ack *extack) +{ + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_u16(msg, DEVLINK_ATTR_RATE_TYPE, devlink_rate->type)) + goto nla_put_failure; + + if (devlink_rate_is_leaf(devlink_rate)) { + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, + devlink_rate->devlink_port->index)) + goto nla_put_failure; + } else if (devlink_rate_is_node(devlink_rate)) { + if (nla_put_string(msg, DEVLINK_ATTR_RATE_NODE_NAME, + devlink_rate->name)) + goto nla_put_failure; + } + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_SHARE, + devlink_rate->tx_share, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_RATE_TX_MAX, + devlink_rate->tx_max, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (devlink_rate->parent) + if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, + devlink_rate->parent->name)) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + static bool devlink_port_fn_state_valid(enum devlink_port_fn_state state) { @@ -919,6 +1063,111 @@ static void devlink_port_notify(struct devlink_port *devlink_port, msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } +static void devlink_rate_notify(struct devlink_rate *devlink_rate, + enum devlink_command cmd) +{ + struct devlink *devlink = devlink_rate->devlink; + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && + cmd != DEVLINK_CMD_RATE_DEL); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_rate_fill(msg, devlink, devlink_rate, + cmd, 0, 0, 0, NULL); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_rate *devlink_rate; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err = 0; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_rate, &devlink->rate_list, list) { + enum devlink_command cmd = DEVLINK_CMD_RATE_NEW; + u32 id = NETLINK_CB(cb->skb).portid; + + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_rate_fill(msg, devlink, + devlink_rate, + cmd, id, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, NULL); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_rate *devlink_rate = info->user_ptr[1]; + struct devlink *devlink = devlink_rate->devlink; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_rate_fill(msg, devlink, devlink_rate, + DEVLINK_CMD_RATE_NEW, + info->snd_portid, info->snd_seq, 0, + info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static bool +devlink_rate_is_parent_node(struct devlink_rate *devlink_rate, + struct devlink_rate *parent) +{ + while (parent) { + if (parent == devlink_rate) + return true; + parent = parent->parent; + } + return false; +} + static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; @@ -1339,6 +1588,255 @@ static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, return devlink->ops->port_del(devlink, port_index, extack); } +static int +devlink_nl_rate_parent_node_set(struct devlink_rate *devlink_rate, + struct genl_info *info, + struct nlattr *nla_parent) +{ + struct devlink *devlink = devlink_rate->devlink; + const char *parent_name = nla_data(nla_parent); + const struct devlink_ops *ops = devlink->ops; + size_t len = strlen(parent_name); + struct devlink_rate *parent; + int err = -EOPNOTSUPP; + + parent = devlink_rate->parent; + if (parent && len) { + NL_SET_ERR_MSG_MOD(info->extack, "Rate object already has parent."); + return -EBUSY; + } else if (parent && !len) { + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_parent_set(devlink_rate, NULL, + devlink_rate->priv, NULL, + info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_parent_set(devlink_rate, NULL, + devlink_rate->priv, NULL, + info->extack); + if (err) + return err; + + refcount_dec(&parent->refcnt); + devlink_rate->parent = NULL; + } else if (!parent && len) { + parent = devlink_rate_node_get_by_name(devlink, parent_name); + if (IS_ERR(parent)) + return -ENODEV; + + if (parent == devlink_rate) { + NL_SET_ERR_MSG_MOD(info->extack, "Parent to self is not allowed"); + return -EINVAL; + } + + if (devlink_rate_is_node(devlink_rate) && + devlink_rate_is_parent_node(devlink_rate, parent->parent)) { + NL_SET_ERR_MSG_MOD(info->extack, "Node is already a parent of parent node."); + return -EEXIST; + } + + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_parent_set(devlink_rate, parent, + devlink_rate->priv, parent->priv, + info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_parent_set(devlink_rate, parent, + devlink_rate->priv, parent->priv, + info->extack); + if (err) + return err; + + refcount_inc(&parent->refcnt); + devlink_rate->parent = parent; + } + + return 0; +} + +static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, + const struct devlink_ops *ops, + struct genl_info *info) +{ + struct nlattr *nla_parent, **attrs = info->attrs; + int err = -EOPNOTSUPP; + u64 rate; + + if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) { + rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_SHARE]); + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tx_share_set(devlink_rate, devlink_rate->priv, + rate, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tx_share_set(devlink_rate, devlink_rate->priv, + rate, info->extack); + if (err) + return err; + devlink_rate->tx_share = rate; + } + + if (attrs[DEVLINK_ATTR_RATE_TX_MAX]) { + rate = nla_get_u64(attrs[DEVLINK_ATTR_RATE_TX_MAX]); + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tx_max_set(devlink_rate, devlink_rate->priv, + rate, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tx_max_set(devlink_rate, devlink_rate->priv, + rate, info->extack); + if (err) + return err; + devlink_rate->tx_max = rate; + } + + nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME]; + if (nla_parent) { + err = devlink_nl_rate_parent_node_set(devlink_rate, info, + nla_parent); + if (err) + return err; + } + + return 0; +} + +static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, + struct genl_info *info, + enum devlink_rate_type type) +{ + struct nlattr **attrs = info->attrs; + + if (type == DEVLINK_RATE_TYPE_LEAF) { + if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_leaf_tx_share_set) { + NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the leafs"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_leaf_tx_max_set) { + NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the leafs"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] && + !ops->rate_leaf_parent_set) { + NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the leafs"); + return false; + } + } else if (type == DEVLINK_RATE_TYPE_NODE) { + if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) { + NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_TX_MAX] && !ops->rate_node_tx_max_set) { + NL_SET_ERR_MSG_MOD(info->extack, "TX max set isn't supported for the nodes"); + return false; + } + if (attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME] && + !ops->rate_node_parent_set) { + NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the nodes"); + return false; + } + } else { + WARN(1, "Unknown type of rate object"); + return false; + } + + return true; +} + +static int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_rate *devlink_rate = info->user_ptr[1]; + struct devlink *devlink = devlink_rate->devlink; + const struct devlink_ops *ops = devlink->ops; + int err; + + if (!ops || !devlink_rate_set_ops_supported(ops, info, devlink_rate->type)) + return -EOPNOTSUPP; + + err = devlink_nl_rate_set(devlink_rate, ops, info); + + if (!err) + devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW); + return err; +} + +static int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_rate *rate_node; + const struct devlink_ops *ops; + int err; + + ops = devlink->ops; + if (!ops || !ops->rate_node_new || !ops->rate_node_del) { + NL_SET_ERR_MSG_MOD(info->extack, "Rate nodes aren't supported"); + return -EOPNOTSUPP; + } + + if (!devlink_rate_set_ops_supported(ops, info, DEVLINK_RATE_TYPE_NODE)) + return -EOPNOTSUPP; + + rate_node = devlink_rate_node_get_from_attrs(devlink, info->attrs); + if (!IS_ERR(rate_node)) + return -EEXIST; + else if (rate_node == ERR_PTR(-EINVAL)) + return -EINVAL; + + rate_node = kzalloc(sizeof(*rate_node), GFP_KERNEL); + if (!rate_node) + return -ENOMEM; + + rate_node->devlink = devlink; + rate_node->type = DEVLINK_RATE_TYPE_NODE; + rate_node->name = nla_strdup(info->attrs[DEVLINK_ATTR_RATE_NODE_NAME], GFP_KERNEL); + if (!rate_node->name) { + err = -ENOMEM; + goto err_strdup; + } + + err = ops->rate_node_new(rate_node, &rate_node->priv, info->extack); + if (err) + goto err_node_new; + + err = devlink_nl_rate_set(rate_node, ops, info); + if (err) + goto err_rate_set; + + refcount_set(&rate_node->refcnt, 1); + list_add(&rate_node->list, &devlink->rate_list); + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW); + return 0; + +err_rate_set: + ops->rate_node_del(rate_node, rate_node->priv, info->extack); +err_node_new: + kfree(rate_node->name); +err_strdup: + kfree(rate_node); + return err; +} + +static int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_rate *rate_node = info->user_ptr[1]; + struct devlink *devlink = rate_node->devlink; + const struct devlink_ops *ops = devlink->ops; + int err; + + if (refcount_read(&rate_node->refcnt) > 1) { + NL_SET_ERR_MSG_MOD(info->extack, "Node has children. Cannot delete node."); + return -EBUSY; + } + + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL); + err = ops->rate_node_del(rate_node, rate_node->priv, info->extack); + if (rate_node->parent) + refcount_dec(&rate_node->parent->refcnt); + list_del(&rate_node->list); + kfree(rate_node->name); + kfree(rate_node); + return err; +} + static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_sb *devlink_sb, enum devlink_command cmd, u32 portid, @@ -2207,6 +2705,23 @@ static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } +static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) +{ + struct devlink_rate *devlink_rate; + + /* Take the lock to sync with devlink_rate_nodes_destroy() */ + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_rate, &devlink->rate_list, list) + if (devlink_rate_is_node(devlink_rate)) { + mutex_unlock(&devlink->lock); + NL_SET_ERR_MSG_MOD(extack, "Rate node(s) exists."); + return -EBUSY; + } + mutex_unlock(&devlink->lock); + return 0; +} + static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) { @@ -2221,6 +2736,9 @@ static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, if (!ops->eswitch_mode_set) return -EOPNOTSUPP; mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); + err = devlink_rate_nodes_check(devlink, mode, info->extack); + if (err) + return err; err = ops->eswitch_mode_set(devlink, mode, info->extack); if (err) return err; @@ -6994,8 +7512,9 @@ static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats, } } -static int devlink_trap_stats_put(struct sk_buff *msg, - struct devlink_stats __percpu *trap_stats) +static int +devlink_trap_group_stats_put(struct sk_buff *msg, + struct devlink_stats __percpu *trap_stats) { struct devlink_stats stats; struct nlattr *attr; @@ -7023,6 +7542,50 @@ nla_put_failure: return -EMSGSIZE; } +static int devlink_trap_stats_put(struct sk_buff *msg, struct devlink *devlink, + const struct devlink_trap_item *trap_item) +{ + struct devlink_stats stats; + struct nlattr *attr; + u64 drops = 0; + int err; + + if (devlink->ops->trap_drop_counter_get) { + err = devlink->ops->trap_drop_counter_get(devlink, + trap_item->trap, + &drops); + if (err) + return err; + } + + devlink_trap_stats_read(trap_item->stats, &stats); + + attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); + if (!attr) + return -EMSGSIZE; + + if (devlink->ops->trap_drop_counter_get && + nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_DROPPED, drops, + DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS, + stats.rx_packets, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES, + stats.rx_bytes, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink, const struct devlink_trap_item *trap_item, enum devlink_command cmd, u32 portid, u32 seq, @@ -7060,7 +7623,7 @@ static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink, if (err) goto nla_put_failure; - err = devlink_trap_stats_put(msg, trap_item->stats); + err = devlink_trap_stats_put(msg, devlink, trap_item); if (err) goto nla_put_failure; @@ -7277,7 +7840,7 @@ devlink_nl_trap_group_fill(struct sk_buff *msg, struct devlink *devlink, group_item->policer_item->policer->id)) goto nla_put_failure; - err = devlink_trap_stats_put(msg, group_item->stats); + err = devlink_trap_group_stats_put(msg, group_item->stats); if (err) goto nla_put_failure; @@ -7801,6 +8364,11 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 }, [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 }, [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 }, + [DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 }, + [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 }, + [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING }, }; static const struct genl_small_ops devlink_nl_ops[] = { @@ -7826,6 +8394,30 @@ static const struct genl_small_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, }, + { + .cmd = DEVLINK_CMD_RATE_GET, + .doit = devlink_nl_cmd_rate_get_doit, + .dumpit = devlink_nl_cmd_rate_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_RATE, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_RATE_SET, + .doit = devlink_nl_cmd_rate_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_RATE, + }, + { + .cmd = DEVLINK_CMD_RATE_NEW, + .doit = devlink_nl_cmd_rate_new_doit, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = DEVLINK_CMD_RATE_DEL, + .doit = devlink_nl_cmd_rate_del_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_RATE_NODE, + }, { .cmd = DEVLINK_CMD_PORT_SPLIT, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -8201,6 +8793,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC); __devlink_net_set(devlink, &init_net); INIT_LIST_HEAD(&devlink->port_list); + INIT_LIST_HEAD(&devlink->rate_list); INIT_LIST_HEAD(&devlink->sb_list); INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); INIT_LIST_HEAD(&devlink->resource_list); @@ -8303,6 +8896,7 @@ void devlink_free(struct devlink *devlink) WARN_ON(!list_empty(&devlink->resource_list)); WARN_ON(!list_empty(&devlink->dpipe_table_list)); WARN_ON(!list_empty(&devlink->sb_list)); + WARN_ON(!list_empty(&devlink->rate_list)); WARN_ON(!list_empty(&devlink->port_list)); xa_destroy(&devlink->snapshot_ids); @@ -8619,6 +9213,110 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 contro } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set); +/** + * devlink_rate_leaf_create - create devlink rate leaf + * + * @devlink_port: devlink port object to create rate object on + * @priv: driver private data + * + * Create devlink rate object of type leaf on provided @devlink_port. + * Throws call trace if @devlink_port already has a devlink rate object. + * + * Context: Takes and release devlink->lock . + * + * Return: -ENOMEM if failed to allocate rate object, 0 otherwise. + */ +int +devlink_rate_leaf_create(struct devlink_port *devlink_port, void *priv) +{ + struct devlink *devlink = devlink_port->devlink; + struct devlink_rate *devlink_rate; + + devlink_rate = kzalloc(sizeof(*devlink_rate), GFP_KERNEL); + if (!devlink_rate) + return -ENOMEM; + + mutex_lock(&devlink->lock); + WARN_ON(devlink_port->devlink_rate); + devlink_rate->type = DEVLINK_RATE_TYPE_LEAF; + devlink_rate->devlink = devlink; + devlink_rate->devlink_port = devlink_port; + devlink_rate->priv = priv; + list_add_tail(&devlink_rate->list, &devlink->rate_list); + devlink_port->devlink_rate = devlink_rate; + devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW); + mutex_unlock(&devlink->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_rate_leaf_create); + +/** + * devlink_rate_leaf_destroy - destroy devlink rate leaf + * + * @devlink_port: devlink port linked to the rate object + * + * Context: Takes and release devlink->lock . + */ +void devlink_rate_leaf_destroy(struct devlink_port *devlink_port) +{ + struct devlink_rate *devlink_rate = devlink_port->devlink_rate; + struct devlink *devlink = devlink_port->devlink; + + if (!devlink_rate) + return; + + mutex_lock(&devlink->lock); + devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL); + if (devlink_rate->parent) + refcount_dec(&devlink_rate->parent->refcnt); + list_del(&devlink_rate->list); + devlink_port->devlink_rate = NULL; + mutex_unlock(&devlink->lock); + kfree(devlink_rate); +} +EXPORT_SYMBOL_GPL(devlink_rate_leaf_destroy); + +/** + * devlink_rate_nodes_destroy - destroy all devlink rate nodes on device + * + * @devlink: devlink instance + * + * Unset parent for all rate objects and destroy all rate nodes + * on specified device. + * + * Context: Takes and release devlink->lock . + */ +void devlink_rate_nodes_destroy(struct devlink *devlink) +{ + static struct devlink_rate *devlink_rate, *tmp; + const struct devlink_ops *ops = devlink->ops; + + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_rate, &devlink->rate_list, list) { + if (!devlink_rate->parent) + continue; + + refcount_dec(&devlink_rate->parent->refcnt); + if (devlink_rate_is_leaf(devlink_rate)) + ops->rate_leaf_parent_set(devlink_rate, NULL, devlink_rate->priv, + NULL, NULL); + else if (devlink_rate_is_node(devlink_rate)) + ops->rate_node_parent_set(devlink_rate, NULL, devlink_rate->priv, + NULL, NULL); + } + list_for_each_entry_safe(devlink_rate, tmp, &devlink->rate_list, list) { + if (devlink_rate_is_node(devlink_rate)) { + ops->rate_node_del(devlink_rate, devlink_rate->priv, NULL); + list_del(&devlink_rate->list); + kfree(devlink_rate->name); + kfree(devlink_rate); + } + } + mutex_unlock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devlink_rate_nodes_destroy); + static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, char *name, size_t len) { @@ -8630,12 +9328,18 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, switch (attrs->flavour) { case DEVLINK_PORT_FLAVOUR_PHYSICAL: + case DEVLINK_PORT_FLAVOUR_VIRTUAL: + n = snprintf(name, len, "p%u", attrs->phys.port_number); + if (n < len && attrs->split) + n += snprintf(name + n, len - n, "s%u", + attrs->phys.split_subport_number); if (!attrs->split) n = snprintf(name, len, "p%u", attrs->phys.port_number); else n = snprintf(name, len, "p%us%u", attrs->phys.port_number, attrs->phys.split_subport_number); + break; case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: @@ -8677,8 +9381,6 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf, attrs->pci_sf.sf); break; - case DEVLINK_PORT_FLAVOUR_VIRTUAL: - return -EOPNOTSUPP; } if (n >= len) diff --git a/net/core/filter.c b/net/core/filter.c index d81352ca1b5c..d70187ce851b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3241,9 +3241,6 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) - return -ENOTSUPP; - ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; @@ -3255,19 +3252,11 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); - /* SKB_GSO_TCPV4 needs to be changed into - * SKB_GSO_TCPV6. - */ + /* SKB_GSO_TCPV4 needs to be changed into SKB_GSO_TCPV6. */ if (shinfo->gso_type & SKB_GSO_TCPV4) { shinfo->gso_type &= ~SKB_GSO_TCPV4; shinfo->gso_type |= SKB_GSO_TCPV6; } - - /* Due to IPv6 header, MSS needs to be downgraded. */ - skb_decrease_gso_size(shinfo, len_diff); - /* Header must be checked, and gso_segs recomputed. */ - shinfo->gso_type |= SKB_GSO_DODGY; - shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IPV6); @@ -3282,9 +3271,6 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) - return -ENOTSUPP; - ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; @@ -3296,19 +3282,11 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); - /* SKB_GSO_TCPV6 needs to be changed into - * SKB_GSO_TCPV4. - */ + /* SKB_GSO_TCPV6 needs to be changed into SKB_GSO_TCPV4. */ if (shinfo->gso_type & SKB_GSO_TCPV6) { shinfo->gso_type &= ~SKB_GSO_TCPV6; shinfo->gso_type |= SKB_GSO_TCPV4; } - - /* Due to IPv4 header, MSS can be upgraded. */ - skb_increase_gso_size(shinfo, len_diff); - /* Header must be checked, and gso_segs recomputed. */ - shinfo->gso_type |= SKB_GSO_DODGY; - shinfo->gso_segs = 0; } skb->protocol = htons(ETH_P_IP); @@ -3919,6 +3897,34 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { .arg2_type = ARG_ANYTHING, }; +/* XDP_REDIRECT works by a three-step process, implemented in the functions + * below: + * + * 1. The bpf_redirect() and bpf_redirect_map() helpers will lookup the target + * of the redirect and store it (along with some other metadata) in a per-CPU + * struct bpf_redirect_info. + * + * 2. When the program returns the XDP_REDIRECT return code, the driver will + * call xdp_do_redirect() which will use the information in struct + * bpf_redirect_info to actually enqueue the frame into a map type-specific + * bulk queue structure. + * + * 3. Before exiting its NAPI poll loop, the driver will call xdp_do_flush(), + * which will flush all the different bulk queues, thus completing the + * redirect. + * + * Pointers to the map entries will be kept around for this whole sequence of + * steps, protected by RCU. However, there is no top-level rcu_read_lock() in + * the core code; instead, the RCU protection relies on everything happening + * inside a single NAPI poll sequence, which means it's between a pair of calls + * to local_bh_disable()/local_bh_enable(). + * + * The map entries are marked as __rcu and the map code makes sure to + * dereference those pointers with rcu_dereference_check() in a way that works + * for both sections that to hold an rcu_read_lock() and sections that are + * called from NAPI without a separate rcu_read_lock(). The code below does not + * use RCU annotations, but relies on those in the map code. + */ void xdp_do_flush(void) { __dev_flush(); @@ -3927,6 +3933,23 @@ void xdp_do_flush(void) } EXPORT_SYMBOL_GPL(xdp_do_flush); +void bpf_clear_redirect_map(struct bpf_map *map) +{ + struct bpf_redirect_info *ri; + int cpu; + + for_each_possible_cpu(cpu) { + ri = per_cpu_ptr(&bpf_redirect_info, cpu); + /* Avoid polluting remote cacheline due to writes if + * not needed. Once we pass this test, we need the + * cmpxchg() to make sure it hasn't been changed in + * the meantime by remote CPU. + */ + if (unlikely(READ_ONCE(ri->map) == map)) + cmpxchg(&ri->map, map, NULL); + } +} + int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { @@ -3934,6 +3957,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ @@ -3943,7 +3967,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - err = dev_map_enqueue(fwd, xdp, dev); + map = READ_ONCE(ri->map); + if (unlikely(map)) { + WRITE_ONCE(ri->map, NULL); + err = dev_map_enqueue_multi(xdp, dev, map, + ri->flags & BPF_F_EXCLUDE_INGRESS); + } else { + err = dev_map_enqueue(fwd, xdp, dev); + } break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_enqueue(fwd, xdp, dev); @@ -3985,13 +4016,21 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, enum bpf_map_type map_type, u32 map_id) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_map *map; int err; switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: - err = dev_map_generic_redirect(fwd, skb, xdp_prog); + map = READ_ONCE(ri->map); + if (unlikely(map)) { + WRITE_ONCE(ri->map, NULL); + err = dev_map_redirect_multi(dev, skb, xdp_prog, map, + ri->flags & BPF_F_EXCLUDE_INGRESS); + } else { + err = dev_map_generic_redirect(fwd, skb, xdp_prog); + } if (unlikely(err)) goto err; break; @@ -10008,11 +10047,13 @@ out: static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock_reuseport *reuse, struct sock *sk, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { reuse_kern->skb = skb; reuse_kern->sk = sk; reuse_kern->selected_sk = NULL; + reuse_kern->migrating_sk = migrating_sk; reuse_kern->data_end = skb->data + skb_headlen(skb); reuse_kern->hash = hash; reuse_kern->reuseport_id = reuse->reuseport_id; @@ -10021,12 +10062,13 @@ static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { struct sk_reuseport_kern reuse_kern; enum sk_action action; - bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash); + bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash); action = BPF_PROG_RUN(prog, &reuse_kern); if (action == SK_PASS) @@ -10136,6 +10178,8 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, return &sk_reuseport_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &sk_reuseport_load_bytes_relative_proto; + case BPF_FUNC_get_socket_cookie: + return &bpf_get_socket_ptr_cookie_proto; default: return bpf_base_func_proto(func_id); } @@ -10165,6 +10209,14 @@ sk_reuseport_is_valid_access(int off, int size, case offsetof(struct sk_reuseport_md, hash): return size == size_default; + case offsetof(struct sk_reuseport_md, sk): + info->reg_type = PTR_TO_SOCKET; + return size == sizeof(__u64); + + case offsetof(struct sk_reuseport_md, migrating_sk): + info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; + return size == sizeof(__u64); + /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): if (size < sizeof_field(struct sk_buff, protocol)) @@ -10237,6 +10289,14 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, case offsetof(struct sk_reuseport_md, bind_inany): SK_REUSEPORT_LOAD_FIELD(bind_inany); break; + + case offsetof(struct sk_reuseport_md, sk): + SK_REUSEPORT_LOAD_FIELD(sk); + break; + + case offsetof(struct sk_reuseport_md, migrating_sk): + SK_REUSEPORT_LOAD_FIELD(migrating_sk); + break; } return insn - insn_buf; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3ed7c98a98e1..2aadbfc5193b 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -943,8 +943,8 @@ bool __skb_flow_dissect(const struct net *net, int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; - /* Tail taggers don't break flow dissection */ - if (!ops->tail_tag) { + /* Only DSA header taggers break flow dissection */ + if (ops->needed_headroom) { if (ops->flow_dissect) ops->flow_dissect(skb, &proto, &offset); else diff --git a/net/core/neighbour.c b/net/core/neighbour.c index bf774575ad71..53e85c70c6e5 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3142,7 +3142,7 @@ static struct pneigh_entry *pneigh_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; struct pneigh_entry *pn = NULL; - int bucket = state->bucket; + int bucket; state->flags |= NEIGH_SEQ_IS_PNEIGH; for (bucket = 0; bucket <= PNEIGH_HASHMASK; bucket++) { diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 465362a9b55d..5e07acbfd5cd 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -58,3 +58,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll); EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_send_reset); +EXPORT_TRACEPOINT_SYMBOL_GPL(tcp_bad_csum); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index c310c7c1cef7..0a6b04714558 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -36,6 +36,7 @@ #include #include #include +#include /* * We maintain a small pool of fully-sized skbs, to make sure the @@ -389,7 +390,8 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) static atomic_t ip_ident; struct ipv6hdr *ip6h; - WARN_ON_ONCE(!irqs_disabled()); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + WARN_ON_ONCE(!irqs_disabled()); udp_len = len + sizeof(*udph); if (np->ipv6) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 3c4c4c7a0402..5e4eb45b139c 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -17,6 +17,7 @@ #include #include #include /* for __put_page() */ +#include #include @@ -221,6 +222,8 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool, return NULL; } + page->pp_magic |= PP_SIGNATURE; + /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt); @@ -263,6 +266,7 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, put_page(page); continue; } + page->pp_magic |= PP_SIGNATURE; pool->alloc.cache[pool->alloc.count++] = page; /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; @@ -341,6 +345,8 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) DMA_ATTR_SKIP_CPU_SYNC); page_pool_set_dma_addr(page, 0); skip_dma_unmap: + page->pp_magic = 0; + /* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. */ @@ -622,3 +628,25 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid) } } EXPORT_SYMBOL(page_pool_update_nid); + +bool page_pool_return_skb_page(struct page *page) +{ + struct page_pool *pp; + + page = compound_head(page); + if (unlikely(page->pp_magic != PP_SIGNATURE)) + return false; + + pp = page->pp; + + /* Driver set this to memory recycling info. Reset it on recycle. + * This will *not* work for NIC using a split-page memory model. + * The page will be returned to the pool here regardless of the + * 'flipped' fragment being in use or not. + */ + page->pp = NULL; + page_pool_put_full_page(pp, page, false); + + return true; +} +EXPORT_SYMBOL(page_pool_return_skb_page); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 3fba429f1f57..7e258d255e90 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -467,7 +467,7 @@ static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, static int pktgen_device_event(struct notifier_block *, unsigned long, void *); static void pktgen_run_all_threads(struct pktgen_net *pn); static void pktgen_reset_all_threads(struct pktgen_net *pn); -static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn); +static void pktgen_stop_all_threads(struct pktgen_net *pn); static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); @@ -516,14 +516,11 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, data[count - 1] = 0; /* Strip trailing '\n' and terminate string */ if (!strcmp(data, "stop")) - pktgen_stop_all_threads_ifs(pn); - + pktgen_stop_all_threads(pn); else if (!strcmp(data, "start")) pktgen_run_all_threads(pn); - else if (!strcmp(data, "reset")) pktgen_reset_all_threads(pn); - else return -EINVAL; @@ -3027,20 +3024,25 @@ static void pktgen_run(struct pktgen_thread *t) t->control &= ~(T_STOP); } -static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn) +static void pktgen_handle_all_threads(struct pktgen_net *pn, u32 flags) { struct pktgen_thread *t; - func_enter(); - mutex_lock(&pktgen_thread_lock); list_for_each_entry(t, &pn->pktgen_threads, th_list) - t->control |= T_STOP; + t->control |= (flags); mutex_unlock(&pktgen_thread_lock); } +static void pktgen_stop_all_threads(struct pktgen_net *pn) +{ + func_enter(); + + pktgen_handle_all_threads(pn, T_STOP); +} + static int thread_is_running(const struct pktgen_thread *t) { const struct pktgen_dev *pkt_dev; @@ -3103,16 +3105,9 @@ static int pktgen_wait_all_threads_run(struct pktgen_net *pn) static void pktgen_run_all_threads(struct pktgen_net *pn) { - struct pktgen_thread *t; - func_enter(); - mutex_lock(&pktgen_thread_lock); - - list_for_each_entry(t, &pn->pktgen_threads, th_list) - t->control |= (T_RUN); - - mutex_unlock(&pktgen_thread_lock); + pktgen_handle_all_threads(pn, T_RUN); /* Propagate thread->control */ schedule_timeout_interruptible(msecs_to_jiffies(125)); @@ -3122,16 +3117,9 @@ static void pktgen_run_all_threads(struct pktgen_net *pn) static void pktgen_reset_all_threads(struct pktgen_net *pn) { - struct pktgen_thread *t; - func_enter(); - mutex_lock(&pktgen_thread_lock); - - list_for_each_entry(t, &pn->pktgen_threads, th_list) - t->control |= (T_REMDEVALL); - - mutex_unlock(&pktgen_thread_lock); + pktgen_handle_all_threads(pn, T_REMDEVALL); /* Propagate thread->control */ schedule_timeout_interruptible(msecs_to_jiffies(125)); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index ec931b080156..f6af3e74fc44 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -9,7 +9,7 @@ * Authors: Alexey Kuznetsov, * * Fixes: - * Vitaly E. Lavrov RTA_OK arithmetics was wrong. + * Vitaly E. Lavrov RTA_OK arithmetic was wrong. */ #include @@ -234,7 +234,7 @@ unlock: * @msgtype: rtnetlink message type * @doit: Function pointer called for each request message * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message - * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions + * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions * * Like rtnl_register, but for use by removable modules. */ @@ -254,7 +254,7 @@ EXPORT_SYMBOL_GPL(rtnl_register_module); * @msgtype: rtnetlink message type * @doit: Function pointer called for each request message * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message - * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions + * @flags: rtnl_link_flags to modify behaviour of doit/dumpit functions * * Registers the specified function pointers (at least one of them has * to be non-NULL) to be called whenever a request message for the @@ -376,12 +376,12 @@ int __rtnl_link_register(struct rtnl_link_ops *ops) if (rtnl_link_ops_get(ops->kind)) return -EEXIST; - /* The check for setup is here because if ops + /* The check for alloc/setup is here because if ops * does not have that filled up, it is not possible * to use the ops for creating device. So do not * fill up dellink as well. That disables rtnl_dellink. */ - if (ops->setup && !ops->dellink) + if ((ops->alloc || ops->setup) && !ops->dellink) ops->dellink = unregister_netdevice_queue; list_add_tail(&ops->list, &link_ops); @@ -543,7 +543,9 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family) { const struct rtnl_af_ops *ops; - list_for_each_entry_rcu(ops, &rtnl_af_ops, list) { + ASSERT_RTNL(); + + list_for_each_entry(ops, &rtnl_af_ops, list) { if (ops->family == family) return ops; } @@ -1819,6 +1821,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, if (rtnl_fill_prop_list(skb, dev)) goto nla_put_failure; + if (dev->dev.parent && + nla_put_string(skb, IFLA_PARENT_DEV_NAME, + dev_name(dev->dev.parent))) + goto nla_put_failure; + + if (dev->dev.parent && dev->dev.parent->bus && + nla_put_string(skb, IFLA_PARENT_DEV_BUS_NAME, + dev->dev.parent->bus->name)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -1878,6 +1890,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PERM_ADDRESS] = { .type = NLA_REJECT }, [IFLA_PROTO_DOWN_REASON] = { .type = NLA_NESTED }, [IFLA_NEW_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1), + [IFLA_PARENT_DEV_NAME] = { .type = NLA_NUL_STRING }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -2274,27 +2287,18 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { const struct rtnl_af_ops *af_ops; - rcu_read_lock(); af_ops = rtnl_af_lookup(nla_type(af)); - if (!af_ops) { - rcu_read_unlock(); + if (!af_ops) return -EAFNOSUPPORT; - } - if (!af_ops->set_link_af) { - rcu_read_unlock(); + if (!af_ops->set_link_af) return -EOPNOTSUPP; - } if (af_ops->validate_link_af) { err = af_ops->validate_link_af(dev, af); - if (err < 0) { - rcu_read_unlock(); + if (err < 0) return err; - } } - - rcu_read_unlock(); } } @@ -2574,7 +2578,7 @@ static int do_set_proto_down(struct net_device *dev, if (nl_proto_down) { proto_down = nla_get_u8(nl_proto_down); - /* Dont turn off protodown if there are active reasons */ + /* Don't turn off protodown if there are active reasons */ if (!proto_down && dev->proto_down_reason) { NL_SET_ERR_MSG(extack, "Cannot clear protodown, active reasons"); return -EBUSY; @@ -2868,17 +2872,12 @@ static int do_setlink(const struct sk_buff *skb, nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { const struct rtnl_af_ops *af_ops; - rcu_read_lock(); - BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af)))); err = af_ops->set_link_af(dev, af, extack); - if (err < 0) { - rcu_read_unlock(); + if (err < 0) goto errout; - } - rcu_read_unlock(); status |= DO_SETLINK_NOTIFY; } } @@ -3177,8 +3176,17 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, return ERR_PTR(-EINVAL); } - dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type, - ops->setup, num_tx_queues, num_rx_queues); + if (ops->alloc) { + dev = ops->alloc(tb, ifname, name_assign_type, + num_tx_queues, num_rx_queues); + if (IS_ERR(dev)) + return dev; + } else { + dev = alloc_netdev_mqs(ops->priv_size, ifname, + name_assign_type, ops->setup, + num_tx_queues, num_rx_queues); + } + if (!dev) return ERR_PTR(-ENOMEM); @@ -3411,7 +3419,7 @@ replay: return -EOPNOTSUPP; } - if (!ops->setup) + if (!ops->alloc && !ops->setup) return -EOPNOTSUPP; if (!ifname[0]) { @@ -3939,12 +3947,12 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm, * implement its own handler for this. */ if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) { - pr_info("%s: FDB only supports static addresses\n", dev->name); + netdev_info(dev, "default FDB implementation only supports local addresses\n"); return err; } if (vid) { - pr_info("%s: vlans aren't supported yet for dev_uc|mc_add()\n", dev->name); + netdev_info(dev, "vlans aren't supported yet for dev_uc|mc_add()\n"); return err; } @@ -4078,7 +4086,7 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm, * implement its own handler for this. */ if (!(ndm->ndm_state & NUD_PERMANENT)) { - pr_info("%s: FDB only supports static addresses\n", dev->name); + netdev_info(dev, "default FDB implementation only supports local addresses\n"); return err; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 06ced658959e..8145e01f6206 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -70,6 +70,7 @@ #include #include #include +#include #include #include @@ -646,10 +647,13 @@ static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; - if (skb->head_frag) + if (skb->head_frag) { + if (skb_pp_recycle(skb, head)) + return; skb_free_frag(head); - else + } else { kfree(head); + } } static void skb_release_data(struct sk_buff *skb) @@ -665,7 +669,7 @@ static void skb_release_data(struct sk_buff *skb) skb_zcopy_clear(skb, true); for (i = 0; i < shinfo->nr_frags; i++) - __skb_frag_unref(&shinfo->frags[i]); + __skb_frag_unref(&shinfo->frags[i], skb->pp_recycle); if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); @@ -1048,6 +1052,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) n->nohdr = 0; n->peeked = 0; C(pfmemalloc); + C(pp_recycle); n->destructor = NULL; C(tail); C(end); @@ -1291,7 +1296,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) } spin_unlock_irqrestore(&q->lock, flags); - sk->sk_error_report(sk); + sk_error_report(sk); release: consume_skb(skb); @@ -3499,7 +3504,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) fragto = &skb_shinfo(tgt)->frags[merge]; skb_frag_size_add(fragto, skb_frag_size(fragfrom)); - __skb_frag_unref(fragfrom); + __skb_frag_unref(fragfrom, skb->pp_recycle); } /* Reposition in the original skb */ @@ -4682,7 +4687,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); @@ -4713,7 +4718,7 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk) sk->sk_err = 0; if (skb_next) - sk->sk_error_report(sk); + sk_error_report(sk); return skb; } @@ -5289,6 +5294,13 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; + /* The page pool signature of struct page will eventually figure out + * which pages can be recycled or not but for now let's prohibit slab + * allocated and page_pool allocated SKBs from being coalesced. + */ + if (to->pp_recycle != from->pp_recycle) + return false; + if (len <= skb_tailroom(to)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 43ce17a6a585..9b6160a191f8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -399,29 +399,6 @@ out: } EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter); -int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, - long timeo, int *err) -{ - DEFINE_WAIT_FUNC(wait, woken_wake_function); - int ret = 0; - - if (sk->sk_shutdown & RCV_SHUTDOWN) - return 1; - - if (!timeo) - return ret; - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - ret = sk_wait_event(sk, &timeo, - !list_empty(&psock->ingress_msg) || - !skb_queue_empty(&sk->sk_receive_queue), &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - return ret; -} -EXPORT_SYMBOL_GPL(sk_msg_wait_data); - /* Receive sk_msg from psock->ingress_msg to @msg. */ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags) @@ -601,6 +578,12 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return sk_psock_skb_ingress(psock, skb); } +static void sock_drop(struct sock *sk, struct sk_buff *skb) +{ + sk_drops_add(sk, skb); + kfree_skb(skb); +} + static void sk_psock_backlog(struct work_struct *work) { struct sk_psock *psock = container_of(work, struct sk_psock, work); @@ -640,7 +623,7 @@ start: /* Hard errors break pipe and stop xmit. */ sk_psock_report_error(psock, ret ? -ret : EPIPE); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); - kfree_skb(skb); + sock_drop(psock->sk, skb); goto end; } off += ret; @@ -731,7 +714,7 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock) while ((skb = skb_dequeue(&psock->ingress_skb)) != NULL) { skb_bpf_redirect_clear(skb); - kfree_skb(skb); + sock_drop(psock->sk, skb); } __sk_psock_purge_ingress_msg(psock); } @@ -847,7 +830,7 @@ out: } EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); -static void sk_psock_skb_redirect(struct sk_buff *skb) +static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) { struct sk_psock *psock_other; struct sock *sk_other; @@ -857,8 +840,8 @@ static void sk_psock_skb_redirect(struct sk_buff *skb) * return code, but then didn't set a redirect interface. */ if (unlikely(!sk_other)) { - kfree_skb(skb); - return; + sock_drop(from->sk, skb); + return -EIO; } psock_other = sk_psock(sk_other); /* This error indicates the socket is being torn down or had another @@ -866,26 +849,30 @@ static void sk_psock_skb_redirect(struct sk_buff *skb) * a socket that is in this state so we drop the skb. */ if (!psock_other || sock_flag(sk_other, SOCK_DEAD)) { - kfree_skb(skb); - return; + skb_bpf_redirect_clear(skb); + sock_drop(from->sk, skb); + return -EIO; } spin_lock_bh(&psock_other->ingress_lock); if (!sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) { spin_unlock_bh(&psock_other->ingress_lock); - kfree_skb(skb); - return; + skb_bpf_redirect_clear(skb); + sock_drop(from->sk, skb); + return -EIO; } skb_queue_tail(&psock_other->ingress_skb, skb); schedule_work(&psock_other->work); spin_unlock_bh(&psock_other->ingress_lock); + return 0; } -static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int verdict) +static void sk_psock_tls_verdict_apply(struct sk_buff *skb, + struct sk_psock *from, int verdict) { switch (verdict) { case __SK_REDIRECT: - sk_psock_skb_redirect(skb); + sk_psock_skb_redirect(from, skb); break; case __SK_PASS: case __SK_DROP: @@ -909,20 +896,21 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } - sk_psock_tls_verdict_apply(skb, psock->sk, ret); + sk_psock_tls_verdict_apply(skb, psock, ret); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); -static void sk_psock_verdict_apply(struct sk_psock *psock, - struct sk_buff *skb, int verdict) +static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, + int verdict) { struct sock *sk_other; - int err = -EIO; + int err = 0; switch (verdict) { case __SK_PASS: + err = -EIO; sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { @@ -945,18 +933,25 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { skb_queue_tail(&psock->ingress_skb, skb); schedule_work(&psock->work); + err = 0; } spin_unlock_bh(&psock->ingress_lock); + if (err < 0) { + skb_bpf_redirect_clear(skb); + goto out_free; + } } break; case __SK_REDIRECT: - sk_psock_skb_redirect(skb); + err = sk_psock_skb_redirect(psock, skb); break; case __SK_DROP: default: out_free: - kfree_skb(skb); + sock_drop(psock->sk, skb); } + + return err; } static void sk_psock_write_space(struct sock *sk) @@ -988,7 +983,7 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) sk = strp->sk; psock = sk_psock(sk); if (unlikely(!psock)) { - kfree_skb(skb); + sock_drop(sk, skb); goto out; } prog = READ_ONCE(psock->progs.stream_verdict); @@ -1109,7 +1104,7 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, psock = sk_psock(sk); if (unlikely(!psock)) { len = 0; - kfree_skb(skb); + sock_drop(sk, skb); goto out; } prog = READ_ONCE(psock->progs.stream_verdict); @@ -1123,7 +1118,8 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } - sk_psock_verdict_apply(psock, skb, ret); + if (sk_psock_verdict_apply(psock, skb, ret) < 0) + len = 0; out: rcu_read_unlock(); return len; diff --git a/net/core/sock.c b/net/core/sock.c index 946888afef88..ba1c0f75cd45 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -331,6 +331,22 @@ int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(__sk_backlog_rcv); +void sk_error_report(struct sock *sk) +{ + sk->sk_error_report(sk); + + switch (sk->sk_family) { + case AF_INET: + fallthrough; + case AF_INET6: + trace_inet_sk_error_report(sk); + break; + default: + break; + } +} +EXPORT_SYMBOL(sk_error_report); + static int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; @@ -776,6 +792,58 @@ void sock_enable_timestamps(struct sock *sk) } EXPORT_SYMBOL(sock_enable_timestamps); +void sock_set_timestamp(struct sock *sk, int optname, bool valbool) +{ + switch (optname) { + case SO_TIMESTAMP_OLD: + __sock_set_timestamps(sk, valbool, false, false); + break; + case SO_TIMESTAMP_NEW: + __sock_set_timestamps(sk, valbool, true, false); + break; + case SO_TIMESTAMPNS_OLD: + __sock_set_timestamps(sk, valbool, false, true); + break; + case SO_TIMESTAMPNS_NEW: + __sock_set_timestamps(sk, valbool, true, true); + break; + } +} + +int sock_set_timestamping(struct sock *sk, int optname, int val) +{ + if (val & ~SOF_TIMESTAMPING_MASK) + return -EINVAL; + + if (val & SOF_TIMESTAMPING_OPT_ID && + !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) { + if ((1 << sk->sk_state) & + (TCPF_CLOSE | TCPF_LISTEN)) + return -EINVAL; + sk->sk_tskey = tcp_sk(sk)->snd_una; + } else { + sk->sk_tskey = 0; + } + } + + if (val & SOF_TIMESTAMPING_OPT_STATS && + !(val & SOF_TIMESTAMPING_OPT_TSONLY)) + return -EINVAL; + + sk->sk_tsflags = val; + sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); + + if (val & SOF_TIMESTAMPING_RX_SOFTWARE) + sock_enable_timestamp(sk, + SOCK_TIMESTAMPING_RX_SOFTWARE); + else + sock_disable_timestamp(sk, + (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); + return 0; +} + void sock_set_keepalive(struct sock *sk) { lock_sock(sk); @@ -997,54 +1065,15 @@ set_sndbuf: break; case SO_TIMESTAMP_OLD: - __sock_set_timestamps(sk, valbool, false, false); - break; case SO_TIMESTAMP_NEW: - __sock_set_timestamps(sk, valbool, true, false); - break; case SO_TIMESTAMPNS_OLD: - __sock_set_timestamps(sk, valbool, false, true); - break; case SO_TIMESTAMPNS_NEW: - __sock_set_timestamps(sk, valbool, true, true); + sock_set_timestamp(sk, valbool, optname); break; + case SO_TIMESTAMPING_NEW: case SO_TIMESTAMPING_OLD: - if (val & ~SOF_TIMESTAMPING_MASK) { - ret = -EINVAL; - break; - } - - if (val & SOF_TIMESTAMPING_OPT_ID && - !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { - if (sk->sk_protocol == IPPROTO_TCP && - sk->sk_type == SOCK_STREAM) { - if ((1 << sk->sk_state) & - (TCPF_CLOSE | TCPF_LISTEN)) { - ret = -EINVAL; - break; - } - sk->sk_tskey = tcp_sk(sk)->snd_una; - } else { - sk->sk_tskey = 0; - } - } - - if (val & SOF_TIMESTAMPING_OPT_STATS && - !(val & SOF_TIMESTAMPING_OPT_TSONLY)) { - ret = -EINVAL; - break; - } - - sk->sk_tsflags = val; - sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW); - - if (val & SOF_TIMESTAMPING_RX_SOFTWARE) - sock_enable_timestamp(sk, - SOCK_TIMESTAMPING_RX_SOFTWARE); - else - sock_disable_timestamp(sk, - (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); + ret = sock_set_timestamping(sk, optname, val); break; case SO_RCVLOWAT: @@ -1622,6 +1651,13 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_bound_dev_if; break; + case SO_NETNS_COOKIE: + lv = sizeof(u64); + if (len != lv) + return -EINVAL; + v.val64 = sock_net(sk)->net_cookie; + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 6f1b82b8ad49..60decd6420ca 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -48,7 +48,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) bpf_map_init_from_attr(&stab->map, attr); raw_spin_lock_init(&stab->lock); - stab->sks = bpf_map_area_alloc(stab->map.max_entries * + stab->sks = bpf_map_area_alloc((u64) stab->map.max_entries * sizeof(struct sock *), stab->map.numa_node); if (!stab->sks) { diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index b065f0a103ed..3f00a28fe762 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -6,6 +6,7 @@ * selecting the socket index from the array of available sockets. */ +#include #include #include #include @@ -17,6 +18,74 @@ DEFINE_SPINLOCK(reuseport_lock); static DEFINE_IDA(reuseport_ida); +static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, + struct sock_reuseport *reuse, bool bind_inany); + +static int reuseport_sock_index(struct sock *sk, + const struct sock_reuseport *reuse, + bool closed) +{ + int left, right; + + if (!closed) { + left = 0; + right = reuse->num_socks; + } else { + left = reuse->max_socks - reuse->num_closed_socks; + right = reuse->max_socks; + } + + for (; left < right; left++) + if (reuse->socks[left] == sk) + return left; + return -1; +} + +static void __reuseport_add_sock(struct sock *sk, + struct sock_reuseport *reuse) +{ + reuse->socks[reuse->num_socks] = sk; + /* paired with smp_rmb() in reuseport_(select|migrate)_sock() */ + smp_wmb(); + reuse->num_socks++; +} + +static bool __reuseport_detach_sock(struct sock *sk, + struct sock_reuseport *reuse) +{ + int i = reuseport_sock_index(sk, reuse, false); + + if (i == -1) + return false; + + reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; + reuse->num_socks--; + + return true; +} + +static void __reuseport_add_closed_sock(struct sock *sk, + struct sock_reuseport *reuse) +{ + reuse->socks[reuse->max_socks - reuse->num_closed_socks - 1] = sk; + /* paired with READ_ONCE() in inet_csk_bind_conflict() */ + WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks + 1); +} + +static bool __reuseport_detach_closed_sock(struct sock *sk, + struct sock_reuseport *reuse) +{ + int i = reuseport_sock_index(sk, reuse, true); + + if (i == -1) + return false; + + reuse->socks[i] = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; + /* paired with READ_ONCE() in inet_csk_bind_conflict() */ + WRITE_ONCE(reuse->num_closed_socks, reuse->num_closed_socks - 1); + + return true; +} static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { @@ -49,6 +118,12 @@ int reuseport_alloc(struct sock *sk, bool bind_inany) reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (reuse) { + if (reuse->num_closed_socks) { + /* sk was shutdown()ed before */ + ret = reuseport_resurrect(sk, reuse, NULL, bind_inany); + goto out; + } + /* Only set reuse->bind_inany if the bind_inany is true. * Otherwise, it will overwrite the reuse->bind_inany * which was set by the bind/hash path. @@ -72,9 +147,9 @@ int reuseport_alloc(struct sock *sk, bool bind_inany) } reuse->reuseport_id = id; + reuse->bind_inany = bind_inany; reuse->socks[0] = sk; reuse->num_socks = 1; - reuse->bind_inany = bind_inany; rcu_assign_pointer(sk->sk_reuseport_cb, reuse); out: @@ -90,14 +165,30 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) u32 more_socks_size, i; more_socks_size = reuse->max_socks * 2U; - if (more_socks_size > U16_MAX) + if (more_socks_size > U16_MAX) { + if (reuse->num_closed_socks) { + /* Make room by removing a closed sk. + * The child has already been migrated. + * Only reqsk left at this point. + */ + struct sock *sk; + + sk = reuse->socks[reuse->max_socks - reuse->num_closed_socks]; + RCU_INIT_POINTER(sk->sk_reuseport_cb, NULL); + __reuseport_detach_closed_sock(sk, reuse); + + return reuse; + } + return NULL; + } more_reuse = __reuseport_alloc(more_socks_size); if (!more_reuse) return NULL; more_reuse->num_socks = reuse->num_socks; + more_reuse->num_closed_socks = reuse->num_closed_socks; more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; @@ -105,9 +196,13 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); + memcpy(more_reuse->socks + + (more_reuse->max_socks - more_reuse->num_closed_socks), + reuse->socks + (reuse->max_socks - reuse->num_closed_socks), + reuse->num_closed_socks * sizeof(struct sock *)); more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts); - for (i = 0; i < reuse->num_socks; ++i) + for (i = 0; i < reuse->max_socks; ++i) rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, more_reuse); @@ -152,13 +247,21 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb, - lockdep_is_held(&reuseport_lock)); + lockdep_is_held(&reuseport_lock)); + if (old_reuse && old_reuse->num_closed_socks) { + /* sk was shutdown()ed before */ + int err = reuseport_resurrect(sk, old_reuse, reuse, reuse->bind_inany); + + spin_unlock_bh(&reuseport_lock); + return err; + } + if (old_reuse && old_reuse->num_socks != 1) { spin_unlock_bh(&reuseport_lock); return -EBUSY; } - if (reuse->num_socks == reuse->max_socks) { + if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); if (!reuse) { spin_unlock_bh(&reuseport_lock); @@ -166,10 +269,7 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) } } - reuse->socks[reuse->num_socks] = sk; - /* paired with smp_rmb() in reuseport_select_sock() */ - smp_wmb(); - reuse->num_socks++; + __reuseport_add_sock(sk, reuse); rcu_assign_pointer(sk->sk_reuseport_cb, reuse); spin_unlock_bh(&reuseport_lock); @@ -180,15 +280,77 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) } EXPORT_SYMBOL(reuseport_add_sock); +static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, + struct sock_reuseport *reuse, bool bind_inany) +{ + if (old_reuse == reuse) { + /* If sk was in the same reuseport group, just pop sk out of + * the closed section and push sk into the listening section. + */ + __reuseport_detach_closed_sock(sk, old_reuse); + __reuseport_add_sock(sk, old_reuse); + return 0; + } + + if (!reuse) { + /* In bind()/listen() path, we cannot carry over the eBPF prog + * for the shutdown()ed socket. In setsockopt() path, we should + * not change the eBPF prog of listening sockets by attaching a + * prog to the shutdown()ed socket. Thus, we will allocate a new + * reuseport group and detach sk from the old group. + */ + int id; + + reuse = __reuseport_alloc(INIT_SOCKS); + if (!reuse) + return -ENOMEM; + + id = ida_alloc(&reuseport_ida, GFP_ATOMIC); + if (id < 0) { + kfree(reuse); + return id; + } + + reuse->reuseport_id = id; + reuse->bind_inany = bind_inany; + } else { + /* Move sk from the old group to the new one if + * - all the other listeners in the old group were close()d or + * shutdown()ed, and then sk2 has listen()ed on the same port + * OR + * - sk listen()ed without bind() (or with autobind), was + * shutdown()ed, and then listen()s on another port which + * sk2 listen()s on. + */ + if (reuse->num_socks + reuse->num_closed_socks == reuse->max_socks) { + reuse = reuseport_grow(reuse); + if (!reuse) + return -ENOMEM; + } + } + + __reuseport_detach_closed_sock(sk, old_reuse); + __reuseport_add_sock(sk, reuse); + rcu_assign_pointer(sk->sk_reuseport_cb, reuse); + + if (old_reuse->num_socks + old_reuse->num_closed_socks == 0) + call_rcu(&old_reuse->rcu, reuseport_free_rcu); + + return 0; +} + void reuseport_detach_sock(struct sock *sk) { struct sock_reuseport *reuse; - int i; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); + /* reuseport_grow() has detached a closed sk */ + if (!reuse) + goto out; + /* Notify the bpf side. The sk may be added to a sockarray * map. If so, sockarray logic will remove it from the map. * @@ -201,19 +363,52 @@ void reuseport_detach_sock(struct sock *sk) rcu_assign_pointer(sk->sk_reuseport_cb, NULL); - for (i = 0; i < reuse->num_socks; i++) { - if (reuse->socks[i] == sk) { - reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; - reuse->num_socks--; - if (reuse->num_socks == 0) - call_rcu(&reuse->rcu, reuseport_free_rcu); - break; - } - } + if (!__reuseport_detach_closed_sock(sk, reuse)) + __reuseport_detach_sock(sk, reuse); + + if (reuse->num_socks + reuse->num_closed_socks == 0) + call_rcu(&reuse->rcu, reuseport_free_rcu); + +out: spin_unlock_bh(&reuseport_lock); } EXPORT_SYMBOL(reuseport_detach_sock); +void reuseport_stop_listen_sock(struct sock *sk) +{ + if (sk->sk_protocol == IPPROTO_TCP) { + struct sock_reuseport *reuse; + struct bpf_prog *prog; + + spin_lock_bh(&reuseport_lock); + + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + prog = rcu_dereference_protected(reuse->prog, + lockdep_is_held(&reuseport_lock)); + + if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req || + (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) { + /* Migration capable, move sk from the listening section + * to the closed section. + */ + bpf_sk_reuseport_detach(sk); + + __reuseport_detach_sock(sk, reuse); + __reuseport_add_closed_sock(sk, reuse); + + spin_unlock_bh(&reuseport_lock); + return; + } + + spin_unlock_bh(&reuseport_lock); + } + + /* Not capable to do migration, detach immediately */ + reuseport_detach_sock(sk); +} +EXPORT_SYMBOL(reuseport_stop_listen_sock); + static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, struct bpf_prog *prog, struct sk_buff *skb, int hdr_len) @@ -244,6 +439,23 @@ static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, return reuse->socks[index]; } +static struct sock *reuseport_select_sock_by_hash(struct sock_reuseport *reuse, + u32 hash, u16 num_socks) +{ + int i, j; + + i = j = reciprocal_scale(hash, num_socks); + while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) { + i++; + if (i >= num_socks) + i = 0; + if (i == j) + return NULL; + } + + return reuse->socks[i]; +} + /** * reuseport_select_sock - Select a socket from an SO_REUSEPORT group. * @sk: First socket in the group. @@ -274,32 +486,21 @@ struct sock *reuseport_select_sock(struct sock *sk, prog = rcu_dereference(reuse->prog); socks = READ_ONCE(reuse->num_socks); if (likely(socks)) { - /* paired with smp_wmb() in reuseport_add_sock() */ + /* paired with smp_wmb() in __reuseport_add_sock() */ smp_rmb(); if (!prog || !skb) goto select_by_hash; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) - sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash); + sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, NULL, hash); else sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len); select_by_hash: /* no bpf or invalid bpf result: fall back to hash usage */ - if (!sk2) { - int i, j; - - i = j = reciprocal_scale(hash, socks); - while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) { - i++; - if (i >= socks) - i = 0; - if (i == j) - goto out; - } - sk2 = reuse->socks[i]; - } + if (!sk2) + sk2 = reuseport_select_sock_by_hash(reuse, hash, socks); } out: @@ -308,14 +509,90 @@ out: } EXPORT_SYMBOL(reuseport_select_sock); +/** + * reuseport_migrate_sock - Select a socket from an SO_REUSEPORT group. + * @sk: close()ed or shutdown()ed socket in the group. + * @migrating_sk: ESTABLISHED/SYN_RECV full socket in the accept queue or + * NEW_SYN_RECV request socket during 3WHS. + * @skb: skb to run through BPF filter. + * Returns a socket (with sk_refcnt +1) that should accept the child socket + * (or NULL on error). + */ +struct sock *reuseport_migrate_sock(struct sock *sk, + struct sock *migrating_sk, + struct sk_buff *skb) +{ + struct sock_reuseport *reuse; + struct sock *nsk = NULL; + bool allocated = false; + struct bpf_prog *prog; + u16 socks; + u32 hash; + + rcu_read_lock(); + + reuse = rcu_dereference(sk->sk_reuseport_cb); + if (!reuse) + goto out; + + socks = READ_ONCE(reuse->num_socks); + if (unlikely(!socks)) + goto failure; + + /* paired with smp_wmb() in __reuseport_add_sock() */ + smp_rmb(); + + hash = migrating_sk->sk_hash; + prog = rcu_dereference(reuse->prog); + if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) { + if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req) + goto select_by_hash; + goto failure; + } + + if (!skb) { + skb = alloc_skb(0, GFP_ATOMIC); + if (!skb) + goto failure; + allocated = true; + } + + nsk = bpf_run_sk_reuseport(reuse, sk, prog, skb, migrating_sk, hash); + + if (allocated) + kfree_skb(skb); + +select_by_hash: + if (!nsk) + nsk = reuseport_select_sock_by_hash(reuse, hash, socks); + + if (IS_ERR_OR_NULL(nsk) || unlikely(!refcount_inc_not_zero(&nsk->sk_refcnt))) { + nsk = NULL; + goto failure; + } + +out: + rcu_read_unlock(); + return nsk; + +failure: + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); + goto out; +} +EXPORT_SYMBOL(reuseport_migrate_sock); + int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; - if (sk_unhashed(sk) && sk->sk_reuseport) { - int err = reuseport_alloc(sk, false); + if (sk_unhashed(sk)) { + int err; + if (!sk->sk_reuseport) + return -EINVAL; + + err = reuseport_alloc(sk, false); if (err) return err; } else if (!rcu_access_pointer(sk->sk_reuseport_cb)) { @@ -341,13 +618,24 @@ int reuseport_detach_prog(struct sock *sk) struct sock_reuseport *reuse; struct bpf_prog *old_prog; - if (!rcu_access_pointer(sk->sk_reuseport_cb)) - return sk->sk_reuseport ? -ENOENT : -EINVAL; - old_prog = NULL; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); + + /* reuse must be checked after acquiring the reuseport_lock + * because reuseport_grow() can detach a closed sk. + */ + if (!reuse) { + spin_unlock_bh(&reuseport_lock); + return sk->sk_reuseport ? -ENOENT : -EINVAL; + } + + if (sk_unhashed(sk) && reuse->num_closed_socks) { + spin_unlock_bh(&reuseport_lock); + return -ENOENT; + } + old_prog = rcu_replace_pointer(reuse->prog, old_prog, lockdep_is_held(&reuseport_lock)); spin_unlock_bh(&reuseport_lock); diff --git a/net/core/xdp.c b/net/core/xdp.c index 858276e72c68..cc92ccb38432 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -113,8 +113,13 @@ static void mem_allocator_disconnect(void *allocator) void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) { struct xdp_mem_allocator *xa; + int type = xdp_rxq->mem.type; int id = xdp_rxq->mem.id; + /* Reset mem info to defaults */ + xdp_rxq->mem.id = 0; + xdp_rxq->mem.type = 0; + if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return; @@ -123,7 +128,7 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) if (id == 0) return; - if (xdp_rxq->mem.type == MEM_TYPE_PAGE_POOL) { + if (type == MEM_TYPE_PAGE_POOL) { rcu_read_lock(); xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); @@ -144,10 +149,6 @@ void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) xdp_rxq->reg_state = REG_STATE_UNREGISTERED; xdp_rxq->dev = NULL; - - /* Reset mem info to defaults */ - xdp_rxq->mem.id = 0; - xdp_rxq->mem.type = 0; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg); @@ -584,3 +585,31 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, return __xdp_build_skb_from_frame(xdpf, skb, dev); } EXPORT_SYMBOL_GPL(xdp_build_skb_from_frame); + +struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf) +{ + unsigned int headroom, totalsize; + struct xdp_frame *nxdpf; + struct page *page; + void *addr; + + headroom = xdpf->headroom + sizeof(*xdpf); + totalsize = headroom + xdpf->len; + + if (unlikely(totalsize > PAGE_SIZE)) + return NULL; + page = dev_alloc_page(); + if (!page) + return NULL; + addr = page_to_virt(page); + + memcpy(addr, xdpf, totalsize); + + nxdpf = addr; + nxdpf->data = addr + headroom; + nxdpf->frame_sz = PAGE_SIZE; + nxdpf->mem.type = MEM_TYPE_PAGE_ORDER0; + nxdpf->mem.id = 0; + + return nxdpf; +} diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 653e3bc9c87b..b441ab330fd3 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1381,7 +1381,7 @@ static int dcbnl_notify(struct net_device *dev, int event, int cmd, skb = dcbnl_newmsg(event, cmd, portid, seq, 0, &nlh); if (!skb) - return -ENOBUFS; + return -ENOMEM; if (dcbx_ver == DCB_CAP_DCBX_VER_IEEE) err = dcbnl_ieee_fill(skb, dev); @@ -1781,7 +1781,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, portid, nlh->nlmsg_seq, nlh->nlmsg_flags, &reply_nlh); if (!reply_skb) - return -ENOBUFS; + return -ENOMEM; ret = fn->cb(netdev, nlh, nlh->nlmsg_seq, tb, reply_skb); if (ret < 0) { @@ -2075,8 +2075,6 @@ EXPORT_SYMBOL(dcb_ieee_getapp_default_prio_mask); static int __init dcbnl_init(void) { - INIT_LIST_HEAD(&dcb_app_list); - rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL, 0); rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL, 0); diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index e2a337fa9ff7..92a8c6bea316 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -688,6 +688,7 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) /** * tfrc_invert_loss_event_rate - Compute p so that 10^6 corresponds to 100% + * @loss_event_rate: loss event rate to invert * When @loss_event_rate is large, there is a chance that p is truncated to 0. * To avoid re-entering slow-start in that case, we set p = TFRC_SMALLEST_P > 0. */ diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index ffc601a3b329..0ea29270d7e5 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -329,7 +329,7 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) __DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS); sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); dccp_done(sk); } else @@ -356,7 +356,7 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) inet = inet_sk(sk); if (!sock_owned_by_user(sk) && inet->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else /* Only an error on timeout */ sk->sk_err_soft = err; out: @@ -977,7 +977,6 @@ static const struct net_protocol dccp_v4_protocol = { .handler = dccp_v4_rcv, .err_handler = dccp_v4_err, .no_policy = 1, - .netns_ok = 1, .icmp_strict_tag_validation = 1, }; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 6f5304db5a67..fa663518fa0e 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -172,7 +172,7 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, * Wake people up to see the error * (see connect in sock.c) */ - sk->sk_error_report(sk); + sk_error_report(sk); dccp_done(sk); } else sk->sk_err_soft = err; @@ -181,7 +181,7 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else sk->sk_err_soft = err; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 6d705d90c614..7eb0fb231940 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -302,7 +302,7 @@ int dccp_disconnect(struct sock *sk, int flags) WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); - sk->sk_error_report(sk); + sk_error_report(sk); return 0; } diff --git a/net/dccp/timer.c b/net/dccp/timer.c index db768f223ef7..27a3b37acd2e 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -20,7 +20,7 @@ int sysctl_dccp_retries2 __read_mostly = TCP_RETR2; static void dccp_write_err(struct sock *sk) { sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; - sk->sk_error_report(sk); + sk_error_report(sk); dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_done(sk); diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index 1a12912b88d6..7ab788f41a3f 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -870,7 +870,7 @@ int dn_nsp_backlog_rcv(struct sock *sk, struct sk_buff *skb) /* * Read out ack data here, this applies equally - * to data, other data, link serivce and both + * to data, other data, link service and both * ack data and ack otherdata. */ dn_process_ack(sk, skb, other); diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 00f2ed721ec1..eadc89583168 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -179,7 +179,7 @@ static void dn_nsp_rtt(struct sock *sk, long rtt) scp->nsp_srtt = 1; /* - * Add new rtt varience to smoothed varience + * Add new rtt variance to smoothed varience */ delta >>= 1; rttvar += ((((delta>0)?(delta):(-delta)) - rttvar) >> 2); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 32b1bed8ae51..729d3de6020d 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -604,7 +604,7 @@ drop_it: static int dn_route_discard(struct net *net, struct sock *sk, struct sk_buff *skb) { /* - * I know we drop the packet here, but thats considered success in + * I know we drop the packet here, but that's considered success in * this case */ kfree_skb(skb); diff --git a/net/devres.c b/net/devres.c index 1f9be2133787..5ccf6ca311dc 100644 --- a/net/devres.c +++ b/net/devres.c @@ -60,7 +60,7 @@ static int netdev_devres_match(struct device *dev, void *this, void *match_data) * @ndev: device to register * * This is a devres variant of register_netdev() for which the unregister - * function will be call automatically when the managing device is + * function will be called automatically when the managing device is * detached. Note: the net_device used must also be resource managed by * the same struct device. */ diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index b71e87909f0e..185629f27f80 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -219,21 +219,6 @@ static void dsa_tree_put(struct dsa_switch_tree *dst) kref_put(&dst->refcount, dsa_tree_release); } -static bool dsa_port_is_dsa(struct dsa_port *port) -{ - return port->type == DSA_PORT_TYPE_DSA; -} - -static bool dsa_port_is_cpu(struct dsa_port *port) -{ - return port->type == DSA_PORT_TYPE_CPU; -} - -static bool dsa_port_is_user(struct dsa_port *dp) -{ - return dp->type == DSA_PORT_TYPE_USER; -} - static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst, struct device_node *dn) { @@ -363,6 +348,9 @@ static int dsa_port_setup(struct dsa_port *dp) if (dp->setup) return 0; + INIT_LIST_HEAD(&dp->fdbs); + INIT_LIST_HEAD(&dp->mdbs); + switch (dp->type) { case DSA_PORT_TYPE_UNUSED: dsa_port_disable(dp); @@ -458,6 +446,7 @@ static int dsa_port_devlink_setup(struct dsa_port *dp) static void dsa_port_teardown(struct dsa_port *dp) { struct devlink_port *dlp = &dp->devlink_port; + struct dsa_mac_addr *a, *tmp; if (!dp->setup) return; @@ -483,6 +472,16 @@ static void dsa_port_teardown(struct dsa_port *dp) break; } + list_for_each_entry_safe(a, tmp, &dp->fdbs, list) { + list_del(&a->list); + kfree(a); + } + + list_for_each_entry_safe(a, tmp, &dp->mdbs, list) { + list_del(&a->list); + kfree(a); + } + dp->setup = false; } @@ -1259,6 +1258,13 @@ static int dsa_switch_parse_member_of(struct dsa_switch *ds, if (!ds->dst) return -ENOMEM; + if (dsa_switch_find(ds->dst->index, ds->index)) { + dev_err(ds->dev, + "A DSA switch with index %d already exists in tree %d\n", + ds->index, ds->dst->index); + return -EEXIST; + } + return 0; } diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 92282de54230..f201c33980bf 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -20,6 +20,8 @@ enum { DSA_NOTIFIER_BRIDGE_LEAVE, DSA_NOTIFIER_FDB_ADD, DSA_NOTIFIER_FDB_DEL, + DSA_NOTIFIER_HOST_FDB_ADD, + DSA_NOTIFIER_HOST_FDB_DEL, DSA_NOTIFIER_HSR_JOIN, DSA_NOTIFIER_HSR_LEAVE, DSA_NOTIFIER_LAG_CHANGE, @@ -27,6 +29,8 @@ enum { DSA_NOTIFIER_LAG_LEAVE, DSA_NOTIFIER_MDB_ADD, DSA_NOTIFIER_MDB_DEL, + DSA_NOTIFIER_HOST_MDB_ADD, + DSA_NOTIFIER_HOST_MDB_DEL, DSA_NOTIFIER_VLAN_ADD, DSA_NOTIFIER_VLAN_DEL, DSA_NOTIFIER_MTU, @@ -84,7 +88,7 @@ struct dsa_notifier_vlan_info { /* DSA_NOTIFIER_MTU */ struct dsa_notifier_mtu_info { - bool propagate_upstream; + bool targeted_match; int sw_index; int port; int mtu; @@ -112,6 +116,7 @@ struct dsa_notifier_mrp_ring_role_info { struct dsa_switchdev_event_work { struct dsa_switch *ds; int port; + struct net_device *dev; struct work_struct work; unsigned long event; /* Specific for SWITCHDEV_FDB_ADD_TO_DEVICE and @@ -119,6 +124,7 @@ struct dsa_switchdev_event_work { */ unsigned char addr[ETH_ALEN]; u16 vid; + bool host_addr; }; /* DSA_NOTIFIER_HSR_* */ @@ -154,6 +160,11 @@ const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf); bool dsa_schedule_work(struct work_struct *work); const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); +static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops) +{ + return ops->needed_headroom + ops->needed_tailroom; +} + /* master.c */ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp); void dsa_master_teardown(struct net_device *dev); @@ -183,28 +194,40 @@ void dsa_port_disable_rt(struct dsa_port *dp); void dsa_port_disable(struct dsa_port *dp); int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, struct netlink_ext_ack *extack); +int dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br, + struct netlink_ext_ack *extack); void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); int dsa_port_lag_change(struct dsa_port *dp, struct netdev_lag_lower_state_info *linfo); int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag_dev, struct netdev_lag_upper_info *uinfo, struct netlink_ext_ack *extack); +int dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag_dev, + struct netlink_ext_ack *extack); void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, struct netlink_ext_ack *extack); bool dsa_port_skip_vlan_configuration(struct dsa_port *dp); int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock); int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, - bool propagate_upstream); + bool targeted_match); int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, u16 vid); int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, u16 vid); +int dsa_port_host_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_host_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid); int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data); int dsa_port_mdb_add(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb); int dsa_port_mdb_del(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb); +int dsa_port_host_mdb_add(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_host_mdb_del(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); int dsa_port_pre_bridge_flags(const struct dsa_port *dp, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); diff --git a/net/dsa/master.c b/net/dsa/master.c index 63adbc21a735..3fc90e36772d 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -346,10 +346,12 @@ static struct lock_class_key dsa_master_addr_list_lock_key; int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { - int mtu = ETH_DATA_LEN + cpu_dp->tag_ops->overhead; + const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops; struct dsa_switch *ds = cpu_dp->ds; struct device_link *consumer_link; - int ret; + int mtu, ret; + + mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops); /* The DSA master must use SET_NETDEV_DEV for this to work. */ consumer_link = device_link_add(ds->dev, dev->dev.parent, diff --git a/net/dsa/port.c b/net/dsa/port.c index 6379d66a6bb3..28b45b7e66df 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -194,26 +194,63 @@ static int dsa_port_switchdev_sync(struct dsa_port *dp, if (err && err != -EOPNOTSUPP) return err; - err = br_mdb_replay(br, brport_dev, - &dsa_slave_switchdev_blocking_notifier, - extack); + err = br_mdb_replay(br, brport_dev, dp, true, + &dsa_slave_switchdev_blocking_notifier, extack); if (err && err != -EOPNOTSUPP) return err; - err = br_fdb_replay(br, brport_dev, &dsa_slave_switchdev_notifier); + /* Forwarding and termination FDB entries on the port */ + err = br_fdb_replay(br, brport_dev, dp, true, + &dsa_slave_switchdev_notifier); if (err && err != -EOPNOTSUPP) return err; - err = br_vlan_replay(br, brport_dev, - &dsa_slave_switchdev_blocking_notifier, - extack); + /* Termination FDB entries on the bridge itself */ + err = br_fdb_replay(br, br, dp, true, &dsa_slave_switchdev_notifier); + if (err && err != -EOPNOTSUPP) + return err; + + err = br_vlan_replay(br, brport_dev, dp, true, + &dsa_slave_switchdev_blocking_notifier, extack); if (err && err != -EOPNOTSUPP) return err; return 0; } -static void dsa_port_switchdev_unsync(struct dsa_port *dp) +static int dsa_port_switchdev_unsync_objs(struct dsa_port *dp, + struct net_device *br, + struct netlink_ext_ack *extack) +{ + struct net_device *brport_dev = dsa_port_to_bridge_port(dp); + int err; + + /* Delete the switchdev objects left on this port */ + err = br_mdb_replay(br, brport_dev, dp, false, + &dsa_slave_switchdev_blocking_notifier, extack); + if (err && err != -EOPNOTSUPP) + return err; + + /* Forwarding and termination FDB entries on the port */ + err = br_fdb_replay(br, brport_dev, dp, false, + &dsa_slave_switchdev_notifier); + if (err && err != -EOPNOTSUPP) + return err; + + /* Termination FDB entries on the bridge itself */ + err = br_fdb_replay(br, br, dp, false, &dsa_slave_switchdev_notifier); + if (err && err != -EOPNOTSUPP) + return err; + + err = br_vlan_replay(br, brport_dev, dp, false, + &dsa_slave_switchdev_blocking_notifier, extack); + if (err && err != -EOPNOTSUPP) + return err; + + return 0; +} + +static void dsa_port_switchdev_unsync_attrs(struct dsa_port *dp) { /* Configure the port for standalone mode (no address learning, * flood everything). @@ -279,6 +316,12 @@ out_rollback: return err; } +int dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br, + struct netlink_ext_ack *extack) +{ + return dsa_port_switchdev_unsync_objs(dp, br, extack); +} + void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) { struct dsa_notifier_bridge_info info = { @@ -298,7 +341,7 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) if (err) pr_err("DSA: failed to notify DSA_NOTIFIER_BRIDGE_LEAVE\n"); - dsa_port_switchdev_unsync(dp); + dsa_port_switchdev_unsync_attrs(dp); } int dsa_port_lag_change(struct dsa_port *dp, @@ -366,6 +409,15 @@ err_lag_join: return err; } +int dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag, + struct netlink_ext_ack *extack) +{ + if (dp->bridge_dev) + return dsa_port_pre_bridge_leave(dp, dp->bridge_dev, extack); + + return 0; +} + void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag) { struct dsa_notifier_lag_info info = { @@ -567,11 +619,11 @@ int dsa_port_mrouter(struct dsa_port *dp, bool mrouter, } int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, - bool propagate_upstream) + bool targeted_match) { struct dsa_notifier_mtu_info info = { .sw_index = dp->ds->index, - .propagate_upstream = propagate_upstream, + .targeted_match = targeted_match, .port = dp->index, .mtu = new_mtu, }; @@ -606,6 +658,44 @@ int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, return dsa_port_notify(dp, DSA_NOTIFIER_FDB_DEL, &info); } +int dsa_port_host_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid) +{ + struct dsa_notifier_fdb_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .addr = addr, + .vid = vid, + }; + struct dsa_port *cpu_dp = dp->cpu_dp; + int err; + + err = dev_uc_add(cpu_dp->master, addr); + if (err) + return err; + + return dsa_port_notify(dp, DSA_NOTIFIER_HOST_FDB_ADD, &info); +} + +int dsa_port_host_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid) +{ + struct dsa_notifier_fdb_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .addr = addr, + .vid = vid, + }; + struct dsa_port *cpu_dp = dp->cpu_dp; + int err; + + err = dev_uc_del(cpu_dp->master, addr); + if (err) + return err; + + return dsa_port_notify(dp, DSA_NOTIFIER_HOST_FDB_DEL, &info); +} + int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data) { struct dsa_switch *ds = dp->ds; @@ -641,6 +731,42 @@ int dsa_port_mdb_del(const struct dsa_port *dp, return dsa_port_notify(dp, DSA_NOTIFIER_MDB_DEL, &info); } +int dsa_port_host_mdb_add(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb) +{ + struct dsa_notifier_mdb_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mdb = mdb, + }; + struct dsa_port *cpu_dp = dp->cpu_dp; + int err; + + err = dev_mc_add(cpu_dp->master, mdb->addr); + if (err) + return err; + + return dsa_port_notify(dp, DSA_NOTIFIER_HOST_MDB_ADD, &info); +} + +int dsa_port_host_mdb_del(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb) +{ + struct dsa_notifier_mdb_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mdb = mdb, + }; + struct dsa_port *cpu_dp = dp->cpu_dp; + int err; + + err = dev_mc_del(cpu_dp->master, mdb->addr); + if (err) + return err; + + return dsa_port_notify(dp, DSA_NOTIFIER_HOST_MDB_DEL, &info); +} + int dsa_port_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index d4756b920108..ffbba1e71551 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -271,13 +271,16 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return phylink_mii_ioctl(p->dp->pl, ifr, cmd); } -static int dsa_slave_port_attr_set(struct net_device *dev, +static int dsa_slave_port_attr_set(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_slave_to_port(dev); int ret; + if (ctx && ctx != dp) + return 0; + switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) @@ -394,13 +397,16 @@ static int dsa_slave_vlan_add(struct net_device *dev, return vlan_vid_add(master, htons(ETH_P_8021Q), vlan.vid); } -static int dsa_slave_port_obj_add(struct net_device *dev, +static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_slave_to_port(dev); int err; + if (ctx && ctx != dp) + return 0; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) @@ -412,10 +418,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev, if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) return -EOPNOTSUPP; - /* DSA can directly translate this to a normal MDB add, - * but on the CPU port. - */ - err = dsa_port_mdb_add(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj)); + err = dsa_port_host_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) @@ -469,12 +472,15 @@ static int dsa_slave_vlan_del(struct net_device *dev, return 0; } -static int dsa_slave_port_obj_del(struct net_device *dev, +static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj) { struct dsa_port *dp = dsa_slave_to_port(dev); int err; + if (ctx && ctx != dp) + return 0; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) @@ -486,10 +492,7 @@ static int dsa_slave_port_obj_del(struct net_device *dev, if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) return -EOPNOTSUPP; - /* DSA can directly translate this to a normal MDB add, - * but on the CPU port. - */ - err = dsa_port_mdb_del(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj)); + err = dsa_port_host_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) @@ -1528,6 +1531,7 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; + struct dsa_port *dp_iter; struct dsa_port *cpu_dp; int port = p->dp->index; int largest_mtu = 0; @@ -1535,31 +1539,31 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) int old_master_mtu; int mtu_limit; int cpu_mtu; - int err, i; + int err; if (!ds->ops->port_change_mtu) return -EOPNOTSUPP; - for (i = 0; i < ds->num_ports; i++) { + list_for_each_entry(dp_iter, &ds->dst->ports, list) { int slave_mtu; - if (!dsa_is_user_port(ds, i)) + if (!dsa_port_is_user(dp_iter)) continue; /* During probe, this function will be called for each slave * device, while not all of them have been allocated. That's * ok, it doesn't change what the maximum is, so ignore it. */ - if (!dsa_to_port(ds, i)->slave) + if (!dp_iter->slave) continue; /* Pretend that we already applied the setting, which we * actually haven't (still haven't done all integrity checks) */ - if (i == port) + if (dp_iter == dp) slave_mtu = new_mtu; else - slave_mtu = dsa_to_port(ds, i)->slave->mtu; + slave_mtu = dp_iter->slave->mtu; if (largest_mtu < slave_mtu) largest_mtu = slave_mtu; @@ -1569,7 +1573,7 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) mtu_limit = min_t(int, master->max_mtu, dev->max_mtu); old_master_mtu = master->mtu; - new_master_mtu = largest_mtu + cpu_dp->tag_ops->overhead; + new_master_mtu = largest_mtu + dsa_tag_protocol_overhead(cpu_dp->tag_ops); if (new_master_mtu > mtu_limit) return -ERANGE; @@ -1585,14 +1589,15 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) goto out_master_failed; /* We only need to propagate the MTU of the CPU port to - * upstream switches. + * upstream switches, so create a non-targeted notifier which + * updates all switches. */ - err = dsa_port_mtu_change(cpu_dp, cpu_mtu, true); + err = dsa_port_mtu_change(cpu_dp, cpu_mtu, false); if (err) goto out_cpu_failed; } - err = dsa_port_mtu_change(dp, new_mtu, false); + err = dsa_port_mtu_change(dp, new_mtu, true); if (err) goto out_port_failed; @@ -1605,8 +1610,8 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) out_port_failed: if (new_master_mtu != old_master_mtu) dsa_port_mtu_change(cpu_dp, old_master_mtu - - cpu_dp->tag_ops->overhead, - true); + dsa_tag_protocol_overhead(cpu_dp->tag_ops), + false); out_cpu_failed: if (new_master_mtu != old_master_mtu) dev_set_mtu(master, old_master_mtu); @@ -1640,27 +1645,6 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .self_test = dsa_slave_net_selftest, }; -/* legacy way, bypassing the bridge *****************************************/ -static int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid, - u16 flags, - struct netlink_ext_ack *extack) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return dsa_port_fdb_add(dp, addr, vid); -} - -static int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return dsa_port_fdb_del(dp, addr, vid); -} - static struct devlink_port *dsa_slave_get_devlink_port(struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); @@ -1702,8 +1686,6 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_change_rx_flags = dsa_slave_change_rx_flags, .ndo_set_rx_mode = dsa_slave_set_rx_mode, .ndo_set_mac_address = dsa_slave_set_mac_address, - .ndo_fdb_add = dsa_legacy_fdb_add, - .ndo_fdb_del = dsa_legacy_fdb_del, .ndo_fdb_dump = dsa_slave_fdb_dump, .ndo_do_ioctl = dsa_slave_ioctl, .ndo_get_iflink = dsa_slave_get_iflink, @@ -1749,7 +1731,8 @@ static void dsa_slave_phylink_fixed_state(struct phylink_config *config, } /* slave device setup *******************************************************/ -static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) +static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr, + u32 flags) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_switch *ds = dp->ds; @@ -1760,6 +1743,8 @@ static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) return -ENODEV; } + slave_dev->phydev->dev_flags |= flags; + return phylink_connect_phy(dp->pl, slave_dev->phydev); } @@ -1804,7 +1789,7 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) /* We could not connect to a designated PHY or SFP, so try to * use the switch internal MDIO bus instead */ - ret = dsa_slave_phy_connect(slave_dev, dp->index); + ret = dsa_slave_phy_connect(slave_dev, dp->index, phy_flags); if (ret) { netdev_err(slave_dev, "failed to connect to port %d: %d\n", @@ -1824,10 +1809,8 @@ void dsa_slave_setup_tagger(struct net_device *slave) const struct dsa_port *cpu_dp = dp->cpu_dp; struct net_device *master = cpu_dp->master; - if (cpu_dp->tag_ops->tail_tag) - slave->needed_tailroom = cpu_dp->tag_ops->overhead; - else - slave->needed_headroom = cpu_dp->tag_ops->overhead; + slave->needed_headroom = cpu_dp->tag_ops->needed_headroom; + slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; /* Try to save one extra realloc later in the TX path (in the master) * by also inheriting the master's needed headroom and tailroom. * The 8021q driver also does this. @@ -2065,6 +2048,26 @@ static int dsa_slave_changeupper(struct net_device *dev, return err; } +static int dsa_slave_prechangeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct netlink_ext_ack *extack; + int err = 0; + + extack = netdev_notifier_info_to_extack(&info->info); + + if (netif_is_bridge_master(info->upper_dev) && !info->linking) + err = dsa_port_pre_bridge_leave(dp, info->upper_dev, extack); + else if (netif_is_lag_master(info->upper_dev) && !info->linking) + err = dsa_port_pre_lag_leave(dp, info->upper_dev, extack); + /* dsa_port_pre_hsr_leave is not yet necessary since hsr cannot be + * meaningfully enslaved to a bridge yet + */ + + return notifier_from_errno(err); +} + static int dsa_slave_lag_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) @@ -2091,6 +2094,35 @@ dsa_slave_lag_changeupper(struct net_device *dev, return err; } +/* Same as dsa_slave_lag_changeupper() except that it calls + * dsa_slave_prechangeupper() + */ +static int +dsa_slave_lag_prechangeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct net_device *lower; + struct list_head *iter; + int err = NOTIFY_DONE; + struct dsa_port *dp; + + netdev_for_each_lower_dev(dev, lower, iter) { + if (!dsa_slave_dev_check(lower)) + continue; + + dp = dsa_slave_to_port(lower); + if (!dp->lag_dev) + /* Software LAG */ + continue; + + err = dsa_slave_prechangeupper(lower, info); + if (notifier_to_errno(err)) + break; + } + + return err; +} + static int dsa_prevent_bridging_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) @@ -2154,6 +2186,32 @@ dsa_slave_check_8021q_upper(struct net_device *dev, return NOTIFY_DONE; } +static int +dsa_slave_prechangeupper_sanity_check(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct dsa_switch *ds; + struct dsa_port *dp; + int err; + + if (!dsa_slave_dev_check(dev)) + return dsa_prevent_bridging_8021q_upper(dev, info); + + dp = dsa_slave_to_port(dev); + ds = dp->ds; + + if (ds->ops->port_prechangeupper) { + err = ds->ops->port_prechangeupper(ds, dp->index, info); + if (err) + return notifier_from_errno(err); + } + + if (is_vlan_dev(info->upper_dev)) + return dsa_slave_check_8021q_upper(dev, info); + + return NOTIFY_DONE; +} + static int dsa_slave_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { @@ -2162,24 +2220,18 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, switch (event) { case NETDEV_PRECHANGEUPPER: { struct netdev_notifier_changeupper_info *info = ptr; - struct dsa_switch *ds; - struct dsa_port *dp; int err; - if (!dsa_slave_dev_check(dev)) - return dsa_prevent_bridging_8021q_upper(dev, ptr); + err = dsa_slave_prechangeupper_sanity_check(dev, info); + if (err != NOTIFY_DONE) + return err; - dp = dsa_slave_to_port(dev); - ds = dp->ds; + if (dsa_slave_dev_check(dev)) + return dsa_slave_prechangeupper(dev, ptr); - if (ds->ops->port_prechangeupper) { - err = ds->ops->port_prechangeupper(ds, dp->index, info); - if (err) - return notifier_from_errno(err); - } + if (netif_is_lag_master(dev)) + return dsa_slave_lag_prechangeupper(dev, ptr); - if (is_vlan_dev(info->upper_dev)) - return dsa_slave_check_8021q_upper(dev, ptr); break; } case NETDEV_CHANGEUPPER: @@ -2263,8 +2315,12 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) rtnl_lock(); switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: - err = dsa_port_fdb_add(dp, switchdev_work->addr, - switchdev_work->vid); + if (switchdev_work->host_addr) + err = dsa_port_host_fdb_add(dp, switchdev_work->addr, + switchdev_work->vid); + else + err = dsa_port_fdb_add(dp, switchdev_work->addr, + switchdev_work->vid); if (err) { dev_err(ds->dev, "port %d failed to add %pM vid %d to fdb: %d\n", @@ -2276,8 +2332,12 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) break; case SWITCHDEV_FDB_DEL_TO_DEVICE: - err = dsa_port_fdb_del(dp, switchdev_work->addr, - switchdev_work->vid); + if (switchdev_work->host_addr) + err = dsa_port_host_fdb_del(dp, switchdev_work->addr, + switchdev_work->vid); + else + err = dsa_port_fdb_del(dp, switchdev_work->addr, + switchdev_work->vid); if (err) { dev_err(ds->dev, "port %d failed to delete %pM vid %d from fdb: %d\n", @@ -2289,9 +2349,8 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) } rtnl_unlock(); + dev_put(switchdev_work->dev); kfree(switchdev_work); - if (dsa_is_user_port(ds, dp->index)) - dev_put(dp->slave); } static int dsa_lower_dev_walk(struct net_device *lower_dev, @@ -2323,6 +2382,7 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, struct net_device *dev = switchdev_notifier_info_to_dev(ptr); const struct switchdev_notifier_fdb_info *fdb_info; struct dsa_switchdev_event_work *switchdev_work; + bool host_addr = false; struct dsa_port *dp; int err; @@ -2337,19 +2397,28 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, fdb_info = ptr; if (dsa_slave_dev_check(dev)) { - if (!fdb_info->added_by_user || fdb_info->is_local) - return NOTIFY_OK; - dp = dsa_slave_to_port(dev); + + if (fdb_info->is_local) + host_addr = true; + else if (!fdb_info->added_by_user) + return NOTIFY_OK; } else { - /* Snoop addresses learnt on foreign interfaces - * bridged with us, for switches that don't - * automatically learn SA from CPU-injected traffic + /* Snoop addresses added to foreign interfaces + * bridged with us, or the bridge + * itself. Dynamically learned addresses can + * also be added for switches that don't + * automatically learn SA from CPU-injected + * traffic. */ struct net_device *br_dev; struct dsa_slave_priv *p; - br_dev = netdev_master_upper_dev_get_rcu(dev); + if (netif_is_bridge_master(dev)) + br_dev = dev; + else + br_dev = netdev_master_upper_dev_get_rcu(dev); + if (!br_dev) return NOTIFY_DONE; @@ -2360,17 +2429,30 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, if (!p) return NOTIFY_DONE; - dp = p->dp->cpu_dp; + dp = p->dp; + host_addr = fdb_info->is_local; - if (!dp->ds->assisted_learning_on_cpu_port) + /* FDB entries learned by the software bridge should + * be installed as host addresses only if the driver + * requests assisted learning. + * On the other hand, FDB entries for local termination + * should always be installed. + */ + if (!fdb_info->added_by_user && !fdb_info->is_local && + !dp->ds->assisted_learning_on_cpu_port) return NOTIFY_DONE; /* When the bridge learns an address on an offloaded * LAG we don't want to send traffic to the CPU, the * other ports bridged with the LAG should be able to * autonomously forward towards it. + * On the other hand, if the address is local + * (therefore not learned) then we want to trap it to + * the CPU regardless of whether the interface it + * belongs to is offloaded or not. */ - if (dsa_tree_offloads_bridge_port(dp->ds->dst, dev)) + if (dsa_tree_offloads_bridge_port(dp->ds->dst, dev) && + !fdb_info->is_local) return NOTIFY_DONE; } @@ -2386,14 +2468,15 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, switchdev_work->ds = dp->ds; switchdev_work->port = dp->index; switchdev_work->event = event; + switchdev_work->dev = dev; ether_addr_copy(switchdev_work->addr, fdb_info->addr); switchdev_work->vid = fdb_info->vid; + switchdev_work->host_addr = host_addr; - /* Hold a reference on the slave for dsa_fdb_offload_notify */ - if (dsa_is_user_port(dp->ds, dp->index)) - dev_hold(dev); + /* Hold a reference for dsa_fdb_offload_notify */ + dev_hold(dev); dsa_schedule_work(&switchdev_work->work); break; default: diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 9bf8e20ecdf3..af71b8638098 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -52,10 +52,13 @@ static int dsa_switch_ageing_time(struct dsa_switch *ds, static bool dsa_switch_mtu_match(struct dsa_switch *ds, int port, struct dsa_notifier_mtu_info *info) { - if (ds->index == info->sw_index) - return (port == info->port) || dsa_is_dsa_port(ds, port); + if (ds->index == info->sw_index && port == info->port) + return true; - if (!info->propagate_upstream) + /* Do not propagate to other switches in the tree if the notifier was + * targeted for a single switch. + */ + if (info->targeted_match) return false; if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) @@ -151,6 +154,214 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, return 0; } +/* Matches for all upstream-facing ports (the CPU port and all upstream-facing + * DSA links) that sit between the targeted port on which the notifier was + * emitted and its dedicated CPU port. + */ +static bool dsa_switch_host_address_match(struct dsa_switch *ds, int port, + int info_sw_index, int info_port) +{ + struct dsa_port *targeted_dp, *cpu_dp; + struct dsa_switch *targeted_ds; + + targeted_ds = dsa_switch_find(ds->dst->index, info_sw_index); + targeted_dp = dsa_to_port(targeted_ds, info_port); + cpu_dp = targeted_dp->cpu_dp; + + if (dsa_switch_is_upstream_of(ds, targeted_ds)) + return port == dsa_towards_port(ds, cpu_dp->ds->index, + cpu_dp->index); + + return false; +} + +static struct dsa_mac_addr *dsa_mac_addr_find(struct list_head *addr_list, + const unsigned char *addr, + u16 vid) +{ + struct dsa_mac_addr *a; + + list_for_each_entry(a, addr_list, list) + if (ether_addr_equal(a->addr, addr) && a->vid == vid) + return a; + + return NULL; +} + +static int dsa_switch_do_mdb_add(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_mac_addr *a; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->port_mdb_add(ds, port, mdb); + + a = dsa_mac_addr_find(&dp->mdbs, mdb->addr, mdb->vid); + if (a) { + refcount_inc(&a->refcount); + return 0; + } + + a = kzalloc(sizeof(*a), GFP_KERNEL); + if (!a) + return -ENOMEM; + + err = ds->ops->port_mdb_add(ds, port, mdb); + if (err) { + kfree(a); + return err; + } + + ether_addr_copy(a->addr, mdb->addr); + a->vid = mdb->vid; + refcount_set(&a->refcount, 1); + list_add_tail(&a->list, &dp->mdbs); + + return 0; +} + +static int dsa_switch_do_mdb_del(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_mac_addr *a; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->port_mdb_del(ds, port, mdb); + + a = dsa_mac_addr_find(&dp->mdbs, mdb->addr, mdb->vid); + if (!a) + return -ENOENT; + + if (!refcount_dec_and_test(&a->refcount)) + return 0; + + err = ds->ops->port_mdb_del(ds, port, mdb); + if (err) { + refcount_inc(&a->refcount); + return err; + } + + list_del(&a->list); + kfree(a); + + return 0; +} + +static int dsa_switch_do_fdb_add(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_mac_addr *a; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->port_fdb_add(ds, port, addr, vid); + + a = dsa_mac_addr_find(&dp->fdbs, addr, vid); + if (a) { + refcount_inc(&a->refcount); + return 0; + } + + a = kzalloc(sizeof(*a), GFP_KERNEL); + if (!a) + return -ENOMEM; + + err = ds->ops->port_fdb_add(ds, port, addr, vid); + if (err) { + kfree(a); + return err; + } + + ether_addr_copy(a->addr, addr); + a->vid = vid; + refcount_set(&a->refcount, 1); + list_add_tail(&a->list, &dp->fdbs); + + return 0; +} + +static int dsa_switch_do_fdb_del(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_mac_addr *a; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->port_fdb_del(ds, port, addr, vid); + + a = dsa_mac_addr_find(&dp->fdbs, addr, vid); + if (!a) + return -ENOENT; + + if (!refcount_dec_and_test(&a->refcount)) + return 0; + + err = ds->ops->port_fdb_del(ds, port, addr, vid); + if (err) { + refcount_inc(&a->refcount); + return err; + } + + list_del(&a->list); + kfree(a); + + return 0; +} + +static int dsa_switch_host_fdb_add(struct dsa_switch *ds, + struct dsa_notifier_fdb_info *info) +{ + int err = 0; + int port; + + if (!ds->ops->port_fdb_add) + return -EOPNOTSUPP; + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_host_address_match(ds, port, info->sw_index, + info->port)) { + err = dsa_switch_do_fdb_add(ds, port, info->addr, + info->vid); + if (err) + break; + } + } + + return err; +} + +static int dsa_switch_host_fdb_del(struct dsa_switch *ds, + struct dsa_notifier_fdb_info *info) +{ + int err = 0; + int port; + + if (!ds->ops->port_fdb_del) + return -EOPNOTSUPP; + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_host_address_match(ds, port, info->sw_index, + info->port)) { + err = dsa_switch_do_fdb_del(ds, port, info->addr, + info->vid); + if (err) + break; + } + } + + return err; +} + static int dsa_switch_fdb_add(struct dsa_switch *ds, struct dsa_notifier_fdb_info *info) { @@ -159,7 +370,7 @@ static int dsa_switch_fdb_add(struct dsa_switch *ds, if (!ds->ops->port_fdb_add) return -EOPNOTSUPP; - return ds->ops->port_fdb_add(ds, port, info->addr, info->vid); + return dsa_switch_do_fdb_add(ds, port, info->addr, info->vid); } static int dsa_switch_fdb_del(struct dsa_switch *ds, @@ -170,7 +381,7 @@ static int dsa_switch_fdb_del(struct dsa_switch *ds, if (!ds->ops->port_fdb_del) return -EOPNOTSUPP; - return ds->ops->port_fdb_del(ds, port, info->addr, info->vid); + return dsa_switch_do_fdb_del(ds, port, info->addr, info->vid); } static int dsa_switch_hsr_join(struct dsa_switch *ds, @@ -232,20 +443,30 @@ static int dsa_switch_lag_leave(struct dsa_switch *ds, return 0; } -static bool dsa_switch_mdb_match(struct dsa_switch *ds, int port, - struct dsa_notifier_mdb_info *info) -{ - if (ds->index == info->sw_index && port == info->port) - return true; - - if (dsa_is_dsa_port(ds, port)) - return true; - - return false; -} - static int dsa_switch_mdb_add(struct dsa_switch *ds, struct dsa_notifier_mdb_info *info) +{ + int port = dsa_towards_port(ds, info->sw_index, info->port); + + if (!ds->ops->port_mdb_add) + return -EOPNOTSUPP; + + return dsa_switch_do_mdb_add(ds, port, info->mdb); +} + +static int dsa_switch_mdb_del(struct dsa_switch *ds, + struct dsa_notifier_mdb_info *info) +{ + int port = dsa_towards_port(ds, info->sw_index, info->port); + + if (!ds->ops->port_mdb_del) + return -EOPNOTSUPP; + + return dsa_switch_do_mdb_del(ds, port, info->mdb); +} + +static int dsa_switch_host_mdb_add(struct dsa_switch *ds, + struct dsa_notifier_mdb_info *info) { int err = 0; int port; @@ -254,8 +475,9 @@ static int dsa_switch_mdb_add(struct dsa_switch *ds, return -EOPNOTSUPP; for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_mdb_match(ds, port, info)) { - err = ds->ops->port_mdb_add(ds, port, info->mdb); + if (dsa_switch_host_address_match(ds, port, info->sw_index, + info->port)) { + err = dsa_switch_do_mdb_add(ds, port, info->mdb); if (err) break; } @@ -264,16 +486,25 @@ static int dsa_switch_mdb_add(struct dsa_switch *ds, return err; } -static int dsa_switch_mdb_del(struct dsa_switch *ds, - struct dsa_notifier_mdb_info *info) +static int dsa_switch_host_mdb_del(struct dsa_switch *ds, + struct dsa_notifier_mdb_info *info) { + int err = 0; + int port; + if (!ds->ops->port_mdb_del) return -EOPNOTSUPP; - if (ds->index == info->sw_index) - return ds->ops->port_mdb_del(ds, info->port, info->mdb); + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_host_address_match(ds, port, info->sw_index, + info->port)) { + err = dsa_switch_do_mdb_del(ds, port, info->mdb); + if (err) + break; + } + } - return 0; + return err; } static bool dsa_switch_vlan_match(struct dsa_switch *ds, int port, @@ -364,36 +595,16 @@ static int dsa_switch_change_tag_proto(struct dsa_switch *ds, return 0; } -static bool dsa_switch_mrp_match(struct dsa_switch *ds, int port, - struct dsa_notifier_mrp_info *info) -{ - if (ds->index == info->sw_index && port == info->port) - return true; - - if (dsa_is_dsa_port(ds, port)) - return true; - - return false; -} - static int dsa_switch_mrp_add(struct dsa_switch *ds, struct dsa_notifier_mrp_info *info) { - int err = 0; - int port; - if (!ds->ops->port_mrp_add) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_mrp_match(ds, port, info)) { - err = ds->ops->port_mrp_add(ds, port, info->mrp); - if (err) - break; - } - } + if (ds->index == info->sw_index) + return ds->ops->port_mrp_add(ds, info->port, info->mrp); - return err; + return 0; } static int dsa_switch_mrp_del(struct dsa_switch *ds, @@ -408,39 +619,18 @@ static int dsa_switch_mrp_del(struct dsa_switch *ds, return 0; } -static bool -dsa_switch_mrp_ring_role_match(struct dsa_switch *ds, int port, - struct dsa_notifier_mrp_ring_role_info *info) -{ - if (ds->index == info->sw_index && port == info->port) - return true; - - if (dsa_is_dsa_port(ds, port)) - return true; - - return false; -} - static int dsa_switch_mrp_add_ring_role(struct dsa_switch *ds, struct dsa_notifier_mrp_ring_role_info *info) { - int err = 0; - int port; - if (!ds->ops->port_mrp_add) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_mrp_ring_role_match(ds, port, info)) { - err = ds->ops->port_mrp_add_ring_role(ds, port, - info->mrp); - if (err) - break; - } - } + if (ds->index == info->sw_index) + return ds->ops->port_mrp_add_ring_role(ds, info->port, + info->mrp); - return err; + return 0; } static int @@ -479,6 +669,12 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_FDB_DEL: err = dsa_switch_fdb_del(ds, info); break; + case DSA_NOTIFIER_HOST_FDB_ADD: + err = dsa_switch_host_fdb_add(ds, info); + break; + case DSA_NOTIFIER_HOST_FDB_DEL: + err = dsa_switch_host_fdb_del(ds, info); + break; case DSA_NOTIFIER_HSR_JOIN: err = dsa_switch_hsr_join(ds, info); break; @@ -500,6 +696,12 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_MDB_DEL: err = dsa_switch_mdb_del(ds, info); break; + case DSA_NOTIFIER_HOST_MDB_ADD: + err = dsa_switch_host_mdb_add(ds, info); + break; + case DSA_NOTIFIER_HOST_MDB_DEL: + err = dsa_switch_host_mdb_del(ds, info); + break; case DSA_NOTIFIER_VLAN_ADD: err = dsa_switch_vlan_add(ds, info); break; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 122ad5833fb1..4aa29f90ecea 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -471,4 +471,27 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, } EXPORT_SYMBOL_GPL(dsa_8021q_xmit); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *subvlan) +{ + u16 vid, tci; + + skb_push_rcsum(skb, ETH_HLEN); + if (skb_vlan_tag_present(skb)) { + tci = skb_vlan_tag_get(skb); + __vlan_hwaccel_clear_tag(skb); + } else { + __skb_vlan_pop(skb, &tci); + } + skb_pull_rcsum(skb, ETH_HLEN); + + vid = tci & VLAN_VID_MASK; + + *source_port = dsa_8021q_rx_source_port(vid); + *switch_id = dsa_8021q_rx_switch_id(vid); + *subvlan = dsa_8021q_rx_subvlan(vid); + skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; +} +EXPORT_SYMBOL_GPL(dsa_8021q_rcv); + MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c index 002cf7f952e2..0efae1a372b3 100644 --- a/net/dsa/tag_ar9331.c +++ b/net/dsa/tag_ar9331.c @@ -85,7 +85,7 @@ static const struct dsa_device_ops ar9331_netdev_ops = { .proto = DSA_TAG_PROTO_AR9331, .xmit = ar9331_tag_xmit, .rcv = ar9331_tag_rcv, - .overhead = AR9331_HDR_LEN, + .needed_headroom = AR9331_HDR_LEN, }; MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 40e9f3098c8d..0750af951fc9 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -205,7 +205,7 @@ static const struct dsa_device_ops brcm_netdev_ops = { .proto = DSA_TAG_PROTO_BRCM, .xmit = brcm_tag_xmit, .rcv = brcm_tag_rcv, - .overhead = BRCM_TAG_LEN, + .needed_headroom = BRCM_TAG_LEN, }; DSA_TAG_DRIVER(brcm_netdev_ops); @@ -286,7 +286,7 @@ static const struct dsa_device_ops brcm_legacy_netdev_ops = { .proto = DSA_TAG_PROTO_BRCM_LEGACY, .xmit = brcm_leg_tag_xmit, .rcv = brcm_leg_tag_rcv, - .overhead = BRCM_LEG_TAG_LEN, + .needed_headroom = BRCM_LEG_TAG_LEN, }; DSA_TAG_DRIVER(brcm_legacy_netdev_ops); @@ -314,7 +314,7 @@ static const struct dsa_device_ops brcm_prepend_netdev_ops = { .proto = DSA_TAG_PROTO_BRCM_PREPEND, .xmit = brcm_tag_xmit_prepend, .rcv = brcm_tag_rcv_prepend, - .overhead = BRCM_TAG_LEN, + .needed_headroom = BRCM_TAG_LEN, }; DSA_TAG_DRIVER(brcm_prepend_netdev_ops); diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 7e7b7decdf39..a822355afc90 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -303,7 +303,7 @@ static const struct dsa_device_ops dsa_netdev_ops = { .proto = DSA_TAG_PROTO_DSA, .xmit = dsa_xmit, .rcv = dsa_rcv, - .overhead = DSA_HLEN, + .needed_headroom = DSA_HLEN, }; DSA_TAG_DRIVER(dsa_netdev_ops); @@ -346,7 +346,7 @@ static const struct dsa_device_ops edsa_netdev_ops = { .proto = DSA_TAG_PROTO_EDSA, .xmit = edsa_xmit, .rcv = edsa_rcv, - .overhead = EDSA_HLEN, + .needed_headroom = EDSA_HLEN, }; DSA_TAG_DRIVER(edsa_netdev_ops); diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c index 2f5bd5e338ab..5985dab06ab8 100644 --- a/net/dsa/tag_gswip.c +++ b/net/dsa/tag_gswip.c @@ -103,7 +103,7 @@ static const struct dsa_device_ops gswip_netdev_ops = { .proto = DSA_TAG_PROTO_GSWIP, .xmit = gswip_tag_xmit, .rcv = gswip_tag_rcv, - .overhead = GSWIP_RX_HEADER_LEN, + .needed_headroom = GSWIP_RX_HEADER_LEN, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index a09805c8e1ab..424130f85f59 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -54,8 +54,7 @@ static const struct dsa_device_ops hellcreek_netdev_ops = { .proto = DSA_TAG_PROTO_HELLCREEK, .xmit = hellcreek_xmit, .rcv = hellcreek_rcv, - .overhead = HELLCREEK_TAG_LEN, - .tail_tag = true, + .needed_tailroom = HELLCREEK_TAG_LEN, }; MODULE_LICENSE("Dual MIT/GPL"); diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 4820dbcedfa2..53565f48934c 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -77,8 +77,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ8795, .xmit = ksz8795_xmit, .rcv = ksz8795_rcv, - .overhead = KSZ_INGRESS_TAG_LEN, - .tail_tag = true, + .needed_tailroom = KSZ_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz8795_netdev_ops); @@ -149,8 +148,7 @@ static const struct dsa_device_ops ksz9477_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ9477, .xmit = ksz9477_xmit, .rcv = ksz9477_rcv, - .overhead = KSZ9477_INGRESS_TAG_LEN, - .tail_tag = true, + .needed_tailroom = KSZ9477_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz9477_netdev_ops); @@ -183,8 +181,7 @@ static const struct dsa_device_ops ksz9893_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ9893, .xmit = ksz9893_xmit, .rcv = ksz9477_rcv, - .overhead = KSZ_INGRESS_TAG_LEN, - .tail_tag = true, + .needed_tailroom = KSZ_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz9893_netdev_ops); diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index aa1318dccaf0..26207ef39ebc 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -125,7 +125,7 @@ static const struct dsa_device_ops lan9303_netdev_ops = { .proto = DSA_TAG_PROTO_LAN9303, .xmit = lan9303_xmit, .rcv = lan9303_rcv, - .overhead = LAN9303_TAG_LEN, + .needed_headroom = LAN9303_TAG_LEN, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index f9b2966d1936..cc3ba864ad5b 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -102,7 +102,7 @@ static const struct dsa_device_ops mtk_netdev_ops = { .proto = DSA_TAG_PROTO_MTK, .xmit = mtk_tag_xmit, .rcv = mtk_tag_rcv, - .overhead = MTK_HDR_LEN, + .needed_headroom = MTK_HDR_LEN, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 91f0fd1242cd..190f4bfd3bef 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -143,7 +143,7 @@ static const struct dsa_device_ops ocelot_netdev_ops = { .proto = DSA_TAG_PROTO_OCELOT, .xmit = ocelot_xmit, .rcv = ocelot_rcv, - .overhead = OCELOT_TOTAL_TAG_LEN, + .needed_headroom = OCELOT_TOTAL_TAG_LEN, .promisc_on_master = true, }; @@ -155,7 +155,7 @@ static const struct dsa_device_ops seville_netdev_ops = { .proto = DSA_TAG_PROTO_SEVILLE, .xmit = seville_xmit, .rcv = ocelot_rcv, - .overhead = OCELOT_TOTAL_TAG_LEN, + .needed_headroom = OCELOT_TOTAL_TAG_LEN, .promisc_on_master = true, }; diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 62a93303bd63..85ac85c3af8c 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -41,29 +41,15 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { - int src_port, switch_id, qos_class; - u16 vid, tci; + int src_port, switch_id, subvlan; - skb_push_rcsum(skb, ETH_HLEN); - if (skb_vlan_tag_present(skb)) { - tci = skb_vlan_tag_get(skb); - __vlan_hwaccel_clear_tag(skb); - } else { - __skb_vlan_pop(skb, &tci); - } - skb_pull_rcsum(skb, ETH_HLEN); - - vid = tci & VLAN_VID_MASK; - src_port = dsa_8021q_rx_source_port(vid); - switch_id = dsa_8021q_rx_switch_id(vid); - qos_class = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + dsa_8021q_rcv(skb, &src_port, &switch_id, &subvlan); skb->dev = dsa_master_find_slave(netdev, switch_id, src_port); if (!skb->dev) return NULL; skb->offload_fwd_mark = 1; - skb->priority = qos_class; return skb; } @@ -73,7 +59,7 @@ static const struct dsa_device_ops ocelot_8021q_netdev_ops = { .proto = DSA_TAG_PROTO_OCELOT_8021Q, .xmit = ocelot_xmit, .rcv = ocelot_rcv, - .overhead = VLAN_HLEN, + .needed_headroom = VLAN_HLEN, .promisc_on_master = true, }; diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 88181b52f480..693bda013065 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -91,7 +91,7 @@ static const struct dsa_device_ops qca_netdev_ops = { .proto = DSA_TAG_PROTO_QCA, .xmit = qca_tag_xmit, .rcv = qca_tag_rcv, - .overhead = QCA_HDR_LEN, + .needed_headroom = QCA_HDR_LEN, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index cf8ac316f4c7..57c46b4ab2b3 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -124,7 +124,7 @@ static const struct dsa_device_ops rtl4a_netdev_ops = { .proto = DSA_TAG_PROTO_RTL4_A, .xmit = rtl4a_tag_xmit, .rcv = rtl4a_tag_rcv, - .overhead = RTL4_A_HDR_LEN, + .needed_headroom = RTL4_A_HDR_LEN, }; module_dsa_tag_driver(rtl4a_netdev_ops); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 50496013cdb7..9c2df9ece01b 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -7,6 +7,52 @@ #include #include "dsa_priv.h" +/* Is this a TX or an RX header? */ +#define SJA1110_HEADER_HOST_TO_SWITCH BIT(15) + +/* RX header */ +#define SJA1110_RX_HEADER_IS_METADATA BIT(14) +#define SJA1110_RX_HEADER_HOST_ONLY BIT(13) +#define SJA1110_RX_HEADER_HAS_TRAILER BIT(12) + +/* Trap-to-host format (no trailer present) */ +#define SJA1110_RX_HEADER_SRC_PORT(x) (((x) & GENMASK(7, 4)) >> 4) +#define SJA1110_RX_HEADER_SWITCH_ID(x) ((x) & GENMASK(3, 0)) + +/* Timestamp format (trailer present) */ +#define SJA1110_RX_HEADER_TRAILER_POS(x) ((x) & GENMASK(11, 0)) + +#define SJA1110_RX_TRAILER_SWITCH_ID(x) (((x) & GENMASK(7, 4)) >> 4) +#define SJA1110_RX_TRAILER_SRC_PORT(x) ((x) & GENMASK(3, 0)) + +/* Meta frame format (for 2-step TX timestamps) */ +#define SJA1110_RX_HEADER_N_TS(x) (((x) & GENMASK(8, 4)) >> 4) + +/* TX header */ +#define SJA1110_TX_HEADER_UPDATE_TC BIT(14) +#define SJA1110_TX_HEADER_TAKE_TS BIT(13) +#define SJA1110_TX_HEADER_TAKE_TS_CASC BIT(12) +#define SJA1110_TX_HEADER_HAS_TRAILER BIT(11) + +/* Only valid if SJA1110_TX_HEADER_HAS_TRAILER is false */ +#define SJA1110_TX_HEADER_PRIO(x) (((x) << 7) & GENMASK(10, 7)) +#define SJA1110_TX_HEADER_TSTAMP_ID(x) ((x) & GENMASK(7, 0)) + +/* Only valid if SJA1110_TX_HEADER_HAS_TRAILER is true */ +#define SJA1110_TX_HEADER_TRAILER_POS(x) ((x) & GENMASK(10, 0)) + +#define SJA1110_TX_TRAILER_TSTAMP_ID(x) (((x) << 24) & GENMASK(31, 24)) +#define SJA1110_TX_TRAILER_PRIO(x) (((x) << 21) & GENMASK(23, 21)) +#define SJA1110_TX_TRAILER_SWITCHID(x) (((x) << 12) & GENMASK(15, 12)) +#define SJA1110_TX_TRAILER_DESTPORTS(x) (((x) << 1) & GENMASK(11, 1)) + +#define SJA1110_META_TSTAMP_SIZE 10 + +#define SJA1110_HEADER_LEN 4 +#define SJA1110_RX_TRAILER_LEN 13 +#define SJA1110_TX_TRAILER_LEN 4 +#define SJA1110_MAX_PADDING_LEN 15 + /* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */ static inline bool sja1105_is_link_local(const struct sk_buff *skb) { @@ -140,6 +186,57 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); } +static struct sk_buff *sja1110_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; + struct dsa_port *dp = dsa_slave_to_port(netdev); + u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); + u16 queue_mapping = skb_get_queue_mapping(skb); + u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + struct ethhdr *eth_hdr; + __be32 *tx_trailer; + __be16 *tx_header; + int trailer_pos; + + /* Transmitting control packets is done using in-band control + * extensions, while data packets are transmitted using + * tag_8021q TX VLANs. + */ + if (likely(!sja1105_is_link_local(skb))) + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp->priv), + ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); + + skb_push(skb, SJA1110_HEADER_LEN); + + /* Move Ethernet header to the left, making space for DSA tag */ + memmove(skb->data, skb->data + SJA1110_HEADER_LEN, 2 * ETH_ALEN); + + trailer_pos = skb->len; + + /* On TX, skb->data points to skb_mac_header(skb) */ + eth_hdr = (struct ethhdr *)skb->data; + tx_header = (__be16 *)(eth_hdr + 1); + tx_trailer = skb_put(skb, SJA1110_TX_TRAILER_LEN); + + eth_hdr->h_proto = htons(ETH_P_SJA1110); + + *tx_header = htons(SJA1110_HEADER_HOST_TO_SWITCH | + SJA1110_TX_HEADER_HAS_TRAILER | + SJA1110_TX_HEADER_TRAILER_POS(trailer_pos)); + *tx_trailer = cpu_to_be32(SJA1110_TX_TRAILER_PRIO(pcp) | + SJA1110_TX_TRAILER_SWITCHID(dp->ds->index) | + SJA1110_TX_TRAILER_DESTPORTS(BIT(dp->index))); + if (clone) { + u8 ts_id = SJA1105_SKB_CB(clone)->ts_id; + + *tx_header |= htons(SJA1110_TX_HEADER_TAKE_TS); + *tx_trailer |= cpu_to_be32(SJA1110_TX_TRAILER_TSTAMP_ID(ts_id)); + } + + return skb; +} + static void sja1105_transfer_meta(struct sk_buff *skb, const struct sja1105_meta *meta) { @@ -147,7 +244,7 @@ static void sja1105_transfer_meta(struct sk_buff *skb, hdr->h_dest[3] = meta->dmac_byte_3; hdr->h_dest[4] = meta->dmac_byte_4; - SJA1105_SKB_CB(skb)->meta_tstamp = meta->tstamp; + SJA1105_SKB_CB(skb)->tstamp = meta->tstamp; } /* This is a simple state machine which follows the hardware mechanism of @@ -275,46 +372,38 @@ static void sja1105_decode_subvlan(struct sk_buff *skb, u16 subvlan) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci); } +static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb) +{ + u16 tpid = ntohs(eth_hdr(skb)->h_proto); + + return tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q || + skb_vlan_tag_present(skb); +} + +static bool sja1110_skb_has_inband_control_extension(const struct sk_buff *skb) +{ + return ntohs(eth_hdr(skb)->h_proto) == ETH_P_SJA1110; +} + static struct sk_buff *sja1105_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { + int source_port, switch_id, subvlan = 0; struct sja1105_meta meta = {0}; - int source_port, switch_id; struct ethhdr *hdr; - u16 tpid, vid, tci; bool is_link_local; - u16 subvlan = 0; - bool is_tagged; bool is_meta; hdr = eth_hdr(skb); - tpid = ntohs(hdr->h_proto); - is_tagged = (tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q || - skb_vlan_tag_present(skb)); is_link_local = sja1105_is_link_local(skb); is_meta = sja1105_is_meta_frame(skb); skb->offload_fwd_mark = 1; - if (is_tagged) { + if (sja1105_skb_has_tag_8021q(skb)) { /* Normal traffic path. */ - skb_push_rcsum(skb, ETH_HLEN); - if (skb_vlan_tag_present(skb)) { - tci = skb_vlan_tag_get(skb); - __vlan_hwaccel_clear_tag(skb); - } else { - __skb_vlan_pop(skb, &tci); - } - skb_pull_rcsum(skb, ETH_HLEN); - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - - vid = tci & VLAN_VID_MASK; - source_port = dsa_8021q_rx_source_port(vid); - switch_id = dsa_8021q_rx_switch_id(vid); - skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; - subvlan = dsa_8021q_rx_subvlan(vid); + dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan); } else if (is_link_local) { /* Management traffic path. Switch embeds the switch ID and * port ID into bytes of the destination MAC, courtesy of @@ -346,6 +435,138 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_meta); } +static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) +{ + int switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); + int n_ts = SJA1110_RX_HEADER_N_TS(rx_header); + struct net_device *master = skb->dev; + struct dsa_port *cpu_dp; + u8 *buf = skb->data + 2; + struct dsa_switch *ds; + int i; + + cpu_dp = master->dsa_ptr; + ds = dsa_switch_find(cpu_dp->dst->index, switch_id); + if (!ds) { + net_err_ratelimited("%s: cannot find switch id %d\n", + master->name, switch_id); + return NULL; + } + + for (i = 0; i <= n_ts; i++) { + u8 ts_id, source_port, dir; + u64 tstamp; + + ts_id = buf[0]; + source_port = (buf[1] & GENMASK(7, 4)) >> 4; + dir = (buf[1] & BIT(3)) >> 3; + tstamp = be64_to_cpu(*(__be64 *)(buf + 2)); + + sja1110_process_meta_tstamp(ds, source_port, ts_id, dir, + tstamp); + + buf += SJA1110_META_TSTAMP_SIZE; + } + + /* Discard the meta frame, we've consumed the timestamps it contained */ + return NULL; +} + +static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, + int *source_port, + int *switch_id) +{ + u16 rx_header; + + if (unlikely(!pskb_may_pull(skb, SJA1110_HEADER_LEN))) + return NULL; + + /* skb->data points to skb_mac_header(skb) + ETH_HLEN, which is exactly + * what we need because the caller has checked the EtherType (which is + * located 2 bytes back) and we just need a pointer to the header that + * comes afterwards. + */ + rx_header = ntohs(*(__be16 *)skb->data); + + if (rx_header & SJA1110_RX_HEADER_IS_METADATA) + return sja1110_rcv_meta(skb, rx_header); + + /* Timestamp frame, we have a trailer */ + if (rx_header & SJA1110_RX_HEADER_HAS_TRAILER) { + int start_of_padding = SJA1110_RX_HEADER_TRAILER_POS(rx_header); + u8 *rx_trailer = skb_tail_pointer(skb) - SJA1110_RX_TRAILER_LEN; + u64 *tstamp = &SJA1105_SKB_CB(skb)->tstamp; + u8 last_byte = rx_trailer[12]; + + /* The timestamp is unaligned, so we need to use packing() + * to get it + */ + packing(rx_trailer, tstamp, 63, 0, 8, UNPACK, 0); + + *source_port = SJA1110_RX_TRAILER_SRC_PORT(last_byte); + *switch_id = SJA1110_RX_TRAILER_SWITCH_ID(last_byte); + + /* skb->len counts from skb->data, while start_of_padding + * counts from the destination MAC address. Right now skb->data + * is still as set by the DSA master, so to trim away the + * padding and trailer we need to account for the fact that + * skb->data points to skb_mac_header(skb) + ETH_HLEN. + */ + pskb_trim_rcsum(skb, start_of_padding - ETH_HLEN); + /* Trap-to-host frame, no timestamp trailer */ + } else { + *source_port = SJA1110_RX_HEADER_SRC_PORT(rx_header); + *switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); + } + + /* Advance skb->data past the DSA header */ + skb_pull_rcsum(skb, SJA1110_HEADER_LEN); + + /* Remove the DSA header */ + memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - SJA1110_HEADER_LEN, + 2 * ETH_ALEN); + + /* With skb->data in its final place, update the MAC header + * so that eth_hdr() continues to works properly. + */ + skb_set_mac_header(skb, -ETH_HLEN); + + return skb; +} + +static struct sk_buff *sja1110_rcv(struct sk_buff *skb, + struct net_device *netdev, + struct packet_type *pt) +{ + int source_port = -1, switch_id = -1, subvlan = 0; + + skb->offload_fwd_mark = 1; + + if (sja1110_skb_has_inband_control_extension(skb)) { + skb = sja1110_rcv_inband_control_extension(skb, &source_port, + &switch_id); + if (!skb) + return NULL; + } + + /* Packets with in-band control extensions might still have RX VLANs */ + if (likely(sja1105_skb_has_tag_8021q(skb))) + dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan); + + skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + if (!skb->dev) { + netdev_warn(netdev, + "Couldn't decode source port %d and switch id %d\n", + source_port, switch_id); + return NULL; + } + + if (subvlan) + sja1105_decode_subvlan(skb, subvlan); + + return skb; +} + static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { @@ -356,18 +577,53 @@ static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto, dsa_tag_generic_flow_dissect(skb, proto, offset); } +static void sja1110_flow_dissect(const struct sk_buff *skb, __be16 *proto, + int *offset) +{ + /* Management frames have 2 DSA tags on RX, so the needed_headroom we + * declared is fine for the generic dissector adjustment procedure. + */ + if (unlikely(sja1105_is_link_local(skb))) + return dsa_tag_generic_flow_dissect(skb, proto, offset); + + /* For the rest, there is a single DSA tag, the tag_8021q one */ + *offset = VLAN_HLEN; + *proto = ((__be16 *)skb->data)[(VLAN_HLEN / 2) - 1]; +} + static const struct dsa_device_ops sja1105_netdev_ops = { .name = "sja1105", .proto = DSA_TAG_PROTO_SJA1105, .xmit = sja1105_xmit, .rcv = sja1105_rcv, .filter = sja1105_filter, - .overhead = VLAN_HLEN, + .needed_headroom = VLAN_HLEN, .flow_dissect = sja1105_flow_dissect, .promisc_on_master = true, }; -MODULE_LICENSE("GPL v2"); +DSA_TAG_DRIVER(sja1105_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1105); -module_dsa_tag_driver(sja1105_netdev_ops); +static const struct dsa_device_ops sja1110_netdev_ops = { + .name = "sja1110", + .proto = DSA_TAG_PROTO_SJA1110, + .xmit = sja1110_xmit, + .rcv = sja1110_rcv, + .filter = sja1105_filter, + .flow_dissect = sja1110_flow_dissect, + .needed_headroom = SJA1110_HEADER_LEN + VLAN_HLEN, + .needed_tailroom = SJA1110_RX_TRAILER_LEN + SJA1110_MAX_PADDING_LEN, +}; + +DSA_TAG_DRIVER(sja1110_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1110); + +static struct dsa_tag_driver *sja1105_tag_driver_array[] = { + &DSA_TAG_DRIVER_NAME(sja1105_netdev_ops), + &DSA_TAG_DRIVER_NAME(sja1110_netdev_ops), +}; + +module_dsa_tag_drivers(sja1105_tag_driver_array); + +MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 5b97ede56a0f..ba73804340a5 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -55,8 +55,7 @@ static const struct dsa_device_ops trailer_netdev_ops = { .proto = DSA_TAG_PROTO_TRAILER, .xmit = trailer_xmit, .rcv = trailer_rcv, - .overhead = 4, - .tail_tag = true, + .needed_tailroom = 4, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_xrs700x.c b/net/dsa/tag_xrs700x.c index 858cdf9d2913..a31ff7fcb45f 100644 --- a/net/dsa/tag_xrs700x.c +++ b/net/dsa/tag_xrs700x.c @@ -56,8 +56,7 @@ static const struct dsa_device_ops xrs700x_netdev_ops = { .proto = DSA_TAG_PROTO_XRS700X, .xmit = xrs700x_xmit, .rcv = xrs700x_rcv, - .overhead = 1, - .tail_tag = true, + .needed_tailroom = 1, }; MODULE_LICENSE("GPL"); diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c index 5d38e90895ac..7e6b37a54add 100644 --- a/net/ethtool/eeprom.c +++ b/net/ethtool/eeprom.c @@ -159,9 +159,6 @@ static int eeprom_parse_request(struct ethnl_req_info *req_info, struct nlattr * request->offset = nla_get_u32(tb[ETHTOOL_A_MODULE_EEPROM_OFFSET]); request->length = nla_get_u32(tb[ETHTOOL_A_MODULE_EEPROM_LENGTH]); - if (!request->length) - return -EINVAL; - /* The following set of conditions limit the API to only dump 1/2 * EEPROM page without crossing low page boundary located at offset 128. * This means user may only request dumps of length limited to 128 from @@ -180,10 +177,6 @@ static int eeprom_parse_request(struct ethnl_req_info *req_info, struct nlattr * NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MODULE_EEPROM_LENGTH], "reading cross half page boundary is illegal"); return -EINVAL; - } else if (request->offset >= ETH_MODULE_EEPROM_PAGE_LEN * 2) { - NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MODULE_EEPROM_OFFSET], - "offset is out of bounds"); - return -EINVAL; } else if (request->offset + request->length > ETH_MODULE_EEPROM_PAGE_LEN * 2) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MODULE_EEPROM_LENGTH], "reading cross page boundary is illegal"); @@ -236,8 +229,10 @@ const struct ethnl_request_ops ethnl_module_eeprom_request_ops = { const struct nla_policy ethnl_module_eeprom_get_policy[] = { [ETHTOOL_A_MODULE_EEPROM_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), - [ETHTOOL_A_MODULE_EEPROM_OFFSET] = { .type = NLA_U32 }, - [ETHTOOL_A_MODULE_EEPROM_LENGTH] = { .type = NLA_U32 }, + [ETHTOOL_A_MODULE_EEPROM_OFFSET] = + NLA_POLICY_MAX(NLA_U32, ETH_MODULE_EEPROM_PAGE_LEN * 2 - 1), + [ETHTOOL_A_MODULE_EEPROM_LENGTH] = + NLA_POLICY_RANGE(NLA_U32, 1, ETH_MODULE_EEPROM_PAGE_LEN), [ETHTOOL_A_MODULE_EEPROM_PAGE] = { .type = NLA_U8 }, [ETHTOOL_A_MODULE_EEPROM_BANK] = { .type = NLA_U8 }, [ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS] = diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 88d8a0243f35..a7346346114f 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -315,9 +315,9 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) struct ethnl_req_info *req_info = NULL; const u8 cmd = info->genlhdr->cmd; const struct ethnl_request_ops *ops; + int hdr_len, reply_len; struct sk_buff *rskb; void *reply_payload; - int reply_len; int ret; ops = ethnl_default_requests[cmd]; @@ -346,15 +346,20 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) ret = ops->reply_size(req_info, reply_data); if (ret < 0) goto err_cleanup; - reply_len = ret + ethnl_reply_header_size(); + reply_len = ret; ret = -ENOMEM; - rskb = ethnl_reply_init(reply_len, req_info->dev, ops->reply_cmd, + rskb = ethnl_reply_init(reply_len + ethnl_reply_header_size(), + req_info->dev, ops->reply_cmd, ops->hdr_attr, info, &reply_payload); if (!rskb) goto err_cleanup; + hdr_len = rskb->len; ret = ops->fill_reply(rskb, req_info, reply_data); if (ret < 0) goto err_msg; + WARN_ONCE(rskb->len - hdr_len > reply_len, + "ethnl cmd %d: calculated reply length %d, but consumed %d\n", + cmd, reply_len, rskb->len - hdr_len); if (ops->cleanup_data) ops->cleanup_data(reply_data); diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 8abcbc10796c..3e25a47fd482 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -138,7 +138,7 @@ static inline void ethnl_update_bool32(u32 *dst, const struct nlattr *attr, } /** - * ethnl_update_binary() - update binary data from NLA_BINARY atribute + * ethnl_update_binary() - update binary data from NLA_BINARY attribute * @dst: value to update * @len: destination buffer length * @attr: netlink attribute with new value or null @@ -380,7 +380,7 @@ extern const struct nla_policy ethnl_cable_test_tdr_act_policy[ETHTOOL_A_CABLE_T extern const struct nla_policy ethnl_tunnel_info_get_policy[ETHTOOL_A_TUNNEL_INFO_HEADER + 1]; extern const struct nla_policy ethnl_fec_get_policy[ETHTOOL_A_FEC_HEADER + 1]; extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1]; -extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_DATA + 1]; +extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1]; extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index bb1351c38397..e31949479305 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -397,7 +397,8 @@ void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port, * ensures entries of restarted nodes gets pruned so that they can * re-register and resume communications. */ - if (seq_nr_before(sequence_nr, node->seq_out[port->type])) + if (!(port->dev->features & NETIF_F_HW_HSR_TAG_RM) && + seq_nr_before(sequence_nr, node->seq_out[port->type])) return; node->time_in[port->type] = jiffies; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 2f94d221c00e..54648181dd56 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -318,7 +318,7 @@ lookup_protocol: WARN_ON(!answer_prot->slab); - err = -ENOBUFS; + err = -ENOMEM; sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, kern); if (!sk) goto out; @@ -1720,7 +1720,6 @@ EXPORT_SYMBOL_GPL(snmp_fold_field64); #ifdef CONFIG_IP_MULTICAST static const struct net_protocol igmp_protocol = { .handler = igmp_rcv, - .netns_ok = 1, }; #endif @@ -1733,7 +1732,6 @@ static struct net_protocol tcp_protocol = { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .no_policy = 1, - .netns_ok = 1, .icmp_strict_tag_validation = 1, }; @@ -1746,14 +1744,12 @@ static struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, .no_policy = 1, - .netns_ok = 1, }; static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = icmp_err, .no_policy = 1, - .netns_ok = 1, }; static __net_init int ipv4_mib_init_net(struct net *net) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index fab0958c41be..6eea1e9e998d 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -555,7 +555,6 @@ static int ah4_rcv_cb(struct sk_buff *skb, int err) static const struct xfrm_type ah_type = { - .description = "AH4", .owner = THIS_MODULE, .proto = IPPROTO_AH, .flags = XFRM_TYPE_REPLAY_PROT, diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index e0480c6cebaa..099259fc826a 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -187,8 +187,7 @@ static int __init cipso_v4_cache_init(void) * cipso_v4_cache_invalidate - Invalidates the current CIPSO cache * * Description: - * Invalidates and frees any entries in the CIPSO cache. Returns zero on - * success and negative values on failure. + * Invalidates and frees any entries in the CIPSO cache. * */ void cipso_v4_cache_invalidate(void) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 1c6429c353a9..73721a4448bd 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1955,7 +1955,7 @@ static int inet_validate_link_af(const struct net_device *dev, struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; - if (dev && !__in_dev_get_rcu(dev)) + if (dev && !__in_dev_get_rtnl(dev)) return -EAFNOSUPPORT; err = nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, @@ -1981,7 +1981,7 @@ static int inet_validate_link_af(const struct net_device *dev, static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, struct netlink_ext_ack *extack) { - struct in_device *in_dev = __in_dev_get_rcu(dev); + struct in_device *in_dev = __in_dev_get_rtnl(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; int rem; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 8e3b445a8c21..a09e36c4a413 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -673,7 +673,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); u32 padto; - padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached)); + padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached)); if (skb->len < padto) esp.tfclen = padto - skb->len; } @@ -1199,7 +1199,6 @@ static int esp4_rcv_cb(struct sk_buff *skb, int err) static const struct xfrm_type esp_type = { - .description = "ESP4", .owner = THIS_MODULE, .proto = IPPROTO_ESP, .flags = XFRM_TYPE_REPLAY_PROT, diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 33687cf58286..8e4e9aa12130 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -33,12 +33,11 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, struct xfrm_state *x; __be32 seq; __be32 spi; - int err; if (!pskb_pull(skb, offset)) return NULL; - if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0) + if (xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq) != 0) goto out; xo = xfrm_offload(skb); @@ -343,7 +342,6 @@ static const struct net_offload esp4_offload = { }; static const struct xfrm_type_offload esp_type_offload = { - .description = "ESP4 OFFLOAD", .owner = THIS_MODULE, .proto = IPPROTO_ESP, .input_tail = esp_input_tail, diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 84bb707bd88d..a933bd6345b1 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -371,6 +371,8 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; + } else { + swap(fl4.fl4_sport, fl4.fl4_dport); } if (fib_lookup(net, &fl4, &res, 0)) @@ -1122,10 +1124,8 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) prefix, ifa->ifa_prefixlen, prim, ifa->ifa_rt_priority); - /* Add network specific broadcasts, when it takes a sense */ + /* Add the network broadcast address, when it makes sense */ if (ifa->ifa_prefixlen < 31) { - fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32, - prim, 0); fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask, 32, prim, 0); } @@ -1516,6 +1516,12 @@ static int __net_init ip_fib_net_init(struct net *net) if (err) return err; +#ifdef CONFIG_IP_ROUTE_MULTIPATH + /* Default to 3-tuple */ + net->ipv4.sysctl_fib_multipath_hash_fields = + FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; +#endif + /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index b58db1ca4bfb..e184bcb19943 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -25,7 +25,7 @@ struct fib_alias { #define FA_S_ACCESSED 0x01 -/* Dont write on fa_state unless needed, to keep it shared on all cpus */ +/* Don't write on fa_state unless needed, to keep it shared on all cpus */ static inline void fib_alias_accessed(struct fib_alias *fa) { if (!(fa->fa_state & FA_S_ACCESSED)) diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 5d1e6fe9d838..cbb2b4bb0dfa 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -195,7 +195,6 @@ static int gre_err(struct sk_buff *skb, u32 info) static const struct net_protocol net_gre_protocol = { .handler = gre_rcv, .err_handler = gre_err, - .netns_ok = 1, }; static int __init gre_init(void) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 752e392083e6..c695d294a5df 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -993,14 +993,8 @@ static bool icmp_redirect(struct sk_buff *skb) static bool icmp_echo(struct sk_buff *skb) { - struct icmp_ext_hdr *ext_hdr, _ext_hdr; - struct icmp_ext_echo_iio *iio, _iio; struct icmp_bxm icmp_param; - struct net_device *dev; - char buff[IFNAMSIZ]; struct net *net; - u16 ident_len; - u8 status; net = dev_net(skb_dst(skb)->dev); /* should there be an ICMP stat for ignored echos? */ @@ -1013,20 +1007,46 @@ static bool icmp_echo(struct sk_buff *skb) icmp_param.data_len = skb->len; icmp_param.head_len = sizeof(struct icmphdr); - if (icmp_param.data.icmph.type == ICMP_ECHO) { + if (icmp_param.data.icmph.type == ICMP_ECHO) icmp_param.data.icmph.type = ICMP_ECHOREPLY; - goto send_reply; - } - if (!net->ipv4.sysctl_icmp_echo_enable_probe) + else if (!icmp_build_probe(skb, &icmp_param.data.icmph)) return true; + + icmp_reply(&icmp_param, skb); + return true; +} + +/* Helper for icmp_echo and icmpv6_echo_reply. + * Searches for net_device that matches PROBE interface identifier + * and builds PROBE reply message in icmphdr. + * + * Returns false if PROBE responses are disabled via sysctl + */ + +bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) +{ + struct icmp_ext_hdr *ext_hdr, _ext_hdr; + struct icmp_ext_echo_iio *iio, _iio; + struct net *net = dev_net(skb->dev); + struct net_device *dev; + char buff[IFNAMSIZ]; + u16 ident_len; + u8 status; + + if (!net->ipv4.sysctl_icmp_echo_enable_probe) + return false; + /* We currently only support probing interfaces on the proxy node * Check to ensure L-bit is set */ - if (!(ntohs(icmp_param.data.icmph.un.echo.sequence) & 1)) - return true; + if (!(ntohs(icmphdr->un.echo.sequence) & 1)) + return false; /* Clear status bits in reply message */ - icmp_param.data.icmph.un.echo.sequence &= htons(0xFF00); - icmp_param.data.icmph.type = ICMP_EXT_ECHOREPLY; + icmphdr->un.echo.sequence &= htons(0xFF00); + if (icmphdr->type == ICMP_EXT_ECHO) + icmphdr->type = ICMP_EXT_ECHOREPLY; + else + icmphdr->type = ICMPV6_EXT_ECHO_REPLY; ext_hdr = skb_header_pointer(skb, 0, sizeof(_ext_hdr), &_ext_hdr); /* Size of iio is class_type dependent. * Only check header here and assign length based on ctype in the switch statement @@ -1066,7 +1086,7 @@ static bool icmp_echo(struct sk_buff *skb) if (ident_len != sizeof(iio->ident.addr.ctype3_hdr) + sizeof(struct in_addr)) goto send_mal_query; - dev = ip_dev_find(net, iio->ident.addr.ip_addr.ipv4_addr.s_addr); + dev = ip_dev_find(net, iio->ident.addr.ip_addr.ipv4_addr); break; #if IS_ENABLED(CONFIG_IPV6) case ICMP_AFI_IP6: @@ -1087,8 +1107,8 @@ static bool icmp_echo(struct sk_buff *skb) goto send_mal_query; } if (!dev) { - icmp_param.data.icmph.code = ICMP_EXT_CODE_NO_IF; - goto send_reply; + icmphdr->code = ICMP_EXT_CODE_NO_IF; + return true; } /* Fill bits in reply message */ if (dev->flags & IFF_UP) @@ -1098,14 +1118,13 @@ static bool icmp_echo(struct sk_buff *skb) if (!list_empty(&rcu_dereference(dev->ip6_ptr)->addr_list)) status |= ICMP_EXT_ECHOREPLY_IPV6; dev_put(dev); - icmp_param.data.icmph.un.echo.sequence |= htons(status); -send_reply: - icmp_reply(&icmp_param, skb); - return true; + icmphdr->un.echo.sequence |= htons(status); + return true; send_mal_query: - icmp_param.data.icmph.code = ICMP_EXT_CODE_MAL_QUERY; - goto send_reply; + icmphdr->code = ICMP_EXT_CODE_MAL_QUERY; + return true; } +EXPORT_SYMBOL_GPL(icmp_build_probe); /* * Handle ICMP Timestamp requests. diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index fd472eae4f5c..754013fa393b 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -135,10 +135,18 @@ static int inet_csk_bind_conflict(const struct sock *sk, bool relax, bool reuseport_ok) { struct sock *sk2; + bool reuseport_cb_ok; bool reuse = sk->sk_reuse; bool reuseport = !!sk->sk_reuseport; + struct sock_reuseport *reuseport_cb; kuid_t uid = sock_i_uid((struct sock *)sk); + rcu_read_lock(); + reuseport_cb = rcu_dereference(sk->sk_reuseport_cb); + /* paired with WRITE_ONCE() in __reuseport_(add|detach)_closed_sock */ + reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks); + rcu_read_unlock(); + /* * Unlike other sk lookup places we do not check * for sk_net here, since _all_ the socks listed @@ -156,14 +164,14 @@ static int inet_csk_bind_conflict(const struct sock *sk, if ((!relax || (!reuseport_ok && reuseport && sk2->sk_reuseport && - !rcu_access_pointer(sk->sk_reuseport_cb) && + reuseport_cb_ok && (sk2->sk_state == TCP_TIME_WAIT || uid_eq(uid, sock_i_uid(sk2))))) && inet_rcv_saddr_equal(sk, sk2, true)) break; } else if (!reuseport_ok || !reuseport || !sk2->sk_reuseport || - rcu_access_pointer(sk->sk_reuseport_cb) || + !reuseport_cb_ok || (sk2->sk_state != TCP_TIME_WAIT && !uid_eq(uid, sock_i_uid(sk2)))) { if (inet_rcv_saddr_equal(sk, sk2, true)) @@ -687,6 +695,66 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) } EXPORT_SYMBOL(inet_rtx_syn_ack); +static struct request_sock *inet_reqsk_clone(struct request_sock *req, + struct sock *sk) +{ + struct sock *req_sk, *nreq_sk; + struct request_sock *nreq; + + nreq = kmem_cache_alloc(req->rsk_ops->slab, GFP_ATOMIC | __GFP_NOWARN); + if (!nreq) { + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); + + /* paired with refcount_inc_not_zero() in reuseport_migrate_sock() */ + sock_put(sk); + return NULL; + } + + req_sk = req_to_sk(req); + nreq_sk = req_to_sk(nreq); + + memcpy(nreq_sk, req_sk, + offsetof(struct sock, sk_dontcopy_begin)); + memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, + req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end)); + + sk_node_init(&nreq_sk->sk_node); + nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping; +#ifdef CONFIG_XPS + nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping; +#endif + nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu; + + nreq->rsk_listener = sk; + + /* We need not acquire fastopenq->lock + * because the child socket is locked in inet_csk_listen_stop(). + */ + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) + rcu_assign_pointer(tcp_sk(nreq->sk)->fastopen_rsk, nreq); + + return nreq; +} + +static void reqsk_queue_migrated(struct request_sock_queue *queue, + const struct request_sock *req) +{ + if (req->num_timeout == 0) + atomic_inc(&queue->young); + atomic_inc(&queue->qlen); +} + +static void reqsk_migrate_reset(struct request_sock *req) +{ + req->saved_syn = NULL; +#if IS_ENABLED(CONFIG_IPV6) + inet_rsk(req)->ipv6_opt = NULL; + inet_rsk(req)->pktopts = NULL; +#else + inet_rsk(req)->ireq_opt = NULL; +#endif +} + /* return true if req was found in the ehash table */ static bool reqsk_queue_unlink(struct request_sock *req) { @@ -727,15 +795,39 @@ EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); static void reqsk_timer_handler(struct timer_list *t) { struct request_sock *req = from_timer(req, t, rsk_timer); + struct request_sock *nreq = NULL, *oreq = req; struct sock *sk_listener = req->rsk_listener; - struct net *net = sock_net(sk_listener); - struct inet_connection_sock *icsk = inet_csk(sk_listener); - struct request_sock_queue *queue = &icsk->icsk_accept_queue; + struct inet_connection_sock *icsk; + struct request_sock_queue *queue; + struct net *net; int max_syn_ack_retries, qlen, expire = 0, resend = 0; - if (inet_sk_state_load(sk_listener) != TCP_LISTEN) - goto drop; + if (inet_sk_state_load(sk_listener) != TCP_LISTEN) { + struct sock *nsk; + nsk = reuseport_migrate_sock(sk_listener, req_to_sk(req), NULL); + if (!nsk) + goto drop; + + nreq = inet_reqsk_clone(req, nsk); + if (!nreq) + goto drop; + + /* The new timer for the cloned req can decrease the 2 + * by calling inet_csk_reqsk_queue_drop_and_put(), so + * hold another count to prevent use-after-free and + * call reqsk_put() just before return. + */ + refcount_set(&nreq->rsk_refcnt, 2 + 1); + timer_setup(&nreq->rsk_timer, reqsk_timer_handler, TIMER_PINNED); + reqsk_queue_migrated(&inet_csk(nsk)->icsk_accept_queue, req); + + req = nreq; + sk_listener = nsk; + } + + icsk = inet_csk(sk_listener); + net = sock_net(sk_listener); max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries; /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. @@ -754,6 +846,7 @@ static void reqsk_timer_handler(struct timer_list *t) * embrions; and abort old ones without pity, if old * ones are about to clog our table. */ + queue = &icsk->icsk_accept_queue; qlen = reqsk_queue_len(queue); if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) { int young = reqsk_queue_len_young(queue) << 1; @@ -778,10 +871,39 @@ static void reqsk_timer_handler(struct timer_list *t) atomic_dec(&queue->young); timeo = min(TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); mod_timer(&req->rsk_timer, jiffies + timeo); + + if (!nreq) + return; + + if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) { + /* delete timer */ + inet_csk_reqsk_queue_drop(sk_listener, nreq); + goto no_ownership; + } + + __NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQSUCCESS); + reqsk_migrate_reset(oreq); + reqsk_queue_removed(&inet_csk(oreq->rsk_listener)->icsk_accept_queue, oreq); + reqsk_put(oreq); + + reqsk_put(nreq); return; } + + /* Even if we can clone the req, we may need not retransmit any more + * SYN+ACKs (nreq->num_timeout > max_syn_ack_retries, etc), or another + * CPU may win the "own_req" race so that inet_ehash_insert() fails. + */ + if (nreq) { + __NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQFAILURE); +no_ownership: + reqsk_migrate_reset(nreq); + reqsk_queue_removed(queue, nreq); + __reqsk_free(nreq); + } + drop: - inet_csk_reqsk_queue_drop_and_put(sk_listener, req); + inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq); } static void reqsk_queue_hash_req(struct request_sock *req, @@ -997,12 +1119,42 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, bool own_req) { if (own_req) { - inet_csk_reqsk_queue_drop(sk, req); - reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); - if (inet_csk_reqsk_queue_add(sk, req, child)) + inet_csk_reqsk_queue_drop(req->rsk_listener, req); + reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req); + + if (sk != req->rsk_listener) { + /* another listening sk has been selected, + * migrate the req to it. + */ + struct request_sock *nreq; + + /* hold a refcnt for the nreq->rsk_listener + * which is assigned in inet_reqsk_clone() + */ + sock_hold(sk); + nreq = inet_reqsk_clone(req, sk); + if (!nreq) { + inet_child_forget(sk, req, child); + goto child_put; + } + + refcount_set(&nreq->rsk_refcnt, 1); + if (inet_csk_reqsk_queue_add(sk, nreq, child)) { + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQSUCCESS); + reqsk_migrate_reset(req); + reqsk_put(req); + return child; + } + + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); + reqsk_migrate_reset(nreq); + __reqsk_free(nreq); + } else if (inet_csk_reqsk_queue_add(sk, req, child)) { return child; + } } /* Too bad, another child took ownership of the request, undo. */ +child_put: bh_unlock_sock(child); sock_put(child); return NULL; @@ -1028,14 +1180,40 @@ void inet_csk_listen_stop(struct sock *sk) * of the variants now. --ANK */ while ((req = reqsk_queue_remove(queue, sk)) != NULL) { - struct sock *child = req->sk; + struct sock *child = req->sk, *nsk; + struct request_sock *nreq; local_bh_disable(); bh_lock_sock(child); WARN_ON(sock_owned_by_user(child)); sock_hold(child); + nsk = reuseport_migrate_sock(sk, child, NULL); + if (nsk) { + nreq = inet_reqsk_clone(req, nsk); + if (nreq) { + refcount_set(&nreq->rsk_refcnt, 1); + + if (inet_csk_reqsk_queue_add(nsk, nreq, child)) { + __NET_INC_STATS(sock_net(nsk), + LINUX_MIB_TCPMIGRATEREQSUCCESS); + reqsk_migrate_reset(req); + } else { + __NET_INC_STATS(sock_net(nsk), + LINUX_MIB_TCPMIGRATEREQFAILURE); + reqsk_migrate_reset(nreq); + __reqsk_free(nreq); + } + + /* inet_csk_reqsk_queue_add() has already + * called inet_child_forget() on failure case. + */ + goto skip_child_forget; + } + } + inet_child_forget(sk, req, child); +skip_child_forget: reqsk_put(req); bh_unlock_sock(child); local_bh_enable(); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 93474b1bea4e..e65f4ef024a4 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -416,7 +416,7 @@ EXPORT_SYMBOL_GPL(inet_sk_diag_fill); static int inet_twsk_diag_fill(struct sock *sk, struct sk_buff *skb, struct netlink_callback *cb, - u16 nlmsg_flags) + u16 nlmsg_flags, bool net_admin) { struct inet_timewait_sock *tw = inet_twsk(sk); struct inet_diag_msg *r; @@ -444,6 +444,12 @@ static int inet_twsk_diag_fill(struct sock *sk, r->idiag_uid = 0; r->idiag_inode = 0; + if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, + tw->tw_mark)) { + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; + } + nlmsg_end(skb, nlh); return 0; } @@ -494,7 +500,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, u16 nlmsg_flags, bool net_admin) { if (sk->sk_state == TCP_TIME_WAIT) - return inet_twsk_diag_fill(sk, skb, cb, nlmsg_flags); + return inet_twsk_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); if (sk->sk_state == TCP_NEW_SYN_RECV) return inet_req_diag_fill(sk, skb, cb, nlmsg_flags, net_admin); @@ -801,6 +807,8 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) entry.mark = sk->sk_mark; else if (sk->sk_state == TCP_NEW_SYN_RECV) entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark; + else if (sk->sk_state == TCP_TIME_WAIT) + entry.mark = inet_twsk(sk)->tw_mark; else entry.mark = 0; #ifdef CONFIG_SOCK_CGROUP_DATA diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c96866a53a66..80aeaf9e6e16 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -697,7 +697,7 @@ void inet_unhash(struct sock *sk) goto unlock; if (rcu_access_pointer(sk->sk_reuseport_cb)) - reuseport_detach_sock(sk); + reuseport_stop_listen_sock(sk); if (ilb) { inet_unhash2(hashinfo, sk); ilb->count--; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index a68bf4c6fe9b..12dca0c85f3c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -107,6 +107,8 @@ module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static struct rtnl_link_ops ipgre_link_ops __read_mostly; +static const struct header_ops ipgre_header_ops; + static int ipgre_tunnel_init(struct net_device *dev); static void erspan_build_header(struct sk_buff *skb, u32 id, u32 index, @@ -364,7 +366,10 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, raw_proto, false) < 0) goto drop; - if (tunnel->dev->type != ARPHRD_NONE) + /* Special case for ipgre_header_parse(), which expects the + * mac_header to point to the outer IP header. + */ + if (tunnel->dev->header_ops == &ipgre_header_ops) skb_pop_mac_header(skb); else skb_reset_mac_header(skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c3efc7d658f6..8d8a8da3ae7e 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1054,7 +1054,7 @@ static int __ip_append_data(struct sock *sk, unsigned int datalen; unsigned int fraglen; unsigned int fraggap; - unsigned int alloclen; + unsigned int alloclen, alloc_extra; unsigned int pagedlen; struct sk_buff *skb_prev; alloc_new_skb: @@ -1074,17 +1074,8 @@ alloc_new_skb: fraglen = datalen + fragheaderlen; pagedlen = 0; - if ((flags & MSG_MORE) && - !(rt->dst.dev->features&NETIF_F_SG)) - alloclen = mtu; - else if (!paged) - alloclen = fraglen; - else { - alloclen = min_t(int, fraglen, MAX_HEADER); - pagedlen = fraglen - alloclen; - } - - alloclen += exthdrlen; + alloc_extra = hh_len + 15; + alloc_extra += exthdrlen; /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, @@ -1092,17 +1083,30 @@ alloc_new_skb: * the last. */ if (datalen == length + fraggap) - alloclen += rt->dst.trailer_len; + alloc_extra += rt->dst.trailer_len; + + if ((flags & MSG_MORE) && + !(rt->dst.dev->features&NETIF_F_SG)) + alloclen = mtu; + else if (!paged && + (fraglen + alloc_extra < SKB_MAX_ALLOC || + !(rt->dst.dev->features & NETIF_F_SG))) + alloclen = fraglen; + else { + alloclen = min_t(int, fraglen, MAX_HEADER); + pagedlen = fraglen - alloclen; + } + + alloclen += alloc_extra; if (transhdrlen) { - skb = sock_alloc_send_skb(sk, - alloclen + hh_len + 15, + skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) - skb = alloc_skb(alloclen + hh_len + 15, + skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index bbb56f5e06dd..366094c1ce6c 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -153,7 +153,6 @@ static int ipcomp4_rcv_cb(struct sk_buff *skb, int err) } static const struct xfrm_type ipcomp_type = { - .description = "IPCOMP4", .owner = THIS_MODULE, .proto = IPPROTO_COMP, .init_state = ipcomp4_init_state, diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index d5bfa087c23a..266c65577ba6 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -242,6 +242,8 @@ static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) if (!tun_dst) return 0; } + skb_reset_mac_header(skb); + return ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); } diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 939792a38814..7b12a40dd465 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1317,7 +1317,7 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags) } /* called from ip_ra_control(), before an RCU grace period, - * we dont need to call synchronize_rcu() here + * we don't need to call synchronize_rcu() here */ static void mrtsock_destruct(struct sock *sk) { @@ -1938,7 +1938,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, if (c->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { struct mfc_cache *cache_proxy; - /* For an (*,G) entry, we only check that the incomming + /* For an (*,G) entry, we only check that the incoming * interface is part of the static tree. */ cache_proxy = mr_mfc_find_any_parent(mrt, vif); @@ -3007,7 +3007,6 @@ static const struct seq_operations ipmr_mfc_seq_ops = { #ifdef CONFIG_IP_PIMSM_V2 static const struct net_protocol pim_protocol = { .handler = pim_rcv, - .netns_ok = 1, }; #endif diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index ff437e4ed6db..55fc23a8f7a7 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -27,7 +27,7 @@ static void nft_reject_ipv4_eval(const struct nft_expr *expr, nf_send_unreach(pkt->skb, priv->icmp_code, nft_hook(pkt)); break; case NFT_REJECT_TCP_RST: - nf_send_reset(nft_net(pkt), pkt->xt.state->sk, pkt->skb, + nf_send_reset(nft_net(pkt), nft_sk(pkt), pkt->skb, nft_hook(pkt)); break; default: diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 95a718397fd1..1e44a43acfe2 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -573,7 +573,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info) } } sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); out: sock_put(sk); } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 6d46297a99f8..b0d3a09dc84e 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -295,6 +295,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TcpDuplicateDataRehash", LINUX_MIB_TCPDUPLICATEDATAREHASH), SNMP_MIB_ITEM("TCPDSACKRecvSegs", LINUX_MIB_TCPDSACKRECVSEGS), SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS), + SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS), + SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index 9a8c0892622b..6913979948d7 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -31,12 +31,6 @@ EXPORT_SYMBOL(inet_offloads); int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol) { - if (!prot->netns_ok) { - pr_err("Protocol %u is not namespace aware, cannot register.\n", - protocol); - return -EINVAL; - } - return !cmpxchg((const struct net_protocol **)&inet_protos[protocol], NULL, prot) ? 0 : -1; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 50a73178d63a..bb446e60cf58 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -280,7 +280,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) if (inet->recverr || harderr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } } @@ -929,7 +929,7 @@ int raw_abort(struct sock *sk, int err) lock_sock(sk); sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); __udp_disconnect(sk, 0); release_sock(sk); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6a36ac98476f..99c06944501a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1306,7 +1306,7 @@ INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) - return mtu; + goto out; mtu = READ_ONCE(dst->dev->mtu); @@ -1315,6 +1315,7 @@ INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = 576; } +out: mtu = min_t(unsigned int, mtu, IP_MAX_MTU); return mtu - lwtunnel_headroom(dst->lwtstate, mtu); @@ -1906,13 +1907,128 @@ out: hash_keys->addrs.v4addrs.dst = key_iph->daddr; } +static u32 fib_multipath_custom_hash_outer(const struct net *net, + const struct sk_buff *skb, + bool *p_has_inner) +{ + u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + struct flow_keys keys, hash_keys; + + if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) + return 0; + + memset(&hash_keys, 0, sizeof(hash_keys)); + skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); + + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) + hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) + hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) + hash_keys.basic.ip_proto = keys.basic.ip_proto; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) + hash_keys.ports.src = keys.ports.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) + hash_keys.ports.dst = keys.ports.dst; + + *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); + return flow_hash_from_keys(&hash_keys); +} + +static u32 fib_multipath_custom_hash_inner(const struct net *net, + const struct sk_buff *skb, + bool has_inner) +{ + u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + struct flow_keys keys, hash_keys; + + /* We assume the packet carries an encapsulation, but if none was + * encountered during dissection of the outer flow, then there is no + * point in calling the flow dissector again. + */ + if (!has_inner) + return 0; + + if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) + return 0; + + memset(&hash_keys, 0, sizeof(hash_keys)); + skb_flow_dissect_flow_keys(skb, &keys, 0); + + if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) + return 0; + + if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) + hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) + hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; + } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) + hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) + hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) + hash_keys.tags.flow_label = keys.tags.flow_label; + } + + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) + hash_keys.basic.ip_proto = keys.basic.ip_proto; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) + hash_keys.ports.src = keys.ports.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) + hash_keys.ports.dst = keys.ports.dst; + + return flow_hash_from_keys(&hash_keys); +} + +static u32 fib_multipath_custom_hash_skb(const struct net *net, + const struct sk_buff *skb) +{ + u32 mhash, mhash_inner; + bool has_inner = true; + + mhash = fib_multipath_custom_hash_outer(net, skb, &has_inner); + mhash_inner = fib_multipath_custom_hash_inner(net, skb, has_inner); + + return jhash_2words(mhash, mhash_inner, 0); +} + +static u32 fib_multipath_custom_hash_fl4(const struct net *net, + const struct flowi4 *fl4) +{ + u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + struct flow_keys hash_keys; + + if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) + return 0; + + memset(&hash_keys, 0, sizeof(hash_keys)); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) + hash_keys.addrs.v4addrs.src = fl4->saddr; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) + hash_keys.addrs.v4addrs.dst = fl4->daddr; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) + hash_keys.basic.ip_proto = fl4->flowi4_proto; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) + hash_keys.ports.src = fl4->fl4_sport; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) + hash_keys.ports.dst = fl4->fl4_dport; + + return flow_hash_from_keys(&hash_keys); +} + /* if skb is set it will be used and fl4 can be NULL */ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys) { u32 multipath_hash = fl4 ? fl4->flowi4_multipath_hash : 0; struct flow_keys hash_keys; - u32 mhash; + u32 mhash = 0; switch (net->ipv4.sysctl_fib_multipath_hash_policy) { case 0: @@ -1924,6 +2040,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } + mhash = flow_hash_from_keys(&hash_keys); break; case 1: /* skb is currently provided only when forwarding */ @@ -1957,6 +2074,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.ports.dst = fl4->fl4_dport; hash_keys.basic.ip_proto = fl4->flowi4_proto; } + mhash = flow_hash_from_keys(&hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); @@ -1987,9 +2105,15 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } + mhash = flow_hash_from_keys(&hash_keys); + break; + case 3: + if (skb) + mhash = fib_multipath_custom_hash_skb(net, skb); + else + mhash = fib_multipath_custom_hash_fl4(net, fl4); break; } - mhash = flow_hash_from_keys(&hash_keys); if (multipath_hash) mhash = jhash_2words(mhash, multipath_hash, 0); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index a62934b9f15a..6f1e64d49232 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -29,6 +30,7 @@ #include static int two = 2; +static int three __maybe_unused = 3; static int four = 4; static int thousand = 1000; static int tcp_retr1_max = 255; @@ -48,6 +50,8 @@ static int ip_ping_group_range_min[] = { 0, 0 }; static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX }; static u32 u32_max_div_HZ = UINT_MAX / HZ; static int one_day_secs = 24 * 3600; +static u32 fib_multipath_hash_fields_all_mask __maybe_unused = + FIB_MULTIPATH_HASH_FIELD_ALL_MASK; /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -461,6 +465,22 @@ static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, return ret; } + +static int proc_fib_multipath_hash_fields(struct ctl_table *table, int write, + void *buffer, size_t *lenp, + loff_t *ppos) +{ + struct net *net; + int ret; + + net = container_of(table->data, struct net, + ipv4.sysctl_fib_multipath_hash_fields); + ret = proc_douintvec_minmax(table, write, buffer, lenp, ppos); + if (write && ret == 0) + call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net); + + return ret; +} #endif static struct ctl_table ipv4_table[] = { @@ -940,6 +960,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dou8vec_minmax, }, #endif + { + .procname = "tcp_migrate_req", + .data = &init_net.ipv4.sysctl_tcp_migrate_req, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, { .procname = "tcp_reordering", .data = &init_net.ipv4.sysctl_tcp_reordering, @@ -1050,7 +1079,16 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_fib_multipath_hash_policy, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = &three, + }, + { + .procname = "fib_multipath_hash_fields", + .data = &init_net.ipv4.sysctl_fib_multipath_hash_fields, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_fib_multipath_hash_fields, + .extra1 = SYSCTL_ONE, + .extra2 = &fib_multipath_hash_fields_all_mask, }, #endif { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f1c1f9e3de72..d5ab5f243640 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1738,8 +1738,8 @@ int tcp_set_rcvlowat(struct sock *sk, int val) } EXPORT_SYMBOL(tcp_set_rcvlowat); -static void tcp_update_recv_tstamps(struct sk_buff *skb, - struct scm_timestamping_internal *tss) +void tcp_update_recv_tstamps(struct sk_buff *skb, + struct scm_timestamping_internal *tss) { if (skb->tstamp) tss->ts[0] = ktime_to_timespec64(skb->tstamp); @@ -2024,8 +2024,6 @@ static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, } #define TCP_VALID_ZC_MSG_FLAGS (TCP_CMSG_TS) -static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, - struct scm_timestamping_internal *tss); static void tcp_zc_finalize_rx_tstamp(struct sock *sk, struct tcp_zerocopy_receive *zc, struct scm_timestamping_internal *tss) @@ -2095,8 +2093,8 @@ static int tcp_zerocopy_receive(struct sock *sk, mmap_read_lock(current->mm); - vma = find_vma(current->mm, address); - if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) { + vma = vma_lookup(current->mm, address); + if (!vma || vma->vm_ops != &tcp_vm_ops) { mmap_read_unlock(current->mm); return -EINVAL; } @@ -2197,8 +2195,8 @@ out: #endif /* Similar to __sock_recv_timestamp, but does not require an skb */ -static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, - struct scm_timestamping_internal *tss) +void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, + struct scm_timestamping_internal *tss) { int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); bool has_timestamping = false; @@ -3061,7 +3059,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_frag.offset = 0; } - sk->sk_error_report(sk); + sk_error_report(sk); return 0; } EXPORT_SYMBOL(tcp_disconnect); @@ -4450,7 +4448,7 @@ int tcp_abort(struct sock *sk, int err) sk->sk_err = err; /* This barrier is coupled with smp_rmb() in tcp_poll() */ smp_wmb(); - sk->sk_error_report(sk); + sk_error_report(sk); if (tcp_need_reset(sk->sk_state)) tcp_send_active_reset(sk, GFP_ATOMIC); tcp_done(sk); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index ad9d17923fc5..f26916a62f25 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -163,6 +163,28 @@ static bool tcp_bpf_stream_read(const struct sock *sk) return !empty; } +static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock, + long timeo) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return 1; + + if (!timeo) + return ret; + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + ret = sk_wait_event(sk, &timeo, + !list_empty(&psock->ingress_msg) || + !skb_queue_empty(&sk->sk_receive_queue), &wait); + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + return ret; +} + static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { @@ -184,11 +206,11 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { - int data, err = 0; long timeo; + int data; timeo = sock_rcvtimeo(sk, nonblock); - data = sk_msg_wait_data(sk, psock, flags, timeo, &err); + data = tcp_msg_wait_data(sk, psock, timeo); if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; @@ -196,14 +218,9 @@ msg_bytes_ready: sk_psock_put(sk, psock); return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); } - if (err) { - ret = err; - goto out; - } copied = -EAGAIN; } ret = copied; -out: release_sock(sk); sk_psock_put(sk, psock); return ret; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index af2814c9342a..47c32604d38f 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -526,7 +526,7 @@ bool tcp_fastopen_active_should_disable(struct sock *sk) if (!tfo_da_times) return false; - /* Limit timout to max: 2^6 * initial timeout */ + /* Limit timeout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); timeout = multiplier * tfo_bh_timeout * HZ; if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout)) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f3bbc2d37c8b..71974ff9411a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2817,8 +2817,17 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack, *rexmit = REXMIT_LOST; } +static bool tcp_force_fast_retransmit(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + return after(tcp_highest_sack_seq(tp), + tp->snd_una + tp->reordering * tp->mss_cache); +} + /* Undo during fast recovery after partial ACK. */ -static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una) +static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una, + bool *do_lost) { struct tcp_sock *tp = tcp_sk(sk); @@ -2843,7 +2852,9 @@ static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una) tcp_undo_cwnd_reduction(sk, true); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO); tcp_try_keep_open(sk); - return true; + } else { + /* Partial ACK arrived. Force fast retransmit. */ + *do_lost = tcp_force_fast_retransmit(sk); } return false; } @@ -2867,14 +2878,6 @@ static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag) } } -static bool tcp_force_fast_retransmit(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - return after(tcp_highest_sack_seq(tp), - tp->snd_una + tp->reordering * tp->mss_cache); -} - /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -2944,17 +2947,21 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, if (!(flag & FLAG_SND_UNA_ADVANCED)) { if (tcp_is_reno(tp)) tcp_add_reno_sack(sk, num_dupack, ece_ack); - } else { - if (tcp_try_undo_partial(sk, prior_snd_una)) - return; - /* Partial ACK arrived. Force fast retransmit. */ - do_lost = tcp_force_fast_retransmit(sk); - } - if (tcp_try_undo_dsack(sk)) { - tcp_try_keep_open(sk); + } else if (tcp_try_undo_partial(sk, prior_snd_una, &do_lost)) return; - } + + if (tcp_try_undo_dsack(sk)) + tcp_try_keep_open(sk); + tcp_identify_packet_loss(sk, ack_flag); + if (icsk->icsk_ca_state != TCP_CA_Recovery) { + if (!tcp_time_to_recover(sk, flag)) + return; + /* Undo reverts the recovery state. If loss is evident, + * starts a new recovery (e.g. reordering then loss); + */ + tcp_enter_recovery(sk, ece_ack); + } break; case TCP_CA_Loss: tcp_process_loss(sk, flag, num_dupack, rexmit); @@ -4264,7 +4271,7 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb) tcp_done(sk); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } /* @@ -5887,6 +5894,7 @@ step5: return; csum_error: + trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 312184cead57..e66ad6bfe808 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -585,7 +585,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) if (!sock_owned_by_user(sk)) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); tcp_done(sk); } else { @@ -613,7 +613,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) inet = inet_sk(sk); if (!sock_owned_by_user(sk) && inet->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else { /* Only an error on timeout */ sk->sk_err_soft = err; } @@ -1731,6 +1731,7 @@ discard: return 0; csum_err: + trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; @@ -1801,6 +1802,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_checksum_complete(skb))) { bh_unlock_sock(sk); + trace_tcp_bad_csum(skb); __TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); return true; @@ -2000,13 +2002,21 @@ process: goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { - inet_csk_reqsk_queue_drop_and_put(sk, req); - goto lookup; + nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb); + if (!nsk) { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } + sk = nsk; + /* reuseport_migrate_sock() has already held one sk_refcnt + * before returning. + */ + } else { + /* We own a reference on the listener, increase it again + * as we might lose it too soon. + */ + sock_hold(sk); } - /* We own a reference on the listener, increase it again - * as we might lose it too soon. - */ - sock_hold(sk); refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { @@ -2098,6 +2108,7 @@ no_tcp_socket: if (tcp_checksum_complete(skb)) { csum_error: + trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7513ba45553d..0a4f3f16140a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -775,8 +775,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, goto listen_overflow; if (own_req && rsk_drop_req(req)) { - reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); - inet_csk_reqsk_queue_drop_and_put(sk, req); + reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req); + inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req); return child; } @@ -786,6 +786,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, return inet_csk_complete_hashdance(sk, child, req, own_req); listen_overflow: + if (sk != req->rsk_listener) + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); + if (!sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow) { inet_rsk(req)->acked = 1; return NULL; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4ef08079ccfa..20cf4a98c69d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -68,7 +68,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) static void tcp_write_err(struct sock *sk) { sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; - sk->sk_error_report(sk); + sk_error_report(sk); tcp_write_queue_purge(sk); tcp_done(sk); @@ -441,7 +441,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) * This function gets called when the kernel timer for a TCP packet * of this socket expires. * - * It handles retransmission, timer adjustment and other necesarry measures. + * It handles retransmission, timer adjustment and other necessary measures. * * Returns: Nothing (void) */ @@ -766,7 +766,7 @@ static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer) if (!sock_owned_by_user(sk)) { if (tp->compressed_ack) { /* Since we have to send one ack finally, - * substract one from tp->compressed_ack to keep + * subtract one from tp->compressed_ack to keep * LINUX_MIB_TCPACKCOMPRESSED accurate. */ tp->compressed_ack--; diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 3bb448761ca3..07c4c93b9fdb 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -221,7 +221,7 @@ static struct tcp_congestion_ops tcp_yeah __read_mostly = { static int __init tcp_yeah_register(void) { - BUG_ON(sizeof(struct yeah) > ICSK_CA_PRIV_SIZE); + BUILD_BUG_ON(sizeof(struct yeah) > ICSK_CA_PRIV_SIZE); tcp_register_congestion_control(&tcp_yeah); return 0; } diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index e44aaf41a138..5048c47c79b2 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -218,7 +218,6 @@ static const struct net_protocol tunnel4_protocol = { .handler = tunnel4_rcv, .err_handler = tunnel4_err, .no_policy = 1, - .netns_ok = 1, }; #if IS_ENABLED(CONFIG_IPV6) @@ -226,7 +225,6 @@ static const struct net_protocol tunnel64_protocol = { .handler = tunnel64_rcv, .err_handler = tunnel64_err, .no_policy = 1, - .netns_ok = 1, }; #endif @@ -235,7 +233,6 @@ static const struct net_protocol tunnelmpls4_protocol = { .handler = tunnelmpls4_rcv, .err_handler = tunnelmpls4_err, .no_policy = 1, - .netns_ok = 1, }; #endif diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1307ad0d3b9e..62682807b4b2 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -776,7 +776,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1)); sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); out: return 0; } @@ -1798,11 +1798,13 @@ int udp_read_sock(struct sock *sk, read_descriptor_t *desc, if (used <= 0) { if (!copied) copied = used; + kfree_skb(skb); break; } else if (used <= skb->len) { copied += used; } + kfree_skb(skb); if (!desc->count) break; } @@ -2867,7 +2869,7 @@ int udp_abort(struct sock *sk, int err) goto out; sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); __udp_disconnect(sk, 0); out: diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 954c4591a6fd..45b8782aec0c 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -21,6 +21,45 @@ static int sk_udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, return udp_prot.recvmsg(sk, msg, len, noblock, flags, addr_len); } +static bool udp_sk_has_data(struct sock *sk) +{ + return !skb_queue_empty(&udp_sk(sk)->reader_queue) || + !skb_queue_empty(&sk->sk_receive_queue); +} + +static bool psock_has_data(struct sk_psock *psock) +{ + return !skb_queue_empty(&psock->ingress_skb) || + !sk_psock_queue_empty(psock); +} + +#define udp_msg_has_data(__sk, __psock) \ + ({ udp_sk_has_data(__sk) || psock_has_data(__psock); }) + +static int udp_msg_wait_data(struct sock *sk, struct sk_psock *psock, + long timeo) +{ + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; + + if (sk->sk_shutdown & RCV_SHUTDOWN) + return 1; + + if (!timeo) + return ret; + + add_wait_queue(sk_sleep(sk), &wait); + sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); + ret = udp_msg_has_data(sk, psock); + if (!ret) { + wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); + ret = udp_msg_has_data(sk, psock); + } + sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); + remove_wait_queue(sk_sleep(sk), &wait); + return ret; +} + static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { @@ -34,8 +73,7 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (unlikely(!psock)) return sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - lock_sock(sk); - if (sk_psock_queue_empty(psock)) { + if (!psock_has_data(psock)) { ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); goto out; } @@ -43,26 +81,21 @@ static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { - int data, err = 0; long timeo; + int data; timeo = sock_rcvtimeo(sk, nonblock); - data = sk_msg_wait_data(sk, psock, flags, timeo, &err); + data = udp_msg_wait_data(sk, psock, timeo); if (data) { - if (!sk_psock_queue_empty(psock)) + if (psock_has_data(psock)) goto msg_bytes_ready; ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len); goto out; } - if (err) { - ret = err; - goto out; - } copied = -EAGAIN; } ret = copied; out: - release_sock(sk); sk_psock_put(sk, psock); return ret; } diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index bd8773b49e72..cd1cd68adeec 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -31,7 +31,6 @@ static const struct net_protocol udplite_protocol = { .handler = udplite_rcv, .err_handler = udplite_err, .no_policy = 1, - .netns_ok = 1, }; struct proto udplite_prot = { diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c index ea595c8549c7..2fe5860c21d6 100644 --- a/net/ipv4/xfrm4_protocol.c +++ b/net/ipv4/xfrm4_protocol.c @@ -181,21 +181,18 @@ static const struct net_protocol esp4_protocol = { .handler = xfrm4_esp_rcv, .err_handler = xfrm4_esp_err, .no_policy = 1, - .netns_ok = 1, }; static const struct net_protocol ah4_protocol = { .handler = xfrm4_ah_rcv, .err_handler = xfrm4_ah_err, .no_policy = 1, - .netns_ok = 1, }; static const struct net_protocol ipcomp4_protocol = { .handler = xfrm4_ipcomp_rcv, .err_handler = xfrm4_ipcomp_err, .no_policy = 1, - .netns_ok = 1, }; static const struct xfrm_input_afinfo xfrm4_input_afinfo = { diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index fb0648e7fb32..f4555a88f86b 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -42,7 +42,6 @@ static void ipip_destroy(struct xfrm_state *x) } static const struct xfrm_type ipip_type = { - .description = "IPIP", .owner = THIS_MODULE, .proto = IPPROTO_IPIP, .init_state = ipip_init_state, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 16cd226a283f..bbeebd858a22 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -6932,10 +6932,10 @@ static const struct ctl_table addrconf_sysctl[] = { .proc_handler = proc_dointvec, }, { - .procname = "addr_gen_mode", - .data = &ipv6_devconf.addr_gen_mode, - .maxlen = sizeof(int), - .mode = 0644, + .procname = "addr_gen_mode", + .data = &ipv6_devconf.addr_gen_mode, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = addrconf_sysctl_addr_gen_mode, }, { diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 20d492da725a..828e62514260 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -755,7 +755,6 @@ static int ah6_rcv_cb(struct sk_buff *skb, int err) } static const struct xfrm_type ah6_type = { - .description = "AH6", .owner = THIS_MODULE, .proto = IPPROTO_AH, .flags = XFRM_TYPE_REPLAY_PROT, @@ -763,7 +762,6 @@ static const struct xfrm_type ah6_type = { .destructor = ah6_destroy, .input = ah6_input, .output = ah6_output, - .hdr_offset = xfrm6_find_1stfragopt, }; static struct xfrm6_protocol ah6_protocol = { diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 393ae2b78e7d..ed2f061b8768 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -708,7 +708,7 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); u32 padto; - padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached)); + padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached)); if (skb->len < padto) esp.tfclen = padto - skb->len; } @@ -1243,7 +1243,6 @@ static int esp6_rcv_cb(struct sk_buff *skb, int err) } static const struct xfrm_type esp6_type = { - .description = "ESP6", .owner = THIS_MODULE, .proto = IPPROTO_ESP, .flags = XFRM_TYPE_REPLAY_PROT, @@ -1251,7 +1250,6 @@ static const struct xfrm_type esp6_type = { .destructor = esp6_destroy, .input = esp6_input, .output = esp6_output, - .hdr_offset = xfrm6_find_1stfragopt, }; static struct xfrm6_protocol esp6_protocol = { diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 40ed4fcf1cf4..a349d4798077 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -377,7 +377,6 @@ static const struct net_offload esp6_offload = { }; static const struct xfrm_type_offload esp6_type_offload = { - .description = "ESP6 OFFLOAD", .owner = THIS_MODULE, .proto = IPPROTO_ESP, .input_tail = esp6_input_tail, diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 56e479d158b7..26882e165c9e 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -135,18 +135,23 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, len -= 2; while (len > 0) { - int optlen = nh[off + 1] + 2; - int i; + int optlen, i; - switch (nh[off]) { - case IPV6_TLV_PAD1: - optlen = 1; + if (nh[off] == IPV6_TLV_PAD1) { padlen++; if (padlen > 7) goto bad; - break; + off++; + len--; + continue; + } + if (len < 2) + goto bad; + optlen = nh[off + 1] + 2; + if (optlen > len) + goto bad; - case IPV6_TLV_PADN: + if (nh[off] == IPV6_TLV_PADN) { /* RFC 2460 states that the purpose of PadN is * to align the containing header to multiples * of 8. 7 is therefore the highest valid value. @@ -163,12 +168,7 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, if (nh[off + i] != 0) goto bad; } - break; - - default: /* Other TLV code so scan list */ - if (optlen > len) - goto bad; - + } else { tlv_count++; if (tlv_count > max_count) goto bad; @@ -188,7 +188,6 @@ static bool ip6_parse_tlv(const struct tlvtype_proc *procs, return false; padlen = 0; - break; } off += optlen; len -= optlen; @@ -306,7 +305,7 @@ fail_and_free: #endif if (ip6_parse_tlv(tlvprocdestopt_lst, skb, - init_net.ipv6.sysctl.max_dst_opts_cnt)) { + net->ipv6.sysctl.max_dst_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) @@ -1037,7 +1036,7 @@ fail_and_free: opt->flags |= IP6SKB_HOPBYHOP; if (ip6_parse_tlv(tlvprochopopt_lst, skb, - init_net.ipv6.sysctl.max_hbh_opts_cnt)) { + net->ipv6.sysctl.max_hbh_opts_cnt)) { skb->transport_header += extlen; opt = IP6CB(skb); opt->nhoff = sizeof(struct ipv6hdr); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 8f9a83314de7..40f3e4f9f33a 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -467,7 +467,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { static int __net_init fib6_rules_net_init(struct net *net) { struct fib_rules_ops *ops; - int err = -ENOMEM; + int err; ops = fib_rules_register(&fib6_rules_ops_template, net); if (IS_ERR(ops)) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index e8398ffb5e35..a7c31ab67c5d 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -725,6 +725,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) struct ipcm6_cookie ipc6; u32 mark = IP6_REPLY_MARK(net, skb->mark); bool acast; + u8 type; if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) && net->ipv6.sysctl.icmpv6_echo_ignore_multicast) @@ -740,8 +741,13 @@ static void icmpv6_echo_reply(struct sk_buff *skb) !(net->ipv6.sysctl.anycast_src_echo_reply && acast)) saddr = NULL; + if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST) + type = ICMPV6_EXT_ECHO_REPLY; + else + type = ICMPV6_ECHO_REPLY; + memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr)); - tmp_hdr.icmp6_type = ICMPV6_ECHO_REPLY; + tmp_hdr.icmp6_type = type; memset(&fl6, 0, sizeof(fl6)); if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES) @@ -752,7 +758,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (saddr) fl6.saddr = *saddr; fl6.flowi6_oif = icmp6_iif(skb); - fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY; + fl6.fl6_icmp_type = type; fl6.flowi6_mark = mark; fl6.flowi6_uid = sock_net_uid(net, NULL); security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6)); @@ -783,13 +789,17 @@ static void icmpv6_echo_reply(struct sk_buff *skb) msg.skb = skb; msg.offset = 0; - msg.type = ICMPV6_ECHO_REPLY; + msg.type = type; ipcm6_init_sk(&ipc6, np); ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb)); ipc6.sockc.mark = mark; + if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST) + if (!icmp_build_probe(skb, (struct icmphdr *)&tmp_hdr)) + goto out_dst_release; + if (ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), &ipc6, &fl6, @@ -911,6 +921,11 @@ static int icmpv6_rcv(struct sk_buff *skb) if (!net->ipv6.sysctl.icmpv6_echo_ignore_all) icmpv6_echo_reply(skb); break; + case ICMPV6_EXT_ECHO_REQUEST: + if (!net->ipv6.sysctl.icmpv6_echo_ignore_all && + net->ipv4.sysctl_icmp_echo_enable_probe) + icmpv6_echo_reply(skb); + break; case ICMPV6_ECHO_REPLY: success = ping_rcv(skb); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 679699e953f1..2d650dc24349 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -32,6 +32,7 @@ #include #include +#include #include #include @@ -2355,6 +2356,10 @@ static int __net_init fib6_net_init(struct net *net) if (err) return err; + /* Default to 3-tuple */ + net->ipv6.sysctl.multipath_hash_fields = + FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; + spin_lock_init(&net->ipv6.fib6_gc_lock); rwlock_init(&net->ipv6.fib6_walker_lock); INIT_LIST_HEAD(&net->ipv6.fib6_walkers); @@ -2362,7 +2367,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL); if (!net->ipv6.rt6_stats) - goto out_timer; + goto out_notifier; /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); @@ -2407,7 +2412,7 @@ out_fib_table_hash: kfree(net->ipv6.fib_table_hash); out_rt6_stats: kfree(net->ipv6.rt6_stats); -out_timer: +out_notifier: fib6_notifier_exit(net); return -ENOMEM; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ff4f9ebcf7f6..984050f35c61 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1055,13 +1055,11 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, * ip6_route_output will fail given src=any saddr, though, so * that's why we try it again later. */ - if (ipv6_addr_any(&fl6->saddr) && (!*dst || !(*dst)->error)) { + if (ipv6_addr_any(&fl6->saddr)) { struct fib6_info *from; struct rt6_info *rt; - bool had_dst = *dst != NULL; - if (!had_dst) - *dst = ip6_route_output(net, sk, fl6); + *dst = ip6_route_output(net, sk, fl6); rt = (*dst)->error ? NULL : (struct rt6_info *)*dst; rcu_read_lock(); @@ -1078,7 +1076,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, * never existed and let the SA-enabled version take * over. */ - if (!had_dst && (*dst)->error) { + if ((*dst)->error) { dst_release(*dst); *dst = NULL; } @@ -1555,7 +1553,7 @@ emsgsize: unsigned int datalen; unsigned int fraglen; unsigned int fraggap; - unsigned int alloclen; + unsigned int alloclen, alloc_extra; unsigned int pagedlen; alloc_new_skb: /* There's no room in the current skb */ @@ -1582,17 +1580,28 @@ alloc_new_skb: fraglen = datalen + fragheaderlen; pagedlen = 0; + alloc_extra = hh_len; + alloc_extra += dst_exthdrlen; + alloc_extra += rt->dst.trailer_len; + + /* We just reserve space for fragment header. + * Note: this may be overallocation if the message + * (without MSG_MORE) fits into the MTU. + */ + alloc_extra += sizeof(struct frag_hdr); + if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; - else if (!paged) + else if (!paged && + (fraglen + alloc_extra < SKB_MAX_ALLOC || + !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; else { alloclen = min_t(int, fraglen, MAX_HEADER); pagedlen = fraglen - alloclen; } - - alloclen += dst_exthdrlen; + alloclen += alloc_extra; if (datalen != length + fraggap) { /* @@ -1602,30 +1611,21 @@ alloc_new_skb: datalen += rt->dst.trailer_len; } - alloclen += rt->dst.trailer_len; fraglen = datalen + fragheaderlen; - /* - * We just reserve space for fragment header. - * Note: this may be overallocation if the message - * (without MSG_MORE) fits into the MTU. - */ - alloclen += sizeof(struct frag_hdr); - copy = datalen - transhdrlen - fraggap - pagedlen; if (copy < 0) { err = -EINVAL; goto error; } if (transhdrlen) { - skb = sock_alloc_send_skb(sk, - alloclen + hh_len, + skb = sock_alloc_send_skb(sk, alloclen, (flags & MSG_DONTWAIT), &err); } else { skb = NULL; if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) - skb = alloc_skb(alloclen + hh_len, + skb = alloc_skb(alloclen, sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 288bafded998..322698d9fcf4 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -837,6 +837,7 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { skb->dev = tunnel->dev; + skb_reset_mac_header(skb); } skb_reset_network_header(skb); @@ -1239,8 +1240,6 @@ route_lookup: if (max_headroom > dev->needed_headroom) dev->needed_headroom = max_headroom; - skb_set_inner_ipproto(skb, proto); - err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) return err; @@ -1377,6 +1376,8 @@ ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; + skb_set_inner_ipproto(skb, protocol); + err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, protocol); if (err != 0) { diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index daef890460b7..15f984be3570 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -172,14 +172,12 @@ static int ipcomp6_rcv_cb(struct sk_buff *skb, int err) } static const struct xfrm_type ipcomp6_type = { - .description = "IPCOMP6", .owner = THIS_MODULE, .proto = IPPROTO_COMP, .init_state = ipcomp6_init_state, .destructor = ipcomp_destroy, .input = ipcomp_input, .output = ipcomp_output, - .hdr_offset = xfrm6_find_1stfragopt, }; static struct xfrm6_protocol ipcomp6_protocol = { diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index d36ef9d25e73..54ec163fbafa 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1729,22 +1729,25 @@ static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb, static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) { + u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, + 2, 0, 0, IPV6_TLV_PADN, 0 }; struct net_device *dev = idev->dev; - struct net *net = dev_net(dev); - struct sock *sk = net->ipv6.igmp_sk; - struct sk_buff *skb; - struct mld2_report *pmr; - struct in6_addr addr_buf; - const struct in6_addr *saddr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; - unsigned int size = mtu + hlen + tlen; + struct net *net = dev_net(dev); + const struct in6_addr *saddr; + struct in6_addr addr_buf; + struct mld2_report *pmr; + struct sk_buff *skb; + unsigned int size; + struct sock *sk; int err; - u8 ra[8] = { IPPROTO_ICMPV6, 0, - IPV6_TLV_ROUTERALERT, 2, 0, 0, - IPV6_TLV_PADN, 0 }; - /* we assume size > sizeof(ra) here */ + sk = net->ipv6.igmp_sk; + /* we assume size > sizeof(ra) here + * Also try to not allocate high-order pages for big MTU + */ + size = min_t(int, mtu, PAGE_SIZE / 2) + hlen + tlen; skb = sock_alloc_send_skb(sk, size, 1, &err); if (!skb) return NULL; diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 878fcec14949..aeb35d26e474 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -247,54 +247,6 @@ static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, return err; } -static int mip6_destopt_offset(struct xfrm_state *x, struct sk_buff *skb, - u8 **nexthdr) -{ - u16 offset = sizeof(struct ipv6hdr); - struct ipv6_opt_hdr *exthdr = - (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); - const unsigned char *nh = skb_network_header(skb); - unsigned int packet_len = skb_tail_pointer(skb) - - skb_network_header(skb); - int found_rhdr = 0; - - *nexthdr = &ipv6_hdr(skb)->nexthdr; - - while (offset + 1 <= packet_len) { - - switch (**nexthdr) { - case NEXTHDR_HOP: - break; - case NEXTHDR_ROUTING: - found_rhdr = 1; - break; - case NEXTHDR_DEST: - /* - * HAO MUST NOT appear more than once. - * XXX: It is better to try to find by the end of - * XXX: packet if HAO exists. - */ - if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) { - net_dbg_ratelimited("mip6: hao exists already, override\n"); - return offset; - } - - if (found_rhdr) - return offset; - - break; - default: - return offset; - } - - offset += ipv6_optlen(exthdr); - *nexthdr = &exthdr->nexthdr; - exthdr = (struct ipv6_opt_hdr *)(nh + offset); - } - - return offset; -} - static int mip6_destopt_init_state(struct xfrm_state *x) { if (x->id.spi) { @@ -324,7 +276,6 @@ static void mip6_destopt_destroy(struct xfrm_state *x) } static const struct xfrm_type mip6_destopt_type = { - .description = "MIP6DESTOPT", .owner = THIS_MODULE, .proto = IPPROTO_DSTOPTS, .flags = XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_LOCAL_COADDR, @@ -333,7 +284,6 @@ static const struct xfrm_type mip6_destopt_type = { .input = mip6_destopt_input, .output = mip6_destopt_output, .reject = mip6_destopt_reject, - .hdr_offset = mip6_destopt_offset, }; static int mip6_rthdr_input(struct xfrm_state *x, struct sk_buff *skb) @@ -383,53 +333,6 @@ static int mip6_rthdr_output(struct xfrm_state *x, struct sk_buff *skb) return 0; } -static int mip6_rthdr_offset(struct xfrm_state *x, struct sk_buff *skb, - u8 **nexthdr) -{ - u16 offset = sizeof(struct ipv6hdr); - struct ipv6_opt_hdr *exthdr = - (struct ipv6_opt_hdr *)(ipv6_hdr(skb) + 1); - const unsigned char *nh = skb_network_header(skb); - unsigned int packet_len = skb_tail_pointer(skb) - - skb_network_header(skb); - int found_rhdr = 0; - - *nexthdr = &ipv6_hdr(skb)->nexthdr; - - while (offset + 1 <= packet_len) { - - switch (**nexthdr) { - case NEXTHDR_HOP: - break; - case NEXTHDR_ROUTING: - if (offset + 3 <= packet_len) { - struct ipv6_rt_hdr *rt; - rt = (struct ipv6_rt_hdr *)(nh + offset); - if (rt->type != 0) - return offset; - } - found_rhdr = 1; - break; - case NEXTHDR_DEST: - if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) - return offset; - - if (found_rhdr) - return offset; - - break; - default: - return offset; - } - - offset += ipv6_optlen(exthdr); - *nexthdr = &exthdr->nexthdr; - exthdr = (struct ipv6_opt_hdr *)(nh + offset); - } - - return offset; -} - static int mip6_rthdr_init_state(struct xfrm_state *x) { if (x->id.spi) { @@ -456,7 +359,6 @@ static void mip6_rthdr_destroy(struct xfrm_state *x) } static const struct xfrm_type mip6_rthdr_type = { - .description = "MIP6RT", .owner = THIS_MODULE, .proto = IPPROTO_ROUTING, .flags = XFRM_TYPE_NON_FRAGMENT | XFRM_TYPE_REMOTE_COADDR, @@ -464,7 +366,6 @@ static const struct xfrm_type mip6_rthdr_type = { .destructor = mip6_rthdr_destroy, .input = mip6_rthdr_input, .output = mip6_rthdr_output, - .hdr_offset = mip6_rthdr_offset, }; static int __init mip6_init(void) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index e810a23baf99..de2cf3943b91 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -51,7 +51,7 @@ ip6_packet_match(const struct sk_buff *skb, const char *outdev, const struct ip6t_ip6 *ip6info, unsigned int *protoff, - int *fragoff, bool *hotdrop) + u16 *fragoff, bool *hotdrop) { unsigned long ret; const struct ipv6hdr *ipv6 = ipv6_hdr(skb); diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c index 7969d1f3018d..ed69c768797e 100644 --- a/net/ipv6/netfilter/nft_reject_ipv6.c +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -28,7 +28,7 @@ static void nft_reject_ipv6_eval(const struct nft_expr *expr, nft_hook(pkt)); break; case NFT_REJECT_TCP_RST: - nf_send_reset6(nft_net(pkt), pkt->xt.state->sk, pkt->skb, + nf_send_reset6(nft_net(pkt), nft_sk(pkt), pkt->skb, nft_hook(pkt)); break; default: diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index af36acc1a644..2880dc7d9a49 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -15,29 +15,11 @@ static u32 __ipv6_select_ident(struct net *net, const struct in6_addr *dst, const struct in6_addr *src) { - const struct { - struct in6_addr dst; - struct in6_addr src; - } __aligned(SIPHASH_ALIGNMENT) combined = { - .dst = *dst, - .src = *src, - }; - u32 hash, id; + u32 id; - /* Note the following code is not safe, but this is okay. */ - if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) - get_random_bytes(&net->ipv4.ip_id_key, - sizeof(net->ipv4.ip_id_key)); - - hash = siphash(&combined, sizeof(combined), &net->ipv4.ip_id_key); - - /* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve, - * set the hight order instead thus minimizing possible future - * collisions. - */ - id = ip_idents_reserve(hash, 1); - if (unlikely(!id)) - id = 1 << 31; + do { + id = prandom_u32(); + } while (!id); return id; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index bf3646b57c68..60f1e4f5be5a 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -354,7 +354,7 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb, if (np->recverr || harderr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 13bbea1aff4b..1457cc22323f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2326,12 +2326,131 @@ out: } } +static u32 rt6_multipath_custom_hash_outer(const struct net *net, + const struct sk_buff *skb, + bool *p_has_inner) +{ + u32 hash_fields = ip6_multipath_hash_fields(net); + struct flow_keys keys, hash_keys; + + if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) + return 0; + + memset(&hash_keys, 0, sizeof(hash_keys)); + skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); + + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) + hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) + hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) + hash_keys.basic.ip_proto = keys.basic.ip_proto; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) + hash_keys.tags.flow_label = keys.tags.flow_label; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) + hash_keys.ports.src = keys.ports.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) + hash_keys.ports.dst = keys.ports.dst; + + *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); + return flow_hash_from_keys(&hash_keys); +} + +static u32 rt6_multipath_custom_hash_inner(const struct net *net, + const struct sk_buff *skb, + bool has_inner) +{ + u32 hash_fields = ip6_multipath_hash_fields(net); + struct flow_keys keys, hash_keys; + + /* We assume the packet carries an encapsulation, but if none was + * encountered during dissection of the outer flow, then there is no + * point in calling the flow dissector again. + */ + if (!has_inner) + return 0; + + if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) + return 0; + + memset(&hash_keys, 0, sizeof(hash_keys)); + skb_flow_dissect_flow_keys(skb, &keys, 0); + + if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) + return 0; + + if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) + hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) + hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; + } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) + hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) + hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) + hash_keys.tags.flow_label = keys.tags.flow_label; + } + + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) + hash_keys.basic.ip_proto = keys.basic.ip_proto; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) + hash_keys.ports.src = keys.ports.src; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) + hash_keys.ports.dst = keys.ports.dst; + + return flow_hash_from_keys(&hash_keys); +} + +static u32 rt6_multipath_custom_hash_skb(const struct net *net, + const struct sk_buff *skb) +{ + u32 mhash, mhash_inner; + bool has_inner = true; + + mhash = rt6_multipath_custom_hash_outer(net, skb, &has_inner); + mhash_inner = rt6_multipath_custom_hash_inner(net, skb, has_inner); + + return jhash_2words(mhash, mhash_inner, 0); +} + +static u32 rt6_multipath_custom_hash_fl6(const struct net *net, + const struct flowi6 *fl6) +{ + u32 hash_fields = ip6_multipath_hash_fields(net); + struct flow_keys hash_keys; + + if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) + return 0; + + memset(&hash_keys, 0, sizeof(hash_keys)); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) + hash_keys.addrs.v6addrs.src = fl6->saddr; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) + hash_keys.addrs.v6addrs.dst = fl6->daddr; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) + hash_keys.basic.ip_proto = fl6->flowi6_proto; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) + hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) + hash_keys.ports.src = fl6->fl6_sport; + if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) + hash_keys.ports.dst = fl6->fl6_dport; + + return flow_hash_from_keys(&hash_keys); +} + /* if skb is set it will be used and fl6 can be NULL */ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, struct flow_keys *flkeys) { struct flow_keys hash_keys; - u32 mhash; + u32 mhash = 0; switch (ip6_multipath_hash_policy(net)) { case 0: @@ -2345,6 +2464,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } + mhash = flow_hash_from_keys(&hash_keys); break; case 1: if (skb) { @@ -2376,6 +2496,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, hash_keys.ports.dst = fl6->fl6_dport; hash_keys.basic.ip_proto = fl6->flowi6_proto; } + mhash = flow_hash_from_keys(&hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); @@ -2412,9 +2533,15 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } + mhash = flow_hash_from_keys(&hash_keys); + break; + case 3: + if (skb) + mhash = rt6_multipath_custom_hash_skb(net, skb); + else + mhash = rt6_multipath_custom_hash_fl6(net, fl6); break; } - mhash = flow_hash_from_keys(&hash_keys); return mhash >> 1; } diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 4ff38cb08f4b..60bf3b877957 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -87,10 +87,10 @@ struct seg6_end_dt_info { int vrf_ifindex; int vrf_table; - /* tunneled packet proto and family (IPv4 or IPv6) */ - __be16 proto; + /* tunneled packet family (IPv4 or IPv6). + * Protocol and header length are inferred from family. + */ u16 family; - int hdrlen; }; struct pcpu_seg6_local_counters { @@ -521,19 +521,6 @@ static int __seg6_end_dt_vrf_build(struct seg6_local_lwt *slwt, const void *cfg, info->net = net; info->vrf_ifindex = vrf_ifindex; - switch (family) { - case AF_INET: - info->proto = htons(ETH_P_IP); - info->hdrlen = sizeof(struct iphdr); - break; - case AF_INET6: - info->proto = htons(ETH_P_IPV6); - info->hdrlen = sizeof(struct ipv6hdr); - break; - default: - return -EINVAL; - } - info->family = family; info->mode = DT_VRF_MODE; @@ -622,22 +609,44 @@ error: } static struct sk_buff *end_dt_vrf_core(struct sk_buff *skb, - struct seg6_local_lwt *slwt) + struct seg6_local_lwt *slwt, u16 family) { struct seg6_end_dt_info *info = &slwt->dt_info; struct net_device *vrf; + __be16 protocol; + int hdrlen; vrf = end_dt_get_vrf_rcu(skb, info); if (unlikely(!vrf)) goto drop; - skb->protocol = info->proto; + switch (family) { + case AF_INET: + protocol = htons(ETH_P_IP); + hdrlen = sizeof(struct iphdr); + break; + case AF_INET6: + protocol = htons(ETH_P_IPV6); + hdrlen = sizeof(struct ipv6hdr); + break; + case AF_UNSPEC: + fallthrough; + default: + goto drop; + } + + if (unlikely(info->family != AF_UNSPEC && info->family != family)) { + pr_warn_once("seg6local: SRv6 End.DT* family mismatch"); + goto drop; + } + + skb->protocol = protocol; skb_dst_drop(skb); - skb_set_transport_header(skb, info->hdrlen); + skb_set_transport_header(skb, hdrlen); - return end_dt_vrf_rcv(skb, info->family, vrf); + return end_dt_vrf_rcv(skb, family, vrf); drop: kfree_skb(skb); @@ -656,7 +665,7 @@ static int input_action_end_dt4(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto drop; - skb = end_dt_vrf_core(skb, slwt); + skb = end_dt_vrf_core(skb, slwt, AF_INET); if (!skb) /* packet has been processed and consumed by the VRF */ return 0; @@ -739,7 +748,7 @@ static int input_action_end_dt6(struct sk_buff *skb, goto legacy_mode; /* DT6_VRF_MODE */ - skb = end_dt_vrf_core(skb, slwt); + skb = end_dt_vrf_core(skb, slwt, AF_INET6); if (!skb) /* packet has been processed and consumed by the VRF */ return 0; @@ -767,6 +776,36 @@ drop: return -EINVAL; } +#ifdef CONFIG_NET_L3_MASTER_DEV +static int seg6_end_dt46_build(struct seg6_local_lwt *slwt, const void *cfg, + struct netlink_ext_ack *extack) +{ + return __seg6_end_dt_vrf_build(slwt, cfg, AF_UNSPEC, extack); +} + +static int input_action_end_dt46(struct sk_buff *skb, + struct seg6_local_lwt *slwt) +{ + unsigned int off = 0; + int nexthdr; + + nexthdr = ipv6_find_hdr(skb, &off, -1, NULL, NULL); + if (unlikely(nexthdr < 0)) + goto drop; + + switch (nexthdr) { + case IPPROTO_IPIP: + return input_action_end_dt4(skb, slwt); + case IPPROTO_IPV6: + return input_action_end_dt6(skb, slwt); + } + +drop: + kfree_skb(skb); + return -EINVAL; +} +#endif + /* push an SRH on top of the current one */ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt) { @@ -968,6 +1007,17 @@ static struct seg6_action_desc seg6_action_table[] = { #endif .input = input_action_end_dt6, }, + { + .action = SEG6_LOCAL_ACTION_END_DT46, + .attrs = SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE), + .optattrs = SEG6_F_LOCAL_COUNTERS, +#ifdef CONFIG_NET_L3_MASTER_DEV + .input = input_action_end_dt46, + .slwt_ops = { + .build_state = seg6_end_dt46_build, + }, +#endif + }, { .action = SEG6_LOCAL_ACTION_END_B6, .attrs = SEG6_F_ATTR(SEG6_LOCAL_SRH), diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index f7c8110ece5f..df5bea818410 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -710,6 +710,8 @@ static int ipip6_rcv(struct sk_buff *skb) * old iph is no longer valid */ iph = (const struct iphdr *)skb_mac_header(skb); + skb_reset_mac_header(skb); + err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) @@ -780,6 +782,8 @@ static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto) tpi = &ipip_tpi; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; + skb_reset_mac_header(skb); + return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error); } @@ -973,7 +977,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if (df) { mtu = dst_mtu(&rt->dst) - t_hlen; - if (mtu < 68) { + if (mtu < IPV4_MIN_MTU) { dev->stats.collisions++; ip_rt_put(rt); goto tx_error; diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 27102c3d6e1d..d7cf26f730d7 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -17,13 +17,17 @@ #include #include #include +#include #ifdef CONFIG_NETLABEL #include #endif static int two = 2; +static int three = 3; static int flowlabel_reflect_max = 0x7; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; +static u32 rt6_multipath_hash_fields_all_mask = + FIB_MULTIPATH_HASH_FIELD_ALL_MASK; static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -40,6 +44,22 @@ static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, return ret; } +static int +proc_rt6_multipath_hash_fields(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + struct net *net; + int ret; + + net = container_of(table->data, struct net, + ipv6.sysctl.multipath_hash_fields); + ret = proc_douintvec_minmax(table, write, buffer, lenp, ppos); + if (write && ret == 0) + call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); + + return ret; +} + static struct ctl_table ipv6_table_template[] = { { .procname = "bindv6only", @@ -149,7 +169,16 @@ static struct ctl_table ipv6_table_template[] = { .mode = 0644, .proc_handler = proc_rt6_multipath_hash_policy, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = &three, + }, + { + .procname = "fib_multipath_hash_fields", + .data = &init_net.ipv6.sysctl.multipath_hash_fields, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_rt6_multipath_hash_fields, + .extra1 = SYSCTL_ONE, + .extra2 = &rt6_multipath_hash_fields_all_mask, }, { .procname = "seg6_flowlabel", diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5f47c0b6e3de..578ab6305c3f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -467,7 +467,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!sock_owned_by_user(sk)) { sk->sk_err = err; - sk->sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ + sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ tcp_done(sk); } else @@ -486,7 +486,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!sock_owned_by_user(sk) && np->recverr) { sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } else sk->sk_err_soft = err; @@ -1538,6 +1538,7 @@ discard: kfree_skb(skb); return 0; csum_err: + trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; @@ -1663,10 +1664,18 @@ process: goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { - inet_csk_reqsk_queue_drop_and_put(sk, req); - goto lookup; + nsk = reuseport_migrate_sock(sk, req_to_sk(req), skb); + if (!nsk) { + inet_csk_reqsk_queue_drop_and_put(sk, req); + goto lookup; + } + sk = nsk; + /* reuseport_migrate_sock() has already held one sk_refcnt + * before returning. + */ + } else { + sock_hold(sk); } - sock_hold(sk); refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { @@ -1754,6 +1763,7 @@ no_tcp_socket: if (tcp_checksum_complete(skb)) { csum_error: + trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3fcd86f4dfdc..368972dbd919 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -610,7 +610,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); out: return 0; } diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8b84d534b19d..57fa27c1cdf9 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -16,13 +16,6 @@ #include #include -int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, - u8 **prevhdr) -{ - return ip6_find_1stfragopt(skb, prevhdr); -} -EXPORT_SYMBOL(xfrm6_find_1stfragopt); - void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu) { struct flowi6 fl6; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f696d46e6910..2b31112c0856 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -291,7 +291,6 @@ static void xfrm6_tunnel_destroy(struct xfrm_state *x) } static const struct xfrm_type xfrm6_tunnel_type = { - .description = "IP6IP6", .owner = THIS_MODULE, .proto = IPPROTO_IPV6, .init_state = xfrm6_tunnel_init_state, diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 0fdb389c3390..44453b35c7b7 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -44,6 +44,7 @@ static struct proto iucv_proto = { }; static struct iucv_interface *pr_iucv; +static struct iucv_handler af_iucv_handler; /* special AF_IUCV IPRM messages */ static const u8 iprm_shutdown[8] = @@ -91,28 +92,11 @@ static void iucv_sock_close(struct sock *sk); static void afiucv_hs_callback_txnotify(struct sock *sk, enum iucv_tx_notify); -/* Call Back functions */ -static void iucv_callback_rx(struct iucv_path *, struct iucv_message *); -static void iucv_callback_txdone(struct iucv_path *, struct iucv_message *); -static void iucv_callback_connack(struct iucv_path *, u8 *); -static int iucv_callback_connreq(struct iucv_path *, u8 *, u8 *); -static void iucv_callback_connrej(struct iucv_path *, u8 *); -static void iucv_callback_shutdown(struct iucv_path *, u8 *); - static struct iucv_sock_list iucv_sk_list = { .lock = __RW_LOCK_UNLOCKED(iucv_sk_list.lock), .autobind_name = ATOMIC_INIT(0) }; -static struct iucv_handler af_iucv_handler = { - .path_pending = iucv_callback_connreq, - .path_complete = iucv_callback_connack, - .path_severed = iucv_callback_connrej, - .message_pending = iucv_callback_rx, - .message_complete = iucv_callback_txdone, - .path_quiesced = iucv_callback_shutdown, -}; - static inline void high_nmcpy(unsigned char *dst, char *src) { memcpy(dst, src, 8); @@ -1817,6 +1801,15 @@ static void iucv_callback_shutdown(struct iucv_path *path, u8 ipuser[16]) bh_unlock_sock(sk); } +static struct iucv_handler af_iucv_handler = { + .path_pending = iucv_callback_connreq, + .path_complete = iucv_callback_connack, + .path_severed = iucv_callback_connrej, + .message_pending = iucv_callback_rx, + .message_complete = iucv_callback_txdone, + .path_quiesced = iucv_callback_shutdown, +}; + /***************** HiperSockets transport callbacks ********************/ static void afiucv_swap_src_dest(struct sk_buff *skb) { diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 6201965bd822..11a715d76a4f 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -47,7 +47,7 @@ static inline struct kcm_tx_msg *kcm_tx_msg(struct sk_buff *skb) static void report_csk_error(struct sock *csk, int err) { csk->sk_err = EPIPE; - csk->sk_error_report(csk); + sk_error_report(csk); } static void kcm_abort_tx_psock(struct kcm_psock *psock, int err, diff --git a/net/key/af_key.c b/net/key/af_key.c index ef9b4ac03e7b..de24a7d474df 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -141,7 +141,6 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; struct pfkey_sock *pfk; - int err; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -150,10 +149,9 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, if (protocol != PF_KEY_V2) return -EPROTONOSUPPORT; - err = -ENOMEM; sk = sk_alloc(net, PF_KEY, GFP_KERNEL, &key_proto, kern); if (sk == NULL) - goto out; + return -ENOMEM; pfk = pfkey_sk(sk); mutex_init(&pfk->dump_lock); @@ -169,8 +167,6 @@ static int pfkey_create(struct net *net, struct socket *sock, int protocol, pfkey_insert(sk); return 0; -out: - return err; } static int pfkey_release(struct socket *sock) diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 97ae1255fcb6..b3edafa5fba4 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -488,7 +488,7 @@ static int l2tp_ip_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } } - /* We dont need to clone dst here, it is guaranteed to not disappear. + /* We don't need to clone dst here, it is guaranteed to not disappear. * __dev_xmit_skb() might force a refcount if needed. */ skb_dst_set_noref(skb, &rt->dst); @@ -635,7 +635,6 @@ static struct inet_protosw l2tp_ip_protosw = { static struct net_protocol l2tp_ip_protocol __read_mostly = { .handler = l2tp_ip_recv, - .netns_ok = 1, }; static int __init l2tp_ip_init(void) diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index aea85f91f059..bf35710127dd 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -226,7 +226,7 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int /* If the first two bytes are 0xFF03, consider that it is the PPP's * Address and Control fields and skip them. The L2TP module has always * worked this way, although, in theory, the use of these fields should - * be negociated and handled at the PPP layer. These fields are + * be negotiated and handled at the PPP layer. These fields are * constant: 0xFF is the All-Stations Address and 0x03 the Unnumbered * Information command with Poll/Final bit set to zero (RFC 1662). */ diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index 1078e14f1acf..0971ca48ba15 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -80,11 +80,9 @@ static void __lapb_insert_cb(struct lapb_cb *lapb) static struct lapb_cb *__lapb_devtostruct(struct net_device *dev) { - struct list_head *entry; struct lapb_cb *lapb, *use = NULL; - list_for_each(entry, &lapb_list) { - lapb = list_entry(entry, struct lapb_cb, node); + list_for_each_entry(lapb, &lapb_list, node) { if (lapb->dev == dev) { use = lapb; break; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 7a99892e5aba..84cc7733ea66 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1442,6 +1442,38 @@ static void sta_apply_mesh_params(struct ieee80211_local *local, #endif } +static void sta_apply_airtime_params(struct ieee80211_local *local, + struct sta_info *sta, + struct station_parameters *params) +{ + u8 ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + struct airtime_sched_info *air_sched = &local->airtime[ac]; + struct airtime_info *air_info = &sta->airtime[ac]; + struct txq_info *txqi; + u8 tid; + + spin_lock_bh(&air_sched->lock); + for (tid = 0; tid < IEEE80211_NUM_TIDS + 1; tid++) { + if (air_info->weight == params->airtime_weight || + !sta->sta.txq[tid] || + ac != ieee80211_ac_from_tid(tid)) + continue; + + airtime_weight_set(air_info, params->airtime_weight); + + txqi = to_txq_info(sta->sta.txq[tid]); + if (RB_EMPTY_NODE(&txqi->schedule_order)) + continue; + + ieee80211_update_airtime_weight(local, air_sched, + 0, true); + } + spin_unlock_bh(&air_sched->lock); + } +} + static int sta_apply_parameters(struct ieee80211_local *local, struct sta_info *sta, struct station_parameters *params) @@ -1629,7 +1661,8 @@ static int sta_apply_parameters(struct ieee80211_local *local, sta_apply_mesh_params(local, sta, params); if (params->airtime_weight) - sta->airtime_weight = params->airtime_weight; + sta_apply_airtime_params(local, sta, params); + /* set the STA state after all sta info from usermode has been set */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) || @@ -1693,15 +1726,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, test_sta_flag(sta, WLAN_STA_ASSOC)) rate_control_rate_init(sta); - err = sta_info_insert_rcu(sta); - if (err) { - rcu_read_unlock(); - return err; - } - - rcu_read_unlock(); - - return 0; + return sta_info_insert(sta); } static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev, diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 907bb1f748a1..76fc36a68750 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * mac80211 - channel management + * Copyright 2020 - 2021 Intel Corporation */ #include @@ -308,8 +309,8 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, * the max of min required widths of all the interfaces bound to this * channel context. */ -void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) +static u32 _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) { enum nl80211_chan_width max_bw; struct cfg80211_chan_def min_def; @@ -326,7 +327,7 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, ctx->conf.def.width == NL80211_CHAN_WIDTH_16 || ctx->conf.radar_enabled) { ctx->conf.min_def = ctx->conf.def; - return; + return 0; } max_bw = ieee80211_get_chanctx_max_required_bw(local, &ctx->conf); @@ -337,17 +338,21 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, ieee80211_chandef_downgrade(&min_def); if (cfg80211_chandef_identical(&ctx->conf.min_def, &min_def)) - return; + return 0; ctx->conf.min_def = min_def; if (!ctx->driver_present) - return; + return 0; - drv_change_chanctx(local, ctx, IEEE80211_CHANCTX_CHANGE_MIN_WIDTH); + return IEEE80211_CHANCTX_CHANGE_MIN_WIDTH; } +/* calling this function is assuming that station vif is updated to + * lates changes by calling ieee80211_vif_update_chandef + */ static void ieee80211_chan_bw_change(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx) + struct ieee80211_chanctx *ctx, + bool narrowed) { struct sta_info *sta; struct ieee80211_supported_band *sband = @@ -366,9 +371,16 @@ static void ieee80211_chan_bw_change(struct ieee80211_local *local, continue; new_sta_bw = ieee80211_sta_cur_vht_bw(sta); + + /* nothing change */ if (new_sta_bw == sta->sta.bandwidth) continue; + /* vif changed to narrow BW and narrow BW for station wasn't + * requested or vise versa */ + if ((new_sta_bw < sta->sta.bandwidth) == !narrowed) + continue; + sta->sta.bandwidth = new_sta_bw; rate_control_rate_update(local, sband, sta, IEEE80211_RC_BW_CHANGED); @@ -376,21 +388,34 @@ static void ieee80211_chan_bw_change(struct ieee80211_local *local, rcu_read_unlock(); } +/* + * recalc the min required chan width of the channel context, which is + * the max of min required widths of all the interfaces bound to this + * channel context. + */ +void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) +{ + u32 changed = _ieee80211_recalc_chanctx_min_def(local, ctx); + + if (!changed) + return; + + /* check is BW narrowed */ + ieee80211_chan_bw_change(local, ctx, true); + + drv_change_chanctx(local, ctx, changed); + + /* check is BW wider */ + ieee80211_chan_bw_change(local, ctx, false); +} + static void ieee80211_change_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, + struct ieee80211_chanctx *old_ctx, const struct cfg80211_chan_def *chandef) { - enum nl80211_chan_width width; - - if (cfg80211_chandef_identical(&ctx->conf.def, chandef)) { - ieee80211_recalc_chanctx_min_def(local, ctx); - return; - } - - WARN_ON(!cfg80211_chandef_compatible(&ctx->conf.def, chandef)); - - width = ctx->conf.def.width; - ctx->conf.def = *chandef; + u32 changed; /* expected to handle only 20/40/80/160 channel widths */ switch (chandef->width) { @@ -405,19 +430,33 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local, WARN_ON(1); } - if (chandef->width < width) - ieee80211_chan_bw_change(local, ctx); + /* Check maybe BW narrowed - we do this _before_ calling recalc_chanctx_min_def + * due to maybe not returning from it, e.g in case new context was added + * first time with all parameters up to date. + */ + ieee80211_chan_bw_change(local, old_ctx, true); - drv_change_chanctx(local, ctx, IEEE80211_CHANCTX_CHANGE_WIDTH); - ieee80211_recalc_chanctx_min_def(local, ctx); + if (cfg80211_chandef_identical(&ctx->conf.def, chandef)) { + ieee80211_recalc_chanctx_min_def(local, ctx); + return; + } + + WARN_ON(!cfg80211_chandef_compatible(&ctx->conf.def, chandef)); + + ctx->conf.def = *chandef; + + /* check if min chanctx also changed */ + changed = IEEE80211_CHANCTX_CHANGE_WIDTH | + _ieee80211_recalc_chanctx_min_def(local, ctx); + drv_change_chanctx(local, ctx, changed); if (!local->use_chanctx) { local->_oper_chandef = *chandef; ieee80211_hw_config(local, 0); } - if (chandef->width > width) - ieee80211_chan_bw_change(local, ctx); + /* check is BW wider */ + ieee80211_chan_bw_change(local, old_ctx, false); } static struct ieee80211_chanctx * @@ -450,7 +489,7 @@ ieee80211_find_chanctx(struct ieee80211_local *local, if (!compat) continue; - ieee80211_change_chanctx(local, ctx, compat); + ieee80211_change_chanctx(local, ctx, ctx, compat); return ctx; } @@ -679,7 +718,7 @@ void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, if (!compat) return; - ieee80211_change_chanctx(local, ctx, compat); + ieee80211_change_chanctx(local, ctx, ctx, compat); } static void ieee80211_recalc_radar_chanctx(struct ieee80211_local *local, @@ -1107,13 +1146,12 @@ ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata) if (WARN_ON(!chandef)) return -EINVAL; - if (old_ctx->conf.def.width > new_ctx->conf.def.width) - ieee80211_chan_bw_change(local, new_ctx); + if (sdata->vif.bss_conf.chandef.width != sdata->reserved_chandef.width) + changed = BSS_CHANGED_BANDWIDTH; - ieee80211_change_chanctx(local, new_ctx, chandef); + ieee80211_vif_update_chandef(sdata, &sdata->reserved_chandef); - if (old_ctx->conf.def.width < new_ctx->conf.def.width) - ieee80211_chan_bw_change(local, new_ctx); + ieee80211_change_chanctx(local, new_ctx, old_ctx, chandef); vif_chsw[0].vif = &sdata->vif; vif_chsw[0].old_ctx = &old_ctx->conf; @@ -1142,14 +1180,9 @@ ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata) if (ieee80211_chanctx_refcount(local, old_ctx) == 0) ieee80211_free_chanctx(local, old_ctx); - if (sdata->vif.bss_conf.chandef.width != sdata->reserved_chandef.width) - changed = BSS_CHANGED_BANDWIDTH; - - ieee80211_vif_update_chandef(sdata, &sdata->reserved_chandef); - + ieee80211_recalc_chanctx_min_def(local, new_ctx); ieee80211_recalc_smps_chanctx(local, new_ctx); ieee80211_recalc_radar_chanctx(local, new_ctx); - ieee80211_recalc_chanctx_min_def(local, new_ctx); if (changed) ieee80211_bss_info_change_notify(sdata, changed); @@ -1188,7 +1221,7 @@ ieee80211_vif_use_reserved_assign(struct ieee80211_sub_if_data *sdata) if (WARN_ON(!chandef)) return -EINVAL; - ieee80211_change_chanctx(local, new_ctx, chandef); + ieee80211_change_chanctx(local, new_ctx, new_ctx, chandef); list_del(&sdata->reserved_chanctx_list); sdata->reserved_chanctx = NULL; @@ -1505,7 +1538,6 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) ieee80211_recalc_smps_chanctx(local, ctx); ieee80211_recalc_radar_chanctx(local, ctx); ieee80211_recalc_chanctx_min_def(local, ctx); - ieee80211_chan_bw_change(local, ctx); list_for_each_entry_safe(sdata, sdata_tmp, &ctx->reserved_vifs, reserved_chanctx_list) { diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index fc34ae2b604c..8dbfe325ee66 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -216,14 +216,14 @@ static ssize_t aql_txq_limit_read(struct file *file, "VI %u %u\n" "BE %u %u\n" "BK %u %u\n", - local->aql_txq_limit_low[IEEE80211_AC_VO], - local->aql_txq_limit_high[IEEE80211_AC_VO], - local->aql_txq_limit_low[IEEE80211_AC_VI], - local->aql_txq_limit_high[IEEE80211_AC_VI], - local->aql_txq_limit_low[IEEE80211_AC_BE], - local->aql_txq_limit_high[IEEE80211_AC_BE], - local->aql_txq_limit_low[IEEE80211_AC_BK], - local->aql_txq_limit_high[IEEE80211_AC_BK]); + local->airtime[IEEE80211_AC_VO].aql_txq_limit_low, + local->airtime[IEEE80211_AC_VO].aql_txq_limit_high, + local->airtime[IEEE80211_AC_VI].aql_txq_limit_low, + local->airtime[IEEE80211_AC_VI].aql_txq_limit_high, + local->airtime[IEEE80211_AC_BE].aql_txq_limit_low, + local->airtime[IEEE80211_AC_BE].aql_txq_limit_high, + local->airtime[IEEE80211_AC_BK].aql_txq_limit_low, + local->airtime[IEEE80211_AC_BK].aql_txq_limit_high); return simple_read_from_buffer(user_buf, count, ppos, buf, len); } @@ -255,11 +255,11 @@ static ssize_t aql_txq_limit_write(struct file *file, if (ac >= IEEE80211_NUM_ACS) return -EINVAL; - q_limit_low_old = local->aql_txq_limit_low[ac]; - q_limit_high_old = local->aql_txq_limit_high[ac]; + q_limit_low_old = local->airtime[ac].aql_txq_limit_low; + q_limit_high_old = local->airtime[ac].aql_txq_limit_high; - local->aql_txq_limit_low[ac] = q_limit_low; - local->aql_txq_limit_high[ac] = q_limit_high; + local->airtime[ac].aql_txq_limit_low = q_limit_low; + local->airtime[ac].aql_txq_limit_high = q_limit_high; mutex_lock(&local->sta_mtx); list_for_each_entry(sta, &local->sta_list, list) { @@ -382,6 +382,46 @@ static const struct file_operations force_tx_status_ops = { .llseek = default_llseek, }; +static ssize_t airtime_read(struct file *file, + char __user *user_buf, + size_t count, + loff_t *ppos) +{ + struct ieee80211_local *local = file->private_data; + char buf[200]; + u64 v_t[IEEE80211_NUM_ACS]; + u64 wt[IEEE80211_NUM_ACS]; + int len = 0, ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->airtime[ac].lock); + v_t[ac] = local->airtime[ac].v_t; + wt[ac] = local->airtime[ac].weight_sum; + spin_unlock_bh(&local->airtime[ac].lock); + } + len = scnprintf(buf, sizeof(buf), + "\tVO VI BE BK\n" + "Virt-t\t%-10llu %-10llu %-10llu %-10llu\n" + "Weight\t%-10llu %-10llu %-10llu %-10llu\n", + v_t[0], + v_t[1], + v_t[2], + v_t[3], + wt[0], + wt[1], + wt[2], + wt[3]); + + return simple_read_from_buffer(user_buf, count, ppos, + buf, len); +} + +static const struct file_operations airtime_ops = { + .read = airtime_read, + .open = simple_open, + .llseek = default_llseek, +}; + #ifdef CONFIG_PM static ssize_t reset_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) @@ -632,7 +672,11 @@ void debugfs_hw_add(struct ieee80211_local *local) if (local->ops->wake_tx_queue) DEBUGFS_ADD_MODE(aqm, 0600); - DEBUGFS_ADD_MODE(airtime_flags, 0600); + if (wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) { + DEBUGFS_ADD_MODE(airtime, 0600); + DEBUGFS_ADD_MODE(airtime_flags, 0600); + } DEBUGFS_ADD(aql_txq_limit); debugfs_create_u32("aql_threshold", 0600, diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 0ad3860852ff..db724fc10a5f 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -57,7 +57,6 @@ static ssize_t ieee80211_if_write( return -EFAULT; buf[count] = '\0'; - ret = -ENODEV; rtnl_lock(); ret = (*write)(sdata, buf, count); rtnl_unlock(); @@ -513,6 +512,34 @@ static ssize_t ieee80211_if_fmt_aqm( } IEEE80211_IF_FILE_R(aqm); +static ssize_t ieee80211_if_fmt_airtime( + const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_txq *txq = sdata->vif.txq; + struct airtime_info *air_info; + int len; + + if (!txq) + return 0; + + spin_lock_bh(&local->airtime[txq->ac].lock); + air_info = to_airtime_info(txq); + len = scnprintf(buf, + buflen, + "RX: %llu us\nTX: %llu us\nWeight: %u\n" + "Virt-T: %lld us\n", + air_info->rx_airtime, + air_info->tx_airtime, + air_info->weight, + air_info->v_t); + spin_unlock_bh(&local->airtime[txq->ac].lock); + + return len; +} + +IEEE80211_IF_FILE_R(airtime); + IEEE80211_IF_FILE(multicast_to_unicast, u.ap.multicast_to_unicast, HEX); /* IBSS attributes */ @@ -658,8 +685,10 @@ static void add_common_files(struct ieee80211_sub_if_data *sdata) if (sdata->local->ops->wake_tx_queue && sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && - sdata->vif.type != NL80211_IFTYPE_NAN) + sdata->vif.type != NL80211_IFTYPE_NAN) { DEBUGFS_ADD(aqm); + DEBUGFS_ADD(airtime); + } } static void add_sta_files(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 936c9dfa86c8..8be28cfd6f64 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -202,7 +202,7 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, size_t bufsz = 400; char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; u64 rx_airtime = 0, tx_airtime = 0; - s64 deficit[IEEE80211_NUM_ACS]; + u64 v_t[IEEE80211_NUM_ACS]; ssize_t rv; int ac; @@ -210,18 +210,18 @@ static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, return -ENOMEM; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - spin_lock_bh(&local->active_txq_lock[ac]); + spin_lock_bh(&local->airtime[ac].lock); rx_airtime += sta->airtime[ac].rx_airtime; tx_airtime += sta->airtime[ac].tx_airtime; - deficit[ac] = sta->airtime[ac].deficit; - spin_unlock_bh(&local->active_txq_lock[ac]); + v_t[ac] = sta->airtime[ac].v_t; + spin_unlock_bh(&local->airtime[ac].lock); } p += scnprintf(p, bufsz + buf - p, "RX: %llu us\nTX: %llu us\nWeight: %u\n" - "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n", - rx_airtime, tx_airtime, sta->airtime_weight, - deficit[0], deficit[1], deficit[2], deficit[3]); + "Virt-T: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n", + rx_airtime, tx_airtime, sta->airtime[0].weight, + v_t[0], v_t[1], v_t[2], v_t[3]); rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); kfree(buf); @@ -236,11 +236,11 @@ static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, int ac; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - spin_lock_bh(&local->active_txq_lock[ac]); + spin_lock_bh(&local->airtime[ac].lock); sta->airtime[ac].rx_airtime = 0; sta->airtime[ac].tx_airtime = 0; - sta->airtime[ac].deficit = sta->airtime_weight; - spin_unlock_bh(&local->active_txq_lock[ac]); + sta->airtime[ac].v_t = 0; + spin_unlock_bh(&local->airtime[ac].lock); } return count; @@ -263,10 +263,10 @@ static ssize_t sta_aql_read(struct file *file, char __user *userbuf, return -ENOMEM; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - spin_lock_bh(&local->active_txq_lock[ac]); + spin_lock_bh(&local->airtime[ac].lock); q_limit_l[ac] = sta->airtime[ac].aql_limit_low; q_limit_h[ac] = sta->airtime[ac].aql_limit_high; - spin_unlock_bh(&local->active_txq_lock[ac]); + spin_unlock_bh(&local->airtime[ac].lock); q_depth[ac] = atomic_read(&sta->airtime[ac].aql_tx_pending); } diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 604ca59937f0..bcb7cc06db3d 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -2,7 +2,7 @@ /* * Portions of this file * Copyright(c) 2016 Intel Deutschland GmbH -* Copyright (C) 2018 - 2019 Intel Corporation +* Copyright (C) 2018 - 2019, 2021 Intel Corporation */ #ifndef __MAC80211_DRIVER_OPS @@ -821,7 +821,7 @@ drv_allow_buffered_frames(struct ieee80211_local *local, static inline void drv_mgd_prepare_tx(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - u16 duration) + struct ieee80211_prep_tx_info *info) { might_sleep(); @@ -829,9 +829,27 @@ static inline void drv_mgd_prepare_tx(struct ieee80211_local *local, return; WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION); - trace_drv_mgd_prepare_tx(local, sdata, duration); + trace_drv_mgd_prepare_tx(local, sdata, info->duration, + info->subtype, info->success); if (local->ops->mgd_prepare_tx) - local->ops->mgd_prepare_tx(&local->hw, &sdata->vif, duration); + local->ops->mgd_prepare_tx(&local->hw, &sdata->vif, info); + trace_drv_return_void(local); +} + +static inline void drv_mgd_complete_tx(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct ieee80211_prep_tx_info *info) +{ + might_sleep(); + + if (!check_sdata_in_driver(sdata)) + return; + WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION); + + trace_drv_mgd_complete_tx(local, sdata, info->duration, + info->subtype, info->success); + if (local->ops->mgd_complete_tx) + local->ops->mgd_complete_tx(&local->hw, &sdata->vif, info); trace_drv_return_void(local); } diff --git a/net/mac80211/he.c b/net/mac80211/he.c index 0c0b970835ce..c05af7018f79 100644 --- a/net/mac80211/he.c +++ b/net/mac80211/he.c @@ -111,7 +111,7 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { struct ieee80211_sta_he_cap *he_cap = &sta->sta.he_cap; - struct ieee80211_sta_he_cap own_he_cap = sband->iftype_data->he_cap; + struct ieee80211_sta_he_cap own_he_cap; struct ieee80211_he_cap_elem *he_cap_ie_elem = (void *)he_cap_ie; u8 he_ppe_size; u8 mcs_nss_size; @@ -120,9 +120,13 @@ ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata, memset(he_cap, 0, sizeof(*he_cap)); - if (!he_cap_ie || !ieee80211_get_he_sta_cap(sband)) + if (!he_cap_ie || + !ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif))) return; + own_he_cap = sband->iftype_data->he_cap; + /* Make sure size is OK */ mcs_nss_size = ieee80211_he_mcs_nss_size(he_cap_ie_elem); he_ppe_size = diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 3d62a80b5790..2eb7641f5556 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -9,7 +9,7 @@ * Copyright 2007, Michael Wu * Copyright 2007-2010, Intel Corporation * Copyright 2017 Intel Deutschland GmbH - * Copyright(c) 2020 Intel Corporation + * Copyright(c) 2020-2021 Intel Corporation */ #include @@ -555,17 +555,15 @@ void ieee80211_request_smps(struct ieee80211_vif *vif, { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); - if (WARN_ON_ONCE(vif->type != NL80211_IFTYPE_STATION && - vif->type != NL80211_IFTYPE_AP)) + if (WARN_ON_ONCE(vif->type != NL80211_IFTYPE_STATION)) return; - if (vif->type == NL80211_IFTYPE_STATION) { - if (sdata->u.mgd.driver_smps_mode == smps_mode) - return; - sdata->u.mgd.driver_smps_mode = smps_mode; - ieee80211_queue_work(&sdata->local->hw, - &sdata->u.mgd.request_smps_work); - } + if (sdata->u.mgd.driver_smps_mode == smps_mode) + return; + + sdata->u.mgd.driver_smps_mode = smps_mode; + ieee80211_queue_work(&sdata->local->hw, + &sdata->u.mgd.request_smps_work); } /* this might change ... don't want non-open drivers using it */ EXPORT_SYMBOL_GPL(ieee80211_request_smps); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 648696b49f89..22549b95d1aa 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc * Copyright 2007-2010 Johannes Berg * Copyright 2013-2015 Intel Mobile Communications GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #ifndef IEEE80211_I_H @@ -831,17 +831,16 @@ enum txq_info_flags { * @def_flow: used as a fallback flow when a packet destined to @tin hashes to * a fq_flow which is already owned by a different tin * @def_cvars: codel vars for @def_flow - * @frags: used to keep fragments created after dequeue * @schedule_order: used with ieee80211_local->active_txqs - * @schedule_round: counter to prevent infinite loops on TXQ scheduling + * @frags: used to keep fragments created after dequeue */ struct txq_info { struct fq_tin tin; struct codel_vars def_cvars; struct codel_stats cstats; + struct rb_node schedule_order; + struct sk_buff_head frags; - struct list_head schedule_order; - u16 schedule_round; unsigned long flags; /* keep last! */ @@ -918,6 +917,8 @@ struct ieee80211_sub_if_data { struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS]; struct mac80211_qos_map __rcu *qos_map; + struct airtime_info airtime[IEEE80211_NUM_ACS]; + struct work_struct csa_finalize_work; bool csa_block_tx; /* write-protected by sdata_lock and local->mtx */ struct cfg80211_chan_def csa_chandef; @@ -1130,6 +1131,44 @@ enum mac80211_scan_state { SCAN_ABORT, }; +/** + * struct airtime_sched_info - state used for airtime scheduling and AQL + * + * @lock: spinlock that protects all the fields in this struct + * @active_txqs: rbtree of currently backlogged queues, sorted by virtual time + * @schedule_pos: the current position maintained while a driver walks the tree + * with ieee80211_next_txq() + * @active_list: list of struct airtime_info structs that were active within + * the last AIRTIME_ACTIVE_DURATION (100 ms), used to compute + * weight_sum + * @last_weight_update: used for rate limiting walking active_list + * @last_schedule_time: tracks the last time a transmission was scheduled; used + * for catching up v_t if no stations are eligible for + * transmission. + * @v_t: global virtual time; queues with v_t < this are eligible for + * transmission + * @weight_sum: total sum of all active stations used for dividing airtime + * @weight_sum_reciprocal: reciprocal of weight_sum (to avoid divisions in fast + * path - see comment above + * IEEE80211_RECIPROCAL_DIVISOR_64) + * @aql_txq_limit_low: AQL limit when total outstanding airtime + * is < IEEE80211_AQL_THRESHOLD + * @aql_txq_limit_high: AQL limit when total outstanding airtime + * is > IEEE80211_AQL_THRESHOLD + */ +struct airtime_sched_info { + spinlock_t lock; + struct rb_root_cached active_txqs; + struct rb_node *schedule_pos; + struct list_head active_list; + u64 last_weight_update; + u64 last_schedule_activity; + u64 v_t; + u64 weight_sum; + u64 weight_sum_reciprocal; + u32 aql_txq_limit_low; + u32 aql_txq_limit_high; +}; DECLARE_STATIC_KEY_FALSE(aql_disable); struct ieee80211_local { @@ -1143,13 +1182,8 @@ struct ieee80211_local { struct codel_params cparams; /* protects active_txqs and txqi->schedule_order */ - spinlock_t active_txq_lock[IEEE80211_NUM_ACS]; - struct list_head active_txqs[IEEE80211_NUM_ACS]; - u16 schedule_round[IEEE80211_NUM_ACS]; - + struct airtime_sched_info airtime[IEEE80211_NUM_ACS]; u16 airtime_flags; - u32 aql_txq_limit_low[IEEE80211_NUM_ACS]; - u32 aql_txq_limit_high[IEEE80211_NUM_ACS]; u32 aql_threshold; atomic_t aql_total_pending_airtime; @@ -1414,10 +1448,6 @@ struct ieee80211_local { /* extended capabilities provided by mac80211 */ u8 ext_capa[8]; - - /* TDLS channel switch */ - struct work_struct tdls_chsw_work; - struct sk_buff_head skb_queue_tdls_chsw; }; static inline struct ieee80211_sub_if_data * @@ -1567,6 +1597,125 @@ static inline bool txq_has_queue(struct ieee80211_txq *txq) return !(skb_queue_empty(&txqi->frags) && !txqi->tin.backlog_packets); } +static inline struct airtime_info *to_airtime_info(struct ieee80211_txq *txq) +{ + struct ieee80211_sub_if_data *sdata; + struct sta_info *sta; + + if (txq->sta) { + sta = container_of(txq->sta, struct sta_info, sta); + return &sta->airtime[txq->ac]; + } + + sdata = vif_to_sdata(txq->vif); + return &sdata->airtime[txq->ac]; +} + +/* To avoid divisions in the fast path, we keep pre-computed reciprocals for + * airtime weight calculations. There are two different weights to keep track + * of: The per-station weight and the sum of weights per phy. + * + * For the per-station weights (kept in airtime_info below), we use 32-bit + * reciprocals with a devisor of 2^19. This lets us keep the multiplications and + * divisions for the station weights as 32-bit operations at the cost of a bit + * of rounding error for high weights; but the choice of divisor keeps rounding + * errors <10% for weights <2^15, assuming no more than 8ms of airtime is + * reported at a time. + * + * For the per-phy sum of weights the values can get higher, so we use 64-bit + * operations for those with a 32-bit divisor, which should avoid any + * significant rounding errors. + */ +#define IEEE80211_RECIPROCAL_DIVISOR_64 0x100000000ULL +#define IEEE80211_RECIPROCAL_SHIFT_64 32 +#define IEEE80211_RECIPROCAL_DIVISOR_32 0x80000U +#define IEEE80211_RECIPROCAL_SHIFT_32 19 + +static inline void airtime_weight_set(struct airtime_info *air_info, u16 weight) +{ + if (air_info->weight == weight) + return; + + air_info->weight = weight; + if (weight) { + air_info->weight_reciprocal = + IEEE80211_RECIPROCAL_DIVISOR_32 / weight; + } else { + air_info->weight_reciprocal = 0; + } +} + +static inline void airtime_weight_sum_set(struct airtime_sched_info *air_sched, + int weight_sum) +{ + if (air_sched->weight_sum == weight_sum) + return; + + air_sched->weight_sum = weight_sum; + if (air_sched->weight_sum) { + air_sched->weight_sum_reciprocal = IEEE80211_RECIPROCAL_DIVISOR_64; + do_div(air_sched->weight_sum_reciprocal, air_sched->weight_sum); + } else { + air_sched->weight_sum_reciprocal = 0; + } +} + +/* A problem when trying to enforce airtime fairness is that we want to divide + * the airtime between the currently *active* stations. However, basing this on + * the instantaneous queue state of stations doesn't work, as queues tend to + * oscillate very quickly between empty and occupied, leading to the scheduler + * thinking only a single station is active when deciding whether to allow + * transmission (and thus not throttling correctly). + * + * To fix this we use a timer-based notion of activity: a station is considered + * active if it has been scheduled within the last 100 ms; we keep a separate + * list of all the stations considered active in this manner, and lazily update + * the total weight of active stations from this list (filtering the stations in + * the list by their 'last active' time). + * + * We add one additional safeguard to guard against stations that manage to get + * scheduled every 100 ms but don't transmit a lot of data, and thus don't use + * up any airtime. Such stations would be able to get priority for an extended + * period of time if they do start transmitting at full capacity again, and so + * we add an explicit maximum for how far behind a station is allowed to fall in + * the virtual airtime domain. This limit is set to a relatively high value of + * 20 ms because the main mechanism for catching up idle stations is the active + * state as described above; i.e., the hard limit should only be hit in + * pathological cases. + */ +#define AIRTIME_ACTIVE_DURATION (100 * NSEC_PER_MSEC) +#define AIRTIME_MAX_BEHIND 20000 /* 20 ms */ + +static inline bool airtime_is_active(struct airtime_info *air_info, u64 now) +{ + return air_info->last_scheduled >= now - AIRTIME_ACTIVE_DURATION; +} + +static inline void airtime_set_active(struct airtime_sched_info *air_sched, + struct airtime_info *air_info, u64 now) +{ + air_info->last_scheduled = now; + air_sched->last_schedule_activity = now; + list_move_tail(&air_info->list, &air_sched->active_list); +} + +static inline bool airtime_catchup_v_t(struct airtime_sched_info *air_sched, + u64 v_t, u64 now) +{ + air_sched->v_t = v_t; + return true; +} + +static inline void init_airtime_info(struct airtime_info *air_info, + struct airtime_sched_info *air_sched) +{ + atomic_set(&air_info->aql_tx_pending, 0); + air_info->aql_limit_low = air_sched->aql_txq_limit_low; + air_info->aql_limit_high = air_sched->aql_txq_limit_high; + airtime_weight_set(air_info, IEEE80211_DEFAULT_AIRTIME_WEIGHT); + INIT_LIST_HEAD(&air_info->list); +} + static inline int ieee80211_bssid_match(const u8 *raddr, const u8 *addr) { return ether_addr_equal(raddr, addr) || @@ -1809,6 +1958,14 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, u64 *cookie); int ieee80211_probe_mesh_link(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len); +void ieee80211_resort_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq); +void ieee80211_unschedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq, + bool purge); +void ieee80211_update_airtime_weight(struct ieee80211_local *local, + struct airtime_sched_info *air_sched, + u64 now, bool force); /* HT */ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata, @@ -1879,7 +2036,6 @@ void ieee80211_sta_set_rx_nss(struct sta_info *sta); enum ieee80211_sta_rx_bandwidth ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width); enum nl80211_chan_width ieee80211_sta_cap_chan_bw(struct sta_info *sta); -void ieee80211_sta_set_rx_nss(struct sta_info *sta); void ieee80211_process_mu_groups(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt); u32 __ieee80211_vht_handle_opmode(struct ieee80211_sub_if_data *sdata, @@ -2287,9 +2443,13 @@ void ieee80211_tdls_cancel_channel_switch(struct wiphy *wiphy, struct net_device *dev, const u8 *addr); void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata); -void ieee80211_tdls_chsw_work(struct work_struct *wk); void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata, const u8 *peer, u16 reason); +void +ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb); + + const char *ieee80211_get_reason_code_string(u16 reason_code); u16 ieee80211_encode_usf(int val); u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 137fa4c50e07..1e5e9fc45523 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1318,13 +1318,130 @@ static void ieee80211_if_setup_no_queue(struct net_device *dev) dev->priv_flags |= IFF_NO_QUEUE; } +static void ieee80211_iface_process_skb(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct sk_buff *skb) +{ + struct ieee80211_mgmt *mgmt = (void *)skb->data; + + if (ieee80211_is_action(mgmt->frame_control) && + mgmt->u.action.category == WLAN_CATEGORY_BACK) { + struct sta_info *sta; + int len = skb->len; + + mutex_lock(&local->sta_mtx); + sta = sta_info_get_bss(sdata, mgmt->sa); + if (sta) { + switch (mgmt->u.action.u.addba_req.action_code) { + case WLAN_ACTION_ADDBA_REQ: + ieee80211_process_addba_request(local, sta, + mgmt, len); + break; + case WLAN_ACTION_ADDBA_RESP: + ieee80211_process_addba_resp(local, sta, + mgmt, len); + break; + case WLAN_ACTION_DELBA: + ieee80211_process_delba(sdata, sta, + mgmt, len); + break; + default: + WARN_ON(1); + break; + } + } + mutex_unlock(&local->sta_mtx); + } else if (ieee80211_is_action(mgmt->frame_control) && + mgmt->u.action.category == WLAN_CATEGORY_VHT) { + switch (mgmt->u.action.u.vht_group_notif.action_code) { + case WLAN_VHT_ACTION_OPMODE_NOTIF: { + struct ieee80211_rx_status *status; + enum nl80211_band band; + struct sta_info *sta; + u8 opmode; + + status = IEEE80211_SKB_RXCB(skb); + band = status->band; + opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode; + + mutex_lock(&local->sta_mtx); + sta = sta_info_get_bss(sdata, mgmt->sa); + + if (sta) + ieee80211_vht_handle_opmode(sdata, sta, opmode, + band); + + mutex_unlock(&local->sta_mtx); + break; + } + case WLAN_VHT_ACTION_GROUPID_MGMT: + ieee80211_process_mu_groups(sdata, mgmt); + break; + default: + WARN_ON(1); + break; + } + } else if (ieee80211_is_ext(mgmt->frame_control)) { + if (sdata->vif.type == NL80211_IFTYPE_STATION) + ieee80211_sta_rx_queued_ext(sdata, skb); + else + WARN_ON(1); + } else if (ieee80211_is_data_qos(mgmt->frame_control)) { + struct ieee80211_hdr *hdr = (void *)mgmt; + struct sta_info *sta; + + /* + * So the frame isn't mgmt, but frame_control + * is at the right place anyway, of course, so + * the if statement is correct. + * + * Warn if we have other data frame types here, + * they must not get here. + */ + WARN_ON(hdr->frame_control & + cpu_to_le16(IEEE80211_STYPE_NULLFUNC)); + WARN_ON(!(hdr->seq_ctrl & + cpu_to_le16(IEEE80211_SCTL_FRAG))); + /* + * This was a fragment of a frame, received while + * a block-ack session was active. That cannot be + * right, so terminate the session. + */ + mutex_lock(&local->sta_mtx); + sta = sta_info_get_bss(sdata, mgmt->sa); + if (sta) { + u16 tid = ieee80211_get_tid(hdr); + + __ieee80211_stop_rx_ba_session( + sta, tid, WLAN_BACK_RECIPIENT, + WLAN_REASON_QSTA_REQUIRE_SETUP, + true); + } + mutex_unlock(&local->sta_mtx); + } else switch (sdata->vif.type) { + case NL80211_IFTYPE_STATION: + ieee80211_sta_rx_queued_mgmt(sdata, skb); + break; + case NL80211_IFTYPE_ADHOC: + ieee80211_ibss_rx_queued_mgmt(sdata, skb); + break; + case NL80211_IFTYPE_MESH_POINT: + if (!ieee80211_vif_is_mesh(&sdata->vif)) + break; + ieee80211_mesh_rx_queued_mgmt(sdata, skb); + break; + default: + WARN(1, "frame for unexpected interface type"); + break; + } +} + static void ieee80211_iface_work(struct work_struct *work) { struct ieee80211_sub_if_data *sdata = container_of(work, struct ieee80211_sub_if_data, work); struct ieee80211_local *local = sdata->local; struct sk_buff *skb; - struct sta_info *sta; if (!ieee80211_sdata_running(sdata)) return; @@ -1337,116 +1454,12 @@ static void ieee80211_iface_work(struct work_struct *work) /* first process frames */ while ((skb = skb_dequeue(&sdata->skb_queue))) { - struct ieee80211_mgmt *mgmt = (void *)skb->data; - kcov_remote_start_common(skb_get_kcov_handle(skb)); - if (ieee80211_is_action(mgmt->frame_control) && - mgmt->u.action.category == WLAN_CATEGORY_BACK) { - int len = skb->len; - mutex_lock(&local->sta_mtx); - sta = sta_info_get_bss(sdata, mgmt->sa); - if (sta) { - switch (mgmt->u.action.u.addba_req.action_code) { - case WLAN_ACTION_ADDBA_REQ: - ieee80211_process_addba_request( - local, sta, mgmt, len); - break; - case WLAN_ACTION_ADDBA_RESP: - ieee80211_process_addba_resp(local, sta, - mgmt, len); - break; - case WLAN_ACTION_DELBA: - ieee80211_process_delba(sdata, sta, - mgmt, len); - break; - default: - WARN_ON(1); - break; - } - } - mutex_unlock(&local->sta_mtx); - } else if (ieee80211_is_action(mgmt->frame_control) && - mgmt->u.action.category == WLAN_CATEGORY_VHT) { - switch (mgmt->u.action.u.vht_group_notif.action_code) { - case WLAN_VHT_ACTION_OPMODE_NOTIF: { - struct ieee80211_rx_status *status; - enum nl80211_band band; - u8 opmode; - - status = IEEE80211_SKB_RXCB(skb); - band = status->band; - opmode = mgmt->u.action.u.vht_opmode_notif.operating_mode; - - mutex_lock(&local->sta_mtx); - sta = sta_info_get_bss(sdata, mgmt->sa); - - if (sta) - ieee80211_vht_handle_opmode(sdata, sta, - opmode, - band); - - mutex_unlock(&local->sta_mtx); - break; - } - case WLAN_VHT_ACTION_GROUPID_MGMT: - ieee80211_process_mu_groups(sdata, mgmt); - break; - default: - WARN_ON(1); - break; - } - } else if (ieee80211_is_ext(mgmt->frame_control)) { - if (sdata->vif.type == NL80211_IFTYPE_STATION) - ieee80211_sta_rx_queued_ext(sdata, skb); - else - WARN_ON(1); - } else if (ieee80211_is_data_qos(mgmt->frame_control)) { - struct ieee80211_hdr *hdr = (void *)mgmt; - /* - * So the frame isn't mgmt, but frame_control - * is at the right place anyway, of course, so - * the if statement is correct. - * - * Warn if we have other data frame types here, - * they must not get here. - */ - WARN_ON(hdr->frame_control & - cpu_to_le16(IEEE80211_STYPE_NULLFUNC)); - WARN_ON(!(hdr->seq_ctrl & - cpu_to_le16(IEEE80211_SCTL_FRAG))); - /* - * This was a fragment of a frame, received while - * a block-ack session was active. That cannot be - * right, so terminate the session. - */ - mutex_lock(&local->sta_mtx); - sta = sta_info_get_bss(sdata, mgmt->sa); - if (sta) { - u16 tid = ieee80211_get_tid(hdr); - - __ieee80211_stop_rx_ba_session( - sta, tid, WLAN_BACK_RECIPIENT, - WLAN_REASON_QSTA_REQUIRE_SETUP, - true); - } - mutex_unlock(&local->sta_mtx); - } else switch (sdata->vif.type) { - case NL80211_IFTYPE_STATION: - ieee80211_sta_rx_queued_mgmt(sdata, skb); - break; - case NL80211_IFTYPE_ADHOC: - ieee80211_ibss_rx_queued_mgmt(sdata, skb); - break; - case NL80211_IFTYPE_MESH_POINT: - if (!ieee80211_vif_is_mesh(&sdata->vif)) - break; - ieee80211_mesh_rx_queued_mgmt(sdata, skb); - break; - default: - WARN(1, "frame for unexpected interface type"); - break; - } + if (skb->protocol == cpu_to_be16(ETH_P_TDLS)) + ieee80211_process_tdls_channel_switch(sdata, skb); + else + ieee80211_iface_process_skb(local, sdata, skb); kfree_skb(skb); kcov_remote_stop(); @@ -1964,6 +1977,9 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, } } + for (i = 0; i < IEEE80211_NUM_ACS; i++) + init_airtime_info(&sdata->airtime[i], &local->airtime[i]); + ieee80211_set_default_queues(sdata); sdata->ap_power_level = IEEE80211_UNSET_POWER_LEVEL; diff --git a/net/mac80211/led.c b/net/mac80211/led.c index b275c8853074..6de8d0ad5497 100644 --- a/net/mac80211/led.c +++ b/net/mac80211/led.c @@ -259,7 +259,6 @@ static void tpt_trig_timer(struct timer_list *t) { struct tpt_led_trigger *tpt_trig = from_timer(tpt_trig, t, timer); struct ieee80211_local *local = tpt_trig->local; - struct led_classdev *led_cdev; unsigned long on, off, tpt; int i; @@ -283,10 +282,7 @@ static void tpt_trig_timer(struct timer_list *t) } } - read_lock(&local->tpt_led.leddev_list_lock); - list_for_each_entry(led_cdev, &local->tpt_led.led_cdevs, trig_list) - led_blink_set(led_cdev, &on, &off); - read_unlock(&local->tpt_led.leddev_list_lock); + led_trigger_blink(&local->tpt_led, &on, &off); } const char * @@ -341,7 +337,6 @@ static void ieee80211_start_tpt_led_trig(struct ieee80211_local *local) static void ieee80211_stop_tpt_led_trig(struct ieee80211_local *local) { struct tpt_led_trigger *tpt_trig = local->tpt_led_trigger; - struct led_classdev *led_cdev; if (!tpt_trig->running) return; @@ -349,10 +344,7 @@ static void ieee80211_stop_tpt_led_trig(struct ieee80211_local *local) tpt_trig->running = false; del_timer_sync(&tpt_trig->timer); - read_lock(&local->tpt_led.leddev_list_lock); - list_for_each_entry(led_cdev, &local->tpt_led.led_cdevs, trig_list) - led_set_brightness(led_cdev, LED_OFF); - read_unlock(&local->tpt_led.leddev_list_lock); + led_trigger_event(&local->tpt_led, LED_OFF); } void ieee80211_mod_tpt_led_trig(struct ieee80211_local *local, diff --git a/net/mac80211/main.c b/net/mac80211/main.c index f33a3acd7f96..05f4c3c72619 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -257,14 +257,13 @@ static void ieee80211_restart_work(struct work_struct *work) /* wait for scan work complete */ flush_workqueue(local->workqueue); flush_work(&local->sched_scan_stopped_work); + flush_work(&local->radar_detected_work); + + rtnl_lock(); WARN(test_bit(SCAN_HW_SCANNING, &local->scanning), "%s called with hardware scan in progress\n", __func__); - flush_work(&local->radar_detected_work); - /* we might do interface manipulations, so need both */ - rtnl_lock(); - wiphy_lock(local->hw.wiphy); list_for_each_entry(sdata, &local->interfaces, list) { /* * XXX: there may be more work for other vif types and even @@ -706,10 +705,13 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, spin_lock_init(&local->queue_stop_reason_lock); for (i = 0; i < IEEE80211_NUM_ACS; i++) { - INIT_LIST_HEAD(&local->active_txqs[i]); - spin_lock_init(&local->active_txq_lock[i]); - local->aql_txq_limit_low[i] = IEEE80211_DEFAULT_AQL_TXQ_LIMIT_L; - local->aql_txq_limit_high[i] = + struct airtime_sched_info *air_sched = &local->airtime[i]; + + air_sched->active_txqs = RB_ROOT_CACHED; + INIT_LIST_HEAD(&air_sched->active_list); + spin_lock_init(&air_sched->lock); + air_sched->aql_txq_limit_low = IEEE80211_DEFAULT_AQL_TXQ_LIMIT_L; + air_sched->aql_txq_limit_high = IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H; } @@ -739,8 +741,6 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, INIT_WORK(&local->sched_scan_stopped_work, ieee80211_sched_scan_stopped_work); - INIT_WORK(&local->tdls_chsw_work, ieee80211_tdls_chsw_work); - spin_lock_init(&local->ack_status_lock); idr_init(&local->ack_status_frames); @@ -757,7 +757,6 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, skb_queue_head_init(&local->skb_queue); skb_queue_head_init(&local->skb_queue_unreliable); - skb_queue_head_init(&local->skb_queue_tdls_chsw); ieee80211_alloc_led_names(local); @@ -1014,8 +1013,13 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) supp_ht = supp_ht || sband->ht_cap.ht_supported; supp_vht = supp_vht || sband->vht_cap.vht_supported; - if (!supp_he) - supp_he = !!ieee80211_get_he_sta_cap(sband); + for (i = 0; i < sband->n_iftype_data; i++) { + const struct ieee80211_sband_iftype_data *iftd; + + iftd = &sband->iftype_data[i]; + + supp_he = supp_he || (iftd && iftd->he_cap.has_he); + } /* HT, VHT, HE require QoS, thus >= 4 queues */ if (WARN_ON(local->hw.queues < IEEE80211_NUM_ACS && @@ -1389,7 +1393,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) cancel_delayed_work_sync(&local->roc_work); cancel_work_sync(&local->restart_work); cancel_work_sync(&local->reconfig_filter); - cancel_work_sync(&local->tdls_chsw_work); flush_work(&local->sched_scan_stopped_work); flush_work(&local->radar_detected_work); @@ -1401,7 +1404,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) wiphy_warn(local->hw.wiphy, "skb_queue not empty\n"); skb_queue_purge(&local->skb_queue); skb_queue_purge(&local->skb_queue_unreliable); - skb_queue_purge(&local->skb_queue_tdls_chsw); wiphy_unregister(local->hw.wiphy); destroy_workqueue(local->workqueue); diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 40492d1bd8fd..77080b4f87b8 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -134,7 +134,7 @@ struct mesh_path { * gate's mpath may or may not be resolved and active. * @gates_lock: protects updates to known_gates * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr - * @walk_head: linked list containging all mesh_path objects + * @walk_head: linked list containing all mesh_path objects * @walk_lock: lock protecting walk_head * @entries: number of entries in the table */ diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 3db514c4c63a..a05b615deb51 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -1124,7 +1124,7 @@ enddiscovery: * forwarding information is found. * * Returns: 0 if the next hop was found and -ENOENT if the frame was queued. - * skb is freeed here if no mpath could be allocated. + * skb is freed here if no mpath could be allocated. */ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 620ecf922408..efbefcbac3ac 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -122,7 +122,7 @@ static void prepare_for_gate(struct sk_buff *skb, char *dst_addr, hdr = (struct ieee80211_hdr *) skb->data; /* we preserve the previous mesh header and only add - * the new addreses */ + * the new addresses */ mshdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); mshdr->flags = MESH_FLAGS_AE_A5_A6; memcpy(mshdr->eaddr1, hdr->addr3, ETH_ALEN); diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index aca26df7587d..a6915847d78a 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -150,7 +150,7 @@ out: * mesh STA in a MBSS. Three HT protection modes are supported for now, non-HT * mixed mode, 20MHz-protection and no-protection mode. non-HT mixed mode is * selected if any non-HT peers are present in our MBSS. 20MHz-protection mode - * is selected if all peers in our 20/40MHz MBSS support HT and atleast one + * is selected if all peers in our 20/40MHz MBSS support HT and at least one * HT20 peer is present. Otherwise no-protection mode is selected. */ static u32 mesh_set_ht_prot_mode(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 3f2aad2e7436..a00f11a33699 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -8,7 +8,7 @@ * Copyright 2007, Michael Wu * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2020 Intel Corporation + * Copyright (C) 2018 - 2021 Intel Corporation */ #include @@ -371,7 +371,6 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, struct cfg80211_chan_def chandef; u16 ht_opmode; u32 flags; - enum ieee80211_sta_rx_bandwidth new_sta_bw; u32 vht_cap_info = 0; int ret; @@ -385,7 +384,9 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, /* don't check HE if we associated as non-HE station */ if (ifmgd->flags & IEEE80211_STA_DISABLE_HE || - !ieee80211_get_he_sta_cap(sband)) + !ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif))) + he_oper = NULL; if (WARN_ON_ONCE(!sta)) @@ -445,40 +446,13 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, IEEE80211_STA_DISABLE_160MHZ)) || !cfg80211_chandef_valid(&chandef)) { sdata_info(sdata, - "AP %pM changed bandwidth in a way we can't support - disconnect\n", - ifmgd->bssid); + "AP %pM changed caps/bw in a way we can't support (0x%x/0x%x) - disconnect\n", + ifmgd->bssid, flags, ifmgd->flags); return -EINVAL; } - switch (chandef.width) { - case NL80211_CHAN_WIDTH_20_NOHT: - case NL80211_CHAN_WIDTH_20: - new_sta_bw = IEEE80211_STA_RX_BW_20; - break; - case NL80211_CHAN_WIDTH_40: - new_sta_bw = IEEE80211_STA_RX_BW_40; - break; - case NL80211_CHAN_WIDTH_80: - new_sta_bw = IEEE80211_STA_RX_BW_80; - break; - case NL80211_CHAN_WIDTH_80P80: - case NL80211_CHAN_WIDTH_160: - new_sta_bw = IEEE80211_STA_RX_BW_160; - break; - default: - return -EINVAL; - } - - if (new_sta_bw > sta->cur_max_bandwidth) - new_sta_bw = sta->cur_max_bandwidth; - - if (new_sta_bw < sta->sta.bandwidth) { - sta->sta.bandwidth = new_sta_bw; - rate_control_rate_update(local, sband, sta, - IEEE80211_RC_BW_CHANGED); - } - ret = ieee80211_vif_change_bandwidth(sdata, &chandef, changed); + if (ret) { sdata_info(sdata, "AP %pM changed bandwidth to incompatible one - disconnect\n", @@ -486,12 +460,6 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata, return ret; } - if (new_sta_bw > sta->sta.bandwidth) { - sta->sta.bandwidth = new_sta_bw; - rate_control_rate_update(local, sband, sta, - IEEE80211_RC_BW_CHANGED); - } - return 0; } @@ -617,7 +585,7 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, cap &= ~IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE; /* - * If some other vif is using the MU-MIMO capablity we cannot associate + * If some other vif is using the MU-MIMO capability we cannot associate * using MU-MIMO - this will lead to contradictions in the group-id * mechanism. * Ownership is defined since association request, in order to avoid @@ -676,7 +644,8 @@ static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); - he_cap = ieee80211_get_he_sta_cap(sband); + he_cap = ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); if (!he_cap || !reg_cap) return; @@ -712,6 +681,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) u32 rates = 0; __le16 listen_int; struct element *ext_capa = NULL; + enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif); + const struct ieee80211_sband_iftype_data *iftd; + struct ieee80211_prep_tx_info info = {}; /* we know it's writable, cast away the const */ if (assoc_data->ie_len) @@ -756,6 +728,8 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) } } + iftd = ieee80211_get_sband_iftype_data(sband, iftype); + skb = alloc_skb(local->hw.extra_tx_headroom + sizeof(*mgmt) + /* bit too much but doesn't matter */ 2 + assoc_data->ssid_len + /* SSID */ @@ -770,7 +744,8 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) 2 + 1 + sizeof(struct ieee80211_he_6ghz_capa) + assoc_data->ie_len + /* extra IEs */ (assoc_data->fils_kek_len ? 16 /* AES-SIV */ : 0) + - 9, /* WMM */ + 9 + /* WMM */ + (iftd ? iftd->vendor_elems.len : 0), GFP_KERNEL); if (!skb) return; @@ -810,12 +785,14 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata) mgmt->u.reassoc_req.listen_interval = listen_int; memcpy(mgmt->u.reassoc_req.current_ap, assoc_data->prev_bssid, ETH_ALEN); + info.subtype = IEEE80211_STYPE_REASSOC_REQ; } else { skb_put(skb, 4); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_REQ); mgmt->u.assoc_req.capab_info = cpu_to_le16(capab); mgmt->u.assoc_req.listen_interval = listen_int; + info.subtype = IEEE80211_STYPE_ASSOC_REQ; } /* SSID */ @@ -1043,6 +1020,9 @@ skip_rates: ieee80211_add_s1g_capab_ie(sdata, &sband->s1g_cap, skb); } + if (iftd && iftd->vendor_elems.data && iftd->vendor_elems.len) + skb_put_data(skb, iftd->vendor_elems.data, iftd->vendor_elems.len); + /* add any remaining custom (i.e. vendor specific here) IEs */ if (assoc_data->ie_len) { noffset = assoc_data->ie_len; @@ -1060,7 +1040,7 @@ skip_rates: ifmgd->assoc_req_ies = kmemdup(ie_start, pos - ie_start, GFP_ATOMIC); ifmgd->assoc_req_ies_len = pos - ie_start; - drv_mgd_prepare_tx(local, sdata, 0); + drv_mgd_prepare_tx(local, sdata, &info); IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) @@ -1094,11 +1074,6 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, struct ieee80211_hdr_3addr *nullfunc; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - /* Don't send NDPs when STA is connected HE */ - if (sdata->vif.type == NL80211_IFTYPE_STATION && - !(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) - return; - skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif, !ieee80211_hw_check(&local->hw, DOESNT_SUPPORT_QOS_NDP)); if (!skb) @@ -1130,10 +1105,6 @@ static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) return; - /* Don't send NDPs when connected HE */ - if (!(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE)) - return; - skb = dev_alloc_skb(local->hw.extra_tx_headroom + 30); if (!skb) return; @@ -1183,10 +1154,6 @@ static void ieee80211_chswitch_work(struct work_struct *work) */ if (sdata->reserved_chanctx) { - struct ieee80211_supported_band *sband = NULL; - struct sta_info *mgd_sta = NULL; - enum ieee80211_sta_rx_bandwidth bw = IEEE80211_STA_RX_BW_20; - /* * with multi-vif csa driver may call ieee80211_csa_finish() * many times while waiting for other interfaces to use their @@ -1195,48 +1162,6 @@ static void ieee80211_chswitch_work(struct work_struct *work) if (sdata->reserved_ready) goto out; - if (sdata->vif.bss_conf.chandef.width != - sdata->csa_chandef.width) { - /* - * For managed interface, we need to also update the AP - * station bandwidth and align the rate scale algorithm - * on the bandwidth change. Here we only consider the - * bandwidth of the new channel definition (as channel - * switch flow does not have the full HT/VHT/HE - * information), assuming that if additional changes are - * required they would be done as part of the processing - * of the next beacon from the AP. - */ - switch (sdata->csa_chandef.width) { - case NL80211_CHAN_WIDTH_20_NOHT: - case NL80211_CHAN_WIDTH_20: - default: - bw = IEEE80211_STA_RX_BW_20; - break; - case NL80211_CHAN_WIDTH_40: - bw = IEEE80211_STA_RX_BW_40; - break; - case NL80211_CHAN_WIDTH_80: - bw = IEEE80211_STA_RX_BW_80; - break; - case NL80211_CHAN_WIDTH_80P80: - case NL80211_CHAN_WIDTH_160: - bw = IEEE80211_STA_RX_BW_160; - break; - } - - mgd_sta = sta_info_get(sdata, ifmgd->bssid); - sband = - local->hw.wiphy->bands[sdata->csa_chandef.chan->band]; - } - - if (sdata->vif.bss_conf.chandef.width > - sdata->csa_chandef.width) { - mgd_sta->sta.bandwidth = bw; - rate_control_rate_update(local, sband, mgd_sta, - IEEE80211_RC_BW_CHANGED); - } - ret = ieee80211_vif_use_reserved_context(sdata); if (ret) { sdata_info(sdata, @@ -1247,13 +1172,6 @@ static void ieee80211_chswitch_work(struct work_struct *work) goto out; } - if (sdata->vif.bss_conf.chandef.width < - sdata->csa_chandef.width) { - mgd_sta->sta.bandwidth = bw; - rate_control_rate_update(local, sband, mgd_sta, - IEEE80211_RC_BW_CHANGED); - } - goto out; } @@ -2341,6 +2259,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; u32 changed = 0; + struct ieee80211_prep_tx_info info = { + .subtype = stype, + }; sdata_assert_lock(sdata); @@ -2390,8 +2311,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, * driver requested so. */ if (ieee80211_hw_check(&local->hw, DEAUTH_NEED_MGD_TX_PREP) && - !ifmgd->have_beacon) - drv_mgd_prepare_tx(sdata->local, sdata, 0); + !ifmgd->have_beacon) { + drv_mgd_prepare_tx(sdata->local, sdata, &info); + } ieee80211_send_deauth_disassoc(sdata, ifmgd->bssid, ifmgd->bssid, stype, reason, @@ -2402,6 +2324,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, if (tx) ieee80211_flush_queues(local, sdata, false); + drv_mgd_complete_tx(sdata->local, sdata, &info); + /* clear bssid only after building the needed mgmt frames */ eth_zero_addr(ifmgd->bssid); @@ -2617,10 +2541,7 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) if (ieee80211_hw_check(&sdata->local->hw, REPORTS_TX_ACK_STATUS)) { ifmgd->nullfunc_failed = false; - if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) - ifmgd->probe_send_count--; - else - ieee80211_send_nullfunc(sdata->local, sdata, false); + ieee80211_send_nullfunc(sdata->local, sdata, false); } else { int ssid_len; @@ -2952,6 +2873,9 @@ static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata, u8 *pos; struct ieee802_11_elems elems; u32 tx_flags = 0; + struct ieee80211_prep_tx_info info = { + .subtype = IEEE80211_STYPE_AUTH, + }; pos = mgmt->u.auth.variable; ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, &elems, @@ -2959,7 +2883,7 @@ static void ieee80211_auth_challenge(struct ieee80211_sub_if_data *sdata, if (!elems.challenge) return; auth_data->expected_transaction = 4; - drv_mgd_prepare_tx(sdata->local, sdata, 0); + drv_mgd_prepare_tx(sdata->local, sdata, &info); if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) tx_flags = IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_INTFL_MLME_CONN_TX; @@ -3012,6 +2936,9 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, .type = MLME_EVENT, .u.mlme.data = AUTH_EVENT, }; + struct ieee80211_prep_tx_info info = { + .subtype = IEEE80211_STYPE_AUTH, + }; sdata_assert_lock(sdata); @@ -3040,7 +2967,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, mgmt->sa, auth_alg, ifmgd->auth_data->algorithm, auth_transaction, ifmgd->auth_data->expected_transaction); - return; + goto notify_driver; } if (status_code != WLAN_STATUS_SUCCESS) { @@ -3051,7 +2978,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, (auth_transaction == 1 && (status_code == WLAN_STATUS_SAE_HASH_TO_ELEMENT || status_code == WLAN_STATUS_SAE_PK)))) - return; + goto notify_driver; sdata_info(sdata, "%pM denied authentication (status %d)\n", mgmt->sa, status_code); @@ -3059,7 +2986,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, event.u.mlme.status = MLME_DENIED; event.u.mlme.reason = status_code; drv_event_callback(sdata->local, sdata, &event); - return; + goto notify_driver; } switch (ifmgd->auth_data->algorithm) { @@ -3081,10 +3008,11 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, default: WARN_ONCE(1, "invalid auth alg %d", ifmgd->auth_data->algorithm); - return; + goto notify_driver; } event.u.mlme.status = MLME_SUCCESS; + info.success = 1; drv_event_callback(sdata->local, sdata, &event); if (ifmgd->auth_data->algorithm != WLAN_AUTH_SAE || (auth_transaction == 2 && @@ -3098,6 +3026,8 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, } cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); +notify_driver: + drv_mgd_complete_tx(sdata->local, sdata, &info); } #define case_WLAN(type) \ @@ -3314,6 +3244,23 @@ static int ieee80211_recalc_twt_req(struct ieee80211_sub_if_data *sdata, return 0; } +static bool ieee80211_twt_bcast_support(struct ieee80211_sub_if_data *sdata, + struct ieee80211_bss_conf *bss_conf, + struct ieee80211_supported_band *sband, + struct sta_info *sta) +{ + const struct ieee80211_sta_he_cap *own_he_cap = + ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); + + return bss_conf->he_support && + (sta->sta.he_cap.he_cap_elem.mac_cap_info[2] & + IEEE80211_HE_MAC_CAP2_BCAST_TWT) && + own_he_cap && + (own_he_cap->he_cap_elem.mac_cap_info[2] & + IEEE80211_HE_MAC_CAP2_BCAST_TWT); +} + static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, struct cfg80211_bss *cbss, struct ieee80211_mgmt *mgmt, size_t len, @@ -3529,6 +3476,9 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, bss_conf->twt_protected = false; } + bss_conf->twt_broadcast = + ieee80211_twt_bcast_support(sdata, bss_conf, sband, sta); + if (bss_conf->he_support) { bss_conf->he_bss_color.color = le32_get_bits(elems->he_operation->he_oper_params, @@ -3699,6 +3649,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, .type = MLME_EVENT, .u.mlme.data = ASSOC_EVENT, }; + struct ieee80211_prep_tx_info info = {}; sdata_assert_lock(sdata); @@ -3728,6 +3679,15 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, aid = 0; /* TODO */ } + /* + * Note: this may not be perfect, AP might misbehave - if + * anyone needs to rely on perfect complete notification + * with the exact right subtype, then we need to track what + * we actually transmitted. + */ + info.subtype = reassoc ? IEEE80211_STYPE_REASSOC_REQ : + IEEE80211_STYPE_ASSOC_REQ; + sdata_info(sdata, "RX %sssocResp from %pM (capab=0x%x status=%d aid=%d)\n", reassoc ? "Rea" : "A", mgmt->sa, @@ -3753,7 +3713,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, assoc_data->timeout_started = true; if (ms > IEEE80211_ASSOC_TIMEOUT) run_again(sdata, assoc_data->timeout); - return; + goto notify_driver; } if (status_code != WLAN_STATUS_SUCCESS) { @@ -3768,7 +3728,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, /* oops -- internal error -- send timeout for now */ ieee80211_destroy_assoc_data(sdata, false, false); cfg80211_assoc_timeout(sdata->dev, cbss); - return; + goto notify_driver; } event.u.mlme.status = MLME_SUCCESS; drv_event_callback(sdata->local, sdata, &event); @@ -3786,10 +3746,14 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) if (sdata->tx_conf[ac].uapsd) uapsd_queues |= ieee80211_ac_to_qos_mask[ac]; + + info.success = 1; } cfg80211_rx_assoc_resp(sdata->dev, cbss, (u8 *)mgmt, len, uapsd_queues, ifmgd->assoc_req_ies, ifmgd->assoc_req_ies_len); +notify_driver: + drv_mgd_complete_tx(sdata->local, sdata, &info); } static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, @@ -4408,7 +4372,9 @@ static int ieee80211_auth(struct ieee80211_sub_if_data *sdata) u32 tx_flags = 0; u16 trans = 1; u16 status = 0; - u16 prepare_tx_duration = 0; + struct ieee80211_prep_tx_info info = { + .subtype = IEEE80211_STYPE_AUTH, + }; sdata_assert_lock(sdata); @@ -4431,10 +4397,9 @@ static int ieee80211_auth(struct ieee80211_sub_if_data *sdata) } if (auth_data->algorithm == WLAN_AUTH_SAE) - prepare_tx_duration = - jiffies_to_msecs(IEEE80211_AUTH_TIMEOUT_SAE); + info.duration = jiffies_to_msecs(IEEE80211_AUTH_TIMEOUT_SAE); - drv_mgd_prepare_tx(local, sdata, prepare_tx_duration); + drv_mgd_prepare_tx(local, sdata, &info); sdata_info(sdata, "send auth to %pM (try %d/%d)\n", auth_data->bss->bssid, auth_data->tries, @@ -4929,11 +4894,13 @@ static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata, } static bool -ieee80211_verify_sta_he_mcs_support(struct ieee80211_supported_band *sband, +ieee80211_verify_sta_he_mcs_support(struct ieee80211_sub_if_data *sdata, + struct ieee80211_supported_band *sband, const struct ieee80211_he_operation *he_op) { const struct ieee80211_sta_he_cap *sta_he_cap = - ieee80211_get_he_sta_cap(sband); + ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); u16 ap_min_req_set; int i; @@ -5027,7 +4994,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } - if (!ieee80211_get_he_sta_cap(sband)) + if (!ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif))) ifmgd->flags |= IEEE80211_STA_DISABLE_HE; rcu_read_lock(); @@ -5085,7 +5053,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, else he_oper = NULL; - if (!ieee80211_verify_sta_he_mcs_support(sband, he_oper)) + if (!ieee80211_verify_sta_he_mcs_support(sdata, sband, he_oper)) ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } @@ -5655,15 +5623,6 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, 2 * FILS_NONCE_LEN); assoc_data->bss = req->bss; - - if (ifmgd->req_smps == IEEE80211_SMPS_AUTOMATIC) { - if (ifmgd->powersave) - sdata->smps_mode = IEEE80211_SMPS_DYNAMIC; - else - sdata->smps_mode = IEEE80211_SMPS_OFF; - } else - sdata->smps_mode = ifmgd->req_smps; - assoc_data->capability = req->bss->capability; assoc_data->supp_rates = bss->supp_rates; assoc_data->supp_rates_len = bss->supp_rates_len; @@ -5770,6 +5729,15 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, if (err) goto err_clear; + if (ifmgd->req_smps == IEEE80211_SMPS_AUTOMATIC) { + if (ifmgd->powersave) + sdata->smps_mode = IEEE80211_SMPS_DYNAMIC; + else + sdata->smps_mode = IEEE80211_SMPS_OFF; + } else { + sdata->smps_mode = ifmgd->req_smps; + } + rcu_read_lock(); beacon_ies = rcu_dereference(req->bss->beacon_ies); @@ -5854,6 +5822,9 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; bool tx = !req->local_state_change; + struct ieee80211_prep_tx_info info = { + .subtype = IEEE80211_STYPE_DEAUTH, + }; if (ifmgd->auth_data && ether_addr_equal(ifmgd->auth_data->bss->bssid, req->bssid)) { @@ -5862,7 +5833,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, req->bssid, req->reason_code, ieee80211_get_reason_code_string(req->reason_code)); - drv_mgd_prepare_tx(sdata->local, sdata, 0); + drv_mgd_prepare_tx(sdata->local, sdata, &info); ieee80211_send_deauth_disassoc(sdata, req->bssid, req->bssid, IEEE80211_STYPE_DEAUTH, req->reason_code, tx, @@ -5871,7 +5842,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, req->reason_code, false); - + drv_mgd_complete_tx(sdata->local, sdata, &info); return 0; } @@ -5882,7 +5853,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, req->bssid, req->reason_code, ieee80211_get_reason_code_string(req->reason_code)); - drv_mgd_prepare_tx(sdata->local, sdata, 0); + drv_mgd_prepare_tx(sdata->local, sdata, &info); ieee80211_send_deauth_disassoc(sdata, req->bssid, req->bssid, IEEE80211_STYPE_DEAUTH, req->reason_code, tx, @@ -5906,6 +5877,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, req->reason_code, false); + drv_mgd_complete_tx(sdata->local, sdata, &info); return 0; } diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 63652c39c8e0..e5935e3d7a07 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -297,15 +297,11 @@ void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata) static bool rc_no_data_or_no_ack_use_min(struct ieee80211_tx_rate_control *txrc) { struct sk_buff *skb = txrc->skb; - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - __le16 fc; - - fc = hdr->frame_control; return (info->flags & (IEEE80211_TX_CTL_NO_ACK | IEEE80211_TX_CTL_USE_MINRATE)) || - !ieee80211_is_data(fc); + !ieee80211_is_tx_data(skb); } static void rc_send_low_basicrate(struct ieee80211_tx_rate *rate, @@ -396,6 +392,10 @@ static bool rate_control_send_low(struct ieee80211_sta *pubsta, int mcast_rate; bool use_basicrate = false; + if (ieee80211_is_tx_data(txrc->skb) && + info->flags & IEEE80211_TX_CTL_NO_ACK) + return false; + if (!pubsta || rc_no_data_or_no_ack_use_min(txrc)) { __rate_control_send_low(txrc->hw, sband, pubsta, info, txrc->rate_idx_mask); @@ -870,7 +870,6 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, int max_rates) { struct ieee80211_sub_if_data *sdata; - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_supported_band *sband; @@ -882,7 +881,7 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, sdata = vif_to_sdata(vif); sband = sdata->local->hw.wiphy->bands[info->band]; - if (ieee80211_is_data(hdr->frame_control)) + if (ieee80211_is_tx_data(skb)) rate_control_apply_mask(sdata, sta, sband, dest, max_rates); if (dest[0].idx < 0) diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index a6f3fb4a9197..72b44d4c42d0 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -434,7 +434,7 @@ minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate, unsigned int nsecs = 0, overhead = mi->overhead; unsigned int ampdu_len = 1; - /* do not account throughput if sucess prob is below 10% */ + /* do not account throughput if success prob is below 10% */ if (prob_avg < MINSTREL_FRAC(10, 100)) return 0; @@ -1175,29 +1175,6 @@ minstrel_downgrade_rate(struct minstrel_ht_sta *mi, u16 *idx, bool primary) } } -static void -minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb) -{ - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; - struct sta_info *sta = container_of(pubsta, struct sta_info, sta); - u16 tid; - - if (skb_get_queue_mapping(skb) == IEEE80211_AC_VO) - return; - - if (unlikely(!ieee80211_is_data_qos(hdr->frame_control))) - return; - - if (unlikely(skb->protocol == cpu_to_be16(ETH_P_PAE))) - return; - - tid = ieee80211_get_tid(hdr); - if (likely(sta->ampdu_mlme.tid_tx[tid])) - return; - - ieee80211_start_tx_ba_session(pubsta, tid, 0); -} - static void minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, void *priv_sta, struct ieee80211_tx_status *st) @@ -1211,6 +1188,10 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, bool last, update = false; int i; + /* Ignore packet that was sent with noAck flag */ + if (info->flags & IEEE80211_TX_CTL_NO_ACK) + return; + /* This packet was aggregated but doesn't carry status info */ if ((info->flags & IEEE80211_TX_CTL_AMPDU) && !(info->flags & IEEE80211_TX_STAT_AMPDU)) @@ -1498,10 +1479,6 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, struct minstrel_priv *mp = priv; u16 sample_idx; - if (!(info->flags & IEEE80211_TX_CTL_AMPDU) && - !minstrel_ht_is_legacy_group(MI_RATE_GROUP(mi->max_prob_rate))) - minstrel_aggr_check(sta, txrc->skb); - info->flags |= mi->tx_flags; #ifdef CONFIG_MAC80211_DEBUGFS @@ -1907,6 +1884,7 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta) static const struct rate_control_ops mac80211_minstrel_ht = { .name = "minstrel_ht", + .capa = RATE_CTRL_CAPA_AMPDU_TRIGGER, .tx_status_ext = minstrel_ht_tx_status, .get_rate = minstrel_ht_get_rate, .rate_init = minstrel_ht_rate_init, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index af0ef456eb0f..771921c057e8 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -214,6 +214,24 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, return len; } +static void __ieee80211_queue_skb_to_iface(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct sk_buff *skb) +{ + skb_queue_tail(&sdata->skb_queue, skb); + ieee80211_queue_work(&sdata->local->hw, &sdata->work); + if (sta) + sta->rx_stats.packets++; +} + +static void ieee80211_queue_skb_to_iface(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct sk_buff *skb) +{ + skb->protocol = 0; + __ieee80211_queue_skb_to_iface(sdata, sta, skb); +} + static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int rtap_space) @@ -254,8 +272,7 @@ static void ieee80211_handle_mu_mimo_mon(struct ieee80211_sub_if_data *sdata, if (!skb) return; - skb_queue_tail(&sdata->skb_queue, skb); - ieee80211_queue_work(&sdata->local->hw, &sdata->work); + ieee80211_queue_skb_to_iface(sdata, NULL, skb); } /* @@ -1339,7 +1356,6 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, struct sk_buff_head *frames) { struct sk_buff *skb = rx->skb; - struct ieee80211_local *local = rx->local; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct sta_info *sta = rx->sta; struct tid_ampdu_rx *tid_agg_rx; @@ -1391,8 +1407,7 @@ static void ieee80211_rx_reorder_ampdu(struct ieee80211_rx_data *rx, /* if this mpdu is fragmented - terminate rx aggregation session */ sc = le16_to_cpu(hdr->seq_ctrl); if (sc & IEEE80211_SCTL_FRAG) { - skb_queue_tail(&rx->sdata->skb_queue, skb); - ieee80211_queue_work(&local->hw, &rx->sdata->work); + ieee80211_queue_skb_to_iface(rx->sdata, NULL, skb); return; } @@ -1563,12 +1578,8 @@ static void sta_ps_start(struct sta_info *sta) for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) { struct ieee80211_txq *txq = sta->sta.txq[tid]; - struct txq_info *txqi = to_txq_info(txq); - spin_lock(&local->active_txq_lock[txq->ac]); - if (!list_empty(&txqi->schedule_order)) - list_del_init(&txqi->schedule_order); - spin_unlock(&local->active_txq_lock[txq->ac]); + ieee80211_unschedule_txq(&local->hw, txq, false); if (txq_has_queue(txq)) set_bit(tid, &sta->txq_buffered_tids); @@ -3009,11 +3020,8 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx) tf->category == WLAN_CATEGORY_TDLS && (tf->action_code == WLAN_TDLS_CHANNEL_SWITCH_REQUEST || tf->action_code == WLAN_TDLS_CHANNEL_SWITCH_RESPONSE)) { - skb_queue_tail(&local->skb_queue_tdls_chsw, rx->skb); - schedule_work(&local->tdls_chsw_work); - if (rx->sta) - rx->sta->rx_stats.packets++; - + rx->skb->protocol = cpu_to_be16(ETH_P_TDLS); + __ieee80211_queue_skb_to_iface(sdata, rx->sta, rx->skb); return RX_QUEUED; } } @@ -3493,10 +3501,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) return RX_QUEUED; queue: - skb_queue_tail(&sdata->skb_queue, rx->skb); - ieee80211_queue_work(&local->hw, &sdata->work); - if (rx->sta) - rx->sta->rx_stats.packets++; + ieee80211_queue_skb_to_iface(sdata, rx->sta, rx->skb); return RX_QUEUED; } @@ -3644,10 +3649,7 @@ ieee80211_rx_h_ext(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; /* for now only beacons are ext, so queue them */ - skb_queue_tail(&sdata->skb_queue, rx->skb); - ieee80211_queue_work(&rx->local->hw, &sdata->work); - if (rx->sta) - rx->sta->rx_stats.packets++; + ieee80211_queue_skb_to_iface(sdata, rx->sta, rx->skb); return RX_QUEUED; } @@ -3704,11 +3706,7 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; } - /* queue up frame and kick off work to process it */ - skb_queue_tail(&sdata->skb_queue, rx->skb); - ieee80211_queue_work(&rx->local->hw, &sdata->work); - if (rx->sta) - rx->sta->rx_stats.packets++; + ieee80211_queue_skb_to_iface(sdata, rx->sta, rx->skb); return RX_QUEUED; } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f2fb69da9b6e..a5505ee51229 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -425,15 +425,11 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, if (sta_prepare_rate_control(local, sta, gfp)) goto free_txq; - sta->airtime_weight = IEEE80211_DEFAULT_AIRTIME_WEIGHT; for (i = 0; i < IEEE80211_NUM_ACS; i++) { skb_queue_head_init(&sta->ps_tx_buf[i]); skb_queue_head_init(&sta->tx_filtered[i]); - sta->airtime[i].deficit = sta->airtime_weight; - atomic_set(&sta->airtime[i].aql_tx_pending, 0); - sta->airtime[i].aql_limit_low = local->aql_txq_limit_low[i]; - sta->airtime[i].aql_limit_high = local->aql_txq_limit_high[i]; + init_airtime_info(&sta->airtime[i], &local->airtime[i]); } for (i = 0; i < IEEE80211_NUM_TIDS; i++) @@ -1398,11 +1394,6 @@ static void ieee80211_send_null_response(struct sta_info *sta, int tid, struct ieee80211_tx_info *info; struct ieee80211_chanctx_conf *chanctx_conf; - /* Don't send NDPs when STA is connected HE */ - if (sdata->vif.type == NL80211_IFTYPE_STATION && - !(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE)) - return; - if (qos) { fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC | @@ -1897,24 +1888,59 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, } EXPORT_SYMBOL(ieee80211_sta_set_buffered); +void ieee80211_register_airtime(struct ieee80211_txq *txq, + u32 tx_airtime, u32 rx_airtime) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->vif); + struct ieee80211_local *local = sdata->local; + u64 weight_sum, weight_sum_reciprocal; + struct airtime_sched_info *air_sched; + struct airtime_info *air_info; + u32 airtime = 0; + + air_sched = &local->airtime[txq->ac]; + air_info = to_airtime_info(txq); + + if (local->airtime_flags & AIRTIME_USE_TX) + airtime += tx_airtime; + if (local->airtime_flags & AIRTIME_USE_RX) + airtime += rx_airtime; + + /* Weights scale so the unit weight is 256 */ + airtime <<= 8; + + spin_lock_bh(&air_sched->lock); + + air_info->tx_airtime += tx_airtime; + air_info->rx_airtime += rx_airtime; + + if (air_sched->weight_sum) { + weight_sum = air_sched->weight_sum; + weight_sum_reciprocal = air_sched->weight_sum_reciprocal; + } else { + weight_sum = air_info->weight; + weight_sum_reciprocal = air_info->weight_reciprocal; + } + + /* Round the calculation of global vt */ + air_sched->v_t += (u64)((airtime + (weight_sum >> 1)) * + weight_sum_reciprocal) >> IEEE80211_RECIPROCAL_SHIFT_64; + air_info->v_t += (u32)((airtime + (air_info->weight >> 1)) * + air_info->weight_reciprocal) >> IEEE80211_RECIPROCAL_SHIFT_32; + ieee80211_resort_txq(&local->hw, txq); + + spin_unlock_bh(&air_sched->lock); +} + void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, u32 tx_airtime, u32 rx_airtime) { - struct sta_info *sta = container_of(pubsta, struct sta_info, sta); - struct ieee80211_local *local = sta->sdata->local; - u8 ac = ieee80211_ac_from_tid(tid); - u32 airtime = 0; + struct ieee80211_txq *txq = pubsta->txq[tid]; - if (sta->local->airtime_flags & AIRTIME_USE_TX) - airtime += tx_airtime; - if (sta->local->airtime_flags & AIRTIME_USE_RX) - airtime += rx_airtime; + if (!txq) + return; - spin_lock_bh(&local->active_txq_lock[ac]); - sta->airtime[ac].tx_airtime += tx_airtime; - sta->airtime[ac].rx_airtime += rx_airtime; - sta->airtime[ac].deficit -= airtime; - spin_unlock_bh(&local->active_txq_lock[ac]); + ieee80211_register_airtime(txq, tx_airtime, rx_airtime); } EXPORT_SYMBOL(ieee80211_sta_register_airtime); @@ -2093,10 +2119,9 @@ static struct ieee80211_sta_rx_stats * sta_get_last_rx_stats(struct sta_info *sta) { struct ieee80211_sta_rx_stats *stats = &sta->rx_stats; - struct ieee80211_local *local = sta->local; int cpu; - if (!ieee80211_hw_check(&local->hw, USES_RSS)) + if (!sta->pcpu_rx_stats) return stats; for_each_possible_cpu(cpu) { @@ -2196,9 +2221,7 @@ static void sta_set_tidstats(struct sta_info *sta, int cpu; if (!(tidstats->filled & BIT(NL80211_TID_STATS_RX_MSDU))) { - if (!ieee80211_hw_check(&local->hw, USES_RSS)) - tidstats->rx_msdu += - sta_get_tidstats_msdu(&sta->rx_stats, tid); + tidstats->rx_msdu += sta_get_tidstats_msdu(&sta->rx_stats, tid); if (sta->pcpu_rx_stats) { for_each_possible_cpu(cpu) { @@ -2277,7 +2300,6 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, sinfo->rx_beacon = sdata->u.mgd.count_beacon_signal; drv_sta_statistics(local, sdata, &sta->sta, sinfo); - sinfo->filled |= BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME) | BIT_ULL(NL80211_STA_INFO_STA_FLAGS) | BIT_ULL(NL80211_STA_INFO_BSS_PARAM) | @@ -2312,8 +2334,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, if (!(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_RX_BYTES64) | BIT_ULL(NL80211_STA_INFO_RX_BYTES)))) { - if (!ieee80211_hw_check(&local->hw, USES_RSS)) - sinfo->rx_bytes += sta_get_stats_bytes(&sta->rx_stats); + sinfo->rx_bytes += sta_get_stats_bytes(&sta->rx_stats); if (sta->pcpu_rx_stats) { for_each_possible_cpu(cpu) { @@ -2363,7 +2384,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT))) { - sinfo->airtime_weight = sta->airtime_weight; + sinfo->airtime_weight = sta->airtime[0].weight; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT); } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 0333072ebd98..ba2796782008 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -135,18 +135,25 @@ enum ieee80211_agg_stop_reason { #define AIRTIME_USE_TX BIT(0) #define AIRTIME_USE_RX BIT(1) + struct airtime_info { u64 rx_airtime; u64 tx_airtime; - s64 deficit; + u64 v_t; + u64 last_scheduled; + struct list_head list; atomic_t aql_tx_pending; /* Estimated airtime for frames pending */ u32 aql_limit_low; u32 aql_limit_high; + u32 weight_reciprocal; + u16 weight; }; void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local, struct sta_info *sta, u8 ac, u16 tx_airtime, bool tx_completed); +void ieee80211_register_airtime(struct ieee80211_txq *txq, + u32 tx_airtime, u32 rx_airtime); struct sta_info; @@ -515,7 +522,6 @@ struct ieee80211_fragment_cache { * @tid_seq: per-TID sequence numbers for sending to this STA * @airtime: per-AC struct airtime_info describing airtime statistics for this * station - * @airtime_weight: station weight for airtime fairness calculation purposes * @ampdu_mlme: A-MPDU state machine state * @mesh: mesh STA information * @debugfs_dir: debug filesystem directory dentry @@ -646,7 +652,6 @@ struct sta_info { u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; struct airtime_info airtime[IEEE80211_NUM_ACS]; - u16 airtime_weight; /* * Aggregation information, locked with lock. diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 9baf185ee4c7..bae321ff77f6 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -970,6 +970,25 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, if (!(info->flags & IEEE80211_TX_CTL_INJECTED) && acked) ieee80211_frame_acked(sta, skb); + } else if (wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) { + struct ieee80211_sub_if_data *sdata; + struct ieee80211_txq *txq; + u32 airtime; + + /* Account airtime to multicast queue */ + sdata = ieee80211_sdata_from_skb(local, skb); + + if (sdata && (txq = sdata->vif.txq)) { + airtime = info->status.tx_time ?: + ieee80211_calc_expected_tx_airtime(hw, + &sdata->vif, + NULL, + skb->len, + false); + + ieee80211_register_airtime(txq, airtime, 0); + } } /* SNMP counters @@ -1006,12 +1025,11 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS) && !(info->flags & IEEE80211_TX_CTL_INJECTED) && local->ps_sdata && !(local->scanning)) { - if (info->flags & IEEE80211_TX_STAT_ACK) { + if (info->flags & IEEE80211_TX_STAT_ACK) local->ps_sdata->u.mgd.flags |= IEEE80211_STA_NULLFUNC_ACKED; - } else - mod_timer(&local->dynamic_ps_timer, jiffies + - msecs_to_jiffies(10)); + mod_timer(&local->dynamic_ps_timer, + jiffies + msecs_to_jiffies(10)); } ieee80211_report_used_skb(local, skb, false); diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index f91d02b81b92..45e532ad1215 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -1920,7 +1920,7 @@ out: return ret; } -static void +void ieee80211_process_tdls_channel_switch(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { @@ -1971,32 +1971,6 @@ void ieee80211_teardown_tdls_peers(struct ieee80211_sub_if_data *sdata) rcu_read_unlock(); } -void ieee80211_tdls_chsw_work(struct work_struct *wk) -{ - struct ieee80211_local *local = - container_of(wk, struct ieee80211_local, tdls_chsw_work); - struct ieee80211_sub_if_data *sdata; - struct sk_buff *skb; - struct ieee80211_tdls_data *tf; - - wiphy_lock(local->hw.wiphy); - while ((skb = skb_dequeue(&local->skb_queue_tdls_chsw))) { - tf = (struct ieee80211_tdls_data *)skb->data; - list_for_each_entry(sdata, &local->interfaces, list) { - if (!ieee80211_sdata_running(sdata) || - sdata->vif.type != NL80211_IFTYPE_STATION || - !ether_addr_equal(tf->da, sdata->vif.addr)) - continue; - - ieee80211_process_tdls_channel_switch(sdata, skb); - break; - } - - kfree_skb(skb); - } - wiphy_unlock(local->hw.wiphy); -} - void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata, const u8 *peer, u16 reason) { diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index 8fcc39056402..f6ef15366938 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -2,7 +2,7 @@ /* * Portions of this file * Copyright(c) 2016-2017 Intel Deutschland GmbH -* Copyright (C) 2018 - 2020 Intel Corporation +* Copyright (C) 2018 - 2021 Intel Corporation */ #if !defined(__MAC80211_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ) @@ -1461,31 +1461,52 @@ DEFINE_EVENT(release_evt, drv_allow_buffered_frames, TP_ARGS(local, sta, tids, num_frames, reason, more_data) ); -TRACE_EVENT(drv_mgd_prepare_tx, +DECLARE_EVENT_CLASS(mgd_prepare_complete_tx_evt, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, - u16 duration), + u16 duration, u16 subtype, bool success), - TP_ARGS(local, sdata, duration), + TP_ARGS(local, sdata, duration, subtype, success), TP_STRUCT__entry( LOCAL_ENTRY VIF_ENTRY __field(u32, duration) + __field(u16, subtype) + __field(u8, success) ), TP_fast_assign( LOCAL_ASSIGN; VIF_ASSIGN; __entry->duration = duration; + __entry->subtype = subtype; + __entry->success = success; ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT " duration: %u", - LOCAL_PR_ARG, VIF_PR_ARG, __entry->duration + LOCAL_PR_FMT VIF_PR_FMT " duration: %u, subtype:0x%x, success:%d", + LOCAL_PR_ARG, VIF_PR_ARG, __entry->duration, + __entry->subtype, __entry->success ) ); +DEFINE_EVENT(mgd_prepare_complete_tx_evt, drv_mgd_prepare_tx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + u16 duration, u16 subtype, bool success), + + TP_ARGS(local, sdata, duration, subtype, success) +); + +DEFINE_EVENT(mgd_prepare_complete_tx_evt, drv_mgd_complete_tx, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + u16 duration, u16 subtype, bool success), + + TP_ARGS(local, sdata, duration, subtype, success) +); + DEFINE_EVENT(local_sdata_evt, drv_mgd_protect_tdls_discover, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata), diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 2651498d05e8..e96981144358 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -666,6 +667,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) u32 len; struct ieee80211_tx_rate_control txrc; struct ieee80211_sta_rates *ratetbl = NULL; + bool encap = info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP; bool assoc = false; memset(&txrc, 0, sizeof(txrc)); @@ -707,7 +709,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) * just wants a probe response. */ if (tx->sdata->vif.bss_conf.use_short_preamble && - (ieee80211_is_data(hdr->frame_control) || + (ieee80211_is_tx_data(tx->skb) || (tx->sta && test_sta_flag(tx->sta, WLAN_STA_SHORT_PREAMBLE)))) txrc.short_preamble = true; @@ -729,7 +731,8 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) "%s: Dropped data frame as no usable bitrate found while " "scanning and associated. Target station: " "%pM on %d GHz band\n", - tx->sdata->name, hdr->addr1, + tx->sdata->name, + encap ? ((struct ethhdr *)hdr)->h_dest : hdr->addr1, info->band ? 5 : 2)) return TX_DROP; @@ -763,7 +766,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) if (txrc.reported_rate.idx < 0) { txrc.reported_rate = tx->rate; - if (tx->sta && ieee80211_is_data(hdr->frame_control)) + if (tx->sta && ieee80211_is_tx_data(tx->skb)) tx->sta->tx_stats.last_rate = txrc.reported_rate; } else if (tx->sta) tx->sta->tx_stats.last_rate = txrc.reported_rate; @@ -1447,7 +1450,7 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, codel_vars_init(&txqi->def_cvars); codel_stats_init(&txqi->cstats); __skb_queue_head_init(&txqi->frags); - INIT_LIST_HEAD(&txqi->schedule_order); + RB_CLEAR_NODE(&txqi->schedule_order); txqi->txq.vif = &sdata->vif; @@ -1491,9 +1494,7 @@ void ieee80211_txq_purge(struct ieee80211_local *local, ieee80211_purge_tx_queue(&local->hw, &txqi->frags); spin_unlock_bh(&fq->lock); - spin_lock_bh(&local->active_txq_lock[txqi->txq.ac]); - list_del_init(&txqi->schedule_order); - spin_unlock_bh(&local->active_txq_lock[txqi->txq.ac]); + ieee80211_unschedule_txq(&local->hw, &txqi->txq, true); } void ieee80211_txq_set_params(struct ieee80211_local *local) @@ -1768,8 +1769,6 @@ static int invoke_tx_handlers_early(struct ieee80211_tx_data *tx) CALL_TXH(ieee80211_tx_h_ps_buf); CALL_TXH(ieee80211_tx_h_check_control_port_protocol); CALL_TXH(ieee80211_tx_h_select_key); - if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL)) - CALL_TXH(ieee80211_tx_h_rate_ctrl); txh_done: if (unlikely(res == TX_DROP)) { @@ -1802,6 +1801,9 @@ static int invoke_tx_handlers_late(struct ieee80211_tx_data *tx) goto txh_done; } + if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL)) + CALL_TXH(ieee80211_tx_h_rate_ctrl); + CALL_TXH(ieee80211_tx_h_michael_mic_add); CALL_TXH(ieee80211_tx_h_sequence); CALL_TXH(ieee80211_tx_h_fragment); @@ -3284,6 +3286,9 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (!ieee80211_hw_check(&local->hw, TX_AMSDU)) return false; + if (sdata->vif.offload_flags & IEEE80211_OFFLOAD_ENCAP_ENABLED) + return false; + if (skb_is_gso(skb)) return false; @@ -3389,15 +3394,21 @@ out: * Can be called while the sta lock is held. Anything that can cause packets to * be generated will cause deadlock! */ -static void ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata, - struct sta_info *sta, u8 pn_offs, - struct ieee80211_key *key, - struct sk_buff *skb) +static ieee80211_tx_result +ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, u8 pn_offs, + struct ieee80211_key *key, + struct ieee80211_tx_data *tx) { + struct sk_buff *skb = tx->skb; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (void *)skb->data; u8 tid = IEEE80211_NUM_TIDS; + if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL) && + ieee80211_tx_h_rate_ctrl(tx) != TX_CONTINUE) + return TX_DROP; + if (key) info->control.hw_key = &key->conf; @@ -3446,6 +3457,8 @@ static void ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata, break; } } + + return TX_CONTINUE; } static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, @@ -3549,24 +3562,17 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, tx.sta = sta; tx.key = fast_tx->key; - if (!ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) { - tx.skb = skb; - r = ieee80211_tx_h_rate_ctrl(&tx); - skb = tx.skb; - tx.skb = NULL; - - if (r != TX_CONTINUE) { - if (r != TX_QUEUED) - kfree_skb(skb); - return true; - } - } - if (ieee80211_queue_skb(local, sdata, sta, skb)) return true; - ieee80211_xmit_fast_finish(sdata, sta, fast_tx->pn_offs, - fast_tx->key, skb); + tx.skb = skb; + r = ieee80211_xmit_fast_finish(sdata, sta, fast_tx->pn_offs, + fast_tx->key, &tx); + tx.skb = NULL; + if (r == TX_DROP) { + kfree_skb(skb); + return true; + } if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) sdata = container_of(sdata->bss, @@ -3671,8 +3677,16 @@ begin: else info->flags &= ~IEEE80211_TX_CTL_AMPDU; - if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) + if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) { + if (!ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) { + r = ieee80211_tx_h_rate_ctrl(&tx); + if (r != TX_CONTINUE) { + ieee80211_free_txskb(&local->hw, skb); + goto begin; + } + } goto encap_out; + } if (info->control.flags & IEEE80211_TX_CTRL_FAST_XMIT) { struct sta_info *sta = container_of(txq->sta, struct sta_info, @@ -3683,8 +3697,12 @@ begin: (tx.key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) pn_offs = ieee80211_hdrlen(hdr->frame_control); - ieee80211_xmit_fast_finish(sta->sdata, sta, pn_offs, - tx.key, skb); + r = ieee80211_xmit_fast_finish(sta->sdata, sta, pn_offs, + tx.key, &tx); + if (r != TX_CONTINUE) { + ieee80211_free_txskb(&local->hw, skb); + goto begin; + } } else { if (invoke_tx_handlers_late(&tx)) goto begin; @@ -3764,102 +3782,259 @@ EXPORT_SYMBOL(ieee80211_tx_dequeue); struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac) { struct ieee80211_local *local = hw_to_local(hw); + struct airtime_sched_info *air_sched; + u64 now = ktime_get_boottime_ns(); struct ieee80211_txq *ret = NULL; - struct txq_info *txqi = NULL, *head = NULL; - bool found_eligible_txq = false; + struct airtime_info *air_info; + struct txq_info *txqi = NULL; + struct rb_node *node; + bool first = false; - spin_lock_bh(&local->active_txq_lock[ac]); + air_sched = &local->airtime[ac]; + spin_lock_bh(&air_sched->lock); - begin: - txqi = list_first_entry_or_null(&local->active_txqs[ac], - struct txq_info, - schedule_order); - if (!txqi) - goto out; + node = air_sched->schedule_pos; - if (txqi == head) { - if (!found_eligible_txq) - goto out; - else - found_eligible_txq = false; +begin: + if (!node) { + node = rb_first_cached(&air_sched->active_txqs); + first = true; + } else { + node = rb_next(node); } - if (!head) - head = txqi; - - if (txqi->txq.sta) { - struct sta_info *sta = container_of(txqi->txq.sta, - struct sta_info, sta); - bool aql_check = ieee80211_txq_airtime_check(hw, &txqi->txq); - s64 deficit = sta->airtime[txqi->txq.ac].deficit; - - if (aql_check) - found_eligible_txq = true; - - if (deficit < 0) - sta->airtime[txqi->txq.ac].deficit += - sta->airtime_weight; - - if (deficit < 0 || !aql_check) { - list_move_tail(&txqi->schedule_order, - &local->active_txqs[txqi->txq.ac]); - goto begin; - } - } - - - if (txqi->schedule_round == local->schedule_round[ac]) + if (!node) goto out; - list_del_init(&txqi->schedule_order); - txqi->schedule_round = local->schedule_round[ac]; + txqi = container_of(node, struct txq_info, schedule_order); + air_info = to_airtime_info(&txqi->txq); + + if (air_info->v_t > air_sched->v_t && + (!first || !airtime_catchup_v_t(air_sched, air_info->v_t, now))) + goto out; + + if (!ieee80211_txq_airtime_check(hw, &txqi->txq)) { + first = false; + goto begin; + } + + air_sched->schedule_pos = node; + air_sched->last_schedule_activity = now; ret = &txqi->txq; - out: - spin_unlock_bh(&local->active_txq_lock[ac]); + spin_unlock_bh(&air_sched->lock); return ret; } EXPORT_SYMBOL(ieee80211_next_txq); -void __ieee80211_schedule_txq(struct ieee80211_hw *hw, +static void __ieee80211_insert_txq(struct rb_root_cached *root, + struct txq_info *txqi) +{ + struct rb_node **new = &root->rb_root.rb_node; + struct airtime_info *old_air, *new_air; + struct rb_node *parent = NULL; + struct txq_info *__txqi; + bool leftmost = true; + + while (*new) { + parent = *new; + __txqi = rb_entry(parent, struct txq_info, schedule_order); + old_air = to_airtime_info(&__txqi->txq); + new_air = to_airtime_info(&txqi->txq); + + if (new_air->v_t <= old_air->v_t) { + new = &parent->rb_left; + } else { + new = &parent->rb_right; + leftmost = false; + } + } + + rb_link_node(&txqi->schedule_order, parent, new); + rb_insert_color_cached(&txqi->schedule_order, root, leftmost); +} + +void ieee80211_resort_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct airtime_info *air_info = to_airtime_info(txq); + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = to_txq_info(txq); + struct airtime_sched_info *air_sched; + + air_sched = &local->airtime[txq->ac]; + + lockdep_assert_held(&air_sched->lock); + + if (!RB_EMPTY_NODE(&txqi->schedule_order)) { + struct airtime_info *a_prev = NULL, *a_next = NULL; + struct txq_info *t_prev, *t_next; + struct rb_node *n_prev, *n_next; + + /* Erasing a node can cause an expensive rebalancing operation, + * so we check the previous and next nodes first and only remove + * and re-insert if the current node is not already in the + * correct position. + */ + if ((n_prev = rb_prev(&txqi->schedule_order)) != NULL) { + t_prev = container_of(n_prev, struct txq_info, + schedule_order); + a_prev = to_airtime_info(&t_prev->txq); + } + + if ((n_next = rb_next(&txqi->schedule_order)) != NULL) { + t_next = container_of(n_next, struct txq_info, + schedule_order); + a_next = to_airtime_info(&t_next->txq); + } + + if ((!a_prev || a_prev->v_t <= air_info->v_t) && + (!a_next || a_next->v_t > air_info->v_t)) + return; + + if (air_sched->schedule_pos == &txqi->schedule_order) + air_sched->schedule_pos = n_prev; + + rb_erase_cached(&txqi->schedule_order, + &air_sched->active_txqs); + RB_CLEAR_NODE(&txqi->schedule_order); + __ieee80211_insert_txq(&air_sched->active_txqs, txqi); + } +} + +void ieee80211_update_airtime_weight(struct ieee80211_local *local, + struct airtime_sched_info *air_sched, + u64 now, bool force) +{ + struct airtime_info *air_info, *tmp; + u64 weight_sum = 0; + + if (unlikely(!now)) + now = ktime_get_boottime_ns(); + + lockdep_assert_held(&air_sched->lock); + + if (!force && (air_sched->last_weight_update < + now - AIRTIME_ACTIVE_DURATION)) + return; + + list_for_each_entry_safe(air_info, tmp, + &air_sched->active_list, list) { + if (airtime_is_active(air_info, now)) + weight_sum += air_info->weight; + else + list_del_init(&air_info->list); + } + airtime_weight_sum_set(air_sched, weight_sum); + air_sched->last_weight_update = now; +} + +void ieee80211_schedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) + __acquires(txq_lock) __releases(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = to_txq_info(txq); + struct airtime_sched_info *air_sched; + u64 now = ktime_get_boottime_ns(); + struct airtime_info *air_info; + u8 ac = txq->ac; + bool was_active; + + air_sched = &local->airtime[ac]; + air_info = to_airtime_info(txq); + + spin_lock_bh(&air_sched->lock); + was_active = airtime_is_active(air_info, now); + airtime_set_active(air_sched, air_info, now); + + if (!RB_EMPTY_NODE(&txqi->schedule_order)) + goto out; + + /* If the station has been inactive for a while, catch up its v_t so it + * doesn't get indefinite priority; see comment above the definition of + * AIRTIME_MAX_BEHIND. + */ + if ((!was_active && air_info->v_t < air_sched->v_t) || + air_info->v_t < air_sched->v_t - AIRTIME_MAX_BEHIND) + air_info->v_t = air_sched->v_t; + + ieee80211_update_airtime_weight(local, air_sched, now, !was_active); + __ieee80211_insert_txq(&air_sched->active_txqs, txqi); + +out: + spin_unlock_bh(&air_sched->lock); +} +EXPORT_SYMBOL(ieee80211_schedule_txq); + +static void __ieee80211_unschedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq, + bool purge) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = to_txq_info(txq); + struct airtime_sched_info *air_sched; + struct airtime_info *air_info; + + air_sched = &local->airtime[txq->ac]; + air_info = to_airtime_info(&txqi->txq); + + lockdep_assert_held(&air_sched->lock); + + if (purge) { + list_del_init(&air_info->list); + ieee80211_update_airtime_weight(local, air_sched, 0, true); + } + + if (RB_EMPTY_NODE(&txqi->schedule_order)) + return; + + if (air_sched->schedule_pos == &txqi->schedule_order) + air_sched->schedule_pos = rb_prev(&txqi->schedule_order); + + if (!purge) + airtime_set_active(air_sched, air_info, + ktime_get_boottime_ns()); + + rb_erase_cached(&txqi->schedule_order, + &air_sched->active_txqs); + RB_CLEAR_NODE(&txqi->schedule_order); +} + +void ieee80211_unschedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, - bool force) + bool purge) + __acquires(txq_lock) __releases(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + + spin_lock_bh(&local->airtime[txq->ac].lock); + __ieee80211_unschedule_txq(hw, txq, purge); + spin_unlock_bh(&local->airtime[txq->ac].lock); +} + +void ieee80211_return_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq, bool force) { struct ieee80211_local *local = hw_to_local(hw); struct txq_info *txqi = to_txq_info(txq); - spin_lock_bh(&local->active_txq_lock[txq->ac]); + spin_lock_bh(&local->airtime[txq->ac].lock); - if (list_empty(&txqi->schedule_order) && - (force || !skb_queue_empty(&txqi->frags) || - txqi->tin.backlog_packets)) { - /* If airtime accounting is active, always enqueue STAs at the - * head of the list to ensure that they only get moved to the - * back by the airtime DRR scheduler once they have a negative - * deficit. A station that already has a negative deficit will - * get immediately moved to the back of the list on the next - * call to ieee80211_next_txq(). - */ - if (txqi->txq.sta && local->airtime_flags && - wiphy_ext_feature_isset(local->hw.wiphy, - NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) - list_add(&txqi->schedule_order, - &local->active_txqs[txq->ac]); - else - list_add_tail(&txqi->schedule_order, - &local->active_txqs[txq->ac]); - } + if (!RB_EMPTY_NODE(&txqi->schedule_order) && !force && + !txq_has_queue(txq)) + __ieee80211_unschedule_txq(hw, txq, false); - spin_unlock_bh(&local->active_txq_lock[txq->ac]); + spin_unlock_bh(&local->airtime[txq->ac].lock); } -EXPORT_SYMBOL(__ieee80211_schedule_txq); +EXPORT_SYMBOL(ieee80211_return_txq); DEFINE_STATIC_KEY_FALSE(aql_disable); bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, struct ieee80211_txq *txq) { - struct sta_info *sta; + struct airtime_info *air_info = to_airtime_info(txq); struct ieee80211_local *local = hw_to_local(hw); if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) @@ -3874,15 +4049,12 @@ bool ieee80211_txq_airtime_check(struct ieee80211_hw *hw, if (unlikely(txq->tid == IEEE80211_NUM_TIDS)) return true; - sta = container_of(txq->sta, struct sta_info, sta); - if (atomic_read(&sta->airtime[txq->ac].aql_tx_pending) < - sta->airtime[txq->ac].aql_limit_low) + if (atomic_read(&air_info->aql_tx_pending) < air_info->aql_limit_low) return true; if (atomic_read(&local->aql_total_pending_airtime) < local->aql_threshold && - atomic_read(&sta->airtime[txq->ac].aql_tx_pending) < - sta->airtime[txq->ac].aql_limit_high) + atomic_read(&air_info->aql_tx_pending) < air_info->aql_limit_high) return true; return false; @@ -3892,63 +4064,85 @@ EXPORT_SYMBOL(ieee80211_txq_airtime_check); bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq) { + struct txq_info *first_txqi = NULL, *txqi = to_txq_info(txq); struct ieee80211_local *local = hw_to_local(hw); - struct txq_info *iter, *tmp, *txqi = to_txq_info(txq); - struct sta_info *sta; - u8 ac = txq->ac; + struct airtime_sched_info *air_sched; + struct airtime_info *air_info; + struct rb_node *node = NULL; + bool ret = false; + u64 now; - spin_lock_bh(&local->active_txq_lock[ac]); - if (!txqi->txq.sta) + if (!ieee80211_txq_airtime_check(hw, txq)) + return false; + + air_sched = &local->airtime[txq->ac]; + spin_lock_bh(&air_sched->lock); + + if (RB_EMPTY_NODE(&txqi->schedule_order)) goto out; - if (list_empty(&txqi->schedule_order)) - goto out; + now = ktime_get_boottime_ns(); - list_for_each_entry_safe(iter, tmp, &local->active_txqs[ac], - schedule_order) { - if (iter == txqi) - break; + /* Like in ieee80211_next_txq(), make sure the first station in the + * scheduling order is eligible for transmission to avoid starvation. + */ + node = rb_first_cached(&air_sched->active_txqs); + if (node) { + first_txqi = container_of(node, struct txq_info, + schedule_order); + air_info = to_airtime_info(&first_txqi->txq); - if (!iter->txq.sta) { - list_move_tail(&iter->schedule_order, - &local->active_txqs[ac]); - continue; - } - sta = container_of(iter->txq.sta, struct sta_info, sta); - if (sta->airtime[ac].deficit < 0) - sta->airtime[ac].deficit += sta->airtime_weight; - list_move_tail(&iter->schedule_order, &local->active_txqs[ac]); + if (air_sched->v_t < air_info->v_t) + airtime_catchup_v_t(air_sched, air_info->v_t, now); } - sta = container_of(txqi->txq.sta, struct sta_info, sta); - if (sta->airtime[ac].deficit >= 0) - goto out; + air_info = to_airtime_info(&txqi->txq); + if (air_info->v_t <= air_sched->v_t) { + air_sched->last_schedule_activity = now; + ret = true; + } - sta->airtime[ac].deficit += sta->airtime_weight; - list_move_tail(&txqi->schedule_order, &local->active_txqs[ac]); - spin_unlock_bh(&local->active_txq_lock[ac]); - - return false; out: - if (!list_empty(&txqi->schedule_order)) - list_del_init(&txqi->schedule_order); - spin_unlock_bh(&local->active_txq_lock[ac]); - - return true; + spin_unlock_bh(&air_sched->lock); + return ret; } EXPORT_SYMBOL(ieee80211_txq_may_transmit); void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) { struct ieee80211_local *local = hw_to_local(hw); + struct airtime_sched_info *air_sched = &local->airtime[ac]; - spin_lock_bh(&local->active_txq_lock[ac]); - local->schedule_round[ac]++; - spin_unlock_bh(&local->active_txq_lock[ac]); + spin_lock_bh(&air_sched->lock); + air_sched->schedule_pos = NULL; + spin_unlock_bh(&air_sched->lock); } EXPORT_SYMBOL(ieee80211_txq_schedule_start); +static void +ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata, + struct sta_info *sta, + struct sk_buff *skb) +{ + struct rate_control_ref *ref = sdata->local->rate_ctrl; + u16 tid; + + if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER)) + return; + + if (!sta || !sta->sta.ht_cap.ht_supported || + !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO || + skb->protocol == sdata->control_port_protocol) + return; + + tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; + if (likely(sta->ampdu_mlme.tid_tx[tid])) + return; + + ieee80211_start_tx_ba_session(&sta->sta, tid, 0); +} + void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 info_flags, @@ -3979,6 +4173,8 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, skb_get_hash(skb); } + ieee80211_aggr_check(sdata, sta, skb); + if (sta) { struct ieee80211_fast_tx *fast_tx; @@ -4242,6 +4438,8 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, memset(info, 0, sizeof(*info)); + ieee80211_aggr_check(sdata, sta, skb); + tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]); if (tid_tx) { diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 060059ef9668..05e96212b104 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -6,7 +6,7 @@ * Copyright 2007 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation * * utilities for mac80211 */ @@ -1693,7 +1693,10 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, if (auth_alg == WLAN_AUTH_SHARED_KEY && transaction == 3) { mgmt->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); err = ieee80211_wep_encrypt(local, skb, key, key_len, key_idx); - WARN_ON(err); + if (WARN_ON(err)) { + kfree_skb(skb); + return; + } } IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | @@ -1934,13 +1937,26 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_sub_if_data *sdata, *offset = noffset; } - he_cap = ieee80211_get_he_sta_cap(sband); - if (he_cap) { + he_cap = ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); + if (he_cap && + cfg80211_any_usable_channels(local->hw.wiphy, BIT(sband->band), + IEEE80211_CHAN_NO_HE)) { pos = ieee80211_ie_build_he_cap(pos, he_cap, end); if (!pos) goto out_err; + } - if (sband->band == NL80211_BAND_6GHZ) { + if (cfg80211_any_usable_channels(local->hw.wiphy, + BIT(NL80211_BAND_6GHZ), + IEEE80211_CHAN_NO_HE)) { + struct ieee80211_supported_band *sband6; + + sband6 = local->hw.wiphy->bands[NL80211_BAND_6GHZ]; + he_cap = ieee80211_get_he_iftype_cap(sband6, + ieee80211_vif_type_p2p(&sdata->vif)); + + if (he_cap) { enum nl80211_iftype iftype = ieee80211_vif_type_p2p(&sdata->vif); __le16 cap = ieee80211_get_he_6ghz_capa(sband, iftype); @@ -2944,12 +2960,15 @@ void ieee80211_ie_build_he_6ghz_cap(struct ieee80211_sub_if_data *sdata, u8 *pos; u16 cap; - sband = ieee80211_get_sband(sdata); - if (!sband) + if (!cfg80211_any_usable_channels(sdata->local->hw.wiphy, + BIT(NL80211_BAND_6GHZ), + IEEE80211_CHAN_NO_HE)) return; + sband = sdata->local->hw.wiphy->bands[NL80211_BAND_6GHZ]; + iftd = ieee80211_get_sband_iftype_data(sband, iftype); - if (WARN_ON(!iftd)) + if (!iftd) return; /* Check for device HE 6 GHz capability before adding element */ diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 96ba616f59bf..7d738bd06f2c 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -4,7 +4,9 @@ * Copyright (c) 2019, Tessares SA. */ +#ifdef CONFIG_SYSCTL #include +#endif #include #include @@ -15,10 +17,14 @@ static int mptcp_pernet_id; struct mptcp_pernet { +#ifdef CONFIG_SYSCTL struct ctl_table_header *ctl_table_hdr; +#endif - int mptcp_enabled; + u8 mptcp_enabled; unsigned int add_addr_timeout; + u8 checksum_enabled; + u8 allow_join_initial_addr_port; }; static struct mptcp_pernet *mptcp_get_pernet(struct net *net) @@ -36,15 +42,36 @@ unsigned int mptcp_get_add_addr_timeout(struct net *net) return mptcp_get_pernet(net)->add_addr_timeout; } +int mptcp_is_checksum_enabled(struct net *net) +{ + return mptcp_get_pernet(net)->checksum_enabled; +} + +int mptcp_allow_join_id0(struct net *net) +{ + return mptcp_get_pernet(net)->allow_join_initial_addr_port; +} + +static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) +{ + pernet->mptcp_enabled = 1; + pernet->add_addr_timeout = TCP_RTO_MAX; + pernet->checksum_enabled = 0; + pernet->allow_join_initial_addr_port = 1; +} + +#ifdef CONFIG_SYSCTL static struct ctl_table mptcp_sysctl_table[] = { { .procname = "enabled", - .maxlen = sizeof(int), + .maxlen = sizeof(u8), .mode = 0644, /* users with CAP_NET_ADMIN or root (not and) can change this * value, same as other sysctl or the 'net' tree. */ - .proc_handler = proc_dointvec, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "add_addr_timeout", @@ -52,15 +79,25 @@ static struct ctl_table mptcp_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "checksum_enabled", + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, + { + .procname = "allow_join_initial_addr_port", + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, {} }; -static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) -{ - pernet->mptcp_enabled = 1; - pernet->add_addr_timeout = TCP_RTO_MAX; -} - static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) { struct ctl_table_header *hdr; @@ -75,6 +112,8 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) table[0].data = &pernet->mptcp_enabled; table[1].data = &pernet->add_addr_timeout; + table[2].data = &pernet->checksum_enabled; + table[3].data = &pernet->allow_join_initial_addr_port; hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table); if (!hdr) @@ -100,6 +139,17 @@ static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) kfree(table); } +#else + +static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) +{ + return 0; +} + +static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) {} + +#endif /* CONFIG_SYSCTL */ + static int __net_init mptcp_net_init(struct net *net) { struct mptcp_pernet *pernet = mptcp_get_pernet(net); diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index eb2dc6dbe212..52ea2517e856 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -25,6 +25,8 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH), SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX), + SNMP_MIB_ITEM("DSSNoMatchTCP", MPTCP_MIB_DSSTCPMISMATCH), + SNMP_MIB_ITEM("DataCsumErr", MPTCP_MIB_DATACSUMERR), SNMP_MIB_ITEM("OFOQueueTail", MPTCP_MIB_OFOQUEUETAIL), SNMP_MIB_ITEM("OFOQueue", MPTCP_MIB_OFOQUEUE), SNMP_MIB_ITEM("OFOMerge", MPTCP_MIB_OFOMERGE), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index f0da4f060fe1..193466c9b549 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -18,6 +18,8 @@ enum linux_mptcp_mib_field { MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ MPTCP_MIB_DSSNOMATCH, /* Received a new mapping that did not match the previous one */ MPTCP_MIB_INFINITEMAPRX, /* Received an infinite mapping */ + MPTCP_MIB_DSSTCPMISMATCH, /* DSS-mapping did not map with TCP's sequence numbers */ + MPTCP_MIB_DATACSUMERR, /* The data checksum fail */ MPTCP_MIB_OFOQUEUETAIL, /* Segments inserted into OoO queue tail */ MPTCP_MIB_OFOQUEUE, /* Segments inserted into OoO queue */ MPTCP_MIB_OFOMERGE, /* Segments merged in OoO queue */ diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index f16d9b5ee978..8f88ddeab6a2 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -144,6 +144,7 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, info->mptcpi_write_seq = READ_ONCE(msk->write_seq); info->mptcpi_snd_una = READ_ONCE(msk->snd_una); info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq); + info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); unlock_sock_fast(sk, slow); } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 9b263f27ce9b..b5850afea343 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -44,7 +44,20 @@ static void mptcp_parse_option(const struct sk_buff *skb, else expected_opsize = TCPOLEN_MPTCP_MPC_SYN; } - if (opsize != expected_opsize) + + /* Cfr RFC 8684 Section 3.3.0: + * If a checksum is present but its use had + * not been negotiated in the MP_CAPABLE handshake, the receiver MUST + * close the subflow with a RST, as it is not behaving as negotiated. + * If a checksum is not present when its use has been negotiated, the + * receiver MUST close the subflow with a RST, as it is considered + * broken + * We parse even option with mismatching csum presence, so that + * later in subflow_data_ready we can trigger the reset. + */ + if (opsize != expected_opsize && + (expected_opsize != TCPOLEN_MPTCP_MPC_ACK_DATA || + opsize != TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM)) break; /* try to be gentle vs future versions on the initial syn */ @@ -66,16 +79,12 @@ static void mptcp_parse_option(const struct sk_buff *skb, * host requires the use of checksums, checksums MUST be used. * In other words, the only way for checksums not to be used * is if both hosts in their SYNs set A=0." - * - * Section 3.3.0: - * "If a checksum is not present when its use has been - * negotiated, the receiver MUST close the subflow with a RST as - * it is considered broken." - * - * We don't implement DSS checksum - fall back to TCP. */ if (flags & MPTCP_CAP_CHECKSUM_REQD) - break; + mp_opt->csum_reqd = 1; + + if (flags & MPTCP_CAP_DENY_JOIN_ID0) + mp_opt->deny_join_id0 = 1; mp_opt->mp_capable = 1; if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) { @@ -86,7 +95,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->rcvr_key = get_unaligned_be64(ptr); ptr += 8; } - if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA) { + if (opsize >= TCPOLEN_MPTCP_MPC_ACK_DATA) { /* Section 3.1.: * "the data parameters in a MP_CAPABLE are semantically * equivalent to those in a DSS option and can be used @@ -98,9 +107,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->data_len = get_unaligned_be16(ptr); ptr += 2; } - pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d", + if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) { + mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + mp_opt->csum_reqd = 1; + ptr += 2; + } + pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u", version, flags, opsize, mp_opt->sndr_key, - mp_opt->rcvr_key, mp_opt->data_len); + mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum); break; case MPTCPOPT_MP_JOIN: @@ -171,10 +185,8 @@ static void mptcp_parse_option(const struct sk_buff *skb, expected_opsize += TCPOLEN_MPTCP_DSS_MAP32; } - /* RFC 6824, Section 3.3: - * If a checksum is present, but its use had - * not been negotiated in the MP_CAPABLE handshake, - * the checksum field MUST be ignored. + /* Always parse any csum presence combination, we will enforce + * RFC 8684 Section 3.3.0 checks later in subflow_data_ready */ if (opsize != expected_opsize && opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) @@ -209,9 +221,15 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->data_len = get_unaligned_be16(ptr); ptr += 2; - pr_debug("data_seq=%llu subflow_seq=%u data_len=%u", + if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) { + mp_opt->csum_reqd = 1; + mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr); + ptr += 2; + } + + pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", mp_opt->data_seq, mp_opt->subflow_seq, - mp_opt->data_len); + mp_opt->data_len, mp_opt->csum_reqd, mp_opt->csum); } break; @@ -323,9 +341,12 @@ static void mptcp_parse_option(const struct sk_buff *skb, } } -void mptcp_get_options(const struct sk_buff *skb, +void mptcp_get_options(const struct sock *sk, + const struct sk_buff *skb, struct mptcp_options_received *mp_opt) { + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); const struct tcphdr *th = tcp_hdr(skb); const unsigned char *ptr; int length; @@ -341,6 +362,8 @@ void mptcp_get_options(const struct sk_buff *skb, mp_opt->dss = 0; mp_opt->mp_prio = 0; mp_opt->reset = 0; + mp_opt->csum_reqd = READ_ONCE(msk->csum_enabled); + mp_opt->deny_join_id0 = 0; length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); @@ -382,6 +405,8 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, subflow->snd_isn = TCP_SKB_CB(skb)->end_seq; if (subflow->request_mptcp) { opts->suboptions = OPTION_MPTCP_MPC_SYN; + opts->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk)); + opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk)); *size = TCPOLEN_MPTCP_MPC_SYN; return true; } else if (subflow->request_join) { @@ -437,8 +462,10 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, struct mptcp_out_options *opts) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct mptcp_ext *mpext; unsigned int data_len; + u8 len; /* When skb is not available, we better over-estimate the emitted * options len. A full DSS option (28 bytes) is longer than @@ -467,16 +494,27 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, opts->suboptions = OPTION_MPTCP_MPC_ACK; opts->sndr_key = subflow->local_key; opts->rcvr_key = subflow->remote_key; + opts->csum_reqd = READ_ONCE(msk->csum_enabled); + opts->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk)); /* Section 3.1. * The MP_CAPABLE option is carried on the SYN, SYN/ACK, and ACK * packets that start the first subflow of an MPTCP connection, * as well as the first packet that carries data */ - if (data_len > 0) - *size = ALIGN(TCPOLEN_MPTCP_MPC_ACK_DATA, 4); - else + if (data_len > 0) { + len = TCPOLEN_MPTCP_MPC_ACK_DATA; + if (opts->csum_reqd) { + /* we need to propagate more info to csum the pseudo hdr */ + opts->ext_copy.data_seq = mpext->data_seq; + opts->ext_copy.subflow_seq = mpext->subflow_seq; + opts->ext_copy.csum = mpext->csum; + len += TCPOLEN_MPTCP_DSS_CHECKSUM; + } + *size = ALIGN(len, 4); + } else { *size = TCPOLEN_MPTCP_MPC_ACK; + } pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d", subflow, subflow->local_key, subflow->remote_key, @@ -537,18 +575,21 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, bool ret = false; u64 ack_seq; + opts->csum_reqd = READ_ONCE(msk->csum_enabled); mpext = skb ? mptcp_get_ext(skb) : NULL; if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) { - unsigned int map_size; + unsigned int map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64; - map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64; + if (mpext) { + if (opts->csum_reqd) + map_size += TCPOLEN_MPTCP_DSS_CHECKSUM; + + opts->ext_copy = *mpext; + } remaining -= map_size; dss_size = map_size; - if (mpext) - opts->ext_copy = *mpext; - if (skb && snd_data_fin_enable) mptcp_write_data_fin(subflow, skb, &opts->ext_copy); ret = true; @@ -791,6 +832,8 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, if (subflow_req->mp_capable) { opts->suboptions = OPTION_MPTCP_MPC_SYNACK; opts->sndr_key = subflow_req->local_key; + opts->csum_reqd = subflow_req->csum_reqd; + opts->allow_join_id0 = subflow_req->allow_join_id0; *size = TCPOLEN_MPTCP_MPC_SYNACK; pr_debug("subflow_req=%p, local_key=%llu", subflow_req, subflow_req->local_key); @@ -869,6 +912,9 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, return false; } + if (mp_opt->deny_join_id0) + WRITE_ONCE(msk->pm.remote_deny_join_id0, true); + if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); mptcp_subflow_fully_established(subflow, mp_opt); @@ -896,19 +942,20 @@ reset: return false; } -static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit) +u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq) { - u32 old_ack32, cur_ack32; + u32 old_seq32, cur_seq32; - if (use_64bit) - return cur_ack; + old_seq32 = (u32)old_seq; + cur_seq32 = (u32)cur_seq; + cur_seq = (old_seq & GENMASK_ULL(63, 32)) + cur_seq32; + if (unlikely(cur_seq32 < old_seq32 && before(old_seq32, cur_seq32))) + return cur_seq + (1LL << 32); - old_ack32 = (u32)old_ack; - cur_ack32 = (u32)cur_ack; - cur_ack = (old_ack & GENMASK_ULL(63, 32)) + cur_ack32; - if (unlikely(before(cur_ack32, old_ack32))) - return cur_ack + (1LL << 32); - return cur_ack; + /* reverse wrap could happen, too */ + if (unlikely(cur_seq32 > old_seq32 && after(old_seq32, cur_seq32))) + return cur_seq - (1LL << 32); + return cur_seq; } static void ack_update_msk(struct mptcp_sock *msk, @@ -926,7 +973,7 @@ static void ack_update_msk(struct mptcp_sock *msk, * more dangerous than missing an ack */ old_snd_una = msk->snd_una; - new_snd_una = expand_ack(old_snd_una, mp_opt->data_ack, mp_opt->ack64); + new_snd_una = mptcp_expand_seq(old_snd_una, mp_opt->data_ack, mp_opt->ack64); /* ACK for data not even sent yet? Ignore. */ if (after64(new_snd_una, snd_nxt)) @@ -963,7 +1010,7 @@ bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool us return false; WRITE_ONCE(msk->rcv_data_fin_seq, - expand_ack(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit)); + mptcp_expand_seq(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit)); WRITE_ONCE(msk->rcv_data_fin, 1); return true; @@ -1009,7 +1056,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) return; } - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) return; @@ -1101,6 +1148,10 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) } mpext->data_len = mp_opt.data_len; mpext->use_map = 1; + mpext->csum_reqd = mp_opt.csum_reqd; + + if (mpext->csum_reqd) + mpext->csum = mp_opt.csum; } } @@ -1120,25 +1171,53 @@ static void mptcp_set_rwin(const struct tcp_sock *tp) WRITE_ONCE(msk->rcv_wnd_sent, ack_seq); } +static u16 mptcp_make_csum(const struct mptcp_ext *mpext) +{ + struct csum_pseudo_header header; + __wsum csum; + + /* cfr RFC 8684 3.3.1.: + * the data sequence number used in the pseudo-header is + * always the 64-bit value, irrespective of what length is used in the + * DSS option itself. + */ + header.data_seq = cpu_to_be64(mpext->data_seq); + header.subflow_seq = htonl(mpext->subflow_seq); + header.data_len = htons(mpext->data_len); + header.csum = 0; + + csum = csum_partial(&header, sizeof(header), ~csum_unfold(mpext->csum)); + return (__force u16)csum_fold(csum); +} + void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) & opts->suboptions) { - u8 len; + u8 len, flag = MPTCP_CAP_HMAC_SHA256; - if (OPTION_MPTCP_MPC_SYN & opts->suboptions) + if (OPTION_MPTCP_MPC_SYN & opts->suboptions) { len = TCPOLEN_MPTCP_MPC_SYN; - else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) + } else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) { len = TCPOLEN_MPTCP_MPC_SYNACK; - else if (opts->ext_copy.data_len) + } else if (opts->ext_copy.data_len) { len = TCPOLEN_MPTCP_MPC_ACK_DATA; - else + if (opts->csum_reqd) + len += TCPOLEN_MPTCP_DSS_CHECKSUM; + } else { len = TCPOLEN_MPTCP_MPC_ACK; + } + + if (opts->csum_reqd) + flag |= MPTCP_CAP_CHECKSUM_REQD; + + if (!opts->allow_join_id0) + flag |= MPTCP_CAP_DENY_JOIN_ID0; *ptr++ = mptcp_option(MPTCPOPT_MP_CAPABLE, len, MPTCP_SUPPORTED_VERSION, - MPTCP_CAP_HMAC_SHA256); + flag); if (!((OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) & opts->suboptions)) @@ -1154,8 +1233,13 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, if (!opts->ext_copy.data_len) goto mp_capable_done; - put_unaligned_be32(opts->ext_copy.data_len << 16 | - TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + if (opts->csum_reqd) { + put_unaligned_be32(opts->ext_copy.data_len << 16 | + mptcp_make_csum(&opts->ext_copy), ptr); + } else { + put_unaligned_be32(opts->ext_copy.data_len << 16 | + TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + } ptr += 1; } @@ -1307,6 +1391,9 @@ mp_capable_done: flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64; if (mpext->data_fin) flags |= MPTCP_DSS_DATA_FIN; + + if (opts->csum_reqd) + len += TCPOLEN_MPTCP_DSS_CHECKSUM; } *ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags); @@ -1326,8 +1413,13 @@ mp_capable_done: ptr += 2; put_unaligned_be32(mpext->subflow_seq, ptr); ptr += 1; - put_unaligned_be32(mpext->data_len << 16 | - TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + if (opts->csum_reqd) { + put_unaligned_be32(mpext->data_len << 16 | + mptcp_make_csum(mpext), ptr); + } else { + put_unaligned_be32(mpext->data_len << 16 | + TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + } } } diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 9d00fa6d22e9..639271e09604 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -320,6 +320,7 @@ void mptcp_pm_data_init(struct mptcp_sock *msk) WRITE_ONCE(msk->pm.addr_signal, 0); WRITE_ONCE(msk->pm.accept_addr, false); WRITE_ONCE(msk->pm.accept_subflow, false); + WRITE_ONCE(msk->pm.remote_deny_join_id0, false); msk->pm.status = 0; spin_lock_init(&msk->pm.lock); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 2469e06a3a9d..d2591ebf01d9 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -451,7 +451,8 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) /* check if should create a new subflow */ if (msk->pm.local_addr_used < local_addr_max && - msk->pm.subflows < subflows_max) { + msk->pm.subflows < subflows_max && + !READ_ONCE(msk->pm.remote_deny_join_id0)) { local = select_local_address(pernet, msk); if (local) { struct mptcp_addr_info remote = { 0 }; @@ -540,6 +541,7 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node); if (subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; spin_unlock_bh(&msk->pm.lock); pr_debug("send ack for %s%s%s", @@ -547,9 +549,9 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) mptcp_pm_should_add_signal_ipv6(msk) ? " [ipv6]" : "", mptcp_pm_should_add_signal_port(msk) ? " [port]" : ""); - lock_sock(ssk); + slow = lock_sock_fast(ssk); tcp_send_ack(ssk); - release_sock(ssk); + unlock_sock_fast(ssk, slow); spin_lock_bh(&msk->pm.lock); } } @@ -566,6 +568,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, struct sock *ssk = mptcp_subflow_tcp_sock(subflow); struct sock *sk = (struct sock *)msk; struct mptcp_addr_info local; + bool slow; local_address((struct sock_common *)ssk, &local); if (!addresses_equal(&local, addr, addr->port)) @@ -578,9 +581,9 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, spin_unlock_bh(&msk->pm.lock); pr_debug("send ack for mp_prio"); - lock_sock(ssk); + slow = lock_sock_fast(ssk); tcp_send_ack(ssk); - release_sock(ssk); + unlock_sock_fast(ssk, slow); spin_lock_bh(&msk->pm.lock); return 0; @@ -971,8 +974,14 @@ skip_family: if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); - if (tb[MPTCP_PM_ADDR_ATTR_PORT]) + if (tb[MPTCP_PM_ADDR_ATTR_PORT]) { + if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { + NL_SET_ERR_MSG_ATTR(info->extack, attr, + "flags must have signal when using port"); + return -EINVAL; + } entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); + } return 0; } @@ -1913,10 +1922,13 @@ static int __net_init pm_nl_init_net(struct net *net) struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id); INIT_LIST_HEAD_RCU(&pernet->local_addr_list); - __reset_counters(pernet); pernet->next_id = 1; - bitmap_zero(pernet->id_bitmap, MAX_ADDR_ID + 1); spin_lock_init(&pernet->lock); + + /* No need to initialize other pernet fields, the struct is zeroed at + * allocation time. + */ + return 0; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 632350018fb6..7a5afa8c6866 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -39,10 +39,15 @@ struct mptcp_skb_cb { u64 map_seq; u64 end_seq; u32 offset; + u8 has_rxtstamp:1; }; #define MPTCP_SKB_CB(__skb) ((struct mptcp_skb_cb *)&((__skb)->cb[0])) +enum { + MPTCP_CMSG_TS = BIT(0), +}; + static struct percpu_counter mptcp_sockets_allocated; static void __mptcp_destroy_sock(struct sock *sk); @@ -272,6 +277,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = (struct sock *)msk; struct sk_buff *tail; + bool has_rxtstamp; __skb_unlink(skb, &ssk->sk_receive_queue); @@ -289,6 +295,8 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, sk->sk_forward_alloc += amount; } + has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; + /* the skb map_seq accounts for the skb offset: * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq * value @@ -296,6 +304,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow); MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len; MPTCP_SKB_CB(skb)->offset = offset; + MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp; if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) { /* in sequence */ @@ -424,56 +433,55 @@ static void mptcp_send_ack(struct mptcp_sock *msk) mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; - lock_sock(ssk); + slow = lock_sock_fast(ssk); if (tcp_can_send_ack(ssk)) tcp_send_ack(ssk); - release_sock(ssk); + unlock_sock_fast(ssk, slow); } } -static bool mptcp_subflow_cleanup_rbuf(struct sock *ssk) +static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) { - int ret; + bool slow; - lock_sock(ssk); - ret = tcp_can_send_ack(ssk); - if (ret) + slow = lock_sock_fast(ssk); + if (tcp_can_send_ack(ssk)) tcp_cleanup_rbuf(ssk, 1); - release_sock(ssk); - return ret; + unlock_sock_fast(ssk, slow); +} + +static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) +{ + const struct inet_connection_sock *icsk = inet_csk(ssk); + u8 ack_pending = READ_ONCE(icsk->icsk_ack.pending); + const struct tcp_sock *tp = tcp_sk(ssk); + + return (ack_pending & ICSK_ACK_SCHED) && + ((READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->rcv_wup) > + READ_ONCE(icsk->icsk_ack.rcv_mss)) || + (rx_empty && ack_pending & + (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); } static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) { - struct sock *ack_hint = READ_ONCE(msk->ack_hint); int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; - bool cleanup; + int space = __mptcp_space(sk); + bool cleanup, rx_empty; - /* this is a simple superset of what tcp_cleanup_rbuf() implements - * so that we don't have to acquire the ssk socket lock most of the time - * to do actually nothing - */ - cleanup = __mptcp_space(sk) - old_space >= max(0, old_space); - if (!cleanup) - return; + cleanup = (space > 0) && (space >= (old_space << 1)); + rx_empty = !atomic_read(&sk->sk_rmem_alloc); - /* if the hinted ssk is still active, try to use it */ - if (likely(ack_hint)) { - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - if (ack_hint == ssk && mptcp_subflow_cleanup_rbuf(ssk)) - return; - } + if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) + mptcp_subflow_cleanup_rbuf(ssk); } - - /* otherwise pick the first active subflow */ - mptcp_for_each_subflow(msk, subflow) - if (mptcp_subflow_cleanup_rbuf(mptcp_subflow_tcp_sock(subflow))) - return; } static bool mptcp_check_data_fin(struct sock *sk) @@ -618,7 +626,6 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, break; } } while (more_data_avail); - WRITE_ONCE(msk->ack_hint, ssk); *bytes += moved; return done; @@ -675,9 +682,6 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) struct sock *sk = (struct sock *)msk; unsigned int moved = 0; - if (inet_sk_state_load(sk) == TCP_CLOSE) - return false; - __mptcp_move_skbs_from_subflow(msk, ssk, &moved); __mptcp_ofo_queue(msk); if (unlikely(ssk->sk_err)) { @@ -893,22 +897,14 @@ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk, df->data_seq + df->data_len == msk->write_seq; } -static int mptcp_wmem_with_overhead(struct sock *sk, int size) +static int mptcp_wmem_with_overhead(int size) { - struct mptcp_sock *msk = mptcp_sk(sk); - int ret, skbs; - - ret = size + ((sizeof(struct mptcp_data_frag) * size) >> PAGE_SHIFT); - skbs = (msk->tx_pending_data + size) / msk->size_goal_cache; - if (skbs < msk->skb_tx_cache.qlen) - return ret; - - return ret + (skbs - msk->skb_tx_cache.qlen) * SKB_TRUESIZE(MAX_TCP_HEADER); + return size + ((sizeof(struct mptcp_data_frag) * size) >> PAGE_SHIFT); } static void __mptcp_wmem_reserve(struct sock *sk, int size) { - int amount = mptcp_wmem_with_overhead(sk, size); + int amount = mptcp_wmem_with_overhead(size); struct mptcp_sock *msk = mptcp_sk(sk); WARN_ON_ONCE(msk->wmem_reserved); @@ -1203,49 +1199,8 @@ static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp) return NULL; } -static bool mptcp_tx_cache_refill(struct sock *sk, int size, - struct sk_buff_head *skbs, int *total_ts) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - struct sk_buff *skb; - int space_needed; - - if (unlikely(tcp_under_memory_pressure(sk))) { - mptcp_mem_reclaim_partial(sk); - - /* under pressure pre-allocate at most a single skb */ - if (msk->skb_tx_cache.qlen) - return true; - space_needed = msk->size_goal_cache; - } else { - space_needed = msk->tx_pending_data + size - - msk->skb_tx_cache.qlen * msk->size_goal_cache; - } - - while (space_needed > 0) { - skb = __mptcp_do_alloc_tx_skb(sk, sk->sk_allocation); - if (unlikely(!skb)) { - /* under memory pressure, try to pass the caller a - * single skb to allow forward progress - */ - while (skbs->qlen > 1) { - skb = __skb_dequeue_tail(skbs); - *total_ts -= skb->truesize; - __kfree_skb(skb); - } - return skbs->qlen > 0; - } - - *total_ts += skb->truesize; - __skb_queue_tail(skbs, skb); - space_needed -= msk->size_goal_cache; - } - return true; -} - static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) { - struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb; if (ssk->sk_tx_skb_cache) { @@ -1256,22 +1211,6 @@ static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) return true; } - skb = skb_peek(&msk->skb_tx_cache); - if (skb) { - if (likely(sk_wmem_schedule(ssk, skb->truesize))) { - skb = __skb_dequeue(&msk->skb_tx_cache); - if (WARN_ON_ONCE(!skb)) - return false; - - mptcp_wmem_uncharge(sk, skb->truesize); - ssk->sk_tx_skb_cache = skb; - return true; - } - - /* over memory limit, no point to try to allocate a new skb */ - return false; - } - skb = __mptcp_do_alloc_tx_skb(sk, gfp); if (!skb) return false; @@ -1287,7 +1226,6 @@ static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) static bool mptcp_must_reclaim_memory(struct sock *sk, struct sock *ssk) { return !ssk->sk_tx_skb_cache && - !skb_peek(&mptcp_sk(sk)->skb_tx_cache) && tcp_under_memory_pressure(sk); } @@ -1298,6 +1236,18 @@ static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk) return __mptcp_alloc_tx_skb(sk, ssk, sk->sk_allocation); } +/* note: this always recompute the csum on the whole skb, even + * if we just appended a single frag. More status info needed + */ +static void mptcp_update_data_checksum(struct sk_buff *skb, int added) +{ + struct mptcp_ext *mpext = mptcp_get_ext(skb); + __wsum csum = ~csum_unfold(mpext->csum); + int offset = skb->len - added; + + mpext->csum = csum_fold(csum_block_add(csum, skb_checksum(skb, offset, added, 0), offset)); +} + static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, struct mptcp_data_frag *dfrag, struct mptcp_sendmsg_info *info) @@ -1318,7 +1268,6 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, /* compute send limit */ info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags); avail_size = info->size_goal; - msk->size_goal_cache = info->size_goal; skb = tcp_write_queue_tail(ssk); if (skb) { /* Limit the write to the size available in the @@ -1392,10 +1341,14 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, if (zero_window_probe) { mptcp_subflow_ctx(ssk)->rel_write_seq += ret; mpext->frozen = 1; - ret = 0; + if (READ_ONCE(msk->csum_enabled)) + mptcp_update_data_checksum(tail, ret); tcp_push_pending_frames(ssk); + return 0; } out: + if (READ_ONCE(msk->csum_enabled)) + mptcp_update_data_checksum(tail, ret); mptcp_subflow_ctx(ssk)->rel_write_seq += ret; return ret; } @@ -1663,7 +1616,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) while (msg_data_left(msg)) { int total_ts, frag_truesize = 0; struct mptcp_data_frag *dfrag; - struct sk_buff_head skbs; bool dfrag_collapsed; size_t psize, offset; @@ -1696,16 +1648,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) psize = pfrag->size - offset; psize = min_t(size_t, psize, msg_data_left(msg)); total_ts = psize + frag_truesize; - __skb_queue_head_init(&skbs); - if (!mptcp_tx_cache_refill(sk, psize, &skbs, &total_ts)) + + if (!mptcp_wmem_alloc(sk, total_ts)) goto wait_for_memory; - if (!mptcp_wmem_alloc(sk, total_ts)) { - __skb_queue_purge(&skbs); - goto wait_for_memory; - } - - skb_queue_splice_tail(&skbs, &msk->skb_tx_cache); if (copy_page_from_iter(dfrag->page, offset, psize, &msg->msg_iter) != psize) { mptcp_wmem_uncharge(sk, psize + frag_truesize); @@ -1762,7 +1708,7 @@ static void mptcp_wait_data(struct sock *sk, long *timeo) sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); sk_wait_event(sk, timeo, - test_and_clear_bit(MPTCP_DATA_READY, &msk->flags), &wait); + test_bit(MPTCP_DATA_READY, &msk->flags), &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); @@ -1770,7 +1716,9 @@ static void mptcp_wait_data(struct sock *sk, long *timeo) static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, struct msghdr *msg, - size_t len, int flags) + size_t len, int flags, + struct scm_timestamping_internal *tss, + int *cmsg_flags) { struct sk_buff *skb, *tmp; int copied = 0; @@ -1790,6 +1738,11 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, } } + if (MPTCP_SKB_CB(skb)->has_rxtstamp) { + tcp_update_recv_tstamps(skb, tss); + *cmsg_flags |= MPTCP_CMSG_TS; + } + copied += count; if (count < data_len) { @@ -1953,7 +1906,6 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) __mptcp_update_rmem(sk); done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); mptcp_data_unlock(sk); - tcp_cleanup_rbuf(ssk, moved); if (unlikely(ssk->sk_err)) __mptcp_error_report(sk); @@ -1969,7 +1921,6 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) ret |= __mptcp_ofo_queue(msk); __mptcp_splice_receive_queue(sk); mptcp_data_unlock(sk); - mptcp_cleanup_rbuf(msk); } if (ret) mptcp_check_data_fin((struct sock *)msk); @@ -1980,7 +1931,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { struct mptcp_sock *msk = mptcp_sk(sk); - int copied = 0; + struct scm_timestamping_internal tss; + int copied = 0, cmsg_flags = 0; int target; long timeo; @@ -2002,7 +1954,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, while (copied < len) { int bytes_read; - bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags); + bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags); if (unlikely(bytes_read < 0)) { if (!copied) copied = bytes_read; @@ -2078,11 +2030,14 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, */ if (unlikely(__mptcp_move_skbs(msk))) set_bit(MPTCP_DATA_READY, &msk->flags); - } else if (unlikely(!test_bit(MPTCP_DATA_READY, &msk->flags))) { - /* data to read but mptcp_wait_data() cleared DATA_READY */ - set_bit(MPTCP_DATA_READY, &msk->flags); } + out_err: + if (cmsg_flags && copied >= 0) { + if (cmsg_flags & MPTCP_CMSG_TS) + tcp_recv_timestamp(msg, sk, &tss); + } + pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d", msk, test_bit(MPTCP_DATA_READY, &msk->flags), skb_queue_empty_lockless(&sk->sk_receive_queue), copied); @@ -2214,9 +2169,6 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (ssk == msk->last_snd) msk->last_snd = NULL; - if (ssk == msk->ack_hint) - msk->ack_hint = NULL; - if (ssk == msk->first) msk->first = NULL; @@ -2288,13 +2240,14 @@ static void mptcp_check_fastclose(struct mptcp_sock *msk) list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); + bool slow; - lock_sock(tcp_sk); + slow = lock_sock_fast(tcp_sk); if (tcp_sk->sk_state != TCP_CLOSE) { tcp_send_active_reset(tcp_sk, GFP_ATOMIC); tcp_set_state(tcp_sk, TCP_CLOSE); } - release_sock(tcp_sk); + unlock_sock_fast(tcp_sk, slow); } inet_sk_state_store(sk, TCP_CLOSE); @@ -2339,8 +2292,8 @@ static void __mptcp_retrans(struct sock *sk) /* limit retransmission to the bytes already sent on some subflows */ info.sent = 0; - info.limit = dfrag->already_sent; - while (info.sent < dfrag->already_sent) { + info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent; + while (info.sent < info.limit) { if (!mptcp_alloc_tx_skb(sk, ssk)) break; @@ -2352,9 +2305,11 @@ static void __mptcp_retrans(struct sock *sk) copied += ret; info.sent += ret; } - if (copied) + if (copied) { + dfrag->already_sent = max(dfrag->already_sent, info.sent); tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); + } mptcp_set_timeout(sk, ssk); release_sock(ssk); @@ -2422,17 +2377,15 @@ static int __mptcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&msk->rtx_queue); INIT_WORK(&msk->work, mptcp_worker); __skb_queue_head_init(&msk->receive_queue); - __skb_queue_head_init(&msk->skb_tx_cache); msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; msk->wmem_reserved = 0; msk->rmem_released = 0; msk->tx_pending_data = 0; - msk->size_goal_cache = TCP_BASE_MSS; - msk->ack_hint = NULL; msk->first = NULL; inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; + WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_init(msk); @@ -2484,15 +2437,10 @@ static void __mptcp_clear_xmit(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; - struct sk_buff *skb; WRITE_ONCE(msk->first_pending, NULL); list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) dfrag_clear(sk, dfrag); - while ((skb = __skb_dequeue(&msk->skb_tx_cache)) != NULL) { - sk->sk_forward_alloc += skb->truesize; - kfree_skb(skb); - } } static void mptcp_cancel_work(struct sock *sk) @@ -2773,6 +2721,8 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->token = subflow_req->token; msk->subflow = NULL; WRITE_ONCE(msk->fully_established, false); + if (mp_opt->csum_reqd) + WRITE_ONCE(msk->csum_enabled, true); msk->write_seq = subflow_req->idsn + 1; msk->snd_nxt = msk->write_seq; @@ -2946,6 +2896,11 @@ static void mptcp_release_cb(struct sock *sk) spin_lock_bh(&sk->sk_lock.slock); } + /* be sure to set the current sk state before tacking actions + * depending on sk_state + */ + if (test_and_clear_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->flags)) + __mptcp_set_connected(sk); if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags)) __mptcp_clean_una_wakeup(sk); if (test_and_clear_bit(MPTCP_ERROR_REPORT, &mptcp_sk(sk)->flags)) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 385796f0ef19..426ed80fe72f 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -68,6 +68,8 @@ #define TCPOLEN_MPTCP_FASTCLOSE 12 #define TCPOLEN_MPTCP_RST 4 +#define TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM (TCPOLEN_MPTCP_DSS_CHECKSUM + TCPOLEN_MPTCP_MPC_ACK_DATA) + /* MPTCP MP_JOIN flags */ #define MPTCPOPT_BACKUP BIT(0) #define MPTCPOPT_HMAC_LEN 20 @@ -77,8 +79,9 @@ #define MPTCP_VERSION_MASK (0x0F) #define MPTCP_CAP_CHECKSUM_REQD BIT(7) #define MPTCP_CAP_EXTENSIBILITY BIT(6) +#define MPTCP_CAP_DENY_JOIN_ID0 BIT(5) #define MPTCP_CAP_HMAC_SHA256 BIT(0) -#define MPTCP_CAP_FLAG_MASK (0x3F) +#define MPTCP_CAP_FLAG_MASK (0x1F) /* MPTCP DSS flags */ #define MPTCP_DSS_DATA_FIN BIT(4) @@ -109,6 +112,7 @@ #define MPTCP_ERROR_REPORT 8 #define MPTCP_RETRANSMIT 9 #define MPTCP_WORK_SYNC_SETSOCKOPT 10 +#define MPTCP_CONNECTED 11 static inline bool before64(__u64 seq1, __u64 seq2) { @@ -124,6 +128,7 @@ struct mptcp_options_received { u64 data_seq; u32 subflow_seq; u16 data_len; + __sum16 csum; u16 mp_capable : 1, mp_join : 1, fastclose : 1, @@ -133,7 +138,9 @@ struct mptcp_options_received { rm_addr : 1, mp_prio : 1, echo : 1, - backup : 1; + csum_reqd : 1, + backup : 1, + deny_join_id0 : 1; u32 token; u32 nonce; u64 thmac; @@ -188,6 +195,7 @@ struct mptcp_pm_data { bool work_pending; bool accept_addr; bool accept_subflow; + bool remote_deny_join_id0; u8 add_addr_signaled; u8 add_addr_accepted; u8 local_addr_used; @@ -234,15 +242,13 @@ struct mptcp_sock { bool snd_data_fin_enable; bool rcv_fastclose; bool use_64bit_ack; /* Set when we received a 64-bit DSN */ + bool csum_enabled; spinlock_t join_list_lock; - struct sock *ack_hint; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; struct sk_buff_head receive_queue; - struct sk_buff_head skb_tx_cache; /* this is wmem accounted */ int tx_pending_data; - int size_goal_cache; struct list_head conn_list; struct list_head rtx_queue; struct mptcp_data_frag *first_pending; @@ -335,11 +341,20 @@ static inline struct mptcp_data_frag *mptcp_rtx_head(const struct sock *sk) return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list); } +struct csum_pseudo_header { + __be64 data_seq; + __be32 subflow_seq; + __be16 data_len; + __sum16 csum; +}; + struct mptcp_subflow_request_sock { struct tcp_request_sock sk; u16 mp_capable : 1, mp_join : 1, - backup : 1; + backup : 1, + csum_reqd : 1, + allow_join_id0 : 1; u8 local_id; u8 remote_id; u64 local_key; @@ -386,6 +401,8 @@ struct mptcp_subflow_context { u32 map_subflow_seq; u32 ssn_offset; u32 map_data_len; + __wsum map_data_csum; + u32 map_csum_len; u32 request_mptcp : 1, /* send MP_CAPABLE */ request_join : 1, /* send MP_JOIN */ request_bkup : 1, @@ -395,6 +412,8 @@ struct mptcp_subflow_context { pm_notified : 1, /* PM hook called for established status */ conn_finished : 1, map_valid : 1, + map_csum_reqd : 1, + map_data_fin : 1, mpc_map : 1, backup : 1, send_mp_prio : 1, @@ -524,6 +543,8 @@ static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *su int mptcp_is_enabled(struct net *net); unsigned int mptcp_get_add_addr_timeout(struct net *net); +int mptcp_is_checksum_enabled(struct net *net); +int mptcp_allow_join_id0(struct net *net); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, struct mptcp_options_received *mp_opt); bool mptcp_subflow_data_available(struct sock *sk); @@ -575,10 +596,12 @@ int __init mptcp_proto_v6_init(void); struct sock *mptcp_sk_clone(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct request_sock *req); -void mptcp_get_options(const struct sk_buff *skb, +void mptcp_get_options(const struct sock *sk, + const struct sk_buff *skb, struct mptcp_options_received *mp_opt); void mptcp_finish_connect(struct sock *sk); +void __mptcp_set_connected(struct sock *sk); static inline bool mptcp_is_fully_established(struct sock *sk) { return inet_sk_state_load(sk) == TCP_ESTABLISHED && @@ -593,6 +616,14 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname, int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option); +u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq); +static inline u64 mptcp_expand_seq(u64 old_seq, u64 cur_seq, bool use_64bit) +{ + if (use_64bit) + return cur_seq; + + return __mptcp_expand_seq(old_seq, cur_seq); +} void __mptcp_check_push(struct sock *sk, struct sock *ssk); void __mptcp_data_acked(struct sock *sk); void __mptcp_error_report(struct sock *sk); @@ -626,6 +657,8 @@ static inline void mptcp_write_space(struct sock *sk) void mptcp_destroy_common(struct mptcp_sock *msk); +#define MPTCP_TOKEN_MAX_RETRIES 4 + void __init mptcp_token_init(void); static inline void mptcp_token_init_request(struct request_sock *req) { @@ -752,9 +785,6 @@ unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk); unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk); -int mptcp_setsockopt(struct sock *sk, int level, int optname, - sockptr_t optval, unsigned int optlen); - void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk); void mptcp_sockopt_sync_all(struct mptcp_sock *msk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index a79798189599..092d1f635d27 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -140,6 +140,43 @@ static void mptcp_so_incoming_cpu(struct mptcp_sock *msk, int val) mptcp_sol_socket_sync_intval(msk, SO_INCOMING_CPU, val); } +static int mptcp_setsockopt_sol_socket_tstamp(struct mptcp_sock *msk, int optname, int val) +{ + sockptr_t optval = KERNEL_SOCKPTR(&val); + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + int ret; + + ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, + optval, sizeof(val)); + if (ret) + return ret; + + lock_sock(sk); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow = lock_sock_fast(ssk); + + switch (optname) { + case SO_TIMESTAMP_OLD: + case SO_TIMESTAMP_NEW: + case SO_TIMESTAMPNS_OLD: + case SO_TIMESTAMPNS_NEW: + sock_set_timestamp(sk, optname, !!val); + break; + case SO_TIMESTAMPING_NEW: + case SO_TIMESTAMPING_OLD: + sock_set_timestamping(sk, optname, val); + break; + } + + unlock_sock_fast(ssk, slow); + } + + release_sock(sk); + return 0; +} + static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname, sockptr_t optval, unsigned int optlen) { @@ -164,6 +201,13 @@ static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname, case SO_INCOMING_CPU: mptcp_so_incoming_cpu(msk, val); return 0; + case SO_TIMESTAMP_OLD: + case SO_TIMESTAMP_NEW: + case SO_TIMESTAMPNS_OLD: + case SO_TIMESTAMPNS_NEW: + case SO_TIMESTAMPING_OLD: + case SO_TIMESTAMPING_NEW: + return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val); } return -ENOPROTOOPT; @@ -251,9 +295,23 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, case SO_MARK: case SO_INCOMING_CPU: case SO_DEBUG: + case SO_TIMESTAMP_OLD: + case SO_TIMESTAMP_NEW: + case SO_TIMESTAMPNS_OLD: + case SO_TIMESTAMPNS_NEW: + case SO_TIMESTAMPING_OLD: + case SO_TIMESTAMPING_NEW: return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen); case SO_LINGER: return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen); + case SO_RCVLOWAT: + case SO_RCVTIMEO_OLD: + case SO_RCVTIMEO_NEW: + case SO_BUSY_POLL: + case SO_PREFER_BUSY_POLL: + case SO_BUSY_POLL_BUDGET: + /* No need to copy: only relevant for msk */ + return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen); case SO_NO_CHECK: case SO_DONTROUTE: case SO_BROADCAST: @@ -267,7 +325,24 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, return 0; } - return sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname, optval, optlen); + /* SO_OOBINLINE is not supported, let's avoid the related mess + * SO_ATTACH_FILTER, SO_ATTACH_BPF, SO_ATTACH_REUSEPORT_CBPF, + * SO_DETACH_REUSEPORT_BPF, SO_DETACH_FILTER, SO_LOCK_FILTER, + * we must be careful with subflows + * + * SO_ATTACH_REUSEPORT_EBPF is not supported, at it checks + * explicitly the sk_protocol field + * + * SO_PEEK_OFF is unsupported, as it is for plain TCP + * SO_MAX_PACING_RATE is unsupported, we must be careful with subflows + * SO_CNX_ADVICE is currently unsupported, could possibly be relevant, + * but likely needs careful design + * + * SO_ZEROCOPY is currently unsupported, TODO in sndmsg + * SO_TXTIME is currently unsupported + */ + + return -EOPNOTSUPP; } static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname, @@ -299,72 +374,6 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname, static bool mptcp_supported_sockopt(int level, int optname) { - if (level == SOL_SOCKET) { - switch (optname) { - case SO_DEBUG: - case SO_REUSEPORT: - case SO_REUSEADDR: - - /* the following ones need a better implementation, - * but are quite common we want to preserve them - */ - case SO_BINDTODEVICE: - case SO_SNDBUF: - case SO_SNDBUFFORCE: - case SO_RCVBUF: - case SO_RCVBUFFORCE: - case SO_KEEPALIVE: - case SO_PRIORITY: - case SO_LINGER: - case SO_TIMESTAMP_OLD: - case SO_TIMESTAMP_NEW: - case SO_TIMESTAMPNS_OLD: - case SO_TIMESTAMPNS_NEW: - case SO_TIMESTAMPING_OLD: - case SO_TIMESTAMPING_NEW: - case SO_RCVLOWAT: - case SO_RCVTIMEO_OLD: - case SO_RCVTIMEO_NEW: - case SO_SNDTIMEO_OLD: - case SO_SNDTIMEO_NEW: - case SO_MARK: - case SO_INCOMING_CPU: - case SO_BINDTOIFINDEX: - case SO_BUSY_POLL: - case SO_PREFER_BUSY_POLL: - case SO_BUSY_POLL_BUDGET: - - /* next ones are no-op for plain TCP */ - case SO_NO_CHECK: - case SO_DONTROUTE: - case SO_BROADCAST: - case SO_BSDCOMPAT: - case SO_PASSCRED: - case SO_PASSSEC: - case SO_RXQ_OVFL: - case SO_WIFI_STATUS: - case SO_NOFCS: - case SO_SELECT_ERR_QUEUE: - return true; - } - - /* SO_OOBINLINE is not supported, let's avoid the related mess */ - /* SO_ATTACH_FILTER, SO_ATTACH_BPF, SO_ATTACH_REUSEPORT_CBPF, - * SO_DETACH_REUSEPORT_BPF, SO_DETACH_FILTER, SO_LOCK_FILTER, - * we must be careful with subflows - */ - /* SO_ATTACH_REUSEPORT_EBPF is not supported, at it checks - * explicitly the sk_protocol field - */ - /* SO_PEEK_OFF is unsupported, as it is for plain TCP */ - /* SO_MAX_PACING_RATE is unsupported, we must be careful with subflows */ - /* SO_CNX_ADVICE is currently unsupported, could possibly be relevant, - * but likely needs careful design - */ - /* SO_ZEROCOPY is currently unsupported, TODO in sndmsg */ - /* SO_TXTIME is currently unsupported */ - return false; - } if (level == SOL_IP) { switch (optname) { /* should work fine */ @@ -574,12 +583,12 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname, pr_debug("msk=%p", msk); - if (!mptcp_supported_sockopt(level, optname)) - return -ENOPROTOOPT; - if (level == SOL_SOCKET) return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen); + if (!mptcp_supported_sockopt(level, optname)) + return -ENOPROTOOPT; + /* @@ the meaning of setsockopt() when the socket is connected and * there are multiple subflows is not yet defined. It is up to the * MPTCP-level socket to configure the subflows until the subflow diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index be1de4084196..66d0b1893d26 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -108,6 +108,8 @@ static void subflow_init_req(struct request_sock *req, const struct sock *sk_lis subflow_req->mp_capable = 0; subflow_req->mp_join = 0; + subflow_req->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk_listener)); + subflow_req->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk_listener)); subflow_req->msk = NULL; mptcp_token_init_request(req); } @@ -150,7 +152,7 @@ static int subflow_check_req(struct request_sock *req, return -EINVAL; #endif - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk_listener, skb, &mp_opt); if (mp_opt.mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); @@ -162,7 +164,7 @@ static int subflow_check_req(struct request_sock *req, } if (mp_opt.mp_capable && listener->request_mptcp) { - int err, retries = 4; + int err, retries = MPTCP_TOKEN_MAX_RETRIES; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; again: @@ -247,7 +249,7 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, int err; subflow_init_req(req, sk_listener); - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk_listener, skb, &mp_opt); if (mp_opt.mp_capable && mp_opt.mp_join) return -EINVAL; @@ -371,6 +373,24 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport; } +void __mptcp_set_connected(struct sock *sk) +{ + if (sk->sk_state == TCP_SYN_SENT) { + inet_sk_state_store(sk, TCP_ESTABLISHED); + sk->sk_state_change(sk); + } +} + +static void mptcp_set_connected(struct sock *sk) +{ + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_set_connected(sk); + else + set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->flags); + mptcp_data_unlock(sk); +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -379,10 +399,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->icsk_af_ops->sk_rx_dst_set(sk, skb); - if (inet_sk_state_load(parent) == TCP_SYN_SENT) { - inet_sk_state_store(parent, TCP_ESTABLISHED); - parent->sk_state_change(parent); - } /* be sure no special action on any packet other than syn-ack */ if (subflow->conn_finished) @@ -394,7 +410,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->ssn_offset = TCP_SKB_CB(skb)->seq; pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset); - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (subflow->request_mptcp) { if (!mp_opt.mp_capable) { MPTCP_INC_STATS(sock_net(sk), @@ -404,6 +420,10 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) goto fallback; } + if (mp_opt.csum_reqd) + WRITE_ONCE(mptcp_sk(parent)->csum_enabled, true); + if (mp_opt.deny_join_id0) + WRITE_ONCE(mptcp_sk(parent)->pm.remote_deny_join_id0, true); subflow->mp_capable = 1; subflow->can_ack = 1; subflow->remote_key = mp_opt.sndr_key; @@ -411,6 +431,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->remote_key); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); + mptcp_set_connected(parent); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; @@ -430,15 +451,15 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) goto do_reset; } + if (!mptcp_finish_join(sk)) + goto do_reset; + subflow_generate_hmac(subflow->local_key, subflow->remote_key, subflow->local_nonce, subflow->remote_nonce, hmac); memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN); - if (!mptcp_finish_join(sk)) - goto do_reset; - subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); @@ -451,6 +472,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } else if (mptcp_check_fallback(sk)) { fallback: mptcp_rcv_space_init(mptcp_sk(parent), sk); + mptcp_set_connected(parent); } return; @@ -558,6 +580,7 @@ static void mptcp_sock_destruct(struct sock *sk) static void mptcp_force_close(struct sock *sk) { + /* the msk is not yet exposed to user-space */ inet_sk_state_store(sk, TCP_CLOSE); sk_common_release(sk); } @@ -638,7 +661,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, * reordered MPC will cause fallback, but we don't have other * options. */ - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (!mp_opt.mp_capable) { fallback = true; goto create_child; @@ -648,7 +671,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, if (!new_msk) fallback = true; } else if (subflow_req->mp_join) { - mptcp_get_options(skb, &mp_opt); + mptcp_get_options(sk, skb, &mp_opt); if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) || !mptcp_can_accept_new_subflow(subflow_req->msk)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); @@ -775,15 +798,6 @@ enum mapping_status { MAPPING_DUMMY }; -static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq) -{ - if ((u32)seq == (u32)old_seq) - return old_seq; - - /* Assume map covers data not mapped yet. */ - return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32)); -} - static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d", @@ -824,10 +838,92 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) return true; } +static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *skb, + bool csum_reqd) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct csum_pseudo_header header; + u32 offset, seq, delta; + __wsum csum; + int len; + + if (!csum_reqd) + return MAPPING_OK; + + /* mapping already validated on previous traversal */ + if (subflow->map_csum_len == subflow->map_data_len) + return MAPPING_OK; + + /* traverse the receive queue, ensuring it contains a full + * DSS mapping and accumulating the related csum. + * Preserve the accoumlate csum across multiple calls, to compute + * the csum only once + */ + delta = subflow->map_data_len - subflow->map_csum_len; + for (;;) { + seq = tcp_sk(ssk)->copied_seq + subflow->map_csum_len; + offset = seq - TCP_SKB_CB(skb)->seq; + + /* if the current skb has not been accounted yet, csum its contents + * up to the amount covered by the current DSS + */ + if (offset < skb->len) { + __wsum csum; + + len = min(skb->len - offset, delta); + csum = skb_checksum(skb, offset, len, 0); + subflow->map_data_csum = csum_block_add(subflow->map_data_csum, csum, + subflow->map_csum_len); + + delta -= len; + subflow->map_csum_len += len; + } + if (delta == 0) + break; + + if (skb_queue_is_last(&ssk->sk_receive_queue, skb)) { + /* if this subflow is closed, the partial mapping + * will be never completed; flush the pending skbs, so + * that subflow_sched_work_if_closed() can kick in + */ + if (unlikely(ssk->sk_state == TCP_CLOSE)) + while ((skb = skb_peek(&ssk->sk_receive_queue))) + sk_eat_skb(ssk, skb); + + /* not enough data to validate the csum */ + return MAPPING_EMPTY; + } + + /* the DSS mapping for next skbs will be validated later, + * when a get_mapping_status call will process such skb + */ + skb = skb->next; + } + + /* note that 'map_data_len' accounts only for the carried data, does + * not include the eventual seq increment due to the data fin, + * while the pseudo header requires the original DSS data len, + * including that + */ + header.data_seq = cpu_to_be64(subflow->map_seq); + header.subflow_seq = htonl(subflow->map_subflow_seq); + header.data_len = htons(subflow->map_data_len + subflow->map_data_fin); + header.csum = 0; + + csum = csum_partial(&header, sizeof(header), subflow->map_data_csum); + if (unlikely(csum_fold(csum))) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR); + return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY; + } + + return MAPPING_OK; +} + static enum mapping_status get_mapping_status(struct sock *ssk, struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + bool csum_reqd = READ_ONCE(msk->csum_enabled); struct mptcp_ext *mpext; struct sk_buff *skb; u16 data_len; @@ -907,22 +1003,17 @@ static enum mapping_status get_mapping_status(struct sock *ssk, data_len--; } - if (!mpext->dsn64) { - map_seq = expand_seq(subflow->map_seq, subflow->map_data_len, - mpext->data_seq); - pr_debug("expanded seq=%llu", subflow->map_seq); - } else { - map_seq = mpext->data_seq; - } + map_seq = mptcp_expand_seq(READ_ONCE(msk->ack_seq), mpext->data_seq, mpext->dsn64); WRITE_ONCE(mptcp_sk(subflow->conn)->use_64bit_ack, !!mpext->dsn64); if (subflow->map_valid) { /* Allow replacing only with an identical map */ if (subflow->map_seq == map_seq && subflow->map_subflow_seq == mpext->subflow_seq && - subflow->map_data_len == data_len) { + subflow->map_data_len == data_len && + subflow->map_csum_reqd == mpext->csum_reqd) { skb_ext_del(skb, SKB_EXT_MPTCP); - return MAPPING_OK; + goto validate_csum; } /* If this skb data are fully covered by the current mapping, @@ -934,27 +1025,41 @@ static enum mapping_status get_mapping_status(struct sock *ssk, } /* will validate the next map after consuming the current one */ - return MAPPING_OK; + goto validate_csum; } subflow->map_seq = map_seq; subflow->map_subflow_seq = mpext->subflow_seq; subflow->map_data_len = data_len; subflow->map_valid = 1; + subflow->map_data_fin = mpext->data_fin; subflow->mpc_map = mpext->mpc_map; - pr_debug("new map seq=%llu subflow_seq=%u data_len=%u", + subflow->map_csum_reqd = mpext->csum_reqd; + subflow->map_csum_len = 0; + subflow->map_data_csum = csum_unfold(mpext->csum); + + /* Cfr RFC 8684 Section 3.3.0 */ + if (unlikely(subflow->map_csum_reqd != csum_reqd)) + return MAPPING_INVALID; + + pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", subflow->map_seq, subflow->map_subflow_seq, - subflow->map_data_len); + subflow->map_data_len, subflow->map_csum_reqd, + subflow->map_data_csum); validate_seq: /* we revalidate valid mapping on new skb, because we must ensure * the current skb is completely covered by the available mapping */ - if (!validate_mapping(ssk, skb)) + if (!validate_mapping(ssk, skb)) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSTCPMISMATCH); return MAPPING_INVALID; + } skb_ext_del(skb, SKB_EXT_MPTCP); - return MAPPING_OK; + +validate_csum: + return validate_data_csum(ssk, skb, csum_reqd); } static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, @@ -1137,7 +1242,7 @@ void __mptcp_error_report(struct sock *sk) /* This barrier is coupled with smp_rmb() in mptcp_poll() */ smp_wmb(); - sk->sk_error_report(sk); + sk_error_report(sk); break; } } @@ -1489,10 +1594,7 @@ static void subflow_state_change(struct sock *sk) mptcp_rcv_space_init(mptcp_sk(parent), sk); pr_fallback(mptcp_sk(parent)); subflow->conn_finished = 1; - if (inet_sk_state_load(parent) == TCP_SYN_SENT) { - inet_sk_state_store(parent, TCP_ESTABLISHED); - parent->sk_state_change(parent); - } + mptcp_set_connected(parent); } /* as recvmsg() does not acquire the subflow socket for ssk selection diff --git a/net/mptcp/token.c b/net/mptcp/token.c index 8f0270a780ce..a98e554b034f 100644 --- a/net/mptcp/token.c +++ b/net/mptcp/token.c @@ -33,7 +33,6 @@ #include #include "protocol.h" -#define TOKEN_MAX_RETRIES 4 #define TOKEN_MAX_CHAIN_LEN 4 struct token_bucket { @@ -153,12 +152,9 @@ int mptcp_token_new_connect(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - int retries = TOKEN_MAX_RETRIES; + int retries = MPTCP_TOKEN_MAX_RETRIES; struct token_bucket *bucket; - pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n", - sk, subflow->local_key, subflow->token, subflow->idsn); - again: mptcp_crypto_key_gen_sha(&subflow->local_key, &subflow->token, &subflow->idsn); @@ -172,6 +168,9 @@ again: goto again; } + pr_debug("ssk=%p, local_key=%llu, token=%u, idsn=%llu\n", + sk, subflow->local_key, subflow->token, subflow->idsn); + WRITE_ONCE(msk->token, subflow->token); __sk_nulls_add_node_rcu((struct sock *)msk, &bucket->msk_chain); bucket->chain_len++; diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 49031f804276..cbbb0de4750a 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -238,7 +238,7 @@ struct ncsi_package { struct ncsi_dev_priv *ndp; /* NCSI device */ spinlock_t lock; /* Protect the package */ unsigned int channel_num; /* Number of channels */ - struct list_head channels; /* List of chanels */ + struct list_head channels; /* List of channels */ struct list_head node; /* Form list of packages */ bool multi_channel; /* Enable multiple channels */ @@ -339,7 +339,7 @@ struct ncsi_cmd_arg { unsigned char type; /* Command in the NCSI packet */ unsigned char id; /* Request ID (sequence number) */ unsigned char package; /* Destination package ID */ - unsigned char channel; /* Detination channel ID or 0x1f */ + unsigned char channel; /* Destination channel ID or 0x1f */ unsigned short payload; /* Command packet payload length */ unsigned int req_flags; /* NCSI request properties */ union { diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index ffff8da707b8..ca04b6df1341 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -627,7 +627,7 @@ static int clear_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, return 0; } -/* Find an outstanding VLAN tag and constuct a "Set VLAN Filter - Enable" +/* Find an outstanding VLAN tag and construct a "Set VLAN Filter - Enable" * packet. */ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 86130dab3273..8b1611de01fe 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -19,6 +19,16 @@ config NETFILTER_FAMILY_BRIDGE config NETFILTER_FAMILY_ARP bool +config NETFILTER_NETLINK_HOOK + tristate "Netfilter base hook dump support" + depends on NETFILTER_ADVANCED + depends on NF_TABLES + select NETFILTER_NETLINK + help + If this option is enabled, the kernel will include support + to list the base netfilter hooks via NFNETLINK. + This is helpful for debugging. + config NETFILTER_NETLINK_ACCT tristate "Netfilter NFACCT over NFNETLINK interface" depends on NETFILTER_ADVANCED @@ -816,7 +826,7 @@ config NETFILTER_XT_TARGET_CLASSIFY the priority of a packet. Some qdiscs can use this value for classification, among these are: - atm, cbq, dsmark, pfifo_fast, htb, prio + atm, cbq, dsmark, pfifo_fast, htb, prio To compile it as a module, choose M here. If unsure, say N. diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index e935742fd273..24ec6a49a0dc 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o obj-$(CONFIG_NETFILTER_NETLINK_OSF) += nfnetlink_osf.o +obj-$(CONFIG_NETFILTER_NETLINK_HOOK) += nfnetlink_hook.o # connection tracking obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o @@ -73,7 +74,7 @@ obj-$(CONFIG_NF_DUP_NETDEV) += nf_dup_netdev.o nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \ nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \ - nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o \ + nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o nft_last.o \ nft_chain_route.o nf_tables_offload.o \ nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o \ nft_set_pipapo.o diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index de2d20c37cda..16ae92054baa 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1685,8 +1685,8 @@ static const struct nla_policy ip_set_adt_policy[IPSET_ATTR_CMD_MAX + 1] = { }; static int -call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, - struct nlattr *tb[], enum ipset_adt adt, +call_ad(struct net *net, struct sock *ctnl, struct sk_buff *skb, + struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 flags, bool use_lineno) { int ret; @@ -1738,8 +1738,7 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, *errline = lineno; - netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); + nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); /* Signal netlink not to send its ACK/errmsg. */ return -EINTR; } @@ -1783,7 +1782,7 @@ static int ip_set_ad(struct net *net, struct sock *ctnl, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; - ret = call_ad(ctnl, skb, set, tb, adt, flags, + ret = call_ad(net, ctnl, skb, set, tb, adt, flags, use_lineno); } else { int nla_rem; @@ -1794,7 +1793,7 @@ static int ip_set_ad(struct net *net, struct sock *ctnl, nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla, set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; - ret = call_ad(ctnl, skb, set, tb, adt, + ret = call_ad(net, ctnl, skb, set, tb, adt, flags, use_lineno); if (ret < 0) return ret; @@ -1859,7 +1858,6 @@ static int ip_set_header(struct sk_buff *skb, const struct nfnl_info *info, const struct ip_set *set; struct sk_buff *skb2; struct nlmsghdr *nlh2; - int ret = 0; if (unlikely(protocol_min_failed(attr) || !attr[IPSET_ATTR_SETNAME])) @@ -1885,12 +1883,7 @@ static int ip_set_header(struct sk_buff *skb, const struct nfnl_info *info, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret < 0) - return ret; - - return 0; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); nla_put_failure: nlmsg_cancel(skb2, nlh2); @@ -1945,12 +1938,7 @@ static int ip_set_type(struct sk_buff *skb, const struct nfnl_info *info, nlmsg_end(skb2, nlh2); pr_debug("Send TYPE, nlmsg_len: %u\n", nlh2->nlmsg_len); - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret < 0) - return ret; - - return 0; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); nla_put_failure: nlmsg_cancel(skb2, nlh2); @@ -1971,7 +1959,6 @@ static int ip_set_protocol(struct sk_buff *skb, const struct nfnl_info *info, { struct sk_buff *skb2; struct nlmsghdr *nlh2; - int ret = 0; if (unlikely(!attr[IPSET_ATTR_PROTOCOL])) return -IPSET_ERR_PROTOCOL; @@ -1990,12 +1977,7 @@ static int ip_set_protocol(struct sk_buff *skb, const struct nfnl_info *info, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret < 0) - return ret; - - return 0; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); nla_put_failure: nlmsg_cancel(skb2, nlh2); @@ -2014,7 +1996,6 @@ static int ip_set_byname(struct sk_buff *skb, const struct nfnl_info *info, struct nlmsghdr *nlh2; ip_set_id_t id = IPSET_INVALID_ID; const struct ip_set *set; - int ret = 0; if (unlikely(protocol_failed(attr) || !attr[IPSET_ATTR_SETNAME])) @@ -2038,12 +2019,7 @@ static int ip_set_byname(struct sk_buff *skb, const struct nfnl_info *info, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret < 0) - return ret; - - return 0; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); nla_put_failure: nlmsg_cancel(skb2, nlh2); @@ -2065,7 +2041,6 @@ static int ip_set_byindex(struct sk_buff *skb, const struct nfnl_info *info, struct nlmsghdr *nlh2; ip_set_id_t id = IPSET_INVALID_ID; const struct ip_set *set; - int ret = 0; if (unlikely(protocol_failed(attr) || !attr[IPSET_ATTR_INDEX])) @@ -2091,12 +2066,7 @@ static int ip_set_byindex(struct sk_buff *skb, const struct nfnl_info *info, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret < 0) - return ret; - - return 0; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); nla_put_failure: nlmsg_cancel(skb2, nlh2); diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index d61886874940..271da8447b29 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -318,7 +318,7 @@ config IP_VS_MH_TAB_INDEX comment 'IPVS application helper' config IP_VS_FTP - tristate "FTP protocol helper" + tristate "FTP protocol helper" depends on IP_VS_PROTO_TCP && NF_CONNTRACK && NF_NAT && \ NF_CONNTRACK_FTP select IP_VS_NFCT diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e0befcf8113a..96ba19fc8155 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -55,8 +55,6 @@ #include "nf_internals.h" -extern unsigned int nf_conntrack_net_id; - __cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS]; EXPORT_SYMBOL_GPL(nf_conntrack_locks); @@ -87,8 +85,6 @@ static __read_mostly bool nf_conntrack_locks_all; static struct conntrack_gc_work conntrack_gc_work; -extern unsigned int nf_conntrack_net_id; - void nf_conntrack_lock(spinlock_t *lock) __acquires(lock) { /* 1) Acquire the lock */ @@ -1404,7 +1400,7 @@ static void gc_worker(struct work_struct *work) continue; net = nf_ct_net(tmp); - cnet = net_generic(net, nf_conntrack_net_id); + cnet = nf_ct_pernet(net); if (atomic_read(&cnet->count) < nf_conntrack_max95) continue; @@ -1484,7 +1480,7 @@ __nf_conntrack_alloc(struct net *net, const struct nf_conntrack_tuple *repl, gfp_t gfp, u32 hash) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); unsigned int ct_count; struct nf_conn *ct; @@ -1556,7 +1552,7 @@ void nf_conntrack_free(struct nf_conn *ct) nf_ct_ext_destroy(ct); kmem_cache_free(nf_conntrack_cachep, ct); - cnet = net_generic(net, nf_conntrack_net_id); + cnet = nf_ct_pernet(net); smp_mb__before_atomic(); atomic_dec(&cnet->count); @@ -1614,7 +1610,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, GFP_ATOMIC); local_bh_disable(); - cnet = net_generic(net, nf_conntrack_net_id); + cnet = nf_ct_pernet(net); if (cnet->expect_count) { spin_lock(&nf_conntrack_expect_lock); exp = nf_ct_find_expectation(net, zone, tuple); @@ -2317,7 +2313,7 @@ __nf_ct_unconfirmed_destroy(struct net *net) void nf_ct_unconfirmed_destroy(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); might_sleep(); @@ -2333,7 +2329,7 @@ void nf_ct_iterate_cleanup_net(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data, u32 portid, int report) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct iter_data d; might_sleep(); @@ -2367,7 +2363,7 @@ nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data) down_read(&net_rwsem); for_each_net(net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); if (atomic_read(&cnet->count) == 0) continue; @@ -2449,7 +2445,7 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list) i_see_dead_people: busy = 0; list_for_each_entry(net, net_exit_list, exit_list) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); nf_ct_iterate_cleanup(kill_all, net, 0, 0); if (atomic_read(&cnet->count) != 0) @@ -2733,7 +2729,7 @@ void nf_conntrack_init_end(void) int nf_conntrack_init_net(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); int ret = -ENOMEM; int cpu; diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 759d87aef95f..296e4a171bd1 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -27,8 +27,6 @@ #include #include -extern unsigned int nf_conntrack_net_id; - static DEFINE_MUTEX(nf_ct_ecache_mutex); #define ECACHE_RETRY_WAIT (HZ/10) @@ -348,7 +346,7 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier); void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); if (state == NFCT_ECACHE_DESTROY_FAIL && !delayed_work_pending(&cnet->ecache_dwork)) { @@ -371,7 +369,7 @@ static const struct nf_ct_ext_type event_extend = { void nf_conntrack_ecache_pernet_init(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); net->ct.sysctl_events = nf_ct_events; cnet->ct_net = &net->ct; @@ -380,7 +378,7 @@ void nf_conntrack_ecache_pernet_init(struct net *net) void nf_conntrack_ecache_pernet_fini(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); cancel_delayed_work_sync(&cnet->ecache_dwork); } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index efdd391b3f72..1e851bc2e61a 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -43,8 +43,6 @@ unsigned int nf_ct_expect_max __read_mostly; static struct kmem_cache *nf_ct_expect_cachep __read_mostly; static unsigned int nf_ct_expect_hashrnd __read_mostly; -extern unsigned int nf_conntrack_net_id; - /* nf_conntrack_expect helper functions */ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, u32 portid, int report) @@ -58,7 +56,7 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, hlist_del_rcu(&exp->hnode); - cnet = net_generic(net, nf_conntrack_net_id); + cnet = nf_ct_pernet(net); cnet->expect_count--; hlist_del_rcu(&exp->lnode); @@ -123,7 +121,7 @@ __nf_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct nf_conntrack_expect *i; unsigned int h; @@ -164,7 +162,7 @@ nf_ct_find_expectation(struct net *net, const struct nf_conntrack_zone *zone, const struct nf_conntrack_tuple *tuple) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct nf_conntrack_expect *i, *exp = NULL; unsigned int h; @@ -397,7 +395,7 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) master_help->expecting[exp->class]++; hlist_add_head_rcu(&exp->hnode, &nf_ct_expect_hash[h]); - cnet = net_generic(net, nf_conntrack_net_id); + cnet = nf_ct_pernet(net); cnet->expect_count++; NF_CT_STAT_INC(net, expect_create); @@ -468,7 +466,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, } } - cnet = net_generic(net, nf_conntrack_net_id); + cnet = nf_ct_pernet(net); if (cnet->expect_count >= nf_ct_expect_max) { net_warn_ratelimited("nf_conntrack: expectation table full\n"); ret = -EMFILE; diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index aafaff00baf1..2eb31ffb3d14 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -194,7 +194,7 @@ static int get_tpkt_data(struct sk_buff *skb, unsigned int protoff, if (tcpdatalen == 4) { /* Separate TPKT header */ /* Netmeeting sends TPKT header and data separately */ pr_debug("nf_ct_h323: separate TPKT header indicates " - "there will be TPKT data of %hu bytes\n", + "there will be TPKT data of %d bytes\n", tpktlen - 4); info->tpkt_len[dir] = tpktlen - 4; return 0; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index ac396cc8bfae..ae4488a13c70 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -43,8 +43,6 @@ MODULE_PARM_DESC(nf_conntrack_helper, static DEFINE_MUTEX(nf_ct_nat_helpers_mutex); static struct list_head nf_ct_nat_helpers __read_mostly; -extern unsigned int nf_conntrack_net_id; - /* Stupid hash, but collision free for the default registrations of the * helpers currently in the kernel. */ static unsigned int helper_hash(const struct nf_conntrack_tuple *tuple) @@ -214,7 +212,7 @@ EXPORT_SYMBOL_GPL(nf_ct_helper_ext_add); static struct nf_conntrack_helper * nf_ct_lookup_helper(struct nf_conn *ct, struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); if (!cnet->sysctl_auto_assign_helper) { if (cnet->auto_assign_helper_warned) @@ -560,7 +558,7 @@ static const struct nf_ct_ext_type helper_extend = { void nf_conntrack_helper_pernet_init(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); cnet->sysctl_auto_assign_helper = nf_ct_auto_assign_helper; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 8690fc07030f..4e1a9dba7077 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1528,7 +1528,7 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); + u8 family = info->nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; @@ -1541,12 +1541,12 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb, if (cda[CTA_TUPLE_ORIG]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, - nfmsg->nfgen_family, &zone); + family, &zone); else if (cda[CTA_TUPLE_REPLY]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, - nfmsg->nfgen_family, &zone); + family, &zone); else { - u_int8_t u3 = nfmsg->version ? nfmsg->nfgen_family : AF_UNSPEC; + u_int8_t u3 = info->nfmsg->version ? family : AF_UNSPEC; return ctnetlink_flush_conntrack(info->net, cda, NETLINK_CB(skb).portid, @@ -1586,8 +1586,7 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; @@ -1628,9 +1627,8 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb, ct = nf_ct_tuplehash_to_ctrack(h); - err = -ENOMEM; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb2 == NULL) { + if (!skb2) { nf_ct_put(ct); return -ENOMEM; } @@ -1640,21 +1638,12 @@ static int ctnetlink_get_conntrack(struct sk_buff *skb, NFNL_MSG_TYPE(info->nlh->nlmsg_type), ct, true, 0); nf_ct_put(ct); - if (err <= 0) - goto free; + if (err <= 0) { + kfree_skb(skb2); + return -ENOMEM; + } - err = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (err < 0) - goto out; - - return 0; - -free: - kfree_skb(skb2); -out: - /* this avoids a loop in nfnetlink. */ - return err == -EAGAIN ? -ENOBUFS : err; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static int ctnetlink_done_list(struct netlink_callback *cb) @@ -2373,10 +2362,9 @@ static int ctnetlink_new_conntrack(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_zone zone; struct nf_conn *ct; int err; @@ -2590,21 +2578,12 @@ static int ctnetlink_stat_ct(struct sk_buff *skb, const struct nfnl_info *info, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), sock_net(skb->sk)); - if (err <= 0) - goto free; + if (err <= 0) { + kfree_skb(skb2); + return -ENOMEM; + } - err = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (err < 0) - goto out; - - return 0; - -free: - kfree_skb(skb2); -out: - /* this avoids a loop in nfnetlink. */ - return err == -EAGAIN ? -ENOBUFS : err; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = { @@ -3278,8 +3257,7 @@ static int ctnetlink_get_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nf_conntrack_zone zone; @@ -3329,11 +3307,10 @@ static int ctnetlink_get_expect(struct sk_buff *skb, } } - err = -ENOMEM; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb2 == NULL) { + if (!skb2) { nf_ct_expect_put(exp); - goto out; + return -ENOMEM; } rcu_read_lock(); @@ -3342,21 +3319,12 @@ static int ctnetlink_get_expect(struct sk_buff *skb, exp); rcu_read_unlock(); nf_ct_expect_put(exp); - if (err <= 0) - goto free; + if (err <= 0) { + kfree_skb(skb2); + return -ENOMEM; + } - err = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (err < 0) - goto out; - - return 0; - -free: - kfree_skb(skb2); -out: - /* this avoids a loop in nfnetlink. */ - return err == -EAGAIN ? -ENOBUFS : err; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static bool expect_iter_name(struct nf_conntrack_expect *exp, void *data) @@ -3378,8 +3346,7 @@ static int ctnetlink_del_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_expect *exp; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; @@ -3630,8 +3597,7 @@ static int ctnetlink_new_expect(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int8_t u3 = nfmsg->nfgen_family; + u_int8_t u3 = info->nfmsg->nfgen_family; struct nf_conntrack_tuple tuple; struct nf_conntrack_expect *exp; struct nf_conntrack_zone zone; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index dc9ca12b0489..55647409a9be 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -42,17 +42,16 @@ #include #include -extern unsigned int nf_conntrack_net_id; - static DEFINE_MUTEX(nf_ct_proto_mutex); #ifdef CONFIG_SYSCTL -__printf(5, 6) +__printf(4, 5) void nf_l4proto_log_invalid(const struct sk_buff *skb, - struct net *net, - u16 pf, u8 protonum, + const struct nf_hook_state *state, + u8 protonum, const char *fmt, ...) { + struct net *net = state->net; struct va_format vaf; va_list args; @@ -64,15 +63,16 @@ void nf_l4proto_log_invalid(const struct sk_buff *skb, vaf.fmt = fmt; vaf.va = &args; - nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, - "nf_ct_proto_%d: %pV ", protonum, &vaf); + nf_log_packet(net, state->pf, 0, skb, state->in, state->out, + NULL, "nf_ct_proto_%d: %pV ", protonum, &vaf); va_end(args); } EXPORT_SYMBOL_GPL(nf_l4proto_log_invalid); -__printf(3, 4) +__printf(4, 5) void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const struct nf_conn *ct, + const struct nf_hook_state *state, const char *fmt, ...) { struct va_format vaf; @@ -87,7 +87,7 @@ void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, vaf.fmt = fmt; vaf.va = &args; - nf_l4proto_log_invalid(skb, net, nf_ct_l3num(ct), + nf_l4proto_log_invalid(skb, state, nf_ct_protonum(ct), "%pV", &vaf); va_end(args); } @@ -446,7 +446,7 @@ static struct nf_ct_bridge_info *nf_ct_bridge_info; static int nf_ct_netns_do_get(struct net *net, u8 nfproto) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); bool fixup_needed = false, retry = true; int err = 0; retry: @@ -531,7 +531,7 @@ retry: static void nf_ct_netns_do_put(struct net *net, u8 nfproto) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); mutex_lock(&nf_ct_proto_mutex); switch (nfproto) { diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 4f33307fa3cf..c1557d47ccd1 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -382,7 +382,8 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = static noinline bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, - const struct dccp_hdr *dh) + const struct dccp_hdr *dh, + const struct nf_hook_state *hook_state) { struct net *net = nf_ct_net(ct); struct nf_dccp_net *dn; @@ -414,7 +415,7 @@ dccp_new(struct nf_conn *ct, const struct sk_buff *skb, return true; out_invalid: - nf_ct_l4proto_log_invalid(skb, ct, "%s", msg); + nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%s", msg); return false; } @@ -464,8 +465,7 @@ static bool dccp_error(const struct dccp_hdr *dh, } return false; out_invalid: - nf_l4proto_log_invalid(skb, state->net, state->pf, - IPPROTO_DCCP, "%s", msg); + nf_l4proto_log_invalid(skb, state, IPPROTO_DCCP, "%s", msg); return true; } @@ -488,7 +488,7 @@ int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, return -NF_ACCEPT; type = dh->dccph_type; - if (!nf_ct_is_confirmed(ct) && !dccp_new(ct, skb, dh)) + if (!nf_ct_is_confirmed(ct) && !dccp_new(ct, skb, dh, state)) return -NF_ACCEPT; if (type == DCCP_PKT_RESET && @@ -543,11 +543,11 @@ int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, ct->proto.dccp.last_pkt = type; spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "%s", "invalid packet"); + nf_ct_l4proto_log_invalid(skb, ct, state, "%s", "invalid packet"); return NF_ACCEPT; case CT_DCCP_INVALID: spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "%s", "invalid state transition"); + nf_ct_l4proto_log_invalid(skb, ct, state, "%s", "invalid state transition"); return -NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 4efd8741c105..b38b7164acd5 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -170,12 +170,12 @@ int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb, ct_daddr = &ct->tuplehash[dir].tuple.dst.u3; if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) { if (state->pf == AF_INET) { - nf_l4proto_log_invalid(skb, state->net, state->pf, + nf_l4proto_log_invalid(skb, state, l4proto, "outer daddr %pI4 != inner %pI4", &outer_daddr->ip, &ct_daddr->ip); } else if (state->pf == AF_INET6) { - nf_l4proto_log_invalid(skb, state->net, state->pf, + nf_l4proto_log_invalid(skb, state, l4proto, "outer daddr %pI6 != inner %pI6", &outer_daddr->ip6, &ct_daddr->ip6); @@ -197,8 +197,7 @@ static void icmp_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { - nf_l4proto_log_invalid(skb, state->net, state->pf, - IPPROTO_ICMP, "%s", msg); + nf_l4proto_log_invalid(skb, state, IPPROTO_ICMP, "%s", msg); } /* Small and modified version of icmp_rcv */ diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index facd8c64ec4e..61e3b05cf02c 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -126,8 +126,7 @@ static void icmpv6_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { - nf_l4proto_log_invalid(skb, state->net, state->pf, - IPPROTO_ICMPV6, "%s", msg); + nf_l4proto_log_invalid(skb, state, IPPROTO_ICMPV6, "%s", msg); } int nf_conntrack_icmpv6_error(struct nf_conn *tmpl, diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index fb8dc02e502f..2394238d01c9 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -351,7 +351,7 @@ static bool sctp_error(struct sk_buff *skb, } return false; out_invalid: - nf_l4proto_log_invalid(skb, state->net, state->pf, IPPROTO_SCTP, "%s", logmsg); + nf_l4proto_log_invalid(skb, state, IPPROTO_SCTP, "%s", logmsg); return true; } diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 34e22416a721..f7e8baf59b51 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -446,14 +446,15 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, } } -static bool tcp_in_window(const struct nf_conn *ct, - struct ip_ct_tcp *state, +static bool tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, unsigned int index, const struct sk_buff *skb, unsigned int dataoff, - const struct tcphdr *tcph) + const struct tcphdr *tcph, + const struct nf_hook_state *hook_state) { + struct ip_ct_tcp *state = &ct->proto.tcp; struct net *net = nf_ct_net(ct); struct nf_tcp_net *tn = nf_tcp_pernet(net); struct ip_ct_tcp_state *sender = &state->seen[dir]; @@ -670,7 +671,7 @@ static bool tcp_in_window(const struct nf_conn *ct, tn->tcp_be_liberal) res = true; if (!res) { - nf_ct_l4proto_log_invalid(skb, ct, + nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%s", before(seq, sender->td_maxend + 1) ? in_recv_win ? @@ -710,7 +711,7 @@ static void tcp_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { - nf_l4proto_log_invalid(skb, state->net, state->pf, IPPROTO_TCP, "%s", msg); + nf_l4proto_log_invalid(skb, state, IPPROTO_TCP, "%s", msg); } /* Protect conntrack agaist broken packets. Code taken from ipt_unclean.c. */ @@ -970,7 +971,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, IP_CT_EXP_CHALLENGE_ACK; } spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, + nf_ct_l4proto_log_invalid(skb, ct, state, "packet (index %d) in dir %d ignored, state %s", index, dir, tcp_conntrack_names[old_state]); @@ -995,7 +996,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n", dir, get_conntrack_index(th), old_state); spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "invalid state"); + nf_ct_l4proto_log_invalid(skb, ct, state, "invalid state"); return -NF_ACCEPT; case TCP_CONNTRACK_TIME_WAIT: /* RFC5961 compliance cause stack to send "challenge-ACK" @@ -1010,7 +1011,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, /* Detected RFC5961 challenge ACK */ ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "challenge-ack ignored"); + nf_ct_l4proto_log_invalid(skb, ct, state, "challenge-ack ignored"); return NF_ACCEPT; /* Don't change state */ } break; @@ -1035,7 +1036,7 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) { /* Invalid RST */ spin_unlock_bh(&ct->lock); - nf_ct_l4proto_log_invalid(skb, ct, "invalid rst"); + nf_ct_l4proto_log_invalid(skb, ct, state, "invalid rst"); return -NF_ACCEPT; } @@ -1079,8 +1080,8 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, break; } - if (!tcp_in_window(ct, &ct->proto.tcp, dir, index, - skb, dataoff, th)) { + if (!tcp_in_window(ct, dir, index, + skb, dataoff, th, state)) { spin_unlock_bh(&ct->lock); return -NF_ACCEPT; } @@ -1441,6 +1442,11 @@ void nf_conntrack_tcp_init_net(struct net *net) * will be started. */ tn->tcp_max_retrans = 3; + +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + tn->offload_timeout = 30 * HZ; + tn->offload_pickup = 120 * HZ; +#endif } const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp = diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index af402f458ee0..698fee49e732 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -38,8 +38,7 @@ static void udp_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { - nf_l4proto_log_invalid(skb, state->net, state->pf, - IPPROTO_UDP, "%s", msg); + nf_l4proto_log_invalid(skb, state, IPPROTO_UDP, "%s", msg); } static bool udp_error(struct sk_buff *skb, @@ -130,8 +129,7 @@ static void udplite_error_log(const struct sk_buff *skb, const struct nf_hook_state *state, const char *msg) { - nf_l4proto_log_invalid(skb, state->net, state->pf, - IPPROTO_UDPLITE, "%s", msg); + nf_l4proto_log_invalid(skb, state, IPPROTO_UDPLITE, "%s", msg); } static bool udplite_error(struct sk_buff *skb, @@ -270,6 +268,11 @@ void nf_conntrack_udp_init_net(struct net *net) for (i = 0; i < UDP_CT_MAX; i++) un->timeouts[i] = udp_timeouts[i]; + +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + un->offload_timeout = 30 * HZ; + un->offload_pickup = 30 * HZ; +#endif } const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp = diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index aaa55246d0ca..f57a951c9b5e 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -512,9 +512,7 @@ static void nf_conntrack_standalone_fini_proc(struct net *net) u32 nf_conntrack_count(const struct net *net) { - const struct nf_conntrack_net *cnet; - - cnet = net_generic(net, nf_conntrack_net_id); + const struct nf_conntrack_net *cnet = nf_ct_pernet(net); return atomic_read(&cnet->count); } @@ -575,11 +573,19 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_RETRANS, NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK, +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD, + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP, +#endif NF_SYSCTL_CT_PROTO_TCP_LOOSE, NF_SYSCTL_CT_PROTO_TCP_LIBERAL, NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP, NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM, +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD, + NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP, +#endif NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP, NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6, #ifdef CONFIG_NF_CT_PROTO_SCTP @@ -762,6 +768,20 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD] = { + .procname = "nf_flowtable_tcp_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP] = { + .procname = "nf_flowtable_tcp_pickup", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, +#endif [NF_SYSCTL_CT_PROTO_TCP_LOOSE] = { .procname = "nf_conntrack_tcp_loose", .maxlen = sizeof(u8), @@ -796,6 +816,20 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, +#if IS_ENABLED(CONFIG_NFT_FLOW_OFFLOAD) + [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD] = { + .procname = "nf_flowtable_udp_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP] = { + .procname = "nf_flowtable_udp_pickup", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, +#endif [NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = { .procname = "nf_conntrack_icmp_timeout", .maxlen = sizeof(unsigned int), @@ -971,6 +1005,12 @@ static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, XASSIGN(LIBERAL, &tn->tcp_be_liberal); XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans); #undef XASSIGN + +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD].data = &tn->offload_timeout; + table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_OFFLOAD_PICKUP].data = &tn->offload_pickup; +#endif + } static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net, @@ -1032,7 +1072,7 @@ static void nf_conntrack_standalone_init_gre_sysctl(struct net *net, static int nf_conntrack_standalone_init_sysctl(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct nf_udp_net *un = nf_udp_pernet(net); struct ctl_table *table; @@ -1059,6 +1099,10 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6].data = &nf_icmpv6_pernet(net)->timeout; table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP].data = &un->timeouts[UDP_CT_UNREPLIED]; table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED]; +#if IS_ENABLED(CONFIG_NF_FLOW_TABLE) + table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD].data = &un->offload_timeout; + table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_OFFLOAD_PICKUP].data = &un->offload_pickup; +#endif nf_conntrack_standalone_init_tcp_sysctl(net, table); nf_conntrack_standalone_init_sctp_sysctl(net, table); @@ -1085,7 +1129,7 @@ out_unregister_netfilter: static void nf_conntrack_standalone_fini_sysctl(struct net *net) { - struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + struct nf_conntrack_net *cnet = nf_ct_pernet(net); struct ctl_table *table; table = cnet->sysctl_header->ctl_table_arg; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 1d02650dd715..1e50908b1b7e 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -178,12 +178,10 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) tcp->seen[1].td_maxwin = 0; } -#define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT (120 * HZ) -#define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT (30 * HZ) - static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) { const struct nf_conntrack_l4proto *l4proto; + struct net *net = nf_ct_net(ct); int l4num = nf_ct_protonum(ct); unsigned int timeout; @@ -191,12 +189,17 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) if (!l4proto) return; - if (l4num == IPPROTO_TCP) - timeout = NF_FLOWTABLE_TCP_PICKUP_TIMEOUT; - else if (l4num == IPPROTO_UDP) - timeout = NF_FLOWTABLE_UDP_PICKUP_TIMEOUT; - else + if (l4num == IPPROTO_TCP) { + struct nf_tcp_net *tn = nf_tcp_pernet(net); + + timeout = tn->offload_pickup; + } else if (l4num == IPPROTO_UDP) { + struct nf_udp_net *tn = nf_udp_pernet(net); + + timeout = tn->offload_pickup; + } else { return; + } if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout) ct->timeout = nfct_time_stamp + timeout; @@ -268,11 +271,35 @@ static const struct rhashtable_params nf_flow_offload_rhash_params = { .automatic_shrinking = true, }; +unsigned long flow_offload_get_timeout(struct flow_offload *flow) +{ + const struct nf_conntrack_l4proto *l4proto; + unsigned long timeout = NF_FLOW_TIMEOUT; + struct net *net = nf_ct_net(flow->ct); + int l4num = nf_ct_protonum(flow->ct); + + l4proto = nf_ct_l4proto_find(l4num); + if (!l4proto) + return timeout; + + if (l4num == IPPROTO_TCP) { + struct nf_tcp_net *tn = nf_tcp_pernet(net); + + timeout = tn->offload_timeout; + } else if (l4num == IPPROTO_UDP) { + struct nf_udp_net *tn = nf_udp_pernet(net); + + timeout = tn->offload_timeout; + } + + return timeout; +} + int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) { int err; - flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; + flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); err = rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[0].node, @@ -304,7 +331,7 @@ EXPORT_SYMBOL_GPL(flow_offload_add); void flow_offload_refresh(struct nf_flowtable *flow_table, struct flow_offload *flow) { - flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; + flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow); if (likely(!nf_flowtable_hw_offload(flow_table))) return; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 528b2f172684..f92006cec94c 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -937,7 +937,7 @@ static void flow_offload_work_stats(struct flow_offload_work *offload) lastused = max_t(u64, stats[0].lastused, stats[1].lastused); offload->flow->timeout = max_t(u64, offload->flow->timeout, - lastused + NF_FLOW_TIMEOUT); + lastused + flow_offload_get_timeout(offload->flow)); if (offload->flowtable->flags & NF_FLOWTABLE_COUNTER) { if (stats[0].pkts) @@ -1041,7 +1041,7 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable, __s32 delta; delta = nf_flow_timeout_delta(flow->timeout); - if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10)) + if ((delta >= (9 * flow_offload_get_timeout(flow)) / 10)) return; offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_STATS); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index bf4d6ec9fc55..390d4466567f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -571,7 +571,7 @@ static struct nft_table *nft_table_lookup(const struct net *net, table->family == family && nft_active_genmask(table, genmask)) { if (nft_table_has_owner(table) && - table->nlpid != nlpid) + nlpid && table->nlpid != nlpid) return ERR_PTR(-EPERM); return table; @@ -583,7 +583,7 @@ static struct nft_table *nft_table_lookup(const struct net *net, static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, - u8 genmask) + u8 genmask, u32 nlpid) { struct nftables_pernet *nft_net; struct nft_table *table; @@ -591,8 +591,13 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net, nft_net = nft_pernet(net); list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && - nft_active_genmask(table, genmask)) + nft_active_genmask(table, genmask)) { + if (nft_table_has_owner(table) && + nlpid && table->nlpid != nlpid) + return ERR_PTR(-EPERM); + return table; + } } return ERR_PTR(-ENOENT); @@ -862,10 +867,9 @@ static int nft_netlink_dump_start_rcu(struct sock *nlsk, struct sk_buff *skb, static int nf_tables_gettable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_table *table; struct net *net = info->net; struct sk_buff *skb2; @@ -1068,10 +1072,9 @@ static int nf_tables_newtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; @@ -1263,10 +1266,9 @@ out: static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; @@ -1279,7 +1281,8 @@ static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_TABLE_HANDLE]) { attr = nla[NFTA_TABLE_HANDLE]; - table = nft_table_lookup_byhandle(net, attr, genmask); + table = nft_table_lookup_byhandle(net, attr, genmask, + NETLINK_CB(skb).portid); } else { attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask, @@ -1636,10 +1639,9 @@ done: static int nf_tables_getchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_chain *chain; struct net *net = info->net; struct nft_table *table; @@ -2015,11 +2017,12 @@ static void nft_basechain_hook_init(struct nf_hook_ops *ops, u8 family, const struct nft_chain_hook *hook, struct nft_chain *chain) { - ops->pf = family; - ops->hooknum = hook->num; - ops->priority = hook->priority; - ops->priv = chain; - ops->hook = hook->type->hooks[ops->hooknum]; + ops->pf = family; + ops->hooknum = hook->num; + ops->priority = hook->priority; + ops->priv = chain; + ops->hook = hook->type->hooks[ops->hooknum]; + ops->hook_ops_type = NF_HOOK_OP_NF_TABLES; } static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, @@ -2371,10 +2374,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct nft_chain *chain = NULL; struct net *net = info->net; const struct nlattr *attr; @@ -2469,10 +2471,9 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, static int nf_tables_delchain(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; @@ -3096,10 +3097,9 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb) static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_chain *chain; const struct nft_rule *rule; struct net *net = info->net; @@ -3237,15 +3237,14 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { struct nftables_pernet *nft_net = nft_pernet(info->net); - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; unsigned int size, i, n, ulen = 0, usize = 0; u8 genmask = nft_genmask_next(info->net); struct nft_rule *rule, *old_rule = NULL; struct nft_expr_info *expr_info = NULL; - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; + struct nft_flow_rule *flow = NULL; struct net *net = info->net; - struct nft_flow_rule *flow; struct nft_userdata *udata; struct nft_table *table; struct nft_chain *chain; @@ -3340,13 +3339,13 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, nla_for_each_nested(tmp, nla[NFTA_RULE_EXPRESSIONS], rem) { err = -EINVAL; if (nla_type(tmp) != NFTA_LIST_ELEM) - goto err1; + goto err_release_expr; if (n == NFT_RULE_MAXEXPRS) - goto err1; + goto err_release_expr; err = nf_tables_expr_parse(&ctx, tmp, &expr_info[n]); if (err < 0) { NL_SET_BAD_ATTR(extack, tmp); - goto err1; + goto err_release_expr; } size += expr_info[n].ops->size; n++; @@ -3355,7 +3354,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, /* Check for overflow of dlen field */ err = -EFBIG; if (size >= 1 << 12) - goto err1; + goto err_release_expr; if (nla[NFTA_RULE_USERDATA]) { ulen = nla_len(nla[NFTA_RULE_USERDATA]); @@ -3366,7 +3365,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, err = -ENOMEM; rule = kzalloc(sizeof(*rule) + size + usize, GFP_KERNEL); if (rule == NULL) - goto err1; + goto err_release_expr; nft_activate_next(net, rule); @@ -3385,7 +3384,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, err = nf_tables_newexpr(&ctx, &expr_info[i], expr); if (err < 0) { NL_SET_BAD_ATTR(extack, expr_info[i].attr); - goto err2; + goto err_release_rule; } if (expr_info[i].ops->validate) @@ -3395,16 +3394,24 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, expr = nft_expr_next(expr); } + if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { + flow = nft_flow_rule_create(net, rule); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto err_release_rule; + } + } + if (info->nlh->nlmsg_flags & NLM_F_REPLACE) { trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; - goto err2; + goto err_destroy_flow_rule; } err = nft_delrule(&ctx, old_rule); if (err < 0) { nft_trans_destroy(trans); - goto err2; + goto err_destroy_flow_rule; } list_add_tail_rcu(&rule->list, &old_rule->list); @@ -3412,7 +3419,7 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (!trans) { err = -ENOMEM; - goto err2; + goto err_destroy_flow_rule; } if (info->nlh->nlmsg_flags & NLM_F_APPEND) { @@ -3430,21 +3437,19 @@ static int nf_tables_newrule(struct sk_buff *skb, const struct nfnl_info *info, kvfree(expr_info); chain->use++; + if (flow) + nft_trans_flow_rule(trans) = flow; + if (nft_net->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); - if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { - flow = nft_flow_rule_create(net, rule); - if (IS_ERR(flow)) - return PTR_ERR(flow); - - nft_trans_flow_rule(trans) = flow; - } - return 0; -err2: + +err_destroy_flow_rule: + nft_flow_rule_destroy(flow); +err_release_rule: nf_tables_rule_release(&ctx, rule); -err1: +err_release_expr: for (i = 0; i < n; i++) { if (expr_info[i].ops) { module_put(expr_info[i].ops->type->owner); @@ -3477,15 +3482,15 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; - int family = nfmsg->nfgen_family, err = 0; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; struct nft_chain *chain = NULL; struct net *net = info->net; struct nft_table *table; struct nft_rule *rule; struct nft_ctx ctx; + int err = 0; table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, NETLINK_CB(skb).portid); @@ -3665,30 +3670,6 @@ static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = { [NFTA_SET_DESC_CONCAT] = { .type = NLA_NESTED }, }; -static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, - const struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack, - u8 genmask, u32 nlpid) -{ - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - int family = nfmsg->nfgen_family; - struct nft_table *table = NULL; - - if (nla[NFTA_SET_TABLE] != NULL) { - table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, - genmask, nlpid); - if (IS_ERR(table)) { - NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); - return PTR_ERR(table); - } - } - - nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla); - return 0; -} - static struct nft_set *nft_set_lookup(const struct nft_table *table, const struct nlattr *nla, u8 genmask) { @@ -4068,20 +4049,26 @@ static int nf_tables_dump_sets_done(struct netlink_callback *cb) static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); + u8 family = info->nfmsg->nfgen_family; + struct nft_table *table = NULL; struct net *net = info->net; const struct nft_set *set; struct sk_buff *skb2; struct nft_ctx ctx; int err; - /* Verify existence before starting dump */ - err = nft_ctx_init_from_setattr(&ctx, net, skb, info->nlh, nla, extack, - genmask, 0); - if (err < 0) - return err; + if (nla[NFTA_SET_TABLE]) { + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, + genmask, 0); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); + return PTR_ERR(table); + } + } + + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { @@ -4096,12 +4083,12 @@ static int nf_tables_getset(struct sk_buff *skb, const struct nfnl_info *info, } /* Only accept unspec with dump */ - if (nfmsg->nfgen_family == NFPROTO_UNSPEC) + if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC) return -EAFNOSUPPORT; if (!nla[NFTA_SET_TABLE]) return -EINVAL; - set = nft_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask); + set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) return PTR_ERR(set); @@ -4189,11 +4176,10 @@ static int nf_tables_set_desc_parse(struct nft_set_desc *desc, static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); u32 ktype, dtype, flags, policy, gc_int, objtype; struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_set_ops *ops; struct nft_expr *expr = NULL; struct net *net = info->net; @@ -4494,31 +4480,31 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; + struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; - int err; - if (nfmsg->nfgen_family == NFPROTO_UNSPEC) + if (info->nfmsg->nfgen_family == NFPROTO_UNSPEC) return -EAFNOSUPPORT; - if (nla[NFTA_SET_TABLE] == NULL) - return -EINVAL; - err = nft_ctx_init_from_setattr(&ctx, net, skb, info->nlh, nla, extack, - genmask, NETLINK_CB(skb).portid); - if (err < 0) - return err; + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, + genmask, NETLINK_CB(skb).portid); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); + return PTR_ERR(table); + } if (nla[NFTA_SET_HANDLE]) { attr = nla[NFTA_SET_HANDLE]; - set = nft_set_lookup_byhandle(ctx.table, attr, genmask); + set = nft_set_lookup_byhandle(table, attr, genmask); } else { attr = nla[NFTA_SET_NAME]; - set = nft_set_lookup(ctx.table, attr, genmask); + set = nft_set_lookup(table, attr, genmask); } if (IS_ERR(set)) { @@ -4532,6 +4518,8 @@ static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, return -EBUSY; } + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + return nft_delset(&ctx, set); } @@ -4733,28 +4721,6 @@ static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + [NFTA_SET_ELEM_LIST_SET_ID] = { .type = NLA_U32 }, }; -static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net, - const struct sk_buff *skb, - const struct nlmsghdr *nlh, - const struct nlattr * const nla[], - struct netlink_ext_ack *extack, - u8 genmask, u32 nlpid) -{ - const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - int family = nfmsg->nfgen_family; - struct nft_table *table; - - table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, - genmask, nlpid); - if (IS_ERR(table)) { - NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); - return PTR_ERR(table); - } - - nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla); - return 0; -} - static int nft_set_elem_expr_dump(struct sk_buff *skb, const struct nft_set *set, const struct nft_set_ext *ext) @@ -5212,21 +5178,27 @@ static int nf_tables_getsetelem(struct sk_buff *skb, { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; + struct nft_table *table; struct nft_set *set; struct nlattr *attr; struct nft_ctx ctx; int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, info->nlh, nla, extack, - genmask, NETLINK_CB(skb).portid); - if (err < 0) - return err; + table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, + genmask, NETLINK_CB(skb).portid); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); + return PTR_ERR(table); + } - set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask); + set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_set_start, @@ -5995,8 +5967,10 @@ static int nf_tables_newsetelem(struct sk_buff *skb, struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; + struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; int rem, err; @@ -6004,12 +5978,14 @@ static int nf_tables_newsetelem(struct sk_buff *skb, if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, info->nlh, nla, extack, - genmask, NETLINK_CB(skb).portid); - if (err < 0) - return err; + table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, + genmask, NETLINK_CB(skb).portid); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); + return PTR_ERR(table); + } - set = nft_set_lookup_global(net, ctx.table, nla[NFTA_SET_ELEM_LIST_SET], + set = nft_set_lookup_global(net, table, nla[NFTA_SET_ELEM_LIST_SET], nla[NFTA_SET_ELEM_LIST_SET_ID], genmask); if (IS_ERR(set)) return PTR_ERR(set); @@ -6017,6 +5993,8 @@ static int nf_tables_newsetelem(struct sk_buff *skb, if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) return -EBUSY; + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_add_set_elem(&ctx, set, attr, info->nlh->nlmsg_flags); if (err < 0) @@ -6024,7 +6002,7 @@ static int nf_tables_newsetelem(struct sk_buff *skb, } if (nft_net->validate_state == NFT_VALIDATE_DO) - return nft_table_validate(net, ctx.table); + return nft_table_validate(net, table); return 0; } @@ -6262,23 +6240,29 @@ static int nf_tables_delsetelem(struct sk_buff *skb, { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; + struct nft_table *table; struct nft_set *set; struct nft_ctx ctx; int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, info->nlh, nla, extack, - genmask, NETLINK_CB(skb).portid); - if (err < 0) - return err; + table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, + genmask, NETLINK_CB(skb).portid); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); + return PTR_ERR(table); + } - set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask); + set = nft_set_lookup(table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) return -EBUSY; + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) return nft_set_flush(&ctx, set, genmask); @@ -6546,11 +6530,10 @@ err_free_trans: static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nft_object_type *type; - int family = nfmsg->nfgen_family; struct net *net = info->net; struct nft_table *table; struct nft_object *obj; @@ -6802,10 +6785,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; const struct nft_table *table; struct net *net = info->net; struct nft_object *obj; @@ -6892,10 +6874,9 @@ static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct net *net = info->net; const struct nlattr *attr; struct nft_table *table; @@ -7323,12 +7304,11 @@ static int nf_tables_newflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; struct nft_flowtable_hook flowtable_hook; u8 genmask = nft_genmask_next(info->net); + u8 family = info->nfmsg->nfgen_family; const struct nf_flowtable_type *type; - int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; struct nft_hook *hook, *next; struct net *net = info->net; @@ -7512,10 +7492,9 @@ static int nf_tables_delflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_next(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct nft_flowtable *flowtable; struct net *net = info->net; const struct nlattr *attr; @@ -7707,9 +7686,8 @@ static int nf_tables_getflowtable(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nla[]) { - const struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); u8 genmask = nft_genmask_cur(info->net); - int family = nfmsg->nfgen_family; + u8 family = info->nfmsg->nfgen_family; struct nft_flowtable *flowtable; const struct nft_table *table; struct net *net = info->net; @@ -8839,11 +8817,16 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_ABORT); + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: trans->ctx.chain->use++; nft_clear(trans->ctx.net, nft_trans_rule(trans)); nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); + nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index dbc2e945c98e..866cfba04d6c 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -81,7 +81,7 @@ static bool nft_payload_fast_eval(const struct nft_expr *expr, else { if (!pkt->tprot_set) return false; - ptr = skb_network_header(skb) + pkt->xt.thoff; + ptr = skb_network_header(skb) + nft_thoff(pkt); } ptr += priv->offset; @@ -268,6 +268,7 @@ static struct nft_expr_type *nft_basic_types[] = { &nft_meta_type, &nft_rt_type, &nft_exthdr_type, + &nft_last_type, }; static struct nft_object_type *nft_basic_objects[] = { diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index a48c5fd53a80..b58d73a96523 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -54,15 +54,10 @@ static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow) { struct nft_flow_match *match = &flow->match; - struct nft_offload_ethertype ethertype; - - if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL) && - match->key.basic.n_proto != htons(ETH_P_8021Q) && - match->key.basic.n_proto != htons(ETH_P_8021AD)) - return; - - ethertype.value = match->key.basic.n_proto; - ethertype.mask = match->mask.basic.n_proto; + struct nft_offload_ethertype ethertype = { + .value = match->key.basic.n_proto, + .mask = match->mask.basic.n_proto, + }; if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_VLAN) && (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) || @@ -76,7 +71,9 @@ static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] = offsetof(struct nft_flow_key, cvlan); match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CVLAN); - } else { + } else if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_BASIC) && + (match->key.basic.n_proto == htons(ETH_P_8021Q) || + match->key.basic.n_proto == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.vlan.vlan_tpid; match->mask.basic.n_proto = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; @@ -594,23 +591,6 @@ int nft_flow_rule_offload_commit(struct net *net) } } - list_for_each_entry(trans, &nft_net->commit_list, list) { - if (trans->ctx.family != NFPROTO_NETDEV) - continue; - - switch (trans->msg_type) { - case NFT_MSG_NEWRULE: - case NFT_MSG_DELRULE: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) - continue; - - nft_flow_rule_destroy(nft_trans_flow_rule(trans)); - break; - default: - break; - } - } - return err; } diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 0cf3278007ba..e4fe2f0780eb 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -113,17 +113,17 @@ static int nf_trace_fill_pkt_info(struct sk_buff *nlskb, int off = skb_network_offset(skb); unsigned int len, nh_end; - nh_end = pkt->tprot_set ? pkt->xt.thoff : skb->len; + nh_end = pkt->tprot_set ? nft_thoff(pkt) : skb->len; len = min_t(unsigned int, nh_end - skb_network_offset(skb), NFT_TRACETYPE_NETWORK_HSIZE); if (trace_fill_header(nlskb, NFTA_TRACE_NETWORK_HEADER, skb, off, len)) return -1; if (pkt->tprot_set) { - len = min_t(unsigned int, skb->len - pkt->xt.thoff, + len = min_t(unsigned int, skb->len - nft_thoff(pkt), NFT_TRACETYPE_TRANSPORT_HSIZE); if (trace_fill_header(nlskb, NFTA_TRACE_TRANSPORT_HEADER, skb, - pkt->xt.thoff, len)) + nft_thoff(pkt), len)) return -1; } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index e8dbd8379027..7e2c8dd01408 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -68,6 +68,7 @@ static const char *const nfnl_lockdep_names[NFNL_SUBSYS_COUNT] = { [NFNL_SUBSYS_CTHELPER] = "nfnl_subsys_cthelper", [NFNL_SUBSYS_NFTABLES] = "nfnl_subsys_nftables", [NFNL_SUBSYS_NFT_COMPAT] = "nfnl_subsys_nftcompat", + [NFNL_SUBSYS_HOOK] = "nfnl_subsys_hook", }; static const int nfnl_group2type[NFNLGRP_MAX+1] = { @@ -256,6 +257,7 @@ replay: .net = net, .sk = nfnlnet->nfnl, .nlh = nlh, + .nfmsg = nlmsg_data(nlh), .extack = extack, }; @@ -491,6 +493,7 @@ replay_abort: .net = net, .sk = nfnlnet->nfnl, .nlh = nlh, + .nfmsg = nlmsg_data(nlh), .extack = &extack, }; diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 3c8cf8748cfb..505f46a32173 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -314,14 +314,11 @@ static int nfnl_acct_get(struct sk_buff *skb, const struct nfnl_info *info, kfree_skb(skb2); break; } - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret > 0) - ret = 0; - /* this avoids a loop in nfnetlink. */ - return ret == -EAGAIN ? -ENOBUFS : ret; + ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); + break; } + return ret; } diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 752b10cae524..5c622f55c9d6 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -667,14 +667,10 @@ static int nfnl_cthelper_get(struct sk_buff *skb, const struct nfnl_info *info, break; } - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret > 0) - ret = 0; - - /* this avoids a loop in nfnetlink. */ - return ret == -EAGAIN ? -ENOBUFS : ret; + ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); + break; } + return ret; } diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 38848ad68899..c57673d499be 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -287,14 +287,11 @@ static int cttimeout_get_timeout(struct sk_buff *skb, kfree_skb(skb2); break; } - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret > 0) - ret = 0; - /* this avoids a loop in nfnetlink. */ - return ret == -EAGAIN ? -ENOBUFS : ret; + ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); + break; } + return ret; } @@ -427,9 +424,9 @@ static int cttimeout_default_get(struct sk_buff *skb, const struct nf_conntrack_l4proto *l4proto; unsigned int *timeouts = NULL; struct sk_buff *skb2; - int ret, err; __u16 l3num; __u8 l4num; + int ret; if (!cda[CTA_TIMEOUT_L3PROTO] || !cda[CTA_TIMEOUT_L4PROTO]) return -EINVAL; @@ -438,9 +435,8 @@ static int cttimeout_default_get(struct sk_buff *skb, l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); l4proto = nf_ct_l4proto_find(l4num); - err = -EOPNOTSUPP; if (l4proto->l4proto != l4num) - goto err; + return -EOPNOTSUPP; switch (l4proto->l4proto) { case IPPROTO_ICMP: @@ -480,13 +476,11 @@ static int cttimeout_default_get(struct sk_buff *skb, } if (!timeouts) - goto err; + return -EOPNOTSUPP; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb2 == NULL) { - err = -ENOMEM; - goto err; - } + if (!skb2) + return -ENOMEM; ret = cttimeout_default_fill_info(info->net, skb2, NETLINK_CB(skb).portid, @@ -496,18 +490,10 @@ static int cttimeout_default_get(struct sk_buff *skb, l3num, l4proto, timeouts); if (ret <= 0) { kfree_skb(skb2); - err = -ENOMEM; - goto err; + return -ENOMEM; } - ret = netlink_unicast(info->sk, skb2, NETLINK_CB(skb).portid, - MSG_DONTWAIT); - if (ret > 0) - ret = 0; - /* this avoids a loop in nfnetlink. */ - return ret == -EAGAIN ? -ENOBUFS : ret; -err: - return err; + return nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); } static struct nf_ct_timeout *ctnl_timeout_find_get(struct net *net, diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c new file mode 100644 index 000000000000..50b4e3c9347a --- /dev/null +++ b/net/netfilter/nfnetlink_hook.c @@ -0,0 +1,377 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2021 Red Hat GmbH + * + * Author: Florian Westphal + */ + +#include +#include +#include +#include +#include +#include +#include + +#include + +#include +#include + +#include +#include + +static const struct nla_policy nfnl_hook_nla_policy[NFNLA_HOOK_MAX + 1] = { + [NFNLA_HOOK_HOOKNUM] = { .type = NLA_U32 }, + [NFNLA_HOOK_PRIORITY] = { .type = NLA_U32 }, + [NFNLA_HOOK_DEV] = { .type = NLA_STRING, + .len = IFNAMSIZ - 1 }, + [NFNLA_HOOK_FUNCTION_NAME] = { .type = NLA_NUL_STRING, + .len = KSYM_NAME_LEN, }, + [NFNLA_HOOK_MODULE_NAME] = { .type = NLA_NUL_STRING, + .len = MODULE_NAME_LEN, }, + [NFNLA_HOOK_CHAIN_INFO] = { .type = NLA_NESTED, }, +}; + +static int nf_netlink_dump_start_rcu(struct sock *nlsk, struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct netlink_dump_control *c) +{ + int err; + + if (!try_module_get(THIS_MODULE)) + return -EINVAL; + + rcu_read_unlock(); + err = netlink_dump_start(nlsk, skb, nlh, c); + rcu_read_lock(); + module_put(THIS_MODULE); + + return err; +} + +struct nfnl_dump_hook_data { + char devname[IFNAMSIZ]; + unsigned long headv; + u8 hook; +}; + +static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb, + const struct nfnl_dump_hook_data *ctx, + unsigned int seq, + const struct nf_hook_ops *ops) +{ + struct net *net = sock_net(nlskb->sk); + struct nlattr *nest, *nest2; + struct nft_chain *chain; + int ret = 0; + + if (ops->hook_ops_type != NF_HOOK_OP_NF_TABLES) + return 0; + + chain = ops->priv; + if (WARN_ON_ONCE(!chain)) + return 0; + + if (!nft_is_active(net, chain)) + return 0; + + nest = nla_nest_start(nlskb, NFNLA_HOOK_CHAIN_INFO); + if (!nest) + return -EMSGSIZE; + + ret = nla_put_be32(nlskb, NFNLA_HOOK_INFO_TYPE, + htonl(NFNL_HOOK_TYPE_NFTABLES)); + if (ret) + goto cancel_nest; + + nest2 = nla_nest_start(nlskb, NFNLA_HOOK_INFO_DESC); + if (!nest2) + goto cancel_nest; + + ret = nla_put_string(nlskb, NFTA_CHAIN_TABLE, chain->table->name); + if (ret) + goto cancel_nest; + + ret = nla_put_string(nlskb, NFTA_CHAIN_NAME, chain->name); + if (ret) + goto cancel_nest; + + nla_nest_end(nlskb, nest2); + nla_nest_end(nlskb, nest); + return ret; + +cancel_nest: + nla_nest_cancel(nlskb, nest); + return -EMSGSIZE; +} + +static int nfnl_hook_dump_one(struct sk_buff *nlskb, + const struct nfnl_dump_hook_data *ctx, + const struct nf_hook_ops *ops, + unsigned int seq) +{ + u16 event = nfnl_msg_type(NFNL_SUBSYS_HOOK, NFNL_MSG_HOOK_GET); + unsigned int portid = NETLINK_CB(nlskb).portid; + struct nlmsghdr *nlh; + int ret = -EMSGSIZE; +#ifdef CONFIG_KALLSYMS + char sym[KSYM_SYMBOL_LEN]; + char *module_name; +#endif + nlh = nfnl_msg_put(nlskb, portid, seq, event, + NLM_F_MULTI, ops->pf, NFNETLINK_V0, 0); + if (!nlh) + goto nla_put_failure; + +#ifdef CONFIG_KALLSYMS + ret = snprintf(sym, sizeof(sym), "%ps", ops->hook); + if (ret >= sizeof(sym)) { + ret = -EINVAL; + goto nla_put_failure; + } + + module_name = strstr(sym, " ["); + if (module_name) { + char *end; + + module_name += 2; + end = strchr(module_name, ']'); + if (end) { + *end = 0; + + ret = nla_put_string(nlskb, NFNLA_HOOK_MODULE_NAME, module_name); + if (ret) + goto nla_put_failure; + } + } + + ret = nla_put_string(nlskb, NFNLA_HOOK_FUNCTION_NAME, sym); + if (ret) + goto nla_put_failure; +#endif + + ret = nla_put_be32(nlskb, NFNLA_HOOK_HOOKNUM, htonl(ops->hooknum)); + if (ret) + goto nla_put_failure; + + ret = nla_put_be32(nlskb, NFNLA_HOOK_PRIORITY, htonl(ops->priority)); + if (ret) + goto nla_put_failure; + + ret = nfnl_hook_put_nft_chain_info(nlskb, ctx, seq, ops); + if (ret) + goto nla_put_failure; + + nlmsg_end(nlskb, nlh); + return 0; +nla_put_failure: + nlmsg_trim(nlskb, nlh); + return ret; +} + +static const struct nf_hook_entries * +nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev) +{ + const struct nf_hook_entries *hook_head = NULL; + struct net_device *netdev; + + switch (pf) { + case NFPROTO_IPV4: + if (hook >= ARRAY_SIZE(net->nf.hooks_ipv4)) + return ERR_PTR(-EINVAL); + hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); + break; + case NFPROTO_IPV6: + if (hook >= ARRAY_SIZE(net->nf.hooks_ipv6)) + return ERR_PTR(-EINVAL); + hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); + break; + case NFPROTO_ARP: +#ifdef CONFIG_NETFILTER_FAMILY_ARP + if (hook >= ARRAY_SIZE(net->nf.hooks_arp)) + return ERR_PTR(-EINVAL); + hook_head = rcu_dereference(net->nf.hooks_arp[hook]); +#endif + break; + case NFPROTO_BRIDGE: +#ifdef CONFIG_NETFILTER_FAMILY_BRIDGE + if (hook >= ARRAY_SIZE(net->nf.hooks_bridge)) + return ERR_PTR(-EINVAL); + hook_head = rcu_dereference(net->nf.hooks_bridge[hook]); +#endif + break; +#if IS_ENABLED(CONFIG_DECNET) + case NFPROTO_DECNET: + if (hook >= ARRAY_SIZE(net->nf.hooks_decnet)) + return ERR_PTR(-EINVAL); + hook_head = rcu_dereference(net->nf.hooks_decnet[hook]); + break; +#endif +#ifdef CONFIG_NETFILTER_INGRESS + case NFPROTO_NETDEV: + if (hook != NF_NETDEV_INGRESS) + return ERR_PTR(-EOPNOTSUPP); + + if (!dev) + return ERR_PTR(-ENODEV); + + netdev = dev_get_by_name_rcu(net, dev); + if (!netdev) + return ERR_PTR(-ENODEV); + + return rcu_dereference(netdev->nf_hooks_ingress); +#endif + default: + return ERR_PTR(-EPROTONOSUPPORT); + } + + return hook_head; +} + +static int nfnl_hook_dump(struct sk_buff *nlskb, + struct netlink_callback *cb) +{ + struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + struct nfnl_dump_hook_data *ctx = cb->data; + int err, family = nfmsg->nfgen_family; + struct net *net = sock_net(nlskb->sk); + struct nf_hook_ops * const *ops; + const struct nf_hook_entries *e; + unsigned int i = cb->args[0]; + + rcu_read_lock(); + + e = nfnl_hook_entries_head(family, ctx->hook, net, ctx->devname); + if (!e) + goto done; + + if (IS_ERR(e)) { + cb->seq++; + goto done; + } + + if ((unsigned long)e != ctx->headv || i >= e->num_hook_entries) + cb->seq++; + + ops = nf_hook_entries_get_hook_ops(e); + + for (; i < e->num_hook_entries; i++) { + err = nfnl_hook_dump_one(nlskb, ctx, ops[i], cb->seq); + if (err) + break; + } + +done: + nl_dump_check_consistent(cb, nlmsg_hdr(nlskb)); + rcu_read_unlock(); + cb->args[0] = i; + return nlskb->len; +} + +static int nfnl_hook_dump_start(struct netlink_callback *cb) +{ + const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + const struct nlattr * const *nla = cb->data; + struct nfnl_dump_hook_data *ctx = NULL; + struct net *net = sock_net(cb->skb->sk); + u8 family = nfmsg->nfgen_family; + char name[IFNAMSIZ] = ""; + const void *head; + u32 hooknum; + + hooknum = ntohl(nla_get_be32(nla[NFNLA_HOOK_HOOKNUM])); + if (hooknum > 255) + return -EINVAL; + + if (family == NFPROTO_NETDEV) { + if (!nla[NFNLA_HOOK_DEV]) + return -EINVAL; + + nla_strscpy(name, nla[NFNLA_HOOK_DEV], sizeof(name)); + } + + rcu_read_lock(); + /* Not dereferenced; for consistency check only */ + head = nfnl_hook_entries_head(family, hooknum, net, name); + rcu_read_unlock(); + + if (head && IS_ERR(head)) + return PTR_ERR(head); + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + strscpy(ctx->devname, name, sizeof(ctx->devname)); + ctx->headv = (unsigned long)head; + ctx->hook = hooknum; + + cb->seq = 1; + cb->data = ctx; + + return 0; +} + +static int nfnl_hook_dump_stop(struct netlink_callback *cb) +{ + kfree(cb->data); + return 0; +} + +static int nfnl_hook_get(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + if (!nla[NFNLA_HOOK_HOOKNUM]) + return -EINVAL; + + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nfnl_hook_dump_start, + .done = nfnl_hook_dump_stop, + .dump = nfnl_hook_dump, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nf_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + } + + return -EOPNOTSUPP; +} + +static const struct nfnl_callback nfnl_hook_cb[NFNL_MSG_HOOK_MAX] = { + [NFNL_MSG_HOOK_GET] = { + .call = nfnl_hook_get, + .type = NFNL_CB_RCU, + .attr_count = NFNLA_HOOK_MAX, + .policy = nfnl_hook_nla_policy + }, +}; + +static const struct nfnetlink_subsystem nfhook_subsys = { + .name = "nfhook", + .subsys_id = NFNL_SUBSYS_HOOK, + .cb_count = NFNL_MSG_HOOK_MAX, + .cb = nfnl_hook_cb, +}; + +MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_HOOK); + +static int __init nfnetlink_hook_init(void) +{ + return nfnetlink_subsys_register(&nfhook_subsys); +} + +static void __exit nfnetlink_hook_exit(void) +{ + nfnetlink_subsys_unregister(&nfhook_subsys); +} + +module_init(nfnetlink_hook_init); +module_exit(nfnetlink_hook_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal "); +MODULE_DESCRIPTION("nfnetlink_hook: list registered netfilter hooks"); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 587086b18c36..691ef4cffdd9 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -871,15 +871,14 @@ static int nfulnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfula[]) { struct nfnl_log_net *log = nfnl_log_pernet(info->net); - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int16_t group_num = ntohs(nfmsg->res_id); + u_int16_t group_num = ntohs(info->nfmsg->res_id); struct nfulnl_msg_config_cmd *cmd = NULL; struct nfulnl_instance *inst; u16 flags = 0; int ret = 0; if (nfula[NFULA_CFG_CMD]) { - u_int8_t pf = nfmsg->nfgen_family; + u_int8_t pf = info->nfmsg->nfgen_family; cmd = nla_data(nfula[NFULA_CFG_CMD]); /* Commands without queue context */ diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index f37a575ebd7f..f774de0fc24f 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1051,8 +1051,7 @@ static int nfqnl_recv_verdict_batch(struct sk_buff *skb, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u16 queue_num = ntohs(nfmsg->res_id); + u16 queue_num = ntohs(info->nfmsg->res_id); struct nf_queue_entry *entry, *tmp; struct nfqnl_msg_verdict_hdr *vhdr; struct nfqnl_instance *queue; @@ -1160,8 +1159,7 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int16_t queue_num = ntohs(nfmsg->res_id); + u_int16_t queue_num = ntohs(info->nfmsg->res_id); struct nfqnl_msg_verdict_hdr *vhdr; enum ip_conntrack_info ctinfo; struct nfqnl_instance *queue; @@ -1243,8 +1241,7 @@ static int nfqnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); - struct nfgenmsg *nfmsg = nlmsg_data(info->nlh); - u_int16_t queue_num = ntohs(nfmsg->res_id); + u_int16_t queue_num = ntohs(info->nfmsg->res_id); struct nfqnl_msg_config_cmd *cmd = NULL; struct nfqnl_instance *queue; __u32 flags = 0, mask = 0; diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 363bdd7044ec..5b02408a920b 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -18,7 +18,7 @@ static unsigned int nft_do_chain_ipv4(void *priv, struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv4(&pkt, skb); + nft_set_pktinfo_ipv4(&pkt); return nft_do_chain(&pkt, priv); } @@ -62,7 +62,7 @@ static unsigned int nft_do_chain_arp(void *priv, struct sk_buff *skb, struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_unspec(&pkt, skb); + nft_set_pktinfo_unspec(&pkt); return nft_do_chain(&pkt, priv); } @@ -102,7 +102,7 @@ static unsigned int nft_do_chain_ipv6(void *priv, struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv6(&pkt, skb); + nft_set_pktinfo_ipv6(&pkt); return nft_do_chain(&pkt, priv); } @@ -149,10 +149,10 @@ static unsigned int nft_do_chain_inet(void *priv, struct sk_buff *skb, switch (state->pf) { case NFPROTO_IPV4: - nft_set_pktinfo_ipv4(&pkt, skb); + nft_set_pktinfo_ipv4(&pkt); break; case NFPROTO_IPV6: - nft_set_pktinfo_ipv6(&pkt, skb); + nft_set_pktinfo_ipv6(&pkt); break; default: break; @@ -174,7 +174,7 @@ static unsigned int nft_do_chain_inet_ingress(void *priv, struct sk_buff *skb, ingress_state.hook = NF_INET_INGRESS; nft_set_pktinfo(&pkt, skb, &ingress_state); - if (nft_set_pktinfo_ipv4_ingress(&pkt, skb) < 0) + if (nft_set_pktinfo_ipv4_ingress(&pkt) < 0) return NF_DROP; break; case htons(ETH_P_IPV6): @@ -182,7 +182,7 @@ static unsigned int nft_do_chain_inet_ingress(void *priv, struct sk_buff *skb, ingress_state.hook = NF_INET_INGRESS; nft_set_pktinfo(&pkt, skb, &ingress_state); - if (nft_set_pktinfo_ipv6_ingress(&pkt, skb) < 0) + if (nft_set_pktinfo_ipv6_ingress(&pkt) < 0) return NF_DROP; break; default: @@ -238,13 +238,13 @@ nft_do_chain_bridge(void *priv, switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): - nft_set_pktinfo_ipv4_validate(&pkt, skb); + nft_set_pktinfo_ipv4_validate(&pkt); break; case htons(ETH_P_IPV6): - nft_set_pktinfo_ipv6_validate(&pkt, skb); + nft_set_pktinfo_ipv6_validate(&pkt); break; default: - nft_set_pktinfo_unspec(&pkt, skb); + nft_set_pktinfo_unspec(&pkt); break; } @@ -293,13 +293,13 @@ static unsigned int nft_do_chain_netdev(void *priv, struct sk_buff *skb, switch (skb->protocol) { case htons(ETH_P_IP): - nft_set_pktinfo_ipv4_validate(&pkt, skb); + nft_set_pktinfo_ipv4_validate(&pkt); break; case htons(ETH_P_IPV6): - nft_set_pktinfo_ipv6_validate(&pkt, skb); + nft_set_pktinfo_ipv6_validate(&pkt); break; default: - nft_set_pktinfo_unspec(&pkt, skb); + nft_set_pktinfo_unspec(&pkt); break; } diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c index eac4a901233f..98e4946100c5 100644 --- a/net/netfilter/nft_chain_nat.c +++ b/net/netfilter/nft_chain_nat.c @@ -17,12 +17,12 @@ static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb, switch (state->pf) { #ifdef CONFIG_NF_TABLES_IPV4 case NFPROTO_IPV4: - nft_set_pktinfo_ipv4(&pkt, skb); + nft_set_pktinfo_ipv4(&pkt); break; #endif #ifdef CONFIG_NF_TABLES_IPV6 case NFPROTO_IPV6: - nft_set_pktinfo_ipv6(&pkt, skb); + nft_set_pktinfo_ipv6(&pkt); break; #endif default: diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c index edd02cda57fc..925db0dce48d 100644 --- a/net/netfilter/nft_chain_route.c +++ b/net/netfilter/nft_chain_route.c @@ -26,7 +26,7 @@ static unsigned int nf_route_table_hook4(void *priv, u8 tos; nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv4(&pkt, skb); + nft_set_pktinfo_ipv4(&pkt); mark = skb->mark; iph = ip_hdr(skb); @@ -74,7 +74,7 @@ static unsigned int nf_route_table_hook6(void *priv, int err; nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv6(&pkt, skb); + nft_set_pktinfo_ipv6(&pkt); /* save source/dest address, mark, hoplimit, flowlabel, priority */ memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr)); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 5415ab14400d..639c337c885b 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -57,8 +57,13 @@ union nft_entry { }; static inline void -nft_compat_set_par(struct xt_action_param *par, void *xt, const void *xt_info) +nft_compat_set_par(struct xt_action_param *par, + const struct nft_pktinfo *pkt, + const void *xt, const void *xt_info) { + par->state = pkt->state; + par->thoff = nft_thoff(pkt); + par->fragoff = pkt->fragoff; par->target = xt; par->targinfo = xt_info; par->hotdrop = false; @@ -71,13 +76,14 @@ static void nft_target_eval_xt(const struct nft_expr *expr, void *info = nft_expr_priv(expr); struct xt_target *target = expr->ops->data; struct sk_buff *skb = pkt->skb; + struct xt_action_param xt; int ret; - nft_compat_set_par((struct xt_action_param *)&pkt->xt, target, info); + nft_compat_set_par(&xt, pkt, target, info); - ret = target->target(skb, &pkt->xt); + ret = target->target(skb, &xt); - if (pkt->xt.hotdrop) + if (xt.hotdrop) ret = NF_DROP; switch (ret) { @@ -97,13 +103,14 @@ static void nft_target_eval_bridge(const struct nft_expr *expr, void *info = nft_expr_priv(expr); struct xt_target *target = expr->ops->data; struct sk_buff *skb = pkt->skb; + struct xt_action_param xt; int ret; - nft_compat_set_par((struct xt_action_param *)&pkt->xt, target, info); + nft_compat_set_par(&xt, pkt, target, info); - ret = target->target(skb, &pkt->xt); + ret = target->target(skb, &xt); - if (pkt->xt.hotdrop) + if (xt.hotdrop) ret = NF_DROP; switch (ret) { @@ -350,13 +357,14 @@ static void __nft_match_eval(const struct nft_expr *expr, { struct xt_match *match = expr->ops->data; struct sk_buff *skb = pkt->skb; + struct xt_action_param xt; bool ret; - nft_compat_set_par((struct xt_action_param *)&pkt->xt, match, info); + nft_compat_set_par(&xt, pkt, match, info); - ret = match->match(skb, (struct xt_action_param *)&pkt->xt); + ret = match->match(skb, &xt); - if (pkt->xt.hotdrop) { + if (xt.hotdrop) { regs->verdict.code = NF_DROP; return; } @@ -617,7 +625,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const tb[]) { - struct nfgenmsg *nfmsg; + u8 family = info->nfmsg->nfgen_family; const char *name, *fmt; struct sk_buff *skb2; int ret = 0, target; @@ -632,9 +640,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, rev = ntohl(nla_get_be32(tb[NFTA_COMPAT_REV])); target = ntohl(nla_get_be32(tb[NFTA_COMPAT_TYPE])); - nfmsg = nlmsg_data(info->nlh); - - switch(nfmsg->nfgen_family) { + switch(family) { case AF_INET: fmt = "ipt_%s"; break; @@ -648,8 +654,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, fmt = "arpt_%s"; break; default: - pr_err("nft_compat: unsupported protocol %d\n", - nfmsg->nfgen_family); + pr_err("nft_compat: unsupported protocol %d\n", family); return -EINVAL; } @@ -657,9 +662,8 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, return -EINVAL; rcu_read_unlock(); - try_then_request_module(xt_find_revision(nfmsg->nfgen_family, name, - rev, target, &ret), - fmt, name); + try_then_request_module(xt_find_revision(family, name, rev, target, &ret), + fmt, name); if (ret < 0) goto out_put; @@ -674,8 +678,7 @@ static int nfnl_compat_get_rcu(struct sk_buff *skb, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), NFNL_MSG_COMPAT_GET, - nfmsg->nfgen_family, - name, ret, target) <= 0) { + family, name, ret, target) <= 0) { kfree_skb(skb2); goto out_put; } diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index f64f0017e9a5..af4ee874a067 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -10,8 +10,10 @@ #include #include #include +#include #include #include +#include #include struct nft_exthdr { @@ -42,6 +44,9 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, unsigned int offset = 0; int err; + if (pkt->skb->protocol != htons(ETH_P_IPV6)) + goto err; + err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL); if (priv->flags & NFT_EXTHDR_F_PRESENT) { nft_reg_store8(dest, err >= 0); @@ -162,10 +167,10 @@ nft_tcp_header_pointer(const struct nft_pktinfo *pkt, { struct tcphdr *tcph; - if (!pkt->tprot_set || pkt->tprot != IPPROTO_TCP) + if (pkt->tprot != IPPROTO_TCP) return NULL; - tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff, sizeof(*tcph), buffer); + tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(*tcph), buffer); if (!tcph) return NULL; @@ -173,7 +178,7 @@ nft_tcp_header_pointer(const struct nft_pktinfo *pkt, if (*tcphdr_len < sizeof(*tcph) || *tcphdr_len > len) return NULL; - return skb_header_pointer(pkt->skb, pkt->xt.thoff, *tcphdr_len, buffer); + return skb_header_pointer(pkt->skb, nft_thoff(pkt), *tcphdr_len, buffer); } static void nft_exthdr_tcp_eval(const struct nft_expr *expr, @@ -249,7 +254,7 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, return; if (skb_ensure_writable(pkt->skb, - pkt->xt.thoff + i + priv->len)) + nft_thoff(pkt) + i + priv->len)) return; tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, @@ -300,6 +305,48 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, } } +static void nft_exthdr_sctp_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + unsigned int offset = nft_thoff(pkt) + sizeof(struct sctphdr); + struct nft_exthdr *priv = nft_expr_priv(expr); + u32 *dest = ®s->data[priv->dreg]; + const struct sctp_chunkhdr *sch; + struct sctp_chunkhdr _sch; + + if (pkt->tprot != IPPROTO_SCTP) + goto err; + + do { + sch = skb_header_pointer(pkt->skb, offset, sizeof(_sch), &_sch); + if (!sch || !sch->length) + break; + + if (sch->type == priv->type) { + if (priv->flags & NFT_EXTHDR_F_PRESENT) { + nft_reg_store8(dest, true); + return; + } + if (priv->offset + priv->len > ntohs(sch->length) || + offset + ntohs(sch->length) > pkt->skb->len) + break; + + dest[priv->len / NFT_REG32_SIZE] = 0; + if (skb_copy_bits(pkt->skb, offset + priv->offset, + dest, priv->len) < 0) + break; + return; + } + offset += SCTP_PAD4(ntohs(sch->length)); + } while (offset < pkt->skb->len); +err: + if (priv->flags & NFT_EXTHDR_F_PRESENT) + nft_reg_store8(dest, false); + else + regs->verdict.code = NFT_BREAK; +} + static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = { [NFTA_EXTHDR_DREG] = { .type = NLA_U32 }, [NFTA_EXTHDR_TYPE] = { .type = NLA_U8 }, @@ -499,6 +546,14 @@ static const struct nft_expr_ops nft_exthdr_tcp_set_ops = { .dump = nft_exthdr_dump_set, }; +static const struct nft_expr_ops nft_exthdr_sctp_ops = { + .type = &nft_exthdr_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), + .eval = nft_exthdr_sctp_eval, + .init = nft_exthdr_init, + .dump = nft_exthdr_dump, +}; + static const struct nft_expr_ops * nft_exthdr_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -529,6 +584,10 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx, return &nft_exthdr_ipv4_ops; } break; + case NFT_EXTHDR_OP_SCTP: + if (tb[NFTA_EXTHDR_DREG]) + return &nft_exthdr_sctp_ops; + break; } return ERR_PTR(-EOPNOTSUPP); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 4843dd2b410c..0af34ad41479 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -291,7 +291,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) { case IPPROTO_TCP: - tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff, + tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(_tcph), &_tcph); if (unlikely(!tcph || tcph->fin || tcph->rst)) goto out; diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c new file mode 100644 index 000000000000..913ac45167f2 --- /dev/null +++ b/net/netfilter/nft_last.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include +#include +#include +#include + +struct nft_last_priv { + unsigned long last_jiffies; + unsigned int last_set; +}; + +static const struct nla_policy nft_last_policy[NFTA_LAST_MAX + 1] = { + [NFTA_LAST_SET] = { .type = NLA_U32 }, + [NFTA_LAST_MSECS] = { .type = NLA_U64 }, +}; + +static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_last_priv *priv = nft_expr_priv(expr); + u64 last_jiffies; + int err; + + if (tb[NFTA_LAST_MSECS]) { + err = nf_msecs_to_jiffies64(tb[NFTA_LAST_MSECS], &last_jiffies); + if (err < 0) + return err; + + priv->last_jiffies = jiffies + (unsigned long)last_jiffies; + priv->last_set = 1; + } + + return 0; +} + +static void nft_last_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt) +{ + struct nft_last_priv *priv = nft_expr_priv(expr); + + priv->last_jiffies = jiffies; + priv->last_set = 1; +} + +static int nft_last_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + struct nft_last_priv *priv = nft_expr_priv(expr); + __be64 msecs; + + if (time_before(jiffies, priv->last_jiffies)) + priv->last_set = 0; + + if (priv->last_set) + msecs = nf_jiffies64_to_msecs(jiffies - priv->last_jiffies); + else + msecs = 0; + + if (nla_put_be32(skb, NFTA_LAST_SET, htonl(priv->last_set)) || + nla_put_be64(skb, NFTA_LAST_MSECS, msecs, NFTA_LAST_PAD)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static const struct nft_expr_ops nft_last_ops = { + .type = &nft_last_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_last_priv)), + .eval = nft_last_eval, + .init = nft_last_init, + .dump = nft_last_dump, +}; + +struct nft_expr_type nft_last_type __read_mostly = { + .name = "last", + .ops = &nft_last_ops, + .policy = nft_last_policy, + .maxattr = NFTA_LAST_MAX, + .flags = NFT_EXPR_STATEFUL, + .owner = THIS_MODULE, +}; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index a479f8a1270c..90becbf5bff3 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -23,6 +23,37 @@ struct nft_lookup { struct nft_set_binding binding; }; +#ifdef CONFIG_RETPOLINE +bool nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) +{ + if (set->ops == &nft_set_hash_fast_type.ops) + return nft_hash_lookup_fast(net, set, key, ext); + if (set->ops == &nft_set_hash_type.ops) + return nft_hash_lookup(net, set, key, ext); + + if (set->ops == &nft_set_rhash_type.ops) + return nft_rhash_lookup(net, set, key, ext); + + if (set->ops == &nft_set_bitmap_type.ops) + return nft_bitmap_lookup(net, set, key, ext); + + if (set->ops == &nft_set_pipapo_type.ops) + return nft_pipapo_lookup(net, set, key, ext); +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) + if (set->ops == &nft_set_pipapo_avx2_type.ops) + return nft_pipapo_avx2_lookup(net, set, key, ext); +#endif + + if (set->ops == &nft_set_rbtree_type.ops) + return nft_rbtree_lookup(net, set, key, ext); + + WARN_ON_ONCE(1); + return set->ops->lookup(net, set, key, ext); +} +EXPORT_SYMBOL_GPL(nft_set_do_lookup); +#endif + void nft_lookup_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -33,8 +64,8 @@ void nft_lookup_eval(const struct nft_expr *expr, const struct net *net = nft_net(pkt); bool found; - found = set->ops->lookup(net, set, ®s->data[priv->sreg], &ext) ^ - priv->invert; + found = nft_set_do_lookup(net, set, ®s->data[priv->sreg], &ext) ^ + priv->invert; if (!found) { ext = nft_set_catchall_lookup(net, set); if (!ext) { diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 7e47edee88ee..94b2327e71dc 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #define nft_objref_priv(expr) *((struct nft_object **)nft_expr_priv(expr)) @@ -110,7 +110,7 @@ static void nft_objref_map_eval(const struct nft_expr *expr, struct nft_object *obj; bool found; - found = set->ops->lookup(net, set, ®s->data[priv->sreg], &ext); + found = nft_set_do_lookup(net, set, ®s->data[priv->sreg], &ext); if (!found) { ext = nft_set_catchall_lookup(net, set); if (!ext) { diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index ac61f708b82d..d82677e83400 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -28,6 +28,11 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs, struct nf_osf_data data; struct tcphdr _tcph; + if (pkt->tprot != IPPROTO_TCP) { + regs->verdict.code = NFT_BREAK; + return; + } + tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); if (!tcp) { diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 501c5b24cc39..a44b14f6c0dc 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -110,7 +110,7 @@ void nft_payload_eval(const struct nft_expr *expr, case NFT_PAYLOAD_TRANSPORT_HEADER: if (!pkt->tprot_set) goto err; - offset = pkt->xt.thoff; + offset = nft_thoff(pkt); break; default: BUG(); @@ -507,7 +507,7 @@ static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt, *l4csum_offset = offsetof(struct tcphdr, check); break; case IPPROTO_UDP: - if (!nft_payload_udp_checksum(skb, pkt->xt.thoff)) + if (!nft_payload_udp_checksum(skb, nft_thoff(pkt))) return -1; fallthrough; case IPPROTO_UDPLITE: @@ -520,7 +520,7 @@ static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt, return -1; } - *l4csum_offset += pkt->xt.thoff; + *l4csum_offset += nft_thoff(pkt); return 0; } @@ -612,7 +612,7 @@ static void nft_payload_set_eval(const struct nft_expr *expr, case NFT_PAYLOAD_TRANSPORT_HEADER: if (!pkt->tprot_set) goto err; - offset = pkt->xt.thoff; + offset = nft_thoff(pkt); break; default: BUG(); @@ -643,7 +643,7 @@ static void nft_payload_set_eval(const struct nft_expr *expr, if (priv->csum_type == NFT_PAYLOAD_CSUM_SCTP && pkt->tprot == IPPROTO_SCTP && skb->ip_summed != CHECKSUM_PARTIAL) { - if (nft_payload_csum_sctp(skb, pkt->xt.thoff)) + if (nft_payload_csum_sctp(skb, nft_thoff(pkt))) goto err; } diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 95090186ee90..554caf967baa 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -28,7 +28,7 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, nft_hook(pkt)); break; case NFT_REJECT_TCP_RST: - nf_send_reset(nft_net(pkt), pkt->xt.state->sk, + nf_send_reset(nft_net(pkt), nft_sk(pkt), pkt->skb, nft_hook(pkt)); break; case NFT_REJECT_ICMPX_UNREACH: @@ -45,7 +45,7 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, priv->icmp_code, nft_hook(pkt)); break; case NFT_REJECT_TCP_RST: - nf_send_reset6(nft_net(pkt), pkt->xt.state->sk, + nf_send_reset6(nft_net(pkt), nft_sk(pkt), pkt->skb, nft_hook(pkt)); break; case NFT_REJECT_ICMPX_UNREACH: diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 2a81ea421819..e7ae5914971e 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -73,8 +73,9 @@ nft_bitmap_active(const u8 *bitmap, u32 idx, u32 off, u8 genmask) return (bitmap[idx] & (0x3 << off)) & (genmask << off); } -static bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +INDIRECT_CALLABLE_SCOPE +bool nft_bitmap_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { const struct nft_bitmap *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 7b3d0a78c569..df40314de21f 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -74,8 +74,9 @@ static const struct rhashtable_params nft_rhash_params = { .automatic_shrinking = true, }; -static bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +INDIRECT_CALLABLE_SCOPE +bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_rhash *priv = nft_set_priv(set); const struct nft_rhash_elem *he; @@ -446,8 +447,9 @@ struct nft_hash_elem { struct nft_set_ext ext; }; -static bool nft_hash_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +INDIRECT_CALLABLE_SCOPE +bool nft_hash_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_hash *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); @@ -484,9 +486,10 @@ static void *nft_hash_get(const struct net *net, const struct nft_set *set, return ERR_PTR(-ENOENT); } -static bool nft_hash_lookup_fast(const struct net *net, - const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +INDIRECT_CALLABLE_SCOPE +bool nft_hash_lookup_fast(const struct net *net, + const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_hash *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index d84afb8fa79a..25a75591583e 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -178,8 +178,6 @@ struct nft_pipapo_elem { int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, union nft_pipapo_map_bucket *mt, bool match_only); -bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext); /** * pipapo_and_field_buckets_4bit() - Intersect 4-bit buckets diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index eabdb8d552ee..e517663e0cd1 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -142,7 +142,6 @@ static void nft_pipapo_avx2_fill(unsigned long *data, int start, int len) * @map: Bitmap to be scanned for set bits * @dst: Destination bitmap * @mt: Mapping table containing bit set specifiers - * @len: Length of bitmap in longs * @last: Return index of first set bit, if this is the last field * * This is an alternative implementation of pipapo_refill() suitable for usage @@ -1109,7 +1108,7 @@ bool nft_pipapo_avx2_estimate(const struct nft_set_desc *desc, u32 features, * nft_pipapo_avx2_lookup() - Lookup function for AVX2 implementation * @net: Network namespace * @set: nftables API set representation - * @elem: nftables API element representation containing key data + * @key: nftables API element representation containing key data * @ext: nftables API extension pointer, filled with matching reference * * For more details, see DOC: Theory of Operation in nft_set_pipapo.c. @@ -1136,8 +1135,13 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, m = rcu_dereference(priv->match); - /* This also protects access to all data related to scratch maps */ - kernel_fpu_begin(); + /* This also protects access to all data related to scratch maps. + * + * Note that we don't need a valid MXCSR state for any of the + * operations we use here, so pass 0 as mask and spare a LDMXCSR + * instruction. + */ + kernel_fpu_begin_mask(0); scratch = *raw_cpu_ptr(m->scratch_aligned); if (unlikely(!scratch)) { diff --git a/net/netfilter/nft_set_pipapo_avx2.h b/net/netfilter/nft_set_pipapo_avx2.h index 394bcb704db7..dbb6aaca8a7a 100644 --- a/net/netfilter/nft_set_pipapo_avx2.h +++ b/net/netfilter/nft_set_pipapo_avx2.h @@ -5,8 +5,6 @@ #include #define NFT_PIPAPO_ALIGN (XSAVE_YMM_SIZE / BITS_PER_BYTE) -bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext); bool nft_pipapo_avx2_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est); #endif /* defined(CONFIG_X86_64) && !defined(CONFIG_UML) */ diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 9e36eb4a7429..d600a566da32 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -107,8 +107,9 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set return false; } -static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, - const u32 *key, const struct nft_set_ext **ext) +INDIRECT_CALLABLE_SCOPE +bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, + const u32 *key, const struct nft_set_ext **ext) { struct nft_rbtree *priv = nft_set_priv(set); unsigned int seq = read_seqcount_begin(&priv->count); diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 4fda8b3f1762..a0109fa1e92d 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -109,7 +109,7 @@ static void nft_synproxy_do_eval(const struct nft_synproxy *priv, { struct synproxy_options opts = {}; struct sk_buff *skb = pkt->skb; - int thoff = pkt->xt.thoff; + int thoff = nft_thoff(pkt); const struct tcphdr *tcp; struct tcphdr _tcph; @@ -123,7 +123,7 @@ static void nft_synproxy_do_eval(const struct nft_synproxy *priv, return; } - tcp = skb_header_pointer(skb, pkt->xt.thoff, + tcp = skb_header_pointer(skb, thoff, sizeof(struct tcphdr), &_tcph); if (!tcp) { diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index accef672088c..b5b09a902c7a 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -30,6 +30,12 @@ static void nft_tproxy_eval_v4(const struct nft_expr *expr, __be16 tport = 0; struct sock *sk; + if (pkt->tprot != IPPROTO_TCP && + pkt->tprot != IPPROTO_UDP) { + regs->verdict.code = NFT_BREAK; + return; + } + hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr); if (!hp) { regs->verdict.code = NFT_BREAK; @@ -82,16 +88,17 @@ static void nft_tproxy_eval_v6(const struct nft_expr *expr, const struct nft_tproxy *priv = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; const struct ipv6hdr *iph = ipv6_hdr(skb); - struct in6_addr taddr; - int thoff = pkt->xt.thoff; + int thoff = nft_thoff(pkt); struct udphdr _hdr, *hp; + struct in6_addr taddr; __be16 tport = 0; struct sock *sk; int l4proto; memset(&taddr, 0, sizeof(taddr)); - if (!pkt->tprot_set) { + if (pkt->tprot != IPPROTO_TCP && + pkt->tprot != IPPROTO_UDP) { regs->verdict.code = NFT_BREAK; return; } diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c index 9cdc16b0d0d8..b6a015aee0ce 100644 --- a/net/netfilter/xt_AUDIT.c +++ b/net/netfilter/xt_AUDIT.c @@ -117,7 +117,7 @@ static int audit_tg_check(const struct xt_tgchk_param *par) const struct xt_audit_info *info = par->targinfo; if (info->type > XT_AUDIT_TYPE_MAX) { - pr_info_ratelimited("Audit type out of range (valid range: 0..%hhu)\n", + pr_info_ratelimited("Audit type out of range (valid range: 0..%u)\n", XT_AUDIT_TYPE_MAX); return -ERANGE; } diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index d4deee39158b..12404d221026 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -172,7 +172,6 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, goto err2; } - ret = 0; if ((info->ct_events || info->exp_events) && !nf_ct_ecache_ext_add(ct, info->ct_events, info->exp_events, GFP_KERNEL)) { diff --git a/net/netfilter/xt_limit.c b/net/netfilter/xt_limit.c index 24d4afb9988d..8b4fd27857f2 100644 --- a/net/netfilter/xt_limit.c +++ b/net/netfilter/xt_limit.c @@ -8,16 +8,14 @@ #include #include #include -#include #include #include #include struct xt_limit_priv { - spinlock_t lock; unsigned long prev; - uint32_t credit; + u32 credit; }; MODULE_LICENSE("GPL"); @@ -66,22 +64,31 @@ limit_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rateinfo *r = par->matchinfo; struct xt_limit_priv *priv = r->master; - unsigned long now = jiffies; + unsigned long now; + u32 old_credit, new_credit, credit_increase = 0; + bool ret; - spin_lock_bh(&priv->lock); - priv->credit += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY; - if (priv->credit > r->credit_cap) - priv->credit = r->credit_cap; + /* fastpath if there is nothing to update */ + if ((READ_ONCE(priv->credit) < r->cost) && (READ_ONCE(priv->prev) == jiffies)) + return false; - if (priv->credit >= r->cost) { - /* We're not limited. */ - priv->credit -= r->cost; - spin_unlock_bh(&priv->lock); - return true; - } + do { + now = jiffies; + credit_increase += (now - xchg(&priv->prev, now)) * CREDITS_PER_JIFFY; + old_credit = READ_ONCE(priv->credit); + new_credit = old_credit; + new_credit += credit_increase; + if (new_credit > r->credit_cap) + new_credit = r->credit_cap; + if (new_credit >= r->cost) { + ret = true; + new_credit -= r->cost; + } else { + ret = false; + } + } while (cmpxchg(&priv->credit, old_credit, new_credit) != old_credit); - spin_unlock_bh(&priv->lock); - return false; + return ret; } /* Precision saver. */ @@ -122,7 +129,6 @@ static int limit_mt_check(const struct xt_mtchk_param *par) r->credit_cap = priv->credit; /* Credits full. */ r->cost = user2credits(r->avg); } - spin_lock_init(&priv->lock); return 0; } diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index f28c8947c730..91a19c3ea1a3 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -105,7 +105,7 @@ static int netlbl_calipso_add(struct sk_buff *skb, struct genl_info *info) !info->attrs[NLBL_CALIPSO_A_MTYPE]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); switch (nla_get_u32(info->attrs[NLBL_CALIPSO_A_MTYPE])) { case CALIPSO_MAP_PASS: ret_val = netlbl_calipso_add_pass(info, &audit_info); @@ -287,7 +287,7 @@ static int netlbl_calipso_remove(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NLBL_CALIPSO_A_DOI]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); cb_arg.doi = nla_get_u32(info->attrs[NLBL_CALIPSO_A_DOI]); cb_arg.audit_info = &audit_info; ret_val = netlbl_domhsh_walk(&skip_bkt, &skip_chain, diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 4f50a64315cf..baf235721c43 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -410,7 +410,7 @@ static int netlbl_cipsov4_add(struct sk_buff *skb, struct genl_info *info) !info->attrs[NLBL_CIPSOV4_A_MTYPE]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); switch (nla_get_u32(info->attrs[NLBL_CIPSOV4_A_MTYPE])) { case CIPSO_V4_MAP_TRANS: ret_val = netlbl_cipsov4_add_std(info, &audit_info); @@ -709,7 +709,7 @@ static int netlbl_cipsov4_remove(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NLBL_CIPSOV4_A_DOI]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); cb_arg.doi = nla_get_u32(info->attrs[NLBL_CIPSOV4_A_DOI]); cb_arg.audit_info = &audit_info; ret_val = netlbl_domhsh_walk(&skip_bkt, &skip_chain, diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index dc8c39f51f7d..8158a25972b4 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -929,7 +929,7 @@ struct netlbl_dommap_def *netlbl_domhsh_getentry_af6(const char *domain, * @cb_arg: argument for the callback function * * Description: - * Interate over the domain mapping hash table, skipping the first @skip_bkt + * Iterate over the domain mapping hash table, skipping the first @skip_bkt * buckets and @skip_chain entries. For each entry in the table call * @callback, if @callback returns a negative value stop 'walking' through the * table and return. Updates the values in @skip_bkt and @skip_chain on diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 5e1239cef000..beb0e573266d 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -719,7 +719,7 @@ int netlbl_catmap_walkrng(struct netlbl_lsm_catmap *catmap, u32 offset) * it in @bitmap. The @offset must be aligned to an unsigned long and will be * updated on return if different from what was requested; if the catmap is * empty at the requested offset and beyond, the @offset is set to (u32)-1. - * Returns zero on sucess, negative values on failure. + * Returns zero on success, negative values on failure. * */ int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap, diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index ca52f5085989..032b7d7b32c7 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -76,6 +76,7 @@ static const struct nla_policy netlbl_mgmt_genl_policy[NLBL_MGMT_A_MAX + 1] = { static int netlbl_mgmt_add_common(struct genl_info *info, struct netlbl_audit *audit_info) { + void *pmap = NULL; int ret_val = -EINVAL; struct netlbl_domaddr_map *addrmap = NULL; struct cipso_v4_doi *cipsov4 = NULL; @@ -175,6 +176,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = -ENOMEM; goto add_free_addrmap; } + pmap = map; map->list.addr = addr->s_addr & mask->s_addr; map->list.mask = mask->s_addr; map->list.valid = 1; @@ -183,10 +185,8 @@ static int netlbl_mgmt_add_common(struct genl_info *info, map->def.cipso = cipsov4; ret_val = netlbl_af4list_add(&map->list, &addrmap->list4); - if (ret_val != 0) { - kfree(map); - goto add_free_addrmap; - } + if (ret_val != 0) + goto add_free_map; entry->family = AF_INET; entry->def.type = NETLBL_NLTYPE_ADDRSELECT; @@ -223,6 +223,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = -ENOMEM; goto add_free_addrmap; } + pmap = map; map->list.addr = *addr; map->list.addr.s6_addr32[0] &= mask->s6_addr32[0]; map->list.addr.s6_addr32[1] &= mask->s6_addr32[1]; @@ -235,10 +236,8 @@ static int netlbl_mgmt_add_common(struct genl_info *info, map->def.calipso = calipso; ret_val = netlbl_af6list_add(&map->list, &addrmap->list6); - if (ret_val != 0) { - kfree(map); - goto add_free_addrmap; - } + if (ret_val != 0) + goto add_free_map; entry->family = AF_INET6; entry->def.type = NETLBL_NLTYPE_ADDRSELECT; @@ -248,10 +247,12 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = netlbl_domhsh_add(entry, audit_info); if (ret_val != 0) - goto add_free_addrmap; + goto add_free_map; return 0; +add_free_map: + kfree(pmap); add_free_addrmap: kfree(addrmap); add_doi_put_def: @@ -434,7 +435,7 @@ static int netlbl_mgmt_add(struct sk_buff *skb, struct genl_info *info) (info->attrs[NLBL_MGMT_A_IPV6MASK] != NULL))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); return netlbl_mgmt_add_common(info, &audit_info); } @@ -457,7 +458,7 @@ static int netlbl_mgmt_remove(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[NLBL_MGMT_A_DOMAIN]) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); domain = nla_data(info->attrs[NLBL_MGMT_A_DOMAIN]); return netlbl_domhsh_remove(domain, AF_UNSPEC, &audit_info); @@ -557,7 +558,7 @@ static int netlbl_mgmt_adddef(struct sk_buff *skb, struct genl_info *info) (info->attrs[NLBL_MGMT_A_IPV6MASK] != NULL))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); return netlbl_mgmt_add_common(info, &audit_info); } @@ -576,7 +577,7 @@ static int netlbl_mgmt_removedef(struct sk_buff *skb, struct genl_info *info) { struct netlbl_audit audit_info; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); return netlbl_domhsh_remove_default(AF_UNSPEC, &audit_info); } diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 3e6ac9b790b1..2483df0bbd7c 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -814,7 +814,7 @@ static int netlbl_unlabel_accept(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NLBL_UNLABEL_A_ACPTFLG]) { value = nla_get_u8(info->attrs[NLBL_UNLABEL_A_ACPTFLG]); if (value == 1 || value == 0) { - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); netlbl_unlabel_acceptflg_set(value, &audit_info); return 0; } @@ -897,7 +897,7 @@ static int netlbl_unlabel_staticadd(struct sk_buff *skb, !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) @@ -947,7 +947,7 @@ static int netlbl_unlabel_staticadddef(struct sk_buff *skb, !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) @@ -994,7 +994,7 @@ static int netlbl_unlabel_staticremove(struct sk_buff *skb, !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) @@ -1034,7 +1034,7 @@ static int netlbl_unlabel_staticremovedef(struct sk_buff *skb, !info->attrs[NLBL_UNLABEL_A_IPV6MASK]))) return -EINVAL; - netlbl_netlink_auditinfo(skb, &audit_info); + netlbl_netlink_auditinfo(&audit_info); ret_val = netlbl_unlabel_addrinfo_get(info, &addr, &mask, &addr_len); if (ret_val != 0) diff --git a/net/netlabel/netlabel_user.h b/net/netlabel/netlabel_user.h index b9ba8112b3c5..6190cbf94bf0 100644 --- a/net/netlabel/netlabel_user.h +++ b/net/netlabel/netlabel_user.h @@ -28,11 +28,9 @@ /** * netlbl_netlink_auditinfo - Fetch the audit information from a NETLINK msg - * @skb: the packet * @audit_info: NetLabel audit information */ -static inline void netlbl_netlink_auditinfo(struct sk_buff *skb, - struct netlbl_audit *audit_info) +static inline void netlbl_netlink_auditinfo(struct netlbl_audit *audit_info) { security_task_getsecid_subj(current, &audit_info->secid); audit_info->loginuid = audit_get_loginuid(current); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6133e412b948..d233ac4a91b6 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -351,7 +351,7 @@ static void netlink_overrun(struct sock *sk) if (!test_and_set_bit(NETLINK_S_CONGESTED, &nlk_sk(sk)->state)) { sk->sk_err = ENOBUFS; - sk->sk_error_report(sk); + sk_error_report(sk); } } atomic_inc(&sk->sk_drops); @@ -1576,7 +1576,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) } sk->sk_err = p->code; - sk->sk_error_report(sk); + sk_error_report(sk); out: return ret; } @@ -2012,7 +2012,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, ret = netlink_dump(sk); if (ret) { sk->sk_err = -ret; - sk->sk_error_report(sk); + sk_error_report(sk); } } @@ -2439,7 +2439,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) { NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; - NETLINK_CB(in_skb).sk->sk_error_report(NETLINK_CB(in_skb).sk); + sk_error_report(NETLINK_CB(in_skb).sk); return; } diff --git a/net/nfc/hci/command.c b/net/nfc/hci/command.c index e02b9befce0b..3a89bd9b89fc 100644 --- a/net/nfc/hci/command.c +++ b/net/nfc/hci/command.c @@ -34,7 +34,7 @@ static int nfc_hci_execute_cmd_async(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, * HCI command execution completion callback. * err will be a standard linux error (may be converted from HCI response) * skb contains the response data and must be disposed, or may be NULL if - * an error occured + * an error occurred */ static void nfc_hci_execute_cb(void *context, struct sk_buff *skb, int err) { diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index 43811b5219b5..3481941be70b 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -705,7 +705,7 @@ static void hci_transceive_cb(void *context, struct sk_buff *skb, int err) /* * TODO: Check RF Error indicator to make sure data is valid. * It seems that HCI cmd can complete without error, but data - * can be invalid if an RF error occured? Ignore for now. + * can be invalid if an RF error occurred? Ignore for now. */ if (err == 0) skb_trim(skb, skb->len - 1); /* RF Err ind */ diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index c0c8fea3a186..1e3a90049da9 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -406,7 +406,7 @@ static void llc_shdlc_rcv_u_frame(struct llc_shdlc *shdlc, case SHDLC_NEGOTIATING: case SHDLC_CONNECTING: /* - * We sent RSET, but chip wants to negociate or we + * We sent RSET, but chip wants to negotiate or we * got RSET before we managed to send out our. */ if (skb->len > 0) diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index 96865142104f..d6732e5e8958 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -161,8 +161,6 @@ static int nci_hci_send_data(struct nci_dev *ndev, u8 pipe, *(u8 *)skb_push(skb, 1) = data_type; do { - len = conn_info->max_pkt_payload_len; - /* If last packet add NCI_HFP_NO_CHAINING */ if (i + conn_info->max_pkt_payload_len - (skb->len + 1) >= data_len) { diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 5f1d438a0a23..5e39640becdb 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -49,7 +49,7 @@ static void rawsock_report_error(struct sock *sk, int err) sk->sk_shutdown = SHUTDOWN_MASK; sk->sk_err = -err; - sk->sk_error_report(sk); + sk_error_report(sk); rawsock_write_queue_purge(sk); } diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile index 41109c326f3a..28982630bef3 100644 --- a/net/openvswitch/Makefile +++ b/net/openvswitch/Makefile @@ -13,6 +13,7 @@ openvswitch-y := \ flow_netlink.o \ flow_table.o \ meter.o \ + openvswitch_trace.o \ vport.o \ vport-internal_dev.o \ vport-netdev.o @@ -24,3 +25,5 @@ endif obj-$(CONFIG_OPENVSWITCH_VXLAN)+= vport-vxlan.o obj-$(CONFIG_OPENVSWITCH_GENEVE)+= vport-geneve.o obj-$(CONFIG_OPENVSWITCH_GRE) += vport-gre.o + +CFLAGS_openvswitch_trace.o = -I$(src) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 77d924ab8cdb..ef15d9eb4774 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -30,6 +30,7 @@ #include "conntrack.h" #include "vport.h" #include "flow_netlink.h" +#include "openvswitch_trace.h" struct deferred_action { struct sk_buff *skb; @@ -1242,6 +1243,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, a = nla_next(a, &rem)) { int err = 0; + if (trace_ovs_do_execute_action_enabled()) + trace_ovs_do_execute_action(dp, skb, key, a, rem); + switch (nla_type(a)) { case OVS_ACTION_ATTR_OUTPUT: { int port = nla_get_u32(a); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index cadb6a29b285..1b5eae57bc90 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -967,8 +967,7 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, /* Associate skb with specified zone. */ if (tmpl) { - if (skb_nfct(skb)) - nf_conntrack_put(skb_nfct(skb)); + nf_conntrack_put(skb_nfct(skb)); nf_conntrack_get(&tmpl->ct_general); nf_ct_set(skb, tmpl, IP_CT_NEW); } @@ -1329,11 +1328,9 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) { - if (skb_nfct(skb)) { - nf_conntrack_put(skb_nfct(skb)); - nf_ct_set(skb, NULL, IP_CT_UNTRACKED); - ovs_ct_fill_key(skb, key, false); - } + nf_conntrack_put(skb_nfct(skb)); + nf_ct_set(skb, NULL, IP_CT_UNTRACKED); + ovs_ct_fill_key(skb, key, false); return 0; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 9d6ef6cb9b26..bc164b35e67d 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -43,6 +43,7 @@ #include "flow_table.h" #include "flow_netlink.h" #include "meter.h" +#include "openvswitch_trace.h" #include "vport-internal_dev.h" #include "vport-netdev.h" @@ -275,6 +276,9 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, struct dp_stats_percpu *stats; int err; + if (trace_ovs_dp_upcall_enabled()) + trace_ovs_dp_upcall(dp, skb, key, upcall_info); + if (upcall_info->portid == 0) { err = -ENOTCONN; goto err; diff --git a/net/openvswitch/openvswitch_trace.c b/net/openvswitch/openvswitch_trace.c new file mode 100644 index 000000000000..62c5f7d6f023 --- /dev/null +++ b/net/openvswitch/openvswitch_trace.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +/* bug in tracepoint.h, it should include this */ +#include + +/* sparse isn't too happy with all macros... */ +#ifndef __CHECKER__ +#define CREATE_TRACE_POINTS +#include "openvswitch_trace.h" + +#endif diff --git a/net/openvswitch/openvswitch_trace.h b/net/openvswitch/openvswitch_trace.h new file mode 100644 index 000000000000..3eb35d9eb700 --- /dev/null +++ b/net/openvswitch/openvswitch_trace.h @@ -0,0 +1,158 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM openvswitch + +#if !defined(_TRACE_OPENVSWITCH_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_OPENVSWITCH_H + +#include + +#include "datapath.h" + +TRACE_EVENT(ovs_do_execute_action, + + TP_PROTO(struct datapath *dp, struct sk_buff *skb, + struct sw_flow_key *key, const struct nlattr *a, int rem), + + TP_ARGS(dp, skb, key, a, rem), + + TP_STRUCT__entry( + __field( void *, dpaddr ) + __string( dp_name, ovs_dp_name(dp) ) + __string( dev_name, skb->dev->name ) + __field( void *, skbaddr ) + __field( unsigned int, len ) + __field( unsigned int, data_len ) + __field( unsigned int, truesize ) + __field( u8, nr_frags ) + __field( u16, gso_size ) + __field( u16, gso_type ) + __field( u32, ovs_flow_hash ) + __field( u32, recirc_id ) + __field( void *, keyaddr ) + __field( u16, key_eth_type ) + __field( u8, key_ct_state ) + __field( u8, key_ct_orig_proto ) + __field( u16, key_ct_zone ) + __field( unsigned int, flow_key_valid ) + __field( u8, action_type ) + __field( unsigned int, action_len ) + __field( void *, action_data ) + __field( u8, is_last ) + ), + + TP_fast_assign( + __entry->dpaddr = dp; + __assign_str(dp_name, ovs_dp_name(dp)); + __assign_str(dev_name, skb->dev->name); + __entry->skbaddr = skb; + __entry->len = skb->len; + __entry->data_len = skb->data_len; + __entry->truesize = skb->truesize; + __entry->nr_frags = skb_shinfo(skb)->nr_frags; + __entry->gso_size = skb_shinfo(skb)->gso_size; + __entry->gso_type = skb_shinfo(skb)->gso_type; + __entry->ovs_flow_hash = key->ovs_flow_hash; + __entry->recirc_id = key->recirc_id; + __entry->keyaddr = key; + __entry->key_eth_type = key->eth.type; + __entry->key_ct_state = key->ct_state; + __entry->key_ct_orig_proto = key->ct_orig_proto; + __entry->key_ct_zone = key->ct_zone; + __entry->flow_key_valid = !(key->mac_proto & SW_FLOW_KEY_INVALID); + __entry->action_type = nla_type(a); + __entry->action_len = nla_len(a); + __entry->action_data = nla_data(a); + __entry->is_last = nla_is_last(a, rem); + ), + + TP_printk("dpaddr=%p dp_name=%s dev=%s skbaddr=%p len=%u data_len=%u truesize=%u nr_frags=%d gso_size=%d gso_type=%#x ovs_flow_hash=0x%08x recirc_id=0x%08x keyaddr=%p eth_type=0x%04x ct_state=%02x ct_orig_proto=%02x ct_Zone=%04x flow_key_valid=%d action_type=%u action_len=%u action_data=%p is_last=%d", + __entry->dpaddr, __get_str(dp_name), __get_str(dev_name), + __entry->skbaddr, __entry->len, __entry->data_len, + __entry->truesize, __entry->nr_frags, __entry->gso_size, + __entry->gso_type, __entry->ovs_flow_hash, + __entry->recirc_id, __entry->keyaddr, __entry->key_eth_type, + __entry->key_ct_state, __entry->key_ct_orig_proto, + __entry->key_ct_zone, + __entry->flow_key_valid, + __entry->action_type, __entry->action_len, + __entry->action_data, __entry->is_last) +); + +TRACE_EVENT(ovs_dp_upcall, + + TP_PROTO(struct datapath *dp, struct sk_buff *skb, + const struct sw_flow_key *key, + const struct dp_upcall_info *upcall_info), + + TP_ARGS(dp, skb, key, upcall_info), + + TP_STRUCT__entry( + __field( void *, dpaddr ) + __string( dp_name, ovs_dp_name(dp) ) + __string( dev_name, skb->dev->name ) + __field( void *, skbaddr ) + __field( unsigned int, len ) + __field( unsigned int, data_len ) + __field( unsigned int, truesize ) + __field( u8, nr_frags ) + __field( u16, gso_size ) + __field( u16, gso_type ) + __field( u32, ovs_flow_hash ) + __field( u32, recirc_id ) + __field( const void *, keyaddr ) + __field( u16, key_eth_type ) + __field( u8, key_ct_state ) + __field( u8, key_ct_orig_proto ) + __field( u16, key_ct_zone ) + __field( unsigned int, flow_key_valid ) + __field( u8, upcall_cmd ) + __field( u32, upcall_port ) + __field( u16, upcall_mru ) + ), + + TP_fast_assign( + __entry->dpaddr = dp; + __assign_str(dp_name, ovs_dp_name(dp)); + __assign_str(dev_name, skb->dev->name); + __entry->skbaddr = skb; + __entry->len = skb->len; + __entry->data_len = skb->data_len; + __entry->truesize = skb->truesize; + __entry->nr_frags = skb_shinfo(skb)->nr_frags; + __entry->gso_size = skb_shinfo(skb)->gso_size; + __entry->gso_type = skb_shinfo(skb)->gso_type; + __entry->ovs_flow_hash = key->ovs_flow_hash; + __entry->recirc_id = key->recirc_id; + __entry->keyaddr = key; + __entry->key_eth_type = key->eth.type; + __entry->key_ct_state = key->ct_state; + __entry->key_ct_orig_proto = key->ct_orig_proto; + __entry->key_ct_zone = key->ct_zone; + __entry->flow_key_valid = !(key->mac_proto & SW_FLOW_KEY_INVALID); + __entry->upcall_cmd = upcall_info->cmd; + __entry->upcall_port = upcall_info->portid; + __entry->upcall_mru = upcall_info->mru; + ), + + TP_printk("dpaddr=%p dp_name=%s dev=%s skbaddr=%p len=%u data_len=%u truesize=%u nr_frags=%d gso_size=%d gso_type=%#x ovs_flow_hash=0x%08x recirc_id=0x%08x keyaddr=%p eth_type=0x%04x ct_state=%02x ct_orig_proto=%02x ct_zone=%04x flow_key_valid=%d upcall_cmd=%u upcall_port=%u upcall_mru=%u", + __entry->dpaddr, __get_str(dp_name), __get_str(dev_name), + __entry->skbaddr, __entry->len, __entry->data_len, + __entry->truesize, __entry->nr_frags, __entry->gso_size, + __entry->gso_type, __entry->ovs_flow_hash, + __entry->recirc_id, __entry->keyaddr, __entry->key_eth_type, + __entry->key_ct_state, __entry->key_ct_orig_proto, + __entry->key_ct_zone, + __entry->flow_key_valid, + __entry->upcall_cmd, __entry->upcall_port, + __entry->upcall_mru) +); + +#endif /* _TRACE_OPENVSWITCH_H */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE openvswitch_trace +#include diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index d56941d51e20..57a1971f29e5 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3207,7 +3207,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, } else { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } out_unlock: @@ -3935,12 +3935,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, return -EFAULT; lock_sock(sk); - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { - ret = -EBUSY; - } else { + if (!po->rx_ring.pg_vec && !po->tx_ring.pg_vec) po->tp_tx_has_off = !!val; - ret = 0; - } + release_sock(sk); return 0; } @@ -4107,7 +4104,7 @@ static int packet_notifier(struct notifier_block *this, __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 8d00dfe8139e..1990d496fcfc 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -775,8 +775,10 @@ int qrtr_ns_init(void) } qrtr_ns.workqueue = alloc_workqueue("qrtr_ns_handler", WQ_UNBOUND, 1); - if (!qrtr_ns.workqueue) + if (!qrtr_ns.workqueue) { + ret = -ENOMEM; goto err_sock; + } qrtr_ns.sock->sk->sk_data_ready = qrtr_ns_data_ready; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index f2efaa4225f9..e6f4a6202f82 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -751,7 +751,7 @@ static void qrtr_reset_ports(void) xa_for_each_start(&qrtr_ports, index, ipc, 1) { sock_hold(&ipc->sk); ipc->sk.sk_err = ENETRESET; - ipc->sk.sk_error_report(&ipc->sk); + sk_error_report(&ipc->sk); sock_put(&ipc->sk); } rcu_read_unlock(); diff --git a/net/rds/ib_ring.c b/net/rds/ib_ring.c index ff97e8eda858..006b2e441418 100644 --- a/net/rds/ib_ring.c +++ b/net/rds/ib_ring.c @@ -141,7 +141,7 @@ int rds_ib_ring_low(struct rds_ib_work_ring *ring) } /* - * returns the oldest alloced ring entry. This will be the next one + * returns the oldest allocated ring entry. This will be the next one * freed. This can't be called if there are none allocated. */ u32 rds_ib_ring_oldest(struct rds_ib_work_ring *ring) diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index 42c5ff1eda95..f4ee13da90c7 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -177,7 +177,7 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb, goto out; } tc->t_tinc = tinc; - rdsdebug("alloced tinc %p\n", tinc); + rdsdebug("allocated tinc %p\n", tinc); rds_inc_path_init(&tinc->ti_inc, cp, &cp->cp_conn->c_faddr); tinc->ti_inc.i_rx_lat_trace[RDS_MSG_RX_HDR] = diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 3ce6d628cd75..19e929c7c38b 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -77,7 +77,7 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, } /* - * Process event packets targetted at a local endpoint. + * Process event packets targeted at a local endpoint. */ void rxrpc_process_local_events(struct rxrpc_local *local) { diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f6d5755d669e..d17a66aab8ee 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -381,7 +381,8 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, } mutex_unlock(&idrinfo->lock); - if (nla_put_u32(skb, TCA_FCNT, n_i)) + ret = nla_put_u32(skb, TCA_FCNT, n_i); + if (ret) goto nla_put_failure; nla_nest_end(skb, nest); diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index e48e980c3b93..e409a0005717 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -43,7 +43,6 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, tcf_lastuse_update(&prog->tcf_tm); bstats_cpu_update(this_cpu_ptr(prog->common.cpu_bstats), skb); - rcu_read_lock(); filter = rcu_dereference(prog->filter); if (at_ingress) { __skb_push(skb, skb->mac_len); @@ -56,7 +55,6 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, } if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK) skb_orphan(skb); - rcu_read_unlock(); /* A BPF program may overwrite the default action opcode. * Similarly as in cls_bpf, if filter_res == -1 we use the diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 1cac3c6fbb49..71f2015c70ca 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -70,7 +70,7 @@ static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a, /* replace the vid */ tci = (tci & ~VLAN_VID_MASK) | p->tcfv_push_vid; /* replace prio bits, if tcfv_push_prio specified */ - if (p->tcfv_push_prio) { + if (p->tcfv_push_prio_exists) { tci &= ~VLAN_PRIO_MASK; tci |= p->tcfv_push_prio << VLAN_PRIO_SHIFT; } @@ -121,6 +121,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, struct tc_action_net *tn = net_generic(net, vlan_net_id); struct nlattr *tb[TCA_VLAN_MAX + 1]; struct tcf_chain *goto_ch = NULL; + bool push_prio_exists = false; struct tcf_vlan_params *p; struct tc_vlan *parm; struct tcf_vlan *v; @@ -189,7 +190,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, push_proto = htons(ETH_P_8021Q); } - if (tb[TCA_VLAN_PUSH_VLAN_PRIORITY]) + push_prio_exists = !!tb[TCA_VLAN_PUSH_VLAN_PRIORITY]; + if (push_prio_exists) push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]); break; case TCA_VLAN_ACT_POP_ETH: @@ -241,6 +243,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, p->tcfv_action = action; p->tcfv_push_vid = push_vid; p->tcfv_push_prio = push_prio; + p->tcfv_push_prio_exists = push_prio_exists || action == TCA_VLAN_ACT_PUSH; p->tcfv_push_proto = push_proto; if (action == TCA_VLAN_ACT_PUSH_ETH) { @@ -304,8 +307,8 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, p->tcfv_push_vid) || nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, p->tcfv_push_proto) || - (nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, - p->tcfv_push_prio)))) + (p->tcfv_push_prio_exists && + nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY, p->tcfv_push_prio)))) goto nla_put_failure; if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) { diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 279f9e2a2319..d73b5c5514a9 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1531,7 +1531,7 @@ static inline int __tcf_classify(struct sk_buff *skb, u32 *last_executed_chain) { #ifdef CONFIG_NET_CLS_ACT - const int max_reclassify_loop = 4; + const int max_reclassify_loop = 16; const struct tcf_proto *first_tp; int limit = 0; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 6e3e63db0e01..fa739efa59f4 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -85,8 +85,6 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_bpf_prog *prog; int ret = -1; - /* Needed here for accessing maps. */ - rcu_read_lock(); list_for_each_entry_rcu(prog, &head->plist, link) { int filter_res; @@ -131,7 +129,6 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, break; } - rcu_read_unlock(); return ret; } diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 2e288f88ff02..27a4b6dbcf57 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -7,7 +7,7 @@ /* Comparing to general packet classification problem, - RSVP needs only sevaral relatively simple rules: + RSVP needs only several relatively simple rules: * (dst, protocol) are always specified, so that we are able to hash them. diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index c4007b9cd16d..5b274534264c 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -304,7 +304,7 @@ static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) int i, err = 0; cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!cp->perfect) return -ENOMEM; diff --git a/net/sched/ematch.c b/net/sched/ematch.c index f885bea5b452..4ce681361851 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -141,7 +141,7 @@ errout: EXPORT_SYMBOL(tcf_em_register); /** - * tcf_em_unregister - unregster and extended match + * tcf_em_unregister - unregister and extended match * * @ops: ematch operations lookup table * diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index fc8b56bcabf3..d9ac60ffe927 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -52,6 +52,8 @@ static void qdisc_maybe_clear_missed(struct Qdisc *q, */ if (!netif_xmit_frozen_or_stopped(txq)) set_bit(__QDISC_STATE_MISSED, &q->state); + else + set_bit(__QDISC_STATE_DRAINING, &q->state); } /* Main transmission queue. */ @@ -164,9 +166,13 @@ static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) skb = next; } - if (lock) + + if (lock) { spin_unlock(lock); - __netif_schedule(q); + set_bit(__QDISC_STATE_MISSED, &q->state); + } else { + __netif_schedule(q); + } } static void try_bulk_dequeue_skb(struct Qdisc *q, @@ -409,7 +415,11 @@ void __qdisc_run(struct Qdisc *q) while (qdisc_restart(q, &packets)) { quota -= packets; if (quota <= 0) { - __netif_schedule(q); + if (q->flags & TCQ_F_NOLOCK) + set_bit(__QDISC_STATE_MISSED, &q->state); + else + __netif_schedule(q); + break; } } @@ -540,6 +550,24 @@ void netif_carrier_off(struct net_device *dev) } EXPORT_SYMBOL(netif_carrier_off); +/** + * netif_carrier_event - report carrier state event + * @dev: network device + * + * Device has detected a carrier event but the carrier state wasn't changed. + * Use in drivers when querying carrier state asynchronously, to avoid missing + * events (link flaps) if link recovers before it's queried. + */ +void netif_carrier_event(struct net_device *dev) +{ + if (dev->reg_state == NETREG_UNINITIALIZED) + return; + atomic_inc(&dev->carrier_up_count); + atomic_inc(&dev->carrier_down_count); + linkwatch_fire_event(dev); +} +EXPORT_SYMBOL_GPL(netif_carrier_event); + /* "NOOP" scheduler: the best scheduler, recommended for all interfaces under all circumstances. It is difficult to invent anything faster or cheaper. @@ -680,13 +708,14 @@ retry: if (likely(skb)) { qdisc_update_stats_at_dequeue(qdisc, skb); } else if (need_retry && - test_bit(__QDISC_STATE_MISSED, &qdisc->state)) { + READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY) { /* Delay clearing the STATE_MISSED here to reduce * the overhead of the second spin_trylock() in * qdisc_run_begin() and __netif_schedule() calling * in qdisc_run_end(). */ clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); /* Make sure dequeuing happens after clearing * STATE_MISSED. @@ -696,8 +725,6 @@ retry: need_retry = false; goto retry; - } else { - WRITE_ONCE(qdisc->empty, true); } return skb; @@ -898,7 +925,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; - sch->empty = true; dev_hold(dev); refcount_set(&sch->refcnt, 1); @@ -1204,6 +1230,7 @@ static void dev_reset_queue(struct net_device *dev, spin_unlock_bh(qdisc_lock(qdisc)); if (nolock) { clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); spin_unlock_bh(&qdisc->seqlock); } } diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index f4132dc25ac0..621dc6afde8f 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -6,7 +6,7 @@ * * 991129: - Bug fix with grio mode * - a better sing. AvgQ mode with Grio(WRED) - * - A finer grained VQ dequeue based on sugestion + * - A finer grained VQ dequeue based on suggestion * from Ren Liu * - More error checks * diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 8827987ba903..5f7ac27a5264 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -52,7 +52,7 @@ */ static int htb_hysteresis __read_mostly = 0; /* whether to use mode hysteresis for speedup */ -#define HTB_VER 0x30011 /* major must be matched with number suplied by TC as version */ +#define HTB_VER 0x30011 /* major must be matched with number supplied by TC as version */ #if HTB_VER >> 16 != TC_HTB_PROTOVER #error "Mismatched sch_htb.c and pkt_sch.h" @@ -273,6 +273,9 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, /** * htb_add_to_id_tree - adds class to the round robin list + * @root: the root of the tree + * @cl: the class to add + * @prio: the give prio in class * * Routine adds class to the list (actually tree) sorted by classid. * Make sure that class is not already on such list for given prio. @@ -298,6 +301,9 @@ static void htb_add_to_id_tree(struct rb_root *root, /** * htb_add_to_wait_tree - adds class to the event queue with delay + * @q: the priority event queue + * @cl: the class to add + * @delay: delay in microseconds * * The class is added to priority event queue to indicate that class will * change its mode in cl->pq_key microseconds. Make sure that class is not @@ -331,6 +337,7 @@ static void htb_add_to_wait_tree(struct htb_sched *q, /** * htb_next_rb_node - finds next node in binary tree + * @n: the current node in binary tree * * When we are past last key we return NULL. * Average complexity is 2 steps per call. @@ -342,6 +349,9 @@ static inline void htb_next_rb_node(struct rb_node **n) /** * htb_add_class_to_row - add class to its row + * @q: the priority event queue + * @cl: the class to add + * @mask: the given priorities in class in bitmap * * The class is added to row at priorities marked in mask. * It does nothing if mask == 0. @@ -371,6 +381,9 @@ static void htb_safe_rb_erase(struct rb_node *rb, struct rb_root *root) /** * htb_remove_class_from_row - removes class from its row + * @q: the priority event queue + * @cl: the class to add + * @mask: the given priorities in class in bitmap * * The class is removed from row at priorities marked in mask. * It does nothing if mask == 0. @@ -398,6 +411,8 @@ static inline void htb_remove_class_from_row(struct htb_sched *q, /** * htb_activate_prios - creates active classe's feed chain + * @q: the priority event queue + * @cl: the class to activate * * The class is connected to ancestors and/or appropriate rows * for priorities it is participating on. cl->cmode must be new @@ -433,6 +448,8 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) /** * htb_deactivate_prios - remove class from feed chain + * @q: the priority event queue + * @cl: the class to deactivate * * cl->cmode must represent old mode (before deactivation). It does * nothing if cl->prio_activity == 0. Class is removed from all feed @@ -493,6 +510,8 @@ static inline s64 htb_hiwater(const struct htb_class *cl) /** * htb_class_mode - computes and returns current class mode + * @cl: the target class + * @diff: diff time in microseconds * * It computes cl's mode at time cl->t_c+diff and returns it. If mode * is not HTB_CAN_SEND then cl->pq_key is updated to time difference @@ -521,9 +540,12 @@ htb_class_mode(struct htb_class *cl, s64 *diff) /** * htb_change_class_mode - changes classe's mode + * @q: the priority event queue + * @cl: the target class + * @diff: diff time in microseconds * * This should be the only way how to change classe's mode under normal - * cirsumstances. Routine will update feed lists linkage, change mode + * circumstances. Routine will update feed lists linkage, change mode * and add class to the wait event queue if appropriate. New mode should * be different from old one and cl->pq_key has to be valid if changing * to mode other than HTB_CAN_SEND (see htb_add_to_wait_tree). @@ -553,6 +575,8 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) /** * htb_activate - inserts leaf cl into appropriate active feeds + * @q: the priority event queue + * @cl: the target class * * Routine learns (new) priority of leaf and activates feed chain * for the prio. It can be called on already active leaf safely. @@ -570,6 +594,8 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) /** * htb_deactivate - remove leaf cl from active feeds + * @q: the priority event queue + * @cl: the target class * * Make sure that leaf is active. In the other words it can't be called * with non-active leaf. It also removes class from the drop list. @@ -649,6 +675,10 @@ static inline void htb_accnt_ctokens(struct htb_class *cl, int bytes, s64 diff) /** * htb_charge_class - charges amount "bytes" to leaf and ancestors + * @q: the priority event queue + * @cl: the class to start iterate + * @level: the minimum level to account + * @skb: the socket buffer * * Routine assumes that packet "bytes" long was dequeued from leaf cl * borrowing from "level". It accounts bytes to ceil leaky bucket for @@ -698,6 +728,9 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl, /** * htb_do_events - make mode changes to classes at the level + * @q: the priority event queue + * @level: which wait_pq in 'q->hlevel' + * @start: start jiffies * * Scans event queue for pending events and applies them. Returns time of * next pending event (0 for no event in pq, q->now for too many events). @@ -766,6 +799,8 @@ static struct rb_node *htb_id_find_next_upper(int prio, struct rb_node *n, /** * htb_lookup_leaf - returns next leaf class in DRR order + * @hprio: the current one + * @prio: which prio in class * * Find leaf where current feed pointers points to. */ diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 1db9d4a2ef5e..b692a0de1ad5 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -485,11 +485,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (cl->qdisc != &noop_qdisc) qdisc_hash_add(cl->qdisc, true); - sch_tree_lock(sch); - qdisc_class_hash_insert(&q->clhash, &cl->common); - sch_tree_unlock(sch); - - qdisc_class_hash_grow(sch, &q->clhash); set_change_agg: sch_tree_lock(sch); @@ -507,8 +502,11 @@ set_change_agg: } if (existing) qfq_deact_rm_from_agg(q, cl); + else + qdisc_class_hash_insert(&q->clhash, &cl->common); qfq_add_to_agg(q, new_agg, cl); sch_tree_unlock(sch); + qdisc_class_hash_grow(sch, &q->clhash); *arg = (unsigned long)cl; return 0; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 5c91df52b8c2..66fe2b82af9a 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -114,9 +114,6 @@ static void taprio_free_sched_cb(struct rcu_head *head) struct sched_gate_list *sched = container_of(head, struct sched_gate_list, rcu); struct sched_entry *entry, *n; - if (!sched) - return; - list_for_each_entry_safe(entry, n, &sched->entries, list) { list_del(&entry->list); kfree(entry); @@ -438,6 +435,11 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct Qdisc *child; int queue; + if (unlikely(FULL_OFFLOAD_IS_ENABLED(q->flags))) { + WARN_ONCE(1, "Trying to enqueue skb into the root of a taprio qdisc configured with full offload\n"); + return qdisc_drop(skb, sch, to_free); + } + queue = skb_get_queue_mapping(skb); child = q->qdiscs[queue]; @@ -529,23 +531,7 @@ static struct sk_buff *taprio_peek_soft(struct Qdisc *sch) static struct sk_buff *taprio_peek_offload(struct Qdisc *sch) { - struct taprio_sched *q = qdisc_priv(sch); - struct net_device *dev = qdisc_dev(sch); - struct sk_buff *skb; - int i; - - for (i = 0; i < dev->num_tx_queues; i++) { - struct Qdisc *child = q->qdiscs[i]; - - if (unlikely(!child)) - continue; - - skb = child->ops->peek(child); - if (!skb) - continue; - - return skb; - } + WARN_ONCE(1, "Trying to peek into the root of a taprio qdisc configured with full offload\n"); return NULL; } @@ -654,27 +640,7 @@ done: static struct sk_buff *taprio_dequeue_offload(struct Qdisc *sch) { - struct taprio_sched *q = qdisc_priv(sch); - struct net_device *dev = qdisc_dev(sch); - struct sk_buff *skb; - int i; - - for (i = 0; i < dev->num_tx_queues; i++) { - struct Qdisc *child = q->qdiscs[i]; - - if (unlikely(!child)) - continue; - - skb = child->ops->dequeue(child); - if (unlikely(!skb)) - continue; - - qdisc_bstats_update(sch, skb); - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; - - return skb; - } + WARN_ONCE(1, "Trying to dequeue from the root of a taprio qdisc configured with full offload\n"); return NULL; } @@ -1759,6 +1725,37 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, return taprio_change(sch, opt, extack); } +static void taprio_attach(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + unsigned int ntx; + + /* Attach underlying qdisc */ + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + struct Qdisc *qdisc = q->qdiscs[ntx]; + struct Qdisc *old; + + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { + qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + old = dev_graft_qdisc(qdisc->dev_queue, qdisc); + if (ntx < dev->real_num_tx_queues) + qdisc_hash_add(qdisc, false); + } else { + old = dev_graft_qdisc(qdisc->dev_queue, sch); + qdisc_refcount_inc(sch); + } + if (old) + qdisc_put(old); + } + + /* access to the child qdiscs is not needed in offload mode */ + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { + kfree(q->qdiscs); + q->qdiscs = NULL; + } +} + static struct netdev_queue *taprio_queue_get(struct Qdisc *sch, unsigned long cl) { @@ -1785,8 +1782,12 @@ static int taprio_graft(struct Qdisc *sch, unsigned long cl, if (dev->flags & IFF_UP) dev_deactivate(dev); - *old = q->qdiscs[cl - 1]; - q->qdiscs[cl - 1] = new; + if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { + *old = dev_graft_qdisc(dev_queue, new); + } else { + *old = q->qdiscs[cl - 1]; + q->qdiscs[cl - 1] = new; + } if (new) new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; @@ -2020,6 +2021,7 @@ static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { .change = taprio_change, .destroy = taprio_destroy, .reset = taprio_reset, + .attach = taprio_attach, .peek = taprio_peek, .dequeue = taprio_dequeue, .enqueue = taprio_enqueue, diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 336df4b36655..be29da09cc7a 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -98,6 +98,7 @@ static struct sctp_association *sctp_association_init( * sock configured value. */ asoc->hbinterval = msecs_to_jiffies(sp->hbinterval); + asoc->probe_interval = msecs_to_jiffies(sp->probe_interval); asoc->encap_port = sp->encap_port; @@ -625,6 +626,7 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, * association configured value. */ peer->hbinterval = asoc->hbinterval; + peer->probe_interval = asoc->probe_interval; peer->encap_port = asoc->encap_port; @@ -714,6 +716,8 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, return NULL; } + sctp_transport_pl_reset(peer); + /* Attach the remote transport to our asoc. */ list_add_tail_rcu(&peer->transports, &asoc->peer.transport_addr_list); asoc->peer.transport_count++; @@ -812,6 +816,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, spc_state = SCTP_ADDR_CONFIRMED; transport->state = SCTP_ACTIVE; + sctp_transport_pl_reset(transport); break; case SCTP_TRANSPORT_DOWN: @@ -821,6 +826,7 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, */ if (transport->state != SCTP_UNCONFIRMED) { transport->state = SCTP_INACTIVE; + sctp_transport_pl_reset(transport); spc_state = SCTP_ADDR_UNREACHABLE; } else { sctp_transport_dst_release(transport); diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 53e5ed79f63f..59e653b528b1 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -270,22 +270,19 @@ int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw_addr_list, rawaddr = (union sctp_addr_param *)raw_addr_list; af = sctp_get_af_specific(param_type2af(param->type)); - if (unlikely(!af)) { + if (unlikely(!af) || + !af->from_addr_param(&addr, rawaddr, htons(port), 0)) { retval = -EINVAL; - sctp_bind_addr_clean(bp); - break; + goto out_err; } - af->from_addr_param(&addr, rawaddr, htons(port), 0); if (sctp_bind_addr_state(bp, &addr) != -1) goto next; retval = sctp_add_bind_addr(bp, &addr, sizeof(addr), SCTP_ADDR_SRC, gfp); - if (retval) { + if (retval) /* Can't finish building the list, clean up. */ - sctp_bind_addr_clean(bp); - break; - } + goto out_err; next: len = ntohs(param->length); @@ -294,6 +291,12 @@ next: } return retval; + +out_err: + if (retval) + sctp_bind_addr_clean(bp); + + return retval; } /******************************************************************** diff --git a/net/sctp/debug.c b/net/sctp/debug.c index c4d9c7feffb9..ccd773e4c371 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -154,6 +154,7 @@ static const char *const sctp_timer_tbl[] = { "TIMEOUT_T5_SHUTDOWN_GUARD", "TIMEOUT_HEARTBEAT", "TIMEOUT_RECONF", + "TIMEOUT_PROBE", "TIMEOUT_SACK", "TIMEOUT_AUTOCLOSE", }; diff --git a/net/sctp/input.c b/net/sctp/input.c index 5ceaf75105ba..eb3c2a34a31c 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -385,7 +385,9 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, struct sctp_transport *t, __u32 pmtu) { - if (!t || (t->pathmtu <= pmtu)) + if (!t || + (t->pathmtu <= pmtu && + t->pl.probe_size + sctp_transport_pl_hlen(t) <= pmtu)) return; if (sock_owned_by_user(sk)) { @@ -554,6 +556,50 @@ void sctp_err_finish(struct sock *sk, struct sctp_transport *t) sctp_transport_put(t); } +static void sctp_v4_err_handle(struct sctp_transport *t, struct sk_buff *skb, + __u8 type, __u8 code, __u32 info) +{ + struct sctp_association *asoc = t->asoc; + struct sock *sk = asoc->base.sk; + int err = 0; + + switch (type) { + case ICMP_PARAMETERPROB: + err = EPROTO; + break; + case ICMP_DEST_UNREACH: + if (code > NR_ICMP_UNREACH) + return; + if (code == ICMP_FRAG_NEEDED) { + sctp_icmp_frag_needed(sk, asoc, t, SCTP_TRUNC4(info)); + return; + } + if (code == ICMP_PROT_UNREACH) { + sctp_icmp_proto_unreachable(sk, asoc, t); + return; + } + err = icmp_err_convert[code].errno; + break; + case ICMP_TIME_EXCEEDED: + if (code == ICMP_EXC_FRAGTIME) + return; + + err = EHOSTUNREACH; + break; + case ICMP_REDIRECT: + sctp_icmp_redirect(sk, t, skb); + return; + default: + return; + } + if (!sock_owned_by_user(sk) && inet_sk(sk)->recverr) { + sk->sk_err = err; + sk_error_report(sk); + } else { /* Only an error on timeout */ + sk->sk_err_soft = err; + } +} + /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should @@ -572,22 +618,19 @@ void sctp_err_finish(struct sock *sk, struct sctp_transport *t) int sctp_v4_err(struct sk_buff *skb, __u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; - const int ihlen = iph->ihl * 4; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; - struct sock *sk; - struct sctp_association *asoc = NULL; - struct sctp_transport *transport; - struct inet_sock *inet; - __u16 saveip, savesctp; - int err; struct net *net = dev_net(skb->dev); + struct sctp_transport *transport; + struct sctp_association *asoc; + __u16 saveip, savesctp; + struct sock *sk; /* Fix up skb to look at the embedded net header. */ saveip = skb->network_header; savesctp = skb->transport_header; skb_reset_network_header(skb); - skb_set_transport_header(skb, ihlen); + skb_set_transport_header(skb, iph->ihl * 4); sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &transport); /* Put back, the original values. */ skb->network_header = saveip; @@ -596,61 +639,43 @@ int sctp_v4_err(struct sk_buff *skb, __u32 info) __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; } - /* Warning: The sock lock is held. Remember to call - * sctp_err_finish! - */ - switch (type) { - case ICMP_PARAMETERPROB: - err = EPROTO; - break; - case ICMP_DEST_UNREACH: - if (code > NR_ICMP_UNREACH) - goto out_unlock; - - /* PMTU discovery (RFC1191) */ - if (ICMP_FRAG_NEEDED == code) { - sctp_icmp_frag_needed(sk, asoc, transport, - SCTP_TRUNC4(info)); - goto out_unlock; - } else { - if (ICMP_PROT_UNREACH == code) { - sctp_icmp_proto_unreachable(sk, asoc, - transport); - goto out_unlock; - } - } - err = icmp_err_convert[code].errno; - break; - case ICMP_TIME_EXCEEDED: - /* Ignore any time exceeded errors due to fragment reassembly - * timeouts. - */ - if (ICMP_EXC_FRAGTIME == code) - goto out_unlock; - - err = EHOSTUNREACH; - break; - case ICMP_REDIRECT: - sctp_icmp_redirect(sk, transport, skb); - goto out_unlock; - default: - goto out_unlock; - } - - inet = inet_sk(sk); - if (!sock_owned_by_user(sk) && inet->recverr) { - sk->sk_err = err; - sk->sk_error_report(sk); - } else { /* Only an error on timeout */ - sk->sk_err_soft = err; - } - -out_unlock: + sctp_v4_err_handle(transport, skb, type, code, info); sctp_err_finish(sk, transport); + return 0; } +int sctp_udp_v4_err(struct sock *sk, struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + struct sctp_association *asoc; + struct sctp_transport *t; + struct icmphdr *hdr; + __u32 info = 0; + + skb->transport_header += sizeof(struct udphdr); + sk = sctp_err_lookup(net, AF_INET, skb, sctp_hdr(skb), &asoc, &t); + if (!sk) { + __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); + return -ENOENT; + } + + skb->transport_header -= sizeof(struct udphdr); + hdr = (struct icmphdr *)(skb_network_header(skb) - sizeof(struct icmphdr)); + if (hdr->type == ICMP_REDIRECT) { + /* can't be handled without outer iphdr known, leave it to udp_err */ + sctp_err_finish(sk, t); + return 0; + } + if (hdr->type == ICMP_DEST_UNREACH && hdr->code == ICMP_FRAG_NEEDED) + info = ntohs(hdr->un.frag.mtu); + sctp_v4_err_handle(t, skb, hdr->type, hdr->code, info); + + sctp_err_finish(sk, t); + return 1; +} + /* * RFC 2960, 8.4 - Handle "Out of the blue" Packets. * @@ -1131,7 +1156,8 @@ static struct sctp_association *__sctp_rcv_init_lookup(struct net *net, if (!af) continue; - af->from_addr_param(paddr, params.addr, sh->source, 0); + if (!af->from_addr_param(paddr, params.addr, sh->source, 0)) + continue; asoc = __sctp_lookup_association(net, laddr, paddr, transportp); if (asoc) @@ -1167,6 +1193,9 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( union sctp_addr_param *param; union sctp_addr paddr; + if (ntohs(ch->length) < sizeof(*asconf) + sizeof(struct sctp_paramhdr)) + return NULL; + /* Skip over the ADDIP header and find the Address parameter */ param = (union sctp_addr_param *)(asconf + 1); @@ -1174,7 +1203,8 @@ static struct sctp_association *__sctp_rcv_asconf_lookup( if (unlikely(!af)) return NULL; - af->from_addr_param(&paddr, param, peer_port, 0); + if (af->from_addr_param(&paddr, param, peer_port, 0)) + return NULL; return __sctp_lookup_association(net, laddr, &paddr, transportp); } @@ -1246,7 +1276,7 @@ static struct sctp_association *__sctp_rcv_walk_lookup(struct net *net, ch = (struct sctp_chunkhdr *)ch_end; chunk_num++; - } while (ch_end < skb_tail_pointer(skb)); + } while (ch_end + sizeof(*ch) < skb_tail_pointer(skb)); return asoc; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index bd08807c9e44..e48dd909dee5 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -122,20 +122,51 @@ static struct notifier_block sctp_inet6addr_notifier = { .notifier_call = sctp_inet6addr_event, }; +static void sctp_v6_err_handle(struct sctp_transport *t, struct sk_buff *skb, + __u8 type, __u8 code, __u32 info) +{ + struct sctp_association *asoc = t->asoc; + struct sock *sk = asoc->base.sk; + struct ipv6_pinfo *np; + int err = 0; + + switch (type) { + case ICMPV6_PKT_TOOBIG: + if (ip6_sk_accept_pmtu(sk)) + sctp_icmp_frag_needed(sk, asoc, t, info); + return; + case ICMPV6_PARAMPROB: + if (ICMPV6_UNK_NEXTHDR == code) { + sctp_icmp_proto_unreachable(sk, asoc, t); + return; + } + break; + case NDISC_REDIRECT: + sctp_icmp_redirect(sk, t, skb); + return; + default: + break; + } + + np = inet6_sk(sk); + icmpv6_err_convert(type, code, &err); + if (!sock_owned_by_user(sk) && np->recverr) { + sk->sk_err = err; + sk_error_report(sk); + } else { + sk->sk_err_soft = err; + } +} + /* ICMP error handler. */ static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { - struct inet6_dev *idev; - struct sock *sk; - struct sctp_association *asoc; - struct sctp_transport *transport; - struct ipv6_pinfo *np; - __u16 saveip, savesctp; - int err, ret = 0; struct net *net = dev_net(skb->dev); - - idev = in6_dev_get(skb->dev); + struct sctp_transport *transport; + struct sctp_association *asoc; + __u16 saveip, savesctp; + struct sock *sk; /* Fix up skb to look at the embedded net header. */ saveip = skb->network_header; @@ -147,49 +178,44 @@ static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, skb->network_header = saveip; skb->transport_header = savesctp; if (!sk) { - __ICMP6_INC_STATS(net, idev, ICMP6_MIB_INERRORS); - ret = -ENOENT; - goto out; + __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); + return -ENOENT; } - /* Warning: The sock lock is held. Remember to call - * sctp_err_finish! - */ - - switch (type) { - case ICMPV6_PKT_TOOBIG: - if (ip6_sk_accept_pmtu(sk)) - sctp_icmp_frag_needed(sk, asoc, transport, ntohl(info)); - goto out_unlock; - case ICMPV6_PARAMPROB: - if (ICMPV6_UNK_NEXTHDR == code) { - sctp_icmp_proto_unreachable(sk, asoc, transport); - goto out_unlock; - } - break; - case NDISC_REDIRECT: - sctp_icmp_redirect(sk, transport, skb); - goto out_unlock; - default: - break; - } - - np = inet6_sk(sk); - icmpv6_err_convert(type, code, &err); - if (!sock_owned_by_user(sk) && np->recverr) { - sk->sk_err = err; - sk->sk_error_report(sk); - } else { /* Only an error on timeout */ - sk->sk_err_soft = err; - } - -out_unlock: + sctp_v6_err_handle(transport, skb, type, code, ntohl(info)); sctp_err_finish(sk, transport); -out: - if (likely(idev != NULL)) - in6_dev_put(idev); - return ret; + return 0; +} + +int sctp_udp_v6_err(struct sock *sk, struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + struct sctp_association *asoc; + struct sctp_transport *t; + struct icmp6hdr *hdr; + __u32 info = 0; + + skb->transport_header += sizeof(struct udphdr); + sk = sctp_err_lookup(net, AF_INET6, skb, sctp_hdr(skb), &asoc, &t); + if (!sk) { + __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); + return -ENOENT; + } + + skb->transport_header -= sizeof(struct udphdr); + hdr = (struct icmp6hdr *)(skb_network_header(skb) - sizeof(struct icmp6hdr)); + if (hdr->icmp6_type == NDISC_REDIRECT) { + /* can't be handled without outer ip6hdr known, leave it to udpv6_err */ + sctp_err_finish(sk, t); + return 0; + } + if (hdr->icmp6_type == ICMPV6_PKT_TOOBIG) + info = ntohl(hdr->icmp6_mtu); + sctp_v6_err_handle(t, skb, hdr->icmp6_type, hdr->icmp6_code, info); + + sctp_err_finish(sk, t); + return 1; } static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t) @@ -551,15 +577,20 @@ static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk) } /* Initialize a sctp_addr from an address parameter. */ -static void sctp_v6_from_addr_param(union sctp_addr *addr, +static bool sctp_v6_from_addr_param(union sctp_addr *addr, union sctp_addr_param *param, __be16 port, int iif) { + if (ntohs(param->v6.param_hdr.length) < sizeof(struct sctp_ipv6addr_param)) + return false; + addr->v6.sin6_family = AF_INET6; addr->v6.sin6_port = port; addr->v6.sin6_flowinfo = 0; /* BUG */ addr->v6.sin6_addr = param->v6.addr; addr->v6.sin6_scope_id = iif; + + return true; } /* Initialize an address parameter from a sctp_addr and return the length diff --git a/net/sctp/output.c b/net/sctp/output.c index a6aa17df09ef..9032ce60d50e 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -103,7 +103,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, sctp_transport_route(tp, NULL, sp); if (asoc->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); - } else if (!sctp_transport_pmtu_check(tp)) { + } else if (!sctp_transport_pl_enabled(tp) && + !sctp_transport_pmtu_check(tp)) { if (asoc->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); } @@ -211,6 +212,30 @@ enum sctp_xmit sctp_packet_transmit_chunk(struct sctp_packet *packet, return retval; } +/* Try to bundle a pad chunk into a packet with a heartbeat chunk for PLPMTUTD probe */ +static enum sctp_xmit sctp_packet_bundle_pad(struct sctp_packet *pkt, struct sctp_chunk *chunk) +{ + struct sctp_transport *t = pkt->transport; + struct sctp_chunk *pad; + int overhead = 0; + + if (!chunk->pmtu_probe) + return SCTP_XMIT_OK; + + /* calculate the Padding Data size for the pad chunk */ + overhead += sizeof(struct sctphdr) + sizeof(struct sctp_chunkhdr); + overhead += sizeof(struct sctp_sender_hb_info) + sizeof(struct sctp_pad_chunk); + pad = sctp_make_pad(t->asoc, t->pl.probe_size - overhead); + if (!pad) + return SCTP_XMIT_DELAY; + + list_add_tail(&pad->list, &pkt->chunk_list); + pkt->size += SCTP_PAD4(ntohs(pad->chunk_hdr->length)); + chunk->transport = t; + + return SCTP_XMIT_OK; +} + /* Try to bundle an auth chunk into the packet. */ static enum sctp_xmit sctp_packet_bundle_auth(struct sctp_packet *pkt, struct sctp_chunk *chunk) @@ -382,6 +407,10 @@ enum sctp_xmit sctp_packet_append_chunk(struct sctp_packet *packet, goto finish; retval = __sctp_packet_append_chunk(packet, chunk); + if (retval != SCTP_XMIT_OK) + goto finish; + + retval = sctp_packet_bundle_pad(packet, chunk); finish: return retval; @@ -553,7 +582,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) sk = chunk->skb->sk; /* check gso */ - if (packet->size > tp->pathmtu && !packet->ipfragok) { + if (packet->size > tp->pathmtu && !packet->ipfragok && !chunk->pmtu_probe) { if (!sk_can_gso(sk)) { pr_err_once("Trying to GSO but underlying device doesn't support it."); goto out; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 5cb1aa5f067b..ff47091c385e 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -769,7 +769,11 @@ static int sctp_packet_singleton(struct sctp_transport *transport, sctp_packet_init(&singleton, transport, sport, dport); sctp_packet_config(&singleton, vtag, 0); - sctp_packet_append_chunk(&singleton, chunk); + if (sctp_packet_append_chunk(&singleton, chunk) != SCTP_XMIT_OK) { + list_del_init(&chunk->list); + sctp_chunk_free(chunk); + return -ENOMEM; + } return sctp_packet_transmit(&singleton, gfp); } @@ -929,8 +933,13 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) one_packet = 1; fallthrough; - case SCTP_CID_SACK: case SCTP_CID_HEARTBEAT: + if (chunk->pmtu_probe) { + sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); + break; + } + fallthrough; + case SCTP_CID_SACK: case SCTP_CID_SHUTDOWN: case SCTP_CID_ECN_ECNE: case SCTP_CID_ASCONF: diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 6f2bbfeec3a4..3c1fbf38f4f7 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -254,14 +254,19 @@ static void sctp_v4_to_sk_daddr(union sctp_addr *addr, struct sock *sk) } /* Initialize a sctp_addr from an address parameter. */ -static void sctp_v4_from_addr_param(union sctp_addr *addr, +static bool sctp_v4_from_addr_param(union sctp_addr *addr, union sctp_addr_param *param, __be16 port, int iif) { + if (ntohs(param->v4.param_hdr.length) < sizeof(struct sctp_ipv4addr_param)) + return false; + addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; addr->v4.sin_addr.s_addr = param->v4.addr.s_addr; memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); + + return true; } /* Initialize an address parameter from a sctp_addr and return the length @@ -850,23 +855,6 @@ static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb) return 0; } -static int sctp_udp_err_lookup(struct sock *sk, struct sk_buff *skb) -{ - struct sctp_association *asoc; - struct sctp_transport *t; - int family; - - skb->transport_header += sizeof(struct udphdr); - family = (ip_hdr(skb)->version == 4) ? AF_INET : AF_INET6; - sk = sctp_err_lookup(dev_net(skb->dev), family, skb, sctp_hdr(skb), - &asoc, &t); - if (!sk) - return -ENOENT; - - sctp_err_finish(sk, t); - return 0; -} - int sctp_udp_sock_start(struct net *net) { struct udp_tunnel_sock_cfg tuncfg = {NULL}; @@ -885,7 +873,7 @@ int sctp_udp_sock_start(struct net *net) tuncfg.encap_type = 1; tuncfg.encap_rcv = sctp_udp_rcv; - tuncfg.encap_err_lookup = sctp_udp_err_lookup; + tuncfg.encap_err_lookup = sctp_udp_v4_err; setup_udp_tunnel_sock(net, sock, &tuncfg); net->sctp.udp4_sock = sock->sk; @@ -907,7 +895,7 @@ int sctp_udp_sock_start(struct net *net) tuncfg.encap_type = 1; tuncfg.encap_rcv = sctp_udp_rcv; - tuncfg.encap_err_lookup = sctp_udp_err_lookup; + tuncfg.encap_err_lookup = sctp_udp_v6_err; setup_udp_tunnel_sock(net, sock, &tuncfg); net->sctp.udp6_sock = sock->sk; #endif @@ -1171,7 +1159,6 @@ static const struct net_protocol sctp_protocol = { .handler = sctp4_rcv, .err_handler = sctp_v4_err, .no_policy = 1, - .netns_ok = 1, .icmp_strict_tag_validation = 1, }; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 5b44d228b6ca..6c08e5048d38 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1160,7 +1160,8 @@ nodata: /* Make a HEARTBEAT chunk. */ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, - const struct sctp_transport *transport) + const struct sctp_transport *transport, + __u32 probe_size) { struct sctp_sender_hb_info hbinfo; struct sctp_chunk *retval; @@ -1176,6 +1177,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, hbinfo.daddr = transport->ipaddr; hbinfo.sent_at = jiffies; hbinfo.hb_nonce = transport->hb_nonce; + hbinfo.probe_size = probe_size; /* Cast away the 'const', as this is just telling the chunk * what transport it belongs to. @@ -1183,6 +1185,7 @@ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, retval->transport = (struct sctp_transport *) transport; retval->subh.hbs_hdr = sctp_addto_chunk(retval, sizeof(hbinfo), &hbinfo); + retval->pmtu_probe = !!probe_size; nodata: return retval; @@ -1218,6 +1221,32 @@ nodata: return retval; } +/* RFC4820 3. Padding Chunk (PAD) + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Type = 0x84 | Flags=0 | Length | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | | + * \ Padding Data / + * / \ + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + */ +struct sctp_chunk *sctp_make_pad(const struct sctp_association *asoc, int len) +{ + struct sctp_chunk *retval; + + retval = sctp_make_control(asoc, SCTP_CID_PAD, 0, len, GFP_ATOMIC); + if (!retval) + return NULL; + + skb_put_zero(retval->skb, len); + retval->chunk_hdr->length = htons(ntohs(retval->chunk_hdr->length) + len); + retval->chunk_end = skb_tail_pointer(retval->skb); + + return retval; +} + /* Create an Operation Error chunk with the specified space reserved. * This routine can be used for containing multiple causes in the chunk. */ @@ -2166,9 +2195,16 @@ static enum sctp_ierror sctp_verify_param(struct net *net, break; case SCTP_PARAM_SET_PRIMARY: - if (ep->asconf_enable) - break; - goto unhandled; + if (!ep->asconf_enable) + goto unhandled; + + if (ntohs(param.p->length) < sizeof(struct sctp_addip_param) + + sizeof(struct sctp_paramhdr)) { + sctp_process_inv_paramlength(asoc, param.p, + chunk, err_chunk); + retval = SCTP_IERROR_ABORT; + } + break; case SCTP_PARAM_HOST_NAME_ADDRESS: /* Tell the peer, we won't support this param. */ @@ -2346,11 +2382,13 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, /* Process the initialization parameters. */ sctp_walk_params(param, peer_init, init_hdr.params) { - if (!src_match && (param.p->type == SCTP_PARAM_IPV4_ADDRESS || - param.p->type == SCTP_PARAM_IPV6_ADDRESS)) { + if (!src_match && + (param.p->type == SCTP_PARAM_IPV4_ADDRESS || + param.p->type == SCTP_PARAM_IPV6_ADDRESS)) { af = sctp_get_af_specific(param_type2af(param.p->type)); - af->from_addr_param(&addr, param.addr, - chunk->sctp_hdr->source, 0); + if (!af->from_addr_param(&addr, param.addr, + chunk->sctp_hdr->source, 0)) + continue; if (sctp_cmp_addr_exact(sctp_source(chunk), &addr)) src_match = 1; } @@ -2531,7 +2569,8 @@ static int sctp_process_param(struct sctp_association *asoc, break; do_addr_param: af = sctp_get_af_specific(param_type2af(param.p->type)); - af->from_addr_param(&addr, param.addr, htons(asoc->peer.port), 0); + if (!af->from_addr_param(&addr, param.addr, htons(asoc->peer.port), 0)) + break; scope = sctp_scope(peer_addr); if (sctp_in_scope(net, &addr, scope)) if (!sctp_assoc_add_peer(asoc, &addr, gfp, SCTP_UNCONFIRMED)) @@ -2632,15 +2671,13 @@ do_addr_param: addr_param = param.v + sizeof(struct sctp_addip_param); af = sctp_get_af_specific(param_type2af(addr_param->p.type)); - if (af == NULL) + if (!af) break; - af->from_addr_param(&addr, addr_param, - htons(asoc->peer.port), 0); + if (!af->from_addr_param(&addr, addr_param, + htons(asoc->peer.port), 0)) + break; - /* if the address is invalid, we can't process it. - * XXX: see spec for what to do. - */ if (!af->addr_valid(&addr, NULL, NULL)) break; @@ -3054,7 +3091,8 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, if (unlikely(!af)) return SCTP_ERROR_DNS_FAILED; - af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0); + if (!af->from_addr_param(&addr, addr_param, htons(asoc->peer.port), 0)) + return SCTP_ERROR_DNS_FAILED; /* ADDIP 4.2.1 This parameter MUST NOT contain a broadcast * or multicast address. @@ -3331,7 +3369,8 @@ static void sctp_asconf_param_success(struct sctp_association *asoc, /* We have checked the packet before, so we do not check again. */ af = sctp_get_af_specific(param_type2af(addr_param->p.type)); - af->from_addr_param(&addr, addr_param, htons(bp->port), 0); + if (!af->from_addr_param(&addr, addr_param, htons(bp->port), 0)) + return; switch (asconf_param->param_hdr.type) { case SCTP_PARAM_ADD_IP: diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index ce15d590a615..b3815b568e8e 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -471,6 +471,38 @@ out_unlock: sctp_transport_put(transport); } +/* Handle the timeout of the probe timer. */ +void sctp_generate_probe_event(struct timer_list *t) +{ + struct sctp_transport *transport = from_timer(transport, t, probe_timer); + struct sctp_association *asoc = transport->asoc; + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); + int error = 0; + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + pr_debug("%s: sock is busy\n", __func__); + + /* Try again later. */ + if (!mod_timer(&transport->probe_timer, jiffies + (HZ / 20))) + sctp_transport_hold(transport); + goto out_unlock; + } + + error = sctp_do_sm(net, SCTP_EVENT_T_TIMEOUT, + SCTP_ST_TIMEOUT(SCTP_EVENT_TIMEOUT_PROBE), + asoc->state, asoc->ep, asoc, + transport, GFP_ATOMIC); + + if (error) + sk->sk_err = -error; + +out_unlock: + bh_unlock_sock(sk); + sctp_transport_put(transport); +} + /* Inject a SACK Timeout event into the state machine. */ static void sctp_generate_sack_event(struct timer_list *t) { @@ -1641,6 +1673,11 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, sctp_cmd_hb_timers_stop(commands, asoc); break; + case SCTP_CMD_PROBE_TIMER_UPDATE: + t = cmd->obj.transport; + sctp_transport_reset_probe_timer(t); + break; + case SCTP_CMD_REPORT_ERROR: error = cmd->obj.error; break; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index fd1e319eda00..09a8f23ec709 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -361,7 +361,7 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, /* If the INIT is coming toward a closing socket, we'll send back * and ABORT. Essentially, this catches the race of INIT being - * backloged to the socket at the same time as the user isses close(). + * backloged to the socket at the same time as the user issues close(). * Since the socket and all its associations are going away, we * can treat this OOTB */ @@ -608,8 +608,8 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_COOKIE_ECHOED)); - /* SCTP-AUTH: genereate the assocition shared keys so that - * we can potentially signe the COOKIE-ECHO. + /* SCTP-AUTH: generate the association shared keys so that + * we can potentially sign the COOKIE-ECHO. */ sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_SHKEY, SCTP_NULL()); @@ -787,7 +787,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, goto nomem_init; /* SCTP-AUTH: Now that we've populate required fields in - * sctp_process_init, set up the assocaition shared keys as + * sctp_process_init, set up the association shared keys as * necessary so that we can potentially authenticate the ACK */ error = sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC); @@ -838,7 +838,7 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, /* Add all the state machine commands now since we've created * everything. This way we don't introduce memory corruptions - * during side-effect processing and correclty count established + * during side-effect processing and correctly count established * associations. */ sctp_add_cmd_sf(commands, SCTP_CMD_NEW_ASOC, SCTP_ASOC(new_asoc)); @@ -923,7 +923,7 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net, commands); /* Reset init error count upon receipt of COOKIE-ACK, - * to avoid problems with the managemement of this + * to avoid problems with the management of this * counter in stale cookie situations when a transition back * from the COOKIE-ECHOED state to the COOKIE-WAIT * state is performed. @@ -1004,7 +1004,7 @@ static enum sctp_disposition sctp_sf_heartbeat( struct sctp_chunk *reply; /* Send a heartbeat to our peer. */ - reply = sctp_make_heartbeat(asoc, transport); + reply = sctp_make_heartbeat(asoc, transport, 0); if (!reply) return SCTP_DISPOSITION_NOMEM; @@ -1095,6 +1095,32 @@ enum sctp_disposition sctp_sf_send_reconf(struct net *net, return SCTP_DISPOSITION_CONSUME; } +/* send hb chunk with padding for PLPMUTD. */ +enum sctp_disposition sctp_sf_send_probe(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) +{ + struct sctp_transport *transport = (struct sctp_transport *)arg; + struct sctp_chunk *reply; + + if (!sctp_transport_pl_enabled(transport)) + return SCTP_DISPOSITION_CONSUME; + + sctp_transport_pl_send(transport); + + reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size); + if (!reply) + return SCTP_DISPOSITION_NOMEM; + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply)); + sctp_add_cmd_sf(commands, SCTP_CMD_PROBE_TIMER_UPDATE, + SCTP_TRANSPORT(transport)); + + return SCTP_DISPOSITION_CONSUME; +} + /* * Process an heartbeat request. * @@ -1243,6 +1269,18 @@ enum sctp_disposition sctp_sf_backbeat_8_3(struct net *net, if (hbinfo->hb_nonce != link->hb_nonce) return SCTP_DISPOSITION_DISCARD; + if (hbinfo->probe_size) { + if (hbinfo->probe_size != link->pl.probe_size || + !sctp_transport_pl_enabled(link)) + return SCTP_DISPOSITION_DISCARD; + + sctp_transport_pl_recv(link); + if (link->pl.state == SCTP_PL_COMPLETE) + return SCTP_DISPOSITION_CONSUME; + + return sctp_sf_send_probe(net, ep, asoc, type, link, commands); + } + max_interval = link->hbinterval + link->rto; /* Check if the timestamp looks valid. */ @@ -2950,7 +2988,7 @@ enum sctp_disposition sctp_sf_do_9_2_reshutack( commands); /* Since we are not going to really process this INIT, there - * is no point in verifying chunk boundries. Just generate + * is no point in verifying chunk boundaries. Just generate * the SHUTDOWN ACK. */ reply = sctp_make_shutdown_ack(asoc, chunk); @@ -3560,7 +3598,7 @@ enum sctp_disposition sctp_sf_do_9_2_final(struct net *net, goto nomem_chunk; /* Do all the commands now (after allocation), so that we - * have consistent state if memory allocation failes + * have consistent state if memory allocation fails */ sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); @@ -3747,7 +3785,7 @@ static enum sctp_disposition sctp_sf_shut_8_4_5( return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); /* We need to discard the rest of the packet to prevent - * potential bomming attacks from additional bundled chunks. + * potential boomming attacks from additional bundled chunks. * This is documented in SCTP Threats ID. */ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); @@ -4257,7 +4295,7 @@ gen_shutdown: } /* - * SCTP-AUTH Section 6.3 Receiving authenticated chukns + * SCTP-AUTH Section 6.3 Receiving authenticated chunks * * The receiver MUST use the HMAC algorithm indicated in the HMAC * Identifier field. If this algorithm was not specified by the @@ -4812,7 +4850,7 @@ static enum sctp_disposition sctp_sf_violation_ctsn( /* Handle protocol violation of an invalid chunk bundling. For example, * when we have an association and we receive bundled INIT-ACK, or - * SHUDOWN-COMPLETE, our peer is clearly violationg the "MUST NOT bundle" + * SHUTDOWN-COMPLETE, our peer is clearly violating the "MUST NOT bundle" * statement from the specs. Additionally, there might be an attacker * on the path and we may not want to continue this communication. */ @@ -5208,7 +5246,7 @@ enum sctp_disposition sctp_sf_cookie_wait_prm_shutdown( * Inputs * (endpoint, asoc) * - * The RFC does not explcitly address this issue, but is the route through the + * The RFC does not explicitly address this issue, but is the route through the * state table when someone issues a shutdown while in COOKIE_ECHOED state. * * Outputs @@ -5932,7 +5970,7 @@ enum sctp_disposition sctp_sf_t1_cookie_timer_expire( /* RFC2960 9.2 If the timer expires, the endpoint must re-send the SHUTDOWN * with the updated last sequential TSN received from its peer. * - * An endpoint should limit the number of retransmissions of the + * An endpoint should limit the number of retransmission of the * SHUTDOWN chunk to the protocol parameter 'Association.Max.Retrans'. * If this threshold is exceeded the endpoint should destroy the TCB and * MUST report the peer endpoint unreachable to the upper layer (and @@ -6010,7 +6048,7 @@ nomem: } /* - * ADDIP Section 4.1 ASCONF CHunk Procedures + * ADDIP Section 4.1 ASCONF Chunk Procedures * If the T4 RTO timer expires the endpoint should do B1 to B5 */ enum sctp_disposition sctp_sf_t4_timer_expire( @@ -6441,7 +6479,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, chunk->ecn_ce_done = 1; if (af->is_ce(sctp_gso_headskb(chunk->skb))) { - /* Do real work as sideffect. */ + /* Do real work as side effect. */ sctp_add_cmd_sf(commands, SCTP_CMD_ECN_CE, SCTP_U32(tsn)); } diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 88ea87f4f0e7..1816a4410b2b 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -526,6 +526,26 @@ auth_chunk_event_table[SCTP_NUM_AUTH_CHUNK_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_AUTH, }; /*state_fn_t auth_chunk_event_table[][] */ +static const struct sctp_sm_table_entry +pad_chunk_event_table[SCTP_STATE_NUM_STATES] = { + /* SCTP_STATE_CLOSED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_COOKIE_WAIT */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_COOKIE_ECHOED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_ESTABLISHED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_PENDING */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_SENT */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_RECEIVED */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), + /* SCTP_STATE_SHUTDOWN_ACK_SENT */ + TYPE_SCTP_FUNC(sctp_sf_discard_chunk), +}; /* chunk pad */ + static const struct sctp_sm_table_entry chunk_event_table_unknown[SCTP_STATE_NUM_STATES] = { /* SCTP_STATE_CLOSED */ @@ -947,6 +967,25 @@ other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ } +#define TYPE_SCTP_EVENT_TIMEOUT_PROBE { \ + /* SCTP_STATE_CLOSED */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_COOKIE_WAIT */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_COOKIE_ECHOED */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_ESTABLISHED */ \ + TYPE_SCTP_FUNC(sctp_sf_send_probe), \ + /* SCTP_STATE_SHUTDOWN_PENDING */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_SHUTDOWN_SENT */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + /* SCTP_STATE_SHUTDOWN_ACK_SENT */ \ + TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ +} + static const struct sctp_sm_table_entry timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_EVENT_TIMEOUT_NONE, @@ -958,6 +997,7 @@ timeout_event_table[SCTP_NUM_TIMEOUT_TYPES][SCTP_STATE_NUM_STATES] = { TYPE_SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD, TYPE_SCTP_EVENT_TIMEOUT_HEARTBEAT, TYPE_SCTP_EVENT_TIMEOUT_RECONF, + TYPE_SCTP_EVENT_TIMEOUT_PROBE, TYPE_SCTP_EVENT_TIMEOUT_SACK, TYPE_SCTP_EVENT_TIMEOUT_AUTOCLOSE, }; @@ -992,6 +1032,9 @@ static const struct sctp_sm_table_entry *sctp_chunk_event_lookup( case SCTP_CID_AUTH: return &auth_chunk_event_table[0][state]; + + case SCTP_CID_PAD: + return &pad_chunk_event_table[state]; } return &chunk_event_table_unknown[state]; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index a79d193ff872..e64e01f61b11 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2496,6 +2496,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, sctp_transport_pmtu(trans, sctp_opt2sk(sp)); sctp_assoc_sync_pmtu(asoc); } + sctp_transport_pl_reset(trans); } else if (asoc) { asoc->param_flags = (asoc->param_flags & ~SPP_PMTUD) | pmtud_change; @@ -4481,6 +4482,61 @@ static int sctp_setsockopt_encap_port(struct sock *sk, return 0; } +static int sctp_setsockopt_probe_interval(struct sock *sk, + struct sctp_probeinterval *params, + unsigned int optlen) +{ + struct sctp_association *asoc; + struct sctp_transport *t; + __u32 probe_interval; + + if (optlen != sizeof(*params)) + return -EINVAL; + + probe_interval = params->spi_interval; + if (probe_interval && probe_interval < SCTP_PROBE_TIMER_MIN) + return -EINVAL; + + /* If an address other than INADDR_ANY is specified, and + * no transport is found, then the request is invalid. + */ + if (!sctp_is_any(sk, (union sctp_addr *)¶ms->spi_address)) { + t = sctp_addr_id2transport(sk, ¶ms->spi_address, + params->spi_assoc_id); + if (!t) + return -EINVAL; + + t->probe_interval = msecs_to_jiffies(probe_interval); + sctp_transport_pl_reset(t); + return 0; + } + + /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. + */ + asoc = sctp_id2assoc(sk, params->spi_assoc_id); + if (!asoc && params->spi_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + + /* If changes are for association, also apply probe_interval to + * each transport. + */ + if (asoc) { + list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { + t->probe_interval = msecs_to_jiffies(probe_interval); + sctp_transport_pl_reset(t); + } + + asoc->probe_interval = msecs_to_jiffies(probe_interval); + return 0; + } + + sctp_sk(sk)->probe_interval = probe_interval; + return 0; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4703,6 +4759,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_REMOTE_UDP_ENCAPS_PORT: retval = sctp_setsockopt_encap_port(sk, kopt, optlen); break; + case SCTP_PLPMTUD_PROBE_INTERVAL: + retval = sctp_setsockopt_probe_interval(sk, kopt, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -4989,6 +5048,7 @@ static int sctp_init_sock(struct sock *sk) atomic_set(&sp->pd_mode, 0); skb_queue_head_init(&sp->pd_lobby); sp->frag_interleave = 0; + sp->probe_interval = net->sctp.probe_interval; /* Create a per socket endpoint structure. Even if we * change the data structure relationships, this may still @@ -7905,6 +7965,66 @@ out: return 0; } +static int sctp_getsockopt_probe_interval(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_probeinterval params; + struct sctp_association *asoc; + struct sctp_transport *t; + __u32 probe_interval; + + if (len < sizeof(params)) + return -EINVAL; + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + return -EFAULT; + + /* If an address other than INADDR_ANY is specified, and + * no transport is found, then the request is invalid. + */ + if (!sctp_is_any(sk, (union sctp_addr *)¶ms.spi_address)) { + t = sctp_addr_id2transport(sk, ¶ms.spi_address, + params.spi_assoc_id); + if (!t) { + pr_debug("%s: failed no transport\n", __func__); + return -EINVAL; + } + + probe_interval = jiffies_to_msecs(t->probe_interval); + goto out; + } + + /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. + */ + asoc = sctp_id2assoc(sk, params.spi_assoc_id); + if (!asoc && params.spi_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { + pr_debug("%s: failed no association\n", __func__); + return -EINVAL; + } + + if (asoc) { + probe_interval = jiffies_to_msecs(asoc->probe_interval); + goto out; + } + + probe_interval = sctp_sk(sk)->probe_interval; + +out: + params.spi_interval = probe_interval; + if (copy_to_user(optval, ¶ms, len)) + return -EFAULT; + + if (put_user(len, optlen)) + return -EFAULT; + + return 0; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -8128,6 +8248,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_REMOTE_UDP_ENCAPS_PORT: retval = sctp_getsockopt_encap_port(sk, len, optval, optlen); break; + case SCTP_PLPMTUD_PROBE_INTERVAL: + retval = sctp_getsockopt_probe_interval(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 55871b277f47..b46a416787ec 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -55,6 +55,8 @@ static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static int proc_sctp_do_auth(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); +static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos); static struct ctl_table sctp_table[] = { { @@ -293,6 +295,13 @@ static struct ctl_table sctp_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "plpmtud_probe_interval", + .data = &init_net.sctp.probe_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_sctp_do_probe_interval, + }, { .procname = "udp_port", .data = &init_net.sctp.udp_port, @@ -539,6 +548,32 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, return ret; } +static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + struct ctl_table tbl; + int ret, new_value; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.probe_interval; + + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { + if (new_value && new_value < SCTP_PROBE_TIMER_MIN) + return -EINVAL; + + net->sctp.probe_interval = new_value; + } + + return ret; +} + int sctp_sysctl_net_register(struct net *net) { struct ctl_table *table; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index bf0ac467e757..5f23804f21c7 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -75,6 +75,7 @@ static struct sctp_transport *sctp_transport_init(struct net *net, timer_setup(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event, 0); timer_setup(&peer->hb_timer, sctp_generate_heartbeat_event, 0); timer_setup(&peer->reconf_timer, sctp_generate_reconf_event, 0); + timer_setup(&peer->probe_timer, sctp_generate_probe_event, 0); timer_setup(&peer->proto_unreach_timer, sctp_generate_proto_unreach_event, 0); @@ -131,6 +132,9 @@ void sctp_transport_free(struct sctp_transport *transport) if (del_timer(&transport->reconf_timer)) sctp_transport_put(transport); + if (del_timer(&transport->probe_timer)) + sctp_transport_put(transport); + /* Delete the ICMP proto unreachable timer if it's active. */ if (del_timer(&transport->proto_unreach_timer)) sctp_transport_put(transport); @@ -207,6 +211,15 @@ void sctp_transport_reset_reconf_timer(struct sctp_transport *transport) sctp_transport_hold(transport); } +void sctp_transport_reset_probe_timer(struct sctp_transport *transport) +{ + if (timer_pending(&transport->probe_timer)) + return; + if (!mod_timer(&transport->probe_timer, + jiffies + transport->probe_interval)) + sctp_transport_hold(transport); +} + /* This transport has been assigned to an association. * Initialize fields from the association or from the sock itself. * Register the reference count in the association. @@ -241,12 +254,143 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) transport->pathmtu = sctp_dst_mtu(transport->dst); else transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; + + sctp_transport_pl_update(transport); +} + +void sctp_transport_pl_send(struct sctp_transport *t) +{ + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + + if (t->pl.probe_count < SCTP_MAX_PROBES) { + t->pl.probe_count++; + return; + } + + if (t->pl.state == SCTP_PL_BASE) { + if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */ + t->pl.state = SCTP_PL_ERROR; /* Base -> Error */ + + t->pl.pmtu = SCTP_MIN_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + } + } else if (t->pl.state == SCTP_PL_SEARCH) { + if (t->pl.pmtu == t->pl.probe_size) { /* Black Hole Detected */ + t->pl.state = SCTP_PL_BASE; /* Search -> Base */ + t->pl.probe_size = SCTP_BASE_PLPMTU; + t->pl.probe_high = 0; + + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + } else { /* Normal probe failure. */ + t->pl.probe_high = t->pl.probe_size; + t->pl.probe_size = t->pl.pmtu; + } + } else if (t->pl.state == SCTP_PL_COMPLETE) { + if (t->pl.pmtu == t->pl.probe_size) { /* Black Hole Detected */ + t->pl.state = SCTP_PL_BASE; /* Search Complete -> Base */ + t->pl.probe_size = SCTP_BASE_PLPMTU; + + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + } + } + t->pl.probe_count = 1; +} + +void sctp_transport_pl_recv(struct sctp_transport *t) +{ + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high); + + t->pl.pmtu = t->pl.probe_size; + t->pl.probe_count = 0; + if (t->pl.state == SCTP_PL_BASE) { + t->pl.state = SCTP_PL_SEARCH; /* Base -> Search */ + t->pl.probe_size += SCTP_PL_BIG_STEP; + } else if (t->pl.state == SCTP_PL_ERROR) { + t->pl.state = SCTP_PL_SEARCH; /* Error -> Search */ + + t->pl.pmtu = t->pl.probe_size; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + t->pl.probe_size += SCTP_PL_BIG_STEP; + } else if (t->pl.state == SCTP_PL_SEARCH) { + if (!t->pl.probe_high) { + t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP, + SCTP_MAX_PLPMTU); + return; + } + t->pl.probe_size += SCTP_PL_MIN_STEP; + if (t->pl.probe_size >= t->pl.probe_high) { + t->pl.probe_high = 0; + t->pl.raise_count = 0; + t->pl.state = SCTP_PL_COMPLETE; /* Search -> Search Complete */ + + t->pl.probe_size = t->pl.pmtu; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + sctp_assoc_sync_pmtu(t->asoc); + } + } else if (t->pl.state == SCTP_PL_COMPLETE && ++t->pl.raise_count == 30) { + /* Raise probe_size again after 30 * interval in Search Complete */ + t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */ + t->pl.probe_size += SCTP_PL_MIN_STEP; + } +} + +static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu) +{ + pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, ptb: %d\n", + __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, pmtu); + + if (pmtu < SCTP_MIN_PLPMTU || pmtu >= t->pl.probe_size) + return false; + + if (t->pl.state == SCTP_PL_BASE) { + if (pmtu >= SCTP_MIN_PLPMTU && pmtu < SCTP_BASE_PLPMTU) { + t->pl.state = SCTP_PL_ERROR; /* Base -> Error */ + + t->pl.pmtu = SCTP_MIN_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + } + } else if (t->pl.state == SCTP_PL_SEARCH) { + if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) { + t->pl.state = SCTP_PL_BASE; /* Search -> Base */ + t->pl.probe_size = SCTP_BASE_PLPMTU; + t->pl.probe_count = 0; + + t->pl.probe_high = 0; + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + } else if (pmtu > t->pl.pmtu && pmtu < t->pl.probe_size) { + t->pl.probe_size = pmtu; + t->pl.probe_count = 0; + + return false; + } + } else if (t->pl.state == SCTP_PL_COMPLETE) { + if (pmtu >= SCTP_BASE_PLPMTU && pmtu < t->pl.pmtu) { + t->pl.state = SCTP_PL_BASE; /* Complete -> Base */ + t->pl.probe_size = SCTP_BASE_PLPMTU; + t->pl.probe_count = 0; + + t->pl.probe_high = 0; + t->pl.pmtu = SCTP_BASE_PLPMTU; + t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t); + } + } + + return true; } bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) { - struct dst_entry *dst = sctp_transport_dst_check(t); struct sock *sk = t->asoc->base.sk; + struct dst_entry *dst; bool change = true; if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) { @@ -257,6 +401,10 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) } pmtu = SCTP_TRUNC4(pmtu); + if (sctp_transport_pl_enabled(t)) + return sctp_transport_pl_toobig(t, pmtu - sctp_transport_pl_hlen(t)); + + dst = sctp_transport_dst_check(t); if (dst) { struct sctp_pf *pf = sctp_get_pf_specific(dst->ops->family); union sctp_addr addr; diff --git a/net/smc/Makefile b/net/smc/Makefile index 77e54fe42b1c..99a0186cba5b 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -2,4 +2,4 @@ obj-$(CONFIG_SMC) += smc.o obj-$(CONFIG_SMC_DIAG) += smc_diag.o smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o -smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o +smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5eff7cccceff..898389611ae8 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -49,6 +49,7 @@ #include "smc_tx.h" #include "smc_rx.h" #include "smc_close.h" +#include "smc_stats.h" static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group * creation on server @@ -508,9 +509,44 @@ static void smc_link_save_peer_info(struct smc_link *link, link->peer_mtu = clc->r0.qp_mtu; } -static void smc_switch_to_fallback(struct smc_sock *smc) +static void smc_stat_inc_fback_rsn_cnt(struct smc_sock *smc, + struct smc_stats_fback *fback_arr) +{ + int cnt; + + for (cnt = 0; cnt < SMC_MAX_FBACK_RSN_CNT; cnt++) { + if (fback_arr[cnt].fback_code == smc->fallback_rsn) { + fback_arr[cnt].count++; + break; + } + if (!fback_arr[cnt].fback_code) { + fback_arr[cnt].fback_code = smc->fallback_rsn; + fback_arr[cnt].count++; + break; + } + } +} + +static void smc_stat_fallback(struct smc_sock *smc) +{ + struct net *net = sock_net(&smc->sk); + + mutex_lock(&net->smc.mutex_fback_rsn); + if (smc->listen_smc) { + smc_stat_inc_fback_rsn_cnt(smc, net->smc.fback_rsn->srv); + net->smc.fback_rsn->srv_fback_cnt++; + } else { + smc_stat_inc_fback_rsn_cnt(smc, net->smc.fback_rsn->clnt); + net->smc.fback_rsn->clnt_fback_cnt++; + } + mutex_unlock(&net->smc.mutex_fback_rsn); +} + +static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) { smc->use_fallback = true; + smc->fallback_rsn = reason_code; + smc_stat_fallback(smc); if (smc->sk.sk_socket && smc->sk.sk_socket->file) { smc->clcsock->file = smc->sk.sk_socket->file; smc->clcsock->file->private_data = smc->clcsock; @@ -522,8 +558,7 @@ static void smc_switch_to_fallback(struct smc_sock *smc) /* fall back during connect */ static int smc_connect_fallback(struct smc_sock *smc, int reason_code) { - smc_switch_to_fallback(smc); - smc->fallback_rsn = reason_code; + smc_switch_to_fallback(smc, reason_code); smc_copy_sock_settings_to_clc(smc); smc->connect_nonblock = 0; if (smc->sk.sk_state == SMC_INIT) @@ -535,9 +570,11 @@ static int smc_connect_fallback(struct smc_sock *smc, int reason_code) static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code, u8 version) { + struct net *net = sock_net(&smc->sk); int rc; if (reason_code < 0) { /* error, fallback is not possible */ + this_cpu_inc(net->smc.smc_stats->clnt_hshake_err_cnt); if (smc->sk.sk_state == SMC_INIT) sock_put(&smc->sk); /* passive closing */ return reason_code; @@ -545,6 +582,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code, if (reason_code != SMC_CLC_DECL_PEERDECL) { rc = smc_clc_send_decline(smc, reason_code, version); if (rc < 0) { + this_cpu_inc(net->smc.smc_stats->clnt_hshake_err_cnt); if (smc->sk.sk_state == SMC_INIT) sock_put(&smc->sk); /* passive closing */ return rc; @@ -992,6 +1030,7 @@ static int __smc_connect(struct smc_sock *smc) if (rc) goto vlan_cleanup; + SMC_STAT_CLNT_SUCC_INC(sock_net(smc->clcsock->sk), aclc); smc_connect_ism_vlan_cleanup(smc, ini); kfree(buf); kfree(ini); @@ -1307,7 +1346,9 @@ static void smc_listen_out_connected(struct smc_sock *new_smc) static void smc_listen_out_err(struct smc_sock *new_smc) { struct sock *newsmcsk = &new_smc->sk; + struct net *net = sock_net(newsmcsk); + this_cpu_inc(net->smc.smc_stats->srv_hshake_err_cnt); if (newsmcsk->sk_state == SMC_INIT) sock_put(&new_smc->sk); /* passive closing */ newsmcsk->sk_state = SMC_CLOSED; @@ -1325,8 +1366,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code, smc_listen_out_err(new_smc); return; } - smc_switch_to_fallback(new_smc); - new_smc->fallback_rsn = reason_code; + smc_switch_to_fallback(new_smc, reason_code); if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) { if (smc_clc_send_decline(new_smc, reason_code, version) < 0) { smc_listen_out_err(new_smc); @@ -1699,8 +1739,7 @@ static void smc_listen_work(struct work_struct *work) /* check if peer is smc capable */ if (!tcp_sk(newclcsock->sk)->syn_smc) { - smc_switch_to_fallback(new_smc); - new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC; + smc_switch_to_fallback(new_smc, SMC_CLC_DECL_PEERNOSMC); smc_listen_out_connected(new_smc); return; } @@ -1778,6 +1817,7 @@ static void smc_listen_work(struct work_struct *work) } smc_conn_save_peer_info(new_smc, cclc); smc_listen_out_connected(new_smc); + SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini); goto out_free; out_unlock: @@ -1984,18 +2024,19 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (msg->msg_flags & MSG_FASTOPEN) { if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { - smc_switch_to_fallback(smc); - smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; + smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); } else { rc = -EINVAL; goto out; } } - if (smc->use_fallback) + if (smc->use_fallback) { rc = smc->clcsock->ops->sendmsg(smc->clcsock, msg, len); - else + } else { rc = smc_tx_sendmsg(smc, msg, len); + SMC_STAT_TX_PAYLOAD(smc, len, rc); + } out: release_sock(sk); return rc; @@ -2030,6 +2071,7 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, } else { msg->msg_namelen = 0; rc = smc_rx_recvmsg(smc, msg, NULL, len, flags); + SMC_STAT_RX_PAYLOAD(smc, rc, rc); } out: @@ -2176,7 +2218,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, optval, optlen); if (smc->clcsock->sk->sk_err) { sk->sk_err = smc->clcsock->sk->sk_err; - sk->sk_error_report(sk); + sk_error_report(sk); } if (optlen < sizeof(int)) @@ -2194,8 +2236,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, case TCP_FASTOPEN_NO_COOKIE: /* option not supported by SMC */ if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { - smc_switch_to_fallback(smc); - smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; + smc_switch_to_fallback(smc, SMC_CLC_DECL_OPTUNSUPP); } else { rc = -EINVAL; } @@ -2204,18 +2245,22 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (val) + if (val) { + SMC_STAT_INC(smc, ndly_cnt); mod_delayed_work(smc->conn.lgr->tx_wq, &smc->conn.tx_work, 0); + } } break; case TCP_CORK: if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (!val) + if (!val) { + SMC_STAT_INC(smc, cork_cnt); mod_delayed_work(smc->conn.lgr->tx_wq, &smc->conn.tx_work, 0); + } } break; case TCP_DEFER_ACCEPT: @@ -2338,11 +2383,13 @@ static ssize_t smc_sendpage(struct socket *sock, struct page *page, goto out; } release_sock(sk); - if (smc->use_fallback) + if (smc->use_fallback) { rc = kernel_sendpage(smc->clcsock, page, offset, size, flags); - else + } else { + SMC_STAT_INC(smc, sendpage_cnt); rc = sock_no_sendpage(sock, page, offset, size, flags); + } out: return rc; @@ -2391,6 +2438,7 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, flags = MSG_DONTWAIT; else flags = 0; + SMC_STAT_INC(smc, splice_cnt); rc = smc_rx_recvmsg(smc, NULL, pipe, len, flags); } out: @@ -2479,6 +2527,16 @@ static void __net_exit smc_net_exit(struct net *net) smc_pnet_net_exit(net); } +static __net_init int smc_net_stat_init(struct net *net) +{ + return smc_stats_init(net); +} + +static void __net_exit smc_net_stat_exit(struct net *net) +{ + smc_stats_exit(net); +} + static struct pernet_operations smc_net_ops = { .init = smc_net_init, .exit = smc_net_exit, @@ -2486,6 +2544,11 @@ static struct pernet_operations smc_net_ops = { .size = sizeof(struct smc_net), }; +static struct pernet_operations smc_net_stat_ops = { + .init = smc_net_stat_init, + .exit = smc_net_stat_exit, +}; + static int __init smc_init(void) { int rc; @@ -2494,6 +2557,10 @@ static int __init smc_init(void) if (rc) return rc; + rc = register_pernet_subsys(&smc_net_stat_ops); + if (rc) + return rc; + smc_ism_init(); smc_clc_init(); @@ -2595,6 +2662,7 @@ static void __exit smc_exit(void) proto_unregister(&smc_proto); smc_pnet_exit(); smc_nl_exit(); + unregister_pernet_subsys(&smc_net_stat_ops); unregister_pernet_subsys(&smc_net_ops); rcu_barrier(); } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 0df85a12651e..cd0d7c908b2a 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -33,6 +33,7 @@ #include "smc_close.h" #include "smc_ism.h" #include "smc_netlink.h" +#include "smc_stats.h" #define SMC_LGR_NUM_INCR 256 #define SMC_LGR_FREE_DELAY_SERV (600 * HZ) @@ -1235,20 +1236,6 @@ static void smc_lgr_free(struct smc_link_group *lgr) kfree(lgr); } -static void smcd_unregister_all_dmbs(struct smc_link_group *lgr) -{ - int i; - - for (i = 0; i < SMC_RMBE_SIZES; i++) { - struct smc_buf_desc *buf_desc; - - list_for_each_entry(buf_desc, &lgr->rmbs[i], list) { - buf_desc->len += sizeof(struct smcd_cdc_msg); - smc_ism_unregister_dmb(lgr->smcd, buf_desc); - } - } -} - static void smc_sk_wake_ups(struct smc_sock *smc) { smc->sk.sk_write_space(&smc->sk); @@ -1285,7 +1272,6 @@ static void smc_lgr_cleanup(struct smc_link_group *lgr) { if (lgr->is_smcd) { smc_ism_signal_shutdown(lgr); - smcd_unregister_all_dmbs(lgr); } else { u32 rsn = lgr->llc_termination_rsn; @@ -2044,6 +2030,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; int bufsize, bufsize_short; + bool is_dgraded = false; struct mutex *lock; /* lock buffer list */ int sk_buf_size; @@ -2071,6 +2058,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) /* check for reusable slot in the link group */ buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list); if (buf_desc) { + SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); + SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb); memset(buf_desc->cpu_addr, 0, bufsize); break; /* found reusable slot */ } @@ -2082,9 +2071,16 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) if (PTR_ERR(buf_desc) == -ENOMEM) break; - if (IS_ERR(buf_desc)) + if (IS_ERR(buf_desc)) { + if (!is_dgraded) { + is_dgraded = true; + SMC_STAT_RMB_DOWNGRADED(smc, is_smcd, is_rmb); + } continue; + } + SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); + SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); buf_desc->used = 1; mutex_lock(lock); list_add(&buf_desc->list, buf_list); diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 967712ba52a0..9cb2df289963 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -470,7 +470,6 @@ void smcd_unregister_dev(struct smcd_dev *smcd) mutex_unlock(&smcd_dev_list.mutex); smcd->going_away = 1; smc_smcd_terminate_all(smcd); - flush_workqueue(smcd->event_wq); destroy_workqueue(smcd->event_wq); device_del(&smcd->dev); diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index 140419a19dbf..6fb6f96c1d17 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -19,6 +19,7 @@ #include "smc_core.h" #include "smc_ism.h" #include "smc_ib.h" +#include "smc_stats.h" #include "smc_netlink.h" #define SMC_CMD_MAX_ATTR 1 @@ -55,6 +56,16 @@ static const struct genl_ops smc_gen_nl_ops[] = { /* can be retrieved by unprivileged users */ .dumpit = smcr_nl_get_device, }, + { + .cmd = SMC_NETLINK_GET_STATS, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_get_stats, + }, + { + .cmd = SMC_NETLINK_GET_FBACK_STATS, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_get_fback_stats, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { diff --git a/net/smc/smc_netlink.h b/net/smc/smc_netlink.h index 3477265cba6c..5ce2c0a89ccd 100644 --- a/net/smc/smc_netlink.h +++ b/net/smc/smc_netlink.h @@ -18,7 +18,7 @@ extern struct genl_family smc_gen_nl_family; struct smc_nl_dmp_ctx { - int pos[2]; + int pos[3]; }; static inline struct smc_nl_dmp_ctx *smc_nl_dmp_ctx(struct netlink_callback *c) diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index fcfac59f8b72..170b733bc736 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -21,6 +21,7 @@ #include "smc_cdc.h" #include "smc_tx.h" /* smc_tx_consumer_update() */ #include "smc_rx.h" +#include "smc_stats.h" /* callback implementation to wakeup consumers blocked with smc_rx_wait(). * indirectly called by smc_cdc_msg_recv_action(). @@ -227,6 +228,7 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len, conn->urg_state == SMC_URG_READ) return -EINVAL; + SMC_STAT_INC(smc, urg_data_cnt); if (conn->urg_state == SMC_URG_VALID) { if (!(flags & MSG_PEEK)) smc->conn.urg_state = SMC_URG_READ; @@ -303,6 +305,12 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + readable = atomic_read(&conn->bytes_to_rcv); + if (readable >= conn->rmb_desc->len) + SMC_STAT_RMB_RX_FULL(smc, !conn->lnk); + + if (len < readable) + SMC_STAT_RMB_RX_SIZE_SMALL(smc, !conn->lnk); /* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */ rcvbuf_base = conn->rx_off + conn->rmb_desc->cpu_addr; diff --git a/net/smc/smc_stats.c b/net/smc/smc_stats.c new file mode 100644 index 000000000000..e80e34f7ac15 --- /dev/null +++ b/net/smc/smc_stats.c @@ -0,0 +1,413 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * SMC statistics netlink routines + * + * Copyright IBM Corp. 2021 + * + * Author(s): Guvenc Gulce + */ +#include +#include +#include +#include +#include +#include +#include +#include "smc_netlink.h" +#include "smc_stats.h" + +int smc_stats_init(struct net *net) +{ + net->smc.fback_rsn = kzalloc(sizeof(*net->smc.fback_rsn), GFP_KERNEL); + if (!net->smc.fback_rsn) + goto err_fback; + net->smc.smc_stats = alloc_percpu(struct smc_stats); + if (!net->smc.smc_stats) + goto err_stats; + mutex_init(&net->smc.mutex_fback_rsn); + return 0; + +err_stats: + kfree(net->smc.fback_rsn); +err_fback: + return -ENOMEM; +} + +void smc_stats_exit(struct net *net) +{ + kfree(net->smc.fback_rsn); + if (net->smc.smc_stats) + free_percpu(net->smc.smc_stats); +} + +static int smc_nl_fill_stats_rmb_data(struct sk_buff *skb, + struct smc_stats *stats, int tech, + int type) +{ + struct smc_stats_rmbcnt *stats_rmb_cnt; + struct nlattr *attrs; + + if (type == SMC_NLA_STATS_T_TX_RMB_STATS) + stats_rmb_cnt = &stats->smc[tech].rmb_tx; + else + stats_rmb_cnt = &stats->smc[tech].rmb_rx; + + attrs = nla_nest_start(skb, type); + if (!attrs) + goto errout; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_REUSE_CNT, + stats_rmb_cnt->reuse_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_SIZE_SM_PEER_CNT, + stats_rmb_cnt->buf_size_small_peer_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_SIZE_SM_CNT, + stats_rmb_cnt->buf_size_small_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_FULL_PEER_CNT, + stats_rmb_cnt->buf_full_peer_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_FULL_CNT, + stats_rmb_cnt->buf_full_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_ALLOC_CNT, + stats_rmb_cnt->alloc_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_RMB_DGRADE_CNT, + stats_rmb_cnt->dgrade_cnt, + SMC_NLA_STATS_RMB_PAD)) + goto errattr; + + nla_nest_end(skb, attrs); + return 0; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + return -EMSGSIZE; +} + +static int smc_nl_fill_stats_bufsize_data(struct sk_buff *skb, + struct smc_stats *stats, int tech, + int type) +{ + struct smc_stats_memsize *stats_pload; + struct nlattr *attrs; + + if (type == SMC_NLA_STATS_T_TXPLOAD_SIZE) + stats_pload = &stats->smc[tech].tx_pd; + else if (type == SMC_NLA_STATS_T_RXPLOAD_SIZE) + stats_pload = &stats->smc[tech].rx_pd; + else if (type == SMC_NLA_STATS_T_TX_RMB_SIZE) + stats_pload = &stats->smc[tech].tx_rmbsize; + else if (type == SMC_NLA_STATS_T_RX_RMB_SIZE) + stats_pload = &stats->smc[tech].rx_rmbsize; + else + goto errout; + + attrs = nla_nest_start(skb, type); + if (!attrs) + goto errout; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_8K, + stats_pload->buf[SMC_BUF_8K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_16K, + stats_pload->buf[SMC_BUF_16K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_32K, + stats_pload->buf[SMC_BUF_32K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_64K, + stats_pload->buf[SMC_BUF_64K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_128K, + stats_pload->buf[SMC_BUF_128K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_256K, + stats_pload->buf[SMC_BUF_256K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_512K, + stats_pload->buf[SMC_BUF_512K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_1024K, + stats_pload->buf[SMC_BUF_1024K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_PLOAD_G_1024K, + stats_pload->buf[SMC_BUF_G_1024K], + SMC_NLA_STATS_PLOAD_PAD)) + goto errattr; + + nla_nest_end(skb, attrs); + return 0; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + return -EMSGSIZE; +} + +static int smc_nl_fill_stats_tech_data(struct sk_buff *skb, + struct smc_stats *stats, int tech) +{ + struct smc_stats_tech *smc_tech; + struct nlattr *attrs; + + smc_tech = &stats->smc[tech]; + if (tech == SMC_TYPE_D) + attrs = nla_nest_start(skb, SMC_NLA_STATS_SMCD_TECH); + else + attrs = nla_nest_start(skb, SMC_NLA_STATS_SMCR_TECH); + + if (!attrs) + goto errout; + if (smc_nl_fill_stats_rmb_data(skb, stats, tech, + SMC_NLA_STATS_T_TX_RMB_STATS)) + goto errattr; + if (smc_nl_fill_stats_rmb_data(skb, stats, tech, + SMC_NLA_STATS_T_RX_RMB_STATS)) + goto errattr; + if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, + SMC_NLA_STATS_T_TXPLOAD_SIZE)) + goto errattr; + if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, + SMC_NLA_STATS_T_RXPLOAD_SIZE)) + goto errattr; + if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, + SMC_NLA_STATS_T_TX_RMB_SIZE)) + goto errattr; + if (smc_nl_fill_stats_bufsize_data(skb, stats, tech, + SMC_NLA_STATS_T_RX_RMB_SIZE)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CLNT_V1_SUCC, + smc_tech->clnt_v1_succ_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CLNT_V2_SUCC, + smc_tech->clnt_v2_succ_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SRV_V1_SUCC, + smc_tech->srv_v1_succ_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SRV_V2_SUCC, + smc_tech->srv_v2_succ_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_BYTES, + smc_tech->rx_bytes, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_TX_BYTES, + smc_tech->tx_bytes, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_CNT, + smc_tech->rx_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_TX_CNT, + smc_tech->tx_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SENDPAGE_CNT, + smc_tech->sendpage_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CORK_CNT, + smc_tech->cork_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_NDLY_CNT, + smc_tech->ndly_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SPLICE_CNT, + smc_tech->splice_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_URG_DATA_CNT, + smc_tech->urg_data_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + + nla_nest_end(skb, attrs); + return 0; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + return -EMSGSIZE; +} + +int smc_nl_get_stats(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct net *net = sock_net(skb->sk); + struct smc_stats *stats; + struct nlattr *attrs; + int cpu, i, size; + void *nlh; + u64 *src; + u64 *sum; + + if (cb_ctx->pos[0]) + goto errmsg; + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_STATS); + if (!nlh) + goto errmsg; + + attrs = nla_nest_start(skb, SMC_GEN_STATS); + if (!attrs) + goto errnest; + stats = kzalloc(sizeof(*stats), GFP_KERNEL); + if (!stats) + goto erralloc; + size = sizeof(*stats) / sizeof(u64); + for_each_possible_cpu(cpu) { + src = (u64 *)per_cpu_ptr(net->smc.smc_stats, cpu); + sum = (u64 *)stats; + for (i = 0; i < size; i++) + *(sum++) += *(src++); + } + if (smc_nl_fill_stats_tech_data(skb, stats, SMC_TYPE_D)) + goto errattr; + if (smc_nl_fill_stats_tech_data(skb, stats, SMC_TYPE_R)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_CLNT_HS_ERR_CNT, + stats->clnt_hshake_err_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_STATS_SRV_HS_ERR_CNT, + stats->srv_hshake_err_cnt, + SMC_NLA_STATS_PAD)) + goto errattr; + + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + cb_ctx->pos[0] = 1; + kfree(stats); + return skb->len; + +errattr: + kfree(stats); +erralloc: + nla_nest_cancel(skb, attrs); +errnest: + genlmsg_cancel(skb, nlh); +errmsg: + return skb->len; +} + +static int smc_nl_get_fback_details(struct sk_buff *skb, + struct netlink_callback *cb, int pos, + bool is_srv) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct net *net = sock_net(skb->sk); + int cnt_reported = cb_ctx->pos[2]; + struct smc_stats_fback *trgt_arr; + struct nlattr *attrs; + int rc = 0; + void *nlh; + + if (is_srv) + trgt_arr = &net->smc.fback_rsn->srv[0]; + else + trgt_arr = &net->smc.fback_rsn->clnt[0]; + if (!trgt_arr[pos].fback_code) + return -ENODATA; + nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_GET_FBACK_STATS); + if (!nlh) + goto errmsg; + attrs = nla_nest_start(skb, SMC_GEN_FBACK_STATS); + if (!attrs) + goto errout; + if (nla_put_u8(skb, SMC_NLA_FBACK_STATS_TYPE, is_srv)) + goto errattr; + if (!cnt_reported) { + if (nla_put_u64_64bit(skb, SMC_NLA_FBACK_STATS_SRV_CNT, + net->smc.fback_rsn->srv_fback_cnt, + SMC_NLA_FBACK_STATS_PAD)) + goto errattr; + if (nla_put_u64_64bit(skb, SMC_NLA_FBACK_STATS_CLNT_CNT, + net->smc.fback_rsn->clnt_fback_cnt, + SMC_NLA_FBACK_STATS_PAD)) + goto errattr; + cnt_reported = 1; + } + + if (nla_put_u32(skb, SMC_NLA_FBACK_STATS_RSN_CODE, + trgt_arr[pos].fback_code)) + goto errattr; + if (nla_put_u16(skb, SMC_NLA_FBACK_STATS_RSN_CNT, + trgt_arr[pos].count)) + goto errattr; + + cb_ctx->pos[2] = cnt_reported; + nla_nest_end(skb, attrs); + genlmsg_end(skb, nlh); + return rc; + +errattr: + nla_nest_cancel(skb, attrs); +errout: + genlmsg_cancel(skb, nlh); +errmsg: + return -EMSGSIZE; +} + +int smc_nl_get_fback_stats(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + struct net *net = sock_net(skb->sk); + int rc_srv = 0, rc_clnt = 0, k; + int skip_serv = cb_ctx->pos[1]; + int snum = cb_ctx->pos[0]; + bool is_srv = true; + + mutex_lock(&net->smc.mutex_fback_rsn); + for (k = 0; k < SMC_MAX_FBACK_RSN_CNT; k++) { + if (k < snum) + continue; + if (!skip_serv) { + rc_srv = smc_nl_get_fback_details(skb, cb, k, is_srv); + if (rc_srv && rc_srv != -ENODATA) + break; + } else { + skip_serv = 0; + } + rc_clnt = smc_nl_get_fback_details(skb, cb, k, !is_srv); + if (rc_clnt && rc_clnt != -ENODATA) { + skip_serv = 1; + break; + } + if (rc_clnt == -ENODATA && rc_srv == -ENODATA) + break; + } + mutex_unlock(&net->smc.mutex_fback_rsn); + cb_ctx->pos[1] = skip_serv; + cb_ctx->pos[0] = k; + return skb->len; +} diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h new file mode 100644 index 000000000000..84b7ecd8c05c --- /dev/null +++ b/net/smc/smc_stats.h @@ -0,0 +1,266 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Macros for SMC statistics + * + * Copyright IBM Corp. 2021 + * + * Author(s): Guvenc Gulce + */ + +#ifndef NET_SMC_SMC_STATS_H_ +#define NET_SMC_SMC_STATS_H_ +#include +#include +#include +#include +#include + +#include "smc_clc.h" + +#define SMC_MAX_FBACK_RSN_CNT 30 + +enum { + SMC_BUF_8K, + SMC_BUF_16K, + SMC_BUF_32K, + SMC_BUF_64K, + SMC_BUF_128K, + SMC_BUF_256K, + SMC_BUF_512K, + SMC_BUF_1024K, + SMC_BUF_G_1024K, + SMC_BUF_MAX, +}; + +struct smc_stats_fback { + int fback_code; + u16 count; +}; + +struct smc_stats_rsn { + struct smc_stats_fback srv[SMC_MAX_FBACK_RSN_CNT]; + struct smc_stats_fback clnt[SMC_MAX_FBACK_RSN_CNT]; + u64 srv_fback_cnt; + u64 clnt_fback_cnt; +}; + +struct smc_stats_rmbcnt { + u64 buf_size_small_peer_cnt; + u64 buf_size_small_cnt; + u64 buf_full_peer_cnt; + u64 buf_full_cnt; + u64 reuse_cnt; + u64 alloc_cnt; + u64 dgrade_cnt; +}; + +struct smc_stats_memsize { + u64 buf[SMC_BUF_MAX]; +}; + +struct smc_stats_tech { + struct smc_stats_memsize tx_rmbsize; + struct smc_stats_memsize rx_rmbsize; + struct smc_stats_memsize tx_pd; + struct smc_stats_memsize rx_pd; + struct smc_stats_rmbcnt rmb_tx; + struct smc_stats_rmbcnt rmb_rx; + u64 clnt_v1_succ_cnt; + u64 clnt_v2_succ_cnt; + u64 srv_v1_succ_cnt; + u64 srv_v2_succ_cnt; + u64 sendpage_cnt; + u64 urg_data_cnt; + u64 splice_cnt; + u64 cork_cnt; + u64 ndly_cnt; + u64 rx_bytes; + u64 tx_bytes; + u64 rx_cnt; + u64 tx_cnt; +}; + +struct smc_stats { + struct smc_stats_tech smc[2]; + u64 clnt_hshake_err_cnt; + u64 srv_hshake_err_cnt; +}; + +#define SMC_STAT_PAYLOAD_SUB(_smc_stats, _tech, key, _len, _rc) \ +do { \ + typeof(_smc_stats) stats = (_smc_stats); \ + typeof(_tech) t = (_tech); \ + typeof(_len) l = (_len); \ + int _pos = fls64((l) >> 13); \ + typeof(_rc) r = (_rc); \ + int m = SMC_BUF_MAX - 1; \ + this_cpu_inc((*stats).smc[t].key ## _cnt); \ + if (r <= 0) \ + break; \ + _pos = (_pos < m) ? ((l == 1 << (_pos + 12)) ? _pos - 1 : _pos) : m; \ + this_cpu_inc((*stats).smc[t].key ## _pd.buf[_pos]); \ + this_cpu_add((*stats).smc[t].key ## _bytes, r); \ +} \ +while (0) + +#define SMC_STAT_TX_PAYLOAD(_smc, length, rcode) \ +do { \ + typeof(_smc) __smc = _smc; \ + struct net *_net = sock_net(&__smc->sk); \ + struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \ + typeof(length) _len = (length); \ + typeof(rcode) _rc = (rcode); \ + bool is_smcd = !__smc->conn.lnk; \ + if (is_smcd) \ + SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_D, tx, _len, _rc); \ + else \ + SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_R, tx, _len, _rc); \ +} \ +while (0) + +#define SMC_STAT_RX_PAYLOAD(_smc, length, rcode) \ +do { \ + typeof(_smc) __smc = _smc; \ + struct net *_net = sock_net(&__smc->sk); \ + struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \ + typeof(length) _len = (length); \ + typeof(rcode) _rc = (rcode); \ + bool is_smcd = !__smc->conn.lnk; \ + if (is_smcd) \ + SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_D, rx, _len, _rc); \ + else \ + SMC_STAT_PAYLOAD_SUB(_smc_stats, SMC_TYPE_R, rx, _len, _rc); \ +} \ +while (0) + +#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _len) \ +do { \ + typeof(_len) _l = (_len); \ + typeof(_tech) t = (_tech); \ + int _pos = fls((_l) >> 13); \ + int m = SMC_BUF_MAX - 1; \ + _pos = (_pos < m) ? ((_l == 1 << (_pos + 12)) ? _pos - 1 : _pos) : m; \ + this_cpu_inc((*(_smc_stats)).smc[t].k ## _rmbsize.buf[_pos]); \ +} \ +while (0) + +#define SMC_STAT_RMB_SUB(_smc_stats, type, t, key) \ + this_cpu_inc((*(_smc_stats)).smc[t].rmb ## _ ## key.type ## _cnt) + +#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _len) \ +do { \ + struct net *_net = sock_net(&(_smc)->sk); \ + struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \ + typeof(_is_smcd) is_d = (_is_smcd); \ + typeof(_is_rx) is_r = (_is_rx); \ + typeof(_len) l = (_len); \ + if ((is_d) && (is_r)) \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, l); \ + if ((is_d) && !(is_r)) \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, l); \ + if (!(is_d) && (is_r)) \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, l); \ + if (!(is_d) && !(is_r)) \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, l); \ +} \ +while (0) + +#define SMC_STAT_RMB(_smc, type, _is_smcd, _is_rx) \ +do { \ + struct net *net = sock_net(&(_smc)->sk); \ + struct smc_stats __percpu *_smc_stats = net->smc.smc_stats; \ + typeof(_is_smcd) is_d = (_is_smcd); \ + typeof(_is_rx) is_r = (_is_rx); \ + if ((is_d) && (is_r)) \ + SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_D, rx); \ + if ((is_d) && !(is_r)) \ + SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_D, tx); \ + if (!(is_d) && (is_r)) \ + SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_R, rx); \ + if (!(is_d) && !(is_r)) \ + SMC_STAT_RMB_SUB(_smc_stats, type, SMC_TYPE_R, tx); \ +} \ +while (0) + +#define SMC_STAT_BUF_REUSE(smc, is_smcd, is_rx) \ + SMC_STAT_RMB(smc, reuse, is_smcd, is_rx) + +#define SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rx) \ + SMC_STAT_RMB(smc, alloc, is_smcd, is_rx) + +#define SMC_STAT_RMB_DOWNGRADED(smc, is_smcd, is_rx) \ + SMC_STAT_RMB(smc, dgrade, is_smcd, is_rx) + +#define SMC_STAT_RMB_TX_PEER_FULL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_full_peer, is_smcd, false) + +#define SMC_STAT_RMB_TX_FULL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_full, is_smcd, false) + +#define SMC_STAT_RMB_TX_PEER_SIZE_SMALL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_size_small_peer, is_smcd, false) + +#define SMC_STAT_RMB_TX_SIZE_SMALL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_size_small, is_smcd, false) + +#define SMC_STAT_RMB_RX_SIZE_SMALL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_size_small, is_smcd, true) + +#define SMC_STAT_RMB_RX_FULL(smc, is_smcd) \ + SMC_STAT_RMB(smc, buf_full, is_smcd, true) + +#define SMC_STAT_INC(_smc, type) \ +do { \ + typeof(_smc) __smc = _smc; \ + bool is_smcd = !(__smc)->conn.lnk; \ + struct net *net = sock_net(&(__smc)->sk); \ + struct smc_stats __percpu *smc_stats = net->smc.smc_stats; \ + if ((is_smcd)) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].type); \ + else \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].type); \ +} \ +while (0) + +#define SMC_STAT_CLNT_SUCC_INC(net, _aclc) \ +do { \ + typeof(_aclc) acl = (_aclc); \ + bool is_v2 = (acl->hdr.version == SMC_V2); \ + bool is_smcd = (acl->hdr.typev1 == SMC_TYPE_D); \ + struct smc_stats __percpu *smc_stats = (net)->smc.smc_stats; \ + if (is_v2 && is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].clnt_v2_succ_cnt); \ + else if (is_v2 && !is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].clnt_v2_succ_cnt); \ + else if (!is_v2 && is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].clnt_v1_succ_cnt); \ + else if (!is_v2 && !is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].clnt_v1_succ_cnt); \ +} \ +while (0) + +#define SMC_STAT_SERV_SUCC_INC(net, _ini) \ +do { \ + typeof(_ini) i = (_ini); \ + bool is_v2 = (i->smcd_version & SMC_V2); \ + bool is_smcd = (i->is_smcd); \ + typeof(net->smc.smc_stats) smc_stats = (net)->smc.smc_stats; \ + if (is_v2 && is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].srv_v2_succ_cnt); \ + else if (is_v2 && !is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].srv_v2_succ_cnt); \ + else if (!is_v2 && is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_D].srv_v1_succ_cnt); \ + else if (!is_v2 && !is_smcd) \ + this_cpu_inc(smc_stats->smc[SMC_TYPE_R].srv_v1_succ_cnt); \ +} \ +while (0) + +int smc_nl_get_stats(struct sk_buff *skb, struct netlink_callback *cb); +int smc_nl_get_fback_stats(struct sk_buff *skb, struct netlink_callback *cb); +int smc_stats_init(struct net *net); +void smc_stats_exit(struct net *net); + +#endif /* NET_SMC_SMC_STATS_H_ */ diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 4532c16bf85e..289025cd545a 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -27,6 +27,7 @@ #include "smc_close.h" #include "smc_ism.h" #include "smc_tx.h" +#include "smc_stats.h" #define SMC_TX_WORK_DELAY 0 #define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */ @@ -45,6 +46,8 @@ static void smc_tx_write_space(struct sock *sk) /* similar to sk_stream_write_space */ if (atomic_read(&smc->conn.sndbuf_space) && sock) { + if (test_bit(SOCK_NOSPACE, &sock->flags)) + SMC_STAT_RMB_TX_FULL(smc, !smc->conn.lnk); clear_bit(SOCK_NOSPACE, &sock->flags); rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); @@ -151,9 +154,19 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) goto out_err; } + if (sk->sk_state == SMC_INIT) + return -ENOTCONN; + + if (len > conn->sndbuf_desc->len) + SMC_STAT_RMB_TX_SIZE_SMALL(smc, !conn->lnk); + + if (len > conn->peer_rmbe_size) + SMC_STAT_RMB_TX_PEER_SIZE_SMALL(smc, !conn->lnk); + + if (msg->msg_flags & MSG_OOB) + SMC_STAT_INC(smc, urg_data_cnt); + while (msg_data_left(msg)) { - if (sk->sk_state == SMC_INIT) - return -ENOTCONN; if (smc->sk.sk_shutdown & SEND_SHUTDOWN || (smc->sk.sk_err == ECONNABORTED) || conn->killed) @@ -419,8 +432,12 @@ static int smc_tx_rdma_writes(struct smc_connection *conn, /* destination: RMBE */ /* cf. snd_wnd */ rmbespace = atomic_read(&conn->peer_rmbe_space); - if (rmbespace <= 0) + if (rmbespace <= 0) { + struct smc_sock *smc = container_of(conn, struct smc_sock, + conn); + SMC_STAT_RMB_TX_PEER_FULL(smc, !conn->lnk); return 0; + } smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn); smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn); diff --git a/net/socket.c b/net/socket.c index 4f2c6d2795d0..bd9233da2497 100644 --- a/net/socket.c +++ b/net/socket.c @@ -165,6 +165,54 @@ static const struct file_operations socket_file_ops = { .show_fdinfo = sock_show_fdinfo, }; +static const char * const pf_family_names[] = { + [PF_UNSPEC] = "PF_UNSPEC", + [PF_UNIX] = "PF_UNIX/PF_LOCAL", + [PF_INET] = "PF_INET", + [PF_AX25] = "PF_AX25", + [PF_IPX] = "PF_IPX", + [PF_APPLETALK] = "PF_APPLETALK", + [PF_NETROM] = "PF_NETROM", + [PF_BRIDGE] = "PF_BRIDGE", + [PF_ATMPVC] = "PF_ATMPVC", + [PF_X25] = "PF_X25", + [PF_INET6] = "PF_INET6", + [PF_ROSE] = "PF_ROSE", + [PF_DECnet] = "PF_DECnet", + [PF_NETBEUI] = "PF_NETBEUI", + [PF_SECURITY] = "PF_SECURITY", + [PF_KEY] = "PF_KEY", + [PF_NETLINK] = "PF_NETLINK/PF_ROUTE", + [PF_PACKET] = "PF_PACKET", + [PF_ASH] = "PF_ASH", + [PF_ECONET] = "PF_ECONET", + [PF_ATMSVC] = "PF_ATMSVC", + [PF_RDS] = "PF_RDS", + [PF_SNA] = "PF_SNA", + [PF_IRDA] = "PF_IRDA", + [PF_PPPOX] = "PF_PPPOX", + [PF_WANPIPE] = "PF_WANPIPE", + [PF_LLC] = "PF_LLC", + [PF_IB] = "PF_IB", + [PF_MPLS] = "PF_MPLS", + [PF_CAN] = "PF_CAN", + [PF_TIPC] = "PF_TIPC", + [PF_BLUETOOTH] = "PF_BLUETOOTH", + [PF_IUCV] = "PF_IUCV", + [PF_RXRPC] = "PF_RXRPC", + [PF_ISDN] = "PF_ISDN", + [PF_PHONET] = "PF_PHONET", + [PF_IEEE802154] = "PF_IEEE802154", + [PF_CAIF] = "PF_CAIF", + [PF_ALG] = "PF_ALG", + [PF_NFC] = "PF_NFC", + [PF_VSOCK] = "PF_VSOCK", + [PF_KCM] = "PF_KCM", + [PF_QIPCRTR] = "PF_QIPCRTR", + [PF_SMC] = "PF_SMC", + [PF_XDP] = "PF_XDP", +}; + /* * The protocol list. Each protocol is registered in here. */ @@ -2975,7 +3023,7 @@ int sock_register(const struct net_proto_family *ops) } spin_unlock(&net_family_lock); - pr_info("NET: Registered protocol family %d\n", ops->family); + pr_info("NET: Registered %s protocol family\n", pf_family_names[ops->family]); return err; } EXPORT_SYMBOL(sock_register); @@ -3003,7 +3051,7 @@ void sock_unregister(int family) synchronize_rcu(); - pr_info("NET: Unregistered protocol family %d\n", family); + pr_info("NET: Unregistered %s protocol family\n", pf_family_names[family]); } EXPORT_SYMBOL(sock_unregister); diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index b3815c1e8f2e..9c0343568d2a 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -58,7 +58,7 @@ static void strp_abort_strp(struct strparser *strp, int err) /* Report an error on the lower socket */ sk->sk_err = -err; - sk->sk_error_report(sk); + sk_error_report(sk); } } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 89a36db47ab4..070698dd19bc 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -381,19 +381,20 @@ EXPORT_SYMBOL_GPL(call_switchdev_blocking_notifiers); static int __switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*add_cb)(struct net_device *dev, + int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)) { + struct switchdev_notifier_info *info = &port_obj_info->info; struct netlink_ext_ack *extack; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; - extack = switchdev_notifier_info_to_extack(&port_obj_info->info); + extack = switchdev_notifier_info_to_extack(info); if (check_cb(dev)) { - err = add_cb(dev, port_obj_info->obj, extack); + err = add_cb(dev, info->ctx, port_obj_info->obj, extack); if (err != -EOPNOTSUPP) port_obj_info->handled = true; return err; @@ -422,7 +423,7 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev, int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*add_cb)(struct net_device *dev, + int (*add_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj, struct netlink_ext_ack *extack)) { @@ -439,15 +440,16 @@ EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_add); static int __switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*del_cb)(struct net_device *dev, + int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)) { + struct switchdev_notifier_info *info = &port_obj_info->info; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; if (check_cb(dev)) { - err = del_cb(dev, port_obj_info->obj); + err = del_cb(dev, info->ctx, port_obj_info->obj); if (err != -EOPNOTSUPP) port_obj_info->handled = true; return err; @@ -476,7 +478,7 @@ static int __switchdev_handle_port_obj_del(struct net_device *dev, int switchdev_handle_port_obj_del(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), - int (*del_cb)(struct net_device *dev, + int (*del_cb)(struct net_device *dev, const void *ctx, const struct switchdev_obj *obj)) { int err; @@ -492,19 +494,20 @@ EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del); static int __switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), - int (*set_cb)(struct net_device *dev, + int (*set_cb)(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack)) { + struct switchdev_notifier_info *info = &port_attr_info->info; struct netlink_ext_ack *extack; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; - extack = switchdev_notifier_info_to_extack(&port_attr_info->info); + extack = switchdev_notifier_info_to_extack(info); if (check_cb(dev)) { - err = set_cb(dev, port_attr_info->attr, extack); + err = set_cb(dev, info->ctx, port_attr_info->attr, extack); if (err != -EOPNOTSUPP) port_attr_info->handled = true; return err; @@ -533,7 +536,7 @@ static int __switchdev_handle_port_attr_set(struct net_device *dev, int switchdev_handle_port_attr_set(struct net_device *dev, struct switchdev_notifier_port_attr_info *port_attr_info, bool (*check_cb)(const struct net_device *dev), - int (*set_cb)(struct net_device *dev, + int (*set_cb)(struct net_device *dev, const void *ctx, const struct switchdev_attr *attr, struct netlink_ext_ack *extack)) { diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index d4beca895992..593846d25214 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -699,7 +699,7 @@ int tipc_bcast_init(struct net *net) spin_lock_init(&tipc_net(net)->bclock); if (!tipc_link_bc_create(net, 0, 0, NULL, - FB_MTU, + one_page_mtu, BCLINK_WIN_DEFAULT, BCLINK_WIN_DEFAULT, 0, diff --git a/net/tipc/link.c b/net/tipc/link.c index 1b7a487c8841..cf586840caeb 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -913,7 +913,7 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr) skb = tipc_msg_create(SOCK_WAKEUP, 0, INT_H_SIZE, 0, dnode, l->addr, dport, 0, 0); if (!skb) - return -ENOBUFS; + return -ENOMEM; msg_set_dest_droppable(buf_msg(skb), true); TIPC_SKB_CB(skb)->chain_imp = msg_importance(hdr); skb_queue_tail(&l->wakeupq, skb); @@ -1031,7 +1031,7 @@ void tipc_link_reset(struct tipc_link *l) * * Consumes the buffer chain. * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted - * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS + * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS or -ENOMEM */ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, struct sk_buff_head *xmitq) @@ -1089,7 +1089,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list, if (!_skb) { kfree_skb(skb); __skb_queue_purge(list); - return -ENOBUFS; + return -ENOMEM; } __skb_queue_tail(transmq, skb); tipc_link_set_skb_retransmit_time(skb, l); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index ce6ab54822d8..5c9fd4791c4b 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -41,19 +41,18 @@ #include "name_table.h" #include "crypto.h" +#define BUF_ALIGN(x) ALIGN(x, 4) #define MAX_FORWARD_SIZE 1024 #ifdef CONFIG_TIPC_CRYPTO #define BUF_HEADROOM ALIGN(((LL_MAX_HEADER + 48) + EHDR_MAX_SIZE), 16) -#define BUF_TAILROOM (TIPC_AES_GCM_TAG_SIZE) +#define BUF_OVERHEAD (BUF_HEADROOM + TIPC_AES_GCM_TAG_SIZE) #else #define BUF_HEADROOM (LL_MAX_HEADER + 48) -#define BUF_TAILROOM 16 +#define BUF_OVERHEAD BUF_HEADROOM #endif -static unsigned int align(unsigned int i) -{ - return (i + 3) & ~3u; -} +const int one_page_mtu = PAGE_SIZE - SKB_DATA_ALIGN(BUF_OVERHEAD) - + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); /** * tipc_buf_acquire - creates a TIPC message buffer @@ -69,13 +68,8 @@ static unsigned int align(unsigned int i) struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp) { struct sk_buff *skb; -#ifdef CONFIG_TIPC_CRYPTO - unsigned int buf_size = (BUF_HEADROOM + size + BUF_TAILROOM + 3) & ~3u; -#else - unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u; -#endif - skb = alloc_skb_fclone(buf_size, gfp); + skb = alloc_skb_fclone(BUF_OVERHEAD + size, gfp); if (skb) { skb_reserve(skb, BUF_HEADROOM); skb_put(skb, size); @@ -395,7 +389,8 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, if (unlikely(!skb)) { if (pktmax != MAX_MSG_SIZE) return -ENOMEM; - rc = tipc_msg_build(mhdr, m, offset, dsz, FB_MTU, list); + rc = tipc_msg_build(mhdr, m, offset, dsz, + one_page_mtu, list); if (rc != dsz) return rc; if (tipc_msg_assemble(list)) @@ -490,7 +485,7 @@ static bool tipc_msg_bundle(struct sk_buff *bskb, struct tipc_msg *msg, msz = msg_size(msg); bsz = msg_size(bmsg); - offset = align(bsz); + offset = BUF_ALIGN(bsz); pad = offset - bsz; if (unlikely(skb_tailroom(bskb) < (pad + msz))) @@ -547,7 +542,7 @@ bool tipc_msg_try_bundle(struct sk_buff *tskb, struct sk_buff **skb, u32 mss, /* Make a new bundle of the two messages if possible */ tsz = msg_size(buf_msg(tskb)); - if (unlikely(mss < align(INT_H_SIZE + tsz) + msg_size(msg))) + if (unlikely(mss < BUF_ALIGN(INT_H_SIZE + tsz) + msg_size(msg))) return true; if (unlikely(pskb_expand_head(tskb, INT_H_SIZE, mss - tsz - INT_H_SIZE, GFP_ATOMIC))) @@ -606,7 +601,7 @@ bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos) if (unlikely(!tipc_msg_validate(iskb))) goto none; - *pos += align(imsz); + *pos += BUF_ALIGN(imsz); return true; none: kfree_skb(skb); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 5d64596ba987..64ae4c4c44f8 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -99,9 +99,10 @@ struct plist; #define MAX_H_SIZE 60 /* Largest possible TIPC header size */ #define MAX_MSG_SIZE (MAX_H_SIZE + TIPC_MAX_USER_MSG_SIZE) -#define FB_MTU 3744 #define TIPC_MEDIA_INFO_OFFSET 5 +extern const int one_page_mtu; + struct tipc_skb_cb { union { struct { diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index fecab516bf41..01396dd1c899 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -673,12 +673,12 @@ exit: * Returns a list of local sockets */ void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua, - bool exact, struct list_head *dports) + struct list_head *dports) { struct service_range *sr; struct tipc_service *sc; struct publication *p; - u32 scope = ua->scope; + u8 scope = ua->scope; rcu_read_lock(); sc = tipc_service_find(net, ua); @@ -688,7 +688,7 @@ void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua, spin_lock_bh(&sc->lock); service_range_foreach_match(sr, sc, ua->sr.lower, ua->sr.upper) { list_for_each_entry(p, &sr->local_publ, local_publ) { - if (p->scope == scope || (!exact && p->scope < scope)) + if (scope == p->scope || scope == TIPC_ANY_SCOPE) tipc_dest_push(dports, 0, p->sk.ref); } } diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index c7c9a3ddd420..259f95e3d99c 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -51,6 +51,8 @@ struct tipc_uaddr; #define TIPC_PUBL_SCOPE_NUM (TIPC_NODE_SCOPE + 1) #define TIPC_NAMETBL_SIZE 1024 /* must be a power of 2 */ +#define TIPC_ANY_SCOPE 10 /* Both node and cluster scope will match */ + /** * struct publication - info about a published service address or range * @sr: service range represented by this publication @@ -113,7 +115,7 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb); bool tipc_nametbl_lookup_anycast(struct net *net, struct tipc_uaddr *ua, struct tipc_socket_addr *sk); void tipc_nametbl_lookup_mcast_sockets(struct net *net, struct tipc_uaddr *ua, - bool exact, struct list_head *dports); + struct list_head *dports); void tipc_nametbl_lookup_mcast_nodes(struct net *net, struct tipc_uaddr *ua, struct tipc_nlist *nodes); bool tipc_nametbl_lookup_group(struct net *net, struct tipc_uaddr *ua, diff --git a/net/tipc/node.c b/net/tipc/node.c index 81af92954c6c..9947b7dfe1d2 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1214,7 +1214,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, /* Peer has changed i/f address without rebooting. * If so, the link will reset soon, and the next * discovery will be accepted. So we can ignore it. - * It may also be an cloned or malicious peer having + * It may also be a cloned or malicious peer having * chosen the same node address and signature as an * existing one. * Ignore requests until the link goes down, if ever. diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 53af72824c9c..34a97ea36cc8 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -73,9 +73,6 @@ struct sockaddr_pair { /** * struct tipc_sock - TIPC socket structure * @sk: socket - interacts with 'port' and with user via the socket API - * @conn_type: TIPC type used when connection was established - * @conn_instance: TIPC instance used when connection was established - * @published: non-zero if port has one or more associated names * @max_pkt: maximum packet size "hint" used when building messages sent by port * @maxnagle: maximum size of msg which can be subject to nagle * @portid: unique port identity in TIPC socket hash table @@ -106,11 +103,11 @@ struct sockaddr_pair { * @expect_ack: whether this TIPC socket is expecting an ack * @nodelay: setsockopt() TIPC_NODELAY setting * @group_is_open: TIPC socket group is fully open (FIXME) + * @published: true if port has one or more associated names + * @conn_addrtype: address type used when establishing connection */ struct tipc_sock { struct sock sk; - u32 conn_type; - u32 conn_instance; u32 max_pkt; u32 maxnagle; u32 portid; @@ -141,6 +138,7 @@ struct tipc_sock { bool nodelay; bool group_is_open; bool published; + u8 conn_addrtype; }; static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); @@ -664,7 +662,7 @@ static int tipc_release(struct socket *sock) * @skaddr: socket address describing name(s) and desired operation * @alen: size of socket address data structure * - * Name and name sequence binding is indicated using a positive scope value; + * Name and name sequence binding are indicated using a positive scope value; * a negative scope value unbinds the specified name. Specifying no name * (i.e. a socket address length of 0) unbinds all names from the socket. * @@ -1202,12 +1200,12 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, struct tipc_msg *hdr; struct tipc_uaddr ua; int user, mtyp, hlen; - bool exact; __skb_queue_head_init(&tmpq); INIT_LIST_HEAD(&dports); ua.addrtype = TIPC_SERVICE_RANGE; + /* tipc_skb_peek() increments the head skb's reference counter */ skb = tipc_skb_peek(arrvq, &inputq->lock); for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) { hdr = buf_msg(skb); @@ -1216,6 +1214,12 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, hlen = skb_headroom(skb) + msg_hdr_sz(hdr); onode = msg_orignode(hdr); ua.sr.type = msg_nametype(hdr); + ua.sr.lower = msg_namelower(hdr); + ua.sr.upper = msg_nameupper(hdr); + if (onode == self) + ua.scope = TIPC_ANY_SCOPE; + else + ua.scope = TIPC_CLUSTER_SCOPE; if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) { spin_lock_bh(&inputq->lock); @@ -1233,20 +1237,10 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, ua.sr.lower = 0; ua.sr.upper = ~0; ua.scope = msg_lookup_scope(hdr); - exact = true; - } else { - /* TIPC_NODE_SCOPE means "any scope" in this context */ - if (onode == self) - ua.scope = TIPC_NODE_SCOPE; - else - ua.scope = TIPC_CLUSTER_SCOPE; - exact = false; - ua.sr.lower = msg_namelower(hdr); - ua.sr.upper = msg_nameupper(hdr); } /* Create destination port list: */ - tipc_nametbl_lookup_mcast_sockets(net, &ua, exact, &dports); + tipc_nametbl_lookup_mcast_sockets(net, &ua, &dports); /* Clone message per destination */ while (tipc_dest_pop(&dports, NULL, &portid)) { @@ -1258,13 +1252,11 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, } pr_warn("Failed to clone mcast rcv buffer\n"); } - /* Append to inputq if not already done by other thread */ + /* Append clones to inputq only if skb is still head of arrvq */ spin_lock_bh(&inputq->lock); if (skb_peek(arrvq) == skb) { skb_queue_splice_tail_init(&tmpq, inputq); - /* Decrease the skb's refcnt as increasing in the - * function tipc_skb_peek - */ + /* Decrement the skb's refcnt */ kfree_skb(__skb_dequeue(arrvq)); } spin_unlock_bh(&inputq->lock); @@ -1463,10 +1455,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) return -EISCONN; if (tsk->published) return -EOPNOTSUPP; - if (atype == TIPC_SERVICE_ADDR) { - tsk->conn_type = ua->sa.type; - tsk->conn_instance = ua->sa.instance; - } + if (atype == TIPC_SERVICE_ADDR) + tsk->conn_addrtype = atype; msg_set_syn(hdr, 1); } @@ -1737,67 +1727,58 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb) static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb, struct tipc_sock *tsk) { - struct tipc_msg *msg; - u32 anc_data[3]; - u32 err; - u32 dest_type; - int has_name; - int res; + struct tipc_msg *hdr; + u32 data[3] = {0,}; + bool has_addr; + int dlen, rc; if (likely(m->msg_controllen == 0)) return 0; - msg = buf_msg(skb); - /* Optionally capture errored message object(s) */ - err = msg ? msg_errcode(msg) : 0; - if (unlikely(err)) { - anc_data[0] = err; - anc_data[1] = msg_data_sz(msg); - res = put_cmsg(m, SOL_TIPC, TIPC_ERRINFO, 8, anc_data); - if (res) - return res; - if (anc_data[1]) { - if (skb_linearize(skb)) - return -ENOMEM; - msg = buf_msg(skb); - res = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, anc_data[1], - msg_data(msg)); - if (res) - return res; - } + hdr = buf_msg(skb); + dlen = msg_data_sz(hdr); + + /* Capture errored message object, if any */ + if (msg_errcode(hdr)) { + if (skb_linearize(skb)) + return -ENOMEM; + hdr = buf_msg(skb); + data[0] = msg_errcode(hdr); + data[1] = dlen; + rc = put_cmsg(m, SOL_TIPC, TIPC_ERRINFO, 8, data); + if (rc || !dlen) + return rc; + rc = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, dlen, msg_data(hdr)); + if (rc) + return rc; } - /* Optionally capture message destination object */ - dest_type = msg ? msg_type(msg) : TIPC_DIRECT_MSG; - switch (dest_type) { + /* Capture TIPC_SERVICE_ADDR/RANGE destination address, if any */ + switch (msg_type(hdr)) { case TIPC_NAMED_MSG: - has_name = 1; - anc_data[0] = msg_nametype(msg); - anc_data[1] = msg_namelower(msg); - anc_data[2] = msg_namelower(msg); + has_addr = true; + data[0] = msg_nametype(hdr); + data[1] = msg_namelower(hdr); + data[2] = data[1]; break; case TIPC_MCAST_MSG: - has_name = 1; - anc_data[0] = msg_nametype(msg); - anc_data[1] = msg_namelower(msg); - anc_data[2] = msg_nameupper(msg); + has_addr = true; + data[0] = msg_nametype(hdr); + data[1] = msg_namelower(hdr); + data[2] = msg_nameupper(hdr); break; case TIPC_CONN_MSG: - has_name = (tsk->conn_type != 0); - anc_data[0] = tsk->conn_type; - anc_data[1] = tsk->conn_instance; - anc_data[2] = tsk->conn_instance; + has_addr = !!tsk->conn_addrtype; + data[0] = msg_nametype(&tsk->phdr); + data[1] = msg_nameinst(&tsk->phdr); + data[2] = data[1]; break; default: - has_name = 0; + has_addr = false; } - if (has_name) { - res = put_cmsg(m, SOL_TIPC, TIPC_DESTNAME, 12, anc_data); - if (res) - return res; - } - - return 0; + if (!has_addr) + return 0; + return put_cmsg(m, SOL_TIPC, TIPC_DESTNAME, 12, data); } static struct sk_buff *tipc_sk_build_ack(struct tipc_sock *tsk) @@ -2750,8 +2731,9 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, tsk_set_importance(new_sk, msg_importance(msg)); if (msg_named(msg)) { - new_tsock->conn_type = msg_nametype(msg); - new_tsock->conn_instance = msg_nameinst(msg); + new_tsock->conn_addrtype = TIPC_SERVICE_ADDR; + msg_set_nametype(&new_tsock->phdr, msg_nametype(msg)); + msg_set_nameinst(&new_tsock->phdr, msg_nameinst(msg)); } /* @@ -3455,13 +3437,14 @@ void tipc_socket_stop(void) /* Caller should hold socket lock for the passed tipc socket. */ static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk) { - u32 peer_node; - u32 peer_port; + u32 peer_node, peer_port; + u32 conn_type, conn_instance; struct nlattr *nest; peer_node = tsk_peer_node(tsk); peer_port = tsk_peer_port(tsk); - + conn_type = msg_nametype(&tsk->phdr); + conn_instance = msg_nameinst(&tsk->phdr); nest = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_CON); if (!nest) return -EMSGSIZE; @@ -3471,12 +3454,12 @@ static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk) if (nla_put_u32(skb, TIPC_NLA_CON_SOCK, peer_port)) goto msg_full; - if (tsk->conn_type != 0) { + if (tsk->conn_addrtype != 0) { if (nla_put_flag(skb, TIPC_NLA_CON_FLAG)) goto msg_full; - if (nla_put_u32(skb, TIPC_NLA_CON_TYPE, tsk->conn_type)) + if (nla_put_u32(skb, TIPC_NLA_CON_TYPE, conn_type)) goto msg_full; - if (nla_put_u32(skb, TIPC_NLA_CON_INST, tsk->conn_instance)) + if (nla_put_u32(skb, TIPC_NLA_CON_INST, conn_instance)) goto msg_full; } nla_nest_end(skb, nest); @@ -3866,9 +3849,9 @@ bool tipc_sk_filtering(struct sock *sk) } if (!tipc_sk_type_connectionless(sk)) { - type = tsk->conn_type; - lower = tsk->conn_instance; - upper = tsk->conn_instance; + type = msg_nametype(&tsk->phdr); + lower = msg_nameinst(&tsk->phdr); + upper = lower; } if ((_type && _type != type) || (_lower && _lower != lower) || @@ -3933,6 +3916,7 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf) { int i = 0; size_t sz = (dqueues) ? SK_LMAX : SK_LMIN; + u32 conn_type, conn_instance; struct tipc_sock *tsk; struct publication *p; bool tsk_connected; @@ -3953,8 +3937,10 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf) if (tsk_connected) { i += scnprintf(buf + i, sz - i, " %x", tsk_peer_node(tsk)); i += scnprintf(buf + i, sz - i, " %u", tsk_peer_port(tsk)); - i += scnprintf(buf + i, sz - i, " %u", tsk->conn_type); - i += scnprintf(buf + i, sz - i, " %u", tsk->conn_instance); + conn_type = msg_nametype(&tsk->phdr); + conn_instance = msg_nameinst(&tsk->phdr); + i += scnprintf(buf + i, sz - i, " %u", conn_type); + i += scnprintf(buf + i, sz - i, " %u", conn_instance); } i += scnprintf(buf + i, sz - i, " | %u", tsk->published); if (tsk->published) { diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 8e00d739f03a..05d49ad81290 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -66,7 +66,7 @@ static void tipc_sub_send_event(struct tipc_subscription *sub, /** * tipc_sub_check_overlap - test for subscription overlap with the given values * @subscribed: the service range subscribed for - * @found: the service range we are checning for match + * @found: the service range we are checking for match * * Returns true if there is overlap, otherwise false. */ diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index bd9f1567aa39..b932469ee69c 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -128,7 +128,7 @@ static void destroy_record(struct tls_record_info *record) int i; for (i = 0; i < record->num_frags; i++) - __skb_frag_unref(&record->frags[i]); + __skb_frag_unref(&record->frags[i], false); kfree(record); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 694de024d0ee..4feb95e34b64 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1153,7 +1153,7 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page, int ret = 0; bool eor; - eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST)); + eor = !(flags & MSG_SENDPAGE_NOTLAST); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); /* Call the sk_stream functions to manage the sndbuf mem. */ @@ -2019,8 +2019,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, if (copied < 0) goto splice_read_end; - if (likely(!(flags & MSG_PEEK))) - tls_sw_advance_skb(sk, skb, copied); + tls_sw_advance_skb(sk, skb, copied); splice_read_end: release_sock(sk); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5d1192ceb139..23c92ad15c61 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -262,6 +262,14 @@ static void __unix_insert_socket(struct hlist_head *list, struct sock *sk) sk_add_node(sk, list); } +static void __unix_set_addr(struct sock *sk, struct unix_address *addr, + unsigned hash) +{ + __unix_remove_socket(sk); + smp_store_release(&unix_sk(sk)->addr, addr); + __unix_insert_socket(&unix_socket_table[hash], sk); +} + static inline void unix_remove_socket(struct sock *sk) { spin_lock(&unix_table_lock); @@ -278,11 +286,11 @@ static inline void unix_insert_socket(struct hlist_head *list, struct sock *sk) static struct sock *__unix_find_socket_byname(struct net *net, struct sockaddr_un *sunname, - int len, int type, unsigned int hash) + int len, unsigned int hash) { struct sock *s; - sk_for_each(s, &unix_socket_table[hash ^ type]) { + sk_for_each(s, &unix_socket_table[hash]) { struct unix_sock *u = unix_sk(s); if (!net_eq(sock_net(s), net)) @@ -297,13 +305,12 @@ static struct sock *__unix_find_socket_byname(struct net *net, static inline struct sock *unix_find_socket_byname(struct net *net, struct sockaddr_un *sunname, - int len, int type, - unsigned int hash) + int len, unsigned int hash) { struct sock *s; spin_lock(&unix_table_lock); - s = __unix_find_socket_byname(net, sunname, len, type, hash); + s = __unix_find_socket_byname(net, sunname, len, hash); if (s) sock_hold(s); spin_unlock(&unix_table_lock); @@ -484,7 +491,7 @@ static void unix_dgram_disconnected(struct sock *sk, struct sock *other) */ if (!sock_flag(other, SOCK_DEAD) && unix_peer(other) == sk) { other->sk_err = ECONNRESET; - other->sk_error_report(other); + sk_error_report(other); } } } @@ -891,12 +898,12 @@ static int unix_autobind(struct socket *sock) retry: addr->len = sprintf(addr->name->sun_path+1, "%05x", ordernum) + 1 + sizeof(short); addr->hash = unix_hash_fold(csum_partial(addr->name, addr->len, 0)); + addr->hash ^= sk->sk_type; spin_lock(&unix_table_lock); ordernum = (ordernum+1)&0xFFFFF; - if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type, - addr->hash)) { + if (__unix_find_socket_byname(net, addr->name, addr->len, addr->hash)) { spin_unlock(&unix_table_lock); /* * __unix_find_socket_byname() may take long time if many names @@ -911,11 +918,8 @@ retry: } goto retry; } - addr->hash ^= sk->sk_type; - __unix_remove_socket(sk); - smp_store_release(&u->addr, addr); - __unix_insert_socket(&unix_socket_table[addr->hash], sk); + __unix_set_addr(sk, addr, addr->hash); spin_unlock(&unix_table_lock); err = 0; @@ -960,7 +964,7 @@ static struct sock *unix_find_other(struct net *net, } } else { err = -ECONNREFUSED; - u = unix_find_socket_byname(net, sunname, len, type, hash); + u = unix_find_socket_byname(net, sunname, len, type ^ hash); if (u) { struct dentry *dentry; dentry = unix_sk(u)->path.dentry; @@ -978,125 +982,125 @@ fail: return NULL; } -static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) +static int unix_bind_bsd(struct sock *sk, struct unix_address *addr) { + struct unix_sock *u = unix_sk(sk); + umode_t mode = S_IFSOCK | + (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask()); + struct user_namespace *ns; // barf... + struct path parent; struct dentry *dentry; - struct path path; - int err = 0; + unsigned int hash; + int err; + /* * Get the parent directory, calculate the hash for last * component. */ - dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); - err = PTR_ERR(dentry); + dentry = kern_path_create(AT_FDCWD, addr->name->sun_path, &parent, 0); if (IS_ERR(dentry)) - return err; + return PTR_ERR(dentry); + ns = mnt_user_ns(parent.mnt); /* * All right, let's create it. */ - err = security_path_mknod(&path, dentry, mode, 0); - if (!err) { - err = vfs_mknod(mnt_user_ns(path.mnt), d_inode(path.dentry), - dentry, mode, 0); - if (!err) { - res->mnt = mntget(path.mnt); - res->dentry = dget(dentry); - } - } - done_path_create(&path, dentry); + err = security_path_mknod(&parent, dentry, mode, 0); + if (!err) + err = vfs_mknod(ns, d_inode(parent.dentry), dentry, mode, 0); + if (err) + goto out; + err = mutex_lock_interruptible(&u->bindlock); + if (err) + goto out_unlink; + if (u->addr) + goto out_unlock; + + addr->hash = UNIX_HASH_SIZE; + hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1); + spin_lock(&unix_table_lock); + u->path.mnt = mntget(parent.mnt); + u->path.dentry = dget(dentry); + __unix_set_addr(sk, addr, hash); + spin_unlock(&unix_table_lock); + mutex_unlock(&u->bindlock); + done_path_create(&parent, dentry); + return 0; + +out_unlock: + mutex_unlock(&u->bindlock); + err = -EINVAL; +out_unlink: + /* failed after successful mknod? unlink what we'd created... */ + vfs_unlink(ns, d_inode(parent.dentry), dentry, NULL); +out: + done_path_create(&parent, dentry); return err; } +static int unix_bind_abstract(struct sock *sk, struct unix_address *addr) +{ + struct unix_sock *u = unix_sk(sk); + int err; + + err = mutex_lock_interruptible(&u->bindlock); + if (err) + return err; + + if (u->addr) { + mutex_unlock(&u->bindlock); + return -EINVAL; + } + + spin_lock(&unix_table_lock); + if (__unix_find_socket_byname(sock_net(sk), addr->name, addr->len, + addr->hash)) { + spin_unlock(&unix_table_lock); + mutex_unlock(&u->bindlock); + return -EADDRINUSE; + } + __unix_set_addr(sk, addr, addr->hash); + spin_unlock(&unix_table_lock); + mutex_unlock(&u->bindlock); + return 0; +} + static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - struct net *net = sock_net(sk); - struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; char *sun_path = sunaddr->sun_path; int err; unsigned int hash; struct unix_address *addr; - struct hlist_head *list; - struct path path = { }; - err = -EINVAL; if (addr_len < offsetofend(struct sockaddr_un, sun_family) || sunaddr->sun_family != AF_UNIX) - goto out; + return -EINVAL; - if (addr_len == sizeof(short)) { - err = unix_autobind(sock); - goto out; - } + if (addr_len == sizeof(short)) + return unix_autobind(sock); err = unix_mkname(sunaddr, addr_len, &hash); if (err < 0) - goto out; + return err; addr_len = err; - - if (sun_path[0]) { - umode_t mode = S_IFSOCK | - (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = unix_mknod(sun_path, mode, &path); - if (err) { - if (err == -EEXIST) - err = -EADDRINUSE; - goto out; - } - } - - err = mutex_lock_interruptible(&u->bindlock); - if (err) - goto out_put; - - err = -EINVAL; - if (u->addr) - goto out_up; - - err = -ENOMEM; addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL); if (!addr) - goto out_up; + return -ENOMEM; memcpy(addr->name, sunaddr, addr_len); addr->len = addr_len; addr->hash = hash ^ sk->sk_type; refcount_set(&addr->refcnt, 1); - if (sun_path[0]) { - addr->hash = UNIX_HASH_SIZE; - hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1); - spin_lock(&unix_table_lock); - u->path = path; - list = &unix_socket_table[hash]; - } else { - spin_lock(&unix_table_lock); - err = -EADDRINUSE; - if (__unix_find_socket_byname(net, sunaddr, addr_len, - sk->sk_type, hash)) { - unix_release_addr(addr); - goto out_unlock; - } - - list = &unix_socket_table[addr->hash]; - } - - err = 0; - __unix_remove_socket(sk); - smp_store_release(&u->addr, addr); - __unix_insert_socket(list, sk); - -out_unlock: - spin_unlock(&unix_table_lock); -out_up: - mutex_unlock(&u->bindlock); -out_put: + if (sun_path[0]) + err = unix_bind_bsd(sk, addr); + else + err = unix_bind_abstract(sk, addr); if (err) - path_put(&path); -out: - return err; + unix_release_addr(addr); + return err == -EEXIST ? -EADDRINUSE : err; } static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) @@ -1393,7 +1397,7 @@ restart: unix_state_unlock(sk); - /* take ten and and send info to listening sock */ + /* take ten and send info to listening sock */ spin_lock(&other->sk_receive_queue.lock); __skb_queue_tail(&other->sk_receive_queue, skb); spin_unlock(&other->sk_receive_queue.lock); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 92a72f0e0d94..3e02cc3b24f8 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -415,8 +415,8 @@ static void vsock_deassign_transport(struct vsock_sock *vsk) /* Assign a transport to a socket and call the .init transport callback. * - * Note: for stream socket this must be called when vsk->remote_addr is set - * (e.g. during the connect() or when a connection request on a listener + * Note: for connection oriented socket this must be called when vsk->remote_addr + * is set (e.g. during the connect() or when a connection request on a listener * socket is received). * The vsk->remote_addr is used to decide which transport to use: * - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if @@ -452,6 +452,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) new_transport = transport_dgram; break; case SOCK_STREAM: + case SOCK_SEQPACKET: if (vsock_use_local_transport(remote_cid)) new_transport = transport_local; else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g || @@ -469,10 +470,10 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) return 0; /* transport->release() must be called with sock lock acquired. - * This path can only be taken during vsock_stream_connect(), - * where we have already held the sock lock. - * In the other cases, this function is called on a new socket - * which is not assigned to any transport. + * This path can only be taken during vsock_connect(), where we + * have already held the sock lock. In the other cases, this + * function is called on a new socket which is not assigned to + * any transport. */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); @@ -484,6 +485,14 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) if (!new_transport || !try_module_get(new_transport->module)) return -ENODEV; + if (sk->sk_type == SOCK_SEQPACKET) { + if (!new_transport->seqpacket_allow || + !new_transport->seqpacket_allow(remote_cid)) { + module_put(new_transport->module); + return -ESOCKTNOSUPPORT; + } + } + ret = new_transport->init(vsk, psk); if (ret) { module_put(new_transport->module); @@ -604,8 +613,8 @@ out: /**** SOCKET OPERATIONS ****/ -static int __vsock_bind_stream(struct vsock_sock *vsk, - struct sockaddr_vm *addr) +static int __vsock_bind_connectible(struct vsock_sock *vsk, + struct sockaddr_vm *addr) { static u32 port; struct sockaddr_vm new_addr; @@ -649,9 +658,10 @@ static int __vsock_bind_stream(struct vsock_sock *vsk, vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port); - /* Remove stream sockets from the unbound list and add them to the hash - * table for easy lookup by its address. The unbound list is simply an - * extra entry at the end of the hash table, a trick used by AF_UNIX. + /* Remove connection oriented sockets from the unbound list and add them + * to the hash table for easy lookup by its address. The unbound list + * is simply an extra entry at the end of the hash table, a trick used + * by AF_UNIX. */ __vsock_remove_bound(vsk); __vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk); @@ -684,8 +694,9 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) switch (sk->sk_socket->type) { case SOCK_STREAM: + case SOCK_SEQPACKET: spin_lock_bh(&vsock_table_lock); - retval = __vsock_bind_stream(vsk, addr); + retval = __vsock_bind_connectible(vsk, addr); spin_unlock_bh(&vsock_table_lock); break; @@ -768,6 +779,11 @@ static struct sock *__vsock_create(struct net *net, return sk; } +static bool sock_type_connectible(u16 type) +{ + return (type == SOCK_STREAM) || (type == SOCK_SEQPACKET); +} + static void __vsock_release(struct sock *sk, int level) { if (sk) { @@ -786,7 +802,7 @@ static void __vsock_release(struct sock *sk, int level) if (vsk->transport) vsk->transport->release(vsk); - else if (sk->sk_type == SOCK_STREAM) + else if (sock_type_connectible(sk->sk_type)) vsock_remove_sock(vsk); sock_orphan(sk); @@ -844,6 +860,16 @@ s64 vsock_stream_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(vsock_stream_has_data); +static s64 vsock_connectible_has_data(struct vsock_sock *vsk) +{ + struct sock *sk = sk_vsock(vsk); + + if (sk->sk_type == SOCK_SEQPACKET) + return vsk->transport->seqpacket_has_data(vsk); + else + return vsock_stream_has_data(vsk); +} + s64 vsock_stream_has_space(struct vsock_sock *vsk) { return vsk->transport->stream_has_space(vsk); @@ -937,10 +963,10 @@ static int vsock_shutdown(struct socket *sock, int mode) if ((mode & ~SHUTDOWN_MASK) || !mode) return -EINVAL; - /* If this is a STREAM socket and it is not connected then bail out - * immediately. If it is a DGRAM socket then we must first kick the - * socket so that it wakes up from any sleeping calls, for example - * recv(), and then afterwards return the error. + /* If this is a connection oriented socket and it is not connected then + * bail out immediately. If it is a DGRAM socket then we must first + * kick the socket so that it wakes up from any sleeping calls, for + * example recv(), and then afterwards return the error. */ sk = sock->sk; @@ -948,7 +974,7 @@ static int vsock_shutdown(struct socket *sock, int mode) lock_sock(sk); if (sock->state == SS_UNCONNECTED) { err = -ENOTCONN; - if (sk->sk_type == SOCK_STREAM) + if (sock_type_connectible(sk->sk_type)) goto out; } else { sock->state = SS_DISCONNECTING; @@ -961,7 +987,7 @@ static int vsock_shutdown(struct socket *sock, int mode) sk->sk_shutdown |= mode; sk->sk_state_change(sk); - if (sk->sk_type == SOCK_STREAM) { + if (sock_type_connectible(sk->sk_type)) { sock_reset_flag(sk, SOCK_DONE); vsock_send_shutdown(sk, mode); } @@ -1016,7 +1042,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, if (!(sk->sk_shutdown & SEND_SHUTDOWN)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; - } else if (sock->type == SOCK_STREAM) { + } else if (sock_type_connectible(sk->sk_type)) { const struct vsock_transport *transport; lock_sock(sk); @@ -1255,7 +1281,7 @@ static void vsock_connect_timeout(struct work_struct *work) (sk->sk_shutdown != SHUTDOWN_MASK)) { sk->sk_state = TCP_CLOSE; sk->sk_err = ETIMEDOUT; - sk->sk_error_report(sk); + sk_error_report(sk); vsock_transport_cancel_pkt(vsk); } release_sock(sk); @@ -1263,8 +1289,8 @@ static void vsock_connect_timeout(struct work_struct *work) sock_put(sk); } -static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, - int addr_len, int flags) +static int vsock_connect(struct socket *sock, struct sockaddr *addr, + int addr_len, int flags) { int err; struct sock *sk; @@ -1369,7 +1395,7 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, if (signal_pending(current)) { err = sock_intr_errno(timeout); - sk->sk_state = TCP_CLOSE; + sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE; sock->state = SS_UNCONNECTED; vsock_transport_cancel_pkt(vsk); goto out_wait; @@ -1414,7 +1440,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, lock_sock(listener); - if (sock->type != SOCK_STREAM) { + if (!sock_type_connectible(sock->type)) { err = -EOPNOTSUPP; goto out; } @@ -1491,7 +1517,7 @@ static int vsock_listen(struct socket *sock, int backlog) lock_sock(sk); - if (sock->type != SOCK_STREAM) { + if (!sock_type_connectible(sk->sk_type)) { err = -EOPNOTSUPP; goto out; } @@ -1535,11 +1561,11 @@ static void vsock_update_buffer_size(struct vsock_sock *vsk, vsk->buffer_size = val; } -static int vsock_stream_setsockopt(struct socket *sock, - int level, - int optname, - sockptr_t optval, - unsigned int optlen) +static int vsock_connectible_setsockopt(struct socket *sock, + int level, + int optname, + sockptr_t optval, + unsigned int optlen) { int err; struct sock *sk; @@ -1617,10 +1643,10 @@ exit: return err; } -static int vsock_stream_getsockopt(struct socket *sock, - int level, int optname, - char __user *optval, - int __user *optlen) +static int vsock_connectible_getsockopt(struct socket *sock, + int level, int optname, + char __user *optval, + int __user *optlen) { int err; int len; @@ -1688,8 +1714,8 @@ static int vsock_stream_getsockopt(struct socket *sock, return 0; } -static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, - size_t len) +static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk; struct vsock_sock *vsk; @@ -1712,7 +1738,9 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, transport = vsk->transport; - /* Callers should not provide a destination with stream sockets. */ + /* Callers should not provide a destination with connection oriented + * sockets. + */ if (msg->msg_namelen) { err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out; @@ -1803,9 +1831,13 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, * responsibility to check how many bytes we were able to send. */ - written = transport->stream_enqueue( - vsk, msg, - len - total_written); + if (sk->sk_type == SOCK_SEQPACKET) { + written = transport->seqpacket_enqueue(vsk, + msg, len - total_written); + } else { + written = transport->stream_enqueue(vsk, + msg, len - total_written); + } if (written < 0) { err = -ENOMEM; goto out_err; @@ -1821,26 +1853,220 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, } out_err: - if (total_written > 0) - err = total_written; + if (total_written > 0) { + /* Return number of written bytes only if: + * 1) SOCK_STREAM socket. + * 2) SOCK_SEQPACKET socket when whole buffer is sent. + */ + if (sk->sk_type == SOCK_STREAM || total_written == len) + err = total_written; + } out: release_sock(sk); return err; } +static int vsock_connectible_wait_data(struct sock *sk, + struct wait_queue_entry *wait, + long timeout, + struct vsock_transport_recv_notify_data *recv_data, + size_t target) +{ + const struct vsock_transport *transport; + struct vsock_sock *vsk; + s64 data; + int err; + + vsk = vsock_sk(sk); + err = 0; + transport = vsk->transport; + + while ((data = vsock_connectible_has_data(vsk)) == 0) { + prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); + + if (sk->sk_err != 0 || + (sk->sk_shutdown & RCV_SHUTDOWN) || + (vsk->peer_shutdown & SEND_SHUTDOWN)) { + break; + } + + /* Don't wait for non-blocking sockets. */ + if (timeout == 0) { + err = -EAGAIN; + break; + } + + if (recv_data) { + err = transport->notify_recv_pre_block(vsk, target, recv_data); + if (err < 0) + break; + } + + release_sock(sk); + timeout = schedule_timeout(timeout); + lock_sock(sk); + + if (signal_pending(current)) { + err = sock_intr_errno(timeout); + break; + } else if (timeout == 0) { + err = -EAGAIN; + break; + } + } + + finish_wait(sk_sleep(sk), wait); + + if (err) + return err; + + /* Internal transport error when checking for available + * data. XXX This should be changed to a connection + * reset in a later change. + */ + if (data < 0) + return -ENOMEM; + + return data; +} + +static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg, + size_t len, int flags) +{ + struct vsock_transport_recv_notify_data recv_data; + const struct vsock_transport *transport; + struct vsock_sock *vsk; + ssize_t copied; + size_t target; + long timeout; + int err; + + DEFINE_WAIT(wait); + + vsk = vsock_sk(sk); + transport = vsk->transport; + + /* We must not copy less than target bytes into the user's buffer + * before returning successfully, so we wait for the consume queue to + * have that much data to consume before dequeueing. Note that this + * makes it impossible to handle cases where target is greater than the + * queue size. + */ + target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + if (target >= transport->stream_rcvhiwat(vsk)) { + err = -ENOMEM; + goto out; + } + timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + copied = 0; + + err = transport->notify_recv_init(vsk, target, &recv_data); + if (err < 0) + goto out; + + + while (1) { + ssize_t read; + + err = vsock_connectible_wait_data(sk, &wait, timeout, + &recv_data, target); + if (err <= 0) + break; + + err = transport->notify_recv_pre_dequeue(vsk, target, + &recv_data); + if (err < 0) + break; + + read = transport->stream_dequeue(vsk, msg, len - copied, flags); + if (read < 0) { + err = -ENOMEM; + break; + } + + copied += read; + + err = transport->notify_recv_post_dequeue(vsk, target, read, + !(flags & MSG_PEEK), &recv_data); + if (err < 0) + goto out; + + if (read >= target || flags & MSG_PEEK) + break; + + target -= read; + } + + if (sk->sk_err) + err = -sk->sk_err; + else if (sk->sk_shutdown & RCV_SHUTDOWN) + err = 0; + + if (copied > 0) + err = copied; + +out: + return err; +} + +static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg, + size_t len, int flags) +{ + const struct vsock_transport *transport; + struct vsock_sock *vsk; + ssize_t record_len; + long timeout; + int err = 0; + DEFINE_WAIT(wait); + + vsk = vsock_sk(sk); + transport = vsk->transport; + + timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + + err = vsock_connectible_wait_data(sk, &wait, timeout, NULL, 0); + if (err <= 0) + goto out; + + record_len = transport->seqpacket_dequeue(vsk, msg, flags); + + if (record_len < 0) { + err = -ENOMEM; + goto out; + } + + if (sk->sk_err) { + err = -sk->sk_err; + } else if (sk->sk_shutdown & RCV_SHUTDOWN) { + err = 0; + } else { + /* User sets MSG_TRUNC, so return real length of + * packet. + */ + if (flags & MSG_TRUNC) + err = record_len; + else + err = len - msg_data_left(msg); + + /* Always set MSG_TRUNC if real length of packet is + * bigger than user's buffer. + */ + if (record_len > len) + msg->msg_flags |= MSG_TRUNC; + } + +out: + return err; +} static int -vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; int err; - size_t target; - ssize_t copied; - long timeout; - struct vsock_transport_recv_notify_data recv_data; DEFINE_WAIT(wait); @@ -1888,114 +2114,10 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; } - /* We must not copy less than target bytes into the user's buffer - * before returning successfully, so we wait for the consume queue to - * have that much data to consume before dequeueing. Note that this - * makes it impossible to handle cases where target is greater than the - * queue size. - */ - target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); - if (target >= transport->stream_rcvhiwat(vsk)) { - err = -ENOMEM; - goto out; - } - timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - copied = 0; - - err = transport->notify_recv_init(vsk, target, &recv_data); - if (err < 0) - goto out; - - - while (1) { - s64 ready; - - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - ready = vsock_stream_has_data(vsk); - - if (ready == 0) { - if (sk->sk_err != 0 || - (sk->sk_shutdown & RCV_SHUTDOWN) || - (vsk->peer_shutdown & SEND_SHUTDOWN)) { - finish_wait(sk_sleep(sk), &wait); - break; - } - /* Don't wait for non-blocking sockets. */ - if (timeout == 0) { - err = -EAGAIN; - finish_wait(sk_sleep(sk), &wait); - break; - } - - err = transport->notify_recv_pre_block( - vsk, target, &recv_data); - if (err < 0) { - finish_wait(sk_sleep(sk), &wait); - break; - } - release_sock(sk); - timeout = schedule_timeout(timeout); - lock_sock(sk); - - if (signal_pending(current)) { - err = sock_intr_errno(timeout); - finish_wait(sk_sleep(sk), &wait); - break; - } else if (timeout == 0) { - err = -EAGAIN; - finish_wait(sk_sleep(sk), &wait); - break; - } - } else { - ssize_t read; - - finish_wait(sk_sleep(sk), &wait); - - if (ready < 0) { - /* Invalid queue pair content. XXX This should - * be changed to a connection reset in a later - * change. - */ - - err = -ENOMEM; - goto out; - } - - err = transport->notify_recv_pre_dequeue( - vsk, target, &recv_data); - if (err < 0) - break; - - read = transport->stream_dequeue( - vsk, msg, - len - copied, flags); - if (read < 0) { - err = -ENOMEM; - break; - } - - copied += read; - - err = transport->notify_recv_post_dequeue( - vsk, target, read, - !(flags & MSG_PEEK), &recv_data); - if (err < 0) - goto out; - - if (read >= target || flags & MSG_PEEK) - break; - - target -= read; - } - } - - if (sk->sk_err) - err = -sk->sk_err; - else if (sk->sk_shutdown & RCV_SHUTDOWN) - err = 0; - - if (copied > 0) - err = copied; + if (sk->sk_type == SOCK_STREAM) + err = __vsock_stream_recvmsg(sk, msg, len, flags); + else + err = __vsock_seqpacket_recvmsg(sk, msg, len, flags); out: release_sock(sk); @@ -2007,7 +2129,7 @@ static const struct proto_ops vsock_stream_ops = { .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, - .connect = vsock_stream_connect, + .connect = vsock_connect, .socketpair = sock_no_socketpair, .accept = vsock_accept, .getname = vsock_getname, @@ -2015,10 +2137,31 @@ static const struct proto_ops vsock_stream_ops = { .ioctl = sock_no_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, - .setsockopt = vsock_stream_setsockopt, - .getsockopt = vsock_stream_getsockopt, - .sendmsg = vsock_stream_sendmsg, - .recvmsg = vsock_stream_recvmsg, + .setsockopt = vsock_connectible_setsockopt, + .getsockopt = vsock_connectible_getsockopt, + .sendmsg = vsock_connectible_sendmsg, + .recvmsg = vsock_connectible_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + +static const struct proto_ops vsock_seqpacket_ops = { + .family = PF_VSOCK, + .owner = THIS_MODULE, + .release = vsock_release, + .bind = vsock_bind, + .connect = vsock_connect, + .socketpair = sock_no_socketpair, + .accept = vsock_accept, + .getname = vsock_getname, + .poll = vsock_poll, + .ioctl = sock_no_ioctl, + .listen = vsock_listen, + .shutdown = vsock_shutdown, + .setsockopt = vsock_connectible_setsockopt, + .getsockopt = vsock_connectible_getsockopt, + .sendmsg = vsock_connectible_sendmsg, + .recvmsg = vsock_connectible_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; @@ -2043,6 +2186,9 @@ static int vsock_create(struct net *net, struct socket *sock, case SOCK_STREAM: sock->ops = &vsock_stream_ops; break; + case SOCK_SEQPACKET: + sock->ops = &vsock_seqpacket_ops; + break; default: return -ESOCKTNOSUPPORT; } diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index cc3bae2659e7..19189cf30a72 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -596,7 +596,7 @@ static ssize_t hvs_stream_dequeue(struct vsock_sock *vsk, struct msghdr *msg, return -EOPNOTSUPP; if (need_refill) { - hvs->recv_desc = hv_pkt_iter_first(hvs->chan); + hvs->recv_desc = hv_pkt_iter_first_raw(hvs->chan); ret = hvs_update_recv_data(hvs); if (ret) return ret; @@ -610,7 +610,7 @@ static ssize_t hvs_stream_dequeue(struct vsock_sock *vsk, struct msghdr *msg, hvs->recv_data_len -= to_read; if (hvs->recv_data_len == 0) { - hvs->recv_desc = hv_pkt_iter_next(hvs->chan, hvs->recv_desc); + hvs->recv_desc = hv_pkt_iter_next_raw(hvs->chan, hvs->recv_desc); if (hvs->recv_desc) { ret = hvs_update_recv_data(hvs); if (ret) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 2700a63ab095..e0c2c992ad9c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -62,6 +62,7 @@ struct virtio_vsock { struct virtio_vsock_event event_list[8]; u32 guest_cid; + bool seqpacket_allow; }; static u32 virtio_transport_get_local_cid(void) @@ -359,7 +360,7 @@ static void virtio_vsock_reset_sock(struct sock *sk) lock_sock(sk); sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; - sk->sk_error_report(sk); + sk_error_report(sk); release_sock(sk); } @@ -443,6 +444,8 @@ static void virtio_vsock_rx_done(struct virtqueue *vq) queue_work(virtio_vsock_workqueue, &vsock->rx_work); } +static bool virtio_transport_seqpacket_allow(u32 remote_cid); + static struct virtio_transport virtio_transport = { .transport = { .module = THIS_MODULE, @@ -469,6 +472,11 @@ static struct virtio_transport virtio_transport = { .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, + .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, + .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, + .seqpacket_allow = virtio_transport_seqpacket_allow, + .seqpacket_has_data = virtio_transport_seqpacket_has_data, + .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, @@ -485,6 +493,21 @@ static struct virtio_transport virtio_transport = { .send_pkt = virtio_transport_send_pkt, }; +static bool virtio_transport_seqpacket_allow(u32 remote_cid) +{ + struct virtio_vsock *vsock; + bool seqpacket_allow; + + seqpacket_allow = false; + rcu_read_lock(); + vsock = rcu_dereference(the_virtio_vsock); + if (vsock) + seqpacket_allow = vsock->seqpacket_allow; + rcu_read_unlock(); + + return seqpacket_allow; +} + static void virtio_transport_rx_work(struct work_struct *work) { struct virtio_vsock *vsock = @@ -608,10 +631,14 @@ static int virtio_vsock_probe(struct virtio_device *vdev) vsock->event_run = true; mutex_unlock(&vsock->event_lock); + if (virtio_has_feature(vdev, VIRTIO_VSOCK_F_SEQPACKET)) + vsock->seqpacket_allow = true; + vdev->priv = vsock; rcu_assign_pointer(the_virtio_vsock, vsock); mutex_unlock(&the_virtio_vsock_mutex); + return 0; out: @@ -695,6 +722,7 @@ static struct virtio_device_id id_table[] = { }; static unsigned int features[] = { + VIRTIO_VSOCK_F_SEQPACKET }; static struct virtio_driver virtio_vsock_driver = { diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index ce404104a212..a268a3892146 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -78,6 +78,10 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, err = memcpy_from_msg(pkt->buf, info->msg, len); if (err) goto out; + + if (msg_data_left(info->msg) == 0 && + info->type == VIRTIO_VSOCK_TYPE_SEQPACKET) + pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); } trace_virtio_transport_alloc_pkt(src_cid, src_port, @@ -169,6 +173,14 @@ void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); +static u16 virtio_transport_get_type(struct sock *sk) +{ + if (sk->sk_type == SOCK_STREAM) + return VIRTIO_VSOCK_TYPE_STREAM; + else + return VIRTIO_VSOCK_TYPE_SEQPACKET; +} + /* This function can only be used on connecting/connected sockets, * since a socket assigned to a transport is required. * @@ -183,6 +195,8 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; + info->type = virtio_transport_get_type(sk_vsock(vsk)); + t_ops = virtio_transport_get_ops(vsk); if (unlikely(!t_ops)) return -EFAULT; @@ -273,13 +287,10 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) } EXPORT_SYMBOL_GPL(virtio_transport_put_credit); -static int virtio_transport_send_credit_update(struct vsock_sock *vsk, - int type, - struct virtio_vsock_hdr *hdr) +static int virtio_transport_send_credit_update(struct vsock_sock *vsk) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, - .type = type, .vsk = vsk, }; @@ -387,11 +398,8 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, * messages, we set the limit to a high value. TODO: experiment * with different values. */ - if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) { - virtio_transport_send_credit_update(vsk, - VIRTIO_VSOCK_TYPE_STREAM, - NULL); - } + if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) + virtio_transport_send_credit_update(vsk); return total; @@ -401,6 +409,75 @@ out: return err; } +static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + struct virtio_vsock_pkt *pkt; + int dequeued_len = 0; + size_t user_buf_len = msg_data_left(msg); + bool msg_ready = false; + + spin_lock_bh(&vvs->rx_lock); + + if (vvs->msg_count == 0) { + spin_unlock_bh(&vvs->rx_lock); + return 0; + } + + while (!msg_ready) { + pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list); + + if (dequeued_len >= 0) { + size_t pkt_len; + size_t bytes_to_copy; + + pkt_len = (size_t)le32_to_cpu(pkt->hdr.len); + bytes_to_copy = min(user_buf_len, pkt_len); + + if (bytes_to_copy) { + int err; + + /* sk_lock is held by caller so no one else can dequeue. + * Unlock rx_lock since memcpy_to_msg() may sleep. + */ + spin_unlock_bh(&vvs->rx_lock); + + err = memcpy_to_msg(msg, pkt->buf, bytes_to_copy); + if (err) { + /* Copy of message failed. Rest of + * fragments will be freed without copy. + */ + dequeued_len = err; + } else { + user_buf_len -= bytes_to_copy; + } + + spin_lock_bh(&vvs->rx_lock); + } + + if (dequeued_len >= 0) + dequeued_len += pkt_len; + } + + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) { + msg_ready = true; + vvs->msg_count--; + } + + virtio_transport_dec_rx_pkt(vvs, pkt); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + + spin_unlock_bh(&vvs->rx_lock); + + virtio_transport_send_credit_update(vsk); + + return dequeued_len; +} + ssize_t virtio_transport_stream_dequeue(struct vsock_sock *vsk, struct msghdr *msg, @@ -413,6 +490,38 @@ virtio_transport_stream_dequeue(struct vsock_sock *vsk, } EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue); +ssize_t +virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags) +{ + if (flags & MSG_PEEK) + return -EOPNOTSUPP; + + return virtio_transport_seqpacket_do_dequeue(vsk, msg, flags); +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue); + +int +virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + spin_lock_bh(&vvs->tx_lock); + + if (len > vvs->peer_buf_alloc) { + spin_unlock_bh(&vvs->tx_lock); + return -EMSGSIZE; + } + + spin_unlock_bh(&vvs->tx_lock); + + return virtio_transport_stream_enqueue(vsk, msg, len); +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_enqueue); + int virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, @@ -435,6 +544,19 @@ s64 virtio_transport_stream_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data); +u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + u32 msg_count; + + spin_lock_bh(&vvs->rx_lock); + msg_count = vvs->msg_count; + spin_unlock_bh(&vvs->rx_lock); + + return msg_count; +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_has_data); + static s64 virtio_transport_has_space(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; @@ -500,8 +622,7 @@ void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val) vvs->buf_alloc = *val; - virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, - NULL); + virtio_transport_send_credit_update(vsk); } EXPORT_SYMBOL_GPL(virtio_transport_notify_buffer_size); @@ -628,7 +749,6 @@ int virtio_transport_connect(struct vsock_sock *vsk) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_REQUEST, - .type = VIRTIO_VSOCK_TYPE_STREAM, .vsk = vsk, }; @@ -640,7 +760,6 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_SHUTDOWN, - .type = VIRTIO_VSOCK_TYPE_STREAM, .flags = (mode & RCV_SHUTDOWN ? VIRTIO_VSOCK_SHUTDOWN_RCV : 0) | (mode & SEND_SHUTDOWN ? @@ -669,7 +788,6 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk, { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RW, - .type = VIRTIO_VSOCK_TYPE_STREAM, .msg = msg, .pkt_len = len, .vsk = vsk, @@ -692,7 +810,6 @@ static int virtio_transport_reset(struct vsock_sock *vsk, { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, - .type = VIRTIO_VSOCK_TYPE_STREAM, .reply = !!pkt, .vsk = vsk, }; @@ -852,7 +969,7 @@ void virtio_transport_release(struct vsock_sock *vsk) struct sock *sk = &vsk->sk; bool remove_sock = true; - if (sk->sk_type == SOCK_STREAM) + if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) remove_sock = virtio_transport_close(vsk); if (remove_sock) { @@ -894,7 +1011,7 @@ destroy: virtio_transport_reset(vsk, pkt); sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; - sk->sk_error_report(sk); + sk_error_report(sk); return err; } @@ -916,6 +1033,9 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, goto out; } + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) + vvs->msg_count++; + /* Try to copy small packets into the buffer of last packet queued, * to avoid wasting memory queueing the entire buffer with a small * payload. @@ -927,13 +1047,18 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, struct virtio_vsock_pkt, list); /* If there is space in the last packet queued, we copy the - * new packet in its buffer. + * new packet in its buffer. We avoid this if the last packet + * queued has VIRTIO_VSOCK_SEQ_EOR set, because this is + * delimiter of SEQPACKET record, so 'pkt' is the first packet + * of a new record. */ - if (pkt->len <= last_pkt->buf_len - last_pkt->len) { + if ((pkt->len <= last_pkt->buf_len - last_pkt->len) && + !(le32_to_cpu(last_pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR)) { memcpy(last_pkt->buf + last_pkt->len, pkt->buf, pkt->len); last_pkt->len += pkt->len; free_pkt = true; + last_pkt->hdr.flags |= pkt->hdr.flags; goto out; } } @@ -1004,7 +1129,6 @@ virtio_transport_send_response(struct vsock_sock *vsk, { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RESPONSE, - .type = VIRTIO_VSOCK_TYPE_STREAM, .remote_cid = le64_to_cpu(pkt->hdr.src_cid), .remote_port = le32_to_cpu(pkt->hdr.src_port), .reply = true, @@ -1100,6 +1224,12 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, return 0; } +static bool virtio_transport_valid_type(u16 type) +{ + return (type == VIRTIO_VSOCK_TYPE_STREAM) || + (type == VIRTIO_VSOCK_TYPE_SEQPACKET); +} + /* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex * lock. */ @@ -1125,7 +1255,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, le32_to_cpu(pkt->hdr.buf_alloc), le32_to_cpu(pkt->hdr.fwd_cnt)); - if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) { + if (!virtio_transport_valid_type(le16_to_cpu(pkt->hdr.type))) { (void)virtio_transport_reset_no_sock(t, pkt); goto free_pkt; } @@ -1142,6 +1272,12 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, } } + if (virtio_transport_get_type(sk) != le16_to_cpu(pkt->hdr.type)) { + (void)virtio_transport_reset_no_sock(t, pkt); + sock_put(sk); + goto free_pkt; + } + vsk = vsock_sk(sk); lock_sock(sk); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index c99bc4ce78e2..7aef34e32bdf 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -831,7 +831,7 @@ static void vmci_transport_handle_detach(struct sock *sk) sk->sk_state = TCP_CLOSE; sk->sk_err = ECONNRESET; - sk->sk_error_report(sk); + sk_error_report(sk); return; } sk->sk_state = TCP_CLOSE; @@ -1248,7 +1248,7 @@ vmci_transport_recv_connecting_server(struct sock *listener, vsock_remove_pending(listener, pending); vsock_enqueue_accept(listener, pending); - /* Callers of accept() will be be waiting on the listening socket, not + /* Callers of accept() will be waiting on the listening socket, not * the pending socket. */ listener->sk_data_ready(listener); @@ -1365,7 +1365,7 @@ destroy: sk->sk_state = TCP_CLOSE; sk->sk_err = skerr; - sk->sk_error_report(sk); + sk_error_report(sk); return err; } diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index a45f7ffca8c5..169a8cf65b39 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -63,6 +63,8 @@ static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk) return 0; } +static bool vsock_loopback_seqpacket_allow(u32 remote_cid); + static struct virtio_transport loopback_transport = { .transport = { .module = THIS_MODULE, @@ -89,6 +91,11 @@ static struct virtio_transport loopback_transport = { .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, + .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, + .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, + .seqpacket_allow = vsock_loopback_seqpacket_allow, + .seqpacket_has_data = virtio_transport_seqpacket_has_data, + .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, @@ -105,6 +112,11 @@ static struct virtio_transport loopback_transport = { .send_pkt = vsock_loopback_send_pkt, }; +static bool vsock_loopback_seqpacket_allow(u32 remote_cid) +{ + return true; +} + static void vsock_loopback_work(struct work_struct *work) { struct vsock_loopback *vsock = diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 285b8076054b..869c43d4414c 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -6,7 +6,7 @@ * * Copyright 2009 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright 2018-2020 Intel Corporation + * Copyright 2018-2021 Intel Corporation */ #include @@ -942,7 +942,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, struct ieee80211_sta_vht_cap *vht_cap; struct ieee80211_edmg *edmg_cap; u32 width, control_freq, cap; - bool support_80_80 = false; + bool ext_nss_cap, support_80_80 = false; if (WARN_ON(!cfg80211_chandef_valid(chandef))) return false; @@ -950,6 +950,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, ht_cap = &wiphy->bands[chandef->chan->band]->ht_cap; vht_cap = &wiphy->bands[chandef->chan->band]->vht_cap; edmg_cap = &wiphy->bands[chandef->chan->band]->edmg_cap; + ext_nss_cap = __le16_to_cpu(vht_cap->vht_mcs.tx_highest) & + IEEE80211_VHT_EXT_NSS_BW_CAPABLE; if (edmg_cap->channels && !cfg80211_edmg_usable(wiphy, @@ -1015,7 +1017,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, (cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) || (cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) || - u32_get_bits(cap, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) > 1; + (ext_nss_cap && + u32_get_bits(cap, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) > 1); if (chandef->chan->band != NL80211_BAND_6GHZ && !support_80_80) return false; fallthrough; @@ -1037,7 +1040,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ && - !(vht_cap->cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK)) + !(ext_nss_cap && + (vht_cap->cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK))) return false; break; default: @@ -1335,3 +1339,34 @@ cfg80211_get_chan_state(struct wireless_dev *wdev, WARN_ON(1); } } + +bool cfg80211_any_usable_channels(struct wiphy *wiphy, + unsigned long sband_mask, + u32 prohibited_flags) +{ + int idx; + + prohibited_flags |= IEEE80211_CHAN_DISABLED; + + for_each_set_bit(idx, &sband_mask, NUM_NL80211_BANDS) { + struct ieee80211_supported_band *sband = wiphy->bands[idx]; + int chanidx; + + if (!sband) + continue; + + for (chanidx = 0; chanidx < sband->n_channels; chanidx++) { + struct ieee80211_channel *chan; + + chan = &sband->channels[chanidx]; + + if (chan->flags & prohibited_flags) + continue; + + return true; + } + } + + return false; +} +EXPORT_SYMBOL(cfg80211_any_usable_channels); diff --git a/net/wireless/core.c b/net/wireless/core.c index 8d0883e81093..03323121ca50 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -5,7 +5,7 @@ * Copyright 2006-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -532,11 +532,11 @@ use_default_name: wiphy_net_set(&rdev->wiphy, &init_net); rdev->rfkill_ops.set_block = cfg80211_rfkill_set_block; - rdev->rfkill = rfkill_alloc(dev_name(&rdev->wiphy.dev), - &rdev->wiphy.dev, RFKILL_TYPE_WLAN, - &rdev->rfkill_ops, rdev); + rdev->wiphy.rfkill = rfkill_alloc(dev_name(&rdev->wiphy.dev), + &rdev->wiphy.dev, RFKILL_TYPE_WLAN, + &rdev->rfkill_ops, rdev); - if (!rdev->rfkill) { + if (!rdev->wiphy.rfkill) { wiphy_free(&rdev->wiphy); return NULL; } @@ -589,14 +589,6 @@ static int wiphy_verify_combinations(struct wiphy *wiphy) if (WARN_ON(!c->num_different_channels)) return -EINVAL; - /* - * Put a sane limit on maximum number of different - * channels to simplify channel accounting code. - */ - if (WARN_ON(c->num_different_channels > - CFG80211_MAX_NUM_DIFFERENT_CHANNELS)) - return -EINVAL; - /* DFS only works on one channel. */ if (WARN_ON(c->radar_detect_widths && (c->num_different_channels > 1))) @@ -936,9 +928,6 @@ int wiphy_register(struct wiphy *wiphy) return res; } - /* set up regulatory info */ - wiphy_regulatory_register(wiphy); - list_add_rcu(&rdev->list, &cfg80211_rdev_list); cfg80211_rdev_list_generation++; @@ -949,6 +938,9 @@ int wiphy_register(struct wiphy *wiphy) cfg80211_debugfs_rdev_add(rdev); nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY); + /* set up regulatory info */ + wiphy_regulatory_register(wiphy); + if (wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) { struct regulatory_request request; @@ -993,10 +985,10 @@ int wiphy_register(struct wiphy *wiphy) rdev->wiphy.registered = true; rtnl_unlock(); - res = rfkill_register(rdev->rfkill); + res = rfkill_register(rdev->wiphy.rfkill); if (res) { - rfkill_destroy(rdev->rfkill); - rdev->rfkill = NULL; + rfkill_destroy(rdev->wiphy.rfkill); + rdev->wiphy.rfkill = NULL; wiphy_unregister(&rdev->wiphy); return res; } @@ -1012,18 +1004,10 @@ void wiphy_rfkill_start_polling(struct wiphy *wiphy) if (!rdev->ops->rfkill_poll) return; rdev->rfkill_ops.poll = cfg80211_rfkill_poll; - rfkill_resume_polling(rdev->rfkill); + rfkill_resume_polling(wiphy->rfkill); } EXPORT_SYMBOL(wiphy_rfkill_start_polling); -void wiphy_rfkill_stop_polling(struct wiphy *wiphy) -{ - struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - - rfkill_pause_polling(rdev->rfkill); -} -EXPORT_SYMBOL(wiphy_rfkill_stop_polling); - void wiphy_unregister(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); @@ -1035,8 +1019,8 @@ void wiphy_unregister(struct wiphy *wiphy) wiphy_unlock(&rdev->wiphy); __count == 0; })); - if (rdev->rfkill) - rfkill_unregister(rdev->rfkill); + if (rdev->wiphy.rfkill) + rfkill_unregister(rdev->wiphy.rfkill); rtnl_lock(); wiphy_lock(&rdev->wiphy); @@ -1088,7 +1072,7 @@ void cfg80211_dev_free(struct cfg80211_registered_device *rdev) { struct cfg80211_internal_bss *scan, *tmp; struct cfg80211_beacon_registration *reg, *treg; - rfkill_destroy(rdev->rfkill); + rfkill_destroy(rdev->wiphy.rfkill); list_for_each_entry_safe(reg, treg, &rdev->beacon_registrations, list) { list_del(®->list); kfree(reg); @@ -1110,7 +1094,7 @@ void wiphy_rfkill_set_hw_state_reason(struct wiphy *wiphy, bool blocked, { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - if (rfkill_set_hw_state_reason(rdev->rfkill, blocked, reason)) + if (rfkill_set_hw_state_reason(wiphy->rfkill, blocked, reason)) schedule_work(&rdev->rfkill_block); } EXPORT_SYMBOL(wiphy_rfkill_set_hw_state_reason); @@ -1503,7 +1487,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, wdev->use_4addr, 0)) return notifier_from_errno(-EOPNOTSUPP); - if (rfkill_blocked(rdev->rfkill)) + if (rfkill_blocked(rdev->wiphy.rfkill)) return notifier_from_errno(-ERFKILL); break; default: diff --git a/net/wireless/core.h b/net/wireless/core.h index a7d19b4b40ac..b35d0db12f1d 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -3,7 +3,7 @@ * Wireless configuration interface internals. * * Copyright 2006-2010 Johannes Berg - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #ifndef __NET_WIRELESS_CORE_H #define __NET_WIRELESS_CORE_H @@ -27,7 +27,6 @@ struct cfg80211_registered_device { /* rfkill support */ struct rfkill_ops rfkill_ops; - struct rfkill *rfkill; struct work_struct rfkill_block; /* ISO / IEC 3166 alpha2 for which this device is receiving diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fc9286afe3c9..50eb405b0690 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -330,7 +330,7 @@ nl80211_pmsr_req_attr_policy[NL80211_PMSR_REQ_ATTR_MAX + 1] = { }; static const struct nla_policy -nl80211_psmr_peer_attr_policy[NL80211_PMSR_PEER_ATTR_MAX + 1] = { +nl80211_pmsr_peer_attr_policy[NL80211_PMSR_PEER_ATTR_MAX + 1] = { [NL80211_PMSR_PEER_ATTR_ADDR] = NLA_POLICY_ETH_ADDR, [NL80211_PMSR_PEER_ATTR_CHAN] = NLA_POLICY_NESTED(nl80211_policy), [NL80211_PMSR_PEER_ATTR_REQ] = @@ -345,7 +345,7 @@ nl80211_pmsr_attr_policy[NL80211_PMSR_ATTR_MAX + 1] = { [NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_TYPE_CAPA] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_PEERS] = - NLA_POLICY_NESTED_ARRAY(nl80211_psmr_peer_attr_policy), + NLA_POLICY_NESTED_ARRAY(nl80211_pmsr_peer_attr_policy), }; static const struct nla_policy @@ -1731,6 +1731,11 @@ nl80211_send_iftype_data(struct sk_buff *msg, &iftdata->he_6ghz_capa)) return -ENOBUFS; + if (iftdata->vendor_elems.data && iftdata->vendor_elems.len && + nla_put(msg, NL80211_BAND_IFTYPE_ATTR_VENDOR_ELEMS, + iftdata->vendor_elems.len, iftdata->vendor_elems.data)) + return -ENOBUFS; + return 0; } @@ -4781,11 +4786,10 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info, sband->ht_cap.mcs.rx_mask, sizeof(mask->control[i].ht_mcs)); - if (!sband->vht_cap.vht_supported) - continue; - - vht_tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map); - vht_build_mcs_mask(vht_tx_mcs_map, mask->control[i].vht_mcs); + if (sband->vht_cap.vht_supported) { + vht_tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map); + vht_build_mcs_mask(vht_tx_mcs_map, mask->control[i].vht_mcs); + } he_cap = ieee80211_get_he_iftype_cap(sband, wdev->iftype); if (!he_cap) @@ -13042,7 +13046,7 @@ static int nl80211_start_p2p_device(struct sk_buff *skb, struct genl_info *info) if (wdev_running(wdev)) return 0; - if (rfkill_blocked(rdev->rfkill)) + if (rfkill_blocked(rdev->wiphy.rfkill)) return -ERFKILL; err = rdev_start_p2p_device(rdev, wdev); @@ -13084,7 +13088,7 @@ static int nl80211_start_nan(struct sk_buff *skb, struct genl_info *info) if (wdev_running(wdev)) return -EEXIST; - if (rfkill_blocked(rdev->rfkill)) + if (rfkill_blocked(rdev->wiphy.rfkill)) return -ERFKILL; if (!info->attrs[NL80211_ATTR_NAN_MASTER_PREF]) diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index d245968b74cb..328cf54bda82 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -168,6 +168,18 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, return -EINVAL; } + if (tb[NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR]) { + if (!out->ftm.non_trigger_based && !out->ftm.trigger_based) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR], + "FTM: BSS color set for EDCA based ranging"); + return -EINVAL; + } + + out->ftm.bss_color = + nla_get_u8(tb[NL80211_PMSR_FTM_REQ_ATTR_BSS_COLOR]); + } + return 0; } diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 8b1358d04ca2..b1d37f582dc6 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -464,8 +464,18 @@ static inline int rdev_assoc(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_assoc_request *req) { + const struct cfg80211_bss_ies *bss_ies; int ret; - trace_rdev_assoc(&rdev->wiphy, dev, req); + + /* + * Note: we might trace not exactly the data that's processed, + * due to races and the driver/mac80211 getting a newer copy. + */ + rcu_read_lock(); + bss_ies = rcu_dereference(req->bss->ies); + trace_rdev_assoc(&rdev->wiphy, dev, req, bss_ies); + rcu_read_unlock(); + ret = rdev->ops->assoc(&rdev->wiphy, dev, req); trace_rdev_return_int(&rdev->wiphy, ret); return ret; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 0406ce7334fa..c2d0ff7f089f 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -3975,7 +3975,9 @@ static int __regulatory_set_wiphy_regd(struct wiphy *wiphy, "wiphy should have REGULATORY_WIPHY_SELF_MANAGED\n")) return -EPERM; - if (WARN(!is_valid_rd(rd), "Invalid regulatory domain detected\n")) { + if (WARN(!is_valid_rd(rd), + "Invalid regulatory domain detected: %c%c\n", + rd->alpha2[0], rd->alpha2[1])) { print_regdomain_info(rd); return -EINVAL; } @@ -4049,6 +4051,7 @@ void wiphy_regulatory_register(struct wiphy *wiphy) wiphy_update_regulatory(wiphy, lr->initiator); wiphy_all_share_dfs_chan_state(wiphy); + reg_process_self_managed_hints(); } void wiphy_regulatory_deregister(struct wiphy *wiphy) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 4f06c1825029..f03c7ac8e184 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -5,7 +5,7 @@ * Copyright 2008 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include #include @@ -618,7 +618,7 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, freq = ieee80211_channel_to_frequency(ap_info->channel, band); - if (end - pos < count * ap_info->tbtt_info_len) + if (end - pos < count * length) break; /* @@ -630,7 +630,7 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, if (band != NL80211_BAND_6GHZ || (length != IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM && length < IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM)) { - pos += count * ap_info->tbtt_info_len; + pos += count * length; continue; } @@ -653,7 +653,7 @@ static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies, kfree(entry); } - pos += ap_info->tbtt_info_len; + pos += length; } } @@ -757,7 +757,8 @@ static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev) } request = kzalloc(struct_size(request, channels, n_channels) + - sizeof(*request->scan_6ghz_params) * count, + sizeof(*request->scan_6ghz_params) * count + + sizeof(*request->ssids) * rdev_req->n_ssids, GFP_KERNEL); if (!request) { cfg80211_free_coloc_ap_list(&coloc_ap_list); @@ -848,9 +849,18 @@ skip: if (request->n_channels) { struct cfg80211_scan_request *old = rdev->int_scan_req; - rdev->int_scan_req = request; + /* + * Add the ssids from the parent scan request to the new scan + * request, so the driver would be able to use them in its + * probe requests to discover hidden APs on PSC channels. + */ + request->ssids = (void *)&request->channels[request->n_channels]; + request->n_ssids = rdev_req->n_ssids; + memcpy(request->ssids, rdev_req->ssids, sizeof(*request->ssids) * + request->n_ssids); + /* * If this scan follows a previous scan, save the scan start * info from the first part of the scan diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 76b777d5903f..440bce5f0274 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -1195,8 +1195,9 @@ TRACE_EVENT(rdev_auth, TRACE_EVENT(rdev_assoc, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, - struct cfg80211_assoc_request *req), - TP_ARGS(wiphy, netdev, req), + struct cfg80211_assoc_request *req, + const struct cfg80211_bss_ies *bss_ies), + TP_ARGS(wiphy, netdev, req, bss_ies), TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY @@ -1204,6 +1205,17 @@ TRACE_EVENT(rdev_assoc, MAC_ENTRY(prev_bssid) __field(bool, use_mfp) __field(u32, flags) + __dynamic_array(u8, bss_elements, bss_ies->len) + __field(bool, bss_elements_bcon) + __field(u64, bss_elements_tsf) + __dynamic_array(u8, elements, req->ie_len) + __array(u8, ht_capa, sizeof(struct ieee80211_ht_cap)) + __array(u8, ht_capa_mask, sizeof(struct ieee80211_ht_cap)) + __array(u8, vht_capa, sizeof(struct ieee80211_vht_cap)) + __array(u8, vht_capa_mask, sizeof(struct ieee80211_vht_cap)) + __dynamic_array(u8, fils_kek, req->fils_kek_len) + __dynamic_array(u8, fils_nonces, + req->fils_nonces ? 2 * FILS_NONCE_LEN : 0) ), TP_fast_assign( WIPHY_ASSIGN; @@ -1215,6 +1227,26 @@ TRACE_EVENT(rdev_assoc, MAC_ASSIGN(prev_bssid, req->prev_bssid); __entry->use_mfp = req->use_mfp; __entry->flags = req->flags; + if (bss_ies->len) + memcpy(__get_dynamic_array(bss_elements), + bss_ies->data, bss_ies->len); + __entry->bss_elements_bcon = bss_ies->from_beacon; + __entry->bss_elements_tsf = bss_ies->tsf; + if (req->ie) + memcpy(__get_dynamic_array(elements), + req->ie, req->ie_len); + memcpy(__entry->ht_capa, &req->ht_capa, sizeof(req->ht_capa)); + memcpy(__entry->ht_capa_mask, &req->ht_capa_mask, + sizeof(req->ht_capa_mask)); + memcpy(__entry->vht_capa, &req->vht_capa, sizeof(req->vht_capa)); + memcpy(__entry->vht_capa_mask, &req->vht_capa_mask, + sizeof(req->vht_capa_mask)); + if (req->fils_kek) + memcpy(__get_dynamic_array(fils_kek), + req->fils_kek, req->fils_kek_len); + if (req->fils_nonces) + memcpy(__get_dynamic_array(fils_nonces), + req->fils_nonces, 2 * FILS_NONCE_LEN); ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: " MAC_PR_FMT ", previous bssid: " MAC_PR_FMT ", use mfp: %s, flags: %u", diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index a8320dc59af7..a32065d600a1 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -902,7 +902,7 @@ static int cfg80211_wext_siwtxpower(struct net_device *dev, /* only change when not disabling */ if (!data->txpower.disabled) { - rfkill_set_sw_state(rdev->rfkill, false); + rfkill_set_sw_state(rdev->wiphy.rfkill, false); if (data->txpower.fixed) { /* @@ -927,7 +927,7 @@ static int cfg80211_wext_siwtxpower(struct net_device *dev, } } } else { - if (rfkill_set_sw_state(rdev->rfkill, true)) + if (rfkill_set_sw_state(rdev->wiphy.rfkill, true)) schedule_work(&rdev->rfkill_block); return 0; } @@ -963,7 +963,7 @@ static int cfg80211_wext_giwtxpower(struct net_device *dev, /* well... oh well */ data->txpower.fixed = 1; - data->txpower.disabled = rfkill_blocked(rdev->rfkill); + data->txpower.disabled = rfkill_blocked(rdev->wiphy.rfkill); data->txpower.value = val; data->txpower.flags = IW_TXPOW_DBM; @@ -1167,7 +1167,7 @@ static int cfg80211_wext_siwpower(struct net_device *dev, { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); - bool ps = wdev->ps; + bool ps; int timeout = wdev->ps_timeout; int err; diff --git a/net/wireless/wext-spy.c b/net/wireless/wext-spy.c index 33bef22e44e9..b379a0371653 100644 --- a/net/wireless/wext-spy.c +++ b/net/wireless/wext-spy.c @@ -120,8 +120,8 @@ int iw_handler_set_thrspy(struct net_device * dev, return -EOPNOTSUPP; /* Just do it */ - memcpy(&(spydata->spy_thr_low), &(threshold->low), - 2 * sizeof(struct iw_quality)); + spydata->spy_thr_low = threshold->low; + spydata->spy_thr_high = threshold->high; /* Clear flag */ memset(spydata->spy_thr_under, '\0', sizeof(spydata->spy_thr_under)); @@ -147,8 +147,8 @@ int iw_handler_get_thrspy(struct net_device * dev, return -EOPNOTSUPP; /* Just do it */ - memcpy(&(threshold->low), &(spydata->spy_thr_low), - 2 * sizeof(struct iw_quality)); + threshold->low = spydata->spy_thr_low; + threshold->high = spydata->spy_thr_high; return 0; } @@ -173,10 +173,10 @@ static void iw_send_thrspy_event(struct net_device * dev, memcpy(threshold.addr.sa_data, address, ETH_ALEN); threshold.addr.sa_family = ARPHRD_ETHER; /* Copy stats */ - memcpy(&(threshold.qual), wstats, sizeof(struct iw_quality)); + threshold.qual = *wstats; /* Copy also thresholds */ - memcpy(&(threshold.low), &(spydata->spy_thr_low), - 2 * sizeof(struct iw_quality)); + threshold.low = spydata->spy_thr_low; + threshold.high = spydata->spy_thr_high; /* Send event to user space */ wireless_send_event(dev, SIOCGIWTHRSPY, &wrqu, (char *) &threshold); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 1816899499ce..3583354a7d7f 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -366,7 +366,7 @@ static void x25_destroy_timer(struct timer_list *t) /* * This is called from user mode and the timers. Thus it protects itself - * against interrupt users but doesn't worry about being called during + * against interrupting users but doesn't worry about being called during * work. Once it is removed from the queue no interrupt or bottom half * will touch it and we are (fairly 8-) ) safe. * Not static as it's used by the timer diff --git a/net/x25/x25_forward.c b/net/x25/x25_forward.c index d48ad6d29197..21b30b56e889 100644 --- a/net/x25/x25_forward.c +++ b/net/x25/x25_forward.c @@ -19,7 +19,6 @@ int x25_forward_call(struct x25_address *dest_addr, struct x25_neigh *from, { struct x25_route *rt; struct x25_neigh *neigh_new = NULL; - struct list_head *entry; struct x25_forward *x25_frwd, *new_frwd; struct sk_buff *skbn; short same_lci = 0; @@ -46,8 +45,7 @@ int x25_forward_call(struct x25_address *dest_addr, struct x25_neigh *from, * established LCI? It shouldn't happen, just in case.. */ read_lock_bh(&x25_forward_list_lock); - list_for_each(entry, &x25_forward_list) { - x25_frwd = list_entry(entry, struct x25_forward, node); + list_for_each_entry(x25_frwd, &x25_forward_list, node) { if (x25_frwd->lci == lci) { pr_warn("call request for lci which is already registered!, transmitting but not registering new pair\n"); same_lci = 1; @@ -92,15 +90,13 @@ out_no_route: int x25_forward_data(int lci, struct x25_neigh *from, struct sk_buff *skb) { struct x25_forward *frwd; - struct list_head *entry; struct net_device *peer = NULL; struct x25_neigh *nb; struct sk_buff *skbn; int rc = 0; read_lock_bh(&x25_forward_list_lock); - list_for_each(entry, &x25_forward_list) { - frwd = list_entry(entry, struct x25_forward, node); + list_for_each_entry(frwd, &x25_forward_list, node) { if (frwd->lci == lci) { /* The call is established, either side can send */ if (from->dev == frwd->dev1) { diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index 57a81100c5da..5460b9146dd8 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -332,12 +332,9 @@ void x25_link_device_down(struct net_device *dev) struct x25_neigh *x25_get_neigh(struct net_device *dev) { struct x25_neigh *nb, *use = NULL; - struct list_head *entry; read_lock_bh(&x25_neigh_list_lock); - list_for_each(entry, &x25_neigh_list) { - nb = list_entry(entry, struct x25_neigh, node); - + list_for_each_entry(nb, &x25_neigh_list, node) { if (nb->dev == dev) { use = nb; break; diff --git a/net/x25/x25_route.c b/net/x25/x25_route.c index 9fbe4bb38d94..647f325ed867 100644 --- a/net/x25/x25_route.c +++ b/net/x25/x25_route.c @@ -27,14 +27,11 @@ static int x25_add_route(struct x25_address *address, unsigned int sigdigits, struct net_device *dev) { struct x25_route *rt; - struct list_head *entry; int rc = -EINVAL; write_lock_bh(&x25_route_list_lock); - list_for_each(entry, &x25_route_list) { - rt = list_entry(entry, struct x25_route, node); - + list_for_each_entry(rt, &x25_route_list, node) { if (!memcmp(&rt->address, address, sigdigits) && rt->sigdigits == sigdigits) goto out; @@ -78,14 +75,11 @@ static int x25_del_route(struct x25_address *address, unsigned int sigdigits, struct net_device *dev) { struct x25_route *rt; - struct list_head *entry; int rc = -EINVAL; write_lock_bh(&x25_route_list_lock); - list_for_each(entry, &x25_route_list) { - rt = list_entry(entry, struct x25_route, node); - + list_for_each_entry(rt, &x25_route_list, node) { if (!memcmp(&rt->address, address, sigdigits) && rt->sigdigits == sigdigits && rt->dev == dev) { __x25_remove_route(rt); @@ -141,13 +135,10 @@ struct net_device *x25_dev_get(char *devname) struct x25_route *x25_get_route(struct x25_address *addr) { struct x25_route *rt, *use = NULL; - struct list_head *entry; read_lock_bh(&x25_route_list_lock); - list_for_each(entry, &x25_route_list) { - rt = list_entry(entry, struct x25_route, node); - + list_for_each_entry(rt, &x25_route_list, node) { if (!memcmp(&rt->address, addr, rt->sigdigits)) { if (!use) use = rt; diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 56a28a686988..f01ef6bda390 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -27,7 +27,7 @@ static void xdp_umem_unpin_pages(struct xdp_umem *umem) { unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true); - kfree(umem->pgs); + kvfree(umem->pgs); umem->pgs = NULL; } @@ -99,8 +99,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) long npgs; int err; - umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs), - GFP_KERNEL | __GFP_NOWARN); + umem->pgs = kvcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL | __GFP_NOWARN); if (!umem->pgs) return -ENOMEM; @@ -123,7 +122,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) out_pin: xdp_umem_unpin_pages(umem); out_pgs: - kfree(umem->pgs); + kvfree(umem->pgs); umem->pgs = NULL; return err; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index cd62d4ba87a9..d6b500dc4208 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -749,7 +749,7 @@ static void xsk_unbind_dev(struct xdp_sock *xs) } static struct xsk_map *xsk_get_map_list_entry(struct xdp_sock *xs, - struct xdp_sock ***map_entry) + struct xdp_sock __rcu ***map_entry) { struct xsk_map *map = NULL; struct xsk_map_node *node; @@ -785,7 +785,7 @@ static void xsk_delete_from_maps(struct xdp_sock *xs) * might be updates to the map between * xsk_get_map_list_entry() and xsk_map_try_sock_delete(). */ - struct xdp_sock **map_entry = NULL; + struct xdp_sock __rcu **map_entry = NULL; struct xsk_map *map; while ((map = xsk_get_map_list_entry(xs, &map_entry))) { @@ -1313,7 +1313,7 @@ static int xsk_notifier(struct notifier_block *this, if (xs->dev == dev) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_error_report(sk); + sk_error_report(sk); xsk_unbind_dev(xs); diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h index edcf249ad1f1..a4bc4749faac 100644 --- a/net/xdp/xsk.h +++ b/net/xdp/xsk.h @@ -31,7 +31,7 @@ struct xdp_mmap_offsets_v1 { struct xsk_map_node { struct list_head node; struct xsk_map *map; - struct xdp_sock **map_entry; + struct xdp_sock __rcu **map_entry; }; static inline struct xdp_sock *xdp_sk(struct sock *sk) @@ -40,7 +40,7 @@ static inline struct xdp_sock *xdp_sk(struct sock *sk) } void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, - struct xdp_sock **map_entry); + struct xdp_sock __rcu **map_entry); void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id); int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, u16 queue_id); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 9d2a89d793c0..9ae13cccfb28 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -128,12 +128,15 @@ static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { - u64 chunk; - - if (desc->len > pool->chunk_size) - return false; + u64 chunk, chunk_end; chunk = xp_aligned_extract_addr(pool, desc->addr); + if (likely(desc->len)) { + chunk_end = xp_aligned_extract_addr(pool, desc->addr + desc->len - 1); + if (chunk != chunk_end) + return false; + } + if (chunk >= pool->addrs_cnt) return false; diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 67b4ce504852..2e48d0e094d9 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -12,7 +12,7 @@ #include "xsk.h" static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map, - struct xdp_sock **map_entry) + struct xdp_sock __rcu **map_entry) { struct xsk_map_node *node; @@ -42,7 +42,7 @@ static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node) } static void xsk_map_sock_delete(struct xdp_sock *xs, - struct xdp_sock **map_entry) + struct xdp_sock __rcu **map_entry) { struct xsk_map_node *n, *tmp; @@ -124,6 +124,10 @@ static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) return insn - insn_buf; } +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. + */ static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) { struct xsk_map *m = container_of(map, struct xsk_map, map); @@ -131,12 +135,11 @@ static void *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) if (key >= map->max_entries) return NULL; - return READ_ONCE(m->xsk_map[key]); + return rcu_dereference_check(m->xsk_map[key], rcu_read_lock_bh_held()); } static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) { - WARN_ON_ONCE(!rcu_read_lock_held()); return __xsk_map_lookup_elem(map, *(u32 *)key); } @@ -149,7 +152,8 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *xs, *old_xs, **map_entry; + struct xdp_sock __rcu **map_entry; + struct xdp_sock *xs, *old_xs; u32 i = *(u32 *)key, fd = *(u32 *)value; struct xsk_map_node *node; struct socket *sock; @@ -179,7 +183,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, } spin_lock_bh(&m->lock); - old_xs = READ_ONCE(*map_entry); + old_xs = rcu_dereference_protected(*map_entry, lockdep_is_held(&m->lock)); if (old_xs == xs) { err = 0; goto out; @@ -191,7 +195,7 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, goto out; } xsk_map_sock_add(xs, node); - WRITE_ONCE(*map_entry, xs); + rcu_assign_pointer(*map_entry, xs); if (old_xs) xsk_map_sock_delete(old_xs, map_entry); spin_unlock_bh(&m->lock); @@ -208,7 +212,8 @@ out: static int xsk_map_delete_elem(struct bpf_map *map, void *key) { struct xsk_map *m = container_of(map, struct xsk_map, map); - struct xdp_sock *old_xs, **map_entry; + struct xdp_sock __rcu **map_entry; + struct xdp_sock *old_xs; int k = *(u32 *)key; if (k >= map->max_entries) @@ -216,7 +221,7 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) spin_lock_bh(&m->lock); map_entry = &m->xsk_map[k]; - old_xs = xchg(map_entry, NULL); + old_xs = unrcu_pointer(xchg(map_entry, NULL)); if (old_xs) xsk_map_sock_delete(old_xs, map_entry); spin_unlock_bh(&m->lock); @@ -226,15 +231,16 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, __xsk_map_lookup_elem); + return __bpf_xdp_redirect_map(map, ifindex, flags, 0, + __xsk_map_lookup_elem); } void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, - struct xdp_sock **map_entry) + struct xdp_sock __rcu **map_entry) { spin_lock_bh(&map->lock); - if (READ_ONCE(*map_entry) == xs) { - WRITE_ONCE(*map_entry, NULL); + if (rcu_access_pointer(*map_entry) == xs) { + rcu_assign_pointer(*map_entry, NULL); xsk_map_sock_delete(xs, map_entry); } spin_unlock_bh(&map->lock); diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 6d6917b68856..e843b0d9e2a6 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -268,6 +268,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, xso->num_exthdrs = 0; xso->flags = 0; xso->dev = NULL; + xso->real_dev = NULL; dev_put(dev); if (err != -EOPNOTSUPP) diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h index ce66323102f9..d12bb906c9c9 100644 --- a/net/xfrm/xfrm_hash.h +++ b/net/xfrm/xfrm_hash.h @@ -131,6 +131,13 @@ __xfrm_spi_hash(const xfrm_address_t *daddr, __be32 spi, u8 proto, return (h ^ (h >> 10) ^ (h >> 20)) & hmask; } +static inline unsigned int +__xfrm_seq_hash(u32 seq, unsigned int hmask) +{ + unsigned int h = seq; + return (h ^ (h >> 10) ^ (h >> 20)) & hmask; +} + static inline unsigned int __idx_hash(u32 index, unsigned int hmask) { return (index ^ (index >> 8)) & hmask; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 1158cd0311d7..3df0861d4390 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -612,7 +612,7 @@ lock: goto drop_unlock; } - if (x->repl->check(x, skb, seq)) { + if (xfrm_replay_check(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } @@ -660,12 +660,12 @@ resume: /* only the first xfrm gets the encap type */ encap_type = 0; - if (x->repl->recheck(x, skb, seq)) { + if (xfrm_replay_recheck(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } - x->repl->advance(x, seq); + xfrm_replay_advance(x, seq); x->curlft.bytes += skb->len; x->curlft.packets++; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 305923522c5b..ad847516e22a 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -77,6 +77,83 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb) return 0; } +#if IS_ENABLED(CONFIG_IPV6_MIP6) +static int mip6_rthdr_offset(struct sk_buff *skb, u8 **nexthdr, int type) +{ + const unsigned char *nh = skb_network_header(skb); + unsigned int offset = sizeof(struct ipv6hdr); + unsigned int packet_len; + int found_rhdr = 0; + + packet_len = skb_tail_pointer(skb) - nh; + *nexthdr = &ipv6_hdr(skb)->nexthdr; + + while (offset <= packet_len) { + struct ipv6_opt_hdr *exthdr; + + switch (**nexthdr) { + case NEXTHDR_HOP: + break; + case NEXTHDR_ROUTING: + if (type == IPPROTO_ROUTING && offset + 3 <= packet_len) { + struct ipv6_rt_hdr *rt; + + rt = (struct ipv6_rt_hdr *)(nh + offset); + if (rt->type != 0) + return offset; + } + found_rhdr = 1; + break; + case NEXTHDR_DEST: + /* HAO MUST NOT appear more than once. + * XXX: It is better to try to find by the end of + * XXX: packet if HAO exists. + */ + if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) { + net_dbg_ratelimited("mip6: hao exists already, override\n"); + return offset; + } + + if (found_rhdr) + return offset; + + break; + default: + return offset; + } + + if (offset + sizeof(struct ipv6_opt_hdr) > packet_len) + return -EINVAL; + + exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + + offset); + offset += ipv6_optlen(exthdr); + if (offset > IPV6_MAXPLEN) + return -EINVAL; + *nexthdr = &exthdr->nexthdr; + } + + return -EINVAL; +} +#endif + +#if IS_ENABLED(CONFIG_IPV6) +static int xfrm6_hdr_offset(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr) +{ + switch (x->type->proto) { +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case IPPROTO_DSTOPTS: + case IPPROTO_ROUTING: + return mip6_rthdr_offset(skb, prevhdr, x->type->proto); +#endif + default: + break; + } + + return ip6_find_1stfragopt(skb, prevhdr); +} +#endif + /* Add encapsulation header. * * The IP header and mutable extension headers will be moved forward to make @@ -92,7 +169,7 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb) iph = ipv6_hdr(skb); skb_set_inner_transport_header(skb, skb_transport_offset(skb)); - hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr); if (hdr_len < 0) return hdr_len; skb_set_mac_header(skb, @@ -122,7 +199,7 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb) iph = ipv6_hdr(skb); - hdr_len = x->type->hdr_offset(x, skb, &prevhdr); + hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr); if (hdr_len < 0) return hdr_len; skb_set_mac_header(skb, @@ -446,7 +523,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err) goto error; } - err = x->repl->overflow(x, skb); + err = xfrm_replay_overflow(x, skb); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR); goto error; @@ -563,6 +640,42 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb return 0; } +/* For partial checksum offload, the outer header checksum is calculated + * by software and the inner header checksum is calculated by hardware. + * This requires hardware to know the inner packet type to calculate + * the inner header checksum. Save inner ip protocol here to avoid + * traversing the packet in the vendor's xmit code. + * If the encap type is IPIP, just save skb->inner_ipproto. Otherwise, + * get the ip protocol from the IP header. + */ +static void xfrm_get_inner_ipproto(struct sk_buff *skb) +{ + struct xfrm_offload *xo = xfrm_offload(skb); + const struct ethhdr *eth; + + if (!xo) + return; + + if (skb->inner_protocol_type == ENCAP_TYPE_IPPROTO) { + xo->inner_ipproto = skb->inner_ipproto; + return; + } + + if (skb->inner_protocol_type != ENCAP_TYPE_ETHER) + return; + + eth = (struct ethhdr *)skb_inner_mac_header(skb); + + switch (ntohs(eth->h_proto)) { + case ETH_P_IPV6: + xo->inner_ipproto = inner_ipv6_hdr(skb)->nexthdr; + break; + case ETH_P_IP: + xo->inner_ipproto = inner_ip_hdr(skb)->protocol; + break; + } +} + int xfrm_output(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -592,12 +705,15 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); return -ENOMEM; } - skb->encapsulation = 1; sp->olen++; sp->xvec[sp->len++] = x; xfrm_state_hold(x); + if (skb->encapsulation) + xfrm_get_inner_ipproto(skb); + skb->encapsulation = 1; + if (skb_is_gso(skb)) { if (skb->inner_protocol) return xfrm_output_gso(net, sk, skb); @@ -709,15 +825,8 @@ out: static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) - unsigned int ptr = 0; int err; - if (x->outer_mode.encap == XFRM_MODE_BEET && - ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL) >= 0) { - net_warn_ratelimited("BEET mode doesn't support inner IPv6 fragments\n"); - return -EAFNOSUPPORT; - } - err = xfrm6_tunnel_check_size(skb); if (err) return err; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ce500f847b99..827d84255021 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1902,8 +1902,7 @@ static int xfrm_policy_match(const struct xfrm_policy *pol, match = xfrm_selector_match(sel, fl, family); if (match) - ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid, - dir); + ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid); return ret; } @@ -2092,12 +2091,15 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if (unlikely(!daddr || !saddr)) return NULL; - rcu_read_lock(); retry: - do { - sequence = read_seqcount_begin(&xfrm_policy_hash_generation); - chain = policy_hash_direct(net, daddr, saddr, family, dir); - } while (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)); + sequence = read_seqcount_begin(&xfrm_policy_hash_generation); + rcu_read_lock(); + + chain = policy_hash_direct(net, daddr, saddr, family, dir); + if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) { + rcu_read_unlock(); + goto retry; + } ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { @@ -2128,11 +2130,15 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, } skip_inexact: - if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) + if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) { + rcu_read_unlock(); goto retry; + } - if (ret && !xfrm_pol_hold_rcu(ret)) + if (ret && !xfrm_pol_hold_rcu(ret)) { + rcu_read_unlock(); goto retry; + } fail: rcu_read_unlock(); @@ -2181,8 +2187,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, goto out; } err = security_xfrm_policy_lookup(pol->security, - fl->flowi_secid, - dir); + fl->flowi_secid); if (!err) { if (!xfrm_pol_hold_rcu(pol)) goto again; @@ -3247,7 +3252,7 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, /* * 0 or more than 0 is returned when validation is succeeded (either bypass - * because of optional transport mode, or next index of the mathced secpath + * because of optional transport mode, or next index of the matched secpath * state with the template. * -1 is returned when no matching template is found. * Otherwise "-2 - errored_index" is returned. diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index c6a4338a0d08..9277d81b344c 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -34,8 +34,11 @@ u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq) return seq_hi; } EXPORT_SYMBOL(xfrm_replay_seqhi); -; -static void xfrm_replay_notify(struct xfrm_state *x, int event) + +static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event); +static void xfrm_replay_notify_esn(struct xfrm_state *x, int event); + +void xfrm_replay_notify(struct xfrm_state *x, int event) { struct km_event c; /* we send notify messages in case @@ -48,6 +51,17 @@ static void xfrm_replay_notify(struct xfrm_state *x, int event) * The state structure must be locked! */ + switch (x->repl_mode) { + case XFRM_REPLAY_MODE_LEGACY: + break; + case XFRM_REPLAY_MODE_BMP: + xfrm_replay_notify_bmp(x, event); + return; + case XFRM_REPLAY_MODE_ESN: + xfrm_replay_notify_esn(x, event); + return; + } + switch (event) { case XFRM_REPLAY_UPDATE: if (!x->replay_maxdiff || @@ -81,7 +95,7 @@ static void xfrm_replay_notify(struct xfrm_state *x, int event) x->xflags &= ~XFRM_TIME_DEFER; } -static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) +static int __xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) { int err = 0; struct net *net = xs_net(x); @@ -98,14 +112,14 @@ static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) return err; } if (xfrm_aevent_is_on(net)) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } return err; } -static int xfrm_replay_check(struct xfrm_state *x, - struct sk_buff *skb, __be32 net_seq) +static int xfrm_replay_check_legacy(struct xfrm_state *x, + struct sk_buff *skb, __be32 net_seq) { u32 diff; u32 seq = ntohl(net_seq); @@ -136,14 +150,26 @@ err: return -EINVAL; } -static void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq) +static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq); +static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq); + +void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq) { - u32 diff; - u32 seq = ntohl(net_seq); + u32 diff, seq; + + switch (x->repl_mode) { + case XFRM_REPLAY_MODE_LEGACY: + break; + case XFRM_REPLAY_MODE_BMP: + return xfrm_replay_advance_bmp(x, net_seq); + case XFRM_REPLAY_MODE_ESN: + return xfrm_replay_advance_esn(x, net_seq); + } if (!x->props.replay_window) return; + seq = ntohl(net_seq); if (seq > x->replay.seq) { diff = seq - x->replay.seq; if (diff < x->props.replay_window) @@ -157,7 +183,7 @@ static void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq) } if (xfrm_aevent_is_on(xs_net(x))) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb) @@ -178,7 +204,7 @@ static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb) return err; } if (xfrm_aevent_is_on(net)) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } return err; @@ -273,7 +299,7 @@ static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq) replay_esn->bmp[nr] |= (1U << bitnr); if (xfrm_aevent_is_on(xs_net(x))) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event) @@ -416,7 +442,7 @@ static int xfrm_replay_overflow_esn(struct xfrm_state *x, struct sk_buff *skb) } } if (xfrm_aevent_is_on(net)) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } return err; @@ -481,6 +507,21 @@ err: return -EINVAL; } +int xfrm_replay_check(struct xfrm_state *x, + struct sk_buff *skb, __be32 net_seq) +{ + switch (x->repl_mode) { + case XFRM_REPLAY_MODE_LEGACY: + break; + case XFRM_REPLAY_MODE_BMP: + return xfrm_replay_check_bmp(x, skb, net_seq); + case XFRM_REPLAY_MODE_ESN: + return xfrm_replay_check_esn(x, skb, net_seq); + } + + return xfrm_replay_check_legacy(x, skb, net_seq); +} + static int xfrm_replay_recheck_esn(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { @@ -493,6 +534,22 @@ static int xfrm_replay_recheck_esn(struct xfrm_state *x, return xfrm_replay_check_esn(x, skb, net_seq); } +int xfrm_replay_recheck(struct xfrm_state *x, + struct sk_buff *skb, __be32 net_seq) +{ + switch (x->repl_mode) { + case XFRM_REPLAY_MODE_LEGACY: + break; + case XFRM_REPLAY_MODE_BMP: + /* no special recheck treatment */ + return xfrm_replay_check_bmp(x, skb, net_seq); + case XFRM_REPLAY_MODE_ESN: + return xfrm_replay_recheck_esn(x, skb, net_seq); + } + + return xfrm_replay_check_legacy(x, skb, net_seq); +} + static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq) { unsigned int bitnr, nr, i; @@ -548,7 +605,7 @@ static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq) replay_esn->bmp[nr] |= (1U << bitnr); if (xfrm_aevent_is_on(xs_net(x))) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } #ifdef CONFIG_XFRM_OFFLOAD @@ -560,7 +617,7 @@ static int xfrm_replay_overflow_offload(struct xfrm_state *x, struct sk_buff *sk __u32 oseq = x->replay.oseq; if (!xo) - return xfrm_replay_overflow(x, skb); + return __xfrm_replay_overflow(x, skb); if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { if (!skb_is_gso(skb)) { @@ -585,7 +642,7 @@ static int xfrm_replay_overflow_offload(struct xfrm_state *x, struct sk_buff *sk x->replay.oseq = oseq; if (xfrm_aevent_is_on(net)) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } return err; @@ -625,7 +682,7 @@ static int xfrm_replay_overflow_offload_bmp(struct xfrm_state *x, struct sk_buff } if (xfrm_aevent_is_on(net)) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } return err; @@ -674,59 +731,39 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff replay_esn->oseq = oseq; if (xfrm_aevent_is_on(net)) - x->repl->notify(x, XFRM_REPLAY_UPDATE); + xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } return err; } -static const struct xfrm_replay xfrm_replay_legacy = { - .advance = xfrm_replay_advance, - .check = xfrm_replay_check, - .recheck = xfrm_replay_check, - .notify = xfrm_replay_notify, - .overflow = xfrm_replay_overflow_offload, -}; +int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) +{ + switch (x->repl_mode) { + case XFRM_REPLAY_MODE_LEGACY: + break; + case XFRM_REPLAY_MODE_BMP: + return xfrm_replay_overflow_offload_bmp(x, skb); + case XFRM_REPLAY_MODE_ESN: + return xfrm_replay_overflow_offload_esn(x, skb); + } -static const struct xfrm_replay xfrm_replay_bmp = { - .advance = xfrm_replay_advance_bmp, - .check = xfrm_replay_check_bmp, - .recheck = xfrm_replay_check_bmp, - .notify = xfrm_replay_notify_bmp, - .overflow = xfrm_replay_overflow_offload_bmp, -}; - -static const struct xfrm_replay xfrm_replay_esn = { - .advance = xfrm_replay_advance_esn, - .check = xfrm_replay_check_esn, - .recheck = xfrm_replay_recheck_esn, - .notify = xfrm_replay_notify_esn, - .overflow = xfrm_replay_overflow_offload_esn, -}; + return xfrm_replay_overflow_offload(x, skb); +} #else -static const struct xfrm_replay xfrm_replay_legacy = { - .advance = xfrm_replay_advance, - .check = xfrm_replay_check, - .recheck = xfrm_replay_check, - .notify = xfrm_replay_notify, - .overflow = xfrm_replay_overflow, -}; +int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) +{ + switch (x->repl_mode) { + case XFRM_REPLAY_MODE_LEGACY: + break; + case XFRM_REPLAY_MODE_BMP: + return xfrm_replay_overflow_bmp(x, skb); + case XFRM_REPLAY_MODE_ESN: + return xfrm_replay_overflow_esn(x, skb); + } -static const struct xfrm_replay xfrm_replay_bmp = { - .advance = xfrm_replay_advance_bmp, - .check = xfrm_replay_check_bmp, - .recheck = xfrm_replay_check_bmp, - .notify = xfrm_replay_notify_bmp, - .overflow = xfrm_replay_overflow_bmp, -}; - -static const struct xfrm_replay xfrm_replay_esn = { - .advance = xfrm_replay_advance_esn, - .check = xfrm_replay_check_esn, - .recheck = xfrm_replay_recheck_esn, - .notify = xfrm_replay_notify_esn, - .overflow = xfrm_replay_overflow_esn, -}; + return __xfrm_replay_overflow(x, skb); +} #endif int xfrm_init_replay(struct xfrm_state *x) @@ -741,12 +778,12 @@ int xfrm_init_replay(struct xfrm_state *x) if (x->props.flags & XFRM_STATE_ESN) { if (replay_esn->replay_window == 0) return -EINVAL; - x->repl = &xfrm_replay_esn; + x->repl_mode = XFRM_REPLAY_MODE_ESN; } else { - x->repl = &xfrm_replay_bmp; + x->repl_mode = XFRM_REPLAY_MODE_BMP; } } else { - x->repl = &xfrm_replay_legacy; + x->repl_mode = XFRM_REPLAY_MODE_LEGACY; } return 0; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 432371d6ffbd..d6f0fbf033e3 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -78,10 +78,16 @@ xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr, return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask); } +static unsigned int xfrm_seq_hash(struct net *net, u32 seq) +{ + return __xfrm_seq_hash(seq, net->xfrm.state_hmask); +} + static void xfrm_hash_transfer(struct hlist_head *list, struct hlist_head *ndsttable, struct hlist_head *nsrctable, struct hlist_head *nspitable, + struct hlist_head *nseqtable, unsigned int nhashmask) { struct hlist_node *tmp; @@ -106,6 +112,11 @@ static void xfrm_hash_transfer(struct hlist_head *list, nhashmask); hlist_add_head_rcu(&x->byspi, nspitable + h); } + + if (x->km.seq) { + h = __xfrm_seq_hash(x->km.seq, nhashmask); + hlist_add_head_rcu(&x->byseq, nseqtable + h); + } } } @@ -117,7 +128,7 @@ static unsigned long xfrm_hash_new_size(unsigned int state_hmask) static void xfrm_hash_resize(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.state_hash_work); - struct hlist_head *ndst, *nsrc, *nspi, *odst, *osrc, *ospi; + struct hlist_head *ndst, *nsrc, *nspi, *nseq, *odst, *osrc, *ospi, *oseq; unsigned long nsize, osize; unsigned int nhashmask, ohashmask; int i; @@ -137,6 +148,13 @@ static void xfrm_hash_resize(struct work_struct *work) xfrm_hash_free(nsrc, nsize); return; } + nseq = xfrm_hash_alloc(nsize); + if (!nseq) { + xfrm_hash_free(ndst, nsize); + xfrm_hash_free(nsrc, nsize); + xfrm_hash_free(nspi, nsize); + return; + } spin_lock_bh(&net->xfrm.xfrm_state_lock); write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); @@ -144,15 +162,17 @@ static void xfrm_hash_resize(struct work_struct *work) nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net); for (i = net->xfrm.state_hmask; i >= 0; i--) - xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nhashmask); + xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nseq, nhashmask); osrc = xfrm_state_deref_prot(net->xfrm.state_bysrc, net); ospi = xfrm_state_deref_prot(net->xfrm.state_byspi, net); + oseq = xfrm_state_deref_prot(net->xfrm.state_byseq, net); ohashmask = net->xfrm.state_hmask; rcu_assign_pointer(net->xfrm.state_bydst, ndst); rcu_assign_pointer(net->xfrm.state_bysrc, nsrc); rcu_assign_pointer(net->xfrm.state_byspi, nspi); + rcu_assign_pointer(net->xfrm.state_byseq, nseq); net->xfrm.state_hmask = nhashmask; write_seqcount_end(&net->xfrm.xfrm_state_hash_generation); @@ -165,6 +185,7 @@ static void xfrm_hash_resize(struct work_struct *work) xfrm_hash_free(odst, osize); xfrm_hash_free(osrc, osize); xfrm_hash_free(ospi, osize); + xfrm_hash_free(oseq, osize); } static DEFINE_SPINLOCK(xfrm_state_afinfo_lock); @@ -621,6 +642,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) INIT_HLIST_NODE(&x->bydst); INIT_HLIST_NODE(&x->bysrc); INIT_HLIST_NODE(&x->byspi); + INIT_HLIST_NODE(&x->byseq); hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT); x->mtimer.function = xfrm_timer_handler; timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0); @@ -664,6 +686,8 @@ int __xfrm_state_delete(struct xfrm_state *x) list_del(&x->km.all); hlist_del_rcu(&x->bydst); hlist_del_rcu(&x->bysrc); + if (x->km.seq) + hlist_del_rcu(&x->byseq); if (x->id.spi) hlist_del_rcu(&x->byspi); net->xfrm.state_num--; @@ -1148,6 +1172,10 @@ found: h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); } + if (x->km.seq) { + h = xfrm_seq_hash(net, x->km.seq); + hlist_add_head_rcu(&x->byseq, net->xfrm.state_byseq + h); + } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), @@ -1263,6 +1291,12 @@ static void __xfrm_state_insert(struct xfrm_state *x) hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); } + if (x->km.seq) { + h = xfrm_seq_hash(net, x->km.seq); + + hlist_add_head_rcu(&x->byseq, net->xfrm.state_byseq + h); + } + hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); if (x->replay_maxage) mod_timer(&x->rtimer, jiffies + x->replay_maxage); @@ -1932,20 +1966,18 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq) { - int i; + unsigned int h = xfrm_seq_hash(net, seq); + struct xfrm_state *x; - for (i = 0; i <= net->xfrm.state_hmask; i++) { - struct xfrm_state *x; - - hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { - if (x->km.seq == seq && - (mark & x->mark.m) == x->mark.v && - x->km.state == XFRM_STATE_ACQ) { - xfrm_state_hold(x); - return x; - } + hlist_for_each_entry_rcu(x, net->xfrm.state_byseq + h, byseq) { + if (x->km.seq == seq && + (mark & x->mark.m) == x->mark.v && + x->km.state == XFRM_STATE_ACQ) { + xfrm_state_hold(x); + return x; } } + return NULL; } @@ -2145,7 +2177,7 @@ static void xfrm_replay_timer_handler(struct timer_list *t) if (x->km.state == XFRM_STATE_VALID) { if (xfrm_aevent_is_on(xs_net(x))) - x->repl->notify(x, XFRM_REPLAY_TIMEOUT); + xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT); else x->xflags |= XFRM_TIME_DEFER; } @@ -2521,7 +2553,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_delete_tunnel); -u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) +u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu) { const struct xfrm_type *type = READ_ONCE(x->type); struct crypto_aead *aead; @@ -2552,7 +2584,17 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) return ((mtu - x->props.header_len - crypto_aead_authsize(aead) - net_adj) & ~(blksize - 1)) + net_adj - 2; } -EXPORT_SYMBOL_GPL(xfrm_state_mtu); +EXPORT_SYMBOL_GPL(__xfrm_state_mtu); + +u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) +{ + mtu = __xfrm_state_mtu(x, mtu); + + if (x->props.family == AF_INET6 && mtu < IPV6_MIN_MTU) + return IPV6_MIN_MTU; + + return mtu; +} int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload) { @@ -2663,6 +2705,9 @@ int __net_init xfrm_state_init(struct net *net) net->xfrm.state_byspi = xfrm_hash_alloc(sz); if (!net->xfrm.state_byspi) goto out_byspi; + net->xfrm.state_byseq = xfrm_hash_alloc(sz); + if (!net->xfrm.state_byseq) + goto out_byseq; net->xfrm.state_hmask = ((sz / sizeof(struct hlist_head)) - 1); net->xfrm.state_num = 0; @@ -2672,6 +2717,8 @@ int __net_init xfrm_state_init(struct net *net) &net->xfrm.xfrm_state_lock); return 0; +out_byseq: + xfrm_hash_free(net->xfrm.state_byspi, sz); out_byspi: xfrm_hash_free(net->xfrm.state_bysrc, sz); out_bysrc: @@ -2691,6 +2738,8 @@ void xfrm_state_fini(struct net *net) WARN_ON(!list_empty(&net->xfrm.state_all)); sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head); + WARN_ON(!hlist_empty(net->xfrm.state_byseq)); + xfrm_hash_free(net->xfrm.state_byseq, sz); WARN_ON(!hlist_empty(net->xfrm.state_byspi)); xfrm_hash_free(net->xfrm.state_byspi, sz); WARN_ON(!hlist_empty(net->xfrm.state_bysrc)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 7b3647f8a2cb..51b3419b4e62 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -580,6 +580,20 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, copy_from_user_state(x, p); + if (attrs[XFRMA_ENCAP]) { + x->encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), + sizeof(*x->encap), GFP_KERNEL); + if (x->encap == NULL) + goto error; + } + + if (attrs[XFRMA_COADDR]) { + x->coaddr = kmemdup(nla_data(attrs[XFRMA_COADDR]), + sizeof(*x->coaddr), GFP_KERNEL); + if (x->coaddr == NULL) + goto error; + } + if (attrs[XFRMA_SA_EXTRA_FLAGS]) x->props.extra_flags = nla_get_u32(attrs[XFRMA_SA_EXTRA_FLAGS]); @@ -600,23 +614,9 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, attrs[XFRMA_ALG_COMP]))) goto error; - if (attrs[XFRMA_ENCAP]) { - x->encap = kmemdup(nla_data(attrs[XFRMA_ENCAP]), - sizeof(*x->encap), GFP_KERNEL); - if (x->encap == NULL) - goto error; - } - if (attrs[XFRMA_TFCPAD]) x->tfcpad = nla_get_u32(attrs[XFRMA_TFCPAD]); - if (attrs[XFRMA_COADDR]) { - x->coaddr = kmemdup(nla_data(attrs[XFRMA_COADDR]), - sizeof(*x->coaddr), GFP_KERNEL); - if (x->coaddr == NULL) - goto error; - } - xfrm_mark_get(attrs, &x->mark); xfrm_smark_init(attrs, &x->props.smark); diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 45ceca4e2c70..520434ea966f 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -41,6 +41,7 @@ tprogs-y += test_map_in_map tprogs-y += per_socket_stats_example tprogs-y += xdp_redirect tprogs-y += xdp_redirect_map +tprogs-y += xdp_redirect_map_multi tprogs-y += xdp_redirect_cpu tprogs-y += xdp_monitor tprogs-y += xdp_rxq_info @@ -99,6 +100,7 @@ test_map_in_map-objs := test_map_in_map_user.o per_socket_stats_example-objs := cookie_uid_helper_example.o xdp_redirect-objs := xdp_redirect_user.o xdp_redirect_map-objs := xdp_redirect_map_user.o +xdp_redirect_map_multi-objs := xdp_redirect_map_multi_user.o xdp_redirect_cpu-objs := xdp_redirect_cpu_user.o xdp_monitor-objs := xdp_monitor_user.o xdp_rxq_info-objs := xdp_rxq_info_user.o @@ -160,6 +162,7 @@ always-y += tcp_tos_reflect_kern.o always-y += tcp_dumpstats_kern.o always-y += xdp_redirect_kern.o always-y += xdp_redirect_map_kern.o +always-y += xdp_redirect_map_multi_kern.o always-y += xdp_redirect_cpu_kern.o always-y += xdp_monitor_kern.o always-y += xdp_rxq_info_kern.o diff --git a/samples/bpf/ibumad_kern.c b/samples/bpf/ibumad_kern.c index 26dcd4dde946..9b193231024a 100644 --- a/samples/bpf/ibumad_kern.c +++ b/samples/bpf/ibumad_kern.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB -/** +/* * ibumad BPF sample kernel side * * This program is free software; you can redistribute it and/or diff --git a/samples/bpf/ibumad_user.c b/samples/bpf/ibumad_user.c index d83d8102f489..0746ca516097 100644 --- a/samples/bpf/ibumad_user.c +++ b/samples/bpf/ibumad_user.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB -/** +/* * ibumad BPF sample user side * * This program is free software; you can redistribute it and/or diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index a78025b0026b..c9a0ca8351fd 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -396,7 +396,7 @@ int main(int argc, char **argv) * on different systems with different compilers. The right way is * to parse the ELF file. We took a shortcut here. */ - uprobe_file_offset = (__u64)main - (__u64)&__executable_start; + uprobe_file_offset = (unsigned long)main - (unsigned long)&__executable_start; CHECK_AND_RET(test_nondebug_fs_probe("uprobe", (char *)argv[0], uprobe_file_offset, 0x0, false, BPF_FD_TYPE_UPROBE, diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c index 74a4583d0d86..00061261a8da 100644 --- a/samples/bpf/xdp_fwd_user.c +++ b/samples/bpf/xdp_fwd_user.c @@ -67,6 +67,8 @@ static void usage(const char *prog) "usage: %s [OPTS] interface-list\n" "\nOPTS:\n" " -d detach program\n" + " -S use skb-mode\n" + " -F force loading prog\n" " -D direct table lookups (skip fib rules)\n", prog); } diff --git a/samples/bpf/xdp_redirect_map_multi_kern.c b/samples/bpf/xdp_redirect_map_multi_kern.c new file mode 100644 index 000000000000..71aa23d1cb2b --- /dev/null +++ b/samples/bpf/xdp_redirect_map_multi_kern.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +#define KBUILD_MODNAME "foo" +#include +#include +#include +#include +#include +#include + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP_HASH); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __uint(max_entries, 32); +} forward_map_general SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP_HASH); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 32); +} forward_map_native SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __type(key, u32); + __type(value, long); + __uint(max_entries, 1); +} rxcnt SEC(".maps"); + +/* map to store egress interfaces mac addresses, set the + * max_entries to 1 and extend it in user sapce prog. + */ +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, __be64); + __uint(max_entries, 1); +} mac_map SEC(".maps"); + +static int xdp_redirect_map(struct xdp_md *ctx, void *forward_map) +{ + long *value; + u32 key = 0; + + /* count packet in global counter */ + value = bpf_map_lookup_elem(&rxcnt, &key); + if (value) + *value += 1; + + return bpf_redirect_map(forward_map, key, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS); +} + +SEC("xdp_redirect_general") +int xdp_redirect_map_general(struct xdp_md *ctx) +{ + return xdp_redirect_map(ctx, &forward_map_general); +} + +SEC("xdp_redirect_native") +int xdp_redirect_map_native(struct xdp_md *ctx) +{ + return xdp_redirect_map(ctx, &forward_map_native); +} + +SEC("xdp_devmap/map_prog") +int xdp_devmap_prog(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + u32 key = ctx->egress_ifindex; + struct ethhdr *eth = data; + __be64 *mac; + u64 nh_off; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return XDP_DROP; + + mac = bpf_map_lookup_elem(&mac_map, &key); + if (mac) + __builtin_memcpy(eth->h_source, mac, ETH_ALEN); + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdp_redirect_map_multi_user.c b/samples/bpf/xdp_redirect_map_multi_user.c new file mode 100644 index 000000000000..84cdbbed20b7 --- /dev/null +++ b/samples/bpf/xdp_redirect_map_multi_user.c @@ -0,0 +1,302 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "bpf_util.h" +#include +#include + +#define MAX_IFACE_NUM 32 + +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static int ifaces[MAX_IFACE_NUM] = {}; +static int rxcnt_map_fd; + +static void int_exit(int sig) +{ + __u32 prog_id = 0; + int i; + + for (i = 0; ifaces[i] > 0; i++) { + if (bpf_get_link_xdp_id(ifaces[i], &prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id) + bpf_set_link_xdp_fd(ifaces[i], -1, xdp_flags); + } + + exit(0); +} + +static void poll_stats(int interval) +{ + unsigned int nr_cpus = bpf_num_possible_cpus(); + __u64 values[nr_cpus], prev[nr_cpus]; + + memset(prev, 0, sizeof(prev)); + + while (1) { + __u64 sum = 0; + __u32 key = 0; + int i; + + sleep(interval); + assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0); + for (i = 0; i < nr_cpus; i++) + sum += (values[i] - prev[i]); + if (sum) + printf("Forwarding %10llu pkt/s\n", sum / interval); + memcpy(prev, values, sizeof(values)); + } +} + +static int get_mac_addr(unsigned int ifindex, void *mac_addr) +{ + char ifname[IF_NAMESIZE]; + struct ifreq ifr; + int fd, ret = -1; + + fd = socket(AF_INET, SOCK_DGRAM, 0); + if (fd < 0) + return ret; + + if (!if_indextoname(ifindex, ifname)) + goto err_out; + + strcpy(ifr.ifr_name, ifname); + + if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0) + goto err_out; + + memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char)); + ret = 0; + +err_out: + close(fd); + return ret; +} + +static int update_mac_map(struct bpf_object *obj) +{ + int i, ret = -1, mac_map_fd; + unsigned char mac_addr[6]; + unsigned int ifindex; + + mac_map_fd = bpf_object__find_map_fd_by_name(obj, "mac_map"); + if (mac_map_fd < 0) { + printf("find mac map fd failed\n"); + return ret; + } + + for (i = 0; ifaces[i] > 0; i++) { + ifindex = ifaces[i]; + + ret = get_mac_addr(ifindex, mac_addr); + if (ret < 0) { + printf("get interface %d mac failed\n", ifindex); + return ret; + } + + ret = bpf_map_update_elem(mac_map_fd, &ifindex, mac_addr, 0); + if (ret) { + perror("bpf_update_elem mac_map_fd"); + return ret; + } + } + + return 0; +} + +static void usage(const char *prog) +{ + fprintf(stderr, + "usage: %s [OPTS] ...\n" + "OPTS:\n" + " -S use skb-mode\n" + " -N enforce native mode\n" + " -F force loading prog\n" + " -X load xdp program on egress\n", + prog); +} + +int main(int argc, char **argv) +{ + int i, ret, opt, forward_map_fd, max_ifindex = 0; + struct bpf_program *ingress_prog, *egress_prog; + int ingress_prog_fd, egress_prog_fd = 0; + struct bpf_devmap_val devmap_val; + bool attach_egress_prog = false; + char ifname[IF_NAMESIZE]; + struct bpf_map *mac_map; + struct bpf_object *obj; + unsigned int ifindex; + char filename[256]; + + while ((opt = getopt(argc, argv, "SNFX")) != -1) { + switch (opt) { + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'N': + /* default, set below */ + break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + case 'X': + attach_egress_prog = true; + break; + default: + usage(basename(argv[0])); + return 1; + } + } + + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) { + xdp_flags |= XDP_FLAGS_DRV_MODE; + } else if (attach_egress_prog) { + printf("Load xdp program on egress with SKB mode not supported yet\n"); + return 1; + } + + if (optind == argc) { + printf("usage: %s ...\n", argv[0]); + return 1; + } + + printf("Get interfaces"); + for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) { + ifaces[i] = if_nametoindex(argv[optind + i]); + if (!ifaces[i]) + ifaces[i] = strtoul(argv[optind + i], NULL, 0); + if (!if_indextoname(ifaces[i], ifname)) { + perror("Invalid interface name or i"); + return 1; + } + + /* Find the largest index number */ + if (ifaces[i] > max_ifindex) + max_ifindex = ifaces[i]; + + printf(" %d", ifaces[i]); + } + printf("\n"); + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + obj = bpf_object__open(filename); + if (libbpf_get_error(obj)) { + printf("ERROR: opening BPF object file failed\n"); + obj = NULL; + goto err_out; + } + + /* Reset the map size to max ifindex + 1 */ + if (attach_egress_prog) { + mac_map = bpf_object__find_map_by_name(obj, "mac_map"); + ret = bpf_map__resize(mac_map, max_ifindex + 1); + if (ret < 0) { + printf("ERROR: reset mac map size failed\n"); + goto err_out; + } + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + printf("ERROR: loading BPF object file failed\n"); + goto err_out; + } + + if (xdp_flags & XDP_FLAGS_SKB_MODE) { + ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_general"); + forward_map_fd = bpf_object__find_map_fd_by_name(obj, "forward_map_general"); + } else { + ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_native"); + forward_map_fd = bpf_object__find_map_fd_by_name(obj, "forward_map_native"); + } + if (!ingress_prog || forward_map_fd < 0) { + printf("finding ingress_prog/forward_map in obj file failed\n"); + goto err_out; + } + + ingress_prog_fd = bpf_program__fd(ingress_prog); + if (ingress_prog_fd < 0) { + printf("find ingress_prog fd failed\n"); + goto err_out; + } + + rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt"); + if (rxcnt_map_fd < 0) { + printf("bpf_object__find_map_fd_by_name failed\n"); + goto err_out; + } + + if (attach_egress_prog) { + /* Update mac_map with all egress interfaces' mac addr */ + if (update_mac_map(obj) < 0) { + printf("Error: update mac map failed"); + goto err_out; + } + + /* Find egress prog fd */ + egress_prog = bpf_object__find_program_by_name(obj, "xdp_devmap_prog"); + if (!egress_prog) { + printf("finding egress_prog in obj file failed\n"); + goto err_out; + } + egress_prog_fd = bpf_program__fd(egress_prog); + if (egress_prog_fd < 0) { + printf("find egress_prog fd failed\n"); + goto err_out; + } + } + + /* Remove attached program when program is interrupted or killed */ + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + /* Init forward multicast groups */ + for (i = 0; ifaces[i] > 0; i++) { + ifindex = ifaces[i]; + + /* bind prog_fd to each interface */ + ret = bpf_set_link_xdp_fd(ifindex, ingress_prog_fd, xdp_flags); + if (ret) { + printf("Set xdp fd failed on %d\n", ifindex); + goto err_out; + } + + /* Add all the interfaces to forward group and attach + * egress devmap programe if exist + */ + devmap_val.ifindex = ifindex; + devmap_val.bpf_prog.fd = egress_prog_fd; + ret = bpf_map_update_elem(forward_map_fd, &ifindex, &devmap_val, 0); + if (ret) { + perror("bpf_map_update_elem forward_map"); + goto err_out; + } + } + + poll_stats(2); + + return 0; + +err_out: + return 1; +} diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c index 41d705c3a1f7..93854e135134 100644 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@ -130,7 +130,7 @@ int main(int argc, char **argv) if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) xdp_flags |= XDP_FLAGS_DRV_MODE; - if (optind == argc) { + if (optind + 2 != argc) { printf("usage: %s _IN _OUT\n", argv[0]); return 1; } @@ -213,5 +213,5 @@ int main(int argc, char **argv) poll_stats(2, ifindex_out); out: - return 0; + return ret; } diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c index 706475e004cb..495e09897bd3 100644 --- a/samples/bpf/xdp_sample_pkts_user.c +++ b/samples/bpf/xdp_sample_pkts_user.c @@ -103,7 +103,8 @@ static void usage(const char *prog) fprintf(stderr, "%s: %s [OPTS] \n\n" "OPTS:\n" - " -F force loading prog\n", + " -F force loading prog\n" + " -S use skb-mode\n", __func__, prog); } diff --git a/samples/pktgen/parameters.sh b/samples/pktgen/parameters.sh index b4c1b371e4b8..81906f199454 100644 --- a/samples/pktgen/parameters.sh +++ b/samples/pktgen/parameters.sh @@ -11,6 +11,7 @@ function usage() { echo " -d : (\$DEST_IP) destination IP. CIDR (e.g. 198.18.0.0/15) is also allowed" echo " -m : (\$DST_MAC) destination MAC-addr" echo " -p : (\$DST_PORT) destination PORT range (e.g. 433-444) is also allowed" + echo " -k : (\$UDP_CSUM) enable UDP tx checksum" echo " -t : (\$THREADS) threads to start" echo " -f : (\$F_THREAD) index of first thread (zero indexed CPU number)" echo " -c : (\$SKB_CLONE) SKB clones send before alloc new SKB" @@ -26,7 +27,7 @@ function usage() { ## --- Parse command line arguments / parameters --- ## echo "Commandline options:" -while getopts "s:i:d:m:p:f:t:c:n:b:w:vxh6a" option; do +while getopts "s:i:d:m:p:f:t:c:n:b:w:vxh6ak" option; do case $option in i) # interface export DEV=$OPTARG @@ -88,6 +89,10 @@ while getopts "s:i:d:m:p:f:t:c:n:b:w:vxh6a" option; do export APPEND=yes info "Append mode: APPEND=$APPEND" ;; + k) + export UDP_CSUM=yes + info "UDP tx checksum: UDP_CSUM=$UDP_CSUM" + ;; h|?|*) usage; err 2 "[ERROR] Unknown parameters!!!" diff --git a/samples/pktgen/pktgen_sample01_simple.sh b/samples/pktgen/pktgen_sample01_simple.sh index a09f3422fbcc..246cfe02bb82 100755 --- a/samples/pktgen/pktgen_sample01_simple.sh +++ b/samples/pktgen/pktgen_sample01_simple.sh @@ -72,6 +72,8 @@ if [ -n "$DST_PORT" ]; then pg_set $DEV "udp_dst_max $UDP_DST_MAX" fi +[ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM" + # Setup random UDP port src range pg_set $DEV "flag UDPSRC_RND" pg_set $DEV "udp_src_min $UDP_SRC_MIN" diff --git a/samples/pktgen/pktgen_sample02_multiqueue.sh b/samples/pktgen/pktgen_sample02_multiqueue.sh index acae8ede0d6c..c6af3d9d5171 100755 --- a/samples/pktgen/pktgen_sample02_multiqueue.sh +++ b/samples/pktgen/pktgen_sample02_multiqueue.sh @@ -75,6 +75,8 @@ for ((thread = $F_THREAD; thread <= $L_THREAD; thread++)); do pg_set $dev "udp_dst_max $UDP_DST_MAX" fi + [ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM" + # Setup random UDP port src range pg_set $dev "flag UDPSRC_RND" pg_set $dev "udp_src_min $UDP_SRC_MIN" diff --git a/samples/pktgen/pktgen_sample03_burst_single_flow.sh b/samples/pktgen/pktgen_sample03_burst_single_flow.sh index 5adcf954de73..ab87de440277 100755 --- a/samples/pktgen/pktgen_sample03_burst_single_flow.sh +++ b/samples/pktgen/pktgen_sample03_burst_single_flow.sh @@ -73,6 +73,8 @@ for ((thread = $F_THREAD; thread <= $L_THREAD; thread++)); do pg_set $dev "udp_dst_max $UDP_DST_MAX" fi + [ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM" + # Setup burst, for easy testing -b 0 disable bursting # (internally in pktgen default and minimum burst=1) if [[ ${BURST} -ne 0 ]]; then diff --git a/samples/pktgen/pktgen_sample04_many_flows.sh b/samples/pktgen/pktgen_sample04_many_flows.sh index ddce876635aa..56c5f5af350f 100755 --- a/samples/pktgen/pktgen_sample04_many_flows.sh +++ b/samples/pktgen/pktgen_sample04_many_flows.sh @@ -72,6 +72,8 @@ for ((thread = $F_THREAD; thread <= $L_THREAD; thread++)); do pg_set $dev "udp_dst_max $UDP_DST_MAX" fi + [ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM" + # Randomize source IP-addresses pg_set $dev "flag IPSRC_RND" pg_set $dev "src_min $SRC_MIN" diff --git a/samples/pktgen/pktgen_sample05_flow_per_thread.sh b/samples/pktgen/pktgen_sample05_flow_per_thread.sh index 4a65fe2fcee9..6e0effabca59 100755 --- a/samples/pktgen/pktgen_sample05_flow_per_thread.sh +++ b/samples/pktgen/pktgen_sample05_flow_per_thread.sh @@ -62,6 +62,8 @@ for ((thread = $F_THREAD; thread <= $L_THREAD; thread++)); do pg_set $dev "udp_dst_max $UDP_DST_MAX" fi + [ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM" + # Setup source IP-addresses based on thread number pg_set $dev "src_min 198.18.$((thread+1)).1" pg_set $dev "src_max 198.18.$((thread+1)).1" diff --git a/samples/pktgen/pktgen_sample06_numa_awared_queue_irq_affinity.sh b/samples/pktgen/pktgen_sample06_numa_awared_queue_irq_affinity.sh index 10f1da571f40..7c27923083a6 100755 --- a/samples/pktgen/pktgen_sample06_numa_awared_queue_irq_affinity.sh +++ b/samples/pktgen/pktgen_sample06_numa_awared_queue_irq_affinity.sh @@ -92,6 +92,8 @@ for ((i = 0; i < $THREADS; i++)); do pg_set $dev "udp_dst_max $UDP_DST_MAX" fi + [ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM" + # Setup random UDP port src range pg_set $dev "flag UDPSRC_RND" pg_set $dev "udp_src_min $UDP_SRC_MIN" diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl index 911c72a2dbc4..1a5fea0519eb 100755 --- a/scripts/kconfig/streamline_config.pl +++ b/scripts/kconfig/streamline_config.pl @@ -601,12 +601,12 @@ if (defined($ENV{'LMC_KEEP'})) { sub in_preserved_kconfigs { my $kconfig = $config2kfile{$_[0]}; if (!defined($kconfig)) { - return 0; + return 0; } foreach my $excl (@preserved_kconfigs) { - if($kconfig =~ /^$excl/) { - return 1; - } + if($kconfig =~ /^$excl/) { + return 1; + } } return 0; } @@ -629,52 +629,52 @@ foreach my $line (@config_file) { } if (/CONFIG_MODULE_SIG_KEY="(.+)"/) { - my $orig_cert = $1; - my $default_cert = "certs/signing_key.pem"; + my $orig_cert = $1; + my $default_cert = "certs/signing_key.pem"; - # Check that the logic in this script still matches the one in Kconfig - if (!defined($depends{"MODULE_SIG_KEY"}) || - $depends{"MODULE_SIG_KEY"} !~ /"\Q$default_cert\E"/) { - print STDERR "WARNING: MODULE_SIG_KEY assertion failure, ", - "update needed to ", __FILE__, " line ", __LINE__, "\n"; - print; - } elsif ($orig_cert ne $default_cert && ! -f $orig_cert) { - print STDERR "Module signature verification enabled but ", - "module signing key \"$orig_cert\" not found. Resetting ", - "signing key to default value.\n"; - print "CONFIG_MODULE_SIG_KEY=\"$default_cert\"\n"; - } else { - print; - } - next; + # Check that the logic in this script still matches the one in Kconfig + if (!defined($depends{"MODULE_SIG_KEY"}) || + $depends{"MODULE_SIG_KEY"} !~ /"\Q$default_cert\E"/) { + print STDERR "WARNING: MODULE_SIG_KEY assertion failure, ", + "update needed to ", __FILE__, " line ", __LINE__, "\n"; + print; + } elsif ($orig_cert ne $default_cert && ! -f $orig_cert) { + print STDERR "Module signature verification enabled but ", + "module signing key \"$orig_cert\" not found. Resetting ", + "signing key to default value.\n"; + print "CONFIG_MODULE_SIG_KEY=\"$default_cert\"\n"; + } else { + print; + } + next; } if (/CONFIG_SYSTEM_TRUSTED_KEYS="(.+)"/) { - my $orig_keys = $1; + my $orig_keys = $1; - if (! -f $orig_keys) { - print STDERR "System keyring enabled but keys \"$orig_keys\" ", - "not found. Resetting keys to default value.\n"; - print "CONFIG_SYSTEM_TRUSTED_KEYS=\"\"\n"; - } else { - print; - } - next; + if (! -f $orig_keys) { + print STDERR "System keyring enabled but keys \"$orig_keys\" ", + "not found. Resetting keys to default value.\n"; + print "CONFIG_SYSTEM_TRUSTED_KEYS=\"\"\n"; + } else { + print; + } + next; } if (/^(CONFIG.*)=(m|y)/) { - if (in_preserved_kconfigs($1)) { - dprint "Preserve config $1"; - print; - next; - } + if (in_preserved_kconfigs($1)) { + dprint "Preserve config $1"; + print; + next; + } if (defined($configs{$1})) { if ($localyesconfig) { - $setconfigs{$1} = 'y'; + $setconfigs{$1} = 'y'; print "$1=y\n"; next; } else { - $setconfigs{$1} = $2; + $setconfigs{$1} = $2; } } elsif ($2 eq "m") { print "# $1 is not set\n"; @@ -702,3 +702,5 @@ foreach my $module (keys(%modules)) { print STDERR "\n"; } } + +# vim: softtabstop=4 diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 0e0f6466b18d..475faa15854e 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -235,6 +235,10 @@ gen_btf() vmlinux_link ${1} + if [ "${pahole_ver}" -ge "118" ] && [ "${pahole_ver}" -le "121" ]; then + # pahole 1.18 through 1.21 can't handle zero-sized per-CPU vars + extra_paholeopt="${extra_paholeopt} --skip_encoding_btf_vars" + fi if [ "${pahole_ver}" -ge "121" ]; then extra_paholeopt="${extra_paholeopt} --btf_gen_floats" fi diff --git a/scripts/spelling.txt b/scripts/spelling.txt index 7b6a01291598..17fdc620d548 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -22,6 +22,7 @@ absolut||absolute absoulte||absolute acccess||access acceess||access +accelaration||acceleration acceleratoin||acceleration accelleration||acceleration accesing||accessing @@ -264,6 +265,7 @@ calucate||calculate calulate||calculate cancelation||cancellation cancle||cancel +canot||cannot capabilites||capabilities capabilties||capabilities capabilty||capability @@ -494,7 +496,10 @@ digial||digital dimention||dimension dimesions||dimensions diconnected||disconnected +disabed||disabled +disble||disable disgest||digest +disired||desired dispalying||displaying diplay||display directon||direction @@ -710,6 +715,7 @@ havind||having heirarchically||hierarchically heirarchy||hierarchy helpfull||helpful +hearbeat||heartbeat heterogenous||heterogeneous hexdecimal||hexadecimal hybernate||hibernate @@ -989,6 +995,7 @@ notications||notifications notifcations||notifications notifed||notified notity||notify +nubmer||number numebr||number numner||number obtaion||obtain @@ -1014,8 +1021,10 @@ ommiting||omitting ommitted||omitted onself||oneself ony||only +openning||opening operatione||operation opertaions||operations +opportunies||opportunities optionnal||optional optmizations||optimizations orientatied||orientated @@ -1111,6 +1120,7 @@ prefitler||prefilter preform||perform premption||preemption prepaired||prepared +prepate||prepare preperation||preparation preprare||prepare pressre||pressure @@ -1123,6 +1133,7 @@ privilaged||privileged privilage||privilege priviledge||privilege priviledges||privileges +privleges||privileges probaly||probably procceed||proceed proccesors||processors @@ -1167,6 +1178,7 @@ promixity||proximity psudo||pseudo psuedo||pseudo psychadelic||psychedelic +purgable||purgeable pwoer||power queing||queuing quering||querying @@ -1180,6 +1192,7 @@ receieve||receive recepient||recipient recevied||received receving||receiving +recievd||received recieved||received recieve||receive reciever||receiver @@ -1228,6 +1241,7 @@ reponse||response representaion||representation reqeust||request reqister||register +requed||requeued requestied||requested requiere||require requirment||requirement @@ -1332,6 +1346,7 @@ singal||signal singed||signed sleeped||slept sliped||slipped +softwade||software softwares||software soley||solely souce||source @@ -1510,6 +1525,7 @@ unintialized||uninitialized unitialized||uninitialized unkmown||unknown unknonw||unknown +unknouwn||unknown unknow||unknown unkown||unknown unamed||unnamed diff --git a/security/lsm_audit.c b/security/lsm_audit.c index 82ce14933513..5a5016ef43b0 100644 --- a/security/lsm_audit.c +++ b/security/lsm_audit.c @@ -119,7 +119,6 @@ int ipv6_skb_to_auditdata(struct sk_buff *skb, return -EINVAL; ad->u.net->v6info.saddr = ip6->saddr; ad->u.net->v6info.daddr = ip6->daddr; - ret = 0; /* IPv6 can have several extension header before the Transport header * skip them */ offset = skb_network_offset(skb); diff --git a/security/safesetid/lsm.c b/security/safesetid/lsm.c index 1079c6d54784..963f4ad9cb66 100644 --- a/security/safesetid/lsm.c +++ b/security/safesetid/lsm.c @@ -22,7 +22,7 @@ #include "lsm.h" /* Flag indicating whether initialization completed */ -int safesetid_initialized; +int safesetid_initialized __initdata; struct setid_ruleset __rcu *safesetid_setuid_rules; struct setid_ruleset __rcu *safesetid_setgid_rules; diff --git a/security/safesetid/lsm.h b/security/safesetid/lsm.h index bde8c43a3767..d346f4849cea 100644 --- a/security/safesetid/lsm.h +++ b/security/safesetid/lsm.h @@ -19,7 +19,7 @@ #include /* Flag indicating whether initialization completed */ -extern int safesetid_initialized; +extern int safesetid_initialized __initdata; enum sid_policy_type { SIDPOL_DEFAULT, /* source ID is unaffected by policy */ diff --git a/security/security.c b/security/security.c index e9f8010a2341..09533cbb7221 100644 --- a/security/security.c +++ b/security/security.c @@ -2466,9 +2466,9 @@ void security_xfrm_state_free(struct xfrm_state *x) call_void_hook(xfrm_state_free_security, x); } -int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir) +int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid) { - return call_int_hook(xfrm_policy_lookup, 0, ctx, fl_secid, dir); + return call_int_hook(xfrm_policy_lookup, 0, ctx, fl_secid); } int security_xfrm_state_pol_flow_match(struct xfrm_state *x, diff --git a/security/selinux/avc.c b/security/selinux/avc.c index ad451cf9375e..97f4c944a20f 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -297,26 +297,27 @@ static struct avc_xperms_decision_node struct avc_xperms_decision_node *xpd_node; struct extended_perms_decision *xpd; - xpd_node = kmem_cache_zalloc(avc_xperms_decision_cachep, GFP_NOWAIT); + xpd_node = kmem_cache_zalloc(avc_xperms_decision_cachep, + GFP_NOWAIT | __GFP_NOWARN); if (!xpd_node) return NULL; xpd = &xpd_node->xpd; if (which & XPERMS_ALLOWED) { xpd->allowed = kmem_cache_zalloc(avc_xperms_data_cachep, - GFP_NOWAIT); + GFP_NOWAIT | __GFP_NOWARN); if (!xpd->allowed) goto error; } if (which & XPERMS_AUDITALLOW) { xpd->auditallow = kmem_cache_zalloc(avc_xperms_data_cachep, - GFP_NOWAIT); + GFP_NOWAIT | __GFP_NOWARN); if (!xpd->auditallow) goto error; } if (which & XPERMS_DONTAUDIT) { xpd->dontaudit = kmem_cache_zalloc(avc_xperms_data_cachep, - GFP_NOWAIT); + GFP_NOWAIT | __GFP_NOWARN); if (!xpd->dontaudit) goto error; } @@ -344,7 +345,7 @@ static struct avc_xperms_node *avc_xperms_alloc(void) { struct avc_xperms_node *xp_node; - xp_node = kmem_cache_zalloc(avc_xperms_cachep, GFP_NOWAIT); + xp_node = kmem_cache_zalloc(avc_xperms_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xp_node) return xp_node; INIT_LIST_HEAD(&xp_node->xpd_head); @@ -500,7 +501,7 @@ static struct avc_node *avc_alloc_node(struct selinux_avc *avc) { struct avc_node *node; - node = kmem_cache_zalloc(avc_node_cachep, GFP_NOWAIT); + node = kmem_cache_zalloc(avc_node_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!node) goto out; @@ -758,7 +759,11 @@ static void avc_audit_post_callback(struct audit_buffer *ab, void *a) } } -/* This is the slow part of avc audit with big stack footprint */ +/* + * This is the slow part of avc audit with big stack footprint. + * Note that it is non-blocking and can be called from under + * rcu_read_lock(). + */ noinline int slow_avc_audit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u32 audited, u32 denied, int result, @@ -819,13 +824,13 @@ out: } /** - * avc_update_node Update an AVC entry + * avc_update_node - Update an AVC entry * @event : Updating event * @perms : Permission mask bits * @ssid,@tsid,@tclass : identifier of an AVC entry * @seqno : sequence number when decision was made * @xpd: extended_perms_decision to be added to the node - * @flags: the AVC_* flags, e.g. AVC_NONBLOCKING, AVC_EXTENDED_PERMS, or 0. + * @flags: the AVC_* flags, e.g. AVC_EXTENDED_PERMS, or 0. * * if a valid AVC entry doesn't exist,this function returns -ENOENT. * if kmalloc() called internal returns NULL, this function returns -ENOMEM. @@ -844,21 +849,6 @@ static int avc_update_node(struct selinux_avc *avc, struct hlist_head *head; spinlock_t *lock; - /* - * If we are in a non-blocking code path, e.g. VFS RCU walk, - * then we must not add permissions to a cache entry - * because we will not audit the denial. Otherwise, - * during the subsequent blocking retry (e.g. VFS ref walk), we - * will find the permissions already granted in the cache entry - * and won't audit anything at all, leading to silent denials in - * permissive mode that only appear when in enforcing mode. - * - * See the corresponding handling of MAY_NOT_BLOCK in avc_audit() - * and selinux_inode_permission(). - */ - if (flags & AVC_NONBLOCKING) - return 0; - node = avc_alloc_node(avc); if (!node) { rc = -ENOMEM; @@ -1119,7 +1109,7 @@ decision: * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions, interpreted based on @tclass - * @flags: AVC_STRICT, AVC_NONBLOCKING, or 0 + * @flags: AVC_STRICT or 0 * @avd: access vector decisions * * Check the AVC to determine whether the @requested permissions are granted @@ -1190,26 +1180,7 @@ int avc_has_perm(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, &avd); rc2 = avc_audit(state, ssid, tsid, tclass, requested, &avd, rc, - auditdata, 0); - if (rc2) - return rc2; - return rc; -} - -int avc_has_perm_flags(struct selinux_state *state, - u32 ssid, u32 tsid, u16 tclass, u32 requested, - struct common_audit_data *auditdata, - int flags) -{ - struct av_decision avd; - int rc, rc2; - - rc = avc_has_perm_noaudit(state, ssid, tsid, tclass, requested, - (flags & MAY_NOT_BLOCK) ? AVC_NONBLOCKING : 0, - &avd); - - rc2 = avc_audit(state, ssid, tsid, tclass, requested, &avd, rc, - auditdata, flags); + auditdata); if (rc2) return rc2; return rc; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index eaea837d89d1..b0032c42333e 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1676,7 +1676,7 @@ static int cred_has_capability(const struct cred *cred, sid, sid, sclass, av, 0, &avd); if (!(opts & CAP_OPT_NOAUDIT)) { int rc2 = avc_audit(&selinux_state, - sid, sid, sclass, av, &avd, rc, &ad, 0); + sid, sid, sclass, av, &avd, rc, &ad); if (rc2) return rc2; } @@ -3153,9 +3153,8 @@ static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode, if (IS_ERR(isec)) return PTR_ERR(isec); - return avc_has_perm_flags(&selinux_state, - sid, isec->sid, isec->sclass, FILE__READ, &ad, - rcu ? MAY_NOT_BLOCK : 0); + return avc_has_perm(&selinux_state, + sid, isec->sid, isec->sclass, FILE__READ, &ad); } static noinline int audit_inode_permission(struct inode *inode, @@ -3164,17 +3163,13 @@ static noinline int audit_inode_permission(struct inode *inode, { struct common_audit_data ad; struct inode_security_struct *isec = selinux_inode(inode); - int rc; ad.type = LSM_AUDIT_DATA_INODE; ad.u.inode = inode; - rc = slow_avc_audit(&selinux_state, + return slow_avc_audit(&selinux_state, current_sid(), isec->sid, isec->sclass, perms, audited, denied, result, &ad); - if (rc) - return rc; - return 0; } static int selinux_inode_permission(struct inode *inode, int mask) @@ -3209,8 +3204,7 @@ static int selinux_inode_permission(struct inode *inode, int mask) return PTR_ERR(isec); rc = avc_has_perm_noaudit(&selinux_state, - sid, isec->sid, isec->sclass, perms, - no_block ? AVC_NONBLOCKING : 0, + sid, isec->sid, isec->sclass, perms, 0, &avd); audited = avc_audit_required(perms, &avd, rc, from_access ? FILE__AUDIT_ACCESS : 0, @@ -3218,10 +3212,6 @@ static int selinux_inode_permission(struct inode *inode, int mask) if (likely(!audited)) return rc; - /* fall back to ref-walk if we have to generate audit */ - if (no_block) - return -ECHILD; - rc2 = audit_inode_permission(inode, perms, audited, denied, rc); if (rc2) return rc2; @@ -6850,7 +6840,7 @@ static int selinux_ib_endport_manage_subnet(void *ib_sec, const char *dev_name, return err; ad.type = LSM_AUDIT_DATA_IBENDPORT; - strncpy(ibendport.dev_name, dev_name, sizeof(ibendport.dev_name)); + ibendport.dev_name = dev_name; ibendport.port = port_num; ad.u.ibendport = &ibendport; return avc_has_perm(&selinux_state, diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h index cf4cc3ef959b..00f78be48283 100644 --- a/security/selinux/include/avc.h +++ b/security/selinux/include/avc.h @@ -111,7 +111,6 @@ int slow_avc_audit(struct selinux_state *state, * @avd: access vector decisions * @result: result from avc_has_perm_noaudit * @a: auxiliary audit data - * @flags: VFS walk flags * * Audit the granting or denial of permissions in accordance * with the policy. This function is typically called by @@ -127,16 +126,12 @@ static inline int avc_audit(struct selinux_state *state, u16 tclass, u32 requested, struct av_decision *avd, int result, - struct common_audit_data *a, - int flags) + struct common_audit_data *a) { u32 audited, denied; audited = avc_audit_required(requested, avd, result, 0, &denied); if (likely(!audited)) return 0; - /* fall back to ref-walk if we have to generate audit */ - if (flags & MAY_NOT_BLOCK) - return -ECHILD; return slow_avc_audit(state, ssid, tsid, tclass, requested, audited, denied, result, a); @@ -144,7 +139,6 @@ static inline int avc_audit(struct selinux_state *state, #define AVC_STRICT 1 /* Ignore permissive mode. */ #define AVC_EXTENDED_PERMS 2 /* update extended permissions */ -#define AVC_NONBLOCKING 4 /* non blocking */ int avc_has_perm_noaudit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, @@ -155,11 +149,6 @@ int avc_has_perm(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata); -int avc_has_perm_flags(struct selinux_state *state, - u32 ssid, u32 tsid, - u16 tclass, u32 requested, - struct common_audit_data *auditdata, - int flags); int avc_has_extended_perms(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h index 0a6f34a7a971..74159400eeee 100644 --- a/security/selinux/include/xfrm.h +++ b/security/selinux/include/xfrm.h @@ -23,7 +23,7 @@ int selinux_xfrm_state_alloc_acquire(struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid); void selinux_xfrm_state_free(struct xfrm_state *x); int selinux_xfrm_state_delete(struct xfrm_state *x); -int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir); +int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid); int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic); diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c index 75df32906055..c97695ae508f 100644 --- a/security/selinux/ss/avtab.c +++ b/security/selinux/ss/avtab.c @@ -29,7 +29,7 @@ static struct kmem_cache *avtab_xperms_cachep __ro_after_init; /* Based on MurmurHash3, written by Austin Appleby and placed in the * public domain. */ -static inline int avtab_hash(struct avtab_key *keyp, u32 mask) +static inline int avtab_hash(const struct avtab_key *keyp, u32 mask) { static const u32 c1 = 0xcc9e2d51; static const u32 c2 = 0x1b873593; @@ -68,7 +68,7 @@ static inline int avtab_hash(struct avtab_key *keyp, u32 mask) static struct avtab_node* avtab_insert_node(struct avtab *h, int hvalue, struct avtab_node *prev, struct avtab_node *cur, - struct avtab_key *key, struct avtab_datum *datum) + const struct avtab_key *key, const struct avtab_datum *datum) { struct avtab_node *newnode; struct avtab_extended_perms *xperms; @@ -103,7 +103,8 @@ avtab_insert_node(struct avtab *h, int hvalue, return newnode; } -static int avtab_insert(struct avtab *h, struct avtab_key *key, struct avtab_datum *datum) +static int avtab_insert(struct avtab *h, const struct avtab_key *key, + const struct avtab_datum *datum) { int hvalue; struct avtab_node *prev, *cur, *newnode; @@ -147,8 +148,9 @@ static int avtab_insert(struct avtab *h, struct avtab_key *key, struct avtab_dat * key/specified mask into the table, as needed by the conditional avtab. * It also returns a pointer to the node inserted. */ -struct avtab_node * -avtab_insert_nonunique(struct avtab *h, struct avtab_key *key, struct avtab_datum *datum) +struct avtab_node *avtab_insert_nonunique(struct avtab *h, + const struct avtab_key *key, + const struct avtab_datum *datum) { int hvalue; struct avtab_node *prev, *cur; @@ -178,7 +180,7 @@ avtab_insert_nonunique(struct avtab *h, struct avtab_key *key, struct avtab_datu return avtab_insert_node(h, hvalue, prev, cur, key, datum); } -struct avtab_datum *avtab_search(struct avtab *h, struct avtab_key *key) +struct avtab_datum *avtab_search(struct avtab *h, const struct avtab_key *key) { int hvalue; struct avtab_node *cur; @@ -213,8 +215,8 @@ struct avtab_datum *avtab_search(struct avtab *h, struct avtab_key *key) /* This search function returns a node pointer, and can be used in * conjunction with avtab_search_next_node() */ -struct avtab_node* -avtab_search_node(struct avtab *h, struct avtab_key *key) +struct avtab_node *avtab_search_node(struct avtab *h, + const struct avtab_key *key) { int hvalue; struct avtab_node *cur; @@ -396,8 +398,8 @@ static uint16_t spec_order[] = { }; int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol, - int (*insertf)(struct avtab *a, struct avtab_key *k, - struct avtab_datum *d, void *p), + int (*insertf)(struct avtab *a, const struct avtab_key *k, + const struct avtab_datum *d, void *p), void *p) { __le16 buf16[4]; @@ -557,8 +559,8 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol, return insertf(a, &key, &datum, p); } -static int avtab_insertf(struct avtab *a, struct avtab_key *k, - struct avtab_datum *d, void *p) +static int avtab_insertf(struct avtab *a, const struct avtab_key *k, + const struct avtab_datum *d, void *p) { return avtab_insert(a, k, d); } @@ -607,7 +609,7 @@ bad: goto out; } -int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp) +int avtab_write_item(struct policydb *p, const struct avtab_node *cur, void *fp) { __le16 buf16[4]; __le32 buf32[ARRAY_SIZE(cur->datum.u.xperms->perms.p)]; diff --git a/security/selinux/ss/avtab.h b/security/selinux/ss/avtab.h index f2eeb36265d1..d3ebea8d146f 100644 --- a/security/selinux/ss/avtab.h +++ b/security/selinux/ss/avtab.h @@ -90,24 +90,26 @@ struct avtab { void avtab_init(struct avtab *h); int avtab_alloc(struct avtab *, u32); int avtab_alloc_dup(struct avtab *new, const struct avtab *orig); -struct avtab_datum *avtab_search(struct avtab *h, struct avtab_key *k); +struct avtab_datum *avtab_search(struct avtab *h, const struct avtab_key *k); void avtab_destroy(struct avtab *h); void avtab_hash_eval(struct avtab *h, char *tag); struct policydb; int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol, - int (*insert)(struct avtab *a, struct avtab_key *k, - struct avtab_datum *d, void *p), + int (*insert)(struct avtab *a, const struct avtab_key *k, + const struct avtab_datum *d, void *p), void *p); int avtab_read(struct avtab *a, void *fp, struct policydb *pol); -int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp); +int avtab_write_item(struct policydb *p, const struct avtab_node *cur, void *fp); int avtab_write(struct policydb *p, struct avtab *a, void *fp); -struct avtab_node *avtab_insert_nonunique(struct avtab *h, struct avtab_key *key, - struct avtab_datum *datum); +struct avtab_node *avtab_insert_nonunique(struct avtab *h, + const struct avtab_key *key, + const struct avtab_datum *datum); -struct avtab_node *avtab_search_node(struct avtab *h, struct avtab_key *key); +struct avtab_node *avtab_search_node(struct avtab *h, + const struct avtab_key *key); struct avtab_node *avtab_search_node_next(struct avtab_node *node, int specified); diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c index 1ef74c085f2b..2ec6e5cd25d9 100644 --- a/security/selinux/ss/conditional.c +++ b/security/selinux/ss/conditional.c @@ -254,7 +254,8 @@ struct cond_insertf_data { struct cond_av_list *other; }; -static int cond_insertf(struct avtab *a, struct avtab_key *k, struct avtab_datum *d, void *ptr) +static int cond_insertf(struct avtab *a, const struct avtab_key *k, + const struct avtab_datum *d, void *ptr) { struct cond_insertf_data *data = ptr; struct policydb *p = data->p; @@ -628,7 +629,8 @@ static int cond_dup_av_list(struct cond_av_list *new, static int duplicate_policydb_cond_list(struct policydb *newp, struct policydb *origp) { - int rc, i, j; + int rc; + u32 i; rc = avtab_alloc_dup(&newp->te_cond_avtab, &origp->te_cond_avtab); if (rc) @@ -648,12 +650,12 @@ static int duplicate_policydb_cond_list(struct policydb *newp, newp->cond_list_len++; newn->cur_state = orign->cur_state; - newn->expr.nodes = kcalloc(orign->expr.len, - sizeof(*newn->expr.nodes), GFP_KERNEL); + newn->expr.nodes = kmemdup(orign->expr.nodes, + orign->expr.len * sizeof(*orign->expr.nodes), + GFP_KERNEL); if (!newn->expr.nodes) goto error; - for (j = 0; j < orign->expr.len; j++) - newn->expr.nodes[j] = orign->expr.nodes[j]; + newn->expr.len = orign->expr.len; rc = cond_dup_av_list(&newn->true_list, &orign->true_list, diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index 572370c71af5..61a571abeec7 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -2597,7 +2597,6 @@ int policydb_read(struct policydb *p, void *fp) if (rc) goto bad; - rc = -EINVAL; rtk->role = le32_to_cpu(buf[0]); rtk->type = le32_to_cpu(buf[1]); rtd->new_role = le32_to_cpu(buf[2]); diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 111a59c07bed..097a0e8593c8 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -859,6 +859,7 @@ int security_validate_transition(struct selinux_state *state, * It returns 0, if @newsid is bounded by @oldsid. * Otherwise, it returns error code. * + * @state: SELinux state * @oldsid : current security identifier * @newsid : destinated security identifier */ @@ -1098,6 +1099,7 @@ allow: /** * security_compute_av - Compute access vector decisions. + * @state: SELinux state * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class @@ -1386,6 +1388,7 @@ out_unlock: /** * security_sid_to_context - Obtain a context for a given SID. + * @state: SELinux state * @sid: security identifier, SID * @scontext: security context * @scontext_len: length in bytes @@ -1411,6 +1414,7 @@ int security_sid_to_context_force(struct selinux_state *state, u32 sid, /** * security_sid_to_context_inval - Obtain a context for a given SID if it * is invalid. + * @state: SELinux state * @sid: security identifier, SID * @scontext: security context * @scontext_len: length in bytes @@ -1587,6 +1591,7 @@ out: /** * security_context_to_sid - Obtain a SID for a given security context. + * @state: SELinux state * @scontext: security context * @scontext_len: length in bytes * @sid: security identifier, SID @@ -1616,6 +1621,7 @@ int security_context_str_to_sid(struct selinux_state *state, * security_context_to_sid_default - Obtain a SID for a given security context, * falling back to specified default if needed. * + * @state: SELinux state * @scontext: security context * @scontext_len: length in bytes * @sid: security identifier, SID @@ -1907,6 +1913,7 @@ out: /** * security_transition_sid - Compute the SID for a new subject/object. + * @state: SELinux state * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class @@ -1962,6 +1969,7 @@ int security_member_sid(struct selinux_state *state, /** * security_change_sid - Compute the SID for object relabeling. + * @state: SELinux state * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class @@ -2060,7 +2068,6 @@ static int convert_context(struct context *oldc, struct context *newc, void *p) context_init(newc); /* Convert the user. */ - rc = -EINVAL; usrdatum = symtab_search(&args->newp->p_users, sym_name(args->oldp, SYM_USERS, oldc->user - 1)); @@ -2069,7 +2076,6 @@ static int convert_context(struct context *oldc, struct context *newc, void *p) newc->user = usrdatum->value; /* Convert the role. */ - rc = -EINVAL; role = symtab_search(&args->newp->p_roles, sym_name(args->oldp, SYM_ROLES, oldc->role - 1)); if (!role) @@ -2077,7 +2083,6 @@ static int convert_context(struct context *oldc, struct context *newc, void *p) newc->role = role->value; /* Convert the type. */ - rc = -EINVAL; typdatum = symtab_search(&args->newp->p_types, sym_name(args->oldp, SYM_TYPES, oldc->type - 1)); @@ -2101,7 +2106,6 @@ static int convert_context(struct context *oldc, struct context *newc, void *p) oc = args->newp->ocontexts[OCON_ISID]; while (oc && oc->sid[0] != SECINITSID_UNLABELED) oc = oc->next; - rc = -EINVAL; if (!oc) { pr_err("SELinux: unable to look up" " the initial SIDs list\n"); @@ -2268,6 +2272,7 @@ void selinux_policy_commit(struct selinux_state *state, /** * security_load_policy - Load a security policy configuration. + * @state: SELinux state * @data: binary policy data * @len: length of data in bytes * @@ -2375,6 +2380,7 @@ err_policy: /** * security_port_sid - Obtain the SID for a port. + * @state: SELinux state * @protocol: protocol number * @port: port number * @out_sid: security identifier @@ -2431,7 +2437,8 @@ out: } /** - * security_pkey_sid - Obtain the SID for a pkey. + * security_ib_pkey_sid - Obtain the SID for a pkey. + * @state: SELinux state * @subnet_prefix: Subnet Prefix * @pkey_num: pkey number * @out_sid: security identifier @@ -2490,6 +2497,7 @@ out: /** * security_ib_endport_sid - Obtain the SID for a subnet management interface. + * @state: SELinux state * @dev_name: device name * @port: port number * @out_sid: security identifier @@ -2548,6 +2556,7 @@ out: /** * security_netif_sid - Obtain the SID for a network interface. + * @state: SELinux state * @name: interface name * @if_sid: interface SID */ @@ -2622,6 +2631,7 @@ static int match_ipv6_addrmask(u32 *input, u32 *addr, u32 *mask) /** * security_node_sid - Obtain the SID for a node (host). + * @state: SELinux state * @domain: communication domain aka address family * @addrp: address * @addrlen: address length in bytes @@ -2715,6 +2725,7 @@ out: /** * security_get_user_sids - Obtain reachable SIDs for a user. + * @state: SELinux state * @fromsid: starting SID * @username: username * @sids: array of reachable SIDs for user @@ -2907,6 +2918,7 @@ out: /** * security_genfs_sid - Obtain a SID for a file in a filesystem + * @state: SELinux state * @fstype: filesystem type * @path: path from root of mount * @sclass: file security class @@ -2951,6 +2963,7 @@ int selinux_policy_genfs_sid(struct selinux_policy *policy, /** * security_fs_use - Determine how to handle labeling for a filesystem. + * @state: SELinux state * @sb: superblock in question */ int security_fs_use(struct selinux_state *state, struct super_block *sb) @@ -3290,6 +3303,7 @@ out_unlock: /** * security_net_peersid_resolve - Compare and resolve two network peer SIDs + * @state: SELinux state * @nlbl_sid: NetLabel SID * @nlbl_type: NetLabel labeling protocol type * @xfrm_sid: XFRM SID @@ -3514,6 +3528,7 @@ int security_get_allow_unknown(struct selinux_state *state) /** * security_policycap_supported - Check for a specific policy capability + * @state: SELinux state * @req_cap: capability * * Description: @@ -3848,6 +3863,7 @@ static void security_netlbl_cache_add(struct netlbl_lsm_secattr *secattr, /** * security_netlbl_secattr_to_sid - Convert a NetLabel secattr to a SELinux SID + * @state: SELinux state * @secattr: the NetLabel packet security attributes * @sid: the SELinux SID * @@ -3930,6 +3946,7 @@ out: /** * security_netlbl_sid_to_secattr - Convert a SELinux SID to a NetLabel secattr + * @state: SELinux state * @sid: the SELinux SID * @secattr: the NetLabel packet security attributes * diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c index 634f3db24da6..be83e5ce4469 100644 --- a/security/selinux/xfrm.c +++ b/security/selinux/xfrm.c @@ -150,7 +150,7 @@ static int selinux_xfrm_delete(struct xfrm_sec_ctx *ctx) * LSM hook implementation that authorizes that a flow can use a xfrm policy * rule. */ -int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir) +int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid) { int rc; diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c index 7eabb448acab..1f391f6a3d47 100644 --- a/security/smack/smack_access.c +++ b/security/smack/smack_access.c @@ -332,7 +332,7 @@ static void smack_log_callback(struct audit_buffer *ab, void *a) * @object_label : smack label of the object being accessed * @request: requested permissions * @result: result from smk_access - * @a: auxiliary audit data + * @ad: auxiliary audit data * * Audit the granting or denial of permissions in accordance * with the policy. @@ -396,6 +396,7 @@ struct hlist_head smack_known_hash[SMACK_HASH_SLOTS]; /** * smk_insert_entry - insert a smack label into a hash map, + * @skp: smack label * * this function must be called under smack_known_lock */ @@ -476,8 +477,10 @@ char *smk_parse_smack(const char *string, int len) /** * smk_netlbl_mls - convert a catset to netlabel mls categories + * @level: MLS sensitivity level * @catset: the Smack categories * @sap: where to put the netlabel categories + * @len: number of bytes for the levels in a CIPSO IP option * * Allocates and fills attr.mls * Returns 0 on success, error code on failure. @@ -688,10 +691,9 @@ bool smack_privileged_cred(int cap, const struct cred *cred) bool smack_privileged(int cap) { /* - * Kernel threads may not have credentials we can use. - * The io_uring kernel threads do have reliable credentials. + * All kernel tasks are privileged */ - if ((current->flags & (PF_KTHREAD | PF_IO_WORKER)) == PF_KTHREAD) + if (unlikely(current->flags & PF_KTHREAD)) return true; return smack_privileged_cred(cap, current_cred()); diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index 22ded2c26089..3a75d2a8f517 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -380,7 +380,7 @@ static int smk_parse_rule(const char *data, struct smack_parsed_rule *rule, * @data: string to be parsed, null terminated * @rule: Will be filled with Smack parsed rule * @import: if non-zero, import labels - * @tokens: numer of substrings expected in data + * @tokens: number of substrings expected in data * * Returns number of processed bytes on success, -ERRNO on failure. */ @@ -855,6 +855,8 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf, if (format == SMK_FIXED24_FMT && (count < SMK_CIPSOMIN || count > SMK_CIPSOMAX)) return -EINVAL; + if (count > PAGE_SIZE) + return -EINVAL; data = memdup_user_nul(buf, count); if (IS_ERR(data)) diff --git a/tools/arch/x86/include/asm/irq_vectors.h b/tools/arch/x86/include/asm/irq_vectors.h index 889f8b1b5b7f..43dcb9284208 100644 --- a/tools/arch/x86/include/asm/irq_vectors.h +++ b/tools/arch/x86/include/asm/irq_vectors.h @@ -26,8 +26,8 @@ * This file enumerates the exact layout of them: */ +/* This is used as an interrupt vector when programming the APIC. */ #define NMI_VECTOR 0x02 -#define MCE_VECTOR 0x12 /* * IDT vectors usable for external interrupt sources start at 0x20. @@ -84,7 +84,7 @@ */ #define IRQ_WORK_VECTOR 0xf6 -#define UV_BAU_MESSAGE 0xf5 +/* 0xf5 - unused, was UV_BAU_MESSAGE */ #define DEFERRED_ERROR_VECTOR 0xf4 /* Vector on which hypervisor callbacks will be delivered */ @@ -114,6 +114,9 @@ #define FIRST_SYSTEM_VECTOR NR_VECTORS #endif +#define NR_EXTERNAL_VECTORS (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) +#define NR_SYSTEM_VECTORS (NR_VECTORS - FIRST_SYSTEM_VECTOR) + /* * Size the maximum number of interrupts. * diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index b3073ae84018..d73232be1e99 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -136,7 +136,7 @@ endif BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool -BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o) +BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o) OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ @@ -180,6 +180,9 @@ endif CFLAGS += $(if $(BUILD_BPF_SKELS),,-DBPFTOOL_WITHOUT_SKELETONS) +$(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c + $(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD -o $@ $< + $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c $(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $< diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 31ade77f5ef8..1d71ff8c52fa 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "json_writer.h" #include "main.h" @@ -106,8 +107,10 @@ static int codegen_datasec_def(struct bpf_object *obj, if (strcmp(sec_name, ".data") == 0) { sec_ident = "data"; + strip_mods = true; } else if (strcmp(sec_name, ".bss") == 0) { sec_ident = "bss"; + strip_mods = true; } else if (strcmp(sec_name, ".rodata") == 0) { sec_ident = "rodata"; strip_mods = true; @@ -129,6 +132,10 @@ static int codegen_datasec_def(struct bpf_object *obj, int need_off = sec_var->offset, align_off, align; __u32 var_type_id = var->type; + /* static variables are not exposed through BPF skeleton */ + if (btf_var(var)->linkage == BTF_VAR_STATIC) + continue; + if (off > need_off) { p_err("Something is wrong for %s's variable #%d: need offset %d, already at %d.\n", sec_name, i, need_off, off); @@ -268,6 +275,327 @@ static void codegen(const char *template, ...) free(s); } +static void print_hex(const char *data, int data_sz) +{ + int i, len; + + for (i = 0, len = 0; i < data_sz; i++) { + int w = data[i] ? 4 : 2; + + len += w; + if (len > 78) { + printf("\\\n"); + len = w; + } + if (!data[i]) + printf("\\0"); + else + printf("\\x%02x", (unsigned char)data[i]); + } +} + +static size_t bpf_map_mmap_sz(const struct bpf_map *map) +{ + long page_sz = sysconf(_SC_PAGE_SIZE); + size_t map_sz; + + map_sz = (size_t)roundup(bpf_map__value_size(map), 8) * bpf_map__max_entries(map); + map_sz = roundup(map_sz, page_sz); + return map_sz; +} + +static void codegen_attach_detach(struct bpf_object *obj, const char *obj_name) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + const char *tp_name; + + codegen("\ + \n\ + \n\ + static inline int \n\ + %1$s__%2$s__attach(struct %1$s *skel) \n\ + { \n\ + int prog_fd = skel->progs.%2$s.prog_fd; \n\ + ", obj_name, bpf_program__name(prog)); + + switch (bpf_program__get_type(prog)) { + case BPF_PROG_TYPE_RAW_TRACEPOINT: + tp_name = strchr(bpf_program__section_name(prog), '/') + 1; + printf("\tint fd = bpf_raw_tracepoint_open(\"%s\", prog_fd);\n", tp_name); + break; + case BPF_PROG_TYPE_TRACING: + printf("\tint fd = bpf_raw_tracepoint_open(NULL, prog_fd);\n"); + break; + default: + printf("\tint fd = ((void)prog_fd, 0); /* auto-attach not supported */\n"); + break; + } + codegen("\ + \n\ + \n\ + if (fd > 0) \n\ + skel->links.%1$s_fd = fd; \n\ + return fd; \n\ + } \n\ + ", bpf_program__name(prog)); + } + + codegen("\ + \n\ + \n\ + static inline int \n\ + %1$s__attach(struct %1$s *skel) \n\ + { \n\ + int ret = 0; \n\ + \n\ + ", obj_name); + + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + ret = ret < 0 ? ret : %1$s__%2$s__attach(skel); \n\ + ", obj_name, bpf_program__name(prog)); + } + + codegen("\ + \n\ + return ret < 0 ? ret : 0; \n\ + } \n\ + \n\ + static inline void \n\ + %1$s__detach(struct %1$s *skel) \n\ + { \n\ + ", obj_name); + + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + skel_closenz(skel->links.%1$s_fd); \n\ + ", bpf_program__name(prog)); + } + + codegen("\ + \n\ + } \n\ + "); +} + +static void codegen_destroy(struct bpf_object *obj, const char *obj_name) +{ + struct bpf_program *prog; + struct bpf_map *map; + + codegen("\ + \n\ + static void \n\ + %1$s__destroy(struct %1$s *skel) \n\ + { \n\ + if (!skel) \n\ + return; \n\ + %1$s__detach(skel); \n\ + ", + obj_name); + + bpf_object__for_each_program(prog, obj) { + codegen("\ + \n\ + skel_closenz(skel->progs.%1$s.prog_fd); \n\ + ", bpf_program__name(prog)); + } + + bpf_object__for_each_map(map, obj) { + const char * ident; + + ident = get_map_ident(map); + if (!ident) + continue; + if (bpf_map__is_internal(map) && + (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + printf("\tmunmap(skel->%1$s, %2$zd);\n", + ident, bpf_map_mmap_sz(map)); + codegen("\ + \n\ + skel_closenz(skel->maps.%1$s.map_fd); \n\ + ", ident); + } + codegen("\ + \n\ + free(skel); \n\ + } \n\ + ", + obj_name); +} + +static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *header_guard) +{ + struct bpf_object_load_attr load_attr = {}; + DECLARE_LIBBPF_OPTS(gen_loader_opts, opts); + struct bpf_map *map; + int err = 0; + + err = bpf_object__gen_loader(obj, &opts); + if (err) + return err; + + load_attr.obj = obj; + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + load_attr.log_level = 1 + 2 + 4; + + err = bpf_object__load_xattr(&load_attr); + if (err) { + p_err("failed to load object file"); + goto out; + } + /* If there was no error during load then gen_loader_opts + * are populated with the loader program. + */ + + /* finish generating 'struct skel' */ + codegen("\ + \n\ + }; \n\ + ", obj_name); + + + codegen_attach_detach(obj, obj_name); + + codegen_destroy(obj, obj_name); + + codegen("\ + \n\ + static inline struct %1$s * \n\ + %1$s__open(void) \n\ + { \n\ + struct %1$s *skel; \n\ + \n\ + skel = calloc(sizeof(*skel), 1); \n\ + if (!skel) \n\ + goto cleanup; \n\ + skel->ctx.sz = (void *)&skel->links - (void *)skel; \n\ + ", + obj_name, opts.data_sz); + bpf_object__for_each_map(map, obj) { + const char *ident; + const void *mmap_data = NULL; + size_t mmap_size = 0; + + ident = get_map_ident(map); + if (!ident) + continue; + + if (!bpf_map__is_internal(map) || + !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + continue; + + codegen("\ + \n\ + skel->%1$s = \n\ + mmap(NULL, %2$zd, PROT_READ | PROT_WRITE,\n\ + MAP_SHARED | MAP_ANONYMOUS, -1, 0); \n\ + if (skel->%1$s == (void *) -1) \n\ + goto cleanup; \n\ + memcpy(skel->%1$s, (void *)\"\\ \n\ + ", ident, bpf_map_mmap_sz(map)); + mmap_data = bpf_map__initial_value(map, &mmap_size); + print_hex(mmap_data, mmap_size); + printf("\", %2$zd);\n" + "\tskel->maps.%1$s.initial_value = (__u64)(long)skel->%1$s;\n", + ident, mmap_size); + } + codegen("\ + \n\ + return skel; \n\ + cleanup: \n\ + %1$s__destroy(skel); \n\ + return NULL; \n\ + } \n\ + \n\ + static inline int \n\ + %1$s__load(struct %1$s *skel) \n\ + { \n\ + struct bpf_load_and_run_opts opts = {}; \n\ + int err; \n\ + \n\ + opts.ctx = (struct bpf_loader_ctx *)skel; \n\ + opts.data_sz = %2$d; \n\ + opts.data = (void *)\"\\ \n\ + ", + obj_name, opts.data_sz); + print_hex(opts.data, opts.data_sz); + codegen("\ + \n\ + \"; \n\ + "); + + codegen("\ + \n\ + opts.insns_sz = %d; \n\ + opts.insns = (void *)\"\\ \n\ + ", + opts.insns_sz); + print_hex(opts.insns, opts.insns_sz); + codegen("\ + \n\ + \"; \n\ + err = bpf_load_and_run(&opts); \n\ + if (err < 0) \n\ + return err; \n\ + ", obj_name); + bpf_object__for_each_map(map, obj) { + const char *ident, *mmap_flags; + + ident = get_map_ident(map); + if (!ident) + continue; + + if (!bpf_map__is_internal(map) || + !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE)) + continue; + if (bpf_map__def(map)->map_flags & BPF_F_RDONLY_PROG) + mmap_flags = "PROT_READ"; + else + mmap_flags = "PROT_READ | PROT_WRITE"; + + printf("\tskel->%1$s =\n" + "\t\tmmap(skel->%1$s, %2$zd, %3$s, MAP_SHARED | MAP_FIXED,\n" + "\t\t\tskel->maps.%1$s.map_fd, 0);\n", + ident, bpf_map_mmap_sz(map), mmap_flags); + } + codegen("\ + \n\ + return 0; \n\ + } \n\ + \n\ + static inline struct %1$s * \n\ + %1$s__open_and_load(void) \n\ + { \n\ + struct %1$s *skel; \n\ + \n\ + skel = %1$s__open(); \n\ + if (!skel) \n\ + return NULL; \n\ + if (%1$s__load(skel)) { \n\ + %1$s__destroy(skel); \n\ + return NULL; \n\ + } \n\ + return skel; \n\ + } \n\ + ", obj_name); + + codegen("\ + \n\ + \n\ + #endif /* %s */ \n\ + ", + header_guard); + err = 0; +out: + return err; +} + static int do_skeleton(int argc, char **argv) { char header_guard[MAX_OBJ_NAME_LEN + sizeof("__SKEL_H__")]; @@ -277,7 +605,7 @@ static int do_skeleton(int argc, char **argv) struct bpf_object *obj = NULL; const char *file, *ident; struct bpf_program *prog; - int fd, len, err = -1; + int fd, err = -1; struct bpf_map *map; struct btf *btf; struct stat st; @@ -359,7 +687,25 @@ static int do_skeleton(int argc, char **argv) } get_header_guard(header_guard, obj_name); - codegen("\ + if (use_loader) { + codegen("\ + \n\ + /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ + /* THIS FILE IS AUTOGENERATED! */ \n\ + #ifndef %2$s \n\ + #define %2$s \n\ + \n\ + #include \n\ + #include \n\ + #include \n\ + \n\ + struct %1$s { \n\ + struct bpf_loader_ctx ctx; \n\ + ", + obj_name, header_guard + ); + } else { + codegen("\ \n\ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ \n\ \n\ @@ -367,6 +713,7 @@ static int do_skeleton(int argc, char **argv) #ifndef %2$s \n\ #define %2$s \n\ \n\ + #include \n\ #include \n\ #include \n\ \n\ @@ -375,7 +722,8 @@ static int do_skeleton(int argc, char **argv) struct bpf_object *obj; \n\ ", obj_name, header_guard - ); + ); + } if (map_cnt) { printf("\tstruct {\n"); @@ -383,7 +731,10 @@ static int do_skeleton(int argc, char **argv) ident = get_map_ident(map); if (!ident) continue; - printf("\t\tstruct bpf_map *%s;\n", ident); + if (use_loader) + printf("\t\tstruct bpf_map_desc %s;\n", ident); + else + printf("\t\tstruct bpf_map *%s;\n", ident); } printf("\t} maps;\n"); } @@ -391,14 +742,22 @@ static int do_skeleton(int argc, char **argv) if (prog_cnt) { printf("\tstruct {\n"); bpf_object__for_each_program(prog, obj) { - printf("\t\tstruct bpf_program *%s;\n", - bpf_program__name(prog)); + if (use_loader) + printf("\t\tstruct bpf_prog_desc %s;\n", + bpf_program__name(prog)); + else + printf("\t\tstruct bpf_program *%s;\n", + bpf_program__name(prog)); } printf("\t} progs;\n"); printf("\tstruct {\n"); bpf_object__for_each_program(prog, obj) { - printf("\t\tstruct bpf_link *%s;\n", - bpf_program__name(prog)); + if (use_loader) + printf("\t\tint %s_fd;\n", + bpf_program__name(prog)); + else + printf("\t\tstruct bpf_link *%s;\n", + bpf_program__name(prog)); } printf("\t} links;\n"); } @@ -409,6 +768,10 @@ static int do_skeleton(int argc, char **argv) if (err) goto out; } + if (use_loader) { + err = gen_trace(obj, obj_name, header_guard); + goto out; + } codegen("\ \n\ @@ -431,18 +794,23 @@ static int do_skeleton(int argc, char **argv) %1$s__open_opts(const struct bpf_object_open_opts *opts) \n\ { \n\ struct %1$s *obj; \n\ + int err; \n\ \n\ obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ - if (!obj) \n\ + if (!obj) { \n\ + errno = ENOMEM; \n\ return NULL; \n\ - if (%1$s__create_skeleton(obj)) \n\ - goto err; \n\ - if (bpf_object__open_skeleton(obj->skeleton, opts)) \n\ - goto err; \n\ + } \n\ + \n\ + err = %1$s__create_skeleton(obj); \n\ + err = err ?: bpf_object__open_skeleton(obj->skeleton, opts);\n\ + if (err) \n\ + goto err_out; \n\ \n\ return obj; \n\ - err: \n\ + err_out: \n\ %1$s__destroy(obj); \n\ + errno = -err; \n\ return NULL; \n\ } \n\ \n\ @@ -462,12 +830,15 @@ static int do_skeleton(int argc, char **argv) %1$s__open_and_load(void) \n\ { \n\ struct %1$s *obj; \n\ + int err; \n\ \n\ obj = %1$s__open(); \n\ if (!obj) \n\ return NULL; \n\ - if (%1$s__load(obj)) { \n\ + err = %1$s__load(obj); \n\ + if (err) { \n\ %1$s__destroy(obj); \n\ + errno = -err; \n\ return NULL; \n\ } \n\ return obj; \n\ @@ -498,7 +869,7 @@ static int do_skeleton(int argc, char **argv) \n\ s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ if (!s) \n\ - return -1; \n\ + goto err; \n\ obj->skeleton = s; \n\ \n\ s->sz = sizeof(*s); \n\ @@ -578,19 +949,7 @@ static int do_skeleton(int argc, char **argv) file_sz); /* embed contents of BPF object file */ - for (i = 0, len = 0; i < file_sz; i++) { - int w = obj_data[i] ? 4 : 2; - - len += w; - if (len > 78) { - printf("\\\n"); - len = w; - } - if (!obj_data[i]) - printf("\\0"); - else - printf("\\x%02x", (unsigned char)obj_data[i]); - } + print_hex(obj_data, file_sz); codegen("\ \n\ @@ -599,7 +958,7 @@ static int do_skeleton(int argc, char **argv) return 0; \n\ err: \n\ bpf_object__destroy_skeleton(s); \n\ - return -1; \n\ + return -ENOMEM; \n\ } \n\ \n\ #endif /* %s */ \n\ @@ -636,7 +995,7 @@ static int do_object(int argc, char **argv) while (argc) { file = GET_ARG(); - err = bpf_linker__add_file(linker, file); + err = bpf_linker__add_file(linker, file, NULL); if (err) { p_err("failed to link '%s': %s (%d)", file, strerror(err), err); goto out; diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index d9afb730136a..3ddfd4843738 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -29,6 +29,7 @@ bool show_pinned; bool block_mount; bool verifier_logs; bool relaxed_maps; +bool use_loader; struct btf *base_btf; struct pinned_obj_table prog_table; struct pinned_obj_table map_table; @@ -340,8 +341,10 @@ static int do_batch(int argc, char **argv) n_argc = make_args(buf, n_argv, BATCH_ARG_NB_MAX, lines); if (!n_argc) continue; - if (n_argc < 0) + if (n_argc < 0) { + err = n_argc; goto err_close; + } if (json_output) { jsonw_start_object(json_wtr); @@ -392,6 +395,7 @@ int main(int argc, char **argv) { "mapcompat", no_argument, NULL, 'm' }, { "nomount", no_argument, NULL, 'n' }, { "debug", no_argument, NULL, 'd' }, + { "use-loader", no_argument, NULL, 'L' }, { "base-btf", required_argument, NULL, 'B' }, { 0 } }; @@ -409,7 +413,7 @@ int main(int argc, char **argv) hash_init(link_table.table); opterr = 0; - while ((opt = getopt_long(argc, argv, "VhpjfmndB:", + while ((opt = getopt_long(argc, argv, "VhpjfLmndB:", options, NULL)) >= 0) { switch (opt) { case 'V': @@ -452,6 +456,9 @@ int main(int argc, char **argv) return -1; } break; + case 'L': + use_loader = true; + break; default: p_err("unrecognized option '%s'", argv[optind - 1]); if (json_output) diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 76e91641262b..c1cf29798b99 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -90,6 +90,7 @@ extern bool show_pids; extern bool block_mount; extern bool verifier_logs; extern bool relaxed_maps; +extern bool use_loader; extern struct btf *base_btf; extern struct pinned_obj_table prog_table; extern struct pinned_obj_table map_table; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index da4846c9856a..cc48726740ad 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -24,6 +25,8 @@ #include #include #include +#include +#include #include "cfg.h" #include "main.h" @@ -1499,7 +1502,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) set_max_rlimit(); obj = bpf_object__open_file(file, &open_opts); - if (IS_ERR_OR_NULL(obj)) { + if (libbpf_get_error(obj)) { p_err("failed to open object file"); goto err_free_reuse_maps; } @@ -1645,8 +1648,110 @@ err_free_reuse_maps: return -1; } +static int count_open_fds(void) +{ + DIR *dp = opendir("/proc/self/fd"); + struct dirent *de; + int cnt = -3; + + if (!dp) + return -1; + + while ((de = readdir(dp))) + cnt++; + + closedir(dp); + return cnt; +} + +static int try_loader(struct gen_loader_opts *gen) +{ + struct bpf_load_and_run_opts opts = {}; + struct bpf_loader_ctx *ctx; + int ctx_sz = sizeof(*ctx) + 64 * max(sizeof(struct bpf_map_desc), + sizeof(struct bpf_prog_desc)); + int log_buf_sz = (1u << 24) - 1; + int err, fds_before, fd_delta; + char *log_buf; + + ctx = alloca(ctx_sz); + memset(ctx, 0, ctx_sz); + ctx->sz = ctx_sz; + ctx->log_level = 1; + ctx->log_size = log_buf_sz; + log_buf = malloc(log_buf_sz); + if (!log_buf) + return -ENOMEM; + ctx->log_buf = (long) log_buf; + opts.ctx = ctx; + opts.data = gen->data; + opts.data_sz = gen->data_sz; + opts.insns = gen->insns; + opts.insns_sz = gen->insns_sz; + fds_before = count_open_fds(); + err = bpf_load_and_run(&opts); + fd_delta = count_open_fds() - fds_before; + if (err < 0) { + fprintf(stderr, "err %d\n%s\n%s", err, opts.errstr, log_buf); + if (fd_delta) + fprintf(stderr, "loader prog leaked %d FDs\n", + fd_delta); + } + free(log_buf); + return err; +} + +static int do_loader(int argc, char **argv) +{ + DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts); + DECLARE_LIBBPF_OPTS(gen_loader_opts, gen); + struct bpf_object_load_attr load_attr = {}; + struct bpf_object *obj; + const char *file; + int err = 0; + + if (!REQ_ARGS(1)) + return -1; + file = GET_ARG(); + + obj = bpf_object__open_file(file, &open_opts); + if (libbpf_get_error(obj)) { + p_err("failed to open object file"); + goto err_close_obj; + } + + err = bpf_object__gen_loader(obj, &gen); + if (err) + goto err_close_obj; + + load_attr.obj = obj; + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + load_attr.log_level = 1 + 2 + 4; + + err = bpf_object__load_xattr(&load_attr); + if (err) { + p_err("failed to load object file"); + goto err_close_obj; + } + + if (verifier_logs) { + struct dump_data dd = {}; + + kernel_syms_load(&dd); + dump_xlated_plain(&dd, (void *)gen.insns, gen.insns_sz, false, false); + kernel_syms_destroy(&dd); + } + err = try_loader(&gen); +err_close_obj: + bpf_object__close(obj); + return err; +} + static int do_load(int argc, char **argv) { + if (use_loader) + return do_loader(argc, argv); return load_with_options(argc, argv, true); } diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c index 6fc3e6f7f40c..f1f32e21d5cd 100644 --- a/tools/bpf/bpftool/xlated_dumper.c +++ b/tools/bpf/bpftool/xlated_dumper.c @@ -196,6 +196,9 @@ static const char *print_imm(void *private_data, else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm); + else if (insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "map[idx:%u]+%u", insn->imm, (insn + 1)->imm); else if (insn->src_reg == BPF_PSEUDO_FUNC) snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), "subprog[%+d]", insn->imm); diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index 7550fd9c3188..3ad9301b0f00 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -655,6 +655,9 @@ static int symbols_patch(struct object *obj) if (sets_patch(obj)) return -1; + /* Set type to ensure endian translation occurs. */ + obj->efile.idlist->d_type = ELF_T_WORD; + elf_flagdata(obj->efile.idlist, ELF_C_SET, ELF_F_DIRTY); err = elf_update(obj->efile.elf, ELF_C_WRITE); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ec6d85a81744..bf9252c7381e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -527,6 +527,15 @@ union bpf_iter_link_info { * Look up an element with the given *key* in the map referred to * by the file descriptor *fd*, and if found, delete the element. * + * For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map + * types, the *flags* argument needs to be set to 0, but for other + * map types, it may be specified as: + * + * **BPF_F_LOCK** + * Look up and delete the value of a spin-locked map + * without returning the lock. This must be specified if + * the elements contain a spinlock. + * * The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types * implement this command as a "pop" operation, deleting the top * element rather than one corresponding to *key*. @@ -536,6 +545,10 @@ union bpf_iter_link_info { * This command is only valid for the following map types: * * **BPF_MAP_TYPE_QUEUE** * * **BPF_MAP_TYPE_STACK** + * * **BPF_MAP_TYPE_HASH** + * * **BPF_MAP_TYPE_PERCPU_HASH** + * * **BPF_MAP_TYPE_LRU_HASH** + * * **BPF_MAP_TYPE_LRU_PERCPU_HASH** * * Return * Returns zero on success. On error, -1 is returned and *errno* @@ -837,6 +850,7 @@ enum bpf_cmd { BPF_PROG_ATTACH, BPF_PROG_DETACH, BPF_PROG_TEST_RUN, + BPF_PROG_RUN = BPF_PROG_TEST_RUN, BPF_PROG_GET_NEXT_ID, BPF_MAP_GET_NEXT_ID, BPF_PROG_GET_FD_BY_ID, @@ -937,6 +951,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_EXT, BPF_PROG_TYPE_LSM, BPF_PROG_TYPE_SK_LOOKUP, + BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ }; enum bpf_attach_type { @@ -979,6 +994,8 @@ enum bpf_attach_type { BPF_SK_LOOKUP, BPF_XDP, BPF_SK_SKB_VERDICT, + BPF_SK_REUSEPORT_SELECT, + BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, __MAX_BPF_ATTACH_TYPE }; @@ -1097,8 +1114,8 @@ enum bpf_link_type { /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * the following extensions: * - * insn[0].src_reg: BPF_PSEUDO_MAP_FD - * insn[0].imm: map fd + * insn[0].src_reg: BPF_PSEUDO_MAP_[FD|IDX] + * insn[0].imm: map fd or fd_idx * insn[1].imm: 0 * insn[0].off: 0 * insn[1].off: 0 @@ -1106,15 +1123,19 @@ enum bpf_link_type { * verifier type: CONST_PTR_TO_MAP */ #define BPF_PSEUDO_MAP_FD 1 -/* insn[0].src_reg: BPF_PSEUDO_MAP_VALUE - * insn[0].imm: map fd +#define BPF_PSEUDO_MAP_IDX 5 + +/* insn[0].src_reg: BPF_PSEUDO_MAP_[IDX_]VALUE + * insn[0].imm: map fd or fd_idx * insn[1].imm: offset into value * insn[0].off: 0 * insn[1].off: 0 * ldimm64 rewrite: address of map[0]+offset * verifier type: PTR_TO_MAP_VALUE */ -#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_IDX_VALUE 6 + /* insn[0].src_reg: BPF_PSEUDO_BTF_ID * insn[0].imm: kernel btd id of VAR * insn[1].imm: 0 @@ -1314,6 +1335,8 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; + __u32 :32; /* pad */ + __aligned_u64 fd_array; /* array of FDs */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -2534,8 +2557,12 @@ union bpf_attr { * The lower two bits of *flags* are used as the return code if * the map lookup fails. This is so that the return value can be * one of the XDP program return codes up to **XDP_TX**, as chosen - * by the caller. Any higher bits in the *flags* argument must be - * unset. + * by the caller. The higher bits of *flags* can be set to + * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below. + * + * With BPF_F_BROADCAST the packet will be broadcasted to all the + * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress + * interface will be excluded when do broadcasting. * * See also **bpf_redirect**\ (), which only supports redirecting * to an ifindex, but doesn't require a map to do so. @@ -4735,6 +4762,24 @@ union bpf_attr { * be zero-terminated except when **str_size** is 0. * * Or **-EBUSY** if the per-CPU memory copy buffer is busy. + * + * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size) + * Description + * Execute bpf syscall with given arguments. + * Return + * A syscall result. + * + * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags) + * Description + * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs. + * Return + * Returns btf_id and btf_obj_fd in lower and upper 32 bits. + * + * long bpf_sys_close(u32 fd) + * Description + * Execute close syscall for given FD. + * Return + * A syscall result. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4903,6 +4948,9 @@ union bpf_attr { FN(check_mtu), \ FN(for_each_map_elem), \ FN(snprintf), \ + FN(sys_bpf), \ + FN(btf_find_by_name_kind), \ + FN(sys_close), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5080,6 +5128,12 @@ enum { BPF_F_BPRM_SECUREEXEC = (1ULL << 0), }; +/* Flags for bpf_redirect_map helper */ +enum { + BPF_F_BROADCAST = (1ULL << 3), + BPF_F_EXCLUDE_INGRESS = (1ULL << 4), +}; + #define __bpf_md_ptr(type, name) \ union { \ type name; \ @@ -5364,6 +5418,20 @@ struct sk_reuseport_md { __u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */ __u32 bind_inany; /* Is sock bound to an INANY address? */ __u32 hash; /* A hash of the packet 4 tuples */ + /* When reuse->migrating_sk is NULL, it is selecting a sk for the + * new incoming connection request (e.g. selecting a listen sk for + * the received SYN in the TCP case). reuse->sk is one of the sk + * in the reuseport group. The bpf prog can use reuse->sk to learn + * the local listening ip/port without looking into the skb. + * + * When reuse->migrating_sk is not NULL, reuse->sk is closed and + * reuse->migrating_sk is the socket that needs to be migrated + * to another listening socket. migrating_sk could be a fullsock + * sk that is fully established or a reqsk that is in-the-middle + * of 3-way handshake. + */ + __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(struct bpf_sock *, migrating_sk); }; #define BPF_TAG_SIZE 8 diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 9b057cc7650a..430f6874fa41 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1,3 +1,3 @@ libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o \ netlink.o bpf_prog_linfo.o libbpf_probes.o xsk.o hashmap.o \ - btf_dump.o ringbuf.o strset.o linker.o + btf_dump.o ringbuf.o strset.o linker.o gen_loader.o diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index e43e1896cb4b..ec14aa725bb0 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -223,18 +223,14 @@ install_lib: all_cmd $(call do_install_mkdir,$(libdir_SQ)); \ cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) +INSTALL_HEADERS = bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \ + bpf_helpers.h $(BPF_HELPER_DEFS) bpf_tracing.h \ + bpf_endian.h bpf_core_read.h skel_internal.h + install_headers: $(BPF_HELPER_DEFS) - $(call QUIET_INSTALL, headers) \ - $(call do_install,bpf.h,$(prefix)/include/bpf,644); \ - $(call do_install,libbpf.h,$(prefix)/include/bpf,644); \ - $(call do_install,btf.h,$(prefix)/include/bpf,644); \ - $(call do_install,libbpf_common.h,$(prefix)/include/bpf,644); \ - $(call do_install,xsk.h,$(prefix)/include/bpf,644); \ - $(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \ - $(call do_install,$(BPF_HELPER_DEFS),$(prefix)/include/bpf,644); \ - $(call do_install,bpf_tracing.h,$(prefix)/include/bpf,644); \ - $(call do_install,bpf_endian.h,$(prefix)/include/bpf,644); \ - $(call do_install,bpf_core_read.h,$(prefix)/include/bpf,644); + $(call QUIET_INSTALL, headers) \ + $(foreach hdr,$(INSTALL_HEADERS), \ + $(call do_install,$(hdr),$(prefix)/include/bpf,644);) install_pkgconfig: $(PC_FILE) $(call QUIET_INSTALL, $(PC_FILE)) \ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index bba48ff4c5c0..86dcac44f32f 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -80,6 +80,7 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size) int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) { union bpf_attr attr; + int fd; memset(&attr, '\0', sizeof(attr)); @@ -102,7 +103,8 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) else attr.inner_map_fd = create_attr->inner_map_fd; - return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); + fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); + return libbpf_err_errno(fd); } int bpf_create_map_node(enum bpf_map_type map_type, const char *name, @@ -160,6 +162,7 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, __u32 map_flags, int node) { union bpf_attr attr; + int fd; memset(&attr, '\0', sizeof(attr)); @@ -178,7 +181,8 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, attr.numa_node = node; } - return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); + fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); + return libbpf_err_errno(fd); } int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, @@ -222,10 +226,10 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) int fd; if (!load_attr->log_buf != !load_attr->log_buf_sz) - return -EINVAL; + return libbpf_err(-EINVAL); if (load_attr->log_level > (4 | 2 | 1) || (load_attr->log_level && !load_attr->log_buf)) - return -EINVAL; + return libbpf_err(-EINVAL); memset(&attr, 0, sizeof(attr)); attr.prog_type = load_attr->prog_type; @@ -281,8 +285,10 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) load_attr->func_info_cnt, load_attr->func_info_rec_size, attr.func_info_rec_size); - if (!finfo) + if (!finfo) { + errno = E2BIG; goto done; + } attr.func_info = ptr_to_u64(finfo); attr.func_info_rec_size = load_attr->func_info_rec_size; @@ -293,8 +299,10 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) load_attr->line_info_cnt, load_attr->line_info_rec_size, attr.line_info_rec_size); - if (!linfo) + if (!linfo) { + errno = E2BIG; goto done; + } attr.line_info = ptr_to_u64(linfo); attr.line_info_rec_size = load_attr->line_info_rec_size; @@ -318,9 +326,10 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) fd = sys_bpf_prog_load(&attr, sizeof(attr)); done: + /* free() doesn't affect errno, so we don't need to restore it */ free(finfo); free(linfo); - return fd; + return libbpf_err_errno(fd); } int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, @@ -329,7 +338,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, struct bpf_prog_load_params p = {}; if (!load_attr || !log_buf != !log_buf_sz) - return -EINVAL; + return libbpf_err(-EINVAL); p.prog_type = load_attr->prog_type; p.expected_attach_type = load_attr->expected_attach_type; @@ -391,6 +400,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, int log_level) { union bpf_attr attr; + int fd; memset(&attr, 0, sizeof(attr)); attr.prog_type = type; @@ -404,13 +414,15 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, attr.kern_version = kern_version; attr.prog_flags = prog_flags; - return sys_bpf_prog_load(&attr, sizeof(attr)); + fd = sys_bpf_prog_load(&attr, sizeof(attr)); + return libbpf_err_errno(fd); } int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags) { union bpf_attr attr; + int ret; memset(&attr, 0, sizeof(attr)); attr.map_fd = fd; @@ -418,22 +430,54 @@ int bpf_map_update_elem(int fd, const void *key, const void *value, attr.value = ptr_to_u64(value); attr.flags = flags; - return sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } int bpf_map_lookup_elem(int fd, const void *key, void *value) { union bpf_attr attr; + int ret; memset(&attr, 0, sizeof(attr)); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); - return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags) +{ + union bpf_attr attr; + int ret; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + attr.flags = flags; + + ret = sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); + return libbpf_err_errno(ret); +} + +int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value) +{ + union bpf_attr attr; + int ret; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + + ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr)); + return libbpf_err_errno(ret); +} + +int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags) { union bpf_attr attr; @@ -443,52 +487,46 @@ int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags) attr.value = ptr_to_u64(value); attr.flags = flags; - return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); -} - -int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value) -{ - union bpf_attr attr; - - memset(&attr, 0, sizeof(attr)); - attr.map_fd = fd; - attr.key = ptr_to_u64(key); - attr.value = ptr_to_u64(value); - return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr)); } int bpf_map_delete_elem(int fd, const void *key) { union bpf_attr attr; + int ret; memset(&attr, 0, sizeof(attr)); attr.map_fd = fd; attr.key = ptr_to_u64(key); - return sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } int bpf_map_get_next_key(int fd, const void *key, void *next_key) { union bpf_attr attr; + int ret; memset(&attr, 0, sizeof(attr)); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.next_key = ptr_to_u64(next_key); - return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } int bpf_map_freeze(int fd) { union bpf_attr attr; + int ret; memset(&attr, 0, sizeof(attr)); attr.map_fd = fd; - return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); + ret = sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } static int bpf_map_batch_common(int cmd, int fd, void *in_batch, @@ -500,7 +538,7 @@ static int bpf_map_batch_common(int cmd, int fd, void *in_batch, int ret; if (!OPTS_VALID(opts, bpf_map_batch_opts)) - return -EINVAL; + return libbpf_err(-EINVAL); memset(&attr, 0, sizeof(attr)); attr.batch.map_fd = fd; @@ -515,7 +553,7 @@ static int bpf_map_batch_common(int cmd, int fd, void *in_batch, ret = sys_bpf(cmd, &attr, sizeof(attr)); *count = attr.batch.count; - return ret; + return libbpf_err_errno(ret); } int bpf_map_delete_batch(int fd, void *keys, __u32 *count, @@ -552,22 +590,26 @@ int bpf_map_update_batch(int fd, void *keys, void *values, __u32 *count, int bpf_obj_pin(int fd, const char *pathname) { union bpf_attr attr; + int ret; memset(&attr, 0, sizeof(attr)); attr.pathname = ptr_to_u64((void *)pathname); attr.bpf_fd = fd; - return sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr)); + ret = sys_bpf(BPF_OBJ_PIN, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } int bpf_obj_get(const char *pathname) { union bpf_attr attr; + int fd; memset(&attr, 0, sizeof(attr)); attr.pathname = ptr_to_u64((void *)pathname); - return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr)); + fd = sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr)); + return libbpf_err_errno(fd); } int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, @@ -585,9 +627,10 @@ int bpf_prog_attach_xattr(int prog_fd, int target_fd, const struct bpf_prog_attach_opts *opts) { union bpf_attr attr; + int ret; if (!OPTS_VALID(opts, bpf_prog_attach_opts)) - return -EINVAL; + return libbpf_err(-EINVAL); memset(&attr, 0, sizeof(attr)); attr.target_fd = target_fd; @@ -596,30 +639,35 @@ int bpf_prog_attach_xattr(int prog_fd, int target_fd, attr.attach_flags = OPTS_GET(opts, flags, 0); attr.replace_bpf_fd = OPTS_GET(opts, replace_prog_fd, 0); - return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } int bpf_prog_detach(int target_fd, enum bpf_attach_type type) { union bpf_attr attr; + int ret; memset(&attr, 0, sizeof(attr)); attr.target_fd = target_fd; attr.attach_type = type; - return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) { union bpf_attr attr; + int ret; memset(&attr, 0, sizeof(attr)); attr.target_fd = target_fd; attr.attach_bpf_fd = prog_fd; attr.attach_type = type; - return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } int bpf_link_create(int prog_fd, int target_fd, @@ -628,15 +676,16 @@ int bpf_link_create(int prog_fd, int target_fd, { __u32 target_btf_id, iter_info_len; union bpf_attr attr; + int fd; if (!OPTS_VALID(opts, bpf_link_create_opts)) - return -EINVAL; + return libbpf_err(-EINVAL); iter_info_len = OPTS_GET(opts, iter_info_len, 0); target_btf_id = OPTS_GET(opts, target_btf_id, 0); if (iter_info_len && target_btf_id) - return -EINVAL; + return libbpf_err(-EINVAL); memset(&attr, 0, sizeof(attr)); attr.link_create.prog_fd = prog_fd; @@ -652,26 +701,30 @@ int bpf_link_create(int prog_fd, int target_fd, attr.link_create.target_btf_id = target_btf_id; } - return sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr)); + fd = sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr)); + return libbpf_err_errno(fd); } int bpf_link_detach(int link_fd) { union bpf_attr attr; + int ret; memset(&attr, 0, sizeof(attr)); attr.link_detach.link_fd = link_fd; - return sys_bpf(BPF_LINK_DETACH, &attr, sizeof(attr)); + ret = sys_bpf(BPF_LINK_DETACH, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } int bpf_link_update(int link_fd, int new_prog_fd, const struct bpf_link_update_opts *opts) { union bpf_attr attr; + int ret; if (!OPTS_VALID(opts, bpf_link_update_opts)) - return -EINVAL; + return libbpf_err(-EINVAL); memset(&attr, 0, sizeof(attr)); attr.link_update.link_fd = link_fd; @@ -679,17 +732,20 @@ int bpf_link_update(int link_fd, int new_prog_fd, attr.link_update.flags = OPTS_GET(opts, flags, 0); attr.link_update.old_prog_fd = OPTS_GET(opts, old_prog_fd, 0); - return sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr)); + ret = sys_bpf(BPF_LINK_UPDATE, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } int bpf_iter_create(int link_fd) { union bpf_attr attr; + int fd; memset(&attr, 0, sizeof(attr)); attr.iter_create.link_fd = link_fd; - return sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr)); + fd = sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr)); + return libbpf_err_errno(fd); } int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, @@ -706,10 +762,12 @@ int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, attr.query.prog_ids = ptr_to_u64(prog_ids); ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr)); + if (attach_flags) *attach_flags = attr.query.attach_flags; *prog_cnt = attr.query.prog_cnt; - return ret; + + return libbpf_err_errno(ret); } int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, @@ -727,13 +785,15 @@ int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, attr.test.repeat = repeat; ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); + if (size_out) *size_out = attr.test.data_size_out; if (retval) *retval = attr.test.retval; if (duration) *duration = attr.test.duration; - return ret; + + return libbpf_err_errno(ret); } int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr) @@ -742,7 +802,7 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr) int ret; if (!test_attr->data_out && test_attr->data_size_out > 0) - return -EINVAL; + return libbpf_err(-EINVAL); memset(&attr, 0, sizeof(attr)); attr.test.prog_fd = test_attr->prog_fd; @@ -757,11 +817,13 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr) attr.test.repeat = test_attr->repeat; ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); + test_attr->data_size_out = attr.test.data_size_out; test_attr->ctx_size_out = attr.test.ctx_size_out; test_attr->retval = attr.test.retval; test_attr->duration = attr.test.duration; - return ret; + + return libbpf_err_errno(ret); } int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) @@ -770,7 +832,7 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) int ret; if (!OPTS_VALID(opts, bpf_test_run_opts)) - return -EINVAL; + return libbpf_err(-EINVAL); memset(&attr, 0, sizeof(attr)); attr.test.prog_fd = prog_fd; @@ -788,11 +850,13 @@ int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts) attr.test.data_out = ptr_to_u64(OPTS_GET(opts, data_out, NULL)); ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr)); + OPTS_SET(opts, data_size_out, attr.test.data_size_out); OPTS_SET(opts, ctx_size_out, attr.test.ctx_size_out); OPTS_SET(opts, duration, attr.test.duration); OPTS_SET(opts, retval, attr.test.retval); - return ret; + + return libbpf_err_errno(ret); } static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd) @@ -807,7 +871,7 @@ static int bpf_obj_get_next_id(__u32 start_id, __u32 *next_id, int cmd) if (!err) *next_id = attr.next_id; - return err; + return libbpf_err_errno(err); } int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id) @@ -833,41 +897,49 @@ int bpf_link_get_next_id(__u32 start_id, __u32 *next_id) int bpf_prog_get_fd_by_id(__u32 id) { union bpf_attr attr; + int fd; memset(&attr, 0, sizeof(attr)); attr.prog_id = id; - return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr)); + return libbpf_err_errno(fd); } int bpf_map_get_fd_by_id(__u32 id) { union bpf_attr attr; + int fd; memset(&attr, 0, sizeof(attr)); attr.map_id = id; - return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr)); + return libbpf_err_errno(fd); } int bpf_btf_get_fd_by_id(__u32 id) { union bpf_attr attr; + int fd; memset(&attr, 0, sizeof(attr)); attr.btf_id = id; - return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr)); + return libbpf_err_errno(fd); } int bpf_link_get_fd_by_id(__u32 id) { union bpf_attr attr; + int fd; memset(&attr, 0, sizeof(attr)); attr.link_id = id; - return sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr)); + fd = sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr)); + return libbpf_err_errno(fd); } int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len) @@ -881,21 +953,24 @@ int bpf_obj_get_info_by_fd(int bpf_fd, void *info, __u32 *info_len) attr.info.info = ptr_to_u64(info); err = sys_bpf(BPF_OBJ_GET_INFO_BY_FD, &attr, sizeof(attr)); + if (!err) *info_len = attr.info.info_len; - return err; + return libbpf_err_errno(err); } int bpf_raw_tracepoint_open(const char *name, int prog_fd) { union bpf_attr attr; + int fd; memset(&attr, 0, sizeof(attr)); attr.raw_tracepoint.name = ptr_to_u64(name); attr.raw_tracepoint.prog_fd = prog_fd; - return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr)); + fd = sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr)); + return libbpf_err_errno(fd); } int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, @@ -915,12 +990,13 @@ retry: } fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr)); - if (fd == -1 && !do_log && log_buf && log_buf_size) { + + if (fd < 0 && !do_log && log_buf && log_buf_size) { do_log = true; goto retry; } - return fd; + return libbpf_err_errno(fd); } int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, @@ -937,37 +1013,42 @@ int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, attr.task_fd_query.buf_len = *buf_len; err = sys_bpf(BPF_TASK_FD_QUERY, &attr, sizeof(attr)); + *buf_len = attr.task_fd_query.buf_len; *prog_id = attr.task_fd_query.prog_id; *fd_type = attr.task_fd_query.fd_type; *probe_offset = attr.task_fd_query.probe_offset; *probe_addr = attr.task_fd_query.probe_addr; - return err; + return libbpf_err_errno(err); } int bpf_enable_stats(enum bpf_stats_type type) { union bpf_attr attr; + int fd; memset(&attr, 0, sizeof(attr)); attr.enable_stats.type = type; - return sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr)); + fd = sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr)); + return libbpf_err_errno(fd); } int bpf_prog_bind_map(int prog_fd, int map_fd, const struct bpf_prog_bind_opts *opts) { union bpf_attr attr; + int ret; if (!OPTS_VALID(opts, bpf_prog_bind_opts)) - return -EINVAL; + return libbpf_err(-EINVAL); memset(&attr, 0, sizeof(attr)); attr.prog_bind_map.prog_fd = prog_fd; attr.prog_bind_map.map_fd = map_fd; attr.prog_bind_map.flags = OPTS_GET(opts, flags, 0); - return sys_bpf(BPF_PROG_BIND_MAP, &attr, sizeof(attr)); + ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, sizeof(attr)); + return libbpf_err_errno(ret); } diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 875dde20d56e..4f758f8f50cd 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -124,6 +124,8 @@ LIBBPF_API int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags); LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value); +LIBBPF_API int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, + void *value, __u64 flags); LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); LIBBPF_API int bpf_map_freeze(int fd); diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h new file mode 100644 index 000000000000..615400391e57 --- /dev/null +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2021 Facebook */ +#ifndef __BPF_GEN_INTERNAL_H +#define __BPF_GEN_INTERNAL_H + +struct ksym_relo_desc { + const char *name; + int kind; + int insn_idx; +}; + +struct bpf_gen { + struct gen_loader_opts *opts; + void *data_start; + void *data_cur; + void *insn_start; + void *insn_cur; + ssize_t cleanup_label; + __u32 nr_progs; + __u32 nr_maps; + int log_level; + int error; + struct ksym_relo_desc *relos; + int relo_cnt; + char attach_target[128]; + int attach_kind; +}; + +void bpf_gen__init(struct bpf_gen *gen, int log_level); +int bpf_gen__finish(struct bpf_gen *gen); +void bpf_gen__free(struct bpf_gen *gen); +void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size); +void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_attr *map_attr, int map_idx); +struct bpf_prog_load_params; +void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_attr, int prog_idx); +void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size); +void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx); +void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type); +void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind, int insn_idx); + +#endif diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index 9720dc0b4605..b9987c3efa3c 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -158,4 +158,70 @@ enum libbpf_tristate { #define __kconfig __attribute__((section(".kconfig"))) #define __ksym __attribute__((section(".ksyms"))) +#ifndef ___bpf_concat +#define ___bpf_concat(a, b) a ## b +#endif +#ifndef ___bpf_apply +#define ___bpf_apply(fn, n) ___bpf_concat(fn, n) +#endif +#ifndef ___bpf_nth +#define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N +#endif +#ifndef ___bpf_narg +#define ___bpf_narg(...) \ + ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) +#endif + +#define ___bpf_fill0(arr, p, x) do {} while (0) +#define ___bpf_fill1(arr, p, x) arr[p] = x +#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args) +#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args) +#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args) +#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args) +#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args) +#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args) +#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args) +#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args) +#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args) +#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args) +#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args) +#define ___bpf_fill(arr, args...) \ + ___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args) + +/* + * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values + * in a structure. + */ +#define BPF_SEQ_PRINTF(seq, fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_seq_printf(seq, ___fmt, sizeof(___fmt), \ + ___param, sizeof(___param)); \ +}) + +/* + * BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of + * an array of u64. + */ +#define BPF_SNPRINTF(out, out_size, fmt, args...) \ +({ \ + static const char ___fmt[] = fmt; \ + unsigned long long ___param[___bpf_narg(args)]; \ + \ + _Pragma("GCC diagnostic push") \ + _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ + ___bpf_fill(___param, args); \ + _Pragma("GCC diagnostic pop") \ + \ + bpf_snprintf(out, out_size, ___fmt, \ + ___param, sizeof(___param)); \ +}) + #endif diff --git a/tools/lib/bpf/bpf_prog_linfo.c b/tools/lib/bpf/bpf_prog_linfo.c index 3ed1a27b5f7c..5c503096ef43 100644 --- a/tools/lib/bpf/bpf_prog_linfo.c +++ b/tools/lib/bpf/bpf_prog_linfo.c @@ -106,7 +106,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info) nr_linfo = info->nr_line_info; if (!nr_linfo) - return NULL; + return errno = EINVAL, NULL; /* * The min size that bpf_prog_linfo has to access for @@ -114,11 +114,11 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info) */ if (info->line_info_rec_size < offsetof(struct bpf_line_info, file_name_off)) - return NULL; + return errno = EINVAL, NULL; prog_linfo = calloc(1, sizeof(*prog_linfo)); if (!prog_linfo) - return NULL; + return errno = ENOMEM, NULL; /* Copy xlated line_info */ prog_linfo->nr_linfo = nr_linfo; @@ -174,7 +174,7 @@ struct bpf_prog_linfo *bpf_prog_linfo__new(const struct bpf_prog_info *info) err_free: bpf_prog_linfo__free(prog_linfo); - return NULL; + return errno = EINVAL, NULL; } const struct bpf_line_info * @@ -186,11 +186,11 @@ bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo, const __u64 *jited_linfo; if (func_idx >= prog_linfo->nr_jited_func) - return NULL; + return errno = ENOENT, NULL; nr_linfo = prog_linfo->nr_jited_linfo_per_func[func_idx]; if (nr_skip >= nr_linfo) - return NULL; + return errno = ENOENT, NULL; start = prog_linfo->jited_linfo_func_idx[func_idx] + nr_skip; jited_rec_size = prog_linfo->jited_rec_size; @@ -198,7 +198,7 @@ bpf_prog_linfo__lfind_addr_func(const struct bpf_prog_linfo *prog_linfo, (start * jited_rec_size); jited_linfo = raw_jited_linfo; if (addr < *jited_linfo) - return NULL; + return errno = ENOENT, NULL; nr_linfo -= nr_skip; rec_size = prog_linfo->rec_size; @@ -225,13 +225,13 @@ bpf_prog_linfo__lfind(const struct bpf_prog_linfo *prog_linfo, nr_linfo = prog_linfo->nr_linfo; if (nr_skip >= nr_linfo) - return NULL; + return errno = ENOENT, NULL; rec_size = prog_linfo->rec_size; raw_linfo = prog_linfo->raw_linfo + (nr_skip * rec_size); linfo = raw_linfo; if (insn_off < linfo->insn_off) - return NULL; + return errno = ENOENT, NULL; nr_linfo -= nr_skip; for (i = 0; i < nr_linfo; i++) { diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index 8c954ebc0c7c..d6bfbe009296 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -25,26 +25,35 @@ #define bpf_target_sparc #define bpf_target_defined #else - #undef bpf_target_defined -#endif /* Fall back to what the compiler says */ -#ifndef bpf_target_defined #if defined(__x86_64__) #define bpf_target_x86 + #define bpf_target_defined #elif defined(__s390__) #define bpf_target_s390 + #define bpf_target_defined #elif defined(__arm__) #define bpf_target_arm + #define bpf_target_defined #elif defined(__aarch64__) #define bpf_target_arm64 + #define bpf_target_defined #elif defined(__mips__) #define bpf_target_mips + #define bpf_target_defined #elif defined(__powerpc__) #define bpf_target_powerpc + #define bpf_target_defined #elif defined(__sparc__) #define bpf_target_sparc + #define bpf_target_defined +#endif /* no compiler target */ + #endif + +#ifndef __BPF_TARGET_MISSING +#define __BPF_TARGET_MISSING "GCC error \"Must specify a BPF target arch via __TARGET_ARCH_xxx\"" #endif #if defined(bpf_target_x86) @@ -287,7 +296,7 @@ struct pt_regs; #elif defined(bpf_target_sparc) #define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); }) #define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP -#else +#elif defined(bpf_target_defined) #define BPF_KPROBE_READ_RET_IP(ip, ctx) \ ({ bpf_probe_read_kernel(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); }) #define BPF_KRETPROBE_READ_RET_IP(ip, ctx) \ @@ -295,13 +304,48 @@ struct pt_regs; (void *)(PT_REGS_FP(ctx) + sizeof(ip))); }) #endif +#if !defined(bpf_target_defined) + +#define PT_REGS_PARM1(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_RET(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_FP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_RC(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_SP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_IP(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define PT_REGS_PARM1_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM2_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM3_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM4_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_PARM5_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_RET_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_FP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_RC_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_SP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define PT_REGS_IP_CORE(x) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) +#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ _Pragma(__BPF_TARGET_MISSING); 0l; }) + +#endif /* !defined(bpf_target_defined) */ + +#ifndef ___bpf_concat #define ___bpf_concat(a, b) a ## b +#endif +#ifndef ___bpf_apply #define ___bpf_apply(fn, n) ___bpf_concat(fn, n) +#endif +#ifndef ___bpf_nth #define ___bpf_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _a, _b, _c, N, ...) N +#endif +#ifndef ___bpf_narg #define ___bpf_narg(...) \ ___bpf_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) -#define ___bpf_empty(...) \ - ___bpf_nth(_, ##__VA_ARGS__, N, N, N, N, N, N, N, N, N, N, 0) +#endif #define ___bpf_ctx_cast0() ctx #define ___bpf_ctx_cast1(x) ___bpf_ctx_cast0(), (void *)ctx[0] @@ -413,56 +457,4 @@ typeof(name(0)) name(struct pt_regs *ctx) \ } \ static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args) -#define ___bpf_fill0(arr, p, x) do {} while (0) -#define ___bpf_fill1(arr, p, x) arr[p] = x -#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args) -#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args) -#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args) -#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args) -#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args) -#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args) -#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args) -#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args) -#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args) -#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args) -#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args) -#define ___bpf_fill(arr, args...) \ - ___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args) - -/* - * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values - * in a structure. - */ -#define BPF_SEQ_PRINTF(seq, fmt, args...) \ -({ \ - static const char ___fmt[] = fmt; \ - unsigned long long ___param[___bpf_narg(args)]; \ - \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - ___bpf_fill(___param, args); \ - _Pragma("GCC diagnostic pop") \ - \ - bpf_seq_printf(seq, ___fmt, sizeof(___fmt), \ - ___param, sizeof(___param)); \ -}) - -/* - * BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of - * an array of u64. - */ -#define BPF_SNPRINTF(out, out_size, fmt, args...) \ -({ \ - static const char ___fmt[] = fmt; \ - unsigned long long ___param[___bpf_narg(args)]; \ - \ - _Pragma("GCC diagnostic push") \ - _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \ - ___bpf_fill(___param, args); \ - _Pragma("GCC diagnostic pop") \ - \ - bpf_snprintf(out, out_size, ___fmt, \ - ___param, sizeof(___param)); \ -}) - #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index d57e13a13798..b46760b93bb4 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -443,7 +443,7 @@ struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id) const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) { if (type_id >= btf->start_id + btf->nr_types) - return NULL; + return errno = EINVAL, NULL; return btf_type_by_id((struct btf *)btf, type_id); } @@ -510,7 +510,7 @@ size_t btf__pointer_size(const struct btf *btf) int btf__set_pointer_size(struct btf *btf, size_t ptr_sz) { if (ptr_sz != 4 && ptr_sz != 8) - return -EINVAL; + return libbpf_err(-EINVAL); btf->ptr_sz = ptr_sz; return 0; } @@ -537,7 +537,7 @@ enum btf_endianness btf__endianness(const struct btf *btf) int btf__set_endianness(struct btf *btf, enum btf_endianness endian) { if (endian != BTF_LITTLE_ENDIAN && endian != BTF_BIG_ENDIAN) - return -EINVAL; + return libbpf_err(-EINVAL); btf->swapped_endian = is_host_big_endian() != (endian == BTF_BIG_ENDIAN); if (!btf->swapped_endian) { @@ -568,8 +568,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) int i; t = btf__type_by_id(btf, type_id); - for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); - i++) { + for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); i++) { switch (btf_kind(t)) { case BTF_KIND_INT: case BTF_KIND_STRUCT: @@ -592,12 +591,12 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_ARRAY: array = btf_array(t); if (nelems && array->nelems > UINT32_MAX / nelems) - return -E2BIG; + return libbpf_err(-E2BIG); nelems *= array->nelems; type_id = array->type; break; default: - return -EINVAL; + return libbpf_err(-EINVAL); } t = btf__type_by_id(btf, type_id); @@ -605,9 +604,9 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) done: if (size < 0) - return -EINVAL; + return libbpf_err(-EINVAL); if (nelems && size > UINT32_MAX / nelems) - return -E2BIG; + return libbpf_err(-E2BIG); return nelems * size; } @@ -640,7 +639,7 @@ int btf__align_of(const struct btf *btf, __u32 id) for (i = 0; i < vlen; i++, m++) { align = btf__align_of(btf, m->type); if (align <= 0) - return align; + return libbpf_err(align); max_align = max(max_align, align); } @@ -648,7 +647,7 @@ int btf__align_of(const struct btf *btf, __u32 id) } default: pr_warn("unsupported BTF_KIND:%u\n", btf_kind(t)); - return 0; + return errno = EINVAL, 0; } } @@ -667,7 +666,7 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id) } if (depth == MAX_RESOLVE_DEPTH || btf_type_is_void_or_null(t)) - return -EINVAL; + return libbpf_err(-EINVAL); return type_id; } @@ -687,7 +686,7 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name) return i; } - return -ENOENT; + return libbpf_err(-ENOENT); } __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, @@ -709,7 +708,7 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, return i; } - return -ENOENT; + return libbpf_err(-ENOENT); } static bool btf_is_modifiable(const struct btf *btf) @@ -785,12 +784,12 @@ static struct btf *btf_new_empty(struct btf *base_btf) struct btf *btf__new_empty(void) { - return btf_new_empty(NULL); + return libbpf_ptr(btf_new_empty(NULL)); } struct btf *btf__new_empty_split(struct btf *base_btf) { - return btf_new_empty(base_btf); + return libbpf_ptr(btf_new_empty(base_btf)); } static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf) @@ -846,7 +845,7 @@ done: struct btf *btf__new(const void *data, __u32 size) { - return btf_new(data, size, NULL); + return libbpf_ptr(btf_new(data, size, NULL)); } static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, @@ -937,7 +936,8 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, goto done; } btf = btf_new(btf_data->d_buf, btf_data->d_size, base_btf); - if (IS_ERR(btf)) + err = libbpf_get_error(btf); + if (err) goto done; switch (gelf_getclass(elf)) { @@ -953,9 +953,9 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf, } if (btf_ext && btf_ext_data) { - *btf_ext = btf_ext__new(btf_ext_data->d_buf, - btf_ext_data->d_size); - if (IS_ERR(*btf_ext)) + *btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size); + err = libbpf_get_error(*btf_ext); + if (err) goto done; } else if (btf_ext) { *btf_ext = NULL; @@ -965,30 +965,24 @@ done: elf_end(elf); close(fd); - if (err) - return ERR_PTR(err); - /* - * btf is always parsed before btf_ext, so no need to clean up - * btf_ext, if btf loading failed - */ - if (IS_ERR(btf)) + if (!err) return btf; - if (btf_ext && IS_ERR(*btf_ext)) { - btf__free(btf); - err = PTR_ERR(*btf_ext); - return ERR_PTR(err); - } - return btf; + + if (btf_ext) + btf_ext__free(*btf_ext); + btf__free(btf); + + return ERR_PTR(err); } struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) { - return btf_parse_elf(path, NULL, btf_ext); + return libbpf_ptr(btf_parse_elf(path, NULL, btf_ext)); } struct btf *btf__parse_elf_split(const char *path, struct btf *base_btf) { - return btf_parse_elf(path, base_btf, NULL); + return libbpf_ptr(btf_parse_elf(path, base_btf, NULL)); } static struct btf *btf_parse_raw(const char *path, struct btf *base_btf) @@ -1056,36 +1050,39 @@ err_out: struct btf *btf__parse_raw(const char *path) { - return btf_parse_raw(path, NULL); + return libbpf_ptr(btf_parse_raw(path, NULL)); } struct btf *btf__parse_raw_split(const char *path, struct btf *base_btf) { - return btf_parse_raw(path, base_btf); + return libbpf_ptr(btf_parse_raw(path, base_btf)); } static struct btf *btf_parse(const char *path, struct btf *base_btf, struct btf_ext **btf_ext) { struct btf *btf; + int err; if (btf_ext) *btf_ext = NULL; btf = btf_parse_raw(path, base_btf); - if (!IS_ERR(btf) || PTR_ERR(btf) != -EPROTO) + err = libbpf_get_error(btf); + if (!err) return btf; - + if (err != -EPROTO) + return ERR_PTR(err); return btf_parse_elf(path, base_btf, btf_ext); } struct btf *btf__parse(const char *path, struct btf_ext **btf_ext) { - return btf_parse(path, NULL, btf_ext); + return libbpf_ptr(btf_parse(path, NULL, btf_ext)); } struct btf *btf__parse_split(const char *path, struct btf *base_btf) { - return btf_parse(path, base_btf, NULL); + return libbpf_ptr(btf_parse(path, base_btf, NULL)); } static int compare_vsi_off(const void *_a, const void *_b) @@ -1178,7 +1175,7 @@ int btf__finalize_data(struct bpf_object *obj, struct btf *btf) } } - return err; + return libbpf_err(err); } static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian); @@ -1191,13 +1188,13 @@ int btf__load(struct btf *btf) int err = 0; if (btf->fd >= 0) - return -EEXIST; + return libbpf_err(-EEXIST); retry_load: if (log_buf_size) { log_buf = malloc(log_buf_size); if (!log_buf) - return -ENOMEM; + return libbpf_err(-ENOMEM); *log_buf = 0; } @@ -1229,7 +1226,7 @@ retry_load: done: free(log_buf); - return err; + return libbpf_err(err); } int btf__fd(const struct btf *btf) @@ -1305,7 +1302,7 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size) data = btf_get_raw_data(btf, &data_sz, btf->swapped_endian); if (!data) - return NULL; + return errno = -ENOMEM, NULL; btf->raw_size = data_sz; if (btf->swapped_endian) @@ -1323,7 +1320,7 @@ const char *btf__str_by_offset(const struct btf *btf, __u32 offset) else if (offset - btf->start_str_off < btf->hdr->str_len) return btf_strs_data(btf) + (offset - btf->start_str_off); else - return NULL; + return errno = EINVAL, NULL; } const char *btf__name_by_offset(const struct btf *btf, __u32 offset) @@ -1388,17 +1385,20 @@ exit_free: int btf__get_from_id(__u32 id, struct btf **btf) { struct btf *res; - int btf_fd; + int err, btf_fd; *btf = NULL; btf_fd = bpf_btf_get_fd_by_id(id); if (btf_fd < 0) - return -errno; + return libbpf_err(-errno); res = btf_get_from_fd(btf_fd, NULL); + err = libbpf_get_error(res); + close(btf_fd); - if (IS_ERR(res)) - return PTR_ERR(res); + + if (err) + return libbpf_err(err); *btf = res; return 0; @@ -1415,31 +1415,30 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, __s64 key_size, value_size; __s32 container_id; - if (snprintf(container_name, max_name, "____btf_map_%s", map_name) == - max_name) { + if (snprintf(container_name, max_name, "____btf_map_%s", map_name) == max_name) { pr_warn("map:%s length of '____btf_map_%s' is too long\n", map_name, map_name); - return -EINVAL; + return libbpf_err(-EINVAL); } container_id = btf__find_by_name(btf, container_name); if (container_id < 0) { pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n", map_name, container_name); - return container_id; + return libbpf_err(container_id); } container_type = btf__type_by_id(btf, container_id); if (!container_type) { pr_warn("map:%s cannot find BTF type for container_id:%u\n", map_name, container_id); - return -EINVAL; + return libbpf_err(-EINVAL); } if (!btf_is_struct(container_type) || btf_vlen(container_type) < 2) { pr_warn("map:%s container_name:%s is an invalid container struct\n", map_name, container_name); - return -EINVAL; + return libbpf_err(-EINVAL); } key = btf_members(container_type); @@ -1448,25 +1447,25 @@ int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, key_size = btf__resolve_size(btf, key->type); if (key_size < 0) { pr_warn("map:%s invalid BTF key_type_size\n", map_name); - return key_size; + return libbpf_err(key_size); } if (expected_key_size != key_size) { pr_warn("map:%s btf_key_type_size:%u != map_def_key_size:%u\n", map_name, (__u32)key_size, expected_key_size); - return -EINVAL; + return libbpf_err(-EINVAL); } value_size = btf__resolve_size(btf, value->type); if (value_size < 0) { pr_warn("map:%s invalid BTF value_type_size\n", map_name); - return value_size; + return libbpf_err(value_size); } if (expected_value_size != value_size) { pr_warn("map:%s btf_value_type_size:%u != map_def_value_size:%u\n", map_name, (__u32)value_size, expected_value_size); - return -EINVAL; + return libbpf_err(-EINVAL); } *key_type_id = key->type; @@ -1563,11 +1562,11 @@ int btf__find_str(struct btf *btf, const char *s) /* BTF needs to be in a modifiable state to build string lookup index */ if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); off = strset__find_str(btf->strs_set, s); if (off < 0) - return off; + return libbpf_err(off); return btf->start_str_off + off; } @@ -1588,11 +1587,11 @@ int btf__add_str(struct btf *btf, const char *s) } if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); off = strset__add_str(btf->strs_set, s); if (off < 0) - return off; + return libbpf_err(off); btf->hdr->str_len = strset__data_size(btf->strs_set); @@ -1616,7 +1615,7 @@ static int btf_commit_type(struct btf *btf, int data_sz) err = btf_add_type_idx_entry(btf, btf->hdr->type_len); if (err) - return err; + return libbpf_err(err); btf->hdr->type_len += data_sz; btf->hdr->str_off += data_sz; @@ -1653,21 +1652,21 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t sz = btf_type_size(src_type); if (sz < 0) - return sz; + return libbpf_err(sz); /* deconstruct BTF, if necessary, and invalidate raw_data */ if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); t = btf_add_type_mem(btf, sz); if (!t) - return -ENOMEM; + return libbpf_err(-ENOMEM); memcpy(t, src_type, sz); err = btf_type_visit_str_offs(t, btf_rewrite_str, &p); if (err) - return err; + return libbpf_err(err); return btf_commit_type(btf, sz); } @@ -1688,21 +1687,21 @@ int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding /* non-empty name */ if (!name || !name[0]) - return -EINVAL; + return libbpf_err(-EINVAL); /* byte_sz must be power of 2 */ if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 16) - return -EINVAL; + return libbpf_err(-EINVAL); if (encoding & ~(BTF_INT_SIGNED | BTF_INT_CHAR | BTF_INT_BOOL)) - return -EINVAL; + return libbpf_err(-EINVAL); /* deconstruct BTF, if necessary, and invalidate raw_data */ if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_type) + sizeof(int); t = btf_add_type_mem(btf, sz); if (!t) - return -ENOMEM; + return libbpf_err(-ENOMEM); /* if something goes wrong later, we might end up with an extra string, * but that shouldn't be a problem, because BTF can't be constructed @@ -1736,20 +1735,20 @@ int btf__add_float(struct btf *btf, const char *name, size_t byte_sz) /* non-empty name */ if (!name || !name[0]) - return -EINVAL; + return libbpf_err(-EINVAL); /* byte_sz must be one of the explicitly allowed values */ if (byte_sz != 2 && byte_sz != 4 && byte_sz != 8 && byte_sz != 12 && byte_sz != 16) - return -EINVAL; + return libbpf_err(-EINVAL); if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_type); t = btf_add_type_mem(btf, sz); if (!t) - return -ENOMEM; + return libbpf_err(-ENOMEM); name_off = btf__add_str(btf, name); if (name_off < 0) @@ -1780,15 +1779,15 @@ static int btf_add_ref_kind(struct btf *btf, int kind, const char *name, int ref int sz, name_off = 0; if (validate_type_id(ref_type_id)) - return -EINVAL; + return libbpf_err(-EINVAL); if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_type); t = btf_add_type_mem(btf, sz); if (!t) - return -ENOMEM; + return libbpf_err(-ENOMEM); if (name && name[0]) { name_off = btf__add_str(btf, name); @@ -1831,15 +1830,15 @@ int btf__add_array(struct btf *btf, int index_type_id, int elem_type_id, __u32 n int sz; if (validate_type_id(index_type_id) || validate_type_id(elem_type_id)) - return -EINVAL; + return libbpf_err(-EINVAL); if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_type) + sizeof(struct btf_array); t = btf_add_type_mem(btf, sz); if (!t) - return -ENOMEM; + return libbpf_err(-ENOMEM); t->name_off = 0; t->info = btf_type_info(BTF_KIND_ARRAY, 0, 0); @@ -1860,12 +1859,12 @@ static int btf_add_composite(struct btf *btf, int kind, const char *name, __u32 int sz, name_off = 0; if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_type); t = btf_add_type_mem(btf, sz); if (!t) - return -ENOMEM; + return libbpf_err(-ENOMEM); if (name && name[0]) { name_off = btf__add_str(btf, name); @@ -1943,30 +1942,30 @@ int btf__add_field(struct btf *btf, const char *name, int type_id, /* last type should be union/struct */ if (btf->nr_types == 0) - return -EINVAL; + return libbpf_err(-EINVAL); t = btf_last_type(btf); if (!btf_is_composite(t)) - return -EINVAL; + return libbpf_err(-EINVAL); if (validate_type_id(type_id)) - return -EINVAL; + return libbpf_err(-EINVAL); /* best-effort bit field offset/size enforcement */ is_bitfield = bit_size || (bit_offset % 8 != 0); if (is_bitfield && (bit_size == 0 || bit_size > 255 || bit_offset > 0xffffff)) - return -EINVAL; + return libbpf_err(-EINVAL); /* only offset 0 is allowed for unions */ if (btf_is_union(t) && bit_offset) - return -EINVAL; + return libbpf_err(-EINVAL); /* decompose and invalidate raw data */ if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_member); m = btf_add_type_mem(btf, sz); if (!m) - return -ENOMEM; + return libbpf_err(-ENOMEM); if (name && name[0]) { name_off = btf__add_str(btf, name); @@ -2008,15 +2007,15 @@ int btf__add_enum(struct btf *btf, const char *name, __u32 byte_sz) /* byte_sz must be power of 2 */ if (!byte_sz || (byte_sz & (byte_sz - 1)) || byte_sz > 8) - return -EINVAL; + return libbpf_err(-EINVAL); if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_type); t = btf_add_type_mem(btf, sz); if (!t) - return -ENOMEM; + return libbpf_err(-ENOMEM); if (name && name[0]) { name_off = btf__add_str(btf, name); @@ -2048,25 +2047,25 @@ int btf__add_enum_value(struct btf *btf, const char *name, __s64 value) /* last type should be BTF_KIND_ENUM */ if (btf->nr_types == 0) - return -EINVAL; + return libbpf_err(-EINVAL); t = btf_last_type(btf); if (!btf_is_enum(t)) - return -EINVAL; + return libbpf_err(-EINVAL); /* non-empty name */ if (!name || !name[0]) - return -EINVAL; + return libbpf_err(-EINVAL); if (value < INT_MIN || value > UINT_MAX) - return -E2BIG; + return libbpf_err(-E2BIG); /* decompose and invalidate raw data */ if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_enum); v = btf_add_type_mem(btf, sz); if (!v) - return -ENOMEM; + return libbpf_err(-ENOMEM); name_off = btf__add_str(btf, name); if (name_off < 0) @@ -2096,7 +2095,7 @@ int btf__add_enum_value(struct btf *btf, const char *name, __s64 value) int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind) { if (!name || !name[0]) - return -EINVAL; + return libbpf_err(-EINVAL); switch (fwd_kind) { case BTF_FWD_STRUCT: @@ -2117,7 +2116,7 @@ int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind) */ return btf__add_enum(btf, name, sizeof(int)); default: - return -EINVAL; + return libbpf_err(-EINVAL); } } @@ -2132,7 +2131,7 @@ int btf__add_fwd(struct btf *btf, const char *name, enum btf_fwd_kind fwd_kind) int btf__add_typedef(struct btf *btf, const char *name, int ref_type_id) { if (!name || !name[0]) - return -EINVAL; + return libbpf_err(-EINVAL); return btf_add_ref_kind(btf, BTF_KIND_TYPEDEF, name, ref_type_id); } @@ -2187,10 +2186,10 @@ int btf__add_func(struct btf *btf, const char *name, int id; if (!name || !name[0]) - return -EINVAL; + return libbpf_err(-EINVAL); if (linkage != BTF_FUNC_STATIC && linkage != BTF_FUNC_GLOBAL && linkage != BTF_FUNC_EXTERN) - return -EINVAL; + return libbpf_err(-EINVAL); id = btf_add_ref_kind(btf, BTF_KIND_FUNC, name, proto_type_id); if (id > 0) { @@ -2198,7 +2197,7 @@ int btf__add_func(struct btf *btf, const char *name, t->info = btf_type_info(BTF_KIND_FUNC, linkage, 0); } - return id; + return libbpf_err(id); } /* @@ -2219,15 +2218,15 @@ int btf__add_func_proto(struct btf *btf, int ret_type_id) int sz; if (validate_type_id(ret_type_id)) - return -EINVAL; + return libbpf_err(-EINVAL); if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_type); t = btf_add_type_mem(btf, sz); if (!t) - return -ENOMEM; + return libbpf_err(-ENOMEM); /* start out with vlen=0; this will be adjusted when adding enum * values, if necessary @@ -2254,23 +2253,23 @@ int btf__add_func_param(struct btf *btf, const char *name, int type_id) int sz, name_off = 0; if (validate_type_id(type_id)) - return -EINVAL; + return libbpf_err(-EINVAL); /* last type should be BTF_KIND_FUNC_PROTO */ if (btf->nr_types == 0) - return -EINVAL; + return libbpf_err(-EINVAL); t = btf_last_type(btf); if (!btf_is_func_proto(t)) - return -EINVAL; + return libbpf_err(-EINVAL); /* decompose and invalidate raw data */ if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_param); p = btf_add_type_mem(btf, sz); if (!p) - return -ENOMEM; + return libbpf_err(-ENOMEM); if (name && name[0]) { name_off = btf__add_str(btf, name); @@ -2308,21 +2307,21 @@ int btf__add_var(struct btf *btf, const char *name, int linkage, int type_id) /* non-empty name */ if (!name || !name[0]) - return -EINVAL; + return libbpf_err(-EINVAL); if (linkage != BTF_VAR_STATIC && linkage != BTF_VAR_GLOBAL_ALLOCATED && linkage != BTF_VAR_GLOBAL_EXTERN) - return -EINVAL; + return libbpf_err(-EINVAL); if (validate_type_id(type_id)) - return -EINVAL; + return libbpf_err(-EINVAL); /* deconstruct BTF, if necessary, and invalidate raw_data */ if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_type) + sizeof(struct btf_var); t = btf_add_type_mem(btf, sz); if (!t) - return -ENOMEM; + return libbpf_err(-ENOMEM); name_off = btf__add_str(btf, name); if (name_off < 0) @@ -2357,15 +2356,15 @@ int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz) /* non-empty name */ if (!name || !name[0]) - return -EINVAL; + return libbpf_err(-EINVAL); if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_type); t = btf_add_type_mem(btf, sz); if (!t) - return -ENOMEM; + return libbpf_err(-ENOMEM); name_off = btf__add_str(btf, name); if (name_off < 0) @@ -2397,22 +2396,22 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ /* last type should be BTF_KIND_DATASEC */ if (btf->nr_types == 0) - return -EINVAL; + return libbpf_err(-EINVAL); t = btf_last_type(btf); if (!btf_is_datasec(t)) - return -EINVAL; + return libbpf_err(-EINVAL); if (validate_type_id(var_type_id)) - return -EINVAL; + return libbpf_err(-EINVAL); /* decompose and invalidate raw data */ if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); sz = sizeof(struct btf_var_secinfo); v = btf_add_type_mem(btf, sz); if (!v) - return -ENOMEM; + return libbpf_err(-ENOMEM); v->type = var_type_id; v->offset = offset; @@ -2614,11 +2613,11 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) err = btf_ext_parse_hdr(data, size); if (err) - return ERR_PTR(err); + return libbpf_err_ptr(err); btf_ext = calloc(1, sizeof(struct btf_ext)); if (!btf_ext) - return ERR_PTR(-ENOMEM); + return libbpf_err_ptr(-ENOMEM); btf_ext->data_size = size; btf_ext->data = malloc(size); @@ -2628,9 +2627,11 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) } memcpy(btf_ext->data, data, size); - if (btf_ext->hdr->hdr_len < - offsetofend(struct btf_ext_header, line_info_len)) + if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, line_info_len)) { + err = -EINVAL; goto done; + } + err = btf_ext_setup_func_info(btf_ext); if (err) goto done; @@ -2639,8 +2640,11 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) if (err) goto done; - if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) + if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, core_relo_len)) { + err = -EINVAL; goto done; + } + err = btf_ext_setup_core_relos(btf_ext); if (err) goto done; @@ -2648,7 +2652,7 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) done: if (err) { btf_ext__free(btf_ext); - return ERR_PTR(err); + return libbpf_err_ptr(err); } return btf_ext; @@ -2687,7 +2691,7 @@ static int btf_ext_reloc_info(const struct btf *btf, existing_len = (*cnt) * record_size; data = realloc(*info, existing_len + records_len); if (!data) - return -ENOMEM; + return libbpf_err(-ENOMEM); memcpy(data + existing_len, sinfo->data, records_len); /* adjust insn_off only, the rest data will be passed @@ -2697,15 +2701,14 @@ static int btf_ext_reloc_info(const struct btf *btf, __u32 *insn_off; insn_off = data + existing_len + (i * record_size); - *insn_off = *insn_off / sizeof(struct bpf_insn) + - insns_cnt; + *insn_off = *insn_off / sizeof(struct bpf_insn) + insns_cnt; } *info = data; *cnt += sinfo->num_info; return 0; } - return -ENOENT; + return libbpf_err(-ENOENT); } int btf_ext__reloc_func_info(const struct btf *btf, @@ -2894,11 +2897,11 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, if (IS_ERR(d)) { pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d)); - return -EINVAL; + return libbpf_err(-EINVAL); } if (btf_ensure_modifiable(btf)) - return -ENOMEM; + return libbpf_err(-ENOMEM); err = btf_dedup_prep(d); if (err) { @@ -2938,7 +2941,7 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, done: btf_dedup_free(d); - return err; + return libbpf_err(err); } #define BTF_UNPROCESSED_ID ((__u32)-1) @@ -4411,7 +4414,7 @@ struct btf *libbpf_find_kernel_btf(void) char path[PATH_MAX + 1]; struct utsname buf; struct btf *btf; - int i; + int i, err; uname(&buf); @@ -4425,17 +4428,16 @@ struct btf *libbpf_find_kernel_btf(void) btf = btf__parse_raw(path); else btf = btf__parse_elf(path, NULL); - - pr_debug("loading kernel BTF '%s': %ld\n", - path, IS_ERR(btf) ? PTR_ERR(btf) : 0); - if (IS_ERR(btf)) + err = libbpf_get_error(btf); + pr_debug("loading kernel BTF '%s': %d\n", path, err); + if (err) continue; return btf; } pr_warn("failed to find valid kernel BTF\n"); - return ERR_PTR(-ESRCH); + return libbpf_err_ptr(-ESRCH); } int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ctx) diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 5e2809d685bf..5dc6b5172bb3 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -128,7 +128,7 @@ struct btf_dump *btf_dump__new(const struct btf *btf, d = calloc(1, sizeof(struct btf_dump)); if (!d) - return ERR_PTR(-ENOMEM); + return libbpf_err_ptr(-ENOMEM); d->btf = btf; d->btf_ext = btf_ext; @@ -156,7 +156,7 @@ struct btf_dump *btf_dump__new(const struct btf *btf, return d; err: btf_dump__free(d); - return ERR_PTR(err); + return libbpf_err_ptr(err); } static int btf_dump_resize(struct btf_dump *d) @@ -236,16 +236,16 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id) int err, i; if (id > btf__get_nr_types(d->btf)) - return -EINVAL; + return libbpf_err(-EINVAL); err = btf_dump_resize(d); if (err) - return err; + return libbpf_err(err); d->emit_queue_cnt = 0; err = btf_dump_order_type(d, id, false); if (err < 0) - return err; + return libbpf_err(err); for (i = 0; i < d->emit_queue_cnt; i++) btf_dump_emit_type(d, d->emit_queue[i], 0 /*top-level*/); @@ -1075,11 +1075,11 @@ int btf_dump__emit_type_decl(struct btf_dump *d, __u32 id, int lvl, err; if (!OPTS_VALID(opts, btf_dump_emit_type_decl_opts)) - return -EINVAL; + return libbpf_err(-EINVAL); err = btf_dump_resize(d); if (err) - return -EINVAL; + return libbpf_err(err); fname = OPTS_GET(opts, field_name, ""); lvl = OPTS_GET(opts, indent_level, 0); diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c new file mode 100644 index 000000000000..8df718a6b142 --- /dev/null +++ b/tools/lib/bpf/gen_loader.c @@ -0,0 +1,729 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2021 Facebook */ +#include +#include +#include +#include +#include +#include "btf.h" +#include "bpf.h" +#include "libbpf.h" +#include "libbpf_internal.h" +#include "hashmap.h" +#include "bpf_gen_internal.h" +#include "skel_internal.h" + +#define MAX_USED_MAPS 64 +#define MAX_USED_PROGS 32 + +/* The following structure describes the stack layout of the loader program. + * In addition R6 contains the pointer to context. + * R7 contains the result of the last sys_bpf command (typically error or FD). + * R9 contains the result of the last sys_close command. + * + * Naming convention: + * ctx - bpf program context + * stack - bpf program stack + * blob - bpf_attr-s, strings, insns, map data. + * All the bytes that loader prog will use for read/write. + */ +struct loader_stack { + __u32 btf_fd; + __u32 map_fd[MAX_USED_MAPS]; + __u32 prog_fd[MAX_USED_PROGS]; + __u32 inner_map_fd; +}; + +#define stack_off(field) \ + (__s16)(-sizeof(struct loader_stack) + offsetof(struct loader_stack, field)) + +#define attr_field(attr, field) (attr + offsetof(union bpf_attr, field)) + +static int realloc_insn_buf(struct bpf_gen *gen, __u32 size) +{ + size_t off = gen->insn_cur - gen->insn_start; + void *insn_start; + + if (gen->error) + return gen->error; + if (size > INT32_MAX || off + size > INT32_MAX) { + gen->error = -ERANGE; + return -ERANGE; + } + insn_start = realloc(gen->insn_start, off + size); + if (!insn_start) { + gen->error = -ENOMEM; + free(gen->insn_start); + gen->insn_start = NULL; + return -ENOMEM; + } + gen->insn_start = insn_start; + gen->insn_cur = insn_start + off; + return 0; +} + +static int realloc_data_buf(struct bpf_gen *gen, __u32 size) +{ + size_t off = gen->data_cur - gen->data_start; + void *data_start; + + if (gen->error) + return gen->error; + if (size > INT32_MAX || off + size > INT32_MAX) { + gen->error = -ERANGE; + return -ERANGE; + } + data_start = realloc(gen->data_start, off + size); + if (!data_start) { + gen->error = -ENOMEM; + free(gen->data_start); + gen->data_start = NULL; + return -ENOMEM; + } + gen->data_start = data_start; + gen->data_cur = data_start + off; + return 0; +} + +static void emit(struct bpf_gen *gen, struct bpf_insn insn) +{ + if (realloc_insn_buf(gen, sizeof(insn))) + return; + memcpy(gen->insn_cur, &insn, sizeof(insn)); + gen->insn_cur += sizeof(insn); +} + +static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn insn2) +{ + emit(gen, insn1); + emit(gen, insn2); +} + +void bpf_gen__init(struct bpf_gen *gen, int log_level) +{ + size_t stack_sz = sizeof(struct loader_stack); + int i; + + gen->log_level = log_level; + /* save ctx pointer into R6 */ + emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1)); + + /* bzero stack */ + emit(gen, BPF_MOV64_REG(BPF_REG_1, BPF_REG_10)); + emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -stack_sz)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, stack_sz)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); + + /* jump over cleanup code */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, + /* size of cleanup code below */ + (stack_sz / 4) * 3 + 2)); + + /* remember the label where all error branches will jump to */ + gen->cleanup_label = gen->insn_cur - gen->insn_start; + /* emit cleanup code: close all temp FDs */ + for (i = 0; i < stack_sz; i += 4) { + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i)); + emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close)); + } + /* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */ + emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7)); + emit(gen, BPF_EXIT_INSN()); +} + +static int add_data(struct bpf_gen *gen, const void *data, __u32 size) +{ + void *prev; + + if (realloc_data_buf(gen, size)) + return 0; + prev = gen->data_cur; + memcpy(gen->data_cur, data, size); + gen->data_cur += size; + return prev - gen->data_start; +} + +static int insn_bytes_to_bpf_size(__u32 sz) +{ + switch (sz) { + case 8: return BPF_DW; + case 4: return BPF_W; + case 2: return BPF_H; + case 1: return BPF_B; + default: return -1; + } +} + +/* *(u64 *)(blob + off) = (u64)(void *)(blob + data) */ +static void emit_rel_store(struct bpf_gen *gen, int off, int data) +{ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, data)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, off)); + emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0)); +} + +/* *(u64 *)(blob + off) = (u64)(void *)(%sp + stack_off) */ +static void emit_rel_store_sp(struct bpf_gen *gen, int off, int stack_off) +{ + emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_10)); + emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, stack_off)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, off)); + emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0)); +} + +static void move_ctx2blob(struct bpf_gen *gen, int off, int size, int ctx_off, + bool check_non_zero) +{ + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_6, ctx_off)); + if (check_non_zero) + /* If value in ctx is zero don't update the blob. + * For example: when ctx->map.max_entries == 0, keep default max_entries from bpf.c + */ + emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, off)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0)); +} + +static void move_stack2blob(struct bpf_gen *gen, int off, int size, int stack_off) +{ + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_10, stack_off)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, off)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0)); +} + +static void move_stack2ctx(struct bpf_gen *gen, int ctx_off, int size, int stack_off) +{ + emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_10, stack_off)); + emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_6, BPF_REG_0, ctx_off)); +} + +static void emit_sys_bpf(struct bpf_gen *gen, int cmd, int attr, int attr_size) +{ + emit(gen, BPF_MOV64_IMM(BPF_REG_1, cmd)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_2, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, attr)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, attr_size)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_bpf)); + /* remember the result in R7 */ + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); +} + +static bool is_simm16(__s64 value) +{ + return value == (__s64)(__s16)value; +} + +static void emit_check_err(struct bpf_gen *gen) +{ + __s64 off = -(gen->insn_cur - gen->insn_start - gen->cleanup_label) / 8 - 1; + + /* R7 contains result of last sys_bpf command. + * if (R7 < 0) goto cleanup; + */ + if (is_simm16(off)) { + emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, off)); + } else { + gen->error = -ERANGE; + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, -1)); + } +} + +/* reg1 and reg2 should not be R1 - R5. They can be R0, R6 - R10 */ +static void emit_debug(struct bpf_gen *gen, int reg1, int reg2, + const char *fmt, va_list args) +{ + char buf[1024]; + int addr, len, ret; + + if (!gen->log_level) + return; + ret = vsnprintf(buf, sizeof(buf), fmt, args); + if (ret < 1024 - 7 && reg1 >= 0 && reg2 < 0) + /* The special case to accommodate common debug_ret(): + * to avoid specifying BPF_REG_7 and adding " r=%%d" to + * prints explicitly. + */ + strcat(buf, " r=%d"); + len = strlen(buf) + 1; + addr = add_data(gen, buf, len); + + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, addr)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, len)); + if (reg1 >= 0) + emit(gen, BPF_MOV64_REG(BPF_REG_3, reg1)); + if (reg2 >= 0) + emit(gen, BPF_MOV64_REG(BPF_REG_4, reg2)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_trace_printk)); +} + +static void debug_regs(struct bpf_gen *gen, int reg1, int reg2, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + emit_debug(gen, reg1, reg2, fmt, args); + va_end(args); +} + +static void debug_ret(struct bpf_gen *gen, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + emit_debug(gen, BPF_REG_7, -1, fmt, args); + va_end(args); +} + +static void __emit_sys_close(struct bpf_gen *gen) +{ + emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, + /* 2 is the number of the following insns + * * 6 is additional insns in debug_regs + */ + 2 + (gen->log_level ? 6 : 0))); + emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_1)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close)); + debug_regs(gen, BPF_REG_9, BPF_REG_0, "close(%%d) = %%d"); +} + +static void emit_sys_close_stack(struct bpf_gen *gen, int stack_off) +{ + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, stack_off)); + __emit_sys_close(gen); +} + +static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off) +{ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, blob_off)); + emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0)); + __emit_sys_close(gen); +} + +int bpf_gen__finish(struct bpf_gen *gen) +{ + int i; + + emit_sys_close_stack(gen, stack_off(btf_fd)); + for (i = 0; i < gen->nr_progs; i++) + move_stack2ctx(gen, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * gen->nr_maps + + sizeof(struct bpf_prog_desc) * i + + offsetof(struct bpf_prog_desc, prog_fd), 4, + stack_off(prog_fd[i])); + for (i = 0; i < gen->nr_maps; i++) + move_stack2ctx(gen, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * i + + offsetof(struct bpf_map_desc, map_fd), 4, + stack_off(map_fd[i])); + emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0)); + emit(gen, BPF_EXIT_INSN()); + pr_debug("gen: finish %d\n", gen->error); + if (!gen->error) { + struct gen_loader_opts *opts = gen->opts; + + opts->insns = gen->insn_start; + opts->insns_sz = gen->insn_cur - gen->insn_start; + opts->data = gen->data_start; + opts->data_sz = gen->data_cur - gen->data_start; + } + return gen->error; +} + +void bpf_gen__free(struct bpf_gen *gen) +{ + if (!gen) + return; + free(gen->data_start); + free(gen->insn_start); + free(gen); +} + +void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, + __u32 btf_raw_size) +{ + int attr_size = offsetofend(union bpf_attr, btf_log_level); + int btf_data, btf_load_attr; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: load_btf: size %d\n", btf_raw_size); + btf_data = add_data(gen, btf_raw_data, btf_raw_size); + + attr.btf_size = btf_raw_size; + btf_load_attr = add_data(gen, &attr, attr_size); + + /* populate union bpf_attr with user provided log details */ + move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_level), 4, + offsetof(struct bpf_loader_ctx, log_level), false); + move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_size), 4, + offsetof(struct bpf_loader_ctx, log_size), false); + move_ctx2blob(gen, attr_field(btf_load_attr, btf_log_buf), 8, + offsetof(struct bpf_loader_ctx, log_buf), false); + /* populate union bpf_attr with a pointer to the BTF data */ + emit_rel_store(gen, attr_field(btf_load_attr, btf), btf_data); + /* emit BTF_LOAD command */ + emit_sys_bpf(gen, BPF_BTF_LOAD, btf_load_attr, attr_size); + debug_ret(gen, "btf_load size %d", btf_raw_size); + emit_check_err(gen); + /* remember btf_fd in the stack, if successful */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, stack_off(btf_fd))); +} + +void bpf_gen__map_create(struct bpf_gen *gen, + struct bpf_create_map_attr *map_attr, int map_idx) +{ + int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id); + bool close_inner_map_fd = false; + int map_create_attr; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + attr.map_type = map_attr->map_type; + attr.key_size = map_attr->key_size; + attr.value_size = map_attr->value_size; + attr.map_flags = map_attr->map_flags; + memcpy(attr.map_name, map_attr->name, + min((unsigned)strlen(map_attr->name), BPF_OBJ_NAME_LEN - 1)); + attr.numa_node = map_attr->numa_node; + attr.map_ifindex = map_attr->map_ifindex; + attr.max_entries = map_attr->max_entries; + switch (attr.map_type) { + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + case BPF_MAP_TYPE_CGROUP_ARRAY: + case BPF_MAP_TYPE_STACK_TRACE: + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH_OF_MAPS: + case BPF_MAP_TYPE_DEVMAP: + case BPF_MAP_TYPE_DEVMAP_HASH: + case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_XSKMAP: + case BPF_MAP_TYPE_SOCKMAP: + case BPF_MAP_TYPE_SOCKHASH: + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + case BPF_MAP_TYPE_RINGBUF: + break; + default: + attr.btf_key_type_id = map_attr->btf_key_type_id; + attr.btf_value_type_id = map_attr->btf_value_type_id; + } + + pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n", + attr.map_name, map_idx, map_attr->map_type, attr.btf_value_type_id); + + map_create_attr = add_data(gen, &attr, attr_size); + if (attr.btf_value_type_id) + /* populate union bpf_attr with btf_fd saved in the stack earlier */ + move_stack2blob(gen, attr_field(map_create_attr, btf_fd), 4, + stack_off(btf_fd)); + switch (attr.map_type) { + case BPF_MAP_TYPE_ARRAY_OF_MAPS: + case BPF_MAP_TYPE_HASH_OF_MAPS: + move_stack2blob(gen, attr_field(map_create_attr, inner_map_fd), 4, + stack_off(inner_map_fd)); + close_inner_map_fd = true; + break; + default: + break; + } + /* conditionally update max_entries */ + if (map_idx >= 0) + move_ctx2blob(gen, attr_field(map_create_attr, max_entries), 4, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * map_idx + + offsetof(struct bpf_map_desc, max_entries), + true /* check that max_entries != 0 */); + /* emit MAP_CREATE command */ + emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size); + debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d", + attr.map_name, map_idx, map_attr->map_type, attr.value_size, + attr.btf_value_type_id); + emit_check_err(gen); + /* remember map_fd in the stack, if successful */ + if (map_idx < 0) { + /* This bpf_gen__map_create() function is called with map_idx >= 0 + * for all maps that libbpf loading logic tracks. + * It's called with -1 to create an inner map. + */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, + stack_off(inner_map_fd))); + } else if (map_idx != gen->nr_maps) { + gen->error = -EDOM; /* internal bug */ + return; + } else { + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, + stack_off(map_fd[map_idx]))); + gen->nr_maps++; + } + if (close_inner_map_fd) + emit_sys_close_stack(gen, stack_off(inner_map_fd)); +} + +void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *attach_name, + enum bpf_attach_type type) +{ + const char *prefix; + int kind, ret; + + btf_get_kernel_prefix_kind(type, &prefix, &kind); + gen->attach_kind = kind; + ret = snprintf(gen->attach_target, sizeof(gen->attach_target), "%s%s", + prefix, attach_name); + if (ret == sizeof(gen->attach_target)) + gen->error = -ENOSPC; +} + +static void emit_find_attach_target(struct bpf_gen *gen) +{ + int name, len = strlen(gen->attach_target) + 1; + + pr_debug("gen: find_attach_tgt %s %d\n", gen->attach_target, gen->attach_kind); + name = add_data(gen, gen->attach_target, len); + + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, name)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, len)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, gen->attach_kind)); + emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind)); + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); + debug_ret(gen, "find_by_name_kind(%s,%d)", + gen->attach_target, gen->attach_kind); + emit_check_err(gen); + /* if successful, btf_id is in lower 32-bit of R7 and + * btf_obj_fd is in upper 32-bit + */ +} + +void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind, + int insn_idx) +{ + struct ksym_relo_desc *relo; + + relo = libbpf_reallocarray(gen->relos, gen->relo_cnt + 1, sizeof(*relo)); + if (!relo) { + gen->error = -ENOMEM; + return; + } + gen->relos = relo; + relo += gen->relo_cnt; + relo->name = name; + relo->kind = kind; + relo->insn_idx = insn_idx; + gen->relo_cnt++; +} + +static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns) +{ + int name, insn, len = strlen(relo->name) + 1; + + pr_debug("gen: emit_relo: %s at %d\n", relo->name, relo->insn_idx); + name = add_data(gen, relo->name, len); + + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, name)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, len)); + emit(gen, BPF_MOV64_IMM(BPF_REG_3, relo->kind)); + emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind)); + emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0)); + debug_ret(gen, "find_by_name_kind(%s,%d)", relo->name, relo->kind); + emit_check_err(gen); + /* store btf_id into insn[insn_idx].imm */ + insn = insns + sizeof(struct bpf_insn) * relo->insn_idx + + offsetof(struct bpf_insn, imm); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, insn)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, 0)); + if (relo->kind == BTF_KIND_VAR) { + /* store btf_obj_fd into insn[insn_idx + 1].imm */ + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, + sizeof(struct bpf_insn))); + } +} + +static void emit_relos(struct bpf_gen *gen, int insns) +{ + int i; + + for (i = 0; i < gen->relo_cnt; i++) + emit_relo(gen, gen->relos + i, insns); +} + +static void cleanup_relos(struct bpf_gen *gen, int insns) +{ + int i, insn; + + for (i = 0; i < gen->relo_cnt; i++) { + if (gen->relos[i].kind != BTF_KIND_VAR) + continue; + /* close fd recorded in insn[insn_idx + 1].imm */ + insn = insns + + sizeof(struct bpf_insn) * (gen->relos[i].insn_idx + 1) + + offsetof(struct bpf_insn, imm); + emit_sys_close_blob(gen, insn); + } + if (gen->relo_cnt) { + free(gen->relos); + gen->relo_cnt = 0; + gen->relos = NULL; + } +} + +void bpf_gen__prog_load(struct bpf_gen *gen, + struct bpf_prog_load_params *load_attr, int prog_idx) +{ + int attr_size = offsetofend(union bpf_attr, fd_array); + int prog_load_attr, license, insns, func_info, line_info; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: prog_load: type %d insns_cnt %zd\n", + load_attr->prog_type, load_attr->insn_cnt); + /* add license string to blob of bytes */ + license = add_data(gen, load_attr->license, strlen(load_attr->license) + 1); + /* add insns to blob of bytes */ + insns = add_data(gen, load_attr->insns, + load_attr->insn_cnt * sizeof(struct bpf_insn)); + + attr.prog_type = load_attr->prog_type; + attr.expected_attach_type = load_attr->expected_attach_type; + attr.attach_btf_id = load_attr->attach_btf_id; + attr.prog_ifindex = load_attr->prog_ifindex; + attr.kern_version = 0; + attr.insn_cnt = (__u32)load_attr->insn_cnt; + attr.prog_flags = load_attr->prog_flags; + + attr.func_info_rec_size = load_attr->func_info_rec_size; + attr.func_info_cnt = load_attr->func_info_cnt; + func_info = add_data(gen, load_attr->func_info, + attr.func_info_cnt * attr.func_info_rec_size); + + attr.line_info_rec_size = load_attr->line_info_rec_size; + attr.line_info_cnt = load_attr->line_info_cnt; + line_info = add_data(gen, load_attr->line_info, + attr.line_info_cnt * attr.line_info_rec_size); + + memcpy(attr.prog_name, load_attr->name, + min((unsigned)strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1)); + prog_load_attr = add_data(gen, &attr, attr_size); + + /* populate union bpf_attr with a pointer to license */ + emit_rel_store(gen, attr_field(prog_load_attr, license), license); + + /* populate union bpf_attr with a pointer to instructions */ + emit_rel_store(gen, attr_field(prog_load_attr, insns), insns); + + /* populate union bpf_attr with a pointer to func_info */ + emit_rel_store(gen, attr_field(prog_load_attr, func_info), func_info); + + /* populate union bpf_attr with a pointer to line_info */ + emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info); + + /* populate union bpf_attr fd_array with a pointer to stack where map_fds are saved */ + emit_rel_store_sp(gen, attr_field(prog_load_attr, fd_array), + stack_off(map_fd[0])); + + /* populate union bpf_attr with user provided log details */ + move_ctx2blob(gen, attr_field(prog_load_attr, log_level), 4, + offsetof(struct bpf_loader_ctx, log_level), false); + move_ctx2blob(gen, attr_field(prog_load_attr, log_size), 4, + offsetof(struct bpf_loader_ctx, log_size), false); + move_ctx2blob(gen, attr_field(prog_load_attr, log_buf), 8, + offsetof(struct bpf_loader_ctx, log_buf), false); + /* populate union bpf_attr with btf_fd saved in the stack earlier */ + move_stack2blob(gen, attr_field(prog_load_attr, prog_btf_fd), 4, + stack_off(btf_fd)); + if (gen->attach_kind) { + emit_find_attach_target(gen); + /* populate union bpf_attr with btf_id and btf_obj_fd found by helper */ + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, prog_load_attr)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, + offsetof(union bpf_attr, attach_btf_id))); + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32)); + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, + offsetof(union bpf_attr, attach_btf_obj_fd))); + } + emit_relos(gen, insns); + /* emit PROG_LOAD command */ + emit_sys_bpf(gen, BPF_PROG_LOAD, prog_load_attr, attr_size); + debug_ret(gen, "prog_load %s insn_cnt %d", attr.prog_name, attr.insn_cnt); + /* successful or not, close btf module FDs used in extern ksyms and attach_btf_obj_fd */ + cleanup_relos(gen, insns); + if (gen->attach_kind) + emit_sys_close_blob(gen, + attr_field(prog_load_attr, attach_btf_obj_fd)); + emit_check_err(gen); + /* remember prog_fd in the stack, if successful */ + emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, + stack_off(prog_fd[gen->nr_progs]))); + gen->nr_progs++; +} + +void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, + __u32 value_size) +{ + int attr_size = offsetofend(union bpf_attr, flags); + int map_update_attr, value, key; + union bpf_attr attr; + int zero = 0; + + memset(&attr, 0, attr_size); + pr_debug("gen: map_update_elem: idx %d\n", map_idx); + + value = add_data(gen, pvalue, value_size); + key = add_data(gen, &zero, sizeof(zero)); + + /* if (map_desc[map_idx].initial_value) + * copy_from_user(value, initial_value, value_size); + */ + emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6, + sizeof(struct bpf_loader_ctx) + + sizeof(struct bpf_map_desc) * map_idx + + offsetof(struct bpf_map_desc, initial_value))); + emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 4)); + emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE, + 0, 0, 0, value)); + emit(gen, BPF_MOV64_IMM(BPF_REG_2, value_size)); + emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user)); + + map_update_attr = add_data(gen, &attr, attr_size); + move_stack2blob(gen, attr_field(map_update_attr, map_fd), 4, + stack_off(map_fd[map_idx])); + emit_rel_store(gen, attr_field(map_update_attr, key), key); + emit_rel_store(gen, attr_field(map_update_attr, value), value); + /* emit MAP_UPDATE_ELEM command */ + emit_sys_bpf(gen, BPF_MAP_UPDATE_ELEM, map_update_attr, attr_size); + debug_ret(gen, "update_elem idx %d value_size %d", map_idx, value_size); + emit_check_err(gen); +} + +void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx) +{ + int attr_size = offsetofend(union bpf_attr, map_fd); + int map_freeze_attr; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: map_freeze: idx %d\n", map_idx); + map_freeze_attr = add_data(gen, &attr, attr_size); + move_stack2blob(gen, attr_field(map_freeze_attr, map_fd), 4, + stack_off(map_fd[map_idx])); + /* emit MAP_FREEZE command */ + emit_sys_bpf(gen, BPF_MAP_FREEZE, map_freeze_attr, attr_size); + debug_ret(gen, "map_freeze"); + emit_check_err(gen); +} diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index c41d9b2b59ac..1e04ce724240 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -54,6 +54,7 @@ #include "str_error.h" #include "libbpf_internal.h" #include "hashmap.h" +#include "bpf_gen_internal.h" #ifndef BPF_FS_MAGIC #define BPF_FS_MAGIC 0xcafe4a11 @@ -150,6 +151,23 @@ static inline __u64 ptr_to_u64(const void *ptr) return (__u64) (unsigned long) ptr; } +/* this goes away in libbpf 1.0 */ +enum libbpf_strict_mode libbpf_mode = LIBBPF_STRICT_NONE; + +int libbpf_set_strict_mode(enum libbpf_strict_mode mode) +{ + /* __LIBBPF_STRICT_LAST is the last power-of-2 value used + 1, so to + * get all possible values we compensate last +1, and then (2*x - 1) + * to get the bit mask + */ + if (mode != LIBBPF_STRICT_ALL + && (mode & ~((__LIBBPF_STRICT_LAST - 1) * 2 - 1))) + return errno = EINVAL, -EINVAL; + + libbpf_mode = mode; + return 0; +} + enum kern_feature_id { /* v4.14: kernel support for program & map names. */ FEAT_PROG_NAME, @@ -178,7 +196,7 @@ enum kern_feature_id { __FEAT_CNT, }; -static bool kernel_supports(enum kern_feature_id feat_id); +static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id); enum reloc_type { RELO_LD64, @@ -432,6 +450,8 @@ struct bpf_object { bool loaded; bool has_subcalls; + struct bpf_gen *gen_loader; + /* * Information when doing elf related work. Only valid if fd * is valid. @@ -677,6 +697,11 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return -LIBBPF_ERRNO__FORMAT; } + if (sec_idx != obj->efile.text_shndx && GELF_ST_BIND(sym.st_info) == STB_LOCAL) { + pr_warn("sec '%s': program '%s' is static and not supported\n", sec_name, name); + return -ENOTSUP; + } + pr_debug("sec '%s': found program '%s' at insn offset %zu (%zu bytes), code size %zu insns (%zu bytes)\n", sec_name, name, sec_off / BPF_INSN_SZ, sec_off, prog_sz / BPF_INSN_SZ, prog_sz); @@ -700,13 +725,14 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, if (err) return err; - /* if function is a global/weak symbol, but has hidden - * visibility (STV_HIDDEN), mark its BTF FUNC as static to - * enable more permissive BPF verification mode with more - * outside context available to BPF verifier + /* if function is a global/weak symbol, but has restricted + * (STV_HIDDEN or STV_INTERNAL) visibility, mark its BTF FUNC + * as static to enable more permissive BPF verification mode + * with more outside context available to BPF verifier */ if (GELF_ST_BIND(sym.st_info) != STB_LOCAL - && GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN) + && (GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN + || GELF_ST_VISIBILITY(sym.st_other) == STV_INTERNAL)) prog->mark_btf_static = true; nr_progs++; @@ -1794,7 +1820,6 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) if (!symbols) return -EINVAL; - scn = elf_sec_by_idx(obj, obj->efile.maps_shndx); data = elf_sec_data(obj, scn); if (!scn || !data) { @@ -1854,6 +1879,12 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict) return -LIBBPF_ERRNO__FORMAT; } + if (GELF_ST_TYPE(sym.st_info) == STT_SECTION + || GELF_ST_BIND(sym.st_info) == STB_LOCAL) { + pr_warn("map '%s' (legacy): static maps are not supported\n", map_name); + return -ENOTSUP; + } + map->libbpf_type = LIBBPF_MAP_UNSPEC; map->sec_idx = sym.st_shndx; map->sec_offset = sym.st_value; @@ -2261,6 +2292,16 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def pr_debug("map '%s': found inner map definition.\n", map->name); } +static const char *btf_var_linkage_str(__u32 linkage) +{ + switch (linkage) { + case BTF_VAR_STATIC: return "static"; + case BTF_VAR_GLOBAL_ALLOCATED: return "global"; + case BTF_VAR_GLOBAL_EXTERN: return "extern"; + default: return "unknown"; + } +} + static int bpf_object__init_user_btf_map(struct bpf_object *obj, const struct btf_type *sec, int var_idx, int sec_idx, @@ -2293,10 +2334,9 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, map_name, btf_kind_str(var)); return -EINVAL; } - if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED && - var_extra->linkage != BTF_VAR_STATIC) { - pr_warn("map '%s': unsupported var linkage %u.\n", - map_name, var_extra->linkage); + if (var_extra->linkage != BTF_VAR_GLOBAL_ALLOCATED) { + pr_warn("map '%s': unsupported map linkage %s.\n", + map_name, btf_var_linkage_str(var_extra->linkage)); return -EOPNOTSUPP; } @@ -2425,10 +2465,8 @@ static int bpf_object__init_maps(struct bpf_object *obj, err = err ?: bpf_object__init_global_data_maps(obj); err = err ?: bpf_object__init_kconfig_map(obj); err = err ?: bpf_object__init_struct_ops_maps(obj); - if (err) - return err; - return 0; + return err; } static bool section_have_execinstr(struct bpf_object *obj, int idx) @@ -2443,20 +2481,20 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx) static bool btf_needs_sanitization(struct bpf_object *obj) { - bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC); - bool has_datasec = kernel_supports(FEAT_BTF_DATASEC); - bool has_float = kernel_supports(FEAT_BTF_FLOAT); - bool has_func = kernel_supports(FEAT_BTF_FUNC); + bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC); + bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); + bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); + bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); return !has_func || !has_datasec || !has_func_global || !has_float; } static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) { - bool has_func_global = kernel_supports(FEAT_BTF_GLOBAL_FUNC); - bool has_datasec = kernel_supports(FEAT_BTF_DATASEC); - bool has_float = kernel_supports(FEAT_BTF_FLOAT); - bool has_func = kernel_supports(FEAT_BTF_FUNC); + bool has_func_global = kernel_supports(obj, FEAT_BTF_GLOBAL_FUNC); + bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); + bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); + bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); struct btf_type *t; int i, j, vlen; @@ -2539,16 +2577,14 @@ static int bpf_object__init_btf(struct bpf_object *obj, if (btf_data) { obj->btf = btf__new(btf_data->d_buf, btf_data->d_size); - if (IS_ERR(obj->btf)) { - err = PTR_ERR(obj->btf); + err = libbpf_get_error(obj->btf); + if (err) { obj->btf = NULL; - pr_warn("Error loading ELF section %s: %d.\n", - BTF_ELF_SEC, err); + pr_warn("Error loading ELF section %s: %d.\n", BTF_ELF_SEC, err); goto out; } /* enforce 8-byte pointers for BPF-targeted BTFs */ btf__set_pointer_size(obj->btf, 8); - err = 0; } if (btf_ext_data) { if (!obj->btf) { @@ -2556,11 +2592,11 @@ static int bpf_object__init_btf(struct bpf_object *obj, BTF_EXT_ELF_SEC, BTF_ELF_SEC); goto out; } - obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, - btf_ext_data->d_size); - if (IS_ERR(obj->btf_ext)) { - pr_warn("Error loading ELF section %s: %ld. Ignored and continue.\n", - BTF_EXT_ELF_SEC, PTR_ERR(obj->btf_ext)); + obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size); + err = libbpf_get_error(obj->btf_ext); + if (err) { + pr_warn("Error loading ELF section %s: %d. Ignored and continue.\n", + BTF_EXT_ELF_SEC, err); obj->btf_ext = NULL; goto out; } @@ -2637,15 +2673,15 @@ static int bpf_object__load_vmlinux_btf(struct bpf_object *obj, bool force) int err; /* btf_vmlinux could be loaded earlier */ - if (obj->btf_vmlinux) + if (obj->btf_vmlinux || obj->gen_loader) return 0; if (!force && !obj_needs_vmlinux_btf(obj)) return 0; obj->btf_vmlinux = libbpf_find_kernel_btf(); - if (IS_ERR(obj->btf_vmlinux)) { - err = PTR_ERR(obj->btf_vmlinux); + err = libbpf_get_error(obj->btf_vmlinux); + if (err) { pr_warn("Error loading vmlinux BTF: %d\n", err); obj->btf_vmlinux = NULL; return err; @@ -2662,7 +2698,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) if (!obj->btf) return 0; - if (!kernel_supports(FEAT_BTF)) { + if (!kernel_supports(obj, FEAT_BTF)) { if (kernel_needs_btf(obj)) { err = -EOPNOTSUPP; goto report; @@ -2711,15 +2747,29 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) /* clone BTF to sanitize a copy and leave the original intact */ raw_data = btf__get_raw_data(obj->btf, &sz); kern_btf = btf__new(raw_data, sz); - if (IS_ERR(kern_btf)) - return PTR_ERR(kern_btf); + err = libbpf_get_error(kern_btf); + if (err) + return err; /* enforce 8-byte pointers for BPF-targeted BTFs */ btf__set_pointer_size(obj->btf, 8); bpf_object__sanitize_btf(obj, kern_btf); } - err = btf__load(kern_btf); + if (obj->gen_loader) { + __u32 raw_size = 0; + const void *raw_data = btf__get_raw_data(kern_btf, &raw_size); + + if (!raw_data) + return -ENOMEM; + bpf_gen__load_btf(obj->gen_loader, raw_data, raw_size); + /* Pretend to have valid FD to pass various fd >= 0 checks. + * This fd == 0 will not be used with any syscall and will be reset to -1 eventually. + */ + btf__set_fd(kern_btf, 0); + } else { + err = btf__load(kern_btf); + } if (sanitize) { if (!err) { /* move fd to libbpf's BTF */ @@ -3473,7 +3523,7 @@ bpf_object__find_program_by_title(const struct bpf_object *obj, if (pos->sec_name && !strcmp(pos->sec_name, title)) return pos; } - return NULL; + return errno = ENOENT, NULL; } static bool prog_is_subprog(const struct bpf_object *obj, @@ -3506,7 +3556,7 @@ bpf_object__find_program_by_name(const struct bpf_object *obj, if (!strcmp(prog->name, name)) return prog; } - return NULL; + return errno = ENOENT, NULL; } static bool bpf_object__shndx_is_data(const struct bpf_object *obj, @@ -3853,11 +3903,11 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd) err = bpf_obj_get_info_by_fd(fd, &info, &len); if (err) - return err; + return libbpf_err(err); new_name = strdup(info.name); if (!new_name) - return -errno; + return libbpf_err(-errno); new_fd = open("/", O_RDONLY | O_CLOEXEC); if (new_fd < 0) { @@ -3895,7 +3945,7 @@ err_close_new_fd: close(new_fd); err_free_new_name: free(new_name); - return err; + return libbpf_err(err); } __u32 bpf_map__max_entries(const struct bpf_map *map) @@ -3906,7 +3956,7 @@ __u32 bpf_map__max_entries(const struct bpf_map *map) struct bpf_map *bpf_map__inner_map(struct bpf_map *map) { if (!bpf_map_type__is_map_in_map(map->def.type)) - return NULL; + return errno = EINVAL, NULL; return map->inner_map; } @@ -3914,7 +3964,7 @@ struct bpf_map *bpf_map__inner_map(struct bpf_map *map) int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) { if (map->fd >= 0) - return -EBUSY; + return libbpf_err(-EBUSY); map->def.max_entries = max_entries; return 0; } @@ -3922,7 +3972,7 @@ int bpf_map__set_max_entries(struct bpf_map *map, __u32 max_entries) int bpf_map__resize(struct bpf_map *map, __u32 max_entries) { if (!map || !max_entries) - return -EINVAL; + return libbpf_err(-EINVAL); return bpf_map__set_max_entries(map, max_entries); } @@ -3938,6 +3988,9 @@ bpf_object__probe_loading(struct bpf_object *obj) }; int ret; + if (obj->gen_loader) + return 0; + /* make sure basic loading works */ memset(&attr, 0, sizeof(attr)); @@ -3947,6 +4000,10 @@ bpf_object__probe_loading(struct bpf_object *obj) attr.license = "GPL"; ret = bpf_load_program_xattr(&attr, NULL, 0); + if (ret < 0) { + attr.prog_type = BPF_PROG_TYPE_TRACEPOINT; + ret = bpf_load_program_xattr(&attr, NULL, 0); + } if (ret < 0) { ret = errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4293,11 +4350,17 @@ static struct kern_feature_desc { }, }; -static bool kernel_supports(enum kern_feature_id feat_id) +static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) { struct kern_feature_desc *feat = &feature_probes[feat_id]; int ret; + if (obj->gen_loader) + /* To generate loader program assume the latest kernel + * to avoid doing extra prog_load, map_create syscalls. + */ + return true; + if (READ_ONCE(feat->res) == FEAT_UNKNOWN) { ret = feat->probe(); if (ret > 0) { @@ -4380,6 +4443,13 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) char *cp, errmsg[STRERR_BUFSIZE]; int err, zero = 0; + if (obj->gen_loader) { + bpf_gen__map_update_elem(obj->gen_loader, map - obj->maps, + map->mmaped, map->def.value_size); + if (map_type == LIBBPF_MAP_RODATA || map_type == LIBBPF_MAP_KCONFIG) + bpf_gen__map_freeze(obj->gen_loader, map - obj->maps); + return 0; + } err = bpf_map_update_elem(map->fd, &zero, map->mmaped, 0); if (err) { err = -errno; @@ -4405,14 +4475,14 @@ bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map) static void bpf_map__destroy(struct bpf_map *map); -static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) +static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner) { struct bpf_create_map_attr create_attr; struct bpf_map_def *def = &map->def; memset(&create_attr, 0, sizeof(create_attr)); - if (kernel_supports(FEAT_PROG_NAME)) + if (kernel_supports(obj, FEAT_PROG_NAME)) create_attr.name = map->name; create_attr.map_ifindex = map->map_ifindex; create_attr.map_type = def->type; @@ -4453,7 +4523,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) if (map->inner_map) { int err; - err = bpf_object__create_map(obj, map->inner_map); + err = bpf_object__create_map(obj, map->inner_map, true); if (err) { pr_warn("map '%s': failed to create inner map: %d\n", map->name, err); @@ -4465,7 +4535,15 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) create_attr.inner_map_fd = map->inner_map_fd; } - map->fd = bpf_create_map_xattr(&create_attr); + if (obj->gen_loader) { + bpf_gen__map_create(obj->gen_loader, &create_attr, is_inner ? -1 : map - obj->maps); + /* Pretend to have valid FD to pass various fd >= 0 checks. + * This fd == 0 will not be used with any syscall and will be reset to -1 eventually. + */ + map->fd = 0; + } else { + map->fd = bpf_create_map_xattr(&create_attr); + } if (map->fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { char *cp, errmsg[STRERR_BUFSIZE]; @@ -4486,6 +4564,8 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) return -errno; if (bpf_map_type__is_map_in_map(def->type) && map->inner_map) { + if (obj->gen_loader) + map->inner_map->fd = -1; bpf_map__destroy(map->inner_map); zfree(&map->inner_map); } @@ -4493,11 +4573,11 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map) return 0; } -static int init_map_slots(struct bpf_map *map) +static int init_map_slots(struct bpf_object *obj, struct bpf_map *map) { const struct bpf_map *targ_map; unsigned int i; - int fd, err; + int fd, err = 0; for (i = 0; i < map->init_slots_sz; i++) { if (!map->init_slots[i]) @@ -4505,7 +4585,13 @@ static int init_map_slots(struct bpf_map *map) targ_map = map->init_slots[i]; fd = bpf_map__fd(targ_map); - err = bpf_map_update_elem(map->fd, &i, &fd, 0); + if (obj->gen_loader) { + pr_warn("// TODO map_update_elem: idx %td key %d value==map_idx %td\n", + map - obj->maps, i, targ_map - obj->maps); + return -ENOTSUP; + } else { + err = bpf_map_update_elem(map->fd, &i, &fd, 0); + } if (err) { err = -errno; pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n", @@ -4547,7 +4633,7 @@ bpf_object__create_maps(struct bpf_object *obj) pr_debug("map '%s': skipping creation (preset fd=%d)\n", map->name, map->fd); } else { - err = bpf_object__create_map(obj, map); + err = bpf_object__create_map(obj, map, false); if (err) goto err_out; @@ -4563,7 +4649,7 @@ bpf_object__create_maps(struct bpf_object *obj) } if (map->init_slots_sz) { - err = init_map_slots(map); + err = init_map_slots(obj, map); if (err < 0) { zclose(map->fd); goto err_out; @@ -4973,11 +5059,14 @@ static int load_module_btfs(struct bpf_object *obj) if (obj->btf_modules_loaded) return 0; + if (obj->gen_loader) + return 0; + /* don't do this again, even if we find no module BTFs */ obj->btf_modules_loaded = true; /* kernel too old to support module BTFs */ - if (!kernel_supports(FEAT_MODULE_BTF)) + if (!kernel_supports(obj, FEAT_MODULE_BTF)) return 0; while (true) { @@ -5018,10 +5107,10 @@ static int load_module_btfs(struct bpf_object *obj) } btf = btf_get_from_fd(fd, obj->btf_vmlinux); - if (IS_ERR(btf)) { - pr_warn("failed to load module [%s]'s BTF object #%d: %ld\n", - name, id, PTR_ERR(btf)); - err = PTR_ERR(btf); + err = libbpf_get_error(btf); + if (err) { + pr_warn("failed to load module [%s]'s BTF object #%d: %d\n", + name, id, err); goto err_out; } @@ -6120,6 +6209,12 @@ static int bpf_core_apply_relo(struct bpf_program *prog, if (str_is_empty(spec_str)) return -EINVAL; + if (prog->obj->gen_loader) { + pr_warn("// TODO core_relo: prog %td insn[%d] %s %s kind %d\n", + prog - prog->obj->programs, relo->insn_off / 8, + local_name, spec_str, relo->kind); + return -ENOTSUP; + } err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec); if (err) { pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n", @@ -6275,8 +6370,8 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) if (targ_btf_path) { obj->btf_vmlinux_override = btf__parse(targ_btf_path, NULL); - if (IS_ERR_OR_NULL(obj->btf_vmlinux_override)) { - err = PTR_ERR(obj->btf_vmlinux_override); + err = libbpf_get_error(obj->btf_vmlinux_override); + if (err) { pr_warn("failed to parse target BTF: %d\n", err); return err; } @@ -6371,19 +6466,34 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) switch (relo->type) { case RELO_LD64: - insn[0].src_reg = BPF_PSEUDO_MAP_FD; - insn[0].imm = obj->maps[relo->map_idx].fd; + if (obj->gen_loader) { + insn[0].src_reg = BPF_PSEUDO_MAP_IDX; + insn[0].imm = relo->map_idx; + } else { + insn[0].src_reg = BPF_PSEUDO_MAP_FD; + insn[0].imm = obj->maps[relo->map_idx].fd; + } break; case RELO_DATA: - insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; insn[1].imm = insn[0].imm + relo->sym_off; - insn[0].imm = obj->maps[relo->map_idx].fd; + if (obj->gen_loader) { + insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE; + insn[0].imm = relo->map_idx; + } else { + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[0].imm = obj->maps[relo->map_idx].fd; + } break; case RELO_EXTERN_VAR: ext = &obj->externs[relo->sym_off]; if (ext->type == EXT_KCFG) { - insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; - insn[0].imm = obj->maps[obj->kconfig_map_idx].fd; + if (obj->gen_loader) { + insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE; + insn[0].imm = obj->kconfig_map_idx; + } else { + insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; + insn[0].imm = obj->maps[obj->kconfig_map_idx].fd; + } insn[1].imm = ext->kcfg.data_off; } else /* EXT_KSYM */ { if (ext->ksym.type_id) { /* typed ksyms */ @@ -6402,11 +6512,15 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) insn[0].imm = ext->ksym.kernel_btf_id; break; case RELO_SUBPROG_ADDR: - insn[0].src_reg = BPF_PSEUDO_FUNC; - /* will be handled as a follow up pass */ + if (insn[0].src_reg != BPF_PSEUDO_FUNC) { + pr_warn("prog '%s': relo #%d: bad insn\n", + prog->name, i); + return -EINVAL; + } + /* handled already */ break; case RELO_CALL: - /* will be handled as a follow up pass */ + /* handled already */ break; default: pr_warn("prog '%s': relo #%d: bad relo type %d\n", @@ -6497,7 +6611,7 @@ reloc_prog_func_and_line_info(const struct bpf_object *obj, /* no .BTF.ext relocation if .BTF.ext is missing or kernel doesn't * supprot func/line info */ - if (!obj->btf_ext || !kernel_supports(FEAT_BTF_FUNC)) + if (!obj->btf_ext || !kernel_supports(obj, FEAT_BTF_FUNC)) return 0; /* only attempt func info relocation if main program's func_info @@ -6575,6 +6689,30 @@ static struct reloc_desc *find_prog_insn_relo(const struct bpf_program *prog, si sizeof(*prog->reloc_desc), cmp_relo_by_insn_idx); } +static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_program *subprog) +{ + int new_cnt = main_prog->nr_reloc + subprog->nr_reloc; + struct reloc_desc *relos; + int i; + + if (main_prog == subprog) + return 0; + relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos)); + if (!relos) + return -ENOMEM; + memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, + sizeof(*relos) * subprog->nr_reloc); + + for (i = main_prog->nr_reloc; i < new_cnt; i++) + relos[i].insn_idx += subprog->sub_insn_off; + /* After insn_idx adjustment the 'relos' array is still sorted + * by insn_idx and doesn't break bsearch. + */ + main_prog->reloc_desc = relos; + main_prog->nr_reloc = new_cnt; + return 0; +} + static int bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, struct bpf_program *prog) @@ -6595,6 +6733,11 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, continue; relo = find_prog_insn_relo(prog, insn_idx); + if (relo && relo->type == RELO_EXTERN_FUNC) + /* kfunc relocations will be handled later + * in bpf_object__relocate_data() + */ + continue; if (relo && relo->type != RELO_CALL && relo->type != RELO_SUBPROG_ADDR) { pr_warn("prog '%s': unexpected relo for insn #%zu, type %d\n", prog->name, insn_idx, relo->type); @@ -6669,6 +6812,10 @@ bpf_object__reloc_code(struct bpf_object *obj, struct bpf_program *main_prog, pr_debug("prog '%s': added %zu insns from sub-prog '%s'\n", main_prog->name, subprog->insns_cnt, subprog->name); + /* The subprog insns are now appended. Append its relos too. */ + err = append_subprog_relos(main_prog, subprog); + if (err) + return err; err = bpf_object__reloc_code(obj, main_prog, subprog); if (err) return err; @@ -6798,11 +6945,25 @@ bpf_object__relocate_calls(struct bpf_object *obj, struct bpf_program *prog) return 0; } +static void +bpf_object__free_relocs(struct bpf_object *obj) +{ + struct bpf_program *prog; + int i; + + /* free up relocation descriptors */ + for (i = 0; i < obj->nr_programs; i++) { + prog = &obj->programs[i]; + zfree(&prog->reloc_desc); + prog->nr_reloc = 0; + } +} + static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) { struct bpf_program *prog; - size_t i; + size_t i, j; int err; if (obj->btf_ext) { @@ -6813,23 +6974,32 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) return err; } } - /* relocate data references first for all programs and sub-programs, - * as they don't change relative to code locations, so subsequent - * subprogram processing won't need to re-calculate any of them + + /* Before relocating calls pre-process relocations and mark + * few ld_imm64 instructions that points to subprogs. + * Otherwise bpf_object__reloc_code() later would have to consider + * all ld_imm64 insns as relocation candidates. That would + * reduce relocation speed, since amount of find_prog_insn_relo() + * would increase and most of them will fail to find a relo. */ for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; - err = bpf_object__relocate_data(obj, prog); - if (err) { - pr_warn("prog '%s': failed to relocate data references: %d\n", - prog->name, err); - return err; + for (j = 0; j < prog->nr_reloc; j++) { + struct reloc_desc *relo = &prog->reloc_desc[j]; + struct bpf_insn *insn = &prog->insns[relo->insn_idx]; + + /* mark the insn, so it's recognized by insn_is_pseudo_func() */ + if (relo->type == RELO_SUBPROG_ADDR) + insn[0].src_reg = BPF_PSEUDO_FUNC; } } - /* now relocate subprogram calls and append used subprograms to main + + /* relocate subprogram calls and append used subprograms to main * programs; each copy of subprogram code needs to be relocated * differently for each main program, because its code location might - * have changed + * have changed. + * Append subprog relos to main programs to allow data relos to be + * processed after text is completely relocated. */ for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; @@ -6846,12 +7016,20 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) return err; } } - /* free up relocation descriptors */ + /* Process data relos for main programs */ for (i = 0; i < obj->nr_programs; i++) { prog = &obj->programs[i]; - zfree(&prog->reloc_desc); - prog->nr_reloc = 0; + if (prog_is_subprog(obj, prog)) + continue; + err = bpf_object__relocate_data(obj, prog); + if (err) { + pr_warn("prog '%s': failed to relocate data references: %d\n", + prog->name, err); + return err; + } } + if (!obj->gen_loader) + bpf_object__free_relocs(obj); return 0; } @@ -7040,6 +7218,9 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program enum bpf_func_id func_id; int i; + if (obj->gen_loader) + return 0; + for (i = 0; i < prog->insns_cnt; i++, insn++) { if (!insn_is_helper_call(insn, &func_id)) continue; @@ -7051,12 +7232,12 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program switch (func_id) { case BPF_FUNC_probe_read_kernel: case BPF_FUNC_probe_read_user: - if (!kernel_supports(FEAT_PROBE_READ_KERN)) + if (!kernel_supports(obj, FEAT_PROBE_READ_KERN)) insn->imm = BPF_FUNC_probe_read; break; case BPF_FUNC_probe_read_kernel_str: case BPF_FUNC_probe_read_user_str: - if (!kernel_supports(FEAT_PROBE_READ_KERN)) + if (!kernel_supports(obj, FEAT_PROBE_READ_KERN)) insn->imm = BPF_FUNC_probe_read_str; break; default: @@ -7091,12 +7272,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.prog_type = prog->type; /* old kernels might not support specifying expected_attach_type */ - if (!kernel_supports(FEAT_EXP_ATTACH_TYPE) && prog->sec_def && + if (!kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE) && prog->sec_def && prog->sec_def->is_exp_attach_type_optional) load_attr.expected_attach_type = 0; else load_attr.expected_attach_type = prog->expected_attach_type; - if (kernel_supports(FEAT_PROG_NAME)) + if (kernel_supports(prog->obj, FEAT_PROG_NAME)) load_attr.name = prog->name; load_attr.insns = insns; load_attr.insn_cnt = insns_cnt; @@ -7112,7 +7293,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, /* specify func_info/line_info only if kernel supports them */ btf_fd = bpf_object__btf_fd(prog->obj); - if (btf_fd >= 0 && kernel_supports(FEAT_BTF_FUNC)) { + if (btf_fd >= 0 && kernel_supports(prog->obj, FEAT_BTF_FUNC)) { load_attr.prog_btf_fd = btf_fd; load_attr.func_info = prog->func_info; load_attr.func_info_rec_size = prog->func_info_rec_size; @@ -7124,6 +7305,12 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, load_attr.log_level = prog->log_level; load_attr.prog_flags = prog->prog_flags; + if (prog->obj->gen_loader) { + bpf_gen__prog_load(prog->obj->gen_loader, &load_attr, + prog - prog->obj->programs); + *pfd = -1; + return 0; + } retry_load: if (log_buf_size) { log_buf = malloc(log_buf_size); @@ -7142,7 +7329,7 @@ retry_load: pr_debug("verifier log:\n%s", log_buf); if (prog->obj->rodata_map_idx >= 0 && - kernel_supports(FEAT_PROG_BIND_MAP)) { + kernel_supports(prog->obj, FEAT_PROG_BIND_MAP)) { struct bpf_map *rodata_map = &prog->obj->maps[prog->obj->rodata_map_idx]; @@ -7201,6 +7388,38 @@ out: return ret; } +static int bpf_program__record_externs(struct bpf_program *prog) +{ + struct bpf_object *obj = prog->obj; + int i; + + for (i = 0; i < prog->nr_reloc; i++) { + struct reloc_desc *relo = &prog->reloc_desc[i]; + struct extern_desc *ext = &obj->externs[relo->sym_off]; + + switch (relo->type) { + case RELO_EXTERN_VAR: + if (ext->type != EXT_KSYM) + continue; + if (!ext->ksym.type_id) { + pr_warn("typeless ksym %s is not supported yet\n", + ext->name); + return -ENOTSUP; + } + bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_VAR, + relo->insn_idx); + break; + case RELO_EXTERN_FUNC: + bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_FUNC, + relo->insn_idx); + break; + default: + continue; + } + } + return 0; +} + static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id); int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) @@ -7209,7 +7428,7 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) if (prog->obj->loaded) { pr_warn("prog '%s': can't load after object was loaded\n", prog->name); - return -EINVAL; + return libbpf_err(-EINVAL); } if ((prog->type == BPF_PROG_TYPE_TRACING || @@ -7219,7 +7438,7 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id); if (err) - return err; + return libbpf_err(err); prog->attach_btf_obj_fd = btf_obj_fd; prog->attach_btf_id = btf_type_id; @@ -7229,13 +7448,13 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) if (prog->preprocessor) { pr_warn("Internal error: can't load program '%s'\n", prog->name); - return -LIBBPF_ERRNO__INTERNAL; + return libbpf_err(-LIBBPF_ERRNO__INTERNAL); } prog->instances.fds = malloc(sizeof(int)); if (!prog->instances.fds) { pr_warn("Not enough memory for BPF fds\n"); - return -ENOMEM; + return libbpf_err(-ENOMEM); } prog->instances.nr = 1; prog->instances.fds[0] = -1; @@ -7246,6 +7465,8 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) pr_warn("prog '%s': inconsistent nr(%d) != 1\n", prog->name, prog->instances.nr); } + if (prog->obj->gen_loader) + bpf_program__record_externs(prog); err = load_program(prog, prog->insns, prog->insns_cnt, license, kern_ver, &fd); if (!err) @@ -7292,7 +7513,7 @@ out: pr_warn("failed to load program '%s'\n", prog->name); zfree(&prog->insns); prog->insns_cnt = 0; - return err; + return libbpf_err(err); } static int @@ -7322,6 +7543,8 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) if (err) return err; } + if (obj->gen_loader) + bpf_object__free_relocs(obj); return 0; } @@ -7423,7 +7646,7 @@ __bpf_object__open_xattr(struct bpf_object_open_attr *attr, int flags) struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr) { - return __bpf_object__open_xattr(attr, 0); + return libbpf_ptr(__bpf_object__open_xattr(attr, 0)); } struct bpf_object *bpf_object__open(const char *path) @@ -7433,18 +7656,18 @@ struct bpf_object *bpf_object__open(const char *path) .prog_type = BPF_PROG_TYPE_UNSPEC, }; - return bpf_object__open_xattr(&attr); + return libbpf_ptr(__bpf_object__open_xattr(&attr, 0)); } struct bpf_object * bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts) { if (!path) - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); pr_debug("loading %s\n", path); - return __bpf_object__open(path, NULL, 0, opts); + return libbpf_ptr(__bpf_object__open(path, NULL, 0, opts)); } struct bpf_object * @@ -7452,9 +7675,9 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts) { if (!obj_buf || obj_buf_sz == 0) - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); - return __bpf_object__open(NULL, obj_buf, obj_buf_sz, opts); + return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, opts)); } struct bpf_object * @@ -7469,9 +7692,9 @@ bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, /* returning NULL is wrong, but backwards-compatible */ if (!obj_buf || obj_buf_sz == 0) - return NULL; + return errno = EINVAL, NULL; - return bpf_object__open_mem(obj_buf, obj_buf_sz, &opts); + return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, &opts)); } int bpf_object__unload(struct bpf_object *obj) @@ -7479,7 +7702,7 @@ int bpf_object__unload(struct bpf_object *obj) size_t i; if (!obj) - return -EINVAL; + return libbpf_err(-EINVAL); for (i = 0; i < obj->nr_maps; i++) { zclose(obj->maps[i].fd); @@ -7500,11 +7723,11 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj) bpf_object__for_each_map(m, obj) { if (!bpf_map__is_internal(m)) continue; - if (!kernel_supports(FEAT_GLOBAL_DATA)) { + if (!kernel_supports(obj, FEAT_GLOBAL_DATA)) { pr_warn("kernel doesn't support global data\n"); return -ENOTSUP; } - if (!kernel_supports(FEAT_ARRAY_MMAP)) + if (!kernel_supports(obj, FEAT_ARRAY_MMAP)) m->def.map_flags ^= BPF_F_MMAPABLE; } @@ -7702,6 +7925,12 @@ static int bpf_object__resolve_ksyms_btf_id(struct bpf_object *obj) if (ext->type != EXT_KSYM || !ext->ksym.type_id) continue; + if (obj->gen_loader) { + ext->is_set = true; + ext->ksym.kernel_btf_obj_fd = 0; + ext->ksym.kernel_btf_id = 0; + continue; + } t = btf__type_by_id(obj->btf, ext->btf_id); if (btf_is_var(t)) err = bpf_object__resolve_ksym_var_btf_id(obj, ext); @@ -7806,16 +8035,19 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) int err, i; if (!attr) - return -EINVAL; + return libbpf_err(-EINVAL); obj = attr->obj; if (!obj) - return -EINVAL; + return libbpf_err(-EINVAL); if (obj->loaded) { pr_warn("object '%s': load can't be attempted twice\n", obj->name); - return -EINVAL; + return libbpf_err(-EINVAL); } + if (obj->gen_loader) + bpf_gen__init(obj->gen_loader, attr->log_level); + err = bpf_object__probe_loading(obj); err = err ? : bpf_object__load_vmlinux_btf(obj, false); err = err ? : bpf_object__resolve_externs(obj, obj->kconfig); @@ -7826,6 +8058,15 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) err = err ? : bpf_object__relocate(obj, attr->target_btf_path); err = err ? : bpf_object__load_progs(obj, attr->log_level); + if (obj->gen_loader) { + /* reset FDs */ + btf__set_fd(obj->btf, -1); + for (i = 0; i < obj->nr_maps; i++) + obj->maps[i].fd = -1; + if (!err) + err = bpf_gen__finish(obj->gen_loader); + } + /* clean up module BTFs */ for (i = 0; i < obj->btf_module_cnt; i++) { close(obj->btf_modules[i].fd); @@ -7852,7 +8093,7 @@ out: bpf_object__unload(obj); pr_warn("failed to load object '%s'\n", obj->path); - return err; + return libbpf_err(err); } int bpf_object__load(struct bpf_object *obj) @@ -7924,28 +8165,28 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path, err = make_parent_dir(path); if (err) - return err; + return libbpf_err(err); err = check_path(path); if (err) - return err; + return libbpf_err(err); if (prog == NULL) { pr_warn("invalid program pointer\n"); - return -EINVAL; + return libbpf_err(-EINVAL); } if (instance < 0 || instance >= prog->instances.nr) { pr_warn("invalid prog instance %d of prog %s (max %d)\n", instance, prog->name, prog->instances.nr); - return -EINVAL; + return libbpf_err(-EINVAL); } if (bpf_obj_pin(prog->instances.fds[instance], path)) { err = -errno; cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warn("failed to pin program: %s\n", cp); - return err; + return libbpf_err(err); } pr_debug("pinned program '%s'\n", path); @@ -7959,22 +8200,23 @@ int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, err = check_path(path); if (err) - return err; + return libbpf_err(err); if (prog == NULL) { pr_warn("invalid program pointer\n"); - return -EINVAL; + return libbpf_err(-EINVAL); } if (instance < 0 || instance >= prog->instances.nr) { pr_warn("invalid prog instance %d of prog %s (max %d)\n", instance, prog->name, prog->instances.nr); - return -EINVAL; + return libbpf_err(-EINVAL); } err = unlink(path); if (err != 0) - return -errno; + return libbpf_err(-errno); + pr_debug("unpinned program '%s'\n", path); return 0; @@ -7986,20 +8228,20 @@ int bpf_program__pin(struct bpf_program *prog, const char *path) err = make_parent_dir(path); if (err) - return err; + return libbpf_err(err); err = check_path(path); if (err) - return err; + return libbpf_err(err); if (prog == NULL) { pr_warn("invalid program pointer\n"); - return -EINVAL; + return libbpf_err(-EINVAL); } if (prog->instances.nr <= 0) { pr_warn("no instances of prog %s to pin\n", prog->name); - return -EINVAL; + return libbpf_err(-EINVAL); } if (prog->instances.nr == 1) { @@ -8043,7 +8285,7 @@ err_unpin: rmdir(path); - return err; + return libbpf_err(err); } int bpf_program__unpin(struct bpf_program *prog, const char *path) @@ -8052,16 +8294,16 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path) err = check_path(path); if (err) - return err; + return libbpf_err(err); if (prog == NULL) { pr_warn("invalid program pointer\n"); - return -EINVAL; + return libbpf_err(-EINVAL); } if (prog->instances.nr <= 0) { pr_warn("no instances of prog %s to pin\n", prog->name); - return -EINVAL; + return libbpf_err(-EINVAL); } if (prog->instances.nr == 1) { @@ -8075,9 +8317,9 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path) len = snprintf(buf, PATH_MAX, "%s/%d", path, i); if (len < 0) - return -EINVAL; + return libbpf_err(-EINVAL); else if (len >= PATH_MAX) - return -ENAMETOOLONG; + return libbpf_err(-ENAMETOOLONG); err = bpf_program__unpin_instance(prog, buf, i); if (err) @@ -8086,7 +8328,7 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path) err = rmdir(path); if (err) - return -errno; + return libbpf_err(-errno); return 0; } @@ -8098,14 +8340,14 @@ int bpf_map__pin(struct bpf_map *map, const char *path) if (map == NULL) { pr_warn("invalid map pointer\n"); - return -EINVAL; + return libbpf_err(-EINVAL); } if (map->pin_path) { if (path && strcmp(path, map->pin_path)) { pr_warn("map '%s' already has pin path '%s' different from '%s'\n", bpf_map__name(map), map->pin_path, path); - return -EINVAL; + return libbpf_err(-EINVAL); } else if (map->pinned) { pr_debug("map '%s' already pinned at '%s'; not re-pinning\n", bpf_map__name(map), map->pin_path); @@ -8115,10 +8357,10 @@ int bpf_map__pin(struct bpf_map *map, const char *path) if (!path) { pr_warn("missing a path to pin map '%s' at\n", bpf_map__name(map)); - return -EINVAL; + return libbpf_err(-EINVAL); } else if (map->pinned) { pr_warn("map '%s' already pinned\n", bpf_map__name(map)); - return -EEXIST; + return libbpf_err(-EEXIST); } map->pin_path = strdup(path); @@ -8130,11 +8372,11 @@ int bpf_map__pin(struct bpf_map *map, const char *path) err = make_parent_dir(map->pin_path); if (err) - return err; + return libbpf_err(err); err = check_path(map->pin_path); if (err) - return err; + return libbpf_err(err); if (bpf_obj_pin(map->fd, map->pin_path)) { err = -errno; @@ -8149,7 +8391,7 @@ int bpf_map__pin(struct bpf_map *map, const char *path) out_err: cp = libbpf_strerror_r(-err, errmsg, sizeof(errmsg)); pr_warn("failed to pin map: %s\n", cp); - return err; + return libbpf_err(err); } int bpf_map__unpin(struct bpf_map *map, const char *path) @@ -8158,29 +8400,29 @@ int bpf_map__unpin(struct bpf_map *map, const char *path) if (map == NULL) { pr_warn("invalid map pointer\n"); - return -EINVAL; + return libbpf_err(-EINVAL); } if (map->pin_path) { if (path && strcmp(path, map->pin_path)) { pr_warn("map '%s' already has pin path '%s' different from '%s'\n", bpf_map__name(map), map->pin_path, path); - return -EINVAL; + return libbpf_err(-EINVAL); } path = map->pin_path; } else if (!path) { pr_warn("no path to unpin map '%s' from\n", bpf_map__name(map)); - return -EINVAL; + return libbpf_err(-EINVAL); } err = check_path(path); if (err) - return err; + return libbpf_err(err); err = unlink(path); if (err != 0) - return -errno; + return libbpf_err(-errno); map->pinned = false; pr_debug("unpinned map '%s' from '%s'\n", bpf_map__name(map), path); @@ -8195,7 +8437,7 @@ int bpf_map__set_pin_path(struct bpf_map *map, const char *path) if (path) { new = strdup(path); if (!new) - return -errno; + return libbpf_err(-errno); } free(map->pin_path); @@ -8229,11 +8471,11 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) int err; if (!obj) - return -ENOENT; + return libbpf_err(-ENOENT); if (!obj->loaded) { pr_warn("object not yet loaded; load it first\n"); - return -ENOENT; + return libbpf_err(-ENOENT); } bpf_object__for_each_map(map, obj) { @@ -8273,7 +8515,7 @@ err_unpin_maps: bpf_map__unpin(map, NULL); } - return err; + return libbpf_err(err); } int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) @@ -8282,7 +8524,7 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) int err; if (!obj) - return -ENOENT; + return libbpf_err(-ENOENT); bpf_object__for_each_map(map, obj) { char *pin_path = NULL; @@ -8294,9 +8536,9 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) len = snprintf(buf, PATH_MAX, "%s/%s", path, bpf_map__name(map)); if (len < 0) - return -EINVAL; + return libbpf_err(-EINVAL); else if (len >= PATH_MAX) - return -ENAMETOOLONG; + return libbpf_err(-ENAMETOOLONG); sanitize_pin_path(buf); pin_path = buf; } else if (!map->pin_path) { @@ -8305,7 +8547,7 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) err = bpf_map__unpin(map, pin_path); if (err) - return err; + return libbpf_err(err); } return 0; @@ -8317,11 +8559,11 @@ int bpf_object__pin_programs(struct bpf_object *obj, const char *path) int err; if (!obj) - return -ENOENT; + return libbpf_err(-ENOENT); if (!obj->loaded) { pr_warn("object not yet loaded; load it first\n"); - return -ENOENT; + return libbpf_err(-ENOENT); } bpf_object__for_each_program(prog, obj) { @@ -8360,7 +8602,7 @@ err_unpin_programs: bpf_program__unpin(prog, buf); } - return err; + return libbpf_err(err); } int bpf_object__unpin_programs(struct bpf_object *obj, const char *path) @@ -8369,7 +8611,7 @@ int bpf_object__unpin_programs(struct bpf_object *obj, const char *path) int err; if (!obj) - return -ENOENT; + return libbpf_err(-ENOENT); bpf_object__for_each_program(prog, obj) { char buf[PATH_MAX]; @@ -8378,13 +8620,13 @@ int bpf_object__unpin_programs(struct bpf_object *obj, const char *path) len = snprintf(buf, PATH_MAX, "%s/%s", path, prog->pin_name); if (len < 0) - return -EINVAL; + return libbpf_err(-EINVAL); else if (len >= PATH_MAX) - return -ENAMETOOLONG; + return libbpf_err(-ENAMETOOLONG); err = bpf_program__unpin(prog, buf); if (err) - return err; + return libbpf_err(err); } return 0; @@ -8396,12 +8638,12 @@ int bpf_object__pin(struct bpf_object *obj, const char *path) err = bpf_object__pin_maps(obj, path); if (err) - return err; + return libbpf_err(err); err = bpf_object__pin_programs(obj, path); if (err) { bpf_object__unpin_maps(obj, path); - return err; + return libbpf_err(err); } return 0; @@ -8451,6 +8693,7 @@ void bpf_object__close(struct bpf_object *obj) if (obj->clear_priv) obj->clear_priv(obj, obj->priv); + bpf_gen__free(obj->gen_loader); bpf_object__elf_finish(obj); bpf_object__unload(obj); btf__free(obj->btf); @@ -8497,7 +8740,7 @@ bpf_object__next(struct bpf_object *prev) const char *bpf_object__name(const struct bpf_object *obj) { - return obj ? obj->name : ERR_PTR(-EINVAL); + return obj ? obj->name : libbpf_err_ptr(-EINVAL); } unsigned int bpf_object__kversion(const struct bpf_object *obj) @@ -8518,7 +8761,7 @@ int bpf_object__btf_fd(const struct bpf_object *obj) int bpf_object__set_kversion(struct bpf_object *obj, __u32 kern_version) { if (obj->loaded) - return -EINVAL; + return libbpf_err(-EINVAL); obj->kern_version = kern_version; @@ -8538,7 +8781,23 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv, void *bpf_object__priv(const struct bpf_object *obj) { - return obj ? obj->priv : ERR_PTR(-EINVAL); + return obj ? obj->priv : libbpf_err_ptr(-EINVAL); +} + +int bpf_object__gen_loader(struct bpf_object *obj, struct gen_loader_opts *opts) +{ + struct bpf_gen *gen; + + if (!opts) + return -EFAULT; + if (!OPTS_VALID(opts, gen_loader_opts)) + return -EINVAL; + gen = calloc(sizeof(*gen), 1); + if (!gen) + return -ENOMEM; + gen->opts = opts; + obj->gen_loader = gen; + return 0; } static struct bpf_program * @@ -8558,7 +8817,7 @@ __bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj, if (p->obj != obj) { pr_warn("error: program handler doesn't match object\n"); - return NULL; + return errno = EINVAL, NULL; } idx = (p - obj->programs) + (forward ? 1 : -1); @@ -8604,7 +8863,7 @@ int bpf_program__set_priv(struct bpf_program *prog, void *priv, void *bpf_program__priv(const struct bpf_program *prog) { - return prog ? prog->priv : ERR_PTR(-EINVAL); + return prog ? prog->priv : libbpf_err_ptr(-EINVAL); } void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex) @@ -8631,7 +8890,7 @@ const char *bpf_program__title(const struct bpf_program *prog, bool needs_copy) title = strdup(title); if (!title) { pr_warn("failed to strdup program title\n"); - return ERR_PTR(-ENOMEM); + return libbpf_err_ptr(-ENOMEM); } } @@ -8646,7 +8905,7 @@ bool bpf_program__autoload(const struct bpf_program *prog) int bpf_program__set_autoload(struct bpf_program *prog, bool autoload) { if (prog->obj->loaded) - return -EINVAL; + return libbpf_err(-EINVAL); prog->load = autoload; return 0; @@ -8668,17 +8927,17 @@ int bpf_program__set_prep(struct bpf_program *prog, int nr_instances, int *instances_fds; if (nr_instances <= 0 || !prep) - return -EINVAL; + return libbpf_err(-EINVAL); if (prog->instances.nr > 0 || prog->instances.fds) { pr_warn("Can't set pre-processor after loading\n"); - return -EINVAL; + return libbpf_err(-EINVAL); } instances_fds = malloc(sizeof(int) * nr_instances); if (!instances_fds) { pr_warn("alloc memory failed for fds\n"); - return -ENOMEM; + return libbpf_err(-ENOMEM); } /* fill all fd with -1 */ @@ -8695,19 +8954,19 @@ int bpf_program__nth_fd(const struct bpf_program *prog, int n) int fd; if (!prog) - return -EINVAL; + return libbpf_err(-EINVAL); if (n >= prog->instances.nr || n < 0) { pr_warn("Can't get the %dth fd from program %s: only %d instances\n", n, prog->name, prog->instances.nr); - return -EINVAL; + return libbpf_err(-EINVAL); } fd = prog->instances.fds[n]; if (fd < 0) { pr_warn("%dth instance of program '%s' is invalid\n", n, prog->name); - return -ENOENT; + return libbpf_err(-ENOENT); } return fd; @@ -8733,7 +8992,7 @@ static bool bpf_program__is_type(const struct bpf_program *prog, int bpf_program__set_##NAME(struct bpf_program *prog) \ { \ if (!prog) \ - return -EINVAL; \ + return libbpf_err(-EINVAL); \ bpf_program__set_type(prog, TYPE); \ return 0; \ } \ @@ -8823,7 +9082,10 @@ static struct bpf_link *attach_iter(const struct bpf_sec_def *sec, static const struct bpf_sec_def section_defs[] = { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), - BPF_PROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT), + BPF_EAPROG_SEC("sk_reuseport/migrate", BPF_PROG_TYPE_SK_REUSEPORT, + BPF_SK_REUSEPORT_SELECT_OR_MIGRATE), + BPF_EAPROG_SEC("sk_reuseport", BPF_PROG_TYPE_SK_REUSEPORT, + BPF_SK_REUSEPORT_SELECT), SEC_DEF("kprobe/", KPROBE, .attach_fn = attach_kprobe), BPF_PROG_SEC("uprobe/", BPF_PROG_TYPE_KPROBE), @@ -8887,6 +9149,8 @@ static const struct bpf_sec_def section_defs[] = { .expected_attach_type = BPF_TRACE_ITER, .is_attach_btf = true, .attach_fn = attach_iter), + SEC_DEF("syscall", SYSCALL, + .is_sleepable = true), BPF_EAPROG_SEC("xdp_devmap/", BPF_PROG_TYPE_XDP, BPF_XDP_DEVMAP), BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP, @@ -9018,7 +9282,7 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, char *type_names; if (!name) - return -EINVAL; + return libbpf_err(-EINVAL); sec_def = find_sec_def(name); if (sec_def) { @@ -9034,7 +9298,7 @@ int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, free(type_names); } - return -ESRCH; + return libbpf_err(-ESRCH); } static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj, @@ -9176,6 +9440,28 @@ invalid_prog: #define BTF_ITER_PREFIX "bpf_iter_" #define BTF_MAX_NAME_SIZE 128 +void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, + const char **prefix, int *kind) +{ + switch (attach_type) { + case BPF_TRACE_RAW_TP: + *prefix = BTF_TRACE_PREFIX; + *kind = BTF_KIND_TYPEDEF; + break; + case BPF_LSM_MAC: + *prefix = BTF_LSM_PREFIX; + *kind = BTF_KIND_FUNC; + break; + case BPF_TRACE_ITER: + *prefix = BTF_ITER_PREFIX; + *kind = BTF_KIND_FUNC; + break; + default: + *prefix = ""; + *kind = BTF_KIND_FUNC; + } +} + static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, const char *name, __u32 kind) { @@ -9196,21 +9482,11 @@ static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, static inline int find_attach_btf_id(struct btf *btf, const char *name, enum bpf_attach_type attach_type) { - int err; + const char *prefix; + int kind; - if (attach_type == BPF_TRACE_RAW_TP) - err = find_btf_by_prefix_kind(btf, BTF_TRACE_PREFIX, name, - BTF_KIND_TYPEDEF); - else if (attach_type == BPF_LSM_MAC) - err = find_btf_by_prefix_kind(btf, BTF_LSM_PREFIX, name, - BTF_KIND_FUNC); - else if (attach_type == BPF_TRACE_ITER) - err = find_btf_by_prefix_kind(btf, BTF_ITER_PREFIX, name, - BTF_KIND_FUNC); - else - err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); - - return err; + btf_get_kernel_prefix_kind(attach_type, &prefix, &kind); + return find_btf_by_prefix_kind(btf, prefix, name, kind); } int libbpf_find_vmlinux_btf_id(const char *name, @@ -9220,9 +9496,10 @@ int libbpf_find_vmlinux_btf_id(const char *name, int err; btf = libbpf_find_kernel_btf(); - if (IS_ERR(btf)) { + err = libbpf_get_error(btf); + if (err) { pr_warn("vmlinux BTF is not found\n"); - return -EINVAL; + return libbpf_err(err); } err = find_attach_btf_id(btf, name, attach_type); @@ -9230,7 +9507,7 @@ int libbpf_find_vmlinux_btf_id(const char *name, pr_warn("%s is not found in vmlinux BTF\n", name); btf__free(btf); - return err; + return libbpf_err(err); } static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) @@ -9241,10 +9518,11 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd) int err = -EINVAL; info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0); - if (IS_ERR_OR_NULL(info_linear)) { + err = libbpf_get_error(info_linear); + if (err) { pr_warn("failed get_prog_info_linear for FD %d\n", attach_prog_fd); - return -EINVAL; + return err; } info = &info_linear->info; if (!info->btf_id) { @@ -9309,7 +9587,7 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, __u32 attach_prog_fd = prog->attach_prog_fd; const char *name = prog->sec_name, *attach_name; const struct bpf_sec_def *sec = NULL; - int i, err; + int i, err = 0; if (!name) return -EINVAL; @@ -9344,7 +9622,13 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, } /* kernel/module BTF ID */ - err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id); + if (prog->obj->gen_loader) { + bpf_gen__record_attach_target(prog->obj->gen_loader, attach_name, attach_type); + *btf_obj_fd = 0; + *btf_type_id = 1; + } else { + err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id); + } if (err) { pr_warn("failed to find kernel BTF type ID of '%s': %d\n", attach_name, err); return err; @@ -9359,13 +9643,13 @@ int libbpf_attach_type_by_name(const char *name, int i; if (!name) - return -EINVAL; + return libbpf_err(-EINVAL); for (i = 0; i < ARRAY_SIZE(section_defs); i++) { if (strncmp(name, section_defs[i].sec, section_defs[i].len)) continue; if (!section_defs[i].is_attachable) - return -EINVAL; + return libbpf_err(-EINVAL); *attach_type = section_defs[i].expected_attach_type; return 0; } @@ -9376,17 +9660,17 @@ int libbpf_attach_type_by_name(const char *name, free(type_names); } - return -EINVAL; + return libbpf_err(-EINVAL); } int bpf_map__fd(const struct bpf_map *map) { - return map ? map->fd : -EINVAL; + return map ? map->fd : libbpf_err(-EINVAL); } const struct bpf_map_def *bpf_map__def(const struct bpf_map *map) { - return map ? &map->def : ERR_PTR(-EINVAL); + return map ? &map->def : libbpf_err_ptr(-EINVAL); } const char *bpf_map__name(const struct bpf_map *map) @@ -9402,7 +9686,7 @@ enum bpf_map_type bpf_map__type(const struct bpf_map *map) int bpf_map__set_type(struct bpf_map *map, enum bpf_map_type type) { if (map->fd >= 0) - return -EBUSY; + return libbpf_err(-EBUSY); map->def.type = type; return 0; } @@ -9415,7 +9699,7 @@ __u32 bpf_map__map_flags(const struct bpf_map *map) int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags) { if (map->fd >= 0) - return -EBUSY; + return libbpf_err(-EBUSY); map->def.map_flags = flags; return 0; } @@ -9428,7 +9712,7 @@ __u32 bpf_map__numa_node(const struct bpf_map *map) int bpf_map__set_numa_node(struct bpf_map *map, __u32 numa_node) { if (map->fd >= 0) - return -EBUSY; + return libbpf_err(-EBUSY); map->numa_node = numa_node; return 0; } @@ -9441,7 +9725,7 @@ __u32 bpf_map__key_size(const struct bpf_map *map) int bpf_map__set_key_size(struct bpf_map *map, __u32 size) { if (map->fd >= 0) - return -EBUSY; + return libbpf_err(-EBUSY); map->def.key_size = size; return 0; } @@ -9454,7 +9738,7 @@ __u32 bpf_map__value_size(const struct bpf_map *map) int bpf_map__set_value_size(struct bpf_map *map, __u32 size) { if (map->fd >= 0) - return -EBUSY; + return libbpf_err(-EBUSY); map->def.value_size = size; return 0; } @@ -9473,7 +9757,7 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv) { if (!map) - return -EINVAL; + return libbpf_err(-EINVAL); if (map->priv) { if (map->clear_priv) @@ -9487,7 +9771,7 @@ int bpf_map__set_priv(struct bpf_map *map, void *priv, void *bpf_map__priv(const struct bpf_map *map) { - return map ? map->priv : ERR_PTR(-EINVAL); + return map ? map->priv : libbpf_err_ptr(-EINVAL); } int bpf_map__set_initial_value(struct bpf_map *map, @@ -9495,12 +9779,20 @@ int bpf_map__set_initial_value(struct bpf_map *map, { if (!map->mmaped || map->libbpf_type == LIBBPF_MAP_KCONFIG || size != map->def.value_size || map->fd >= 0) - return -EINVAL; + return libbpf_err(-EINVAL); memcpy(map->mmaped, data, size); return 0; } +const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize) +{ + if (!map->mmaped) + return NULL; + *psize = map->def.value_size; + return map->mmaped; +} + bool bpf_map__is_offload_neutral(const struct bpf_map *map) { return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; @@ -9519,7 +9811,7 @@ __u32 bpf_map__ifindex(const struct bpf_map *map) int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex) { if (map->fd >= 0) - return -EBUSY; + return libbpf_err(-EBUSY); map->map_ifindex = ifindex; return 0; } @@ -9528,11 +9820,11 @@ int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd) { if (!bpf_map_type__is_map_in_map(map->def.type)) { pr_warn("error: unsupported map type\n"); - return -EINVAL; + return libbpf_err(-EINVAL); } if (map->inner_map_fd != -1) { pr_warn("error: inner_map_fd already specified\n"); - return -EINVAL; + return libbpf_err(-EINVAL); } zfree(&map->inner_map); map->inner_map_fd = fd; @@ -9546,7 +9838,7 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) struct bpf_map *s, *e; if (!obj || !obj->maps) - return NULL; + return errno = EINVAL, NULL; s = obj->maps; e = obj->maps + obj->nr_maps; @@ -9554,7 +9846,7 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i) if ((m < s) || (m >= e)) { pr_warn("error in %s: map handler doesn't belong to object\n", __func__); - return NULL; + return errno = EINVAL, NULL; } idx = (m - obj->maps) + i; @@ -9593,7 +9885,7 @@ bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name) if (pos->name && !strcmp(pos->name, name)) return pos; } - return NULL; + return errno = ENOENT, NULL; } int @@ -9605,12 +9897,23 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name) struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset) { - return ERR_PTR(-ENOTSUP); + return libbpf_err_ptr(-ENOTSUP); } long libbpf_get_error(const void *ptr) { - return PTR_ERR_OR_ZERO(ptr); + if (!IS_ERR_OR_NULL(ptr)) + return 0; + + if (IS_ERR(ptr)) + errno = -PTR_ERR(ptr); + + /* If ptr == NULL, then errno should be already set by the failing + * API, because libbpf never returns NULL on success and it now always + * sets errno on error. So no extra errno handling for ptr == NULL + * case. + */ + return -errno; } int bpf_prog_load(const char *file, enum bpf_prog_type type, @@ -9636,16 +9939,17 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, int err; if (!attr) - return -EINVAL; + return libbpf_err(-EINVAL); if (!attr->file) - return -EINVAL; + return libbpf_err(-EINVAL); open_attr.file = attr->file; open_attr.prog_type = attr->prog_type; obj = bpf_object__open_xattr(&open_attr); - if (IS_ERR_OR_NULL(obj)) - return -ENOENT; + err = libbpf_get_error(obj); + if (err) + return libbpf_err(-ENOENT); bpf_object__for_each_program(prog, obj) { enum bpf_attach_type attach_type = attr->expected_attach_type; @@ -9665,7 +9969,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, * didn't provide a fallback type, too bad... */ bpf_object__close(obj); - return -EINVAL; + return libbpf_err(-EINVAL); } prog->prog_ifindex = attr->ifindex; @@ -9683,13 +9987,13 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, if (!first_prog) { pr_warn("object file doesn't contain bpf program\n"); bpf_object__close(obj); - return -ENOENT; + return libbpf_err(-ENOENT); } err = bpf_object__load(obj); if (err) { bpf_object__close(obj); - return err; + return libbpf_err(err); } *pobj = obj; @@ -9708,7 +10012,10 @@ struct bpf_link { /* Replace link's underlying BPF program with the new one */ int bpf_link__update_program(struct bpf_link *link, struct bpf_program *prog) { - return bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL); + int ret; + + ret = bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), NULL); + return libbpf_err_errno(ret); } /* Release "ownership" of underlying BPF resource (typically, BPF program @@ -9741,7 +10048,7 @@ int bpf_link__destroy(struct bpf_link *link) free(link->pin_path); free(link); - return err; + return libbpf_err(err); } int bpf_link__fd(const struct bpf_link *link) @@ -9756,7 +10063,7 @@ const char *bpf_link__pin_path(const struct bpf_link *link) static int bpf_link__detach_fd(struct bpf_link *link) { - return close(link->fd); + return libbpf_err_errno(close(link->fd)); } struct bpf_link *bpf_link__open(const char *path) @@ -9768,13 +10075,13 @@ struct bpf_link *bpf_link__open(const char *path) if (fd < 0) { fd = -errno; pr_warn("failed to open link at %s: %d\n", path, fd); - return ERR_PTR(fd); + return libbpf_err_ptr(fd); } link = calloc(1, sizeof(*link)); if (!link) { close(fd); - return ERR_PTR(-ENOMEM); + return libbpf_err_ptr(-ENOMEM); } link->detach = &bpf_link__detach_fd; link->fd = fd; @@ -9782,7 +10089,7 @@ struct bpf_link *bpf_link__open(const char *path) link->pin_path = strdup(path); if (!link->pin_path) { bpf_link__destroy(link); - return ERR_PTR(-ENOMEM); + return libbpf_err_ptr(-ENOMEM); } return link; @@ -9798,22 +10105,22 @@ int bpf_link__pin(struct bpf_link *link, const char *path) int err; if (link->pin_path) - return -EBUSY; + return libbpf_err(-EBUSY); err = make_parent_dir(path); if (err) - return err; + return libbpf_err(err); err = check_path(path); if (err) - return err; + return libbpf_err(err); link->pin_path = strdup(path); if (!link->pin_path) - return -ENOMEM; + return libbpf_err(-ENOMEM); if (bpf_obj_pin(link->fd, link->pin_path)) { err = -errno; zfree(&link->pin_path); - return err; + return libbpf_err(err); } pr_debug("link fd=%d: pinned at %s\n", link->fd, link->pin_path); @@ -9825,11 +10132,11 @@ int bpf_link__unpin(struct bpf_link *link) int err; if (!link->pin_path) - return -EINVAL; + return libbpf_err(-EINVAL); err = unlink(link->pin_path); if (err != 0) - return -errno; + return libbpf_err_errno(err); pr_debug("link fd=%d: unpinned from %s\n", link->fd, link->pin_path); zfree(&link->pin_path); @@ -9845,11 +10152,10 @@ static int bpf_link__detach_perf_event(struct bpf_link *link) err = -errno; close(link->fd); - return err; + return libbpf_err(err); } -struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, - int pfd) +struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd) { char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; @@ -9858,18 +10164,18 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, if (pfd < 0) { pr_warn("prog '%s': invalid perf event FD %d\n", prog->name, pfd); - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); } prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { pr_warn("prog '%s': can't attach BPF program w/o FD (did you load it?)\n", prog->name); - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); } link = calloc(1, sizeof(*link)); if (!link) - return ERR_PTR(-ENOMEM); + return libbpf_err_ptr(-ENOMEM); link->detach = &bpf_link__detach_perf_event; link->fd = pfd; @@ -9881,14 +10187,14 @@ struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, if (err == -EPROTO) pr_warn("prog '%s': try add PERF_SAMPLE_CALLCHAIN to or remove exclude_callchain_[kernel|user] from pfd %d\n", prog->name, pfd); - return ERR_PTR(err); + return libbpf_err_ptr(err); } if (ioctl(pfd, PERF_EVENT_IOC_ENABLE, 0) < 0) { err = -errno; free(link); pr_warn("prog '%s': failed to enable pfd %d: %s\n", prog->name, pfd, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return ERR_PTR(err); + return libbpf_err_ptr(err); } return link; } @@ -10012,16 +10318,16 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n", prog->name, retprobe ? "kretprobe" : "kprobe", func_name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return ERR_PTR(pfd); + return libbpf_err_ptr(pfd); } link = bpf_program__attach_perf_event(prog, pfd); - if (IS_ERR(link)) { + err = libbpf_get_error(link); + if (err) { close(pfd); - err = PTR_ERR(link); pr_warn("prog '%s': failed to attach to %s '%s': %s\n", prog->name, retprobe ? "kretprobe" : "kprobe", func_name, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return link; + return libbpf_err_ptr(err); } return link; } @@ -10054,17 +10360,17 @@ struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog, prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return ERR_PTR(pfd); + return libbpf_err_ptr(pfd); } link = bpf_program__attach_perf_event(prog, pfd); - if (IS_ERR(link)) { + err = libbpf_get_error(link); + if (err) { close(pfd); - err = PTR_ERR(link); pr_warn("prog '%s': failed to attach to %s '%s:0x%zx': %s\n", prog->name, retprobe ? "uretprobe" : "uprobe", binary_path, func_offset, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return link; + return libbpf_err_ptr(err); } return link; } @@ -10132,16 +10438,16 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog, pr_warn("prog '%s': failed to create tracepoint '%s/%s' perf event: %s\n", prog->name, tp_category, tp_name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return ERR_PTR(pfd); + return libbpf_err_ptr(pfd); } link = bpf_program__attach_perf_event(prog, pfd); - if (IS_ERR(link)) { + err = libbpf_get_error(link); + if (err) { close(pfd); - err = PTR_ERR(link); pr_warn("prog '%s': failed to attach to tracepoint '%s/%s': %s\n", prog->name, tp_category, tp_name, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); - return link; + return libbpf_err_ptr(err); } return link; } @@ -10154,20 +10460,19 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, sec_name = strdup(prog->sec_name); if (!sec_name) - return ERR_PTR(-ENOMEM); + return libbpf_err_ptr(-ENOMEM); /* extract "tp//" */ tp_cat = sec_name + sec->len; tp_name = strchr(tp_cat, '/'); if (!tp_name) { - link = ERR_PTR(-EINVAL); - goto out; + free(sec_name); + return libbpf_err_ptr(-EINVAL); } *tp_name = '\0'; tp_name++; link = bpf_program__attach_tracepoint(prog, tp_cat, tp_name); -out: free(sec_name); return link; } @@ -10182,12 +10487,12 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { pr_warn("prog '%s': can't attach before loaded\n", prog->name); - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); } link = calloc(1, sizeof(*link)); if (!link) - return ERR_PTR(-ENOMEM); + return libbpf_err_ptr(-ENOMEM); link->detach = &bpf_link__detach_fd; pfd = bpf_raw_tracepoint_open(tp_name, prog_fd); @@ -10196,7 +10501,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, free(link); pr_warn("prog '%s': failed to attach to raw tracepoint '%s': %s\n", prog->name, tp_name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return ERR_PTR(pfd); + return libbpf_err_ptr(pfd); } link->fd = pfd; return link; @@ -10220,12 +10525,12 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog) prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { pr_warn("prog '%s': can't attach before loaded\n", prog->name); - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); } link = calloc(1, sizeof(*link)); if (!link) - return ERR_PTR(-ENOMEM); + return libbpf_err_ptr(-ENOMEM); link->detach = &bpf_link__detach_fd; pfd = bpf_raw_tracepoint_open(NULL, prog_fd); @@ -10234,7 +10539,7 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog) free(link); pr_warn("prog '%s': failed to attach: %s\n", prog->name, libbpf_strerror_r(pfd, errmsg, sizeof(errmsg))); - return ERR_PTR(pfd); + return libbpf_err_ptr(pfd); } link->fd = pfd; return (struct bpf_link *)link; @@ -10262,12 +10567,6 @@ static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, return bpf_program__attach_lsm(prog); } -static struct bpf_link *attach_iter(const struct bpf_sec_def *sec, - struct bpf_program *prog) -{ - return bpf_program__attach_iter(prog, NULL); -} - static struct bpf_link * bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id, const char *target_name) @@ -10282,12 +10581,12 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id, prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { pr_warn("prog '%s': can't attach before loaded\n", prog->name); - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); } link = calloc(1, sizeof(*link)); if (!link) - return ERR_PTR(-ENOMEM); + return libbpf_err_ptr(-ENOMEM); link->detach = &bpf_link__detach_fd; attach_type = bpf_program__get_expected_attach_type(prog); @@ -10298,7 +10597,7 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id, pr_warn("prog '%s': failed to attach to %s: %s\n", prog->name, target_name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); - return ERR_PTR(link_fd); + return libbpf_err_ptr(link_fd); } link->fd = link_fd; return link; @@ -10331,19 +10630,19 @@ struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog, if (!!target_fd != !!attach_func_name) { pr_warn("prog '%s': supply none or both of target_fd and attach_func_name\n", prog->name); - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); } if (prog->type != BPF_PROG_TYPE_EXT) { pr_warn("prog '%s': only BPF_PROG_TYPE_EXT can attach as freplace", prog->name); - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); } if (target_fd) { btf_id = libbpf_find_prog_btf_id(attach_func_name, target_fd); if (btf_id < 0) - return ERR_PTR(btf_id); + return libbpf_err_ptr(btf_id); return bpf_program__attach_fd(prog, target_fd, btf_id, "freplace"); } else { @@ -10365,7 +10664,7 @@ bpf_program__attach_iter(struct bpf_program *prog, __u32 target_fd = 0; if (!OPTS_VALID(opts, bpf_iter_attach_opts)) - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); link_create_opts.iter_info = OPTS_GET(opts, link_info, (void *)0); link_create_opts.iter_info_len = OPTS_GET(opts, link_info_len, 0); @@ -10373,12 +10672,12 @@ bpf_program__attach_iter(struct bpf_program *prog, prog_fd = bpf_program__fd(prog); if (prog_fd < 0) { pr_warn("prog '%s': can't attach before loaded\n", prog->name); - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); } link = calloc(1, sizeof(*link)); if (!link) - return ERR_PTR(-ENOMEM); + return libbpf_err_ptr(-ENOMEM); link->detach = &bpf_link__detach_fd; link_fd = bpf_link_create(prog_fd, target_fd, BPF_TRACE_ITER, @@ -10388,19 +10687,25 @@ bpf_program__attach_iter(struct bpf_program *prog, free(link); pr_warn("prog '%s': failed to attach to iterator: %s\n", prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg))); - return ERR_PTR(link_fd); + return libbpf_err_ptr(link_fd); } link->fd = link_fd; return link; } +static struct bpf_link *attach_iter(const struct bpf_sec_def *sec, + struct bpf_program *prog) +{ + return bpf_program__attach_iter(prog, NULL); +} + struct bpf_link *bpf_program__attach(struct bpf_program *prog) { const struct bpf_sec_def *sec_def; sec_def = find_sec_def(prog->sec_name); if (!sec_def || !sec_def->attach_fn) - return ERR_PTR(-ESRCH); + return libbpf_err_ptr(-ESRCH); return sec_def->attach_fn(sec_def, prog); } @@ -10423,11 +10728,11 @@ struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map) int err; if (!bpf_map__is_struct_ops(map) || map->fd == -1) - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); link = calloc(1, sizeof(*link)); if (!link) - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); st_ops = map->st_ops; for (i = 0; i < btf_vlen(st_ops->type); i++) { @@ -10447,7 +10752,7 @@ struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map) if (err) { err = -errno; free(link); - return ERR_PTR(err); + return libbpf_err_ptr(err); } link->detach = bpf_link__detach_struct_ops; @@ -10501,7 +10806,7 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size, } ring_buffer_write_tail(header, data_tail); - return ret; + return libbpf_err(ret); } struct perf_buffer; @@ -10654,7 +10959,7 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, p.lost_cb = opts ? opts->lost_cb : NULL; p.ctx = opts ? opts->ctx : NULL; - return __perf_buffer__new(map_fd, page_cnt, &p); + return libbpf_ptr(__perf_buffer__new(map_fd, page_cnt, &p)); } struct perf_buffer * @@ -10670,7 +10975,7 @@ perf_buffer__new_raw(int map_fd, size_t page_cnt, p.cpus = opts->cpus; p.map_keys = opts->map_keys; - return __perf_buffer__new(map_fd, page_cnt, &p); + return libbpf_ptr(__perf_buffer__new(map_fd, page_cnt, &p)); } static struct perf_buffer *__perf_buffer__new(int map_fd, size_t page_cnt, @@ -10891,16 +11196,19 @@ int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms) int i, cnt, err; cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms); + if (cnt < 0) + return libbpf_err_errno(cnt); + for (i = 0; i < cnt; i++) { struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr; err = perf_buffer__process_records(pb, cpu_buf); if (err) { pr_warn("error while processing records: %d\n", err); - return err; + return libbpf_err(err); } } - return cnt < 0 ? -errno : cnt; + return cnt; } /* Return number of PERF_EVENT_ARRAY map slots set up by this perf_buffer @@ -10921,11 +11229,11 @@ int perf_buffer__buffer_fd(const struct perf_buffer *pb, size_t buf_idx) struct perf_cpu_buf *cpu_buf; if (buf_idx >= pb->cpu_cnt) - return -EINVAL; + return libbpf_err(-EINVAL); cpu_buf = pb->cpu_bufs[buf_idx]; if (!cpu_buf) - return -ENOENT; + return libbpf_err(-ENOENT); return cpu_buf->fd; } @@ -10943,11 +11251,11 @@ int perf_buffer__consume_buffer(struct perf_buffer *pb, size_t buf_idx) struct perf_cpu_buf *cpu_buf; if (buf_idx >= pb->cpu_cnt) - return -EINVAL; + return libbpf_err(-EINVAL); cpu_buf = pb->cpu_bufs[buf_idx]; if (!cpu_buf) - return -ENOENT; + return libbpf_err(-ENOENT); return perf_buffer__process_records(pb, cpu_buf); } @@ -10965,7 +11273,7 @@ int perf_buffer__consume(struct perf_buffer *pb) err = perf_buffer__process_records(pb, cpu_buf); if (err) { pr_warn("perf_buffer: failed to process records in buffer #%d: %d\n", i, err); - return err; + return libbpf_err(err); } } return 0; @@ -11077,13 +11385,13 @@ bpf_program__get_prog_info_linear(int fd, __u64 arrays) void *ptr; if (arrays >> BPF_PROG_INFO_LAST_ARRAY) - return ERR_PTR(-EINVAL); + return libbpf_err_ptr(-EINVAL); /* step 1: get array dimensions */ err = bpf_obj_get_info_by_fd(fd, &info, &info_len); if (err) { pr_debug("can't get prog info: %s", strerror(errno)); - return ERR_PTR(-EFAULT); + return libbpf_err_ptr(-EFAULT); } /* step 2: calculate total size of all arrays */ @@ -11115,7 +11423,7 @@ bpf_program__get_prog_info_linear(int fd, __u64 arrays) data_len = roundup(data_len, sizeof(__u64)); info_linear = malloc(sizeof(struct bpf_prog_info_linear) + data_len); if (!info_linear) - return ERR_PTR(-ENOMEM); + return libbpf_err_ptr(-ENOMEM); /* step 4: fill data to info_linear->info */ info_linear->arrays = arrays; @@ -11147,7 +11455,7 @@ bpf_program__get_prog_info_linear(int fd, __u64 arrays) if (err) { pr_debug("can't get prog info: %s", strerror(errno)); free(info_linear); - return ERR_PTR(-EFAULT); + return libbpf_err_ptr(-EFAULT); } /* step 6: verify the data */ @@ -11226,26 +11534,26 @@ int bpf_program__set_attach_target(struct bpf_program *prog, int btf_obj_fd = 0, btf_id = 0, err; if (!prog || attach_prog_fd < 0 || !attach_func_name) - return -EINVAL; + return libbpf_err(-EINVAL); if (prog->obj->loaded) - return -EINVAL; + return libbpf_err(-EINVAL); if (attach_prog_fd) { btf_id = libbpf_find_prog_btf_id(attach_func_name, attach_prog_fd); if (btf_id < 0) - return btf_id; + return libbpf_err(btf_id); } else { /* load btf_vmlinux, if not yet */ err = bpf_object__load_vmlinux_btf(prog->obj, true); if (err) - return err; + return libbpf_err(err); err = find_kernel_btf_id(prog->obj, attach_func_name, prog->expected_attach_type, &btf_obj_fd, &btf_id); if (err) - return err; + return libbpf_err(err); } prog->attach_btf_id = btf_id; @@ -11344,7 +11652,7 @@ int libbpf_num_possible_cpus(void) err = parse_cpu_mask_file(fcpu, &mask, &n); if (err) - return err; + return libbpf_err(err); tmp_cpus = 0; for (i = 0; i < n; i++) { @@ -11364,7 +11672,7 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s, .object_name = s->name, ); struct bpf_object *obj; - int i; + int i, err; /* Attempt to preserve opts->object_name, unless overriden by user * explicitly. Overwriting object name for skeletons is discouraged, @@ -11379,10 +11687,11 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s, } obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts); - if (IS_ERR(obj)) { - pr_warn("failed to initialize skeleton BPF object '%s': %ld\n", - s->name, PTR_ERR(obj)); - return PTR_ERR(obj); + err = libbpf_get_error(obj); + if (err) { + pr_warn("failed to initialize skeleton BPF object '%s': %d\n", + s->name, err); + return libbpf_err(err); } *s->obj = obj; @@ -11395,7 +11704,7 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s, *map = bpf_object__find_map_by_name(obj, name); if (!*map) { pr_warn("failed to find skeleton map '%s'\n", name); - return -ESRCH; + return libbpf_err(-ESRCH); } /* externs shouldn't be pre-setup from user code */ @@ -11410,7 +11719,7 @@ int bpf_object__open_skeleton(struct bpf_object_skeleton *s, *prog = bpf_object__find_program_by_name(obj, name); if (!*prog) { pr_warn("failed to find skeleton program '%s'\n", name); - return -ESRCH; + return libbpf_err(-ESRCH); } } @@ -11424,7 +11733,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) err = bpf_object__load(*s->obj); if (err) { pr_warn("failed to load BPF skeleton '%s': %d\n", s->name, err); - return err; + return libbpf_err(err); } for (i = 0; i < s->map_cnt; i++) { @@ -11463,7 +11772,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) *mmaped = NULL; pr_warn("failed to re-mmap() map '%s': %d\n", bpf_map__name(map), err); - return err; + return libbpf_err(err); } } @@ -11472,7 +11781,7 @@ int bpf_object__load_skeleton(struct bpf_object_skeleton *s) int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) { - int i; + int i, err; for (i = 0; i < s->prog_cnt; i++) { struct bpf_program *prog = *s->progs[i].prog; @@ -11487,10 +11796,11 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) continue; *link = sec_def->attach_fn(sec_def, prog); - if (IS_ERR(*link)) { - pr_warn("failed to auto-attach program '%s': %ld\n", - bpf_program__name(prog), PTR_ERR(*link)); - return PTR_ERR(*link); + err = libbpf_get_error(*link); + if (err) { + pr_warn("failed to auto-attach program '%s': %d\n", + bpf_program__name(prog), err); + return libbpf_err(err); } } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index bec4e6a6e31d..6e61342ba56c 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -18,6 +18,7 @@ #include #include "libbpf_common.h" +#include "libbpf_legacy.h" #ifdef __cplusplus extern "C" { @@ -471,6 +472,7 @@ LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, LIBBPF_API void *bpf_map__priv(const struct bpf_map *map); LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map, const void *data, size_t size); +LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize); LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map); LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map); LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path); @@ -498,6 +500,7 @@ LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd); +/* XDP related API */ struct xdp_link_info { __u32 prog_id; __u32 drv_prog_id; @@ -520,6 +523,49 @@ LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); LIBBPF_API int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, size_t info_size, __u32 flags); +/* TC related API */ +enum bpf_tc_attach_point { + BPF_TC_INGRESS = 1 << 0, + BPF_TC_EGRESS = 1 << 1, + BPF_TC_CUSTOM = 1 << 2, +}; + +#define BPF_TC_PARENT(a, b) \ + ((((a) << 16) & 0xFFFF0000U) | ((b) & 0x0000FFFFU)) + +enum bpf_tc_flags { + BPF_TC_F_REPLACE = 1 << 0, +}; + +struct bpf_tc_hook { + size_t sz; + int ifindex; + enum bpf_tc_attach_point attach_point; + __u32 parent; + size_t :0; +}; +#define bpf_tc_hook__last_field parent + +struct bpf_tc_opts { + size_t sz; + int prog_fd; + __u32 flags; + __u32 prog_id; + __u32 handle; + __u32 priority; + size_t :0; +}; +#define bpf_tc_opts__last_field priority + +LIBBPF_API int bpf_tc_hook_create(struct bpf_tc_hook *hook); +LIBBPF_API int bpf_tc_hook_destroy(struct bpf_tc_hook *hook); +LIBBPF_API int bpf_tc_attach(const struct bpf_tc_hook *hook, + struct bpf_tc_opts *opts); +LIBBPF_API int bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts); +LIBBPF_API int bpf_tc_query(const struct bpf_tc_hook *hook, + struct bpf_tc_opts *opts); + /* Ring buffer APIs */ struct ring_buffer; @@ -756,6 +802,18 @@ LIBBPF_API int bpf_object__attach_skeleton(struct bpf_object_skeleton *s); LIBBPF_API void bpf_object__detach_skeleton(struct bpf_object_skeleton *s); LIBBPF_API void bpf_object__destroy_skeleton(struct bpf_object_skeleton *s); +struct gen_loader_opts { + size_t sz; /* size of this struct, for forward/backward compatiblity */ + const char *data; + const char *insns; + __u32 data_sz; + __u32 insns_sz; +}; + +#define gen_loader_opts__last_field insns_sz +LIBBPF_API int bpf_object__gen_loader(struct bpf_object *obj, + struct gen_loader_opts *opts); + enum libbpf_tristate { TRI_NO = 0, TRI_YES = 1, @@ -768,10 +826,18 @@ struct bpf_linker_opts { }; #define bpf_linker_opts__last_field sz +struct bpf_linker_file_opts { + /* size of this struct, for forward/backward compatiblity */ + size_t sz; +}; +#define bpf_linker_file_opts__last_field sz + struct bpf_linker; LIBBPF_API struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts *opts); -LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, const char *filename); +LIBBPF_API int bpf_linker__add_file(struct bpf_linker *linker, + const char *filename, + const struct bpf_linker_file_opts *opts); LIBBPF_API int bpf_linker__finalize(struct bpf_linker *linker); LIBBPF_API void bpf_linker__free(struct bpf_linker *linker); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index b9b29baf1df8..944c99d1ded3 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -361,4 +361,17 @@ LIBBPF_0.4.0 { bpf_linker__new; bpf_map__inner_map; bpf_object__set_kversion; + bpf_tc_attach; + bpf_tc_detach; + bpf_tc_hook_create; + bpf_tc_hook_destroy; + bpf_tc_query; } LIBBPF_0.3.0; + +LIBBPF_0.5.0 { + global: + bpf_map__initial_value; + bpf_map_lookup_and_delete_elem_flags; + bpf_object__gen_loader; + libbpf_set_strict_mode; +} LIBBPF_0.4.0; diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c index 0afb51f7a919..96f67a772a1b 100644 --- a/tools/lib/bpf/libbpf_errno.c +++ b/tools/lib/bpf/libbpf_errno.c @@ -12,6 +12,7 @@ #include #include "libbpf.h" +#include "libbpf_internal.h" /* make sure libbpf doesn't use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 @@ -39,7 +40,7 @@ static const char *libbpf_strerror_table[NR_ERRNO] = { int libbpf_strerror(int err, char *buf, size_t size) { if (!buf || !size) - return -1; + return libbpf_err(-EINVAL); err = err > 0 ? err : -err; @@ -48,7 +49,7 @@ int libbpf_strerror(int err, char *buf, size_t size) ret = strerror_r(err, buf, size); buf[size - 1] = '\0'; - return ret; + return libbpf_err_errno(ret); } if (err < __LIBBPF_ERRNO__END) { @@ -62,5 +63,5 @@ int libbpf_strerror(int err, char *buf, size_t size) snprintf(buf, size, "Unknown libbpf error %d", err); buf[size - 1] = '\0'; - return -1; + return libbpf_err(-ENOENT); } diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index acbcf6c7bdf8..016ca7cb4f8a 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -11,6 +11,9 @@ #include #include +#include +#include +#include "libbpf_legacy.h" /* make sure libbpf doesn't use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 @@ -28,6 +31,12 @@ #ifndef R_BPF_64_64 #define R_BPF_64_64 1 #endif +#ifndef R_BPF_64_ABS64 +#define R_BPF_64_ABS64 2 +#endif +#ifndef R_BPF_64_ABS32 +#define R_BPF_64_ABS32 3 +#endif #ifndef R_BPF_64_32 #define R_BPF_64_32 10 #endif @@ -263,6 +272,8 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name, int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, __u32 *off); struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); +void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, + const char **prefix, int *kind); struct btf_ext_info { /* @@ -433,4 +444,54 @@ int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ct int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx); int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx); +extern enum libbpf_strict_mode libbpf_mode; + +/* handle direct returned errors */ +static inline int libbpf_err(int ret) +{ + if (ret < 0) + errno = -ret; + return ret; +} + +/* handle errno-based (e.g., syscall or libc) errors according to libbpf's + * strict mode settings + */ +static inline int libbpf_err_errno(int ret) +{ + if (libbpf_mode & LIBBPF_STRICT_DIRECT_ERRS) + /* errno is already assumed to be set on error */ + return ret < 0 ? -errno : ret; + + /* legacy: on error return -1 directly and don't touch errno */ + return ret; +} + +/* handle error for pointer-returning APIs, err is assumed to be < 0 always */ +static inline void *libbpf_err_ptr(int err) +{ + /* set errno on error, this doesn't break anything */ + errno = -err; + + if (libbpf_mode & LIBBPF_STRICT_CLEAN_PTRS) + return NULL; + + /* legacy: encode err as ptr */ + return ERR_PTR(err); +} + +/* handle pointer-returning APIs' error handling */ +static inline void *libbpf_ptr(void *ret) +{ + /* set errno on error, this doesn't break anything */ + if (IS_ERR(ret)) + errno = -PTR_ERR(ret); + + if (libbpf_mode & LIBBPF_STRICT_CLEAN_PTRS) + return IS_ERR(ret) ? NULL : ret; + + /* legacy: pass-through original pointer */ + return ret; +} + #endif /* __LIBBPF_LIBBPF_INTERNAL_H */ diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h new file mode 100644 index 000000000000..df0d03dcffab --- /dev/null +++ b/tools/lib/bpf/libbpf_legacy.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ + +/* + * Libbpf legacy APIs (either discouraged or deprecated, as mentioned in [0]) + * + * [0] https://docs.google.com/document/d/1UyjTZuPFWiPFyKk1tV5an11_iaRuec6U-ZESZ54nNTY + * + * Copyright (C) 2021 Facebook + */ +#ifndef __LIBBPF_LEGACY_BPF_H +#define __LIBBPF_LEGACY_BPF_H + +#include +#include +#include +#include +#include "libbpf_common.h" + +#ifdef __cplusplus +extern "C" { +#endif + +enum libbpf_strict_mode { + /* Turn on all supported strict features of libbpf to simulate libbpf + * v1.0 behavior. + * This will be the default behavior in libbpf v1.0. + */ + LIBBPF_STRICT_ALL = 0xffffffff, + + /* + * Disable any libbpf 1.0 behaviors. This is the default before libbpf + * v1.0. It won't be supported anymore in v1.0, please update your + * code so that it handles LIBBPF_STRICT_ALL mode before libbpf v1.0. + */ + LIBBPF_STRICT_NONE = 0x00, + /* + * Return NULL pointers on error, not ERR_PTR(err). + * Additionally, libbpf also always sets errno to corresponding Exx + * (positive) error code. + */ + LIBBPF_STRICT_CLEAN_PTRS = 0x01, + /* + * Return actual error codes from low-level APIs directly, not just -1. + * Additionally, libbpf also always sets errno to corresponding Exx + * (positive) error code. + */ + LIBBPF_STRICT_DIRECT_ERRS = 0x02, + + __LIBBPF_STRICT_LAST, +}; + +LIBBPF_API int libbpf_set_strict_mode(enum libbpf_strict_mode mode); + + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif /* __LIBBPF_LEGACY_BPF_H */ diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 9de084b1c699..10911a8cad0f 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -158,7 +158,9 @@ struct bpf_linker { static int init_output_elf(struct bpf_linker *linker, const char *file); -static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, struct src_obj *obj); +static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, + const struct bpf_linker_file_opts *opts, + struct src_obj *obj); static int linker_sanity_check_elf(struct src_obj *obj); static int linker_sanity_check_elf_symtab(struct src_obj *obj, struct src_sec *sec); static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *sec); @@ -218,16 +220,16 @@ struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts int err; if (!OPTS_VALID(opts, bpf_linker_opts)) - return NULL; + return errno = EINVAL, NULL; if (elf_version(EV_CURRENT) == EV_NONE) { pr_warn_elf("libelf initialization failed"); - return NULL; + return errno = EINVAL, NULL; } linker = calloc(1, sizeof(*linker)); if (!linker) - return NULL; + return errno = ENOMEM, NULL; linker->fd = -1; @@ -239,7 +241,7 @@ struct bpf_linker *bpf_linker__new(const char *filename, struct bpf_linker_opts err_out: bpf_linker__free(linker); - return NULL; + return errno = -err, NULL; } static struct dst_sec *add_dst_sec(struct bpf_linker *linker, const char *sec_name) @@ -435,15 +437,19 @@ static int init_output_elf(struct bpf_linker *linker, const char *file) return 0; } -int bpf_linker__add_file(struct bpf_linker *linker, const char *filename) +int bpf_linker__add_file(struct bpf_linker *linker, const char *filename, + const struct bpf_linker_file_opts *opts) { struct src_obj obj = {}; int err = 0; - if (!linker->elf) - return -EINVAL; + if (!OPTS_VALID(opts, bpf_linker_file_opts)) + return libbpf_err(-EINVAL); - err = err ?: linker_load_obj_file(linker, filename, &obj); + if (!linker->elf) + return libbpf_err(-EINVAL); + + err = err ?: linker_load_obj_file(linker, filename, opts, &obj); err = err ?: linker_append_sec_data(linker, &obj); err = err ?: linker_append_elf_syms(linker, &obj); err = err ?: linker_append_elf_relos(linker, &obj); @@ -461,7 +467,7 @@ int bpf_linker__add_file(struct bpf_linker *linker, const char *filename) if (obj.fd >= 0) close(obj.fd); - return err; + return libbpf_err(err); } static bool is_dwarf_sec_name(const char *name) @@ -529,7 +535,9 @@ static struct src_sec *add_src_sec(struct src_obj *obj, const char *sec_name) return sec; } -static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, struct src_obj *obj) +static int linker_load_obj_file(struct bpf_linker *linker, const char *filename, + const struct bpf_linker_file_opts *opts, + struct src_obj *obj) { #if __BYTE_ORDER == __LITTLE_ENDIAN const int host_endianness = ELFDATA2LSB; @@ -884,7 +892,8 @@ static int linker_sanity_check_elf_relos(struct src_obj *obj, struct src_sec *se size_t sym_idx = ELF64_R_SYM(relo->r_info); size_t sym_type = ELF64_R_TYPE(relo->r_info); - if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32) { + if (sym_type != R_BPF_64_64 && sym_type != R_BPF_64_32 && + sym_type != R_BPF_64_ABS64 && sym_type != R_BPF_64_ABS32) { pr_warn("ELF relo #%d in section #%zu has unexpected type %zu in %s\n", i, sec->sec_idx, sym_type, obj->filename); return -EINVAL; @@ -1780,7 +1789,7 @@ static void sym_update_visibility(Elf64_Sym *sym, int sym_vis) /* libelf doesn't provide setters for ST_VISIBILITY, * but it is stored in the lower 2 bits of st_other */ - sym->st_other &= 0x03; + sym->st_other &= ~0x03; sym->st_other |= sym_vis; } @@ -2539,11 +2548,11 @@ int bpf_linker__finalize(struct bpf_linker *linker) int err, i; if (!linker->elf) - return -EINVAL; + return libbpf_err(-EINVAL); err = finalize_btf(linker); if (err) - return err; + return libbpf_err(err); /* Finalize strings */ strs_sz = strset__data_size(linker->strtab_strs); @@ -2575,14 +2584,14 @@ int bpf_linker__finalize(struct bpf_linker *linker) if (elf_update(linker->elf, ELF_C_NULL) < 0) { err = -errno; pr_warn_elf("failed to finalize ELF layout"); - return err; + return libbpf_err(err); } /* Write out final ELF contents */ if (elf_update(linker->elf, ELF_C_WRITE) < 0) { err = -errno; pr_warn_elf("failed to write ELF contents"); - return err; + return libbpf_err(err); } elf_end(linker->elf); diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index d2cb28e9ef52..39f25e09b51e 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -4,7 +4,10 @@ #include #include #include +#include #include +#include +#include #include #include #include @@ -73,9 +76,20 @@ cleanup: return ret; } -static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq, - __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn, - void *cookie) +static void libbpf_netlink_close(int sock) +{ + close(sock); +} + +enum { + NL_CONT, + NL_NEXT, + NL_DONE, +}; + +static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq, + __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn, + void *cookie) { bool multipart = true; struct nlmsgerr *err; @@ -84,6 +98,7 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq, int len, ret; while (multipart) { +start: multipart = false; len = recv(sock, buf, sizeof(buf), 0); if (len < 0) { @@ -121,8 +136,16 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq, } if (_fn) { ret = _fn(nh, fn, cookie); - if (ret) + switch (ret) { + case NL_CONT: + break; + case NL_NEXT: + goto start; + case NL_DONE: + return 0; + default: return ret; + } } } } @@ -131,95 +154,92 @@ done: return ret; } -static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, - __u32 flags) +static int libbpf_netlink_send_recv(struct libbpf_nla_req *req, + __dump_nlmsg_t parse_msg, + libbpf_dump_nlmsg_t parse_attr, + void *cookie) { - int sock, seq = 0, ret; - struct nlattr *nla, *nla_xdp; - struct { - struct nlmsghdr nh; - struct ifinfomsg ifinfo; - char attrbuf[64]; - } req; __u32 nl_pid = 0; + int sock, ret; sock = libbpf_netlink_open(&nl_pid); if (sock < 0) return sock; - memset(&req, 0, sizeof(req)); - req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); - req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; - req.nh.nlmsg_type = RTM_SETLINK; - req.nh.nlmsg_pid = 0; - req.nh.nlmsg_seq = ++seq; - req.ifinfo.ifi_family = AF_UNSPEC; - req.ifinfo.ifi_index = ifindex; + req->nh.nlmsg_pid = 0; + req->nh.nlmsg_seq = time(NULL); - /* started nested attribute for XDP */ - nla = (struct nlattr *)(((char *)&req) - + NLMSG_ALIGN(req.nh.nlmsg_len)); - nla->nla_type = NLA_F_NESTED | IFLA_XDP; - nla->nla_len = NLA_HDRLEN; - - /* add XDP fd */ - nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); - nla_xdp->nla_type = IFLA_XDP_FD; - nla_xdp->nla_len = NLA_HDRLEN + sizeof(int); - memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd)); - nla->nla_len += nla_xdp->nla_len; - - /* if user passed in any flags, add those too */ - if (flags) { - nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); - nla_xdp->nla_type = IFLA_XDP_FLAGS; - nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags); - memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags)); - nla->nla_len += nla_xdp->nla_len; - } - - if (flags & XDP_FLAGS_REPLACE) { - nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); - nla_xdp->nla_type = IFLA_XDP_EXPECTED_FD; - nla_xdp->nla_len = NLA_HDRLEN + sizeof(old_fd); - memcpy((char *)nla_xdp + NLA_HDRLEN, &old_fd, sizeof(old_fd)); - nla->nla_len += nla_xdp->nla_len; - } - - req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len); - - if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) { + if (send(sock, req, req->nh.nlmsg_len, 0) < 0) { ret = -errno; - goto cleanup; + goto out; } - ret = bpf_netlink_recv(sock, nl_pid, seq, NULL, NULL, NULL); -cleanup: - close(sock); + ret = libbpf_netlink_recv(sock, nl_pid, req->nh.nlmsg_seq, + parse_msg, parse_attr, cookie); +out: + libbpf_netlink_close(sock); return ret; } +static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, + __u32 flags) +{ + struct nlattr *nla; + int ret; + struct libbpf_nla_req req; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_SETLINK; + req.ifinfo.ifi_family = AF_UNSPEC; + req.ifinfo.ifi_index = ifindex; + + nla = nlattr_begin_nested(&req, IFLA_XDP); + if (!nla) + return -EMSGSIZE; + ret = nlattr_add(&req, IFLA_XDP_FD, &fd, sizeof(fd)); + if (ret < 0) + return ret; + if (flags) { + ret = nlattr_add(&req, IFLA_XDP_FLAGS, &flags, sizeof(flags)); + if (ret < 0) + return ret; + } + if (flags & XDP_FLAGS_REPLACE) { + ret = nlattr_add(&req, IFLA_XDP_EXPECTED_FD, &old_fd, + sizeof(old_fd)); + if (ret < 0) + return ret; + } + nlattr_end_nested(&req, nla); + + return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); +} + int bpf_set_link_xdp_fd_opts(int ifindex, int fd, __u32 flags, const struct bpf_xdp_set_link_opts *opts) { - int old_fd = -1; + int old_fd = -1, ret; if (!OPTS_VALID(opts, bpf_xdp_set_link_opts)) - return -EINVAL; + return libbpf_err(-EINVAL); if (OPTS_HAS(opts, old_fd)) { old_fd = OPTS_GET(opts, old_fd, -1); flags |= XDP_FLAGS_REPLACE; } - return __bpf_set_link_xdp_fd_replace(ifindex, fd, - old_fd, - flags); + ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, old_fd, flags); + return libbpf_err(ret); } int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) { - return __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags); + int ret; + + ret = __bpf_set_link_xdp_fd_replace(ifindex, fd, 0, flags); + return libbpf_err(ret); } static int __dump_link_nlmsg(struct nlmsghdr *nlh, @@ -231,6 +251,7 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh, len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi)); attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi))); + if (libbpf_nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0) return -LIBBPF_ERRNO__NLPARSE; @@ -282,34 +303,33 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) return 0; } -static int libbpf_nl_get_link(int sock, unsigned int nl_pid, - libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie); - int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, size_t info_size, __u32 flags) { struct xdp_id_md xdp_id = {}; - int sock, ret; - __u32 nl_pid = 0; __u32 mask; + int ret; + struct libbpf_nla_req req = { + .nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), + .nh.nlmsg_type = RTM_GETLINK, + .nh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .ifinfo.ifi_family = AF_PACKET, + }; if (flags & ~XDP_FLAGS_MASK || !info_size) - return -EINVAL; + return libbpf_err(-EINVAL); /* Check whether the single {HW,DRV,SKB} mode is set */ flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE); mask = flags - 1; if (flags && flags & mask) - return -EINVAL; - - sock = libbpf_netlink_open(&nl_pid); - if (sock < 0) - return sock; + return libbpf_err(-EINVAL); xdp_id.ifindex = ifindex; xdp_id.flags = flags; - ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_info, &xdp_id); + ret = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, + get_xdp_info, &xdp_id); if (!ret) { size_t sz = min(info_size, sizeof(xdp_id.info)); @@ -317,8 +337,7 @@ int bpf_get_link_xdp_info(int ifindex, struct xdp_link_info *info, memset((void *) info + sz, 0, info_size - sz); } - close(sock); - return ret; + return libbpf_err(ret); } static __u32 get_xdp_id(struct xdp_link_info *info, __u32 flags) @@ -346,27 +365,394 @@ int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) if (!ret) *prog_id = get_xdp_id(&info, flags); + return libbpf_err(ret); +} + +typedef int (*qdisc_config_t)(struct libbpf_nla_req *req); + +static int clsact_config(struct libbpf_nla_req *req) +{ + req->tc.tcm_parent = TC_H_CLSACT; + req->tc.tcm_handle = TC_H_MAKE(TC_H_CLSACT, 0); + + return nlattr_add(req, TCA_KIND, "clsact", sizeof("clsact")); +} + +static int attach_point_to_config(struct bpf_tc_hook *hook, + qdisc_config_t *config) +{ + switch (OPTS_GET(hook, attach_point, 0)) { + case BPF_TC_INGRESS: + case BPF_TC_EGRESS: + case BPF_TC_INGRESS | BPF_TC_EGRESS: + if (OPTS_GET(hook, parent, 0)) + return -EINVAL; + *config = &clsact_config; + return 0; + case BPF_TC_CUSTOM: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +static int tc_get_tcm_parent(enum bpf_tc_attach_point attach_point, + __u32 *parent) +{ + switch (attach_point) { + case BPF_TC_INGRESS: + case BPF_TC_EGRESS: + if (*parent) + return -EINVAL; + *parent = TC_H_MAKE(TC_H_CLSACT, + attach_point == BPF_TC_INGRESS ? + TC_H_MIN_INGRESS : TC_H_MIN_EGRESS); + break; + case BPF_TC_CUSTOM: + if (!*parent) + return -EINVAL; + break; + default: + return -EINVAL; + } + return 0; +} + +static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags) +{ + qdisc_config_t config; + int ret; + struct libbpf_nla_req req; + + ret = attach_point_to_config(hook, &config); + if (ret < 0) + return ret; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | flags; + req.nh.nlmsg_type = cmd; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = OPTS_GET(hook, ifindex, 0); + + ret = config(&req); + if (ret < 0) + return ret; + + return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); +} + +static int tc_qdisc_create_excl(struct bpf_tc_hook *hook) +{ + return tc_qdisc_modify(hook, RTM_NEWQDISC, NLM_F_CREATE | NLM_F_EXCL); +} + +static int tc_qdisc_delete(struct bpf_tc_hook *hook) +{ + return tc_qdisc_modify(hook, RTM_DELQDISC, 0); +} + +int bpf_tc_hook_create(struct bpf_tc_hook *hook) +{ + int ret; + + if (!hook || !OPTS_VALID(hook, bpf_tc_hook) || + OPTS_GET(hook, ifindex, 0) <= 0) + return libbpf_err(-EINVAL); + + ret = tc_qdisc_create_excl(hook); + return libbpf_err(ret); +} + +static int __bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts, + const bool flush); + +int bpf_tc_hook_destroy(struct bpf_tc_hook *hook) +{ + if (!hook || !OPTS_VALID(hook, bpf_tc_hook) || + OPTS_GET(hook, ifindex, 0) <= 0) + return libbpf_err(-EINVAL); + + switch (OPTS_GET(hook, attach_point, 0)) { + case BPF_TC_INGRESS: + case BPF_TC_EGRESS: + return libbpf_err(__bpf_tc_detach(hook, NULL, true)); + case BPF_TC_INGRESS | BPF_TC_EGRESS: + return libbpf_err(tc_qdisc_delete(hook)); + case BPF_TC_CUSTOM: + return libbpf_err(-EOPNOTSUPP); + default: + return libbpf_err(-EINVAL); + } +} + +struct bpf_cb_ctx { + struct bpf_tc_opts *opts; + bool processed; +}; + +static int __get_tc_info(void *cookie, struct tcmsg *tc, struct nlattr **tb, + bool unicast) +{ + struct nlattr *tbb[TCA_BPF_MAX + 1]; + struct bpf_cb_ctx *info = cookie; + + if (!info || !info->opts) + return -EINVAL; + if (unicast && info->processed) + return -EINVAL; + if (!tb[TCA_OPTIONS]) + return NL_CONT; + + libbpf_nla_parse_nested(tbb, TCA_BPF_MAX, tb[TCA_OPTIONS], NULL); + if (!tbb[TCA_BPF_ID]) + return -EINVAL; + + OPTS_SET(info->opts, prog_id, libbpf_nla_getattr_u32(tbb[TCA_BPF_ID])); + OPTS_SET(info->opts, handle, tc->tcm_handle); + OPTS_SET(info->opts, priority, TC_H_MAJ(tc->tcm_info) >> 16); + + info->processed = true; + return unicast ? NL_NEXT : NL_DONE; +} + +static int get_tc_info(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct tcmsg *tc = NLMSG_DATA(nh); + struct nlattr *tb[TCA_MAX + 1]; + + libbpf_nla_parse(tb, TCA_MAX, + (struct nlattr *)((void *)tc + NLMSG_ALIGN(sizeof(*tc))), + NLMSG_PAYLOAD(nh, sizeof(*tc)), NULL); + if (!tb[TCA_KIND]) + return NL_CONT; + return __get_tc_info(cookie, tc, tb, nh->nlmsg_flags & NLM_F_ECHO); +} + +static int tc_add_fd_and_name(struct libbpf_nla_req *req, int fd) +{ + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + char name[256]; + int len, ret; + + ret = bpf_obj_get_info_by_fd(fd, &info, &info_len); + if (ret < 0) + return ret; + + ret = nlattr_add(req, TCA_BPF_FD, &fd, sizeof(fd)); + if (ret < 0) + return ret; + len = snprintf(name, sizeof(name), "%s:[%u]", info.name, info.id); + if (len < 0) + return -errno; + if (len >= sizeof(name)) + return -ENAMETOOLONG; + return nlattr_add(req, TCA_BPF_NAME, name, len + 1); +} + +int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) +{ + __u32 protocol, bpf_flags, handle, priority, parent, prog_id, flags; + int ret, ifindex, attach_point, prog_fd; + struct bpf_cb_ctx info = {}; + struct libbpf_nla_req req; + struct nlattr *nla; + + if (!hook || !opts || + !OPTS_VALID(hook, bpf_tc_hook) || + !OPTS_VALID(opts, bpf_tc_opts)) + return libbpf_err(-EINVAL); + + ifindex = OPTS_GET(hook, ifindex, 0); + parent = OPTS_GET(hook, parent, 0); + attach_point = OPTS_GET(hook, attach_point, 0); + + handle = OPTS_GET(opts, handle, 0); + priority = OPTS_GET(opts, priority, 0); + prog_fd = OPTS_GET(opts, prog_fd, 0); + prog_id = OPTS_GET(opts, prog_id, 0); + flags = OPTS_GET(opts, flags, 0); + + if (ifindex <= 0 || !prog_fd || prog_id) + return libbpf_err(-EINVAL); + if (priority > UINT16_MAX) + return libbpf_err(-EINVAL); + if (flags & ~BPF_TC_F_REPLACE) + return libbpf_err(-EINVAL); + + flags = (flags & BPF_TC_F_REPLACE) ? NLM_F_REPLACE : NLM_F_EXCL; + protocol = ETH_P_ALL; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_CREATE | + NLM_F_ECHO | flags; + req.nh.nlmsg_type = RTM_NEWTFILTER; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = ifindex; + req.tc.tcm_handle = handle; + req.tc.tcm_info = TC_H_MAKE(priority << 16, htons(protocol)); + + ret = tc_get_tcm_parent(attach_point, &parent); + if (ret < 0) + return libbpf_err(ret); + req.tc.tcm_parent = parent; + + ret = nlattr_add(&req, TCA_KIND, "bpf", sizeof("bpf")); + if (ret < 0) + return libbpf_err(ret); + nla = nlattr_begin_nested(&req, TCA_OPTIONS); + if (!nla) + return libbpf_err(-EMSGSIZE); + ret = tc_add_fd_and_name(&req, prog_fd); + if (ret < 0) + return libbpf_err(ret); + bpf_flags = TCA_BPF_FLAG_ACT_DIRECT; + ret = nlattr_add(&req, TCA_BPF_FLAGS, &bpf_flags, sizeof(bpf_flags)); + if (ret < 0) + return libbpf_err(ret); + nlattr_end_nested(&req, nla); + + info.opts = opts; + + ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info); + if (ret < 0) + return libbpf_err(ret); + if (!info.processed) + return libbpf_err(-ENOENT); return ret; } -int libbpf_nl_get_link(int sock, unsigned int nl_pid, - libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie) +static int __bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts, + const bool flush) { - struct { - struct nlmsghdr nlh; - struct ifinfomsg ifm; - } req = { - .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), - .nlh.nlmsg_type = RTM_GETLINK, - .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, - .ifm.ifi_family = AF_PACKET, - }; - int seq = time(NULL); + __u32 protocol = 0, handle, priority, parent, prog_id, flags; + int ret, ifindex, attach_point, prog_fd; + struct libbpf_nla_req req; - req.nlh.nlmsg_seq = seq; - if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) - return -errno; + if (!hook || + !OPTS_VALID(hook, bpf_tc_hook) || + !OPTS_VALID(opts, bpf_tc_opts)) + return -EINVAL; - return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg, - dump_link_nlmsg, cookie); + ifindex = OPTS_GET(hook, ifindex, 0); + parent = OPTS_GET(hook, parent, 0); + attach_point = OPTS_GET(hook, attach_point, 0); + + handle = OPTS_GET(opts, handle, 0); + priority = OPTS_GET(opts, priority, 0); + prog_fd = OPTS_GET(opts, prog_fd, 0); + prog_id = OPTS_GET(opts, prog_id, 0); + flags = OPTS_GET(opts, flags, 0); + + if (ifindex <= 0 || flags || prog_fd || prog_id) + return -EINVAL; + if (priority > UINT16_MAX) + return -EINVAL; + if (!flush) { + if (!handle || !priority) + return -EINVAL; + protocol = ETH_P_ALL; + } else { + if (handle || priority) + return -EINVAL; + } + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_DELTFILTER; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = ifindex; + if (!flush) { + req.tc.tcm_handle = handle; + req.tc.tcm_info = TC_H_MAKE(priority << 16, htons(protocol)); + } + + ret = tc_get_tcm_parent(attach_point, &parent); + if (ret < 0) + return ret; + req.tc.tcm_parent = parent; + + if (!flush) { + ret = nlattr_add(&req, TCA_KIND, "bpf", sizeof("bpf")); + if (ret < 0) + return ret; + } + + return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); +} + +int bpf_tc_detach(const struct bpf_tc_hook *hook, + const struct bpf_tc_opts *opts) +{ + int ret; + + if (!opts) + return libbpf_err(-EINVAL); + + ret = __bpf_tc_detach(hook, opts, false); + return libbpf_err(ret); +} + +int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) +{ + __u32 protocol, handle, priority, parent, prog_id, flags; + int ret, ifindex, attach_point, prog_fd; + struct bpf_cb_ctx info = {}; + struct libbpf_nla_req req; + + if (!hook || !opts || + !OPTS_VALID(hook, bpf_tc_hook) || + !OPTS_VALID(opts, bpf_tc_opts)) + return libbpf_err(-EINVAL); + + ifindex = OPTS_GET(hook, ifindex, 0); + parent = OPTS_GET(hook, parent, 0); + attach_point = OPTS_GET(hook, attach_point, 0); + + handle = OPTS_GET(opts, handle, 0); + priority = OPTS_GET(opts, priority, 0); + prog_fd = OPTS_GET(opts, prog_fd, 0); + prog_id = OPTS_GET(opts, prog_id, 0); + flags = OPTS_GET(opts, flags, 0); + + if (ifindex <= 0 || flags || prog_fd || prog_id || + !handle || !priority) + return libbpf_err(-EINVAL); + if (priority > UINT16_MAX) + return libbpf_err(-EINVAL); + + protocol = ETH_P_ALL; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST; + req.nh.nlmsg_type = RTM_GETTFILTER; + req.tc.tcm_family = AF_UNSPEC; + req.tc.tcm_ifindex = ifindex; + req.tc.tcm_handle = handle; + req.tc.tcm_info = TC_H_MAKE(priority << 16, htons(protocol)); + + ret = tc_get_tcm_parent(attach_point, &parent); + if (ret < 0) + return libbpf_err(ret); + req.tc.tcm_parent = parent; + + ret = nlattr_add(&req, TCA_KIND, "bpf", sizeof("bpf")); + if (ret < 0) + return libbpf_err(ret); + + info.opts = opts; + + ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info); + if (ret < 0) + return libbpf_err(ret); + if (!info.processed) + return libbpf_err(-ENOENT); + return ret; } diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index b607fa9852b1..f57e77a6e40f 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -27,7 +27,7 @@ static struct nlattr *nla_next(const struct nlattr *nla, int *remaining) int totlen = NLA_ALIGN(nla->nla_len); *remaining -= totlen; - return (struct nlattr *) ((char *) nla + totlen); + return (struct nlattr *)((void *)nla + totlen); } static int nla_ok(const struct nlattr *nla, int remaining) diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h index 6cc3ac91690f..4d15ae2ff812 100644 --- a/tools/lib/bpf/nlattr.h +++ b/tools/lib/bpf/nlattr.h @@ -10,7 +10,11 @@ #define __LIBBPF_NLATTR_H #include +#include +#include #include +#include + /* avoid multiple definition of netlink features */ #define __LINUX_NETLINK_H @@ -49,6 +53,15 @@ struct libbpf_nla_policy { uint16_t maxlen; }; +struct libbpf_nla_req { + struct nlmsghdr nh; + union { + struct ifinfomsg ifinfo; + struct tcmsg tc; + }; + char buf[128]; +}; + /** * @ingroup attr * Iterate over a stream of attributes @@ -68,7 +81,7 @@ struct libbpf_nla_policy { */ static inline void *libbpf_nla_data(const struct nlattr *nla) { - return (char *) nla + NLA_HDRLEN; + return (void *)nla + NLA_HDRLEN; } static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla) @@ -103,4 +116,49 @@ int libbpf_nla_parse_nested(struct nlattr *tb[], int maxtype, int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh); +static inline struct nlattr *nla_data(struct nlattr *nla) +{ + return (struct nlattr *)((void *)nla + NLA_HDRLEN); +} + +static inline struct nlattr *req_tail(struct libbpf_nla_req *req) +{ + return (struct nlattr *)((void *)req + NLMSG_ALIGN(req->nh.nlmsg_len)); +} + +static inline int nlattr_add(struct libbpf_nla_req *req, int type, + const void *data, int len) +{ + struct nlattr *nla; + + if (NLMSG_ALIGN(req->nh.nlmsg_len) + NLA_ALIGN(NLA_HDRLEN + len) > sizeof(*req)) + return -EMSGSIZE; + if (!!data != !!len) + return -EINVAL; + + nla = req_tail(req); + nla->nla_type = type; + nla->nla_len = NLA_HDRLEN + len; + if (data) + memcpy(nla_data(nla), data, len); + req->nh.nlmsg_len = NLMSG_ALIGN(req->nh.nlmsg_len) + NLA_ALIGN(nla->nla_len); + return 0; +} + +static inline struct nlattr *nlattr_begin_nested(struct libbpf_nla_req *req, int type) +{ + struct nlattr *tail; + + tail = req_tail(req); + if (nlattr_add(req, type | NLA_F_NESTED, NULL, 0)) + return NULL; + return tail; +} + +static inline void nlattr_end_nested(struct libbpf_nla_req *req, + struct nlattr *tail) +{ + tail->nla_len = (void *)req_tail(req) - (void *)tail; +} + #endif /* __LIBBPF_NLATTR_H */ diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index 1d80ad4e0de8..8bc117bcc7bc 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -69,23 +69,23 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, err = -errno; pr_warn("ringbuf: failed to get map info for fd=%d: %d\n", map_fd, err); - return err; + return libbpf_err(err); } if (info.type != BPF_MAP_TYPE_RINGBUF) { pr_warn("ringbuf: map fd=%d is not BPF_MAP_TYPE_RINGBUF\n", map_fd); - return -EINVAL; + return libbpf_err(-EINVAL); } tmp = libbpf_reallocarray(rb->rings, rb->ring_cnt + 1, sizeof(*rb->rings)); if (!tmp) - return -ENOMEM; + return libbpf_err(-ENOMEM); rb->rings = tmp; tmp = libbpf_reallocarray(rb->events, rb->ring_cnt + 1, sizeof(*rb->events)); if (!tmp) - return -ENOMEM; + return libbpf_err(-ENOMEM); rb->events = tmp; r = &rb->rings[rb->ring_cnt]; @@ -103,7 +103,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, err = -errno; pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n", map_fd, err); - return err; + return libbpf_err(err); } r->consumer_pos = tmp; @@ -118,7 +118,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, ringbuf_unmap_ring(rb, r); pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n", map_fd, err); - return err; + return libbpf_err(err); } r->producer_pos = tmp; r->data = tmp + rb->page_size; @@ -133,7 +133,7 @@ int ring_buffer__add(struct ring_buffer *rb, int map_fd, ringbuf_unmap_ring(rb, r); pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n", map_fd, err); - return err; + return libbpf_err(err); } rb->ring_cnt++; @@ -165,11 +165,11 @@ ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx, int err; if (!OPTS_VALID(opts, ring_buffer_opts)) - return NULL; + return errno = EINVAL, NULL; rb = calloc(1, sizeof(*rb)); if (!rb) - return NULL; + return errno = ENOMEM, NULL; rb->page_size = getpagesize(); @@ -188,7 +188,7 @@ ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx, err_out: ring_buffer__free(rb); - return NULL; + return errno = -err, NULL; } static inline int roundup_len(__u32 len) @@ -260,7 +260,7 @@ int ring_buffer__consume(struct ring_buffer *rb) err = ringbuf_process_ring(ring); if (err < 0) - return err; + return libbpf_err(err); res += err; } if (res > INT_MAX) @@ -279,7 +279,7 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms) cnt = epoll_wait(rb->epoll_fd, rb->events, rb->ring_cnt, timeout_ms); if (cnt < 0) - return -errno; + return libbpf_err(-errno); for (i = 0; i < cnt; i++) { __u32 ring_id = rb->events[i].data.fd; @@ -287,7 +287,7 @@ int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms) err = ringbuf_process_ring(ring); if (err < 0) - return err; + return libbpf_err(err); res += err; } if (res > INT_MAX) diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h new file mode 100644 index 000000000000..b22b50c1b173 --- /dev/null +++ b/tools/lib/bpf/skel_internal.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2021 Facebook */ +#ifndef __SKEL_INTERNAL_H +#define __SKEL_INTERNAL_H + +#include +#include +#include + +/* This file is a base header for auto-generated *.lskel.h files. + * Its contents will change and may become part of auto-generation in the future. + * + * The layout of bpf_[map|prog]_desc and bpf_loader_ctx is feature dependent + * and will change from one version of libbpf to another and features + * requested during loader program generation. + */ +struct bpf_map_desc { + union { + /* input for the loader prog */ + struct { + __aligned_u64 initial_value; + __u32 max_entries; + }; + /* output of the loader prog */ + struct { + int map_fd; + }; + }; +}; +struct bpf_prog_desc { + int prog_fd; +}; + +struct bpf_loader_ctx { + size_t sz; + __u32 log_level; + __u32 log_size; + __u64 log_buf; +}; + +struct bpf_load_and_run_opts { + struct bpf_loader_ctx *ctx; + const void *data; + const void *insns; + __u32 data_sz; + __u32 insns_sz; + const char *errstr; +}; + +static inline int skel_sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, + unsigned int size) +{ + return syscall(__NR_bpf, cmd, attr, size); +} + +static inline int skel_closenz(int fd) +{ + if (fd > 0) + return close(fd); + return -EINVAL; +} + +static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) +{ + int map_fd = -1, prog_fd = -1, key = 0, err; + union bpf_attr attr; + + map_fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, + opts->data_sz, 1, 0); + if (map_fd < 0) { + opts->errstr = "failed to create loader map"; + err = -errno; + goto out; + } + + err = bpf_map_update_elem(map_fd, &key, opts->data, 0); + if (err < 0) { + opts->errstr = "failed to update loader map"; + err = -errno; + goto out; + } + + memset(&attr, 0, sizeof(attr)); + attr.prog_type = BPF_PROG_TYPE_SYSCALL; + attr.insns = (long) opts->insns; + attr.insn_cnt = opts->insns_sz / sizeof(struct bpf_insn); + attr.license = (long) "Dual BSD/GPL"; + memcpy(attr.prog_name, "__loader.prog", sizeof("__loader.prog")); + attr.fd_array = (long) &map_fd; + attr.log_level = opts->ctx->log_level; + attr.log_size = opts->ctx->log_size; + attr.log_buf = opts->ctx->log_buf; + attr.prog_flags = BPF_F_SLEEPABLE; + prog_fd = skel_sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); + if (prog_fd < 0) { + opts->errstr = "failed to load loader prog"; + err = -errno; + goto out; + } + + memset(&attr, 0, sizeof(attr)); + attr.test.prog_fd = prog_fd; + attr.test.ctx_in = (long) opts->ctx; + attr.test.ctx_size_in = opts->ctx->sz; + err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr)); + if (err < 0 || (int)attr.test.retval < 0) { + opts->errstr = "failed to execute loader prog"; + if (err < 0) + err = -errno; + else + err = (int)attr.test.retval; + goto out; + } + err = 0; +out: + if (map_fd >= 0) + close(map_fd); + if (prog_fd >= 0) + close(prog_fd); + return err; +} + +#endif diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c index ab940c508ef0..bf9fd3549a1d 100644 --- a/tools/power/x86/intel-speed-select/isst-config.c +++ b/tools/power/x86/intel-speed-select/isst-config.c @@ -15,7 +15,7 @@ struct process_cmd_struct { int arg; }; -static const char *version_str = "v1.9"; +static const char *version_str = "v1.10"; static const int supported_api_ver = 1; static struct isst_if_platform_info isst_platform_info; static char *progname; @@ -106,6 +106,22 @@ int is_skx_based_platform(void) return 0; } +int is_spr_platform(void) +{ + if (cpu_model == 0x8F) + return 1; + + return 0; +} + +int is_icx_platform(void) +{ + if (cpu_model == 0x6A || cpu_model == 0x6C) + return 1; + + return 0; +} + static int update_cpu_model(void) { unsigned int ebx, ecx, edx; diff --git a/tools/power/x86/intel-speed-select/isst-core.c b/tools/power/x86/intel-speed-select/isst-core.c index 6a26d5769984..4431c8a0d40a 100644 --- a/tools/power/x86/intel-speed-select/isst-core.c +++ b/tools/power/x86/intel-speed-select/isst-core.c @@ -201,6 +201,7 @@ void isst_get_uncore_mem_freq(int cpu, int config_index, { unsigned int resp; int ret; + ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_GET_MEM_FREQ, 0, config_index, &resp); if (ret) { @@ -209,6 +210,20 @@ void isst_get_uncore_mem_freq(int cpu, int config_index, } ctdp_level->mem_freq = resp & GENMASK(7, 0); + if (is_spr_platform()) { + ctdp_level->mem_freq *= 200; + } else if (is_icx_platform()) { + if (ctdp_level->mem_freq < 7) { + ctdp_level->mem_freq = (12 - ctdp_level->mem_freq) * 133.33 * 2 * 10; + ctdp_level->mem_freq /= 10; + if (ctdp_level->mem_freq % 10 > 5) + ctdp_level->mem_freq++; + } else { + ctdp_level->mem_freq = 0; + } + } else { + ctdp_level->mem_freq = 0; + } debug_printf( "cpu:%d ctdp:%d CONFIG_TDP_GET_MEM_FREQ resp:%x uncore mem_freq:%d\n", cpu, config_index, resp, ctdp_level->mem_freq); diff --git a/tools/power/x86/intel-speed-select/isst-display.c b/tools/power/x86/intel-speed-select/isst-display.c index 3bf1820c0da1..f97d8859ada7 100644 --- a/tools/power/x86/intel-speed-select/isst-display.c +++ b/tools/power/x86/intel-speed-select/isst-display.c @@ -446,7 +446,7 @@ void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level, if (ctdp_level->mem_freq) { snprintf(header, sizeof(header), "mem-frequency(MHz)"); snprintf(value, sizeof(value), "%d", - ctdp_level->mem_freq * DISP_FREQ_MULTIPLIER); + ctdp_level->mem_freq); format_and_print(outf, level + 2, header, value); } diff --git a/tools/power/x86/intel-speed-select/isst.h b/tools/power/x86/intel-speed-select/isst.h index 0cac6c54be87..1aa15d5ea57c 100644 --- a/tools/power/x86/intel-speed-select/isst.h +++ b/tools/power/x86/intel-speed-select/isst.h @@ -257,5 +257,7 @@ extern int get_cpufreq_base_freq(int cpu); extern int isst_read_pm_config(int cpu, int *cp_state, int *cp_cap); extern void isst_display_error_info_message(int error, char *msg, int arg_valid, int arg); extern int is_skx_based_platform(void); +extern int is_spr_platform(void); +extern int is_icx_platform(void); extern void isst_trl_display_information(int cpu, FILE *outf, unsigned long long trl); #endif diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index bc3299a20338..fb010a35d61a 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -49,6 +49,7 @@ TARGETS += proc TARGETS += pstore TARGETS += ptrace TARGETS += openat2 +TARGETS += rlimits TARGETS += rseq TARGETS += rtc TARGETS += seccomp diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 4866f6a21901..addcfd8b615e 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -10,6 +10,7 @@ FEATURE-DUMP.libbpf fixdep test_dev_cgroup /test_progs* +!test_progs.h test_verifier_log feature test_sock @@ -30,10 +31,13 @@ test_sysctl xdping test_cpp *.skel.h +*.lskel.h /no_alu32 /bpf_gcc /tools /runqslower /bench *.ko +*.tmp xdpxceiver +xdp_redirect_multi diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 511259c2c6c5..f405b20c1e6c 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -54,6 +54,7 @@ TEST_FILES = xsk_prereqs.sh \ # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ test_xdp_redirect.sh \ + test_xdp_redirect_multi.sh \ test_xdp_meta.sh \ test_xdp_veth.sh \ test_offload.py \ @@ -84,7 +85,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \ - xdpxceiver + xdpxceiver xdp_redirect_multi TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read @@ -312,6 +313,10 @@ SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ linked_vars.skel.h linked_maps.skel.h +LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \ + test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c +SKEL_BLACKLIST += $$(LSKELS) + test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o linked_funcs.skel.h-deps := linked_funcs1.o linked_funcs2.o linked_vars.skel.h-deps := linked_vars1.o linked_vars2.o @@ -339,6 +344,7 @@ TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS) TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \ $$(filter-out $(SKEL_BLACKLIST) $(LINKED_BPF_SRCS),\ $$(TRUNNER_BPF_SRCS))) +TRUNNER_BPF_LSKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS)) TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS)) TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS) @@ -380,6 +386,14 @@ $(TRUNNER_BPF_SKELS): %.skel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT) $(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o) $(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@ +$(TRUNNER_BPF_LSKELS): %.lskel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT) + $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@) + $(Q)$$(BPFTOOL) gen object $$(<:.o=.linked1.o) $$< + $(Q)$$(BPFTOOL) gen object $$(<:.o=.linked2.o) $$(<:.o=.linked1.o) + $(Q)$$(BPFTOOL) gen object $$(<:.o=.linked3.o) $$(<:.o=.linked2.o) + $(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o) + $(Q)$$(BPFTOOL) gen skeleton -L $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@ + $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT) $$(call msg,LINK-BPF,$(TRUNNER_BINARY),$$(@:.skel.h=.o)) $(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked1.o) $$(addprefix $(TRUNNER_OUTPUT)/,$$($$(@F)-deps)) @@ -409,6 +423,7 @@ $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o: \ $(TRUNNER_EXTRA_HDRS) \ $(TRUNNER_BPF_OBJS) \ $(TRUNNER_BPF_SKELS) \ + $(TRUNNER_BPF_LSKELS) \ $(TRUNNER_BPF_SKELS_LINKED) \ $$(BPFOBJ) | $(TRUNNER_OUTPUT) $$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@) @@ -516,6 +531,6 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ feature \ - $(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc bpf_testmod.ko) + $(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h no_alu32 bpf_gcc bpf_testmod.ko) .PHONY: docs docs-clean diff --git a/tools/testing/selftests/bpf/Makefile.docs b/tools/testing/selftests/bpf/Makefile.docs index ccf260021e83..eb6a4fea8c79 100644 --- a/tools/testing/selftests/bpf/Makefile.docs +++ b/tools/testing/selftests/bpf/Makefile.docs @@ -52,7 +52,8 @@ $(OUTPUT)%.$2: $(OUTPUT)%.rst ifndef RST2MAN_DEP $$(error "rst2man not found, but required to generate man pages") endif - $$(QUIET_GEN)rst2man $$< > $$@ + $$(QUIET_GEN)rst2man --exit-status=1 $$< > $$@.tmp + $$(QUIET_GEN)mv $$@.tmp $$@ docs-clean-$1: $$(call QUIET_CLEAN, eBPF_$1-manpage) diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 3353778c30f8..8deec1ca9150 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -202,3 +202,22 @@ generate valid BTF information for weak variables. Please make sure you use Clang that contains the fix. __ https://reviews.llvm.org/D100362 + +Clang relocation changes +======================== + +Clang 13 patch `clang reloc patch`_ made some changes on relocations such +that existing relocation types are broken into more types and +each new type corresponds to only one way to resolve relocation. +See `kernel llvm reloc`_ for more explanation and some examples. +Using clang 13 to compile old libbpf which has static linker support, +there will be a compilation failure:: + + libbpf: ELF relo #0 in section #6 has unexpected type 2 in .../bpf_tcp_nogpl.o + +Here, ``type 2`` refers to new relocation type ``R_BPF_64_ABS64``. +To fix this issue, user newer libbpf. + +.. Links +.. _clang reloc patch: https://reviews.llvm.org/D102712 +.. _kernel llvm reloc: /Documentation/bpf/llvm_reloc.rst diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index 332ed2f7b402..6ea15b93a2f8 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -43,6 +43,7 @@ void setup_libbpf() { int err; + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); libbpf_set_print(libbpf_print_fn); err = bump_memlock_rlimit(); diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c index a967674098ad..c7ec114eca56 100644 --- a/tools/testing/selftests/bpf/benchs/bench_rename.c +++ b/tools/testing/selftests/bpf/benchs/bench_rename.c @@ -65,7 +65,7 @@ static void attach_bpf(struct bpf_program *prog) struct bpf_link *link; link = bpf_program__attach(prog); - if (IS_ERR(link)) { + if (!link) { fprintf(stderr, "failed to attach program!\n"); exit(1); } diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c index bde6c9d4cbd4..d167bffac679 100644 --- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c +++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c @@ -181,7 +181,7 @@ static void ringbuf_libbpf_setup() } link = bpf_program__attach(ctx->skel->progs.bench_ringbuf); - if (IS_ERR(link)) { + if (!link) { fprintf(stderr, "failed to attach program!\n"); exit(1); } @@ -271,7 +271,7 @@ static void ringbuf_custom_setup() } link = bpf_program__attach(ctx->skel->progs.bench_ringbuf); - if (IS_ERR(link)) { + if (!link) { fprintf(stderr, "failed to attach program\n"); exit(1); } @@ -430,7 +430,7 @@ static void perfbuf_libbpf_setup() } link = bpf_program__attach(ctx->skel->progs.bench_perfbuf); - if (IS_ERR(link)) { + if (!link) { fprintf(stderr, "failed to attach program\n"); exit(1); } diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index 2a0b6c9885a4..f41a491a8cc0 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -60,7 +60,7 @@ static void attach_bpf(struct bpf_program *prog) struct bpf_link *link; link = bpf_program__attach(prog); - if (IS_ERR(link)) { + if (!link) { fprintf(stderr, "failed to attach program!\n"); exit(1); } diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c index 21efe7bbf10d..ba0e1efe5a45 100644 --- a/tools/testing/selftests/bpf/prog_tests/atomics.c +++ b/tools/testing/selftests/bpf/prog_tests/atomics.c @@ -2,19 +2,19 @@ #include -#include "atomics.skel.h" +#include "atomics.lskel.h" static void test_add(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.add); - if (CHECK(IS_ERR(link), "attach(add)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__add__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(add)")) return; - prog_fd = bpf_program__fd(skel->progs.add); + prog_fd = skel->progs.add.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run add", @@ -33,20 +33,20 @@ static void test_add(struct atomics *skel) ASSERT_EQ(skel->data->add_noreturn_value, 3, "add_noreturn_value"); cleanup: - bpf_link__destroy(link); + close(link_fd); } static void test_sub(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.sub); - if (CHECK(IS_ERR(link), "attach(sub)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__sub__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(sub)")) return; - prog_fd = bpf_program__fd(skel->progs.sub); + prog_fd = skel->progs.sub.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run sub", @@ -66,20 +66,20 @@ static void test_sub(struct atomics *skel) ASSERT_EQ(skel->data->sub_noreturn_value, -1, "sub_noreturn_value"); cleanup: - bpf_link__destroy(link); + close(link_fd); } static void test_and(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.and); - if (CHECK(IS_ERR(link), "attach(and)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__and__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(and)")) return; - prog_fd = bpf_program__fd(skel->progs.and); + prog_fd = skel->progs.and.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run and", @@ -94,20 +94,20 @@ static void test_and(struct atomics *skel) ASSERT_EQ(skel->data->and_noreturn_value, 0x010ull << 32, "and_noreturn_value"); cleanup: - bpf_link__destroy(link); + close(link_fd); } static void test_or(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.or); - if (CHECK(IS_ERR(link), "attach(or)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__or__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(or)")) return; - prog_fd = bpf_program__fd(skel->progs.or); + prog_fd = skel->progs.or.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run or", @@ -123,20 +123,20 @@ static void test_or(struct atomics *skel) ASSERT_EQ(skel->data->or_noreturn_value, 0x111ull << 32, "or_noreturn_value"); cleanup: - bpf_link__destroy(link); + close(link_fd); } static void test_xor(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.xor); - if (CHECK(IS_ERR(link), "attach(xor)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__xor__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(xor)")) return; - prog_fd = bpf_program__fd(skel->progs.xor); + prog_fd = skel->progs.xor.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run xor", @@ -151,20 +151,20 @@ static void test_xor(struct atomics *skel) ASSERT_EQ(skel->data->xor_noreturn_value, 0x101ull << 32, "xor_nxoreturn_value"); cleanup: - bpf_link__destroy(link); + close(link_fd); } static void test_cmpxchg(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.cmpxchg); - if (CHECK(IS_ERR(link), "attach(cmpxchg)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__cmpxchg__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(cmpxchg)")) return; - prog_fd = bpf_program__fd(skel->progs.cmpxchg); + prog_fd = skel->progs.cmpxchg.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run add", @@ -180,20 +180,20 @@ static void test_cmpxchg(struct atomics *skel) ASSERT_EQ(skel->bss->cmpxchg32_result_succeed, 1, "cmpxchg_result_succeed"); cleanup: - bpf_link__destroy(link); + close(link_fd); } static void test_xchg(struct atomics *skel) { int err, prog_fd; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; - link = bpf_program__attach(skel->progs.xchg); - if (CHECK(IS_ERR(link), "attach(xchg)", "err: %ld\n", PTR_ERR(link))) + link_fd = atomics__xchg__attach(skel); + if (!ASSERT_GT(link_fd, 0, "attach(xchg)")) return; - prog_fd = bpf_program__fd(skel->progs.xchg); + prog_fd = skel->progs.xchg.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); if (CHECK(err || retval, "test_run add", @@ -207,7 +207,7 @@ static void test_xchg(struct atomics *skel) ASSERT_EQ(skel->bss->xchg32_result, 1, "xchg32_result"); cleanup: - bpf_link__destroy(link); + close(link_fd); } void test_atomics(void) diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index 9dc4e3dfbcf3..ec11e20d2b92 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -85,16 +85,14 @@ void test_attach_probe(void) kprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kprobe, false /* retprobe */, SYS_NANOSLEEP_KPROBE_NAME); - if (CHECK(IS_ERR(kprobe_link), "attach_kprobe", - "err %ld\n", PTR_ERR(kprobe_link))) + if (!ASSERT_OK_PTR(kprobe_link, "attach_kprobe")) goto cleanup; skel->links.handle_kprobe = kprobe_link; kretprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kretprobe, true /* retprobe */, SYS_NANOSLEEP_KPROBE_NAME); - if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe", - "err %ld\n", PTR_ERR(kretprobe_link))) + if (!ASSERT_OK_PTR(kretprobe_link, "attach_kretprobe")) goto cleanup; skel->links.handle_kretprobe = kretprobe_link; @@ -103,8 +101,7 @@ void test_attach_probe(void) 0 /* self pid */, "/proc/self/exe", uprobe_offset); - if (CHECK(IS_ERR(uprobe_link), "attach_uprobe", - "err %ld\n", PTR_ERR(uprobe_link))) + if (!ASSERT_OK_PTR(uprobe_link, "attach_uprobe")) goto cleanup; skel->links.handle_uprobe = uprobe_link; @@ -113,8 +110,7 @@ void test_attach_probe(void) -1 /* any pid */, "/proc/self/exe", uprobe_offset); - if (CHECK(IS_ERR(uretprobe_link), "attach_uretprobe", - "err %ld\n", PTR_ERR(uretprobe_link))) + if (!ASSERT_OK_PTR(uretprobe_link, "attach_uretprobe")) goto cleanup; skel->links.handle_uretprobe = uretprobe_link; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 2d3590cfb5e1..1f1aade56504 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -47,7 +47,7 @@ static void do_dummy_read(struct bpf_program *prog) int iter_fd, len; link = bpf_program__attach_iter(prog, NULL); - if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + if (!ASSERT_OK_PTR(link, "attach_iter")) return; iter_fd = bpf_iter_create(bpf_link__fd(link)); @@ -201,7 +201,7 @@ static int do_btf_read(struct bpf_iter_task_btf *skel) int ret = 0; link = bpf_program__attach_iter(prog, NULL); - if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + if (!ASSERT_OK_PTR(link, "attach_iter")) return ret; iter_fd = bpf_iter_create(bpf_link__fd(link)); @@ -396,7 +396,7 @@ static void test_file_iter(void) return; link = bpf_program__attach_iter(skel1->progs.dump_task, NULL); - if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + if (!ASSERT_OK_PTR(link, "attach_iter")) goto out; /* unlink this path if it exists. */ @@ -502,7 +502,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) skel->bss->map2_id = map_info.id; link = bpf_program__attach_iter(skel->progs.dump_bpf_map, NULL); - if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + if (!ASSERT_OK_PTR(link, "attach_iter")) goto free_map2; iter_fd = bpf_iter_create(bpf_link__fd(link)); @@ -607,14 +607,12 @@ static void test_bpf_hash_map(void) opts.link_info = &linfo; opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); - if (CHECK(!IS_ERR(link), "attach_iter", - "attach_iter for hashmap2 unexpected succeeded\n")) + if (!ASSERT_ERR_PTR(link, "attach_iter")) goto out; linfo.map.map_fd = bpf_map__fd(skel->maps.hashmap3); link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); - if (CHECK(!IS_ERR(link), "attach_iter", - "attach_iter for hashmap3 unexpected succeeded\n")) + if (!ASSERT_ERR_PTR(link, "attach_iter")) goto out; /* hashmap1 should be good, update map values here */ @@ -636,7 +634,7 @@ static void test_bpf_hash_map(void) linfo.map.map_fd = map_fd; link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); - if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + if (!ASSERT_OK_PTR(link, "attach_iter")) goto out; iter_fd = bpf_iter_create(bpf_link__fd(link)); @@ -727,7 +725,7 @@ static void test_bpf_percpu_hash_map(void) opts.link_info = &linfo; opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_hash_map, &opts); - if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + if (!ASSERT_OK_PTR(link, "attach_iter")) goto out; iter_fd = bpf_iter_create(bpf_link__fd(link)); @@ -798,7 +796,7 @@ static void test_bpf_array_map(void) opts.link_info = &linfo; opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.dump_bpf_array_map, &opts); - if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + if (!ASSERT_OK_PTR(link, "attach_iter")) goto out; iter_fd = bpf_iter_create(bpf_link__fd(link)); @@ -894,7 +892,7 @@ static void test_bpf_percpu_array_map(void) opts.link_info = &linfo; opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_array_map, &opts); - if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + if (!ASSERT_OK_PTR(link, "attach_iter")) goto out; iter_fd = bpf_iter_create(bpf_link__fd(link)); @@ -957,7 +955,7 @@ static void test_bpf_sk_storage_delete(void) opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.delete_bpf_sk_storage_map, &opts); - if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + if (!ASSERT_OK_PTR(link, "attach_iter")) goto out; iter_fd = bpf_iter_create(bpf_link__fd(link)); @@ -1075,7 +1073,7 @@ static void test_bpf_sk_storage_map(void) opts.link_info = &linfo; opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.dump_bpf_sk_storage_map, &opts); - if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + if (!ASSERT_OK_PTR(link, "attach_iter")) goto out; iter_fd = bpf_iter_create(bpf_link__fd(link)); @@ -1128,7 +1126,7 @@ static void test_rdonly_buf_out_of_bound(void) opts.link_info = &linfo; opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts); - if (CHECK(!IS_ERR(link), "attach_iter", "unexpected success\n")) + if (!ASSERT_ERR_PTR(link, "attach_iter")) bpf_link__destroy(link); bpf_iter_test_kern5__destroy(skel); @@ -1186,8 +1184,7 @@ static void test_task_vma(void) skel->links.proc_maps = bpf_program__attach_iter( skel->progs.proc_maps, NULL); - if (CHECK(IS_ERR(skel->links.proc_maps), "bpf_program__attach_iter", - "attach iterator failed\n")) { + if (!ASSERT_OK_PTR(skel->links.proc_maps, "bpf_program__attach_iter")) { skel->links.proc_maps = NULL; goto out; } diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index e25917f04602..efe1e979affb 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -82,7 +82,7 @@ static void *server(void *arg) bytes, total_bytes, nr_sent, errno); done: - if (fd != -1) + if (fd >= 0) close(fd); if (err) { WRITE_ONCE(stop, 1); @@ -191,8 +191,7 @@ static void test_cubic(void) return; link = bpf_map__attach_struct_ops(cubic_skel->maps.cubic); - if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n", - PTR_ERR(link))) { + if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops")) { bpf_cubic__destroy(cubic_skel); return; } @@ -213,8 +212,7 @@ static void test_dctcp(void) return; link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp); - if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n", - PTR_ERR(link))) { + if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops")) { bpf_dctcp__destroy(dctcp_skel); return; } diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 0457ae32b270..857e3f26086f 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -3811,7 +3811,7 @@ static void do_test_raw(unsigned int test_num) always_log); free(raw_btf); - err = ((btf_fd == -1) != test->btf_load_err); + err = ((btf_fd < 0) != test->btf_load_err); if (CHECK(err, "btf_fd:%d test->btf_load_err:%u", btf_fd, test->btf_load_err) || CHECK(test->err_str && !strstr(btf_log_buf, test->err_str), @@ -3820,7 +3820,7 @@ static void do_test_raw(unsigned int test_num) goto done; } - if (err || btf_fd == -1) + if (err || btf_fd < 0) goto done; create_attr.name = test->map_name; @@ -3834,16 +3834,16 @@ static void do_test_raw(unsigned int test_num) map_fd = bpf_create_map_xattr(&create_attr); - err = ((map_fd == -1) != test->map_create_err); + err = ((map_fd < 0) != test->map_create_err); CHECK(err, "map_fd:%d test->map_create_err:%u", map_fd, test->map_create_err); done: if (*btf_log_buf && (err || always_log)) fprintf(stderr, "\n%s", btf_log_buf); - if (btf_fd != -1) + if (btf_fd >= 0) close(btf_fd); - if (map_fd != -1) + if (map_fd >= 0) close(map_fd); } @@ -3941,7 +3941,7 @@ static int test_big_btf_info(unsigned int test_num) btf_fd = bpf_load_btf(raw_btf, raw_btf_size, btf_log_buf, BTF_LOG_BUF_SIZE, always_log); - if (CHECK(btf_fd == -1, "errno:%d", errno)) { + if (CHECK(btf_fd < 0, "errno:%d", errno)) { err = -1; goto done; } @@ -3987,7 +3987,7 @@ done: free(raw_btf); free(user_btf); - if (btf_fd != -1) + if (btf_fd >= 0) close(btf_fd); return err; @@ -4029,7 +4029,7 @@ static int test_btf_id(unsigned int test_num) btf_fd[0] = bpf_load_btf(raw_btf, raw_btf_size, btf_log_buf, BTF_LOG_BUF_SIZE, always_log); - if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) { + if (CHECK(btf_fd[0] < 0, "errno:%d", errno)) { err = -1; goto done; } @@ -4043,7 +4043,7 @@ static int test_btf_id(unsigned int test_num) } btf_fd[1] = bpf_btf_get_fd_by_id(info[0].id); - if (CHECK(btf_fd[1] == -1, "errno:%d", errno)) { + if (CHECK(btf_fd[1] < 0, "errno:%d", errno)) { err = -1; goto done; } @@ -4071,7 +4071,7 @@ static int test_btf_id(unsigned int test_num) create_attr.btf_value_type_id = 2; map_fd = bpf_create_map_xattr(&create_attr); - if (CHECK(map_fd == -1, "errno:%d", errno)) { + if (CHECK(map_fd < 0, "errno:%d", errno)) { err = -1; goto done; } @@ -4094,7 +4094,7 @@ static int test_btf_id(unsigned int test_num) /* Test BTF ID is removed from the kernel */ btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id); - if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) { + if (CHECK(btf_fd[0] < 0, "errno:%d", errno)) { err = -1; goto done; } @@ -4105,7 +4105,7 @@ static int test_btf_id(unsigned int test_num) close(map_fd); map_fd = -1; btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id); - if (CHECK(btf_fd[0] != -1, "BTF lingers")) { + if (CHECK(btf_fd[0] >= 0, "BTF lingers")) { err = -1; goto done; } @@ -4117,11 +4117,11 @@ done: fprintf(stderr, "\n%s", btf_log_buf); free(raw_btf); - if (map_fd != -1) + if (map_fd >= 0) close(map_fd); for (i = 0; i < 2; i++) { free(user_btf[i]); - if (btf_fd[i] != -1) + if (btf_fd[i] >= 0) close(btf_fd[i]); } @@ -4166,7 +4166,7 @@ static void do_test_get_info(unsigned int test_num) btf_fd = bpf_load_btf(raw_btf, raw_btf_size, btf_log_buf, BTF_LOG_BUF_SIZE, always_log); - if (CHECK(btf_fd == -1, "errno:%d", errno)) { + if (CHECK(btf_fd <= 0, "errno:%d", errno)) { err = -1; goto done; } @@ -4212,7 +4212,7 @@ done: free(raw_btf); free(user_btf); - if (btf_fd != -1) + if (btf_fd >= 0) close(btf_fd); } @@ -4249,8 +4249,9 @@ static void do_test_file(unsigned int test_num) return; btf = btf__parse_elf(test->file, &btf_ext); - if (IS_ERR(btf)) { - if (PTR_ERR(btf) == -ENOENT) { + err = libbpf_get_error(btf); + if (err) { + if (err == -ENOENT) { printf("%s:SKIP: No ELF %s found", __func__, BTF_ELF_SEC); test__skip(); return; @@ -4263,7 +4264,8 @@ static void do_test_file(unsigned int test_num) btf_ext__free(btf_ext); obj = bpf_object__open(test->file); - if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj))) + err = libbpf_get_error(obj); + if (CHECK(err, "obj: %d", err)) return; prog = bpf_program__next(NULL, obj); @@ -4298,7 +4300,7 @@ static void do_test_file(unsigned int test_num) info_len = sizeof(struct bpf_prog_info); err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); - if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) { + if (CHECK(err < 0, "invalid get info (1st) errno:%d", errno)) { fprintf(stderr, "%s\n", btf_log_buf); err = -1; goto done; @@ -4330,7 +4332,7 @@ static void do_test_file(unsigned int test_num) err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); - if (CHECK(err == -1, "invalid get info (2nd) errno:%d", errno)) { + if (CHECK(err < 0, "invalid get info (2nd) errno:%d", errno)) { fprintf(stderr, "%s\n", btf_log_buf); err = -1; goto done; @@ -4886,7 +4888,7 @@ static void do_test_pprint(int test_num) always_log); free(raw_btf); - if (CHECK(btf_fd == -1, "errno:%d", errno)) { + if (CHECK(btf_fd < 0, "errno:%d", errno)) { err = -1; goto done; } @@ -4901,7 +4903,7 @@ static void do_test_pprint(int test_num) create_attr.btf_value_type_id = test->value_type_id; map_fd = bpf_create_map_xattr(&create_attr); - if (CHECK(map_fd == -1, "errno:%d", errno)) { + if (CHECK(map_fd < 0, "errno:%d", errno)) { err = -1; goto done; } @@ -4982,7 +4984,7 @@ static void do_test_pprint(int test_num) err = check_line(expected_line, nexpected_line, sizeof(expected_line), line); - if (err == -1) + if (err < 0) goto done; } @@ -4998,7 +5000,7 @@ static void do_test_pprint(int test_num) cpu, cmapv); err = check_line(expected_line, nexpected_line, sizeof(expected_line), line); - if (err == -1) + if (err < 0) goto done; cmapv = cmapv + rounded_value_size; @@ -5036,9 +5038,9 @@ done: fprintf(stderr, "OK"); if (*btf_log_buf && (err || always_log)) fprintf(stderr, "\n%s", btf_log_buf); - if (btf_fd != -1) + if (btf_fd >= 0) close(btf_fd); - if (map_fd != -1) + if (map_fd >= 0) close(map_fd); if (pin_file) fclose(pin_file); @@ -5950,7 +5952,7 @@ static int test_get_finfo(const struct prog_info_raw_test *test, /* get necessary lens */ info_len = sizeof(struct bpf_prog_info); err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); - if (CHECK(err == -1, "invalid get info (1st) errno:%d", errno)) { + if (CHECK(err < 0, "invalid get info (1st) errno:%d", errno)) { fprintf(stderr, "%s\n", btf_log_buf); return -1; } @@ -5980,7 +5982,7 @@ static int test_get_finfo(const struct prog_info_raw_test *test, info.func_info_rec_size = rec_size; info.func_info = ptr_to_u64(func_info); err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); - if (CHECK(err == -1, "invalid get info (2nd) errno:%d", errno)) { + if (CHECK(err < 0, "invalid get info (2nd) errno:%d", errno)) { fprintf(stderr, "%s\n", btf_log_buf); err = -1; goto done; @@ -6044,7 +6046,7 @@ static int test_get_linfo(const struct prog_info_raw_test *test, info_len = sizeof(struct bpf_prog_info); err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); - if (CHECK(err == -1, "err:%d errno:%d", err, errno)) { + if (CHECK(err < 0, "err:%d errno:%d", err, errno)) { err = -1; goto done; } @@ -6123,7 +6125,7 @@ static int test_get_linfo(const struct prog_info_raw_test *test, * Only recheck the info.*line_info* fields. * Other fields are not the concern of this test. */ - if (CHECK(err == -1 || + if (CHECK(err < 0 || info.nr_line_info != cnt || (jited_cnt && !info.jited_line_info) || info.nr_jited_line_info != jited_cnt || @@ -6260,7 +6262,7 @@ static void do_test_info_raw(unsigned int test_num) always_log); free(raw_btf); - if (CHECK(btf_fd == -1, "invalid btf_fd errno:%d", errno)) { + if (CHECK(btf_fd < 0, "invalid btf_fd errno:%d", errno)) { err = -1; goto done; } @@ -6273,7 +6275,8 @@ static void do_test_info_raw(unsigned int test_num) patched_linfo = patch_name_tbd(test->line_info, test->str_sec, linfo_str_off, test->str_sec_size, &linfo_size); - if (IS_ERR(patched_linfo)) { + err = libbpf_get_error(patched_linfo); + if (err) { fprintf(stderr, "error in creating raw bpf_line_info"); err = -1; goto done; @@ -6297,7 +6300,7 @@ static void do_test_info_raw(unsigned int test_num) } prog_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); - err = ((prog_fd == -1) != test->expected_prog_load_failure); + err = ((prog_fd < 0) != test->expected_prog_load_failure); if (CHECK(err, "prog_fd:%d expected_prog_load_failure:%u errno:%d", prog_fd, test->expected_prog_load_failure, errno) || CHECK(test->err_str && !strstr(btf_log_buf, test->err_str), @@ -6306,7 +6309,7 @@ static void do_test_info_raw(unsigned int test_num) goto done; } - if (prog_fd == -1) + if (prog_fd < 0) goto done; err = test_get_finfo(test, prog_fd); @@ -6323,12 +6326,12 @@ done: if (*btf_log_buf && (err || always_log)) fprintf(stderr, "\n%s", btf_log_buf); - if (btf_fd != -1) + if (btf_fd >= 0) close(btf_fd); - if (prog_fd != -1) + if (prog_fd >= 0) close(prog_fd); - if (!IS_ERR(patched_linfo)) + if (!libbpf_get_error(patched_linfo)) free(patched_linfo); } @@ -6839,9 +6842,9 @@ static void do_test_dedup(unsigned int test_num) return; test_btf = btf__new((__u8 *)raw_btf, raw_btf_size); + err = libbpf_get_error(test_btf); free(raw_btf); - if (CHECK(IS_ERR(test_btf), "invalid test_btf errno:%ld", - PTR_ERR(test_btf))) { + if (CHECK(err, "invalid test_btf errno:%d", err)) { err = -1; goto done; } @@ -6853,9 +6856,9 @@ static void do_test_dedup(unsigned int test_num) if (!raw_btf) return; expect_btf = btf__new((__u8 *)raw_btf, raw_btf_size); + err = libbpf_get_error(expect_btf); free(raw_btf); - if (CHECK(IS_ERR(expect_btf), "invalid expect_btf errno:%ld", - PTR_ERR(expect_btf))) { + if (CHECK(err, "invalid expect_btf errno:%d", err)) { err = -1; goto done; } @@ -6966,10 +6969,8 @@ static void do_test_dedup(unsigned int test_num) } done: - if (!IS_ERR(test_btf)) - btf__free(test_btf); - if (!IS_ERR(expect_btf)) - btf__free(expect_btf); + btf__free(test_btf); + btf__free(expect_btf); } void test_btf(void) diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index 5e129dc2073c..1b90e684ff13 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -32,8 +32,9 @@ static int btf_dump_all_types(const struct btf *btf, int err = 0, id; d = btf_dump__new(btf, NULL, opts, btf_dump_printf); - if (IS_ERR(d)) - return PTR_ERR(d); + err = libbpf_get_error(d); + if (err) + return err; for (id = 1; id <= type_cnt; id++) { err = btf_dump__dump_type(d, id); @@ -56,8 +57,7 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t) snprintf(test_file, sizeof(test_file), "%s.o", t->file); btf = btf__parse_elf(test_file, NULL); - if (CHECK(IS_ERR(btf), "btf_parse_elf", - "failed to load test BTF: %ld\n", PTR_ERR(btf))) { + if (!ASSERT_OK_PTR(btf, "btf_parse_elf")) { err = -PTR_ERR(btf); btf = NULL; goto done; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c index f36da15b134f..022c7d89d6f4 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_write.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c @@ -4,8 +4,6 @@ #include #include "btf_helpers.h" -static int duration = 0; - void test_btf_write() { const struct btf_var_secinfo *vi; const struct btf_type *t; @@ -16,7 +14,7 @@ void test_btf_write() { int id, err, str_off; btf = btf__new_empty(); - if (CHECK(IS_ERR(btf), "new_empty", "failed: %ld\n", PTR_ERR(btf))) + if (!ASSERT_OK_PTR(btf, "new_empty")) return; str_off = btf__find_str(btf, "int"); diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c index 643dfa35419c..876be0ecb654 100644 --- a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c @@ -102,8 +102,7 @@ static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd) */ parent_link = bpf_program__attach_cgroup(obj->progs.egress, parent_cgroup_fd); - if (CHECK(IS_ERR(parent_link), "parent-cg-attach", - "err %ld", PTR_ERR(parent_link))) + if (!ASSERT_OK_PTR(parent_link, "parent-cg-attach")) goto close_bpf_object; err = connect_send(CHILD_CGROUP); if (CHECK(err, "first-connect-send", "errno %d", errno)) @@ -126,8 +125,7 @@ static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd) */ child_link = bpf_program__attach_cgroup(obj->progs.egress, child_cgroup_fd); - if (CHECK(IS_ERR(child_link), "child-cg-attach", - "err %ld", PTR_ERR(child_link))) + if (!ASSERT_OK_PTR(child_link, "child-cg-attach")) goto close_bpf_object; err = connect_send(CHILD_CGROUP); if (CHECK(err, "second-connect-send", "errno %d", errno)) @@ -147,10 +145,8 @@ static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd) goto close_bpf_object; close_bpf_object: - if (!IS_ERR(parent_link)) - bpf_link__destroy(parent_link); - if (!IS_ERR(child_link)) - bpf_link__destroy(child_link); + bpf_link__destroy(parent_link); + bpf_link__destroy(child_link); cg_storage_multi_egress_only__destroy(obj); } @@ -176,18 +172,15 @@ static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd) */ parent_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1, parent_cgroup_fd); - if (CHECK(IS_ERR(parent_egress1_link), "parent-egress1-cg-attach", - "err %ld", PTR_ERR(parent_egress1_link))) + if (!ASSERT_OK_PTR(parent_egress1_link, "parent-egress1-cg-attach")) goto close_bpf_object; parent_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2, parent_cgroup_fd); - if (CHECK(IS_ERR(parent_egress2_link), "parent-egress2-cg-attach", - "err %ld", PTR_ERR(parent_egress2_link))) + if (!ASSERT_OK_PTR(parent_egress2_link, "parent-egress2-cg-attach")) goto close_bpf_object; parent_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress, parent_cgroup_fd); - if (CHECK(IS_ERR(parent_ingress_link), "parent-ingress-cg-attach", - "err %ld", PTR_ERR(parent_ingress_link))) + if (!ASSERT_OK_PTR(parent_ingress_link, "parent-ingress-cg-attach")) goto close_bpf_object; err = connect_send(CHILD_CGROUP); if (CHECK(err, "first-connect-send", "errno %d", errno)) @@ -221,18 +214,15 @@ static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd) */ child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1, child_cgroup_fd); - if (CHECK(IS_ERR(child_egress1_link), "child-egress1-cg-attach", - "err %ld", PTR_ERR(child_egress1_link))) + if (!ASSERT_OK_PTR(child_egress1_link, "child-egress1-cg-attach")) goto close_bpf_object; child_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2, child_cgroup_fd); - if (CHECK(IS_ERR(child_egress2_link), "child-egress2-cg-attach", - "err %ld", PTR_ERR(child_egress2_link))) + if (!ASSERT_OK_PTR(child_egress2_link, "child-egress2-cg-attach")) goto close_bpf_object; child_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress, child_cgroup_fd); - if (CHECK(IS_ERR(child_ingress_link), "child-ingress-cg-attach", - "err %ld", PTR_ERR(child_ingress_link))) + if (!ASSERT_OK_PTR(child_ingress_link, "child-ingress-cg-attach")) goto close_bpf_object; err = connect_send(CHILD_CGROUP); if (CHECK(err, "second-connect-send", "errno %d", errno)) @@ -264,18 +254,12 @@ static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd) goto close_bpf_object; close_bpf_object: - if (!IS_ERR(parent_egress1_link)) - bpf_link__destroy(parent_egress1_link); - if (!IS_ERR(parent_egress2_link)) - bpf_link__destroy(parent_egress2_link); - if (!IS_ERR(parent_ingress_link)) - bpf_link__destroy(parent_ingress_link); - if (!IS_ERR(child_egress1_link)) - bpf_link__destroy(child_egress1_link); - if (!IS_ERR(child_egress2_link)) - bpf_link__destroy(child_egress2_link); - if (!IS_ERR(child_ingress_link)) - bpf_link__destroy(child_ingress_link); + bpf_link__destroy(parent_egress1_link); + bpf_link__destroy(parent_egress2_link); + bpf_link__destroy(parent_ingress_link); + bpf_link__destroy(child_egress1_link); + bpf_link__destroy(child_egress2_link); + bpf_link__destroy(child_ingress_link); cg_storage_multi_isolated__destroy(obj); } @@ -301,18 +285,15 @@ static void test_shared(int parent_cgroup_fd, int child_cgroup_fd) */ parent_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1, parent_cgroup_fd); - if (CHECK(IS_ERR(parent_egress1_link), "parent-egress1-cg-attach", - "err %ld", PTR_ERR(parent_egress1_link))) + if (!ASSERT_OK_PTR(parent_egress1_link, "parent-egress1-cg-attach")) goto close_bpf_object; parent_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2, parent_cgroup_fd); - if (CHECK(IS_ERR(parent_egress2_link), "parent-egress2-cg-attach", - "err %ld", PTR_ERR(parent_egress2_link))) + if (!ASSERT_OK_PTR(parent_egress2_link, "parent-egress2-cg-attach")) goto close_bpf_object; parent_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress, parent_cgroup_fd); - if (CHECK(IS_ERR(parent_ingress_link), "parent-ingress-cg-attach", - "err %ld", PTR_ERR(parent_ingress_link))) + if (!ASSERT_OK_PTR(parent_ingress_link, "parent-ingress-cg-attach")) goto close_bpf_object; err = connect_send(CHILD_CGROUP); if (CHECK(err, "first-connect-send", "errno %d", errno)) @@ -338,18 +319,15 @@ static void test_shared(int parent_cgroup_fd, int child_cgroup_fd) */ child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1, child_cgroup_fd); - if (CHECK(IS_ERR(child_egress1_link), "child-egress1-cg-attach", - "err %ld", PTR_ERR(child_egress1_link))) + if (!ASSERT_OK_PTR(child_egress1_link, "child-egress1-cg-attach")) goto close_bpf_object; child_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2, child_cgroup_fd); - if (CHECK(IS_ERR(child_egress2_link), "child-egress2-cg-attach", - "err %ld", PTR_ERR(child_egress2_link))) + if (!ASSERT_OK_PTR(child_egress2_link, "child-egress2-cg-attach")) goto close_bpf_object; child_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress, child_cgroup_fd); - if (CHECK(IS_ERR(child_ingress_link), "child-ingress-cg-attach", - "err %ld", PTR_ERR(child_ingress_link))) + if (!ASSERT_OK_PTR(child_ingress_link, "child-ingress-cg-attach")) goto close_bpf_object; err = connect_send(CHILD_CGROUP); if (CHECK(err, "second-connect-send", "errno %d", errno)) @@ -375,18 +353,12 @@ static void test_shared(int parent_cgroup_fd, int child_cgroup_fd) goto close_bpf_object; close_bpf_object: - if (!IS_ERR(parent_egress1_link)) - bpf_link__destroy(parent_egress1_link); - if (!IS_ERR(parent_egress2_link)) - bpf_link__destroy(parent_egress2_link); - if (!IS_ERR(parent_ingress_link)) - bpf_link__destroy(parent_ingress_link); - if (!IS_ERR(child_egress1_link)) - bpf_link__destroy(child_egress1_link); - if (!IS_ERR(child_egress2_link)) - bpf_link__destroy(child_egress2_link); - if (!IS_ERR(child_ingress_link)) - bpf_link__destroy(child_ingress_link); + bpf_link__destroy(parent_egress1_link); + bpf_link__destroy(parent_egress2_link); + bpf_link__destroy(parent_ingress_link); + bpf_link__destroy(child_egress1_link); + bpf_link__destroy(child_egress2_link); + bpf_link__destroy(child_ingress_link); cg_storage_multi_shared__destroy(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c index 0a1fc9816cef..20bb8831dda6 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -167,7 +167,7 @@ void test_cgroup_attach_multi(void) prog_cnt = 2; CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE, &attach_flags, - prog_ids, &prog_cnt) != -1); + prog_ids, &prog_cnt) >= 0); CHECK_FAIL(errno != ENOSPC); CHECK_FAIL(prog_cnt != 4); /* check that prog_ids are returned even when buffer is too small */ diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c index 736796e56ed1..9091524131d6 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c @@ -65,8 +65,7 @@ void test_cgroup_link(void) for (i = 0; i < cg_nr; i++) { links[i] = bpf_program__attach_cgroup(skel->progs.egress, cgs[i].fd); - if (CHECK(IS_ERR(links[i]), "cg_attach", "i: %d, err: %ld\n", - i, PTR_ERR(links[i]))) + if (!ASSERT_OK_PTR(links[i], "cg_attach")) goto cleanup; } @@ -121,8 +120,7 @@ void test_cgroup_link(void) links[last_cg] = bpf_program__attach_cgroup(skel->progs.egress, cgs[last_cg].fd); - if (CHECK(IS_ERR(links[last_cg]), "cg_attach", "err: %ld\n", - PTR_ERR(links[last_cg]))) + if (!ASSERT_OK_PTR(links[last_cg], "cg_attach")) goto cleanup; ping_and_check(cg_nr + 1, 0); @@ -147,7 +145,7 @@ void test_cgroup_link(void) /* attempt to mix in with multi-attach bpf_link */ tmp_link = bpf_program__attach_cgroup(skel->progs.egress, cgs[last_cg].fd); - if (CHECK(!IS_ERR(tmp_link), "cg_attach_fail", "unexpected success!\n")) { + if (!ASSERT_ERR_PTR(tmp_link, "cg_attach_fail")) { bpf_link__destroy(tmp_link); goto cleanup; } @@ -165,8 +163,7 @@ void test_cgroup_link(void) /* attach back link-based one */ links[last_cg] = bpf_program__attach_cgroup(skel->progs.egress, cgs[last_cg].fd); - if (CHECK(IS_ERR(links[last_cg]), "cg_attach", "err: %ld\n", - PTR_ERR(links[last_cg]))) + if (!ASSERT_OK_PTR(links[last_cg], "cg_attach")) goto cleanup; ping_and_check(cg_nr, 0); @@ -249,8 +246,7 @@ cleanup: BPF_CGROUP_INET_EGRESS); for (i = 0; i < cg_nr; i++) { - if (!IS_ERR(links[i])) - bpf_link__destroy(links[i]); + bpf_link__destroy(links[i]); } test_cgroup_link__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c index 464edc1c1708..b9dc4ec655b5 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_sk_lookup.c @@ -60,7 +60,7 @@ static void run_cgroup_bpf_test(const char *cg_path, int out_sk) goto cleanup; link = bpf_program__attach_cgroup(skel->progs.ingress_lookup, cgfd); - if (CHECK(IS_ERR(link), "cgroup_attach", "err: %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "cgroup_attach")) goto cleanup; run_lookup_test(&skel->bss->g_serv_port, out_sk); diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c index b62a39315336..012068f33a0a 100644 --- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c +++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c @@ -53,7 +53,7 @@ static void test_check_mtu_xdp_attach(void) prog = skel->progs.xdp_use_helper_basic; link = bpf_program__attach_xdp(prog, IFINDEX_LO); - if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "link_attach")) goto out; skel->links.xdp_use_helper_basic = link; diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 607710826dca..d02e064c535f 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -369,8 +369,7 @@ static int setup_type_id_case_local(struct core_reloc_test_case *test) const char *name; int i; - if (CHECK(IS_ERR(local_btf), "local_btf", "failed: %ld\n", PTR_ERR(local_btf)) || - CHECK(IS_ERR(targ_btf), "targ_btf", "failed: %ld\n", PTR_ERR(targ_btf))) { + if (!ASSERT_OK_PTR(local_btf, "local_btf") || !ASSERT_OK_PTR(targ_btf, "targ_btf")) { btf__free(local_btf); btf__free(targ_btf); return -EINVAL; @@ -848,8 +847,7 @@ void test_core_reloc(void) } obj = bpf_object__open_file(test_case->bpf_obj_file, NULL); - if (CHECK(IS_ERR(obj), "obj_open", "failed to open '%s': %ld\n", - test_case->bpf_obj_file, PTR_ERR(obj))) + if (!ASSERT_OK_PTR(obj, "obj_open")) continue; probe_name = "raw_tracepoint/sys_enter"; @@ -899,8 +897,7 @@ void test_core_reloc(void) data->my_pid_tgid = my_pid_tgid; link = bpf_program__attach_raw_tracepoint(prog, tp_name); - if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", - PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_raw_tp")) goto cleanup; /* trigger test run */ @@ -941,10 +938,8 @@ cleanup: CHECK_FAIL(munmap(mmap_data, mmap_sz)); mmap_data = NULL; } - if (!IS_ERR_OR_NULL(link)) { - bpf_link__destroy(link); - link = NULL; - } + bpf_link__destroy(link); + link = NULL; bpf_object__close(obj); } } diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c index 109d0345a2be..91154c2ba256 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include -#include "fentry_test.skel.h" -#include "fexit_test.skel.h" +#include "fentry_test.lskel.h" +#include "fexit_test.lskel.h" void test_fentry_fexit(void) { @@ -26,7 +26,7 @@ void test_fentry_fexit(void) if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) goto close_prog; - prog_fd = bpf_program__fd(fexit_skel->progs.test1); + prog_fd = fexit_skel->progs.test1.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); CHECK(err || retval, "ipv6", diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c index 7cb111b11995..174c89e7456e 100644 --- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c @@ -1,13 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include -#include "fentry_test.skel.h" +#include "fentry_test.lskel.h" static int fentry_test(struct fentry_test *fentry_skel) { int err, prog_fd, i; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; __u64 *result; err = fentry_test__attach(fentry_skel); @@ -15,11 +15,11 @@ static int fentry_test(struct fentry_test *fentry_skel) return err; /* Check that already linked program can't be attached again. */ - link = bpf_program__attach(fentry_skel->progs.test1); - if (!ASSERT_ERR_PTR(link, "fentry_attach_link")) + link_fd = fentry_test__test1__attach(fentry_skel); + if (!ASSERT_LT(link_fd, 0, "fentry_attach_link")) return -1; - prog_fd = bpf_program__fd(fentry_skel->progs.test1); + prog_fd = fentry_skel->progs.test1.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); ASSERT_OK(err, "test_run"); diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index 63990842d20f..73b4c76e6b86 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -146,10 +146,8 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, close_prog: for (i = 0; i < prog_cnt; i++) - if (!IS_ERR_OR_NULL(link[i])) - bpf_link__destroy(link[i]); - if (!IS_ERR_OR_NULL(obj)) - bpf_object__close(obj); + bpf_link__destroy(link[i]); + bpf_object__close(obj); bpf_object__close(tgt_obj); free(link); free(prog); @@ -231,7 +229,7 @@ static int test_second_attach(struct bpf_object *obj) return err; link = bpf_program__attach_freplace(prog, tgt_fd, tgt_name); - if (CHECK(IS_ERR(link), "second_link", "failed to attach second link prog_fd %d tgt_fd %d\n", bpf_program__fd(prog), tgt_fd)) + if (!ASSERT_OK_PTR(link, "second_link")) goto out; err = bpf_prog_test_run(tgt_fd, 1, &pkt_v6, sizeof(pkt_v6), @@ -283,9 +281,7 @@ static void test_fmod_ret_freplace(void) opts.attach_prog_fd = pkt_fd; freplace_obj = bpf_object__open_file(freplace_name, &opts); - if (CHECK(IS_ERR_OR_NULL(freplace_obj), "freplace_obj_open", - "failed to open %s: %ld\n", freplace_name, - PTR_ERR(freplace_obj))) + if (!ASSERT_OK_PTR(freplace_obj, "freplace_obj_open")) goto out; err = bpf_object__load(freplace_obj); @@ -294,14 +290,12 @@ static void test_fmod_ret_freplace(void) prog = bpf_program__next(NULL, freplace_obj); freplace_link = bpf_program__attach_trace(prog); - if (CHECK(IS_ERR(freplace_link), "freplace_attach_trace", "failed to link\n")) + if (!ASSERT_OK_PTR(freplace_link, "freplace_attach_trace")) goto out; opts.attach_prog_fd = bpf_program__fd(prog); fmod_obj = bpf_object__open_file(fmod_ret_name, &opts); - if (CHECK(IS_ERR_OR_NULL(fmod_obj), "fmod_obj_open", - "failed to open %s: %ld\n", fmod_ret_name, - PTR_ERR(fmod_obj))) + if (!ASSERT_OK_PTR(fmod_obj, "fmod_obj_open")) goto out; err = bpf_object__load(fmod_obj); @@ -350,9 +344,7 @@ static void test_obj_load_failure_common(const char *obj_file, ); obj = bpf_object__open_file(obj_file, &opts); - if (CHECK(IS_ERR_OR_NULL(obj), "obj_open", - "failed to open %s: %ld\n", obj_file, - PTR_ERR(obj))) + if (!ASSERT_OK_PTR(obj, "obj_open")) goto close_prog; /* It should fail to load the program */ @@ -361,8 +353,7 @@ static void test_obj_load_failure_common(const char *obj_file, goto close_prog; close_prog: - if (!IS_ERR_OR_NULL(obj)) - bpf_object__close(obj); + bpf_object__close(obj); bpf_object__close(pkt_obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c index ccc7e8a34ab6..4e7f4b42ea29 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c @@ -6,7 +6,7 @@ #include #include #include -#include "fexit_sleep.skel.h" +#include "fexit_sleep.lskel.h" static int do_sleep(void *skel) { @@ -58,8 +58,8 @@ void test_fexit_sleep(void) * waiting for percpu_ref_kill to confirm). The other one * will be freed quickly. */ - close(bpf_program__fd(fexit_skel->progs.nanosleep_fentry)); - close(bpf_program__fd(fexit_skel->progs.nanosleep_fexit)); + close(fexit_skel->progs.nanosleep_fentry.prog_fd); + close(fexit_skel->progs.nanosleep_fexit.prog_fd); fexit_sleep__detach(fexit_skel); /* kill the thread to unwind sys_nanosleep stack through the trampoline */ diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c index 6792e41f7f69..af3dba726701 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c @@ -1,13 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include -#include "fexit_test.skel.h" +#include "fexit_test.lskel.h" static int fexit_test(struct fexit_test *fexit_skel) { int err, prog_fd, i; __u32 duration = 0, retval; - struct bpf_link *link; + int link_fd; __u64 *result; err = fexit_test__attach(fexit_skel); @@ -15,11 +15,11 @@ static int fexit_test(struct fexit_test *fexit_skel) return err; /* Check that already linked program can't be attached again. */ - link = bpf_program__attach(fexit_skel->progs.test1); - if (!ASSERT_ERR_PTR(link, "fexit_attach_link")) + link_fd = fexit_test__test1__attach(fexit_skel); + if (!ASSERT_LT(link_fd, 0, "fexit_attach_link")) return -1; - prog_fd = bpf_program__fd(fexit_skel->progs.test1); + prog_fd = fexit_skel->progs.test1.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); ASSERT_OK(err, "test_run"); diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index cd6dc80edf18..225714f71ac6 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -541,7 +541,7 @@ static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd) return; link = bpf_program__attach_netns(skel->progs._dissect, net_fd); - if (CHECK(IS_ERR(link), "attach_netns", "err %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_netns")) goto out_close; run_tests_skb_less(tap_fd, skel->maps.last_dissection); diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c index 172c586b6996..3931ede5c534 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c @@ -134,9 +134,9 @@ static void test_link_create_link_create(int netns, int prog1, int prog2) /* Expect failure creating link when another link exists */ errno = 0; link2 = bpf_link_create(prog2, netns, BPF_FLOW_DISSECTOR, &opts); - if (CHECK_FAIL(link2 != -1 || errno != E2BIG)) + if (CHECK_FAIL(link2 >= 0 || errno != E2BIG)) perror("bpf_prog_attach(prog2) expected E2BIG"); - if (link2 != -1) + if (link2 >= 0) close(link2); CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); @@ -159,9 +159,9 @@ static void test_prog_attach_link_create(int netns, int prog1, int prog2) /* Expect failure creating link when prog attached */ errno = 0; link = bpf_link_create(prog2, netns, BPF_FLOW_DISSECTOR, &opts); - if (CHECK_FAIL(link != -1 || errno != EEXIST)) + if (CHECK_FAIL(link >= 0 || errno != EEXIST)) perror("bpf_link_create(prog2) expected EEXIST"); - if (link != -1) + if (link >= 0) close(link); CHECK_FAIL(query_attached_prog_id(netns) != query_prog_id(prog1)); @@ -623,7 +623,7 @@ static void run_tests(int netns) } out_close: for (i = 0; i < ARRAY_SIZE(progs); i++) { - if (progs[i] != -1) + if (progs[i] >= 0) CHECK_FAIL(close(progs[i])); } } diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c index 925722217edf..522237aa4470 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c @@ -121,12 +121,12 @@ void test_get_stack_raw_tp(void) goto close_prog; link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); - if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_raw_tp")) goto close_prog; pb_opts.sample_cb = get_stack_print_output; pb = perf_buffer__new(bpf_map__fd(map), 8, &pb_opts); - if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb))) + if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto close_prog; /* trigger some syscall action */ @@ -141,9 +141,7 @@ void test_get_stack_raw_tp(void) } close_prog: - if (!IS_ERR_OR_NULL(link)) - bpf_link__destroy(link); - if (!IS_ERR_OR_NULL(pb)) - perf_buffer__free(pb); + bpf_link__destroy(link); + perf_buffer__free(pb); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c index d884b2ed5bc5..8d5a6023a1bb 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c @@ -48,8 +48,7 @@ void test_get_stackid_cannot_attach(void) skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, pmu_fd); - CHECK(!IS_ERR(skel->links.oncpu), "attach_perf_event_no_callchain", - "should have failed\n"); + ASSERT_ERR_PTR(skel->links.oncpu, "attach_perf_event_no_callchain"); close(pmu_fd); /* add PERF_SAMPLE_CALLCHAIN, attach should succeed */ @@ -65,8 +64,7 @@ void test_get_stackid_cannot_attach(void) skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, pmu_fd); - CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event_callchain", - "err: %ld\n", PTR_ERR(skel->links.oncpu)); + ASSERT_OK_PTR(skel->links.oncpu, "attach_perf_event_callchain"); close(pmu_fd); /* add exclude_callchain_kernel, attach should fail */ @@ -82,8 +80,7 @@ void test_get_stackid_cannot_attach(void) skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, pmu_fd); - CHECK(!IS_ERR(skel->links.oncpu), "attach_perf_event_exclude_callchain_kernel", - "should have failed\n"); + ASSERT_ERR_PTR(skel->links.oncpu, "attach_perf_event_exclude_callchain_kernel"); close(pmu_fd); cleanup: diff --git a/tools/testing/selftests/bpf/prog_tests/hashmap.c b/tools/testing/selftests/bpf/prog_tests/hashmap.c index 428d488830c6..4747ab18f97f 100644 --- a/tools/testing/selftests/bpf/prog_tests/hashmap.c +++ b/tools/testing/selftests/bpf/prog_tests/hashmap.c @@ -48,8 +48,7 @@ static void test_hashmap_generic(void) struct hashmap *map; map = hashmap__new(hash_fn, equal_fn, NULL); - if (CHECK(IS_ERR(map), "hashmap__new", - "failed to create map: %ld\n", PTR_ERR(map))) + if (!ASSERT_OK_PTR(map, "hashmap__new")) return; for (i = 0; i < ELEM_CNT; i++) { @@ -267,8 +266,7 @@ static void test_hashmap_multimap(void) /* force collisions */ map = hashmap__new(collision_hash_fn, equal_fn, NULL); - if (CHECK(IS_ERR(map), "hashmap__new", - "failed to create map: %ld\n", PTR_ERR(map))) + if (!ASSERT_OK_PTR(map, "hashmap__new")) return; /* set up multimap: @@ -339,8 +337,7 @@ static void test_hashmap_empty() /* force collisions */ map = hashmap__new(hash_fn, equal_fn, NULL); - if (CHECK(IS_ERR(map), "hashmap__new", - "failed to create map: %ld\n", PTR_ERR(map))) + if (!ASSERT_OK_PTR(map, "hashmap__new")) goto cleanup; if (CHECK(hashmap__size(map) != 0, "hashmap__size", diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c index d65107919998..ddfb6bf97152 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c +++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c @@ -97,15 +97,13 @@ void test_kfree_skb(void) goto close_prog; link = bpf_program__attach_raw_tracepoint(prog, NULL); - if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_raw_tp")) goto close_prog; link_fentry = bpf_program__attach_trace(fentry); - if (CHECK(IS_ERR(link_fentry), "attach fentry", "err %ld\n", - PTR_ERR(link_fentry))) + if (!ASSERT_OK_PTR(link_fentry, "attach fentry")) goto close_prog; link_fexit = bpf_program__attach_trace(fexit); - if (CHECK(IS_ERR(link_fexit), "attach fexit", "err %ld\n", - PTR_ERR(link_fexit))) + if (!ASSERT_OK_PTR(link_fexit, "attach fexit")) goto close_prog; perf_buf_map = bpf_object__find_map_by_name(obj2, "perf_buf_map"); @@ -116,7 +114,7 @@ void test_kfree_skb(void) pb_opts.sample_cb = on_sample; pb_opts.ctx = &passed; pb = perf_buffer__new(bpf_map__fd(perf_buf_map), 1, &pb_opts); - if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb))) + if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto close_prog; memcpy(skb.cb, &cb, sizeof(cb)); @@ -144,12 +142,9 @@ void test_kfree_skb(void) CHECK_FAIL(!test_ok[0] || !test_ok[1]); close_prog: perf_buffer__free(pb); - if (!IS_ERR_OR_NULL(link)) - bpf_link__destroy(link); - if (!IS_ERR_OR_NULL(link_fentry)) - bpf_link__destroy(link_fentry); - if (!IS_ERR_OR_NULL(link_fexit)) - bpf_link__destroy(link_fexit); + bpf_link__destroy(link); + bpf_link__destroy(link_fentry); + bpf_link__destroy(link_fexit); bpf_object__close(obj); bpf_object__close(obj2); } diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 7fc0951ee75f..30a7b9b837bf 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -2,7 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include #include -#include "kfunc_call_test.skel.h" +#include "kfunc_call_test.lskel.h" #include "kfunc_call_test_subprog.skel.h" static void test_main(void) @@ -14,13 +14,13 @@ static void test_main(void) if (!ASSERT_OK_PTR(skel, "skel")) return; - prog_fd = bpf_program__fd(skel->progs.kfunc_call_test1); + prog_fd = skel->progs.kfunc_call_test1.prog_fd; err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL); ASSERT_OK(err, "bpf_prog_test_run(test1)"); ASSERT_EQ(retval, 12, "test1-retval"); - prog_fd = bpf_program__fd(skel->progs.kfunc_call_test2); + prog_fd = skel->progs.kfunc_call_test2.prog_fd; err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL); ASSERT_OK(err, "bpf_prog_test_run(test2)"); diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c index b58b775d19f3..67bebd324147 100644 --- a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c +++ b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c @@ -87,8 +87,7 @@ void test_ksyms_btf(void) struct btf *btf; btf = libbpf_find_kernel_btf(); - if (CHECK(IS_ERR(btf), "btf_exists", "failed to load kernel BTF: %ld\n", - PTR_ERR(btf))) + if (!ASSERT_OK_PTR(btf, "btf_exists")) return; percpu_datasec = btf__find_by_name_kind(btf, ".data..percpu", diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c index 4c232b456479..2cd5cded543f 100644 --- a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c +++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c @@ -4,7 +4,7 @@ #include #include #include -#include "test_ksyms_module.skel.h" +#include "test_ksyms_module.lskel.h" static int duration; diff --git a/tools/testing/selftests/bpf/prog_tests/link_pinning.c b/tools/testing/selftests/bpf/prog_tests/link_pinning.c index a743288cf384..6fc97c45f71e 100644 --- a/tools/testing/selftests/bpf/prog_tests/link_pinning.c +++ b/tools/testing/selftests/bpf/prog_tests/link_pinning.c @@ -17,7 +17,7 @@ void test_link_pinning_subtest(struct bpf_program *prog, int err, i; link = bpf_program__attach(prog); - if (CHECK(IS_ERR(link), "link_attach", "err: %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "link_attach")) goto cleanup; bss->in = 1; @@ -51,7 +51,7 @@ void test_link_pinning_subtest(struct bpf_program *prog, /* re-open link from BPFFS */ link = bpf_link__open(link_pin_path); - if (CHECK(IS_ERR(link), "link_open", "err: %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "link_open")) goto cleanup; CHECK(strcmp(link_pin_path, bpf_link__pin_path(link)), "pin_path2", @@ -84,8 +84,7 @@ void test_link_pinning_subtest(struct bpf_program *prog, CHECK(i == 10000, "link_attached", "got to iteration #%d\n", i); cleanup: - if (!IS_ERR(link)) - bpf_link__destroy(link); + bpf_link__destroy(link); } void test_link_pinning(void) diff --git a/tools/testing/selftests/bpf/prog_tests/lookup_and_delete.c b/tools/testing/selftests/bpf/prog_tests/lookup_and_delete.c new file mode 100644 index 000000000000..beebfa9730e1 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/lookup_and_delete.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include "test_lookup_and_delete.skel.h" + +#define START_VALUE 1234 +#define NEW_VALUE 4321 +#define MAX_ENTRIES 2 + +static int duration; +static int nr_cpus; + +static int fill_values(int map_fd) +{ + __u64 key, value = START_VALUE; + int err; + + for (key = 1; key < MAX_ENTRIES + 1; key++) { + err = bpf_map_update_elem(map_fd, &key, &value, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + return -1; + } + + return 0; +} + +static int fill_values_percpu(int map_fd) +{ + __u64 key, value[nr_cpus]; + int i, err; + + for (i = 0; i < nr_cpus; i++) + value[i] = START_VALUE; + + for (key = 1; key < MAX_ENTRIES + 1; key++) { + err = bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + return -1; + } + + return 0; +} + +static struct test_lookup_and_delete *setup_prog(enum bpf_map_type map_type, + int *map_fd) +{ + struct test_lookup_and_delete *skel; + int err; + + skel = test_lookup_and_delete__open(); + if (!ASSERT_OK_PTR(skel, "test_lookup_and_delete__open")) + return NULL; + + err = bpf_map__set_type(skel->maps.hash_map, map_type); + if (!ASSERT_OK(err, "bpf_map__set_type")) + goto cleanup; + + err = bpf_map__set_max_entries(skel->maps.hash_map, MAX_ENTRIES); + if (!ASSERT_OK(err, "bpf_map__set_max_entries")) + goto cleanup; + + err = test_lookup_and_delete__load(skel); + if (!ASSERT_OK(err, "test_lookup_and_delete__load")) + goto cleanup; + + *map_fd = bpf_map__fd(skel->maps.hash_map); + if (!ASSERT_GE(*map_fd, 0, "bpf_map__fd")) + goto cleanup; + + return skel; + +cleanup: + test_lookup_and_delete__destroy(skel); + return NULL; +} + +/* Triggers BPF program that updates map with given key and value */ +static int trigger_tp(struct test_lookup_and_delete *skel, __u64 key, + __u64 value) +{ + int err; + + skel->bss->set_pid = getpid(); + skel->bss->set_key = key; + skel->bss->set_value = value; + + err = test_lookup_and_delete__attach(skel); + if (!ASSERT_OK(err, "test_lookup_and_delete__attach")) + return -1; + + syscall(__NR_getpgid); + + test_lookup_and_delete__detach(skel); + + return 0; +} + +static void test_lookup_and_delete_hash(void) +{ + struct test_lookup_and_delete *skel; + __u64 key, value; + int map_fd, err; + + /* Setup program and fill the map. */ + skel = setup_prog(BPF_MAP_TYPE_HASH, &map_fd); + if (!ASSERT_OK_PTR(skel, "setup_prog")) + return; + + err = fill_values(map_fd); + if (!ASSERT_OK(err, "fill_values")) + goto cleanup; + + /* Lookup and delete element. */ + key = 1; + err = bpf_map_lookup_and_delete_elem(map_fd, &key, &value); + if (!ASSERT_OK(err, "bpf_map_lookup_and_delete_elem")) + goto cleanup; + + /* Fetched value should match the initially set value. */ + if (CHECK(value != START_VALUE, "bpf_map_lookup_and_delete_elem", + "unexpected value=%lld\n", value)) + goto cleanup; + + /* Check that the entry is non existent. */ + err = bpf_map_lookup_elem(map_fd, &key, &value); + if (!ASSERT_ERR(err, "bpf_map_lookup_elem")) + goto cleanup; + +cleanup: + test_lookup_and_delete__destroy(skel); +} + +static void test_lookup_and_delete_percpu_hash(void) +{ + struct test_lookup_and_delete *skel; + __u64 key, val, value[nr_cpus]; + int map_fd, err, i; + + /* Setup program and fill the map. */ + skel = setup_prog(BPF_MAP_TYPE_PERCPU_HASH, &map_fd); + if (!ASSERT_OK_PTR(skel, "setup_prog")) + return; + + err = fill_values_percpu(map_fd); + if (!ASSERT_OK(err, "fill_values_percpu")) + goto cleanup; + + /* Lookup and delete element. */ + key = 1; + err = bpf_map_lookup_and_delete_elem(map_fd, &key, value); + if (!ASSERT_OK(err, "bpf_map_lookup_and_delete_elem")) + goto cleanup; + + for (i = 0; i < nr_cpus; i++) { + val = value[i]; + + /* Fetched value should match the initially set value. */ + if (CHECK(val != START_VALUE, "map value", + "unexpected for cpu %d: %lld\n", i, val)) + goto cleanup; + } + + /* Check that the entry is non existent. */ + err = bpf_map_lookup_elem(map_fd, &key, value); + if (!ASSERT_ERR(err, "bpf_map_lookup_elem")) + goto cleanup; + +cleanup: + test_lookup_and_delete__destroy(skel); +} + +static void test_lookup_and_delete_lru_hash(void) +{ + struct test_lookup_and_delete *skel; + __u64 key, value; + int map_fd, err; + + /* Setup program and fill the LRU map. */ + skel = setup_prog(BPF_MAP_TYPE_LRU_HASH, &map_fd); + if (!ASSERT_OK_PTR(skel, "setup_prog")) + return; + + err = fill_values(map_fd); + if (!ASSERT_OK(err, "fill_values")) + goto cleanup; + + /* Insert new element at key=3, should reuse LRU element. */ + key = 3; + err = trigger_tp(skel, key, NEW_VALUE); + if (!ASSERT_OK(err, "trigger_tp")) + goto cleanup; + + /* Lookup and delete element 3. */ + err = bpf_map_lookup_and_delete_elem(map_fd, &key, &value); + if (!ASSERT_OK(err, "bpf_map_lookup_and_delete_elem")) + goto cleanup; + + /* Value should match the new value. */ + if (CHECK(value != NEW_VALUE, "bpf_map_lookup_and_delete_elem", + "unexpected value=%lld\n", value)) + goto cleanup; + + /* Check that entries 3 and 1 are non existent. */ + err = bpf_map_lookup_elem(map_fd, &key, &value); + if (!ASSERT_ERR(err, "bpf_map_lookup_elem")) + goto cleanup; + + key = 1; + err = bpf_map_lookup_elem(map_fd, &key, &value); + if (!ASSERT_ERR(err, "bpf_map_lookup_elem")) + goto cleanup; + +cleanup: + test_lookup_and_delete__destroy(skel); +} + +static void test_lookup_and_delete_lru_percpu_hash(void) +{ + struct test_lookup_and_delete *skel; + __u64 key, val, value[nr_cpus]; + int map_fd, err, i, cpucnt = 0; + + /* Setup program and fill the LRU map. */ + skel = setup_prog(BPF_MAP_TYPE_LRU_PERCPU_HASH, &map_fd); + if (!ASSERT_OK_PTR(skel, "setup_prog")) + return; + + err = fill_values_percpu(map_fd); + if (!ASSERT_OK(err, "fill_values_percpu")) + goto cleanup; + + /* Insert new element at key=3, should reuse LRU element 1. */ + key = 3; + err = trigger_tp(skel, key, NEW_VALUE); + if (!ASSERT_OK(err, "trigger_tp")) + goto cleanup; + + /* Clean value. */ + for (i = 0; i < nr_cpus; i++) + value[i] = 0; + + /* Lookup and delete element 3. */ + err = bpf_map_lookup_and_delete_elem(map_fd, &key, value); + if (!ASSERT_OK(err, "bpf_map_lookup_and_delete_elem")) { + goto cleanup; + } + + /* Check if only one CPU has set the value. */ + for (i = 0; i < nr_cpus; i++) { + val = value[i]; + if (val) { + if (CHECK(val != NEW_VALUE, "map value", + "unexpected for cpu %d: %lld\n", i, val)) + goto cleanup; + cpucnt++; + } + } + if (CHECK(cpucnt != 1, "map value", "set for %d CPUs instead of 1!\n", + cpucnt)) + goto cleanup; + + /* Check that entries 3 and 1 are non existent. */ + err = bpf_map_lookup_elem(map_fd, &key, &value); + if (!ASSERT_ERR(err, "bpf_map_lookup_elem")) + goto cleanup; + + key = 1; + err = bpf_map_lookup_elem(map_fd, &key, &value); + if (!ASSERT_ERR(err, "bpf_map_lookup_elem")) + goto cleanup; + +cleanup: + test_lookup_and_delete__destroy(skel); +} + +void test_lookup_and_delete(void) +{ + nr_cpus = bpf_num_possible_cpus(); + + if (test__start_subtest("lookup_and_delete")) + test_lookup_and_delete_hash(); + if (test__start_subtest("lookup_and_delete_percpu")) + test_lookup_and_delete_percpu_hash(); + if (test__start_subtest("lookup_and_delete_lru")) + test_lookup_and_delete_lru_hash(); + if (test__start_subtest("lookup_and_delete_lru_percpu")) + test_lookup_and_delete_lru_percpu_hash(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c new file mode 100644 index 000000000000..59adb4715394 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c @@ -0,0 +1,559 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Check if we can migrate child sockets. + * + * 1. call listen() for 4 server sockets. + * 2. call connect() for 25 client sockets. + * 3. call listen() for 1 server socket. (migration target) + * 4. update a map to migrate all child sockets + * to the last server socket (migrate_map[cookie] = 4) + * 5. call shutdown() for first 4 server sockets + * and migrate the requests in the accept queue + * to the last server socket. + * 6. call listen() for the second server socket. + * 7. call shutdown() for the last server + * and migrate the requests in the accept queue + * to the second server socket. + * 8. call listen() for the last server. + * 9. call shutdown() for the second server + * and migrate the requests in the accept queue + * to the last server socket. + * 10. call accept() for the last server socket. + * + * Author: Kuniyuki Iwashima + */ + +#include +#include + +#include "test_progs.h" +#include "test_migrate_reuseport.skel.h" +#include "network_helpers.h" + +#ifndef TCP_FASTOPEN_CONNECT +#define TCP_FASTOPEN_CONNECT 30 +#endif + +#define IFINDEX_LO 1 + +#define NR_SERVERS 5 +#define NR_CLIENTS (NR_SERVERS * 5) +#define MIGRATED_TO (NR_SERVERS - 1) + +/* fastopenq->max_qlen and sk->sk_max_ack_backlog */ +#define QLEN (NR_CLIENTS * 5) + +#define MSG "Hello World\0" +#define MSGLEN 12 + +static struct migrate_reuseport_test_case { + const char *name; + __s64 servers[NR_SERVERS]; + __s64 clients[NR_CLIENTS]; + struct sockaddr_storage addr; + socklen_t addrlen; + int family; + int state; + bool drop_ack; + bool expire_synack_timer; + bool fastopen; + struct bpf_link *link; +} test_cases[] = { + { + .name = "IPv4 TCP_ESTABLISHED inet_csk_listen_stop", + .family = AF_INET, + .state = BPF_TCP_ESTABLISHED, + .drop_ack = false, + .expire_synack_timer = false, + .fastopen = false, + }, + { + .name = "IPv4 TCP_SYN_RECV inet_csk_listen_stop", + .family = AF_INET, + .state = BPF_TCP_SYN_RECV, + .drop_ack = true, + .expire_synack_timer = false, + .fastopen = true, + }, + { + .name = "IPv4 TCP_NEW_SYN_RECV reqsk_timer_handler", + .family = AF_INET, + .state = BPF_TCP_NEW_SYN_RECV, + .drop_ack = true, + .expire_synack_timer = true, + .fastopen = false, + }, + { + .name = "IPv4 TCP_NEW_SYN_RECV inet_csk_complete_hashdance", + .family = AF_INET, + .state = BPF_TCP_NEW_SYN_RECV, + .drop_ack = true, + .expire_synack_timer = false, + .fastopen = false, + }, + { + .name = "IPv6 TCP_ESTABLISHED inet_csk_listen_stop", + .family = AF_INET6, + .state = BPF_TCP_ESTABLISHED, + .drop_ack = false, + .expire_synack_timer = false, + .fastopen = false, + }, + { + .name = "IPv6 TCP_SYN_RECV inet_csk_listen_stop", + .family = AF_INET6, + .state = BPF_TCP_SYN_RECV, + .drop_ack = true, + .expire_synack_timer = false, + .fastopen = true, + }, + { + .name = "IPv6 TCP_NEW_SYN_RECV reqsk_timer_handler", + .family = AF_INET6, + .state = BPF_TCP_NEW_SYN_RECV, + .drop_ack = true, + .expire_synack_timer = true, + .fastopen = false, + }, + { + .name = "IPv6 TCP_NEW_SYN_RECV inet_csk_complete_hashdance", + .family = AF_INET6, + .state = BPF_TCP_NEW_SYN_RECV, + .drop_ack = true, + .expire_synack_timer = false, + .fastopen = false, + } +}; + +static void init_fds(__s64 fds[], int len) +{ + int i; + + for (i = 0; i < len; i++) + fds[i] = -1; +} + +static void close_fds(__s64 fds[], int len) +{ + int i; + + for (i = 0; i < len; i++) { + if (fds[i] != -1) { + close(fds[i]); + fds[i] = -1; + } + } +} + +static int setup_fastopen(char *buf, int size, int *saved_len, bool restore) +{ + int err = 0, fd, len; + + fd = open("/proc/sys/net/ipv4/tcp_fastopen", O_RDWR); + if (!ASSERT_NEQ(fd, -1, "open")) + return -1; + + if (restore) { + len = write(fd, buf, *saved_len); + if (!ASSERT_EQ(len, *saved_len, "write - restore")) + err = -1; + } else { + *saved_len = read(fd, buf, size); + if (!ASSERT_GE(*saved_len, 1, "read")) { + err = -1; + goto close; + } + + err = lseek(fd, 0, SEEK_SET); + if (!ASSERT_OK(err, "lseek")) + goto close; + + /* (TFO_CLIENT_ENABLE | TFO_SERVER_ENABLE | + * TFO_CLIENT_NO_COOKIE | TFO_SERVER_COOKIE_NOT_REQD) + */ + len = write(fd, "519", 3); + if (!ASSERT_EQ(len, 3, "write - setup")) + err = -1; + } + +close: + close(fd); + + return err; +} + +static int drop_ack(struct migrate_reuseport_test_case *test_case, + struct test_migrate_reuseport *skel) +{ + if (test_case->family == AF_INET) + skel->bss->server_port = ((struct sockaddr_in *) + &test_case->addr)->sin_port; + else + skel->bss->server_port = ((struct sockaddr_in6 *) + &test_case->addr)->sin6_port; + + test_case->link = bpf_program__attach_xdp(skel->progs.drop_ack, + IFINDEX_LO); + if (!ASSERT_OK_PTR(test_case->link, "bpf_program__attach_xdp")) + return -1; + + return 0; +} + +static int pass_ack(struct migrate_reuseport_test_case *test_case) +{ + int err; + + err = bpf_link__detach(test_case->link); + if (!ASSERT_OK(err, "bpf_link__detach")) + return -1; + + test_case->link = NULL; + + return 0; +} + +static int start_servers(struct migrate_reuseport_test_case *test_case, + struct test_migrate_reuseport *skel) +{ + int i, err, prog_fd, reuseport = 1, qlen = QLEN; + + prog_fd = bpf_program__fd(skel->progs.migrate_reuseport); + + make_sockaddr(test_case->family, + test_case->family == AF_INET ? "127.0.0.1" : "::1", 0, + &test_case->addr, &test_case->addrlen); + + for (i = 0; i < NR_SERVERS; i++) { + test_case->servers[i] = socket(test_case->family, SOCK_STREAM, + IPPROTO_TCP); + if (!ASSERT_NEQ(test_case->servers[i], -1, "socket")) + return -1; + + err = setsockopt(test_case->servers[i], SOL_SOCKET, + SO_REUSEPORT, &reuseport, sizeof(reuseport)); + if (!ASSERT_OK(err, "setsockopt - SO_REUSEPORT")) + return -1; + + err = bind(test_case->servers[i], + (struct sockaddr *)&test_case->addr, + test_case->addrlen); + if (!ASSERT_OK(err, "bind")) + return -1; + + if (i == 0) { + err = setsockopt(test_case->servers[i], SOL_SOCKET, + SO_ATTACH_REUSEPORT_EBPF, + &prog_fd, sizeof(prog_fd)); + if (!ASSERT_OK(err, + "setsockopt - SO_ATTACH_REUSEPORT_EBPF")) + return -1; + + err = getsockname(test_case->servers[i], + (struct sockaddr *)&test_case->addr, + &test_case->addrlen); + if (!ASSERT_OK(err, "getsockname")) + return -1; + } + + if (test_case->fastopen) { + err = setsockopt(test_case->servers[i], + SOL_TCP, TCP_FASTOPEN, + &qlen, sizeof(qlen)); + if (!ASSERT_OK(err, "setsockopt - TCP_FASTOPEN")) + return -1; + } + + /* All requests will be tied to the first four listeners */ + if (i != MIGRATED_TO) { + err = listen(test_case->servers[i], qlen); + if (!ASSERT_OK(err, "listen")) + return -1; + } + } + + return 0; +} + +static int start_clients(struct migrate_reuseport_test_case *test_case) +{ + char buf[MSGLEN] = MSG; + int i, err; + + for (i = 0; i < NR_CLIENTS; i++) { + test_case->clients[i] = socket(test_case->family, SOCK_STREAM, + IPPROTO_TCP); + if (!ASSERT_NEQ(test_case->clients[i], -1, "socket")) + return -1; + + /* The attached XDP program drops only the final ACK, so + * clients will transition to TCP_ESTABLISHED immediately. + */ + err = settimeo(test_case->clients[i], 100); + if (!ASSERT_OK(err, "settimeo")) + return -1; + + if (test_case->fastopen) { + int fastopen = 1; + + err = setsockopt(test_case->clients[i], IPPROTO_TCP, + TCP_FASTOPEN_CONNECT, &fastopen, + sizeof(fastopen)); + if (!ASSERT_OK(err, + "setsockopt - TCP_FASTOPEN_CONNECT")) + return -1; + } + + err = connect(test_case->clients[i], + (struct sockaddr *)&test_case->addr, + test_case->addrlen); + if (!ASSERT_OK(err, "connect")) + return -1; + + err = write(test_case->clients[i], buf, MSGLEN); + if (!ASSERT_EQ(err, MSGLEN, "write")) + return -1; + } + + return 0; +} + +static int update_maps(struct migrate_reuseport_test_case *test_case, + struct test_migrate_reuseport *skel) +{ + int i, err, migrated_to = MIGRATED_TO; + int reuseport_map_fd, migrate_map_fd; + __u64 value; + + reuseport_map_fd = bpf_map__fd(skel->maps.reuseport_map); + migrate_map_fd = bpf_map__fd(skel->maps.migrate_map); + + for (i = 0; i < NR_SERVERS; i++) { + value = (__u64)test_case->servers[i]; + err = bpf_map_update_elem(reuseport_map_fd, &i, &value, + BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem - reuseport_map")) + return -1; + + err = bpf_map_lookup_elem(reuseport_map_fd, &i, &value); + if (!ASSERT_OK(err, "bpf_map_lookup_elem - reuseport_map")) + return -1; + + err = bpf_map_update_elem(migrate_map_fd, &value, &migrated_to, + BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem - migrate_map")) + return -1; + } + + return 0; +} + +static int migrate_dance(struct migrate_reuseport_test_case *test_case) +{ + int i, err; + + /* Migrate TCP_ESTABLISHED and TCP_SYN_RECV requests + * to the last listener based on eBPF. + */ + for (i = 0; i < MIGRATED_TO; i++) { + err = shutdown(test_case->servers[i], SHUT_RDWR); + if (!ASSERT_OK(err, "shutdown")) + return -1; + } + + /* No dance for TCP_NEW_SYN_RECV to migrate based on eBPF */ + if (test_case->state == BPF_TCP_NEW_SYN_RECV) + return 0; + + /* Note that we use the second listener instead of the + * first one here. + * + * The fist listener is bind()ed with port 0 and, + * SOCK_BINDPORT_LOCK is not set to sk_userlocks, so + * calling listen() again will bind() the first listener + * on a new ephemeral port and detach it from the existing + * reuseport group. (See: __inet_bind(), tcp_set_state()) + * + * OTOH, the second one is bind()ed with a specific port, + * and SOCK_BINDPORT_LOCK is set. Thus, re-listen() will + * resurrect the listener on the existing reuseport group. + */ + err = listen(test_case->servers[1], QLEN); + if (!ASSERT_OK(err, "listen")) + return -1; + + /* Migrate from the last listener to the second one. + * + * All listeners were detached out of the reuseport_map, + * so migration will be done by kernel random pick from here. + */ + err = shutdown(test_case->servers[MIGRATED_TO], SHUT_RDWR); + if (!ASSERT_OK(err, "shutdown")) + return -1; + + /* Back to the existing reuseport group */ + err = listen(test_case->servers[MIGRATED_TO], QLEN); + if (!ASSERT_OK(err, "listen")) + return -1; + + /* Migrate back to the last one from the second one */ + err = shutdown(test_case->servers[1], SHUT_RDWR); + if (!ASSERT_OK(err, "shutdown")) + return -1; + + return 0; +} + +static void count_requests(struct migrate_reuseport_test_case *test_case, + struct test_migrate_reuseport *skel) +{ + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int err, cnt = 0, client; + char buf[MSGLEN]; + + err = settimeo(test_case->servers[MIGRATED_TO], 4000); + if (!ASSERT_OK(err, "settimeo")) + goto out; + + for (; cnt < NR_CLIENTS; cnt++) { + client = accept(test_case->servers[MIGRATED_TO], + (struct sockaddr *)&addr, &len); + if (!ASSERT_NEQ(client, -1, "accept")) + goto out; + + memset(buf, 0, MSGLEN); + read(client, &buf, MSGLEN); + close(client); + + if (!ASSERT_STREQ(buf, MSG, "read")) + goto out; + } + +out: + ASSERT_EQ(cnt, NR_CLIENTS, "count in userspace"); + + switch (test_case->state) { + case BPF_TCP_ESTABLISHED: + cnt = skel->bss->migrated_at_close; + break; + case BPF_TCP_SYN_RECV: + cnt = skel->bss->migrated_at_close_fastopen; + break; + case BPF_TCP_NEW_SYN_RECV: + if (test_case->expire_synack_timer) + cnt = skel->bss->migrated_at_send_synack; + else + cnt = skel->bss->migrated_at_recv_ack; + break; + default: + cnt = 0; + } + + ASSERT_EQ(cnt, NR_CLIENTS, "count in BPF prog"); +} + +static void run_test(struct migrate_reuseport_test_case *test_case, + struct test_migrate_reuseport *skel) +{ + int err, saved_len; + char buf[16]; + + skel->bss->migrated_at_close = 0; + skel->bss->migrated_at_close_fastopen = 0; + skel->bss->migrated_at_send_synack = 0; + skel->bss->migrated_at_recv_ack = 0; + + init_fds(test_case->servers, NR_SERVERS); + init_fds(test_case->clients, NR_CLIENTS); + + if (test_case->fastopen) { + memset(buf, 0, sizeof(buf)); + + err = setup_fastopen(buf, sizeof(buf), &saved_len, false); + if (!ASSERT_OK(err, "setup_fastopen - setup")) + return; + } + + err = start_servers(test_case, skel); + if (!ASSERT_OK(err, "start_servers")) + goto close_servers; + + if (test_case->drop_ack) { + /* Drop the final ACK of the 3-way handshake and stick the + * in-flight requests on TCP_SYN_RECV or TCP_NEW_SYN_RECV. + */ + err = drop_ack(test_case, skel); + if (!ASSERT_OK(err, "drop_ack")) + goto close_servers; + } + + /* Tie requests to the first four listners */ + err = start_clients(test_case); + if (!ASSERT_OK(err, "start_clients")) + goto close_clients; + + err = listen(test_case->servers[MIGRATED_TO], QLEN); + if (!ASSERT_OK(err, "listen")) + goto close_clients; + + err = update_maps(test_case, skel); + if (!ASSERT_OK(err, "fill_maps")) + goto close_clients; + + /* Migrate the requests in the accept queue only. + * TCP_NEW_SYN_RECV requests are not migrated at this point. + */ + err = migrate_dance(test_case); + if (!ASSERT_OK(err, "migrate_dance")) + goto close_clients; + + if (test_case->expire_synack_timer) { + /* Wait for SYN+ACK timers to expire so that + * reqsk_timer_handler() migrates TCP_NEW_SYN_RECV requests. + */ + sleep(1); + } + + if (test_case->link) { + /* Resume 3WHS and migrate TCP_NEW_SYN_RECV requests */ + err = pass_ack(test_case); + if (!ASSERT_OK(err, "pass_ack")) + goto close_clients; + } + + count_requests(test_case, skel); + +close_clients: + close_fds(test_case->clients, NR_CLIENTS); + + if (test_case->link) { + err = pass_ack(test_case); + ASSERT_OK(err, "pass_ack - clean up"); + } + +close_servers: + close_fds(test_case->servers, NR_SERVERS); + + if (test_case->fastopen) { + err = setup_fastopen(buf, sizeof(buf), &saved_len, true); + ASSERT_OK(err, "setup_fastopen - restore"); + } +} + +void test_migrate_reuseport(void) +{ + struct test_migrate_reuseport *skel; + int i; + + skel = test_migrate_reuseport__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + test__start_subtest(test_cases[i].name); + run_test(&test_cases[i], skel); + } + + test_migrate_reuseport__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/obj_name.c b/tools/testing/selftests/bpf/prog_tests/obj_name.c index e178416bddad..6194b776a28b 100644 --- a/tools/testing/selftests/bpf/prog_tests/obj_name.c +++ b/tools/testing/selftests/bpf/prog_tests/obj_name.c @@ -38,13 +38,13 @@ void test_obj_name(void) fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); CHECK((tests[i].success && fd < 0) || - (!tests[i].success && fd != -1) || + (!tests[i].success && fd >= 0) || (!tests[i].success && errno != tests[i].expected_errno), "check-bpf-prog-name", "fd %d(%d) errno %d(%d)\n", fd, tests[i].success, errno, tests[i].expected_errno); - if (fd != -1) + if (fd >= 0) close(fd); /* test different attr.map_name during BPF_MAP_CREATE */ @@ -59,13 +59,13 @@ void test_obj_name(void) memcpy(attr.map_name, tests[i].name, ncopy); fd = syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr)); CHECK((tests[i].success && fd < 0) || - (!tests[i].success && fd != -1) || + (!tests[i].success && fd >= 0) || (!tests[i].success && errno != tests[i].expected_errno), "check-bpf-map-name", "fd %d(%d) errno %d(%d)\n", fd, tests[i].success, errno, tests[i].expected_errno); - if (fd != -1) + if (fd >= 0) close(fd); } } diff --git a/tools/testing/selftests/bpf/prog_tests/perf_branches.c b/tools/testing/selftests/bpf/prog_tests/perf_branches.c index e35c444902a7..12c4f45cee1a 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_branches.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_branches.c @@ -74,7 +74,7 @@ static void test_perf_branches_common(int perf_fd, /* attach perf_event */ link = bpf_program__attach_perf_event(skel->progs.perf_branches, perf_fd); - if (CHECK(IS_ERR(link), "attach_perf_event", "err %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_perf_event")) goto out_destroy_skel; /* generate some branches on cpu 0 */ @@ -119,7 +119,7 @@ static void test_perf_branches_hw(void) * Some setups don't support branch records (virtual machines, !x86), * so skip test in this case. */ - if (pfd == -1) { + if (pfd < 0) { if (errno == ENOENT || errno == EOPNOTSUPP) { printf("%s:SKIP:no PERF_SAMPLE_BRANCH_STACK\n", __func__); diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c index ca9f0895ec84..6490e9673002 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c @@ -80,7 +80,7 @@ void test_perf_buffer(void) pb_opts.sample_cb = on_sample; pb_opts.ctx = &cpu_seen; pb = perf_buffer__new(bpf_map__fd(skel->maps.perf_buf_map), 1, &pb_opts); - if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb))) + if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto out_close; CHECK(perf_buffer__epoll_fd(pb) < 0, "epoll_fd", diff --git a/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c index 72c3690844fb..33144c9432ae 100644 --- a/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c +++ b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c @@ -97,8 +97,7 @@ void test_perf_event_stackmap(void) skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, pmu_fd); - if (CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event", - "err %ld\n", PTR_ERR(skel->links.oncpu))) { + if (!ASSERT_OK_PTR(skel->links.oncpu, "attach_perf_event")) { close(pmu_fd); goto cleanup; } diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c index 7aecfd9e87d1..95bd12097358 100644 --- a/tools/testing/selftests/bpf/prog_tests/probe_user.c +++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c @@ -15,7 +15,7 @@ void test_probe_user(void) static const int zero = 0; obj = bpf_object__open_file(obj_file, &opts); - if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) + if (!ASSERT_OK_PTR(obj, "obj_open_file")) return; kprobe_prog = bpf_object__find_program_by_title(obj, prog_name); @@ -33,11 +33,8 @@ void test_probe_user(void) goto cleanup; kprobe_link = bpf_program__attach(kprobe_prog); - if (CHECK(IS_ERR(kprobe_link), "attach_kprobe", - "err %ld\n", PTR_ERR(kprobe_link))) { - kprobe_link = NULL; + if (!ASSERT_OK_PTR(kprobe_link, "attach_kprobe")) goto cleanup; - } memset(&curr, 0, sizeof(curr)); in->sin_family = AF_INET; diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c index 131d7f7eeb42..89fc98faf19e 100644 --- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c +++ b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c @@ -46,7 +46,7 @@ void test_prog_run_xattr(void) tattr.prog_fd = bpf_program__fd(skel->progs.test_pkt_access); err = bpf_prog_test_run_xattr(&tattr); - CHECK_ATTR(err != -1 || errno != ENOSPC || tattr.retval, "run", + CHECK_ATTR(err >= 0 || errno != ENOSPC || tattr.retval, "run", "err %d errno %d retval %d\n", err, errno, tattr.retval); CHECK_ATTR(tattr.data_size_out != sizeof(pkt_v4), "data_size_out", @@ -78,6 +78,6 @@ void test_prog_run_xattr(void) cleanup: if (skel) test_pkt_access__destroy(skel); - if (stats_fd != -1) + if (stats_fd >= 0) close(stats_fd); } diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c index c5fb191874ac..41720a62c4fa 100644 --- a/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_test_run.c @@ -77,7 +77,7 @@ void test_raw_tp_test_run(void) /* invalid cpu ID should fail with ENXIO */ opts.cpu = 0xffffffff; err = bpf_prog_test_run_opts(prog_fd, &opts); - CHECK(err != -1 || errno != ENXIO, + CHECK(err >= 0 || errno != ENXIO, "test_run_opts_fail", "should failed with ENXIO\n"); @@ -85,7 +85,7 @@ void test_raw_tp_test_run(void) opts.cpu = 1; opts.flags = 0; err = bpf_prog_test_run_opts(prog_fd, &opts); - CHECK(err != -1 || errno != EINVAL, + CHECK(err >= 0 || errno != EINVAL, "test_run_opts_fail", "should failed with EINVAL\n"); diff --git a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c index 563e12120e77..5f9eaa3ab584 100644 --- a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c +++ b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c @@ -30,7 +30,7 @@ void test_rdonly_maps(void) struct bss bss; obj = bpf_object__open_file(file, NULL); - if (CHECK(IS_ERR(obj), "obj_open", "err %ld\n", PTR_ERR(obj))) + if (!ASSERT_OK_PTR(obj, "obj_open")) return; err = bpf_object__load(obj); @@ -58,11 +58,8 @@ void test_rdonly_maps(void) goto cleanup; link = bpf_program__attach_raw_tracepoint(prog, "sys_enter"); - if (CHECK(IS_ERR(link), "attach_prog", "prog '%s', err %ld\n", - t->prog_name, PTR_ERR(link))) { - link = NULL; + if (!ASSERT_OK_PTR(link, "attach_prog")) goto cleanup; - } /* trigger probe */ usleep(1); diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c index ac1ee10cffd8..de2688166696 100644 --- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c +++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c @@ -15,7 +15,7 @@ void test_reference_tracking(void) int err = 0; obj = bpf_object__open_file(file, &open_opts); - if (CHECK_FAIL(IS_ERR(obj))) + if (!ASSERT_OK_PTR(obj, "obj_open_file")) return; if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name", diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c index d3c2de2c24d1..f62361306f6d 100644 --- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c +++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c @@ -76,7 +76,7 @@ __resolve_symbol(struct btf *btf, int type_id) } for (i = 0; i < ARRAY_SIZE(test_symbols); i++) { - if (test_symbols[i].id != -1) + if (test_symbols[i].id >= 0) continue; if (BTF_INFO_KIND(type->info) != test_symbols[i].type) diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c index f9a8ae331963..4706cee84360 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c @@ -12,7 +12,7 @@ #include #include #include -#include "test_ringbuf.skel.h" +#include "test_ringbuf.lskel.h" #define EDONE 7777 @@ -94,15 +94,13 @@ void test_ringbuf(void) if (CHECK(!skel, "skel_open", "skeleton open failed\n")) return; - err = bpf_map__set_max_entries(skel->maps.ringbuf, page_size); - if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n")) - goto cleanup; + skel->maps.ringbuf.max_entries = page_size; err = test_ringbuf__load(skel); if (CHECK(err != 0, "skel_load", "skeleton load failed\n")) goto cleanup; - rb_fd = bpf_map__fd(skel->maps.ringbuf); + rb_fd = skel->maps.ringbuf.map_fd; /* good read/write cons_pos */ mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0); ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos"); @@ -151,7 +149,7 @@ void test_ringbuf(void) /* only trigger BPF program for current process */ skel->bss->pid = getpid(); - ringbuf = ring_buffer__new(bpf_map__fd(skel->maps.ringbuf), + ringbuf = ring_buffer__new(skel->maps.ringbuf.map_fd, process_sample, NULL, NULL); if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c index cef63e703924..167cd8a2edfd 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c @@ -63,7 +63,7 @@ void test_ringbuf_multi(void) goto cleanup; proto_fd = bpf_create_map(BPF_MAP_TYPE_RINGBUF, 0, 0, page_size, 0); - if (CHECK(proto_fd == -1, "bpf_create_map", "bpf_create_map failed\n")) + if (CHECK(proto_fd < 0, "bpf_create_map", "bpf_create_map failed\n")) goto cleanup; err = bpf_map__set_inner_map_fd(skel->maps.ringbuf_hash, proto_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 821b4146b7b6..4efd337d6a3c 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -78,7 +78,7 @@ static int create_maps(enum bpf_map_type inner_type) attr.max_entries = REUSEPORT_ARRAY_SIZE; reuseport_array = bpf_create_map_xattr(&attr); - RET_ERR(reuseport_array == -1, "creating reuseport_array", + RET_ERR(reuseport_array < 0, "creating reuseport_array", "reuseport_array:%d errno:%d\n", reuseport_array, errno); /* Creating outer_map */ @@ -89,7 +89,7 @@ static int create_maps(enum bpf_map_type inner_type) attr.max_entries = 1; attr.inner_map_fd = reuseport_array; outer_map = bpf_create_map_xattr(&attr); - RET_ERR(outer_map == -1, "creating outer_map", + RET_ERR(outer_map < 0, "creating outer_map", "outer_map:%d errno:%d\n", outer_map, errno); return 0; @@ -102,8 +102,9 @@ static int prepare_bpf_obj(void) int err; obj = bpf_object__open("test_select_reuseport_kern.o"); - RET_ERR(IS_ERR_OR_NULL(obj), "open test_select_reuseport_kern.o", - "obj:%p PTR_ERR(obj):%ld\n", obj, PTR_ERR(obj)); + err = libbpf_get_error(obj); + RET_ERR(err, "open test_select_reuseport_kern.o", + "obj:%p PTR_ERR(obj):%d\n", obj, err); map = bpf_object__find_map_by_name(obj, "outer_map"); RET_ERR(!map, "find outer_map", "!map\n"); @@ -116,31 +117,31 @@ static int prepare_bpf_obj(void) prog = bpf_program__next(NULL, obj); RET_ERR(!prog, "get first bpf_program", "!prog\n"); select_by_skb_data_prog = bpf_program__fd(prog); - RET_ERR(select_by_skb_data_prog == -1, "get prog fd", + RET_ERR(select_by_skb_data_prog < 0, "get prog fd", "select_by_skb_data_prog:%d\n", select_by_skb_data_prog); map = bpf_object__find_map_by_name(obj, "result_map"); RET_ERR(!map, "find result_map", "!map\n"); result_map = bpf_map__fd(map); - RET_ERR(result_map == -1, "get result_map fd", + RET_ERR(result_map < 0, "get result_map fd", "result_map:%d\n", result_map); map = bpf_object__find_map_by_name(obj, "tmp_index_ovr_map"); RET_ERR(!map, "find tmp_index_ovr_map\n", "!map"); tmp_index_ovr_map = bpf_map__fd(map); - RET_ERR(tmp_index_ovr_map == -1, "get tmp_index_ovr_map fd", + RET_ERR(tmp_index_ovr_map < 0, "get tmp_index_ovr_map fd", "tmp_index_ovr_map:%d\n", tmp_index_ovr_map); map = bpf_object__find_map_by_name(obj, "linum_map"); RET_ERR(!map, "find linum_map", "!map\n"); linum_map = bpf_map__fd(map); - RET_ERR(linum_map == -1, "get linum_map fd", + RET_ERR(linum_map < 0, "get linum_map fd", "linum_map:%d\n", linum_map); map = bpf_object__find_map_by_name(obj, "data_check_map"); RET_ERR(!map, "find data_check_map", "!map\n"); data_check_map = bpf_map__fd(map); - RET_ERR(data_check_map == -1, "get data_check_map fd", + RET_ERR(data_check_map < 0, "get data_check_map fd", "data_check_map:%d\n", data_check_map); return 0; @@ -237,7 +238,7 @@ static long get_linum(void) int err; err = bpf_map_lookup_elem(linum_map, &index_zero, &linum); - RET_ERR(err == -1, "lookup_elem(linum_map)", "err:%d errno:%d\n", + RET_ERR(err < 0, "lookup_elem(linum_map)", "err:%d errno:%d\n", err, errno); return linum; @@ -254,11 +255,11 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd, addrlen = sizeof(cli_sa); err = getsockname(cli_fd, (struct sockaddr *)&cli_sa, &addrlen); - RET_IF(err == -1, "getsockname(cli_fd)", "err:%d errno:%d\n", + RET_IF(err < 0, "getsockname(cli_fd)", "err:%d errno:%d\n", err, errno); err = bpf_map_lookup_elem(data_check_map, &index_zero, &result); - RET_IF(err == -1, "lookup_elem(data_check_map)", "err:%d errno:%d\n", + RET_IF(err < 0, "lookup_elem(data_check_map)", "err:%d errno:%d\n", err, errno); if (type == SOCK_STREAM) { @@ -347,7 +348,7 @@ static void check_results(void) for (i = 0; i < NR_RESULTS; i++) { err = bpf_map_lookup_elem(result_map, &i, &results[i]); - RET_IF(err == -1, "lookup_elem(result_map)", + RET_IF(err < 0, "lookup_elem(result_map)", "i:%u err:%d errno:%d\n", i, err, errno); } @@ -524,12 +525,12 @@ static void test_syncookie(int type, sa_family_t family) */ err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &tmp_index, BPF_ANY); - RET_IF(err == -1, "update_elem(tmp_index_ovr_map, 0, 1)", + RET_IF(err < 0, "update_elem(tmp_index_ovr_map, 0, 1)", "err:%d errno:%d\n", err, errno); do_test(type, family, &cmd, PASS); err = bpf_map_lookup_elem(tmp_index_ovr_map, &index_zero, &tmp_index); - RET_IF(err == -1 || tmp_index != -1, + RET_IF(err < 0 || tmp_index >= 0, "lookup_elem(tmp_index_ovr_map)", "err:%d errno:%d tmp_index:%d\n", err, errno, tmp_index); @@ -569,7 +570,7 @@ static void test_detach_bpf(int type, sa_family_t family) for (i = 0; i < NR_RESULTS; i++) { err = bpf_map_lookup_elem(result_map, &i, &tmp); - RET_IF(err == -1, "lookup_elem(result_map)", + RET_IF(err < 0, "lookup_elem(result_map)", "i:%u err:%d errno:%d\n", i, err, errno); nr_run_before += tmp; } @@ -584,7 +585,7 @@ static void test_detach_bpf(int type, sa_family_t family) for (i = 0; i < NR_RESULTS; i++) { err = bpf_map_lookup_elem(result_map, &i, &tmp); - RET_IF(err == -1, "lookup_elem(result_map)", + RET_IF(err < 0, "lookup_elem(result_map)", "i:%u err:%d errno:%d\n", i, err, errno); nr_run_after += tmp; } @@ -632,24 +633,24 @@ static void prepare_sk_fds(int type, sa_family_t family, bool inany) SO_ATTACH_REUSEPORT_EBPF, &select_by_skb_data_prog, sizeof(select_by_skb_data_prog)); - RET_IF(err == -1, "setsockopt(SO_ATTACH_REUEPORT_EBPF)", + RET_IF(err < 0, "setsockopt(SO_ATTACH_REUEPORT_EBPF)", "err:%d errno:%d\n", err, errno); } err = bind(sk_fds[i], (struct sockaddr *)&srv_sa, addrlen); - RET_IF(err == -1, "bind()", "sk_fds[%d] err:%d errno:%d\n", + RET_IF(err < 0, "bind()", "sk_fds[%d] err:%d errno:%d\n", i, err, errno); if (type == SOCK_STREAM) { err = listen(sk_fds[i], 10); - RET_IF(err == -1, "listen()", + RET_IF(err < 0, "listen()", "sk_fds[%d] err:%d errno:%d\n", i, err, errno); } err = bpf_map_update_elem(reuseport_array, &i, &sk_fds[i], BPF_NOEXIST); - RET_IF(err == -1, "update_elem(reuseport_array)", + RET_IF(err < 0, "update_elem(reuseport_array)", "sk_fds[%d] err:%d errno:%d\n", i, err, errno); if (i == first) { @@ -682,7 +683,7 @@ static void setup_per_test(int type, sa_family_t family, bool inany, prepare_sk_fds(type, family, inany); err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &ovr, BPF_ANY); - RET_IF(err == -1, "update_elem(tmp_index_ovr_map, 0, -1)", + RET_IF(err < 0, "update_elem(tmp_index_ovr_map, 0, -1)", "err:%d errno:%d\n", err, errno); /* Install reuseport_array to outer_map? */ @@ -691,7 +692,7 @@ static void setup_per_test(int type, sa_family_t family, bool inany, err = bpf_map_update_elem(outer_map, &index_zero, &reuseport_array, BPF_ANY); - RET_IF(err == -1, "update_elem(outer_map, 0, reuseport_array)", + RET_IF(err < 0, "update_elem(outer_map, 0, reuseport_array)", "err:%d errno:%d\n", err, errno); } @@ -720,18 +721,18 @@ static void cleanup_per_test(bool no_inner_map) return; err = bpf_map_delete_elem(outer_map, &index_zero); - RET_IF(err == -1, "delete_elem(outer_map)", + RET_IF(err < 0, "delete_elem(outer_map)", "err:%d errno:%d\n", err, errno); } static void cleanup(void) { - if (outer_map != -1) { + if (outer_map >= 0) { close(outer_map); outer_map = -1; } - if (reuseport_array != -1) { + if (reuseport_array >= 0) { close(reuseport_array); reuseport_array = -1; } diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c index 7043e6ded0e6..023cc532992d 100644 --- a/tools/testing/selftests/bpf/prog_tests/send_signal.c +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -2,7 +2,7 @@ #include #include "test_send_signal_kern.skel.h" -static volatile int sigusr1_received = 0; +int sigusr1_received = 0; static void sigusr1_handler(int signum) { @@ -91,8 +91,7 @@ static void test_send_signal_common(struct perf_event_attr *attr, skel->links.send_signal_perf = bpf_program__attach_perf_event(skel->progs.send_signal_perf, pmu_fd); - if (CHECK(IS_ERR(skel->links.send_signal_perf), "attach_perf_event", - "err %ld\n", PTR_ERR(skel->links.send_signal_perf))) + if (!ASSERT_OK_PTR(skel->links.send_signal_perf, "attach_perf_event")) goto disable_pmu; } diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c index 45c82db3c58c..aee41547e7f4 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c @@ -480,7 +480,7 @@ static struct bpf_link *attach_lookup_prog(struct bpf_program *prog) } link = bpf_program__attach_netns(prog, net_fd); - if (CHECK(IS_ERR(link), "bpf_program__attach_netns", "failed\n")) { + if (!ASSERT_OK_PTR(link, "bpf_program__attach_netns")) { errno = -PTR_ERR(link); log_err("failed to attach program '%s' to netns", bpf_program__name(prog)); diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c index fe87b77af459..f6f130c99b8c 100644 --- a/tools/testing/selftests/bpf/prog_tests/skeleton.c +++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c @@ -82,10 +82,8 @@ void test_skeleton(void) CHECK(data->out2 != 2, "res2", "got %lld != exp %d\n", data->out2, 2); CHECK(bss->out3 != 3, "res3", "got %d != exp %d\n", (int)bss->out3, 3); CHECK(bss->out4 != 4, "res4", "got %lld != exp %d\n", bss->out4, 4); - CHECK(bss->handler_out5.a != 5, "res5", "got %d != exp %d\n", - bss->handler_out5.a, 5); - CHECK(bss->handler_out5.b != 6, "res6", "got %lld != exp %d\n", - bss->handler_out5.b, 6); + CHECK(bss->out5.a != 5, "res5", "got %d != exp %d\n", bss->out5.a, 5); + CHECK(bss->out5.b != 6, "res6", "got %lld != exp %d\n", bss->out5.b, 6); CHECK(bss->out6 != 14, "res7", "got %d != exp %d\n", bss->out6, 14); CHECK(bss->bpf_syscall != kcfg->CONFIG_BPF_SYSCALL, "ext1", diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c index af87118e748e..577d619fb07e 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c @@ -97,12 +97,12 @@ static void check_result(void) err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx, &egress_linum); - CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)", + CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)", "err:%d errno:%d\n", err, errno); err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx, &ingress_linum); - CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)", + CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)", "err:%d errno:%d\n", err, errno); memcpy(&srv_sk, &skel->bss->srv_sk, sizeof(srv_sk)); @@ -355,14 +355,12 @@ void test_sock_fields(void) egress_link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields, child_cg_fd); - if (CHECK(IS_ERR(egress_link), "attach_cgroup(egress)", "err:%ld\n", - PTR_ERR(egress_link))) + if (!ASSERT_OK_PTR(egress_link, "attach_cgroup(egress)")) goto done; ingress_link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields, child_cg_fd); - if (CHECK(IS_ERR(ingress_link), "attach_cgroup(ingress)", "err:%ld\n", - PTR_ERR(ingress_link))) + if (!ASSERT_OK_PTR(ingress_link, "attach_cgroup(ingress)")) goto done; linum_map_fd = bpf_map__fd(skel->maps.linum_map); @@ -375,8 +373,8 @@ done: bpf_link__destroy(egress_link); bpf_link__destroy(ingress_link); test_sock_fields__destroy(skel); - if (child_cg_fd != -1) + if (child_cg_fd >= 0) close(child_cg_fd); - if (parent_cg_fd != -1) + if (parent_cg_fd >= 0) close(parent_cg_fd); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index ab77596b64e3..1352ec104149 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -88,11 +88,11 @@ static void test_sockmap_create_update_free(enum bpf_map_type map_type) int s, map, err; s = connected_socket_v4(); - if (CHECK_FAIL(s == -1)) + if (CHECK_FAIL(s < 0)) return; map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0); - if (CHECK_FAIL(map == -1)) { + if (CHECK_FAIL(map < 0)) { perror("bpf_create_map"); goto out; } @@ -245,7 +245,7 @@ static void test_sockmap_copy(enum bpf_map_type map_type) opts.link_info = &linfo; opts.link_info_len = sizeof(linfo); link = bpf_program__attach_iter(skel->progs.copy, &opts); - if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n")) + if (!ASSERT_OK_PTR(link, "attach_iter")) goto out; iter_fd = bpf_iter_create(bpf_link__fd(link)); @@ -304,7 +304,7 @@ static void test_sockmap_skb_verdict_attach(enum bpf_attach_type first, } err = bpf_prog_attach(verdict, map, second, 0); - assert(err == -1 && errno == EBUSY); + ASSERT_EQ(err, -EBUSY, "prog_attach_fail"); err = bpf_prog_detach2(verdict, map, first); if (CHECK_FAIL(err)) { diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c index 06b86addc181..7a0d64fdc192 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c @@ -98,7 +98,7 @@ static void run_tests(int family, enum bpf_map_type map_type) int map; map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0); - if (CHECK_FAIL(map == -1)) { + if (CHECK_FAIL(map < 0)) { perror("bpf_map_create"); return; } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 648d9ae898d2..515229f24a93 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -139,7 +139,7 @@ #define xbpf_map_delete_elem(fd, key) \ ({ \ int __ret = bpf_map_delete_elem((fd), (key)); \ - if (__ret == -1) \ + if (__ret < 0) \ FAIL_ERRNO("map_delete"); \ __ret; \ }) @@ -147,7 +147,7 @@ #define xbpf_map_lookup_elem(fd, key, val) \ ({ \ int __ret = bpf_map_lookup_elem((fd), (key), (val)); \ - if (__ret == -1) \ + if (__ret < 0) \ FAIL_ERRNO("map_lookup"); \ __ret; \ }) @@ -155,7 +155,7 @@ #define xbpf_map_update_elem(fd, key, val, flags) \ ({ \ int __ret = bpf_map_update_elem((fd), (key), (val), (flags)); \ - if (__ret == -1) \ + if (__ret < 0) \ FAIL_ERRNO("map_update"); \ __ret; \ }) @@ -164,7 +164,7 @@ ({ \ int __ret = \ bpf_prog_attach((prog), (target), (type), (flags)); \ - if (__ret == -1) \ + if (__ret < 0) \ FAIL_ERRNO("prog_attach(" #type ")"); \ __ret; \ }) @@ -172,7 +172,7 @@ #define xbpf_prog_detach2(prog, target, type) \ ({ \ int __ret = bpf_prog_detach2((prog), (target), (type)); \ - if (__ret == -1) \ + if (__ret < 0) \ FAIL_ERRNO("prog_detach2(" #type ")"); \ __ret; \ }) @@ -1610,6 +1610,7 @@ static void udp_redir_to_connected(int family, int sotype, int sock_mapfd, struct sockaddr_storage addr; int c0, c1, p0, p1; unsigned int pass; + int retries = 100; socklen_t len; int err, n; u64 value; @@ -1686,9 +1687,13 @@ static void udp_redir_to_connected(int family, int sotype, int sock_mapfd, if (pass != 1) FAIL("%s: want pass count 1, have %d", log_prefix, pass); +again: n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1); - if (n < 0) + if (n < 0) { + if (errno == EAGAIN && retries--) + goto again; FAIL_ERRNO("%s: read", log_prefix); + } if (n == 0) FAIL("%s: incomplete read", log_prefix); diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c index 11a769e18f5d..0a91d8d9954b 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c @@ -62,8 +62,7 @@ retry: skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu, pmu_fd); - if (CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event", - "err %ld\n", PTR_ERR(skel->links.oncpu))) { + if (!ASSERT_OK_PTR(skel->links.oncpu, "attach_perf_event")) { close(pmu_fd); goto cleanup; } diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c index 37269d23df93..04b476bd62b9 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c @@ -21,7 +21,7 @@ void test_stacktrace_map(void) goto close_prog; link = bpf_program__attach_tracepoint(prog, "sched", "sched_switch"); - if (CHECK(IS_ERR(link), "attach_tp", "err %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_tp")) goto close_prog; /* find map fds */ diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c index 404a5498e1a3..4fd30bb651ad 100644 --- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c @@ -21,7 +21,7 @@ void test_stacktrace_map_raw_tp(void) goto close_prog; link = bpf_program__attach_raw_tracepoint(prog, "sched_switch"); - if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_raw_tp")) goto close_prog; /* find map fds */ @@ -59,7 +59,6 @@ void test_stacktrace_map_raw_tp(void) goto close_prog; close_prog: - if (!IS_ERR_OR_NULL(link)) - bpf_link__destroy(link); + bpf_link__destroy(link); bpf_object__close(obj); } diff --git a/tools/testing/selftests/bpf/prog_tests/static_linked.c b/tools/testing/selftests/bpf/prog_tests/static_linked.c index 46556976dccc..5c4e3014e063 100644 --- a/tools/testing/selftests/bpf/prog_tests/static_linked.c +++ b/tools/testing/selftests/bpf/prog_tests/static_linked.c @@ -14,12 +14,7 @@ void test_static_linked(void) return; skel->rodata->rovar1 = 1; - skel->bss->static_var1 = 2; - skel->bss->static_var11 = 3; - skel->rodata->rovar2 = 4; - skel->bss->static_var2 = 5; - skel->bss->static_var22 = 6; err = test_static_linked__load(skel); if (!ASSERT_OK(err, "skel_load")) @@ -32,8 +27,8 @@ void test_static_linked(void) /* trigger */ usleep(1); - ASSERT_EQ(skel->bss->var1, 1 * 2 + 2 + 3, "var1"); - ASSERT_EQ(skel->bss->var2, 4 * 3 + 5 + 6, "var2"); + ASSERT_EQ(skel->data->var1, 1 * 2 + 2 + 3, "var1"); + ASSERT_EQ(skel->data->var2, 4 * 3 + 5 + 6, "var2"); cleanup: test_static_linked__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/syscall.c b/tools/testing/selftests/bpf/prog_tests/syscall.c new file mode 100644 index 000000000000..81e997a69f7a --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/syscall.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include +#include "syscall.skel.h" + +struct args { + __u64 log_buf; + __u32 log_size; + int max_entries; + int map_fd; + int prog_fd; + int btf_fd; +}; + +void test_syscall(void) +{ + static char verifier_log[8192]; + struct args ctx = { + .max_entries = 1024, + .log_buf = (uintptr_t) verifier_log, + .log_size = sizeof(verifier_log), + }; + struct bpf_prog_test_run_attr tattr = { + .ctx_in = &ctx, + .ctx_size_in = sizeof(ctx), + }; + struct syscall *skel = NULL; + __u64 key = 12, value = 0; + int err; + + skel = syscall__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + tattr.prog_fd = bpf_program__fd(skel->progs.bpf_prog); + err = bpf_prog_test_run_xattr(&tattr); + ASSERT_EQ(err, 0, "err"); + ASSERT_EQ(tattr.retval, 1, "retval"); + ASSERT_GT(ctx.map_fd, 0, "ctx.map_fd"); + ASSERT_GT(ctx.prog_fd, 0, "ctx.prog_fd"); + ASSERT_OK(memcmp(verifier_log, "processed", sizeof("processed") - 1), + "verifier_log"); + + err = bpf_map_lookup_elem(ctx.map_fd, &key, &value); + ASSERT_EQ(err, 0, "map_lookup"); + ASSERT_EQ(value, 34, "map lookup value"); +cleanup: + syscall__destroy(skel); + if (ctx.prog_fd > 0) + close(ctx.prog_fd); + if (ctx.map_fd > 0) + close(ctx.map_fd); + if (ctx.btf_fd > 0) + close(ctx.btf_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c new file mode 100644 index 000000000000..4a505a5adf4d --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c @@ -0,0 +1,395 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +#include "test_tc_bpf.skel.h" + +#define LO_IFINDEX 1 + +#define TEST_DECLARE_OPTS(__fd) \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_h, .handle = 1); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_p, .priority = 1); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_f, .prog_fd = __fd); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hp, .handle = 1, .priority = 1); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hf, .handle = 1, .prog_fd = __fd); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_pf, .priority = 1, .prog_fd = __fd); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hpf, .handle = 1, .priority = 1, .prog_fd = __fd); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hpi, .handle = 1, .priority = 1, .prog_id = 42); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hpr, .handle = 1, .priority = 1, \ + .flags = BPF_TC_F_REPLACE); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_hpfi, .handle = 1, .priority = 1, .prog_fd = __fd, \ + .prog_id = 42); \ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts_prio_max, .handle = 1, .priority = UINT16_MAX + 1); + +static int test_tc_bpf_basic(const struct bpf_tc_hook *hook, int fd) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts, .handle = 1, .priority = 1, .prog_fd = fd); + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int ret; + + ret = bpf_obj_get_info_by_fd(fd, &info, &info_len); + if (!ASSERT_OK(ret, "bpf_obj_get_info_by_fd")) + return ret; + + ret = bpf_tc_attach(hook, &opts); + if (!ASSERT_OK(ret, "bpf_tc_attach")) + return ret; + + if (!ASSERT_EQ(opts.handle, 1, "handle set") || + !ASSERT_EQ(opts.priority, 1, "priority set") || + !ASSERT_EQ(opts.prog_id, info.id, "prog_id set")) + goto end; + + opts.prog_id = 0; + opts.flags = BPF_TC_F_REPLACE; + ret = bpf_tc_attach(hook, &opts); + if (!ASSERT_OK(ret, "bpf_tc_attach replace mode")) + goto end; + + opts.flags = opts.prog_fd = opts.prog_id = 0; + ret = bpf_tc_query(hook, &opts); + if (!ASSERT_OK(ret, "bpf_tc_query")) + goto end; + + if (!ASSERT_EQ(opts.handle, 1, "handle set") || + !ASSERT_EQ(opts.priority, 1, "priority set") || + !ASSERT_EQ(opts.prog_id, info.id, "prog_id set")) + goto end; + +end: + opts.flags = opts.prog_fd = opts.prog_id = 0; + ret = bpf_tc_detach(hook, &opts); + ASSERT_OK(ret, "bpf_tc_detach"); + return ret; +} + +static int test_tc_bpf_api(struct bpf_tc_hook *hook, int fd) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_opts, attach_opts, .handle = 1, .priority = 1, .prog_fd = fd); + DECLARE_LIBBPF_OPTS(bpf_tc_hook, inv_hook, .attach_point = BPF_TC_INGRESS); + DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts, .handle = 1, .priority = 1); + int ret; + + ret = bpf_tc_hook_create(NULL); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook = NULL")) + return -EINVAL; + + /* hook ifindex = 0 */ + ret = bpf_tc_hook_create(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook ifindex == 0")) + return -EINVAL; + + ret = bpf_tc_hook_destroy(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_destroy invalid hook ifindex == 0")) + return -EINVAL; + + ret = bpf_tc_attach(&inv_hook, &attach_opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook ifindex == 0")) + return -EINVAL; + attach_opts.prog_id = 0; + + ret = bpf_tc_detach(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook ifindex == 0")) + return -EINVAL; + + ret = bpf_tc_query(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook ifindex == 0")) + return -EINVAL; + + /* hook ifindex < 0 */ + inv_hook.ifindex = -1; + + ret = bpf_tc_hook_create(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook ifindex < 0")) + return -EINVAL; + + ret = bpf_tc_hook_destroy(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_destroy invalid hook ifindex < 0")) + return -EINVAL; + + ret = bpf_tc_attach(&inv_hook, &attach_opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook ifindex < 0")) + return -EINVAL; + attach_opts.prog_id = 0; + + ret = bpf_tc_detach(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook ifindex < 0")) + return -EINVAL; + + ret = bpf_tc_query(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook ifindex < 0")) + return -EINVAL; + + inv_hook.ifindex = LO_IFINDEX; + + /* hook.attach_point invalid */ + inv_hook.attach_point = 0xabcd; + ret = bpf_tc_hook_create(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook.attach_point")) + return -EINVAL; + + ret = bpf_tc_hook_destroy(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_destroy invalid hook.attach_point")) + return -EINVAL; + + ret = bpf_tc_attach(&inv_hook, &attach_opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook.attach_point")) + return -EINVAL; + + ret = bpf_tc_detach(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook.attach_point")) + return -EINVAL; + + ret = bpf_tc_query(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook.attach_point")) + return -EINVAL; + + inv_hook.attach_point = BPF_TC_INGRESS; + + /* hook.attach_point valid, but parent invalid */ + inv_hook.parent = TC_H_MAKE(1UL << 16, 10); + ret = bpf_tc_hook_create(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_create invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_hook_destroy(&inv_hook); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_hook_destroy invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_attach(&inv_hook, &attach_opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_detach(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_query(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook parent")) + return -EINVAL; + + inv_hook.attach_point = BPF_TC_CUSTOM; + inv_hook.parent = 0; + /* These return EOPNOTSUPP instead of EINVAL as parent is checked after + * attach_point of the hook. + */ + ret = bpf_tc_hook_create(&inv_hook); + if (!ASSERT_EQ(ret, -EOPNOTSUPP, "bpf_tc_hook_create invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_hook_destroy(&inv_hook); + if (!ASSERT_EQ(ret, -EOPNOTSUPP, "bpf_tc_hook_destroy invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_attach(&inv_hook, &attach_opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_detach(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook parent")) + return -EINVAL; + + ret = bpf_tc_query(&inv_hook, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook parent")) + return -EINVAL; + + inv_hook.attach_point = BPF_TC_INGRESS; + + /* detach */ + { + TEST_DECLARE_OPTS(fd); + + ret = bpf_tc_detach(NULL, &opts_hp); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid hook = NULL")) + return -EINVAL; + + ret = bpf_tc_detach(hook, NULL); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid opts = NULL")) + return -EINVAL; + + ret = bpf_tc_detach(hook, &opts_hpr); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid flags set")) + return -EINVAL; + + ret = bpf_tc_detach(hook, &opts_hpf); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid prog_fd set")) + return -EINVAL; + + ret = bpf_tc_detach(hook, &opts_hpi); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid prog_id set")) + return -EINVAL; + + ret = bpf_tc_detach(hook, &opts_p); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid handle unset")) + return -EINVAL; + + ret = bpf_tc_detach(hook, &opts_h); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid priority unset")) + return -EINVAL; + + ret = bpf_tc_detach(hook, &opts_prio_max); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_detach invalid priority > UINT16_MAX")) + return -EINVAL; + } + + /* query */ + { + TEST_DECLARE_OPTS(fd); + + ret = bpf_tc_query(NULL, &opts); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid hook = NULL")) + return -EINVAL; + + ret = bpf_tc_query(hook, NULL); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid opts = NULL")) + return -EINVAL; + + ret = bpf_tc_query(hook, &opts_hpr); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid flags set")) + return -EINVAL; + + ret = bpf_tc_query(hook, &opts_hpf); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid prog_fd set")) + return -EINVAL; + + ret = bpf_tc_query(hook, &opts_hpi); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid prog_id set")) + return -EINVAL; + + ret = bpf_tc_query(hook, &opts_p); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid handle unset")) + return -EINVAL; + + ret = bpf_tc_query(hook, &opts_h); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid priority unset")) + return -EINVAL; + + ret = bpf_tc_query(hook, &opts_prio_max); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query invalid priority > UINT16_MAX")) + return -EINVAL; + + /* when chain is not present, kernel returns -EINVAL */ + ret = bpf_tc_query(hook, &opts_hp); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_query valid handle, priority set")) + return -EINVAL; + } + + /* attach */ + { + TEST_DECLARE_OPTS(fd); + + ret = bpf_tc_attach(NULL, &opts_hp); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid hook = NULL")) + return -EINVAL; + + ret = bpf_tc_attach(hook, NULL); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid opts = NULL")) + return -EINVAL; + + opts_hp.flags = 42; + ret = bpf_tc_attach(hook, &opts_hp); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid flags")) + return -EINVAL; + + ret = bpf_tc_attach(hook, NULL); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid prog_fd unset")) + return -EINVAL; + + ret = bpf_tc_attach(hook, &opts_hpi); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid prog_id set")) + return -EINVAL; + + ret = bpf_tc_attach(hook, &opts_pf); + if (!ASSERT_OK(ret, "bpf_tc_attach valid handle unset")) + return -EINVAL; + opts_pf.prog_fd = opts_pf.prog_id = 0; + ASSERT_OK(bpf_tc_detach(hook, &opts_pf), "bpf_tc_detach"); + + ret = bpf_tc_attach(hook, &opts_hf); + if (!ASSERT_OK(ret, "bpf_tc_attach valid priority unset")) + return -EINVAL; + opts_hf.prog_fd = opts_hf.prog_id = 0; + ASSERT_OK(bpf_tc_detach(hook, &opts_hf), "bpf_tc_detach"); + + ret = bpf_tc_attach(hook, &opts_prio_max); + if (!ASSERT_EQ(ret, -EINVAL, "bpf_tc_attach invalid priority > UINT16_MAX")) + return -EINVAL; + + ret = bpf_tc_attach(hook, &opts_f); + if (!ASSERT_OK(ret, "bpf_tc_attach valid both handle and priority unset")) + return -EINVAL; + opts_f.prog_fd = opts_f.prog_id = 0; + ASSERT_OK(bpf_tc_detach(hook, &opts_f), "bpf_tc_detach"); + } + + return 0; +} + +void test_tc_bpf(void) +{ + DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX, + .attach_point = BPF_TC_INGRESS); + struct test_tc_bpf *skel = NULL; + bool hook_created = false; + int cls_fd, ret; + + skel = test_tc_bpf__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_tc_bpf__open_and_load")) + return; + + cls_fd = bpf_program__fd(skel->progs.cls); + + ret = bpf_tc_hook_create(&hook); + if (ret == 0) + hook_created = true; + + ret = ret == -EEXIST ? 0 : ret; + if (!ASSERT_OK(ret, "bpf_tc_hook_create(BPF_TC_INGRESS)")) + goto end; + + hook.attach_point = BPF_TC_CUSTOM; + hook.parent = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); + ret = bpf_tc_hook_create(&hook); + if (!ASSERT_EQ(ret, -EOPNOTSUPP, "bpf_tc_hook_create invalid hook.attach_point")) + goto end; + + ret = test_tc_bpf_basic(&hook, cls_fd); + if (!ASSERT_OK(ret, "test_tc_internal ingress")) + goto end; + + ret = bpf_tc_hook_destroy(&hook); + if (!ASSERT_EQ(ret, -EOPNOTSUPP, "bpf_tc_hook_destroy invalid hook.attach_point")) + goto end; + + hook.attach_point = BPF_TC_INGRESS; + hook.parent = 0; + bpf_tc_hook_destroy(&hook); + + ret = test_tc_bpf_basic(&hook, cls_fd); + if (!ASSERT_OK(ret, "test_tc_internal ingress")) + goto end; + + bpf_tc_hook_destroy(&hook); + + hook.attach_point = BPF_TC_EGRESS; + ret = test_tc_bpf_basic(&hook, cls_fd); + if (!ASSERT_OK(ret, "test_tc_internal egress")) + goto end; + + bpf_tc_hook_destroy(&hook); + + ret = test_tc_bpf_api(&hook, cls_fd); + if (!ASSERT_OK(ret, "test_tc_bpf_api")) + goto end; + + bpf_tc_hook_destroy(&hook); + +end: + if (hook_created) { + hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS; + bpf_tc_hook_destroy(&hook); + } + test_tc_bpf__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c index 08d19cafd5e8..1fa772079967 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c @@ -353,8 +353,7 @@ static void fastopen_estab(void) return; link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd); - if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n", - PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_cgroup(estab)")) return; if (sk_fds_connect(&sk_fds, true)) { @@ -398,8 +397,7 @@ static void syncookie_estab(void) return; link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd); - if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n", - PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_cgroup(estab)")) return; if (sk_fds_connect(&sk_fds, false)) { @@ -431,8 +429,7 @@ static void fin(void) return; link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd); - if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n", - PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_cgroup(estab)")) return; if (sk_fds_connect(&sk_fds, false)) { @@ -471,8 +468,7 @@ static void __simple_estab(bool exprm) return; link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd); - if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n", - PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_cgroup(estab)")) return; if (sk_fds_connect(&sk_fds, false)) { @@ -509,8 +505,7 @@ static void misc(void) return; link = bpf_program__attach_cgroup(misc_skel->progs.misc_estab, cg_fd); - if (CHECK(IS_ERR(link), "attach_cgroup(misc_estab)", "err: %ld\n", - PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_cgroup(misc_estab)")) return; if (sk_fds_connect(&sk_fds, false)) { diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c index 9966685866fd..123c68c1917d 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c +++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c @@ -73,7 +73,7 @@ void test_test_overhead(void) return; obj = bpf_object__open_file("./test_overhead.o", NULL); - if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) + if (!ASSERT_OK_PTR(obj, "obj_open_file")) return; kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name); @@ -108,7 +108,7 @@ void test_test_overhead(void) /* attach kprobe */ link = bpf_program__attach_kprobe(kprobe_prog, false /* retprobe */, kprobe_func); - if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_kprobe")) goto cleanup; test_run("kprobe"); bpf_link__destroy(link); @@ -116,28 +116,28 @@ void test_test_overhead(void) /* attach kretprobe */ link = bpf_program__attach_kprobe(kretprobe_prog, true /* retprobe */, kprobe_func); - if (CHECK(IS_ERR(link), "attach kretprobe", "err %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_kretprobe")) goto cleanup; test_run("kretprobe"); bpf_link__destroy(link); /* attach raw_tp */ link = bpf_program__attach_raw_tracepoint(raw_tp_prog, "task_rename"); - if (CHECK(IS_ERR(link), "attach fentry", "err %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_raw_tp")) goto cleanup; test_run("raw_tp"); bpf_link__destroy(link); /* attach fentry */ link = bpf_program__attach_trace(fentry_prog); - if (CHECK(IS_ERR(link), "attach fentry", "err %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_fentry")) goto cleanup; test_run("fentry"); bpf_link__destroy(link); /* attach fexit */ link = bpf_program__attach_trace(fexit_prog); - if (CHECK(IS_ERR(link), "attach fexit", "err %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "attach_fexit")) goto cleanup; test_run("fexit"); bpf_link__destroy(link); diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c index 39b0decb1bb2..d39bc00feb45 100644 --- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c +++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c @@ -3,7 +3,7 @@ #include -#include "trace_printk.skel.h" +#include "trace_printk.lskel.h" #define TRACEBUF "/sys/kernel/debug/tracing/trace_pipe" #define SEARCHMSG "testing,testing" @@ -21,6 +21,9 @@ void test_trace_printk(void) if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) return; + ASSERT_EQ(skel->rodata->fmt[0], 'T', "invalid printk fmt string"); + skel->rodata->fmt[0] = 't'; + err = trace_printk__load(skel); if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err)) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c index f3022d934e2d..d7f5a931d7f3 100644 --- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c +++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c @@ -55,7 +55,7 @@ void test_trampoline_count(void) /* attach 'allowed' trampoline programs */ for (i = 0; i < MAX_TRAMP_PROGS; i++) { obj = bpf_object__open_file(object, NULL); - if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) { + if (!ASSERT_OK_PTR(obj, "obj_open_file")) { obj = NULL; goto cleanup; } @@ -68,14 +68,14 @@ void test_trampoline_count(void) if (rand() % 2) { link = load(inst[i].obj, fentry_name); - if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) { + if (!ASSERT_OK_PTR(link, "attach_prog")) { link = NULL; goto cleanup; } inst[i].link_fentry = link; } else { link = load(inst[i].obj, fexit_name); - if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link))) { + if (!ASSERT_OK_PTR(link, "attach_prog")) { link = NULL; goto cleanup; } @@ -85,7 +85,7 @@ void test_trampoline_count(void) /* and try 1 extra.. */ obj = bpf_object__open_file(object, NULL); - if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj))) { + if (!ASSERT_OK_PTR(obj, "obj_open_file")) { obj = NULL; goto cleanup; } @@ -96,13 +96,15 @@ void test_trampoline_count(void) /* ..that needs to fail */ link = load(obj, fentry_name); - if (CHECK(!IS_ERR(link), "cannot attach over the limit", "err %ld\n", PTR_ERR(link))) { + err = libbpf_get_error(link); + if (!ASSERT_ERR_PTR(link, "cannot attach over the limit")) { bpf_link__destroy(link); goto cleanup_extra; } /* with E2BIG error */ - CHECK(PTR_ERR(link) != -E2BIG, "proper error check", "err %ld\n", PTR_ERR(link)); + ASSERT_EQ(err, -E2BIG, "proper error check"); + ASSERT_EQ(link, NULL, "ptr_is_null"); /* and finaly execute the probe */ if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L))) diff --git a/tools/testing/selftests/bpf/prog_tests/udp_limit.c b/tools/testing/selftests/bpf/prog_tests/udp_limit.c index 2aba09d4d01b..56c9d6bd38a3 100644 --- a/tools/testing/selftests/bpf/prog_tests/udp_limit.c +++ b/tools/testing/selftests/bpf/prog_tests/udp_limit.c @@ -22,11 +22,10 @@ void test_udp_limit(void) goto close_cgroup_fd; skel->links.sock = bpf_program__attach_cgroup(skel->progs.sock, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.sock, "cg_attach_sock")) + goto close_skeleton; skel->links.sock_release = bpf_program__attach_cgroup(skel->progs.sock_release, cgroup_fd); - if (CHECK(IS_ERR(skel->links.sock) || IS_ERR(skel->links.sock_release), - "cg-attach", "sock %ld sock_release %ld", - PTR_ERR(skel->links.sock), - PTR_ERR(skel->links.sock_release))) + if (!ASSERT_OK_PTR(skel->links.sock_release, "cg_attach_sock_release")) goto close_skeleton; /* BPF program enforces a single UDP socket per cgroup, diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c index 2c6c570b21f8..3bd5904b4db5 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -90,7 +90,7 @@ void test_xdp_bpf2bpf(void) pb_opts.ctx = &passed; pb = perf_buffer__new(bpf_map__fd(ftrace_skel->maps.perf_buf_map), 1, &pb_opts); - if (CHECK(IS_ERR(pb), "perf_buf__new", "err %ld\n", PTR_ERR(pb))) + if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto out; /* Run test program */ diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c index 6f814999b395..46eed0a33c23 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c @@ -51,7 +51,7 @@ void test_xdp_link(void) /* BPF link is not allowed to replace prog attachment */ link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO); - if (CHECK(!IS_ERR(link), "link_attach_fail", "unexpected success\n")) { + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { bpf_link__destroy(link); /* best-effort detach prog */ opts.old_fd = prog_fd1; @@ -67,7 +67,7 @@ void test_xdp_link(void) /* now BPF link should attach successfully */ link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO); - if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "link_attach")) goto cleanup; skel1->links.xdp_handler = link; @@ -95,7 +95,7 @@ void test_xdp_link(void) /* BPF link is not allowed to replace another BPF link */ link = bpf_program__attach_xdp(skel2->progs.xdp_handler, IFINDEX_LO); - if (CHECK(!IS_ERR(link), "link_attach_fail", "unexpected success\n")) { + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { bpf_link__destroy(link); goto cleanup; } @@ -105,7 +105,7 @@ void test_xdp_link(void) /* new link attach should succeed */ link = bpf_program__attach_xdp(skel2->progs.xdp_handler, IFINDEX_LO); - if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link))) + if (!ASSERT_OK_PTR(link, "link_attach")) goto cleanup; skel2->links.xdp_handler = link; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c index 6dfce3fd68bc..0aa3cd34cbe3 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c @@ -2,7 +2,6 @@ /* Copyright (c) 2020 Facebook */ #include "bpf_iter.h" #include -#include char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c index b83b5d2e17dc..6c39e86b666f 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c @@ -2,7 +2,6 @@ /* Copyright (c) 2020 Facebook */ #include "bpf_iter.h" #include -#include char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c index d58d9f1642b5..784a610ce039 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c @@ -3,7 +3,6 @@ #include "bpf_iter.h" #include "bpf_tracing_net.h" #include -#include char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c index 95989f4c99b5..a28e51e2dcee 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c @@ -3,7 +3,6 @@ #include "bpf_iter.h" #include "bpf_tracing_net.h" #include -#include char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c index b7f32c160f4e..c86b93f33b32 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c @@ -2,7 +2,6 @@ /* Copyright (c) 2020 Facebook */ #include "bpf_iter.h" #include -#include char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c index a1ddc36f13ec..bca8b889cb10 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c @@ -2,7 +2,6 @@ /* Copyright (c) 2020, Oracle and/or its affiliates. */ #include "bpf_iter.h" #include -#include #include #include diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c index b2f7c7c5f952..6e7b400888fe 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c @@ -2,7 +2,6 @@ /* Copyright (c) 2020 Facebook */ #include "bpf_iter.h" #include -#include char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c index 43c36f5f7649..f2b8167b72a8 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c @@ -2,7 +2,6 @@ /* Copyright (c) 2020 Facebook */ #include "bpf_iter.h" #include -#include char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c index 11d1aa37cf11..4ea6a37d1345 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c @@ -2,7 +2,6 @@ /* Copyright (c) 2020 Facebook */ #include "bpf_iter.h" #include -#include char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c index 54380c5e1069..2e4775c35414 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c @@ -3,7 +3,6 @@ #include "bpf_iter.h" #include "bpf_tracing_net.h" #include -#include #include char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c index b4fbddfa4e10..943f7bba180e 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c @@ -3,7 +3,6 @@ #include "bpf_iter.h" #include "bpf_tracing_net.h" #include -#include #include char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c index ee49493dc125..400fdf8d6233 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c @@ -9,8 +9,8 @@ __u32 map1_id = 0, map2_id = 0; __u32 map1_accessed = 0, map2_accessed = 0; __u64 map1_seqnum = 0, map2_seqnum1 = 0, map2_seqnum2 = 0; -static volatile const __u32 print_len; -static volatile const __u32 ret1; +volatile const __u32 print_len; +volatile const __u32 ret1; SEC("iter/bpf_map") int dump_bpf_map(struct bpf_iter__bpf_map *ctx) diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c index f258583afbbd..cf0c485b1ed7 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c @@ -3,7 +3,6 @@ #include "bpf_iter.h" #include "bpf_tracing_net.h" #include -#include #include char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c index 65f93bb03f0f..5031e21c433f 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c @@ -3,7 +3,6 @@ #include "bpf_iter.h" #include "bpf_tracing_net.h" #include -#include #include char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c index a46a264ce24e..55e283050cab 100644 --- a/tools/testing/selftests/bpf/progs/kfree_skb.c +++ b/tools/testing/selftests/bpf/progs/kfree_skb.c @@ -109,10 +109,10 @@ int BPF_PROG(trace_kfree_skb, struct sk_buff *skb, void *location) return 0; } -static volatile struct { +struct { bool fentry_test_ok; bool fexit_test_ok; -} result; +} result = {}; SEC("fentry/eth_type_trans") int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb, struct net_device *dev, diff --git a/tools/testing/selftests/bpf/progs/linked_maps1.c b/tools/testing/selftests/bpf/progs/linked_maps1.c index 52291515cc72..00bf1ca95986 100644 --- a/tools/testing/selftests/bpf/progs/linked_maps1.c +++ b/tools/testing/selftests/bpf/progs/linked_maps1.c @@ -75,7 +75,7 @@ int BPF_PROG(handler_exit1) val = bpf_map_lookup_elem(&map_weak, &key); if (val) output_weak1 = *val; - + return 0; } diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c new file mode 100644 index 000000000000..e550f728962d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/syscall.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include +#include +#include +#include +#include <../../../tools/include/linux/filter.h> +#include + +char _license[] SEC("license") = "GPL"; + +struct args { + __u64 log_buf; + __u32 log_size; + int max_entries; + int map_fd; + int prog_fd; + int btf_fd; +}; + +#define BTF_INFO_ENC(kind, kind_flag, vlen) \ + ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) +#define BTF_TYPE_ENC(name, info, size_or_type) (name), (info), (size_or_type) +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) + +static int btf_load(void) +{ + struct btf_blob { + struct btf_header btf_hdr; + __u32 types[8]; + __u32 str; + } raw_btf = { + .btf_hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = sizeof(__u32) * 8, + .str_off = sizeof(__u32) * 8, + .str_len = sizeof(__u32), + }, + .types = { + /* long */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8), /* [1] */ + /* unsigned long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + }, + }; + static union bpf_attr btf_load_attr = { + .btf_size = sizeof(raw_btf), + }; + + btf_load_attr.btf = (long)&raw_btf; + return bpf_sys_bpf(BPF_BTF_LOAD, &btf_load_attr, sizeof(btf_load_attr)); +} + +SEC("syscall") +int bpf_prog(struct args *ctx) +{ + static char license[] = "GPL"; + static struct bpf_insn insns[] = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + static union bpf_attr map_create_attr = { + .map_type = BPF_MAP_TYPE_HASH, + .key_size = 8, + .value_size = 8, + .btf_key_type_id = 1, + .btf_value_type_id = 2, + }; + static union bpf_attr map_update_attr = { .map_fd = 1, }; + static __u64 key = 12; + static __u64 value = 34; + static union bpf_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + .insn_cnt = sizeof(insns) / sizeof(insns[0]), + }; + int ret; + + ret = btf_load(); + if (ret <= 0) + return ret; + + ctx->btf_fd = ret; + map_create_attr.max_entries = ctx->max_entries; + map_create_attr.btf_fd = ret; + + prog_load_attr.license = (long) license; + prog_load_attr.insns = (long) insns; + prog_load_attr.log_buf = ctx->log_buf; + prog_load_attr.log_size = ctx->log_size; + prog_load_attr.log_level = 1; + + ret = bpf_sys_bpf(BPF_MAP_CREATE, &map_create_attr, sizeof(map_create_attr)); + if (ret <= 0) + return ret; + ctx->map_fd = ret; + insns[3].imm = ret; + + map_update_attr.map_fd = ret; + map_update_attr.key = (long) &key; + map_update_attr.value = (long) &value; + ret = bpf_sys_bpf(BPF_MAP_UPDATE_ELEM, &map_update_attr, sizeof(map_update_attr)); + if (ret < 0) + return ret; + + ret = bpf_sys_bpf(BPF_PROG_LOAD, &prog_load_attr, sizeof(prog_load_attr)); + if (ret <= 0) + return ret; + ctx->prog_fd = ret; + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c index 739dc2a51e74..910858fe078a 100644 --- a/tools/testing/selftests/bpf/progs/tailcall3.c +++ b/tools/testing/selftests/bpf/progs/tailcall3.c @@ -10,7 +10,7 @@ struct { __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); -static volatile int count; +int count = 0; SEC("classifier/0") int bpf_func_0(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c index f82075b47d7d..bd4be135c39d 100644 --- a/tools/testing/selftests/bpf/progs/tailcall4.c +++ b/tools/testing/selftests/bpf/progs/tailcall4.c @@ -10,7 +10,7 @@ struct { __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); -static volatile int selector; +int selector = 0; #define TAIL_FUNC(x) \ SEC("classifier/" #x) \ diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c index ce5450744fd4..adf30a33064e 100644 --- a/tools/testing/selftests/bpf/progs/tailcall5.c +++ b/tools/testing/selftests/bpf/progs/tailcall5.c @@ -10,7 +10,7 @@ struct { __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); -static volatile int selector; +int selector = 0; #define TAIL_FUNC(x) \ SEC("classifier/" #x) \ diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c index 7b1c04183824..3cc4c12817b5 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c @@ -20,7 +20,7 @@ int subprog_tail(struct __sk_buff *skb) return 1; } -static volatile int count; +int count = 0; SEC("classifier/0") int bpf_func_0(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c index 9a1b166b7fbe..77df6d4db895 100644 --- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c +++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c @@ -9,7 +9,7 @@ struct { __uint(value_size, sizeof(__u32)); } jmp_table SEC(".maps"); -static volatile int count; +int count = 0; __noinline int subprog_tail_2(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c index c4a9bae96e75..71184af57749 100644 --- a/tools/testing/selftests/bpf/progs/test_check_mtu.c +++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c @@ -11,8 +11,8 @@ char _license[] SEC("license") = "GPL"; /* Userspace will update with MTU it can see on device */ -static volatile const int GLOBAL_USER_MTU; -static volatile const __u32 GLOBAL_USER_IFINDEX; +volatile const int GLOBAL_USER_MTU; +volatile const __u32 GLOBAL_USER_IFINDEX; /* BPF-prog will update these with MTU values it can see */ __u32 global_bpf_mtu_xdp = 0; diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c index 3c1e042962e6..e2a5acc4785c 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -39,8 +39,8 @@ char _license[] SEC("license") = "Dual BSD/GPL"; /** * Destination port and IP used for UDP encapsulation. */ -static volatile const __be16 ENCAPSULATION_PORT; -static volatile const __be32 ENCAPSULATION_IP; +volatile const __be16 ENCAPSULATION_PORT; +volatile const __be32 ENCAPSULATION_IP; typedef struct { uint64_t processed_packets_total; diff --git a/tools/testing/selftests/bpf/progs/test_global_func_args.c b/tools/testing/selftests/bpf/progs/test_global_func_args.c index cae309538a9e..e712bf77daae 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func_args.c +++ b/tools/testing/selftests/bpf/progs/test_global_func_args.c @@ -8,7 +8,7 @@ struct S { int v; }; -static volatile struct S global_variable; +struct S global_variable = {}; struct { __uint(type, BPF_MAP_TYPE_ARRAY); diff --git a/tools/testing/selftests/bpf/progs/test_lookup_and_delete.c b/tools/testing/selftests/bpf/progs/test_lookup_and_delete.c new file mode 100644 index 000000000000..3a193f42c7e7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_lookup_and_delete.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include + +__u32 set_pid = 0; +__u64 set_key = 0; +__u64 set_value = 0; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 2); + __type(key, __u64); + __type(value, __u64); +} hash_map SEC(".maps"); + +SEC("tp/syscalls/sys_enter_getpgid") +int bpf_lookup_and_delete_test(const void *ctx) +{ + if (set_pid == bpf_get_current_pid_tgid() >> 32) + bpf_map_update_elem(&hash_map, &set_key, &set_value, BPF_NOEXIST); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_migrate_reuseport.c b/tools/testing/selftests/bpf/progs/test_migrate_reuseport.c new file mode 100644 index 000000000000..27df571abf5b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_migrate_reuseport.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Check if we can migrate child sockets. + * + * 1. If reuse_md->migrating_sk is NULL (SYN packet), + * return SK_PASS without selecting a listener. + * 2. If reuse_md->migrating_sk is not NULL (socket migration), + * select a listener (reuseport_map[migrate_map[cookie]]) + * + * Author: Kuniyuki Iwashima + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct { + __uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY); + __uint(max_entries, 256); + __type(key, int); + __type(value, __u64); +} reuseport_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 256); + __type(key, __u64); + __type(value, int); +} migrate_map SEC(".maps"); + +int migrated_at_close = 0; +int migrated_at_close_fastopen = 0; +int migrated_at_send_synack = 0; +int migrated_at_recv_ack = 0; +__be16 server_port; + +SEC("xdp") +int drop_ack(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + struct tcphdr *tcp = NULL; + + if (eth + 1 > data_end) + goto pass; + + switch (bpf_ntohs(eth->h_proto)) { + case ETH_P_IP: { + struct iphdr *ip = (struct iphdr *)(eth + 1); + + if (ip + 1 > data_end) + goto pass; + + if (ip->protocol != IPPROTO_TCP) + goto pass; + + tcp = (struct tcphdr *)((void *)ip + ip->ihl * 4); + break; + } + case ETH_P_IPV6: { + struct ipv6hdr *ipv6 = (struct ipv6hdr *)(eth + 1); + + if (ipv6 + 1 > data_end) + goto pass; + + if (ipv6->nexthdr != IPPROTO_TCP) + goto pass; + + tcp = (struct tcphdr *)(ipv6 + 1); + break; + } + default: + goto pass; + } + + if (tcp + 1 > data_end) + goto pass; + + if (tcp->dest != server_port) + goto pass; + + if (!tcp->syn && tcp->ack) + return XDP_DROP; + +pass: + return XDP_PASS; +} + +SEC("sk_reuseport/migrate") +int migrate_reuseport(struct sk_reuseport_md *reuse_md) +{ + int *key, flags = 0, state, err; + __u64 cookie; + + if (!reuse_md->migrating_sk) + return SK_PASS; + + state = reuse_md->migrating_sk->state; + cookie = bpf_get_socket_cookie(reuse_md->sk); + + key = bpf_map_lookup_elem(&migrate_map, &cookie); + if (!key) + return SK_DROP; + + err = bpf_sk_select_reuseport(reuse_md, &reuseport_map, key, flags); + if (err) + return SK_PASS; + + switch (state) { + case BPF_TCP_ESTABLISHED: + __sync_fetch_and_add(&migrated_at_close, 1); + break; + case BPF_TCP_SYN_RECV: + __sync_fetch_and_add(&migrated_at_close_fastopen, 1); + break; + case BPF_TCP_NEW_SYN_RECV: + if (!reuse_md->len) + __sync_fetch_and_add(&migrated_at_send_synack, 1); + else + __sync_fetch_and_add(&migrated_at_recv_ack, 1); + break; + } + + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c index ecbeea2df259..fc8e8a34a3db 100644 --- a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c +++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c @@ -5,7 +5,7 @@ #include #include -static volatile const struct { +const struct { unsigned a[4]; /* * if the struct's size is multiple of 16, compiler will put it into @@ -15,11 +15,11 @@ static volatile const struct { char _y; } rdonly_values = { .a = {2, 3, 4, 5} }; -static volatile struct { +struct { unsigned did_run; unsigned iters; unsigned sum; -} res; +} res = {}; SEC("raw_tracepoint/sys_enter:skip_loop") int skip_loop(struct pt_regs *ctx) diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf.c b/tools/testing/selftests/bpf/progs/test_ringbuf.c index 6b3f288b7c63..eaa7d9dba0be 100644 --- a/tools/testing/selftests/bpf/progs/test_ringbuf.c +++ b/tools/testing/selftests/bpf/progs/test_ringbuf.c @@ -35,7 +35,7 @@ long prod_pos = 0; /* inner state */ long seq = 0; -SEC("tp/syscalls/sys_enter_getpgid") +SEC("fentry/__x64_sys_getpgid") int test_ringbuf(void *ctx) { int cur_pid = bpf_get_current_pid_tgid() >> 32; @@ -48,7 +48,7 @@ int test_ringbuf(void *ctx) sample = bpf_ringbuf_reserve(&ringbuf, sizeof(*sample), 0); if (!sample) { __sync_fetch_and_add(&dropped, 1); - return 1; + return 0; } sample->pid = pid; diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c index 374ccef704e1..441fa1c552c8 100644 --- a/tools/testing/selftests/bpf/progs/test_skeleton.c +++ b/tools/testing/selftests/bpf/progs/test_skeleton.c @@ -38,11 +38,11 @@ extern int LINUX_KERNEL_VERSION __kconfig; bool bpf_syscall = 0; int kern_ver = 0; +struct s out5 = {}; + SEC("raw_tp/sys_enter") int handler(const void *ctx) { - static volatile struct s out5; - out1 = in1; out2 = in2; out3 = in3; diff --git a/tools/testing/selftests/bpf/progs/test_snprintf.c b/tools/testing/selftests/bpf/progs/test_snprintf.c index e35129bea0a0..e2ad26150f9b 100644 --- a/tools/testing/selftests/bpf/progs/test_snprintf.c +++ b/tools/testing/selftests/bpf/progs/test_snprintf.c @@ -3,7 +3,6 @@ #include #include -#include __u32 pid = 0; diff --git a/tools/testing/selftests/bpf/progs/test_snprintf_single.c b/tools/testing/selftests/bpf/progs/test_snprintf_single.c index 402adaf344f9..3095837334d3 100644 --- a/tools/testing/selftests/bpf/progs/test_snprintf_single.c +++ b/tools/testing/selftests/bpf/progs/test_snprintf_single.c @@ -5,7 +5,7 @@ #include /* The format string is filled from the userspace such that loading fails */ -static const char fmt[10]; +const char fmt[10]; SEC("raw_tp/sys_enter") int handler(const void *ctx) diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c index a39eba9f5201..a1cc58b10c7c 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c @@ -28,8 +28,8 @@ struct { __type(value, unsigned int); } verdict_map SEC(".maps"); -static volatile bool test_sockmap; /* toggled by user-space */ -static volatile bool test_ingress; /* toggled by user-space */ +bool test_sockmap = false; /* toggled by user-space */ +bool test_ingress = false; /* toggled by user-space */ SEC("sk_skb/stream_parser") int prog_stream_parser(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/test_static_linked1.c b/tools/testing/selftests/bpf/progs/test_static_linked1.c index ea1a6c4c7172..4f0b612e1661 100644 --- a/tools/testing/selftests/bpf/progs/test_static_linked1.c +++ b/tools/testing/selftests/bpf/progs/test_static_linked1.c @@ -4,10 +4,10 @@ #include #include -/* 8-byte aligned .bss */ -static volatile long static_var1; -static volatile int static_var11; -int var1 = 0; +/* 8-byte aligned .data */ +static volatile long static_var1 = 2; +static volatile int static_var2 = 3; +int var1 = -1; /* 4-byte aligned .rodata */ const volatile int rovar1; @@ -21,7 +21,7 @@ static __noinline int subprog(int x) SEC("raw_tp/sys_enter") int handler1(const void *ctx) { - var1 = subprog(rovar1) + static_var1 + static_var11; + var1 = subprog(rovar1) + static_var1 + static_var2; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_static_linked2.c b/tools/testing/selftests/bpf/progs/test_static_linked2.c index 54d8d1ab577c..766ebd502a60 100644 --- a/tools/testing/selftests/bpf/progs/test_static_linked2.c +++ b/tools/testing/selftests/bpf/progs/test_static_linked2.c @@ -4,10 +4,10 @@ #include #include -/* 4-byte aligned .bss */ -static volatile int static_var2; -static volatile int static_var22; -int var2 = 0; +/* 4-byte aligned .data */ +static volatile int static_var1 = 5; +static volatile int static_var2 = 6; +int var2 = -1; /* 8-byte aligned .rodata */ const volatile long rovar2; @@ -21,7 +21,7 @@ static __noinline int subprog(int x) SEC("raw_tp/sys_enter") int handler2(const void *ctx) { - var2 = subprog(rovar2) + static_var2 + static_var22; + var2 = subprog(rovar2) + static_var1 + static_var2; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_subprogs.c b/tools/testing/selftests/bpf/progs/test_subprogs.c index d3c5673c0218..b7c37ca09544 100644 --- a/tools/testing/selftests/bpf/progs/test_subprogs.c +++ b/tools/testing/selftests/bpf/progs/test_subprogs.c @@ -4,8 +4,18 @@ const char LICENSE[] SEC("license") = "GPL"; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, __u64); +} array SEC(".maps"); + __noinline int sub1(int x) { + int key = 0; + + bpf_map_lookup_elem(&array, &key); return x + 1; } @@ -23,6 +33,9 @@ static __noinline int sub3(int z) static __noinline int sub4(int w) { + int key = 0; + + bpf_map_lookup_elem(&array, &key); return w + sub3(5) + sub1(6); } diff --git a/tools/testing/selftests/bpf/progs/test_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c new file mode 100644 index 000000000000..18a3a7ed924a --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +/* Dummy prog to test TC-BPF API */ + +SEC("classifier") +int cls(struct __sk_buff *skb) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/trace_printk.c b/tools/testing/selftests/bpf/progs/trace_printk.c index 8ca7f399b670..119582aa105a 100644 --- a/tools/testing/selftests/bpf/progs/trace_printk.c +++ b/tools/testing/selftests/bpf/progs/trace_printk.c @@ -10,11 +10,11 @@ char _license[] SEC("license") = "GPL"; int trace_printk_ret = 0; int trace_printk_ran = 0; -SEC("tp/raw_syscalls/sys_enter") +const char fmt[] = "Testing,testing %d\n"; + +SEC("fentry/__x64_sys_nanosleep") int sys_enter(void *ctx) { - static const char fmt[] = "testing,testing %d\n"; - trace_printk_ret = bpf_trace_printk(fmt, sizeof(fmt), ++trace_printk_ran); return 0; diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c new file mode 100644 index 000000000000..880debcbcd65 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0 +#define KBUILD_MODNAME "foo" +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +/* One map use devmap, another one use devmap_hash for testing */ +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(int)); + __uint(max_entries, 1024); +} map_all SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP_HASH); + __uint(key_size, sizeof(int)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 128); +} map_egress SEC(".maps"); + +/* map to store egress interfaces mac addresses */ +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, __u32); + __type(value, __be64); + __uint(max_entries, 128); +} mac_map SEC(".maps"); + +SEC("xdp_redirect_map_multi") +int xdp_redirect_map_multi_prog(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + int if_index = ctx->ingress_ifindex; + struct ethhdr *eth = data; + __u16 h_proto; + __u64 nh_off; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return XDP_DROP; + + h_proto = eth->h_proto; + + /* Using IPv4 for (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) testing */ + if (h_proto == bpf_htons(ETH_P_IP)) + return bpf_redirect_map(&map_all, 0, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS); + /* Using IPv6 for none flag testing */ + else if (h_proto == bpf_htons(ETH_P_IPV6)) + return bpf_redirect_map(&map_all, if_index, 0); + /* All others for BPF_F_BROADCAST testing */ + else + return bpf_redirect_map(&map_all, 0, BPF_F_BROADCAST); +} + +/* The following 2 progs are for 2nd devmap prog testing */ +SEC("xdp_redirect_map_ingress") +int xdp_redirect_map_all_prog(struct xdp_md *ctx) +{ + return bpf_redirect_map(&map_egress, 0, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS); +} + +SEC("xdp_devmap/map_prog") +int xdp_devmap_prog(struct xdp_md *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + __u32 key = ctx->egress_ifindex; + struct ethhdr *eth = data; + __u64 nh_off; + __be64 *mac; + + nh_off = sizeof(*eth); + if (data + nh_off > data_end) + return XDP_DROP; + + mac = bpf_map_lookup_elem(&mac_map, &key); + if (mac) + __builtin_memcpy(eth->h_source, mac, ETH_ALEN); + + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_doc_build.sh b/tools/testing/selftests/bpf/test_doc_build.sh index 7eb940a7b2eb..ed12111cd2f0 100755 --- a/tools/testing/selftests/bpf/test_doc_build.sh +++ b/tools/testing/selftests/bpf/test_doc_build.sh @@ -1,5 +1,6 @@ #!/bin/bash # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +set -e # Assume script is located under tools/testing/selftests/bpf/. We want to start # build attempts from the top of kernel repository. diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index 6a5349f9eb14..7e9049fa3edf 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -231,6 +231,14 @@ static void test_lru_sanity0(int map_type, int map_flags) assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 && errno == ENOENT); + /* lookup elem key=1 and delete it, then check it doesn't exist */ + key = 1; + assert(!bpf_map_lookup_and_delete_elem(lru_map_fd, &key, &value)); + assert(value[0] == 1234); + + /* remove the same element from the expected map */ + assert(!bpf_map_delete_elem(expected_map_fd, &key)); + assert(map_equal(lru_map_fd, expected_map_fd)); close(expected_map_fd); diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 51adc42b2b40..30cbf5d98f7d 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -53,23 +53,30 @@ static void test_hashmap(unsigned int task, void *data) value = 0; /* BPF_NOEXIST means add new element if it doesn't exist. */ - assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) < 0 && /* key=1 already exists. */ errno == EEXIST); /* -1 is an invalid flag. */ - assert(bpf_map_update_elem(fd, &key, &value, -1) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, -1) < 0 && errno == EINVAL); /* Check that key=1 can be found. */ assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 1234); key = 2; + value = 1234; + /* Insert key=2 element. */ + assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0); + + /* Check that key=2 matches the value and delete it */ + assert(bpf_map_lookup_and_delete_elem(fd, &key, &value) == 0 && value == 1234); + /* Check that key=2 is not found. */ - assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT); + assert(bpf_map_lookup_elem(fd, &key, &value) < 0 && errno == ENOENT); /* BPF_EXIST means update existing element. */ - assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) < 0 && /* key=2 is not there. */ errno == ENOENT); @@ -80,7 +87,7 @@ static void test_hashmap(unsigned int task, void *data) * inserted due to max_entries limit. */ key = 0; - assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) < 0 && errno == E2BIG); /* Update existing element, though the map is full. */ @@ -89,12 +96,12 @@ static void test_hashmap(unsigned int task, void *data) key = 2; assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0); key = 3; - assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) < 0 && errno == E2BIG); /* Check that key = 0 doesn't exist. */ key = 0; - assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT); + assert(bpf_map_delete_elem(fd, &key) < 0 && errno == ENOENT); /* Iterate over two elements. */ assert(bpf_map_get_next_key(fd, NULL, &first_key) == 0 && @@ -104,7 +111,7 @@ static void test_hashmap(unsigned int task, void *data) assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 && (next_key == 1 || next_key == 2) && (next_key != first_key)); - assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 && + assert(bpf_map_get_next_key(fd, &next_key, &next_key) < 0 && errno == ENOENT); /* Delete both elements. */ @@ -112,13 +119,13 @@ static void test_hashmap(unsigned int task, void *data) assert(bpf_map_delete_elem(fd, &key) == 0); key = 2; assert(bpf_map_delete_elem(fd, &key) == 0); - assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT); + assert(bpf_map_delete_elem(fd, &key) < 0 && errno == ENOENT); key = 0; /* Check that map is empty. */ - assert(bpf_map_get_next_key(fd, NULL, &next_key) == -1 && + assert(bpf_map_get_next_key(fd, NULL, &next_key) < 0 && errno == ENOENT); - assert(bpf_map_get_next_key(fd, &key, &next_key) == -1 && + assert(bpf_map_get_next_key(fd, &key, &next_key) < 0 && errno == ENOENT); close(fd); @@ -166,15 +173,25 @@ static void test_hashmap_percpu(unsigned int task, void *data) /* Insert key=1 element. */ assert(!(expected_key_mask & key)); assert(bpf_map_update_elem(fd, &key, value, BPF_ANY) == 0); + + /* Lookup and delete elem key=1 and check value. */ + assert(bpf_map_lookup_and_delete_elem(fd, &key, value) == 0 && + bpf_percpu(value,0) == 100); + + for (i = 0; i < nr_cpus; i++) + bpf_percpu(value,i) = i + 100; + + /* Insert key=1 element which should not exist. */ + assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == 0); expected_key_mask |= key; /* BPF_NOEXIST means add new element if it doesn't exist. */ - assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) < 0 && /* key=1 already exists. */ errno == EEXIST); /* -1 is an invalid flag. */ - assert(bpf_map_update_elem(fd, &key, value, -1) == -1 && + assert(bpf_map_update_elem(fd, &key, value, -1) < 0 && errno == EINVAL); /* Check that key=1 can be found. Value could be 0 if the lookup @@ -186,10 +203,10 @@ static void test_hashmap_percpu(unsigned int task, void *data) key = 2; /* Check that key=2 is not found. */ - assert(bpf_map_lookup_elem(fd, &key, value) == -1 && errno == ENOENT); + assert(bpf_map_lookup_elem(fd, &key, value) < 0 && errno == ENOENT); /* BPF_EXIST means update existing element. */ - assert(bpf_map_update_elem(fd, &key, value, BPF_EXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, value, BPF_EXIST) < 0 && /* key=2 is not there. */ errno == ENOENT); @@ -202,11 +219,11 @@ static void test_hashmap_percpu(unsigned int task, void *data) * inserted due to max_entries limit. */ key = 0; - assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, value, BPF_NOEXIST) < 0 && errno == E2BIG); /* Check that key = 0 doesn't exist. */ - assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT); + assert(bpf_map_delete_elem(fd, &key) < 0 && errno == ENOENT); /* Iterate over two elements. */ assert(bpf_map_get_next_key(fd, NULL, &first_key) == 0 && @@ -237,13 +254,13 @@ static void test_hashmap_percpu(unsigned int task, void *data) assert(bpf_map_delete_elem(fd, &key) == 0); key = 2; assert(bpf_map_delete_elem(fd, &key) == 0); - assert(bpf_map_delete_elem(fd, &key) == -1 && errno == ENOENT); + assert(bpf_map_delete_elem(fd, &key) < 0 && errno == ENOENT); key = 0; /* Check that map is empty. */ - assert(bpf_map_get_next_key(fd, NULL, &next_key) == -1 && + assert(bpf_map_get_next_key(fd, NULL, &next_key) < 0 && errno == ENOENT); - assert(bpf_map_get_next_key(fd, &key, &next_key) == -1 && + assert(bpf_map_get_next_key(fd, &key, &next_key) < 0 && errno == ENOENT); close(fd); @@ -360,7 +377,7 @@ static void test_arraymap(unsigned int task, void *data) assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0); value = 0; - assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) < 0 && errno == EEXIST); /* Check that key=1 can be found. */ @@ -374,11 +391,11 @@ static void test_arraymap(unsigned int task, void *data) * due to max_entries limit. */ key = 2; - assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_EXIST) < 0 && errno == E2BIG); /* Check that key = 2 doesn't exist. */ - assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT); + assert(bpf_map_lookup_elem(fd, &key, &value) < 0 && errno == ENOENT); /* Iterate over two elements. */ assert(bpf_map_get_next_key(fd, NULL, &next_key) == 0 && @@ -387,12 +404,12 @@ static void test_arraymap(unsigned int task, void *data) next_key == 0); assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 && next_key == 1); - assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 && + assert(bpf_map_get_next_key(fd, &next_key, &next_key) < 0 && errno == ENOENT); /* Delete shouldn't succeed. */ key = 1; - assert(bpf_map_delete_elem(fd, &key) == -1 && errno == EINVAL); + assert(bpf_map_delete_elem(fd, &key) < 0 && errno == EINVAL); close(fd); } @@ -418,7 +435,7 @@ static void test_arraymap_percpu(unsigned int task, void *data) assert(bpf_map_update_elem(fd, &key, values, BPF_ANY) == 0); bpf_percpu(values, 0) = 0; - assert(bpf_map_update_elem(fd, &key, values, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, values, BPF_NOEXIST) < 0 && errno == EEXIST); /* Check that key=1 can be found. */ @@ -433,11 +450,11 @@ static void test_arraymap_percpu(unsigned int task, void *data) /* Check that key=2 cannot be inserted due to max_entries limit. */ key = 2; - assert(bpf_map_update_elem(fd, &key, values, BPF_EXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, values, BPF_EXIST) < 0 && errno == E2BIG); /* Check that key = 2 doesn't exist. */ - assert(bpf_map_lookup_elem(fd, &key, values) == -1 && errno == ENOENT); + assert(bpf_map_lookup_elem(fd, &key, values) < 0 && errno == ENOENT); /* Iterate over two elements. */ assert(bpf_map_get_next_key(fd, NULL, &next_key) == 0 && @@ -446,12 +463,12 @@ static void test_arraymap_percpu(unsigned int task, void *data) next_key == 0); assert(bpf_map_get_next_key(fd, &next_key, &next_key) == 0 && next_key == 1); - assert(bpf_map_get_next_key(fd, &next_key, &next_key) == -1 && + assert(bpf_map_get_next_key(fd, &next_key, &next_key) < 0 && errno == ENOENT); /* Delete shouldn't succeed. */ key = 1; - assert(bpf_map_delete_elem(fd, &key) == -1 && errno == EINVAL); + assert(bpf_map_delete_elem(fd, &key) < 0 && errno == EINVAL); close(fd); } @@ -555,7 +572,7 @@ static void test_queuemap(unsigned int task, void *data) assert(bpf_map_update_elem(fd, NULL, &vals[i], 0) == 0); /* Check that element cannot be pushed due to max_entries limit */ - assert(bpf_map_update_elem(fd, NULL, &val, 0) == -1 && + assert(bpf_map_update_elem(fd, NULL, &val, 0) < 0 && errno == E2BIG); /* Peek element */ @@ -571,12 +588,12 @@ static void test_queuemap(unsigned int task, void *data) val == vals[i]); /* Check that there are not elements left */ - assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == -1 && + assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) < 0 && errno == ENOENT); /* Check that non supported functions set errno to EINVAL */ - assert(bpf_map_delete_elem(fd, NULL) == -1 && errno == EINVAL); - assert(bpf_map_get_next_key(fd, NULL, NULL) == -1 && errno == EINVAL); + assert(bpf_map_delete_elem(fd, NULL) < 0 && errno == EINVAL); + assert(bpf_map_get_next_key(fd, NULL, NULL) < 0 && errno == EINVAL); close(fd); } @@ -613,7 +630,7 @@ static void test_stackmap(unsigned int task, void *data) assert(bpf_map_update_elem(fd, NULL, &vals[i], 0) == 0); /* Check that element cannot be pushed due to max_entries limit */ - assert(bpf_map_update_elem(fd, NULL, &val, 0) == -1 && + assert(bpf_map_update_elem(fd, NULL, &val, 0) < 0 && errno == E2BIG); /* Peek element */ @@ -629,12 +646,12 @@ static void test_stackmap(unsigned int task, void *data) val == vals[i]); /* Check that there are not elements left */ - assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == -1 && + assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) < 0 && errno == ENOENT); /* Check that non supported functions set errno to EINVAL */ - assert(bpf_map_delete_elem(fd, NULL) == -1 && errno == EINVAL); - assert(bpf_map_get_next_key(fd, NULL, NULL) == -1 && errno == EINVAL); + assert(bpf_map_delete_elem(fd, NULL) < 0 && errno == EINVAL); + assert(bpf_map_get_next_key(fd, NULL, NULL) < 0 && errno == EINVAL); close(fd); } @@ -835,7 +852,7 @@ static void test_sockmap(unsigned int tasks, void *data) } bpf_map_rx = bpf_object__find_map_by_name(obj, "sock_map_rx"); - if (IS_ERR(bpf_map_rx)) { + if (!bpf_map_rx) { printf("Failed to load map rx from verdict prog\n"); goto out_sockmap; } @@ -847,7 +864,7 @@ static void test_sockmap(unsigned int tasks, void *data) } bpf_map_tx = bpf_object__find_map_by_name(obj, "sock_map_tx"); - if (IS_ERR(bpf_map_tx)) { + if (!bpf_map_tx) { printf("Failed to load map tx from verdict prog\n"); goto out_sockmap; } @@ -859,7 +876,7 @@ static void test_sockmap(unsigned int tasks, void *data) } bpf_map_msg = bpf_object__find_map_by_name(obj, "sock_map_msg"); - if (IS_ERR(bpf_map_msg)) { + if (!bpf_map_msg) { printf("Failed to load map msg from msg_verdict prog\n"); goto out_sockmap; } @@ -871,7 +888,7 @@ static void test_sockmap(unsigned int tasks, void *data) } bpf_map_break = bpf_object__find_map_by_name(obj, "sock_map_break"); - if (IS_ERR(bpf_map_break)) { + if (!bpf_map_break) { printf("Failed to load map tx from verdict prog\n"); goto out_sockmap; } @@ -1153,7 +1170,7 @@ static void test_map_in_map(void) } map = bpf_object__find_map_by_name(obj, "mim_array"); - if (IS_ERR(map)) { + if (!map) { printf("Failed to load array of maps from test prog\n"); goto out_map_in_map; } @@ -1164,7 +1181,7 @@ static void test_map_in_map(void) } map = bpf_object__find_map_by_name(obj, "mim_hash"); - if (IS_ERR(map)) { + if (!map) { printf("Failed to load hash of maps from test prog\n"); goto out_map_in_map; } @@ -1177,7 +1194,7 @@ static void test_map_in_map(void) bpf_object__load(obj); map = bpf_object__find_map_by_name(obj, "mim_array"); - if (IS_ERR(map)) { + if (!map) { printf("Failed to load array of maps from test prog\n"); goto out_map_in_map; } @@ -1194,7 +1211,7 @@ static void test_map_in_map(void) } map = bpf_object__find_map_by_name(obj, "mim_hash"); - if (IS_ERR(map)) { + if (!map) { printf("Failed to load hash of maps from test prog\n"); goto out_map_in_map; } @@ -1246,7 +1263,7 @@ static void test_map_large(void) } key.c = -1; - assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) < 0 && errno == E2BIG); /* Iterate through all elements. */ @@ -1254,12 +1271,12 @@ static void test_map_large(void) key.c = -1; for (i = 0; i < MAP_SIZE; i++) assert(bpf_map_get_next_key(fd, &key, &key) == 0); - assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT); + assert(bpf_map_get_next_key(fd, &key, &key) < 0 && errno == ENOENT); key.c = 0; assert(bpf_map_lookup_elem(fd, &key, &value) == 0 && value == 0); key.a = 1; - assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT); + assert(bpf_map_lookup_elem(fd, &key, &value) < 0 && errno == ENOENT); close(fd); } @@ -1391,7 +1408,7 @@ static void test_map_parallel(void) run_parallel(TASKS, test_update_delete, data); /* Check that key=0 is already there. */ - assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST) < 0 && errno == EEXIST); /* Check that all elements were inserted. */ @@ -1399,7 +1416,7 @@ static void test_map_parallel(void) key = -1; for (i = 0; i < MAP_SIZE; i++) assert(bpf_map_get_next_key(fd, &key, &key) == 0); - assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT); + assert(bpf_map_get_next_key(fd, &key, &key) < 0 && errno == ENOENT); /* Another check for all elements */ for (i = 0; i < MAP_SIZE; i++) { @@ -1415,8 +1432,8 @@ static void test_map_parallel(void) /* Nothing should be left. */ key = -1; - assert(bpf_map_get_next_key(fd, NULL, &key) == -1 && errno == ENOENT); - assert(bpf_map_get_next_key(fd, &key, &key) == -1 && errno == ENOENT); + assert(bpf_map_get_next_key(fd, NULL, &key) < 0 && errno == ENOENT); + assert(bpf_map_get_next_key(fd, &key, &key) < 0 && errno == ENOENT); } static void test_map_rdonly(void) @@ -1434,12 +1451,12 @@ static void test_map_rdonly(void) key = 1; value = 1234; /* Try to insert key=1 element. */ - assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == -1 && + assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) < 0 && errno == EPERM); /* Check that key=1 is not found. */ - assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == ENOENT); - assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == ENOENT); + assert(bpf_map_lookup_elem(fd, &key, &value) < 0 && errno == ENOENT); + assert(bpf_map_get_next_key(fd, &key, &value) < 0 && errno == ENOENT); close(fd); } @@ -1462,8 +1479,8 @@ static void test_map_wronly_hash(void) assert(bpf_map_update_elem(fd, &key, &value, BPF_ANY) == 0); /* Check that reading elements and keys from the map is not allowed. */ - assert(bpf_map_lookup_elem(fd, &key, &value) == -1 && errno == EPERM); - assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == EPERM); + assert(bpf_map_lookup_elem(fd, &key, &value) < 0 && errno == EPERM); + assert(bpf_map_get_next_key(fd, &key, &value) < 0 && errno == EPERM); close(fd); } @@ -1490,10 +1507,10 @@ static void test_map_wronly_stack_or_queue(enum bpf_map_type map_type) assert(bpf_map_update_elem(fd, NULL, &value, BPF_ANY) == 0); /* Peek element should fail */ - assert(bpf_map_lookup_elem(fd, NULL, &value) == -1 && errno == EPERM); + assert(bpf_map_lookup_elem(fd, NULL, &value) < 0 && errno == EPERM); /* Pop element should fail */ - assert(bpf_map_lookup_and_delete_elem(fd, NULL, &value) == -1 && + assert(bpf_map_lookup_and_delete_elem(fd, NULL, &value) < 0 && errno == EPERM); close(fd); @@ -1547,7 +1564,7 @@ static void prepare_reuseport_grp(int type, int map_fd, size_t map_elem_size, value = &fd32; } err = bpf_map_update_elem(map_fd, &index0, value, BPF_ANY); - CHECK(err != -1 || errno != EINVAL, + CHECK(err >= 0 || errno != EINVAL, "reuseport array update unbound sk", "sock_type:%d err:%d errno:%d\n", type, err, errno); @@ -1576,7 +1593,7 @@ static void prepare_reuseport_grp(int type, int map_fd, size_t map_elem_size, */ err = bpf_map_update_elem(map_fd, &index0, value, BPF_ANY); - CHECK(err != -1 || errno != EINVAL, + CHECK(err >= 0 || errno != EINVAL, "reuseport array update non-listening sk", "sock_type:%d err:%d errno:%d\n", type, err, errno); @@ -1606,31 +1623,31 @@ static void test_reuseport_array(void) map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, sizeof(__u32), sizeof(__u64), array_size, 0); - CHECK(map_fd == -1, "reuseport array create", + CHECK(map_fd < 0, "reuseport array create", "map_fd:%d, errno:%d\n", map_fd, errno); /* Test lookup/update/delete with invalid index */ err = bpf_map_delete_elem(map_fd, &bad_index); - CHECK(err != -1 || errno != E2BIG, "reuseport array del >=max_entries", + CHECK(err >= 0 || errno != E2BIG, "reuseport array del >=max_entries", "err:%d errno:%d\n", err, errno); err = bpf_map_update_elem(map_fd, &bad_index, &fd64, BPF_ANY); - CHECK(err != -1 || errno != E2BIG, + CHECK(err >= 0 || errno != E2BIG, "reuseport array update >=max_entries", "err:%d errno:%d\n", err, errno); err = bpf_map_lookup_elem(map_fd, &bad_index, &map_cookie); - CHECK(err != -1 || errno != ENOENT, + CHECK(err >= 0 || errno != ENOENT, "reuseport array update >=max_entries", "err:%d errno:%d\n", err, errno); /* Test lookup/delete non existence elem */ err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie); - CHECK(err != -1 || errno != ENOENT, + CHECK(err >= 0 || errno != ENOENT, "reuseport array lookup not-exist elem", "err:%d errno:%d\n", err, errno); err = bpf_map_delete_elem(map_fd, &index3); - CHECK(err != -1 || errno != ENOENT, + CHECK(err >= 0 || errno != ENOENT, "reuseport array del not-exist elem", "err:%d errno:%d\n", err, errno); @@ -1644,7 +1661,7 @@ static void test_reuseport_array(void) /* BPF_EXIST failure case */ err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx], BPF_EXIST); - CHECK(err != -1 || errno != ENOENT, + CHECK(err >= 0 || errno != ENOENT, "reuseport array update empty elem BPF_EXIST", "sock_type:%d err:%d errno:%d\n", type, err, errno); @@ -1653,7 +1670,7 @@ static void test_reuseport_array(void) /* BPF_NOEXIST success case */ err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx], BPF_NOEXIST); - CHECK(err == -1, + CHECK(err < 0, "reuseport array update empty elem BPF_NOEXIST", "sock_type:%d err:%d errno:%d\n", type, err, errno); @@ -1662,7 +1679,7 @@ static void test_reuseport_array(void) /* BPF_EXIST success case. */ err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx], BPF_EXIST); - CHECK(err == -1, + CHECK(err < 0, "reuseport array update same elem BPF_EXIST", "sock_type:%d err:%d errno:%d\n", type, err, errno); fds_idx = REUSEPORT_FD_IDX(err, fds_idx); @@ -1670,7 +1687,7 @@ static void test_reuseport_array(void) /* BPF_NOEXIST failure case */ err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx], BPF_NOEXIST); - CHECK(err != -1 || errno != EEXIST, + CHECK(err >= 0 || errno != EEXIST, "reuseport array update non-empty elem BPF_NOEXIST", "sock_type:%d err:%d errno:%d\n", type, err, errno); @@ -1679,7 +1696,7 @@ static void test_reuseport_array(void) /* BPF_ANY case (always succeed) */ err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx], BPF_ANY); - CHECK(err == -1, + CHECK(err < 0, "reuseport array update same sk with BPF_ANY", "sock_type:%d err:%d errno:%d\n", type, err, errno); @@ -1688,32 +1705,32 @@ static void test_reuseport_array(void) /* The same sk cannot be added to reuseport_array twice */ err = bpf_map_update_elem(map_fd, &index3, &fd64, BPF_ANY); - CHECK(err != -1 || errno != EBUSY, + CHECK(err >= 0 || errno != EBUSY, "reuseport array update same sk with same index", "sock_type:%d err:%d errno:%d\n", type, err, errno); err = bpf_map_update_elem(map_fd, &index0, &fd64, BPF_ANY); - CHECK(err != -1 || errno != EBUSY, + CHECK(err >= 0 || errno != EBUSY, "reuseport array update same sk with different index", "sock_type:%d err:%d errno:%d\n", type, err, errno); /* Test delete elem */ err = bpf_map_delete_elem(map_fd, &index3); - CHECK(err == -1, "reuseport array delete sk", + CHECK(err < 0, "reuseport array delete sk", "sock_type:%d err:%d errno:%d\n", type, err, errno); /* Add it back with BPF_NOEXIST */ err = bpf_map_update_elem(map_fd, &index3, &fd64, BPF_NOEXIST); - CHECK(err == -1, + CHECK(err < 0, "reuseport array re-add with BPF_NOEXIST after del", "sock_type:%d err:%d errno:%d\n", type, err, errno); /* Test cookie */ err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie); - CHECK(err == -1 || sk_cookie != map_cookie, + CHECK(err < 0 || sk_cookie != map_cookie, "reuseport array lookup re-added sk", "sock_type:%d err:%d errno:%d sk_cookie:0x%llx map_cookie:0x%llxn", type, err, errno, sk_cookie, map_cookie); @@ -1722,7 +1739,7 @@ static void test_reuseport_array(void) for (f = 0; f < ARRAY_SIZE(grpa_fds64); f++) close(grpa_fds64[f]); err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie); - CHECK(err != -1 || errno != ENOENT, + CHECK(err >= 0 || errno != ENOENT, "reuseport array lookup after close()", "sock_type:%d err:%d errno:%d\n", type, err, errno); @@ -1733,7 +1750,7 @@ static void test_reuseport_array(void) CHECK(fd64 == -1, "socket(SOCK_RAW)", "err:%d errno:%d\n", err, errno); err = bpf_map_update_elem(map_fd, &index3, &fd64, BPF_NOEXIST); - CHECK(err != -1 || errno != ENOTSUPP, "reuseport array update SOCK_RAW", + CHECK(err >= 0 || errno != ENOTSUPP, "reuseport array update SOCK_RAW", "err:%d errno:%d\n", err, errno); close(fd64); @@ -1743,16 +1760,16 @@ static void test_reuseport_array(void) /* Test 32 bit fd */ map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, sizeof(__u32), sizeof(__u32), array_size, 0); - CHECK(map_fd == -1, "reuseport array create", + CHECK(map_fd < 0, "reuseport array create", "map_fd:%d, errno:%d\n", map_fd, errno); prepare_reuseport_grp(SOCK_STREAM, map_fd, sizeof(__u32), &fd64, &sk_cookie, 1); fd = fd64; err = bpf_map_update_elem(map_fd, &index3, &fd, BPF_NOEXIST); - CHECK(err == -1, "reuseport array update 32 bit fd", + CHECK(err < 0, "reuseport array update 32 bit fd", "err:%d errno:%d\n", err, errno); err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie); - CHECK(err != -1 || errno != ENOSPC, + CHECK(err >= 0 || errno != ENOSPC, "reuseport array lookup 32 bit fd", "err:%d errno:%d\n", err, errno); close(fd); @@ -1798,6 +1815,8 @@ int main(void) { srand(time(NULL)); + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + map_flags = 0; run_all_tests(); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 6396932b97e2..6f103106a39b 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -737,6 +737,9 @@ int main(int argc, char **argv) if (err) return err; + /* Use libbpf 1.0 API mode */ + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + libbpf_set_print(libbpf_print_fn); srand(time(NULL)); diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index dda52cb649dc..8ef7f334e715 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -249,16 +249,17 @@ extern int test__join_cgroup(const char *path); #define ASSERT_OK_PTR(ptr, name) ({ \ static int duration = 0; \ const void *___res = (ptr); \ - bool ___ok = !IS_ERR_OR_NULL(___res); \ - CHECK(!___ok, (name), \ - "unexpected error: %ld\n", PTR_ERR(___res)); \ + int ___err = libbpf_get_error(___res); \ + bool ___ok = ___err == 0; \ + CHECK(!___ok, (name), "unexpected error: %d\n", ___err); \ ___ok; \ }) #define ASSERT_ERR_PTR(ptr, name) ({ \ static int duration = 0; \ const void *___res = (ptr); \ - bool ___ok = IS_ERR(___res); \ + int ___err = libbpf_get_error(___res); \ + bool ___ok = ___err != 0; \ CHECK(!___ok, (name), "unexpected pointer: %p\n", ___res); \ ___ok; \ }) diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c index 73da7fe8c152..4a39304cc5a6 100644 --- a/tools/testing/selftests/bpf/test_tcpnotify_user.c +++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c @@ -82,6 +82,8 @@ int main(int argc, char **argv) cpu_set_t cpuset; __u32 key = 0; + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + CPU_ZERO(&cpuset); CPU_SET(0, &cpuset); pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset); @@ -116,7 +118,7 @@ int main(int argc, char **argv) pb_opts.sample_cb = dummyfn; pb = perf_buffer__new(bpf_map__fd(perf_map), 8, &pb_opts); - if (IS_ERR(pb)) + if (!pb) goto err; pthread_create(&tid, NULL, poller_thread, pb); @@ -163,7 +165,6 @@ err: bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS); close(cg_fd); cleanup_cgroup_environment(); - if (!IS_ERR_OR_NULL(pb)) - perf_buffer__free(pb); + perf_buffer__free(pb); return error; } diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh new file mode 100755 index 000000000000..1538373157e3 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh @@ -0,0 +1,204 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test topology: +# - - - - - - - - - - - - - - - - - - - - - - - - - +# | veth1 veth2 veth3 | ... init net +# - -| - - - - - - | - - - - - - | - - +# --------- --------- --------- +# | veth0 | | veth0 | | veth0 | ... +# --------- --------- --------- +# ns1 ns2 ns3 +# +# Test modules: +# XDP modes: generic, native, native + egress_prog +# +# Test cases: +# ARP: Testing BPF_F_BROADCAST, the ingress interface also should receive +# the redirects. +# ns1 -> gw: ns1, ns2, ns3, should receive the arp request +# IPv4: Testing BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, the ingress +# interface should not receive the redirects. +# ns1 -> gw: ns1 should not receive, ns2, ns3 should receive redirects. +# IPv6: Testing none flag, all the pkts should be redirected back +# ping test: ns1 -> ns2 (block), echo requests will be redirect back +# egress_prog: +# all src mac should be egress interface's mac + +# netns numbers +NUM=3 +IFACES="" +DRV_MODE="xdpgeneric xdpdrv xdpegress" +PASS=0 +FAIL=0 + +test_pass() +{ + echo "Pass: $@" + PASS=$((PASS + 1)) +} + +test_fail() +{ + echo "fail: $@" + FAIL=$((FAIL + 1)) +} + +clean_up() +{ + for i in $(seq $NUM); do + ip link del veth$i 2> /dev/null + ip netns del ns$i 2> /dev/null + done +} + +# Kselftest framework requirement - SKIP code is 4. +check_env() +{ + ip link set dev lo xdpgeneric off &>/dev/null + if [ $? -ne 0 ];then + echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support" + exit 4 + fi + + which tcpdump &>/dev/null + if [ $? -ne 0 ];then + echo "selftests: [SKIP] Could not run test without tcpdump" + exit 4 + fi +} + +setup_ns() +{ + local mode=$1 + IFACES="" + + if [ "$mode" = "xdpegress" ]; then + mode="xdpdrv" + fi + + for i in $(seq $NUM); do + ip netns add ns$i + ip link add veth$i type veth peer name veth0 netns ns$i + ip link set veth$i up + ip -n ns$i link set veth0 up + + ip -n ns$i addr add 192.0.2.$i/24 dev veth0 + ip -n ns$i addr add 2001:db8::$i/64 dev veth0 + # Add a neigh entry for IPv4 ping test + ip -n ns$i neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0 + ip -n ns$i link set veth0 $mode obj \ + xdp_dummy.o sec xdp_dummy &> /dev/null || \ + { test_fail "Unable to load dummy xdp" && exit 1; } + IFACES="$IFACES veth$i" + veth_mac[$i]=$(ip link show veth$i | awk '/link\/ether/ {print $2}') + done +} + +do_egress_tests() +{ + local mode=$1 + + # mac test + ip netns exec ns2 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-2_${mode}.log & + ip netns exec ns3 tcpdump -e -i veth0 -nn -l -e &> mac_ns1-3_${mode}.log & + sleep 0.5 + ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null + sleep 0.5 + pkill -9 tcpdump + + # mac check + grep -q "${veth_mac[2]} > ff:ff:ff:ff:ff:ff" mac_ns1-2_${mode}.log && \ + test_pass "$mode mac ns1-2" || test_fail "$mode mac ns1-2" + grep -q "${veth_mac[3]} > ff:ff:ff:ff:ff:ff" mac_ns1-3_${mode}.log && \ + test_pass "$mode mac ns1-3" || test_fail "$mode mac ns1-3" +} + +do_ping_tests() +{ + local mode=$1 + + # ping6 test: echo request should be redirect back to itself, not others + ip netns exec ns1 ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02 + + ip netns exec ns1 tcpdump -i veth0 -nn -l -e &> ns1-1_${mode}.log & + ip netns exec ns2 tcpdump -i veth0 -nn -l -e &> ns1-2_${mode}.log & + ip netns exec ns3 tcpdump -i veth0 -nn -l -e &> ns1-3_${mode}.log & + sleep 0.5 + # ARP test + ip netns exec ns1 ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null + # IPv4 test + ip netns exec ns1 ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null + # IPv6 test + ip netns exec ns1 ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null + sleep 0.5 + pkill -9 tcpdump + + # All netns should receive the redirect arp requests + [ $(grep -c "who-has 192.0.2.254" ns1-1_${mode}.log) -gt 4 ] && \ + test_pass "$mode arp(F_BROADCAST) ns1-1" || \ + test_fail "$mode arp(F_BROADCAST) ns1-1" + [ $(grep -c "who-has 192.0.2.254" ns1-2_${mode}.log) -le 4 ] && \ + test_pass "$mode arp(F_BROADCAST) ns1-2" || \ + test_fail "$mode arp(F_BROADCAST) ns1-2" + [ $(grep -c "who-has 192.0.2.254" ns1-3_${mode}.log) -le 4 ] && \ + test_pass "$mode arp(F_BROADCAST) ns1-3" || \ + test_fail "$mode arp(F_BROADCAST) ns1-3" + + # ns1 should not receive the redirect echo request, others should + [ $(grep -c "ICMP echo request" ns1-1_${mode}.log) -eq 4 ] && \ + test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1" || \ + test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1" + [ $(grep -c "ICMP echo request" ns1-2_${mode}.log) -eq 4 ] && \ + test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2" || \ + test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2" + [ $(grep -c "ICMP echo request" ns1-3_${mode}.log) -eq 4 ] && \ + test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3" || \ + test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3" + + # ns1 should receive the echo request, ns2 should not + [ $(grep -c "ICMP6, echo request" ns1-1_${mode}.log) -eq 4 ] && \ + test_pass "$mode IPv6 (no flags) ns1-1" || \ + test_fail "$mode IPv6 (no flags) ns1-1" + [ $(grep -c "ICMP6, echo request" ns1-2_${mode}.log) -eq 0 ] && \ + test_pass "$mode IPv6 (no flags) ns1-2" || \ + test_fail "$mode IPv6 (no flags) ns1-2" +} + +do_tests() +{ + local mode=$1 + local drv_p + + case ${mode} in + xdpdrv) drv_p="-N";; + xdpegress) drv_p="-X";; + xdpgeneric) drv_p="-S";; + esac + + ./xdp_redirect_multi $drv_p $IFACES &> xdp_redirect_${mode}.log & + xdp_pid=$! + sleep 1 + + if [ "$mode" = "xdpegress" ]; then + do_egress_tests $mode + else + do_ping_tests $mode + fi + + kill $xdp_pid +} + +trap clean_up 0 2 3 6 9 + +check_env +rm -f xdp_redirect_*.log ns*.log mac_ns*.log + +for mode in ${DRV_MODE}; do + setup_ns $mode + do_tests $mode + clean_up +done + +echo "Summary: PASS $PASS, FAIL $FAIL" +[ $FAIL -eq 0 ] && exit 0 || exit 1 diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c new file mode 100644 index 000000000000..3696a8f32c23 --- /dev/null +++ b/tools/testing/selftests/bpf/xdp_redirect_multi.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "bpf_util.h" +#include +#include + +#define MAX_IFACE_NUM 32 +#define MAX_INDEX_NUM 1024 + +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static int ifaces[MAX_IFACE_NUM] = {}; + +static void int_exit(int sig) +{ + __u32 prog_id = 0; + int i; + + for (i = 0; ifaces[i] > 0; i++) { + if (bpf_get_link_xdp_id(ifaces[i], &prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id) + bpf_set_link_xdp_fd(ifaces[i], -1, xdp_flags); + } + + exit(0); +} + +static int get_mac_addr(unsigned int ifindex, void *mac_addr) +{ + char ifname[IF_NAMESIZE]; + struct ifreq ifr; + int fd, ret = -1; + + fd = socket(AF_INET, SOCK_DGRAM, 0); + if (fd < 0) + return ret; + + if (!if_indextoname(ifindex, ifname)) + goto err_out; + + strcpy(ifr.ifr_name, ifname); + + if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0) + goto err_out; + + memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char)); + ret = 0; + +err_out: + close(fd); + return ret; +} + +static void usage(const char *prog) +{ + fprintf(stderr, + "usage: %s [OPTS] ...\n" + "OPTS:\n" + " -S use skb-mode\n" + " -N enforce native mode\n" + " -F force loading prog\n" + " -X load xdp program on egress\n", + prog); +} + +int main(int argc, char **argv) +{ + int prog_fd, group_all, mac_map; + struct bpf_program *ingress_prog, *egress_prog; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_UNSPEC, + }; + int i, ret, opt, egress_prog_fd = 0; + struct bpf_devmap_val devmap_val; + bool attach_egress_prog = false; + unsigned char mac_addr[6]; + char ifname[IF_NAMESIZE]; + struct bpf_object *obj; + unsigned int ifindex; + char filename[256]; + + while ((opt = getopt(argc, argv, "SNFX")) != -1) { + switch (opt) { + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'N': + /* default, set below */ + break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + case 'X': + attach_egress_prog = true; + break; + default: + usage(basename(argv[0])); + return 1; + } + } + + if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) { + xdp_flags |= XDP_FLAGS_DRV_MODE; + } else if (attach_egress_prog) { + printf("Load xdp program on egress with SKB mode not supported yet\n"); + goto err_out; + } + + if (optind == argc) { + printf("usage: %s ...\n", argv[0]); + goto err_out; + } + + printf("Get interfaces"); + for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) { + ifaces[i] = if_nametoindex(argv[optind + i]); + if (!ifaces[i]) + ifaces[i] = strtoul(argv[optind + i], NULL, 0); + if (!if_indextoname(ifaces[i], ifname)) { + perror("Invalid interface name or i"); + goto err_out; + } + if (ifaces[i] > MAX_INDEX_NUM) { + printf("Interface index to large\n"); + goto err_out; + } + printf(" %d", ifaces[i]); + } + printf("\n"); + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + goto err_out; + + if (attach_egress_prog) + group_all = bpf_object__find_map_fd_by_name(obj, "map_egress"); + else + group_all = bpf_object__find_map_fd_by_name(obj, "map_all"); + mac_map = bpf_object__find_map_fd_by_name(obj, "mac_map"); + + if (group_all < 0 || mac_map < 0) { + printf("bpf_object__find_map_fd_by_name failed\n"); + goto err_out; + } + + if (attach_egress_prog) { + /* Find ingress/egress prog for 2nd xdp prog */ + ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_all_prog"); + egress_prog = bpf_object__find_program_by_name(obj, "xdp_devmap_prog"); + if (!ingress_prog || !egress_prog) { + printf("finding ingress/egress_prog in obj file failed\n"); + goto err_out; + } + prog_fd = bpf_program__fd(ingress_prog); + egress_prog_fd = bpf_program__fd(egress_prog); + if (prog_fd < 0 || egress_prog_fd < 0) { + printf("find egress_prog fd failed\n"); + goto err_out; + } + } + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + /* Init forward multicast groups and exclude group */ + for (i = 0; ifaces[i] > 0; i++) { + ifindex = ifaces[i]; + + if (attach_egress_prog) { + ret = get_mac_addr(ifindex, mac_addr); + if (ret < 0) { + printf("get interface %d mac failed\n", ifindex); + goto err_out; + } + ret = bpf_map_update_elem(mac_map, &ifindex, mac_addr, 0); + if (ret) { + perror("bpf_update_elem mac_map failed\n"); + goto err_out; + } + } + + /* Add all the interfaces to group all */ + devmap_val.ifindex = ifindex; + devmap_val.bpf_prog.fd = egress_prog_fd; + ret = bpf_map_update_elem(group_all, &ifindex, &devmap_val, 0); + if (ret) { + perror("bpf_map_update_elem"); + goto err_out; + } + + /* bind prog_fd to each interface */ + ret = bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags); + if (ret) { + printf("Set xdp fd failed on %d\n", ifindex); + goto err_out; + } + } + + /* sleep some time for testing */ + sleep(999); + + return 0; + +err_out: + return 1; +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh index 4029833f7e27..160891dcb4bc 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh @@ -109,6 +109,9 @@ router_destroy() __addr_add_del $rp1 del 192.0.2.2/24 2001:db8:1::2/64 tc qdisc del dev $rp2 clsact + + ip link set dev $rp2 down + ip link set dev $rp1 down } setup_prepare() diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh index 42d44e27802c..190c1b6b5365 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh @@ -111,6 +111,9 @@ router_destroy() __addr_add_del $rp1 del 192.0.2.2/24 2001:db8:1::2/64 tc qdisc del dev $rp2 clsact + + ip link set dev $rp2 down + ip link set dev $rp1 down } setup_prepare() diff --git a/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh index 65f43a7ce9c9..1e9a4aff76a2 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/port_scale.sh @@ -7,6 +7,8 @@ PORT_NUM_NETIFS=0 +declare -a unsplit + port_setup_prepare() { : @@ -20,12 +22,12 @@ port_cleanup() devlink port unsplit $port check_err $? "Did not unsplit $netdev" done + unsplit=() } split_all_ports() { local should_fail=$1; shift - local -a unsplit # Loop over the splittable netdevs and create tuples of netdev along # with its width. For example: diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh index 5cbff8038f84..28a570006d4d 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh @@ -93,7 +93,9 @@ switch_destroy() lldptool -T -i $swp1 -V APP -d $(dscp_map 10) >/dev/null lldpad_app_wait_del + ip link set dev $swp2 down ip link set dev $swp2 nomaster + ip link set dev $swp1 down ip link set dev $swp1 nomaster ip link del dev br1 } diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh index 27de3d9ed08e..f4493ef9cca1 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh @@ -29,37 +29,38 @@ cleanup() get_prio_pg() { - __mlnx_qos -i $swp | sed -n '/^PFC/,/^[^[:space:]]/p' | - grep buffer | sed 's/ \+/ /g' | cut -d' ' -f 2- + # Produces a string of numbers " ... ", where BX is number + # of buffer that priority X is mapped to. + dcb -j buffer show dev $swp | + jq -r '[.prio_buffer | .[] | tostring + " "] | add' } get_prio_pfc() { - __mlnx_qos -i $swp | sed -n '/^PFC/,/^[^[:space:]]/p' | - grep enabled | sed 's/ \+/ /g' | cut -d' ' -f 2- + # Produces a string of numbers " ... ", where PX denotes + # whether priority X has PFC enabled (the value is 1) or disabled (0). + dcb -j pfc show dev $swp | + jq -r '[.prio_pfc | .[] | if . then "1 " else "0 " end] | add' } get_prio_tc() { - __mlnx_qos -i $swp | sed -n '/^tc/,$p' | - awk '/^tc/ { TC = $2 } - /priority:/ { PRIO[$2]=TC } - END { - for (i in PRIO) - printf("%d ", PRIO[i]) - }' + # Produces a string of numbers " ... ", where TC is number + # of TC that priority X is mapped to. + dcb -j ets show dev $swp | + jq -r '[.prio_tc | .[] | tostring + " "] | add' } get_buf_size() { local idx=$1; shift - __mlnx_qos -i $swp | grep Receive | sed 's/.*: //' | cut -d, -f $((idx + 1)) + dcb -j buffer show dev $swp | jq ".buffer_size[$idx]" } get_tot_size() { - __mlnx_qos -i $swp | grep Receive | sed 's/.*total_size=//' + dcb -j buffer show dev $swp | jq '.total_size' } check_prio_pg() @@ -121,18 +122,18 @@ test_dcb_ets() { RET=0 - __mlnx_qos -i $swp --prio_tc=0,2,4,6,1,3,5,7 > /dev/null + dcb ets set dev $swp prio-tc 0:0 1:2 2:4 3:6 4:1 5:3 6:5 7:7 check_prio_pg "0 2 4 6 1 3 5 7 " check_prio_tc "0 2 4 6 1 3 5 7 " check_prio_pfc "0 0 0 0 0 0 0 0 " - __mlnx_qos -i $swp --prio_tc=0,0,0,0,0,0,0,0 > /dev/null + dcb ets set dev $swp prio-tc all:0 check_prio_pg "0 0 0 0 0 0 0 0 " check_prio_tc "0 0 0 0 0 0 0 0 " - __mlnx_qos -i $swp --prio2buffer=1,3,5,7,0,2,4,6 &> /dev/null + dcb buffer set dev $swp prio-buffer 0:1 1:3 2:5 3:7 4:0 5:2 6:4 7:6 2>/dev/null check_fail $? "prio2buffer accepted in DCB mode" log_test "Configuring headroom through ETS" @@ -174,7 +175,7 @@ test_pfc() { RET=0 - __mlnx_qos -i $swp --prio_tc=0,0,0,0,0,1,2,3 > /dev/null + dcb ets set dev $swp prio-tc all:0 5:1 6:2 7:3 local buf0size=$(get_buf_size 0) local buf1size=$(get_buf_size 1) @@ -193,7 +194,7 @@ test_pfc() RET=0 - __mlnx_qos -i $swp --pfc=0,0,0,0,0,1,1,1 --cable_len=0 > /dev/null + dcb pfc set dev $swp prio-pfc all:off 5:on 6:on 7:on delay 0 check_prio_pg "0 0 0 0 0 1 2 3 " check_prio_pfc "0 0 0 0 0 1 1 1 " @@ -210,7 +211,7 @@ test_pfc() RET=0 - __mlnx_qos -i $swp --pfc=0,0,0,0,0,1,1,1 --cable_len=1000 > /dev/null + dcb pfc set dev $swp delay 1000 check_buf_size 0 "== $buf0size" check_buf_size 1 "> $buf1size" @@ -221,8 +222,8 @@ test_pfc() RET=0 - __mlnx_qos -i $swp --pfc=0,0,0,0,0,0,0,0 --cable_len=0 > /dev/null - __mlnx_qos -i $swp --prio_tc=0,0,0,0,0,0,0,0 > /dev/null + dcb pfc set dev $swp prio-pfc all:off delay 0 + dcb ets set dev $swp prio-tc all:0 check_prio_pg "0 0 0 0 0 0 0 0 " check_prio_tc "0 0 0 0 0 0 0 0 " @@ -242,13 +243,13 @@ test_tc_priomap() { RET=0 - __mlnx_qos -i $swp --prio_tc=0,1,2,3,4,5,6,7 > /dev/null + dcb ets set dev $swp prio-tc 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7 check_prio_pg "0 1 2 3 4 5 6 7 " tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M check_prio_pg "0 0 0 0 0 0 0 0 " - __mlnx_qos -i $swp --prio2buffer=1,3,5,7,0,2,4,6 > /dev/null + dcb buffer set dev $swp prio-buffer 0:1 1:3 2:5 3:7 4:0 5:2 6:4 7:6 check_prio_pg "1 3 5 7 0 2 4 6 " tc qdisc delete dev $swp root @@ -256,9 +257,9 @@ test_tc_priomap() # Clean up. tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M - __mlnx_qos -i $swp --prio2buffer=0,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp prio-buffer all:0 tc qdisc delete dev $swp root - __mlnx_qos -i $swp --prio_tc=0,0,0,0,0,0,0,0 > /dev/null + dcb ets set dev $swp prio-tc all:0 log_test "TC: priomap" } @@ -270,12 +271,12 @@ test_tc_sizes() RET=0 - __mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 &> /dev/null + dcb buffer set dev $swp buffer-size all:0 0:$size 2>/dev/null check_fail $? "buffer_size should fail before qdisc is added" tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M - __mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 0:$size check_err $? "buffer_size should pass after qdisc is added" check_buf_size 0 "== $size" "set size: " @@ -283,26 +284,26 @@ test_tc_sizes() check_buf_size 0 "== $size" "set MTU: " mtu_restore $swp - __mlnx_qos -i $swp --buffer_size=0,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 # After replacing the qdisc for the same kind, buffer_size still has to # work. tc qdisc replace dev $swp root handle 1: bfifo limit 1M - __mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 0:$size check_buf_size 0 "== $size" "post replace, set size: " - __mlnx_qos -i $swp --buffer_size=0,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 # Likewise after replacing for a different kind. tc qdisc replace dev $swp root handle 2: prio bands 8 - __mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 0:$size check_buf_size 0 "== $size" "post replace different kind, set size: " tc qdisc delete dev $swp root - __mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 &> /dev/null + dcb buffer set dev $swp buffer-size all:0 0:$size 2>/dev/null check_fail $? "buffer_size should fail after qdisc is deleted" log_test "TC: buffer size" @@ -363,10 +364,10 @@ test_tc_int_buf() tc qdisc replace dev $swp root handle 1: bfifo limit 1.5M test_int_buf "TC: " - __mlnx_qos -i $swp --buffer_size=$size,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 0:$size test_int_buf "TC+buffsize: " - __mlnx_qos -i $swp --buffer_size=0,0,0,0,0,0,0,0 > /dev/null + dcb buffer set dev $swp buffer-size all:0 tc qdisc delete dev $swp root } diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh index 0bf76f13c030..faa51012cdac 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh @@ -82,17 +82,3 @@ bail_on_lldpad() fi fi } - -__mlnx_qos() -{ - local err - - mlnx_qos "$@" 2>/dev/null - err=$? - - if ((err)); then - echo "Error ($err) in mlnx_qos $@" >/dev/stderr - fi - - return $err -} diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh index 5c7700212f75..5d5622fc2758 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh @@ -171,7 +171,7 @@ switch_create() # assignment. tc qdisc replace dev $swp1 root handle 1: \ ets bands 8 strict 8 priomap 7 6 - __mlnx_qos -i $swp1 --prio2buffer=0,1,0,0,0,0,0,0 >/dev/null + dcb buffer set dev $swp1 prio-buffer all:0 1:1 # $swp2 # ----- @@ -209,8 +209,8 @@ switch_create() # the lossless prio into a buffer of its own. Don't bother with buffer # sizes though, there is not going to be any pressure in the "backward" # direction. - __mlnx_qos -i $swp3 --prio2buffer=0,1,0,0,0,0,0,0 >/dev/null - __mlnx_qos -i $swp3 --pfc=0,1,0,0,0,0,0,0 >/dev/null + dcb buffer set dev $swp3 prio-buffer all:0 1:1 + dcb pfc set dev $swp3 prio-pfc all:off 1:on # $swp4 # ----- @@ -226,11 +226,11 @@ switch_create() # Configure qdisc so that we can hand-tune headroom. tc qdisc replace dev $swp4 root handle 1: \ ets bands 8 strict 8 priomap 7 6 - __mlnx_qos -i $swp4 --prio2buffer=0,1,0,0,0,0,0,0 >/dev/null - __mlnx_qos -i $swp4 --pfc=0,1,0,0,0,0,0,0 >/dev/null + dcb buffer set dev $swp4 prio-buffer all:0 1:1 + dcb pfc set dev $swp4 prio-pfc all:off 1:on # PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which # is (-2*MTU) about 80K of delay provision. - __mlnx_qos -i $swp4 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null + dcb buffer set dev $swp4 buffer-size all:0 1:$_100KB # bridges # ------- @@ -273,9 +273,9 @@ switch_destroy() # $swp4 # ----- - __mlnx_qos -i $swp4 --buffer_size=0,0,0,0,0,0,0,0 >/dev/null - __mlnx_qos -i $swp4 --pfc=0,0,0,0,0,0,0,0 >/dev/null - __mlnx_qos -i $swp4 --prio2buffer=0,0,0,0,0,0,0,0 >/dev/null + dcb buffer set dev $swp4 buffer-size all:0 + dcb pfc set dev $swp4 prio-pfc all:off + dcb buffer set dev $swp4 prio-buffer all:0 tc qdisc del dev $swp4 root devlink_tc_bind_pool_th_restore $swp4 1 ingress @@ -288,8 +288,8 @@ switch_destroy() # $swp3 # ----- - __mlnx_qos -i $swp3 --pfc=0,0,0,0,0,0,0,0 >/dev/null - __mlnx_qos -i $swp3 --prio2buffer=0,0,0,0,0,0,0,0 >/dev/null + dcb pfc set dev $swp3 prio-pfc all:off + dcb buffer set dev $swp3 prio-buffer all:0 tc qdisc del dev $swp3 root devlink_tc_bind_pool_th_restore $swp3 1 egress @@ -315,7 +315,7 @@ switch_destroy() # $swp1 # ----- - __mlnx_qos -i $swp1 --prio2buffer=0,0,0,0,0,0,0,0 >/dev/null + dcb buffer set dev $swp1 prio-buffer all:0 tc qdisc del dev $swp1 root devlink_tc_bind_pool_th_restore $swp1 1 ingress diff --git a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh index e93878d42596..683759d29199 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh @@ -68,7 +68,7 @@ wait_for_routes() local t0=$1; shift local route_count=$1; shift - local t1=$(ip route | grep -o 'offload' | wc -l) + local t1=$(ip route | grep 'offload' | grep -v 'offload_failed' | wc -l) local delta=$((t1 - t0)) echo $delta [[ $delta -ge $route_count ]] diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh index 093bed088ad0..373d5f2a846e 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh @@ -234,15 +234,15 @@ __tc_sample_rate_test() psample_capture_start - ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \ + ip vrf exec v$h1 $MZ $h1 -c 320000 -d 100usec -p 64 -A 192.0.2.1 \ -B $dip -t udp dp=52768,sp=42768 -q psample_capture_stop pkts=$(grep -e "group 1 " $CAPTURE_FILE | wc -l) - pct=$((100 * (pkts - 100) / 100)) + pct=$((100 * (pkts - 10000) / 10000)) (( -25 <= pct && pct <= 25)) - check_err $? "Expected 100 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%" + check_err $? "Expected 10000 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%" log_test "tc sample rate ($desc)" @@ -587,15 +587,15 @@ __tc_sample_acl_rate_test() psample_capture_start - ip vrf exec v$h1 $MZ $h1 -c 3200 -d 1msec -p 64 -A 192.0.2.1 \ + ip vrf exec v$h1 $MZ $h1 -c 320000 -d 100usec -p 64 -A 192.0.2.1 \ -B 198.51.100.1 -t udp dp=52768,sp=42768 -q psample_capture_stop pkts=$(grep -e "group 1 " $CAPTURE_FILE | wc -l) - pct=$((100 * (pkts - 100) / 100)) + pct=$((100 * (pkts - 10000) / 10000)) (( -25 <= pct && pct <= 25)) - check_err $? "Expected 100 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%" + check_err $? "Expected 10000 packets, got $pkts packets, which is $pct% off. Required accuracy is +-25%" # Setup a filter that should not match any packet and make sure packets # are not sampled. diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index 40909c254365..9de1d123f4f5 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -5,12 +5,13 @@ lib_dir=$(dirname $0)/../../../net/forwarding ALL_TESTS="fw_flash_test params_test regions_test reload_test \ netns_reload_test resource_test dev_info_test \ - empty_reporter_test dummy_reporter_test" + empty_reporter_test dummy_reporter_test rate_test" NUM_NETIFS=0 source $lib_dir/lib.sh BUS_ADDR=10 PORT_COUNT=4 +VF_COUNT=4 DEV_NAME=netdevsim$BUS_ADDR SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV_NAME/net/ DEBUGFS_DIR=/sys/kernel/debug/netdevsim/$DEV_NAME/ @@ -507,6 +508,170 @@ dummy_reporter_test() log_test "dummy reporter test" } +rate_leafs_get() +{ + local handle=$1 + + cmd_jq "devlink port function rate show -j" \ + '.[] | to_entries | .[] | select(.value.type == "leaf") | .key | select(contains("'$handle'"))' +} + +rate_nodes_get() +{ + local handle=$1 + + cmd_jq "devlink port function rate show -j" \ + '.[] | to_entries | .[] | select(.value.type == "node") | .key | select(contains("'$handle'"))' +} + +rate_attr_set() +{ + local handle=$1 + local name=$2 + local value=$3 + local units=$4 + + devlink port function rate set $handle $name $value$units +} + +rate_attr_get() +{ + local handle=$1 + local name=$2 + + cmd_jq "devlink port function rate show $handle -j" '.[][].'$name +} + +rate_attr_tx_rate_check() +{ + local handle=$1 + local name=$2 + local rate=$3 + local debug_file=$4 + + rate_attr_set $handle $name $rate mbit + check_err $? "Failed to set $name value" + + local debug_value=$(cat $debug_file) + check_err $? "Failed to read $name value from debugfs" + [ "$debug_value" == "$rate" ] + check_err $? "Unexpected $name debug value $debug_value != $rate" + + local api_value=$(( $(rate_attr_get $handle $name) * 8 / 1000000 )) + check_err $? "Failed to get $name attr value" + [ "$api_value" == "$rate" ] + check_err $? "Unexpected $name attr value $api_value != $rate" +} + +rate_attr_parent_check() +{ + local handle=$1 + local parent=$2 + local debug_file=$3 + + rate_attr_set $handle parent $parent + check_err $? "Failed to set parent" + + debug_value=$(cat $debug_file) + check_err $? "Failed to get parent debugfs value" + [ "$debug_value" == "$parent" ] + check_err $? "Unexpected parent debug value $debug_value != $parent" + + api_value=$(rate_attr_get $r_obj parent) + check_err $? "Failed to get parent attr value" + [ "$api_value" == "$parent" ] + check_err $? "Unexpected parent attr value $api_value != $parent" +} + +rate_node_add() +{ + local handle=$1 + + devlink port function rate add $handle +} + +rate_node_del() +{ + local handle=$1 + + devlink port function rate del $handle +} + +rate_test() +{ + RET=0 + + echo $VF_COUNT > /sys/bus/netdevsim/devices/$DEV_NAME/sriov_numvfs + devlink dev eswitch set $DL_HANDLE mode switchdev + local leafs=`rate_leafs_get $DL_HANDLE` + local num_leafs=`echo $leafs | wc -w` + [ "$num_leafs" == "$VF_COUNT" ] + check_err $? "Expected $VF_COUNT rate leafs but got $num_leafs" + + rate=10 + for r_obj in $leafs + do + rate_attr_tx_rate_check $r_obj tx_share $rate \ + $DEBUGFS_DIR/ports/${r_obj##*/}/tx_share + rate=$(($rate+10)) + done + + rate=100 + for r_obj in $leafs + do + rate_attr_tx_rate_check $r_obj tx_max $rate \ + $DEBUGFS_DIR/ports/${r_obj##*/}/tx_max + rate=$(($rate+100)) + done + + local node1_name='group1' + local node1="$DL_HANDLE/$node1_name" + rate_node_add "$node1" + check_err $? "Failed to add node $node1" + + local num_nodes=`rate_nodes_get $DL_HANDLE | wc -w` + [ $num_nodes == 1 ] + check_err $? "Expected 1 rate node in output but got $num_nodes" + + local node_tx_share=10 + rate_attr_tx_rate_check $node1 tx_share $node_tx_share \ + $DEBUGFS_DIR/rate_nodes/${node1##*/}/tx_share + + local node_tx_max=100 + rate_attr_tx_rate_check $node1 tx_max $node_tx_max \ + $DEBUGFS_DIR/rate_nodes/${node1##*/}/tx_max + + rate_node_del "$node1" + check_err $? "Failed to delete node $node1" + local num_nodes=`rate_nodes_get $DL_HANDLE | wc -w` + [ $num_nodes == 0 ] + check_err $? "Expected 0 rate node but got $num_nodes" + + local node1_name='group1' + local node1="$DL_HANDLE/$node1_name" + rate_node_add "$node1" + check_err $? "Failed to add node $node1" + + rate_attr_parent_check $r_obj $node1_name \ + $DEBUGFS_DIR/ports/${r_obj##*/}/rate_parent + + local node2_name='group2' + local node2="$DL_HANDLE/$node2_name" + rate_node_add "$node2" + check_err $? "Failed to add node $node2" + + rate_attr_parent_check $node2 $node1_name \ + $DEBUGFS_DIR/rate_nodes/$node2_name/rate_parent + rate_node_del "$node2" + check_err $? "Failed to delete node $node2" + rate_attr_set "$r_obj" noparent + check_err $? "Failed to unset $r_obj parent node" + rate_node_del "$node1" + check_err $? "Failed to delete node $node1" + + log_test "rate test" +} + setup_prepare() { modprobe netdevsim diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh index da49ad2761b5..109900c817be 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink_trap.sh @@ -24,13 +24,15 @@ ALL_TESTS=" NETDEVSIM_PATH=/sys/bus/netdevsim/ DEV_ADDR=1337 DEV=netdevsim${DEV_ADDR} -DEVLINK_DEV=netdevsim/${DEV} DEBUGFS_DIR=/sys/kernel/debug/netdevsim/$DEV/ SLEEP_TIME=1 NETDEV="" NUM_NETIFS=0 source $lib_dir/lib.sh + +DEVLINK_DEV= source $lib_dir/devlink_lib.sh +DEVLINK_DEV=netdevsim/${DEV} require_command udevadm @@ -163,6 +165,16 @@ trap_stats_test() devlink_trap_action_set $trap_name "drop" devlink_trap_stats_idle_test $trap_name check_err $? "Stats of trap $trap_name not idle when action is drop" + + echo "y"> $DEBUGFS_DIR/fail_trap_drop_counter_get + devlink -s trap show $DEVLINK_DEV trap $trap_name &> /dev/null + check_fail $? "Managed to read trap (hard dropped) statistics when should not" + echo "n"> $DEBUGFS_DIR/fail_trap_drop_counter_get + devlink -s trap show $DEVLINK_DEV trap $trap_name &> /dev/null + check_err $? "Did not manage to read trap (hard dropped) statistics when should" + + devlink_trap_drop_stats_idle_test $trap_name + check_fail $? "Drop stats of trap $trap_name idle when should not" else devlink_trap_stats_idle_test $trap_name check_fail $? "Stats of non-drop trap $trap_name idle when should not" diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib.sh b/tools/testing/selftests/drivers/net/netdevsim/fib.sh index 251f228ce63e..fc794cd30389 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/fib.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/fib.sh @@ -33,13 +33,15 @@ ALL_TESTS=" NETDEVSIM_PATH=/sys/bus/netdevsim/ DEV_ADDR=1337 DEV=netdevsim${DEV_ADDR} -DEVLINK_DEV=netdevsim/${DEV} SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/ NUM_NETIFS=0 source $lib_dir/lib.sh -source $lib_dir/devlink_lib.sh source $lib_dir/fib_offload_lib.sh +DEVLINK_DEV= +source $lib_dir/devlink_lib.sh +DEVLINK_DEV=netdevsim/${DEV} + ipv4_identical_routes() { fib_ipv4_identical_routes_test "testns1" diff --git a/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh index ba75c81cda91..e8e0dc088d6a 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh @@ -44,12 +44,14 @@ ALL_TESTS=" NETDEVSIM_PATH=/sys/bus/netdevsim/ DEV_ADDR=1337 DEV=netdevsim${DEV_ADDR} -DEVLINK_DEV=netdevsim/${DEV} SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/ DEBUGFS_NET_DIR=/sys/kernel/debug/netdevsim/$DEV/ NUM_NETIFS=0 source $lib_dir/lib.sh + +DEVLINK_DEV= source $lib_dir/devlink_lib.sh +DEVLINK_DEV=netdevsim/${DEV} nexthop_check() { diff --git a/tools/testing/selftests/drivers/net/netdevsim/psample.sh b/tools/testing/selftests/drivers/net/netdevsim/psample.sh index ee10b1a8933c..e689ff7a0b12 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/psample.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/psample.sh @@ -14,13 +14,15 @@ ALL_TESTS=" NETDEVSIM_PATH=/sys/bus/netdevsim/ DEV_ADDR=1337 DEV=netdevsim${DEV_ADDR} -DEVLINK_DEV=netdevsim/${DEV} SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/ PSAMPLE_DIR=/sys/kernel/debug/netdevsim/$DEV/psample/ CAPTURE_FILE=$(mktemp) NUM_NETIFS=0 source $lib_dir/lib.sh + +DEVLINK_DEV= source $lib_dir/devlink_lib.sh +DEVLINK_DEV=netdevsim/${DEV} # Available at https://github.com/Mellanox/libpsample require_command psample diff --git a/tools/testing/selftests/lib/Makefile b/tools/testing/selftests/lib/Makefile index a105f094676e..ee71fc99d5b5 100644 --- a/tools/testing/selftests/lib/Makefile +++ b/tools/testing/selftests/lib/Makefile @@ -4,6 +4,6 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests" all: -TEST_PROGS := printf.sh bitmap.sh prime_numbers.sh strscpy.sh +TEST_PROGS := printf.sh bitmap.sh prime_numbers.sh scanf.sh strscpy.sh include ../lib.mk diff --git a/tools/testing/selftests/lib/config b/tools/testing/selftests/lib/config index b80ee3f6e265..645839b50b0a 100644 --- a/tools/testing/selftests/lib/config +++ b/tools/testing/selftests/lib/config @@ -1,4 +1,5 @@ CONFIG_TEST_PRINTF=m +CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_PRIME_NUMBERS=m CONFIG_TEST_STRSCPY=m diff --git a/tools/testing/selftests/lib/scanf.sh b/tools/testing/selftests/lib/scanf.sh new file mode 100755 index 000000000000..b59b8ba561c3 --- /dev/null +++ b/tools/testing/selftests/lib/scanf.sh @@ -0,0 +1,4 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# Tests the scanf infrastructure using test_scanf kernel module. +$(dirname $0)/../kselftest/module.sh "scanf" test_scanf diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index 4e94e566e040..f31205f04ee0 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -136,6 +136,10 @@ struct mount_attr { #define MOUNT_ATTR_IDMAP 0x00100000 #endif +#ifndef MOUNT_ATTR_NOSYMFOLLOW +#define MOUNT_ATTR_NOSYMFOLLOW 0x00200000 +#endif + static inline int sys_mount_setattr(int dfd, const char *path, unsigned int flags, struct mount_attr *attr, size_t size) { @@ -235,6 +239,10 @@ static int prepare_unpriv_mountns(void) return 0; } +#ifndef ST_NOSYMFOLLOW +#define ST_NOSYMFOLLOW 0x2000 /* do not follow symlinks */ +#endif + static int read_mnt_flags(const char *path) { int ret; @@ -245,9 +253,9 @@ static int read_mnt_flags(const char *path) if (ret != 0) return -EINVAL; - if (stat.f_flag & - ~(ST_RDONLY | ST_NOSUID | ST_NODEV | ST_NOEXEC | ST_NOATIME | - ST_NODIRATIME | ST_RELATIME | ST_SYNCHRONOUS | ST_MANDLOCK)) + if (stat.f_flag & ~(ST_RDONLY | ST_NOSUID | ST_NODEV | ST_NOEXEC | + ST_NOATIME | ST_NODIRATIME | ST_RELATIME | + ST_SYNCHRONOUS | ST_MANDLOCK | ST_NOSYMFOLLOW)) return -EINVAL; mnt_flags = 0; @@ -269,6 +277,8 @@ static int read_mnt_flags(const char *path) mnt_flags |= MS_SYNCHRONOUS; if (stat.f_flag & ST_MANDLOCK) mnt_flags |= ST_MANDLOCK; + if (stat.f_flag & ST_NOSYMFOLLOW) + mnt_flags |= ST_NOSYMFOLLOW; return mnt_flags; } @@ -368,8 +378,13 @@ static bool mount_setattr_supported(void) FIXTURE(mount_setattr) { }; +#define NOSYMFOLLOW_TARGET "/mnt/A/AA/data" +#define NOSYMFOLLOW_SYMLINK "/mnt/A/AA/symlink" + FIXTURE_SETUP(mount_setattr) { + int fd = -EBADF; + if (!mount_setattr_supported()) SKIP(return, "mount_setattr syscall not supported"); @@ -412,6 +427,11 @@ FIXTURE_SETUP(mount_setattr) ASSERT_EQ(mount("testing", "/tmp/B/BB", "devpts", MS_RELATIME | MS_NOEXEC | MS_RDONLY, 0), 0); + + fd = creat(NOSYMFOLLOW_TARGET, O_RDWR | O_CLOEXEC); + ASSERT_GT(fd, 0); + ASSERT_EQ(symlink(NOSYMFOLLOW_TARGET, NOSYMFOLLOW_SYMLINK), 0); + ASSERT_EQ(close(fd), 0); } FIXTURE_TEARDOWN(mount_setattr) @@ -1421,4 +1441,66 @@ TEST_F(mount_setattr_idmapped, idmap_mount_tree_invalid) ASSERT_EQ(expected_uid_gid(open_tree_fd, "B/BB/b", 0, 0, 0), 0); } +TEST_F(mount_setattr, mount_attr_nosymfollow) +{ + int fd; + unsigned int old_flags = 0, new_flags = 0, expected_flags = 0; + struct mount_attr attr = { + .attr_set = MOUNT_ATTR_NOSYMFOLLOW, + }; + + if (!mount_setattr_supported()) + SKIP(return, "mount_setattr syscall not supported"); + + fd = open(NOSYMFOLLOW_SYMLINK, O_RDWR | O_CLOEXEC); + ASSERT_GT(fd, 0); + ASSERT_EQ(close(fd), 0); + + old_flags = read_mnt_flags("/mnt/A"); + ASSERT_GT(old_flags, 0); + + ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0); + + expected_flags = old_flags; + expected_flags |= ST_NOSYMFOLLOW; + + new_flags = read_mnt_flags("/mnt/A"); + ASSERT_EQ(new_flags, expected_flags); + + new_flags = read_mnt_flags("/mnt/A/AA"); + ASSERT_EQ(new_flags, expected_flags); + + new_flags = read_mnt_flags("/mnt/A/AA/B"); + ASSERT_EQ(new_flags, expected_flags); + + new_flags = read_mnt_flags("/mnt/A/AA/B/BB"); + ASSERT_EQ(new_flags, expected_flags); + + fd = open(NOSYMFOLLOW_SYMLINK, O_RDWR | O_CLOEXEC); + ASSERT_LT(fd, 0); + ASSERT_EQ(errno, ELOOP); + + attr.attr_set &= ~MOUNT_ATTR_NOSYMFOLLOW; + attr.attr_clr |= MOUNT_ATTR_NOSYMFOLLOW; + + ASSERT_EQ(sys_mount_setattr(-1, "/mnt/A", AT_RECURSIVE, &attr, sizeof(attr)), 0); + + expected_flags &= ~ST_NOSYMFOLLOW; + new_flags = read_mnt_flags("/mnt/A"); + ASSERT_EQ(new_flags, expected_flags); + + new_flags = read_mnt_flags("/mnt/A/AA"); + ASSERT_EQ(new_flags, expected_flags); + + new_flags = read_mnt_flags("/mnt/A/AA/B"); + ASSERT_EQ(new_flags, expected_flags); + + new_flags = read_mnt_flags("/mnt/A/AA/B/BB"); + ASSERT_EQ(new_flags, expected_flags); + + fd = open(NOSYMFOLLOW_SYMLINK, O_RDWR | O_CLOEXEC); + ASSERT_GT(fd, 0); + ASSERT_EQ(close(fd), 0); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 61ae899cfc17..19deb9cdf72f 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -30,3 +30,4 @@ hwtstamp_config rxtimestamp timestamping txtimestamp +so_netns_cookie diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 3915bb7bfc39..79c9eb0034d5 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -30,7 +30,7 @@ TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag -TEST_GEN_FILES += so_txtime ipv6_flowlabel ipv6_flowlabel_mgr +TEST_GEN_FILES += so_txtime ipv6_flowlabel ipv6_flowlabel_mgr so_netns_cookie TEST_GEN_FILES += tcp_fastopen_backup_key TEST_GEN_FILES += fin_ack_lat TEST_GEN_FILES += reuseaddr_ports_exhausted diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 614d5477365a..6f905b53904f 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -1,4 +1,5 @@ CONFIG_USER_NS=y +CONFIG_NET_NS=y CONFIG_BPF_SYSCALL=y CONFIG_TEST_BPF=m CONFIG_NUMA=y diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/net/devlink_port_split.py index 834066d465fc..2b5d6ff87373 100755 --- a/tools/testing/selftests/net/devlink_port_split.py +++ b/tools/testing/selftests/net/devlink_port_split.py @@ -18,6 +18,8 @@ import sys # +# Kselftest framework requirement - SKIP code is 4 +KSFT_SKIP=4 Port = collections.namedtuple('Port', 'bus_info name') @@ -239,7 +241,11 @@ def main(cmdline=None): assert stderr == "" devs = json.loads(stdout)['dev'] - dev = list(devs.keys())[0] + if devs: + dev = list(devs.keys())[0] + else: + print("no devlink device was found, test skipped") + sys.exit(KSFT_SKIP) cmd = "devlink dev show %s" % dev stdout, stderr = run_command(cmd) diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 49774a8a7736..0d293391e9a4 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -925,6 +925,14 @@ ipv6_fcnal_runtime() run_cmd "$IP nexthop add id 86 via 2001:db8:91::2 dev veth1" run_cmd "$IP ro add 2001:db8:101::1/128 nhid 81" + # route can not use prefsrc with nexthops + run_cmd "$IP ro add 2001:db8:101::2/128 nhid 86 from 2001:db8:91::1" + log_test $? 2 "IPv6 route can not use src routing with external nexthop" + + # check cleanup path on invalid metric + run_cmd "$IP ro add 2001:db8:101::2/128 nhid 86 congctl lock foo" + log_test $? 2 "IPv6 route with invalid metric" + # rpfilter and default route $IP nexthop flush >/dev/null 2>&1 run_cmd "ip netns exec me ip6tables -t mangle -I PREROUTING 1 -m rpfilter --invert -j DROP" @@ -1366,6 +1374,10 @@ ipv4_fcnal_runtime() run_cmd "$IP nexthop replace id 22 via 172.16.2.2 dev veth3" log_test $? 2 "Nexthop replace with invalid scope for existing route" + # check cleanup path on invalid metric + run_cmd "$IP ro add 172.16.101.2/32 nhid 22 congctl lock foo" + log_test $? 2 "IPv4 route with invalid metric" + # # add route with nexthop and check traffic # diff --git a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh new file mode 100755 index 000000000000..a15d21dc035a --- /dev/null +++ b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh @@ -0,0 +1,364 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test traffic distribution between two paths when using custom hash policy. +# +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.{2-253}/24 | | +# | 2001:db8:1::{2-fd}/64 | | +# +-------------------------|------+ +# | +# +-------------------------|-------------------------+ +# | SW1 | | +# | $rp1 + | +# | 198.51.100.1/24 | +# | 2001:db8:1::1/64 | +# | | +# | | +# | $rp11 + + $rp12 | +# | 192.0.2.1/28 | | 192.0.2.17/28 | +# | 2001:db8:2::1/64 | | 2001:db8:3::1/64 | +# +------------------|-------------|------------------+ +# | | +# +------------------|-------------|------------------+ +# | SW2 | | | +# | | | | +# | $rp21 + + $rp22 | +# | 192.0.2.2/28 192.0.2.18/28 | +# | 2001:db8:2::2/64 2001:db8:3::2/64 | +# | | +# | | +# | $rp2 + | +# | 203.0.113.1/24 | | +# | 2001:db8:4::1/64 | | +# +-------------------------|-------------------------+ +# | +# +-------------------------|------+ +# | H2 | | +# | $h2 + | +# | 203.0.113.{2-253}/24 | +# | 2001:db8:4::{2-fd}/64 | +# +--------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + custom_hash +" + +NUM_NETIFS=8 +source lib.sh + +h1_create() +{ + simple_if_init $h1 198.51.100.2/24 2001:db8:1::2/64 + ip route add vrf v$h1 default via 198.51.100.1 dev $h1 + ip -6 route add vrf v$h1 default via 2001:db8:1::1 dev $h1 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 default + ip route del vrf v$h1 default + simple_if_fini $h1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw1_create() +{ + simple_if_init $rp1 198.51.100.1/24 2001:db8:1::1/64 + __simple_if_init $rp11 v$rp1 192.0.2.1/28 2001:db8:2::1/64 + __simple_if_init $rp12 v$rp1 192.0.2.17/28 2001:db8:3::1/64 + + ip route add vrf v$rp1 203.0.113.0/24 \ + nexthop via 192.0.2.2 dev $rp11 \ + nexthop via 192.0.2.18 dev $rp12 + + ip -6 route add vrf v$rp1 2001:db8:4::/64 \ + nexthop via 2001:db8:2::2 dev $rp11 \ + nexthop via 2001:db8:3::2 dev $rp12 +} + +sw1_destroy() +{ + ip -6 route del vrf v$rp1 2001:db8:4::/64 + + ip route del vrf v$rp1 203.0.113.0/24 + + __simple_if_fini $rp12 192.0.2.17/28 2001:db8:3::1/64 + __simple_if_fini $rp11 192.0.2.1/28 2001:db8:2::1/64 + simple_if_fini $rp1 198.51.100.1/24 2001:db8:1::1/64 +} + +sw2_create() +{ + simple_if_init $rp2 203.0.113.1/24 2001:db8:4::1/64 + __simple_if_init $rp21 v$rp2 192.0.2.2/28 2001:db8:2::2/64 + __simple_if_init $rp22 v$rp2 192.0.2.18/28 2001:db8:3::2/64 + + ip route add vrf v$rp2 198.51.100.0/24 \ + nexthop via 192.0.2.1 dev $rp21 \ + nexthop via 192.0.2.17 dev $rp22 + + ip -6 route add vrf v$rp2 2001:db8:1::/64 \ + nexthop via 2001:db8:2::1 dev $rp21 \ + nexthop via 2001:db8:3::1 dev $rp22 +} + +sw2_destroy() +{ + ip -6 route del vrf v$rp2 2001:db8:1::/64 + + ip route del vrf v$rp2 198.51.100.0/24 + + __simple_if_fini $rp22 192.0.2.18/28 2001:db8:3::2/64 + __simple_if_fini $rp21 192.0.2.2/28 2001:db8:2::2/64 + simple_if_fini $rp2 203.0.113.1/24 2001:db8:4::1/64 +} + +h2_create() +{ + simple_if_init $h2 203.0.113.2/24 2001:db8:4::2/64 + ip route add vrf v$h2 default via 203.0.113.1 dev $h2 + ip -6 route add vrf v$h2 default via 2001:db8:4::1 dev $h2 +} + +h2_destroy() +{ + ip -6 route del vrf v$h2 default + ip route del vrf v$h2 default + simple_if_fini $h2 203.0.113.2/24 2001:db8:4::2/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + + rp1=${NETIFS[p2]} + + rp11=${NETIFS[p3]} + rp21=${NETIFS[p4]} + + rp12=${NETIFS[p5]} + rp22=${NETIFS[p6]} + + rp2=${NETIFS[p7]} + + h2=${NETIFS[p8]} + + vrf_prepare + h1_create + sw1_create + sw2_create + h2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + h2_destroy + sw2_destroy + sw1_destroy + h1_destroy + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 203.0.113.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:4::2 +} + +send_src_ipv4() +{ + $MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_dst_ipv4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_src_udp4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + -d 1msec -t udp "sp=0-32768,dp=30000" +} + +send_dst_udp4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + -d 1msec -t udp "sp=20000,dp=0-32768" +} + +send_src_ipv6() +{ + $MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:4::2 \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_dst_ipv6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:4::2-2001:db8:4::fd" \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_flowlabel() +{ + # Generate 16384 echo requests, each with a random flow label. + for _ in $(seq 1 16384); do + ip vrf exec v$h1 \ + $PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1 + done +} + +send_src_udp6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:4::2 \ + -d 1msec -t udp "sp=0-32768,dp=30000" +} + +send_dst_udp6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:4::2 \ + -d 1msec -t udp "sp=20000,dp=0-32768" +} + +custom_hash_test() +{ + local field="$1"; shift + local balanced="$1"; shift + local send_flows="$@" + + RET=0 + + local t0_rp11=$(link_stats_tx_packets_get $rp11) + local t0_rp12=$(link_stats_tx_packets_get $rp12) + + $send_flows + + local t1_rp11=$(link_stats_tx_packets_get $rp11) + local t1_rp12=$(link_stats_tx_packets_get $rp12) + + local d_rp11=$((t1_rp11 - t0_rp11)) + local d_rp12=$((t1_rp12 - t0_rp12)) + + local diff=$((d_rp12 - d_rp11)) + local sum=$((d_rp11 + d_rp12)) + + local pct=$(echo "$diff / $sum * 100" | bc -l) + local is_balanced=$(echo "-20 <= $pct && $pct <= 20" | bc) + + [[ ( $is_balanced -eq 1 && $balanced == "balanced" ) || + ( $is_balanced -eq 0 && $balanced == "unbalanced" ) ]] + check_err $? "Expected traffic to be $balanced, but it is not" + + log_test "Multipath hash field: $field ($balanced)" + log_info "Packets sent on path1 / path2: $d_rp11 / $d_rp12" +} + +custom_hash_v4() +{ + log_info "Running IPv4 custom multipath hash tests" + + sysctl_set net.ipv4.fib_multipath_hash_policy 3 + + # Prevent the neighbour table from overflowing, as different neighbour + # entries will be created on $ol4 when using different destination IPs. + sysctl_set net.ipv4.neigh.default.gc_thresh1 1024 + sysctl_set net.ipv4.neigh.default.gc_thresh2 1024 + sysctl_set net.ipv4.neigh.default.gc_thresh3 1024 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0001 + custom_hash_test "Source IP" "balanced" send_src_ipv4 + custom_hash_test "Source IP" "unbalanced" send_dst_ipv4 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0002 + custom_hash_test "Destination IP" "balanced" send_dst_ipv4 + custom_hash_test "Destination IP" "unbalanced" send_src_ipv4 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0010 + custom_hash_test "Source port" "balanced" send_src_udp4 + custom_hash_test "Source port" "unbalanced" send_dst_udp4 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0020 + custom_hash_test "Destination port" "balanced" send_dst_udp4 + custom_hash_test "Destination port" "unbalanced" send_src_udp4 + + sysctl_restore net.ipv4.neigh.default.gc_thresh3 + sysctl_restore net.ipv4.neigh.default.gc_thresh2 + sysctl_restore net.ipv4.neigh.default.gc_thresh1 + + sysctl_restore net.ipv4.fib_multipath_hash_policy +} + +custom_hash_v6() +{ + log_info "Running IPv6 custom multipath hash tests" + + sysctl_set net.ipv6.fib_multipath_hash_policy 3 + + # Prevent the neighbour table from overflowing, as different neighbour + # entries will be created on $ol4 when using different destination IPs. + sysctl_set net.ipv6.neigh.default.gc_thresh1 1024 + sysctl_set net.ipv6.neigh.default.gc_thresh2 1024 + sysctl_set net.ipv6.neigh.default.gc_thresh3 1024 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0001 + custom_hash_test "Source IP" "balanced" send_src_ipv6 + custom_hash_test "Source IP" "unbalanced" send_dst_ipv6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0002 + custom_hash_test "Destination IP" "balanced" send_dst_ipv6 + custom_hash_test "Destination IP" "unbalanced" send_src_ipv6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0008 + custom_hash_test "Flowlabel" "balanced" send_flowlabel + custom_hash_test "Flowlabel" "unbalanced" send_src_ipv6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0010 + custom_hash_test "Source port" "balanced" send_src_udp6 + custom_hash_test "Source port" "unbalanced" send_dst_udp6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0020 + custom_hash_test "Destination port" "balanced" send_dst_udp6 + custom_hash_test "Destination port" "unbalanced" send_src_udp6 + + sysctl_restore net.ipv6.neigh.default.gc_thresh3 + sysctl_restore net.ipv6.neigh.default.gc_thresh2 + sysctl_restore net.ipv6.neigh.default.gc_thresh1 + + sysctl_restore net.ipv6.fib_multipath_hash_policy +} + +custom_hash() +{ + # Test that when the hash policy is set to custom, traffic is + # distributed only according to the fields set in the + # fib_multipath_hash_fields sysctl. + # + # Each time set a different field and make sure traffic is only + # distributed when the field is changed in the packet stream. + custom_hash_v4 + custom_hash_v6 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 9c12c4fd3afc..13d3d4428a32 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -18,6 +18,12 @@ if [[ ! -v DEVLINK_DEV ]]; then DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \ -n | cut -d" " -f3) +elif [[ ! -z "$DEVLINK_DEV" ]]; then + devlink dev show $DEVLINK_DEV &> /dev/null + if [ $? -ne 0 ]; then + echo "SKIP: devlink device \"$DEVLINK_DEV\" not found" + exit 1 + fi fi ############################################################################## @@ -318,6 +324,14 @@ devlink_trap_rx_bytes_get() | jq '.[][][]["stats"]["rx"]["bytes"]' } +devlink_trap_drop_packets_get() +{ + local trap_name=$1; shift + + devlink -js trap show $DEVLINK_DEV trap $trap_name \ + | jq '.[][][]["stats"]["rx"]["dropped"]' +} + devlink_trap_stats_idle_test() { local trap_name=$1; shift @@ -339,6 +353,24 @@ devlink_trap_stats_idle_test() fi } +devlink_trap_drop_stats_idle_test() +{ + local trap_name=$1; shift + local t0_packets t0_bytes + + t0_packets=$(devlink_trap_drop_packets_get $trap_name) + + sleep 1 + + t1_packets=$(devlink_trap_drop_packets_get $trap_name) + + if [[ $t0_packets -eq $t1_packets ]]; then + return 0 + else + return 1 + fi +} + devlink_traps_enable_all() { local trap_name diff --git a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh new file mode 100755 index 000000000000..a73f52efcb6c --- /dev/null +++ b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh @@ -0,0 +1,456 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test traffic distribution when there are multiple paths between an IPv4 GRE +# tunnel. The tunnel carries IPv4 and IPv6 traffic between multiple hosts. +# Multiple routes are in the underlay network. With the default multipath +# policy, SW2 will only look at the outer IP addresses, hence only a single +# route would be used. +# +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.{2-253}/24 | | +# | 2001:db8:1::{2-fd}/64 | | +# +-------------------------|------+ +# | +# +-------------------------|------------------+ +# | SW1 | | +# | $ol1 + | +# | 198.51.100.1/24 | +# | 2001:db8:1::1/64 | +# | | +# | + g1 (gre) | +# | loc=192.0.2.1 | +# | rem=192.0.2.2 --. | +# | tos=inherit | | +# | v | +# | + $ul1 | +# | | 192.0.2.17/28 | +# +---------------------|----------------------+ +# | +# +---------------------|----------------------+ +# | SW2 | | +# | $ul21 + | +# | 192.0.2.18/28 | | +# | | | +# ! __________________+___ | +# | / \ | +# | | | | +# | + $ul22.111 (vlan) + $ul22.222 (vlan) | +# | | 192.0.2.33/28 | 192.0.2.49/28 | +# | | | | +# +--|----------------------|------------------+ +# | | +# +--|----------------------|------------------+ +# | | | | +# | + $ul32.111 (vlan) + $ul32.222 (vlan) | +# | | 192.0.2.34/28 | 192.0.2.50/28 | +# | | | | +# | \__________________+___/ | +# | | | +# | | | +# | $ul31 + | +# | 192.0.2.65/28 | SW3 | +# +---------------------|----------------------+ +# | +# +---------------------|----------------------+ +# | + $ul4 | +# | ^ 192.0.2.66/28 | +# | | | +# | + g2 (gre) | | +# | loc=192.0.2.2 | | +# | rem=192.0.2.1 --' | +# | tos=inherit | +# | | +# | $ol4 + | +# | 203.0.113.1/24 | | +# | 2001:db8:2::1/64 | SW4 | +# +-------------------------|------------------+ +# | +# +-------------------------|------+ +# | | | +# | $h2 + | +# | 203.0.113.{2-253}/24 | +# | 2001:db8:2::{2-fd}/64 H2 | +# +--------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + custom_hash +" + +NUM_NETIFS=10 +source lib.sh + +h1_create() +{ + simple_if_init $h1 198.51.100.2/24 2001:db8:1::2/64 + ip route add vrf v$h1 default via 198.51.100.1 dev $h1 + ip -6 route add vrf v$h1 default via 2001:db8:1::1 dev $h1 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 default + ip route del vrf v$h1 default + simple_if_fini $h1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw1_create() +{ + simple_if_init $ol1 198.51.100.1/24 2001:db8:1::1/64 + __simple_if_init $ul1 v$ol1 192.0.2.17/28 + + tunnel_create g1 gre 192.0.2.1 192.0.2.2 tos inherit dev v$ol1 + __simple_if_init g1 v$ol1 192.0.2.1/32 + ip route add vrf v$ol1 192.0.2.2/32 via 192.0.2.18 + + ip route add vrf v$ol1 203.0.113.0/24 dev g1 + ip -6 route add vrf v$ol1 2001:db8:2::/64 dev g1 +} + +sw1_destroy() +{ + ip -6 route del vrf v$ol1 2001:db8:2::/64 + ip route del vrf v$ol1 203.0.113.0/24 + + ip route del vrf v$ol1 192.0.2.2/32 + __simple_if_fini g1 192.0.2.1/32 + tunnel_destroy g1 + + __simple_if_fini $ul1 192.0.2.17/28 + simple_if_fini $ol1 198.51.100.1/24 2001:db8:1::1/64 +} + +sw2_create() +{ + simple_if_init $ul21 192.0.2.18/28 + __simple_if_init $ul22 v$ul21 + vlan_create $ul22 111 v$ul21 192.0.2.33/28 + vlan_create $ul22 222 v$ul21 192.0.2.49/28 + + ip route add vrf v$ul21 192.0.2.1/32 via 192.0.2.17 + ip route add vrf v$ul21 192.0.2.2/32 \ + nexthop via 192.0.2.34 \ + nexthop via 192.0.2.50 +} + +sw2_destroy() +{ + ip route del vrf v$ul21 192.0.2.2/32 + ip route del vrf v$ul21 192.0.2.1/32 + + vlan_destroy $ul22 222 + vlan_destroy $ul22 111 + __simple_if_fini $ul22 + simple_if_fini $ul21 192.0.2.18/28 +} + +sw3_create() +{ + simple_if_init $ul31 192.0.2.65/28 + __simple_if_init $ul32 v$ul31 + vlan_create $ul32 111 v$ul31 192.0.2.34/28 + vlan_create $ul32 222 v$ul31 192.0.2.50/28 + + ip route add vrf v$ul31 192.0.2.2/32 via 192.0.2.66 + ip route add vrf v$ul31 192.0.2.1/32 \ + nexthop via 192.0.2.33 \ + nexthop via 192.0.2.49 + + tc qdisc add dev $ul32 clsact + tc filter add dev $ul32 ingress pref 111 prot 802.1Q \ + flower vlan_id 111 action pass + tc filter add dev $ul32 ingress pref 222 prot 802.1Q \ + flower vlan_id 222 action pass +} + +sw3_destroy() +{ + tc qdisc del dev $ul32 clsact + + ip route del vrf v$ul31 192.0.2.1/32 + ip route del vrf v$ul31 192.0.2.2/32 + + vlan_destroy $ul32 222 + vlan_destroy $ul32 111 + __simple_if_fini $ul32 + simple_if_fini $ul31 192.0.2.65/28 +} + +sw4_create() +{ + simple_if_init $ol4 203.0.113.1/24 2001:db8:2::1/64 + __simple_if_init $ul4 v$ol4 192.0.2.66/28 + + tunnel_create g2 gre 192.0.2.2 192.0.2.1 tos inherit dev v$ol4 + __simple_if_init g2 v$ol4 192.0.2.2/32 + ip route add vrf v$ol4 192.0.2.1/32 via 192.0.2.65 + + ip route add vrf v$ol4 198.51.100.0/24 dev g2 + ip -6 route add vrf v$ol4 2001:db8:1::/64 dev g2 +} + +sw4_destroy() +{ + ip -6 route del vrf v$ol4 2001:db8:1::/64 + ip route del vrf v$ol4 198.51.100.0/24 + + ip route del vrf v$ol4 192.0.2.1/32 + __simple_if_fini g2 192.0.2.2/32 + tunnel_destroy g2 + + __simple_if_fini $ul4 192.0.2.66/28 + simple_if_fini $ol4 203.0.113.1/24 2001:db8:2::1/64 +} + +h2_create() +{ + simple_if_init $h2 203.0.113.2/24 2001:db8:2::2/64 + ip route add vrf v$h2 default via 203.0.113.1 dev $h2 + ip -6 route add vrf v$h2 default via 2001:db8:2::1 dev $h2 +} + +h2_destroy() +{ + ip -6 route del vrf v$h2 default + ip route del vrf v$h2 default + simple_if_fini $h2 203.0.113.2/24 2001:db8:2::2/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + + ol1=${NETIFS[p2]} + ul1=${NETIFS[p3]} + + ul21=${NETIFS[p4]} + ul22=${NETIFS[p5]} + + ul32=${NETIFS[p6]} + ul31=${NETIFS[p7]} + + ul4=${NETIFS[p8]} + ol4=${NETIFS[p9]} + + h2=${NETIFS[p10]} + + vrf_prepare + h1_create + sw1_create + sw2_create + sw3_create + sw4_create + h2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + h2_destroy + sw4_destroy + sw3_destroy + sw2_destroy + sw1_destroy + h1_destroy + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 203.0.113.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + +send_src_ipv4() +{ + $MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_dst_ipv4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_src_udp4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + -d 1msec -t udp "sp=0-32768,dp=30000" +} + +send_dst_udp4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + -d 1msec -t udp "sp=20000,dp=0-32768" +} + +send_src_ipv6() +{ + $MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_dst_ipv6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_flowlabel() +{ + # Generate 16384 echo requests, each with a random flow label. + for _ in $(seq 1 16384); do + ip vrf exec v$h1 \ + $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1 + done +} + +send_src_udp6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + -d 1msec -t udp "sp=0-32768,dp=30000" +} + +send_dst_udp6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + -d 1msec -t udp "sp=20000,dp=0-32768" +} + +custom_hash_test() +{ + local field="$1"; shift + local balanced="$1"; shift + local send_flows="$@" + + RET=0 + + local t0_111=$(tc_rule_stats_get $ul32 111 ingress) + local t0_222=$(tc_rule_stats_get $ul32 222 ingress) + + $send_flows + + local t1_111=$(tc_rule_stats_get $ul32 111 ingress) + local t1_222=$(tc_rule_stats_get $ul32 222 ingress) + + local d111=$((t1_111 - t0_111)) + local d222=$((t1_222 - t0_222)) + + local diff=$((d222 - d111)) + local sum=$((d111 + d222)) + + local pct=$(echo "$diff / $sum * 100" | bc -l) + local is_balanced=$(echo "-20 <= $pct && $pct <= 20" | bc) + + [[ ( $is_balanced -eq 1 && $balanced == "balanced" ) || + ( $is_balanced -eq 0 && $balanced == "unbalanced" ) ]] + check_err $? "Expected traffic to be $balanced, but it is not" + + log_test "Multipath hash field: $field ($balanced)" + log_info "Packets sent on path1 / path2: $d111 / $d222" +} + +custom_hash_v4() +{ + log_info "Running IPv4 overlay custom multipath hash tests" + + # Prevent the neighbour table from overflowing, as different neighbour + # entries will be created on $ol4 when using different destination IPs. + sysctl_set net.ipv4.neigh.default.gc_thresh1 1024 + sysctl_set net.ipv4.neigh.default.gc_thresh2 1024 + sysctl_set net.ipv4.neigh.default.gc_thresh3 1024 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0040 + custom_hash_test "Inner source IP" "balanced" send_src_ipv4 + custom_hash_test "Inner source IP" "unbalanced" send_dst_ipv4 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0080 + custom_hash_test "Inner destination IP" "balanced" send_dst_ipv4 + custom_hash_test "Inner destination IP" "unbalanced" send_src_ipv4 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0400 + custom_hash_test "Inner source port" "balanced" send_src_udp4 + custom_hash_test "Inner source port" "unbalanced" send_dst_udp4 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0800 + custom_hash_test "Inner destination port" "balanced" send_dst_udp4 + custom_hash_test "Inner destination port" "unbalanced" send_src_udp4 + + sysctl_restore net.ipv4.neigh.default.gc_thresh3 + sysctl_restore net.ipv4.neigh.default.gc_thresh2 + sysctl_restore net.ipv4.neigh.default.gc_thresh1 +} + +custom_hash_v6() +{ + log_info "Running IPv6 overlay custom multipath hash tests" + + # Prevent the neighbour table from overflowing, as different neighbour + # entries will be created on $ol4 when using different destination IPs. + sysctl_set net.ipv6.neigh.default.gc_thresh1 1024 + sysctl_set net.ipv6.neigh.default.gc_thresh2 1024 + sysctl_set net.ipv6.neigh.default.gc_thresh3 1024 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0040 + custom_hash_test "Inner source IP" "balanced" send_src_ipv6 + custom_hash_test "Inner source IP" "unbalanced" send_dst_ipv6 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0080 + custom_hash_test "Inner destination IP" "balanced" send_dst_ipv6 + custom_hash_test "Inner destination IP" "unbalanced" send_src_ipv6 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0200 + custom_hash_test "Inner flowlabel" "balanced" send_flowlabel + custom_hash_test "Inner flowlabel" "unbalanced" send_src_ipv6 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0400 + custom_hash_test "Inner source port" "balanced" send_src_udp6 + custom_hash_test "Inner source port" "unbalanced" send_dst_udp6 + + sysctl_set net.ipv4.fib_multipath_hash_fields 0x0800 + custom_hash_test "Inner destination port" "balanced" send_dst_udp6 + custom_hash_test "Inner destination port" "unbalanced" send_src_udp6 + + sysctl_restore net.ipv6.neigh.default.gc_thresh3 + sysctl_restore net.ipv6.neigh.default.gc_thresh2 + sysctl_restore net.ipv6.neigh.default.gc_thresh1 +} + +custom_hash() +{ + # Test that when the hash policy is set to custom, traffic is + # distributed only according to the fields set in the + # fib_multipath_hash_fields sysctl. + # + # Each time set a different field and make sure traffic is only + # distributed when the field is changed in the packet stream. + + sysctl_set net.ipv4.fib_multipath_hash_policy 3 + + custom_hash_v4 + custom_hash_v6 + + sysctl_restore net.ipv4.fib_multipath_hash_policy +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh new file mode 100755 index 000000000000..8fea2c2e0b25 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh @@ -0,0 +1,458 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test traffic distribution when there are multiple paths between an IPv6 GRE +# tunnel. The tunnel carries IPv4 and IPv6 traffic between multiple hosts. +# Multiple routes are in the underlay network. With the default multipath +# policy, SW2 will only look at the outer IP addresses, hence only a single +# route would be used. +# +# +--------------------------------+ +# | H1 | +# | $h1 + | +# | 198.51.100.{2-253}/24 | | +# | 2001:db8:1::{2-fd}/64 | | +# +-------------------------|------+ +# | +# +-------------------------|-------------------+ +# | SW1 | | +# | $ol1 + | +# | 198.51.100.1/24 | +# | 2001:db8:1::1/64 | +# | | +# |+ g1 (ip6gre) | +# | loc=2001:db8:3::1 | +# | rem=2001:db8:3::2 -. | +# | tos=inherit | | +# | v | +# | + $ul1 | +# | | 2001:db8:10::1/64 | +# +---------------------|-----------------------+ +# | +# +---------------------|-----------------------+ +# | SW2 | | +# | $ul21 + | +# | 2001:db8:10::2/64 | | +# | | | +# ! __________________+___ | +# | / \ | +# | | | | +# | + $ul22.111 (vlan) + $ul22.222 (vlan) | +# | | 2001:db8:11::1/64 | 2001:db8:12::1/64 | +# | | | | +# +--|----------------------|-------------------+ +# | | +# +--|----------------------|-------------------+ +# | | | | +# | + $ul32.111 (vlan) + $ul32.222 (vlan) | +# | | 2001:db8:11::2/64 | 2001:db8:12::2/64 | +# | | | | +# | \__________________+___/ | +# | | | +# | | | +# | $ul31 + | +# | 2001:db8:13::1/64 | SW3 | +# +---------------------|-----------------------+ +# | +# +---------------------|-----------------------+ +# | + $ul4 | +# | ^ 2001:db8:13::2/64 | +# | | | +# |+ g2 (ip6gre) | | +# | loc=2001:db8:3::2 | | +# | rem=2001:db8:3::1 -' | +# | tos=inherit | +# | | +# | $ol4 + | +# | 203.0.113.1/24 | | +# | 2001:db8:2::1/64 | SW4 | +# +-------------------------|-------------------+ +# | +# +-------------------------|------+ +# | | | +# | $h2 + | +# | 203.0.113.{2-253}/24 | +# | 2001:db8:2::{2-fd}/64 H2 | +# +--------------------------------+ + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + custom_hash +" + +NUM_NETIFS=10 +source lib.sh + +h1_create() +{ + simple_if_init $h1 198.51.100.2/24 2001:db8:1::2/64 + ip route add vrf v$h1 default via 198.51.100.1 dev $h1 + ip -6 route add vrf v$h1 default via 2001:db8:1::1 dev $h1 +} + +h1_destroy() +{ + ip -6 route del vrf v$h1 default + ip route del vrf v$h1 default + simple_if_fini $h1 198.51.100.2/24 2001:db8:1::2/64 +} + +sw1_create() +{ + simple_if_init $ol1 198.51.100.1/24 2001:db8:1::1/64 + __simple_if_init $ul1 v$ol1 2001:db8:10::1/64 + + tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \ + dev v$ol1 + __simple_if_init g1 v$ol1 2001:db8:3::1/128 + ip route add vrf v$ol1 2001:db8:3::2/128 via 2001:db8:10::2 + + ip route add vrf v$ol1 203.0.113.0/24 dev g1 + ip -6 route add vrf v$ol1 2001:db8:2::/64 dev g1 +} + +sw1_destroy() +{ + ip -6 route del vrf v$ol1 2001:db8:2::/64 + ip route del vrf v$ol1 203.0.113.0/24 + + ip route del vrf v$ol1 2001:db8:3::2/128 + __simple_if_fini g1 2001:db8:3::1/128 + tunnel_destroy g1 + + __simple_if_fini $ul1 2001:db8:10::1/64 + simple_if_fini $ol1 198.51.100.1/24 2001:db8:1::1/64 +} + +sw2_create() +{ + simple_if_init $ul21 2001:db8:10::2/64 + __simple_if_init $ul22 v$ul21 + vlan_create $ul22 111 v$ul21 2001:db8:11::1/64 + vlan_create $ul22 222 v$ul21 2001:db8:12::1/64 + + ip -6 route add vrf v$ul21 2001:db8:3::1/128 via 2001:db8:10::1 + ip -6 route add vrf v$ul21 2001:db8:3::2/128 \ + nexthop via 2001:db8:11::2 \ + nexthop via 2001:db8:12::2 +} + +sw2_destroy() +{ + ip -6 route del vrf v$ul21 2001:db8:3::2/128 + ip -6 route del vrf v$ul21 2001:db8:3::1/128 + + vlan_destroy $ul22 222 + vlan_destroy $ul22 111 + __simple_if_fini $ul22 + simple_if_fini $ul21 2001:db8:10::2/64 +} + +sw3_create() +{ + simple_if_init $ul31 2001:db8:13::1/64 + __simple_if_init $ul32 v$ul31 + vlan_create $ul32 111 v$ul31 2001:db8:11::2/64 + vlan_create $ul32 222 v$ul31 2001:db8:12::2/64 + + ip -6 route add vrf v$ul31 2001:db8:3::2/128 via 2001:db8:13::2 + ip -6 route add vrf v$ul31 2001:db8:3::1/128 \ + nexthop via 2001:db8:11::1 \ + nexthop via 2001:db8:12::1 + + tc qdisc add dev $ul32 clsact + tc filter add dev $ul32 ingress pref 111 prot 802.1Q \ + flower vlan_id 111 action pass + tc filter add dev $ul32 ingress pref 222 prot 802.1Q \ + flower vlan_id 222 action pass +} + +sw3_destroy() +{ + tc qdisc del dev $ul32 clsact + + ip -6 route del vrf v$ul31 2001:db8:3::1/128 + ip -6 route del vrf v$ul31 2001:db8:3::2/128 + + vlan_destroy $ul32 222 + vlan_destroy $ul32 111 + __simple_if_fini $ul32 + simple_if_fini $ul31 2001:db8:13::1/64 +} + +sw4_create() +{ + simple_if_init $ol4 203.0.113.1/24 2001:db8:2::1/64 + __simple_if_init $ul4 v$ol4 2001:db8:13::2/64 + + tunnel_create g2 ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \ + dev v$ol4 + __simple_if_init g2 v$ol4 2001:db8:3::2/128 + ip -6 route add vrf v$ol4 2001:db8:3::1/128 via 2001:db8:13::1 + + ip route add vrf v$ol4 198.51.100.0/24 dev g2 + ip -6 route add vrf v$ol4 2001:db8:1::/64 dev g2 +} + +sw4_destroy() +{ + ip -6 route del vrf v$ol4 2001:db8:1::/64 + ip route del vrf v$ol4 198.51.100.0/24 + + ip -6 route del vrf v$ol4 2001:db8:3::1/128 + __simple_if_fini g2 2001:db8:3::2/128 + tunnel_destroy g2 + + __simple_if_fini $ul4 2001:db8:13::2/64 + simple_if_fini $ol4 203.0.113.1/24 2001:db8:2::1/64 +} + +h2_create() +{ + simple_if_init $h2 203.0.113.2/24 2001:db8:2::2/64 + ip route add vrf v$h2 default via 203.0.113.1 dev $h2 + ip -6 route add vrf v$h2 default via 2001:db8:2::1 dev $h2 +} + +h2_destroy() +{ + ip -6 route del vrf v$h2 default + ip route del vrf v$h2 default + simple_if_fini $h2 203.0.113.2/24 2001:db8:2::2/64 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + + ol1=${NETIFS[p2]} + ul1=${NETIFS[p3]} + + ul21=${NETIFS[p4]} + ul22=${NETIFS[p5]} + + ul32=${NETIFS[p6]} + ul31=${NETIFS[p7]} + + ul4=${NETIFS[p8]} + ol4=${NETIFS[p9]} + + h2=${NETIFS[p10]} + + vrf_prepare + h1_create + sw1_create + sw2_create + sw3_create + sw4_create + h2_create + + forwarding_enable +} + +cleanup() +{ + pre_cleanup + + forwarding_restore + + h2_destroy + sw4_destroy + sw3_destroy + sw2_destroy + sw1_destroy + h1_destroy + vrf_cleanup +} + +ping_ipv4() +{ + ping_test $h1 203.0.113.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + +send_src_ipv4() +{ + $MZ $h1 -q -p 64 -A "198.51.100.2-198.51.100.253" -B 203.0.113.2 \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_dst_ipv4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B "203.0.113.2-203.0.113.253" \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_src_udp4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + -d 1msec -t udp "sp=0-32768,dp=30000" +} + +send_dst_udp4() +{ + $MZ $h1 -q -p 64 -A 198.51.100.2 -B 203.0.113.2 \ + -d 1msec -t udp "sp=20000,dp=0-32768" +} + +send_src_ipv6() +{ + $MZ -6 $h1 -q -p 64 -A "2001:db8:1::2-2001:db8:1::fd" -B 2001:db8:2::2 \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_dst_ipv6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B "2001:db8:2::2-2001:db8:2::fd" \ + -d 1msec -c 50 -t udp "sp=20000,dp=30000" +} + +send_flowlabel() +{ + # Generate 16384 echo requests, each with a random flow label. + for _ in $(seq 1 16384); do + ip vrf exec v$h1 \ + $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1 + done +} + +send_src_udp6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + -d 1msec -t udp "sp=0-32768,dp=30000" +} + +send_dst_udp6() +{ + $MZ -6 $h1 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ + -d 1msec -t udp "sp=20000,dp=0-32768" +} + +custom_hash_test() +{ + local field="$1"; shift + local balanced="$1"; shift + local send_flows="$@" + + RET=0 + + local t0_111=$(tc_rule_stats_get $ul32 111 ingress) + local t0_222=$(tc_rule_stats_get $ul32 222 ingress) + + $send_flows + + local t1_111=$(tc_rule_stats_get $ul32 111 ingress) + local t1_222=$(tc_rule_stats_get $ul32 222 ingress) + + local d111=$((t1_111 - t0_111)) + local d222=$((t1_222 - t0_222)) + + local diff=$((d222 - d111)) + local sum=$((d111 + d222)) + + local pct=$(echo "$diff / $sum * 100" | bc -l) + local is_balanced=$(echo "-20 <= $pct && $pct <= 20" | bc) + + [[ ( $is_balanced -eq 1 && $balanced == "balanced" ) || + ( $is_balanced -eq 0 && $balanced == "unbalanced" ) ]] + check_err $? "Expected traffic to be $balanced, but it is not" + + log_test "Multipath hash field: $field ($balanced)" + log_info "Packets sent on path1 / path2: $d111 / $d222" +} + +custom_hash_v4() +{ + log_info "Running IPv4 overlay custom multipath hash tests" + + # Prevent the neighbour table from overflowing, as different neighbour + # entries will be created on $ol4 when using different destination IPs. + sysctl_set net.ipv4.neigh.default.gc_thresh1 1024 + sysctl_set net.ipv4.neigh.default.gc_thresh2 1024 + sysctl_set net.ipv4.neigh.default.gc_thresh3 1024 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0040 + custom_hash_test "Inner source IP" "balanced" send_src_ipv4 + custom_hash_test "Inner source IP" "unbalanced" send_dst_ipv4 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0080 + custom_hash_test "Inner destination IP" "balanced" send_dst_ipv4 + custom_hash_test "Inner destination IP" "unbalanced" send_src_ipv4 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0400 + custom_hash_test "Inner source port" "balanced" send_src_udp4 + custom_hash_test "Inner source port" "unbalanced" send_dst_udp4 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0800 + custom_hash_test "Inner destination port" "balanced" send_dst_udp4 + custom_hash_test "Inner destination port" "unbalanced" send_src_udp4 + + sysctl_restore net.ipv4.neigh.default.gc_thresh3 + sysctl_restore net.ipv4.neigh.default.gc_thresh2 + sysctl_restore net.ipv4.neigh.default.gc_thresh1 +} + +custom_hash_v6() +{ + log_info "Running IPv6 overlay custom multipath hash tests" + + # Prevent the neighbour table from overflowing, as different neighbour + # entries will be created on $ol4 when using different destination IPs. + sysctl_set net.ipv6.neigh.default.gc_thresh1 1024 + sysctl_set net.ipv6.neigh.default.gc_thresh2 1024 + sysctl_set net.ipv6.neigh.default.gc_thresh3 1024 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0040 + custom_hash_test "Inner source IP" "balanced" send_src_ipv6 + custom_hash_test "Inner source IP" "unbalanced" send_dst_ipv6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0080 + custom_hash_test "Inner destination IP" "balanced" send_dst_ipv6 + custom_hash_test "Inner destination IP" "unbalanced" send_src_ipv6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0200 + custom_hash_test "Inner flowlabel" "balanced" send_flowlabel + custom_hash_test "Inner flowlabel" "unbalanced" send_src_ipv6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0400 + custom_hash_test "Inner source port" "balanced" send_src_udp6 + custom_hash_test "Inner source port" "unbalanced" send_dst_udp6 + + sysctl_set net.ipv6.fib_multipath_hash_fields 0x0800 + custom_hash_test "Inner destination port" "balanced" send_dst_udp6 + custom_hash_test "Inner destination port" "unbalanced" send_src_udp6 + + sysctl_restore net.ipv6.neigh.default.gc_thresh3 + sysctl_restore net.ipv6.neigh.default.gc_thresh2 + sysctl_restore net.ipv6.neigh.default.gc_thresh1 +} + +custom_hash() +{ + # Test that when the hash policy is set to custom, traffic is + # distributed only according to the fields set in the + # fib_multipath_hash_fields sysctl. + # + # Each time set a different field and make sure traffic is only + # distributed when the field is changed in the packet stream. + + sysctl_set net.ipv6.fib_multipath_hash_policy 3 + + custom_hash_v4 + custom_hash_v6 + + sysctl_restore net.ipv6.fib_multipath_hash_policy +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh index 55eeacf59241..64fbd211d907 100755 --- a/tools/testing/selftests/net/forwarding/pedit_dsfield.sh +++ b/tools/testing/selftests/net/forwarding/pedit_dsfield.sh @@ -75,7 +75,9 @@ switch_destroy() tc qdisc del dev $swp2 clsact tc qdisc del dev $swp1 clsact + ip link set dev $swp2 down ip link set dev $swp2 nomaster + ip link set dev $swp1 down ip link set dev $swp1 nomaster ip link del dev br1 } diff --git a/tools/testing/selftests/net/forwarding/pedit_l4port.sh b/tools/testing/selftests/net/forwarding/pedit_l4port.sh index 5f20d289ee43..10e594c55117 100755 --- a/tools/testing/selftests/net/forwarding/pedit_l4port.sh +++ b/tools/testing/selftests/net/forwarding/pedit_l4port.sh @@ -71,7 +71,9 @@ switch_destroy() tc qdisc del dev $swp2 clsact tc qdisc del dev $swp1 clsact + ip link set dev $swp2 down ip link set dev $swp2 nomaster + ip link set dev $swp1 down ip link set dev $swp1 nomaster ip link del dev br1 } diff --git a/tools/testing/selftests/net/forwarding/skbedit_priority.sh b/tools/testing/selftests/net/forwarding/skbedit_priority.sh index e3bd8a6bb8b4..bde11dc27873 100755 --- a/tools/testing/selftests/net/forwarding/skbedit_priority.sh +++ b/tools/testing/selftests/net/forwarding/skbedit_priority.sh @@ -72,7 +72,9 @@ switch_destroy() tc qdisc del dev $swp2 clsact tc qdisc del dev $swp1 clsact + ip link set dev $swp2 down ip link set dev $swp2 nomaster + ip link set dev $swp1 down ip link set dev $swp1 nomaster ip link del dev br1 } diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh index bf361f30d6ef..c19ecc6a8614 100755 --- a/tools/testing/selftests/net/icmp_redirect.sh +++ b/tools/testing/selftests/net/icmp_redirect.sh @@ -63,10 +63,14 @@ log_test() local rc=$1 local expected=$2 local msg="$3" + local xfail=$4 if [ ${rc} -eq ${expected} ]; then printf "TEST: %-60s [ OK ]\n" "${msg}" nsuccess=$((nsuccess+1)) + elif [ ${rc} -eq ${xfail} ]; then + printf "TEST: %-60s [XFAIL]\n" "${msg}" + nxfail=$((nxfail+1)) else ret=1 nfail=$((nfail+1)) @@ -322,7 +326,7 @@ check_exception() ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \ grep -v "mtu" | grep -q "${R1_LLADDR}" fi - log_test $? 0 "IPv6: ${desc}" + log_test $? 0 "IPv6: ${desc}" 1 } run_ping() @@ -488,6 +492,7 @@ which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) ret=0 nsuccess=0 nfail=0 +nxfail=0 while getopts :pv o do @@ -532,5 +537,6 @@ fi printf "\nTests passed: %3d\n" ${nsuccess} printf "Tests failed: %3d\n" ${nfail} +printf "Tests xfailed: %3d\n" ${nxfail} exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index d88e1fdfb147..89c4753c2760 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -25,6 +26,7 @@ #include #include +#include extern int optind; @@ -66,6 +68,13 @@ static unsigned int cfg_do_w; static int cfg_wait; static uint32_t cfg_mark; +struct cfg_cmsg_types { + unsigned int cmsg_enabled:1; + unsigned int timestampns:1; +}; + +static struct cfg_cmsg_types cfg_cmsg_types; + static void die_usage(void) { fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] [-m mode]" @@ -80,11 +89,22 @@ static void die_usage(void) fprintf(stderr, "\t-M mark -- set socket packet mark\n"); fprintf(stderr, "\t-u -- check mptcp ulp\n"); fprintf(stderr, "\t-w num -- wait num sec before closing the socket\n"); + fprintf(stderr, "\t-c cmsg -- test cmsg type \n"); fprintf(stderr, "\t-P [saveWithPeek|saveAfterPeek] -- save data with/after MSG_PEEK form tcp socket\n"); exit(1); } +static void xerror(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + exit(1); +} + static void handle_signal(int nr) { quit = true; @@ -338,6 +358,58 @@ static size_t do_write(const int fd, char *buf, const size_t len) return offset; } +static void process_cmsg(struct msghdr *msgh) +{ + struct __kernel_timespec ts; + bool ts_found = false; + struct cmsghdr *cmsg; + + for (cmsg = CMSG_FIRSTHDR(msgh); cmsg ; cmsg = CMSG_NXTHDR(msgh, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == SO_TIMESTAMPNS_NEW) { + memcpy(&ts, CMSG_DATA(cmsg), sizeof(ts)); + ts_found = true; + continue; + } + } + + if (cfg_cmsg_types.timestampns) { + if (!ts_found) + xerror("TIMESTAMPNS not present\n"); + } +} + +static ssize_t do_recvmsg_cmsg(const int fd, char *buf, const size_t len) +{ + char msg_buf[8192]; + struct iovec iov = { + .iov_base = buf, + .iov_len = len, + }; + struct msghdr msg = { + .msg_iov = &iov, + .msg_iovlen = 1, + .msg_control = msg_buf, + .msg_controllen = sizeof(msg_buf), + }; + int flags = 0; + int ret = recvmsg(fd, &msg, flags); + + if (ret <= 0) + return ret; + + if (msg.msg_controllen && !cfg_cmsg_types.cmsg_enabled) + xerror("got %lu bytes of cmsg data, expected 0\n", + (unsigned long)msg.msg_controllen); + + if (msg.msg_controllen == 0 && cfg_cmsg_types.cmsg_enabled) + xerror("%s\n", "got no cmsg data"); + + if (msg.msg_controllen) + process_cmsg(&msg); + + return ret; +} + static ssize_t do_rnd_read(const int fd, char *buf, const size_t len) { int ret = 0; @@ -357,6 +429,8 @@ static ssize_t do_rnd_read(const int fd, char *buf, const size_t len) } else if (cfg_peek == CFG_AFTER_PEEK) { ret = recv(fd, buf, cap, MSG_PEEK); ret = (ret < 0) ? ret : read(fd, buf, cap); + } else if (cfg_cmsg_types.cmsg_enabled) { + ret = do_recvmsg_cmsg(fd, buf, cap); } else { ret = read(fd, buf, cap); } @@ -786,6 +860,48 @@ static void init_rng(void) srand(foo); } +static void xsetsockopt(int fd, int level, int optname, const void *optval, socklen_t optlen) +{ + int err; + + err = setsockopt(fd, level, optname, optval, optlen); + if (err) { + perror("setsockopt"); + exit(1); + } +} + +static void apply_cmsg_types(int fd, const struct cfg_cmsg_types *cmsg) +{ + static const unsigned int on = 1; + + if (cmsg->timestampns) + xsetsockopt(fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW, &on, sizeof(on)); +} + +static void parse_cmsg_types(const char *type) +{ + char *next = strchr(type, ','); + unsigned int len = 0; + + cfg_cmsg_types.cmsg_enabled = 1; + + if (next) { + parse_cmsg_types(next + 1); + len = next - type; + } else { + len = strlen(type); + } + + if (strncmp(type, "TIMESTAMPNS", len) == 0) { + cfg_cmsg_types.timestampns = 1; + return; + } + + fprintf(stderr, "Unrecognized cmsg option %s\n", type); + exit(1); +} + int main_loop(void) { int fd; @@ -801,6 +917,8 @@ int main_loop(void) set_rcvbuf(fd, cfg_rcvbuf); if (cfg_sndbuf) set_sndbuf(fd, cfg_sndbuf); + if (cfg_cmsg_types.cmsg_enabled) + apply_cmsg_types(fd, &cfg_cmsg_types); return copyfd_io(0, fd, 1); } @@ -887,7 +1005,7 @@ static void parse_opts(int argc, char **argv) { int c; - while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:P:")) != -1) { + while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:P:c:")) != -1) { switch (c) { case 'j': cfg_join = true; @@ -943,6 +1061,9 @@ static void parse_opts(int argc, char **argv) case 'P': cfg_peek = parse_peek(optarg); break; + case 'c': + parse_cmsg_types(optarg); + break; } } @@ -976,6 +1097,8 @@ int main(int argc, char *argv[]) set_sndbuf(fd, cfg_sndbuf); if (cfg_mark) set_mark(fd, cfg_mark); + if (cfg_cmsg_types.cmsg_enabled) + apply_cmsg_types(fd, &cfg_cmsg_types); return main_loop_s(fd); } diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 2b495dc8d78e..559173a8e387 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -3,7 +3,7 @@ time_start=$(date +%s) -optstring="S:R:d:e:l:r:h4cm:f:t" +optstring="S:R:d:e:l:r:h4cm:f:tC" ret=0 sin="" sout="" @@ -22,6 +22,7 @@ sndbuf=0 rcvbuf=0 options_log=true do_tcp=0 +checksum=false filesize=0 if [ $tc_loss -eq 100 ];then @@ -47,6 +48,7 @@ usage() { echo -e "\t-R: set rcvbuf value (default: use kernel default)" echo -e "\t-m: test mode (poll, sendfile; default: poll)" echo -e "\t-t: also run tests with TCP (use twice to non-fallback tcp)" + echo -e "\t-C: enable the MPTCP data checksum" } while getopts "$optstring" option;do @@ -104,6 +106,9 @@ while getopts "$optstring" option;do "t") do_tcp=$((do_tcp+1)) ;; + "C") + checksum=true + ;; "?") usage $0 exit 1 @@ -197,6 +202,12 @@ ip -net "$ns4" link set ns4eth3 up ip -net "$ns4" route add default via 10.0.3.2 ip -net "$ns4" route add default via dead:beef:3::2 +if $checksum; then + for i in "$ns1" "$ns2" "$ns3" "$ns4";do + ip netns exec $i sysctl -q net.mptcp.checksum_enabled=1 + done +fi + set_ethtool_flags() { local ns="$1" local dev="$2" @@ -669,6 +680,25 @@ run_tests_peekmode() run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-P ${peekmode}" } +display_time() +{ + time_end=$(date +%s) + time_run=$((time_end-time_start)) + + echo "Time: ${time_run} seconds" +} + +stop_if_error() +{ + local msg="$1" + + if [ ${ret} -ne 0 ]; then + echo "FAIL: ${msg}" 1>&2 + display_time + exit ${ret} + fi +} + make_file "$cin" "client" make_file "$sin" "server" @@ -676,6 +706,8 @@ check_mptcp_disabled check_mptcp_ulp_setsockopt +stop_if_error "The kernel configuration is not valid for MPTCP" + echo "INFO: validating network environment with pings" for sender in "$ns1" "$ns2" "$ns3" "$ns4";do do_ping "$ns1" $sender 10.0.1.1 @@ -695,6 +727,8 @@ for sender in "$ns1" "$ns2" "$ns3" "$ns4";do do_ping "$ns4" $sender dead:beef:3::1 done +stop_if_error "Could not even run ping tests" + [ -n "$tc_loss" ] && tc -net "$ns2" qdisc add dev ns2eth3 root netem loss random $tc_loss delay ${tc_delay}ms echo -n "INFO: Using loss of $tc_loss " test "$tc_delay" -gt 0 && echo -n "delay $tc_delay ms " @@ -722,18 +756,13 @@ echo "on ns3eth4" tc -net "$ns3" qdisc add dev ns3eth4 root netem delay ${reorder_delay}ms $tc_reorder -for sender in $ns1 $ns2 $ns3 $ns4;do - run_tests_lo "$ns1" "$sender" 10.0.1.1 1 - if [ $ret -ne 0 ] ;then - echo "FAIL: Could not even run loopback test" 1>&2 - exit $ret - fi - run_tests_lo "$ns1" $sender dead:beef:1::1 1 - if [ $ret -ne 0 ] ;then - echo "FAIL: Could not even run loopback v6 test" 2>&1 - exit $ret - fi +run_tests_lo "$ns1" "$ns1" 10.0.1.1 1 +stop_if_error "Could not even run loopback test" +run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 +stop_if_error "Could not even run loopback v6 test" + +for sender in $ns1 $ns2 $ns3 $ns4;do # ns1<->ns2 is not subject to reordering/tc delays. Use it to test # mptcp syncookie support. if [ $sender = $ns1 ]; then @@ -742,6 +771,9 @@ for sender in $ns1 $ns2 $ns3 $ns4;do ip netns exec "$ns2" sysctl -q net.ipv4.tcp_syncookies=1 fi + run_tests "$ns1" $sender 10.0.1.1 + run_tests "$ns1" $sender dead:beef:1::1 + run_tests "$ns2" $sender 10.0.1.2 run_tests "$ns2" $sender dead:beef:1::2 run_tests "$ns2" $sender 10.0.2.1 @@ -754,14 +786,13 @@ for sender in $ns1 $ns2 $ns3 $ns4;do run_tests "$ns4" $sender 10.0.3.1 run_tests "$ns4" $sender dead:beef:3::1 + + stop_if_error "Tests with $sender as a sender have failed" done run_tests_peekmode "saveWithPeek" run_tests_peekmode "saveAfterPeek" +stop_if_error "Tests with peek mode have failed" -time_end=$(date +%s) -time_run=$((time_end-time_start)) - -echo "Time: ${time_run} seconds" - +display_time exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index fd99485cf2a4..9a191c1a5de8 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -12,6 +12,7 @@ timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) mptcp_connect="" capture=0 +checksum=0 do_all_tests=1 TEST_COUNT=0 @@ -49,6 +50,9 @@ init() ip netns exec $netns sysctl -q net.mptcp.enabled=1 ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0 ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0 + if [ $checksum -eq 1 ]; then + ip netns exec $netns sysctl -q net.mptcp.checksum_enabled=1 + fi done # ns1 ns2 @@ -124,6 +128,28 @@ reset_with_add_addr_timeout() -j DROP } +reset_with_checksum() +{ + local ns1_enable=$1 + local ns2_enable=$2 + + reset + + ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=$ns1_enable + ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=$ns2_enable +} + +reset_with_allow_join_id0() +{ + local ns1_enable=$1 + local ns2_enable=$2 + + reset + + ip netns exec $ns1 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns1_enable + ip netns exec $ns2 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns2_enable +} + ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -476,6 +502,45 @@ run_tests() fi } +chk_csum_nr() +{ + local msg=${1:-""} + local count + local dump_stats + + if [ ! -z "$msg" ]; then + printf "%02u" "$TEST_COUNT" + else + echo -n " " + fi + printf " %-36s %s" "$msg" "sum" + count=`ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}'` + [ -z "$count" ] && count=0 + if [ "$count" != 0 ]; then + echo "[fail] got $count data checksum error[s] expected 0" + ret=1 + dump_stats=1 + else + echo -n "[ ok ]" + fi + echo -n " - csum " + count=`ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}'` + [ -z "$count" ] && count=0 + if [ "$count" != 0 ]; then + echo "[fail] got $count data checksum error[s] expected 0" + ret=1 + dump_stats=1 + else + echo "[ ok ]" + fi + if [ "${dump_stats}" = 1 ]; then + echo Server ns stats + ip netns exec $ns1 nstat -as | grep MPTcp + echo Client ns stats + ip netns exec $ns2 nstat -as | grep MPTcp + fi +} + chk_join_nr() { local msg="$1" @@ -523,6 +588,9 @@ chk_join_nr() echo Client ns stats ip netns exec $ns2 nstat -as | grep MPTcp fi + if [ $checksum -eq 1 ]; then + chk_csum_nr + fi } chk_add_nr() @@ -1374,6 +1442,94 @@ syncookies_tests() chk_add_nr 1 1 } +checksum_tests() +{ + # checksum test 0 0 + reset_with_checksum 0 0 + ip netns exec $ns1 ./pm_nl_ctl limits 0 1 + ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_csum_nr "checksum test 0 0" + + # checksum test 1 1 + reset_with_checksum 1 1 + ip netns exec $ns1 ./pm_nl_ctl limits 0 1 + ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_csum_nr "checksum test 1 1" + + # checksum test 0 1 + reset_with_checksum 0 1 + ip netns exec $ns1 ./pm_nl_ctl limits 0 1 + ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_csum_nr "checksum test 0 1" + + # checksum test 1 0 + reset_with_checksum 1 0 + ip netns exec $ns1 ./pm_nl_ctl limits 0 1 + ip netns exec $ns2 ./pm_nl_ctl limits 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_csum_nr "checksum test 1 0" +} + +deny_join_id0_tests() +{ + # subflow allow join id0 ns1 + reset_with_allow_join_id0 1 0 + ip netns exec $ns1 ./pm_nl_ctl limits 1 1 + ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr "single subflow allow join id0 ns1" 1 1 1 + + # subflow allow join id0 ns2 + reset_with_allow_join_id0 0 1 + ip netns exec $ns1 ./pm_nl_ctl limits 1 1 + ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr "single subflow allow join id0 ns2" 0 0 0 + + # signal address allow join id0 ns1 + # ADD_ADDRs are not affected by allow_join_id0 value. + reset_with_allow_join_id0 1 0 + ip netns exec $ns1 ./pm_nl_ctl limits 1 1 + ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr "signal address allow join id0 ns1" 1 1 1 + chk_add_nr 1 1 + + # signal address allow join id0 ns2 + # ADD_ADDRs are not affected by allow_join_id0 value. + reset_with_allow_join_id0 0 1 + ip netns exec $ns1 ./pm_nl_ctl limits 1 1 + ip netns exec $ns2 ./pm_nl_ctl limits 1 1 + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr "signal address allow join id0 ns2" 1 1 1 + chk_add_nr 1 1 + + # subflow and address allow join id0 ns1 + reset_with_allow_join_id0 1 0 + ip netns exec $ns1 ./pm_nl_ctl limits 2 2 + ip netns exec $ns2 ./pm_nl_ctl limits 2 2 + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr "subflow and address allow join id0 1" 2 2 2 + + # subflow and address allow join id0 ns2 + reset_with_allow_join_id0 0 1 + ip netns exec $ns1 ./pm_nl_ctl limits 2 2 + ip netns exec $ns2 ./pm_nl_ctl limits 2 2 + ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal + ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr "subflow and address allow join id0 2" 1 1 1 +} + all_tests() { subflows_tests @@ -1387,6 +1543,8 @@ all_tests() backup_tests add_addr_ports_tests syncookies_tests + checksum_tests + deny_join_id0_tests } usage() @@ -1403,7 +1561,10 @@ usage() echo " -b backup_tests" echo " -p add_addr_ports_tests" echo " -k syncookies_tests" + echo " -S checksum_tests" + echo " -d deny_join_id0_tests" echo " -c capture pcap files" + echo " -C enable data checksum" echo " -h help" } @@ -1418,13 +1579,16 @@ make_file "$sin" "server" 1 trap cleanup EXIT for arg in "$@"; do - # check for "capture" arg before launching tests + # check for "capture/checksum" args before launching tests if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"c"[0-9a-zA-Z]*$ ]]; then capture=1 fi + if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"C"[0-9a-zA-Z]*$ ]]; then + checksum=1 + fi - # exception for the capture option, the rest means: a part of the tests - if [ "${arg}" != "-c" ]; then + # exception for the capture/checksum options, the rest means: a part of the tests + if [ "${arg}" != "-c" ] && [ "${arg}" != "-C" ]; then do_all_tests=0 fi done @@ -1434,7 +1598,7 @@ if [ $do_all_tests -eq 1 ]; then exit $ret fi -while getopts 'fsltra64bpkch' opt; do +while getopts 'fsltra64bpkdchCS' opt; do case $opt in f) subflows_tests @@ -1469,8 +1633,16 @@ while getopts 'fsltra64bpkch' opt; do k) syncookies_tests ;; + S) + checksum_tests + ;; + d) + deny_join_id0_tests + ;; c) ;; + C) + ;; h | *) usage ;; diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 2fa13946ac04..1579e471a5e7 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -178,7 +178,7 @@ do_transfer() timeout ${timeout_test} \ ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} \ + $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c TIMESTAMPNS \ ${local_addr} < "$sin" > "$sout" & spid=$! @@ -186,7 +186,7 @@ do_transfer() timeout ${timeout_test} \ ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} \ + $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c TIMESTAMPNS \ $connect_addr < "$cin" > "$cout" & cpid=$! diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 3aeef3bcb101..fd63ebfe9a2b 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -60,6 +60,8 @@ setup() for i in "$ns1" "$ns2" "$ns3";do ip netns add $i || exit $ksft_skip ip -net $i link set lo up + ip netns exec $i sysctl -q net.ipv4.conf.all.rp_filter=0 + ip netns exec $i sysctl -q net.ipv4.conf.default.rp_filter=0 done ip link add ns1eth1 netns "$ns1" type veth peer name ns2eth1 netns "$ns2" @@ -80,7 +82,6 @@ setup() ip netns exec "$ns1" ./pm_nl_ctl limits 1 1 ip netns exec "$ns1" ./pm_nl_ctl add 10.0.2.1 dev ns1eth2 flags subflow - ip netns exec "$ns1" sysctl -q net.ipv4.conf.all.rp_filter=0 ip -net "$ns2" addr add 10.0.1.2/24 dev ns2eth1 ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad diff --git a/tools/testing/selftests/net/so_netns_cookie.c b/tools/testing/selftests/net/so_netns_cookie.c new file mode 100644 index 000000000000..b39e87e967cd --- /dev/null +++ b/tools/testing/selftests/net/so_netns_cookie.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifndef SO_NETNS_COOKIE +#define SO_NETNS_COOKIE 71 +#endif + +#define pr_err(fmt, ...) \ + ({ \ + fprintf(stderr, "%s:%d:" fmt ": %m\n", \ + __func__, __LINE__, ##__VA_ARGS__); \ + 1; \ + }) + +int main(int argc, char *argvp[]) +{ + uint64_t cookie1, cookie2; + socklen_t vallen; + int sock1, sock2; + + sock1 = socket(AF_INET, SOCK_STREAM, 0); + if (sock1 < 0) + return pr_err("Unable to create TCP socket"); + + vallen = sizeof(cookie1); + if (getsockopt(sock1, SOL_SOCKET, SO_NETNS_COOKIE, &cookie1, &vallen) != 0) + return pr_err("getsockopt(SOL_SOCKET, SO_NETNS_COOKIE)"); + + if (!cookie1) + return pr_err("SO_NETNS_COOKIE returned zero cookie"); + + if (unshare(CLONE_NEWNET)) + return pr_err("unshare"); + + sock2 = socket(AF_INET, SOCK_STREAM, 0); + if (sock2 < 0) + return pr_err("Unable to create TCP socket"); + + vallen = sizeof(cookie2); + if (getsockopt(sock2, SOL_SOCKET, SO_NETNS_COOKIE, &cookie2, &vallen) != 0) + return pr_err("getsockopt(SOL_SOCKET, SO_NETNS_COOKIE)"); + + if (!cookie2) + return pr_err("SO_NETNS_COOKIE returned zero cookie"); + + if (cookie1 == cookie2) + return pr_err("SO_NETNS_COOKIE returned identical cookies for distinct ns"); + + close(sock1); + close(sock2); + return 0; +} diff --git a/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh new file mode 100755 index 000000000000..75ada17ac061 --- /dev/null +++ b/tools/testing/selftests/net/srv6_end_dt46_l3vpn_test.sh @@ -0,0 +1,573 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# author: Andrea Mayer +# author: Paolo Lungaroni + +# This test is designed for evaluating the new SRv6 End.DT46 Behavior used for +# implementing IPv4/IPv6 L3 VPN use cases. +# +# The current SRv6 code in the Linux kernel only implements SRv6 End.DT4 and +# End.DT6 Behaviors which can be used respectively to support IPv4-in-IPv6 and +# IPv6-in-IPv6 VPNs. With End.DT4 and End.DT6 it is not possible to create a +# single SRv6 VPN tunnel to carry both IPv4 and IPv6 traffic. +# The SRv6 End.DT46 Behavior implementation is meant to support the +# decapsulation of IPv4 and IPv6 traffic coming from a single SRv6 tunnel. +# Therefore, the SRv6 End.DT46 Behavior in the Linux kernel greatly simplifies +# the setup and operations of SRv6 VPNs. +# +# Hereafter a network diagram is shown, where two different tenants (named 100 +# and 200) offer IPv4/IPv6 L3 VPN services allowing hosts to communicate with +# each other across an IPv6 network. +# +# Only hosts belonging to the same tenant (and to the same VPN) can communicate +# with each other. Instead, the communication among hosts of different tenants +# is forbidden. +# In other words, hosts hs-t100-1 and hs-t100-2 are connected through the +# IPv4/IPv6 L3 VPN of tenant 100 while hs-t200-3 and hs-t200-4 are connected +# using the IPv4/IPv6 L3 VPN of tenant 200. Cross connection between tenant 100 +# and tenant 200 is forbidden and thus, for example, hs-t100-1 cannot reach +# hs-t200-3 and vice versa. +# +# Routers rt-1 and rt-2 implement IPv4/IPv6 L3 VPN services leveraging the SRv6 +# architecture. The key components for such VPNs are: a) SRv6 Encap behavior, +# b) SRv6 End.DT46 Behavior and c) VRF. +# +# To explain how an IPv4/IPv6 L3 VPN based on SRv6 works, let us briefly +# consider an example where, within the same domain of tenant 100, the host +# hs-t100-1 pings the host hs-t100-2. +# +# First of all, L2 reachability of the host hs-t100-2 is taken into account by +# the router rt-1 which acts as a arp/ndp proxy. +# +# When the host hs-t100-1 sends an IPv6 or IPv4 packet destined to hs-t100-2, +# the router rt-1 receives the packet on the internal veth-t100 interface. Such +# interface is enslaved to the VRF vrf-100 whose associated table contains the +# SRv6 Encap route for encapsulating any IPv6 or IPv4 packet in a IPv6 plus the +# Segment Routing Header (SRH) packet. This packet is sent through the (IPv6) +# core network up to the router rt-2 that receives it on veth0 interface. +# +# The rt-2 router uses the 'localsid' routing table to process incoming +# IPv6+SRH packets which belong to the VPN of the tenant 100. For each of these +# packets, the SRv6 End.DT46 Behavior removes the outer IPv6+SRH headers and +# performs the lookup on the vrf-100 table using the destination address of +# the decapsulated IPv6 or IPv4 packet. Afterwards, the packet is sent to the +# host hs-t100-2 through the veth-t100 interface. +# +# The ping response follows the same processing but this time the roles of rt-1 +# and rt-2 are swapped. +# +# Of course, the IPv4/IPv6 L3 VPN for tenant 200 works exactly as the IPv4/IPv6 +# L3 VPN for tenant 100. In this case, only hosts hs-t200-3 and hs-t200-4 are +# able to connect with each other. +# +# +# +-------------------+ +-------------------+ +# | | | | +# | hs-t100-1 netns | | hs-t100-2 netns | +# | | | | +# | +-------------+ | | +-------------+ | +# | | veth0 | | | | veth0 | | +# | | cafe::1/64 | | | | cafe::2/64 | | +# | | 10.0.0.1/24 | | | | 10.0.0.2/24 | | +# | +-------------+ | | +-------------+ | +# | . | | . | +# +-------------------+ +-------------------+ +# . . +# . . +# . . +# +-----------------------------------+ +-----------------------------------+ +# | . | | . | +# | +---------------+ | | +---------------- | +# | | veth-t100 | | | | veth-t100 | | +# | | cafe::254/64 | | | | cafe::254/64 | | +# | | 10.0.0.254/24 | +----------+ | | +----------+ | 10.0.0.254/24 | | +# | +-------+-------+ | localsid | | | | localsid | +-------+-------- | +# | | | table | | | | table | | | +# | +----+----+ +----------+ | | +----------+ +----+----+ | +# | | vrf-100 | | | | vrf-100 | | +# | +---------+ +------------+ | | +------------+ +---------+ | +# | | veth0 | | | | veth0 | | +# | | fd00::1/64 |.|...|.| fd00::2/64 | | +# | +---------+ +------------+ | | +------------+ +---------+ | +# | | vrf-200 | | | | vrf-200 | | +# | +----+----+ | | +----+----+ | +# | | | | | | +# | +-------+-------+ | | +-------+-------- | +# | | veth-t200 | | | | veth-t200 | | +# | | cafe::254/64 | | | | cafe::254/64 | | +# | | 10.0.0.254/24 | | | | 10.0.0.254/24 | | +# | +---------------+ rt-1 netns | | rt-2 netns +---------------- | +# | . | | . | +# +-----------------------------------+ +-----------------------------------+ +# . . +# . . +# . . +# . . +# +-------------------+ +-------------------+ +# | . | | . | +# | +-------------+ | | +-------------+ | +# | | veth0 | | | | veth0 | | +# | | cafe::3/64 | | | | cafe::4/64 | | +# | | 10.0.0.3/24 | | | | 10.0.0.4/24 | | +# | +-------------+ | | +-------------+ | +# | | | | +# | hs-t200-3 netns | | hs-t200-4 netns | +# | | | | +# +-------------------+ +-------------------+ +# +# +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# | Network configuration | +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# +# rt-1: localsid table (table 90) +# +--------------------------------------------------+ +# |SID |Action | +# +--------------------------------------------------+ +# |fc00:21:100::6046|apply SRv6 End.DT46 vrftable 100| +# +--------------------------------------------------+ +# |fc00:21:200::6046|apply SRv6 End.DT46 vrftable 200| +# +--------------------------------------------------+ +# +# rt-1: VRF tenant 100 (table 100) +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |cafe::2 |apply seg6 encap segs fc00:12:100::6046| +# +---------------------------------------------------+ +# |cafe::/64 |forward to dev veth-t100 | +# +---------------------------------------------------+ +# |10.0.0.2 |apply seg6 encap segs fc00:12:100::6046| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth-t100 | +# +---------------------------------------------------+ +# +# rt-1: VRF tenant 200 (table 200) +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |cafe::4 |apply seg6 encap segs fc00:12:200::6046| +# +---------------------------------------------------+ +# |cafe::/64 |forward to dev veth-t200 | +# +---------------------------------------------------+ +# |10.0.0.4 |apply seg6 encap segs fc00:12:200::6046| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth-t200 | +# +---------------------------------------------------+ +# +# +# rt-2: localsid table (table 90) +# +--------------------------------------------------+ +# |SID |Action | +# +--------------------------------------------------+ +# |fc00:12:100::6046|apply SRv6 End.DT46 vrftable 100| +# +--------------------------------------------------+ +# |fc00:12:200::6046|apply SRv6 End.DT46 vrftable 200| +# +--------------------------------------------------+ +# +# rt-2: VRF tenant 100 (table 100) +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |cafe::1 |apply seg6 encap segs fc00:21:100::6046| +# +---------------------------------------------------+ +# |cafe::/64 |forward to dev veth-t100 | +# +---------------------------------------------------+ +# |10.0.0.1 |apply seg6 encap segs fc00:21:100::6046| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth-t100 | +# +---------------------------------------------------+ +# +# rt-2: VRF tenant 200 (table 200) +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |cafe::3 |apply seg6 encap segs fc00:21:200::6046| +# +---------------------------------------------------+ +# |cafe::/64 |forward to dev veth-t200 | +# +---------------------------------------------------+ +# |10.0.0.3 |apply seg6 encap segs fc00:21:200::6046| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth-t200 | +# +---------------------------------------------------+ +# + +readonly LOCALSID_TABLE_ID=90 +readonly IPv6_RT_NETWORK=fd00 +readonly IPv6_HS_NETWORK=cafe +readonly IPv4_HS_NETWORK=10.0.0 +readonly VPN_LOCATOR_SERVICE=fc00 +PING_TIMEOUT_SEC=4 + +ret=0 + +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-60s [ OK ]\n" "${msg}" + else + ret=1 + nfail=$((nfail+1)) + printf "\n TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +print_log_test_results() +{ + if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} + fi +} + +log_section() +{ + echo + echo "################################################################################" + echo "TEST SECTION: $*" + echo "################################################################################" +} + +cleanup() +{ + ip link del veth-rt-1 2>/dev/null || true + ip link del veth-rt-2 2>/dev/null || true + + # destroy routers rt-* and hosts hs-* + for ns in $(ip netns show | grep -E 'rt-*|hs-*'); do + ip netns del ${ns} || true + done +} + +# Setup the basic networking for the routers +setup_rt_networking() +{ + local rt=$1 + local nsname=rt-${rt} + + ip netns add ${nsname} + ip link set veth-rt-${rt} netns ${nsname} + ip -netns ${nsname} link set veth-rt-${rt} name veth0 + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad + ip -netns ${nsname} link set veth0 up + ip -netns ${nsname} link set lo up + + ip netns exec ${nsname} sysctl -wq net.ipv4.ip_forward=1 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.forwarding=1 +} + +setup_hs() +{ + local hs=$1 + local rt=$2 + local tid=$3 + local hsname=hs-t${tid}-${hs} + local rtname=rt-${rt} + local rtveth=veth-t${tid} + + # set the networking for the host + ip netns add ${hsname} + + ip netns exec ${hsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${hsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} + ip -netns ${hsname} link set ${rtveth} netns ${rtname} + ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hs}/64 dev veth0 nodad + ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0 + ip -netns ${hsname} link set veth0 up + ip -netns ${hsname} link set lo up + + # configure the VRF for the tenant X on the router which is directly + # connected to the source host. + ip -netns ${rtname} link add vrf-${tid} type vrf table ${tid} + ip -netns ${rtname} link set vrf-${tid} up + + ip netns exec ${rtname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${rtname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + + # enslave the veth-tX interface to the vrf-X in the access router + ip -netns ${rtname} link set ${rtveth} master vrf-${tid} + ip -netns ${rtname} addr add ${IPv6_HS_NETWORK}::254/64 dev ${rtveth} nodad + ip -netns ${rtname} addr add ${IPv4_HS_NETWORK}.254/24 dev ${rtveth} + ip -netns ${rtname} link set ${rtveth} up + + ip netns exec ${rtname} sysctl -wq net.ipv6.conf.${rtveth}.proxy_ndp=1 + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 + + # disable the rp_filter otherwise the kernel gets confused about how + # to route decap ipv4 packets. + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0 + + ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode" +} + +setup_vpn_config() +{ + local hssrc=$1 + local rtsrc=$2 + local hsdst=$3 + local rtdst=$4 + local tid=$5 + + local hssrc_name=hs-t${tid}-${hssrc} + local hsdst_name=hs-t${tid}-${hsdst} + local rtsrc_name=rt-${rtsrc} + local rtdst_name=rt-${rtdst} + local rtveth=veth-t${tid} + local vpn_sid=${VPN_LOCATOR_SERVICE}:${hssrc}${hsdst}:${tid}::6046 + + ip -netns ${rtsrc_name} -6 neigh add proxy ${IPv6_HS_NETWORK}::${hsdst} dev ${rtveth} + + # set the encap route for encapsulating packets which arrive from the + # host hssrc and destined to the access router rtsrc. + ip -netns ${rtsrc_name} -6 route add ${IPv6_HS_NETWORK}::${hsdst}/128 vrf vrf-${tid} \ + encap seg6 mode encap segs ${vpn_sid} dev veth0 + ip -netns ${rtsrc_name} -4 route add ${IPv4_HS_NETWORK}.${hsdst}/32 vrf vrf-${tid} \ + encap seg6 mode encap segs ${vpn_sid} dev veth0 + ip -netns ${rtsrc_name} -6 route add ${vpn_sid}/128 vrf vrf-${tid} \ + via fd00::${rtdst} dev veth0 + + # set the decap route for decapsulating packets which arrive from + # the rtdst router and destined to the hsdst host. + ip -netns ${rtdst_name} -6 route add ${vpn_sid}/128 table ${LOCALSID_TABLE_ID} \ + encap seg6local action End.DT46 vrftable ${tid} dev vrf-${tid} + + # all sids for VPNs start with a common locator which is fc00::/16. + # Routes for handling the SRv6 End.DT46 behavior instances are grouped + # together in the 'localsid' table. + # + # NOTE: added only once + if [ -z "$(ip -netns ${rtdst_name} -6 rule show | \ + grep "to ${VPN_LOCATOR_SERVICE}::/16 lookup ${LOCALSID_TABLE_ID}")" ]; then + ip -netns ${rtdst_name} -6 rule add \ + to ${VPN_LOCATOR_SERVICE}::/16 \ + lookup ${LOCALSID_TABLE_ID} prio 999 + fi + + # set default routes to unreachable for both ipv4 and ipv6 + ip -netns ${rtsrc_name} -6 route add unreachable default metric 4278198272 \ + vrf vrf-${tid} + + ip -netns ${rtsrc_name} -4 route add unreachable default metric 4278198272 \ + vrf vrf-${tid} +} + +setup() +{ + ip link add veth-rt-1 type veth peer name veth-rt-2 + # setup the networking for router rt-1 and router rt-2 + setup_rt_networking 1 + setup_rt_networking 2 + + # setup two hosts for the tenant 100. + # - host hs-1 is directly connected to the router rt-1; + # - host hs-2 is directly connected to the router rt-2. + setup_hs 1 1 100 #args: host router tenant + setup_hs 2 2 100 + + # setup two hosts for the tenant 200 + # - host hs-3 is directly connected to the router rt-1; + # - host hs-4 is directly connected to the router rt-2. + setup_hs 3 1 200 + setup_hs 4 2 200 + + # setup the IPv4/IPv6 L3 VPN which connects the host hs-t100-1 and host + # hs-t100-2 within the same tenant 100. + setup_vpn_config 1 1 2 2 100 #args: src_host src_router dst_host dst_router tenant + setup_vpn_config 2 2 1 1 100 + + # setup the IPv4/IPv6 L3 VPN which connects the host hs-t200-3 and host + # hs-t200-4 within the same tenant 200. + setup_vpn_config 3 1 4 2 200 + setup_vpn_config 4 2 3 1 200 +} + +check_rt_connectivity() +{ + local rtsrc=$1 + local rtdst=$2 + + ip netns exec rt-${rtsrc} ping -c 1 -W 1 ${IPv6_RT_NETWORK}::${rtdst} \ + >/dev/null 2>&1 +} + +check_and_log_rt_connectivity() +{ + local rtsrc=$1 + local rtdst=$2 + + check_rt_connectivity ${rtsrc} ${rtdst} + log_test $? 0 "Routers connectivity: rt-${rtsrc} -> rt-${rtdst}" +} + +check_hs_ipv6_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + ip netns exec hs-t${tid}-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \ + ${IPv6_HS_NETWORK}::${hsdst} >/dev/null 2>&1 +} + +check_hs_ipv4_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + ip netns exec hs-t${tid}-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \ + ${IPv4_HS_NETWORK}.${hsdst} >/dev/null 2>&1 +} + +check_and_log_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + check_hs_ipv6_connectivity ${hssrc} ${hsdst} ${tid} + log_test $? 0 "IPv6 Hosts connectivity: hs-t${tid}-${hssrc} -> hs-t${tid}-${hsdst} (tenant ${tid})" + + check_hs_ipv4_connectivity ${hssrc} ${hsdst} ${tid} + log_test $? 0 "IPv4 Hosts connectivity: hs-t${tid}-${hssrc} -> hs-t${tid}-${hsdst} (tenant ${tid})" + +} + +check_and_log_hs_isolation() +{ + local hssrc=$1 + local tidsrc=$2 + local hsdst=$3 + local tiddst=$4 + + check_hs_ipv6_connectivity ${hssrc} ${hsdst} ${tidsrc} + # NOTE: ping should fail + log_test $? 1 "IPv6 Hosts isolation: hs-t${tidsrc}-${hssrc} -X-> hs-t${tiddst}-${hsdst}" + + check_hs_ipv4_connectivity ${hssrc} ${hsdst} ${tidsrc} + # NOTE: ping should fail + log_test $? 1 "IPv4 Hosts isolation: hs-t${tidsrc}-${hssrc} -X-> hs-t${tiddst}-${hsdst}" + +} + + +check_and_log_hs2gw_connectivity() +{ + local hssrc=$1 + local tid=$2 + + check_hs_ipv6_connectivity ${hssrc} 254 ${tid} + log_test $? 0 "IPv6 Hosts connectivity: hs-t${tid}-${hssrc} -> gw (tenant ${tid})" + + check_hs_ipv4_connectivity ${hssrc} 254 ${tid} + log_test $? 0 "IPv4 Hosts connectivity: hs-t${tid}-${hssrc} -> gw (tenant ${tid})" + +} + +router_tests() +{ + log_section "IPv6 routers connectivity test" + + check_and_log_rt_connectivity 1 2 + check_and_log_rt_connectivity 2 1 +} + +host2gateway_tests() +{ + log_section "IPv4/IPv6 connectivity test among hosts and gateway" + + check_and_log_hs2gw_connectivity 1 100 + check_and_log_hs2gw_connectivity 2 100 + + check_and_log_hs2gw_connectivity 3 200 + check_and_log_hs2gw_connectivity 4 200 +} + +host_vpn_tests() +{ + log_section "SRv6 VPN connectivity test among hosts in the same tenant" + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 + + check_and_log_hs_connectivity 3 4 200 + check_and_log_hs_connectivity 4 3 200 +} + +host_vpn_isolation_tests() +{ + local i + local j + local k + local tmp + local l1="1 2" + local l2="3 4" + local t1=100 + local t2=200 + + log_section "SRv6 VPN isolation test among hosts in different tentants" + + for k in 0 1; do + for i in ${l1}; do + for j in ${l2}; do + check_and_log_hs_isolation ${i} ${t1} ${j} ${t2} + done + done + + # let us test the reverse path + tmp="${l1}"; l1="${l2}"; l2="${tmp}" + tmp=${t1}; t1=${t2}; t2=${tmp} + done +} + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit 0 +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit 0 +fi + +modprobe vrf &>/dev/null +if [ ! -e /proc/sys/net/vrf/strict_mode ]; then + echo "SKIP: vrf sysctl does not exist" + exit 0 +fi + +cleanup &>/dev/null + +setup + +router_tests +host2gateway_tests +host_vpn_tests +host_vpn_isolation_tests + +print_log_test_results + +cleanup &>/dev/null + +exit ${ret} diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 426d07875a48..112d41d01b12 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -25,6 +25,47 @@ #define TLS_PAYLOAD_MAX_LEN 16384 #define SOL_TLS 282 +struct tls_crypto_info_keys { + union { + struct tls12_crypto_info_aes_gcm_128 aes128; + struct tls12_crypto_info_chacha20_poly1305 chacha20; + }; + size_t len; +}; + +static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type, + struct tls_crypto_info_keys *tls12) +{ + memset(tls12, 0, sizeof(*tls12)); + + switch (cipher_type) { + case TLS_CIPHER_CHACHA20_POLY1305: + tls12->len = sizeof(struct tls12_crypto_info_chacha20_poly1305); + tls12->chacha20.info.version = tls_version; + tls12->chacha20.info.cipher_type = cipher_type; + break; + case TLS_CIPHER_AES_GCM_128: + tls12->len = sizeof(struct tls12_crypto_info_aes_gcm_128); + tls12->aes128.info.version = tls_version; + tls12->aes128.info.cipher_type = cipher_type; + break; + default: + break; + } +} + +static void memrnd(void *s, size_t n) +{ + int *dword = s; + char *byte; + + for (; n >= 4; n -= 4) + *dword++ = rand(); + byte = (void *)dword; + while (n--) + *byte++ = rand(); +} + FIXTURE(tls_basic) { int fd, cfd; @@ -133,33 +174,16 @@ FIXTURE_VARIANT_ADD(tls, 13_chacha) FIXTURE_SETUP(tls) { - union { - struct tls12_crypto_info_aes_gcm_128 aes128; - struct tls12_crypto_info_chacha20_poly1305 chacha20; - } tls12; + struct tls_crypto_info_keys tls12; struct sockaddr_in addr; socklen_t len; int sfd, ret; - size_t tls12_sz; self->notls = false; len = sizeof(addr); - memset(&tls12, 0, sizeof(tls12)); - switch (variant->cipher_type) { - case TLS_CIPHER_CHACHA20_POLY1305: - tls12_sz = sizeof(struct tls12_crypto_info_chacha20_poly1305); - tls12.chacha20.info.version = variant->tls_version; - tls12.chacha20.info.cipher_type = variant->cipher_type; - break; - case TLS_CIPHER_AES_GCM_128: - tls12_sz = sizeof(struct tls12_crypto_info_aes_gcm_128); - tls12.aes128.info.version = variant->tls_version; - tls12.aes128.info.cipher_type = variant->cipher_type; - break; - default: - tls12_sz = 0; - } + tls_crypto_info_init(variant->tls_version, variant->cipher_type, + &tls12); addr.sin_family = AF_INET; addr.sin_addr.s_addr = htonl(INADDR_ANY); @@ -187,7 +211,7 @@ FIXTURE_SETUP(tls) if (!self->notls) { ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, - tls12_sz); + tls12.len); ASSERT_EQ(ret, 0); } @@ -200,7 +224,7 @@ FIXTURE_SETUP(tls) ASSERT_EQ(ret, 0); ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, - tls12_sz); + tls12.len); ASSERT_EQ(ret, 0); } @@ -308,6 +332,8 @@ TEST_F(tls, recv_max) char recv_mem[TLS_PAYLOAD_MAX_LEN]; char buf[TLS_PAYLOAD_MAX_LEN]; + memrnd(buf, sizeof(buf)); + EXPECT_GE(send(self->fd, buf, send_len, 0), 0); EXPECT_NE(recv(self->cfd, recv_mem, send_len, 0), -1); EXPECT_EQ(memcmp(buf, recv_mem, send_len), 0); @@ -588,6 +614,8 @@ TEST_F(tls, recvmsg_single_max) struct iovec vec; struct msghdr hdr; + memrnd(send_mem, sizeof(send_mem)); + EXPECT_EQ(send(self->fd, send_mem, send_len, 0), send_len); vec.iov_base = (char *)recv_mem; vec.iov_len = TLS_PAYLOAD_MAX_LEN; @@ -610,6 +638,8 @@ TEST_F(tls, recvmsg_multiple) struct msghdr hdr; int i; + memrnd(buf, sizeof(buf)); + EXPECT_EQ(send(self->fd, buf, send_len, 0), send_len); for (i = 0; i < msg_iovlen; i++) { iov_base[i] = (char *)malloc(iov_len); @@ -634,6 +664,8 @@ TEST_F(tls, single_send_multiple_recv) char send_mem[TLS_PAYLOAD_MAX_LEN * 2]; char recv_mem[TLS_PAYLOAD_MAX_LEN * 2]; + memrnd(send_mem, sizeof(send_mem)); + EXPECT_GE(send(self->fd, send_mem, total_len, 0), 0); memset(recv_mem, 0, total_len); @@ -834,18 +866,17 @@ TEST_F(tls, bidir) int ret; if (!self->notls) { - struct tls12_crypto_info_aes_gcm_128 tls12; + struct tls_crypto_info_keys tls12; - memset(&tls12, 0, sizeof(tls12)); - tls12.info.version = variant->tls_version; - tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; + tls_crypto_info_init(variant->tls_version, variant->cipher_type, + &tls12); ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12, - sizeof(tls12)); + tls12.len); ASSERT_EQ(ret, 0); ret = setsockopt(self->cfd, SOL_TLS, TLS_TX, &tls12, - sizeof(tls12)); + tls12.len); ASSERT_EQ(ret, 0); } diff --git a/tools/testing/selftests/net/unicast_extensions.sh b/tools/testing/selftests/net/unicast_extensions.sh index dbf0421986df..66354cdd5ce4 100755 --- a/tools/testing/selftests/net/unicast_extensions.sh +++ b/tools/testing/selftests/net/unicast_extensions.sh @@ -189,6 +189,15 @@ segmenttest 255.255.255.1 255.255.255.254 24 "assign and ping inside 255.255.255 route_test 240.5.6.7 240.5.6.1 255.1.2.1 255.1.2.3 24 "route between 240.5.6/24 and 255.1.2/24 (is allowed)" route_test 0.200.6.7 0.200.38.1 245.99.101.1 245.99.200.111 16 "route between 0.200/16 and 245.99/16 (is allowed)" # +# Test support for lowest address ending in .0 +segmenttest 5.10.15.20 5.10.15.0 24 "assign and ping lowest address (/24)" +# +# Test support for lowest address not ending in .0 +segmenttest 192.168.101.192 192.168.101.193 26 "assign and ping lowest address (/26)" +# +# Routing using lowest address as a gateway/endpoint +route_test 192.168.42.1 192.168.42.0 9.8.7.6 9.8.7.0 24 "routing using lowest address" +# # ============================================== # ==== TESTS THAT CURRENTLY EXPECT FAILURE ===== # ============================================== @@ -202,14 +211,6 @@ segmenttest 255.255.255.1 255.255.255.255 16 "assigning 255.255.255.255 (is forb # Currently Linux does not allow this, so this should fail too segmenttest 127.99.4.5 127.99.4.6 16 "assign and ping inside 127/8 (is forbidden)" # -# Test support for lowest address -# Currently Linux does not allow this, so this should fail too -segmenttest 5.10.15.20 5.10.15.0 24 "assign and ping lowest address (is forbidden)" -# -# Routing using lowest address as a gateway/endpoint -# Currently Linux does not allow this, so this should fail too -route_test 192.168.42.1 192.168.42.0 9.8.7.6 9.8.7.0 24 "routing using lowest address (is forbidden)" -# # Test support for unicast use of class D # Currently Linux does not allow this, so this should fail too segmenttest 225.1.2.3 225.1.2.200 24 "assign and ping class D address (is forbidden)" diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c index 381d874cce99..d7ec1e7da0d0 100644 --- a/tools/testing/selftests/openat2/openat2_test.c +++ b/tools/testing/selftests/openat2/openat2_test.c @@ -155,7 +155,7 @@ struct flag_test { int err; }; -#define NUM_OPENAT2_FLAG_TESTS 24 +#define NUM_OPENAT2_FLAG_TESTS 25 void test_openat2_flags(void) { @@ -229,6 +229,11 @@ void test_openat2_flags(void) { .name = "invalid how.resolve and O_PATH", .how.flags = O_PATH, .how.resolve = 0x1337, .err = -EINVAL }, + + /* currently unknown upper 32 bit rejected. */ + { .name = "currently unknown bit (1 << 63)", + .how.flags = O_RDONLY | (1ULL << 63), + .how.resolve = 0, .err = -EINVAL }, }; BUILD_BUG_ON(ARRAY_LEN(tests) != NUM_OPENAT2_FLAG_TESTS); diff --git a/tools/testing/selftests/rlimits/.gitignore b/tools/testing/selftests/rlimits/.gitignore new file mode 100644 index 000000000000..091021f255b3 --- /dev/null +++ b/tools/testing/selftests/rlimits/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +rlimits-per-userns diff --git a/tools/testing/selftests/rlimits/Makefile b/tools/testing/selftests/rlimits/Makefile new file mode 100644 index 000000000000..03aadb406212 --- /dev/null +++ b/tools/testing/selftests/rlimits/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-or-later + +CFLAGS += -Wall -O2 -g +TEST_GEN_PROGS := rlimits-per-userns + +include ../lib.mk diff --git a/tools/testing/selftests/rlimits/config b/tools/testing/selftests/rlimits/config new file mode 100644 index 000000000000..416bd53ce982 --- /dev/null +++ b/tools/testing/selftests/rlimits/config @@ -0,0 +1 @@ +CONFIG_USER_NS=y diff --git a/tools/testing/selftests/rlimits/rlimits-per-userns.c b/tools/testing/selftests/rlimits/rlimits-per-userns.c new file mode 100644 index 000000000000..26dc949e93ea --- /dev/null +++ b/tools/testing/selftests/rlimits/rlimits-per-userns.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Author: Alexey Gladkov + */ +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define NR_CHILDS 2 + +static char *service_prog; +static uid_t user = 60000; +static uid_t group = 60000; + +static void setrlimit_nproc(rlim_t n) +{ + pid_t pid = getpid(); + struct rlimit limit = { + .rlim_cur = n, + .rlim_max = n + }; + + warnx("(pid=%d): Setting RLIMIT_NPROC=%ld", pid, n); + + if (setrlimit(RLIMIT_NPROC, &limit) < 0) + err(EXIT_FAILURE, "(pid=%d): setrlimit(RLIMIT_NPROC)", pid); +} + +static pid_t fork_child(void) +{ + pid_t pid = fork(); + + if (pid < 0) + err(EXIT_FAILURE, "fork"); + + if (pid > 0) + return pid; + + pid = getpid(); + + warnx("(pid=%d): New process starting ...", pid); + + if (prctl(PR_SET_PDEATHSIG, SIGKILL) < 0) + err(EXIT_FAILURE, "(pid=%d): prctl(PR_SET_PDEATHSIG)", pid); + + signal(SIGUSR1, SIG_DFL); + + warnx("(pid=%d): Changing to uid=%d, gid=%d", pid, user, group); + + if (setgid(group) < 0) + err(EXIT_FAILURE, "(pid=%d): setgid(%d)", pid, group); + if (setuid(user) < 0) + err(EXIT_FAILURE, "(pid=%d): setuid(%d)", pid, user); + + warnx("(pid=%d): Service running ...", pid); + + warnx("(pid=%d): Unshare user namespace", pid); + if (unshare(CLONE_NEWUSER) < 0) + err(EXIT_FAILURE, "unshare(CLONE_NEWUSER)"); + + char *const argv[] = { "service", NULL }; + char *const envp[] = { "I_AM_SERVICE=1", NULL }; + + warnx("(pid=%d): Executing real service ...", pid); + + execve(service_prog, argv, envp); + err(EXIT_FAILURE, "(pid=%d): execve", pid); +} + +int main(int argc, char **argv) +{ + size_t i; + pid_t child[NR_CHILDS]; + int wstatus[NR_CHILDS]; + int childs = NR_CHILDS; + pid_t pid; + + if (getenv("I_AM_SERVICE")) { + pause(); + exit(EXIT_SUCCESS); + } + + service_prog = argv[0]; + pid = getpid(); + + warnx("(pid=%d) Starting testcase", pid); + + /* + * This rlimit is not a problem for root because it can be exceeded. + */ + setrlimit_nproc(1); + + for (i = 0; i < NR_CHILDS; i++) { + child[i] = fork_child(); + wstatus[i] = 0; + usleep(250000); + } + + while (1) { + for (i = 0; i < NR_CHILDS; i++) { + if (child[i] <= 0) + continue; + + errno = 0; + pid_t ret = waitpid(child[i], &wstatus[i], WNOHANG); + + if (!ret || (!WIFEXITED(wstatus[i]) && !WIFSIGNALED(wstatus[i]))) + continue; + + if (ret < 0 && errno != ECHILD) + warn("(pid=%d): waitpid(%d)", pid, child[i]); + + child[i] *= -1; + childs -= 1; + } + + if (!childs) + break; + + usleep(250000); + + for (i = 0; i < NR_CHILDS; i++) { + if (child[i] <= 0) + continue; + kill(child[i], SIGUSR1); + } + } + + for (i = 0; i < NR_CHILDS; i++) { + if (WIFEXITED(wstatus[i])) + warnx("(pid=%d): pid %d exited, status=%d", + pid, -child[i], WEXITSTATUS(wstatus[i])); + else if (WIFSIGNALED(wstatus[i])) + warnx("(pid=%d): pid %d killed by signal %d", + pid, -child[i], WTERMSIG(wstatus[i])); + + if (WIFSIGNALED(wstatus[i]) && WTERMSIG(wstatus[i]) == SIGUSR1) + continue; + + warnx("(pid=%d): Test failed", pid); + exit(EXIT_FAILURE); + } + + warnx("(pid=%d): Test passed", pid); + exit(EXIT_SUCCESS); +} diff --git a/tools/testing/selftests/tc-testing/plugin-lib/scapyPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/scapyPlugin.py index 229ee185b27e..254136e3da5a 100644 --- a/tools/testing/selftests/tc-testing/plugin-lib/scapyPlugin.py +++ b/tools/testing/selftests/tc-testing/plugin-lib/scapyPlugin.py @@ -29,22 +29,26 @@ class SubPlugin(TdcPlugin): return # Check for required fields - scapyinfo = self.args.caseinfo['scapy'] - scapy_keys = ['iface', 'count', 'packet'] - missing_keys = [] - keyfail = False - for k in scapy_keys: - if k not in scapyinfo: - keyfail = True - missing_keys.add(k) - if keyfail: - print('{}: Scapy block present in the test, but is missing info:' - .format(self.sub_class)) - print('{}'.format(missing_keys)) + lscapyinfo = self.args.caseinfo['scapy'] + if type(lscapyinfo) != list: + lscapyinfo = [ lscapyinfo, ] - pkt = eval(scapyinfo['packet']) - if '$' in scapyinfo['iface']: - tpl = Template(scapyinfo['iface']) - scapyinfo['iface'] = tpl.safe_substitute(NAMES) - for count in range(scapyinfo['count']): - sendp(pkt, iface=scapyinfo['iface']) + for scapyinfo in lscapyinfo: + scapy_keys = ['iface', 'count', 'packet'] + missing_keys = [] + keyfail = False + for k in scapy_keys: + if k not in scapyinfo: + keyfail = True + missing_keys.append(k) + if keyfail: + print('{}: Scapy block present in the test, but is missing info:' + .format(self.sub_class)) + print('{}'.format(missing_keys)) + + pkt = eval(scapyinfo['packet']) + if '$' in scapyinfo['iface']: + tpl = Template(scapyinfo['iface']) + scapyinfo['iface'] = tpl.safe_substitute(NAMES) + for count in range(scapyinfo['count']): + sendp(pkt, iface=scapyinfo['iface']) diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json index 4202e95e27b9..bd843ab00a58 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json @@ -406,5 +406,50 @@ "teardown": [ "$TC actions flush action ct" ] + }, + { + "id": "3992", + "name": "Add ct action triggering DNAT tuple conflict", + "category": [ + "actions", + "ct", + "scapy" + ], + "plugins": { + "requires": [ + "nsPlugin", + "scapyPlugin" + ] + }, + "setup": [ + [ + "$TC qdisc del dev $DEV1 ingress", + 0, + 1, + 2, + 255 + ], + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress protocol ip prio 1 flower ct_state -trk action ct commit nat dst addr 20.0.0.1 port 10 pipe action drop", + "scapy": [ + { + "iface": "$DEV0", + "count": 1, + "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.10')/TCP(sport=5000,dport=10)" + }, + { + "iface": "$DEV0", + "count": 1, + "packet": "Ether(type=0x800)/IP(src='10.0.0.10',dst='10.0.0.20')/TCP(sport=5000,dport=10)" + } + ], + "expExitCode": "0", + "verifyCmd": "cat /proc/net/nf_conntrack", + "matchPattern": "dst=10.0.0.20", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json index 41d783254b08..2aad4caa8581 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json @@ -445,6 +445,30 @@ "matchCount": "0", "teardown": [] }, + { + "id": "ba5b", + "name": "Add vlan modify action for protocol 802.1Q setting priority 0", + "category": [ + "actions", + "vlan" + ], + "setup": [ + [ + "$TC actions flush action vlan", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action vlan modify protocol 802.1Q id 5 priority 0 index 100", + "expExitCode": "0", + "verifyCmd": "$TC actions get action vlan index 100", + "matchPattern": "action order [0-9]+: vlan.*modify id 100 priority 0 protocol 802.1Q pipe.*index 100 ref", + "matchCount": "0", + "teardown": [ + "$TC actions flush action vlan" + ] + }, { "id": "6812", "name": "Add vlan modify action for protocol 802.1Q", @@ -463,7 +487,7 @@ "cmdUnderTest": "$TC actions add action vlan modify protocol 802.1Q id 5 index 100", "expExitCode": "0", "verifyCmd": "$TC actions get action vlan index 100", - "matchPattern": "action order [0-9]+: vlan.*modify id 100 protocol 802.1Q priority 0 pipe.*index 100 ref", + "matchPattern": "action order [0-9]+: vlan.*modify id 100 protocol 802.1Q pipe.*index 100 ref", "matchCount": "0", "teardown": [ "$TC actions flush action vlan" @@ -487,7 +511,7 @@ "cmdUnderTest": "$TC actions add action vlan modify protocol 802.1ad id 500 reclassify index 12", "expExitCode": "0", "verifyCmd": "$TC actions get action vlan index 12", - "matchPattern": "action order [0-9]+: vlan.*modify id 500 protocol 802.1ad priority 0 reclassify.*index 12 ref", + "matchPattern": "action order [0-9]+: vlan.*modify id 500 protocol 802.1ad reclassify.*index 12 ref", "matchCount": "1", "teardown": [ "$TC actions flush action vlan" diff --git a/tools/testing/selftests/vm/gup_test.c b/tools/testing/selftests/vm/gup_test.c index 1e662d59c502..fe043f67798b 100644 --- a/tools/testing/selftests/vm/gup_test.c +++ b/tools/testing/selftests/vm/gup_test.c @@ -6,6 +6,8 @@ #include #include #include +#include +#include #include "../../../../mm/gup_test.h" #define MB (1UL << 20) @@ -15,6 +17,12 @@ #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ +static unsigned long cmd = GUP_FAST_BENCHMARK; +static int gup_fd, repeats = 1; +static unsigned long size = 128 * MB; +/* Serialize prints */ +static pthread_mutex_t print_mutex = PTHREAD_MUTEX_INITIALIZER; + static char *cmd_to_str(unsigned long cmd) { switch (cmd) { @@ -34,17 +42,55 @@ static char *cmd_to_str(unsigned long cmd) return "Unknown command"; } +void *gup_thread(void *data) +{ + struct gup_test gup = *(struct gup_test *)data; + int i; + + /* Only report timing information on the *_BENCHMARK commands: */ + if ((cmd == PIN_FAST_BENCHMARK) || (cmd == GUP_FAST_BENCHMARK) || + (cmd == PIN_LONGTERM_BENCHMARK)) { + for (i = 0; i < repeats; i++) { + gup.size = size; + if (ioctl(gup_fd, cmd, &gup)) + perror("ioctl"), exit(1); + + pthread_mutex_lock(&print_mutex); + printf("%s: Time: get:%lld put:%lld us", + cmd_to_str(cmd), gup.get_delta_usec, + gup.put_delta_usec); + if (gup.size != size) + printf(", truncated (size: %lld)", gup.size); + printf("\n"); + pthread_mutex_unlock(&print_mutex); + } + } else { + gup.size = size; + if (ioctl(gup_fd, cmd, &gup)) { + perror("ioctl"); + exit(1); + } + + pthread_mutex_lock(&print_mutex); + printf("%s: done\n", cmd_to_str(cmd)); + if (gup.size != size) + printf("Truncated (size: %lld)\n", gup.size); + pthread_mutex_unlock(&print_mutex); + } + + return NULL; +} + int main(int argc, char **argv) { struct gup_test gup = { 0 }; - unsigned long size = 128 * MB; - int i, fd, filed, opt, nr_pages = 1, thp = -1, repeats = 1, write = 1; - unsigned long cmd = GUP_FAST_BENCHMARK; + int filed, i, opt, nr_pages = 1, thp = -1, write = 1, nthreads = 1, ret; int flags = MAP_PRIVATE, touch = 0; char *file = "/dev/zero"; + pthread_t *tid; char *p; - while ((opt = getopt(argc, argv, "m:r:n:F:f:abctTLUuwWSHpz")) != -1) { + while ((opt = getopt(argc, argv, "m:r:n:F:f:abcj:tTLUuwWSHpz")) != -1) { switch (opt) { case 'a': cmd = PIN_FAST_BENCHMARK; @@ -74,6 +120,9 @@ int main(int argc, char **argv) /* strtol, so you can pass flags in hex form */ gup.gup_flags = strtol(optarg, 0, 0); break; + case 'j': + nthreads = atoi(optarg); + break; case 'm': size = atoi(optarg) * MB; break; @@ -154,8 +203,8 @@ int main(int argc, char **argv) if (write) gup.gup_flags |= FOLL_WRITE; - fd = open("/sys/kernel/debug/gup_test", O_RDWR); - if (fd == -1) { + gup_fd = open("/sys/kernel/debug/gup_test", O_RDWR); + if (gup_fd == -1) { perror("open"); exit(1); } @@ -185,32 +234,17 @@ int main(int argc, char **argv) p[0] = 0; } - /* Only report timing information on the *_BENCHMARK commands: */ - if ((cmd == PIN_FAST_BENCHMARK) || (cmd == GUP_FAST_BENCHMARK) || - (cmd == PIN_LONGTERM_BENCHMARK)) { - for (i = 0; i < repeats; i++) { - gup.size = size; - if (ioctl(fd, cmd, &gup)) - perror("ioctl"), exit(1); - - printf("%s: Time: get:%lld put:%lld us", - cmd_to_str(cmd), gup.get_delta_usec, - gup.put_delta_usec); - if (gup.size != size) - printf(", truncated (size: %lld)", gup.size); - printf("\n"); - } - } else { - gup.size = size; - if (ioctl(fd, cmd, &gup)) { - perror("ioctl"); - exit(1); - } - - printf("%s: done\n", cmd_to_str(cmd)); - if (gup.size != size) - printf("Truncated (size: %lld)\n", gup.size); + tid = malloc(sizeof(pthread_t) * nthreads); + assert(tid); + for (i = 0; i < nthreads; i++) { + ret = pthread_create(&tid[i], NULL, gup_thread, &gup); + assert(ret == 0); } + for (i = 0; i < nthreads; i++) { + ret = pthread_join(tid[i], NULL); + assert(ret == 0); + } + free(tid); return 0; } diff --git a/tools/testing/selftests/x86/syscall_numbering.c b/tools/testing/selftests/x86/syscall_numbering.c index d6b09cb1aa2c..991591718bb0 100644 --- a/tools/testing/selftests/x86/syscall_numbering.c +++ b/tools/testing/selftests/x86/syscall_numbering.c @@ -1,6 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * syscall_arg_fault.c - tests faults 32-bit fast syscall stack args + * syscall_numbering.c - test calling the x86-64 kernel with various + * valid and invalid system call numbers. + * * Copyright (c) 2018 Andrew Lutomirski */ @@ -11,79 +13,470 @@ #include #include #include -#include +#include +#include +#include +#include +#include -static int nerrs; +#include +#include +#include +#include -#define X32_BIT 0x40000000UL +#include -static void check_enosys(unsigned long nr, bool *ok) +/* Common system call numbers */ +#define SYS_READ 0 +#define SYS_WRITE 1 +#define SYS_GETPID 39 +/* x64-only system call numbers */ +#define X64_IOCTL 16 +#define X64_READV 19 +#define X64_WRITEV 20 +/* x32-only system call numbers (without X32_BIT) */ +#define X32_IOCTL 514 +#define X32_READV 515 +#define X32_WRITEV 516 + +#define X32_BIT 0x40000000 + +static int nullfd = -1; /* File descriptor for /dev/null */ +static bool with_x32; /* x32 supported on this kernel? */ + +enum ptrace_pass { + PTP_NOTHING, + PTP_GETREGS, + PTP_WRITEBACK, + PTP_FUZZRET, + PTP_FUZZHIGH, + PTP_INTNUM, + PTP_DONE +}; + +static const char * const ptrace_pass_name[] = { - /* If this fails, a segfault is reasonably likely. */ - fflush(stdout); + [PTP_NOTHING] = "just stop, no data read", + [PTP_GETREGS] = "only getregs", + [PTP_WRITEBACK] = "getregs, unmodified setregs", + [PTP_FUZZRET] = "modifying the default return", + [PTP_FUZZHIGH] = "clobbering the top 32 bits", + [PTP_INTNUM] = "sign-extending the syscall number", +}; - long ret = syscall(nr, 0, 0, 0, 0, 0, 0); - if (ret == 0) { - printf("[FAIL]\tsyscall %lu succeeded, but it should have failed\n", nr); - *ok = false; - } else if (errno != ENOSYS) { - printf("[FAIL]\tsyscall %lu had error code %d, but it should have reported ENOSYS\n", nr, errno); - *ok = false; - } +/* + * Shared memory block between tracer and test + */ +struct shared { + unsigned int nerr; /* Total error count */ + unsigned int indent; /* Message indentation level */ + enum ptrace_pass ptrace_pass; + bool probing_syscall; /* In probe_syscall() */ +}; +static volatile struct shared *sh; + +static inline unsigned int offset(void) +{ + unsigned int level = sh ? sh->indent : 0; + + return 8 + level * 4; } -static void test_x32_without_x32_bit(void) +#define msg(lvl, fmt, ...) printf("%-*s" fmt, offset(), "[" #lvl "]", \ + ## __VA_ARGS__) + +#define run(fmt, ...) msg(RUN, fmt, ## __VA_ARGS__) +#define info(fmt, ...) msg(INFO, fmt, ## __VA_ARGS__) +#define ok(fmt, ...) msg(OK, fmt, ## __VA_ARGS__) + +#define fail(fmt, ...) \ + do { \ + msg(FAIL, fmt, ## __VA_ARGS__); \ + sh->nerr++; \ + } while (0) + +#define crit(fmt, ...) \ + do { \ + sh->indent = 0; \ + msg(FAIL, fmt, ## __VA_ARGS__); \ + msg(SKIP, "Unable to run test\n"); \ + exit(EX_OSERR); \ + } while (0) + +/* Sentinel for ptrace-modified return value */ +#define MODIFIED_BY_PTRACE -9999 + +/* + * Directly invokes the given syscall with nullfd as the first argument + * and the rest zero. Avoids involving glibc wrappers in case they ever + * end up intercepting some system calls for some reason, or modify + * the system call number itself. + */ +static long long probe_syscall(int msb, int lsb) { - bool ok = true; + register long long arg1 asm("rdi") = nullfd; + register long long arg2 asm("rsi") = 0; + register long long arg3 asm("rdx") = 0; + register long long arg4 asm("r10") = 0; + register long long arg5 asm("r8") = 0; + register long long arg6 asm("r9") = 0; + long long nr = ((long long)msb << 32) | (unsigned int)lsb; + long long ret; /* - * Syscalls 512-547 are "x32" syscalls. They are intended to be - * called with the x32 (0x40000000) bit set. Calling them without - * the x32 bit set is nonsense and should not work. + * We pass in an extra copy of the extended system call number + * in %rbx, so we can examine it from the ptrace handler without + * worrying about it being possibly modified. This is to test + * the validity of struct user regs.orig_rax a.k.a. + * struct pt_regs.orig_ax. */ - printf("[RUN]\tChecking syscalls 512-547\n"); - for (int i = 512; i <= 547; i++) - check_enosys(i, &ok); + sh->probing_syscall = true; + asm volatile("syscall" + : "=a" (ret) + : "a" (nr), "b" (nr), + "r" (arg1), "r" (arg2), "r" (arg3), + "r" (arg4), "r" (arg5), "r" (arg6) + : "rcx", "r11", "memory", "cc"); + sh->probing_syscall = false; + + return ret; +} + +static const char *syscall_str(int msb, int start, int end) +{ + static char buf[64]; + const char * const type = (start & X32_BIT) ? "x32" : "x64"; + int lsb = start; /* - * Check that a handful of 64-bit-only syscalls are rejected if the x32 - * bit is set. + * Improve readability by stripping the x32 bit, but round + * toward zero so we don't display -1 as -1073741825. */ - printf("[RUN]\tChecking some 64-bit syscalls in x32 range\n"); - check_enosys(16 | X32_BIT, &ok); /* ioctl */ - check_enosys(19 | X32_BIT, &ok); /* readv */ - check_enosys(20 | X32_BIT, &ok); /* writev */ - - /* - * Check some syscalls with high bits set. - */ - printf("[RUN]\tChecking numbers above 2^32-1\n"); - check_enosys((1UL << 32), &ok); - check_enosys(X32_BIT | (1UL << 32), &ok); - - if (!ok) - nerrs++; + if (lsb < 0) + lsb |= X32_BIT; else - printf("[OK]\tThey all returned -ENOSYS\n"); + lsb &= ~X32_BIT; + + if (start == end) + snprintf(buf, sizeof buf, "%s syscall %d:%d", + type, msb, lsb); + else + snprintf(buf, sizeof buf, "%s syscalls %d:%d..%d", + type, msb, lsb, lsb + (end-start)); + + return buf; } -int main() +static unsigned int _check_for(int msb, int start, int end, long long expect, + const char *expect_str) { - /* - * Anyone diagnosing a failure will want to know whether the kernel - * supports x32. Tell them. - */ - printf("\tChecking for x32..."); - fflush(stdout); - if (syscall(39 | X32_BIT, 0, 0, 0, 0, 0, 0) >= 0) { - printf(" supported\n"); - } else if (errno == ENOSYS) { - printf(" not supported\n"); - } else { - printf(" confused\n"); + unsigned int err = 0; + + sh->indent++; + if (start != end) + sh->indent++; + + for (int nr = start; nr <= end; nr++) { + long long ret = probe_syscall(msb, nr); + + if (ret != expect) { + fail("%s returned %lld, but it should have returned %s\n", + syscall_str(msb, nr, nr), + ret, expect_str); + err++; + } } - test_x32_without_x32_bit(); + if (start != end) + sh->indent--; - return nerrs ? 1 : 0; + if (err) { + if (start != end) + fail("%s had %u failure%s\n", + syscall_str(msb, start, end), + err, err == 1 ? "s" : ""); + } else { + ok("%s returned %s as expected\n", + syscall_str(msb, start, end), expect_str); + } + + sh->indent--; + + return err; +} + +#define check_for(msb,start,end,expect) \ + _check_for(msb,start,end,expect,#expect) + +static bool check_zero(int msb, int nr) +{ + return check_for(msb, nr, nr, 0); +} + +static bool check_enosys(int msb, int nr) +{ + return check_for(msb, nr, nr, -ENOSYS); +} + +/* + * Anyone diagnosing a failure will want to know whether the kernel + * supports x32. Tell them. This can also be used to conditionalize + * tests based on existence or nonexistence of x32. + */ +static bool test_x32(void) +{ + long long ret; + pid_t mypid = getpid(); + + run("Checking for x32 by calling x32 getpid()\n"); + ret = probe_syscall(0, SYS_GETPID | X32_BIT); + + sh->indent++; + if (ret == mypid) { + info("x32 is supported\n"); + with_x32 = true; + } else if (ret == -ENOSYS) { + info("x32 is not supported\n"); + with_x32 = false; + } else { + fail("x32 getpid() returned %lld, but it should have returned either %lld or -ENOSYS\n", ret, (long long)mypid); + with_x32 = false; + } + sh->indent--; + return with_x32; +} + +static void test_syscalls_common(int msb) +{ + enum ptrace_pass pass = sh->ptrace_pass; + + run("Checking some common syscalls as 64 bit\n"); + check_zero(msb, SYS_READ); + check_zero(msb, SYS_WRITE); + + run("Checking some 64-bit only syscalls as 64 bit\n"); + check_zero(msb, X64_READV); + check_zero(msb, X64_WRITEV); + + run("Checking out of range system calls\n"); + check_for(msb, -64, -2, -ENOSYS); + if (pass >= PTP_FUZZRET) + check_for(msb, -1, -1, MODIFIED_BY_PTRACE); + else + check_for(msb, -1, -1, -ENOSYS); + check_for(msb, X32_BIT-64, X32_BIT-1, -ENOSYS); + check_for(msb, -64-X32_BIT, -1-X32_BIT, -ENOSYS); + check_for(msb, INT_MAX-64, INT_MAX-1, -ENOSYS); +} + +static void test_syscalls_with_x32(int msb) +{ + /* + * Syscalls 512-547 are "x32" syscalls. They are + * intended to be called with the x32 (0x40000000) bit + * set. Calling them without the x32 bit set is + * nonsense and should not work. + */ + run("Checking x32 syscalls as 64 bit\n"); + check_for(msb, 512, 547, -ENOSYS); + + run("Checking some common syscalls as x32\n"); + check_zero(msb, SYS_READ | X32_BIT); + check_zero(msb, SYS_WRITE | X32_BIT); + + run("Checking some x32 syscalls as x32\n"); + check_zero(msb, X32_READV | X32_BIT); + check_zero(msb, X32_WRITEV | X32_BIT); + + run("Checking some 64-bit syscalls as x32\n"); + check_enosys(msb, X64_IOCTL | X32_BIT); + check_enosys(msb, X64_READV | X32_BIT); + check_enosys(msb, X64_WRITEV | X32_BIT); +} + +static void test_syscalls_without_x32(int msb) +{ + run("Checking for absence of x32 system calls\n"); + check_for(msb, 0 | X32_BIT, 999 | X32_BIT, -ENOSYS); +} + +static void test_syscall_numbering(void) +{ + static const int msbs[] = { + 0, 1, -1, X32_BIT-1, X32_BIT, X32_BIT-1, -X32_BIT, INT_MAX, + INT_MIN, INT_MIN+1 + }; + + sh->indent++; + + /* + * The MSB is supposed to be ignored, so we loop over a few + * to test that out. + */ + for (size_t i = 0; i < sizeof(msbs)/sizeof(msbs[0]); i++) { + int msb = msbs[i]; + run("Checking system calls with msb = %d (0x%x)\n", + msb, msb); + + sh->indent++; + + test_syscalls_common(msb); + if (with_x32) + test_syscalls_with_x32(msb); + else + test_syscalls_without_x32(msb); + + sh->indent--; + } + + sh->indent--; +} + +static void syscall_numbering_tracee(void) +{ + enum ptrace_pass pass; + + if (ptrace(PTRACE_TRACEME, 0, 0, 0)) { + crit("Failed to request tracing\n"); + return; + } + raise(SIGSTOP); + + for (sh->ptrace_pass = pass = PTP_NOTHING; pass < PTP_DONE; + sh->ptrace_pass = ++pass) { + run("Running tests under ptrace: %s\n", ptrace_pass_name[pass]); + test_syscall_numbering(); + } +} + +static void mess_with_syscall(pid_t testpid, enum ptrace_pass pass) +{ + struct user_regs_struct regs; + + sh->probing_syscall = false; /* Do this on entry only */ + + /* For these, don't even getregs */ + if (pass == PTP_NOTHING || pass == PTP_DONE) + return; + + ptrace(PTRACE_GETREGS, testpid, NULL, ®s); + + if (regs.orig_rax != regs.rbx) { + fail("orig_rax %#llx doesn't match syscall number %#llx\n", + (unsigned long long)regs.orig_rax, + (unsigned long long)regs.rbx); + } + + switch (pass) { + case PTP_GETREGS: + /* Just read, no writeback */ + return; + case PTP_WRITEBACK: + /* Write back the same register state verbatim */ + break; + case PTP_FUZZRET: + regs.rax = MODIFIED_BY_PTRACE; + break; + case PTP_FUZZHIGH: + regs.rax = MODIFIED_BY_PTRACE; + regs.orig_rax = regs.orig_rax | 0xffffffff00000000ULL; + break; + case PTP_INTNUM: + regs.rax = MODIFIED_BY_PTRACE; + regs.orig_rax = (int)regs.orig_rax; + break; + default: + crit("invalid ptrace_pass\n"); + break; + } + + ptrace(PTRACE_SETREGS, testpid, NULL, ®s); +} + +static void syscall_numbering_tracer(pid_t testpid) +{ + int wstatus; + + do { + pid_t wpid = waitpid(testpid, &wstatus, 0); + if (wpid < 0 && errno != EINTR) + break; + if (wpid != testpid) + continue; + if (!WIFSTOPPED(wstatus)) + break; /* Thread exited? */ + + if (sh->probing_syscall && WSTOPSIG(wstatus) == SIGTRAP) + mess_with_syscall(testpid, sh->ptrace_pass); + } while (sh->ptrace_pass != PTP_DONE && + !ptrace(PTRACE_SYSCALL, testpid, NULL, NULL)); + + ptrace(PTRACE_DETACH, testpid, NULL, NULL); + + /* Wait for the child process to terminate */ + while (waitpid(testpid, &wstatus, 0) != testpid || !WIFEXITED(wstatus)) + /* wait some more */; +} + +static void test_traced_syscall_numbering(void) +{ + pid_t testpid; + + /* Launch the test thread; this thread continues as the tracer thread */ + testpid = fork(); + + if (testpid < 0) { + crit("Unable to launch tracer process\n"); + } else if (testpid == 0) { + syscall_numbering_tracee(); + _exit(0); + } else { + syscall_numbering_tracer(testpid); + } +} + +int main(void) +{ + unsigned int nerr; + + /* + * It is quite likely to get a segfault on a failure, so make + * sure the message gets out by setting stdout to nonbuffered. + */ + setvbuf(stdout, NULL, _IONBF, 0); + + /* + * Harmless file descriptor to work on... + */ + nullfd = open("/dev/null", O_RDWR); + if (nullfd < 0) { + crit("Unable to open /dev/null: %s\n", strerror(errno)); + } + + /* + * Set up a block of shared memory... + */ + sh = mmap(NULL, sysconf(_SC_PAGE_SIZE), PROT_READ|PROT_WRITE, + MAP_ANONYMOUS|MAP_SHARED, 0, 0); + if (sh == MAP_FAILED) { + crit("Unable to allocated shared memory block: %s\n", + strerror(errno)); + } + + with_x32 = test_x32(); + + run("Running tests without ptrace...\n"); + test_syscall_numbering(); + + test_traced_syscall_numbering(); + + nerr = sh->nerr; + if (!nerr) { + ok("All system calls succeeded or failed as expected\n"); + return 0; + } else { + fail("A total of %u system call%s had incorrect behavior\n", + nerr, nerr != 1 ? "s" : ""); + return 1; + } } diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 93cbd6f603f9..2acbb7703c6a 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -84,7 +84,7 @@ void vsock_wait_remote_close(int fd) } /* Connect to and return the file descriptor. */ -int vsock_stream_connect(unsigned int cid, unsigned int port) +static int vsock_connect(unsigned int cid, unsigned int port, int type) { union { struct sockaddr sa; @@ -101,7 +101,7 @@ int vsock_stream_connect(unsigned int cid, unsigned int port) control_expectln("LISTENING"); - fd = socket(AF_VSOCK, SOCK_STREAM, 0); + fd = socket(AF_VSOCK, type, 0); timeout_begin(TIMEOUT); do { @@ -120,11 +120,21 @@ int vsock_stream_connect(unsigned int cid, unsigned int port) return fd; } +int vsock_stream_connect(unsigned int cid, unsigned int port) +{ + return vsock_connect(cid, port, SOCK_STREAM); +} + +int vsock_seqpacket_connect(unsigned int cid, unsigned int port) +{ + return vsock_connect(cid, port, SOCK_SEQPACKET); +} + /* Listen on and return the first incoming connection. The remote * address is stored to clientaddrp. clientaddrp may be NULL. */ -int vsock_stream_accept(unsigned int cid, unsigned int port, - struct sockaddr_vm *clientaddrp) +static int vsock_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp, int type) { union { struct sockaddr sa; @@ -145,7 +155,7 @@ int vsock_stream_accept(unsigned int cid, unsigned int port, int client_fd; int old_errno; - fd = socket(AF_VSOCK, SOCK_STREAM, 0); + fd = socket(AF_VSOCK, type, 0); if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { perror("bind"); @@ -189,6 +199,18 @@ int vsock_stream_accept(unsigned int cid, unsigned int port, return client_fd; } +int vsock_stream_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp) +{ + return vsock_accept(cid, port, clientaddrp, SOCK_STREAM); +} + +int vsock_seqpacket_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp) +{ + return vsock_accept(cid, port, clientaddrp, SOCK_SEQPACKET); +} + /* Transmit one byte and check the return value. * * expected_ret: diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index e53dd09d26d9..a3375ad2fb7f 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -36,8 +36,11 @@ struct test_case { void init_signals(void); unsigned int parse_cid(const char *str); int vsock_stream_connect(unsigned int cid, unsigned int port); +int vsock_seqpacket_connect(unsigned int cid, unsigned int port); int vsock_stream_accept(unsigned int cid, unsigned int port, struct sockaddr_vm *clientaddrp); +int vsock_seqpacket_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp); void vsock_wait_remote_close(int fd); void send_byte(int fd, int expected_ret, int flags); void recv_byte(int fd, int expected_ret, int flags); diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 5a4fb80fa832..67766bfe176f 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -14,6 +14,8 @@ #include #include #include +#include +#include #include "timeout.h" #include "control.h" @@ -279,6 +281,110 @@ static void test_stream_msg_peek_server(const struct test_opts *opts) close(fd); } +#define MESSAGES_CNT 7 +static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) +{ + int fd; + + fd = vsock_seqpacket_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + /* Send several messages, one with MSG_EOR flag */ + for (int i = 0; i < MESSAGES_CNT; i++) + send_byte(fd, 1, 0); + + control_writeln("SENDDONE"); + close(fd); +} + +static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) +{ + int fd; + char buf[16]; + struct msghdr msg = {0}; + struct iovec iov = {0}; + + fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + control_expectln("SENDDONE"); + iov.iov_base = buf; + iov.iov_len = sizeof(buf); + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + for (int i = 0; i < MESSAGES_CNT; i++) { + if (recvmsg(fd, &msg, 0) != 1) { + perror("message bound violated"); + exit(EXIT_FAILURE); + } + } + + close(fd); +} + +#define MESSAGE_TRUNC_SZ 32 +static void test_seqpacket_msg_trunc_client(const struct test_opts *opts) +{ + int fd; + char buf[MESSAGE_TRUNC_SZ]; + + fd = vsock_seqpacket_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + if (send(fd, buf, sizeof(buf), 0) != sizeof(buf)) { + perror("send failed"); + exit(EXIT_FAILURE); + } + + control_writeln("SENDDONE"); + close(fd); +} + +static void test_seqpacket_msg_trunc_server(const struct test_opts *opts) +{ + int fd; + char buf[MESSAGE_TRUNC_SZ / 2]; + struct msghdr msg = {0}; + struct iovec iov = {0}; + + fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + control_expectln("SENDDONE"); + iov.iov_base = buf; + iov.iov_len = sizeof(buf); + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + ssize_t ret = recvmsg(fd, &msg, MSG_TRUNC); + + if (ret != MESSAGE_TRUNC_SZ) { + printf("%zi\n", ret); + perror("MSG_TRUNC doesn't work"); + exit(EXIT_FAILURE); + } + + if (!(msg.msg_flags & MSG_TRUNC)) { + fprintf(stderr, "MSG_TRUNC expected\n"); + exit(EXIT_FAILURE); + } + + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -309,6 +415,16 @@ static struct test_case test_cases[] = { .run_client = test_stream_msg_peek_client, .run_server = test_stream_msg_peek_server, }, + { + .name = "SOCK_SEQPACKET msg bounds", + .run_client = test_seqpacket_msg_bounds_client, + .run_server = test_seqpacket_msg_bounds_server, + }, + { + .name = "SOCK_SEQPACKET MSG_TRUNC flag", + .run_client = test_seqpacket_msg_trunc_client, + .run_server = test_seqpacket_msg_trunc_server, + }, {}, }; diff --git a/tools/vm/page_owner_sort.c b/tools/vm/page_owner_sort.c index 85eb65ea16d3..0e75f22c9475 100644 --- a/tools/vm/page_owner_sort.c +++ b/tools/vm/page_owner_sort.c @@ -132,6 +132,10 @@ int main(int argc, char **argv) qsort(list, list_size, sizeof(list[0]), compare_txt); list2 = malloc(sizeof(*list) * list_size); + if (!list2) { + printf("Out of memory\n"); + exit(1); + } printf("culling\n"); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6866c1780cf5..7d95126cda9e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2290,7 +2290,7 @@ static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, } retry: - vma = find_vma_intersection(current->mm, addr, addr + 1); + vma = vma_lookup(current->mm, addr); if (vma == NULL) pfn = KVM_PFN_ERR_FAULT;