sbitmap: fix improper use of smp_mb__before_atomic()

commit a0934fd upstream.

This barrier only applies to the read-modify-write operations; in
particular, it does not apply to the atomic_set() primitive.

Replace the barrier with an smp_mb().

Fixes: 6c0ca7a ("sbitmap: fix wakeup hang after sbq resize")
Cc: [email protected]
Reported-by: "Paul E. McKenney" <[email protected]>
Reported-by: Peter Zijlstra <[email protected]>
Signed-off-by: Andrea Parri <[email protected]>
Reviewed-by: Ming Lei <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: Omar Sandoval <[email protected]>
Cc: Ming Lei <[email protected]>
Cc: [email protected]
Cc: "Paul E. McKenney" <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>

lib/sbitmap.c

@@ -338,7 +338,7 @@ void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth)
 		 * Pairs with the memory barrier in sbq_wake_up() to ensure that
 		 * the batch size is updated before the wait counts.
 		 */
-		smp_mb__before_atomic();
+		smp_mb();
 		for (i = 0; i < SBQ_WAIT_QUEUES; i++)
 			atomic_set(&sbq->ws[i].wait_cnt, 1);
 	}