diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-07-16 17:13:31 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-07-16 17:13:31 -0700 |
commit | 576a997c6315ee482519e7cc080f341b07638808 (patch) | |
tree | 625cff628b8db0638ed496f560d38eda0375cacb /arch/x86/include | |
parent | 4a996d90b9e046c6d59845acf00a54d464c34ff3 (diff) | |
parent | fa0c1c9d283b37fdb7fc1dcccbb88fc8f48a4aa4 (diff) |
Merge tag 'perf-core-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull performance events updates from Ingo Molnar:
- Intel PT support enhancements & fixes
- Fix leaked SIGTRAP events
- Improve and fix the Intel uncore driver
- Add support for Intel HBM and CXL uncore counters
- Add Intel Lake and Arrow Lake support
- AMD uncore driver fixes
- Make SIGTRAP and __perf_pending_irq() work on RT
- Micro-optimizations
- Misc cleanups and fixes
* tag 'perf-core-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
perf/x86/intel: Add a distinct name for Granite Rapids
perf/x86/intel/ds: Fix non 0 retire latency on Raptorlake
perf/x86/intel: Hide Topdown metrics events if the feature is not enumerated
perf/x86/intel/uncore: Fix the bits of the CHA extended umask for SPR
perf: Split __perf_pending_irq() out of perf_pending_irq()
perf: Don't disable preemption in perf_pending_task().
perf: Move swevent_htable::recursion into task_struct.
perf: Shrink the size of the recursion counter.
perf: Enqueue SIGTRAP always via task_work.
task_work: Add TWA_NMI_CURRENT as an additional notify mode.
perf: Move irq_work_queue() where the event is prepared.
perf: Fix event leak upon exec and file release
perf: Fix event leak upon exit
task_work: Introduce task_work_cancel() again
task_work: s/task_work_cancel()/task_work_cancel_func()/
perf/x86/amd/uncore: Fix DF and UMC domain identification
perf/x86/amd/uncore: Avoid PMU registration if counters are unavailable
perf/x86/intel: Support Perfmon MSRs aliasing
perf/x86/intel: Support PERFEVTSEL extension
perf/x86: Add config_mask to represent EVENTSEL bitmask
...
Diffstat (limited to 'arch/x86/include')
-rw-r--r-- | arch/x86/include/asm/intel_ds.h | 1 | ||||
-rw-r--r-- | arch/x86/include/asm/msr-index.h | 6 | ||||
-rw-r--r-- | arch/x86/include/asm/perf_event.h | 8 |
3 files changed, 15 insertions, 0 deletions
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h index 2f9eeb5c3069..5dbeac48a5b9 100644 --- a/arch/x86/include/asm/intel_ds.h +++ b/arch/x86/include/asm/intel_ds.h @@ -9,6 +9,7 @@ /* The maximal number of PEBS events: */ #define MAX_PEBS_EVENTS_FMT4 8 #define MAX_PEBS_EVENTS 32 +#define MAX_PEBS_EVENTS_MASK GENMASK_ULL(MAX_PEBS_EVENTS - 1, 0) #define MAX_FIXED_PEBS_EVENTS 16 /* diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index e5069ddac222..82c6a4d350e0 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -566,6 +566,12 @@ #define MSR_RELOAD_PMC0 0x000014c1 #define MSR_RELOAD_FIXED_CTR0 0x00001309 +/* V6 PMON MSR range */ +#define MSR_IA32_PMC_V6_GP0_CTR 0x1900 +#define MSR_IA32_PMC_V6_GP0_CFG_A 0x1901 +#define MSR_IA32_PMC_V6_FX0_CTR 0x1980 +#define MSR_IA32_PMC_V6_STEP 4 + /* KeyID partitioning between MKTME and TDX */ #define MSR_IA32_MKTME_KEYID_PARTITIONING 0x00000087 diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 7f1e17250546..91b73571412f 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -32,6 +32,8 @@ #define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23) #define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL #define ARCH_PERFMON_EVENTSEL_BR_CNTR (1ULL << 35) +#define ARCH_PERFMON_EVENTSEL_EQ (1ULL << 36) +#define ARCH_PERFMON_EVENTSEL_UMASK2 (0xFFULL << 40) #define INTEL_FIXED_BITS_MASK 0xFULL #define INTEL_FIXED_BITS_STRIDE 4 @@ -185,6 +187,8 @@ union cpuid10_edx { * detection/enumeration details: */ #define ARCH_PERFMON_EXT_LEAF 0x00000023 +#define ARCH_PERFMON_EXT_UMASK2 0x1 +#define ARCH_PERFMON_EXT_EQ 0x2 #define ARCH_PERFMON_NUM_COUNTER_LEAF_BIT 0x1 #define ARCH_PERFMON_NUM_COUNTER_LEAF 0x1 @@ -307,6 +311,10 @@ struct x86_pmu_capability { #define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3) #define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS) +/* TOPDOWN_BAD_SPECULATION.ALL: fixed counter 4 (Atom only) */ +/* TOPDOWN_FE_BOUND.ALL: fixed counter 5 (Atom only) */ +/* TOPDOWN_RETIRING.ALL: fixed counter 6 (Atom only) */ + static inline bool use_fixed_pseudo_encoding(u64 code) { return !(code & 0xff); |