Suggested by Roland.

do_wait(__WNOTHREAD) can only succeed if the caller is either ptracer, or
it is ->real_parent and the child is not traced. IOW, caller == p->parent
otherwise we should not wake up.

Change child_wait_callback() to check this. Ratan reports the workload with
CPU load >99% caused by unnecessary wakeups, should be fixed by this patch.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Roland McGrath <roland@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ratan Nalumasu <rnalumasu@gmail.com>
Cc: Vitaly Mayatskikh <vmayatsk@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

kernel/exit.c

@@ -1581,6 +1581,9 @@ static int child_wait_callback(wait_queue_t *wait, unsigned mode,
 	if (!eligible_child(wo, p))
 		return 0;
 
+	if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
+		return 0;
+
 	return default_wake_function(wait, mode, sync, key);
 }