From 4cdb1b3ab96eb1b7eb70bc5c82fede334bd60df2 Mon Sep 17 00:00:00 2001 From: Taeyang Lee <0wn@theori.io> Date: Thu, 9 Jul 2026 23:29:58 +0900 Subject: [PATCH] perf/core: Detach event groups during remove_on_exec [ Upstream commit 037a3c43edfb597665dd34457cd22b14692f2ba3 ] 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) Link: https://patch.msgid.link/ai65GgZcC0LAlWLG@Taeyangs-MacBook-Pro.local Signed-off-by: Sasha Levin --- kernel/events/core.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 73a86db06cc9..d45bce2acdbc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4449,7 +4449,8 @@ out: 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 perf_event_context *ctx, + unsigned long detach_flags); /* * Removes all events from the current task that have been marked @@ -4476,7 +4477,7 @@ static void perf_event_remove_on_exec(struct perf_event_context *ctx) modified = true; - perf_event_exit_event(event, ctx); + perf_event_exit_event(event, ctx, DETACH_GROUP); } raw_spin_lock_irqsave(&ctx->lock, flags); @@ -13230,10 +13231,11 @@ static void sync_child_event(struct perf_event *child_event) } static void -perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx) +perf_event_exit_event(struct perf_event *event, + struct perf_event_context *ctx, + unsigned long detach_flags) { struct perf_event *parent_event = event->parent; - unsigned long detach_flags = 0; if (parent_event) { /* @@ -13248,7 +13250,7 @@ perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx) * Do destroy all inherited groups, we don't care about those * and being thorough is better. */ - detach_flags = DETACH_GROUP | DETACH_CHILD; + detach_flags |= DETACH_GROUP | DETACH_CHILD; mutex_lock(&parent_event->child_mutex); } @@ -13328,7 +13330,7 @@ static void perf_event_exit_task_context(struct task_struct *child) perf_event_task(child, child_ctx, 0); list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry) - perf_event_exit_event(child_event, child_ctx); + perf_event_exit_event(child_event, child_ctx, 0); mutex_unlock(&child_ctx->mutex);