From: Taeyang Lee <0wn@theori.io>
Date: Sun, 14 Jun 2026 14:22:18 +0000 (+0900)
Subject: perf/core: Detach event groups during remove_on_exec
X-Git-Tag: v7.2-rc2~2^2~3
X-Git-Url: http://git.ipfire.org/index.cgi?a=commitdiff_plain;h=037a3c43edfb597665dd34457cd22b14692f2ba3;p=thirdparty%2Fkernel%2Flinux.git

perf/core: Detach event groups during remove_on_exec

perf_event_remove_on_exec() removes events by calling
perf_event_exit_event(). For top-level events, this removes the event from
the context with DETACH_EXIT only.

This can leave inconsistent group state when a removed event is a group
leader and the group contains siblings without remove_on_exec. If the group
was active, the surviving siblings can remain active and attached to the
removed leader's sibling list, but are no longer represented by a valid
group leader on the PMU context active lists.

A later close of the removed leader uses DETACH_GROUP and can promote the
still-active siblings from this stale group state. The next schedule-in can
then add an already-linked active_list entry again, corrupting the PMU
context active list.

With DEBUG_LIST enabled, this is caught as a list_add double-add in
merge_sched_in().

Fix this by detaching group relationships when remove_on_exec removes an
event. This preserves the existing task-exit and revoke behavior, while
ensuring surviving siblings are ungrouped before the removed event leaves
the context.

Fixes: 2e498d0a74e5 ("perf: Add support for event removal on exec")
Signed-off-by: Taeyang Lee <0wn@theori.io>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/ai65GgZcC0LAlWLG@Taeyangs-MacBook-Pro.local
---

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 954c36e28101..d7f3e2c2ecb1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4729,7 +4729,7 @@ static void perf_remove_from_owner(struct perf_event *event);
 static void perf_event_exit_event(struct perf_event *event,
 				  struct perf_event_context *ctx,
 				  struct task_struct *task,
-				  bool revoke);
+				  unsigned long detach_flags);
 
 /*
  * Removes all events from the current task that have been marked
@@ -4756,7 +4756,7 @@ static void perf_event_remove_on_exec(struct perf_event_context *ctx)
 
 		modified = true;
 
-		perf_event_exit_event(event, ctx, ctx->task, false);
+		perf_event_exit_event(event, ctx, ctx->task, DETACH_GROUP);
 	}
 
 	raw_spin_lock_irqsave(&ctx->lock, flags);
@@ -12937,7 +12937,7 @@ static void __pmu_detach_event(struct pmu *pmu, struct perf_event *event,
 	/*
 	 * De-schedule the event and mark it REVOKED.
 	 */
-	perf_event_exit_event(event, ctx, ctx->task, true);
+	perf_event_exit_event(event, ctx, ctx->task, DETACH_REVOKE);
 
 	/*
 	 * All _free_event() bits that rely on event->pmu:
@@ -14525,12 +14525,13 @@ static void
 perf_event_exit_event(struct perf_event *event,
 		      struct perf_event_context *ctx,
 		      struct task_struct *task,
-		      bool revoke)
+		      unsigned long detach_flags)
 {
 	struct perf_event *parent_event = event->parent;
-	unsigned long detach_flags = DETACH_EXIT;
 	unsigned int attach_state;
 
+	detach_flags |= DETACH_EXIT;
+
 	if (parent_event) {
 		/*
 		 * Do not destroy the 'original' grouping; because of the
@@ -14553,8 +14554,8 @@ perf_event_exit_event(struct perf_event *event,
 			sync_child_event(event, task);
 	}
 
-	if (revoke)
-		detach_flags |= DETACH_GROUP | DETACH_REVOKE;
+	if (detach_flags & DETACH_REVOKE)
+		detach_flags |= DETACH_GROUP;
 
 	perf_remove_from_context(event, detach_flags);
 	/*
@@ -14642,7 +14643,7 @@ static void perf_event_exit_task_context(struct task_struct *task, bool exit)
 		perf_event_task(task, ctx, 0);
 
 	list_for_each_entry_safe(child_event, next, &ctx->event_list, event_entry)
-		perf_event_exit_event(child_event, ctx, exit ? task : NULL, false);
+		perf_event_exit_event(child_event, ctx, exit ? task : NULL, 0);
 
 	mutex_unlock(&ctx->mutex);