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

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) <[email protected]>

Author: Peter Zijlstra

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);