diff --git a/.mailmap b/.mailmap index b78aa092b4bb..eec4a740f7ca 100644 --- a/.mailmap +++ b/.mailmap @@ -682,6 +682,7 @@ Peter A Jonsson Peter Hilber Peter Oruba Peter Oruba +Peter Rosin Pierre-Louis Bossart Pratyush Anand Pratyush Yadav diff --git a/Documentation/devicetree/bindings/i2c/amlogic,meson6-i2c.yaml b/Documentation/devicetree/bindings/i2c/amlogic,meson6-i2c.yaml index c4cc8af18280..7b59b60b62e5 100644 --- a/Documentation/devicetree/bindings/i2c/amlogic,meson6-i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/amlogic,meson6-i2c.yaml @@ -16,10 +16,15 @@ allOf: properties: compatible: - enum: - - amlogic,meson6-i2c # Meson6, Meson8 and compatible SoCs - - amlogic,meson-gxbb-i2c # GXBB and compatible SoCs - - amlogic,meson-axg-i2c # AXG and compatible SoCs + oneOf: + - items: + - enum: + - amlogic,t7-i2c + - const: amlogic,meson-axg-i2c + - enum: + - amlogic,meson6-i2c # Meson6, Meson8 and compatible SoCs + - amlogic,meson-gxbb-i2c # GXBB and compatible SoCs + - amlogic,meson-axg-i2c # AXG and compatible SoCs reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml index 500a965bdb7a..9e59200ad37b 100644 --- a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml @@ -22,7 +22,9 @@ properties: compatible: oneOf: - items: - - const: apple,t6020-i2c + - enum: + - apple,t6020-i2c + - apple,t8122-i2c - const: apple,t8103-i2c - items: - enum: diff --git a/Documentation/hwmon/yogafan.rst b/Documentation/hwmon/yogafan.rst index c553a381f772..68761947a1a8 100644 --- a/Documentation/hwmon/yogafan.rst +++ b/Documentation/hwmon/yogafan.rst @@ -135,4 +135,4 @@ References 4. **Lenovo IdeaPad Laptop Driver:** Reference for DMI-based hardware feature gating in Lenovo laptops. - https://github.com/torvalds/linux/blob/master/drivers/platform/x86/ideapad-laptop.c + https://github.com/torvalds/linux/blob/master/drivers/platform/x86/lenovo/ideapad-laptop.c diff --git a/Documentation/userspace-api/rseq.rst b/Documentation/userspace-api/rseq.rst index 3cd27a3c7c7e..8549a6c61531 100644 --- a/Documentation/userspace-api/rseq.rst +++ b/Documentation/userspace-api/rseq.rst @@ -24,6 +24,97 @@ Quick access to CPU number, node ID Allows to implement per CPU data efficiently. Documentation is in code and selftests. :( +Optimized RSEQ V2 +----------------- + +On architectures which utilize the generic entry code and generic TIF bits +the kernel supports runtime optimizations for RSEQ, which also enable +enhanced features like scheduler time slice extensions. + +To enable them a task has to register the RSEQ region with at least the +length advertised by getauxval(AT_RSEQ_FEATURE_SIZE). + +If existing binaries register with RSEQ_ORIG_SIZE (32 bytes), the kernel +keeps the legacy low performance mode enabled to fulfil the expectations +of existing users regarding the original RSEQ implementation behaviour. + +The following table documents the ABI and behavioral guarantees of the +legacy and the optimized V2 mode. + +.. list-table:: RSEQ modes + :header-rows: 1 + + * - Nr + - What + + - Legacy + - Optimized V2 + + * - 1 + - The cpu_id_start, cpu_id, node_id and mm_cid fields (User mode read + only) + .. Legacy + - Updated by the kernel unconditionally after each context switch and + before signal delivery + .. Optimized V2 + - Updated by the kernel if and only if they change, i.e. if the task + is migrated or mm_cid changes + + * - 2 + - The rseq_cs critical section field + .. Legacy + - Evaluated and handled unconditionally after each context switch and + before signal delivery + .. Optimized V2 + - Evaluated and handled conditionally only when user space was + interrupted and was scheduled out or before delivering a signal in + the interrupted context. + + * - 3 + - Read only fields + .. Legacy + - No strict enforcement except in debug mode + .. Optimized V2 + - Strict enforcement + + * - 4 + - membarrier(...RSEQ) + .. Legacy + - All running threads of the process are interrupted and the ID fields + are rewritten and eventually active critical sections are aborted + before they return to user space. All threads which are scheduled + out whether voluntary or not are covered by #1/#2 above. + .. Optimized V2 + - All running threads of the process are interrupted and eventually + active critical sections are aborted before these threads return to + user space. The ID fields are only updated if changed as a + consequence of the interrupt. All threads which are scheduled out + whether voluntary or not are covered by #1/#2 above. + + * - 5 + - Time slice extensions + .. Legacy + - Not supported + .. Optimized V2 + - Supported + +The legacy mode is obviously less performant as it does unconditional +updates and critical section checks even if not strictly required by the +ABI contract. That can't be changed anymore as some users depend on that +observed behavior, which in turn enables them to violate the ABI and +overwrite the cpu_id_start field for their own purposes. This is obviously +discouraged as it renders RSEQ incompatible with the intended usage and +breaks the expectation of other libraries in the same application. + +The ABI compliant optimized v2 mode, which respects the read only fields, +does not require unconditional updates and therefore is way more +performant. The kernel validates the read only fields for compliance. If +user space modifies them, the process is killed. Compliant usage allows +multiple libraries in the same application to benefit from the RSEQ +functionality without disturbing each other. The ABI compliant optimized v2 +mode also enables extended RSEQ features like time slice extensions. + + Scheduler time slice extensions ------------------------------- @@ -37,7 +128,8 @@ The prerequisites for this functionality are: * Enabled at boot time (default is enabled) - * A rseq userspace pointer has been registered for the thread + * A rseq userspace pointer has been registered for the thread in + optimized V2 mode The thread has to enable the functionality via prctl(2):: diff --git a/MAINTAINERS b/MAINTAINERS index c634665b8c33..eaf07c3898ba 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4299,18 +4299,16 @@ F: Documentation/devicetree/bindings/leds/backlight/awinic,aw99706.yaml F: drivers/video/backlight/aw99706.c AXENTIA ARM DEVICES -M: Peter Rosin L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained +S: Orphan F: arch/arm/boot/dts/microchip/at91-linea.dtsi F: arch/arm/boot/dts/microchip/at91-natte.dtsi F: arch/arm/boot/dts/microchip/at91-nattis-2-natte-2.dts F: arch/arm/boot/dts/microchip/at91-tse850-3.dts AXENTIA ASOC DRIVERS -M: Peter Rosin L: linux-sound@vger.kernel.org -S: Maintained +S: Orphan F: Documentation/devicetree/bindings/sound/axentia,* F: sound/soc/atmel/tse850-pcm5142.c @@ -12051,7 +12049,7 @@ F: Documentation/i2c/busses/i2c-nvidia-gpu.rst F: drivers/i2c/busses/i2c-nvidia-gpu.c I2C MUXES -M: Peter Rosin +M: Peter Rosin L: linux-i2c@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/i2c/i2c-arb* @@ -12452,7 +12450,7 @@ F: drivers/iio/industrialio-backend.c F: include/linux/iio/backend.h IIO DIGITAL POTENTIOMETER DAC -M: Peter Rosin +M: Peter Rosin L: linux-iio@vger.kernel.org S: Maintained F: Documentation/ABI/testing/sysfs-bus-iio-dac-dpot-dac @@ -12460,7 +12458,7 @@ F: Documentation/devicetree/bindings/iio/dac/dpot-dac.yaml F: drivers/iio/dac/dpot-dac.c IIO ENVELOPE DETECTOR -M: Peter Rosin +M: Peter Rosin L: linux-iio@vger.kernel.org S: Maintained F: Documentation/ABI/testing/sysfs-bus-iio-adc-envelope-detector @@ -12476,7 +12474,7 @@ F: include/linux/iio/iio-gts-helper.h F: drivers/iio/test/iio-test-gts.c IIO MULTIPLEXER -M: Peter Rosin +M: Peter Rosin L: linux-iio@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/iio/multiplexer/io-channel-mux.yaml @@ -12507,7 +12505,7 @@ F: include/linux/iio/ F: tools/iio/ IIO UNIT CONVERTER -M: Peter Rosin +M: Peter Rosin L: linux-iio@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/iio/afe/current-sense-amplifier.yaml @@ -15730,7 +15728,7 @@ F: Documentation/devicetree/bindings/media/i2c/maxim,max96717.yaml F: drivers/media/i2c/max96717.c MAX9860 MONO AUDIO VOICE CODEC DRIVER -M: Peter Rosin +M: Peter Rosin L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/max9860.txt @@ -15945,7 +15943,7 @@ F: Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml F: drivers/net/can/spi/mcp251xfd/ MCP4018 AND MCP4531 MICROCHIP DIGITAL POTENTIOMETER DRIVERS -M: Peter Rosin +M: Peter Rosin L: linux-iio@vger.kernel.org S: Maintained F: Documentation/ABI/testing/sysfs-bus-iio-potentiometer-mcp4531 @@ -18250,7 +18248,7 @@ F: include/linux/mmc/ F: include/uapi/linux/mmc/ MULTIPLEXER SUBSYSTEM -M: Peter Rosin +M: Peter Rosin S: Odd Fixes F: Documentation/ABI/testing/sysfs-class-mux* F: Documentation/devicetree/bindings/mux/ @@ -19359,7 +19357,7 @@ F: include/dt-bindings/display/tda998x.h K: "nxp,tda998x" NXP TFA9879 DRIVER -M: Peter Rosin +M: Peter Rosin L: linux-sound@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/sound/trivial-codec.yaml diff --git a/Makefile b/Makefile index 8939cc0b0b88..55d3cfe16a71 100644 --- a/Makefile +++ b/Makefile @@ -504,6 +504,8 @@ export rust_common_flags := --edition=2021 \ -Wclippy::as_ptr_cast_mut \ -Wclippy::as_underscore \ -Wclippy::cast_lossless \ + -Aclippy::collapsible_if \ + -Aclippy::collapsible_match \ -Wclippy::ignored_unit_patterns \ -Aclippy::incompatible_msrv \ -Wclippy::mut_mut \ diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig index 69ef3dc31c4b..7a515390646b 100644 --- a/arch/powerpc/configs/amigaone_defconfig +++ b/arch/powerpc/configs/amigaone_defconfig @@ -76,7 +76,6 @@ CONFIG_SERIAL_8250_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_RADEON=y CONFIG_FB_3DFX=y diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig index b799c95480ae..66eae5b7e16c 100644 --- a/arch/powerpc/configs/chrp32_defconfig +++ b/arch/powerpc/configs/chrp32_defconfig @@ -76,7 +76,6 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_NVRAM=y # CONFIG_HWMON is not set CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_OF=y CONFIG_FB_MATROX=y CONFIG_FB_MATROX_MILLENIUM=y diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index 04bbb37f5978..e9996711b362 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -121,7 +121,6 @@ CONFIG_I2C_CHARDEV=y CONFIG_AGP=m CONFIG_AGP_UNINORTH=m CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_OF=y CONFIG_FB_NVIDIA=y diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index 8bbf51b38480..89bcbeb05067 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -98,7 +98,6 @@ CONFIG_SENSORS_LM85=y CONFIG_SENSORS_LM90=y CONFIG_DRM=y CONFIG_DRM_RADEON=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_VGA16=y CONFIG_FB_NVIDIA=y diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index cc9802420237..5d32c2767a65 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -196,7 +196,6 @@ CONFIG_I2C_CHARDEV=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_DRM=y CONFIG_DRM_AST=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_OF=y CONFIG_FB_MATROX=m CONFIG_FB_MATROX_MILLENIUM=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 3bf518e3a573..6316ca4df25d 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -249,7 +249,6 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_AMD8111=y CONFIG_I2C_PASEMI=y CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_OF=y CONFIG_FB_MATROX=y CONFIG_FB_MATROX_MILLENIUM=y diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 0fd49f67331f..20cc17dce94d 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -118,7 +118,6 @@ CONFIG_SERIAL_8250_CONSOLE=y CONFIG_I2C_CHARDEV=y CONFIG_I2C_AMD8111=y CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y CONFIG_FB_OF=y CONFIG_FB_MATROX=y CONFIG_FB_MATROX_MILLENIUM=y diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index ff1bed4b6d2c..005536ee75bb 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -214,7 +214,6 @@ CONFIG_SENSORS_IBMPOWERNV=m CONFIG_DRM=m CONFIG_DRM_AST=m CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y # CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index 8834dfe9d727..368759f81708 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -62,6 +62,12 @@ CC32FLAGSREMOVE += -fno-stack-clash-protection # 32-bit one. clang validates the values passed to these arguments during # parsing, even when -fno-stack-protector is passed afterwards. CC32FLAGSREMOVE += -mstack-protector-guard% +# ftrace is disabled for the vdso but arch/powerpc/Makefile adds this define to +# KBUILD_CPPFLAGS, which enables use of the 'patchable_function_entry' +# attribute in the 'inline' define via 'notrace'. This attribute is not +# supported for the powerpcle target, resulting in many instances of +# -Wunknown-attributes. +CC32FLAGSREMOVE += -DCC_USING_PATCHABLE_FUNCTION_ENTRY endif LD32FLAGS := -Wl,-soname=linux-vdso32.so.1 AS32FLAGS := -D__VDSO32__ diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile index 470eb0453e17..ec7a0eed75dc 100644 --- a/arch/powerpc/kexec/Makefile +++ b/arch/powerpc/kexec/Makefile @@ -16,4 +16,4 @@ GCOV_PROFILE_core_$(BITS).o := n KCOV_INSTRUMENT_core_$(BITS).o := n UBSAN_SANITIZE_core_$(BITS).o := n KASAN_SANITIZE_core.o := n -KASAN_SANITIZE_core_$(BITS) := n +KASAN_SANITIZE_core_$(BITS).o := n diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index 554b248002b4..57e897b60db8 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -52,7 +52,14 @@ int exit_vmx_usercopy(void) } EXPORT_SYMBOL(exit_vmx_usercopy); -int enter_vmx_ops(void) +/* + * Can be called from kexec copy_page() path with MMU off. The kexec + * code sets preempt_count to HARDIRQ_OFFSET so we return early here. + * Since in_interrupt() is always inline, __no_sanitize_address on this + * function is sufficient to avoid KASAN shadow memory accesses in real + * mode. + */ +int __no_sanitize_address enter_vmx_ops(void) { if (in_interrupt()) return 0; diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 8b0081441f85..2e6adf5b95c4 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -2242,6 +2242,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val, const u64 last_period = event->hw.last_period; s64 prev, delta, left; int record = 0; + int mark_event = regs->dsisr & MMCRA_SAMPLE_ENABLE; if (event->hw.state & PERF_HES_STOPPED) { write_pmc(event->hw.idx, 0); @@ -2304,9 +2305,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val, * In ISA v3.0 and before values "0" and "7" are considered reserved. * In ISA v3.1, value "7" has been used to indicate "larx/stcx". * Drop the sample if "type" has reserved values for this field with a - * ISA version check. + * ISA version check for marked events. */ - if (event->attr.sample_type & PERF_SAMPLE_DATA_SRC && + if (mark_event && event->attr.sample_type & PERF_SAMPLE_DATA_SRC && ppmu->get_mem_data_src) { val = (regs->dar & SIER_TYPE_MASK) >> SIER_TYPE_SHIFT; if (val == 0 || (val == 7 && !cpu_has_feature(CPU_FTR_ARCH_31))) { diff --git a/arch/powerpc/platforms/8xx/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c index 7433be7d66ee..f00734f0590c 100644 --- a/arch/powerpc/platforms/8xx/cpm1.c +++ b/arch/powerpc/platforms/8xx/cpm1.c @@ -477,7 +477,7 @@ int cpm1_gpiochip_add16(struct device *dev) struct device_node *np = dev->of_node; struct cpm1_gpio16_chip *cpm1_gc; struct gpio_chip *gc; - u16 mask; + u32 mask; cpm1_gc = devm_kzalloc(dev, sizeof(*cpm1_gc), GFP_KERNEL); if (!cpm1_gc) @@ -485,7 +485,7 @@ int cpm1_gpiochip_add16(struct device *dev) spin_lock_init(&cpm1_gc->lock); - if (!of_property_read_u16(np, "fsl,cpm1-gpio-irq-mask", &mask)) { + if (!of_property_read_u32(np, "fsl,cpm1-gpio-irq-mask", &mask)) { int i, j; for (i = 0, j = 0; i < 16; i++) diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c index 60f990a336c4..2df955274652 100644 --- a/arch/powerpc/platforms/pasemi/pci.c +++ b/arch/powerpc/platforms/pasemi/pci.c @@ -272,13 +272,12 @@ void __init pas_pci_init(void) { struct device_node *root = of_find_node_by_path("/"); struct device_node *np; - int res; pci_set_flags(PCI_SCAN_ALL_PCIE_DEVS); np = of_find_compatible_node(root, NULL, "pasemi,rootbus"); if (np) { - res = pas_add_bridge(np); + pas_add_bridge(np); of_node_put(np); } of_node_put(root); diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c index 12c473768c39..9109c218a060 100644 --- a/arch/powerpc/platforms/ps3/device-init.c +++ b/arch/powerpc/platforms/ps3/device-init.c @@ -950,8 +950,6 @@ static int __init ps3_start_probe_thread(enum ps3_bus_type bus_type) static int __init ps3_register_devices(void) { - int result; - if (!firmware_has_feature(FW_FEATURE_PS3_LV1)) return -ENODEV; @@ -959,7 +957,7 @@ static int __init ps3_register_devices(void) /* ps3_repository_dump_bus_info(); */ - result = ps3_start_probe_thread(PS3_BUS_TYPE_STORAGE); + ps3_start_probe_thread(PS3_BUS_TYPE_STORAGE); ps3_register_vuart_devices(); diff --git a/arch/powerpc/platforms/pseries/htmdump.c b/arch/powerpc/platforms/pseries/htmdump.c index 742ec52c9d4d..489a80e87082 100644 --- a/arch/powerpc/platforms/pseries/htmdump.c +++ b/arch/powerpc/platforms/pseries/htmdump.c @@ -16,6 +16,7 @@ static void *htm_buf; static void *htm_status_buf; static void *htm_info_buf; static void *htm_caps_buf; +static void *htm_mem_buf; static u32 nodeindex; static u32 nodalchipindex; static u32 coreindexonchip; @@ -86,7 +87,7 @@ static ssize_t htm_return_check(long rc) static ssize_t htmdump_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - void *htm_buf = filp->private_data; + void *htm_buf_data = filp->private_data; unsigned long page, read_size, available; loff_t offset; long rc, ret; @@ -100,7 +101,7 @@ static ssize_t htmdump_read(struct file *filp, char __user *ubuf, * - last three values are address, size and offset */ rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip, - htmtype, H_HTM_OP_DUMP_DATA, virt_to_phys(htm_buf), + htmtype, H_HTM_OP_DUMP_DATA, virt_to_phys(htm_buf_data), PAGE_SIZE, page); ret = htm_return_check(rc); @@ -112,7 +113,61 @@ static ssize_t htmdump_read(struct file *filp, char __user *ubuf, available = PAGE_SIZE; read_size = min(count, available); *ppos += read_size; - return simple_read_from_buffer(ubuf, count, &offset, htm_buf, available); + return simple_read_from_buffer(ubuf, count, &offset, htm_buf_data, available); +} + +static ssize_t htmsystem_mem_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + void *htm_mem_data = filp->private_data; + long rc, ret; + u64 *num_entries; + u64 to_copy = 0; + loff_t offset = 0; + u64 mem_offset = 0; + + /* + * Invoke H_HTM call with: + * - operation as htm status (H_HTM_OP_STATUS) + * - last three values as addr, size and offset. "offset" + * is value from output buffer header that points to next + * entry to dump. 0 is the first entry to dump. next entry + * is read from the output bufferbyte offset 0x8. + * + * When first time hcall is invoked, mem_offset should be + * zero because zero is the first entry. + * In the next hcall, offset of next entry to read from is + * picked from output buffer header itself. So don't fill + * mem_offset for first read. + * + * If there is no further data to read in next iteration, + * offset value from output buffer header will point to -1. + */ + if (*ppos) { + mem_offset = *(u64 *)(htm_mem_data + 0x8); + if (mem_offset == -1) + return 0; + } + rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip, + htmtype, H_HTM_OP_DUMP_SYSMEM_CONF, virt_to_phys(htm_mem_data), + PAGE_SIZE, be64_to_cpu(mem_offset)); + ret = htm_return_check(rc); + if (ret <= 0) { + pr_debug("H_HTM hcall returned for op: H_HTM_OP_DUMP_SYSMEM_CONF with hcall returning %ld\n", ret); + return ret; + } + + /* + * HTM system mem buffer, start of buffer + 0x10 gives the + * number of HTM entries in the buffer. + * So total count to copy is: + * 32 bytes (for first 5 fields) + (number of HTM entries * entry size) + */ + num_entries = htm_mem_data + 0x10; + to_copy = 32 + (be64_to_cpu(*num_entries) * 32); + + *ppos += to_copy; + return simple_read_from_buffer(ubuf, count, &offset, htm_mem_data, to_copy); } static const struct file_operations htmdump_fops = { @@ -121,6 +176,12 @@ static const struct file_operations htmdump_fops = { .open = simple_open, }; +static const struct file_operations htmsystem_mem_fops = { + .llseek = NULL, + .read = htmsystem_mem_read, + .open = simple_open, +}; + static int htmconfigure_set(void *data, u64 val) { long rc, ret; @@ -226,20 +287,31 @@ static int htmstart_get(void *data, u64 *val) static ssize_t htmstatus_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - void *htm_status_buf = filp->private_data; + void *htm_status_data = filp->private_data; long rc, ret; u64 *num_entries; u64 to_copy; int htmstatus_flag; + loff_t offset = 0; + u64 status_offset = 0; /* * Invoke H_HTM call with: * - operation as htm status (H_HTM_OP_STATUS) - * - last three values as addr, size and offset + * - last three values as addr, size and offset. + * "offset" is value from output buffer header + * that points to next entry to dump. 0 is the first + * entry to dump. next entry is read from the output + * bufferbyte offset 0x8. */ + if (*ppos) { + status_offset = *(u64 *)(htm_status_data + 0x8); + if (status_offset == -1) + return 0; + } rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip, - htmtype, H_HTM_OP_STATUS, virt_to_phys(htm_status_buf), - PAGE_SIZE, 0); + htmtype, H_HTM_OP_STATUS, virt_to_phys(htm_status_data), + PAGE_SIZE, be64_to_cpu(status_offset)); ret = htm_return_check(rc); if (ret <= 0) { @@ -255,13 +327,15 @@ static ssize_t htmstatus_read(struct file *filp, char __user *ubuf, * So total count to copy is: * 32 bytes (for first 7 fields) + (number of HTM entries * entry size) */ - num_entries = htm_status_buf + 0x10; + num_entries = htm_status_data + 0x10; if (htmtype == 0x2) htmstatus_flag = 0x8; else htmstatus_flag = 0x6; to_copy = 32 + (be64_to_cpu(*num_entries) * htmstatus_flag); - return simple_read_from_buffer(ubuf, count, ppos, htm_status_buf, to_copy); + *ppos += to_copy; + + return simple_read_from_buffer(ubuf, count, &offset, htm_status_data, to_copy); } static const struct file_operations htmstatus_fops = { @@ -273,19 +347,30 @@ static const struct file_operations htmstatus_fops = { static ssize_t htminfo_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - void *htm_info_buf = filp->private_data; + void *htm_info_data = filp->private_data; long rc, ret; u64 *num_entries; u64 to_copy; + loff_t offset = 0; + u64 info_offset = 0; /* * Invoke H_HTM call with: * - operation as htm status (H_HTM_OP_STATUS) * - last three values as addr, size and offset + * "offset" is value from output buffer header + * that points to next entry to dump. 0 is the first + * entry to dump. next entry is read from the output + * bufferbyte offset 0x8. */ + if (*ppos) { + info_offset = *(u64 *)(htm_info_data + 0x8); + if (info_offset == -1) + return 0; + } rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip, - htmtype, H_HTM_OP_DUMP_SYSPROC_CONF, virt_to_phys(htm_info_buf), - PAGE_SIZE, 0); + htmtype, H_HTM_OP_DUMP_SYSPROC_CONF, virt_to_phys(htm_info_data), + PAGE_SIZE, be64_to_cpu(info_offset)); ret = htm_return_check(rc); if (ret <= 0) { @@ -301,15 +386,17 @@ static ssize_t htminfo_read(struct file *filp, char __user *ubuf, * So total count to copy is: * 32 bytes (for first 5 fields) + (number of HTM entries * entry size) */ - num_entries = htm_info_buf + 0x10; + num_entries = htm_info_data + 0x10; to_copy = 32 + (be64_to_cpu(*num_entries) * 16); - return simple_read_from_buffer(ubuf, count, ppos, htm_info_buf, to_copy); + + *ppos += to_copy; + return simple_read_from_buffer(ubuf, count, &offset, htm_info_data, to_copy); } static ssize_t htmcaps_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { - void *htm_caps_buf = filp->private_data; + void *htm_caps_data = filp->private_data; long rc, ret; /* @@ -319,7 +406,7 @@ static ssize_t htmcaps_read(struct file *filp, char __user *ubuf, * and zero */ rc = htm_hcall_wrapper(htmflags, nodeindex, nodalchipindex, coreindexonchip, - htmtype, H_HTM_OP_CAPABILITIES, virt_to_phys(htm_caps_buf), + htmtype, H_HTM_OP_CAPABILITIES, virt_to_phys(htm_caps_data), 0x80, 0); ret = htm_return_check(rc); @@ -328,7 +415,7 @@ static ssize_t htmcaps_read(struct file *filp, char __user *ubuf, return ret; } - return simple_read_from_buffer(ubuf, count, ppos, htm_caps_buf, 0x80); + return simple_read_from_buffer(ubuf, count, ppos, htm_caps_data, 0x80); } static const struct file_operations htminfo_fops = { @@ -457,9 +544,17 @@ static int htmdump_init_debugfs(void) return -ENOMEM; } + /* Memory to present HTM system memory configuration */ + htm_mem_buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!htm_mem_buf) { + pr_err("Failed to allocate htm mem buf\n"); + return -ENOMEM; + } + debugfs_create_file("htmstatus", 0400, htmdump_debugfs_dir, htm_status_buf, &htmstatus_fops); debugfs_create_file("htminfo", 0400, htmdump_debugfs_dir, htm_info_buf, &htminfo_fops); debugfs_create_file("htmcaps", 0400, htmdump_debugfs_dir, htm_caps_buf, &htmcaps_fops); + debugfs_create_file("htmsystem_mem", 0400, htmdump_debugfs_dir, htm_mem_buf, &htmsystem_mem_fops); return 0; } @@ -482,6 +577,10 @@ static void __exit htmdump_exit(void) { debugfs_remove_recursive(htmdump_debugfs_dir); kfree(htm_buf); + kfree(htm_status_buf); + kfree(htm_info_buf); + kfree(htm_caps_buf); + kfree(htm_mem_buf); } module_init(htmdump_init); diff --git a/arch/powerpc/platforms/pseries/papr-hvpipe.c b/arch/powerpc/platforms/pseries/papr-hvpipe.c index 14ae480d060a..0c40bdde45e2 100644 --- a/arch/powerpc/platforms/pseries/papr-hvpipe.c +++ b/arch/powerpc/platforms/pseries/papr-hvpipe.c @@ -190,33 +190,34 @@ static int hvpipe_rtas_recv_msg(char __user *buf, int size) return -ENOMEM; } - ret = rtas_ibm_receive_hvpipe_msg(work_area, &srcID, - &bytes_written); - if (!ret) { - /* - * Recv HVPIPE RTAS is successful. - * When releasing FD or no one is waiting on the - * specific source, issue recv HVPIPE RTAS call - * so that pipe is not blocked - this func is called - * with NULL buf. - */ - if (buf) { - if (size < bytes_written) { - pr_err("Received the payload size = %d, but the buffer size = %d\n", - bytes_written, size); - bytes_written = size; - } - ret = copy_to_user(buf, - rtas_work_area_raw_buf(work_area), - bytes_written); - if (!ret) - ret = bytes_written; - } - } else { - pr_err("ibm,receive-hvpipe-msg failed with %d\n", - ret); + /* + * Recv HVPIPE RTAS is successful. + * When releasing FD or no one is waiting on the + * specific source, issue recv HVPIPE RTAS call + * so that pipe is not blocked - this func is called + * with NULL buf. + */ + ret = rtas_ibm_receive_hvpipe_msg(work_area, &srcID, &bytes_written); + if (ret) { + pr_err("ibm,receive-hvpipe-msg failed with %d\n", ret); + goto out; } + if (!buf) + goto out; + + if (size < bytes_written) { + pr_err("Received the payload size = %d, but the buffer size = %d\n", + bytes_written, size); + bytes_written = size; + } + + if (copy_to_user(buf, rtas_work_area_raw_buf(work_area), bytes_written)) + ret = -EFAULT; + else + ret = bytes_written; + +out: rtas_work_area_free(work_area); return ret; } @@ -327,8 +328,8 @@ static ssize_t papr_hvpipe_handle_read(struct file *file, { struct hvpipe_source_info *src_info = file->private_data; - struct papr_hvpipe_hdr hdr; - long ret; + struct papr_hvpipe_hdr hdr = {}; + ssize_t ret = 0; /* * Return -ENXIO during migration @@ -376,7 +377,7 @@ static ssize_t papr_hvpipe_handle_read(struct file *file, ret = copy_to_user(buf, &hdr, HVPIPE_HDR_LEN); if (ret) - return ret; + return -EFAULT; /* * Message event has payload, so get the payload with @@ -385,19 +386,23 @@ static ssize_t papr_hvpipe_handle_read(struct file *file, if (hdr.flags & HVPIPE_MSG_AVAILABLE) { ret = hvpipe_rtas_recv_msg(buf + HVPIPE_HDR_LEN, size - HVPIPE_HDR_LEN); - if (ret > 0) { + /* + * Always clear MSG_AVAILABLE once the RTAS call has drained + * the message, regardless of whether copy_to_user succeeded. + */ + if (ret >= 0 || ret == -EFAULT) src_info->hvpipe_status &= ~HVPIPE_MSG_AVAILABLE; - ret += HVPIPE_HDR_LEN; - } } else if (hdr.flags & HVPIPE_LOST_CONNECTION) { /* * Hypervisor is closing the pipe for the specific * source. So notify user space. */ src_info->hvpipe_status &= ~HVPIPE_LOST_CONNECTION; - ret = HVPIPE_HDR_LEN; } + if (ret >= 0) + ret += HVPIPE_HDR_LEN; + return ret; } @@ -444,16 +449,18 @@ static int papr_hvpipe_handle_release(struct inode *inode, struct file *file) { struct hvpipe_source_info *src_info; + unsigned long flags; /* * Hold the lock, remove source from src_list, reset the * hvpipe status and release the lock to prevent any race * with message event IRQ. */ - spin_lock(&hvpipe_src_list_lock); + spin_lock_irqsave(&hvpipe_src_list_lock, flags); src_info = file->private_data; list_del(&src_info->list); file->private_data = NULL; + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); /* * If the pipe for this specific source has any pending * payload, issue recv HVPIPE RTAS so that pipe will not @@ -461,10 +468,8 @@ static int papr_hvpipe_handle_release(struct inode *inode, */ if (src_info->hvpipe_status & HVPIPE_MSG_AVAILABLE) { src_info->hvpipe_status = 0; - spin_unlock(&hvpipe_src_list_lock); hvpipe_rtas_recv_msg(NULL, 0); - } else - spin_unlock(&hvpipe_src_list_lock); + } kfree(src_info); return 0; @@ -479,50 +484,53 @@ static const struct file_operations papr_hvpipe_handle_ops = { static int papr_hvpipe_dev_create_handle(u32 srcID) { - struct hvpipe_source_info *src_info __free(kfree) = NULL; - - spin_lock(&hvpipe_src_list_lock); - /* - * Do not allow more than one process communicates with - * each source. - */ - src_info = hvpipe_find_source(srcID); - if (src_info) { - spin_unlock(&hvpipe_src_list_lock); - pr_err("pid(%d) is already using the source(%d)\n", - src_info->tsk->pid, srcID); - return -EALREADY; - } - spin_unlock(&hvpipe_src_list_lock); + struct hvpipe_source_info *src_info; + int fd; + unsigned long flags; src_info = kzalloc_obj(*src_info, GFP_KERNEL_ACCOUNT); if (!src_info) return -ENOMEM; src_info->srcID = srcID; - src_info->tsk = current; init_waitqueue_head(&src_info->recv_wqh); - FD_PREPARE(fdf, O_RDONLY | O_CLOEXEC, - anon_inode_getfile("[papr-hvpipe]", &papr_hvpipe_handle_ops, - (void *)src_info, O_RDWR)); - if (fdf.err) - return fdf.err; - - retain_and_null_ptr(src_info); - spin_lock(&hvpipe_src_list_lock); /* - * If two processes are executing ioctl() for the same - * source ID concurrently, prevent the second process to - * acquire FD. + * Do not allow more than one process communicates with + * each source. */ + spin_lock_irqsave(&hvpipe_src_list_lock, flags); if (hvpipe_find_source(srcID)) { - spin_unlock(&hvpipe_src_list_lock); + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); + pr_err("pid(%s:%d) could not get the source(%d)\n", + current->comm, task_pid_nr(current), srcID); + kfree(src_info); return -EALREADY; } list_add(&src_info->list, &hvpipe_src_list); - spin_unlock(&hvpipe_src_list_lock); - return fd_publish(fdf); + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); + + fd = FD_ADD(O_RDONLY | O_CLOEXEC, + anon_inode_getfile("[papr-hvpipe]", &papr_hvpipe_handle_ops, + (void *)src_info, O_RDWR)); + if (fd < 0) { + spin_lock_irqsave(&hvpipe_src_list_lock, flags); + list_del(&src_info->list); + spin_unlock_irqrestore(&hvpipe_src_list_lock, flags); + /* + * if we fail to add FD, that means no userspace program is + * polling. In that case if there is a msg pending because the + * interrupt was fired after the src_info was added to the + * global list, then let's consume it here, to unblock the + * hvpipe + */ + if (src_info->hvpipe_status & HVPIPE_MSG_AVAILABLE) + hvpipe_rtas_recv_msg(NULL, 0); + kfree(src_info); + return fd; + } + + return fd; } /* @@ -685,20 +693,19 @@ static int __init enable_hvpipe_IRQ(void) struct device_node *np; hvpipe_check_exception_token = rtas_function_token(RTAS_FN_CHECK_EXCEPTION); - if (hvpipe_check_exception_token == RTAS_UNKNOWN_SERVICE) + if (hvpipe_check_exception_token == RTAS_UNKNOWN_SERVICE) return -ENODEV; /* hvpipe events */ np = of_find_node_by_path("/event-sources/ibm,hvpipe-msg-events"); - if (np != NULL) { - request_event_sources_irqs(np, hvpipe_event_interrupt, - "HPIPE_EVENT"); - of_node_put(np); - } else { - pr_err("Can not enable hvpipe event IRQ\n"); + if (!np) { + pr_err("No device node found, could not enable hvpipe event IRQ\n"); return -ENODEV; } + request_event_sources_irqs(np, hvpipe_event_interrupt, "HPIPE_EVENT"); + of_node_put(np); + return 0; } @@ -775,23 +782,29 @@ static int __init papr_hvpipe_init(void) } ret = enable_hvpipe_IRQ(); - if (!ret) { - ret = set_hvpipe_sys_param(1); - if (!ret) - ret = misc_register(&papr_hvpipe_dev); - } + if (ret) + goto out_wq; - if (!ret) { - pr_info("hvpipe feature is enabled\n"); - hvpipe_feature = true; - return 0; - } + ret = misc_register(&papr_hvpipe_dev); + if (ret) + goto out_wq; - pr_err("hvpipe feature is not enabled %d\n", ret); + ret = set_hvpipe_sys_param(1); + if (ret) + goto out_misc; + + pr_info("hvpipe feature is enabled\n"); + hvpipe_feature = true; + return 0; + +out_misc: + misc_deregister(&papr_hvpipe_dev); +out_wq: destroy_workqueue(papr_hvpipe_wq); out: kfree(papr_hvpipe_work); papr_hvpipe_work = NULL; + pr_err("hvpipe feature is not enabled %d\n", ret); return ret; } machine_device_initcall(pseries, papr_hvpipe_init); diff --git a/arch/powerpc/platforms/pseries/papr-hvpipe.h b/arch/powerpc/platforms/pseries/papr-hvpipe.h index c343f4230865..4bdf7bb2fc4d 100644 --- a/arch/powerpc/platforms/pseries/papr-hvpipe.h +++ b/arch/powerpc/platforms/pseries/papr-hvpipe.h @@ -21,7 +21,6 @@ struct hvpipe_source_info { u32 srcID; u32 hvpipe_status; wait_queue_head_t recv_wqh; /* wake up poll() waitq */ - struct task_struct *tsk; }; /* diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 810ab21ffd99..4b9e105309c6 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1294,13 +1294,16 @@ int x86_perf_rdpmc_index(struct perf_event *event) return event->hw.event_base_rdpmc; } -static inline int match_prev_assignment(struct hw_perf_event *hwc, +static inline int match_prev_assignment(struct perf_event *event, struct cpu_hw_events *cpuc, int i) { + struct hw_perf_event *hwc = &event->hw; + return hwc->idx == cpuc->assign[i] && - hwc->last_cpu == smp_processor_id() && - hwc->last_tag == cpuc->tags[i]; + hwc->last_cpu == smp_processor_id() && + hwc->last_tag == cpuc->tags[i] && + !is_acr_event_group(event); } static void x86_pmu_start(struct perf_event *event, int flags); @@ -1346,7 +1349,7 @@ static void x86_pmu_enable(struct pmu *pmu) * - no other event has used the counter since */ if (hwc->idx == -1 || - match_prev_assignment(hwc, cpuc, i)) + match_prev_assignment(event, cpuc, i)) continue; /* @@ -1367,7 +1370,7 @@ static void x86_pmu_enable(struct pmu *pmu) event = cpuc->event_list[i]; hwc = &event->hw; - if (!match_prev_assignment(hwc, cpuc, i)) + if (!match_prev_assignment(event, cpuc, i)) x86_assign_hw_event(event, cpuc, i); else if (i < n_running) continue; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index d9488ade0f8e..dd1e3aa75ee9 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3118,11 +3118,11 @@ static void intel_pmu_enable_fixed(struct perf_event *event) intel_set_masks(event, idx); /* - * Enable IRQ generation (0x8), if not PEBS, - * and enable ring-3 counting (0x2) and ring-0 counting (0x1) - * if requested: + * Enable IRQ generation (0x8), if not PEBS or self-reloaded + * ACR event, and enable ring-3 counting (0x2) and ring-0 + * counting (0x1) if requested: */ - if (!event->attr.precise_ip) + if (!event->attr.precise_ip && !is_acr_self_reload_event(event)) bits |= INTEL_FIXED_0_ENABLE_PMI; if (hwc->config & ARCH_PERFMON_EVENTSEL_USR) bits |= INTEL_FIXED_0_USER; @@ -3306,6 +3306,15 @@ static void intel_pmu_enable_event(struct perf_event *event) intel_set_masks(event, idx); static_call_cond(intel_pmu_enable_acr_event)(event); static_call_cond(intel_pmu_enable_event_ext)(event); + /* + * For self-reloaded ACR event, don't enable PMI since + * HW won't set overflow bit in GLOBAL_STATUS. Otherwise, + * the PMI would be recognized as a suspicious NMI. + */ + if (is_acr_self_reload_event(event)) + hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; + else if (!event->attr.precise_ip) + hwc->config |= ARCH_PERFMON_EVENTSEL_INT; __x86_pmu_enable_event(hwc, enable_mask); break; case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1: @@ -3332,23 +3341,41 @@ static void intel_pmu_enable_event(struct perf_event *event) static void intel_pmu_acr_late_setup(struct cpu_hw_events *cpuc) { struct perf_event *event, *leader; - int i, j, idx; + int i, j, k, bit, idx; + /* + * FIXME: ACR mask parsing relies on cpuc->event_list[] (active events only). + * Disabling an ACR event causes bit-shifting errors in the acr_mask of + * remaining group members. As ACR sampling requires all events to be active, + * this limitation is acceptable for now. Revisit if independent event toggling + * is required. + */ for (i = 0; i < cpuc->n_events; i++) { leader = cpuc->event_list[i]; if (!is_acr_event_group(leader)) continue; - /* The ACR events must be contiguous. */ + /* Find the last event of the ACR group. */ for (j = i; j < cpuc->n_events; j++) { event = cpuc->event_list[j]; if (event->group_leader != leader->group_leader) break; - for_each_set_bit(idx, (unsigned long *)&event->attr.config2, X86_PMC_IDX_MAX) { - if (i + idx >= cpuc->n_events || - !is_acr_event_group(cpuc->event_list[i + idx])) - return; - __set_bit(cpuc->assign[i + idx], (unsigned long *)&event->hw.config1); + } + + /* + * Translate the user-space ACR mask (attr.config2) into the physical + * counter bitmask (hw.config1) for each ACR event in the group. + * NOTE: ACR event contiguity is guaranteed by intel_pmu_hw_config(). + */ + for (k = i; k < j; k++) { + event = cpuc->event_list[k]; + event->hw.config1 = 0; + for_each_set_bit(bit, (unsigned long *)&event->attr.config2, X86_PMC_IDX_MAX) { + idx = i + bit; + /* Event index of ACR group must locate in [i, j). */ + if (idx >= j || !is_acr_event_group(cpuc->event_list[idx])) + continue; + __set_bit(cpuc->assign[idx], (unsigned long *)&event->hw.config1); } } i = j - 1; @@ -7504,6 +7531,7 @@ static __always_inline void intel_pmu_init_pnc(struct pmu *pmu) hybrid(pmu, event_constraints) = intel_pnc_event_constraints; hybrid(pmu, pebs_constraints) = intel_pnc_pebs_event_constraints; hybrid(pmu, extra_regs) = intel_pnc_extra_regs; + static_call_update(intel_pmu_enable_acr_event, intel_pmu_enable_acr); } static __always_inline void intel_pmu_init_skt(struct pmu *pmu) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index fad87d3c8b2c..524668dcf4cc 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -137,6 +137,16 @@ static inline bool is_acr_event_group(struct perf_event *event) return check_leader_group(event->group_leader, PERF_X86_EVENT_ACR); } +static inline bool is_acr_self_reload_event(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + if (hwc->idx < 0) + return false; + + return test_bit(hwc->idx, (unsigned long *)&hwc->config1); +} + struct amd_nb { int nb_id; /* NorthBridge id */ int refcnt; /* reference count */ diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 2a9992758933..eb72537bc0b1 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -450,6 +450,10 @@ __init static int append_e820_table(struct boot_e820_entry *entries, u32 nr_entr { struct boot_e820_entry *entry = entries; + /* If there aren't any entries, we'll want to fall back to another source: */ + if (!nr_entries) + return -ENOENT; + while (nr_entries) { u64 start = entry->addr; u64 size = entry->size; @@ -458,7 +462,7 @@ __init static int append_e820_table(struct boot_e820_entry *entries, u32 nr_entr /* Ignore the remaining entries on 64-bit overflow: */ if (start > end && likely(size)) - return -1; + return -EINVAL; e820__range_add(start, size, type); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index ac8021c3a997..bb95a05259b8 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -695,17 +695,22 @@ static void __init xen_e820_resolve_conflicts(phys_addr_t start, return; end = start + size; - entry = xen_e820_table.entries; + mapcnt = 0; - for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) { + while (mapcnt < xen_e820_table.nr_entries) { + entry = xen_e820_table.entries + mapcnt; if (entry->addr >= end) return; if (entry->addr + entry->size > start && - entry->type == E820_TYPE_NVS) + entry->type == E820_TYPE_NVS) { xen_e820_swap_entry_with_ram(entry); + /* E820 map has been changed, restart loop! */ + mapcnt = 0; + continue; + } - entry++; + mapcnt++; } } diff --git a/drivers/android/binder/range_alloc/array.rs b/drivers/android/binder/range_alloc/array.rs index ada1d1b4302e..081d19b09d4b 100644 --- a/drivers/android/binder/range_alloc/array.rs +++ b/drivers/android/binder/range_alloc/array.rs @@ -204,7 +204,6 @@ impl ArrayRangeAllocator { // caller will mark them as unused, which means that they can be freed if the system comes // under memory pressure. let mut freed_range = FreedRange::interior_pages(offset, size); - #[expect(clippy::collapsible_if)] // reads better like this if offset % PAGE_SIZE != 0 { if i == 0 || self.ranges[i - 1].endpoint() <= (offset & PAGE_MASK) { freed_range.start_page_idx -= 1; diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile index 4788996aa137..982ee2c6f9de 100644 --- a/drivers/hwmon/Makefile +++ b/drivers/hwmon/Makefile @@ -201,7 +201,6 @@ obj-$(CONFIG_SENSORS_PWM_FAN) += pwm-fan.o obj-$(CONFIG_SENSORS_QNAP_MCU_HWMON) += qnap-mcu-hwmon.o obj-$(CONFIG_SENSORS_RASPBERRYPI_HWMON) += raspberrypi-hwmon.o obj-$(CONFIG_SENSORS_SBTSI) += sbtsi_temp.o -obj-$(CONFIG_SENSORS_SBRMI) += sbrmi.o obj-$(CONFIG_SENSORS_SCH56XX_COMMON)+= sch56xx-common.o obj-$(CONFIG_SENSORS_SCH5627) += sch5627.o obj-$(CONFIG_SENSORS_SCH5636) += sch5636.o diff --git a/drivers/hwmon/ads7871.c b/drivers/hwmon/ads7871.c index 9bfdf9e6bcd7..9ee3ce01f130 100644 --- a/drivers/hwmon/ads7871.c +++ b/drivers/hwmon/ads7871.c @@ -77,9 +77,13 @@ static int ads7871_read_reg8(struct spi_device *spi, int reg) static int ads7871_read_reg16(struct spi_device *spi, int reg) { int ret; + reg = reg | INST_READ_BM | INST_16BIT_BM; ret = spi_w8r16(spi, reg); - return ret; + if (ret < 0) + return ret; + + return le16_to_cpu((__force __le16)ret); } static int ads7871_write_reg8(struct spi_device *spi, int reg, u8 val) diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c index dddbd2463f8d..76f3e1da68d0 100644 --- a/drivers/hwmon/corsair-psu.c +++ b/drivers/hwmon/corsair-psu.c @@ -796,13 +796,13 @@ static int corsairpsu_probe(struct hid_device *hdev, const struct hid_device_id ret = corsairpsu_init(priv); if (ret < 0) { dev_err(&hdev->dev, "unable to initialize device (%d)\n", ret); - goto fail_and_stop; + goto fail_and_close; } ret = corsairpsu_fwinfo(priv); if (ret < 0) { dev_err(&hdev->dev, "unable to query firmware (%d)\n", ret); - goto fail_and_stop; + goto fail_and_close; } corsairpsu_get_criticals(priv); diff --git a/drivers/hwmon/lm63.c b/drivers/hwmon/lm63.c index 035176a98ce9..30500b4d2221 100644 --- a/drivers/hwmon/lm63.c +++ b/drivers/hwmon/lm63.c @@ -333,7 +333,13 @@ static ssize_t show_fan(struct device *dev, struct device_attribute *devattr, { struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); struct lm63_data *data = lm63_update_device(dev); - return sprintf(buf, "%d\n", FAN_FROM_REG(data->fan[attr->index])); + int fan; + + mutex_lock(&data->update_lock); + fan = FAN_FROM_REG(data->fan[attr->index]); + mutex_unlock(&data->update_lock); + + return sprintf(buf, "%d\n", fan); } static ssize_t set_fan(struct device *dev, struct device_attribute *dummy, @@ -366,12 +372,14 @@ static ssize_t show_pwm1(struct device *dev, struct device_attribute *devattr, int nr = attr->index; int pwm; + mutex_lock(&data->update_lock); if (data->pwm_highres) pwm = data->pwm1[nr]; else pwm = data->pwm1[nr] >= 2 * data->pwm1_freq ? 255 : (data->pwm1[nr] * 255 + data->pwm1_freq) / (2 * data->pwm1_freq); + mutex_unlock(&data->update_lock); return sprintf(buf, "%d\n", pwm); } @@ -529,6 +537,7 @@ static ssize_t show_temp11(struct device *dev, struct device_attribute *devattr, int nr = attr->index; int temp; + mutex_lock(&data->update_lock); if (!nr) { /* * Use unsigned temperature unless its value is zero. @@ -544,7 +553,10 @@ static ssize_t show_temp11(struct device *dev, struct device_attribute *devattr, else temp = TEMP11_FROM_REG(data->temp11[nr]); } - return sprintf(buf, "%d\n", temp + data->temp2_offset); + temp += data->temp2_offset; + mutex_unlock(&data->update_lock); + + return sprintf(buf, "%d\n", temp); } static ssize_t set_temp11(struct device *dev, struct device_attribute *devattr, @@ -592,9 +604,14 @@ static ssize_t temp2_crit_hyst_show(struct device *dev, struct device_attribute *dummy, char *buf) { struct lm63_data *data = lm63_update_device(dev); - return sprintf(buf, "%d\n", temp8_from_reg(data, 2) - + data->temp2_offset - - TEMP8_FROM_REG(data->temp2_crit_hyst)); + int temp; + + mutex_lock(&data->update_lock); + temp = temp8_from_reg(data, 2) + data->temp2_offset + - TEMP8_FROM_REG(data->temp2_crit_hyst); + mutex_unlock(&data->update_lock); + + return sprintf(buf, "%d\n", temp); } static ssize_t show_lut_temp_hyst(struct device *dev, @@ -602,10 +619,14 @@ static ssize_t show_lut_temp_hyst(struct device *dev, { struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr); struct lm63_data *data = lm63_update_device(dev); + int temp; - return sprintf(buf, "%d\n", lut_temp_from_reg(data, attr->index) - + data->temp2_offset - - TEMP8_FROM_REG(data->lut_temp_hyst)); + mutex_lock(&data->update_lock); + temp = lut_temp_from_reg(data, attr->index) + data->temp2_offset + - TEMP8_FROM_REG(data->lut_temp_hyst); + mutex_unlock(&data->update_lock); + + return sprintf(buf, "%d\n", temp); } /* @@ -616,7 +637,7 @@ static ssize_t temp2_crit_hyst_store(struct device *dev, struct device_attribute *dummy, const char *buf, size_t count) { - struct lm63_data *data = dev_get_drvdata(dev); + struct lm63_data *data = lm63_update_device(dev); struct i2c_client *client = data->client; long val; int err; diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c index f1a1e5b888f6..c283443e363b 100644 --- a/drivers/hwmon/lm75.c +++ b/drivers/hwmon/lm75.c @@ -137,7 +137,7 @@ static const struct lm75_params device_params[] = { }, [as6200] = { .config_reg_16bits = true, - .set_mask = 0x94C0, /* 8 sample/s, 4 CF, positive polarity */ + .set_mask = 0xC010, /* 8 sample/s, 4 CF */ .default_resolution = 12, .default_sample_time = 125, .num_sample_times = 4, @@ -286,8 +286,8 @@ static const struct lm75_params device_params[] = { }, [tmp112] = { .config_reg_16bits = true, - .set_mask = 0x60C0, /* 12-bit mode, 8 samples / second */ - .clr_mask = 1 << 15, /* no one-shot mode*/ + .set_mask = 0xC060, /* 12-bit mode, 8 samples / second */ + .clr_mask = 1 << 7, /* no one-shot mode*/ .default_resolution = 12, .default_sample_time = 125, .num_sample_times = 4, @@ -353,7 +353,7 @@ static inline int lm75_write_config(struct lm75_data *data, u16 set_mask, u16 clr_mask) { return regmap_update_bits(data->regmap, LM75_REG_CONF, - clr_mask | LM75_SHUTDOWN, set_mask); + clr_mask | set_mask | LM75_SHUTDOWN, set_mask); } static irqreturn_t lm75_alarm_handler(int irq, void *private) @@ -416,7 +416,7 @@ static int lm75_read(struct device *dev, enum hwmon_sensor_types type, switch (data->kind) { case as6200: case tmp112: - *val = (regval >> 13) & 0x1; + *val = !!(regval & BIT(13)) == !!(regval & BIT(2)); break; default: return -EINVAL; diff --git a/drivers/hwmon/ltc2992.c b/drivers/hwmon/ltc2992.c index 1fcd320d6161..2617c4538af9 100644 --- a/drivers/hwmon/ltc2992.c +++ b/drivers/hwmon/ltc2992.c @@ -431,10 +431,16 @@ static int ltc2992_get_voltage(struct ltc2992_state *st, u32 reg, u32 scale, lon static int ltc2992_set_voltage(struct ltc2992_state *st, u32 reg, u32 scale, long val) { - val = DIV_ROUND_CLOSEST(val * 1000, scale); - val = val << 4; + u32 reg_val; + long vmax; - return ltc2992_write_reg(st, reg, 2, val); + vmax = DIV_ROUND_CLOSEST_ULL(0xFFFULL * scale, 1000); + val = max(val, 0L); + val = min(val, vmax); + reg_val = min(DIV_ROUND_CLOSEST_ULL((u64)val * 1000, scale), + 0xFFFULL) << 4; + + return ltc2992_write_reg(st, reg, 2, reg_val); } static int ltc2992_read_gpio_alarm(struct ltc2992_state *st, int nr_gpio, u32 attr, long *val) @@ -559,9 +565,15 @@ static int ltc2992_get_current(struct ltc2992_state *st, u32 reg, u32 channel, l static int ltc2992_set_current(struct ltc2992_state *st, u32 reg, u32 channel, long val) { u32 reg_val; + long cmax; - reg_val = DIV_ROUND_CLOSEST(val * st->r_sense_uohm[channel], LTC2992_IADC_NANOV_LSB); - reg_val = reg_val << 4; + cmax = DIV_ROUND_CLOSEST_ULL(0xFFFULL * LTC2992_IADC_NANOV_LSB, + st->r_sense_uohm[channel]); + val = max(val, 0L); + val = min(val, cmax); + reg_val = min(DIV_ROUND_CLOSEST_ULL((u64)val * st->r_sense_uohm[channel], + LTC2992_IADC_NANOV_LSB), + 0xFFFULL) << 4; return ltc2992_write_reg(st, reg, 2, reg_val); } @@ -625,8 +637,10 @@ static int ltc2992_get_power(struct ltc2992_state *st, u32 reg, u32 channel, lon if (reg_val < 0) return reg_val; - *val = mul_u64_u32_div(reg_val, LTC2992_VADC_UV_LSB * LTC2992_IADC_NANOV_LSB, - st->r_sense_uohm[channel] * 1000); + *val = mul_u64_u32_div(reg_val, + LTC2992_VADC_UV_LSB / 1000 * + LTC2992_IADC_NANOV_LSB, + st->r_sense_uohm[channel]); return 0; } @@ -634,9 +648,18 @@ static int ltc2992_get_power(struct ltc2992_state *st, u32 reg, u32 channel, lon static int ltc2992_set_power(struct ltc2992_state *st, u32 reg, u32 channel, long val) { u32 reg_val; + u64 pmax, uval; - reg_val = mul_u64_u32_div(val, st->r_sense_uohm[channel] * 1000, - LTC2992_VADC_UV_LSB * LTC2992_IADC_NANOV_LSB); + uval = max(val, 0L); + pmax = mul_u64_u32_div(0xFFFFFFULL, + LTC2992_VADC_UV_LSB / 1000 * + LTC2992_IADC_NANOV_LSB, + st->r_sense_uohm[channel]); + uval = min(uval, pmax); + reg_val = min(mul_u64_u32_div(uval, st->r_sense_uohm[channel], + LTC2992_VADC_UV_LSB / 1000 * + LTC2992_IADC_NANOV_LSB), + 0xFFFFFFULL); return ltc2992_write_reg(st, reg, 3, reg_val); } diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index 70cb5822bf17..53d9df70ebe4 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -895,8 +895,6 @@ static void stm32f7_i2c_xfer_msg(struct stm32f7_i2c_dev *i2c_dev, f7_msg->result = 0; f7_msg->stop = (i2c_dev->msg_id >= i2c_dev->msg_num - 1); - reinit_completion(&i2c_dev->complete); - cr1 = readl_relaxed(base + STM32F7_I2C_CR1); cr2 = readl_relaxed(base + STM32F7_I2C_CR2); @@ -1728,6 +1726,8 @@ static int stm32f7_i2c_xfer_core(struct i2c_adapter *i2c_adap, if (ret) goto pm_free; + reinit_completion(&i2c_dev->complete); + stm32f7_i2c_xfer_msg(i2c_dev, msgs); if (!i2c_dev->atomic) @@ -2253,7 +2253,7 @@ static int stm32f7_i2c_probe(struct platform_device *pdev) snprintf(adap->name, sizeof(adap->name), "STM32F7 I2C(%pa)", &res->start); adap->owner = THIS_MODULE; - adap->timeout = 2 * HZ; + adap->timeout = 8 * HZ; adap->retries = 3; adap->algo = &stm32f7_i2c_algo; adap->dev.parent = &pdev->dev; diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 2cbd31f77667..28c0e4884a7f 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -371,6 +371,7 @@ static const struct acpi_device_id i2c_acpi_force_100khz_device_ids[] = { * a 400KHz frequency. The root cause of the issue is not known. */ { "DLL0945", 0 }, + { "ELAN0678", 0 }, { "ELAN06FA", 0 }, {} }; diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 9c46147e3506..a2132d70fb36 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -445,8 +445,7 @@ static int i2c_init_recovery(struct i2c_adapter *adap) bri->set_scl = set_scl_gpio_value; if (bri->sda_gpiod) { bri->get_sda = get_sda_gpio_value; - /* FIXME: add proper flag instead of '0' once available */ - if (gpiod_get_direction(bri->sda_gpiod) == 0) + if (gpiod_get_direction(bri->sda_gpiod) == GPIO_LINE_DIRECTION_OUT) bri->set_sda = set_sda_gpio_value; } } else if (bri->recover_bus == i2c_generic_scl_recovery) { diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c index 71eb1ef56f0c..ad6acb5ebadc 100644 --- a/drivers/i2c/i2c-core-smbus.c +++ b/drivers/i2c/i2c-core-smbus.c @@ -566,6 +566,18 @@ s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, if (res) return res; + /* Reject invalid caller-supplied block lengths before any + * tracepoint or native smbus_xfer callback runs. + */ + if (data && + (protocol == I2C_SMBUS_I2C_BLOCK_DATA || + protocol == I2C_SMBUS_BLOCK_PROC_CALL || + (protocol == I2C_SMBUS_BLOCK_DATA && + read_write == I2C_SMBUS_WRITE)) && + (data->block[0] == 0 || + data->block[0] > I2C_SMBUS_BLOCK_MAX)) + return -EINVAL; + /* If enabled, the following two tracepoints are conditional on * read_write and protocol. */ diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index 7bbe0263411e..ccaac5e29f90 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -487,12 +487,13 @@ static long i2cdev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) client->adapter->retries = arg; break; case I2C_TIMEOUT: - if (arg > INT_MAX) + /* + * For historical reasons, user-space sets the timeout value in + * units of 10 ms. + */ + if (arg > INT_MAX / 10) return -EINVAL; - /* For historical reasons, user-space sets the timeout - * value in units of 10 ms. - */ client->adapter->timeout = msecs_to_jiffies(arg * 10); break; default: diff --git a/drivers/i2c/i2c-slave-testunit.c b/drivers/i2c/i2c-slave-testunit.c index 6de4307050dd..871c58461ebc 100644 --- a/drivers/i2c/i2c-slave-testunit.c +++ b/drivers/i2c/i2c-slave-testunit.c @@ -15,7 +15,7 @@ #include #include #include -#include /* FIXME: is system_long_wq the best choice? */ +#include #define TU_VERSION_MAX_LENGTH 128 @@ -124,7 +124,7 @@ static int i2c_slave_testunit_slave_cb(struct i2c_client *client, case I2C_SLAVE_STOP: if (tu->reg_idx == TU_NUM_REGS) { set_bit(TU_FLAG_IN_PROCESS, &tu->flags); - queue_delayed_work(system_long_wq, &tu->worker, + queue_delayed_work(system_dfl_long_wq, &tu->worker, msecs_to_jiffies(10 * tu->regs[TU_REG_DELAY])); } diff --git a/drivers/i2c/i2c-stub.c b/drivers/i2c/i2c-stub.c index fbb0db41b10e..04314e3ed24c 100644 --- a/drivers/i2c/i2c-stub.c +++ b/drivers/i2c/i2c-stub.c @@ -214,6 +214,11 @@ static s32 stub_xfer(struct i2c_adapter *adap, u16 addr, unsigned short flags, * We ignore banks here, because banked chips don't use I2C * block transfers */ + if (data->block[0] == 0 || + data->block[0] > I2C_SMBUS_BLOCK_MAX) { + ret = -EINVAL; + break; + } if (data->block[0] > 256 - command) /* Avoid overrun */ data->block[0] = 256 - command; len = data->block[0]; diff --git a/drivers/staging/rtl8723bs/os_dep/osdep_service.c b/drivers/staging/rtl8723bs/os_dep/osdep_service.c index 7959daeabc6f..4cfdf7c62344 100644 --- a/drivers/staging/rtl8723bs/os_dep/osdep_service.c +++ b/drivers/staging/rtl8723bs/os_dep/osdep_service.c @@ -194,7 +194,8 @@ struct rtw_cbuf *rtw_cbuf_alloc(u32 size) struct rtw_cbuf *cbuf; cbuf = kzalloc_flex(*cbuf, bufs, size); - cbuf->size = size; + if (cbuf) + cbuf->size = size; return cbuf; } diff --git a/drivers/staging/vme_user/vme_fake.c b/drivers/staging/vme_user/vme_fake.c index be4ad47ed526..8abaa3165fbb 100644 --- a/drivers/staging/vme_user/vme_fake.c +++ b/drivers/staging/vme_user/vme_fake.c @@ -1230,6 +1230,8 @@ err_master: err_driver: kfree(fake_bridge); err_struct: + root_device_unregister(vme_root); + return retval; } diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c index 669b9e6879bf..746414763da5 100644 --- a/drivers/usb/class/usblp.c +++ b/drivers/usb/class/usblp.c @@ -1178,7 +1178,7 @@ static int usblp_probe(struct usb_interface *intf, } /* Allocate buffer for printer status */ - usblp->statusbuf = kmalloc(STATUS_BUF_SIZE, GFP_KERNEL); + usblp->statusbuf = kzalloc(STATUS_BUF_SIZE, GFP_KERNEL); if (!usblp->statusbuf) { retval = -ENOMEM; goto abort; @@ -1377,6 +1377,7 @@ static int usblp_cache_device_id_string(struct usblp *usblp) { int err, length; + memset(usblp->device_id_string, 0, USBLP_DEVICE_ID_SIZE); err = usblp_get_id(usblp, 0, usblp->device_id_string, USBLP_DEVICE_ID_SIZE - 1); if (err < 0) { dev_dbg(&usblp->intf->dev, diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c index b34fb65813c4..9b69148128e5 100644 --- a/drivers/usb/common/ulpi.c +++ b/drivers/usb/common/ulpi.c @@ -286,12 +286,15 @@ static int ulpi_register(struct device *dev, struct ulpi *ulpi) ACPI_COMPANION_SET(&ulpi->dev, ACPI_COMPANION(dev)); ret = ulpi_of_register(ulpi); - if (ret) + if (ret) { + kfree(ulpi); return ret; + } ret = ulpi_read_id(ulpi); if (ret) { of_node_put(ulpi->dev.of_node); + kfree(ulpi); return ret; } diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 58899b1fa96d..65213896de99 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1359,12 +1359,6 @@ int dwc3_core_init(struct dwc3 *dwc) hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0); - /* - * Write Linux Version Code to our GUID register so it's easy to figure - * out which kernel version a bug was found. - */ - dwc3_writel(dwc, DWC3_GUID, LINUX_VERSION_CODE); - ret = dwc3_phy_setup(dwc); if (ret) return ret; @@ -1398,6 +1392,12 @@ int dwc3_core_init(struct dwc3 *dwc) if (ret) goto err_exit_phy; + /* + * Write Linux Version Code to our GUID register so it's easy to figure + * out which kernel version a bug was found. + */ + dwc3_writel(dwc, DWC3_GUID, LINUX_VERSION_CODE); + dwc3_core_setup_global_control(dwc); dwc3_core_num_eps(dwc); diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c index 91139ae668f4..f3ca79cece1b 100644 --- a/drivers/usb/gadget/udc/omap_udc.c +++ b/drivers/usb/gadget/udc/omap_udc.c @@ -733,8 +733,6 @@ static void dma_channel_claim(struct omap_ep *ep, unsigned channel) if (status == 0) { omap_writew(reg, UDC_TXDMA_CFG); /* EMIFF or SDRC */ - omap_set_dma_src_burst_mode(ep->lch, - OMAP_DMA_DATA_BURST_4); omap_set_dma_src_data_pack(ep->lch, 1); /* TIPB */ omap_set_dma_dest_params(ep->lch, @@ -756,8 +754,6 @@ static void dma_channel_claim(struct omap_ep *ep, unsigned channel) UDC_DATA_DMA, 0, 0); /* EMIFF or SDRC */ - omap_set_dma_dest_burst_mode(ep->lch, - OMAP_DMA_DATA_BURST_4); omap_set_dma_dest_data_pack(ep->lch, 1); } } diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index c71461893d20..42e4cecd28ac 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1513,7 +1513,11 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1231, 0xff), /* Telit LE910Cx (RNDIS) */ .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x1250, 0xff, 0x00, 0x00) }, /* Telit LE910Cx (rmnet) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1251, 0xff) }, /* Telit LE910Cx (RNDIS) */ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1252, 0xff) }, /* Telit LE910Cx (MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1253, 0xff) }, /* Telit LE910Cx (ECM) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1254, 0xff) }, /* Telit LE910Cx */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1255, 0xff) }, /* Telit LE910Cx */ { USB_DEVICE(TELIT_VENDOR_ID, 0x1260), .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE(TELIT_VENDOR_ID, 0x1261), diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index dfbb94ddc98a..55fee96d3342 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -732,9 +732,14 @@ static const char * const pd_rev[] = { (tcpm_cc_is_source((port)->cc2) && \ !tcpm_cc_is_source((port)->cc1))) +#define tcpm_port_is_debug_source(port) \ + (tcpm_cc_is_source((port)->cc1) && tcpm_cc_is_source((port)->cc2)) + +#define tcpm_port_is_debug_sink(port) \ + (tcpm_cc_is_sink((port)->cc1) && tcpm_cc_is_sink((port)->cc2)) + #define tcpm_port_is_debug(port) \ - ((tcpm_cc_is_source((port)->cc1) && tcpm_cc_is_source((port)->cc2)) || \ - (tcpm_cc_is_sink((port)->cc1) && tcpm_cc_is_sink((port)->cc2))) + (tcpm_port_is_debug_source(port) || tcpm_port_is_debug_sink(port)) #define tcpm_port_is_audio(port) \ (tcpm_cc_is_audio((port)->cc1) && tcpm_cc_is_audio((port)->cc2)) @@ -5176,7 +5181,7 @@ static void run_state_machine(struct tcpm_port *port) tcpm_set_state(port, SNK_UNATTACHED, PD_T_DRP_SNK); break; case SRC_ATTACH_WAIT: - if (tcpm_port_is_debug(port)) + if (tcpm_port_is_debug_source(port)) tcpm_set_state(port, DEBUG_ACC_ATTACHED, port->timings.cc_debounce_time); else if (tcpm_port_is_audio(port)) @@ -5434,7 +5439,7 @@ static void run_state_machine(struct tcpm_port *port) tcpm_set_state(port, SRC_UNATTACHED, PD_T_DRP_SRC); break; case SNK_ATTACH_WAIT: - if (tcpm_port_is_debug(port)) + if (tcpm_port_is_debug_sink(port)) tcpm_set_state(port, DEBUG_ACC_ATTACHED, PD_T_CC_DEBOUNCE); else if (tcpm_port_is_audio(port)) @@ -5454,7 +5459,7 @@ static void run_state_machine(struct tcpm_port *port) if (tcpm_port_is_disconnected(port)) tcpm_set_state(port, SNK_UNATTACHED, PD_T_PD_DEBOUNCE); - else if (tcpm_port_is_debug(port)) + else if (tcpm_port_is_debug_sink(port)) tcpm_set_state(port, DEBUG_ACC_ATTACHED, PD_T_CC_DEBOUNCE); else if (tcpm_port_is_audio(port)) @@ -5935,6 +5940,8 @@ static void run_state_machine(struct tcpm_port *port) /* remove existing capabilities */ tcpm_partner_source_caps_reset(port); tcpm_pd_send_control(port, PD_CTRL_ACCEPT, TCPC_TX_SOP); + port->vdm_sm_running = false; + port->explicit_contract = false; tcpm_ams_finish(port); if (port->pwr_role == TYPEC_SOURCE) { port->upcoming_state = SRC_SEND_CAPABILITIES; @@ -6360,10 +6367,10 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1, switch (port->state) { case TOGGLING: - if (tcpm_port_is_debug(port) || tcpm_port_is_audio(port) || + if (tcpm_port_is_debug_source(port) || tcpm_port_is_audio(port) || tcpm_port_is_source(port)) tcpm_set_state(port, SRC_ATTACH_WAIT, 0); - else if (tcpm_port_is_sink(port)) + else if (tcpm_port_is_debug_sink(port) || tcpm_port_is_sink(port)) tcpm_set_state(port, SNK_ATTACH_WAIT, 0); break; case CHECK_CONTAMINANT: @@ -6371,9 +6378,11 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1, break; case SRC_UNATTACHED: case ACC_UNATTACHED: - if (tcpm_port_is_debug(port) || tcpm_port_is_audio(port) || + if (tcpm_port_is_debug_source(port) || tcpm_port_is_audio(port) || tcpm_port_is_source(port)) tcpm_set_state(port, SRC_ATTACH_WAIT, 0); + else if (tcpm_port_is_debug_sink(port)) + tcpm_set_state(port, SNK_ATTACH_WAIT, 0); break; case SRC_ATTACH_WAIT: if (tcpm_port_is_disconnected(port) || @@ -6395,7 +6404,7 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1, } break; case SNK_UNATTACHED: - if (tcpm_port_is_debug(port) || tcpm_port_is_audio(port) || + if (tcpm_port_is_debug_sink(port) || tcpm_port_is_audio(port) || tcpm_port_is_sink(port)) tcpm_set_state(port, SNK_ATTACH_WAIT, 0); break; diff --git a/include/linux/rseq.h b/include/linux/rseq.h index b9d62fc2140d..7ef79b25e714 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -9,6 +9,11 @@ void __rseq_handle_slowpath(struct pt_regs *regs); +static __always_inline bool rseq_v2(struct task_struct *t) +{ + return IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY) && likely(t->rseq.event.has_rseq > 1); +} + /* Invoked from resume_user_mode_work() */ static inline void rseq_handle_slowpath(struct pt_regs *regs) { @@ -16,8 +21,7 @@ static inline void rseq_handle_slowpath(struct pt_regs *regs) if (current->rseq.event.slowpath) __rseq_handle_slowpath(regs); } else { - /* '&' is intentional to spare one conditional branch */ - if (current->rseq.event.sched_switch & current->rseq.event.has_rseq) + if (current->rseq.event.sched_switch && current->rseq.event.has_rseq) __rseq_handle_slowpath(regs); } } @@ -30,9 +34,9 @@ void __rseq_signal_deliver(int sig, struct pt_regs *regs); */ static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { - if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { - /* '&' is intentional to spare one conditional branch */ - if (current->rseq.event.has_rseq & current->rseq.event.user_irq) + if (rseq_v2(current)) { + /* has_rseq is implied in rseq_v2() */ + if (current->rseq.event.user_irq) __rseq_signal_deliver(ksig->sig, regs); } else { if (current->rseq.event.has_rseq) @@ -50,15 +54,22 @@ static __always_inline void rseq_sched_switch_event(struct task_struct *t) { struct rseq_event *ev = &t->rseq.event; - if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + /* + * Only apply the user_irq optimization for RSEQ ABI V2 registrations. + * Legacy users like TCMalloc rely on the original ABI V1 behaviour + * which updates IDs on every context swtich. + */ + if (rseq_v2(t)) { /* - * Avoid a boat load of conditionals by using simple logic - * to determine whether NOTIFY_RESUME needs to be raised. + * Avoid a boat load of conditionals by using simple logic to + * determine whether TIF_NOTIFY_RESUME or TIF_RSEQ needs to be + * raised. * - * It's required when the CPU or MM CID has changed or - * the entry was from user space. + * It's required when the CPU or MM CID has changed or the entry + * was via interrupt from user space. ev->has_rseq does not have + * to be evaluated here because rseq_v2() implies has_rseq. */ - bool raise = (ev->user_irq | ev->ids_changed) & ev->has_rseq; + bool raise = ev->user_irq | ev->ids_changed; if (raise) { ev->sched_switch = true; @@ -66,6 +77,7 @@ static __always_inline void rseq_sched_switch_event(struct task_struct *t) } } else { if (ev->has_rseq) { + t->rseq.event.ids_changed = true; t->rseq.event.sched_switch = true; rseq_raise_notify_resume(t); } @@ -119,6 +131,8 @@ static inline void rseq_virt_userspace_exit(void) static inline void rseq_reset(struct task_struct *t) { + /* Protect against preemption and membarrier IPI */ + guard(irqsave)(); memset(&t->rseq, 0, sizeof(t->rseq)); t->rseq.ids.cpu_id = RSEQ_CPU_ID_UNINITIALIZED; } @@ -159,6 +173,7 @@ static inline unsigned int rseq_alloc_align(void) } #else /* CONFIG_RSEQ */ +static inline bool rseq_v2(struct task_struct *t) { return false; } static inline void rseq_handle_slowpath(struct pt_regs *regs) { } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_sched_switch_event(struct task_struct *t) { } diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h index f11ebd34f8b9..2d0295df5107 100644 --- a/include/linux/rseq_entry.h +++ b/include/linux/rseq_entry.h @@ -111,6 +111,20 @@ static __always_inline void rseq_slice_clear_grant(struct task_struct *t) t->rseq.slice.state.granted = false; } +/* + * Open coded, so it can be invoked within a user access region. + * + * This clears the user space state of the time slice extensions field only when + * the task has registered the optimized RSEQ_ABI V2. Some legacy registrations, + * e.g. TCMalloc, have conflicting non-ABI fields in struct RSEQ, which would be + * overwritten by an unconditional write. + */ +#define rseq_slice_clear_user(rseq, efault) \ +do { \ + if (rseq_slice_extension_enabled()) \ + unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); \ +} while (0) + static __always_inline bool __rseq_grant_slice_extension(bool work_pending) { struct task_struct *curr = current; @@ -230,10 +244,10 @@ static __always_inline bool rseq_slice_extension_enabled(void) { return false; } static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; } static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { } static __always_inline bool rseq_grant_slice_extension(unsigned long ti_work, unsigned long mask) { return false; } +#define rseq_slice_clear_user(rseq, efault) do { } while (0) #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */ bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr); -bool rseq_debug_validate_ids(struct task_struct *t); static __always_inline void rseq_note_user_irq_entry(void) { @@ -353,43 +367,6 @@ efault: return false; } -/* - * On debug kernels validate that user space did not mess with it if the - * debug branch is enabled. - */ -bool rseq_debug_validate_ids(struct task_struct *t) -{ - struct rseq __user *rseq = t->rseq.usrptr; - u32 cpu_id, uval, node_id; - - /* - * On the first exit after registering the rseq region CPU ID is - * RSEQ_CPU_ID_UNINITIALIZED and node_id in user space is 0! - */ - node_id = t->rseq.ids.cpu_id != RSEQ_CPU_ID_UNINITIALIZED ? - cpu_to_node(t->rseq.ids.cpu_id) : 0; - - scoped_user_read_access(rseq, efault) { - unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault); - if (cpu_id != t->rseq.ids.cpu_id) - goto die; - unsafe_get_user(uval, &rseq->cpu_id, efault); - if (uval != cpu_id) - goto die; - unsafe_get_user(uval, &rseq->node_id, efault); - if (uval != node_id) - goto die; - unsafe_get_user(uval, &rseq->mm_cid, efault); - if (uval != t->rseq.ids.mm_cid) - goto die; - } - return true; -die: - t->rseq.event.fatal = true; -efault: - return false; -} - #endif /* RSEQ_BUILD_SLOW_PATH */ /* @@ -499,37 +476,50 @@ efault: * faults in task context are fatal too. */ static rseq_inline -bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, - u32 node_id, u64 *csaddr) +bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, u64 *csaddr) { struct rseq __user *rseq = t->rseq.usrptr; - if (static_branch_unlikely(&rseq_debug_enabled)) { - if (!rseq_debug_validate_ids(t)) - return false; - } - scoped_user_rw_access(rseq, efault) { + /* Validate the R/O fields for debug and optimized mode */ + if (static_branch_unlikely(&rseq_debug_enabled) || rseq_v2(t)) { + u32 cpu_id, uval; + + unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault); + if (cpu_id != t->rseq.ids.cpu_id) + goto die; + unsafe_get_user(uval, &rseq->cpu_id, efault); + if (uval != cpu_id) + goto die; + unsafe_get_user(uval, &rseq->node_id, efault); + if (uval != t->rseq.ids.node_id) + goto die; + unsafe_get_user(uval, &rseq->mm_cid, efault); + if (uval != t->rseq.ids.mm_cid) + goto die; + } + unsafe_put_user(ids->cpu_id, &rseq->cpu_id_start, efault); unsafe_put_user(ids->cpu_id, &rseq->cpu_id, efault); - unsafe_put_user(node_id, &rseq->node_id, efault); + unsafe_put_user(ids->node_id, &rseq->node_id, efault); unsafe_put_user(ids->mm_cid, &rseq->mm_cid, efault); if (csaddr) unsafe_get_user(*csaddr, &rseq->rseq_cs, efault); - /* Open coded, so it's in the same user access region */ - if (rseq_slice_extension_enabled()) { - /* Unconditionally clear it, no point in conditionals */ - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); - } + /* RSEQ ABI V2 only operations */ + if (rseq_v2(t)) + rseq_slice_clear_user(rseq, efault); } rseq_slice_clear_grant(t); /* Cache the new values */ - t->rseq.ids.cpu_cid = ids->cpu_cid; + t->rseq.ids = *ids; rseq_stat_inc(rseq_stats.ids); rseq_trace_update(t, ids); return true; + +die: + t->rseq.event.fatal = true; efault: return false; } @@ -539,11 +529,11 @@ efault: * is in a critical section. */ static rseq_inline bool rseq_update_usr(struct task_struct *t, struct pt_regs *regs, - struct rseq_ids *ids, u32 node_id) + struct rseq_ids *ids) { u64 csaddr; - if (!rseq_set_ids_get_csaddr(t, ids, node_id, &csaddr)) + if (!rseq_set_ids_get_csaddr(t, ids, &csaddr)) return false; /* @@ -612,6 +602,14 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t * interrupts disabled */ guard(pagefault)(); + /* + * This optimization is only valid when the task registered for the + * optimized RSEQ_ABI_V2 variant. Some legacy users rely on the original + * RSEQ implementation behaviour which unconditionally updated the IDs. + * rseq_sched_switch_event() ensures that legacy registrations always + * have both sched_switch and ids_changed set, which is compatible with + * the historical TIF_NOTIFY_RESUME behaviour. + */ if (likely(!t->rseq.event.ids_changed)) { struct rseq __user *rseq = t->rseq.usrptr; /* @@ -623,11 +621,9 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t scoped_user_rw_access(rseq, efault) { unsafe_get_user(csaddr, &rseq->rseq_cs, efault); - /* Open coded, so it's in the same user access region */ - if (rseq_slice_extension_enabled()) { - /* Unconditionally clear it, no point in conditionals */ - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); - } + /* RSEQ ABI V2 only operations */ + if (rseq_v2(t)) + rseq_slice_clear_user(rseq, efault); } rseq_slice_clear_grant(t); @@ -640,12 +636,12 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t } struct rseq_ids ids = { - .cpu_id = task_cpu(t), - .mm_cid = task_mm_cid(t), + .cpu_id = task_cpu(t), + .mm_cid = task_mm_cid(t), + .node_id = cpu_to_node(ids.cpu_id), }; - u32 node_id = cpu_to_node(ids.cpu_id); - return rseq_update_usr(t, regs, &ids, node_id); + return rseq_update_usr(t, regs, &ids); efault: return false; } diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h index 0b42045988db..85739a63e85e 100644 --- a/include/linux/rseq_types.h +++ b/include/linux/rseq_types.h @@ -9,6 +9,12 @@ #ifdef CONFIG_RSEQ struct rseq; +/* + * rseq_event::has_rseq contains the ABI version number so preserving it + * in AND operations requires a mask. + */ +#define RSEQ_HAS_RSEQ_VERSION_MASK 0xff + /** * struct rseq_event - Storage for rseq related event management * @all: Compound to initialize and clear the data efficiently @@ -17,7 +23,8 @@ struct rseq; * exit to user * @ids_changed: Indicator that IDs need to be updated * @user_irq: True on interrupt entry from user mode - * @has_rseq: True if the task has a rseq pointer installed + * @has_rseq: Greater than 0 if the task has a rseq pointer installed. + * Contains the RSEQ version number * @error: Compound error code for the slow path to analyze * @fatal: User space data corrupted or invalid * @slowpath: Indicator that slow path processing via TIF_NOTIFY_RESUME @@ -59,8 +66,9 @@ struct rseq_event { * compiler emit a single compare on 64-bit * @cpu_id: The CPU ID which was written last to user space * @mm_cid: The MM CID which was written last to user space + * @node_id: The node ID which was written last to user space * - * @cpu_id and @mm_cid are updated when the data is written to user space. + * @cpu_id, @mm_cid and @node_id are updated when the data is written to user space. */ struct rseq_ids { union { @@ -70,6 +78,7 @@ struct rseq_ids { u32 mm_cid; }; }; + u32 node_id; }; /** diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index f69344fe6c08..ca6fe1f9d05e 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -28,7 +28,7 @@ enum rseq_cs_flags_bit { RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT = 0, RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT = 1, RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT = 2, - /* (3) Intentional gap to put new bits into a separate byte */ + /* (3) Intentional gap to keep new bits separate */ /* User read only feature flags */ RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE_BIT = 4, @@ -161,6 +161,9 @@ struct rseq { * - RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT * - RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL * - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE + * + * It is now used for feature status advertisement by the kernel. + * See: enum rseq_cs_flags_bit for further information. */ __u32 flags; diff --git a/kernel/events/core.c b/kernel/events/core.c index 4050525ab7d8..a4c884d4ecfb 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7007,6 +7007,7 @@ static void perf_mmap_open(struct vm_area_struct *vma) } static void perf_pmu_output_stop(struct perf_event *event); +static void perf_mmap_unaccount(struct vm_area_struct *vma, struct perf_buffer *rb); /* * A buffer can be mmap()ed multiple times; either directly through the same @@ -7022,8 +7023,6 @@ static void perf_mmap_close(struct vm_area_struct *vma) mapped_f unmapped = get_mapped(event, event_unmapped); struct perf_buffer *rb = ring_buffer_get(event); struct user_struct *mmap_user = rb->mmap_user; - int mmap_locked = rb->mmap_locked; - unsigned long size = perf_data_size(rb); bool detach_rest = false; /* FIXIES vs perf_pmu_unregister() */ @@ -7118,11 +7117,7 @@ again: * Aside from that, this buffer is 'fully' detached and unmapped, * undo the VM accounting. */ - - atomic_long_sub((size >> PAGE_SHIFT) + 1 - mmap_locked, - &mmap_user->locked_vm); - atomic64_sub(mmap_locked, &vma->vm_mm->pinned_vm); - free_uid(mmap_user); + perf_mmap_unaccount(vma, rb); out_put: ring_buffer_put(rb); /* could be last */ @@ -7262,6 +7257,15 @@ static void perf_mmap_account(struct vm_area_struct *vma, long user_extra, long atomic64_add(extra, &vma->vm_mm->pinned_vm); } +static void perf_mmap_unaccount(struct vm_area_struct *vma, struct perf_buffer *rb) +{ + struct user_struct *user = rb->mmap_user; + + atomic_long_sub((perf_data_size(rb) >> PAGE_SHIFT) + 1 - rb->mmap_locked, + &user->locked_vm); + atomic64_sub(rb->mmap_locked, &vma->vm_mm->pinned_vm); +} + static int perf_mmap_rb(struct vm_area_struct *vma, struct perf_event *event, unsigned long nr_pages) { @@ -7324,8 +7328,6 @@ static int perf_mmap_rb(struct vm_area_struct *vma, struct perf_event *event, if (!rb) return -ENOMEM; - refcount_set(&rb->mmap_count, 1); - rb->mmap_user = get_current_user(); rb->mmap_locked = extra; ring_buffer_attach(event, rb); @@ -7475,16 +7477,54 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) mapped(event, vma->vm_mm); /* - * Try to map it into the page table. On fail, invoke - * perf_mmap_close() to undo the above, as the callsite expects - * full cleanup in this case and therefore does not invoke - * vmops::close(). + * Try to map it into the page table. On fail undo the above, + * as the callsite expects full cleanup in this case and + * therefore does not invoke vmops::close(). */ ret = map_range(event->rb, vma); - if (ret) - perf_mmap_close(vma); + if (likely(!ret)) + return 0; + + /* Error path */ + + /* + * If this is the first mmap(), then event->mmap_count should + * be stable at 1. It is only modified by: + * perf_mmap_{open,close}() and perf_mmap(). + * + * The former are not possible because this mmap() hasn't been + * successful yet, and the latter is serialized by + * event->mmap_mutex which we still hold (note that mmap_lock + * is not strictly sufficient here, because the event fd can + * be passed to another process through trivial means like + * fork(), leading to concurrent mmap() from different mm). + * + * Make sure to remove event->rb before releasing + * event->mmap_mutex, such that any concurrent mmap() will not + * attempt use this failed buffer. + */ + if (refcount_read(&event->mmap_count) == 1) { + /* + * Minimal perf_mmap_close(); there can't be AUX or + * other events on account of this being the first. + */ + mapped = get_mapped(event, event_unmapped); + if (mapped) + mapped(event, vma->vm_mm); + perf_mmap_unaccount(vma, event->rb); + ring_buffer_attach(event, NULL); /* drops last rb->refcount */ + refcount_set(&event->mmap_count, 0); + return ret; + } + + /* + * Otherwise this is an already existing buffer, and there is + * no race vs first exposure, so fall-through and call + * perf_mmap_close(). + */ } + perf_mmap_close(vma); return ret; } diff --git a/kernel/events/internal.h b/kernel/events/internal.h index d9cc57083091..c03c4f2eea57 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -67,6 +67,7 @@ static inline void rb_free_rcu(struct rcu_head *rcu_head) struct perf_buffer *rb; rb = container_of(rcu_head, struct perf_buffer, rcu_head); + free_uid(rb->mmap_user); rb_free(rb); } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 3e7de2661417..9fe92161715e 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -340,6 +340,8 @@ ring_buffer_init(struct perf_buffer *rb, long watermark, int flags) rb->paused = 1; mutex_init(&rb->aux_mutex); + rb->mmap_user = get_current_user(); + refcount_set(&rb->mmap_count, 1); } void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags) diff --git a/kernel/rseq.c b/kernel/rseq.c index 38d3ef540760..e75e3a5e312c 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -236,11 +236,6 @@ static int __init rseq_debugfs_init(void) } __initcall(rseq_debugfs_init); -static bool rseq_set_ids(struct task_struct *t, struct rseq_ids *ids, u32 node_id) -{ - return rseq_set_ids_get_csaddr(t, ids, node_id, NULL); -} - static bool rseq_handle_cs(struct task_struct *t, struct pt_regs *regs) { struct rseq __user *urseq = t->rseq.usrptr; @@ -258,14 +253,16 @@ efault: static void rseq_slowpath_update_usr(struct pt_regs *regs) { /* - * Preserve rseq state and user_irq state. The generic entry code - * clears user_irq on the way out, the non-generic entry - * architectures are not having user_irq. + * Preserve has_rseq and user_irq state. The generic entry code clears + * user_irq on the way out, the non-generic entry architectures are not + * setting user_irq. */ - const struct rseq_event evt_mask = { .has_rseq = true, .user_irq = true, }; + const struct rseq_event evt_mask = { + .has_rseq = RSEQ_HAS_RSEQ_VERSION_MASK, + .user_irq = true, + }; struct task_struct *t = current; struct rseq_ids ids; - u32 node_id; bool event; if (unlikely(t->flags & PF_EXITING)) @@ -301,9 +298,9 @@ static void rseq_slowpath_update_usr(struct pt_regs *regs) if (!event) return; - node_id = cpu_to_node(ids.cpu_id); + ids.node_id = cpu_to_node(ids.cpu_id); - if (unlikely(!rseq_update_usr(t, regs, &ids, node_id))) { + if (unlikely(!rseq_update_usr(t, regs, &ids))) { /* * Clear the errors just in case this might survive magically, but * leave the rest intact. @@ -335,8 +332,9 @@ void __rseq_handle_slowpath(struct pt_regs *regs) void __rseq_signal_deliver(int sig, struct pt_regs *regs) { rseq_stat_inc(rseq_stats.signal); + /* - * Don't update IDs, they are handled on exit to user if + * Don't update IDs yet, they are handled on exit to user if * necessary. The important thing is to abort a critical section of * the interrupted context as after this point the instruction * pointer in @regs points to the signal handler. @@ -349,6 +347,13 @@ void __rseq_signal_deliver(int sig, struct pt_regs *regs) current->rseq.event.error = 0; force_sigsegv(sig); } + + /* + * In legacy mode, force the update of IDs before returning to user + * space to stay compatible. + */ + if (!rseq_v2(current)) + rseq_force_update(); } /* @@ -384,19 +389,22 @@ void rseq_syscall(struct pt_regs *regs) static bool rseq_reset_ids(void) { - struct rseq_ids ids = { - .cpu_id = RSEQ_CPU_ID_UNINITIALIZED, - .mm_cid = 0, - }; + struct rseq __user *rseq = current->rseq.usrptr; /* * If this fails, terminate it because this leaves the kernel in * stupid state as exit to user space will try to fixup the ids * again. */ - if (rseq_set_ids(current, &ids, 0)) - return true; + scoped_user_rw_access(rseq, efault) { + unsafe_put_user(0, &rseq->cpu_id_start, efault); + unsafe_put_user(RSEQ_CPU_ID_UNINITIALIZED, &rseq->cpu_id, efault); + unsafe_put_user(0, &rseq->node_id, efault); + unsafe_put_user(0, &rseq->mm_cid, efault); + } + return true; +efault: force_sig(SIGSEGV); return false; } @@ -404,70 +412,29 @@ static bool rseq_reset_ids(void) /* The original rseq structure size (including padding) is 32 bytes. */ #define ORIG_RSEQ_SIZE 32 -/* - * sys_rseq - setup restartable sequences for caller thread. - */ -SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig) +static long rseq_register(struct rseq __user * rseq, u32 rseq_len, int flags, u32 sig) { u32 rseqfl = 0; + u8 version = 1; - if (flags & RSEQ_FLAG_UNREGISTER) { - if (flags & ~RSEQ_FLAG_UNREGISTER) - return -EINVAL; - /* Unregister rseq for current thread. */ - if (current->rseq.usrptr != rseq || !current->rseq.usrptr) - return -EINVAL; - if (rseq_len != current->rseq.len) - return -EINVAL; - if (current->rseq.sig != sig) - return -EPERM; - if (!rseq_reset_ids()) - return -EFAULT; - rseq_reset(current); - return 0; - } - - if (unlikely(flags & ~(RSEQ_FLAG_SLICE_EXT_DEFAULT_ON))) - return -EINVAL; - - if (current->rseq.usrptr) { - /* - * If rseq is already registered, check whether - * the provided address differs from the prior - * one. - */ - if (current->rseq.usrptr != rseq || rseq_len != current->rseq.len) - return -EINVAL; - if (current->rseq.sig != sig) - return -EPERM; - /* Already registered. */ - return -EBUSY; - } - - /* - * If there was no rseq previously registered, ensure the provided rseq - * is properly aligned, as communcated to user-space through the ELF - * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq - * size, the required alignment is the original struct rseq alignment. - * - * The rseq_len is required to be greater or equal to the original rseq - * size. In order to be valid, rseq_len is either the original rseq size, - * or large enough to contain all supported fields, as communicated to - * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE. - */ - if (rseq_len < ORIG_RSEQ_SIZE || - (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) || - (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) || - rseq_len < offsetof(struct rseq, end)))) - return -EINVAL; if (!access_ok(rseq, rseq_len)) return -EFAULT; - if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) { - rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE; - if (rseq_slice_extension_enabled() && - (flags & RSEQ_FLAG_SLICE_EXT_DEFAULT_ON)) - rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_ENABLED; + /* + * Architectures, which use the generic IRQ entry code (at least) enable + * registrations with a size greater than the original v1 fixed sized + * @rseq_len, which has been validated already to utilize the optimized + * v2 ABI mode which also enables extended RSEQ features beyond MMCID. + */ + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY) && rseq_len > ORIG_RSEQ_SIZE) + version = 2; + + if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION) && version > 1) { + if (rseq_slice_extension_enabled()) { + rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE; + if (flags & RSEQ_FLAG_SLICE_EXT_DEFAULT_ON) + rseqfl |= RSEQ_CS_FLAG_SLICE_EXT_ENABLED; + } } scoped_user_write_access(rseq, efault) { @@ -485,7 +452,15 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 unsafe_put_user(RSEQ_CPU_ID_UNINITIALIZED, &rseq->cpu_id, efault); unsafe_put_user(0U, &rseq->node_id, efault); unsafe_put_user(0U, &rseq->mm_cid, efault); - unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); + + /* + * All fields past mm_cid are only valid for non-legacy v2 + * registrations. + */ + if (version > 1) { + if (IS_ENABLED(CONFIG_RSEQ_SLICE_EXTENSION)) + unsafe_put_user(0U, &rseq->slice_ctrl.all, efault); + } } /* @@ -501,11 +476,10 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 #endif /* - * If rseq was previously inactive, and has just been - * registered, ensure the cpu_id_start and cpu_id fields - * are updated before returning to user-space. + * Ensure the cpu_id_start and cpu_id fields are updated before + * returning to user-space. */ - current->rseq.event.has_rseq = true; + current->rseq.event.has_rseq = version; rseq_force_update(); return 0; @@ -513,6 +487,80 @@ efault: return -EFAULT; } +static long rseq_unregister(struct rseq __user * rseq, u32 rseq_len, int flags, u32 sig) +{ + if (flags & ~RSEQ_FLAG_UNREGISTER) + return -EINVAL; + if (current->rseq.usrptr != rseq || !current->rseq.usrptr) + return -EINVAL; + if (rseq_len != current->rseq.len) + return -EINVAL; + if (current->rseq.sig != sig) + return -EPERM; + if (!rseq_reset_ids()) + return -EFAULT; + rseq_reset(current); + return 0; +} + +static long rseq_reregister(struct rseq __user * rseq, u32 rseq_len, u32 sig) +{ + /* + * If rseq is already registered, check whether the provided address + * differs from the prior one. + */ + if (current->rseq.usrptr != rseq || rseq_len != current->rseq.len) + return -EINVAL; + if (current->rseq.sig != sig) + return -EPERM; + /* Already registered. */ + return -EBUSY; +} + +static bool rseq_length_valid(struct rseq __user *rseq, unsigned int rseq_len) +{ + /* + * Ensure the provided rseq is properly aligned, as communicated to + * user-space through the ELF auxiliary vector AT_RSEQ_ALIGN. If + * rseq_len is the original rseq size, the required alignment is the + * original struct rseq alignment. + * + * In order to be valid, rseq_len is either the original rseq size, or + * large enough to contain all supported fields, as communicated to + * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE. + */ + if (rseq_len < ORIG_RSEQ_SIZE) + return false; + + if (rseq_len == ORIG_RSEQ_SIZE) + return IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE); + + return IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) && + rseq_len >= offsetof(struct rseq, end); +} + +#define RSEQ_FLAGS_SUPPORTED (RSEQ_FLAG_SLICE_EXT_DEFAULT_ON) + +/* + * sys_rseq - Register or unregister restartable sequences for the caller thread. + */ +SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig) +{ + if (flags & RSEQ_FLAG_UNREGISTER) + return rseq_unregister(rseq, rseq_len, flags, sig); + + if (unlikely(flags & ~RSEQ_FLAGS_SUPPORTED)) + return -EINVAL; + + if (current->rseq.usrptr) + return rseq_reregister(rseq, rseq_len, sig); + + if (!rseq_length_valid(rseq, rseq_len)) + return -EINVAL; + + return rseq_register(rseq, rseq_len, flags, sig); +} + #ifdef CONFIG_RSEQ_SLICE_EXTENSION struct slice_timer { struct hrtimer timer; @@ -713,6 +761,8 @@ int rseq_slice_extension_prctl(unsigned long arg2, unsigned long arg3) return -ENOTSUPP; if (!current->rseq.usrptr) return -ENXIO; + if (!rseq_v2(current)) + return -ENOTSUPP; /* No change? */ if (enable == !!current->rseq.slice.state.enabled) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3ca3cfa580c1..25f672d6dcaa 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -913,11 +913,11 @@ bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) * * lag_i >= 0 -> V >= v_i * - * \Sum (v_i - v)*w_i - * V = ------------------ + v + * \Sum (v_i - v0)*w_i + * V = ------------------- + v0 * \Sum w_i * - * lag_i >= 0 -> \Sum (v_i - v)*w_i >= (v_i - v)*(\Sum w_i) + * lag_i >= 0 -> \Sum (v_i - v0)*w_i >= (v_i - v0)*(\Sum w_i) * * Note: using 'avg_vruntime() > se->vruntime' is inaccurate due * to the loss in precision caused by the division. @@ -925,7 +925,7 @@ bool update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime) { struct sched_entity *curr = cfs_rq->curr; - s64 avg = cfs_rq->sum_w_vruntime; + s64 key, avg = cfs_rq->sum_w_vruntime; long load = cfs_rq->sum_weight; if (curr && curr->on_rq) { @@ -935,7 +935,36 @@ static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime) load += weight; } - return avg >= vruntime_op(vruntime, "-", cfs_rq->zero_vruntime) * load; + key = vruntime_op(vruntime, "-", cfs_rq->zero_vruntime); + + /* + * The worst case term for @key includes 'NSEC_TICK * NICE_0_LOAD' + * and @load obviously includes NICE_0_LOAD. NSEC_TICK is around 24 + * bits, while NICE_0_LOAD is 20 on 64bit and 10 otherwise. + * + * This gives that on 64bit the product will be at least 64bit which + * overflows s64, while on 32bit it will only be 44bits and should fit + * comfortably. + */ +#ifdef CONFIG_64BIT +#ifdef CONFIG_ARCH_SUPPORTS_INT128 + /* This often results in simpler code than __builtin_mul_overflow(). */ + return avg >= (__int128)key * load; +#else + s64 rhs; + /* + * On overflow, the sign of key tells us the correct answer: a large + * positive key means vruntime >> V, so not eligible; a large negative + * key means vruntime << V, so eligible. + */ + if (check_mul_overflow(key, load, &rhs)) + return key <= 0; + + return avg >= rhs; +#endif +#else /* 32bit */ + return avg >= key * load; +#endif } int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -9221,9 +9250,10 @@ pick: /* * Because p is enqueued, nse being null can only mean that we - * dequeued a delayed task. + * dequeued a delayed task. If there are still entities queued in + * cfs, check if the next one will be p. */ - if (!nse) + if (!nse && cfs_rq->nr_queued) goto pick; if (sched_feat(RUN_TO_PARITY)) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 623445603725..226a6329f3e9 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -199,7 +199,16 @@ static void ipi_rseq(void *info) * is negligible. */ smp_mb(); - rseq_sched_switch_event(current); + /* + * Legacy mode requires that IDs are written and the critical section is + * evaluated. V2 optimized mode handles the critical section and IDs are + * only updated if they change as a consequence of preemption after + * return from this IPI. + */ + if (rseq_v2(current)) + rseq_sched_switch_event(current); + else + rseq_force_update(); } static void ipi_sync_rq_state(void *info) diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 155eeaea4113..1d0d3a4058d5 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -1860,19 +1860,37 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node, * child to the new parents. So tmigr_active_up() activates the * new parents while walking up from the old root to the new. * - * * It is ensured that @start is active, as this setup path is - * executed in hotplug prepare callback. This is executed by an - * already connected and !idle CPU. Even if all other CPUs go idle, - * the CPU executing the setup will be responsible up to current top - * level group. And the next time it goes inactive, it will release - * the new childmask and parent to subsequent walkers through this - * @child. Therefore propagate active state unconditionally. + * * It is ensured that @start is active, (or on the way to be activated + * by another CPU that woke up before the current one) as this setup path + * is executed in hotplug prepare callback. This is executed by an already + * connected and !idle CPU in the hierarchy. + * + * * The below RmW atomic operation ensures that: + * + * 1) If the old root has been completely activated, the latest state is + * acquired (the below implicit acquire pairs with the implicit release + * from cmpxchg() in tmigr_active_up()). + * + * 2) If the old root is still on the way to be activated, the lagging behind + * CPU performing the activation will acquire the links up to the new root. + * (The below implicit release pairs with the implicit acquire from cmpxchg() + * in tmigr_active_up()). + * + * 3) Every subsequent CPU below the old root will acquire the new links while + * walking through the old root (The below implicit release pairs with the + * implicit acquire from cmpxchg() in either tmigr_active_up()) or + * tmigr_inactive_up(). */ - state.state = atomic_read(&start->migr_state); - WARN_ON_ONCE(!state.active); + state.state = atomic_fetch_or(0, &start->migr_state); WARN_ON_ONCE(!start->parent); - data.childmask = start->groupmask; - __walk_groups_from(tmigr_active_up, &data, start, start->parent); + /* + * If the state of the old root is inactive, another CPU is on its way to activate + * it and propagate to the new root. + */ + if (state.active) { + data.childmask = start->groupmask; + __walk_groups_from(tmigr_active_up, &data, start, start->parent); + } } /* Root update */ diff --git a/rust/Makefile b/rust/Makefile index b361bfedfdf0..b9e9f512cec3 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -403,6 +403,8 @@ BINDGEN_TARGET_x86 := x86_64-linux-gnu BINDGEN_TARGET_arm64 := aarch64-linux-gnu BINDGEN_TARGET_arm := arm-linux-gnueabi BINDGEN_TARGET_loongarch := loongarch64-linux-gnusf +# This is only for i386 UM builds, which need the 32-bit target not -m32 +BINDGEN_TARGET_i386 := i386-linux-gnu BINDGEN_TARGET_um := $(BINDGEN_TARGET_$(SUBARCH)) BINDGEN_TARGET := $(BINDGEN_TARGET_$(SRCARCH)) diff --git a/rust/pin-init/internal/src/init.rs b/rust/pin-init/internal/src/init.rs index daa3f1c6466e..487ee0013faf 100644 --- a/rust/pin-init/internal/src/init.rs +++ b/rust/pin-init/internal/src/init.rs @@ -249,22 +249,6 @@ fn init_fields( }); // Again span for better diagnostics let write = quote_spanned!(ident.span()=> ::core::ptr::write); - // NOTE: the field accessor ensures that the initialized field is properly aligned. - // Unaligned fields will cause the compiler to emit E0793. We do not support - // unaligned fields since `Init::__init` requires an aligned pointer; the call to - // `ptr::write` below has the same requirement. - let accessor = if pinned { - let project_ident = format_ident!("__project_{ident}"); - quote! { - // SAFETY: TODO - unsafe { #data.#project_ident(&mut (*#slot).#ident) } - } - } else { - quote! { - // SAFETY: TODO - unsafe { &mut (*#slot).#ident } - } - }; quote! { #(#attrs)* { @@ -272,51 +256,31 @@ fn init_fields( // SAFETY: TODO unsafe { #write(&raw mut (*#slot).#ident, #value_ident) }; } - #(#cfgs)* - #[allow(unused_variables)] - let #ident = #accessor; } } InitializerKind::Init { ident, value, .. } => { // Again span for better diagnostics let init = format_ident!("init", span = value.span()); - // NOTE: the field accessor ensures that the initialized field is properly aligned. - // Unaligned fields will cause the compiler to emit E0793. We do not support - // unaligned fields since `Init::__init` requires an aligned pointer; the call to - // `ptr::write` below has the same requirement. - let (value_init, accessor) = if pinned { - let project_ident = format_ident!("__project_{ident}"); - ( - quote! { - // SAFETY: - // - `slot` is valid, because we are inside of an initializer closure, we - // return when an error/panic occurs. - // - We also use `#data` to require the correct trait (`Init` or `PinInit`) - // for `#ident`. - unsafe { #data.#ident(&raw mut (*#slot).#ident, #init)? }; - }, - quote! { - // SAFETY: TODO - unsafe { #data.#project_ident(&mut (*#slot).#ident) } - }, - ) + let value_init = if pinned { + quote! { + // SAFETY: + // - `slot` is valid, because we are inside of an initializer closure, we + // return when an error/panic occurs. + // - We also use `#data` to require the correct trait (`Init` or `PinInit`) + // for `#ident`. + unsafe { #data.#ident(&raw mut (*#slot).#ident, #init)? }; + } } else { - ( - quote! { - // SAFETY: `slot` is valid, because we are inside of an initializer - // closure, we return when an error/panic occurs. - unsafe { - ::pin_init::Init::__init( - #init, - &raw mut (*#slot).#ident, - )? - }; - }, - quote! { - // SAFETY: TODO - unsafe { &mut (*#slot).#ident } - }, - ) + quote! { + // SAFETY: `slot` is valid, because we are inside of an initializer + // closure, we return when an error/panic occurs. + unsafe { + ::pin_init::Init::__init( + #init, + &raw mut (*#slot).#ident, + )? + }; + } }; quote! { #(#attrs)* @@ -324,9 +288,6 @@ fn init_fields( let #init = #value; #value_init } - #(#cfgs)* - #[allow(unused_variables)] - let #ident = #accessor; } } InitializerKind::Code { block: value, .. } => quote! { @@ -339,18 +300,41 @@ fn init_fields( if let Some(ident) = kind.ident() { // `mixed_site` ensures that the guard is not accessible to the user-controlled code. let guard = format_ident!("__{ident}_guard", span = Span::mixed_site()); + + // NOTE: The reference is derived from the guard so that it only lives as long as the + // guard does and cannot escape the scope. If it's created via `&mut (*#slot).#ident` + // like the unaligned field guard, it will become effectively `'static`. + let accessor = if pinned { + let project_ident = format_ident!("__project_{ident}"); + quote! { + // SAFETY: the initialization is pinned. + unsafe { #data.#project_ident(#guard.let_binding()) } + } + } else { + quote! { + #guard.let_binding() + } + }; + res.extend(quote! { #(#cfgs)* - // Create the drop guard: + // Create the drop guard. // - // We rely on macro hygiene to make it impossible for users to access this local - // variable. - // SAFETY: We forget the guard later when initialization has succeeded. - let #guard = unsafe { + // SAFETY: + // - `&raw mut (*slot).#ident` is valid. + // - `make_field_check` checks that `&raw mut (*slot).#ident` is properly aligned. + // - `(*slot).#ident` has been initialized above. + // - We only need the ownership to the pointee back when initialization has + // succeeded, where we `forget` the guard. + let mut #guard = unsafe { ::pin_init::__internal::DropGuard::new( &raw mut (*slot).#ident ) }; + + #(#cfgs)* + #[allow(unused_variables)] + let #ident = #accessor; }); guards.push(guard); guard_attrs.push(cfgs); @@ -367,49 +351,49 @@ fn init_fields( } } -/// Generate the check for ensuring that every field has been initialized. +/// Generate the check for ensuring that every field has been initialized and aligned. fn make_field_check( fields: &Punctuated, init_kind: InitKind, path: &Path, ) -> TokenStream { - let field_attrs = fields + let field_attrs: Vec<_> = fields .iter() - .filter_map(|f| f.kind.ident().map(|_| &f.attrs)); - let field_name = fields.iter().filter_map(|f| f.kind.ident()); - match init_kind { - InitKind::Normal => quote! { - // We use unreachable code to ensure that all fields have been mentioned exactly once, - // this struct initializer will still be type-checked and complain with a very natural - // error message if a field is forgotten/mentioned more than once. - #[allow(unreachable_code, clippy::diverging_sub_expression)] - // SAFETY: this code is never executed. - let _ = || unsafe { - ::core::ptr::write(slot, #path { - #( - #(#field_attrs)* - #field_name: ::core::panic!(), - )* - }) - }; - }, - InitKind::Zeroing => quote! { - // We use unreachable code to ensure that all fields have been mentioned at most once. - // Since the user specified `..Zeroable::zeroed()` at the end, all missing fields will - // be zeroed. This struct initializer will still be type-checked and complain with a - // very natural error message if a field is mentioned more than once, or doesn't exist. - #[allow(unreachable_code, clippy::diverging_sub_expression, unused_assignments)] - // SAFETY: this code is never executed. - let _ = || unsafe { - ::core::ptr::write(slot, #path { - #( - #(#field_attrs)* - #field_name: ::core::panic!(), - )* - ..::core::mem::zeroed() - }) - }; - }, + .filter_map(|f| f.kind.ident().map(|_| &f.attrs)) + .collect(); + let field_name: Vec<_> = fields.iter().filter_map(|f| f.kind.ident()).collect(); + let zeroing_trailer = match init_kind { + InitKind::Normal => None, + InitKind::Zeroing => Some(quote! { + ..::core::mem::zeroed() + }), + }; + quote! { + #[allow(unreachable_code, clippy::diverging_sub_expression)] + // We use unreachable code to perform field checks. They're still checked by the compiler. + // SAFETY: this code is never executed. + let _ = || unsafe { + // Create references to ensure that the initialized field is properly aligned. + // Unaligned fields will cause the compiler to emit E0793. We do not support + // unaligned fields since `Init::__init` requires an aligned pointer; the call to + // `ptr::write` for value-initialization case has the same requirement. + #( + #(#field_attrs)* + let _ = &(*slot).#field_name; + )* + + // If the zeroing trailer is not present, this checks that all fields have been + // mentioned exactly once. If the zeroing trailer is present, all missing fields will be + // zeroed, so this checks that all fields have been mentioned at most once. The use of + // struct initializer will still generate very natural error messages for any misuse. + ::core::ptr::write(slot, #path { + #( + #(#field_attrs)* + #field_name: ::core::panic!(), + )* + #zeroing_trailer + }) + }; } } diff --git a/rust/pin-init/src/__internal.rs b/rust/pin-init/src/__internal.rs index 90adbdc1893b..5720a621aed7 100644 --- a/rust/pin-init/src/__internal.rs +++ b/rust/pin-init/src/__internal.rs @@ -238,32 +238,42 @@ fn stack_init_reuse() { /// When a value of this type is dropped, it drops a `T`. /// /// Can be forgotten to prevent the drop. +/// +/// # Invariants +/// +/// - `ptr` is valid and properly aligned. +/// - `*ptr` is initialized and owned by this guard. pub struct DropGuard { ptr: *mut T, } impl DropGuard { - /// Creates a new [`DropGuard`]. It will [`ptr::drop_in_place`] `ptr` when it gets dropped. + /// Creates a drop guard and transfer the ownership of the pointer content. + /// + /// The ownership is only relinguished if the guard is forgotten via [`core::mem::forget`]. /// /// # Safety /// - /// `ptr` must be a valid pointer. - /// - /// It is the callers responsibility that `self` will only get dropped if the pointee of `ptr`: - /// - has not been dropped, - /// - is not accessible by any other means, - /// - will not be dropped by any other means. + /// - `ptr` is valid and properly aligned. + /// - `*ptr` is initialized, and the ownership is transferred to this guard. #[inline] pub unsafe fn new(ptr: *mut T) -> Self { + // INVARIANT: By safety requirement. Self { ptr } } + + /// Create a let binding for accessor use. + #[inline] + pub fn let_binding(&mut self) -> &mut T { + // SAFETY: Per type invariant. + unsafe { &mut *self.ptr } + } } impl Drop for DropGuard { #[inline] fn drop(&mut self) { - // SAFETY: A `DropGuard` can only be constructed using the unsafe `new` function - // ensuring that this operation is safe. + // SAFETY: `self.ptr` is valid, properly aligned and `*self.ptr` is owned by this guard. unsafe { ptr::drop_in_place(self.ptr) } } } diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 4ef90823b652..50d69e22ee7a 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -14,14 +14,20 @@ LDLIBS += -lpthread -ldl # still track changes to header files and depend on shared object. OVERRIDE_TARGETS = 1 -TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ - param_test_benchmark param_test_compare_twice param_test_mm_cid \ - param_test_mm_cid_benchmark param_test_mm_cid_compare_twice \ - syscall_errors_test slice_test +TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test \ + param_test_benchmark param_test_mm_cid_benchmark -TEST_GEN_PROGS_EXTENDED = librseq.so +TEST_GEN_PROGS_EXTENDED = librseq.so \ + param_test \ + param_test_compare_twice \ + param_test_mm_cid \ + param_test_mm_cid_compare_twice \ + syscall_errors_test \ + legacy_check \ + slice_test \ + check_optimized -TEST_PROGS = run_param_test.sh run_syscall_errors_test.sh +TEST_PROGS = run_param_test.sh run_syscall_errors_test.sh run_legacy_check.sh run_timeslice_test.sh TEST_FILES := settings @@ -62,3 +68,6 @@ $(OUTPUT)/syscall_errors_test: syscall_errors_test.c $(TEST_GEN_PROGS_EXTENDED) $(OUTPUT)/slice_test: slice_test.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h $(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@ + +$(OUTPUT)/check_optimized: check_optimized.c $(TEST_GEN_PROGS_EXTENDED) rseq.h rseq-*.h + $(CC) $(CFLAGS) $< $(LDLIBS) -lrseq -o $@ diff --git a/tools/testing/selftests/rseq/check_optimized.c b/tools/testing/selftests/rseq/check_optimized.c new file mode 100644 index 000000000000..a13e3f2c8fc6 --- /dev/null +++ b/tools/testing/selftests/rseq/check_optimized.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include + +#include "rseq.h" + +int main(int argc, char **argv) +{ + if (__rseq_register_current_thread(true, false)) + return -1; + return 0; +} diff --git a/tools/testing/selftests/rseq/legacy_check.c b/tools/testing/selftests/rseq/legacy_check.c new file mode 100644 index 000000000000..3f7de4e28303 --- /dev/null +++ b/tools/testing/selftests/rseq/legacy_check.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif + +#include +#include +#include +#include + +#include "rseq.h" + +#include "../kselftest_harness.h" + +FIXTURE(legacy) +{ +}; + +static int cpu_id_in_sigfn = -1; + +static void sigfn(int sig) +{ + struct rseq_abi *rs = rseq_get_abi(); + + cpu_id_in_sigfn = rs->cpu_id_start; +} + +FIXTURE_SETUP(legacy) +{ + int res = __rseq_register_current_thread(true, true); + + switch (res) { + case -ENOSYS: + SKIP(return, "RSEQ not enabled\n"); + case -EBUSY: + SKIP(return, "GLIBC owns RSEQ. Disable GLIBC RSEQ registration\n"); + default: + ASSERT_EQ(res, 0); + } + + ASSERT_NE(signal(SIGUSR1, sigfn), SIG_ERR); +} + +FIXTURE_TEARDOWN(legacy) +{ +} + +TEST_F(legacy, legacy_test) +{ + struct rseq_abi *rs = rseq_get_abi(); + + ASSERT_NE(rs, NULL); + + /* Overwrite rs::cpu_id_start */ + rs->cpu_id_start = -1; + sleep(1); + ASSERT_NE(rs->cpu_id_start, -1); + + rs->cpu_id_start = -1; + ASSERT_EQ(raise(SIGUSR1), 0); + ASSERT_NE(rs->cpu_id_start, -1); + ASSERT_NE(cpu_id_in_sigfn, -1); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index 05d03e679e06..e1e98dbabe4b 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -38,7 +38,7 @@ static int opt_modulo, verbose; static int opt_yield, opt_signal, opt_sleep, opt_disable_rseq, opt_threads = 200, opt_disable_mod = 0, opt_test = 's'; - +static bool opt_rseq_legacy; static long long opt_reps = 5000; static __thread __attribute__((tls_model("initial-exec"))) @@ -281,9 +281,12 @@ unsigned int yield_mod_cnt, nr_abort; } \ } +#define rseq_no_glibc true + #else #define printf_verbose(fmt, ...) +#define rseq_no_glibc false #endif /* BENCHMARK */ @@ -481,7 +484,7 @@ void *test_percpu_spinlock_thread(void *arg) long long i, reps; if (!opt_disable_rseq && thread_data->reg && - rseq_register_current_thread()) + __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = thread_data->reps; for (i = 0; i < reps; i++) { @@ -558,7 +561,7 @@ void *test_percpu_inc_thread(void *arg) long long i, reps; if (!opt_disable_rseq && thread_data->reg && - rseq_register_current_thread()) + __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = thread_data->reps; for (i = 0; i < reps; i++) { @@ -712,7 +715,7 @@ void *test_percpu_list_thread(void *arg) long long i, reps; struct percpu_list *list = (struct percpu_list *)arg; - if (!opt_disable_rseq && rseq_register_current_thread()) + if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = opt_reps; @@ -895,7 +898,7 @@ void *test_percpu_buffer_thread(void *arg) long long i, reps; struct percpu_buffer *buffer = (struct percpu_buffer *)arg; - if (!opt_disable_rseq && rseq_register_current_thread()) + if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = opt_reps; @@ -1105,7 +1108,7 @@ void *test_percpu_memcpy_buffer_thread(void *arg) long long i, reps; struct percpu_memcpy_buffer *buffer = (struct percpu_memcpy_buffer *)arg; - if (!opt_disable_rseq && rseq_register_current_thread()) + if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) abort(); reps = opt_reps; @@ -1258,7 +1261,7 @@ void *test_membarrier_worker_thread(void *arg) const int iters = opt_reps; int i; - if (rseq_register_current_thread()) { + if (__rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) { fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", errno, strerror(errno)); abort(); @@ -1323,7 +1326,7 @@ void *test_membarrier_manager_thread(void *arg) intptr_t expect_a = 0, expect_b = 0; int cpu_a = 0, cpu_b = 0; - if (rseq_register_current_thread()) { + if (__rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) { fprintf(stderr, "Error: rseq_register_current_thread(...) failed(%d): %s\n", errno, strerror(errno)); abort(); @@ -1475,6 +1478,7 @@ static void show_usage(int argc, char **argv) printf(" [-D M] Disable rseq for each M threads\n"); printf(" [-T test] Choose test: (s)pinlock, (l)ist, (b)uffer, (m)emcpy, (i)ncrement, membarrie(r)\n"); printf(" [-M] Push into buffer and memcpy buffer with memory barriers.\n"); + printf(" [-O] Test with optimized RSEQ\n"); printf(" [-v] Verbose output.\n"); printf(" [-h] Show this help.\n"); printf("\n"); @@ -1602,6 +1606,9 @@ int main(int argc, char **argv) case 'M': opt_mo = RSEQ_MO_RELEASE; break; + case 'L': + opt_rseq_legacy = true; + break; default: show_usage(argc, argv); goto error; @@ -1618,7 +1625,7 @@ int main(int argc, char **argv) if (set_signal_handler()) goto error; - if (!opt_disable_rseq && rseq_register_current_thread()) + if (!opt_disable_rseq && __rseq_register_current_thread(rseq_no_glibc, opt_rseq_legacy)) goto error; if (!opt_disable_rseq && !rseq_validate_cpu_id()) { fprintf(stderr, "Error: cpu id getter unavailable\n"); diff --git a/tools/testing/selftests/rseq/rseq-abi.h b/tools/testing/selftests/rseq/rseq-abi.h index ecef315204b2..5f4ea2152c2f 100644 --- a/tools/testing/selftests/rseq/rseq-abi.h +++ b/tools/testing/selftests/rseq/rseq-abi.h @@ -191,10 +191,15 @@ struct rseq_abi { */ struct rseq_abi_slice_ctrl slice_ctrl; + /* + * Place holder to push the size above 32 bytes. + */ + __u8 __reserved; + /* * Flexible array member at end of structure, after last feature field. */ char end[]; -} __attribute__((aligned(4 * sizeof(__u64)))); +} __attribute__((aligned(256))); #endif /* _RSEQ_ABI_H */ diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index a736727b83c1..be0d0a97031e 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -56,6 +56,7 @@ ptrdiff_t rseq_offset; * unsuccessful. */ unsigned int rseq_size = -1U; +static unsigned int rseq_alloc_size; /* Flags used during rseq registration. */ unsigned int rseq_flags; @@ -115,29 +116,17 @@ bool rseq_available(void) } } -/* The rseq areas need to be at least 32 bytes. */ -static -unsigned int get_rseq_min_alloc_size(void) -{ - unsigned int alloc_size = rseq_size; - - if (alloc_size < ORIG_RSEQ_ALLOC_SIZE) - alloc_size = ORIG_RSEQ_ALLOC_SIZE; - return alloc_size; -} - /* * Return the feature size supported by the kernel. * * Depending on the value returned by getauxval(AT_RSEQ_FEATURE_SIZE): * - * 0: Return ORIG_RSEQ_FEATURE_SIZE (20) + * 0: Return ORIG_RSEQ_FEATURE_SIZE (20) * > 0: Return the value from getauxval(AT_RSEQ_FEATURE_SIZE). * * It should never return a value below ORIG_RSEQ_FEATURE_SIZE. */ -static -unsigned int get_rseq_kernel_feature_size(void) +static unsigned int get_rseq_kernel_feature_size(void) { unsigned long auxv_rseq_feature_size, auxv_rseq_align; @@ -152,15 +141,24 @@ unsigned int get_rseq_kernel_feature_size(void) return ORIG_RSEQ_FEATURE_SIZE; } -int rseq_register_current_thread(void) +int __rseq_register_current_thread(bool nolibc, bool legacy) { + unsigned int size; int rc; if (!rseq_ownership) { /* Treat libc's ownership as a successful registration. */ - return 0; + return nolibc ? -EBUSY : 0; } - rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG); + + /* The minimal allocation size is 32, which is the legacy allocation size */ + size = get_rseq_kernel_feature_size(); + if (legacy || size < ORIG_RSEQ_ALLOC_SIZE) + rseq_alloc_size = ORIG_RSEQ_ALLOC_SIZE; + else + rseq_alloc_size = size; + + rc = sys_rseq(&__rseq.abi, rseq_alloc_size, 0, RSEQ_SIG); if (rc) { /* * After at least one thread has registered successfully @@ -179,9 +177,8 @@ int rseq_register_current_thread(void) * The first thread to register sets the rseq_size to mimic the libc * behavior. */ - if (RSEQ_READ_ONCE(rseq_size) == 0) { - RSEQ_WRITE_ONCE(rseq_size, get_rseq_kernel_feature_size()); - } + if (RSEQ_READ_ONCE(rseq_size) == 0) + RSEQ_WRITE_ONCE(rseq_size, size); return 0; } @@ -194,7 +191,7 @@ int rseq_unregister_current_thread(void) /* Treat libc's ownership as a successful unregistration. */ return 0; } - rc = sys_rseq(&__rseq.abi, get_rseq_min_alloc_size(), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); + rc = sys_rseq(&__rseq.abi, rseq_alloc_size, RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG); if (rc) return -1; return 0; diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index f51a5fdb0444..c62ebb9290c0 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -8,6 +8,7 @@ #ifndef RSEQ_H #define RSEQ_H +#include #include #include #include @@ -142,7 +143,12 @@ static inline struct rseq_abi *rseq_get_abi(void) * succeed. A restartable sequence executed from a non-registered * thread will always fail. */ -int rseq_register_current_thread(void); +int __rseq_register_current_thread(bool nolibc, bool legacy); + +static inline int rseq_register_current_thread(void) +{ + return __rseq_register_current_thread(false, false); +} /* * Unregister rseq for current thread. diff --git a/tools/testing/selftests/rseq/run_legacy_check.sh b/tools/testing/selftests/rseq/run_legacy_check.sh new file mode 100755 index 000000000000..5577b46ea092 --- /dev/null +++ b/tools/testing/selftests/rseq/run_legacy_check.sh @@ -0,0 +1,4 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0" ./legacy_check diff --git a/tools/testing/selftests/rseq/run_param_test.sh b/tools/testing/selftests/rseq/run_param_test.sh index 8d31426ab41f..69a3fa049929 100755 --- a/tools/testing/selftests/rseq/run_param_test.sh +++ b/tools/testing/selftests/rseq/run_param_test.sh @@ -34,6 +34,11 @@ REPS=1000 SLOW_REPS=100 NR_THREADS=$((6*${NR_CPUS})) +# Prevent GLIBC from registering RSEQ so the selftest can run in legacy and +# performance optimized mode. +GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0" +export GLIBC_TUNABLES + function do_tests() { local i=0 @@ -103,6 +108,40 @@ function inject_blocking() NR_LOOPS= } +echo "Testing in legacy RSEQ mode" +echo "Yield injection (25%)" +inject_blocking -m 4 -y -L + +echo "Yield injection (50%)" +inject_blocking -m 2 -y -L + +echo "Yield injection (100%)" +inject_blocking -m 1 -y -L + +echo "Kill injection (25%)" +inject_blocking -m 4 -k -L + +echo "Kill injection (50%)" +inject_blocking -m 2 -k -L + +echo "Kill injection (100%)" +inject_blocking -m 1 -k -L + +echo "Sleep injection (1ms, 25%)" +inject_blocking -m 4 -s 1 -L + +echo "Sleep injection (1ms, 50%)" +inject_blocking -m 2 -s 1 -L + +echo "Sleep injection (1ms, 100%)" +inject_blocking -m 1 -s 1 -L + +./check_optimized || { + echo "Skipping optimized RSEQ mode test. Not supported"; + exit 0 +} + +echo "Testing in optimized RSEQ mode" echo "Yield injection (25%)" inject_blocking -m 4 -y diff --git a/tools/testing/selftests/rseq/run_timeslice_test.sh b/tools/testing/selftests/rseq/run_timeslice_test.sh new file mode 100755 index 000000000000..551ebed71ec6 --- /dev/null +++ b/tools/testing/selftests/rseq/run_timeslice_test.sh @@ -0,0 +1,14 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ + +# Prevent GLIBC from registering RSEQ so the selftest can run in legacy +# and performance optimized mode. +GLIBC_TUNABLES="${GLIBC_TUNABLES:-}:glibc.pthread.rseq=0" +export GLIBC_TUNABLES + +./check_optimized || { + echo "Skipping optimized RSEQ mode test. Not supported"; + exit 0 +} + +./slice_test diff --git a/tools/testing/selftests/rseq/slice_test.c b/tools/testing/selftests/rseq/slice_test.c index 357122dcb487..e402d4440bc2 100644 --- a/tools/testing/selftests/rseq/slice_test.c +++ b/tools/testing/selftests/rseq/slice_test.c @@ -124,6 +124,13 @@ FIXTURE_SETUP(slice_ext) { cpu_set_t affinity; + if (__rseq_register_current_thread(true, false)) + SKIP(return, "RSEQ not supported\n"); + + if (prctl(PR_RSEQ_SLICE_EXTENSION, PR_RSEQ_SLICE_EXTENSION_SET, + PR_RSEQ_SLICE_EXT_ENABLE, 0, 0)) + SKIP(return, "Time slice extension not supported\n"); + ASSERT_EQ(sched_getaffinity(0, sizeof(affinity), &affinity), 0); /* Pin it on a single CPU. Avoid CPU 0 */ @@ -137,11 +144,6 @@ FIXTURE_SETUP(slice_ext) break; } - ASSERT_EQ(rseq_register_current_thread(), 0); - - ASSERT_EQ(prctl(PR_RSEQ_SLICE_EXTENSION, PR_RSEQ_SLICE_EXTENSION_SET, - PR_RSEQ_SLICE_EXT_ENABLE, 0, 0), 0); - self->noise_params.noise_nsecs = variant->noise_nsecs; self->noise_params.sleep_nsecs = variant->sleep_nsecs; self->noise_params.run = 1;