From 342cb0d80613719c5e5ac30619e54b9a3fd83625 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Mon, 20 Jun 2022 13:39:04 +0300 Subject: [PATCH 1/9] perf inject: Fix missing free in copy_kcore_dir() Free string allocated by asprintf(). Fixes: d8fc08550929bb84 ("perf inject: Keep a copy of kcore_dir") Signed-off-by: Adrian Hunter Cc: Adrian Hunter Cc: Jiri Olsa Link: https://lore.kernel.org/r/20220620103904.7960-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index a75bf11585b5..063f74f5b8db 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -891,7 +891,9 @@ static int copy_kcore_dir(struct perf_inject *inject) if (ret < 0) return ret; pr_debug("%s\n", cmd); - return system(cmd); + ret = system(cmd); + free(cmd); + return ret; } static int output_fd(struct perf_inject *inject) From 0fdd435cb4f873b5602913db4f2ba497a5443daf Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 13 Nov 2021 11:08:31 -0300 Subject: [PATCH 2/9] tools headers UAPI: Sync drm/i915_drm.h with the kernel sources To pick up the changes in: ecf8eca51f33dbfd ("drm/i915/xehp: Add compute engine ABI") 991b4de3275728fd ("drm/i915/uapi: Add kerneldoc for engine class enum") c94fde8f516610b0 ("drm/i915/uapi: Add DRM_I915_QUERY_GEOMETRY_SUBSLICES") 1c671ad753dbbf5f ("drm/i915/doc: Link query items to their uapi structs") a2e5402691e23269 ("drm/i915/doc: Convert perf UAPI comments to kerneldoc") 462ac1cdf4d7acf1 ("drm/i915/doc: Convert drm_i915_query_topology_info comment to kerneldoc") 034d47b25b2ce627 ("drm/i915/uapi: Document DRM_I915_QUERY_HWCONFIG_BLOB") 78e1fb3112c0ac44 ("drm/i915/uapi: Add query for hwconfig blob") That don't add any new ioctl, so no changes in tooling. This silences this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/drm/i915_drm.h' differs from latest version at 'include/uapi/drm/i915_drm.h' diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h Cc: John Harrison Cc: Matt Atwood Cc: Matt Roper Cc: Rodrigo Vivi Cc: Tvrtko Ursulin Link: http://lore.kernel.org/lkml/YrDi4ALYjv9Mdocq@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/i915_drm.h | 353 +++++++++++++++++++++++------- 1 file changed, 272 insertions(+), 81 deletions(-) diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 05c3642aaece..a2def7b27009 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -154,25 +154,77 @@ enum i915_mocs_table_index { I915_MOCS_CACHED, }; -/* +/** + * enum drm_i915_gem_engine_class - uapi engine type enumeration + * * Different engines serve different roles, and there may be more than one - * engine serving each role. enum drm_i915_gem_engine_class provides a - * classification of the role of the engine, which may be used when requesting - * operations to be performed on a certain subset of engines, or for providing - * information about that group. + * engine serving each role. This enum provides a classification of the role + * of the engine, which may be used when requesting operations to be performed + * on a certain subset of engines, or for providing information about that + * group. */ enum drm_i915_gem_engine_class { + /** + * @I915_ENGINE_CLASS_RENDER: + * + * Render engines support instructions used for 3D, Compute (GPGPU), + * and programmable media workloads. These instructions fetch data and + * dispatch individual work items to threads that operate in parallel. + * The threads run small programs (called "kernels" or "shaders") on + * the GPU's execution units (EUs). + */ I915_ENGINE_CLASS_RENDER = 0, + + /** + * @I915_ENGINE_CLASS_COPY: + * + * Copy engines (also referred to as "blitters") support instructions + * that move blocks of data from one location in memory to another, + * or that fill a specified location of memory with fixed data. + * Copy engines can perform pre-defined logical or bitwise operations + * on the source, destination, or pattern data. + */ I915_ENGINE_CLASS_COPY = 1, + + /** + * @I915_ENGINE_CLASS_VIDEO: + * + * Video engines (also referred to as "bit stream decode" (BSD) or + * "vdbox") support instructions that perform fixed-function media + * decode and encode. + */ I915_ENGINE_CLASS_VIDEO = 2, + + /** + * @I915_ENGINE_CLASS_VIDEO_ENHANCE: + * + * Video enhancement engines (also referred to as "vebox") support + * instructions related to image enhancement. + */ I915_ENGINE_CLASS_VIDEO_ENHANCE = 3, - /* should be kept compact */ + /** + * @I915_ENGINE_CLASS_COMPUTE: + * + * Compute engines support a subset of the instructions available + * on render engines: compute engines support Compute (GPGPU) and + * programmable media workloads, but do not support the 3D pipeline. + */ + I915_ENGINE_CLASS_COMPUTE = 4, + /* Values in this enum should be kept compact. */ + + /** + * @I915_ENGINE_CLASS_INVALID: + * + * Placeholder value to represent an invalid engine class assignment. + */ I915_ENGINE_CLASS_INVALID = -1 }; -/* +/** + * struct i915_engine_class_instance - Engine class/instance identifier + * * There may be more than one engine fulfilling any role within the system. * Each engine of a class is given a unique instance number and therefore * any engine can be specified by its class:instance tuplet. APIs that allow @@ -180,10 +232,21 @@ enum drm_i915_gem_engine_class { * for this identification. */ struct i915_engine_class_instance { - __u16 engine_class; /* see enum drm_i915_gem_engine_class */ - __u16 engine_instance; + /** + * @engine_class: + * + * Engine class from enum drm_i915_gem_engine_class + */ + __u16 engine_class; #define I915_ENGINE_CLASS_INVALID_NONE -1 #define I915_ENGINE_CLASS_INVALID_VIRTUAL -2 + + /** + * @engine_instance: + * + * Engine instance. + */ + __u16 engine_instance; }; /** @@ -2657,24 +2720,65 @@ enum drm_i915_perf_record_type { DRM_I915_PERF_RECORD_MAX /* non-ABI */ }; -/* +/** + * struct drm_i915_perf_oa_config + * * Structure to upload perf dynamic configuration into the kernel. */ struct drm_i915_perf_oa_config { - /** String formatted like "%08x-%04x-%04x-%04x-%012x" */ + /** + * @uuid: + * + * String formatted like "%\08x-%\04x-%\04x-%\04x-%\012x" + */ char uuid[36]; + /** + * @n_mux_regs: + * + * Number of mux regs in &mux_regs_ptr. + */ __u32 n_mux_regs; + + /** + * @n_boolean_regs: + * + * Number of boolean regs in &boolean_regs_ptr. + */ __u32 n_boolean_regs; + + /** + * @n_flex_regs: + * + * Number of flex regs in &flex_regs_ptr. + */ __u32 n_flex_regs; - /* - * These fields are pointers to tuples of u32 values (register address, - * value). For example the expected length of the buffer pointed by - * mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs). + /** + * @mux_regs_ptr: + * + * Pointer to tuples of u32 values (register address, value) for mux + * registers. Expected length of buffer is (2 * sizeof(u32) * + * &n_mux_regs). */ __u64 mux_regs_ptr; + + /** + * @boolean_regs_ptr: + * + * Pointer to tuples of u32 values (register address, value) for mux + * registers. Expected length of buffer is (2 * sizeof(u32) * + * &n_boolean_regs). + */ __u64 boolean_regs_ptr; + + /** + * @flex_regs_ptr: + * + * Pointer to tuples of u32 values (register address, value) for mux + * registers. Expected length of buffer is (2 * sizeof(u32) * + * &n_flex_regs). + */ __u64 flex_regs_ptr; }; @@ -2685,12 +2789,24 @@ struct drm_i915_perf_oa_config { * @data_ptr is also depends on the specific @query_id. */ struct drm_i915_query_item { - /** @query_id: The id for this query */ + /** + * @query_id: + * + * The id for this query. Currently accepted query IDs are: + * - %DRM_I915_QUERY_TOPOLOGY_INFO (see struct drm_i915_query_topology_info) + * - %DRM_I915_QUERY_ENGINE_INFO (see struct drm_i915_engine_info) + * - %DRM_I915_QUERY_PERF_CONFIG (see struct drm_i915_query_perf_config) + * - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions) + * - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`) + * - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info) + */ __u64 query_id; -#define DRM_I915_QUERY_TOPOLOGY_INFO 1 -#define DRM_I915_QUERY_ENGINE_INFO 2 -#define DRM_I915_QUERY_PERF_CONFIG 3 -#define DRM_I915_QUERY_MEMORY_REGIONS 4 +#define DRM_I915_QUERY_TOPOLOGY_INFO 1 +#define DRM_I915_QUERY_ENGINE_INFO 2 +#define DRM_I915_QUERY_PERF_CONFIG 3 +#define DRM_I915_QUERY_MEMORY_REGIONS 4 +#define DRM_I915_QUERY_HWCONFIG_BLOB 5 +#define DRM_I915_QUERY_GEOMETRY_SUBSLICES 6 /* Must be kept compact -- no holes and well documented */ /** @@ -2706,14 +2822,17 @@ struct drm_i915_query_item { /** * @flags: * - * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0. + * When &query_id == %DRM_I915_QUERY_TOPOLOGY_INFO, must be 0. * - * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the + * When &query_id == %DRM_I915_QUERY_PERF_CONFIG, must be one of the * following: * - * - DRM_I915_QUERY_PERF_CONFIG_LIST - * - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID - * - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID + * - %DRM_I915_QUERY_PERF_CONFIG_LIST + * - %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID + * - %DRM_I915_QUERY_PERF_CONFIG_FOR_UUID + * + * When &query_id == %DRM_I915_QUERY_GEOMETRY_SUBSLICES must contain + * a struct i915_engine_class_instance that references a render engine. */ __u32 flags; #define DRM_I915_QUERY_PERF_CONFIG_LIST 1 @@ -2771,66 +2890,112 @@ struct drm_i915_query { __u64 items_ptr; }; -/* - * Data written by the kernel with query DRM_I915_QUERY_TOPOLOGY_INFO : +/** + * struct drm_i915_query_topology_info * - * data: contains the 3 pieces of information : - * - * - the slice mask with one bit per slice telling whether a slice is - * available. The availability of slice X can be queried with the following - * formula : - * - * (data[X / 8] >> (X % 8)) & 1 - * - * - the subslice mask for each slice with one bit per subslice telling - * whether a subslice is available. Gen12 has dual-subslices, which are - * similar to two gen11 subslices. For gen12, this array represents dual- - * subslices. The availability of subslice Y in slice X can be queried - * with the following formula : - * - * (data[subslice_offset + - * X * subslice_stride + - * Y / 8] >> (Y % 8)) & 1 - * - * - the EU mask for each subslice in each slice with one bit per EU telling - * whether an EU is available. The availability of EU Z in subslice Y in - * slice X can be queried with the following formula : - * - * (data[eu_offset + - * (X * max_subslices + Y) * eu_stride + - * Z / 8] >> (Z % 8)) & 1 + * Describes slice/subslice/EU information queried by + * %DRM_I915_QUERY_TOPOLOGY_INFO */ struct drm_i915_query_topology_info { - /* + /** + * @flags: + * * Unused for now. Must be cleared to zero. */ __u16 flags; + /** + * @max_slices: + * + * The number of bits used to express the slice mask. + */ __u16 max_slices; + + /** + * @max_subslices: + * + * The number of bits used to express the subslice mask. + */ __u16 max_subslices; + + /** + * @max_eus_per_subslice: + * + * The number of bits in the EU mask that correspond to a single + * subslice's EUs. + */ __u16 max_eus_per_subslice; - /* + /** + * @subslice_offset: + * * Offset in data[] at which the subslice masks are stored. */ __u16 subslice_offset; - /* + /** + * @subslice_stride: + * * Stride at which each of the subslice masks for each slice are * stored. */ __u16 subslice_stride; - /* + /** + * @eu_offset: + * * Offset in data[] at which the EU masks are stored. */ __u16 eu_offset; - /* + /** + * @eu_stride: + * * Stride at which each of the EU masks for each subslice are stored. */ __u16 eu_stride; + /** + * @data: + * + * Contains 3 pieces of information : + * + * - The slice mask with one bit per slice telling whether a slice is + * available. The availability of slice X can be queried with the + * following formula : + * + * .. code:: c + * + * (data[X / 8] >> (X % 8)) & 1 + * + * Starting with Xe_HP platforms, Intel hardware no longer has + * traditional slices so i915 will always report a single slice + * (hardcoded slicemask = 0x1) which contains all of the platform's + * subslices. I.e., the mask here does not reflect any of the newer + * hardware concepts such as "gslices" or "cslices" since userspace + * is capable of inferring those from the subslice mask. + * + * - The subslice mask for each slice with one bit per subslice telling + * whether a subslice is available. Starting with Gen12 we use the + * term "subslice" to refer to what the hardware documentation + * describes as a "dual-subslices." The availability of subslice Y + * in slice X can be queried with the following formula : + * + * .. code:: c + * + * (data[subslice_offset + X * subslice_stride + Y / 8] >> (Y % 8)) & 1 + * + * - The EU mask for each subslice in each slice, with one bit per EU + * telling whether an EU is available. The availability of EU Z in + * subslice Y in slice X can be queried with the following formula : + * + * .. code:: c + * + * (data[eu_offset + + * (X * max_subslices + Y) * eu_stride + + * Z / 8 + * ] >> (Z % 8)) & 1 + */ __u8 data[]; }; @@ -2951,52 +3116,68 @@ struct drm_i915_query_engine_info { struct drm_i915_engine_info engines[]; }; -/* - * Data written by the kernel with query DRM_I915_QUERY_PERF_CONFIG. +/** + * struct drm_i915_query_perf_config + * + * Data written by the kernel with query %DRM_I915_QUERY_PERF_CONFIG and + * %DRM_I915_QUERY_GEOMETRY_SUBSLICES. */ struct drm_i915_query_perf_config { union { - /* - * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets - * this fields to the number of configurations available. + /** + * @n_configs: + * + * When &drm_i915_query_item.flags == + * %DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets this fields to + * the number of configurations available. */ __u64 n_configs; - /* - * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, - * i915 will use the value in this field as configuration - * identifier to decide what data to write into config_ptr. + /** + * @config: + * + * When &drm_i915_query_item.flags == + * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, i915 will use the + * value in this field as configuration identifier to decide + * what data to write into config_ptr. */ __u64 config; - /* - * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, - * i915 will use the value in this field as configuration - * identifier to decide what data to write into config_ptr. + /** + * @uuid: + * + * When &drm_i915_query_item.flags == + * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, i915 will use the + * value in this field as configuration identifier to decide + * what data to write into config_ptr. * * String formatted like "%08x-%04x-%04x-%04x-%012x" */ char uuid[36]; }; - /* + /** + * @flags: + * * Unused for now. Must be cleared to zero. */ __u32 flags; - /* - * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 will - * write an array of __u64 of configuration identifiers. + /** + * @data: * - * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_DATA, i915 will - * write a struct drm_i915_perf_oa_config. If the following fields of - * drm_i915_perf_oa_config are set not set to 0, i915 will write into - * the associated pointers the values of submitted when the + * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_LIST, + * i915 will write an array of __u64 of configuration identifiers. + * + * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_DATA, + * i915 will write a struct drm_i915_perf_oa_config. If the following + * fields of struct drm_i915_perf_oa_config are not set to 0, i915 will + * write into the associated pointers the values of submitted when the * configuration was created : * - * - n_mux_regs - * - n_boolean_regs - * - n_flex_regs + * - &drm_i915_perf_oa_config.n_mux_regs + * - &drm_i915_perf_oa_config.n_boolean_regs + * - &drm_i915_perf_oa_config.n_flex_regs */ __u8 data[]; }; @@ -3134,6 +3315,16 @@ struct drm_i915_query_memory_regions { struct drm_i915_memory_region_info regions[]; }; +/** + * DOC: GuC HWCONFIG blob uAPI + * + * The GuC produces a blob with information about the current device. + * i915 reads this blob from GuC and makes it available via this uAPI. + * + * The format and meaning of the blob content are documented in the + * Programmer's Reference Manual. + */ + /** * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added * extension support using struct i915_user_extension. From 4b3f7644ae84bcf785cc88d35327227cb2fb6b82 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 1 Jul 2021 13:39:15 -0300 Subject: [PATCH 3/9] tools headers cpufeatures: Sync with the kernel sources To pick the changes from: d6d0c7f681fda1d0 ("x86/cpufeatures: Add PerfMonV2 feature bit") 296d5a17e793956f ("KVM: SEV-ES: Use V_TSC_AUX if available instead of RDTSC/MSR_TSC_AUX intercepts") f30903394eb62316 ("x86/cpufeatures: Add virtual TSC_AUX feature bit") 8ad7e8f696951f19 ("x86/fpu/xsave: Support XSAVEC in the kernel") 59bd54a84d15e933 ("x86/tdx: Detect running as a TDX guest in early boot") a77d41ac3a0f41c8 ("x86/cpufeatures: Add AMD Fam19h Branch Sampling feature") This only causes these perf files to be rebuilt: CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o CC /tmp/build/perf/bench/mem-memset-x86-64-asm.o And addresses this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/disabled-features.h' differs from latest version at 'arch/x86/include/asm/disabled-features.h' diff -u tools/arch/x86/include/asm/disabled-features.h arch/x86/include/asm/disabled-features.h Cc: Peter Zijlstra Cc: Sandipan Das Cc: Babu Moger Cc: Paolo Bonzini Cc: Thomas Gleixner Cc: Dave Hansen Cc: Kuppuswamy Sathyanarayanan Cc: Stephane Eranian Cc: Peter Zijlstra Link: https://lore.kernel.org/lkml/YrDkgmwhLv+nKeOo@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/cpufeatures.h | 7 +++++-- tools/arch/x86/include/asm/disabled-features.h | 8 +++++++- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index e17de69faa54..03acc823838a 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -201,7 +201,7 @@ #define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -/* FREE! ( 7*32+10) */ +#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ @@ -211,7 +211,7 @@ #define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */ #define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */ #define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */ -/* FREE! ( 7*32+20) */ +#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* AMD Performance Monitoring Version 2 */ #define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */ #define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ @@ -238,6 +238,7 @@ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ #define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ #define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ +#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* Intel Trust Domain Extensions Guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -315,6 +316,7 @@ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ +#define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ @@ -405,6 +407,7 @@ #define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ #define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ /* diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 1ae0fab7d902..36369e76cc63 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -62,6 +62,12 @@ # define DISABLE_SGX (1 << (X86_FEATURE_SGX & 31)) #endif +#ifdef CONFIG_INTEL_TDX_GUEST +# define DISABLE_TDX_GUEST 0 +#else +# define DISABLE_TDX_GUEST (1 << (X86_FEATURE_TDX_GUEST & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -73,7 +79,7 @@ #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) -#define DISABLED_MASK8 0 +#define DISABLED_MASK8 (DISABLE_TDX_GUEST) #define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 From ab66fdace8581ef3b4e7cf5381a168ed4058d779 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 21 Jun 2022 15:51:44 +0300 Subject: [PATCH 4/9] perf build-id: Fix caching files with a wrong build ID Build ID events associate a file name with a build ID. However, when using perf inject, there is no guarantee that the file on the current machine at the current time has that build ID. Fix by comparing the build IDs and skip adding to the cache if they are different. Example: $ echo "int main() {return 0;}" > prog.c $ gcc -o prog prog.c $ perf record --buildid-all ./prog [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.019 MB perf.data ] $ file-buildid() { file $1 | awk -F= '{print $2}' | awk -F, '{print $1}' ; } $ file-buildid prog 444ad9be165d8058a48ce2ffb4e9f55854a3293e $ file-buildid ~/.debug/$(pwd)/prog/444ad9be165d8058a48ce2ffb4e9f55854a3293e/elf 444ad9be165d8058a48ce2ffb4e9f55854a3293e $ echo "int main() {return 1;}" > prog.c $ gcc -o prog prog.c $ file-buildid prog 885524d5aaa24008a3e2b06caa3ea95d013c0fc5 Before: $ perf buildid-cache --purge $(pwd)/prog $ perf inject -i perf.data -o junk $ file-buildid ~/.debug/$(pwd)/prog/444ad9be165d8058a48ce2ffb4e9f55854a3293e/elf 885524d5aaa24008a3e2b06caa3ea95d013c0fc5 $ After: $ perf buildid-cache --purge $(pwd)/prog $ perf inject -i perf.data -o junk $ file-buildid ~/.debug/$(pwd)/prog/444ad9be165d8058a48ce2ffb4e9f55854a3293e/elf $ Fixes: 454c407ec17a0c63 ("perf: add perf-inject builtin") Signed-off-by: Adrian Hunter Cc: Jiri Olsa Cc: Namhyung Kim Cc: Tom Zanussi Link: https://lore.kernel.org/r/20220621125144.5623-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/build-id.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index 82f3d46bea70..328668f38c69 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -872,6 +872,30 @@ int build_id_cache__remove_s(const char *sbuild_id) return err; } +static int filename__read_build_id_ns(const char *filename, + struct build_id *bid, + struct nsinfo *nsi) +{ + struct nscookie nsc; + int ret; + + nsinfo__mountns_enter(nsi, &nsc); + ret = filename__read_build_id(filename, bid); + nsinfo__mountns_exit(&nsc); + + return ret; +} + +static bool dso__build_id_mismatch(struct dso *dso, const char *name) +{ + struct build_id bid; + + if (filename__read_build_id_ns(name, &bid, dso->nsinfo) < 0) + return false; + + return !dso__build_id_equal(dso, &bid); +} + static int dso__cache_build_id(struct dso *dso, struct machine *machine, void *priv __maybe_unused) { @@ -886,6 +910,10 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine, is_kallsyms = true; name = machine->mmap_name; } + + if (!is_kallsyms && dso__build_id_mismatch(dso, name)) + return 0; + return build_id_cache__add_b(&dso->bid, name, dso->nsinfo, is_kallsyms, is_vdso); } From 3713e2494b6ab98f0476bb575b22323775f7d77a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 21 Jun 2022 12:34:37 -0300 Subject: [PATCH 5/9] perf trace beauty: Fix generation of errno id->str table on ALT Linux For some reason using: cat < Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/trace/beauty/arch_errno_names.sh | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh index 2c5f72fa8108..37c53bac5f56 100755 --- a/tools/perf/trace/beauty/arch_errno_names.sh +++ b/tools/perf/trace/beauty/arch_errno_names.sh @@ -33,23 +33,13 @@ create_errno_lookup_func() local arch=$(arch_string "$1") local nr name - cat < Date: Tue, 21 Jun 2022 15:27:25 +0000 Subject: [PATCH 6/9] perf inject: Adjust output data offset for backward compatibility When 'perf inject' creates a new file, it reuses the data offset from the input file. If there has been a change on the size of the header, as happened in v5.12 -> v5.13, the new offsets will be wrong, resulting in a corrupted output file. This change adds the function perf_session__data_offset to compute the data offset based on the current header size, and uses that instead of the offset from the original input file. Signed-off-by: Raul Silvera Acked-by: Adrian Hunter Cc: Alexander Shishkin Cc: Athira Jajeev Cc: Colin Ian King Cc: Dave Marchevsky Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220621152725.2668041-1-rsilvera@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-inject.c | 2 +- tools/perf/util/header.c | 14 ++++++++++++++ tools/perf/util/header.h | 2 ++ 3 files changed, 17 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 063f74f5b8db..54d4e508a092 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -918,7 +918,7 @@ static int __cmd_inject(struct perf_inject *inject) inject->tool.tracing_data = perf_event__repipe_tracing_data; } - output_data_offset = session->header.data_offset; + output_data_offset = perf_session__data_offset(session->evlist); if (inject->build_id_all) { inject->tool.mmap = perf_event__repipe_buildid_mmap; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 53332da100e8..6ad629db63b7 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -3686,6 +3686,20 @@ int perf_session__write_header(struct perf_session *session, return perf_session__do_write_header(session, evlist, fd, at_exit, NULL); } +size_t perf_session__data_offset(const struct evlist *evlist) +{ + struct evsel *evsel; + size_t data_offset; + + data_offset = sizeof(struct perf_file_header); + evlist__for_each_entry(evlist, evsel) { + data_offset += evsel->core.ids * sizeof(u64); + } + data_offset += evlist->core.nr_entries * sizeof(struct perf_file_attr); + + return data_offset; +} + int perf_session__inject_header(struct perf_session *session, struct evlist *evlist, int fd, diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 08563c1f1bff..56916dabce7b 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -136,6 +136,8 @@ int perf_session__inject_header(struct perf_session *session, int fd, struct feat_copier *fc); +size_t perf_session__data_offset(const struct evlist *evlist); + void perf_header__set_feat(struct perf_header *header, int feat); void perf_header__clear_feat(struct perf_header *header, int feat); bool perf_header__has_feat(const struct perf_header *header, int feat); From 448ce0e6ea93ae99e0b36055e5f5a3f723fe3665 Mon Sep 17 00:00:00 2001 From: Gang Li Date: Wed, 22 Jun 2022 11:00:37 +0800 Subject: [PATCH 7/9] perf stat: Enable ignore_missing_thread perf already support ignore_missing_thread for -p, but not yet applied to `perf stat -p `. This patch enables ignore_missing_thread for `perf stat -p `. Committer notes: And here is a refresher about the 'ignore_missing_thread' knob, from a previous patch using it: ca8000684ec4e66f ("perf evsel: Enable ignore_missing_thread for pid option") --- While monitoring a multithread process with pid option, perf sometimes may return sys_perf_event_open failure with 3(No such process) if any of the process's threads die before we open the event. However, we want perf continue monitoring the remaining threads and do not exit with error. --- Signed-off-by: Gang Li Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20220622030037.15005-1-ligang.bdlg@bytedance.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 4ce87a8eb7d7..d2ecd4d29624 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -2586,6 +2586,8 @@ int cmd_stat(int argc, const char **argv) if (evlist__initialize_ctlfd(evsel_list, stat_config.ctl_fd, stat_config.ctl_fd_ack)) goto out; + /* Enable ignoring missing threads when -p option is defined. */ + evlist__first(evsel_list)->ignore_missing_thread = target.pid; status = 0; for (run_idx = 0; forever || run_idx < stat_config.run_count; run_idx++) { if (stat_config.run_count != 1 && verbose > 0) From e2213a2dc63e1b2941728a9a938c2196548e980f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 14 Apr 2020 09:12:55 -0300 Subject: [PATCH 8/9] tools include UAPI: Sync linux/vhost.h with the kernel sources To get the changes in: 84d7c8fd3aade2fe ("vhost-vdpa: introduce uAPI to set group ASID") 2d1fcb7758e49fd9 ("vhost-vdpa: uAPI to get virtqueue group id") a0c95f201170bd55 ("vhost-vdpa: introduce uAPI to get the number of address spaces") 3ace88bd37436abc ("vhost-vdpa: introduce uAPI to get the number of virtqueue groups") 175d493c3c3e09a3 ("vhost: move the backend feature bits to vhost_types.h") Silencing this perf build warning: Warning: Kernel ABI header at 'tools/include/uapi/linux/vhost.h' differs from latest version at 'include/uapi/linux/vhost.h' diff -u tools/include/uapi/linux/vhost.h include/uapi/linux/vhost.h To pick up these changes and support them: $ tools/perf/trace/beauty/vhost_virtio_ioctl.sh > before $ cp include/uapi/linux/vhost.h tools/include/uapi/linux/vhost.h $ tools/perf/trace/beauty/vhost_virtio_ioctl.sh > after $ diff -u before after --- before 2022-06-26 12:04:35.982003781 -0300 +++ after 2022-06-26 12:04:43.819972476 -0300 @@ -28,6 +28,7 @@ [0x74] = "VDPA_SET_CONFIG", [0x75] = "VDPA_SET_VRING_ENABLE", [0x77] = "VDPA_SET_CONFIG_CALL", + [0x7C] = "VDPA_SET_GROUP_ASID", }; static const char *vhost_virtio_ioctl_read_cmds[] = { [0x00] = "GET_FEATURES", @@ -39,5 +40,8 @@ [0x76] = "VDPA_GET_VRING_NUM", [0x78] = "VDPA_GET_IOVA_RANGE", [0x79] = "VDPA_GET_CONFIG_SIZE", + [0x7A] = "VDPA_GET_AS_NUM", + [0x7B] = "VDPA_GET_VRING_GROUP", [0x80] = "VDPA_GET_VQS_COUNT", + [0x81] = "VDPA_GET_GROUP_NUM", }; $ Cc: Adrian Hunter Cc: Gautam Dawar Cc: Jiri Olsa Cc: Michael S. Tsirkin Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/Yrh3xMYbfeAD0MFL@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/vhost.h | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index 5d99e7c242a2..cab645d4a645 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -89,11 +89,6 @@ /* Set or get vhost backend capability */ -/* Use message type V2 */ -#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 -/* IOTLB can accept batching hints */ -#define VHOST_BACKEND_F_IOTLB_BATCH 0x2 - #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) #define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) @@ -150,11 +145,30 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) - /* Get the config size */ #define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) /* Get the count of all virtqueues */ #define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) + +/* Get the number of address spaces. */ +#define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int) + +/* Get the group for a virtqueue: read index, write group in num, + * The virtqueue index is stored in the index field of + * vhost_vring_state. The group for this specific virtqueue is + * returned via num field of vhost_vring_state. + */ +#define VHOST_VDPA_GET_VRING_GROUP _IOWR(VHOST_VIRTIO, 0x7B, \ + struct vhost_vring_state) +/* Set the ASID for a virtqueue group. The group index is stored in + * the index field of vhost_vring_state, the ASID associated with this + * group is stored at num field of vhost_vring_state. + */ +#define VHOST_VDPA_SET_GROUP_ASID _IOW(VHOST_VIRTIO, 0x7C, \ + struct vhost_vring_state) + #endif From f8d866194082e703c86751cceb07f6243cde96d2 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 21 Dec 2020 20:04:45 -0300 Subject: [PATCH 9/9] tools headers UAPI: Synch KVM's svm.h header with the kernel To pick up the changes from: d5af44dde5461d12 ("x86/sev: Provide support for SNP guest request NAEs") 0afb6b660a6b58cb ("x86/sev: Use SEV-SNP AP creation to start secondary CPUs") dc3f3d2474b80eae ("x86/mm: Validate memory when changing the C-bit") cbd3d4f7c4e5a93e ("x86/sev: Check SEV-SNP features support") That gets these new SVM exit reasons: + { SVM_VMGEXIT_PSC, "vmgexit_page_state_change" }, \ + { SVM_VMGEXIT_GUEST_REQUEST, "vmgexit_guest_request" }, \ + { SVM_VMGEXIT_EXT_GUEST_REQUEST, "vmgexit_ext_guest_request" }, \ + { SVM_VMGEXIT_AP_CREATION, "vmgexit_ap_creation" }, \ + { SVM_VMGEXIT_HV_FEATURES, "vmgexit_hypervisor_feature" }, \ Addressing this perf build warning: Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/svm.h' differs from latest version at 'arch/x86/include/uapi/asm/svm.h' diff -u tools/arch/x86/include/uapi/asm/svm.h arch/x86/include/uapi/asm/svm.h This causes these changes: CC /tmp/build/perf-urgent/arch/x86/util/kvm-stat.o LD /tmp/build/perf-urgent/arch/x86/util/perf-in.o LD /tmp/build/perf-urgent/arch/x86/perf-in.o LD /tmp/build/perf-urgent/arch/perf-in.o LD /tmp/build/perf-urgent/perf-in.o LINK /tmp/build/perf-urgent/perf Cc: Adrian Hunter Cc: Borislav Petkov Cc: Brijesh Singh Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Tom Lendacky Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/uapi/asm/svm.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h index efa969325ede..f69c168391aa 100644 --- a/tools/arch/x86/include/uapi/asm/svm.h +++ b/tools/arch/x86/include/uapi/asm/svm.h @@ -108,6 +108,14 @@ #define SVM_VMGEXIT_AP_JUMP_TABLE 0x80000005 #define SVM_VMGEXIT_SET_AP_JUMP_TABLE 0 #define SVM_VMGEXIT_GET_AP_JUMP_TABLE 1 +#define SVM_VMGEXIT_PSC 0x80000010 +#define SVM_VMGEXIT_GUEST_REQUEST 0x80000011 +#define SVM_VMGEXIT_EXT_GUEST_REQUEST 0x80000012 +#define SVM_VMGEXIT_AP_CREATION 0x80000013 +#define SVM_VMGEXIT_AP_CREATE_ON_INIT 0 +#define SVM_VMGEXIT_AP_CREATE 1 +#define SVM_VMGEXIT_AP_DESTROY 2 +#define SVM_VMGEXIT_HV_FEATURES 0x8000fffd #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff /* Exit code reserved for hypervisor/software use */ @@ -218,6 +226,11 @@ { SVM_VMGEXIT_NMI_COMPLETE, "vmgexit_nmi_complete" }, \ { SVM_VMGEXIT_AP_HLT_LOOP, "vmgexit_ap_hlt_loop" }, \ { SVM_VMGEXIT_AP_JUMP_TABLE, "vmgexit_ap_jump_table" }, \ + { SVM_VMGEXIT_PSC, "vmgexit_page_state_change" }, \ + { SVM_VMGEXIT_GUEST_REQUEST, "vmgexit_guest_request" }, \ + { SVM_VMGEXIT_EXT_GUEST_REQUEST, "vmgexit_ext_guest_request" }, \ + { SVM_VMGEXIT_AP_CREATION, "vmgexit_ap_creation" }, \ + { SVM_VMGEXIT_HV_FEATURES, "vmgexit_hypervisor_feature" }, \ { SVM_EXIT_ERR, "invalid_guest_state" }