md: fix deadlock in md/raid1 and md/raid10 when handling a read error

When handling a read error, we freeze the array to stop any other IO while
attempting to over-write with correct data.

This is done in the raid1d(raid10d) thread and must wait for all submitted IO
to complete (except for requests that failed and are sitting in the retry
queue - these are counted in ->nr_queue and will stay there during a freeze).

However write requests need attention from raid1d as bitmap updates might be
required.  This can cause a deadlock as raid1 is waiting for requests to
finish that themselves need attention from raid1d.

So we create a new function 'flush_pending_writes' to give that attention, and
call it in freeze_array to be sure that we aren't waiting on raid1d.

Thanks to "K.Tanaka" <k-tanaka@ce.jp.nec.com> for finding and reporting this
problem.

Cc: "K.Tanaka" <k-tanaka@ce.jp.nec.com>
Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 41 insertions, 21 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 5c7fef0..38f076a 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -592,6 +592,37 @@ static int raid1_congested(void *data, int bits)
 }
 
 
+static int flush_pending_writes(conf_t *conf)
+{
+	/* Any writes that have been queued but are awaiting
+	 * bitmap updates get flushed here.
+	 * We return 1 if any requests were actually submitted.
+	 */
+	int rv = 0;
+
+	spin_lock_irq(&conf->device_lock);
+
+	if (conf->pending_bio_list.head) {
+		struct bio *bio;
+		bio = bio_list_get(&conf->pending_bio_list);
+		blk_remove_plug(conf->mddev->queue);
+		spin_unlock_irq(&conf->device_lock);
+		/* flush any pending bitmap writes to
+		 * disk before proceeding w/ I/O */
+		bitmap_unplug(conf->mddev->bitmap);
+
+		while (bio) { /* submit pending writes */
+			struct bio *next = bio->bi_next;
+			bio->bi_next = NULL;
+			generic_make_request(bio);
+			bio = next;
+		}
+		rv = 1;
+	} else
+		spin_unlock_irq(&conf->device_lock);
+	return rv;
+}
+
 /* Barriers....
  * Sometimes we need to suspend IO while we do something else,
  * either some resync/recovery, or reconfigure the array.
@@ -681,7 +712,8 @@ static void freeze_array(conf_t *conf)
 	wait_event_lock_irq(conf->wait_barrier,
 			    conf->barrier+conf->nr_pending == conf->nr_queued+2,
 			    conf->resync_lock,
-			    raid1_unplug(conf->mddev->queue));
+			    ({ flush_pending_writes(conf);
+			       raid1_unplug(conf->mddev->queue); }));
 	spin_unlock_irq(&conf->resync_lock);
 }
 static void unfreeze_array(conf_t *conf)
@@ -907,6 +939,9 @@ static int make_request(struct request_queue *q, struct bio * bio)
 	blk_plug_device(mddev->queue);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
+	/* In case raid1d snuck into freeze_array */
+	wake_up(&conf->wait_barrier);
+
 	if (do_sync)
 		md_wakeup_thread(mddev->thread);
 #if 0
@@ -1473,28 +1508,14 @@ static void raid1d(mddev_t *mddev)
 	
 	for (;;) {
 		char b[BDEVNAME_SIZE];
-		spin_lock_irqsave(&conf->device_lock, flags);
-
-		if (conf->pending_bio_list.head) {
-			bio = bio_list_get(&conf->pending_bio_list);
-			blk_remove_plug(mddev->queue);
-			spin_unlock_irqrestore(&conf->device_lock, flags);
-			/* flush any pending bitmap writes to disk before proceeding w/ I/O */
-			bitmap_unplug(mddev->bitmap);
 
-			while (bio) { /* submit pending writes */
-				struct bio *next = bio->bi_next;
-				bio->bi_next = NULL;
-				generic_make_request(bio);
-				bio = next;
-			}
-			unplug = 1;
+		unplug += flush_pending_writes(conf);
 
-			continue;
-		}
-
-		if (list_empty(head))
+		spin_lock_irqsave(&conf->device_lock, flags);
+		if (list_empty(head)) {
+			spin_unlock_irqrestore(&conf->device_lock, flags);
 			break;
+		}
 		r1_bio = list_entry(head->prev, r1bio_t, retry_list);
 		list_del(head->prev);
 		conf->nr_queued--;
@@ -1590,7 +1611,6 @@ static void raid1d(mddev_t *mddev)
 			}
 		}
 	}
-	spin_unlock_irqrestore(&conf->device_lock, flags);
 	if (unplug)
 		unplug_slaves(mddev);
 }