perf/hw_breakpoint: Annotate tsk->perf_event_mutex vs ctx->mutex

Peter Zijlstra · Peter Zijlstra · commit 82aad7ff7ac2 · 2022-10-04T13:32:09.000+02:00
Perf fuzzer gifted a lockdep splat: perf_event_init_context() mutex_lock(parent_ctx->mutex); (B) inherit_task_group() inherit_group() inherit_event() perf_event_alloc() perf_try_init_event() := hw_breakpoint_event_init() register_perf_hw_breakpoint() mutex_lock(child->perf_event_mutex); (A) Which is against the normal (documented) order. Now, this is a false positive in that child is not published yet, but also inherited events never end up on ->perf_event_list. Annotate this one away. Fixes: 0912037 ("perf/hw_breakpoint: Reduce contention with large number of tasks") Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
@@ -117,7 +117,17 @@ static struct mutex *bp_constraints_lock(struct perf_event *bp)
 	struct mutex *tsk_mtx = get_task_bps_mutex(bp);
 
 	if (tsk_mtx) {
-		mutex_lock(tsk_mtx);
+		/*
+		 * Fully analogous to the perf_try_init_event() nesting
+		 * argument in the comment near perf_event_ctx_lock_nested();
+		 * this child->perf_event_mutex cannot ever deadlock against
+		 * the parent->perf_event_mutex usage from
+		 * perf_event_task_{en,dis}able().
+		 *
+		 * Specifically, inherited events will never occur on
+		 * ->perf_event_list.
+		 */
+		mutex_lock_nested(tsk_mtx, SINGLE_DEPTH_NESTING);
 		percpu_down_read(&bp_cpuinfo_sem);
 	} else {
 		percpu_down_write(&bp_cpuinfo_sem);
