[tip: perf/urgent] perf: Make sure to use pmu_ctx->pmu for groups

[tip-bot2 for Peter Zijlstra]

The following commit has been merged into the perf/urgent branch of tip:

Commit-ID:     4b9ce671960627b2505b3f64742544ae9801df97
Gitweb:        https://git.kernel.org/tip/4b9ce671960627b2505b3f64742544ae9801df97
Author:        Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate:    Mon, 09 Mar 2026 13:55:46 +01:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Thu, 12 Mar 2026 11:29:16 +01:00

perf: Make sure to use pmu_ctx->pmu for groups

Oliver reported that x86_pmu_del() ended up doing an out-of-bound memory access
when group_sched_in() fails and needs to roll back.

This *should* be handled by the transaction callbacks, but he found that when
the group leader is a software event, the transaction handlers of the wrong PMU
are used. Despite the move_group case in perf_event_open() and group_sched_in()
using pmu_ctx->pmu.

Turns out, inherit uses event->pmu to clone the events, effectively undoing the
move_group case for all inherited contexts. Fix this by also making inherit use
pmu_ctx->pmu, ensuring all inherited counters end up in the same pmu context.

Similarly, __perf_event_read() should use equally use pmu_ctx->pmu for the
group case.

Fixes: bd2756811766 ("perf: Rewrite core context handling")
Reported-by: Oliver Rosenberg <olrose55@xxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Ian Rogers <irogers@xxxxxxxxxx>
Link: https://patch.msgid.link/20260309133713.GB606826@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
---
 kernel/events/core.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1f5699b..89b40e4 100644
--- a/kernel/events/core.c
+++ b/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);