Kernel bump from 4.1.3-rt to 4.1.7-rt.

These changes brings a vanilla kernel from kernel.org, and the patch
applied for rt is patch-4.1.7-rt8.patch. No further changes needed.

Change-Id: Id8dd03c2ddd971e4d1d69b905f3069737053b700
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

15 files changed, 179 insertions, 93 deletions

diff --git a/kernel/drivers/md/bitmap.c b/kernel/drivers/md/bitmap.c
index 135a0907e..c90118e90 100644
--- a/kernel/drivers/md/bitmap.c
+++ b/kernel/drivers/md/bitmap.c
@@ -494,7 +494,7 @@ static int bitmap_new_disk_sb(struct bitmap *bitmap)
 	bitmap_super_t *sb;
 	unsigned long chunksize, daemon_sleep, write_behind;
 
-	bitmap->storage.sb_page = alloc_page(GFP_KERNEL);
+	bitmap->storage.sb_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (bitmap->storage.sb_page == NULL)
 		return -ENOMEM;
 	bitmap->storage.sb_page->index = 0;
@@ -541,6 +541,7 @@ static int bitmap_new_disk_sb(struct bitmap *bitmap)
 	sb->state = cpu_to_le32(bitmap->flags);
 	bitmap->events_cleared = bitmap->mddev->events;
 	sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
+	bitmap->mddev->bitmap_info.nodes = 0;
 
 	kunmap_atomic(sb);
 
@@ -611,8 +612,16 @@ re_read:
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
 	write_behind = le32_to_cpu(sb->write_behind);
 	sectors_reserved = le32_to_cpu(sb->sectors_reserved);
-	nodes = le32_to_cpu(sb->nodes);
-	strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
+	/* XXX: This is a hack to ensure that we don't use clustering
+	 *  in case:
+	 *	- dm-raid is in use and
+	 *	- the nodes written in bitmap_sb is erroneous.
+	 */
+	if (!bitmap->mddev->sync_super) {
+		nodes = le32_to_cpu(sb->nodes);
+		strlcpy(bitmap->mddev->bitmap_info.cluster_name,
+				sb->cluster_name, 64);
+	}
 
 	/* verify that the bitmap-specific fields are valid */
 	if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
diff --git a/kernel/drivers/md/dm-cache-policy-cleaner.c b/kernel/drivers/md/dm-cache-policy-cleaner.c
index b04d1f904..004e463c9 100644
--- a/kernel/drivers/md/dm-cache-policy-cleaner.c
+++ b/kernel/drivers/md/dm-cache-policy-cleaner.c
@@ -171,7 +171,8 @@ static void remove_cache_hash_entry(struct wb_cache_entry *e)
 /* Public interface (see dm-cache-policy.h */
 static int wb_map(struct dm_cache_policy *pe, dm_oblock_t oblock,
 		  bool can_block, bool can_migrate, bool discarded_oblock,
-		  struct bio *bio, struct policy_result *result)
+		  struct bio *bio, struct policy_locker *locker,
+		  struct policy_result *result)
 {
 	struct policy *p = to_policy(pe);
 	struct wb_cache_entry *e;
diff --git a/kernel/drivers/md/dm-cache-policy-internal.h b/kernel/drivers/md/dm-cache-policy-internal.h
index 2256a1f24..c198e6def 100644
--- a/kernel/drivers/md/dm-cache-policy-internal.h
+++ b/kernel/drivers/md/dm-cache-policy-internal.h
@@ -16,9 +16,10 @@
  */
 static inline int policy_map(struct dm_cache_policy *p, dm_oblock_t oblock,
 			     bool can_block, bool can_migrate, bool discarded_oblock,
-			     struct bio *bio, struct policy_result *result)
+			     struct bio *bio, struct policy_locker *locker,
+			     struct policy_result *result)
 {
-	return p->map(p, oblock, can_block, can_migrate, discarded_oblock, bio, result);
+	return p->map(p, oblock, can_block, can_migrate, discarded_oblock, bio, locker, result);
 }
 
 static inline int policy_lookup(struct dm_cache_policy *p, dm_oblock_t oblock, dm_cblock_t *cblock)
diff --git a/kernel/drivers/md/dm-cache-policy-mq.c b/kernel/drivers/md/dm-cache-policy-mq.c
index 3ddd11623..515d44bf2 100644
--- a/kernel/drivers/md/dm-cache-policy-mq.c
+++ b/kernel/drivers/md/dm-cache-policy-mq.c
@@ -693,9 +693,10 @@ static void requeue(struct mq_policy *mq, struct entry *e)
  * - set the hit count to a hard coded value other than 1, eg, is it better
  *   if it goes in at level 2?
  */
-static int demote_cblock(struct mq_policy *mq, dm_oblock_t *oblock)
+static int demote_cblock(struct mq_policy *mq,
+			 struct policy_locker *locker, dm_oblock_t *oblock)
 {
-	struct entry *demoted = pop(mq, &mq->cache_clean);
+	struct entry *demoted = peek(&mq->cache_clean);
 
 	if (!demoted)
 		/*
@@ -707,6 +708,13 @@ static int demote_cblock(struct mq_policy *mq, dm_oblock_t *oblock)
 		 */
 		return -ENOSPC;
 
+	if (locker->fn(locker, demoted->oblock))
+		/*
+		 * We couldn't lock the demoted block.
+		 */
+		return -EBUSY;
+
+	del(mq, demoted);
 	*oblock = demoted->oblock;
 	free_entry(&mq->cache_pool, demoted);
 
@@ -795,6 +803,7 @@ static int cache_entry_found(struct mq_policy *mq,
  * finding which cache block to use.
  */
 static int pre_cache_to_cache(struct mq_policy *mq, struct entry *e,
+			      struct policy_locker *locker,
 			      struct policy_result *result)
 {
 	int r;
@@ -803,11 +812,12 @@ static int pre_cache_to_cache(struct mq_policy *mq, struct entry *e,
 	/* Ensure there's a free cblock in the cache */
 	if (epool_empty(&mq->cache_pool)) {
 		result->op = POLICY_REPLACE;
-		r = demote_cblock(mq, &result->old_oblock);
+		r = demote_cblock(mq, locker, &result->old_oblock);
 		if (r) {
 			result->op = POLICY_MISS;
 			return 0;
 		}
+
 	} else
 		result->op = POLICY_NEW;
 
@@ -829,7 +839,8 @@ static int pre_cache_to_cache(struct mq_policy *mq, struct entry *e,
 
 static int pre_cache_entry_found(struct mq_policy *mq, struct entry *e,
 				 bool can_migrate, bool discarded_oblock,
-				 int data_dir, struct policy_result *result)
+				 int data_dir, struct policy_locker *locker,
+				 struct policy_result *result)
 {
 	int r = 0;
 
@@ -842,7 +853,7 @@ static int pre_cache_entry_found(struct mq_policy *mq, struct entry *e,
 
 	else {
 		requeue(mq, e);
-		r = pre_cache_to_cache(mq, e, result);
+		r = pre_cache_to_cache(mq, e, locker, result);
 	}
 
 	return r;
@@ -872,6 +883,7 @@ static void insert_in_pre_cache(struct mq_policy *mq,
 }
 
 static void insert_in_cache(struct mq_policy *mq, dm_oblock_t oblock,
+			    struct policy_locker *locker,
 			    struct policy_result *result)
 {
 	int r;
@@ -879,7 +891,7 @@ static void insert_in_cache(struct mq_policy *mq, dm_oblock_t oblock,
 
 	if (epool_empty(&mq->cache_pool)) {
 		result->op = POLICY_REPLACE;
-		r = demote_cblock(mq, &result->old_oblock);
+		r = demote_cblock(mq, locker, &result->old_oblock);
 		if (unlikely(r)) {
 			result->op = POLICY_MISS;
 			insert_in_pre_cache(mq, oblock);
@@ -907,11 +919,12 @@ static void insert_in_cache(struct mq_policy *mq, dm_oblock_t oblock,
 
 static int no_entry_found(struct mq_policy *mq, dm_oblock_t oblock,
 			  bool can_migrate, bool discarded_oblock,
-			  int data_dir, struct policy_result *result)
+			  int data_dir, struct policy_locker *locker,
+			  struct policy_result *result)
 {
 	if (adjusted_promote_threshold(mq, discarded_oblock, data_dir) <= 1) {
 		if (can_migrate)
-			insert_in_cache(mq, oblock, result);
+			insert_in_cache(mq, oblock, locker, result);
 		else
 			return -EWOULDBLOCK;
 	} else {
@@ -928,7 +941,8 @@ static int no_entry_found(struct mq_policy *mq, dm_oblock_t oblock,
  */
 static int map(struct mq_policy *mq, dm_oblock_t oblock,
 	       bool can_migrate, bool discarded_oblock,
-	       int data_dir, struct policy_result *result)
+	       int data_dir, struct policy_locker *locker,
+	       struct policy_result *result)
 {
 	int r = 0;
 	struct entry *e = hash_lookup(mq, oblock);
@@ -942,11 +956,11 @@ static int map(struct mq_policy *mq, dm_oblock_t oblock,
 
 	else if (e)
 		r = pre_cache_entry_found(mq, e, can_migrate, discarded_oblock,
-					  data_dir, result);
+					  data_dir, locker, result);
 
 	else
 		r = no_entry_found(mq, oblock, can_migrate, discarded_oblock,
-				   data_dir, result);
+				   data_dir, locker, result);
 
 	if (r == -EWOULDBLOCK)
 		result->op = POLICY_MISS;
@@ -1012,7 +1026,8 @@ static void copy_tick(struct mq_policy *mq)
 
 static int mq_map(struct dm_cache_policy *p, dm_oblock_t oblock,
 		  bool can_block, bool can_migrate, bool discarded_oblock,
-		  struct bio *bio, struct policy_result *result)
+		  struct bio *bio, struct policy_locker *locker,
+		  struct policy_result *result)
 {
 	int r;
 	struct mq_policy *mq = to_mq_policy(p);
@@ -1028,7 +1043,7 @@ static int mq_map(struct dm_cache_policy *p, dm_oblock_t oblock,
 
 	iot_examine_bio(&mq->tracker, bio);
 	r = map(mq, oblock, can_migrate, discarded_oblock,
-		bio_data_dir(bio), result);
+		bio_data_dir(bio), locker, result);
 
 	mutex_unlock(&mq->lock);
 
diff --git a/kernel/drivers/md/dm-cache-policy.h b/kernel/drivers/md/dm-cache-policy.h
index f50fe360c..5524e21e4 100644
--- a/kernel/drivers/md/dm-cache-policy.h
+++ b/kernel/drivers/md/dm-cache-policy.h
@@ -70,6 +70,18 @@ enum policy_operation {
 };
 
 /*
+ * When issuing a POLICY_REPLACE the policy needs to make a callback to
+ * lock the block being demoted.  This doesn't need to occur during a
+ * writeback operation since the block remains in the cache.
+ */
+struct policy_locker;
+typedef int (*policy_lock_fn)(struct policy_locker *l, dm_oblock_t oblock);
+
+struct policy_locker {
+	policy_lock_fn fn;
+};
+
+/*
  * This is the instruction passed back to the core target.
  */
 struct policy_result {
@@ -122,7 +134,8 @@ struct dm_cache_policy {
 	 */
 	int (*map)(struct dm_cache_policy *p, dm_oblock_t oblock,
 		   bool can_block, bool can_migrate, bool discarded_oblock,
-		   struct bio *bio, struct policy_result *result);
+		   struct bio *bio, struct policy_locker *locker,
+		   struct policy_result *result);
 
 	/*
 	 * Sometimes we want to see if a block is in the cache, without
diff --git a/kernel/drivers/md/dm-cache-target.c b/kernel/drivers/md/dm-cache-target.c
index 7755af351..e049becaa 100644
--- a/kernel/drivers/md/dm-cache-target.c
+++ b/kernel/drivers/md/dm-cache-target.c
@@ -1445,16 +1445,43 @@ static void inc_miss_counter(struct cache *cache, struct bio *bio)
 		   &cache->stats.read_miss : &cache->stats.write_miss);
 }
 
+/*----------------------------------------------------------------*/
+
+struct old_oblock_lock {
+	struct policy_locker locker;
+	struct cache *cache;
+	struct prealloc *structs;
+	struct dm_bio_prison_cell *cell;
+};
+
+static int null_locker(struct policy_locker *locker, dm_oblock_t b)
+{
+	/* This should never be called */
+	BUG();
+	return 0;
+}
+
+static int cell_locker(struct policy_locker *locker, dm_oblock_t b)
+{
+	struct old_oblock_lock *l = container_of(locker, struct old_oblock_lock, locker);
+	struct dm_bio_prison_cell *cell_prealloc = prealloc_get_cell(l->structs);
+
+	return bio_detain(l->cache, b, NULL, cell_prealloc,
+			  (cell_free_fn) prealloc_put_cell,
+			  l->structs, &l->cell);
+}
+
 static void process_bio(struct cache *cache, struct prealloc *structs,
 			struct bio *bio)
 {
 	int r;
 	bool release_cell = true;
 	dm_oblock_t block = get_bio_block(cache, bio);
-	struct dm_bio_prison_cell *cell_prealloc, *old_ocell, *new_ocell;
+	struct dm_bio_prison_cell *cell_prealloc, *new_ocell;
 	struct policy_result lookup_result;
 	bool passthrough = passthrough_mode(&cache->features);
 	bool discarded_block, can_migrate;
+	struct old_oblock_lock ool;
 
 	/*
 	 * Check to see if that block is currently migrating.
@@ -1469,8 +1496,12 @@ static void process_bio(struct cache *cache, struct prealloc *structs,
 	discarded_block = is_discarded_oblock(cache, block);
 	can_migrate = !passthrough && (discarded_block || spare_migration_bandwidth(cache));
 
+	ool.locker.fn = cell_locker;
+	ool.cache = cache;
+	ool.structs = structs;
+	ool.cell = NULL;
 	r = policy_map(cache->policy, block, true, can_migrate, discarded_block,
-		       bio, &lookup_result);
+		       bio, &ool.locker, &lookup_result);
 
 	if (r == -EWOULDBLOCK)
 		/* migration has been denied */
@@ -1527,27 +1558,11 @@ static void process_bio(struct cache *cache, struct prealloc *structs,
 		break;
 
 	case POLICY_REPLACE:
-		cell_prealloc = prealloc_get_cell(structs);
-		r = bio_detain(cache, lookup_result.old_oblock, bio, cell_prealloc,
-			       (cell_free_fn) prealloc_put_cell,
-			       structs, &old_ocell);
-		if (r > 0) {
-			/*
-			 * We have to be careful to avoid lock inversion of
-			 * the cells.  So we back off, and wait for the
-			 * old_ocell to become free.
-			 */
-			policy_force_mapping(cache->policy, block,
-					     lookup_result.old_oblock);
-			atomic_inc(&cache->stats.cache_cell_clash);
-			break;
-		}
 		atomic_inc(&cache->stats.demotion);
 		atomic_inc(&cache->stats.promotion);
-
 		demote_then_promote(cache, structs, lookup_result.old_oblock,
 				    block, lookup_result.cblock,
-				    old_ocell, new_ocell);
+				    ool.cell, new_ocell);
 		release_cell = false;
 		break;
 
@@ -2595,6 +2610,9 @@ static int __cache_map(struct cache *cache, struct bio *bio, struct dm_bio_priso
 	bool discarded_block;
 	struct policy_result lookup_result;
 	struct per_bio_data *pb = init_per_bio_data(bio, pb_data_size);
+	struct old_oblock_lock ool;
+
+	ool.locker.fn = null_locker;
 
 	if (unlikely(from_oblock(block) >= from_oblock(cache->origin_blocks))) {
 		/*
@@ -2633,7 +2651,7 @@ static int __cache_map(struct cache *cache, struct bio *bio, struct dm_bio_priso
 	discarded_block = is_discarded_oblock(cache, block);
 
 	r = policy_map(cache->policy, block, false, can_migrate, discarded_block,
-		       bio, &lookup_result);
+		       bio, &ool.locker, &lookup_result);
 	if (r == -EWOULDBLOCK) {
 		cell_defer(cache, *cell, true);
 		return DM_MAPIO_SUBMITTED;
diff --git a/kernel/drivers/md/dm-stats.c b/kernel/drivers/md/dm-stats.c
index f478a4c96..419bdd4fc 100644
--- a/kernel/drivers/md/dm-stats.c
+++ b/kernel/drivers/md/dm-stats.c
@@ -795,6 +795,8 @@ static int message_stats_create(struct mapped_device *md,
 		return -EINVAL;
 
 	if (sscanf(argv[2], "/%u%c", &divisor, &dummy) == 1) {
+		if (!divisor)
+			return -EINVAL;
 		step = end - start;
 		if (do_div(step, divisor))
 			step++;
diff --git a/kernel/drivers/md/dm-thin-metadata.c b/kernel/drivers/md/dm-thin-metadata.c
index 79f694120..cde1d6749 100644
--- a/kernel/drivers/md/dm-thin-metadata.c
+++ b/kernel/drivers/md/dm-thin-metadata.c
@@ -1295,8 +1295,8 @@ static int __release_metadata_snap(struct dm_pool_metadata *pmd)
 		return r;
 
 	disk_super = dm_block_data(copy);
-	dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->data_mapping_root));
-	dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->device_details_root));
+	dm_btree_del(&pmd->info, le64_to_cpu(disk_super->data_mapping_root));
+	dm_btree_del(&pmd->details_info, le64_to_cpu(disk_super->device_details_root));
 	dm_sm_dec_block(pmd->metadata_sm, held_root);
 
 	return dm_tm_unlock(pmd->tm, copy);
diff --git a/kernel/drivers/md/dm-thin.c b/kernel/drivers/md/dm-thin.c
index 921aafd12..e22e6c892 100644
--- a/kernel/drivers/md/dm-thin.c
+++ b/kernel/drivers/md/dm-thin.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <linux/sort.h>
 #include <linux/rbtree.h>
 
@@ -260,7 +261,7 @@ struct pool {
 	process_mapping_fn process_prepared_mapping;
 	process_mapping_fn process_prepared_discard;
 
-	struct dm_bio_prison_cell *cell_sort_array[CELL_SORT_ARRAY_SIZE];
+	struct dm_bio_prison_cell **cell_sort_array;
 };
 
 static enum pool_mode get_pool_mode(struct pool *pool);
@@ -2499,6 +2500,7 @@ static void __pool_destroy(struct pool *pool)
 {
 	__pool_table_remove(pool);
 
+	vfree(pool->cell_sort_array);
 	if (dm_pool_metadata_close(pool->pmd) < 0)
 		DMWARN("%s: dm_pool_metadata_close() failed.", __func__);
 
@@ -2611,6 +2613,13 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 		goto bad_mapping_pool;
 	}
 
+	pool->cell_sort_array = vmalloc(sizeof(*pool->cell_sort_array) * CELL_SORT_ARRAY_SIZE);
+	if (!pool->cell_sort_array) {
+		*error = "Error allocating cell sort array";
+		err_p = ERR_PTR(-ENOMEM);
+		goto bad_sort_array;
+	}
+
 	pool->ref_count = 1;
 	pool->last_commit_jiffies = jiffies;
 	pool->pool_md = pool_md;
@@ -2619,6 +2628,8 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 
 	return pool;
 
+bad_sort_array:
+	mempool_destroy(pool->mapping_pool);
 bad_mapping_pool:
 	dm_deferred_set_destroy(pool->all_io_ds);
 bad_all_io_ds:
diff --git a/kernel/drivers/md/dm.c b/kernel/drivers/md/dm.c
index 927523984..98347e2cf 100644
--- a/kernel/drivers/md/dm.c
+++ b/kernel/drivers/md/dm.c
@@ -1053,13 +1053,10 @@ static struct dm_rq_target_io *tio_from_request(struct request *rq)
  */
 static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
 {
-	int nr_requests_pending;
-
 	atomic_dec(&md->pending[rw]);
 
 	/* nudge anyone waiting on suspend queue */
-	nr_requests_pending = md_in_flight(md);
-	if (!nr_requests_pending)
+	if (!md_in_flight(md))
 		wake_up(&md->wait);
 
 	/*
@@ -1071,8 +1068,7 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
 	if (run_queue) {
 		if (md->queue->mq_ops)
 			blk_mq_run_hw_queues(md->queue, true);
-		else if (!nr_requests_pending ||
-			 (nr_requests_pending >= md->queue->nr_congestion_on))
+		else
 			blk_run_queue_async(md->queue);
 	}
 
@@ -1723,7 +1719,8 @@ static int dm_merge_bvec(struct request_queue *q,
 	struct mapped_device *md = q->queuedata;
 	struct dm_table *map = dm_get_live_table_fast(md);
 	struct dm_target *ti;
-	sector_t max_sectors, max_size = 0;
+	sector_t max_sectors;
+	int max_size = 0;
 
 	if (unlikely(!map))
 		goto out;
@@ -1736,18 +1733,10 @@ static int dm_merge_bvec(struct request_queue *q,
 	 * Find maximum amount of I/O that won't need splitting
 	 */
 	max_sectors = min(max_io_len(bvm->bi_sector, ti),
-			  (sector_t) queue_max_sectors(q));
+			  (sector_t) BIO_MAX_SECTORS);
 	max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size;
-
-	/*
-	 * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t
-	 * to the targets' merge function since it holds sectors not bytes).
-	 * Just doing this as an interim fix for stable@ because the more
-	 * comprehensive cleanup of switching to sector_t will impact every
-	 * DM target that implements a ->merge hook.
-	 */
-	if (max_size > INT_MAX)
-		max_size = INT_MAX;
+	if (max_size < 0)
+		max_size = 0;
 
 	/*
 	 * merge_bvec_fn() returns number of bytes
@@ -1755,13 +1744,13 @@ static int dm_merge_bvec(struct request_queue *q,
 	 * max is precomputed maximal io size
 	 */
 	if (max_size && ti->type->merge)
-		max_size = ti->type->merge(ti, bvm, biovec, (int) max_size);
+		max_size = ti->type->merge(ti, bvm, biovec, max_size);
 	/*
 	 * If the target doesn't support merge method and some of the devices
-	 * provided their merge_bvec method (we know this by looking for the
-	 * max_hw_sectors that dm_set_device_limits may set), then we can't
-	 * allow bios with multiple vector entries.  So always set max_size
-	 * to 0, and the code below allows just one page.
+	 * provided their merge_bvec method (we know this by looking at
+	 * queue_max_hw_sectors), then we can't allow bios with multiple vector
+	 * entries.  So always set max_size to 0, and the code below allows
+	 * just one page.
 	 */
 	else if (queue_max_hw_sectors(q) <= PAGE_SIZE >> 9)
 		max_size = 0;
diff --git a/kernel/drivers/md/md.c b/kernel/drivers/md/md.c
index 4dbed4a67..e4621511d 100644
--- a/kernel/drivers/md/md.c
+++ b/kernel/drivers/md/md.c
@@ -4005,8 +4005,10 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
 	else
 		rdev = md_import_device(dev, -1, -1);
 
-	if (IS_ERR(rdev))
+	if (IS_ERR(rdev)) {
+		mddev_unlock(mddev);
 		return PTR_ERR(rdev);
+	}
 	err = bind_rdev_to_array(rdev, mddev);
  out:
 	if (err)
@@ -5159,6 +5161,7 @@ int md_run(struct mddev *mddev)
 		mddev_detach(mddev);
 		if (mddev->private)
 			pers->free(mddev, mddev->private);
+		mddev->private = NULL;
 		module_put(pers->owner);
 		bitmap_destroy(mddev);
 		return err;
@@ -5294,6 +5297,7 @@ static void md_clean(struct mddev *mddev)
 	mddev->changed = 0;
 	mddev->degraded = 0;
 	mddev->safemode = 0;
+	mddev->private = NULL;
 	mddev->merge_check_needed = 0;
 	mddev->bitmap_info.offset = 0;
 	mddev->bitmap_info.default_offset = 0;
@@ -5366,6 +5370,7 @@ static void __md_stop(struct mddev *mddev)
 	mddev->pers = NULL;
 	spin_unlock(&mddev->lock);
 	pers->free(mddev, mddev->private);
+	mddev->private = NULL;
 	if (pers->sync_request && mddev->to_remove == NULL)
 		mddev->to_remove = &md_redundancy_group;
 	module_put(pers->owner);
@@ -5735,7 +5740,7 @@ static int get_bitmap_file(struct mddev *mddev, void __user * arg)
 	char *ptr;
 	int err;
 
-	file = kmalloc(sizeof(*file), GFP_NOIO);
+	file = kzalloc(sizeof(*file), GFP_NOIO);
 	if (!file)
 		return -ENOMEM;
 
@@ -6375,7 +6380,7 @@ static int update_array_info(struct mddev *mddev, mdu_array_info_t *info)
 	    mddev->ctime         != info->ctime         ||
 	    mddev->level         != info->level         ||
 /*	    mddev->layout        != info->layout        || */
-	    !mddev->persistent	 != info->not_persistent||
+	    mddev->persistent	 != !info->not_persistent ||
 	    mddev->chunk_sectors != info->chunk_size >> 9 ||
 	    /* ignore bottom 8 bits of state, and allow SB_BITMAP_PRESENT to change */
 	    ((state^info->state) & 0xfffffe00)
diff --git a/kernel/drivers/md/persistent-data/dm-btree-remove.c b/kernel/drivers/md/persistent-data/dm-btree-remove.c
index b88757cd0..a03178e91 100644
--- a/kernel/drivers/md/persistent-data/dm-btree-remove.c
+++ b/kernel/drivers/md/persistent-data/dm-btree-remove.c
@@ -309,8 +309,8 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent,
 
 		if (s < 0 && nr_center < -s) {
 			/* not enough in central node */
-			shift(left, center, nr_center);
-			s = nr_center - target;
+			shift(left, center, -nr_center);
+			s += nr_center;
 			shift(left, right, s);
 			nr_right += s;
 		} else
@@ -323,7 +323,7 @@ static void redistribute3(struct dm_btree_info *info, struct btree_node *parent,
 		if (s > 0 && nr_center < s) {
 			/* not enough in central node */
 			shift(center, right, nr_center);
-			s = target - nr_center;
+			s -= nr_center;
 			shift(left, right, s);
 			nr_left -= s;
 		} else
diff --git a/kernel/drivers/md/persistent-data/dm-btree.c b/kernel/drivers/md/persistent-data/dm-btree.c
index 200ac12a1..fdd3793e2 100644
--- a/kernel/drivers/md/persistent-data/dm-btree.c
+++ b/kernel/drivers/md/persistent-data/dm-btree.c
@@ -255,7 +255,7 @@ int dm_btree_del(struct dm_btree_info *info, dm_block_t root)
 	int r;
 	struct del_stack *s;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = kmalloc(sizeof(*s), GFP_NOIO);
 	if (!s)
 		return -ENOMEM;
 	s->info = info;
diff --git a/kernel/drivers/md/persistent-data/dm-space-map-metadata.c b/kernel/drivers/md/persistent-data/dm-space-map-metadata.c
index e8a904298..53091295f 100644
--- a/kernel/drivers/md/persistent-data/dm-space-map-metadata.c
+++ b/kernel/drivers/md/persistent-data/dm-space-map-metadata.c
@@ -204,6 +204,27 @@ static void in(struct sm_metadata *smm)
 	smm->recursion_count++;
 }
 
+static int apply_bops(struct sm_metadata *smm)
+{
+	int r = 0;
+
+	while (!brb_empty(&smm->uncommitted)) {
+		struct block_op bop;
+
+		r = brb_pop(&smm->uncommitted, &bop);
+		if (r) {
+			DMERR("bug in bop ring buffer");
+			break;
+		}
+
+		r = commit_bop(smm, &bop);
+		if (r)
+			break;
+	}
+
+	return r;
+}
+
 static int out(struct sm_metadata *smm)
 {
 	int r = 0;
@@ -216,21 +237,8 @@ static int out(struct sm_metadata *smm)
 		return -ENOMEM;
 	}
 
-	if (smm->recursion_count == 1) {
-		while (!brb_empty(&smm->uncommitted)) {
-			struct block_op bop;
-
-			r = brb_pop(&smm->uncommitted, &bop);
-			if (r) {
-				DMERR("bug in bop ring buffer");
-				break;
-			}
-
-			r = commit_bop(smm, &bop);
-			if (r)
-				break;
-		}
-	}
+	if (smm->recursion_count == 1)
+		apply_bops(smm);
 
 	smm->recursion_count--;
 
@@ -704,6 +712,12 @@ static int sm_metadata_extend(struct dm_space_map *sm, dm_block_t extra_blocks)
 		}
 		old_len = smm->begin;
 
+		r = apply_bops(smm);
+		if (r) {
+			DMERR("%s: apply_bops failed", __func__);
+			goto out;
+		}
+
 		r = sm_ll_commit(&smm->ll);
 		if (r)
 			goto out;
@@ -773,6 +787,12 @@ int dm_sm_metadata_create(struct dm_space_map *sm,
 	if (r)
 		return r;
 
+	r = apply_bops(smm);
+	if (r) {
+		DMERR("%s: apply_bops failed", __func__);
+		return r;
+	}
+
 	return sm_metadata_commit(sm);
 }
 
diff --git a/kernel/drivers/md/raid1.c b/kernel/drivers/md/raid1.c
index 9157a29c8..5ce3cd5c4 100644
--- a/kernel/drivers/md/raid1.c
+++ b/kernel/drivers/md/raid1.c
@@ -336,7 +336,7 @@ static void raid1_end_read_request(struct bio *bio, int error)
 		spin_lock_irqsave(&conf->device_lock, flags);
 		if (r1_bio->mddev->degraded == conf->raid_disks ||
 		    (r1_bio->mddev->degraded == conf->raid_disks-1 &&
-		     !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags)))
+		     test_bit(In_sync, &conf->mirrors[mirror].rdev->flags)))
 			uptodate = 1;
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
@@ -1475,6 +1475,7 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 {
 	char b[BDEVNAME_SIZE];
 	struct r1conf *conf = mddev->private;
+	unsigned long flags;
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
@@ -1494,14 +1495,13 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
 		return;
 	}
 	set_bit(Blocked, &rdev->flags);
+	spin_lock_irqsave(&conf->device_lock, flags);
 	if (test_and_clear_bit(In_sync, &rdev->flags)) {
-		unsigned long flags;
-		spin_lock_irqsave(&conf->device_lock, flags);
 		mddev->degraded++;
 		set_bit(Faulty, &rdev->flags);
-		spin_unlock_irqrestore(&conf->device_lock, flags);
 	} else
 		set_bit(Faulty, &rdev->flags);
+	spin_unlock_irqrestore(&conf->device_lock, flags);
 	/*
 	 * if recovery is running, make sure it aborts.
 	 */
@@ -1567,7 +1567,10 @@ static int raid1_spare_active(struct mddev *mddev)
 	 * Find all failed disks within the RAID1 configuration
 	 * and mark them readable.
 	 * Called under mddev lock, so rcu protection not needed.
+	 * device_lock used to avoid races with raid1_end_read_request
+	 * which expects 'In_sync' flags and ->degraded to be consistent.
 	 */
+	spin_lock_irqsave(&conf->device_lock, flags);
 	for (i = 0; i < conf->raid_disks; i++) {
 		struct md_rdev *rdev = conf->mirrors[i].rdev;
 		struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev;
@@ -1598,7 +1601,6 @@ static int raid1_spare_active(struct mddev *mddev)
 			sysfs_notify_dirent_safe(rdev->sysfs_state);
 		}
 	}
-	spin_lock_irqsave(&conf->device_lock, flags);
 	mddev->degraded -= count;
 	spin_unlock_irqrestore(&conf->device_lock, flags);