diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-10 19:27:46 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-10 19:27:46 +0300 |
commit | 3871d93b82a4a6c1f4308064f046a544f16ada21 (patch) | |
tree | 99ef06b536798100cd7abb4753263505cc465215 /include/uapi | |
parent | 30c999937f69abf935b0228b8411713737377d9e (diff) | |
parent | 82aad7ff7ac25c8cf09d491ae23b9823f1901486 (diff) | |
download | linux-3871d93b82a4a6c1f4308064f046a544f16ada21.tar.xz |
Merge tag 'perf-core-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf events updates from Ingo Molnar:
"PMU driver updates:
- Add AMD Last Branch Record Extension Version 2 (LbrExtV2) feature
support for Zen 4 processors.
- Extend the perf ABI to provide branch speculation information, if
available, and use this on CPUs that have it (eg. LbrExtV2).
- Improve Intel PEBS TSC timestamp handling & integration.
- Add Intel Raptor Lake S CPU support.
- Add 'perf mem' and 'perf c2c' memory profiling support on AMD CPUs
by utilizing IBS tagged load/store samples.
- Clean up & optimize various x86 PMU details.
HW breakpoints:
- Big rework to optimize the code for systems with hundreds of CPUs
and thousands of breakpoints:
- Replace the nr_bp_mutex global mutex with the bp_cpuinfo_sem
per-CPU rwsem that is read-locked during most of the key
operations.
- Improve the O(#cpus * #tasks) logic in toggle_bp_slot() and
fetch_bp_busy_slots().
- Apply micro-optimizations & cleanups.
- Misc cleanups & enhancements"
* tag 'perf-core-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (75 commits)
perf/hw_breakpoint: Annotate tsk->perf_event_mutex vs ctx->mutex
perf: Fix pmu_filter_match()
perf: Fix lockdep_assert_event_ctx()
perf/x86/amd/lbr: Adjust LBR regardless of filtering
perf/x86/utils: Fix uninitialized var in get_branch_type()
perf/uapi: Define PERF_MEM_SNOOPX_PEER in kernel header file
perf/x86/amd: Support PERF_SAMPLE_PHY_ADDR
perf/x86/amd: Support PERF_SAMPLE_ADDR
perf/x86/amd: Support PERF_SAMPLE_{WEIGHT|WEIGHT_STRUCT}
perf/x86/amd: Support PERF_SAMPLE_DATA_SRC
perf/x86/amd: Add IBS OP_DATA2 DataSrc bit definitions
perf/mem: Introduce PERF_MEM_LVLNUM_{EXTN_MEM|IO}
perf/x86/uncore: Add new Raptor Lake S support
perf/x86/cstate: Add new Raptor Lake S support
perf/x86/msr: Add new Raptor Lake S support
perf/x86: Add new Raptor Lake S support
bpf: Check flags for branch stack in bpf_read_branch_records helper
perf, hw_breakpoint: Fix use-after-free if perf_event_open() fails
perf: Use sample_flags for raw_data
perf: Use sample_flags for addr
...
Diffstat (limited to 'include/uapi')
-rw-r--r-- | include/uapi/linux/perf_event.h | 57 |
1 files changed, 52 insertions, 5 deletions
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 03b370062741..85be78e0e7f6 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -164,8 +164,6 @@ enum perf_event_sample_format { PERF_SAMPLE_WEIGHT_STRUCT = 1U << 24, PERF_SAMPLE_MAX = 1U << 25, /* non-ABI */ - - __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; #define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT) @@ -204,6 +202,8 @@ enum perf_branch_sample_type_shift { PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT = 17, /* save low level index of raw branch records */ + PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT = 18, /* save privilege mode */ + PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ }; @@ -233,6 +233,8 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT, + PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; @@ -253,9 +255,48 @@ enum { PERF_BR_COND_RET = 10, /* conditional function return */ PERF_BR_ERET = 11, /* exception return */ PERF_BR_IRQ = 12, /* irq */ + PERF_BR_SERROR = 13, /* system error */ + PERF_BR_NO_TX = 14, /* not in transaction */ + PERF_BR_EXTEND_ABI = 15, /* extend ABI */ PERF_BR_MAX, }; +/* + * Common branch speculation outcome classification + */ +enum { + PERF_BR_SPEC_NA = 0, /* Not available */ + PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ + PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ + PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ + PERF_BR_SPEC_MAX, +}; + +enum { + PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ + PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ + PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */ + PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */ + PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */ + PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */ + PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */ + PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */ + PERF_BR_NEW_MAX, +}; + +enum { + PERF_BR_PRIV_UNKNOWN = 0, + PERF_BR_PRIV_USER = 1, + PERF_BR_PRIV_KERNEL = 2, + PERF_BR_PRIV_HV = 3, +}; + +#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 +#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 +#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 +#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 +#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 + #define PERF_SAMPLE_BRANCH_PLM_ALL \ (PERF_SAMPLE_BRANCH_USER|\ PERF_SAMPLE_BRANCH_KERNEL|\ @@ -1295,7 +1336,9 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ #define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ #define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -/* 5-0xa available */ +/* 5-0x8 available */ +#define PERF_MEM_LVLNUM_EXTN_MEM 0x09 /* Extension memory */ +#define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ #define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ #define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ @@ -1313,7 +1356,7 @@ union perf_mem_data_src { #define PERF_MEM_SNOOP_SHIFT 19 #define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ -/* 1 free */ +#define PERF_MEM_SNOOPX_PEER 0x02 /* xfer from peer */ #define PERF_MEM_SNOOPX_SHIFT 38 /* locked instruction */ @@ -1363,6 +1406,7 @@ union perf_mem_data_src { * abort: aborting a hardware transaction * cycles: cycles from last branch (or 0 if not supported) * type: branch type + * spec: branch speculation info (or 0 if not supported) */ struct perf_branch_entry { __u64 from; @@ -1373,7 +1417,10 @@ struct perf_branch_entry { abort:1, /* transaction abort */ cycles:16, /* cycle count to last branch */ type:4, /* branch type */ - reserved:40; + spec:2, /* branch speculation info */ + new_type:4, /* additional branch type */ + priv:3, /* privilege level */ + reserved:31; }; union perf_sample_weight { |