tmakin/ack-tegra
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'for-5.8' into for-linus

Browse Source
This commit is contained in:
Petr Mladek
2020-06-01 10:15:16 +02:00
parent 6a0af9fc8c eb012d125a
commit d053cf0d77
15035 changed files with 814517 additions and 406602 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.clang-format
+21 -4
View File
@@ -86,6 +86,8 @@ ForEachMacros:
- 'bio_for_each_segment_all'
- 'bio_list_for_each'
- 'bip_for_each_vec'
- 'bitmap_for_each_clear_region'
- 'bitmap_for_each_set_region'
- 'blkg_for_each_descendant_post'
- 'blkg_for_each_descendant_pre'
- 'blk_queue_for_each_rl'
@@ -115,6 +117,7 @@ ForEachMacros:
- 'drm_client_for_each_connector_iter'
- 'drm_client_for_each_modeset'
- 'drm_connector_for_each_possible_encoder'
- 'drm_for_each_bridge_in_chain'
- 'drm_for_each_connector_iter'
- 'drm_for_each_crtc'
- 'drm_for_each_encoder'
@@ -136,9 +139,10 @@ ForEachMacros:
- 'for_each_bio'
- 'for_each_board_func_rsrc'
- 'for_each_bvec'
- 'for_each_card_auxs'
- 'for_each_card_auxs_safe'
- 'for_each_card_components'
- 'for_each_card_links'
- 'for_each_card_links_safe'
- 'for_each_card_pre_auxs'
- 'for_each_card_prelinks'
- 'for_each_card_rtds'
- 'for_each_card_rtds_safe'
@@ -166,6 +170,7 @@ ForEachMacros:
- 'for_each_dpcm_fe'
- 'for_each_drhd_unit'
- 'for_each_dss_dev'
- 'for_each_efi_handle'
- 'for_each_efi_memory_desc'
- 'for_each_efi_memory_desc_in_map'
- 'for_each_element'
@@ -190,6 +195,7 @@ ForEachMacros:
- 'for_each_lru'
- 'for_each_matching_node'
- 'for_each_matching_node_and_match'
- 'for_each_member'
- 'for_each_memblock'
- 'for_each_memblock_type'
- 'for_each_memcg_cache_index'
@@ -200,9 +206,11 @@ ForEachMacros:
- 'for_each_msi_entry'
- 'for_each_msi_entry_safe'
- 'for_each_net'
- 'for_each_net_continue_reverse'
- 'for_each_netdev'
- 'for_each_netdev_continue'
- 'for_each_netdev_continue_rcu'
- 'for_each_netdev_continue_reverse'
- 'for_each_netdev_feature'
- 'for_each_netdev_in_bond_rcu'
- 'for_each_netdev_rcu'
@@ -254,10 +262,10 @@ ForEachMacros:
- 'for_each_reserved_mem_region'
- 'for_each_rtd_codec_dai'
- 'for_each_rtd_codec_dai_rollback'
- 'for_each_rtdcom'
- 'for_each_rtdcom_safe'
- 'for_each_rtd_components'
- 'for_each_set_bit'
- 'for_each_set_bit_from'
- 'for_each_set_clump8'
- 'for_each_sg'
- 'for_each_sg_dma_page'
- 'for_each_sg_page'
@@ -267,6 +275,7 @@ ForEachMacros:
- 'for_each_subelement_id'
- '__for_each_thread'
- 'for_each_thread'
- 'for_each_wakeup_source'
- 'for_each_zone'
- 'for_each_zone_zonelist'
- 'for_each_zone_zonelist_nodemask'
@@ -330,6 +339,7 @@ ForEachMacros:
- 'list_for_each'
- 'list_for_each_codec'
- 'list_for_each_codec_safe'
- 'list_for_each_continue'
- 'list_for_each_entry'
- 'list_for_each_entry_continue'
- 'list_for_each_entry_continue_rcu'
@@ -351,6 +361,7 @@ ForEachMacros:
- 'llist_for_each_entry'
- 'llist_for_each_entry_safe'
- 'llist_for_each_safe'
- 'mci_for_each_dimm'
- 'media_device_for_each_entity'
- 'media_device_for_each_intf'
- 'media_device_for_each_link'
@@ -444,10 +455,16 @@ ForEachMacros:
- 'virtio_device_for_each_vq'
- 'xa_for_each'
- 'xa_for_each_marked'
- 'xa_for_each_range'
- 'xa_for_each_start'
- 'xas_for_each'
- 'xas_for_each_conflict'
- 'xas_for_each_marked'
- 'xbc_array_for_each_value'
- 'xbc_for_each_key_value'
- 'xbc_node_for_each_array_value'
- 'xbc_node_for_each_child'
- 'xbc_node_for_each_key_value'
- 'zorro_for_each_dev'
#IncludeBlocks: Preserve # Unknown to clang-format-5.0
.gitignore
+1
View File
@@ -1,3 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
#
# NOTE! Don't add files that are generated in specific
# subdirectories here. Add them in the ".gitignore" file
.mailmap
+8
View File
@@ -18,6 +18,7 @@ Aleksey Gorelov <aleksey_gorelov@phoenix.com>
Aleksandar Markovic <aleksandar.markovic@mips.com> <aleksandar.markovic@imgtec.com>
Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@intel.com>
Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@linaro.org>
Alexandre Belloni <alexandre.belloni@bootlin.com> <alexandre.belloni@free-electrons.com>
Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
@@ -27,6 +28,8 @@ Andi Shyti <andi@etezian.org> <andi.shyti@samsung.com>
Andreas Herrmann <aherrman@de.ibm.com>
Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
Andrew Morton <akpm@linux-foundation.org>
Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com>
Andrew Murray <amurray@thegoodpenguin.co.uk> <amurray@embedded-bits.co.uk>
Andrew Vasquez <andrew.vasquez@qlogic.com>
Andy Adamson <andros@citi.umich.edu>
Antoine Tenart <antoine.tenart@free-electrons.com>
@@ -207,6 +210,7 @@ Oleksij Rempel <linux@rempel-privat.de> <external.Oleksij.Rempel@de.bosch.com>
Oleksij Rempel <linux@rempel-privat.de> <fixed-term.Oleksij.Rempel@de.bosch.com>
Oleksij Rempel <linux@rempel-privat.de> <o.rempel@pengutronix.de>
Oleksij Rempel <linux@rempel-privat.de> <ore@pengutronix.de>
Pali Rohár <pali@kernel.org> <pali.rohar@gmail.com>
Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Patrick Mochel <mochel@digitalimplant.org>
Paul Burton <paulburton@kernel.org> <paul.burton@imgtec.com>
@@ -222,6 +226,7 @@ Pratyush Anand <pratyush.anand@gmail.com> <pratyush.anand@st.com>
Praveen BP <praveenbp@ti.com>
Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com>
Qais Yousef <qsyousef@gmail.com> <qais.yousef@imgtec.com>
Quentin Monnet <quentin@isovalent.com> <quentin.monnet@netronome.com>
Quentin Perret <qperret@qperret.net> <quentin.perret@arm.com>
Rafael J. Wysocki <rjw@rjwysocki.net> <rjw@sisk.pl>
Rajesh Shah <rajesh.shah@intel.com>
@@ -240,9 +245,11 @@ Santosh Shilimkar <ssantosh@kernel.org>
Santosh Shilimkar <santosh.shilimkar@oracle.org>
Sascha Hauer <s.hauer@pengutronix.de>
S.Çağlar Onur <caglar@pardus.org.tr>
Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi>
Sean Nyekjaer <sean@geanix.com> <sean.nyekjaer@prevas.dk>
Sebastian Reichel <sre@kernel.org> <sre@debian.org>
Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk>
Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de>
Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com>
Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com>
Shuah Khan <shuah@kernel.org> <shuah.khan@hp.com>
@@ -259,6 +266,7 @@ Sumit Semwal <sumit.semwal@ti.com>
Tejun Heo <htejun@gmail.com>
Thomas Graf <tgraf@suug.ch>
Thomas Pedersen <twp@codeaurora.org>
Tiezhu Yang <yangtiezhu@loongson.cn> <kernelpatch@126.com>
Todor Tomov <todor.too@gmail.com> <todor.tomov@linaro.org>
Tony Luck <tony.luck@intel.com>
TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
COPYING
+2
View File
@@ -16,3 +16,5 @@ In addition, other licenses may also apply. Please see:
Documentation/process/license-rules.rst
for more details.
All contributions to the Linux Kernel are subject to this COPYING file.
CREDITS
+5
View File
@@ -567,6 +567,11 @@ D: Original author of Amiga FFS filesystem
S: Orlando, Florida
S: USA
N: Paul Burton
E: paulburton@kernel.org
W: https://pburton.com
D: MIPS maintainer 2018-2020
N: Lennert Buytenhek
E: kernel@wantstofly.org
D: Original (2.4) rewrite of the ethernet bridging code
Documentation/.gitignore
+1
View File
@@ -1,2 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
output
*.pyc
Documentation/ABI/obsolete/sysfs-kernel-fadump_enabled
+9
View File
@@ -0,0 +1,9 @@
This ABI is renamed and moved to a new location /sys/kernel/fadump/enabled.
What: /sys/kernel/fadump_enabled
Date: Feb 2012
Contact: linuxppc-dev@lists.ozlabs.org
Description: read only
Primarily used to identify whether the FADump is enabled in
the kernel or not.
User: Kdump service
Documentation/ABI/obsolete/sysfs-kernel-fadump_registered
+10
View File
@@ -0,0 +1,10 @@
This ABI is renamed and moved to a new location /sys/kernel/fadump/registered.¬
What: /sys/kernel/fadump_registered
Date: Feb 2012
Contact: linuxppc-dev@lists.ozlabs.org
Description: read/write
Helps to control the dump collect feature from userspace.
Setting 1 to this file enables the system to collect the
dump and 0 to disable it.
User: Kdump service
Documentation/ABI/obsolete/sysfs-kernel-fadump_release_mem
+10
View File
@@ -0,0 +1,10 @@
This ABI is renamed and moved to a new location /sys/kernel/fadump/release_mem.¬
What: /sys/kernel/fadump_release_mem
Date: Feb 2012
Contact: linuxppc-dev@lists.ozlabs.org
Description: write only
This is a special sysfs file and only available when
the system is booted to capture the vmcore using FADump.
It is used to release the memory reserved by FADump to
save the crash dump.
Documentation/ABI/obsolete/sysfs-selinux-checkreqprot
+23
View File
@@ -0,0 +1,23 @@
What: /sys/fs/selinux/checkreqprot
Date: April 2005 (predates git)
KernelVersion: 2.6.12-rc2 (predates git)
Contact: selinux@vger.kernel.org
Description:
The selinuxfs "checkreqprot" node allows SELinux to be configured
to check the protection requested by userspace for mmap/mprotect
calls instead of the actual protection applied by the kernel.
This was a compatibility mechanism for legacy userspace and
for the READ_IMPLIES_EXEC personality flag. However, if set to
1, it weakens security by allowing mappings to be made executable
without authorization by policy. The default value of checkreqprot
at boot was changed starting in Linux v4.4 to 0 (i.e. check the
actual protection), and Android and Linux distributions have been
explicitly writing a "0" to /sys/fs/selinux/checkreqprot during
initialization for some time. Support for setting checkreqprot to 1
will be removed in a future kernel release, at which point the kernel
will always cease using checkreqprot internally and will always
check the actual protections being applied upon mmap/mprotect calls.
The checkreqprot selinuxfs node will remain for backward compatibility
but will discard writes of the "0" value and will reject writes of the
"1" value when this mechanism is removed.
Documentation/ABI/removed/sysfs-kernel-fadump_release_opalcore
+9
View File
@@ -0,0 +1,9 @@
This ABI is moved to /sys/firmware/opal/mpipl/release_core.
What: /sys/kernel/fadump_release_opalcore
Date: Sep 2019
Contact: linuxppc-dev@lists.ozlabs.org
Description: write only
The sysfs file is available when the system is booted to
collect the dump on OPAL based machine. It used to release
the memory used to collect the opalcore.
Documentation/ABI/testing/sysfs-kernel-uids → Documentation/ABI/removed/sysfs-kernel-uids
+1 -1
View File
@@ -1,5 +1,5 @@
What: /sys/kernel/uids/<uid>/cpu_shares
Date: December 2007
Date: December 2007, finally removed in kernel v2.6.34-rc1
Contact: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Description:
Documentation/ABI/testing/configfs-most
+196
View File
@@ -0,0 +1,196 @@
What: /sys/kernel/config/most_<component>
Date: March 8, 2019
KernelVersion: 5.2
Description: Interface is used to configure and connect device channels
to component drivers.
Attributes are visible only when configfs is mounted. To mount
configfs in /sys/kernel/config directory use:
# mount -t configfs none /sys/kernel/config/
What: /sys/kernel/config/most_cdev/<link>
Date: March 8, 2019
KernelVersion: 5.2
Description:
The attributes:
buffer_size configure the buffer size for this channel
subbuffer_size configure the sub-buffer size for this channel
(needed for synchronous and isochrnous data)
num_buffers configure number of buffers used for this
channel
datatype configure type of data that will travel over
this channel
direction configure whether this link will be an input
or output
dbr_size configure DBR data buffer size (this is used
for MediaLB communication only)
packets_per_xact
configure the number of packets that will be
collected from the network before being
transmitted via USB (this is used for USB
communication only)
device name of the device the link is to be attached to
channel name of the channel the link is to be attached to
comp_params pass parameters needed by some components
create_link write '1' to this attribute to trigger the
creation of the link. In case of speculative
configuration, the creation is post-poned until
a physical device is being attached to the bus.
destroy_link write '1' to this attribute to destroy an
active link
What: /sys/kernel/config/most_video/<link>
Date: March 8, 2019
KernelVersion: 5.2
Description:
The attributes:
buffer_size configure the buffer size for this channel
subbuffer_size configure the sub-buffer size for this channel
(needed for synchronous and isochrnous data)
num_buffers configure number of buffers used for this
channel
datatype configure type of data that will travel over
this channel
direction configure whether this link will be an input
or output
dbr_size configure DBR data buffer size (this is used
for MediaLB communication only)
packets_per_xact
configure the number of packets that will be
collected from the network before being
transmitted via USB (this is used for USB
communication only)
device name of the device the link is to be attached to
channel name of the channel the link is to be attached to
comp_params pass parameters needed by some components
create_link write '1' to this attribute to trigger the
creation of the link. In case of speculative
configuration, the creation is post-poned until
a physical device is being attached to the bus.
destroy_link write '1' to this attribute to destroy an
active link
What: /sys/kernel/config/most_net/<link>
Date: March 8, 2019
KernelVersion: 5.2
Description:
The attributes:
buffer_size configure the buffer size for this channel
subbuffer_size configure the sub-buffer size for this channel
(needed for synchronous and isochrnous data)
num_buffers configure number of buffers used for this
channel
datatype configure type of data that will travel over
this channel
direction configure whether this link will be an input
or output
dbr_size configure DBR data buffer size (this is used
for MediaLB communication only)
packets_per_xact
configure the number of packets that will be
collected from the network before being
transmitted via USB (this is used for USB
communication only)
device name of the device the link is to be attached to
channel name of the channel the link is to be attached to
comp_params pass parameters needed by some components
create_link write '1' to this attribute to trigger the
creation of the link. In case of speculative
configuration, the creation is post-poned until
a physical device is being attached to the bus.
destroy_link write '1' to this attribute to destroy an
active link
What: /sys/kernel/config/most_sound/<card>
Date: March 8, 2019
KernelVersion: 5.2
Description:
The attributes:
create_card write '1' to this attribute to trigger the
registration of the sound card with the ALSA
subsystem.
What: /sys/kernel/config/most_sound/<card>/<link>
Date: March 8, 2019
KernelVersion: 5.2
Description:
The attributes:
buffer_size configure the buffer size for this channel
subbuffer_size configure the sub-buffer size for this channel
(needed for synchronous and isochrnous data)
num_buffers configure number of buffers used for this
channel
datatype configure type of data that will travel over
this channel
direction configure whether this link will be an input
or output
dbr_size configure DBR data buffer size (this is used
for MediaLB communication only)
packets_per_xact
configure the number of packets that will be
collected from the network before being
transmitted via USB (this is used for USB
communication only)
device name of the device the link is to be attached to
channel name of the channel the link is to be attached to
comp_params pass parameters needed by some components
create_link write '1' to this attribute to trigger the
creation of the link. In case of speculative
configuration, the creation is post-poned until
a physical device is being attached to the bus.
destroy_link write '1' to this attribute to destroy an
active link
Documentation/ABI/testing/debugfs-driver-habanalabs
+14
View File
@@ -43,6 +43,20 @@ Description: Allows the root user to read or write directly through the
If the IOMMU is disabled, it also allows the root user to read
or write from the host a device VA of a host mapped memory
What: /sys/kernel/debug/habanalabs/hl<n>/data64
Date: Jan 2020
KernelVersion: 5.6
Contact: oded.gabbay@gmail.com
Description: Allows the root user to read or write 64 bit data directly
through the device's PCI bar. Writing to this file generates a
write transaction while reading from the file generates a read
transaction. This custom interface is needed (instead of using
the generic Linux user-space PCI mapping) because the DDR bar
is very small compared to the DDR memory and only the driver can
move the bar before and after the transaction.
If the IOMMU is disabled, it also allows the root user to read
or write from the host a device VA of a host mapped memory
What: /sys/kernel/debug/habanalabs/hl<n>/device
Date: Jan 2019
KernelVersion: 5.1
Documentation/ABI/testing/dev-kmsg
+5
View File
@@ -56,6 +56,11 @@ Description: The /dev/kmsg character device node provides userspace access
seek after the last record available at the time
the last SYSLOG_ACTION_CLEAR was issued.
Due to the record nature of this interface with a "read all"
behavior and the specific positions each seek operation sets,
SEEK_CUR is not supported, returning -ESPIPE (invalid seek) to
errno whenever requested.
The output format consists of a prefix carrying the syslog
prefix including priority and facility, the 64 bit message
sequence number and the monotonic timestamp in microseconds,
Documentation/ABI/testing/rtc-cdev
+8
View File
@@ -33,6 +33,14 @@ Description:
Requires a separate RTC_PIE_ON call to enable the periodic
interrupts.
* RTC_VL_READ: Read the voltage inputs status of the RTC when
supported. The value is a bit field of RTC_VL_*, giving the
status of the main and backup voltages.
* RTC_VL_CLEAR: Clear the voltage status of the RTC. Some RTCs
need user interaction when the backup power provider is
replaced or charged to be able to clear the status.
The ioctl() calls supported by the older /dev/rtc interface are
also supported by the newer RTC class framework. However,
because the chips and systems are not standardized, some PC/AT
Documentation/ABI/testing/sysfs-bus-coresight-devices-cti
+241
View File
@@ -0,0 +1,241 @@
What: /sys/bus/coresight/devices/<cti-name>/enable
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (RW) Enable/Disable the CTI hardware.
What: /sys/bus/coresight/devices/<cti-name>/powered
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) Indicate if the CTI hardware is powered.
What: /sys/bus/coresight/devices/<cti-name>/ctmid
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) Display the associated CTM ID
What: /sys/bus/coresight/devices/<cti-name>/nr_trigger_cons
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) Number of devices connected to triggers on this CTI
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/name
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) Name of connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/in_signals
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) Input trigger signals from connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/in_types
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) Functional types for the input trigger signals
from connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/out_signals
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) Output trigger signals to connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/triggers<N>/out_types
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) Functional types for the output trigger signals
to connected device <N>
What: /sys/bus/coresight/devices/<cti-name>/regs/inout_sel
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (RW) Select the index for inen and outen registers.
What: /sys/bus/coresight/devices/<cti-name>/regs/inen
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (RW) Read or write the CTIINEN register selected by inout_sel.
What: /sys/bus/coresight/devices/<cti-name>/regs/outen
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (RW) Read or write the CTIOUTEN register selected by inout_sel.
What: /sys/bus/coresight/devices/<cti-name>/regs/gate
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (RW) Read or write CTIGATE register.
What: /sys/bus/coresight/devices/<cti-name>/regs/asicctl
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (RW) Read or write ASICCTL register.
What: /sys/bus/coresight/devices/<cti-name>/regs/intack
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (W) Write the INTACK register.
What: /sys/bus/coresight/devices/<cti-name>/regs/appset
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (RW) Set CTIAPPSET register to activate channel. Read back to
determine current value of register.
What: /sys/bus/coresight/devices/<cti-name>/regs/appclear
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (W) Write APPCLEAR register to deactivate channel.
What: /sys/bus/coresight/devices/<cti-name>/regs/apppulse
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (W) Write APPPULSE to pulse a channel active for one clock
cycle.
What: /sys/bus/coresight/devices/<cti-name>/regs/chinstatus
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) Read current status of channel inputs.
What: /sys/bus/coresight/devices/<cti-name>/regs/choutstatus
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) read current status of channel outputs.
What: /sys/bus/coresight/devices/<cti-name>/regs/triginstatus
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) read current status of input trigger signals
What: /sys/bus/coresight/devices/<cti-name>/regs/trigoutstatus
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) read current status of output trigger signals.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigin_attach
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (W) Attach a CTI input trigger to a CTM channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigin_detach
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (W) Detach a CTI input trigger from a CTM channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigout_attach
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (W) Attach a CTI output trigger to a CTM channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigout_detach
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (W) Detach a CTI output trigger from a CTM channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_gate_enable
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (RW) Enable CTIGATE for single channel (W) or list enabled
channels through the gate (R).
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_gate_disable
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (W) Disable CTIGATE for single channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_set
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (W) Activate a single channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_clear
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (W) Deactivate a single channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_pulse
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (W) Pulse a single channel - activate for a single clock cycle.
What: /sys/bus/coresight/devices/<cti-name>/channels/trigout_filtered
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) List of output triggers filtered across all connections.
What: /sys/bus/coresight/devices/<cti-name>/channels/trig_filter_enable
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (RW) Enable or disable trigger output signal filtering.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_inuse
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) show channels with at least one attached trigger signal.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_free
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) show channels with no attached trigger signals.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_xtrigs_sel
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (RW) Write channel number to select a channel to view, read to
see selected channel number.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_xtrigs_in
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) Read to see input triggers connected to selected view
channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_xtrigs_out
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (R) Read to see output triggers connected to selected view
channel.
What: /sys/bus/coresight/devices/<cti-name>/channels/chan_xtrigs_reset
Date: March 2020
KernelVersion 5.7
Contact: Mike Leach or Mathieu Poirier
Description: (W) Clear all channel / trigger programming.
Documentation/ABI/testing/sysfs-bus-counter-104-quad-8
+25
View File
@@ -1,3 +1,28 @@
What: /sys/bus/counter/devices/counterX/signalY/cable_fault
KernelVersion: 5.7
Contact: linux-iio@vger.kernel.org
Description:
Read-only attribute that indicates whether a differential
encoder cable fault (not connected or loose wires) is detected
for the respective channel of Signal Y. Valid attribute values
are boolean. Detection must first be enabled via the
corresponding cable_fault_enable attribute.
What: /sys/bus/counter/devices/counterX/signalY/cable_fault_enable
KernelVersion: 5.7
Contact: linux-iio@vger.kernel.org
Description:
Whether detection of differential encoder cable faults for the
respective channel of Signal Y is enabled. Valid attribute
values are boolean.
What: /sys/bus/counter/devices/counterX/signalY/filter_clock_prescaler
KernelVersion: 5.7
Contact: linux-iio@vger.kernel.org
Description:
Filter clock factor for input Signal Y. This prescaler value
affects the inputs of both quadrature pair signals.
What: /sys/bus/counter/devices/counterX/signalY/index_polarity
KernelVersion: 5.2
Contact: linux-iio@vger.kernel.org
Documentation/ABI/testing/sysfs-bus-iio-adc-ad7192
+18 -6
View File
@@ -2,17 +2,22 @@ What: /sys/bus/iio/devices/iio:deviceX/ac_excitation_en
KernelVersion:
Contact: linux-iio@vger.kernel.org
Description:
Reading gives the state of AC excitation.
Writing '1' enables AC excitation.
This attribute, if available, is used to enable the AC
excitation mode found on some converters. In ac excitation mode,
the polarity of the excitation voltage is reversed on
alternate cycles, to eliminate DC errors.
What: /sys/bus/iio/devices/iio:deviceX/bridge_switch_en
KernelVersion:
Contact: linux-iio@vger.kernel.org
Description:
This bridge switch is used to disconnect it when there is a
need to minimize the system current consumption.
Reading gives the state of the bridge switch.
Writing '1' enables the bridge switch.
This attribute, if available, is used to close or open the
bridge power down switch found on some converters.
In bridge applications, such as strain gauges and load cells,
the bridge itself consumes the majority of the current in the
system. To minimize the current consumption of the system,
the bridge can be disconnected (when it is not being used
using the bridge_switch_en attribute.
What: /sys/bus/iio/devices/iio:deviceX/in_voltagex_sys_calibration
KernelVersion:
@@ -21,6 +26,13 @@ Description:
Initiates the system calibration procedure. This is done on a
single channel at a time. Write '1' to start the calibration.
What: /sys/bus/iio/devices/iio:deviceX/in_voltage2-voltage2_shorted_raw
KernelVersion:
Contact: linux-iio@vger.kernel.org
Description:
Measure voltage from AIN2 pin connected to AIN(+)
and AIN(-) shorted.
What: /sys/bus/iio/devices/iio:deviceX/in_voltagex_sys_calibration_mode_available
KernelVersion:
Contact: linux-iio@vger.kernel.org
Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc
+8
View File
@@ -40,3 +40,11 @@ Description: (RW) Trigger window switch for the MSC's buffer, in
triggering a window switch for the buffer. Returns an error in any
other operating mode or attempts to write something other than "1".
What: /sys/bus/intel_th/devices/<intel_th_id>-msc<msc-id>/stop_on_full
Date: March 2020
KernelVersion: 5.7
Contact: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Description: (RW) Configure whether trace stops when the last available window
becomes full (1/y/Y) or wraps around and continues until the next
window becomes available again (0/n/N).
Documentation/ABI/testing/sysfs-bus-most
+295
View File
@@ -0,0 +1,295 @@
What: /sys/bus/most/devices/.../description
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Provides information about the interface type and the physical
location of the device. Hardware attached via USB, for instance,
might return <1-1.1:1.0>
Users:
What: /sys/bus/most/devices/.../interface
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Indicates the type of peripheral interface the device uses.
Users:
What: /sys/bus/most/devices/.../dci
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
If the network interface controller is attached via USB, a dci
directory is created that allows applications to read and
write the controller's DCI registers.
Users:
What: /sys/bus/most/devices/.../dci/arb_address
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is used to set an arbitrary DCI register address an
application wants to read from or write to.
Users:
What: /sys/bus/most/devices/.../dci/arb_value
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is used to read and write the DCI register whose address
is stored in arb_address.
Users:
What: /sys/bus/most/devices/.../dci/mep_eui48_hi
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is used to check and configure the MAC address.
Users:
What: /sys/bus/most/devices/.../dci/mep_eui48_lo
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is used to check and configure the MAC address.
Users:
What: /sys/bus/most/devices/.../dci/mep_eui48_mi
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is used to check and configure the MAC address.
Users:
What: /sys/bus/most/devices/.../dci/mep_filter
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is used to check and configure the MEP filter address.
Users:
What: /sys/bus/most/devices/.../dci/mep_hash0
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is used to check and configure the MEP hash table.
Users:
What: /sys/bus/most/devices/.../dci/mep_hash1
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is used to check and configure the MEP hash table.
Users:
What: /sys/bus/most/devices/.../dci/mep_hash2
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is used to check and configure the MEP hash table.
Users:
What: /sys/bus/most/devices/.../dci/mep_hash3
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is used to check and configure the MEP hash table.
Users:
What: /sys/bus/most/devices/.../dci/ni_state
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Indicates the current network interface state.
Users:
What: /sys/bus/most/devices/.../dci/node_address
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Indicates the current node address.
Users:
What: /sys/bus/most/devices/.../dci/node_position
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Indicates the current node position.
Users:
What: /sys/bus/most/devices/.../dci/packet_bandwidth
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Indicates the configured packet bandwidth.
Users:
What: /sys/bus/most/devices/.../dci/sync_ep
Date: June 2016
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Triggers the controller's synchronization process for a certain
endpoint.
Users:
What: /sys/bus/most/devices/.../<channel>/
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
For every channel of the device a directory is created, whose
name is dictated by the HDM. This enables an application to
collect information about the channel's capabilities and
configure it.
Users:
What: /sys/bus/most/devices/.../<channel>/available_datatypes
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Indicates the data types the current channel can transport.
Users:
What: /sys/bus/most/devices/.../<channel>/available_directions
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Indicates the directions the current channel is capable of.
Users:
What: /sys/bus/most/devices/.../<channel>/number_of_packet_buffers
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Indicates the number of packet buffers the current channel can
handle.
Users:
What: /sys/bus/most/devices/.../<channel>/number_of_stream_buffers
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Indicates the number of streaming buffers the current channel can
handle.
Users:
What: /sys/bus/most/devices/.../<channel>/size_of_packet_buffer
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Indicates the size of a packet buffer the current channel can
handle.
Users:
What: /sys/bus/most/devices/.../<channel>/size_of_stream_buffer
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Indicates the size of a streaming buffer the current channel can
handle.
Users:
What: /sys/bus/most/devices/.../<channel>/set_number_of_buffers
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is to configure the number of buffers of the current channel.
Users:
What: /sys/bus/most/devices/.../<channel>/set_buffer_size
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is to configure the size of a buffer of the current channel.
Users:
What: /sys/bus/most/devices/.../<channel>/set_direction
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is to configure the direction of the current channel.
The following strings will be accepted:
'dir_tx',
'dir_rx'
Users:
What: /sys/bus/most/devices/.../<channel>/set_datatype
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is to configure the data type of the current channel.
The following strings will be accepted:
'control',
'async',
'sync',
'isoc_avp'
Users:
What: /sys/bus/most/devices/.../<channel>/set_subbuffer_size
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is to configure the subbuffer size of the current channel.
Users:
What: /sys/bus/most/devices/.../<channel>/set_packets_per_xact
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is to configure the number of packets per transaction of
the current channel. This is only needed network interface
controller is attached via USB.
Users:
What: /sys/bus/most/devices/.../<channel>/channel_starving
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
Indicates whether current channel ran out of buffers.
Users:
What: /sys/bus/most/drivers/most_core/components
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is used to retrieve a list of registered components.
Users:
What: /sys/bus/most/drivers/most_core/links
Date: March 2017
KernelVersion: 4.15
Contact: Christian Gromm <christian.gromm@microchip.com>
Description:
This is used to retrieve a list of established links.
Users:
Documentation/ABI/testing/sysfs-class-power
+2 -1
View File
@@ -189,7 +189,8 @@ Description:
Access: Read
Valid values: "Unknown", "Good", "Overheat", "Dead",
"Over voltage", "Unspecified failure", "Cold",
"Watchdog timer expire", "Safety timer expire"
"Watchdog timer expire", "Safety timer expire",
"Over current"
What: /sys/class/power_supply/<supply_name>/precharge_current
Date: June 2017
Documentation/ABI/testing/sysfs-class-typec
+16 -7
View File
@@ -20,13 +20,13 @@ Date: April 2017
Contact: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Description:
The supported power roles. This attribute can be used to request
power role swap on the port when the port supports USB Power
Delivery. Swapping is supported as synchronous operation, so
write(2) to the attribute will not return until the operation
has finished. The attribute is notified about role changes so
that poll(2) on the attribute wakes up. Change on the role will
also generate uevent KOBJ_CHANGE. The current role is show in
brackets, for example "[source] sink" when in source mode.
power role swap on the port. Swapping is supported as
synchronous operation, so write(2) to the attribute will not
return until the operation has finished. The attribute is
notified about role changes so that poll(2) on the attribute
wakes up. Change on the role will also generate uevent
KOBJ_CHANGE. The current role is show in brackets, for example
"[source] sink" when in source mode.
Valid values: source, sink
@@ -108,6 +108,15 @@ Contact: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Description:
Revision number of the supported USB Type-C specification.
What: /sys/class/typec/<port>/orientation
Date: February 2020
Contact: Badhri Jagan Sridharan <badhri@google.com>
Description:
Indicates the active orientation of the Type-C connector.
Valid values:
- "normal": CC1 orientation
- "reverse": CC2 orientation
- "unknown": Orientation cannot be determined.
USB Type-C partner devices (eg. /sys/class/typec/port0-partner/)
Documentation/ABI/testing/sysfs-driver-jz4780-efuse
+16
View File
@@ -0,0 +1,16 @@
What: /sys/devices/*/<our-device>/nvmem
Date: December 2017
Contact: PrasannaKumar Muralidharan <prasannatsmkumar@gmail.com>
Description: read-only access to the efuse on the Ingenic JZ4780 SoC
The SoC has a one time programmable 8K efuse that is
split into segments. The driver supports read only.
The segments are
0x000 64 bit Random Number
0x008 128 bit Ingenic Chip ID
0x018 128 bit Customer ID
0x028 3520 bit Reserved
0x1E0 8 bit Protect Segment
0x1E1 2296 bit HDMI Key
0x300 2048 bit Security boot key
Users: any user space application which wants to read the Chip
and Customer ID
Documentation/ABI/testing/sysfs-driver-pciback
+13
View File
@@ -11,3 +11,16 @@ Description:
#echo 00:19.0-E0:2:FF > /sys/bus/pci/drivers/pciback/quirks
will allow the guest to read and write to the configuration
register 0x0E.
What: /sys/bus/pci/drivers/pciback/allow_interrupt_control
Date: Jan 2020
KernelVersion: 5.6
Contact: xen-devel@lists.xenproject.org
Description:
List of devices which can have interrupt control flag (INTx,
MSI, MSI-X) set by a connected guest. It is meant to be set
only when the guest is a stubdomain hosting device model (qemu)
and the actual device is assigned to a HVM. It is not safe
(similar to permissive attribute) to set for a devices assigned
to a PV guest. The device is automatically removed from this
list when the connected pcifront terminates.
Documentation/ABI/testing/sysfs-driver-uacce
+39
View File
@@ -0,0 +1,39 @@
What: /sys/class/uacce/<dev_name>/api
Date: Feb 2020
KernelVersion: 5.7
Contact: linux-accelerators@lists.ozlabs.org
Description: Api of the device
Can be any string and up to userspace to parse.
Application use the api to match the correct driver
What: /sys/class/uacce/<dev_name>/flags
Date: Feb 2020
KernelVersion: 5.7
Contact: linux-accelerators@lists.ozlabs.org
Description: Attributes of the device, see UACCE_DEV_xxx flag defined in uacce.h
What: /sys/class/uacce/<dev_name>/available_instances
Date: Feb 2020
KernelVersion: 5.7
Contact: linux-accelerators@lists.ozlabs.org
Description: Available instances left of the device
Return -ENODEV if uacce_ops get_available_instances is not provided
What: /sys/class/uacce/<dev_name>/algorithms
Date: Feb 2020
KernelVersion: 5.7
Contact: linux-accelerators@lists.ozlabs.org
Description: Algorithms supported by this accelerator, separated by new line.
Can be any string and up to userspace to parse.
What: /sys/class/uacce/<dev_name>/region_mmio_size
Date: Feb 2020
KernelVersion: 5.7
Contact: linux-accelerators@lists.ozlabs.org
Description: Size (bytes) of mmio region queue file
What: /sys/class/uacce/<dev_name>/region_dus_size
Date: Feb 2020
KernelVersion: 5.7
Contact: linux-accelerators@lists.ozlabs.org
Description: Size (bytes) of dus region queue file
Documentation/ABI/testing/sysfs-driver-xen-blkback
+10
View File
@@ -25,3 +25,13 @@ Description:
allocated without being in use. The time is in
seconds, 0 means indefinitely long.
The default is 60 seconds.
What: /sys/module/xen_blkback/parameters/buffer_squeeze_duration_ms
Date: December 2019
KernelVersion: 5.6
Contact: SeongJae Park <sjpark@amazon.de>
Description:
When memory pressure is reported to blkback this option
controls the duration in milliseconds that blkback will not
cache any page not backed by a grant mapping.
The default is 10ms.
Documentation/ABI/testing/sysfs-firmware-opal-sensor-groups
+21
View File
@@ -0,0 +1,21 @@
What: /sys/firmware/opal/sensor_groups
Date: August 2017
Contact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>
Description: Sensor groups directory for POWER9 powernv servers
Each folder in this directory contains a sensor group
which are classified based on type of the sensor
like power, temperature, frequency, current, etc. They
can also indicate the group of sensors belonging to
different owners like CSM, Profiler, Job-Scheduler
What: /sys/firmware/opal/sensor_groups/<sensor_group_name>/clear
Date: August 2017
Contact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>
Description: Sysfs file to clear the min-max of all the sensors
belonging to the group.
Writing 1 to this file will clear the minimum and
maximum values of all the sensors in the group.
In POWER9, the min-max of a sensor is the historical minimum
and maximum value of the sensor cached by OCC.
Documentation/ABI/testing/sysfs-fs-f2fs
+171 -112
View File
@@ -1,37 +1,40 @@
What: /sys/fs/f2fs/<disk>/gc_max_sleep_time
Date: July 2013
Contact: "Namjae Jeon" <namjae.jeon@samsung.com>
Description:
Controls the maximun sleep time for gc_thread. Time
is in milliseconds.
Description: Controls the maximum sleep time for gc_thread. Time
is in milliseconds.
What: /sys/fs/f2fs/<disk>/gc_min_sleep_time
Date: July 2013
Contact: "Namjae Jeon" <namjae.jeon@samsung.com>
Description:
Controls the minimum sleep time for gc_thread. Time
is in milliseconds.
Description: Controls the minimum sleep time for gc_thread. Time
is in milliseconds.
What: /sys/fs/f2fs/<disk>/gc_no_gc_sleep_time
Date: July 2013
Contact: "Namjae Jeon" <namjae.jeon@samsung.com>
Description:
Controls the default sleep time for gc_thread. Time
is in milliseconds.
Description: Controls the default sleep time for gc_thread. Time
is in milliseconds.
What: /sys/fs/f2fs/<disk>/gc_idle
Date: July 2013
Contact: "Namjae Jeon" <namjae.jeon@samsung.com>
Description:
Controls the victim selection policy for garbage collection.
Description: Controls the victim selection policy for garbage collection.
Setting gc_idle = 0(default) will disable this option. Setting
gc_idle = 1 will select the Cost Benefit approach & setting
gc_idle = 2 will select the greedy approach.
What: /sys/fs/f2fs/<disk>/reclaim_segments
Date: October 2013
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description:
Controls the issue rate of segment discard commands.
Description: This parameter controls the number of prefree segments to be
reclaimed. If the number of prefree segments is larger than
the number of segments in the proportion to the percentage
over total volume size, f2fs tries to conduct checkpoint to
reclaim the prefree segments to free segments.
By default, 5% over total # of segments.
What: /sys/fs/f2fs/<disk>/max_blkaddr
What: /sys/fs/f2fs/<disk>/main_blkaddr
Date: November 2019
Contact: "Ramon Pantin" <pantin@google.com>
Description:
@@ -40,227 +43,283 @@ Description:
What: /sys/fs/f2fs/<disk>/ipu_policy
Date: November 2013
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description:
Controls the in-place-update policy.
Description: Controls the in-place-update policy.
updates in f2fs. User can set:
0x01: F2FS_IPU_FORCE, 0x02: F2FS_IPU_SSR,
0x04: F2FS_IPU_UTIL, 0x08: F2FS_IPU_SSR_UTIL,
0x10: F2FS_IPU_FSYNC, 0x20: F2FS_IPU_ASYNC,
0x40: F2FS_IPU_NOCACHE.
Refer segment.h for details.
What: /sys/fs/f2fs/<disk>/min_ipu_util
Date: November 2013
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description:
Controls the FS utilization condition for the in-place-update
policies.
Description: Controls the FS utilization condition for the in-place-update
policies. It is used by F2FS_IPU_UTIL and F2FS_IPU_SSR_UTIL policies.
What: /sys/fs/f2fs/<disk>/min_fsync_blocks
Date: September 2014
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls the dirty page count condition for the in-place-update
policies.
Description: Controls the dirty page count condition for the in-place-update
policies.
What: /sys/fs/f2fs/<disk>/min_seq_blocks
Date: August 2018
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls the dirty page count condition for batched sequential
writes in ->writepages.
Description: Controls the dirty page count condition for batched sequential
writes in writepages.
What: /sys/fs/f2fs/<disk>/min_hot_blocks
Date: March 2017
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls the dirty page count condition for redefining hot data.
Description: Controls the dirty page count condition for redefining hot data.
What: /sys/fs/f2fs/<disk>/min_ssr_sections
Date: October 2017
Contact: "Chao Yu" <yuchao0@huawei.com>
Description:
Controls the fee section threshold to trigger SSR allocation.
Description: Controls the free section threshold to trigger SSR allocation.
If this is large, SSR mode will be enabled early.
What: /sys/fs/f2fs/<disk>/max_small_discards
Date: November 2013
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description:
Controls the issue rate of small discard commands.
Description: Controls the issue rate of discard commands that consist of small
blocks less than 2MB. The candidates to be discarded are cached until
checkpoint is triggered, and issued during the checkpoint.
By default, it is disabled with 0.
What: /sys/fs/f2fs/<disk>/discard_granularity
Date: July 2017
Contact: "Chao Yu" <yuchao0@huawei.com>
Description:
Controls discard granularity of inner discard thread, inner thread
What: /sys/fs/f2fs/<disk>/discard_granularity
Date: July 2017
Contact: "Chao Yu" <yuchao0@huawei.com>
Description: Controls discard granularity of inner discard thread. Inner thread
will not issue discards with size that is smaller than granularity.
The unit size is one block, now only support configuring in range
of [1, 512].
The unit size is one block(4KB), now only support configuring
in range of [1, 512]. Default value is 4(=16KB).
What: /sys/fs/f2fs/<disk>/umount_discard_timeout
Date: January 2019
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Set timeout to issue discard commands during umount.
Default: 5 secs
What: /sys/fs/f2fs/<disk>/umount_discard_timeout
Date: January 2019
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description: Set timeout to issue discard commands during umount.
Default: 5 secs
What: /sys/fs/f2fs/<disk>/max_victim_search
Date: January 2014
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description:
Controls the number of trials to find a victim segment.
Description: Controls the number of trials to find a victim segment
when conducting SSR and cleaning operations. The default value
is 4096 which covers 8GB block address range.
What: /sys/fs/f2fs/<disk>/migration_granularity
Date: October 2018
Contact: "Chao Yu" <yuchao0@huawei.com>
Description:
Controls migration granularity of garbage collection on large
section, it can let GC move partial segment{s} of one section
in one GC cycle, so that dispersing heavy overhead GC to
multiple lightweight one.
Description: Controls migration granularity of garbage collection on large
section, it can let GC move partial segment{s} of one section
in one GC cycle, so that dispersing heavy overhead GC to
multiple lightweight one.
What: /sys/fs/f2fs/<disk>/dir_level
Date: March 2014
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description:
Controls the directory level for large directory.
Description: Controls the directory level for large directory. If a
directory has a number of files, it can reduce the file lookup
latency by increasing this dir_level value. Otherwise, it
needs to decrease this value to reduce the space overhead.
The default value is 0.
What: /sys/fs/f2fs/<disk>/ram_thresh
Date: March 2014
Contact: "Jaegeuk Kim" <jaegeuk.kim@samsung.com>
Description:
Controls the memory footprint used by f2fs.
Description: Controls the memory footprint used by free nids and cached
nat entries. By default, 1 is set, which indicates
10 MB / 1 GB RAM.
What: /sys/fs/f2fs/<disk>/batched_trim_sections
Date: February 2015
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls the trimming rate in batch mode.
<deprecated>
Description: Controls the trimming rate in batch mode.
<deprecated>
What: /sys/fs/f2fs/<disk>/cp_interval
Date: October 2015
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls the checkpoint timing.
Description: Controls the checkpoint timing, set to 60 seconds by default.
What: /sys/fs/f2fs/<disk>/idle_interval
Date: January 2016
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls the idle timing for all paths other than
discard and gc path.
Description: Controls the idle timing of system, if there is no FS operation
during given interval.
Set to 5 seconds by default.
What: /sys/fs/f2fs/<disk>/discard_idle_interval
Date: September 2018
Contact: "Chao Yu" <yuchao0@huawei.com>
Contact: "Sahitya Tummala" <stummala@codeaurora.org>
Description:
Controls the idle timing for discard path.
Description: Controls the idle timing of discard thread given
this time interval.
Default is 5 secs.
What: /sys/fs/f2fs/<disk>/gc_idle_interval
Date: September 2018
Contact: "Chao Yu" <yuchao0@huawei.com>
Contact: "Sahitya Tummala" <stummala@codeaurora.org>
Description:
Controls the idle timing for gc path.
Description: Controls the idle timing for gc path. Set to 5 seconds by default.
What: /sys/fs/f2fs/<disk>/iostat_enable
Date: August 2017
Contact: "Chao Yu" <yuchao0@huawei.com>
Description:
Controls to enable/disable IO stat.
Description: Controls to enable/disable IO stat.
What: /sys/fs/f2fs/<disk>/ra_nid_pages
Date: October 2015
Contact: "Chao Yu" <chao2.yu@samsung.com>
Description:
Controls the count of nid pages to be readaheaded.
Description: Controls the count of nid pages to be readaheaded.
When building free nids, F2FS reads NAT blocks ahead for
speed up. Default is 0.
What: /sys/fs/f2fs/<disk>/dirty_nats_ratio
Date: January 2016
Contact: "Chao Yu" <chao2.yu@samsung.com>
Description:
Controls dirty nat entries ratio threshold, if current
ratio exceeds configured threshold, checkpoint will
be triggered for flushing dirty nat entries.
Description: Controls dirty nat entries ratio threshold, if current
ratio exceeds configured threshold, checkpoint will
be triggered for flushing dirty nat entries.
What: /sys/fs/f2fs/<disk>/lifetime_write_kbytes
Date: January 2016
Contact: "Shuoran Liu" <liushuoran@huawei.com>
Description:
Shows total written kbytes issued to disk.
Description: Shows total written kbytes issued to disk.
What: /sys/fs/f2fs/<disk>/features
Date: July 2017
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Shows all enabled features in current device.
Description: Shows all enabled features in current device.
What: /sys/fs/f2fs/<disk>/inject_rate
Date: May 2016
Contact: "Sheng Yong" <shengyong1@huawei.com>
Description:
Controls the injection rate.
Description: Controls the injection rate of arbitrary faults.
What: /sys/fs/f2fs/<disk>/inject_type
Date: May 2016
Contact: "Sheng Yong" <shengyong1@huawei.com>
Description:
Controls the injection type.
Description: Controls the injection type of arbitrary faults.
What: /sys/fs/f2fs/<disk>/dirty_segments
Date: October 2017
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description: Shows the number of dirty segments.
What: /sys/fs/f2fs/<disk>/reserved_blocks
Date: June 2017
Contact: "Chao Yu" <yuchao0@huawei.com>
Description:
Controls target reserved blocks in system, the threshold
is soft, it could exceed current available user space.
Description: Controls target reserved blocks in system, the threshold
is soft, it could exceed current available user space.
What: /sys/fs/f2fs/<disk>/current_reserved_blocks
Date: October 2017
Contact: "Yunlong Song" <yunlong.song@huawei.com>
Contact: "Chao Yu" <yuchao0@huawei.com>
Description:
Shows current reserved blocks in system, it may be temporarily
smaller than target_reserved_blocks, but will gradually
increase to target_reserved_blocks when more free blocks are
freed by user later.
Description: Shows current reserved blocks in system, it may be temporarily
smaller than target_reserved_blocks, but will gradually
increase to target_reserved_blocks when more free blocks are
freed by user later.
What: /sys/fs/f2fs/<disk>/gc_urgent
Date: August 2017
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Do background GC agressively
Description: Do background GC agressively when set. When gc_urgent = 1,
background thread starts to do GC by given gc_urgent_sleep_time
interval. It is set to 0 by default.
What: /sys/fs/f2fs/<disk>/gc_urgent_sleep_time
Date: August 2017
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description:
Controls sleep time of GC urgent mode
Description: Controls sleep time of GC urgent mode. Set to 500ms by default.
What: /sys/fs/f2fs/<disk>/readdir_ra
Date: November 2017
Contact: "Sheng Yong" <shengyong1@huawei.com>
Description:
Controls readahead inode block in readdir.
Description: Controls readahead inode block in readdir. Enabled by default.
What: /sys/fs/f2fs/<disk>/gc_pin_file_thresh
Date: January 2018
Contact: Jaegeuk Kim <jaegeuk@kernel.org>
Description: This indicates how many GC can be failed for the pinned
file. If it exceeds this, F2FS doesn't guarantee its pinning
state. 2048 trials is set by default.
What: /sys/fs/f2fs/<disk>/extension_list
Date: Feburary 2018
Contact: "Chao Yu" <yuchao0@huawei.com>
Description:
Used to control configure extension list:
- Query: cat /sys/fs/f2fs/<disk>/extension_list
- Add: echo '[h/c]extension' > /sys/fs/f2fs/<disk>/extension_list
- Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list
- [h] means add/del hot file extension
- [c] means add/del cold file extension
Description: Used to control configure extension list:
- Query: cat /sys/fs/f2fs/<disk>/extension_list
- Add: echo '[h/c]extension' > /sys/fs/f2fs/<disk>/extension_list
- Del: echo '[h/c]!extension' > /sys/fs/f2fs/<disk>/extension_list
- [h] means add/del hot file extension
- [c] means add/del cold file extension
What: /sys/fs/f2fs/<disk>/unusable
Date April 2019
Contact: "Daniel Rosenberg" <drosen@google.com>
Description:
If checkpoint=disable, it displays the number of blocks that are unusable.
If checkpoint=enable it displays the enumber of blocks that would be unusable
if checkpoint=disable were to be set.
Description: If checkpoint=disable, it displays the number of blocks that
are unusable.
If checkpoint=enable it displays the enumber of blocks that
would be unusable if checkpoint=disable were to be set.
What: /sys/fs/f2fs/<disk>/encoding
Date July 2019
Contact: "Daniel Rosenberg" <drosen@google.com>
Description:
Displays name and version of the encoding set for the filesystem.
If no encoding is set, displays (none)
Description: Displays name and version of the encoding set for the filesystem.
If no encoding is set, displays (none)
What: /sys/fs/f2fs/<disk>/free_segments
Date: September 2019
Contact: "Hridya Valsaraju" <hridya@google.com>
Description: Number of free segments in disk.
What: /sys/fs/f2fs/<disk>/cp_foreground_calls
Date: September 2019
Contact: "Hridya Valsaraju" <hridya@google.com>
Description: Number of checkpoint operations performed on demand. Available when
CONFIG_F2FS_STAT_FS=y.
What: /sys/fs/f2fs/<disk>/cp_background_calls
Date: September 2019
Contact: "Hridya Valsaraju" <hridya@google.com>
Description: Number of checkpoint operations performed in the background to
free segments. Available when CONFIG_F2FS_STAT_FS=y.
What: /sys/fs/f2fs/<disk>/gc_foreground_calls
Date: September 2019
Contact: "Hridya Valsaraju" <hridya@google.com>
Description: Number of garbage collection operations performed on demand.
Available when CONFIG_F2FS_STAT_FS=y.
What: /sys/fs/f2fs/<disk>/gc_background_calls
Date: September 2019
Contact: "Hridya Valsaraju" <hridya@google.com>
Description: Number of garbage collection operations triggered in background.
Available when CONFIG_F2FS_STAT_FS=y.
What: /sys/fs/f2fs/<disk>/moved_blocks_foreground
Date: September 2019
Contact: "Hridya Valsaraju" <hridya@google.com>
Description: Number of blocks moved by garbage collection in foreground.
Available when CONFIG_F2FS_STAT_FS=y.
What: /sys/fs/f2fs/<disk>/moved_blocks_background
Date: September 2019
Contact: "Hridya Valsaraju" <hridya@google.com>
Description: Number of blocks moved by garbage collection in background.
Available when CONFIG_F2FS_STAT_FS=y.
What: /sys/fs/f2fs/<disk>/avg_vblocks
Date: September 2019
Contact: "Hridya Valsaraju" <hridya@google.com>
Description: Average number of valid blocks.
Available when CONFIG_F2FS_STAT_FS=y.
What: /sys/fs/f2fs/<disk>/mounted_time_sec
Date: February 2020
Contact: "Jaegeuk Kim" <jaegeuk@kernel.org>
Description: Show the mounted time in secs of this partition.
Documentation/ABI/testing/sysfs-kernel-fadump
+40
View File
@@ -0,0 +1,40 @@
What: /sys/kernel/fadump/*
Date: Dec 2019
Contact: linuxppc-dev@lists.ozlabs.org
Description:
The /sys/kernel/fadump/* is a collection of FADump sysfs
file provide information about the configuration status
of Firmware Assisted Dump (FADump).
What: /sys/kernel/fadump/enabled
Date: Dec 2019
Contact: linuxppc-dev@lists.ozlabs.org
Description: read only
Primarily used to identify whether the FADump is enabled in
the kernel or not.
User: Kdump service
What: /sys/kernel/fadump/registered
Date: Dec 2019
Contact: linuxppc-dev@lists.ozlabs.org
Description: read/write
Helps to control the dump collect feature from userspace.
Setting 1 to this file enables the system to collect the
dump and 0 to disable it.
User: Kdump service
What: /sys/kernel/fadump/release_mem
Date: Dec 2019
Contact: linuxppc-dev@lists.ozlabs.org
Description: write only
This is a special sysfs file and only available when
the system is booted to capture the vmcore using FADump.
It is used to release the memory reserved by FADump to
save the crash dump.
What: /sys/kernel/fadump/mem_reserved
Date: Dec 2019
Contact: linuxppc-dev@lists.ozlabs.org
Description: read only
Provide information about the amount of memory reserved by
FADump to save the crash dump in bytes.
Documentation/ABI/testing/sysfs-platform-dell-laptop
+4 -4
View File
@@ -2,7 +2,7 @@ What: /sys/class/leds/dell::kbd_backlight/als_enabled
Date: December 2014
KernelVersion: 3.19
Contact: Gabriele Mazzotta <gabriele.mzt@gmail.com>,
Pali Rohár <pali.rohar@gmail.com>
Pali Rohár <pali@kernel.org>
Description:
This file allows to control the automatic keyboard
illumination mode on some systems that have an ambient
@@ -13,7 +13,7 @@ What: /sys/class/leds/dell::kbd_backlight/als_setting
Date: December 2014
KernelVersion: 3.19
Contact: Gabriele Mazzotta <gabriele.mzt@gmail.com>,
Pali Rohár <pali.rohar@gmail.com>
Pali Rohár <pali@kernel.org>
Description:
This file allows to specifiy the on/off threshold value,
as reported by the ambient light sensor.
@@ -22,7 +22,7 @@ What: /sys/class/leds/dell::kbd_backlight/start_triggers
Date: December 2014
KernelVersion: 3.19
Contact: Gabriele Mazzotta <gabriele.mzt@gmail.com>,
Pali Rohár <pali.rohar@gmail.com>
Pali Rohár <pali@kernel.org>
Description:
This file allows to control the input triggers that
turn on the keyboard backlight illumination that is
@@ -45,7 +45,7 @@ What: /sys/class/leds/dell::kbd_backlight/stop_timeout
Date: December 2014
KernelVersion: 3.19
Contact: Gabriele Mazzotta <gabriele.mzt@gmail.com>,
Pali Rohár <pali.rohar@gmail.com>
Pali Rohár <pali@kernel.org>
Description:
This file allows to specify the interval after which the
keyboard illumination is disabled because of inactivity.
Documentation/ABI/testing/sysfs-tty
+7
View File
@@ -154,3 +154,10 @@ Description:
device specification. For example, when user sets 7bytes on
16550A, which has 1/4/8/14 bytes trigger, the RX trigger is
automatically changed to 4 bytes.
What: /sys/class/tty/ttyS0/console
Date: February 2020
Contact: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Description:
Allows user to detach or attach back the given device as
kernel console. It shows and accepts a boolean variable.
Documentation/Makefile
+3 -2
View File
@@ -2,7 +2,8 @@
# Makefile for Sphinx documentation
#
subdir-y := devicetree/bindings/
# for cleaning
subdir- := devicetree/bindings
# Check for broken documentation file references
ifeq ($(CONFIG_WARN_MISSING_DOCUMENTS),y)
@@ -13,7 +14,7 @@ endif
SPHINXBUILD = sphinx-build
SPHINXOPTS =
SPHINXDIRS = .
_SPHINXDIRS = $(patsubst $(srctree)/Documentation/%/index.rst,%,$(wildcard $(srctree)/Documentation/*/index.rst))
_SPHINXDIRS = $(sort $(patsubst $(srctree)/Documentation/%/index.rst,%,$(wildcard $(srctree)/Documentation/*/index.rst)))
SPHINX_CONF = conf.py
PAPER =
BUILDDIR = $(obj)/output
Documentation/PCI/boot-interrupts.rst
+155
View File
@@ -0,0 +1,155 @@
.. SPDX-License-Identifier: GPL-2.0
===============
Boot Interrupts
===============
:Author: - Sean V Kelley <sean.v.kelley@linux.intel.com>
Overview
========
On PCI Express, interrupts are represented with either MSI or inbound
interrupt messages (Assert_INTx/Deassert_INTx). The integrated IO-APIC in a
given Core IO converts the legacy interrupt messages from PCI Express to
MSI interrupts. If the IO-APIC is disabled (via the mask bits in the
IO-APIC table entries), the messages are routed to the legacy PCH. This
in-band interrupt mechanism was traditionally necessary for systems that
did not support the IO-APIC and for boot. Intel in the past has used the
term "boot interrupts" to describe this mechanism. Further, the PCI Express
protocol describes this in-band legacy wire-interrupt INTx mechanism for
I/O devices to signal PCI-style level interrupts. The subsequent paragraphs
describe problems with the Core IO handling of INTx message routing to the
PCH and mitigation within BIOS and the OS.
Issue
=====
When in-band legacy INTx messages are forwarded to the PCH, they in turn
trigger a new interrupt for which the OS likely lacks a handler. When an
interrupt goes unhandled over time, they are tracked by the Linux kernel as
Spurious Interrupts. The IRQ will be disabled by the Linux kernel after it
reaches a specific count with the error "nobody cared". This disabled IRQ
now prevents valid usage by an existing interrupt which may happen to share
the IRQ line.
irq 19: nobody cared (try booting with the "irqpoll" option)
CPU: 0 PID: 2988 Comm: irq/34-nipalk Tainted: 4.14.87-rt49-02410-g4a640ec-dirty #1
Hardware name: National Instruments NI PXIe-8880/NI PXIe-8880, BIOS 2.1.5f1 01/09/2020
Call Trace:
<IRQ>
? dump_stack+0x46/0x5e
? __report_bad_irq+0x2e/0xb0
? note_interrupt+0x242/0x290
? nNIKAL100_memoryRead16+0x8/0x10 [nikal]
? handle_irq_event_percpu+0x55/0x70
? handle_irq_event+0x4f/0x80
? handle_fasteoi_irq+0x81/0x180
? handle_irq+0x1c/0x30
? do_IRQ+0x41/0xd0
? common_interrupt+0x84/0x84
</IRQ>
handlers:
irq_default_primary_handler threaded usb_hcd_irq
Disabling IRQ #19
Conditions
==========
The use of threaded interrupts is the most likely condition to trigger
this problem today. Threaded interrupts may not be reenabled after the IRQ
handler wakes. These "one shot" conditions mean that the threaded interrupt
needs to keep the interrupt line masked until the threaded handler has run.
Especially when dealing with high data rate interrupts, the thread needs to
run to completion; otherwise some handlers will end up in stack overflows
since the interrupt of the issuing device is still active.
Affected Chipsets
=================
The legacy interrupt forwarding mechanism exists today in a number of
devices including but not limited to chipsets from AMD/ATI, Broadcom, and
Intel. Changes made through the mitigations below have been applied to
drivers/pci/quirks.c
Starting with ICX there are no longer any IO-APICs in the Core IO's
devices. IO-APIC is only in the PCH. Devices connected to the Core IO's
PCIe Root Ports will use native MSI/MSI-X mechanisms.
Mitigations
===========
The mitigations take the form of PCI quirks. The preference has been to
first identify and make use of a means to disable the routing to the PCH.
In such a case a quirk to disable boot interrupt generation can be
added.[1]
Intel® 6300ESB I/O Controller Hub
Alternate Base Address Register:
BIE: Boot Interrupt Enable
0 = Boot interrupt is enabled.
1 = Boot interrupt is disabled.
Intel® Sandy Bridge through Sky Lake based Xeon servers:
Coherent Interface Protocol Interrupt Control
dis_intx_route2pch/dis_intx_route2ich/dis_intx_route2dmi2:
When this bit is set. Local INTx messages received from the
Intel® Quick Data DMA/PCI Express ports are not routed to legacy
PCH - they are either converted into MSI via the integrated IO-APIC
(if the IO-APIC mask bit is clear in the appropriate entries)
or cause no further action (when mask bit is set)
In the absence of a way to directly disable the routing, another approach
has been to make use of PCI Interrupt pin to INTx routing tables for
purposes of redirecting the interrupt handler to the rerouted interrupt
line by default. Therefore, on chipsets where this INTx routing cannot be
disabled, the Linux kernel will reroute the valid interrupt to its legacy
interrupt. This redirection of the handler will prevent the occurrence of
the spurious interrupt detection which would ordinarily disable the IRQ
line due to excessive unhandled counts.[2]
The config option X86_REROUTE_FOR_BROKEN_BOOT_IRQS exists to enable (or
disable) the redirection of the interrupt handler to the PCH interrupt
line. The option can be overridden by either pci=ioapicreroute or
pci=noioapicreroute.[3]
More Documentation
==================
There is an overview of the legacy interrupt handling in several datasheets
(6300ESB and 6700PXH below). While largely the same, it provides insight
into the evolution of its handling with chipsets.
Example of disabling of the boot interrupt
------------------------------------------
Intel® 6300ESB I/O Controller Hub (Document # 300641-004US)
5.7.3 Boot Interrupt
https://www.intel.com/content/dam/doc/datasheet/6300esb-io-controller-hub-datasheet.pdf
Intel® Xeon® Processor E5-1600/2400/2600/4600 v3 Product Families
Datasheet - Volume 2: Registers (Document # 330784-003)
6.6.41 cipintrc Coherent Interface Protocol Interrupt Control
https://www.intel.com/content/dam/www/public/us/en/documents/datasheets/xeon-e5-v3-datasheet-vol-2.pdf
Example of handler rerouting
----------------------------
Intel® 6700PXH 64-bit PCI Hub (Document # 302628)
2.15.2 PCI Express Legacy INTx Support and Boot Interrupt
https://www.intel.com/content/dam/doc/datasheet/6700pxh-64-bit-pci-hub-datasheet.pdf
If you have any legacy PCI interrupt questions that aren't answered, email me.
Cheers,
Sean V Kelley
sean.v.kelley@linux.intel.com
[1] https://lore.kernel.org/r/12131949181903-git-send-email-sassmann@suse.de/
[2] https://lore.kernel.org/r/12131949182094-git-send-email-sassmann@suse.de/
[3] https://lore.kernel.org/r/487C8EA7.6020205@suse.de/
Documentation/PCI/index.rst
+1
View File
@@ -16,3 +16,4 @@ Linux PCI Bus Subsystem
pci-error-recovery
pcieaer-howto
endpoint/index
boot-interrupts
Documentation/PCI/msi-howto.rst
+1 -1
View File
@@ -283,5 +283,5 @@ or disabled (0). If 0 is found in any of the msi_bus files belonging
to bridges between the PCI root and the device, MSIs are disabled.
It is also worth checking the device driver to see whether it supports MSIs.
For example, it may contain calls to pci_irq_alloc_vectors() with the
For example, it may contain calls to pci_alloc_irq_vectors() with the
PCI_IRQ_MSI or PCI_IRQ_MSIX flags.
Documentation/PCI/pci.rst
+1 -1
View File
@@ -239,7 +239,7 @@ from the PCI device config space. Use the values in the pci_dev structure
as the PCI "bus address" might have been remapped to a "host physical"
address by the arch/chip-set specific kernel support.
See Documentation/io-mapping.txt for how to access device registers
See Documentation/driver-api/io-mapping.rst for how to access device registers
or device memory.
The device driver needs to call pci_request_region() to verify
Documentation/PCI/pcieaer-howto.rst
+6 -17
View File
@@ -156,12 +156,6 @@ default reset_link function, but different upstream ports might
have different specifications to reset pci express link, so all
upstream ports should provide their own reset_link functions.
In struct pcie_port_service_driver, a new pointer, reset_link, is
added.
::
pci_ers_result_t (*reset_link) (struct pci_dev *dev);
Section 3.2.2.2 provides more detailed info on when to call
reset_link.
@@ -212,15 +206,10 @@ error_detected(dev, pci_channel_io_frozen) to all drivers within
a hierarchy in question. Then, performing link reset at upstream is
necessary. As different kinds of devices might use different approaches
to reset link, AER port service driver is required to provide the
function to reset link. Firstly, kernel looks for if the upstream
component has an aer driver. If it has, kernel uses the reset_link
callback of the aer driver. If the upstream component has no aer driver
and the port is downstream port, we will perform a hot reset as the
default by setting the Secondary Bus Reset bit of the Bridge Control
register associated with the downstream port. As for upstream ports,
they should provide their own aer service drivers with reset_link
function. If error_detected returns PCI_ERS_RESULT_CAN_RECOVER and
reset_link returns PCI_ERS_RESULT_RECOVERED, the error handling goes
function to reset link via callback parameter of pcie_do_recovery()
function. If reset_link is not NULL, recovery function will use it
to reset the link. If error_detected returns PCI_ERS_RESULT_CAN_RECOVER
and reset_link returns PCI_ERS_RESULT_RECOVERED, the error handling goes
to mmio_enabled.
helper functions
@@ -243,9 +232,9 @@ messages to root port when an error is detected.
::
int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev);`
int pci_aer_clear_nonfatal_status(struct pci_dev *dev);`
pci_cleanup_aer_uncorrect_error_status cleanups the uncorrectable
pci_aer_clear_nonfatal_status clears non-fatal errors in the uncorrectable
error status register.
Frequent Asked Questions
Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst
+4 -4
View File
@@ -4,7 +4,7 @@ A Tour Through TREE_RCU's Grace-Period Memory Ordering
August 8, 2017
This article was contributed by Paul E.&nbsp;McKenney
This article was contributed by Paul E. McKenney
Introduction
============
@@ -48,7 +48,7 @@ Tree RCU Grace Period Memory Ordering Building Blocks
The workhorse for RCU's grace-period memory ordering is the
critical section for the ``rcu_node`` structure's
``-&gt;lock``. These critical sections use helper functions for lock
``->lock``. These critical sections use helper functions for lock
acquisition, including ``raw_spin_lock_rcu_node()``,
``raw_spin_lock_irq_rcu_node()``, and ``raw_spin_lock_irqsave_rcu_node()``.
Their lock-release counterparts are ``raw_spin_unlock_rcu_node()``,
@@ -102,9 +102,9 @@ lock-acquisition and lock-release functions::
23 r3 = READ_ONCE(x);
24 }
25
26 WARN_ON(r1 == 0 &amp;&amp; r2 == 0 &amp;&amp; r3 == 0);
26 WARN_ON(r1 == 0 && r2 == 0 && r3 == 0);
The ``WARN_ON()`` is evaluated at &ldquo;the end of time&rdquo;,
The ``WARN_ON()`` is evaluated at "the end of time",
after all changes have propagated throughout the system.
Without the ``smp_mb__after_unlock_lock()`` provided by the
acquisition functions, this ``WARN_ON()`` could trigger, for example
Documentation/RCU/listRCU.rst
+214 -67
View File
@@ -4,12 +4,61 @@ Using RCU to Protect Read-Mostly Linked Lists
=============================================
One of the best applications of RCU is to protect read-mostly linked lists
("struct list_head" in list.h). One big advantage of this approach
(``struct list_head`` in list.h). One big advantage of this approach
is that all of the required memory barriers are included for you in
the list macros. This document describes several applications of RCU,
with the best fits first.
Example 1: Read-Side Action Taken Outside of Lock, No In-Place Updates
Example 1: Read-mostly list: Deferred Destruction
-------------------------------------------------
A widely used usecase for RCU lists in the kernel is lockless iteration over
all processes in the system. ``task_struct::tasks`` represents the list node that
links all the processes. The list can be traversed in parallel to any list
additions or removals.
The traversal of the list is done using ``for_each_process()`` which is defined
by the 2 macros::
#define next_task(p) \
list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
#define for_each_process(p) \
for (p = &init_task ; (p = next_task(p)) != &init_task ; )
The code traversing the list of all processes typically looks like::
rcu_read_lock();
for_each_process(p) {
/* Do something with p */
}
rcu_read_unlock();
The simplified code for removing a process from a task list is::
void release_task(struct task_struct *p)
{
write_lock(&tasklist_lock);
list_del_rcu(&p->tasks);
write_unlock(&tasklist_lock);
call_rcu(&p->rcu, delayed_put_task_struct);
}
When a process exits, ``release_task()`` calls ``list_del_rcu(&p->tasks)`` under
``tasklist_lock`` writer lock protection, to remove the task from the list of
all tasks. The ``tasklist_lock`` prevents concurrent list additions/removals
from corrupting the list. Readers using ``for_each_process()`` are not protected
with the ``tasklist_lock``. To prevent readers from noticing changes in the list
pointers, the ``task_struct`` object is freed only after one or more grace
periods elapse (with the help of call_rcu()). This deferring of destruction
ensures that any readers traversing the list will see valid ``p->tasks.next``
pointers and deletion/freeing can happen in parallel with traversal of the list.
This pattern is also called an **existence lock**, since RCU pins the object in
memory until all existing readers finish.
Example 2: Read-Side Action Taken Outside of Lock: No In-Place Updates
----------------------------------------------------------------------
The best applications are cases where, if reader-writer locking were
@@ -26,7 +75,7 @@ added or deleted, rather than being modified in place.
A straightforward example of this use of RCU may be found in the
system-call auditing support. For example, a reader-writer locked
implementation of audit_filter_task() might be as follows::
implementation of ``audit_filter_task()`` might be as follows::
static enum audit_state audit_filter_task(struct task_struct *tsk)
{
@@ -34,7 +83,7 @@ implementation of audit_filter_task() might be as follows::
enum audit_state state;
read_lock(&auditsc_lock);
/* Note: audit_netlink_sem held by caller. */
/* Note: audit_filter_mutex held by caller. */
list_for_each_entry(e, &audit_tsklist, list) {
if (audit_filter_rules(tsk, &e->rule, NULL, &state)) {
read_unlock(&auditsc_lock);
@@ -58,7 +107,7 @@ This means that RCU can be easily applied to the read side, as follows::
enum audit_state state;
rcu_read_lock();
/* Note: audit_netlink_sem held by caller. */
/* Note: audit_filter_mutex held by caller. */
list_for_each_entry_rcu(e, &audit_tsklist, list) {
if (audit_filter_rules(tsk, &e->rule, NULL, &state)) {
rcu_read_unlock();
@@ -69,18 +118,18 @@ This means that RCU can be easily applied to the read side, as follows::
return AUDIT_BUILD_CONTEXT;
}
The read_lock() and read_unlock() calls have become rcu_read_lock()
The ``read_lock()`` and ``read_unlock()`` calls have become rcu_read_lock()
and rcu_read_unlock(), respectively, and the list_for_each_entry() has
become list_for_each_entry_rcu(). The _rcu() list-traversal primitives
become list_for_each_entry_rcu(). The **_rcu()** list-traversal primitives
insert the read-side memory barriers that are required on DEC Alpha CPUs.
The changes to the update side are also straightforward. A reader-writer
lock might be used as follows for deletion and insertion::
The changes to the update side are also straightforward. A reader-writer lock
might be used as follows for deletion and insertion::
static inline int audit_del_rule(struct audit_rule *rule,
struct list_head *list)
{
struct audit_entry *e;
struct audit_entry *e;
write_lock(&auditsc_lock);
list_for_each_entry(e, list, list) {
@@ -113,9 +162,9 @@ Following are the RCU equivalents for these two functions::
static inline int audit_del_rule(struct audit_rule *rule,
struct list_head *list)
{
struct audit_entry *e;
struct audit_entry *e;
/* Do not use the _rcu iterator here, since this is the only
/* No need to use the _rcu iterator here, since this is the only
* deletion routine. */
list_for_each_entry(e, list, list) {
if (!audit_compare_rule(rule, &e->rule)) {
@@ -139,45 +188,45 @@ Following are the RCU equivalents for these two functions::
return 0;
}
Normally, the write_lock() and write_unlock() would be replaced by
a spin_lock() and a spin_unlock(), but in this case, all callers hold
audit_netlink_sem, so no additional locking is required. The auditsc_lock
can therefore be eliminated, since use of RCU eliminates the need for
writers to exclude readers. Normally, the write_lock() calls would
be converted into spin_lock() calls.
Normally, the ``write_lock()`` and ``write_unlock()`` would be replaced by a
spin_lock() and a spin_unlock(). But in this case, all callers hold
``audit_filter_mutex``, so no additional locking is required. The
``auditsc_lock`` can therefore be eliminated, since use of RCU eliminates the
need for writers to exclude readers.
The list_del(), list_add(), and list_add_tail() primitives have been
replaced by list_del_rcu(), list_add_rcu(), and list_add_tail_rcu().
The _rcu() list-manipulation primitives add memory barriers that are
needed on weakly ordered CPUs (most of them!). The list_del_rcu()
primitive omits the pointer poisoning debug-assist code that would
otherwise cause concurrent readers to fail spectacularly.
The **_rcu()** list-manipulation primitives add memory barriers that are needed on
weakly ordered CPUs (most of them!). The list_del_rcu() primitive omits the
pointer poisoning debug-assist code that would otherwise cause concurrent
readers to fail spectacularly.
So, when readers can tolerate stale data and when entries are either added
or deleted, without in-place modification, it is very easy to use RCU!
So, when readers can tolerate stale data and when entries are either added or
deleted, without in-place modification, it is very easy to use RCU!
Example 2: Handling In-Place Updates
Example 3: Handling In-Place Updates
------------------------------------
The system-call auditing code does not update auditing rules in place.
However, if it did, reader-writer-locked code to do so might look as
follows (presumably, the field_count is only permitted to decrease,
otherwise, the added fields would need to be filled in)::
The system-call auditing code does not update auditing rules in place. However,
if it did, the reader-writer-locked code to do so might look as follows
(assuming only ``field_count`` is updated, otherwise, the added fields would
need to be filled in)::
static inline int audit_upd_rule(struct audit_rule *rule,
struct list_head *list,
__u32 newaction,
__u32 newfield_count)
{
struct audit_entry *e;
struct audit_newentry *ne;
struct audit_entry *e;
struct audit_entry *ne;
write_lock(&auditsc_lock);
/* Note: audit_netlink_sem held by caller. */
/* Note: audit_filter_mutex held by caller. */
list_for_each_entry(e, list, list) {
if (!audit_compare_rule(rule, &e->rule)) {
e->rule.action = newaction;
e->rule.file_count = newfield_count;
e->rule.field_count = newfield_count;
write_unlock(&auditsc_lock);
return 0;
}
@@ -188,16 +237,16 @@ otherwise, the added fields would need to be filled in)::
The RCU version creates a copy, updates the copy, then replaces the old
entry with the newly updated entry. This sequence of actions, allowing
concurrent reads while doing a copy to perform an update, is what gives
RCU ("read-copy update") its name. The RCU code is as follows::
concurrent reads while making a copy to perform an update, is what gives
RCU (*read-copy update*) its name. The RCU code is as follows::
static inline int audit_upd_rule(struct audit_rule *rule,
struct list_head *list,
__u32 newaction,
__u32 newfield_count)
{
struct audit_entry *e;
struct audit_newentry *ne;
struct audit_entry *e;
struct audit_entry *ne;
list_for_each_entry(e, list, list) {
if (!audit_compare_rule(rule, &e->rule)) {
@@ -206,7 +255,7 @@ RCU ("read-copy update") its name. The RCU code is as follows::
return -ENOMEM;
audit_copy_rule(&ne->rule, &e->rule);
ne->rule.action = newaction;
ne->rule.file_count = newfield_count;
ne->rule.field_count = newfield_count;
list_replace_rcu(&e->list, &ne->list);
call_rcu(&e->rcu, audit_free_rule);
return 0;
@@ -215,34 +264,45 @@ RCU ("read-copy update") its name. The RCU code is as follows::
return -EFAULT; /* No matching rule */
}
Again, this assumes that the caller holds audit_netlink_sem. Normally,
the reader-writer lock would become a spinlock in this sort of code.
Again, this assumes that the caller holds ``audit_filter_mutex``. Normally, the
writer lock would become a spinlock in this sort of code.
Example 3: Eliminating Stale Data
Another use of this pattern can be found in the openswitch driver's *connection
tracking table* code in ``ct_limit_set()``. The table holds connection tracking
entries and has a limit on the maximum entries. There is one such table
per-zone and hence one *limit* per zone. The zones are mapped to their limits
through a hashtable using an RCU-managed hlist for the hash chains. When a new
limit is set, a new limit object is allocated and ``ct_limit_set()`` is called
to replace the old limit object with the new one using list_replace_rcu().
The old limit object is then freed after a grace period using kfree_rcu().
Example 4: Eliminating Stale Data
---------------------------------
The auditing examples above tolerate stale data, as do most algorithms
The auditing example above tolerates stale data, as do most algorithms
that are tracking external state. Because there is a delay from the
time the external state changes before Linux becomes aware of the change,
additional RCU-induced staleness is normally not a problem.
additional RCU-induced staleness is generally not a problem.
However, there are many examples where stale data cannot be tolerated.
One example in the Linux kernel is the System V IPC (see the ipc_lock()
function in ipc/util.c). This code checks a "deleted" flag under a
per-entry spinlock, and, if the "deleted" flag is set, pretends that the
One example in the Linux kernel is the System V IPC (see the shm_lock()
function in ipc/shm.c). This code checks a *deleted* flag under a
per-entry spinlock, and, if the *deleted* flag is set, pretends that the
entry does not exist. For this to be helpful, the search function must
return holding the per-entry spinlock, as ipc_lock() does in fact do.
return holding the per-entry spinlock, as shm_lock() does in fact do.
.. _quick_quiz:
Quick Quiz:
Why does the search function need to return holding the per-entry lock for
this deleted-flag technique to be helpful?
For the deleted-flag technique to be helpful, why is it necessary
to hold the per-entry lock while returning from the search function?
:ref:`Answer to Quick Quiz <answer_quick_quiz_list>`
:ref:`Answer to Quick Quiz <quick_quiz_answer>`
If the system-call audit module were to ever need to reject stale data,
one way to accomplish this would be to add a "deleted" flag and a "lock"
spinlock to the audit_entry structure, and modify audit_filter_task()
as follows::
If the system-call audit module were to ever need to reject stale data, one way
to accomplish this would be to add a ``deleted`` flag and a ``lock`` spinlock to the
audit_entry structure, and modify ``audit_filter_task()`` as follows::
static enum audit_state audit_filter_task(struct task_struct *tsk)
{
@@ -267,20 +327,20 @@ as follows::
}
Note that this example assumes that entries are only added and deleted.
Additional mechanism is required to deal correctly with the
update-in-place performed by audit_upd_rule(). For one thing,
audit_upd_rule() would need additional memory barriers to ensure
that the list_add_rcu() was really executed before the list_del_rcu().
Additional mechanism is required to deal correctly with the update-in-place
performed by ``audit_upd_rule()``. For one thing, ``audit_upd_rule()`` would
need additional memory barriers to ensure that the list_add_rcu() was really
executed before the list_del_rcu().
The audit_del_rule() function would need to set the "deleted"
flag under the spinlock as follows::
The ``audit_del_rule()`` function would need to set the ``deleted`` flag under the
spinlock as follows::
static inline int audit_del_rule(struct audit_rule *rule,
struct list_head *list)
{
struct audit_entry *e;
struct audit_entry *e;
/* Do not need to use the _rcu iterator here, since this
/* No need to use the _rcu iterator here, since this
* is the only deletion routine. */
list_for_each_entry(e, list, list) {
if (!audit_compare_rule(rule, &e->rule)) {
@@ -295,6 +355,91 @@ flag under the spinlock as follows::
return -EFAULT; /* No matching rule */
}
This too assumes that the caller holds ``audit_filter_mutex``.
Example 5: Skipping Stale Objects
---------------------------------
For some usecases, reader performance can be improved by skipping stale objects
during read-side list traversal if the object in concern is pending destruction
after one or more grace periods. One such example can be found in the timerfd
subsystem. When a ``CLOCK_REALTIME`` clock is reprogrammed - for example due to
setting of the system time, then all programmed timerfds that depend on this
clock get triggered and processes waiting on them to expire are woken up in
advance of their scheduled expiry. To facilitate this, all such timers are added
to an RCU-managed ``cancel_list`` when they are setup in
``timerfd_setup_cancel()``::
static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
{
spin_lock(&ctx->cancel_lock);
if ((ctx->clockid == CLOCK_REALTIME &&
(flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) {
if (!ctx->might_cancel) {
ctx->might_cancel = true;
spin_lock(&cancel_lock);
list_add_rcu(&ctx->clist, &cancel_list);
spin_unlock(&cancel_lock);
}
}
spin_unlock(&ctx->cancel_lock);
}
When a timerfd is freed (fd is closed), then the ``might_cancel`` flag of the
timerfd object is cleared, the object removed from the ``cancel_list`` and
destroyed::
int timerfd_release(struct inode *inode, struct file *file)
{
struct timerfd_ctx *ctx = file->private_data;
spin_lock(&ctx->cancel_lock);
if (ctx->might_cancel) {
ctx->might_cancel = false;
spin_lock(&cancel_lock);
list_del_rcu(&ctx->clist);
spin_unlock(&cancel_lock);
}
spin_unlock(&ctx->cancel_lock);
hrtimer_cancel(&ctx->t.tmr);
kfree_rcu(ctx, rcu);
return 0;
}
If the ``CLOCK_REALTIME`` clock is set, for example by a time server, the
hrtimer framework calls ``timerfd_clock_was_set()`` which walks the
``cancel_list`` and wakes up processes waiting on the timerfd. While iterating
the ``cancel_list``, the ``might_cancel`` flag is consulted to skip stale
objects::
void timerfd_clock_was_set(void)
{
struct timerfd_ctx *ctx;
unsigned long flags;
rcu_read_lock();
list_for_each_entry_rcu(ctx, &cancel_list, clist) {
if (!ctx->might_cancel)
continue;
spin_lock_irqsave(&ctx->wqh.lock, flags);
if (ctx->moffs != ktime_mono_to_real(0)) {
ctx->moffs = KTIME_MAX;
ctx->ticks++;
wake_up_locked_poll(&ctx->wqh, EPOLLIN);
}
spin_unlock_irqrestore(&ctx->wqh.lock, flags);
}
rcu_read_unlock();
}
The key point here is, because RCU-traversal of the ``cancel_list`` happens
while objects are being added and removed to the list, sometimes the traversal
can step on an object that has been removed from the list. In this example, it
is seen that it is better to skip such objects using a flag.
Summary
-------
@@ -303,19 +448,21 @@ the most amenable to use of RCU. The simplest case is where entries are
either added or deleted from the data structure (or atomically modified
in place), but non-atomic in-place modifications can be handled by making
a copy, updating the copy, then replacing the original with the copy.
If stale data cannot be tolerated, then a "deleted" flag may be used
If stale data cannot be tolerated, then a *deleted* flag may be used
in conjunction with a per-entry spinlock in order to allow the search
function to reject newly deleted data.
.. _answer_quick_quiz_list:
.. _quick_quiz_answer:
Answer to Quick Quiz:
Why does the search function need to return holding the per-entry
lock for this deleted-flag technique to be helpful?
For the deleted-flag technique to be helpful, why is it necessary
to hold the per-entry lock while returning from the search function?
If the search function drops the per-entry lock before returning,
then the caller will be processing stale data in any case. If it
is really OK to be processing stale data, then you don't need a
"deleted" flag. If processing stale data really is a problem,
*deleted* flag. If processing stale data really is a problem,
then you need to hold the per-entry lock across all of the code
that uses the value that was returned.
:ref:`Back to Quick Quiz <quick_quiz>`
Documentation/RCU/rcu.rst
+9 -9
View File
@@ -11,8 +11,8 @@ must be long enough that any readers accessing the item being deleted have
since dropped their references. For example, an RCU-protected deletion
from a linked list would first remove the item from the list, wait for
a grace period to elapse, then free the element. See the
Documentation/RCU/listRCU.rst file for more information on using RCU with
linked lists.
:ref:`Documentation/RCU/listRCU.rst <list_rcu_doc>` for more information on
using RCU with linked lists.
Frequently Asked Questions
--------------------------
@@ -50,7 +50,7 @@ Frequently Asked Questions
- If I am running on a uniprocessor kernel, which can only do one
thing at a time, why should I wait for a grace period?
See the Documentation/RCU/UP.rst file for more information.
See :ref:`Documentation/RCU/UP.rst <up_doc>` for more information.
- How can I see where RCU is currently used in the Linux kernel?
@@ -68,18 +68,18 @@ Frequently Asked Questions
- Why the name "RCU"?
"RCU" stands for "read-copy update". The file Documentation/RCU/listRCU.rst
has more information on where this name came from, search for
"read-copy update" to find it.
"RCU" stands for "read-copy update".
:ref:`Documentation/RCU/listRCU.rst <list_rcu_doc>` has more information on where
this name came from, search for "read-copy update" to find it.
- I hear that RCU is patented? What is with that?
Yes, it is. There are several known patents related to RCU,
search for the string "Patent" in RTFP.txt to find them.
search for the string "Patent" in Documentation/RCU/RTFP.txt to find them.
Of these, one was allowed to lapse by the assignee, and the
others have been contributed to the Linux kernel under GPL.
There are now also LGPL implementations of user-level RCU
available (http://liburcu.org/).
available (https://liburcu.org/).
- I hear that RCU needs work in order to support realtime kernels?
@@ -88,5 +88,5 @@ Frequently Asked Questions
- Where can I find more information on RCU?
See the RTFP.txt file in this directory.
See the Documentation/RCU/RTFP.txt file.
Or point your browser at (http://www.rdrop.com/users/paulmck/RCU/).
Documentation/RCU/torture.txt
+140 -7
View File
@@ -124,9 +124,14 @@ using a dynamically allocated srcu_struct (hence "srcud-" rather than
debugging. The final "T" entry contains the totals of the counters.
USAGE
USAGE ON SPECIFIC KERNEL BUILDS
The following script may be used to torture RCU:
It is sometimes desirable to torture RCU on a specific kernel build,
for example, when preparing to put that kernel build into production.
In that case, the kernel should be built with CONFIG_RCU_TORTURE_TEST=m
so that the test can be started using modprobe and terminated using rmmod.
For example, the following script may be used to torture RCU:
#!/bin/sh
@@ -142,8 +147,136 @@ checked for such errors. The "rmmod" command forces a "SUCCESS",
two are self-explanatory, while the last indicates that while there
were no RCU failures, CPU-hotplug problems were detected.
However, the tools/testing/selftests/rcutorture/bin/kvm.sh script
provides better automation, including automatic failure analysis.
It assumes a qemu/kvm-enabled platform, and runs guest OSes out of initrd.
See tools/testing/selftests/rcutorture/doc/initrd.txt for instructions
on setting up such an initrd.
USAGE ON MAINLINE KERNELS
When using rcutorture to test changes to RCU itself, it is often
necessary to build a number of kernels in order to test that change
across a broad range of combinations of the relevant Kconfig options
and of the relevant kernel boot parameters. In this situation, use
of modprobe and rmmod can be quite time-consuming and error-prone.
Therefore, the tools/testing/selftests/rcutorture/bin/kvm.sh
script is available for mainline testing for x86, arm64, and
powerpc. By default, it will run the series of tests specified by
tools/testing/selftests/rcutorture/configs/rcu/CFLIST, with each test
running for 30 minutes within a guest OS using a minimal userspace
supplied by an automatically generated initrd. After the tests are
complete, the resulting build products and console output are analyzed
for errors and the results of the runs are summarized.
On larger systems, rcutorture testing can be accelerated by passing the
--cpus argument to kvm.sh. For example, on a 64-CPU system, "--cpus 43"
would use up to 43 CPUs to run tests concurrently, which as of v5.4 would
complete all the scenarios in two batches, reducing the time to complete
from about eight hours to about one hour (not counting the time to build
the sixteen kernels). The "--dryrun sched" argument will not run tests,
but rather tell you how the tests would be scheduled into batches. This
can be useful when working out how many CPUs to specify in the --cpus
argument.
Not all changes require that all scenarios be run. For example, a change
to Tree SRCU might run only the SRCU-N and SRCU-P scenarios using the
--configs argument to kvm.sh as follows: "--configs 'SRCU-N SRCU-P'".
Large systems can run multiple copies of of the full set of scenarios,
for example, a system with 448 hardware threads can run five instances
of the full set concurrently. To make this happen:
kvm.sh --cpus 448 --configs '5*CFLIST'
Alternatively, such a system can run 56 concurrent instances of a single
eight-CPU scenario:
kvm.sh --cpus 448 --configs '56*TREE04'
Or 28 concurrent instances of each of two eight-CPU scenarios:
kvm.sh --cpus 448 --configs '28*TREE03 28*TREE04'
Of course, each concurrent instance will use memory, which can be
limited using the --memory argument, which defaults to 512M. Small
values for memory may require disabling the callback-flooding tests
using the --bootargs parameter discussed below.
Sometimes additional debugging is useful, and in such cases the --kconfig
parameter to kvm.sh may be used, for example, "--kconfig 'CONFIG_KASAN=y'".
Kernel boot arguments can also be supplied, for example, to control
rcutorture's module parameters. For example, to test a change to RCU's
CPU stall-warning code, use "--bootargs 'rcutorture.stall_cpu=30'".
This will of course result in the scripting reporting a failure, namely
the resuling RCU CPU stall warning. As noted above, reducing memory may
require disabling rcutorture's callback-flooding tests:
kvm.sh --cpus 448 --configs '56*TREE04' --memory 128M \
--bootargs 'rcutorture.fwd_progress=0'
Sometimes all that is needed is a full set of kernel builds. This is
what the --buildonly argument does.
Finally, the --trust-make argument allows each kernel build to reuse what
it can from the previous kernel build.
There are additional more arcane arguments that are documented in the
source code of the kvm.sh script.
If a run contains failures, the number of buildtime and runtime failures
is listed at the end of the kvm.sh output, which you really should redirect
to a file. The build products and console output of each run is kept in
tools/testing/selftests/rcutorture/res in timestamped directories. A
given directory can be supplied to kvm-find-errors.sh in order to have
it cycle you through summaries of errors and full error logs. For example:
tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh \
tools/testing/selftests/rcutorture/res/2020.01.20-15.54.23
However, it is often more convenient to access the files directly.
Files pertaining to all scenarios in a run reside in the top-level
directory (2020.01.20-15.54.23 in the example above), while per-scenario
files reside in a subdirectory named after the scenario (for example,
"TREE04"). If a given scenario ran more than once (as in "--configs
'56*TREE04'" above), the directories corresponding to the second and
subsequent runs of that scenario include a sequence number, for example,
"TREE04.2", "TREE04.3", and so on.
The most frequently used file in the top-level directory is testid.txt.
If the test ran in a git repository, then this file contains the commit
that was tested and any uncommitted changes in diff format.
The most frequently used files in each per-scenario-run directory are:
.config: This file contains the Kconfig options.
Make.out: This contains build output for a specific scenario.
console.log: This contains the console output for a specific scenario.
This file may be examined once the kernel has booted, but
it might not exist if the build failed.
vmlinux: This contains the kernel, which can be useful with tools like
objdump and gdb.
A number of additional files are available, but are less frequently used.
Many are intended for debugging of rcutorture itself or of its scripting.
As of v5.4, a successful run with the default set of scenarios produces
the following summary at the end of the run on a 12-CPU system:
SRCU-N ------- 804233 GPs (148.932/s) [srcu: g10008272 f0x0 ]
SRCU-P ------- 202320 GPs (37.4667/s) [srcud: g1809476 f0x0 ]
SRCU-t ------- 1122086 GPs (207.794/s) [srcu: g0 f0x0 ]
SRCU-u ------- 1111285 GPs (205.794/s) [srcud: g1 f0x0 ]
TASKS01 ------- 19666 GPs (3.64185/s) [tasks: g0 f0x0 ]
TASKS02 ------- 20541 GPs (3.80389/s) [tasks: g0 f0x0 ]
TASKS03 ------- 19416 GPs (3.59556/s) [tasks: g0 f0x0 ]
TINY01 ------- 836134 GPs (154.84/s) [rcu: g0 f0x0 ] n_max_cbs: 34198
TINY02 ------- 850371 GPs (157.476/s) [rcu: g0 f0x0 ] n_max_cbs: 2631
TREE01 ------- 162625 GPs (30.1157/s) [rcu: g1124169 f0x0 ]
TREE02 ------- 333003 GPs (61.6672/s) [rcu: g2647753 f0x0 ] n_max_cbs: 35844
TREE03 ------- 306623 GPs (56.782/s) [rcu: g2975325 f0x0 ] n_max_cbs: 1496497
CPU count limited from 16 to 12
TREE04 ------- 246149 GPs (45.5831/s) [rcu: g1695737 f0x0 ] n_max_cbs: 434961
TREE05 ------- 314603 GPs (58.2598/s) [rcu: g2257741 f0x2 ] n_max_cbs: 193997
TREE07 ------- 167347 GPs (30.9902/s) [rcu: g1079021 f0x0 ] n_max_cbs: 478732
CPU count limited from 16 to 12
TREE09 ------- 752238 GPs (139.303/s) [rcu: g13075057 f0x0 ] n_max_cbs: 99011
Documentation/accounting/psi.rst
+2
View File
@@ -1,3 +1,5 @@
.. _psi:
================================
PSI - Pressure Stall Information
================================
Documentation/admin-guide/acpi/fan_performance_states.rst
+2 -2
View File
@@ -18,7 +18,7 @@ may look as follows::
$ ls -l /sys/bus/acpi/devices/INT3404:00/
total 0
...
...
-r--r--r-- 1 root root 4096 Dec 13 20:38 state0
-r--r--r-- 1 root root 4096 Dec 13 20:38 state1
-r--r--r-- 1 root root 4096 Dec 13 20:38 state10
@@ -38,7 +38,7 @@ where each of the "state*" files represents one performance state of the fan
and contains a colon-separated list of 5 integer numbers (fields) with the
following interpretation::
control_percent:trip_point_index:speed_rpm:noise_level_mdb:power_mw
control_percent:trip_point_index:speed_rpm:noise_level_mdb:power_mw
* ``control_percent``: The percent value to be used to set the fan speed to a
specific level using the _FSL object (0-100).
Documentation/admin-guide/binderfs.rst
+6
View File
@@ -33,6 +33,12 @@ max
a per-instance limit. If ``max=<count>`` is set then only ``<count>`` number
of binder devices can be allocated in this binderfs instance.
stats
Using ``stats=global`` enables global binder statistics.
``stats=global`` is only available for a binderfs instance mounted in the
initial user namespace. An attempt to use the option to mount a binderfs
instance in another user namespace will return a permission error.
Allocating binder Devices
-------------------------
Documentation/admin-guide/binfmt-misc.rst
+4 -4
View File
@@ -1,5 +1,5 @@
Kernel Support for miscellaneous (your favourite) Binary Formats v1.1
=====================================================================
Kernel Support for miscellaneous Binary Formats (binfmt_misc)
=============================================================
This Kernel feature allows you to invoke almost (for restrictions see below)
every program by simply typing its name in the shell.
@@ -140,8 +140,8 @@ Hints
-----
If you want to pass special arguments to your interpreter, you can
write a wrapper script for it. See Documentation/admin-guide/java.rst for an
example.
write a wrapper script for it.
See :doc:`Documentation/admin-guide/java.rst <./java>` for an example.
Your interpreter should NOT look in the PATH for the filename; the kernel
passes it the full filename (or the file descriptor) to use. Using ``$PATH`` can
Documentation/admin-guide/blockdev/zram.rst
+32 -33
View File
@@ -1,15 +1,15 @@
========================================
zram: Compressed RAM based block devices
zram: Compressed RAM-based block devices
========================================
Introduction
============
The zram module creates RAM based block devices named /dev/zram<id>
The zram module creates RAM-based block devices named /dev/zram<id>
(<id> = 0, 1, ...). Pages written to these disks are compressed and stored
in memory itself. These disks allow very fast I/O and compression provides
good amounts of memory savings. Some of the usecases include /tmp storage,
use as swap disks, various caches under /var and maybe many more :)
good amounts of memory savings. Some of the use cases include /tmp storage,
use as swap disks, various caches under /var and maybe many more. :)
Statistics for individual zram devices are exported through sysfs nodes at
/sys/block/zram<id>/
@@ -43,17 +43,17 @@ The list of possible return codes:
======== =============================================================
-EBUSY an attempt to modify an attribute that cannot be changed once
the device has been initialised. Please reset device first;
the device has been initialised. Please reset device first.
-ENOMEM zram was not able to allocate enough memory to fulfil your
needs;
needs.
-EINVAL invalid input has been provided.
======== =============================================================
If you use 'echo', the returned value that is changed by 'echo' utility,
If you use 'echo', the returned value is set by the 'echo' utility,
and, in general case, something like::
echo 3 > /sys/block/zram0/max_comp_streams
if [ $? -ne 0 ];
if [ $? -ne 0 ]; then
handle_error
fi
@@ -65,7 +65,8 @@ should suffice.
::
modprobe zram num_devices=4
This creates 4 devices: /dev/zram{0,1,2,3}
This creates 4 devices: /dev/zram{0,1,2,3}
num_devices parameter is optional and tells zram how many devices should be
pre-created. Default: 1.
@@ -73,12 +74,12 @@ pre-created. Default: 1.
2) Set max number of compression streams
========================================
Regardless the value passed to this attribute, ZRAM will always
allocate multiple compression streams - one per online CPUs - thus
Regardless of the value passed to this attribute, ZRAM will always
allocate multiple compression streams - one per online CPU - thus
allowing several concurrent compression operations. The number of
allocated compression streams goes down when some of the CPUs
become offline. There is no single-compression-stream mode anymore,
unless you are running a UP system or has only 1 CPU online.
unless you are running a UP system or have only 1 CPU online.
To find out how many streams are currently available::
@@ -89,7 +90,7 @@ To find out how many streams are currently available::
Using comp_algorithm device attribute one can see available and
currently selected (shown in square brackets) compression algorithms,
change selected compression algorithm (once the device is initialised
or change the selected compression algorithm (once the device is initialised
there is no way to change compression algorithm).
Examples::
@@ -167,9 +168,9 @@ Examples::
zram provides a control interface, which enables dynamic (on-demand) device
addition and removal.
In order to add a new /dev/zramX device, perform read operation on hot_add
attribute. This will return either new device's device id (meaning that you
can use /dev/zram<id>) or error code.
In order to add a new /dev/zramX device, perform a read operation on the hot_add
attribute. This will return either the new device's device id (meaning that you
can use /dev/zram<id>) or an error code.
Example::
@@ -186,8 +187,8 @@ execute::
Per-device statistics are exported as various nodes under /sys/block/zram<id>/
A brief description of exported device attributes. For more details please
read Documentation/ABI/testing/sysfs-block-zram.
A brief description of exported device attributes follows. For more details
please read Documentation/ABI/testing/sysfs-block-zram.
====================== ====== ===============================================
Name access description
@@ -245,13 +246,11 @@ whitespace:
File /sys/block/zram<id>/mm_stat
The stat file represents device's mm statistics. It consists of a single
The mm_stat file represents the device's mm statistics. It consists of a single
line of text and contains the following stats separated by whitespace:
================ =============================================================
orig_data_size uncompressed size of data stored in this disk.
This excludes same-element-filled pages (same_pages) since
no memory is allocated for them.
Unit: bytes
compr_data_size compressed size of data stored in this disk
mem_used_total the amount of memory allocated for this disk. This
@@ -261,7 +260,7 @@ line of text and contains the following stats separated by whitespace:
Unit: bytes
mem_limit the maximum amount of memory ZRAM can use to store
the compressed data
mem_used_max the maximum amount of memory zram have consumed to
mem_used_max the maximum amount of memory zram has consumed to
store the data
same_pages the number of same element filled pages written to this disk.
No memory is allocated for such pages.
@@ -271,7 +270,7 @@ line of text and contains the following stats separated by whitespace:
File /sys/block/zram<id>/bd_stat
The stat file represents device's backing device statistics. It consists of
The bd_stat file represents a device's backing device statistics. It consists of
a single line of text and contains the following stats separated by whitespace:
============== =============================================================
@@ -316,9 +315,9 @@ To use the feature, admin should set up backing device via::
echo /dev/sda5 > /sys/block/zramX/backing_dev
before disksize setting. It supports only partition at this moment.
If admin want to use incompressible page writeback, they could do via::
If admin wants to use incompressible page writeback, they could do via::
echo huge > /sys/block/zramX/write
echo huge > /sys/block/zramX/writeback
To use idle page writeback, first, user need to declare zram pages
as idle::
@@ -326,7 +325,7 @@ as idle::
echo all > /sys/block/zramX/idle
From now on, any pages on zram are idle pages. The idle mark
will be removed until someone request access of the block.
will be removed until someone requests access of the block.
IOW, unless there is access request, those pages are still idle pages.
Admin can request writeback of those idle pages at right timing via::
@@ -341,16 +340,16 @@ to guarantee storage health for entire product life.
To overcome the concern, zram supports "writeback_limit" feature.
The "writeback_limit_enable"'s default value is 0 so that it doesn't limit
any writeback. IOW, if admin want to apply writeback budget, he should
any writeback. IOW, if admin wants to apply writeback budget, he should
enable writeback_limit_enable via::
$ echo 1 > /sys/block/zramX/writeback_limit_enable
Once writeback_limit_enable is set, zram doesn't allow any writeback
until admin set the budget via /sys/block/zramX/writeback_limit.
until admin sets the budget via /sys/block/zramX/writeback_limit.
(If admin doesn't enable writeback_limit_enable, writeback_limit's value
assigned via /sys/block/zramX/writeback_limit is meaninless.)
assigned via /sys/block/zramX/writeback_limit is meaningless.)
If admin want to limit writeback as per-day 400M, he could do it
like below::
@@ -361,13 +360,13 @@ like below::
/sys/block/zram0/writeback_limit.
$ echo 1 > /sys/block/zram0/writeback_limit_enable
If admin want to allow further write again once the bugdet is exausted,
If admins want to allow further write again once the bugdet is exhausted,
he could do it like below::
$ echo $((400<<MB_SHIFT>>4K_SHIFT)) > \
/sys/block/zram0/writeback_limit
If admin want to see remaining writeback budget since he set::
If admin wants to see remaining writeback budget since last set::
$ cat /sys/block/zramX/writeback_limit
@@ -375,12 +374,12 @@ If admin want to disable writeback limit, he could do::
$ echo 0 > /sys/block/zramX/writeback_limit_enable
The writeback_limit count will reset whenever you reset zram(e.g.,
The writeback_limit count will reset whenever you reset zram (e.g.,
system reboot, echo 1 > /sys/block/zramX/reset) so keeping how many of
writeback happened until you reset the zram to allocate extra writeback
budget in next setting is user's job.
If admin want to measure writeback count in a certain period, he could
If admin wants to measure writeback count in a certain period, he could
know it via /sys/block/zram0/bd_stat's 3rd column.
memory tracking
Documentation/admin-guide/bootconfig.rst
+218
View File
@@ -0,0 +1,218 @@
.. SPDX-License-Identifier: GPL-2.0
.. _bootconfig:
==================
Boot Configuration
==================
:Author: Masami Hiramatsu <mhiramat@kernel.org>
Overview
========
The boot configuration expands the current kernel command line to support
additional key-value data when booting the kernel in an efficient way.
This allows administrators to pass a structured-Key config file.
Config File Syntax
==================
The boot config syntax is a simple structured key-value. Each key consists
of dot-connected-words, and key and value are connected by ``=``. The value
has to be terminated by semi-colon (``;``) or newline (``\n``).
For array value, array entries are separated by comma (``,``). ::
KEY[.WORD[...]] = VALUE[, VALUE2[...]][;]
Unlike the kernel command line syntax, spaces are OK around the comma and ``=``.
Each key word must contain only alphabets, numbers, dash (``-``) or underscore
(``_``). And each value only contains printable characters or spaces except
for delimiters such as semi-colon (``;``), new-line (``\n``), comma (``,``),
hash (``#``) and closing brace (``}``).
If you want to use those delimiters in a value, you can use either double-
quotes (``"VALUE"``) or single-quotes (``'VALUE'``) to quote it. Note that
you can not escape these quotes.
There can be a key which doesn't have value or has an empty value. Those keys
are used for checking if the key exists or not (like a boolean).
Key-Value Syntax
----------------
The boot config file syntax allows user to merge partially same word keys
by brace. For example::
foo.bar.baz = value1
foo.bar.qux.quux = value2
These can be written also in::
foo.bar {
baz = value1
qux.quux = value2
}
Or more shorter, written as following::
foo.bar { baz = value1; qux.quux = value2 }
In both styles, same key words are automatically merged when parsing it
at boot time. So you can append similar trees or key-values.
Same-key Values
---------------
It is prohibited that two or more values or arrays share a same-key.
For example,::
foo = bar, baz
foo = qux # !ERROR! we can not re-define same key
If you want to append the value to existing key as an array member,
you can use ``+=`` operator. For example::
foo = bar, baz
foo += qux
In this case, the key ``foo`` has ``bar``, ``baz`` and ``qux``.
However, a sub-key and a value can not co-exist under a parent key.
For example, following config is NOT allowed.::
foo = value1
foo.bar = value2 # !ERROR! subkey "bar" and value "value1" can NOT co-exist
Comments
--------
The config syntax accepts shell-script style comments. The comments starting
with hash ("#") until newline ("\n") will be ignored.
::
# comment line
foo = value # value is set to foo.
bar = 1, # 1st element
2, # 2nd element
3 # 3rd element
This is parsed as below::
foo = value
bar = 1, 2, 3
Note that you can not put a comment between value and delimiter(``,`` or
``;``). This means following config has a syntax error ::
key = 1 # comment
,2
/proc/bootconfig
================
/proc/bootconfig is a user-space interface of the boot config.
Unlike /proc/cmdline, this file shows the key-value style list.
Each key-value pair is shown in each line with following style::
KEY[.WORDS...] = "[VALUE]"[,"VALUE2"...]
Boot Kernel With a Boot Config
==============================
Since the boot configuration file is loaded with initrd, it will be added
to the end of the initrd (initramfs) image file with size, checksum and
12-byte magic word as below.
[initrd][bootconfig][size(u32)][checksum(u32)][#BOOTCONFIG\n]
The Linux kernel decodes the last part of the initrd image in memory to
get the boot configuration data.
Because of this "piggyback" method, there is no need to change or
update the boot loader and the kernel image itself.
To do this operation, Linux kernel provides "bootconfig" command under
tools/bootconfig, which allows admin to apply or delete the config file
to/from initrd image. You can build it by the following command::
# make -C tools/bootconfig
To add your boot config file to initrd image, run bootconfig as below
(Old data is removed automatically if exists)::
# tools/bootconfig/bootconfig -a your-config /boot/initrd.img-X.Y.Z
To remove the config from the image, you can use -d option as below::
# tools/bootconfig/bootconfig -d /boot/initrd.img-X.Y.Z
Then add "bootconfig" on the normal kernel command line to tell the
kernel to look for the bootconfig at the end of the initrd file.
Config File Limitation
======================
Currently the maximum config size size is 32KB and the total key-words (not
key-value entries) must be under 1024 nodes.
Note: this is not the number of entries but nodes, an entry must consume
more than 2 nodes (a key-word and a value). So theoretically, it will be
up to 512 key-value pairs. If keys contains 3 words in average, it can
contain 256 key-value pairs. In most cases, the number of config items
will be under 100 entries and smaller than 8KB, so it would be enough.
If the node number exceeds 1024, parser returns an error even if the file
size is smaller than 32KB.
Anyway, since bootconfig command verifies it when appending a boot config
to initrd image, user can notice it before boot.
Bootconfig APIs
===============
User can query or loop on key-value pairs, also it is possible to find
a root (prefix) key node and find key-values under that node.
If you have a key string, you can query the value directly with the key
using xbc_find_value(). If you want to know what keys exist in the boot
config, you can use xbc_for_each_key_value() to iterate key-value pairs.
Note that you need to use xbc_array_for_each_value() for accessing
each array's value, e.g.::
vnode = NULL;
xbc_find_value("key.word", &vnode);
if (vnode && xbc_node_is_array(vnode))
xbc_array_for_each_value(vnode, value) {
printk("%s ", value);
}
If you want to focus on keys which have a prefix string, you can use
xbc_find_node() to find a node by the prefix string, and iterate
keys under the prefix node with xbc_node_for_each_key_value().
But the most typical usage is to get the named value under prefix
or get the named array under prefix as below::
root = xbc_find_node("key.prefix");
value = xbc_node_find_value(root, "option", &vnode);
...
xbc_node_for_each_array_value(root, "array-option", value, anode) {
...
}
This accesses a value of "key.prefix.option" and an array of
"key.prefix.array-option".
Locking is not needed, since after initialization, the config becomes
read-only. All data and keys must be copied if you need to modify it.
Functions and structures
========================
.. kernel-doc:: include/linux/bootconfig.h
.. kernel-doc:: lib/bootconfig.c
Documentation/admin-guide/cgroup-v1/cpusets.rst
+11
View File
@@ -223,6 +223,17 @@ cpu_online_mask using a CPU hotplug notifier, and the mems file
automatically tracks the value of node_states[N_MEMORY]--i.e.,
nodes with memory--using the cpuset_track_online_nodes() hook.
The cpuset.effective_cpus and cpuset.effective_mems files are
normally read-only copies of cpuset.cpus and cpuset.mems files
respectively. If the cpuset cgroup filesystem is mounted with the
special "cpuset_v2_mode" option, the behavior of these files will become
similar to the corresponding files in cpuset v2. In other words, hotplug
events will not change cpuset.cpus and cpuset.mems. Those events will
only affect cpuset.effective_cpus and cpuset.effective_mems which show
the actual cpus and memory nodes that are currently used by this cpuset.
See Documentation/admin-guide/cgroup-v2.rst for more information about
cpuset v2 behavior.
1.4 What are exclusive cpusets ?
--------------------------------
Documentation/admin-guide/cgroup-v1/hugetlb.rst
+92 -11
View File
@@ -2,13 +2,6 @@
HugeTLB Controller
==================
The HugeTLB controller allows to limit the HugeTLB usage per control group and
enforces the controller limit during page fault. Since HugeTLB doesn't
support page reclaim, enforcing the limit at page fault time implies that,
the application will get SIGBUS signal if it tries to access HugeTLB pages
beyond its limit. This requires the application to know beforehand how much
HugeTLB pages it would require for its use.
HugeTLB controller can be created by first mounting the cgroup filesystem.
# mount -t cgroup -o hugetlb none /sys/fs/cgroup
@@ -28,10 +21,14 @@ process (bash) into it.
Brief summary of control files::
hugetlb.<hugepagesize>.limit_in_bytes # set/show limit of "hugepagesize" hugetlb usage
hugetlb.<hugepagesize>.max_usage_in_bytes # show max "hugepagesize" hugetlb usage recorded
hugetlb.<hugepagesize>.usage_in_bytes # show current usage for "hugepagesize" hugetlb
hugetlb.<hugepagesize>.failcnt # show the number of allocation failure due to HugeTLB limit
hugetlb.<hugepagesize>.rsvd.limit_in_bytes # set/show limit of "hugepagesize" hugetlb reservations
hugetlb.<hugepagesize>.rsvd.max_usage_in_bytes # show max "hugepagesize" hugetlb reservations and no-reserve faults
hugetlb.<hugepagesize>.rsvd.usage_in_bytes # show current reservations and no-reserve faults for "hugepagesize" hugetlb
hugetlb.<hugepagesize>.rsvd.failcnt # show the number of allocation failure due to HugeTLB reservation limit
hugetlb.<hugepagesize>.limit_in_bytes # set/show limit of "hugepagesize" hugetlb faults
hugetlb.<hugepagesize>.max_usage_in_bytes # show max "hugepagesize" hugetlb usage recorded
hugetlb.<hugepagesize>.usage_in_bytes # show current usage for "hugepagesize" hugetlb
hugetlb.<hugepagesize>.failcnt # show the number of allocation failure due to HugeTLB usage limit
For a system supporting three hugepage sizes (64k, 32M and 1G), the control
files include::
@@ -40,11 +37,95 @@ files include::
hugetlb.1GB.max_usage_in_bytes
hugetlb.1GB.usage_in_bytes
hugetlb.1GB.failcnt
hugetlb.1GB.rsvd.limit_in_bytes
hugetlb.1GB.rsvd.max_usage_in_bytes
hugetlb.1GB.rsvd.usage_in_bytes
hugetlb.1GB.rsvd.failcnt
hugetlb.64KB.limit_in_bytes
hugetlb.64KB.max_usage_in_bytes
hugetlb.64KB.usage_in_bytes
hugetlb.64KB.failcnt
hugetlb.64KB.rsvd.limit_in_bytes
hugetlb.64KB.rsvd.max_usage_in_bytes
hugetlb.64KB.rsvd.usage_in_bytes
hugetlb.64KB.rsvd.failcnt
hugetlb.32MB.limit_in_bytes
hugetlb.32MB.max_usage_in_bytes
hugetlb.32MB.usage_in_bytes
hugetlb.32MB.failcnt
hugetlb.32MB.rsvd.limit_in_bytes
hugetlb.32MB.rsvd.max_usage_in_bytes
hugetlb.32MB.rsvd.usage_in_bytes
hugetlb.32MB.rsvd.failcnt
1. Page fault accounting
hugetlb.<hugepagesize>.limit_in_bytes
hugetlb.<hugepagesize>.max_usage_in_bytes
hugetlb.<hugepagesize>.usage_in_bytes
hugetlb.<hugepagesize>.failcnt
The HugeTLB controller allows users to limit the HugeTLB usage (page fault) per
control group and enforces the limit during page fault. Since HugeTLB
doesn't support page reclaim, enforcing the limit at page fault time implies
that, the application will get SIGBUS signal if it tries to fault in HugeTLB
pages beyond its limit. Therefore the application needs to know exactly how many
HugeTLB pages it uses before hand, and the sysadmin needs to make sure that
there are enough available on the machine for all the users to avoid processes
getting SIGBUS.
2. Reservation accounting
hugetlb.<hugepagesize>.rsvd.limit_in_bytes
hugetlb.<hugepagesize>.rsvd.max_usage_in_bytes
hugetlb.<hugepagesize>.rsvd.usage_in_bytes
hugetlb.<hugepagesize>.rsvd.failcnt
The HugeTLB controller allows to limit the HugeTLB reservations per control
group and enforces the controller limit at reservation time and at the fault of
HugeTLB memory for which no reservation exists. Since reservation limits are
enforced at reservation time (on mmap or shget), reservation limits never causes
the application to get SIGBUS signal if the memory was reserved before hand. For
MAP_NORESERVE allocations, the reservation limit behaves the same as the fault
limit, enforcing memory usage at fault time and causing the application to
receive a SIGBUS if it's crossing its limit.
Reservation limits are superior to page fault limits described above, since
reservation limits are enforced at reservation time (on mmap or shget), and
never causes the application to get SIGBUS signal if the memory was reserved
before hand. This allows for easier fallback to alternatives such as
non-HugeTLB memory for example. In the case of page fault accounting, it's very
hard to avoid processes getting SIGBUS since the sysadmin needs precisely know
the HugeTLB usage of all the tasks in the system and make sure there is enough
pages to satisfy all requests. Avoiding tasks getting SIGBUS on overcommited
systems is practically impossible with page fault accounting.
3. Caveats with shared memory
For shared HugeTLB memory, both HugeTLB reservation and page faults are charged
to the first task that causes the memory to be reserved or faulted, and all
subsequent uses of this reserved or faulted memory is done without charging.
Shared HugeTLB memory is only uncharged when it is unreserved or deallocated.
This is usually when the HugeTLB file is deleted, and not when the task that
caused the reservation or fault has exited.
4. Caveats with HugeTLB cgroup offline.
When a HugeTLB cgroup goes offline with some reservations or faults still
charged to it, the behavior is as follows:
- The fault charges are charged to the parent HugeTLB cgroup (reparented),
- the reservation charges remain on the offline HugeTLB cgroup.
This means that if a HugeTLB cgroup gets offlined while there is still HugeTLB
reservations charged to it, that cgroup persists as a zombie until all HugeTLB
reservations are uncharged. HugeTLB reservations behave in this manner to match
the memory controller whose cgroups also persist as zombie until all charged
memory is uncharged. Also, the tracking of HugeTLB reservations is a bit more
complex compared to the tracking of HugeTLB faults, so it is significantly
harder to reparent reservations at offline time.
Documentation/admin-guide/cgroup-v1/index.rst
+2
View File
@@ -1,3 +1,5 @@
.. _cgroup-v1:
========================
Control Groups version 1
========================
Documentation/admin-guide/cgroup-v2.rst
+19 -20
View File
@@ -9,7 +9,7 @@ This is the authoritative documentation on the design, interface and
conventions of cgroup v2. It describes all userland-visible aspects
of cgroup including core and specific controller behaviors. All
future changes must be reflected in this document. Documentation for
v1 is available under Documentation/admin-guide/cgroup-v1/.
v1 is available under :ref:`Documentation/admin-guide/cgroup-v1/index.rst <cgroup-v1>`.
.. CONTENTS
@@ -188,6 +188,17 @@ cgroup v2 currently supports the following mount options.
modified through remount from the init namespace. The mount
option is ignored on non-init namespace mounts.
memory_recursiveprot
Recursively apply memory.min and memory.low protection to
entire subtrees, without requiring explicit downward
propagation into leaf cgroups. This allows protecting entire
subtrees from one another, while retaining free competition
within those subtrees. This should have been the default
behavior but is a mount-option to avoid regressing setups
relying on the original semantics (e.g. specifying bogusly
high 'bypass' protection values at higher tree levels).
Organizing Processes and Threads
--------------------------------
@@ -1023,7 +1034,7 @@ All time durations are in microseconds.
A read-only nested-key file which exists on non-root cgroups.
Shows pressure stall information for CPU. See
Documentation/accounting/psi.rst for details.
:ref:`Documentation/accounting/psi.rst <psi>` for details.
cpu.uclamp.min
A read-write single value file which exists on non-root cgroups.
@@ -1103,7 +1114,7 @@ PAGE_SIZE multiple when read back.
proportionally to the overage, reducing reclaim pressure for
smaller overages.
Effective min boundary is limited by memory.min values of
Effective min boundary is limited by memory.min values of
all ancestor cgroups. If there is memory.min overcommitment
(child cgroup or cgroups are requiring more protected memory
than parent will allow), then each child cgroup will get
@@ -1313,53 +1324,41 @@ PAGE_SIZE multiple when read back.
Number of major page faults incurred
workingset_refault
Number of refaults of previously evicted pages
workingset_activate
Number of refaulted pages that were immediately activated
workingset_nodereclaim
Number of times a shadow node has been reclaimed
pgrefill
Amount of scanned pages (in an active LRU list)
pgscan
Amount of scanned pages (in an inactive LRU list)
pgsteal
Amount of reclaimed pages
pgactivate
Amount of pages moved to the active LRU list
pgdeactivate
Amount of pages moved to the inactive LRU list
pglazyfree
Amount of pages postponed to be freed under memory pressure
pglazyfreed
Amount of reclaimed lazyfree pages
thp_fault_alloc
Number of transparent hugepages which were allocated to satisfy
a page fault, including COW faults. This counter is not present
when CONFIG_TRANSPARENT_HUGEPAGE is not set.
thp_collapse_alloc
Number of transparent hugepages which were allocated to allow
collapsing an existing range of pages. This counter is not
present when CONFIG_TRANSPARENT_HUGEPAGE is not set.
@@ -1403,7 +1402,7 @@ PAGE_SIZE multiple when read back.
A read-only nested-key file which exists on non-root cgroups.
Shows pressure stall information for memory. See
Documentation/accounting/psi.rst for details.
:ref:`Documentation/accounting/psi.rst <psi>` for details.
Usage Guidelines
@@ -1478,7 +1477,7 @@ IO Interface Files
dios Number of discard IOs
====== =====================
An example read output follows:
An example read output follows::
8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353 dbytes=0 dios=0
8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252 dbytes=50331648 dios=3021
@@ -1643,7 +1642,7 @@ IO Interface Files
A read-only nested-key file which exists on non-root cgroups.
Shows pressure stall information for IO. See
Documentation/accounting/psi.rst for details.
:ref:`Documentation/accounting/psi.rst <psi>` for details.
Writeback
@@ -1853,7 +1852,7 @@ Cpuset Interface Files
from the requested CPUs.
The CPU numbers are comma-separated numbers or ranges.
For example:
For example::
# cat cpuset.cpus
0-4,6,8-10
@@ -1892,7 +1891,7 @@ Cpuset Interface Files
from the requested memory nodes.
The memory node numbers are comma-separated numbers or ranges.
For example:
For example::
# cat cpuset.mems
0-1,3
Documentation/admin-guide/device-mapper/dm-raid.rst
+2
View File
@@ -419,3 +419,5 @@ Version History
rebuild errors.
1.15.0 Fix size extensions not being synchronized in case of new MD bitmap
pages allocated; also fix those not occuring after previous reductions
1.15.1 Fix argument count and arguments for rebuild/write_mostly/journal_(dev|mode)
on the status line.
Documentation/admin-guide/dynamic-debug-howto.rst
+3
View File
@@ -54,6 +54,9 @@ If you make a mistake with the syntax, the write will fail thus::
<debugfs>/dynamic_debug/control
-bash: echo: write error: Invalid argument
Note, for systems without 'debugfs' enabled, the control file can be
found in ``/proc/dynamic_debug/control``.
Viewing Dynamic Debug Behaviour
===============================
Documentation/driver-api/edid.rst → Documentation/admin-guide/edid.rst
+3 -1
View File
@@ -11,11 +11,13 @@ Today, with the advent of Kernel Mode Setting, a graphics board is
either correctly working because all components follow the standards -
or the computer is unusable, because the screen remains dark after
booting or it displays the wrong area. Cases when this happens are:
- The graphics board does not recognize the monitor.
- The graphics board is unable to detect any EDID data.
- The graphics board incorrectly forwards EDID data to the driver.
- The monitor sends no or bogus EDID data.
- A KVM sends its own EDID data instead of querying the connected monitor.
Adding the kernel parameter "nomodeset" helps in most cases, but causes
restrictions later on.
@@ -32,7 +34,7 @@ individual data for a specific misbehaving monitor, commented sources
and a Makefile environment are given here.
To create binary EDID and C source code files from the existing data
material, simply type "make".
material, simply type "make" in tools/edid/.
If you want to create your own EDID file, copy the file 1024x768.S,
replace the settings with your own data and add a new target to the
Documentation/admin-guide/ext4.rst
+2
View File
@@ -92,6 +92,8 @@ Currently Available
* efficient new ordered mode in JBD2 and ext4 (avoid using buffer head to force
the ordering)
* Case-insensitive file name lookups
* file-based encryption support (fscrypt)
* file-based verity support (fsverity)
[1] Filesystems with a block size of 1k may see a limit imposed by the
directory hash tree having a maximum depth of two.
Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
-2
View File
@@ -136,8 +136,6 @@ enables the mitigation by default.
The mitigation can be controlled at boot time via a kernel command line option.
See :ref:`taa_mitigation_control_command_line`.
.. _virt_mechanism:
Virtualization mitigation
^^^^^^^^^^^^^^^^^^^^^^^^^
Documentation/admin-guide/index.rst
+3
View File
@@ -64,6 +64,7 @@ configure specific aspects of kernel behavior to your liking.
binderfs
binfmt-misc
blockdev/index
bootconfig
braille-console
btmrvl
cgroup-v1/index
@@ -74,8 +75,10 @@ configure specific aspects of kernel behavior to your liking.
cputopology
dell_rbu
device-mapper/index
edid
efi-stub
ext4
nfs/index
gpio/index
highuid
hw_random
Documentation/admin-guide/iostats.rst
+4 -1
View File
@@ -100,7 +100,7 @@ Field 10 -- # of milliseconds spent doing I/Os (unsigned int)
Since 5.0 this field counts jiffies when at least one request was
started or completed. If request runs more than 2 jiffies then some
I/O time will not be accounted unless there are other requests.
I/O time might be not accounted in case of concurrent requests.
Field 11 -- weighted # of milliseconds spent doing I/Os (unsigned int)
This field is incremented at each I/O start, I/O completion, I/O
@@ -143,6 +143,9 @@ are summed (possibly overflowing the unsigned long variable they are
summed to) and the result given to the user. There is no convenient
user interface for accessing the per-CPU counters themselves.
Since 4.19 request times are measured with nanoseconds precision and
truncated to milliseconds before showing in this interface.
Disks vs Partitions
-------------------
Documentation/admin-guide/kernel-parameters.txt
+152 -28
View File
@@ -22,11 +22,13 @@
default: 0
acpi_backlight= [HW,ACPI]
acpi_backlight=vendor
acpi_backlight=video
If set to vendor, prefer vendor specific driver
{ vendor | video | native | none }
If set to vendor, prefer vendor-specific driver
(e.g. thinkpad_acpi, sony_acpi, etc.) instead
of the ACPI video.ko driver.
If set to video, use the ACPI video.ko driver.
If set to native, use the device's native backlight mode.
If set to none, disable the ACPI backlight interface.
acpi_force_32bit_fadt_addr
force FADT to use 32 bit addresses rather than the
@@ -136,6 +138,10 @@
dynamic table installation which will install SSDT
tables to /sys/firmware/acpi/tables/dynamic.
acpi_no_watchdog [HW,ACPI,WDT]
Ignore the ACPI-based watchdog interface (WDAT) and let
a native driver control the watchdog device instead.
acpi_rsdp= [ACPI,EFI,KEXEC]
Pass the RSDP address to the kernel, mostly used
on machines running EFI runtime service to boot the
@@ -437,9 +443,18 @@
no delay (0).
Format: integer
bootconfig [KNL]
Extended command line options can be added to an initrd
and this will cause the kernel to look for it.
See Documentation/admin-guide/bootconfig.rst
bert_disable [ACPI]
Disable BERT OS support on buggy BIOSes.
bgrt_disable [ACPI][X86]
Disable BGRT to avoid flickering OEM logo.
bttv.card= [HW,V4L] bttv (bt848 + bt878 based grabber cards)
bttv.radio= Most important insmod options are available as
kernel args too.
@@ -512,6 +527,7 @@
Default value is set via a kernel config option.
Value can be changed at runtime via
/sys/fs/selinux/checkreqprot.
Setting checkreqprot to 1 is deprecated.
cio_ignore= [S390]
See Documentation/s390/common_io.rst for details.
@@ -669,7 +685,7 @@
coredump_filter=
[KNL] Change the default value for
/proc/<pid>/coredump_filter.
See also Documentation/filesystems/proc.txt.
See also Documentation/filesystems/proc.rst.
coresight_cpu_debug.enable
[ARM,ARM64]
@@ -834,6 +850,18 @@
dump out devices still on the deferred probe list after
retrying.
dfltcc= [HW,S390]
Format: { on | off | def_only | inf_only | always }
on: s390 zlib hardware support for compression on
level 1 and decompression (default)
off: No s390 zlib hardware support
def_only: s390 zlib hardware support for deflate
only (compression on level 1)
inf_only: s390 zlib hardware support for inflate
only (decompression)
always: Same as 'on' but ignores the selected compression
level always using hardware support (used for debugging)
dhash_entries= [KNL]
Set number of hash buckets for dentry cache.
@@ -934,7 +962,7 @@
edid/1680x1050.bin, or edid/1920x1080.bin is given
and no file with the same name exists. Details and
instructions how to build your own EDID data are
available in Documentation/driver-api/edid.rst. An EDID
available in Documentation/admin-guide/edid.rst. An EDID
data set will only be used for a particular connector,
if its name and a colon are prepended to the EDID
name. Each connector may use a unique EDID data
@@ -964,10 +992,6 @@
Documentation/admin-guide/dynamic-debug-howto.rst
for details.
nompx [X86] Disables Intel Memory Protection Extensions.
See Documentation/x86/intel_mpx.rst for more
information about the feature.
nopku [X86] Disable Memory Protection Keys CPU feature found
in some Intel CPUs.
@@ -1077,6 +1101,12 @@
A valid base address must be provided, and the serial
port must already be setup and configured.
ec_imx21,<addr>
ec_imx6q,<addr>
Start an early, polled-mode, output-only console on the
Freescale i.MX UART at the specified address. The UART
must already be setup and configured.
ar3700_uart,<addr>
Start an early, polled-mode console on the
Armada 3700 serial port at the specified
@@ -1332,6 +1362,24 @@
can be changed at run time by the max_graph_depth file
in the tracefs tracing directory. default: 0 (no limit)
fw_devlink= [KNL] Create device links between consumer and supplier
devices by scanning the firmware to infer the
consumer/supplier relationships. This feature is
especially useful when drivers are loaded as modules as
it ensures proper ordering of tasks like device probing
(suppliers first, then consumers), supplier boot state
clean up (only after all consumers have probed),
suspend/resume & runtime PM (consumers first, then
suppliers).
Format: { off | permissive | on | rpm }
off -- Don't create device links from firmware info.
permissive -- Create device links from firmware info
but use it only for ordering boot state clean
up (sync_state() calls).
on -- Create device links from firmware info and use it
to enforce probe and suspend/resume ordering.
rpm -- Like "on", but also use to order runtime PM.
gamecon.map[2|3]=
[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
support via parallel port (up to 5 devices per port)
@@ -1423,6 +1471,14 @@
hpet_mmap= [X86, HPET_MMAP] Allow userspace to mmap HPET
registers. Default set by CONFIG_HPET_MMAP_DEFAULT.
hugetlb_cma= [HW] The size of a cma area used for allocation
of gigantic hugepages.
Format: nn[KMGTPE]
Reserve a cma area of given size and allocate gigantic
hugepages using the cma allocator. If enabled, the
boot-time allocation of gigantic hugepages is skipped.
hugepages= [HW,X86-32,IA-64] HugeTLB pages to allocate at boot.
hugepagesz= [HW,IA-64,PPC,X86-64] The size of the HugeTLB pages.
On x86-64 and powerpc, this option can be specified
@@ -1757,7 +1813,7 @@
provided by tboot because it makes the system
vulnerable to DMA attacks.
nobounce [Default off]
Disable bounce buffer for unstrusted devices such as
Disable bounce buffer for untrusted devices such as
the Thunderbolt devices. This will treat the untrusted
devices as the trusted ones, hence might expose security
risks of DMA attacks.
@@ -1861,7 +1917,7 @@
No delay
ip= [IP_PNP]
See Documentation/filesystems/nfs/nfsroot.txt.
See Documentation/admin-guide/nfs/nfsroot.rst.
ipcmni_extend [KNL] Extend the maximum number of unique System V
IPC identifiers from 32,768 to 16,777,216.
@@ -2521,13 +2577,22 @@
For details see: Documentation/admin-guide/hw-vuln/mds.rst
mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory
Amount of memory to be used when the kernel is not able
to see the whole system memory or for test.
Amount of memory to be used in cases as follows:
1 for test;
2 when the kernel is not able to see the whole system memory;
3 memory that lies after 'mem=' boundary is excluded from
the hypervisor, then assigned to KVM guests.
[X86] Work as limiting max address. Use together
with memmap= to avoid physical address space collisions.
Without memmap= PCI devices could be placed at addresses
belonging to unused RAM.
Note that this only takes effects during boot time since
in above case 3, memory may need be hot added after boot
if system memory of hypervisor is not sufficient.
mem=nopentium [BUGS=X86-32] Disable usage of 4MB pages for kernel
memory.
@@ -2773,7 +2838,7 @@
<name>,<region-number>[,<base>,<size>,<buswidth>,<altbuswidth>]
mtdparts= [MTD]
See drivers/mtd/cmdlinepart.c.
See drivers/mtd/parsers/cmdlinepart.c
multitce=off [PPC] This parameter disables the use of the pSeries
firmware feature for updating multiple TCE entries
@@ -2831,13 +2896,13 @@
Default value is 0.
nfsaddrs= [NFS] Deprecated. Use ip= instead.
See Documentation/filesystems/nfs/nfsroot.txt.
See Documentation/admin-guide/nfs/nfsroot.rst.
nfsroot= [NFS] nfs root filesystem for disk-less boxes.
See Documentation/filesystems/nfs/nfsroot.txt.
See Documentation/admin-guide/nfs/nfsroot.rst.
nfsrootdebug [NFS] enable nfsroot debugging messages.
See Documentation/filesystems/nfs/nfsroot.txt.
See Documentation/admin-guide/nfs/nfsroot.rst.
nfs.callback_nr_threads=
[NFSv4] set the total number of threads that the
@@ -3152,7 +3217,7 @@
[X86,PV_OPS] Disable paravirtualized VMware scheduler
clock and use the default one.
no-steal-acc [X86,KVM,ARM64] Disable paravirtualized steal time
no-steal-acc [X86,PV_OPS,ARM64] Disable paravirtualized steal time
accounting. steal time is computed, but won't
influence scheduler behaviour
@@ -3263,12 +3328,6 @@
This can be set from sysctl after boot.
See Documentation/admin-guide/sysctl/vm.rst for details.
of_devlink [OF, KNL] Create device links between consumer and
supplier devices by scanning the devictree to infer the
consumer/supplier relationships. A consumer device
will not be probed until all the supplier devices have
probed successfully.
ohci1394_dma=early [HW] enable debugging via the ohci1394 driver.
See Documentation/debugging-via-ohci1394.txt for more
info.
@@ -3676,6 +3735,9 @@
Override pmtimer IOPort with a hex value.
e.g. pmtmr=0x508
pm_debug_messages [SUSPEND,KNL]
Enable suspend/resume debug messages during boot up.
pnp.debug=1 [PNP]
Enable PNP debug messages (depends on the
CONFIG_PNP_DEBUG_MESSAGES option). Change at run-time
@@ -3777,6 +3839,11 @@
before loading.
See Documentation/admin-guide/blockdev/ramdisk.rst.
prot_virt= [S390] enable hosting protected virtual machines
isolated from the hypervisor (if hardware supports
that).
Format: <bool>
psi= [KNL] Enable or disable pressure stall information
tracking.
Format: <bool>
@@ -3962,6 +4029,15 @@
Set threshold of queued RCU callbacks below which
batch limiting is re-enabled.
rcutree.qovld= [KNL]
Set threshold of queued RCU callbacks beyond which
RCU's force-quiescent-state scan will aggressively
enlist help from cond_resched() and sched IPIs to
help CPUs more quickly reach quiescent states.
Set to less than zero to make this be set based
on rcutree.qhimark at boot time and to zero to
disable more aggressive help enlistment.
rcutree.rcu_idle_gp_delay= [KNL]
Set wakeup interval for idle CPUs that have
RCU callbacks (RCU_FAST_NO_HZ=y).
@@ -4177,6 +4253,12 @@
rcupdate.rcu_cpu_stall_suppress= [KNL]
Suppress RCU CPU stall warning messages.
rcupdate.rcu_cpu_stall_suppress_at_boot= [KNL]
Suppress RCU CPU stall warning messages and
rcutorture writer stall warnings that occur
during early boot, that is, during the time
before the init task is spawned.
rcupdate.rcu_cpu_stall_timeout= [KNL]
Set timeout for RCU CPU stall warning messages.
@@ -4370,6 +4452,22 @@
incurs a small amount of overhead in the scheduler
but is useful for debugging and performance tuning.
sched_thermal_decay_shift=
[KNL, SMP] Set a decay shift for scheduler thermal
pressure signal. Thermal pressure signal follows the
default decay period of other scheduler pelt
signals(usually 32 ms but configurable). Setting
sched_thermal_decay_shift will left shift the decay
period for the thermal pressure signal by the shift
value.
i.e. with the default pelt decay period of 32 ms
sched_thermal_decay_shift thermal pressure decay pr
1 64 ms
2 128 ms
and so on.
Format: integer between 0 and 10
Default is 0.
skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate
xtime_lock contention on larger systems, and/or RCU lock
contention on all systems with CONFIG_MAXSMP set.
@@ -4492,10 +4590,10 @@
Format: <integer>
A nonzero value instructs the soft-lockup detector
to panic the machine when a soft-lockup occurs. This
is also controlled by CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC
which is the respective build-time switch to that
functionality.
to panic the machine when a soft-lockup occurs. It is
also controlled by the kernel.softlockup_panic sysctl
and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the
respective build-time switch to that functionality.
softlockup_all_cpu_backtrace=
[KNL] Should the soft-lockup detector generate
@@ -4637,6 +4735,28 @@
spia_pedr=
spia_peddr=
split_lock_detect=
[X86] Enable split lock detection
When enabled (and if hardware support is present), atomic
instructions that access data across cache line
boundaries will result in an alignment check exception.
off - not enabled
warn - the kernel will emit rate limited warnings
about applications triggering the #AC
exception. This mode is the default on CPUs
that supports split lock detection.
fatal - the kernel will send SIGBUS to applications
that trigger the #AC exception.
If an #AC exception is hit in the kernel or in
firmware (i.e. not while executing in user mode)
the kernel will oops in either "warn" or "fatal"
mode.
srcutree.counter_wrap_check [KNL]
Specifies how frequently to check for
grace-period sequence counter wrap for the
@@ -4849,6 +4969,10 @@
topology updates sent by the hypervisor to this
LPAR.
torture.disable_onoff_at_boot= [KNL]
Prevent the CPU-hotplug component of torturing
until after init has spawned.
tp720= [HW,PS2]
tpm_suspend_pcr=[HW,TPM]
Documentation/admin-guide/kernel-per-CPU-kthreads.rst
+1 -1
View File
@@ -234,7 +234,7 @@ To reduce its OS jitter, do any of the following:
Such a workqueue can be confined to a given subset of the
CPUs using the ``/sys/devices/virtual/workqueue/*/cpumask`` sysfs
files. The set of WQ_SYSFS workqueues can be displayed using
"ls sys/devices/virtual/workqueue". That said, the workqueues
"ls /sys/devices/virtual/workqueue". That said, the workqueues
maintainer would like to caution people against indiscriminately
sprinkling WQ_SYSFS across all the workqueues. The reason for
caution is that it is easy to add WQ_SYSFS, but because sysfs is
Documentation/admin-guide/mm/transhuge.rst
+14
View File
@@ -310,6 +310,11 @@ thp_fault_fallback
is incremented if a page fault fails to allocate
a huge page and instead falls back to using small pages.
thp_fault_fallback_charge
is incremented if a page fault fails to charge a huge page and
instead falls back to using small pages even though the
allocation was successful.
thp_collapse_alloc_failed
is incremented if khugepaged found a range
of pages that should be collapsed into one huge page but failed
@@ -319,6 +324,15 @@ thp_file_alloc
is incremented every time a file huge page is successfully
allocated.
thp_file_fallback
is incremented if a file huge page is attempted to be allocated
but fails and instead falls back to using small pages.
thp_file_fallback_charge
is incremented if a file huge page cannot be charged and instead
falls back to using small pages even though the allocation was
successful.
thp_file_mapped
is incremented every time a file huge page is mapped into
user address space.
Documentation/admin-guide/mm/userfaultfd.rst
+51
View File
@@ -108,6 +108,57 @@ UFFDIO_COPY. They're atomic as in guaranteeing that nothing can see an
half copied page since it'll keep userfaulting until the copy has
finished.
Notes:
- If you requested UFFDIO_REGISTER_MODE_MISSING when registering then
you must provide some kind of page in your thread after reading from
the uffd. You must provide either UFFDIO_COPY or UFFDIO_ZEROPAGE.
The normal behavior of the OS automatically providing a zero page on
an annonymous mmaping is not in place.
- None of the page-delivering ioctls default to the range that you
registered with. You must fill in all fields for the appropriate
ioctl struct including the range.
- You get the address of the access that triggered the missing page
event out of a struct uffd_msg that you read in the thread from the
uffd. You can supply as many pages as you want with UFFDIO_COPY or
UFFDIO_ZEROPAGE. Keep in mind that unless you used DONTWAKE then
the first of any of those IOCTLs wakes up the faulting thread.
- Be sure to test for all errors including (pollfd[0].revents &
POLLERR). This can happen, e.g. when ranges supplied were
incorrect.
Write Protect Notifications
---------------------------
This is equivalent to (but faster than) using mprotect and a SIGSEGV
signal handler.
Firstly you need to register a range with UFFDIO_REGISTER_MODE_WP.
Instead of using mprotect(2) you use ioctl(uffd, UFFDIO_WRITEPROTECT,
struct *uffdio_writeprotect) while mode = UFFDIO_WRITEPROTECT_MODE_WP
in the struct passed in. The range does not default to and does not
have to be identical to the range you registered with. You can write
protect as many ranges as you like (inside the registered range).
Then, in the thread reading from uffd the struct will have
msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP set. Now you send
ioctl(uffd, UFFDIO_WRITEPROTECT, struct *uffdio_writeprotect) again
while pagefault.mode does not have UFFDIO_WRITEPROTECT_MODE_WP set.
This wakes up the thread which will continue to run with writes. This
allows you to do the bookkeeping about the write in the uffd reading
thread before the ioctl.
If you registered with both UFFDIO_REGISTER_MODE_MISSING and
UFFDIO_REGISTER_MODE_WP then you need to think about the sequence in
which you supply a page and undo write protect. Note that there is a
difference between writes into a WP area and into a !WP area. The
former will have UFFD_PAGEFAULT_FLAG_WP set, the latter
UFFD_PAGEFAULT_FLAG_WRITE. The latter did not fail on protection but
you still need to supply a page when UFFDIO_REGISTER_MODE_MISSING was
used.
QEMU/KVM
========
Documentation/admin-guide/nfs/fault_injection.rst
+70
View File
@@ -0,0 +1,70 @@
===================
NFS Fault Injection
===================
Fault injection is a method for forcing errors that may not normally occur, or
may be difficult to reproduce. Forcing these errors in a controlled environment
can help the developer find and fix bugs before their code is shipped in a
production system. Injecting an error on the Linux NFS server will allow us to
observe how the client reacts and if it manages to recover its state correctly.
NFSD_FAULT_INJECTION must be selected when configuring the kernel to use this
feature.
Using Fault Injection
=====================
On the client, mount the fault injection server through NFS v4.0+ and do some
work over NFS (open files, take locks, ...).
On the server, mount the debugfs filesystem to <debug_dir> and ls
<debug_dir>/nfsd. This will show a list of files that will be used for
injecting faults on the NFS server. As root, write a number n to the file
corresponding to the action you want the server to take. The server will then
process the first n items it finds. So if you want to forget 5 locks, echo '5'
to <debug_dir>/nfsd/forget_locks. A value of 0 will tell the server to forget
all corresponding items. A log message will be created containing the number
of items forgotten (check dmesg).
Go back to work on the client and check if the client recovered from the error
correctly.
Available Faults
================
forget_clients:
The NFS server keeps a list of clients that have placed a mount call. If
this list is cleared, the server will have no knowledge of who the client
is, forcing the client to reauthenticate with the server.
forget_openowners:
The NFS server keeps a list of what files are currently opened and who
they were opened by. Clearing this list will force the client to reopen
its files.
forget_locks:
The NFS server keeps a list of what files are currently locked in the VFS.
Clearing this list will force the client to reclaim its locks (files are
unlocked through the VFS as they are cleared from this list).
forget_delegations:
A delegation is used to assure the client that a file, or part of a file,
has not changed since the delegation was awarded. Clearing this list will
force the client to reacquire its delegation before accessing the file
again.
recall_delegations:
Delegations can be recalled by the server when another client attempts to
access a file. This test will notify the client that its delegation has
been revoked, forcing the client to reacquire the delegation before using
the file again.
tools/nfs/inject_faults.sh script
=================================
This script has been created to ease the fault injection process. This script
will detect the mounted debugfs directory and write to the files located there
based on the arguments passed by the user. For example, running
`inject_faults.sh forget_locks 1` as root will instruct the server to forget
one lock. Running `inject_faults forget_locks` will instruct the server to
forgetall locks.
Documentation/admin-guide/nfs/index.rst
+15
View File
@@ -0,0 +1,15 @@
=============
NFS
=============
.. toctree::
:maxdepth: 1
nfs-client
nfsroot
nfs-rdma
nfsd-admin-interfaces
nfs-idmapper
pnfs-block-server
pnfs-scsi-server
fault_injection
Documentation/admin-guide/nfs/nfs-client.rst
+141
View File
@@ -0,0 +1,141 @@
==========
NFS Client
==========
The NFS client
==============
The NFS version 2 protocol was first documented in RFC1094 (March 1989).
Since then two more major releases of NFS have been published, with NFSv3
being documented in RFC1813 (June 1995), and NFSv4 in RFC3530 (April
2003).
The Linux NFS client currently supports all the above published versions,
and work is in progress on adding support for minor version 1 of the NFSv4
protocol.
The purpose of this document is to provide information on some of the
special features of the NFS client that can be configured by system
administrators.
The nfs4_unique_id parameter
============================
NFSv4 requires clients to identify themselves to servers with a unique
string. File open and lock state shared between one client and one server
is associated with this identity. To support robust NFSv4 state recovery
and transparent state migration, this identity string must not change
across client reboots.
Without any other intervention, the Linux client uses a string that contains
the local system's node name. System administrators, however, often do not
take care to ensure that node names are fully qualified and do not change
over the lifetime of a client system. Node names can have other
administrative requirements that require particular behavior that does not
work well as part of an nfs_client_id4 string.
The nfs.nfs4_unique_id boot parameter specifies a unique string that can be
used instead of a system's node name when an NFS client identifies itself to
a server. Thus, if the system's node name is not unique, or it changes, its
nfs.nfs4_unique_id stays the same, preventing collision with other clients
or loss of state during NFS reboot recovery or transparent state migration.
The nfs.nfs4_unique_id string is typically a UUID, though it can contain
anything that is believed to be unique across all NFS clients. An
nfs4_unique_id string should be chosen when a client system is installed,
just as a system's root file system gets a fresh UUID in its label at
install time.
The string should remain fixed for the lifetime of the client. It can be
changed safely if care is taken that the client shuts down cleanly and all
outstanding NFSv4 state has expired, to prevent loss of NFSv4 state.
This string can be stored in an NFS client's grub.conf, or it can be provided
via a net boot facility such as PXE. It may also be specified as an nfs.ko
module parameter. Specifying a uniquifier string is not support for NFS
clients running in containers.
The DNS resolver
================
NFSv4 allows for one server to refer the NFS client to data that has been
migrated onto another server by means of the special "fs_locations"
attribute. See `RFC3530 Section 6: Filesystem Migration and Replication`_ and
`Implementation Guide for Referrals in NFSv4`_.
.. _RFC3530 Section 6\: Filesystem Migration and Replication: http://tools.ietf.org/html/rfc3530#section-6
.. _Implementation Guide for Referrals in NFSv4: http://tools.ietf.org/html/draft-ietf-nfsv4-referrals-00
The fs_locations information can take the form of either an ip address and
a path, or a DNS hostname and a path. The latter requires the NFS client to
do a DNS lookup in order to mount the new volume, and hence the need for an
upcall to allow userland to provide this service.
Assuming that the user has the 'rpc_pipefs' filesystem mounted in the usual
/var/lib/nfs/rpc_pipefs, the upcall consists of the following steps:
(1) The process checks the dns_resolve cache to see if it contains a
valid entry. If so, it returns that entry and exits.
(2) If no valid entry exists, the helper script '/sbin/nfs_cache_getent'
(may be changed using the 'nfs.cache_getent' kernel boot parameter)
is run, with two arguments:
- the cache name, "dns_resolve"
- the hostname to resolve
(3) After looking up the corresponding ip address, the helper script
writes the result into the rpc_pipefs pseudo-file
'/var/lib/nfs/rpc_pipefs/cache/dns_resolve/channel'
in the following (text) format:
"<ip address> <hostname> <ttl>\n"
Where <ip address> is in the usual IPv4 (123.456.78.90) or IPv6
(ffee:ddcc:bbaa:9988:7766:5544:3322:1100, ffee::1100, ...) format.
<hostname> is identical to the second argument of the helper
script, and <ttl> is the 'time to live' of this cache entry (in
units of seconds).
.. note::
If <ip address> is invalid, say the string "0", then a negative
entry is created, which will cause the kernel to treat the hostname
as having no valid DNS translation.
A basic sample /sbin/nfs_cache_getent
=====================================
.. code-block:: sh
#!/bin/bash
#
ttl=600
#
cut=/usr/bin/cut
getent=/usr/bin/getent
rpc_pipefs=/var/lib/nfs/rpc_pipefs
#
die()
{
echo "Usage: $0 cache_name entry_name"
exit 1
}
[ $# -lt 2 ] && die
cachename="$1"
cache_path=${rpc_pipefs}/cache/${cachename}/channel
case "${cachename}" in
dns_resolve)
name="$2"
result="$(${getent} hosts ${name} | ${cut} -f1 -d\ )"
[ -z "${result}" ] && result="0"
;;
*)
die
;;
esac
echo "${result} ${name} ${ttl}" >${cache_path}
Documentation/admin-guide/nfs/nfs-idmapper.rst
+78
View File
@@ -0,0 +1,78 @@
=============
NFS ID Mapper
=============
Id mapper is used by NFS to translate user and group ids into names, and to
translate user and group names into ids. Part of this translation involves
performing an upcall to userspace to request the information. There are two
ways NFS could obtain this information: placing a call to /sbin/request-key
or by placing a call to the rpc.idmap daemon.
NFS will attempt to call /sbin/request-key first. If this succeeds, the
result will be cached using the generic request-key cache. This call should
only fail if /etc/request-key.conf is not configured for the id_resolver key
type, see the "Configuring" section below if you wish to use the request-key
method.
If the call to /sbin/request-key fails (if /etc/request-key.conf is not
configured with the id_resolver key type), then the idmapper will ask the
legacy rpc.idmap daemon for the id mapping. This result will be stored
in a custom NFS idmap cache.
Configuring
===========
The file /etc/request-key.conf will need to be modified so /sbin/request-key can
direct the upcall. The following line should be added:
``#OP TYPE DESCRIPTION CALLOUT INFO PROGRAM ARG1 ARG2 ARG3 ...``
``#====== ======= =============== =============== ===============================``
``create id_resolver * * /usr/sbin/nfs.idmap %k %d 600``
This will direct all id_resolver requests to the program /usr/sbin/nfs.idmap.
The last parameter, 600, defines how many seconds into the future the key will
expire. This parameter is optional for /usr/sbin/nfs.idmap. When the timeout
is not specified, nfs.idmap will default to 600 seconds.
id mapper uses for key descriptions::
uid: Find the UID for the given user
gid: Find the GID for the given group
user: Find the user name for the given UID
group: Find the group name for the given GID
You can handle any of these individually, rather than using the generic upcall
program. If you would like to use your own program for a uid lookup then you
would edit your request-key.conf so it look similar to this:
``#OP TYPE DESCRIPTION CALLOUT INFO PROGRAM ARG1 ARG2 ARG3 ...``
``#====== ======= =============== =============== ===============================``
``create id_resolver uid:* * /some/other/program %k %d 600``
``create id_resolver * * /usr/sbin/nfs.idmap %k %d 600``
Notice that the new line was added above the line for the generic program.
request-key will find the first matching line and corresponding program. In
this case, /some/other/program will handle all uid lookups and
/usr/sbin/nfs.idmap will handle gid, user, and group lookups.
See Documentation/security/keys/request-key.rst for more information
about the request-key function.
nfs.idmap
=========
nfs.idmap is designed to be called by request-key, and should not be run "by
hand". This program takes two arguments, a serialized key and a key
description. The serialized key is first converted into a key_serial_t, and
then passed as an argument to keyctl_instantiate (both are part of keyutils.h).
The actual lookups are performed by functions found in nfsidmap.h. nfs.idmap
determines the correct function to call by looking at the first part of the
description string. For example, a uid lookup description will appear as
"uid:user@domain".
nfs.idmap will return 0 if the key was instantiated, and non-zero otherwise.
Documentation/admin-guide/nfs/nfs-rdma.rst
+292
View File
@@ -0,0 +1,292 @@
===================
Setting up NFS/RDMA
===================
:Author:
NetApp and Open Grid Computing (May 29, 2008)
.. warning::
This document is probably obsolete.
Overview
========
This document describes how to install and setup the Linux NFS/RDMA client
and server software.
The NFS/RDMA client was first included in Linux 2.6.24. The NFS/RDMA server
was first included in the following release, Linux 2.6.25.
In our testing, we have obtained excellent performance results (full 10Gbit
wire bandwidth at minimal client CPU) under many workloads. The code passes
the full Connectathon test suite and operates over both Infiniband and iWARP
RDMA adapters.
Getting Help
============
If you get stuck, you can ask questions on the
nfs-rdma-devel@lists.sourceforge.net mailing list.
Installation
============
These instructions are a step by step guide to building a machine for
use with NFS/RDMA.
- Install an RDMA device
Any device supported by the drivers in drivers/infiniband/hw is acceptable.
Testing has been performed using several Mellanox-based IB cards, the
Ammasso AMS1100 iWARP adapter, and the Chelsio cxgb3 iWARP adapter.
- Install a Linux distribution and tools
The first kernel release to contain both the NFS/RDMA client and server was
Linux 2.6.25 Therefore, a distribution compatible with this and subsequent
Linux kernel release should be installed.
The procedures described in this document have been tested with
distributions from Red Hat's Fedora Project (http://fedora.redhat.com/).
- Install nfs-utils-1.1.2 or greater on the client
An NFS/RDMA mount point can be obtained by using the mount.nfs command in
nfs-utils-1.1.2 or greater (nfs-utils-1.1.1 was the first nfs-utils
version with support for NFS/RDMA mounts, but for various reasons we
recommend using nfs-utils-1.1.2 or greater). To see which version of
mount.nfs you are using, type:
.. code-block:: sh
$ /sbin/mount.nfs -V
If the version is less than 1.1.2 or the command does not exist,
you should install the latest version of nfs-utils.
Download the latest package from: http://www.kernel.org/pub/linux/utils/nfs
Uncompress the package and follow the installation instructions.
If you will not need the idmapper and gssd executables (you do not need
these to create an NFS/RDMA enabled mount command), the installation
process can be simplified by disabling these features when running
configure:
.. code-block:: sh
$ ./configure --disable-gss --disable-nfsv4
To build nfs-utils you will need the tcp_wrappers package installed. For
more information on this see the package's README and INSTALL files.
After building the nfs-utils package, there will be a mount.nfs binary in
the utils/mount directory. This binary can be used to initiate NFS v2, v3,
or v4 mounts. To initiate a v4 mount, the binary must be called
mount.nfs4. The standard technique is to create a symlink called
mount.nfs4 to mount.nfs.
This mount.nfs binary should be installed at /sbin/mount.nfs as follows:
.. code-block:: sh
$ sudo cp utils/mount/mount.nfs /sbin/mount.nfs
In this location, mount.nfs will be invoked automatically for NFS mounts
by the system mount command.
.. note::
mount.nfs and therefore nfs-utils-1.1.2 or greater is only needed
on the NFS client machine. You do not need this specific version of
nfs-utils on the server. Furthermore, only the mount.nfs command from
nfs-utils-1.1.2 is needed on the client.
- Install a Linux kernel with NFS/RDMA
The NFS/RDMA client and server are both included in the mainline Linux
kernel version 2.6.25 and later. This and other versions of the Linux
kernel can be found at: https://www.kernel.org/pub/linux/kernel/
Download the sources and place them in an appropriate location.
- Configure the RDMA stack
Make sure your kernel configuration has RDMA support enabled. Under
Device Drivers -> InfiniBand support, update the kernel configuration
to enable InfiniBand support [NOTE: the option name is misleading. Enabling
InfiniBand support is required for all RDMA devices (IB, iWARP, etc.)].
Enable the appropriate IB HCA support (mlx4, mthca, ehca, ipath, etc.) or
iWARP adapter support (amso, cxgb3, etc.).
If you are using InfiniBand, be sure to enable IP-over-InfiniBand support.
- Configure the NFS client and server
Your kernel configuration must also have NFS file system support and/or
NFS server support enabled. These and other NFS related configuration
options can be found under File Systems -> Network File Systems.
- Build, install, reboot
The NFS/RDMA code will be enabled automatically if NFS and RDMA
are turned on. The NFS/RDMA client and server are configured via the hidden
SUNRPC_XPRT_RDMA config option that depends on SUNRPC and INFINIBAND. The
value of SUNRPC_XPRT_RDMA will be:
#. N if either SUNRPC or INFINIBAND are N, in this case the NFS/RDMA client
and server will not be built
#. M if both SUNRPC and INFINIBAND are on (M or Y) and at least one is M,
in this case the NFS/RDMA client and server will be built as modules
#. Y if both SUNRPC and INFINIBAND are Y, in this case the NFS/RDMA client
and server will be built into the kernel
Therefore, if you have followed the steps above and turned no NFS and RDMA,
the NFS/RDMA client and server will be built.
Build a new kernel, install it, boot it.
Check RDMA and NFS Setup
========================
Before configuring the NFS/RDMA software, it is a good idea to test
your new kernel to ensure that the kernel is working correctly.
In particular, it is a good idea to verify that the RDMA stack
is functioning as expected and standard NFS over TCP/IP and/or UDP/IP
is working properly.
- Check RDMA Setup
If you built the RDMA components as modules, load them at
this time. For example, if you are using a Mellanox Tavor/Sinai/Arbel
card:
.. code-block:: sh
$ modprobe ib_mthca
$ modprobe ib_ipoib
If you are using InfiniBand, make sure there is a Subnet Manager (SM)
running on the network. If your IB switch has an embedded SM, you can
use it. Otherwise, you will need to run an SM, such as OpenSM, on one
of your end nodes.
If an SM is running on your network, you should see the following:
.. code-block:: sh
$ cat /sys/class/infiniband/driverX/ports/1/state
4: ACTIVE
where driverX is mthca0, ipath5, ehca3, etc.
To further test the InfiniBand software stack, use IPoIB (this
assumes you have two IB hosts named host1 and host2):
.. code-block:: sh
host1$ ip link set dev ib0 up
host1$ ip address add dev ib0 a.b.c.x
host2$ ip link set dev ib0 up
host2$ ip address add dev ib0 a.b.c.y
host1$ ping a.b.c.y
host2$ ping a.b.c.x
For other device types, follow the appropriate procedures.
- Check NFS Setup
For the NFS components enabled above (client and/or server),
test their functionality over standard Ethernet using TCP/IP or UDP/IP.
NFS/RDMA Setup
==============
We recommend that you use two machines, one to act as the client and
one to act as the server.
One time configuration:
-----------------------
- On the server system, configure the /etc/exports file and start the NFS/RDMA server.
Exports entries with the following formats have been tested::
/vol0 192.168.0.47(fsid=0,rw,async,insecure,no_root_squash)
/vol0 192.168.0.0/255.255.255.0(fsid=0,rw,async,insecure,no_root_squash)
The IP address(es) is(are) the client's IPoIB address for an InfiniBand
HCA or the client's iWARP address(es) for an RNIC.
.. note::
The "insecure" option must be used because the NFS/RDMA client does
not use a reserved port.
Each time a machine boots:
--------------------------
- Load and configure the RDMA drivers
For InfiniBand using a Mellanox adapter:
.. code-block:: sh
$ modprobe ib_mthca
$ modprobe ib_ipoib
$ ip li set dev ib0 up
$ ip addr add dev ib0 a.b.c.d
.. note::
Please use unique addresses for the client and server!
- Start the NFS server
If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
kernel config), load the RDMA transport module:
.. code-block:: sh
$ modprobe svcrdma
Regardless of how the server was built (module or built-in), start the
server:
.. code-block:: sh
$ /etc/init.d/nfs start
or
.. code-block:: sh
$ service nfs start
Instruct the server to listen on the RDMA transport:
.. code-block:: sh
$ echo rdma 20049 > /proc/fs/nfsd/portlist
- On the client system
If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
kernel config), load the RDMA client module:
.. code-block:: sh
$ modprobe xprtrdma.ko
Regardless of how the client was built (module or built-in), use this
command to mount the NFS/RDMA server:
.. code-block:: sh
$ mount -o rdma,port=20049 <IPoIB-server-name-or-address>:/<export> /mnt
To verify that the mount is using RDMA, run "cat /proc/mounts" and check
the "proto" field for the given mount.
Congratulations! You're using NFS/RDMA!
Documentation/admin-guide/nfs/nfsd-admin-interfaces.rst
+40
View File
@@ -0,0 +1,40 @@
==================================
Administrative interfaces for nfsd
==================================
Note that normally these interfaces are used only by the utilities in
nfs-utils.
nfsd is controlled mainly by pseudofiles under the "nfsd" filesystem,
which is normally mounted at /proc/fs/nfsd/.
The server is always started by the first write of a nonzero value to
nfsd/threads.
Before doing that, NFSD can be told which sockets to listen on by
writing to nfsd/portlist; that write may be:
- an ascii-encoded file descriptor, which should refer to a
bound (and listening, for tcp) socket, or
- "transportname port", where transportname is currently either
"udp", "tcp", or "rdma".
If nfsd is started without doing any of these, then it will create one
udp and one tcp listener at port 2049 (see nfsd_init_socks).
On startup, nfsd and lockd grace periods start. nfsd is shut down by a write of
0 to nfsd/threads. All locks and state are thrown away at that point.
Between startup and shutdown, the number of threads may be adjusted up
or down by additional writes to nfsd/threads or by writes to
nfsd/pool_threads.
For more detail about files under nfsd/ and what they control, see
fs/nfsd/nfsctl.c; most of them have detailed comments.
Implementation notes
====================
Note that the rpc server requires the caller to serialize addition and
removal of listening sockets, and startup and shutdown of the server.
For nfsd this is done using nfsd_mutex.
Documentation/admin-guide/nfs/nfsroot.rst
+364
View File
@@ -0,0 +1,364 @@
===============================================
Mounting the root filesystem via NFS (nfsroot)
===============================================
:Authors:
Written 1996 by Gero Kuhlmann <gero@gkminix.han.de>
Updated 1997 by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
Updated 2006 by Nico Schottelius <nico-kernel-nfsroot@schottelius.org>
Updated 2006 by Horms <horms@verge.net.au>
Updated 2018 by Chris Novakovic <chris@chrisn.me.uk>
In order to use a diskless system, such as an X-terminal or printer server for
example, it is necessary for the root filesystem to be present on a non-disk
device. This may be an initramfs (see
Documentation/filesystems/ramfs-rootfs-initramfs.txt), a ramdisk (see
Documentation/admin-guide/initrd.rst) or a filesystem mounted via NFS. The
following text describes on how to use NFS for the root filesystem. For the rest
of this text 'client' means the diskless system, and 'server' means the NFS
server.
Enabling nfsroot capabilities
=============================
In order to use nfsroot, NFS client support needs to be selected as
built-in during configuration. Once this has been selected, the nfsroot
option will become available, which should also be selected.
In the networking options, kernel level autoconfiguration can be selected,
along with the types of autoconfiguration to support. Selecting all of
DHCP, BOOTP and RARP is safe.
Kernel command line
===================
When the kernel has been loaded by a boot loader (see below) it needs to be
told what root fs device to use. And in the case of nfsroot, where to find
both the server and the name of the directory on the server to mount as root.
This can be established using the following kernel command line parameters:
root=/dev/nfs
This is necessary to enable the pseudo-NFS-device. Note that it's not a
real device but just a synonym to tell the kernel to use NFS instead of
a real device.
nfsroot=[<server-ip>:]<root-dir>[,<nfs-options>]
If the `nfsroot' parameter is NOT given on the command line,
the default ``"/tftpboot/%s"`` will be used.
<server-ip> Specifies the IP address of the NFS server.
The default address is determined by the ip parameter
(see below). This parameter allows the use of different
servers for IP autoconfiguration and NFS.
<root-dir> Name of the directory on the server to mount as root.
If there is a "%s" token in the string, it will be
replaced by the ASCII-representation of the client's
IP address.
<nfs-options> Standard NFS options. All options are separated by commas.
The following defaults are used::
port = as given by server portmap daemon
rsize = 4096
wsize = 4096
timeo = 7
retrans = 3
acregmin = 3
acregmax = 60
acdirmin = 30
acdirmax = 60
flags = hard, nointr, noposix, cto, ac
ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>:<dns0-ip>:<dns1-ip>:<ntp0-ip>
This parameter tells the kernel how to configure IP addresses of devices
and also how to set up the IP routing table. It was originally called
nfsaddrs, but now the boot-time IP configuration works independently of
NFS, so it was renamed to ip and the old name remained as an alias for
compatibility reasons.
If this parameter is missing from the kernel command line, all fields are
assumed to be empty, and the defaults mentioned below apply. In general
this means that the kernel tries to configure everything using
autoconfiguration.
The <autoconf> parameter can appear alone as the value to the ip
parameter (without all the ':' characters before). If the value is
"ip=off" or "ip=none", no autoconfiguration will take place, otherwise
autoconfiguration will take place. The most common way to use this
is "ip=dhcp".
<client-ip> IP address of the client.
Default: Determined using autoconfiguration.
<server-ip> IP address of the NFS server.
If RARP is used to determine
the client address and this parameter is NOT empty only
replies from the specified server are accepted.
Only required for NFS root. That is autoconfiguration
will not be triggered if it is missing and NFS root is not
in operation.
Value is exported to /proc/net/pnp with the prefix "bootserver "
(see below).
Default: Determined using autoconfiguration.
The address of the autoconfiguration server is used.
<gw-ip> IP address of a gateway if the server is on a different subnet.
Default: Determined using autoconfiguration.
<netmask> Netmask for local network interface.
If unspecified the netmask is derived from the client IP address
assuming classful addressing.
Default: Determined using autoconfiguration.
<hostname> Name of the client.
If a '.' character is present, anything
before the first '.' is used as the client's hostname, and anything
after it is used as its NIS domain name. May be supplied by
autoconfiguration, but its absence will not trigger autoconfiguration.
If specified and DHCP is used, the user-provided hostname (and NIS
domain name, if present) will be carried in the DHCP request; this
may cause a DNS record to be created or updated for the client.
Default: Client IP address is used in ASCII notation.
<device> Name of network device to use.
Default: If the host only has one device, it is used.
Otherwise the device is determined using
autoconfiguration. This is done by sending
autoconfiguration requests out of all devices,
and using the device that received the first reply.
<autoconf> Method to use for autoconfiguration.
In the case of options
which specify multiple autoconfiguration protocols,
requests are sent using all protocols, and the first one
to reply is used.
Only autoconfiguration protocols that have been compiled
into the kernel will be used, regardless of the value of
this option::
off or none: don't use autoconfiguration
(do static IP assignment instead)
on or any: use any protocol available in the kernel
(default)
dhcp: use DHCP
bootp: use BOOTP
rarp: use RARP
both: use both BOOTP and RARP but not DHCP
(old option kept for backwards compatibility)
if dhcp is used, the client identifier can be used by following
format "ip=dhcp,client-id-type,client-id-value"
Default: any
<dns0-ip> IP address of primary nameserver.
Value is exported to /proc/net/pnp with the prefix "nameserver "
(see below).
Default: None if not using autoconfiguration; determined
automatically if using autoconfiguration.
<dns1-ip> IP address of secondary nameserver.
See <dns0-ip>.
<ntp0-ip> IP address of a Network Time Protocol (NTP) server.
Value is exported to /proc/net/ipconfig/ntp_servers, but is
otherwise unused (see below).
Default: None if not using autoconfiguration; determined
automatically if using autoconfiguration.
After configuration (whether manual or automatic) is complete, two files
are created in the following format; lines are omitted if their respective
value is empty following configuration:
- /proc/net/pnp:
#PROTO: <DHCP|BOOTP|RARP|MANUAL> (depending on configuration method)
domain <dns-domain> (if autoconfigured, the DNS domain)
nameserver <dns0-ip> (primary name server IP)
nameserver <dns1-ip> (secondary name server IP)
nameserver <dns2-ip> (tertiary name server IP)
bootserver <server-ip> (NFS server IP)
- /proc/net/ipconfig/ntp_servers:
<ntp0-ip> (NTP server IP)
<ntp1-ip> (NTP server IP)
<ntp2-ip> (NTP server IP)
<dns-domain> and <dns2-ip> (in /proc/net/pnp) and <ntp1-ip> and <ntp2-ip>
(in /proc/net/ipconfig/ntp_servers) are requested during autoconfiguration;
they cannot be specified as part of the "ip=" kernel command line parameter.
Because the "domain" and "nameserver" options are recognised by DNS
resolvers, /etc/resolv.conf is often linked to /proc/net/pnp on systems
that use an NFS root filesystem.
Note that the kernel will not synchronise the system time with any NTP
servers it discovers; this is the responsibility of a user space process
(e.g. an initrd/initramfs script that passes the IP addresses listed in
/proc/net/ipconfig/ntp_servers to an NTP client before mounting the real
root filesystem if it is on NFS).
nfsrootdebug
This parameter enables debugging messages to appear in the kernel
log at boot time so that administrators can verify that the correct
NFS mount options, server address, and root path are passed to the
NFS client.
rdinit=<executable file>
To specify which file contains the program that starts system
initialization, administrators can use this command line parameter.
The default value of this parameter is "/init". If the specified
file exists and the kernel can execute it, root filesystem related
kernel command line parameters, including 'nfsroot=', are ignored.
A description of the process of mounting the root file system can be
found in Documentation/driver-api/early-userspace/early_userspace_support.rst
Boot Loader
===========
To get the kernel into memory different approaches can be used.
They depend on various facilities being available:
- Booting from a floppy using syslinux
When building kernels, an easy way to create a boot floppy that uses
syslinux is to use the zdisk or bzdisk make targets which use zimage
and bzimage images respectively. Both targets accept the
FDARGS parameter which can be used to set the kernel command line.
e.g::
make bzdisk FDARGS="root=/dev/nfs"
Note that the user running this command will need to have
access to the floppy drive device, /dev/fd0
For more information on syslinux, including how to create bootdisks
for prebuilt kernels, see http://syslinux.zytor.com/
.. note::
Previously it was possible to write a kernel directly to
a floppy using dd, configure the boot device using rdev, and
boot using the resulting floppy. Linux no longer supports this
method of booting.
- Booting from a cdrom using isolinux
When building kernels, an easy way to create a bootable cdrom that
uses isolinux is to use the isoimage target which uses a bzimage
image. Like zdisk and bzdisk, this target accepts the FDARGS
parameter which can be used to set the kernel command line.
e.g::
make isoimage FDARGS="root=/dev/nfs"
The resulting iso image will be arch/<ARCH>/boot/image.iso
This can be written to a cdrom using a variety of tools including
cdrecord.
e.g::
cdrecord dev=ATAPI:1,0,0 arch/x86/boot/image.iso
For more information on isolinux, including how to create bootdisks
for prebuilt kernels, see http://syslinux.zytor.com/
- Using LILO
When using LILO all the necessary command line parameters may be
specified using the 'append=' directive in the LILO configuration
file.
However, to use the 'root=' directive you also need to create
a dummy root device, which may be removed after LILO is run.
e.g::
mknod /dev/boot255 c 0 255
For information on configuring LILO, please refer to its documentation.
- Using GRUB
When using GRUB, kernel parameter are simply appended after the kernel
specification: kernel <kernel> <parameters>
- Using loadlin
loadlin may be used to boot Linux from a DOS command prompt without
requiring a local hard disk to mount as root. This has not been
thoroughly tested by the authors of this document, but in general
it should be possible configure the kernel command line similarly
to the configuration of LILO.
Please refer to the loadlin documentation for further information.
- Using a boot ROM
This is probably the most elegant way of booting a diskless client.
With a boot ROM the kernel is loaded using the TFTP protocol. The
authors of this document are not aware of any no commercial boot
ROMs that support booting Linux over the network. However, there
are two free implementations of a boot ROM, netboot-nfs and
etherboot, both of which are available on sunsite.unc.edu, and both
of which contain everything you need to boot a diskless Linux client.
- Using pxelinux
Pxelinux may be used to boot linux using the PXE boot loader
which is present on many modern network cards.
When using pxelinux, the kernel image is specified using
"kernel <relative-path-below /tftpboot>". The nfsroot parameters
are passed to the kernel by adding them to the "append" line.
It is common to use serial console in conjunction with pxeliunx,
see Documentation/admin-guide/serial-console.rst for more information.
For more information on isolinux, including how to create bootdisks
for prebuilt kernels, see http://syslinux.zytor.com/
Credits
=======
The nfsroot code in the kernel and the RARP support have been written
by Gero Kuhlmann <gero@gkminix.han.de>.
The rest of the IP layer autoconfiguration code has been written
by Martin Mares <mj@atrey.karlin.mff.cuni.cz>.
In order to write the initial version of nfsroot I would like to thank
Jens-Uwe Mager <jum@anubis.han.de> for his help.
Documentation/admin-guide/nfs/pnfs-block-server.rst
+42
View File
@@ -0,0 +1,42 @@
===================================
pNFS block layout server user guide
===================================
The Linux NFS server now supports the pNFS block layout extension. In this
case the NFS server acts as Metadata Server (MDS) for pNFS, which in addition
to handling all the metadata access to the NFS export also hands out layouts
to the clients to directly access the underlying block devices that are
shared with the client.
To use pNFS block layouts with with the Linux NFS server the exported file
system needs to support the pNFS block layouts (currently just XFS), and the
file system must sit on shared storage (typically iSCSI) that is accessible
to the clients in addition to the MDS. As of now the file system needs to
sit directly on the exported volume, striping or concatenation of
volumes on the MDS and clients is not supported yet.
On the server, pNFS block volume support is automatically if the file system
support it. On the client make sure the kernel has the CONFIG_PNFS_BLOCK
option enabled, the blkmapd daemon from nfs-utils is running, and the
file system is mounted using the NFSv4.1 protocol version (mount -o vers=4.1).
If the nfsd server needs to fence a non-responding client it calls
/sbin/nfsd-recall-failed with the first argument set to the IP address of
the client, and the second argument set to the device node without the /dev
prefix for the file system to be fenced. Below is an example file that shows
how to translate the device into a serial number from SCSI EVPD 0x80::
cat > /sbin/nfsd-recall-failed << EOF
.. code-block:: sh
#!/bin/sh
CLIENT="$1"
DEV="/dev/$2"
EVPD=`sg_inq --page=0x80 ${DEV} | \
grep "Unit serial number:" | \
awk -F ': ' '{print $2}'`
echo "fencing client ${CLIENT} serial ${EVPD}" >> /var/log/pnfsd-fence.log
EOF
Documentation/admin-guide/nfs/pnfs-scsi-server.rst
+24
View File
@@ -0,0 +1,24 @@
==================================
pNFS SCSI layout server user guide
==================================
This document describes support for pNFS SCSI layouts in the Linux NFS server.
With pNFS SCSI layouts, the NFS server acts as Metadata Server (MDS) for pNFS,
which in addition to handling all the metadata access to the NFS export,
also hands out layouts to the clients so that they can directly access the
underlying SCSI LUNs that are shared with the client.
To use pNFS SCSI layouts with with the Linux NFS server, the exported file
system needs to support the pNFS SCSI layouts (currently just XFS), and the
file system must sit on a SCSI LUN that is accessible to the clients in
addition to the MDS. As of now the file system needs to sit directly on the
exported LUN, striping or concatenation of LUNs on the MDS and clients
is not supported yet.
On a server built with CONFIG_NFSD_SCSI, the pNFS SCSI volume support is
automatically enabled if the file system is exported using the "pnfs"
option and the underlying SCSI device support persistent reservations.
On the client make sure the kernel has the CONFIG_PNFS_BLOCK option
enabled, and the file system is mounted using the NFSv4.1 protocol
version (mount -o vers=4.1).
Documentation/admin-guide/perf/imx-ddr.rst
+2 -1
View File
@@ -43,7 +43,8 @@ value 1 for supported.
AXI_ID and AXI_MASKING are mapped on DPCR1 register in performance counter.
When non-masked bits are matching corresponding AXI_ID bits then counter is
incremented. Perf counter is incremented if
incremented. Perf counter is incremented if::
AxID && AXI_MASKING == AXI_ID && AXI_MASKING
This filter doesn't support filter different AXI ID for axid-read and axid-write
Documentation/admin-guide/pm/cpufreq_drivers.rst
+274
View File
@@ -0,0 +1,274 @@
.. SPDX-License-Identifier: GPL-2.0
=======================================================
Legacy Documentation of CPU Performance Scaling Drivers
=======================================================
Included below are historic documents describing assorted
:doc:`CPU performance scaling <cpufreq>` drivers. They are reproduced verbatim,
with the original white space formatting and indentation preserved, except for
the added leading space character in every line of text.
AMD PowerNow! Drivers
=====================
::
PowerNow! and Cool'n'Quiet are AMD names for frequency
management capabilities in AMD processors. As the hardware
implementation changes in new generations of the processors,
there is a different cpu-freq driver for each generation.
Note that the driver's will not load on the "wrong" hardware,
so it is safe to try each driver in turn when in doubt as to
which is the correct driver.
Note that the functionality to change frequency (and voltage)
is not available in all processors. The drivers will refuse
to load on processors without this capability. The capability
is detected with the cpuid instruction.
The drivers use BIOS supplied tables to obtain frequency and
voltage information appropriate for a particular platform.
Frequency transitions will be unavailable if the BIOS does
not supply these tables.
6th Generation: powernow-k6
7th Generation: powernow-k7: Athlon, Duron, Geode.
8th Generation: powernow-k8: Athlon, Athlon 64, Opteron, Sempron.
Documentation on this functionality in 8th generation processors
is available in the "BIOS and Kernel Developer's Guide", publication
26094, in chapter 9, available for download from www.amd.com.
BIOS supplied data, for powernow-k7 and for powernow-k8, may be
from either the PSB table or from ACPI objects. The ACPI support
is only available if the kernel config sets CONFIG_ACPI_PROCESSOR.
The powernow-k8 driver will attempt to use ACPI if so configured,
and fall back to PST if that fails.
The powernow-k7 driver will try to use the PSB support first, and
fall back to ACPI if the PSB support fails. A module parameter,
acpi_force, is provided to force ACPI support to be used instead
of PSB support.
``cpufreq-nforce2``
===================
::
The cpufreq-nforce2 driver changes the FSB on nVidia nForce2 platforms.
This works better than on other platforms, because the FSB of the CPU
can be controlled independently from the PCI/AGP clock.
The module has two options:
fid: multiplier * 10 (for example 8.5 = 85)
min_fsb: minimum FSB
If not set, fid is calculated from the current CPU speed and the FSB.
min_fsb defaults to FSB at boot time - 50 MHz.
IMPORTANT: The available range is limited downwards!
Also the minimum available FSB can differ, for systems
booting with 200 MHz, 150 should always work.
``pcc-cpufreq``
===============
::
/*
* pcc-cpufreq.txt - PCC interface documentation
*
* Copyright (C) 2009 Red Hat, Matthew Garrett <mjg@redhat.com>
* Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
* Nagananda Chumbalkar <nagananda.chumbalkar@hp.com>
*/
Processor Clocking Control Driver
---------------------------------
Contents:
---------
1. Introduction
1.1 PCC interface
1.1.1 Get Average Frequency
1.1.2 Set Desired Frequency
1.2 Platforms affected
2. Driver and /sys details
2.1 scaling_available_frequencies
2.2 cpuinfo_transition_latency
2.3 cpuinfo_cur_freq
2.4 related_cpus
3. Caveats
1. Introduction:
----------------
Processor Clocking Control (PCC) is an interface between the platform
firmware and OSPM. It is a mechanism for coordinating processor
performance (ie: frequency) between the platform firmware and the OS.
The PCC driver (pcc-cpufreq) allows OSPM to take advantage of the PCC
interface.
OS utilizes the PCC interface to inform platform firmware what frequency the
OS wants for a logical processor. The platform firmware attempts to achieve
the requested frequency. If the request for the target frequency could not be
satisfied by platform firmware, then it usually means that power budget
conditions are in place, and "power capping" is taking place.
1.1 PCC interface:
------------------
The complete PCC specification is available here:
https://acpica.org/sites/acpica/files/Processor-Clocking-Control-v1p0.pdf
PCC relies on a shared memory region that provides a channel for communication
between the OS and platform firmware. PCC also implements a "doorbell" that
is used by the OS to inform the platform firmware that a command has been
sent.
The ACPI PCCH() method is used to discover the location of the PCC shared
memory region. The shared memory region header contains the "command" and
"status" interface. PCCH() also contains details on how to access the platform
doorbell.
The following commands are supported by the PCC interface:
* Get Average Frequency
* Set Desired Frequency
The ACPI PCCP() method is implemented for each logical processor and is
used to discover the offsets for the input and output buffers in the shared
memory region.
When PCC mode is enabled, the platform will not expose processor performance
or throttle states (_PSS, _TSS and related ACPI objects) to OSPM. Therefore,
the native P-state driver (such as acpi-cpufreq for Intel, powernow-k8 for
AMD) will not load.
However, OSPM remains in control of policy. The governor (eg: "ondemand")
computes the required performance for each processor based on server workload.
The PCC driver fills in the command interface, and the input buffer and
communicates the request to the platform firmware. The platform firmware is
responsible for delivering the requested performance.
Each PCC command is "global" in scope and can affect all the logical CPUs in
the system. Therefore, PCC is capable of performing "group" updates. With PCC
the OS is capable of getting/setting the frequency of all the logical CPUs in
the system with a single call to the BIOS.
1.1.1 Get Average Frequency:
----------------------------
This command is used by the OSPM to query the running frequency of the
processor since the last time this command was completed. The output buffer
indicates the average unhalted frequency of the logical processor expressed as
a percentage of the nominal (ie: maximum) CPU frequency. The output buffer
also signifies if the CPU frequency is limited by a power budget condition.
1.1.2 Set Desired Frequency:
----------------------------
This command is used by the OSPM to communicate to the platform firmware the
desired frequency for a logical processor. The output buffer is currently
ignored by OSPM. The next invocation of "Get Average Frequency" will inform
OSPM if the desired frequency was achieved or not.
1.2 Platforms affected:
-----------------------
The PCC driver will load on any system where the platform firmware:
* supports the PCC interface, and the associated PCCH() and PCCP() methods
* assumes responsibility for managing the hardware clocking controls in order
to deliver the requested processor performance
Currently, certain HP ProLiant platforms implement the PCC interface. On those
platforms PCC is the "default" choice.
However, it is possible to disable this interface via a BIOS setting. In
such an instance, as is also the case on platforms where the PCC interface
is not implemented, the PCC driver will fail to load silently.
2. Driver and /sys details:
---------------------------
When the driver loads, it merely prints the lowest and the highest CPU
frequencies supported by the platform firmware.
The PCC driver loads with a message such as:
pcc-cpufreq: (v1.00.00) driver loaded with frequency limits: 1600 MHz, 2933
MHz
This means that the OPSM can request the CPU to run at any frequency in
between the limits (1600 MHz, and 2933 MHz) specified in the message.
Internally, there is no need for the driver to convert the "target" frequency
to a corresponding P-state.
The VERSION number for the driver will be of the format v.xy.ab.
eg: 1.00.02
----- --
| |
| -- this will increase with bug fixes/enhancements to the driver
|-- this is the version of the PCC specification the driver adheres to
The following is a brief discussion on some of the fields exported via the
/sys filesystem and how their values are affected by the PCC driver:
2.1 scaling_available_frequencies:
----------------------------------
scaling_available_frequencies is not created in /sys. No intermediate
frequencies need to be listed because the BIOS will try to achieve any
frequency, within limits, requested by the governor. A frequency does not have
to be strictly associated with a P-state.
2.2 cpuinfo_transition_latency:
-------------------------------
The cpuinfo_transition_latency field is 0. The PCC specification does
not include a field to expose this value currently.
2.3 cpuinfo_cur_freq:
---------------------
A) Often cpuinfo_cur_freq will show a value different than what is declared
in the scaling_available_frequencies or scaling_cur_freq, or scaling_max_freq.
This is due to "turbo boost" available on recent Intel processors. If certain
conditions are met the BIOS can achieve a slightly higher speed than requested
by OSPM. An example:
scaling_cur_freq : 2933000
cpuinfo_cur_freq : 3196000
B) There is a round-off error associated with the cpuinfo_cur_freq value.
Since the driver obtains the current frequency as a "percentage" (%) of the
nominal frequency from the BIOS, sometimes, the values displayed by
scaling_cur_freq and cpuinfo_cur_freq may not match. An example:
scaling_cur_freq : 1600000
cpuinfo_cur_freq : 1583000
In this example, the nominal frequency is 2933 MHz. The driver obtains the
current frequency, cpuinfo_cur_freq, as 54% of the nominal frequency:
54% of 2933 MHz = 1583 MHz
Nominal frequency is the maximum frequency of the processor, and it usually
corresponds to the frequency of the P0 P-state.
2.4 related_cpus:
-----------------
The related_cpus field is identical to affected_cpus.
affected_cpus : 4
related_cpus : 4
Currently, the PCC driver does not evaluate _PSD. The platforms that support
PCC do not implement SW_ALL. So OSPM doesn't need to perform any coordination
to ensure that the same frequency is requested of all dependent CPUs.
3. Caveats:
-----------
The "cpufreq_stats" module in its present form cannot be loaded and
expected to work with the PCC driver. Since the "cpufreq_stats" module
provides information wrt each P-state, it is not applicable to the PCC driver.
Documentation/admin-guide/pm/cpuidle.rst
+40 -41
View File
@@ -583,20 +583,17 @@ Power Management Quality of Service for CPUs
The power management quality of service (PM QoS) framework in the Linux kernel
allows kernel code and user space processes to set constraints on various
energy-efficiency features of the kernel to prevent performance from dropping
below a required level. The PM QoS constraints can be set globally, in
predefined categories referred to as PM QoS classes, or against individual
devices.
below a required level.
CPU idle time management can be affected by PM QoS in two ways, through the
global constraint in the ``PM_QOS_CPU_DMA_LATENCY`` class and through the
resume latency constraints for individual CPUs. Kernel code (e.g. device
drivers) can set both of them with the help of special internal interfaces
provided by the PM QoS framework. User space can modify the former by opening
the :file:`cpu_dma_latency` special device file under :file:`/dev/` and writing
a binary value (interpreted as a signed 32-bit integer) to it. In turn, the
resume latency constraint for a CPU can be modified by user space by writing a
string (representing a signed 32-bit integer) to the
:file:`power/pm_qos_resume_latency_us` file under
global CPU latency limit and through the resume latency constraints for
individual CPUs. Kernel code (e.g. device drivers) can set both of them with
the help of special internal interfaces provided by the PM QoS framework. User
space can modify the former by opening the :file:`cpu_dma_latency` special
device file under :file:`/dev/` and writing a binary value (interpreted as a
signed 32-bit integer) to it. In turn, the resume latency constraint for a CPU
can be modified from user space by writing a string (representing a signed
32-bit integer) to the :file:`power/pm_qos_resume_latency_us` file under
:file:`/sys/devices/system/cpu/cpu<N>/` in ``sysfs``, where the CPU number
``<N>`` is allocated at the system initialization time. Negative values
will be rejected in both cases and, also in both cases, the written integer
@@ -605,52 +602,54 @@ number will be interpreted as a requested PM QoS constraint in microseconds.
The requested value is not automatically applied as a new constraint, however,
as it may be less restrictive (greater in this particular case) than another
constraint previously requested by someone else. For this reason, the PM QoS
framework maintains a list of requests that have been made so far in each
global class and for each device, aggregates them and applies the effective
(minimum in this particular case) value as the new constraint.
framework maintains a list of requests that have been made so far for the
global CPU latency limit and for each individual CPU, aggregates them and
applies the effective (minimum in this particular case) value as the new
constraint.
In fact, opening the :file:`cpu_dma_latency` special device file causes a new
PM QoS request to be created and added to the priority list of requests in the
``PM_QOS_CPU_DMA_LATENCY`` class and the file descriptor coming from the
"open" operation represents that request. If that file descriptor is then
used for writing, the number written to it will be associated with the PM QoS
request represented by it as a new requested constraint value. Next, the
priority list mechanism will be used to determine the new effective value of
the entire list of requests and that effective value will be set as a new
constraint. Thus setting a new requested constraint value will only change the
real constraint if the effective "list" value is affected by it. In particular,
for the ``PM_QOS_CPU_DMA_LATENCY`` class it only affects the real constraint if
it is the minimum of the requested constraints in the list. The process holding
a file descriptor obtained by opening the :file:`cpu_dma_latency` special device
file controls the PM QoS request associated with that file descriptor, but it
controls this particular PM QoS request only.
PM QoS request to be created and added to a global priority list of CPU latency
limit requests and the file descriptor coming from the "open" operation
represents that request. If that file descriptor is then used for writing, the
number written to it will be associated with the PM QoS request represented by
it as a new requested limit value. Next, the priority list mechanism will be
used to determine the new effective value of the entire list of requests and
that effective value will be set as a new CPU latency limit. Thus requesting a
new limit value will only change the real limit if the effective "list" value is
affected by it, which is the case if it is the minimum of the requested values
in the list.
The process holding a file descriptor obtained by opening the
:file:`cpu_dma_latency` special device file controls the PM QoS request
associated with that file descriptor, but it controls this particular PM QoS
request only.
Closing the :file:`cpu_dma_latency` special device file or, more precisely, the
file descriptor obtained while opening it, causes the PM QoS request associated
with that file descriptor to be removed from the ``PM_QOS_CPU_DMA_LATENCY``
class priority list and destroyed. If that happens, the priority list mechanism
will be used, again, to determine the new effective value for the whole list
and that value will become the new real constraint.
with that file descriptor to be removed from the global priority list of CPU
latency limit requests and destroyed. If that happens, the priority list
mechanism will be used again, to determine the new effective value for the whole
list and that value will become the new limit.
In turn, for each CPU there is only one resume latency PM QoS request
associated with the :file:`power/pm_qos_resume_latency_us` file under
In turn, for each CPU there is one resume latency PM QoS request associated with
the :file:`power/pm_qos_resume_latency_us` file under
:file:`/sys/devices/system/cpu/cpu<N>/` in ``sysfs`` and writing to it causes
this single PM QoS request to be updated regardless of which user space
process does that. In other words, this PM QoS request is shared by the entire
user space, so access to the file associated with it needs to be arbitrated
to avoid confusion. [Arguably, the only legitimate use of this mechanism in
practice is to pin a process to the CPU in question and let it use the
``sysfs`` interface to control the resume latency constraint for it.] It
still only is a request, however. It is a member of a priority list used to
``sysfs`` interface to control the resume latency constraint for it.] It is
still only a request, however. It is an entry in a priority list used to
determine the effective value to be set as the resume latency constraint for the
CPU in question every time the list of requests is updated this way or another
(there may be other requests coming from kernel code in that list).
CPU idle time governors are expected to regard the minimum of the global
effective ``PM_QOS_CPU_DMA_LATENCY`` class constraint and the effective
resume latency constraint for the given CPU as the upper limit for the exit
latency of the idle states they can select for that CPU. They should never
select any idle states with exit latency beyond that limit.
(effective) CPU latency limit and the effective resume latency constraint for
the given CPU as the upper limit for the exit latency of the idle states that
they are allowed to select for that CPU. They should never select any idle
states with exit latency beyond that limit.
Idle States Control Via Kernel Command Line
Documentation/admin-guide/pm/intel_idle.rst
+26 -4
View File
@@ -60,6 +60,9 @@ of the system. The former are always used if the processor model at hand is
recognized by ``intel_idle`` and the latter are used if that is required for
the given processor model (which is the case for all server processor models
recognized by ``intel_idle``) or if the processor model is not recognized.
[There is a module parameter that can be used to make the driver use the ACPI
tables with any processor model recognized by it; see
`below <intel-idle-parameters_>`_.]
If the ACPI tables are going to be used for building the list of available idle
states, ``intel_idle`` first looks for a ``_CST`` object under one of the ACPI
@@ -165,7 +168,7 @@ and ``idle=nomwait``. If any of them is present in the kernel command line, the
``MWAIT`` instruction is not allowed to be used, so the initialization of
``intel_idle`` will fail.
Apart from that there are two module parameters recognized by ``intel_idle``
Apart from that there are four module parameters recognized by ``intel_idle``
itself that can be set via the kernel command line (they cannot be updated via
sysfs, so that is the only way to change their values).
@@ -186,9 +189,28 @@ QoS) feature can be used to prevent ``CPUIdle`` from touching those idle states
even if they have been enumerated (see :ref:`cpu-pm-qos` in :doc:`cpuidle`).
Setting ``max_cstate`` to 0 causes the ``intel_idle`` initialization to fail.
The ``noacpi`` module parameter (which is recognized by ``intel_idle`` if the
kernel has been configured with ACPI support), can be set to make the driver
ignore the system's ACPI tables entirely (it is unset by default).
The ``no_acpi`` and ``use_acpi`` module parameters (recognized by ``intel_idle``
if the kernel has been configured with ACPI support) can be set to make the
driver ignore the system's ACPI tables entirely or use them for all of the
recognized processor models, respectively (they both are unset by default and
``use_acpi`` has no effect if ``no_acpi`` is set).
The value of the ``states_off`` module parameter (0 by default) represents a
list of idle states to be disabled by default in the form of a bitmask.
Namely, the positions of the bits that are set in the ``states_off`` value are
the indices of idle states to be disabled by default (as reflected by the names
of the corresponding idle state directories in ``sysfs``, :file:`state0`,
:file:`state1` ... :file:`state<i>` ..., where ``<i>`` is the index of the given
idle state; see :ref:`idle-states-representation` in :doc:`cpuidle`).
For example, if ``states_off`` is equal to 3, the driver will disable idle
states 0 and 1 by default, and if it is equal to 8, idle state 3 will be
disabled by default and so on (bit positions beyond the maximum idle state index
are ignored).
The idle states disabled this way can be enabled (on a per-CPU basis) from user
space via ``sysfs``.
.. _intel-idle-core-and-package-idle-states:
Documentation/admin-guide/pm/intel_pstate.rst
+2 -2
View File
@@ -734,10 +734,10 @@ References
==========
.. [1] Kristen Accardi, *Balancing Power and Performance in the Linux Kernel*,
http://events.linuxfoundation.org/sites/events/files/slides/LinuxConEurope_2015.pdf
https://events.static.linuxfound.org/sites/events/files/slides/LinuxConEurope_2015.pdf
.. [2] *Intel® 64 and IA-32 Architectures Software Developer’s Manual Volume 3: System Programming Guide*,
http://www.intel.com/content/www/us/en/architecture-and-technology/64-ia-32-architectures-software-developer-system-programming-manual-325384.html
https://www.intel.com/content/www/us/en/architecture-and-technology/64-ia-32-architectures-software-developer-system-programming-manual-325384.html
.. [3] *Advanced Configuration and Power Interface Specification*,
https://uefi.org/sites/default/files/resources/ACPI_6_3_final_Jan30.pdf
Documentation/admin-guide/pm/sleep-states.rst
+59 -17
View File
@@ -153,8 +153,11 @@ for the given CPU architecture includes the low-level code for system resume.
Basic ``sysfs`` Interfaces for System Suspend and Hibernation
=============================================================
The following files located in the :file:`/sys/power/` directory can be used by
user space for sleep states control.
The power management subsystem provides userspace with a unified ``sysfs``
interface for system sleep regardless of the underlying system architecture or
platform. That interface is located in the :file:`/sys/power/` directory
(assuming that ``sysfs`` is mounted at :file:`/sys`) and it consists of the
following attributes (files):
``state``
This file contains a list of strings representing sleep states supported
@@ -162,9 +165,9 @@ user space for sleep states control.
to start a transition of the system into the sleep state represented by
that string.
In particular, the strings "disk", "freeze" and "standby" represent the
In particular, the "disk", "freeze" and "standby" strings represent the
:ref:`hibernation <hibernation>`, :ref:`suspend-to-idle <s2idle>` and
:ref:`standby <standby>` sleep states, respectively. The string "mem"
:ref:`standby <standby>` sleep states, respectively. The "mem" string
is interpreted in accordance with the contents of the ``mem_sleep`` file
described below.
@@ -177,7 +180,7 @@ user space for sleep states control.
associated with the "mem" string in the ``state`` file described above.
The strings that may be present in this file are "s2idle", "shallow"
and "deep". The string "s2idle" always represents :ref:`suspend-to-idle
and "deep". The "s2idle" string always represents :ref:`suspend-to-idle
<s2idle>` and, by convention, "shallow" and "deep" represent
:ref:`standby <standby>` and :ref:`suspend-to-RAM <s2ram>`,
respectively.
@@ -185,15 +188,17 @@ user space for sleep states control.
Writing one of the listed strings into this file causes the system
suspend variant represented by it to be associated with the "mem" string
in the ``state`` file. The string representing the suspend variant
currently associated with the "mem" string in the ``state`` file
is listed in square brackets.
currently associated with the "mem" string in the ``state`` file is
shown in square brackets.
If the kernel does not support system suspend, this file is not present.
``disk``
This file contains a list of strings representing different operations
that can be carried out after the hibernation image has been saved. The
possible options are as follows:
This file controls the operating mode of hibernation (Suspend-to-Disk).
Specifically, it tells the kernel what to do after creating a
hibernation image.
Reading from it returns a list of supported options encoded as:
``platform``
Put the system into a special low-power state (e.g. ACPI S4) to
@@ -201,6 +206,11 @@ user space for sleep states control.
platform firmware to take a simplified initialization path after
wakeup.
It is only available if the platform provides a special
mechanism to put the system to sleep after creating a
hibernation image (platforms with ACPI do that as a rule, for
example).
``shutdown``
Power off the system.
@@ -214,22 +224,53 @@ user space for sleep states control.
the hibernation image and continue. Otherwise, use the image
to restore the previous state of the system.
It is available if system suspend is supported.
``test_resume``
Diagnostic operation. Load the image as though the system had
just woken up from hibernation and the currently running kernel
instance was a restore kernel and follow up with full system
resume.
Writing one of the listed strings into this file causes the option
Writing one of the strings listed above into this file causes the option
represented by it to be selected.
The currently selected option is shown in square brackets which means
The currently selected option is shown in square brackets, which means
that the operation represented by it will be carried out after creating
and saving the image next time hibernation is triggered by writing
``disk`` to :file:`/sys/power/state`.
and saving the image when hibernation is triggered by writing ``disk``
to :file:`/sys/power/state`.
If the kernel does not support hibernation, this file is not present.
``image_size``
This file controls the size of hibernation images.
It can be written a string representing a non-negative integer that will
be used as a best-effort upper limit of the image size, in bytes. The
hibernation core will do its best to ensure that the image size will not
exceed that number, but if that turns out to be impossible to achieve, a
hibernation image will still be created and its size will be as small as
possible. In particular, writing '0' to this file causes the size of
hibernation images to be minimum.
Reading from it returns the current image size limit, which is set to
around 2/5 of the available RAM size by default.
``pm_trace``
This file controls the "PM trace" mechanism saving the last suspend
or resume event point in the RTC memory across reboots. It helps to
debug hard lockups or reboots due to device driver failures that occur
during system suspend or resume (which is more common) more effectively.
If it contains "1", the fingerprint of each suspend/resume event point
in turn will be stored in the RTC memory (overwriting the actual RTC
information), so it will survive a system crash if one occurs right
after storing it and it can be used later to identify the driver that
caused the crash to happen.
It contains "0" by default, which may be changed to "1" by writing a
string representing a nonzero integer into it.
According to the above, there are two ways to make the system go into the
:ref:`suspend-to-idle <s2idle>` state. The first one is to write "freeze"
directly to :file:`/sys/power/state`. The second one is to write "s2idle" to
@@ -244,6 +285,7 @@ system go into the :ref:`suspend-to-RAM <s2ram>` state (write "deep" into
The default suspend variant (ie. the one to be used without writing anything
into :file:`/sys/power/mem_sleep`) is either "deep" (on the majority of systems
supporting :ref:`suspend-to-RAM <s2ram>`) or "s2idle", but it can be overridden
by the value of the "mem_sleep_default" parameter in the kernel command line.
On some ACPI-based systems, depending on the information in the ACPI tables, the
default may be "s2idle" even if :ref:`suspend-to-RAM <s2ram>` is supported.
by the value of the ``mem_sleep_default`` parameter in the kernel command line.
On some systems with ACPI, depending on the information in the ACPI tables, the
default may be "s2idle" even if :ref:`suspend-to-RAM <s2ram>` is supported in
principle.
Documentation/admin-guide/pm/suspend-flows.rst
+270
View File
@@ -0,0 +1,270 @@
.. SPDX-License-Identifier: GPL-2.0
.. include:: <isonum.txt>
=========================
System Suspend Code Flows
=========================
:Copyright: |copy| 2020 Intel Corporation
:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
At least one global system-wide transition needs to be carried out for the
system to get from the working state into one of the supported
:doc:`sleep states <sleep-states>`. Hibernation requires more than one
transition to occur for this purpose, but the other sleep states, commonly
referred to as *system-wide suspend* (or simply *system suspend*) states, need
only one.
For those sleep states, the transition from the working state of the system into
the target sleep state is referred to as *system suspend* too (in the majority
of cases, whether this means a transition or a sleep state of the system should
be clear from the context) and the transition back from the sleep state into the
working state is referred to as *system resume*.
The kernel code flows associated with the suspend and resume transitions for
different sleep states of the system are quite similar, but there are some
significant differences between the :ref:`suspend-to-idle <s2idle>` code flows
and the code flows related to the :ref:`suspend-to-RAM <s2ram>` and
:ref:`standby <standby>` sleep states.
The :ref:`suspend-to-RAM <s2ram>` and :ref:`standby <standby>` sleep states
cannot be implemented without platform support and the difference between them
boils down to the platform-specific actions carried out by the suspend and
resume hooks that need to be provided by the platform driver to make them
available. Apart from that, the suspend and resume code flows for these sleep
states are mostly identical, so they both together will be referred to as
*platform-dependent suspend* states in what follows.
.. _s2idle_suspend:
Suspend-to-idle Suspend Code Flow
=================================
The following steps are taken in order to transition the system from the working
state to the :ref:`suspend-to-idle <s2idle>` sleep state:
1. Invoking system-wide suspend notifiers.
Kernel subsystems can register callbacks to be invoked when the suspend
transition is about to occur and when the resume transition has finished.
That allows them to prepare for the change of the system state and to clean
up after getting back to the working state.
2. Freezing tasks.
Tasks are frozen primarily in order to avoid unchecked hardware accesses
from user space through MMIO regions or I/O registers exposed directly to
it and to prevent user space from entering the kernel while the next step
of the transition is in progress (which might have been problematic for
various reasons).
All user space tasks are intercepted as though they were sent a signal and
put into uninterruptible sleep until the end of the subsequent system resume
transition.
The kernel threads that choose to be frozen during system suspend for
specific reasons are frozen subsequently, but they are not intercepted.
Instead, they are expected to periodically check whether or not they need
to be frozen and to put themselves into uninterruptible sleep if so. [Note,
however, that kernel threads can use locking and other concurrency controls
available in kernel space to synchronize themselves with system suspend and
resume, which can be much more precise than the freezing, so the latter is
not a recommended option for kernel threads.]
3. Suspending devices and reconfiguring IRQs.
Devices are suspended in four phases called *prepare*, *suspend*,
*late suspend* and *noirq suspend* (see :ref:`driverapi_pm_devices` for more
information on what exactly happens in each phase).
Every device is visited in each phase, but typically it is not physically
accessed in more than two of them.
The runtime PM API is disabled for every device during the *late* suspend
phase and high-level ("action") interrupt handlers are prevented from being
invoked before the *noirq* suspend phase.
Interrupts are still handled after that, but they are only acknowledged to
interrupt controllers without performing any device-specific actions that
would be triggered in the working state of the system (those actions are
deferred till the subsequent system resume transition as described
`below <s2idle_resume_>`_).
IRQs associated with system wakeup devices are "armed" so that the resume
transition of the system is started when one of them signals an event.
4. Freezing the scheduler tick and suspending timekeeping.
When all devices have been suspended, CPUs enter the idle loop and are put
into the deepest available idle state. While doing that, each of them
"freezes" its own scheduler tick so that the timer events associated with
the tick do not occur until the CPU is woken up by another interrupt source.
The last CPU to enter the idle state also stops the timekeeping which
(among other things) prevents high resolution timers from triggering going
forward until the first CPU that is woken up restarts the timekeeping.
That allows the CPUs to stay in the deep idle state relatively long in one
go.
From this point on, the CPUs can only be woken up by non-timer hardware
interrupts. If that happens, they go back to the idle state unless the
interrupt that woke up one of them comes from an IRQ that has been armed for
system wakeup, in which case the system resume transition is started.
.. _s2idle_resume:
Suspend-to-idle Resume Code Flow
================================
The following steps are taken in order to transition the system from the
:ref:`suspend-to-idle <s2idle>` sleep state into the working state:
1. Resuming timekeeping and unfreezing the scheduler tick.
When one of the CPUs is woken up (by a non-timer hardware interrupt), it
leaves the idle state entered in the last step of the preceding suspend
transition, restarts the timekeeping (unless it has been restarted already
by another CPU that woke up earlier) and the scheduler tick on that CPU is
unfrozen.
If the interrupt that has woken up the CPU was armed for system wakeup,
the system resume transition begins.
2. Resuming devices and restoring the working-state configuration of IRQs.
Devices are resumed in four phases called *noirq resume*, *early resume*,
*resume* and *complete* (see :ref:`driverapi_pm_devices` for more
information on what exactly happens in each phase).
Every device is visited in each phase, but typically it is not physically
accessed in more than two of them.
The working-state configuration of IRQs is restored after the *noirq* resume
phase and the runtime PM API is re-enabled for every device whose driver
supports it during the *early* resume phase.
3. Thawing tasks.
Tasks frozen in step 2 of the preceding `suspend <s2idle_suspend_>`_
transition are "thawed", which means that they are woken up from the
uninterruptible sleep that they went into at that time and user space tasks
are allowed to exit the kernel.
4. Invoking system-wide resume notifiers.
This is analogous to step 1 of the `suspend <s2idle_suspend_>`_ transition
and the same set of callbacks is invoked at this point, but a different
"notification type" parameter value is passed to them.
Platform-dependent Suspend Code Flow
====================================
The following steps are taken in order to transition the system from the working
state to platform-dependent suspend state:
1. Invoking system-wide suspend notifiers.
This step is the same as step 1 of the suspend-to-idle suspend transition
described `above <s2idle_suspend_>`_.
2. Freezing tasks.
This step is the same as step 2 of the suspend-to-idle suspend transition
described `above <s2idle_suspend_>`_.
3. Suspending devices and reconfiguring IRQs.
This step is analogous to step 3 of the suspend-to-idle suspend transition
described `above <s2idle_suspend_>`_, but the arming of IRQs for system
wakeup generally does not have any effect on the platform.
There are platforms that can go into a very deep low-power state internally
when all CPUs in them are in sufficiently deep idle states and all I/O
devices have been put into low-power states. On those platforms,
suspend-to-idle can reduce system power very effectively.
On the other platforms, however, low-level components (like interrupt
controllers) need to be turned off in a platform-specific way (implemented
in the hooks provided by the platform driver) to achieve comparable power
reduction.
That usually prevents in-band hardware interrupts from waking up the system,
which must be done in a special platform-dependent way. Then, the
configuration of system wakeup sources usually starts when system wakeup
devices are suspended and is finalized by the platform suspend hooks later
on.
4. Disabling non-boot CPUs.
On some platforms the suspend hooks mentioned above must run in a one-CPU
configuration of the system (in particular, the hardware cannot be accessed
by any code running in parallel with the platform suspend hooks that may,
and often do, trap into the platform firmware in order to finalize the
suspend transition).
For this reason, the CPU offline/online (CPU hotplug) framework is used
to take all of the CPUs in the system, except for one (the boot CPU),
offline (typically, the CPUs that have been taken offline go into deep idle
states).
This means that all tasks are migrated away from those CPUs and all IRQs are
rerouted to the only CPU that remains online.
5. Suspending core system components.
This prepares the core system components for (possibly) losing power going
forward and suspends the timekeeping.
6. Platform-specific power removal.
This is expected to remove power from all of the system components except
for the memory controller and RAM (in order to preserve the contents of the
latter) and some devices designated for system wakeup.
In many cases control is passed to the platform firmware which is expected
to finalize the suspend transition as needed.
Platform-dependent Resume Code Flow
===================================
The following steps are taken in order to transition the system from a
platform-dependent suspend state into the working state:
1. Platform-specific system wakeup.
The platform is woken up by a signal from one of the designated system
wakeup devices (which need not be an in-band hardware interrupt) and
control is passed back to the kernel (the working configuration of the
platform may need to be restored by the platform firmware before the
kernel gets control again).
2. Resuming core system components.
The suspend-time configuration of the core system components is restored and
the timekeeping is resumed.
3. Re-enabling non-boot CPUs.
The CPUs disabled in step 4 of the preceding suspend transition are taken
back online and their suspend-time configuration is restored.
4. Resuming devices and restoring the working-state configuration of IRQs.
This step is the same as step 2 of the suspend-to-idle suspend transition
described `above <s2idle_resume_>`_.
5. Thawing tasks.
This step is the same as step 3 of the suspend-to-idle suspend transition
described `above <s2idle_resume_>`_.
6. Invoking system-wide resume notifiers.
This step is the same as step 4 of the suspend-to-idle suspend transition
described `above <s2idle_resume_>`_.
Documentation/admin-guide/pm/system-wide.rst
+1
View File
@@ -8,3 +8,4 @@ System-Wide Power Management
:maxdepth: 2
sleep-states
suspend-flows
Documentation/admin-guide/pm/working-state.rst
+1
View File
@@ -11,4 +11,5 @@ Working-State Power Management
intel_idle
cpufreq
intel_pstate
cpufreq_drivers
intel_epb
Documentation/admin-guide/sysctl/kernel.rst
+563 -497
View File
File diff suppressed because it is too large Load Diff
Documentation/admin-guide/sysctl/net.rst
+2 -1
View File
@@ -67,7 +67,8 @@ two flavors of JITs, the newer eBPF JIT currently supported on:
- sparc64
- mips64
- s390x
- riscv
- riscv64
- riscv32
And the older cBPF JIT supported on the following archs:
Documentation/admin-guide/sysctl/user.rst
+6
View File
@@ -65,6 +65,12 @@ max_pid_namespaces
The maximum number of pid namespaces that any user in the current
user namespace may create.
max_time_namespaces
===================
The maximum number of time namespaces that any user in the current
user namespace may create.
max_user_namespaces
===================
Documentation/admin-guide/sysctl/vm.rst
+3
View File
@@ -128,6 +128,9 @@ allowed to examine the unevictable lru (mlocked pages) for pages to compact.
This should be used on systems where stalls for minor page faults are an
acceptable trade for large contiguous free memory. Set to 0 to prevent
compaction from moving pages that are unevictable. Default value is 1.
On CONFIG_PREEMPT_RT the default value is 0 in order to avoid a page fault, due
to compaction, which would block the task from becomming active until the fault
is resolved.
dirty_background_bytes
Documentation/admin-guide/sysrq.rst
+11 -9
View File
@@ -48,9 +48,10 @@ always allowed (by a user with admin privileges).
How do I use the magic SysRq key?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
On x86 - You press the key combo :kbd:`ALT-SysRq-<command key>`.
On x86
You press the key combo :kbd:`ALT-SysRq-<command key>`.
.. note::
.. note::
Some
keyboards may not have a key labeled 'SysRq'. The 'SysRq' key is
also known as the 'Print Screen' key. Also some keyboards cannot
@@ -58,14 +59,15 @@ On x86 - You press the key combo :kbd:`ALT-SysRq-<command key>`.
have better luck with press :kbd:`Alt`, press :kbd:`SysRq`,
release :kbd:`SysRq`, press :kbd:`<command key>`, release everything.
On SPARC - You press :kbd:`ALT-STOP-<command key>`, I believe.
On SPARC
You press :kbd:`ALT-STOP-<command key>`, I believe.
On the serial console (PC style standard serial ports only)
You send a ``BREAK``, then within 5 seconds a command key. Sending
``BREAK`` twice is interpreted as a normal BREAK.
On PowerPC
Press :kbd:`ALT - Print Screen` (or :kbd:`F13`) - :kbd:`<command key>`,
Press :kbd:`ALT - Print Screen` (or :kbd:`F13`) - :kbd:`<command key>`.
:kbd:`Print Screen` (or :kbd:`F13`) - :kbd:`<command key>` may suffice.
On other
@@ -73,7 +75,7 @@ On other
let me know so I can add them to this section.
On all
write a character to /proc/sysrq-trigger. e.g.::
Write a character to /proc/sysrq-trigger. e.g.::
echo t > /proc/sysrq-trigger
@@ -282,7 +284,7 @@ Just ask them on the linux-kernel mailing list:
Credits
~~~~~~~
Written by Mydraal <vulpyne@vulpyne.net>
Updated by Adam Sulmicki <adam@cfar.umd.edu>
Updated by Jeremy M. Dolan <jmd@turbogeek.org> 2001/01/28 10:15:59
Added to by Crutcher Dunnavant <crutcher+kernel@datastacks.com>
- Written by Mydraal <vulpyne@vulpyne.net>
- Updated by Adam Sulmicki <adam@cfar.umd.edu>
- Updated by Jeremy M. Dolan <jmd@turbogeek.org> 2001/01/28 10:15:59
- Added to by Crutcher Dunnavant <crutcher+kernel@datastacks.com>
Documentation/arm/microchip.rst
+6
View File
@@ -92,6 +92,12 @@ the Microchip website: http://www.microchip.com.
http://ww1.microchip.com/downloads/en/DeviceDoc/DS60001517A.pdf
- sam9x60
* Datasheet
http://ww1.microchip.com/downloads/en/DeviceDoc/SAM9X60-Data-Sheet-DS60001579A.pdf
* ARM Cortex-A5 based SoCs
- sama5d3 family
Documentation/arm/tcm.rst
+3 -3
View File
@@ -4,18 +4,18 @@ ARM TCM (Tightly-Coupled Memory) handling in Linux
Written by Linus Walleij <linus.walleij@stericsson.com>
Some ARM SoC:s have a so-called TCM (Tightly-Coupled Memory).
Some ARM SoCs have a so-called TCM (Tightly-Coupled Memory).
This is usually just a few (4-64) KiB of RAM inside the ARM
processor.
Due to being embedded inside the CPU The TCM has a
Due to being embedded inside the CPU, the TCM has a
Harvard-architecture, so there is an ITCM (instruction TCM)
and a DTCM (data TCM). The DTCM can not contain any
instructions, but the ITCM can actually contain data.
The size of DTCM or ITCM is minimum 4KiB so the typical
minimum configuration is 4KiB ITCM and 4KiB DTCM.
ARM CPU:s have special registers to read out status, physical
ARM CPUs have special registers to read out status, physical
location and size of TCM memories. arch/arm/include/asm/cputype.h
defines a CPUID_TCM register that you can read out from the
system control coprocessor. Documentation from ARM can be found
Documentation/arm64/amu.rst
+112
View File
@@ -0,0 +1,112 @@
=======================================================
Activity Monitors Unit (AMU) extension in AArch64 Linux
=======================================================
Author: Ionela Voinescu <ionela.voinescu@arm.com>
Date: 2019-09-10
This document briefly describes the provision of Activity Monitors Unit
support in AArch64 Linux.
Architecture overview
---------------------
The activity monitors extension is an optional extension introduced by the
ARMv8.4 CPU architecture.
The activity monitors unit, implemented in each CPU, provides performance
counters intended for system management use. The AMU extension provides a
system register interface to the counter registers and also supports an
optional external memory-mapped interface.
Version 1 of the Activity Monitors architecture implements a counter group
of four fixed and architecturally defined 64-bit event counters.
- CPU cycle counter: increments at the frequency of the CPU.
- Constant counter: increments at the fixed frequency of the system
clock.
- Instructions retired: increments with every architecturally executed
instruction.
- Memory stall cycles: counts instruction dispatch stall cycles caused by
misses in the last level cache within the clock domain.
When in WFI or WFE these counters do not increment.
The Activity Monitors architecture provides space for up to 16 architected
event counters. Future versions of the architecture may use this space to
implement additional architected event counters.
Additionally, version 1 implements a counter group of up to 16 auxiliary
64-bit event counters.
On cold reset all counters reset to 0.
Basic support
-------------
The kernel can safely run a mix of CPUs with and without support for the
activity monitors extension. Therefore, when CONFIG_ARM64_AMU_EXTN is
selected we unconditionally enable the capability to allow any late CPU
(secondary or hotplugged) to detect and use the feature.
When the feature is detected on a CPU, we flag the availability of the
feature but this does not guarantee the correct functionality of the
counters, only the presence of the extension.
Firmware (code running at higher exception levels, e.g. arm-tf) support is
needed to:
- Enable access for lower exception levels (EL2 and EL1) to the AMU
registers.
- Enable the counters. If not enabled these will read as 0.
- Save/restore the counters before/after the CPU is being put/brought up
from the 'off' power state.
When using kernels that have this feature enabled but boot with broken
firmware the user may experience panics or lockups when accessing the
counter registers. Even if these symptoms are not observed, the values
returned by the register reads might not correctly reflect reality. Most
commonly, the counters will read as 0, indicating that they are not
enabled.
If proper support is not provided in firmware it's best to disable
CONFIG_ARM64_AMU_EXTN. To be noted that for security reasons, this does not
bypass the setting of AMUSERENR_EL0 to trap accesses from EL0 (userspace) to
EL1 (kernel). Therefore, firmware should still ensure accesses to AMU registers
are not trapped in EL2/EL3.
The fixed counters of AMUv1 are accessible though the following system
register definitions:
- SYS_AMEVCNTR0_CORE_EL0
- SYS_AMEVCNTR0_CONST_EL0
- SYS_AMEVCNTR0_INST_RET_EL0
- SYS_AMEVCNTR0_MEM_STALL_EL0
Auxiliary platform specific counters can be accessed using
SYS_AMEVCNTR1_EL0(n), where n is a value between 0 and 15.
Details can be found in: arch/arm64/include/asm/sysreg.h.
Userspace access
----------------
Currently, access from userspace to the AMU registers is disabled due to:
- Security reasons: they might expose information about code executed in
secure mode.
- Purpose: AMU counters are intended for system management use.
Also, the presence of the feature is not visible to userspace.
Virtualization
--------------
Currently, access from userspace (EL0) and kernelspace (EL1) on the KVM
guest side is disabled due to:
- Security reasons: they might expose information about code executed
by other guests or the host.
Any attempt to access the AMU registers will result in an UNDEFINED
exception being injected into the guest.
Documentation/arm64/booting.rst
+14
View File
@@ -248,6 +248,20 @@ Before jumping into the kernel, the following conditions must be met:
- HCR_EL2.APK (bit 40) must be initialised to 0b1
- HCR_EL2.API (bit 41) must be initialised to 0b1
For CPUs with Activity Monitors Unit v1 (AMUv1) extension present:
- If EL3 is present:
CPTR_EL3.TAM (bit 30) must be initialised to 0b0
CPTR_EL2.TAM (bit 30) must be initialised to 0b0
AMCNTENSET0_EL0 must be initialised to 0b1111
AMCNTENSET1_EL0 must be initialised to a platform specific value
having 0b1 set for the corresponding bit for each of the auxiliary
counters present.
- If the kernel is entered at EL1:
AMCNTENSET0_EL0 must be initialised to 0b1111
AMCNTENSET1_EL0 must be initialised to a platform specific value
having 0b1 set for the corresponding bit for each of the auxiliary
counters present.
The requirements described above for CPU mode, caches, MMUs, architected
timers, coherency and system registers apply to all CPUs. All CPUs must
enter the kernel in the same exception level.
Documentation/arm64/index.rst
+1
View File
@@ -6,6 +6,7 @@ ARM64 Architecture
:maxdepth: 1
acpi_object_usage
amu
arm-acpi
booting
cpu-feature-registers
Documentation/arm64/memory.rst
+1 -1
View File
@@ -129,7 +129,7 @@ this logic.
As a single binary will need to support both 48-bit and 52-bit VA
spaces, the VMEMMAP must be sized large enough for 52-bit VAs and
also must be sized large enought to accommodate a fixed PAGE_OFFSET.
also must be sized large enough to accommodate a fixed PAGE_OFFSET.
Most code in the kernel should not need to consider the VA_BITS, for
code that does need to know the VA size the variables are
Documentation/arm64/silicon-errata.rst
+2
View File
@@ -110,6 +110,8 @@ stable kernels.
+----------------+-----------------+-----------------+-----------------------------+
| Cavium | ThunderX GICv3 | #23154 | CAVIUM_ERRATUM_23154 |
+----------------+-----------------+-----------------+-----------------------------+
| Cavium | ThunderX GICv3 | #38539 | N/A |
+----------------+-----------------+-----------------+-----------------------------+
| Cavium | ThunderX Core | #27456 | CAVIUM_ERRATUM_27456 |
+----------------+-----------------+-----------------+-----------------------------+
| Cavium | ThunderX Core | #30115 | CAVIUM_ERRATUM_30115 |
Documentation/arm64/tagged-address-abi.rst
+9 -2
View File
@@ -44,8 +44,15 @@ The AArch64 Tagged Address ABI has two stages of relaxation depending
how the user addresses are used by the kernel:
1. User addresses not accessed by the kernel but used for address space
management (e.g. ``mmap()``, ``mprotect()``, ``madvise()``). The use
of valid tagged pointers in this context is always allowed.
management (e.g. ``mprotect()``, ``madvise()``). The use of valid
tagged pointers in this context is allowed with the exception of
``brk()``, ``mmap()`` and the ``new_address`` argument to
``mremap()`` as these have the potential to alias with existing
user addresses.
NOTE: This behaviour changed in v5.6 and so some earlier kernels may
incorrectly accept valid tagged pointers for the ``brk()``,
``mmap()`` and ``mremap()`` system calls.
2. User addresses accessed by the kernel (e.g. ``write()``). This ABI
relaxation is disabled by default and the application thread needs to
Documentation/asm-annotations.rst
+5 -4
View File
@@ -73,10 +73,11 @@ The new macros are prefixed with the ``SYM_`` prefix and can be divided into
three main groups:
1. ``SYM_FUNC_*`` -- to annotate C-like functions. This means functions with
standard C calling conventions, i.e. the stack contains a return address at
the predefined place and a return from the function can happen in a
standard way. When frame pointers are enabled, save/restore of frame
pointer shall happen at the start/end of a function, respectively, too.
standard C calling conventions. For example, on x86, this means that the
stack contains a return address at the predefined place and a return from
the function can happen in a standard way. When frame pointers are enabled,
save/restore of frame pointer shall happen at the start/end of a function,
respectively, too.
Checking tools like ``objtool`` should ensure such marked functions conform
to these rules. The tools can also easily annotate these functions with
Documentation/block/biovecs.rst
+1 -1
View File
@@ -47,7 +47,7 @@ Having a real iterator, and making biovecs immutable, has a number of
advantages:
* Before, iterating over bios was very awkward when you weren't processing
exactly one bvec at a time - for example, bio_copy_data() in fs/bio.c,
exactly one bvec at a time - for example, bio_copy_data() in block/bio.c,
which copies the contents of one bio into another. Because the biovecs
wouldn't necessarily be the same size, the old code was tricky convoluted -
it had to walk two different bios at the same time, keeping both bi_idx and
Documentation/block/capability.rst
+4 -12
View File
@@ -2,17 +2,9 @@
Generic Block Device Capability
===============================
This file documents the sysfs file block/<disk>/capability
This file documents the sysfs file ``block/<disk>/capability``.
capability is a hex word indicating which capabilities a specific disk
supports. For more information on bits not listed here, see
include/linux/genhd.h
``capability`` is a bitfield, printed in hexadecimal, indicating which
capabilities a specific block device supports:
GENHD_FL_MEDIA_CHANGE_NOTIFY
----------------------------
Value: 4
When this bit is set, the disk supports Asynchronous Notification
of media change events. These events will be broadcast to user
space via kernel uevent.
.. kernel-doc:: include/linux/genhd.h
Documentation/bpf/bpf_devel_QA.rst
+12 -17
View File
@@ -20,11 +20,11 @@ Reporting bugs
Q: How do I report bugs for BPF kernel code?
--------------------------------------------
A: Since all BPF kernel development as well as bpftool and iproute2 BPF
loader development happens through the netdev kernel mailing list,
loader development happens through the bpf kernel mailing list,
please report any found issues around BPF to the following mailing
list:
netdev@vger.kernel.org
bpf@vger.kernel.org
This may also include issues related to XDP, BPF tracing, etc.
@@ -46,17 +46,12 @@ Submitting patches
Q: To which mailing list do I need to submit my BPF patches?
------------------------------------------------------------
A: Please submit your BPF patches to the netdev kernel mailing list:
A: Please submit your BPF patches to the bpf kernel mailing list:
netdev@vger.kernel.org
Historically, BPF came out of networking and has always been maintained
by the kernel networking community. Although these days BPF touches
many other subsystems as well, the patches are still routed mainly
through the networking community.
bpf@vger.kernel.org
In case your patch has changes in various different subsystems (e.g.
tracing, security, etc), make sure to Cc the related kernel mailing
networking, tracing, security, etc), make sure to Cc the related kernel mailing
lists and maintainers from there as well, so they are able to review
the changes and provide their Acked-by's to the patches.
@@ -168,7 +163,7 @@ a BPF point of view.
Be aware that this is not a final verdict that the patch will
automatically get accepted into net or net-next trees eventually:
On the netdev kernel mailing list reviews can come in at any point
On the bpf kernel mailing list reviews can come in at any point
in time. If discussions around a patch conclude that they cannot
get included as-is, we will either apply a follow-up fix or drop
them from the trees entirely. Therefore, we also reserve to rebase
@@ -494,15 +489,15 @@ A: You need cmake and gcc-c++ as build requisites for LLVM. Once you have
that set up, proceed with building the latest LLVM and clang version
from the git repositories::
$ git clone http://llvm.org/git/llvm.git
$ cd llvm/tools
$ git clone --depth 1 http://llvm.org/git/clang.git
$ cd ..; mkdir build; cd build
$ cmake .. -DLLVM_TARGETS_TO_BUILD="BPF;X86" \
$ git clone https://github.com/llvm/llvm-project.git
$ mkdir -p llvm-project/llvm/build/install
$ cd llvm-project/llvm/build
$ cmake .. -G "Ninja" -DLLVM_TARGETS_TO_BUILD="BPF;X86" \
-DLLVM_ENABLE_PROJECTS="clang" \
-DBUILD_SHARED_LIBS=OFF \
-DCMAKE_BUILD_TYPE=Release \
-DLLVM_BUILD_RUNTIME=OFF
$ make -j $(getconf _NPROCESSORS_ONLN)
$ ninja
The built binaries can then be found in the build/bin/ directory, where
you can point the PATH variable to.
Documentation/bpf/bpf_lsm.rst
+142
View File
@@ -0,0 +1,142 @@
.. SPDX-License-Identifier: GPL-2.0+
.. Copyright (C) 2020 Google LLC.
================
LSM BPF Programs
================
These BPF programs allow runtime instrumentation of the LSM hooks by privileged
users to implement system-wide MAC (Mandatory Access Control) and Audit
policies using eBPF.
Structure
---------
The example shows an eBPF program that can be attached to the ``file_mprotect``
LSM hook:
.. c:function:: int file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot);
Other LSM hooks which can be instrumented can be found in
``include/linux/lsm_hooks.h``.
eBPF programs that use :doc:`/bpf/btf` do not need to include kernel headers
for accessing information from the attached eBPF program's context. They can
simply declare the structures in the eBPF program and only specify the fields
that need to be accessed.
.. code-block:: c
struct mm_struct {
unsigned long start_brk, brk, start_stack;
} __attribute__((preserve_access_index));
struct vm_area_struct {
unsigned long start_brk, brk, start_stack;
unsigned long vm_start, vm_end;
struct mm_struct *vm_mm;
} __attribute__((preserve_access_index));
.. note:: The order of the fields is irrelevant.
This can be further simplified (if one has access to the BTF information at
build time) by generating the ``vmlinux.h`` with:
.. code-block:: console
# bpftool btf dump file <path-to-btf-vmlinux> format c > vmlinux.h
.. note:: ``path-to-btf-vmlinux`` can be ``/sys/kernel/btf/vmlinux`` if the
build environment matches the environment the BPF programs are
deployed in.
The ``vmlinux.h`` can then simply be included in the BPF programs without
requiring the definition of the types.
The eBPF programs can be declared using the``BPF_PROG``
macros defined in `tools/lib/bpf/bpf_tracing.h`_. In this
example:
* ``"lsm/file_mprotect"`` indicates the LSM hook that the program must
be attached to
* ``mprotect_audit`` is the name of the eBPF program
.. code-block:: c
SEC("lsm/file_mprotect")
int BPF_PROG(mprotect_audit, struct vm_area_struct *vma,
unsigned long reqprot, unsigned long prot, int ret)
{
/* ret is the return value from the previous BPF program
* or 0 if it's the first hook.
*/
if (ret != 0)
return ret;
int is_heap;
is_heap = (vma->vm_start >= vma->vm_mm->start_brk &&
vma->vm_end <= vma->vm_mm->brk);
/* Return an -EPERM or write information to the perf events buffer
* for auditing
*/
if (is_heap)
return -EPERM;
}
The ``__attribute__((preserve_access_index))`` is a clang feature that allows
the BPF verifier to update the offsets for the access at runtime using the
:doc:`/bpf/btf` information. Since the BPF verifier is aware of the types, it
also validates all the accesses made to the various types in the eBPF program.
Loading
-------
eBPF programs can be loaded with the :manpage:`bpf(2)` syscall's
``BPF_PROG_LOAD`` operation:
.. code-block:: c
struct bpf_object *obj;
obj = bpf_object__open("./my_prog.o");
bpf_object__load(obj);
This can be simplified by using a skeleton header generated by ``bpftool``:
.. code-block:: console
# bpftool gen skeleton my_prog.o > my_prog.skel.h
and the program can be loaded by including ``my_prog.skel.h`` and using
the generated helper, ``my_prog__open_and_load``.
Attachment to LSM Hooks
-----------------------
The LSM allows attachment of eBPF programs as LSM hooks using :manpage:`bpf(2)`
syscall's ``BPF_RAW_TRACEPOINT_OPEN`` operation or more simply by
using the libbpf helper ``bpf_program__attach_lsm``.
The program can be detached from the LSM hook by *destroying* the ``link``
link returned by ``bpf_program__attach_lsm`` using ``bpf_link__destroy``.
One can also use the helpers generated in ``my_prog.skel.h`` i.e.
``my_prog__attach`` for attachment and ``my_prog__destroy`` for cleaning up.
Examples
--------
An example eBPF program can be found in
`tools/testing/selftests/bpf/progs/lsm.c`_ and the corresponding
userspace code in `tools/testing/selftests/bpf/prog_tests/test_lsm.c`_
.. Links
.. _tools/lib/bpf/bpf_tracing.h:
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/tree/tools/lib/bpf/bpf_tracing.h
.. _tools/testing/selftests/bpf/progs/lsm.c:
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/tree/tools/testing/selftests/bpf/progs/lsm.c
.. _tools/testing/selftests/bpf/prog_tests/test_lsm.c:
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/tree/tools/testing/selftests/bpf/prog_tests/test_lsm.c
Documentation/bpf/drgn.rst
+213
View File
@@ -0,0 +1,213 @@
.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
==============
BPF drgn tools
==============
drgn scripts is a convenient and easy to use mechanism to retrieve arbitrary
kernel data structures. drgn is not relying on kernel UAPI to read the data.
Instead it's reading directly from ``/proc/kcore`` or vmcore and pretty prints
the data based on DWARF debug information from vmlinux.
This document describes BPF related drgn tools.
See `drgn/tools`_ for all tools available at the moment and `drgn/doc`_ for
more details on drgn itself.
bpf_inspect.py
--------------
Description
===========
`bpf_inspect.py`_ is a tool intended to inspect BPF programs and maps. It can
iterate over all programs and maps in the system and print basic information
about these objects, including id, type and name.
The main use-case `bpf_inspect.py`_ covers is to show BPF programs of types
``BPF_PROG_TYPE_EXT`` and ``BPF_PROG_TYPE_TRACING`` attached to other BPF
programs via ``freplace``/``fentry``/``fexit`` mechanisms, since there is no
user-space API to get this information.
Getting started
===============
List BPF programs (full names are obtained from BTF)::
% sudo bpf_inspect.py prog
27: BPF_PROG_TYPE_TRACEPOINT tracepoint__tcp__tcp_send_reset
4632: BPF_PROG_TYPE_CGROUP_SOCK_ADDR tw_ipt_bind
49464: BPF_PROG_TYPE_RAW_TRACEPOINT raw_tracepoint__sched_process_exit
List BPF maps::
% sudo bpf_inspect.py map
2577: BPF_MAP_TYPE_HASH tw_ipt_vips
4050: BPF_MAP_TYPE_STACK_TRACE stack_traces
4069: BPF_MAP_TYPE_PERCPU_ARRAY ned_dctcp_cntr
Find BPF programs attached to BPF program ``test_pkt_access``::
% sudo bpf_inspect.py p | grep test_pkt_access
650: BPF_PROG_TYPE_SCHED_CLS test_pkt_access
654: BPF_PROG_TYPE_TRACING test_main linked:[650->25: BPF_TRAMP_FEXIT test_pkt_access->test_pkt_access()]
655: BPF_PROG_TYPE_TRACING test_subprog1 linked:[650->29: BPF_TRAMP_FEXIT test_pkt_access->test_pkt_access_subprog1()]
656: BPF_PROG_TYPE_TRACING test_subprog2 linked:[650->31: BPF_TRAMP_FEXIT test_pkt_access->test_pkt_access_subprog2()]
657: BPF_PROG_TYPE_TRACING test_subprog3 linked:[650->21: BPF_TRAMP_FEXIT test_pkt_access->test_pkt_access_subprog3()]
658: BPF_PROG_TYPE_EXT new_get_skb_len linked:[650->16: BPF_TRAMP_REPLACE test_pkt_access->get_skb_len()]
659: BPF_PROG_TYPE_EXT new_get_skb_ifindex linked:[650->23: BPF_TRAMP_REPLACE test_pkt_access->get_skb_ifindex()]
660: BPF_PROG_TYPE_EXT new_get_constant linked:[650->19: BPF_TRAMP_REPLACE test_pkt_access->get_constant()]
It can be seen that there is a program ``test_pkt_access``, id 650 and there
are multiple other tracing and ext programs attached to functions in
``test_pkt_access``.
For example the line::
658: BPF_PROG_TYPE_EXT new_get_skb_len linked:[650->16: BPF_TRAMP_REPLACE test_pkt_access->get_skb_len()]
, means that BPF program id 658, type ``BPF_PROG_TYPE_EXT``, name
``new_get_skb_len`` replaces (``BPF_TRAMP_REPLACE``) function ``get_skb_len()``
that has BTF id 16 in BPF program id 650, name ``test_pkt_access``.
Getting help:
.. code-block:: none
% sudo bpf_inspect.py
usage: bpf_inspect.py [-h] {prog,p,map,m} ...
drgn script to list BPF programs or maps and their properties
unavailable via kernel API.
See https://github.com/osandov/drgn/ for more details on drgn.
optional arguments:
-h, --help show this help message and exit
subcommands:
{prog,p,map,m}
prog (p) list BPF programs
map (m) list BPF maps
Customization
=============
The script is intended to be customized by developers to print relevant
information about BPF programs, maps and other objects.
For example, to print ``struct bpf_prog_aux`` for BPF program id 53077:
.. code-block:: none
% git diff
diff --git a/tools/bpf_inspect.py b/tools/bpf_inspect.py
index 650e228..aea2357 100755
--- a/tools/bpf_inspect.py
+++ b/tools/bpf_inspect.py
@@ -112,7 +112,9 @@ def list_bpf_progs(args):
if linked:
linked = f" linked:[{linked}]"
- print(f"{id_:>6}: {type_:32} {name:32} {linked}")
+ if id_ == 53077:
+ print(f"{id_:>6}: {type_:32} {name:32}")
+ print(f"{bpf_prog.aux}")
def list_bpf_maps(args):
It produces the output::
% sudo bpf_inspect.py p
53077: BPF_PROG_TYPE_XDP tw_xdp_policer
*(struct bpf_prog_aux *)0xffff8893fad4b400 = {
.refcnt = (atomic64_t){
.counter = (long)58,
},
.used_map_cnt = (u32)1,
.max_ctx_offset = (u32)8,
.max_pkt_offset = (u32)15,
.max_tp_access = (u32)0,
.stack_depth = (u32)8,
.id = (u32)53077,
.func_cnt = (u32)0,
.func_idx = (u32)0,
.attach_btf_id = (u32)0,
.linked_prog = (struct bpf_prog *)0x0,
.verifier_zext = (bool)0,
.offload_requested = (bool)0,
.attach_btf_trace = (bool)0,
.func_proto_unreliable = (bool)0,
.trampoline_prog_type = (enum bpf_tramp_prog_type)BPF_TRAMP_FENTRY,
.trampoline = (struct bpf_trampoline *)0x0,
.tramp_hlist = (struct hlist_node){
.next = (struct hlist_node *)0x0,
.pprev = (struct hlist_node **)0x0,
},
.attach_func_proto = (const struct btf_type *)0x0,
.attach_func_name = (const char *)0x0,
.func = (struct bpf_prog **)0x0,
.jit_data = (void *)0x0,
.poke_tab = (struct bpf_jit_poke_descriptor *)0x0,
.size_poke_tab = (u32)0,
.ksym_tnode = (struct latch_tree_node){
.node = (struct rb_node [2]){
{
.__rb_parent_color = (unsigned long)18446612956263126665,
.rb_right = (struct rb_node *)0x0,
.rb_left = (struct rb_node *)0xffff88a0be3d0088,
},
{
.__rb_parent_color = (unsigned long)18446612956263126689,
.rb_right = (struct rb_node *)0x0,
.rb_left = (struct rb_node *)0xffff88a0be3d00a0,
},
},
},
.ksym_lnode = (struct list_head){
.next = (struct list_head *)0xffff88bf481830b8,
.prev = (struct list_head *)0xffff888309f536b8,
},
.ops = (const struct bpf_prog_ops *)xdp_prog_ops+0x0 = 0xffffffff820fa350,
.used_maps = (struct bpf_map **)0xffff889ff795de98,
.prog = (struct bpf_prog *)0xffffc9000cf2d000,
.user = (struct user_struct *)root_user+0x0 = 0xffffffff82444820,
.load_time = (u64)2408348759285319,
.cgroup_storage = (struct bpf_map *[2]){},
.name = (char [16])"tw_xdp_policer",
.security = (void *)0xffff889ff795d548,
.offload = (struct bpf_prog_offload *)0x0,
.btf = (struct btf *)0xffff8890ce6d0580,
.func_info = (struct bpf_func_info *)0xffff889ff795d240,
.func_info_aux = (struct bpf_func_info_aux *)0xffff889ff795de20,
.linfo = (struct bpf_line_info *)0xffff888a707afc00,
.jited_linfo = (void **)0xffff8893fad48600,
.func_info_cnt = (u32)1,
.nr_linfo = (u32)37,
.linfo_idx = (u32)0,
.num_exentries = (u32)0,
.extable = (struct exception_table_entry *)0xffffffffa032d950,
.stats = (struct bpf_prog_stats *)0x603fe3a1f6d0,
.work = (struct work_struct){
.data = (atomic_long_t){
.counter = (long)0,
},
.entry = (struct list_head){
.next = (struct list_head *)0x0,
.prev = (struct list_head *)0x0,
},
.func = (work_func_t)0x0,
},
.rcu = (struct callback_head){
.next = (struct callback_head *)0x0,
.func = (void (*)(struct callback_head *))0x0,
},
}
.. Links
.. _drgn/doc: https://drgn.readthedocs.io/en/latest/
.. _drgn/tools: https://github.com/osandov/drgn/tree/master/tools
.. _bpf_inspect.py:
https://github.com/osandov/drgn/blob/master/tools/bpf_inspect.py

Some files were not shown because too many files have changed in this diff Show More