[PATCH] md: fix deadlock due to md thread processing delayed requests.

Before completing a 'write' the md superblock might need to be updated.
This is best done by the md_thread.

The current code schedules this up and queues the write request for later
handling by the md_thread.

However some personalities (Raid5/raid6) will deadlock if the md_thread
tries to submit requests to its own array.

So this patch changes things so the processes submitting the request waits
for the superblock to be written and then submits the request itself.

This fixes a recently-created deadlock in raid5/raid6

Signed-off-by: Neil Brown <neilb@cse.unsw.edu.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

7 files changed, 23 insertions, 39 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 789b114f860a..7075bebb7f37 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -224,8 +224,8 @@ static mddev_t * mddev_find(dev_t unit)
 	INIT_LIST_HEAD(&new->all_mddevs);
 	init_timer(&new->safemode_timer);
 	atomic_set(&new->active, 1);
-	bio_list_init(&new->write_list);
 	spin_lock_init(&new->write_lock);
+	init_waitqueue_head(&new->sb_wait);
 
 	new->queue = blk_alloc_queue(GFP_KERNEL);
 	if (!new->queue) {
@@ -1307,6 +1307,7 @@ repeat:
 	if (!mddev->persistent) {
 		mddev->sb_dirty = 0;
 		spin_unlock(&mddev->write_lock);
+		wake_up(&mddev->sb_wait);
 		return;
 	}
 	spin_unlock(&mddev->write_lock);
@@ -1348,6 +1349,7 @@ repeat:
 	}
 	mddev->sb_dirty = 0;
 	spin_unlock(&mddev->write_lock);
+	wake_up(&mddev->sb_wait);
 
 }
 
@@ -3368,29 +3370,26 @@ void md_done_sync(mddev_t *mddev, int blocks, int ok)
 
 /* md_write_start(mddev, bi)
  * If we need to update some array metadata (e.g. 'active' flag
- * in superblock) before writing, queue bi for later writing
- * and return 0, else return 1 and it will be written now
+ * in superblock) before writing, schedule a superblock update
+ * and wait for it to complete.
  */
-int md_write_start(mddev_t *mddev, struct bio *bi)
+void md_write_start(mddev_t *mddev, struct bio *bi)
 {
+	DEFINE_WAIT(w);
 	if (bio_data_dir(bi) != WRITE)
-		return 1;
+		return;
 
 	atomic_inc(&mddev->writes_pending);
-	spin_lock(&mddev->write_lock);
-	if (mddev->in_sync == 0 && mddev->sb_dirty == 0) {
-		spin_unlock(&mddev->write_lock);
-		return 1;
-	}
-	bio_list_add(&mddev->write_list, bi);
-
 	if (mddev->in_sync) {
-		mddev->in_sync = 0;
-		mddev->sb_dirty = 1;
+		spin_lock(&mddev->write_lock);
+		if (mddev->in_sync) {
+			mddev->in_sync = 0;
+			mddev->sb_dirty = 1;
+			md_wakeup_thread(mddev->thread);
+		}
+		spin_unlock(&mddev->write_lock);
 	}
-	spin_unlock(&mddev->write_lock);
-	md_wakeup_thread(mddev->thread);
-	return 0;
+	wait_event(mddev->sb_wait, mddev->sb_dirty==0);
 }
 
 void md_write_end(mddev_t *mddev)
@@ -3685,7 +3684,6 @@ void md_check_recovery(mddev_t *mddev)
 		mddev->sb_dirty ||
 		test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
 		test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
-		mddev->write_list.head ||
 		(mddev->safemode == 1) ||
 		(mddev->safemode == 2 && ! atomic_read(&mddev->writes_pending)
 		 && !mddev->in_sync && mddev->recovery_cp == MaxSector)
@@ -3694,7 +3692,6 @@ void md_check_recovery(mddev_t *mddev)
 
 	if (mddev_trylock(mddev)==0) {
 		int spares =0;
-		struct bio *blist;
 
 		spin_lock(&mddev->write_lock);
 		if (mddev->safemode && !atomic_read(&mddev->writes_pending) &&
@@ -3704,21 +3701,11 @@ void md_check_recovery(mddev_t *mddev)
 		}
 		if (mddev->safemode == 1)
 			mddev->safemode = 0;
-		blist = bio_list_get(&mddev->write_list);
 		spin_unlock(&mddev->write_lock);
 
 		if (mddev->sb_dirty)
 			md_update_sb(mddev);
 
-		while (blist) {
-			struct bio *b = blist;
-			blist = blist->bi_next;
-			b->bi_next = NULL;
-			generic_make_request(b);
-			/* we already counted this, so need to un-count */
-			md_write_end(mddev);
-		}
-
 
 		if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
 		    !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) {
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 3f5234fe3593..98b09773e79e 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -561,8 +561,8 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	 * thread has put up a bar for new requests.
 	 * Continue immediately if no resync is active currently.
 	 */
-	if (md_write_start(mddev, bio)==0)
-		return 0;
+	md_write_start(mddev, bio); /* wait on superblock update early */
+
 	spin_lock_irq(&conf->resync_lock);
 	wait_event_lock_irq(conf->wait_resume, !conf->barrier, conf->resync_lock, );
 	conf->nr_pending++;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 8476515bfdc7..fd7324a86d13 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -700,8 +700,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
 		return 0;
 	}
 
-	if (md_write_start(mddev, bio) == 0)
-		return 0;
+	md_write_start(mddev, bio);
 
 	/*
 	 * Register the new request and wait if the reconstruction
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 1ce3f5aaa984..93a9726cc2d6 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1411,8 +1411,7 @@ static int make_request (request_queue_t *q, struct bio * bi)
 	sector_t logical_sector, last_sector;
 	struct stripe_head *sh;
 
-	if (md_write_start(mddev, bi)==0)
-		return 0;
+	md_write_start(mddev, bi);
 
 	if (bio_data_dir(bi)==WRITE) {
 		disk_stat_inc(mddev->gendisk, writes);
diff --git a/drivers/md/raid6main.c b/drivers/md/raid6main.c
index d9c385496dc5..f62ea1a73d0d 100644
--- a/drivers/md/raid6main.c
+++ b/drivers/md/raid6main.c
@@ -1570,8 +1570,7 @@ static int make_request (request_queue_t *q, struct bio * bi)
 	sector_t logical_sector, last_sector;
 	struct stripe_head *sh;
 
-	if (md_write_start(mddev, bi)==0)
-		return 0;
+	md_write_start(mddev, bi);
 
 	if (bio_data_dir(bi)==WRITE) {
 		disk_stat_inc(mddev->gendisk, writes);
diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h
index cfde8f497d6d..75f41d8faed2 100644
--- a/include/linux/raid/md.h
+++ b/include/linux/raid/md.h
@@ -69,7 +69,7 @@ extern mdk_thread_t * md_register_thread (void (*run) (mddev_t *mddev),
 extern void md_unregister_thread (mdk_thread_t *thread);
 extern void md_wakeup_thread(mdk_thread_t *thread);
 extern void md_check_recovery(mddev_t *mddev);
-extern int md_write_start(mddev_t *mddev, struct bio *bi);
+extern void md_write_start(mddev_t *mddev, struct bio *bi);
 extern void md_write_end(mddev_t *mddev);
 extern void md_handle_safemode(mddev_t *mddev);
 extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
index 6cdcb4434c6c..3e977025cf43 100644
--- a/include/linux/raid/md_k.h
+++ b/include/linux/raid/md_k.h
@@ -261,7 +261,7 @@ struct mddev_s
 	sector_t			recovery_cp;
 
 	spinlock_t			write_lock;
-	struct bio_list			write_list;
+	wait_queue_head_t		sb_wait;	/* for waiting on superblock updates */
 
 	unsigned int			safemode;	/* if set, update "clean" superblock
 							 * when no writes pending.