@@ -543,9 +543,6 @@ static void md_end_flush(struct bio *bio
 	rdev_dec_pending(rdev, mddev);
 
 	if (atomic_dec_and_test(&mddev->flush_pending)) {
-		/* The pair is percpu_ref_get() from md_flush_request() */
-		percpu_ref_put(&mddev->active_io);
-
 		/* The pre-request flush has finished */
 		queue_work(md_wq, &mddev->flush_work);
 	}

@@ -565,7 +562,12 @@ static void submit_flushes(struct work_s
 	rdev_for_each_rcu(rdev, mddev)
 		if (rdev->raid_disk >= 0 &&
 		    !test_bit(Faulty, &rdev->flags)) {
+			/* Take two references, one is dropped
+			 * when request finishes, one after
+			 * we reclaim rcu_read_lock
+			 */
 			struct bio *bi;
+			atomic_inc(&rdev->nr_pending);
 
 			atomic_inc(&rdev->nr_pending);
 			rcu_read_unlock();

@@ -577,6 +579,7 @@ static void submit_flushes(struct work_s
 			atomic_inc(&mddev->flush_pending);
 			submit_bio(bi);
 			rcu_read_lock();
+			rdev_dec_pending(rdev, mddev);
 		}
 	rcu_read_unlock();
 	if (atomic_dec_and_test(&mddev->flush_pending))

@@ -629,18 +632,6 @@ bool md_flush_request(struct mddev *mdde
 	/* new request after previous flush is completed */
 	if (ktime_after(req_start, mddev->prev_flush_start)) {
 		WARN_ON(mddev->flush_bio);
-		/*
-		 * Grab a reference to make sure mddev_suspend() will wait for
-		 * this flush to be done.
-		 *
-		 * md_flush_reqeust() is called under md_handle_request() and
-		 * 'active_io' is already grabbed, hence percpu_ref_is_zero()
-		 * won't pass, percpu_ref_tryget_live() can't be used because
-		 * percpu_ref_kill() can be called by mddev_suspend()
-		 * concurrently.
-		 */
-		WARN_ON(percpu_ref_is_zero(&mddev->active_io));
-		percpu_ref_get(&mddev->active_io);
 		mddev->flush_bio = bio;
 		bio = NULL;
 	}