perf: Fix cgroup state vs ERROR

While chasing down a missing perf_cgroup_event_disable() elsewhere,
Leo Yan found that both perf_put_aux_event() and
perf_remove_sibling_event() were also missing one.

Specifically, the rule is that events that switch to OFF,ERROR need to
call perf_cgroup_event_disable().

Unify the disable paths to ensure this.

Fixes: ab43762ef010 ("perf: Allow normal events to output AUX data")
Fixes: 9f0c4fa111dc ("perf/core: Add a new PERF_EV_CAP_SIBLING event capability")
Reported-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250605123343.GD35970@noisy.programming.kicks-ass.net

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 26dec1d8a5ab64c1238c2cda5903cd0ea9326759..1cc98b9b3c0b4e0a1c561618c53039ca30eb430d 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2149,8 +2149,9 @@ perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event)
 }
 
 static void put_event(struct perf_event *event);
-static void event_sched_out(struct perf_event *event,
-                           struct perf_event_context *ctx);
+static void __event_disable(struct perf_event *event,
+                           struct perf_event_context *ctx,
+                           enum perf_event_state state);
 
 static void perf_put_aux_event(struct perf_event *event)
 {
@@ -2183,8 +2184,7 @@ static void perf_put_aux_event(struct perf_event *event)
                 * state so that we don't try to schedule it again. Note
                 * that perf_event_enable() will clear the ERROR status.
                 */
-               event_sched_out(iter, ctx);
-               perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+               __event_disable(iter, ctx, PERF_EVENT_STATE_ERROR);
        }
 }
 
@@ -2242,18 +2242,6 @@ static inline struct list_head *get_event_list(struct perf_event *event)
                                    &event->pmu_ctx->flexible_active;
 }
 
-/*
- * Events that have PERF_EV_CAP_SIBLING require being part of a group and
- * cannot exist on their own, schedule them out and move them into the ERROR
- * state. Also see _perf_event_enable(), it will not be able to recover
- * this ERROR state.
- */
-static inline void perf_remove_sibling_event(struct perf_event *event)
-{
-       event_sched_out(event, event->ctx);
-       perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
-}
-
 static void perf_group_detach(struct perf_event *event)
 {
        struct perf_event *leader = event->group_leader;
@@ -2289,8 +2277,15 @@ static void perf_group_detach(struct perf_event *event)
         */
        list_for_each_entry_safe(sibling, tmp, &event->sibling_list, sibling_list) {
 
+               /*
+                * Events that have PERF_EV_CAP_SIBLING require being part of
+                * a group and cannot exist on their own, schedule them out
+                * and move them into the ERROR state. Also see
+                * _perf_event_enable(), it will not be able to recover this
+                * ERROR state.
+                */
                if (sibling->event_caps & PERF_EV_CAP_SIBLING)
-                       perf_remove_sibling_event(sibling);
+                       __event_disable(sibling, ctx, PERF_EVENT_STATE_ERROR);
 
                sibling->group_leader = sibling;
                list_del_init(&sibling->sibling_list);
@@ -2562,6 +2557,15 @@ static void perf_remove_from_context(struct perf_event *event, unsigned long fla
        event_function_call(event, __perf_remove_from_context, (void *)flags);
 }
 
+static void __event_disable(struct perf_event *event,
+                           struct perf_event_context *ctx,
+                           enum perf_event_state state)
+{
+       event_sched_out(event, ctx);
+       perf_cgroup_event_disable(event, ctx);
+       perf_event_set_state(event, state);
+}
+
 /*
  * Cross CPU call to disable a performance event
  */
@@ -2576,13 +2580,18 @@ static void __perf_event_disable(struct perf_event *event,
        perf_pmu_disable(event->pmu_ctx->pmu);
        ctx_time_update_event(ctx, event);
 
+       /*
+        * When disabling a group leader, the whole group becomes ineligible
+        * to run, so schedule out the full group.
+        */
        if (event == event->group_leader)
                group_sched_out(event, ctx);
-       else
-               event_sched_out(event, ctx);
 
-       perf_event_set_state(event, PERF_EVENT_STATE_OFF);
-       perf_cgroup_event_disable(event, ctx);
+       /*
+        * But only mark the leader OFF; the siblings will remain
+        * INACTIVE.
+        */
+       __event_disable(event, ctx, PERF_EVENT_STATE_OFF);
 
        perf_pmu_enable(event->pmu_ctx->pmu);
 }