There may be concurrency between perf_cgroup_switch and
perf_cgroup_event_disable. Consider the following scenario: after a new
perf cgroup event is created on CPU0, the new event might not trigger
reprogramm, leaving ctx->is_active as 0. In this case, when CPU1 disables
the perf event, it executes __perf_remove_from_context->list_del_event->
perf_cgroup_event_disable on CPU1, resulting in a race with
perf_cgroup_switch running on CPU0.

To fix this problem, expand the lock-holding critical section in
perf_cgroup_switch.

Fixes: db4a835601b7 ("perf/core: Set cgroup in CPU contexts for new cgroup events")
Signed-off-by: Luo Gengkun <luogengkun@huaweicloud.com>
---
 kernel/events/core.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index ecb4d852a006..fae1f68cbca5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -931,20 +931,20 @@ static void perf_cgroup_switch(struct task_struct *task)
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
 	struct perf_cgroup *cgrp;
 
+	cgrp = perf_cgroup_from_task(task, NULL);
+	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 	/*
 	 * cpuctx->cgrp is set when the first cgroup event enabled,
 	 * and is cleared when the last cgroup event disabled.
 	 */
 	if (READ_ONCE(cpuctx->cgrp) == NULL)
-		return;
+		goto unlock;
 
 	WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
 
-	cgrp = perf_cgroup_from_task(task, NULL);
 	if (READ_ONCE(cpuctx->cgrp) == cgrp)
-		return;
+		goto unlock;
 
-	perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 	perf_ctx_disable(&cpuctx->ctx, true);
 
 	ctx_sched_out(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
@@ -962,6 +962,7 @@ static void perf_cgroup_switch(struct task_struct *task)
 	ctx_sched_in(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
 
 	perf_ctx_enable(&cpuctx->ctx, true);
+unlock:
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
-- 
2.34.1