Merge tag 'md/4.3-fixes' of git://neil.brown.name/md

Pull md fixes from Neil Brown:
 "Assorted fixes for md in 4.3-rc.

  Two tagged for -stable, and one is really a cleanup to match and
  improve kmemcache interface.

* tag 'md/4.3-fixes' of git://neil.brown.name/md:
  md/bitmap: don't pass -1 to bitmap_storage_alloc.
  md/raid1: Avoid raid1 resync getting stuck
  md: drop null test before destroy functions
  md: clear CHANGE_PENDING in readonly array
  md/raid0: apply base queue limits *before* disk_stack_limits
  md/raid5: don't index beyond end of array in need_this_block().
  raid5: update analysis state for failed stripe
  md: wait for pending superblock updates before switching to read-only

7 files changed, 28 insertions, 26 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index e51de52eeb94..48b5890c28e3 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1997,7 +1997,8 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	if (bitmap->mddev->bitmap_info.offset || bitmap->mddev->bitmap_info.file)
 		ret = bitmap_storage_alloc(&store, chunks,
 					   !bitmap->mddev->bitmap_info.external,
-					   bitmap->cluster_slot);
+					   mddev_is_clustered(bitmap->mddev)
+					   ? bitmap->cluster_slot : 0);
 	if (ret)
 		goto err;
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4f5ecbe94ccb..c702de18207a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5409,9 +5409,13 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev)
 		 * which will now never happen */
 		wake_up_process(mddev->sync_thread->tsk);
 
+	if (mddev->external && test_bit(MD_CHANGE_PENDING, &mddev->flags))
+		return -EBUSY;
 	mddev_unlock(mddev);
 	wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING,
 					  &mddev->recovery));
+	wait_event(mddev->sb_wait,
+		   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
 	mddev_lock_nointr(mddev);
 
 	mutex_lock(&mddev->open_mutex);
@@ -8160,6 +8164,7 @@ void md_check_recovery(struct mddev *mddev)
 			md_reap_sync_thread(mddev);
 			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+			clear_bit(MD_CHANGE_PENDING, &mddev->flags);
 			goto unlock;
 		}
 
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index d222522c52e0..d132f06afdd1 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -470,8 +470,7 @@ static int multipath_run (struct mddev *mddev)
 	return 0;
 
 out_free_conf:
-	if (conf->pool)
-		mempool_destroy(conf->pool);
+	mempool_destroy(conf->pool);
 	kfree(conf->multipaths);
 	kfree(conf);
 	mddev->private = NULL;
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 63e619b2f44e..f8e5db0cb5aa 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -376,12 +376,6 @@ static int raid0_run(struct mddev *mddev)
 		struct md_rdev *rdev;
 		bool discard_supported = false;
 
-		rdev_for_each(rdev, mddev) {
-			disk_stack_limits(mddev->gendisk, rdev->bdev,
-					  rdev->data_offset << 9);
-			if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
-				discard_supported = true;
-		}
 		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
 		blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
 		blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
@@ -390,6 +384,12 @@ static int raid0_run(struct mddev *mddev)
 		blk_queue_io_opt(mddev->queue,
 				 (mddev->chunk_sectors << 9) * mddev->raid_disks);
 
+		rdev_for_each(rdev, mddev) {
+			disk_stack_limits(mddev->gendisk, rdev->bdev,
+					  rdev->data_offset << 9);
+			if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+				discard_supported = true;
+		}
 		if (!discard_supported)
 			queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
 		else
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 4517f06c41ba..049df6c4a8cc 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -881,8 +881,7 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
 	}
 
 	if (bio && bio_data_dir(bio) == WRITE) {
-		if (bio->bi_iter.bi_sector >=
-		    conf->mddev->curr_resync_completed) {
+		if (bio->bi_iter.bi_sector >= conf->next_resync) {
 			if (conf->start_next_window == MaxSector)
 				conf->start_next_window =
 					conf->next_resync +
@@ -1516,7 +1515,7 @@ static void close_sync(struct r1conf *conf)
 	conf->r1buf_pool = NULL;
 
 	spin_lock_irq(&conf->resync_lock);
-	conf->next_resync = 0;
+	conf->next_resync = MaxSector - 2 * NEXT_NORMALIO_DISTANCE;
 	conf->start_next_window = MaxSector;
 	conf->current_window_requests +=
 		conf->next_window_requests;
@@ -2843,8 +2842,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 
  abort:
 	if (conf) {
-		if (conf->r1bio_pool)
-			mempool_destroy(conf->r1bio_pool);
+		mempool_destroy(conf->r1bio_pool);
 		kfree(conf->mirrors);
 		safe_put_page(conf->tmppage);
 		kfree(conf->poolinfo);
@@ -2946,8 +2944,7 @@ static void raid1_free(struct mddev *mddev, void *priv)
 {
 	struct r1conf *conf = priv;
 
-	if (conf->r1bio_pool)
-		mempool_destroy(conf->r1bio_pool);
+	mempool_destroy(conf->r1bio_pool);
 	kfree(conf->mirrors);
 	safe_put_page(conf->tmppage);
 	kfree(conf->poolinfo);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 0fc33eb88855..7c99a4037715 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3486,8 +3486,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 		printk(KERN_ERR "md/raid10:%s: couldn't allocate memory.\n",
 		       mdname(mddev));
 	if (conf) {
-		if (conf->r10bio_pool)
-			mempool_destroy(conf->r10bio_pool);
+		mempool_destroy(conf->r10bio_pool);
 		kfree(conf->mirrors);
 		safe_put_page(conf->tmppage);
 		kfree(conf);
@@ -3682,8 +3681,7 @@ static int run(struct mddev *mddev)
 
 out_free_conf:
 	md_unregister_thread(&mddev->thread);
-	if (conf->r10bio_pool)
-		mempool_destroy(conf->r10bio_pool);
+	mempool_destroy(conf->r10bio_pool);
 	safe_put_page(conf->tmppage);
 	kfree(conf->mirrors);
 	kfree(conf);
@@ -3696,8 +3694,7 @@ static void raid10_free(struct mddev *mddev, void *priv)
 {
 	struct r10conf *conf = priv;
 
-	if (conf->r10bio_pool)
-		mempool_destroy(conf->r10bio_pool);
+	mempool_destroy(conf->r10bio_pool);
 	safe_put_page(conf->tmppage);
 	kfree(conf->mirrors);
 	kfree(conf->mirrors_old);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 15ef2c641b2b..49bb8d3ff9be 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2271,8 +2271,7 @@ static void shrink_stripes(struct r5conf *conf)
 	       drop_one_stripe(conf))
 		;
 
-	if (conf->slab_cache)
-		kmem_cache_destroy(conf->slab_cache);
+	kmem_cache_destroy(conf->slab_cache);
 	conf->slab_cache = NULL;
 }
 
@@ -3150,6 +3149,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 			spin_unlock_irq(&sh->stripe_lock);
 			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
 				wake_up(&conf->wait_for_overlap);
+			if (bi)
+				s->to_read--;
 			while (bi && bi->bi_iter.bi_sector <
 			       sh->dev[i].sector + STRIPE_SECTORS) {
 				struct bio *nextbi =
@@ -3169,6 +3170,8 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
 		 */
 		clear_bit(R5_LOCKED, &sh->dev[i].flags);
 	}
+	s->to_write = 0;
+	s->written = 0;
 
 	if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
 		if (atomic_dec_and_test(&conf->pending_full_writes))
@@ -3300,7 +3303,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 		 */
 		return 0;
 
-	for (i = 0; i < s->failed; i++) {
+	for (i = 0; i < s->failed && i < 2; i++) {
 		if (fdev[i]->towrite &&
 		    !test_bit(R5_UPTODATE, &fdev[i]->flags) &&
 		    !test_bit(R5_OVERWRITE, &fdev[i]->flags))
@@ -3324,7 +3327,7 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 	    sh->sector < sh->raid_conf->mddev->recovery_cp)
 		/* reconstruct-write isn't being forced */
 		return 0;
-	for (i = 0; i < s->failed; i++) {
+	for (i = 0; i < s->failed && i < 2; i++) {
 		if (s->failed_num[i] != sh->pd_idx &&
 		    s->failed_num[i] != sh->qd_idx &&
 		    !test_bit(R5_UPTODATE, &fdev[i]->flags) &&