With commit cc27b0c78c79, pers->make_request could bail out without handling the bio. If that happens, we should retry. The commit fixes md_make_request but not other call sites. Separate the request handling part, so other call sites can use it.

Reported-by Nate Dailey <[email protected]>

Fix: cc27b0c78c79(md: fix deadlock between mddev_suspend() and md_write_start())

Reviewed-by NeilBrown <[email protected]>

Signed-off-by Shaohua Li <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/md/md.c |   58 +++++++++++++++++++++++++++++++-------------------------
 drivers/md/md.h |    1 
 2 files changed, 34 insertions(+), 25 deletions(-)

drivers/md/md.c +33 ~~-25~~

@@ -266,6 +266,37 @@ static DEFINE_SPINLOCK(all_mddevs_lock);
  * call has finished, the bio has been linked into some internal structure
  * and so is visible to ->quiesce(), so we don't need the refcount any more.
  */
+void md_handle_request(struct mddev *mddev, struct bio *bio)
+{
+check_suspended:
+	rcu_read_lock();
+	if (mddev->suspended) {
+		DEFINE_WAIT(__wait);
+		for (;;) {
+			prepare_to_wait(&mddev->sb_wait, &__wait,
+					TASK_UNINTERRUPTIBLE);
+			if (!mddev->suspended)
+				break;
+			rcu_read_unlock();
+			schedule();
+			rcu_read_lock();
+		}
+		finish_wait(&mddev->sb_wait, &__wait);
+	}
+	atomic_inc(&mddev->active_io);
+	rcu_read_unlock();
+
+	if (!mddev->pers->make_request(mddev, bio)) {
+		atomic_dec(&mddev->active_io);
+		wake_up(&mddev->sb_wait);
+		goto check_suspended;
+	}
+
+	if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
+		wake_up(&mddev->sb_wait);
+}
+EXPORT_SYMBOL(md_handle_request);
+
 static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);

@@ -285,23 +316,6 @@ static blk_qc_t md_make_request(struct r
 		bio_endio(bio);
 		return BLK_QC_T_NONE;
 	}
-check_suspended:
-	rcu_read_lock();
-	if (mddev->suspended) {
-		DEFINE_WAIT(__wait);
-		for (;;) {
-			prepare_to_wait(&mddev->sb_wait, &__wait,
-					TASK_UNINTERRUPTIBLE);
-			if (!mddev->suspended)
-				break;
-			rcu_read_unlock();
-			schedule();
-			rcu_read_lock();
-		}
-		finish_wait(&mddev->sb_wait, &__wait);
-	}
-	atomic_inc(&mddev->active_io);
-	rcu_read_unlock();
 
 	/*
 	 * save the sectors now since our bio can

@@ -310,20 +324,14 @@ check_suspended:
 	sectors = bio_sectors(bio);
 	/* bio could be mergeable after passing to underlayer */
 	bio->bi_opf &= ~REQ_NOMERGE;
-	if (!mddev->pers->make_request(mddev, bio)) {
-		atomic_dec(&mddev->active_io);
-		wake_up(&mddev->sb_wait);
-		goto check_suspended;
-	}
+
+	md_handle_request(mddev, bio);
 
 	cpu = part_stat_lock();
 	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
 	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
 	part_stat_unlock();
 
-	if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
-		wake_up(&mddev->sb_wait);
-
 	return BLK_QC_T_NONE;
 }

drivers/md/md.h +1 -0

@@ -686,6 +686,7 @@ extern void md_stop_writes(struct mddev
 extern int md_rdev_init(struct md_rdev *rdev);
 extern void md_rdev_clear(struct md_rdev *rdev);
 
+extern void md_handle_request(struct mddev *mddev, struct bio *bio);
 extern void mddev_suspend(struct mddev *mddev);
 extern void mddev_resume(struct mddev *mddev);
 extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,

Patches currently in stable-queue which might be from [email protected] are

queue-4.13/md-separate-request-handling.patch queue-4.13/md-raid5-preserve-stripe_on_unplug_list-in-break_stripe_batch_list.patch queue-4.13/md-fix-a-race-condition-for-flush-request-handling.patch queue-4.13/md-raid5-fix-a-race-condition-in-stripe-batch.patch