Merge tag 'md/3.13-fixes' of git://neil.brown.name/md

Pull late md fixes from Neil Brown:
 "Half a dozen md bug fixes.

  All of these fix real bugs the people have hit, and are tagged for
  -stable.  Sorry they are late ....  Christmas holidays and all that.
  Hopefully they can still squeak into 3.13"

* tag 'md/3.13-fixes' of git://neil.brown.name/md:
  md: fix problem when adding device to read-only array with bitmap.
  md/raid10: fix bug when raid10 recovery fails to recover a block.
  md/raid5: fix a recently broken BUG_ON().
  md/raid1: fix request counting bug in new 'barrier' code.
  md/raid10: fix two bugs in handling of known-bad-blocks.
  md/raid5: Fix possible confusion when multiple write errors occur.

5 files changed, 29 insertions, 14 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 21f4d7f..369d919 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1077,6 +1077,7 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 	rdev->raid_disk = -1;
 	clear_bit(Faulty, &rdev->flags);
 	clear_bit(In_sync, &rdev->flags);
+	clear_bit(Bitmap_sync, &rdev->flags);
 	clear_bit(WriteMostly, &rdev->flags);
 
 	if (mddev->raid_disks == 0) {
@@ -1155,6 +1156,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
 		 */
 		if (ev1 < mddev->bitmap->events_cleared)
 			return 0;
+		if (ev1 < mddev->events)
+			set_bit(Bitmap_sync, &rdev->flags);
 	} else {
 		if (ev1 < mddev->events)
 			/* just a hot-add of a new device, leave raid_disk at -1 */
@@ -1563,6 +1566,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 	rdev->raid_disk = -1;
 	clear_bit(Faulty, &rdev->flags);
 	clear_bit(In_sync, &rdev->flags);
+	clear_bit(Bitmap_sync, &rdev->flags);
 	clear_bit(WriteMostly, &rdev->flags);
 
 	if (mddev->raid_disks == 0) {
@@ -1645,6 +1649,8 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
 		 */
 		if (ev1 < mddev->bitmap->events_cleared)
 			return 0;
+		if (ev1 < mddev->events)
+			set_bit(Bitmap_sync, &rdev->flags);
 	} else {
 		if (ev1 < mddev->events)
 			/* just a hot-add of a new device, leave raid_disk at -1 */
@@ -2788,6 +2794,7 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
 		else
 			rdev->saved_raid_disk = -1;
 		clear_bit(In_sync, &rdev->flags);
+		clear_bit(Bitmap_sync, &rdev->flags);
 		err = rdev->mddev->pers->
 			hot_add_disk(rdev->mddev, rdev);
 		if (err) {
@@ -5760,6 +5767,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
 			    info->raid_disk < mddev->raid_disks) {
 				rdev->raid_disk = info->raid_disk;
 				set_bit(In_sync, &rdev->flags);
+				clear_bit(Bitmap_sync, &rdev->flags);
 			} else
 				rdev->raid_disk = -1;
 		} else
@@ -7706,7 +7714,8 @@ static int remove_and_add_spares(struct mddev *mddev,
 		if (test_bit(Faulty, &rdev->flags))
 			continue;
 		if (mddev->ro &&
-		    rdev->saved_raid_disk < 0)
+		    ! (rdev->saved_raid_disk >= 0 &&
+		       !test_bit(Bitmap_sync, &rdev->flags)))
 			continue;
 
 		rdev->recovery_offset = 0;
@@ -7787,9 +7796,12 @@ void md_check_recovery(struct mddev *mddev)
 			 * As we only add devices that are already in-sync,
 			 * we can activate the spares immediately.
 			 */
-			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			remove_and_add_spares(mddev, NULL);
-			mddev->pers->spare_active(mddev);
+			/* There is no thread, but we need to call
+			 * ->spare_active and clear saved_raid_disk
+			 */
+			md_reap_sync_thread(mddev);
+			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			goto unlock;
 		}
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 2f5cc8a..0095ec8 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -129,6 +129,9 @@ struct md_rdev {
 enum flag_bits {
 	Faulty,			/* device is known to have a fault */
 	In_sync,		/* device is in_sync with rest of array */
+	Bitmap_sync,		/* ..actually, not quite In_sync.  Need a
+				 * bitmap-based recovery to get fully in sync
+				 */
 	Unmerged,		/* device is being added to array and should
 				 * be considerred for bvec_merge_fn but not
 				 * yet for actual IO
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 1e5a540..a49cfcc 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -924,9 +924,8 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
 				conf->next_window_requests++;
 			else
 				conf->current_window_requests++;
-		}
-		if (bio->bi_sector >= conf->start_next_window)
 			sector = conf->start_next_window;
+		}
 	}
 
 	conf->nr_pending++;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index c504e83..06eeb99 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1319,7 +1319,7 @@ read_again:
 			/* Could not read all from this device, so we will
 			 * need another r10_bio.
 			 */
-			sectors_handled = (r10_bio->sectors + max_sectors
+			sectors_handled = (r10_bio->sector + max_sectors
 					   - bio->bi_sector);
 			r10_bio->sectors = max_sectors;
 			spin_lock_irq(&conf->device_lock);
@@ -1327,7 +1327,7 @@ read_again:
 				bio->bi_phys_segments = 2;
 			else
 				bio->bi_phys_segments++;
-			spin_unlock(&conf->device_lock);
+			spin_unlock_irq(&conf->device_lock);
 			/* Cannot call generic_make_request directly
 			 * as that will be queued in __generic_make_request
 			 * and subsequent mempool_alloc might block
@@ -3218,10 +3218,6 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 			if (j == conf->copies) {
 				/* Cannot recover, so abort the recovery or
 				 * record a bad block */
-				put_buf(r10_bio);
-				if (rb2)
-					atomic_dec(&rb2->remaining);
-				r10_bio = rb2;
 				if (any_working) {
 					/* problem is that there are bad blocks
 					 * on other device(s)
@@ -3253,6 +3249,10 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr,
 					mirror->recovery_disabled
 						= mddev->recovery_disabled;
 				}
+				put_buf(r10_bio);
+				if (rb2)
+					atomic_dec(&rb2->remaining);
+				r10_bio = rb2;
 				break;
 			}
 		}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index cc055da..cbb1571 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -687,7 +687,8 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
 			} else {
 				if (!test_bit(STRIPE_HANDLE, &sh->state))
 					atomic_inc(&conf->active_stripes);
-				BUG_ON(list_empty(&sh->lru));
+				BUG_ON(list_empty(&sh->lru) &&
+				       !test_bit(STRIPE_EXPANDING, &sh->state));
 				list_del_init(&sh->lru);
 				if (sh->group) {
 					sh->group->stripes_cnt--;
@@ -3608,7 +3609,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			 */
 			set_bit(R5_Insync, &dev->flags);
 
-		if (rdev && test_bit(R5_WriteError, &dev->flags)) {
+		if (test_bit(R5_WriteError, &dev->flags)) {
 			/* This flag does not apply to '.replacement'
 			 * only to .rdev, so make sure to check that*/
 			struct md_rdev *rdev2 = rcu_dereference(
@@ -3621,7 +3622,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			} else
 				clear_bit(R5_WriteError, &dev->flags);
 		}
-		if (rdev && test_bit(R5_MadeGood, &dev->flags)) {
+		if (test_bit(R5_MadeGood, &dev->flags)) {
 			/* This flag does not apply to '.replacement'
 			 * only to .rdev, so make sure to check that*/
 			struct md_rdev *rdev2 = rcu_dereference(