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()

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;

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))

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;

kernel/events/core.c

@@ -4813,7 +4813,7 @@ static void __perf_event_read(void *info)
 	struct perf_event *sub, *event = data->event;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
-	struct pmu *pmu = event->pmu;
+	struct pmu *pmu;
 
 	/*
 	 * If this is a task context, we need to check whether it is
@@ -4825,7 +4825,7 @@ static void __perf_event_read(void *info)
 	if (ctx->task && cpuctx->task_ctx != ctx)
 		return;
 
-	raw_spin_lock(&ctx->lock);
+	guard(raw_spinlock)(&ctx->lock);
 	ctx_time_update_event(ctx, event);
 
 	perf_event_update_time(event);
@@ -4833,25 +4833,22 @@ static void __perf_event_read(void *info)
 		perf_event_update_sibling_time(event);
 
 	if (event->state != PERF_EVENT_STATE_ACTIVE)
-		goto unlock;
+		return;
 
 	if (!data->group) {
-		pmu->read(event);
+		perf_pmu_read(event);
 		data->ret = 0;
-		goto unlock;
+		return;
 	}
 
+	pmu = event->pmu_ctx->pmu;
 	pmu->start_txn(pmu, PERF_PMU_TXN_READ);
 
-	pmu->read(event);
-
+	perf_pmu_read(event);
 	for_each_sibling_event(sub, event)
 		perf_pmu_read(sub);
 
 	data->ret = pmu->commit_txn(pmu);
-
-unlock:
-	raw_spin_unlock(&ctx->lock);
 }
 
 static inline u64 perf_event_count(struct perf_event *event, bool self)
@@ -14744,7 +14741,7 @@ inherit_event(struct perf_event *parent_event,
 	get_ctx(child_ctx);
 	child_event->ctx = child_ctx;
 
-	pmu_ctx = find_get_pmu_context(child_event->pmu, child_ctx, child_event);
+	pmu_ctx = find_get_pmu_context(parent_event->pmu_ctx->pmu, child_ctx, child_event);
 	if (IS_ERR(pmu_ctx)) {
 		free_event(child_event);
 		return ERR_CAST(pmu_ctx);