1 files changed, 33 insertions, 22 deletions

diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 29eb0484215a..1f31147872e6 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -611,32 +611,43 @@ static bool __sbq_wake_up(struct sbitmap_queue *sbq)
 		return false;
 
 	wait_cnt = atomic_dec_return(&ws->wait_cnt);
-	if (wait_cnt <= 0) {
-		int ret;
+	/*
+	 * For concurrent callers of this, callers should call this function
+	 * again to wakeup a new batch on a different 'ws'.
+	 */
+	if (wait_cnt < 0 || !waitqueue_active(&ws->wait))
+		return true;
 
-		wake_batch = READ_ONCE(sbq->wake_batch);
+	if (wait_cnt > 0)
+		return false;
 
-		/*
-		 * Pairs with the memory barrier in sbitmap_queue_resize() to
-		 * ensure that we see the batch size update before the wait
-		 * count is reset.
-		 */
-		smp_mb__before_atomic();
+	wake_batch = READ_ONCE(sbq->wake_batch);
 
-		/*
-		 * For concurrent callers of this, the one that failed the
-		 * atomic_cmpxhcg() race should call this function again
-		 * to wakeup a new batch on a different 'ws'.
-		 */
-		ret = atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wake_batch);
-		if (ret == wait_cnt) {
-			sbq_index_atomic_inc(&sbq->wake_index);
-			wake_up_nr(&ws->wait, wake_batch);
-			return false;
-		}
+	/*
+	 * Wake up first in case that concurrent callers decrease wait_cnt
+	 * while waitqueue is empty.
+	 */
+	wake_up_nr(&ws->wait, wake_batch);
 
-		return true;
-	}
+	/*
+	 * Pairs with the memory barrier in sbitmap_queue_resize() to
+	 * ensure that we see the batch size update before the wait
+	 * count is reset.
+	 *
+	 * Also pairs with the implicit barrier between decrementing wait_cnt
+	 * and checking for waitqueue_active() to make sure waitqueue_active()
+	 * sees result of the wakeup if atomic_dec_return() has seen the result
+	 * of atomic_set().
+	 */
+	smp_mb__before_atomic();
+
+	/*
+	 * Increase wake_index before updating wait_cnt, otherwise concurrent
+	 * callers can see valid wait_cnt in old waitqueue, which can cause
+	 * invalid wakeup on the old waitqueue.
+	 */
+	sbq_index_atomic_inc(&sbq->wake_index);
+	atomic_set(&ws->wait_cnt, wake_batch);
 
 	return false;
 }