diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-03-22 10:31:51 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-03-22 10:31:51 -0700 |
| commit | ebfd9b7af2fb1e4bbc97a8b33845e7402c3defa9 (patch) | |
| tree | f084f6b3e07b843bf625c60e8da3233b77913c6f /arch | |
| parent | dea622e183d34e6a4f90acfee9abb605885432bf (diff) | |
| parent | e7fcc54524f04e42641de99028edd9c69dc19f8c (diff) | |
Merge tag 'perf-urgent-2026-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf fixes from Ingo Molnar:
- Fix a PMU driver crash on AMD EPYC systems, caused by
a race condition in x86_pmu_enable()
- Fix a possible counter-initialization bug in x86_pmu_enable()
- Fix a counter inheritance bug in inherit_event() and
__perf_event_read()
- Fix an Intel PMU driver branch constraints handling bug
found by UBSAN
- Fix the Intel PMU driver's new Off-Module Response (OMR)
support code for Diamond Rapids / Nova lake, to fix a snoop
information parsing bug
* tag 'perf-urgent-2026-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel: Fix OMR snoop information parsing issues
perf/x86/intel: Add missing branch counters constraint apply
perf: Make sure to use pmu_ctx->pmu for groups
x86/perf: Make sure to program the counter value for stopped events on migration
perf/x86: Move event pointer setup earlier in x86_pmu_enable()
Diffstat (limited to 'arch')
| -rw-r--r-- | arch/x86/events/core.c | 7 | ||||
| -rw-r--r-- | arch/x86/events/intel/core.c | 31 | ||||
| -rw-r--r-- | arch/x86/events/intel/ds.c | 11 |
3 files changed, 33 insertions, 16 deletions
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 03ce1bc7ef2e..810ab21ffd99 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1372,14 +1372,17 @@ static void x86_pmu_enable(struct pmu *pmu) else if (i < n_running) continue; - if (hwc->state & PERF_HES_ARCH) + cpuc->events[hwc->idx] = event; + + if (hwc->state & PERF_HES_ARCH) { + static_call(x86_pmu_set_period)(event); continue; + } /* * if cpuc->enabled = 0, then no wrmsr as * per x86_pmu_enable_event() */ - cpuc->events[hwc->idx] = event; x86_pmu_start(event, PERF_EF_RELOAD); } cpuc->n_added = 0; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index cf3a4fe06ff2..36c68210d4d2 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4628,6 +4628,19 @@ static inline void intel_pmu_set_acr_caused_constr(struct perf_event *event, event->hw.dyn_constraint &= hybrid(event->pmu, acr_cause_mask64); } +static inline int intel_set_branch_counter_constr(struct perf_event *event, + int *num) +{ + if (branch_sample_call_stack(event)) + return -EINVAL; + if (branch_sample_counters(event)) { + (*num)++; + event->hw.dyn_constraint &= x86_pmu.lbr_counters; + } + + return 0; +} + static int intel_pmu_hw_config(struct perf_event *event) { int ret = x86_pmu_hw_config(event); @@ -4698,21 +4711,19 @@ static int intel_pmu_hw_config(struct perf_event *event) * group, which requires the extra space to store the counters. */ leader = event->group_leader; - if (branch_sample_call_stack(leader)) + if (intel_set_branch_counter_constr(leader, &num)) return -EINVAL; - if (branch_sample_counters(leader)) { - num++; - leader->hw.dyn_constraint &= x86_pmu.lbr_counters; - } leader->hw.flags |= PERF_X86_EVENT_BRANCH_COUNTERS; for_each_sibling_event(sibling, leader) { - if (branch_sample_call_stack(sibling)) + if (intel_set_branch_counter_constr(sibling, &num)) + return -EINVAL; + } + + /* event isn't installed as a sibling yet. */ + if (event != leader) { + if (intel_set_branch_counter_constr(event, &num)) return -EINVAL; - if (branch_sample_counters(sibling)) { - num++; - sibling->hw.dyn_constraint &= x86_pmu.lbr_counters; - } } if (num > fls(x86_pmu.lbr_counters)) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 5027afc97b65..7f0d515c07c5 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -345,12 +345,12 @@ static u64 parse_omr_data_source(u8 dse) if (omr.omr_remote) val |= REM; - val |= omr.omr_hitm ? P(SNOOP, HITM) : P(SNOOP, HIT); - if (omr.omr_source == 0x2) { - u8 snoop = omr.omr_snoop | omr.omr_promoted; + u8 snoop = omr.omr_snoop | (omr.omr_promoted << 1); - if (snoop == 0x0) + if (omr.omr_hitm) + val |= P(SNOOP, HITM); + else if (snoop == 0x0) val |= P(SNOOP, NA); else if (snoop == 0x1) val |= P(SNOOP, MISS); @@ -359,7 +359,10 @@ static u64 parse_omr_data_source(u8 dse) else if (snoop == 0x3) val |= P(SNOOP, NONE); } else if (omr.omr_source > 0x2 && omr.omr_source < 0x7) { + val |= omr.omr_hitm ? P(SNOOP, HITM) : P(SNOOP, HIT); val |= omr.omr_snoop ? P(SNOOPX, FWD) : 0; + } else { + val |= P(SNOOP, NONE); } return val; |
